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>

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;
 

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;
 

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.

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);

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;

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));
 }
 
 /**

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;
 

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

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

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();
 
-	control_page = page_address(image->control_code_page);
-	memcpy(control_page, relocate_kernel, PAGE_SIZE);
+	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/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)

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;

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)

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;
 }

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);

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,

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,
 };
 

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,

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.

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
+
+	movl	%ebp, %edi
+	movl	%eax, %esi
+	movl	$1024, %ecx
+	rep ; movsl
+
+	movl	%eax, %edi
+	movl	%edx, %esi
+	movl	$1024, %ecx
+	rep ; movsl
+
+	lea	PAGE_SIZE(%ebp), %esi
 	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
-
-	/* set all of the registers to known values */
-	/* leave %esp alone */
-
-	xorl	%eax, %eax
-	xorl	%ebx, %ebx
-	xorl    %ecx, %ecx
-	xorl    %edx, %edx
-	xorl    %esi, %esi
-	xorl    %edi, %edi
-	xorl    %ebp, %ebp
+	popl	%esi
+	popl	%edi
+	popl	%ebx
+	popl	%ebp
 	ret

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