gcc/ChangeLog:
	PR tree-optimization/83312
	* domwalk.h (dom_walker::dom_walker): Fix typo in comment.
	* tree-cfg.c (find_taken_edge): Update to handle NULL_TREE for
	"val" param, and to cope with arbitrary basic blocks.
	(find_taken_edge_cond_expr): Add "cond_stmt" param and use it to
	handle NULL_TREE for "val", dropping "bb" param.
	(find_taken_edge_switch_expr): Make "switch_stmt" param const and
	drop "bb" param.  Handle NULL_TREE for "val".
	(find_case_label_for_value): Make "switch_stmt" param const.
	* tree-vrp.c (class check_array_bounds_dom_walker): New subclass
	of dom_walker.
	(vrp_prop::check_all_array_refs): Reimplement as...
	(check_array_bounds_dom_walker::before_dom_children): ...this new
	vfunc.  Replace linear search through BB block list, excluding
	those with non-executable in-edges via dominator walk.

gcc/testsuite/ChangeLog:
	PR tree-optimization/83312
	* gcc.dg/pr83312.c: New test case.

From-SVN: r255649

trans.c (Call_to_gnu): Set DECL_DISREGARD_INLINE_LIMITS to 0 on the callee if the call is recursive.

	* gcc-interface/trans.c (Call_to_gnu): Set DECL_DISREGARD_INLINE_LIMITS
	to 0 on the callee if the call is recursive.

From-SVN: r255648

decl.c (gnat_to_gnu_field): Do not set the alignment of the enclosing record type if it is not already set.

	* gcc-interface/decl.c (gnat_to_gnu_field): Do not set the alignment
	of the enclosing record type if it is not already set.

From-SVN: r255645

This patch adds an -mverbose-cost-dump option, similar to the one in aarch64.
It makes the RTX cost dump print the RTX we're costing in the backend, as well as its cost.
This can be distracting in other cost-related RTL dumps like combine's.

So now we don't dump the backend information by default, but provide the power-user option -mverbose-cost-dump
to enable the old verbose dumping.

This option is for GCC developers debugging the compiler only, so no documentation are added.
It's also trivially simple in functionality so no test is added either.

Bootstrapped and tested on arm-none-linux-gnueabihf.

Committed to trunk.

	* config/arm/arm.opt (mverbose-cost-dump): New option.
	* config/arm/arm.c (arm_rtx_costs): Use it.

From-SVN: r255644

	PR lto/81406
	* gcc.dg/lto/pr81406_0.c: New test.

From-SVN: r255643

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/66974
	* gcc.dg/Warray-bounds-24.c: New testcase.

From-SVN: r255642

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/65258
	* gcc.dg/Warray-bounds-23.c: New testcase.

From-SVN: r255641

	PR bootstrap/83396
	* reload1.c (emit_input_reload_insns): Skip debug markers.

From-SVN: r255640

We skip debug insns and notes after a call that needs a nop_endbr, but
since a debug insn could be the last in a block, it may affect the loc
in the emitted nop_endbr insn.  Although this has no effect on
codegen, it does mess with debug info a bit, and it causes
-fcompare-debug to fail for e.g. libsanitizer's
tsan/tsan_platform_linux.cc on x86_64.

So, pick the location of the call insn for the nop_endbr insn, to
avoid the line number differences in dumps, including -fcompare-debug
ones.

Also, we don't need to determine what the insert point would be unless
we're actually emitting the nop_endbr insn after the call, so
rearrange the code to avoid wasting cycles.

Finally, it seems like testing for barriers is a mistake.  We probably
never actually pass that test, for the barriers would hit BB_END
first.  If we did, we'd end up emitting the nop_endbr outside any BB,
even after the end of the function!  That would be Very Bad (TM).
Now, since the test as it is can't hurt, I figured I wouldn't change
the logic right now, just add a comment so that someone involved in
endbr stuff can have a second look and hopefully fix it.

for  gcc/ChangeLog

	* config/i386/i386.c (rest_of_insert_endbranch): Use call loc
	for its nop_endbr.

From-SVN: r255639

The patch that added _nondebug to next_ and prev_nonnote_insn_bb
failed to find and adjust uses within config.  Fixed.

for  gcc/ChangeLog

	PR bootstrap/83396
	* config/arc/arc.c (hwloop_optimize): Skip debug insns.
	* config/sh/sh-protos.h (sh_find_set_of_reg): Adjust.
	* config/sh/sh.c: Skip debug insns besides notes.
	* config/sh/sh.md: Likewise.
	* config/sh/sh_treg_combine.cc: Likewise.
	* config/sh/sync.md: Likewise.

From-SVN: r255638

2017-12-14  Tom de Vries  <tom@codesourcery.com>

	* lib/target-supports.exp (check_effective_target_weak_undefined): New
	proc.
	* gcc.dg/visibility-22.c: Require effective target weak_undefined.

	* doc/sourcebuild.texi (Effective-Target Keywords, Other attributes):
	Add item for weak_undefined.

From-SVN: r255637

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/67842
	* sese.h (bb_in_region): Remove #if 0'ed code.

From-SVN: r255636

re PR tree-optimization/83326 (SPEC CPU2017 648.exchange2_s ~6% performance regression with r255267 (reproducer attached))

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/83326
	* tree-ssa-loop-ivcanon.c (try_unroll_loop_completely): Add
	may_be_zero parameter and handle it by not marking the first
	peeled copy as not exiting the loop.
	(try_peel_loop): Likewise.
	(canonicalize_loop_induction_variables): Use number_of_iterations_exit
	to handle the case of constant or zero iterations and perform
	loop header copying on-the-fly.

	* gcc.dg/tree-ssa/pr81388-2.c: Adjust.

From-SVN: r255635

	* testsuite/26_numerics/complex/inserters_extractors/char/dr2714.cc:
	Add tests using noskipws.

From-SVN: r255632

	* gcc-interface/gigi.h (pad_type_has_rm_size): Declare.
	* gcc-interface/decl.c (gnat_to_gnu_entity) <E_Variable>: Do not build
	a padding type for the alignment before validating the size.
	Flip conditional construct and add a comment.
	* gcc-interface/trans.c (Attribute_to_gnu) <Attr_Size>: Make sure to
	apply the exception for padded objects to the type of the object.
	* gcc-interface/utils.c (hash_pad_type): New static function.
	(lookup_and_insert_pad_type): Rename into...
	(canonicalize_pad_type): ...this.  Call hash_pad_type, do only one
	lookup with insertion and always return the canonical type.
	(maybe_pad_type): Adjust to above changes.  Set debug type later.
	(pad_type_has_rm_size): New predicate.
	(set_reverse_storage_order_on_pad_type): Adjust to above changes.

From-SVN: r255631

	* testsuite/26_numerics/complex/dr2714.cc: Move to ...
	* testsuite/26_numerics/complex/inserters_extractors/char/dr2714.cc:
	... Here. Remove duplicate header and dg-options. Check first invalid
	character gets putback. Remove wchar_t test.

From-SVN: r255630

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR c/83415
	c/
	* c-fold.c (c_fully_fold_internal): Treat VIEW_CONVERT_EXPR
	like REALPART_EXPR for the behavior of whether its operand
	is an lvalue.

	* gcc.dg/pr83415.c: New testcase.

From-SVN: r255629

re PR tree-optimization/83418 (ICE in extract_range_for_var_from_comparison_expr, at vr-values.c:448)

2017-12-14  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/83418
	* vr-values.c (vr_values::extract_range_for_var_from_comparison_expr):
	Instead of asserting we don't get unfolded comparisons deal with
	them.

	* gcc.dg/torture/pr83418.c: New testcase.

From-SVN: r255628

	PR bootstrap/83396
	* var-tracking.c (vt_initialize): Ignore non-DEBUG_INSNs outside of
	basic blocks.  Assert debug bind insns don't appear outside of bbs,
	don't reset them.  Assert insns without BLOCK_FOR_INSN are outside of
	bb.  Simplify.

	* gcc.dg/pr83396.c: New test.

From-SVN: r255627

	PR tree-optimization/83198
	* gimple-ssa-sprintf.c (format_floating): Set type solely based on
	dir.modifier, regardless of TREE_TYPE (arg).  Assume non-REAL_CST
	value if arg is a REAL_CST with incompatible type.

	* gcc.dg/pr83198.c: New test.
	* gcc.dg/tree-ssa/pr83198.c: New test.

From-SVN: r255626

This patch is a follow up to the existing discussions on
https://gcc.gnu.org/ml/gcc-patches/2017-07/msg01904.html
Bin had earlier submitted this patch to fix the ICE that
occurs because of the missing LTGT in aarch64-simd.md.
That discussion opened up a new bug report PR81647 for
an inconsistent behavior.

As discussed earlier on the gcc-patches discussion and on
the bug report, PR81647 was occurring because of how UNEQ
was handled in aarch64-simd.md rather than LTGT.
Since __builtin_islessgreater is guaranteed to not give an
FP exception but LTGT might, __builtin_islessgreater gets
converted to ~UNEQ very early on in fold_builtin_unordered_cmp.
Thus I will post a separate patch for correcting how UNEQ and
other unordered comparisons are handled in aarch64-simd.md.

This patch is only adding the missing LTGT to plug the ICE.

Testing done: Checked for regressions on bootstrapped
aarch64-none-linux-gnu and added a new compile time test case
that gives out LTGT to make sure it doesn't ICE

*** gcc/ChangeLog ***

2017-12-14  Sudakshina Das  <sudi.das@arm.com>
	    Bin Cheng  <bin.cheng@arm.com>

	PR target/81228
	* config/aarch64/aarch64.c (aarch64_select_cc_mode): Move LTGT
	to CCFPEmode.
	* config/aarch64/aarch64-simd.md (vec_cmp<mode><v_int_equiv>): Add
	LTGT.

*** gcc/testsuite/ChangeLog ***

2017-12-14  Sudakshina Das  <sudi.das@arm.com>

	PR target/81228
	* gcc.dg/pr81228.c: New.

Co-Authored-By: Bin Cheng <bin.cheng@arm.com>

From-SVN: r255625

The Cortex-A55 and Cortex-A75 processors support the fp16 extension.
We already specify them as such in the arm port.
This patch makes aarch64 consistent on this front.

Bootstrapped and tested on aarch64-none-linux-gnu.
Manually checked that compiling with aarch64-none-linux-gnu-gcc -mcpu=cortex-a55 -dM -E - < /dev/null
shows __ARM_FEATURE_FP16_VECTOR_ARITHMETIC and __ARM_FEATURE_FP16_SCALAR_ARITHMETIC being specified
as expected whereas they were not before this patch.

	* config/aarch64/aarch64-cores.def (cortex-a55, cortex-a75,
	cortex-a75.cortex-a55): Specify AARCH64_FL_F16 in the arch features.

From-SVN: r255624

re PR c++/79650 (ICE on invalid c++ code with label arithmetic in convert_nontype_argument (pt.c:6515))

	PR c++/79650
	* pt.c (convert_nontype_argument): Diagnose
	reduced_constant_expression_p expressions that aren't INTEGER_CST.

	* g++.dg/template/pr79650.C: New test.

From-SVN: r255623

2017-12-12  Jerry DeLisle  <jvdelisle@gcc.gnu.org>

        PR libgfortran/78549
        * io/inquire.c (inquire_via_unit): Adjust test for existence for
        pre-connected internal units.
        * io/transfer.c (finalize_transfer): When done with a transfer
        to internal units, free the format buffer and close the stream.
        (st_read_done): Delete freeing the stream, now handled using
        sclose in finalize_transfer. (st_write_done): Likewise.
        * io/unit.c (get_unit): Return NULL for special reserved unit
        numbers, signifying not accessible to the user.
        (init_units): Insert the two special internal units into the
        unit treap. This makes these unit structures available without
        further allocations for later use by internal unit I/O. These
        units are automatically deleted by normal program termination.
        * io/unix.c (mem_close): Add a guard check to protect from double free.

From-SVN: r255621

From-SVN: r255620

This patch adds a new "poly_int" class to represent polynomial integers
of the form:

  C0 + C1*X1 + C2*X2 ... + Cn*Xn

It also adds poly_int-based typedefs for offsets and sizes of various
precisions.  In these typedefs, the Ci coefficients are compile-time
constants and the Xi indeterminates are run-time invariants.  The number
of coefficients is controlled by the target and is initially 1 for all
ports.

Most routines can handle general coefficient counts, but for now a few
are specific to one or two coefficients.  Support for other coefficient
counts can be added when needed.

The patch also adds a new macro, IN_TARGET_CODE, that can be
set to indicate that a TU contains target-specific rather than
target-independent code.  When this macro is set and the number of
coefficients is 1, the poly-int.h classes define a conversion operator
to a constant.  This allows most existing target code to work without
modification.  The main exceptions are:

- values passed through ..., which need an explicit conversion to a
  constant

- ?: expression in which one arm ends up being a polynomial and the
  other remains a constant.  In these cases it would be valid to convert
  the constant to a polynomial and the polynomial to a constant, so a
  cast is needed to break the ambiguity.

The patch also adds a new target hook to return the estimated
value of a polynomial for costing purposes.

The patch also adds operator<< on wide_ints (it was already defined
for offset_int and widest_int).  I think this was originally excluded
because >> is ambiguous for wide_int, but << is useful for converting
bytes to bits, etc., so is worth defining on its own.  The patch also
adds operator% and operator/ for offset_int and widest_int, since those
types are always signed.  These changes allow the poly_int interface to
be more predictable.

I'd originally tried adding the tests as selftests, but that ended up
bloating cc1 by at least a third.  It also took a while to build them
at -O2.  The patch therefore uses plugin tests instead, where we can
force the tests to be built at -O0.  They still run in negligible time
when built that way.

2017-12-14  Richard Sandiford  <richard.sandiford@linaro.org>
	    Alan Hayward  <alan.hayward@arm.com>
	    David Sherwood  <david.sherwood@arm.com>

gcc/
	* poly-int.h: New file.
	* poly-int-types.h: Likewise.
	* coretypes.h: Include them.
	(POLY_INT_CONVERSION): Define.
	* target.def (estimated_poly_value): New hook.
	* doc/tm.texi.in (TARGET_ESTIMATED_POLY_VALUE): New hook.
	* doc/tm.texi: Regenerate.
	* doc/poly-int.texi: New file.
	* doc/gccint.texi: Include it.
	* doc/rtl.texi: Describe restrictions on subreg modes.
	* Makefile.in (TEXI_GCCINT_FILES): Add poly-int.texi.
	* genmodes.c (NUM_POLY_INT_COEFFS): Provide a default definition.
	(emit_insn_modes_h): Emit a definition of NUM_POLY_INT_COEFFS.
	* targhooks.h (default_estimated_poly_value): Declare.
	* targhooks.c (default_estimated_poly_value): New function.
	* target.h (estimated_poly_value): Likewise.
	* wide-int.h (WI_UNARY_RESULT): Use wi::binary_traits.
	(wi::unary_traits): Delete.
	(wi::binary_traits::signed_shift_result_type): Define for
	offset_int << HOST_WIDE_INT, etc.
	(generic_wide_int::operator <<=): Define for all types and use
	wi::lshift instead of <<.
	(wi::hwi_with_prec): Add a default constructor.
	(wi::ints_for): New class.
	(operator <<): Define for all wide-int types.
	(operator /): New function.
	(operator %): Likewise.
	* selftest.h (ASSERT_KNOWN_EQ, ASSERT_KNOWN_EQ_AT, ASSERT_MAYBE_NE)
	(ASSERT_MAYBE_NE_AT): New macros.

gcc/testsuite/
	* gcc.dg/plugin/poly-int-tests.h,
	gcc.dg/plugin/poly-int-test-1.c,
	gcc.dg/plugin/poly-int-01_plugin.c,
	gcc.dg/plugin/poly-int-02_plugin.c,
	gcc.dg/plugin/poly-int-03_plugin.c,
	gcc.dg/plugin/poly-int-04_plugin.c,
	gcc.dg/plugin/poly-int-05_plugin.c,
	gcc.dg/plugin/poly-int-06_plugin.c,
	gcc.dg/plugin/poly-int-07_plugin.c: New tests.
	* gcc.dg/plugin/plugin.exp: Run them.

Co-Authored-By: Alan Hayward <alan.hayward@arm.com>
Co-Authored-By: David Sherwood <david.sherwood@arm.com>

From-SVN: r255617

	PR middle-end/78468
	* emit-rtl.c (init_emit): Remove ??? comment.
	* explow.c (get_dynamic_stack_size): Take known alignment of stack
	pointer + STACK_DYNAMIC_OFFSET into account in lieu of STACK_BOUNDARY.
	* config/sparc/sparc.h (INIT_EXPANDERS): In 32-bit mode, lower the
	alignment of 3 virtual registers to BITS_PER_WORD.

	* config/sparc/sparc.c (sparc_compute_frame_size): Simplify.

Co-Authored-By: Dominik Vogt <vogt@linux.vnet.ibm.com>

From-SVN: r255616

gcc/
	* config/rs6000/ppc-auxv.h (PPC_FEATURE2_HTM_NO_SUSPEND): New define.
	* config/rs6000/rs6000.c (cpu_supports_info): Use it.

gcc/testsuite/
	* gcc.target/powerpc/cpu-builtin-1.c (htm-no-suspend): Add test.

From-SVN: r255614

/cp
2017-12-13  Paolo Carlini  <paolo.carlini@oracle.com>

	PR c++/81061
	* typeck.c (cp_build_modify_expr): Upon cxx_readonly_error
	immediately return error_mark_node.

/testsuite
2017-12-13  Paolo Carlini  <paolo.carlini@oracle.com>

	PR c++/81061
	* g++.dg/other/const5.C: New.

From-SVN: r255613

Eliminate regs in debug bind insns, but not in markers.

for  gcc/ChangeLog

	PR bootstrap/83396
	* reload1.c (eliminate_regs_in_insn): Skip debug markers.

From-SVN: r255612

tree-cfg.c (verify_gimple_in_cfg): Verify no non-label stmts with the exception of debug begin stmt markers appear...

	* tree-cfg.c (verify_gimple_in_cfg): Verify no non-label stmts
	with the exception of debug begin stmt markers appear before
	labels.

From-SVN: r255611

	PR bootstrap/83396
	* final.c (rest_of_handle_final): Call variable_tracking_main only
	if !flag_var_tracking.

From-SVN: r255610

	PR bootstrap/83396
	PR debug/83391
	* tree-cfgcleanup.c (remove_forwarder_block): Keep after
	labels debug stmts that can only appear after labels.

	* gcc.dg/torture/pr83396.c: New test.
	* g++.dg/torture/pr83391.C: New test.

Co-Authored-By: Jakub Jelinek <jakub@redhat.com>

From-SVN: r255609

	PR libstdc++/59568
	* include/std/complex (operator>>): Implement proposed resolution to
	LWG 2714. Use putback if and only if a character has been successfully
	extracted but isn't a delimiter. Use ctype::widen and traits::eq when
	testing if extracted characters match delimiters.
	* testsuite/26_numerics/complex/dr2714.cc: New test.

From-SVN: r255608

	PR rtl-optimization/82398
	* sel-sched.c (sel_rank_for_schedule): Fix check for zero
	EXPR_USEFULNESS in priority comparison.

From-SVN: r255607

In move_deaths we move a REG_DEAD note if the instruction combination
has extended the lifetime of a register so that the existing note is
no longer valid.  We find that note using reg_stat, but what that finds
can refer to a later insn.  If so, we cannot use the cached value.  This
patch implements that.


	PR rtl-optimization/83393
	* combine.c (move_deaths): If reg_stat points to a too new insn in
	last_death, do not use it: find the proper insn instead.

gcc/testsuite/
	PR rtl-optimization/83393
	* gcc.dg/pr83393.c: New testcase.

From-SVN: r255606

https://gcc.gnu.org/ml/gcc-patches/2017-12/msg00766.html
	PR c++/15272
	* pt.c (tsubst_baselink): Don't repeat the lookup for
	non-dependent baselinks.

	PR c++/15272
	* g++.dg/template/pr71826.C: Adjust for 15272 fix.

From-SVN: r255605

From-SVN: r255603

	* gcc-interface/trans.c (process_freeze_entity): Be prepared for a
	package without body.

From-SVN: r255601

	* gcc-interface/decl.c (gnat_to_gnu_entity): Robustify test for types
	descendant of System.Address.
	(gnat_to_gnu_subprog_type): Likewise.

From-SVN: r255599