Merge ../linus

13 files changed, 70 insertions, 84 deletions

diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index f71fb4a..b2751ea 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -142,6 +142,7 @@ config X86_SUMMIT
 	  In particular, it is needed for the x440.
 
 	  If you don't have one of these computers, you should say N here.
+	  If you want to build a NUMA kernel, you must select ACPI.
 
 config X86_BIGSMP
 	bool "Support for other sub-arch SMP systems with more than 8 CPUs"
@@ -169,6 +170,7 @@ config X86_GENERICARCH
        help
           This option compiles in the Summit, bigsmp, ES7000, default subarchitectures.
 	  It is intended for a generic binary kernel.
+	  If you want a NUMA kernel, select ACPI.   We need SRAT for NUMA.
 
 config X86_ES7000
 	bool "Support for Unisys ES7000 IA32 series"
@@ -542,7 +544,7 @@ config X86_PAE
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support"
-	depends on SMP && HIGHMEM64G && (X86_NUMAQ || X86_GENERICARCH || (X86_SUMMIT && ACPI))
+	depends on SMP && HIGHMEM64G && (X86_NUMAQ || (X86_SUMMIT || X86_GENERICARCH) && ACPI)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT)
 
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index 0db6387..ee003bc 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -59,7 +59,7 @@ static inline int gsi_irq_sharing(int gsi) { return gsi; }
 
 #define BAD_MADT_ENTRY(entry, end) (					    \
 		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
-		((acpi_table_entry_header *)entry)->length != sizeof(*entry))
+		((acpi_table_entry_header *)entry)->length < sizeof(*entry))
 
 #define PREFIX			"ACPI: "
 
diff --git a/arch/i386/kernel/acpi/wakeup.S b/arch/i386/kernel/acpi/wakeup.S
index 9f408ee..b781b38 100644
--- a/arch/i386/kernel/acpi/wakeup.S
+++ b/arch/i386/kernel/acpi/wakeup.S
@@ -292,7 +292,10 @@ ENTRY(do_suspend_lowlevel)
 	pushl	$3
 	call	acpi_enter_sleep_state
 	addl	$4, %esp
-	ret
+
+#	In case of S3 failure, we'll emerge here.  Jump
+# 	to ret_point to recover
+	jmp	ret_point
 	.p2align 4,,7
 ret_point:
 	call	restore_registers
diff --git a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
index efb41e8..e6ea00e 100644
--- a/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/i386/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -567,16 +567,11 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 static int __init
 acpi_cpufreq_init (void)
 {
-	int                     result = 0;
-
 	dprintk("acpi_cpufreq_init\n");
 
-	result = acpi_cpufreq_early_init_acpi();
+	acpi_cpufreq_early_init_acpi();
 
-	if (!result)
- 		result = cpufreq_register_driver(&acpi_cpufreq_driver);
-	
-	return (result);
+ 	return cpufreq_register_driver(&acpi_cpufreq_driver);
 }
 
 
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index eb79aa2..a6b8bd8 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -317,20 +317,14 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%gs
 	lldt %ax
 	cld			# gcc2 wants the direction flag cleared at all times
+	pushl %eax		# fake return address
 #ifdef CONFIG_SMP
 	movb ready, %cl
 	movb $1, ready
-	cmpb $0,%cl
-	je 1f			# the first CPU calls start_kernel
-				# all other CPUs call initialize_secondary
-	call initialize_secondary
-	jmp L6
-1:
+	cmpb $0,%cl		# the first CPU calls start_kernel
+	jne initialize_secondary # all other CPUs call initialize_secondary
 #endif /* CONFIG_SMP */
-	call start_kernel
-L6:
-	jmp L6			# main should never return here, but
-				# just in case, we know what happens.
+	jmp start_kernel
 
 /*
  * We depend on ET to be correct. This checks for 287/387.
diff --git a/arch/i386/kernel/hpet.c b/arch/i386/kernel/hpet.c
index c6737c3..17647a5 100644
--- a/arch/i386/kernel/hpet.c
+++ b/arch/i386/kernel/hpet.c
@@ -35,7 +35,7 @@ static int __init init_hpet_clocksource(void)
 	void __iomem* hpet_base;
 	u64 tmp;
 
-	if (!hpet_address)
+	if (!is_hpet_enabled())
 		return -ENODEV;
 
 	/* calculate the hpet address: */
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 6cb529f..5fe547c 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -82,10 +82,6 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
 	}
 #endif
 
-	if (!irq_desc[irq].handle_irq) {
-		__do_IRQ(irq, regs);
-		goto out_exit;
-	}
 #ifdef CONFIG_4KSTACKS
 
 	curctx = (union irq_ctx *) current_thread_info();
@@ -125,7 +121,6 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
 #endif
 		__do_IRQ(irq, regs);
 
-out_exit:
 	irq_exit();
 
 	return 1;
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index f168220..345ffb7 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -956,38 +956,6 @@ efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
 	return 0;
 }
 
- /*
-  * This function checks if the entire range <start,end> is mapped with type.
-  *
-  * Note: this function only works correct if the e820 table is sorted and
-  * not-overlapping, which is the case
-  */
-int __init
-e820_all_mapped(unsigned long s, unsigned long e, unsigned type)
-{
-	u64 start = s;
-	u64 end = e;
-	int i;
-	for (i = 0; i < e820.nr_map; i++) {
-		struct e820entry *ei = &e820.map[i];
-		if (type && ei->type != type)
-			continue;
-		/* is the region (part) in overlap with the current region ?*/
-		if (ei->addr >= end || ei->addr + ei->size <= start)
-			continue;
-		/* if the region is at the beginning of <start,end> we move
-		 * start to the end of the region since it's ok until there
-		 */
-		if (ei->addr <= start)
-			start = ei->addr + ei->size;
-		/* if start is now at or beyond end, we're done, full
-		 * coverage */
-		if (start >= end)
-			return 1; /* we're done */
-	}
-	return 0;
-}
-
 /*
  * Find the highest page frame number we have available
  */
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 0d4005dc..7e9edaf 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -92,7 +92,11 @@ asmlinkage void spurious_interrupt_bug(void);
 asmlinkage void machine_check(void);
 
 static int kstack_depth_to_print = 24;
+#ifdef CONFIG_STACK_UNWIND
 static int call_trace = 1;
+#else
+#define call_trace (-1)
+#endif
 ATOMIC_NOTIFIER_HEAD(i386die_chain);
 
 int register_die_notifier(struct notifier_block *nb)
@@ -187,22 +191,21 @@ static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			if (unwind_init_blocked(&info, task) == 0)
 				unw_ret = show_trace_unwind(&info, log_lvl);
 		}
-		if (unw_ret > 0 && !arch_unw_user_mode(&info)) {
-#ifdef CONFIG_STACK_UNWIND
-			print_symbol("DWARF2 unwinder stuck at %s\n",
-				     UNW_PC(&info));
-			if (call_trace == 1) {
-				printk("Leftover inexact backtrace:\n");
-				if (UNW_SP(&info))
+		if (unw_ret > 0) {
+			if (call_trace == 1 && !arch_unw_user_mode(&info)) {
+				print_symbol("DWARF2 unwinder stuck at %s\n",
+					     UNW_PC(&info));
+				if (UNW_SP(&info) >= PAGE_OFFSET) {
+					printk("Leftover inexact backtrace:\n");
 					stack = (void *)UNW_SP(&info);
-			} else if (call_trace > 1)
+				} else
+					printk("Full inexact backtrace again:\n");
+			} else if (call_trace >= 1)
 				return;
 			else
 				printk("Full inexact backtrace again:\n");
-#else
+		} else
 			printk("Inexact backtrace:\n");
-#endif
-		}
 	}
 
 	if (task == current) {
@@ -454,7 +457,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 		panic("Fatal exception in interrupt");
 
 	if (panic_on_oops)
-		panic("Fatal exception: panic_on_oops");
+		panic("Fatal exception");
 
 	oops_exit();
 	do_exit(SIGSEGV);
@@ -1241,6 +1244,7 @@ static int __init kstack_setup(char *s)
 }
 __setup("kstack=", kstack_setup);
 
+#ifdef CONFIG_STACK_UNWIND
 static int __init call_trace_setup(char *s)
 {
 	if (strcmp(s, "old") == 0)
@@ -1254,3 +1258,4 @@ static int __init call_trace_setup(char *s)
 	return 1;
 }
 __setup("call_trace=", call_trace_setup);
+#endif
diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c
index 0a362e3..1220dd8 100644
--- a/arch/i386/pci/common.c
+++ b/arch/i386/pci/common.c
@@ -237,6 +237,11 @@ char * __devinit  pcibios_setup(char *str)
 		pci_probe &= ~PCI_PROBE_MMCONF;
 		return NULL;
 	}
+	/* override DMI blacklist */
+	else if (!strcmp(str, "mmconf")) {
+		pci_probe |= PCI_PROBE_MMCONF_FORCE;
+		return NULL;
+	}
 #endif
 	else if (!strcmp(str, "noacpi")) {
 		acpi_noirq_set();
diff --git a/arch/i386/pci/init.c b/arch/i386/pci/init.c
index c7650a7..51087a9 100644
--- a/arch/i386/pci/init.c
+++ b/arch/i386/pci/init.c
@@ -14,8 +14,12 @@ static __init int pci_access_init(void)
 #ifdef CONFIG_PCI_BIOS
 	pci_pcbios_init();
 #endif
-	if (raw_pci_ops)
-		return 0;
+	/*
+	 * don't check for raw_pci_ops here because we want pcbios as last
+	 * fallback, yet it's needed to run first to set pcibios_last_bus
+	 * in case legacy PCI probing is used. otherwise detecting peer busses
+	 * fails.
+	 */
 #ifdef CONFIG_PCI_DIRECT
 	pci_direct_init();
 #endif
diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c
index e545b09..ef5a2fa 100644
--- a/arch/i386/pci/mmconfig.c
+++ b/arch/i386/pci/mmconfig.c
@@ -12,6 +12,7 @@
 #include <linux/pci.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/dmi.h>
 #include <asm/e820.h>
 #include "pci.h"
 
@@ -178,7 +179,7 @@ static __init void unreachable_devices(void)
 				pci_exp_set_dev_base(addr, k, PCI_DEVFN(i, 0));
 			if (addr == 0 ||
 			    readl((u32 __iomem *)mmcfg_virt_addr) != val1) {
-				set_bit(i, fallback_slots);
+				set_bit(i + 32*k, fallback_slots);
 				printk(KERN_NOTICE
 			"PCI: No mmconfig possible on %x:%x\n", k, i);
 			}
@@ -187,9 +188,31 @@ static __init void unreachable_devices(void)
 	}
 }
 
+static int disable_mcfg(struct dmi_system_id *d)
+{
+	printk("PCI: %s detected. Disabling MCFG.\n", d->ident);
+	pci_probe &= ~PCI_PROBE_MMCONF;
+	return 0;
+}
+
+static struct dmi_system_id __initdata dmi_bad_mcfg[] = {
+	/* Has broken MCFG table that makes the system hang when used */
+        {
+         .callback = disable_mcfg,
+         .ident = "Intel D3C5105 SDV",
+         .matches = {
+                     DMI_MATCH(DMI_BIOS_VENDOR, "Intel"),
+                     DMI_MATCH(DMI_BOARD_NAME, "D26928"),
+                     },
+         },
+         {}
+};
+
 void __init pci_mmcfg_init(void)
 {
-	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
+	dmi_check_system(dmi_bad_mcfg);
+
+	if ((pci_probe & (PCI_PROBE_MMCONF_FORCE|PCI_PROBE_MMCONF)) == 0)
 		return;
 
 	acpi_table_parse(ACPI_MCFG, acpi_parse_mcfg);
@@ -198,15 +221,6 @@ void __init pci_mmcfg_init(void)
 	    (pci_mmcfg_config[0].base_address == 0))
 		return;
 
-	if (!e820_all_mapped(pci_mmcfg_config[0].base_address,
-			pci_mmcfg_config[0].base_address + MMCONFIG_APER_MIN,
-			E820_RESERVED)) {
-		printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %x is not E820-reserved\n",
-				pci_mmcfg_config[0].base_address);
-		printk(KERN_ERR "PCI: Not using MMCONFIG.\n");
-		return;
-	}
-
 	printk(KERN_INFO "PCI: Using MMCONFIG\n");
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h
index bf4e793..49a849b 100644
--- a/arch/i386/pci/pci.h
+++ b/arch/i386/pci/pci.h
@@ -16,7 +16,8 @@
 #define PCI_PROBE_CONF1		0x0002
 #define PCI_PROBE_CONF2		0x0004
 #define PCI_PROBE_MMCONF	0x0008
-#define PCI_PROBE_MASK		0x000f
+#define PCI_PROBE_MMCONF_FORCE	0x0010
+#define PCI_PROBE_MASK		0x00ff
 
 #define PCI_NO_SORT		0x0100
 #define PCI_BIOS_SORT		0x0200