aboutsummaryrefslogtreecommitdiff
path: root/arch/ia64
diff options
context:
space:
mode:
authorZou Nan hai <nanhai.zou@intel.com>2007-03-20 13:41:57 -0700
committerTony Luck <tony.luck@intel.com>2007-03-20 13:41:57 -0700
commita3f5c338b9f30f328276739d9589beae19254936 (patch)
tree5c197e9c6565382a548180bdfb57ee5315d9fc60 /arch/ia64
parentbe521466feb3bb1cd89de82a2b1d080e9ebd3cb6 (diff)
[IA64] min_low_pfn and max_low_pfn calculation fix
We have seen bad_pte_print when testing crashdump on an SN machine in recent 2.6.20 kernel. There are tons of bad pte print (pfn < max_low_pfn) reports when the crash kernel boots up, all those reported bad pages are inside initmem range; That is because if the crash kernel code and data happens to be at the beginning of the 1st node. build_node_maps in discontig.c will bypass reserved regions with filter_rsvd_memory. Since min_low_pfn is calculated in build_node_map, so in this case, min_low_pfn will be greater than kernel code and data. Because pages inside initmem are freed and reused later, we saw pfn_valid check fail on those pages. I think this theoretically happen on a normal kernel. When I check min_low_pfn and max_low_pfn calculation in contig.c and discontig.c. I found more issues than this. 1. min_low_pfn and max_low_pfn calculation is inconsistent between contig.c and discontig.c, min_low_pfn is calculated as the first page number of boot memmap in contig.c (Why? Though this may work at the most of the time, I don't think it is the right logic). It is calculated as the lowest physical memory page number bypass reserved regions in discontig.c. max_low_pfn is calculated include reserved regions in contig.c. It is calculated exclude reserved regions in discontig.c. 2. If kernel code and data region is happen to be at the begin or the end of physical memory, when min_low_pfn and max_low_pfn calculation is bypassed kernel code and data, pages in initmem will report bad. 3. initrd is also in reserved regions, if it is at the begin or at the end of physical memory, kernel will refuse to reuse the memory. Because the virt_addr_valid check in free_initrd_mem. So it is better to fix and clean up those issues. Calculate min_low_pfn and max_low_pfn in a consistent way. Signed-off-by: Zou Nan hai <nanhai.zou@intel.com> Acked-by: Jay Lan <jlan@sgi.com> Signed-off-by: Tony Luck <tony.luck@intel.com>
Diffstat (limited to 'arch/ia64')
-rw-r--r--arch/ia64/mm/contig.c30
-rw-r--r--arch/ia64/mm/discontig.c4
-rw-r--r--arch/ia64/mm/init.c16
3 files changed, 23 insertions, 27 deletions
diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index fb0f4698f5d..44ce5ed9444 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -97,26 +97,6 @@ void show_mem(void)
unsigned long bootmap_start;
/**
- * find_max_pfn - adjust the maximum page number callback
- * @start: start of range
- * @end: end of range
- * @arg: address of pointer to global max_pfn variable
- *
- * Passed as a callback function to efi_memmap_walk() to determine the highest
- * available page frame number in the system.
- */
-int
-find_max_pfn (unsigned long start, unsigned long end, void *arg)
-{
- unsigned long *max_pfnp = arg, pfn;
-
- pfn = (PAGE_ALIGN(end - 1) - PAGE_OFFSET) >> PAGE_SHIFT;
- if (pfn > *max_pfnp)
- *max_pfnp = pfn;
- return 0;
-}
-
-/**
* find_bootmap_location - callback to find a memory area for the bootmap
* @start: start of region
* @end: end of region
@@ -177,9 +157,10 @@ find_memory (void)
reserve_memory();
/* first find highest page frame number */
- max_pfn = 0;
- efi_memmap_walk(find_max_pfn, &max_pfn);
-
+ min_low_pfn = ~0UL;
+ max_low_pfn = 0;
+ efi_memmap_walk(find_max_min_low_pfn, NULL);
+ max_pfn = max_low_pfn;
/* how many bytes to cover all the pages */
bootmap_size = bootmem_bootmap_pages(max_pfn) << PAGE_SHIFT;
@@ -189,7 +170,8 @@ find_memory (void)
if (bootmap_start == ~0UL)
panic("Cannot find %ld bytes for bootmap\n", bootmap_size);
- bootmap_size = init_bootmem(bootmap_start >> PAGE_SHIFT, max_pfn);
+ bootmap_size = init_bootmem_node(NODE_DATA(0),
+ (bootmap_start >> PAGE_SHIFT), 0, max_pfn);
/* Free all available memory, then mark bootmem-map as being in use. */
efi_memmap_walk(filter_rsvd_memory, free_bootmem);
diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index 11a2d8825d8..872da7a2acc 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -88,9 +88,6 @@ static int __init build_node_maps(unsigned long start, unsigned long len,
bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
}
- min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
- max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);
-
return 0;
}
@@ -438,6 +435,7 @@ void __init find_memory(void)
/* These actually end up getting called by call_pernode_memory() */
efi_memmap_walk(filter_rsvd_memory, build_node_maps);
efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
+ efi_memmap_walk(find_max_min_low_pfn, NULL);
for_each_online_node(node)
if (mem_data[node].bootmem_data.node_low_pfn) {
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index f225dd72968..c8da621aab1 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -648,6 +648,22 @@ count_reserved_pages (u64 start, u64 end, void *arg)
return 0;
}
+int
+find_max_min_low_pfn (unsigned long start, unsigned long end, void *arg)
+{
+ unsigned long pfn_start, pfn_end;
+#ifdef CONFIG_FLATMEM
+ pfn_start = (PAGE_ALIGN(__pa(start))) >> PAGE_SHIFT;
+ pfn_end = (PAGE_ALIGN(__pa(end - 1))) >> PAGE_SHIFT;
+#else
+ pfn_start = GRANULEROUNDDOWN(__pa(start)) >> PAGE_SHIFT;
+ pfn_end = GRANULEROUNDUP(__pa(end - 1)) >> PAGE_SHIFT;
+#endif
+ min_low_pfn = min(min_low_pfn, pfn_start);
+ max_low_pfn = max(max_low_pfn, pfn_end);
+ return 0;
+}
+
/*
* Boot command-line option "nolwsys" can be used to disable the use of any light-weight
* system call handler. When this option is in effect, all fsyscalls will end up bubbling