[PATCH 1/5] x86: Only direct map addresses that are marked as E820_RAM

[Jacob Shin <jacob.shin@amd.com>]

Currently direct mappings are created for [ 0 to max_low_pfn<<PAGE_SHIFT )
and [ 4GB to max_pfn<<PAGE_SHIFT ), which may include regions that are not
backed by actual DRAM. This is fine for holes under 4GB which are covered
by fixed and variable range MTRRs to be UC. However, we run into trouble
on higher memory addresses which cannot be covered by MTRRs.

This patch iterates through e820 and only direct maps ranges that are
marked as E820_RAM, and keeps track of those pfn ranges.

Signed-off-by: Jacob Shin <jacob.shin@amd.com>
---
 arch/x86/include/asm/page_types.h |    9 ++++
 arch/x86/kernel/setup.c           |  108 +++++++++++++++++++++++++++++++------
 2 files changed, 101 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index e21fdd1..409047a 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -3,6 +3,7 @@
 
 #include <linux/const.h>
 #include <linux/types.h>
+#include <asm/e820.h>
 
 /* PAGE_SHIFT determines the page size */
 #define PAGE_SHIFT	12
@@ -40,12 +41,20 @@
 #endif	/* CONFIG_X86_64 */
 
 #ifndef __ASSEMBLY__
+#include <linux/range.h>
 
 extern int devmem_is_allowed(unsigned long pagenr);
 
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
+extern struct range pfn_mapped[E820_X_MAX];
+extern int nr_pfn_mapped;
+
+extern void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn);
+extern bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn);
+extern bool pfn_is_mapped(unsigned long pfn);
+
 static inline phys_addr_t get_max_mapped(void)
 {
 	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f4b9b80..f71fa310 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -115,13 +115,46 @@
 #include <asm/prom.h>
 
 /*
- * end_pfn only includes RAM, while max_pfn_mapped includes all e820 entries.
- * The direct mapping extends to max_pfn_mapped, so that we can directly access
- * apertures, ACPI and other tables without having to play with fixmaps.
+ * max_low_pfn_mapped: highest direct mapped pfn under 4GB
+ * max_pfn_mapped:     highest direct mapped pfn over 4GB
+ *
+ * The direct mapping only covers E820_RAM regions, so the ranges and gaps are
+ * represented by pfn_mapped
  */
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
+struct range pfn_mapped[E820_X_MAX];
+int nr_pfn_mapped;
+
+void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX,
+					     nr_pfn_mapped, start_pfn, end_pfn);
+
+	max_pfn_mapped = max(max_pfn_mapped, end_pfn);
+
+	if (end_pfn <= (1UL << (32 - PAGE_SHIFT)))
+		max_low_pfn_mapped = max(max_low_pfn_mapped, end_pfn);
+}
+
+bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn)
+{
+	int i;
+
+	for (i = 0; i < nr_pfn_mapped; i++)
+		if ((start_pfn >= pfn_mapped[i].start) &&
+		    (end_pfn <= pfn_mapped[i].end))
+			return true;
+
+	return false;
+}
+
+bool pfn_is_mapped(unsigned long pfn)
+{
+	return pfn_range_is_mapped(pfn, pfn + 1);
+}
+
 #ifdef CONFIG_DMI
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
@@ -296,6 +329,61 @@ static void __init cleanup_highmap(void)
 }
 #endif
 
+/*
+ * Iterate through E820 memory map and create direct mappings for only E820_RAM
+ * regions. We cannot simply create direct mappings for all pfns from
+ * [0 to max_low_pfn) and [4GB to max_pfn) because of possible memory holes in
+ * high addresses that cannot be marked as UC by fixed/variable range MTRRs.
+ */
+static void __init init_memory(void)
+{
+	int i;
+	unsigned long pfn;
+
+	init_gbpages();
+
+	for (i = 0; i < e820.nr_map; i++) {
+		struct e820entry *ei = &e820.map[i];
+		u64 start = ei->addr;
+		u64 end = ei->addr + ei->size;
+
+		/* we only map E820_RAM */
+		if (ei->type != E820_RAM)
+			continue;
+
+		/* except we need to ignore gaps under 1MB */
+		if (end <= ISA_END_ADDRESS)
+			continue;
+
+		/* expand the first entry that spans 1MB to start at 0 */
+		if (start <= ISA_END_ADDRESS)
+			start = 0;
+#ifdef CONFIG_X86_32
+		/* on 32 bit, we only map up to max_low_pfn */
+		if ((start >> PAGE_SHIFT) >= max_low_pfn)
+			continue;
+
+		if ((end >> PAGE_SHIFT) > max_low_pfn)
+			end = max_low_pfn << PAGE_SHIFT;
+#endif
+		pfn = init_memory_mapping(start, end);
+		add_pfn_range_mapped(start >> PAGE_SHIFT, pfn);
+	}
+
+	/* map 0 to 1MB if we haven't already */
+	if (!pfn_range_is_mapped(0, ISA_END_ADDRESS << PAGE_SHIFT)) {
+		pfn = init_memory_mapping(0, ISA_END_ADDRESS);
+		add_pfn_range_mapped(0, pfn);
+	}
+
+#ifdef CONFIG_X86_64
+	if (max_pfn > max_low_pfn) {
+		/* can we preseve max_low_pfn ?*/
+		max_low_pfn = max_pfn;
+	}
+#endif
+}
+
 static void __init reserve_brk(void)
 {
 	if (_brk_end > _brk_start)
@@ -911,20 +999,8 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_real_mode();
 
-	init_gbpages();
-
-	/* max_pfn_mapped is updated here */
-	max_low_pfn_mapped = init_memory_mapping(0, max_low_pfn<<PAGE_SHIFT);
-	max_pfn_mapped = max_low_pfn_mapped;
+	init_memory();
 
-#ifdef CONFIG_X86_64
-	if (max_pfn > max_low_pfn) {
-		max_pfn_mapped = init_memory_mapping(1UL<<32,
-						     max_pfn<<PAGE_SHIFT);
-		/* can we preseve max_low_pfn ?*/
-		max_low_pfn = max_pfn;
-	}
-#endif
 	memblock.current_limit = get_max_mapped();
 	dma_contiguous_reserve(0);
 
-- 
1.7.9.5