1 files changed, 265 insertions, 48 deletions

diff --git a/arch/powerpc/platforms/85xx/smp.c b/arch/powerpc/platforms/85xx/smp.c
index 5c91a992f02..ba093f55367 100644
--- a/arch/powerpc/platforms/85xx/smp.c
+++ b/arch/powerpc/platforms/85xx/smp.c
@@ -2,7 +2,7 @@
  * Author: Andy Fleming <afleming@freescale.com>
  * 	   Kumar Gala <galak@kernel.crashing.org>
  *
- * Copyright 2006-2008 Freescale Semiconductor Inc.
+ * Copyright 2006-2008, 2011-2012 Freescale Semiconductor Inc.
  *
  * This program is free software; you can redistribute  it and/or modify it
  * under  the terms of  the GNU General  Public License as published by the
@@ -15,8 +15,10 @@
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/kexec.h>
 #include <linux/highmem.h>
+#include <linux/cpu.h>
 
 #include <asm/machdep.h>
 #include <asm/pgtable.h>
@@ -24,34 +26,160 @@
 #include <asm/mpic.h>
 #include <asm/cacheflush.h>
 #include <asm/dbell.h>
+#include <asm/fsl_guts.h>
+#include <asm/code-patching.h>
 
 #include <sysdev/fsl_soc.h>
 #include <sysdev/mpic.h>
+#include "smp.h"
+
+struct epapr_spin_table {
+	u32	addr_h;
+	u32	addr_l;
+	u32	r3_h;
+	u32	r3_l;
+	u32	reserved;
+	u32	pir;
+};
+
+static struct ccsr_guts __iomem *guts;
+static u64 timebase;
+static int tb_req;
+static int tb_valid;
+
+static void mpc85xx_timebase_freeze(int freeze)
+{
+	uint32_t mask;
+
+	mask = CCSR_GUTS_DEVDISR_TB0 | CCSR_GUTS_DEVDISR_TB1;
+	if (freeze)
+		setbits32(&guts->devdisr, mask);
+	else
+		clrbits32(&guts->devdisr, mask);
+
+	in_be32(&guts->devdisr);
+}
+
+static void mpc85xx_give_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	while (!tb_req)
+		barrier();
+	tb_req = 0;
+
+	mpc85xx_timebase_freeze(1);
+#ifdef CONFIG_PPC64
+	/*
+	 * e5500/e6500 have a workaround for erratum A-006958 in place
+	 * that will reread the timebase until TBL is non-zero.
+	 * That would be a bad thing when the timebase is frozen.
+	 *
+	 * Thus, we read it manually, and instead of checking that
+	 * TBL is non-zero, we ensure that TB does not change.  We don't
+	 * do that for the main mftb implementation, because it requires
+	 * a scratch register
+	 */
+	{
+		u64 prev;
+
+		asm volatile("mfspr %0, %1" : "=r" (timebase) :
+			     "i" (SPRN_TBRL));
+
+		do {
+			prev = timebase;
+			asm volatile("mfspr %0, %1" : "=r" (timebase) :
+				     "i" (SPRN_TBRL));
+		} while (prev != timebase);
+	}
+#else
+	timebase = get_tb();
+#endif
+	mb();
+	tb_valid = 1;
+
+	while (tb_valid)
+		barrier();
+
+	mpc85xx_timebase_freeze(0);
+
+	local_irq_restore(flags);
+}
+
+static void mpc85xx_take_timebase(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	tb_req = 1;
+	while (!tb_valid)
+		barrier();
+
+	set_tb(timebase >> 32, timebase & 0xffffffff);
+	isync();
+	tb_valid = 0;
+
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void smp_85xx_mach_cpu_die(void)
+{
+	unsigned int cpu = smp_processor_id();
+	u32 tmp;
+
+	local_irq_disable();
+	idle_task_exit();
+	generic_set_cpu_dead(cpu);
+	mb();
+
+	mtspr(SPRN_TCR, 0);
+
+	__flush_disable_L1();
+	tmp = (mfspr(SPRN_HID0) & ~(HID0_DOZE|HID0_SLEEP)) | HID0_NAP;
+	mtspr(SPRN_HID0, tmp);
+	isync();
+
+	/* Enter NAP mode. */
+	tmp = mfmsr();
+	tmp |= MSR_WE;
+	mb();
+	mtmsr(tmp);
+	isync();
+
+	while (1)
+		;
+}
+#endif
+
+static inline void flush_spin_table(void *spin_table)
+{
+	flush_dcache_range((ulong)spin_table,
+		(ulong)spin_table + sizeof(struct epapr_spin_table));
+}
 
-extern void __early_start(void);
-
-#define BOOT_ENTRY_ADDR_UPPER	0
-#define BOOT_ENTRY_ADDR_LOWER	1
-#define BOOT_ENTRY_R3_UPPER	2
-#define BOOT_ENTRY_R3_LOWER	3
-#define BOOT_ENTRY_RESV		4
-#define BOOT_ENTRY_PIR		5
-#define BOOT_ENTRY_R6_UPPER	6
-#define BOOT_ENTRY_R6_LOWER	7
-#define NUM_BOOT_ENTRY		8
-#define SIZE_BOOT_ENTRY		(NUM_BOOT_ENTRY * sizeof(u32))
-
-static void __init
-smp_85xx_kick_cpu(int nr)
+static inline u32 read_spin_table_addr_l(void *spin_table)
+{
+	flush_dcache_range((ulong)spin_table,
+		(ulong)spin_table + sizeof(struct epapr_spin_table));
+	return in_be32(&((struct epapr_spin_table *)spin_table)->addr_l);
+}
+
+static int smp_85xx_kick_cpu(int nr)
 {
 	unsigned long flags;
 	const u64 *cpu_rel_addr;
-	__iomem u32 *bptr_vaddr;
+	__iomem struct epapr_spin_table *spin_table;
 	struct device_node *np;
-	int n = 0;
+	int hw_cpu = get_hard_smp_processor_id(nr);
 	int ioremappable;
+	int ret = 0;
 
-	WARN_ON (nr < 0 || nr >= NR_CPUS);
+	WARN_ON(nr < 0 || nr >= NR_CPUS);
+	WARN_ON(hw_cpu < 0 || hw_cpu >= NR_CPUS);
 
 	pr_debug("smp_85xx_kick_cpu: kick CPU #%d\n", nr);
 
@@ -60,7 +188,7 @@ smp_85xx_kick_cpu(int nr)
 
 	if (cpu_rel_addr == NULL) {
 		printk(KERN_ERR "No cpu-release-addr for cpu %d\n", nr);
-		return;
+		return -ENOENT;
 	}
 
 	/*
@@ -73,48 +201,92 @@ smp_85xx_kick_cpu(int nr)
 
 	/* Map the spin table */
 	if (ioremappable)
-		bptr_vaddr = ioremap(*cpu_rel_addr, SIZE_BOOT_ENTRY);
+		spin_table = ioremap_prot(*cpu_rel_addr,
+			sizeof(struct epapr_spin_table), _PAGE_COHERENT);
 	else
-		bptr_vaddr = phys_to_virt(*cpu_rel_addr);
+		spin_table = phys_to_virt(*cpu_rel_addr);
 
 	local_irq_save(flags);
-
-	out_be32(bptr_vaddr + BOOT_ENTRY_PIR, nr);
 #ifdef CONFIG_PPC32
-	out_be32(bptr_vaddr + BOOT_ENTRY_ADDR_LOWER, __pa(__early_start));
+#ifdef CONFIG_HOTPLUG_CPU
+	/* Corresponding to generic_set_cpu_dead() */
+	generic_set_cpu_up(nr);
+
+	if (system_state == SYSTEM_RUNNING) {
+		/*
+		 * To keep it compatible with old boot program which uses
+		 * cache-inhibit spin table, we need to flush the cache
+		 * before accessing spin table to invalidate any staled data.
+		 * We also need to flush the cache after writing to spin
+		 * table to push data out.
+		 */
+		flush_spin_table(spin_table);
+		out_be32(&spin_table->addr_l, 0);
+		flush_spin_table(spin_table);
+
+		/*
+		 * We don't set the BPTR register here since it already points
+		 * to the boot page properly.
+		 */
+		mpic_reset_core(nr);
+
+		/*
+		 * wait until core is ready...
+		 * We need to invalidate the stale data, in case the boot
+		 * loader uses a cache-inhibited spin table.
+		 */
+		if (!spin_event_timeout(
+				read_spin_table_addr_l(spin_table) == 1,
+				10000, 100)) {
+			pr_err("%s: timeout waiting for core %d to reset\n",
+							__func__, hw_cpu);
+			ret = -ENOENT;
+			goto out;
+		}
 
-	if (!ioremappable)
-		flush_dcache_range((ulong)bptr_vaddr,
-				(ulong)(bptr_vaddr + SIZE_BOOT_ENTRY));
+		/*  clear the acknowledge status */
+		__secondary_hold_acknowledge = -1;
+	}
+#endif
+	flush_spin_table(spin_table);
+	out_be32(&spin_table->pir, hw_cpu);
+	out_be32(&spin_table->addr_l, __pa(__early_start));
+	flush_spin_table(spin_table);
 
 	/* Wait a bit for the CPU to ack. */
-	while ((__secondary_hold_acknowledge != nr) && (++n < 1000))
-		mdelay(1);
+	if (!spin_event_timeout(__secondary_hold_acknowledge == hw_cpu,
+					10000, 100)) {
+		pr_err("%s: timeout waiting for core %d to ack\n",
+						__func__, hw_cpu);
+		ret = -ENOENT;
+		goto out;
+	}
+out:
 #else
-	out_be64((u64 *)(bptr_vaddr + BOOT_ENTRY_ADDR_UPPER),
-		__pa((u64)*((unsigned long long *) generic_secondary_smp_init)));
-
 	smp_generic_kick_cpu(nr);
+
+	flush_spin_table(spin_table);
+	out_be32(&spin_table->pir, hw_cpu);
+	out_be64((u64 *)(&spin_table->addr_h),
+		__pa(ppc_function_entry(generic_secondary_smp_init)));
+	flush_spin_table(spin_table);
 #endif
 
 	local_irq_restore(flags);
 
 	if (ioremappable)
-		iounmap(bptr_vaddr);
+		iounmap(spin_table);
 
-	pr_debug("waited %d msecs for CPU #%d.\n", n, nr);
-}
-
-static void __init
-smp_85xx_setup_cpu(int cpu_nr)
-{
-	mpic_setup_this_cpu();
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		doorbell_setup_this_cpu();
+	return ret;
 }
 
 struct smp_ops_t smp_85xx_ops = {
 	.kick_cpu = smp_85xx_kick_cpu,
+	.cpu_bootable = smp_generic_cpu_bootable,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= generic_cpu_disable,
+	.cpu_die	= generic_cpu_die,
+#endif
 #ifdef CONFIG_KEXEC
 	.give_timebase	= smp_generic_give_timebase,
 	.take_timebase	= smp_generic_take_timebase,
@@ -208,7 +380,7 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 	if ( !timeout )
 		printk(KERN_ERR "Unable to bring down secondary cpu(s)");
 
-	for (i = 0; i < num_cpus; i++)
+	for_each_online_cpu(i)
 	{
 		if ( i == smp_processor_id() ) continue;
 		mpic_reset_core(i);
@@ -218,21 +390,66 @@ static void mpc85xx_smp_machine_kexec(struct kimage *image)
 }
 #endif /* CONFIG_KEXEC */
 
+static void smp_85xx_basic_setup(int cpu_nr)
+{
+	if (cpu_has_feature(CPU_FTR_DBELL))
+		doorbell_setup_this_cpu();
+}
+
+static void smp_85xx_setup_cpu(int cpu_nr)
+{
+	mpic_setup_this_cpu();
+	smp_85xx_basic_setup(cpu_nr);
+}
+
+static const struct of_device_id mpc85xx_smp_guts_ids[] = {
+	{ .compatible = "fsl,mpc8572-guts", },
+	{ .compatible = "fsl,p1020-guts", },
+	{ .compatible = "fsl,p1021-guts", },
+	{ .compatible = "fsl,p1022-guts", },
+	{ .compatible = "fsl,p1023-guts", },
+	{ .compatible = "fsl,p2020-guts", },
+	{},
+};
+
 void __init mpc85xx_smp_init(void)
 {
 	struct device_node *np;
 
+
 	np = of_find_node_by_type(NULL, "open-pic");
 	if (np) {
 		smp_85xx_ops.probe = smp_mpic_probe;
 		smp_85xx_ops.setup_cpu = smp_85xx_setup_cpu;
 		smp_85xx_ops.message_pass = smp_mpic_message_pass;
+	} else
+		smp_85xx_ops.setup_cpu = smp_85xx_basic_setup;
+
+	if (cpu_has_feature(CPU_FTR_DBELL)) {
+		/*
+		 * If left NULL, .message_pass defaults to
+		 * smp_muxed_ipi_message_pass
+		 */
+		smp_85xx_ops.message_pass = NULL;
+		smp_85xx_ops.cause_ipi = doorbell_cause_ipi;
+		smp_85xx_ops.probe = NULL;
 	}
 
-	if (cpu_has_feature(CPU_FTR_DBELL))
-		smp_85xx_ops.message_pass = doorbell_message_pass;
-
-	BUG_ON(!smp_85xx_ops.message_pass);
+	np = of_find_matching_node(NULL, mpc85xx_smp_guts_ids);
+	if (np) {
+		guts = of_iomap(np, 0);
+		of_node_put(np);
+		if (!guts) {
+			pr_err("%s: Could not map guts node address\n",
+								__func__);
+			return;
+		}
+		smp_85xx_ops.give_timebase = mpc85xx_give_timebase;
+		smp_85xx_ops.take_timebase = mpc85xx_take_timebase;
+#ifdef CONFIG_HOTPLUG_CPU
+		ppc_md.cpu_die = smp_85xx_mach_cpu_die;
+#endif
+	}
 
 	smp_ops = &smp_85xx_ops;