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

…nux/kernel/git/tip/linux-2.6-tip

* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (32 commits)
  x86: add MAP_STACK mmap flag
  x86: fix section mismatch warning - spp_getpage()
  x86: change init_gdt to update the gdt via write_gdt, rather than a direct write.
  x86-64: fix overlap of modules and fixmap areas
  x86, geode-mfgpt: check IRQ before using MFGPT as clocksource
  x86, acpi: cleanup, temp_stack is used only when CONFIG_SMP is set
  x86: fix spin_is_contended()
  x86, nmi: clean UP NMI watchdog failure message
  x86, NMI: fix watchdog failure message
  x86: fix /proc/meminfo DirectMap
  x86: fix readb() et al compile error with gcc-3.2.3
  arch/x86/Kconfig: clean up, experimental adjustement
  x86: invalidate caches before going into suspend
  x86, perfctr: don't use CCCR_OVF_PMI1 on Pentium 4Ds
  x86, AMD IOMMU: initialize dma_ops after sysfs registration
  x86m AMD IOMMU: cleanup: replace LOW_U32 macro with generic lower_32_bits
  x86, AMD IOMMU: initialize device table properly
  x86, AMD IOMMU: use status bit instead of memory write-back for completion wait
  x86: silence mmconfig printk
  x86, msr: fix NULL pointer deref due to msr_open on nonexistent CPUs
  ...

arch/x86/Kconfig

@@ -951,9 +951,9 @@ config NUMA
 	  local memory controller of the CPU and add some more
 	  NUMA awareness to the kernel.
 
-	  For i386 this is currently highly experimental and should be only
+	  For 32-bit this is currently highly experimental and should be only
 	  used for kernel development. It might also cause boot failures.
-	  For x86_64 this is recommended on all multiprocessor Opteron systems.
+	  For 64-bit this is recommended on all multiprocessor Opteron systems.
 	  If the system is EM64T, you should say N unless your system is
 	  EM64T NUMA.
 
@@ -1263,7 +1263,7 @@ config KEXEC
 	  strongly in flux, so no good recommendation can be made.
 
 config CRASH_DUMP
-	bool "kernel crash dumps (EXPERIMENTAL)"
+	bool "kernel crash dumps"
 	depends on X86_64 || (X86_32 && HIGHMEM)
 	help
 	  Generate crash dump after being started by kexec.

arch/x86/boot/boot.h

@@ -24,6 +24,8 @@
 #include <linux/edd.h>
 #include <asm/boot.h>
 #include <asm/setup.h>
+#include "bitops.h"
+#include <asm/cpufeature.h>
 
 /* Useful macros */
 #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
@@ -242,6 +244,12 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize);
 int cmdline_find_option_bool(const char *option);
 
 /* cpu.c, cpucheck.c */
+struct cpu_features {
+	int level;		/* Family, or 64 for x86-64 */
+	int model;
+	u32 flags[NCAPINTS];
+};
+extern struct cpu_features cpu;
 int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr);
 int validate_cpu(void);
 

arch/x86/boot/cpu.c

@@ -16,9 +16,6 @@
  */
 
 #include "boot.h"
-#include "bitops.h"
-#include <asm/cpufeature.h>
-
 #include "cpustr.h"
 
 static char *cpu_name(int level)

arch/x86/boot/cpucheck.c

@@ -22,21 +22,13 @@
 
 #ifdef _SETUP
 # include "boot.h"
-# include "bitops.h"
 #endif
 #include <linux/types.h>
-#include <asm/cpufeature.h>
 #include <asm/processor-flags.h>
 #include <asm/required-features.h>
 #include <asm/msr-index.h>
 
-struct cpu_features {
-	int level;		/* Family, or 64 for x86-64 */
-	int model;
-	u32 flags[NCAPINTS];
-};
-
-static struct cpu_features cpu;
+struct cpu_features cpu;
 static u32 cpu_vendor[3];
 static u32 err_flags[NCAPINTS];
 

arch/x86/boot/main.c

@@ -73,6 +73,11 @@ static void keyboard_set_repeat(void)
  */
 static void query_ist(void)
 {
+	/* Some older BIOSes apparently crash on this call, so filter
+	   it from machines too old to have SpeedStep at all. */
+	if (cpu.level < 6)
+		return;
+
 	asm("int $0x15"
 	    : "=a" (boot_params.ist_info.signature),
 	      "=b" (boot_params.ist_info.command),

arch/x86/kernel/acpi/boot.c

@@ -97,6 +97,8 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
 #warning ACPI uses CMPXCHG, i486 and later hardware
 #endif
 
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
    -------------------------------------------------------------------------- */
@@ -158,6 +160,14 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
 struct acpi_mcfg_allocation *pci_mmcfg_config;
 int pci_mmcfg_config_num;
 
+static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
+{
+	if (!strcmp(mcfg->header.oem_id, "SGI"))
+		acpi_mcfg_64bit_base_addr = TRUE;
+
+	return 0;
+}
+
 int __init acpi_parse_mcfg(struct acpi_table_header *header)
 {
 	struct acpi_table_mcfg *mcfg;
@@ -190,8 +200,12 @@ int __init acpi_parse_mcfg(struct acpi_table_header *header)
 	}
 
 	memcpy(pci_mmcfg_config, &mcfg[1], config_size);
+
+	acpi_mcfg_oem_check(mcfg);
+
 	for (i = 0; i < pci_mmcfg_config_num; ++i) {
-		if (pci_mmcfg_config[i].address > 0xFFFFFFFF) {
+		if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) &&
+		    !acpi_mcfg_64bit_base_addr) {
 			printk(KERN_ERR PREFIX
 			       "MMCONFIG not in low 4GB of memory\n");
 			kfree(pci_mmcfg_config);

arch/x86/kernel/acpi/sleep.c

@@ -20,7 +20,7 @@ unsigned long acpi_realmode_flags;
 /* address in low memory of the wakeup routine. */
 static unsigned long acpi_realmode;
 
-#ifdef CONFIG_64BIT
+#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
 static char temp_stack[10240];
 #endif
 

arch/x86/kernel/amd_iommu.c

@@ -101,16 +101,13 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
  */
 static int iommu_completion_wait(struct amd_iommu *iommu)
 {
-	int ret;
+	int ret, ready = 0;
+	unsigned status = 0;
 	struct iommu_cmd cmd;
-	volatile u64 ready = 0;
-	unsigned long ready_phys = virt_to_phys(&ready);
 	unsigned long i = 0;
 
 	memset(&cmd, 0, sizeof(cmd));
-	cmd.data[0] = LOW_U32(ready_phys) | CMD_COMPL_WAIT_STORE_MASK;
-	cmd.data[1] = upper_32_bits(ready_phys);
-	cmd.data[2] = 1; /* value written to 'ready' */
+	cmd.data[0] = CMD_COMPL_WAIT_INT_MASK;
 	CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT);
 
 	iommu->need_sync = 0;
@@ -122,9 +119,15 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 
 	while (!ready && (i < EXIT_LOOP_COUNT)) {
 		++i;
-		cpu_relax();
+		/* wait for the bit to become one */
+		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+		ready = status & MMIO_STATUS_COM_WAIT_INT_MASK;
 	}
 
+	/* set bit back to zero */
+	status &= ~MMIO_STATUS_COM_WAIT_INT_MASK;
+	writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
 	if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit()))
 		printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n");
 
@@ -161,7 +164,7 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu,
 	address &= PAGE_MASK;
 	CMD_SET_TYPE(&cmd, CMD_INV_IOMMU_PAGES);
 	cmd.data[1] |= domid;
-	cmd.data[2] = LOW_U32(address);
+	cmd.data[2] = lower_32_bits(address);
 	cmd.data[3] = upper_32_bits(address);
 	if (s) /* size bit - we flush more than one 4kb page */
 		cmd.data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;

arch/x86/kernel/amd_iommu_init.c

@@ -800,6 +800,21 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
 	return 0;
 }
 
+/*
+ * Init the device table to not allow DMA access for devices and
+ * suppress all page faults
+ */
+static void init_device_table(void)
+{
+	u16 devid;
+
+	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
+		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
+		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
+		set_dev_entry_bit(devid, DEV_ENTRY_NO_PAGE_FAULT);
+	}
+}
+
 /*
  * This function finally enables all IOMMUs found in the system after
  * they have been initialized
@@ -931,6 +946,9 @@ int __init amd_iommu_init(void)
 	if (amd_iommu_pd_alloc_bitmap == NULL)
 		goto free;
 
+	/* init the device table */
+	init_device_table();
+
 	/*
 	 * let all alias entries point to itself
 	 */
@@ -954,15 +972,15 @@ int __init amd_iommu_init(void)
 	if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
 		goto free;
 
-	ret = amd_iommu_init_dma_ops();
+	ret = sysdev_class_register(&amd_iommu_sysdev_class);
 	if (ret)
 		goto free;
 
-	ret = sysdev_class_register(&amd_iommu_sysdev_class);
+	ret = sysdev_register(&device_amd_iommu);
 	if (ret)
 		goto free;
 
-	ret = sysdev_register(&device_amd_iommu);
+	ret = amd_iommu_init_dma_ops();
 	if (ret)
 		goto free;
 

arch/x86/kernel/apic_32.c

@@ -1454,8 +1454,6 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 	}
 }
 
-unsigned int __cpuinitdata maxcpus = NR_CPUS;
-
 void __cpuinit generic_processor_info(int apicid, int version)
 {
 	int cpu;
@@ -1482,12 +1480,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		return;
 	}
 
-	if (num_processors >= maxcpus) {
-		printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
-			" Processor ignored.\n", maxcpus);
-		return;
-	}
-
 	num_processors++;
 	cpus_complement(tmp_map, cpu_present_map);
 	cpu = first_cpu(tmp_map);

arch/x86/kernel/apic_64.c

@@ -90,7 +90,6 @@ static unsigned long apic_phys;
 
 unsigned long mp_lapic_addr;
 
-unsigned int __cpuinitdata maxcpus = NR_CPUS;
 /*
  * Get the LAPIC version
  */
@@ -1062,12 +1061,6 @@ void __cpuinit generic_processor_info(int apicid, int version)
 		return;
 	}
 
-	if (num_processors >= maxcpus) {
-		printk(KERN_WARNING "WARNING: maxcpus limit of %i reached."
-		       " Processor ignored.\n", maxcpus);
-		return;
-	}
-
 	num_processors++;
 	cpus_complement(tmp_map, cpu_present_map);
 	cpu = first_cpu(tmp_map);

arch/x86/kernel/cpu/perfctr-watchdog.c

@@ -478,7 +478,13 @@ static int setup_p4_watchdog(unsigned nmi_hz)
 		perfctr_msr = MSR_P4_IQ_PERFCTR1;
 		evntsel_msr = MSR_P4_CRU_ESCR0;
 		cccr_msr = MSR_P4_IQ_CCCR1;
-		cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4);
+
+		/* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */
+		if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4)
+			cccr_val = P4_CCCR_OVF_PMI0;
+		else
+			cccr_val = P4_CCCR_OVF_PMI1;
+		cccr_val |= P4_CCCR_ESCR_SELECT(4);
 	}
 
 	evntsel = P4_ESCR_EVENT_SELECT(0x3F)

arch/x86/kernel/genx2apic_uv_x.c

@@ -222,7 +222,7 @@ static __init void map_low_mmrs(void)
 
 enum map_type {map_wb, map_uc};
 
-static void map_high(char *id, unsigned long base, int shift, enum map_type map_type)
+static __init void map_high(char *id, unsigned long base, int shift, enum map_type map_type)
 {
 	unsigned long bytes, paddr;
 

arch/x86/kernel/head64.c

@@ -88,6 +88,7 @@ void __init x86_64_start_kernel(char * real_mode_data)
 	BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
 	BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) ==
 				(__START_KERNEL & PGDIR_MASK)));
+	BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END);
 
 	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();

arch/x86/kernel/hpet.c

@@ -359,6 +359,7 @@ static int hpet_clocksource_register(void)
 int __init hpet_enable(void)
 {
 	unsigned long id;
+	int i;
 
 	if (!is_hpet_capable())
 		return 0;
@@ -369,6 +370,29 @@ int __init hpet_enable(void)
 	 * Read the period and check for a sane value:
 	 */
 	hpet_period = hpet_readl(HPET_PERIOD);
+
+	/*
+	 * AMD SB700 based systems with spread spectrum enabled use a
+	 * SMM based HPET emulation to provide proper frequency
+	 * setting. The SMM code is initialized with the first HPET
+	 * register access and takes some time to complete. During
+	 * this time the config register reads 0xffffffff. We check
+	 * for max. 1000 loops whether the config register reads a non
+	 * 0xffffffff value to make sure that HPET is up and running
+	 * before we go further. A counting loop is safe, as the HPET
+	 * access takes thousands of CPU cycles. On non SB700 based
+	 * machines this check is only done once and has no side
+	 * effects.
+	 */
+	for (i = 0; hpet_readl(HPET_CFG) == 0xFFFFFFFF; i++) {
+		if (i == 1000) {
+			printk(KERN_WARNING
+			       "HPET config register value = 0xFFFFFFFF. "
+			       "Disabling HPET\n");
+			goto out_nohpet;
+		}
+	}
+
 	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
 		goto out_nohpet;