aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-12-14 10:08:40 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2012-12-14 10:08:40 -0800
commitd42b3a2906a10b732ea7d7f849d49be79d242ef0 (patch)
tree1f4f2387bf53f8015aa87eb9c05ba8316cb5ed50
parent18dd0bf22b6f0c1bd5e4e813a42245ed86ec57b6 (diff)
parente83af1f18c78c7b6aa720beecc927ecc8afd3647 (diff)
downloadvexpress-lsk-d42b3a2906a10b732ea7d7f849d49be79d242ef0.tar.gz
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 ...
-rw-r--r--Documentation/filesystems/00-INDEX2
-rw-r--r--Documentation/filesystems/efivarfs.txt16
-rw-r--r--arch/x86/include/asm/efi.h28
-rw-r--r--arch/x86/kernel/tboot.c78
-rw-r--r--arch/x86/mm/init_64.c9
-rw-r--r--arch/x86/mm/ioremap.c105
-rw-r--r--arch/x86/mm/pageattr.c10
-rw-r--r--arch/x86/platform/efi/efi-bgrt.c2
-rw-r--r--arch/x86/platform/efi/efi.c30
-rw-r--r--arch/x86/platform/efi/efi_64.c15
-rw-r--r--arch/x86/realmode/init.c17
-rw-r--r--drivers/firmware/efivars.c512
-rw-r--r--include/linux/efi.h8
-rw-r--r--include/uapi/linux/magic.h1
-rw-r--r--init/main.c8
15 files changed, 714 insertions, 127 deletions
diff --git a/Documentation/filesystems/00-INDEX b/Documentation/filesystems/00-INDEX
index 8c624a18f67..7b52ba7bf32 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 00000000000..c477af086e6
--- /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 6e8fdf5ad11..fd13815fe85 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 f84fe00fad4..d4f460f962e 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 2ead3c8a4c8..07519a12044 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 78fe3f1ac49..e190f7b5665 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 a718e0d2350..931930a9616 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 f6a0c1b8e51..d9c1b95af17 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 ad4439145f8..0a34d9e9c26 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 95fd505dfeb..06c8b2e662a 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 cbca565af5b..8e6ab613785 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 6e51c1e81f1..52c5d8956d7 100644
--- a/drivers/firmware/efivars.c
+++ b/drivers/firmware/efivars.c
@@ -80,6 +80,10 @@
#include <linux/slab.h>
#include <linux/pstore.h>
+#include <linux/fs.h>
+#include <linux/ramfs.h>
+#include <linux/pagemap.h>
+
#include <asm/uaccess.h>
#define EFIVARS_VERSION "0.08"
@@ -93,6 +97,12 @@ 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
* space in each part of the structure,
@@ -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 b02099d0b4f..02a69418be1 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 e15192cb9cf..12f68c7ceba 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 63ae904a99a..6af5470b806 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);