1 files changed, 568 insertions, 0 deletions
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
new file mode 100644
index 000000000..96c514bee
--- /dev/null
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -0,0 +1,568 @@
+/*
+ * Copyright (C) 2002 Paul Mackerras, IBM Corp.
+ *
+ * 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 <asm/processor.h>
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+
+#ifndef SELFTEST_CASE
+/* 0 == most CPUs, 1 == POWER6, 2 == Cell */
+#define SELFTEST_CASE	0
+#endif
+
+#ifdef __BIG_ENDIAN__
+#define sLd sld		/* Shift towards low-numbered address. */
+#define sHd srd		/* Shift towards high-numbered address. */
+#else
+#define sLd srd		/* Shift towards low-numbered address. */
+#define sHd sld		/* Shift towards high-numbered address. */
+#endif
+
+/*
+ * These macros are used to generate exception table entries.
+ * The exception handlers below use the original arguments
+ * (stored on the stack) and the point where we're up to in
+ * the destination buffer, i.e. the address of the first
+ * unmodified byte.  Generally r3 points into the destination
+ * buffer, but the first unmodified byte is at a variable
+ * offset from r3.  In the code below, the symbol r3_offset
+ * is set to indicate the current offset at each point in
+ * the code.  This offset is then used as a negative offset
+ * from the exception handler code, and those instructions
+ * before the exception handlers are addi instructions that
+ * adjust r3 to point to the correct place.
+ */
+	.macro	lex		/* exception handler for load */
+100:	EX_TABLE(100b, .Lld_exc - r3_offset)
+	.endm
+
+	.macro	stex		/* exception handler for store */
+100:	EX_TABLE(100b, .Lst_exc - r3_offset)
+	.endm
+
+	.align	7
+_GLOBAL_TOC(__copy_tofrom_user)
+#ifdef CONFIG_PPC_BOOK3S_64
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
+	b	__copy_tofrom_user_power7
+ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
+#endif
+_GLOBAL(__copy_tofrom_user_base)
+	/* first check for a 4kB copy on a 4kB boundary */
+	cmpldi	cr1,r5,16
+	cmpdi	cr6,r5,4096
+	or	r0,r3,r4
+	neg	r6,r3		/* LS 3 bits = # bytes to 8-byte dest bdry */
+	andi.	r0,r0,4095
+	std	r3,-24(r1)
+	crand	cr0*4+2,cr0*4+2,cr6*4+2
+	std	r4,-16(r1)
+	std	r5,-8(r1)
+	dcbt	0,r4
+	beq	.Lcopy_page_4K
+	andi.	r6,r6,7
+	PPC_MTOCRF(0x01,r5)
+	blt	cr1,.Lshort_copy
+/* Below we want to nop out the bne if we're on a CPU that has the
+ * CPU_FTR_UNALIGNED_LD_STD bit set and the CPU_FTR_CP_USE_DCBTZ bit
+ * cleared.
+ * At the time of writing the only CPU that has this combination of bits
+ * set is Power6.
+ */
+test_feature = (SELFTEST_CASE == 1)
+BEGIN_FTR_SECTION
+	nop
+FTR_SECTION_ELSE
+	bne	.Ldst_unaligned
+ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
+		    CPU_FTR_UNALIGNED_LD_STD)
+.Ldst_aligned:
+	addi	r3,r3,-16
+r3_offset = 16
+test_feature = (SELFTEST_CASE == 0)
+BEGIN_FTR_SECTION
+	andi.	r0,r4,7
+	bne	.Lsrc_unaligned
+END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
+	blt	cr1,.Ldo_tail		/* if < 16 bytes to copy */
+	srdi	r0,r5,5
+	cmpdi	cr1,r0,0
+lex;	ld	r7,0(r4)
+lex;	ld	r6,8(r4)
+	addi	r4,r4,16
+	mtctr	r0
+	andi.	r0,r5,0x10
+	beq	22f
+	addi	r3,r3,16
+r3_offset = 0
+	addi	r4,r4,-16
+	mr	r9,r7
+	mr	r8,r6
+	beq	cr1,72f
+21:
+lex;	ld	r7,16(r4)
+lex;	ld	r6,24(r4)
+	addi	r4,r4,32
+stex;	std	r9,0(r3)
+r3_offset = 8
+stex;	std	r8,8(r3)
+r3_offset = 16
+22:
+lex;	ld	r9,0(r4)
+lex;	ld	r8,8(r4)
+stex;	std	r7,16(r3)
+r3_offset = 24
+stex;	std	r6,24(r3)
+	addi	r3,r3,32
+r3_offset = 0
+	bdnz	21b
+72:
+stex;	std	r9,0(r3)
+r3_offset = 8
+stex;	std	r8,8(r3)
+r3_offset = 16
+	andi.	r5,r5,0xf
+	beq+	3f
+	addi	r4,r4,16
+.Ldo_tail:
+	addi	r3,r3,16
+r3_offset = 0
+	bf	cr7*4+0,246f
+lex;	ld	r9,0(r4)
+	addi	r4,r4,8
+stex;	std	r9,0(r3)
+	addi	r3,r3,8
+246:	bf	cr7*4+1,1f
+lex;	lwz	r9,0(r4)
+	addi	r4,r4,4
+stex;	stw	r9,0(r3)
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+lex;	lhz	r9,0(r4)
+	addi	r4,r4,2
+stex;	sth	r9,0(r3)
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+lex;	lbz	r9,0(r4)
+stex;	stb	r9,0(r3)
+3:	li	r3,0
+	blr
+
+.Lsrc_unaligned:
+r3_offset = 16
+	srdi	r6,r5,3
+	addi	r5,r5,-16
+	subf	r4,r0,r4
+	srdi	r7,r5,4
+	sldi	r10,r0,3
+	cmpldi	cr6,r6,3
+	andi.	r5,r5,7
+	mtctr	r7
+	subfic	r11,r10,64
+	add	r5,r5,r0
+	bt	cr7*4+0,28f
+
+lex;	ld	r9,0(r4)	/* 3+2n loads, 2+2n stores */
+lex;	ld	r0,8(r4)
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	or	r7,r7,r6
+	blt	cr6,79f
+lex;	ld	r0,8(r4)
+	b	2f
+
+28:
+lex;	ld	r0,0(r4)	/* 4+2n loads, 3+2n stores */
+lex;	ldu	r9,8(r4)
+	sLd	r8,r0,r10
+	addi	r3,r3,-8
+r3_offset = 24
+	blt	cr6,5f
+lex;	ld	r0,8(r4)
+	sHd	r12,r9,r11
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	or	r12,r8,r12
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	addi	r3,r3,16
+r3_offset = 8
+	beq	cr6,78f
+
+1:	or	r7,r7,r6
+lex;	ld	r0,8(r4)
+stex;	std	r12,8(r3)
+r3_offset = 16
+2:	sHd	r12,r9,r11
+	sLd	r6,r9,r10
+lex;	ldu	r9,16(r4)
+	or	r12,r8,r12
+stex;	stdu	r7,16(r3)
+r3_offset = 8
+	sHd	r7,r0,r11
+	sLd	r8,r0,r10
+	bdnz	1b
+
+78:
+stex;	std	r12,8(r3)
+r3_offset = 16
+	or	r7,r7,r6
+79:
+stex;	std	r7,16(r3)
+r3_offset = 24
+5:	sHd	r12,r9,r11
+	or	r12,r8,r12
+stex;	std	r12,24(r3)
+r3_offset = 32
+	bne	6f
+	li	r3,0
+	blr
+6:	cmpwi	cr1,r5,8
+	addi	r3,r3,32
+r3_offset = 0
+	sLd	r9,r9,r10
+	ble	cr1,7f
+lex;	ld	r0,8(r4)
+	sHd	r7,r0,r11
+	or	r9,r7,r9
+7:
+	bf	cr7*4+1,1f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,32
+#endif
+stex;	stw	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,32
+#endif
+	addi	r3,r3,4
+1:	bf	cr7*4+2,2f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,16
+#endif
+stex;	sth	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,16
+#endif
+	addi	r3,r3,2
+2:	bf	cr7*4+3,3f
+#ifdef __BIG_ENDIAN__
+	rotldi	r9,r9,8
+#endif
+stex;	stb	r9,0(r3)
+#ifdef __LITTLE_ENDIAN__
+	rotrdi	r9,r9,8
+#endif
+3:	li	r3,0
+	blr
+
+.Ldst_unaligned:
+r3_offset = 0
+	PPC_MTOCRF(0x01,r6)		/* put #bytes to 8B bdry into cr7 */
+	subf	r5,r6,r5
+	li	r7,0
+	cmpldi	cr1,r5,16
+	bf	cr7*4+3,1f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lbz	r0,0(r4)
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	stb	r0,0(r3)
+	addi	r7,r7,1
+1:	bf	cr7*4+2,2f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lhzx	r0,r7,r4
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	sthx	r0,r7,r3
+	addi	r7,r7,2
+2:	bf	cr7*4+1,3f
+100:	EX_TABLE(100b, .Lld_exc_r7)
+	lwzx	r0,r7,r4
+100:	EX_TABLE(100b, .Lst_exc_r7)
+	stwx	r0,r7,r3
+3:	PPC_MTOCRF(0x01,r5)
+	add	r4,r6,r4
+	add	r3,r6,r3
+	b	.Ldst_aligned
+
+.Lshort_copy:
+r3_offset = 0
+	bf	cr7*4+0,1f
+lex;	lwz	r0,0(r4)
+lex;	lwz	r9,4(r4)
+	addi	r4,r4,8
+stex;	stw	r0,0(r3)
+stex;	stw	r9,4(r3)
+	addi	r3,r3,8
+1:	bf	cr7*4+1,2f
+lex;	lwz	r0,0(r4)
+	addi	r4,r4,4
+stex;	stw	r0,0(r3)
+	addi	r3,r3,4
+2:	bf	cr7*4+2,3f
+lex;	lhz	r0,0(r4)
+	addi	r4,r4,2
+stex;	sth	r0,0(r3)
+	addi	r3,r3,2
+3:	bf	cr7*4+3,4f
+lex;	lbz	r0,0(r4)
+stex;	stb	r0,0(r3)
+4:	li	r3,0
+	blr
+
+/*
+ * exception handlers follow
+ * we have to return the number of bytes not copied
+ * for an exception on a load, we set the rest of the destination to 0
+ * Note that the number of bytes of instructions for adjusting r3 needs
+ * to equal the amount of the adjustment, due to the trick of using
+ * .Lld_exc - r3_offset as the handler address.
+ */
+
+.Lld_exc_r7:
+	add	r3,r3,r7
+	b	.Lld_exc
+
+	/* adjust by 24 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 16 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 8 */
+	addi	r3,r3,8
+	nop
+
+/*
+ * Here we have had a fault on a load and r3 points to the first
+ * unmodified byte of the destination.  We use the original arguments
+ * and r3 to work out how much wasn't copied.  Since we load some
+ * distance ahead of the stores, we continue copying byte-by-byte until
+ * we hit the load fault again in order to copy as much as possible.
+ */
+.Lld_exc:
+	ld	r6,-24(r1)
+	ld	r4,-16(r1)
+	ld	r5,-8(r1)
+	subf	r6,r6,r3
+	add	r4,r4,r6
+	subf	r5,r6,r5	/* #bytes left to go */
+
+/*
+ * first see if we can copy any more bytes before hitting another exception
+ */
+	mtctr	r5
+r3_offset = 0
+100:	EX_TABLE(100b, .Ldone)
+43:	lbz	r0,0(r4)
+	addi	r4,r4,1
+stex;	stb	r0,0(r3)
+	addi	r3,r3,1
+	bdnz	43b
+	li	r3,0		/* huh? all copied successfully this time? */
+	blr
+
+/*
+ * here we have trapped again, amount remaining is in ctr.
+ */
+.Ldone:
+	mfctr	r3
+	blr
+
+/*
+ * exception handlers for stores: we need to work out how many bytes
+ * weren't copied, and we may need to copy some more.
+ * Note that the number of bytes of instructions for adjusting r3 needs
+ * to equal the amount of the adjustment, due to the trick of using
+ * .Lst_exc - r3_offset as the handler address.
+ */
+.Lst_exc_r7:
+	add	r3,r3,r7
+	b	.Lst_exc
+
+	/* adjust by 24 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 16 */
+	addi	r3,r3,8
+	nop
+	/* adjust by 8 */
+	addi	r3,r3,4
+	/* adjust by 4 */
+	addi	r3,r3,4
+.Lst_exc:
+	ld	r6,-24(r1)	/* original destination pointer */
+	ld	r4,-16(r1)	/* original source pointer */
+	ld	r5,-8(r1)	/* original number of bytes */
+	add	r7,r6,r5
+	/*
+	 * If the destination pointer isn't 8-byte aligned,
+	 * we may have got the exception as a result of a
+	 * store that overlapped a page boundary, so we may be
+	 * able to copy a few more bytes.
+	 */
+17:	andi.	r0,r3,7
+	beq	19f
+	subf	r8,r6,r3	/* #bytes copied */
+100:	EX_TABLE(100b,19f)
+	lbzx	r0,r8,r4
+100:	EX_TABLE(100b,19f)
+	stb	r0,0(r3)
+	addi	r3,r3,1
+	cmpld	r3,r7
+	blt	17b
+19:	subf	r3,r3,r7	/* #bytes not copied in r3 */
+	blr
+
+/*
+ * Routine to copy a whole page of data, optimized for POWER4.
+ * On POWER4 it is more than 50% faster than the simple loop
+ * above (following the .Ldst_aligned label).
+ */
+	.macro	exc
+100:	EX_TABLE(100b, .Labort)
+	.endm
+.Lcopy_page_4K:
+	std	r31,-32(1)
+	std	r30,-40(1)
+	std	r29,-48(1)
+	std	r28,-56(1)
+	std	r27,-64(1)
+	std	r26,-72(1)
+	std	r25,-80(1)
+	std	r24,-88(1)
+	std	r23,-96(1)
+	std	r22,-104(1)
+	std	r21,-112(1)
+	std	r20,-120(1)
+	li	r5,4096/32 - 1
+	addi	r3,r3,-8
+	li	r0,5
+0:	addi	r5,r5,-24
+	mtctr	r0
+exc;	ld	r22,640(4)
+exc;	ld	r21,512(4)
+exc;	ld	r20,384(4)
+exc;	ld	r11,256(4)
+exc;	ld	r9,128(4)
+exc;	ld	r7,0(4)
+exc;	ld	r25,648(4)
+exc;	ld	r24,520(4)
+exc;	ld	r23,392(4)
+exc;	ld	r10,264(4)
+exc;	ld	r8,136(4)
+exc;	ldu	r6,8(4)
+	cmpwi	r5,24
+1:
+exc;	std	r22,648(3)
+exc;	std	r21,520(3)
+exc;	std	r20,392(3)
+exc;	std	r11,264(3)
+exc;	std	r9,136(3)
+exc;	std	r7,8(3)
+exc;	ld	r28,648(4)
+exc;	ld	r27,520(4)
+exc;	ld	r26,392(4)
+exc;	ld	r31,264(4)
+exc;	ld	r30,136(4)
+exc;	ld	r29,8(4)
+exc;	std	r25,656(3)
+exc;	std	r24,528(3)
+exc;	std	r23,400(3)
+exc;	std	r10,272(3)
+exc;	std	r8,144(3)
+exc;	std	r6,16(3)
+exc;	ld	r22,656(4)
+exc;	ld	r21,528(4)
+exc;	ld	r20,400(4)
+exc;	ld	r11,272(4)
+exc;	ld	r9,144(4)
+exc;	ld	r7,16(4)
+exc;	std	r28,664(3)
+exc;	std	r27,536(3)
+exc;	std	r26,408(3)
+exc;	std	r31,280(3)
+exc;	std	r30,152(3)
+exc;	stdu	r29,24(3)
+exc;	ld	r25,664(4)
+exc;	ld	r24,536(4)
+exc;	ld	r23,408(4)
+exc;	ld	r10,280(4)
+exc;	ld	r8,152(4)
+exc;	ldu	r6,24(4)
+	bdnz	1b
+exc;	std	r22,648(3)
+exc;	std	r21,520(3)
+exc;	std	r20,392(3)
+exc;	std	r11,264(3)
+exc;	std	r9,136(3)
+exc;	std	r7,8(3)
+	addi	r4,r4,640
+	addi	r3,r3,648
+	bge	0b
+	mtctr	r5
+exc;	ld	r7,0(4)
+exc;	ld	r8,8(4)
+exc;	ldu	r9,16(4)
+3:
+exc;	ld	r10,8(4)
+exc;	std	r7,8(3)
+exc;	ld	r7,16(4)
+exc;	std	r8,16(3)
+exc;	ld	r8,24(4)
+exc;	std	r9,24(3)
+exc;	ldu	r9,32(4)
+exc;	stdu	r10,32(3)
+	bdnz	3b
+4:
+exc;	ld	r10,8(4)
+exc;	std	r7,8(3)
+exc;	std	r8,16(3)
+exc;	std	r9,24(3)
+exc;	std	r10,32(3)
+9:	ld	r20,-120(1)
+	ld	r21,-112(1)
+	ld	r22,-104(1)
+	ld	r23,-96(1)
+	ld	r24,-88(1)
+	ld	r25,-80(1)
+	ld	r26,-72(1)
+	ld	r27,-64(1)
+	ld	r28,-56(1)
+	ld	r29,-48(1)
+	ld	r30,-40(1)
+	ld	r31,-32(1)
+	li	r3,0
+	blr
+
+/*
+ * on an exception, reset to the beginning and jump back into the
+ * standard __copy_tofrom_user
+ */
+.Labort:
+	ld	r20,-120(1)
+	ld	r21,-112(1)
+	ld	r22,-104(1)
+	ld	r23,-96(1)
+	ld	r24,-88(1)
+	ld	r25,-80(1)
+	ld	r26,-72(1)
+	ld	r27,-64(1)
+	ld	r28,-56(1)
+	ld	r29,-48(1)
+	ld	r30,-40(1)
+	ld	r31,-32(1)
+	ld	r3,-24(r1)
+	ld	r4,-16(r1)
+	li	r5,4096
+	b	.Ldst_aligned
+EXPORT_SYMBOL(__copy_tofrom_user)