Merge branch 'linus' into x86/asm, before applying dependent patch

Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 249 insertions, 419 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index efb00ec75805..e49502acbab4 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -146,6 +146,10 @@ config GENERIC_ISA_DMA
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y if SPARC64
 
+config PGTABLE_LEVELS
+	default 4 if 64BIT
+	default 3
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/sparc/include/asm/iommu_64.h b/arch/sparc/include/asm/iommu_64.h
index 2b9321ab064d..cd0d69fa7592 100644
--- a/arch/sparc/include/asm/iommu_64.h
+++ b/arch/sparc/include/asm/iommu_64.h
@@ -16,6 +16,7 @@
 #define IOPTE_WRITE   0x0000000000000002UL
 
 #define IOMMU_NUM_CTXS	4096
+#include <linux/iommu-common.h>
 
 struct iommu_arena {
 	unsigned long	*map;
@@ -24,11 +25,10 @@ struct iommu_arena {
 };
 
 struct iommu {
+	struct iommu_map_table	tbl;
 	spinlock_t		lock;
-	struct iommu_arena	arena;
-	void			(*flush_all)(struct iommu *);
+	u32			dma_addr_mask;
 	iopte_t			*page_table;
-	u32			page_table_map_base;
 	unsigned long		iommu_control;
 	unsigned long		iommu_tsbbase;
 	unsigned long		iommu_flush;
@@ -40,7 +40,6 @@ struct iommu {
 	unsigned long		dummy_page_pa;
 	unsigned long		ctx_lowest_free;
 	DECLARE_BITMAP(ctx_bitmap, IOMMU_NUM_CTXS);
-	u32			dma_addr_mask;
 };
 
 struct strbuf {
diff --git a/arch/sparc/include/asm/seccomp.h b/arch/sparc/include/asm/seccomp.h
index adca1bce41d4..5ef8826d44f8 100644
--- a/arch/sparc/include/asm/seccomp.h
+++ b/arch/sparc/include/asm/seccomp.h
@@ -1,15 +1,10 @@
 #ifndef _ASM_SECCOMP_H
+#define _ASM_SECCOMP_H
 
 #include <linux/unistd.h>
 
-#define __NR_seccomp_read __NR_read
-#define __NR_seccomp_write __NR_write
-#define __NR_seccomp_exit __NR_exit
-#define __NR_seccomp_sigreturn __NR_rt_sigreturn
-
-#define __NR_seccomp_read_32 __NR_read
-#define __NR_seccomp_write_32 __NR_write
-#define __NR_seccomp_exit_32 __NR_exit
 #define __NR_seccomp_sigreturn_32 __NR_sigreturn
 
+#include <asm-generic/seccomp.h>
+
 #endif /* _ASM_SECCOMP_H */
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index fd7bd0a440ca..229475f0d7ce 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -27,7 +27,6 @@
 struct thread_info {
 	unsigned long		uwinmask;
 	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
 	unsigned long		flags;		/* low level flags */
 	int			cpu;		/* cpu we're on */
 	int			preempt_count;	/* 0 => preemptable,
@@ -35,6 +34,8 @@ struct thread_info {
 	int			softirq_count;
 	int			hardirq_count;
 
+	u32 __unused;
+
 	/* Context switch saved kernel state. */
 	unsigned long ksp;	/* ... ksp __attribute__ ((aligned (8))); */
 	unsigned long kpc;
@@ -56,7 +57,6 @@ struct thread_info {
 {							\
 	.uwinmask	=	0,			\
 	.task		=	&tsk,			\
-	.exec_domain	=	&default_exec_domain,	\
 	.flags		=	0,			\
 	.cpu		=	0,			\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
@@ -85,12 +85,11 @@ register struct thread_info *current_thread_info_reg asm("g6");
  */
 #define TI_UWINMASK	0x00	/* uwinmask */
 #define TI_TASK		0x04
-#define TI_EXECDOMAIN	0x08	/* exec_domain */
-#define TI_FLAGS	0x0c
-#define TI_CPU		0x10
-#define TI_PREEMPT	0x14	/* preempt_count */
-#define TI_SOFTIRQ	0x18	/* softirq_count */
-#define TI_HARDIRQ	0x1c	/* hardirq_count */
+#define TI_FLAGS	0x08
+#define TI_CPU		0x0c
+#define TI_PREEMPT	0x10	/* preempt_count */
+#define TI_SOFTIRQ	0x14	/* softirq_count */
+#define TI_HARDIRQ	0x18	/* hardirq_count */
 #define TI_KSP		0x20	/* ksp */
 #define TI_KPC		0x24	/* kpc (ldd'ed with kpc) */
 #define TI_KPSR		0x28	/* kpsr */
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index ff455164732a..bde59825d06c 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -31,7 +31,6 @@
 #include <asm/types.h>
 
 struct task_struct;
-struct exec_domain;
 
 struct thread_info {
 	/* D$ line 1 */
@@ -44,7 +43,6 @@ struct thread_info {
 	/* D$ line 2 */
 	unsigned long		fault_address;
 	struct pt_regs		*kregs;
-	struct exec_domain	*exec_domain;
 	int			preempt_count;	/* 0 => preemptable, <0 => BUG */
 	__u8			new_child;
 	__u8			current_ds;
@@ -80,18 +78,17 @@ struct thread_info {
 #define TI_KSP		0x00000018
 #define TI_FAULT_ADDR	0x00000020
 #define TI_KREGS	0x00000028
-#define TI_EXEC_DOMAIN	0x00000030
-#define TI_PRE_COUNT	0x00000038
-#define TI_NEW_CHILD	0x0000003c
-#define TI_CURRENT_DS	0x0000003d
-#define TI_CPU		0x0000003e
-#define TI_UTRAPS	0x00000040
-#define TI_REG_WINDOW	0x00000048
-#define TI_RWIN_SPTRS	0x000003c8
-#define TI_GSR		0x00000400
-#define TI_XFSR		0x00000438
-#define TI_KUNA_REGS	0x00000470
-#define TI_KUNA_INSN	0x00000478
+#define TI_PRE_COUNT	0x00000030
+#define TI_NEW_CHILD	0x00000034
+#define TI_CURRENT_DS	0x00000035
+#define TI_CPU		0x00000036
+#define TI_UTRAPS	0x00000038
+#define TI_REG_WINDOW	0x00000040
+#define TI_RWIN_SPTRS	0x000003c0
+#define TI_GSR		0x000003f8
+#define TI_XFSR		0x00000430
+#define TI_KUNA_REGS	0x00000468
+#define TI_KUNA_INSN	0x00000470
 #define TI_FPREGS	0x00000480
 
 /* We embed this in the uppermost byte of thread_info->flags */
@@ -119,7 +116,6 @@ struct thread_info {
 {							\
 	.task		=	&tsk,			\
 	.current_ds	=	ASI_P,			\
-	.exec_domain	=	&default_exec_domain,	\
 	.preempt_count	=	INIT_PREEMPT_COUNT,	\
 }
 
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index bfa4d0c2df42..5320689c06e9 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -13,6 +13,7 @@
 #include <linux/errno.h>
 #include <linux/iommu-helper.h>
 #include <linux/bitmap.h>
+#include <linux/iommu-common.h>
 
 #ifdef CONFIG_PCI
 #include <linux/pci.h>
@@ -45,8 +46,9 @@
 			       "i" (ASI_PHYS_BYPASS_EC_E))
 
 /* Must be invoked under the IOMMU lock. */
-static void iommu_flushall(struct iommu *iommu)
+static void iommu_flushall(struct iommu_map_table *iommu_map_table)
 {
+	struct iommu *iommu = container_of(iommu_map_table, struct iommu, tbl);
 	if (iommu->iommu_flushinv) {
 		iommu_write(iommu->iommu_flushinv, ~(u64)0);
 	} else {
@@ -87,94 +89,6 @@ static inline void iopte_make_dummy(struct iommu *iommu, iopte_t *iopte)
 	iopte_val(*iopte) = val;
 }
 
-/* Based almost entirely upon the ppc64 iommu allocator.  If you use the 'handle'
- * facility it must all be done in one pass while under the iommu lock.
- *
- * On sun4u platforms, we only flush the IOMMU once every time we've passed
- * over the entire page table doing allocations.  Therefore we only ever advance
- * the hint and cannot backtrack it.
- */
-unsigned long iommu_range_alloc(struct device *dev,
-				struct iommu *iommu,
-				unsigned long npages,
-				unsigned long *handle)
-{
-	unsigned long n, end, start, limit, boundary_size;
-	struct iommu_arena *arena = &iommu->arena;
-	int pass = 0;
-
-	/* This allocator was derived from x86_64's bit string search */
-
-	/* Sanity check */
-	if (unlikely(npages == 0)) {
-		if (printk_ratelimit())
-			WARN_ON(1);
-		return DMA_ERROR_CODE;
-	}
-
-	if (handle && *handle)
-		start = *handle;
-	else
-		start = arena->hint;
-
-	limit = arena->limit;
-
-	/* The case below can happen if we have a small segment appended
-	 * to a large, or when the previous alloc was at the very end of
-	 * the available space. If so, go back to the beginning and flush.
-	 */
-	if (start >= limit) {
-		start = 0;
-		if (iommu->flush_all)
-			iommu->flush_all(iommu);
-	}
-
- again:
-
-	if (dev)
-		boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
-				      1 << IO_PAGE_SHIFT);
-	else
-		boundary_size = ALIGN(1UL << 32, 1 << IO_PAGE_SHIFT);
-
-	n = iommu_area_alloc(arena->map, limit, start, npages,
-			     iommu->page_table_map_base >> IO_PAGE_SHIFT,
-			     boundary_size >> IO_PAGE_SHIFT, 0);
-	if (n == -1) {
-		if (likely(pass < 1)) {
-			/* First failure, rescan from the beginning.  */
-			start = 0;
-			if (iommu->flush_all)
-				iommu->flush_all(iommu);
-			pass++;
-			goto again;
-		} else {
-			/* Second failure, give up */
-			return DMA_ERROR_CODE;
-		}
-	}
-
-	end = n + npages;
-
-	arena->hint = end;
-
-	/* Update handle for SG allocations */
-	if (handle)
-		*handle = end;
-
-	return n;
-}
-
-void iommu_range_free(struct iommu *iommu, dma_addr_t dma_addr, unsigned long npages)
-{
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long entry;
-
-	entry = (dma_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT;
-
-	bitmap_clear(arena->map, entry, npages);
-}
-
 int iommu_table_init(struct iommu *iommu, int tsbsize,
 		     u32 dma_offset, u32 dma_addr_mask,
 		     int numa_node)
@@ -187,22 +101,20 @@ int iommu_table_init(struct iommu *iommu, int tsbsize,
 	/* Setup initial software IOMMU state. */
 	spin_lock_init(&iommu->lock);
 	iommu->ctx_lowest_free = 1;
-	iommu->page_table_map_base = dma_offset;
+	iommu->tbl.table_map_base = dma_offset;
 	iommu->dma_addr_mask = dma_addr_mask;
 
 	/* Allocate and initialize the free area map.  */
 	sz = num_tsb_entries / 8;
 	sz = (sz + 7UL) & ~7UL;
-	iommu->arena.map = kmalloc_node(sz, GFP_KERNEL, numa_node);
-	if (!iommu->arena.map) {
-		printk(KERN_ERR "IOMMU: Error, kmalloc(arena.map) failed.\n");
+	iommu->tbl.map = kmalloc_node(sz, GFP_KERNEL, numa_node);
+	if (!iommu->tbl.map)
 		return -ENOMEM;
-	}
-	memset(iommu->arena.map, 0, sz);
-	iommu->arena.limit = num_tsb_entries;
+	memset(iommu->tbl.map, 0, sz);
 
-	if (tlb_type != hypervisor)
-		iommu->flush_all = iommu_flushall;
+	iommu_tbl_pool_init(&iommu->tbl, num_tsb_entries, IO_PAGE_SHIFT,
+			    (tlb_type != hypervisor ? iommu_flushall : NULL),
+			    false, 1, false);
 
 	/* Allocate and initialize the dummy page which we
 	 * set inactive IO PTEs to point to.
@@ -235,18 +147,20 @@ out_free_dummy_page:
 	iommu->dummy_page = 0UL;
 
 out_free_map:
-	kfree(iommu->arena.map);
-	iommu->arena.map = NULL;
+	kfree(iommu->tbl.map);
+	iommu->tbl.map = NULL;
 
 	return -ENOMEM;
 }
 
-static inline iopte_t *alloc_npages(struct device *dev, struct iommu *iommu,
+static inline iopte_t *alloc_npages(struct device *dev,
+				    struct iommu *iommu,
 				    unsigned long npages)
 {
 	unsigned long entry;
 
-	entry = iommu_range_alloc(dev, iommu, npages, NULL);
+	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+				      (unsigned long)(-1), 0);
 	if (unlikely(entry == DMA_ERROR_CODE))
 		return NULL;
 
@@ -284,7 +198,7 @@ static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
 				   dma_addr_t *dma_addrp, gfp_t gfp,
 				   struct dma_attrs *attrs)
 {
-	unsigned long flags, order, first_page;
+	unsigned long order, first_page;
 	struct iommu *iommu;
 	struct page *page;
 	int npages, nid;
@@ -306,16 +220,14 @@ static void *dma_4u_alloc_coherent(struct device *dev, size_t size,
 
 	iommu = dev->archdata.iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	iopte = alloc_npages(dev, iommu, size >> IO_PAGE_SHIFT);
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	if (unlikely(iopte == NULL)) {
 		free_pages(first_page, order);
 		return NULL;
 	}
 
-	*dma_addrp = (iommu->page_table_map_base +
+	*dma_addrp = (iommu->tbl.table_map_base +
 		      ((iopte - iommu->page_table) << IO_PAGE_SHIFT));
 	ret = (void *) first_page;
 	npages = size >> IO_PAGE_SHIFT;
@@ -336,16 +248,12 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
 				 struct dma_attrs *attrs)
 {
 	struct iommu *iommu;
-	unsigned long flags, order, npages;
+	unsigned long order, npages;
 
 	npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT;
 	iommu = dev->archdata.iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
-
-	iommu_range_free(iommu, dvma, npages);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	iommu_tbl_range_free(&iommu->tbl, dvma, npages, DMA_ERROR_CODE);
 
 	order = get_order(size);
 	if (order < 10)
@@ -375,8 +283,8 @@ static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	base = alloc_npages(dev, iommu, npages);
+	spin_lock_irqsave(&iommu->lock, flags);
 	ctx = 0;
 	if (iommu->iommu_ctxflush)
 		ctx = iommu_alloc_ctx(iommu);
@@ -385,7 +293,7 @@ static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
 	if (unlikely(!base))
 		goto bad;
 
-	bus_addr = (iommu->page_table_map_base +
+	bus_addr = (iommu->tbl.table_map_base +
 		    ((base - iommu->page_table) << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
 	base_paddr = __pa(oaddr & IO_PAGE_MASK);
@@ -496,7 +404,7 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
 	npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 	base = iommu->page_table +
-		((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
+		((bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT);
 	bus_addr &= IO_PAGE_MASK;
 
 	spin_lock_irqsave(&iommu->lock, flags);
@@ -515,11 +423,10 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
 	for (i = 0; i < npages; i++)
 		iopte_make_dummy(iommu, base + i);
 
-	iommu_range_free(iommu, bus_addr, npages);
-
 	iommu_free_ctx(iommu, ctx);
-
 	spin_unlock_irqrestore(&iommu->lock, flags);
+
+	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, DMA_ERROR_CODE);
 }
 
 static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -567,7 +474,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 	max_seg_size = dma_get_max_seg_size(dev);
 	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
-	base_shift = iommu->page_table_map_base >> IO_PAGE_SHIFT;
+	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
 		iopte_t *base;
@@ -581,7 +488,8 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 		/* Allocate iommu entries for that segment */
 		paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s);
 		npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE);
-		entry = iommu_range_alloc(dev, iommu, npages, &handle);
+		entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages,
+					      &handle, (unsigned long)(-1), 0);
 
 		/* Handle failure */
 		if (unlikely(entry == DMA_ERROR_CODE)) {
@@ -594,7 +502,7 @@ static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
 		base = iommu->page_table + entry;
 
 		/* Convert entry to a dma_addr_t */
-		dma_addr = iommu->page_table_map_base +
+		dma_addr = iommu->tbl.table_map_base +
 			(entry << IO_PAGE_SHIFT);
 		dma_addr |= (s->offset & ~IO_PAGE_MASK);
 
@@ -654,15 +562,17 @@ iommu_map_failed:
 			vaddr = s->dma_address & IO_PAGE_MASK;
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IO_PAGE_SIZE);
-			iommu_range_free(iommu, vaddr, npages);
 
-			entry = (vaddr - iommu->page_table_map_base)
+			entry = (vaddr - iommu->tbl.table_map_base)
 				>> IO_PAGE_SHIFT;
 			base = iommu->page_table + entry;
 
 			for (j = 0; j < npages; j++)
 				iopte_make_dummy(iommu, base + j);
 
+			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
+					     DMA_ERROR_CODE);
+
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
 		}
@@ -684,10 +594,11 @@ static unsigned long fetch_sg_ctx(struct iommu *iommu, struct scatterlist *sg)
 	if (iommu->iommu_ctxflush) {
 		iopte_t *base;
 		u32 bus_addr;
+		struct iommu_map_table *tbl = &iommu->tbl;
 
 		bus_addr = sg->dma_address & IO_PAGE_MASK;
 		base = iommu->page_table +
-			((bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
+			((bus_addr - tbl->table_map_base) >> IO_PAGE_SHIFT);
 
 		ctx = (iopte_val(*base) & IOPTE_CONTEXT) >> 47UL;
 	}
@@ -723,9 +634,8 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		if (!len)
 			break;
 		npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE);
-		iommu_range_free(iommu, dma_handle, npages);
 
-		entry = ((dma_handle - iommu->page_table_map_base)
+		entry = ((dma_handle - iommu->tbl.table_map_base)
 			 >> IO_PAGE_SHIFT);
 		base = iommu->page_table + entry;
 
@@ -737,6 +647,8 @@ static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
 		for (i = 0; i < npages; i++)
 			iopte_make_dummy(iommu, base + i);
 
+		iommu_tbl_range_free(&iommu->tbl, dma_handle, npages,
+				     DMA_ERROR_CODE);
 		sg = sg_next(sg);
 	}
 
@@ -770,9 +682,10 @@ static void dma_4u_sync_single_for_cpu(struct device *dev,
 	if (iommu->iommu_ctxflush &&
 	    strbuf->strbuf_ctxflush) {
 		iopte_t *iopte;
+		struct iommu_map_table *tbl = &iommu->tbl;
 
 		iopte = iommu->page_table +
-			((bus_addr - iommu->page_table_map_base)>>IO_PAGE_SHIFT);
+			((bus_addr - tbl->table_map_base)>>IO_PAGE_SHIFT);
 		ctx = (iopte_val(*iopte) & IOPTE_CONTEXT) >> 47UL;
 	}
 
@@ -805,9 +718,10 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
 	if (iommu->iommu_ctxflush &&
 	    strbuf->strbuf_ctxflush) {
 		iopte_t *iopte;
+		struct iommu_map_table *tbl = &iommu->tbl;
 
-		iopte = iommu->page_table +
-			((sglist[0].dma_address - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
+		iopte = iommu->page_table + ((sglist[0].dma_address -
+			tbl->table_map_base) >> IO_PAGE_SHIFT);
 		ctx = (iopte_val(*iopte) & IOPTE_CONTEXT) >> 47UL;
 	}
 
diff --git a/arch/sparc/kernel/iommu_common.h b/arch/sparc/kernel/iommu_common.h
index 1ec0de4156e7..f4be0d724fc6 100644
--- a/arch/sparc/kernel/iommu_common.h
+++ b/arch/sparc/kernel/iommu_common.h
@@ -48,12 +48,4 @@ static inline int is_span_boundary(unsigned long entry,
 	return iommu_is_span_boundary(entry, nr, shift, boundary_size);
 }
 
-unsigned long iommu_range_alloc(struct device *dev,
-				struct iommu *iommu,
-				unsigned long npages,
-				unsigned long *handle);
-void iommu_range_free(struct iommu *iommu,
-		      dma_addr_t dma_addr,
-		      unsigned long npages);
-
 #endif /* _IOMMU_COMMON_H */
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 274a9f59d95c..7d3ca30fcd15 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/bitmap.h>
+#include <linux/iommu-common.h>
 
 #include <asm/hypervisor.h>
 #include <asm/iommu.h>
@@ -27,6 +28,10 @@
 #define DRV_MODULE_VERSION	"1.1"
 #define DRV_MODULE_RELDATE	"July 22, 2008"
 
+#define COOKIE_PGSZ_CODE	0xf000000000000000ULL
+#define COOKIE_PGSZ_CODE_SHIFT	60ULL
+
+
 static char version[] =
 	DRV_MODULE_NAME ".c:v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
 #define LDC_PACKET_SIZE		64
@@ -98,10 +103,10 @@ static const struct ldc_mode_ops stream_ops;
 int ldom_domaining_enabled;
 
 struct ldc_iommu {
-	/* Protects arena alloc/free.  */
+	/* Protects ldc_unmap.  */
 	spinlock_t			lock;
-	struct iommu_arena		arena;
 	struct ldc_mtable_entry		*page_table;
+	struct iommu_map_table		iommu_map_table;
 };
 
 struct ldc_channel {
@@ -998,31 +1003,59 @@ static void free_queue(unsigned long num_entries, struct ldc_packet *q)
 	free_pages((unsigned long)q, order);
 }
 
+static unsigned long ldc_cookie_to_index(u64 cookie, void *arg)
+{
+	u64 szcode = cookie >> COOKIE_PGSZ_CODE_SHIFT;
+	/* struct ldc_iommu *ldc_iommu = (struct ldc_iommu *)arg; */
+
+	cookie &= ~COOKIE_PGSZ_CODE;
+
+	return (cookie >> (13ULL + (szcode * 3ULL)));
+}
+
+static void ldc_demap(struct ldc_iommu *iommu, unsigned long id, u64 cookie,
+		      unsigned long entry, unsigned long npages)
+{
+	struct ldc_mtable_entry *base;
+	unsigned long i, shift;
+
+	shift = (cookie >> COOKIE_PGSZ_CODE_SHIFT) * 3;
+	base = iommu->page_table + entry;
+	for (i = 0; i < npages; i++) {
+		if (base->cookie)
+			sun4v_ldc_revoke(id, cookie + (i << shift),
+					 base->cookie);
+		base->mte = 0;
+	}
+}
+
 /* XXX Make this configurable... XXX */
 #define LDC_IOTABLE_SIZE	(8 * 1024)
 
-static int ldc_iommu_init(struct ldc_channel *lp)
+static int ldc_iommu_init(const char *name, struct ldc_channel *lp)
 {
 	unsigned long sz, num_tsb_entries, tsbsize, order;
-	struct ldc_iommu *iommu = &lp->iommu;
+	struct ldc_iommu *ldc_iommu = &lp->iommu;
+	struct iommu_map_table *iommu = &ldc_iommu->iommu_map_table;
 	struct ldc_mtable_entry *table;
 	unsigned long hv_err;
 	int err;
 
 	num_tsb_entries = LDC_IOTABLE_SIZE;
 	tsbsize = num_tsb_entries * sizeof(struct ldc_mtable_entry);
-
-	spin_lock_init(&iommu->lock);
+	spin_lock_init(&ldc_iommu->lock);
 
 	sz = num_tsb_entries / 8;
 	sz = (sz + 7UL) & ~7UL;
-	iommu->arena.map = kzalloc(sz, GFP_KERNEL);
-	if (!iommu->arena.map) {
+	iommu->map = kzalloc(sz, GFP_KERNEL);
+	if (!iommu->map) {
 		printk(KERN_ERR PFX "Alloc of arena map failed, sz=%lu\n", sz);
 		return -ENOMEM;
 	}
-
-	iommu->arena.limit = num_tsb_entries;
+	iommu_tbl_pool_init(iommu, num_tsb_entries, PAGE_SHIFT,
+			    NULL, false /* no large pool */,
+			    1 /* npools */,
+			    true /* skip span boundary check */);
 
 	order = get_order(tsbsize);
 
@@ -1037,7 +1070,7 @@ static int ldc_iommu_init(struct ldc_channel *lp)
 
 	memset(table, 0, PAGE_SIZE << order);
 
-	iommu->page_table = table;
+	ldc_iommu->page_table = table;
 
 	hv_err = sun4v_ldc_set_map_table(lp->id, __pa(table),
 					 num_tsb_entries);
@@ -1049,31 +1082,32 @@ static int ldc_iommu_init(struct ldc_channel *lp)
 
 out_free_table:
 	free_pages((unsigned long) table, order);
-	iommu->page_table = NULL;
+	ldc_iommu->page_table = NULL;
 
 out_free_map:
-	kfree(iommu->arena.map);
-	iommu->arena.map = NULL;
+	kfree(iommu->map);
+	iommu->map = NULL;
 
 	return err;
 }
 
 static void ldc_iommu_release(struct ldc_channel *lp)
 {
-	struct ldc_iommu *iommu = &lp->iommu;
+	struct ldc_iommu *ldc_iommu = &lp->iommu;
+	struct iommu_map_table *iommu = &ldc_iommu->iommu_map_table;
 	unsigned long num_tsb_entries, tsbsize, order;
 
 	(void) sun4v_ldc_set_map_table(lp->id, 0, 0);
 
-	num_tsb_entries = iommu->arena.limit;
+	num_tsb_entries = iommu->poolsize * iommu->nr_pools;
 	tsbsize = num_tsb_entries * sizeof(struct ldc_mtable_entry);
 	order = get_order(tsbsize);
 
-	free_pages((unsigned long) iommu->page_table, order);
-	iommu->page_table = NULL;
+	free_pages((unsigned long) ldc_iommu->page_table, order);
+	ldc_iommu->page_table = NULL;
 
-	kfree(iommu->arena.map);
-	iommu->arena.map = NULL;
+	kfree(iommu->map);
+	iommu->map = NULL;
 }
 
 struct ldc_channel *ldc_alloc(unsigned long id,
@@ -1140,7 +1174,7 @@ struct ldc_channel *ldc_alloc(unsigned long id,
 
 	lp->id = id;
 
-	err = ldc_iommu_init(lp);
+	err = ldc_iommu_init(name, lp);
 	if (err)
 		goto out_free_ldc;
 
@@ -1885,40 +1919,6 @@ int ldc_read(struct ldc_channel *lp, void *buf, unsigned int size)
 }
 EXPORT_SYMBOL(ldc_read);
 
-static long arena_alloc(struct ldc_iommu *iommu, unsigned long npages)
-{
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long n, start, end, limit;
-	int pass;
-
-	limit = arena->limit;
-	start = arena->hint;
-	pass = 0;
-
-again:
-	n = bitmap_find_next_zero_area(arena->map, limit, start, npages, 0);
-	end = n + npages;
-	if (unlikely(end >= limit)) {
-		if (likely(pass < 1)) {
-			limit = start;
-			start = 0;
-			pass++;
-			goto again;
-		} else {
-			/* Scanned the whole thing, give up. */
-			return -1;
-		}
-	}
-	bitmap_set(arena->map, n, npages);
-
-	arena->hint = end;
-
-	return n;
-}
-
-#define COOKIE_PGSZ_CODE	0xf000000000000000ULL
-#define COOKIE_PGSZ_CODE_SHIFT	60ULL
-
 static u64 pagesize_code(void)
 {
 	switch (PAGE_SIZE) {
@@ -1945,23 +1945,14 @@ static u64 make_cookie(u64 index, u64 pgsz_code, u64 page_offset)
 		page_offset);
 }
 
-static u64 cookie_to_index(u64 cookie, unsigned long *shift)
-{
-	u64 szcode = cookie >> COOKIE_PGSZ_CODE_SHIFT;
-
-	cookie &= ~COOKIE_PGSZ_CODE;
-
-	*shift = szcode * 3;
-
-	return (cookie >> (13ULL + (szcode * 3ULL)));
-}
 
 static struct ldc_mtable_entry *alloc_npages(struct ldc_iommu *iommu,
 					     unsigned long npages)
 {
 	long entry;
 
-	entry = arena_alloc(iommu, npages);
+	entry = iommu_tbl_range_alloc(NULL, &iommu->iommu_map_table,
+				      npages, NULL, (unsigned long)-1, 0);
 	if (unlikely(entry < 0))
 		return NULL;
 
@@ -2090,7 +2081,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 	       struct ldc_trans_cookie *cookies, int ncookies,
 	       unsigned int map_perm)
 {
-	unsigned long i, npages, flags;
+	unsigned long i, npages;
 	struct ldc_mtable_entry *base;
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
@@ -2109,9 +2100,7 @@ int ldc_map_sg(struct ldc_channel *lp,
 
 	iommu = &lp->iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	base = alloc_npages(iommu, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	if (!base)
 		return -ENOMEM;
@@ -2136,7 +2125,7 @@ int ldc_map_single(struct ldc_channel *lp,
 		   struct ldc_trans_cookie *cookies, int ncookies,
 		   unsigned int map_perm)
 {
-	unsigned long npages, pa, flags;
+	unsigned long npages, pa;
 	struct ldc_mtable_entry *base;
 	struct cookie_state state;
 	struct ldc_iommu *iommu;
@@ -2152,9 +2141,7 @@ int ldc_map_single(struct ldc_channel *lp,
 
 	iommu = &lp->iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
 	base = alloc_npages(iommu, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
 
 	if (!base)
 		return -ENOMEM;
@@ -2172,35 +2159,25 @@ int ldc_map_single(struct ldc_channel *lp,
 }
 EXPORT_SYMBOL(ldc_map_single);
 
+
 static void free_npages(unsigned long id, struct ldc_iommu *iommu,
 			u64 cookie, u64 size)
 {
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long i, shift, index, npages;
-	struct ldc_mtable_entry *base;
+	unsigned long npages, entry;
 
 	npages = PAGE_ALIGN(((cookie & ~PAGE_MASK) + size)) >> PAGE_SHIFT;
-	index = cookie_to_index(cookie, &shift);
-	base = iommu->page_table + index;
 
-	BUG_ON(index > arena->limit ||
-	       (index + npages) > arena->limit);
-
-	for (i = 0; i < npages; i++) {
-		if (base->cookie)
-			sun4v_ldc_revoke(id, cookie + (i << shift),
-					 base->cookie);
-		base->mte = 0;
-		__clear_bit(index + i, arena->map);
-	}
+	entry = ldc_cookie_to_index(cookie, iommu);
+	ldc_demap(iommu, id, cookie, entry, npages);
+	iommu_tbl_range_free(&iommu->iommu_map_table, cookie, npages, entry);
 }
 
 void ldc_unmap(struct ldc_channel *lp, struct ldc_trans_cookie *cookies,
 	       int ncookies)
 {
 	struct ldc_iommu *iommu = &lp->iommu;
-	unsigned long flags;
 	int i;
+	unsigned long flags;
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	for (i = 0; i < ncookies; i++) {
@@ -2313,7 +2290,7 @@ void *ldc_alloc_exp_dring(struct ldc_channel *lp, unsigned int len,
 	if (len & (8UL - 1))
 		return ERR_PTR(-EINVAL);
 
-	buf = kzalloc(len, GFP_KERNEL);
+	buf = kzalloc(len, GFP_ATOMIC);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/arch/sparc/kernel/leon_pci.c b/arch/sparc/kernel/leon_pci.c
index 899b7203a4e4..4371f72ff025 100644
--- a/arch/sparc/kernel/leon_pci.c
+++ b/arch/sparc/kernel/leon_pci.c
@@ -34,15 +34,17 @@ void leon_pci_init(struct platform_device *ofdev, struct leon_pci_info *info)
 
 	root_bus = pci_scan_root_bus(&ofdev->dev, 0, info->ops, info,
 				     &resources);
-	if (root_bus) {
-		/* Setup IRQs of all devices using custom routines */
-		pci_fixup_irqs(pci_common_swizzle, info->map_irq);
-
-		/* Assign devices with resources */
-		pci_assign_unassigned_resources();
-	} else {
+	if (!root_bus) {
 		pci_free_resource_list(&resources);
+		return;
 	}
+
+	/* Setup IRQs of all devices using custom routines */
+	pci_fixup_irqs(pci_common_swizzle, info->map_irq);
+
+	/* Assign devices with resources */
+	pci_assign_unassigned_resources();
+	pci_bus_add_devices(root_bus);
 }
 
 void pcibios_fixup_bus(struct pci_bus *pbus)
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index 99632a87e697..26c80e18d7b1 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -130,26 +130,26 @@ static struct mdesc_mem_ops memblock_mdesc_ops = {
 static struct mdesc_handle *mdesc_kmalloc(unsigned int mdesc_size)
 {
 	unsigned int handle_size;
+	struct mdesc_handle *hp;
+	unsigned long addr;
 	void *base;
 
 	handle_size = (sizeof(struct mdesc_handle) -
 		       sizeof(struct mdesc_hdr) +
 		       mdesc_size);
 
+	/*
+	 * Allocation has to succeed because mdesc update would be missed
+	 * and such events are not retransmitted.
+	 */
 	base = kmalloc(handle_size + 15, GFP_KERNEL | __GFP_NOFAIL);
-	if (base) {
-		struct mdesc_handle *hp;
-		unsigned long addr;
-
-		addr = (unsigned long)base;
-		addr = (addr + 15UL) & ~15UL;
-		hp = (struct mdesc_handle *) addr;
+	addr = (unsigned long)base;
+	addr = (addr + 15UL) & ~15UL;
+	hp = (struct mdesc_handle *) addr;
 
-		mdesc_handle_init(hp, handle_size, base);
-		return hp;
-	}
+	mdesc_handle_init(hp, handle_size, base);
 
-	return NULL;
+	return hp;
 }
 
 static void mdesc_kfree(struct mdesc_handle *hp)
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index b36365f49478..6f7251fd2eab 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -674,11 +674,10 @@ struct pci_bus *pci_scan_one_pbm(struct pci_pbm_info *pbm,
 	}
 
 	pci_of_scan_bus(pbm, node, bus);
-	pci_bus_add_devices(bus);
 	pci_bus_register_of_sysfs(bus);
 
 	pci_claim_bus_resources(bus);
-
+	pci_bus_add_devices(bus);
 	return bus;
 }
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 47ddbd496a1e..d2fe57dad433 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -15,6 +15,7 @@
 #include <linux/export.h>
 #include <linux/log2.h>
 #include <linux/of_device.h>
+#include <linux/iommu-common.h>
 
 #include <asm/iommu.h>
 #include <asm/irq.h>
@@ -155,15 +156,13 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 
 	iommu = dev->archdata.iommu;
 
-	spin_lock_irqsave(&iommu->lock, flags);
-	entry = iommu_range_alloc(dev, iommu, npages, NULL);
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == DMA_ERROR_CODE))
 		goto range_alloc_fail;
 
-	*dma_addrp = (iommu->page_table_map_base +
-		      (entry << IO_PAGE_SHIFT));
+	*dma_addrp = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = (void *) first_page;
 	first_page = __pa(first_page);
 
@@ -188,45 +187,46 @@ static void *dma_4v_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 
 iommu_map_fail:
-	/* Interrupts are disabled.  */
-	spin_lock(&iommu->lock);
-	iommu_range_free(iommu, *dma_addrp, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	iommu_tbl_range_free(&iommu->tbl, *dma_addrp, npages, DMA_ERROR_CODE);
 
 range_alloc_fail:
 	free_pages(first_page, order);
 	return NULL;
 }
 
+static void dma_4v_iommu_demap(void *demap_arg, unsigned long entry,
+			       unsigned long npages)
+{
+	u32 devhandle = *(u32 *)demap_arg;
+	unsigned long num, flags;
+
+	local_irq_save(flags);
+	do {
+		num = pci_sun4v_iommu_demap(devhandle,
+					    HV_PCI_TSBID(0, entry),
+					    npages);
+
+		entry += num;
+		npages -= num;
+	} while (npages != 0);
+	local_irq_restore(flags);
+}
+
 static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 				 dma_addr_t dvma, struct dma_attrs *attrs)
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
-	unsigned long flags, order, npages, entry;
+	unsigned long order, npages, entry;
 	u32 devhandle;
 
 	npages = IO_PAGE_ALIGN(size) >> IO_PAGE_SHIFT;
 	iommu = dev->archdata.iommu;
 	pbm = dev->archdata.host_controller;
 	devhandle = pbm->devhandle;
-	entry = ((dvma - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
-
-	spin_lock_irqsave(&iommu->lock, flags);
-
-	iommu_range_free(iommu, dvma, npages);
-
-	do {
-		unsigned long num;
-
-		num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
-					    npages);
-		entry += num;
-		npages -= num;
-	} while (npages != 0);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
-
+	entry = ((dvma - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT);
+	dma_4v_iommu_demap(&devhandle, entry, npages);
+	iommu_tbl_range_free(&iommu->tbl, dvma, npages, DMA_ERROR_CODE);
 	order = get_order(size);
 	if (order < 10)
 		free_pages((unsigned long)cpu, order);
@@ -253,15 +253,13 @@ static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
 	npages = IO_PAGE_ALIGN(oaddr + sz) - (oaddr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 
-	spin_lock_irqsave(&iommu->lock, flags);
-	entry = iommu_range_alloc(dev, iommu, npages, NULL);
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages, NULL,
+				      (unsigned long)(-1), 0);
 
 	if (unlikely(entry == DMA_ERROR_CODE))
 		goto bad;
 
-	bus_addr = (iommu->page_table_map_base +
-		    (entry << IO_PAGE_SHIFT));
+	bus_addr = (iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT));
 	ret = bus_addr | (oaddr & ~IO_PAGE_MASK);
 	base_paddr = __pa(oaddr & IO_PAGE_MASK);
 	prot = HV_PCI_MAP_ATTR_READ;
@@ -290,11 +288,7 @@ bad:
 	return DMA_ERROR_CODE;
 
 iommu_map_fail:
-	/* Interrupts are disabled.  */
-	spin_lock(&iommu->lock);
-	iommu_range_free(iommu, bus_addr, npages);
-	spin_unlock_irqrestore(&iommu->lock, flags);
-
+	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, DMA_ERROR_CODE);
 	return DMA_ERROR_CODE;
 }
 
@@ -304,7 +298,7 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 {
 	struct pci_pbm_info *pbm;
 	struct iommu *iommu;
-	unsigned long flags, npages;
+	unsigned long npages;
 	long entry;
 	u32 devhandle;
 
@@ -321,22 +315,9 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 	npages = IO_PAGE_ALIGN(bus_addr + sz) - (bus_addr & IO_PAGE_MASK);
 	npages >>= IO_PAGE_SHIFT;
 	bus_addr &= IO_PAGE_MASK;
-
-	spin_lock_irqsave(&iommu->lock, flags);
-
-	iommu_range_free(iommu, bus_addr, npages);
-
-	entry = (bus_addr - iommu->page_table_map_base) >> IO_PAGE_SHIFT;
-	do {
-		unsigned long num;
-
-		num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
-					    npages);
-		entry += num;
-		npages -= num;
-	} while (npages != 0);
-
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	entry = (bus_addr - iommu->tbl.table_map_base) >> IO_PAGE_SHIFT;
+	dma_4v_iommu_demap(&devhandle, entry, npages);
+	iommu_tbl_range_free(&iommu->tbl, bus_addr, npages, DMA_ERROR_CODE);
 }
 
 static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
@@ -371,14 +352,14 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	/* Init first segment length for backout at failure */
 	outs->dma_length = 0;
 
-	spin_lock_irqsave(&iommu->lock, flags);
+	local_irq_save(flags);
 
 	iommu_batch_start(dev, prot, ~0UL);
 
 	max_seg_size = dma_get_max_seg_size(dev);
 	seg_boundary_size = ALIGN(dma_get_seg_boundary(dev) + 1,
 				  IO_PAGE_SIZE) >> IO_PAGE_SHIFT;
-	base_shift = iommu->page_table_map_base >> IO_PAGE_SHIFT;
+	base_shift = iommu->tbl.table_map_base >> IO_PAGE_SHIFT;
 	for_each_sg(sglist, s, nelems, i) {
 		unsigned long paddr, npages, entry, out_entry = 0, slen;
 
@@ -391,7 +372,8 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		/* Allocate iommu entries for that segment */
 		paddr = (unsigned long) SG_ENT_PHYS_ADDRESS(s);
 		npages = iommu_num_pages(paddr, slen, IO_PAGE_SIZE);
-		entry = iommu_range_alloc(dev, iommu, npages, &handle);
+		entry = iommu_tbl_range_alloc(dev, &iommu->tbl, npages,
+					      &handle, (unsigned long)(-1), 0);
 
 		/* Handle failure */
 		if (unlikely(entry == DMA_ERROR_CODE)) {
@@ -404,8 +386,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 		iommu_batch_new_entry(entry);
 
 		/* Convert entry to a dma_addr_t */
-		dma_addr = iommu->page_table_map_base +
-			(entry << IO_PAGE_SHIFT);
+		dma_addr = iommu->tbl.table_map_base + (entry << IO_PAGE_SHIFT);
 		dma_addr |= (s->offset & ~IO_PAGE_MASK);
 
 		/* Insert into HW table */
@@ -451,7 +432,7 @@ static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
 	if (unlikely(err < 0L))
 		goto iommu_map_failed;
 
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	local_irq_restore(flags);
 
 	if (outcount < incount) {
 		outs = sg_next(outs);
@@ -469,7 +450,8 @@ iommu_map_failed:
 			vaddr = s->dma_address & IO_PAGE_MASK;
 			npages = iommu_num_pages(s->dma_address, s->dma_length,
 						 IO_PAGE_SIZE);
-			iommu_range_free(iommu, vaddr, npages);
+			iommu_tbl_range_free(&iommu->tbl, vaddr, npages,
+					     DMA_ERROR_CODE);
 			/* XXX demap? XXX */
 			s->dma_address = DMA_ERROR_CODE;
 			s->dma_length = 0;
@@ -477,7 +459,7 @@ iommu_map_failed:
 		if (s == outs)
 			break;
 	}
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	local_irq_restore(flags);
 
 	return 0;
 }
@@ -489,7 +471,7 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	struct pci_pbm_info *pbm;
 	struct scatterlist *sg;
 	struct iommu *iommu;
-	unsigned long flags;
+	unsigned long flags, entry;
 	u32 devhandle;
 
 	BUG_ON(direction == DMA_NONE);
@@ -498,33 +480,27 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	pbm = dev->archdata.host_controller;
 	devhandle = pbm->devhandle;
 	
-	spin_lock_irqsave(&iommu->lock, flags);
+	local_irq_save(flags);
 
 	sg = sglist;
 	while (nelems--) {
 		dma_addr_t dma_handle = sg->dma_address;
 		unsigned int len = sg->dma_length;
-		unsigned long npages, entry;
+		unsigned long npages;
+		struct iommu_map_table *tbl = &iommu->tbl;
+		unsigned long shift = IO_PAGE_SHIFT;
 
 		if (!len)
 			break;
 		npages = iommu_num_pages(dma_handle, len, IO_PAGE_SIZE);
-		iommu_range_free(iommu, dma_handle, npages);
-
-		entry = ((dma_handle - iommu->page_table_map_base) >> IO_PAGE_SHIFT);
-		while (npages) {
-			unsigned long num;
-
-			num = pci_sun4v_iommu_demap(devhandle, HV_PCI_TSBID(0, entry),
-						    npages);
-			entry += num;
-			npages -= num;
-		}
-
+		entry = ((dma_handle - tbl->table_map_base) >> shift);
+		dma_4v_iommu_demap(&devhandle, entry, npages);
+		iommu_tbl_range_free(&iommu->tbl, dma_handle, npages,
+				     DMA_ERROR_CODE);
 		sg = sg_next(sg);
 	}
 
-	spin_unlock_irqrestore(&iommu->lock, flags);
+	local_irq_restore(flags);
 }
 
 static struct dma_map_ops sun4v_dma_ops = {
@@ -550,30 +526,33 @@ static void pci_sun4v_scan_bus(struct pci_pbm_info *pbm, struct device *parent)
 }
 
 static unsigned long probe_existing_entries(struct pci_pbm_info *pbm,
-					    struct iommu *iommu)
+					    struct iommu_map_table *iommu)
 {
-	struct iommu_arena *arena = &iommu->arena;
-	unsigned long i, cnt = 0;
+	struct iommu_pool *pool;
+	unsigned long i, pool_nr, cnt = 0;
 	u32 devhandle;
 
 	devhandle = pbm->devhandle;
-	for (i = 0; i < arena->limit; i++) {
-		unsigned long ret, io_attrs, ra;
-
-		ret = pci_sun4v_iommu_getmap(devhandle,
-					     HV_PCI_TSBID(0, i),
-					     &io_attrs, &ra);
-		if (ret == HV_EOK) {
-			if (page_in_phys_avail(ra)) {
-				pci_sun4v_iommu_demap(devhandle,
-						      HV_PCI_TSBID(0, i), 1);
-			} else {
-				cnt++;
-				__set_bit(i, arena->map);
+	for (pool_nr = 0; pool_nr < iommu->nr_pools; pool_nr++) {
+		pool = &(iommu->pools[pool_nr]);
+		for (i = pool->start; i <= pool->end; i++) {
+			unsigned long ret, io_attrs, ra;
+
+			ret = pci_sun4v_iommu_getmap(devhandle,
+						     HV_PCI_TSBID(0, i),
+						     &io_attrs, &ra);
+			if (ret == HV_EOK) {
+				if (page_in_phys_avail(ra)) {
+					pci_sun4v_iommu_demap(devhandle,
+							      HV_PCI_TSBID(0,
+							      i), 1);
+				} else {
+					cnt++;
+					__set_bit(i, iommu->map);
+				}
 			}
 		}
 	}
-
 	return cnt;
 }
 
@@ -603,20 +582,22 @@ static int pci_sun4v_iommu_init(struct pci_pbm_info *pbm)
 	/* Setup initial software IOMMU state. */
 	spin_lock_init(&iommu->lock);
 	iommu->ctx_lowest_free = 1;
-	iommu->page_table_map_base = dma_offset;
+	iommu->tbl.table_map_base = dma_offset;
 	iommu->dma_addr_mask = dma_mask;
 
 	/* Allocate and initialize the free area map.  */
 	sz = (num_tsb_entries + 7) / 8;
 	sz = (sz + 7UL) & ~7UL;
-	iommu->arena.map = kzalloc(sz, GFP_KERNEL);
-	if (!iommu->arena.map) {
+	iommu->tbl.map = kzalloc(sz, GFP_KERNEL);
+	if (!iommu->tbl.map) {
 		printk(KERN_ERR PFX "Error, kmalloc(arena.map) failed.\n");
 		return -ENOMEM;
 	}
-	iommu->arena.limit = num_tsb_entries;
-
-	sz = probe_existing_entries(pbm, iommu);
+	iommu_tbl_pool_init(&iommu->tbl, num_tsb_entries, IO_PAGE_SHIFT,
+			    NULL, false /* no large_pool */,
+			    0 /* default npools */,
+			    false /* want span boundary checking */);
+	sz = probe_existing_entries(pbm, &iommu->tbl);
 	if (sz)
 		printk("%s: Imported %lu TSB entries from OBP\n",
 		       pbm->name, sz);
diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c
index 6cc78c213c01..24384e1dc33d 100644
--- a/arch/sparc/kernel/pcic.c
+++ b/arch/sparc/kernel/pcic.c
@@ -391,12 +391,16 @@ static void __init pcic_pbm_scan_bus(struct linux_pcic *pcic)
 	struct linux_pbm_info *pbm = &pcic->pbm;
 
 	pbm->pci_bus = pci_scan_bus(pbm->pci_first_busno, &pcic_ops, pbm);
+	if (!pbm->pci_bus)
+		return;
+
 #if 0 /* deadwood transplanted from sparc64 */
 	pci_fill_in_pbm_cookies(pbm->pci_bus, pbm, pbm->prom_node);
 	pci_record_assignments(pbm, pbm->pci_bus);
 	pci_assign_unassigned(pbm, pbm->pci_bus);
 	pci_fixup_irq(pbm, pbm->pci_bus);
 #endif
+	pci_bus_add_devices(pbm->pci_bus);
 }
 
 /*
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 86eebfa3b158..59cf917a77b5 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -737,25 +737,9 @@ static void sparc_vt_write_pmc(int idx, u64 val)
 {
 	u64 pcr;
 
-	/* There seems to be an internal latch on the overflow event
-	 * on SPARC-T4 that prevents it from triggering unless you
-	 * update the PIC exactly as we do here.  The requirement
-	 * seems to be that you have to turn off event counting in the
-	 * PCR around the PIC update.
-	 *
-	 * For example, after the following sequence:
-	 *
-	 * 1) set PIC to -1
-	 * 2) enable event counting and overflow reporting in PCR
-	 * 3) overflow triggers, softint 15 handler invoked
-	 * 4) clear OV bit in PCR
-	 * 5) write PIC to -1
-	 *
-	 * a subsequent overflow event will not trigger.  This
-	 * sequence works on SPARC-T3 and previous chips.
-	 */
 	pcr = pcr_ops->read_pcr(idx);
-	pcr_ops->write_pcr(idx, PCR_N4_PICNPT);
+	/* ensure ov and ntc are reset */
+	pcr &= ~(PCR_N4_OV | PCR_N4_NTC);
 
 	pcr_ops->write_pic(idx, val & 0xffffffff);
 
@@ -792,25 +776,12 @@ static const struct sparc_pmu niagara4_pmu = {
 	.num_pic_regs	= 4,
 };
 
-static void sparc_m7_write_pmc(int idx, u64 val)
-{
-	u64 pcr;
-
-	pcr = pcr_ops->read_pcr(idx);
-	/* ensure ov and ntc are reset */
-	pcr &= ~(PCR_N4_OV | PCR_N4_NTC);
-
-	pcr_ops->write_pic(idx, val & 0xffffffff);
-
-	pcr_ops->write_pcr(idx, pcr);
-}
-
 static const struct sparc_pmu sparc_m7_pmu = {
 	.event_map	= niagara4_event_map,
 	.cache_map	= &niagara4_cache_map,
 	.max_events	= ARRAY_SIZE(niagara4_perfmon_event_map),
 	.read_pmc	= sparc_vt_read_pmc,
-	.write_pmc	= sparc_m7_write_pmc,
+	.write_pmc	= sparc_vt_write_pmc,
 	.upper_shift	= 5,
 	.lower_shift	= 5,
 	.event_mask	= 0x7ff,
diff --git a/arch/sparc/kernel/time_32.c b/arch/sparc/kernel/time_32.c
index 18147a5523d9..8caf45ee81d9 100644
--- a/arch/sparc/kernel/time_32.c
+++ b/arch/sparc/kernel/time_32.c
@@ -194,7 +194,7 @@ static __init int setup_timer_cs(void)
 static void percpu_ce_setup(enum clock_event_mode mode,
 			struct clock_event_device *evt)
 {
-	int cpu = __first_cpu(evt->cpumask);
+	int cpu = cpumask_first(evt->cpumask);
 
 	switch (mode) {
 		case CLOCK_EVT_MODE_PERIODIC:
@@ -214,7 +214,7 @@ static void percpu_ce_setup(enum clock_event_mode mode,
 static int percpu_ce_set_next_event(unsigned long delta,
 				    struct clock_event_device *evt)
 {
-	int cpu = __first_cpu(evt->cpumask);
+	int cpu = cpumask_first(evt->cpumask);
 	unsigned int next = (unsigned int)delta;
 
 	sparc_config.load_profile_irq(cpu, next);
diff --git a/arch/sparc/kernel/traps_32.c b/arch/sparc/kernel/traps_32.c
index 6fd386c5232a..4f21df7d4f13 100644
--- a/arch/sparc/kernel/traps_32.c
+++ b/arch/sparc/kernel/traps_32.c
@@ -433,7 +433,6 @@ void trap_init(void)
 	/* Force linker to barf if mismatched */
 	if (TI_UWINMASK    != offsetof(struct thread_info, uwinmask) ||
 	    TI_TASK        != offsetof(struct thread_info, task) ||
-	    TI_EXECDOMAIN  != offsetof(struct thread_info, exec_domain) ||
 	    TI_FLAGS       != offsetof(struct thread_info, flags) ||
 	    TI_CPU         != offsetof(struct thread_info, cpu) ||
 	    TI_PREEMPT     != offsetof(struct thread_info, preempt_count) ||
diff --git a/arch/sparc/kernel/traps_64.c b/arch/sparc/kernel/traps_64.c
index 0e699745d643..d21cd625c0de 100644
--- a/arch/sparc/kernel/traps_64.c
+++ b/arch/sparc/kernel/traps_64.c
@@ -2691,8 +2691,6 @@ void __init trap_init(void)
 					       fault_address) ||
 		     TI_KREGS != offsetof(struct thread_info, kregs) ||
 		     TI_UTRAPS != offsetof(struct thread_info, utraps) ||
-		     TI_EXEC_DOMAIN != offsetof(struct thread_info,
-						exec_domain) ||
 		     TI_REG_WINDOW != offsetof(struct thread_info,
 					       reg_window) ||
 		     TI_RWIN_SPTRS != offsetof(struct thread_info,