openrisc: initial SMP support

This patch introduces the SMP support for the OpenRISC architecture.
The SMP architecture requires cores which have multi-core features which
have been introduced a few years back including:

 - New SPRS SPR_COREID SPR_NUMCORES
 - Shadow SPRs
 - Atomic Instructions
 - Cache Coherency
 - A wired in IPI controller

This patch adds all of the SMP specific changes to core infrastructure,
it looks big but it needs to go all together as its hard to split this
one up.

Boot loader spinning of second cpu is not supported yet, it's assumed
that Linux is booted straight after cpu reset.

The bulk of these changes are trivial changes to refactor to use per cpu
data structures throughout.  The addition of the smp.c and changes in
time.c are the changes.  Some specific notes:

MM changes
----------
The reason why this is created as an array, and not with DEFINE_PER_CPU
is that doing it this way, we'll save a load in the tlb-miss handler
(the load from __per_cpu_offset).

TLB Flush
---------
The SMP implementation of flush_tlb_* works by sending out a
function-call IPI to all the non-local cpus by using the generic
on_each_cpu() function.

Currently, all flush_tlb_* functions will result in a flush_tlb_all(),
which has always been the behaviour in the UP case.

CPU INFO
--------
This creates a per cpu cpuinfo struct and fills it out accordingly for
each activated cpu.  show_cpuinfo is also updated to reflect new version
information in later versions of the spec.

SMP API
-------
This imitates the arm64 implementation by having a smp_cross_call
callback that can be set by set_smp_cross_call to initiate an IPI and a
handle_IPI function that is expected to be called from an IPI irqchip
driver.

Signed-off-by: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
[shorne@gmail.com: added cpu stop, checkpatch fixes, wrote commit message]
Signed-off-by: Stafford Horne <shorne@gmail.com>

1 files changed, 107 insertions, 58 deletions

diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c
index dbf5ee95a0d5..9d28ab14d139 100644
--- a/arch/openrisc/kernel/setup.c
+++ b/arch/openrisc/kernel/setup.c
@@ -93,7 +93,7 @@ static void __init setup_memory(void)
 	memblock_dump_all();
 }
 
-struct cpuinfo cpuinfo;
+struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 
 static void print_cpuinfo(void)
 {
@@ -101,12 +101,13 @@ static void print_cpuinfo(void)
 	unsigned long vr = mfspr(SPR_VR);
 	unsigned int version;
 	unsigned int revision;
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
 
 	version = (vr & SPR_VR_VER) >> 24;
 	revision = (vr & SPR_VR_REV);
 
 	printk(KERN_INFO "CPU: OpenRISC-%x (revision %d) @%d MHz\n",
-	       version, revision, cpuinfo.clock_frequency / 1000000);
+	       version, revision, cpuinfo->clock_frequency / 1000000);
 
 	if (!(upr & SPR_UPR_UP)) {
 		printk(KERN_INFO
@@ -117,15 +118,15 @@ static void print_cpuinfo(void)
 	if (upr & SPR_UPR_DCP)
 		printk(KERN_INFO
 		       "-- dcache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo.dcache_size, cpuinfo.dcache_block_size,
-		       cpuinfo.dcache_ways);
+		       cpuinfo->dcache_size, cpuinfo->dcache_block_size,
+		       cpuinfo->dcache_ways);
 	else
 		printk(KERN_INFO "-- dcache disabled\n");
 	if (upr & SPR_UPR_ICP)
 		printk(KERN_INFO
 		       "-- icache: %4d bytes total, %2d bytes/line, %d way(s)\n",
-		       cpuinfo.icache_size, cpuinfo.icache_block_size,
-		       cpuinfo.icache_ways);
+		       cpuinfo->icache_size, cpuinfo->icache_block_size,
+		       cpuinfo->icache_ways);
 	else
 		printk(KERN_INFO "-- icache disabled\n");
 
@@ -153,38 +154,58 @@ static void print_cpuinfo(void)
 		printk(KERN_INFO "-- custom unit(s)\n");
 }
 
+static struct device_node *setup_find_cpu_node(int cpu)
+{
+	u32 hwid;
+	struct device_node *cpun;
+	struct device_node *cpus = of_find_node_by_path("/cpus");
+
+	for_each_available_child_of_node(cpus, cpun) {
+		if (of_property_read_u32(cpun, "reg", &hwid))
+			continue;
+		if (hwid == cpu)
+			return cpun;
+	}
+
+	return NULL;
+}
+
 void __init setup_cpuinfo(void)
 {
 	struct device_node *cpu;
 	unsigned long iccfgr, dccfgr;
 	unsigned long cache_set_size;
+	int cpu_id = smp_processor_id();
+	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[cpu_id];
 
-	cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481");
+	cpu = setup_find_cpu_node(cpu_id);
 	if (!cpu)
-		panic("No compatible CPU found in device tree...\n");
+		panic("Couldn't find CPU%d in device tree...\n", cpu_id);
 
 	iccfgr = mfspr(SPR_ICCFGR);
-	cpuinfo.icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
+	cpuinfo->icache_ways = 1 << (iccfgr & SPR_ICCFGR_NCW);
 	cache_set_size = 1 << ((iccfgr & SPR_ICCFGR_NCS) >> 3);
-	cpuinfo.icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
-	cpuinfo.icache_size =
-	    cache_set_size * cpuinfo.icache_ways * cpuinfo.icache_block_size;
+	cpuinfo->icache_block_size = 16 << ((iccfgr & SPR_ICCFGR_CBS) >> 7);
+	cpuinfo->icache_size =
+	    cache_set_size * cpuinfo->icache_ways * cpuinfo->icache_block_size;
 
 	dccfgr = mfspr(SPR_DCCFGR);
-	cpuinfo.dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
+	cpuinfo->dcache_ways = 1 << (dccfgr & SPR_DCCFGR_NCW);
 	cache_set_size = 1 << ((dccfgr & SPR_DCCFGR_NCS) >> 3);
-	cpuinfo.dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
-	cpuinfo.dcache_size =
-	    cache_set_size * cpuinfo.dcache_ways * cpuinfo.dcache_block_size;
+	cpuinfo->dcache_block_size = 16 << ((dccfgr & SPR_DCCFGR_CBS) >> 7);
+	cpuinfo->dcache_size =
+	    cache_set_size * cpuinfo->dcache_ways * cpuinfo->dcache_block_size;
 
 	if (of_property_read_u32(cpu, "clock-frequency",
-				 &cpuinfo.clock_frequency)) {
+				 &cpuinfo->clock_frequency)) {
 		printk(KERN_WARNING
 		       "Device tree missing CPU 'clock-frequency' parameter."
 		       "Assuming frequency 25MHZ"
 		       "This is probably not what you want.");
 	}
 
+	cpuinfo->coreid = mfspr(SPR_COREID);
+
 	of_node_put(cpu);
 
 	print_cpuinfo();
@@ -251,8 +272,8 @@ void __init detect_unit_config(unsigned long upr, unsigned long mask,
 void calibrate_delay(void)
 {
 	const int *val;
-	struct device_node *cpu = NULL;
-	cpu = of_find_compatible_node(NULL, NULL, "opencores,or1200-rtlsvn481");
+	struct device_node *cpu = setup_find_cpu_node(smp_processor_id());
+
 	val = of_get_property(cpu, "clock-frequency", NULL);
 	if (!val)
 		panic("no cpu 'clock-frequency' parameter in device tree");
@@ -268,6 +289,10 @@ void __init setup_arch(char **cmdline_p)
 
 	setup_cpuinfo();
 
+#ifdef CONFIG_SMP
+	smp_init_cpus();
+#endif
+
 	/* process 1's initial memory region is the kernel code/data */
 	init_mm.start_code = (unsigned long)_stext;
 	init_mm.end_code = (unsigned long)_etext;
@@ -302,54 +327,78 @@ void __init setup_arch(char **cmdline_p)
 
 static int show_cpuinfo(struct seq_file *m, void *v)
 {
-	unsigned long vr;
-	int version, revision;
+	unsigned int vr, cpucfgr;
+	unsigned int avr;
+	unsigned int version;
+	struct cpuinfo_or1k *cpuinfo = v;
 
 	vr = mfspr(SPR_VR);
-	version = (vr & SPR_VR_VER) >> 24;
-	revision = vr & SPR_VR_REV;
-
-	seq_printf(m,
-		  "cpu\t\t: OpenRISC-%x\n"
-		  "revision\t: %d\n"
-		  "frequency\t: %ld\n"
-		  "dcache size\t: %d bytes\n"
-		  "dcache block size\t: %d bytes\n"
-		  "dcache ways\t: %d\n"
-		  "icache size\t: %d bytes\n"
-		  "icache block size\t: %d bytes\n"
-		  "icache ways\t: %d\n"
-		  "immu\t\t: %d entries, %lu ways\n"
-		  "dmmu\t\t: %d entries, %lu ways\n"
-		  "bogomips\t: %lu.%02lu\n",
-		  version,
-		  revision,
-		  loops_per_jiffy * HZ,
-		  cpuinfo.dcache_size,
-		  cpuinfo.dcache_block_size,
-		  cpuinfo.dcache_ways,
-		  cpuinfo.icache_size,
-		  cpuinfo.icache_block_size,
-		  cpuinfo.icache_ways,
-		  1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
-		  1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW),
-		  1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2),
-		  1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW),
-		  (loops_per_jiffy * HZ) / 500000,
-		  ((loops_per_jiffy * HZ) / 5000) % 100);
+	cpucfgr = mfspr(SPR_CPUCFGR);
+
+#ifdef CONFIG_SMP
+	seq_printf(m, "processor\t\t: %d\n", cpuinfo->coreid);
+#endif
+	if (vr & SPR_VR_UVRP) {
+		vr = mfspr(SPR_VR2);
+		version = vr & SPR_VR2_VER;
+		avr = mfspr(SPR_AVR);
+		seq_printf(m, "cpu architecture\t: "
+			   "OpenRISC 1000 (%d.%d-rev%d)\n",
+			   (avr >> 24) & 0xff,
+			   (avr >> 16) & 0xff,
+			   (avr >> 8) & 0xff);
+		seq_printf(m, "cpu implementation id\t: 0x%x\n",
+			   (vr & SPR_VR2_CPUID) >> 24);
+		seq_printf(m, "cpu version\t\t: 0x%x\n", version);
+	} else {
+		version = (vr & SPR_VR_VER) >> 24;
+		seq_printf(m, "cpu\t\t\t: OpenRISC-%x\n", version);
+		seq_printf(m, "revision\t\t: %d\n", vr & SPR_VR_REV);
+	}
+	seq_printf(m, "frequency\t\t: %ld\n", loops_per_jiffy * HZ);
+	seq_printf(m, "dcache size\t\t: %d bytes\n", cpuinfo->dcache_size);
+	seq_printf(m, "dcache block size\t: %d bytes\n",
+		   cpuinfo->dcache_block_size);
+	seq_printf(m, "dcache ways\t\t: %d\n", cpuinfo->dcache_ways);
+	seq_printf(m, "icache size\t\t: %d bytes\n", cpuinfo->icache_size);
+	seq_printf(m, "icache block size\t: %d bytes\n",
+		   cpuinfo->icache_block_size);
+	seq_printf(m, "icache ways\t\t: %d\n", cpuinfo->icache_ways);
+	seq_printf(m, "immu\t\t\t: %d entries, %lu ways\n",
+		   1 << ((mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTS) >> 2),
+		   1 + (mfspr(SPR_DMMUCFGR) & SPR_DMMUCFGR_NTW));
+	seq_printf(m, "dmmu\t\t\t: %d entries, %lu ways\n",
+		   1 << ((mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTS) >> 2),
+		   1 + (mfspr(SPR_IMMUCFGR) & SPR_IMMUCFGR_NTW));
+	seq_printf(m, "bogomips\t\t: %lu.%02lu\n",
+		   (loops_per_jiffy * HZ) / 500000,
+		   ((loops_per_jiffy * HZ) / 5000) % 100);
+
+	seq_puts(m, "features\t\t: ");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB32S ? "orbis32" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OB64S ? "orbis64" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF32S ? "orfpx32" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OF64S ? "orfpx64" : "");
+	seq_printf(m, "%s ", cpucfgr & SPR_CPUCFGR_OV64S ? "orvdx64" : "");
+	seq_puts(m, "\n");
+
+	seq_puts(m, "\n");
+
 	return 0;
 }
 
-static void *c_start(struct seq_file *m, loff_t * pos)
+static void *c_start(struct seq_file *m, loff_t *pos)
 {
-	/* We only have one CPU... */
-	return *pos < 1 ? (void *)1 : NULL;
+	*pos = cpumask_next(*pos - 1, cpu_online_mask);
+	if ((*pos) < nr_cpu_ids)
+		return &cpuinfo_or1k[*pos];
+	return NULL;
 }
 
-static void *c_next(struct seq_file *m, void *v, loff_t * pos)
+static void *c_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	++*pos;
-	return NULL;
+	(*pos)++;
+	return c_start(m, pos);
 }
 
 static void c_stop(struct seq_file *m, void *v)