[PATCH] powerpc: Fix sparsemem with memory holes [was Re: ppc64 oops..]

This patch should fix the crashes we have been seeing on 64-bit
powerpc systems with a memory hole when sparsemem is enabled.
I'd appreciate it if people who know more about NUMA and sparsemem
than me could look over it.

There were two bugs.  The first was that if NUMA was enabled but there
was no NUMA information for the machine, the setup_nonnuma() function
was adding a single region, assuming memory was contiguous.  The
second was that the loops in mem_init() and show_mem() assumed that
all pages within the span of a pgdat were valid (had a valid struct
page).

I also fixed the incorrect setting of num_physpages that Mike Kravetz
pointed out.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index e2c95fc..4bd7b0a 100644 (file)
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -200,6 +200,8 @@ void show_mem(void)
                unsigned long flags;
                pgdat_resize_lock(pgdat, &flags);
                for (i = 0; i < pgdat->node_spanned_pages; i++) {
+                       if (!pfn_valid(pgdat->node_start_pfn + i))
+                               continue;
                        page = pgdat_page_nr(pgdat, i);
                        total++;
                        if (PageHighMem(page))
@@ -336,7 +338,7 @@ void __init mem_init(void)
        struct page *page;
        unsigned long reservedpages = 0, codesize, initsize, datasize, bsssize;
 
-       num_physpages = max_pfn;        /* RAM is assumed contiguous */
+       num_physpages = lmb.memory.size >> PAGE_SHIFT;
        high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
@@ -348,11 +350,13 @@ void __init mem_init(void)
                }
        }
 #else
-       max_mapnr = num_physpages;
+       max_mapnr = max_pfn;
        totalram_pages += free_all_bootmem();
 #endif
        for_each_pgdat(pgdat) {
                for (i = 0; i < pgdat->node_spanned_pages; i++) {
+                       if (!pfn_valid(pgdat->node_start_pfn + i))
+                               continue;
                        page = pgdat_page_nr(pgdat, i);
                        if (PageReserved(page))
                                reservedpages++;

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index bd2cf13..f72cf87 100644 (file)
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -483,6 +483,7 @@ static void __init setup_nonnuma(void)
 {
        unsigned long top_of_ram = lmb_end_of_DRAM();
        unsigned long total_ram = lmb_phys_mem_size();
+       unsigned int i;
 
        printk(KERN_INFO "Top of RAM: 0x%lx, Total RAM: 0x%lx\n",
               top_of_ram, total_ram);
@@ -490,7 +491,9 @@ static void __init setup_nonnuma(void)
               (top_of_ram - total_ram) >> 20);
 
        map_cpu_to_node(boot_cpuid, 0);
-       add_region(0, 0, lmb_end_of_DRAM() >> PAGE_SHIFT);
+       for (i = 0; i < lmb.memory.cnt; ++i)
+               add_region(0, lmb.memory.region[i].base >> PAGE_SHIFT,
+                          lmb_size_pages(&lmb.memory, i));
        node_set_online(0);
 }