From: Marco Elver <elver@google.com>
To: elver@google.com, Andrew Morton <akpm@linux-foundation.org>,
Kees Cook <keescook@chromium.org>
Cc: Guenter Roeck <linux@roeck-us.net>,
Peter Zijlstra <peterz@infradead.org>,
Mark Rutland <mark.rutland@arm.com>,
Steven Rostedt <rostedt@goodmis.org>,
Marc Zyngier <maz@kernel.org>,
Oliver Upton <oliver.upton@linux.dev>,
James Morse <james.morse@arm.com>,
Suzuki K Poulose <suzuki.poulose@arm.com>,
Zenghui Yu <yuzenghui@huawei.com>,
Catalin Marinas <catalin.marinas@arm.com>,
Will Deacon <will@kernel.org>,
Nathan Chancellor <nathan@kernel.org>,
Nick Desaulniers <ndesaulniers@google.com>,
Tom Rix <trix@redhat.com>, Miguel Ojeda <ojeda@kernel.org>,
linux-arm-kernel@lists.infradead.org, kvmarm@lists.linux.dev,
linux-kernel@vger.kernel.org, llvm@lists.linux.dev,
Dmitry Vyukov <dvyukov@google.com>,
Alexander Potapenko <glider@google.com>,
kasan-dev@googlegroups.com, linux-toolchains@vger.kernel.org
Subject: [PATCH v2 1/3] compiler_types: Introduce the Clang __preserve_most function attribute
Date: Fri, 4 Aug 2023 11:02:56 +0200 [thread overview]
Message-ID: <20230804090621.400-1-elver@google.com> (raw)
[1]: "On X86-64 and AArch64 targets, this attribute changes the calling
convention of a function. The preserve_most calling convention attempts
to make the code in the caller as unintrusive as possible. This
convention behaves identically to the C calling convention on how
arguments and return values are passed, but it uses a different set of
caller/callee-saved registers. This alleviates the burden of saving and
recovering a large register set before and after the call in the
caller."
[1] https://clang.llvm.org/docs/AttributeReference.html#preserve-most
Introduce the attribute to compiler_types.h as __preserve_most.
Use of this attribute results in better code generation for calls to
very rarely called functions, such as error-reporting functions, or
rarely executed slow paths.
Beware that the attribute conflicts with instrumentation calls inserted
on function entry which do not use __preserve_most themselves. Notably,
function tracing which assumes the normal C calling convention for the
given architecture. Where the attribute is supported, __preserve_most
will imply notrace. It is recommended to restrict use of the attribute
to functions that should or already disable tracing.
Signed-off-by: Marco Elver <elver@google.com>
---
v2:
* Imply notrace, to avoid any conflicts with tracing which is inserted
on function entry. See added comments.
---
include/linux/compiler_types.h | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 547ea1ff806e..12c4540335b7 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -106,6 +106,33 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
#define __cold
#endif
+/*
+ * On x86-64 and arm64 targets, __preserve_most changes the calling convention
+ * of a function to make the code in the caller as unintrusive as possible. This
+ * convention behaves identically to the C calling convention on how arguments
+ * and return values are passed, but uses a different set of caller- and callee-
+ * saved registers.
+ *
+ * The purpose is to alleviates the burden of saving and recovering a large
+ * register set before and after the call in the caller. This is beneficial for
+ * rarely taken slow paths, such as error-reporting functions that may be called
+ * from hot paths.
+ *
+ * Note: This may conflict with instrumentation inserted on function entry which
+ * does not use __preserve_most or equivalent convention (if in assembly). Since
+ * function tracing assumes the normal C calling convention, where the attribute
+ * is supported, __preserve_most implies notrace.
+ *
+ * Optional: not supported by gcc.
+ *
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#preserve-most
+ */
+#if __has_attribute(__preserve_most__)
+# define __preserve_most notrace __attribute__((__preserve_most__))
+#else
+# define __preserve_most
+#endif
+
/* Builtins */
/*
--
2.41.0.640.ga95def55d0-goog
next reply other threads:[~2023-08-04 9:10 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-08-04 9:02 Marco Elver [this message]
2023-08-04 9:02 ` [PATCH v2 2/3] list_debug: Introduce inline wrappers for debug checks Marco Elver
2023-08-04 16:03 ` Steven Rostedt
2023-08-04 17:49 ` Marco Elver
2023-08-04 17:57 ` Steven Rostedt
2023-08-04 17:59 ` Steven Rostedt
2023-08-04 18:08 ` Marco Elver
2023-08-04 18:19 ` Peter Zijlstra
2023-08-05 6:30 ` Miguel Ojeda
2023-08-04 9:02 ` [PATCH v2 3/3] list_debug: Introduce CONFIG_DEBUG_LIST_MINIMAL Marco Elver
2023-08-04 15:58 ` [PATCH v2 1/3] compiler_types: Introduce the Clang __preserve_most function attribute Steven Rostedt
2023-08-04 18:14 ` Peter Zijlstra
2023-08-05 6:35 ` Miguel Ojeda
2023-08-07 11:41 ` Florian Weimer
2023-08-07 12:24 ` Marco Elver
2023-08-07 12:36 ` Florian Weimer
2023-08-07 13:07 ` Marco Elver
2023-08-07 15:06 ` Peter Zijlstra
2023-08-07 12:38 ` Jakub Jelinek
2023-08-07 12:43 ` Florian Weimer
2023-08-07 13:06 ` Jakub Jelinek
2023-08-07 12:31 ` Peter Zijlstra
2023-08-08 2:16 ` Steven Rostedt
2023-08-07 15:27 ` Nick Desaulniers
2023-08-08 10:57 ` Peter Zijlstra
2023-08-08 11:41 ` Florian Weimer
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230804090621.400-1-elver@google.com \
--to=elver@google.com \
--cc=akpm@linux-foundation.org \
--cc=catalin.marinas@arm.com \
--cc=dvyukov@google.com \
--cc=glider@google.com \
--cc=james.morse@arm.com \
--cc=kasan-dev@googlegroups.com \
--cc=keescook@chromium.org \
--cc=kvmarm@lists.linux.dev \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-toolchains@vger.kernel.org \
--cc=linux@roeck-us.net \
--cc=llvm@lists.linux.dev \
--cc=mark.rutland@arm.com \
--cc=maz@kernel.org \
--cc=nathan@kernel.org \
--cc=ndesaulniers@google.com \
--cc=ojeda@kernel.org \
--cc=oliver.upton@linux.dev \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=suzuki.poulose@arm.com \
--cc=trix@redhat.com \
--cc=will@kernel.org \
--cc=yuzenghui@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).