Merge remote-tracking branch 'sourceryinstitute/master' into teams

Author: Damian Rouson

gcc/ChangeLog

@@ -1,3 +1,153 @@
+2017-09-20  Sebastian Peryt  <[email protected]>
+
+	* config.gcc: Support "knm".
+	* config/i386/driver-i386.c (host_detect_local_cpu): Detect "knm".
+	* config/i386/i386-c.c (ix86_target_macros_internal): Handle
+	PROCESSOR_KNM.
+	* config/i386/i386.c (m_KNM): Define.
+	(processor_target_table): Add "knm".
+	(PTA_KNM): Define.
+	(ix86_option_override_internal): Add "knm".
+	(ix86_issue_rate): Add PROCESSOR_KNM.
+	(ix86_adjust_cost): Ditto.
+	(ia32_multipass_dfa_lookahead): Ditto.
+	(get_builtin_code_for_version): Handle PROCESSOR_KNM.
+	(fold_builtin_cpu): Add M_INTEL_KNM.
+	* config/i386/i386.h (processor_costs): Define TARGET_KNM.
+	(processor_type): Add PROCESSOR_KNM.
+	* config/i386/x86-tune.def: Add m_KNM.
+	* doc/invoke.texi: Add knm as x86 -march=/-mtune= CPU type.
+
+2017-09-20  Richard Biener  <[email protected]>
+
+	PR tree-optimization/80213
+	* graphite-scop-detection.c (trivially_empty_bb_p): Labels
+	are allowed in empty BBs as well.
+	(canonicalize_loop_closed_ssa): Also look for other complex
+	edges.
+	(scop_detection::get_sese): Include the loop-closed PHI block
+	in loop SESEs.
+	(scop_detection::merge_sese): Remove code adding extra blocks.
+	(scop_detection::region_has_one_loop): Adjust for get_sese changes.
+	(build_scops): Assert the final returned scop is invalid.
+
+2017-09-20  Richard Biener  <[email protected]>
+
+	PR tree-optimization/82264
+	* tree-ssa-sccvn.c (vn_phi_eq): Use safe_dyn_cast to check
+	for GIMPLE_CONDs.
+	(vn_phi_lookup): Likewise.
+	(vn_phi_insert): Likewise.
+
+2017-09-20  Jakub Jelinek  <[email protected]>
+
+	* dwarf2out.c (tree_add_const_value_attribute): For INTEGER_CST
+	that fits into uhwi or shwi, add DW_AT_const_value regardless
+	of early_dwarf without going through RTL, using add_AT_unsigned
+	or add_AT_int.
+
+	* dwarf2out.c (DEBUG_LTO_DWO_INFO_SECTION): Reorder defines.
+	(DEBUG_LTO_ABBREV_SECTION): Likewise.
+	(DEBUG_LTO_MACINFO_SECTION): Likewise.
+	(DEBUG_MACRO_SECTION): Likewise.
+	(DEBUG_LTO_MACRO_SECTION): Likewise.
+	(DEBUG_STR_DWO_SECTION): Likewise.
+	(DEBUG_LTO_STR_DWO_SECTION): Likewise.
+	(DEBUG_LTO_LINE_SECTION): Drop .dwo suffix from the name.
+	(DEBUG_LTO_DWO_LINE_SECTION): Define.
+	(DEBUG_LTO_LINE_STR_SECTION): Define.
+	(init_sections_and_labels): Initialize debug_line_str_section
+	variable.  Initialize debug_loc_section for -gdwarf-5 to
+	DEBUG_LOCLISTS_SECTION.  Formatting fixes.
+
+2017-09-20  Richard Biener  <[email protected]>
+
+	* graphite-sese-to-poly.c (extract_affine): Properly handle
+	POINTER_PLUS_EXPR, BIT_NOT_EXPR and conversion to signed.
+
+2017-09-20  Richard Biener  <[email protected]>
+
+	PR tree-optimization/81373
+	* graphite-scop-detection.c (build_cross_bb_scalars_def):
+	Force SESE live-out defs to be handled even if they are
+	scev_analyzable_p.
+
+2017-09-19  Jeff Law  <[email protected]>
+
+	* combine-stack-adj.c (combine_stack_adjustments_for_block): Do
+	nothing for stack adjustments with REG_STACK_CHECK.
+	* sched-deps.c (parse_add_or_inc): Reject insns with
+	REG_STACK_CHECK from dependency breaking.
+	* config/i386/i386.c (pro_epilogue_adjust_stack): Return insn.
+	(ix86_adjust_satck_and_probe_stack_clash): Add REG_STACK_NOTEs.
+	* reg-notes.def (STACK_CHECK): New note.
+
+	* config/i386/i386.c (ix86_adjust_stack_and_probe_stack_clash): New.
+	(ix86_expand_prologue): Dump stack clash info as needed.
+	Call ix86_adjust_stack_and_probe_stack_clash as needed.
+
+        * function.c (dump_stack_clash_frame_info): New function.
+        * function.h (dump_stack_clash_frame_info): Prototype.
+        (enum stack_clash_probes): New enum.
+
+	* config/alpha/alpha.c (alpha_expand_prologue): Also check
+	flag_stack_clash_protection.
+	* config/arm/arm.c (arm_compute_static_chain_stack_bytes): Likewise.
+	(arm_expand_prologue, thumb1_expand_prologue): Likewise.
+	(arm_frame_pointer_required): Likewise.
+	* config/ia64/ia64.c (ia64_compute_frame_size): Likewise.
+	(ia64_expand_prologue): Likewise.
+	* config/mips/mips.c (mips_expand_prologue): Likewise.
+	* config/powerpcspe/powerpcspe.c (rs6000_expand_prologue): Likewise.
+	* config/sparc/sparc.c (sparc_expand_prologue): Likewise.
+	(sparc_flat_expand_prologue): Likewise.
+	* config/spu/spu.c (spu_expand_prologue): Likewise.
+
+	* explow.c: Include "params.h".
+	(anti_adjust_stack_and_probe_stack_clash): New function.
+	(get_stack_check_protect): Likewise.
+	(compute_stack_clash_protection_loop_data): Likewise.
+	(emit_stack_clash_protection_loop_start): Likewise.
+	(emit_stack_clash_protection_loop_end): Likewise.
+	(allocate_dynamic_stack_space): Use get_stack_check_protect.
+	Use anti_adjust_stack_and_probe_stack_clash.
+	* explow.h (compute_stack_clash_protection_loop_data): Prototype.
+	(emit_stack_clash_protection_loop_start): Likewise.
+	(emit_stack_clash_protection_loop_end): Likewise.
+	* rtl.h (get_stack_check_protect): Prototype.
+	* target.def (stack_clash_protection_final_dynamic_probe): New hook.
+	* targhooks.c (default_stack_clash_protection_final_dynamic_probe): New.
+	* targhooks.h (default_stack_clash_protection_final_dynamic_probe):
+	Prototype.
+	* doc/tm.texi.in (TARGET_STACK_CLASH_PROTECTION_FINAL_DYNAMIC_PROBE):
+	Add @hook.
+	* doc/tm.texi: Rebuilt.
+	* config/aarch64/aarch64.c (aarch64_expand_prologue): Use
+	get_stack_check_protect.
+	* config/alpha/alpha.c (alpha_expand_prologue): Likewise.
+	* config/arm/arm.c (arm_expand_prologue): Likewise.
+	(arm_frame_pointer_required): Likewise.
+	* config/i386/i386.c (ix86_expand_prologue): Likewise.
+	* config/ia64/ia64.c (ia64_expand_prologue): Likewise.
+	* config/mips/mips.c (mips_expand_prologue): Likewise.
+	* config/powerpcspe/powerpcspe.c (rs6000_emit_prologue): Likewise.
+	* config/rs6000/rs6000.c (rs6000_emit_prologue): Likewise.
+	* config/sparc/sparc.c (sparc_expand_prologue): Likewise.
+	(sparc_flat_expand_prologue): Likewise.
+
+	* common.opt (-fstack-clash-protection): New option.
+	* flag-types.h (enum stack_check_type): Note difference between
+	-fstack-check= and -fstack-clash-protection.
+	* params.def (PARAM_STACK_CLASH_PROTECTION_GUARD_SIZE): New PARAM.
+	(PARAM_STACK_CLASH_PROTECTION_PROBE_INTERVAL): Likewise.
+	* toplev.c (process_options): Issue warnings/errors for cases
+	not handled with -fstack-clash-protection.
+	* doc/invoke.texi (-fstack-clash-protection): Document new option.
+	(-fstack-check): Note additional problem with -fstack-check=generic.
+	Note that -fstack-check is primarily for Ada and refer users
+	to -fstack-clash-protection for stack-clash-protection.
+	Document new params for stack clash protection.
+
 2017-09-19  Uros Bizjak  <[email protected]>
 
 	* config/i386/i386.c (ix86_split_long_move): Do not handle
@@ -182,8 +332,8 @@
 
 2017-09-17  Daniel Santos  <[email protected]>
 
-	config/i386/i386.c: (xlogue_layout::STUB_NAME_MAX_LEN): Increase to 20
-	bytes.
+	* config/i386/i386.c (xlogue_layout::STUB_NAME_MAX_LEN):
+	Increase to 20 bytes.
 	(xlogue_layout::s_stub_names): Add an additional size-2 diminsion.
 	(xlogue_layout::get_stub_name): Modify to select the appropairate sse
 	or avx version of the stub.

gcc/DATESTAMP

@@ -1 +1 @@
-20170919
+20170920

gcc/combine-stack-adj.c

@@ -508,6 +508,8 @@ combine_stack_adjustments_for_block (basic_block bb)
 	continue;
 
       set = single_set_for_csa (insn);
+      if (set && find_reg_note (insn, REG_STACK_CHECK, NULL_RTX))
+	set = NULL_RTX;
       if (set)
 	{
 	  rtx dest = SET_DEST (set);

gcc/common.opt

@@ -2320,13 +2320,18 @@ Common Report Var(flag_variable_expansion_in_unroller) Optimization
 Apply variable expansion when loops are unrolled.
 
 fstack-check=
-Common Report RejectNegative Joined
+Common Report RejectNegative Joined Optimization
 -fstack-check=[no|generic|specific]	Insert stack checking code into the program.
 
 fstack-check
 Common Alias(fstack-check=, specific, no)
 Insert stack checking code into the program.  Same as -fstack-check=specific.
 
+fstack-clash-protection
+Common Report Var(flag_stack_clash_protection) Optimization
+Insert code to probe each page of stack space as it is allocated to protect
+from stack-clash style attacks.
+
 fstack-limit
 Common Var(common_deferred_options) Defer
 

gcc/config.gcc

@@ -623,7 +623,7 @@ pentium4 pentium4m pentiumpro prescott lakemont"
 x86_64_archs="amdfam10 athlon64 athlon64-sse3 barcelona bdver1 bdver2 \
 bdver3 bdver4 znver1 btver1 btver2 k8 k8-sse3 opteron opteron-sse3 nocona \
 core2 corei7 corei7-avx core-avx-i core-avx2 atom slm nehalem westmere \
-sandybridge ivybridge haswell broadwell bonnell silvermont knl \
+sandybridge ivybridge haswell broadwell bonnell silvermont knl knm \
 skylake-avx512 x86-64 native"
 
 # Additional x86 processors supported by --with-cpu=.  Each processor

gcc/config/aarch64/aarch64.c

@@ -3666,12 +3666,14 @@ aarch64_expand_prologue (void)
     {
       if (crtl->is_leaf && !cfun->calls_alloca)
 	{
-	  if (frame_size > PROBE_INTERVAL && frame_size > STACK_CHECK_PROTECT)
-	    aarch64_emit_probe_stack_range (STACK_CHECK_PROTECT,
-					    frame_size - STACK_CHECK_PROTECT);
+	  if (frame_size > PROBE_INTERVAL
+	      && frame_size > get_stack_check_protect ())
+	    aarch64_emit_probe_stack_range (get_stack_check_protect (),
+					    (frame_size
+					     - get_stack_check_protect ()));
 	}
       else if (frame_size > 0)
-	aarch64_emit_probe_stack_range (STACK_CHECK_PROTECT, frame_size);
+	aarch64_emit_probe_stack_range (get_stack_check_protect (), frame_size);
     }
 
   aarch64_sub_sp (IP0_REGNUM, initial_adjust, true);

gcc/config/alpha/alpha.c

@@ -7760,8 +7760,8 @@ alpha_expand_prologue (void)
      Note that we are only allowed to adjust sp once in the prologue.  */
 
   probed_size = frame_size;
-  if (flag_stack_check)
-    probed_size += STACK_CHECK_PROTECT;
+  if (flag_stack_check || flag_stack_clash_protection)
+    probed_size += get_stack_check_protect ();
 
   if (probed_size <= 32768)
     {
@@ -7775,7 +7775,7 @@ alpha_expand_prologue (void)
 	  /* We only have to do this probe if we aren't saving registers or
 	     if we are probing beyond the frame because of -fstack-check.  */
 	  if ((sa_size == 0 && probed_size > probed - 4096)
-	      || flag_stack_check)
+	      || flag_stack_check || flag_stack_clash_protection)
 	    emit_insn (gen_probe_stack (GEN_INT (-probed_size)));
 	}
 
@@ -7805,15 +7805,16 @@ alpha_expand_prologue (void)
 	 late in the compilation, generate the loop as a single insn.  */
       emit_insn (gen_prologue_stack_probe_loop (count, ptr));
 
-      if ((leftover > 4096 && sa_size == 0) || flag_stack_check)
+      if ((leftover > 4096 && sa_size == 0)
+	  || flag_stack_check || flag_stack_clash_protection)
 	{
 	  rtx last = gen_rtx_MEM (DImode,
 				  plus_constant (Pmode, ptr, -leftover));
 	  MEM_VOLATILE_P (last) = 1;
 	  emit_move_insn (last, const0_rtx);
 	}
 
-      if (flag_stack_check)
+      if (flag_stack_check || flag_stack_clash_protection)
 	{
 	  /* If -fstack-check is specified we have to load the entire
 	     constant into a register and subtract from the sp in one go,

gcc/config/arm/arm.c

@@ -19164,7 +19164,8 @@ arm_compute_static_chain_stack_bytes (void)
   /* See the defining assertion in arm_expand_prologue.  */
   if (IS_NESTED (arm_current_func_type ())
       && ((TARGET_APCS_FRAME && frame_pointer_needed && TARGET_ARM)
-	  || (flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+	  || ((flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+	       || flag_stack_clash_protection)
 	      && !df_regs_ever_live_p (LR_REGNUM)))
       && arm_r3_live_at_start_p ()
       && crtl->args.pretend_args_size == 0)
@@ -21466,7 +21467,8 @@ arm_expand_prologue (void)
      clobbered when creating the frame, we need to save and restore it.  */
   clobber_ip = IS_NESTED (func_type)
 	       && ((TARGET_APCS_FRAME && frame_pointer_needed && TARGET_ARM)
-		   || (flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+		   || ((flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+			|| flag_stack_clash_protection)
 		       && !df_regs_ever_live_p (LR_REGNUM)
 		       && arm_r3_live_at_start_p ()));
 
@@ -21680,7 +21682,8 @@ arm_expand_prologue (void)
      stack checking.  We use IP as the first scratch register, except for the
      non-APCS nested functions if LR or r3 are available (see clobber_ip).  */
   if (!IS_INTERRUPT (func_type)
-      && flag_stack_check == STATIC_BUILTIN_STACK_CHECK)
+      && (flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+	  || flag_stack_clash_protection))
     {
       unsigned int regno;
 
@@ -21693,13 +21696,13 @@ arm_expand_prologue (void)
 
       if (crtl->is_leaf && !cfun->calls_alloca)
 	{
-	  if (size > PROBE_INTERVAL && size > STACK_CHECK_PROTECT)
-	    arm_emit_probe_stack_range (STACK_CHECK_PROTECT,
-					size - STACK_CHECK_PROTECT,
+	  if (size > PROBE_INTERVAL && size > get_stack_check_protect ())
+	    arm_emit_probe_stack_range (get_stack_check_protect (),
+					size - get_stack_check_protect (),
 					regno, live_regs_mask);
 	}
       else if (size > 0)
-	arm_emit_probe_stack_range (STACK_CHECK_PROTECT, size,
+	arm_emit_probe_stack_range (get_stack_check_protect (), size,
 				    regno, live_regs_mask);
     }
 
@@ -24991,7 +24994,9 @@ thumb1_expand_prologue (void)
     current_function_static_stack_size = size;
 
   /* If we have a frame, then do stack checking.  FIXME: not implemented.  */
-  if (flag_stack_check == STATIC_BUILTIN_STACK_CHECK && size)
+  if ((flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+       || flag_stack_clash_protection)
+      && size)
     sorry ("-fstack-check=specific for Thumb-1");
 
   amount = offsets->outgoing_args - offsets->saved_regs;
@@ -27871,7 +27876,8 @@ arm_frame_pointer_required (void)
      instruction prior to the stack adjustment and this requires a frame
      pointer if we want to catch the exception using the EABI unwinder.  */
   if (!IS_INTERRUPT (arm_current_func_type ())
-      && flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+      && (flag_stack_check == STATIC_BUILTIN_STACK_CHECK
+	  || flag_stack_clash_protection)
       && arm_except_unwind_info (&global_options) == UI_TARGET
       && cfun->can_throw_non_call_exceptions)
     {
@@ -27886,7 +27892,7 @@ arm_frame_pointer_required (void)
 	{
 	  /* We don't have the final size of the frame so adjust.  */
 	  size += 32 * UNITS_PER_WORD;
-	  if (size > PROBE_INTERVAL && size > STACK_CHECK_PROTECT)
+	  if (size > PROBE_INTERVAL && size > get_stack_check_protect ())
 	    return true;
 	}
       else

gcc/config/i386/driver-i386.c

@@ -790,13 +790,20 @@ const char *host_detect_local_cpu (int argc, const char **argv)
 	  /* Knights Landing.  */
 	  cpu = "knl";
 	  break;
+	case 0x85:
+	  /* Knights Mill. */
+	  cpu = "knm";
+	  break;
 	default:
 	  if (arch)
 	    {
 	      /* This is unknown family 0x6 CPU.  */
 	      /* Assume Knights Landing.  */
 	      if (has_avx512f)
 		cpu = "knl";
+	      /* Assume Knights Mill */
+	      else if (has_avx5124vnniw)
+		cpu = "knm";
 	      /* Assume Skylake.  */
 	      else if (has_clflushopt)
 		cpu = "skylake";

gcc/config/i386/i386-c.c

@@ -176,6 +176,10 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
       def_or_undef (parse_in, "__knl");
       def_or_undef (parse_in, "__knl__");
       break;
+    case PROCESSOR_KNM:
+      def_or_undef (parse_in, "__knm");
+      def_or_undef (parse_in, "__knm__");
+      break;
     case PROCESSOR_SKYLAKE_AVX512:
       def_or_undef (parse_in, "__skylake_avx512");
       def_or_undef (parse_in, "__skylake_avx512__");
@@ -292,6 +296,9 @@ ix86_target_macros_internal (HOST_WIDE_INT isa_flag,
     case PROCESSOR_KNL:
       def_or_undef (parse_in, "__tune_knl__");
       break;
+    case PROCESSOR_KNM:
+      def_or_undef (parse_in, "__tune_knm__");
+      break;
     case PROCESSOR_SKYLAKE_AVX512:
       def_or_undef (parse_in, "__tune_skylake_avx512__");
       break;