NUMA CPU Reconfiguration using PRRN

Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
@@ -276,6 +276,7 @@
 		const char *uname, int depth, void *data);
 
 extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+extern int update_devicetree(s32 scope);
 
 #ifdef CONFIG_PPC_RTAS_DAEMON
 extern void rtas_cancel_event_scan(void);

Index: powerpc/arch/powerpc/platforms/pseries/mobility.c
===================================================================
@@ -19,6 +19,7 @@
 #include <linux/slab.h>
 
 #include <asm/rtas.h>
+#include <asm/machdep.h>
 #include "pseries.h"
 
 static struct kobject *mobility_kobj;

@@ -37,14 +38,16 @@
 #define UPDATE_DT_NODE	0x02000000
 #define ADD_DT_NODE	0x03000000
 
-static int mobility_rtas_call(int token, char *buf)
+#define MIGRATION_SCOPE	(1)
+
+static int mobility_rtas_call(int token, char *buf, s32 scope)
 {
 	int rc;
 
 	spin_lock(&rtas_data_buf_lock);
 
 	memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE);
-	rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1);
+	rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, scope);
 	memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE);
 
 	spin_unlock(&rtas_data_buf_lock);

@@ -123,7 +126,7 @@
 	return 0;
 }
 
-static int update_dt_node(u32 phandle)
+static int update_dt_node(u32 phandle, s32 scope)
 {
 	struct update_props_workarea *upwa;
 	struct device_node *dn;

@@ -151,7 +154,8 @@
 	upwa->phandle = phandle;
 
 	do {
-		rc = mobility_rtas_call(update_properties_token, rtas_buf);
+		rc = mobility_rtas_call(update_properties_token, rtas_buf,
+					scope);
 		if (rc < 0)
 			break;
 

@@ -219,7 +223,7 @@
 	return rc;
 }
 
-static int pseries_devicetree_update(void)
+static int pseries_devicetree_update(s32 scope)
 {
 	char *rtas_buf;
 	u32 *data;

@@ -235,7 +239,7 @@
 		return -ENOMEM;
 
 	do {
-		rc = mobility_rtas_call(update_nodes_token, rtas_buf);
+		rc = mobility_rtas_call(update_nodes_token, rtas_buf, scope);
 		if (rc && rc != 1)
 			break;
 

@@ -256,7 +260,7 @@
 					delete_dt_node(phandle);
 					break;
 				case UPDATE_DT_NODE:
-					update_dt_node(phandle);
+					update_dt_node(phandle, scope);
 					break;
 				case ADD_DT_NODE:
 					drc_index = *data++;

@@ -276,7 +280,7 @@
 	int rc;
 	int activate_fw_token;
 
-	rc = pseries_devicetree_update();
+	rc = pseries_devicetree_update(MIGRATION_SCOPE);
 	if (rc) {
 		printk(KERN_ERR "Initial post-mobility device tree update "
 		       "failed: %d\n", rc);

@@ -292,7 +296,7 @@
 
 	rc = rtas_call(activate_fw_token, 0, 1, NULL);
 	if (!rc) {
-		rc = pseries_devicetree_update();
+		rc = pseries_devicetree_update(MIGRATION_SCOPE);
 		if (rc)
 			printk(KERN_ERR "Secondary post-mobility device tree "
 			       "update failed: %d\n", rc);

@@ -346,6 +350,8 @@
 {
 	int rc;
 
+	ppc_md.update_devicetree = pseries_devicetree_update;
+
 	mobility_kobj = kobject_create_and_add("mobility", kernel_kobj);
 	if (!mobility_kobj)
 		return -ENOMEM;

Index: powerpc/arch/powerpc/include/asm/machdep.h
===================================================================
@@ -256,6 +256,8 @@
 	ssize_t (*cpu_probe)(const char *, size_t);
 	ssize_t (*cpu_release)(const char *, size_t);
 #endif
+
+	int (*update_devicetree)(s32);
 };
 
 extern void e500_idle(void);

Index: powerpc/arch/powerpc/kernel/rtas.c
===================================================================
@@ -1085,3 +1085,13 @@
 	timebase = 0;
 	arch_spin_unlock(&timebase_lock);
 }
+
+int update_devicetree(s32 scope)
+{
+	int rc = 0;
+
+	if (ppc_md.update_devicetree)
+		rc = ppc_md.update_devicetree(scope);
+
+	return rc;
+}

Index: powerpc/arch/powerpc/platforms/pseries/mobility.c
===================================================================
@@ -135,6 +135,7 @@
 	char *prop_data;
 	char *rtas_buf;
 	int update_properties_token;
+	u32 vd;
 
 	update_properties_token = rtas_token("ibm,update-properties");
 	if (update_properties_token == RTAS_UNKNOWN_SERVICE)

@@ -161,13 +162,24 @@
 
 		prop_data = rtas_buf + sizeof(*upwa);
 
-		for (i = 0; i < upwa->nprops; i++) {
+		/* The first element of the buffer is the path of the node
+		 * being updated in the form of a 8 byte string length
+		 * followed by the string. Skip past this to get to the
+		 * properties being updated.
+		 */
+		vd = *prop_data++;
+		prop_data += vd;
+
+		/* The path we skipped over is counted as one of the elements
+		 * returned so start counting at one.
+		 */
+		for (i = 1; i < upwa->nprops; i++) {
 			char *prop_name;
-			u32 vd;
 
-			prop_name = prop_data + 1;
+			prop_name = prop_data;
 			prop_data += strlen(prop_name) + 1;
-			vd = *prop_data++;
+			vd = *(u32 *)prop_data;
+			prop_data += sizeof(vd);
 
 			switch (vd) {
 			case 0x00000000:

Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
@@ -143,6 +143,8 @@
 #define RTAS_TYPE_PMGM_TIME_ALARM	0x6f
 #define RTAS_TYPE_PMGM_CONFIG_CHANGE	0x70
 #define RTAS_TYPE_PMGM_SERVICE_PROC	0x71
+/* Platform Resource Reassignment Notification */
+#define RTAS_TYPE_PRRN			0xA0
 
 /* RTAS check-exception vector offset */
 #define RTAS_VECTOR_EXTERNAL_INTERRUPT	0x500

Index: powerpc/arch/powerpc/kernel/rtasd.c
===================================================================
@@ -87,6 +87,8 @@
 			return "Resource Deallocation Event";
 		case RTAS_TYPE_DUMP:
 			return "Dump Notification Event";
+		case RTAS_TYPE_PRRN:
+			return "Platform Resource Reassignment Event";
 	}
 
 	return rtas_type[0];

@@ -265,7 +267,40 @@
 		spin_unlock_irqrestore(&rtasd_log_lock, s);
 		return;
 	}
+}
+
+static s32 update_scope;
+
+static void prrn_work_fn(struct work_struct *work)
+{
+	/*
+	 * For PRRN, we must pass the negative of the scope value in
+	 * the RTAS event.
+	 */
+	if (ppc_md.update_devicetree)
+		ppc_md.update_devicetree(-update_scope);
+}
+
+static DECLARE_WORK(prrn_work, prrn_work_fn);
+
+void prrn_schedule_update(u32 scope)
+{
+	flush_work(&prrn_work);
+	update_scope = scope;
+	schedule_work(&prrn_work);
+}
+
+static void pseries_handle_event(const struct rtas_error_log *log)
+{
+	pSeries_log_error((char *)log, ERR_TYPE_RTAS_LOG, 0);
+
+	if (log->type == RTAS_TYPE_PRRN)
+		/* For PRRN Events the extended log length is used to denote
+		 * the scope for calling rtas update-nodes.
+		 */
+		prrn_schedule_update(log->extended_log_length);
 
+	return;
 }
 
 static int rtas_log_open(struct inode * inode, struct file * file)

@@ -389,7 +424,7 @@
 		}
 
 		if (error == 0)
-			pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0);
+			pseries_handle_event((struct rtas_error_log *)logdata);
 
 	} while(error == 0);
 }

Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
@@ -74,6 +74,79 @@
 #define DRCONF_MEM_AI_INVALID	0x00000040
 #define DRCONF_MEM_RESERVED	0x00000080
 
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+/*
+ * There are two methods for telling firmware what our capabilities are.
+ * Newer machines have an "ibm,client-architecture-support" method on the
+ * root node.  For older machines, we have to call the "process-elf-header"
+ * method in the /packages/elf-loader node, passing it a fake 32-bit
+ * ELF header containing a couple of PT_NOTE sections that contain
+ * structures that contain various information.
+ */
+
+/* New method - extensible architecture description vector. */
+
+/* Option vector bits - generic bits in byte 1 */
+#define OV_IGNORE		0x80	/* ignore this vector */
+#define OV_CESSATION_POLICY	0x40	/* halt if unsupported option present*/
+
+/* Option vector 1: processor architectures supported */
+#define OV1_PPC_2_00		0x80	/* set if we support PowerPC 2.00 */
+#define OV1_PPC_2_01		0x40	/* set if we support PowerPC 2.01 */
+#define OV1_PPC_2_02		0x20	/* set if we support PowerPC 2.02 */
+#define OV1_PPC_2_03		0x10	/* set if we support PowerPC 2.03 */
+#define OV1_PPC_2_04		0x08	/* set if we support PowerPC 2.04 */
+#define OV1_PPC_2_05		0x04	/* set if we support PowerPC 2.05 */
+#define OV1_PPC_2_06		0x02	/* set if we support PowerPC 2.06 */
+#define OV1_PPC_2_07		0x01	/* set if we support PowerPC 2.07 */
+
+/* Option vector 2: Open Firmware options supported */
+#define OV2_REAL_MODE		0x20	/* set if we want OF in real mode */
+
+/* Option vector 3: processor options supported */
+#define OV3_FP			0x80	/* floating point */
+#define OV3_VMX			0x40	/* VMX/Altivec */
+#define OV3_DFP			0x20	/* decimal FP */
+
+/* Option vector 4: IBM PAPR implementation */
+#define OV4_MIN_ENT_CAP		0x01	/* minimum VP entitled capacity */
+
+/* Option vector 5: PAPR/OF options supported */
+#define OV5_LPAR		0x80	/* logical partitioning supported */
+#define OV5_SPLPAR		0x40	/* shared-processor LPAR supported */
+/* ibm,dynamic-reconfiguration-memory property supported */
+#define OV5_DRCONF_MEMORY	0x20
+#define OV5_LARGE_PAGES		0x10	/* large pages supported */
+#define OV5_DONATE_DEDICATE_CPU	0x02	/* donate dedicated CPU support */
+/* PCIe/MSI support.  Without MSI full PCIe is not supported */
+#ifdef CONFIG_PCI_MSI
+#define OV5_MSI			0x01	/* PCIe/MSI support */
+#else
+#define OV5_MSI			0x00
+#endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_PPC_SMLPAR
+#define OV5_CMO			0x80	/* Cooperative Memory Overcommitment */
+#define OV5_XCMO		0x40	/* Page Coalescing */
+#else
+#define OV5_CMO			0x00
+#define OV5_XCMO		0x00
+#endif
+#define OV5_TYPE1_AFFINITY	0x80	/* Type 1 NUMA affinity */
+#define OV5_PFO_HW_RNG		0x80	/* PFO Random Number Generator */
+#define OV5_PFO_HW_842		0x40	/* PFO Compression Accelerator */
+#define OV5_PFO_HW_ENCR		0x20	/* PFO Encryption Accelerator */
+#define OV5_SUB_PROCESSORS	0x01	/* 1,2,or 4 Sub-Processors supported */
+
+/* Option Vector 6: IBM PAPR hints */
+#define OV6_LINUX		0x02	/* Linux is our OS */
+
+/*
+ * The architecture vector has an array of PVR mask/value pairs,
+ * followed by # option vectors - 1, followed by the option vectors.
+ */
+extern unsigned char ibm_architecture_vec[];
+#endif
+
 /* These includes are put at the bottom because they may contain things
  * that are overridden by this file.  Ideally they shouldn't be included
  * by this file, but there are a bunch of .c files that currently depend

87 lines not on this page · raw message

Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
@@ -111,31 +111,27 @@
 /* Option vector 4: IBM PAPR implementation */
 #define OV4_MIN_ENT_CAP		0x01	/* minimum VP entitled capacity */
 
-/* Option vector 5: PAPR/OF options supported */
-#define OV5_LPAR		0x80	/* logical partitioning supported */
-#define OV5_SPLPAR		0x40	/* shared-processor LPAR supported */
+/* Option vector 5: PAPR/OF options supported
+ * Thses bits are also used for the platform_has_feature() call so
+ * we encode the vector index in the define and use the OV5_FEAT()
+ * and OV5_INDX() macros to extract the desired information.
+ */
+#define OV5_FEAT(x)	((x) & 0xff)
+#define OV5_INDX(x)	((x) >> 8)
+#define OV5_LPAR		0x0280	/* logical partitioning supported */
+#define OV5_SPLPAR		0x0240	/* shared-processor LPAR supported */
 /* ibm,dynamic-reconfiguration-memory property supported */
-#define OV5_DRCONF_MEMORY	0x20
-#define OV5_LARGE_PAGES		0x10	/* large pages supported */
-#define OV5_DONATE_DEDICATE_CPU	0x02	/* donate dedicated CPU support */
-/* PCIe/MSI support.  Without MSI full PCIe is not supported */
-#ifdef CONFIG_PCI_MSI
-#define OV5_MSI			0x01	/* PCIe/MSI support */
-#else
-#define OV5_MSI			0x00
-#endif /* CONFIG_PCI_MSI */
-#ifdef CONFIG_PPC_SMLPAR
-#define OV5_CMO			0x80	/* Cooperative Memory Overcommitment */
-#define OV5_XCMO		0x40	/* Page Coalescing */
-#else
-#define OV5_CMO			0x00
-#define OV5_XCMO		0x00
-#endif
-#define OV5_TYPE1_AFFINITY	0x80	/* Type 1 NUMA affinity */
-#define OV5_PFO_HW_RNG		0x80	/* PFO Random Number Generator */
-#define OV5_PFO_HW_842		0x40	/* PFO Compression Accelerator */
-#define OV5_PFO_HW_ENCR		0x20	/* PFO Encryption Accelerator */
-#define OV5_SUB_PROCESSORS	0x01	/* 1,2,or 4 Sub-Processors supported */
+#define OV5_DRCONF_MEMORY	0x0220
+#define OV5_LARGE_PAGES		0x0210	/* large pages supported */
+#define OV5_DONATE_DEDICATE_CPU	0x0202	/* donate dedicated CPU support */
+#define OV5_MSI			0x0201	/* PCIe/MSI support */
+#define OV5_CMO			0x0480	/* Cooperative Memory Overcommitment */
+#define OV5_XCMO		0x0440	/* Page Coalescing */
+#define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
+#define OV5_PFO_HW_RNG		0x0E80	/* PFO Random Number Generator */
+#define OV5_PFO_HW_842		0x0E40	/* PFO Compression Accelerator */
+#define OV5_PFO_HW_ENCR		0x0E20	/* PFO Encryption Accelerator */
+#define OV5_SUB_PROCESSORS	0x0F01	/* 1,2,or 4 Sub-Processors supported */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */

@@ -145,6 +141,7 @@
  * followed by # option vectors - 1, followed by the option vectors.
  */
 extern unsigned char ibm_architecture_vec[];
+bool platform_has_feature(unsigned int);
 #endif
 
 /* These includes are put at the bottom because they may contain things

Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
@@ -684,11 +684,21 @@
 	/* option vector 5: PAPR/OF options */
 	19 - 2,				/* length */
 	0,				/* don't ignore, don't halt */
-	OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY |
-	OV5_DONATE_DEDICATE_CPU | OV5_MSI,
+	OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
+	OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
+#ifdef CONFIG_PCI_MSI
+	/* PCIe/MSI support.  Without MSI full PCIe is not supported */
+	OV5_FEAT(OV5_MSI),
+#else
+	0,
+#endif
+	0,
+#ifdef CONFIG_PPC_SMLPAR
+	OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO),
+#else
 	0,
-	OV5_CMO | OV5_XCMO,
-	OV5_TYPE1_AFFINITY,
+#endif
+	OV5_FEAT(OV5_TYPE1_AFFINITY),
 	0,
 	0,
 	0,

@@ -702,8 +712,9 @@
 	0,
 	0,
 	0,
-	OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842,
-	OV5_SUB_PROCESSORS,
+	OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
+	OV5_FEAT(OV5_PFO_HW_842),
+	OV5_FEAT(OV5_SUB_PROCESSORS),
 	/* option vector 6: IBM PAPR hints */
 	4 - 2,				/* length */
 	0,

Index: powerpc/arch/powerpc/platforms/pseries/setup.c
===================================================================
@@ -628,25 +628,39 @@
  * Called very early, MMU is off, device-tree isn't unflattened
  */
 
-static int __init pSeries_probe_hypertas(unsigned long node,
-					 const char *uname, int depth,
-					 void *data)
+static int __init pseries_probe_fw_features(unsigned long node,
+					    const char *uname, int depth,
+					    void *data)
 {
-	const char *hypertas;
+	const char *prop;
 	unsigned long len;
+	static int hypertas_found;
+	static int vec5_found;
 
-	if (depth != 1 ||
-	    (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
+	if (depth != 1)
 		return 0;
 
-	hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len);
-	if (!hypertas)
-		return 1;
+	if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) {
+		prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions",
+					   &len);
+		if (prop) {
+			powerpc_firmware_features |= FW_FEATURE_LPAR;
+			fw_hypertas_feature_init(prop, len);
+		}
+
+		hypertas_found = 1;
+	}
+
+	if (!strcmp(uname, "chosen")) {
+		prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
+					   &len);
+		if (prop)
+			fw_vec5_feature_init(prop, len);
 
-	powerpc_firmware_features |= FW_FEATURE_LPAR;
-	fw_feature_init(hypertas, len);
+		vec5_found = 1;
+	}
 
-	return 1;
+	return hypertas_found && vec5_found;
 }
 
 static int __init pSeries_probe(void)

@@ -669,7 +683,7 @@
 	pr_debug("pSeries detected, looking for LPAR capability...\n");
 
 	/* Now try to figure out if we are running on LPAR */
-	of_scan_flat_dt(pSeries_probe_hypertas, NULL);
+	of_scan_flat_dt(pseries_probe_fw_features, NULL);
 
 	if (firmware_has_feature(FW_FEATURE_LPAR))
 		hpte_init_lpar();

82 lines not on this page · raw message

Index: powerpc/arch/powerpc/include/asm/firmware.h
===================================================================
@@ -51,6 +51,7 @@
 #define FW_FEATURE_OPALv2	ASM_CONST(0x0000000020000000)
 #define FW_FEATURE_SET_MODE	ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
+#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
 
 #ifndef __ASSEMBLY__
 

@@ -65,7 +66,8 @@
 		FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
 		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
-		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY,
+		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
+		FW_FEATURE_TYPE1_AFFINITY,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
 	FW_FEATURE_POWERNV_ALWAYS = 0,

Index: powerpc/arch/powerpc/platforms/pseries/pseries.h
===================================================================
@@ -19,7 +19,10 @@
 
 #include <linux/of.h>
 
-extern void __init fw_feature_init(const char *hypertas, unsigned long len);
+extern void __init fw_hypertas_feature_init(const char *hypertas,
+					    unsigned long len);
+extern void __init fw_vec5_feature_init(const char *hypertas,
+					unsigned long len);
 
 struct pt_regs;
 

Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
@@ -291,9 +291,7 @@
 static int __init find_min_common_depth(void)
 {
 	int depth;
-	struct device_node *chosen;
 	struct device_node *root;
-	const char *vec5;
 
 	if (firmware_has_feature(FW_FEATURE_OPAL))
 		root = of_find_node_by_path("/ibm,opal");

@@ -325,24 +323,10 @@
 
 	distance_ref_points_depth /= sizeof(int);
 
-#define VEC5_AFFINITY_BYTE	5
-#define VEC5_AFFINITY		0x80
-
-	if (firmware_has_feature(FW_FEATURE_OPAL))
+	if (firmware_has_feature(FW_FEATURE_OPAL) ||
+	    firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
+		dbg("Using form 1 affinity\n");
 		form1_affinity = 1;
-	else {
-		chosen = of_find_node_by_path("/chosen");
-		if (chosen) {
-			vec5 = of_get_property(chosen,
-					       "ibm,architecture-vec-5", NULL);
-			if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
-							VEC5_AFFINITY)) {
-				dbg("Using form 1 affinity\n");
-				form1_affinity = 1;
-			}
-
-			of_node_put(chosen);
-		}
 	}
 
 	if (form1_affinity) {

Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
@@ -128,6 +128,7 @@
 #define OV5_CMO			0x0480	/* Cooperative Memory Overcommitment */
 #define OV5_XCMO		0x0440	/* Page Coalescing */
 #define OV5_TYPE1_AFFINITY	0x0580	/* Type 1 NUMA affinity */
+#define OV5_PRRN		0x0540	/* Platform Resource Reassignment */
 #define OV5_PFO_HW_RNG		0x0E80	/* PFO Random Number Generator */
 #define OV5_PFO_HW_842		0x0E40	/* PFO Compression Accelerator */
 #define OV5_PFO_HW_ENCR		0x0E20	/* PFO Encryption Accelerator */

161 lines not on this page · raw message

Index: powerpc/arch/powerpc/include/asm/firmware.h
===================================================================
@@ -52,6 +52,7 @@
 #define FW_FEATURE_SET_MODE	ASM_CONST(0x0000000040000000)
 #define FW_FEATURE_BEST_ENERGY	ASM_CONST(0x0000000080000000)
 #define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
+#define FW_FEATURE_PRRN		ASM_CONST(0x0000000200000000)
 
 #ifndef __ASSEMBLY__
 

@@ -67,7 +68,7 @@
 		FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
 		FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
 		FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
-		FW_FEATURE_TYPE1_AFFINITY,
+		FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
 	FW_FEATURE_PSERIES_ALWAYS = 0,
 	FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
 	FW_FEATURE_POWERNV_ALWAYS = 0,

Index: powerpc/arch/powerpc/platforms/pseries/firmware.c
===================================================================
@@ -113,6 +113,7 @@
 static __initdata struct vec5_fw_feature
 vec5_fw_features_table[FIRMWARE_MAX_FEATURES] = {
 	{FW_FEATURE_TYPE1_AFFINITY,	OV5_TYPE1_AFFINITY},
+	{FW_FEATURE_PRRN,		OV5_PRRN},
 };
 
 void __init fw_vec5_feature_init(const char *vec5, unsigned long len)

Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
@@ -22,6 +22,7 @@
 #include <linux/pfn.h>
 #include <linux/cpuset.h>
 #include <linux/node.h>
+#include <linux/stop_machine.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>

@@ -1254,6 +1255,13 @@
 
 /* Virtual Processor Home Node (VPHN) support */
 #ifdef CONFIG_PPC_SPLPAR
+struct topology_update_data {
+	struct topology_update_data *next;
+	unsigned int cpu;
+	int old_nid;
+	int new_nid;
+};
+
 static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
 static cpumask_t cpu_associativity_changes_mask;
 static int vphn_enabled;

@@ -1405,41 +1413,79 @@
 }
 
 /*
+ * Update the CPU maps and sysfs entries for a single CPU when its NUMA
+ * characteristics change. This function doesn't perform any locking and is
+ * only safe to call from stop_machine().
+ */
+static int update_cpu_topology(void *data)
+{
+	struct topology_update_data *update;
+	unsigned long cpu;
+
+	if (!data)
+		return -EINVAL;
+
+	cpu = get_cpu();
+
+	for (update = data; update; update = update->next) {
+		if (cpu != update->cpu)
+			continue;
+
+		unregister_cpu_under_node(update->cpu, update->old_nid);
+		unmap_cpu_from_node(update->cpu);
+		map_cpu_to_node(update->cpu, update->new_nid);
+		register_cpu_under_node(update->cpu, update->new_nid);
+	}
+
+	return 0;
+}
+
+/*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
  */
 int arch_update_cpu_topology(void)
 {
-	int cpu, nid, old_nid, changed = 0;
+	unsigned int cpu, changed = 0;
+	struct topology_update_data *updates, *ud;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
 	struct device *dev;
+	int weight, i = 0;
+
+	weight = cpumask_weight(&cpu_associativity_changes_mask);
+	if (!weight)
+		return 0;
+
+	updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
+	if (!updates)
+		return 0;
 
 	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
+		ud = &updates[i++];
+		ud->cpu = cpu;
 		vphn_get_associativity(cpu, associativity);
-		nid = associativity_to_nid(associativity);
+		ud->new_nid = associativity_to_nid(associativity);
 
-		if (nid < 0 || !node_online(nid))
-			nid = first_online_node;
+		if (ud->new_nid < 0 || !node_online(ud->new_nid))
+			ud->new_nid = first_online_node;
 
-		old_nid = numa_cpu_lookup_table[cpu];
+		ud->old_nid = numa_cpu_lookup_table[cpu];
 
-		/* Disable hotplug while we update the cpu
-		 * masks and sysfs.
-		 */
-		get_online_cpus();
-		unregister_cpu_under_node(cpu, old_nid);
-		unmap_cpu_from_node(cpu);
-		map_cpu_to_node(cpu, nid);
-		register_cpu_under_node(cpu, nid);
-		put_online_cpus();
+		if (i < weight)
+			ud->next = &updates[i];
+	}
+
+	stop_machine(update_cpu_topology, &updates[0], cpu_online_mask);
 
-		dev = get_cpu_device(cpu);
+	for (ud = &updates[0]; ud; ud = ud->next) {
+		dev = get_cpu_device(ud->cpu);
 		if (dev)
 			kobject_uevent(&dev->kobj, KOBJ_CHANGE);
-		cpumask_clear_cpu(cpu, &cpu_associativity_changes_mask);
+		cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
 		changed = 1;
 	}
 
+	kfree(updates);
 	return changed;
 }
 

@@ -1488,10 +1534,10 @@
 	int rc = NOTIFY_DONE;
 
 	switch (action) {
-	case OF_RECONFIG_ADD_PROPERTY:
 	case OF_RECONFIG_UPDATE_PROPERTY:
 		update = (struct of_prop_reconfig *)data;
-		if (!of_prop_cmp(update->dn->type, "cpu")) {
+		if (!of_prop_cmp(update->dn->type, "cpu") &&
+		    !of_prop_cmp(update->prop->name, "ibm,associativity")) {
 			u32 core_id;
 			of_property_read_u32(update->dn, "reg", &core_id);
 			stage_topology_update(core_id);

Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
@@ -30,6 +30,7 @@
 #include <asm/paca.h>
 #include <asm/hvcall.h>
 #include <asm/setup.h>
+#include <asm/vdso.h>
 
 static int numa_enabled = 1;
 

@@ -1434,6 +1435,7 @@
 		unregister_cpu_under_node(update->cpu, update->old_nid);
 		unmap_cpu_from_node(update->cpu);
 		map_cpu_to_node(update->cpu, update->new_nid);
+		vdso_getcpu_init();
 		register_cpu_under_node(update->cpu, update->new_nid);
 	}
 

@@ -1449,6 +1451,7 @@
 	unsigned int cpu, changed = 0;
 	struct topology_update_data *updates, *ud;
 	unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	cpumask_t updated_cpus;
 	struct device *dev;
 	int weight, i = 0;
 

@@ -1460,6 +1463,8 @@
 	if (!updates)
 		return 0;
 
+	cpumask_clear(&updated_cpus);
+
 	for_each_cpu(cpu, &cpu_associativity_changes_mask) {
 		ud = &updates[i++];
 		ud->cpu = cpu;

@@ -1470,12 +1475,13 @@
 			ud->new_nid = first_online_node;
 
 		ud->old_nid = numa_cpu_lookup_table[cpu];
+		cpumask_set_cpu(cpu, &updated_cpus);
 
 		if (i < weight)
 			ud->next = &updates[i];
 	}
 
-	stop_machine(update_cpu_topology, &updates[0], cpu_online_mask);
+	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		dev = get_cpu_device(ud->cpu);

Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
@@ -1572,9 +1572,8 @@
 			vphn_enabled = 0;
 			rc = of_reconfig_notifier_register(&dt_update_nb);
 		}
-	} else if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
+	} else if (firmware_has_feature(FW_FEATURE_VPHN) &&
 		   get_lppaca()->shared_proc) {
-		/* Disabled until races with load balancing are fixed */
 		if (!vphn_enabled) {
 			prrn_enabled = 0;
 			vphn_enabled = 1;

Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
@@ -698,7 +698,7 @@
 #else
 	0,
 #endif
-	OV5_FEAT(OV5_TYPE1_AFFINITY),
+	OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
 	0,
 	0,
 	0,

Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
@@ -23,6 +23,9 @@
 #include <linux/cpuset.h>
 #include <linux/node.h>
 #include <linux/stop_machine.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>

@@ -1585,7 +1588,6 @@
 
 	return rc;
 }
-__initcall(start_topology_update);
 
 /*
  * Disable polling for VPHN associativity changes.

@@ -1604,4 +1606,62 @@
 
 	return rc;
 }
+
+inline int prrn_is_enabled(void)
+{
+	return prrn_enabled;
+}
+
+static int topology_read(struct seq_file *file, void *v)
+{
+	if (vphn_enabled || prrn_enabled)
+		seq_puts(file, "on\n");
+	else
+		seq_puts(file, "off\n");
+
+	return 0;
+}
+
+static int topology_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, topology_read, NULL);
+}
+
+static ssize_t topology_write(struct file *file, const char __user *buf,
+			      size_t count, loff_t *off)
+{
+	char kbuf[4]; /* "on" or "off" plus null. */
+	int read_len;
+
+	read_len = count < 3 ? count : 3;
+	if (copy_from_user(kbuf, buf, read_len))
+		return -EINVAL;
+
+	kbuf[read_len] = '\0';
+
+	if (!strncmp(kbuf, "on", 2))
+		start_topology_update();
+	else if (!strncmp(kbuf, "off", 3))
+		stop_topology_update();
+	else
+		return -EINVAL;
+
+	return count;
+}
+
+static const struct file_operations topology_ops = {
+	.read = seq_read,
+	.write = topology_write,
+	.open = topology_open,
+	.release = single_release
+};
+
+static int topology_update_init(void)
+{
+	start_topology_update();
+	proc_create("powerpc/topology_updates", 644, NULL, &topology_ops);
+
+	return 0;
+}
+device_initcall(topology_update_init);
 #endif /* CONFIG_PPC_SPLPAR */

Index: powerpc/arch/powerpc/include/asm/topology.h
===================================================================
@@ -71,6 +71,7 @@
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
 extern int start_topology_update(void);
 extern int stop_topology_update(void);
+extern inline int prrn_is_enabled(void);
 #else
 static inline int start_topology_update(void)
 {

@@ -80,6 +81,10 @@
 {
 	return 0;
 }
+static inline int prrn_is_enabled(void)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
 
 #include <asm-generic/topology.h>

Index: powerpc/arch/powerpc/kernel/rtasd.c
===================================================================
@@ -29,6 +29,7 @@
 #include <asm/nvram.h>
 #include <linux/atomic.h>
 #include <asm/machdep.h>
+#include <asm/topology.h>
 
 
 static DEFINE_SPINLOCK(rtasd_log_lock);

@@ -294,11 +295,13 @@
 {
 	pSeries_log_error((char *)log, ERR_TYPE_RTAS_LOG, 0);
 
-	if (log->type == RTAS_TYPE_PRRN)
+	if (log->type == RTAS_TYPE_PRRN) {
 		/* For PRRN Events the extended log length is used to denote
 		 * the scope for calling rtas update-nodes.
 		 */
-		prrn_schedule_update(log->extended_log_length);
+		if (prrn_is_enabled())
+			prrn_schedule_update(log->extended_log_length);
+	}
 
 	return;
 }