Revert "x86-64/efi: Use EFI to deal with platform wall clock (again)"

This reverts commit bd52276fa1 ("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 53b87cf088 ("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 <yinghai@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

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,

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);
 

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);

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();

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;

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;
 

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);