23 files changed, 375 insertions, 586 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 8b133afbdc20..7af23c43fd4b 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -38,7 +38,6 @@ obj-$(CONFIG_6xx)		+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
 obj-$(CONFIG_TAU)               += tau_6xx.o
 obj32-$(CONFIG_SOFTWARE_SUSPEND) += swsusp_32.o
 obj32-$(CONFIG_MODULES)         += module_32.o
-obj-$(CONFIG_E500)              += perfmon_fsl_booke.o
 
 ifeq ($(CONFIG_PPC_MERGE),y)
 
diff --git a/arch/powerpc/kernel/btext.c b/arch/powerpc/kernel/btext.c
index 995fcef156fd..93f21aaf7c8e 100644
--- a/arch/powerpc/kernel/btext.c
+++ b/arch/powerpc/kernel/btext.c
@@ -182,7 +182,7 @@ int btext_initialize(struct device_node *np)
         prop = get_property(np, "linux,bootx-linebytes", NULL);
         if (prop == NULL)
                 prop = get_property(np, "linebytes", NULL);
-        if (prop)
+        if (prop && *prop != 0xffffffffu)
                 pitch = *prop;
         if (pitch == 1)
                 pitch = 0x1000;
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 95382f994404..bfd499ee3753 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -18,6 +18,7 @@
 
 #include <asm/oprofile_impl.h>
 #include <asm/cputable.h>
+#include <asm/prom.h>           /* for PTRRELOC on ARCH=ppc */
 
 struct cpu_spec* cur_cpu_spec = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
@@ -73,7 +74,7 @@ extern void __restore_cpu_ppc970(void);
 #define PPC_FEATURE_SPE_COMP    0
 #endif
 
-struct cpu_spec cpu_specs[] = {
+static struct cpu_spec cpu_specs[] = {
 #ifdef CONFIG_PPC64
         {       /* Power3 */
                 .pvr_mask               = 0xffff0000,
@@ -227,6 +228,21 @@ struct cpu_spec	cpu_specs[] = {
                 .oprofile_type          = PPC_OPROFILE_POWER4,
                 .platform               = "ppc970",
         },
+        {       /* PPC970GX */
+                .pvr_mask               = 0xffff0000,
+                .pvr_value              = 0x00450000,
+                .cpu_name               = "PPC970GX",
+                .cpu_features           = CPU_FTRS_PPC970,
+                .cpu_user_features      = COMMON_USER_POWER4 |
+                        PPC_FEATURE_HAS_ALTIVEC_COMP,
+                .icache_bsize           = 128,
+                .dcache_bsize           = 128,
+                .num_pmcs               = 8,
+                .cpu_setup              = __setup_cpu_ppc970,
+                .oprofile_cpu_type      = "ppc64/970",
+                .oprofile_type          = PPC_OPROFILE_POWER4,
+                .platform               = "ppc970",
+        },
         {       /* Power5 GR */
                 .pvr_mask               = 0xffff0000,
                 .pvr_value              = 0x003a0000,
@@ -1152,3 +1168,71 @@ struct cpu_spec	cpu_specs[] = {
 #endif /* !CLASSIC_PPC */
 #endif /* CONFIG_PPC32 */
 };
+
+struct cpu_spec *identify_cpu(unsigned long offset)
+{
+        struct cpu_spec *s = cpu_specs;
+        struct cpu_spec **cur = &cur_cpu_spec;
+        unsigned int pvr = mfspr(SPRN_PVR);
+        int i;
+
+        s = PTRRELOC(s);
+        cur = PTRRELOC(cur);
+
+        if (*cur != NULL)
+                return PTRRELOC(*cur);
+
+        for (i = 0; i < ARRAY_SIZE(cpu_specs); i++,s++)
+                if ((pvr & s->pvr_mask) == s->pvr_value) {
+                        *cur = cpu_specs + i;
+#ifdef CONFIG_PPC64
+                        /* ppc64 expects identify_cpu to also call setup_cpu
+                         * for that processor. I will consolidate that at a
+                         * later time, for now, just use our friend #ifdef.
+                         * we also don't need to PTRRELOC the function pointer
+                         * on ppc64 as we are running at 0 in real mode.
+                         */
+                        if (s->cpu_setup) {
+                                s->cpu_setup(offset, s);
+                        }
+#endif /* CONFIG_PPC64 */
+                        return s;
+                }
+        BUG();
+        return NULL;
+}
+
+void do_feature_fixups(unsigned long value, void *fixup_start, void *fixup_end)
+{
+        struct fixup_entry {
+                unsigned long   mask;
+                unsigned long   value;
+                long            start_off;
+                long            end_off;
+        } *fcur, *fend;
+
+        fcur = fixup_start;
+        fend = fixup_end;
+
+        for (; fcur < fend; fcur++) {
+                unsigned int *pstart, *pend, *p;
+
+                if ((value & fcur->mask) == fcur->value)
+                        continue;
+
+                /* These PTRRELOCs will disappear once the new scheme for
+                 * modules and vdso is implemented
+                 */
+                pstart = ((unsigned int *)fcur) + (fcur->start_off / 4);
+                pend = ((unsigned int *)fcur) + (fcur->end_off / 4);
+
+                for (p = pstart; p < pend; p++) {
+                        *p = 0x60000000u;
+                        asm volatile ("dcbst 0, %0" : : "r" (p));
+                }
+                asm volatile ("sync" : : : "memory");
+                for (p = pstart; p < pend; p++)
+                        asm volatile ("icbi 0,%0" : : "r" (p));
+                asm volatile ("sync; isync" : : : "memory");
+        }
+}
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index 645c7f10fb28..e720729f3e55 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -487,7 +487,7 @@ BEGIN_FTR_SECTION
         rlwimi  r13,r12,16,0x20
         mfcr    r12
         cmpwi   r13,0x2c
-        beq     .do_stab_bolted_pSeries
+        beq     do_stab_bolted_pSeries
         mtcrf   0x80,r12
         mfspr   r12,SPRN_SPRG2
 END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
@@ -600,7 +600,7 @@ system_call_pSeries:
         STD_EXCEPTION_PSERIES(., performance_monitor)
 
         .align  7
-_GLOBAL(do_stab_bolted_pSeries)
+do_stab_bolted_pSeries:
         mtcrf   0x80,r12
         mfspr   r12,SPRN_SPRG2
         EXCEPTION_PROLOG_PSERIES(PACA_EXSLB, .do_stab_bolted)
@@ -1046,7 +1046,7 @@ slb_miss_fault:
         li      r5,0
         std     r4,_DAR(r1)
         std     r5,_DSISR(r1)
-        b       .handle_page_fault
+        b       handle_page_fault
 
 unrecov_user_slb:
         EXCEPTION_PROLOG_COMMON(0x4200, PACA_EXGEN)
@@ -1174,12 +1174,13 @@ program_check_common:
         .globl fp_unavailable_common
 fp_unavailable_common:
         EXCEPTION_PROLOG_COMMON(0x800, PACA_EXGEN)
-        bne     .load_up_fpu            /* if from user, just load it up */
+        bne     1f                      /* if from user, just load it up */
         bl      .save_nvgprs
         addi    r3,r1,STACK_FRAME_OVERHEAD
         ENABLE_INTS
         bl      .kernel_fp_unavailable_exception
         BUG_OPCODE
+1:      b       .load_up_fpu
 
         .align  7
         .globl altivec_unavailable_common
@@ -1279,10 +1280,10 @@ _GLOBAL(do_hash_page)
         std     r4,_DSISR(r1)
 
         andis.  r0,r4,0xa450            /* weird error? */
-        bne-    .handle_page_fault      /* if not, try to insert a HPTE */
+        bne-    handle_page_fault       /* if not, try to insert a HPTE */
 BEGIN_FTR_SECTION
         andis.  r0,r4,0x0020            /* Is it a segment table fault? */
-        bne-    .do_ste_alloc           /* If so handle it */
+        bne-    do_ste_alloc            /* If so handle it */
 END_FTR_SECTION_IFCLR(CPU_FTR_SLB)
 
         /*
@@ -1324,7 +1325,7 @@ BEGIN_FW_FTR_SECTION
          * because ret_from_except_lite will check for and handle pending
          * interrupts if necessary.
          */
-        beq     .ret_from_except_lite
+        beq     13f
         /* For a hash failure, we don't bother re-enabling interrupts */
         ble-    12f
 
@@ -1346,14 +1347,14 @@ BEGIN_FW_FTR_SECTION
 END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISERIES)
 
 /* Here we have a page fault that hash_page can't handle. */
-_GLOBAL(handle_page_fault)
+handle_page_fault:
         ENABLE_INTS
 11:     ld      r4,_DAR(r1)
         ld      r5,_DSISR(r1)
         addi    r3,r1,STACK_FRAME_OVERHEAD
         bl      .do_page_fault
         cmpdi   r3,0
-        beq+    .ret_from_except_lite
+        beq+    13f
         bl      .save_nvgprs
         mr      r5,r3
         addi    r3,r1,STACK_FRAME_OVERHEAD
@@ -1370,12 +1371,14 @@ _GLOBAL(handle_page_fault)
         bl      .low_hash_fault
         b       .ret_from_except
 
+13:     b       .ret_from_except_lite
+
         /* here we have a segment miss */
-_GLOBAL(do_ste_alloc)
+do_ste_alloc:
         bl      .ste_allocate           /* try to insert stab entry */
         cmpdi   r3,0
-        beq+    fast_exception_return
-        b       .handle_page_fault
+        bne-    handle_page_fault
+        b       fast_exception_return
 
 /*
  * r13 points to the PACA, r9 contains the saved CR,
@@ -1580,11 +1583,6 @@ _STATIC(__start_initialization_iSeries)
         li      r0,0
         stdu    r0,-STACK_FRAME_OVERHEAD(r1)
 
-        LOAD_REG_IMMEDIATE(r3,cpu_specs)
-        LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-        li      r5,0
-        bl      .identify_cpu
-
         LOAD_REG_IMMEDIATE(r2,__toc_start)
         addi    r2,r2,0x4000
         addi    r2,r2,0x4000
@@ -1646,6 +1644,8 @@ _GLOBAL(__start_initialization_multiplatform)
         cmpwi   r0,0x3c         /* 970FX */
         beq     1f
         cmpwi   r0,0x44         /* 970MP */
+        beq     1f
+        cmpwi   r0,0x45         /* 970GX */
         bne     2f
 1:      bl      .__cpu_preinit_ppc970
 2:
@@ -1964,13 +1964,6 @@ _STATIC(start_here_multiplatform)
         addi    r2,r2,0x4000
         add     r2,r2,r26
 
-        LOAD_REG_IMMEDIATE(r3, cpu_specs)
-        add     r3,r3,r26
-        LOAD_REG_IMMEDIATE(r4,cur_cpu_spec)
-        add     r4,r4,r26
-        mr      r5,r26
-        bl      .identify_cpu
-
         /* Do very early kernel initializations, including initial hash table,
          * stab and slb setup before we turn on relocation.     */
 
@@ -2000,13 +1993,6 @@ _STATIC(start_here_common)
         li      r0,0
         stdu    r0,-STACK_FRAME_OVERHEAD(r1)
 
-        /* Apply the CPUs-specific fixups (nop out sections not relevant
-         * to this CPU
-         */
-        li      r3,0
-        bl      .do_cpu_ftr_fixups
-        bl      .do_fw_ftr_fixups
-
         /* ptr to current */
         LOAD_REG_IMMEDIATE(r4, init_task)
         std     r4,PACACURRENT(r13)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index f88a2a675d90..ba6b7256084b 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -47,6 +47,17 @@ static int novmerge = 0;
 static int novmerge = 1;
 #endif
 
+static inline unsigned long iommu_num_pages(unsigned long vaddr,
+                                            unsigned long slen)
+{
+        unsigned long npages;
+
+        npages = IOMMU_PAGE_ALIGN(vaddr + slen) - (vaddr & IOMMU_PAGE_MASK);
+        npages >>= IOMMU_PAGE_SHIFT;
+
+        return npages;
+}
+
 static int __init setup_iommu(char *str)
 {
         if (!strcmp(str, "novmerge"))
@@ -178,10 +189,10 @@ static dma_addr_t iommu_alloc(struct iommu_table *tbl, void *page,
         }
 
         entry += tbl->it_offset;        /* Offset into real TCE table */
-        ret = entry << PAGE_SHIFT;      /* Set the return dma address */
+        ret = entry << IOMMU_PAGE_SHIFT;        /* Set the return dma address */
 
         /* Put the TCEs in the HW table */
-        ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & PAGE_MASK,
+        ppc_md.tce_build(tbl, entry, npages, (unsigned long)page & IOMMU_PAGE_MASK,
                          direction);
 
 
@@ -203,7 +214,7 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
         unsigned long entry, free_entry;
         unsigned long i;
 
-        entry = dma_addr >> PAGE_SHIFT;
+        entry = dma_addr >> IOMMU_PAGE_SHIFT;
         free_entry = entry - tbl->it_offset;
 
         if (((free_entry + npages) > tbl->it_size) ||
@@ -270,7 +281,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
         /* Init first segment length for backout at failure */
         outs->dma_length = 0;
 
-        DBG("mapping %d elements:\n", nelems);
+        DBG("sg mapping %d elements:\n", nelems);
 
         spin_lock_irqsave(&(tbl->it_lock), flags);
 
@@ -285,9 +296,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 }
                 /* Allocate iommu entries for that segment */
                 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, mask >> PAGE_SHIFT, 0);
+                npages = iommu_num_pages(vaddr, slen);
+                entry = iommu_range_alloc(tbl, npages, &handle, mask >> IOMMU_PAGE_SHIFT, 0);
 
                 DBG("  - vaddr: %lx, size: %lx\n", vaddr, slen);
 
@@ -301,14 +311,14 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
 
                 /* Convert entry to a dma_addr_t */
                 entry += tbl->it_offset;
-                dma_addr = entry << PAGE_SHIFT;
-                dma_addr |= s->offset;
+                dma_addr = entry << IOMMU_PAGE_SHIFT;
+                dma_addr |= (s->offset & ~IOMMU_PAGE_MASK);
 
-                DBG("  - %lx pages, entry: %lx, dma_addr: %lx\n",
+                DBG("  - %lu pages, entry: %lx, dma_addr: %lx\n",
                             npages, entry, dma_addr);
 
                 /* Insert into HW table */
-                ppc_md.tce_build(tbl, entry, npages, vaddr & PAGE_MASK, direction);
+                ppc_md.tce_build(tbl, entry, npages, vaddr & IOMMU_PAGE_MASK, direction);
 
                 /* If we are in an open segment, try merging */
                 if (segstart != s) {
@@ -323,7 +333,7 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                                 DBG("    can't merge, new segment.\n");
                         } else {
                                 outs->dma_length += s->length;
-                                DBG("    merged, new len: %lx\n", outs->dma_length);
+                                DBG("    merged, new len: %ux\n", outs->dma_length);
                         }
                 }
 
@@ -367,9 +377,8 @@ int iommu_map_sg(struct device *dev, struct iommu_table *tbl,
                 if (s->dma_length != 0) {
                         unsigned long vaddr, npages;
 
-                        vaddr = s->dma_address & PAGE_MASK;
-                        npages = (PAGE_ALIGN(s->dma_address + s->dma_length) - vaddr)
-                                >> PAGE_SHIFT;
+                        vaddr = s->dma_address & IOMMU_PAGE_MASK;
+                        npages = iommu_num_pages(s->dma_address, s->dma_length);
                         __iommu_free(tbl, vaddr, npages);
                         s->dma_address = DMA_ERROR_CODE;
                         s->dma_length = 0;
@@ -398,8 +407,7 @@ void iommu_unmap_sg(struct iommu_table *tbl, struct scatterlist *sglist,
 
                 if (sglist->dma_length == 0)
                         break;
-                npages = (PAGE_ALIGN(dma_handle + sglist->dma_length)
-                          - (dma_handle & PAGE_MASK)) >> PAGE_SHIFT;
+                npages = iommu_num_pages(dma_handle,sglist->dma_length);
                 __iommu_free(tbl, dma_handle, npages);
                 sglist++;
         }
@@ -532,12 +540,11 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
         BUG_ON(direction == DMA_NONE);
 
         uaddr = (unsigned long)vaddr;
-        npages = PAGE_ALIGN(uaddr + size) - (uaddr & PAGE_MASK);
-        npages >>= PAGE_SHIFT;
+        npages = iommu_num_pages(uaddr, size);
 
         if (tbl) {
                 dma_handle = iommu_alloc(tbl, vaddr, npages, direction,
-                                         mask >> PAGE_SHIFT, 0);
+                                         mask >> IOMMU_PAGE_SHIFT, 0);
                 if (dma_handle == DMA_ERROR_CODE) {
                         if (printk_ratelimit())  {
                                 printk(KERN_INFO "iommu_alloc failed, "
@@ -545,7 +552,7 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
                                                 tbl, vaddr, npages);
                         }
                 } else
-                        dma_handle |= (uaddr & ~PAGE_MASK);
+                        dma_handle |= (uaddr & ~IOMMU_PAGE_MASK);
         }
 
         return dma_handle;
@@ -554,11 +561,14 @@ dma_addr_t iommu_map_single(struct iommu_table *tbl, void *vaddr,
 void iommu_unmap_single(struct iommu_table *tbl, dma_addr_t dma_handle,
                 size_t size, enum dma_data_direction direction)
 {
+        unsigned int npages;
+
         BUG_ON(direction == DMA_NONE);
 
-        if (tbl)
-                iommu_free(tbl, dma_handle, (PAGE_ALIGN(dma_handle + size) -
-                                        (dma_handle & PAGE_MASK)) >> PAGE_SHIFT);
+        if (tbl) {
+                npages = iommu_num_pages(dma_handle, size);
+                iommu_free(tbl, dma_handle, npages);
+        }
 }
 
 /* Allocates a contiguous real buffer and creates mappings over it.
@@ -570,11 +580,11 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
 {
         void *ret = NULL;
         dma_addr_t mapping;
-        unsigned int npages, order;
+        unsigned int order;
+        unsigned int nio_pages, io_order;
         struct page *page;
 
         size = PAGE_ALIGN(size);
-        npages = size >> PAGE_SHIFT;
         order = get_order(size);
 
         /*
@@ -598,8 +608,10 @@ 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,
-                              mask >> PAGE_SHIFT, order);
+        nio_pages = size >> IOMMU_PAGE_SHIFT;
+        io_order = get_iommu_order(size);
+        mapping = iommu_alloc(tbl, ret, nio_pages, DMA_BIDIRECTIONAL,
+                              mask >> IOMMU_PAGE_SHIFT, io_order);
         if (mapping == DMA_ERROR_CODE) {
                 free_pages((unsigned long)ret, order);
                 return NULL;
@@ -611,12 +623,13 @@ void *iommu_alloc_coherent(struct iommu_table *tbl, size_t size,
 void iommu_free_coherent(struct iommu_table *tbl, size_t size,
                          void *vaddr, dma_addr_t dma_handle)
 {
-        unsigned int npages;
-
         if (tbl) {
+                unsigned int nio_pages;
+
+                size = PAGE_ALIGN(size);
+                nio_pages = size >> IOMMU_PAGE_SHIFT;
+                iommu_free(tbl, dma_handle, nio_pages);
                 size = PAGE_ALIGN(size);
-                npages = size >> PAGE_SHIFT;
-                iommu_free(tbl, dma_handle, npages);
                 free_pages((unsigned long)vaddr, get_order(size));
         }
 }
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 88fd73fdf048..412bea3cf813 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -102,80 +102,6 @@ _GLOBAL(reloc_got2)
         blr
 
 /*
- * identify_cpu,
- * called with r3 = data offset and r4 = CPU number
- * doesn't change r3
- */
-_GLOBAL(identify_cpu)
-        addis   r8,r3,cpu_specs@ha
-        addi    r8,r8,cpu_specs@l
-        mfpvr   r7
-1:
-        lwz     r5,CPU_SPEC_PVR_MASK(r8)
-        and     r5,r5,r7
-        lwz     r6,CPU_SPEC_PVR_VALUE(r8)
-        cmplw   0,r6,r5
-        beq     1f
-        addi    r8,r8,CPU_SPEC_ENTRY_SIZE
-        b       1b
-1:
-        addis   r6,r3,cur_cpu_spec@ha
-        addi    r6,r6,cur_cpu_spec@l
-        sub     r8,r8,r3
-        stw     r8,0(r6)
-        blr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-        /* Get CPU 0 features */
-        addis   r6,r3,cur_cpu_spec@ha
-        addi    r6,r6,cur_cpu_spec@l
-        lwz     r4,0(r6)
-        add     r4,r4,r3
-        lwz     r4,CPU_SPEC_FEATURES(r4)
-
-        /* Get the fixup table */
-        addis   r6,r3,__start___ftr_fixup@ha
-        addi    r6,r6,__start___ftr_fixup@l
-        addis   r7,r3,__stop___ftr_fixup@ha
-        addi    r7,r7,__stop___ftr_fixup@l
-
-        /* Do the fixup */
-1:      cmplw   0,r6,r7
-        bgelr
-        addi    r6,r6,16
-        lwz     r8,-16(r6)      /* mask */
-        and     r8,r8,r4
-        lwz     r9,-12(r6)      /* value */
-        cmplw   0,r8,r9
-        beq     1b
-        lwz     r8,-8(r6)       /* section begin */
-        lwz     r9,-4(r6)       /* section end */
-        subf.   r9,r8,r9
-        beq     1b
-        /* write nops over the section of code */
-        /* todo: if large section, add a branch at the start of it */
-        srwi    r9,r9,2
-        mtctr   r9
-        add     r8,r8,r3
-        lis     r0,0x60000000@h /* nop */
-3:      stw     r0,0(r8)
-        andi.   r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-        beq     2f
-        dcbst   0,r8            /* suboptimal, but simpler */
-        sync
-        icbi    0,r8
-2:      addi    r8,r8,4
-        bdnz    3b
-        sync                    /* additional sync needed on g4 */
-        isync
-        b       1b
-
-/*
  * call_setup_cpu - call the setup_cpu function for this cpu
  * r3 = data offset, r24 = cpu number
  *
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index c70e20708a1f..21fd2c662a99 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -246,130 +246,6 @@ _GLOBAL(__flush_dcache_icache)
         isync
         blr
 
-/*
- * identify_cpu and calls setup_cpu
- * In:  r3 = base of the cpu_specs array
- *      r4 = address of cur_cpu_spec
- *      r5 = relocation offset
- */
-_GLOBAL(identify_cpu)
-        mfpvr   r7
-1:
-        lwz     r8,CPU_SPEC_PVR_MASK(r3)
-        and     r8,r8,r7
-        lwz     r9,CPU_SPEC_PVR_VALUE(r3)
-        cmplw   0,r9,r8
-        beq     1f
-        addi    r3,r3,CPU_SPEC_ENTRY_SIZE
-        b       1b
-1:
-        sub     r0,r3,r5
-        std     r0,0(r4)
-        ld      r4,CPU_SPEC_SETUP(r3)
-        cmpdi   0,r4,0
-        add     r4,r4,r5
-        beqlr
-        ld      r4,0(r4)
-        add     r4,r4,r5
-        mtctr   r4
-        /* Calling convention for cpu setup is r3=offset, r4=cur_cpu_spec */
-        mr      r4,r3
-        mr      r3,r5
-        bctr
-
-/*
- * do_cpu_ftr_fixups - goes through the list of CPU feature fixups
- * and writes nop's over sections of code that don't apply for this cpu.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_cpu_ftr_fixups)
-        /* Get CPU 0 features */
-        LOAD_REG_IMMEDIATE(r6,cur_cpu_spec)
-        sub     r6,r6,r3
-        ld      r4,0(r6)
-        sub     r4,r4,r3
-        ld      r4,CPU_SPEC_FEATURES(r4)
-        /* Get the fixup table */
-        LOAD_REG_IMMEDIATE(r6,__start___ftr_fixup)
-        sub     r6,r6,r3
-        LOAD_REG_IMMEDIATE(r7,__stop___ftr_fixup)
-        sub     r7,r7,r3
-        /* Do the fixup */
-1:      cmpld   r6,r7
-        bgelr
-        addi    r6,r6,32
-        ld      r8,-32(r6)      /* mask */
-        and     r8,r8,r4
-        ld      r9,-24(r6)      /* value */
-        cmpld   r8,r9
-        beq     1b
-        ld      r8,-16(r6)      /* section begin */
-        ld      r9,-8(r6)       /* section end */
-        subf.   r9,r8,r9
-        beq     1b
-        /* write nops over the section of code */
-        /* todo: if large section, add a branch at the start of it */
-        srwi    r9,r9,2
-        mtctr   r9
-        sub     r8,r8,r3
-        lis     r0,0x60000000@h /* nop */
-3:      stw     r0,0(r8)
-        andi.   r10,r4,CPU_FTR_SPLIT_ID_CACHE@l
-        beq     2f
-        dcbst   0,r8            /* suboptimal, but simpler */
-        sync
-        icbi    0,r8
-2:      addi    r8,r8,4
-        bdnz    3b
-        sync                    /* additional sync needed on g4 */
-        isync
-        b       1b
-
-/*
- * do_fw_ftr_fixups - goes through the list of firmware feature fixups
- * and writes nop's over sections of code that don't apply for this firmware.
- * r3 = data offset (not changed)
- */
-_GLOBAL(do_fw_ftr_fixups)
-        /* Get firmware features */
-        LOAD_REG_IMMEDIATE(r6,powerpc_firmware_features)
-        sub     r6,r6,r3
-        ld      r4,0(r6)
-        /* Get the fixup table */
-        LOAD_REG_IMMEDIATE(r6,__start___fw_ftr_fixup)
-        sub     r6,r6,r3
-        LOAD_REG_IMMEDIATE(r7,__stop___fw_ftr_fixup)
-        sub     r7,r7,r3
-        /* Do the fixup */
-1:      cmpld   r6,r7
-        bgelr
-        addi    r6,r6,32
-        ld      r8,-32(r6)      /* mask */
-        and     r8,r8,r4
-        ld      r9,-24(r6)      /* value */
-        cmpld   r8,r9
-        beq     1b
-        ld      r8,-16(r6)      /* section begin */
-        ld      r9,-8(r6)       /* section end */
-        subf.   r9,r8,r9
-        beq     1b
-        /* write nops over the section of code */
-        /* todo: if large section, add a branch at the start of it */
-        srwi    r9,r9,2
-        mtctr   r9
-        sub     r8,r8,r3
-        lis     r0,0x60000000@h /* nop */
-3:      stw     r0,0(r8)
-BEGIN_FTR_SECTION
-        dcbst   0,r8            /* suboptimal, but simpler */
-        sync
-        icbi    0,r8
-END_FTR_SECTION_IFSET(CPU_FTR_SPLIT_ID_CACHE)
-        addi    r8,r8,4
-        bdnz    3b
-        sync                    /* additional sync needed on g4 */
-        isync
-        b       1b
 
 #if defined(CONFIG_PPC_PMAC) || defined(CONFIG_PPC_MAPLE)
 /*
diff --git a/arch/powerpc/kernel/module_32.c b/arch/powerpc/kernel/module_32.c
index 92f4e5f64f02..e2c3c6a85f33 100644
--- a/arch/powerpc/kernel/module_32.c
+++ b/arch/powerpc/kernel/module_32.c
@@ -24,6 +24,8 @@
 #include <linux/kernel.h>
 #include <linux/cache.h>
 
+#include "setup.h"
+
 #if 0
 #define DEBUGP printk
 #else
@@ -269,33 +271,50 @@ int apply_relocate_add(Elf32_Shdr *sechdrs,
         return 0;
 }
 
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+                                    const Elf_Shdr *sechdrs,
+                                    const char *name)
+{
+        char *secstrings;
+        unsigned int i;
+
+        secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+        for (i = 1; i < hdr->e_shnum; i++)
+                if (strcmp(secstrings+sechdrs[i].sh_name, name) == 0)
+                        return &sechdrs[i];
+        return NULL;
+}
+
 int module_finalize(const Elf_Ehdr *hdr,
                     const Elf_Shdr *sechdrs,
                     struct module *me)
 {
-        char *secstrings;
-        unsigned int i;
+        const Elf_Shdr *sect;
 
         me->arch.bug_table = NULL;
         me->arch.num_bugs = 0;
 
         /* Find the __bug_table section, if present */
-        secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-        for (i = 1; i < hdr->e_shnum; i++) {
-                if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table"))
-                        continue;
-                me->arch.bug_table = (void *) sechdrs[i].sh_addr;
-                me->arch.num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry);
-                break;
+        sect = find_section(hdr, sechdrs, "__bug_table");
+        if (sect != NULL) {
+                me->arch.bug_table = (void *) sect->sh_addr;
+                me->arch.num_bugs = sect->sh_size / sizeof(struct bug_entry);
         }
 
-        /*
+        /*
          * Strictly speaking this should have a spinlock to protect against
          * traversals, but since we only traverse on BUG()s, a spinlock
          * could potentially lead to deadlock and thus be counter-productive.
          */
         list_add(&me->arch.bug_list, &module_bug_list);
 
+        /* Apply feature fixups */
+        sect = find_section(hdr, sechdrs, "__ftr_fixup");
+        if (sect != NULL)
+                do_feature_fixups(cur_cpu_spec->cpu_features,
+                                  (void *)sect->sh_addr,
+                                  (void *)sect->sh_addr + sect->sh_size);
+
         return 0;
 }
 
diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ba34001fca8e..8dd1f0aae5d6 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -22,6 +22,9 @@
 #include <linux/vmalloc.h>
 #include <asm/module.h>
 #include <asm/uaccess.h>
+#include <asm/firmware.h>
+
+#include "setup.h"
 
 /* FIXME: We don't do .init separately.  To do this, we'd need to have
    a separate r2 value in the init and core section, and stub between
@@ -400,6 +403,11 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
                                 | (value & 0x03fffffc);
                         break;
 
+                case R_PPC64_REL64:
+                        /* 64 bits relative (used by features fixups) */
+                        *location = value - (unsigned long)location;
+                        break;
+
                 default:
                         printk("%s: Unknown ADD relocation: %lu\n",
                                me->name,
@@ -413,23 +421,33 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 
 LIST_HEAD(module_bug_list);
 
-int module_finalize(const Elf_Ehdr *hdr,
-                const Elf_Shdr *sechdrs, struct module *me)
+static const Elf_Shdr *find_section(const Elf_Ehdr *hdr,
+                                    const Elf_Shdr *sechdrs,
+                                    const char *name)
 {
         char *secstrings;
         unsigned int i;
 
+        secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+        for (i = 1; i < hdr->e_shnum; i++)
+                if (strcmp(secstrings+sechdrs[i].sh_name, name) == 0)
+                        return &sechdrs[i];
+        return NULL;
+}
+
+int module_finalize(const Elf_Ehdr *hdr,
+                const Elf_Shdr *sechdrs, struct module *me)
+{
+        const Elf_Shdr *sect;
+
         me->arch.bug_table = NULL;
         me->arch.num_bugs = 0;
 
         /* Find the __bug_table section, if present */
-        secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-        for (i = 1; i < hdr->e_shnum; i++) {
-                if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table"))
-                        continue;
-                me->arch.bug_table = (void *) sechdrs[i].sh_addr;
-                me->arch.num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry);
-                break;
+        sect = find_section(hdr, sechdrs, "__bug_table");
+        if (sect != NULL) {
+                me->arch.bug_table = (void *) sect->sh_addr;
+                me->arch.num_bugs = sect->sh_size / sizeof(struct bug_entry);
         }
 
         /*
@@ -439,6 +457,19 @@ int module_finalize(const Elf_Ehdr *hdr,
          */
         list_add(&me->arch.bug_list, &module_bug_list);
 
+        /* Apply feature fixups */
+        sect = find_section(hdr, sechdrs, "__ftr_fixup");
+        if (sect != NULL)
+                do_feature_fixups(cur_cpu_spec->cpu_features,
+                                  (void *)sect->sh_addr,
+                                  (void *)sect->sh_addr + sect->sh_size);
+
+        sect = find_section(hdr, sechdrs, "__fw_ftr_fixup");
+        if (sect != NULL)
+                do_feature_fixups(powerpc_firmware_features,
+                                  (void *)sect->sh_addr,
+                                  (void *)sect->sh_addr + sect->sh_size);
+
         return 0;
 }
 
diff --git a/arch/powerpc/kernel/perfmon_fsl_booke.c b/arch/powerpc/kernel/perfmon_fsl_booke.c
deleted file mode 100644
index e0dcf2b41fbe..000000000000
--- a/arch/powerpc/kernel/perfmon_fsl_booke.c
+++ /dev/null
@@ -1,221 +0,0 @@
-/* arch/powerpc/kernel/perfmon_fsl_booke.c
- * Freescale Book-E Performance Monitor code
- *
- * Author: Andy Fleming
- * Copyright (c) 2004 Freescale Semiconductor, Inc
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- */
-
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/stddef.h>
-#include <linux/unistd.h>
-#include <linux/ptrace.h>
-#include <linux/slab.h>
-#include <linux/user.h>
-#include <linux/a.out.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/prctl.h>
-
-#include <asm/pgtable.h>
-#include <asm/uaccess.h>
-#include <asm/system.h>
-#include <asm/io.h>
-#include <asm/reg.h>
-#include <asm/xmon.h>
-#include <asm/pmc.h>
-
-static inline u32 get_pmlca(int ctr);
-static inline void set_pmlca(int ctr, u32 pmlca);
-
-static inline u32 get_pmlca(int ctr)
-{
-        u32 pmlca;
-
-        switch (ctr) {
-                case 0:
-                        pmlca = mfpmr(PMRN_PMLCA0);
-                        break;
-                case 1:
-                        pmlca = mfpmr(PMRN_PMLCA1);
-                        break;
-                case 2:
-                        pmlca = mfpmr(PMRN_PMLCA2);
-                        break;
-                case 3:
-                        pmlca = mfpmr(PMRN_PMLCA3);
-                        break;
-                default:
-                        panic("Bad ctr number\n");
-        }
-
-        return pmlca;
-}
-
-static inline void set_pmlca(int ctr, u32 pmlca)
-{
-        switch (ctr) {
-                case 0:
-                        mtpmr(PMRN_PMLCA0, pmlca);
-                        break;
-                case 1:
-                        mtpmr(PMRN_PMLCA1, pmlca);
-                        break;
-                case 2:
-                        mtpmr(PMRN_PMLCA2, pmlca);
-                        break;
-                case 3:
-                        mtpmr(PMRN_PMLCA3, pmlca);
-                        break;
-                default:
-                        panic("Bad ctr number\n");
-        }
-}
-
-void init_pmc_stop(int ctr)
-{
-        u32 pmlca = (PMLCA_FC | PMLCA_FCS | PMLCA_FCU |
-                        PMLCA_FCM1 | PMLCA_FCM0);
-        u32 pmlcb = 0;
-
-        switch (ctr) {
-                case 0:
-                        mtpmr(PMRN_PMLCA0, pmlca);
-                        mtpmr(PMRN_PMLCB0, pmlcb);
-                        break;
-                case 1:
-                        mtpmr(PMRN_PMLCA1, pmlca);
-                        mtpmr(PMRN_PMLCB1, pmlcb);
-                        break;
-                case 2:
-                        mtpmr(PMRN_PMLCA2, pmlca);
-                        mtpmr(PMRN_PMLCB2, pmlcb);
-                        break;
-                case 3:
-                        mtpmr(PMRN_PMLCA3, pmlca);
-                        mtpmr(PMRN_PMLCB3, pmlcb);
-                        break;
-                default:
-                        panic("Bad ctr number!\n");
-        }
-}
-
-void set_pmc_event(int ctr, int event)
-{
-        u32 pmlca;
-
-        pmlca = get_pmlca(ctr);
-
-        pmlca = (pmlca & ~PMLCA_EVENT_MASK) |
-                ((event << PMLCA_EVENT_SHIFT) &
-                 PMLCA_EVENT_MASK);
-
-        set_pmlca(ctr, pmlca);
-}
-
-void set_pmc_user_kernel(int ctr, int user, int kernel)
-{
-        u32 pmlca;
-
-        pmlca = get_pmlca(ctr);
-
-        if(user)
-                pmlca &= ~PMLCA_FCU;
-        else
-                pmlca |= PMLCA_FCU;
-
-        if(kernel)
-                pmlca &= ~PMLCA_FCS;
-        else
-                pmlca |= PMLCA_FCS;
-
-        set_pmlca(ctr, pmlca);
-}
-
-void set_pmc_marked(int ctr, int mark0, int mark1)
-{
-        u32 pmlca = get_pmlca(ctr);
-
-        if(mark0)
-                pmlca &= ~PMLCA_FCM0;
-        else
-                pmlca |= PMLCA_FCM0;
-
-        if(mark1)
-                pmlca &= ~PMLCA_FCM1;
-        else
-                pmlca |= PMLCA_FCM1;
-
-        set_pmlca(ctr, pmlca);
-}
-
-void pmc_start_ctr(int ctr, int enable)
-{
-        u32 pmlca = get_pmlca(ctr);
-
-        pmlca &= ~PMLCA_FC;
-
-        if (enable)
-                pmlca |= PMLCA_CE;
-        else
-                pmlca &= ~PMLCA_CE;
-
-        set_pmlca(ctr, pmlca);
-}
-
-void pmc_start_ctrs(int enable)
-{
-        u32 pmgc0 = mfpmr(PMRN_PMGC0);
-
-        pmgc0 &= ~PMGC0_FAC;
-        pmgc0 |= PMGC0_FCECE;
-
-        if (enable)
-                pmgc0 |= PMGC0_PMIE;
-        else
-                pmgc0 &= ~PMGC0_PMIE;
-
-        mtpmr(PMRN_PMGC0, pmgc0);
-}
-
-void pmc_stop_ctrs(void)
-{
-        u32 pmgc0 = mfpmr(PMRN_PMGC0);
-
-        pmgc0 |= PMGC0_FAC;
-
-        pmgc0 &= ~(PMGC0_PMIE | PMGC0_FCECE);
-
-        mtpmr(PMRN_PMGC0, pmgc0);
-}
-
-void dump_pmcs(void)
-{
-        printk("pmgc0: %x\n", mfpmr(PMRN_PMGC0));
-        printk("pmc\t\tpmlca\t\tpmlcb\n");
-        printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC0),
-                        mfpmr(PMRN_PMLCA0), mfpmr(PMRN_PMLCB0));
-        printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC1),
-                        mfpmr(PMRN_PMLCA1), mfpmr(PMRN_PMLCB1));
-        printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC2),
-                        mfpmr(PMRN_PMLCA2), mfpmr(PMRN_PMLCB2));
-        printk("%8x\t%8x\t%8x\n", mfpmr(PMRN_PMC3),
-                        mfpmr(PMRN_PMLCA3), mfpmr(PMRN_PMLCB3));
-}
-
-EXPORT_SYMBOL(init_pmc_stop);
-EXPORT_SYMBOL(set_pmc_event);
-EXPORT_SYMBOL(set_pmc_user_kernel);
-EXPORT_SYMBOL(set_pmc_marked);
-EXPORT_SYMBOL(pmc_start_ctr);
-EXPORT_SYMBOL(pmc_start_ctrs);
-EXPORT_SYMBOL(pmc_stop_ctrs);
-EXPORT_SYMBOL(dump_pmcs);
diff --git a/arch/powerpc/kernel/pmc.c b/arch/powerpc/kernel/pmc.c
index a0a2efadeabf..3d8f6f44641e 100644
--- a/arch/powerpc/kernel/pmc.c
+++ b/arch/powerpc/kernel/pmc.c
@@ -71,7 +71,7 @@ int reserve_pmc_hardware(perf_irq_t new_perf_irq)
         }
 
         pmc_owner_caller = __builtin_return_address(0);
-        perf_irq = new_perf_irq ? : dummy_perf;
+        perf_irq = new_perf_irq ? new_perf_irq : dummy_perf;
 
  out:
         spin_unlock(&pmc_owner_lock);
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 865b9648d0d5..bdb412d4b748 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -1014,7 +1014,7 @@ EXPORT_SYMBOL(find_all_nodes);
 /** Checks if the given "compat" string matches one of the strings in
  * the device's "compatible" property
  */
-int device_is_compatible(struct device_node *device, const char *compat)
+int device_is_compatible(const struct device_node *device, const char *compat)
 {
         const char* cp;
         int cplen, l;
@@ -1491,7 +1491,8 @@ static int __init prom_reconfig_setup(void)
 __initcall(prom_reconfig_setup);
 #endif
 
-struct property *of_find_property(struct device_node *np, const char *name,
+struct property *of_find_property(const struct device_node *np,
+                                  const char *name,
                                   int *lenp)
 {
         struct property *pp;
@@ -1512,7 +1513,8 @@ struct property *of_find_property(struct device_node *np, const char *name,
  * Find a property with a given name for a given node
  * and return the value.
  */
-const void *get_property(struct device_node *np, const char *name, int *lenp)
+const void *get_property(const struct device_node *np, const char *name,
+                         int *lenp)
 {
         struct property *pp = of_find_property(np,name,lenp);
         return pp ? pp->value : NULL;
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 1442b63a75da..6f6fc977cb39 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -72,6 +72,10 @@
 #define VALIDATE_BUF_SIZE 4096    
 #define RTAS_MSG_MAXLEN   64
 
+/* Quirk - RTAS requires 4k list length and block size */
+#define RTAS_BLKLIST_LENGTH 4096
+#define RTAS_BLK_SIZE 4096
+
 struct flash_block {
         char *data;
         unsigned long length;
@@ -83,7 +87,7 @@ struct flash_block {
  * into a version/length and translate the pointers
  * to absolute.
  */
-#define FLASH_BLOCKS_PER_NODE ((PAGE_SIZE - 16) / sizeof(struct flash_block))
+#define FLASH_BLOCKS_PER_NODE ((RTAS_BLKLIST_LENGTH - 16) / sizeof(struct flash_block))
 struct flash_block_list {
         unsigned long num_blocks;
         struct flash_block_list *next;
@@ -96,6 +100,9 @@ struct flash_block_list_header { /* just the header of flash_block_list */
 
 static struct flash_block_list_header rtas_firmware_flash_list = {0, NULL};
 
+/* Use slab cache to guarantee 4k alignment */
+static kmem_cache_t *flash_block_cache = NULL;
+
 #define FLASH_BLOCK_LIST_VERSION (1UL)
 
 /* Local copy of the flash block list.
@@ -153,7 +160,7 @@ static int flash_list_valid(struct flash_block_list *flist)
                                 return FLASH_IMG_NULL_DATA;
                         }
                         block_size = f->blocks[i].length;
-                        if (block_size <= 0 || block_size > PAGE_SIZE) {
+                        if (block_size <= 0 || block_size > RTAS_BLK_SIZE) {
                                 return FLASH_IMG_BAD_LEN;
                         }
                         image_size += block_size;
@@ -177,9 +184,9 @@ static void free_flash_list(struct flash_block_list *f)
 
         while (f) {
                 for (i = 0; i < f->num_blocks; i++)
-                        free_page((unsigned long)(f->blocks[i].data));
+                        kmem_cache_free(flash_block_cache, f->blocks[i].data);
                 next = f->next;
-                free_page((unsigned long)f);
+                kmem_cache_free(flash_block_cache, f);
                 f = next;
         }
 }
@@ -278,6 +285,12 @@ static ssize_t rtas_flash_read(struct file *file, char __user *buf,
         return msglen;
 }
 
+/* constructor for flash_block_cache */
+void rtas_block_ctor(void *ptr, kmem_cache_t *cache, unsigned long flags)
+{
+        memset(ptr, 0, RTAS_BLK_SIZE);
+}
+
 /* We could be much more efficient here.  But to keep this function
  * simple we allocate a page to the block list no matter how small the
  * count is.  If the system is low on memory it will be just as well
@@ -302,7 +315,7 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
          * proc file
          */
         if (uf->flist == NULL) {
-                uf->flist = (struct flash_block_list *) get_zeroed_page(GFP_KERNEL);
+                uf->flist = kmem_cache_alloc(flash_block_cache, GFP_KERNEL);
                 if (!uf->flist)
                         return -ENOMEM;
         }
@@ -313,21 +326,21 @@ static ssize_t rtas_flash_write(struct file *file, const char __user *buffer,
         next_free = fl->num_blocks;
         if (next_free == FLASH_BLOCKS_PER_NODE) {
                 /* Need to allocate another block_list */
-                fl->next = (struct flash_block_list *)get_zeroed_page(GFP_KERNEL);
+                fl->next = kmem_cache_alloc(flash_block_cache, GFP_KERNEL);
                 if (!fl->next)
                         return -ENOMEM;
                 fl = fl->next;
                 next_free = 0;
         }
 
-        if (count > PAGE_SIZE)
-                count = PAGE_SIZE;
-        p = (char *)get_zeroed_page(GFP_KERNEL);
+        if (count > RTAS_BLK_SIZE)
+                count = RTAS_BLK_SIZE;
+        p = kmem_cache_alloc(flash_block_cache, GFP_KERNEL);
         if (!p)
                 return -ENOMEM;
         
         if(copy_from_user(p, buffer, count)) {
-                free_page((unsigned long)p);
+                kmem_cache_free(flash_block_cache, p);
                 return -EFAULT;
         }
         fl->blocks[next_free].data = p;
@@ -791,6 +804,16 @@ int __init rtas_flash_init(void)
                 goto cleanup;
 
         rtas_flash_term_hook = rtas_flash_firmware;
+
+        flash_block_cache = kmem_cache_create("rtas_flash_cache",
+                                RTAS_BLK_SIZE, RTAS_BLK_SIZE, 0,
+                                rtas_block_ctor, NULL);
+        if (!flash_block_cache) {
+                printk(KERN_ERR "%s: failed to create block cache\n",
+                                __FUNCTION__);
+                rc = -ENOMEM;
+                goto cleanup;
+        }
         return 0;
 
 cleanup:
@@ -805,6 +828,10 @@ cleanup:
 void __exit rtas_flash_cleanup(void)
 {
         rtas_flash_term_hook = NULL;
+
+        if (flash_block_cache)
+                kmem_cache_destroy(flash_block_cache);
+
         remove_flash_pde(firmware_flash_pde);
         remove_flash_pde(firmware_update_pde);
         remove_flash_pde(validate_pde);
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index 191d0ab09222..a4c2964a3ca6 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -91,6 +91,7 @@ int ucache_bsize;
 unsigned long __init early_init(unsigned long dt_ptr)
 {
         unsigned long offset = reloc_offset();
+        struct cpu_spec *spec;
 
         /* First zero the BSS -- use memset_io, some platforms don't have
          * caches on yet */
@@ -100,8 +101,11 @@ unsigned long __init early_init(unsigned long dt_ptr)
          * Identify the CPU type and fix up code sections
          * that depend on which cpu we have.
          */
-        identify_cpu(offset, 0);
-        do_cpu_ftr_fixups(offset);
+        spec = identify_cpu(offset);
+
+        do_feature_fixups(spec->cpu_features,
+                          PTRRELOC(&__start___ftr_fixup),
+                          PTRRELOC(&__stop___ftr_fixup));
 
         return KERNELBASE + offset;
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 4b2e32eab9dc..16278968dab6 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -170,6 +170,9 @@ void __init setup_paca(int cpu)
 
 void __init early_setup(unsigned long dt_ptr)
 {
+        /* Identify CPU type */
+        identify_cpu(0);
+
         /* Assume we're on cpu 0 for now. Don't write to the paca yet! */
         setup_paca(0);
 
@@ -348,6 +351,14 @@ void __init setup_system(void)
 {
         DBG(" -> setup_system()\n");
 
+        /* Apply the CPUs-specific and firmware specific fixups to kernel
+         * text (nop out sections not relevant to this CPU or this firmware)
+         */
+        do_feature_fixups(cur_cpu_spec->cpu_features,
+                          &__start___ftr_fixup, &__stop___ftr_fixup);
+        do_feature_fixups(powerpc_firmware_features,
+                          &__start___fw_ftr_fixup, &__stop___fw_ftr_fixup);
+
         /*
          * Unflatten the device-tree passed by prom_init or kexec
          */
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 5b59bc18dfe7..a1b5e4b16151 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -220,11 +220,8 @@ static void account_process_time(struct pt_regs *regs)
  */
 struct cpu_purr_data {
         int     initialized;                    /* thread is running */
-        u64     tb0;                    /* timebase at origin time */
-        u64     purr0;                  /* PURR at origin time */
         u64     tb;                     /* last TB value read */
         u64     purr;                   /* last PURR value read */
-        u64     stolen;                 /* stolen time so far */
         spinlock_t lock;
 };
 
@@ -234,10 +231,8 @@ static void snapshot_tb_and_purr(void *data)
 {
         struct cpu_purr_data *p = &__get_cpu_var(cpu_purr_data);
 
-        p->tb0 = mftb();
-        p->purr0 = mfspr(SPRN_PURR);
-        p->tb = p->tb0;
-        p->purr = 0;
+        p->tb = mftb();
+        p->purr = mfspr(SPRN_PURR);
         wmb();
         p->initialized = 1;
 }
@@ -258,37 +253,24 @@ void snapshot_timebases(void)
 
 void calculate_steal_time(void)
 {
-        u64 tb, purr, t0;
+        u64 tb, purr;
         s64 stolen;
-        struct cpu_purr_data *p0, *pme, *phim;
-        int cpu;
+        struct cpu_purr_data *pme;
 
         if (!cpu_has_feature(CPU_FTR_PURR))
                 return;
-        cpu = smp_processor_id();
-        pme = &per_cpu(cpu_purr_data, cpu);
+        pme = &per_cpu(cpu_purr_data, smp_processor_id());
         if (!pme->initialized)
                 return;         /* this can happen in early boot */
-        p0 = &per_cpu(cpu_purr_data, cpu & ~1);
-        phim = &per_cpu(cpu_purr_data, cpu ^ 1);
-        spin_lock(&p0->lock);
+        spin_lock(&pme->lock);
         tb = mftb();
-        purr = mfspr(SPRN_PURR) - pme->purr0;
-        if (!phim->initialized || !cpu_online(cpu ^ 1)) {
-                stolen = (tb - pme->tb) - (purr - pme->purr);
-        } else {
-                t0 = pme->tb0;
-                if (phim->tb0 < t0)
-                        t0 = phim->tb0;
-                stolen = phim->tb - t0 - phim->purr - purr - p0->stolen;
-        }
-        if (stolen > 0) {
+        purr = mfspr(SPRN_PURR);
+        stolen = (tb - pme->tb) - (purr - pme->purr);
+        if (stolen > 0)
                 account_steal_time(current, stolen);
-                p0->stolen += stolen;
-        }
         pme->tb = tb;
         pme->purr = purr;
-        spin_unlock(&p0->lock);
+        spin_unlock(&pme->lock);
 }
 
 /*
@@ -297,30 +279,17 @@ void calculate_steal_time(void)
  */
 static void snapshot_purr(void)
 {
-        int cpu;
-        u64 purr;
-        struct cpu_purr_data *p0, *pme, *phim;
+        struct cpu_purr_data *pme;
         unsigned long flags;
 
         if (!cpu_has_feature(CPU_FTR_PURR))
                 return;
-        cpu = smp_processor_id();
-        pme = &per_cpu(cpu_purr_data, cpu);
-        p0 = &per_cpu(cpu_purr_data, cpu & ~1);
-        phim = &per_cpu(cpu_purr_data, cpu ^ 1);
-        spin_lock_irqsave(&p0->lock, flags);
-        pme->tb = pme->tb0 = mftb();
-        purr = mfspr(SPRN_PURR);
-        if (!phim->initialized) {
-                pme->purr = 0;
-                pme->purr0 = purr;
-        } else {
-                /* set p->purr and p->purr0 for no change in p0->stolen */
-                pme->purr = phim->tb - phim->tb0 - phim->purr - p0->stolen;
-                pme->purr0 = purr - pme->purr;
-        }
+        pme = &per_cpu(cpu_purr_data, smp_processor_id());
+        spin_lock_irqsave(&pme->lock, flags);
+        pme->tb = mftb();
+        pme->purr = mfspr(SPRN_PURR);
         pme->initialized = 1;
-        spin_unlock_irqrestore(&p0->lock, flags);
+        spin_unlock_irqrestore(&pme->lock, flags);
 }
 
 #endif /* CONFIG_PPC_SPLPAR */
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 5ed4c2ceb5ca..c66b4771ef44 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -843,7 +843,7 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 
 void alignment_exception(struct pt_regs *regs)
 {
-        int fixed = 0;
+        int sig, code, fixed = 0;
 
         /* we don't implement logging of alignment exceptions */
         if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
@@ -857,14 +857,16 @@ void alignment_exception(struct pt_regs *regs)
 
         /* Operand address was bad */
         if (fixed == -EFAULT) {
-                if (user_mode(regs))
-                        _exception(SIGSEGV, regs, SEGV_ACCERR, regs->dar);
-                else
-                        /* Search exception table */
-                        bad_page_fault(regs, regs->dar, SIGSEGV);
-                return;
+                sig = SIGSEGV;
+                code = SEGV_ACCERR;
+        } else {
+                sig = SIGBUS;
+                code = BUS_ADRALN;
         }
-        _exception(SIGBUS, regs, BUS_ADRALN, regs->dar);
+        if (user_mode(regs))
+                _exception(sig, regs, code, regs->dar);
+        else
+                bad_page_fault(regs, regs->dar, sig);
 }
 
 void StackOverflow(struct pt_regs *regs)
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index 1a7e19cdab39..c913ad5cad29 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -36,6 +36,8 @@
 #include <asm/vdso.h>
 #include <asm/vdso_datapage.h>
 
+#include "setup.h"
+
 #undef DEBUG
 
 #ifdef DEBUG
@@ -586,6 +588,43 @@ static __init int vdso_fixup_datapage(struct lib32_elfinfo *v32,
         return 0;
 }
 
+
+static __init int vdso_fixup_features(struct lib32_elfinfo *v32,
+                                      struct lib64_elfinfo *v64)
+{
+        void *start32;
+        unsigned long size32;
+
+#ifdef CONFIG_PPC64
+        void *start64;
+        unsigned long size64;
+
+        start64 = find_section64(v64->hdr, "__ftr_fixup", &size64);
+        if (start64)
+                do_feature_fixups(cur_cpu_spec->cpu_features,
+                                  start64, start64 + size64);
+
+        start64 = find_section64(v64->hdr, "__fw_ftr_fixup", &size64);
+        if (start64)
+                do_feature_fixups(powerpc_firmware_features,
+                                  start64, start64 + size64);
+#endif /* CONFIG_PPC64 */
+
+        start32 = find_section32(v32->hdr, "__ftr_fixup", &size32);
+        if (start32)
+                do_feature_fixups(cur_cpu_spec->cpu_features,
+                                  start32, start32 + size32);
+
+#ifdef CONFIG_PPC64
+        start32 = find_section32(v32->hdr, "__fw_ftr_fixup", &size32);
+        if (start32)
+                do_feature_fixups(powerpc_firmware_features,
+                                  start32, start32 + size32);
+#endif /* CONFIG_PPC64 */
+
+        return 0;
+}
+
 static __init int vdso_fixup_alt_funcs(struct lib32_elfinfo *v32,
                                        struct lib64_elfinfo *v64)
 {
@@ -634,6 +673,9 @@ static __init int vdso_setup(void)
         if (vdso_fixup_datapage(&v32, &v64))
                 return -1;
 
+        if (vdso_fixup_features(&v32, &v64))
+                return -1;
+
         if (vdso_fixup_alt_funcs(&v32, &v64))
                 return -1;
 
@@ -714,6 +756,7 @@ void __init vdso_init(void)
          * Setup the syscall map in the vDOS
          */
         vdso_setup_syscall_map();
+
         /*
          * Initialize the vDSO images in memory, that is do necessary
          * fixups of vDSO symbols, locate trampolines, etc...
diff --git a/arch/powerpc/kernel/vdso32/vdso32.lds.S b/arch/powerpc/kernel/vdso32/vdso32.lds.S
index 6187af2d54c3..26e138c4ce17 100644
--- a/arch/powerpc/kernel/vdso32/vdso32.lds.S
+++ b/arch/powerpc/kernel/vdso32/vdso32.lds.S
@@ -32,6 +32,18 @@ SECTIONS
   PROVIDE (_etext = .);
   PROVIDE (etext = .);
 
+  . = ALIGN(8);
+  __ftr_fixup : {
+    *(__ftr_fixup)
+  }
+
+#ifdef CONFIG_PPC64
+  . = ALIGN(8);
+  __fw_ftr_fixup : {
+    *(__fw_ftr_fixup)
+  }
+#endif
+
   /* Other stuff is appended to the text segment: */
   .rodata               : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
   .rodata1              : { *(.rodata1) }
diff --git a/arch/powerpc/kernel/vdso64/gettimeofday.S b/arch/powerpc/kernel/vdso64/gettimeofday.S
index 56e76ff5498f..40ffd9b6cef7 100644
--- a/arch/powerpc/kernel/vdso64/gettimeofday.S
+++ b/arch/powerpc/kernel/vdso64/gettimeofday.S
@@ -229,8 +229,10 @@ V_FUNCTION_BEGIN(__do_get_xsec)
         xor     r0,r8,r8                /* create dependency */
         add     r3,r3,r0
 
-        /* Get TB & offset it */
-        mftb    r7
+        /* Get TB & offset it. We use the MFTB macro which will generate
+         * workaround code for Cell.
+         */
+        MFTB(r7)
         ld      r9,CFG_TB_ORIG_STAMP(r3)
         subf    r7,r9,r7
 
diff --git a/arch/powerpc/kernel/vdso64/vdso64.lds.S b/arch/powerpc/kernel/vdso64/vdso64.lds.S
index 4a2b6dc0960c..2d70f35d50b5 100644
--- a/arch/powerpc/kernel/vdso64/vdso64.lds.S
+++ b/arch/powerpc/kernel/vdso64/vdso64.lds.S
@@ -31,6 +31,16 @@ SECTIONS
   PROVIDE (_etext = .);
   PROVIDE (etext = .);
 
+  . = ALIGN(8);
+  __ftr_fixup : {
+    *(__ftr_fixup)
+  }
+
+  . = ALIGN(8);
+  __fw_ftr_fixup : {
+    *(__fw_ftr_fixup)
+  }
+
   /* Other stuff is appended to the text segment: */
   .rodata         : { *(.rodata .rodata.* .gnu.linkonce.r.*) }
   .rodata1        : { *(.rodata1) }
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index cb87e71eec66..ed007878d1bf 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -92,9 +92,9 @@ static struct iommu_table *vio_build_iommu_table(struct vio_dev *dev)
                                 &tbl->it_index, &offset, &size);
 
                 /* TCE table size - measured in tce entries */
-                tbl->it_size = size >> PAGE_SHIFT;
+                tbl->it_size = size >> IOMMU_PAGE_SHIFT;
                 /* offset for VIO should always be 0 */
-                tbl->it_offset = offset >> PAGE_SHIFT;
+                tbl->it_offset = offset >> IOMMU_PAGE_SHIFT;
                 tbl->it_busno = 0;
                 tbl->it_type = TCE_VB;
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index cb0e8d46c3e8..e8342d867536 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -108,13 +108,7 @@ SECTIONS
 
         .initcall.init : {
                 __initcall_start = .;
-                *(.initcall1.init)
-                *(.initcall2.init)
-                *(.initcall3.init)
-                *(.initcall4.init)
-                *(.initcall5.init)
-                *(.initcall6.init)
-                *(.initcall7.init)
+                INITCALLS
                 __initcall_end = .;
                 }