Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

15 files changed, 98 insertions, 125 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 45d79ea890a..5fed98ca0e1 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -65,7 +65,8 @@ __setup("noreplace-paravirt", setup_noreplace_paravirt);
    get them easily into strings. */
 asm("\t.section .rodata, \"a\"\nintelnops: "
 	GENERIC_NOP1 GENERIC_NOP2 GENERIC_NOP3 GENERIC_NOP4 GENERIC_NOP5 GENERIC_NOP6
-	GENERIC_NOP7 GENERIC_NOP8);
+	GENERIC_NOP7 GENERIC_NOP8
+    "\t.previous");
 extern const unsigned char intelnops[];
 static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -83,7 +84,8 @@ static const unsigned char *const intel_nops[ASM_NOP_MAX+1] = {
 #ifdef K8_NOP1
 asm("\t.section .rodata, \"a\"\nk8nops: "
 	K8_NOP1 K8_NOP2 K8_NOP3 K8_NOP4 K8_NOP5 K8_NOP6
-	K8_NOP7 K8_NOP8);
+	K8_NOP7 K8_NOP8
+    "\t.previous");
 extern const unsigned char k8nops[];
 static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -101,7 +103,8 @@ static const unsigned char *const k8_nops[ASM_NOP_MAX+1] = {
 #ifdef K7_NOP1
 asm("\t.section .rodata, \"a\"\nk7nops: "
 	K7_NOP1 K7_NOP2 K7_NOP3 K7_NOP4 K7_NOP5 K7_NOP6
-	K7_NOP7 K7_NOP8);
+	K7_NOP7 K7_NOP8
+    "\t.previous");
 extern const unsigned char k7nops[];
 static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 	NULL,
@@ -119,7 +122,8 @@ static const unsigned char *const k7_nops[ASM_NOP_MAX+1] = {
 #ifdef P6_NOP1
 asm("\t.section .rodata, \"a\"\np6nops: "
 	P6_NOP1 P6_NOP2 P6_NOP3 P6_NOP4 P6_NOP5 P6_NOP6
-	P6_NOP7 P6_NOP8);
+	P6_NOP7 P6_NOP8
+    "\t.previous");
 extern const unsigned char p6nops[];
 static const unsigned char *const p6_nops[ASM_NOP_MAX+1] = {
 	NULL,
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 027e5c003b1..170d2f5523b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -143,14 +143,6 @@ static void __init check_config(void)
 #endif
 
 /*
- * If we configured ourselves for a TSC, we'd better have one!
- */
-#ifdef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
-		panic("Kernel compiled for Pentium+, requires TSC feature!");
-#endif
-
-/*
  * If we were told we had a good local APIC, check for buggy Pentia,
  * i.e. all B steppings and the C2 stepping of P54C when using their
  * integrated APIC (see 11AP erratum in "Pentium Processor
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 9b838324b81..b943e10ad81 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -652,9 +652,6 @@ static void probe_nmi_watchdog(void)
 			wd_ops = &p6_wd_ops;
 			break;
 		case 15:
-			if (boot_cpu_data.x86_model > 0x4)
-				return;
-
 			wd_ops = &p4_wd_ops;
 			break;
 		default:
@@ -670,8 +667,10 @@ int lapic_watchdog_init(unsigned nmi_hz)
 {
 	if (!wd_ops) {
 		probe_nmi_watchdog();
-		if (!wd_ops)
+		if (!wd_ops) {
+			printk(KERN_INFO "NMI watchdog: CPU not supported\n");
 			return -1;
+		}
 
 		if (!wd_ops->reserve()) {
 			printk(KERN_ERR
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 235fd6c7750..36652ea1a26 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -133,13 +133,16 @@ static void hpet_reserve_platform_timers(unsigned long id)
 #ifdef CONFIG_HPET_EMULATE_RTC
 	hpet_reserve_timer(&hd, 1);
 #endif
+
 	hd.hd_irq[0] = HPET_LEGACY_8254;
 	hd.hd_irq[1] = HPET_LEGACY_RTC;
 
-       for (i = 2; i < nrtimers; timer++, i++)
-	       hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
-		       Tn_INT_ROUTE_CNF_SHIFT;
+	for (i = 2; i < nrtimers; timer++, i++)
+		hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
+			Tn_INT_ROUTE_CNF_SHIFT;
+
 	hpet_alloc(&hd);
+
 }
 #else
 static void hpet_reserve_platform_timers(unsigned long id) { }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index faf3229f8fb..700e4647dd3 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -615,8 +615,8 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
  nommu:
 	/* Should not happen anymore */
-	printk(KERN_ERR "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
-	       KERN_ERR "PCI-DMA: 32bit PCI IO may malfunction.\n");
+	printk(KERN_WARNING "PCI-DMA: More than 4GB of RAM and no IOMMU\n"
+	       KERN_WARNING "falling back to iommu=soft.\n");
 	return -1;
 }
 
@@ -692,9 +692,9 @@ void __init gart_iommu_init(void)
 	    !gart_iommu_aperture ||
 	    (no_agp && init_k8_gatt(&info) < 0)) {
 		if (end_pfn > MAX_DMA32_PFN) {
-			printk(KERN_ERR "WARNING more than 4GB of memory "
-					"but GART IOMMU not available.\n"
-			       KERN_ERR "WARNING 32bit PCI may malfunction.\n");
+			printk(KERN_WARNING "More than 4GB of memory "
+			       	          "but GART IOMMU not available.\n"
+			       KERN_WARNING "falling back to iommu=soft.\n");
 		}
 		return;
 	}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index be3c7a299f0..43930e73f65 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -82,7 +82,6 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
  */
 void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
 void disable_hlt(void)
 {
@@ -190,9 +189,6 @@ void cpu_idle(void)
 		while (!need_resched()) {
 			void (*idle)(void);
 
-			if (__get_cpu_var(cpu_idle_state))
-				__get_cpu_var(cpu_idle_state) = 0;
-
 			check_pgt_cache();
 			rmb();
 			idle = pm_idle;
@@ -220,40 +216,19 @@ static void do_nothing(void *unused)
 {
 }
 
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
 void cpu_idle_wait(void)
 {
-	unsigned int cpu, this_cpu = get_cpu();
-	cpumask_t map, tmp = current->cpus_allowed;
-
-	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
-	put_cpu();
-
-	cpus_clear(map);
-	for_each_online_cpu(cpu) {
-		per_cpu(cpu_idle_state, cpu) = 1;
-		cpu_set(cpu, map);
-	}
-
-	__get_cpu_var(cpu_idle_state) = 0;
-
-	wmb();
-	do {
-		ssleep(1);
-		for_each_online_cpu(cpu) {
-			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
-				cpu_clear(cpu, map);
-		}
-		cpus_and(map, map, cpu_online_map);
-		/*
-		 * We waited 1 sec, if a CPU still did not call idle
-		 * it may be because it is in idle and not waking up
-		 * because it has nothing to do.
-		 * Give all the remaining CPUS a kick.
-		 */
-		smp_call_function_mask(map, do_nothing, NULL, 0);
-	} while (!cpus_empty(map));
-
-	set_cpus_allowed(current, tmp);
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3baf9b9f4c8..46c4c546b49 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -63,7 +63,6 @@ EXPORT_SYMBOL(boot_option_idle_override);
  */
 void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
-static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
 static ATOMIC_NOTIFIER_HEAD(idle_notifier);
 
@@ -173,9 +172,6 @@ void cpu_idle(void)
 		while (!need_resched()) {
 			void (*idle)(void);
 
-			if (__get_cpu_var(cpu_idle_state))
-				__get_cpu_var(cpu_idle_state) = 0;
-
 			rmb();
 			idle = pm_idle;
 			if (!idle)
@@ -207,40 +203,19 @@ static void do_nothing(void *unused)
 {
 }
 
+/*
+ * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
+ * pm_idle and update to new pm_idle value. Required while changing pm_idle
+ * handler on SMP systems.
+ *
+ * Caller must have changed pm_idle to the new value before the call. Old
+ * pm_idle value will not be used by any CPU after the return of this function.
+ */
 void cpu_idle_wait(void)
 {
-	unsigned int cpu, this_cpu = get_cpu();
-	cpumask_t map, tmp = current->cpus_allowed;
-
-	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
-	put_cpu();
-
-	cpus_clear(map);
-	for_each_online_cpu(cpu) {
-		per_cpu(cpu_idle_state, cpu) = 1;
-		cpu_set(cpu, map);
-	}
-
-	__get_cpu_var(cpu_idle_state) = 0;
-
-	wmb();
-	do {
-		ssleep(1);
-		for_each_online_cpu(cpu) {
-			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
-				cpu_clear(cpu, map);
-		}
-		cpus_and(map, map, cpu_online_map);
-		/*
-		 * We waited 1 sec, if a CPU still did not call idle
-		 * it may be because it is in idle and not waking up
-		 * because it has nothing to do.
-		 * Give all the remaining CPUS a kick.
-		 */
-		smp_call_function_mask(map, do_nothing, 0, 0);
-	} while (!cpus_empty(map));
-
-	set_cpus_allowed(current, tmp);
+	smp_mb();
+	/* kick all the CPUs so that they exit out of pm_idle */
+	smp_call_function(do_nothing, NULL, 0, 1);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9d406cdc847..071ff479823 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -140,6 +140,9 @@ static int enable_single_step(struct task_struct *child)
  */
 static void write_debugctlmsr(struct task_struct *child, unsigned long val)
 {
+	if (child->thread.debugctlmsr == val)
+		return;
+
 	child->thread.debugctlmsr = val;
 
 	if (child != current)
@@ -165,11 +168,11 @@ static void enable_step(struct task_struct *child, bool block)
 		write_debugctlmsr(child,
 				  child->thread.debugctlmsr | DEBUGCTLMSR_BTF);
 	} else {
-	    write_debugctlmsr(child,
-			      child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
+		write_debugctlmsr(child,
+				  child->thread.debugctlmsr & ~DEBUGCTLMSR_BTF);
 
-	    if (!child->thread.debugctlmsr)
-		    clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
+		if (!child->thread.debugctlmsr)
+			clear_tsk_thread_flag(child, TIF_DEBUGCTLMSR);
 	}
 }
 
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 022bcaa3b42..ab6bf375a30 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -92,7 +92,7 @@ int do_set_thread_area(struct task_struct *p, int idx,
 asmlinkage int sys_set_thread_area(struct user_desc __user *u_info)
 {
 	int ret = do_set_thread_area(current, -1, u_info, 1);
-	prevent_tail_call(ret);
+	asmlinkage_protect(1, ret, u_info);
 	return ret;
 }
 
@@ -142,7 +142,7 @@ int do_get_thread_area(struct task_struct *p, int idx,
 asmlinkage int sys_get_thread_area(struct user_desc __user *u_info)
 {
 	int ret = do_get_thread_area(current, -1, u_info);
-	prevent_tail_call(ret);
+	asmlinkage_protect(1, ret, u_info);
 	return ret;
 }
 
diff --git a/arch/x86/kernel/tsc_32.c b/arch/x86/kernel/tsc_32.c
index f14cfd9d1f9..c2241e04ea5 100644
--- a/arch/x86/kernel/tsc_32.c
+++ b/arch/x86/kernel/tsc_32.c
@@ -256,9 +256,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data)
 						ref_freq, freq->new);
 			if (!(freq->flags & CPUFREQ_CONST_LOOPS)) {
 				tsc_khz = cpu_khz;
-				preempt_disable();
-				set_cyc2ns_scale(cpu_khz, smp_processor_id());
-				preempt_enable();
+				set_cyc2ns_scale(cpu_khz, freq->cpu);
 				/*
 				 * TSC based sched_clock turns
 				 * to junk w/ cpufreq
diff --git a/arch/x86/kernel/tsc_64.c b/arch/x86/kernel/tsc_64.c
index 947554ddabb..d3bebaaad84 100644
--- a/arch/x86/kernel/tsc_64.c
+++ b/arch/x86/kernel/tsc_64.c
@@ -148,9 +148,7 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 			mark_tsc_unstable("cpufreq changes");
 	}
 
-	preempt_disable();
-	set_cyc2ns_scale(tsc_khz_ref, smp_processor_id());
-	preempt_enable();
+	set_cyc2ns_scale(tsc_khz_ref, freq->cpu);
 
 	return 0;
 }
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 0234f2831bf..378136fb504 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -219,8 +219,21 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 	if (pxm >= 0)
 		sd->node = pxm_to_node(pxm);
 #endif
+	/*
+	 * Maybe the desired pci bus has been already scanned. In such case
+	 * it is unnecessary to scan the pci bus with the given domain,busnum.
+	 */
+	bus = pci_find_bus(domain, busnum);
+	if (bus) {
+		/*
+		 * If the desired bus exits, the content of bus->sysdata will
+		 * be replaced by sd.
+		 */
+		memcpy(bus->sysdata, sd, sizeof(*sd));
+		kfree(sd);
+	} else
+		bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
 
-	bus = pci_scan_bus_parented(NULL, busnum, &pci_root_ops, sd);
 	if (!bus)
 		kfree(sd);
 
@@ -228,7 +241,7 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_device *device, int do
 	if (bus != NULL) {
 		if (pxm >= 0) {
 			printk("bus %d -> pxm %d -> node %d\n",
-				busnum, pxm, sd->node);
+				busnum, pxm, pxm_to_node(pxm));
 		}
 	}
 #endif
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index de4e6f05840..27ee26aedf9 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -667,10 +667,10 @@ static void xen_release_pt_init(u32 pfn)
 	make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
-static void pin_pagetable_pfn(unsigned level, unsigned long pfn)
+static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
 {
 	struct mmuext_op op;
-	op.cmd = level;
+	op.cmd = cmd;
 	op.arg1.mfn = pfn_to_mfn(pfn);
 	if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
 		BUG();
@@ -687,7 +687,8 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
 
 		if (!PageHighMem(page)) {
 			make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
-			pin_pagetable_pfn(level, pfn);
+			if (level == PT_PTE)
+				pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
 		} else
 			/* make sure there are no stray mappings of
 			   this page */
@@ -697,27 +698,39 @@ static void xen_alloc_ptpage(struct mm_struct *mm, u32 pfn, unsigned level)
 
 static void xen_alloc_pt(struct mm_struct *mm, u32 pfn)
 {
-	xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L1_TABLE);
+	xen_alloc_ptpage(mm, pfn, PT_PTE);
 }
 
 static void xen_alloc_pd(struct mm_struct *mm, u32 pfn)
 {
-	xen_alloc_ptpage(mm, pfn, MMUEXT_PIN_L2_TABLE);
+	xen_alloc_ptpage(mm, pfn, PT_PMD);
 }
 
 /* This should never happen until we're OK to use struct page */
-static void xen_release_pt(u32 pfn)
+static void xen_release_ptpage(u32 pfn, unsigned level)
 {
 	struct page *page = pfn_to_page(pfn);
 
 	if (PagePinned(page)) {
 		if (!PageHighMem(page)) {
-			pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
+			if (level == PT_PTE)
+				pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
 			make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 		}
+		ClearPagePinned(page);
 	}
 }
 
+static void xen_release_pt(u32 pfn)
+{
+	xen_release_ptpage(pfn, PT_PTE);
+}
+
+static void xen_release_pd(u32 pfn)
+{
+	xen_release_ptpage(pfn, PT_PMD);
+}
+
 #ifdef CONFIG_HIGHPTE
 static void *xen_kmap_atomic_pte(struct page *page, enum km_type type)
 {
@@ -838,7 +851,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 	pv_mmu_ops.alloc_pt = xen_alloc_pt;
 	pv_mmu_ops.alloc_pd = xen_alloc_pd;
 	pv_mmu_ops.release_pt = xen_release_pt;
-	pv_mmu_ops.release_pd = xen_release_pt;
+	pv_mmu_ops.release_pd = xen_release_pd;
 	pv_mmu_ops.set_pte = xen_set_pte;
 
 	setup_shared_info();
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 0144395448a..2a054ef2a3d 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -310,13 +310,6 @@ pgd_t xen_make_pgd(unsigned long pgd)
 }
 #endif	/* CONFIG_X86_PAE */
 
-enum pt_level {
-	PT_PGD,
-	PT_PUD,
-	PT_PMD,
-	PT_PTE
-};
-
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
   pagetable.  This means that it walks a pagetable and calls the
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index c9ff27f3ac3..b5e189b1519 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -3,6 +3,13 @@
 #include <linux/linkage.h>
 #include <asm/page.h>
 
+enum pt_level {
+	PT_PGD,
+	PT_PUD,
+	PT_PMD,
+	PT_PTE
+};
+
 /*
  * Page-directory addresses above 4GB do not fit into architectural %cr3.
  * When accessing %cr3, or equivalent field in vcpu_guest_context, guests