public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Yinghai Lu <yhlu.kernel@gmail.com>
To: Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Andrew Morton <akpm@linux-foundation.org>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Subject: [PATCH] x86: 32bit numa increase max_elements to 1024
Date: Sat, 31 May 2008 22:51:51 -0700	[thread overview]
Message-ID: <200805312251.52297.yhlu.kernel@gmail.com> (raw)
In-Reply-To: <200805291625.56942.yhlu.kernel@gmail.com>


so every element will repsent to 64M instead of 256M.

AMD opteron later based could have HW memory hole remapping. so could have
[0, 8g + 64M) on node0. reduce element size to 64M could keep that on node 0

later need to use find_e820_area to allocate memory_node_map like 64bit.
but need to move memory_present out of populate_mem_map...

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>

diff --git a/arch/x86/mm/discontig_32.c b/arch/x86/mm/discontig_32.c
index 0c1a1bf..0ea4854 100644
--- a/arch/x86/mm/discontig_32.c
+++ b/arch/x86/mm/discontig_32.c
@@ -59,14 +59,14 @@ unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;
 /*
  * 4) physnode_map     - the mapping between a pfn and owning node
  * physnode_map keeps track of the physical memory layout of a generic
- * numa node on a 256Mb break (each element of the array will
- * represent 256Mb of memory and will be marked by the node id.  so,
+ * numa node on a 64Mb break (each element of the array will
+ * represent 64Mb of memory and will be marked by the node id.  so,
  * if the first gig is on node 0, and the second gig is on node 1
  * physnode_map will contain:
  *
- *     physnode_map[0-3] = 0;
- *     physnode_map[4-7] = 1;
- *     physnode_map[8- ] = -1;
+ *     physnode_map[0-15] = 0;
+ *     physnode_map[16-31] = 1;
+ *     physnode_map[32- ] = -1;
  */
 s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
 EXPORT_SYMBOL(physnode_map);
@@ -81,9 +81,9 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 	printk(KERN_DEBUG "  ");
 	for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
 		physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
-		printk("%ld ", pfn);
+		printk(KERN_CONT "%ld ", pfn);
 	}
-	printk("\n");
+	printk(KERN_CONT "\n");
 }
 
 unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
index faef751..ab00128 100644
--- a/include/asm-x86/mmzone_32.h
+++ b/include/asm-x86/mmzone_32.h
@@ -51,14 +51,14 @@ extern int early_pfn_to_nid(unsigned long pfn);
 /*
  * generic node memory support, the following assumptions apply:
  *
- * 1) memory comes in 256Mb contigious chunks which are either present or not
+ * 1) memory comes in 64Mb contigious chunks which are either present or not
  * 2) we will not have more than 64Gb in total
  *
  * for now assume that 64Gb is max amount of RAM for whole system
  *    64Gb / 4096bytes/page = 16777216 pages
  */
 #define MAX_NR_PAGES 16777216
-#define MAX_ELEMENTS 256
+#define MAX_ELEMENTS 1024
 #define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
 
 extern s8 physnode_map[];

  parent reply	other threads:[~2008-06-01  5:57 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-11  7:30 [PATCH] x86: make e820.c to have common functions Yinghai Lu
2008-05-13 13:05 ` Ingo Molnar
2008-05-13 17:35   ` Yinghai Lu
2008-05-18  8:18 ` [PATCH] x86: extend e820 ealy_res support 32bit Yinghai Lu
2008-05-21  3:10   ` [PATCH] x86: move e820_mark_nosave_regions to e820.c Yinghai Lu
2008-05-22  1:40   ` [PATCH] x86: extend e820 ealy_res support 32bit - fix Yinghai Lu
2008-05-22 10:12     ` Jeremy Fitzhardinge
2008-05-22 17:58       ` Yinghai Lu
2008-05-22 22:20     ` [PATCH] x86: extend e820 ealy_res support 32bit - fix v2 Yinghai Lu
2008-05-23 23:08       ` Yinghai Lu
2008-05-23 23:32         ` Jeremy Fitzhardinge
2008-05-23 23:38         ` Jeremy Fitzhardinge
2008-05-24  0:01           ` Yinghai Lu
2008-05-24  0:09             ` Yinghai Lu
2008-05-24  8:54       ` Jeremy Fitzhardinge
2008-05-24  9:49         ` [PATCH] xen: boot via i386_start_kernel to get early reservations Jeremy Fitzhardinge
2008-05-24 22:04           ` Yinghai Lu
2008-05-24 19:57         ` [PATCH] x86: extend e820 ealy_res support 32bit - fix v2 Yinghai Lu
2008-05-25 17:00     ` [PATCH] x86: extend e820 ealy_res support 32bit - fix #2 Yinghai Lu
2008-05-27 15:44       ` Thomas Gleixner
2008-05-27 20:37         ` Jeremy Fitzhardinge
2008-05-27 20:58           ` Thomas Gleixner
2008-05-27 21:06             ` Jeremy Fitzhardinge
2008-05-27 21:06           ` Yinghai Lu
2008-05-27 21:22             ` Jeremy Fitzhardinge
2008-05-27 21:35               ` Yinghai Lu
2008-05-27 21:47                 ` Jeremy Fitzhardinge
2008-05-27 22:52                   ` Yinghai Lu
2008-05-28 10:01                     ` Jeremy Fitzhardinge
2008-05-28 20:48                       ` Yinghai Lu
2008-05-28 21:24                         ` Jeremy Fitzhardinge
2008-05-29 13:37                         ` Jeremy Fitzhardinge
2008-05-29 18:41                           ` Yinghai Lu
2008-05-29 18:58                             ` H. Peter Anvin
2008-05-29 18:52                           ` Yinghai Lu
2008-05-29 19:14                             ` Yinghai Lu
2008-05-30 15:50                               ` Jeremy Fitzhardinge
2008-05-29 19:56       ` [PATCH] x86: extend e820 early_res support 32bit -fix #3 Yinghai Lu
2008-05-29 19:57       ` [PATCH] x86: extend e820 early_res support 32bit -fix #4 Yinghai Lu
2008-05-29 19:58       ` [PATCH] x86: extend e820 early_res support 32bit -fix #5 Yinghai Lu
2008-05-29 23:25       ` [PATCH] x86: 32bit numa srat fix early_ioremap leak Yinghai Lu
2008-05-31  8:01         ` Ingo Molnar
2008-06-01  5:51         ` Yinghai Lu [this message]
2008-06-01  5:52           ` [PATCH] x86: change propagate_e820_map back to find_max_pfn -32bit Yinghai Lu
2008-06-01  5:53             ` [PATCH] x86: set node_remap_size[0] in fallback path Yinghai Lu
2008-06-01  5:56               ` [PATCH] x86: numa_32 print out debug info all kva Yinghai Lu
2008-06-01 20:15                 ` [PATCH] x86: numa_32 print out debug info all kva v2 Yinghai Lu
2008-06-03  2:16             ` [PATCH] x86: change propagate_e820_map back to find_max_pfn -32bit -v2 Yinghai Lu
2008-06-02  4:06         ` [PATCH] x86: numa_32 avoid clash between ramdisk and kva Yinghai Lu
2008-06-02  6:53           ` [PATCH] x86: cleanup max_pfn_mapped usage - 32bit Yinghai Lu
2008-06-02  6:55           ` [PATCH] x86: cleanup max_pfn_mapped usage - 64bit Yinghai Lu

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=200805312251.52297.yhlu.kernel@gmail.com \
    --to=yhlu.kernel@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=tglx@linutronix.de \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox