[PATCH 0/3] perf: Fix missing CET property notes on x86 with -fcf-protection

[PATCH 0/3] perf: Fix missing CET property notes on x86 with -fcf-protection

[Trevor Allison]

When perf is built with -fcf-protection, the x86 binary can lack CET
(IBT/SHSTK) in .note.gnu.property because perf links several static
archives whole-archive: if any input object lacks matching property
notes, the linker drops CET from the final binary.

Fix libbpf EXTRA_CFLAGS handling, C++ flag propagation, and missing
.note.gnu.property sections in x86 assembly (like .note.GNU-stack).
All three are needed for CET to survive the link.

Trevor Allison (3):
  perf build: Preserve EXTRA_CFLAGS when building in-tree libbpf
  perf build: Apply EXTRA_CXXFLAGS to C++ builds
  perf x86: Add .note.gnu.property to assembly linked into perf

 tools/perf/Makefile.config               |  1 +
 tools/perf/Makefile.perf                 |  2 +-
 tools/perf/arch/x86/tests/regs_load.S    | 24 ++++++++++++++++++++++++
 tools/perf/bench/mem-memcpy-x86-64-asm.S | 24 ++++++++++++++++++++++++
 tools/perf/bench/mem-memset-x86-64-asm.S | 24 ++++++++++++++++++++++++
 5 files changed, 74 insertions(+), 1 deletion(-)

-- 
2.50.1 (Apple Git-155)

[PATCH 1/3] perf build: Preserve EXTRA_CFLAGS when building in-tree libbpf

[Trevor Allison]

The libbpf sub-make passes EXTRA_CFLAGS="-fPIC", replacing the
parent EXTRA_CFLAGS.  Append -fPIC instead, since libbpf.a is linked
whole-archive into perf.

Signed-off-by: Trevor Allison <tallison@redhat.com>
---
 tools/perf/Makefile.perf | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2b53d9e0c73b..a59ed1d70ecc 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -706,7 +706,7 @@ $(LIBAPI)-clean:
 $(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(LIBBPF_DIR) FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) \
 		O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= subdir= \
-		EXTRA_CFLAGS="-fPIC" $@ install_headers
+		EXTRA_CFLAGS="$(EXTRA_CFLAGS) -fPIC" $@ install_headers
 
 $(LIBBPF)-clean:
 	$(call QUIET_CLEAN, libbpf)
-- 
2.50.1 (Apple Git-155)

[PATCH 2/3] perf build: Apply EXTRA_CXXFLAGS to C++ builds

[Trevor Allison]

C++ sources did not receive EXTRA_CXXFLAGS or EXTRA_CFLAGS, unlike C
sources. Initialize CXXFLAGS from both so C++ objects such as
demangle-cxx.o get the same builder flags as the rest of perf.

Signed-off-by: Trevor Allison <tallison@redhat.com>
---
 tools/perf/Makefile.config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0ba307e78fe1..052a6cc7942f 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -17,6 +17,7 @@ detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
 detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
+CXXFLAGS := $(EXTRA_CXXFLAGS) $(EXTRA_CFLAGS)
 HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
 
 # This is required because the kernel is built with this and some of the code
-- 
2.50.1 (Apple Git-155)

[PATCH 3/3] perf x86: Add .note.gnu.property to assembly linked into perf

[Trevor Allison]

Assembly sources do not get .note.gnu.property from the compiler.
Add the section to the x86 files that are linked into perf, using the
same approach as the existing .note.GNU-stack notes.

Signed-off-by: Trevor Allison <tallison@redhat.com>
---
 tools/perf/arch/x86/tests/regs_load.S    | 24 ++++++++++++++++++++++++
 tools/perf/bench/mem-memcpy-x86-64-asm.S | 24 ++++++++++++++++++++++++
 tools/perf/bench/mem-memset-x86-64-asm.S | 24 ++++++++++++++++++++++++
 3 files changed, 72 insertions(+)

diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index 80f14f52e3f6..1947f95cceda 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -97,3 +97,27 @@ SYM_FUNC_END(perf_regs_load)
  * the ELF stack should not be restricted at all and set it RWX.
  */
 .section .note.GNU-stack,"",@progbits
+
+/*
+ * We need to provide .note.gnu.property section with IBT and SHSTK,
+ * saying that this object supports the same CET properties as C code
+ * built with -fcf-protection. Otherwise static linking drops CET from
+ * the final perf binary when other objects are CET-enabled.
+ */
+	.pushsection .note.gnu.property, "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
+	.popsection
diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
index 1b9fef7efcdc..e7b84aa43ab4 100644
--- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
+++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
@@ -18,3 +18,27 @@
  * the ELF stack should not be restricted at all and set it RWX.
  */
 .section .note.GNU-stack,"",@progbits
+
+/*
+ * We need to provide .note.gnu.property section with IBT and SHSTK,
+ * saying that this object supports the same CET properties as C code
+ * built with -fcf-protection. Otherwise static linking drops CET from
+ * the final perf binary when other objects are CET-enabled.
+ */
+	.pushsection .note.gnu.property, "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
+	.popsection
diff --git a/tools/perf/bench/mem-memset-x86-64-asm.S b/tools/perf/bench/mem-memset-x86-64-asm.S
index abd26c95f1aa..f8002da91c3c 100644
--- a/tools/perf/bench/mem-memset-x86-64-asm.S
+++ b/tools/perf/bench/mem-memset-x86-64-asm.S
@@ -13,3 +13,27 @@
  * the ELF stack should not be restricted at all and set it RWX.
  */
 .section .note.GNU-stack,"",@progbits
+
+/*
+ * We need to provide .note.gnu.property section with IBT and SHSTK,
+ * saying that this object supports the same CET properties as C code
+ * built with -fcf-protection. Otherwise static linking drops CET from
+ * the final perf binary when other objects are CET-enabled.
+ */
+	.pushsection .note.gnu.property, "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
+	.popsection
-- 
2.50.1 (Apple Git-155)

Re: [PATCH 2/3] perf build: Apply EXTRA_CXXFLAGS to C++ builds

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] C++ feature detection tests do not receive `EXTRA_CFLAGS`, causing a structural mismatch between feature detection and actual build compilation flags.
- [Low] Injecting `EXTRA_CFLAGS` into `CXXFLAGS` breaks C++ builds when C-specific flags are present.
--

--- Patch [2]: [PATCH 2/3] perf build: Apply EXTRA_CXXFLAGS to C++ builds ---
commit 4b2b9e4dd8644e0e1fa95ec876a875596e1e9178
Author: Trevor Allison <tallison@redhat.com>

perf build: Apply EXTRA_CXXFLAGS to C++ builds

The commit initializes CXXFLAGS in tools/perf/Makefile.config with both
EXTRA_CXXFLAGS and EXTRA_CFLAGS so that C++ objects receive the same builder
flags as the rest of perf.

> diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
> index 0ba307e78fe1f..052a6cc7942f9 100644
> --- a/tools/perf/Makefile.config
> +++ b/tools/perf/Makefile.config
> @@ -17,6 +17,7 @@ detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
>  detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
>  
>  CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
> +CXXFLAGS := $(EXTRA_CXXFLAGS) $(EXTRA_CFLAGS)

[Severity: Low]
Could this cause a build regression if EXTRA_CFLAGS contains C-only flags?

If EXTRA_CFLAGS contains flags that are only valid for C/ObjC (such as
-Wstrict-prototypes), applying them to C++ files causes compiler warnings.
With -Werror enabled, this results in a build failure.

[Severity: Medium]
Does this create a mismatch between feature detection and the main build?

While CXXFLAGS here receives EXTRA_CFLAGS, the C++ feature detection tests in
tools/build/Makefile.feature still only use:

CXXFLAGS="$(EXTRA_CXXFLAGS) $(FEATURE_CHECK_CXXFLAGS-$(1))"

If EXTRA_CFLAGS contains mandatory compiler flags like --sysroot or -m32,
the C++ feature detection tests will fail without EXTRA_CFLAGS. This causes
false negatives where the perf binary silently lacks supported features,
despite the main build succeeding.

>  HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708045606.43649-1-tallison@redhat.com?part=2

Re: [PATCH 3/3] perf x86: Add .note.gnu.property to assembly linked into perf

[sashiko-bot]

Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
- [Medium] Adding .note.gnu.property asserts IBT support without providing ENDBR64 instructions, causing a #CP crash in perf memory benchmarks.
- [Medium] The .note.gnu.property section hardcodes 8-byte alignment, violating the 32-bit x86 ELF specification.
--

--- Patch [3]: [PATCH 3/3] perf x86: Add .note.gnu.property to assembly linked into perf ---
commit b48d7edb7fb18bc3dace2af272de108eb561d69b
Author: Trevor Allison <tallison@redhat.com>

perf x86: Add .note.gnu.property to assembly linked into perf

This commit adds `.note.gnu.property` to x86 assembly files linked into
perf to indicate CET properties support. This is intended to prevent static
linking from dropping CET from the final binary.

> diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
> index 80f14f52e3f60..1947f95cceda5 100644
> --- a/tools/perf/arch/x86/tests/regs_load.S
> +++ b/tools/perf/arch/x86/tests/regs_load.S
[ ... ]
> @@ -97,3 +97,27 @@ SYM_FUNC_END(perf_regs_load)
>   * the ELF stack should not be restricted at all and set it RWX.
>   */
>  .section .note.GNU-stack,"",@progbits
> +
> +/*
> + * We need to provide .note.gnu.property section with IBT and SHSTK,
> + * saying that this object supports the same CET properties as C code
> + * built with -fcf-protection. Otherwise static linking drops CET from
> + * the final perf binary when other objects are CET-enabled.
> + */
> +	.pushsection .note.gnu.property, "a"
> +	.p2align 3

[Severity: Medium]
Does this unconditionally hardcode 8-byte alignment for 32-bit x86 builds?

The assembly file `regs_load.S` can be compiled for 32-bit x86, which requires
4-byte alignment (`.p2align 2`) for ELF notes. When the linker merges these,
the forced 8-byte alignment can create zero-byte padding gaps between notes,
corrupting the contiguous ELF note structure.

Could this cause the dynamic loader or tools like `readelf` to fail to parse
the ELF notes properly?

[ ... ]
> diff --git a/tools/perf/bench/mem-memcpy-x86-64-asm.S b/tools/perf/bench/mem-memcpy-x86-64-asm.S
> index 1b9fef7efcdcc..e7b84aa43ab44 100644
> --- a/tools/perf/bench/mem-memcpy-x86-64-asm.S
> +++ b/tools/perf/bench/mem-memcpy-x86-64-asm.S
[ ... ]
> @@ -18,3 +18,27 @@
>   * the ELF stack should not be restricted at all and set it RWX.
>   */
>  .section .note.GNU-stack,"",@progbits
> +
> +/*
> + * We need to provide .note.gnu.property section with IBT and SHSTK,
> + * saying that this object supports the same CET properties as C code
> + * built with -fcf-protection. Otherwise static linking drops CET from
> + * the final perf binary when other objects are CET-enabled.
> + */
> +	.pushsection .note.gnu.property, "a"
> +	.p2align 3

[Severity: Medium]
Will this cause a Control Protection Exception (#CP) crash on IBT-capable
hardware when running `perf bench mem memcpy`?

Adding this section artificially claims IBT support and forces the linker to
enable CET on the final `perf` binary. However, `perf`'s local linkage headers
do not automatically emit `endbr64` instructions for `SYM_FUNC_START`.

When `do_memcpy()` in `tools/perf/bench/mem-functions.c` indirectly calls
these assembly entry points like `memcpy_orig`:

	fn(dst, src, size);

the hardware may detect the missing `endbr64` on the indirect branch target
and throw a #CP fault.

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260708045606.43649-1-tallison@redhat.com?part=3