diff options
Diffstat (limited to 'arch/x86/platform')
-rw-r--r-- | arch/x86/platform/Makefile | 1 | ||||
-rw-r--r-- | arch/x86/platform/efi/Makefile | 1 | ||||
-rw-r--r-- | arch/x86/platform/efi/early_printk.c | 83 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi.c | 418 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_32.c | 7 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_64.c | 368 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_stub_64.S | 166 | ||||
-rw-r--r-- | arch/x86/platform/efi/efi_thunk_64.S | 65 | ||||
-rw-r--r-- | arch/x86/platform/olpc/olpc-xo1-pm.c | 2 | ||||
-rw-r--r-- | arch/x86/platform/ts5500/ts5500.c | 2 | ||||
-rw-r--r-- | arch/x86/platform/visws/Makefile | 1 | ||||
-rw-r--r-- | arch/x86/platform/visws/visws_quirks.c | 608 |
12 files changed, 933 insertions, 789 deletions
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile index 20342d4c82c..85afde1fa3e 100644 --- a/arch/x86/platform/Makefile +++ b/arch/x86/platform/Makefile @@ -9,5 +9,4 @@ obj-y += olpc/ obj-y += scx200/ obj-y += sfi/ obj-y += ts5500/ -obj-y += visws/ obj-y += uv/ diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index b7b0b35c198..d51045afcaa 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -1,3 +1,4 @@ obj-$(CONFIG_EFI) += efi.o efi_$(BITS).o efi_stub_$(BITS).o obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o obj-$(CONFIG_EARLY_PRINTK_EFI) += early_printk.o +obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o diff --git a/arch/x86/platform/efi/early_printk.c b/arch/x86/platform/efi/early_printk.c index 81b506d5bef..52414211729 100644 --- a/arch/x86/platform/efi/early_printk.c +++ b/arch/x86/platform/efi/early_printk.c @@ -14,48 +14,92 @@ static const struct font_desc *font; static u32 efi_x, efi_y; +static void *efi_fb; +static bool early_efi_keep; -static __init void early_efi_clear_scanline(unsigned int y) +/* + * efi earlyprintk need use early_ioremap to map the framebuffer. + * But early_ioremap is not usable for earlyprintk=efi,keep, ioremap should + * be used instead. ioremap will be available after paging_init() which is + * earlier than initcall callbacks. Thus adding this early initcall function + * early_efi_map_fb to map the whole efi framebuffer. + */ +static __init int early_efi_map_fb(void) { - unsigned long base, *dst; - u16 len; + unsigned long base, size; + + if (!early_efi_keep) + return 0; base = boot_params.screen_info.lfb_base; - len = boot_params.screen_info.lfb_linelength; + size = boot_params.screen_info.lfb_size; + efi_fb = ioremap(base, size); + + return efi_fb ? 0 : -ENOMEM; +} +early_initcall(early_efi_map_fb); + +/* + * early_efi_map maps efi framebuffer region [start, start + len -1] + * In case earlyprintk=efi,keep we have the whole framebuffer mapped already + * so just return the offset efi_fb + start. + */ +static __init_refok void *early_efi_map(unsigned long start, unsigned long len) +{ + unsigned long base; + + base = boot_params.screen_info.lfb_base; + + if (efi_fb) + return (efi_fb + start); + else + return early_ioremap(base + start, len); +} - dst = early_ioremap(base + y*len, len); +static __init_refok void early_efi_unmap(void *addr, unsigned long len) +{ + if (!efi_fb) + early_iounmap(addr, len); +} + +static void early_efi_clear_scanline(unsigned int y) +{ + unsigned long *dst; + u16 len; + + len = boot_params.screen_info.lfb_linelength; + dst = early_efi_map(y*len, len); if (!dst) return; memset(dst, 0, len); - early_iounmap(dst, len); + early_efi_unmap(dst, len); } -static __init void early_efi_scroll_up(void) +static void early_efi_scroll_up(void) { - unsigned long base, *dst, *src; + unsigned long *dst, *src; u16 len; u32 i, height; - base = boot_params.screen_info.lfb_base; len = boot_params.screen_info.lfb_linelength; height = boot_params.screen_info.lfb_height; for (i = 0; i < height - font->height; i++) { - dst = early_ioremap(base + i*len, len); + dst = early_efi_map(i*len, len); if (!dst) return; - src = early_ioremap(base + (i + font->height) * len, len); + src = early_efi_map((i + font->height) * len, len); if (!src) { - early_iounmap(dst, len); + early_efi_unmap(dst, len); return; } memmove(dst, src, len); - early_iounmap(src, len); - early_iounmap(dst, len); + early_efi_unmap(src, len); + early_efi_unmap(dst, len); } } @@ -79,16 +123,14 @@ static void early_efi_write_char(u32 *dst, unsigned char c, unsigned int h) } } -static __init void +static void early_efi_write(struct console *con, const char *str, unsigned int num) { struct screen_info *si; - unsigned long base; unsigned int len; const char *s; void *dst; - base = boot_params.screen_info.lfb_base; si = &boot_params.screen_info; len = si->lfb_linelength; @@ -109,7 +151,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num) for (h = 0; h < font->height; h++) { unsigned int n, x; - dst = early_ioremap(base + (efi_y + h) * len, len); + dst = early_efi_map((efi_y + h) * len, len); if (!dst) return; @@ -123,7 +165,7 @@ early_efi_write(struct console *con, const char *str, unsigned int num) s++; } - early_iounmap(dst, len); + early_efi_unmap(dst, len); } num -= count; @@ -179,6 +221,9 @@ static __init int early_efi_setup(struct console *con, char *options) for (i = 0; i < (yres - efi_y) / font->height; i++) early_efi_scroll_up(); + /* early_console_register will unset CON_BOOT in case ,keep */ + if (!(con->flags & CON_BOOT)) + early_efi_keep = true; return 0; } diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index b97acecf3fd..4d36932ca4f 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -68,9 +68,7 @@ struct efi_memory_map memmap; static struct efi efi_phys __initdata; static efi_system_table_t efi_systab __initdata; -unsigned long x86_efi_facility; - -static __initdata efi_config_table_type_t arch_tables[] = { +static efi_config_table_type_t arch_tables[] __initdata = { #ifdef CONFIG_X86_UV {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab}, #endif @@ -79,16 +77,7 @@ static __initdata efi_config_table_type_t arch_tables[] = { u64 efi_setup; /* efi setup_data physical address */ -/* - * Returns 1 if 'facility' is enabled, 0 otherwise. - */ -int efi_enabled(int facility) -{ - return test_bit(facility, &x86_efi_facility) != 0; -} -EXPORT_SYMBOL(efi_enabled); - -static bool __initdata disable_runtime = false; +static bool disable_runtime __initdata = false; static int __init setup_noefi(char *arg) { disable_runtime = true; @@ -257,27 +246,12 @@ 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(const struct timespec *now) { unsigned long nowtime = now->tv_sec; - efi_status_t status; - efi_time_t eft; - efi_time_cap_t cap; + efi_status_t status; + efi_time_t eft; + efi_time_cap_t cap; struct rtc_time tm; status = efi.get_time(&eft, &cap); @@ -295,9 +269,8 @@ int efi_set_rtc_mmss(const struct timespec *now) eft.second = tm.tm_sec; eft.nanosecond = 0; } else { - printk(KERN_ERR - "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", - __FUNCTION__, nowtime); + pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n", + __func__, nowtime); return -1; } @@ -413,8 +386,7 @@ static void __init print_efi_memmap(void) p < memmap.map_end; p += memmap.desc_size, i++) { md = p; - pr_info("mem%02u: type=%u, attr=0x%llx, " - "range=[0x%016llx-0x%016llx) (%lluMB)\n", + pr_info("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))); @@ -446,9 +418,8 @@ void __init efi_reserve_boot_services(void) memblock_is_region_reserved(start, size)) { /* Could not reserve, skip it */ md->num_pages = 0; - memblock_dbg("Could not reserve boot range " - "[0x%010llx-0x%010llx]\n", - start, start+size-1); + memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n", + start, start+size-1); } else memblock_reserve(start, size); } @@ -456,7 +427,7 @@ void __init efi_reserve_boot_services(void) void __init efi_unmap_memmap(void) { - clear_bit(EFI_MEMMAP, &x86_efi_facility); + clear_bit(EFI_MEMMAP, &efi.flags); if (memmap.map) { early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size); memmap.map = NULL; @@ -467,9 +438,6 @@ void __init efi_free_boot_services(void) { void *p; - if (!efi_is_native()) - return; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { efi_memory_desc_t *md = p; unsigned long long start = md->phys_addr; @@ -584,45 +552,82 @@ static int __init efi_systab_init(void *phys) return -EINVAL; } if ((efi.systab->hdr.revision >> 16) == 0) - pr_err("Warning: System table version " - "%d.%02d, expected 1.00 or greater!\n", + pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n", efi.systab->hdr.revision >> 16, efi.systab->hdr.revision & 0xffff); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); + return 0; } -static int __init efi_runtime_init(void) +static int __init efi_runtime_init32(void) { - efi_runtime_services_t *runtime; + efi_runtime_services_32_t *runtime; + + runtime = early_ioremap((unsigned long)efi.systab->runtime, + sizeof(efi_runtime_services_32_t)); + if (!runtime) { + pr_err("Could not map the runtime service table!\n"); + return -ENOMEM; + } /* - * 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. + * We will only need *early* access to the following two + * EFI runtime services before set_virtual_address_map + * is invoked. */ + efi_phys.set_virtual_address_map = + (efi_set_virtual_address_map_t *) + (unsigned long)runtime->set_virtual_address_map; + early_iounmap(runtime, sizeof(efi_runtime_services_32_t)); + + return 0; +} + +static int __init efi_runtime_init64(void) +{ + efi_runtime_services_64_t *runtime; + runtime = early_ioremap((unsigned long)efi.systab->runtime, - sizeof(efi_runtime_services_t)); + sizeof(efi_runtime_services_64_t)); if (!runtime) { pr_err("Could not map the runtime service table!\n"); return -ENOMEM; } + /* - * We will only need *early* access to the following - * two EFI runtime services before set_virtual_address_map + * 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; + (efi_set_virtual_address_map_t *) + (unsigned long)runtime->set_virtual_address_map; + early_iounmap(runtime, sizeof(efi_runtime_services_64_t)); + + return 0; +} + +static int __init efi_runtime_init(void) +{ + int rv; + /* - * Make efi_get_time can be called before entering - * virtual mode. + * 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. */ - efi.get_time = phys_efi_get_time; - early_iounmap(runtime, sizeof(efi_runtime_services_t)); + if (efi_enabled(EFI_64BIT)) + rv = efi_runtime_init64(); + else + rv = efi_runtime_init32(); + + if (rv) + return rv; + + set_bit(EFI_RUNTIME_SERVICES, &efi.flags); return 0; } @@ -641,6 +646,8 @@ static int __init efi_memmap_init(void) if (add_efi_memmap) do_add_efi_memmap(); + set_bit(EFI_MEMMAP, &efi.flags); + return 0; } @@ -723,7 +730,7 @@ void __init efi_init(void) if (efi_systab_init(efi_phys.systab)) return; - set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility); + set_bit(EFI_SYSTEM_TABLES, &efi.flags); efi.config_table = (unsigned long)efi.systab->tables; efi.fw_vendor = (unsigned long)efi.systab->fw_vendor; @@ -751,24 +758,21 @@ void __init efi_init(void) if (efi_config_init(arch_tables)) return; - set_bit(EFI_CONFIG_TABLES, &x86_efi_facility); - /* * Note: We currently don't support runtime services on an EFI * that doesn't match the kernel 32/64-bit mode. */ - if (!efi_is_native()) + if (!efi_runtime_supported()) pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n"); else { if (disable_runtime || efi_runtime_init()) return; - set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility); } if (efi_memmap_init()) return; - set_bit(EFI_MEMMAP, &x86_efi_facility); + set_bit(EFI_MEMMAP, &efi.flags); print_efi_memmap(); } @@ -845,6 +849,22 @@ void __init old_map_region(efi_memory_desc_t *md) (unsigned long long)md->phys_addr); } +static void native_runtime_setup(void) +{ + 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.query_variable_info = virt_efi_query_variable_info; + efi.update_capsule = virt_efi_update_capsule; + efi.query_capsule_caps = virt_efi_query_capsule_caps; +} + /* Merge contiguous regions of the same type and attribute */ static void __init efi_merge_regions(void) { @@ -892,12 +912,16 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md) } } -static int __init save_runtime_map(void) +static void __init save_runtime_map(void) { +#ifdef CONFIG_KEXEC efi_memory_desc_t *md; void *tmp, *p, *q = NULL; int count = 0; + if (efi_enabled(EFI_OLD_MEMMAP)) + return; + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; @@ -915,38 +939,44 @@ static int __init save_runtime_map(void) } efi_runtime_map_setup(q, count, memmap.desc_size); + return; - return 0; out: kfree(q); - return -ENOMEM; + pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); +#endif } -/* - * Map efi regions which were passed via setup_data. The virt_addr is a fixed - * addr which was used in first kernel of a kexec boot. - */ -static void __init efi_map_regions_fixed(void) +static void *realloc_pages(void *old_memmap, int old_shift) { - void *p; - efi_memory_desc_t *md; + void *ret; - for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { - md = p; - efi_map_region_fixed(md); /* FIXME: add error handling */ - get_systab_virt_addr(md); - } + ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1); + if (!ret) + goto out; + + /* + * A first-time allocation doesn't have anything to copy. + */ + if (!old_memmap) + return ret; + + memcpy(ret, old_memmap, PAGE_SIZE << old_shift); +out: + free_pages((unsigned long)old_memmap, old_shift); + return ret; } /* - * Map efi memory ranges for runtime serivce and update new_memmap with virtual - * addresses. + * Map the efi memory ranges of the runtime services and update new_mmap with + * virtual addresses. */ -static void * __init efi_map_regions(int *count) +static void * __init efi_map_regions(int *count, int *pg_shift) { + void *p, *new_memmap = NULL; + unsigned long left = 0; efi_memory_desc_t *md; - void *p, *tmp, *new_memmap = NULL; for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { md = p; @@ -961,20 +991,80 @@ static void * __init efi_map_regions(int *count) efi_map_region(md); get_systab_virt_addr(md); - tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size, - GFP_KERNEL); - if (!tmp) - goto out; - new_memmap = tmp; + if (left < memmap.desc_size) { + new_memmap = realloc_pages(new_memmap, *pg_shift); + if (!new_memmap) + return NULL; + + left += PAGE_SIZE << *pg_shift; + (*pg_shift)++; + } + memcpy(new_memmap + (*count * memmap.desc_size), md, memmap.desc_size); + + left -= memmap.desc_size; (*count)++; } return new_memmap; -out: - kfree(new_memmap); - return NULL; +} + +static void __init kexec_enter_virtual_mode(void) +{ +#ifdef CONFIG_KEXEC + efi_memory_desc_t *md; + void *p; + + efi.systab = NULL; + + /* + * We don't do virtual mode, since we don't do runtime services, on + * non-native EFI + */ + if (!efi_is_native()) { + efi_unmap_memmap(); + return; + } + + /* + * Map efi regions which were passed via setup_data. The virt_addr is a + * fixed addr which was used in first kernel of a kexec boot. + */ + for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) { + md = p; + efi_map_region_fixed(md); /* FIXME: add error handling */ + get_systab_virt_addr(md); + } + + save_runtime_map(); + + BUG_ON(!efi.systab); + + efi_sync_low_kernel_mappings(); + + /* + * 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.runtime_version = efi_systab.hdr.revision; + + native_runtime_setup(); + + efi.set_virtual_address_map = NULL; + + if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX)) + runtime_code_page_mkexec(); + + /* clean DUMMY object */ + efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, + EFI_VARIABLE_NON_VOLATILE | + EFI_VARIABLE_BOOTSERVICE_ACCESS | + EFI_VARIABLE_RUNTIME_ACCESS, + 0, NULL); +#endif } /* @@ -996,57 +1086,53 @@ out: * * Specially for kexec boot, efi runtime maps in previous kernel should * be passed in via setup_data. In that case runtime ranges will be mapped - * to the same virtual addresses as the first kernel. + * to the same virtual addresses as the first kernel, see + * kexec_enter_virtual_mode(). */ -void __init efi_enter_virtual_mode(void) +static void __init __efi_enter_virtual_mode(void) { - efi_status_t status; + int count = 0, pg_shift = 0; void *new_memmap = NULL; - int err, count = 0; + efi_status_t status; efi.systab = NULL; - /* - * We don't do virtual mode, since we don't do runtime services, on - * non-native EFI - */ - if (!efi_is_native()) { - efi_unmap_memmap(); + efi_merge_regions(); + new_memmap = efi_map_regions(&count, &pg_shift); + if (!new_memmap) { + pr_err("Error reallocating memory, EFI runtime non-functional!\n"); return; } - if (efi_setup) { - efi_map_regions_fixed(); - } else { - efi_merge_regions(); - new_memmap = efi_map_regions(&count); - if (!new_memmap) { - pr_err("Error reallocating memory, EFI runtime non-functional!\n"); - return; - } - } - - err = save_runtime_map(); - if (err) - pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n"); + save_runtime_map(); BUG_ON(!efi.systab); - efi_setup_page_tables(); + if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift)) + return; + efi_sync_low_kernel_mappings(); + efi_dump_pagetable(); - if (!efi_setup) { + if (efi_is_native()) { status = phys_efi_set_virtual_address_map( - memmap.desc_size * count, - memmap.desc_size, - memmap.desc_version, - (efi_memory_desc_t *)__pa(new_memmap)); - - if (status != EFI_SUCCESS) { - pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", - status); - panic("EFI call to SetVirtualAddressMap() failed!"); - } + memmap.desc_size * count, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)__pa(new_memmap)); + } else { + status = efi_thunk_set_virtual_address_map( + efi_phys.set_virtual_address_map, + memmap.desc_size * count, + memmap.desc_size, + memmap.desc_version, + (efi_memory_desc_t *)__pa(new_memmap)); + } + + if (status != EFI_SUCCESS) { + pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n", + status); + panic("EFI call to SetVirtualAddressMap() failed!"); } /* @@ -1056,23 +1142,43 @@ void __init efi_enter_virtual_mode(void) * Call EFI services through wrapper functions. */ efi.runtime_version = efi_systab.hdr.revision; - 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; + + if (efi_is_native()) + native_runtime_setup(); + else + efi_thunk_runtime_setup(); + efi.set_virtual_address_map = NULL; - efi.query_variable_info = virt_efi_query_variable_info; - efi.update_capsule = virt_efi_update_capsule; - efi.query_capsule_caps = virt_efi_query_capsule_caps; efi_runtime_mkexec(); - kfree(new_memmap); + /* + * We mapped the descriptor array into the EFI pagetable above but we're + * not unmapping it here. Here's why: + * + * We're copying select PGDs from the kernel page table to the EFI page + * table and when we do so and make changes to those PGDs like unmapping + * stuff from them, those changes appear in the kernel page table and we + * go boom. + * + * From setup_real_mode(): + * + * ... + * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd; + * + * In this particular case, our allocation is in PGD 0 of the EFI page + * table but we've copied that PGD from PGD[272] of the EFI page table: + * + * pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272 + * + * where the direct memory mapping in kernel space is. + * + * new_memmap's VA comes from that direct mapping and thus clearing it, + * it would get cleared in the kernel page table too. + * + * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift); + */ + free_pages((unsigned long)new_memmap, pg_shift); /* clean DUMMY object */ efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID, @@ -1082,6 +1188,14 @@ void __init efi_enter_virtual_mode(void) 0, NULL); } +void __init efi_enter_virtual_mode(void) +{ + if (efi_setup) + kexec_enter_virtual_mode(); + else + __efi_enter_virtual_mode(); +} + /* * Convenience functions to obtain memory types and attributes */ @@ -1119,9 +1233,8 @@ u64 efi_mem_attributes(unsigned long phys_addr) } /* - * Some firmware has serious problems when using more than 50% of the EFI - * variable store, i.e. it triggers bugs that can brick machines. Ensure that - * we never use more than this safe limit. + * Some firmware implementations refuse to boot if there's insufficient space + * in the variable store. Ensure that we never use more than a safe limit. * * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable * store. @@ -1140,10 +1253,9 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size) return status; /* - * Some firmware implementations refuse to boot if there's insufficient - * space in the variable store. We account for that by refusing the - * write if permitting it would reduce the available space to under - * 5KB. This figure was provided by Samsung, so should be safe. + * We account for that by refusing the write if permitting it would + * reduce the available space to under 5KB. This figure was provided by + * Samsung, so should be safe. */ if ((remaining_size - size < EFI_MIN_RESERVE) && !efi_no_storage_paranoia) { @@ -1206,7 +1318,7 @@ static int __init parse_efi_cmdline(char *str) str++; if (!strncmp(str, "old_map", 7)) - set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + set_bit(EFI_OLD_MEMMAP, &efi.flags); return 0; } @@ -1219,7 +1331,7 @@ void __init efi_apply_memmap_quirks(void) * firmware/kernel architectures since there is no support for runtime * services. */ - if (!efi_is_native()) { + if (!efi_runtime_supported()) { pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n"); efi_unmap_memmap(); } @@ -1228,5 +1340,5 @@ void __init efi_apply_memmap_quirks(void) * UV doesn't support the new EFI pagetable mapping yet. */ if (is_uv_system()) - set_bit(EFI_OLD_MEMMAP, &x86_efi_facility); + set_bit(EFI_OLD_MEMMAP, &efi.flags); } diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c index 0b74cdf7f81..9ee3491e31f 100644 --- a/arch/x86/platform/efi/efi_32.c +++ b/arch/x86/platform/efi/efi_32.c @@ -40,7 +40,12 @@ static unsigned long efi_rt_eflags; void efi_sync_low_kernel_mappings(void) {} -void efi_setup_page_tables(void) {} +void __init efi_dump_pagetable(void) {} +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + return 0; +} +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {} void __init efi_map_region(efi_memory_desc_t *md) { diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 0c2a234fef1..290d397e1dd 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -39,6 +39,7 @@ #include <asm/cacheflush.h> #include <asm/fixmap.h> #include <asm/realmode.h> +#include <asm/time.h> static pgd_t *save_pgd __initdata; static unsigned long efi_flags __initdata; @@ -58,7 +59,8 @@ struct efi_scratch { u64 prev_cr3; pgd_t *efi_pgt; bool use_pgd; -}; + u64 phys_stack; +} __packed; static void __init early_code_mapping_set_exec(int executable) { @@ -137,12 +139,64 @@ void efi_sync_low_kernel_mappings(void) sizeof(pgd_t) * num_pgds); } -void efi_setup_page_tables(void) +int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages) { + unsigned long text; + struct page *page; + unsigned npages; + pgd_t *pgd; + + if (efi_enabled(EFI_OLD_MEMMAP)) + return 0; + efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd; + pgd = __va(efi_scratch.efi_pgt); - if (!efi_enabled(EFI_OLD_MEMMAP)) - efi_scratch.use_pgd = true; + /* + * It can happen that the physical address of new_memmap lands in memory + * which is not mapped in the EFI page table. Therefore we need to go + * and ident-map those pages containing the map before calling + * phys_efi_set_virtual_address_map(). + */ + if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) { + pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap); + return 1; + } + + efi_scratch.use_pgd = true; + + /* + * When making calls to the firmware everything needs to be 1:1 + * mapped and addressable with 32-bit pointers. Map the kernel + * text and allocate a new stack because we can't rely on the + * stack pointer being < 4GB. + */ + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return 0; + + page = alloc_page(GFP_KERNEL|__GFP_DMA32); + if (!page) + panic("Unable to allocate EFI runtime stack < 4GB\n"); + + efi_scratch.phys_stack = virt_to_phys(page_address(page)); + efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */ + + npages = (_end - _text) >> PAGE_SHIFT; + text = __pa(_text); + + if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) { + pr_err("Failed to map kernel text 1:1\n"); + return 1; + } + + return 0; +} + +void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) +{ + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages); } static void __init __map_region(efi_memory_desc_t *md, u64 va) @@ -173,6 +227,16 @@ void __init efi_map_region(efi_memory_desc_t *md) */ __map_region(md, md->phys_addr); + /* + * Enforce the 1:1 mapping as the default virtual address when + * booting in EFI mixed mode, because even though we may be + * running a 64-bit kernel, the firmware may only be 32-bit. + */ + if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) { + md->virt_addr = md->phys_addr; + return; + } + efi_va -= size; /* Is PA 2M-aligned? */ @@ -242,3 +306,299 @@ void __init efi_runtime_mkexec(void) if (__supported_pte_mask & _PAGE_NX) runtime_code_page_mkexec(); } + +void __init efi_dump_pagetable(void) +{ +#ifdef CONFIG_EFI_PGT_DUMP + pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd); + + ptdump_walk_pgd_level(NULL, pgd); +#endif +} + +#ifdef CONFIG_EFI_MIXED +extern efi_status_t efi64_thunk(u32, ...); + +#define runtime_service32(func) \ +({ \ + u32 table = (u32)(unsigned long)efi.systab; \ + u32 *rt, *___f; \ + \ + rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime)); \ + ___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \ + *___f; \ +}) + +/* + * Switch to the EFI page tables early so that we can access the 1:1 + * runtime services mappings which are not mapped in any other page + * tables. This function must be called before runtime_service32(). + * + * Also, disable interrupts because the IDT points to 64-bit handlers, + * which aren't going to function correctly when we switch to 32-bit. + */ +#define efi_thunk(f, ...) \ +({ \ + efi_status_t __s; \ + unsigned long flags; \ + u32 func; \ + \ + efi_sync_low_kernel_mappings(); \ + local_irq_save(flags); \ + \ + efi_scratch.prev_cr3 = read_cr3(); \ + write_cr3((unsigned long)efi_scratch.efi_pgt); \ + __flush_tlb_all(); \ + \ + func = runtime_service32(f); \ + __s = efi64_thunk(func, __VA_ARGS__); \ + \ + write_cr3(efi_scratch.prev_cr3); \ + __flush_tlb_all(); \ + local_irq_restore(flags); \ + \ + __s; \ +}) + +efi_status_t efi_thunk_set_virtual_address_map( + void *phys_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; + unsigned long flags; + u32 func; + + efi_sync_low_kernel_mappings(); + local_irq_save(flags); + + efi_scratch.prev_cr3 = read_cr3(); + write_cr3((unsigned long)efi_scratch.efi_pgt); + __flush_tlb_all(); + + func = (u32)(unsigned long)phys_set_virtual_address_map; + status = efi64_thunk(func, memory_map_size, descriptor_size, + descriptor_version, virtual_map); + + write_cr3(efi_scratch.prev_cr3); + __flush_tlb_all(); + local_irq_restore(flags); + + return status; +} + +static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc) +{ + efi_status_t status; + u32 phys_tm, phys_tc; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + phys_tc = virt_to_phys(tc); + + status = efi_thunk(get_time, phys_tm, phys_tc); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t efi_thunk_set_time(efi_time_t *tm) +{ + efi_status_t status; + u32 phys_tm; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + + status = efi_thunk(set_time, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t +efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending, + efi_time_t *tm) +{ + efi_status_t status; + u32 phys_enabled, phys_pending, phys_tm; + + spin_lock(&rtc_lock); + + phys_enabled = virt_to_phys(enabled); + phys_pending = virt_to_phys(pending); + phys_tm = virt_to_phys(tm); + + status = efi_thunk(get_wakeup_time, phys_enabled, + phys_pending, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + +static efi_status_t +efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm) +{ + efi_status_t status; + u32 phys_tm; + + spin_lock(&rtc_lock); + + phys_tm = virt_to_phys(tm); + + status = efi_thunk(set_wakeup_time, enabled, phys_tm); + + spin_unlock(&rtc_lock); + + return status; +} + + +static efi_status_t +efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 *attr, unsigned long *data_size, void *data) +{ + efi_status_t status; + u32 phys_name, phys_vendor, phys_attr; + u32 phys_data_size, phys_data; + + phys_data_size = virt_to_phys(data_size); + phys_vendor = virt_to_phys(vendor); + phys_name = virt_to_phys(name); + phys_attr = virt_to_phys(attr); + phys_data = virt_to_phys(data); + + status = efi_thunk(get_variable, phys_name, phys_vendor, + phys_attr, phys_data_size, phys_data); + + return status; +} + +static efi_status_t +efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor, + u32 attr, unsigned long data_size, void *data) +{ + u32 phys_name, phys_vendor, phys_data; + efi_status_t status; + + phys_name = virt_to_phys(name); + phys_vendor = virt_to_phys(vendor); + phys_data = virt_to_phys(data); + + /* If data_size is > sizeof(u32) we've got problems */ + status = efi_thunk(set_variable, phys_name, phys_vendor, + attr, data_size, phys_data); + + return status; +} + +static efi_status_t +efi_thunk_get_next_variable(unsigned long *name_size, + efi_char16_t *name, + efi_guid_t *vendor) +{ + efi_status_t status; + u32 phys_name_size, phys_name, phys_vendor; + + phys_name_size = virt_to_phys(name_size); + phys_vendor = virt_to_phys(vendor); + phys_name = virt_to_phys(name); + + status = efi_thunk(get_next_variable, phys_name_size, + phys_name, phys_vendor); + + return status; +} + +static efi_status_t +efi_thunk_get_next_high_mono_count(u32 *count) +{ + efi_status_t status; + u32 phys_count; + + phys_count = virt_to_phys(count); + status = efi_thunk(get_next_high_mono_count, phys_count); + + return status; +} + +static void +efi_thunk_reset_system(int reset_type, efi_status_t status, + unsigned long data_size, efi_char16_t *data) +{ + u32 phys_data; + + phys_data = virt_to_phys(data); + + efi_thunk(reset_system, reset_type, status, data_size, phys_data); +} + +static efi_status_t +efi_thunk_update_capsule(efi_capsule_header_t **capsules, + unsigned long count, unsigned long sg_list) +{ + /* + * To properly support this function we would need to repackage + * 'capsules' because the firmware doesn't understand 64-bit + * pointers. + */ + return EFI_UNSUPPORTED; +} + +static efi_status_t +efi_thunk_query_variable_info(u32 attr, u64 *storage_space, + u64 *remaining_space, + u64 *max_variable_size) +{ + efi_status_t status; + u32 phys_storage, phys_remaining, phys_max; + + if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION) + return EFI_UNSUPPORTED; + + phys_storage = virt_to_phys(storage_space); + phys_remaining = virt_to_phys(remaining_space); + phys_max = virt_to_phys(max_variable_size); + + status = efi_thunk(query_variable_info, attr, phys_storage, + phys_remaining, phys_max); + + return status; +} + +static efi_status_t +efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules, + unsigned long count, u64 *max_size, + int *reset_type) +{ + /* + * To properly support this function we would need to repackage + * 'capsules' because the firmware doesn't understand 64-bit + * pointers. + */ + return EFI_UNSUPPORTED; +} + +void efi_thunk_runtime_setup(void) +{ + efi.get_time = efi_thunk_get_time; + efi.set_time = efi_thunk_set_time; + efi.get_wakeup_time = efi_thunk_get_wakeup_time; + efi.set_wakeup_time = efi_thunk_set_wakeup_time; + efi.get_variable = efi_thunk_get_variable; + efi.get_next_variable = efi_thunk_get_next_variable; + efi.set_variable = efi_thunk_set_variable; + efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count; + efi.reset_system = efi_thunk_reset_system; + efi.query_variable_info = efi_thunk_query_variable_info; + efi.update_capsule = efi_thunk_update_capsule; + efi.query_capsule_caps = efi_thunk_query_capsule_caps; +} +#endif /* CONFIG_EFI_MIXED */ diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S index 88073b14029..e0984ef0374 100644 --- a/arch/x86/platform/efi/efi_stub_64.S +++ b/arch/x86/platform/efi/efi_stub_64.S @@ -7,6 +7,10 @@ */ #include <linux/linkage.h> +#include <asm/segment.h> +#include <asm/msr.h> +#include <asm/processor-flags.h> +#include <asm/page_types.h> #define SAVE_XMM \ mov %rsp, %rax; \ @@ -164,7 +168,169 @@ ENTRY(efi_call6) ret ENDPROC(efi_call6) +#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 .byte 0 + .quad 0 diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S new file mode 100644 index 00000000000..8806fa73e6e --- /dev/null +++ b/arch/x86/platform/efi/efi_thunk_64.S @@ -0,0 +1,65 @@ +/* + * Copyright (C) 2014 Intel Corporation; author Matt Fleming + */ + +#include <linux/linkage.h> +#include <asm/page_types.h> + + .text + .code64 +ENTRY(efi64_thunk) + push %rbp + push %rbx + + /* + * Switch to 1:1 mapped 32-bit stack pointer. + */ + movq %rsp, efi_saved_sp(%rip) + movq efi_scratch+25(%rip), %rsp + + /* + * Calculate the physical address of the kernel text. + */ + movq $__START_KERNEL_map, %rax + subq phys_base(%rip), %rax + + /* + * Push some physical addresses onto the stack. This is easier + * to do now in a code64 section while the assembler can address + * 64-bit values. Note that all the addresses on the stack are + * 32-bit. + */ + subq $16, %rsp + leaq efi_exit32(%rip), %rbx + subq %rax, %rbx + movl %ebx, 8(%rsp) + leaq efi_gdt64(%rip), %rbx + subq %rax, %rbx + movl %ebx, 2(%ebx) + movl %ebx, 4(%rsp) + leaq efi_gdt32(%rip), %rbx + subq %rax, %rbx + movl %ebx, 2(%ebx) + movl %ebx, (%rsp) + + leaq __efi64_thunk(%rip), %rbx + subq %rax, %rbx + call *%rbx + + movq efi_saved_sp(%rip), %rsp + pop %rbx + pop %rbp + retq +ENDPROC(efi64_thunk) + + .data +efi_gdt32: + .word efi_gdt32_end - efi_gdt32 + .long 0 /* Filled out above */ + .word 0 + .quad 0x0000000000000000 /* NULL descriptor */ + .quad 0x00cf9a000000ffff /* __KERNEL_CS */ + .quad 0x00cf93000000ffff /* __KERNEL_DS */ +efi_gdt32_end: + +efi_saved_sp: .quad 0 diff --git a/arch/x86/platform/olpc/olpc-xo1-pm.c b/arch/x86/platform/olpc/olpc-xo1-pm.c index ff0174dda81..a9acde72d4e 100644 --- a/arch/x86/platform/olpc/olpc-xo1-pm.c +++ b/arch/x86/platform/olpc/olpc-xo1-pm.c @@ -75,7 +75,7 @@ static int xo1_power_state_enter(suspend_state_t pm_state) return 0; } -asmlinkage int xo1_do_sleep(u8 sleep_state) +asmlinkage __visible int xo1_do_sleep(u8 sleep_state) { void *pgd_addr = __va(read_cr3()); diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c index 39febb214e8..9471b9456f2 100644 --- a/arch/x86/platform/ts5500/ts5500.c +++ b/arch/x86/platform/ts5500/ts5500.c @@ -88,7 +88,7 @@ struct ts5500_sbc { static const struct { const char * const string; const ssize_t offset; -} ts5500_signatures[] __initdata = { +} ts5500_signatures[] __initconst = { { "TS-5x00 AMD Elan", 0xb14 }, }; diff --git a/arch/x86/platform/visws/Makefile b/arch/x86/platform/visws/Makefile deleted file mode 100644 index 91bc17ab2fd..00000000000 --- a/arch/x86/platform/visws/Makefile +++ /dev/null @@ -1 +0,0 @@ -obj-$(CONFIG_X86_VISWS) += visws_quirks.o diff --git a/arch/x86/platform/visws/visws_quirks.c b/arch/x86/platform/visws/visws_quirks.c deleted file mode 100644 index 94d8a39332e..00000000000 --- a/arch/x86/platform/visws/visws_quirks.c +++ /dev/null @@ -1,608 +0,0 @@ -/* - * SGI Visual Workstation support and quirks, unmaintained. - * - * Split out from setup.c by davej@suse.de - * - * Copyright (C) 1999 Bent Hagemark, Ingo Molnar - * - * SGI Visual Workstation interrupt controller - * - * The Cobalt system ASIC in the Visual Workstation contains a "Cobalt" APIC - * which serves as the main interrupt controller in the system. Non-legacy - * hardware in the system uses this controller directly. Legacy devices - * are connected to the PIIX4 which in turn has its 8259(s) connected to - * a of the Cobalt APIC entry. - * - * 09/02/2000 - Updated for 2.4 by jbarnes@sgi.com - * - * 25/11/2002 - Updated for 2.5 by Andrey Panin <pazke@orbita1.ru> - */ -#include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/init.h> -#include <linux/smp.h> - -#include <asm/visws/cobalt.h> -#include <asm/visws/piix4.h> -#include <asm/io_apic.h> -#include <asm/fixmap.h> -#include <asm/reboot.h> -#include <asm/setup.h> -#include <asm/apic.h> -#include <asm/e820.h> -#include <asm/time.h> -#include <asm/io.h> - -#include <linux/kernel_stat.h> - -#include <asm/i8259.h> -#include <asm/irq_vectors.h> -#include <asm/visws/lithium.h> - -#include <linux/sched.h> -#include <linux/kernel.h> -#include <linux/pci.h> -#include <linux/pci_ids.h> - -extern int no_broadcast; - -char visws_board_type = -1; -char visws_board_rev = -1; - -static void __init visws_time_init(void) -{ - printk(KERN_INFO "Starting Cobalt Timer system clock\n"); - - /* Set the countdown value */ - co_cpu_write(CO_CPU_TIMEVAL, CO_TIME_HZ/HZ); - - /* Start the timer */ - co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) | CO_CTRL_TIMERUN); - - /* Enable (unmask) the timer interrupt */ - co_cpu_write(CO_CPU_CTRL, co_cpu_read(CO_CPU_CTRL) & ~CO_CTRL_TIMEMASK); - - setup_default_timer_irq(); -} - -/* Replaces the default init_ISA_irqs in the generic setup */ -static void __init visws_pre_intr_init(void); - -/* Quirk for machine specific memory setup. */ - -#define MB (1024 * 1024) - -unsigned long sgivwfb_mem_phys; -unsigned long sgivwfb_mem_size; -EXPORT_SYMBOL(sgivwfb_mem_phys); -EXPORT_SYMBOL(sgivwfb_mem_size); - -long long mem_size __initdata = 0; - -static char * __init visws_memory_setup(void) -{ - long long gfx_mem_size = 8 * MB; - - mem_size = boot_params.alt_mem_k; - - if (!mem_size) { - printk(KERN_WARNING "Bootloader didn't set memory size, upgrade it !\n"); - mem_size = 128 * MB; - } - - /* - * this hardcodes the graphics memory to 8 MB - * it really should be sized dynamically (or at least - * set as a boot param) - */ - if (!sgivwfb_mem_size) { - printk(KERN_WARNING "Defaulting to 8 MB framebuffer size\n"); - sgivwfb_mem_size = 8 * MB; - } - - /* - * Trim to nearest MB - */ - sgivwfb_mem_size &= ~((1 << 20) - 1); - sgivwfb_mem_phys = mem_size - gfx_mem_size; - - e820_add_region(0, LOWMEMSIZE(), E820_RAM); - e820_add_region(HIGH_MEMORY, mem_size - sgivwfb_mem_size - HIGH_MEMORY, E820_RAM); - e820_add_region(sgivwfb_mem_phys, sgivwfb_mem_size, E820_RESERVED); - - return "PROM"; -} - -static void visws_machine_emergency_restart(void) -{ - /* - * Visual Workstations restart after this - * register is poked on the PIIX4 - */ - outb(PIIX4_RESET_VAL, PIIX4_RESET_PORT); -} - -static void visws_machine_power_off(void) -{ - unsigned short pm_status; -/* extern unsigned int pci_bus0; */ - - while ((pm_status = inw(PMSTS_PORT)) & 0x100) - outw(pm_status, PMSTS_PORT); - - outw(PM_SUSPEND_ENABLE, PMCNTRL_PORT); - - mdelay(10); - -#define PCI_CONF1_ADDRESS(bus, devfn, reg) \ - (0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3)) - -/* outl(PCI_CONF1_ADDRESS(pci_bus0, SPECIAL_DEV, SPECIAL_REG), 0xCF8); */ - outl(PIIX_SPECIAL_STOP, 0xCFC); -} - -static void __init visws_get_smp_config(unsigned int early) -{ -} - -/* - * The Visual Workstation is Intel MP compliant in the hardware - * sense, but it doesn't have a BIOS(-configuration table). - * No problem for Linux. - */ - -static void __init MP_processor_info(struct mpc_cpu *m) -{ - int ver, logical_apicid; - physid_mask_t apic_cpus; - - if (!(m->cpuflag & CPU_ENABLED)) - return; - - logical_apicid = m->apicid; - printk(KERN_INFO "%sCPU #%d %u:%u APIC version %d\n", - m->cpuflag & CPU_BOOTPROCESSOR ? "Bootup " : "", - m->apicid, (m->cpufeature & CPU_FAMILY_MASK) >> 8, - (m->cpufeature & CPU_MODEL_MASK) >> 4, m->apicver); - - if (m->cpuflag & CPU_BOOTPROCESSOR) - boot_cpu_physical_apicid = m->apicid; - - ver = m->apicver; - if ((ver >= 0x14 && m->apicid >= 0xff) || m->apicid >= 0xf) { - printk(KERN_ERR "Processor #%d INVALID. (Max ID: %d).\n", - m->apicid, MAX_LOCAL_APIC); - return; - } - - apic->apicid_to_cpu_present(m->apicid, &apic_cpus); - physids_or(phys_cpu_present_map, phys_cpu_present_map, apic_cpus); - /* - * Validate version - */ - if (ver == 0x0) { - printk(KERN_ERR "BIOS bug, APIC version is 0 for CPU#%d! " - "fixing up to 0x10. (tell your hw vendor)\n", - m->apicid); - ver = 0x10; - } - apic_version[m->apicid] = ver; -} - -static void __init visws_find_smp_config(void) -{ - struct mpc_cpu *mp = phys_to_virt(CO_CPU_TAB_PHYS); - unsigned short ncpus = readw(phys_to_virt(CO_CPU_NUM_PHYS)); - - if (ncpus > CO_CPU_MAX) { - printk(KERN_WARNING "find_visws_smp: got cpu count of %d at %p\n", - ncpus, mp); - - ncpus = CO_CPU_MAX; - } - - if (ncpus > setup_max_cpus) - ncpus = setup_max_cpus; - -#ifdef CONFIG_X86_LOCAL_APIC - smp_found_config = 1; -#endif - while (ncpus--) - MP_processor_info(mp++); - - mp_lapic_addr = APIC_DEFAULT_PHYS_BASE; -} - -static void visws_trap_init(void); - -void __init visws_early_detect(void) -{ - int raw; - - visws_board_type = (char)(inb_p(PIIX_GPI_BD_REG) & PIIX_GPI_BD_REG) - >> PIIX_GPI_BD_SHIFT; - - if (visws_board_type < 0) - return; - - /* - * Override the default platform setup functions - */ - x86_init.resources.memory_setup = visws_memory_setup; - x86_init.mpparse.get_smp_config = visws_get_smp_config; - x86_init.mpparse.find_smp_config = visws_find_smp_config; - x86_init.irqs.pre_vector_init = visws_pre_intr_init; - x86_init.irqs.trap_init = visws_trap_init; - x86_init.timers.timer_init = visws_time_init; - x86_init.pci.init = pci_visws_init; - x86_init.pci.init_irq = x86_init_noop; - - /* - * Install reboot quirks: - */ - pm_power_off = visws_machine_power_off; - machine_ops.emergency_restart = visws_machine_emergency_restart; - - /* - * Do not use broadcast IPIs: - */ - no_broadcast = 0; - -#ifdef CONFIG_X86_IO_APIC - /* - * Turn off IO-APIC detection and initialization: - */ - skip_ioapic_setup = 1; -#endif - - /* - * Get Board rev. - * First, we have to initialize the 307 part to allow us access - * to the GPIO registers. Let's map them at 0x0fc0 which is right - * after the PIIX4 PM section. - */ - outb_p(SIO_DEV_SEL, SIO_INDEX); - outb_p(SIO_GP_DEV, SIO_DATA); /* Talk to GPIO regs. */ - - outb_p(SIO_DEV_MSB, SIO_INDEX); - outb_p(SIO_GP_MSB, SIO_DATA); /* MSB of GPIO base address */ - - outb_p(SIO_DEV_LSB, SIO_INDEX); - outb_p(SIO_GP_LSB, SIO_DATA); /* LSB of GPIO base address */ - - outb_p(SIO_DEV_ENB, SIO_INDEX); - outb_p(1, SIO_DATA); /* Enable GPIO registers. */ - - /* - * Now, we have to map the power management section to write - * a bit which enables access to the GPIO registers. - * What lunatic came up with this shit? - */ - outb_p(SIO_DEV_SEL, SIO_INDEX); - outb_p(SIO_PM_DEV, SIO_DATA); /* Talk to GPIO regs. */ - - outb_p(SIO_DEV_MSB, SIO_INDEX); - outb_p(SIO_PM_MSB, SIO_DATA); /* MSB of PM base address */ - - outb_p(SIO_DEV_LSB, SIO_INDEX); - outb_p(SIO_PM_LSB, SIO_DATA); /* LSB of PM base address */ - - outb_p(SIO_DEV_ENB, SIO_INDEX); - outb_p(1, SIO_DATA); /* Enable PM registers. */ - - /* - * Now, write the PM register which enables the GPIO registers. - */ - outb_p(SIO_PM_FER2, SIO_PM_INDEX); - outb_p(SIO_PM_GP_EN, SIO_PM_DATA); - - /* - * Now, initialize the GPIO registers. - * We want them all to be inputs which is the - * power on default, so let's leave them alone. - * So, let's just read the board rev! - */ - raw = inb_p(SIO_GP_DATA1); - raw &= 0x7f; /* 7 bits of valid board revision ID. */ - - if (visws_board_type == VISWS_320) { - if (raw < 0x6) { - visws_board_rev = 4; - } else if (raw < 0xc) { - visws_board_rev = 5; - } else { - visws_board_rev = 6; - } - } else if (visws_board_type == VISWS_540) { - visws_board_rev = 2; - } else { - visws_board_rev = raw; - } - - printk(KERN_INFO "Silicon Graphics Visual Workstation %s (rev %d) detected\n", - (visws_board_type == VISWS_320 ? "320" : - (visws_board_type == VISWS_540 ? "540" : - "unknown")), visws_board_rev); -} - -#define A01234 (LI_INTA_0 | LI_INTA_1 | LI_INTA_2 | LI_INTA_3 | LI_INTA_4) -#define BCD (LI_INTB | LI_INTC | LI_INTD) -#define ALLDEVS (A01234 | BCD) - -static __init void lithium_init(void) -{ - set_fixmap(FIX_LI_PCIA, LI_PCI_A_PHYS); - set_fixmap(FIX_LI_PCIB, LI_PCI_B_PHYS); - - if ((li_pcia_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcia_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { - printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'A'); -/* panic("This machine is not SGI Visual Workstation 320/540"); */ - } - - if ((li_pcib_read16(PCI_VENDOR_ID) != PCI_VENDOR_ID_SGI) || - (li_pcib_read16(PCI_DEVICE_ID) != PCI_DEVICE_ID_SGI_LITHIUM)) { - printk(KERN_EMERG "Lithium hostbridge %c not found\n", 'B'); -/* panic("This machine is not SGI Visual Workstation 320/540"); */ - } - - li_pcia_write16(LI_PCI_INTEN, ALLDEVS); - li_pcib_write16(LI_PCI_INTEN, ALLDEVS); -} - -static __init void cobalt_init(void) -{ - /* - * On normal SMP PC this is used only with SMP, but we have to - * use it and set it up here to start the Cobalt clock - */ - set_fixmap(FIX_APIC_BASE, APIC_DEFAULT_PHYS_BASE); - setup_local_APIC(); - printk(KERN_INFO "Local APIC Version %#x, ID %#x\n", - (unsigned int)apic_read(APIC_LVR), - (unsigned int)apic_read(APIC_ID)); - - set_fixmap(FIX_CO_CPU, CO_CPU_PHYS); - set_fixmap(FIX_CO_APIC, CO_APIC_PHYS); - printk(KERN_INFO "Cobalt Revision %#lx, APIC ID %#lx\n", - co_cpu_read(CO_CPU_REV), co_apic_read(CO_APIC_ID)); - - /* Enable Cobalt APIC being careful to NOT change the ID! */ - co_apic_write(CO_APIC_ID, co_apic_read(CO_APIC_ID) | CO_APIC_ENABLE); - - printk(KERN_INFO "Cobalt APIC enabled: ID reg %#lx\n", - co_apic_read(CO_APIC_ID)); -} - -static void __init visws_trap_init(void) -{ - lithium_init(); - cobalt_init(); -} - -/* - * IRQ controller / APIC support: - */ - -static DEFINE_SPINLOCK(cobalt_lock); - -/* - * Set the given Cobalt APIC Redirection Table entry to point - * to the given IDT vector/index. - */ -static inline void co_apic_set(int entry, int irq) -{ - co_apic_write(CO_APIC_LO(entry), CO_APIC_LEVEL | (irq + FIRST_EXTERNAL_VECTOR)); - co_apic_write(CO_APIC_HI(entry), 0); -} - -/* - * Cobalt (IO)-APIC functions to handle PCI devices. - */ -static inline int co_apic_ide0_hack(void) -{ - extern char visws_board_type; - extern char visws_board_rev; - - if (visws_board_type == VISWS_320 && visws_board_rev == 5) - return 5; - return CO_APIC_IDE0; -} - -static int is_co_apic(unsigned int irq) -{ - if (IS_CO_APIC(irq)) - return CO_APIC(irq); - - switch (irq) { - case 0: return CO_APIC_CPU; - case CO_IRQ_IDE0: return co_apic_ide0_hack(); - case CO_IRQ_IDE1: return CO_APIC_IDE1; - default: return -1; - } -} - - -/* - * This is the SGI Cobalt (IO-)APIC: - */ -static void enable_cobalt_irq(struct irq_data *data) -{ - co_apic_set(is_co_apic(data->irq), data->irq); -} - -static void disable_cobalt_irq(struct irq_data *data) -{ - int entry = is_co_apic(data->irq); - - co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK); - co_apic_read(CO_APIC_LO(entry)); -} - -static void ack_cobalt_irq(struct irq_data *data) -{ - unsigned long flags; - - spin_lock_irqsave(&cobalt_lock, flags); - disable_cobalt_irq(data); - apic_write(APIC_EOI, APIC_EOI_ACK); - spin_unlock_irqrestore(&cobalt_lock, flags); -} - -static struct irq_chip cobalt_irq_type = { - .name = "Cobalt-APIC", - .irq_enable = enable_cobalt_irq, - .irq_disable = disable_cobalt_irq, - .irq_ack = ack_cobalt_irq, -}; - - -/* - * This is the PIIX4-based 8259 that is wired up indirectly to Cobalt - * -- not the manner expected by the code in i8259.c. - * - * there is a 'master' physical interrupt source that gets sent to - * the CPU. But in the chipset there are various 'virtual' interrupts - * waiting to be handled. We represent this to Linux through a 'master' - * interrupt controller type, and through a special virtual interrupt- - * controller. Device drivers only see the virtual interrupt sources. - */ -static unsigned int startup_piix4_master_irq(struct irq_data *data) -{ - legacy_pic->init(0); - enable_cobalt_irq(data); - return 0; -} - -static struct irq_chip piix4_master_irq_type = { - .name = "PIIX4-master", - .irq_startup = startup_piix4_master_irq, - .irq_ack = ack_cobalt_irq, -}; - -static void pii4_mask(struct irq_data *data) { } - -static struct irq_chip piix4_virtual_irq_type = { - .name = "PIIX4-virtual", - .irq_mask = pii4_mask, -}; - -/* - * PIIX4-8259 master/virtual functions to handle interrupt requests - * from legacy devices: floppy, parallel, serial, rtc. - * - * None of these get Cobalt APIC entries, neither do they have IDT - * entries. These interrupts are purely virtual and distributed from - * the 'master' interrupt source: CO_IRQ_8259. - * - * When the 8259 interrupts its handler figures out which of these - * devices is interrupting and dispatches to its handler. - * - * CAREFUL: devices see the 'virtual' interrupt only. Thus disable/ - * enable_irq gets the right irq. This 'master' irq is never directly - * manipulated by any driver. - */ -static irqreturn_t piix4_master_intr(int irq, void *dev_id) -{ - unsigned long flags; - int realirq; - - raw_spin_lock_irqsave(&i8259A_lock, flags); - - /* Find out what's interrupting in the PIIX4 master 8259 */ - outb(0x0c, 0x20); /* OCW3 Poll command */ - realirq = inb(0x20); - - /* - * Bit 7 == 0 means invalid/spurious - */ - if (unlikely(!(realirq & 0x80))) - goto out_unlock; - - realirq &= 7; - - if (unlikely(realirq == 2)) { - outb(0x0c, 0xa0); - realirq = inb(0xa0); - - if (unlikely(!(realirq & 0x80))) - goto out_unlock; - - realirq = (realirq & 7) + 8; - } - - /* mask and ack interrupt */ - cached_irq_mask |= 1 << realirq; - if (unlikely(realirq > 7)) { - inb(0xa1); - outb(cached_slave_mask, 0xa1); - outb(0x60 + (realirq & 7), 0xa0); - outb(0x60 + 2, 0x20); - } else { - inb(0x21); - outb(cached_master_mask, 0x21); - outb(0x60 + realirq, 0x20); - } - - raw_spin_unlock_irqrestore(&i8259A_lock, flags); - - /* - * handle this 'virtual interrupt' as a Cobalt one now. - */ - generic_handle_irq(realirq); - - return IRQ_HANDLED; - -out_unlock: - raw_spin_unlock_irqrestore(&i8259A_lock, flags); - return IRQ_NONE; -} - -static struct irqaction master_action = { - .handler = piix4_master_intr, - .name = "PIIX4-8259", - .flags = IRQF_NO_THREAD, -}; - -static struct irqaction cascade_action = { - .handler = no_action, - .name = "cascade", - .flags = IRQF_NO_THREAD, -}; - -static inline void set_piix4_virtual_irq_type(void) -{ - piix4_virtual_irq_type.irq_enable = i8259A_chip.irq_unmask; - piix4_virtual_irq_type.irq_disable = i8259A_chip.irq_mask; - piix4_virtual_irq_type.irq_unmask = i8259A_chip.irq_unmask; -} - -static void __init visws_pre_intr_init(void) -{ - int i; - - set_piix4_virtual_irq_type(); - - for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) { - struct irq_chip *chip = NULL; - - if (i == 0) - chip = &cobalt_irq_type; - else if (i == CO_IRQ_IDE0) - chip = &cobalt_irq_type; - else if (i == CO_IRQ_IDE1) - chip = &cobalt_irq_type; - else if (i == CO_IRQ_8259) - chip = &piix4_master_irq_type; - else if (i < CO_IRQ_APIC0) - chip = &piix4_virtual_irq_type; - else if (IS_CO_APIC(i)) - chip = &cobalt_irq_type; - - if (chip) - irq_set_chip(i, chip); - } - - setup_irq(CO_IRQ_8259, &master_action); - setup_irq(2, &cascade_action); -} |