lkml.org 
[lkml]   [2011]   [Mar]   [2]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
SubjectRe: [PATCH x86/mm UPDATED] x86-64, NUMA: Fix distance table handling
On 03/02/2011 02:25 AM, Tejun Heo wrote:
>>From d968be2ff381c667bfd09795f82248558902a1ae Mon Sep 17 00:00:00 2001
> From: Tejun Heo <tj@kernel.org>
> Date: Wed, 2 Mar 2011 11:22:14 +0100
>
> NUMA distance table handling has the following problems.
>
> * numa_reset_distance() uses numa_distance * sizeof(numa_distance[0])
> as the table size when it should be using the square of
> numa_distance.
>
> * The same size miscalculation when allocation space for phys_dist in
> numa_emulation().
>
> * In numa_emulation(), phys_dist must be reserved; otherwise, the new
> emulated distance table may overlap it.
>
> Fix them and, while at it, take numa_distance_cnt resetting in
> numa_reset_distance() out of the if block to simplify the code a bit.
>
> David Rientjes reported incorrect handling of distance table during
> emulation and Yinghai identified the above problems and wrote the
> original patch to fix the problems. This patch is based on Yinghai's
> patch.
>
> -v2: Ingo was unhappy with 80-column limit induced linebreaks. Let
> lines run over 80-column.
>
> Reported-by: David Rientjes <rientjes@google.com>
> Patch-originally-from: Yinghai Lu <yinghai@kernel.org>
> Signed-off-by: Tejun Heo <tj@kernel.org>
> Cc: Ingo Molnar <mingo@elte.hu>
> ---
> arch/x86/mm/numa_64.c | 8 +++-----
> arch/x86/mm/numa_emulation.c | 14 ++++++++------
> 2 files changed, 11 insertions(+), 11 deletions(-)
>
> diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
> index 7757d22..541746f 100644
> --- a/arch/x86/mm/numa_64.c
> +++ b/arch/x86/mm/numa_64.c
> @@ -390,14 +390,12 @@ static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
> */
> void __init numa_reset_distance(void)
> {
> - size_t size;
> + size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
>
> - if (numa_distance_cnt) {
> - size = numa_distance_cnt * sizeof(numa_distance[0]);
> + if (numa_distance_cnt)
> memblock_x86_free_range(__pa(numa_distance),
> __pa(numa_distance) + size);
> - numa_distance_cnt = 0;
> - }
> + numa_distance_cnt = 0;
> numa_distance = NULL;
> }

my original part:

@@ -393,7 +393,7 @@ void __init numa_reset_distance(void)
size_t size;

if (numa_distance_cnt) {
- size = numa_distance_cnt * sizeof(numa_distance[0]);
+ size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]);
memblock_x86_free_range(__pa(numa_distance),
__pa(numa_distance) + size);
numa_distance_cnt = 0;

So can you tell me why you need to make those change?
move out assigning or numa_distance_cnt and size of the the IF

>
> diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
> index 607a2e8..0afa25d 100644
> --- a/arch/x86/mm/numa_emulation.c
> +++ b/arch/x86/mm/numa_emulation.c
> @@ -300,6 +300,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
> static struct numa_meminfo pi __initdata;
> const u64 max_addr = max_pfn << PAGE_SHIFT;
> u8 *phys_dist = NULL;
> + size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]);
> int i, j, ret;
>
> if (!emu_cmdline)
> @@ -336,21 +337,18 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
> goto no_emu;
> }
>
> - /*
> - * Copy the original distance table. It's temporary so no need to
> - * reserve it.
> - */
> + /* copy the physical distance table */
> if (numa_dist_cnt) {
> - size_t size = numa_dist_cnt * sizeof(phys_dist[0]);
> u64 phys;
>
> phys = memblock_find_in_range(0,
> (u64)max_pfn_mapped << PAGE_SHIFT,
> - size, PAGE_SIZE);
> + phys_size, PAGE_SIZE);
> if (phys == MEMBLOCK_ERROR) {
> pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
> goto no_emu;
> }
> + memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST");
> phys_dist = __va(phys);
>
> for (i = 0; i < numa_dist_cnt; i++)
> @@ -398,6 +396,10 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
> numa_set_distance(i, j, dist);
> }
> }
> +
> + /* free the copied physical distance table */
> + if (phys_dist)
> + memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size);
> return;
>
> no_emu:

you missed

@@ -383,21 +386,40 @@ void __init numa_emulation(struct numa_m

/* transform distance table */
numa_reset_distance();
- for (i = 0; i < MAX_NUMNODES; i++) {
- for (j = 0; j < MAX_NUMNODES; j++) {
- int physi = emu_nid_to_phys[i];
- int physj = emu_nid_to_phys[j];
- int dist;
-
- if (physi >= numa_dist_cnt || physj >= numa_dist_cnt)
- dist = physi == physj ?
- LOCAL_DISTANCE : REMOTE_DISTANCE;
- else
+ /* allocate numa_distance at first, it will set new numa_dist_cnt */
+ new_nr = numa_alloc_distance();
+ if (new_nr < 0)
+ goto free_temp_phys;
+
+ /*
+ * only set it when we have old phys_dist,
+ * numa_alloc_distance already set default values
+ */
+ if (phys_dist)
+ for (i = 0; i < new_nr; i++) {
+ for (j = 0; j < new_nr; j++) {
+ int physi = emu_nid_to_phys[i];
+ int physj = emu_nid_to_phys[j];
+ int dist;
+
+ /* really need this check ? */
+ if (physi >= numa_dist_cnt ||
+ physj >= numa_dist_cnt)
+ continue;
+
dist = phys_dist[physi * numa_dist_cnt + physj];

- numa_set_distance(i, j, dist);
+ numa_set_distance(i, j, dist);
+ }
}
- }
+

the change include:
1. you only need to go over new_nr*new_nr instead huge MAX_NUMNODES * MAX_NUMNODES
2. you do NOT need to go over it if you don't have phys_dist assigned before.
numa_alloc_distance already have that default set.
3. do need to check if phys_dist is assigned before referring phys_dist.

so please just use my original patch.
Thanks

Yinghai


\
 
 \ /
  Last update: 2011-03-02 17:21    [W:0.175 / U:0.848 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site