Merge commit 'v2.6.28-rc6' into sched/core

16 files changed, 150 insertions, 23 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f232d5a..7b7d276 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -167,9 +167,12 @@ config GENERIC_PENDING_IRQ
 config X86_SMP
 	bool
 	depends on SMP && ((X86_32 && !X86_VOYAGER) || X86_64)
-	select USE_GENERIC_SMP_HELPERS
 	default y
 
+config USE_GENERIC_SMP_HELPERS
+	def_bool y
+	depends on SMP
+
 config X86_32_SMP
 	def_bool y
 	depends on X86_32 && SMP
@@ -957,7 +960,7 @@ config ARCH_PHYS_ADDR_T_64BIT
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support (EXPERIMENTAL)"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && BROKEN)
+	depends on X86_64 || (X86_32 && HIGHMEM64G && (X86_NUMAQ || X86_BIGSMP || X86_SUMMIT && ACPI) && EXPERIMENTAL)
 	default n if X86_PC
 	default y if (X86_NUMAQ || X86_SUMMIT || X86_BIGSMP)
 	help
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
new file mode 100644
index 0000000..c1f0628
--- /dev/null
+++ b/arch/x86/include/asm/iomap.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright © 2008 Ingo Molnar
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ */
+
+#include <linux/fs.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+#include <asm/tlbflush.h>
+
+void *
+iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void
+iounmap_atomic(void *kvaddr, enum km_type type);
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 485bdf0..07f1af4 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -34,10 +34,14 @@ static inline void get_memcfg_numa(void)
 
 extern int early_pfn_to_nid(unsigned long pfn);
 
+extern void resume_map_numa_kva(pgd_t *pgd);
+
 #else /* !CONFIG_NUMA */
 
 #define get_memcfg_numa get_memcfg_numa_flat
 
+static inline void resume_map_numa_kva(pgd_t *pgd) {}
+
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_DISCONTIGMEM
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 664f152..f8cfd00 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,7 +46,7 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
 		return ret;
 	case 10:
 		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
-			       ret, "q", "", "=r", 16);
+			       ret, "q", "", "=r", 10);
 		if (unlikely(ret))
 			return ret;
 		__get_user_asm(*(u16 *)(8 + (char *)dst),
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 834b2c1..d2e415e 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -639,8 +639,8 @@ __SYSCALL(__NR_fallocate, sys_fallocate)
 __SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
 #define __NR_timerfd_gettime			287
 __SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
-#define __NR_paccept				288
-__SYSCALL(__NR_paccept, sys_paccept)
+#define __NR_accept4				288
+__SYSCALL(__NR_accept4, sys_accept4)
 #define __NR_signalfd4				289
 __SYSCALL(__NR_signalfd4, sys_signalfd4)
 #define __NR_eventfd2				290
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 331b318..e4899e0 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -537,7 +537,7 @@ static void dma_ops_free_addresses(struct dma_ops_domain *dom,
 	address >>= PAGE_SHIFT;
 	iommu_area_free(dom->bitmap, address, pages);
 
-	if (address + pages >= dom->next_bit)
+	if (address >= dom->next_bit)
 		dom->need_flush = true;
 }
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 0cdcda3..30ae270 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -121,7 +121,7 @@ u16 amd_iommu_last_bdf;			/* largest PCI device id we have
 LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
 					   we find in ACPI */
 unsigned amd_iommu_aperture_order = 26; /* size of aperture in power of 2 */
-int amd_iommu_isolate;			/* if 1, device isolation is enabled */
+int amd_iommu_isolate = 1;		/* if 1, device isolation is enabled */
 bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */
 
 LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
@@ -1213,7 +1213,9 @@ static int __init parse_amd_iommu_options(char *str)
 	for (; *str; ++str) {
 		if (strncmp(str, "isolate", 7) == 0)
 			amd_iommu_isolate = 1;
-		if (strncmp(str, "fullflush", 11) == 0)
+		if (strncmp(str, "share", 5) == 0)
+			amd_iommu_isolate = 0;
+		if (strncmp(str, "fullflush", 9) == 0)
 			amd_iommu_unmap_flush = true;
 	}
 
diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index 2b69994..d1a1214 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -236,17 +236,33 @@ static inline struct ds_context *ds_alloc_context(struct task_struct *task)
 	struct ds_context *context = *p_context;
 
 	if (!context) {
+		spin_unlock(&ds_lock);
+
 		context = kzalloc(sizeof(*context), GFP_KERNEL);
 
-		if (!context)
+		if (!context) {
+			spin_lock(&ds_lock);
 			return NULL;
+		}
 
 		context->ds = kzalloc(ds_cfg.sizeof_ds, GFP_KERNEL);
 		if (!context->ds) {
 			kfree(context);
+			spin_lock(&ds_lock);
 			return NULL;
 		}
 
+		spin_lock(&ds_lock);
+		/*
+		 * Check for race - another CPU could have allocated
+		 * it meanwhile:
+		 */
+		if (*p_context) {
+			kfree(context->ds);
+			kfree(context);
+			return *p_context;
+		}
+
 		*p_context = context;
 
 		context->this = p_context;
@@ -384,14 +400,15 @@ static int ds_request(struct task_struct *task, void *base, size_t size,
 
 	spin_lock(&ds_lock);
 
-	if (!check_tracer(task))
-		return -EPERM;
-
 	error = -ENOMEM;
 	context = ds_alloc_context(task);
 	if (!context)
 		goto out_unlock;
 
+	error = -EPERM;
+	if (!check_tracer(task))
+		goto out_unlock;
+
 	error = -EALREADY;
 	if (context->owner[qual] == current)
 		goto out_unlock;
diff --git a/arch/x86/kernel/es7000_32.c b/arch/x86/kernel/es7000_32.c
index f454c78f..0aa2c44 100644
--- a/arch/x86/kernel/es7000_32.c
+++ b/arch/x86/kernel/es7000_32.c
@@ -250,31 +250,24 @@ int __init find_unisys_acpi_oem_table(unsigned long *oem_addr)
 {
 	struct acpi_table_header *header = NULL;
 	int i = 0;
-	acpi_size tbl_size;
 
-	while (ACPI_SUCCESS(acpi_get_table_with_size("OEM1", i++, &header, &tbl_size))) {
+	while (ACPI_SUCCESS(acpi_get_table("OEM1", i++, &header))) {
 		if (!memcmp((char *) &header->oem_id, "UNISYS", 6)) {
 			struct oem_table *t = (struct oem_table *)header;
 
 			oem_addrX = t->OEMTableAddr;
 			oem_size = t->OEMTableSize;
-			early_acpi_os_unmap_memory(header, tbl_size);
 
 			*oem_addr = (unsigned long)__acpi_map_table(oem_addrX,
 								    oem_size);
 			return 0;
 		}
-		early_acpi_os_unmap_memory(header, tbl_size);
 	}
 	return -1;
 }
 
 void __init unmap_unisys_acpi_oem_table(unsigned long oem_addr)
 {
-	if (!oem_addr)
-		return;
-
-	__acpi_unmap_table((char *)oem_addr, oem_size);
 }
 #endif
 
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 7a3f202..c9513e1 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1140,6 +1140,20 @@ static void __clear_irq_vector(int irq)
 
 	cfg->vector = 0;
 	cpus_clear(cfg->domain);
+
+	if (likely(!cfg->move_in_progress))
+		return;
+	cpus_and(mask, cfg->old_domain, cpu_online_map);
+	for_each_cpu_mask_nr(cpu, mask) {
+		for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS;
+								vector++) {
+			if (per_cpu(vector_irq, cpu)[vector] != irq)
+				continue;
+			per_cpu(vector_irq, cpu)[vector] = -1;
+			break;
+		}
+	}
+	cfg->move_in_progress = 0;
 }
 
 void __setup_vector_irq(int cpu)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 724adfc..cc5a254 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -169,6 +169,15 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "0KW626"),
 		},
 	},
+	{   /* Handle problems with rebooting on Dell Optiplex 330 with 0KP561 */
+		.callback = set_bios_reboot,
+		.ident = "Dell OptiPlex 330",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 330"),
+			DMI_MATCH(DMI_BOARD_NAME, "0KP561"),
+		},
+	},
 	{	/* Handle problems with rebooting on Dell 2400's */
 		.callback = set_bios_reboot,
 		.ident = "Dell PowerEdge 2400",
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0fa6790..9d5674f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -764,7 +764,7 @@ static struct dmi_system_id __initdata bad_bios_dmi_table[] = {
 		.callback = dmi_low_memory_corruption,
 		.ident = "Phoenix BIOS",
 		.matches = {
-			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies, LTD"),
+			DMI_MATCH(DMI_BIOS_VENDOR, "Phoenix Technologies"),
 		},
 	},
 #endif
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 9ffb01c..1c0dfbc 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -46,7 +46,9 @@ static __cpuinit void check_tsc_warp(void)
 	cycles_t start, now, prev, end;
 	int i;
 
+	rdtsc_barrier();
 	start = get_cycles();
+	rdtsc_barrier();
 	/*
 	 * The measurement runs for 20 msecs:
 	 */
@@ -61,7 +63,9 @@ static __cpuinit void check_tsc_warp(void)
 		 */
 		__raw_spin_lock(&sync_lock);
 		prev = last_tsc;
+		rdtsc_barrier();
 		now = get_cycles();
+		rdtsc_barrier();
 		last_tsc = now;
 		__raw_spin_unlock(&sync_lock);
 
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 0e33165..5214500 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -7,6 +7,7 @@
  * This file provides all the same external entries as smp.c but uses
  * the voyager hal to provide the functionality
  */
+#include <linux/cpu.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/kernel_stat.h>
@@ -1790,6 +1791,17 @@ 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)
+{
+	__u32 mask = cpus_addr(callmask)[0] & ~(1 << smp_processor_id());
+	send_CPI(mask, VIC_CALL_FUNCTION_CPI);
+}
+
+static void voyager_send_call_func_single(int cpu)
+{
+	send_CPI(1 << cpu, VIC_CALL_FUNCTION_SINGLE_CPI);
+}
+
 struct smp_ops smp_ops = {
 	.smp_prepare_boot_cpu = voyager_smp_prepare_boot_cpu,
 	.smp_prepare_cpus = voyager_smp_prepare_cpus,
@@ -1799,6 +1811,6 @@ struct smp_ops smp_ops = {
 	.smp_send_stop = voyager_smp_send_stop,
 	.smp_send_reschedule = voyager_smp_send_reschedule,
 
-	.send_call_func_ipi = native_send_call_func_ipi,
-	.send_call_func_single_ipi = native_send_call_func_single_ipi,
+	.send_call_func_ipi = voyager_send_call_func,
+	.send_call_func_single_ipi = voyager_send_call_func_single,
 };
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 847c164..8518c67 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -222,6 +222,41 @@ static void __init remap_numa_kva(void)
 	}
 }
 
+#ifdef CONFIG_HIBERNATION
+/**
+ * resume_map_numa_kva - add KVA mapping to the temporary page tables created
+ *                       during resume from hibernation
+ * @pgd_base - temporary resume page directory
+ */
+void resume_map_numa_kva(pgd_t *pgd_base)
+{
+	int node;
+
+	for_each_online_node(node) {
+		unsigned long start_va, start_pfn, size, pfn;
+
+		start_va = (unsigned long)node_remap_start_vaddr[node];
+		start_pfn = node_remap_start_pfn[node];
+		size = node_remap_size[node];
+
+		printk(KERN_DEBUG "%s: node %d\n", __FUNCTION__, node);
+
+		for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) {
+			unsigned long vaddr = start_va + (pfn << PAGE_SHIFT);
+			pgd_t *pgd = pgd_base + pgd_index(vaddr);
+			pud_t *pud = pud_offset(pgd, vaddr);
+			pmd_t *pmd = pmd_offset(pud, vaddr);
+
+			set_pmd(pmd, pfn_pmd(start_pfn + pfn,
+						PAGE_KERNEL_LARGE_EXEC));
+
+			printk(KERN_DEBUG "%s: %08lx -> pfn %08lx\n",
+				__FUNCTION__, vaddr, start_pfn + pfn);
+		}
+	}
+}
+#endif
+
 static unsigned long calculate_numa_remap_pages(void)
 {
 	int nid;
diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c
index f2b6e3f..81197c6 100644
--- a/arch/x86/power/hibernate_32.c
+++ b/arch/x86/power/hibernate_32.c
@@ -12,6 +12,7 @@
 #include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/mmzone.h>
 
 /* Defined in hibernate_asm_32.S */
 extern int restore_image(void);
@@ -127,6 +128,9 @@ static int resume_physical_mapping_init(pgd_t *pgd_base)
 			}
 		}
 	}
+
+	resume_map_numa_kva(pgd_base);
+
 	return 0;
 }