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>

1 files changed, 480 insertions, 0 deletions

diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
new file mode 100644
index 000000000000..0a61522e85c7
--- /dev/null
+++ b/arch/x86/kernel/efi.c
@@ -0,0 +1,480 @@
+/*
+ * Common EFI (Extensible Firmware Interface) support functions
+ * Based on Extensible Firmware Interface Specification version 1.0
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ *      David Mosberger-Tang <davidm@hpl.hp.com>
+ *      Stephane Eranian <eranian@hpl.hp.com>
+ * 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>
+ *
+ * Copied from efi_32.c to eliminate the duplicated code between EFI
+ * 32/64 support code. --ying 2007-10-26
+ *
+ * All EFI Runtime Services are not implemented yet as EFI only
+ * supports physical mode addressing on SoftSDV. This is to be fixed
+ * in a future version.  --drummond 1999-07-20
+ *
+ * Implemented EFI runtime services and virtual mode calls.  --davidm
+ *
+ * Goutham Rao: <goutham.rao@intel.com>
+ *      Skip non-WB memory and ignore empty memory ranges.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/efi.h>
+#include <linux/bootmem.h>
+#include <linux/spinlock.h>
+#include <linux/uaccess.h>
+#include <linux/time.h>
+#include <linux/io.h>
+#include <linux/reboot.h>
+#include <linux/bcd.h>
+
+#include <asm/setup.h>
+#include <asm/efi.h>
+#include <asm/time.h>
+
+#define EFI_DEBUG       1
+#define PFX             "EFI: "
+
+int efi_enabled;
+EXPORT_SYMBOL(efi_enabled);
+
+struct efi efi;
+EXPORT_SYMBOL(efi);
+
+struct efi_memory_map memmap;
+
+struct efi efi_phys __initdata;
+static efi_system_table_t efi_systab __initdata;
+
+static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+        return efi_call_virt2(get_time, tm, tc);
+}
+
+static efi_status_t virt_efi_set_time(efi_time_t *tm)
+{
+        return efi_call_virt1(set_time, tm);
+}
+
+static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
+                                             efi_bool_t *pending,
+                                             efi_time_t *tm)
+{
+        return efi_call_virt3(get_wakeup_time,
+                              enabled, pending, tm);
+}
+
+static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+        return efi_call_virt2(set_wakeup_time,
+                              enabled, tm);
+}
+
+static efi_status_t virt_efi_get_variable(efi_char16_t *name,
+                                          efi_guid_t *vendor,
+                                          u32 *attr,
+                                          unsigned long *data_size,
+                                          void *data)
+{
+        return efi_call_virt5(get_variable,
+                              name, vendor, attr,
+                              data_size, data);
+}
+
+static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
+                                               efi_char16_t *name,
+                                               efi_guid_t *vendor)
+{
+        return efi_call_virt3(get_next_variable,
+                              name_size, name, vendor);
+}
+
+static efi_status_t virt_efi_set_variable(efi_char16_t *name,
+                                          efi_guid_t *vendor,
+                                          unsigned long attr,
+                                          unsigned long data_size,
+                                          void *data)
+{
+        return efi_call_virt5(set_variable,
+                              name, vendor, attr,
+                              data_size, data);
+}
+
+static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
+{
+        return efi_call_virt1(get_next_high_mono_count, count);
+}
+
+static void virt_efi_reset_system(int reset_type,
+                                  efi_status_t status,
+                                  unsigned long data_size,
+                                  efi_char16_t *data)
+{
+        efi_call_virt4(reset_system, reset_type, status,
+                       data_size, data);
+}
+
+static efi_status_t virt_efi_set_virtual_address_map(
+        unsigned long memory_map_size,
+        unsigned long descriptor_size,
+        u32 descriptor_version,
+        efi_memory_desc_t *virtual_map)
+{
+        return efi_call_virt4(set_virtual_address_map,
+                              memory_map_size, descriptor_size,
+                              descriptor_version, virtual_map);
+}
+
+static efi_status_t __init phys_efi_set_virtual_address_map(
+        unsigned long memory_map_size,
+        unsigned long descriptor_size,
+        u32 descriptor_version,
+        efi_memory_desc_t *virtual_map)
+{
+        efi_status_t status;
+
+        efi_call_phys_prelog();
+        status = efi_call_phys4(efi_phys.set_virtual_address_map,
+                                memory_map_size, descriptor_size,
+                                descriptor_version, virtual_map);
+        efi_call_phys_epilog();
+        return status;
+}
+
+static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
+                                             efi_time_cap_t *tc)
+{
+        efi_status_t status;
+
+        efi_call_phys_prelog();
+        status = efi_call_phys2(efi_phys.get_time, tm, tc);
+        efi_call_phys_epilog();
+        return status;
+}
+
+int efi_set_rtc_mmss(unsigned long nowtime)
+{
+        int real_seconds, real_minutes;
+        efi_status_t    status;
+        efi_time_t      eft;
+        efi_time_cap_t  cap;
+
+        status = efi.get_time(&eft, &cap);
+        if (status != EFI_SUCCESS) {
+                printk(KERN_ERR "Oops: efitime: can't read time!\n");
+                return -1;
+        }
+
+        real_seconds = nowtime % 60;
+        real_minutes = nowtime / 60;
+        if (((abs(real_minutes - eft.minute) + 15)/30) & 1)
+                real_minutes += 30;
+        real_minutes %= 60;
+        eft.minute = real_minutes;
+        eft.second = real_seconds;
+
+        status = efi.set_time(&eft);
+        if (status != EFI_SUCCESS) {
+                printk(KERN_ERR "Oops: efitime: can't write time!\n");
+                return -1;
+        }
+        return 0;
+}
+
+unsigned long efi_get_time(void)
+{
+        efi_status_t status;
+        efi_time_t eft;
+        efi_time_cap_t cap;
+
+        status = efi.get_time(&eft, &cap);
+        if (status != EFI_SUCCESS)
+                printk(KERN_ERR "Oops: efitime: can't read time!\n");
+
+        return mktime(eft.year, eft.month, eft.day, eft.hour,
+                      eft.minute, eft.second);
+}
+
+#if EFI_DEBUG
+static void __init print_efi_memmap(void)
+{
+        efi_memory_desc_t *md;
+        void *p;
+        int i;
+
+        for (p = memmap.map, i = 0;
+             p < memmap.map_end;
+             p += memmap.desc_size, i++) {
+                md = p;
+                printk(KERN_INFO PFX "mem%02u: type=%u, attr=0x%llx, "
+                        "range=[0x%016llx-0x%016llx) (%lluMB)\n",
+                        i, md->type, md->attribute, md->phys_addr,
+                        md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
+                        (md->num_pages >> (20 - EFI_PAGE_SHIFT)));
+        }
+}
+#endif  /*  EFI_DEBUG  */
+
+void __init efi_init(void)
+{
+        efi_config_table_t *config_tables;
+        efi_runtime_services_t *runtime;
+        efi_char16_t *c16;
+        char vendor[100] = "unknown";
+        int i = 0;
+        void *tmp;
+
+#ifdef CONFIG_X86_32
+        efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
+        memmap.phys_map = (void *)boot_params.efi_info.efi_memmap;
+#else
+        efi_phys.systab = (efi_system_table_t *)
+                (boot_params.efi_info.efi_systab |
+                 ((__u64)boot_params.efi_info.efi_systab_hi<<32));
+        memmap.phys_map = (void *)
+                (boot_params.efi_info.efi_memmap |
+                 ((__u64)boot_params.efi_info.efi_memmap_hi<<32));
+#endif
+        memmap.nr_map = boot_params.efi_info.efi_memmap_size /
+                boot_params.efi_info.efi_memdesc_size;
+        memmap.desc_version = boot_params.efi_info.efi_memdesc_version;
+        memmap.desc_size = boot_params.efi_info.efi_memdesc_size;
+
+        efi.systab = efi_early_ioremap((unsigned long)efi_phys.systab,
+                                       sizeof(efi_system_table_t));
+        if (efi.systab == NULL)
+                printk(KERN_ERR "Couldn't map the EFI system table!\n");
+        memcpy(&efi_systab, efi.systab, sizeof(efi_system_table_t));
+        efi_early_iounmap(efi.systab, sizeof(efi_system_table_t));
+        efi.systab = &efi_systab;
+
+        /*
+         * Verify the EFI Table
+         */
+        if (efi.systab->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+                printk(KERN_ERR "EFI system table signature incorrect!\n");
+        if ((efi.systab->hdr.revision >> 16) == 0)
+                printk(KERN_ERR "Warning: EFI system table version "
+                       "%d.%02d, expected 1.00 or greater!\n",
+                       efi.systab->hdr.revision >> 16,
+                       efi.systab->hdr.revision & 0xffff);
+
+        /*
+         * Show what we know for posterity
+         */
+        c16 = tmp = efi_early_ioremap(efi.systab->fw_vendor, 2);
+        if (c16) {
+                for (i = 0; i < sizeof(vendor) && *c16; ++i)
+                        vendor[i] = *c16++;
+                vendor[i] = '\0';
+        } else
+                printk(KERN_ERR PFX "Could not map the firmware vendor!\n");
+        efi_early_iounmap(tmp, 2);
+
+        printk(KERN_INFO "EFI v%u.%.02u by %s \n",
+               efi.systab->hdr.revision >> 16,
+               efi.systab->hdr.revision & 0xffff, vendor);
+
+        /*
+         * Let's see what config tables the firmware passed to us.
+         */
+        config_tables = efi_early_ioremap(
+                efi.systab->tables,
+                efi.systab->nr_tables * sizeof(efi_config_table_t));
+        if (config_tables == NULL)
+                printk(KERN_ERR "Could not map EFI Configuration Table!\n");
+
+        printk(KERN_INFO);
+        for (i = 0; i < efi.systab->nr_tables; i++) {
+                if (!efi_guidcmp(config_tables[i].guid, MPS_TABLE_GUID)) {
+                        efi.mps = config_tables[i].table;
+                        printk(" MPS=0x%lx ", config_tables[i].table);
+                } else if (!efi_guidcmp(config_tables[i].guid,
+                                        ACPI_20_TABLE_GUID)) {
+                        efi.acpi20 = config_tables[i].table;
+                        printk(" ACPI 2.0=0x%lx ", config_tables[i].table);
+                } else if (!efi_guidcmp(config_tables[i].guid,
+                                        ACPI_TABLE_GUID)) {
+                        efi.acpi = config_tables[i].table;
+                        printk(" ACPI=0x%lx ", config_tables[i].table);
+                } else if (!efi_guidcmp(config_tables[i].guid,
+                                        SMBIOS_TABLE_GUID)) {
+                        efi.smbios = config_tables[i].table;
+                        printk(" SMBIOS=0x%lx ", config_tables[i].table);
+                } else if (!efi_guidcmp(config_tables[i].guid,
+                                        HCDP_TABLE_GUID)) {
+                        efi.hcdp = config_tables[i].table;
+                        printk(" HCDP=0x%lx ", config_tables[i].table);
+                } else if (!efi_guidcmp(config_tables[i].guid,
+                                        UGA_IO_PROTOCOL_GUID)) {
+                        efi.uga = config_tables[i].table;
+                        printk(" UGA=0x%lx ", config_tables[i].table);
+                }
+        }
+        printk("\n");
+        efi_early_iounmap(config_tables,
+                          efi.systab->nr_tables * sizeof(efi_config_table_t));
+
+        /*
+         * Check out the runtime services table. We need to map
+         * the runtime services table so that we can grab the physical
+         * address of several of the EFI runtime functions, needed to
+         * set the firmware into virtual mode.
+         */
+        runtime = efi_early_ioremap((unsigned long)efi.systab->runtime,
+                                    sizeof(efi_runtime_services_t));
+        if (runtime != NULL) {
+                /*
+                 * We will only need *early* access to the following
+                 * two EFI runtime services 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;
+        } else
+                printk(KERN_ERR "Could not map the EFI runtime service "
+                       "table!\n");
+        efi_early_iounmap(runtime, sizeof(efi_runtime_services_t));
+
+        /* Map the EFI memory map */
+        memmap.map = efi_early_ioremap((unsigned long)memmap.phys_map,
+                                       memmap.nr_map * memmap.desc_size);
+        if (memmap.map == NULL)
+                printk(KERN_ERR "Could not map the EFI memory map!\n");
+        memmap.map_end = memmap.map + (memmap.nr_map * memmap.desc_size);
+        if (memmap.desc_size != sizeof(efi_memory_desc_t))
+                printk(KERN_WARNING "Kernel-defined memdesc"
+                       "doesn't match the one from EFI!\n");
+
+#ifdef CONFIG_X86_64
+        /* Setup for EFI runtime service */
+        reboot_type = BOOT_EFI;
+
+#endif
+#if EFI_DEBUG
+        print_efi_memmap();
+#endif
+}
+
+/*
+ * This function will switch the EFI runtime services to virtual mode.
+ * Essentially, look through the EFI memmap and map every region that
+ * has the runtime attribute bit set in its memory descriptor and update
+ * that memory descriptor with the virtual address obtained from ioremap().
+ * This enables the runtime services to be called without having to
+ * thunk back into physical mode for every invocation.
+ */
+void __init efi_enter_virtual_mode(void)
+{
+        efi_memory_desc_t *md;
+        efi_status_t status;
+        unsigned long end;
+        void *p;
+
+        efi.systab = NULL;
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                md = p;
+                if (!(md->attribute & EFI_MEMORY_RUNTIME))
+                        continue;
+                if ((md->attribute & EFI_MEMORY_WB) &&
+                    (((md->phys_addr + (md->num_pages<<EFI_PAGE_SHIFT)) >>
+                      PAGE_SHIFT) < end_pfn_map))
+                        md->virt_addr = (unsigned long)__va(md->phys_addr);
+                else
+                        md->virt_addr = (unsigned long)
+                                efi_ioremap(md->phys_addr,
+                                            md->num_pages << EFI_PAGE_SHIFT);
+                if (!md->virt_addr)
+                        printk(KERN_ERR PFX "ioremap of 0x%llX failed!\n",
+                               (unsigned long long)md->phys_addr);
+                end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT);
+                if ((md->phys_addr <= (unsigned long)efi_phys.systab) &&
+                    ((unsigned long)efi_phys.systab < end))
+                        efi.systab = (efi_system_table_t *)(unsigned long)
+                                (md->virt_addr - md->phys_addr +
+                                 (unsigned long)efi_phys.systab);
+        }
+
+        BUG_ON(!efi.systab);
+
+        status = phys_efi_set_virtual_address_map(
+                memmap.desc_size * memmap.nr_map,
+                memmap.desc_size,
+                memmap.desc_version,
+                memmap.phys_map);
+
+        if (status != EFI_SUCCESS) {
+                printk(KERN_ALERT "Unable to switch EFI into virtual mode "
+                       "(status=%lx)!\n", status);
+                panic("EFI call to SetVirtualAddressMap() failed!");
+        }
+
+        /*
+         * Now that EFI is in virtual mode, update the function
+         * pointers in the runtime service table to the new virtual addresses.
+         *
+         * Call EFI services through wrapper functions.
+         */
+        efi.get_time = virt_efi_get_time;
+        efi.set_time = virt_efi_set_time;
+        efi.get_wakeup_time = virt_efi_get_wakeup_time;
+        efi.set_wakeup_time = virt_efi_set_wakeup_time;
+        efi.get_variable = virt_efi_get_variable;
+        efi.get_next_variable = virt_efi_get_next_variable;
+        efi.set_variable = virt_efi_set_variable;
+        efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
+        efi.reset_system = virt_efi_reset_system;
+        efi.set_virtual_address_map = virt_efi_set_virtual_address_map;
+#ifdef CONFIG_X86_64
+        runtime_code_page_mkexec();
+#endif
+}
+
+/*
+ * Convenience functions to obtain memory types and attributes
+ */
+u32 efi_mem_type(unsigned long phys_addr)
+{
+        efi_memory_desc_t *md;
+        void *p;
+
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                md = p;
+                if ((md->phys_addr <= phys_addr) &&
+                    (phys_addr < (md->phys_addr +
+                                  (md->num_pages << EFI_PAGE_SHIFT))))
+                        return md->type;
+        }
+        return 0;
+}
+
+u64 efi_mem_attributes(unsigned long phys_addr)
+{
+        efi_memory_desc_t *md;
+        void *p;
+
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                md = p;
+                if ((md->phys_addr <= phys_addr) &&
+                    (phys_addr < (md->phys_addr +
+                                  (md->num_pages << EFI_PAGE_SHIFT))))
+                        return md->attribute;
+        }
+        return 0;
+}