li t6, SR_SUM
csrs CSR_STATUS, t6
- add a3, a1, a2
- /* Use word-oriented copy only if low-order bits match */
- andi t0, a0, SZREG-1
- andi t1, a1, SZREG-1
- bne t0, t1, 2f
+ /* Save for return value */
+ mv t5, a2
- addi t0, a1, SZREG-1
- andi t1, a3, ~(SZREG-1)
- andi t0, t0, ~(SZREG-1)
/*
- * a3: terminal address of source region
- * t0: lowest XLEN-aligned address in source
- * t1: highest XLEN-aligned address in source
+ * Register allocation for code below:
+ * a0 - start of uncopied dst
+ * a1 - start of uncopied src
+ * a2 - size
+ * t0 - end of uncopied dst
*/
- bgeu t0, t1, 2f
- bltu a1, t0, 4f
+ add t0, a0, a2
+
+ /*
+ * Use byte copy only if too small.
+ * SZREG holds 4 for RV32 and 8 for RV64
+ */
+ li a3, 9*SZREG /* size must be larger than size in word_copy */
+ bltu a2, a3, .Lbyte_copy_tail
+
+ /*
+ * Copy first bytes until dst is aligned to word boundary.
+ * a0 - start of dst
+ * t1 - start of aligned dst
+ */
+ addi t1, a0, SZREG-1
+ andi t1, t1, ~(SZREG-1)
+ /* dst is already aligned, skip */
+ beq a0, t1, .Lskip_align_dst
1:
- fixup REG_L, t2, (a1), 10f
- fixup REG_S, t2, (a0), 10f
- addi a1, a1, SZREG
- addi a0, a0, SZREG
- bltu a1, t1, 1b
+ /* 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 */
+
+.Lskip_align_dst:
+ /*
+ * 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
+ */
+ addi t0, t0, -(8*SZREG) /* not to over run */
2:
- bltu a1, a3, 5f
+ 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
+
+ addi t0, t0, 8*SZREG /* revert to original value */
+ 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.
+ * This is safe because reading is less than a word size.
+ *
+ * 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)
+ /* Converting unaligned src to aligned src */
+ andi a1, a1, ~(SZREG-1)
+
+ /*
+ * Calculate shifts
+ * t3 - prev shift
+ * t4 - current shift
+ */
+ slli t3, a3, 3 /* converting bytes in a3 to bits */
+ li a5, SZREG*8
+ sub t4, a5, t3
+
+ /* Load the first word to combine with second word */
+ fixup REG_L a5, 0(a1), 10f
3:
+ /* 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
+ */
+ bgeu a0, t0, .Lout_copy_user /* check if end of copy */
+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 */
+
+.Lout_copy_user:
/* Disable access to user memory */
csrc CSR_STATUS, t6
- li a0, 0
+ li a0, 0
ret
-4: /* Edge case: unalignment */
- fixup lbu, t2, (a1), 10f
- fixup sb, t2, (a0), 10f
- addi a1, a1, 1
- addi a0, a0, 1
- bltu a1, t0, 4b
- j 1b
-5: /* Edge case: remainder */
- fixup lbu, t2, (a1), 10f
- fixup sb, t2, (a0), 10f
- addi a1, a1, 1
- addi a0, a0, 1
- bltu a1, a3, 5b
- j 3b
ENDPROC(__asm_copy_to_user)
ENDPROC(__asm_copy_from_user)
EXPORT_SYMBOL(__asm_copy_to_user)
10:
/* Disable access to user memory */
csrs CSR_STATUS, t6
- mv a0, a2
+ mv a0, t5
ret
11:
csrs CSR_STATUS, t6
projects / linux-2.6-microblaze.git / blobdiff