"Jose E. Marchesi" <jose.march...@oracle.com> writes:
> There are many places in GCC where alternative local sequences are
> tried in order to determine what is the cheapest or best alternative
> to use in the current target. When any of these sequences involve a
> libcall, the current implementation of emit_library_call_value_1
> introduce a side-effect consisting on emitting an external declaration
> for the funcall (such as __divdi3) which is thus emitted even if the
> sequence that does the libcall is not retained.
>
> This is problematic in targets such as BPF, because the kernel loader
> chokes on the spurious symbol __divdi3 and makes the resulting BPF
> object unloadable. Note that BPF objects are not linked before being
> loaded.
>
> This patch changes asssemble_external_libcall to defer emitting
> declarations of external libcall symbols, by saving the call tree
> nodes in a temporary list pending_libcall_symbols and letting
> process_pending_assembly_externals to emit them only if they have been
> referenced. Solution suggested and sketched by Richard Sandiford.
>
> Regtested in x86_64-linux-gnu.
> Tested with host x86_64-linux-gnu with target bpf-unknown-none.
>
> gcc/ChangeLog
>
> * varasm.cc (pending_libcall_symbols): New variable.
> (process_pending_assemble_externals): Process
> pending_libcall_symbols.
> (assemble_external_libcall): Defer emitting external libcall
> symbols to process_pending_assemble_externals.
>
> gcc/testsuite/ChangeLog
>
> * gcc.target/bpf/divmod-libcall-1.c: New test.
> * gcc.target/bpf/divmod-libcall-2.c: Likewise.
> * gcc.c-torture/compile/libcall-2.c: Likewise.
OK, thanks.
Richard
> ---
> .../gcc.c-torture/compile/libcall-2.c | 8 +++++++
> .../gcc.target/bpf/divmod-libcall-1.c | 19 ++++++++++++++++
> .../gcc.target/bpf/divmod-libcall-2.c | 16 ++++++++++++++
> gcc/varasm.cc | 22 ++++++++++++++++++-
> 4 files changed, 64 insertions(+), 1 deletion(-)
> create mode 100644 gcc/testsuite/gcc.c-torture/compile/libcall-2.c
> create mode 100644 gcc/testsuite/gcc.target/bpf/divmod-libcall-1.c
> create mode 100644 gcc/testsuite/gcc.target/bpf/divmod-libcall-2.c
>
> diff --git a/gcc/testsuite/gcc.c-torture/compile/libcall-2.c
> b/gcc/testsuite/gcc.c-torture/compile/libcall-2.c
> new file mode 100644
> index 00000000000..b33944c83ff
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/compile/libcall-2.c
> @@ -0,0 +1,8 @@
> +/* Make sure that external refences for libcalls are generated even for
> + indirect calls. */
> +
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mcmodel=large" { target x86_64-*-* } } */
> +/* { dg-final { scan-assembler "globl\t__divti3" } } */
> +
> +__int128 a, b; void foo () { a = a / b; }
> diff --git a/gcc/testsuite/gcc.target/bpf/divmod-libcall-1.c
> b/gcc/testsuite/gcc.target/bpf/divmod-libcall-1.c
> new file mode 100644
> index 00000000000..7481076602a
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/bpf/divmod-libcall-1.c
> @@ -0,0 +1,19 @@
> +/* This test makes sure that no spurious external symbol declarations are
> + emitted for libcalls in tried but eventually not used code sequences. */
> +
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mcpu=v3" } */
> +/* { dg-final { scan-assembler-not "global\t__divdi3" } } */
> +/* { dg-final { scan-assembler-not "global\t__moddi3" } } */
> +
> +int
> +foo (unsigned int len)
> +{
> + return ((unsigned long)len) * 234 / 5;
> +}
> +
> +int
> +bar (unsigned int len)
> +{
> + return ((unsigned long)len) * 234 % 5;
> +}
> diff --git a/gcc/testsuite/gcc.target/bpf/divmod-libcall-2.c
> b/gcc/testsuite/gcc.target/bpf/divmod-libcall-2.c
> new file mode 100644
> index 00000000000..792d689395a
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/bpf/divmod-libcall-2.c
> @@ -0,0 +1,16 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -mcpu=v3" } */
> +/* { dg-final { scan-assembler "global\t__divdi3" } } */
> +/* { dg-final { scan-assembler "global\t__moddi3" } } */
> +
> +int
> +foo (unsigned int len)
> +{
> + return ((long)len) * 234 / 5;
> +}
> +
> +int
> +bar (unsigned int len)
> +{
> + return ((long)len) * 234 % 5;
> +}
> diff --git a/gcc/varasm.cc b/gcc/varasm.cc
> index 6ae35edc5ae..deb7eab7af9 100644
> --- a/gcc/varasm.cc
> +++ b/gcc/varasm.cc
> @@ -2461,6 +2461,10 @@ contains_pointers_p (tree type)
> it all the way to final. See PR 17982 for further discussion. */
> static GTY(()) tree pending_assemble_externals;
>
> +/* A similar list of pending libcall symbols. We only want to declare
> + symbols that are actually used in the final assembly. */
> +static GTY(()) rtx pending_libcall_symbols;
> +
> #ifdef ASM_OUTPUT_EXTERNAL
> /* Some targets delay some output to final using TARGET_ASM_FILE_END.
> As a result, assemble_external can be called after the list of externals
> @@ -2520,8 +2524,17 @@ process_pending_assemble_externals (void)
> for (list = pending_assemble_externals; list; list = TREE_CHAIN (list))
> assemble_external_real (TREE_VALUE (list));
>
> + for (rtx list = pending_libcall_symbols; list; list = XEXP (list, 1))
> + {
> + rtx symbol = XEXP (list, 0);
> + tree id = get_identifier (XSTR (symbol, 0));
> + if (TREE_SYMBOL_REFERENCED (id))
> + targetm.asm_out.external_libcall (symbol);
> + }
> +
> pending_assemble_externals = 0;
> pending_assemble_externals_processed = true;
> + pending_libcall_symbols = NULL_RTX;
> delete pending_assemble_externals_set;
> #endif
> }
> @@ -2594,8 +2607,15 @@ assemble_external_libcall (rtx fun)
> /* Declare library function name external when first used, if nec. */
> if (! SYMBOL_REF_USED (fun))
> {
> + gcc_assert (!pending_assemble_externals_processed);
> SYMBOL_REF_USED (fun) = 1;
> - targetm.asm_out.external_libcall (fun);
> + /* Make sure the libcall symbol is in the symtab so any
> + reference to it will mark its tree node as referenced, via
> + assemble_name_resolve. These are eventually emitted, if
> + used, in process_pending_assemble_externals. */
> + get_identifier (XSTR (fun, 0));
> + pending_libcall_symbols = gen_rtx_EXPR_LIST (VOIDmode, fun,
> + pending_libcall_symbols);
> }
> }
