x86_64: fix cpu_to_node setup for sparse apic_ids

While booting with SMT disabled in bios, when using acpi srat to setup cpu_to_node[], sparse apic_ids create problems. Here's a fix for that.

Index: linux-2.6.13-rc3/arch/x86_64/mm/srat.c
===================================================================

arch/x86_64/mm/srat.c +11 -6

@@ -20,6 +20,9 @@
 
 static struct acpi_table_slit *acpi_slit;
 
+/* Internal processor count */
+static unsigned int __initdata num_processors = 0;
+
 static nodemask_t nodes_parsed __initdata;
 static nodemask_t nodes_found __initdata;
 static struct node nodes[MAX_NUMNODES] __initdata;

@@ -101,16 +104,18 @@
 		bad_srat();
 		return;
 	}
-	if (pa->apic_id >= NR_CPUS) {
-		printk(KERN_ERR "SRAT: lapic %u too large.\n",
-		       pa->apic_id);
+	if (num_processors >= NR_CPUS) {
+		printk(KERN_ERR "SRAT: Processor #%d (lapic %u) INVALID. (Max ID: %d).\n",
+			num_processors, pa->apic_id, NR_CPUS);
 		bad_srat();
 		return;
 	}
-	cpu_to_node[pa->apic_id] = node;
+	cpu_to_node[num_processors] = node;
 	acpi_numa = 1;
-	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n",
-	       pxm, pa->apic_id, node);
+	printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> CPU %u -> Node %u\n",
+	       pxm, pa->apic_id, num_processors, node);
+
+	num_processors++;
 }
 
 /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */

Quoted 4 lines · Ravikiran G Thirumalai

While booting with SMT disabled in bios, when using acpi srat to setup cpu_to_node[], sparse apic_ids create problems. Here's a fix for that.

Again, I don't have enough info here to judge the urgency of this patch.

What are the consequences and risks of not having this patch in 2.6.13, and to how many machines?

Quoted 4 lines · Ravikiran G Thirumalai

While booting with SMT disabled in bios, when using acpi srat to setup cpu_to_node[], sparse apic_ids create problems. Here's a fix for that.

Again, I don't have enough info here to judge the urgency of this patch.

MM, NUMA : sys_set_mempolicy() doesnt check if mode < 0

A kernel BUG() is triggered by a call to set_mempolicy() with a negative first argument.
This is because the mode is declared as an int, and the validity check doesnt check < 0 values.
Alternatively, mode could be declared as unsigned int or unsigned long.

Thank you
Eric
---------------------------------
Test program for x86_64:
---------------------------------
#include <unistd.h>
#include <stdio.h>
#include <errno.h>
#include <linux/unistd.h>

#define __NR_set_mempolicy 238
#define __sys_set_mempolicy(mode, nmask, maxnode) _syscall3(int, set_mempolicy, int, mode, unsigned long *, nmask, unsigned long, maxnode) static __sys_set_mempolicy(mode, nmask, maxnode)

unsigned long nodes = 3;

int main()
{
int ret = set_mempolicy(-6, &nodes, 2);
printf("result=%d errno=%d\n", ret, errno);
return 0;
}

Signed-off-by Eric Dumazet <[email protected]>

mm/mempolicy.c +1 -1

@@ -443,7 +443,7 @@
 	struct mempolicy *new;
 	DECLARE_BITMAP(nodes, MAX_NUMNODES);
 
-	if (mode > MPOL_MAX)
+	if ((unsigned int)mode > MPOL_MAX)
 		return -EINVAL;
 	err = get_nodes(nodes, nmask, maxnode, mode);
 	if (err)