[PATCH 2/2] Update ibm,client-architecture call field based on device tree

Joel Schopp jschopp at austin.ibm.com
Fri Jan 15 07:41:14 EST 2010


In the previous patch the client-architecture field for the number of
cores supported is set statically as high as is possible.  However, that
static setting could be too high if the system supports smt, resulting
in cpus assigned to Linux that are not booted.  This patch reads the
device tree (before it is unflattened) to determine the amount of smt.
It then dynamically updates the entires in the array with the proper
number of cores supported.  Tests show this correctly detecting SMT4 on
a Power7 and still booting all the supported cores on a large machine.


Signed-off-by:Joel Schopp<jschopp at austin.ibm.com> 
Index: linux-2.6.git/arch/powerpc/kernel/prom_init.c
===================================================================
--- linux-2.6.git.orig/arch/powerpc/kernel/prom_init.c
+++ linux-2.6.git/arch/powerpc/kernel/prom_init.c
@@ -141,6 +141,8 @@ typedef u32 cell_t;
 
 extern void __start(unsigned long r3, unsigned long r4, unsigned long r5);
 
+static int __init prom_smt_way(void);
+
 #ifdef CONFIG_PPC64
 extern int enter_prom(struct prom_args *args, unsigned long entry);
 #else
@@ -811,9 +813,17 @@ static void __init prom_send_capabilitie
 {
 	ihandle elfloader, root;
 	prom_arg_t ret;
+	u32 *cores;
 
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
+		/*
+		 * If you add to the struct, please be sure the 100 index
+		 * didn't change.  The BUILD_BUG_ON is a reminder.
+		 */
+		BUILD_BUG_ON(sizeof(ibm_architecture_vec) != 108);
+		cores = (u32 *) &ibm_architecture_vec[100];
+		*cores = (u32) (NR_CPUS/prom_smt_way());
 		/* try calling the ibm,client-architecture-support method */
 		prom_printf("Calling ibm,client-architecture-support...");
 		if (call_prom_ret("call-method", 3, 2, &ret,
@@ -1031,6 +1041,45 @@ static void __init reserve_mem(u64 base,
 	RELOC(mem_reserve_cnt) = cnt + 1;
 }
 
+
+static int __init prom_smt_way(void)
+{
+	phandle node;
+	char type[64];
+	unsigned int plen;
+
+	for (node = 0; prom_next_node(&node); ) {
+		type[0] = 0;
+		prom_getprop(node, "device_type", type, sizeof(type));
+
+		if (type[0] == 0) {
+			/*
+			 * CHRP Longtrail machines have no device_type
+			 * on the memory node, so check the name instead...
+			 */
+			prom_getprop(node, "name", type, sizeof(type));
+		}
+		if (strcmp(type, RELOC("cpu")))
+			continue;
+
+		/*
+		 * There is an entry for each smt thread, each entry being
+		 * 4 bytes long.  All cpus should have the same number of
+		 * smt threads, so return after finding the first.
+		 */
+		plen = prom_getproplen(node, "ibm,ppc-interrupt-server#s");
+		prom_debug("smt %x\n", (unsigned long) plen);
+		if (plen >= 4)
+			return plen / 4;
+	}
+	/*
+	 * If things go wrong and we get here fallback to SMT1
+	 */
+	prom_debug("unable to determine smt from device tree, guessing smt1\n");
+	return 1;
+
+}
+
 /*
  * Initialize memory allocation mechanism, parse "memory" nodes and
  * obtain that way the top of memory and RMO to setup out local allocator




More information about the Linuxppc-dev mailing list