Merge branch 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 fixes from Peter Anvin:
 "This is a collection of miscellaneous fixes, the most important one is
  the fix for the Samsung laptop bricking issue (auto-blacklisting the
  samsung-laptop driver); the efi_enabled() changes you see below are
  prerequisites for that fix.

  The other issues fixed are booting on OLPC XO-1.5, an UV fix, NMI
  debugging, and requiring CAP_SYS_RAWIO for MSR references, just as
  with I/O port references."

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  samsung-laptop: Disable on EFI hardware
  efi: Make 'efi_enabled' a function to query EFI facilities
  smp: Fix SMP function call empty cpu mask race
  x86/msr: Add capabilities check
  x86/dma-debug: Bump PREALLOC_DMA_DEBUG_ENTRIES
  x86/olpc: Fix olpc-xo1-sci.c build errors
  arch/x86/platform/uv: Fix incorrect tlb flush all issue
  x86-64: Fix unwind annotations in recent NMI changes
  x86-32: Start out cr0 clean, disable paging before modifying cr3/4

arch/x86/Kconfig

@@ -2138,6 +2138,7 @@ config OLPC_XO1_RTC
 config OLPC_XO1_SCI
 	bool "OLPC XO-1 SCI extras"
 	depends on OLPC && OLPC_XO1_PM
+	depends on INPUT=y
 	select POWER_SUPPLY
 	select GPIO_CS5535
 	select MFD_CORE

arch/x86/include/asm/efi.h

@@ -94,6 +94,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
+extern unsigned long x86_efi_facility;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);

arch/x86/include/asm/uv/uv.h

@@ -16,7 +16,7 @@ extern void uv_system_init(void);
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 						 struct mm_struct *mm,
 						 unsigned long start,
-						 unsigned end,
+						 unsigned long end,
 						 unsigned int cpu);
 
 #else	/* X86_UV */

arch/x86/kernel/entry_64.S

@@ -1781,6 +1781,7 @@ first_nmi:
 	 * Leave room for the "copied" frame
 	 */
 	subq $(5*8), %rsp
+	CFI_ADJUST_CFA_OFFSET 5*8
 
 	/* Copy the stack frame to the Saved frame */
 	.rept 5
@@ -1863,10 +1864,8 @@ end_repeat_nmi:
 nmi_swapgs:
 	SWAPGS_UNSAFE_STACK
 nmi_restore:
-	RESTORE_ALL 8
-
-	/* Pop the extra iret frame */
-	addq $(5*8), %rsp
+	/* Pop the extra iret frame at once */
+	RESTORE_ALL 6*8
 
 	/* Clear the NMI executing stack variable */
 	movq $0, 5*8(%rsp)

arch/x86/kernel/head_32.S

@@ -300,6 +300,12 @@ ENTRY(startup_32_smp)
 	leal -__PAGE_OFFSET(%ecx),%esp
 
 default_entry:
+#define CR0_STATE	(X86_CR0_PE | X86_CR0_MP | X86_CR0_ET | \
+			 X86_CR0_NE | X86_CR0_WP | X86_CR0_AM | \
+			 X86_CR0_PG)
+	movl $(CR0_STATE & ~X86_CR0_PG),%eax
+	movl %eax,%cr0
+
 /*
  *	New page tables may be in 4Mbyte page mode and may
  *	be using the global pages. 
@@ -364,8 +370,7 @@ default_entry:
  */
 	movl $pa(initial_page_table), %eax
 	movl %eax,%cr3		/* set the page table pointer.. */
-	movl %cr0,%eax
-	orl  $X86_CR0_PG,%eax
+	movl $CR0_STATE,%eax
 	movl %eax,%cr0		/* ..and set paging (PG) bit */
 	ljmp $__BOOT_CS,$1f	/* Clear prefetch and normalize %eip */
 1:

arch/x86/kernel/msr.c

@@ -174,6 +174,9 @@ static int msr_open(struct inode *inode, struct file *file)
 	unsigned int cpu;
 	struct cpuinfo_x86 *c;
 
+	if (!capable(CAP_SYS_RAWIO))
+		return -EPERM;
+
 	cpu = iminor(file->f_path.dentry->d_inode);
 	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return -ENXIO;	/* No such CPU */

arch/x86/kernel/pci-dma.c

@@ -56,7 +56,7 @@ struct device x86_dma_fallback_dev = {
 EXPORT_SYMBOL(x86_dma_fallback_dev);
 
 /* Number of entries preallocated for DMA-API debugging */
-#define PREALLOC_DMA_DEBUG_ENTRIES       32768
+#define PREALLOC_DMA_DEBUG_ENTRIES       65536
 
 int dma_set_mask(struct device *dev, u64 mask)
 {

arch/x86/kernel/reboot.c

@@ -584,7 +584,7 @@ static void native_machine_emergency_restart(void)
 			break;
 
 		case BOOT_EFI:
-			if (efi_enabled)
+			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,

arch/x86/kernel/setup.c

@@ -807,15 +807,15 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
 	if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL32", 4)) {
-		efi_enabled = 1;
-		efi_64bit = false;
+		set_bit(EFI_BOOT, &x86_efi_facility);
 	} else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
 		     "EL64", 4)) {
-		efi_enabled = 1;
-		efi_64bit = true;
+		set_bit(EFI_BOOT, &x86_efi_facility);
+		set_bit(EFI_64BIT, &x86_efi_facility);
 	}
-	if (efi_enabled && efi_memblock_x86_reserve_range())
-		efi_enabled = 0;
+
+	if (efi_enabled(EFI_BOOT))
+		efi_memblock_x86_reserve_range();
 #endif
 
 	x86_init.oem.arch_setup();
@@ -888,7 +888,7 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_BOOT))
 		efi_init();
 
 	dmi_scan_machine();
@@ -971,7 +971,7 @@ void __init setup_arch(char **cmdline_p)
 	 * The EFI specification says that boot service code won't be called
 	 * after ExitBootServices(). This is, in fact, a lie.
 	 */
-	if (efi_enabled)
+	if (efi_enabled(EFI_MEMMAP))
 		efi_reserve_boot_services();
 
 	/* preallocate 4k for mptable mpc */
@@ -1114,7 +1114,7 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
-	if (!efi_enabled || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
+	if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY))
 		conswitchp = &vga_con;
 #elif defined(CONFIG_DUMMY_CONSOLE)
 	conswitchp = &dummy_con;
@@ -1131,14 +1131,14 @@ void __init setup_arch(char **cmdline_p)
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-	/* Once setup is done above, disable efi_enabled on mismatched
-	 * firmware/kernel archtectures since there is no support for
-	 * runtime services.
+	/* Once setup is done above, unmap the EFI memory map on
+	 * mismatched firmware/kernel archtectures since there is no
+	 * support for runtime services.
 	 */
-	if (efi_enabled && IS_ENABLED(CONFIG_X86_64) != efi_64bit) {
+	if (efi_enabled(EFI_BOOT) &&
+	    IS_ENABLED(CONFIG_X86_64) != efi_enabled(EFI_64BIT)) {
 		pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
 		efi_unmap_memmap();
-		efi_enabled = 0;
 	}
 #endif
 }

arch/x86/platform/efi/efi.c

@@ -51,9 +51,6 @@
 
 #define EFI_DEBUG	1
 
-int efi_enabled;
-EXPORT_SYMBOL(efi_enabled);
-
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
 	.acpi       = EFI_INVALID_TABLE_ADDR,
@@ -69,19 +66,28 @@ EXPORT_SYMBOL(efi);
 
 struct efi_memory_map memmap;
 
-bool efi_64bit;
-
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
 static inline bool efi_is_native(void)
 {
-	return IS_ENABLED(CONFIG_X86_64) == efi_64bit;
+	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
+}
+
+unsigned long x86_efi_facility;
+
+/*
+ * 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 int __init setup_noefi(char *arg)
 {
-	efi_enabled = 0;
+	clear_bit(EFI_BOOT, &x86_efi_facility);
 	return 0;
 }
 early_param("noefi", setup_noefi);
@@ -426,6 +432,7 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_unmap_memmap(void)
 {
+	clear_bit(EFI_MEMMAP, &x86_efi_facility);
 	if (memmap.map) {
 		early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
 		memmap.map = NULL;
@@ -460,7 +467,7 @@ void __init efi_free_boot_services(void)
 
 static int __init efi_systab_init(void *phys)
 {
-	if (efi_64bit) {
+	if (efi_enabled(EFI_64BIT)) {
 		efi_system_table_64_t *systab64;
 		u64 tmp = 0;
 
@@ -552,7 +559,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 	void *config_tables, *tablep;
 	int i, sz;
 
-	if (efi_64bit)
+	if (efi_enabled(EFI_64BIT))
 		sz = sizeof(efi_config_table_64_t);
 	else
 		sz = sizeof(efi_config_table_32_t);
@@ -572,7 +579,7 @@ static int __init efi_config_init(u64 tables, int nr_tables)
 		efi_guid_t guid;
 		unsigned long table;
 
-		if (efi_64bit) {
+		if (efi_enabled(EFI_64BIT)) {
 			u64 table64;
 			guid = ((efi_config_table_64_t *)tablep)->guid;
 			table64 = ((efi_config_table_64_t *)tablep)->table;
@@ -684,7 +691,6 @@ void __init efi_init(void)
 	if (boot_params.efi_info.efi_systab_hi ||
 	    boot_params.efi_info.efi_memmap_hi) {
 		pr_info("Table located above 4GB, disabling EFI.\n");
-		efi_enabled = 0;
 		return;
 	}
 	efi_phys.systab = (efi_system_table_t *)boot_params.efi_info.efi_systab;
@@ -694,10 +700,10 @@ void __init efi_init(void)
 			  ((__u64)boot_params.efi_info.efi_systab_hi<<32));
 #endif
 
-	if (efi_systab_init(efi_phys.systab)) {
-		efi_enabled = 0;
+	if (efi_systab_init(efi_phys.systab))
 		return;
-	}
+
+	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
 	 * Show what we know for posterity
@@ -715,10 +721,10 @@ void __init efi_init(void)
 		efi.systab->hdr.revision >> 16,
 		efi.systab->hdr.revision & 0xffff, vendor);
 
-	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables)) {
-		efi_enabled = 0;
+	if (efi_config_init(efi.systab->tables, efi.systab->nr_tables))
 		return;
-	}
+
+	set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
 
 	/*
 	 * Note: We currently don't support runtime services on an EFI
@@ -727,15 +733,17 @@ void __init efi_init(void)
 
 	if (!efi_is_native())
 		pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
-	else if (efi_runtime_init()) {
-		efi_enabled = 0;
-		return;
+	else {
+		if (efi_runtime_init())
+			return;
+		set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
 	}
 
-	if (efi_memmap_init()) {
-		efi_enabled = 0;
+	if (efi_memmap_init())
 		return;
-	}
+
+	set_bit(EFI_MEMMAP, &x86_efi_facility);
+
 #ifdef CONFIG_X86_32
 	if (efi_is_native()) {
 		x86_platform.get_wallclock = efi_get_time;
@@ -969,6 +977,9 @@ u32 efi_mem_type(unsigned long phys_addr)
 	efi_memory_desc_t *md;
 	void *p;
 
+	if (!efi_enabled(EFI_MEMMAP))
+		return 0;
+
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		md = p;
 		if ((md->phys_addr <= phys_addr) &&

arch/x86/platform/uv/tlb_uv.c

@@ -1034,7 +1034,8 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  * globally purge translation cache of a virtual address or all TLB's
  * @cpumask: mask of all cpu's in which the address is to be removed
  * @mm: mm_struct containing virtual address range
- * @va: virtual address to be removed (or TLB_FLUSH_ALL for all TLB's on cpu)
+ * @start: start virtual address to be removed from TLB
+ * @end: end virtual address to be remove from TLB
  * @cpu: the current cpu
  *
  * This is the entry point for initiating any UV global TLB shootdown.
@@ -1056,7 +1057,7 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 				struct mm_struct *mm, unsigned long start,
-				unsigned end, unsigned int cpu)
+				unsigned long end, unsigned int cpu)
 {
 	int locals = 0;
 	int remotes = 0;
@@ -1113,7 +1114,10 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
-	bau_desc->payload.address = start;
+	if (!end || (end - start) <= PAGE_SIZE)
+		bau_desc->payload.address = start;
+	else
+		bau_desc->payload.address = TLB_FLUSH_ALL;
 	bau_desc->payload.sending_cpu = cpu;
 	/*
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,

drivers/acpi/osl.c

@@ -250,7 +250,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void)
 		return acpi_rsdp;
 #endif
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.acpi20 != EFI_INVALID_TABLE_ADDR)
 			return efi.acpi20;
 		else if (efi.acpi != EFI_INVALID_TABLE_ADDR)

drivers/firmware/dmi_scan.c

@@ -471,7 +471,7 @@ void __init dmi_scan_machine(void)
 	char __iomem *p, *q;
 	int rc;
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_CONFIG_TABLES)) {
 		if (efi.smbios == EFI_INVALID_TABLE_ADDR)
 			goto error;
 

drivers/firmware/efivars.c

@@ -1782,7 +1782,7 @@ efivars_init(void)
 	printk(KERN_INFO "EFI Variables Facility v%s %s\n", EFIVARS_VERSION,
 	       EFIVARS_DATE);
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
 		return 0;
 
 	/* For now we'll register the efi directory at /sys/firmware/efi */
@@ -1822,7 +1822,7 @@ err_put:
 static void __exit
 efivars_exit(void)
 {
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		unregister_efivars(&__efivars);
 		kobject_put(efi_kobj);
 	}

drivers/firmware/iscsi_ibft_find.c

@@ -99,7 +99,7 @@ unsigned long __init find_ibft_region(unsigned long *sizep)
 	/* iBFT 1.03 section 1.4.3.1 mandates that UEFI machines will
 	 * only use ACPI for this */
 
-	if (!efi_enabled)
+	if (!efi_enabled(EFI_BOOT))
 		find_ibft_in_mem();
 
 	if (ibft_addr) {

drivers/gpu/drm/radeon/radeon_device.c

@@ -429,7 +429,8 @@ bool radeon_card_posted(struct radeon_device *rdev)
 {
 	uint32_t reg;
 
-	if (efi_enabled && rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
+	if (efi_enabled(EFI_BOOT) &&
+	    rdev->pdev->subsystem_vendor == PCI_VENDOR_ID_APPLE)
 		return false;
 
 	/* first check CRTCs */

drivers/platform/x86/ibm_rtl.c

@@ -244,7 +244,7 @@ static int __init ibm_rtl_init(void) {
 	if (force)
 		pr_warn("module loaded by force\n");
 	/* first ensure that we are running on IBM HW */
-	else if (efi_enabled || !dmi_check_system(ibm_rtl_dmi_table))
+	else if (efi_enabled(EFI_BOOT) || !dmi_check_system(ibm_rtl_dmi_table))
 		return -ENODEV;
 
 	/* Get the address for the Extended BIOS Data Area */

drivers/platform/x86/samsung-laptop.c

@@ -26,6 +26,7 @@
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
+#include <linux/efi.h>
 #include <acpi/video.h>
 
 /*
@@ -1544,6 +1545,9 @@ static int __init samsung_init(void)
 	struct samsung_laptop *samsung;
 	int ret;
 
+	if (efi_enabled(EFI_BOOT))
+		return -ENODEV;
+
 	quirks = &samsung_unknown;
 	if (!force && !dmi_check_system(samsung_dmi_table))
 		return -ENODEV;

drivers/scsi/isci/init.c

@@ -633,7 +633,7 @@ static int isci_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 	pci_set_drvdata(pdev, pci_info);
 
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		orom = isci_get_efi_var(pdev);
 
 	if (!orom)

include/linux/efi.h

@@ -618,18 +618,30 @@ extern int __init efi_setup_pcdp_console(char *);
 #endif
 
 /*
- * We play games with efi_enabled so that the compiler will, if possible, remove
- * EFI-related code altogether.
+ * We play games with efi_enabled so that the compiler will, if
+ * possible, remove EFI-related code altogether.
  */
+#define EFI_BOOT		0	/* Were we booted from EFI? */
+#define EFI_SYSTEM_TABLES	1	/* Can we use EFI system tables? */
+#define EFI_CONFIG_TABLES	2	/* Can we use EFI config tables? */
+#define EFI_RUNTIME_SERVICES	3	/* Can we use runtime services? */
+#define EFI_MEMMAP		4	/* Can we use EFI memory map? */
+#define EFI_64BIT		5	/* Is the firmware 64-bit? */
+
 #ifdef CONFIG_EFI
 # ifdef CONFIG_X86
-   extern int efi_enabled;
-   extern bool efi_64bit;
+extern int efi_enabled(int facility);
 # else
-#  define efi_enabled 1
+static inline int efi_enabled(int facility)
+{
+	return 1;
+}
 # endif
 #else
-# define efi_enabled 0
+static inline int efi_enabled(int facility)
+{
+	return 0;
+}
 #endif
 
 /*

init/main.c

@@ -604,7 +604,7 @@ asmlinkage void __init start_kernel(void)
 	pidmap_init();
 	anon_vma_init();
 #ifdef CONFIG_X86
-	if (efi_enabled)
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
 		efi_enter_virtual_mode();
 #endif
 	thread_info_cache_init();
@@ -632,7 +632,7 @@ asmlinkage void __init start_kernel(void)
 	acpi_early_init(); /* before LAPIC and SMP init */
 	sfi_init_late();
 
-	if (efi_enabled) {
+	if (efi_enabled(EFI_RUNTIME_SERVICES)) {
 		efi_late_init();
 		efi_free_boot_services();
 	}

kernel/smp.c

@@ -33,6 +33,7 @@ struct call_function_data {
 	struct call_single_data	csd;
 	atomic_t		refs;
 	cpumask_var_t		cpumask;
+	cpumask_var_t		cpumask_ipi;
 };
 
 static DEFINE_PER_CPU_SHARED_ALIGNED(struct call_function_data, cfd_data);
@@ -56,6 +57,9 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
 				cpu_to_node(cpu)))
 			return notifier_from_errno(-ENOMEM);
+		if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL,
+				cpu_to_node(cpu)))
+			return notifier_from_errno(-ENOMEM);
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -65,6 +69,7 @@ hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
 		free_cpumask_var(cfd->cpumask);
+		free_cpumask_var(cfd->cpumask_ipi);
 		break;
 #endif
 	};
@@ -526,6 +531,12 @@ void smp_call_function_many(const struct cpumask *mask,
 		return;
 	}
 
+	/*
+	 * After we put an entry into the list, data->cpumask
+	 * may be cleared again when another CPU sends another IPI for
+	 * a SMP function call, so data->cpumask will be zero.
+	 */
+	cpumask_copy(data->cpumask_ipi, data->cpumask);
 	raw_spin_lock_irqsave(&call_function.lock, flags);
 	/*
 	 * Place entry at the _HEAD_ of the list, so that any cpu still
@@ -549,7 +560,7 @@ void smp_call_function_many(const struct cpumask *mask,
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(data->cpumask);
+	arch_send_call_function_ipi_mask(data->cpumask_ipi);
 
 	/* Optionally wait for the CPUs to complete */
 	if (wait)