[PATCH UPDATED 13/33] x86-64, NUMA: Factor out memblk handlinginto numa_{add|register}_memblk()

From: Tejun Heo
Date: Wed Feb 16 2011 - 11:15:42 EST

Next message: Guenter Roeck: "Re: [lm-sensors] [PATCH 3/3] hwmon: (jc42) do not allow writing tolocked registers"
Previous message: Christoph Lameter: "Re: I have a blaze of 353 page allocation failures, all alike"
In reply to: Tejun Heo: "[PATCH 13/33] x86-64, NUMA: Factor out memblk handling into numa_{add|register}_memblk()"
Next in thread: Tejun Heo: "[PATCH 12/33] x86-64, NUMA: Kill {acpi|amd}_get_nodes()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Factor out memblk handling from srat_64.c into two functions in
numa_64.c. This patch doesn't introduce any behavior change. The
next patch will make all init methods use these functions.

- v2: Fixed build failure on 32bit due to misplaced NR_NODE_MEMBLKS.
Reported by Ingo.

Signed-off-by: Tejun Heo <tj@xxxxxxxxxx>
Cc: Yinghai Lu <yinghai@xxxxxxxxxx>
Cc: Brian Gerst <brgerst@xxxxxxxxx>
Cc: Cyrill Gorcunov <gorcunov@xxxxxxxxx>
Cc: Shaohui Zheng <shaohui.zheng@xxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxxxxxxxx>
---
NR_NODE_MEMBLKS move from numa_64.h to numa.h. Git tree updated
accordingly.

Thanks.

arch/x86/include/asm/acpi.h | 1 -
arch/x86/include/asm/numa.h | 3 +
arch/x86/include/asm/numa_64.h | 2 +
arch/x86/mm/numa_64.c | 109 ++++++++++++++++++++++++++++++++++++++++
arch/x86/mm/srat_64.c | 96 +----------------------------------
5 files changed, 117 insertions(+), 94 deletions(-)

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 446a5b9..12bd1fd 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -187,7 +187,6 @@ struct bootnode;
extern int acpi_numa;
extern int x86_acpi_numa_init(void);
extern int acpi_scan_nodes(void);
-#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)

#ifdef CONFIG_NUMA_EMU
extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 26fc6e2..3d4dab4 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -5,6 +5,9 @@
#include <asm/apicdef.h>

#ifdef CONFIG_NUMA
+
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+
/*
* __apicid_to_node[] stores the raw mapping between physical apicid and
* node and is used to initialize cpu_to_node mapping.
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index d3a4514..3306a2b 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -32,6 +32,8 @@ extern nodemask_t mem_nodes_parsed __initdata;
extern struct bootnode numa_nodes[MAX_NUMNODES] __initdata;

extern int __cpuinit numa_cpu_node(int cpu);
+extern int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+extern int __init numa_register_memblks(void);

#ifdef CONFIG_NUMA_EMU
#define FAKE_NODE_MIN_SIZE ((u64)32 << 20)
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 82ee308..a1d702d 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -33,6 +33,10 @@ 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;
+
struct bootnode numa_nodes[MAX_NUMNODES] __initdata;

/*
@@ -184,6 +188,43 @@ static void * __init early_node_mem(int nodeid, unsigned long start,
return NULL;
}

+static __init int conflicting_memblks(unsigned long start, unsigned long end)
+{
+ int i;
+ for (i = 0; i < num_node_memblks; i++) {
+ struct bootnode *nd = &node_memblk_range[i];
+ if (nd->start == nd->end)
+ continue;
+ if (nd->end > start && nd->start < end)
+ return memblk_nodeid[i];
+ if (nd->end == end && nd->start == start)
+ return memblk_nodeid[i];
+ }
+ return -1;
+}
+
+int __init numa_add_memblk(int nid, u64 start, u64 end)
+{
+ int i;
+
+ i = conflicting_memblks(start, end);
+ if (i == nid) {
+ printk(KERN_WARNING "NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n",
+ nid, start, end, numa_nodes[i].start, numa_nodes[i].end);
+ } else if (i >= 0) {
+ printk(KERN_ERR "NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n",
+ nid, start, end, i,
+ numa_nodes[i].start, numa_nodes[i].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++;
+ return 0;
+}
+
static __init void cutoff_node(int i, unsigned long start, unsigned long end)
{
struct bootnode *nd = &numa_nodes[i];
@@ -246,6 +287,71 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end)
node_set_online(nodeid);
}

+int __init numa_register_memblks(void)
+{
+ 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) {
+ int j, k;
+
+ for (j = i + 1; j < num_node_memblks; ++j) {
+ unsigned long start, end;
+
+ if (memblk_nodeid[i] != memblk_nodeid[j])
+ 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])
+ continue;
+ if (start < node_memblk_range[k].end &&
+ end > node_memblk_range[k].start)
+ break;
+ }
+ if (k < num_node_memblks)
+ 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);
+ 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,
+ 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));
+ --j;
+ }
+ }
+
+ memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks,
+ memblk_nodeid);
+ 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);
+ return 0;
+}
+
#ifdef CONFIG_NUMA_EMU
/* Numa emulation */
static struct bootnode nodes[MAX_NUMNODES] __initdata;
@@ -653,6 +759,9 @@ 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_nodes, 0, sizeof(numa_nodes));

if (numa_init[i]() < 0)
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 82b1087..341b371 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -30,30 +30,11 @@ static struct acpi_table_slit *acpi_slit;

static struct bootnode nodes_add[MAX_NUMNODES];

-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 __init int setup_node(int pxm)
{
return acpi_map_pxm_to_node(pxm);
}

-static __init int conflicting_memblks(unsigned long start, unsigned long end)
-{
- int i;
- for (i = 0; i < num_node_memblks; i++) {
- struct bootnode *nd = &node_memblk_range[i];
- if (nd->start == nd->end)
- continue;
- if (nd->end > start && nd->start < end)
- return memblk_nodeid[i];
- if (nd->end == end && nd->start == start)
- return memblk_nodeid[i];
- }
- return -1;
-}
-
static __init void bad_srat(void)
{
int i;
@@ -233,7 +214,6 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
struct bootnode *nd;
unsigned long start, end;
int node, pxm;
- int i;

if (srat_disabled())
return;
@@ -255,16 +235,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
bad_srat();
return;
}
- i = conflicting_memblks(start, end);
- if (i == node) {
- printk(KERN_WARNING
- "SRAT: Warning: PXM %d (%lx-%lx) overlaps with itself (%Lx-%Lx)\n",
- pxm, start, end, numa_nodes[i].start, numa_nodes[i].end);
- } else if (i >= 0) {
- printk(KERN_ERR
- "SRAT: PXM %d (%lx-%lx) overlaps with PXM %d (%Lx-%Lx)\n",
- pxm, start, end, node_to_pxm(i),
- numa_nodes[i].start, numa_nodes[i].end);
+
+ if (numa_add_memblk(node, start, end) < 0) {
bad_srat();
return;
}
@@ -285,11 +257,6 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma)
}
} else
update_nodes_add(node, start, end);
-
- node_memblk_range[num_node_memblks].start = start;
- node_memblk_range[num_node_memblks].end = end;
- memblk_nodeid[num_node_memblks] = node;
- num_node_memblks++;
}

/* Sanity check to catch more bad SRATs (they are amazingly common).
@@ -341,68 +308,11 @@ int __init acpi_scan_nodes(void)
if (acpi_numa <= 0)
return -1;

- /*
- * 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) {
- int j, k;
-
- for (j = i + 1; j < num_node_memblks; ++j) {
- unsigned long start, end;
-
- if (memblk_nodeid[i] != memblk_nodeid[j])
- 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])
- continue;
- if (start < node_memblk_range[k].end &&
- end > node_memblk_range[k].start)
- break;
- }
- if (k < num_node_memblks)
- 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);
- printk(KERN_INFO "SRAT: 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,
- 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));
- --j;
- }
- }
-
- memnode_shift = compute_hash_shift(node_memblk_range, num_node_memblks,
- memblk_nodeid);
- if (memnode_shift < 0) {
- printk(KERN_ERR
- "SRAT: No NUMA node hash function found. Contact maintainer\n");
+ if (numa_register_memblks() < 0) {
bad_srat();
return -1;
}

- 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 out of order entries in SRAT */
sort_node_map();
if (!nodes_cover_memory(numa_nodes)) {
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Guenter Roeck: "Re: [lm-sensors] [PATCH 3/3] hwmon: (jc42) do not allow writing tolocked registers"
Previous message: Christoph Lameter: "Re: I have a blaze of 353 page allocation failures, all alike"
In reply to: Tejun Heo: "[PATCH 13/33] x86-64, NUMA: Factor out memblk handling into numa_{add|register}_memblk()"
Next in thread: Tejun Heo: "[PATCH 12/33] x86-64, NUMA: Kill {acpi|amd}_get_nodes()"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]