18 files changed, 205 insertions, 113 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 0cc0995b81b0..803858e86160 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -20,7 +20,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o binfmt_elf32.o sys_ppc32.o \
                                    firmware.o sysfs.o
 obj-$(CONFIG_PPC64)             += vdso64/
 obj-$(CONFIG_ALTIVEC)           += vecemu.o vector.o
-obj-$(CONFIG_POWER4)            += idle_power4.o
+obj-$(CONFIG_PPC_970_NAP)       += idle_power4.o
 obj-$(CONFIG_PPC_OF)            += of_device.o prom_parse.o
 procfs-$(CONFIG_PPC64)          := proc_ppc64.o
 obj-$(CONFIG_PROC_FS)           += $(procfs-y)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 54b48f330051..8f85c5e8a55a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -91,6 +91,7 @@ int main(void)
 #endif /* CONFIG_PPC64 */
 
         DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
+        DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
         DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
         DEFINE(TI_TASK, offsetof(struct thread_info, task));
 #ifdef CONFIG_PPC32
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index b3a979467225..8866fd26c6b9 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -128,37 +128,36 @@ transfer_to_handler:
         stw     r12,4(r11)
 #endif
         b       3f
+
 2:      /* if from kernel, check interrupted DOZE/NAP mode and
          * check for stack overflow
          */
+        lwz     r9,THREAD_INFO-THREAD(r12)
+        cmplw   r1,r9                   /* if r1 <= current->thread_info */
+        ble-    stack_ovf               /* then the kernel stack overflowed */
+5:
 #ifdef CONFIG_6xx
-        mfspr   r11,SPRN_HID0
-        mtcr    r11
-BEGIN_FTR_SECTION
-        bt-     8,4f                    /* Check DOZE */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
-BEGIN_FTR_SECTION
-        bt-     9,4f                    /* Check NAP */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+        tophys(r9,r9)                   /* check local flags */
+        lwz     r12,TI_LOCAL_FLAGS(r9)
+        mtcrf   0x01,r12
+        bt-     31-TLF_NAPPING,4f
 #endif /* CONFIG_6xx */
         .globl transfer_to_handler_cont
 transfer_to_handler_cont:
-        lwz     r11,THREAD_INFO-THREAD(r12)
-        cmplw   r1,r11                  /* if r1 <= current->thread_info */
-        ble-    stack_ovf               /* then the kernel stack overflowed */
 3:
         mflr    r9
         lwz     r11,0(r9)               /* virtual address of handler */
         lwz     r9,4(r9)                /* where to go when done */
-        FIX_SRR1(r10,r12)
         mtspr   SPRN_SRR0,r11
         mtspr   SPRN_SRR1,r10
         mtlr    r9
         SYNC
         RFI                             /* jump to handler, enable MMU */
 
-#ifdef CONFIG_6xx       
-4:      b       power_save_6xx_restore
+#ifdef CONFIG_6xx
+4:      rlwinm  r12,r12,0,~_TLF_NAPPING
+        stw     r12,TI_LOCAL_FLAGS(r9)
+        b       power_save_6xx_restore
 #endif
 
 /*
@@ -167,10 +166,10 @@ transfer_to_handler_cont:
  */
 stack_ovf:
         /* sometimes we use a statically-allocated stack, which is OK. */
-        lis     r11,_end@h
-        ori     r11,r11,_end@l
-        cmplw   r1,r11
-        ble     3b                      /* r1 <= &_end is OK */
+        lis     r12,_end@h
+        ori     r12,r12,_end@l
+        cmplw   r1,r12
+        ble     5b                      /* r1 <= &_end is OK */
         SAVE_NVGPRS(r11)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         lis     r1,init_thread_union@ha
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index a5ae04a57c78..b7d140430a41 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -376,11 +376,28 @@ label##_common:						\
         bl      hdlr;                                   \
         b       .ret_from_except
 
+/*
+ * Like STD_EXCEPTION_COMMON, but for exceptions that can occur
+ * in the idle task and therefore need the special idle handling.
+ */
+#define STD_EXCEPTION_COMMON_IDLE(trap, label, hdlr)    \
+        .align  7;                                      \
+        .globl label##_common;                          \
+label##_common:                                         \
+        EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);      \
+        FINISH_NAP;                                     \
+        DISABLE_INTS;                                   \
+        bl      .save_nvgprs;                           \
+        addi    r3,r1,STACK_FRAME_OVERHEAD;             \
+        bl      hdlr;                                   \
+        b       .ret_from_except
+
 #define STD_EXCEPTION_COMMON_LITE(trap, label, hdlr)    \
         .align  7;                                      \
         .globl label##_common;                          \
 label##_common:                                         \
         EXCEPTION_PROLOG_COMMON(trap, PACA_EXGEN);      \
+        FINISH_NAP;                                     \
         DISABLE_INTS;                                   \
         bl      .ppc64_runlatch_on;                     \
         addi    r3,r1,STACK_FRAME_OVERHEAD;             \
@@ -388,6 +405,25 @@ label##_common:						\
         b       .ret_from_except_lite
 
 /*
+ * When the idle code in power4_idle puts the CPU into NAP mode,
+ * it has to do so in a loop, and relies on the external interrupt
+ * and decrementer interrupt entry code to get it out of the loop.
+ * It sets the _TLF_NAPPING bit in current_thread_info()->local_flags
+ * to signal that it is in the loop and needs help to get out.
+ */
+#ifdef CONFIG_PPC_970_NAP
+#define FINISH_NAP                              \
+BEGIN_FTR_SECTION                               \
+        clrrdi  r11,r1,THREAD_SHIFT;            \
+        ld      r9,TI_LOCAL_FLAGS(r11);         \
+        andi.   r10,r9,_TLF_NAPPING;            \
+        bnel    power4_fixup_nap;               \
+END_FTR_SECTION_IFSET(CPU_FTR_CAN_NAP)
+#else
+#define FINISH_NAP
+#endif
+
+/*
  * Start of pSeries system interrupt routines
  */
         . = 0x100
@@ -772,6 +808,7 @@ hardware_interrupt_iSeries_masked:
         .globl machine_check_common
 machine_check_common:
         EXCEPTION_PROLOG_COMMON(0x200, PACA_EXMC)
+        FINISH_NAP
         DISABLE_INTS
         bl      .save_nvgprs
         addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -783,7 +820,7 @@ machine_check_common:
         STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
         STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
         STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-        STD_EXCEPTION_COMMON(0xf00, performance_monitor, .performance_monitor_exception)
+        STD_EXCEPTION_COMMON_IDLE(0xf00, performance_monitor, .performance_monitor_exception)
         STD_EXCEPTION_COMMON(0x1300, instruction_breakpoint, .instruction_breakpoint_exception)
 #ifdef CONFIG_ALTIVEC
         STD_EXCEPTION_COMMON(0x1700, altivec_assist, .altivec_assist_exception)
@@ -1034,6 +1071,7 @@ unrecov_slb:
         .globl hardware_interrupt_entry
 hardware_interrupt_common:
         EXCEPTION_PROLOG_COMMON(0x500, PACA_EXGEN)
+        FINISH_NAP
 hardware_interrupt_entry:
         DISABLE_INTS
         bl      .ppc64_runlatch_on
@@ -1041,6 +1079,15 @@ hardware_interrupt_entry:
         bl      .do_IRQ
         b       .ret_from_except_lite
 
+#ifdef CONFIG_PPC_970_NAP
+power4_fixup_nap:
+        andc    r9,r9,r10
+        std     r9,TI_LOCAL_FLAGS(r11)
+        ld      r10,_LINK(r1)           /* make idle task do the */
+        std     r10,_NIP(r1)            /* equivalent of a blr */
+        blr
+#endif
+
         .align  7
         .globl alignment_common
 alignment_common:
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index e9f321d74d85..d491052c8e0c 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -50,9 +50,9 @@ void cpu_idle(void)
 
         set_thread_flag(TIF_POLLING_NRFLAG);
         while (1) {
-                ppc64_runlatch_off();
-
                 while (!need_resched() && !cpu_should_die()) {
+                        ppc64_runlatch_off();
+
                         if (ppc_md.power_save) {
                                 clear_thread_flag(TIF_POLLING_NRFLAG);
                                 /*
diff --git a/arch/powerpc/kernel/idle_6xx.S b/arch/powerpc/kernel/idle_6xx.S
index 12a4efbaa08f..b45fa0e37212 100644
--- a/arch/powerpc/kernel/idle_6xx.S
+++ b/arch/powerpc/kernel/idle_6xx.S
@@ -22,8 +22,6 @@
 #include <asm/ppc_asm.h>
 #include <asm/asm-offsets.h>
 
-#undef DEBUG
-
         .text
 
 /*
@@ -109,12 +107,6 @@ BEGIN_FTR_SECTION
         dcbf    0,r4
         dcbf    0,r4
 END_FTR_SECTION_IFSET(CPU_FTR_NAP_DISABLE_L2_PR)
-#ifdef DEBUG
-        lis     r6,nap_enter_count@ha
-        lwz     r4,nap_enter_count@l(r6)
-        addi    r4,r4,1
-        stw     r4,nap_enter_count@l(r6)
-#endif  
 2:
 BEGIN_FTR_SECTION
         /* Go to low speed mode on some 750FX */
@@ -144,48 +136,42 @@ BEGIN_FTR_SECTION
         DSSALL
         sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+        rlwinm  r9,r1,0,0,31-THREAD_SHIFT       /* current thread_info */
+        lwz     r8,TI_LOCAL_FLAGS(r9)   /* set napping bit */
+        ori     r8,r8,_TLF_NAPPING      /* so when we take an exception */
+        stw     r8,TI_LOCAL_FLAGS(r9)   /* it will return to our caller */
         mfmsr   r7
         ori     r7,r7,MSR_EE
         oris    r7,r7,MSR_POW@h
-        sync
-        isync
+1:      sync
         mtmsr   r7
         isync
-        sync
-        blr
-        
+        b       1b
+
 /*
  * Return from NAP/DOZE mode, restore some CPU specific registers,
  * we are called with DR/IR still off and r2 containing physical
- * address of current.
+ * address of current.  R11 points to the exception frame (physical
+ * address).  We have to preserve r10.
  */
 _GLOBAL(power_save_6xx_restore)
-        mfspr   r11,SPRN_HID0
-        rlwinm. r11,r11,0,10,8  /* Clear NAP & copy NAP bit !state to cr1 EQ */
-        cror    4*cr1+eq,4*cr0+eq,4*cr0+eq
-BEGIN_FTR_SECTION
-        rlwinm  r11,r11,0,9,7   /* Clear DOZE */
-END_FTR_SECTION_IFSET(CPU_FTR_CAN_DOZE)
-        mtspr   SPRN_HID0, r11
+        lwz     r9,_LINK(r11)           /* interrupted in ppc6xx_idle: */
+        stw     r9,_NIP(r11)            /* make it do a blr */
 
-#ifdef DEBUG
-        beq     cr1,1f
-        lis     r11,(nap_return_count-KERNELBASE)@ha
-        lwz     r9,nap_return_count@l(r11)
-        addi    r9,r9,1
-        stw     r9,nap_return_count@l(r11)
-1:
-#endif
-        
-        rlwinm  r9,r1,0,0,18
-        tophys(r9,r9)
-        lwz     r11,TI_CPU(r9)
+#ifdef CONFIG_SMP
+        mfspr   r12,SPRN_SPRG3
+        lwz     r11,TI_CPU(r12)         /* get cpu number * 4 */
         slwi    r11,r11,2
+#else
+        li      r11,0
+#endif
         /* Todo make sure all these are in the same page
-         * and load r22 (@ha part + CPU offset) only once
+         * and load r11 (@ha part + CPU offset) only once
          */
 BEGIN_FTR_SECTION
-        beq     cr1,1f
+        mfspr   r9,SPRN_HID0
+        andis.  r9,r9,HID0_NAP@h
+        beq     1f
         addis   r9,r11,(nap_save_msscr0-KERNELBASE)@ha
         lwz     r9,nap_save_msscr0@l(r9)
         mtspr   SPRN_MSSCR0, r9
@@ -210,10 +196,3 @@ _GLOBAL(nap_save_hid1)
 
 _GLOBAL(powersave_lowspeed)
         .long   0
-
-#ifdef DEBUG
-_GLOBAL(nap_enter_count)
-        .space  4
-_GLOBAL(nap_return_count)
-        .space  4
-#endif
diff --git a/arch/powerpc/kernel/idle_power4.S b/arch/powerpc/kernel/idle_power4.S
index 6dad1c02496e..d85c7c938eed 100644
--- a/arch/powerpc/kernel/idle_power4.S
+++ b/arch/powerpc/kernel/idle_power4.S
@@ -35,12 +35,16 @@ BEGIN_FTR_SECTION
         DSSALL
         sync
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
+        clrrdi  r9,r1,THREAD_SHIFT      /* current thread_info */
+        ld      r8,TI_LOCAL_FLAGS(r9)   /* set napping bit */
+        ori     r8,r8,_TLF_NAPPING      /* so when we take an exception */
+        std     r8,TI_LOCAL_FLAGS(r9)   /* it will return to our caller */
         mfmsr   r7
         ori     r7,r7,MSR_EE
         oris    r7,r7,MSR_POW@h
-        sync
+1:      sync
         isync
         mtmsrd  r7
         isync
-        sync
-        blr
+        b       1b
+
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index d9a7fdef59b9..4eba60a32890 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -61,6 +61,7 @@ __setup("iommu=", setup_iommu);
 static unsigned long iommu_range_alloc(struct iommu_table *tbl,
                                        unsigned long npages,
                                        unsigned long *handle,
+                                       unsigned long mask,
                                        unsigned int align_order)
 { 
         unsigned long n, end, i, start;
@@ -97,9 +98,21 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
          */
         if (start >= limit)
                 start = largealloc ? tbl->it_largehint : tbl->it_hint;
-        
+
  again:
 
+        if (limit + tbl->it_offset > mask) {
+                limit = mask - tbl->it_offset + 1;
+                /* If we're constrained on address range, first try
+                 * at the masked hint to avoid O(n) search complexity,
+                 * but on second pass, start at 0.
+                 */
+                if ((start & mask) >= limit || pass > 0)
+                        start = 0;
+                else
+                        start &= mask;
+        }
+
         n = find_next_zero_bit(tbl->it_map, limit, start);
 
         /* Align allocation */
@@ -150,14 +163,14 @@ static unsigned long iommu_range_alloc(struct iommu_table *tbl,
 
 static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page,
                        unsigned int npages, enum dma_data_direction direction,
-                       unsigned int align_order)
+                       unsigned long mask, unsigned int align_order)
 {
         unsigned long entry, flags;
         dma_addr_t ret = DMA_ERROR_CODE;
-        
+
         spin_lock_irqsave(&(tbl->it_lock), flags);
 
-        entry = iommu_range_alloc(tbl, npages, NULL, align_order);
+        entry = iommu_range_alloc(tbl, npages, NULL, mask, align_order);
 
         if (unlikely(entry == DMA_ERROR_CODE)) {
                 spin_unlock_irqrestore(&(tbl->it_lock), flags);
@@ -236,7 +249,7 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 
 int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 struct scatterlist *sglist, int nelems,
-                enum dma_data_direction direction)
+                unsigned long mask, enum dma_data_direction direction)
 {
         dma_addr_t dma_next = 0, dma_addr;
         unsigned long flags;
@@ -274,7 +287,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 vaddr = (unsigned long)page_address(s->page) + s->offset;
                 npages = PAGE_ALIGN(vaddr + slen) - (vaddr & PAGE_MASK);
                 npages >>= PAGE_SHIFT;
-                entry = iommu_range_alloc(tbl, npages, &handle, 0);
+                entry = iommu_range_alloc(tbl, npages, &handle, mask >> PAGE_SHIFT, 0);
 
                 DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -479,7 +492,8 @@ void iommu_free_table(struct device_node *dn)
  * byte within the page as vaddr.
  */
 dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
-                size_t size, enum dma_data_direction direction)
+                size_t size, unsigned long mask,
+                enum dma_data_direction direction)
 {
         dma_addr_t dma_handle = DMA_ERROR_CODE;
         unsigned long uaddr;
@@ -492,7 +506,8 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
         npages >>= PAGE_SHIFT;
 
         if (tbl) {
-                dma_handle = iommu_alloc(tbl, vaddr, npages, direction, 0);
+                dma_handle = iommu_alloc(tbl, vaddr, npages, direction,
+                                         mask >> PAGE_SHIFT, 0);
                 if (dma_handle == DMA_ERROR_CODE) {
                         if (printk_ratelimit())  {
                                 printk(KERN_INFO "iommu_alloc failed, "
@@ -521,7 +536,7 @@ void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
  * to the dma address (mapping) of the first page.
  */
 void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
-                dma_addr_t *dma_handle, gfp_t flag)
+                dma_addr_t *dma_handle, unsigned long mask, gfp_t flag)
 {
         void *ret = NULL;
         dma_addr_t mapping;
@@ -551,7 +566,8 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
         memset(ret, 0, size);
 
         /* Set up tces to cover the allocated range */
-        mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL, order);
+        mapping = iommu_alloc(tbl, ret, npages, DMA_BIDIRECTIONAL,
+                              mask >> PAGE_SHIFT, order);
         if (mapping == DMA_ERROR_CODE) {
                 free_pages((unsigned long)ret, order);
                 ret = NULL;
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index bb5c9501234c..57d560c68897 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -272,18 +272,26 @@ unsigned int virt_irq_to_real_map[NR_IRQS];
  * Don't use virtual irqs 0, 1, 2 for devices.
  * The pcnet32 driver considers interrupt numbers < 2 to be invalid,
  * and 2 is the XICS IPI interrupt.
- * We limit virtual irqs to 17 less than NR_IRQS so that when we
- * offset them by 16 (to reserve the first 16 for ISA interrupts)
- * we don't end up with an interrupt number >= NR_IRQS.
+ * We limit virtual irqs to __irq_offet_value less than virt_irq_max so
+ * that when we offset them we don't end up with an interrupt
+ * number >= virt_irq_max.
  */
 #define MIN_VIRT_IRQ    3
-#define MAX_VIRT_IRQ    (NR_IRQS - NUM_ISA_INTERRUPTS - 1)
-#define NR_VIRT_IRQS    (MAX_VIRT_IRQ - MIN_VIRT_IRQ + 1)
+
+unsigned int virt_irq_max;
+static unsigned int max_virt_irq;
+static unsigned int nr_virt_irqs;
 
 void
 virt_irq_init(void)
 {
         int i;
+
+        if ((virt_irq_max == 0) || (virt_irq_max > (NR_IRQS - 1)))
+                virt_irq_max = NR_IRQS - 1;
+        max_virt_irq = virt_irq_max - __irq_offset_value;
+        nr_virt_irqs = max_virt_irq - MIN_VIRT_IRQ + 1;
+
         for (i = 0; i < NR_IRQS; i++)
                 virt_irq_to_real_map[i] = UNDEFINED_IRQ;
 }
@@ -308,17 +316,17 @@ int virt_irq_create_mapping(unsigned int real_irq)
                 return real_irq;
         }
 
-        /* map to a number between MIN_VIRT_IRQ and MAX_VIRT_IRQ */
+        /* map to a number between MIN_VIRT_IRQ and max_virt_irq */
         virq = real_irq;
-        if (virq > MAX_VIRT_IRQ)
-                virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+        if (virq > max_virt_irq)
+                virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ;
 
         /* search for this number or a free slot */
         first_virq = virq;
         while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) {
                 if (virt_irq_to_real_map[virq] == real_irq)
                         return virq;
-                if (++virq > MAX_VIRT_IRQ)
+                if (++virq > max_virt_irq)
                         virq = MIN_VIRT_IRQ;
                 if (virq == first_virq)
                         goto nospace;   /* oops, no free slots */
@@ -330,8 +338,8 @@ int virt_irq_create_mapping(unsigned int real_irq)
  nospace:
         if (!warned) {
                 printk(KERN_CRIT "Interrupt table is full\n");
-                printk(KERN_CRIT "Increase NR_IRQS (currently %d) "
-                       "in your kernel sources and rebuild.\n", NR_IRQS);
+                printk(KERN_CRIT "Increase virt_irq_max (currently %d) "
+                       "in your kernel sources and rebuild.\n", virt_irq_max);
                 warned = 1;
         }
         return NO_IRQ;
@@ -349,8 +357,8 @@ unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
 
         virq = real_irq;
 
-        if (virq > MAX_VIRT_IRQ)
-                virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;
+        if (virq > max_virt_irq)
+                virq = (virq % nr_virt_irqs) + MIN_VIRT_IRQ;
 
         first_virq = virq;
 
@@ -360,7 +368,7 @@ unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
 
                 virq++;
 
-                if (virq >= MAX_VIRT_IRQ)
+                if (virq >= max_virt_irq)
                         virq = 0;
 
         } while (first_virq != virq);
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index ad7a90212204..856ef1a832b9 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -88,7 +88,7 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
         mutex_unlock(&kprobe_mutex);
 }
 
-static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
         kprobe_opcode_t insn = *p->ainsn.insn;
 
@@ -101,21 +101,21 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
                 regs->nip = (unsigned long)p->ainsn.insn;
 }
 
-static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
+static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
         kcb->prev_kprobe.kp = kprobe_running();
         kcb->prev_kprobe.status = kcb->kprobe_status;
         kcb->prev_kprobe.saved_msr = kcb->kprobe_saved_msr;
 }
 
-static inline void restore_previous_kprobe(struct kprobe_ctlblk *kcb)
+static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
         __get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
         kcb->kprobe_status = kcb->prev_kprobe.status;
         kcb->kprobe_saved_msr = kcb->prev_kprobe.saved_msr;
 }
 
-static inline void set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
+static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs,
                                 struct kprobe_ctlblk *kcb)
 {
         __get_cpu_var(current_kprobe) = p;
@@ -141,7 +141,7 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe *rp,
         }
 }
 
-static inline int kprobe_handler(struct pt_regs *regs)
+static int __kprobes kprobe_handler(struct pt_regs *regs)
 {
         struct kprobe *p;
         int ret = 0;
@@ -334,7 +334,7 @@ static void __kprobes resume_execution(struct kprobe *p, struct pt_regs *regs)
                 regs->nip = (unsigned long)p->addr + 4;
 }
 
-static inline int post_kprobe_handler(struct pt_regs *regs)
+static int __kprobes post_kprobe_handler(struct pt_regs *regs)
 {
         struct kprobe *cur = kprobe_running();
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
@@ -370,7 +370,7 @@ out:
         return 1;
 }
 
-static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+static int __kprobes kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 {
         struct kprobe *cur = kprobe_running();
         struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
diff --git a/arch/powerpc/kernel/pci_iommu.c b/arch/powerpc/kernel/pci_iommu.c
index c336f3e31cff..c1d95e14bbed 100644
--- a/arch/powerpc/kernel/pci_iommu.c
+++ b/arch/powerpc/kernel/pci_iommu.c
@@ -59,6 +59,25 @@ static inline struct iommu_table *devnode_table(struct device *dev)
 }
 
 
+static inline unsigned long device_to_mask(struct device *hwdev)
+{
+        struct pci_dev *pdev;
+
+        if (!hwdev) {
+                pdev = ppc64_isabridge_dev;
+                if (!pdev) /* This is the best guess we can do */
+                        return 0xfffffffful;
+        } else
+                pdev = to_pci_dev(hwdev);
+
+        if (pdev->dma_mask)
+                return pdev->dma_mask;
+
+        /* Assume devices without mask can take 32 bit addresses */
+        return 0xfffffffful;
+}
+
+
 /* Allocates a contiguous real buffer and creates mappings over it.
  * Returns the virtual address of the buffer and sets dma_handle
  * to the dma address (mapping) of the first page.
@@ -67,7 +86,7 @@ static void *pci_iommu_alloc_coherent(struct device *hwdev, size_t size,
                            dma_addr_t *dma_handle, gfp_t flag)
 {
         return iommu_alloc_coherent(devnode_table(hwdev), size, dma_handle,
-                        flag);
+                        device_to_mask(hwdev), flag);
 }
 
 static void pci_iommu_free_coherent(struct device *hwdev, size_t size,
@@ -85,7 +104,8 @@ static void pci_iommu_free_coherent(struct device *hwdev, size_t size,
 static dma_addr_t pci_iommu_map_single(struct device *hwdev, void *vaddr,
                 size_t size, enum dma_data_direction direction)
 {
-        return iommu_map_single(devnode_table(hwdev), vaddr, size, direction);
+        return iommu_map_single(devnode_table(hwdev), vaddr, size,
+                                device_to_mask(hwdev), direction);
 }
 
 
@@ -100,7 +120,7 @@ static int pci_iommu_map_sg(struct device *pdev, struct scatterlist *sglist,
                 int nelems, enum dma_data_direction direction)
 {
         return iommu_map_sg(pdev, devnode_table(pdev), sglist,
-                        nelems, direction);
+                        nelems, device_to_mask(pdev), direction);
 }
 
 static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist,
@@ -112,7 +132,19 @@ static void pci_iommu_unmap_sg(struct device *pdev, struct scatterlist *sglist,
 /* We support DMA to/from any memory page via the iommu */
 static int pci_iommu_dma_supported(struct device *dev, u64 mask)
 {
-        return 1;
+        struct iommu_table *tbl = devnode_table(dev);
+
+        if (!tbl || tbl->it_offset > mask) {
+                printk(KERN_INFO "Warning: IOMMU table offset too big for device mask\n");
+                if (tbl)
+                        printk(KERN_INFO "mask: 0x%08lx, table offset: 0x%08lx\n",
+                                mask, tbl->it_offset);
+                else
+                        printk(KERN_INFO "mask: 0x%08lx, table unavailable\n",
+                                mask);
+                return 0;
+        } else
+                return 1;
 }
 
 void pci_iommu_init(void)
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index dfa5398ab3c8..4b052ae5dc34 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -81,6 +81,7 @@ EXPORT_SYMBOL(strcat);
 EXPORT_SYMBOL(strlen);
 EXPORT_SYMBOL(strcmp);
 EXPORT_SYMBOL(strcasecmp);
+EXPORT_SYMBOL(strncasecmp);
 
 EXPORT_SYMBOL(csum_partial);
 EXPORT_SYMBOL(csum_partial_copy_generic);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 4336390bcf34..1cb69e8fb0b1 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -62,7 +62,7 @@ static int __initdata dt_root_addr_cells;
 static int __initdata dt_root_size_cells;
 
 #ifdef CONFIG_PPC64
-static int __initdata iommu_is_off;
+int __initdata iommu_is_off;
 int __initdata iommu_force_on;
 unsigned long tce_alloc_start, tce_alloc_end;
 #endif
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index d66c5e77fcff..7e4d54821a07 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -1528,12 +1528,11 @@ static int __init prom_find_machine_type(void)
          *    non-IBM designs !
          *  - it has /rtas
          */
-        len = prom_getprop(_prom->root, "model",
+        len = prom_getprop(_prom->root, "device_type",
                            compat, sizeof(compat)-1);
         if (len <= 0)
                 return PLATFORM_GENERIC;
-        compat[len] = 0;
-        if (strcmp(compat, "chrp"))
+        if (strncmp(compat, RELOC("chrp"), 4))
                 return PLATFORM_GENERIC;
 
         /* Default to pSeries. We need to know if we are running LPAR */
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index 456286cf1d14..9c9ad1fa9cce 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -258,11 +258,11 @@ static int __init proc_rtas_init(void)
         struct proc_dir_entry *entry;
 
         if (!machine_is(pseries))
-                return 1;
+                return -ENODEV;
 
         rtas_node = of_find_node_by_name(NULL, "rtas");
         if (rtas_node == NULL)
-                return 1;
+                return -ENODEV;
 
         entry = create_proc_entry("ppc64/rtas/progress", S_IRUGO|S_IWUSR, NULL);
         if (entry)
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 73560ef6f802..ed737cacf92d 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -279,7 +279,7 @@ static void unregister_cpu_online(unsigned int cpu)
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __devinit sysfs_cpu_notify(struct notifier_block *self,
+static int sysfs_cpu_notify(struct notifier_block *self,
                                       unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned int)(long)hcpu;
@@ -297,7 +297,7 @@ static int __devinit sysfs_cpu_notify(struct notifier_block *self,
         return NOTIFY_OK;
 }
 
-static struct notifier_block __devinitdata sysfs_cpu_nb = {
+static struct notifier_block sysfs_cpu_nb = {
         .notifier_call  = sysfs_cpu_notify,
 };
 
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index a14c96403840..0b98eea73c5e 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -324,3 +324,9 @@ COMPAT_SYS(ppoll)
 SYSCALL(unshare)
 SYSCALL(splice)
 SYSCALL(tee)
+SYSCALL(vmsplice)
+
+/*
+ * please add new calls to arch/powerpc/platforms/cell/spu_callbacks.c
+ * as well when appropriate.
+ */
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 13c655ba2841..971020cf3f7d 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -202,7 +202,7 @@ static dma_addr_t vio_map_single(struct device *dev, void *vaddr,
                           size_t size, enum dma_data_direction direction)
 {
         return iommu_map_single(to_vio_dev(dev)->iommu_table, vaddr, size,
-                        direction);
+                        ~0ul, direction);
 }
 
 static void vio_unmap_single(struct device *dev, dma_addr_t dma_handle,
@@ -216,7 +216,7 @@ static int vio_map_sg(struct device *dev, struct scatterlist *sglist,
                 int nelems, enum dma_data_direction direction)
 {
         return iommu_map_sg(dev, to_vio_dev(dev)->iommu_table, sglist,
-                        nelems, direction);
+                        nelems, ~0ul, direction);
 }
 
 static void vio_unmap_sg(struct device *dev, struct scatterlist *sglist,
@@ -229,7 +229,7 @@ static void *vio_alloc_coherent(struct device *dev, size_t size,
                            dma_addr_t *dma_handle, gfp_t flag)
 {
         return iommu_alloc_coherent(to_vio_dev(dev)->iommu_table, size,
-                        dma_handle, flag);
+                        dma_handle, ~0ul, flag);
 }
 
 static void vio_free_coherent(struct device *dev, size_t size,