x86_64: fix e820_hole_size based on address ranges

e820_hole_size() now uses the newly extracted helper function,
e820_find_active_region(), to determine the size of usable RAM in a range of
PFN's.

This was previously broken because of two reasons:

 - The start and end PFN's of each e820 entry were not properly rounded
   prior to excluding those entries in the range, and

 - Entries smaller than a page were not properly excluded from being
   accumulated.

This resulted in emulated nodes being incorrectly mapped to ranges that
were completely reserved and not candidates for being registered as
active ranges.

Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 2570643..62e051b 100644 (file)
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -193,37 +193,6 @@ unsigned long __init e820_end_of_ram(void)
        return end_pfn; 
 }
 
        return end_pfn; 
 }
 

-/*
- * Find the hole size in the range.
- */
-unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
-{
-       unsigned long ram = 0;
-       int i;
-
-       for (i = 0; i < e820.nr_map; i++) {
-               struct e820entry *ei = &e820.map[i];
-               unsigned long last, addr;
-
-               if (ei->type != E820_RAM ||
-                   ei->addr+ei->size <= start ||
-                   ei->addr >= end)
-                       continue;
-
-               addr = round_up(ei->addr, PAGE_SIZE);
-               if (addr < start)
-                       addr = start;
-
-               last = round_down(ei->addr + ei->size, PAGE_SIZE);
-               if (last >= end)
-                       last = end;
-
-               if (last > addr)
-                       ram += last - addr;
-       }
-       return ((end - start) - ram);
-}
-

 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */
 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */


@@ -364,6 +333,29 @@ void __init add_memory_region(unsigned long start, unsigned long size, int type)
        e820.nr_map++;
 }
 
        e820.nr_map++;
 }
 

+/*
+ * Find the hole size (in bytes) in the memory range.
+ * @start: starting address of the memory range to scan
+ * @end: ending address of the memory range to scan
+ */
+unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
+{
+       unsigned long start_pfn = start >> PAGE_SHIFT;
+       unsigned long end_pfn = end >> PAGE_SHIFT;
+       unsigned long ei_startpfn;
+       unsigned long ei_endpfn;
+       unsigned long ram = 0;
+       int i;
+
+       for (i = 0; i < e820.nr_map; i++) {
+               if (e820_find_active_region(&e820.map[i],
+                                           start_pfn, end_pfn,
+                                           &ei_startpfn, &ei_endpfn))
+                       ram += ei_endpfn - ei_startpfn;
+       }
+       return end - start - (ram << PAGE_SHIFT);
+}
+

 void __init e820_print_map(char *who)
 {
        int i;
 void __init e820_print_map(char *who)
 {
        int i;

diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 30bf804..0191b1c 100644 (file)
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -273,9 +273,6 @@ void __init numa_init_array(void)
 
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */
 
 #ifdef CONFIG_NUMA_EMU
 /* Numa emulation */

-#define E820_ADDR_HOLE_SIZE(start, end)                                        \
-       (e820_hole_size((start) >> PAGE_SHIFT, (end) >> PAGE_SHIFT) <<  \
-       PAGE_SHIFT)

 char *cmdline __initdata;
 
 /*
 char *cmdline __initdata;
 
 /*


@@ -319,7 +316,7 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
                return -1;
        if (num_nodes > MAX_NUMNODES)
                num_nodes = MAX_NUMNODES;
                return -1;
        if (num_nodes > MAX_NUMNODES)
                num_nodes = MAX_NUMNODES;

-       size = (max_addr - *addr - E820_ADDR_HOLE_SIZE(*addr, max_addr)) /
+       size = (max_addr - *addr - e820_hole_size(*addr, max_addr)) /

               num_nodes;
        /*
         * Calculate the number of big nodes that can be allocated as a result
               num_nodes;
        /*
         * Calculate the number of big nodes that can be allocated as a result


@@ -347,7 +344,7 @@ static int __init split_nodes_equally(struct bootnode *nodes, u64 *addr,
                if (i == num_nodes + node_start - 1)
                        end = max_addr;
                else
                if (i == num_nodes + node_start - 1)
                        end = max_addr;
                else

-                       while (end - *addr - E820_ADDR_HOLE_SIZE(*addr, end) <
+                       while (end - *addr - e820_hole_size(*addr, end) <

                               size) {
                                end += FAKE_NODE_MIN_SIZE;
                                if (end > max_addr) {
                               size) {
                                end += FAKE_NODE_MIN_SIZE;
                                if (end > max_addr) {


@@ -488,7 +485,6 @@ out:
        numa_init_array();
        return 0;
 }
        numa_init_array();
        return 0;
 }

-#undef E820_ADDR_HOLE_SIZE

 #endif /* CONFIG_NUMA_EMU */
 
 void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
 #endif /* CONFIG_NUMA_EMU */
 
 void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)