Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm updates from Ingo Molnar:
 "The main changes in this cycle were:

   - make the debugfs 'kernel_page_tables' file read-only, as it only
     has read ops.  (Borislav Petkov)

   - micro-optimize clflush_cache_range() (Chris Wilson)

   - swiotlb enhancements, which fixes certain KVM emulated devices
     (Igor Mammedov)

   - fix an LDT related debug message (Jan Beulich)

   - modularize CONFIG_X86_PTDUMP (Kees Cook)

   - tone down an overly alarming warning (Laura Abbott)

   - Mark variable __initdata (Rasmus Villemoes)

   - PAT additions (Toshi Kani)"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Micro-optimise clflush_cache_range()
  x86/mm/pat: Change free_memtype() to support shrinking case
  x86/mm/pat: Add untrack_pfn_moved for mremap
  x86/mm: Drop WARN from multi-BAR check
  x86/LDT: Print the real LDT base address
  x86/mm/64: Enable SWIOTLB if system has SRAT memory regions above MAX_DMA32_PFN
  x86/mm: Introduce max_possible_pfn
  x86/mm/ptdump: Make (debugfs)/kernel_page_tables read-only
  x86/mm/mtrr: Mark the 'range_new' static variable in mtrr_calc_range_state() as __initdata
  x86/mm: Turn CONFIG_X86_PTDUMP into a module

arch/x86/Kconfig.debug

@@ -69,7 +69,7 @@ config X86_PTDUMP_CORE
 	def_bool n
 
 config X86_PTDUMP
-	bool "Export kernel pagetable layout to userspace via debugfs"
+	tristate "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
 	select DEBUG_FS
 	select X86_PTDUMP_CORE

arch/x86/kernel/cpu/mtrr/cleanup.c

@@ -593,9 +593,16 @@ mtrr_calc_range_state(u64 chunk_size, u64 gran_size,
 		      unsigned long x_remove_base,
 		      unsigned long x_remove_size, int i)
 {
-	static struct range range_new[RANGE_NUM];
+	/*
+	 * range_new should really be an automatic variable, but
+	 * putting 4096 bytes on the stack is frowned upon, to put it
+	 * mildly. It is safe to make it a static __initdata variable,
+	 * since mtrr_calc_range_state is only called during init and
+	 * there's no way it will call itself recursively.
+	 */
+	static struct range range_new[RANGE_NUM] __initdata;
 	unsigned long range_sums_new;
-	static int nr_range_new;
+	int nr_range_new;
 	int num_reg;
 
 	/* Convert ranges to var ranges state: */

arch/x86/kernel/pci-swiotlb.c

@@ -88,7 +88,7 @@ int __init pci_swiotlb_detect_4gb(void)
 {
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
-	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
+	if (!no_iommu && max_possible_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
 #endif
 	return swiotlb;

arch/x86/kernel/process_64.c

@@ -125,7 +125,7 @@ void release_thread(struct task_struct *dead_task)
 		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
-				dead_task->mm->context.ldt,
+				dead_task->mm->context.ldt->entries,
 				dead_task->mm->context.ldt->size);
 			BUG();
 		}

arch/x86/kernel/setup.c

@@ -1048,6 +1048,8 @@ void __init setup_arch(char **cmdline_p)
 	if (mtrr_trim_uncached_memory(max_pfn))
 		max_pfn = e820_end_of_ram_pfn();
 
+	max_possible_pfn = max_pfn;
+
 #ifdef CONFIG_X86_32
 	/* max_low_pfn get updated here */
 	find_low_pfn_range();

arch/x86/mm/Makefile

@@ -15,6 +15,7 @@ obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_X86_PTDUMP_CORE)	+= dump_pagetables.o
+obj-$(CONFIG_X86_PTDUMP)	+= debug_pagetables.o
 
 obj-$(CONFIG_HIGHMEM)		+= highmem_32.o
 

arch/x86/mm/debug_pagetables.c

@@ -0,0 +1,46 @@
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <asm/pgtable.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	ptdump_walk_pgd_level(m, NULL);
+	return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *filp)
+{
+	return single_open(filp, ptdump_show, NULL);
+}
+
+static const struct file_operations ptdump_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ptdump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static struct dentry *pe;
+
+static int __init pt_dump_debug_init(void)
+{
+	pe = debugfs_create_file("kernel_page_tables", S_IRUSR, NULL, NULL,
+				 &ptdump_fops);
+	if (!pe)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __exit pt_dump_debug_exit(void)
+{
+	debugfs_remove_recursive(pe);
+}
+
+module_init(pt_dump_debug_init);
+module_exit(pt_dump_debug_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
+MODULE_DESCRIPTION("Kernel debugging helper that dumps pagetables");

arch/x86/mm/dump_pagetables.c

@@ -426,38 +426,15 @@ void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 {
 	ptdump_walk_pgd_level_core(m, pgd, false);
 }
+EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level);
 
 void ptdump_walk_pgd_level_checkwx(void)
 {
 	ptdump_walk_pgd_level_core(NULL, NULL, true);
 }
 
-#ifdef CONFIG_X86_PTDUMP
+static int __init pt_dump_init(void)
-static int ptdump_show(struct seq_file *m, void *v)
 {
-	ptdump_walk_pgd_level(m, NULL);
-	return 0;
-}
-
-static int ptdump_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, ptdump_show, NULL);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-#endif
-
-static int pt_dump_init(void)
-{
-#ifdef CONFIG_X86_PTDUMP
-	struct dentry *pe;
-#endif
-
 #ifdef CONFIG_X86_32
 	/* Not a compile-time constant on x86-32 */
 	address_markers[VMALLOC_START_NR].start_address = VMALLOC_START;
@@ -468,13 +445,6 @@ static int pt_dump_init(void)
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 #endif
 
-#ifdef CONFIG_X86_PTDUMP
-	pe = debugfs_create_file("kernel_page_tables", 0600, NULL, NULL,
-				 &ptdump_fops);
-	if (!pe)
-		return -ENOMEM;
-#endif
-
 	return 0;
 }
 

arch/x86/mm/ioremap.c

@@ -194,8 +194,8 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr,
 	 * Check if the request spans more than any BAR in the iomem resource
 	 * tree.
 	 */
-	WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size),
+	if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size))
-		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
+		pr_warn("caller %pS mapping multiple BARs\n", caller);
 
 	return ret_addr;
 err_free_area:

arch/x86/mm/pageattr.c

@@ -129,14 +129,16 @@ within(unsigned long addr, unsigned long start, unsigned long end)
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
-	unsigned long clflush_mask = boot_cpu_data.x86_clflush_size - 1;
+	const unsigned long clflush_size = boot_cpu_data.x86_clflush_size;
+	void *p = (void *)((unsigned long)vaddr & ~(clflush_size - 1));
 	void *vend = vaddr + size;
-	void *p;
+
+	if (p >= vend)
+		return;
 
 	mb();
 
-	for (p = (void *)((unsigned long)vaddr & ~clflush_mask);
+	for (; p < vend; p += clflush_size)
-	     p < vend; p += boot_cpu_data.x86_clflush_size)
 		clflushopt(p);
 
 	mb();

arch/x86/mm/pat.c

@@ -586,7 +586,7 @@ int free_memtype(u64 start, u64 end)
 	entry = rbt_memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
-	if (!entry) {
+	if (IS_ERR(entry)) {
 		pr_info("x86/PAT: %s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid, start, end - 1);
 		return -EINVAL;
@@ -992,6 +992,16 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 	vma->vm_flags &= ~VM_PAT;
 }
 
+/*
+ * untrack_pfn_moved is called, while mremapping a pfnmap for a new region,
+ * with the old vma after its pfnmap page table has been removed.  The new
+ * vma has a new pfnmap to the same pfn & cache type with VM_PAT set.
+ */
+void untrack_pfn_moved(struct vm_area_struct *vma)
+{
+	vma->vm_flags &= ~VM_PAT;
+}
+
 pgprot_t pgprot_writecombine(pgprot_t prot)
 {
 	return __pgprot(pgprot_val(prot) |

arch/x86/mm/pat_rbtree.c

@@ -98,8 +98,13 @@ static struct memtype *memtype_rb_lowest_match(struct rb_root *root,
 	return last_lower; /* Returns NULL if there is no overlap */
 }
 
-static struct memtype *memtype_rb_exact_match(struct rb_root *root,
+enum {
-				u64 start, u64 end)
+	MEMTYPE_EXACT_MATCH	= 0,
+	MEMTYPE_END_MATCH	= 1
+};
+
+static struct memtype *memtype_rb_match(struct rb_root *root,
+				u64 start, u64 end, int match_type)
 {
 	struct memtype *match;
 
@@ -107,7 +112,12 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root,
 	while (match != NULL && match->start < end) {
 		struct rb_node *node;
 
-		if (match->start == start && match->end == end)
+		if ((match_type == MEMTYPE_EXACT_MATCH) &&
+		    (match->start == start) && (match->end == end))
+			return match;
+
+		if ((match_type == MEMTYPE_END_MATCH) &&
+		    (match->start < start) && (match->end == end))
 			return match;
 
 		node = rb_next(&match->rb);
@@ -117,7 +127,7 @@ static struct memtype *memtype_rb_exact_match(struct rb_root *root,
 			match = NULL;
 	}
 
-	return NULL; /* Returns NULL if there is no exact match */
+	return NULL; /* Returns NULL if there is no match */
 }
 
 static int memtype_rb_check_conflict(struct rb_root *root,
@@ -210,12 +220,36 @@ struct memtype *rbt_memtype_erase(u64 start, u64 end)
 {
 	struct memtype *data;
 
-	data = memtype_rb_exact_match(&memtype_rbroot, start, end);
+	/*
-	if (!data)
+	 * Since the memtype_rbroot tree allows overlapping ranges,
-		goto out;
+	 * rbt_memtype_erase() checks with EXACT_MATCH first, i.e. free
+	 * a whole node for the munmap case.  If no such entry is found,
+	 * it then checks with END_MATCH, i.e. shrink the size of a node
+	 * from the end for the mremap case.
+	 */
+	data = memtype_rb_match(&memtype_rbroot, start, end,
+				MEMTYPE_EXACT_MATCH);
+	if (!data) {
+		data = memtype_rb_match(&memtype_rbroot, start, end,
+					MEMTYPE_END_MATCH);
+		if (!data)
+			return ERR_PTR(-EINVAL);
+	}
+
+	if (data->start == start) {
+		/* munmap: erase this node */
+		rb_erase_augmented(&data->rb, &memtype_rbroot,
+					&memtype_rb_augment_cb);
+	} else {
+		/* mremap: update the end value of this node */
+		rb_erase_augmented(&data->rb, &memtype_rbroot,
+					&memtype_rb_augment_cb);
+		data->end = start;
+		data->subtree_max_end = data->end;
+		memtype_rb_insert(&memtype_rbroot, data);
+		return NULL;
+	}
 
-	rb_erase_augmented(&data->rb, &memtype_rbroot, &memtype_rb_augment_cb);
-out:
 	return data;
 }
 

arch/x86/mm/srat.c

@@ -203,6 +203,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
 		pr_warn("SRAT: Failed to mark hotplug range [mem %#010Lx-%#010Lx] in memblock\n",
 			(unsigned long long)start, (unsigned long long)end - 1);
 
+	max_possible_pfn = max(max_possible_pfn, PFN_UP(end - 1));
+
 	return 0;
 out_err_bad_srat:
 	bad_srat();

include/asm-generic/pgtable.h

@@ -569,7 +569,7 @@ static inline int track_pfn_copy(struct vm_area_struct *vma)
 }
 
 /*
- * untrack_pfn_vma is called while unmapping a pfnmap for a region.
+ * untrack_pfn is called while unmapping a pfnmap for a region.
  * untrack can be called for a specific region indicated by pfn and size or
  * can be for the entire vma (in which case pfn, size are zero).
  */
@@ -577,6 +577,13 @@ static inline void untrack_pfn(struct vm_area_struct *vma,
 			       unsigned long pfn, unsigned long size)
 {
 }
+
+/*
+ * untrack_pfn_moved is called while mremapping a pfnmap for a new region.
+ */
+static inline void untrack_pfn_moved(struct vm_area_struct *vma)
+{
+}
 #else
 extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 			   unsigned long pfn, unsigned long addr,
@@ -586,6 +593,7 @@ extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 extern int track_pfn_copy(struct vm_area_struct *vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size);
+extern void untrack_pfn_moved(struct vm_area_struct *vma);
 #endif
 
 #ifdef __HAVE_COLOR_ZERO_PAGE

include/linux/bootmem.h

@@ -19,6 +19,10 @@ extern unsigned long min_low_pfn;
  * highest page
  */
 extern unsigned long max_pfn;
+/*
+ * highest possible page
+ */
+extern unsigned long long max_possible_pfn;
 
 #ifndef CONFIG_NO_BOOTMEM
 /*

mm/bootmem.c

@@ -33,6 +33,7 @@ EXPORT_SYMBOL(contig_page_data);
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
+unsigned long long max_possible_pfn;
 
 bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
 

mm/mremap.c

@@ -319,6 +319,10 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 	hiwater_vm = mm->hiwater_vm;
 	vm_stat_account(mm, vma->vm_flags, vma->vm_file, new_len>>PAGE_SHIFT);
 
+	/* Tell pfnmap has moved from this vma */
+	if (unlikely(vma->vm_flags & VM_PFNMAP))
+		untrack_pfn_moved(vma);
+
 	if (do_munmap(mm, old_addr, old_len) < 0) {
 		/* OOM: unable to split vma, just get accounts right */
 		vm_unacct_memory(excess >> PAGE_SHIFT);

mm/nobootmem.c

@@ -31,6 +31,7 @@ EXPORT_SYMBOL(contig_page_data);
 unsigned long max_low_pfn;
 unsigned long min_low_pfn;
 unsigned long max_pfn;
+unsigned long long max_possible_pfn;
 
 static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)