[PATCH 13/17] riscv: add vectorized strcspn

The vector implementation builds a 256-byte stop table on the stack (the
reject bytes plus NUL) and scans the string in vector-length chunks using
fault-only-first loads (vle8ff.v) with an indexed gather into the table,
so the scan never crosses into an unmapped page and the gather only
touches the fully-mapped table.  This provides significant performance
improvements on RVV-capable hardware.  Use conditional compilation to fall
back to the generic implementation when __riscv_vector is not available,
maintaining compatibility with non-vector RISC-V systems.

Signed-off-by: Pincheng Wang <[email protected]>
---
 newlib/libc/machine/riscv/Makefile.inc  |  2 +
 newlib/libc/machine/riscv/strcspn-asm.S | 55 +++++++++++++++++++++++++
 newlib/libc/machine/riscv/strcspn.c     |  5 +++
 3 files changed, 62 insertions(+)
 create mode 100644 newlib/libc/machine/riscv/strcspn-asm.S
 create mode 100644 newlib/libc/machine/riscv/strcspn.c

diff --git a/newlib/libc/machine/riscv/Makefile.inc b/newlib/libc/machine/riscv/Makefile.inc
index 55f137a3c..1e35cf17d 100644
--- a/newlib/libc/machine/riscv/Makefile.inc
+++ b/newlib/libc/machine/riscv/Makefile.inc
@@ -30,6 +30,8 @@ libc_a_SOURCES += \
 	%D%/strcmp.S \
 	%D%/strcpy-asm.S \
 	%D%/strcpy.c \
+	%D%/strcspn-asm.S \
+	%D%/strcspn.c \
 	%D%/strlen-asm.S \
 	%D%/strlen.c \
 	%D%/strncat-asm.S \
diff --git a/newlib/libc/machine/riscv/strcspn-asm.S b/newlib/libc/machine/riscv/strcspn-asm.S
new file mode 100644
index 000000000..713632444
--- /dev/null
+++ b/newlib/libc/machine/riscv/strcspn-asm.S
@@ -0,0 +1,55 @@
+#if defined(__riscv_vector) && __riscv_xlen == 64 && !defined(__OPTIMIZE_SIZE__) && !defined(PREFER_SIZE_OVER_SPEED)
+.text
+.option push
+.option arch, +v
+/* size_t strcspn(const char *a0, const char *a1)
+   Length of the initial segment of a0 made up of bytes NOT in a1.
+   Build a 256-byte "stop" table on the stack (a1's bytes plus NUL marked),
+   then scan a0: a gathered table entry != 0 ends the segment.  The scan of
+   a0 uses vle8ff so it never loads across a page boundary; the indexed
+   gather only touches the fully-mapped 256-byte table.  */
+.global strcspn
+.type strcspn, @function
+strcspn:
+  addi sp, sp, -256
+  /* zero the table */
+  li t1, 256
+  mv t0, sp
+.Lzero:
+  vsetvli t2, t1, e8, m8, ta, ma
+  vmv.v.i v8, 0
+  vse8.v v8, (t0)
+  add t0, t0, t2
+  sub t1, t1, t2
+  bnez t1, .Lzero
+  /* mark NUL as a stopper so the scan halts at end of string */
+  li t1, 1
+  sb t1, 0(sp)
+  /* mark every byte of a1 */
+.Lbuild:
+  lbu t0, 0(a1)
+  beqz t0, .Lscan
+  add t2, sp, t0
+  sb t1, 0(t2)
+  addi a1, a1, 1
+  j .Lbuild
+.Lscan:
+  mv a2, a0             /* remember start */
+.Lloop:
+  vsetvli t3, zero, e8, m1, ta, ma
+  vle8ff.v v8, (a0)
+  csrr t3, vl
+  vluxei8.v v16, (sp), v8       /* gather table[a0[i]] */
+  vmsne.vi v0, v16, 0           /* lanes that are stoppers */
+  vfirst.m t4, v0
+  bgez t4, .Lfound
+  add a0, a0, t3
+  j .Lloop
+.Lfound:
+  add a0, a0, t4
+  sub a0, a0, a2
+  addi sp, sp, 256
+  ret
+.size strcspn, .-strcspn
+.option pop
+#endif
diff --git a/newlib/libc/machine/riscv/strcspn.c b/newlib/libc/machine/riscv/strcspn.c
new file mode 100644
index 000000000..3d3558e5e
--- /dev/null
+++ b/newlib/libc/machine/riscv/strcspn.c
@@ -0,0 +1,5 @@
+#if defined(__OPTIMIZE_SIZE__) || defined(PREFER_SIZE_OVER_SPEED) || !defined(__riscv_vector) || __riscv_xlen != 64
+# include "../../string/strcspn.c"
+#else
+/* strcspn defined in strcspn-asm.S */
+#endif
-- 
2.39.5