[IA64] multi-core/multi-thread identification

Version 3 - rediffed to apply on top of Ashok's hotplug cpu
patch.  /proc/cpuinfo output in step with x86.

This is an updated MC/MT identification patch based on the 
previous discussions on list. 

Add the Multi-core and Multi-threading detection for IPF.
  - Add new core and threading related fields in /proc/cpuinfo.
		Physical id
		Core id
		Thread id
		Siblings
  - setup the cpu_core_map and cpu_sibling_map appropriately
  - Handles Hot plug CPU
 
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Gordon Jin <gordon.jin@intel.com>
Signed-off-by: Rohit Seth <rohit.seth@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>

6 files changed, 365 insertions, 2 deletions

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index f05650c..8804384 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -4,10 +4,15 @@
  * Copyright (C) 1998-2001, 2003-2004 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
  *	Stephane Eranian <eranian@hpl.hp.com>
- * Copyright (C) 2000, Rohit Seth <rohit.seth@intel.com>
+ * Copyright (C) 2000, 2004 Intel Corp
+ * 	Rohit Seth <rohit.seth@intel.com>
+ * 	Suresh Siddha <suresh.b.siddha@intel.com>
+ * 	Gordon Jin <gordon.jin@intel.com>
  * Copyright (C) 1999 VA Linux Systems
  * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
  *
+ * 12/26/04 S.Siddha, G.Jin, R.Seth
+ *			Add multi-threading and multi-core detection
  * 11/12/01 D.Mosberger Convert get_cpuinfo() to seq_file based show_cpuinfo().
  * 04/04/00 D.Mosberger renamed cpu_initialized to cpu_online_map
  * 03/31/00 R.Seth	cpu_initialized and current->processor fixes
@@ -296,6 +301,34 @@ mark_bsp_online (void)
 #endif
 }
 
+#ifdef CONFIG_SMP
+static void
+check_for_logical_procs (void)
+{
+	pal_logical_to_physical_t info;
+	s64 status;
+
+	status = ia64_pal_logical_to_phys(0, &info);
+	if (status == -1) {
+		printk(KERN_INFO "No logical to physical processor mapping "
+		       "available\n");
+		return;
+	}
+	if (status) {
+		printk(KERN_ERR "ia64_pal_logical_to_phys failed with %ld\n",
+		       status);
+		return;
+	}
+	/*
+	 * Total number of siblings that BSP has.  Though not all of them 
+	 * may have booted successfully. The correct number of siblings 
+	 * booted is in info.overview_num_log.
+	 */
+	smp_num_siblings = info.overview_tpc;
+	smp_num_cpucores = info.overview_cpp;
+}
+#endif
+
 void __init
 setup_arch (char **cmdline_p)
 {
@@ -356,6 +389,19 @@ setup_arch (char **cmdline_p)
 
 #ifdef CONFIG_SMP
 	cpu_physical_id(0) = hard_smp_processor_id();
+
+	cpu_set(0, cpu_sibling_map[0]);
+	cpu_set(0, cpu_core_map[0]);
+
+	check_for_logical_procs();
+	if (smp_num_cpucores > 1)
+		printk(KERN_INFO
+		       "cpu package is Multi-Core capable: number of cores=%d\n",
+		       smp_num_cpucores);
+	if (smp_num_siblings > 1)
+		printk(KERN_INFO
+		       "cpu package is Multi-Threading capable: number of siblings=%d\n",
+		       smp_num_siblings);
 #endif
 
 	cpu_init();	/* initialize the bootstrap CPU */
@@ -459,12 +505,23 @@ show_cpuinfo (struct seq_file *m, void *v)
 		   "cpu regs   : %u\n"
 		   "cpu MHz    : %lu.%06lu\n"
 		   "itc MHz    : %lu.%06lu\n"
-		   "BogoMIPS   : %lu.%02lu\n\n",
+		   "BogoMIPS   : %lu.%02lu\n",
 		   cpunum, c->vendor, family, c->model, c->revision, c->archrev,
 		   features, c->ppn, c->number,
 		   c->proc_freq / 1000000, c->proc_freq % 1000000,
 		   c->itc_freq / 1000000, c->itc_freq % 1000000,
 		   lpj*HZ/500000, (lpj*HZ/5000) % 100);
+#ifdef CONFIG_SMP
+	if (c->threads_per_core > 1 || c->cores_per_socket > 1)
+		seq_printf(m,
+		   	   "physical id: %u\n"
+		   	   "core id    : %u\n"
+		   	   "thread id  : %u\n",
+		   	   c->socket_id, c->core_id, c->thread_id);
+	seq_printf(m, "siblings   : %u\n", c->num_log);
+#endif
+	seq_printf(m,"\n");
+
 	return 0;
 }
 
@@ -533,6 +590,14 @@ identify_cpu (struct cpuinfo_ia64 *c)
 	memcpy(c->vendor, cpuid.field.vendor, 16);
 #ifdef CONFIG_SMP
 	c->cpu = smp_processor_id();
+
+	/* below default values will be overwritten  by identify_siblings() 
+	 * for Multi-Threading/Multi-Core capable cpu's
+	 */
+	c->threads_per_core = c->cores_per_socket = c->num_log = 1;
+	c->socket_id = -1;
+
+	identify_siblings(c);
 #endif
 	c->ppn = cpuid.field.ppn;
 	c->number = cpuid.field.number;
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index dbc6b61..0d5ee57 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -3,6 +3,11 @@
  *
  * Copyright (C) 1998-2003, 2005 Hewlett-Packard Co
  *	David Mosberger-Tang <davidm@hpl.hp.com>
+ * Copyright (C) 2001, 2004-2005 Intel Corp
+ * 	Rohit Seth <rohit.seth@intel.com>
+ * 	Suresh Siddha <suresh.b.siddha@intel.com>
+ * 	Gordon Jin <gordon.jin@intel.com>
+ *	Ashok Raj  <ashok.raj@intel.com>
  *
  * 01/05/16 Rohit Seth <rohit.seth@intel.com>	Moved SMP booting functions from smp.c to here.
  * 01/04/27 David Mosberger <davidm@hpl.hp.com>	Added ITC synching code.
@@ -10,6 +15,11 @@
  *						smp_boot_cpus()/smp_commence() is replaced by
  *						smp_prepare_cpus()/__cpu_up()/smp_cpus_done().
  * 04/06/21 Ashok Raj		<ashok.raj@intel.com> Added CPU Hotplug Support
+ * 04/12/26 Jin Gordon <gordon.jin@intel.com>
+ * 04/12/26 Rohit Seth <rohit.seth@intel.com>
+ *						Add multi-threading and multi-core detection
+ * 05/01/30 Suresh Siddha <suresh.b.siddha@intel.com>
+ *						Setup cpu_sibling_map and cpu_core_map
  */
 #include <linux/config.h>
 
@@ -122,6 +132,11 @@ EXPORT_SYMBOL(cpu_online_map);
 cpumask_t cpu_possible_map;
 EXPORT_SYMBOL(cpu_possible_map);
 
+cpumask_t cpu_core_map[NR_CPUS] __cacheline_aligned;
+cpumask_t cpu_sibling_map[NR_CPUS] __cacheline_aligned;
+int smp_num_siblings = 1;
+int smp_num_cpucores = 1;
+
 /* which logical CPU number maps to which CPU (physical APIC ID) */
 volatile int ia64_cpu_to_sapicid[NR_CPUS];
 EXPORT_SYMBOL(ia64_cpu_to_sapicid);
@@ -598,7 +613,68 @@ void __devinit smp_prepare_boot_cpu(void)
 	cpu_set(smp_processor_id(), cpu_callin_map);
 }
 
+/*
+ * mt_info[] is a temporary store for all info returned by
+ * PAL_LOGICAL_TO_PHYSICAL, to be copied into cpuinfo_ia64 when the
+ * specific cpu comes.
+ */
+static struct {
+	__u32   socket_id;
+	__u16   core_id;
+	__u16   thread_id;
+	__u16   proc_fixed_addr;
+	__u8    valid;
+}mt_info[NR_CPUS] __devinit;
+
 #ifdef CONFIG_HOTPLUG_CPU
+static inline void
+remove_from_mtinfo(int cpu)
+{
+	int i;
+
+	for_each_cpu(i)
+		if (mt_info[i].valid &&  mt_info[i].socket_id ==
+		    				cpu_data(cpu)->socket_id)
+			mt_info[i].valid = 0;
+}
+
+static inline void
+clear_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	for_each_cpu_mask(i, cpu_sibling_map[cpu])
+		cpu_clear(cpu, cpu_sibling_map[i]);
+	for_each_cpu_mask(i, cpu_core_map[cpu])
+		cpu_clear(cpu, cpu_core_map[i]);
+
+	cpu_sibling_map[cpu] = cpu_core_map[cpu] = CPU_MASK_NONE;
+}
+
+static void
+remove_siblinginfo(int cpu)
+{
+	int last = 0;
+
+	if (cpu_data(cpu)->threads_per_core == 1 &&
+	    cpu_data(cpu)->cores_per_socket == 1) {
+		cpu_clear(cpu, cpu_core_map[cpu]);
+		cpu_clear(cpu, cpu_sibling_map[cpu]);
+		return;
+	}
+
+	last = (cpus_weight(cpu_core_map[cpu]) == 1 ? 1 : 0);
+
+	/* remove it from all sibling map's */
+	clear_cpu_sibling_map(cpu);
+
+	/* if this cpu is the last in the core group, remove all its info 
+	 * from mt_info structure
+	 */
+	if (last)
+		remove_from_mtinfo(cpu);
+}
+
 extern void fixup_irqs(void);
 /* must be called with cpucontrol mutex held */
 int __cpu_disable(void)
@@ -611,6 +687,7 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
+	remove_siblinginfo(cpu);
 	fixup_irqs();
 	local_flush_tlb_all();
 	cpu_clear(cpu, cpu_callin_map);
@@ -663,6 +740,23 @@ smp_cpus_done (unsigned int dummy)
 	       (int)num_online_cpus(), bogosum/(500000/HZ), (bogosum/(5000/HZ))%100);
 }
 
+static inline void __devinit
+set_cpu_sibling_map(int cpu)
+{
+	int i;
+
+	for_each_online_cpu(i) {
+		if ((cpu_data(cpu)->socket_id == cpu_data(i)->socket_id)) {
+			cpu_set(i, cpu_core_map[cpu]);
+			cpu_set(cpu, cpu_core_map[i]);
+			if (cpu_data(cpu)->core_id == cpu_data(i)->core_id) {
+				cpu_set(i, cpu_sibling_map[cpu]);
+				cpu_set(cpu, cpu_sibling_map[i]);
+			}
+		}
+	}
+}
+
 int __devinit
 __cpu_up (unsigned int cpu)
 {
@@ -685,6 +779,15 @@ __cpu_up (unsigned int cpu)
 	if (ret < 0)
 		return ret;
 
+	if (cpu_data(cpu)->threads_per_core == 1 &&
+	    cpu_data(cpu)->cores_per_socket == 1) {
+		cpu_set(cpu, cpu_sibling_map[cpu]);
+		cpu_set(cpu, cpu_core_map[cpu]);
+		return 0;
+	}
+
+	set_cpu_sibling_map(cpu);
+
 	return 0;
 }
 
@@ -712,3 +815,106 @@ init_smp_config(void)
 		       ia64_sal_strerror(sal_ret));
 }
 
+static inline int __devinit
+check_for_mtinfo_index(void)
+{
+	int i;
+	
+	for_each_cpu(i)
+		if (!mt_info[i].valid)
+			return i;
+
+	return -1;
+}
+
+/*
+ * Search the mt_info to find out if this socket's cid/tid information is
+ * cached or not. If the socket exists, fill in the core_id and thread_id 
+ * in cpuinfo
+ */
+static int __devinit
+check_for_new_socket(__u16 logical_address, struct cpuinfo_ia64 *c)
+{
+	int i;
+	__u32 sid = c->socket_id;
+
+	for_each_cpu(i) {
+		if (mt_info[i].valid && mt_info[i].proc_fixed_addr == logical_address
+		    && mt_info[i].socket_id == sid) {
+			c->core_id = mt_info[i].core_id;
+			c->thread_id = mt_info[i].thread_id;
+			return 1; /* not a new socket */
+		}
+	}
+	return 0;
+}
+
+/*
+ * identify_siblings(cpu) gets called from identify_cpu. This populates the 
+ * information related to logical execution units in per_cpu_data structure.
+ */
+void __devinit
+identify_siblings(struct cpuinfo_ia64 *c)
+{
+	s64 status;
+	u16 pltid;
+	u64 proc_fixed_addr;
+	int count, i;
+	pal_logical_to_physical_t info;
+
+	if (smp_num_cpucores == 1 && smp_num_siblings == 1)
+		return;
+
+	if ((status = ia64_pal_logical_to_phys(0, &info)) != PAL_STATUS_SUCCESS) {
+		printk(KERN_ERR "ia64_pal_logical_to_phys failed with %ld\n",
+		       status);
+		return;
+	}
+	if ((status = ia64_sal_physical_id_info(&pltid)) != PAL_STATUS_SUCCESS) {
+		printk(KERN_ERR "ia64_sal_pltid failed with %ld\n", status);
+		return;
+	}
+	if ((status = ia64_pal_fixed_addr(&proc_fixed_addr)) != PAL_STATUS_SUCCESS) {
+		printk(KERN_ERR "ia64_pal_fixed_addr failed with %ld\n", status);
+		return;
+	}
+
+	c->socket_id =  (pltid << 8) | info.overview_ppid;
+	c->cores_per_socket = info.overview_cpp;
+	c->threads_per_core = info.overview_tpc;
+	count = c->num_log = info.overview_num_log;
+
+	/* If the thread and core id information is already cached, then
+	 * we will simply update cpu_info and return. Otherwise, we will
+	 * do the PAL calls and cache core and thread id's of all the siblings.
+	 */
+	if (check_for_new_socket(proc_fixed_addr, c))
+		return;
+
+	for (i = 0; i < count; i++) {
+		int index;
+
+		if (i && (status = ia64_pal_logical_to_phys(i, &info))
+			  != PAL_STATUS_SUCCESS) {
+                	printk(KERN_ERR "ia64_pal_logical_to_phys failed"
+					" with %ld\n", status);
+                	return;
+		}
+		if (info.log2_la == proc_fixed_addr) {
+			c->core_id = info.log1_cid;
+			c->thread_id = info.log1_tid;
+		}
+
+		index = check_for_mtinfo_index();
+		/* We will not do the mt_info caching optimization in this case.
+		 */
+		if (index < 0)
+			continue;
+
+		mt_info[index].valid = 1;
+		mt_info[index].socket_id = c->socket_id;
+		mt_info[index].core_id = info.log1_cid;
+		mt_info[index].thread_id = info.log1_tid;
+		mt_info[index].proc_fixed_addr = info.log2_la;
+	}
+}
diff --git a/include/asm-ia64/pal.h b/include/asm-ia64/pal.h
index 5dd477f..2303a10 100644
--- a/include/asm-ia64/pal.h
+++ b/include/asm-ia64/pal.h
@@ -67,6 +67,7 @@
 #define PAL_REGISTER_INFO	39	/* return AR and CR register information*/
 #define PAL_SHUTDOWN		40	/* enter processor shutdown state */
 #define PAL_PREFETCH_VISIBILITY	41	/* Make Processor Prefetches Visible */
+#define PAL_LOGICAL_TO_PHYSICAL 42	/* returns information on logical to physical processor mapping */
 
 #define PAL_COPY_PAL		256	/* relocate PAL procedures and PAL PMI */
 #define PAL_HALT_INFO		257	/* return the low power capabilities of processor */
@@ -1559,6 +1560,73 @@ ia64_pal_prefetch_visibility (s64 trans_type)
 	return iprv.status;
 }
 
+/* data structure for getting information on logical to physical mappings */
+typedef union pal_log_overview_u {
+	struct {
+		u64	num_log		:16,	/* Total number of logical
+						 * processors on this die
+						 */
+			tpc		:8,	/* Threads per core */
+			reserved3	:8,	/* Reserved */
+			cpp		:8,	/* Cores per processor */
+			reserved2	:8,	/* Reserved */
+			ppid		:8,	/* Physical processor ID */
+			reserved1	:8;	/* Reserved */
+	} overview_bits;
+	u64 overview_data;
+} pal_log_overview_t;
+
+typedef union pal_proc_n_log_info1_u{
+	struct {
+		u64	tid		:16,	/* Thread id */
+			reserved2	:16,	/* Reserved */
+			cid		:16,	/* Core id */
+			reserved1	:16;	/* Reserved */
+	} ppli1_bits;
+	u64	ppli1_data;
+} pal_proc_n_log_info1_t;
+
+typedef union pal_proc_n_log_info2_u {
+	struct {
+		u64	la		:16,	/* Logical address */
+			reserved	:48;	/* Reserved */
+	} ppli2_bits;
+	u64	ppli2_data;
+} pal_proc_n_log_info2_t;
+
+typedef struct pal_logical_to_physical_s
+{
+	pal_log_overview_t overview;
+	pal_proc_n_log_info1_t ppli1;
+	pal_proc_n_log_info2_t ppli2;
+} pal_logical_to_physical_t;
+
+#define overview_num_log	overview.overview_bits.num_log
+#define overview_tpc		overview.overview_bits.tpc
+#define overview_cpp		overview.overview_bits.cpp
+#define overview_ppid		overview.overview_bits.ppid
+#define log1_tid		ppli1.ppli1_bits.tid
+#define log1_cid		ppli1.ppli1_bits.cid
+#define log2_la			ppli2.ppli2_bits.la
+
+/* Get information on logical to physical processor mappings. */
+static inline s64
+ia64_pal_logical_to_phys(u64 proc_number, pal_logical_to_physical_t *mapping)
+{
+	struct ia64_pal_retval iprv;
+
+	PAL_CALL(iprv, PAL_LOGICAL_TO_PHYSICAL, proc_number, 0, 0);
+
+	if (iprv.status == PAL_STATUS_SUCCESS)
+	{
+		if (proc_number == 0)
+			mapping->overview.overview_data = iprv.v0;
+		mapping->ppli1.ppli1_data = iprv.v1;
+		mapping->ppli2.ppli2_data = iprv.v2;
+	}
+
+	return iprv.status;
+}
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_IA64_PAL_H */
diff --git a/include/asm-ia64/processor.h b/include/asm-ia64/processor.h
index 983798e..9e1ba8b 100644
--- a/include/asm-ia64/processor.h
+++ b/include/asm-ia64/processor.h
@@ -148,6 +148,13 @@ struct cpuinfo_ia64 {
 #ifdef CONFIG_SMP
 	__u64 loops_per_jiffy;
 	int cpu;
+	__u32 socket_id;	/* physical processor socket id */
+	__u16 core_id;		/* core id */
+	__u16 thread_id;	/* thread id */
+	__u16 num_log;		/* Total number of logical processors on
+				 * this socket that were successfully booted */
+	__u8  cores_per_socket;	/* Cores per processor socket */
+	__u8  threads_per_core;	/* Threads per core */
 #endif
 
 	/* CPUID-derived information: */
diff --git a/include/asm-ia64/sal.h b/include/asm-ia64/sal.h
index 240676f..29df88bd 100644
--- a/include/asm-ia64/sal.h
+++ b/include/asm-ia64/sal.h
@@ -91,6 +91,7 @@ extern spinlock_t sal_lock;
 #define SAL_PCI_CONFIG_READ		0x01000010
 #define SAL_PCI_CONFIG_WRITE		0x01000011
 #define SAL_FREQ_BASE			0x01000012
+#define SAL_PHYSICAL_ID_INFO		0x01000013
 
 #define SAL_UPDATE_PAL			0x01000020
 
@@ -815,6 +816,17 @@ ia64_sal_update_pal (u64 param_buf, u64 scratch_buf, u64 scratch_buf_size,
 	return isrv.status;
 }
 
+/* Get physical processor die mapping in the platform. */
+static inline s64
+ia64_sal_physical_id_info(u16 *splid)
+{
+	struct ia64_sal_retval isrv;
+	SAL_CALL(isrv, SAL_PHYSICAL_ID_INFO, 0, 0, 0, 0, 0, 0, 0);
+	if (splid)
+		*splid = isrv.v0;
+	return isrv.status;
+}
+
 extern unsigned long sal_platform_features;
 
 extern int (*salinfo_platform_oemdata)(const u8 *, u8 **, u64 *);
diff --git a/include/asm-ia64/smp.h b/include/asm-ia64/smp.h
index c4a227a..3ba1a06 100644
--- a/include/asm-ia64/smp.h
+++ b/include/asm-ia64/smp.h
@@ -56,6 +56,10 @@ extern struct smp_boot_data {
 extern char no_int_routing __devinitdata;
 
 extern cpumask_t cpu_online_map;
+extern cpumask_t cpu_core_map[NR_CPUS];
+extern cpumask_t cpu_sibling_map[NR_CPUS];
+extern int smp_num_siblings;
+extern int smp_num_cpucores;
 extern void __iomem *ipi_base_addr;
 extern unsigned char smp_int_redirect;
 
@@ -124,6 +128,7 @@ extern int smp_call_function_single (int cpuid, void (*func) (void *info), void
 extern void smp_send_reschedule (int cpu);
 extern void lock_ipi_calllock(void);
 extern void unlock_ipi_calllock(void);
+extern void identify_siblings (struct cpuinfo_ia64 *);
 
 #else