[PATCH] Make swsusp avoid memory holes and reserved memory regions on x86_64

On x86_64 machines with more than 2 GB of RAM there are large memory gaps
(with no corresponding kernel virtual addresses) and reserved memory
regions between areas of usable physical RAM.  Moreover, if CONFIG_FLATMEM
is set, they appear within the normal zone.  swsusp should not try to save
them, so the corresponding page structs have to be marked as 'nosave'.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Mel Gorman <mel@csn.ul.ie>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 50 insertions, 0 deletions

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index d6d7f731f6f0..708a3cd9a27e 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -16,6 +16,7 @@
 #include <linux/string.h>
 #include <linux/kexec.h>
 #include <linux/module.h>
+#include <linux/mm.h>
 
 #include <asm/pgtable.h>
 #include <asm/page.h>
@@ -297,6 +298,53 @@ void __init e820_reserve_resources(void)
         }
 }
 
+/* Mark pages corresponding to given address range as nosave */
+static void __init
+e820_mark_nosave_range(unsigned long start, unsigned long end)
+{
+        unsigned long pfn, max_pfn;
+
+        if (start >= end)
+                return;
+
+        printk("Nosave address range: %016lx - %016lx\n", start, end);
+        max_pfn = end >> PAGE_SHIFT;
+        for (pfn = start >> PAGE_SHIFT; pfn < max_pfn; pfn++)
+                if (pfn_valid(pfn))
+                        SetPageNosave(pfn_to_page(pfn));
+}
+
+/*
+ * Find the ranges of physical addresses that do not correspond to
+ * e820 RAM areas and mark the corresponding pages as nosave for software
+ * suspend and suspend to RAM.
+ *
+ * This function requires the e820 map to be sorted and without any
+ * overlapping entries and assumes the first e820 area to be RAM.
+ */
+void __init e820_mark_nosave_regions(void)
+{
+        int i;
+        unsigned long paddr;
+
+        paddr = round_down(e820.map[0].addr + e820.map[0].size, PAGE_SIZE);
+        for (i = 1; i < e820.nr_map; i++) {
+                struct e820entry *ei = &e820.map[i];
+
+                if (paddr < ei->addr)
+                        e820_mark_nosave_range(paddr,
+                                        round_up(ei->addr, PAGE_SIZE));
+
+                paddr = round_down(ei->addr + ei->size, PAGE_SIZE);
+                if (ei->type != E820_RAM)
+                        e820_mark_nosave_range(round_up(ei->addr, PAGE_SIZE),
+                                        paddr);
+
+                if (paddr >= (end_pfn << PAGE_SHIFT))
+                        break;
+        }
+}
+
 /* 
  * Add a memory region to the kernel e820 map.
  */ 
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 34afad704824..4b39f0da17f3 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -689,6 +689,7 @@ void __init setup_arch(char **cmdline_p)
          */
         probe_roms();
         e820_reserve_resources(); 
+        e820_mark_nosave_regions();
 
         request_resource(&iomem_resource, &video_ram_resource);
 
diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h
index 670a3388e70a..f65674832318 100644
--- a/include/asm-x86_64/e820.h
+++ b/include/asm-x86_64/e820.h
@@ -46,6 +46,7 @@ extern void setup_memory_region(void);
 extern void contig_e820_setup(void); 
 extern unsigned long e820_end_of_ram(void);
 extern void e820_reserve_resources(void);
+extern void e820_mark_nosave_regions(void);
 extern void e820_print_map(char *who);
 extern int e820_any_mapped(unsigned long start, unsigned long end, unsigned type);
 extern int e820_all_mapped(unsigned long start, unsigned long end, unsigned type);