From: Denys Vlasenko <dvlasenk@redhat.com>
To: Ingo Molnar <mingo@kernel.org>
Cc: Denys Vlasenko <dvlasenk@redhat.com>, Thomas Graf <tgraf@suug.ch>,
Peter Zijlstra <peterz@infradead.org>,
David Rientjes <rientjes@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org
Subject: [PATCH] force inlining of unaligned byteswap operations
Date: Thu, 4 Feb 2016 20:45:36 +0100 [thread overview]
Message-ID: <1454615136-32308-3-git-send-email-dvlasenk@redhat.com> (raw)
In-Reply-To: <1454615136-32308-1-git-send-email-dvlasenk@redhat.com>
Sometimes gcc mysteriously doesn't inline
very small functions we expect to be inlined. See
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122
With this .config:
http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os,
the following functions get deinlined many times.
Examples of disassembly:
<get_unaligned_be16> (24 copies, 108 calls):
66 8b 07 mov (%rdi),%ax
55 push %rbp
48 89 e5 mov %rsp,%rbp
86 e0 xchg %ah,%al
5d pop %rbp
c3 retq
<get_unaligned_be32> (25 copies, 181 calls):
8b 07 mov (%rdi),%eax
55 push %rbp
48 89 e5 mov %rsp,%rbp
0f c8 bswap %eax
5d pop %rbp
c3 retq
<get_unaligned_be64> (23 copies, 94 calls):
48 8b 07 mov (%rdi),%rax
55 push %rbp
48 89 e5 mov %rsp,%rbp
48 0f c8 bswap %rax
5d pop %rbp
c3 retq
<put_unaligned_be16> (2 copies, 11 calls):
89 f8 mov %edi,%eax
55 push %rbp
c1 ef 08 shr $0x8,%edi
c1 e0 08 shl $0x8,%eax
09 c7 or %eax,%edi
48 89 e5 mov %rsp,%rbp
66 89 3e mov %di,(%rsi)
<put_unaligned_be32> (8 copies, 43 calls):
55 push %rbp
0f cf bswap %edi
89 3e mov %edi,(%rsi)
48 89 e5 mov %rsp,%rbp
5d pop %rbp
c3 retq
<put_unaligned_be64> (26 copies, 157 calls):
55 push %rbp
48 0f cf bswap %rdi
48 89 3e mov %rdi,(%rsi)
48 89 e5 mov %rsp,%rbp
5d pop %rbp
c3 retq
This patch fixes this via s/inline/__always_inline/.
It only affects arches with efficient unaligned access insns, such as x86.
(arched which lack such ops do not include linux/unaligned/access_ok.h)
Code size decrease after the patch is ~8.5k:
text data bss dec hex filename
92197848 20826112 36417536 149441496 8e84bd8 vmlinux
92189231 20826144 36417536 149432911 8e82a4f vmlinux6_unaligned_be_after
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-kernel@vger.kernel.org
---
include/linux/unaligned/access_ok.h | 24 ++++++++++++------------
1 file changed, 12 insertions(+), 12 deletions(-)
diff --git a/include/linux/unaligned/access_ok.h b/include/linux/unaligned/access_ok.h
index 99c1b4d..33383ca 100644
--- a/include/linux/unaligned/access_ok.h
+++ b/include/linux/unaligned/access_ok.h
@@ -4,62 +4,62 @@
#include <linux/kernel.h>
#include <asm/byteorder.h>
-static inline u16 get_unaligned_le16(const void *p)
+static __always_inline u16 get_unaligned_le16(const void *p)
{
return le16_to_cpup((__le16 *)p);
}
-static inline u32 get_unaligned_le32(const void *p)
+static __always_inline u32 get_unaligned_le32(const void *p)
{
return le32_to_cpup((__le32 *)p);
}
-static inline u64 get_unaligned_le64(const void *p)
+static __always_inline u64 get_unaligned_le64(const void *p)
{
return le64_to_cpup((__le64 *)p);
}
-static inline u16 get_unaligned_be16(const void *p)
+static __always_inline u16 get_unaligned_be16(const void *p)
{
return be16_to_cpup((__be16 *)p);
}
-static inline u32 get_unaligned_be32(const void *p)
+static __always_inline u32 get_unaligned_be32(const void *p)
{
return be32_to_cpup((__be32 *)p);
}
-static inline u64 get_unaligned_be64(const void *p)
+static __always_inline u64 get_unaligned_be64(const void *p)
{
return be64_to_cpup((__be64 *)p);
}
-static inline void put_unaligned_le16(u16 val, void *p)
+static __always_inline void put_unaligned_le16(u16 val, void *p)
{
*((__le16 *)p) = cpu_to_le16(val);
}
-static inline void put_unaligned_le32(u32 val, void *p)
+static __always_inline void put_unaligned_le32(u32 val, void *p)
{
*((__le32 *)p) = cpu_to_le32(val);
}
-static inline void put_unaligned_le64(u64 val, void *p)
+static __always_inline void put_unaligned_le64(u64 val, void *p)
{
*((__le64 *)p) = cpu_to_le64(val);
}
-static inline void put_unaligned_be16(u16 val, void *p)
+static __always_inline void put_unaligned_be16(u16 val, void *p)
{
*((__be16 *)p) = cpu_to_be16(val);
}
-static inline void put_unaligned_be32(u32 val, void *p)
+static __always_inline void put_unaligned_be32(u32 val, void *p)
{
*((__be32 *)p) = cpu_to_be32(val);
}
-static inline void put_unaligned_be64(u64 val, void *p)
+static __always_inline void put_unaligned_be64(u64 val, void *p)
{
*((__be64 *)p) = cpu_to_be64(val);
}
--
1.8.1.4
next prev parent reply other threads:[~2016-02-04 19:45 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-02-04 19:45 [PATCH] asm-generic: force inlining of some atomic_long operations Denys Vlasenko
2016-02-04 19:45 ` [PATCH] force inlining of some byteswap operations Denys Vlasenko
2016-02-05 7:28 ` Ingo Molnar
2016-04-13 3:36 ` This patch triggers a bad gcc bug (was Re: [PATCH] force inlining of some byteswap operations) Josh Poimboeuf
2016-04-13 12:12 ` Denys Vlasenko
2016-04-13 12:36 ` Josh Poimboeuf
2016-04-13 15:15 ` Josh Poimboeuf
2016-04-13 16:55 ` James Bottomley
2016-04-13 17:10 ` Josh Poimboeuf
2016-04-14 15:29 ` Denys Vlasenko
2016-04-14 15:57 ` Josh Poimboeuf
2016-04-14 17:09 ` Denys Vlasenko
2016-04-15 5:45 ` Ingo Molnar
2016-04-15 13:47 ` Josh Poimboeuf
2016-04-15 22:20 ` Josh Poimboeuf
2016-04-16 9:03 ` Ingo Molnar
2016-04-18 13:39 ` Josh Poimboeuf
2016-04-18 14:07 ` Arnd Bergmann
2016-04-18 14:12 ` Josh Poimboeuf
2016-04-18 14:21 ` Arnd Bergmann
2016-04-19 8:52 ` Ingo Molnar
2016-04-19 13:56 ` [PATCH] scsi: fc: force inlining of wwn conversion functions Josh Poimboeuf
2016-04-22 23:17 ` Quinn Tran
2016-04-25 16:07 ` Josh Poimboeuf
2016-04-26 2:40 ` Martin K. Petersen
2016-04-26 3:37 ` James Bottomley
2016-04-26 7:22 ` Arnd Bergmann
2016-04-26 8:35 ` Christoph Hellwig
2016-04-26 10:05 ` Arnd Bergmann
2016-04-26 13:06 ` Martin K. Petersen
2016-04-26 15:58 ` Arnd Bergmann
2016-04-26 22:36 ` James Bottomley
2016-04-27 0:44 ` Martin K. Petersen
2016-04-27 11:05 ` Martin Jambor
2016-04-27 21:34 ` Arnd Bergmann
2016-04-28 14:58 ` Chris Metcalf
2016-04-28 15:23 ` Arnd Bergmann
2016-04-28 15:48 ` Chris Metcalf
2016-04-27 22:00 ` [PATCH, RFT] byteswap: try to avoid __builtin_constant_p gcc bug Arnd Bergmann
2016-04-27 22:11 ` Josh Poimboeuf
2016-04-28 16:27 ` Quinn Tran
2016-04-16 7:42 ` This patch triggers a bad gcc bug (was Re: [PATCH] force inlining of some byteswap operations) Arnd Bergmann
2016-04-18 13:22 ` Josh Poimboeuf
2016-02-04 19:45 ` Denys Vlasenko [this message]
2016-02-05 7:28 ` [PATCH] force inlining of unaligned byteswap operations Ingo Molnar
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=1454615136-32308-3-git-send-email-dvlasenk@redhat.com \
--to=dvlasenk@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--cc=tgraf@suug.ch \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).