19 files changed, 599 insertions, 208 deletions

diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index 1cf466d..7202b98 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -734,10 +734,13 @@ void mtrr_ap_init(void)
  */
 void mtrr_save_state(void)
 {
-	if (smp_processor_id() == 0)
+	int cpu = get_cpu();
+
+	if (cpu == 0)
 		mtrr_save_fixed_ranges(NULL);
 	else
 		smp_call_function_single(0, mtrr_save_fixed_ranges, NULL, 1, 1);
+	put_cpu();
 }
 
 static int __init mtrr_init_finialize(void)
diff --git a/arch/powerpc/boot/crt0.S b/arch/powerpc/boot/crt0.S
index 5a4215c..f1c4dfc 100644
--- a/arch/powerpc/boot/crt0.S
+++ b/arch/powerpc/boot/crt0.S
@@ -13,6 +13,7 @@
 
 	.text
 	/* a procedure descriptor used when booting this as a COFF file */
+	.globl	_zimage_start_opd
 _zimage_start_opd:
 	.long	_zimage_start, 0, 0, 0
 
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index d501c23..d454f61 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -433,7 +433,7 @@ static int __devinit of_pci_phb_probe(struct of_device *dev,
 	 * Note also that we don't do ISA, this will also be fixed with a
 	 * more massive rework.
 	 */
-	pci_setup_phb_io(phb, 0);
+	pci_setup_phb_io(phb, pci_io_base == 0);
 
 	/* Init pci_dn data structures */
 	pci_devs_phb_init_dynamic(phb);
diff --git a/arch/powerpc/platforms/cell/cbe_cpufreq.c b/arch/powerpc/platforms/cell/cbe_cpufreq.c
index f9ac3fe..ac445998 100644
--- a/arch/powerpc/platforms/cell/cbe_cpufreq.c
+++ b/arch/powerpc/platforms/cell/cbe_cpufreq.c
@@ -67,6 +67,7 @@ static u64 MIC_Slow_Next_Timer_table[] = {
 	0x00003FC000000000ull,
 };
 
+static unsigned int pmi_frequency_limit = 0;
 /*
  * hardware specific functions
  */
@@ -164,7 +165,6 @@ static int set_pmode(int cpu, unsigned int slow_mode) {
 
 static void cbe_cpufreq_handle_pmi(struct of_device *dev, pmi_message_t pmi_msg)
 {
-	struct cpufreq_policy policy;
 	u8 cpu;
 	u8 cbe_pmode_new;
 
@@ -173,15 +173,27 @@ static void cbe_cpufreq_handle_pmi(struct of_device *dev, pmi_message_t pmi_msg)
 	cpu = cbe_node_to_cpu(pmi_msg.data1);
 	cbe_pmode_new = pmi_msg.data2;
 
-	cpufreq_get_policy(&policy, cpu);
+	pmi_frequency_limit = cbe_freqs[cbe_pmode_new].frequency;
 
-	policy.max = min(policy.max, cbe_freqs[cbe_pmode_new].frequency);
-	policy.min = min(policy.min, policy.max);
+	pr_debug("cbe_handle_pmi: max freq=%d\n", pmi_frequency_limit);
+}
+
+static int pmi_notifier(struct notifier_block *nb,
+				       unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
 
-	pr_debug("cbe_handle_pmi: new policy.min=%d policy.max=%d\n", policy.min, policy.max);
-	cpufreq_set_policy(&policy);
+	if (event != CPUFREQ_INCOMPATIBLE)
+		return 0;
+
+	cpufreq_verify_within_limits(policy, 0, pmi_frequency_limit);
+	return 0;
 }
 
+static struct notifier_block pmi_notifier_block = {
+	.notifier_call = pmi_notifier,
+};
+
 static struct pmi_handler cbe_pmi_handler = {
 	.type			= PMI_TYPE_FREQ_CHANGE,
 	.handle_pmi_message	= cbe_cpufreq_handle_pmi,
@@ -238,12 +250,21 @@ static int cbe_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpufreq_frequency_table_get_attr(cbe_freqs, policy->cpu);
 
+	if (pmi_dev) {
+		/* frequency might get limited later, initialize limit with max_freq */
+		pmi_frequency_limit = max_freq;
+		cpufreq_register_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
+	}
+
 	/* this ensures that policy->cpuinfo_min and policy->cpuinfo_max are set correctly */
 	return cpufreq_frequency_table_cpuinfo(policy, cbe_freqs);
 }
 
 static int cbe_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
+	if (pmi_dev)
+		cpufreq_unregister_notifier(&pmi_notifier_block, CPUFREQ_POLICY_NOTIFIER);
+
 	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
 }
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 8654749..7c51cb5 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -39,7 +39,7 @@ struct spu_context *alloc_spu_context(struct spu_gang *gang)
 	if (spu_init_csa(&ctx->csa))
 		goto out_free;
 	spin_lock_init(&ctx->mmio_lock);
-	spin_lock_init(&ctx->mapping_lock);
+	mutex_init(&ctx->mapping_lock);
 	kref_init(&ctx->kref);
 	mutex_init(&ctx->state_mutex);
 	mutex_init(&ctx->run_mutex);
@@ -103,6 +103,7 @@ void spu_forget(struct spu_context *ctx)
 
 void spu_unmap_mappings(struct spu_context *ctx)
 {
+	mutex_lock(&ctx->mapping_lock);
 	if (ctx->local_store)
 		unmap_mapping_range(ctx->local_store, 0, LS_SIZE, 1);
 	if (ctx->mfc)
@@ -117,6 +118,7 @@ void spu_unmap_mappings(struct spu_context *ctx)
 		unmap_mapping_range(ctx->mss, 0, 0x1000, 1);
 	if (ctx->psmap)
 		unmap_mapping_range(ctx->psmap, 0, 0x20000, 1);
+	mutex_unlock(&ctx->mapping_lock);
 }
 
 /**
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 45614c73..b1e7e2f 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -45,11 +45,11 @@ spufs_mem_open(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = ctx;
 	if (!i->i_openers++)
 		ctx->local_store = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -59,10 +59,10 @@ spufs_mem_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->local_store = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -217,6 +217,7 @@ unsigned long spufs_get_unmapped_area(struct file *file, unsigned long addr,
 
 static const struct file_operations spufs_mem_fops = {
 	.open	 		= spufs_mem_open,
+	.release 		= spufs_mem_release,
 	.read   		= spufs_mem_read,
 	.write   		= spufs_mem_write,
 	.llseek  		= generic_file_llseek,
@@ -309,11 +310,11 @@ static int spufs_cntl_open(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = ctx;
 	if (!i->i_openers++)
 		ctx->cntl = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return simple_attr_open(inode, file, spufs_cntl_get,
 					spufs_cntl_set, "0x%08lx");
 }
@@ -326,10 +327,10 @@ spufs_cntl_release(struct inode *inode, struct file *file)
 
 	simple_attr_close(inode, file);
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->cntl = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -812,11 +813,11 @@ static int spufs_signal1_open(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = ctx;
 	if (!i->i_openers++)
 		ctx->signal1 = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return nonseekable_open(inode, file);
 }
 
@@ -826,10 +827,10 @@ spufs_signal1_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->signal1 = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -936,11 +937,11 @@ static int spufs_signal2_open(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = ctx;
 	if (!i->i_openers++)
 		ctx->signal2 = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return nonseekable_open(inode, file);
 }
 
@@ -950,10 +951,10 @@ spufs_signal2_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->signal2 = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -1154,10 +1155,10 @@ static int spufs_mss_open(struct inode *inode, struct file *file)
 
 	file->private_data = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!i->i_openers++)
 		ctx->mss = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return nonseekable_open(inode, file);
 }
 
@@ -1167,10 +1168,10 @@ spufs_mss_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->mss = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -1211,11 +1212,11 @@ static int spufs_psmap_open(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = i->i_ctx;
 	if (!i->i_openers++)
 		ctx->psmap = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return nonseekable_open(inode, file);
 }
 
@@ -1225,10 +1226,10 @@ spufs_psmap_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->psmap = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
@@ -1281,11 +1282,11 @@ static int spufs_mfc_open(struct inode *inode, struct file *file)
 	if (atomic_read(&inode->i_count) != 1)
 		return -EBUSY;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	file->private_data = ctx;
 	if (!i->i_openers++)
 		ctx->mfc = inode->i_mapping;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return nonseekable_open(inode, file);
 }
 
@@ -1295,10 +1296,10 @@ spufs_mfc_release(struct inode *inode, struct file *file)
 	struct spufs_inode_info *i = SPUFS_I(inode);
 	struct spu_context *ctx = i->i_ctx;
 
-	spin_lock(&ctx->mapping_lock);
+	mutex_lock(&ctx->mapping_lock);
 	if (!--i->i_openers)
 		ctx->mfc = NULL;
-	spin_unlock(&ctx->mapping_lock);
+	mutex_unlock(&ctx->mapping_lock);
 	return 0;
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 7150730..9807206 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -177,7 +177,7 @@ static int spufs_rmdir(struct inode *parent, struct dentry *dir)
 static int spufs_fill_dir(struct dentry *dir, struct tree_descr *files,
 			  int mode, struct spu_context *ctx)
 {
-	struct dentry *dentry;
+	struct dentry *dentry, *tmp;
 	int ret;
 
 	while (files->name && files->name[0]) {
@@ -193,7 +193,20 @@ static int spufs_fill_dir(struct dentry *dir, struct tree_descr *files,
 	}
 	return 0;
 out:
-	spufs_prune_dir(dir);
+	/*
+	 * remove all children from dir. dir->inode is not set so don't
+	 * just simply use spufs_prune_dir() and panic afterwards :)
+	 * dput() looks like it will do the right thing:
+	 * - dec parent's ref counter
+	 * - remove child from parent's child list
+	 * - free child's inode if possible
+	 * - free child
+	 */
+	list_for_each_entry_safe(dentry, tmp, &dir->d_subdirs, d_u.d_child) {
+		dput(dentry);
+	}
+
+	shrink_dcache_parent(dir);
 	return ret;
 }
 
@@ -274,6 +287,7 @@ spufs_mkdir(struct inode *dir, struct dentry *dentry, unsigned int flags,
 	goto out;
 
 out_free_ctx:
+	spu_forget(ctx);
 	put_spu_context(ctx);
 out_iput:
 	iput(inode);
@@ -349,37 +363,6 @@ out:
 	return ret;
 }
 
-static int spufs_rmgang(struct inode *root, struct dentry *dir)
-{
-	/* FIXME: this fails if the dir is not empty,
-	          which causes a leak of gangs. */
-	return simple_rmdir(root, dir);
-}
-
-static int spufs_gang_close(struct inode *inode, struct file *file)
-{
-	struct inode *parent;
-	struct dentry *dir;
-	int ret;
-
-	dir = file->f_path.dentry;
-	parent = dir->d_parent->d_inode;
-
-	ret = spufs_rmgang(parent, dir);
-	WARN_ON(ret);
-
-	return dcache_dir_close(inode, file);
-}
-
-const struct file_operations spufs_gang_fops = {
-	.open		= dcache_dir_open,
-	.release	= spufs_gang_close,
-	.llseek		= dcache_dir_lseek,
-	.read		= generic_read_dir,
-	.readdir	= dcache_readdir,
-	.fsync		= simple_sync_file,
-};
-
 static int
 spufs_mkgang(struct inode *dir, struct dentry *dentry, int mode)
 {
@@ -407,7 +390,6 @@ spufs_mkgang(struct inode *dir, struct dentry *dentry, int mode)
 	inode->i_fop = &simple_dir_operations;
 
 	d_instantiate(dentry, inode);
-	dget(dentry);
 	dir->i_nlink++;
 	dentry->d_inode->i_nlink++;
 	return ret;
@@ -437,7 +419,7 @@ static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt)
 		goto out;
 	}
 
-	filp->f_op = &spufs_gang_fops;
+	filp->f_op = &simple_dir_operations;
 	fd_install(ret, filp);
 out:
 	return ret;
@@ -458,8 +440,10 @@ static int spufs_create_gang(struct inode *inode,
 	 * in error path of *_open().
 	 */
 	ret = spufs_gang_open(dget(dentry), mntget(mnt));
-	if (ret < 0)
-		WARN_ON(spufs_rmgang(inode, dentry));
+	if (ret < 0) {
+		int err = simple_rmdir(inode, dentry);
+		WARN_ON(err);
+	}
 
 out:
 	mutex_unlock(&inode->i_mutex);
@@ -600,6 +584,10 @@ spufs_create_root(struct super_block *sb, void *data)
 	struct inode *inode;
 	int ret;
 
+	ret = -ENODEV;
+	if (!spu_management_ops)
+		goto out;
+
 	ret = -ENOMEM;
 	inode = spufs_new_inode(sb, S_IFDIR | 0775);
 	if (!inode)
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index b6ecb30..3b831e0 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -93,43 +93,6 @@ void spu_stop_tick(struct spu_context *ctx)
 	}
 }
 
-void spu_sched_tick(struct work_struct *work)
-{
-	struct spu_context *ctx =
-		container_of(work, struct spu_context, sched_work.work);
-	struct spu *spu;
-	int preempted = 0;
-
-	/*
-	 * If this context is being stopped avoid rescheduling from the
-	 * scheduler tick because we would block on the state_mutex.
-	 * The caller will yield the spu later on anyway.
-	 */
-	if (test_bit(SPU_SCHED_EXITING, &ctx->sched_flags))
-		return;
-
-	mutex_lock(&ctx->state_mutex);
-	spu = ctx->spu;
-	if (spu) {
-		int best = sched_find_first_bit(spu_prio->bitmap);
-		if (best <= ctx->prio) {
-			spu_deactivate(ctx);
-			preempted = 1;
-		}
-	}
-	mutex_unlock(&ctx->state_mutex);
-
-	if (preempted) {
-		/*
-		 * We need to break out of the wait loop in spu_run manually
-		 * to ensure this context gets put on the runqueue again
-		 * ASAP.
-		 */
-		wake_up(&ctx->stop_wq);
-	} else
-		spu_start_tick(ctx);
-}
-
 /**
  * spu_add_to_active_list - add spu to active list
  * @spu:	spu to add to the active list
@@ -273,34 +236,6 @@ static void spu_prio_wait(struct spu_context *ctx)
 	remove_wait_queue(&ctx->stop_wq, &wait);
 }
 
-/**
- * spu_reschedule - try to find a runnable context for a spu
- * @spu:       spu available
- *
- * This function is called whenever a spu becomes idle.  It looks for the
- * most suitable runnable spu context and schedules it for execution.
- */
-static void spu_reschedule(struct spu *spu)
-{
-	int best;
-
-	spu_free(spu);
-
-	spin_lock(&spu_prio->runq_lock);
-	best = sched_find_first_bit(spu_prio->bitmap);
-	if (best < MAX_PRIO) {
-		struct list_head *rq = &spu_prio->runq[best];
-		struct spu_context *ctx;
-
-		BUG_ON(list_empty(rq));
-
-		ctx = list_entry(rq->next, struct spu_context, rq);
-		__spu_del_from_rq(ctx);
-		wake_up(&ctx->stop_wq);
-	}
-	spin_unlock(&spu_prio->runq_lock);
-}
-
 static struct spu *spu_get_idle(struct spu_context *ctx)
 {
 	struct spu *spu = NULL;
@@ -429,6 +364,51 @@ int spu_activate(struct spu_context *ctx, unsigned long flags)
 }
 
 /**
+ * grab_runnable_context - try to find a runnable context
+ *
+ * Remove the highest priority context on the runqueue and return it
+ * to the caller.  Returns %NULL if no runnable context was found.
+ */
+static struct spu_context *grab_runnable_context(int prio)
+{
+	struct spu_context *ctx = NULL;
+	int best;
+
+	spin_lock(&spu_prio->runq_lock);
+	best = sched_find_first_bit(spu_prio->bitmap);
+	if (best < prio) {
+		struct list_head *rq = &spu_prio->runq[best];
+
+		BUG_ON(list_empty(rq));
+
+		ctx = list_entry(rq->next, struct spu_context, rq);
+		__spu_del_from_rq(ctx);
+	}
+	spin_unlock(&spu_prio->runq_lock);
+
+	return ctx;
+}
+
+static int __spu_deactivate(struct spu_context *ctx, int force, int max_prio)
+{
+	struct spu *spu = ctx->spu;
+	struct spu_context *new = NULL;
+
+	if (spu) {
+		new = grab_runnable_context(max_prio);
+		if (new || force) {
+			spu_unbind_context(spu, ctx);
+			spu_free(spu);
+			if (new)
+				wake_up(&new->stop_wq);
+		}
+
+	}
+
+	return new != NULL;
+}
+
+/**
  * spu_deactivate - unbind a context from it's physical spu
  * @ctx:	spu context to unbind
  *
@@ -437,12 +417,7 @@ int spu_activate(struct spu_context *ctx, unsigned long flags)
  */
 void spu_deactivate(struct spu_context *ctx)
 {
-	struct spu *spu = ctx->spu;
-
-	if (spu) {
-		spu_unbind_context(spu, ctx);
-		spu_reschedule(spu);
-	}
+	__spu_deactivate(ctx, 1, MAX_PRIO);
 }
 
 /**
@@ -455,21 +430,43 @@ void spu_deactivate(struct spu_context *ctx)
  */
 void spu_yield(struct spu_context *ctx)
 {
-	struct spu *spu;
-
-	if (mutex_trylock(&ctx->state_mutex)) {
-		if ((spu = ctx->spu) != NULL) {
-			int best = sched_find_first_bit(spu_prio->bitmap);
-			if (best < MAX_PRIO) {
-				pr_debug("%s: yielding SPU %d NODE %d\n",
-					 __FUNCTION__, spu->number, spu->node);
-				spu_deactivate(ctx);
-			}
-		}
+	if (!(ctx->flags & SPU_CREATE_NOSCHED)) {
+		mutex_lock(&ctx->state_mutex);
+		__spu_deactivate(ctx, 0, MAX_PRIO);
 		mutex_unlock(&ctx->state_mutex);
 	}
 }
 
+void spu_sched_tick(struct work_struct *work)
+{
+	struct spu_context *ctx =
+		container_of(work, struct spu_context, sched_work.work);
+	int preempted;
+
+	/*
+	 * If this context is being stopped avoid rescheduling from the
+	 * scheduler tick because we would block on the state_mutex.
+	 * The caller will yield the spu later on anyway.
+	 */
+	if (test_bit(SPU_SCHED_EXITING, &ctx->sched_flags))
+		return;
+
+	mutex_lock(&ctx->state_mutex);
+	preempted = __spu_deactivate(ctx, 0, ctx->prio + 1);
+	mutex_unlock(&ctx->state_mutex);
+
+	if (preempted) {
+		/*
+		 * We need to break out of the wait loop in spu_run manually
+		 * to ensure this context gets put on the runqueue again
+		 * ASAP.
+		 */
+		wake_up(&ctx->stop_wq);
+	} else {
+		spu_start_tick(ctx);
+	}
+}
+
 int __init spu_sched_init(void)
 {
 	int i;
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 0a947fd..47617e8 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -55,7 +55,7 @@ struct spu_context {
 	struct address_space *signal2;	   /* 'signal2' area mappings. */
 	struct address_space *mss;	   /* 'mss' area mappings. */
 	struct address_space *psmap;	   /* 'psmap' area mappings. */
-	spinlock_t mapping_lock;
+	struct mutex mapping_lock;
 	u64 object_id;		   /* user space pointer for oprofile */
 
 	enum { SPU_STATE_RUNNABLE, SPU_STATE_SAVED } state;
diff --git a/arch/powerpc/platforms/celleb/Makefile b/arch/powerpc/platforms/celleb/Makefile
index f4f8252..5240046 100644
--- a/arch/powerpc/platforms/celleb/Makefile
+++ b/arch/powerpc/platforms/celleb/Makefile
@@ -4,5 +4,5 @@ obj-y				+= interrupt.o iommu.o setup.o \
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PPC_UDBG_BEAT)	+= udbg_beat.o
-obj-$(CONFIG_HAS_TXX9_SERIAL)	+= scc_sio.o
+obj-$(CONFIG_SERIAL_TXX9)	+= scc_sio.o
 obj-$(CONFIG_SPU_BASE)		+= spu_priv1.o
diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c
index 95fa6a7..f33b21b 100644
--- a/arch/powerpc/platforms/pasemi/iommu.c
+++ b/arch/powerpc/platforms/pasemi/iommu.c
@@ -31,8 +31,6 @@
 #define IOBMAP_PAGE_SIZE	(1 << IOBMAP_PAGE_SHIFT)
 #define IOBMAP_PAGE_MASK	(IOBMAP_PAGE_SIZE - 1)
 
-#define IOBMAP_PAGE_FACTOR	(PAGE_SHIFT - IOBMAP_PAGE_SHIFT)
-
 #define IOB_BASE		0xe0000000
 #define IOB_SIZE		0x3000
 /* Configuration registers */
@@ -97,9 +95,6 @@ static void iobmap_build(struct iommu_table *tbl, long index,
 
 	bus_addr = (tbl->it_offset + index) << PAGE_SHIFT;
 
-	npages <<= IOBMAP_PAGE_FACTOR;
-	index <<= IOBMAP_PAGE_FACTOR;
-
 	ip = ((u32 *)tbl->it_base) + index;
 
 	while (npages--) {
@@ -125,9 +120,6 @@ static void iobmap_free(struct iommu_table *tbl, long index,
 
 	bus_addr = (tbl->it_offset + index) << PAGE_SHIFT;
 
-	npages <<= IOBMAP_PAGE_FACTOR;
-	index <<= IOBMAP_PAGE_FACTOR;
-
 	ip = ((u32 *)tbl->it_base) + index;
 
 	while (npages--) {
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index bd00f89..89a1b46 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -396,6 +396,15 @@ config SCHED_SMT
 	  when dealing with UltraSPARC cpus at a cost of slightly increased
 	  overhead in some places. If unsure say N here.
 
+config SCHED_MC
+	bool "Multi-core scheduler support"
+	depends on SMP
+	default y
+	help
+	  Multi-core scheduler support improves the CPU scheduler's decision
+	  making when dealing with multi-core CPU chips at a cost of slightly
+	  increased overhead in some places. If unsure say N here.
+
 source "kernel/Kconfig.preempt"
 
 config CMDLINE_BOOL
diff --git a/arch/sparc64/kernel/Makefile b/arch/sparc64/kernel/Makefile
index d8d1909..f964bf2 100644
--- a/arch/sparc64/kernel/Makefile
+++ b/arch/sparc64/kernel/Makefile
@@ -1,4 +1,4 @@
-# $Id: Makefile,v 1.70 2002/02/09 19:49:30 davem Exp $
+#
 # Makefile for the linux kernel.
 #
 
@@ -8,7 +8,7 @@ EXTRA_CFLAGS := -Werror
 extra-y		:= head.o init_task.o vmlinux.lds
 
 obj-y		:= process.o setup.o cpu.o idprom.o \
-		   traps.o auxio.o una_asm.o \
+		   traps.o auxio.o una_asm.o sysfs.o \
 		   irq.o ptrace.o time.o sys_sparc.o signal.o \
 		   unaligned.o central.o pci.o starfire.o semaphore.o \
 		   power.o sbus.o iommu_common.o sparc64_ksyms.o chmc.o \
diff --git a/arch/sparc64/kernel/entry.S b/arch/sparc64/kernel/entry.S
index ed712e0..7d1a118 100644
--- a/arch/sparc64/kernel/entry.S
+++ b/arch/sparc64/kernel/entry.S
@@ -2514,9 +2514,9 @@ sun4v_ncs_request:
 	 nop
 	.size	sun4v_ncs_request, .-sun4v_ncs_request
 
-	.globl	sun4v_scv_send
-	.type	sun4v_scv_send,#function
-sun4v_scv_send:
+	.globl	sun4v_svc_send
+	.type	sun4v_svc_send,#function
+sun4v_svc_send:
 	save	%sp, -192, %sp
 	mov	%i0, %o0
 	mov	%i1, %o1
@@ -2526,11 +2526,11 @@ sun4v_scv_send:
 	stx	%o1, [%i3]
 	ret
 	restore
-	.size	sun4v_scv_send, .-sun4v_scv_send
+	.size	sun4v_svc_send, .-sun4v_svc_send
 
-	.globl	sun4v_scv_recv
-	.type	sun4v_scv_recv,#function
-sun4v_scv_recv:
+	.globl	sun4v_svc_recv
+	.type	sun4v_svc_recv,#function
+sun4v_svc_recv:
 	save	%sp, -192, %sp
 	mov	%i0, %o0
 	mov	%i1, %o1
@@ -2540,33 +2540,55 @@ sun4v_scv_recv:
 	stx	%o1, [%i3]
 	ret
 	restore
-	.size	sun4v_scv_recv, .-sun4v_scv_recv
+	.size	sun4v_svc_recv, .-sun4v_svc_recv
 
-	.globl	sun4v_scv_getstatus
-	.type	sun4v_scv_getstatus,#function
-sun4v_scv_getstatus:
+	.globl	sun4v_svc_getstatus
+	.type	sun4v_svc_getstatus,#function
+sun4v_svc_getstatus:
 	mov	HV_FAST_SVC_GETSTATUS, %o5
 	mov	%o1, %o4
 	ta	HV_FAST_TRAP
 	stx	%o1, [%o4]
 	retl
 	 nop
-	.size	sun4v_scv_getstatus, .-sun4v_scv_getstatus
+	.size	sun4v_svc_getstatus, .-sun4v_svc_getstatus
 
-	.globl	sun4v_scv_setstatus
-	.type	sun4v_scv_setstatus,#function
-sun4v_scv_setstatus:
+	.globl	sun4v_svc_setstatus
+	.type	sun4v_svc_setstatus,#function
+sun4v_svc_setstatus:
 	mov	HV_FAST_SVC_SETSTATUS, %o5
 	ta	HV_FAST_TRAP
 	retl
 	 nop
-	.size	sun4v_scv_setstatus, .-sun4v_scv_setstatus
+	.size	sun4v_svc_setstatus, .-sun4v_svc_setstatus
 
-	.globl	sun4v_scv_clrstatus
-	.type	sun4v_scv_clrstatus,#function
-sun4v_scv_clrstatus:
+	.globl	sun4v_svc_clrstatus
+	.type	sun4v_svc_clrstatus,#function
+sun4v_svc_clrstatus:
 	mov	HV_FAST_SVC_CLRSTATUS, %o5
 	ta	HV_FAST_TRAP
 	retl
 	 nop
-	.size	sun4v_scv_clrstatus, .-sun4v_scv_clrstatus
+	.size	sun4v_svc_clrstatus, .-sun4v_svc_clrstatus
+
+	.globl	sun4v_mmustat_conf
+	.type	sun4v_mmustat_conf,#function
+sun4v_mmustat_conf:
+	mov	%o1, %o4
+	mov	HV_FAST_MMUSTAT_CONF, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+	.size	sun4v_mmustat_conf, .-sun4v_mmustat_conf
+
+	.globl	sun4v_mmustat_info
+	.type	sun4v_mmustat_info,#function
+sun4v_mmustat_info:
+	mov	%o0, %o4
+	mov	HV_FAST_MMUSTAT_INFO, %o5
+	ta	HV_FAST_TRAP
+	stx	%o1, [%o4]
+	retl
+	 nop
+	.size	sun4v_mmustat_info, .-sun4v_mmustat_info
diff --git a/arch/sparc64/kernel/mdesc.c b/arch/sparc64/kernel/mdesc.c
index 9246c2c..f0e16045 100644
--- a/arch/sparc64/kernel/mdesc.c
+++ b/arch/sparc64/kernel/mdesc.c
@@ -473,6 +473,53 @@ static void __init set_core_ids(void)
 	}
 }
 
+static void __init mark_proc_ids(struct mdesc_node *mp, int proc_id)
+{
+	int i;
+
+	for (i = 0; i < mp->num_arcs; i++) {
+		struct mdesc_node *t = mp->arcs[i].arc;
+		const u64 *id;
+
+		if (strcmp(mp->arcs[i].name, "back"))
+			continue;
+
+		if (strcmp(t->name, "cpu"))
+			continue;
+
+		id = md_get_property(t, "id", NULL);
+		if (*id < NR_CPUS)
+			cpu_data(*id).proc_id = proc_id;
+	}
+}
+
+static void __init __set_proc_ids(const char *exec_unit_name)
+{
+	struct mdesc_node *mp;
+	int idx;
+
+	idx = 0;
+	md_for_each_node_by_name(mp, exec_unit_name) {
+		const char *type;
+		int len;
+
+		type = md_get_property(mp, "type", &len);
+		if (!find_in_proplist(type, "int", len) &&
+		    !find_in_proplist(type, "integer", len))
+			continue;
+
+		mark_proc_ids(mp, idx);
+
+		idx++;
+	}
+}
+
+static void __init set_proc_ids(void)
+{
+	__set_proc_ids("exec_unit");
+	__set_proc_ids("exec-unit");
+}
+
 static void __init get_one_mondo_bits(const u64 *p, unsigned int *mask, unsigned char def)
 {
 	u64 val;
@@ -574,9 +621,15 @@ static void __init mdesc_fill_in_cpu_data(void)
 #endif
 
 		c->core_id = 0;
+		c->proc_id = -1;
 	}
 
+#ifdef CONFIG_SMP
+	sparc64_multi_core = 1;
+#endif
+
 	set_core_ids();
+	set_proc_ids();
 
 	smp_fill_in_sib_core_maps();
 }
diff --git a/arch/sparc64/kernel/prom.c b/arch/sparc64/kernel/prom.c
index dad4b3b..6f4a528 100644
--- a/arch/sparc64/kernel/prom.c
+++ b/arch/sparc64/kernel/prom.c
@@ -1781,6 +1781,10 @@ static void __init of_fill_in_cpu_data(void)
 			}
 
 			cpu_data(cpuid).core_id = portid + 1;
+			cpu_data(cpuid).proc_id = portid;
+#ifdef CONFIG_SMP
+			sparc64_multi_core = 1;
+#endif
 		} else {
 			cpu_data(cpuid).dcache_size =
 				of_getintprop_default(dp, "dcache-size", 16 * 1024);
@@ -1799,6 +1803,7 @@ static void __init of_fill_in_cpu_data(void)
 				of_getintprop_default(dp, "ecache-line-size", 64);
 
 			cpu_data(cpuid).core_id = 0;
+			cpu_data(cpuid).proc_id = -1;
 		}
 
 #ifdef CONFIG_SMP
diff --git a/arch/sparc64/kernel/setup.c b/arch/sparc64/kernel/setup.c
index de9b4c1..7490cc6 100644
--- a/arch/sparc64/kernel/setup.c
+++ b/arch/sparc64/kernel/setup.c
@@ -513,22 +513,3 @@ void sun_do_break(void)
 
 int serial_console = -1;
 int stop_a_enabled = 1;
-
-static int __init topology_init(void)
-{
-	int i, err;
-
-	err = -ENOMEM;
-
-	for_each_possible_cpu(i) {
-		struct cpu *p = kzalloc(sizeof(*p), GFP_KERNEL);
-		if (p) {
-			register_cpu(p, i);
-			err = 0;
-		}
-	}
-
-	return err;
-}
-
-subsys_initcall(topology_init);
diff --git a/arch/sparc64/kernel/smp.c b/arch/sparc64/kernel/smp.c
index c550bba..4dcd7d0 100644
--- a/arch/sparc64/kernel/smp.c
+++ b/arch/sparc64/kernel/smp.c
@@ -44,6 +44,8 @@
 
 extern void calibrate_delay(void);
 
+int sparc64_multi_core __read_mostly;
+
 /* Please don't make this stuff initdata!!!  --DaveM */
 unsigned char boot_cpu_id;
 
@@ -51,6 +53,8 @@ cpumask_t cpu_online_map __read_mostly = CPU_MASK_NONE;
 cpumask_t phys_cpu_present_map __read_mostly = CPU_MASK_NONE;
 cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly =
 	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
+cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
+	{ [0 ... NR_CPUS-1] = CPU_MASK_NONE };
 static cpumask_t smp_commenced_mask;
 static cpumask_t cpu_callout_map;
 
@@ -1217,13 +1221,28 @@ void __devinit smp_fill_in_sib_core_maps(void)
 		unsigned int j;
 
 		if (cpu_data(i).core_id == 0) {
-			cpu_set(i, cpu_sibling_map[i]);
+			cpu_set(i, cpu_core_map[i]);
 			continue;
 		}
 
 		for_each_possible_cpu(j) {
 			if (cpu_data(i).core_id ==
 			    cpu_data(j).core_id)
+				cpu_set(j, cpu_core_map[i]);
+		}
+	}
+
+	for_each_possible_cpu(i) {
+		unsigned int j;
+
+		if (cpu_data(i).proc_id == -1) {
+			cpu_set(i, cpu_sibling_map[i]);
+			continue;
+		}
+
+		for_each_possible_cpu(j) {
+			if (cpu_data(i).proc_id ==
+			    cpu_data(j).proc_id)
 				cpu_set(j, cpu_sibling_map[i]);
 		}
 	}
diff --git a/arch/sparc64/kernel/sysfs.c b/arch/sparc64/kernel/sysfs.c
new file mode 100644
index 0000000..cdb1477
--- /dev/null
+++ b/arch/sparc64/kernel/sysfs.c
@@ -0,0 +1,297 @@
+/* sysfs.c: Toplogy sysfs support code for sparc64.
+ *
+ * Copyright (C) 2007 David S. Miller <davem@davemloft.net>
+ */
+#include <linux/sysdev.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+
+#include <asm/hypervisor.h>
+#include <asm/spitfire.h>
+
+static DEFINE_PER_CPU(struct hv_mmu_statistics, mmu_stats) __attribute__((aligned(64)));
+
+#define SHOW_MMUSTAT_ULONG(NAME) \
+static ssize_t show_##NAME(struct sys_device *dev, char *buf) \
+{ \
+	struct hv_mmu_statistics *p = &per_cpu(mmu_stats, dev->id); \
+	return sprintf(buf, "%lu\n", p->NAME); \
+} \
+static SYSDEV_ATTR(NAME, 0444, show_##NAME, NULL)
+
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctx0_8k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctx0_8k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctx0_64k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctx0_64k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctx0_4mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctx0_4mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctx0_256mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctx0_256mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctxnon0_8k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctxnon0_8k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctxnon0_64k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctxnon0_64k_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctxnon0_4mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctxnon0_4mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_hits_ctxnon0_256mb_tte);
+SHOW_MMUSTAT_ULONG(immu_tsb_ticks_ctxnon0_256mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctx0_8k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctx0_8k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctx0_64k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctx0_64k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctx0_4mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctx0_4mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctx0_256mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctx0_256mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctxnon0_8k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctxnon0_8k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctxnon0_64k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctxnon0_64k_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctxnon0_4mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctxnon0_4mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_hits_ctxnon0_256mb_tte);
+SHOW_MMUSTAT_ULONG(dmmu_tsb_ticks_ctxnon0_256mb_tte);
+
+static struct attribute *mmu_stat_attrs[] = {
+	&attr_immu_tsb_hits_ctx0_8k_tte.attr,
+	&attr_immu_tsb_ticks_ctx0_8k_tte.attr,
+	&attr_immu_tsb_hits_ctx0_64k_tte.attr,
+	&attr_immu_tsb_ticks_ctx0_64k_tte.attr,
+	&attr_immu_tsb_hits_ctx0_4mb_tte.attr,
+	&attr_immu_tsb_ticks_ctx0_4mb_tte.attr,
+	&attr_immu_tsb_hits_ctx0_256mb_tte.attr,
+	&attr_immu_tsb_ticks_ctx0_256mb_tte.attr,
+	&attr_immu_tsb_hits_ctxnon0_8k_tte.attr,
+	&attr_immu_tsb_ticks_ctxnon0_8k_tte.attr,
+	&attr_immu_tsb_hits_ctxnon0_64k_tte.attr,
+	&attr_immu_tsb_ticks_ctxnon0_64k_tte.attr,
+	&attr_immu_tsb_hits_ctxnon0_4mb_tte.attr,
+	&attr_immu_tsb_ticks_ctxnon0_4mb_tte.attr,
+	&attr_immu_tsb_hits_ctxnon0_256mb_tte.attr,
+	&attr_immu_tsb_ticks_ctxnon0_256mb_tte.attr,
+	&attr_dmmu_tsb_hits_ctx0_8k_tte.attr,
+	&attr_dmmu_tsb_ticks_ctx0_8k_tte.attr,
+	&attr_dmmu_tsb_hits_ctx0_64k_tte.attr,
+	&attr_dmmu_tsb_ticks_ctx0_64k_tte.attr,
+	&attr_dmmu_tsb_hits_ctx0_4mb_tte.attr,
+	&attr_dmmu_tsb_ticks_ctx0_4mb_tte.attr,
+	&attr_dmmu_tsb_hits_ctx0_256mb_tte.attr,
+	&attr_dmmu_tsb_ticks_ctx0_256mb_tte.attr,
+	&attr_dmmu_tsb_hits_ctxnon0_8k_tte.attr,
+	&attr_dmmu_tsb_ticks_ctxnon0_8k_tte.attr,
+	&attr_dmmu_tsb_hits_ctxnon0_64k_tte.attr,
+	&attr_dmmu_tsb_ticks_ctxnon0_64k_tte.attr,
+	&attr_dmmu_tsb_hits_ctxnon0_4mb_tte.attr,
+	&attr_dmmu_tsb_ticks_ctxnon0_4mb_tte.attr,
+	&attr_dmmu_tsb_hits_ctxnon0_256mb_tte.attr,
+	&attr_dmmu_tsb_ticks_ctxnon0_256mb_tte.attr,
+	NULL,
+};
+
+static struct attribute_group mmu_stat_group = {
+	.attrs = mmu_stat_attrs,
+	.name = "mmu_stats",
+};
+
+/* XXX convert to rusty's on_one_cpu */
+static unsigned long run_on_cpu(unsigned long cpu,
+			        unsigned long (*func)(unsigned long),
+				unsigned long arg)
+{
+	cpumask_t old_affinity = current->cpus_allowed;
+	unsigned long ret;
+
+	/* should return -EINVAL to userspace */
+	if (set_cpus_allowed(current, cpumask_of_cpu(cpu)))
+		return 0;
+
+	ret = func(arg);
+
+	set_cpus_allowed(current, old_affinity);
+
+	return ret;
+}
+
+static unsigned long read_mmustat_enable(unsigned long junk)
+{
+	unsigned long ra = 0;
+
+	sun4v_mmustat_info(&ra);
+
+	return ra != 0;
+}
+
+static unsigned long write_mmustat_enable(unsigned long val)
+{
+	unsigned long ra, orig_ra;
+
+	if (val)
+		ra = __pa(&per_cpu(mmu_stats, smp_processor_id()));
+	else
+		ra = 0UL;
+
+	return sun4v_mmustat_conf(ra, &orig_ra);
+}
+
+static ssize_t show_mmustat_enable(struct sys_device *s, char *buf)
+{
+	unsigned long val = run_on_cpu(s->id, read_mmustat_enable, 0);
+	return sprintf(buf, "%lx\n", val);
+}
+
+static ssize_t store_mmustat_enable(struct sys_device *s, const char *buf, size_t count)
+{
+	unsigned long val, err;
+	int ret = sscanf(buf, "%ld", &val);
+
+	if (ret != 1)
+		return -EINVAL;
+
+	err = run_on_cpu(s->id, write_mmustat_enable, val);
+	if (err)
+		return -EIO;
+
+	return count;
+}
+
+static SYSDEV_ATTR(mmustat_enable, 0644, show_mmustat_enable, store_mmustat_enable);
+
+static int mmu_stats_supported;
+
+static int register_mmu_stats(struct sys_device *s)
+{
+	if (!mmu_stats_supported)
+		return 0;
+	sysdev_create_file(s, &attr_mmustat_enable);
+	return sysfs_create_group(&s->kobj, &mmu_stat_group);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void unregister_mmu_stats(struct sys_device *s)
+{
+	if (!mmu_stats_supported)
+		return;
+	sysfs_remove_group(&s->kobj, &mmu_stat_group);
+	sysdev_remove_file(s, &attr_mmustat_enable);
+}
+#endif
+
+#define SHOW_CPUDATA_ULONG_NAME(NAME, MEMBER) \
+static ssize_t show_##NAME(struct sys_device *dev, char *buf) \
+{ \
+	cpuinfo_sparc *c = &cpu_data(dev->id); \
+	return sprintf(buf, "%lu\n", c->MEMBER); \
+}
+
+#define SHOW_CPUDATA_UINT_NAME(NAME, MEMBER) \
+static ssize_t show_##NAME(struct sys_device *dev, char *buf) \
+{ \
+	cpuinfo_sparc *c = &cpu_data(dev->id); \
+	return sprintf(buf, "%u\n", c->MEMBER); \
+}
+
+SHOW_CPUDATA_ULONG_NAME(clock_tick, clock_tick);
+SHOW_CPUDATA_ULONG_NAME(udelay_val, udelay_val);
+SHOW_CPUDATA_UINT_NAME(l1_dcache_size, dcache_size);
+SHOW_CPUDATA_UINT_NAME(l1_dcache_line_size, dcache_line_size);
+SHOW_CPUDATA_UINT_NAME(l1_icache_size, icache_size);
+SHOW_CPUDATA_UINT_NAME(l1_icache_line_size, icache_line_size);
+SHOW_CPUDATA_UINT_NAME(l2_cache_size, ecache_size);
+SHOW_CPUDATA_UINT_NAME(l2_cache_line_size, ecache_line_size);
+
+static struct sysdev_attribute cpu_core_attrs[] = {
+	_SYSDEV_ATTR(clock_tick,          0444, show_clock_tick, NULL),
+	_SYSDEV_ATTR(udelay_val,          0444, show_udelay_val, NULL),
+	_SYSDEV_ATTR(l1_dcache_size,      0444, show_l1_dcache_size, NULL),
+	_SYSDEV_ATTR(l1_dcache_line_size, 0444, show_l1_dcache_line_size, NULL),
+	_SYSDEV_ATTR(l1_icache_size,      0444, show_l1_icache_size, NULL),
+	_SYSDEV_ATTR(l1_icache_line_size, 0444, show_l1_icache_line_size, NULL),
+	_SYSDEV_ATTR(l2_cache_size,       0444, show_l2_cache_size, NULL),
+	_SYSDEV_ATTR(l2_cache_line_size,  0444, show_l2_cache_line_size, NULL),
+};
+
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
+
+static void register_cpu_online(unsigned int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct sys_device *s = &c->sysdev;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(cpu_core_attrs); i++)
+		sysdev_create_file(s, &cpu_core_attrs[i]);
+
+	register_mmu_stats(s);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void unregister_cpu_online(unsigned int cpu)
+{
+	struct cpu *c = &per_cpu(cpu_devices, cpu);
+	struct sys_device *s = &c->sysdev;
+	int i;
+
+	unregister_mmu_stats(s);
+	for (i = 0; i < ARRAY_SIZE(cpu_core_attrs); i++)
+		sysdev_remove_file(s, &cpu_core_attrs[i]);
+}
+#endif
+
+static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
+				      unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned int)(long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		register_cpu_online(cpu);
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		unregister_cpu_online(cpu);
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata sysfs_cpu_nb = {
+	.notifier_call	= sysfs_cpu_notify,
+};
+
+static void __init check_mmu_stats(void)
+{
+	unsigned long dummy1, err;
+
+	if (tlb_type != hypervisor)
+		return;
+
+	err = sun4v_mmustat_info(&dummy1);
+	if (!err)
+		mmu_stats_supported = 1;
+}
+
+static int __init topology_init(void)
+{
+	int cpu;
+
+	check_mmu_stats();
+
+	register_cpu_notifier(&sysfs_cpu_nb);
+
+	for_each_possible_cpu(cpu) {
+		struct cpu *c = &per_cpu(cpu_devices, cpu);
+
+		register_cpu(c, cpu);
+		if (cpu_online(cpu))
+			register_cpu_online(cpu);
+	}
+
+	return 0;
+}
+
+subsys_initcall(topology_init);