Merge ../linux-2.6

9 files changed, 205 insertions, 114 deletions

diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 856ef1a832b..f78866367b7 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -90,15 +90,15 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
 
 static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = *p->ainsn.insn;
-
 	regs->msr |= MSR_SE;
 
-	/* single step inline if it is a trap variant */
-	if (is_trap(insn))
-		regs->nip = (unsigned long)p->addr;
-	else
-		regs->nip = (unsigned long)p->ainsn.insn;
+	/*
+	 * On powerpc we should single step on the original
+	 * instruction even if the probed insn is a trap
+	 * variant as values in regs could play a part in
+	 * if the trap is taken or not
+	 */
+	regs->nip = (unsigned long)p->ainsn.insn;
 }
 
 static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 1cb69e8fb0b..9a07f97f071 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -885,6 +885,74 @@ void __init unflatten_device_tree(void)
 	DBG(" <- unflatten_device_tree()\n");
 }
 
+/*
+ * ibm,pa-features is a per-cpu property that contains a string of
+ * attribute descriptors, each of which has a 2 byte header plus up
+ * to 254 bytes worth of processor attribute bits.  First header
+ * byte specifies the number of bytes following the header.
+ * Second header byte is an "attribute-specifier" type, of which
+ * zero is the only currently-defined value.
+ * Implementation:  Pass in the byte and bit offset for the feature
+ * that we are interested in.  The function will return -1 if the
+ * pa-features property is missing, or a 1/0 to indicate if the feature
+ * is supported/not supported.  Note that the bit numbers are
+ * big-endian to match the definition in PAPR.
+ */
+static struct ibm_pa_feature {
+	unsigned long	cpu_features;	/* CPU_FTR_xxx bit */
+	unsigned int	cpu_user_ftrs;	/* PPC_FEATURE_xxx bit */
+	unsigned char	pabyte;		/* byte number in ibm,pa-features */
+	unsigned char	pabit;		/* bit number (big-endian) */
+	unsigned char	invert;		/* if 1, pa bit set => clear feature */
+} ibm_pa_features[] __initdata = {
+	{0, PPC_FEATURE_HAS_MMU,	0, 0, 0},
+	{0, PPC_FEATURE_HAS_FPU,	0, 1, 0},
+	{CPU_FTR_SLB, 0,		0, 2, 0},
+	{CPU_FTR_CTRL, 0,		0, 3, 0},
+	{CPU_FTR_NOEXECUTE, 0,		0, 6, 0},
+	{CPU_FTR_NODSISRALIGN, 0,	1, 1, 1},
+	{CPU_FTR_CI_LARGE_PAGE, 0,	1, 2, 0},
+};
+
+static void __init check_cpu_pa_features(unsigned long node)
+{
+	unsigned char *pa_ftrs;
+	unsigned long len, tablelen, i, bit;
+
+	pa_ftrs = of_get_flat_dt_prop(node, "ibm,pa-features", &tablelen);
+	if (pa_ftrs == NULL)
+		return;
+
+	/* find descriptor with type == 0 */
+	for (;;) {
+		if (tablelen < 3)
+			return;
+		len = 2 + pa_ftrs[0];
+		if (tablelen < len)
+			return;		/* descriptor 0 not found */
+		if (pa_ftrs[1] == 0)
+			break;
+		tablelen -= len;
+		pa_ftrs += len;
+	}
+
+	/* loop over bits we know about */
+	for (i = 0; i < ARRAY_SIZE(ibm_pa_features); ++i) {
+		struct ibm_pa_feature *fp = &ibm_pa_features[i];
+
+		if (fp->pabyte >= pa_ftrs[0])
+			continue;
+		bit = (pa_ftrs[2 + fp->pabyte] >> (7 - fp->pabit)) & 1;
+		if (bit ^ fp->invert) {
+			cur_cpu_spec->cpu_features |= fp->cpu_features;
+			cur_cpu_spec->cpu_user_features |= fp->cpu_user_ftrs;
+		} else {
+			cur_cpu_spec->cpu_features &= ~fp->cpu_features;
+			cur_cpu_spec->cpu_user_features &= ~fp->cpu_user_ftrs;
+		}
+	}
+}
+
 static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
@@ -969,6 +1037,8 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	}
 #endif /* CONFIG_ALTIVEC */
 
+	check_cpu_pa_features(node);
+
 #ifdef CONFIG_PPC_PSERIES
 	if (nthreads > 1)
 		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index bcb83574335..4a677d1bd4e 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -538,7 +538,7 @@ void do_syscall_trace_enter(struct pt_regs *regs)
 		do_syscall_trace();
 
 	if (unlikely(current->audit_context))
-		audit_syscall_entry(current,
+		audit_syscall_entry(
 #ifdef CONFIG_PPC32
 				    AUDIT_ARCH_PPC,
 #else
@@ -556,8 +556,7 @@ void do_syscall_trace_leave(struct pt_regs *regs)
 #endif
 
 	if (unlikely(current->audit_context))
-		audit_syscall_exit(current,
-				   (regs->ccr&0x1000)?AUDITSC_FAILURE:AUDITSC_SUCCESS,
+		audit_syscall_exit((regs->ccr&0x1000)?AUDITSC_FAILURE:AUDITSC_SUCCESS,
 				   regs->result);
 
 	if ((test_thread_flag(TIF_SYSCALL_TRACE)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index ed737cacf92..5bc2585c803 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -322,13 +322,31 @@ static void register_nodes(void)
 		}
 	}
 }
+
+int sysfs_add_device_to_node(struct sys_device *dev, int nid)
+{
+	struct node *node = &node_devices[nid];
+	return sysfs_create_link(&node->sysdev.kobj, &dev->kobj,
+			kobject_name(&dev->kobj));
+}
+
+void sysfs_remove_device_from_node(struct sys_device *dev, int nid)
+{
+	struct node *node = &node_devices[nid];
+	sysfs_remove_link(&node->sysdev.kobj, kobject_name(&dev->kobj));
+}
+
 #else
 static void register_nodes(void)
 {
 	return;
 }
+
 #endif
 
+EXPORT_SYMBOL_GPL(sysfs_add_device_to_node);
+EXPORT_SYMBOL_GPL(sysfs_remove_device_from_node);
+
 /* Only valid if CPU is present. */
 static ssize_t show_physical_id(struct sys_device *dev, char *buf)
 {
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index ea816c618a7..aa98cb3b59d 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -194,7 +194,7 @@ static int *of_get_associativity(struct device_node *dev)
 /* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
  * info is found.
  */
-static int of_node_to_nid(struct device_node *device)
+static int of_node_to_nid_single(struct device_node *device)
 {
 	int nid = -1;
 	unsigned int *tmp;
@@ -216,6 +216,28 @@ out:
 	return nid;
 }
 
+/* Walk the device tree upwards, looking for an associativity id */
+int of_node_to_nid(struct device_node *device)
+{
+	struct device_node *tmp;
+	int nid = -1;
+
+	of_node_get(device);
+	while (device) {
+		nid = of_node_to_nid_single(device);
+		if (nid != -1)
+			break;
+
+	        tmp = device;
+		device = of_get_parent(tmp);
+		of_node_put(tmp);
+	}
+	of_node_put(device);
+
+	return nid;
+}
+EXPORT_SYMBOL_GPL(of_node_to_nid);
+
 /*
  * In theory, the "ibm,associativity" property may contain multiple
  * associativity lists because a resource may be multiply connected
@@ -300,7 +322,7 @@ static int __cpuinit numa_setup_cpu(unsigned long lcpu)
 		goto out;
 	}
 
-	nid = of_node_to_nid(cpu);
+	nid = of_node_to_nid_single(cpu);
 
 	if (nid < 0 || !node_online(nid))
 		nid = any_online_node(NODE_MASK_ALL);
@@ -393,7 +415,7 @@ static int __init parse_numa_properties(void)
 
 		cpu = find_cpu_node(i);
 		BUG_ON(!cpu);
-		nid = of_node_to_nid(cpu);
+		nid = of_node_to_nid_single(cpu);
 		of_node_put(cpu);
 
 		/*
@@ -437,7 +459,7 @@ new_range:
 		 * have associativity properties.  If none, then
 		 * everything goes to default_nid.
 		 */
-		nid = of_node_to_nid(memory);
+		nid = of_node_to_nid_single(memory);
 		if (nid < 0)
 			nid = default_nid;
 		node_set_online(nid);
@@ -776,7 +798,7 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
 ha_new_range:
 		start = read_n_cells(n_mem_addr_cells, &memcell_buf);
 		size = read_n_cells(n_mem_size_cells, &memcell_buf);
-		nid = of_node_to_nid(memory);
+		nid = of_node_to_nid_single(memory);
 
 		/* Domains not present at boot default to 0 */
 		if (nid < 0 || !node_online(nid))
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index c2a3db8edb0..6a02d51086c 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -12,7 +12,8 @@ config SPU_FS
 
 config SPUFS_MMAP
 	bool
-	depends on SPU_FS && SPARSEMEM && !PPC_64K_PAGES
+	depends on SPU_FS && SPARSEMEM
+	select MEMORY_HOTPLUG
 	default y
 
 endmenu
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index dac5d0365fd..6574b22b3cf 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -29,6 +29,8 @@
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
 #include <linux/console.h>
+#include <linux/mutex.h>
+#include <linux/memory_hotplug.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -46,6 +48,7 @@
 #include <asm/cputable.h>
 #include <asm/ppc-pci.h>
 #include <asm/irq.h>
+#include <asm/spu.h>
 
 #include "interrupt.h"
 #include "iommu.h"
@@ -69,77 +72,6 @@ static void cell_show_cpuinfo(struct seq_file *m)
 	of_node_put(root);
 }
 
-#ifdef CONFIG_SPARSEMEM
-static int __init find_spu_node_id(struct device_node *spe)
-{
-	unsigned int *id;
-#ifdef CONFIG_NUMA
-	struct device_node *cpu;
-	cpu = spe->parent->parent;
-	id = (unsigned int *)get_property(cpu, "node-id", NULL);
-#else
-	id = NULL;
-#endif
-	return id ? *id : 0;
-}
-
-static void __init cell_spuprop_present(struct device_node *spe,
-				       const char *prop, int early)
-{
-	struct address_prop {
-		unsigned long address;
-		unsigned int len;
-	} __attribute__((packed)) *p;
-	int proplen;
-
-	unsigned long start_pfn, end_pfn, pfn;
-	int node_id;
-
-	p = (void*)get_property(spe, prop, &proplen);
-	WARN_ON(proplen != sizeof (*p));
-
-	node_id = find_spu_node_id(spe);
-
-	start_pfn = p->address >> PAGE_SHIFT;
-	end_pfn = (p->address + p->len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-
-	/* We need to call memory_present *before* the call to sparse_init,
-	   but we can initialize the page structs only *after* that call.
-	   Thus, we're being called twice. */
-	if (early)
-		memory_present(node_id, start_pfn, end_pfn);
-	else {
-		/* As the pages backing SPU LS and I/O are outside the range
-		   of regular memory, their page structs were not initialized
-		   by free_area_init. Do it here instead. */
-		for (pfn = start_pfn; pfn < end_pfn; pfn++) {
-			struct page *page = pfn_to_page(pfn);
-			set_page_links(page, ZONE_DMA, node_id, pfn);
-			init_page_count(page);
-			reset_page_mapcount(page);
-			SetPageReserved(page);
-			INIT_LIST_HEAD(&page->lru);
-		}
-	}
-}
-
-static void __init cell_spumem_init(int early)
-{
-	struct device_node *node;
-	for (node = of_find_node_by_type(NULL, "spe");
-			node; node = of_find_node_by_type(node, "spe")) {
-		cell_spuprop_present(node, "local-store", early);
-		cell_spuprop_present(node, "problem", early);
-		cell_spuprop_present(node, "priv1", early);
-		cell_spuprop_present(node, "priv2", early);
-	}
-}
-#else
-static void __init cell_spumem_init(int early)
-{
-}
-#endif
-
 static void cell_progress(char *s, unsigned short hex)
 {
 	printk("*** %04x : %s\n", hex, s ? s : "");
@@ -172,8 +104,6 @@ static void __init cell_setup_arch(void)
 #endif
 
 	mmio_nvram_init();
-
-	cell_spumem_init(0);
 }
 
 /*
@@ -189,8 +119,6 @@ static void __init cell_init_early(void)
 
 	ppc64_interrupt_controller = IC_CELL_PIC;
 
-	cell_spumem_init(1);
-
 	DBG(" <- cell_init_early()\n");
 }
 
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index ef47a6239d4..ad141fe8d52 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -520,8 +520,50 @@ void spu_irq_setaffinity(struct spu *spu, int cpu)
 }
 EXPORT_SYMBOL_GPL(spu_irq_setaffinity);
 
-static void __iomem * __init map_spe_prop(struct device_node *n,
-						 const char *name)
+static int __init find_spu_node_id(struct device_node *spe)
+{
+	unsigned int *id;
+	struct device_node *cpu;
+	cpu = spe->parent->parent;
+	id = (unsigned int *)get_property(cpu, "node-id", NULL);
+	return id ? *id : 0;
+}
+
+static int __init cell_spuprop_present(struct spu *spu, struct device_node *spe,
+		const char *prop)
+{
+	static DEFINE_MUTEX(add_spumem_mutex);
+
+	struct address_prop {
+		unsigned long address;
+		unsigned int len;
+	} __attribute__((packed)) *p;
+	int proplen;
+
+	unsigned long start_pfn, nr_pages;
+	struct pglist_data *pgdata;
+	struct zone *zone;
+	int ret;
+
+	p = (void*)get_property(spe, prop, &proplen);
+	WARN_ON(proplen != sizeof (*p));
+
+	start_pfn = p->address >> PAGE_SHIFT;
+	nr_pages = ((unsigned long)p->len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	pgdata = NODE_DATA(spu->nid);
+	zone = pgdata->node_zones;
+
+	/* XXX rethink locking here */
+	mutex_lock(&add_spumem_mutex);
+	ret = __add_pages(zone, start_pfn, nr_pages);
+	mutex_unlock(&add_spumem_mutex);
+
+	return ret;
+}
+
+static void __iomem * __init map_spe_prop(struct spu *spu,
+		struct device_node *n, const char *name)
 {
 	struct address_prop {
 		unsigned long address;
@@ -530,6 +572,8 @@ static void __iomem * __init map_spe_prop(struct device_node *n,
 
 	void *p;
 	int proplen;
+	void* ret = NULL;
+	int err = 0;
 
 	p = get_property(n, name, &proplen);
 	if (proplen != sizeof (struct address_prop))
@@ -537,7 +581,14 @@ static void __iomem * __init map_spe_prop(struct device_node *n,
 
 	prop = p;
 
-	return ioremap(prop->address, prop->len);
+	err = cell_spuprop_present(spu, n, name);
+	if (err && (err != -EEXIST))
+		goto out;
+
+	ret = ioremap(prop->address, prop->len);
+
+ out:
+	return ret;
 }
 
 static void spu_unmap(struct spu *spu)
@@ -548,44 +599,45 @@ static void spu_unmap(struct spu *spu)
 	iounmap((u8 __iomem *)spu->local_store);
 }
 
-static int __init spu_map_device(struct spu *spu, struct device_node *spe)
+static int __init spu_map_device(struct spu *spu, struct device_node *node)
 {
 	char *prop;
 	int ret;
 
 	ret = -ENODEV;
-	prop = get_property(spe, "isrc", NULL);
+	prop = get_property(node, "isrc", NULL);
 	if (!prop)
 		goto out;
 	spu->isrc = *(unsigned int *)prop;
 
-	spu->name = get_property(spe, "name", NULL);
+	spu->name = get_property(node, "name", NULL);
 	if (!spu->name)
 		goto out;
 
-	prop = get_property(spe, "local-store", NULL);
+	prop = get_property(node, "local-store", NULL);
 	if (!prop)
 		goto out;
 	spu->local_store_phys = *(unsigned long *)prop;
 
 	/* we use local store as ram, not io memory */
-	spu->local_store = (void __force *)map_spe_prop(spe, "local-store");
+	spu->local_store = (void __force *)
+		map_spe_prop(spu, node, "local-store");
 	if (!spu->local_store)
 		goto out;
 
-	prop = get_property(spe, "problem", NULL);
+	prop = get_property(node, "problem", NULL);
 	if (!prop)
 		goto out_unmap;
 	spu->problem_phys = *(unsigned long *)prop;
 
-	spu->problem= map_spe_prop(spe, "problem");
+	spu->problem= map_spe_prop(spu, node, "problem");
 	if (!spu->problem)
 		goto out_unmap;
 
-	spu->priv1= map_spe_prop(spe, "priv1");
+	spu->priv1= map_spe_prop(spu, node, "priv1");
 	/* priv1 is not available on a hypervisor */
 
-	spu->priv2= map_spe_prop(spe, "priv2");
+	spu->priv2= map_spe_prop(spu, node, "priv2");
 	if (!spu->priv2)
 		goto out_unmap;
 	ret = 0;
@@ -597,17 +649,6 @@ out:
 	return ret;
 }
 
-static int __init find_spu_node_id(struct device_node *spe)
-{
-	unsigned int *id;
-	struct device_node *cpu;
-
-	cpu = spe->parent->parent;
-	id = (unsigned int *)get_property(cpu, "node-id", NULL);
-
-	return id ? *id : 0;
-}
-
 static int __init create_spu(struct device_node *spe)
 {
 	struct spu *spu;
@@ -624,6 +665,10 @@ static int __init create_spu(struct device_node *spe)
 		goto out_free;
 
 	spu->node = find_spu_node_id(spe);
+	spu->nid = of_node_to_nid(spe);
+	if (spu->nid == -1)
+		spu->nid = 0;
+
 	spu->stop_code = 0;
 	spu->slb_replace = 0;
 	spu->mm = NULL;
diff --git a/arch/powerpc/platforms/pseries/eeh_event.c b/arch/powerpc/platforms/pseries/eeh_event.c
index a0b39640a00..8f2d12935b9 100644
--- a/arch/powerpc/platforms/pseries/eeh_event.c
+++ b/arch/powerpc/platforms/pseries/eeh_event.c
@@ -124,7 +124,15 @@ int eeh_send_failure_event (struct device_node *dn,
 {
 	unsigned long flags;
 	struct eeh_event *event;
+	char *location;
 
+	if (!mem_init_done) {
+		printk(KERN_ERR "EEH: event during early boot not handled\n");
+		location = (char *) get_property(dn, "ibm,loc-code", NULL);
+		printk(KERN_ERR "EEH: device node = %s\n", dn->full_name);
+		printk(KERN_ERR "EEH: PCI location = %s\n", location);
+		return 1;
+	}
 	event = kmalloc(sizeof(*event), GFP_ATOMIC);
 	if (event == NULL) {
 		printk (KERN_ERR "EEH: out of memory, event not handled\n");