On Fri, Apr 28, 2023 at 2:47 AM Fangrui Song <mask...@google.com> wrote:
>
> When using -mcmodel=medium, large data is placed into .l* sections. GNU ld
> places .l* sections into separate output sections. If small and medium
> code model object files are mixed, the .l* sections won't cause
> relocation overflow pressure on sections in -mcmodel=small object files.
>
> However, when using -mcmodel=large, -mlarge-data-threshold doesn't apply.
> This
> means that the .rodata/.data/.bss sections may cause relocation overflow
> pressure on sections in -mcmodel=small object files.
>
> This patch allows -mcmodel=large to generate .l* sections.
The x86_64 psABI does not specify how -mlarge-threshold is handled
with -mcmodel=large and it also doesn't mention that -mcmodel=large
inherits handling from -mcmodel=medium. The ABI does say that the
-mcmodel=large is strictly only required if the text of a single
function becomes larger than what the medium model allows.
OTOH, the ABI also doesn't prohibit large sections with -mcmodel=large
and IMO, the introduction of -mlarge-threshold with -mcmodel=large
does not create an ABI change.
I think the best way is to first discuss the issue with the x86_64
psABI group, to clarify how -mlarge-threshold and large data is
handled under a large code model.
Uros.
>
> Signed-off-by: Fangrui Song <mask...@google.com>
> ---
> gcc/config/i386/i386.cc | 15 +++++++++------
> gcc/config/i386/i386.opt | 2 +-
> gcc/doc/invoke.texi | 7 ++++---
> gcc/testsuite/gcc.target/i386/large-data.c | 13 +++++++++++++
> 4 files changed, 27 insertions(+), 10 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/i386/large-data.c
>
> diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
> index a3db55642e3..c68c66a5567 100644
> --- a/gcc/config/i386/i386.cc
> +++ b/gcc/config/i386/i386.cc
> @@ -637,7 +637,8 @@ ix86_can_inline_p (tree caller, tree callee)
> static bool
> ix86_in_large_data_p (tree exp)
> {
> - if (ix86_cmodel != CM_MEDIUM && ix86_cmodel != CM_MEDIUM_PIC)
> + if (ix86_cmodel != CM_MEDIUM && ix86_cmodel != CM_MEDIUM_PIC &&
> + ix86_cmodel != CM_LARGE && ix86_cmodel != CM_LARGE_PIC)
> return false;
>
> if (exp == NULL_TREE)
> @@ -848,8 +849,9 @@ x86_elf_aligned_decl_common (FILE *file, tree decl,
> const char *name, unsigned HOST_WIDE_INT size,
> unsigned align)
> {
> - if ((ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_MEDIUM_PIC)
> - && size > (unsigned int)ix86_section_threshold)
> + if ((ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_MEDIUM_PIC ||
> + ix86_cmodel == CM_LARGE || ix86_cmodel == CM_LARGE_PIC) &&
> + size > (unsigned int)ix86_section_threshold)
> {
> switch_to_section (get_named_section (decl, ".lbss", 0));
> fputs (LARGECOMM_SECTION_ASM_OP, file);
> @@ -869,9 +871,10 @@ void
> x86_output_aligned_bss (FILE *file, tree decl, const char *name,
> unsigned HOST_WIDE_INT size, unsigned align)
> {
> - if ((ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_MEDIUM_PIC)
> - && size > (unsigned int)ix86_section_threshold)
> - switch_to_section (get_named_section (decl, ".lbss", 0));
> + if ((ix86_cmodel == CM_MEDIUM || ix86_cmodel == CM_MEDIUM_PIC ||
> + ix86_cmodel == CM_LARGE || ix86_cmodel == CM_LARGE_PIC) &&
> + size > (unsigned int)ix86_section_threshold)
> + switch_to_section(get_named_section(decl, ".lbss", 0));
> else
> switch_to_section (bss_section);
> ASM_OUTPUT_ALIGN (file, floor_log2 (align / BITS_PER_UNIT));
> diff --git a/gcc/config/i386/i386.opt b/gcc/config/i386/i386.opt
> index d74f6b1f8fc..de8e722cd62 100644
> --- a/gcc/config/i386/i386.opt
> +++ b/gcc/config/i386/i386.opt
> @@ -282,7 +282,7 @@ Branches are this expensive (arbitrary units).
>
> mlarge-data-threshold=
> Target RejectNegative Joined UInteger Var(ix86_section_threshold)
> Init(DEFAULT_LARGE_SECTION_THRESHOLD)
> --mlarge-data-threshold=<number> Data greater than given threshold
> will go into .ldata section in x86-64 medium model.
> +-mlarge-data-threshold=<number> Data greater than given threshold
> will go into a large data section in x86-64 medium and large code models.
>
> mcmodel=
> Target RejectNegative Joined Enum(cmodel) Var(ix86_cmodel) Init(CM_32)
> diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
> index e5ee2d536fc..4a20eef92e5 100644
> --- a/gcc/doc/invoke.texi
> +++ b/gcc/doc/invoke.texi
> @@ -32927,9 +32927,10 @@ the cache line size. @samp{compat} is the default.
>
> @opindex mlarge-data-threshold
> @item -mlarge-data-threshold=@var{threshold}
> -When @option{-mcmodel=medium} is specified, data objects larger than
> -@var{threshold} are placed in the large data section. This value must be the
> -same across all objects linked into the binary, and defaults to 65535.
> +When @option{-mcmodel=medium} or @option{-mcmodel=large} is specified, data
> +objects larger than @var{threshold} are placed in large data sections. This
> +value must be the same across all objects linked into the binary, and
> defaults
> +to 65535.
>
> @opindex mrtd
> @item -mrtd
> diff --git a/gcc/testsuite/gcc.target/i386/large-data.c
> b/gcc/testsuite/gcc.target/i386/large-data.c
> new file mode 100644
> index 00000000000..09a917431d4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/large-data.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-require-effective-target lp64 } */
> +/* { dg-options "-O2 -mcmodel=large -mlarge-data-threshold=4" } */
> +/* { dg-final { scan-assembler ".lbss" } } */
> +/* { dg-final { scan-assembler ".bss" } } */
> +/* { dg-final { scan-assembler ".ldata" } } */
> +/* { dg-final { scan-assembler ".data" } } */
> +/* { dg-final { scan-assembler ".lrodata" } } */
> +/* { dg-final { scan-assembler ".rodata" } } */
> +
> +const char rodata_a[] = "abc", rodata_b[] = "abcd";
> +char data_a[4] = {1}, data_b[5] = {1};
> +char bss_a[4], bss_b[5];
> --
> 2.40.1.495.gc816e09b53d-goog
>
