Merge branch 'x86-pat-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-pat-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, pat: Update the page flags for memtype atomically instead of using memtype_lock
  x86, pat: In rbt_memtype_check_insert(), update new->type only if valid
  x86, pat: Migrate to rbtree only backend for pat memtype management
  x86, pat: Preparatory changes in pat.c for bigger rbtree change
  rbtree: Add support for augmented rbtrees

8 files changed, 470 insertions, 244 deletions

diff --git a/Documentation/rbtree.txt b/Documentation/rbtree.txt
index aae8355d3166..221f38be98f4 100644
--- a/Documentation/rbtree.txt
+++ b/Documentation/rbtree.txt
@@ -190,3 +190,61 @@ Example:
   for (node = rb_first(&mytree); node; node = rb_next(node))
         printk("key=%s\n", rb_entry(node, struct mytype, node)->keystring);
 
+Support for Augmented rbtrees
+-----------------------------
+
+Augmented rbtree is an rbtree with "some" additional data stored in each node.
+This data can be used to augment some new functionality to rbtree.
+Augmented rbtree is an optional feature built on top of basic rbtree
+infrastructure. rbtree user who wants this feature will have an augment
+callback function in rb_root initialized.
+
+This callback function will be called from rbtree core routines whenever
+a node has a change in one or both of its children. It is the responsibility
+of the callback function to recalculate the additional data that is in the
+rb node using new children information. Note that if this new additional
+data affects the parent node's additional data, then callback function has
+to handle it and do the recursive updates.
+
+
+Interval tree is an example of augmented rb tree. Reference -
+"Introduction to Algorithms" by Cormen, Leiserson, Rivest and Stein.
+More details about interval trees:
+
+Classical rbtree has a single key and it cannot be directly used to store
+interval ranges like [lo:hi] and do a quick lookup for any overlap with a new
+lo:hi or to find whether there is an exact match for a new lo:hi.
+
+However, rbtree can be augmented to store such interval ranges in a structured
+way making it possible to do efficient lookup and exact match.
+
+This "extra information" stored in each node is the maximum hi
+(max_hi) value among all the nodes that are its descendents. This
+information can be maintained at each node just be looking at the node
+and its immediate children. And this will be used in O(log n) lookup
+for lowest match (lowest start address among all possible matches)
+with something like:
+
+find_lowest_match(lo, hi, node)
+{
+        lowest_match = NULL;
+        while (node) {
+                if (max_hi(node->left) > lo) {
+                        // Lowest overlap if any must be on left side
+                        node = node->left;
+                } else if (overlap(lo, hi, node)) {
+                        lowest_match = node;
+                        break;
+                } else if (lo > node->lo) {
+                        // Lowest overlap if any must be on right side
+                        node = node->right;
+                } else {
+                        break;
+                }
+        }
+        return lowest_match;
+}
+
+Finding exact match will be to first find lowest match and then to follow
+successor nodes looking for exact match, until the start of a node is beyond
+the hi value we are looking for.
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 634c40a739a6..c70068d05f70 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -44,9 +44,6 @@ static inline void copy_from_user_page(struct vm_area_struct *vma,
         memcpy(dst, src, len);
 }
 
-#define PG_WC                           PG_arch_1
-PAGEFLAG(WC, WC)
-
 #ifdef CONFIG_X86_PAT
 /*
  * X86 PAT uses page flags WC and Uncached together to keep track of
@@ -55,16 +52,24 @@ PAGEFLAG(WC, WC)
  * _PAGE_CACHE_UC_MINUS and fourth state where page's memory type has not
  * been changed from its default (value of -1 used to denote this).
  * Note we do not support _PAGE_CACHE_UC here.
- *
- * Caller must hold memtype_lock for atomicity.
  */
+
+#define _PGMT_DEFAULT           0
+#define _PGMT_WC                (1UL << PG_arch_1)
+#define _PGMT_UC_MINUS          (1UL << PG_uncached)
+#define _PGMT_WB                (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_MASK              (1UL << PG_uncached | 1UL << PG_arch_1)
+#define _PGMT_CLEAR_MASK        (~_PGMT_MASK)
+
 static inline unsigned long get_page_memtype(struct page *pg)
 {
-        if (!PageUncached(pg) && !PageWC(pg))
+        unsigned long pg_flags = pg->flags & _PGMT_MASK;
+
+        if (pg_flags == _PGMT_DEFAULT)
                 return -1;
-        else if (!PageUncached(pg) && PageWC(pg))
+        else if (pg_flags == _PGMT_WC)
                 return _PAGE_CACHE_WC;
-        else if (PageUncached(pg) && !PageWC(pg))
+        else if (pg_flags == _PGMT_UC_MINUS)
                 return _PAGE_CACHE_UC_MINUS;
         else
                 return _PAGE_CACHE_WB;
@@ -72,25 +77,26 @@ static inline unsigned long get_page_memtype(struct page *pg)
 
 static inline void set_page_memtype(struct page *pg, unsigned long memtype)
 {
+        unsigned long memtype_flags = _PGMT_DEFAULT;
+        unsigned long old_flags;
+        unsigned long new_flags;
+
         switch (memtype) {
         case _PAGE_CACHE_WC:
-                ClearPageUncached(pg);
-                SetPageWC(pg);
+                memtype_flags = _PGMT_WC;
                 break;
         case _PAGE_CACHE_UC_MINUS:
-                SetPageUncached(pg);
-                ClearPageWC(pg);
+                memtype_flags = _PGMT_UC_MINUS;
                 break;
         case _PAGE_CACHE_WB:
-                SetPageUncached(pg);
-                SetPageWC(pg);
-                break;
-        default:
-        case -1:
-                ClearPageUncached(pg);
-                ClearPageWC(pg);
+                memtype_flags = _PGMT_WB;
                 break;
         }
+
+        do {
+                old_flags = pg->flags;
+                new_flags = (old_flags & _PGMT_CLEAR_MASK) | memtype_flags;
+        } while (cmpxchg(&pg->flags, old_flags, new_flags) != old_flags);
 }
 #else
 static inline unsigned long get_page_memtype(struct page *pg) { return -1; }
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 06630d26e56d..a4c768397baa 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -6,6 +6,7 @@ nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_physaddr.o               := $(nostackp)
 CFLAGS_setup_nx.o               := $(nostackp)
 
+obj-$(CONFIG_X86_PAT)           += pat_rbtree.o
 obj-$(CONFIG_SMP)               += tlb.o
 
 obj-$(CONFIG_X86_32)            += pgtable_32.o iomap_32.o
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edc8b95afc1a..bbe5502ee1cb 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -30,6 +30,8 @@
 #include <asm/pat.h>
 #include <asm/io.h>
 
+#include "pat_internal.h"