uaccess.S 5.1 KB
Newer Older
1
#include <linux/linkage.h>
2
#include <asm-generic/export.h>
3 4 5 6
#include <asm/asm.h>
#include <asm/csr.h>

	.macro fixup op reg addr lbl
7
100:
8 9
	\op \reg, \addr
	.section __ex_table,"a"
10 11
	.balign 4
	.long (100b - .), (\lbl - .)
12 13 14
	.previous
	.endm

15 16
ENTRY(__asm_copy_to_user)
ENTRY(__asm_copy_from_user)
17 18 19

	/* Enable access to user memory */
	li t6, SR_SUM
20
	csrs CSR_STATUS, t6
21

22 23
	/* Save for return value */
	mv	t5, a2
24 25

	/*
26 27 28 29 30
	 * Register allocation for code below:
	 * a0 - start of uncopied dst
	 * a1 - start of uncopied src
	 * a2 - size
	 * t0 - end of uncopied dst
31
	 */
32 33 34 35
	add	t0, a0, a2

	/*
	 * Use byte copy only if too small.
36
	 * SZREG holds 4 for RV32 and 8 for RV64
37
	 */
38
	li	a3, 9*SZREG /* size must be larger than size in word_copy */
39 40 41
	bltu	a2, a3, .Lbyte_copy_tail

	/*
42
	 * Copy first bytes until dst is aligned to word boundary.
43 44 45 46 47 48
	 * a0 - start of dst
	 * t1 - start of aligned dst
	 */
	addi	t1, a0, SZREG-1
	andi	t1, t1, ~(SZREG-1)
	/* dst is already aligned, skip */
49
	beq	a0, t1, .Lskip_align_dst
50
1:
51 52 53 54 55 56 57
	/* a5 - one byte for copying data */
	fixup lb      a5, 0(a1), 10f
	addi	a1, a1, 1	/* src */
	fixup sb      a5, 0(a0), 10f
	addi	a0, a0, 1	/* dst */
	bltu	a0, t1, 1b	/* t1 - start of aligned dst */

58
.Lskip_align_dst:
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
	/*
	 * Now dst is aligned.
	 * Use shift-copy if src is misaligned.
	 * Use word-copy if both src and dst are aligned because
	 * can not use shift-copy which do not require shifting
	 */
	/* a1 - start of src */
	andi	a3, a1, SZREG-1
	bnez	a3, .Lshift_copy

.Lword_copy:
        /*
	 * Both src and dst are aligned, unrolled word copy
	 *
	 * a0 - start of aligned dst
	 * a1 - start of aligned src
	 * t0 - end of aligned dst
	 */
77
	addi	t0, t0, -(8*SZREG) /* not to over run */
78
2:
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98
	fixup REG_L   a4,        0(a1), 10f
	fixup REG_L   a5,    SZREG(a1), 10f
	fixup REG_L   a6,  2*SZREG(a1), 10f
	fixup REG_L   a7,  3*SZREG(a1), 10f
	fixup REG_L   t1,  4*SZREG(a1), 10f
	fixup REG_L   t2,  5*SZREG(a1), 10f
	fixup REG_L   t3,  6*SZREG(a1), 10f
	fixup REG_L   t4,  7*SZREG(a1), 10f
	fixup REG_S   a4,        0(a0), 10f
	fixup REG_S   a5,    SZREG(a0), 10f
	fixup REG_S   a6,  2*SZREG(a0), 10f
	fixup REG_S   a7,  3*SZREG(a0), 10f
	fixup REG_S   t1,  4*SZREG(a0), 10f
	fixup REG_S   t2,  5*SZREG(a0), 10f
	fixup REG_S   t3,  6*SZREG(a0), 10f
	fixup REG_S   t4,  7*SZREG(a0), 10f
	addi	a0, a0, 8*SZREG
	addi	a1, a1, 8*SZREG
	bltu	a0, t0, 2b

99
	addi	t0, t0, 8*SZREG /* revert to original value */
100 101 102 103 104 105 106 107 108
	j	.Lbyte_copy_tail

.Lshift_copy:

	/*
	 * Word copy with shifting.
	 * For misaligned copy we still perform aligned word copy, but
	 * we need to use the value fetched from the previous iteration and
	 * do some shifts.
109
	 * This is safe because reading is less than a word size.
110 111 112 113 114 115 116 117 118
	 *
	 * a0 - start of aligned dst
	 * a1 - start of src
	 * a3 - a1 & mask:(SZREG-1)
	 * t0 - end of uncopied dst
	 * t1 - end of aligned dst
	 */
	/* calculating aligned word boundary for dst */
	andi	t1, t0, ~(SZREG-1)
119
	/* Converting unaligned src to aligned src */
120 121 122 123 124 125 126
	andi	a1, a1, ~(SZREG-1)

	/*
	 * Calculate shifts
	 * t3 - prev shift
	 * t4 - current shift
	 */
127
	slli	t3, a3, 3 /* converting bytes in a3 to bits */
128 129 130
	li	a5, SZREG*8
	sub	t4, a5, t3

131
	/* Load the first word to combine with second word */
132
	fixup REG_L   a5, 0(a1), 10f
133 134

3:
135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162
	/* Main shifting copy
	 *
	 * a0 - start of aligned dst
	 * a1 - start of aligned src
	 * t1 - end of aligned dst
	 */

	/* At least one iteration will be executed */
	srl	a4, a5, t3
	fixup REG_L   a5, SZREG(a1), 10f
	addi	a1, a1, SZREG
	sll	a2, a5, t4
	or	a2, a2, a4
	fixup REG_S   a2, 0(a0), 10f
	addi	a0, a0, SZREG
	bltu	a0, t1, 3b

	/* Revert src to original unaligned value  */
	add	a1, a1, a3

.Lbyte_copy_tail:
	/*
	 * Byte copy anything left.
	 *
	 * a0 - start of remaining dst
	 * a1 - start of remaining src
	 * t0 - end of remaining dst
	 */
163
	bgeu	a0, t0, .Lout_copy_user  /* check if end of copy */
164 165 166 167 168 169 170
4:
	fixup lb      a5, 0(a1), 10f
	addi	a1, a1, 1	/* src */
	fixup sb      a5, 0(a0), 10f
	addi	a0, a0, 1	/* dst */
	bltu	a0, t0, 4b	/* t0 - end of dst */

171
.Lout_copy_user:
172
	/* Disable access to user memory */
173
	csrc CSR_STATUS, t6
174
	li	a0, 0
175
	ret
176 177
ENDPROC(__asm_copy_to_user)
ENDPROC(__asm_copy_from_user)
178 179
EXPORT_SYMBOL(__asm_copy_to_user)
EXPORT_SYMBOL(__asm_copy_from_user)
180 181 182 183 184 185


ENTRY(__clear_user)

	/* Enable access to user memory */
	li t6, SR_SUM
186
	csrs CSR_STATUS, t6
187 188 189 190 191 192 193 194 195 196 197 198 199

	add a3, a0, a1
	addi t0, a0, SZREG-1
	andi t1, a3, ~(SZREG-1)
	andi t0, t0, ~(SZREG-1)
	/*
	 * a3: terminal address of target region
	 * t0: lowest doubleword-aligned address in target region
	 * t1: highest doubleword-aligned address in target region
	 */
	bgeu t0, t1, 2f
	bltu a0, t0, 4f
1:
200
	fixup REG_S, zero, (a0), 11f
201 202 203 204 205 206 207
	addi a0, a0, SZREG
	bltu a0, t1, 1b
2:
	bltu a0, a3, 5f

3:
	/* Disable access to user memory */
208
	csrc CSR_STATUS, t6
209 210 211
	li a0, 0
	ret
4: /* Edge case: unalignment */
212
	fixup sb, zero, (a0), 11f
213 214 215 216
	addi a0, a0, 1
	bltu a0, t0, 4b
	j 1b
5: /* Edge case: remainder */
217
	fixup sb, zero, (a0), 11f
218 219 220 221
	addi a0, a0, 1
	bltu a0, a3, 5b
	j 3b
ENDPROC(__clear_user)
222
EXPORT_SYMBOL(__clear_user)
223 224 225

	.section .fixup,"ax"
	.balign 4
226
	/* Fixup code for __copy_user(10) and __clear_user(11) */
227 228
10:
	/* Disable access to user memory */
229
	csrs CSR_STATUS, t6
230
	mv a0, t5
231 232
	ret
11:
233
	csrs CSR_STATUS, t6
234
	mv a0, a1
235 236
	ret
	.previous