diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX index 8c624a18f67d..7b52ba7bf32a 100644 --- a/Documentation/filesystems/00-INDEX +++ b/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 diff --git a/Documentation/filesystems/efivarfs.txt b/Documentation/filesystems/efivarfs.txt new file mode 100644 index 000000000000..c477af086e65 --- /dev/null +++ b/Documentation/filesystems/efivarfs.txt @@ -0,0 +1,16 @@ + +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 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 6e8fdf5ad113..fd13815fe85c 100644 --- a/arch/x86/include/asm/efi.h +++ b/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, diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index f84fe00fad48..d4f460f962ee 100644 --- a/arch/x86/kernel/tboot.c +++ b/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); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 2ead3c8a4c84..07519a120449 100644 --- a/arch/x86/mm/init_64.c +++ b/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); } } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 78fe3f1ac49f..e190f7b56653 100644 --- a/arch/x86/mm/ioremap.c +++ b/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. diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index a718e0d23503..931930a96160 100644 --- a/arch/x86/mm/pageattr.c +++ b/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); diff --git a/arch/x86/platform/efi/efi-bgrt.c b/arch/x86/platform/efi/efi-bgrt.c index f6a0c1b8e518..d9c1b95af17c 100644 --- a/arch/x86/platform/efi/efi-bgrt.c +++ b/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) diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index ad4439145f85..0a34d9e9c263 100644 --- a/arch/x86/platform/efi/efi.c +++ b/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(); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 95fd505dfeb6..06c8b2e662ab 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/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; diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index cbca565af5bd..8e6ab6137852 100644 --- a/arch/x86/realmode/init.c +++ b/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 } diff --git a/drivers/firmware/efivars.c b/drivers/firmware/efivars.c index 6e51c1e81f14..52c5d8956d7d 100644 --- a/drivers/firmware/efivars.c +++ b/drivers/firmware/efivars.c @@ -80,6 +80,10 @@ #include #include +#include +#include +#include + #include #define EFIVARS_VERSION "0.08" @@ -92,6 +96,12 @@ MODULE_VERSION(EFIVARS_VERSION); #define DUMP_NAME_LEN 52 +/* + * Length of a GUID string (strlen("aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee")) + * not including trailing NUL + */ +#define GUID_LEN 36 + /* * The maximum size of VariableName + Data = 1024 * Therefore, it's reasonable to save that much @@ -108,7 +118,6 @@ struct efi_variable { __u32 Attributes; } __attribute__((packed)); - struct efivar_entry { struct efivars *efivars; struct efi_variable var; @@ -122,6 +131,9 @@ struct efivar_attribute { ssize_t (*store)(struct efivar_entry *entry, const char *buf, size_t count); }; +static struct efivars __efivars; +static struct efivar_operations ops; + #define PSTORE_EFI_ATTRIBUTES \ (EFI_VARIABLE_NON_VOLATILE | \ EFI_VARIABLE_BOOTSERVICE_ACCESS | \ @@ -629,14 +641,482 @@ static struct kobj_type efivar_ktype = { .default_attrs = def_attrs, }; -static struct pstore_info efi_pstore_info; - static inline void efivar_unregister(struct efivar_entry *var) { kobject_put(&var->kobj); } +static int efivarfs_file_open(struct inode *inode, struct file *file) +{ + file->private_data = inode->i_private; + return 0; +} + +static int efi_status_to_err(efi_status_t status) +{ + int err; + + switch (status) { + case EFI_INVALID_PARAMETER: + err = -EINVAL; + break; + case EFI_OUT_OF_RESOURCES: + err = -ENOSPC; + break; + case EFI_DEVICE_ERROR: + err = -EIO; + break; + case EFI_WRITE_PROTECTED: + err = -EROFS; + break; + case EFI_SECURITY_VIOLATION: + err = -EACCES; + break; + case EFI_NOT_FOUND: + err = -ENOENT; + break; + default: + err = -EINVAL; + } + + return err; +} + +static ssize_t efivarfs_file_write(struct file *file, + const char __user *userbuf, size_t count, loff_t *ppos) +{ + struct efivar_entry *var = file->private_data; + struct efivars *efivars; + efi_status_t status; + void *data; + u32 attributes; + struct inode *inode = file->f_mapping->host; + unsigned long datasize = count - sizeof(attributes); + unsigned long newdatasize; + u64 storage_size, remaining_size, max_size; + ssize_t bytes = 0; + + if (count < sizeof(attributes)) + return -EINVAL; + + if (copy_from_user(&attributes, userbuf, sizeof(attributes))) + return -EFAULT; + + if (attributes & ~(EFI_VARIABLE_MASK)) + return -EINVAL; + + efivars = var->efivars; + + /* + * Ensure that the user can't allocate arbitrarily large + * amounts of memory. Pick a default size of 64K if + * QueryVariableInfo() isn't supported by the firmware. + */ + spin_lock(&efivars->lock); + + if (!efivars->ops->query_variable_info) + status = EFI_UNSUPPORTED; + else { + const struct efivar_operations *fops = efivars->ops; + status = fops->query_variable_info(attributes, &storage_size, + &remaining_size, &max_size); + } + + spin_unlock(&efivars->lock); + + if (status != EFI_SUCCESS) { + if (status != EFI_UNSUPPORTED) + return efi_status_to_err(status); + + remaining_size = 65536; + } + + if (datasize > remaining_size) + return -ENOSPC; + + data = kmalloc(datasize, GFP_KERNEL); + if (!data) + return -ENOMEM; + + if (copy_from_user(data, userbuf + sizeof(attributes), datasize)) { + bytes = -EFAULT; + goto out; + } + + if (validate_var(&var->var, data, datasize) == false) { + bytes = -EINVAL; + goto out; + } + + /* + * The lock here protects the get_variable call, the conditional + * set_variable call, and removal of the variable from the efivars + * list (in the case of an authenticated delete). + */ + spin_lock(&efivars->lock); + + status = efivars->ops->set_variable(var->var.VariableName, + &var->var.VendorGuid, + attributes, datasize, + data); + + if (status != EFI_SUCCESS) { + spin_unlock(&efivars->lock); + kfree(data); + + return efi_status_to_err(status); + } + + bytes = count; + + /* + * Writing to the variable may have caused a change in size (which + * could either be an append or an overwrite), or the variable to be + * deleted. Perform a GetVariable() so we can tell what actually + * happened. + */ + newdatasize = 0; + status = efivars->ops->get_variable(var->var.VariableName, + &var->var.VendorGuid, + NULL, &newdatasize, + NULL); + + if (status == EFI_BUFFER_TOO_SMALL) { + spin_unlock(&efivars->lock); + mutex_lock(&inode->i_mutex); + i_size_write(inode, newdatasize + sizeof(attributes)); + mutex_unlock(&inode->i_mutex); + + } else if (status == EFI_NOT_FOUND) { + list_del(&var->list); + spin_unlock(&efivars->lock); + efivar_unregister(var); + drop_nlink(inode); + dput(file->f_dentry); + + } else { + spin_unlock(&efivars->lock); + pr_warn("efivarfs: inconsistent EFI variable implementation? " + "status = %lx\n", status); + } + +out: + kfree(data); + + return bytes; +} + +static ssize_t efivarfs_file_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct efivar_entry *var = file->private_data; + struct efivars *efivars = var->efivars; + efi_status_t status; + unsigned long datasize = 0; + u32 attributes; + void *data; + ssize_t size = 0; + + spin_lock(&efivars->lock); + status = efivars->ops->get_variable(var->var.VariableName, + &var->var.VendorGuid, + &attributes, &datasize, NULL); + spin_unlock(&efivars->lock); + + if (status != EFI_BUFFER_TOO_SMALL) + return efi_status_to_err(status); + + data = kmalloc(datasize + sizeof(attributes), GFP_KERNEL); + + if (!data) + return -ENOMEM; + + spin_lock(&efivars->lock); + status = efivars->ops->get_variable(var->var.VariableName, + &var->var.VendorGuid, + &attributes, &datasize, + (data + sizeof(attributes))); + spin_unlock(&efivars->lock); + + if (status != EFI_SUCCESS) { + size = efi_status_to_err(status); + goto out_free; + } + + memcpy(data, &attributes, sizeof(attributes)); + size = simple_read_from_buffer(userbuf, count, ppos, + data, datasize + sizeof(attributes)); +out_free: + kfree(data); + + return size; +} + +static void efivarfs_evict_inode(struct inode *inode) +{ + clear_inode(inode); +} + +static const struct super_operations efivarfs_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .evict_inode = efivarfs_evict_inode, + .show_options = generic_show_options, +}; + +static struct super_block *efivarfs_sb; + +static const struct inode_operations efivarfs_dir_inode_operations; + +static const struct file_operations efivarfs_file_operations = { + .open = efivarfs_file_open, + .read = efivarfs_file_read, + .write = efivarfs_file_write, + .llseek = no_llseek, +}; + +static struct inode *efivarfs_get_inode(struct super_block *sb, + const struct inode *dir, int mode, dev_t dev) +{ + struct inode *inode = new_inode(sb); + + if (inode) { + inode->i_ino = get_next_ino(); + inode->i_uid = inode->i_gid = 0; + inode->i_mode = mode; + inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + switch (mode & S_IFMT) { + case S_IFREG: + inode->i_fop = &efivarfs_file_operations; + break; + case S_IFDIR: + inode->i_op = &efivarfs_dir_inode_operations; + inode->i_fop = &simple_dir_operations; + inc_nlink(inode); + break; + } + } + return inode; +} + +static void efivarfs_hex_to_guid(const char *str, efi_guid_t *guid) +{ + guid->b[0] = hex_to_bin(str[6]) << 4 | hex_to_bin(str[7]); + guid->b[1] = hex_to_bin(str[4]) << 4 | hex_to_bin(str[5]); + guid->b[2] = hex_to_bin(str[2]) << 4 | hex_to_bin(str[3]); + guid->b[3] = hex_to_bin(str[0]) << 4 | hex_to_bin(str[1]); + guid->b[4] = hex_to_bin(str[11]) << 4 | hex_to_bin(str[12]); + guid->b[5] = hex_to_bin(str[9]) << 4 | hex_to_bin(str[10]); + guid->b[6] = hex_to_bin(str[16]) << 4 | hex_to_bin(str[17]); + guid->b[7] = hex_to_bin(str[14]) << 4 | hex_to_bin(str[15]); + guid->b[8] = hex_to_bin(str[19]) << 4 | hex_to_bin(str[20]); + guid->b[9] = hex_to_bin(str[21]) << 4 | hex_to_bin(str[22]); + guid->b[10] = hex_to_bin(str[24]) << 4 | hex_to_bin(str[25]); + guid->b[11] = hex_to_bin(str[26]) << 4 | hex_to_bin(str[27]); + guid->b[12] = hex_to_bin(str[28]) << 4 | hex_to_bin(str[29]); + guid->b[13] = hex_to_bin(str[30]) << 4 | hex_to_bin(str[31]); + guid->b[14] = hex_to_bin(str[32]) << 4 | hex_to_bin(str[33]); + guid->b[15] = hex_to_bin(str[34]) << 4 | hex_to_bin(str[35]); +} + +static int efivarfs_create(struct inode *dir, struct dentry *dentry, + umode_t mode, bool excl) +{ + struct inode *inode; + struct efivars *efivars = &__efivars; + struct efivar_entry *var; + int namelen, i = 0, err = 0; + + /* + * We need a GUID, plus at least one letter for the variable name, + * plus the '-' separator + */ + if (dentry->d_name.len < GUID_LEN + 2) + return -EINVAL; + + inode = efivarfs_get_inode(dir->i_sb, dir, mode, 0); + if (!inode) + return -ENOMEM; + + var = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); + if (!var) { + err = -ENOMEM; + goto out; + } + + /* length of the variable name itself: remove GUID and separator */ + namelen = dentry->d_name.len - GUID_LEN - 1; + + efivarfs_hex_to_guid(dentry->d_name.name + namelen + 1, + &var->var.VendorGuid); + + for (i = 0; i < namelen; i++) + var->var.VariableName[i] = dentry->d_name.name[i]; + + var->var.VariableName[i] = '\0'; + + inode->i_private = var; + var->efivars = efivars; + var->kobj.kset = efivars->kset; + + err = kobject_init_and_add(&var->kobj, &efivar_ktype, NULL, "%s", + dentry->d_name.name); + if (err) + goto out; + + kobject_uevent(&var->kobj, KOBJ_ADD); + spin_lock(&efivars->lock); + list_add(&var->list, &efivars->list); + spin_unlock(&efivars->lock); + d_instantiate(dentry, inode); + dget(dentry); +out: + if (err) { + kfree(var); + iput(inode); + } + return err; +} + +static int efivarfs_unlink(struct inode *dir, struct dentry *dentry) +{ + struct efivar_entry *var = dentry->d_inode->i_private; + struct efivars *efivars = var->efivars; + efi_status_t status; + + spin_lock(&efivars->lock); + + status = efivars->ops->set_variable(var->var.VariableName, + &var->var.VendorGuid, + 0, 0, NULL); + + if (status == EFI_SUCCESS || status == EFI_NOT_FOUND) { + list_del(&var->list); + spin_unlock(&efivars->lock); + efivar_unregister(var); + drop_nlink(dir); + dput(dentry); + return 0; + } + + spin_unlock(&efivars->lock); + return -EINVAL; +}; + +static int efivarfs_fill_super(struct super_block *sb, void *data, int silent) +{ + struct inode *inode = NULL; + struct dentry *root; + struct efivar_entry *entry, *n; + struct efivars *efivars = &__efivars; + char *name; + + efivarfs_sb = sb; + + sb->s_maxbytes = MAX_LFS_FILESIZE; + sb->s_blocksize = PAGE_CACHE_SIZE; + sb->s_blocksize_bits = PAGE_CACHE_SHIFT; + sb->s_magic = EFIVARFS_MAGIC; + sb->s_op = &efivarfs_ops; + sb->s_time_gran = 1; + + inode = efivarfs_get_inode(sb, NULL, S_IFDIR | 0755, 0); + if (!inode) + return -ENOMEM; + inode->i_op = &efivarfs_dir_inode_operations; + + root = d_make_root(inode); + sb->s_root = root; + if (!root) + return -ENOMEM; + + list_for_each_entry_safe(entry, n, &efivars->list, list) { + struct dentry *dentry, *root = efivarfs_sb->s_root; + unsigned long size = 0; + int len, i; + + inode = NULL; + + len = utf16_strlen(entry->var.VariableName); + + /* name, plus '-', plus GUID, plus NUL*/ + name = kmalloc(len + 1 + GUID_LEN + 1, GFP_ATOMIC); + if (!name) + goto fail; + + for (i = 0; i < len; i++) + name[i] = entry->var.VariableName[i] & 0xFF; + + name[len] = '-'; + + efi_guid_unparse(&entry->var.VendorGuid, name + len + 1); + + name[len+GUID_LEN+1] = '\0'; + + inode = efivarfs_get_inode(efivarfs_sb, root->d_inode, + S_IFREG | 0644, 0); + if (!inode) + goto fail_name; + + dentry = d_alloc_name(root, name); + if (!dentry) + goto fail_inode; + + /* copied by the above to local storage in the dentry. */ + kfree(name); + + spin_lock(&efivars->lock); + efivars->ops->get_variable(entry->var.VariableName, + &entry->var.VendorGuid, + &entry->var.Attributes, + &size, + NULL); + spin_unlock(&efivars->lock); + + mutex_lock(&inode->i_mutex); + inode->i_private = entry; + i_size_write(inode, size+4); + mutex_unlock(&inode->i_mutex); + d_add(dentry, inode); + } + + return 0; + +fail_inode: + iput(inode); +fail_name: + kfree(name); +fail: + return -ENOMEM; +} + +static struct dentry *efivarfs_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data) +{ + return mount_single(fs_type, flags, data, efivarfs_fill_super); +} + +static void efivarfs_kill_sb(struct super_block *sb) +{ + kill_litter_super(sb); + efivarfs_sb = NULL; +} + +static struct file_system_type efivarfs_type = { + .name = "efivarfs", + .mount = efivarfs_mount, + .kill_sb = efivarfs_kill_sb, +}; + +static const struct inode_operations efivarfs_dir_inode_operations = { + .lookup = simple_lookup, + .unlink = efivarfs_unlink, + .create = efivarfs_create, +}; + +static struct pstore_info efi_pstore_info; + #ifdef CONFIG_PSTORE static int efi_pstore_open(struct pstore_info *psi) @@ -1065,11 +1545,18 @@ efivar_create_sysfs_entry(struct efivars *efivars, efi_char16_t *variable_name, efi_guid_t *vendor_guid) { - int i, short_name_size = variable_name_size / sizeof(efi_char16_t) + 38; + int i, short_name_size; char *short_name; struct efivar_entry *new_efivar; - short_name = kzalloc(short_name_size + 1, GFP_KERNEL); + /* + * Length of the variable bytes in ASCII, plus the '-' separator, + * plus the GUID, plus trailing NUL + */ + short_name_size = variable_name_size / sizeof(efi_char16_t) + + 1 + GUID_LEN + 1; + + short_name = kzalloc(short_name_size, GFP_KERNEL); new_efivar = kzalloc(sizeof(struct efivar_entry), GFP_KERNEL); if (!short_name || !new_efivar) { @@ -1189,6 +1676,7 @@ void unregister_efivars(struct efivars *efivars) sysfs_remove_bin_file(&efivars->kset->kobj, efivars->del_var); kfree(efivars->new_var); kfree(efivars->del_var); + kobject_put(efivars->kobject); kset_unregister(efivars->kset); } EXPORT_SYMBOL_GPL(unregister_efivars); @@ -1220,6 +1708,14 @@ int register_efivars(struct efivars *efivars, goto out; } + efivars->kobject = kobject_create_and_add("efivars", parent_kobj); + if (!efivars->kobject) { + pr_err("efivars: Subsystem registration failed.\n"); + error = -ENOMEM; + kset_unregister(efivars->kset); + goto out; + } + /* * Per EFI spec, the maximum storage allocated for both * the variable name and variable data is 1024 bytes. @@ -1262,6 +1758,8 @@ int register_efivars(struct efivars *efivars, pstore_register(&efivars->efi_pstore_info); } + register_filesystem(&efivarfs_type); + out: kfree(variable_name); @@ -1269,9 +1767,6 @@ out: } EXPORT_SYMBOL_GPL(register_efivars); -static struct efivars __efivars; -static struct efivar_operations ops; - /* * For now we register the efi subsystem with the firmware subsystem * and the vars subsystem with the efi subsystem. In the future, it @@ -1302,6 +1797,7 @@ efivars_init(void) ops.set_variable = efi.set_variable; ops.get_next_variable = efi.get_next_variable; ops.query_variable_info = efi.query_variable_info; + error = register_efivars(&__efivars, &ops, efi_kobj); if (error) goto err_put; diff --git a/include/linux/efi.h b/include/linux/efi.h index b02099d0b4fc..02a69418be18 100644 --- a/include/linux/efi.h +++ b/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; diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index e15192cb9cf4..12f68c7ceba6 100644 --- a/include/uapi/linux/magic.h +++ b/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 */ diff --git a/init/main.c b/init/main.c index 63ae904a99a8..6af5470b8067 100644 --- a/init/main.c +++ b/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);