Merge branch 'linux-2.6'

16 files changed, 151 insertions, 90 deletions

diff --git a/arch/powerpc/platforms/52xx/mpc52xx_common.c b/arch/powerpc/platforms/52xx/mpc52xx_common.c
index 9aa4425d80b..4d5fd1dbd40 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_common.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_common.c
@@ -199,6 +199,7 @@ int mpc52xx_set_psc_clkdiv(int psc_id, int clkdiv)
 
 	return 0;
 }
+EXPORT_SYMBOL(mpc52xx_set_psc_clkdiv);
 
 /**
  * mpc52xx_restart: ppc_md->restart hook for mpc5200 using the watchdog timer
diff --git a/arch/powerpc/platforms/83xx/mpc837x_mds.c b/arch/powerpc/platforms/83xx/mpc837x_mds.c
index 8a9c2697360..64d17b0d645 100644
--- a/arch/powerpc/platforms/83xx/mpc837x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c
@@ -39,12 +39,9 @@ static int mpc837xmds_usb_cfg(void)
 	if (ret)
 		return ret;
 	/* Map BCSR area */
-	np = of_find_node_by_name(NULL, "bcsr");
+	np = of_find_compatible_node(NULL, NULL, "fsl,mpc837xmds-bcsr");
 	if (np) {
-		struct resource res;
-
-		of_address_to_resource(np, 0, &res);
-		bcsr_regs = ioremap(res.start, res.end - res.start + 1);
+		bcsr_regs = of_iomap(np, 0);
 		of_node_put(np);
 	}
 	if (!bcsr_regs)
@@ -96,6 +93,7 @@ static void __init mpc837x_mds_setup_arch(void)
 static struct of_device_id mpc837x_ids[] = {
 	{ .type = "soc", },
 	{ .compatible = "soc", },
+	{ .compatible = "simple-bus", },
 	{},
 };
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 0afd2259554..a578b966ecb 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -22,7 +22,6 @@ config PPC_83xx
 	select FSL_SOC
 	select MPC83xx
 	select IPIC
-	select FSL_EMB_PERFMON
 
 config PPC_86xx
 	bool "Freescale 86xx"
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 73d81ce14b6..0c3face0ddb 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -113,7 +113,12 @@ config FSL_BOOKE
 	default y
 
 config FSL_EMB_PERFMON
-	bool
+	bool "Freescale Embedded Perfmon"
+	depends on E500 || PPC_83xx
+	help
+	  This is the Performance Monitor support found on the e500 core
+	  and some e300 cores (c3 and c4).  Select this only if your
+	  core supports the Embedded Performance Monitor APU
 
 config PTE_64BIT
 	bool
diff --git a/arch/powerpc/platforms/cell/iommu.c b/arch/powerpc/platforms/cell/iommu.c
index 61381586895..d6a732503ea 100644
--- a/arch/powerpc/platforms/cell/iommu.c
+++ b/arch/powerpc/platforms/cell/iommu.c
@@ -113,7 +113,7 @@
 
 /* IOMMU sizing */
 #define IO_SEGMENT_SHIFT	28
-#define IO_PAGENO_BITS		(IO_SEGMENT_SHIFT - IOMMU_PAGE_SHIFT)
+#define IO_PAGENO_BITS(shift)	(IO_SEGMENT_SHIFT - (shift))
 
 /* The high bit needs to be set on every DMA address */
 #define SPIDER_DMA_OFFSET	0x80000000ul
@@ -123,7 +123,6 @@ struct iommu_window {
 	struct cbe_iommu *iommu;
 	unsigned long offset;
 	unsigned long size;
-	unsigned long pte_offset;
 	unsigned int ioid;
 	struct iommu_table table;
 };
@@ -200,7 +199,7 @@ static void tce_build_cell(struct iommu_table *tbl, long index, long npages,
 		(window->ioid & IOPTE_IOID_Mask);
 #endif
 
-	io_pte = (unsigned long *)tbl->it_base + (index - window->pte_offset);
+	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
 	for (i = 0; i < npages; i++, uaddr += IOMMU_PAGE_SIZE)
 		io_pte[i] = base_pte | (__pa(uaddr) & IOPTE_RPN_Mask);
@@ -232,7 +231,7 @@ static void tce_free_cell(struct iommu_table *tbl, long index, long npages)
 		| (window->ioid & IOPTE_IOID_Mask);
 #endif
 
-	io_pte = (unsigned long *)tbl->it_base + (index - window->pte_offset);
+	io_pte = (unsigned long *)tbl->it_base + (index - tbl->it_offset);
 
 	for (i = 0; i < npages; i++)
 		io_pte[i] = pte;
@@ -307,76 +306,84 @@ static int cell_iommu_find_ioc(int nid, unsigned long *base)
 	return -ENODEV;
 }
 
-static void cell_iommu_setup_page_tables(struct cbe_iommu *iommu,
+static void cell_iommu_setup_stab(struct cbe_iommu *iommu,
 				unsigned long dbase, unsigned long dsize,
 				unsigned long fbase, unsigned long fsize)
 {
 	struct page *page;
-	int i;
-	unsigned long reg, segments, pages_per_segment, ptab_size, stab_size,
-		      n_pte_pages, base;
-
-	base = dbase;
-	if (fsize != 0)
-		base = min(fbase, dbase);
+	unsigned long segments, stab_size;
 
 	segments = max(dbase + dsize, fbase + fsize) >> IO_SEGMENT_SHIFT;
-	pages_per_segment = 1ull << IO_PAGENO_BITS;
 
-	pr_debug("%s: iommu[%d]: segments: %lu, pages per segment: %lu\n",
-			__FUNCTION__, iommu->nid, segments, pages_per_segment);
+	pr_debug("%s: iommu[%d]: segments: %lu\n",
+			__FUNCTION__, iommu->nid, segments);
 
 	/* set up the segment table */
 	stab_size = segments * sizeof(unsigned long);
 	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(stab_size));
 	BUG_ON(!page);
 	iommu->stab = page_address(page);
-	clear_page(iommu->stab);
+	memset(iommu->stab, 0, stab_size);
+}
+
+static unsigned long *cell_iommu_alloc_ptab(struct cbe_iommu *iommu,
+		unsigned long base, unsigned long size, unsigned long gap_base,
+		unsigned long gap_size, unsigned long page_shift)
+{
+	struct page *page;
+	int i;
+	unsigned long reg, segments, pages_per_segment, ptab_size,
+		      n_pte_pages, start_seg, *ptab;
+
+	start_seg = base >> IO_SEGMENT_SHIFT;
+	segments  = size >> IO_SEGMENT_SHIFT;
+	pages_per_segment = 1ull << IO_PAGENO_BITS(page_shift);
+	/* PTEs for each segment must start on a 4K bounday */
+	pages_per_segment = max(pages_per_segment,
+				(1 << 12) / sizeof(unsigned long));
 
-	/* ... and the page tables. Since these are contiguous, we can treat
-	 * the page tables as one array of ptes, like pSeries does.
-	 */
 	ptab_size = segments * pages_per_segment * sizeof(unsigned long);
 	pr_debug("%s: iommu[%d]: ptab_size: %lu, order: %d\n", __FUNCTION__,
 			iommu->nid, ptab_size, get_order(ptab_size));
 	page = alloc_pages_node(iommu->nid, GFP_KERNEL, get_order(ptab_size));
 	BUG_ON(!page);
 
-	iommu->ptab = page_address(page);
-	memset(iommu->ptab, 0, ptab_size);
+	ptab = page_address(page);
+	memset(ptab, 0, ptab_size);
 
-	/* allocate a bogus page for the end of each mapping */
-	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
-	BUG_ON(!page);
-	iommu->pad_page = page_address(page);
-	clear_page(iommu->pad_page);
-
-	/* number of pages needed for a page table */
-	n_pte_pages = (pages_per_segment *
-		       sizeof(unsigned long)) >> IOMMU_PAGE_SHIFT;
+	/* number of 4K pages needed for a page table */
+	n_pte_pages = (pages_per_segment * sizeof(unsigned long)) >> 12;
 
 	pr_debug("%s: iommu[%d]: stab at %p, ptab at %p, n_pte_pages: %lu\n",
-			__FUNCTION__, iommu->nid, iommu->stab, iommu->ptab,
+			__FUNCTION__, iommu->nid, iommu->stab, ptab,
 			n_pte_pages);
 
 	/* initialise the STEs */
 	reg = IOSTE_V | ((n_pte_pages - 1) << 5);
 
-	if (IOMMU_PAGE_SIZE == 0x1000)
-		reg |= IOSTE_PS_4K;
-	else if (IOMMU_PAGE_SIZE == 0x10000)
-		reg |= IOSTE_PS_64K;
-	else {
-		extern void __unknown_page_size_error(void);
-		__unknown_page_size_error();
+	switch (page_shift) {
+	case 12: reg |= IOSTE_PS_4K;  break;
+	case 16: reg |= IOSTE_PS_64K; break;
+	case 20: reg |= IOSTE_PS_1M;  break;
+	case 24: reg |= IOSTE_PS_16M; break;
+	default: BUG();
 	}
 
+	gap_base = gap_base >> IO_SEGMENT_SHIFT;
+	gap_size = gap_size >> IO_SEGMENT_SHIFT;
+
 	pr_debug("Setting up IOMMU stab:\n");
-	for (i = base >> IO_SEGMENT_SHIFT; i < segments; i++) {
-		iommu->stab[i] = reg |
-			(__pa(iommu->ptab) + n_pte_pages * IOMMU_PAGE_SIZE * i);
+	for (i = start_seg; i < (start_seg + segments); i++) {
+		if (i >= gap_base && i < (gap_base + gap_size)) {
+			pr_debug("\toverlap at %d, skipping\n", i);
+			continue;
+		}
+		iommu->stab[i] = reg | (__pa(ptab) + (n_pte_pages << 12) *
+					(i - start_seg));
 		pr_debug("\t[%d] 0x%016lx\n", i, iommu->stab[i]);
 	}
+
+	return ptab;
 }
 
 static void cell_iommu_enable_hardware(struct cbe_iommu *iommu)
@@ -423,7 +430,9 @@ static void cell_iommu_enable_hardware(struct cbe_iommu *iommu)
 static void cell_iommu_setup_hardware(struct cbe_iommu *iommu,
 	unsigned long base, unsigned long size)
 {
-	cell_iommu_setup_page_tables(iommu, base, size, 0, 0);
+	cell_iommu_setup_stab(iommu, base, size, 0, 0);
+	iommu->ptab = cell_iommu_alloc_ptab(iommu, base, size, 0, 0,
+					    IOMMU_PAGE_SHIFT);
 	cell_iommu_enable_hardware(iommu);
 }
 
@@ -464,6 +473,7 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 			unsigned long pte_offset)
 {
 	struct iommu_window *window;
+	struct page *page;
 	u32 ioid;
 
 	ioid = cell_iommu_get_ioid(np);
@@ -475,13 +485,11 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	window->size = size;
 	window->ioid = ioid;
 	window->iommu = iommu;
-	window->pte_offset = pte_offset;
 
 	window->table.it_blocksize = 16;
 	window->table.it_base = (unsigned long)iommu->ptab;
 	window->table.it_index = iommu->nid;
-	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) +
-		window->pte_offset;
+	window->table.it_offset = (offset >> IOMMU_PAGE_SHIFT) + pte_offset;
 	window->table.it_size = size >> IOMMU_PAGE_SHIFT;
 
 	iommu_init_table(&window->table, iommu->nid);
@@ -504,6 +512,11 @@ cell_iommu_setup_window(struct cbe_iommu *iommu, struct device_node *np,
 	 * This code also assumes that we have a window that starts at 0,
 	 * which is the case on all spider based blades.
 	 */
+	page = alloc_pages_node(iommu->nid, GFP_KERNEL, 0);
+	BUG_ON(!page);
+	iommu->pad_page = page_address(page);
+	clear_page(iommu->pad_page);
+
 	__set_bit(0, window->table.it_map);
 	tce_build_cell(&window->table, window->table.it_offset, 1,
 		       (unsigned long)iommu->pad_page, DMA_TO_DEVICE);
@@ -549,7 +562,7 @@ static void cell_dma_dev_setup_iommu(struct device *dev)
 	archdata->dma_data = &window->table;
 }
 
-static void cell_dma_dev_setup_static(struct device *dev);
+static void cell_dma_dev_setup_fixed(struct device *dev);
 
 static void cell_dma_dev_setup(struct device *dev)
 {
@@ -557,7 +570,7 @@ static void cell_dma_dev_setup(struct device *dev)
 
 	/* Order is important here, these are not mutually exclusive */
 	if (get_dma_ops(dev) == &dma_iommu_fixed_ops)
-		cell_dma_dev_setup_static(dev);
+		cell_dma_dev_setup_fixed(dev);
 	else if (get_pci_dma_ops() == &dma_iommu_ops)
 		cell_dma_dev_setup_iommu(dev);
 	else if (get_pci_dma_ops() == &dma_direct_ops)
@@ -858,7 +871,7 @@ static int dma_set_mask_and_switch(struct device *dev, u64 dma_mask)
 	return 0;
 }
 
-static void cell_dma_dev_setup_static(struct device *dev)
+static void cell_dma_dev_setup_fixed(struct device *dev)
 {
 	struct dev_archdata *archdata = &dev->archdata;
 	u64 addr;
@@ -869,35 +882,45 @@ static void cell_dma_dev_setup_static(struct device *dev)
 	dev_dbg(dev, "iommu: fixed addr = %lx\n", addr);
 }
 
+static void insert_16M_pte(unsigned long addr, unsigned long *ptab,
+			   unsigned long base_pte)
+{
+	unsigned long segment, offset;
+
+	segment = addr >> IO_SEGMENT_SHIFT;
+	offset = (addr >> 24) - (segment << IO_PAGENO_BITS(24));
+	ptab = ptab + (segment * (1 << 12) / sizeof(unsigned long));
+
+	pr_debug("iommu: addr %lx ptab %p segment %lx offset %lx\n",
+		  addr, ptab, segment, offset);
+
+	ptab[offset] = base_pte | (__pa(addr) & IOPTE_RPN_Mask);
+}
+
 static void cell_iommu_setup_fixed_ptab(struct cbe_iommu *iommu,
 	struct device_node *np, unsigned long dbase, unsigned long dsize,
 	unsigned long fbase, unsigned long fsize)
 {
-	unsigned long base_pte, uaddr, *io_pte;
-	int i;
+	unsigned long base_pte, uaddr, ioaddr, *ptab;
 
-	dma_iommu_fixed_base = fbase;
+	ptab = cell_iommu_alloc_ptab(iommu, fbase, fsize, dbase, dsize, 24);
 
-	/* convert from bytes into page table indices */
-	dbase = dbase >> IOMMU_PAGE_SHIFT;
-	dsize = dsize >> IOMMU_PAGE_SHIFT;
-	fbase = fbase >> IOMMU_PAGE_SHIFT;
-	fsize = fsize >> IOMMU_PAGE_SHIFT;
+	dma_iommu_fixed_base = fbase;
 
 	pr_debug("iommu: mapping 0x%lx pages from 0x%lx\n", fsize, fbase);
 
-	io_pte = iommu->ptab;
 	base_pte = IOPTE_PP_W | IOPTE_PP_R | IOPTE_M | IOPTE_SO_RW
 		    | (cell_iommu_get_ioid(np) & IOPTE_IOID_Mask);
 
-	uaddr = 0;
-	for (i = fbase; i < fbase + fsize; i++, uaddr += IOMMU_PAGE_SIZE) {
+	for (uaddr = 0; uaddr < fsize; uaddr += (1 << 24)) {
 		/* Don't touch the dynamic region */
-		if (i >= dbase && i < (dbase + dsize)) {
-			pr_debug("iommu: static/dynamic overlap, skipping\n");
+		ioaddr = uaddr + fbase;
+		if (ioaddr >= dbase && ioaddr < (dbase + dsize)) {
+			pr_debug("iommu: fixed/dynamic overlap, skipping\n");
 			continue;
 		}
-		io_pte[i] = base_pte | (__pa(uaddr) & IOPTE_RPN_Mask);
+
+		insert_16M_pte(uaddr, ptab, base_pte);
 	}
 
 	mb();
@@ -995,7 +1018,9 @@ static int __init cell_iommu_fixed_mapping_init(void)
 			"fixed window 0x%lx-0x%lx\n", iommu->nid, dbase,
 			 dbase + dsize, fbase, fbase + fsize);
 
-		cell_iommu_setup_page_tables(iommu, dbase, dsize, fbase, fsize);
+		cell_iommu_setup_stab(iommu, dbase, dsize, fbase, fsize);
+		iommu->ptab = cell_iommu_alloc_ptab(iommu, dbase, dsize, 0, 0,
+						    IOMMU_PAGE_SHIFT);
 		cell_iommu_setup_fixed_ptab(iommu, np, dbase, dsize,
 					     fbase, fsize);
 		cell_iommu_enable_hardware(iommu);
diff --git a/arch/powerpc/platforms/cell/setup.c b/arch/powerpc/platforms/cell/setup.c
index a7f609b3b87..dda34650cb0 100644
--- a/arch/powerpc/platforms/cell/setup.c
+++ b/arch/powerpc/platforms/cell/setup.c
@@ -149,6 +149,11 @@ static void __init cell_init_irq(void)
 	mpic_init_IRQ();
 }
 
+static void __init cell_set_dabrx(void)
+{
+	mtspr(SPRN_DABRX, DABRX_KERNEL | DABRX_USER);
+}
+
 static void __init cell_setup_arch(void)
 {
 #ifdef CONFIG_SPU_BASE
@@ -158,6 +163,8 @@ static void __init cell_setup_arch(void)
 
 	cbe_regs_init();
 
+	cell_set_dabrx();
+
 #ifdef CONFIG_CBE_RAS
 	cbe_ras_init();
 #endif
diff --git a/arch/powerpc/platforms/cell/spu_base.c b/arch/powerpc/platforms/cell/spu_base.c
index 87eb07f94c5..712001f6b7d 100644
--- a/arch/powerpc/platforms/cell/spu_base.c
+++ b/arch/powerpc/platforms/cell/spu_base.c
@@ -81,9 +81,12 @@ struct spu_slb {
 void spu_invalidate_slbs(struct spu *spu)
 {
 	struct spu_priv2 __iomem *priv2 = spu->priv2;
+	unsigned long flags;
 
+	spin_lock_irqsave(&spu->register_lock, flags);
 	if (spu_mfc_sr1_get(spu) & MFC_STATE1_RELOCATE_MASK)
 		out_be64(&priv2->slb_invalidate_all_W, 0UL);
+	spin_unlock_irqrestore(&spu->register_lock, flags);
 }
 EXPORT_SYMBOL_GPL(spu_invalidate_slbs);
 
@@ -148,7 +151,11 @@ static inline void spu_load_slb(struct spu *spu, int slbe, struct spu_slb *slb)
 			__func__, slbe, slb->vsid, slb->esid);
 
 	out_be64(&priv2->slb_index_W, slbe);
+	/* set invalid before writing vsid */
+	out_be64(&priv2->slb_esid_RW, 0);
+	/* now it's safe to write the vsid */
 	out_be64(&priv2->slb_vsid_RW, slb->vsid);
+	/* setting the new esid makes the entry valid again */
 	out_be64(&priv2->slb_esid_RW, slb->esid);
 }
 
@@ -290,9 +297,11 @@ void spu_setup_kernel_slbs(struct spu *spu, struct spu_lscsa *lscsa,
 		nr_slbs++;
 	}
 
+	spin_lock_irq(&spu->register_lock);
 	/* Add the set of SLBs */
 	for (i = 0; i < nr_slbs; i++)
 		spu_load_slb(spu, i, &slbs[i]);
+	spin_unlock_irq(&spu->register_lock);
 }
 EXPORT_SYMBOL_GPL(spu_setup_kernel_slbs);
 
@@ -337,13 +346,14 @@ spu_irq_class_1(int irq, void *data)
 	if (stat & CLASS1_STORAGE_FAULT_INTR)
 		spu_mfc_dsisr_set(spu, 0ul);
 	spu_int_stat_clear(spu, 1, stat);
-	spin_unlock(&spu->register_lock);
-	pr_debug("%s: %lx %lx %lx %lx\n", __FUNCTION__, mask, stat,
-			dar, dsisr);
 
 	if (stat & CLASS1_SEGMENT_FAULT_INTR)
 		__spu_trap_data_seg(spu, dar);
 
+	spin_unlock(&spu->register_lock);
+	pr_debug("%s: %lx %lx %lx %lx\n", __FUNCTION__, mask, stat,
+			dar, dsisr);
+
 	if (stat & CLASS1_STORAGE_FAULT_INTR)
 		__spu_trap_data_map(spu, dar, dsisr);
 
diff --git a/arch/powerpc/platforms/cell/spufs/context.c b/arch/powerpc/platforms/cell/spufs/context.c
index 133995ed5cc..0ad83aeb70b 100644
--- a/arch/powerpc/platforms/cell/spufs/context.c
+++ b/arch/powerpc/platforms/cell/spufs/context.c
@@ -109,13 +109,12 @@ void spu_forget(struct spu_context *ctx)
 
 	/*
 	 * This is basically an open-coded spu_acquire_saved, except that
-	 * we don't acquire the state mutex interruptible.
+	 * we don't acquire the state mutex interruptible, and we don't
+	 * want this context to be rescheduled on release.
 	 */
 	mutex_lock(&ctx->state_mutex);
-	if (ctx->state != SPU_STATE_SAVED) {
-		set_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags);
+	if (ctx->state != SPU_STATE_SAVED)
 		spu_deactivate(ctx);
-	}
 
 	mm = ctx->owner;
 	ctx->owner = NULL;
@@ -171,7 +170,8 @@ void spu_release_saved(struct spu_context *ctx)
 {
 	BUG_ON(ctx->state != SPU_STATE_SAVED);
 
-	if (test_and_clear_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags))
+	if (test_and_clear_bit(SPU_SCHED_WAS_ACTIVE, &ctx->sched_flags) &&
+			test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 		spu_activate(ctx, 0);
 
 	spu_release(ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c
index c66c3756970..f7a7e8635fb 100644
--- a/arch/powerpc/platforms/cell/spufs/file.c
+++ b/arch/powerpc/platforms/cell/spufs/file.c
@@ -367,6 +367,13 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 		return NOPFN_SIGBUS;
 
 	/*
+	 * Because we release the mmap_sem, the context may be destroyed while
+	 * we're in spu_wait. Grab an extra reference so it isn't destroyed
+	 * in the meantime.
+	 */
+	get_spu_context(ctx);
+
+	/*
 	 * We have to wait for context to be loaded before we have
 	 * pages to hand out to the user, but we don't want to wait
 	 * with the mmap_sem held.
@@ -375,7 +382,7 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 	 * hanged.
 	 */
 	if (spu_acquire(ctx))
-		return NOPFN_REFAULT;
+		goto refault;
 
 	if (ctx->state == SPU_STATE_SAVED) {
 		up_read(&current->mm->mmap_sem);
@@ -391,6 +398,9 @@ static unsigned long spufs_ps_nopfn(struct vm_area_struct *vma,
 
 	if (!ret)
 		spu_release(ctx);
+
+refault:
+	put_spu_context(ctx);
 	return NOPFN_REFAULT;
 }
 
diff --git a/arch/powerpc/platforms/cell/spufs/run.c b/arch/powerpc/platforms/cell/spufs/run.c
index 6221968c2a3..cac69e11677 100644
--- a/arch/powerpc/platforms/cell/spufs/run.c
+++ b/arch/powerpc/platforms/cell/spufs/run.c
@@ -220,6 +220,7 @@ static int spu_run_init(struct spu_context *ctx, u32 *npc)
 		}
 	}
 
+	set_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
 	return 0;
 }
 
@@ -234,7 +235,7 @@ static int spu_run_fini(struct spu_context *ctx, u32 *npc,
 	*npc = ctx->ops->npc_read(ctx);
 
 	spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
-	ctx->policy = SCHED_IDLE;
+	clear_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags);
 	spu_release(ctx);
 
 	if (signal_pending(current))
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 3a5972117de..00528ef84ad 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -246,7 +246,7 @@ static void spu_bind_context(struct spu *spu, struct spu_context *ctx)
 	spu_switch_notify(spu, ctx);
 	ctx->state = SPU_STATE_RUNNABLE;
 
-	spuctx_switch_state(ctx, SPU_UTIL_IDLE_LOADED);
+	spuctx_switch_state(ctx, SPU_UTIL_USER);
 }
 
 /*
@@ -867,7 +867,7 @@ static noinline void spusched_tick(struct spu_context *ctx)
 	if (ctx->policy == SCHED_FIFO)
 		goto out;
 
-	if (--ctx->time_slice && ctx->policy != SCHED_IDLE)
+	if (--ctx->time_slice && test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 		goto out;
 
 	spu = ctx->spu;
@@ -877,7 +877,7 @@ static noinline void spusched_tick(struct spu_context *ctx)
 	new = grab_runnable_context(ctx->prio + 1, spu->node);
 	if (new) {
 		spu_unschedule(spu, ctx);
-		if (ctx->policy != SCHED_IDLE)
+		if (test_bit(SPU_SCHED_SPU_RUN, &ctx->sched_flags))
 			spu_add_to_rq(ctx);
 	} else {
 		spu_context_nospu_trace(spusched_tick__newslice, ctx);
diff --git a/arch/powerpc/platforms/cell/spufs/spufs.h b/arch/powerpc/platforms/cell/spufs/spufs.h
index 2c2fe3c07d7..cdc515182f8 100644
--- a/arch/powerpc/platforms/cell/spufs/spufs.h
+++ b/arch/powerpc/platforms/cell/spufs/spufs.h
@@ -44,6 +44,7 @@ struct spu_gang;
 enum {
 	SPU_SCHED_NOTIFY_ACTIVE,
 	SPU_SCHED_WAS_ACTIVE,	/* was active upon spu_acquire_saved()  */
+	SPU_SCHED_SPU_RUN,	/* context is within spu_run */
 };
 
 struct spu_context {
diff --git a/arch/powerpc/platforms/cell/spufs/sputrace.c b/arch/powerpc/platforms/cell/spufs/sputrace.c
index 01974f7776e..79aa773f3c9 100644
--- a/arch/powerpc/platforms/cell/spufs/sputrace.c
+++ b/arch/powerpc/platforms/cell/spufs/sputrace.c
@@ -58,12 +58,12 @@ static int sputrace_sprint(char *tbuf, int n)
 		ktime_to_timespec(ktime_sub(t->tstamp, sputrace_start));
 
 	return snprintf(tbuf, n,
-		"[%lu.%09lu] %d: %s (thread = %d, spu = %d)\n",
+		"[%lu.%09lu] %d: %s (ctxthread = %d, spu = %d)\n",
 		(unsigned long) tv.tv_sec,
 		(unsigned long) tv.tv_nsec,
-		t->owner_tid,
-		t->name,
 		t->curr_tid,
+		t->name,
+		t->owner_tid,
 		t->number);
 }
 
@@ -188,6 +188,7 @@ struct spu_probe spu_probes[] = {
 	{ "spufs_ps_nopfn__insert", "%p %p", spu_context_event },
 	{ "spu_acquire_saved__enter", "%p", spu_context_nospu_event },
 	{ "destroy_spu_context__enter", "%p", spu_context_nospu_event },
+	{ "spufs_stop_callback__enter", "%p %p", spu_context_event },
 };
 
 static int __init sputrace_init(void)
diff --git a/arch/powerpc/platforms/cell/spufs/switch.c b/arch/powerpc/platforms/cell/spufs/switch.c
index 6f5886c7b1f..e9dc7a55d1b 100644
--- a/arch/powerpc/platforms/cell/spufs/switch.c
+++ b/arch/powerpc/platforms/cell/spufs/switch.c
@@ -34,6 +34,7 @@
 
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/hardirq.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -117,6 +118,8 @@ static inline void disable_interrupts(struct spu_state *csa, struct spu *spu)
 	 *     Write INT_MASK_class1 with value of 0.
 	 *     Save INT_Mask_class2 in CSA.
 	 *     Write INT_MASK_class2 with value of 0.
+	 *     Synchronize all three interrupts to be sure
+	 *     we no longer execute a handler on another CPU.
 	 */
 	spin_lock_irq(&spu->register_lock);
 	if (csa) {
@@ -129,6 +132,9 @@ static inline void disable_interrupts(struct spu_state *csa, struct spu *spu)
 	spu_int_mask_set(spu, 2, 0ul);
 	eieio();
 	spin_unlock_irq(&spu->register_lock);
+	synchronize_irq(spu->irqs[0]);
+	synchronize_irq(spu->irqs[1]);
+	synchronize_irq(spu->irqs[2]);
 }
 
 static inline void set_watchdog_timer(struct spu_state *csa, struct spu *spu)
diff --git a/arch/powerpc/platforms/celleb/beat.h b/arch/powerpc/platforms/celleb/beat.h
index b2e292df13c..ac82ac35b99 100644
--- a/arch/powerpc/platforms/celleb/beat.h
+++ b/arch/powerpc/platforms/celleb/beat.h
@@ -21,9 +21,6 @@
 #ifndef _CELLEB_BEAT_H
 #define _CELLEB_BEAT_H
 
-#define DABRX_KERNEL		(1UL<<1)
-#define DABRX_USER		(1UL<<0)
-
 int64_t beat_get_term_char(uint64_t,uint64_t*,uint64_t*,uint64_t*);
 int64_t beat_put_term_char(uint64_t,uint64_t,uint64_t,uint64_t);
 int64_t beat_repository_encode(int, const char *, uint64_t[4]);
diff --git a/arch/powerpc/platforms/powermac/pic.c b/arch/powerpc/platforms/powermac/pic.c
index 40736400ef8..829b8b02527 100644
--- a/arch/powerpc/platforms/powermac/pic.c
+++ b/arch/powerpc/platforms/powermac/pic.c
@@ -618,9 +618,9 @@ static int pmacpic_find_viaint(void)
 	if (np == NULL)
 		goto not_found;
 	viaint = irq_of_parse_and_map(np, 0);;
-#endif /* CONFIG_ADB_PMU */
 
 not_found:
+#endif /* CONFIG_ADB_PMU */
 	return viaint;
 }