x86: track memtype for RAM in page struct

Track the memtype for RAM pages in page struct instead of using the
memtype list. This avoids the explosion in the number of entries in
memtype list (of the order of 20,000 with AGP) and makes the PAT
tracking simpler.

We are using PG_arch_1 bit in page->flags.

We still use the memtype list for non RAM pages.

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 105 insertions, 0 deletions

diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index d4b6e6a29ae..d03c461e045 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -83,6 +83,25 @@ int page_is_ram(unsigned long pagenr)
 	return 0;
 }
 
+int pagerange_is_ram(unsigned long start, unsigned long end)
+{
+	int ram_page = 0, not_rampage = 0;
+	unsigned long page_nr;
+
+	for (page_nr = (start >> PAGE_SHIFT); page_nr < (end >> PAGE_SHIFT);
+	     ++page_nr) {
+		if (page_is_ram(page_nr))
+			ram_page = 1;
+		else
+			not_rampage = 1;
+
+		if (ram_page == not_rampage)
+			return -1;
+	}
+
+	return ram_page;
+}
+
 /*
  * Fix up the linear direct mapping of the kernel to avoid cache attribute
  * conflicts.
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index f049b1d6ebd..aceb6c7c6db 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -211,6 +211,75 @@ static struct memtype *cached_entry;
 static u64 cached_start;
 
 /*
+ * RED-PEN:  TODO: Add PageReserved() check as well here,
+ * once we add SetPageReserved() to all the drivers using
+ * set_memory_* or set_pages_*.
+ *
+ * This will help prevent accidentally freeing pages
+ * before setting the attribute back to WB.
+ */
+
+/*
+ * 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.
+ */
+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;
+
+	for (pfn = (start >> PAGE_SHIFT); pfn < (end >> PAGE_SHIFT); ++pfn) {
+		page = pfn_to_page(pfn);
+		if (page_mapped(page) || PageNonWB(page))
+			goto out;
+
+		SetPageNonWB(page);
+	}
+	return 0;
+
+out:
+	end_pfn = pfn;
+	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+		page = pfn_to_page(pfn);
+		ClearPageNonWB(page);
+	}
+
+	return -EINVAL;
+}
+
+static int free_ram_pages_type(u64 start, u64 end)
+{
+	struct page *page;
+	u64 pfn, end_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);
+	}
+	return 0;
+
+out:
+	end_pfn = pfn;
+	for (pfn = (start >> PAGE_SHIFT); pfn < end_pfn; ++pfn) {
+		page = pfn_to_page(pfn);
+		SetPageNonWB(page);
+	}
+	return -EINVAL;
+}
+
+/*
  * req_type typically has one of the:
  * - _PAGE_CACHE_WB
  * - _PAGE_CACHE_WC
@@ -232,6 +301,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 	unsigned long actual_type;
 	struct list_head *where;
 	int err = 0;
+	int is_range_ram;
 
  	BUG_ON(start >= end); /* end is exclusive */
 
@@ -270,6 +340,12 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type,
 		actual_type = pat_x_mtrr_type(start, end,
 					      req_type & _PAGE_CACHE_MASK);
 
+	is_range_ram = 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)
+		return -EINVAL;
+
 	new  = kmalloc(sizeof(struct memtype), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
@@ -358,6 +434,7 @@ int free_memtype(u64 start, u64 end)
 {
 	struct memtype *entry;
 	int err = -EINVAL;
+	int is_range_ram;
 
 	if (!pat_enabled)
 		return 0;
@@ -366,6 +443,12 @@ int free_memtype(u64 start, u64 end)
 	if (is_ISA_range(start, end - 1))
 		return 0;
 
+	is_range_ram = pagerange_is_ram(start, end);
+	if (is_range_ram == 1)
+		return free_ram_pages_type(start, end);
+	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) {
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
index 8e205a13125..092b9b4eb00 100644
--- a/include/asm-x86/cacheflush.h
+++ b/include/asm-x86/cacheflush.h
@@ -24,6 +24,8 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
 	memcpy((dst), (src), (len))
 
+#define PG_non_WB				PG_arch_1
+PAGEFLAG(NonWB, non_WB)
 
 /*
  * The set_memory_* API can be used to change various attributes of a virtual
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
index 49982110e4d..3407ac12ba3 100644
--- a/include/asm-x86/page.h
+++ b/include/asm-x86/page.h
@@ -57,6 +57,7 @@ typedef struct { pgdval_t pgd; } pgd_t;
 typedef struct { pgprotval_t pgprot; } pgprot_t;
 
 extern int page_is_ram(unsigned long pagenr);
+extern int pagerange_is_ram(unsigned long start, unsigned long end);
 extern int devmem_is_allowed(unsigned long pagenr);
 extern void map_devmem(unsigned long pfn, unsigned long size,
 		       pgprot_t vma_prot);