From 5d8b532af9e52ea89208f5ef31889f646e67ba28 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Fri, 16 Jan 2009 23:09:14 +0100
Subject: ACPI suspend: Fix compilation warnings in drivers/acpi/sleep.c

Fix two compilation warnings in drivers/acpi/sleep.c, one triggered
by unsetting CONFIG_SUSPEND and the other triggered by unsetting
CONFIG_HIBERNATION, by moving some code under the appropriate
#ifdefs .

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/kernel/acpi/sleep.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6f95f..a60c1f3bcb8 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -156,11 +156,11 @@ static int __init acpi_sleep_setup(char *str)
 #ifdef CONFIG_HIBERNATION
 		if (strncmp(str, "s4_nohwsig", 10) == 0)
 			acpi_no_s4_hw_signature();
+		if (strncmp(str, "s4_nonvs", 8) == 0)
+			acpi_s4_no_nvs();
 #endif
 		if (strncmp(str, "old_ordering", 12) == 0)
 			acpi_old_suspend_ordering();
-		if (strncmp(str, "s4_nonvs", 8) == 0)
-			acpi_s4_no_nvs();
 		str = strchr(str, ',');
 		if (str != NULL)
 			str += strspn(str, ", \t");
-- 
cgit v1.2.3-18-g5258


From ba2607fe9c1f2d4ad5a3d4c4ae9117c5bfdca826 Mon Sep 17 00:00:00 2001
From: Markus Metzger <markus.t.metzger@intel.com>
Date: Mon, 19 Jan 2009 10:38:35 +0100
Subject: x86, ds, bts: cleanup/fix DS configuration

Cleanup the cpuid check for DS configuration.

This also fixes a Corei7 CPUID enumeration bug.

Signed-off-by: Markus Metzger <markus.t.metzger@intel.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/ds.c | 31 +++++++++++++++++--------------
 1 file changed, 17 insertions(+), 14 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index da91701a234..169a120587b 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -15,8 +15,8 @@
  * - buffer allocation (memory accounting)
  *
  *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ * Copyright (C) 2007-2009 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2009
  */
 
 
@@ -890,7 +890,7 @@ int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value)
 }
 
 static const struct ds_configuration ds_cfg_netburst = {
-	.name = "netburst",
+	.name = "Netburst",
 	.ctl[dsf_bts]		= (1 << 2) | (1 << 3),
 	.ctl[dsf_bts_kernel]	= (1 << 5),
 	.ctl[dsf_bts_user]	= (1 << 6),
@@ -904,7 +904,7 @@ static const struct ds_configuration ds_cfg_netburst = {
 #endif
 };
 static const struct ds_configuration ds_cfg_pentium_m = {
-	.name = "pentium m",
+	.name = "Pentium M",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 
 	.sizeof_field		= sizeof(long),
@@ -915,8 +915,8 @@ static const struct ds_configuration ds_cfg_pentium_m = {
 	.sizeof_rec[ds_pebs]	= sizeof(long) * 18,
 #endif
 };
-static const struct ds_configuration ds_cfg_core2 = {
-	.name = "core 2",
+static const struct ds_configuration ds_cfg_core2_atom = {
+	.name = "Core 2/Atom",
 	.ctl[dsf_bts]		= (1 << 6) | (1 << 7),
 	.ctl[dsf_bts_kernel]	= (1 << 9),
 	.ctl[dsf_bts_user]	= (1 << 10),
@@ -949,19 +949,22 @@ void __cpuinit ds_init_intel(struct cpuinfo_x86 *c)
 	switch (c->x86) {
 	case 0x6:
 		switch (c->x86_model) {
-		case 0 ... 0xC:
-			/* sorry, don't know about them */
-			break;
-		case 0xD:
-		case 0xE: /* Pentium M */
+		case 0x9:
+		case 0xd: /* Pentium M */
 			ds_configure(&ds_cfg_pentium_m);
 			break;
-		default: /* Core2, Atom, ... */
-			ds_configure(&ds_cfg_core2);
+		case 0xf:
+		case 0x17: /* Core2 */
+		case 0x1c: /* Atom */
+			ds_configure(&ds_cfg_core2_atom);
+			break;
+		case 0x1a: /* i7 */
+		default:
+			/* sorry, don't know about them */
 			break;
 		}
 		break;
-	case 0xF:
+	case 0xf:
 		switch (c->x86_model) {
 		case 0x0:
 		case 0x1:
-- 
cgit v1.2.3-18-g5258


From 30a0fb947a68ad3ab8a7184e3b3d79dce10e3688 Mon Sep 17 00:00:00 2001
From: "H. Peter Anvin" <hpa@zytor.com>
Date: Mon, 26 Jan 2009 09:40:58 -0800
Subject: x86: correct the CPUID pattern for MSR_IA32_MISC_ENABLE availability

Impact: re-enable CPUID unmasking on affected processors

As far as I am capable of discerning from the documentation,
MSR_IA32_MISC_ENABLE should be available for all family 0xf CPUs, as
well as family 6 for model >= 0xd (newer Pentium M).

The documentation on this isn't ideal, so we need to be on the lookout
for errors, still.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/cpu/intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 549f2ada55f..430e5c38a54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -30,7 +30,7 @@
 static void __cpuinit early_init_intel(struct cpuinfo_x86 *c)
 {
 	/* Unmask CPUID levels if masked: */
-	if (c->x86 == 6 && c->x86_model >= 15) {
+	if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
 		u64 misc_enable;
 
 		rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-- 
cgit v1.2.3-18-g5258


From 57064d213d2e44654d4f13c66df135b5e7389a26 Mon Sep 17 00:00:00 2001
From: Seth Heasley <seth.heasley@intel.com>
Date: Fri, 23 Jan 2009 12:43:38 -0800
Subject: PCI: irq and pci_ids patch for Intel Tigerpoint DeviceIDs

This patch adds the Intel Tigerpoint LPC Controller DeviceIDs.

Signed-off-by: Seth Heasley <seth.heasley@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/pci/irq.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 4064345cf14..fecbce6e7d7 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -572,6 +572,7 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
 	case PCI_DEVICE_ID_INTEL_ICH7_1:
 	case PCI_DEVICE_ID_INTEL_ICH7_30:
 	case PCI_DEVICE_ID_INTEL_ICH7_31:
+	case PCI_DEVICE_ID_INTEL_TGP_LPC:
 	case PCI_DEVICE_ID_INTEL_ESB2_0:
 	case PCI_DEVICE_ID_INTEL_ICH8_0:
 	case PCI_DEVICE_ID_INTEL_ICH8_1:
-- 
cgit v1.2.3-18-g5258


From bf3647c44bc76c43c4b2ebb4c37a559e899ac70e Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Thu, 29 Jan 2009 11:45:35 +0100
Subject: x86: tone down mtrr_trim_uncached_memory() warning

kerneloops.org is reporting a lot of these warnings that come due to
vmware not setting up any MTRRs for emulated CPUs:

| Reported 709 times (14696 total reports)
| BIOS bug (often in VMWare) where the MTRR's are set up incorrectly
| or not at all
|
| This warning was last seen in version 2.6.29-rc2-git1, and first
| seen in 2.6.24.
|
| More info:
|   http://www.kerneloops.org/searchweek.php?search=mtrr_trim_uncached_memory

Keep a one-liner KERN_INFO about it - so that we have so notice if empty
MTRRs are caused by native hardware/BIOS weirdness.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/mtrr/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index d259e5d2e05..236a401b825 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -1594,8 +1594,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn)
 
 	/* kvm/qemu doesn't have mtrr set right, don't trim them all */
 	if (!highest_pfn) {
-		WARN(!kvm_para_available(), KERN_WARNING
-				"WARNING: strange, CPU MTRRs all blank?\n");
+		printk(KERN_INFO "CPU MTRRs all blank - virtualized system.\n");
 		return 0;
 	}
 
-- 
cgit v1.2.3-18-g5258


From 7fc49f19813030f2e15ad2ccec5cb701f7f4a3ec Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Tue, 27 Jan 2009 21:45:57 +0100
Subject: x86 setup: fix asm constraints in vesa_store_edid

Impact: fix potential miscompile (currently believed non-manifest)

As the comment explains, the VBE DDC call can clobber any register.
Tell the compiler about that fact.

Signed-off-by: Andreas Schwab <schwab@suse.de>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/boot/video-vesa.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/boot/video-vesa.c b/arch/x86/boot/video-vesa.c
index 75115849af3..4a58c8ce3f6 100644
--- a/arch/x86/boot/video-vesa.c
+++ b/arch/x86/boot/video-vesa.c
@@ -269,9 +269,8 @@ void vesa_store_edid(void)
 	   we genuinely have to assume all registers are destroyed here. */
 
 	asm("pushw %%es; movw %2,%%es; "INT10"; popw %%es"
-	    : "+a" (ax), "+b" (bx)
-	    :  "c" (cx), "D" (di)
-	    : "esi");
+	    : "+a" (ax), "+b" (bx), "+c" (cx), "+D" (di)
+	    : : "esi", "edx");
 
 	if (ax != 0x004f)
 		return;		/* No EDID */
@@ -285,9 +284,9 @@ void vesa_store_edid(void)
 	dx = 0;			/* EDID block number */
 	di =(size_t) &boot_params.edid_info; /* (ES:)Pointer to block */
 	asm(INT10
-	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info)
-	    : "c" (cx), "D" (di)
-	    : "esi");
+	    : "+a" (ax), "+b" (bx), "+d" (dx), "=m" (boot_params.edid_info),
+	      "+c" (cx), "+D" (di)
+	    : : "esi");
 #endif /* CONFIG_FIRMWARE_EDID */
 }
 
-- 
cgit v1.2.3-18-g5258


From 92ab78315c638515d0e81b0c70b2082f713582d9 Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Sat, 31 Jan 2009 17:24:43 +0100
Subject: x86/Voyager: make it build and boot

[
  mingo@elte.hu: these fixes are a subset of changes cherry-picked from:

     git://git.kernel.org:/pub/scm/linux/kernel/git/jejb/voyager-2.6.git

  They fix various problems that recent x86 changes caused in the Voyager
  subarchitecture: both APIC changes and cpumask changes and certain
  cleanups caused subarch assumptions to break.

  Most of these changes are obsolete as the subarch code has been removed
  from the x86 development tree - but we merge them upstream to make Voyager
  build and boot.
]

Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/irqinit_32.c        | 12 ------------
 arch/x86/mach-default/setup.c       | 12 ++++++++++++
 arch/x86/mach-voyager/setup.c       | 12 +++++++++++-
 arch/x86/mach-voyager/voyager_smp.c | 25 ++++++++++++-------------
 4 files changed, 35 insertions(+), 26 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 1507ad4e674..10a09c2f182 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -78,15 +78,6 @@ void __init init_ISA_irqs(void)
 	}
 }
 
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.mask = CPU_MASK_NONE,
-	.name = "cascade",
-};
-
 DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
 	[0 ... IRQ0_VECTOR - 1] = -1,
 	[IRQ0_VECTOR] = 0,
@@ -178,9 +169,6 @@ void __init native_init_IRQ(void)
 	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
 
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-
 	/* setup after call gates are initialised (usually add in
 	 * the architecture specific gates)
 	 */
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index df167f26562..a265a7c6319 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -38,6 +38,15 @@ void __init pre_intr_init_hook(void)
 	init_ISA_irqs();
 }
 
+/*
+ * IRQ2 is cascade interrupt to second interrupt controller
+ */
+static struct irqaction irq2 = {
+	.handler = no_action,
+	.mask = CPU_MASK_NONE,
+	.name = "cascade",
+};
+
 /**
  * intr_init_hook - post gate setup interrupt initialisation
  *
@@ -53,6 +62,9 @@ void __init intr_init_hook(void)
 		if (x86_quirks->arch_intr_init())
 			return;
 	}
+	if (!acpi_ioapic)
+		setup_irq(2, &irq2);
+
 }
 
 /**
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index a580b9562e7..d914a7996a6 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -33,13 +33,23 @@ void __init intr_init_hook(void)
 	setup_irq(2, &irq2);
 }
 
-void __init pre_setup_arch_hook(void)
+static void voyager_disable_tsc(void)
 {
 	/* Voyagers run their CPUs from independent clocks, so disable
 	 * the TSC code because we can't sync them */
 	setup_clear_cpu_cap(X86_FEATURE_TSC);
 }
 
+void __init pre_setup_arch_hook(void)
+{
+	voyager_disable_tsc();
+}
+
+void __init pre_time_init_hook(void)
+{
+	voyager_disable_tsc();
+}
+
 void __init trap_init_hook(void)
 {
 }
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 9840b7ec749..7ffcdeec463 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -81,7 +81,7 @@ static void enable_local_vic_irq(unsigned int irq);
 static void disable_local_vic_irq(unsigned int irq);
 static void before_handle_vic_irq(unsigned int irq);
 static void after_handle_vic_irq(unsigned int irq);
-static void set_vic_irq_affinity(unsigned int irq, cpumask_t mask);
+static void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask);
 static void ack_vic_irq(unsigned int irq);
 static void vic_enable_cpi(void);
 static void do_boot_cpu(__u8 cpuid);
@@ -211,8 +211,6 @@ static __u32 cpu_booted_map;
 static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 
 /* This is for the new dynamic CPU boot code */
-cpumask_t cpu_callin_map = CPU_MASK_NONE;
-cpumask_t cpu_callout_map = CPU_MASK_NONE;
 
 /* The per processor IRQ masks (these are usually kept in sync) */
 static __u16 vic_irq_mask[NR_CPUS] __cacheline_aligned;
@@ -378,7 +376,7 @@ void __init find_smp_config(void)
 	cpus_addr(phys_cpu_present_map)[0] |=
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
 				       3) << 24;
-	cpu_possible_map = phys_cpu_present_map;
+	init_cpu_possible(&phys_cpu_present_map);
 	printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n",
 	       cpus_addr(phys_cpu_present_map)[0]);
 	/* Here we set up the VIC to enable SMP */
@@ -1599,16 +1597,16 @@ static void after_handle_vic_irq(unsigned int irq)
  * change the mask and then do an interrupt enable CPI to re-enable on
  * the selected processors */
 
-void set_vic_irq_affinity(unsigned int irq, cpumask_t mask)
+void set_vic_irq_affinity(unsigned int irq, const struct cpumask *mask)
 {
 	/* Only extended processors handle interrupts */
 	unsigned long real_mask;
 	unsigned long irq_mask = 1 << irq;
 	int cpu;
 
-	real_mask = cpus_addr(mask)[0] & voyager_extended_vic_processors;
+	real_mask = cpus_addr(*mask)[0] & voyager_extended_vic_processors;
 
-	if (cpus_addr(mask)[0] == 0)
+	if (cpus_addr(*mask)[0] == 0)
 		/* can't have no CPUs to accept the interrupt -- extremely
 		 * bad things will happen */
 		return;
@@ -1750,10 +1748,11 @@ static void __cpuinit voyager_smp_prepare_boot_cpu(void)
 	init_gdt(smp_processor_id());
 	switch_to_new_gdt();
 
-	cpu_set(smp_processor_id(), cpu_online_map);
-	cpu_set(smp_processor_id(), cpu_callout_map);
-	cpu_set(smp_processor_id(), cpu_possible_map);
-	cpu_set(smp_processor_id(), cpu_present_map);
+	cpu_online_map = cpumask_of_cpu(smp_processor_id());
+	cpu_callout_map = cpumask_of_cpu(smp_processor_id());
+	cpu_callin_map = CPU_MASK_NONE;
+	cpu_present_map = cpumask_of_cpu(smp_processor_id());
+
 }
 
 static int __cpuinit voyager_cpu_up(unsigned int cpu)
@@ -1783,9 +1782,9 @@ void __init smp_setup_processor_id(void)
 	x86_write_percpu(cpu_number, hard_smp_processor_id());
 }
 
-static void voyager_send_call_func(cpumask_t callmask)
+static void voyager_send_call_func(const struct cpumask *callmask)
 {
-	__u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+	__u32 mask = cpus_addr(*callmask)[0] & ~(1 << smp_processor_id());
 	send_CPI(mask, VIC_CALL_FUNCTION_CPI);
 }
 
-- 
cgit v1.2.3-18-g5258


From 9a8ecae87a2b698964b1db9ea504ba1099f479fc Mon Sep 17 00:00:00 2001
From: Dave Jones <davej@redhat.com>
Date: Sat, 31 Jan 2009 20:12:14 -0500
Subject: x86: add cache descriptors for Intel Core i7

Signed-off-by: Dave Jones <davej@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/cpu/intel_cacheinfo.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 48533d77be7..da299eb85fc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -36,8 +36,11 @@ static struct _cache_table cache_table[] __cpuinitdata =
 {
 	{ 0x06, LVL_1_INST, 8 },	/* 4-way set assoc, 32 byte line size */
 	{ 0x08, LVL_1_INST, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x09, LVL_1_INST, 32 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x0a, LVL_1_DATA, 8 },	/* 2 way set assoc, 32 byte line size */
 	{ 0x0c, LVL_1_DATA, 16 },	/* 4-way set assoc, 32 byte line size */
+	{ 0x0d, LVL_1_DATA, 16 },	/* 4-way set assoc, 64 byte line size */
+	{ 0x21, LVL_2,      256 },	/* 8-way set assoc, 64 byte line size */
 	{ 0x22, LVL_3,      512 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x23, LVL_3,      1024 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x25, LVL_3,      2048 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -85,6 +88,18 @@ static struct _cache_table cache_table[] __cpuinitdata =
 	{ 0x85, LVL_2,    2048 },	/* 8-way set assoc, 32 byte line size */
 	{ 0x86, LVL_2,     512 },	/* 4-way set assoc, 64 byte line size */
 	{ 0x87, LVL_2,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd0, LVL_3,     512 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd1, LVL_3,    1024 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd2, LVL_3,    2048 },	/* 4-way set assoc, 64 byte line size */
+	{ 0xd6, LVL_3,    1024 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd7, LVL_3,    2038 },	/* 8-way set assoc, 64 byte line size */
+	{ 0xd8, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdc, LVL_3,    2048 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xdd, LVL_3,    4096 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xde, LVL_3,    8192 },	/* 12-way set assoc, 64 byte line size */
+	{ 0xe2, LVL_3,    2048 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe3, LVL_3,    4096 },	/* 16-way set assoc, 64 byte line size */
+	{ 0xe4, LVL_3,    8192 },	/* 16-way set assoc, 64 byte line size */
 	{ 0x00, 0, 0}
 };
 
-- 
cgit v1.2.3-18-g5258


From 10b888d6cec2688e65e9e128b14bf98ecd199da2 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Sat, 31 Jan 2009 14:50:07 -0800
Subject: irq, x86: fix lock status with numa_migrate_irq_desc

Eric Paris reported:

> I have an hp dl785g5 which is unable to successfully run
> 2.6.29-0.66.rc3.fc11.x86_64 or 2.6.29-rc2-next-20090126.  During bootup
> (early in userspace daemons starting) I get the below BUG, which quickly
> renders the machine dead.  I assume it is because sparse_irq_lock never
> gets released when the BUG kills that task.

Adjust lock sequence when migrating a descriptor with
CONFIG_NUMA_MIGRATE_IRQ_DESC enabled.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 1c4a1302536..9b0c480c383 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -2528,14 +2528,15 @@ static void irq_complete_move(struct irq_desc **descp)
 
 	vector = ~get_irq_regs()->orig_ax;
 	me = smp_processor_id();
+
+	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain)) {
 #ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
 		*descp = desc = move_irq_desc(desc, me);
 		/* get the new one */
 		cfg = desc->chip_data;
 #endif
-
-	if (vector == cfg->vector && cpumask_test_cpu(me, cfg->domain))
 		send_cleanup_vector(cfg);
+	}
 }
 #else
 static inline void irq_complete_move(struct irq_desc **descp) {}
-- 
cgit v1.2.3-18-g5258


From a67798cd7bb130bf37f5ffb28f3260f4c10232db Mon Sep 17 00:00:00 2001
From: Martin Hicks <mort@sgi.com>
Date: Fri, 30 Jan 2009 10:50:54 -0600
Subject: x86: push old stack address on irqstack for unwinder

Impact: Fixes dumpstack and KDB on 64 bits

This re-adds the old stack pointer to the top of the irqstack to help
with unwinding.  It was removed in commit d99015b1abbad743aa049b439c1e1dede6d0fa49
as part of the save_args out-of-line work.

Both dumpstack and KDB require this information.

Signed-off-by: Martin Hicks <mort@sgi.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/entry_64.S | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a98779..a1346217e43 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -346,6 +346,7 @@ ENTRY(save_args)
 	popq_cfi %rax			/* move return address... */
 	mov %gs:pda_irqstackptr,%rsp
 	EMPTY_FRAME 0
+	pushq_cfi %rbp			/* backlink for unwinder */
 	pushq_cfi %rax			/* ... to the new stack */
 	/*
 	 * We entered an interrupt context - irqs are off:
-- 
cgit v1.2.3-18-g5258


From 06fc732c33a7ff5e4c91bcf4a6ca86b5e335ad9a Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Tue, 3 Feb 2009 16:01:46 -0800
Subject: xen: disable interrupts before saving in percpu

Impact: Fix race condition

xen_mc_batch has a small preempt race where it takes the address of a
percpu variable immediately before disabling interrupts, thereby
leaving a small window in which we may migrate to another cpu and save
the flags in the wrong percpu variable.  Disable interrupts before
saving the old flags in a percpu.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/xen/multicalls.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/xen/multicalls.h b/arch/x86/xen/multicalls.h
index 85893824161..fa3e10725d9 100644
--- a/arch/x86/xen/multicalls.h
+++ b/arch/x86/xen/multicalls.h
@@ -19,8 +19,10 @@ DECLARE_PER_CPU(unsigned long, xen_mc_irq_flags);
    paired with xen_mc_issue() */
 static inline void xen_mc_batch(void)
 {
+	unsigned long flags;
 	/* need to disable interrupts until this entry is complete */
-	local_irq_save(__get_cpu_var(xen_mc_irq_flags));
+	local_irq_save(flags);
+	__get_cpu_var(xen_mc_irq_flags) = flags;
 }
 
 static inline struct multicall_space xen_mc_entry(size_t args)
-- 
cgit v1.2.3-18-g5258


From 858770619debfb9269add63e4ba8b7c6b5538dd1 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <borislav.petkov@amd.com>
Date: Tue, 3 Feb 2009 16:24:22 +0100
Subject: x86: APIC: enable workaround on AMD Fam10h CPUs

Impact: fix to enable APIC for AMD Fam10h on chipsets with a missing/b0rked
	ACPI MP table (MADT)

Booting a 32bit kernel on an AMD Fam10h CPU running on chipsets with
missing/b0rked MP table leads to a hang pretty early in the boot process
due to the APIC not being initialized. Fix that by falling back to the
default APIC base address in 32bit code, as it is done in the 64bit
codepath.

Signed-off-by: Borislav Petkov <borislav.petkov@amd.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/kernel/apic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index 4b6df2469fe..115449f869e 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1436,7 +1436,7 @@ static int __init detect_init_APIC(void)
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
 		if ((boot_cpu_data.x86 == 6 && boot_cpu_data.x86_model > 1) ||
-		    (boot_cpu_data.x86 == 15))
+		    (boot_cpu_data.x86 >= 15))
 			break;
 		goto no_apic;
 	case X86_VENDOR_INTEL:
-- 
cgit v1.2.3-18-g5258


From 62663ea8220366472fe20462831f2d69d7987439 Mon Sep 17 00:00:00 2001
From: Thomas Renninger <trenn@suse.de>
Date: Tue, 3 Feb 2009 17:46:46 +0100
Subject: ACPI: cpufreq: Remove deprecated /proc/acpi/processor/../performance
 proc entries

They were long enough set deprecated...

Update Documentation/cpu-freq/users-guide.txt:
The deprecated files listed there seen not to exist for some time anymore
already.

Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/x86/kernel/cpu/cpufreq/Kconfig | 11 -----------
 1 file changed, 11 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/cpufreq/Kconfig b/arch/x86/kernel/cpu/cpufreq/Kconfig
index efae3b22a0f..65792c2cc46 100644
--- a/arch/x86/kernel/cpu/cpufreq/Kconfig
+++ b/arch/x86/kernel/cpu/cpufreq/Kconfig
@@ -245,17 +245,6 @@ config X86_E_POWERSAVER
 
 comment "shared options"
 
-config X86_ACPI_CPUFREQ_PROC_INTF
-	bool "/proc/acpi/processor/../performance interface (deprecated)"
-	depends on PROC_FS
-	depends on X86_ACPI_CPUFREQ || X86_POWERNOW_K7_ACPI || X86_POWERNOW_K8_ACPI
-	help
-	  This enables the deprecated /proc/acpi/processor/../performance
-	  interface. While it is helpful for debugging, the generic,
-	  cross-architecture cpufreq interfaces should be used.
-
-	  If in doubt, say N.
-
 config X86_SPEEDSTEP_LIB
 	tristate
 	default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
-- 
cgit v1.2.3-18-g5258


From 48ec4d9537282a55d602136724f069faafcac8c8 Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@infradead.org>
Date: Wed, 4 Feb 2009 15:54:45 -0500
Subject: x86, 64-bit: print DMI info in the oops trace

This patch echoes what we already do on 32-bit since
90f7d25c6b672137344f447a30a9159945ffea72, and prints the DMI
product name in show_regs, so that system specific problems can be
easily identified.

Signed-off-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/process_64.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 416fb9282f4..85b4cb5c198 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -40,6 +40,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/ftrace.h>
+#include <linux/dmi.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -151,14 +152,18 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned long d0, d1, d2, d3, d6, d7;
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
+	const char *board;
 
 	printk("\n");
 	print_modules();
-	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s\n",
+	board = dmi_get_system_info(DMI_PRODUCT_NAME);
+	if (!board)
+		board = "";
+	printk(KERN_INFO "Pid: %d, comm: %.20s %s %s %.*s %s\n",
 		current->pid, current->comm, print_tainted(),
 		init_utsname()->release,
 		(int)strcspn(init_utsname()->version, " "),
-		init_utsname()->version);
+		init_utsname()->version, board);
 	printk(KERN_INFO "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip);
 	printk_address(regs->ip, 1);
 	printk(KERN_INFO "RSP: %04lx:%016lx  EFLAGS: %08lx\n", regs->ss,
-- 
cgit v1.2.3-18-g5258


From 36723bfe81f374fd8abc05a46f10a7cac2f01a75 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <petkovbb@googlemail.com>
Date: Wed, 4 Feb 2009 21:44:04 +0100
Subject: x86/Kconfig.cpu: make Kconfig help readable in the console

Impact: cleanup

Some lines exceed the 80 char width making them unreadable.

Signed-off-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/Kconfig.cpu | 28 +++++++++++++++-------------
 1 file changed, 15 insertions(+), 13 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 8078955845a..c98d52e8296 100644
--- a/arch/x86/Kconfig.cpu
+++ b/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
-- 
cgit v1.2.3-18-g5258


From a6a95406c676ffe4f9dee708eb404a17c69f7fdd Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov <xemul@openvz.org>
Date: Wed, 4 Feb 2009 13:40:31 +0300
Subject: x86: fix hpet timer reinit for x86_64

There's a small problem with hpet_rtc_reinit function - it checks
for the:

	hpet_readl(HPET_COUNTER) - hpet_t1_cmp > 0

to continue increasing both the HPET_T1_CMP (register) and the
hpet_t1_cmp (variable).

But since the HPET_COUNTER is always 32-bit, if the hpet_t1_cmp
is 64-bit this condition will always be FALSE once the latter hits
the 32-bit boundary, and we can have a situation, when we don't
increase the HPET_T1_CMP register high enough.

The result - timer stops ticking, since HPET_T1_CMP becomes less,
than the COUNTER and never increased again.

The solution is (based on Linus's suggestion) to not compare 64-bits
(on 64-bit x86), but to do the comparison on 32-bit signed
integers.

Reported-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/hpet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 64d5ad0b8ad..c761f914430 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1075,7 +1075,7 @@ static void hpet_rtc_timer_reinit(void)
 		hpet_t1_cmp += delta;
 		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
 		lost_ints++;
-	} while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+	} while ((s32)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
 
 	if (lost_ints) {
 		if (hpet_rtc_flags & RTC_PIE)
-- 
cgit v1.2.3-18-g5258


From 4560839939f4b4a96e21e80584f87308ac93c1da Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Wed, 4 Feb 2009 16:44:01 -0700
Subject: x86: fix grammar in user-visible BIOS warning

Fix user-visible grammo.

Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index ae0d8042cf6..c461f6d6907 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -607,7 +607,7 @@ struct x86_quirks *x86_quirks __initdata = &default_x86_quirks;
 static int __init dmi_low_memory_corruption(const struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE
-		"%s detected: BIOS may corrupt low RAM, working it around.\n",
+		"%s detected: BIOS may corrupt low RAM, working around it.\n",
 		d->ident);
 
 	e820_update_range(0, 0x10000, E820_RAM, E820_RESERVED);
-- 
cgit v1.2.3-18-g5258


From b534816b552d35bbd3c60702139ed5c7da2f55c2 Mon Sep 17 00:00:00 2001
From: Jeremy Fitzhardinge <jeremy@goop.org>
Date: Wed, 4 Feb 2009 18:33:38 -0800
Subject: x86: don't apply __supported_pte_mask to non-present ptes

On an x86 system which doesn't support global mappings,
__supported_pte_mask has _PAGE_GLOBAL clear, to make sure it never
appears in the PTE.  pfn_pte() and so on will enforce it with:

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);
}

However, we overload _PAGE_GLOBAL with _PAGE_PROTNONE on non-present
ptes to distinguish them from swap entries.  However, applying
__supported_pte_mask indiscriminately will clear the bit and corrupt the
pte.

I guess the best fix is to only apply __supported_pte_mask to present
ptes.  This seems like the right solution to me, as it means we can
completely ignore the issue of overlaps between the present pte bits and
the non-present pte-as-swap entry use of the bits.

__supported_pte_mask contains the set of flags we support on the
current hardware.  We also use bits in the pte for things like
logically present ptes with no permissions, and swap entries for
swapped out pages.  We should only apply __supported_pte_mask to
present ptes, because otherwise we may destroy other information being
stored in the ptes.

Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/x86/include/asm/pgtable.h  | 26 ++++++++++++++++++++------
 arch/x86/include/asm/xen/page.h |  2 +-
 2 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 06bbcbd66e9..4f5af8447d5 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/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)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 7ef617ef1df..4bd990ee43d 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/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;
 }
-- 
cgit v1.2.3-18-g5258


From 0cd5c3c80a0ebd68c08312fa7d8c13149cc61c4c Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@redhat.com>
Date: Wed, 4 Feb 2009 14:29:19 -0800
Subject: x86: disable intel_iommu support by default

Due to recurring issues with DMAR support on certain platforms.
There's a number of filesystem corruption incidents reported:

  https://bugzilla.redhat.com/show_bug.cgi?id=479996
  http://bugzilla.kernel.org/show_bug.cgi?id=12578

Provide a Kconfig option to change whether it is enabled by
default.

If disabled, it can still be reenabled by passing intel_iommu=on to the
kernel. Keep the .config option off by default.

Signed-off-by: Kyle McMartin <kyle@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-By: David Woodhouse <David.Woodhouse@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/Kconfig | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 73f7fe8fd4d..9c39095b33f 100644
--- a/arch/x86/Kconfig
+++ b/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"
-- 
cgit v1.2.3-18-g5258


From 732553e567c2700ba5b9bccc6ec885c75779a94b Mon Sep 17 00:00:00 2001
From: Mark Langsdorf <mark.langsdorf@amd.com>
Date: Tue, 3 Feb 2009 17:46:43 +0100
Subject: [CPUFREQ] powernow-k8: Get transition latency from ACPI _PSS table

At this time, the PowerNow! driver for K8 uses an experimentally
derived formula to calculate transition latency.  The value it
provides is orders of magnitude too large on modern systems.
This patch replaces the formula with ACPI _PSS latency values
for more accuracy and better performance.

I've tested it on two 2nd generation Opteron systems, a 3rd
generation Operton system, and a Turion X2 without seeing any
stability problems.

Signed-off-by: Mark Langsdorf <mark.langsdorf@amd.com>
Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Dave Jones <davej@redhat.com>
---
 arch/x86/kernel/cpu/cpufreq/powernow-k8.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 5c28b37dea1..fb039cd345d 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -939,10 +939,25 @@ static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 	free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
+static int get_transition_latency(struct powernow_k8_data *data)
+{
+	int max_latency = 0;
+	int i;
+	for (i = 0; i < data->acpi_data.state_count; i++) {
+		int cur_latency = data->acpi_data.states[i].transition_latency
+			+ data->acpi_data.states[i].bus_master_latency;
+		if (cur_latency > max_latency)
+			max_latency = cur_latency;
+	}
+	/* value in usecs, needs to be in nanoseconds */
+	return 1000 * max_latency;
+}
+
 #else
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; }
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; }
 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; }
+static int get_transition_latency(struct powernow_k8_data *data) { return 0; }
 #endif /* CONFIG_X86_POWERNOW_K8_ACPI */
 
 /* Take a frequency, and issue the fid/vid transition command */
@@ -1173,7 +1188,13 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		if (rc) {
 			goto err_out;
 		}
-	}
+		/* Take a crude guess here.
+		 * That guess was in microseconds, so multiply with 1000 */
+		pol->cpuinfo.transition_latency = (
+			 ((data->rvo + 8) * data->vstable * VST_UNITS_20US) +
+			 ((1 << data->irt) * 30)) * 1000;
+	} else /* ACPI _PSS objects available */
+		pol->cpuinfo.transition_latency = get_transition_latency(data);
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
@@ -1204,11 +1225,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
 	data->available_cores = pol->cpus;
 
-	/* Take a crude guess here.
-	 * That guess was in microseconds, so multiply with 1000 */
-	pol->cpuinfo.transition_latency = (((data->rvo + 8) * data->vstable * VST_UNITS_20US)
-	    + (3 * (1 << data->irt) * 10)) * 1000;
-
 	if (cpu_family == CPU_HW_PSTATE)
 		pol->cur = find_khz_freq_from_pstate(data->powernow_table, data->currpstate);
 	else
-- 
cgit v1.2.3-18-g5258


From 9be260a646bf76fa418ee519afa10196b3164681 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@redhat.com>
Date: Thu, 5 Feb 2009 17:12:39 -0500
Subject: prevent kprobes from catching spurious page faults

Prevent kprobes from catching spurious faults which will cause infinite
recursive page-fault and memory corruption by stack overflow.

Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Cc: <stable@kernel.org>		[2.6.28.x]
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/fault.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 90dfae511a4..c76ef1d701c 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -603,8 +603,6 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
 	si_code = SEGV_MAPERR;
 
-	if (notify_page_fault(regs))
-		return;
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -634,6 +632,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		if (spurious_fault(address, error_code))
 			return;
 
+		/* kprobes don't want to hook the spurious faults. */
+		if (notify_page_fault(regs))
+			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
 		 * fault we could otherwise deadlock.
@@ -641,6 +642,9 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 		goto bad_area_nosemaphore;
 	}
 
+	/* kprobes don't want to hook the spurious faults. */
+	if (notify_page_fault(regs))
+		return;
 
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
-- 
cgit v1.2.3-18-g5258


From ff08f76d738d0ec0f334b187f61e160caa321d54 Mon Sep 17 00:00:00 2001
From: Pavel Emelyanov <xemul@openvz.org>
Date: Wed, 4 Feb 2009 13:40:31 +0300
Subject: x86: clean up hpet timer reinit

Implement Linus's suggestion: introduce the hpet_cnt_ahead()
helper function to compare hpet time values - like other
wrapping counter comparisons are abstracted away elsewhere.
(jiffies, ktime_t, etc.)

Reported-by: Kirill Korotaev <dev@openvz.org>
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/hpet.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index c761f914430..388254f69a2 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -897,13 +897,21 @@ static unsigned long hpet_rtc_flags;
 static int hpet_prev_update_sec;
 static struct rtc_time hpet_alarm_time;
 static unsigned long hpet_pie_count;
-static unsigned long hpet_t1_cmp;
+static u32 hpet_t1_cmp;
 static unsigned long hpet_default_delta;
 static unsigned long hpet_pie_delta;
 static unsigned long hpet_pie_limit;
 
 static rtc_irq_handler irq_handler;
 
+/*
+ * Check that the hpet counter c1 is ahead of the c2
+ */
+static inline int hpet_cnt_ahead(u32 c1, u32 c2)
+{
+	return (s32)(c2 - c1) < 0;
+}
+
 /*
  * Registers a IRQ handler.
  */
@@ -1075,7 +1083,7 @@ static void hpet_rtc_timer_reinit(void)
 		hpet_t1_cmp += delta;
 		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
 		lost_ints++;
-	} while ((s32)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+	} while (!hpet_cnt_ahead(hpet_t1_cmp, hpet_readl(HPET_COUNTER)));
 
 	if (lost_ints) {
 		if (hpet_rtc_flags & RTC_PIE)
-- 
cgit v1.2.3-18-g5258


From c09249f8d1b84344eca882547afdbffee8c09d14 Mon Sep 17 00:00:00 2001
From: Roland McGrath <roland@redhat.com>
Date: Fri, 6 Feb 2009 18:15:18 -0800
Subject: x86-64: fix int $0x80 -ENOSYS return

One of my past fixes to this code introduced a different new bug.
When using 32-bit "int $0x80" entry for a bogus syscall number,
the return value is not correctly set to -ENOSYS.  This only happens
when neither syscall-audit nor syscall tracing is enabled (i.e., never
seen if auditd ever started).  Test program:

	/* gcc -o int80-badsys -m32 -g int80-badsys.c
	   Run on x86-64 kernel.
	   Note to reproduce the bug you need auditd never to have started.  */

	#include <errno.h>
	#include <stdio.h>

	int
	main (void)
	{
	  long res;
	  asm ("int $0x80" : "=a" (res) : "0" (99999));
	  printf ("bad syscall returns %ld\n", res);
	  return res != -ENOSYS;
	}

The fix makes the int $0x80 path match the sysenter and syscall paths.

Reported-by: Dmitry V. Levin <ldv@altlinux.org>
Signed-off-by: Roland McGrath <roland@redhat.com>
---
 arch/x86/ia32/ia32entry.S | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 256b00b6189..5a0d76dc56a 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -418,9 +418,9 @@ ENTRY(ia32_syscall)
 	orl   $TS_COMPAT,TI_status(%r10)
 	testl $_TIF_WORK_SYSCALL_ENTRY,TI_flags(%r10)
 	jnz ia32_tracesys
-ia32_do_syscall:	
 	cmpl $(IA32_NR_syscalls-1),%eax
-	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	ja ia32_badsys
+ia32_do_call:
 	IA32_ARG_FIXUP
 	call *ia32_sys_call_table(,%rax,8) # xxx: rip relative
 ia32_sysret:
@@ -435,7 +435,9 @@ ia32_tracesys:
 	call syscall_trace_enter
 	LOAD_ARGS32 ARGOFFSET  /* reload args from stack in case ptrace changed it */
 	RESTORE_REST
-	jmp ia32_do_syscall
+	cmpl $(IA32_NR_syscalls-1),%eax
+	ja  int_ret_from_sys_call	/* ia32_tracesys has set RAX(%rsp) */
+	jmp ia32_do_call
 END(ia32_syscall)
 
 ia32_badsys:
-- 
cgit v1.2.3-18-g5258


From e736ad548db152776de61d7a26805cfae77ce5ce Mon Sep 17 00:00:00 2001
From: "Pallipadi, Venkatesh" <venkatesh.pallipadi@intel.com>
Date: Fri, 6 Feb 2009 16:52:05 -0800
Subject: x86: add clflush before monitor for Intel 7400 series

For Intel 7400 series CPUs, the recommendation is to use a clflush on the
monitored address just before monitor and mwait pair [1].

This clflush makes sure that there are no false wakeups from mwait when the
monitored address was recently written to.

[1] "MONITOR/MWAIT Recommendations for Intel Xeon Processor 7400 series"
    section in specification update document of 7400 series
    http://download.intel.com/design/xeon/specupdt/32033601.pdf

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/cpufeature.h | 1 +
 arch/x86/kernel/cpu/intel.c       | 3 +++
 arch/x86/kernel/process.c         | 6 ++++++
 3 files changed, 10 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index ea408dcba51..7301e60dc4a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/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 */
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 430e5c38a54..24ff26a38ad 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/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;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index e68bb9e3086..6d12f7e37f8 100644
--- a/arch/x86/kernel/process.c
+++ b/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())
-- 
cgit v1.2.3-18-g5258


From 3f4a739c6accd651a11fcf3c7a20ec8147c42660 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yinghai@kernel.org>
Date: Sun, 8 Feb 2009 16:18:03 -0800
Subject: x86: find nr_irqs_gsi with mp_ioapic_routing

Impact: find right nr_irqs_gsi on some systems.

One test-system has gap between gsi's:

[    0.000000] ACPI: IOAPIC (id[0x04] address[0xfec00000] gsi_base[0])
[    0.000000] IOAPIC[0]: apic_id 4, version 0, address 0xfec00000, GSI 0-23
[    0.000000] ACPI: IOAPIC (id[0x05] address[0xfeafd000] gsi_base[48])
[    0.000000] IOAPIC[1]: apic_id 5, version 0, address 0xfeafd000, GSI 48-54
[    0.000000] ACPI: IOAPIC (id[0x06] address[0xfeafc000] gsi_base[56])
[    0.000000] IOAPIC[2]: apic_id 6, version 0, address 0xfeafc000, GSI 56-62
...
[    0.000000] nr_irqs_gsi: 38

So nr_irqs_gsi is not right. some irq for MSI will overwrite with io_apic.

need to get that with acpi_probe_gsi when acpi io_apic is used

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/mpspec.h |  6 ++++++
 arch/x86/kernel/acpi/boot.c   | 23 +++++++++++++++++++++++
 arch/x86/kernel/io_apic.c     | 20 +++++++++++++++-----
 3 files changed, 44 insertions(+), 5 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 62d14ce3cd0..bd22f2a3713 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/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)
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index d37593c2f43..7678f10c456 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/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)
 {
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 9b0c480c383..bc7ac4da90d 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/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);
 }
 
 /* --------------------------------------------------------------------------
-- 
cgit v1.2.3-18-g5258


From 55a8ba4b7f76bebd7e8ce3f74c04b140627a1bad Mon Sep 17 00:00:00 2001
From: Alok Kataria <akataria@vmware.com>
Date: Fri, 6 Feb 2009 10:29:35 -0800
Subject: x86, vmi: put a missing paravirt_release_pmd in pgd_dtor

Commit 6194ba6ff6ccf8d5c54c857600843c67aa82c407 ("x86: don't special-case
pmd allocations as much") made changes to the way we handle pmd allocations,
and while doing that it dropped a call to  paravirt_release_pd on the
pgd page from the pgd_dtor code path.

As a result of this missing release, the hypervisor is now unaware of the
pgd page being freed, and as a result it ends up tracking this page as a
page table page.

After this the guest may start using the same page for other purposes, and
depending on what use the page is put to, it may result in various performance
and/or functional issues ( hangs, reboots).

Since this release is only required for VMI, I now release the pgd page from
the (vmi)_pgd_free hook.

Signed-off-by: Alok N Kataria <akataria@vmware.com>
Acked-by: Jeremy Fitzhardinge <jeremy@goop.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: <stable@kernel.org>
---
 arch/x86/kernel/vmi_32.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'arch/x86')

diff --git a/arch/x86/kernel/vmi_32.c b/arch/x86/kernel/vmi_32.c
index 1d3302cc2dd..bef58b4982d 100644
--- a/arch/x86/kernel/vmi_32.c
+++ b/arch/x86/kernel/vmi_32.c
@@ -320,6 +320,16 @@ static void vmi_release_pmd(unsigned long pfn)
 	vmi_ops.release_page(pfn, VMI_PAGE_L2);
 }
 
+/*
+ * We use the pgd_free hook for releasing the pgd page:
+ */
+static void vmi_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	unsigned long pfn = __pa(pgd) >> PAGE_SHIFT;
+
+	vmi_ops.release_page(pfn, VMI_PAGE_L2);
+}
+
 /*
  * Helper macros for MMU update flags.  We can defer updates until a flush
  * or page invalidation only if the update is to the current address space
@@ -762,6 +772,7 @@ static inline int __init activate_vmi(void)
 	if (vmi_ops.release_page) {
 		pv_mmu_ops.release_pte = vmi_release_pte;
 		pv_mmu_ops.release_pmd = vmi_release_pmd;
+		pv_mmu_ops.pgd_free = vmi_pgd_free;
 	}
 
 	/* Set linear is needed in all cases */
-- 
cgit v1.2.3-18-g5258


From 914c3d630b29b07d04908eab1b246812dadd5bd6 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 9 Feb 2009 22:17:39 +0900
Subject: x86: include correct %gs in a.out core dump

Impact: dump the correct %gs into a.out core dump

aout_dump_thread() read %gs but didn't include it in core dump.  Fix
it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/a.out-core.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
index 37822206083..3c601f8224b 100644
--- a/arch/x86/include/asm/a.out-core.h
+++ b/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;
-- 
cgit v1.2.3-18-g5258


From ae6af41f5a4841f06eb92bc86ad020ad44ae2a30 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Mon, 9 Feb 2009 22:17:39 +0900
Subject: x86: math_emu info cleanup

Impact: cleanup

* Come on, struct info?  s/struct info/struct math_emu_info/

* Use struct pt_regs and kernel_vm86_regs instead of defining its own
  register frame structure.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/include/asm/math_emu.h  | 29 +++++-------------
 arch/x86/include/asm/processor.h |  2 +-
 arch/x86/math-emu/fpu_entry.c    |  2 +-
 arch/x86/math-emu/fpu_proto.h    |  2 +-
 arch/x86/math-emu/fpu_system.h   | 14 ++++-----
 arch/x86/math-emu/get_address.c  | 63 +++++++++++++++++++---------------------
 6 files changed, 48 insertions(+), 64 deletions(-)

(limited to 'arch/x86')

diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
index 5a65b107ad5..302492c7795 100644
--- a/arch/x86/include/asm/math_emu.h
+++ b/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 */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 091cd8855f2..3bfd5235a9e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/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;
 };
 
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index c7b06feb139..c268abe7225 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -659,7 +659,7 @@ static int valid_prefix(u_char *Byte, u_char __user **fpu_eip,
 	}
 }
 
-void math_abort(struct info *info, unsigned int signal)
+void math_abort(struct math_emu_info *info, unsigned int signal)
 {
 	FPU_EIP = FPU_ORIG_EIP;
 	current->thread.trap_no = 16;
diff --git a/arch/x86/math-emu/fpu_proto.h b/arch/x86/math-emu/fpu_proto.h
index aa49b6a0d85..51bfbb61c5b 100644
--- a/arch/x86/math-emu/fpu_proto.h
+++ b/arch/x86/math-emu/fpu_proto.h
@@ -52,7 +52,7 @@ extern void fst_i_(void);
 extern void fstp_i(void);
 /* fpu_entry.c */
 asmlinkage extern void math_emulate(long arg);
-extern void math_abort(struct info *info, unsigned int signal);
+extern void math_abort(struct math_emu_info *info, unsigned int signal);
 /* fpu_etc.c */
 extern void FPU_etc(void);
 /* fpu_tags.c */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 13488fa153e..6729c6a3134 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -18,7 +18,7 @@
 
 /* This sets the pointer FPU_info to point to the argument part
    of the stack frame of math_emulate() */
-#define SETUP_DATA_AREA(arg)	FPU_info = (struct info *) &arg
+#define SETUP_DATA_AREA(arg)	FPU_info = (struct math_emu_info *) &arg
 
 /* s is always from a cpu register, and the cpu does bounds checking
  * during register load --> no further bounds checks needed */
@@ -38,12 +38,12 @@
 #define I387			(current->thread.xstate)
 #define FPU_info		(I387->soft.info)
 
-#define FPU_CS			(*(unsigned short *) &(FPU_info->___cs))
-#define FPU_SS			(*(unsigned short *) &(FPU_info->___ss))
-#define FPU_DS			(*(unsigned short *) &(FPU_info->___ds))
-#define FPU_EAX			(FPU_info->___eax)
-#define FPU_EFLAGS		(FPU_info->___eflags)
-#define FPU_EIP			(FPU_info->___eip)
+#define FPU_CS			(*(unsigned short *) &(FPU_info->regs.cs))
+#define FPU_SS			(*(unsigned short *) &(FPU_info->regs.ss))
+#define FPU_DS			(*(unsigned short *) &(FPU_info->regs.ds))
+#define FPU_EAX			(FPU_info->regs.ax)
+#define FPU_EFLAGS		(FPU_info->regs.flags)
+#define FPU_EIP			(FPU_info->regs.ip)
 #define FPU_ORIG_EIP		(FPU_info->___orig_eip)
 
 #define FPU_lookahead           (I387->soft.lookahead)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index d701e2b39e4..62daa7fcc44 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -29,42 +29,39 @@
 #define FPU_WRITE_BIT 0x10
 
 static int reg_offset[] = {
-	offsetof(struct info, ___eax),
-	offsetof(struct info, ___ecx),
-	offsetof(struct info, ___edx),
-	offsetof(struct info, ___ebx),
-	offsetof(struct info, ___esp),
-	offsetof(struct info, ___ebp),
-	offsetof(struct info, ___esi),
-	offsetof(struct info, ___edi)
+	offsetof(struct math_emu_info, regs.ax),
+	offsetof(struct math_emu_info, regs.cx),
+	offsetof(struct math_emu_info, regs.dx),
+	offsetof(struct math_emu_info, regs.bx),
+	offsetof(struct math_emu_info, regs.sp),
+	offsetof(struct math_emu_info, regs.bp),
+	offsetof(struct math_emu_info, regs.si),
+	offsetof(struct math_emu_info, regs.di)
 };
 
 #define REG_(x) (*(long *)(reg_offset[(x)]+(u_char *) FPU_info))
 
 static int reg_offset_vm86[] = {
-	offsetof(struct info, ___cs),
-	offsetof(struct info, ___vm86_ds),
-	offsetof(struct info, ___vm86_es),
-	offsetof(struct info, ___vm86_fs),
-	offsetof(struct info, ___vm86_gs),
-	offsetof(struct info, ___ss),
-	offsetof(struct info, ___vm86_ds)
+	offsetof(struct math_emu_info, regs.cs),
+	offsetof(struct math_emu_info, vm86.ds),
+	offsetof(struct math_emu_info, vm86.es),
+	offsetof(struct math_emu_info, vm86.fs),
+	offsetof(struct math_emu_info, vm86.gs),
+	offsetof(struct math_emu_info, regs.ss),
+	offsetof(struct math_emu_info, vm86.ds)
 };
 
 #define VM86_REG_(x) (*(unsigned short *) \
 		      (reg_offset_vm86[((unsigned)x)]+(u_char *) FPU_info))
 
-/* This dummy, gs is not saved on the stack. */
-#define ___GS ___ds
-
 static int reg_offset_pm[] = {
-	offsetof(struct info, ___cs),
-	offsetof(struct info, ___ds),
-	offsetof(struct info, ___es),
-	offsetof(struct info, ___fs),
-	offsetof(struct info, ___GS),
-	offsetof(struct info, ___ss),
-	offsetof(struct info, ___ds)
+	offsetof(struct math_emu_info, regs.cs),
+	offsetof(struct math_emu_info, regs.ds),
+	offsetof(struct math_emu_info, regs.es),
+	offsetof(struct math_emu_info, regs.fs),
+	offsetof(struct math_emu_info, regs.ds), /* dummy, not saved on stack */
+	offsetof(struct math_emu_info, regs.ss),
+	offsetof(struct math_emu_info, regs.ds)
 };
 
 #define PM_REG_(x) (*(unsigned short *) \
@@ -349,34 +346,34 @@ void __user *FPU_get_address_16(u_char FPU_modrm, unsigned long *fpu_eip,
 	}
 	switch (rm) {
 	case 0:
-		address += FPU_info->___ebx + FPU_info->___esi;
+		address += FPU_info->regs.bx + FPU_info->regs.si;
 		break;
 	case 1:
-		address += FPU_info->___ebx + FPU_info->___edi;
+		address += FPU_info->regs.bx + FPU_info->regs.di;
 		break;
 	case 2:
-		address += FPU_info->___ebp + FPU_info->___esi;
+		address += FP