Merge commit 'v2.6.27-rc1' into x86/core

Conflicts:

	include/asm-x86/dma-mapping.h
	include/asm-x86/namei.h
	include/asm-x86/uaccess.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

36 files changed, 718 insertions, 562 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 97e97ee9662..608a12ff483 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -22,6 +22,7 @@ config X86
 	select HAVE_IDE
 	select HAVE_OPROFILE
 	select HAVE_IOREMAP_PROT
+	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_KPROBES
 	select ARCH_WANT_OPTIONAL_GPIOLIB
 	select HAVE_KRETPROBES
@@ -29,6 +30,7 @@ config X86
 	select HAVE_FTRACE
 	select HAVE_KVM if ((X86_32 && !X86_VOYAGER && !X86_VISWS && !X86_NUMAQ) || X86_64)
 	select HAVE_ARCH_KGDB if !X86_VOYAGER
+	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 
 config ARCH_DEFCONFIG
@@ -1275,6 +1277,14 @@ config CRASH_DUMP
 	  (CONFIG_RELOCATABLE=y).
 	  For more details see Documentation/kdump/kdump.txt
 
+config KEXEC_JUMP
+	bool "kexec jump (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on KEXEC && HIBERNATION && X86_32
+	help
+	  Jump between original kernel and kexeced kernel and invoke
+	  code in physical address mode via KEXEC
+
 config PHYSICAL_START
 	hex "Physical address where the kernel is loaded" if (EMBEDDED || CRASH_DUMP)
 	default "0x1000000" if X86_NUMAQ
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 58cccb6483b..a0e1dbe67dc 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -441,12 +441,6 @@ beyond_if:
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 =
 	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
 	set_fs(USER_DS);
-	if (unlikely(current->ptrace & PT_PTRACED)) {
-		if (current->ptrace & PT_TRACE_EXEC)
-			ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP);
-		else
-			send_sig(SIGTRAP, current, 0);
-	}
 	return 0;
 }
 
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 9220cf46aa1..c2502eb9aa8 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -73,7 +73,6 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 	cpumask_t saved_mask;
-	cpumask_of_cpu_ptr(new_mask, cpu);
 	int retval;
 	unsigned int eax, ebx, ecx, edx;
 	unsigned int edx_part;
@@ -92,7 +91,7 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 
 	/* Make sure we are running on right CPU */
 	saved_mask = current->cpus_allowed;
-	retval = set_cpus_allowed_ptr(current, new_mask);
+	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (retval)
 		return -1;
 
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index 74697408576..22d7d050905 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -29,9 +29,6 @@
 
 #define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
 
-#define to_pages(addr, size) \
-	 (round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
-
 #define EXIT_LOOP_COUNT 10000000
 
 static DEFINE_RWLOCK(amd_iommu_devtable_lock);
@@ -185,7 +182,7 @@ static int iommu_flush_pages(struct amd_iommu *iommu, u16 domid,
 		u64 address, size_t size)
 {
 	int s = 0;
-	unsigned pages = to_pages(address, size);
+	unsigned pages = iommu_num_pages(address, size);
 
 	address &= PAGE_MASK;
 
@@ -557,8 +554,8 @@ static struct dma_ops_domain *dma_ops_domain_alloc(struct amd_iommu *iommu,
 	if (iommu->exclusion_start &&
 	    iommu->exclusion_start < dma_dom->aperture_size) {
 		unsigned long startpage = iommu->exclusion_start >> PAGE_SHIFT;
-		int pages = to_pages(iommu->exclusion_start,
-				iommu->exclusion_length);
+		int pages = iommu_num_pages(iommu->exclusion_start,
+					    iommu->exclusion_length);
 		dma_ops_reserve_addresses(dma_dom, startpage, pages);
 	}
 
@@ -767,7 +764,7 @@ static dma_addr_t __map_single(struct device *dev,
 	unsigned int pages;
 	int i;
 
-	pages = to_pages(paddr, size);
+	pages = iommu_num_pages(paddr, size);
 	paddr &= PAGE_MASK;
 
 	address = dma_ops_alloc_addresses(dev, dma_dom, pages);
@@ -802,7 +799,7 @@ static void __unmap_single(struct amd_iommu *iommu,
 	if ((dma_addr == 0) || (dma_addr + size > dma_dom->aperture_size))
 		return;
 
-	pages = to_pages(dma_addr, size);
+	pages = iommu_num_pages(dma_addr, size);
 	dma_addr &= PAGE_MASK;
 	start = dma_addr;
 
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index ff2fff56f0a..dd097b83583 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -200,12 +200,10 @@ static void drv_read(struct drv_cmd *cmd)
 static void drv_write(struct drv_cmd *cmd)
 {
 	cpumask_t saved_mask = current->cpus_allowed;
-	cpumask_of_cpu_ptr_declare(cpu_mask);
 	unsigned int i;
 
 	for_each_cpu_mask_nr(i, cmd->mask) {
-		cpumask_of_cpu_ptr_next(cpu_mask, i);
-		set_cpus_allowed_ptr(current, cpu_mask);
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
 		do_drv_write(cmd);
 	}
 
@@ -269,12 +267,11 @@ static unsigned int get_measured_perf(unsigned int cpu)
 	} aperf_cur, mperf_cur;
 
 	cpumask_t saved_mask;
-	cpumask_of_cpu_ptr(cpu_mask, cpu);
 	unsigned int perf_percent;
 	unsigned int retval;
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpu_mask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (get_cpu() != cpu) {
 		/* We were not able to run on requested processor */
 		put_cpu();
@@ -340,7 +337,6 @@ static unsigned int get_measured_perf(unsigned int cpu)
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
-	cpumask_of_cpu_ptr(cpu_mask, cpu);
 	struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
 	unsigned int freq;
 	unsigned int cached_freq;
@@ -353,7 +349,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 	}
 
 	cached_freq = data->freq_table[data->acpi_data->state].frequency;
-	freq = extract_freq(get_cur_val(cpu_mask), data);
+	freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
 	if (freq != cached_freq) {
 		/*
 		 * The dreaded BIOS frequency change behind our back.
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 53c7b693697..c45ca6d4dce 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -479,12 +479,11 @@ static int core_voltage_post_transition(struct powernow_k8_data *data, u32 reqvi
 static int check_supported_cpu(unsigned int cpu)
 {
 	cpumask_t oldmask;
-	cpumask_of_cpu_ptr(cpu_mask, cpu);
 	u32 eax, ebx, ecx, edx;
 	unsigned int rc = 0;
 
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpu_mask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 	if (smp_processor_id() != cpu) {
 		printk(KERN_ERR PFX "limiting to cpu %u failed\n", cpu);
@@ -1017,7 +1016,6 @@ static int transition_frequency_pstate(struct powernow_k8_data *data, unsigned i
 static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsigned relation)
 {
 	cpumask_t oldmask;
-	cpumask_of_cpu_ptr(cpu_mask, pol->cpu);
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 	u32 checkfid;
 	u32 checkvid;
@@ -1032,7 +1030,7 @@ static int powernowk8_target(struct cpufreq_policy *pol, unsigned targfreq, unsi
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, cpu_mask);
+	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);
@@ -1107,7 +1105,6 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data;
 	cpumask_t oldmask;
-	cpumask_of_cpu_ptr_declare(newmask);
 	int rc;
 
 	if (!cpu_online(pol->cpu))
@@ -1159,8 +1156,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 
 	/* only run on specific CPU from here on */
 	oldmask = current->cpus_allowed;
-	cpumask_of_cpu_ptr_next(newmask, pol->cpu);
-	set_cpus_allowed_ptr(current, newmask);
+	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);
@@ -1182,7 +1178,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	set_cpus_allowed_ptr(current, &oldmask);
 
 	if (cpu_family == CPU_HW_PSTATE)
-		pol->cpus = *newmask;
+		pol->cpus = cpumask_of_cpu(pol->cpu);
 	else
 		pol->cpus = per_cpu(cpu_core_map, pol->cpu);
 	data->available_cores = &(pol->cpus);
@@ -1248,7 +1244,6 @@ static unsigned int powernowk8_get (unsigned int cpu)
 {
 	struct powernow_k8_data *data;
 	cpumask_t oldmask = current->cpus_allowed;
-	cpumask_of_cpu_ptr(newmask, cpu);
 	unsigned int khz = 0;
 	unsigned int first;
 
@@ -1258,7 +1253,7 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (!data)
 		return -EINVAL;
 
-	set_cpus_allowed_ptr(current, newmask);
+	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);
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index ca2ac13b7af..15e13c01cc3 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -324,10 +324,9 @@ static unsigned int get_cur_freq(unsigned int cpu)
 	unsigned l, h;
 	unsigned clock_freq;
 	cpumask_t saved_mask;
-	cpumask_of_cpu_ptr(new_mask, cpu);
 
 	saved_mask = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, new_mask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (smp_processor_id() != cpu)
 		return 0;
 
@@ -585,15 +584,12 @@ static int centrino_target (struct cpufreq_policy *policy,
 		 * Best effort undo..
 		 */
 
-		if (!cpus_empty(*covered_cpus)) {
-			cpumask_of_cpu_ptr_declare(new_mask);
-
+		if (!cpus_empty(*covered_cpus))
 			for_each_cpu_mask_nr(j, *covered_cpus) {
-				cpumask_of_cpu_ptr_next(new_mask, j);
-				set_cpus_allowed_ptr(current, new_mask);
+				set_cpus_allowed_ptr(current,
+						     &cpumask_of_cpu(j));
 				wrmsr(MSR_IA32_PERF_CTL, oldmsr, h);
 			}
-		}
 
 		tmp = freqs.new;
 		freqs.new = freqs.old;
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 2f3728dc24f..191f7263c61 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -244,8 +244,7 @@ static unsigned int _speedstep_get(const cpumask_t *cpus)
 
 static unsigned int speedstep_get(unsigned int cpu)
 {
-	cpumask_of_cpu_ptr(newmask, cpu);
-	return _speedstep_get(newmask);
+	return _speedstep_get(&cpumask_of_cpu(cpu));
 }
 
 /**
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 650d40f7912..6b0a10b002f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -516,7 +516,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	unsigned long		j;
 	int			retval;
 	cpumask_t		oldmask;
-	cpumask_of_cpu_ptr(newmask, cpu);
 
 	if (num_cache_leaves == 0)
 		return -ENOENT;
@@ -527,7 +526,7 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 		return -ENOMEM;
 
 	oldmask = current->cpus_allowed;
-	retval = set_cpus_allowed_ptr(current, newmask);
+	retval = set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	if (retval)
 		goto out;
 
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index f67e93441ca..a7010c3a377 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -456,9 +456,6 @@ is386:	movl $2,%ecx		# set MP
 1:
 #endif /* CONFIG_SMP */
 	jmp *(initial_code)
-.align 4
-ENTRY(initial_code)
-	.long i386_start_kernel
 
 /*
  * We depend on ET to be correct. This checks for 287/387.
@@ -601,6 +598,11 @@ ignore_int:
 #endif
 	iret
 
+.section .cpuinit.data,"wa"
+.align 4
+ENTRY(initial_code)
+	.long i386_start_kernel
+
 .section .text
 /*
  * Real beginning of normal "text" segment
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 3fee2aa50f3..b68e21f06f4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -62,12 +62,10 @@ static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
 
 	if (reload) {
 #ifdef CONFIG_SMP
-		cpumask_of_cpu_ptr_declare(mask);
-
 		preempt_disable();
 		load_LDT(pc);
-		cpumask_of_cpu_ptr_next(mask, smp_processor_id());
-		if (!cpus_equal(current->mm->cpu_vm_mask, *mask))
+		if (!cpus_equal(current->mm->cpu_vm_mask,
+				cpumask_of_cpu(smp_processor_id())))
 			smp_call_function(flush_ldt, current->mm, 1);
 		preempt_enable();
 #else
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 8864230d55a..9fe478d9840 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -22,6 +22,7 @@
 #include <asm/cpufeature.h>
 #include <asm/desc.h>
 #include <asm/system.h>
+#include <asm/cacheflush.h>
 
 #define PAGE_ALIGNED __attribute__ ((__aligned__(PAGE_SIZE)))
 static u32 kexec_pgd[1024] PAGE_ALIGNED;
@@ -85,10 +86,12 @@ static void load_segments(void)
  * reboot code buffer to allow us to avoid allocations
  * later.
  *
- * Currently nothing.
+ * Make control page executable.
  */
 int machine_kexec_prepare(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_x(image->control_code_page, 1);
 	return 0;
 }
 
@@ -98,27 +101,48 @@ int machine_kexec_prepare(struct kimage *image)
  */
 void machine_kexec_cleanup(struct kimage *image)
 {
+	if (nx_enabled)
+		set_pages_nx(image->control_code_page, 1);
 }
 
 /*
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
+	asmlinkage unsigned long
+		(*relocate_kernel_ptr)(unsigned long indirection_page,
+				       unsigned long control_page,
+				       unsigned long start_address,
+				       unsigned int has_pae,
+				       unsigned int preserve_context);
 
 	tracer_disable();
 
 	/* Interrupts aren't acceptable while we reboot */
 	local_irq_disable();
 
+	if (image->preserve_context) {
+#ifdef CONFIG_X86_IO_APIC
+		/* We need to put APICs in legacy mode so that we can
+		 * get timer interrupts in second kernel. kexec/kdump
+		 * paths already have calls to disable_IO_APIC() in
+		 * one form or other. kexec jump path also need
+		 * one.
+		 */
+		disable_IO_APIC();
+#endif
+	}
+
 	control_page = page_address(image->control_code_page);
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	memcpy(control_page, relocate_kernel, PAGE_SIZE/2);
 
+	relocate_kernel_ptr = control_page;
 	page_list[PA_CONTROL_PAGE] = __pa(control_page);
-	page_list[VA_CONTROL_PAGE] = (unsigned long)relocate_kernel;
+	page_list[VA_CONTROL_PAGE] = (unsigned long)control_page;
 	page_list[PA_PGD] = __pa(kexec_pgd);
 	page_list[VA_PGD] = (unsigned long)kexec_pgd;
 #ifdef CONFIG_X86_PAE
@@ -131,6 +155,7 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	page_list[VA_PTE_0] = (unsigned long)kexec_pte0;
 	page_list[PA_PTE_1] = __pa(kexec_pte1);
 	page_list[VA_PTE_1] = (unsigned long)kexec_pte1;
+	page_list[PA_SWAP_PAGE] = (page_to_pfn(image->swap_page) << PAGE_SHIFT);
 
 	/* The segment registers are funny things, they have both a
 	 * visible and an invisible part.  Whenever the visible part is
@@ -149,8 +174,10 @@ NORET_TYPE void machine_kexec(struct kimage *image)
 	set_idt(phys_to_virt(0),0);
 
 	/* now call it */
-	relocate_kernel((unsigned long)image->head, (unsigned long)page_list,
-			image->start, cpu_has_pae);
+	image->start = relocate_kernel_ptr((unsigned long)image->head,
+					   (unsigned long)page_list,
+					   image->start, cpu_has_pae,
+					   image->preserve_context);
 }
 
 void arch_crash_save_vmcoreinfo(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 9dd9262693a..c43caa3a91f 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -181,7 +181,7 @@ void machine_kexec_cleanup(struct kimage *image)
  * Do not allocate memory (or fail in any way) in machine_kexec().
  * We are past the point of no return, committed to rebooting now.
  */
-NORET_TYPE void machine_kexec(struct kimage *image)
+void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list[PAGES_NR];
 	void *control_page;
diff --git a/arch/x86/kernel/microcode.c b/arch/x86/kernel/microcode.c
index 6994c751590..652fa5c38eb 100644
--- a/arch/x86/kernel/microcode.c
+++ b/arch/x86/kernel/microcode.c
@@ -388,7 +388,6 @@ static int do_microcode_update (void)
 	void *new_mc = NULL;
 	int cpu;
 	cpumask_t old;
-	cpumask_of_cpu_ptr_declare(newmask);
 
 	old = current->cpus_allowed;
 
@@ -405,8 +404,7 @@ static int do_microcode_update (void)
 
 			if (!uci->valid)
 				continue;
-			cpumask_of_cpu_ptr_next(newmask, cpu);
-			set_cpus_allowed_ptr(current, newmask);
+			set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 			error = get_maching_microcode(new_mc, cpu);
 			if (error < 0)
 				goto out;
@@ -576,7 +574,6 @@ static int apply_microcode_check_cpu(int cpu)
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	cpumask_t old;
-	cpumask_of_cpu_ptr(newmask, cpu);
 	unsigned int val[2];
 	int err = 0;
 
@@ -585,7 +582,7 @@ static int apply_microcode_check_cpu(int cpu)
 		return 0;
 
 	old = current->cpus_allowed;
-	set_cpus_allowed_ptr(current, newmask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 	/* Check if the microcode we have in memory matches the CPU */
 	if (c->x86_vendor != X86_VENDOR_INTEL || c->x86 < 6 ||
@@ -623,12 +620,11 @@ static int apply_microcode_check_cpu(int cpu)
 static void microcode_init_cpu(int cpu, int resume)
 {
 	cpumask_t old;
-	cpumask_of_cpu_ptr(newmask, cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 	old = current->cpus_allowed;
 
-	set_cpus_allowed_ptr(current, newmask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 	mutex_lock(&microcode_mutex);
 	collect_cpu_info(cpu);
 	if (uci->valid && system_state == SYSTEM_RUNNING && !resume)
@@ -661,13 +657,10 @@ static ssize_t reload_store(struct sys_device *dev,
 	if (end == buf)
 		return -EINVAL;
 	if (val == 1) {
-		cpumask_t old;
-		cpumask_of_cpu_ptr(newmask, cpu);
-
-		old = current->cpus_allowed;
+		cpumask_t old = current->cpus_allowed;
 
 		get_online_cpus();
-		set_cpus_allowed_ptr(current, newmask);
+		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
 
 		mutex_lock(&microcode_mutex);
 		if (uci->valid)
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 19e7fc7c2c4..b67a4b1d4ea 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -37,6 +37,7 @@
 #include <linux/delay.h>
 #include <linux/scatterlist.h>
 #include <linux/iommu-helper.h>
+
 #include <asm/iommu.h>
 #include <asm/calgary.h>
 #include <asm/tce.h>
@@ -413,22 +414,6 @@ static void calgary_unmap_sg(struct device *dev,
 	}
 }
 
-static int calgary_nontranslate_map_sg(struct device* dev,
-	struct scatterlist *sg, int nelems, int direction)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i) {
-		struct page *p = sg_page(s);
-
-		BUG_ON(!p);
-		s->dma_address = virt_to_bus(sg_virt(s));
-		s->dma_length = s->length;
-	}
-	return nelems;
-}
-
 static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	int nelems, int direction)
 {
@@ -439,9 +424,6 @@ static int calgary_map_sg(struct device *dev, struct scatterlist *sg,
 	unsigned long entry;
 	int i;
 
-	if (!translation_enabled(tbl))
-		return calgary_nontranslate_map_sg(dev, sg, nelems, direction);
-
 	for_each_sg(sg, s, nelems, i) {
 		BUG_ON(!sg_page(s));
 
@@ -477,7 +459,6 @@ error:
 static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	size_t size, int direction)
 {
-	dma_addr_t dma_handle = bad_dma_address;
 	void *vaddr = phys_to_virt(paddr);
 	unsigned long uaddr;
 	unsigned int npages;
@@ -486,12 +467,7 @@ static dma_addr_t calgary_map_single(struct device *dev, phys_addr_t paddr,
 	uaddr = (unsigned long)vaddr;
 	npages = num_dma_pages(uaddr, size);
 
-	if (translation_enabled(tbl))
-		dma_handle = iommu_alloc(dev, tbl, vaddr, npages, direction);
-	else
-		dma_handle = virt_to_bus(vaddr);
-
-	return dma_handle;
+	return iommu_alloc(dev, tbl, vaddr, npages, direction);
 }
 
 static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
@@ -500,9 +476,6 @@ static void calgary_unmap_single(struct device *dev, dma_addr_t dma_handle,
 	struct iommu_table *tbl = find_iommu_table(dev);
 	unsigned int npages;
 
-	if (!translation_enabled(tbl))
-		return;
-
 	npages = num_dma_pages(dma_handle, size);
 	iommu_free(tbl, dma_handle, npages);
 }
@@ -525,18 +498,12 @@ static void* calgary_alloc_coherent(struct device *dev, size_t size,
 		goto error;
 	memset(ret, 0, size);
 
-	if (translation_enabled(tbl)) {
-		/* set up tces to cover the allocated range */
-		mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
-		if (mapping == bad_dma_address)
-			goto free;
-
-		*dma_handle = mapping;
-	} else /* non translated slot */
-		*dma_handle = virt_to_bus(ret);
-
+	/* set up tces to cover the allocated range */
+	mapping = iommu_alloc(dev, tbl, ret, npages, DMA_BIDIRECTIONAL);
+	if (mapping == bad_dma_address)
+		goto free;
+	*dma_handle = mapping;
 	return ret;
-
 free:
 	free_pages((unsigned long)ret, get_order(size));
 	ret = NULL;
@@ -544,7 +511,7 @@ error:
 	return ret;
 }
 
-static const struct dma_mapping_ops calgary_dma_ops = {
+static struct dma_mapping_ops calgary_dma_ops = {
 	.alloc_coherent = calgary_alloc_coherent,
 	.map_single = calgary_map_single,
 	.unmap_single = calgary_unmap_single,
@@ -1241,6 +1208,16 @@ static int __init calgary_init(void)
 			goto error;
 	} while (1);
 
+	dev = NULL;
+	for_each_pci_dev(dev) {
+		struct iommu_table *tbl;
+
+		tbl = find_iommu_table(&dev->dev);
+
+		if (translation_enabled(tbl))
+			dev->dev.archdata.dma_ops = &calgary_dma_ops;
+	}
+
 	return ret;
 
 error:
@@ -1262,6 +1239,7 @@ error:
 		calgary_disable_translation(dev);
 		calgary_free_bus(dev);
 		pci_dev_put(dev); /* Undo calgary_init_one()'s pci_dev_get() */
+		dev->dev.archdata.dma_ops = NULL;
 	} while (1);
 
 	return ret;
@@ -1503,6 +1481,10 @@ void __init detect_calgary(void)
 		printk(KERN_INFO "PCI-DMA: Calgary TCE table spec is %d, "
 		       "CONFIG_IOMMU_DEBUG is %s.\n", specified_table_size,
 		       debugging ? "enabled" : "disabled");
+
+		/* swiotlb for devices that aren't behind the Calgary. */
+		if (max_pfn > MAX_DMA32_PFN)
+			swiotlb = 1;
 	}
 	return;
 
@@ -1519,7 +1501,7 @@ int __init calgary_iommu_init(void)
 {
 	int ret;
 
-	if (no_iommu || swiotlb)
+	if (no_iommu || (swiotlb && !calgary_detected))
 		return -ENODEV;
 
 	if (!calgary_detected)
@@ -1532,15 +1514,14 @@ int __init calgary_iommu_init(void)
 	if (ret) {
 		printk(KERN_ERR "PCI-DMA: Calgary init failed %d, "
 		       "falling back to no_iommu\n", ret);
-		if (max_pfn > MAX_DMA32_PFN)
-			printk(KERN_ERR "WARNING more than 4GB of memory, "
-					"32bit PCI may malfunction.\n");
 		return ret;
 	}
 
 	force_iommu = 1;
 	bad_dma_address = 0x0;
-	dma_ops = &calgary_dma_ops;
+	/* dma_ops is set to swiotlb or nommu */
+	if (!dma_ops)
+		dma_ops = &nommu_dma_ops;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index cbecb05551b..8dbffb846de 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,7 +11,7 @@
 
 static int forbid_dac __read_mostly;
 
-const struct dma_mapping_ops *dma_ops;
+struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 static int iommu_sac_force __read_mostly;
@@ -192,126 +192,10 @@ static __init int iommu_setup(char *p)
 }
 early_param("iommu", iommu_setup);
 
-#ifdef CONFIG_X86_32
-int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
-				dma_addr_t device_addr, size_t size, int flags)
-{
-	void __iomem *mem_base = NULL;
-	int pages = size >> PAGE_SHIFT;
-	int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
-
-	if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
-		goto out;
-	if (!size)
-		goto out;
-	if (dev->dma_mem)
-		goto out;
-
-	/* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
-
-	mem_base = ioremap(bus_addr, size);
-	if (!mem_base)
-		goto out;
-
-	dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
-	if (!dev->dma_mem)
-		goto out;
-	dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
-	if (!dev->dma_mem->bitmap)
-		goto free1_out;
-
-	dev->dma_mem->virt_base = mem_base;
-	dev->dma_mem->device_base = device_addr;
-	dev->dma_mem->size = pages;
-	dev->dma_mem->flags = flags;
-
-	if (flags & DMA_MEMORY_MAP)
-		return DMA_MEMORY_MAP;
-
-	return DMA_MEMORY_IO;
-
- free1_out:
-	kfree(dev->dma_mem);
- out:
-	if (mem_base)
-		iounmap(mem_base);
-	return 0;
-}
-EXPORT_SYMBOL(dma_declare_coherent_memory);
-
-void dma_release_declared_memory(struct device *dev)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-
-	if (!mem)
-		return;
-	dev->dma_mem = NULL;
-	iounmap(mem->virt_base);
-	kfree(mem->bitmap);
-	kfree(mem);
-}
-EXPORT_SYMBOL(dma_release_declared_memory);
-
-void *dma_mark_declared_memory_occupied(struct device *dev,
-					dma_addr_t device_addr, size_t size)
-{
-	struct dma_coherent_mem *mem = dev->dma_mem;
-	int pos, err;
-	int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1);
-
-	pages >>= PAGE_SHIFT;
-
-	if (!mem)
-		return ERR_PTR(-EINVAL);
-
-	pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
-	err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
-	if (err != 0)
-		return ERR_PTR(err);
-	return mem->virt_base + (pos << PAGE_SHIFT);
-}
-EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
-
-static int dma_alloc_from_coherent_mem(struct device *dev, ssize_t size,
-				       dma_addr_t *dma_handle, void **ret)
-{
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
-	int order = get_order(size);
-
-	if (mem) {
-		int page = bitmap_find_free_region(mem->bitmap, mem->size,
-						     order);
-		if (page >= 0) {
-			*dma_handle = mem->device_base + (page << PAGE_SHIFT);
-			*ret = mem->virt_base + (page << PAGE_SHIFT);
-			memset(*ret, 0, size);
-		}
-		if (mem->flags & DMA_MEMORY_EXCLUSIVE)
-			*ret = NULL;
-	}
-	return (mem != NULL);
-}
-
-static int dma_release_coherent(struct device *dev, int order, void *vaddr)
-{
-	struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
-
-	if (mem && vaddr >= mem->virt_base && vaddr <
-		   (mem->virt_base + (mem->size << PAGE_SHIFT))) {
-		int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
-
-		bitmap_release_region(mem->bitmap, page, order);
-		return 1;
-	}
-	return 0;
-}
-#else
-#define dma_alloc_from_coherent_mem(dev, size, handle, ret) (0)
-#define dma_release_coherent(dev, order, vaddr) (0)
-#endif /* CONFIG_X86_32 */
-
 int dma_supported(struct device *dev, u64 mask)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
 #ifdef CONFIG_PCI
 	if (mask > 0xffffffff && forbid_dac > 0) {
 		dev_info(dev, "PCI: Disallowing DAC for device\n");
@@ -319,8 +203,8 @@ int dma_supported(struct device *dev, u64 mask)
 	}
 #endif
 
-	if (dma_ops->dma_supported)
-		return dma_ops->dma_supported(dev, mask);
+	if (ops->dma_supported)
+		return ops->dma_supported(dev, mask);
 
 	/* Copied from i386. Doesn't make much sense, because it will
 	   only work for pci_alloc_coherent.
@@ -367,6 +251,7 @@ void *
 dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		   gfp_t gfp)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
 	void *memory = NULL;
 	struct page *page;
 	unsigned long dma_mask = 0;
@@ -376,7 +261,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	/* ignore region specifiers */
 	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
 
-	if (dma_alloc_from_coherent_mem(dev, size, dma_handle, &memory))
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
 		return memory;
 
 	if (!dev) {
@@ -435,8 +320,8 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 			/* Let low level make its own zone decisions */
 			gfp &= ~(GFP_DMA32|GFP_DMA);
 
-			if (dma_ops->alloc_coherent)
-				return dma_ops->alloc_coherent(dev, size,
+			if (ops->alloc_coherent)
+				return ops->alloc_coherent(dev, size,
 							   dma_handle, gfp);
 			return NULL;
 		}
@@ -448,14 +333,14 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		}
 	}
 
-	if (dma_ops->alloc_coherent) {
+	if (ops->alloc_coherent) {
 		free_pages((unsigned long)memory, get_order(size));
 		gfp &= ~(GFP_DMA|GFP_DMA32);
-		return dma_ops->alloc_coherent(dev, size, dma_handle, gfp);
+		return ops->alloc_coherent(dev, size, dma_handle, gfp);
 	}
 
-	if (dma_ops->map_simple) {
-		*dma_handle = dma_ops->map_simple(dev, virt_to_phys(memory),
+	if (ops->map_simple) {
+		*dma_handle = ops->map_simple(dev, virt_to_phys(memory),
 					      size,
 					      PCI_DMA_BIDIRECTIONAL);
 		if (*dma_handle != bad_dma_address)
@@ -477,12 +362,14 @@ EXPORT_SYMBOL(dma_alloc_coherent);
 void dma_free_coherent(struct device *dev, size_t size,
 			 void *vaddr, dma_addr_t bus)
 {
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
 	int order = get_order(size);
 	WARN_ON(irqs_disabled());	/* for portability */
-	if (dma_release_coherent(dev, order, vaddr))
+	if (dma_release_from_coherent(dev, order, vaddr))
 		return;
-	if (dma_ops->unmap_single)
-		dma_ops->unmap_single(dev, bus, size, 0);
+	if (ops->unmap_single)
+		ops->unmap_single(dev, bus, size, 0);
 	free_pages((unsigned long)vaddr, order);
 }
 EXPORT_SYMBOL(dma_free_coherent);
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index df5f142657d..49285f8fd4d 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -67,9 +67,6 @@ static u32 gart_unmapped_entry;
 	(((x) & 0xfffff000) | (((x) >> 32) << 4) | GPTE_VALID | GPTE_COHERENT)
 #define GPTE_DECODE(x) (((x) & 0xfffff000) | (((u64)(x) & 0xff0) << 28))
 
-#define to_pages(addr, size) \
-	(round_up(((addr) & ~PAGE_MASK) + (size), PAGE_SIZE) >> PAGE_SHIFT)
-
 #define EMERGENCY_PAGES 32 /* = 128KB */
 
 #ifdef CONFIG_AGP
@@ -241,7 +238,7 @@ nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 static dma_addr_t dma_map_area(struct device *dev, dma_addr_t phys_mem,
 				size_t size, int dir)
 {
-	unsigned long npages = to_pages(phys_mem, size);
+	unsigned long npages = iommu_num_pages(phys_mem, size);
 	unsigned long iommu_page = alloc_iommu(dev, npages);
 	int i;
 
@@ -304,7 +301,7 @@ static void gart_unmap_single(struct device *dev, dma_addr_t dma_addr,
 		return;
 
 	iommu_page = (dma_addr - iommu_bus_base)>>PAGE_SHIFT;
-	npages = to_pages(dma_addr, size);
+	npages = iommu_num_pages(dma_addr, size);
 	for (i = 0; i < npages; i++) {
 		iommu_gatt_base[iommu_page + i] = gart_unmapped_entry;
 		CLEAR_LEAK(iommu_page + i);
@@ -387,7 +384,7 @@ static int __dma_map_cont(struct device *dev, struct scatterlist *start,
 		}
 
 		addr = phys_addr;
-		pages = to_pages(s->offset, s->length);
+		pages = iommu_num_pages(s->offset, s->length);
 		while (pages--) {
 			iommu_gatt_base[iommu_page] = GPTE_ENCODE(addr);
 			SET_LEAK(iommu_page);
@@ -470,7 +467,7 @@ gart_map_sg(struct device *dev, struct scatterlist *sg, int nents, int dir)
 
 		seg_size += s->length;
 		need = nextneed;
-		pages += to_pages(s->offset, s->length);
+		pages += iommu_num_pages(s->offset, s->length);
 		ps = s;
 	}
 	if (dma_map_cont(dev, start_sg, i - start, sgmap, pages, need) < 0)
@@ -692,8 +689,7 @@ static __init int init_k8_gatt(struct agp_kern_info *info)
 
 extern int agp_amd64_init(void);
 
-static const struct dma_mapping_ops gart_dma_ops = {
-	.mapping_error			= NULL,
+static struct dma_mapping_ops gart_dma_ops = {
 	.map_single			= gart_map_single,
 	.map_simple			= gart_map_simple,
 	.unmap_single			= gart_unmap_single,
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 792b9179eff..3f91f71cdc3 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -72,21 +72,9 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 	return nents;
 }
 
-/* Make sure we keep the same behaviour */
-static int nommu_mapping_error(dma_addr_t dma_addr)
-{
-#ifdef CONFIG_X86_32
-	return 0;
-#else
-	return (dma_addr == bad_dma_address);
-#endif
-}
-
-
-const struct dma_mapping_ops nommu_dma_ops = {
+struct dma_mapping_ops nommu_dma_ops = {
 	.map_single = nommu_map_single,
 	.map_sg = nommu_map_sg,
-	.mapping_error = nommu_mapping_error,
 	.is_phys = 1,
 };
 
diff --git a/arch/x86/kernel/pci-swiotlb_64.c b/arch/x86/kernel/pci-swiotlb_64.c
index 20df839b9c2..c4ce0332759 100644
--- a/arch/x86/kernel/pci-swiotlb_64.c
+++ b/arch/x86/kernel/pci-swiotlb_64.c
@@ -18,7 +18,7 @@ swiotlb_map_single_phys(struct device *hwdev, phys_addr_t paddr, size_t size,
 	return swiotlb_map_single(hwdev, phys_to_virt(paddr), size, direction);
 }
 
-const struct dma_mapping_ops swiotlb_dma_ops = {
+struct dma_mapping_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
 	.alloc_coherent = swiotlb_alloc_coherent,
 	.free_coherent = swiotlb_free_coherent,
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 06a9f643817..724adfc63cb 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -414,25 +414,20 @@ void native_machine_shutdown(void)
 
 	/* The boot cpu is always logical cpu 0 */
 	int reboot_cpu_id = 0;
-	cpumask_of_cpu_ptr(newmask, reboot_cpu_id);
 
 #ifdef CONFIG_X86_32
 	/* See if there has been given a command line override */
 	if ((reboot_cpu != -1) && (reboot_cpu < NR_CPUS) &&
-		cpu_online(reboot_cpu)) {
+		cpu_online(reboot_cpu))
 		reboot_cpu_id = reboot_cpu;
-		cpumask_of_cpu_ptr_next(newmask, reboot_cpu_id);
-	}
 #endif
 
 	/* Make certain the cpu I'm about to reboot on is online */
-	if (!cpu_online(reboot_cpu_id)) {
+	if (!cpu_online(reboot_cpu_id))
 		reboot_cpu_id = smp_processor_id();
-		cpumask_of_cpu_ptr_next(newmask, reboot_cpu_id);
-	}
 
 	/* Make certain I only run on the appropriate processor */
-	set_cpus_allowed_ptr(current, newmask);
+	set_cpus_allowed_ptr(current, &cpumask_of_cpu(reboot_cpu_id));
 
 	/* O.K Now that I'm on the appropriate processor,
 	 * stop all of the others.
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index c30fe25d470..703310a9902 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -20,11 +20,44 @@
 #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define PAE_PGD_ATTR (_PAGE_PRESENT)
 
+/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are
+ * used to save some data for jumping back
+ */
+#define DATA(offset)		(PAGE_SIZE/2+(offset))
+
+/* Minimal CPU state */
+#define ESP			DATA(0x0)
+#define CR0			DATA(0x4)
+#define CR3			DATA(0x8)
+#define CR4			DATA(0xc)
+
+/* other data */
+#define CP_VA_CONTROL_PAGE	DATA(0x10)
+#define CP_PA_PGD		DATA(0x14)
+#define CP_PA_SWAP_PAGE		DATA(0x18)
+#define CP_PA_BACKUP_PAGES_MAP	DATA(0x1c)
+
 	.text
 	.align PAGE_SIZE
 	.globl relocate_kernel
 relocate_kernel:
-	movl	8(%esp), %ebp /* list of pages */
+	/* Save the CPU context, used for jumping back */
+
+	pushl	%ebx
+	pushl	%esi
+	pushl	%edi
+	pushl	%ebp
+	pushf
+
+	movl	20+8(%esp), %ebp /* list of pages */
+	movl	PTR(VA_CONTROL_PAGE)(%ebp), %edi
+	movl	%esp, ESP(%edi)
+	movl	%cr0, %eax
+	movl	%eax, CR0(%edi)
+	movl	%cr3, %eax
+	movl	%eax, CR3(%edi)
+	movl	%cr4, %eax
+	movl	%eax, CR4(%edi)
 
 #ifdef CONFIG_X86_PAE
 	/* map the control page at its virtual address */
@@ -138,15 +171,25 @@ relocate_kernel:
 
 relocate_new_kernel:
 	/* read the arguments and say goodbye to the stack */
-	movl  4(%esp), %ebx /* page_list */
-	movl  8(%esp), %ebp /* list of pages */
-	movl  12(%esp), %edx /* start address */
-	movl  16(%esp), %ecx /* cpu_has_pae */
+	movl  20+4(%esp), %ebx /* page_list */
+	movl  20+8(%esp), %ebp /* list of pages */
+	movl  20+12(%esp), %edx /* start address */
+	movl  20+16(%esp), %ecx /* cpu_has_pae */
+	movl  20+20(%esp), %esi /* preserve_context */
 
 	/* zero out flags, and disable interrupts */
 	pushl $0
 	popfl
 
+	/* save some information for jumping back */
+	movl	PTR(VA_CONTROL_PAGE)(%ebp), %edi
+	movl	%edi, CP_VA_CONTROL_PAGE(%edi)
+	movl	PTR(PA_PGD)(%ebp), %eax
+	movl	%eax, CP_PA_PGD(%edi)
+	movl	PTR(PA_SWAP_PAGE)(%ebp), %eax
+	movl	%eax, CP_PA_SWAP_PAGE(%edi)
+	movl	%ebx, CP_PA_BACKUP_PAGES_MAP(%edi)
+
 	/* get physical address of control page now */
 	/* this is impossible after page table switch */
 	movl	PTR(PA_CONTROL_PAGE)(%ebp), %edi
@@ -197,8 +240,90 @@ identity_mapped:
 	xorl	%eax, %eax
 	movl	%eax, %cr3
 
+	movl	CP_PA_SWAP_PAGE(%edi), %eax
+	pushl	%eax
+	pushl	%ebx
+	call	swap_pages
+	addl	$8, %esp
+
+	/* To be certain of avoiding problems with self-modifying code
+	 * I need to execute a serializing instruction here.
+	 * So I flush the TLB, it's handy, and not processor dependent.
+	 */
+	xorl	%eax, %eax
+	movl	%eax, %cr3
+
+	/* set all of the registers to known values */
+	/* leave %esp alone */
+
+	testl	%esi, %esi
+	jnz 1f
+	xorl	%edi, %edi
+	xorl	%eax, %eax
+	xorl	%ebx, %ebx
+	xorl    %ecx, %ecx
+	xorl    %edx, %edx
+	xorl    %esi, %esi
+	xorl    %ebp, %ebp
+	ret
+1:
+	popl	%edx
+	movl	CP_PA_SWAP_PAGE(%edi), %esp
+	addl	$PAGE_SIZE, %esp
+2:
+	call	*%edx
+
+	/* get the re-entry point of the peer system */
+	movl	0(%esp), %ebp
+	call	1f
+1:
+	popl	%ebx
+	subl	$(1b - relocate_kernel), %ebx
+	movl	CP_VA_CONTROL_PAGE(%ebx), %edi
+	lea	PAGE_SIZE(%ebx), %esp
+	movl	CP_PA_SWAP_PAGE(%ebx), %eax
+	movl	CP_PA_BACKUP_PAGES_MAP(%ebx), %edx
+	pushl	%eax
+	pushl	%edx
+	call	swap_pages
+	addl	$8, %esp
+	movl	CP_PA_PGD(%ebx), %eax
+	movl	%eax, %cr3
+	movl	%cr0, %eax
+	orl	$(1<<31), %eax
+	movl	%eax, %cr0
+	lea	PAGE_SIZE(%edi), %esp
+	movl	%edi, %eax
+	addl	$(virtual_mapped - relocate_kernel), %eax
+	pushl	%eax
+	ret
+
+virtual_mapped:
+	movl	CR4(%edi), %eax
+	movl	%eax, %cr4
+	movl	CR3(%edi), %eax
+	movl	%eax, %cr3
+	movl	CR0(%edi), %eax
+	movl	%eax, %cr0
+	movl	ESP(%edi), %esp
+	movl	%ebp, %eax
+
+	popf
+	popl	%ebp
+	popl	%edi
+	popl	%esi
+	popl	%ebx
+	ret
+
 	/* Do the copies */
-	movl	%ebx, %ecx
+swap_pages:
+	movl	8(%esp), %edx
+	movl	4(%esp), %ecx
+	pushl	%ebp
+	pushl	%ebx
+	pushl	%edi
+	pushl	%esi
+	movl	%ecx, %ebx
 	jmp	1f
 
 0:	/* top, read another word from the indirection page */
@@ -226,27 +351,28 @@ identity_mapped:
 	movl    %ecx,   %esi /* For every source page do a copy */
 	andl    $0xfffff000, %esi
 
+	movl	%edi, %eax
+	movl	%esi, %ebp
+
+	movl	%edx, %edi
 	movl    $1024, %ecx
 	rep ; movsl
-	jmp     0b
 
-3:
-
-	/* To be certain of avoiding problems with self-modifying code
-	 * I need to execute a serializing instruction here.
-	 * So I flush the TLB, it's handy, and not processor dependent.
-	 */
-	xorl	%eax, %eax
-	movl	%eax, %cr3
+	movl	%ebp, %edi
+	movl	%eax, %esi
+	movl	$1024, %ecx
+	rep ; movsl
 
-	/* set all of the registers to known values */
-	/* leave %esp alone */
+	movl	%eax, %edi
+	movl	%edx, %esi
+	movl	$1024, %ecx
+	rep ; movsl
 
-	xorl	%eax, %eax
-	xorl	%ebx, %ebx
-	xorl    %ecx, %ecx
-	xorl    %edx, %edx
-	xorl    %esi, %esi
-	xorl    %edi, %edi
-	xorl    %ebp, %ebp
+	lea	PAGE_SIZE(%ebp), %esi
+	jmp     0b
+3:
+	popl	%esi
+	popl	%edi
+	popl	%ebx
+	popl	%ebp
 	ret
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index f7745f94c00..76e305e064f 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -80,24 +80,6 @@ static void __init setup_per_cpu_maps(void)
 #endif
 }
 
-#ifdef CONFIG_HAVE_CPUMASK_OF_CPU_MAP
-cpumask_t *cpumask_of_cpu_map __read_mostly;
-EXPORT_SYMBOL(cpumask_of_cpu_map);
-
-/* requires nr_cpu_ids to be initialized */
-static void __init setup_cpumask_of_cpu(void)
-{
-	int i;
-
-	/* alloc_bootmem zeroes memory */
-	cpumask_of_cpu_map = alloc_bootmem_low(sizeof(cpumask_t) * nr_cpu_ids);
-	for (i = 0; i < nr_cpu_ids; i++)
-		cpu_set(i, cpumask_of_cpu_map[i]);
-}
-#else
-static inline void setup_cpumask_of_cpu(void) { }
-#endif
-
 #ifdef CONFIG_X86_32
 /*
  * Great future not-so-futuristic plan: make i386 and x86_64 do it
@@ -197,9 +179,6 @@ void __init setup_per_cpu_areas(void)
 
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
-
-	/* Setup cpumask_of_cpu map */
-	setup_cpumask_of_cpu();
 }
 
 #endif
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 8d45fabc5f3..ce3251ce550 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -21,6 +21,7 @@ config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
 	select PREEMPT_NOTIFIERS
+	select MMU_NOTIFIER
 	select ANON_INODES
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b0e4ddca6c1..2fa231923cf 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1814,6 +1814,7 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva)
 	spin_unlock(&vcpu->kvm->mmu_lock);
 	return r;
 }
+EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt);
 
 void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 {
@@ -1870,6 +1871,12 @@ void kvm_enable_tdp(void)
 }
 EXPORT_SYMBOL_GPL(kvm_enable_tdp);
 
+void kvm_disable_tdp(void)
+{
+	tdp_enabled = false;
+}
+EXPORT_SYMBOL_GPL(kvm_disable_tdp);
+
 static void free_mmu_pages(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu_page *sp;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index b756e876dce..e2ee264740c 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -453,7 +453,8 @@ static __init int svm_hardware_setup(void)
 	if (npt_enabled) {
 		printk(KERN_INFO "kvm: Nested Paging enabled\n");
 		kvm_enable_tdp();
-	}
+	} else
+		kvm_disable_tdp();
 
 	return 0;
 
@@ -1007,10 +1008,13 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	struct kvm *kvm = svm->vcpu.kvm;
 	u64 fault_address;
 	u32 error_code;
+	bool event_injection = false;
 
 	if (!irqchip_in_kernel(kvm) &&
-		is_external_interrupt(exit_int_info))
+	    is_external_interrupt(exit_int_info)) {
+		event_injection = true;
 		push_irq(&svm->vcpu, exit_int_info & SVM_EVTINJ_VEC_MASK);
+	}
 
 	fault_address  = svm->vmcb->control.exit_info_2;
 	error_code = svm->vmcb->control.exit_info_1;
@@ -1024,6 +1028,8 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 			    (u32)fault_address, (u32)(fault_address >> 32),
 			    handler);
 
+	if (event_injection)
+		kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address);
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 0cac6370171..2a69773e3b2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2298,6 +2298,8 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		cr2 = vmcs_readl(EXIT_QUALIFICATION);
 		KVMTRACE_3D(PAGE_FAULT, vcpu, error_code, (u32)cr2,
 			    (u32)((u64)cr2 >> 32), handler);
+		if (vect_info & VECTORING_INFO_VALID_MASK)
+			kvm_mmu_unprotect_page_virt(vcpu, cr2);
 		return kvm_mmu_page_fault(vcpu, cr2, error_code);
 	}
 
@@ -3116,15 +3118,6 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 		return ERR_PTR(-ENOMEM);
 
 	allocate_vpid(vmx);
-	if (id == 0 && vm_need_ept()) {
-		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
-			VMX_EPT_WRITABLE_MASK |
-			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
-		kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK,
-				VMX_EPT_FAKE_DIRTY_MASK, 0ull,
-				VMX_EPT_EXECUTABLE_MASK);
-		kvm_enable_tdp();
-	}
 
 	err = kvm_vcpu_init(&vmx->vcpu, kvm, id);
 	if (err)
@@ -3303,8 +3296,17 @@ static int __init vmx_init(void)
 	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_ESP);
 	vmx_disable_intercept_for_msr(vmx_msr_bitmap, MSR_IA32_SYSENTER_EIP);
 
-	if (cpu_has_vmx_ept())
+	if (vm_need_ept()) {
 		bypass_guest_pf = 0;
+		kvm_mmu_set_base_ptes(VMX_EPT_READABLE_MASK |
+			VMX_EPT_WRITABLE_MASK |
+			VMX_EPT_DEFAULT_MT << VMX_EPT_MT_EPTE_SHIFT);
+		kvm_mmu_set_mask_ptes(0ull, VMX_EPT_FAKE_ACCESSED_MASK,
+				VMX_EPT_FAKE_DIRTY_MASK, 0ull,
+				VMX_EPT_EXECUTABLE_MASK);
+		kvm_enable_tdp();
+	} else
+		kvm_disable_tdp();
 
 	if (bypass_guest_pf)
 		kvm_mmu_set_nonpresent_ptes(~0xffeull, 0ull);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9f1cdb011cf..5916191420c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3184,6 +3184,10 @@ static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector,
 	kvm_desct->base |= seg_desc->base2 << 24;
 	kvm_desct->limit = seg_desc->limit0;
 	kvm_desct->limit |= seg_desc->limit << 16;
+	if (seg_desc->g) {
+		kvm_desct->limit <<= 12;
+		kvm_desct->limit |= 0xfff;
+	}
 	kvm_desct->selector = selector;
 	kvm_desct->type = seg_desc->type;
 	kvm_desct->present = seg_desc->p;
@@ -3223,6 +3227,7 @@ static void get_segment_descritptor_dtable(struct kvm_vcpu *vcpu,
 static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 					 struct desc_struct *seg_desc)
 {
+	gpa_t gpa;
 	struct descriptor_table dtable;
 	u16 index = selector >> 3;
 
@@ -3232,13 +3237,16 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 		kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc);
 		return 1;
 	}
-	return kvm_read_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base);
+	gpa += index * 8;
+	return kvm_read_guest(vcpu->kvm, gpa, seg_desc, 8);
 }
 
 /* allowed just for 8 bytes segments */
 static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 					 struct desc_struct *seg_desc)
 {
+	gpa_t gpa;
 	struct descriptor_table dtable;
 	u16 index = selector >> 3;
 
@@ -3246,7 +3254,9 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
 
 	if (dtable.limit < index * 8 + 7)
 		return 1;
-	return kvm_write_guest(vcpu->kvm, dtable.base + index * 8, seg_desc, 8);
+	gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, dtable.base);
+	gpa += index * 8;
+	return kvm_write_guest(vcpu->kvm, gpa, seg_desc, 8);
 }
 
 static u32 get_tss_base_addr(struct kvm_vcpu *vcpu,
@@ -3258,55 +3268,7 @@ static u32 get_tss_base_addr(struct kvm_vcpu *vcpu,
 	base_addr |= (seg_desc->base1 << 16);
 	base_addr |= (seg_desc->base2 << 24);
 
-	return base_addr;
-}
-
-static int load_tss_segment32(struct kvm_vcpu *vcpu,
-			      struct desc_struct *seg_desc,
-			      struct tss_segment_32 *tss)
-{
-	u32 base_addr;
-
-	base_addr = get_tss_base_addr(vcpu, seg_desc);
-
-	return kvm_read_guest(vcpu->kvm, base_addr, tss,
-			      sizeof(struct tss_segment_32));
-}
-
-static int save_tss_segment32(struct kvm_vcpu *vcpu,
-			      struct desc_struct *seg_desc,
-			      struct tss_segment_32 *tss)
-{
-	u32 base_addr;
-
-	base_addr = get_tss_base_addr(vcpu, seg_desc);
-
-	return kvm_write_guest(vcpu->kvm, base_addr, tss,
-			       sizeof(struct tss_segment_32));
-}
-
-static int load_tss_segment16(struct kvm_vcpu *vcpu,
-			      struct desc_struct *seg_desc,
-			      struct tss_segment_16 *tss)
-{
-	u32 base_addr;
-
-	base_addr = get_tss_base_addr(vcpu, seg_desc);
-
-	return kvm_read_guest(vcpu->kvm, base_addr, tss,
-			      sizeof(struct tss_segment_16));
-}
-
-static int save_tss_segment16(struct kvm_vcpu *vcpu,
-			      struct desc_struct *seg_desc,
-			      struct tss_segment_16 *tss)
-{
-	u32 base_addr;
-
-	base_addr = get_tss_base_addr(vcpu, seg_desc);
-
-	return kvm_write_guest(vcpu->kvm, base_addr, tss,
-			       sizeof(struct tss_segment_16));
+	return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr);
 }
 
 static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg)
@@ -3466,20 +3428,26 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu,
 }
 
 static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       struct desc_struct *cseg_desc,
+		       u32 old_tss_base,
 		       struct desc_struct *nseg_desc)
 {
 	struct tss_segment_16 tss_segment_16;
 	int ret = 0;
 
-	if (load_tss_segment16(vcpu, cseg_desc, &tss_segment_16))
+	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
+			   sizeof tss_segment_16))
 		goto out;
 
 	save_state_to_tss16(vcpu, &tss_segment_16);
-	save_tss_segment16(vcpu, cseg_desc, &tss_segment_16);
 
-	if (load_tss_segment16(vcpu, nseg_desc, &tss_segment_16))
+	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16,
+			    sizeof tss_segment_16))
 		goto out;
+
+	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc),
+			   &tss_segment_16, sizeof tss_segment_16))
+		goto out;
+
 	if (load_state_from_tss16(vcpu, &tss_segment_16))
 		goto out;
 
@@ -3489,20 +3457,26 @@ out:
 }
 
 static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector,
-		       struct desc_struct *cseg_desc,
+		       u32 old_tss_base,
 		       struct desc_struct *nseg_desc)
 {
 	struct tss_segment_32 tss_segment_32;
 	int ret = 0;
 
-	if (load_tss_segment32(vcpu, cseg_desc, &tss_segment_32))
+	if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
+			   sizeof tss_segment_32))
 		goto out;
 
 	save_state_to_tss32(vcpu, &tss_segment_32);
-	save_tss_segment32(vcpu, cseg_desc, &tss_segment_32);
 
-	if (load_tss_segment32(vcpu, nseg_desc, &tss_segment_32))
+	if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32,
+			    sizeof tss_segment_32))
+		goto out;
+
+	if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc),
+			   &tss_segment_32, sizeof tss_segment_32))
 		goto out;
+
 	if (load_state_from_tss32(vcpu, &tss_segment_32))
 		goto out;
 
@@ -3517,16 +3491,20 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	struct desc_struct cseg_desc;
 	struct desc_struct nseg_desc;
 	int ret = 0;
+	u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
+	u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
 
-	kvm_get_segment(vcpu, &tr_seg, VCPU_SREG_TR);
+	old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base);
 
+	/* FIXME: Handle errors. Failure to read either TSS or their
+	 * descriptors should generate a pagefault.
+	 */
 	if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc))
 		goto out;
 
-	if (load_guest_segment_descriptor(vcpu, tr_seg.selector, &cseg_desc))
+	if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc))
 		goto out;
 
-
 	if (reason != TASK_SWITCH_IRET) {
 		int cpl;
 
@@ -3544,8 +3522,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 
 	if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
 		cseg_desc.type &= ~(1 << 1); //clear the B flag
-		save_guest_segment_descriptor(vcpu, tr_seg.selector,
-					      &cseg_desc);
+		save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc);
 	}
 
 	if (reason == TASK_SWITCH_IRET) {
@@ -3557,10 +3534,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	kvm_x86_ops->cache_regs(vcpu);
 
 	if (nseg_desc.type & 8)
-		ret = kvm_task_switch_32(vcpu, tss_selector, &cseg_desc,
+		ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_base,
 					 &nseg_desc);
 	else
-		ret = kvm_task_switch_16(vcpu, tss_selector, &cseg_desc,
+		ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_base,
 					 &nseg_desc);
 
 	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 756fc489652..65f0b8a47be 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1044,6 +1044,9 @@ __init void lguest_init(void)
 	init_pg_tables_start = __pa(pg0);
 	init_pg_tables_end = __pa(pg0);
 
+	/* As described in head_32.S, we map the first 128M of memory. */
+	max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
+
 	/* Load the %fs segment register (the per-cpu segment register) with
 	 * the normal data segment to get through booting. */
 	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_DS) : "memory");
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 1fbb844c3d7..2977ea37791 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,6 +1,7 @@
 obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o
 
+obj-$(CONFIG_HAVE_GET_USER_PAGES_FAST) += gup.o
 obj-$(CONFIG_X86_32)		+= pgtable_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
new file mode 100644
index 00000000000..007bb06c750
--- /dev/null
+++ b/arch/x86/mm/gup.c
@@ -0,0 +1,298 @@
+/*
+ * Lockless get_user_pages_fast for x86
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ */
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
+#include <linux/highmem.h>
+
+#include <asm/pgtable.h>
+
+static inline pte_t gup_get_pte(pte_t *ptep)
+{
+#ifndef CONFIG_X86_PAE
+	return *ptep;
+#else
+	/*
+	 * With get_user_pages_fast, we walk down the pagetables without taking
+	 * any locks.  For this we would like to load the pointers atoimcally,
+	 * but that is not possible (without expensive cmpxchg8b) on PAE.  What
+	 * we do have is the guarantee that a pte will only either go from not
+	 * present to present, or present to not present or both -- it will not
+	 * switch to a completely different present page without a TLB flush in
+	 * between; something that we are blocking by holding interrupts off.
+	 *
+	 * Setting ptes from not present to present goes:
+	 * ptep->pte_high = h;
+	 * smp_wmb();
+	 * ptep->pte_low = l;
+	 *
+	 * And present to not present goes:
+	 * ptep->pte_low = 0;
+	 * smp_wmb();
+	 * ptep->pte_high = 0;
+	 *
+	 * We must ensure here that the load of pte_low sees l iff pte_high
+	 * sees h. We load pte_high *after* loading pte_low, which ensures we
+	 * don't see an older value of pte_high.  *Then* we recheck pte_low,
+	 * which ensures that we haven't picked up a changed pte high. We might
+	 * have got rubbish values from pte_low and pte_high, but we are
+	 * guaranteed that pte_low will not have the present bit set *unless*
+	 * it is 'l'. And get_user_pages_fast only operates on present ptes, so
+	 * we're safe.
+	 *
+	 * gup_get_pte should not be used or copied outside gup.c without being
+	 * very careful -- it does not atomically load the pte or anything that
+	 * is likely to be useful for you.
+	 */
+	pte_t pte;
+
+retry:
+	pte.pte_low = ptep->pte_low;
+	smp_rmb();
+	pte.pte_high = ptep->pte_high;
+	smp_rmb();
+	if (unlikely(pte.pte_low != ptep->pte_low))
+		goto retry;
+
+	return pte;
+#endif
+}
+
+/*
+ * The performance critical leaf functions are made noinline otherwise gcc
+ * inlines everything into a single function which results in too much
+ * register pressure.
+ */
+static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t *ptep;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+
+	ptep = pte_offset_map(&pmd, addr);
+	do {
+		pte_t pte = gup_get_pte(ptep);
+		struct page *page;
+
+		if ((pte_val(pte) & (mask | _PAGE_SPECIAL)) != mask) {
+			pte_unmap(ptep);
+			return 0;
+		}
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
+		get_page(page);
+		pages[*nr] = page;
+		(*nr)++;
+
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+	pte_unmap(ptep - 1);
+
+	return 1;
+}
+
+static inline void get_head_page_multiple(struct page *page, int nr)
+{
+	VM_BUG_ON(page != compound_head(page));
+	VM_BUG_ON(page_count(page) == 0);
+	atomic_add(nr, &page->_count);
+}
+
+static noinline int gup_huge_pmd(pmd_t pmd, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t pte = *(pte_t *)&pmd;
+	struct page *head, *page;
+	int refs;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+	get_head_page_multiple(head, refs);
+
+	return 1;
+}
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pmd_t *pmdp;
+
+	pmdp = pmd_offset(&pud, addr);
+	do {
+		pmd_t pmd = *pmdp;
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			return 0;
+		if (unlikely(pmd_large(pmd))) {
+			if (!gup_huge_pmd(pmd, addr, next, write, pages, nr))
+				return 0;
+		} else {
+			if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+				return 0;
+		}
+	} while (pmdp++, addr = next, addr != end);
+
+	return 1;
+}
+
+static noinline int gup_huge_pud(pud_t pud, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	pte_t pte = *(pte_t *)&pud;
+	struct page *head, *page;
+	int refs;
+
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(pte_val(pte) & _PAGE_SPECIAL);
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		pages[*nr] = page;
+		(*nr)++;
+		page++;
+		refs++;
+	} while (addr += PAGE_SIZE, addr != end);
+	get_head_page_multiple(head, refs);
+
+	return 1;
+}
+
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+			int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pud_t *pudp;
+
+	pudp = pud_offset(&pgd, addr);
+	do {
+		pud_t pud = *pudp;
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			return 0;
+		if (unlikely(pud_large(pud))) {
+			if (!gup_huge_pud(pud, addr, next, write, pages, nr))
+				return 0;
+		} else {
+			if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+				return 0;
+		}
+	} while (pudp++, addr = next, addr != end);
+
+	return 1;
+}
+
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	pgd_t *pgdp;
+	int nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					start, len)))
+		goto slow_irqon;
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch size
+	 * will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables and pages from being freed on x86.
+	 *
+	 * So long as we atomically load page table pointers versus teardown
+	 * (which we do on x86, with the above PAE exception), we can follow the
+	 * address down to the the page and take a ref on it.
+	 */
+	local_irq_disable();
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		next = pgd_addr_end(addr, end);
+		if (pgd_none(pgd))
+			goto slow;
+		if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+			goto slow;
+	} while (pgdp++, addr = next, addr != end);
+	local_irq_enable();
+
+	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
+	return nr;
+
+	{
+		int ret;
+
+slow:
+		local_irq_enable();
+slow_irqon:
+		/* Try to get the remaining pages with get_user_pages */
+		start += nr << PAGE_SHIFT;
+		pages += nr;
+
+		down_read(&mm->mmap_sem);
+		ret = get_user_pages(current, mm, start,
+			(end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
+		up_read(&mm->mmap_sem);
+
+		/* Have to be a bit careful with return values */
+		if (nr > 0) {
+			if (ret < 0)
+				ret = nr;
+			else
+				ret += nr;
+		}
+
+		return ret;
+	}
+}
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ec37121f670..129618ca0ea 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -86,43 +86,6 @@ early_param("gbpages", parse_direct_gbpages_on);
  * around without checking the pgd every time.
  */
 
-void show_mem(void)
-{
-	long i, total = 0, reserved = 0;
-	long shared = 0, cached = 0;
-	struct page *page;
-	pg_data_t *pgdat;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
-	for_each_online_pgdat(pgdat) {
-		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-			/*
-			 * This loop can take a while with 256 GB and
-			 * 4k pages so defer the NMI watchdog:
-			 */
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-
-			if (!pfn_valid(pgdat->node_start_pfn + i))
-				continue;
-
-			page = pfn_to_page(pgdat->node_start_pfn + i);
-			total++;
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page) - 1;
-		}
-	}
-	printk(KERN_INFO "%lu pages of RAM\n",		total);
-	printk(KERN_INFO "%lu reserved pages\n",	reserved);
-	printk(KERN_INFO "%lu pages shared\n",		shared);
-	printk(KERN_INFO "%lu pages swap cached\n",	cached);
-}
-
 int after_bootmem;
 
 static __init void *spp_getpage(void)
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index b4becbf8c57..cab0abbd1eb 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -20,53 +20,6 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-void show_mem(void)
-{
-	int total = 0, reserved = 0;
-	int shared = 0, cached = 0;
-	int highmem = 0;
-	struct page *page;
-	pg_data_t *pgdat;
-	unsigned long i;
-	unsigned long flags;
-
-	printk(KERN_INFO "Mem-info:\n");
-	show_free_areas();
-	for_each_online_pgdat(pgdat) {
-		pgdat_resize_lock(pgdat, &flags);
-		for (i = 0; i < pgdat->node_spanned_pages; ++i) {
-			if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
-				touch_nmi_watchdog();
-			page = pgdat_page_nr(pgdat, i);
-			total++;
-			if (PageHighMem(page))
-				highmem++;
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (page_count(page))
-				shared += page_count(page) - 1;
-		}
-		pgdat_resize_unlock(pgdat, &flags);
-	}
-	printk(KERN_INFO "%d pages of RAM\n", total);
-	printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
-	printk(KERN_INFO "%d reserved pages\n", reserved);
-	printk(KERN_INFO "%d pages shared\n", shared);
-	printk(KERN_INFO "%d pages swap cached\n", cached);
-
-	printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
-	printk(KERN_INFO "%lu pages writeback\n",
-					global_page_state(NR_WRITEBACK));
-	printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
-	printk(KERN_INFO "%lu pages slab\n",
-		global_page_state(NR_SLAB_RECLAIMABLE) +
-		global_page_state(NR_SLAB_UNRECLAIMABLE));
-	printk(KERN_INFO "%lu pages pagetables\n",
-					global_page_state(NR_PAGETABLE));
-}
-
 /*
  * Associate a virtual page frame with a given physical page frame 
  * and protection flags for that frame.
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index ff3a6a33634..4bdaa590375 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -23,7 +23,8 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
 		pci_read_config_byte(d, reg++, &busno);
 		pci_read_config_byte(d, reg++, &suba);
 		pci_read_config_byte(d, reg++, &subb);
-		DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
+		dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno,
+			suba, subb);
 		if (busno)
 			pci_scan_bus_with_sysdata(busno);	/* Bus A */
 		if (suba < subb)
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index a09505806b8..5807d1bc73f 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -128,10 +128,8 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list)
 				pr = pci_find_parent_resource(dev, r);
 				if (!r->start || !pr ||
 				    request_resource(pr, r) < 0) {
-					printk(KERN_ERR "PCI: Cannot allocate "
-						"resource region %d "
-						"of bridge %s\n",
-						idx, pci_name(dev));
+					dev_err(&dev->dev, "BAR %d: can't "
+						"allocate resource\n", idx);
 					/*
 					 * Something is wrong with the region.
 					 * Invalidate the resource to prevent
@@ -166,15 +164,15 @@ static void __init pcibios_allocate_resources(int pass)
 			else
 				disabled = !(command & PCI_COMMAND_MEMORY);
 			if (pass == disabled) {
-				DBG("PCI: Resource %08lx-%08lx "
-				    "(f=%lx, d=%d, p=%d)\n",
-				    r->start, r->end, r->flags, disabled, pass);
+				dev_dbg(&dev->dev, "resource %#08llx-%#08llx "
+					"(f=%lx, d=%d, p=%d)\n",
+					(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) {
-					printk(KERN_ERR "PCI: Cannot allocate "
-						"resource region %d "
-						"of device %s\n",
-						idx, pci_name(dev));
+					dev_err(&dev->dev, "BAR %d: can't "
+						"allocate resource\n", idx);
 					/* We'll assign a new address later */
 					r->end -= r->start;
 					r->start = 0;
@@ -187,8 +185,7 @@ static void __init pcibios_allocate_resources(int pass)
 				/* Turn the ROM off, leave the resource region,
 				 * but keep it unregistered. */
 				u32 reg;
-				DBG("PCI: Switching off ROM of %s\n",
-					pci_name(dev));
+				dev_dbg(&dev->dev, "disabling ROM\n");
 				r->flags &= ~IORESOURCE_ROM_ENABLE;
 				pci_read_config_dword(dev,
 						dev->rom_base_reg, &reg);
@@ -257,8 +254,7 @@ void pcibios_set_master(struct pci_dev *dev)
 		lat = pcibios_max_latency;
 	else
 		return;
-	printk(KERN_DEBUG "PCI: Setting latency timer of device %s to %d\n",
-		pci_name(dev), lat);
+	dev_printk(KERN_DEBUG, &dev->dev, "setting latency timer to %d\n", lat);
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 6a06a2eb059..fec0123b33a 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -436,7 +436,7 @@ static int pirq_vlsi_get(struct pci_dev *router, struct pci_dev *dev, int pirq)
 {
 	WARN_ON_ONCE(pirq >= 9);
 	if (pirq > 8) {
-		printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+		dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
 		return 0;
 	}
 	return read_config_nybble(router, 0x74, pirq-1);
@@ -446,7 +446,7 @@ static int pirq_vlsi_set(struct pci_dev *router, struct pci_dev *dev, int pirq,
 {
 	WARN_ON_ONCE(pirq >= 9);
 	if (pirq > 8) {
-		printk(KERN_INFO "VLSI router pirq escape (%d)\n", pirq);
+		dev_info(&dev->dev, "VLSI router PIRQ escape (%d)\n", pirq);
 		return 0;
 	}
 	write_config_nybble(router, 0x74, pirq-1, irq);
@@ -492,15 +492,17 @@ static int pirq_amd756_get(struct pci_dev *router, struct pci_dev *dev, int pirq
 	irq = 0;
 	if (pirq <= 4)
 		irq = read_config_nybble(router, 0x56, pirq - 1);
-	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d get irq : %2d\n",
-		dev->vendor, dev->device, pirq, irq);
+	dev_info(&dev->dev,
+		 "AMD756: dev [%04x/%04x], router PIRQ %d get IRQ %d\n",
+		 dev->vendor, dev->device, pirq, irq);
 	return irq;
 }
 
 static int pirq_amd756_set(struct pci_dev *router, struct pci_dev *dev, int pirq, int irq)
 {
-	printk(KERN_INFO "AMD756: dev %04x:%04x, router pirq : %d SET irq : %2d\n",
-		dev->vendor, dev->device, pirq, irq);
+	dev_info(&dev->dev,
+		 "AMD756: dev [%04x/%04x], router PIRQ %d set IRQ %d\n",
+		 dev->vendor, dev->device, pirq, irq);
 	if (pirq <= 4)
 		write_config_nybble(router, 0x56, pirq - 1, irq);
 	return 1;
@@ -730,7 +732,6 @@ static __init int ali_router_probe(struct irq_router *r, struct pci_dev *router,
 	switch (device) {
 	case PCI_DEVICE_ID_AL_M1533:
 	case PCI_DEVICE_ID_AL_M1563:
-		printk(KERN_DEBUG "PCI: Using ALI IRQ Router\n");
 		r->name = "ALI";
 		r->get = pirq_ali_get;
 		r->set = pirq_ali_set;
@@ -840,11 +841,9 @@ static void __init pirq_find_router(struct irq_router *r)
 			h->probe(r, pirq_router_dev, pirq_router_dev->device))
 			break;
 	}
-	printk(KERN_INFO "PCI: Using IRQ router %s [%04x/%04x] at %s\n",
-		pirq_router.name,
-		pirq_router_dev->vendor,
-		pirq_router_dev->device,
-		pci_name(pirq_router_dev));
+	dev_info(&pirq_router_dev->dev, "%s IRQ router [%04x/%04x]\n",
+		 pirq_router.name,
+		 pirq_router_dev->vendor, pirq_router_dev->device);
 
 	/* The device remains referenced for the kernel lifetime */
 }
@@ -877,7 +876,7 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	/* Find IRQ pin */
 	pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
 	if (!pin) {
-		DBG(KERN_DEBUG " -> no interrupt pin\n");
+		dev_dbg(&dev->dev, "no interrupt pin\n");
 		return 0;
 	}
 	pin = pin - 1;
@@ -887,20 +886,20 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 	if (!pirq_table)
 		return 0;
 
-	DBG(KERN_DEBUG "IRQ for %s[%c]", pci_name(dev), 'A' + pin);
 	info = pirq_get_info(dev);
 	if (!info) {
-		DBG(" -> not found in routing table\n" KERN_DEBUG);
+		dev_dbg(&dev->dev, "PCI INT %c not found in routing table\n",
+			'A' + pin);
 		return 0;
 	}
 	pirq = info->irq[pin].link;
 	mask = info->irq[pin].bitmap;
 	if (!pirq) {
-		DBG(" -> not routed\n" KERN_DEBUG);
+		dev_dbg(&dev->dev, "PCI INT %c not routed\n", 'A' + pin);
 		return 0;
 	}
-	DBG(" -> PIRQ %02x, mask %04x, excl %04x", pirq, mask,
-		pirq_table->exclusive_irqs);
+	dev_dbg(&dev->dev, "PCI INT %c -> PIRQ %02x, mask %04x, excl %04x",
+		'A' + pin, pirq, mask, pirq_table->exclusive_irqs);
 	mask &= pcibios_irq_mask;
 
 	/* Work around broken HP Pavilion Notebooks which assign USB to
@@ -930,10 +929,8 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 		if (pci_probe & PCI_USE_PIRQ_MASK)
 			newirq = 0;
 		else
-			printk("\n" KERN_WARNING
-				"PCI: IRQ %i for device %s doesn't match PIRQ mask - try pci=usepirqmask\n"
-				KERN_DEBUG, newirq,
-				pci_name(dev));
+			dev_warn(&dev->dev, "IRQ %d doesn't match PIRQ mask "
+				 "%#x; try pci=usepirqmask\n", newirq, mask);
 	}
 	if (!newirq && assign) {
 		for (i = 0; i < 16; i++) {
@@ -944,39 +941,35 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 				newirq = i;
 		}
 	}
-	DBG(" -> newirq=%d", newirq);
+	dev_dbg(&dev->dev, "PCI INT %c -> newirq %d", 'A' + pin, newirq);
 
 	/* Check if it is hardcoded */
 	if ((pirq & 0xf0) == 0xf0) {
 		irq = pirq & 0xf;
-		DBG(" -> hardcoded IRQ %d\n", irq);
-		msg = "Hardcoded";
+		msg = "hardcoded";
 	} else if (r->get && (irq = r->get(pirq_router_dev, dev, pirq)) && \
 	((!(pci_probe & PCI_USE_PIRQ_MASK)) || ((1 << irq) & mask))) {
-		DBG(" -> got IRQ %d\n", irq);
-		msg = "Found";
+		msg = "found";
 		eisa_set_level_irq(irq);
 	} else if (newirq && r->set &&
 		(dev->class >> 8) != PCI_CLASS_DISPLAY_VGA) {
-		DBG(" -> assigning IRQ %d", newirq);
 		if (r->set(pirq_router_dev, dev, pirq, newirq)) {
 			eisa_set_level_irq(newirq);
-			DBG(" ... OK\n");
-			msg = "Assigned";
+			msg = "assigned";
 			irq = newirq;
 		}
 	}
 
 	if (!irq) {
-		DBG(" ... failed\n");
 		if (newirq && mask == (1 << newirq)) {
-			msg = "Guessed";
+			msg = "guessed";
 			irq = newirq;
-		} else
+		} else {
+			dev_dbg(&dev->dev, "can't route interrupt\n");
 			return 0;
+		}
 	}
-	printk(KERN_INFO "PCI: %s IRQ %d for device %s\n", msg, irq,
-		pci_name(dev));
+	dev_info(&dev->dev, "%s PCI INT %c -> IRQ %d\n", msg, 'A' + pin, irq);
 
 	/* Update IRQ for all devices with the same pirq value */
 	while ((dev2 = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev2)) != NULL) {
@@ -996,17 +989,17 @@ static int pcibios_lookup_irq(struct pci_dev *dev, int assign)
 			(!(pci_probe & PCI_USE_PIRQ_MASK) || \
 			((1 << dev2->irq) & mask))) {
 #ifndef CONFIG_PCI_MSI
-				printk(KERN_INFO "IRQ routing conflict for %s, have irq %d, want irq %d\n",
-				       pci_name(dev2), dev2->irq, irq);
+				dev_info(&dev2->dev, "IRQ routing conflict: "
+					 "have IRQ %d, want IRQ %d\n",
+					 dev2->irq, irq);
 #endif
 				continue;
 			}
 			dev2->irq = irq;
 			pirq_penalty[irq]++;
 			if (dev != dev2)
-				printk(KERN_INFO
-					"PCI: Sharing IRQ %d with %s\n",
-					irq, pci_name(dev2));
+				dev_info(&dev->dev, "sharing IRQ %d with %s\n",
+					 irq, pci_name(dev2));
 		}
 	}
 	return 1;
@@ -1025,8 +1018,7 @@ static void __init pcibios_fixup_irqs(void)
 		 * already in use.
 		 */
 		if (dev->irq >= 16) {
-			DBG(KERN_DEBUG "%s: ignoring bogus IRQ %d\n",
-				pci_name(dev), dev->irq);
+			dev_dbg(&dev->dev, "ignoring bogus IRQ %d\n", dev->irq);
 			dev->irq = 0;
 		}
 		/*
@@ -1070,12 +1062,12 @@ static void __init pcibios_fixup_irqs(void)
 					irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 							PCI_SLOT(bridge->devfn), pin);
 					if (irq >= 0)
-						printk(KERN_WARNING "PCI: using PPB %s[%c] to get irq %d\n",
-							pci_name(bridge), 'A' + pin, irq);
+						dev_warn(&dev->dev, "using bridge %s INT %c to get IRQ %d\n",
+							 pci_name(bridge),
+							 'A' + pin, irq);
 				}
 				if (irq >= 0) {
-					printk(KERN_INFO "PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n",
-						pci_name(dev), 'A' + pin, irq);
+					dev_info(&dev->dev, "PCI->APIC IRQ transform: INT %c -> IRQ %d\n", 'A' + pin, irq);
 					dev->irq = irq;
 				}
 			}
@@ -1231,25 +1223,24 @@ static int pirq_enable_irq(struct pci_dev *dev)
 				irq = IO_APIC_get_PCI_irq_vector(bridge->bus->number,
 						PCI_SLOT(bridge->devfn), pin);
 				if (irq >= 0)
-					printk(KERN_WARNING
-						"PCI: using PPB %s[%c] to get irq %d\n",
-						pci_name(bridge),
-						'A' + pin, irq);
+					dev_warn(&dev->dev, "using bridge %s "
+						 "INT %c to get IRQ %d\n",
+						 pci_name(bridge), 'A' + pin,
+						 irq);
 				dev = bridge;
 			}
 			dev = temp_dev;
 			if (irq >= 0) {
-				printk(KERN_INFO
-					"PCI->APIC IRQ transform: %s[%c] -> IRQ %d\n",
-					pci_name(dev), 'A' + pin, irq);
+				dev_info(&dev->dev, "PCI->APIC IRQ transform: "
+					 "INT %c -> IRQ %d\n", 'A' + pin, irq);
 				dev->irq = irq;
 				return 0;
 			} else
-				msg = " Probably buggy MP table.";
+				msg = "; probably buggy MP table";
 		} else if (pci_probe & PCI_BIOS_IRQ_SCAN)
 			msg = "";
 		else
-			msg = " Please try using pci=biosirq.";
+			msg = "; please try using pci=biosirq";
 
 		/*
 		 * With IDE legacy devices the IRQ lookup failure is not
@@ -1259,9 +1250,8 @@ static int pirq_enable_irq(struct pci_dev *dev)
 				!(dev->class & 0x5))
 			return 0;
 
-		printk(KERN_WARNING
-			"PCI: No IRQ known for interrupt pin %c of device %s.%s\n",
-			'A' + pin, pci_name(dev), msg);
+		dev_warn(&dev->dev, "can't find IRQ for PCI INT %c%s\n",
+			 'A' + pin, msg);
 	}
 	return 0;
 }
diff --git a/arch/x86/pci/numaq_32.c b/arch/x86/pci/numaq_32.c
index f4b16dc11da..1177845d318 100644
--- a/arch/x86/pci/numaq_32.c
+++ b/arch/x86/pci/numaq_32.c
@@ -131,13 +131,14 @@ static void __devinit pci_fixup_i450nx(struct pci_dev *d)
 	u8 busno, suba, subb;
 	int quad = BUS2QUAD(d->bus->number);
 
-	printk("PCI: Searching for i450NX host bridges on %s\n", pci_name(d));
+	dev_info(&d->dev, "searching for i450NX host bridges\n");
 	reg = 0xd0;
 	for(pxb=0; pxb<2; pxb++) {
 		pci_read_config_byte(d, reg++, &busno);
 		pci_read_config_byte(d, reg++, &suba);
 		pci_read_config_byte(d, reg++, &subb);
-		DBG("i450NX PXB %d: %02x/%02x/%02x\n", pxb, busno, suba, subb);
+		dev_dbg(&d->dev, "i450NX PXB %d: %02x/%02x/%02x\n",
+			pxb, busno, suba, subb);
 		if (busno) {
 			/* Bus A */
 			pci_scan_bus_with_sysdata(QUADLOCAL2BUS(quad, busno));