[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>

9 files changed, 84 insertions, 158 deletions

diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index efe249e7d6b3..326aff7a87ea 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -85,6 +85,9 @@ config ARCH_MAY_HAVE_PC_FDC
         bool
         default y
 
+config ARCH_POPULATES_NODE_MAP
+        def_bool y
+
 config DMI
         bool
         default y
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.
diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c
index 1e4669fa5734..47928399e38a 100644
--- a/arch/x86_64/mm/init.c
+++ b/arch/x86_64/mm/init.c
@@ -403,69 +403,15 @@ void __cpuinit zap_low_mappings(int cpu)
         __flush_tlb_all();
 }
 
-/* Compute zone sizes for the DMA and DMA32 zones in a node. */
-__init void
-size_zones(unsigned long *z, unsigned long *h,
-           unsigned long start_pfn, unsigned long end_pfn)
-{
-        int i;
-        unsigned long w;
-
-        for (i = 0; i < MAX_NR_ZONES; i++)
-                z[i] = 0;
-
-        if (start_pfn < MAX_DMA_PFN)
-                z[ZONE_DMA] = MAX_DMA_PFN - start_pfn;
-        if (start_pfn < MAX_DMA32_PFN) {
-                unsigned long dma32_pfn = MAX_DMA32_PFN;
-                if (dma32_pfn > end_pfn)
-                        dma32_pfn = end_pfn;
-                z[ZONE_DMA32] = dma32_pfn - start_pfn;
-        }
-        z[ZONE_NORMAL] = end_pfn - start_pfn;
-
-        /* Remove lower zones from higher ones. */
-        w = 0;
-        for (i = 0; i < MAX_NR_ZONES; i++) {
-                if (z[i])
-                        z[i] -= w;
-                w += z[i];
-        }
-
-        /* Compute holes */
-        w = start_pfn;
-        for (i = 0; i < MAX_NR_ZONES; i++) {
-                unsigned long s = w;
-                w += z[i];
-                h[i] = e820_hole_size(s, w);
-        }
-
-        /* Add the space pace needed for mem_map to the holes too. */
-        for (i = 0; i < MAX_NR_ZONES; i++)
-                h[i] += (z[i] * sizeof(struct page)) / PAGE_SIZE;
-
-        /* The 16MB DMA zone has the kernel and other misc mappings.
-           Account them too */
-        if (h[ZONE_DMA]) {
-                h[ZONE_DMA] += dma_reserve;
-                if (h[ZONE_DMA] >= z[ZONE_DMA]) {
-                        printk(KERN_WARNING
-                                "Kernel too large and filling up ZONE_DMA?\n");
-                        h[ZONE_DMA] = z[ZONE_DMA];
-                }
-        }
-}
-
 #ifndef CONFIG_NUMA
 void __init paging_init(void)
 {
-        unsigned long zones[MAX_NR_ZONES], holes[MAX_NR_ZONES];
-
+        unsigned long max_zone_pfns[MAX_NR_ZONES] = {MAX_DMA_PFN,
+                                                        MAX_DMA32_PFN,
+                                                        end_pfn};
         memory_present(0, 0, end_pfn);
         sparse_init();
-        size_zones(zones, holes, 0, end_pfn);
-        free_area_init_node(0, NODE_DATA(0), zones,
-                            __pa(PAGE_OFFSET) >> PAGE_SHIFT, holes);
+        free_area_init_nodes(max_zone_pfns);
 }
 #endif
 
@@ -608,7 +554,8 @@ void __init mem_init(void)
 #else
         totalram_pages = free_all_bootmem();
 #endif
-        reservedpages = end_pfn - totalram_pages - e820_hole_size(0, end_pfn);
+        reservedpages = end_pfn - totalram_pages -
+                                        absent_pages_in_range(0, end_pfn);
 
         after_bootmem = 1;
 
diff --git a/arch/x86_64/mm/k8topology.c b/arch/x86_64/mm/k8topology.c
index 5cf594f9230d..b5b8dba28b4e 100644
--- a/arch/x86_64/mm/k8topology.c
+++ b/arch/x86_64/mm/k8topology.c
@@ -149,6 +149,9 @@ int __init k8_scan_nodes(unsigned long start, unsigned long end)
                 
                 nodes[nodeid].start = base; 
                 nodes[nodeid].end = limit;
+                e820_register_active_regions(nodeid,
+                                nodes[nodeid].start >> PAGE_SHIFT,
+                                nodes[nodeid].end >> PAGE_SHIFT);
 
                 prevbase = base;
 
diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c
index 322bf45fc36a..829a008bd39b 100644
--- a/arch/x86_64/mm/numa.c
+++ b/arch/x86_64/mm/numa.c
@@ -161,7 +161,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
                                          bootmap_start >> PAGE_SHIFT, 
                                          start_pfn, end_pfn); 
 
-        e820_bootmem_free(NODE_DATA(nodeid), start, end);
+        free_bootmem_with_active_regions(nodeid, end);
 
         reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size); 
         reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start, bootmap_pages<<PAGE_SHIFT);
@@ -175,13 +175,11 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en
 void __init setup_node_zones(int nodeid)
 { 
         unsigned long start_pfn, end_pfn, memmapsize, limit;
-        unsigned long zones[MAX_NR_ZONES];
-        unsigned long holes[MAX_NR_ZONES];
 
         start_pfn = node_start_pfn(nodeid);
         end_pfn = node_end_pfn(nodeid);
 
-        Dprintk(KERN_INFO "Setting up node %d %lx-%lx\n",
+        Dprintk(KERN_INFO "Setting up memmap for node %d %lx-%lx\n",
                 nodeid, start_pfn, end_pfn);
 
         /* Try to allocate mem_map at end to not fill up precious <4GB
@@ -195,10 +193,6 @@ void __init setup_node_zones(int nodeid)
                                 round_down(limit - memmapsize, PAGE_SIZE), 
                                 limit);
 #endif
-
-        size_zones(zones, holes, start_pfn, end_pfn);
-        free_area_init_node(nodeid, NODE_DATA(nodeid), zones,
-                            start_pfn, holes);
 } 
 
 void __init numa_init_array(void)
@@ -259,8 +253,11 @@ static int __init numa_emulation(unsigned long start_pfn, unsigned long end_pfn)
                 printk(KERN_ERR "No NUMA hash function found. Emulation disabled.\n");
                 return -1;
         }
-        for_each_online_node(i)
+        for_each_online_node(i) {
+                e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT,
+                                                nodes[i].end >> PAGE_SHIFT);
                 setup_node_bootmem(i, nodes[i].start, nodes[i].end);
+        }
         numa_init_array();
         return 0;
 }
@@ -299,6 +296,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
         for (i = 0; i < NR_CPUS; i++)
                 numa_set_node(i, 0);
         node_to_cpumask[0] = cpumask_of_cpu(0);
+        e820_register_active_regions(0, start_pfn, end_pfn);
         setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
 }
 
@@ -340,12 +338,17 @@ static void __init arch_sparse_init(void)
 void __init paging_init(void)
 { 
         int i;
+        unsigned long max_zone_pfns[MAX_NR_ZONES] = { MAX_DMA_PFN,
+                MAX_DMA32_PFN,
+                end_pfn};
 
         arch_sparse_init();
 
         for_each_online_node(i) {
                 setup_node_zones(i); 
         }
+
+        free_area_init_nodes(max_zone_pfns);
 } 
 
 static __init int numa_setup(char *opt)
diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c
index ca10701e7a90..7b50bb1caabe 100644
--- a/arch/x86_64/mm/srat.c
+++ b/arch/x86_64/mm/srat.c
@@ -93,6 +93,7 @@ static __init void bad_srat(void)
                 apicid_to_node[i] = NUMA_NO_NODE;
         for (i = 0; i < MAX_NUMNODES; i++)
                 nodes_add[i].start = nodes[i].end = 0;
+        remove_all_active_ranges();
 }
 
 static __init inline int srat_disabled(void)
@@ -175,7 +176,7 @@ static int hotadd_enough_memory(struct bootnode *nd)
 
         if (mem < 0)
                 return 0;
-        allowed = (end_pfn - e820_hole_size(0, end_pfn)) * PAGE_SIZE;
+        allowed = (end_pfn - absent_pages_in_range(0, end_pfn)) * PAGE_SIZE;
         allowed = (allowed / 100) * hotadd_percent;
         if (allocated + mem > allowed) {
                 unsigned long range;
@@ -225,7 +226,7 @@ static int reserve_hotadd(int node, unsigned long start, unsigned long end)
         }
 
         /* This check might be a bit too strict, but I'm keeping it for now. */
-        if (e820_hole_size(s_pfn, e_pfn) != e_pfn - s_pfn) {
+        if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) {
                 printk(KERN_ERR "SRAT: Hotplug area has existing memory\n");
                 return -1;
         }
@@ -319,6 +320,8 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma)
 
         printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm,
                nd->start, nd->end);
+        e820_register_active_regions(node, nd->start >> PAGE_SHIFT,
+                                                nd->end >> PAGE_SHIFT);
 
 #ifdef RESERVE_HOTADD
         if (ma->flags.hot_pluggable && reserve_hotadd(node, start, end) < 0) {
@@ -343,13 +346,13 @@ static int nodes_cover_memory(void)
                 unsigned long s = nodes[i].start >> PAGE_SHIFT;
                 unsigned long e = nodes[i].end >> PAGE_SHIFT;
                 pxmram += e - s;
-                pxmram -= e820_hole_size(s, e);
+                pxmram -= absent_pages_in_range(s, e);
                 pxmram -= nodes_add[i].end - nodes_add[i].start;
                 if ((long)pxmram < 0)
                         pxmram = 0;
         }
 
-        e820ram = end_pfn - e820_hole_size(0, end_pfn);
+        e820ram = end_pfn - absent_pages_in_range(0, end_pfn);
         /* We seem to lose 3 pages somewhere. Allow a bit of slack. */
         if ((long)(e820ram - pxmram) >= 1*1024*1024) {
                 printk(KERN_ERR
diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h
index e15d3c8628f3..fa2086774105 100644
--- a/include/asm-x86_64/e820.h
+++ b/include/asm-x86_64/e820.h
@@ -47,10 +47,9 @@ 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);
 
-extern void e820_bootmem_free(pg_data_t *pgdat, unsigned long start,unsigned long end);
 extern void e820_setup_gap(void);
-extern unsigned long e820_hole_size(unsigned long start_pfn,
-                                    unsigned long end_pfn);
+extern void e820_register_active_regions(int nid,
+                                unsigned long start_pfn, unsigned long end_pfn);
 
 extern void finish_e820_parsing(void);
 
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index b73d0c76613c..c28fc2db2171 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -24,8 +24,6 @@ extern void mtrr_bp_init(void);
 #define mtrr_bp_init() do {} while (0)
 #endif
 extern void init_memory_mapping(unsigned long start, unsigned long end);
-extern void size_zones(unsigned long *z, unsigned long *h,
-                        unsigned long start_pfn, unsigned long end_pfn);
 
 extern void system_call(void); 
 extern int kernel_syscall(void);