[amdgcn] Update CFI configuration

Currently we don't get any call frame information for the amdgcn target.
This patch makes necessary adjustments to generate CFI that can work with
ROCGDB (ROCm 3.8+).

gcc/

	* config/gcn/gcn.c (move_callee_saved_registers): Emit CFI notes for
	prologue register saves.
	(gcn_debug_unwind_info): Use UI_DWARF2.
	(gcn_dwarf_register_number): Map DWARF_LINK_REGISTER to DWARF PC.
	(gcn_dwarf_register_span): DWARF_LINK_REGISTER doesn't span.
	* config/gcn/gcn.h: (DWARF_FRAME_RETURN_COLUMN): New define.
	(DWARF_LINK_REGISTER): New define.
	(FIRST_PSEUDO_REGISTER): Increment.
	(FIXED_REGISTERS): Add entry for DWARF_LINK_REGISTER.
	(CALL_USED_REGISTERS): Likewise.
	(REGISTER_NAMES): Likewise.

diff --git a/gcc/config/gcn/gcn.c b/gcc/config/gcn/gcn.c
index aa9d455bb08b43914fe7b49d633a3816c50b64b9..ef4ed7c8454fcc2355d95f4880581f9ff8cf0e66 100644 (file)
--- a/gcc/config/gcn/gcn.c
+++ b/gcc/config/gcn/gcn.c
@@ -2649,6 +2649,7 @@ move_callee_saved_registers (rtx sp, machine_function *offsets,
   rtx as = gen_rtx_CONST_INT (VOIDmode, STACK_ADDR_SPACE);
   HOST_WIDE_INT exec_set = 0;
   int offreg_set = 0;
+  auto_vec<int> saved_sgprs;
 
   start_sequence ();
 
@@ -2665,7 +2666,10 @@ move_callee_saved_registers (rtx sp, machine_function *offsets,
        int lane = saved_scalars % 64;
 
        if (prologue)
-         emit_insn (gen_vec_setv64si (vreg, reg, GEN_INT (lane)));
+         {
+           emit_insn (gen_vec_setv64si (vreg, reg, GEN_INT (lane)));
+           saved_sgprs.safe_push (regno);
+         }
        else
          emit_insn (gen_vec_extractv64sisi (reg, vreg, GEN_INT (lane)));
 
@@ -2698,7 +2702,7 @@ move_callee_saved_registers (rtx sp, machine_function *offsets,
                                  gcn_gen_undef (V64SImode), exec));
 
   /* Move vectors.  */
-  for (regno = FIRST_VGPR_REG, offset = offsets->pretend_size;
+  for (regno = FIRST_VGPR_REG, offset = 0;
        regno < FIRST_PSEUDO_REGISTER; regno++)
     if ((df_regs_ever_live_p (regno) && !call_used_or_fixed_reg_p (regno))
        || (regno == VGPR_REGNO (6) && saved_scalars > 0)
@@ -2719,8 +2723,67 @@ move_callee_saved_registers (rtx sp, machine_function *offsets,
          }
 
        if (prologue)
-         emit_insn (gen_scatterv64si_insn_1offset_exec (vsp, const0_rtx, reg,
-                                                        as, const0_rtx, exec));
+         {
+           rtx insn = emit_insn (gen_scatterv64si_insn_1offset_exec
+                                 (vsp, const0_rtx, reg, as, const0_rtx,
+                                  exec));
+
+           /* Add CFI metadata.  */
+           rtx note;
+           if (regno == VGPR_REGNO (6) || regno == VGPR_REGNO (7))
+             {
+               int start = (regno == VGPR_REGNO (7) ? 64 : 0);
+               int count = MIN (saved_scalars - start, 64);
+               int add_lr = (regno == VGPR_REGNO (6)
+                             && df_regs_ever_live_p (LINK_REGNUM));
+               int lrdest = -1;
+               rtvec seq = rtvec_alloc (count + add_lr);
+
+               /* Add an REG_FRAME_RELATED_EXPR entry for each scalar
+                  register that was saved in this batch.  */
+               for (int idx = 0; idx < count; idx++)
+                 {
+                   int stackaddr = offset + idx * 4;
+                   rtx dest = gen_rtx_MEM (SImode,
+                                           gen_rtx_PLUS
+                                           (DImode, sp,
+                                            GEN_INT (stackaddr)));
+                   rtx src = gen_rtx_REG (SImode, saved_sgprs[start + idx]);
+                   rtx set = gen_rtx_SET (dest, src);
+                   RTX_FRAME_RELATED_P (set) = 1;
+                   RTVEC_ELT (seq, idx) = set;
+
+                   if (saved_sgprs[start + idx] == LINK_REGNUM)
+                     lrdest = stackaddr;
+                 }
+
+               /* Add an additional expression for DWARF_LINK_REGISTER if
+                  LINK_REGNUM was saved.  */
+               if (lrdest != -1)
+                 {
+                   rtx dest = gen_rtx_MEM (DImode,
+                                           gen_rtx_PLUS
+                                           (DImode, sp,
+                                            GEN_INT (lrdest)));
+                   rtx src = gen_rtx_REG (DImode, DWARF_LINK_REGISTER);
+                   rtx set = gen_rtx_SET (dest, src);
+                   RTX_FRAME_RELATED_P (set) = 1;
+                   RTVEC_ELT (seq, count) = set;
+                 }
+
+               note = gen_rtx_SEQUENCE (VOIDmode, seq);
+             }
+           else
+             {
+               rtx dest = gen_rtx_MEM (V64SImode,
+                                       gen_rtx_PLUS (DImode, sp,
+                                                     GEN_INT (offset)));
+               rtx src = gen_rtx_REG (V64SImode, regno);
+               note = gen_rtx_SET (dest, src);
+             }
+           RTX_FRAME_RELATED_P (insn) = 1;
+           add_reg_note (insn, REG_FRAME_RELATED_EXPR, note);
+         }
        else
          emit_insn (gen_gatherv64si_insn_1offset_exec
                     (reg, vsp, const0_rtx, as, const0_rtx,
@@ -3224,8 +3287,7 @@ gcn_cannot_copy_insn_p (rtx_insn *insn)
 static enum unwind_info_type
 gcn_debug_unwind_info ()
 {
-  /* No support for debug info, yet.  */
-  return UI_NONE;
+  return UI_DWARF2;
 }
 
 /* Determine if there is a suitable hardware conversion instruction.
@@ -6251,6 +6313,8 @@ gcn_dwarf_register_number (unsigned int regno)
     return 768;  */
   else if (regno == SCC_REG)
     return 128;
+  else if (regno == DWARF_LINK_REGISTER)
+    return 16;
   else if (SGPR_REGNO_P (regno))
     {
       if (regno - FIRST_SGPR_REG < 64)
@@ -6280,8 +6344,12 @@ gcn_dwarf_register_span (rtx rtl)
   if (GET_MODE_SIZE (mode) != 8)
     return NULL_RTX;
 
-  rtx p = gen_rtx_PARALLEL (VOIDmode, rtvec_alloc (2));
   unsigned regno = REGNO (rtl);
+
+  if (regno == DWARF_LINK_REGISTER)
+    return NULL_RTX;
+
+  rtx p = gen_rtx_PARALLEL (VOIDmode, rtvec_alloc (2));
   XVECEXP (p, 0, 0) = gen_rtx_REG (SImode, regno);
   XVECEXP (p, 0, 1) = gen_rtx_REG (SImode, regno + 1);
 

diff --git a/gcc/config/gcn/gcn.h b/gcc/config/gcn/gcn.h
index 540835b81cc0dd1aa4f2d498142543e845879123..5822ec34aa7bcf32b4593602a8c6d4cb1129c973 100644 (file)
--- a/gcc/config/gcn/gcn.h
+++ b/gcc/config/gcn/gcn.h
@@ -88,6 +88,7 @@
 #define FIRST_PARM_OFFSET(FNDECL)    0
 #define DYNAMIC_CHAIN_ADDRESS(FP)    plus_constant (Pmode, (FP), -16)
 #define INCOMING_RETURN_ADDR_RTX     gen_rtx_REG (Pmode, LINK_REGNUM)
+#define DWARF_FRAME_RETURN_COLUMN    16
 #define STACK_DYNAMIC_OFFSET(FNDECL) (-crtl->outgoing_args_size)
 #define ACCUMULATE_OUTGOING_ARGS     1
 #define RETURN_ADDR_RTX(COUNT,FRAMEADDR) \
@@ -138,7 +139,8 @@
 #define WORK_ITEM_ID_Z_REG       162
 #define SOFT_ARG_REG             416
 #define FRAME_POINTER_REGNUM     418
-#define FIRST_PSEUDO_REGISTER    420
+#define DWARF_LINK_REGISTER      420
+#define FIRST_PSEUDO_REGISTER    421
 
 #define FIRST_PARM_REG 24
 #define NUM_PARM_REGS  6
@@ -200,7 +202,7 @@
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, \
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, \
     /* Other registers.  */                        \
-    1, 1, 1, 1                                     \
+    1, 1, 1, 1, 1                                  \
 }
 
 #define CALL_USED_REGISTERS {                      \
@@ -238,7 +240,7 @@
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, \
     0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, \
     /* Other registers.  */                        \
-    1, 1, 1, 1                                     \
+    1, 1, 1, 1, 1                                  \
 }
 
 \f
@@ -517,7 +519,7 @@ enum gcn_address_spaces
     "v236", "v237", "v238", "v239", "v240", "v241", "v242", "v243", "v244", \
     "v245", "v246", "v247", "v248", "v249", "v250", "v251", "v252", "v253", \
     "v254", "v255",                                                        \
-    "?ap0", "?ap1", "?fp0", "?fp1" }
+    "?ap0", "?ap1", "?fp0", "?fp1", "?dwlr" }
 
 #define PRINT_OPERAND(FILE, X, CODE)  print_operand(FILE, X, CODE)
 #define PRINT_OPERAND_ADDRESS(FILE, ADDR)  print_operand_address (FILE, ADDR)