x86_64: fix setup_node_bootmem to support big mem excluding with memmap

typical case: four sockets system, every node has 4g ram, and we are using:

	memmap=10g$4g

to mask out memory on node1 and node2

when numa is enabled, early_node_mem is used to get node_data and node_bootmap.

if it can not get memory from the same node with find_e820_area(), it will
use alloc_bootmem to get buff from previous nodes.

so check it and print out some info about it.

need to move early_res_to_bootmem into every setup_node_bootmem.
and it takes range that node has. otherwise alloc_bootmem could return addr
that reserved early.

depends on "mm: make reserve_bootmem can crossed the nodes".

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 46 insertions, 12 deletions

diff --git a/arch/x86/kernel/e820_64.c b/arch/x86/kernel/e820_64.c
index 79f0d52fa99a..645ee5e32a27 100644
--- a/arch/x86/kernel/e820_64.c
+++ b/arch/x86/kernel/e820_64.c
@@ -106,14 +106,19 @@ void __init free_early(unsigned long start, unsigned long end)
         early_res[j - 1].end = 0;
 }
 
-void __init early_res_to_bootmem(void)
+void __init early_res_to_bootmem(unsigned long start, unsigned long end)
 {
         int i;
+        unsigned long final_start, final_end;
         for (i = 0; i < MAX_EARLY_RES && early_res[i].end; i++) {
                 struct early_res *r = &early_res[i];
-                printk(KERN_INFO "early res: %d [%lx-%lx] %s\n", i,
-                        r->start, r->end - 1, r->name);
-                reserve_bootmem_generic(r->start, r->end - r->start);
+                final_start = max(start, r->start);
+                final_end = min(end, r->end);
+                if (final_start >= final_end)
+                        continue;
+                printk(KERN_INFO "  early res: %d [%lx-%lx] %s\n", i,
+                        final_start, final_end - 1, r->name);
+                reserve_bootmem_generic(final_start, final_end - final_start);
         }
 }
 
diff --git a/arch/x86/kernel/setup_64.c b/arch/x86/kernel/setup_64.c
index b04e2c011e1a..60e64c8eee92 100644
--- a/arch/x86/kernel/setup_64.c
+++ b/arch/x86/kernel/setup_64.c
@@ -190,6 +190,7 @@ contig_initmem_init(unsigned long start_pfn, unsigned long end_pfn)
         bootmap_size = init_bootmem(bootmap >> PAGE_SHIFT, end_pfn);
         e820_register_active_regions(0, start_pfn, end_pfn);
         free_bootmem_with_active_regions(0, end_pfn);
+        early_res_to_bootmem(0, end_pfn<<PAGE_SHIFT);
         reserve_bootmem(bootmap, bootmap_size, BOOTMEM_DEFAULT);
 }
 #endif
@@ -421,8 +422,6 @@ void __init setup_arch(char **cmdline_p)
         contig_initmem_init(0, end_pfn);
 #endif
 
-        early_res_to_bootmem();
-
         dma32_reserve_bootmem();
 
 #ifdef CONFIG_ACPI_SLEEP
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 9a6892200b27..c5066d519e5d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -196,6 +196,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
         unsigned long bootmap_start, nodedata_phys;
         void *bootmap;
         const int pgdat_size = round_up(sizeof(pg_data_t), PAGE_SIZE);
+        int nid;
 
         start = round_up(start, ZONE_ALIGN);
 
@@ -218,9 +219,19 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
         NODE_DATA(nodeid)->node_start_pfn = start_pfn;
         NODE_DATA(nodeid)->node_spanned_pages = end_pfn - start_pfn;
 
-        /* Find a place for the bootmem map */
+        /*
+         * Find a place for the bootmem map
+         * nodedata_phys could be on other nodes by alloc_bootmem,
+         * so need to sure bootmap_start not to be small, otherwise
+         * early_node_mem will get that with find_e820_area instead
+         * of alloc_bootmem, that could clash with reserved range
+         */
         bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-        bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+        nid = phys_to_nid(nodedata_phys);
+        if (nid == nodeid)
+                bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+        else
+                bootmap_start = round_up(start, PAGE_SIZE);
         /*
          * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
          * to use that to align to PAGE_SIZE
@@ -245,10 +256,29 @@ void __init setup_node_bootmem(int nodeid, unsigned long start,
 
         free_bootmem_with_active_regions(nodeid, end);
 
-        reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size,
-                        BOOTMEM_DEFAULT);
-        reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
-                        bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+        /*
+         * convert early reserve to bootmem reserve earlier
+         * otherwise early_node_mem could use early reserved mem
+         * on previous node
+         */
+        early_res_to_bootmem(start, end);
+
+        /*
+         * in some case early_node_mem could use alloc_bootmem
+         * to get range on other node, don't reserve that again
+         */
+        if (nid != nodeid)
+                printk(KERN_INFO "    NODE_DATA(%d) on node %d\n", nodeid, nid);
+        else
+                reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys,
+                                        pgdat_size, BOOTMEM_DEFAULT);
+        nid = phys_to_nid(bootmap_start);
+        if (nid != nodeid)
+                printk(KERN_INFO "    bootmap(%d) on node %d\n", nodeid, nid);
+        else
+                reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
+                                 bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
+
 #ifdef CONFIG_ACPI_NUMA
         srat_reserve_add_area(nodeid);
 #endif