patch-2.4.20 linux-2.4.20/arch/parisc/kernel/pacache.S

Next file: linux-2.4.20/arch/parisc/kernel/parisc_ksyms.c
Previous file: linux-2.4.20/arch/parisc/kernel/pa7300lc.c
Back to the patch index
Back to the overall index

diff -urN linux-2.4.19/arch/parisc/kernel/pacache.S linux-2.4.20/arch/parisc/kernel/pacache.S
@@ -0,0 +1,908 @@
+/*
+ *  Parisc tlb and cache flushing support
+ *  Copyright (C) 2000 Hewlett-Packard (John Marvin)
+ *
+ *    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, or (at your option)
+ *    any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * NOTE: fdc,fic, and pdc instructions that use base register modification
+ *       should only use index and base registers that are not shadowed,
+ *       so that the fast path emulation in the non access miss handler
+ *       can be used.
+ */
+
+#ifdef __LP64__
+#define ADDIB   addib,*
+#define CMPB    cmpb,*
+#define ANDCM   andcm,*
+
+	.level 2.0w
+#else
+#define ADDIB   addib,
+#define CMPB    cmpb,
+#define ANDCM   andcm
+
+	.level 2.0
+#endif
+
+#include <asm/assembly.h>
+#include <asm/psw.h>
+#include <asm/pgtable.h>
+#include <asm/cache.h>
+
+	.text
+	.align 128
+
+	.export flush_tlb_all_local,code
+
+flush_tlb_all_local:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	/*
+	 * The pitlbe and pdtlbe instructions should only be used to
+	 * flush the entire tlb. Also, there needs to be no intervening
+	 * tlb operations, e.g. tlb misses, so the operation needs
+	 * to happen in real mode with all interruptions disabled.
+	 */
+
+	/*
+	 * Once again, we do the rfi dance ... some day we need examine
+	 * all of our uses of this type of code and see what can be
+	 * consolidated.
+	 */
+
+	rsm     PSW_SM_I,%r19      /* relied upon translation! */
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	
+	rsm     PSW_SM_Q,%r0       /* Turn off Q bit to load iia queue */
+	ldil    L%REAL_MODE_PSW, %r1
+	ldo     R%REAL_MODE_PSW(%r1), %r1
+	mtctl	%r1, %cr22
+	mtctl	%r0, %cr17
+	mtctl	%r0, %cr17
+	ldil    L%PA(1f),%r1
+	ldo     R%PA(1f)(%r1),%r1
+	mtctl	%r1, %cr18
+	ldo	4(%r1), %r1
+	mtctl	%r1, %cr18
+	rfi
+	nop
+
+1:      ldil            L%PA(cache_info),%r1
+	ldo             R%PA(cache_info)(%r1),%r1
+
+	/* Flush Instruction Tlb */
+
+	LDREG           ITLB_SID_BASE(%r1),%r20
+	LDREG           ITLB_SID_STRIDE(%r1),%r21
+	LDREG           ITLB_SID_COUNT(%r1),%r22
+	LDREG           ITLB_OFF_BASE(%r1),%arg0
+	LDREG           ITLB_OFF_STRIDE(%r1),%arg1
+	LDREG           ITLB_OFF_COUNT(%r1),%arg2
+	LDREG           ITLB_LOOP(%r1),%arg3
+
+	ADDIB=          -1,%arg3,fitoneloop     /* Preadjust and test */
+	movb,<,n        %arg3,%r31,fitdone      /* If loop < 0, skip */
+	copy            %arg0,%r28              /* Init base addr */
+
+fitmanyloop:                                    /* Loop if LOOP >= 2 */
+	mtsp            %r20,%sr1
+	add             %r21,%r20,%r20          /* increment space */
+	copy            %arg2,%r29              /* Init middle loop count */
+
+fitmanymiddle:                                  /* Loop if LOOP >= 2 */
+	ADDIB>          -1,%r31,fitmanymiddle   /* Adjusted inner loop decr */
+	pitlbe          0(%sr1,%r28)
+	pitlbe,m        %arg1(%sr1,%r28)        /* Last pitlbe and addr adjust */
+	ADDIB>          -1,%r29,fitmanymiddle   /* Middle loop decr */
+	copy            %arg3,%r31              /* Re-init inner loop count */
+
+	movb,tr         %arg0,%r28,fitmanyloop  /* Re-init base addr */
+	ADDIB<=,n       -1,%r22,fitdone         /* Outer loop count decr */
+
+fitoneloop:                                     /* Loop if LOOP = 1 */
+	mtsp            %r20,%sr1
+	copy            %arg0,%r28              /* init base addr */
+	copy            %arg2,%r29              /* init middle loop count */
+
+fitonemiddle:                                   /* Loop if LOOP = 1 */
+	ADDIB>          -1,%r29,fitonemiddle    /* Middle loop count decr */
+	pitlbe,m        %arg1(%sr1,%r28)        /* pitlbe for one loop */
+
+	ADDIB>          -1,%r22,fitoneloop      /* Outer loop count decr */
+	add             %r21,%r20,%r20          /* increment space */
+
+fitdone:
+
+	/* Flush Data Tlb */
+
+	LDREG           DTLB_SID_BASE(%r1),%r20
+	LDREG           DTLB_SID_STRIDE(%r1),%r21
+	LDREG           DTLB_SID_COUNT(%r1),%r22
+	LDREG           DTLB_OFF_BASE(%r1),%arg0
+	LDREG           DTLB_OFF_STRIDE(%r1),%arg1
+	LDREG           DTLB_OFF_COUNT(%r1),%arg2
+	LDREG           DTLB_LOOP(%r1),%arg3
+
+	ADDIB=          -1,%arg3,fdtoneloop     /* Preadjust and test */
+	movb,<,n        %arg3,%r31,fdtdone      /* If loop < 0, skip */
+	copy            %arg0,%r28              /* Init base addr */
+
+fdtmanyloop:                                    /* Loop if LOOP >= 2 */
+	mtsp            %r20,%sr1
+	add             %r21,%r20,%r20          /* increment space */
+	copy            %arg2,%r29              /* Init middle loop count */
+
+fdtmanymiddle:                                  /* Loop if LOOP >= 2 */
+	ADDIB>          -1,%r31,fdtmanymiddle   /* Adjusted inner loop decr */
+	pdtlbe          0(%sr1,%r28)
+	pdtlbe,m        %arg1(%sr1,%r28)        /* Last pdtlbe and addr adjust */
+	ADDIB>          -1,%r29,fdtmanymiddle   /* Middle loop decr */
+	copy            %arg3,%r31              /* Re-init inner loop count */
+
+	movb,tr         %arg0,%r28,fdtmanyloop  /* Re-init base addr */
+	ADDIB<=,n       -1,%r22,fdtdone         /* Outer loop count decr */
+
+fdtoneloop:                                     /* Loop if LOOP = 1 */
+	mtsp            %r20,%sr1
+	copy            %arg0,%r28              /* init base addr */
+	copy            %arg2,%r29              /* init middle loop count */
+
+fdtonemiddle:                                   /* Loop if LOOP = 1 */
+	ADDIB>          -1,%r29,fdtonemiddle    /* Middle loop count decr */
+	pdtlbe,m        %arg1(%sr1,%r28)        /* pdtlbe for one loop */
+
+	ADDIB>          -1,%r22,fdtoneloop      /* Outer loop count decr */
+	add             %r21,%r20,%r20          /* increment space */
+
+fdtdone:
+
+	/* Switch back to virtual mode */
+
+	rsm     PSW_SM_Q,%r0       /* clear Q bit to load iia queue */
+	ldil	L%KERNEL_PSW, %r1
+	ldo	R%KERNEL_PSW(%r1), %r1
+	or      %r1,%r19,%r1    /* Set I bit if set on entry */
+	mtctl	%r1, %cr22
+	mtctl	%r0, %cr17
+	mtctl	%r0, %cr17
+	ldil    L%(2f), %r1
+	ldo     R%(2f)(%r1), %r1
+	mtctl	%r1, %cr18
+	ldo	4(%r1), %r1
+	mtctl	%r1, %cr18
+	rfi
+	nop
+
+2:      bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_instruction_cache_local,code
+	.import cache_info,data
+
+flush_instruction_cache_local:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	mtsp            %r0,%sr1
+	ldil            L%cache_info,%r1
+	ldo             R%cache_info(%r1),%r1
+
+	/* Flush Instruction Cache */
+
+	LDREG           ICACHE_BASE(%r1),%arg0
+	LDREG           ICACHE_STRIDE(%r1),%arg1
+	LDREG           ICACHE_COUNT(%r1),%arg2
+	LDREG           ICACHE_LOOP(%r1),%arg3
+	ADDIB=          -1,%arg3,fioneloop      /* Preadjust and test */
+	movb,<,n        %arg3,%r31,fisync       /* If loop < 0, do sync */
+
+fimanyloop:                                     /* Loop if LOOP >= 2 */
+	ADDIB>          -1,%r31,fimanyloop      /* Adjusted inner loop decr */
+	fice            0(%sr1,%arg0)
+	fice,m          %arg1(%sr1,%arg0)       /* Last fice and addr adjust */
+	movb,tr         %arg3,%r31,fimanyloop   /* Re-init inner loop count */
+	ADDIB<=,n       -1,%arg2,fisync         /* Outer loop decr */
+
+fioneloop:                                      /* Loop if LOOP = 1 */
+	ADDIB>          -1,%arg2,fioneloop      /* Outer loop count decr */
+	fice,m          %arg1(%sr1,%arg0)       /* Fice for one loop */
+
+fisync:
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_data_cache_local,code
+	.import cache_info,data
+
+flush_data_cache_local:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	mtsp            %r0,%sr1
+	ldil            L%cache_info,%r1
+	ldo             R%cache_info(%r1),%r1
+
+	/* Flush Data Cache */
+
+	LDREG           DCACHE_BASE(%r1),%arg0
+	LDREG           DCACHE_STRIDE(%r1),%arg1
+	LDREG           DCACHE_COUNT(%r1),%arg2
+	LDREG           DCACHE_LOOP(%r1),%arg3
+	rsm             PSW_SM_I,%r22
+	ADDIB=          -1,%arg3,fdoneloop      /* Preadjust and test */
+	movb,<,n        %arg3,%r31,fdsync       /* If loop < 0, do sync */
+
+fdmanyloop:                                     /* Loop if LOOP >= 2 */
+	ADDIB>          -1,%r31,fdmanyloop      /* Adjusted inner loop decr */
+	fdce            0(%sr1,%arg0)
+	fdce,m          %arg1(%sr1,%arg0)       /* Last fdce and addr adjust */
+	movb,tr         %arg3,%r31,fdmanyloop   /* Re-init inner loop count */
+	ADDIB<=,n       -1,%arg2,fdsync         /* Outer loop decr */
+
+fdoneloop:                                      /* Loop if LOOP = 1 */
+	ADDIB>          -1,%arg2,fdoneloop      /* Outer loop count decr */
+	fdce,m          %arg1(%sr1,%arg0)       /* Fdce for one loop */
+
+fdsync:
+	syncdma
+	sync
+	mtsm    %r22
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export copy_user_page_asm,code
+
+copy_user_page_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldi 64,%r1
+
+	/*
+	 * This loop is optimized for PCXL/PCXL2 ldw/ldw and stw/stw
+	 * bundles (very restricted rules for bundling). It probably
+	 * does OK on PCXU and better, but we could do better with
+	 * ldd/std instructions. Note that until (if) we start saving
+	 * the full 64 bit register values on interrupt, we can't
+	 * use ldd/std on a 32 bit kernel.
+	 */
+
+
+1:
+	ldw 0(%r25),%r19
+	ldw 4(%r25),%r20
+	ldw 8(%r25),%r21
+	ldw 12(%r25),%r22
+	stw %r19,0(%r26)
+	stw %r20,4(%r26)
+	stw %r21,8(%r26)
+	stw %r22,12(%r26)
+	ldw 16(%r25),%r19
+	ldw 20(%r25),%r20
+	ldw 24(%r25),%r21
+	ldw 28(%r25),%r22
+	stw %r19,16(%r26)
+	stw %r20,20(%r26)
+	stw %r21,24(%r26)
+	stw %r22,28(%r26)
+	ldw 32(%r25),%r19
+	ldw 36(%r25),%r20
+	ldw 40(%r25),%r21
+	ldw 44(%r25),%r22
+	stw %r19,32(%r26)
+	stw %r20,36(%r26)
+	stw %r21,40(%r26)
+	stw %r22,44(%r26)
+	ldw 48(%r25),%r19
+	ldw 52(%r25),%r20
+	ldw 56(%r25),%r21
+	ldw 60(%r25),%r22
+	stw %r19,48(%r26)
+	stw %r20,52(%r26)
+	stw %r21,56(%r26)
+	stw %r22,60(%r26)
+	ldo 64(%r26),%r26
+	ADDIB>  -1,%r1,1b
+	ldo 64(%r25),%r25
+
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+#if (TMPALIAS_MAP_START >= 0x80000000UL)
+Warning TMPALIAS_MAP_START changed. If > 2 Gb, code in pacache.S is bogus
+#endif
+
+/*
+ * NOTE: Code in clear_user_page has a hard coded dependency on the
+ *       maximum alias boundary being 4 Mb. We've been assured by the
+ *       parisc chip designers that there will not ever be a parisc
+ *       chip with a larger alias boundary (Never say never :-) ).
+ *
+ *       Subtle: the dtlb miss handlers support the temp alias region by
+ *       "knowing" that if a dtlb miss happens within the temp alias
+ *       region it must have occurred while in clear_user_page. Since
+ *       this routine makes use of processor local translations, we
+ *       don't want to insert them into the kernel page table. Instead,
+ *       we load up some general registers (they need to be registers
+ *       which aren't shadowed) with the physical page numbers (preshifted
+ *       for tlb insertion) needed to insert the translations. When we
+ *       miss on the translation, the dtlb miss handler inserts the
+ *       translation into the tlb using these values:
+ *
+ *          %r26 physical page (shifted for tlb insert) of "to" translation
+ *          %r23 physical page (shifted for tlb insert) of "from" translation
+ */
+
+#if 0
+
+	/*
+	 * We can't do this since copy_user_page is used to bring in
+	 * file data that might have instructions. Since the data would
+	 * then need to be flushed out so the i-fetch can see it, it
+	 * makes more sense to just copy through the kernel translation
+	 * and flush it.
+	 *
+	 * I'm still keeping this around because it may be possible to
+	 * use it if more information is passed into copy_user_page().
+	 * Have to do some measurements to see if it is worthwhile to
+	 * lobby for such a change.
+	 */
+
+	.export copy_user_page_asm,code
+
+copy_user_page_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%(__PAGE_OFFSET),%r1
+	sub     %r26,%r1,%r26
+	sub     %r25,%r1,%r23  /* move physical addr into non shadowed reg */
+
+	ldil    L%(TMPALIAS_MAP_START),%r28
+#ifdef __LP64__
+	extrd,u %r26,56,32,%r26 /* convert phys addr to tlb insert format */
+	extrd,u %r23,56,32,%r23 /* convert phys addr to tlb insert format */
+	depd    %r24,63,22,%r28 /* Form aliased virtual address 'to' */
+	depdi   0,63,12,%r28    /* Clear any offset bits */
+	copy    %r28,%r29
+	depdi   1,41,1,%r29     /* Form aliased virtual address 'from' */
+#else
+	extrw,u %r26,24,25,%r26 /* convert phys addr to tlb insert format */
+	extrw,u %r23,24,25,%r23 /* convert phys addr to tlb insert format */
+	depw    %r24,31,22,%r28 /* Form aliased virtual address 'to' */
+	depwi   0,31,12,%r28    /* Clear any offset bits */
+	copy    %r28,%r29
+	depwi   1,9,1,%r29      /* Form aliased virtual address 'from' */
+#endif
+
+	/* Purge any old translations */
+
+	pdtlb   0(%r28)
+	pdtlb   0(%r29)
+
+	ldi 64,%r1
+
+	/*
+	 * This loop is optimized for PCXL/PCXL2 ldw/ldw and stw/stw
+	 * bundles (very restricted rules for bundling). It probably
+	 * does OK on PCXU and better, but we could do better with
+	 * ldd/std instructions. Note that until (if) we start saving
+	 * the full 64 bit register values on interrupt, we can't
+	 * use ldd/std on a 32 bit kernel.
+	 */
+
+
+1:
+	ldw 0(%r29),%r19
+	ldw 4(%r29),%r20
+	ldw 8(%r29),%r21
+	ldw 12(%r29),%r22
+	stw %r19,0(%r28)
+	stw %r20,4(%r28)
+	stw %r21,8(%r28)
+	stw %r22,12(%r28)
+	ldw 16(%r29),%r19
+	ldw 20(%r29),%r20
+	ldw 24(%r29),%r21
+	ldw 28(%r29),%r22
+	stw %r19,16(%r28)
+	stw %r20,20(%r28)
+	stw %r21,24(%r28)
+	stw %r22,28(%r28)
+	ldw 32(%r29),%r19
+	ldw 36(%r29),%r20
+	ldw 40(%r29),%r21
+	ldw 44(%r29),%r22
+	stw %r19,32(%r28)
+	stw %r20,36(%r28)
+	stw %r21,40(%r28)
+	stw %r22,44(%r28)
+	ldw 48(%r29),%r19
+	ldw 52(%r29),%r20
+	ldw 56(%r29),%r21
+	ldw 60(%r29),%r22
+	stw %r19,48(%r28)
+	stw %r20,52(%r28)
+	stw %r21,56(%r28)
+	stw %r22,60(%r28)
+	ldo 64(%r28),%r28
+	ADDIB>  -1,%r1,1b
+	ldo 64(%r29),%r29
+
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+#endif
+
+	.export clear_user_page_asm,code
+
+clear_user_page_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	tophys_r1 %r26
+
+	ldil    L%(TMPALIAS_MAP_START),%r28
+#ifdef __LP64__
+	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)
+
+	ldi 64,%r1
+
+1:
+	stw %r0,0(%r28)
+	stw %r0,4(%r28)
+	stw %r0,8(%r28)
+	stw %r0,12(%r28)
+	stw %r0,16(%r28)
+	stw %r0,20(%r28)
+	stw %r0,24(%r28)
+	stw %r0,28(%r28)
+	stw %r0,32(%r28)
+	stw %r0,36(%r28)
+	stw %r0,40(%r28)
+	stw %r0,44(%r28)
+	stw %r0,48(%r28)
+	stw %r0,52(%r28)
+	stw %r0,56(%r28)
+	stw %r0,60(%r28)
+	ADDIB>  -1,%r1,1b
+	ldo 64(%r28),%r28
+
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_kernel_dcache_page
+
+flush_kernel_dcache_page:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%dcache_stride,%r1
+	ldw     R%dcache_stride(%r1),%r23
+
+#ifdef __LP64__
+	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<<  %r26,%r25,1b
+	fdc,m   %r23(%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export purge_kernel_dcache_page
+
+purge_kernel_dcache_page:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%dcache_stride,%r1
+	ldw     R%dcache_stride(%r1),%r23
+
+#ifdef __LP64__
+	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:      pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	pdc,m   %r23(%r26)
+	CMPB<<  %r26,%r25,1b
+	pdc,m   %r23(%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+#if 0
+	/* Currently not used, but it still is a possible alternate
+	 * solution.
+	 */
+
+	.export flush_alias_page
+
+flush_alias_page:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	tophys_r1 %r26
+
+	ldil    L%(TMPALIAS_MAP_START),%r28
+#ifdef __LP64__
+	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 __LP64__
+	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<<  %r28,%r29,1b
+	fdc,m   %r23(%r28)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+#endif
+
+	.export flush_user_dcache_range_asm
+
+flush_user_dcache_range_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%dcache_stride,%r1
+	ldw     R%dcache_stride(%r1),%r23
+	ldo     -1(%r23),%r21
+	ANDCM   %r26,%r21,%r26
+
+1:      CMPB<<,n %r26,%r25,1b
+	fdc,m   %r23(%sr3,%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_kernel_dcache_range_asm
+
+flush_kernel_dcache_range_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%dcache_stride,%r1
+	ldw     R%dcache_stride(%r1),%r23
+	ldo     -1(%r23),%r21
+	ANDCM   %r26,%r21,%r26
+
+1:      CMPB<<,n %r26,%r25,1b
+	fdc,m   %r23(%r26)
+
+	sync
+	syncdma
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_user_icache_range_asm
+
+flush_user_icache_range_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%icache_stride,%r1
+	ldw     R%icache_stride(%r1),%r23
+	ldo     -1(%r23),%r21
+	ANDCM   %r26,%r21,%r26
+
+1:      CMPB<<,n %r26,%r25,1b
+	fic,m   %r23(%sr3,%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_kernel_icache_page
+
+flush_kernel_icache_page:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%icache_stride,%r1
+	ldw     R%icache_stride(%r1),%r23
+
+#ifdef __LP64__
+	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:      fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	fic,m   %r23(%r26)
+	CMPB<<  %r26,%r25,1b
+	fic,m   %r23(%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.export flush_kernel_icache_range_asm
+
+flush_kernel_icache_range_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	ldil    L%icache_stride,%r1
+	ldw     R%icache_stride(%r1),%r23
+	ldo     -1(%r23),%r21
+	ANDCM   %r26,%r21,%r26
+
+1:      CMPB<<,n %r26,%r25,1b
+	fic,m   %r23(%r26)
+
+	sync
+	bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.align 128
+
+	.export disable_sr_hashing_asm,code
+
+disable_sr_hashing_asm:
+	.proc
+	.callinfo NO_CALLS
+	.entry
+
+	/* Switch to real mode */
+
+	ssm     0,%r0           /* relied upon translation! */
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	nop
+	
+	rsm     (PSW_SM_Q|PSW_SM_I),%r0 /* disable Q&I to load the iia queue */
+	ldil    L%REAL_MODE_PSW, %r1
+	ldo     R%REAL_MODE_PSW(%r1), %r1
+	mtctl	%r1, %cr22
+	mtctl	%r0, %cr17
+	mtctl	%r0, %cr17
+	ldil    L%PA(1f),%r1
+	ldo     R%PA(1f)(%r1),%r1
+	mtctl	%r1, %cr18
+	ldo	4(%r1), %r1
+	mtctl	%r1, %cr18
+	rfi
+	nop
+
+1:      cmpib,=,n SRHASH_PCXST,%r26,srdis_pcxs
+	cmpib,=,n SRHASH_PCXL,%r26,srdis_pcxl
+	cmpib,=,n SRHASH_PA20,%r26,srdis_pa20
+	b,n       srdis_done
+
+srdis_pcxs:
+
+	/* Disable Space Register Hashing for PCXS,PCXT,PCXT' */
+
+	.word           0x141c1a00  /* mfdiag %dr0,%r28 */
+	.word           0x141c1a00  /* must issue twice */
+	depwi           0,18,1,%r28 /* Clear DHE (dcache hash enable) */
+	depwi           0,20,1,%r28 /* Clear IHE (icache hash enable) */
+	.word           0x141c1600  /* mtdiag %r28,%dr0 */
+	.word           0x141c1600  /* must issue twice */
+	b,n             srdis_done
+
+srdis_pcxl:
+
+	/* Disable Space Register Hashing for PCXL */
+
+	.word           0x141c0600  /* mfdiag %dr0,%r28 */
+	depwi           0,28,2,%r28 /* Clear DHASH_EN & IHASH_EN */
+	.word           0x141c0240  /* mtdiag %r28,%dr0 */
+	b,n             srdis_done
+
+srdis_pa20:
+
+	/* Disable Space Register Hashing for PCXU,PCXU+,PCXW,PCXW+ */
+
+	.word           0x144008bc  /* mfdiag %dr2,%r28 */
+	depdi           0,54,1,%r28 /* clear DIAG_SPHASH_ENAB (bit 54) */
+	.word           0x145c1840  /* mtdiag %r28,%dr2 */
+
+srdis_done:
+
+	/* Switch back to virtual mode */
+
+	rsm     PSW_SM_Q,%r0           /* clear Q bit to load iia queue */
+	ldil	L%KERNEL_PSW, %r1
+	ldo	R%KERNEL_PSW(%r1), %r1
+	mtctl	%r1, %cr22
+	mtctl	%r0, %cr17
+	mtctl	%r0, %cr17
+	ldil    L%(2f), %r1
+	ldo     R%(2f)(%r1), %r1
+	mtctl	%r1, %cr18
+	ldo	4(%r1), %r1
+	mtctl	%r1, %cr18
+	rfi
+	nop
+
+2:      bv      %r0(%r2)
+	nop
+	.exit
+
+	.procend
+
+	.end

FUNET's LINUX-ADM group, linux-adm@nic.funet.fi
TCL-scripts by Sam Shen (who was at: slshen@lbl.gov)