Merge git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

* git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc:
  [POWERPC] cell: fix bugs found by sparse
  [POWERPC] spiderpic: enable new style devtree support
  [POWERPC] Update cell_defconfig
  [POWERPC] spufs: add infrastructure for finding elf objects
  [POWERPC] spufs: support new OF device tree format
  [POWERPC] spufs: add support for read/write on cntl
  [POWERPC] spufs: remove support for ancient firmware
  [POWERPC] spufs: make mailbox functions handle multiple elements
  [POWERPC] spufs: use correct pg_prot for mapping SPU local store
  [POWERPC] spufs: Add infrastructure needed for gang scheduling
  [POWERPC] spufs: implement error event delivery to user space
  [POWERPC] spufs: fix context switch during page fault
  [POWERPC] spufs: scheduler support for NUMA.
  [POWERPC] spufs: cell spu problem state mapping updates

17 files changed, 1017 insertions, 496 deletions

diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 6fd9e7acec2..892d5dd3254 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.18-rc6
-# Sun Sep 10 10:20:32 2006
+# Linux kernel version: 2.6.18
+# Wed Oct  4 15:30:50 2006
 #
 CONFIG_PPC64=y
 CONFIG_64BIT=y
@@ -22,6 +22,7 @@ CONFIG_ARCH_MAY_HAVE_PC_FDC=y
 CONFIG_PPC_OF=y
 CONFIG_PPC_UDBG_16550=y
 # CONFIG_GENERIC_TBSYNC is not set
+CONFIG_AUDIT_ARCH=y
 # CONFIG_DEFAULT_UIMAGE is not set
 
 #
@@ -52,10 +53,11 @@ CONFIG_LOCALVERSION=""
 CONFIG_LOCALVERSION_AUTO=y
 CONFIG_SWAP=y
 CONFIG_SYSVIPC=y
+# CONFIG_IPC_NS is not set
 # CONFIG_POSIX_MQUEUE is not set
 # CONFIG_BSD_PROCESS_ACCT is not set
 # CONFIG_TASKSTATS is not set
-CONFIG_SYSCTL=y
+# CONFIG_UTS_NS is not set
 # CONFIG_AUDIT is not set
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
@@ -63,7 +65,9 @@ CONFIG_CPUSETS=y
 # CONFIG_RELAY is not set
 CONFIG_INITRAMFS_SOURCE=""
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
 # CONFIG_EMBEDDED is not set
+# CONFIG_SYSCTL_SYSCALL is not set
 CONFIG_KALLSYMS=y
 # CONFIG_KALLSYMS_ALL is not set
 # CONFIG_KALLSYMS_EXTRA_PASS is not set
@@ -72,12 +76,12 @@ CONFIG_PRINTK=y
 CONFIG_BUG=y
 CONFIG_ELF_CORE=y
 CONFIG_BASE_FULL=y
-CONFIG_RT_MUTEXES=y
 CONFIG_FUTEX=y
 CONFIG_EPOLL=y
 CONFIG_SHMEM=y
 CONFIG_SLAB=y
 CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_RT_MUTEXES=y
 # CONFIG_TINY_SHMEM is not set
 CONFIG_BASE_SMALL=0
 # CONFIG_SLOB is not set
@@ -96,6 +100,7 @@ CONFIG_STOP_MACHINE=y
 #
 # Block layer
 #
+CONFIG_BLOCK=y
 # CONFIG_BLK_DEV_IO_TRACE is not set
 
 #
@@ -115,12 +120,13 @@ CONFIG_DEFAULT_IOSCHED="anticipatory"
 # Platform support
 #
 CONFIG_PPC_MULTIPLATFORM=y
-# CONFIG_PPC_ISERIES is not set
 # CONFIG_EMBEDDED6xx is not set
 # CONFIG_APUS is not set
 # CONFIG_PPC_PSERIES is not set
+# CONFIG_PPC_ISERIES is not set
 # CONFIG_PPC_PMAC is not set
 # CONFIG_PPC_MAPLE is not set
+# CONFIG_PPC_PASEMI is not set
 CONFIG_PPC_CELL=y
 CONFIG_PPC_CELL_NATIVE=y
 CONFIG_PPC_IBM_CELL_BLADE=y
@@ -142,7 +148,6 @@ CONFIG_MMIO_NVRAM=y
 #
 CONFIG_SPU_FS=m
 CONFIG_SPU_BASE=y
-CONFIG_SPUFS_MMAP=y
 CONFIG_CBE_RAS=y
 
 #
@@ -158,7 +163,7 @@ CONFIG_PREEMPT_NONE=y
 CONFIG_PREEMPT_BKL=y
 CONFIG_BINFMT_ELF=y
 CONFIG_BINFMT_MISC=m
-CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_FORCE_MAX_ZONEORDER=9
 # CONFIG_IOMMU_VMERGE is not set
 CONFIG_ARCH_ENABLE_MEMORY_HOTPLUG=y
 CONFIG_KEXEC=y
@@ -168,6 +173,7 @@ CONFIG_NUMA=y
 CONFIG_NODES_SHIFT=4
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_SPARSEMEM_ENABLE=y
+CONFIG_ARCH_POPULATES_NODE_MAP=y
 CONFIG_SELECT_MEMORY_MODEL=y
 # CONFIG_FLATMEM_MANUAL is not set
 # CONFIG_DISCONTIGMEM_MANUAL is not set
@@ -178,12 +184,12 @@ CONFIG_HAVE_MEMORY_PRESENT=y
 # CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPARSEMEM_EXTREME=y
 CONFIG_MEMORY_HOTPLUG=y
+CONFIG_MEMORY_HOTPLUG_SPARSE=y
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_MIGRATION=y
 CONFIG_RESOURCES_64BIT=y
-CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID=y
 CONFIG_ARCH_MEMORY_PROBE=y
-# CONFIG_PPC_64K_PAGES is not set
+CONFIG_PPC_64K_PAGES=y
 CONFIG_SCHED_SMT=y
 CONFIG_PROC_DEVICETREE=y
 # CONFIG_CMDLINE_BOOL is not set
@@ -201,6 +207,7 @@ CONFIG_GENERIC_ISA_DMA=y
 CONFIG_PCI=y
 CONFIG_PCI_DOMAINS=y
 CONFIG_PCIEPORTBUS=y
+# CONFIG_PCI_MULTITHREAD_PROBE is not set
 # CONFIG_PCI_DEBUG is not set
 
 #
@@ -228,6 +235,7 @@ CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
+# CONFIG_XFRM_SUB_POLICY is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -249,7 +257,8 @@ CONFIG_INET_XFRM_MODE_TUNNEL=y
 CONFIG_INET_DIAG=y
 CONFIG_INET_TCP_DIAG=y
 # CONFIG_TCP_CONG_ADVANCED is not set
-CONFIG_TCP_CONG_BIC=y
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
 
 #
 # IP: Virtual Server Configuration
@@ -261,11 +270,15 @@ CONFIG_IPV6=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
 CONFIG_INET6_IPCOMP=m
+# CONFIG_IPV6_MIP6 is not set
 CONFIG_INET6_XFRM_TUNNEL=m
 CONFIG_INET6_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_TRANSPORT=y
 CONFIG_INET6_XFRM_MODE_TUNNEL=y
+# CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION is not set
 CONFIG_IPV6_TUNNEL=m
+# CONFIG_IPV6_SUBTREES is not set
+# CONFIG_IPV6_MULTIPLE_TABLES is not set
 # CONFIG_NETWORK_SECMARK is not set
 CONFIG_NETFILTER=y
 # CONFIG_NETFILTER_DEBUG is not set
@@ -322,7 +335,6 @@ CONFIG_IP_NF_QUEUE=m
 # CONFIG_ATALK is not set
 # CONFIG_X25 is not set
 # CONFIG_LAPB is not set
-# CONFIG_NET_DIVERT is not set
 # CONFIG_ECONET is not set
 # CONFIG_WAN_ROUTER is not set
 
@@ -434,6 +446,7 @@ CONFIG_BLK_DEV_AEC62XX=y
 # CONFIG_BLK_DEV_CS5530 is not set
 # CONFIG_BLK_DEV_HPT34X is not set
 # CONFIG_BLK_DEV_HPT366 is not set
+# CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
 # CONFIG_BLK_DEV_PIIX is not set
 # CONFIG_BLK_DEV_IT821X is not set
@@ -456,6 +469,12 @@ CONFIG_IDEDMA_AUTO=y
 #
 # CONFIG_RAID_ATTRS is not set
 # CONFIG_SCSI is not set
+# CONFIG_SCSI_NETLINK is not set
+
+#
+# Serial ATA (prod) and Parallel ATA (experimental) drivers
+#
+# CONFIG_ATA is not set
 
 #
 # Multi-device support (RAID and LVM)
@@ -470,6 +489,7 @@ CONFIG_MD_RAID1=m
 # CONFIG_MD_MULTIPATH is not set
 # CONFIG_MD_FAULTY is not set
 CONFIG_BLK_DEV_DM=m
+# CONFIG_DM_DEBUG is not set
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
@@ -504,7 +524,7 @@ CONFIG_NETDEVICES=y
 # CONFIG_DUMMY is not set
 CONFIG_BONDING=y
 # CONFIG_EQUALIZER is not set
-# CONFIG_TUN is not set
+CONFIG_TUN=y
 
 #
 # ARCnet devices
@@ -552,7 +572,7 @@ CONFIG_SKGE=m
 # CONFIG_TIGON3 is not set
 # CONFIG_BNX2 is not set
 CONFIG_SPIDER_NET=m
-# CONFIG_MV643XX_ETH is not set
+# CONFIG_QLA3XXX is not set
 
 #
 # Ethernet (10000 Mbit)
@@ -599,6 +619,7 @@ CONFIG_SPIDER_NET=m
 # Input device support
 #
 CONFIG_INPUT=y
+# CONFIG_INPUT_FF_MEMLESS is not set
 
 #
 # Userland interfaces
@@ -865,6 +886,7 @@ CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_INFINIBAND_ADDR_TRANS=y
 CONFIG_INFINIBAND_MTHCA=m
 CONFIG_INFINIBAND_MTHCA_DEBUG=y
+# CONFIG_INFINIBAND_AMSO1100 is not set
 CONFIG_INFINIBAND_IPOIB=m
 CONFIG_INFINIBAND_IPOIB_DEBUG=y
 CONFIG_INFINIBAND_IPOIB_DEBUG_DATA=y
@@ -916,7 +938,7 @@ CONFIG_INOTIFY_USER=y
 # CONFIG_QUOTA is not set
 CONFIG_DNOTIFY=y
 # CONFIG_AUTOFS_FS is not set
-# CONFIG_AUTOFS4_FS is not set
+CONFIG_AUTOFS4_FS=m
 # CONFIG_FUSE_FS is not set
 
 #
@@ -943,8 +965,10 @@ CONFIG_FAT_DEFAULT_IOCHARSET="iso8859-1"
 #
 CONFIG_PROC_FS=y
 CONFIG_PROC_KCORE=y
+CONFIG_PROC_SYSCTL=y
 CONFIG_SYSFS=y
 CONFIG_TMPFS=y
+# CONFIG_TMPFS_POSIX_ACL is not set
 CONFIG_HUGETLBFS=y
 CONFIG_HUGETLB_PAGE=y
 CONFIG_RAMFS=y
@@ -1084,6 +1108,7 @@ CONFIG_PLIST=y
 # Kernel hacking
 #
 # CONFIG_PRINTK_TIME is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_MAGIC_SYSRQ=y
 # CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_KERNEL=y
@@ -1102,6 +1127,7 @@ CONFIG_DEBUG_SPINLOCK_SLEEP=y
 # CONFIG_DEBUG_INFO is not set
 CONFIG_DEBUG_FS=y
 # CONFIG_DEBUG_VM is not set
+# CONFIG_DEBUG_LIST is not set
 # CONFIG_FORCED_INLINING is not set
 # CONFIG_RCU_TORTURE_TEST is not set
 # CONFIG_DEBUG_STACKOVERFLOW is not set
@@ -1123,6 +1149,10 @@ CONFIG_IRQSTACKS=y
 # Cryptographic options
 #
 CONFIG_CRYPTO=y
+CONFIG_CRYPTO_ALGAPI=y
+CONFIG_CRYPTO_BLKCIPHER=m
+CONFIG_CRYPTO_HASH=y
+# CONFIG_CRYPTO_MANAGER is not set
 CONFIG_CRYPTO_HMAC=y
 # CONFIG_CRYPTO_NULL is not set
 # CONFIG_CRYPTO_MD4 is not set
@@ -1132,6 +1162,8 @@ CONFIG_CRYPTO_SHA1=m
 # CONFIG_CRYPTO_SHA512 is not set
 # CONFIG_CRYPTO_WP512 is not set
 # CONFIG_CRYPTO_TGR192 is not set
+CONFIG_CRYPTO_ECB=m
+CONFIG_CRYPTO_CBC=m
 CONFIG_CRYPTO_DES=m
 # CONFIG_CRYPTO_BLOWFISH is not set
 # CONFIG_CRYPTO_TWOFISH is not set
diff --git a/arch/powerpc/platforms/cell/Kconfig b/arch/powerpc/platforms/cell/Kconfig
index 0c8c7b6ab89..3e430b489bb 100644
--- a/arch/powerpc/platforms/cell/Kconfig
+++ b/arch/powerpc/platforms/cell/Kconfig
@@ -16,11 +16,6 @@ config SPU_BASE
 	bool
 	default n
 
-config SPUFS_MMAP
-	bool
-	depends on SPU_FS && SPARSEMEM
-	default y
-
 config CBE_RAS
 	bool "RAS features for bare metal Cell BE"
 	default y
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index 6cc59e0b458..8533f13a5ed 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -101,7 +101,7 @@ static void iic_ioexc_eoi(unsigned int irq)
 static void iic_ioexc_cascade(unsigned int irq, struct irq_desc *desc,
 			    struct pt_regs *regs)
 {
-	struct cbe_iic_regs *node_iic = desc->handler_data;
+	struct cbe_iic_regs __iomem *node_iic = (void __iomem *)desc->handler_data;
 	unsigned int base = (irq & 0xffffff00) | IIC_IRQ_TYPE_IOEXC;
 	unsigned long bits, ack;
 	int cascade;
@@ -320,7 +320,7 @@ static int __init setup_iic(void)
 	struct device_node *dn;
 	struct resource r0, r1;
 	unsigned int node, cascade, found = 0;
-	struct cbe_iic_regs *node_iic;
+	struct cbe_iic_regs __iomem *node_iic;
 	const u32 *np;
 
 	for (dn = NULL;
@@ -357,7 +357,11 @@ static int __init setup_iic(void)
 		cascade = irq_create_mapping(iic_host, cascade);
 		if (cascade == NO_IRQ)
 			continue;
-		set_irq_data(cascade, node_iic);
+		/*
+		 * irq_data is a generic pointer that gets passed back
+		 * to us later, so the forced cast is fine.
+		 */
+		set_irq_data(cascade, (void __force *)node_iic);
 		set_irq_chained_handler(cascade , iic_ioexc_cascade);
 		out_be64(&node_iic->iic_ir,
 			 (1 << 12)		/* priority */ |
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index d2b20eba5b8..aca4c3db0dd 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -345,8 +345,8 @@ static int cell_map_iommu_hardcoded(int num_nodes)
 
 	/* node 0 */
 	iommu = &cell_iommus[0];
-	iommu->mapped_base = ioremap(0x20000511000, 0x1000);
-	iommu->mapped_mmio_base = ioremap(0x20000510000, 0x1000);
+	iommu->mapped_base = ioremap(0x20000511000ul, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x20000510000ul, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
@@ -358,8 +358,8 @@ static int cell_map_iommu_hardcoded(int num_nodes)
 
 	/* node 1 */
 	iommu = &cell_iommus[1];
-	iommu->mapped_base = ioremap(0x30000511000, 0x1000);
-	iommu->mapped_mmio_base = ioremap(0x30000510000, 0x1000);
+	iommu->mapped_base = ioremap(0x30000511000ul, 0x1000);
+	iommu->mapped_mmio_base = ioremap(0x30000510000ul, 0x1000);
 
 	enable_mapping(iommu->mapped_base, iommu->mapped_mmio_base);
 
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 608b1ebc56b..b0e95d594c5 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -244,7 +244,6 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	int imaplen, intsize, unit;
 	struct device_node *iic;
 
-#if 0 /* Enable that when we have a way to retreive the node as well */
 	/* First, we check wether we have a real "interrupts" in the device
 	 * tree in case the device-tree is ever fixed
 	 */
@@ -252,9 +251,8 @@ static unsigned int __init spider_find_cascade_and_node(struct spider_pic *pic)
 	if (of_irq_map_one(pic->of_node, 0, &oirq) == 0) {
 		virq = irq_create_of_mapping(oirq.controller, oirq.specifier,
 					     oirq.size);
-		goto bail;
+		return virq;
 	}
-#endif
 
 	/* Now do the horrible hacks */
 	tmp = get_property(pic->of_node, "#interrupt-cells", NULL);
@@ -369,7 +367,7 @@ void __init spider_init_IRQ(void)
 		} else if (device_is_compatible(dn, "sti,platform-spider-pic")
 			   && (chip < 2)) {
 			static long hard_coded_pics[] =
-				{ 0x24000008000, 0x34000008000 };
+				{ 0x24000008000ul, 0x34000008000ul};
 			r.start = hard_coded_pics[chip];
 		} else
 			continue;
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index f78680346e5..ac5f12662db 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -25,11 +25,13 @@
 #include <linux/interrupt.h>
 #include <linux/list.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <linux/poll.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/wait.h>
 
+#include <asm/firmware.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <linux/mutex.h>
@@ -46,21 +48,21 @@ EXPORT_SYMBOL_GPL(spu_priv1_ops);
 static int __spu_trap_invalid_dma(struct spu *spu)
 {
 	pr_debug("%s\n", __FUNCTION__);
-	force_sig(SIGBUS, /* info, */ current);
+	spu->dma_callback(spu, SPE_EVENT_INVALID_DMA);
 	return 0;
 }
 
 static int __spu_trap_dma_align(struct spu *spu)
 {
 	pr_debug("%s\n", __FUNCTION__);
-	force_sig(SIGBUS, /* info, */ current);
+	spu->dma_callback(spu, SPE_EVENT_DMA_ALIGNMENT);
 	return 0;
 }
 
 static int __spu_trap_error(struct spu *spu)
 {
 	pr_debug("%s\n", __FUNCTION__);
-	force_sig(SIGILL, /* info, */ current);
+	spu->dma_callback(spu, SPE_EVENT_SPE_ERROR);
 	return 0;
 }
 
@@ -317,7 +319,7 @@ static void spu_free_irqs(struct spu *spu)
 		free_irq(spu->irqs[2], spu);
 }
 
-static LIST_HEAD(spu_list);
+static struct list_head spu_list[MAX_NUMNODES];
 static DEFINE_MUTEX(spu_mutex);
 
 static void spu_init_channels(struct spu *spu)
@@ -354,32 +356,42 @@ static void spu_init_channels(struct spu *spu)
 	}
 }
 
-struct spu *spu_alloc(void)
+struct spu *spu_alloc_node(int node)
 {
-	struct spu *spu;
+	struct spu *spu = NULL;
 
 	mutex_lock(&spu_mutex);
-	if (!list_empty(&spu_list)) {
-		spu = list_entry(spu_list.next, struct spu, list);
+	if (!list_empty(&spu_list[node])) {
+		spu = list_entry(spu_list[node].next, struct spu, list);
 		list_del_init(&spu->list);
-		pr_debug("Got SPU %x %d\n", spu->isrc, spu->number);
-	} else {
-		pr_debug("No SPU left\n");
-		spu = NULL;
+		pr_debug("Got SPU %x %d %d\n",
+			 spu->isrc, spu->number, spu->node);
+		spu_init_channels(spu);
 	}
 	mutex_unlock(&spu_mutex);
 
-	if (spu)
-		spu_init_channels(spu);
+	return spu;
+}
+EXPORT_SYMBOL_GPL(spu_alloc_node);
+
+struct spu *spu_alloc(void)
+{
+	struct spu *spu = NULL;
+	int node;
+
+	for (node = 0; node < MAX_NUMNODES; node++) {
+		spu = spu_alloc_node(node);
+		if (spu)
+			break;
+	}
 
 	return spu;
 }
-EXPORT_SYMBOL_GPL(spu_alloc);
 
 void spu_free(struct spu *spu)
 {
 	mutex_lock(&spu_mutex);
-	list_add_tail(&spu->list, &spu_list);
+	list_add_tail(&spu->list, &spu_list[spu->node]);
 	mutex_unlock(&spu_mutex);
 }
 EXPORT_SYMBOL_GPL(spu_free);
@@ -566,7 +578,7 @@ static void spu_unmap(struct spu *spu)
 }
 
 /* This function shall be abstracted for HV platforms */
-static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
+static int __init spu_map_interrupts_old(struct spu *spu, struct device_node *np)
 {
 	unsigned int isrc;
 	const u32 *tmp;
@@ -590,7 +602,7 @@ static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
 	return spu->irqs[2] == NO_IRQ ? -EINVAL : 0;
 }
 
-static int __init spu_map_device(struct spu *spu, struct device_node *node)
+static int __init spu_map_device_old(struct spu *spu, struct device_node *node)
 {
 	const char *prop;
 	int ret;
@@ -635,6 +647,88 @@ out:
 	return ret;
 }
 
+static int __init spu_map_interrupts(struct spu *spu, struct device_node *np)
+{
+	struct of_irq oirq;
+	int ret;
+	int i;
+
+	for (i=0; i < 3; i++) {
+		ret = of_irq_map_one(np, i, &oirq);
+		if (ret)
+			goto err;
+
+		ret = -EINVAL;
+		spu->irqs[i] = irq_create_of_mapping(oirq.controller,
+					oirq.specifier, oirq.size);
+		if (spu->irqs[i] == NO_IRQ)
+			goto err;
+	}
+	return 0;
+
+err:
+	pr_debug("failed to map irq %x for spu %s\n", *oirq.specifier, spu->name);
+	for (; i >= 0; i--) {
+		if (spu->irqs[i] != NO_IRQ)
+			irq_dispose_mapping(spu->irqs[i]);
+	}
+	return ret;
+}
+
+static int spu_map_resource(struct device_node *node, int nr,
+		void __iomem** virt, unsigned long *phys)
+{
+	struct resource resource = { };
+	int ret;
+
+	ret = of_address_to_resource(node, 0, &resource);
+	if (ret)
+		goto out;
+
+	if (phys)
+		*phys = resource.start;
+	*virt = ioremap(resource.start, resource.end - resource.start);
+	if (!*virt)
+		ret = -EINVAL;
+
+out:
+	return ret;
+}
+
+static int __init spu_map_device(struct spu *spu, struct device_node *node)
+{
+	int ret = -ENODEV;
+	spu->name = get_property(node, "name", NULL);
+	if (!spu->name)
+		goto out;
+
+	ret = spu_map_resource(node, 0, (void __iomem**)&spu->local_store,
+					&spu->local_store_phys);
+	if (ret)
+		goto out;
+	ret = spu_map_resource(node, 1, (void __iomem**)&spu->problem,
+					&spu->problem_phys);
+	if (ret)
+		goto out_unmap;
+	ret = spu_map_resource(node, 2, (void __iomem**)&spu->priv2,
+					NULL);
+	if (ret)
+		goto out_unmap;
+
+	if (!firmware_has_feature(FW_FEATURE_LPAR))
+		ret = spu_map_resource(node, 3, (void __iomem**)&spu->priv1,
+					NULL);
+	if (ret)
+		goto out_unmap;
+	return 0;
+
+out_unmap:
+	spu_unmap(spu);
+out:
+	pr_debug("failed to map spe %s: %d\n", spu->name, ret);
+	return ret;
+}
+
 struct sysdev_class spu_sysdev_class = {
 	set_kset_name("spu")
 };
@@ -688,6 +782,9 @@ static int __init create_spu(struct device_node *spe)
 		goto out;
 
 	ret = spu_map_device(spu, spe);
+	/* try old method */
+	if (ret)
+		ret = spu_map_device_old(spu, spe);
 	if (ret)
 		goto out_free;
 
@@ -697,6 +794,8 @@ static int __init create_spu(struct device_node *spe)
 		spu->nid = 0;
 	ret = spu_map_interrupts(spu, spe);
 	if (ret)
+		ret = spu_map_interrupts_old(spu, spe);
+	if (ret)
 		goto out_unmap;
 	spin_lock_init(&spu->register_lock);
 	spu_mfc_sdr_set(spu, mfspr(SPRN_SDR1));
@@ -706,13 +805,13 @@ static int __init create_spu(struct device_node *spe)
 	spu->number = number++;
 	ret = spu_request_irqs(spu);
 	if (ret)
-		goto out_unmap;
+		goto out_unlock;
 
 	ret = spu_create_sysdev(spu);
 	if (ret)
 		goto out_free_irqs;
 
-	list_add(&spu->list, &spu_list);
+	list_add(&spu->list, &spu_list[spu->node]);
 	mutex_unlock(&spu_mutex);
 
 	pr_debug(KERN_DEBUG "Using SPE %s %02x %p %p %p %p %d\n",
@@ -722,9 +821,9 @@ static int __init create_spu(struct device_node *spe)
 
 out_free_irqs:
 	spu_free_irqs(spu);
-
-out_unmap:
+out_unlock:
 	mutex_unlock(&spu_mutex);
+out_unmap:
 	spu_unmap(spu);
 out_free:
 	kfree(spu);
@@ -745,9 +844,13 @@ static void destroy_spu(struct spu *spu)
 static void cleanup_spu_base(void)
 {
 	struct spu *spu, *tmp;
+	int node;
+
 	mutex_lock(&spu_mutex);
-	list_for_each_entry_safe(spu, tmp, &spu_list, list)
-		destroy_spu(spu);
+	for (node = 0; node < MAX_NUMNODES; node++) {
+		list_for_each_entry_safe(spu, tmp, &spu_list[node], list)
+			destroy_spu(spu);
+	}
 	mutex_unlock(&spu_mutex);
 	sysdev_class_unregister(&spu_sysdev_class);
 }
@@ -756,13 +859,16 @@ module_exit(cleanup_spu_base);
 static int __init init_spu_base(void)
 {
 	struct device_node *node;
-	int ret;
+	int i, ret;
 
 	/* create sysdev class for spus */
 	ret = sysdev_class_register(&spu_sysdev_class);
 	if (ret)
 		return ret;
 
+	for (i = 0; i < MAX_NUMNODES; i++)
+		INIT_LIST_HEAD(&spu_list[i]);
+
 	ret = -ENODEV;
 	for (node = of_find_node_by_type(NULL, "spe");
 			node; node = of_find_node_by_type(node, "spe")) {
@@ -774,18 +880,6 @@ static int __init init_spu_base(void)
 			break;
 		}
 	}
-	/* in some old firmware versions, the spe is called 'spc', so we
-	   look for that as well */
-	for (node = of_find_node_by_type(NULL, "spc");
-			node; node = of_find_node_by_type(node, "spc")) {
-		ret = create_spu(node);
-		if (ret) {
-			printk(KERN_WARNING "%s: Error initializing %s\n",
-				__FUNCTION__, node->name);
-			cleanup_spu_base();
-			break;
-		}
-	}
 	return ret;
 }
 module_init(init_spu_base);
diff --git a/arch/powerpc/platforms/cell/spufs/Makefile b/arch/powerpc/platforms/cell/spufs/Makefile
index bb5dc634272..ecdfbb35f82 100644
--- a/arch/powerpc/platforms/cell/spufs/Makefile
+++ b/arch/powerpc/platforms/cell/spufs/Makefile
@@ -2,7 +2,7 @@ obj-y += switch.o
 
 obj-$(CONFIG_SPU_FS) += spufs.o
 spufs-y += inode.o file.o context.o syscalls.o
-spufs-y += sched.o backing_ops.o hw_ops.o run.o
+spufs-y += sched.o backing_ops.o hw_ops.o run.o gang.o
 
 # Rules to build switch.o with the help of SPU tool chain
 SPU_CROSS	:= spu-
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 36439c5e9f2..034cf6af53a 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -27,7 +27,7 @@
 #include <asm/spu_csa.h>
 #include "spufs.h"
 
-struct spu_context *alloc_spu_context(void)
+struct spu_context *alloc_spu_context(struct spu_gang *gang)
 {
 	struct spu_context *ctx;
 	ctx = kzalloc(sizeof *ctx, GFP_KERNEL);
@@ -51,6 +51,8 @@ struct spu_context *alloc_spu_context(void)
 	ctx->state = SPU_STATE_SAVED;
 	ctx->ops = &spu_backing_ops;
 	ctx->owner = get_task_mm(current);
+	if (gang)
+		spu_gang_add_ctx(gang, ctx);
 	goto out;
 out_free:
 	kfree(ctx);
@@ -67,6 +69,8 @@ void destroy_spu_context(struct kref *kref)
 	spu_deactivate(ctx);
 	up_write(&ctx->state_sema);
 	spu_fini_csa(&ctx->csa);
+	if (ctx->gang)
+		spu_gang_remove_ctx(ctx->gang, ctx);
 	kfree(ctx);
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index 51fd197ab5d..e0d73004526 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -36,6 +36,8 @@
 
 #include "spufs.h"
 
+#define SPUFS_MMAP_4K (PAGE_SIZE == 0x1000)
+
 
 static int
 spufs_mem_open(struct inode *inode, struct file *file)
@@ -88,7 +90,6 @@ spufs_mem_write(struct file *file, const char __user *buffer,
 	return ret;
 }
 
-#ifdef CONFIG_SPUFS_MMAP
 static struct page *
 spufs_mem_mmap_nopage(struct vm_area_struct *vma,
 		      unsigned long address, int *type)
@@ -101,12 +102,16 @@ spufs_mem_mmap_nopage(struct vm_area_struct *vma,
 
 	spu_acquire(ctx);
 
-	if (ctx->state == SPU_STATE_SAVED)
+	if (ctx->state == SPU_STATE_SAVED) {
+		vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+					& ~(_PAGE_NO_CACHE | _PAGE_GUARDED));
 		page = vmalloc_to_page(ctx->csa.lscsa->ls + offset);
-	else
+	} else {
+		vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
+					| _PAGE_NO_CACHE | _PAGE_GUARDED);
 		page = pfn_to_page((ctx->spu->local_store_phys + offset)
 				   >> PAGE_SHIFT);
-
+	}
 	spu_release(ctx);
 
 	if (type)
@@ -133,22 +138,19 @@ spufs_mem_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_ops = &spufs_mem_mmap_vmops;
 	return 0;
 }
-#endif
 
 static struct file_operations spufs_mem_fops = {
 	.open	 = spufs_mem_open,
 	.read    = spufs_mem_read,
 	.write   = spufs_mem_write,
 	.llseek  = generic_file_llseek,
-#ifdef CONFIG_SPUFS_MMAP
 	.mmap    = spufs_mem_mmap,
-#endif
 };
 
-#ifdef CONFIG_SPUFS_MMAP
 static struct page *spufs_ps_nopage(struct vm_area_struct *vma,
 				    unsigned long address,
-				    int *type, unsigned long ps_offs)
+				    int *type, unsigned long ps_offs,
+				    unsigned long ps_size)
 {
 	struct page *page = NOPAGE_SIGBUS;
 	int fault_type = VM_FAULT_SIGBUS;
@@ -158,7 +160,7 @@ static struct page *spufs_ps_nopage(struct vm_area_struct *vma,
 	int ret;
 
 	offset += vma->vm_pgoff << PAGE_SHIFT;
-	if (offset >= 0x4000)
+	if (offset >= ps_size)
 		goto out;
 
 	ret = spu_acquire_runnable(ctx);
@@ -179,10 +181,11 @@ static struct page *spufs_ps_nopage(struct vm_area_struct *vma,
 	return page;
 }
 
+#if SPUFS_MMAP_4K
 static struct page *spufs_cntl_mmap_nopage(struct vm_area_struct *vma,
 					   unsigned long address, int *type)
 {
-	return spufs_ps_nopage(vma, address, type, 0x4000);
+	return spufs_ps_nopage(vma, address, type, 0x4000, 0x1000);
 }
 
 static struct vm_operations_struct spufs_cntl_mmap_vmops = {
@@ -191,17 +194,12 @@ static struct vm_operations_struct spufs_cntl_mmap_vmops = {
 
 /*
  * mmap support for problem state control area [0x4000 - 0x4fff].
- * Mapping this area requires that the application have CAP_SYS_RAWIO,
- * as these registers require special care when read/writing.
  */
 static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	if (!(vma->vm_flags & VM_SHARED))
 		return -EINVAL;
 
-	if (!capable(CAP_SYS_RAWIO))
-		return -EPERM;
-
 	vma->vm_flags |= VM_RESERVED;
 	vma->vm_page_prot = __pgprot(pgprot_val(vma->vm_page_prot)
 				     | _PAGE_NO_CACHE | _PAGE_GUARDED);
@@ -209,42 +207,48 @@ static int spufs_cntl_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_ops = &spufs_cntl_mmap_vmops;
 	return 0;
 }
-#endif
+#else /* SPUFS_MMAP_4K */
+#define spufs_cntl_mmap NULL
+#endif /* !SPUFS_MMAP_4K */
 
-static int spufs_cntl_open(struct inode *inode, struct file *file)
+static u64 spufs_cntl_get(void *data)
 {
-	struct spufs_inode_info *i = SPUFS_I(inode);
-	struct spu_context *ctx = i->i_ctx;
+	struct spu_context *ctx = data;
+	u64 val;
 
-	file->private_data = ctx;
-	file->f_mapping = inode->i_mapping;
-	ctx->cntl = inode->i_mapping;
-	return 0;
+	spu_acquire(ctx);
+	val = ctx->ops->status_read(ctx);
+	spu_release(ctx);
+
+	return val;
 }
 
-static ssize_t
-spufs_cntl_read(struct file *file, char __user *buffer,
-		size_t size, loff_t *pos)
+static void spufs_cntl_set(void *data, u64 val)
 {
-	/* FIXME: read from spu status */
-	return -EINVAL;
+	struct spu_context *ctx = data;
+
+	spu_acquire(ctx);
+	ctx->ops->runcntl_write(ctx, val);
+	spu_release(ctx);
 }
 
-static ssize_t
-spufs_cntl_write(struct file *file, const char __user *buffer,
-		 size_t size, loff_t *pos)
+static int spufs_cntl_open(struct inode *inode, struct file *file)
 {
-	/* FIXME: write to runctl bit */
-	return -EINVAL;
+	struct spufs_inode_info *i = SPUFS_I(inode);
+	struct spu_context *ctx = i->i_ctx;
+
+	file->private_data = ctx;
+	file->f_mapping = inode->i_mapping;
+	ctx->cntl = inode->i_mapping;
+	return simple_attr_open(inode, file, spufs_cntl_get,
+					spufs_cntl_set, "0x%08lx");
 }
 
 static struct file_operations spufs_cntl_fops = {
 	.open = spufs_cntl_open,
-	.read = spufs_cntl_read,
-	.write = spufs_cntl_write,
-#ifdef CONFIG_SPUFS_MMAP
+	.read = simple_attr_read,
+	.write = simple_attr_write,
 	.mmap = spufs_cntl_mmap,
-#endif
 };
 
 static int
@@ -356,27 +360,54 @@ static int spufs_pipe_open(struct inode *inode, struct file *file)
 	return nonseekable_open(inode, file);
 }
 
+/*
+ * Read as many bytes from the mailbox as possible, until
+ * one of the conditions becomes true:
+ *
+ * - no more data available in the mailbox
+ * - end of the user provided buffer
+ * - end of the mapped area
+ */
 static ssize_t spufs_mbox_read(struct file *file, char __user *buf,
 			size_t len, loff_t *pos)
 {
 	struct spu_context *ctx = file->private_data;
-	u32 mbox_data;
-	int ret;
+	u32 mbox_data, __user *udata;
+	ssize_t count;
 
 	if (len < 4)
 		return -EINVAL;
 
+	if (!access_ok(VERIFY_WRITE, buf, len))
+		return -EFAULT;
+
+	udata = (void __user *)buf;
+
 	spu_acquire(ctx);
-	ret = ctx->ops->mbox_read(ctx, &mbox_data);
+	for (count = 0; count <= len; count += 4, udata++) {
+		int ret;
+		ret = ctx->ops->mbox_read(ctx, &mbox_data);
+		if (ret == 0)
+			break;
+
+		/*
+		 * at the end of the mapped area, we can fault
+		 * but still need to return the data we have
+		 * read successfully so far.
+		 */
+		ret = __put_user(mbox_data, udata);
+		if (ret) {
+			if (!count)
+				count = -EFAULT;
+			break;
+		}
+