1 files changed, 333 insertions, 431 deletions

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index c009a241d56..657438858e8 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -12,13 +12,15 @@
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/gfp.h>
+#include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
+#include <linux/rbtree.h>
 
 #include <asm/cacheflush.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
+#include <asm/x86_init.h>
 #include <asm/pgtable.h>
 #include <asm/fcntl.h>
 #include <asm/e820.h>
@@ -28,6 +30,8 @@
 #include <asm/pat.h>
 #include <asm/io.h>
 
+#include "pat_internal.h"
+
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_enabled = 1;
 
@@ -51,19 +55,15 @@ static inline void pat_disable(const char *reason)
 #endif
 
 
-static int debug_enable;
+int pat_debug_enable;
 
 static int __init pat_debug_setup(char *str)
 {
-	debug_enable = 1;
+	pat_debug_enable = 1;
 	return 0;
 }
 __setup("debugpat", pat_debug_setup);
 
-#define dprintk(fmt, arg...) \
-	do { if (debug_enable) printk(KERN_INFO fmt, ##arg); } while (0)
-
-
 static u64 __read_mostly boot_pat_state;
 
 enum {
@@ -80,6 +80,7 @@ enum {
 void pat_init(void)
 {
 	u64 pat;
+	bool boot_cpu = !boot_pat_state;
 
 	if (!pat_enabled)
 		return;
@@ -121,49 +122,15 @@ void pat_init(void)
 		rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
 
 	wrmsrl(MSR_IA32_CR_PAT, pat);
-	printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
-	       smp_processor_id(), boot_pat_state, pat);
-}
 
-#undef PAT
-
-static char *cattr_name(unsigned long flags)
-{
-	switch (flags & _PAGE_CACHE_MASK) {
-	case _PAGE_CACHE_UC:		return "uncached";
-	case _PAGE_CACHE_UC_MINUS:	return "uncached-minus";
-	case _PAGE_CACHE_WB:		return "write-back";
-	case _PAGE_CACHE_WC:		return "write-combining";
-	default:			return "broken";
-	}
+	if (boot_cpu)
+		printk(KERN_INFO "x86 PAT enabled: cpu %d, old 0x%Lx, new 0x%Lx\n",
+		       smp_processor_id(), boot_pat_state, pat);
 }
 
-/*
- * The global memtype list keeps track of memory type for specific
- * physical memory areas. Conflicting memory types in different
- * mappings can cause CPU cache corruption. To avoid this we keep track.
- *
- * The list is sorted based on starting address and can contain multiple
- * entries for each address (this allows reference counting for overlapping
- * areas). All the aliases have the same cache attributes of course.
- * Zero attributes are represented as holes.
- *
- * Currently the data structure is a list because the number of mappings
- * are expected to be relatively small. If this should be a problem
- * it could be changed to a rbtree or similar.
- *
- * memtype_lock protects the whole list.
- */
-
-struct memtype {
-	u64			start;
-	u64			end;
-	unsigned long		type;
-	struct list_head	nd;
-};
+#undef PAT
 
-static LIST_HEAD(memtype_list);
-static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype list */
+static DEFINE_SPINLOCK(memtype_lock);	/* protects memtype accesses */
 
 /*
  * Does intersection of PAT memory type and MTRR memory type and returns
@@ -182,130 +149,111 @@ 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;
 }
 
+struct pagerange_state {
+	unsigned long		cur_pfn;
+	int			ram;
+	int			not_ram;
+};
+
 static int
-chk_conflict(struct memtype *new, struct memtype *entry, unsigned long *type)
-{
-	if (new->type != entry->type) {
-		if (type) {
-			new->type = entry->type;
-			*type = entry->type;
-		} else
-			goto conflict;
-	}
+pagerange_is_ram_callback(unsigned long initial_pfn, unsigned long total_nr_pages, void *arg)
+{
+	struct pagerange_state *state = arg;
 
-	 /* check overlaps with more than one entry in the list */
-	list_for_each_entry_continue(entry, &memtype_list, nd) {
-		if (new->end <= entry->start)
-			break;
-		else if (new->type != entry->type)
-			goto conflict;
-	}
-	return 0;
+	state->not_ram	|= initial_pfn > state->cur_pfn;
+	state->ram	|= total_nr_pages > 0;
+	state->cur_pfn	 = initial_pfn + total_nr_pages;
 
- conflict:
-	printk(KERN_INFO "%s:%d conflicting memory types "
-	       "%Lx-%Lx %s<->%s\n", current->comm, current->pid, new->start,
-	       new->end, cattr_name(new->type), cattr_name(entry->type));
-	return -EBUSY;
+	return state->ram && state->not_ram;
 }
 
-static struct memtype *cached_entry;
-static u64 cached_start;
-
-static int pat_pagerange_is_ram(unsigned long start, unsigned long end)
+static int pat_pagerange_is_ram(resource_size_t start, resource_size_t end)
 {
-	int ram_page = 0, not_rampage = 0;
-	unsigned long page_nr;
+	int ret = 0;
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long end_pfn = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	struct pagerange_state state = {start_pfn, 0, 0};
 
-	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
-	     ++page_nr) {
-		/*
-		 * For legacy reasons, physical address range in the legacy ISA
-		 * region is tracked as non-RAM. This will allow users of
-		 * /dev/mem to map portions of legacy ISA region, even when
-		 * some of those portions are listed(or not even listed) with
-		 * different e820 types(RAM/reserved/..)
-		 */
-		if (page_nr >= (ISA_END_ADDRESS >> PAGE_SHIFT) &&
-		    page_is_ram(page_nr))
-			ram_page = 1;
-		else
-			not_rampage = 1;
-
-		if (ram_page == not_rampage)
-			return -1;
+	/*
+	 * For legacy reasons, physical address range in the legacy ISA
+	 * region is tracked as non-RAM. This will allow users of
+	 * /dev/mem to map portions of legacy ISA region, even when
+	 * some of those portions are listed(or not even listed) with
+	 * different e820 types(RAM/reserved/..)
+	 */
+	if (start_pfn < ISA_END_ADDRESS >> PAGE_SHIFT)
+		start_pfn = ISA_END_ADDRESS >> PAGE_SHIFT;
+
+	if (start_pfn < end_pfn) {
+		ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn,
+				&state, pagerange_is_ram_callback);
 	}
 
-	return ram_page;
+	return (ret > 0) ? -1 : (state.ram ? 1 : 0);
 }
 
 /*
- * For RAM pages, mark the pages as non WB memory type using
- * PageNonWB (PG_arch_1). We allow only one set_memory_uc() or
- * set_memory_wc() on a RAM page at a time before marking it as WB again.
- * This is ok, because only one driver will be owning the page and
- * doing set_memory_*() calls.
- *
- * For now, we use PageNonWB to track that the RAM page is being mapped
- * as non WB. In future, we will have to use one more flag
- * (or some other mechanism in page_struct) to distinguish between
- * UC and WC mapping.
+ * For RAM pages, we use page flags to mark the pages with appropriate type.
+ * Here we do two pass:
+ * - Find the memtype of all the pages in the range, look for any conflicts
+ * - In case of no conflicts, set the new memtype for pages in the range
  */
 static int reserve_ram_pages_type(u64 start, u64 end, unsigned long req_type,
 				  unsigned long *new_type)
 {
 	struct page *page;
-	u64 pfn, end_pfn;
+	u64 pfn;
+
+	if (req_type == _PAGE_CACHE_UC) {
+		/* We do not support strong UC */
+		WARN_ON_ONCE(1);
+		req_type = _PAGE_CACHE_UC_MINUS;
+	}
 
 	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
-		page = pfn_to_page(pfn);
-		if (page_mapped(page) || PageNonWB(page))
-			goto out;
+		unsigned long type;
 
-		SetPageNonWB(page);
+		page = pfn_to_page(pfn);
+		type = get_page_memtype(page);
+		if (type != -1) {
+			printk(KERN_INFO "reserve_ram_pages_type failed [mem %#010Lx-%#010Lx], track 0x%lx, req 0x%lx\n",
+				start, end - 1, type, req_type);
+			if (new_type)
+				*new_type = type;
+
+			return -EBUSY;
+		}
 	}
-	return 0;
 
-out:
-	end_pfn = pfn;
-	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+	if (new_type)
+		*new_type = req_type;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
 		page = pfn_to_page(pfn);
-		ClearPageNonWB(page);
+		set_page_memtype(page, req_type);
 	}
-
-	return -EINVAL;
+	return 0;
 }
 
 static int free_ram_pages_type(u64 start, u64 end)
 {
 	struct page *page;
-	u64 pfn, end_pfn;
+	u64 pfn;
 
 	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
 		page = pfn_to_page(pfn);
-		if (page_mapped(page) || !PageNonWB(page))
-			goto out;
-
-		ClearPageNonWB(page);
+		set_page_memtype(page, -1);
 	}
 	return 0;
-
-out:
-	end_pfn = pfn;
-	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
-		page = pfn_to_page(pfn);
-		SetPageNonWB(page);
-	}
-	return -EINVAL;
 }
 
 /*
@@ -315,9 +263,6 @@ out:
  * - _PAGE_CACHE_UC_MINUS
  * - _PAGE_CACHE_UC
  *
- * req_type will have a special case value '-1', when requester want to inherit
- * the memory type from mtrr (if WB), existing PAT, defaulting to UC_MINUS.
- *
  * If new_type is NULL, function will return an error if it cannot reserve the
  * region with req_type. If new_type is non-NULL, function will return
  * available type in new_type in case of no error. In case of any error
@@ -326,9 +271,8 @@ out:
 int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		    unsigned long *new_type)
 {
-	struct memtype *new, *entry;
+	struct memtype *new;
 	unsigned long actual_type;
-	struct list_head *where;
 	int is_range_ram;
 	int err = 0;
 
@@ -337,8 +281,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	if (!pat_enabled) {
 		/* This is identical to page table setting without PAT */
 		if (new_type) {
-			if (req_type == -1)
-				*new_type = _PAGE_CACHE_WB;
+			if (req_type == _PAGE_CACHE_WC)
+				*new_type = _PAGE_CACHE_UC_MINUS;
 			else
 				*new_type = req_type & _PAGE_CACHE_MASK;
 		}
@@ -346,41 +290,34 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	}
 
 	/* Low ISA region is always mapped WB in page table. No need to track */
-	if (is_ISA_range(start, end - 1)) {
+	if (x86_platform.is_untracked_pat_range(start, end)) {
 		if (new_type)
 			*new_type = _PAGE_CACHE_WB;
 		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;
 
 	is_range_ram = pat_pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return reserve_ram_pages_type(start, end, req_type,
-					      new_type);
-	else if (is_range_ram < 0)
+	if (is_range_ram == 1) {
+
+		err = reserve_ram_pages_type(start, end, req_type, new_type);
+
+		return err;
+	} else if (is_range_ram < 0) {
 		return -EINVAL;
+	}
 
-	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+	new  = kzalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -390,73 +327,21 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 	spin_lock(&memtype_lock);
 
-	if (cached_entry && start >= cached_start)
-		entry = cached_entry;
-	else
-		entry = list_entry(&memtype_list, struct memtype, nd);
-
-	/* Search for existing mapping that overlaps the current range */
-	where = NULL;
-	list_for_each_entry_continue(entry, &memtype_list, nd) {
-		if (end <= entry->start) {
-			where = entry->nd.prev;
-			cached_entry = list_entry(where, struct memtype, nd);
-			break;
-		} else if (start <= entry->start) { /* end > entry->start */
-			err = chk_conflict(new, entry, new_type);
-			if (!err) {
-				dprintk("Overlap at 0x%Lx-0x%Lx\n",
-					entry->start, entry->end);
-				where = entry->nd.prev;
-				cached_entry = list_entry(where,
-							struct memtype, nd);
-			}
-			break;
-		} else if (start < entry->end) { /* start > entry->start */
-			err = chk_conflict(new, entry, new_type);
-			if (!err) {
-				dprintk("Overlap at 0x%Lx-0x%Lx\n",
-					entry->start, entry->end);
-				cached_entry = list_entry(entry->nd.prev,
-							struct memtype, nd);
-
-				/*
-				 * Move to right position in the linked
-				 * list to add this new entry
-				 */
-				list_for_each_entry_continue(entry,
-							&memtype_list, nd) {
-					if (start <= entry->start) {
-						where = entry->nd.prev;
-						break;
-					}
-				}
-			}
-			break;
-		}
-	}
-
+	err = rbt_memtype_check_insert(new, new_type);
 	if (err) {
-		printk(KERN_INFO "reserve_memtype failed 0x%Lx-0x%Lx, "
-		       "track %s, req %s\n",
-		       start, end, cattr_name(new->type), cattr_name(req_type));
+		printk(KERN_INFO "reserve_memtype failed [mem %#010Lx-%#010Lx], track %s, req %s\n",
+		       start, end - 1,
+		       cattr_name(new->type), cattr_name(req_type));
 		kfree(new);
 		spin_unlock(&memtype_lock);
 
 		return err;
 	}
 
-	cached_start = start;
-
-	if (where)
-		list_add(&new->nd, where);
-	else
-		list_add_tail(&new->nd, &memtype_list);
-
 	spin_unlock(&memtype_lock);
 
-	dprintk("reserve_memtype added 0x%Lx-0x%Lx, track %s, req %s, ret %s\n",
-		start, end, cattr_name(new->type), cattr_name(req_type),
+	dprintk("reserve_memtype added [mem %#010Lx-%#010Lx], track %s, req %s, ret %s\n",
+		start, end - 1, cattr_name(new->type), cattr_name(req_type),
 		new_type ? cattr_name(*new_type) : "-");
 
 	return err;
@@ -464,48 +349,138 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 
 int free_memtype(u64 start, u64 end)
 {
-	struct memtype *entry;
 	int err = -EINVAL;
 	int is_range_ram;
+	struct memtype *entry;
 
 	if (!pat_enabled)
 		return 0;
 
 	/* Low ISA region is always mapped WB. No need to track */
-	if (is_ISA_range(start, end - 1))
+	if (x86_platform.is_untracked_pat_range(start, end))
 		return 0;
 
 	is_range_ram = pat_pagerange_is_ram(start, end);
-	if (is_range_ram == 1)
-		return free_ram_pages_type(start, end);
-	else if (is_range_ram < 0)
+	if (is_range_ram == 1) {
+
+		err = free_ram_pages_type(start, end);
+
+		return err;
+	} else if (is_range_ram < 0) {
 		return -EINVAL;
+	}
 
 	spin_lock(&memtype_lock);
-	list_for_each_entry(entry, &memtype_list, nd) {
-		if (entry->start == start && entry->end == end) {
-			if (cached_entry == entry || cached_start == start)
-				cached_entry = NULL;
-
-			list_del(&entry->nd);
-			kfree(entry);
-			err = 0;
-			break;
-		}
-	}
+	entry = rbt_memtype_erase(start, end);
 	spin_unlock(&memtype_lock);
 
-	if (err) {
-		printk(KERN_INFO "%s:%d freeing invalid memtype %Lx-%Lx\n",
-			current->comm, current->pid, start, end);
+	if (!entry) {
+		printk(KERN_INFO "%s:%d freeing invalid memtype [mem %#010Lx-%#010Lx]\n",
+		       current->comm, current->pid, start, end - 1);
+		return -EINVAL;
 	}
 
-	dprintk("free_memtype request 0x%Lx-0x%Lx\n", start, end);
+	kfree(entry);
 
-	return err;
+	dprintk("free_memtype request [mem %#010Lx-%#010Lx]\n", start, end - 1);
+
+	return 0;
 }
 
 
+/**
+ * lookup_memtype - Looksup the memory type for a physical address
+ * @paddr: physical address of which memory type needs to be looked up
+ *
+ * Only to be called when PAT is enabled
+ *
+ * Returns _PAGE_CACHE_WB, _PAGE_CACHE_WC, _PAGE_CACHE_UC_MINUS or
+ * _PAGE_CACHE_UC
+ */
+static unsigned long lookup_memtype(u64 paddr)
+{
+	int rettype = _PAGE_CACHE_WB;
+	struct memtype *entry;
+
+	if (x86_platform.is_untracked_pat_range(paddr, paddr + PAGE_SIZE))
+		return rettype;
+
+	if (pat_pagerange_is_ram(paddr, paddr + PAGE_SIZE)) {
+		struct page *page;
+		page = pfn_to_page(paddr >> PAGE_SHIFT);
+		rettype = get_page_memtype(page);
+		/*
+		 * -1 from get_page_memtype() implies RAM page is in its
+		 * default state and not reserved, and hence of type WB
+		 */
+		if (rettype == -1)
+			rettype = _PAGE_CACHE_WB;
+
+		return rettype;
+	}
+
+	spin_lock(&memtype_lock);
+
+	entry = rbt_memtype_lookup(paddr);
+	if (entry != NULL)
+		rettype = entry->type;
+	else
+		rettype = _PAGE_CACHE_UC_MINUS;
+
+	spin_unlock(&memtype_lock);
+	return rettype;
+}
+
+/**
+ * io_reserve_memtype - Request a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ * @type: A pointer to memtype, with requested type. On success, requested
+ * or any other compatible type that was available for the region is returned
+ *
+ * On success, returns 0
+ * On failure, returns non-zero
+ */
+int io_reserve_memtype(resource_size_t start, resource_size_t end,
+			unsigned long *type)
+{
+	resource_size_t size = end - start;
+	unsigned long req_type = *type;
+	unsigned long new_type;
+	int ret;
+
+	WARN_ON_ONCE(iomem_map_sanity_check(start, size));
+
+	ret = reserve_memtype(start, end, req_type, &new_type);
+	if (ret)
+		goto out_err;
+
+	if (!is_new_memtype_allowed(start, size, req_type, new_type))
+		goto out_free;
+
+	if (kernel_map_sync_memtype(start, size, new_type) < 0)
+		goto out_free;
+
+	*type = new_type;
+	return 0;
+
+out_free:
+	free_memtype(start, end);
+	ret = -EBUSY;
+out_err:
+	return ret;
+}
+
+/**
+ * io_free_memtype - Release a memory type mapping for a region of memory
+ * @start: start (physical address) of the region
+ * @end: end (physical address) of the region
+ */
+void io_free_memtype(resource_size_t start, resource_size_t end)
+{
+	free_memtype(start, end);
+}
+
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 				unsigned long size, pgprot_t vma_prot)
 {
@@ -531,9 +506,8 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size)
 
 	while (cursor < to) {
 		if (!devmem_is_allowed(pfn)) {
-			printk(KERN_INFO
-		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
-				current->comm, from, to);
+			printk(KERN_INFO "Program %s tried to access /dev/mem between [mem %#010Lx-%#010Lx]\n",
+				current->comm, from, to - 1);
 			return 0;
 		}
 		cursor += PAGE_SIZE;
@@ -546,16 +520,13 @@ 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;
 
-	if (file->f_flags & O_SYNC) {
+	if (file->f_flags & O_DSYNC)
 		flags = _PAGE_CACHE_UC_MINUS;
-	}
 
 #ifdef CONFIG_X86_32
 	/*
@@ -576,64 +547,11 @@ 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.
@@ -642,20 +560,26 @@ int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
 {
 	unsigned long id_sz;
 
-	if (!pat_enabled || base >= __pa(high_memory))
+	if (base > __pa(high_memory-1))
 		return 0;
 
-	id_sz = (__pa(high_memory) < base + size) ?
+	/*
+	 * some areas in the middle of the kernel identity range
+	 * are not mapped, like the PCI space.
+	 */
+	if (!page_is_ram(base >> PAGE_SHIFT))
+		return 0;
+
+	id_sz = (__pa(high_memory-1) <= base + size) ?
 				__pa(high_memory) - base :
 				size;
 
 	if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
-		printk(KERN_INFO
-			"%s:%d ioremap_change_attr failed %s "
-			"for %Lx-%Lx\n",
+		printk(KERN_INFO "%s:%d ioremap_change_attr failed %s "
+			"for [mem %#010Lx-%#010Lx]\n",
 			current->comm, current->pid,
 			cattr_name(flags),
-			base, (unsigned long long)(base + size));
+			base, (unsigned long long)(base + size-1));
 		return -EINVAL;
 	}
 	return 0;
@@ -671,31 +595,49 @@ 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);
 
 	/*
-	 * reserve_pfn_range() doesn't support RAM pages. Maintain the current
-	 * behavior with RAM pages by returning success.
+	 * reserve_pfn_range() for RAM pages. We do not refcount to keep
+	 * track of number of mappings of RAM pages. We can assert that
+	 * the type requested matches the type of first page in the range.
 	 */
-	if (is_ram != 0)
+	if (is_ram) {
+		if (!pat_enabled)
+			return 0;
+
+		flags = lookup_memtype(paddr);
+		if (want_flags != flags) {
+			printk(KERN_WARNING "%s:%d map pfn RAM range req %s for [mem %#010Lx-%#010Lx], got %s\n",
+				current->comm, current->pid,
+				cattr_name(want_flags),
+				(unsigned long long)paddr,
+				(unsigned long long)(paddr + size - 1),
+				cattr_name(flags));
+			*vma_prot = __pgprot((pgprot_val(*vma_prot) &
+					      (~_PAGE_CACHE_MASK)) |
+					     flags);
+		}
 		return 0;
+	}
 
 	ret = reserve_memtype(paddr, paddr + size, want_flags, &flags);
 	if (ret)
 		return ret;
 
 	if (flags != want_flags) {
-		if (strict_prot || !is_new_memtype_allowed(want_flags, flags)) {
+		if (strict_prot ||
+		    !is_new_memtype_allowed(paddr, size, want_flags, flags)) {
 			free_memtype(paddr, paddr + size);
 			printk(KERN_ERR "%s:%d map pfn expected mapping type %s"
-				" for %Lx-%Lx, got %s\n",
+				" for [mem %#010Lx-%#010Lx], got %s\n",
 				current->comm, current->pid,
 				cattr_name(want_flags),
 				(unsigned long long)paddr,
-				(unsigned long long)(paddr + size),
+				(unsigned long long)(paddr + size - 1),
 				cattr_name(flags));
 			return -EINVAL;
 		}
@@ -729,34 +671,25 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 }
 
 /*
- * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
  *
  * 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 track_pfn_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;
-
-	if (is_linear_pfn_mapping(vma)) {
+	if (vma->vm_flags & VM_PAT) {
 		/*
 		 * 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;
 		}
@@ -764,124 +697,95 @@ 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;
 }
 
 /*
- * track_pfn_vma_new is called when a _new_ pfn mapping is being established
- * for physical range indicated by pfn and size.
- *
  * 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 track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
+		    unsigned long pfn, unsigned long addr, 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;
+	resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
+	unsigned long flags;
+
+	/* reserve the whole chunk starting from paddr */
+	if (addr == vma->vm_start && size == (vma->vm_end - vma->vm_start)) {
+		int ret;
+
+		ret = reserve_pfn_range(paddr, size, prot, 0);
+		if (!ret)
+			vma->vm_flags |= VM_PAT;
+		return ret;
+	}
 
 	if (!pat_enabled)
 		return 0;
 
-	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);
-	}
+	/*
+	 * For anything smaller than the vma size we set prot based on the
+	 * lookup.
+	 */
+	flags = lookup_memtype(paddr);
 
-	/* 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;
+	/* Check memtype for the remaining pages */
+	while (size > PAGE_SIZE) {
+		size -= PAGE_SIZE;
+		paddr += PAGE_SIZE;
+		if (flags != lookup_memtype(paddr))
+			return -EINVAL;
 	}
+
+	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+			 flags);
+
 	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);
-	}
+int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
+		     unsigned long pfn)
+{
+	unsigned long flags;
+
+	if (!pat_enabled)
+		return 0;
 
-	return retval;
+	/* Set prot based on lookup */
+	flags = lookup_memtype((resource_size_t)pfn << PAGE_SHIFT);
+	*prot = __pgprot((pgprot_val(vma->vm_page_prot) & (~_PAGE_CACHE_MASK)) |
+			 flags);
+
+	return 0;
 }
 
 /*
- * 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 size can be zero).
+ * can be for the entire vma (in which case pfn, size are zero).
  */
-void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
-			unsigned long size)
+void untrack_pfn(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;
-
-	if (!pat_enabled)
-		return;
 
-	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);
+	if (!(vma->vm_flags & VM_PAT))
 		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);
+	/* free the chunk starting from pfn or the whole chunk */
+	paddr = (resource_size_t)pfn << PAGE_SHIFT;
+	if (!paddr && !size) {
+		if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) {
+			WARN_ON_ONCE(1);
+			return;
 		}
-	} 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);
-		}
+		size = vma->vm_end - vma->vm_start;
 	}
+	free_pfn_range(paddr, size);
+	vma->vm_flags &= ~VM_PAT;
 }
 
 pgprot_t pgprot_writecombine(pgprot_t prot)
@@ -895,29 +799,25 @@ EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
-/* get Nth element of the linked list */
 static struct memtype *memtype_get_idx(loff_t pos)
 {
-	struct memtype *list_node, *print_entry;
-	int i = 1;
+	struct memtype *print_entry;
+	int ret;
 
-	print_entry  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
+	print_entry  = kzalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!print_entry)
 		return NULL;
 
 	spin_lock(&memtype_lock);
-	list_for_each_entry(list_node, &memtype_list, nd) {
-		if (pos == i) {
-			*print_entry = *list_node;
-			spin_unlock(&memtype_lock);
-			return print_entry;
-		}
-		++i;
-	}
+	ret = rbt_memtype_copy_nth_element(print_entry, pos);
 	spin_unlock(&memtype_lock);
-	kfree(print_entry);
 
-	return NULL;
+	if (!ret) {
+		return print_entry;
+	} else {
+		kfree(print_entry);
+		return NULL;
+	}
 }
 
 static void *memtype_seq_start(struct seq_file *seq, loff_t *pos)
@@ -951,7 +851,7 @@ static int memtype_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
-static struct seq_operations memtype_seq_ops = {
+static const struct seq_operations memtype_seq_ops = {
 	.start = memtype_seq_start,
 	.next  = memtype_seq_next,
 	.stop  = memtype_seq_stop,
@@ -972,8 +872,10 @@ static const struct file_operations memtype_fops = {
 
 static int __init pat_memtype_list_init(void)
 {
-	debugfs_create_file("pat_memtype_list", S_IRUSR, arch_debugfs_dir,
-				NULL, &memtype_fops);
+	if (pat_enabled) {
+		debugfs_create_file("pat_memtype_list", S_IRUSR,
+				    arch_debugfs_dir, NULL, &memtype_fops);
+	}
 	return 0;
 }