summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-02-21 10:41:29 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2015-02-21 10:41:29 -0800
commit5fbe4c224ce3e2e62bd487158dfd1e89f9ae3e11 (patch)
treeaee3c146fb7dd3dd10cb71f44affa9c680481f08 /arch
parente2defd02717ebc54ae2f4862271a3093665b426a (diff)
parent570e1aa84c376ff39809442f09c7606ddf62cfd1 (diff)
Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull misc x86 fixes from Ingo Molnar: "This contains: - EFI fixes - a boot printout fix - ASLR/kASLR fixes - intel microcode driver fixes - other misc fixes Most of the linecount comes from an EFI revert" * 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mm/ASLR: Avoid PAGE_SIZE redefinition for UML subarch x86/microcode/intel: Handle truncated microcode images more robustly x86/microcode/intel: Guard against stack overflow in the loader x86, mm/ASLR: Fix stack randomization on 64-bit systems x86/mm/init: Fix incorrect page size in init_memory_mapping() printks x86/mm/ASLR: Propagate base load address calculation Documentation/x86: Fix path in zero-page.txt x86/apic: Fix the devicetree build in certain configs Revert "efi/libstub: Call get_memory_map() to obtain map and desc sizes" x86/efi: Avoid triple faults during EFI mixed mode calls
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/aslr.c34
-rw-r--r--arch/x86/boot/compressed/efi_stub_64.S25
-rw-r--r--arch/x86/boot/compressed/efi_thunk_64.S196
-rw-r--r--arch/x86/boot/compressed/misc.c3
-rw-r--r--arch/x86/boot/compressed/misc.h6
-rw-r--r--arch/x86/include/asm/apic.h8
-rw-r--r--arch/x86/include/asm/page_types.h2
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h1
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_early.c6
-rw-r--r--arch/x86/kernel/module.c10
-rw-r--r--arch/x86/kernel/setup.c22
-rw-r--r--arch/x86/mm/init.c28
-rw-r--r--arch/x86/mm/mmap.c6
-rw-r--r--arch/x86/platform/efi/efi_stub_64.S161
-rw-r--r--arch/x86/platform/efi/efi_thunk_64.S121
17 files changed, 409 insertions, 226 deletions
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 843feb3eb20b..0a291cdfaf77 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -51,6 +51,7 @@ $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
$(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
$(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index bb1376381985..7083c16cccba 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -14,6 +14,13 @@
static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+struct kaslr_setup_data {
+ __u64 next;
+ __u32 type;
+ __u32 len;
+ __u8 data[1];
+} kaslr_setup_data;
+
#define I8254_PORT_CONTROL 0x43
#define I8254_PORT_COUNTER0 0x40
#define I8254_CMD_READBACK 0xC0
@@ -295,7 +302,29 @@ static unsigned long find_random_addr(unsigned long minimum,
return slots_fetch_random();
}
-unsigned char *choose_kernel_location(unsigned char *input,
+static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
+{
+ struct setup_data *data;
+
+ kaslr_setup_data.type = SETUP_KASLR;
+ kaslr_setup_data.len = 1;
+ kaslr_setup_data.next = 0;
+ kaslr_setup_data.data[0] = enabled;
+
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
+
+ if (data)
+ data->next = (unsigned long)&kaslr_setup_data;
+ else
+ params->hdr.setup_data = (unsigned long)&kaslr_setup_data;
+
+}
+
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size)
@@ -306,14 +335,17 @@ unsigned char *choose_kernel_location(unsigned char *input,
#ifdef CONFIG_HIBERNATION
if (!cmdline_find_option_bool("kaslr")) {
debug_putstr("KASLR disabled by default...\n");
+ add_kaslr_setup_data(params, 0);
goto out;
}
#else
if (cmdline_find_option_bool("nokaslr")) {
debug_putstr("KASLR disabled by cmdline...\n");
+ add_kaslr_setup_data(params, 0);
goto out;
}
#endif
+ add_kaslr_setup_data(params, 1);
/* Record the various known unsafe memory ranges. */
mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index 7ff3632806b1..99494dff2113 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -3,28 +3,3 @@
#include <asm/processor-flags.h>
#include "../../platform/efi/efi_stub_64.S"
-
-#ifdef CONFIG_EFI_MIXED
- .code64
- .text
-ENTRY(efi64_thunk)
- push %rbp
- push %rbx
-
- subq $16, %rsp
- leaq efi_exit32(%rip), %rax
- movl %eax, 8(%rsp)
- leaq efi_gdt64(%rip), %rax
- movl %eax, 4(%rsp)
- movl %eax, 2(%rax) /* Fixup the gdt base address */
- leaq efi32_boot_gdt(%rip), %rax
- movl %eax, (%rsp)
-
- call __efi64_thunk
-
- addq $16, %rsp
- pop %rbx
- pop %rbp
- ret
-ENDPROC(efi64_thunk)
-#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
new file mode 100644
index 000000000000..630384a4c14a
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * since the firmware's 32-bit IDT is still currently installed and it
+ * needs to be able to service interrupts.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identify
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+ .code64
+ .text
+ENTRY(efi64_thunk)
+ push %rbp
+ push %rbx
+
+ subq $8, %rsp
+ leaq efi_exit32(%rip), %rax
+ movl %eax, 4(%rsp)
+ leaq efi_gdt64(%rip), %rax
+ movl %eax, (%rsp)
+ movl %eax, 2(%rax) /* Fixup the gdt base address */
+
+ movl %ds, %eax
+ push %rax
+ movl %es, %eax
+ push %rax
+ movl %ss, %eax
+ push %rax
+
+ /*
+ * Convert x86-64 ABI params to i386 ABI
+ */
+ subq $32, %rsp
+ movl %esi, 0x0(%rsp)
+ movl %edx, 0x4(%rsp)
+ movl %ecx, 0x8(%rsp)
+ movq %r8, %rsi
+ movl %esi, 0xc(%rsp)
+ movq %r9, %rsi
+ movl %esi, 0x10(%rsp)
+
+ sgdt save_gdt(%rip)
+
+ leaq 1f(%rip), %rbx
+ movq %rbx, func_rt_ptr(%rip)
+
+ /*
+ * Switch to gdt with 32-bit segments. This is the firmware GDT
+ * that was installed when the kernel started executing. This
+ * pointer was saved at the EFI stub entry point in head_64.S.
+ */
+ leaq efi32_boot_gdt(%rip), %rax
+ lgdt (%rax)
+
+ pushq $__KERNEL_CS
+ leaq efi_enter32(%rip), %rax
+ pushq %rax
+ lretq
+
+1: addq $32, %rsp
+
+ lgdt save_gdt(%rip)
+
+ pop %rbx
+ movl %ebx, %ss
+ pop %rbx
+ movl %ebx, %es
+ pop %rbx
+ movl %ebx, %ds
+
+ /*
+ * Convert 32-bit status code into 64-bit.
+ */
+ test %rax, %rax
+ jz 1f
+ movl %eax, %ecx
+ andl $0x0fffffff, %ecx
+ andl $0xf0000000, %eax
+ shl $32, %rax
+ or %rcx, %rax
+1:
+ addq $8, %rsp
+ pop %rbx
+ pop %rbp
+ ret
+ENDPROC(efi64_thunk)
+
+ENTRY(efi_exit32)
+ movq func_rt_ptr(%rip), %rax
+ push %rax
+ mov %rdi, %rax
+ ret
+ENDPROC(efi_exit32)
+
+ .code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %eax, %ss
+
+ /* Reload pgtables */
+ movl %cr3, %eax
+ movl %eax, %cr3
+
+ /* Disable paging */
+ movl %cr0, %eax
+ btrl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+
+ /* Disable long mode via EFER */
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btrl $_EFER_LME, %eax
+ wrmsr
+
+ call *%edi
+
+ /* We must preserve return value */
+ movl %eax, %edi
+
+ /*
+ * Some firmware will return with interrupts enabled. Be sure to
+ * disable them before we switch GDTs.
+ */
+ cli
+
+ movl 56(%esp), %eax
+ movl %eax, 2(%eax)
+ lgdtl (%eax)
+
+ movl %cr4, %eax
+ btsl $(X86_CR4_PAE_BIT), %eax
+ movl %eax, %cr4
+
+ movl %cr3, %eax
+ movl %eax, %cr3
+
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+
+ xorl %eax, %eax
+ lldt %ax
+
+ movl 60(%esp), %eax
+ pushl $__KERNEL_CS
+ pushl %eax
+
+ /* Enable paging */
+ movl %cr0, %eax
+ btsl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+ lret
+ENDPROC(efi_enter32)
+
+ .data
+ .balign 8
+ .global efi32_boot_gdt
+efi32_boot_gdt: .word 0
+ .quad 0
+
+save_gdt: .word 0
+ .quad 0
+func_rt_ptr: .quad 0
+
+ .global efi_gdt64
+efi_gdt64:
+ .word efi_gdt64_end - efi_gdt64
+ .long 0 /* Filled out by user */
+ .word 0
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x00af9a000000ffff /* __KERNEL_CS */
+ .quad 0x00cf92000000ffff /* __KERNEL_DS */
+ .quad 0x0080890000000000 /* TS descriptor */
+ .quad 0x0000000000000000 /* TS continued */
+efi_gdt64_end:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index a950864a64da..5903089c818f 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -401,7 +401,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
* the entire decompressed kernel plus relocation table, or the
* entire decompressed kernel plus .bss and .brk sections.
*/
- output = choose_kernel_location(input_data, input_len, output,
+ output = choose_kernel_location(real_mode, input_data, input_len,
+ output,
output_len > run_size ? output_len
: run_size);
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 04477d68403f..ee3576b2666b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -57,7 +57,8 @@ int cmdline_find_option_bool(const char *option);
#if CONFIG_RANDOMIZE_BASE
/* aslr.c */
-unsigned char *choose_kernel_location(unsigned char *input,
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size);
@@ -65,7 +66,8 @@ unsigned char *choose_kernel_location(unsigned char *input,
bool has_cpuflag(int flag);
#else
static inline
-unsigned char *choose_kernel_location(unsigned char *input,
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size)
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 92003f3c8a42..efc3b22d896e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -213,7 +213,15 @@ void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
extern int APIC_init_uniprocessor(void);
+
+#ifdef CONFIG_X86_64
+static inline int apic_force_enable(unsigned long addr)
+{
+ return -1;
+}
+#else
extern int apic_force_enable(unsigned long addr);
+#endif
extern int apic_bsp_setup(bool upmode);
extern void apic_ap_setup(void);
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index f97fbe3abb67..95e11f79f123 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,6 +51,8 @@ extern int devmem_is_allowed(unsigned long pagenr);
extern unsigned long max_low_pfn_mapped;
extern unsigned long max_pfn_mapped;
+extern bool kaslr_enabled;
+
static inline phys_addr_t get_max_mapped(void)
{
return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 225b0988043a..44e6dd7e36a2 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -7,6 +7,7 @@
#define SETUP_DTB 2
#define SETUP_PCI 3
#define SETUP_EFI 4
+#define SETUP_KASLR 5
/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index c6826d1e8082..746e7fd08aad 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -196,6 +196,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
struct microcode_header_intel mc_header;
unsigned int mc_size;
+ if (leftover < sizeof(mc_header)) {
+ pr_err("error! Truncated header in microcode data file\n");
+ break;
+ }
+
if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
break;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index ec9df6f9cd47..420eb933189c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,11 @@ get_matching_model_microcode(int cpu, unsigned long start,
unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
int i;
- while (leftover) {
+ while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
+
+ if (leftover < sizeof(mc_header))
+ break;
+
mc_header = (struct microcode_header_intel *)ucode_ptr;
mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d1ac80b72c72..9bbb9b35c144 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -47,21 +47,13 @@ do { \
#ifdef CONFIG_RANDOMIZE_BASE
static unsigned long module_load_offset;
-static int randomize_modules = 1;
/* Mutex protects the module_load_offset. */
static DEFINE_MUTEX(module_kaslr_mutex);
-static int __init parse_nokaslr(char *p)
-{
- randomize_modules = 0;
- return 0;
-}
-early_param("nokaslr", parse_nokaslr);
-
static unsigned long int get_module_load_offset(void)
{
- if (randomize_modules) {
+ if (kaslr_enabled) {
mutex_lock(&module_kaslr_mutex);
/*
* Calculate the module_load_offset the first time this
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0a2421cca01f..98dc9317286e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -122,6 +122,8 @@
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
+bool __read_mostly kaslr_enabled = false;
+
#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
#endif
@@ -425,6 +427,11 @@ static void __init reserve_initrd(void)
}
#endif /* CONFIG_BLK_DEV_INITRD */
+static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
+{
+ kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
+}
+
static void __init parse_setup_data(void)
{
struct setup_data *data;
@@ -450,6 +457,9 @@ static void __init parse_setup_data(void)
case SETUP_EFI:
parse_efi_setup(pa_data, data_len);
break;
+ case SETUP_KASLR:
+ parse_kaslr_setup(pa_data, data_len);
+ break;
default:
break;
}
@@ -832,10 +842,14 @@ static void __init trim_low_memory_range(void)
static int
dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
{
- pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
- "(relocation range: 0x%lx-0x%lx)\n",
- (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
- __START_KERNEL_map, MODULES_VADDR-1);
+ if (kaslr_enabled)
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
+ (unsigned long)&_text - __START_KERNEL,
+ __START_KERNEL,
+ __START_KERNEL_map,
+ MODULES_VADDR-1);
+ else
+ pr_emerg("Kernel Offset: disabled\n");
return 0;
}
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 553c094b9cd7..a110efca6d06 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -238,6 +238,31 @@ static void __init_refok adjust_range_page_size_mask(struct map_range *mr,
}
}
+static const char *page_size_string(struct map_range *mr)
+{
+ static const char str_1g[] = "1G";
+ static const char str_2m[] = "2M";
+ static const char str_4m[] = "4M";
+ static const char str_4k[] = "4k";
+
+ if (mr->page_size_mask & (1<<PG_LEVEL_1G))
+ return str_1g;
+ /*
+ * 32-bit without PAE has a 4M large page size.
+ * PG_LEVEL_2M is misnamed, but we can at least
+ * print out the right size in the string.
+ */
+ if (IS_ENABLED(CONFIG_X86_32) &&
+ !IS_ENABLED(CONFIG_X86_PAE) &&
+ mr->page_size_mask & (1<<PG_LEVEL_2M))
+ return str_4m;
+
+ if (mr->page_size_mask & (1<<PG_LEVEL_2M))
+ return str_2m;
+
+ return str_4k;
+}
+
static int __meminit split_mem_range(struct map_range *mr, int nr_range,
unsigned long start,
unsigned long end)
@@ -333,8 +358,7 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
for (i = 0; i < nr_range; i++)
printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
mr[i].start, mr[i].end - 1,
- (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
- (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
+ page_size_string(&mr[i]));
return nr_range;
}
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 919b91205cd4..df4552bd239e 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -35,12 +35,12 @@ struct va_alignment __read_mostly va_align = {
.flags = -1,
};
-static unsigned int stack_maxrandom_size(void)
+static unsigned long stack_maxrandom_size(void)
{
- unsigned int max = 0;
+ unsigned long max = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
- max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+ max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
}
return max;
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 5fcda7272550..86d0f9e08dd9 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -91,167 +91,6 @@ ENTRY(efi_call)
ret
ENDPROC(efi_call)
-#ifdef CONFIG_EFI_MIXED
-
-/*
- * We run this function from the 1:1 mapping.
- *
- * This function must be invoked with a 1:1 mapped stack.
- */
-ENTRY(__efi64_thunk)
- movl %ds, %eax
- push %rax
- movl %es, %eax
- push %rax
- movl %ss, %eax
- push %rax
-
- subq $32, %rsp
- movl %esi, 0x0(%rsp)
- movl %edx, 0x4(%rsp)
- movl %ecx, 0x8(%rsp)
- movq %r8, %rsi
- movl %esi, 0xc(%rsp)
- movq %r9, %rsi
- movl %esi, 0x10(%rsp)
-
- sgdt save_gdt(%rip)
-
- leaq 1f(%rip), %rbx
- movq %rbx, func_rt_ptr(%rip)
-
- /* Switch to gdt with 32-bit segments */
- movl 64(%rsp), %eax
- lgdt (%rax)
-
- leaq efi_enter32(%rip), %rax
- pushq $__KERNEL_CS
- pushq %rax
- lretq
-
-1: addq $32, %rsp
-
- lgdt save_gdt(%rip)
-
- pop %rbx
- movl %ebx, %ss
- pop %rbx
- movl %ebx, %es
- pop %rbx
- movl %ebx, %ds
-
- /*
- * Convert 32-bit status code into 64-bit.
- */
- test %rax, %rax
- jz 1f
- movl %eax, %ecx
- andl $0x0fffffff, %ecx
- andl $0xf0000000, %eax
- shl $32, %rax
- or %rcx, %rax
-1:
- ret
-ENDPROC(__efi64_thunk)
-
-ENTRY(efi_exit32)
- movq func_rt_ptr(%rip), %rax
- push %rax
- mov %rdi, %rax
- ret
-ENDPROC(efi_exit32)
-
- .code32
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-ENTRY(efi_enter32)
- movl $__KERNEL_DS, %eax
- movl %eax, %ds
- movl %eax, %es
- movl %eax, %ss
-
- /* Reload pgtables */
- movl %cr3, %eax
- movl %eax, %cr3
-
- /* Disable paging */
- movl %cr0, %eax
- btrl $X86_CR0_PG_BIT, %eax
- movl %eax, %cr0
-
- /* Disable long mode via EFER */
- movl $MSR_EFER, %ecx
- rdmsr
- btrl $_EFER_LME, %eax
- wrmsr
-
- call *%edi
-
- /* We must preserve return value */
- movl %eax, %edi
-
- /*
- * Some firmware will return with interrupts enabled. Be sure to
- * disable them before we switch GDTs.
- */
- cli
-
- movl 68(%esp), %eax
- movl %eax, 2(%eax)
- lgdtl (%eax)
-
- movl %cr4, %eax
- btsl $(X86_CR4_PAE_BIT), %eax
- movl %eax, %cr4
-
- movl %cr3, %eax
- movl %eax, %cr3
-
- movl $MSR_EFER, %ecx
- rdmsr
- btsl $_EFER_LME, %eax
- wrmsr
-
- xorl %eax, %eax
- lldt %ax
-
- movl 72(%esp), %eax
- pushl $__KERNEL_CS
- pushl %eax
-
- /* Enable paging */
- movl %cr0, %eax
- btsl $X86_CR0_PG_BIT, %eax
- movl %eax, %cr0
- lret
-ENDPROC(efi_enter32)
-
- .data
- .balign 8
- .global efi32_boot_gdt
-efi32_boot_gdt: .word 0
- .quad 0
-
-save_gdt: .word 0
- .quad 0
-func_rt_ptr: .quad 0
-
- .global efi_gdt64
-efi_gdt64:
- .word efi_gdt64_end - efi_gdt64
- .long 0 /* Filled out by user */
- .word 0
- .quad 0x0000000000000000 /* NULL descriptor */
- .quad 0x00af9a000000ffff /* __KERNEL_CS */
- .quad 0x00cf92000000ffff /* __KERNEL_DS */
- .quad 0x0080890000000000 /* TS descriptor */
- .quad 0x0000000000000000 /* TS continued */
-efi_gdt64_end:
-#endif /* CONFIG_EFI_MIXED */
-
.data
ENTRY(efi_scratch)
.fill 3,8,0
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 8806fa73e6e6..ff85d28c50f2 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -1,9 +1,26 @@
/*
* Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
*/
#include <linux/linkage.h>
#include <asm/page_types.h>
+#include <asm/segment.h>
.text
.code64
@@ -33,14 +50,6 @@ ENTRY(efi64_thunk)
leaq efi_exit32(%rip), %rbx
subq %rax, %rbx
movl %ebx, 8(%rsp)
- leaq efi_gdt64(%rip), %rbx
- subq %rax, %rbx
- movl %ebx, 2(%ebx)
- movl %ebx, 4(%rsp)
- leaq efi_gdt32(%rip), %rbx
- subq %rax, %rbx
- movl %ebx, 2(%ebx)
- movl %ebx, (%rsp)
leaq __efi64_thunk(%rip), %rbx
subq %rax, %rbx
@@ -52,14 +61,92 @@ ENTRY(efi64_thunk)
retq
ENDPROC(efi64_thunk)
- .data
-efi_gdt32:
- .word efi_gdt32_end - efi_gdt32
- .long 0 /* Filled out above */
- .word 0
- .quad 0x0000000000000000 /* NULL descriptor */
- .quad 0x00cf9a000000ffff /* __KERNEL_CS */
- .quad 0x00cf93000000ffff /* __KERNEL_DS */
-efi_gdt32_end:
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+ movl %ds, %eax
+ push %rax
+ movl %es, %eax
+ push %rax
+ movl %ss, %eax
+ push %rax
+
+ subq $32, %rsp
+ movl %esi, 0x0(%rsp)
+ movl %edx, 0x4(%rsp)
+ movl %ecx, 0x8(%rsp)
+ movq %r8, %rsi
+ movl %esi, 0xc(%rsp)
+ movq %r9, %rsi
+ movl %esi, 0x10(%rsp)
+
+ leaq 1f(%rip), %rbx
+ movq %rbx, func_rt_ptr(%rip)
+
+ /* Switch to 32-bit descriptor */
+ pushq $__KERNEL32_CS
+ leaq efi_enter32(%rip), %rax
+ pushq %rax
+ lretq
+
+1: addq $32, %rsp
+
+ pop %rbx
+ movl %ebx, %ss
+ pop %rbx
+ movl %ebx, %es
+ pop %rbx
+ movl %ebx, %ds
+ /*
+ * Convert 32-bit status code into 64-bit.
+ */
+ test %rax, %rax
+ jz 1f
+ movl %eax, %ecx
+ andl $0x0fffffff, %ecx
+ andl $0xf0000000, %eax
+ shl $32, %rax
+ or %rcx, %rax
+1:
+ ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+ movq func_rt_ptr(%rip), %rax
+ push %rax
+ mov %rdi, %rax
+ ret
+ENDPROC(efi_exit32)
+
+ .code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %eax, %ss
+
+ call *%edi
+
+ /* We must preserve return value */
+ movl %eax, %edi
+
+ movl 72(%esp), %eax
+ pushl $__KERNEL_CS
+ pushl %eax
+
+ lret
+ENDPROC(efi_enter32)
+
+ .data
+ .balign 8
+func_rt_ptr: .quad 0
efi_saved_sp: .quad 0