Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6:
  [PATCH] x86-64: Fix race in exit_idle
  [PATCH] x86-64: Fix vgetcpu when CONFIG_HOTPLUG_CPU is disabled
  [PATCH] x86: Add acpi_user_timer_override option for Asus boards
  [PATCH] x86-64: setup saved_max_pfn correctly (kdump)
  [PATCH] x86-64: Handle reserve_bootmem_generic beyond end_pfn
  [PATCH] x86-64: shorten the x86_64 boot setup GDT to what the comment says
  [PATCH] x86-64: Fix PTRACE_[SG]ET_THREAD_AREA regression with ia32 emulation.
  [PATCH] x86-64: Fix partial page check to ensure unusable memory is not being marked usable.
  Revert "[PATCH] MMCONFIG and new Intel motherboards"

17 files changed, 86 insertions, 75 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index dd00fd5..6747384 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -164,6 +164,10 @@ and is between 256 and 4096 characters. It is defined in the file
 	acpi_skip_timer_override [HW,ACPI]
 			Recognize and ignore IRQ0/pin2 Interrupt Override.
 			For broken nForce2 BIOS resulting in XT-PIC timer.
+	acpi_use_timer_override [HW,ACPI}
+			Use timer override. For some broken Nvidia NF5 boards
+			that require a timer override, but don't have
+			HPET
 
 	acpi_dbg_layer=	[HW,ACPI]
 			Format: <int>
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index 22e4c466..d12fb97 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -82,6 +82,7 @@ EXPORT_SYMBOL(acpi_strict);
 acpi_interrupt_flags acpi_sci_flags __initdata;
 int acpi_sci_override_gsi __initdata;
 int acpi_skip_timer_override __initdata;
+int acpi_use_timer_override __initdata;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
@@ -1300,6 +1301,13 @@ static int __init parse_acpi_skip_timer_override(char *arg)
 	return 0;
 }
 early_param("acpi_skip_timer_override", parse_acpi_skip_timer_override);
+
+static int __init parse_acpi_use_timer_override(char *arg)
+{
+	acpi_use_timer_override = 1;
+	return 0;
+}
+early_param("acpi_use_timer_override", parse_acpi_use_timer_override);
 #endif /* CONFIG_X86_IO_APIC */
 
 static int __init setup_acpi_sci(char *s)
diff --git a/arch/i386/kernel/acpi/earlyquirk.c b/arch/i386/kernel/acpi/earlyquirk.c
index fe799b1..c984169 100644
--- a/arch/i386/kernel/acpi/earlyquirk.c
+++ b/arch/i386/kernel/acpi/earlyquirk.c
@@ -27,11 +27,17 @@ static int __init check_bridge(int vendor, int device)
 #ifdef CONFIG_ACPI
 	/* According to Nvidia all timer overrides are bogus unless HPET
 	   is enabled. */
-	if (vendor == PCI_VENDOR_ID_NVIDIA) {
+	if (!acpi_use_timer_override && vendor == PCI_VENDOR_ID_NVIDIA) {
 		nvidia_hpet_detected = 0;
 		acpi_table_parse(ACPI_HPET, nvidia_hpet_check);
 		if (nvidia_hpet_detected == 0) {
 			acpi_skip_timer_override = 1;
+			  printk(KERN_INFO "Nvidia board "
+                       "detected. Ignoring ACPI "
+                       "timer override.\n");
+                printk(KERN_INFO "If you got timer trouble "
+			 	 "try acpi_use_timer_override\n");
+
 		}
 	}
 #endif
diff --git a/arch/x86_64/boot/setup.S b/arch/x86_64/boot/setup.S
index c3bfd22..770940c 100644
--- a/arch/x86_64/boot/setup.S
+++ b/arch/x86_64/boot/setup.S
@@ -836,13 +836,12 @@ gdt:
 	.word	0x9200				# data read/write
 	.word	0x00CF				# granularity = 4096, 386
 						#  (+5th nibble of limit)
+gdt_end:
 idt_48:
 	.word	0				# idt limit = 0
 	.word	0, 0				# idt base = 0L
 gdt_48:
-	.word	0x8000				# gdt limit=2048,
-						#  256 GDT entries
-
+	.word	gdt_end-gdt-1			# gdt limit
 	.word	0, 0				# gdt base (filled in later)
 
 # Include video setup & detection code
diff --git a/arch/x86_64/ia32/ptrace32.c b/arch/x86_64/ia32/ptrace32.c
index 3a7561d..04566fe 100644
--- a/arch/x86_64/ia32/ptrace32.c
+++ b/arch/x86_64/ia32/ptrace32.c
@@ -244,6 +244,8 @@ asmlinkage long sys32_ptrace(long request, u32 pid, u32 addr, u32 data)
 	case PTRACE_DETACH:
 	case PTRACE_SYSCALL:
 	case PTRACE_SETOPTIONS:
+	case PTRACE_SET_THREAD_AREA:
+	case PTRACE_GET_THREAD_AREA:
 		return sys_ptrace(request, pid, addr, data); 
 
 	default:
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index a75c829..6fe191c 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -278,7 +278,7 @@ e820_register_active_regions(int nid, unsigned long start_pfn,
 								>> PAGE_SHIFT;
 
 		/* Skip map entries smaller than a page */
-		if (ei_startpfn > ei_endpfn)
+		if (ei_startpfn >= ei_endpfn)
 			continue;
 
 		/* Check if end_pfn_map should be updated */
@@ -594,7 +594,9 @@ static int __init parse_memmap_opt(char *p)
 		 * size before original memory map is
 		 * reset.
 		 */
+		e820_register_active_regions(0, 0, -1UL);
 		saved_max_pfn = e820_end_of_ram();
+		remove_all_active_ranges();
 #endif
 		end_pfn_map = 0;
 		e820.nr_map = 0;
diff --git a/arch/x86_64/kernel/early-quirks.c b/arch/x86_64/kernel/early-quirks.c
index 2b1245d..68273bf 100644
--- a/arch/x86_64/kernel/early-quirks.c
+++ b/arch/x86_64/kernel/early-quirks.c
@@ -45,7 +45,13 @@ static void nvidia_bugs(void)
 	/*
 	 * All timer overrides on Nvidia are
 	 * wrong unless HPET is enabled.
+	 * Unfortunately that's not true on many Asus boards.
+	 * We don't know yet how to detect this automatically, but
+	 * at least allow a command line override.
 	 */
+	if (acpi_use_timer_override)
+		return;
+
 	nvidia_hpet_detected = 0;
 	acpi_table_parse(ACPI_HPET, nvidia_hpet_check);
 	if (nvidia_hpet_detected == 0) {
@@ -53,6 +59,8 @@ static void nvidia_bugs(void)
 		printk(KERN_INFO "Nvidia board "
 		       "detected. Ignoring ACPI "
 		       "timer override.\n");
+		printk(KERN_INFO "If you got timer trouble "
+			"try acpi_use_timer_override\n");
 	}
 #endif
 	/* RED-PEN skip them on mptables too? */
diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 49f7fac..f622605 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -88,9 +88,8 @@ void enter_idle(void)
 
 static void __exit_idle(void)
 {
-	if (read_pda(isidle) == 0)
+	if (test_and_clear_bit_pda(0, isidle) == 0)
 		return;
-	write_pda(isidle, 0);
 	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
 }
 
diff --git a/arch/x86_64/kernel/smp.c b/arch/x86_64/kernel/smp.c
index 4f67697..9f74c88 100644
--- a/arch/x86_64/kernel/smp.c
+++ b/arch/x86_64/kernel/smp.c
@@ -376,9 +376,8 @@ int smp_call_function_single (int cpu, void (*func) (void *info), void *info,
 	/* prevent preemption and reschedule on another processor */
 	int me = get_cpu();
 	if (cpu == me) {
-		WARN_ON(1);
 		put_cpu();
-		return -EBUSY;
+		return 0;
 	}
 	spin_lock_bh(&call_lock);
 	__smp_call_function_single(cpu, func, info, nonatomic, wait);
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 88722f1..e3ef544 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -876,15 +876,6 @@ static struct irqaction irq0 = {
 	timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL
 };
 
-static int __cpuinit
-time_cpu_notifier(struct notifier_block *nb, unsigned long action, void *hcpu)
-{
-	unsigned cpu = (unsigned long) hcpu;
-	if (action == CPU_ONLINE)
-		vsyscall_set_cpu(cpu);
-	return NOTIFY_DONE;
-}
-
 void __init time_init(void)
 {
 	if (nohpet)
@@ -925,8 +916,6 @@ void __init time_init(void)
 	vxtime.last_tsc = get_cycles_sync();
 	set_cyc2ns_scale(cpu_khz);
 	setup_irq(0, &irq0);
-	hotcpu_notifier(time_cpu_notifier, 0);
-	time_cpu_notifier(NULL, CPU_ONLINE, (void *)(long)smp_processor_id());
 
 #ifndef CONFIG_SMP
 	time_init_gtod();
diff --git a/arch/x86_64/kernel/vsyscall.c b/arch/x86_64/kernel/vsyscall.c
index a98b460..a730bac 100644
--- a/arch/x86_64/kernel/vsyscall.c
+++ b/arch/x86_64/kernel/vsyscall.c
@@ -27,6 +27,9 @@
 #include <linux/jiffies.h>
 #include <linux/sysctl.h>
 #include <linux/getcpu.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/notifier.h>
 
 #include <asm/vsyscall.h>
 #include <asm/pgtable.h>
@@ -243,32 +246,17 @@ static ctl_table kernel_root_table2[] = {
 
 #endif
 
-static void __cpuinit write_rdtscp_cb(void *info)
-{
-	write_rdtscp_aux((unsigned long)info);
-}
-
-void __cpuinit vsyscall_set_cpu(int cpu)
+/* Assume __initcall executes before all user space. Hopefully kmod
+   doesn't violate that. We'll find out if it does. */
+static void __cpuinit vsyscall_set_cpu(int cpu)
 {
 	unsigned long *d;
 	unsigned long node = 0;
 #ifdef CONFIG_NUMA
 	node = cpu_to_node[cpu];
 #endif
-	if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP)) {
-		void *info = (void *)((node << 12) | cpu);
-		/* Can happen on preemptive kernel */
-		if (get_cpu() == cpu)
-			write_rdtscp_cb(info);
-#ifdef CONFIG_SMP
-		else {
-			/* the notifier is unfortunately not executed on the
-			   target CPU */
-			smp_call_function_single(cpu,write_rdtscp_cb,info,0,1);
-		}
-#endif
-		put_cpu();
-	}
+	if (cpu_has(&cpu_data[cpu], X86_FEATURE_RDTSCP))
+		write_rdtscp_aux((node << 12) | cpu);
 
 	/* Store cpu number in limit so that it can be loaded quickly
 	   in user space in vgetcpu.
@@ -280,6 +268,21 @@ void __cpuinit vsyscall_set_cpu(int cpu)
 	*d |= (node >> 4) << 48;
 }
 
+static void __cpuinit cpu_vsyscall_init(void *arg)
+{
+	/* preemption should be already off */
+	vsyscall_set_cpu(raw_smp_processor_id());
+}
+
+static int __cpuinit
+cpu_vsyscall_notifier(struct notifier_block *n, unsigned long action, void *arg)
+{
+	long cpu = (long)arg;
+	if (action == CPU_ONLINE)
+		smp_call_function_single(cpu, cpu_vsyscall_init, NULL, 0, 1);
+	return NOTIFY_DONE;
+}
+
 static void __init map_vsyscall(void)
 {
 	extern char __vsyscall_0;
@@ -299,6 +302,8 @@ static int __init vsyscall_init(void)
 #ifdef CONFIG_SYSCTL
 	register_sysctl_table(kernel_root_table2, 0);
 #endif
+	on_each_cpu(cpu_vsyscall_init, NULL, 0, 1);
+	hotcpu_notifier(cpu_vsyscall_notifier, 0);
 	return 0;
 }
 
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 971dc11..f1f977a 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -655,9 +655,22 @@ void free_initrd_mem(unsigned long start, unsigned long end)
 
 void __init reserve_bootmem_generic(unsigned long phys, unsigned len) 
 { 
-	/* Should check here against the e820 map to avoid double free */ 
 #ifdef CONFIG_NUMA
 	int nid = phys_to_nid(phys);
+#endif
+	unsigned long pfn = phys >> PAGE_SHIFT;
+	if (pfn >= end_pfn) {
+		/* This can happen with kdump kernels when accessing firmware
+		   tables. */
+		if (pfn < end_pfn_map)
+			return;
+		printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %u\n",
+				phys, len);
+		return;
+	}
+
+	/* Should check here against the e820 map to avoid double free */
+#ifdef CONFIG_NUMA
   	reserve_bootmem_node(NODE_DATA(nid), phys, len);
 #else       		
 	reserve_bootmem(phys, len);    
diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c
index e61093b..f8b6b28 100644
--- a/arch/x86_64/pci/mmconfig.c
+++ b/arch/x86_64/pci/mmconfig.c
@@ -163,37 +163,6 @@ static __init void unreachable_devices(void)
 	}
 }
 
-static __init void pci_mmcfg_insert_resources(void)
-{
-#define PCI_MMCFG_RESOURCE_NAME_LEN 19
-	int i;
-	struct resource *res;
-	char *names;
-	unsigned num_buses;
-
-	res = kcalloc(PCI_MMCFG_RESOURCE_NAME_LEN + sizeof(*res),
-			pci_mmcfg_config_num, GFP_KERNEL);
-
-	if (!res) {
-		printk(KERN_ERR "PCI: Unable to allocate MMCONFIG resources\n");
-		return;
-	}
-
-	names = (void *)&res[pci_mmcfg_config_num];
-	for (i = 0; i < pci_mmcfg_config_num; i++, res++) {
-		num_buses = pci_mmcfg_config[i].end_bus_number -
-		    pci_mmcfg_config[i].start_bus_number + 1;
-		res->name = names;
-		snprintf(names, PCI_MMCFG_RESOURCE_NAME_LEN, "PCI MMCONFIG %u",
-			pci_mmcfg_config[i].pci_segment_group_number);
-		res->start = pci_mmcfg_config[i].base_address;
-		res->end = res->start + (num_buses << 20) - 1;
-		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
-		insert_resource(&iomem_resource, res);
-		names += PCI_MMCFG_RESOURCE_NAME_LEN;
-	}
-}
-
 void __init pci_mmcfg_init(int type)
 {
 	int i;
@@ -237,7 +206,6 @@ void __init pci_mmcfg_init(int type)
 	}
 
 	unreachable_devices();
-	pci_mmcfg_insert_resources();
 
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
diff --git a/include/asm-i386/acpi.h b/include/asm-i386/acpi.h
index 6016632..c80b3a9 100644
--- a/include/asm-i386/acpi.h
+++ b/include/asm-i386/acpi.h
@@ -132,6 +132,7 @@ extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
 extern int acpi_skip_timer_override;
+extern int acpi_use_timer_override;
 #endif
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
diff --git a/include/asm-x86_64/acpi.h b/include/asm-x86_64/acpi.h
index ed59aa4..9d1916e 100644
--- a/include/asm-x86_64/acpi.h
+++ b/include/asm-x86_64/acpi.h
@@ -163,6 +163,7 @@ extern u8 x86_acpiid_to_apicid[];
 #define ARCH_HAS_POWER_INIT 1
 
 extern int acpi_skip_timer_override;
+extern int acpi_use_timer_override;
 
 #endif /*__KERNEL__*/
 
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index 14996d9..5642634 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -109,6 +109,15 @@ extern struct x8664_pda _proxy_pda;
 #define sub_pda(field,val) pda_to_op("sub",field,val)
 #define or_pda(field,val) pda_to_op("or",field,val)
 
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define test_and_clear_bit_pda(bit,field) ({		\
+	int old__;						\
+	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"		\
+	    : "=r" (old__), "+m" (_proxy_pda.field) 		\
+	    : "dIr" (bit), "i" (pda_offset(field)) : "memory");	\
+	old__;							\
+})
+
 #endif
 
 #define PDA_STACKOFFSET (5*8)
diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h
index fd452fc..01d1c17 100644
--- a/include/asm-x86_64/vsyscall.h
+++ b/include/asm-x86_64/vsyscall.h
@@ -59,8 +59,6 @@ extern seqlock_t xtime_lock;
 
 extern int sysctl_vsyscall;
 
-extern void vsyscall_set_cpu(int cpu);
-
 #define ARCH_HAVE_XTIME_LOCK 1
 
 #endif /* __KERNEL__ */