parisc: flush pages through tmpalias space

The kernel has an 8M tmpailas space (originally designed for copying
and clearing pages but now only used for clearing).  The idea is
to place zeros into the cache above a physical page rather than into
the physical page and flush the cache, because often the zeros end up
being replaced quickly anyway.

We can also use the tmpalias space for flushing a page.  The difference
here is that we have to do tmpalias processing in the non access data and
instruction traps.  The principle is the same: as long as we know the physical
address and have a virtual address congruent to the real one, the flush will
be effective.

In order to use the tmpalias space, the icache miss path has to be enhanced to
check for the alias region to make the fic instruction effective.

Signed-off-by: James Bottomley <James.Bottomley@suse.de>

4 files changed, 272 insertions, 283 deletions

diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index f388a85bba11..dc9286a4dcc7 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -26,8 +26,6 @@ void flush_user_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
 void flush_kernel_dcache_page_asm(void *);
 void flush_kernel_icache_page(void *);
-void flush_user_dcache_page(unsigned long);
-void flush_user_icache_page(unsigned long);
 void flush_user_dcache_range(unsigned long, unsigned long);
 void flush_user_icache_range(unsigned long, unsigned long);
 
@@ -90,12 +88,15 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned
 void flush_cache_range(struct vm_area_struct *vma,
                 unsigned long start, unsigned long end);
 
+/* defined in pacache.S exported in cache.c used by flush_anon_page */
+void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
+
 #define ARCH_HAS_FLUSH_ANON_PAGE
 static inline void
 flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
 {
         if (PageAnon(page))
-                flush_user_dcache_page(vmaddr);
+                flush_dcache_page_asm(page_to_phys(page), vmaddr);
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index d054f3da3ff5..3f11331c2775 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -27,12 +27,17 @@
 #include <asm/pgalloc.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
+#include <asm/shmparam.h>
 
 int split_tlb __read_mostly;
 int dcache_stride __read_mostly;
 int icache_stride __read_mostly;
 EXPORT_SYMBOL(dcache_stride);
 
+void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
+EXPORT_SYMBOL(flush_dcache_page_asm);
+void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
+
 
 /* On some machines (e.g. ones with the Merced bus), there can be
  * only a single PxTLB broadcast at a time; this must be guaranteed
@@ -259,81 +264,13 @@ void disable_sr_hashing(void)
                 panic("SpaceID hashing is still on!\n");
 }
 
-/* Simple function to work out if we have an existing address translation
- * for a user space vma. */
-static inline int translation_exists(struct vm_area_struct *vma,
-                                unsigned long addr, unsigned long pfn)
-{
-        pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
-        pmd_t *pmd;
-        pte_t pte;
-
-        if(pgd_none(*pgd))
-                return 0;
-
-        pmd = pmd_offset(pgd, addr);
-        if(pmd_none(*pmd) || pmd_bad(*pmd))
-                return 0;
-
-        /* We cannot take the pte lock here: flush_cache_page is usually
-         * called with pte lock already held.  Whereas flush_dcache_page
-         * takes flush_dcache_mmap_lock, which is lower in the hierarchy:
-         * the vma itself is secure, but the pte might come or go racily.
-         */
-        pte = *pte_offset_map(pmd, addr);
-        /* But pte_unmap() does nothing on this architecture */
-
-        /* Filter out coincidental file entries and swap entries */
-        if (!(pte_val(pte) & (_PAGE_FLUSH|_PAGE_PRESENT)))
-                return 0;
-
-        return pte_pfn(pte) == pfn;
-}
-
-/* Private function to flush a page from the cache of a non-current
- * process.  cr25 contains the Page Directory of the current user
- * process; we're going to hijack both it and the user space %sr3 to
- * temporarily make the non-current process current.  We have to do
- * this because cache flushing may cause a non-access tlb miss which
- * the handlers have to fill in from the pgd of the non-current
- * process. */
 static inline void
-flush_user_cache_page_non_current(struct vm_area_struct *vma,
-                                  unsigned long vmaddr)
+__flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
+                   unsigned long physaddr)
 {
-        /* save the current process space and pgd */
-        unsigned long space = mfsp(3), pgd = mfctl(25);
-
-        /* we don't mind taking interrupts since they may not
-         * do anything with user space, but we can't
-         * be preempted here */
-        preempt_disable();
-
-        /* make us current */
-        mtctl(__pa(vma->vm_mm->pgd), 25);
-        mtsp(vma->vm_mm->context, 3);
-
-        flush_user_dcache_page(vmaddr);
-        if(vma->vm_flags & VM_EXEC)
-                flush_user_icache_page(vmaddr);
-
-        /* put the old current process back */
-        mtsp(space, 3);
-        mtctl(pgd, 25);
-        preempt_enable();
-}
-
-
-static inline void
-__flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr)
-{
-        if (likely(vma->vm_mm->context == mfsp(3))) {
-                flush_user_dcache_page(vmaddr);
-                if (vma->vm_flags & VM_EXEC)
-                        flush_user_icache_page(vmaddr);
-        } else {
-                flush_user_cache_page_non_current(vma, vmaddr);
-        }
+        flush_dcache_page_asm(physaddr, vmaddr);
+        if (vma->vm_flags & VM_EXEC)
+                flush_icache_page_asm(physaddr, vmaddr);
 }
 
 void flush_dcache_page(struct page *page)
@@ -342,10 +279,8 @@ void flush_dcache_page(struct page *page)
         struct vm_area_struct *mpnt;
         struct prio_tree_iter iter;
         unsigned long offset;
-        unsigned long addr;
+        unsigned long addr, old_addr = 0;
         pgoff_t pgoff;
-        unsigned long pfn = page_to_pfn(page);
-
 
         if (mapping && !mapping_mapped(mapping)) {
                 set_bit(PG_dcache_dirty, &page->flags);
@@ -369,20 +304,11 @@ void flush_dcache_page(struct page *page)
                 offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
                 addr = mpnt->vm_start + offset;
 
-                /* Flush instructions produce non access tlb misses.
-                 * On PA, we nullify these instructions rather than
-                 * taking a page fault if the pte doesn't exist.
-                 * This is just for speed.  If the page translation
-                 * isn't there, there's no point exciting the
-                 * nadtlb handler into a nullification frenzy.
-                 *
-                 * Make sure we really have this page: the private
-                 * mappings may cover this area but have COW'd this
-                 * particular page.
-                 */
-                if (translation_exists(mpnt, addr, pfn)) {
-                        __flush_cache_page(mpnt, addr);
-                        break;
+                if (old_addr == 0 || (old_addr & (SHMLBA - 1)) != (addr & (SHMLBA - 1))) {
+                        __flush_cache_page(mpnt, addr, page_to_phys(page));
+                        if (old_addr)
+                                printk(KERN_ERR "INEQUIVALENT ALIASES 0x%lx and 0x%lx in file %s\n", old_addr, addr, mpnt->vm_file ? mpnt->vm_file->f_path.dentry->d_name.name : "(null)");
+                        old_addr = addr;
                 }
         }
         flush_dcache_mmap_unlock(mapping);
@@ -573,7 +499,6 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
 {
         BUG_ON(!vma->vm_mm->context);
 
-        if (likely(translation_exists(vma, vmaddr, pfn)))
-                __flush_cache_page(vma, vmaddr);
+        __flush_cache_page(vma, vmaddr, page_to_phys(pfn_to_page(pfn)));
 
 }
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 6337adef30f6..e8c119b61fc7 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -225,22 +225,13 @@
 #ifndef CONFIG_64BIT
         /*
          * naitlb miss interruption handler (parisc 1.1 - 32 bit)
-         *
-         * Note: naitlb misses will be treated
-         * as an ordinary itlb miss for now.
-         * However, note that naitlb misses
-         * have the faulting address in the
-         * IOR/ISR.
          */
 
         .macro  naitlb_11 code
 
         mfctl   %isr,spc
-        b       itlb_miss_11
+        b       naitlb_miss_11
         mfctl   %ior,va
-        /* FIXME: If user causes a naitlb miss, the priv level may not be in
-         * lower bits of va, where the itlb miss handler is expecting them
-         */
 
         .align          32
         .endm
@@ -248,26 +239,17 @@
         
         /*
          * naitlb miss interruption handler (parisc 2.0)
-         *
-         * Note: naitlb misses will be treated
-         * as an ordinary itlb miss for now.
-         * However, note that naitlb misses
-         * have the faulting address in the
-         * IOR/ISR.
          */
 
         .macro  naitlb_20 code
 
         mfctl   %isr,spc
 #ifdef CONFIG_64BIT
-        b       itlb_miss_20w
+        b       naitlb_miss_20w
 #else
-        b       itlb_miss_20
+        b       naitlb_miss_20
 #endif
         mfctl   %ior,va
-        /* FIXME: If user causes a naitlb miss, the priv level may not be in
-         * lower bits of va, where the itlb miss handler is expecting them
-         */
 
         .align          32
         .endm
@@ -581,7 +563,24 @@
         copy            \va,\tmp1
         depi            0,31,23,\tmp1
         cmpb,COND(<>),n \tmp,\tmp1,\fault
-        ldi             (_PAGE_DIRTY|_PAGE_WRITE|_PAGE_READ),\prot
+        mfctl           %cr19,\tmp      /* iir */
+        /* get the opcode (first six bits) into \tmp */
+        extrw,u         \tmp,5,6,\tmp
+        /*
+         * Only setting the T bit prevents data cache movein
+         * Setting access rights to zero prevents instruction cache movein
+         *
+         * Note subtlety here: _PAGE_GATEWAY, _PAGE_EXEC and _PAGE_WRITE go
+         * to type field and _PAGE_READ goes to top bit of PL1
+         */
+        ldi             (_PAGE_REFTRAP|_PAGE_READ|_PAGE_WRITE),\prot
+        /*
+         * so if the opcode is one (i.e. this is a memory management
+         * instruction) nullify the next load so \prot is only T.
+         * Otherwise this is a normal data operation
+         */
+        cmpiclr,=       0x01,\tmp,%r0
+        ldi             (_PAGE_DIRTY|_PAGE_READ|_PAGE_WRITE),\prot
         depd,z          \prot,8,7,\prot
         /*
          * OK, it is in the temp alias region, check whether "from" or "to".
@@ -631,11 +630,7 @@ ENTRY(fault_vector_20)
         def             13
         def             14
         dtlb_20         15
-#if 0
         naitlb_20       16
-#else
-        def             16
-#endif
         nadtlb_20       17
         def             18
         def             19
@@ -678,11 +673,7 @@ ENTRY(fault_vector_11)
         def             13
         def             14
         dtlb_11         15
-#if 0
         naitlb_11       16
-#else
-        def             16
-#endif
         nadtlb_11       17
         def             18
         def             19
@@ -1203,7 +1194,7 @@ nadtlb_miss_20w:
         get_pgd         spc,ptp
         space_check     spc,t0,nadtlb_fault
 
-        L3_ptep         ptp,pte,t0,va,nadtlb_check_flush_20w
+        L3_ptep         ptp,pte,t0,va,nadtlb_check_alias_20w
 
         update_ptep     ptp,pte,t0,t1
 
@@ -1214,6 +1205,14 @@ nadtlb_miss_20w:
         rfir
         nop
 
+nadtlb_check_alias_20w:
+        do_alias        spc,t0,t1,va,pte,prot,nadtlb_check_flush_20w
+
+        idtlbt          pte,prot
+
+        rfir
+        nop
+
 nadtlb_check_flush_20w:
         bb,>=,n          pte,_PAGE_FLUSH_BIT,nadtlb_emulate
 
@@ -1255,25 +1254,7 @@ dtlb_miss_11:
         nop
 
 dtlb_check_alias_11:
-
-        /* Check to see if fault is in the temporary alias region */
-
-        cmpib,<>,n      0,spc,dtlb_fault /* forward */
-        ldil            L%(TMPALIAS_MAP_START),t0
-        copy            va,t1
-        depwi           0,31,23,t1
-        cmpb,<>,n       t0,t1,dtlb_fault /* forward */
-        ldi             (_PAGE_DIRTY|_PAGE_WRITE|_PAGE_READ),prot
-        depw,z          prot,8,7,prot
-
-        /*
-         * OK, it is in the temp alias region, check whether "from" or "to".
-         * Check "subtle" note in pacache.S re: r23/r26.
-         */
-
-        extrw,u,=       va,9,1,r0
-        or,tr           %r23,%r0,pte    /* If "from" use "from" page */
-        or              %r26,%r0,pte    /* else "to", use "to" page  */
+        do_alias        spc,t0,t1,va,pte,prot,dtlb_fault
 
         idtlba          pte,(va)
         idtlbp          prot,(va)
@@ -1286,7 +1267,7 @@ nadtlb_miss_11:
 
         space_check     spc,t0,nadtlb_fault
 
-        L2_ptep         ptp,pte,t0,va,nadtlb_check_flush_11
+        L2_ptep         ptp,pte,t0,va,nadtlb_check_alias_11
 
         update_ptep     ptp,pte,t0,t1
 
@@ -1304,6 +1285,15 @@ nadtlb_miss_11:
         rfir
         nop
 
+nadtlb_check_alias_11:
+        do_alias        spc,t0,t1,va,pte,prot,nadtlb_check_flush_11
+
+        idtlba          pte,(va)
+        idtlbp          prot,(va)
+
+        rfir
+        nop
+
 nadtlb_check_flush_11:
         bb,>=,n          pte,_PAGE_FLUSH_BIT,nadtlb_emulate
 
@@ -1359,7 +1349,7 @@ nadtlb_miss_20:
 
         space_check     spc,t0,nadtlb_fault
 
-        L2_ptep         ptp,pte,t0,va,nadtlb_check_flush_20
+        L2_ptep         ptp,pte,t0,va,nadtlb_check_alias_20
 
         update_ptep     ptp,pte,t0,t1
 
@@ -1372,6 +1362,14 @@ nadtlb_miss_20:
         rfir
         nop
 
+nadtlb_check_alias_20:
+        do_alias        spc,t0,t1,va,pte,prot,nadtlb_check_flush_20
+
+        idtlbt          pte,prot
+
+        rfir
+        nop
+
 nadtlb_check_flush_20:
         bb,>=,n          pte,_PAGE_FLUSH_BIT,nadtlb_emulate
 
@@ -1484,6 +1482,36 @@ itlb_miss_20w:
         rfir
         nop
 
+naitlb_miss_20w:
+
+        /*
+         * I miss is a little different, since we allow users to fault
+         * on the gateway page which is in the kernel address space.
+         */
+
+        space_adjust    spc,va,t0
+        get_pgd         spc,ptp
+        space_check     spc,t0,naitlb_fault
+
+        L3_ptep         ptp,pte,t0,va,naitlb_check_alias_20w
+
+        update_ptep     ptp,pte,t0,t1
+
+        make_insert_tlb spc,pte,prot
+
+        iitlbt          pte,prot
+
+        rfir
+        nop
+
+naitlb_check_alias_20w:
+        do_alias        spc,t0,t1,va,pte,prot,naitlb_fault
+
+        iitlbt          pte,prot
+
+        rfir
+        nop
+
 #else
 
 itlb_miss_11:
@@ -1508,6 +1536,38 @@ itlb_miss_11:
         rfir
         nop
 
+naitlb_miss_11:
+        get_pgd         spc,ptp
+
+        space_check     spc,t0,naitlb_fault
+
+        L2_ptep         ptp,pte,t0,va,naitlb_check_alias_11
+
+        update_ptep     ptp,pte,t0,t1
+
+        make_insert_tlb_11      spc,pte,prot
+
+        mfsp            %sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+        mtsp            spc,%sr1
+
+        iitlba          pte,(%sr1,va)
+        iitlbp          prot,(%sr1,va)
+
+        mtsp            t0, %sr1        /* Restore sr1 */
+
+        rfir
+        nop
+
+naitlb_check_alias_11:
+        do_alias        spc,t0,t1,va,pte,prot,itlb_fault
+
+        iitlba          pte,(%sr0, va)
+        iitlbp          prot,(%sr0, va)
+
+        rfir
+        nop
+
+
 itlb_miss_20:
         get_pgd         spc,ptp
 
@@ -1526,6 +1586,32 @@ itlb_miss_20:
         rfir
         nop
 
+naitlb_miss_20:
+        get_pgd         spc,ptp
+
+        space_check     spc,t0,naitlb_fault
+
+        L2_ptep         ptp,pte,t0,va,naitlb_check_alias_20
+
+        update_ptep     ptp,pte,t0,t1
+
+        make_insert_tlb spc,pte,prot
+
+        f_extend        pte,t0
+
+        iitlbt          pte,prot
+
+        rfir
+        nop
+
+naitlb_check_alias_20:
+        do_alias        spc,t0,t1,va,pte,prot,naitlb_fault
+
+        iitlbt          pte,prot
+
+        rfir
+        nop
+
 #endif
 
 #ifdef CONFIG_64BIT
@@ -1662,6 +1748,10 @@ nadtlb_fault:
         b               intr_save
         ldi             17,%r8
 
+naitlb_fault:
+        b               intr_save
+        ldi             16,%r8
+
 dtlb_fault:
         b               intr_save
         ldi             15,%r8
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 09b77b2553c6..a85823668cba 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -608,93 +608,131 @@ ENTRY(__clear_user_page_asm)
         .procend
 ENDPROC(__clear_user_page_asm)
 
-ENTRY(flush_kernel_dcache_page_asm)
+ENTRY(flush_dcache_page_asm)
         .proc
         .callinfo NO_CALLS
         .entry
 
+        ldil            L%(TMPALIAS_MAP_START), %r28
+#ifdef CONFIG_64BIT
+#if (TMPALIAS_MAP_START >= 0x80000000)
+        depdi           0, 31,32, %r28          /* clear any sign extension */
+        /* FIXME: page size dependend */
+#endif
+        extrd,u         %r26, 56,32, %r26       /* convert phys addr to tlb insert format */
+        depd            %r25, 63,22, %r28       /* Form aliased virtual address 'to' */
+        depdi           0, 63,12, %r28          /* Clear any offset bits */
+#else
+        extrw,u         %r26, 24,25, %r26       /* convert phys addr to tlb insert format */
+        depw            %r25, 31,22, %r28       /* Form aliased virtual address 'to' */
+        depwi           0, 31,12, %r28          /* Clear any offset bits */
+#endif
+
+        /* Purge any old translation */
+
+        pdtlb           0(%r28)
+
         ldil            L%dcache_stride, %r1
-        ldw             R%dcache_stride(%r1), %r23
+        ldw             R%dcache_stride(%r1), %r1
 
 #ifdef CONFIG_64BIT
         depdi,z         1, 63-PAGE_SHIFT,1, %r25
 #else
         depwi,z         1, 31-PAGE_SHIFT,1, %r25
 #endif
-        add             %r26, %r25, %r25
-        sub             %r25, %r23, %r25
-
-
-1:      fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        fdc,m           %r23(%r26)
-        cmpb,COND(<<)           %r26, %r25,1b
-        fdc,m           %r23(%r26)
+        add             %r28, %r25, %r25
+        sub             %r25, %r1, %r25
+
+
+1:      fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        fdc,m           %r1(%r28)
+        cmpb,COND(<<)           %r28, %r25,1b
+        fdc,m           %r1(%r28)
 
         sync
         bv              %r0(%r2)
-        nop
+        pdtlb           (%r25)
         .exit
 
         .procend
-ENDPROC(flush_kernel_dcache_page_asm)
-        
-ENTRY(flush_user_dcache_page)
+ENDPROC(flush_dcache_page_asm)
+
+ENTRY(flush_icache_page_asm)
         .proc
         .callinfo NO_CALLS
         .entry
 
-        ldil            L%dcache_stride, %r1
-        ldw             R%dcache_stride(%r1), %r23
-
+        ldil            L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
-        depdi,z         1,63-PAGE_SHIFT,1, %r25
+#if (TMPALIAS_MAP_START >= 0x80000000)
+        depdi           0, 31,32, %r28          /* clear any sign extension */
+        /* FIXME: page size dependend */
+#endif
+        extrd,u         %r26, 56,32, %r26       /* convert phys addr to tlb insert format */
+        depd            %r25, 63,22, %r28       /* Form aliased virtual address 'to' */
+        depdi           0, 63,12, %r28          /* Clear any offset bits */
 #else
-        depwi,z         1,31-PAGE_SHIFT,1, %r25
+        extrw,u         %r26, 24,25, %r26       /* convert phys addr to tlb insert format */
+        depw            %r25, 31,22, %r28       /* Form aliased virtual address 'to' */
+        depwi           0, 31,12, %r28          /* Clear any offset bits */
 #endif
-        add             %r26, %r25, %r25
-        sub             %r25, %r23, %r25
 
+        /* Purge any old translation */
 
-1:      fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        fdc,m           %r23(%sr3, %r26)
-        cmpb,COND(<<)           %r26, %r25,1b
-        fdc,m           %r23(%sr3, %r26)
+        pitlb           (%sr0,%r28)
+
+        ldil            L%icache_stride, %r1
+        ldw             R%icache_stride(%r1), %r1
+
+#ifdef CONFIG_64BIT
+        depdi,z         1, 63-PAGE_SHIFT,1, %r25
+#else
+        depwi,z         1, 31-PAGE_SHIFT,1, %r25
+#endif
+        add             %r28, %r25, %r25
+        sub             %r25, %r1, %r25
+
+
+1:      fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        fic,m           %r1(%r28)
+        cmpb,COND(<<)           %r28, %r25,1b
+        fic,m           %r1(%r28)
 
         sync
         bv              %r0(%r2)
-        nop
+        pitlb           (%sr0,%r25)
         .exit
 
         .procend
-ENDPROC(flush_user_dcache_page)
+ENDPROC(flush_icache_page_asm)
 
-ENTRY(flush_user_icache_page)
+ENTRY(flush_kernel_dcache_page_asm)
         .proc
         .callinfo NO_CALLS
         .entry
@@ -711,23 +749,23 @@ ENTRY(flush_user_icache_page)
         sub             %r25, %r23, %r25
 
 
-1:      fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
-        fic,m           %r23(%sr3, %r26)
+1:      fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
+        fdc,m           %r23(%r26)
         cmpb,COND(<<)           %r26, %r25,1b
-        fic,m           %r23(%sr3, %r26)
+        fdc,m           %r23(%r26)
 
         sync
         bv              %r0(%r2)
@@ -735,8 +773,7 @@ ENTRY(flush_user_icache_page)
         .exit
 
         .procend
-ENDPROC(flush_user_icache_page)
-
+ENDPROC(flush_kernel_dcache_page_asm)
 
 ENTRY(purge_kernel_dcache_page)
         .proc
@@ -780,69 +817,6 @@ ENTRY(purge_kernel_dcache_page)
         .procend
 ENDPROC(purge_kernel_dcache_page)
 
-#if 0
-        /* Currently not used, but it still is a possible alternate
-         * solution.
-         */
-
-ENTRY(flush_alias_page)
-        .proc
-        .callinfo NO_CALLS
-        .entry
-
-        tophys_r1               %r26
-
-        ldil            L%(TMPALIAS_MAP_START), %r28
-#ifdef CONFIG_64BIT
-        extrd,u         %r26, 56,32, %r26       /* convert phys addr to tlb insert format */
-        depd            %r25, 63,22, %r28       /* Form aliased virtual address 'to' */
-        depdi           0, 63,12, %r28          /* Clear any offset bits */
-#else
-        extrw,u         %r26, 24,25, %r26       /* convert phys addr to tlb insert format */
-        depw            %r25, 31,22, %r28       /* Form aliased virtual address 'to' */
-        depwi           0, 31,12, %r28          /* Clear any offset bits */
-#endif
-
-        /* Purge any old translation */
-
-        pdtlb           0(%r28)
-
-        ldil            L%dcache_stride, %r1
-        ldw             R%dcache_stride(%r1), %r23
-
-#ifdef CONFIG_64BIT
-        depdi,z         1, 63-PAGE_SHIFT,1, %r29
-#else
-        depwi,z         1, 31-PAGE_SHIFT,1, %r29
-#endif
-        add             %r28, %r29, %r29
-        sub             %r29, %r23, %r29
-
-1:      fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        fdc,m           %r23(%r28)
-        cmpb,COND(<<)           %r28, %r29, 1b
-        fdc,m           %r23(%r28)
-
-        sync
-        bv              %r0(%r2)
-        nop
-        .exit
-
-        .procend
-#endif
 
         .export flush_user_dcache_range_asm
 
@@ -865,7 +839,6 @@ flush_user_dcache_range_asm:
         .exit
 
         .procend
-ENDPROC(flush_alias_page)
 
 ENTRY(flush_kernel_dcache_range_asm)
         .proc