[PATCH v2] RISC-V: setjmp: reduce code size for register load/store with Zilsd

[puranikvinit]

This patch optimizes the RISC-V setjmp implementation in
newlib/libc/machine/riscv/setjmp.S for 32-bit targets. It reduces code
size by using doubleword store/load instructions (sd/ld) when the Zilsd
or Zclsd extensions are available for saving and
restoring s0-s11 registers, while preserving the original
single-word instructions (REG_S/REG_L) for compatibility with other
configurations.

Signed-off-by: puranikvinit <kvp933.vinit@gmail.com>
Reviewed-by: Christian Herber <christian.herber@oss.nxp.com>

RISC-V: setjmp: reduce code size for register load/store with Zilsd
---
 newlib/libc/machine/riscv/setjmp.S | 74 ++++++++++++++++++++----------
 1 file changed, 49 insertions(+), 25 deletions(-)

diff --git a/newlib/libc/machine/riscv/setjmp.S b/newlib/libc/machine/riscv/setjmp.S
index 2d4ab6cfc..f2b50537e 100644
--- a/newlib/libc/machine/riscv/setjmp.S
+++ b/newlib/libc/machine/riscv/setjmp.S
@@ -16,21 +16,33 @@
   .type   setjmp, @function
 setjmp:
 	REG_S ra,  0*SZREG(a0)
-	REG_S s0,  1*SZREG(a0)
-	REG_S s1,  2*SZREG(a0)
+  #if __riscv_xlen == 32 && (__riscv_zilsd) && (__riscv_misaligned_fast)
+	  sd    s0,  1*SZREG(a0)
+  #else
+	  REG_S s0,  1*SZREG(a0)
+	  REG_S s1,  2*SZREG(a0)
+  #endif
 
 #ifndef __riscv_abi_rve
-	REG_S s2,  3*SZREG(a0)
-	REG_S s3,  4*SZREG(a0)
-	REG_S s4,  5*SZREG(a0)
-	REG_S s5,  6*SZREG(a0)
-	REG_S s6,  7*SZREG(a0)
-	REG_S s7,  8*SZREG(a0)
-	REG_S s8,  9*SZREG(a0)
-	REG_S s9, 10*SZREG(a0)
-	REG_S s10,11*SZREG(a0)
-	REG_S s11,12*SZREG(a0)
-	REG_S sp, 13*SZREG(a0)
+  #if __riscv_xlen == 32 && (__riscv_zilsd) && (__riscv_misaligned_fast)
+	  sd    s2,  3*SZREG(a0)
+	  sd    s4,  5*SZREG(a0)
+	  sd    s6,  7*SZREG(a0)
+	  sd    s8,  9*SZREG(a0)
+	  sd    s10,11*SZREG(a0)
+  #else
+	  REG_S s2,  3*SZREG(a0)
+	  REG_S s3,  4*SZREG(a0)
+	  REG_S s4,  5*SZREG(a0)
+	  REG_S s5,  6*SZREG(a0)
+	  REG_S s6,  7*SZREG(a0)
+	  REG_S s7,  8*SZREG(a0)
+	  REG_S s8,  9*SZREG(a0)
+	  REG_S s9, 10*SZREG(a0)
+	  REG_S s10,11*SZREG(a0)
+	  REG_S s11,12*SZREG(a0)
+  #endif
+  REG_S sp, 13*SZREG(a0)
 #else
 	REG_S sp, 3*SZREG(a0)
 #endif
@@ -59,19 +71,31 @@ setjmp:
   .type   longjmp, @function
 longjmp:
 	REG_L ra,  0*SZREG(a0)
-	REG_L s0,  1*SZREG(a0)
-	REG_L s1,  2*SZREG(a0)
+  #if __riscv_xlen == 32 && (__riscv_zilsd) && (__riscv_misaligned_fast)
+    ld s0, 1*SZREG(a0)
+  #else
+    REG_L s0,  1*SZREG(a0)
+    REG_L s1,  2*SZREG(a0)
+  #endif
 #ifndef __riscv_abi_rve
-	REG_L s2,  3*SZREG(a0)
-	REG_L s3,  4*SZREG(a0)
-	REG_L s4,  5*SZREG(a0)
-	REG_L s5,  6*SZREG(a0)
-	REG_L s6,  7*SZREG(a0)
-	REG_L s7,  8*SZREG(a0)
-	REG_L s8,  9*SZREG(a0)
-	REG_L s9, 10*SZREG(a0)
-	REG_L s10,11*SZREG(a0)
-	REG_L s11,12*SZREG(a0)
+  #if __riscv_xlen == 32 && (__riscv_zilsd) && (__riscv_misaligned_fast)
+	  ld    s2,  3*SZREG(a0)
+	  ld    s4,  5*SZREG(a0)
+	  ld    s6,  7*SZREG(a0)
+	  ld    s8,  9*SZREG(a0)
+	  ld    s10,11*SZREG(a0)
+  #else
+	  REG_L s2,  3*SZREG(a0)
+	  REG_L s3,  4*SZREG(a0)
+	  REG_L s4,  5*SZREG(a0)
+	  REG_L s5,  6*SZREG(a0)
+	  REG_L s6,  7*SZREG(a0)
+	  REG_L s7,  8*SZREG(a0)
+	  REG_L s8,  9*SZREG(a0)
+	  REG_L s9, 10*SZREG(a0)
+	  REG_L s10,11*SZREG(a0)
+	  REG_L s11,12*SZREG(a0)
+  #endif
 	REG_L sp, 13*SZREG(a0)
 #else
 	REG_L sp, 3*SZREG(a0)
-- 
2.49.0