From: Yinghai Lu <yinghai@kernel.org>
To: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>, Ingo Molnar <mingo@elte.hu>,
tglx@linutronix.de, "H. Peter Anvin" <hpa@zytor.com>,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH x86/mm UPDATED] x86-64, NUMA: Fix distance table handling
Date: Wed, 02 Mar 2011 08:16:18 -0800 [thread overview]
Message-ID: <4D6E6D52.8030901@kernel.org> (raw)
In-Reply-To: <20110302102530.GB3319@htj.dyndns.org>
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
next prev parent reply other threads:[~2011-03-02 16:18 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-02-24 14:51 [GIT PULL tip:x86/mm] Tejun Heo
2011-02-24 14:52 ` [GIT PULL tip:x86/mm] bootmem,x86: cleanup changes Tejun Heo
2011-02-24 19:08 ` [GIT PULL tip:x86/mm] Yinghai Lu
2011-02-24 19:23 ` Ingo Molnar
2011-02-24 19:28 ` Yinghai Lu
2011-02-24 19:32 ` Ingo Molnar
2011-02-24 19:46 ` Tejun Heo
2011-02-24 22:46 ` [patch] x86, mm: Fix size of numa_distance array David Rientjes
2011-02-24 23:30 ` Yinghai Lu
2011-02-24 23:31 ` David Rientjes
2011-02-25 9:05 ` Tejun Heo
2011-02-25 9:03 ` Tejun Heo
2011-02-25 10:58 ` Tejun Heo
2011-02-25 11:05 ` Tejun Heo
2011-02-25 9:11 ` [PATCH x86-mm] x86-64, NUMA: " Tejun Heo
2011-03-01 17:18 ` [GIT PULL tip:x86/mm] David Rientjes
2011-03-01 18:25 ` Tejun Heo
2011-03-01 22:19 ` Yinghai Lu
2011-03-02 9:17 ` Tejun Heo
2011-03-02 10:04 ` [PATCH x86/mm] x86-64, NUMA: Fix distance table handling Tejun Heo
2011-03-02 10:07 ` Ingo Molnar
2011-03-02 10:15 ` Tejun Heo
2011-03-02 10:36 ` Ingo Molnar
2011-03-02 10:25 ` [PATCH x86/mm UPDATED] " Tejun Heo
2011-03-02 10:39 ` [PATCH x86/mm] x86-64, NUMA: Better explain numa_distance handling Tejun Heo
2011-03-02 10:42 ` [PATCH UPDATED " Tejun Heo
2011-03-02 14:31 ` David Rientjes
2011-03-02 14:30 ` [PATCH x86/mm UPDATED] x86-64, NUMA: Fix distance table handling David Rientjes
2011-03-02 15:42 ` Tejun Heo
2011-03-02 21:12 ` Yinghai Lu
2011-03-02 21:36 ` Yinghai Lu
2011-03-03 20:07 ` David Rientjes
2011-03-04 14:32 ` Tejun Heo
2011-03-03 20:04 ` David Rientjes
2011-03-03 20:00 ` David Rientjes
2011-03-04 15:31 ` [PATCH x86/mm] x86-64, NUMA: Don't assume phys node 0 is always online in numa_emulation() handling Tejun Heo
2011-03-04 21:33 ` David Rientjes
2011-03-05 7:50 ` Tejun Heo
2011-03-05 15:50 ` [tip:x86/mm] x86-64, NUMA: Don't assume phys node 0 is always online in numa_emulation() tip-bot for Tejun Heo
2011-03-02 16:16 ` Yinghai Lu [this message]
2011-03-02 16:37 ` [PATCH x86/mm UPDATED] x86-64, NUMA: Fix distance table handling Tejun Heo
2011-03-02 16:46 ` Yinghai Lu
2011-03-02 16:55 ` Tejun Heo
2011-03-02 18:52 ` Yinghai Lu
2011-03-02 19:02 ` Tejun Heo
2011-03-02 19:06 ` Yinghai Lu
2011-03-02 19:13 ` Tejun Heo
2011-03-02 20:32 ` Yinghai Lu
2011-03-02 20:57 ` Tejun Heo
2011-03-02 21:14 ` Yinghai Lu
2011-03-03 6:17 ` Tejun Heo
2011-03-10 18:46 ` Yinghai Lu
2011-03-11 8:29 ` Tejun Heo
2011-03-11 8:33 ` Tejun Heo
2011-03-11 15:48 ` Yinghai Lu
2011-03-11 15:54 ` Tejun Heo
2011-03-11 18:02 ` Yinghai Lu
2011-03-11 18:19 ` Tejun Heo
2011-03-11 18:25 ` Yinghai Lu
2011-03-11 18:29 ` Tejun Heo
2011-03-11 18:45 ` Yinghai Lu
2011-03-11 9:31 ` [PATCH x86/mm] x86-64, NUMA: Don't call numa_set_distanc() for all possible node combinations during emulation Tejun Heo
2011-03-11 15:42 ` Yinghai Lu
2011-03-11 16:03 ` Tejun Heo
2011-03-11 19:05 ` Yinghai Lu
2011-03-02 10:43 ` [PATCH x86/mm] x86-64, NUMA: Fix distance table handling Ingo Molnar
2011-03-02 10:53 ` Tejun Heo
2011-03-02 10:59 ` Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4D6E6D52.8030901@kernel.org \
--to=yinghai@kernel.org \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rientjes@google.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.