[PATCH] Have x86_64 use add_active_range() and free_area_init_nodes

Size zones and holes in an architecture independent manner for x86_64.

Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Andi Kleen <ak@muc.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Keith Mannthey" <kmannth@gmail.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 51 insertions, 81 deletions

diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index c0af3828df45..b3f0908668ec 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -162,59 +162,14 @@ unsigned long __init find_e820_area(unsigned long start, unsigned long end, unsi
         return -1UL;            
 } 
 
-/* 
- * Free bootmem based on the e820 table for a node.
- */
-void __init e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end)
-{
-        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 && last-addr >= PAGE_SIZE)
-                        free_bootmem_node(pgdat, addr, last-addr);
-        }
-}
-
 /*
  * Find the highest page frame number we have available
  */
 unsigned long __init e820_end_of_ram(void)
 {
-        int i;
         unsigned long end_pfn = 0;
+        end_pfn = find_max_pfn_with_active_regions();
         
-        for (i = 0; i < e820.nr_map; i++) {
-                struct e820entry *ei = &e820.map[i]; 
-                unsigned long start, end;
-
-                start = round_up(ei->addr, PAGE_SIZE); 
-                end = round_down(ei->addr + ei->size, PAGE_SIZE); 
-                if (start >= end)
-                        continue;
-                if (ei->type == E820_RAM) { 
-                if (end > end_pfn<<PAGE_SHIFT)
-                        end_pfn = end>>PAGE_SHIFT;
-                } else { 
-                        if (end > end_pfn_map<<PAGE_SHIFT) 
-                                end_pfn_map = end>>PAGE_SHIFT;
-                } 
-        }
-
         if (end_pfn > end_pfn_map) 
                 end_pfn_map = end_pfn;
         if (end_pfn_map > MAXMEM>>PAGE_SHIFT)
@@ -224,43 +179,10 @@ unsigned long __init e820_end_of_ram(void)
         if (end_pfn > end_pfn_map) 
                 end_pfn = end_pfn_map; 
 
+        printk("end_pfn_map = %lu\n", end_pfn_map);
         return end_pfn; 
 }
 
-/* 
- * Compute how much memory is missing in a range.
- * Unlike the other functions in this file the arguments are in page numbers.
- */
-unsigned long __init
-e820_hole_size(unsigned long start_pfn, unsigned long end_pfn)
-{
-        unsigned long ram = 0;
-        unsigned long start = start_pfn << PAGE_SHIFT;
-        unsigned long end = end_pfn << PAGE_SHIFT;
-        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) >> PAGE_SHIFT;
-}
-
 /*
  * Mark e820 reserved areas as busy for the resource manager.
  */
@@ -342,6 +264,49 @@ void __init e820_mark_nosave_regions(void)
         }
 }
 
+/* Walk the e820 map and register active regions within a node */
+void __init
+e820_register_active_regions(int nid, unsigned long start_pfn,
+                                                        unsigned long end_pfn)
+{
+        int i;
+        unsigned long ei_startpfn, ei_endpfn;
+        for (i = 0; i < e820.nr_map; i++) {
+                struct e820entry *ei = &e820.map[i];
+                ei_startpfn = round_up(ei->addr, PAGE_SIZE) >> PAGE_SHIFT;
+                ei_endpfn = round_down(ei->addr + ei->size, PAGE_SIZE)
+                                                                >> PAGE_SHIFT;
+
+                /* Skip map entries smaller than a page */
+                if (ei_startpfn > ei_endpfn)
+                        continue;
+
+                /* Check if end_pfn_map should be updated */
+                if (ei->type != E820_RAM && ei_endpfn > end_pfn_map)
+                        end_pfn_map = ei_endpfn;
+
+                /* Skip if map is outside the node */
+                if (ei->type != E820_RAM ||
+                                ei_endpfn <= start_pfn ||
+                                ei_startpfn >= end_pfn)
+                        continue;
+
+                /* Check for overlaps */
+                if (ei_startpfn < start_pfn)
+                        ei_startpfn = start_pfn;
+                if (ei_endpfn > end_pfn)
+                        ei_endpfn = end_pfn;
+
+                /* Obey end_user_pfn to save on memmap */
+                if (ei_startpfn >= end_user_pfn)
+                        continue;
+                if (ei_endpfn > end_user_pfn)
+                        ei_endpfn = end_user_pfn;
+
+                add_active_range(nid, ei_startpfn, ei_endpfn);
+        }
+}
+
 /* 
  * 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 f98e48cae6da..0b00bb2ea576 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -292,7 +292,8 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
         if (bootmap == -1L)
                 panic("Cannot find bootmem map of size %ld\n",bootmap_size);
         bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
-        e820_bootmem_free(NODE_DATA(0), 0, end_pfn << PAGE_SHIFT);
+        e820_register_active_regions(0, start_pfn, end_pfn);
+        free_bootmem_with_active_regions(0, end_pfn);
         reserve_bootmem(bootmap, bootmap_size);
 } 
 #endif
@@ -384,6 +385,7 @@ void __init setup_arch(char **cmdline_p)
 
         finish_e820_parsing();
 
+        e820_register_active_regions(0, 0, -1UL);
         /*
          * partially used pages are not usable - thus
          * we are rounding upwards:
@@ -414,6 +416,9 @@ void __init setup_arch(char **cmdline_p)
         max_pfn = end_pfn;
         high_memory = (void *)__va(end_pfn * PAGE_SIZE - 1) + 1;
 
+        /* Remove active ranges so rediscovery with NUMA-awareness happens */
+        remove_all_active_ranges();
+
 #ifdef CONFIG_ACPI_NUMA
         /*
          * Parse SRAT to discover nodes.