From 11520e5e7c1855fc3bf202bb3be35a39d9efa034 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sat, 15 Dec 2012 15:15:24 -0800 Subject: [PATCH] Revert "x86-64/efi: Use EFI to deal with platform wall clock (again)" This reverts commit bd52276fa1d4 ("x86-64/efi: Use EFI to deal with platform wall clock (again)"), and the two supporting commits: da5a108d05b4: "x86/kernel: remove tboot 1:1 page table creation code" 185034e72d59: "x86, efi: 1:1 pagetable mapping for virtual EFI calls") as they all depend semantically on commit 53b87cf088e2 ("x86, mm: Include the entire kernel memory map in trampoline_pgd") that got reverted earlier due to the problems it caused. This was pointed out by Yinghai Lu, and verified by me on my Macbook Air that uses EFI. Pointed-out-by: Yinghai Lu Signed-off-by: Linus Torvalds --- arch/x86/include/asm/efi.h | 28 +++--------- arch/x86/kernel/tboot.c | 78 +++++++++++++++++++++++++++++++--- arch/x86/mm/pageattr.c | 10 ++--- arch/x86/platform/efi/efi.c | 30 +++++++++++-- arch/x86/platform/efi/efi_64.c | 15 ------- include/linux/efi.h | 2 + init/main.c | 8 ++-- 7 files changed, 116 insertions(+), 55 deletions(-) diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index fd13815fe85c..6e8fdf5ad113 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -69,37 +69,23 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3, efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3), \ (u64)(a4), (u64)(a5), (u64)(a6)) -extern unsigned long efi_call_virt_prelog(void); -extern void efi_call_virt_epilog(unsigned long); - -#define efi_callx(x, func, ...) \ - ({ \ - efi_status_t __status; \ - unsigned long __pgd; \ - \ - __pgd = efi_call_virt_prelog(); \ - __status = efi_call##x(func, __VA_ARGS__); \ - efi_call_virt_epilog(__pgd); \ - __status; \ - }) - #define efi_call_virt0(f) \ - efi_callx(0, (void *)(efi.systab->runtime->f)) + efi_call0((void *)(efi.systab->runtime->f)) #define efi_call_virt1(f, a1) \ - efi_callx(1, (void *)(efi.systab->runtime->f), (u64)(a1)) + efi_call1((void *)(efi.systab->runtime->f), (u64)(a1)) #define efi_call_virt2(f, a1, a2) \ - efi_callx(2, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2)) + efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2)) #define efi_call_virt3(f, a1, a2, a3) \ - efi_callx(3, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3)) #define efi_call_virt4(f, a1, a2, a3, a4) \ - efi_callx(4, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + 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_callx(5, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + 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_callx(6, (void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ + efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \ (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6)) extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index d4f460f962ee..f84fe00fad48 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -103,13 +103,71 @@ void __init tboot_probe(void) pr_debug("tboot_size: 0x%x\n", tboot->tboot_size); } +static pgd_t *tboot_pg_dir; +static struct mm_struct tboot_mm = { + .mm_rb = RB_ROOT, + .pgd = swapper_pg_dir, + .mm_users = ATOMIC_INIT(2), + .mm_count = ATOMIC_INIT(1), + .mmap_sem = __RWSEM_INITIALIZER(init_mm.mmap_sem), + .page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock), + .mmlist = LIST_HEAD_INIT(init_mm.mmlist), +}; + static inline void switch_to_tboot_pt(void) { -#ifdef CONFIG_X86_32 - load_cr3(initial_page_table); -#else - write_cr3(real_mode_header->trampoline_pgd); -#endif + write_cr3(virt_to_phys(tboot_pg_dir)); +} + +static int map_tboot_page(unsigned long vaddr, unsigned long pfn, + pgprot_t prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset(&tboot_mm, vaddr); + pud = pud_alloc(&tboot_mm, pgd, vaddr); + if (!pud) + return -1; + pmd = pmd_alloc(&tboot_mm, pud, vaddr); + if (!pmd) + return -1; + pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr); + if (!pte) + return -1; + set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot)); + pte_unmap(pte); + return 0; +} + +static int map_tboot_pages(unsigned long vaddr, unsigned long start_pfn, + unsigned long nr) +{ + /* Reuse the original kernel mapping */ + tboot_pg_dir = pgd_alloc(&tboot_mm); + if (!tboot_pg_dir) + return -1; + + for (; nr > 0; nr--, vaddr += PAGE_SIZE, start_pfn++) { + if (map_tboot_page(vaddr, start_pfn, PAGE_KERNEL_EXEC)) + return -1; + } + + return 0; +} + +static void tboot_create_trampoline(void) +{ + u32 map_base, map_size; + + /* Create identity map for tboot shutdown code. */ + map_base = PFN_DOWN(tboot->tboot_base); + map_size = PFN_UP(tboot->tboot_size); + if (map_tboot_pages(map_base << PAGE_SHIFT, map_base, map_size)) + panic("tboot: Error mapping tboot pages (mfns) @ 0x%x, 0x%x\n", + map_base, map_size); } #ifdef CONFIG_ACPI_SLEEP @@ -167,6 +225,14 @@ void tboot_shutdown(u32 shutdown_type) if (!tboot_enabled()) return; + /* + * if we're being called before the 1:1 mapping is set up then just + * return and let the normal shutdown happen; this should only be + * due to very early panic() + */ + if (!tboot_pg_dir) + return; + /* if this is S3 then set regions to MAC */ if (shutdown_type == TB_SHUTDOWN_S3) if (tboot_setup_sleep()) @@ -277,6 +343,8 @@ static __init int tboot_late_init(void) if (!tboot_enabled()) return 0; + tboot_create_trampoline(); + atomic_set(&ap_wfs_count, 0); register_hotcpu_notifier(&tboot_cpu_notifier); diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 931930a96160..a718e0d23503 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -919,13 +919,11 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages, /* * On success we use clflush, when the CPU supports it to - * avoid the wbindv. If the CPU does not support it, in the - * error case, and during early boot (for EFI) we fall back - * to cpa_flush_all (which uses wbinvd): + * avoid the wbindv. If the CPU does not support it and in the + * error case we fall back to cpa_flush_all (which uses + * wbindv): */ - if (early_boot_irqs_disabled) - __cpa_flush_all((void *)(long)cache); - else if (!ret && cpu_has_clflush) { + if (!ret && cpu_has_clflush) { if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) { cpa_flush_array(addr, numpages, cache, cpa.flags, pages); diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 0a34d9e9c263..ad4439145f85 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -239,7 +239,22 @@ static efi_status_t __init phys_efi_set_virtual_address_map( return status; } -static int efi_set_rtc_mmss(unsigned long nowtime) +static efi_status_t __init phys_efi_get_time(efi_time_t *tm, + efi_time_cap_t *tc) +{ + unsigned long flags; + efi_status_t status; + + spin_lock_irqsave(&rtc_lock, flags); + efi_call_phys_prelog(); + status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm), + virt_to_phys(tc)); + efi_call_phys_epilog(); + spin_unlock_irqrestore(&rtc_lock, flags); + return status; +} + +int efi_set_rtc_mmss(unsigned long nowtime) { int real_seconds, real_minutes; efi_status_t status; @@ -268,7 +283,7 @@ static int efi_set_rtc_mmss(unsigned long nowtime) return 0; } -static unsigned long efi_get_time(void) +unsigned long efi_get_time(void) { efi_status_t status; efi_time_t eft; @@ -624,13 +639,18 @@ static int __init efi_runtime_init(void) } /* * We will only need *early* access to the following - * EFI runtime service before set_virtual_address_map + * 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; early_iounmap(runtime, sizeof(efi_runtime_services_t)); return 0; @@ -716,10 +736,12 @@ void __init efi_init(void) efi_enabled = 0; return; } +#ifdef CONFIG_X86_32 if (efi_is_native()) { x86_platform.get_wallclock = efi_get_time; x86_platform.set_wallclock = efi_set_rtc_mmss; } +#endif #if EFI_DEBUG print_efi_memmap(); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index 06c8b2e662ab..95fd505dfeb6 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -58,21 +58,6 @@ static void __init early_code_mapping_set_exec(int executable) } } -unsigned long efi_call_virt_prelog(void) -{ - unsigned long saved; - - saved = read_cr3(); - write_cr3(real_mode_header->trampoline_pgd); - - return saved; -} - -void efi_call_virt_epilog(unsigned long saved) -{ - write_cr3(saved); -} - void __init efi_call_phys_prelog(void) { unsigned long vaddress; diff --git a/include/linux/efi.h b/include/linux/efi.h index 02a69418be18..8b84916dc671 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -587,6 +587,8 @@ extern u64 efi_mem_attribute (unsigned long phys_addr, unsigned long size); extern int __init efi_uart_console_only (void); extern void efi_initialize_iomem_resources(struct resource *code_resource, struct resource *data_resource, struct resource *bss_resource); +extern unsigned long efi_get_time(void); +extern int efi_set_rtc_mmss(unsigned long nowtime); extern void efi_reserve_boot_services(void); extern struct efi_memory_map memmap; diff --git a/init/main.c b/init/main.c index 6af5470b8067..63ae904a99a8 100644 --- a/init/main.c +++ b/init/main.c @@ -463,10 +463,6 @@ static void __init mm_init(void) percpu_init_late(); pgtable_cache_init(); vmalloc_init(); -#ifdef CONFIG_X86 - if (efi_enabled) - efi_enter_virtual_mode(); -#endif } asmlinkage void __init start_kernel(void) @@ -607,6 +603,10 @@ asmlinkage void __init start_kernel(void) calibrate_delay(); pidmap_init(); anon_vma_init(); +#ifdef CONFIG_X86 + if (efi_enabled) + efi_enter_virtual_mode(); +#endif thread_info_cache_init(); cred_init(); fork_init(totalram_pages);