Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/li…

…nux/kernel/git/tip/linux-2.6-tip

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  ptrace, x86: fix the usage of ptrace_fork()
  i8327: fix outb() parameter order
  x86: fix math_emu register frame access
  x86: math_emu info cleanup
  x86: include correct %gs in a.out core dump
  x86, vmi: put a missing paravirt_release_pmd in pgd_dtor
  x86: find nr_irqs_gsi with mp_ioapic_routing
  x86: add clflush before monitor for Intel 7400 series
  x86: disable intel_iommu support by default
  x86: don't apply __supported_pte_mask to non-present ptes
  x86: fix grammar in user-visible BIOS warning
  x86/Kconfig.cpu: make Kconfig help readable in the console
  x86, 64-bit: print DMI info in the oops trace

Documentation/kernel-parameters.txt

@@ -937,6 +937,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 
 	intel_iommu=	[DMAR] Intel IOMMU driver (DMAR) option
+		on
+			Enable intel iommu driver.
 		off
 			Disable intel iommu driver.
 		igfx_off [Default Off]

arch/x86/Kconfig

@@ -1802,6 +1802,17 @@ config DMAR
 	  and include PCI device scope covered by these DMA
 	  remapping devices.
 
+config DMAR_DEFAULT_ON
+	def_bool n
+	prompt "Enable DMA Remapping Devices by default"
+	depends on DMAR
+	help
+	  Selecting this option will enable a DMAR device at boot time if
+	  one is found. If this option is not selected, DMAR support can
+	  be enabled by passing intel_iommu=on to the kernel. It is
+	  recommended you say N here while the DMAR code remains
+	  experimental.
+
 config DMAR_GFX_WA
 	def_bool y
 	prompt "Support for Graphics workaround"

arch/x86/Kconfig.cpu

@@ -167,9 +167,9 @@ config MK7
 config MK8
 	bool "Opteron/Athlon64/Hammer/K8"
 	help
-	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.  Enables
-	  use of some extended instructions, and passes appropriate optimization
-	  flags to GCC.
+	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
+	  Enables use of some extended instructions, and passes appropriate
+	  optimization flags to GCC.
 
 config MCRUSOE
 	bool "Crusoe"
@@ -256,9 +256,11 @@ config MPSC
 config MCORE2
 	bool "Core 2/newer Xeon"
 	help
-	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and 53xx)
-	  CPUs. You can distinguish newer from older Xeons by the CPU family
-	  in /proc/cpuinfo. Newer ones have 6 and older ones 15 (not a typo)
+
+	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
+	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
+	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
+	  (not a typo)
 
 config GENERIC_CPU
 	bool "Generic-x86-64"
@@ -320,14 +322,14 @@ config X86_PPRO_FENCE
 	bool "PentiumPro memory ordering errata workaround"
 	depends on M686 || M586MMX || M586TSC || M586 || M486 || M386 || MGEODEGX1
 	help
-	  Old PentiumPro multiprocessor systems had errata that could cause memory
-	  operations to violate the x86 ordering standard in rare cases. Enabling this
-	  option will attempt to work around some (but not all) occurances of
-	  this problem, at the cost of much heavier spinlock and memory barrier
-	  operations.
+	  Old PentiumPro multiprocessor systems had errata that could cause
+	  memory operations to violate the x86 ordering standard in rare cases.
+	  Enabling this option will attempt to work around some (but not all)
+	  occurances of this problem, at the cost of much heavier spinlock and
+	  memory barrier operations.
 
-	  If unsure, say n here. Even distro kernels should think twice before enabling
-	  this: there are few systems, and an unlikely bug.
+	  If unsure, say n here. Even distro kernels should think twice before
+	  enabling this: there are few systems, and an unlikely bug.
 
 config X86_F00F_BUG
 	def_bool y

arch/x86/include/asm/a.out-core.h

@@ -23,8 +23,6 @@
  */
 static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 {
-	u16 gs;
-
 /* changed the size calculations - should hopefully work better. lbt */
 	dump->magic = CMAGIC;
 	dump->start_code = 0;
@@ -57,7 +55,7 @@ static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
 	dump->regs.ds = (u16)regs->ds;
 	dump->regs.es = (u16)regs->es;
 	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs, gs);
+	savesegment(gs, dump->regs.gs);
 	dump->regs.orig_ax = regs->orig_ax;
 	dump->regs.ip = regs->ip;
 	dump->regs.cs = (u16)regs->cs;

arch/x86/include/asm/cpufeature.h

@@ -93,6 +93,7 @@
 #define X86_FEATURE_XTOPOLOGY	(3*32+22) /* cpu topology enum extensions */
 #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
+#define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */

arch/x86/include/asm/math_emu.h

@@ -1,31 +1,18 @@
 #ifndef _ASM_X86_MATH_EMU_H
 #define _ASM_X86_MATH_EMU_H
 
+#include <asm/ptrace.h>
+#include <asm/vm86.h>
+
 /* This structure matches the layout of the data saved to the stack
    following a device-not-present interrupt, part of it saved
    automatically by the 80386/80486.
    */
-struct info {
+struct math_emu_info {
 	long ___orig_eip;
-	long ___ebx;
-	long ___ecx;
-	long ___edx;
-	long ___esi;
-	long ___edi;
-	long ___ebp;
-	long ___eax;
-	long ___ds;
-	long ___es;
-	long ___fs;
-	long ___orig_eax;
-	long ___eip;
-	long ___cs;
-	long ___eflags;
-	long ___esp;
-	long ___ss;
-	long ___vm86_es; /* This and the following only in vm86 mode */
-	long ___vm86_ds;
-	long ___vm86_fs;
-	long ___vm86_gs;
+	union {
+		struct pt_regs *regs;
+		struct kernel_vm86_regs *vm86;
+	};
 };
 #endif /* _ASM_X86_MATH_EMU_H */

arch/x86/include/asm/mpspec.h

@@ -60,6 +60,7 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+extern int acpi_probe_gsi(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
@@ -71,6 +72,11 @@ mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 	return 0;
 }
 #endif
+#else /* !CONFIG_ACPI: */
+static inline int acpi_probe_gsi(void)
+{
+	return 0;
+}
 #endif /* CONFIG_ACPI */
 
 #define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)

arch/x86/include/asm/pgtable.h

@@ -302,16 +302,30 @@ static inline pte_t pte_mkspecial(pte_t pte)
 
 extern pteval_t __supported_pte_mask;
 
+/*
+ * Mask out unsupported bits in a present pgprot.  Non-present pgprots
+ * can use those bits for other purposes, so leave them be.
+ */
+static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
+{
+	pgprotval_t protval = pgprot_val(pgprot);
+
+	if (protval & _PAGE_PRESENT)
+		protval &= __supported_pte_mask;
+
+	return protval;
+}
+
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
+	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
+		     massage_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
+	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
+		     massage_pgprot(pgprot));
 }
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
@@ -323,7 +337,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 * the newprot (if present):
 	 */
 	val &= _PAGE_CHG_MASK;
-	val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
+	val |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
 
 	return __pte(val);
 }
@@ -339,7 +353,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
 
-#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
+#define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
 static inline int is_new_memtype_allowed(unsigned long flags,
 						unsigned long new_flags)

arch/x86/include/asm/processor.h

@@ -353,7 +353,7 @@ struct i387_soft_struct {
 	u8			no_update;
 	u8			rm;
 	u8			alimit;
-	struct info		*info;
+	struct math_emu_info	*info;
 	u32			entry_eip;
 };
 

arch/x86/include/asm/traps.h

@@ -41,7 +41,7 @@ dotraplinkage void do_int3(struct pt_regs *, long);
 dotraplinkage void do_overflow(struct pt_regs *, long);
 dotraplinkage void do_bounds(struct pt_regs *, long);
 dotraplinkage void do_invalid_op(struct pt_regs *, long);
-dotraplinkage void do_device_not_available(struct pt_regs *, long);
+dotraplinkage void do_device_not_available(struct pt_regs);
 dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
@@ -77,7 +77,7 @@ extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
 
 void math_error(void __user *);
-asmlinkage void math_emulate(long);
+void math_emulate(struct math_emu_info *);
 #ifdef CONFIG_X86_32
 unsigned long patch_espfix_desc(unsigned long, unsigned long);
 #else

arch/x86/include/asm/xen/page.h

@@ -137,7 +137,7 @@ static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
 	pte_t pte;
 
 	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
-		(pgprot_val(pgprot) & __supported_pte_mask);
+			massage_pgprot(pgprot);
 
 	return pte;
 }

arch/x86/kernel/acpi/boot.c

@@ -973,6 +973,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	nr_ioapics++;
 }
 
+int __init acpi_probe_gsi(void)
+{
+	int idx;
+	int gsi;
+	int max_gsi = 0;
+
+	if (acpi_disabled)
+		return 0;
+
+	if (!acpi_ioapic)
+		return 0;
+
+	max_gsi = 0;
+	for (idx = 0; idx < nr_ioapics; idx++) {
+		gsi = mp_ioapic_routing[idx].gsi_end;
+
+		if (gsi > max_gsi)
+			max_gsi = gsi;
+	}
+
+	return max_gsi + 1;
+}
+
 static void assign_to_mp_irq(struct mp_config_intsrc *m,
 				    struct mp_config_intsrc *mp_irq)
 {

arch/x86/kernel/cpu/intel.c

@@ -291,6 +291,9 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
 		ds_init_intel(c);
 	}
 
+	if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush)
+		set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR);
+
 #ifdef CONFIG_X86_64
 	if (c->x86 == 15)
 		c->x86_cache_alignment = c->x86_clflush_size * 2;

arch/x86/kernel/i8237.c

@@ -28,10 +28,10 @@ static int i8237A_resume(struct sys_device *dev)
 
 	flags = claim_dma_lock();
 
-	dma_outb(DMA1_RESET_REG, 0);
-	dma_outb(DMA2_RESET_REG, 0);
+	dma_outb(0, DMA1_RESET_REG);
+	dma_outb(0, DMA2_RESET_REG);
 
-	for (i = 0;i < 8;i++) {
+	for (i = 0; i < 8; i++) {
 		set_dma_addr(i, 0x000000);
 		/* DMA count is a bit weird so this is not 0 */
 		set_dma_count(i, 1);
@@ -51,14 +51,14 @@ static int i8237A_suspend(struct sys_device *dev, pm_message_t state)
 }
 
 static struct sysdev_class i8237_sysdev_class = {
-	.name = "i8237",
-	.suspend = i8237A_suspend,
-	.resume = i8237A_resume,
+	.name		= "i8237",
+	.suspend	= i8237A_suspend,
+	.resume		= i8237A_resume,
 };
 
 static struct sys_device device_i8237A = {
-	.id	= 0,
-	.cls	= &i8237_sysdev_class,
+	.id		= 0,
+	.cls		= &i8237_sysdev_class,
 };
 
 static int __init i8237A_init_sysfs(void)
@@ -68,5 +68,4 @@ static int __init i8237A_init_sysfs(void)
 		error = sysdev_register(&device_i8237A);
 	return error;
 }
-
 device_initcall(i8237A_init_sysfs);

arch/x86/kernel/io_apic.c

@@ -3841,14 +3841,24 @@ int __init io_apic_get_redir_entries (int ioapic)
 
 void __init probe_nr_irqs_gsi(void)
 {
-	int idx;
 	int nr = 0;
 
-	for (idx = 0; idx < nr_ioapics; idx++)
-		nr += io_apic_get_redir_entries(idx) + 1;
-
-	if (nr > nr_irqs_gsi)
+	nr = acpi_probe_gsi();
+	if (nr > nr_irqs_gsi) {
 		nr_irqs_gsi = nr;
+	} else {
+		/* for acpi=off or acpi is not compiled in */
+		int idx;
+
+		nr = 0;
+		for (idx = 0; idx < nr_ioapics; idx++)
+			nr += io_apic_get_redir_entries(idx) + 1;
+
+		if (nr > nr_irqs_gsi)
+			nr_irqs_gsi = nr;
+	}
+
+	printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi);
 }
 
 /* --------------------------------------------------------------------------

arch/x86/kernel/process.c

@@ -180,6 +180,9 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 
 	trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
 	if (!need_resched()) {
+		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
+
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
@@ -194,6 +197,9 @@ static void mwait_idle(void)
 	struct power_trace it;
 	if (!need_resched()) {
 		trace_power_start(&it, POWER_CSTATE, 1);
+		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
+			clflush((void *)&current_thread_info()->flags);
+
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())