[PATCH 3/3] RISC-V: Add memset-zero expansion to cbo.zero

The Zicboz extension offers the cbo.zero instruction, which can be used
to clean a memory region corresponding to a cache block.
The Zic64b extension defines the cache block size to 64 byte.
If both extensions are available, it is possible to use cbo.zero
to clear memory, if the alignment and size constraints are met.
This patch implements this.

gcc/ChangeLog:

	* config/riscv/riscv-protos.h (riscv_expand_block_clear): New prototype.
	* config/riscv/riscv-string.cc (riscv_expand_block_clear_zicboz_zic64b):
	New function to expand a block-clear with cbo.zero.
	(riscv_expand_block_clear): New RISC-V block-clear expansion function.
	* config/riscv/riscv.md (setmem<mode>): New setmem expansion.

3 files changed, 84 insertions, 0 deletions

diff --git a/gcc/config/riscv/riscv-protos.h b/gcc/config/riscv/riscv-protos.h
index e5aebf3..255fd6a 100644
--- a/gcc/config/riscv/riscv-protos.h
+++ b/gcc/config/riscv/riscv-protos.h
@@ -189,6 +189,7 @@ rtl_opt_pass * make_pass_vsetvl (gcc::context *ctxt);
 
 /* Routines implemented in riscv-string.c.  */
 extern bool riscv_expand_block_move (rtx, rtx, rtx);
+extern bool riscv_expand_block_clear (rtx, rtx);
 
 /* Information about one CPU we know about.  */
 struct riscv_cpu_info {
diff --git a/gcc/config/riscv/riscv-string.cc b/gcc/config/riscv/riscv-string.cc
index 41cb061..87f5fde 100644
--- a/gcc/config/riscv/riscv-string.cc
+++ b/gcc/config/riscv/riscv-string.cc
@@ -794,6 +794,65 @@ riscv_expand_block_move (rtx dest, rtx src, rtx length)
   return false;
 }
 
+/* Expand a block-clear instruction via cbo.zero instructions.  */
+
+static bool
+riscv_expand_block_clear_zicboz_zic64b (rtx dest, rtx length)
+{
+  unsigned HOST_WIDE_INT hwi_length;
+  unsigned HOST_WIDE_INT align;
+  const unsigned HOST_WIDE_INT cbo_bytes = 64;
+
+  gcc_assert (TARGET_ZICBOZ && TARGET_ZIC64B);
+
+  if (!CONST_INT_P (length))
+    return false;
+
+  hwi_length = UINTVAL (length);
+  if (hwi_length < cbo_bytes)
+    return false;
+
+  align = MEM_ALIGN (dest) / BITS_PER_UNIT;
+  if (align < cbo_bytes)
+    return false;
+
+  /* We don't emit loops.  Instead apply move-bytes limitation.  */
+  unsigned HOST_WIDE_INT max_bytes = RISCV_MAX_MOVE_BYTES_STRAIGHT /
+	  UNITS_PER_WORD * cbo_bytes;
+  if (hwi_length > max_bytes)
+    return false;
+
+  unsigned HOST_WIDE_INT offset = 0;
+  while (offset + cbo_bytes <= hwi_length)
+    {
+      rtx mem = adjust_address (dest, BLKmode, offset);
+      rtx addr = force_reg (Pmode, XEXP (mem, 0));
+      emit_insn (gen_riscv_zero_di (addr));
+      offset += cbo_bytes;
+    }
+
+  if (offset < hwi_length)
+    {
+      rtx mem = adjust_address (dest, BLKmode, offset);
+      clear_by_pieces (mem, hwi_length - offset, align);
+    }
+
+  return true;
+}
+
+bool
+riscv_expand_block_clear (rtx dest, rtx length)
+{
+  /* Only use setmem-zero expansion for Zicboz + Zic64b.  */
+  if (!TARGET_ZICBOZ || !TARGET_ZIC64B)
+    return false;
+
+  if (optimize_function_for_size_p (cfun))
+    return false;
+
+  return riscv_expand_block_clear_zicboz_zic64b (dest, length);
+}
+
 /* --- Vector expanders --- */
 
 namespace riscv_vector {
diff --git a/gcc/config/riscv/riscv.md b/gcc/config/riscv/riscv.md
index 4d6de99..c45b112 100644
--- a/gcc/config/riscv/riscv.md
+++ b/gcc/config/riscv/riscv.md
@@ -2608,6 +2608,30 @@
     FAIL;
 })
 
+;; Fill memory with constant byte.
+;; Argument 0 is the destination
+;; Argument 1 is the constant byte
+;; Argument 2 is the length
+;; Argument 3 is the alignment
+
+(define_expand "setmem<mode>"
+  [(parallel [(set (match_operand:BLK 0 "memory_operand")
+		   (match_operand:QI 2 "const_int_operand"))
+	      (use (match_operand:P 1 ""))
+	      (use (match_operand:SI 3 "const_int_operand"))])]
+ ""
+ {
+  /* If value to set is not zero, use the library routine.  */
+  if (operands[2] != const0_rtx)
+    FAIL;
+
+  if (riscv_expand_block_clear (operands[0], operands[1]))
+    DONE;
+  else
+    FAIL;
+})
+
+
 ;; Expand in-line code to clear the instruction cache between operand[0] and
 ;; operand[1].
 (define_expand "clear_cache"