All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: linux-kernel@vger.kernel.org, x86@kernel.org, yinghai@kernel.org,
	brgerst@gmail.com, gorcunov@gmail.com, shaohui.zheng@intel.com,
	rientjes@google.com, mingo@elte.hu, hpa@linux.intel.com
Cc: Tejun Heo <tj@kernel.org>
Subject: [PATCH 18/26] x86-64, NUMA: Introduce struct numa_meminfo
Date: Sat, 12 Feb 2011 18:10:55 +0100	[thread overview]
Message-ID: <1297530663-26234-19-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1297530663-26234-1-git-send-email-tj@kernel.org>

Arrays for memblks and nodeids and their length lived in separate
variables making things unnecessarily cumbersome.  Introduce struct
numa_meminfo which contains all memory configuration info.  This patch
doesn't cause any behavior change.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Shaohui Zheng <shaohui.zheng@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: H. Peter Anvin <hpa@linux.intel.com>
---
 arch/x86/mm/numa_64.c |  145 +++++++++++++++++++++++++------------------------
 1 files changed, 75 insertions(+), 70 deletions(-)

diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 1d79cd8..04ea17b 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -22,6 +22,17 @@
 #include <asm/acpi.h>
 #include <asm/amd_nb.h>
 
+struct numa_memblk {
+	u64			start;
+	u64			end;
+	int			nid;
+};
+
+struct numa_meminfo {
+	int			nr_blks;
+	struct numa_memblk	blk[NR_NODE_MEMBLKS];
+};
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
@@ -33,9 +44,7 @@ struct memnode memnode;
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
-static int num_node_memblks __initdata;
-static struct bootnode node_memblk_range[NR_NODE_MEMBLKS] __initdata;
-static int memblk_nodeid[NR_NODE_MEMBLKS] __initdata;
+static struct numa_meminfo numa_meminfo __initdata;
 
 struct bootnode numa_nodes[MAX_NUMNODES] __initdata;
 
@@ -46,16 +55,15 @@ struct bootnode numa_nodes[MAX_NUMNODES] __initdata;
  * 0 if memnodmap[] too small (of shift too small)
  * -1 if node overlap or lost ram (shift too big)
  */
-static int __init populate_memnodemap(const struct bootnode *nodes,
-				      int numnodes, int shift, int *nodeids)
+static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift)
 {
 	unsigned long addr, end;
 	int i, res = -1;
 
 	memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
-	for (i = 0; i < numnodes; i++) {
-		addr = nodes[i].start;
-		end = nodes[i].end;
+	for (i = 0; i < mi->nr_blks; i++) {
+		addr = mi->blk[i].start;
+		end = mi->blk[i].end;
 		if (addr >= end)
 			continue;
 		if ((end >> shift) >= memnodemapsize)
@@ -63,7 +71,7 @@ static int __init populate_memnodemap(const struct bootnode *nodes,
 		do {
 			if (memnodemap[addr >> shift] != NUMA_NO_NODE)
 				return -1;
-			memnodemap[addr >> shift] = nodeids[i];
+			memnodemap[addr >> shift] = mi->blk[i].nid;
 			addr += (1UL << shift);
 		} while (addr < end);
 		res = 1;
@@ -101,16 +109,15 @@ static int __init allocate_cachealigned_memnodemap(void)
  * The LSB of all start and end addresses in the node map is the value of the
  * maximum possible shift.
  */
-static int __init extract_lsb_from_nodes(const struct bootnode *nodes,
-					 int numnodes)
+static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi)
 {
 	int i, nodes_used = 0;
 	unsigned long start, end;
 	unsigned long bitfield = 0, memtop = 0;
 
-	for (i = 0; i < numnodes; i++) {
-		start = nodes[i].start;
-		end = nodes[i].end;
+	for (i = 0; i < mi->nr_blks; i++) {
+		start = mi->blk[i].start;
+		end = mi->blk[i].end;
 		if (start >= end)
 			continue;
 		bitfield |= start;
@@ -126,18 +133,17 @@ static int __init extract_lsb_from_nodes(const struct bootnode *nodes,
 	return i;
 }
 
-static int __init compute_hash_shift(struct bootnode *nodes, int numnodes,
-				     int *nodeids)
+static int __init compute_hash_shift(const struct numa_meminfo *mi)
 {
 	int shift;
 
-	shift = extract_lsb_from_nodes(nodes, numnodes);
+	shift = extract_lsb_from_nodes(mi);
 	if (allocate_cachealigned_memnodemap())
 		return -1;
 	printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n",
 		shift);
 
-	if (populate_memnodemap(nodes, numnodes, shift, nodeids) != 1) {
+	if (populate_memnodemap(mi, shift) != 1) {
 		printk(KERN_INFO "Your memory is not aligned you need to "
 		       "rebuild your kernel with a bigger NODEMAPSIZE "
 		       "shift=%d\n", shift);
@@ -185,21 +191,25 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
 
 static __init int conflicting_memblks(unsigned long start, unsigned long end)
 {
+	struct numa_meminfo *mi = &numa_meminfo;
 	int i;
-	for (i = 0; i < num_node_memblks; i++) {
-		struct bootnode *nd = &node_memblk_range[i];
-		if (nd->start == nd->end)
+
+	for (i = 0; i < mi->nr_blks; i++) {
+		struct numa_memblk *blk = &mi->blk[i];
+
+		if (blk->start == blk->end)
 			continue;
-		if (nd->end > start && nd->start < end)
-			return memblk_nodeid[i];
-		if (nd->end == end && nd->start == start)
-			return memblk_nodeid[i];
+		if (blk->end > start && blk->start < end)
+			return blk->nid;
+		if (blk->end == end && blk->start == start)
+			return blk->nid;
 	}
 	return -1;
 }
 
 int __init numa_add_memblk(int nid, u64 start, u64 end)
 {
+	struct numa_meminfo *mi = &numa_meminfo;
 	int i;
 
 	i = conflicting_memblks(start, end);
@@ -213,10 +223,10 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 		return -EINVAL;
 	}
 
-	node_memblk_range[num_node_memblks].start = start;
-	node_memblk_range[num_node_memblks].end = end;
-	memblk_nodeid[num_node_memblks] = nid;
-	num_node_memblks++;
+	mi->blk[mi->nr_blks].start = start;
+	mi->blk[mi->nr_blks].end = end;
+	mi->blk[mi->nr_blks].nid = nid;
+	mi->nr_blks++;
 	return 0;
 }
 
@@ -315,66 +325,59 @@ static int __init nodes_cover_memory(const struct bootnode *nodes)
 
 static int __init numa_register_memblks(void)
 {
+	struct numa_meminfo *mi = &numa_meminfo;
 	int i;
 
 	/*
 	 * Join together blocks on the same node, holes between
 	 * which don't overlap with memory on other nodes.
 	 */
-	for (i = 0; i < num_node_memblks; ++i) {
+	for (i = 0; i < mi->nr_blks; ++i) {
+		struct numa_memblk *bi = &mi->blk[i];
 		int j, k;
 
-		for (j = i + 1; j < num_node_memblks; ++j) {
+		for (j = i + 1; j < mi->nr_blks; ++j) {
+			struct numa_memblk *bj = &mi->blk[j];
 			unsigned long start, end;
 
-			if (memblk_nodeid[i] != memblk_nodeid[j])
+			if (bi->nid != bj->nid)
 				continue;
-			start = min(node_memblk_range[i].end,
-			            node_memblk_range[j].end);
-			end = max(node_memblk_range[i].start,
-			          node_memblk_range[j].start);
-			for (k = 0; k < num_node_memblks; ++k) {
-				if (memblk_nodeid[i] == memblk_nodeid[k])
+			start = min(bi->end, bj->end);
+			end = max(bi->start, bj->start);
+			for (k = 0; k < mi->nr_blks; ++k) {
+				struct numa_memblk *bk = &mi->blk[k];
+
+				if (bi->nid == bk->nid)
 					continue;
-				if (start < node_memblk_range[k].end &&
-				    end > node_memblk_range[k].start)
+				if (start < bk->end && end > bk->start)
 					break;
 			}
-			if (k < num_node_memblks)
+			if (k < mi->nr_blks)
 				continue;
-			start = min(node_memblk_range[i].start,
-			            node_memblk_range[j].start);
-			end = max(node_memblk_range[i].end,
-			          node_memblk_range[j].end);
+			start = min(bi->start, bj->start);
+			end = max(bi->end, bj->end);
 			printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n",
-			       memblk_nodeid[i],
-			       node_memblk_range[i].start,
-			       node_memblk_range[i].end,
-			       node_memblk_range[j].start,
-			       node_memblk_range[j].end,
+			       bi->nid, bi->start, bi->end, bj->start, bj->end,
 			       start, end);
-			node_memblk_range[i].start = start;
-			node_memblk_range[i].end = end;
-			k = --num_node_memblks - j;
-			memmove(memblk_nodeid + j, memblk_nodeid + j+1,
-				k * sizeof(*memblk_nodeid));
-			memmove(node_memblk_range + j, node_memblk_range + j+1,
-				k * sizeof(*node_memblk_range));
+			bi->start = start;
+			bi->end = end;
+			k = --mi->nr_blks - j;
+			memmove(mi->blk + j, mi->blk + j + 1,
+				k * sizeof(mi->blk[0]));
 			--j;
 		}
 	}
 
-	memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks,
-					   memblk_nodeid);
+	memnode_shift = compute_hash_shift(mi);
 	if (memnode_shift < 0) {
 		printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n");
 		return -EINVAL;
 	}
 
-	for (i = 0; i < num_node_memblks; i++)
-		memblock_x86_register_active_regions(memblk_nodeid[i],
-				node_memblk_range[i].start >> PAGE_SHIFT,
-				node_memblk_range[i].end >> PAGE_SHIFT);
+	for (i = 0; i < mi->nr_blks; i++)
+		memblock_x86_register_active_regions(mi->blk[i].nid,
+					mi->blk[i].start >> PAGE_SHIFT,
+					mi->blk[i].end >> PAGE_SHIFT);
 
 	/* for out of order entries */
 	sort_node_map();
@@ -699,7 +702,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size)
 static int __init numa_emulation(unsigned long start_pfn,
 			unsigned long last_pfn, int acpi, int amd)
 {
-	static int nodeid[NR_NODE_MEMBLKS] __initdata;
+	static struct numa_meminfo ei __initdata;
 	u64 addr = start_pfn << PAGE_SHIFT;
 	u64 max_addr = last_pfn << PAGE_SHIFT;
 	int num_nodes;
@@ -725,10 +728,14 @@ static int __init numa_emulation(unsigned long start_pfn,
 	if (num_nodes < 0)
 		return num_nodes;
 
-	for (i = 0; i < ARRAY_SIZE(nodeid); i++)
-		nodeid[i] = i;
+	ei.nr_blks = num_nodes;
+	for (i = 0; i < ei.nr_blks; i++) {
+		ei.blk[i].start = nodes[i].start;
+		ei.blk[i].end = nodes[i].end;
+		ei.blk[i].nid = i;
+	}
 
-	memnode_shift = compute_hash_shift(nodes, num_nodes, nodeid);
+	memnode_shift = compute_hash_shift(&ei);
 	if (memnode_shift < 0) {
 		memnode_shift = 0;
 		printk(KERN_ERR "No NUMA hash function found.  NUMA emulation "
@@ -794,9 +801,7 @@ void __init initmem_init(void)
 		nodes_clear(mem_nodes_parsed);
 		nodes_clear(node_possible_map);
 		nodes_clear(node_online_map);
-		num_node_memblks = 0;
-		memset(node_memblk_range, 0, sizeof(node_memblk_range));
-		memset(memblk_nodeid, 0, sizeof(memblk_nodeid));
+		memset(&numa_meminfo, 0, sizeof(numa_meminfo));
 		memset(numa_nodes, 0, sizeof(numa_nodes));
 		remove_all_active_ranges();
 
-- 
1.7.1


  parent reply	other threads:[~2011-02-12 17:15 UTC|newest]

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-12 17:10 [PATCHSET x86/numa] x86-64, NUMA: bring sanity to NUMA configuration Tejun Heo
2011-02-12 17:10 ` [PATCH 01/26] x86-64, NUMA: Make dummy node initialization path similar to non-dummy ones Tejun Heo
2011-02-12 17:52   ` Yinghai Lu
2011-02-12 17:10 ` [PATCH 02/26] x86-64, NUMA: Simplify hotplug node handling in acpi_numa_memory_affinity_init() Tejun Heo
2011-02-12 17:47   ` Yinghai Lu
2011-02-12 17:56     ` Tejun Heo
2011-02-12 18:04       ` Yinghai Lu
2011-02-12 18:06         ` Tejun Heo
2011-02-12 18:13           ` Yinghai Lu
2011-02-14 11:25             ` Tejun Heo
2011-02-14 16:12               ` Yinghai Lu
2011-02-12 17:10 ` [PATCH 03/26] x86-64, NUMA: Drop @start/last_pfn from initmem_init() Tejun Heo
2011-02-12 17:58   ` Yinghai Lu
2011-02-12 18:03     ` Tejun Heo
2011-02-14 13:50   ` [PATCH UPDATED 03/26] x86, NUMA: Drop @start/last_pfn from initmem_init() initmem_init() Tejun Heo
2011-02-14 14:20     ` Ingo Molnar
2011-02-14 14:58       ` Tejun Heo
2011-02-14 19:03         ` Yinghai Lu
2011-02-14 19:31           ` Tejun Heo
2011-02-15  2:29             ` Ingo Molnar
2011-02-12 17:10 ` [PATCH 04/26] x86-64, NUMA: Unify {acpi|amd}_{numa_init|scan_nodes}() arguments and return values Tejun Heo
2011-02-12 18:39   ` Yinghai Lu
2011-02-14 11:29     ` Tejun Heo
2011-02-14 16:14       ` Yinghai Lu
2011-02-14 16:18         ` Tejun Heo
2011-02-14 18:00           ` Yinghai Lu
2011-02-12 17:10 ` [PATCH 05/26] x86-64, NUMA: Wrap acpi_numa_init() so that failure can be indicated by return value Tejun Heo
2011-02-12 17:10 ` [PATCH 06/26] x86-64, NUMA: Move *_numa_init() invocations into initmem_init() Tejun Heo
2011-02-14  6:10   ` Ankita Garg
2011-02-14 11:09     ` Tejun Heo
2011-02-14 13:51   ` [PATCH UPDATED 06/26] x86, " Tejun Heo
2011-02-14 14:21     ` Ingo Molnar
2011-02-12 17:10 ` [PATCH 07/26] x86-64, NUMA: Restructure initmem_init() Tejun Heo
2011-02-12 17:10 ` [PATCH 08/26] x86-64, NUMA: Use common {cpu|mem}_nodes_parsed Tejun Heo
2011-02-12 17:10 ` [PATCH 09/26] x86-64, NUMA: Remove local variable found from amd_numa_init() Tejun Heo
2011-02-12 17:10 ` [PATCH 10/26] x86-64, NUMA: Move apicid to numa mapping initialization from amd_scan_nodes() to amd_numa_init() Tejun Heo
2011-02-14 22:59   ` Cyrill Gorcunov
2011-02-15  9:36     ` Tejun Heo
2011-02-15 17:31       ` Cyrill Gorcunov
2011-02-15 17:54         ` Yinghai Lu
2011-02-15 18:01           ` Cyrill Gorcunov
2011-02-15 18:27             ` Cyrill Gorcunov
2011-02-15 19:41             ` Yinghai Lu
2011-02-12 17:10 ` [PATCH 11/26] x86-64, NUMA: Use common numa_nodes[] Tejun Heo
2011-02-12 17:10 ` [PATCH 12/26] x86-64, NUMA: Kill {acpi|amd}_get_nodes() Tejun Heo
2011-02-12 17:10 ` [PATCH 13/26] x86-64, NUMA: Factor out memblk handling into numa_{add|register}_memblk() Tejun Heo
2011-02-12 17:10 ` [PATCH 14/26] x86-64, NUMA: Unify use of memblk in all init methods Tejun Heo
2011-02-12 17:10 ` [PATCH 15/26] x86-64, NUMA: Unify the rest of memblk registration Tejun Heo
2011-02-13  0:45   ` Yinghai Lu
2011-02-14 11:32     ` Tejun Heo
2011-02-14 16:08       ` Yinghai Lu
2011-02-14 16:12         ` Tejun Heo
2011-02-14 16:17           ` Yinghai Lu
2011-02-14 16:22             ` Tejun Heo
2011-02-14 18:14               ` Yinghai Lu
2011-02-14 18:27                 ` Tejun Heo
2011-02-14 19:07                   ` Yinghai Lu
2011-02-14 19:30                     ` Tejun Heo
2011-02-14 19:35                       ` Yinghai Lu
2011-02-15  9:11                         ` Tejun Heo
2011-02-15  9:43                           ` Ingo Molnar
2011-02-15 16:49                             ` Tejun Heo
2011-02-16  8:41                               ` Ingo Molnar
2011-02-16  8:48                                 ` Ingo Molnar
2011-02-16  9:01                                   ` Tejun Heo
2011-02-16  9:31                                     ` Ingo Molnar
2011-02-12 17:10 ` [PATCH 16/26] x86-64, NUMA: Kill {acpi|amd|dummy}_scan_nodes() Tejun Heo
2011-02-12 17:10 ` [PATCH 17/26] x86-64, NUMA: Remove %NULL @nodeids handling from compute_hash_shift() Tejun Heo
2011-02-12 17:10 ` Tejun Heo [this message]
2011-02-12 17:10 ` [PATCH 19/26] x86-64, NUMA: Separate out numa_cleanup_meminfo() Tejun Heo
2011-02-12 17:10 ` [PATCH 20/26] x86-64, NUMA: make numa_cleanup_meminfo() prettier Tejun Heo
2011-02-12 17:10 ` [PATCH 21/26] x86-64, NUMA: consolidate and improve memblk sanity checks Tejun Heo
2011-02-12 17:10 ` [PATCH 22/26] x86-64, NUMA: Add common find_node_by_addr() Tejun Heo
2011-02-12 17:11 ` [PATCH 23/26] x86-64, NUMA: kill numa_nodes[] Tejun Heo
2011-02-12 17:11 ` [PATCH 24/26] x86-64, NUMA: Rename cpu_nodes_parsed to numa_nodes_parsed Tejun Heo
2011-02-12 17:11 ` [PATCH 25/26] x86-64, NUMA: Kill mem_nodes_parsed Tejun Heo
2011-02-12 17:11 ` [PATCH 26/26] x86-64, NUMA: Implement generic node distance handling 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=1297530663-26234-19-git-send-email-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=brgerst@gmail.com \
    --cc=gorcunov@gmail.com \
    --cc=hpa@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rientjes@google.com \
    --cc=shaohui.zheng@intel.com \
    --cc=x86@kernel.org \
    --cc=yinghai@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.