Merge commit 'linus' into x86/urgent, to pick up recent x86 changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

10 files changed, 116 insertions, 56 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 65c47fd..f9d38a4 100644
--- a/arch/x86/mm/Makefile
+++ b/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
 
diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c
new file mode 100644
index 0000000..bfcffdf
--- /dev/null
+++ b/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");
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0f1c6fc..4a6f1d9 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/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 ptdump_show(struct seq_file *m, void *v)
+static int __init pt_dump_init(void)
 {
-	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;
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index b9c78f3..0d8d53d 100644
--- a/arch/x86/mm/ioremap.c
+++ b/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),
-		  KERN_INFO "Info: mapping multiple BARs. Your kernel is fine.");
+	if (iomem_map_sanity_check(unaligned_phys_addr, unaligned_size))
+		pr_warn("caller %pS mapping multiple BARs\n", caller);
 
 	return ret_addr;
 err_free_area:
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a3137a4..6000ad7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/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);
-	     p < vend; p += boot_cpu_data.x86_clflush_size)
+	for (; p < vend; p += clflush_size)
 		clflushopt(p);
 
 	mb();
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index 188e3e0..031782e 100644
--- a/arch/x86/mm/pat.c
+++ b/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) |
diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c
index 6393108..2f77022 100644
--- a/arch/x86/mm/pat_rbtree.c
+++ b/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,
-				u64 start, u64 end)
+enum {
+	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)
-		goto out;
+	/*
+	 * Since the memtype_rbroot tree allows overlapping ranges,
+	 * 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;
 }
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index fb0a9dd..ee9c2e3 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -414,7 +414,7 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 
 	if (changed && dirty) {
 		*ptep = entry;
-		pte_update_defer(vma->vm_mm, address, ptep);
+		pte_update(vma->vm_mm, address, ptep);
 	}
 
 	return changed;
@@ -431,7 +431,6 @@ int pmdp_set_access_flags(struct vm_area_struct *vma,
 
 	if (changed && dirty) {
 		*pmdp = entry;
-		pmd_update_defer(vma->vm_mm, address, pmdp);
 		/*
 		 * We had a write-protection fault here and changed the pmd
 		 * to to more permissive. No need to flush the TLB for that,
@@ -469,9 +468,6 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma,
 		ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
 					 (unsigned long *)pmdp);
 
-	if (ret)
-		pmd_update(vma->vm_mm, addr, pmdp);
-
 	return ret;
 }
 #endif
@@ -518,7 +514,6 @@ void pmdp_splitting_flush(struct vm_area_struct *vma,
 	set = !test_and_set_bit(_PAGE_BIT_SPLITTING,
 				(unsigned long *)pmdp);
 	if (set) {
-		pmd_update(vma->vm_mm, address, pmdp);
 		/* need tlb flush only to serialize against gup-fast */
 		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	}
diff --git a/arch/x86/mm/setup_nx.c b/arch/x86/mm/setup_nx.c
index 90555bf..92e2eac 100644
--- a/arch/x86/mm/setup_nx.c
+++ b/arch/x86/mm/setup_nx.c
@@ -31,7 +31,7 @@ early_param("noexec", noexec_setup);
 
 void x86_configure_nx(void)
 {
-	if (cpu_has_nx && !disable_nx)
+	if (boot_cpu_has(X86_FEATURE_NX) && !disable_nx)
 		__supported_pte_mask |= _PAGE_NX;
 	else
 		__supported_pte_mask &= ~_PAGE_NX;
@@ -39,7 +39,7 @@ void x86_configure_nx(void)
 
 void __init x86_report_nx(void)
 {
-	if (!cpu_has_nx) {
+	if (!boot_cpu_has(X86_FEATURE_NX)) {
 		printk(KERN_NOTICE "Notice: NX (Execute Disable) protection "
 		       "missing in CPU!\n");
 	} else {
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index c2aea63..b5f8218 100644
--- a/arch/x86/mm/srat.c
+++ b/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();