x86: EFI runtime service support

This patch adds basic runtime services support for EFI x86_64 system.  The
main file of the patch is the addition of efi_64.c for x86_64.  This file is
modeled after the EFI IA32 avatar.  EFI runtime services initialization are
implemented in efi_64.c.  Some x86_64 specifics are worth noting here.  On
x86_64, parameters passed to EFI firmware services need to follow the EFI
calling convention.  For this purpose, a set of functions named efi_call<x>
(<x> is the number of parameters) are implemented.  EFI function calls are
wrapped before calling the firmware service.  The duplicated code between
efi_32.c and efi_64.c is placed in efi.c to remove them from efi_32.c.
Signed-off-by: Chandramouli Narayanan <mouli@linux.intel.com>
Signed-off-by: Huang Ying <ying.huang@intel.com>
Cc: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/Kconfig

@@ -959,7 +959,7 @@ config MTRR
 config EFI
 	def_bool n
 	prompt "Boot from EFI support"
-	depends on X86_32 && ACPI
+	depends on ACPI
 	---help---
 	This enables the kernel to boot on EFI platforms using
 	system configuration information passed to it from the firmware.

arch/x86/kernel/Makefile_64

@@ -39,6 +39,7 @@ obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
 obj-$(CONFIG_X86_VSMP)		+= vsmp_64.o
 obj-$(CONFIG_K8_NB)		+= k8.o
 obj-$(CONFIG_AUDIT)		+= audit_64.o
+obj-$(CONFIG_EFI)		+= efi.o efi_64.o efi_stub_64.o
 
 obj-$(CONFIG_MODULES)		+= module_64.o
 obj-$(CONFIG_PCI)		+= early-quirks.o

arch/x86/kernel/efi_64.c

+/*
+ * x86_64 specific EFI support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * Copyright (C) 2005-2008 Intel Co.
+ *	Fenghua Yu <fenghua.yu@intel.com>
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Chandramouli Narayanan <mouli@linux.intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ *
+ * Code to convert EFI to E820 map has been implemented in elilo bootloader
+ * based on a EFI patch by Edgar Hucek. Based on the E820 map, the page table
+ * is setup appropriately for EFI runtime code.
+ * - mouli 06/14/2007.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/bootmem.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/efi.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/e820.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <asm/proto.h>
+#include <asm/efi.h>
+
+static pgd_t save_pgd __initdata;
+static unsigned long efi_flags __initdata;
+
+static int __init setup_noefi(char *arg)
+{
+	efi_enabled = 0;
+	return 0;
+}
+early_param("noefi", setup_noefi);
+
+static void __init early_mapping_set_exec(unsigned long start,
+					  unsigned long end,
+					  int executable)
+{
+	pte_t *kpte;
+	int level;
+
+	while (start < end) {
+		kpte = lookup_address((unsigned long)__va(start), &level);
+		BUG_ON(!kpte);
+		if (executable)
+			set_pte(kpte, pte_mkexec(*kpte));
+		else
+			set_pte(kpte, __pte((pte_val(*kpte) | _PAGE_NX) & \
+					    __supported_pte_mask));
+		if (pte_huge(*kpte))
+			start = (start + PMD_SIZE) & PMD_MASK;
+		else
+			start = (start + PAGE_SIZE) & PAGE_MASK;
+	}
+}
+
+static void __init early_runtime_code_mapping_set_exec(int executable)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	/* Make EFI runtime service code area executable */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if (md->type == EFI_RUNTIME_SERVICES_CODE) {
+			unsigned long end;
+			end = md->phys_addr + (md->num_pages << PAGE_SHIFT);
+			early_mapping_set_exec(md->phys_addr, end, executable);
+		}
+	}
+}
+
+void __init efi_call_phys_prelog(void)
+{
+	unsigned long vaddress;
+
+	local_irq_save(efi_flags);
+	early_runtime_code_mapping_set_exec(1);
+	vaddress = (unsigned long)__va(0x0UL);
+	pgd_val(save_pgd) = pgd_val(*pgd_offset_k(0x0UL));
+	set_pgd(pgd_offset_k(0x0UL), *pgd_offset_k(vaddress));
+	__flush_tlb_all();
+}
+
+void __init efi_call_phys_epilog(void)
+{
+	/*
+	 * After the lock is released, the original page table is restored.
+	 */
+	set_pgd(pgd_offset_k(0x0UL), save_pgd);
+	early_runtime_code_mapping_set_exec(0);
+	__flush_tlb_all();
+	local_irq_restore(efi_flags);
+}
+
+/*
+ * We need to map the EFI memory map again after init_memory_mapping().
+ */
+void __init efi_map_memmap(void)
+{
+	memmap.map = __va(memmap.phys_map);
+	memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+}
+
+void __init efi_reserve_bootmem(void)
+{
+	reserve_bootmem_generic((unsigned long)memmap.phys_map,
+				memmap.nr_map * memmap.desc_size);
+}
+
+void __init runtime_code_page_mkexec(void)
+{
+	efi_memory_desc_t *md;
+	void *p;
+
+	/* Make EFI runtime service code area executable */
+	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+		md = p;
+		if (md->type == EFI_RUNTIME_SERVICES_CODE)
+			change_page_attr_addr(md->virt_addr,
+					      md->num_pages,
+					      PAGE_KERNEL_EXEC);
+	}
+	__flush_tlb_all();
+}
+
+void __iomem * __init efi_ioremap(unsigned long offset,
+				  unsigned long size)
+{
+	static unsigned pages_mapped;
+	unsigned long last_addr;
+	unsigned i, pages;
+
+	last_addr = offset + size - 1;
+	offset &= PAGE_MASK;
+	pages = (PAGE_ALIGN(last_addr) - offset) >> PAGE_SHIFT;
+	if (pages_mapped + pages > MAX_EFI_IO_PAGES)
+		return NULL;
+
+	for (i = 0; i < pages; i++) {
+		set_fixmap_nocache(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped,
+				   offset);
+		offset += PAGE_SIZE;
+		pages_mapped++;
+	}
+
+	return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \
+					     (pages_mapped - pages));
+}

arch/x86/kernel/efi_stub_64.S

+/*
+ * Function calling ABI conversion from Linux to EFI for x86_64
+ *
+ * Copyright (C) 2007 Intel Corp
+ *	Bibo Mao <bibo.mao@intel.com>
+ *	Huang Ying <ying.huang@intel.com>
+ */
+
+#include <linux/linkage.h>
+
+#define SAVE_XMM			\
+	mov %rsp, %rax;			\
+	subq $0x70, %rsp;		\
+	and $~0xf, %rsp;		\
+	mov %rax, (%rsp);		\
+	mov %cr0, %rax;			\
+	clts;				\
+	mov %rax, 0x8(%rsp);		\
+	movaps %xmm0, 0x60(%rsp);	\
+	movaps %xmm1, 0x50(%rsp);	\
+	movaps %xmm2, 0x40(%rsp);	\
+	movaps %xmm3, 0x30(%rsp);	\
+	movaps %xmm4, 0x20(%rsp);	\
+	movaps %xmm5, 0x10(%rsp)
+
+#define RESTORE_XMM			\
+	movaps 0x60(%rsp), %xmm0;	\
+	movaps 0x50(%rsp), %xmm1;	\
+	movaps 0x40(%rsp), %xmm2;	\
+	movaps 0x30(%rsp), %xmm3;	\
+	movaps 0x20(%rsp), %xmm4;	\
+	movaps 0x10(%rsp), %xmm5;	\
+	mov 0x8(%rsp), %rsi;		\
+	mov %rsi, %cr0;			\
+	mov (%rsp), %rsp
+
+ENTRY(efi_call0)
+	SAVE_XMM
+	subq $32, %rsp
+	call *%rdi
+	addq $32, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call1)
+	SAVE_XMM
+	subq $32, %rsp
+	mov  %rsi, %rcx
+	call *%rdi
+	addq $32, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call2)
+	SAVE_XMM
+	subq $32, %rsp
+	mov  %rsi, %rcx
+	call *%rdi
+	addq $32, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call3)
+	SAVE_XMM
+	subq $32, %rsp
+	mov  %rcx, %r8
+	mov  %rsi, %rcx
+	call *%rdi
+	addq $32, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call4)
+	SAVE_XMM
+	subq $32, %rsp
+	mov %r8, %r9
+	mov %rcx, %r8
+	mov %rsi, %rcx
+	call *%rdi
+	addq $32, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call5)
+	SAVE_XMM
+	subq $48, %rsp
+	mov %r9, 32(%rsp)
+	mov %r8, %r9
+	mov %rcx, %r8
+	mov %rsi, %rcx
+	call *%rdi
+	addq $48, %rsp
+	RESTORE_XMM
+	ret
+
+ENTRY(efi_call6)
+	SAVE_XMM
+	mov (%rsp), %rax
+	mov 8(%rax), %rax
+	subq $48, %rsp
+	mov %r9, 32(%rsp)
+	mov %rax, 40(%rsp)
+	mov %r8, %r9
+	mov %rcx, %r8
+	mov %rsi, %rcx
+	call *%rdi
+	addq $48, %rsp
+	RESTORE_XMM
+	ret

arch/x86/kernel/setup_64.c

@@ -30,6 +30,7 @@
 #include <linux/crash_dump.h>
 #include <linux/root_dev.h>
 #include <linux/pci.h>
+#include <linux/efi.h>
 #include <linux/acpi.h>
 #include <linux/kallsyms.h>
 #include <linux/edd.h>
@@ -299,6 +300,11 @@ void __init setup_arch(char **cmdline_p)
 	rd_prompt = ((boot_params.hdr.ram_size & RAMDISK_PROMPT_FLAG) != 0);
 	rd_doload = ((boot_params.hdr.ram_size & RAMDISK_LOAD_FLAG) != 0);
 #endif
+#ifdef CONFIG_EFI
+	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
+		     "EL64", 4))
+		efi_enabled = 1;
+#endif
 
 	ARCH_SETUP
 
@@ -341,6 +347,8 @@ void __init setup_arch(char **cmdline_p)
 	discover_ebda();
 
 	init_memory_mapping(0, (end_pfn_map << PAGE_SHIFT));
+	if (efi_enabled)
+		efi_init();
 
 	dmi_scan_machine();
 
@@ -414,6 +422,12 @@ void __init setup_arch(char **cmdline_p)
 	 */
        acpi_reserve_bootmem();
 #endif
+
+	if (efi_enabled) {
+		efi_map_memmap();
+		efi_reserve_bootmem();
+	}
+
        /*
 	* Find and reserve possible boot-time SMP configuration:
 	*/
@@ -479,6 +493,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
+	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;

include/asm-x86/bootparam.h

@@ -54,13 +54,14 @@ struct sys_desc_table {
 };
 
 struct efi_info {
-	__u32 _pad1;
+	__u32 efi_loader_signature;
 	__u32 efi_systab;
 	__u32 efi_memdesc_size;
 	__u32 efi_memdesc_version;
 	__u32 efi_memmap;
 	__u32 efi_memmap_size;
-	__u32 _pad2[2];
+	__u32 efi_systab_hi;
+	__u32 efi_memmap_hi;
 };
 
 /* The so-called "zeropage" */

include/asm-x86/efi.h

+#ifndef _ASM_X86_EFI_H
+#define _ASM_X86_EFI_H
+
+#ifdef CONFIG_X86_32
+#else /* !CONFIG_X86_32 */
+
+#define MAX_EFI_IO_PAGES	100
+
+extern u64 efi_call0(void *fp);
+extern u64 efi_call1(void *fp, u64 arg1);
+extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
+extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3);
+extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4);
+extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3,
+		     u64 arg4, u64 arg5);
+extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
+		     u64 arg4, u64 arg5, u64 arg6);
+
+#define efi_call_phys0(f)			\
+	efi_call0((void *)(f))
+#define efi_call_phys1(f, a1)			\
+	efi_call1((void *)(f), (u64)(a1))
+#define efi_call_phys2(f, a1, a2)			\
+	efi_call2((void *)(f), (u64)(a1), (u64)(a2))
+#define efi_call_phys3(f, a1, a2, a3)				\
+	efi_call3((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3))
+#define efi_call_phys4(f, a1, a2, a3, a4)				\
+	efi_call4((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4))
+#define efi_call_phys5(f, a1, a2, a3, a4, a5)				\
+	efi_call5((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4), (u64)(a5))
+#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6)			\
+	efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4), (u64)(a5), (u64)(a6))
+
+#define efi_call_virt0(f)				\
+	efi_call0((void *)(efi.systab->runtime->f))
+#define efi_call_virt1(f, a1)					\
+	efi_call1((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))
+#define efi_call_virt3(f, a1, a2, a3)					\
+	efi_call3((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), \
+		  (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), \
+		  (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), \
+		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+
+#define efi_early_ioremap(addr, size)		early_ioremap(addr, size)
+#define efi_early_iounmap(vaddr, size)		early_iounmap(vaddr, size)
+
+extern void *efi_ioremap(unsigned long offset, unsigned long size);
+
+extern int efi_time;
+
+#endif /* CONFIG_X86_32 */
+
+extern void efi_reserve_bootmem(void);
+extern void efi_call_phys_prelog(void);
+extern void efi_call_phys_epilog(void);
+extern void runtime_code_page_mkexec(void);
+
+#endif

include/asm-x86/fixmap_64.h

@@ -15,6 +15,7 @@
 #include <asm/apicdef.h>
 #include <asm/page.h>
 #include <asm/vsyscall.h>
+#include <asm/efi.h>
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -41,6 +42,8 @@ enum fixed_addresses {
 	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
 	FIX_IO_APIC_BASE_0,
 	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
+	FIX_EFI_IO_MAP_LAST_PAGE,
+	FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE+MAX_EFI_IO_PAGES-1,
 	__end_of_fixed_addresses
 };