14 files changed, 191 insertions, 370 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cf42fc30541..73c0bda73fc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -28,6 +28,7 @@ config X86
 	select HAVE_KPROBES
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select ARCH_WANT_FRAME_POINTERS
+	select HAVE_DMA_ATTRS
 	select HAVE_KRETPROBES
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_DYNAMIC_FTRACE
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 8d16ada2504..ec749c2bfdd 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -70,6 +70,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
 KBUILD_CFLAGS	+= $(call cc-option, -m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
 
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
 
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 49c8a4c37d7..e2ff504b4dd 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -15,6 +15,7 @@ KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 KBUILD_CFLAGS += $(call cc-option,-fno-stack-protector)
 
 KBUILD_AFLAGS  := $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
 LDFLAGS_vmlinux := -T
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index b93405b228b..1c3f9435f1c 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -33,6 +33,8 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 #endif
 }
 
+#include <asm-generic/dma-mapping-common.h>
+
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -53,177 +55,6 @@ extern int dma_set_mask(struct device *dev, u64 mask);
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 					dma_addr_t *dma_addr, gfp_t flag);
 
-static inline dma_addr_t
-dma_map_single(struct device *hwdev, void *ptr, size_t size,
-	       enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	kmemcheck_mark_initialized(ptr, size);
-	addr = ops->map_page(hwdev, virt_to_page(ptr),
-			     (unsigned long)ptr & ~PAGE_MASK, size,
-			     dir, NULL);
-	debug_dma_map_page(hwdev, virt_to_page(ptr),
-			   (unsigned long)ptr & ~PAGE_MASK, size,
-			   dir, addr, true);
-	return addr;
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
-		 enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, true);
-}
-
-static inline int
-dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-	   int nents, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-	int ents;
-	struct scatterlist *s;
-	int i;
-
-	BUG_ON(!valid_dma_direction(dir));
-	for_each_sg(sg, s, nents, i)
-		kmemcheck_mark_initialized(sg_virt(s), s->length);
-	ents = ops->map_sg(hwdev, sg, nents, dir, NULL);
-	debug_dma_map_sg(hwdev, sg, nents, ents, dir);
-
-	return ents;
-}
-
-static inline void
-dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-	     enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	debug_dma_unmap_sg(hwdev, sg, nents, dir);
-	if (ops->unmap_sg)
-		ops->unmap_sg(hwdev, sg, nents, dir, NULL);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(hwdev, dma_handle, size, dir);
-	debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
-			   size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(hwdev, dma_handle, size, dir);
-	debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_range_for_cpu)
-		ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-					       size, dir);
-	debug_dma_sync_single_range_for_cpu(hwdev, dma_handle,
-					    offset, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_single_range_for_device)
-		ops->sync_single_range_for_device(hwdev, dma_handle,
-						  offset, size, dir);
-	debug_dma_sync_single_range_for_device(hwdev, dma_handle,
-					       offset, size, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(hwdev, sg, nelems, dir);
-	debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(hwdev, sg, nelems, dir);
-	debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir);
-
-	flush_write_buffers();
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	dma_addr_t addr;
-
-	BUG_ON(!valid_dma_direction(dir));
-	kmemcheck_mark_initialized(page_address(page) + offset, size);
-	addr = ops->map_page(dev, page, offset, size, dir, NULL);
-	debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-	return addr;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-				  size_t size, enum dma_data_direction dir)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(dir));
-	if (ops->unmap_page)
-		ops->unmap_page(dev, addr, size, dir, NULL);
-	debug_dma_unmap_page(dev, addr, size, dir, false);
-}
-
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	enum dma_data_direction dir)
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index f3477bb8456..6c327b852e2 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -24,6 +24,8 @@ CFLAGS_vsyscall_64.o	:= $(PROFILING) -g0 $(nostackp)
 CFLAGS_hpet.o		:= $(nostackp)
 CFLAGS_tsc.o		:= $(nostackp)
 CFLAGS_paravirt.o	:= $(nostackp)
+GCOV_PROFILE_vsyscall_64.o	:= n
+GCOV_PROFILE_hpet.o		:= n
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile
index 167bc16ce0e..6a564ac67ef 100644
--- a/arch/x86/kernel/acpi/realmode/Makefile
+++ b/arch/x86/kernel/acpi/realmode/Makefile
@@ -42,6 +42,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D_WAKEUP -D__KERNEL__ \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
 KBUILD_CFLAGS	+= $(call cc-option, -m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
+GCOV_PROFILE := n
 
 WAKEUP_OBJS = $(addprefix $(obj)/,$(wakeup-y))
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index cf52215d9eb..81cbe64ed6b 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1,3 +1,4 @@
+
 /*
  *   (c) 2003-2006 Advanced Micro Devices, Inc.
  *  Your use of this code is subject to the terms and conditions of the
@@ -117,20 +118,17 @@ static int query_current_values_with_pending_wait(struct powernow_k8_data *data)
 	u32 i = 0;
 
 	if (cpu_family == CPU_HW_PSTATE) {
-		if (data->currpstate == HW_PSTATE_INVALID) {
-			/* read (initial) hw pstate if not yet set */
-			rdmsr(MSR_PSTATE_STATUS, lo, hi);
-			i = lo & HW_PSTATE_MASK;
-
-			/*
-			 * a workaround for family 11h erratum 311 might cause
-			 * an "out-of-range Pstate if the core is in Pstate-0
-			 */
-			if (i >= data->numps)
-				data->currpstate = HW_PSTATE_0;
-			else
-				data->currpstate = i;
-		}
+		rdmsr(MSR_PSTATE_STATUS, lo, hi);
+		i = lo & HW_PSTATE_MASK;
+		data->currpstate = i;
+
+		/*
+		 * a workaround for family 11h erratum 311 might cause
+		 * an "out-of-range Pstate if the core is in Pstate-0
+		 */
+		if ((boot_cpu_data.x86 == 0x11) && (i >= data->numps))
+			data->currpstate = HW_PSTATE_0;
+
 		return 0;
 	}
 	do {
@@ -510,41 +508,34 @@ static int core_voltage_post_transition(struct powernow_k8_data *data,
 	return 0;
 }
 
-static int check_supported_cpu(unsigned int cpu)
+static void check_supported_cpu(void *_rc)
 {
-	cpumask_t oldmask;
 	u32 eax, ebx, ecx, edx;
-	unsigned int rc = 0;
-
-	oldmask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
+	int *rc = _rc;
 
-	if (smp_processor_id() != cpu) {
-		printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu);
-		goto out;
-	}
+	*rc = -ENODEV;
 
 	if (current_cpu_data.x86_vendor != X86_VENDOR_AMD)
-		goto out;
+		return;
 
 	eax = cpuid_eax(CPUID_PROCESSOR_SIGNATURE);
 	if (((eax & CPUID_XFAM) != CPUID_XFAM_K8) &&
 	    ((eax & CPUID_XFAM) < CPUID_XFAM_10H))
-		goto out;
+		return;
 
 	if ((eax & CPUID_XFAM) == CPUID_XFAM_K8) {
 		if (((eax & CPUID_USE_XFAM_XMOD) != CPUID_USE_XFAM_XMOD) ||
 		    ((eax & CPUID_XMOD) > CPUID_XMOD_REV_MASK)) {
 			printk(KERN_INFO PFX
 				"Processor cpuid %x not supported\n", eax);
-			goto out;
+			return;
 		}
 
 		eax = cpuid_eax(CPUID_GET_MAX_CAPABILITIES);
 		if (eax < CPUID_FREQ_VOLT_CAPABILITIES) {
 			printk(KERN_INFO PFX
 			       "No frequency change capabilities detected\n");
-			goto out;
+			return;
 		}
 
 		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
@@ -552,21 +543,17 @@ static int check_supported_cpu(unsigned int cpu)
 			!= P_STATE_TRANSITION_CAPABLE) {
 			printk(KERN_INFO PFX
 				"Power state transitions not supported\n");
-			goto out;
+			return;
 		}
 	} else { /* must be a HW Pstate capable processor */
 		cpuid(CPUID_FREQ_VOLT_CAPABILITIES, &eax, &ebx, &ecx, &edx);
 		if ((edx & USE_HW_PSTATE) == USE_HW_PSTATE)
 			cpu_family = CPU_HW_PSTATE;
 		else
-			goto out;
+			return;
 	}
 
-	rc = 1;
-
-out:
-	set_cpus_allowed_ptr(current, &oldmask);
-	return rc;
+	*rc = 0;
 }
 
 static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst,
@@ -823,13 +810,14 @@ static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data,
 	if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE))
 		return;
 
-	control = data->acpi_data.states[index].control; data->irt = (control
-			>> IRT_SHIFT) & IRT_MASK; data->rvo = (control >>
-				RVO_SHIFT) & RVO_MASK; data->exttype = (control
-					>> EXT_TYPE_SHIFT) & EXT_TYPE_MASK;
-	data->plllock = (control >> PLL_L_SHIFT) & PLL_L_MASK; data->vidmvs = 1
-		<< ((control >> MVS_SHIFT) & MVS_MASK); data->vstable =
-		(control >> VST_SHIFT) & VST_MASK; }
+	control = data->acpi_data.states[index].control;
+	data->irt = (control >> IRT_SHIFT) & IRT_MASK;
+	data->rvo = (control >> RVO_SHIFT) & RVO_MASK;
+	data->exttype = (control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK;
+	data->plllock = (control >> PLL_L_SHIFT) & PLL_L_MASK;
+	data->vidmvs = 1 << ((control >> MVS_SHIFT) & MVS_MASK);
+	data->vstable = (control >> VST_SHIFT) & VST_MASK;
+}
 
 static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 {
@@ -1046,6 +1034,19 @@ static int get_transition_latency(struct powernow_k8_data *data)
 		if (cur_latency > max_latency)
 			max_latency = cur_latency;
 	}
+	if (max_latency == 0) {
+		/*
+		 * Fam 11h always returns 0 as transition latency.
+		 * This is intended and means "very fast". While cpufreq core
+		 * and governors currently can handle that gracefully, better
+		 * set it to 1 to avoid problems in the future.
+		 * For all others it's a BIOS bug.
+		 */
+		if (!boot_cpu_data.x86 == 0x11)
+			printk(KERN_ERR FW_WARN PFX "Invalid zero transition "
+				"latency\n");
+		max_latency = 1;
+	}
 	/* value in usecs, needs to be in nanoseconds */
 	return 1000 * max_latency;
 }
@@ -1093,7 +1094,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	freqs.old = find_khz_freq_from_fid(data->currfid);
 	freqs.new = find_khz_freq_from_fid(fid);
 
-	for_each_cpu_mask_nr(i, *(data->available_cores)) {
+	for_each_cpu(i, data->available_cores) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
@@ -1101,7 +1102,7 @@ static int transition_frequency_fidvid(struct powernow_k8_data *data,
 	res = transition_fid_vid(data, fid, vid);
 	freqs.new = find_khz_freq_from_fid(data->currfid);
 
-	for_each_cpu_mask_nr(i, *(data->available_cores)) {
+	for_each_cpu(i, data->available_cores) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	}
@@ -1126,7 +1127,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data,
 			data->currpstate);
 	freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate);
 
-	for_each_cpu_mask_nr(i, *(data->available_cores)) {
+	for_each_cpu(i, data->available_cores) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
@@ -1134,7 +1135,7 @@ static int transition_frequency_pstate(struct powernow_k8_data *data,
 	res = transition_pstate(data, pstate);
 	freqs.new = find_khz_freq_from_pstate(data->powernow_table, pstate);
 
-	for_each_cpu_mask_nr(i, *(data->available_cores)) {
+	for_each_cpu(i, data->available_cores) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 	}
@@ -1235,21 +1236,47 @@ static int powernowk8_verify(struct cpufreq_policy *pol)
 	return cpufreq_frequency_table_verify(pol, data->powernow_table);
 }
 
-static const char ACPI_PSS_BIOS_BUG_MSG[] =
-	KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
-	KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
+struct init_on_cpu {
+	struct powernow_k8_data *data;
+	int rc;
+};
+
+static void __cpuinit powernowk8_cpu_init_on_cpu(void *_init_on_cpu)
+{
+	struct init_on_cpu *init_on_cpu = _init_on_cpu;
+
+	if (pending_bit_stuck()) {
+		printk(KERN_ERR PFX "failing init, change pending bit set\n");
+		init_on_cpu->rc = -ENODEV;
+		return;
+	}
+
+	if (query_current_values_with_pending_wait(init_on_cpu->data)) {
+		init_on_cpu->rc = -ENODEV;
+		return;
+	}
+
+	if (cpu_family == CPU_OPTERON)
+		fidvid_msr_init();
+
+	init_on_cpu->rc = 0;
+}
 
 /* per CPU init entry point to the driver */
 static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
+	static const char ACPI_PSS_BIOS_BUG_MSG[] =
+		KERN_ERR FW_BUG PFX "No compatible ACPI _PSS objects found.\n"
+		KERN_ERR FW_BUG PFX "Try again with latest BIOS.\n";
 	struct powernow_k8_data *data;
-	cpumask_t oldmask;
+	struct init_on_cpu init_on_cpu;
 	int rc;
 
 	if (!cpu_online(pol->cpu))
 		return -ENODEV;
 
-	if (!check_supported_cpu(pol->cpu))
+	smp_call_function_single(pol->cpu, check_supported_cpu, &rc, 1);
+	if (rc)
 		return -ENODEV;
 
 	data = kzalloc(sizeof(struct powernow_k8_data), GFP_KERNEL);
@@ -1289,27 +1316,12 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 		pol->cpuinfo.transition_latency = get_transition_latency(data);
 
 	/* only run on specific CPU from here on */
-	oldmask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(pol->cpu));
-
-	if (smp_processor_id() != pol->cpu) {
-		printk(KERN_ERR PFX "limiting to cpu %u failed\n", pol->cpu);
-		goto err_out_unmask;
-	}
-
-	if (pending_bit_stuck()) {
-		printk(KERN_ERR PFX "failing init, change pending bit set\n");
-		goto err_out_unmask;
-	}
-
-	if (query_current_values_with_pending_wait(data))
-		goto err_out_unmask;
-
-	if (cpu_family == CPU_OPTERON)
-		fidvid_msr_init();
-
-	/* run on any CPU again */
-	set_cpus_allowed_ptr(current, &oldmask);
+	init_on_cpu.data = data;
+	smp_call_function_single(data->cpu, powernowk8_cpu_init_on_cpu,
+				 &init_on_cpu, 1);
+	rc = init_on_cpu.rc;
+	if (rc != 0)
+		goto err_out_exit_acpi;
 
 	if (cpu_family == CPU_HW_PSTATE)
 		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
@@ -1346,8 +1358,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 
 	return 0;
 
-err_out_unmask:
-	set_cpus_allowed_ptr(current, &oldmask);
+err_out_exit_acpi:
 	powernow_k8_cpu_exit_acpi(data);
 
 err_out:
@@ -1372,28 +1383,25 @@ static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
 	return 0;
 }
 
+static void query_values_on_cpu(void *_err)
+{
+	int *err = _err;
+	struct powernow_k8_data *data = __get_cpu_var(powernow_data);
+
+	*err = query_current_values_with_pending_wait(data);
+}
+
 static unsigned int powernowk8_get(unsigned int cpu)
 {
-	struct powernow_k8_data *data;
-	cpumask_t oldmask = current->cpus_allowed;
+	struct powernow_k8_data *data = per_cpu(powernow_data, cpu);
 	unsigned int khz = 0;
-	unsigned int first;
-
-	first = cpumask_first(cpu_core_mask(cpu));
-	data = per_cpu(powernow_data, first);
+	int err;
 
 	if (!data)
 		return -EINVAL;
 
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	if (smp_processor_id() != cpu) {
-		printk(KERN_ERR PFX
-			"limiting to CPU %d failed in powernowk8_get\n", cpu);
-		set_cpus_allowed_ptr(current, &oldmask);
-		return 0;
-	}
-
-	if (query_current_values_with_pending_wait(data))
+	smp_call_function_single(cpu, query_values_on_cpu, &err, true);
+	if (err)
 		goto out;
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1404,7 +1412,6 @@ static unsigned int powernowk8_get(unsigned int cpu)
 
 
 out:
-	set_cpus_allowed_ptr(current, &oldmask);
 	return khz;
 }
 
@@ -1430,7 +1437,9 @@ static int __cpuinit powernowk8_init(void)
 	unsigned int i, supported_cpus = 0;
 
 	for_each_online_cpu(i) {
-		if (check_supported_cpu(i))
+		int rc;
+		smp_call_function_single(i, check_supported_cpu, &rc, 1);
+		if (rc == 0)
 			supported_cpus++;
 	}
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index 6c6698feade..c9c1190b5e1 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -223,14 +223,3 @@ static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned
 
 static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
 static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
-
-#ifdef CONFIG_SMP
-static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[])
-{
-}
-#else
-static inline void define_siblings(int cpu, cpumask_t cpu_sharedcore_mask[])
-{
-	cpu_set(0, cpu_sharedcore_mask[0]);
-}
-#endif
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index 55c831ed71c..8d672ef162c 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -323,14 +323,8 @@ static unsigned int get_cur_freq(unsigned int cpu)
 {
 	unsigned l, h;
 	unsigned clock_freq;
-	cpumask_t saved_mask;
 
-	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	if (smp_processor_id() != cpu)
-		return 0;
-
-	rdmsr(MSR_IA32_PERF_STATUS, l, h);
+	rdmsr_on_cpu(cpu, MSR_IA32_PERF_STATUS, &l, &h);
 	clock_freq = extract_clock(l, cpu, 0);
 
 	if (unlikely(clock_freq == 0)) {
@@ -340,11 +334,9 @@ static unsigned int get_cur_freq(unsigned int cpu)
 		 * P-state transition (like TM2). Get the last freq set 
 		 * in PERF_CTL.
 		 */
-		rdmsr(MSR_IA32_PERF_CTL, l, h);
+		rdmsr_on_cpu(cpu, MSR_IA32_PERF_CTL, &l, &h);
 		clock_freq = extract_clock(l, cpu, 1);
 	}
-
-	set_cpus_allowed_ptr(current, &saved_mask);
 	return clock_freq;
 }
 
@@ -467,15 +459,10 @@ static int centrino_target (struct cpufreq_policy *policy,
 	struct cpufreq_freqs	freqs;
 	int			retval = 0;
 	unsigned int		j, k, first_cpu, tmp;
-	cpumask_var_t saved_mask, covered_cpus;
+	cpumask_var_t covered_cpus;
 
-	if (unlikely(!alloc_cpumask_var(&saved_mask, GFP_KERNEL)))
-		return -ENOMEM;
-	if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))) {
-		free_cpumask_var(saved_mask);
+	if (unlikely(!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL)))
 		return -ENOMEM;
-	}
-	cpumask_copy(saved_mask, &current->cpus_allowed);
 
 	if (unlikely(per_cpu(centrino_model, cpu) == NULL)) {
 		retval = -ENODEV;
@@ -493,7 +480,7 @@ static int centrino_target (struct cpufreq_policy *policy,
 
 	first_cpu = 1;
 	for_each_cpu(j, policy->cpus) {
-		const struct cpumask *mask;
+		int good_cpu;
 
 		/* cpufreq holds the hotplug lock, so we are safe here */
 		if (!cpu_online(j))
@@ -504,32 +491,30 @@ static int centrino_target (struct cpufreq_policy *policy,
 		 * Make sure we are running on CPU that wants to change freq
 		 */
 		if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
-			mask = policy->cpus;
+			good_cpu = cpumask_any_and(policy->cpus,
+						   cpu_online_mask);
 		else
-			mask = cpumask_of(j);
+			good_cpu = j;
 
-		set_cpus_allowed_ptr(current, mask);
-		preempt_disable();
-		if (unlikely(!cpu_isset(smp_processor_id(), *mask))) {
+		if (good_cpu >= nr_cpu_ids) {
 			dprintk("couldn't limit to CPUs in this domain\n");
 			retval = -EAGAIN;
 			if (first_cpu) {
 				/* We haven't started the transition yet. */
-				goto migrate_end;
+				goto out;
 			}
-			preempt_enable();
 			break;
 		}
 
 		msr = per_cpu(centrino_model, cpu)->op_points[newstate].index;
 
 		if (first_cpu) {
-			rdmsr(MSR_IA32_PERF_CTL, oldmsr, h);
+			rdmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, &oldmsr, &h);
 			if (msr == (oldmsr & 0xffff)) {
 				dprintk("no change needed - msr was and needs "
 					"to be %x\n", oldmsr);
 				retval = 0;
-				goto migrate_end;
+				goto out;
 			}
 
 			freqs.old = extract_clock(oldmsr, cpu, 0);
@@ -553,14 +538,11 @@ static int centrino_target (struct cpufreq_policy *policy,
 			oldmsr |= msr;
 		}
 
-		wrmsr(MSR_IA32_PERF_CTL, oldmsr, h);
-		if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
-			preempt_enable();
+		wrmsr_on_cpu(good_cpu, MSR_IA32_PERF_CTL, oldmsr, h);
+		if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
 			break;
-		}
 
-		cpu_set(j, *covered_cpus);
-		preempt_enable();
+		cpumask_set_cpu(j, covered_cpus);
 	}
 
 	for_each_cpu(k, policy->cpus) {
@@ -578,10 +560,8 @@ static int centrino_target (struct cpufreq_policy *policy,
 		 * Best effort undo..
 		 */
 
-		for_each_cpu_mask_nr(j, *covered_cpus) {
-			set_cpus_allowed_ptr(current, &cpumask_of_cpu(j));
-			wrmsr(MSR_IA32_PERF_CTL, oldmsr, h);
-		}
+		for_each_cpu(j, covered_cpus)
+			wrmsr_on_cpu(j, MSR_IA32_PERF_CTL, oldmsr, h);
 
 		tmp = freqs.new;
 		freqs.new = freqs.old;
@@ -593,15 +573,9 @@ static int centrino_target (struct cpufreq_policy *policy,
 			cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 		}
 	}
-	set_cpus_allowed_ptr(current, saved_mask);
 	retval = 0;
-	goto out;
 
-migrate_end:
-	preempt_enable();
-	set_cpus_allowed_ptr(current, saved_mask);
 out:
-	free_cpumask_var(saved_mask);
 	free_cpumask_var(covered_cpus);
 	return retval;
 }
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 016c1a4fa3f..6911e91fb4f 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -89,7 +89,8 @@ static int speedstep_find_register(void)
  * speedstep_set_state - set the SpeedStep state
  * @state: new processor frequency state (SPEEDSTEP_LOW or SPEEDSTEP_HIGH)
  *
- *   Tries to change the SpeedStep state.
+ *   Tries to change the SpeedStep state.  Can be called from
+ *   smp_call_function_single.
  */
 static void speedstep_set_state(unsigned int state)
 {
@@ -143,6 +144,11 @@ static void speedstep_set_state(unsigned int state)
 	return;
 }
 
+/* Wrapper for smp_call_function_single. */
+static void _speedstep_set_state(void *_state)
+{
+	speedstep_set_state(*(unsigned int *)_state);
+}
 
 /**
  * speedstep_activate - activate SpeedStep control in the chipset
@@ -226,22 +232,28 @@ static unsigned int speedstep_detect_chipset(void)
 	return 0;
 }
 
-static unsigned int _speedstep_get(const struct cpumask *cpus)
-{
+struct get_freq_data {
 	unsigned int speed;
-	cpumask_t cpus_allowed;
-
-	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpus);
-	speed = speedstep_get_frequency(speedstep_processor);
-	set_cpus_allowed_ptr(current, &cpus_allowed);
-	dprintk("detected %u kHz as current frequency\n", speed);
-	return speed;
+	unsigned int processor;
+};
+
+static void get_freq_data(void *_data)
+{
+	struct get_freq_data *data = _data;
+
+	data->speed = speedstep_get_frequency(data->processor);
 }
 
 static unsigned int speedstep_get(unsigned int cpu)
 {
-	return _speedstep_get(cpumask_of(cpu));
+	struct get_freq_data data = { .processor = cpu };
+
+	/* You're supposed to ensure CPU is online. */
+	if (smp_call_function_single(cpu, get_freq_data, &data, 1) != 0)
+		BUG();
+
+	dprintk("detected %u kHz as current frequency\n", data.speed);
+	return data.speed;
 }
 
 /**
@@ -257,16 +269,16 @@ static int speedstep_target(struct cpufreq_policy *policy,
 			     unsigned int target_freq,
 			     unsigned int relation)
 {
-	unsigned int newstate = 0;
+	unsigned int newstate = 0, policy_cpu;
 	struct cpufreq_freqs freqs;
-	cpumask_t cpus_allowed;
 	int i;
 
 	if (cpufreq_frequency_table_target(policy, &speedstep_freqs[0],
 				target_freq, relation, &newstate))
 		return -EINVAL;
 
-	freqs.old = _speedstep_get(policy->cpus);
+	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
+	freqs.old = speedstep_get(policy_cpu);
 	freqs.new = speedstep_freqs[newstate].frequency;
 	freqs.cpu = policy->cpu;
 
@@ -276,20 +288,13 @@ static int speedstep_target(struct cpufreq_policy *policy,
 	if (freqs.old == freqs.new)
 		return 0;
 
-	cpus_allowed = current->cpus_allowed;
-
 	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
 		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 	}
 
-	/* switch to physical CPU where state is to be changed */
-	set_cpus_allowed_ptr(current, policy->cpus);
-
-	speedstep_set_state(newstate);
-
-	/* allow to be run on all CPUs */
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	smp_call_function_single(policy_cpu, _speedstep_set_state, &newstate,
+				 true);
 
 	for_each_cpu(i, policy->cpus) {
 		freqs.cpu = i;
@@ -312,33 +317,43 @@ static int speedstep_verify(struct cpufreq_policy *policy)
 	return cpufreq_frequency_table_verify(policy, &speedstep_freqs[0]);
 }
 
+struct get_freqs {
+	struct cpufreq_policy *policy;
+	int ret;
+};
+
+static void get_freqs_on_cpu(void *_get_freqs)
+{
+	struct get_freqs *get_freqs = _get_freqs;
+
+	get_freqs->ret =
+		speedstep_get_freqs(speedstep_processor,
+			    &speedstep_freqs[SPEEDSTEP_LOW].frequency,
+			    &speedstep_freqs[SPEEDSTEP_HIGH].frequency,
+			    &get_freqs->policy->cpuinfo.transition_latency,
+			    &speedstep_set_state);
+}
 
 static int speedstep_cpu_init(struct cpufreq_policy *policy)
 {
-	int result = 0;
-	unsigned int speed;
-	cpumask_t cpus_allowed;
+	int result;
+	unsigned int policy_cpu, speed;
+	struct get_freqs gf;
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
 	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
-
-	cpus_allowed = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, policy->cpus);
+	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 
 	/* detect low and high frequency and transition latency */
-	result = speedstep_get_freqs(speedstep_processor,
-				     &speedstep_freqs[SPEEDSTEP_LOW].frequency,
-				     &speedstep_freqs[SPEEDSTEP_HIGH].frequency,
-				     &policy->cpuinfo.transition_latency,
-				     &speedstep_set_state);
-	set_cpus_allowed_ptr(current, &cpus_allowed);
-	if (result)
-		return result;
+	gf.policy = policy;
+	smp_call_function_single(policy_cpu, get_freqs_on_cpu, &gf, 1);
+	if (gf.ret)
+		return gf.ret;
 
 	/* get current speed setting */
-	speed = _speedstep_get(policy->cpus);
+	speed = speedstep_get(policy_cpu);
 	if (!speed)
 		return -EIO;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
index 2e3c6862657..f4c290b8482 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-lib.c
@@ -226,6 +226,7 @@ static unsigned int pentium4_get_frequency(void)
 }
 
 
+/* Warning: may get called from smp_call_function_single. */
 unsigned int speedstep_get_frequency(unsigned int processor)
 {
 	switch (processor) {
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ae3180c506a..b0597ad02c9 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -632,17 +632,15 @@ static int time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 				void *data)
 {
 	struct cpufreq_freqs *freq = data;
-	unsigned long *lpj, dummy;
+	unsigned long *lpj;
 
 	if (cpu_has(&cpu_data(freq->cpu), X86_FEATURE_CONSTANT_TSC))
 		return 0;
 
-	lpj = &dummy;
-	if (!(freq->flags & CPUFREQ_CONST_LOOPS))
+	lpj = &boot_cpu_data.loops_per_jiffy;
 #ifdef CONFIG_SMP
+	if (!(freq->flags & CPUFREQ_CONST_LOOPS))
 		lpj = &cpu_data(freq->cpu).loops_per_jiffy;
-#else
-	lpj = &boot_cpu_data.loops_per_jiffy;
 #endif
 
 	if (!ref_freq) {
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index a85bef20a3b..0fb56db16d1 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -116,7 +116,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 	struct pci_bus *bus;
 	struct pci_dev *dev;
 	int idx;
-	struct resource *r, *pr;
+	struct resource *r;
 
 	/* Depth-First Search on bus tree */
 	list_for_each_entry(bus, bus_list, node) {
@@ -126,9 +126,8 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				r = &dev->resource[idx];
 				if (!r->flags)
 					continue;
-				pr = pci_find_parent_resource(dev, r);
-				if (!r->start || !pr ||
-				    request_resource(pr, r) < 0) {
+				if (!r->start ||
+				    pci_claim_resource(dev, idx) < 0) {
 					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/*
 					 * Something is wrong with the region.
@@ -149,7 +148,7 @@ static void __init pcibios_allocate_resources(int pass)
 	struct pci_dev *dev = NULL;
 	int idx, disabled;
 	u16 command;
-	struct resource *r, *pr;
+	struct resource *r;
 
 	for_each_pci_dev(dev) {
 		pci_read_config_word(dev, PCI_COMMAND, &command);
@@ -168,8 +167,7 @@ static void __init pcibios_allocate_resources(int pass)
 					(unsigned long long) r->start,
 					(unsigned long long) r->end,
 					r->flags, disabled, pass);
-				pr = pci_find_parent_resource(dev, r);
-				if (!pr || request_resource(pr, r) < 0) {
+				if (pci_claim_resource(dev, idx) < 0) {
 					dev_info(&dev->dev, "BAR %d: can't allocate resource\n", idx);
 					/* We'll assign a new address later */
 					r->end -= r->start;
@@ -197,7 +195,7 @@ static void __init pcibios_allocate_resources(int pass)
 static int __init pcibios_assign_resources(void)
 {
 	struct pci_dev *dev = NULL;
-	struct resource *r, *pr;
+	struct resource *r;
 
 	if (!(pci_probe & PCI_ASSIGN_ROMS)) {
 		/*
@@ -209,8 +207,7 @@ static int __init pcibios_assign_resources(void)
 			r = &dev->resource[PCI_ROM_RESOURCE];
 			if (!r->flags || !r->start)
 				continue;
-			pr = pci_find_parent_resource(dev, r);
-			if (!pr || request_resource(pr, r) < 0) {
+			if (pci_claim_resource(dev, PCI_ROM_RESOURCE) < 0) {
 				r->end -= r->start;
 				r->start = 0;
 			}
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 16a9020c8f1..88112b49f02 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -123,6 +123,7 @@ quiet_cmd_vdso = VDSO    $@
 		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^)
 
 VDSO_LDFLAGS = -fPIC -shared $(call ld-option, -Wl$(comma)--hash-style=sysv)
+GCOV_PROFILE := n
 
 #
 # Install the unstripped copy of vdso*.so listed in $(vdso-install-y).