Re: [PATCH] Register memory ranges in a consistent manner on IA64

[Horms <horms@verge.net.au>]

On Wed, Jan 17, 2007 at 08:18:32AM -0500, Bob Picco wrote:
> While pursuing and unrelated issue with 64Mb granules I noticed a problem
> related to inconsistent use of add_active_range. There doesn't appear any
> reason to me why FLATMEM versus DISCONTIG_MEM should register memory
> to add_active_range with different code. So I've changed the code into
> a common implementation. 
> 
> The other subtle issue fixed by this patch was calling add_active_range
> in count_node_pages before granule aligning is performed. We were lucky with
> 16MB granules but not so with 64MB granules. count_node_pages has reserved
> regions filtered out and as a consequence linked kernel text and data
> aren't covered by calls to count_node_pages. So linked kernel regions
> wasn't reported to add_active_regions. This resulted in free_initmem causing
> numerous bad_page reports. This won't occur with this patch because now
> all known memory regions are reported by register_active_ranges.
> 
> Acked-by: Mel Gorman <mel@csn.ul.ie>
> Signed-off-by: Bob Picco <bob.picco@hp.com>

This appears to resolve the problem that I was seeing.

http://article.gmane.org/gmane.linux.ports.ia64/15347/match\x05e0caad3b7bd0d0fbeff980bca22f186241a501

Signed-off-by: Simon Horman <horms@verge.net.au>

>  arch/ia64/mm/discontig.c   |    4 +++-
>  arch/ia64/mm/init.c        |   19 +++++++++++++++++--
>  include/asm-ia64/meminit.h |    3 ++-
>  3 files changed, 22 insertions(+), 4 deletions(-)
> 
> Index: linux-2.6.20-rc4/arch/ia64/mm/discontig.c
> =================================> --- linux-2.6.20-rc4.orig/arch/ia64/mm/discontig.c	2007-01-11 12:11:08.000000000 -0500
> +++ linux-2.6.20-rc4/arch/ia64/mm/discontig.c	2007-01-17 05:27:11.000000000 -0500
> @@ -473,6 +473,9 @@ void __init find_memory(void)
>  			node_clear(node, memory_less_mask);
>  			mem_data[node].min_pfn = ~0UL;
>  		}
> +
> +	efi_memmap_walk(register_active_ranges, NULL);
> +
>  	/*
>  	 * Initialize the boot memory maps in reverse order since that's
>  	 * what the bootmem allocator expects
> @@ -654,7 +657,6 @@ static __init int count_node_pages(unsig
>  {
>  	unsigned long end = start + len;
>  
> -	add_active_range(node, start >> PAGE_SHIFT, end >> PAGE_SHIFT);
>  	mem_data[node].num_physpages += len >> PAGE_SHIFT;
>  	if (start <= __pa(MAX_DMA_ADDRESS))
>  		mem_data[node].num_dma_physpages +> Index: linux-2.6.20-rc4/arch/ia64/mm/init.c
> =================================> --- linux-2.6.20-rc4.orig/arch/ia64/mm/init.c	2007-01-11 10:47:39.000000000 -0500
> +++ linux-2.6.20-rc4/arch/ia64/mm/init.c	2007-01-11 12:11:54.000000000 -0500
> @@ -19,6 +19,7 @@
>  #include <linux/swap.h>
>  #include <linux/proc_fs.h>
>  #include <linux/bitops.h>
> +#include <linux/kexec.h>
>  
>  #include <asm/a.out.h>
>  #include <asm/dma.h>
> @@ -594,13 +595,27 @@ find_largest_hole (u64 start, u64 end, v
>  	return 0;
>  }
>  
> +#endif /* CONFIG_VIRTUAL_MEM_MAP */
> +
>  int __init
>  register_active_ranges(u64 start, u64 end, void *arg)
>  {
> -	add_active_range(0, __pa(start) >> PAGE_SHIFT, __pa(end) >> PAGE_SHIFT);
> +	int nid = paddr_to_nid(__pa(start));
> +
> +	if (nid < 0)
> +		nid = 0;
> +#ifdef CONFIG_KEXEC
> +	if (start > crashk_res.start && start < crashk_res.end)
> +		start = crashk_res.end;
> +	if (end > crashk_res.start && end < crashk_res.end)
> +		end = crashk_res.start;
> +#endif
> +
> +	if (start < end)
> +		add_active_range(nid, __pa(start) >> PAGE_SHIFT,
> +			__pa(end) >> PAGE_SHIFT);
>  	return 0;
>  }
> -#endif /* CONFIG_VIRTUAL_MEM_MAP */
>  
>  static int __init
>  count_reserved_pages (u64 start, u64 end, void *arg)
> Index: linux-2.6.20-rc4/include/asm-ia64/meminit.h
> =================================> --- linux-2.6.20-rc4.orig/include/asm-ia64/meminit.h	2007-01-11 10:47:41.000000000 -0500
> +++ linux-2.6.20-rc4/include/asm-ia64/meminit.h	2007-01-11 12:11:54.000000000 -0500
> @@ -51,12 +51,13 @@ extern void efi_memmap_init(unsigned lon
>  
>  #define IGNORE_PFN0	1	/* XXX fix me: ignore pfn 0 until TLB miss handler is updated... */
>  
> +extern int register_active_ranges (u64 start, u64 end, void *arg);
> +
>  #ifdef CONFIG_VIRTUAL_MEM_MAP
>  # define LARGE_GAP	0x40000000 /* Use virtual mem map if hole is > than this */
>    extern unsigned long vmalloc_end;
>    extern struct page *vmem_map;
>    extern int find_largest_hole (u64 start, u64 end, void *arg);
> -  extern int register_active_ranges (u64 start, u64 end, void *arg);
>    extern int create_mem_map_page_table (u64 start, u64 end, void *arg);
>    extern int vmemmap_find_next_valid_pfn(int, int);
>  #else

-- 
Horms
  H: http://www.vergenet.net/~horms/
  W: http://www.valinux.co.jp/en/