7 files changed, 125 insertions, 214 deletions

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 09daebfdb11..8a450930834 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -280,15 +280,16 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 		return NULL;
 	area->phys_addr = phys_addr;
 	vaddr = (unsigned long) area->addr;
-	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
+
+	if (kernel_map_sync_memtype(phys_addr, size, prot_val)) {
 		free_memtype(phys_addr, phys_addr + size);
 		free_vm_area(area);
 		return NULL;
 	}
 
-	if (ioremap_change_attr(vaddr, size, prot_val) < 0) {
+	if (ioremap_page_range(vaddr, vaddr + size, phys_addr, prot)) {
 		free_memtype(phys_addr, phys_addr + size);
-		vunmap(area->addr);
+		free_vm_area(area);
 		return NULL;
 	}
 
@@ -374,7 +375,8 @@ static void __iomem *ioremap_default(resource_size_t phys_addr,
 	 * - UC_MINUS for non-WB-able memory with no other conflicting mappings
 	 * - Inherit from confliting mappings otherwise
 	 */
-	err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags);
+	err = reserve_memtype(phys_addr, phys_addr + size,
+				_PAGE_CACHE_WB, &flags);
 	if (err < 0)
 		return NULL;
 
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 256ce643b0b..16ccbd77917 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -87,7 +87,7 @@ static struct kmmio_probe *get_kmmio_probe(unsigned long addr)
 {
 	struct kmmio_probe *p;
 	list_for_each_entry_rcu(p, &kmmio_probes, list) {
-		if (addr >= p->addr && addr <= (p->addr + p->len))
+		if (addr >= p->addr && addr < (p->addr + p->len))
 			return p;
 	}
 	return NULL;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 3daefa04ace..d2530062fe0 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -257,7 +257,7 @@ void resume_map_numa_kva(pgd_t *pgd_base)
 }
 #endif
 
-static unsigned long calculate_numa_remap_pages(void)
+static __init unsigned long calculate_numa_remap_pages(void)
 {
 	int nid;
 	unsigned long size, reserve_pages = 0;
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index d73aaa89237..2d05a12029d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -188,6 +188,9 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 	const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE);
 	int nid;
 
+	if (!end)
+		return;
+
 	start = roundup(start, ZONE_ALIGN);
 
 	printk(KERN_INFO "Bootmem setup node %d %016lx-%016lx\n", nodeid,
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index d71e1b636ce..797f9f107cb 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -945,71 +945,94 @@ int _set_memory_uc(unsigned long addr, int numpages)
 
 int set_memory_uc(unsigned long addr, int numpages)
 {
+	int ret;
+
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
-	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-			    _PAGE_CACHE_UC_MINUS, NULL))
-		return -EINVAL;
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+			    _PAGE_CACHE_UC_MINUS, NULL);
+	if (ret)
+		goto out_err;
+
+	ret = _set_memory_uc(addr, numpages);
+	if (ret)
+		goto out_free;
 
-	return _set_memory_uc(addr, numpages);
+	return 0;
+
+out_free:
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_uc);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray)
 {
-	unsigned long start;
-	unsigned long end;
-	int i;
+	int i, j;
+	int ret;
+
 	/*
 	 * for now UC MINUS. see comments in ioremap_nocache()
 	 */
 	for (i = 0; i < addrinarray; i++) {
-		start = __pa(addr[i]);
-		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
-			if (end != __pa(addr[i + 1]))
-				break;
-			i++;
-		}
-		if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
-			goto out;
+		ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
+					_PAGE_CACHE_UC_MINUS, NULL);
+		if (ret)
+			goto out_free;
 	}
 
-	return change_page_attr_set(addr, addrinarray,
+	ret = change_page_attr_set(addr, addrinarray,
 				    __pgprot(_PAGE_CACHE_UC_MINUS), 1);
-out:
-	for (i = 0; i < addrinarray; i++) {
-		unsigned long tmp = __pa(addr[i]);
-
-		if (tmp == start)
-			break;
-		for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
-			if (end != __pa(addr[i + 1]))
-				break;
-			i++;
-		}
-		free_memtype(tmp, end);
-	}
-	return -EINVAL;
+	if (ret)
+		goto out_free;
+
+	return 0;
+
+out_free:
+	for (j = 0; j < i; j++)
+		free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);
+
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_array_uc);
 
 int _set_memory_wc(unsigned long addr, int numpages)
 {
-	return change_page_attr_set(&addr, numpages,
+	int ret;
+	ret = change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+
+	if (!ret) {
+		ret = change_page_attr_set(&addr, numpages,
 				    __pgprot(_PAGE_CACHE_WC), 0);
+	}
+	return ret;
 }
 
 int set_memory_wc(unsigned long addr, int numpages)
 {
+	int ret;
+
 	if (!pat_enabled)
 		return set_memory_uc(addr, numpages);
 
-	if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
-		_PAGE_CACHE_WC, NULL))
-		return -EINVAL;
+	ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+		_PAGE_CACHE_WC, NULL);
+	if (ret)
+		goto out_err;
+
+	ret = _set_memory_wc(addr, numpages);
+	if (ret)
+		goto out_free;
+
+	return 0;
 
-	return _set_memory_wc(addr, numpages);
+out_free:
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+out_err:
+	return ret;
 }
 EXPORT_SYMBOL(set_memory_wc);
 
@@ -1021,29 +1044,31 @@ int _set_memory_wb(unsigned long addr, int numpages)
 
 int set_memory_wb(unsigned long addr, int numpages)
 {
-	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	int ret;
+
+	ret = _set_memory_wb(addr, numpages);
+	if (ret)
+		return ret;
 
-	return _set_memory_wb(addr, numpages);
+	free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+	return 0;
 }
 EXPORT_SYMBOL(set_memory_wb);
 
 int set_memory_array_wb(unsigned long *addr, int addrinarray)
 {
 	int i;
+	int ret;
 
-	for (i = 0; i < addrinarray; i++) {
-		unsigned long start = __pa(addr[i]);
-		unsigned long end;
-
-		for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
-			if (end != __pa(addr[i + 1]))
-				break;
-			i++;
-		}
-		free_memtype(start, end);
-	}
-	return change_page_attr_clear(addr, addrinarray,
+	ret = change_page_attr_clear(addr, addrinarray,
 				      __pgprot(_PAGE_CACHE_MASK), 1);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < addrinarray; i++)
+		free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
+
+	return 0;
 }
 EXPORT_SYMBOL(set_memory_array_wb);
 
@@ -1136,6 +1161,8 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 
 	retval = cpa_clear_pages_array(pages, addrinarray,
 			__pgprot(_PAGE_CACHE_MASK));
+	if (retval)
+		return retval;
 
 	for (i = 0; i < addrinarray; i++) {
 		start = (unsigned long)page_address(pages[i]);
@@ -1143,7 +1170,7 @@ int set_pages_array_wb(struct page **pages, int addrinarray)
 		free_memtype(start, end);
 	}
 
-	return retval;
+	return 0;
 }
 EXPORT_SYMBOL(set_pages_array_wb);
 
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index c009a241d56..e6718bb2806 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -182,10 +182,10 @@ static unsigned long pat_x_mtrr_type(u64 start, u64 end, unsigned long req_type)
 		u8 mtrr_type;
 
 		mtrr_type = mtrr_type_lookup(start, end);
-		if (mtrr_type == MTRR_TYPE_UNCACHABLE)
-			return _PAGE_CACHE_UC;
-		if (mtrr_type == MTRR_TYPE_WRCOMB)
-			return _PAGE_CACHE_WC;
+		if (mtrr_type != MTRR_TYPE_WRBACK)
+			return _PAGE_CACHE_UC_MINUS;
+
+		return _PAGE_CACHE_WB;
 	}
 
 	return req_type;
@@ -352,23 +352,13 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		return 0;
 	}
 
-	if (req_type == -1) {
-		/*
-		 * Call mtrr_lookup to get the type hint. This is an
-		 * optimization for /dev/mem mmap'ers into WB memory (BIOS
-		 * tools and ACPI tools). Use WB request for WB memory and use
-		 * UC_MINUS otherwise.
-		 */
-		u8 mtrr_type = mtrr_type_lookup(start, end);
-
-		if (mtrr_type == MTRR_TYPE_WRBACK)
-			actual_type = _PAGE_CACHE_WB;
-		else
-			actual_type = _PAGE_CACHE_UC_MINUS;
-	} else {
-		actual_type = pat_x_mtrr_type(start, end,
-					      req_type & _PAGE_CACHE_MASK);
-	}
+	/*
+	 * Call mtrr_lookup to get the type hint. This is an
+	 * optimization for /dev/mem mmap'ers into WB memory (BIOS
+	 * tools and ACPI tools). Use WB request for WB memory and use
+	 * UC_MINUS otherwise.
+	 */
+	actual_type = pat_x_mtrr_type(start, end, req_type & _PAGE_CACHE_MASK);
 
 	if (new_type)
 		*new_type = actual_type;
@@ -546,9 +536,7 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t *vma_prot)
 {
-	u64 offset = ((u64) pfn) << PAGE_SHIFT;
-	unsigned long flags = -1;
-	int retval;
+	unsigned long flags = _PAGE_CACHE_WB;
 
 	if (!range_is_allowed(pfn, size))
 		return 0;
@@ -576,64 +564,11 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 	}
 #endif
 
-	/*
-	 * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot.
-	 *
-	 * Without O_SYNC, we want to get
-	 * - WB for WB-able memory and no other conflicting mappings
-	 * - UC_MINUS for non-WB-able memory with no other conflicting mappings
-	 * - Inherit from confliting mappings otherwise
-	 */
-	if (flags != -1) {
-		retval = reserve_memtype(offset, offset + size, flags, NULL);
-	} else {
-		retval = reserve_memtype(offset, offset + size, -1, &flags);
-	}
-
-	if (retval < 0)
-		return 0;
-
-	if (((pfn < max_low_pfn_mapped) ||
-	     (pfn >= (1UL<<(32 - PAGE_SHIFT)) && pfn < max_pfn_mapped)) &&
-	    ioremap_change_attr((unsigned long)__va(offset), size, flags) < 0) {
-		free_memtype(offset, offset + size);
-		printk(KERN_INFO
-		"%s:%d /dev/mem ioremap_change_attr failed %s for %Lx-%Lx\n",
-			current->comm, current->pid,
-			cattr_name(flags),
-			offset, (unsigned long long)(offset + size));
-		return 0;
-	}
-
 	*vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
 			     flags);
 	return 1;
 }
 
-void map_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
-{
-	unsigned long want_flags = (pgprot_val(vma_prot) & _PAGE_CACHE_MASK);
-	u64 addr = (u64)pfn << PAGE_SHIFT;
-	unsigned long flags;
-
-	reserve_memtype(addr, addr + size, want_flags, &flags);
-	if (flags != want_flags) {
-		printk(KERN_INFO
-		"%s:%d /dev/mem expected mapping type %s for %Lx-%Lx, got %s\n",
-			current->comm, current->pid,
-			cattr_name(want_flags),
-			addr, (unsigned long long)(addr + size),
-			cattr_name(flags));
-	}
-}
-
-void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
-{
-	u64 addr = (u64)pfn << PAGE_SHIFT;
-
-	free_memtype(addr, addr + size);
-}
-
 /*
  * Change the memory type for the physial address range in kernel identity
  * mapping space if that range is a part of identity map.
@@ -671,8 +606,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 {
 	int is_ram = 0;
 	int ret;
-	unsigned long flags;
 	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
+	unsigned long flags = want_flags;
 
 	is_ram = pat_pagerange_is_ram(paddr, paddr + size);
 
@@ -734,29 +669,28 @@ static void free_pfn_range(u64 paddr, unsigned long size)
  *
  * If the vma has a linear pfn mapping for the entire range, we get the prot
  * from pte and reserve the entire vma range with single reserve_pfn_range call.
- * Otherwise, we reserve the entire vma range, my ging through the PTEs page
- * by page to get physical address and protection.
  */
 int track_pfn_vma_copy(struct vm_area_struct *vma)
 {
-	int retval = 0;
-	unsigned long i, j;
 	resource_size_t paddr;
 	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 	pgprot_t pgprot;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/*
 		 * reserve the whole chunk covered by vma. We need the
 		 * starting address and protection from pte.
 		 */
-		if (follow_phys(vma, vma_start, 0, &prot, &paddr)) {
+		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
 			WARN_ON_ONCE(1);
 			return -EINVAL;
 		}
@@ -764,28 +698,7 @@ int track_pfn_vma_copy(struct vm_area_struct *vma)
 		return reserve_pfn_range(paddr, vma_size, &pgprot, 1);
 	}
 
-	/* reserve entire vma page by page, using pfn and prot from pte */
-	for (i = 0; i < vma_size; i += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-			continue;
-
-		pgprot = __pgprot(prot);
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, &pgprot, 1);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		if (follow_phys(vma, vma_start + j, 0, &prot, &paddr))
-			continue;
-
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -795,50 +708,28 @@ cleanup_ret:
  * prot is passed in as a parameter for the new mapping. If the vma has a
  * linear pfn mapping for the entire range reserve the entire vma range with
  * single reserve_pfn_range call.
- * Otherwise, we look t the pfn and size and reserve only the specified range
- * page by page.
- *
- * Note that this function can be called with caller trying to map only a
- * subrange/page inside the vma.
  */
 int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
 			unsigned long pfn, unsigned long size)
 {
-	int retval = 0;
-	unsigned long i, j;
-	resource_size_t base_paddr;
 	resource_size_t paddr;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return 0;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/* reserve the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
 		return reserve_pfn_range(paddr, vma_size, prot, 0);
 	}
 
-	/* reserve page by page using pfn and size */
-	base_paddr = (resource_size_t)pfn << PAGE_SHIFT;
-	for (i = 0; i < size; i += PAGE_SIZE) {
-		paddr = base_paddr + i;
-		retval = reserve_pfn_range(paddr, PAGE_SIZE, prot, 0);
-		if (retval)
-			goto cleanup_ret;
-	}
 	return 0;
-
-cleanup_ret:
-	/* Reserve error: Cleanup partial reservation and return error */
-	for (j = 0; j < i; j += PAGE_SIZE) {
-		paddr = base_paddr + j;
-		free_pfn_range(paddr, PAGE_SIZE);
-	}
-
-	return retval;
 }
 
 /*
@@ -849,39 +740,23 @@ cleanup_ret:
 void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size)
 {
-	unsigned long i;
 	resource_size_t paddr;
-	unsigned long prot;
-	unsigned long vma_start = vma->vm_start;
-	unsigned long vma_end = vma->vm_end;
-	unsigned long vma_size = vma_end - vma_start;
+	unsigned long vma_size = vma->vm_end - vma->vm_start;
 
 	if (!pat_enabled)
 		return;
 
+	/*
+	 * For now, only handle remap_pfn_range() vmas where
+	 * is_linear_pfn_mapping() == TRUE. Handling of
+	 * vm_insert_pfn() is TBD.
+	 */
 	if (is_linear_pfn_mapping(vma)) {
 		/* free the whole chunk starting from vm_pgoff */
 		paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
 		free_pfn_range(paddr, vma_size);
 		return;
 	}
-
-	if (size != 0 && size != vma_size) {
-		/* free page by page, using pfn and size */
-		paddr = (resource_size_t)pfn << PAGE_SHIFT;
-		for (i = 0; i < size; i += PAGE_SIZE) {
-			paddr = paddr + i;
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	} else {
-		/* free entire vma, page by page, using the pfn from pte */
-		for (i = 0; i < vma_size; i += PAGE_SIZE) {
-			if (follow_phys(vma, vma_start + i, 0, &prot, &paddr))
-				continue;
-
-			free_pfn_range(paddr, PAGE_SIZE);
-		}
-	}
 }
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index c7d272b8574..33c5fa57e43 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -28,6 +28,7 @@ int acpi_numa __initdata;
 static struct acpi_table_slit *acpi_slit;
 
 static nodemask_t nodes_parsed __initdata;
+static nodemask_t cpu_nodes_parsed __initdata;
 static struct bootnode nodes[MAX_NUMNODES] __initdata;
 static struct bootnode nodes_add[MAX_NUMNODES];
 static int found_add_area __initdata;
@@ -141,6 +142,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 
 	apic_id = pa->apic_id;
 	apicid_to_node[apic_id] = node;
+	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
 	       pxm, apic_id, node);
@@ -174,6 +176,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 	else
 		apic_id = pa->apic_id;
 	apicid_to_node[apic_id] = node;
+	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
 	       pxm, apic_id, node);
@@ -402,7 +405,8 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end)
 		return -1;
 	}
 
-	node_possible_map = nodes_parsed;
+	/* Account for nodes with cpus and no memory */
+	nodes_or(node_possible_map, nodes_parsed, cpu_nodes_parsed);
 
 	/* Finally register nodes */
 	for_each_node_mask(i, node_possible_map)