arm64: Improve HAVE_DYNAMIC_FTRACE_WITH_REGS selection for clang

Will and Anders reported that using just 'CC=clang' with CONFIG_FTRACE=y
and CONFIG_STACK_TRACER=y would result in an error while linking:

  aarch64-linux-gnu-ld: .init.data has both ordered [`__patchable_function_entries' in init/main.o] and unordered [`.meminit.data' in mm/sparse.o] sections
  aarch64-linux-gnu-ld: final link failed: bad value

This error was exposed by commit f12b034afe ("scripts/Makefile.clang:
default to LLVM_IAS=1") in combination with binutils older than 2.36.

When '-fpatchable-function-entry' was implemented in LLVM, two code
paths were added for adding the section attributes, one for the
integrated assembler and another for GNU as, due to binutils
deficiencies at the time. If the integrated assembler was used,
attributes that GNU ld < 2.36 could not handle were added, presumably
with the assumption that use of the integrated assembler meant the whole
LLVM stack was being used, namely ld.lld.

Prior to the kernel change previously mentioned, that assumption was
valid, as there were three commonly used combinations of tools for
compiling, assembling, and linking respectively:

$ make CC=clang (clang, GNU as, GNU ld)
$ make LLVM=1 (clang, GNU as, ld.lld)
$ make LLVM=1 LLVM_IAS=1 (clang, integrated assembler, ld.lld)

After the default switch of the integrated assembler, the second and
third commands become equivalent and the first command means "clang,
integrated assembler, and GNU ld", which was not a combination that was
considered when the aforementioned LLVM change was implemented.

It is not possible to go back and fix LLVM, as this change was
implemented in the 10.x series, which is no longer supported. To
workaround this on the kernel side, split out the selection of
HAVE_DYNAMIC_FTRACE_WITH_REGS to two separate configurations, one for
GCC and one for clang.

The GCC config inherits the '-fpatchable-function-entry' check. The
Clang config does not it, as '-fpatchable-function-entry' is always
available for LLVM 11.0.0 and newer, which is the supported range of
versions for the kernel.

The Clang config makes sure that the user is using GNU as or the
integrated assembler with ld.lld or GNU ld 2.36 or newer, which will
avoid the error above.

Link: https://github.com/ClangBuiltLinux/linux/issues/1507
Link: https://github.com/ClangBuiltLinux/linux/issues/788
Link: https://lore.kernel.org/YlCA5PoIjF6nhwYj@dev-arch.thelio-3990X/
Link: https://sourceware.org/bugzilla/show_bug.cgi?id=26256
Link: 7fa5290d5b
Link: 853a264916
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Reported-by: Will Deacon <will@kernel.org>
Tested-by: Will Deacon <will@kernel.org>
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Link: https://lore.kernel.org/r/20220413181420.3522187-1-nathan@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
This commit is contained in:
Nathan Chancellor 2022-04-13 11:14:21 -07:00 committed by Will Deacon
parent e5c23779f9
commit 45bd895180

View File

@ -175,8 +175,6 @@ config ARM64
select HAVE_DEBUG_KMEMLEAK select HAVE_DEBUG_KMEMLEAK
select HAVE_DMA_CONTIGUOUS select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS \
if $(cc-option,-fpatchable-function-entry=2)
select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \ select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY \
if DYNAMIC_FTRACE_WITH_REGS if DYNAMIC_FTRACE_WITH_REGS
select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EFFICIENT_UNALIGNED_ACCESS
@ -228,6 +226,17 @@ config ARM64
help help
ARM 64-bit (AArch64) Linux support. ARM 64-bit (AArch64) Linux support.
config CLANG_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS
def_bool CC_IS_CLANG
# https://github.com/ClangBuiltLinux/linux/issues/1507
depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600))
select HAVE_DYNAMIC_FTRACE_WITH_REGS
config GCC_SUPPORTS_DYNAMIC_FTRACE_WITH_REGS
def_bool CC_IS_GCC
depends on $(cc-option,-fpatchable-function-entry=2)
select HAVE_DYNAMIC_FTRACE_WITH_REGS
config 64BIT config 64BIT
def_bool y def_bool y