Merge branch 'master' into for-linus

56 files changed, 2168 insertions, 710 deletions

diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 3f8b6a92eabd..2bd5c287538a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -25,6 +25,9 @@ config SPARC
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select RTC_CLASS
         select RTC_DRV_M48T59
+        select HAVE_PERF_COUNTERS
+        select HAVE_DMA_ATTRS
+        select HAVE_DMA_API_DEBUG
 
 config SPARC32
         def_bool !64BIT
@@ -44,6 +47,7 @@ config SPARC64
         select RTC_DRV_BQ4802
         select RTC_DRV_SUN4V
         select RTC_DRV_STARFIRE
+        select HAVE_PERF_COUNTERS
 
 config ARCH_DEFCONFIG
         string
@@ -437,6 +441,17 @@ config SERIAL_CONSOLE
 
           If unsure, say N.
 
+config SPARC_LEON
+        bool "Sparc Leon processor family"
+        depends on SPARC32
+        ---help---
+          If you say Y here if you are running on a SPARC-LEON processor.
+          The LEON processor is a synthesizable VHDL model of the
+          SPARC-v8 standard. LEON is  part of the GRLIB collection of
+          IP cores that are distributed under GPL. GRLIB can be downloaded
+          from www.gaisler.com. You can download a sparc-linux cross-compilation
+          toolchain at www.gaisler.com.
+
 endmenu
 
 menu "Bus options (PCI etc.)"
diff --git a/arch/sparc/Makefile b/arch/sparc/Makefile
index 2003ded054c2..467221dd5702 100644
--- a/arch/sparc/Makefile
+++ b/arch/sparc/Makefile
@@ -38,10 +38,6 @@ CPPFLAGS_vmlinux.lds += -m32
 #  Actual linking is done with "make image".
 LDFLAGS_vmlinux = -r
 
-# Default target
-all: zImage
-
-
 else
 #####
 # sparc64
@@ -91,6 +87,9 @@ endif
 
 boot := arch/sparc/boot
 
+# Default target
+all: zImage
+
 image zImage tftpboot.img vmlinux.aout: vmlinux
         $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
@@ -109,8 +108,9 @@ define archhelp
 endef
 else
 define archhelp
-  echo  '* vmlinux       - Standard sparc64 kernel'
-  echo  '  vmlinux.aout  - a.out kernel for sparc64'
+  echo  '* vmlinux      - standard sparc64 kernel'
+  echo  '* zImage       - stripped and compressed sparc64 kernel ($(boot)/zImage)'
+  echo  '  vmlinux.aout - a.out kernel for sparc64'
   echo  '  tftpboot.img - image prepared for tftp'
 endef
 endif
diff --git a/arch/sparc/boot/Makefile b/arch/sparc/boot/Makefile
index 1ff0fd924756..97e3feb9ff1b 100644
--- a/arch/sparc/boot/Makefile
+++ b/arch/sparc/boot/Makefile
@@ -79,6 +79,9 @@ $(obj)/image: vmlinux FORCE
         $(call if_changed,strip)
         @echo '  kernel: $@ is ready'
 
+$(obj)/zImage: $(obj)/image
+        $(call if_changed,gzip)
+
 $(obj)/tftpboot.img: $(obj)/image $(obj)/piggyback_64 System.map $(ROOT_IMG) FORCE
         $(call if_changed,elftoaout)
         $(call if_changed,piggy)
diff --git a/arch/sparc/include/asm/asi.h b/arch/sparc/include/asm/asi.h
index 74703c5ef985..b2e3db63a64b 100644
--- a/arch/sparc/include/asm/asi.h
+++ b/arch/sparc/include/asm/asi.h
@@ -40,7 +40,11 @@
 #define ASI_M_UNA01         0x01   /* Same here... */
 #define ASI_M_MXCC          0x02   /* Access to TI VIKING MXCC registers */
 #define ASI_M_FLUSH_PROBE   0x03   /* Reference MMU Flush/Probe; rw, ss */
+#ifndef CONFIG_SPARC_LEON
 #define ASI_M_MMUREGS       0x04   /* MMU Registers; rw, ss */
+#else
+#define ASI_M_MMUREGS       0x19
+#endif /* CONFIG_SPARC_LEON */
 #define ASI_M_TLBDIAG       0x05   /* MMU TLB only Diagnostics */
 #define ASI_M_DIAGS         0x06   /* Reference MMU Diagnostics */
 #define ASI_M_IODIAG        0x07   /* MMU I/O TLB only Diagnostics */
diff --git a/arch/sparc/include/asm/dma-mapping.h b/arch/sparc/include/asm/dma-mapping.h
index 204e4bf64438..5a8c308e2b5c 100644
--- a/arch/sparc/include/asm/dma-mapping.h
+++ b/arch/sparc/include/asm/dma-mapping.h
@@ -3,6 +3,7 @@
 
 #include <linux/scatterlist.h>
 #include <linux/mm.h>
+#include <linux/dma-debug.h>
 
 #define DMA_ERROR_CODE  (~(dma_addr_t)0x0)
 
@@ -13,142 +14,40 @@ extern int dma_set_mask(struct device *dev, u64 dma_mask);
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 #define dma_is_consistent(d, h) (1)
 
-struct dma_ops {
-        void *(*alloc_coherent)(struct device *dev, size_t size,
-                                dma_addr_t *dma_handle, gfp_t flag);
-        void (*free_coherent)(struct device *dev, size_t size,
-                              void *cpu_addr, dma_addr_t dma_handle);
-        dma_addr_t (*map_page)(struct device *dev, struct page *page,
-                               unsigned long offset, size_t size,
-                               enum dma_data_direction direction);
-        void (*unmap_page)(struct device *dev, dma_addr_t dma_addr,
-                           size_t size,
-                           enum dma_data_direction direction);
-        int (*map_sg)(struct device *dev, struct scatterlist *sg, int nents,
-                      enum dma_data_direction direction);
-        void (*unmap_sg)(struct device *dev, struct scatterlist *sg,
-                         int nhwentries,
-                         enum dma_data_direction direction);
-        void (*sync_single_for_cpu)(struct device *dev,
-                                    dma_addr_t dma_handle, size_t size,
-                                    enum dma_data_direction direction);
-        void (*sync_single_for_device)(struct device *dev,
-                                       dma_addr_t dma_handle, size_t size,
-                                       enum dma_data_direction direction);
-        void (*sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg,
-                                int nelems,
-                                enum dma_data_direction direction);
-        void (*sync_sg_for_device)(struct device *dev,
-                                   struct scatterlist *sg, int nents,
-                                   enum dma_data_direction dir);
-};
-extern const struct dma_ops *dma_ops;
+extern struct dma_map_ops *dma_ops, pci32_dma_ops;
+extern struct bus_type pci_bus_type;
 
-static inline void *dma_alloc_coherent(struct device *dev, size_t size,
-                                       dma_addr_t *dma_handle, gfp_t flag)
-{
-        return dma_ops->alloc_coherent(dev, size, dma_handle, flag);
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-                                     void *cpu_addr, dma_addr_t dma_handle)
-{
-        dma_ops->free_coherent(dev, size, cpu_addr, dma_handle);
-}
-
-static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
-                                        size_t size,
-                                        enum dma_data_direction direction)
-{
-        return dma_ops->map_page(dev, virt_to_page(cpu_addr),
-                                 (unsigned long)cpu_addr & ~PAGE_MASK, size,
-                                 direction);
-}
-
-static inline void dma_unmap_single(struct device *dev, dma_addr_t dma_addr,
-                                    size_t size,
-                                    enum dma_data_direction direction)
-{
-        dma_ops->unmap_page(dev, dma_addr, size, direction);
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-                                      unsigned long offset, size_t size,
-                                      enum dma_data_direction direction)
-{
-        return dma_ops->map_page(dev, page, offset, size, direction);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-                                  size_t size,
-                                  enum dma_data_direction direction)
-{
-        dma_ops->unmap_page(dev, dma_address, size, direction);
-}
-
-static inline int dma_map_sg(struct device *dev, struct scatterlist *sg,
-                             int nents, enum dma_data_direction direction)
-{
-        return dma_ops->map_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-                                int nents, enum dma_data_direction direction)
+static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 {
-        dma_ops->unmap_sg(dev, sg, nents, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev,
-                                           dma_addr_t dma_handle, size_t size,
-                                           enum dma_data_direction direction)
-{
-        dma_ops->sync_single_for_cpu(dev, dma_handle, size, direction);
+#if defined(CONFIG_SPARC32) && defined(CONFIG_PCI)
+        if (dev->bus == &pci_bus_type)
+                return &pci32_dma_ops;
+#endif
+        return dma_ops;
 }
 
-static inline void dma_sync_single_for_device(struct device *dev,
-                                              dma_addr_t dma_handle,
-                                              size_t size,
-                                              enum dma_data_direction direction)
-{
-        if (dma_ops->sync_single_for_device)
-                dma_ops->sync_single_for_device(dev, dma_handle, size,
-                                                direction);
-}
+#include <asm-generic/dma-mapping-common.h>
 
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-                                       struct scatterlist *sg, int nelems,
-                                       enum dma_data_direction direction)
+static inline void *dma_alloc_coherent(struct device *dev, size_t size,
+                                       dma_addr_t *dma_handle, gfp_t flag)
 {
-        dma_ops->sync_sg_for_cpu(dev, sg, nelems, direction);
-}
+        struct dma_map_ops *ops = get_dma_ops(dev);
+        void *cpu_addr;
 
-static inline void dma_sync_sg_for_device(struct device *dev,
-                                          struct scatterlist *sg, int nelems,
-                                          enum dma_data_direction direction)
-{
-        if (dma_ops->sync_sg_for_device)
-                dma_ops->sync_sg_for_device(dev, sg, nelems, direction);
+        cpu_addr = ops->alloc_coherent(dev, size, dma_handle, flag);
+        debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+        return cpu_addr;
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-                                                 dma_addr_t dma_handle,
-                                                 unsigned long offset,
-                                                 size_t size,
-                                                 enum dma_data_direction dir)
+static inline void dma_free_coherent(struct device *dev, size_t size,
+                                     void *cpu_addr, dma_addr_t dma_handle)
 {
-        dma_sync_single_for_cpu(dev, dma_handle+offset, size, dir);
-}
+        struct dma_map_ops *ops = get_dma_ops(dev);
 
-static inline void dma_sync_single_range_for_device(struct device *dev,
-                                                    dma_addr_t dma_handle,
-                                                    unsigned long offset,
-                                                    size_t size,
-                                                    enum dma_data_direction dir)
-{
-        dma_sync_single_for_device(dev, dma_handle+offset, size, dir);
+        debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+        ops->free_coherent(dev, size, cpu_addr, dma_handle);
 }
 
-
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
         return (dma_addr == DMA_ERROR_CODE);
diff --git a/arch/sparc/include/asm/irq_64.h b/arch/sparc/include/asm/irq_64.h
index 1934f2cbf513..a0b443cb3c1f 100644
--- a/arch/sparc/include/asm/irq_64.h
+++ b/arch/sparc/include/asm/irq_64.h
@@ -89,8 +89,8 @@ static inline unsigned long get_softint(void)
         return retval;
 }
 
-void __trigger_all_cpu_backtrace(void);
-#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 
 extern void *hardirq_stack[NR_CPUS];
 extern void *softirq_stack[NR_CPUS];
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
new file mode 100644
index 000000000000..28a42b73f64f
--- /dev/null
+++ b/arch/sparc/include/asm/leon.h
@@ -0,0 +1,362 @@
+/*
+ * Copyright (C) 2004 Konrad Eisele (eiselekd@web.de,konrad@gaisler.com) Gaisler Research
+ * Copyright (C) 2004 Stefan Holst (mail@s-holst.de) Uni-Stuttgart
+ * Copyright (C) 2009 Daniel Hellstrom (daniel@gaisler.com) Aeroflex Gaisler AB
+ * Copyright (C) 2009 Konrad Eisele (konrad@gaisler.com) Aeroflex Gaisler AB
+ */
+
+#ifndef LEON_H_INCLUDE
+#define LEON_H_INCLUDE
+
+#ifdef CONFIG_SPARC_LEON
+
+#define ASI_LEON_NOCACHE        0x01
+
+#define ASI_LEON_DCACHE_MISS    0x1
+
+#define ASI_LEON_CACHEREGS      0x02
+#define ASI_LEON_IFLUSH         0x10
+#define ASI_LEON_DFLUSH         0x11
+
+#define ASI_LEON_MMUFLUSH       0x18
+#define ASI_LEON_MMUREGS        0x19
+#define ASI_LEON_BYPASS         0x1c
+#define ASI_LEON_FLUSH_PAGE     0x10
+
+/* mmu register access, ASI_LEON_MMUREGS */
+#define LEON_CNR_CTRL           0x000
+#define LEON_CNR_CTXP           0x100
+#define LEON_CNR_CTX            0x200
+#define LEON_CNR_F              0x300
+#define LEON_CNR_FADDR          0x400
+
+#define LEON_CNR_CTX_NCTX       256     /*number of MMU ctx */
+
+#define LEON_CNR_CTRL_TLBDIS    0x80000000
+
+#define LEON_MMUTLB_ENT_MAX     64
+
+/*
+ * diagnostic access from mmutlb.vhd:
+ * 0: pte address
+ * 4: pte
+ * 8: additional flags
+ */
+#define LEON_DIAGF_LVL          0x3
+#define LEON_DIAGF_WR           0x8
+#define LEON_DIAGF_WR_SHIFT     3
+#define LEON_DIAGF_HIT          0x10
+#define LEON_DIAGF_HIT_SHIFT    4
+#define LEON_DIAGF_CTX          0x1fe0
+#define LEON_DIAGF_CTX_SHIFT    5
+#define LEON_DIAGF_VALID        0x2000
+#define LEON_DIAGF_VALID_SHIFT  13
+
+/*
+ *  Interrupt Sources
+ *
+ *  The interrupt source numbers directly map to the trap type and to
+ *  the bits used in the Interrupt Clear, Interrupt Force, Interrupt Mask,
+ *  and the Interrupt Pending Registers.
+ */
+#define LEON_INTERRUPT_CORRECTABLE_MEMORY_ERROR 1
+#define LEON_INTERRUPT_UART_1_RX_TX             2
+#define LEON_INTERRUPT_UART_0_RX_TX             3
+#define LEON_INTERRUPT_EXTERNAL_0               4
+#define LEON_INTERRUPT_EXTERNAL_1               5
+#define LEON_INTERRUPT_EXTERNAL_2               6
+#define LEON_INTERRUPT_EXTERNAL_3               7
+#define LEON_INTERRUPT_TIMER1                   8
+#define LEON_INTERRUPT_TIMER2                   9
+#define LEON_INTERRUPT_EMPTY1                   10
+#define LEON_INTERRUPT_EMPTY2                   11
+#define LEON_INTERRUPT_OPEN_ETH                 12
+#define LEON_INTERRUPT_EMPTY4                   13
+#define LEON_INTERRUPT_EMPTY5                   14
+#define LEON_INTERRUPT_EMPTY6                   15
+
+/* irq masks */
+#define LEON_HARD_INT(x)        (1 << (x))      /* irq 0-15 */
+#define LEON_IRQMASK_R          0x0000fffe      /* bit 15- 1 of lregs.irqmask */
+#define LEON_IRQPRIO_R          0xfffe0000      /* bit 31-17 of lregs.irqmask */
+
+/* leon uart register definitions */
+#define LEON_OFF_UDATA  0x0
+#define LEON_OFF_USTAT  0x4
+#define LEON_OFF_UCTRL  0x8
+#define LEON_OFF_USCAL  0xc
+
+#define LEON_UCTRL_RE   0x01
+#define LEON_UCTRL_TE   0x02
+#define LEON_UCTRL_RI   0x04
+#define LEON_UCTRL_TI   0x08
+#define LEON_UCTRL_PS   0x10
+#define LEON_UCTRL_PE   0x20
+#define LEON_UCTRL_FL   0x40
+#define LEON_UCTRL_LB   0x80
+
+#define LEON_USTAT_DR   0x01
+#define LEON_USTAT_TS   0x02
+#define LEON_USTAT_TH   0x04
+#define LEON_USTAT_BR   0x08
+#define LEON_USTAT_OV   0x10
+#define LEON_USTAT_PE   0x20
+#define LEON_USTAT_FE   0x40
+
+#define LEON_MCFG2_SRAMDIS              0x00002000
+#define LEON_MCFG2_SDRAMEN              0x00004000
+#define LEON_MCFG2_SRAMBANKSZ           0x00001e00      /* [12-9] */
+#define LEON_MCFG2_SRAMBANKSZ_SHIFT     9
+#define LEON_MCFG2_SDRAMBANKSZ          0x03800000      /* [25-23] */
+#define LEON_MCFG2_SDRAMBANKSZ_SHIFT    23
+
+#define LEON_TCNT0_MASK 0x7fffff
+
+#define LEON_USTAT_ERROR (LEON_USTAT_OV | LEON_USTAT_PE | LEON_USTAT_FE)
+/* no break yet */
+
+#define ASI_LEON3_SYSCTRL               0x02
+#define ASI_LEON3_SYSCTRL_ICFG          0x08
+#define ASI_LEON3_SYSCTRL_DCFG          0x0c
+#define ASI_LEON3_SYSCTRL_CFG_SNOOPING (1 << 27)
+#define ASI_LEON3_SYSCTRL_CFG_SSIZE(c) (1 << ((c >> 20) & 0xf))
+
+#ifndef __ASSEMBLY__
+
+/* do a virtual address read without cache */
+static inline unsigned long leon_readnobuffer_reg(unsigned long paddr)
+{
+        unsigned long retval;
+        __asm__ __volatile__("lda [%1] %2, %0\n\t" :
+                             "=r"(retval) : "r"(paddr), "i"(ASI_LEON_NOCACHE));
+        return retval;
+}
+
+/* do a physical address bypass write, i.e. for 0x80000000 */
+static inline void leon_store_reg(unsigned long paddr, unsigned long value)
+{
+        __asm__ __volatile__("sta %0, [%1] %2\n\t" : : "r"(value), "r"(paddr),
+                             "i"(ASI_LEON_BYPASS) : "memory");
+}
+
+/* do a physical address bypass load, i.e. for 0x80000000 */
+static inline unsigned long leon_load_reg(unsigned long paddr)
+{
+        unsigned long retval;
+        __asm__ __volatile__("lda [%1] %2, %0\n\t" :
+                             "=r"(retval) : "r"(paddr), "i"(ASI_LEON_BYPASS));
+        return retval;
+}
+
+extern inline void leon_srmmu_disabletlb(void)
+{
+        unsigned int retval;
+        __asm__ __volatile__("lda [%%g0] %2, %0\n\t" : "=r"(retval) : "r"(0),
+                             "i"(ASI_LEON_MMUREGS));
+        retval |= LEON_CNR_CTRL_TLBDIS;
+        __asm__ __volatile__("sta %0, [%%g0] %2\n\t" : : "r"(retval), "r"(0),
+                             "i"(ASI_LEON_MMUREGS) : "memory");
+}
+
+extern inline void leon_srmmu_enabletlb(void)
+{
+        unsigned int retval;
+        __asm__ __volatile__("lda [%%g0] %2, %0\n\t" : "=r"(retval) : "r"(0),
+                             "i"(ASI_LEON_MMUREGS));
+        retval = retval & ~LEON_CNR_CTRL_TLBDIS;
+        __asm__ __volatile__("sta %0, [%%g0] %2\n\t" : : "r"(retval), "r"(0),
+                             "i"(ASI_LEON_MMUREGS) : "memory");
+}
+
+/* macro access for leon_load_reg() and leon_store_reg() */
+#define LEON3_BYPASS_LOAD_PA(x)     (leon_load_reg((unsigned long)(x)))
+#define LEON3_BYPASS_STORE_PA(x, v) (leon_store_reg((unsigned long)(x), (unsigned long)(v)))
+#define LEON3_BYPASS_ANDIN_PA(x, v) LEON3_BYPASS_STORE_PA(x, LEON3_BYPASS_LOAD_PA(x) & v)
+#define LEON3_BYPASS_ORIN_PA(x, v)  LEON3_BYPASS_STORE_PA(x, LEON3_BYPASS_LOAD_PA(x) | v)
+#define LEON_BYPASS_LOAD_PA(x)      leon_load_reg((unsigned long)(x))
+#define LEON_BYPASS_STORE_PA(x, v)  leon_store_reg((unsigned long)(x), (unsigned long)(v))
+#define LEON_REGLOAD_PA(x)          leon_load_reg((unsigned long)(x)+LEON_PREGS)
+#define LEON_REGSTORE_PA(x, v)      leon_store_reg((unsigned long)(x)+LEON_PREGS, (unsigned long)(v))
+#define LEON_REGSTORE_OR_PA(x, v)   LEON_REGSTORE_PA(x, LEON_REGLOAD_PA(x) | (unsigned long)(v))
+#define LEON_REGSTORE_AND_PA(x, v)  LEON_REGSTORE_PA(x, LEON_REGLOAD_PA(x) & (unsigned long)(v))
+
+/* macro access for leon_readnobuffer_reg() */
+#define LEON_BYPASSCACHE_LOAD_VA(x) leon_readnobuffer_reg((unsigned long)(x))
+
+extern void sparc_leon_eirq_register(int eirq);
+extern void leon_init(void);
+extern void leon_switch_mm(void);
+extern void leon_init_IRQ(void);
+
+extern unsigned long last_valid_pfn;
+
+extern inline unsigned long sparc_leon3_get_dcachecfg(void)
+{
+        unsigned int retval;
+        __asm__ __volatile__("lda [%1] %2, %0\n\t" :
+                             "=r"(retval) :
+                             "r"(ASI_LEON3_SYSCTRL_DCFG),
+                             "i"(ASI_LEON3_SYSCTRL));
+        return retval;
+}
+
+/* enable snooping */
+extern inline void sparc_leon3_enable_snooping(void)
+{
+        __asm__ __volatile__ ("lda [%%g0] 2, %%l1\n\t"
+                          "set 0x800000, %%l2\n\t"
+                          "or  %%l2, %%l1, %%l2\n\t"
+                          "sta %%l2, [%%g0] 2\n\t" : : : "l1", "l2");
+};
+
+extern inline void sparc_leon3_disable_cache(void)
+{
+        __asm__ __volatile__ ("lda [%%g0] 2, %%l1\n\t"
+                          "set 0x00000f, %%l2\n\t"
+                          "andn  %%l2, %%l1, %%l2\n\t"
+                          "sta %%l2, [%%g0] 2\n\t" : : : "l1", "l2");
+};
+
+#endif /*!__ASSEMBLY__*/
+
+#ifdef CONFIG_SMP
+# define LEON3_IRQ_RESCHEDULE           13
+# define LEON3_IRQ_TICKER               (leon_percpu_timer_dev[0].irq)
+# define LEON3_IRQ_CROSS_CALL           15
+#endif
+
+#if defined(PAGE_SIZE_LEON_8K)
+#define LEON_PAGE_SIZE_LEON 1
+#elif defined(PAGE_SIZE_LEON_16K)
+#define LEON_PAGE_SIZE_LEON 2)
+#else
+#define LEON_PAGE_SIZE_LEON 0
+#endif
+
+#if LEON_PAGE_SIZE_LEON == 0
+/* [ 8, 6, 6 ] + 12 */
+#define LEON_PGD_SH    24
+#define LEON_PGD_M     0xff
+#define LEON_PMD_SH    18
+#define LEON_PMD_SH_V  (LEON_PGD_SH-2)
+#define LEON_PMD_M     0x3f
+#define LEON_PTE_SH    12
+#define LEON_PTE_M     0x3f
+#elif LEON_PAGE_SIZE_LEON == 1
+/* [ 7, 6, 6 ] + 13 */
+#define LEON_PGD_SH    25
+#define LEON_PGD_M     0x7f
+#define LEON_PMD_SH    19
+#define LEON_PMD_SH_V  (LEON_PGD_SH-1)
+#define LEON_PMD_M     0x3f
+#define LEON_PTE_SH    13
+#define LEON_PTE_M     0x3f
+#elif LEON_PAGE_SIZE_LEON == 2
+/* [ 6, 6, 6 ] + 14 */
+#define LEON_PGD_SH    26
+#define LEON_PGD_M     0x3f
+#define LEON_PMD_SH    20
+#define LEON_PMD_SH_V  (LEON_PGD_SH-0)
+#define LEON_PMD_M     0x3f
+#define LEON_PTE_SH    14
+#define LEON_PTE_M     0x3f
+#elif LEON_PAGE_SIZE_LEON == 3
+/* [ 4, 7, 6 ] + 15 */
+#define LEON_PGD_SH    28
+#define LEON_PGD_M     0x0f
+#define LEON_PMD_SH    21
+#define LEON_PMD_SH_V  (LEON_PGD_SH-0)
+#define LEON_PMD_M     0x7f
+#define LEON_PTE_SH    15
+#define LEON_PTE_M     0x3f
+#else
+#error cannot determine LEON_PAGE_SIZE_LEON
+#endif
+
+#define PAGE_MIN_SHIFT   (12)
+#define PAGE_MIN_SIZE    (1UL << PAGE_MIN_SHIFT)
+
+#define LEON3_XCCR_SETS_MASK  0x07000000UL
+#define LEON3_XCCR_SSIZE_MASK 0x00f00000UL
+
+#define LEON2_CCR_DSETS_MASK 0x03000000UL
+#define LEON2_CFG_SSIZE_MASK 0x00007000UL
+
+#ifndef __ASSEMBLY__
+extern unsigned long srmmu_swprobe(unsigned long vaddr, unsigned long *paddr);
+extern void leon_flush_icache_all(void);
+extern void leon_flush_dcache_all(void);
+extern void leon_flush_cache_all(void);
+extern void leon_flush_tlb_all(void);
+extern int leon_flush_during_switch;
+extern int leon_flush_needed(void);
+
+struct vm_area_struct;
+extern void leon_flush_icache_all(void);
+extern void leon_flush_dcache_all(void);
+extern void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
+extern void leon_flush_cache_all(void);
+extern void leon_flush_tlb_all(void);
+extern int leon_flush_during_switch;
+extern int leon_flush_needed(void);
+extern void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page);
+
+/* struct that hold LEON3 cache configuration registers */
+struct leon3_cacheregs {
+        unsigned long ccr;      /* 0x00 - Cache Control Register  */
+        unsigned long iccr;     /* 0x08 - Instruction Cache Configuration Register */
+        unsigned long dccr;     /* 0x0c - Data Cache Configuration Register */
+};
+
+/* struct that hold LEON2 cache configuration register
+ * & configuration register
+ */
+struct leon2_cacheregs {
+        unsigned long ccr, cfg;
+};
+
+#ifdef __KERNEL__
+
+#include <linux/interrupt.h>
+
+struct device_node;
+extern int sparc_leon_eirq_get(int eirq, int cpu);
+extern irqreturn_t sparc_leon_eirq_isr(int dummy, void *dev_id);
+extern void sparc_leon_eirq_register(int eirq);
+extern void leon_clear_clock_irq(void);
+extern void leon_load_profile_irq(int cpu, unsigned int limit);
+extern void leon_init_timers(irq_handler_t counter_fn);
+extern void leon_clear_clock_irq(void);
+extern void leon_load_profile_irq(int cpu, unsigned int limit);
+extern void leon_trans_init(struct device_node *dp);
+extern void leon_node_init(struct device_node *dp, struct device_node ***nextp);
+extern void leon_init_IRQ(void);
+extern void leon_init(void);
+extern unsigned long srmmu_swprobe(unsigned long vaddr, unsigned long *paddr);
+extern void init_leon(void);
+extern void poke_leonsparc(void);
+extern void leon3_getCacheRegs(struct leon3_cacheregs *regs);
+extern int leon_flush_needed(void);
+extern void leon_switch_mm(void);
+extern int srmmu_swprobe_trace;
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASSEMBLY__ */
+
+/* macros used in leon_mm.c */
+#define PFN(x)           ((x) >> PAGE_SHIFT)
+#define _pfn_valid(pfn)  ((pfn < last_valid_pfn) && (pfn >= PFN(phys_base)))
+#define _SRMMU_PTE_PMASK_LEON 0xffffffff
+
+#else /* defined(CONFIG_SPARC_LEON) */
+
+/* nop definitions for !LEON case */
+#define leon_init() do {} while (0)
+#define leon_switch_mm() do {} while (0)
+#define leon_init_IRQ() do {} while (0)
+#define init_leon() do {} while (0)
+
+#endif /* !defined(CONFIG_SPARC_LEON) */
+
+#endif
diff --git a/arch/sparc/include/asm/leon_amba.h b/arch/sparc/include/asm/leon_amba.h
new file mode 100644
index 000000000000..618e88821795
--- /dev/null
+++ b/arch/sparc/include/asm/leon_amba.h
@@ -0,0 +1,263 @@
+/*
+*Copyright (C) 2004 Konrad Eisele (eiselekd@web.de,konrad@gaisler.com), Gaisler Research
+*Copyright (C) 2004 Stefan Holst (mail@s-holst.de), Uni-Stuttgart
+*Copyright (C) 2009 Daniel Hellstrom (daniel@gaisler.com),Konrad Eisele (konrad@gaisler.com) Aeroflex Gaisler AB
+*/
+
+#ifndef LEON_AMBA_H_INCLUDE
+#define LEON_AMBA_H_INCLUDE
+
+#ifndef __ASSEMBLY__
+
+struct amba_prom_registers {
+        unsigned int phys_addr; /* The physical address of this register */
+        unsigned int reg_size;  /* How many bytes does this register take up? */
+};
+
+#endif
+
+/*
+ *  The following defines the bits in the LEON UART Status Registers.
+ */
+
+#define LEON_REG_UART_STATUS_DR   0x00000001    /* Data Ready */
+#define LEON_REG_UART_STATUS_TSE  0x00000002    /* TX Send Register Empty */
+#define LEON_REG_UART_STATUS_THE  0x00000004    /* TX Hold Register Empty */
+#define LEON_REG_UART_STATUS_BR   0x00000008    /* Break Error */
+#define LEON_REG_UART_STATUS_OE   0x00000010    /* RX Overrun Error */
+#define LEON_REG_UART_STATUS_PE   0x00000020    /* RX Parity Error */
+#define LEON_REG_UART_STATUS_FE   0x00000040    /* RX Framing Error */
+#define LEON_REG_UART_STATUS_ERR  0x00000078    /* Error Mask */
+
+/*
+ *  The following defines the bits in the LEON UART Ctrl Registers.
+ */
+
+#define LEON_REG_UART_CTRL_RE     0x00000001    /* Receiver enable */
+#define LEON_REG_UART_CTRL_TE     0x00000002    /* Transmitter enable */
+#define LEON_REG_UART_CTRL_RI     0x00000004    /* Receiver interrupt enable */
+#define LEON_REG_UART_CTRL_TI     0x00000008    /* Transmitter irq */
+#define LEON_REG_UART_CTRL_PS     0x00000010    /* Parity select */
+#define LEON_REG_UART_CTRL_PE     0x00000020    /* Parity enable */
+#define LEON_REG_UART_CTRL_FL     0x00000040    /* Flow control enable */
+#define LEON_REG_UART_CTRL_LB     0x00000080    /* Loop Back enable */
+
+#define LEON3_GPTIMER_EN 1
+#define LEON3_GPTIMER_RL 2
+#define LEON3_GPTIMER_LD 4
+#define LEON3_GPTIMER_IRQEN 8
+#define LEON3_GPTIMER_SEPIRQ 8
+
+#define LEON23_REG_TIMER_CONTROL_EN    0x00000001 /* 1 = enable counting */
+/* 0 = hold scalar and counter */
+#define LEON23_REG_TIMER_CONTROL_RL    0x00000002 /* 1 = reload at 0 */
+                                                  /* 0 = stop at 0 */
+#define LEON23_REG_TIMER_CONTROL_LD    0x00000004 /* 1 = load counter */
+                                                  /* 0 = no function */
+#define LEON23_REG_TIMER_CONTROL_IQ    0x00000008 /* 1 = irq enable */
+                                                  /* 0 = no function */
+
+/*
+ *  The following defines the bits in the LEON PS/2 Status Registers.
+ */
+
+#define LEON_REG_PS2_STATUS_DR   0x00000001     /* Data Ready */
+#define LEON_REG_PS2_STATUS_PE   0x00000002     /* Parity error */
+#define LEON_REG_PS2_STATUS_FE   0x00000004     /* Framing error */
+#define LEON_REG_PS2_STATUS_KI   0x00000008     /* Keyboard inhibit */
+#define LEON_REG_PS2_STATUS_RF   0x00000010     /* RX buffer full */
+#define LEON_REG_PS2_STATUS_TF   0x00000020     /* TX buffer full */
+
+/*
+ *  The following defines the bits in the LEON PS/2 Ctrl Registers.
+ */
+
+#define LEON_REG_PS2_CTRL_RE 0x00000001 /* Receiver enable */
+#define LEON_REG_PS2_CTRL_TE 0x00000002 /* Transmitter enable */
+#define LEON_REG_PS2_CTRL_RI 0x00000004 /* Keyboard receive irq  */
+#define LEON_REG_PS2_CTRL_TI 0x00000008 /* Keyboard transmit irq */
+
+#define LEON3_IRQMPSTATUS_CPUNR     28
+#define LEON3_IRQMPSTATUS_BROADCAST 27
+
+#define GPTIMER_CONFIG_IRQNT(a)          (((a) >> 3) & 0x1f)
+#define GPTIMER_CONFIG_ISSEP(a)          ((a) & (1 << 8))
+#define GPTIMER_CONFIG_NTIMERS(a)        ((a) & (0x7))
+#define LEON3_GPTIMER_CTRL_PENDING       0x10
+#define LEON3_GPTIMER_CONFIG_NRTIMERS(c) ((c)->config & 0x7)
+#define LEON3_GPTIMER_CTRL_ISPENDING(r)  (((r)&LEON3_GPTIMER_CTRL_PENDING) ? 1 : 0)
+
+#ifdef CONFIG_SPARC_LEON
+
+#ifndef __ASSEMBLY__
+
+struct leon3_irqctrl_regs_map {
+        u32 ilevel;
+        u32 ipend;
+        u32 iforce;
+        u32 iclear;
+        u32 mpstatus;
+        u32 mpbroadcast;
+        u32 notused02;
+        u32 notused03;
+        u32 notused10;
+        u32 notused11;
+        u32 notused12;
+        u32 notused13;
+        u32 notused20;
+        u32 notused21;
+        u32 notused22;
+        u32 notused23;
+        u32 mask[16];
+        u32 force[16];
+        /* Extended IRQ registers */
+        u32 intid[16];  /* 0xc0 */
+};
+
+struct leon3_apbuart_regs_map {
+        u32 data;
+        u32 status;
+        u32 ctrl;
+        u32 scaler;
+};
+
+struct leon3_gptimerelem_regs_map {
+        u32 val;
+        u32 rld;
+        u32 ctrl;
+        u32 unused;
+};
+
+struct leon3_gptimer_regs_map {
+        u32 scalar;
+        u32 scalar_reload;
+        u32 config;
+        u32 unused;
+        struct leon3_gptimerelem_regs_map e[8];
+};
+
+/*
+ *  Types and structure used for AMBA Plug & Play bus scanning
+ */
+
+#define AMBA_MAXAPB_DEVS 64
+#define AMBA_MAXAPB_DEVS_PERBUS 16
+
+struct amba_device_table {
+        int devnr;                 /* number of devices on AHB or APB bus */
+        unsigned int *addr[16];    /* addresses to the devices configuration tables */
+        unsigned int allocbits[1]; /* 0=unallocated, 1=allocated driver */
+};
+
+struct amba_apbslv_device_table {
+        int devnr;                                /* number of devices on AHB or APB bus */
+        unsigned int *addr[AMBA_MAXAPB_DEVS];     /* addresses to the devices configuration tables */
+        unsigned int apbmst[AMBA_MAXAPB_DEVS];    /* apb master if a entry is a apb slave */
+        unsigned int apbmstidx[AMBA_MAXAPB_DEVS]; /* apb master idx if a entry is a apb slave */
+        unsigned int allocbits[4];                /* 0=unallocated, 1=allocated driver */
+};
+
+struct amba_confarea_type {
+        struct amba_confarea_type *next;/* next bus in chain */
+        struct amba_device_table ahbmst;
+        struct amba_device_table ahbslv;
+        struct amba_apbslv_device_table apbslv;
+        unsigned int apbmst;
+};
+
+/* collect apb slaves */
+struct amba_apb_device {
+        unsigned int start, irq, bus_id;
+        struct amba_confarea_type *bus;
+};
+
+/* collect ahb slaves */
+struct amba_ahb_device {
+        unsigned int start[4], irq, bus_id;
+        struct amba_confarea_type *bus;
+};
+
+struct device_node;
+void _amba_init(struct device_node *dp, struct device_node ***nextp);
+
+extern struct leon3_irqctrl_regs_map *leon3_irqctrl_regs;
+extern struct leon3_gptimer_regs_map *leon3_gptimer_regs;
+extern struct amba_apb_device leon_percpu_timer_dev[16];
+extern int leondebug_irq_disable;
+extern int leon_debug_irqout;
+extern unsigned long leon3_gptimer_irq;
+extern unsigned int sparc_leon_eirq;
+
+#endif /* __ASSEMBLY__ */
+
+#define LEON3_IO_AREA 0xfff00000
+#define LEON3_CONF_AREA 0xff000
+#define LEON3_AHB_SLAVE_CONF_AREA (1 << 11)
+
+#define LEON3_AHB_CONF_WORDS 8
+#define LEON3_APB_CONF_WORDS 2
+#define LEON3_AHB_MASTERS 16
+#define LEON3_AHB_SLAVES 16
+#define LEON3_APB_SLAVES 16
+#define LEON3_APBUARTS 8
+
+/* Vendor codes */
+#define VENDOR_GAISLER   1
+#define VENDOR_PENDER    2
+#define VENDOR_ESA       4
+#define VENDOR_OPENCORES 8
+
+/* Gaisler Research device id's */
+#define GAISLER_LEON3    0x003
+#define GAISLER_LEON3DSU 0x004
+#define GAISLER_ETHAHB   0x005
+#define GAISLER_APBMST   0x006
+#define GAISLER_AHBUART  0x007
+#define GAISLER_SRCTRL   0x008
+#define GAISLER_SDCTRL   0x009
+#define GAISLER_APBUART  0x00C
+#define GAISLER_IRQMP    0x00D
+#define GAISLER_AHBRAM   0x00E
+#define GAISLER_GPTIMER  0x011
+#define GAISLER_PCITRG   0x012
+#define GAISLER_PCISBRG  0x013
+#define GAISLER_PCIFBRG  0x014
+#define GAISLER_PCITRACE 0x015
+#define GAISLER_PCIDMA   0x016
+#define GAISLER_AHBTRACE 0x017
+#define GAISLER_ETHDSU   0x018
+#define GAISLER_PIOPORT  0x01A
+#define GAISLER_GRGPIO   0x01A
+#define GAISLER_AHBJTAG  0x01c
+#define GAISLER_ETHMAC   0x01D
+#define GAISLER_AHB2AHB  0x020
+#define GAISLER_USBDC    0x021
+#define GAISLER_ATACTRL  0x024
+#define GAISLER_DDRSPA   0x025
+#define GAISLER_USBEHC   0x026
+#define GAISLER_USBUHC   0x027
+#define GAISLER_I2CMST   0x028
+#define GAISLER_SPICTRL  0x02D
+#define GAISLER_DDR2SPA  0x02E
+#define GAISLER_SPIMCTRL 0x045
+#define GAISLER_LEON4    0x048
+#define GAISLER_LEON4DSU 0x049
+#define GAISLER_AHBSTAT  0x052
+#define GAISLER_FTMCTRL  0x054
+#define GAISLER_KBD      0x060
+#define GAISLER_VGA      0x061
+#define GAISLER_SVGA     0x063
+#define GAISLER_GRSYSMON 0x066
+#define GAISLER_GRACECTRL 0x067
+
+#define GAISLER_L2TIME   0xffd  /* internal device: leon2 timer */
+#define GAISLER_L2C      0xffe  /* internal device: leon2compat */
+#define GAISLER_PLUGPLAY 0xfff  /* internal device: plug & play configarea */
+
+#define amba_vendor(x) (((x) >> 24) & 0xff)
+
+#define amba_device(x) (((x) >> 12) & 0xfff)
+
+#endif /* !defined(CONFIG_SPARC_LEON) */
+
+#endif
diff --git a/arch/sparc/include/asm/machines.h b/arch/sparc/include/asm/machines.h
index c28c2f248794..cd9c099567e4 100644
--- a/arch/sparc/include/asm/machines.h
+++ b/arch/sparc/include/asm/machines.h
@@ -15,7 +15,7 @@ struct Sun_Machine_Models {
 /* Current number of machines we know about that has an IDPROM
  * machtype entry including one entry for the 0x80 OBP machines.
  */
-#define NUM_SUN_MACHINES   15
+#define NUM_SUN_MACHINES   16
 
 /* The machine type in the idprom area looks like this:
  *
@@ -30,6 +30,7 @@ struct Sun_Machine_Models {
 
 #define SM_ARCH_MASK  0xf0
 #define SM_SUN4       0x20
+#define  M_LEON       0x30
 #define SM_SUN4C      0x50
 #define SM_SUN4M      0x70
 #define SM_SUN4M_OBP  0x80
@@ -41,6 +42,9 @@ struct Sun_Machine_Models {
 #define SM_4_330      0x03    /* Sun 4/300 series */
 #define SM_4_470      0x04    /* Sun 4/400 series */
 
+/* Leon machines */
+#define M_LEON3_SOC   0x02    /* Leon3 SoC */
+
 /* Sun4c machines                Full Name              - PROM NAME */
 #define SM_4C_SS1     0x01    /* Sun4c SparcStation 1   - Sun 4/60  */
 #define SM_4C_IPC     0x02    /* Sun4c SparcStation IPC - Sun 4/40  */
diff --git a/arch/sparc/include/asm/nmi.h b/arch/sparc/include/asm/nmi.h
index fbd546dd4feb..72e6500e7ab0 100644
--- a/arch/sparc/include/asm/nmi.h
+++ b/arch/sparc/include/asm/nmi.h
@@ -5,6 +5,9 @@ extern int __init nmi_init(void);
 extern void perfctr_irq(int irq, struct pt_regs *regs);
 extern void nmi_adjust_hz(unsigned int new_hz);
 
-extern int nmi_usable;
+extern atomic_t nmi_active;
+
+extern void start_nmi_watchdog(void *unused);
+extern void stop_nmi_watchdog(void *unused);
 
 #endif /* __NMI_H */
diff --git a/arch/sparc/include/asm/pci.h b/arch/sparc/include/asm/pci.h
index 6e14fd179335..d9c031f9910f 100644
--- a/arch/sparc/include/asm/pci.h
+++ b/arch/sparc/include/asm/pci.h
@@ -5,4 +5,7 @@
 #else
 #include <asm/pci_32.h>
 #endif
+
+#include <asm-generic/pci-dma-compat.h>
+
 #endif
diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h
index b41c4c198159..ac0e8369fd97 100644
--- a/arch/sparc/include/asm/pci_32.h
+++ b/arch/sparc/include/asm/pci_32.h
@@ -31,42 +31,8 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  */
 #define PCI_DMA_BUS_IS_PHYS     (0)
 
-#include <asm/scatterlist.h>
-
 struct pci_dev;
 
-/* Allocate and map kernel buffer using consistent mode DMA for a device.
- * hwdev should be valid struct pci_dev pointer for PCI devices.
- */
-extern void *pci_alloc_consistent(struct pci_dev *hwdev, size_t size, dma_addr_t *dma_handle);
-
-/* Free and unmap a consistent DMA buffer.
- * cpu_addr is what was returned from pci_alloc_consistent,
- * size must be the same as what as passed into pci_alloc_consistent,
- * and likewise dma_addr must be the same as what *dma_addrp was set to.
- *
- * References to the memory and mappings assosciated with cpu_addr/dma_addr
- * past this call are illegal.
- */
-extern void pci_free_consistent(struct pci_dev *hwdev, size_t size, void *vaddr, dma_addr_t dma_handle);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_for_cpu is performed.
- */
-extern dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size, int direction);
-
-/* Unmap a single streaming mode DMA translation.  The dma_addr and size
- * must match what was provided for in a previous pci_map_single call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t size, int direction);
-
 /* pci_unmap_{single,page} is not a nop, thus... */
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
         dma_addr_t ADDR_NAME;
@@ -81,69 +47,6 @@ extern void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t dma_addr, size_t
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
         (((PTR)->LEN_NAME) = (VAL))
 
-/*
- * Same as above, only with pages instead of mapped addresses.
- */
-extern dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
-                        unsigned long offset, size_t size, int direction);
-extern void pci_unmap_page(struct pci_dev *hwdev,
-                        dma_addr_t dma_address, size_t size, int direction);
-
-/* Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scather-gather version of the
- * above pci_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for pci_map_single are
- * the same here.
- */
-extern int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nents, int direction);
-
-/* Unmap a set of streaming mode DMA translations.
- * Again, cpu read rules concerning calls here are the same as for
- * pci_unmap_single() above.
- */
-extern void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sg, int nhwents, int direction);
-
-/* Make physical memory consistent for a single
- * streaming mode DMA translation after a transfer.
- *
- * If you perform a pci_map_single() but wish to interrogate the
- * buffer using the cpu, yet do not wish to teardown the PCI dma
- * mapping, you must call this function before doing so.  At the
- * next point you give the PCI dma address back to the card, you
- * must first perform a pci_dma_sync_for_device, and then the device
- * again owns the buffer.
- */
-extern void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-extern void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t dma_handle, size_t size, int direction);
-
-/* Make physical memory consistent for a set of streaming
- * mode DMA translations after a transfer.
- *
- * The same as pci_dma_sync_single_* but for a scatter-gather list,
- * same rules and usage.
- */
-extern void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-extern void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sg, int nelems, int direction);
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly.  For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-static inline int pci_dma_supported(struct pci_dev *hwdev, u64 mask)
-{
-        return 1;
-}
-
 #ifdef CONFIG_PCI
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
                                         enum pci_dma_burst_strategy *strat,
@@ -154,14 +57,6 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 }
 #endif
 
-#define PCI_DMA_ERROR_CODE      (~(dma_addr_t)0x0)
-
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
-                                        dma_addr_t dma_addr)
-{
-        return (dma_addr == PCI_DMA_ERROR_CODE);
-}
-
 struct device_node;
 extern struct device_node *pci_device_to_OF_node(struct pci_dev *pdev);
 
diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h
index 7a1e3566e59c..5cc9f6aa5494 100644
--- a/arch/sparc/include/asm/pci_64.h
+++ b/arch/sparc/include/asm/pci_64.h
@@ -35,37 +35,6 @@ static inline void pcibios_penalize_isa_irq(int irq, int active)
  */
 #define PCI_DMA_BUS_IS_PHYS     (0)
 
-static inline void *pci_alloc_consistent(struct pci_dev *pdev, size_t size,
-                                         dma_addr_t *dma_handle)
-{
-        return dma_alloc_coherent(&pdev->dev, size, dma_handle, GFP_ATOMIC);
-}
-
-static inline void pci_free_consistent(struct pci_dev *pdev, size_t size,
-                                       void *vaddr, dma_addr_t dma_handle)
-{
-        return dma_free_coherent(&pdev->dev, size, vaddr, dma_handle);
-}
-
-static inline dma_addr_t pci_map_single(struct pci_dev *pdev, void *ptr,
-                                        size_t size, int direction)
-{
-        return dma_map_single(&pdev->dev, ptr, size,
-                              (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
-                                    size_t size, int direction)
-{
-        dma_unmap_single(&pdev->dev, dma_addr, size,
-                         (enum dma_data_direction) direction);
-}
-
-#define pci_map_page(dev, page, off, size, dir) \
-        pci_map_single(dev, (page_address(page) + (off)), size, dir)
-#define pci_unmap_page(dev,addr,sz,dir) \
-        pci_unmap_single(dev,addr,sz,dir)
-
 /* pci_unmap_{single,page} is not a nop, thus... */
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
         dma_addr_t ADDR_NAME;
@@ -80,57 +49,6 @@ static inline void pci_unmap_single(struct pci_dev *pdev, dma_addr_t dma_addr,
 #define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
         (((PTR)->LEN_NAME) = (VAL))
 
-static inline int pci_map_sg(struct pci_dev *pdev, struct scatterlist *sg,
-                             int nents, int direction)
-{
-        return dma_map_sg(&pdev->dev, sg, nents,
-                          (enum dma_data_direction) direction);
-}
-
-static inline void pci_unmap_sg(struct pci_dev *pdev, struct scatterlist *sg,
-                                int nents, int direction)
-{
-        dma_unmap_sg(&pdev->dev, sg, nents,
-                     (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_cpu(struct pci_dev *pdev,
-                                               dma_addr_t dma_handle,
-                                               size_t size, int direction)
-{
-        dma_sync_single_for_cpu(&pdev->dev, dma_handle, size,
-                                (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_single_for_device(struct pci_dev *pdev,
-                                                  dma_addr_t dma_handle,
-                                                  size_t size, int direction)
-{
-        /* No flushing needed to sync cpu writes to the device.  */
-}
-
-static inline void pci_dma_sync_sg_for_cpu(struct pci_dev *pdev,
-                                           struct scatterlist *sg,
-                                           int nents, int direction)
-{
-        dma_sync_sg_for_cpu(&pdev->dev, sg, nents,
-                            (enum dma_data_direction) direction);
-}
-
-static inline void pci_dma_sync_sg_for_device(struct pci_dev *pdev,
-                                              struct scatterlist *sg,
-                                              int nelems, int direction)
-{
-        /* No flushing needed to sync cpu writes to the device.  */
-}
-
-/* Return whether the given PCI device DMA address mask can
- * be supported properly.  For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
-
 /* PCI IOMMU mapping bypass support. */
 
 /* PCI 64-bit addressing works for all slots on all controller
@@ -140,12 +58,6 @@ extern int pci_dma_supported(struct pci_dev *hwdev, u64 mask);
 #define PCI64_REQUIRED_MASK     (~(dma64_addr_t)0)
 #define PCI64_ADDR_BASE         0xfffc000000000000UL
 
-static inline int pci_dma_mapping_error(struct pci_dev *pdev,
-                                        dma_addr_t dma_addr)
-{
-        return dma_mapping_error(&pdev->dev, dma_addr);
-}
-
 #ifdef CONFIG_PCI
 static inline void pci_dma_burst_advice(struct pci_dev *pdev,
                                         enum pci_dma_burst_strategy *strat,
diff --git a/arch/sparc/include/asm/perf_counter.h b/arch/sparc/include/asm/perf_counter.h
new file mode 100644
index 000000000000..5d7a8ca0e491
--- /dev/null
+++ b/arch/sparc/include/asm/perf_counter.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_SPARC_PERF_COUNTER_H
+#define __ASM_SPARC_PERF_COUNTER_H
+
+extern void set_perf_counter_pending(void);
+
+#define PERF_COUNTER_INDEX_OFFSET       0
+
+#ifdef CONFIG_PERF_COUNTERS
+extern void init_hw_perf_counters(void);
+#else
+static inline void init_hw_perf_counters(void)  { }
+#endif
+
+#endif
diff --git a/arch/sparc/include/asm/pgtsrmmu.h b/arch/sparc/include/asm/pgtsrmmu.h
index 808555fc1d58..1407c07bdade 100644
--- a/arch/sparc/include/asm/pgtsrmmu.h
+++ b/arch/sparc/include/asm/pgtsrmmu.h
@@ -267,6 +267,7 @@ static inline void srmmu_flush_tlb_page(unsigned long page)
 
 }
 
+#ifndef CONFIG_SPARC_LEON
 static inline unsigned long srmmu_hwprobe(unsigned long vaddr)
 {
         unsigned long retval;
@@ -278,6 +279,9 @@ static inline unsigned long srmmu_hwprobe(unsigned long vaddr)
 
         return retval;
 }
+#else
+#define srmmu_hwprobe(addr) (srmmu_swprobe(addr, 0) & SRMMU_PTE_PMASK)
+#endif
 
 static inline int
 srmmu_get_pte (unsigned long addr)
diff --git a/arch/sparc/include/asm/prom.h b/arch/sparc/include/asm/prom.h
index be8d7aaeb60d..82a190d7efc1 100644
--- a/arch/sparc/include/asm/prom.h
+++ b/arch/sparc/include/asm/prom.h
@@ -118,5 +118,8 @@ extern struct device_node *of_console_device;
 extern char *of_console_path;
 extern char *of_console_options;
 
+extern void (*prom_build_more)(struct device_node *dp, struct device_node ***nextp);
+extern char *build_full_name(struct device_node *dp);
+
 #endif /* __KERNEL__ */
 #endif /* _SPARC_PROM_H */
diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h
index 982a12f959f4..3a5ae3d12088 100644
--- a/arch/sparc/include/asm/socket.h
+++ b/arch/sparc/include/asm/socket.h
@@ -29,6 +29,9 @@
 #define SO_RCVBUFFORCE  0x100b
 #define SO_ERROR        0x1007
 #define SO_TYPE         0x1008
+#define SO_PROTOCOL     0x1028
+#define SO_DOMAIN       0x1029
+
 
 /* Linux specific, keep the same. */
 #define SO_NO_CHECK     0x000b
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index 46f91ab66a50..857630cff636 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -76,7 +76,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
  *
  * Unfortunately this scheme limits us to ~16,000,000 cpus.
  */
-static inline void __read_lock(raw_rwlock_t *rw)
+static inline void arch_read_lock(raw_rwlock_t *rw)
 {
         register raw_rwlock_t *lp asm("g1");
         lp = rw;
@@ -92,11 +92,11 @@ static inline void __read_lock(raw_rwlock_t *rw)
 #define __raw_read_lock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        __read_lock(lock); \
+        arch_read_lock(lock); \
         local_irq_restore(flags); \
 } while(0)
 
-static inline void __read_unlock(raw_rwlock_t *rw)
+static inline void arch_read_unlock(raw_rwlock_t *rw)
 {
         register raw_rwlock_t *lp asm("g1");
         lp = rw;
@@ -112,7 +112,7 @@ static inline void __read_unlock(raw_rwlock_t *rw)
 #define __raw_read_unlock(lock) \
 do {    unsigned long flags; \
         local_irq_save(flags); \
-        __read_unlock(lock); \
+        arch_read_unlock(lock); \
         local_irq_restore(flags); \
 } while(0)
 
@@ -150,7 +150,7 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
         return (val == 0);
 }
 
-static inline int __read_trylock(raw_rwlock_t *rw)
+static inline int arch_read_trylock(raw_rwlock_t *rw)
 {
         register raw_rwlock_t *lp asm("g1");
         register int res asm("o0");
@@ -169,7 +169,7 @@ static inline int __read_trylock(raw_rwlock_t *rw)
 ({      unsigned long flags; \
         int res; \
         local_irq_save(flags); \
-        res = __read_trylock(lock); \
+        res = arch_read_trylock(lock); \
         local_irq_restore(flags); \
         res; \
 })
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index f6b2b92ad8d2..43e514783582 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -92,7 +92,7 @@ static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long fla
 
 /* Multi-reader locks, these are much saner than the 32-bit Sparc ones... */
 
-static void inline __read_lock(raw_rwlock_t *lock)
+static void inline arch_read_lock(raw_rwlock_t *lock)
 {
         unsigned long tmp1, tmp2;
 
@@ -115,7 +115,7 @@ static void inline __read_lock(raw_rwlock_t *lock)
         : "memory");
 }
 
-static int inline __read_trylock(raw_rwlock_t *lock)
+static int inline arch_read_trylock(raw_rwlock_t *lock)
 {
         int tmp1, tmp2;
 
@@ -136,7 +136,7 @@ static int inline __read_trylock(raw_rwlock_t *lock)
         return tmp1;
 }
 
-static void inline __read_unlock(raw_rwlock_t *lock)
+static void inline arch_read_unlock(raw_rwlock_t *lock)
 {
         unsigned long tmp1, tmp2;
 
@@ -152,7 +152,7 @@ static void inline __read_unlock(raw_rwlock_t *lock)
         : "memory");
 }
 
-static void inline __write_lock(raw_rwlock_t *lock)
+static void inline arch_write_lock(raw_rwlock_t *lock)
 {
         unsigned long mask, tmp1, tmp2;
 
@@ -177,7 +177,7 @@ static void inline __write_lock(raw_rwlock_t *lock)
         : "memory");
 }
 
-static void inline __write_unlock(raw_rwlock_t *lock)
+static void inline arch_write_unlock(raw_rwlock_t *lock)
 {
         __asm__ __volatile__(
 "       stw             %%g0, [%0]"
@@ -186,7 +186,7 @@ static void inline __write_unlock(raw_rwlock_t *lock)
         : "memory");
 }
 
-static int inline __write_trylock(raw_rwlock_t *lock)
+static int inline arch_write_trylock(raw_rwlock_t *lock)
 {
         unsigned long mask, tmp1, tmp2, result;
 
@@ -210,14 +210,14 @@ static int inline __write_trylock(raw_rwlock_t *lock)
         return result;
 }
 
-#define __raw_read_lock(p)      __read_lock(p)
-#define __raw_read_lock_flags(p, f) __read_lock(p)
-#define __raw_read_trylock(p)   __read_trylock(p)
-#define __raw_read_unlock(p)    __read_unlock(p)
-#define __raw_write_lock(p)     __write_lock(p)
-#define __raw_write_lock_flags(p, f) __write_lock(p)
-#define __raw_write_unlock(p)   __write_unlock(p)
-#define __raw_write_trylock(p)  __write_trylock(p)
+#define __raw_read_lock(p)      arch_read_lock(p)
+#define __raw_read_lock_flags(p, f) arch_read_lock(p)
+#define __raw_read_trylock(p)   arch_read_trylock(p)
+#define __raw_read_unlock(p)    arch_read_unlock(p)
+#define __raw_write_lock(p)     arch_write_lock(p)
+#define __raw_write_lock_flags(p, f) arch_write_lock(p)
+#define __raw_write_unlock(p)   arch_write_unlock(p)
+#define __raw_write_trylock(p)  arch_write_trylock(p)
 
 #define __raw_read_can_lock(rw)         (!((rw)->lock & 0x80000000UL))
 #define __raw_write_can_lock(rw)        (!(rw)->lock)
diff --git a/arch/sparc/include/asm/system_32.h b/arch/sparc/include/asm/system_32.h
index 751c8c17f5a0..890036b3689a 100644
--- a/arch/sparc/include/asm/system_32.h
+++ b/arch/sparc/include/asm/system_32.h
@@ -32,6 +32,7 @@ enum sparc_cpu {
   sun4u       = 0x05, /* V8 ploos ploos */
   sun_unknown = 0x06,
   ap1000      = 0x07, /* almost a sun4m */
+  sparc_leon  = 0x08, /* Leon SoC */
 };
 
 /* Really, userland should not be looking at any of this... */
diff --git a/arch/sparc/include/asm/system_64.h b/arch/sparc/include/asm/system_64.h
index 6c077816ab28..25e848f0cad7 100644
--- a/arch/sparc/include/asm/system_64.h
+++ b/arch/sparc/include/asm/system_64.h
@@ -29,6 +29,10 @@ enum sparc_cpu {
 /* This cannot ever be a sun4c :) That's just history. */
 #define ARCH_SUN4C 0
 
+extern const char *sparc_cpu_type;
+extern const char *sparc_fpu_type;
+extern const char *sparc_pmu_type;
+
 extern char reboot_command[];
 
 /* These are here in an effort to more fully work around Spitfire Errata
diff --git a/arch/sparc/include/asm/types.h b/arch/sparc/include/asm/types.h
index de671d73baed..09c79a9c8516 100644
--- a/arch/sparc/include/asm/types.h
+++ b/arch/sparc/include/asm/types.h
@@ -8,9 +8,8 @@
  * need to be careful to avoid a name clashes.
  */
 
-#if defined(__sparc__) && defined(__arch64__)
+#if defined(__sparc__)
 
-/*** SPARC 64 bit ***/
 #include <asm-generic/int-ll64.h>
 
 #ifndef __ASSEMBLY__
@@ -26,33 +25,21 @@ typedef unsigned short umode_t;
 /* Dma addresses come in generic and 64-bit flavours.  */
 
 typedef u32 dma_addr_t;
-typedef u64 dma64_addr_t;
 
-#endif /* __ASSEMBLY__ */
+#if defined(__arch64__)
 
-#endif /* __KERNEL__ */
+/*** SPARC 64 bit ***/
+typedef u64 dma64_addr_t;
 #else
-
 /*** SPARC 32 bit ***/
-#include <asm-generic/int-ll64.h>
-
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-#endif /* __ASSEMBLY__ */
-
-#ifdef __KERNEL__
-
-#ifndef __ASSEMBLY__
-
-typedef u32 dma_addr_t;
 typedef u32 dma64_addr_t;
 
+#endif /* defined(__arch64__) */
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __KERNEL__ */
 
-#endif /* defined(__sparc__) && defined(__arch64__) */
+#endif /* defined(__sparc__) */
 
 #endif /* defined(_SPARC_TYPES_H) */
diff --git a/arch/sparc/include/asm/uaccess_64.h b/arch/sparc/include/asm/uaccess_64.h
index a38c03238918..9ea271e19c70 100644
--- a/arch/sparc/include/asm/uaccess_64.h
+++ b/arch/sparc/include/asm/uaccess_64.h
@@ -7,8 +7,8 @@
 
 #ifdef __KERNEL__
 #include <linux/compiler.h>
-#include <linux/sched.h>
 #include <linux/string.h>
+#include <linux/thread_info.h>
 #include <asm/asi.h>
 #include <asm/system.h>
 #include <asm/spitfire.h>
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index b2c406de7d4f..706df669f3b8 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -395,8 +395,9 @@
 #define __NR_preadv             324
 #define __NR_pwritev            325
 #define __NR_rt_tgsigqueueinfo  326
+#define __NR_perf_counter_open  327
 
-#define NR_SYSCALLS             327
+#define NR_SYSCALLS             328
 
 #ifdef __32bit_syscall_numbers__
 /* Sparc 32-bit only has the "setresuid32", "getresuid32" variants,
diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 475ce4696acd..247cc620cee5 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -41,6 +41,8 @@ obj-y                   += of_device_common.o
 obj-y                   += of_device_$(BITS).o
 obj-$(CONFIG_SPARC64)   += prom_irqtrans.o
 
+obj-$(CONFIG_SPARC_LEON)+= leon_kernel.o
+
 obj-$(CONFIG_SPARC64)   += reboot.o
 obj-$(CONFIG_SPARC64)   += sysfs.o
 obj-$(CONFIG_SPARC64)   += iommu.o
@@ -61,7 +63,7 @@ obj-$(CONFIG_SPARC64_SMP) += cpumap.o
 obj-$(CONFIG_SPARC32)     += devres.o
 devres-y                  := ../../../kernel/irq/devres.o
 
-obj-$(CONFIG_SPARC32)     += dma.o
+obj-y                     += dma.o
 
 obj-$(CONFIG_SPARC32_PCI) += pcic.o
 
@@ -101,3 +103,6 @@ obj-$(CONFIG_SUN_LDOMS) += ldc.o vio.o viohs.o ds.o
 obj-$(CONFIG_AUDIT)     += audit.o
 audit--$(CONFIG_AUDIT)  := compat_audit.o
 obj-$(CONFIG_COMPAT)    += $(audit--y)
+
+pc--$(CONFIG_PERF_COUNTERS) := perf_counter.o
+obj-$(CONFIG_SPARC64)   += $(pc--y)
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index d85c3dc4953a..1446df90ef85 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -312,7 +312,12 @@ void __cpuinit cpu_probe(void)
 
         psr = get_psr();
         put_psr(psr | PSR_EF);
+#ifdef CONFIG_SPARC_LEON
+        fpu_vers = 7;
+#else
         fpu_vers = ((get_fsr() >> 17) & 0x7);
+#endif
+
         put_psr(psr);
 
         set_cpu_and_fpu(psr_impl, psr_vers, fpu_vers);
diff --git a/arch/sparc/kernel/dma.c b/arch/sparc/kernel/dma.c
index 524c32f97c55..e1ba8ee21b9a 100644
--- a/arch/sparc/kernel/dma.c
+++ b/arch/sparc/kernel/dma.c
@@ -1,178 +1,13 @@
-/* dma.c: PCI and SBUS DMA accessors for 32-bit sparc.
- *
- * Copyright (C) 2008 David S. Miller <davem@davemloft.net>
- */
-
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
-#include <linux/mm.h>
-
-#ifdef CONFIG_PCI
-#include <linux/pci.h>
-#endif
+#include <linux/dma-debug.h>
 
-#include "dma.h"
+#define PREALLOC_DMA_DEBUG_ENTRIES       (1 << 15)
 
-int dma_supported(struct device *dev, u64 mask)
+static int __init dma_init(void)
 {
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                return pci_dma_supported(to_pci_dev(dev), mask);
-#endif
+        dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
         return 0;
 }
-EXPORT_SYMBOL(dma_supported);
-
-int dma_set_mask(struct device *dev, u64 dma_mask)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
-#endif
-        return -EOPNOTSUPP;
-}
-EXPORT_SYMBOL(dma_set_mask);
-
-static void *dma32_alloc_coherent(struct device *dev, size_t size,
-                                  dma_addr_t *dma_handle, gfp_t flag)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                return pci_alloc_consistent(to_pci_dev(dev), size, dma_handle);
-#endif
-        return sbus_alloc_consistent(dev, size, dma_handle);
-}
-
-static void dma32_free_coherent(struct device *dev, size_t size,
-                                void *cpu_addr, dma_addr_t dma_handle)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_free_consistent(to_pci_dev(dev), size,
-                                    cpu_addr, dma_handle);
-                return;
-        }
-#endif
-        sbus_free_consistent(dev, size, cpu_addr, dma_handle);
-}
-
-static dma_addr_t dma32_map_page(struct device *dev, struct page *page,
-                                 unsigned long offset, size_t size,
-                                 enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                return pci_map_page(to_pci_dev(dev), page, offset,
-                                    size, (int)direction);
-#endif
-        return sbus_map_single(dev, page_address(page) + offset,
-                               size, (int)direction);
-}
-
-static void dma32_unmap_page(struct device *dev, dma_addr_t dma_address,
-                             size_t size, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_unmap_page(to_pci_dev(dev), dma_address,
-                               size, (int)direction);
-                return;
-        }
-#endif
-        sbus_unmap_single(dev, dma_address, size, (int)direction);
-}
-
-static int dma32_map_sg(struct device *dev, struct scatterlist *sg,
-                        int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type)
-                return pci_map_sg(to_pci_dev(dev), sg, nents, (int)direction);
-#endif
-        return sbus_map_sg(dev, sg, nents, direction);
-}
-
-void dma32_unmap_sg(struct device *dev, struct scatterlist *sg,
-                    int nents, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_unmap_sg(to_pci_dev(dev), sg, nents, (int)direction);
-                return;
-        }
-#endif
-        sbus_unmap_sg(dev, sg, nents, (int)direction);
-}
-
-static void dma32_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
-                                      size_t size,
-                                      enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_dma_sync_single_for_cpu(to_pci_dev(dev), dma_handle,
-                                            size, (int)direction);
-                return;
-        }
-#endif
-        sbus_dma_sync_single_for_cpu(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_single_for_device(struct device *dev,
-                                         dma_addr_t dma_handle, size_t size,
-                                         enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_dma_sync_single_for_device(to_pci_dev(dev), dma_handle,
-                                               size, (int)direction);
-                return;
-        }
-#endif
-        sbus_dma_sync_single_for_device(dev, dma_handle, size, (int) direction);
-}
-
-static void dma32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-                                  int nelems, enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_dma_sync_sg_for_cpu(to_pci_dev(dev), sg,
-                                        nelems, (int)direction);
-                return;
-        }
-#endif
-        BUG();
-}
-
-static void dma32_sync_sg_for_device(struct device *dev,
-                                     struct scatterlist *sg, int nelems,
-                                     enum dma_data_direction direction)
-{
-#ifdef CONFIG_PCI
-        if (dev->bus == &pci_bus_type) {
-                pci_dma_sync_sg_for_device(to_pci_dev(dev), sg,
-                                           nelems, (int)direction);
-                return;
-        }
-#endif
-        BUG();
-}
-
-static const struct dma_ops dma32_dma_ops = {
-        .alloc_coherent         = dma32_alloc_coherent,
-        .free_coherent          = dma32_free_coherent,
-        .map_page               = dma32_map_page,
-        .unmap_page             = dma32_unmap_page,
-        .map_sg                 = dma32_map_sg,
-        .unmap_sg               = dma32_unmap_sg,
-        .sync_single_for_cpu    = dma32_sync_single_for_cpu,
-        .sync_single_for_device = dma32_sync_single_for_device,
-        .sync_sg_for_cpu        = dma32_sync_sg_for_cpu,
-        .sync_sg_for_device     = dma32_sync_sg_for_device,
-};
-
-const struct dma_ops *dma_ops = &dma32_dma_ops;
-EXPORT_SYMBOL(dma_ops);
+fs_initcall(dma_init);
diff --git a/arch/sparc/kernel/dma.h b/arch/sparc/kernel/dma.h
deleted file mode 100644
index f8d8951adb53..000000000000
--- a/arch/sparc/kernel/dma.h
+++ /dev/null
@@ -1,14 +0,0 @@
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp);
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba);
-dma_addr_t sbus_map_single(struct device *dev, void *va,
-                           size_t len, int direction);
-void sbus_unmap_single(struct device *dev, dma_addr_t ba,
-                       size_t n, int direction);
-int sbus_map_sg(struct device *dev, struct scatterlist *sg,
-                int n, int direction);
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg,
-                   int n, int direction);
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
-                                  size_t size, int direction);
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba,
-                                     size_t size, int direction);
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index 6b4d8acc4c83..439d82a95ac9 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -809,6 +809,11 @@ found_version:
                  nop
 
 got_prop:
+#ifdef CONFIG_SPARC_LEON
+                /* no cpu-type check is needed, it is a SPARC-LEON */
+                ba sun4c_continue_boot
+                 nop
+#endif
                 set     cputypval, %o2
                 ldub    [%o2 + 0x4], %l1
 
diff --git a/arch/sparc/kernel/idprom.c b/arch/sparc/kernel/idprom.c
index 57922f69c3f7..52a15fe2db19 100644
--- a/arch/sparc/kernel/idprom.c
+++ b/arch/sparc/kernel/idprom.c
@@ -31,6 +31,8 @@ static struct Sun_Machine_Models Sun_Machines[NUM_SUN_MACHINES] = {
 { .name = "Sun 4/200 Series",        .id_machtype = (SM_SUN4 | SM_4_260) },
 { .name = "Sun 4/300 Series",        .id_machtype = (SM_SUN4 | SM_4_330) },
 { .name = "Sun 4/400 Series",        .id_machtype = (SM_SUN4 | SM_4_470) },
+/* Now Leon */
+{ .name = "Leon3 System-on-a-Chip",  .id_machtype = (M_LEON | M_LEON3_SOC) },
 /* Now, Sun4c's */
 { .name = "Sun4c SparcStation 1",    .id_machtype = (SM_SUN4C | SM_4C_SS1) },
 { .name = "Sun4c SparcStation IPC",  .id_machtype = (SM_SUN4C | SM_4C_IPC) },
diff --git a/arch/sparc/kernel/iommu.c b/arch/sparc/kernel/iommu.c
index 0aeaefe696b9..7690cc219ecc 100644
--- a/arch/sparc/kernel/iommu.c
+++ b/arch/sparc/kernel/iommu.c
@@ -353,7 +353,8 @@ static void dma_4u_free_coherent(struct device *dev, size_t size,
 
 static dma_addr_t dma_4u_map_page(struct device *dev, struct page *page,
                                   unsigned long offset, size_t sz,
-                                  enum dma_data_direction direction)
+                                  enum dma_data_direction direction,
+                                  struct dma_attrs *attrs)
 {
         struct iommu *iommu;
         struct strbuf *strbuf;
@@ -474,7 +475,8 @@ do_flush_sync:
 }
 
 static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
-                              size_t sz, enum dma_data_direction direction)
+                              size_t sz, enum dma_data_direction direction,
+                              struct dma_attrs *attrs)
 {
         struct iommu *iommu;
         struct strbuf *strbuf;
@@ -520,7 +522,8 @@ static void dma_4u_unmap_page(struct device *dev, dma_addr_t bus_addr,
 }
 
 static int dma_4u_map_sg(struct device *dev, struct scatterlist *sglist,
-                         int nelems, enum dma_data_direction direction)
+                         int nelems, enum dma_data_direction direction,
+                         struct dma_attrs *attrs)
 {
         struct scatterlist *s, *outs, *segstart;
         unsigned long flags, handle, prot, ctx;
@@ -691,7 +694,8 @@ static unsigned long fetch_sg_ctx(struct iommu *iommu, struct scatterlist *sg)
 }
 
 static void dma_4u_unmap_sg(struct device *dev, struct scatterlist *sglist,
-                            int nelems, enum dma_data_direction direction)
+                            int nelems, enum dma_data_direction direction,
+                            struct dma_attrs *attrs)
 {
         unsigned long flags, ctx;
         struct scatterlist *sg;
@@ -822,7 +826,7 @@ static void dma_4u_sync_sg_for_cpu(struct device *dev,
         spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static const struct dma_ops sun4u_dma_ops = {
+static struct dma_map_ops sun4u_dma_ops = {
         .alloc_coherent         = dma_4u_alloc_coherent,
         .free_coherent          = dma_4u_free_coherent,
         .map_page               = dma_4u_map_page,
@@ -833,9 +837,11 @@ static const struct dma_ops sun4u_dma_ops = {
         .sync_sg_for_cpu        = dma_4u_sync_sg_for_cpu,
 };
 
-const struct dma_ops *dma_ops = &sun4u_dma_ops;
+struct dma_map_ops *dma_ops = &sun4u_dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
+extern int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask);
+
 int dma_supported(struct device *dev, u64 device_mask)
 {
         struct iommu *iommu = dev->archdata.iommu;
@@ -849,7 +855,7 @@ int dma_supported(struct device *dev, u64 device_mask)
 
 #ifdef CONFIG_PCI
         if (dev->bus == &pci_bus_type)
-                return pci_dma_supported(to_pci_dev(dev), device_mask);
+                return pci64_dma_supported(to_pci_dev(dev), device_mask);
 #endif
 
         return 0;
diff --git a/arch/sparc/kernel/ioport.c b/arch/sparc/kernel/ioport.c
index 87ea0d03d975..9f61fd8cbb7b 100644
--- a/arch/sparc/kernel/ioport.c
+++ b/arch/sparc/kernel/ioport.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>          /* struct pci_dev */
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/scatterlist.h>
 #include <linux/of_device.h>
 
@@ -48,8 +49,6 @@
 #include <asm/iommu.h>
 #include <asm/io-unit.h>
 
-#include "dma.h"
-
 #define mmu_inval_dma_area(p, l)        /* Anton pulled it out for 2.4.0-xx */
 
 static struct resource *_sparc_find_resource(struct resource *r,
@@ -246,7 +245,8 @@ EXPORT_SYMBOL(sbus_set_sbus64);
  * Typically devices use them for control blocks.
  * CPU may access them without any explicit flushing.
  */
-void *sbus_alloc_consistent(struct device *dev, long len, u32 *dma_addrp)
+static void *sbus_alloc_coherent(struct device *dev, size_t len,
+                                 dma_addr_t *dma_addrp, gfp_t gfp)
 {
         struct of_device *op = to_of_device(dev);
         unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
@@ -299,7 +299,8 @@ err_nopages:
         return NULL;
 }
 
-void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
+static void sbus_free_coherent(struct device *dev, size_t n, void *p,
+                               dma_addr_t ba)
 {
         struct resource *res;
         struct page *pgv;
@@ -317,7 +318,7 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
 
         n = (n + PAGE_SIZE-1) & PAGE_MASK;
         if ((res->end-res->start)+1 != n) {
-                printk("sbus_free_consistent: region 0x%lx asked 0x%lx\n",
+                printk("sbus_free_consistent: region 0x%lx asked 0x%zx\n",
                     (long)((res->end-res->start)+1), n);
                 return;
         }
@@ -337,8 +338,13 @@ void sbus_free_consistent(struct device *dev, long n, void *p, u32 ba)
  * CPU view of this memory may be inconsistent with
  * a device view and explicit flushing is necessary.
  */
-dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int direction)
+static dma_addr_t sbus_map_page(struct device *dev, struct page *page,
+                                unsigned long offset, size_t len,
+                                enum dma_data_direction dir,
+                                struct dma_attrs *attrs)
 {
+        void *va = page_address(page) + offset;
+
         /* XXX why are some lengths signed, others unsigned? */
         if (len <= 0) {
                 return 0;
@@ -350,12 +356,14 @@ dma_addr_t sbus_map_single(struct device *dev, void *va, size_t len, int directi
         return mmu_get_scsi_one(dev, va, len);
 }
 
-void sbus_unmap_single(struct device *dev, dma_addr_t ba, size_t n, int direction)
+static void sbus_unmap_page(struct device *dev, dma_addr_t ba, size_t n,
+                            enum dma_data_direction dir, struct dma_attrs *attrs)
 {
         mmu_release_scsi_one(dev, ba, n);
 }
 
-int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n,
+                       enum dma_data_direction dir, struct dma_attrs *attrs)
 {
         mmu_get_scsi_sgl(dev, sg, n);
 
@@ -366,19 +374,38 @@ int sbus_map_sg(struct device *dev, struct scatterlist *sg, int n, int direction
         return n;
 }
 
-void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n, int direction)
+static void sbus_unmap_sg(struct device *dev, struct scatterlist *sg, int n,
+                          enum dma_data_direction dir, struct dma_attrs *attrs)
 {
         mmu_release_scsi_sgl(dev, sg, n);
 }
 
-void sbus_dma_sync_single_for_cpu(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+                                 int n, enum dma_data_direction dir)
 {
+        BUG();
 }
 
-void sbus_dma_sync_single_for_device(struct device *dev, dma_addr_t ba, size_t size, int direction)
+static void sbus_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+                                    int n, enum dma_data_direction dir)
 {
+        BUG();
 }
 
+struct dma_map_ops sbus_dma_ops = {
+        .alloc_coherent         = sbus_alloc_coherent,
+        .free_coherent          = sbus_free_coherent,
+        .map_page               = sbus_map_page,
+        .unmap_page             = sbus_unmap_page,
+        .map_sg                 = sbus_map_sg,
+        .unmap_sg               = sbus_unmap_sg,
+        .sync_sg_for_cpu        = sbus_sync_sg_for_cpu,
+        .sync_sg_for_device     = sbus_sync_sg_for_device,
+};
+
+struct dma_map_ops *dma_ops = &sbus_dma_ops;
+EXPORT_SYMBOL(dma_ops);
+
 static int __init sparc_register_ioport(void)
 {
         register_proc_sparc_ioport();
@@ -395,7 +422,8 @@ arch_initcall(sparc_register_ioport);
 /* Allocate and map kernel buffer using consistent mode DMA for a device.
  * hwdev should be valid struct pci_dev pointer for PCI devices.
  */
-void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
+static void *pci32_alloc_coherent(struct device *dev, size_t len,
+                                  dma_addr_t *pba, gfp_t gfp)
 {
         unsigned long len_total = (len + PAGE_SIZE-1) & PAGE_MASK;
         unsigned long va;
@@ -439,7 +467,6 @@ void *pci_alloc_consistent(struct pci_dev *pdev, size_t len, dma_addr_t *pba)
         *pba = virt_to_phys(va); /* equals virt_to_bus (R.I.P.) for us. */
         return (void *) res->start;
 }
-EXPORT_SYMBOL(pci_alloc_consistent);
 
 /* Free and unmap a consistent DMA buffer.
  * cpu_addr is what was returned from pci_alloc_consistent,
@@ -449,7 +476,8 @@ EXPORT_SYMBOL(pci_alloc_consistent);
  * References to the memory and mappings associated with cpu_addr/dma_addr
  * past this call are illegal.
  */
-void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
+static void pci32_free_coherent(struct device *dev, size_t n, void *p,
+                                dma_addr_t ba)
 {
         struct resource *res;
         unsigned long pgp;
@@ -481,60 +509,18 @@ void pci_free_consistent(struct pci_dev *pdev, size_t n, void *p, dma_addr_t ba)
 
         free_pages(pgp, get_order(n));
 }
-EXPORT_SYMBOL(pci_free_consistent);
-
-/* Map a single buffer of the indicated size for DMA in streaming mode.
- * The 32-bit bus address to use is returned.
- *
- * Once the device is given the dma address, the device owns this memory
- * until either pci_unmap_single or pci_dma_sync_single_* is performed.
- */
-dma_addr_t pci_map_single(struct pci_dev *hwdev, void *ptr, size_t size,
-    int direction)
-{
-        BUG_ON(direction == PCI_DMA_NONE);
-        /* IIep is write-through, not flushing. */
-        return virt_to_phys(ptr);
-}
-EXPORT_SYMBOL(pci_map_single);
-
-/* Unmap a single streaming mode DMA translation.  The dma_addr and size
- * must match what was provided for in a previous pci_map_single call.  All
- * other usages are undefined.
- *
- * After this call, reads by the cpu to the buffer are guaranteed to see
- * whatever the device wrote there.
- */
-void pci_unmap_single(struct pci_dev *hwdev, dma_addr_t ba, size_t size,
-    int direction)
-{
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
-                mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
-                    (size + PAGE_SIZE-1) & PAGE_MASK);
-        }
-}
-EXPORT_SYMBOL(pci_unmap_single);
 
 /*
  * Same as pci_map_single, but with pages.
  */
-dma_addr_t pci_map_page(struct pci_dev *hwdev, struct page *page,
-                        unsigned long offset, size_t size, int direction)
+static dma_addr_t pci32_map_page(struct device *dev, struct page *page,
+                                 unsigned long offset, size_t size,
+                                 enum dma_data_direction dir,
+                                 struct dma_attrs *attrs)
 {
-        BUG_ON(direction == PCI_DMA_NONE);
         /* IIep is write-through, not flushing. */
         return page_to_phys(page) + offset;
 }
-EXPORT_SYMBOL(pci_map_page);
-
-void pci_unmap_page(struct pci_dev *hwdev,
-                        dma_addr_t dma_address, size_t size, int direction)
-{
-        BUG_ON(direction == PCI_DMA_NONE);
-        /* mmu_inval_dma_area XXX */
-}
-EXPORT_SYMBOL(pci_unmap_page);
 
 /* Map a set of buffers described by scatterlist in streaming
  * mode for DMA.  This is the scather-gather version of the
@@ -551,13 +537,13 @@ EXPORT_SYMBOL(pci_unmap_page);
  * Device ownership issues as mentioned above for pci_map_single are
  * the same here.
  */
-int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
-    int direction)
+static int pci32_map_sg(struct device *device, struct scatterlist *sgl,
+                        int nents, enum dma_data_direction dir,
+                        struct dma_attrs *attrs)
 {
         struct scatterlist *sg;
         int n;
 
-        BUG_ON(direction == PCI_DMA_NONE);
         /* IIep is write-through, not flushing. */
         for_each_sg(sgl, sg, nents, n) {
                 BUG_ON(page_address(sg_page(sg)) == NULL);
@@ -566,20 +552,19 @@ int pci_map_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
         }
         return nents;
 }
-EXPORT_SYMBOL(pci_map_sg);
 
 /* Unmap a set of streaming mode DMA translations.
  * Again, cpu read rules concerning calls here are the same as for
  * pci_unmap_single() above.
  */
-void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
-    int direction)
+static void pci32_unmap_sg(struct device *dev, struct scatterlist *sgl,
+                           int nents, enum dma_data_direction dir,
+                           struct dma_attrs *attrs)
 {
         struct scatterlist *sg;
         int n;
 
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
+        if (dir != PCI_DMA_TODEVICE) {
                 for_each_sg(sgl, sg, nents, n) {
                         BUG_ON(page_address(sg_page(sg)) == NULL);
                         mmu_inval_dma_area(
@@ -588,7 +573,6 @@ void pci_unmap_sg(struct pci_dev *hwdev, struct scatterlist *sgl, int nents,
                 }
         }
 }
-EXPORT_SYMBOL(pci_unmap_sg);
 
 /* Make physical memory consistent for a single
  * streaming mode DMA translation before or after a transfer.
@@ -600,25 +584,23 @@ EXPORT_SYMBOL(pci_unmap_sg);
  * must first perform a pci_dma_sync_for_device, and then the
  * device again owns the buffer.
  */
-void pci_dma_sync_single_for_cpu(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_cpu(struct device *dev, dma_addr_t ba,
+                                      size_t size, enum dma_data_direction dir)
 {
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
+        if (dir != PCI_DMA_TODEVICE) {
                 mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
                     (size + PAGE_SIZE-1) & PAGE_MASK);
         }
 }
-EXPORT_SYMBOL(pci_dma_sync_single_for_cpu);
 
-void pci_dma_sync_single_for_device(struct pci_dev *hwdev, dma_addr_t ba, size_t size, int direction)
+static void pci32_sync_single_for_device(struct device *dev, dma_addr_t ba,
+                                         size_t size, enum dma_data_direction dir)
 {
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
+        if (dir != PCI_DMA_TODEVICE) {
                 mmu_inval_dma_area((unsigned long)phys_to_virt(ba),
                     (size + PAGE_SIZE-1) & PAGE_MASK);
         }
 }
-EXPORT_SYMBOL(pci_dma_sync_single_for_device);
 
 /* Make physical memory consistent for a set of streaming
  * mode DMA translations after a transfer.
@@ -626,13 +608,13 @@ EXPORT_SYMBOL(pci_dma_sync_single_for_device);
  * The same as pci_dma_sync_single_* but for a scatter-gather list,
  * same rules and usage.
  */
-void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+                                  int nents, enum dma_data_direction dir)
 {
         struct scatterlist *sg;
         int n;
 
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
+        if (dir != PCI_DMA_TODEVICE) {
                 for_each_sg(sgl, sg, nents, n) {
                         BUG_ON(page_address(sg_page(sg)) == NULL);
                         mmu_inval_dma_area(
@@ -641,15 +623,14 @@ void pci_dma_sync_sg_for_cpu(struct pci_dev *hwdev, struct scatterlist *sgl, int
                 }
         }
 }
-EXPORT_SYMBOL(pci_dma_sync_sg_for_cpu);
 
-void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl, int nents, int direction)
+static void pci32_sync_sg_for_device(struct device *device, struct scatterlist *sgl,
+                                     int nents, enum dma_data_direction dir)
 {
         struct scatterlist *sg;
         int n;
 
-        BUG_ON(direction == PCI_DMA_NONE);
-        if (direction != PCI_DMA_TODEVICE) {
+        if (dir != PCI_DMA_TODEVICE) {
                 for_each_sg(sgl, sg, nents, n) {
                         BUG_ON(page_address(sg_page(sg)) == NULL);
                         mmu_inval_dma_area(
@@ -658,31 +639,78 @@ void pci_dma_sync_sg_for_device(struct pci_dev *hwdev, struct scatterlist *sgl,
                 }
         }
 }
-EXPORT_SYMBOL(pci_dma_sync_sg_for_device);
+
+struct dma_map_ops pci32_dma_ops = {
+        .alloc_coherent         = pci32_alloc_coherent,
+        .free_coherent          = pci32_free_coherent,
+        .map_page               = pci32_map_page,
+        .map_sg                 = pci32_map_sg,
+        .unmap_sg               = pci32_unmap_sg,
+        .sync_single_for_cpu    = pci32_sync_single_for_cpu,
+        .sync_single_for_device = pci32_sync_single_for_device,
+        .sync_sg_for_cpu        = pci32_sync_sg_for_cpu,
+        .sync_sg_for_device     = pci32_sync_sg_for_device,
+};
+EXPORT_SYMBOL(pci32_dma_ops);
+
 #endif /* CONFIG_PCI */
 
+/*
+ * Return whether the given PCI device DMA address mask can be
+ * supported properly.  For example, if your device can only drive the
+ * low 24-bits during PCI bus mastering, then you would pass
+ * 0x00ffffff as the mask to this function.
+ */
+int dma_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_PCI
+        if (dev->bus == &pci_bus_type)
+                return 1;
+#endif
+        return 0;
+}
+EXPORT_SYMBOL(dma_supported);
+
+int dma_set_mask(struct device *dev, u64 dma_mask)
+{
+#ifdef CONFIG_PCI
+        if (dev->bus == &pci_bus_type)
+                return pci_set_dma_mask(to_pci_dev(dev), dma_mask);
+#endif
+        return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(dma_set_mask);
+
+
 #ifdef CONFIG_PROC_FS
 
-static int
-_sparc_io_get_info(char *buf, char **start, off_t fpos, int length, int *eof,
-    void *data)
+static int sparc_io_proc_show(struct seq_file *m, void *v)
 {
-        char *p = buf, *e = buf + length;
-        struct resource *r;
+        struct resource *root = m->private, *r;
         const char *nm;
 
-        for (r = ((struct resource *)data)->child; r != NULL; r = r->sibling) {
-                if (p + 32 >= e)        /* Better than nothing */
-                        break;
+        for (r = root->child; r != NULL; r = r->sibling) {
                 if ((nm = r->name) == 0) nm = "???";
-                p += sprintf(p, "%016llx-%016llx: %s\n",
+                seq_printf(m, "%016llx-%016llx: %s\n",
                                 (unsigned long long)r->start,
                                 (unsigned long long)r->end, nm);
         }
 
-        return p-buf;
+        return 0;
 }
 
+static int sparc_io_proc_open(struct inode *inode, struct file *file)
+{
+        return single_open(file, sparc_io_proc_show, PDE(inode)->data);
+}
+
+static const struct file_operations sparc_io_proc_fops = {
+        .owner          = THIS_MODULE,
+        .open           = sparc_io_proc_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
 #endif /* CONFIG_PROC_FS */
 
 /*
@@ -707,7 +735,7 @@ static struct resource *_sparc_find_resource(struct resource *root,
 static void register_proc_sparc_ioport(void)
 {
 #ifdef CONFIG_PROC_FS
-        create_proc_read_entry("io_map",0,NULL,_sparc_io_get_info,&sparc_iomap);
-        create_proc_read_entry("dvma_map",0,NULL,_sparc_io_get_info,&_sparc_dvma);
+        proc_create_data("io_map", 0, NULL, &sparc_io_proc_fops, &sparc_iomap);
+        proc_create_data("dvma_map", 0, NULL, &sparc_io_proc_fops, &_sparc_dvma);
 #endif
 }
diff --git a/arch/sparc/kernel/irq_32.c b/arch/sparc/kernel/irq_32.c
index ad800b80c718..e1af43728329 100644
--- a/arch/sparc/kernel/irq_32.c
+++ b/arch/sparc/kernel/irq_32.c
@@ -45,6 +45,7 @@
 #include <asm/pcic.h>
 #include <asm/cacheflush.h>
 #include <asm/irq_regs.h>
+#include <asm/leon.h>
 
 #include "kernel.h"
 #include "irq.h"
@@ -661,6 +662,10 @@ void __init init_IRQ(void)
                 sun4d_init_IRQ();
                 break;
 
+        case sparc_leon:
+                leon_init_IRQ();
+                break;
+
         default:
                 prom_printf("Cannot initialize IRQs on this Sun machine...");
                 break;
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
new file mode 100644
index 000000000000..54d8a5bd4824
--- /dev/null
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -0,0 +1,203 @@
+/*
+ * Copyright (C) 2009 Daniel Hellstrom (daniel@gaisler.com) Aeroflex Gaisler AB
+ * Copyright (C) 2009 Konrad Eisele (konrad@gaisler.com) Aeroflex Gaisler AB
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/interrupt.h>
+#include <linux/of_device.h>
+#include <asm/oplib.h>
+#include <asm/timer.h>
+#include <asm/prom.h>
+#include <asm/leon.h>
+#include <asm/leon_amba.h>
+
+#include "prom.h"
+#include "irq.h"
+
+struct leon3_irqctrl_regs_map *leon3_irqctrl_regs; /* interrupt controller base address, initialized by amba_init() */
+struct leon3_gptimer_regs_map *leon3_gptimer_regs; /* timer controller base address, initialized by amba_init() */
+struct amba_apb_device leon_percpu_timer_dev[16];
+
+int leondebug_irq_disable;
+int leon_debug_irqout;
+static int dummy_master_l10_counter;
+
+unsigned long leon3_gptimer_irq; /* interrupt controller irq number, initialized by amba_init() */
+unsigned int sparc_leon_eirq;
+#define LEON_IMASK ((&leon3_irqctrl_regs->mask[0]))
+
+/* Return the IRQ of the pending IRQ on the extended IRQ controller */
+int sparc_leon_eirq_get(int eirq, int cpu)
+{
+        return LEON3_BYPASS_LOAD_PA(&leon3_irqctrl_regs->intid[cpu]) & 0x1f;
+}
+
+irqreturn_t sparc_leon_eirq_isr(int dummy, void *dev_id)
+{
+        printk(KERN_ERR "sparc_leon_eirq_isr: ERROR EXTENDED IRQ\n");
+        return IRQ_HANDLED;
+}
+
+/* The extended IRQ controller has been found, this function registers it */
+void sparc_leon_eirq_register(int eirq)
+{
+        int irq;
+
+        /* Register a "BAD" handler for this interrupt, it should never happen */
+        irq = request_irq(eirq, sparc_leon_eirq_isr,
+                          (IRQF_DISABLED | SA_STATIC_ALLOC), "extirq", NULL);
+
+        if (irq) {
+                printk(KERN_ERR
+                       "sparc_leon_eirq_register: unable to attach IRQ%d\n",
+                       eirq);
+        } else {
+                sparc_leon_eirq = eirq;
+        }
+
+}
+
+static inline unsigned long get_irqmask(unsigned int irq)
+{
+        unsigned long mask;
+
+        if (!irq || ((irq > 0xf) && !sparc_leon_eirq)
+            || ((irq > 0x1f) && sparc_leon_eirq)) {
+                printk(KERN_ERR
+                       "leon_get_irqmask: false irq number: %d\n", irq);
+                mask = 0;
+        } else {
+                mask = LEON_HARD_INT(irq);
+        }
+        return mask;
+}
+
+static void leon_enable_irq(unsigned int irq_nr)
+{
+        unsigned long mask, flags;
+        mask = get_irqmask(irq_nr);
+        local_irq_save(flags);
+        LEON3_BYPASS_STORE_PA(LEON_IMASK,
+                              (LEON3_BYPASS_LOAD_PA(LEON_IMASK) | (mask)));
+        local_irq_restore(flags);
+}
+
+static void leon_disable_irq(unsigned int irq_nr)
+{
+        unsigned long mask, flags;
+        mask = get_irqmask(irq_nr);
+        local_irq_save(flags);
+        LEON3_BYPASS_STORE_PA(LEON_IMASK,
+                              (LEON3_BYPASS_LOAD_PA(LEON_IMASK) & ~(mask)));
+        local_irq_restore(flags);
+
+}
+
+void __init leon_init_timers(irq_handler_t counter_fn)
+{
+        int irq;
+
+        leondebug_irq_disable = 0;
+        leon_debug_irqout = 0;
+        master_l10_counter = (unsigned int *)&dummy_master_l10_counter;
+        dummy_master_l10_counter = 0;
+
+        if (leon3_gptimer_regs && leon3_irqctrl_regs) {
+                LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].val, 0);
+                LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].rld,
+                                      (((1000000 / 100) - 1)));
+                LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].ctrl, 0);
+
+        } else {
+                printk(KERN_ERR "No Timer/irqctrl found\n");
+                BUG();
+        }
+
+        irq = request_irq(leon3_gptimer_irq,
+                          counter_fn,
+                          (IRQF_DISABLED | SA_STATIC_ALLOC), "timer", NULL);
+
+        if (irq) {
+                printk(KERN_ERR "leon_time_init: unable to attach IRQ%d\n",
+                       LEON_INTERRUPT_TIMER1);
+                prom_halt();
+        }
+
+        if (leon3_gptimer_regs) {
+                LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[0].ctrl,
+                                      LEON3_GPTIMER_EN |
+                                      LEON3_GPTIMER_RL |
+                                      LEON3_GPTIMER_LD | LEON3_GPTIMER_IRQEN);
+        }
+}
+
+void leon_clear_clock_irq(void)
+{
+}
+
+void leon_load_profile_irq(int cpu, unsigned int limit)
+{
+        BUG();
+}
+
+
+
+
+void __init leon_trans_init(struct device_node *dp)
+{
+        if (strcmp(dp->type, "cpu") == 0 && strcmp(dp->name, "<NULL>") == 0) {
+                struct property *p;
+                p = of_find_property(dp, "mid", (void *)0);
+                if (p) {
+                        int mid;
+                        dp->name = prom_early_alloc(5 + 1);
+                        memcpy(&mid, p->value, p->length);
+                        sprintf((char *)dp->name, "cpu%.2d", mid);
+                }
+        }
+}
+
+void __initdata (*prom_amba_init)(struct device_node *dp, struct device_node ***nextp) = 0;
+
+void __init leon_node_init(struct device_node *dp, struct device_node ***nextp)
+{
+        if (prom_amba_init &&
+            strcmp(dp->type, "ambapp") == 0 &&
+            strcmp(dp->name, "ambapp0") == 0) {
+                prom_amba_init(dp, nextp);
+        }
+}
+
+void __init leon_init_IRQ(void)
+{
+        sparc_init_timers = leon_init_timers;
+
+        BTFIXUPSET_CALL(enable_irq, leon_enable_irq, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(disable_irq, leon_disable_irq, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(enable_pil_irq, leon_enable_irq, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(disable_pil_irq, leon_disable_irq, BTFIXUPCALL_NORM);
+
+        BTFIXUPSET_CALL(clear_clock_irq, leon_clear_clock_irq,
+                        BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(load_profile_irq, leon_load_profile_irq,
+                        BTFIXUPCALL_NOP);
+
+#ifdef CONFIG_SMP
+        BTFIXUPSET_CALL(set_cpu_int, leon_set_cpu_int, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(clear_cpu_int, leon_clear_ipi, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(set_irq_udt, leon_set_udt, BTFIXUPCALL_NORM);
+#endif
+
+}
+
+void __init leon_init(void)
+{
+        prom_build_more = &leon_node_init;
+}
diff --git a/arch/sparc/kernel/nmi.c b/arch/sparc/kernel/nmi.c
index b75bf502cd42..378eb53e0776 100644
--- a/arch/sparc/kernel/nmi.c
+++ b/arch/sparc/kernel/nmi.c
@@ -19,6 +19,7 @@
 #include <linux/delay.h>
 #include <linux/smp.h>
 
+#include <asm/perf_counter.h>
 #include <asm/ptrace.h>
 #include <asm/local.h>
 #include <asm/pcr.h>
@@ -31,13 +32,19 @@
  * level 14 as our IRQ off level.
  */
 
-static int nmi_watchdog_active;
 static int panic_on_timeout;
 
-int nmi_usable;
-EXPORT_SYMBOL_GPL(nmi_usable);
+/* nmi_active:
+ * >0: the NMI watchdog is active, but can be disabled
+ * <0: the NMI watchdog has not been set up, and cannot be enabled
+ *  0: the NMI watchdog is disabled, but can be enabled
+ */
+atomic_t nmi_active = ATOMIC_INIT(0);           /* oprofile uses this */
+EXPORT_SYMBOL(nmi_active);
 
 static unsigned int nmi_hz = HZ;
+static DEFINE_PER_CPU(short, wd_enabled);
+static int endflag __initdata;
 
 static DEFINE_PER_CPU(unsigned int, last_irq_sum);
 static DEFINE_PER_CPU(local_t, alert_counter);
@@ -45,7 +52,7 @@ static DEFINE_PER_CPU(int, nmi_touch);
 
 void touch_nmi_watchdog(void)
 {
-        if (nmi_watchdog_active) {
+        if (atomic_read(&nmi_active)) {
                 int cpu;
 
                 for_each_present_cpu(cpu) {
@@ -78,6 +85,7 @@ static void die_nmi(const char *str, struct pt_regs *regs, int do_panic)
         if (do_panic || panic_on_oops)
                 panic("Non maskable interrupt");
 
+        nmi_exit();
         local_irq_enable();
         do_exit(SIGBUS);
 }
@@ -92,6 +100,8 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
 
         local_cpu_data().__nmi_count++;
 
+        nmi_enter();
+
         if (notify_die(DIE_NMI, "nmi", regs, 0,
                        pt_regs_trap_type(regs), SIGINT) == NOTIFY_STOP)
                 touched = 1;
@@ -110,10 +120,12 @@ notrace __kprobes void perfctr_irq(int irq, struct pt_regs *regs)
                 __get_cpu_var(last_irq_sum) = sum;
                 local_set(&__get_cpu_var(alert_counter), 0);
         }
-        if (nmi_usable) {
+        if (__get_cpu_var(wd_enabled)) {
                 write_pic(picl_value(nmi_hz));
                 pcr_ops->write(pcr_enable);
         }
+
+        nmi_exit();
 }
 
 static inline unsigned int get_nmi_count(int cpu)
@@ -121,8 +133,6 @@ static inline unsigned int get_nmi_count(int cpu)
         return cpu_data(cpu).__nmi_count;
 }
 
-static int endflag __initdata;
-
 static __init void nmi_cpu_busy(void *data)
 {
         local_irq_enable_in_hardirq();
@@ -143,12 +153,15 @@ static void report_broken_nmi(int cpu, int *prev_nmi_count)
         printk(KERN_WARNING
                 "and attach the output of the 'dmesg' command.\n");
 
-        nmi_usable = 0;
+        per_cpu(wd_enabled, cpu) = 0;
+        atomic_dec(&nmi_active);
 }
 
-static void stop_watchdog(void *unused)
+void stop_nmi_watchdog(void *unused)
 {
         pcr_ops->write(PCR_PIC_PRIV);
+        __get_cpu_var(wd_enabled) = 0;
+        atomic_dec(&nmi_active);
 }
 
 static int __init check_nmi_watchdog(void)
@@ -156,6 +169,9 @@ static int __init check_nmi_watchdog(void)
         unsigned int *prev_nmi_count;
         int cpu, err;
 
+        if (!atomic_read(&nmi_active))
+                return 0;
+
         prev_nmi_count = kmalloc(nr_cpu_ids * sizeof(unsigned int), GFP_KERNEL);
         if (!prev_nmi_count) {
                 err = -ENOMEM;
@@ -172,12 +188,15 @@ static int __init check_nmi_watchdog(void)
         mdelay((20 * 1000) / nmi_hz); /* wait 20 ticks */
 
         for_each_online_cpu(cpu) {
+                if (!per_cpu(wd_enabled, cpu))
+                        continue;
                 if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5)
                         report_broken_nmi(cpu, prev_nmi_count);
         }
         endflag = 1;
-        if (!nmi_usable) {
+        if (!atomic_read(&nmi_active)) {
                 kfree(prev_nmi_count);
+                atomic_set(&nmi_active, -1);
                 err = -ENODEV;
                 goto error;
         }
@@ -188,12 +207,26 @@ static int __init check_nmi_watchdog(void)
         kfree(prev_nmi_count);
         return 0;
 error:
-        on_each_cpu(stop_watchdog, NULL, 1);
+        on_each_cpu(stop_nmi_watchdog, NULL, 1);
         return err;
 }
 
-static void start_watchdog(void *unused)
+void start_nmi_watchdog(void *unused)
 {
+        __get_cpu_var(wd_enabled) = 1;
+        atomic_inc(&nmi_active);
+
+        pcr_ops->write(PCR_PIC_PRIV);
+        write_pic(picl_value(nmi_hz));
+
+        pcr_ops->write(pcr_enable);
+}
+
+static void nmi_adjust_hz_one(void *unused)
+{
+        if (!__get_cpu_var(wd_enabled))
+                return;
+
         pcr_ops->write(PCR_PIC_PRIV);
         write_pic(picl_value(nmi_hz));
 
@@ -203,13 +236,13 @@ static void start_watchdog(void *unused)
 void nmi_adjust_hz(unsigned int new_hz)
 {
         nmi_hz = new_hz;
-        on_each_cpu(start_watchdog, NULL, 1);
+        on_each_cpu(nmi_adjust_hz_one, NULL, 1);
 }
 EXPORT_SYMBOL_GPL(nmi_adjust_hz);
 
 static int nmi_shutdown(struct notifier_block *nb, unsigned long cmd, void *p)
 {
-        on_each_cpu(stop_watchdog, NULL, 1);
+        on_each_cpu(stop_nmi_watchdog, NULL, 1);
         return 0;
 }
 
@@ -221,18 +254,19 @@ int __init nmi_init(void)
 {
         int err;
 
-        nmi_usable = 1;
-
-        on_each_cpu(start_watchdog, NULL, 1);
+        on_each_cpu(start_nmi_watchdog, NULL, 1);
 
         err = check_nmi_watchdog();
         if (!err) {
                 err = register_reboot_notifier(&nmi_reboot_notifier);
                 if (err) {
-                        nmi_usable = 0;
-                        on_each_cpu(stop_watchdog, NULL, 1);
+                        on_each_cpu(stop_nmi_watchdog, NULL, 1);
+                        atomic_set(&nmi_active, -1);
                 }
         }
+        if (!err)
+                init_hw_perf_counters();
+
         return err;
 }
 
diff --git a/arch/sparc/kernel/of_device_32.c b/arch/sparc/kernel/of_device_32.c
index 90396702ea2c..4c26eb59e742 100644
--- a/arch/sparc/kernel/of_device_32.c
+++ b/arch/sparc/kernel/of_device_32.c
@@ -9,6 +9,8 @@
 #include <linux/irq.h>
 #include <linux/of_device.h>
 #include <linux/of_platform.h>
+#include <asm/leon.h>
+#include <asm/leon_amba.h>
 
 #include "of_device_common.h"
 
@@ -97,6 +99,35 @@ static unsigned long of_bus_sbus_get_flags(const u32 *addr, unsigned long flags)
         return IORESOURCE_MEM;
 }
 
+ /*
+ * AMBAPP bus specific translator
+ */
+
+static int of_bus_ambapp_match(struct device_node *np)
+{
+        return !strcmp(np->name, "ambapp");
+}
+
+static void of_bus_ambapp_count_cells(struct device_node *child,
+                                      int *addrc, int *sizec)
+{
+        if (addrc)
+                *addrc = 1;
+        if (sizec)
+                *sizec = 1;
+}
+
+static int of_bus_ambapp_map(u32 *addr, const u32 *range,
+                             int na, int ns, int pna)
+{
+        return of_bus_default_map(addr, range, na, ns, pna);
+}
+
+static unsigned long of_bus_ambapp_get_flags(const u32 *addr,
+                                             unsigned long flags)
+{
+        return IORESOURCE_MEM;
+}
 
 /*
  * Array of bus specific translators
@@ -121,6 +152,15 @@ static struct of_bus of_busses[] = {
                 .map = of_bus_default_map,
                 .get_flags = of_bus_sbus_get_flags,
         },
+        /* AMBA */
+        {
+                .name = "ambapp",
+                .addr_prop_name = "reg",
+                .match = of_bus_ambapp_match,
+                .count_cells = of_bus_ambapp_count_cells,
+                .map = of_bus_ambapp_map,
+                .get_flags = of_bus_ambapp_get_flags,
+        },
         /* Default */
         {
                 .name = "default",
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 57859ad23547..c68648662802 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -1039,7 +1039,7 @@ static void ali_sound_dma_hack(struct pci_dev *pdev, int set_bit)
         pci_dev_put(ali_isa_bridge);
 }
 
-int pci_dma_supported(struct pci_dev *pdev, u64 device_mask)
+int pci64_dma_supported(struct pci_dev *pdev, u64 device_mask)
 {
         u64 dma_addr_mask;
 
diff --git a/arch/sparc/kernel/pci_sun4v.c b/arch/sparc/kernel/pci_sun4v.c
index 2485eaa23101..23c33ff9c31e 100644
--- a/arch/sparc/kernel/pci_sun4v.c
+++ b/arch/sparc/kernel/pci_sun4v.c
@@ -232,7 +232,8 @@ static void dma_4v_free_coherent(struct device *dev, size_t size, void *cpu,
 
 static dma_addr_t dma_4v_map_page(struct device *dev, struct page *page,
                                   unsigned long offset, size_t sz,
-                                  enum dma_data_direction direction)
+                                  enum dma_data_direction direction,
+                                  struct dma_attrs *attrs)
 {
         struct iommu *iommu;
         unsigned long flags, npages, oaddr;
@@ -296,7 +297,8 @@ iommu_map_fail:
 }
 
 static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
-                              size_t sz, enum dma_data_direction direction)
+                              size_t sz, enum dma_data_direction direction,
+                              struct dma_attrs *attrs)
 {
         struct pci_pbm_info *pbm;
         struct iommu *iommu;
@@ -336,7 +338,8 @@ static void dma_4v_unmap_page(struct device *dev, dma_addr_t bus_addr,
 }
 
 static int dma_4v_map_sg(struct device *dev, struct scatterlist *sglist,
-                         int nelems, enum dma_data_direction direction)
+                         int nelems, enum dma_data_direction direction,
+                         struct dma_attrs *attrs)
 {
         struct scatterlist *s, *outs, *segstart;
         unsigned long flags, handle, prot;
@@ -478,7 +481,8 @@ iommu_map_failed:
 }
 
 static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
-                            int nelems, enum dma_data_direction direction)
+                            int nelems, enum dma_data_direction direction,
+                            struct dma_attrs *attrs)
 {
         struct pci_pbm_info *pbm;
         struct scatterlist *sg;
@@ -521,29 +525,13 @@ static void dma_4v_unmap_sg(struct device *dev, struct scatterlist *sglist,
         spin_unlock_irqrestore(&iommu->lock, flags);
 }
 
-static void dma_4v_sync_single_for_cpu(struct device *dev,
-                                       dma_addr_t bus_addr, size_t sz,
-                                       enum dma_data_direction direction)
-{
-        /* Nothing to do... */
-}
-
-static void dma_4v_sync_sg_for_cpu(struct device *dev,
-                                   struct scatterlist *sglist, int nelems,
-                                   enum dma_data_direction direction)
-{
-        /* Nothing to do... */
-}
-
-static const struct dma_ops sun4v_dma_ops = {
+static struct dma_map_ops sun4v_dma_ops = {
         .alloc_coherent                 = dma_4v_alloc_coherent,
         .free_coherent                  = dma_4v_free_coherent,
         .map_page                       = dma_4v_map_page,
         .unmap_page                     = dma_4v_unmap_page,
         .map_sg                         = dma_4v_map_sg,
         .unmap_sg                       = dma_4v_unmap_sg,
-        .sync_single_for_cpu            = dma_4v_sync_single_for_cpu,
-        .sync_sg_for_cpu                = dma_4v_sync_sg_for_cpu,
 };
 
 static void __devinit pci_sun4v_scan_bus(struct pci_pbm_info *pbm,
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index 1ae8cdd7e703..68ff00107073 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -7,6 +7,8 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 
+#include <linux/perf_counter.h>
+
 #include <asm/pil.h>
 #include <asm/pcr.h>
 #include <asm/nmi.h>
@@ -34,10 +36,20 @@ unsigned int picl_shift;
  */
 void deferred_pcr_work_irq(int irq, struct pt_regs *regs)
 {
+        struct pt_regs *old_regs;
+
         clear_softint(1 << PIL_DEFERRED_PCR_WORK);
+
+        old_regs = set_irq_regs(regs);
+        irq_enter();
+#ifdef CONFIG_PERF_COUNTERS
+        perf_counter_do_pending();
+#endif
+        irq_exit();
+        set_irq_regs(old_regs);
 }
 
-void schedule_deferred_pcr_work(void)
+void set_perf_counter_pending(void)
 {
         set_softint(1 << PIL_DEFERRED_PCR_WORK);
 }
diff --git a/arch/sparc/kernel/perf_counter.c b/arch/sparc/kernel/perf_counter.c
new file mode 100644
index 000000000000..09de4035eaa9
--- /dev/null
+++ b/arch/sparc/kernel/perf_counter.c
@@ -0,0 +1,557 @@
+/* Performance counter support for sparc64.
+ *
+ * Copyright (C) 2009 David S. Miller <davem@davemloft.net>
+ *
+ * This code is based almost entirely upon the x86 perf counter
+ * code, which is:
+ *
+ *  Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
+ *  Copyright (C) 2009 Jaswinder Singh Rajput
+ *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ */
+
+#include <linux/perf_counter.h>
+#include <linux/kprobes.h>
+#include <linux/kernel.h>
+#include <linux/kdebug.h>
+#include <linux/mutex.h>
+
+#include <asm/cpudata.h>
+#include <asm/atomic.h>
+#include <asm/nmi.h>
+#include <asm/pcr.h>
+
+/* Sparc64 chips have two performance counters, 32-bits each, with
+ * overflow interrupts generated on transition from 0xffffffff to 0.
+ * The counters are accessed in one go using a 64-bit register.
+ *
+ * Both counters are controlled using a single control register.  The
+ * only way to stop all sampling is to clear all of the context (user,
+ * supervisor, hypervisor) sampling enable bits.  But these bits apply
+ * to both counters, thus the two counters can't be enabled/disabled
+ * individually.
+ *
+ * The control register has two event fields, one for each of the two
+ * counters.  It's thus nearly impossible to have one counter going
+ * while keeping the other one stopped.  Therefore it is possible to
+ * get overflow interrupts for counters not currently "in use" and
+ * that condition must be checked in the overflow interrupt handler.
+ *
+ * So we use a hack, in that we program inactive counters with the
+ * "sw_count0" and "sw_count1" events.  These count how many times
+ * the instruction "sethi %hi(0xfc000), %g0" is executed.  It's an
+ * unusual way to encode a NOP and therefore will not trigger in
+ * normal code.
+ */
+
+#define MAX_HWCOUNTERS                  2
+#define MAX_PERIOD                      ((1UL << 32) - 1)
+
+#define PIC_UPPER_INDEX                 0
+#define PIC_LOWER_INDEX                 1
+
+struct cpu_hw_counters {
+        struct perf_counter     *counters[MAX_HWCOUNTERS];
+        unsigned long           used_mask[BITS_TO_LONGS(MAX_HWCOUNTERS)];
+        unsigned long           active_mask[BITS_TO_LONGS(MAX_HWCOUNTERS)];
+        int enabled;
+};
+DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters) = { .enabled = 1, };
+
+struct perf_event_map {
+        u16     encoding;
+        u8      pic_mask;
+#define PIC_NONE        0x00
+#define PIC_UPPER       0x01
+#define PIC_LOWER       0x02
+};
+
+struct sparc_pmu {
+        const struct perf_event_map     *(*event_map)(int);
+        int                             max_events;
+        int                             upper_shift;
+        int                             lower_shift;
+        int                             event_mask;
+        int                             hv_bit;
+        int                             irq_bit;
+        int                             upper_nop;
+        int                             lower_nop;
+};
+
+static const struct perf_event_map ultra3i_perfmon_event_map[] = {
+        [PERF_COUNT_HW_CPU_CYCLES] = { 0x0000, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_INSTRUCTIONS] = { 0x0001, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_CACHE_REFERENCES] = { 0x0009, PIC_LOWER },
+        [PERF_COUNT_HW_CACHE_MISSES] = { 0x0009, PIC_UPPER },
+};
+
+static const struct perf_event_map *ultra3i_event_map(int event)
+{
+        return &ultra3i_perfmon_event_map[event];
+}
+
+static const struct sparc_pmu ultra3i_pmu = {
+        .event_map      = ultra3i_event_map,
+        .max_events     = ARRAY_SIZE(ultra3i_perfmon_event_map),
+        .upper_shift    = 11,
+        .lower_shift    = 4,
+        .event_mask     = 0x3f,
+        .upper_nop      = 0x1c,
+        .lower_nop      = 0x14,
+};
+
+static const struct perf_event_map niagara2_perfmon_event_map[] = {
+        [PERF_COUNT_HW_CPU_CYCLES] = { 0x02ff, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_INSTRUCTIONS] = { 0x02ff, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_CACHE_REFERENCES] = { 0x0208, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_CACHE_MISSES] = { 0x0302, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = { 0x0201, PIC_UPPER | PIC_LOWER },
+        [PERF_COUNT_HW_BRANCH_MISSES] = { 0x0202, PIC_UPPER | PIC_LOWER },
+};
+
+static const struct perf_event_map *niagara2_event_map(int event)
+{
+        return &niagara2_perfmon_event_map[event];
+}
+
+static const struct sparc_pmu niagara2_pmu = {
+        .event_map      = niagara2_event_map,
+        .max_events     = ARRAY_SIZE(niagara2_perfmon_event_map),
+        .upper_shift    = 19,
+        .lower_shift    = 6,
+        .event_mask     = 0xfff,
+        .hv_bit         = 0x8,
+        .irq_bit        = 0x03,
+        .upper_nop      = 0x220,
+        .lower_nop      = 0x220,
+};
+
+static const struct sparc_pmu *sparc_pmu __read_mostly;
+
+static u64 event_encoding(u64 event, int idx)
+{
+        if (idx == PIC_UPPER_INDEX)
+                event <<= sparc_pmu->upper_shift;
+        else
+                event <<= sparc_pmu->lower_shift;
+        return event;
+}
+
+static u64 mask_for_index(int idx)
+{
+        return event_encoding(sparc_pmu->event_mask, idx);
+}
+
+static u64 nop_for_index(int idx)
+{
+        return event_encoding(idx == PIC_UPPER_INDEX ?
+                              sparc_pmu->upper_nop :
+                              sparc_pmu->lower_nop, idx);
+}
+
+static inline void sparc_pmu_enable_counter(struct hw_perf_counter *hwc,
+                                            int idx)
+{
+        u64 val, mask = mask_for_index(idx);
+
+        val = pcr_ops->read();
+        pcr_ops->write((val & ~mask) | hwc->config);
+}
+
+static inline void sparc_pmu_disable_counter(struct hw_perf_counter *hwc,
+                                             int idx)
+{
+        u64 mask = mask_for_index(idx);
+        u64 nop = nop_for_index(idx);
+        u64 val = pcr_ops->read();
+
+        pcr_ops->write((val & ~mask) | nop);
+}
+
+void hw_perf_enable(void)
+{
+        struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+        u64 val;
+        int i;
+
+        if (cpuc->enabled)
+                return;
+
+        cpuc->enabled = 1;
+        barrier();
+
+        val = pcr_ops->read();
+
+        for (i = 0; i < MAX_HWCOUNTERS; i++) {
+                struct perf_counter *cp = cpuc->counters[i];
+                struct hw_perf_counter *hwc;
+
+                if (!cp)
+                        continue;
+                hwc = &cp->hw;
+                val |= hwc->config_base;
+        }
+
+        pcr_ops->write(val);
+}
+
+void hw_perf_disable(void)
+{
+        struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+        u64 val;
+
+        if (!cpuc->enabled)
+                return;
+
+        cpuc->enabled = 0;
+
+        val = pcr_ops->read();
+        val &= ~(PCR_UTRACE | PCR_STRACE |
+                 sparc_pmu->hv_bit | sparc_pmu->irq_bit);
+        pcr_ops->write(val);
+}
+
+static u32 read_pmc(int idx)
+{
+        u64 val;
+
+        read_pic(val);
+        if (idx == PIC_UPPER_INDEX)
+                val >>= 32;
+
+        return val & 0xffffffff;
+}
+
+static void write_pmc(int idx, u64 val)
+{
+        u64 shift, mask, pic;
+
+        shift = 0;
+        if (idx == PIC_UPPER_INDEX)
+                shift = 32;
+
+        mask = ((u64) 0xffffffff) << shift;
+        val <<= shift;
+
+        read_pic(pic);
+        pic &= ~mask;
+        pic |= val;
+        write_pic(pic);
+}
+
+static int sparc_perf_counter_set_period(struct perf_counter *counter,
+                                         struct hw_perf_counter *hwc, int idx)
+{
+        s64 left = atomic64_read(&hwc->period_left);
+        s64 period = hwc->sample_period;
+        int ret = 0;
+
+        if (unlikely(left <= -period)) {
+                left = period;
+                atomic64_set(&hwc->period_left, left);
+                hwc->last_period = period;
+                ret = 1;
+        }
+
+        if (unlikely(left <= 0)) {
+                left += period;
+                atomic64_set(&hwc->period_left, left);
+                hwc->last_period = period;
+                ret = 1;
+        }
+        if (left > MAX_PERIOD)
+                left = MAX_PERIOD;
+
+        atomic64_set(&hwc->prev_count, (u64)-left);
+
+        write_pmc(idx, (u64)(-left) & 0xffffffff);
+
+        perf_counter_update_userpage(counter);
+
+        return ret;
+}
+
+static int sparc_pmu_enable(struct perf_counter *counter)
+{
+        struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+        struct hw_perf_counter *hwc = &counter->hw;
+        int idx = hwc->idx;
+
+        if (test_and_set_bit(idx, cpuc->used_mask))
+                return -EAGAIN;
+
+        sparc_pmu_disable_counter(hwc, idx);
+
+        cpuc->counters[idx] = counter;
+        set_bit(idx, cpuc->active_mask);
+
+        sparc_perf_counter_set_period(counter, hwc, idx);
+        sparc_pmu_enable_counter(hwc, idx);
+        perf_counter_update_userpage(counter);
+        return 0;
+}
+
+static u64 sparc_perf_counter_update(struct perf_counter *counter,
+                                     struct hw_perf_counter *hwc, int idx)
+{
+        int shift = 64 - 32;
+        u64 prev_raw_count, new_raw_count;
+        s64 delta;
+
+again:
+        prev_raw_count = atomic64_read(&hwc->prev_count);
+        new_raw_count = read_pmc(idx);
+
+        if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+                             new_raw_count) != prev_raw_count)
+                goto again;
+
+        delta = (new_raw_count << shift) - (prev_raw_count << shift);
+        delta >>= shift;
+
+        atomic64_add(delta, &counter->count);
+        atomic64_sub(delta, &hwc->period_left);
+
+        return new_raw_count;
+}
+
+static void sparc_pmu_disable(struct perf_counter *counter)
+{
+        struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
+        struct hw_perf_counter *hwc = &counter->hw;
+        int idx = hwc->idx;
+
+        clear_bit(idx, cpuc->active_mask);
+        sparc_pmu_disable_counter(hwc, idx);
+
+        barrier();
+
+        sparc_perf_counter_update(counter, hwc, idx);
+        cpuc->counters[idx] = NULL;
+        clear_bit(idx, cpuc->used_mask);
+
+        perf_counter_update_userpage(counter);
+}
+
+static void sparc_pmu_read(struct perf_counter *counter)
+{
+        struct hw_perf_counter *hwc = &counter->hw;
+        sparc_perf_counter_update(counter, hwc, hwc->idx);
+}
+
+static void sparc_pmu_unthrottle(struct perf_counter *counter)
+{
+        struct hw_perf_counter *hwc = &counter->hw;
+        sparc_pmu_enable_counter(hwc, hwc->idx);
+}
+
+static atomic_t active_counters = ATOMIC_INIT(0);
+static DEFINE_MUTEX(pmc_grab_mutex);
+
+void perf_counter_grab_pmc(void)
+{
+        if (atomic_inc_not_zero(&active_counters))
+                return;
+
+        mutex_lock(&pmc_grab_mutex);
+        if (atomic_read(&active_counters) == 0) {
+                if (atomic_read(&nmi_active) > 0) {
+                        on_each_cpu(stop_nmi_watchdog, NULL, 1);
+                        BUG_ON(atomic_read(&nmi_active) != 0);
+                }
+                atomic_inc(&active_counters);
+        }
+        mutex_unlock(&pmc_grab_mutex);
+}
+
+void perf_counter_release_pmc(void)
+{
+        if (atomic_dec_and_mutex_lock(&active_counters, &pmc_grab_mutex)) {
+                if (atomic_read(&nmi_active) == 0)
+                        on_each_cpu(start_nmi_watchdog, NULL, 1);
+                mutex_unlock(&pmc_grab_mutex);
+        }
+}
+
+static void hw_perf_counter_destroy(struct perf_counter *counter)
+{
+        perf_counter_release_pmc();
+}
+
+static int __hw_perf_counter_init(struct perf_counter *counter)
+{
+        struct perf_counter_attr *attr = &counter->attr;
+        struct hw_perf_counter *hwc = &counter->hw;
+        const struct perf_event_map *pmap;
+        u64 enc;
+
+        if (atomic_read(&nmi_active) < 0)
+                return -ENODEV;
+
+        if (attr->type != PERF_TYPE_HARDWARE)
+                return -EOPNOTSUPP;
+
+        if (attr->config >= sparc_pmu->max_events)
+                return -EINVAL;
+
+        perf_counter_grab_pmc();
+        counter->destroy = hw_perf_counter_destroy;
+
+        /* We save the enable bits in the config_base.  So to
+         * turn off sampling just write 'config', and to enable
+         * things write 'config | config_base'.
+         */
+        hwc->config_base = sparc_pmu->irq_bit;
+        if (!attr->exclude_user)
+                hwc->config_base |= PCR_UTRACE;
+        if (!attr->exclude_kernel)
+                hwc->config_base |= PCR_STRACE;
+        if (!attr->exclude_hv)
+                hwc->config_base |= sparc_pmu->hv_bit;
+
+        if (!hwc->sample_period) {
+                hwc->sample_period = MAX_PERIOD;
+                hwc->last_period = hwc->sample_period;
+                atomic64_set(&hwc->period_left, hwc->sample_period);
+        }
+
+        pmap = sparc_pmu->event_map(attr->config);
+
+        enc = pmap->encoding;
+        if (pmap->pic_mask & PIC_UPPER) {
+                hwc->idx = PIC_UPPER_INDEX;
+                enc <<= sparc_pmu->upper_shift;
+        } else {
+                hwc->idx = PIC_LOWER_INDEX;
+                enc <<= sparc_pmu->lower_shift;
+        }
+
+        hwc->config |= enc;
+        return 0;
+}
+
+static const struct pmu pmu = {
+        .enable         = sparc_pmu_enable,
+        .disable        = sparc_pmu_disable,
+        .read           = sparc_pmu_read,
+        .unthrottle     = sparc_pmu_unthrottle,
+};
+
+const struct pmu *hw_perf_counter_init(struct perf_counter *counter)
+{
+        int err = __hw_perf_counter_init(counter);
+
+        if (err)
+                return ERR_PTR(err);
+        return &pmu;
+}
+
+void perf_counter_print_debug(void)
+{
+        unsigned long flags;
+        u64 pcr, pic;
+        int cpu;
+
+        if (!sparc_pmu)
+                return;
+
+        local_irq_save(flags);
+
+        cpu = smp_processor_id();
+
+        pcr = pcr_ops->read();
+        read_pic(pic);
+
+        pr_info("\n");
+        pr_info("CPU#%d: PCR[%016llx] PIC[%016llx]\n",
+                cpu, pcr, pic);
+
+        local_irq_restore(flags);
+}
+
+static int __kprobes perf_counter_nmi_handler(struct notifier_block *self,
+                                              unsigned long cmd, void *__args)
+{
+        struct die_args *args = __args;
+        struct perf_sample_data data;
+        struct cpu_hw_counters *cpuc;
+        struct pt_regs *regs;
+        int idx;
+
+        if (!atomic_read(&active_counters))
+                return NOTIFY_DONE;
+
+        switch (cmd) {
+        case DIE_NMI:
+                break;
+
+        default:
+                return NOTIFY_DONE;
+        }
+
+        regs = args->regs;
+
+        data.regs = regs;
+        data.addr = 0;
+
+        cpuc = &__get_cpu_var(cpu_hw_counters);
+        for (idx = 0; idx < MAX_HWCOUNTERS; idx++) {
+                struct perf_counter *counter = cpuc->counters[idx];
+                struct hw_perf_counter *hwc;
+                u64 val;
+
+                if (!test_bit(idx, cpuc->active_mask))
+                        continue;
+                hwc = &counter->hw;
+                val = sparc_perf_counter_update(counter, hwc, idx);
+                if (val & (1ULL << 31))
+                        continue;
+
+                data.period = counter->hw.last_period;
+                if (!sparc_perf_counter_set_period(counter, hwc, idx))
+                        continue;
+
+                if (perf_counter_overflow(counter, 1, &data))
+                        sparc_pmu_disable_counter(hwc, idx);
+        }
+
+        return NOTIFY_STOP;
+}
+
+static __read_mostly struct notifier_block perf_counter_nmi_notifier = {
+        .notifier_call          = perf_counter_nmi_handler,
+};
+
+static bool __init supported_pmu(void)
+{
+        if (!strcmp(sparc_pmu_type, "ultra3i")) {
+                sparc_pmu = &ultra3i_pmu;
+                return true;
+        }
+        if (!strcmp(sparc_pmu_type, "niagara2")) {
+                sparc_pmu = &niagara2_pmu;
+                return true;
+        }
+        return false;
+}
+
+void __init init_hw_perf_counters(void)
+{
+        pr_info("Performance counters: ");
+
+        if (!supported_pmu()) {
+                pr_cont("No support for PMU type '%s'\n", sparc_pmu_type);
+                return;
+        }
+
+        pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
+
+        /* All sparc64 PMUs currently have 2 counters.  But this simple
+         * driver only supports one active counter at a time.
+         */
+        perf_max_counters = 1;
+
+        register_die_notifier(&perf_counter_nmi_notifier);
+}
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 4041f94e7724..18d67854a1b8 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -251,7 +251,7 @@ static void __global_reg_poll(struct global_reg_snapshot *gp)
         }
 }
 
-void __trigger_all_cpu_backtrace(void)
+void arch_trigger_all_cpu_backtrace(void)
 {
         struct thread_info *tp = current_thread_info();
         struct pt_regs *regs = get_irq_regs();
@@ -304,7 +304,7 @@ void __trigger_all_cpu_backtrace(void)
 
 static void sysrq_handle_globreg(int key, struct tty_struct *tty)
 {
-        __trigger_all_cpu_backtrace();
+        arch_trigger_all_cpu_backtrace();
 }
 
 static struct sysrq_key_op sparc_globalreg_op = {
diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c
index fe43e80772db..0a37e8cfd160 100644
--- a/arch/sparc/kernel/prom_32.c
+++ b/arch/sparc/kernel/prom_32.c
@@ -24,6 +24,8 @@
 
 #include <asm/prom.h>
 #include <asm/oplib.h>
+#include <asm/leon.h>
+#include <asm/leon_amba.h>
 
 #include "prom.h"
 
@@ -131,6 +133,35 @@ static void __init ebus_path_component(struct device_node *dp, char *tmp_buf)
                 regs->which_io, regs->phys_addr);
 }
 
+/* "name:vendor:device@irq,addrlo" */
+static void __init ambapp_path_component(struct device_node *dp, char *tmp_buf)
+{
+        struct amba_prom_registers *regs; unsigned int *intr;
+        unsigned int *device, *vendor;
+        struct property *prop;
+
+        prop = of_find_property(dp, "reg", NULL);
+        if (!prop)
+                return;
+        regs = prop->value;
+        prop = of_find_property(dp, "interrupts", NULL);
+        if (!prop)
+                return;
+        intr = prop->value;
+        prop = of_find_property(dp, "vendor", NULL);
+        if (!prop)
+                return;
+        vendor = prop->value;
+        prop = of_find_property(dp, "device", NULL);
+        if (!prop)
+                return;
+        device = prop->value;
+
+        sprintf(tmp_buf, "%s:%d:%d@%x,%x",
+                dp->name, *vendor, *device,
+                *intr, regs->phys_addr);
+}
+
 static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
 {
         struct device_node *parent = dp->parent;
@@ -143,6 +174,8 @@ static void __init __build_path_component(struct device_node *dp, char *tmp_buf)
                         return sbus_path_component(dp, tmp_buf);
                 if (!strcmp(parent->type, "ebus"))
                         return ebus_path_component(dp, tmp_buf);
+                if (!strcmp(parent->type, "ambapp"))
+                        return ambapp_path_component(dp, tmp_buf);
 
                 /* "isa" is handled with platform naming */
         }
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index 0fb5789d43c8..138910c67206 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -22,9 +22,12 @@
 #include <linux/of.h>
 #include <asm/prom.h>
 #include <asm/oplib.h>
+#include <asm/leon.h>
 
 #include "prom.h"
 
+void (*prom_build_more)(struct device_node *dp, struct device_node ***nextp);
+
 struct device_node *of_console_device;
 EXPORT_SYMBOL(of_console_device);
 
@@ -161,7 +164,7 @@ static struct property * __init build_one_prop(phandle node, char *prev,
                         name = prom_nextprop(node, prev, p->name);
                 }
 
-                if (strlen(name) == 0) {
+                if (!name || strlen(name) == 0) {
                         tmp = p;
                         return NULL;
                 }
@@ -242,7 +245,7 @@ static struct device_node * __init prom_create_node(phandle node,
         return dp;
 }
 
-static char * __init build_full_name(struct device_node *dp)
+char * __init build_full_name(struct device_node *dp)
 {
         int len, ourlen, plen;
         char *n;
@@ -289,6 +292,9 @@ static struct device_node * __init prom_build_tree(struct device_node *parent,
 
                 dp->child = prom_build_tree(dp, prom_getchild(node), nextp);
 
+                if (prom_build_more)
+                        prom_build_more(dp, nextp);
+
                 node = prom_getsibling(node);
         }
 
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 998cadb4e7f2..16a47ffe03c1 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -235,6 +235,8 @@ void __init setup_arch(char **cmdline_p)
                 sparc_cpu_model = sun4e;
         if (!strcmp(&cputypval,"sun4u"))
                 sparc_cpu_model = sun4u;
+        if (!strncmp(&cputypval, "leon" , 4))
+                sparc_cpu_model = sparc_leon;
 
         printk("ARCH: ");
         switch(sparc_cpu_model) {
@@ -256,6 +258,9 @@ void __init setup_arch(char **cmdline_p)
         case sun4u:
                 printk("SUN4U\n");
                 break;
+        case sparc_leon:
+                printk("LEON\n");
+                break;
         default:
                 printk("UNKNOWN!\n");
                 break;
diff --git a/arch/sparc/kernel/signal_32.c b/arch/sparc/kernel/signal_32.c
index 181d069a2d44..7ce1a1005b1d 100644
--- a/arch/sparc/kernel/signal_32.c
+++ b/arch/sparc/kernel/signal_32.c
@@ -590,6 +590,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0,
         if (thread_info_flags & _TIF_NOTIFY_RESUME) {
                 clear_thread_flag(TIF_NOTIFY_RESUME);
                 tracehook_notify_resume(regs);
+                if (current->replacement_session_keyring)
+                        key_replace_session_keyring();
         }
 }
 
diff --git a/arch/sparc/kernel/signal_64.c b/arch/sparc/kernel/signal_64.c
index ec82d76dc6f2..647afbda7ae1 100644
--- a/arch/sparc/kernel/signal_64.c
+++ b/arch/sparc/kernel/signal_64.c
@@ -613,5 +613,8 @@ void do_notify_resume(struct pt_regs *regs, unsigned long orig_i0, unsigned long
         if (thread_info_flags & _TIF_NOTIFY_RESUME) {
                 clear_thread_flag(TIF_NOTIFY_RESUME);
                 tracehook_notify_resume(regs);
+                if (current->replacement_session_keyring)
+                        key_replace_session_keyring();
         }
 }
+
diff --git a/arch/sparc/kernel/sys32.S b/arch/sparc/kernel/sys32.S
index aed94869ad6a..e7061138c98a 100644
--- a/arch/sparc/kernel/sys32.S
+++ b/arch/sparc/kernel/sys32.S
@@ -121,7 +121,7 @@ SIGN2(sys32_syslog, sys_syslog, %o0, %o2)
 SIGN1(sys32_umask, sys_umask, %o0)
 SIGN3(sys32_tgkill, sys_tgkill, %o0, %o1, %o2)
 SIGN1(sys32_sendto, sys_sendto, %o0)
-SIGN1(sys32_recvfrom, sys_recvfrom, %o0)
+SIGN1(sys32_recvfrom, compat_sys_recvfrom, %o0)
 SIGN3(sys32_socket, sys_socket, %o0, %o1, %o2)
 SIGN2(sys32_connect, sys_connect, %o0, %o2)
 SIGN2(sys32_bind, sys_bind, %o0, %o2)
diff --git a/arch/sparc/kernel/sysfs.c b/arch/sparc/kernel/sysfs.c
index d28f496f4669..ca39c606fe8e 100644
--- a/arch/sparc/kernel/sysfs.c
+++ b/arch/sparc/kernel/sysfs.c
@@ -2,6 +2,7 @@
  *
  * Copyright (C) 2007 David S. Miller <davem@davemloft.net>
  */
+#include <linux/sched.h>
 #include <linux/sysdev.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 690901657291..04181577cb65 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -82,5 +82,5 @@ sys_call_table:
 /*310*/ .long sys_utimensat, sys_signalfd, sys_timerfd_create, sys_eventfd, sys_fallocate
 /*315*/ .long sys_timerfd_settime, sys_timerfd_gettime, sys_signalfd4, sys_eventfd2, sys_epoll_create1
 /*320*/ .long sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
-/*325*/ .long sys_pwritev, sys_rt_tgsigqueueinfo
+/*325*/ .long sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_counter_open
 
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 2ee7250ba7ae..91b06b7f7acf 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -83,7 +83,7 @@ sys_call_table32:
 /*310*/ .word compat_sys_utimensat, compat_sys_signalfd, sys_timerfd_create, sys_eventfd, compat_sys_fallocate
         .word compat_sys_timerfd_settime, compat_sys_timerfd_gettime, compat_sys_signalfd4, sys_eventfd2, sys_epoll_create1
 /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, compat_sys_preadv
-        .word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo
+        .word compat_sys_pwritev, compat_sys_rt_tgsigqueueinfo, sys_perf_counter_open
 
 #endif /* CONFIG_COMPAT */
 
@@ -158,4 +158,4 @@ sys_call_table:
 /*310*/ .word sys_utimensat, sys_signalfd, sys_timerfd_create, sys_eventfd, sys_fallocate
         .word sys_timerfd_settime, sys_timerfd_gettime, sys_signalfd4, sys_eventfd2, sys_epoll_create1
 /*320*/ .word sys_dup3, sys_pipe2, sys_inotify_init1, sys_accept4, sys_preadv
-        .word sys_pwritev, sys_rt_tgsigqueueinfo
+        .word sys_pwritev, sys_rt_tgsigqueueinfo, sys_perf_counter_open
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 681abe0a4594..79836a7dd00c 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_SPARC32)   += loadmmu.o
 obj-y                   += generic_$(BITS).o
 obj-$(CONFIG_SPARC32)   += extable.o btfixup.o srmmu.o iommu.o io-unit.o
 obj-$(CONFIG_SPARC32)   += hypersparc.o viking.o tsunami.o swift.o
+obj-$(CONFIG_SPARC_LEON)+= leon_mm.o
 
 # Only used by sparc64
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 26bb3919ff1f..54114ad0bdee 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -34,6 +34,7 @@
 #include <asm/pgalloc.h>        /* bug in asm-generic/tlb.h: check_pgt_cache */
 #include <asm/tlb.h>
 #include <asm/prom.h>
+#include <asm/leon.h>
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
@@ -326,6 +327,9 @@ void __init paging_init(void)
                 sparc_unmapped_base = 0xe0000000;
                 BTFIXUPSET_SETHI(sparc_unmapped_base, 0xe0000000);
                 break;
+        case sparc_leon:
+                leon_init();
+                /* fall through */
         case sun4m:
         case sun4d:
                 srmmu_paging_init();
diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c
new file mode 100644
index 000000000000..c0e01297e64e
--- /dev/null
+++ b/arch/sparc/mm/leon_mm.c
@@ -0,0 +1,260 @@
+/*
+ *  linux/arch/sparc/mm/leon_m.c
+ *
+ * Copyright (C) 2004 Konrad Eisele (eiselekd@web.de, konrad@gaisler.com) Gaisler Research
+ * Copyright (C) 2009 Daniel Hellstrom (daniel@gaisler.com) Aeroflex Gaisler AB
+ * Copyright (C) 2009 Konrad Eisele (konrad@gaisler.com) Aeroflex Gaisler AB
+ *
+ * do srmmu probe in software
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/asi.h>
+#include <asm/leon.h>
+#include <asm/tlbflush.h>
+
+int leon_flush_during_switch = 1;
+int srmmu_swprobe_trace;
+
+unsigned long srmmu_swprobe(unsigned long vaddr, unsigned long *paddr)
+{
+
+        unsigned int ctxtbl;
+        unsigned int pgd, pmd, ped;
+        unsigned int ptr;
+        unsigned int lvl, pte, paddrbase;
+        unsigned int ctx;
+        unsigned int paddr_calc;
+
+        paddrbase = 0;
+
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe: trace on\n");
+
+        ctxtbl = srmmu_get_ctable_ptr();
+        if (!(ctxtbl)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: srmmu_get_ctable_ptr returned 0=>0\n");
+                return 0;
+        }
+        if (!_pfn_valid(PFN(ctxtbl))) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO
+                               "swprobe: !_pfn_valid(%x)=>0\n",
+                               PFN(ctxtbl));
+                return 0;
+        }
+
+        ctx = srmmu_get_context();
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe:  --- ctx (%x) ---\n", ctx);
+
+        pgd = LEON_BYPASS_LOAD_PA(ctxtbl + (ctx * 4));
+
+        if (((pgd & SRMMU_ET_MASK) == SRMMU_ET_PTE)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: pgd is entry level 3\n");
+                lvl = 3;
+                pte = pgd;
+                paddrbase = pgd & _SRMMU_PTE_PMASK_LEON;
+                goto ready;
+        }
+        if (((pgd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: pgd is invalid => 0\n");
+                return 0;
+        }
+
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe:  --- pgd (%x) ---\n", pgd);
+
+        ptr = (pgd & SRMMU_PTD_PMASK) << 4;
+        ptr += ((((vaddr) >> LEON_PGD_SH) & LEON_PGD_M) * 4);
+        if (!_pfn_valid(PFN(ptr)))
+                return 0;
+
+        pmd = LEON_BYPASS_LOAD_PA(ptr);
+        if (((pmd & SRMMU_ET_MASK) == SRMMU_ET_PTE)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: pmd is entry level 2\n");
+                lvl = 2;
+                pte = pmd;
+                paddrbase = pmd & _SRMMU_PTE_PMASK_LEON;
+                goto ready;
+        }
+        if (((pmd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: pmd is invalid => 0\n");
+                return 0;
+        }
+
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe:  --- pmd (%x) ---\n", pmd);
+
+        ptr = (pmd & SRMMU_PTD_PMASK) << 4;
+        ptr += (((vaddr >> LEON_PMD_SH) & LEON_PMD_M) * 4);
+        if (!_pfn_valid(PFN(ptr))) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: !_pfn_valid(%x)=>0\n",
+                               PFN(ptr));
+                return 0;
+        }
+
+        ped = LEON_BYPASS_LOAD_PA(ptr);
+
+        if (((ped & SRMMU_ET_MASK) == SRMMU_ET_PTE)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: ped is entry level 1\n");
+                lvl = 1;
+                pte = ped;
+                paddrbase = ped & _SRMMU_PTE_PMASK_LEON;
+                goto ready;
+        }
+        if (((ped & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: ped is invalid => 0\n");
+                return 0;
+        }
+
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe:  --- ped (%x) ---\n", ped);
+
+        ptr = (ped & SRMMU_PTD_PMASK) << 4;
+        ptr += (((vaddr >> LEON_PTE_SH) & LEON_PTE_M) * 4);
+        if (!_pfn_valid(PFN(ptr)))
+                return 0;
+
+        ptr = LEON_BYPASS_LOAD_PA(ptr);
+        if (((ptr & SRMMU_ET_MASK) == SRMMU_ET_PTE)) {
+                if (srmmu_swprobe_trace)
+                        printk(KERN_INFO "swprobe: ptr is entry level 0\n");
+                lvl = 0;
+                pte = ptr;
+                paddrbase = ptr & _SRMMU_PTE_PMASK_LEON;
+                goto ready;
+        }
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe: ptr is invalid => 0\n");
+        return 0;
+
+ready:
+        switch (lvl) {
+        case 0:
+                paddr_calc =
+                    (vaddr & ~(-1 << LEON_PTE_SH)) | ((pte & ~0xff) << 4);
+                break;
+        case 1:
+                paddr_calc =
+                    (vaddr & ~(-1 << LEON_PMD_SH)) | ((pte & ~0xff) << 4);
+                break;
+        case 2:
+                paddr_calc =
+                    (vaddr & ~(-1 << LEON_PGD_SH)) | ((pte & ~0xff) << 4);
+                break;
+        default:
+        case 3:
+                paddr_calc = vaddr;
+                break;
+        }
+        if (srmmu_swprobe_trace)
+                printk(KERN_INFO "swprobe: padde %x\n", paddr_calc);
+        if (paddr)
+                *paddr = paddr_calc;
+        return paddrbase;
+}
+
+void leon_flush_icache_all(void)
+{
+        __asm__ __volatile__(" flush ");        /*iflush*/
+}
+
+void leon_flush_dcache_all(void)
+{
+        __asm__ __volatile__("sta %%g0, [%%g0] %0\n\t" : :
+                             "i"(ASI_LEON_DFLUSH) : "memory");
+}
+
+void leon_flush_pcache_all(struct vm_area_struct *vma, unsigned long page)
+{
+        if (vma->vm_flags & VM_EXEC)
+                leon_flush_icache_all();
+        leon_flush_dcache_all();
+}
+
+void leon_flush_cache_all(void)
+{
+        __asm__ __volatile__(" flush ");        /*iflush*/
+        __asm__ __volatile__("sta %%g0, [%%g0] %0\n\t" : :
+                             "i"(ASI_LEON_DFLUSH) : "memory");
+}
+
+void leon_flush_tlb_all(void)
+{
+        leon_flush_cache_all();
+        __asm__ __volatile__("sta %%g0, [%0] %1\n\t" : : "r"(0x400),
+                             "i"(ASI_LEON_MMUFLUSH) : "memory");
+}
+
+/* get all cache regs */
+void leon3_getCacheRegs(struct leon3_cacheregs *regs)
+{
+        unsigned long ccr, iccr, dccr;
+
+        if (!regs)
+                return;
+        /* Get Cache regs from "Cache ASI" address 0x0, 0x8 and 0xC */
+        __asm__ __volatile__("lda [%%g0] %3, %0\n\t"
+                             "mov 0x08, %%g1\n\t"
+                             "lda [%%g1] %3, %1\n\t"
+                             "mov 0x0c, %%g1\n\t"
+                             "lda [%%g1] %3, %2\n\t"
+                             : "=r"(ccr), "=r"(iccr), "=r"(dccr)
+                               /* output */
+                             : "i"(ASI_LEON_CACHEREGS)  /* input */
+                             : "g1"     /* clobber list */
+            );
+        regs->ccr = ccr;
+        regs->iccr = iccr;
+        regs->dccr = dccr;
+}
+
+/* Due to virtual cache we need to check cache configuration if
+ * it is possible to skip flushing in some cases.
+ *
+ * Leon2 and Leon3 differ in their way of telling cache information
+ *
+ */
+int leon_flush_needed(void)
+{
+        int flush_needed = -1;
+        unsigned int ssize, sets;
+        char *setStr[4] =
+            { "direct mapped", "2-way associative", "3-way associative",
+                "4-way associative"
+        };
+        /* leon 3 */
+        struct leon3_cacheregs cregs;
+        leon3_getCacheRegs(&cregs);
+        sets = (cregs.dccr & LEON3_XCCR_SETS_MASK) >> 24;
+        /* (ssize=>realsize) 0=>1k, 1=>2k, 2=>4k, 3=>8k ... */
+        ssize = 1 << ((cregs.dccr & LEON3_XCCR_SSIZE_MASK) >> 20);
+
+        printk(KERN_INFO "CACHE: %s cache, set size %dk\n",
+               sets > 3 ? "unknown" : setStr[sets], ssize);
+        if ((ssize <= (PAGE_SIZE / 1024)) && (sets == 0)) {
+                /* Set Size <= Page size  ==>
+                   flush on every context switch not needed. */
+                flush_needed = 0;
+                printk(KERN_INFO "CACHE: not flushing on every context switch\n");
+        }
+        return flush_needed;
+}
+
+void leon_switch_mm(void)
+{
+        flush_tlb_mm((void *)0);
+        if (leon_flush_during_switch)
+                leon_flush_cache_all();
+}
diff --git a/arch/sparc/mm/loadmmu.c b/arch/sparc/mm/loadmmu.c
index 652be05acbea..82ec8f666036 100644
--- a/arch/sparc/mm/loadmmu.c
+++ b/arch/sparc/mm/loadmmu.c
@@ -33,6 +33,7 @@ void __init load_mmu(void)
                 break;
         case sun4m:
         case sun4d:
+        case sparc_leon:
                 ld_mmu_srmmu();
                 break;
         default:
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index ade4eb373bdd..509b1ffeba66 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -46,6 +46,7 @@
 #include <asm/tsunami.h>
 #include <asm/swift.h>
 #include <asm/turbosparc.h>
+#include <asm/leon.h>
 
 #include <asm/btfixup.h>
 
@@ -569,6 +570,9 @@ static void srmmu_switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
                 srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd);
         }
 
+        if (sparc_cpu_model == sparc_leon)
+                leon_switch_mm();
+
         if (is_hypersparc)
                 hyper_flush_whole_icache();
 
@@ -1977,6 +1981,45 @@ static void __init init_viking(void)
         poke_srmmu = poke_viking;
 }
 
+#ifdef CONFIG_SPARC_LEON
+
+void __init poke_leonsparc(void)
+{
+}
+
+void __init init_leon(void)
+{
+
+        srmmu_name = "Leon";
+
+        BTFIXUPSET_CALL(flush_cache_all, leon_flush_cache_all,
+                        BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_cache_mm, leon_flush_cache_all,
+                        BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_cache_page, leon_flush_pcache_all,
+                        BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_cache_range, leon_flush_cache_all,
+                        BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_page_for_dma, leon_flush_dcache_all,
+                        BTFIXUPCALL_NORM);
+
+        BTFIXUPSET_CALL(flush_tlb_all, leon_flush_tlb_all, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_tlb_mm, leon_flush_tlb_all, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_tlb_page, leon_flush_tlb_all, BTFIXUPCALL_NORM);
+        BTFIXUPSET_CALL(flush_tlb_range, leon_flush_tlb_all, BTFIXUPCALL_NORM);
+
+        BTFIXUPSET_CALL(__flush_page_to_ram, leon_flush_cache_all,
+                        BTFIXUPCALL_NOP);
+        BTFIXUPSET_CALL(flush_sig_insns, leon_flush_cache_all, BTFIXUPCALL_NOP);
+
+        poke_srmmu = poke_leonsparc;
+
+        srmmu_cache_pagetables = 0;
+
+        leon_flush_during_switch = leon_flush_needed();
+}
+#endif
+
 /* Probe for the srmmu chip version. */
 static void __init get_srmmu_type(void)
 {
@@ -1992,7 +2035,15 @@ static void __init get_srmmu_type(void)
         psr_typ = (psr >> 28) & 0xf;
         psr_vers = (psr >> 24) & 0xf;
 
-        /* First, check for HyperSparc or Cypress. */
+        /* First, check for sparc-leon. */
+        if (sparc_cpu_model == sparc_leon) {
+                psr_typ = 0xf;  /* hardcoded ids for older models/simulators */
+                psr_vers = 2;
+                init_leon();
+                return;
+        }
+
+        /* Second, check for HyperSparc or Cypress. */
         if(mod_typ == 1) {
                 switch(mod_rev) {
                 case 7:
diff --git a/arch/sparc/oprofile/init.c b/arch/sparc/oprofile/init.c
index d172f86439b1..f97cb8b6ee5f 100644
--- a/arch/sparc/oprofile/init.c
+++ b/arch/sparc/oprofile/init.c
@@ -21,7 +21,7 @@
 static int profile_timer_exceptions_notify(struct notifier_block *self,
                                            unsigned long val, void *data)
 {
-        struct die_args *args = (struct die_args *)data;
+        struct die_args *args = data;
         int ret = NOTIFY_DONE;
 
         switch (val) {
@@ -57,7 +57,7 @@ static void timer_stop(void)
 
 static int op_nmi_timer_init(struct oprofile_operations *ops)
 {
-        if (!nmi_usable)
+        if (atomic_read(&nmi_active) <= 0)
                 return -ENODEV;
 
         ops->start = timer_start;