linux-arm-kernel.lists.infradead.org archive mirror
 help / color / mirror / Atom feed
From: Arnd Bergmann <arnd@kernel.org>
To: linux-arch@vger.kernel.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
	Vineet Gupta <vgupta@synopsys.com>, Arnd Bergmann <arnd@arndb.de>,
	Russell King <linux@armlinux.org.uk>,
	Nathan Chancellor <nathan@kernel.org>,
	Nick Desaulniers <ndesaulniers@google.com>,
	linux-arm-kernel@lists.infradead.org,
	linux-kernel@vger.kernel.org, clang-built-linux@googlegroups.com
Subject: [PATCH v2 06/13] asm-generic: unaligned: remove byteshift helpers
Date: Fri, 14 May 2021 12:00:54 +0200	[thread overview]
Message-ID: <20210514100106.3404011-7-arnd@kernel.org> (raw)
In-Reply-To: <20210514100106.3404011-1-arnd@kernel.org>

From: Arnd Bergmann <arnd@arndb.de>

In theory, compilers should be able to work this out themselves so we
can use a simpler version based on the swab() helpers.

I have verified that this works on all supported compiler versions
(gcc-4.9 and up, clang-10 and up). Looking at the object code produced by
gcc-11, I found that the impact is mostly a change in inlining decisions
that lead to slightly larger code.

In other cases, this version produces explicit byte swaps in place of
separate byte access, or comparing against pre-swapped constants.

While the source code is clearly simpler, I have not seen an indication
of the new version actually producing better code on Arm, so maybe
we want to skip this after all. From what I can tell, gcc recognizes
the byteswap pattern in the byteshift.h header and can turn it into
explicit instructions, but it does not turn a __builtin_bswap32() back
into individual bytes when that would result in better output, e.g.
when storing a byte-reversed constant.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/include/asm/unaligned.h       |  2 -
 include/asm-generic/unaligned.h        |  2 -
 include/linux/unaligned/be_byteshift.h | 71 --------------------------
 include/linux/unaligned/be_struct.h    | 30 +++++++++++
 include/linux/unaligned/le_byteshift.h | 71 --------------------------
 include/linux/unaligned/le_struct.h    | 30 +++++++++++
 6 files changed, 60 insertions(+), 146 deletions(-)
 delete mode 100644 include/linux/unaligned/be_byteshift.h
 delete mode 100644 include/linux/unaligned/le_byteshift.h

diff --git a/arch/arm/include/asm/unaligned.h b/arch/arm/include/asm/unaligned.h
index ab905ffcf193..3c5248fb4cdc 100644
--- a/arch/arm/include/asm/unaligned.h
+++ b/arch/arm/include/asm/unaligned.h
@@ -10,13 +10,11 @@
 
 #if defined(__LITTLE_ENDIAN)
 # include <linux/unaligned/le_struct.h>
-# include <linux/unaligned/be_byteshift.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_le
 # define put_unaligned	__put_unaligned_le
 #elif defined(__BIG_ENDIAN)
 # include <linux/unaligned/be_struct.h>
-# include <linux/unaligned/le_byteshift.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be
diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h
index 374c940e9be1..d79df721ae60 100644
--- a/include/asm-generic/unaligned.h
+++ b/include/asm-generic/unaligned.h
@@ -16,7 +16,6 @@
 #if defined(__LITTLE_ENDIAN)
 # ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 #  include <linux/unaligned/le_struct.h>
-#  include <linux/unaligned/be_byteshift.h>
 # endif
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_le
@@ -24,7 +23,6 @@
 #elif defined(__BIG_ENDIAN)
 # ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 #  include <linux/unaligned/be_struct.h>
-#  include <linux/unaligned/le_byteshift.h>
 # endif
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_be
diff --git a/include/linux/unaligned/be_byteshift.h b/include/linux/unaligned/be_byteshift.h
deleted file mode 100644
index c43ff5918c8a..000000000000
--- a/include/linux/unaligned/be_byteshift.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_UNALIGNED_BE_BYTESHIFT_H
-#define _LINUX_UNALIGNED_BE_BYTESHIFT_H
-
-#include <linux/types.h>
-
-static inline u16 __get_unaligned_be16(const u8 *p)
-{
-	return p[0] << 8 | p[1];
-}
-
-static inline u32 __get_unaligned_be32(const u8 *p)
-{
-	return p[0] << 24 | p[1] << 16 | p[2] << 8 | p[3];
-}
-
-static inline u64 __get_unaligned_be64(const u8 *p)
-{
-	return (u64)__get_unaligned_be32(p) << 32 |
-	       __get_unaligned_be32(p + 4);
-}
-
-static inline void __put_unaligned_be16(u16 val, u8 *p)
-{
-	*p++ = val >> 8;
-	*p++ = val;
-}
-
-static inline void __put_unaligned_be32(u32 val, u8 *p)
-{
-	__put_unaligned_be16(val >> 16, p);
-	__put_unaligned_be16(val, p + 2);
-}
-
-static inline void __put_unaligned_be64(u64 val, u8 *p)
-{
-	__put_unaligned_be32(val >> 32, p);
-	__put_unaligned_be32(val, p + 4);
-}
-
-static inline u16 get_unaligned_be16(const void *p)
-{
-	return __get_unaligned_be16(p);
-}
-
-static inline u32 get_unaligned_be32(const void *p)
-{
-	return __get_unaligned_be32(p);
-}
-
-static inline u64 get_unaligned_be64(const void *p)
-{
-	return __get_unaligned_be64(p);
-}
-
-static inline void put_unaligned_be16(u16 val, void *p)
-{
-	__put_unaligned_be16(val, p);
-}
-
-static inline void put_unaligned_be32(u32 val, void *p)
-{
-	__put_unaligned_be32(val, p);
-}
-
-static inline void put_unaligned_be64(u64 val, void *p)
-{
-	__put_unaligned_be64(val, p);
-}
-
-#endif /* _LINUX_UNALIGNED_BE_BYTESHIFT_H */
diff --git a/include/linux/unaligned/be_struct.h b/include/linux/unaligned/be_struct.h
index 15ea503a13fc..76d9fe297c33 100644
--- a/include/linux/unaligned/be_struct.h
+++ b/include/linux/unaligned/be_struct.h
@@ -34,4 +34,34 @@ static inline void put_unaligned_be64(u64 val, void *p)
 	__put_unaligned_cpu64(val, p);
 }
 
+static inline u16 get_unaligned_le16(const void *p)
+{
+	return swab16(__get_unaligned_cpu16((const u8 *)p));
+}
+
+static inline u32 get_unaligned_le32(const void *p)
+{
+	return swab32(__get_unaligned_cpu32((const u8 *)p));
+}
+
+static inline u64 get_unaligned_le64(const void *p)
+{
+	return swab64(__get_unaligned_cpu64((const u8 *)p));
+}
+
+static inline void put_unaligned_le16(u16 val, void *p)
+{
+	__put_unaligned_cpu16(swab16(val), p);
+}
+
+static inline void put_unaligned_le32(u32 val, void *p)
+{
+	__put_unaligned_cpu32(swab32(val), p);
+}
+
+static inline void put_unaligned_le64(u64 val, void *p)
+{
+	__put_unaligned_cpu64(swab64(val), p);
+}
+
 #endif /* _LINUX_UNALIGNED_BE_STRUCT_H */
diff --git a/include/linux/unaligned/le_byteshift.h b/include/linux/unaligned/le_byteshift.h
deleted file mode 100644
index 2248dcb0df76..000000000000
--- a/include/linux/unaligned/le_byteshift.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_UNALIGNED_LE_BYTESHIFT_H
-#define _LINUX_UNALIGNED_LE_BYTESHIFT_H
-
-#include <linux/types.h>
-
-static inline u16 __get_unaligned_le16(const u8 *p)
-{
-	return p[0] | p[1] << 8;
-}
-
-static inline u32 __get_unaligned_le32(const u8 *p)
-{
-	return p[0] | p[1] << 8 | p[2] << 16 | p[3] << 24;
-}
-
-static inline u64 __get_unaligned_le64(const u8 *p)
-{
-	return (u64)__get_unaligned_le32(p + 4) << 32 |
-	       __get_unaligned_le32(p);
-}
-
-static inline void __put_unaligned_le16(u16 val, u8 *p)
-{
-	*p++ = val;
-	*p++ = val >> 8;
-}
-
-static inline void __put_unaligned_le32(u32 val, u8 *p)
-{
-	__put_unaligned_le16(val >> 16, p + 2);
-	__put_unaligned_le16(val, p);
-}
-
-static inline void __put_unaligned_le64(u64 val, u8 *p)
-{
-	__put_unaligned_le32(val >> 32, p + 4);
-	__put_unaligned_le32(val, p);
-}
-
-static inline u16 get_unaligned_le16(const void *p)
-{
-	return __get_unaligned_le16(p);
-}
-
-static inline u32 get_unaligned_le32(const void *p)
-{
-	return __get_unaligned_le32(p);
-}
-
-static inline u64 get_unaligned_le64(const void *p)
-{
-	return __get_unaligned_le64(p);
-}
-
-static inline void put_unaligned_le16(u16 val, void *p)
-{
-	__put_unaligned_le16(val, p);
-}
-
-static inline void put_unaligned_le32(u32 val, void *p)
-{
-	__put_unaligned_le32(val, p);
-}
-
-static inline void put_unaligned_le64(u64 val, void *p)
-{
-	__put_unaligned_le64(val, p);
-}
-
-#endif /* _LINUX_UNALIGNED_LE_BYTESHIFT_H */
diff --git a/include/linux/unaligned/le_struct.h b/include/linux/unaligned/le_struct.h
index 9977987883a6..22f90a4afaa5 100644
--- a/include/linux/unaligned/le_struct.h
+++ b/include/linux/unaligned/le_struct.h
@@ -34,4 +34,34 @@ static inline void put_unaligned_le64(u64 val, void *p)
 	__put_unaligned_cpu64(val, p);
 }
 
+static inline u16 get_unaligned_be16(const void *p)
+{
+	return swab16(__get_unaligned_cpu16((const u8 *)p));
+}
+
+static inline u32 get_unaligned_be32(const void *p)
+{
+	return swab32(__get_unaligned_cpu32((const u8 *)p));
+}
+
+static inline u64 get_unaligned_be64(const void *p)
+{
+	return swab64(__get_unaligned_cpu64((const u8 *)p));
+}
+
+static inline void put_unaligned_be16(u16 val, void *p)
+{
+	__put_unaligned_cpu16(swab16(val), p);
+}
+
+static inline void put_unaligned_be32(u32 val, void *p)
+{
+	__put_unaligned_cpu32(swab32(val), p);
+}
+
+static inline void put_unaligned_be64(u64 val, void *p)
+{
+	__put_unaligned_cpu64(swab64(val), p);
+}
+
 #endif /* _LINUX_UNALIGNED_LE_STRUCT_H */
-- 
2.29.2


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

  reply	other threads:[~2021-05-14 10:06 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-14 10:00 [PATCH v2 00/13] Unify asm/unaligned.h around struct helper Arnd Bergmann
2021-05-14 10:00 ` Arnd Bergmann [this message]
2021-05-14 10:00 ` [PATCH v2 07/13] asm-generic: unaligned always use struct helpers Arnd Bergmann
2021-05-17 21:53   ` Eric Biggers
2021-05-18  7:25     ` Arnd Bergmann
2021-05-18 14:56       ` Linus Torvalds
2021-05-18 15:41         ` Arnd Bergmann
2021-05-18 16:12           ` Linus Torvalds
2021-05-18 18:09             ` Jason A. Donenfeld
2021-05-18 20:51             ` Arnd Bergmann
2021-05-18 21:31               ` Eric Biggers
2021-05-18 21:14         ` David Laight
2021-05-14 17:32 ` [PATCH v2 00/13] Unify asm/unaligned.h around struct helper Linus Torvalds
2021-05-14 18:51   ` Vineet Gupta
2021-05-14 19:22     ` Linus Torvalds
2021-05-14 19:45       ` Vineet Gupta
2021-05-14 20:19         ` Linus Torvalds
2021-05-14 19:31   ` Arnd Bergmann

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=20210514100106.3404011-7-arnd@kernel.org \
    --to=arnd@kernel.org \
    --cc=arnd@arndb.de \
    --cc=clang-built-linux@googlegroups.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux@armlinux.org.uk \
    --cc=nathan@kernel.org \
    --cc=ndesaulniers@google.com \
    --cc=torvalds@linux-foundation.org \
    --cc=vgupta@synopsys.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).