From: Ingo Molnar <mingo@kernel.org> To: Michal Hocko <mhocko@kernel.org> Cc: LKML <linux-kernel@vger.kernel.org>, Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>, Thomas Gleixner <tglx@linutronix.de>, "H. Peter Anvin" <hpa@zytor.com>, "David S. Miller" <davem@davemloft.net>, Tony Luck <tony.luck@intel.com>, Andrew Morton <akpm@linux-foundation.org>, Chris Zankel <chris@zankel.net>, Max Filippov <jcmvbkbc@gmail.com>, x86@kernel.org, linux-alpha@vger.kernel.org, linux-ia64@vger.kernel.org, linux-s390@vger.kernel.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org, linux-xtensa@linux-xtensa.org, linux-arch@vger.kernel.org, Michal Hocko <mhocko@suse.com>, Linus Torvalds <torvalds@linux-foundation.org>, "Paul E. McKenney" <paulmck@us.ibm.com>, Peter Zijlstra <a.p.zijlstra@chello.nl> Subject: Re: [RFC 10/12] x86, rwsem: simplify __down_write Date: Wed, 03 Feb 2016 08:10:16 +0000 [thread overview] Message-ID: <20160203081016.GD32652@gmail.com> (raw) In-Reply-To: <1454444369-2146-11-git-send-email-mhocko@kernel.org> * Michal Hocko <mhocko@kernel.org> wrote: > From: Michal Hocko <mhocko@suse.com> > > x86 implementation of __down_write is using inline asm to optimize the > code flow. This however requires that it has go over an additional hop > for the slow path call_rwsem_down_write_failed which has to > save_common_regs/restore_common_regs to preserve the calling convention. > This, however doesn't add much because the fast path only saves one > register push/pop (rdx) when compared to the generic implementation: > > Before: > 0000000000000019 <down_write>: > 19: e8 00 00 00 00 callq 1e <down_write+0x5> > 1e: 55 push %rbp > 1f: 48 ba 01 00 00 00 ff movabs $0xffffffff00000001,%rdx > 26: ff ff ff > 29: 48 89 f8 mov %rdi,%rax > 2c: 48 89 e5 mov %rsp,%rbp > 2f: f0 48 0f c1 10 lock xadd %rdx,(%rax) > 34: 85 d2 test %edx,%edx > 36: 74 05 je 3d <down_write+0x24> > 38: e8 00 00 00 00 callq 3d <down_write+0x24> > 3d: 65 48 8b 04 25 00 00 mov %gs:0x0,%rax > 44: 00 00 > 46: 5d pop %rbp > 47: 48 89 47 38 mov %rax,0x38(%rdi) > 4b: c3 retq > > After: > 0000000000000019 <down_write>: > 19: e8 00 00 00 00 callq 1e <down_write+0x5> > 1e: 55 push %rbp > 1f: 48 b8 01 00 00 00 ff movabs $0xffffffff00000001,%rax > 26: ff ff ff > 29: 48 89 e5 mov %rsp,%rbp > 2c: 53 push %rbx > 2d: 48 89 fb mov %rdi,%rbx > 30: f0 48 0f c1 07 lock xadd %rax,(%rdi) > 35: 48 85 c0 test %rax,%rax > 38: 74 05 je 3f <down_write+0x26> > 3a: e8 00 00 00 00 callq 3f <down_write+0x26> > 3f: 65 48 8b 04 25 00 00 mov %gs:0x0,%rax > 46: 00 00 > 48: 48 89 43 38 mov %rax,0x38(%rbx) > 4c: 5b pop %rbx > 4d: 5d pop %rbp > 4e: c3 retq I'm not convinced about the removal of this optimization at all. > This doesn't seem to justify the code obfuscation and complexity. Use > the generic implementation instead. > > Signed-off-by: Michal Hocko <mhocko@suse.com> > --- > arch/x86/include/asm/rwsem.h | 17 +++++------------ > arch/x86/lib/rwsem.S | 9 --------- > 2 files changed, 5 insertions(+), 21 deletions(-) Turn the argument around, would we be willing to save two instructions off the fast path of a commonly used locking construct, with such a simple optimization: > arch/x86/include/asm/rwsem.h | 17 ++++++++++++----- > arch/x86/lib/rwsem.S | 9 +++++++++ > 2 files changed, 21 insertions(+), 5 deletions(-) ? Yes! So, if you want to remove the assembly code - can we achieve that without hurting the generated fast path, using the compiler? Thanks, Ingo
WARNING: multiple messages have this Message-ID (diff)
From: Ingo Molnar <mingo@kernel.org> To: Michal Hocko <mhocko@kernel.org> Cc: LKML <linux-kernel@vger.kernel.org>, Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>, Thomas Gleixner <tglx@linutronix.de>, "H. Peter Anvin" <hpa@zytor.com>, "David S. Miller" <davem@davemloft.net>, Tony Luck <tony.luck@intel.com>, Andrew Morton <akpm@linux-foundation.org>, Chris Zankel <chris@zankel.net>, Max Filippov <jcmvbkbc@gmail.com>, x86@kernel.org, linux-alpha@vger.kernel.org, linux-ia64@vger.kernel.org, linux-s390@vger.kernel.org, linux-sh@vger.kernel.org, sparclinux@vger.kernel.org, linux-xtensa@linux-xtensa.org, linux-arch@vger.kernel.org, Michal Hocko <mhocko@suse.com>, Linus Torvalds <torvalds@linux-foundation.org>, "Paul E. McKenney" <paulmck@us.ibm.com>, Peter Zijlstra <a.p.zijlstra@chello.nl> Subject: Re: [RFC 10/12] x86, rwsem: simplify __down_write Date: Wed, 3 Feb 2016 09:10:16 +0100 [thread overview] Message-ID: <20160203081016.GD32652@gmail.com> (raw) In-Reply-To: <1454444369-2146-11-git-send-email-mhocko@kernel.org> * Michal Hocko <mhocko@kernel.org> wrote: > From: Michal Hocko <mhocko@suse.com> > > x86 implementation of __down_write is using inline asm to optimize the > code flow. This however requires that it has go over an additional hop > for the slow path call_rwsem_down_write_failed which has to > save_common_regs/restore_common_regs to preserve the calling convention. > This, however doesn't add much because the fast path only saves one > register push/pop (rdx) when compared to the generic implementation: > > Before: > 0000000000000019 <down_write>: > 19: e8 00 00 00 00 callq 1e <down_write+0x5> > 1e: 55 push %rbp > 1f: 48 ba 01 00 00 00 ff movabs $0xffffffff00000001,%rdx > 26: ff ff ff > 29: 48 89 f8 mov %rdi,%rax > 2c: 48 89 e5 mov %rsp,%rbp > 2f: f0 48 0f c1 10 lock xadd %rdx,(%rax) > 34: 85 d2 test %edx,%edx > 36: 74 05 je 3d <down_write+0x24> > 38: e8 00 00 00 00 callq 3d <down_write+0x24> > 3d: 65 48 8b 04 25 00 00 mov %gs:0x0,%rax > 44: 00 00 > 46: 5d pop %rbp > 47: 48 89 47 38 mov %rax,0x38(%rdi) > 4b: c3 retq > > After: > 0000000000000019 <down_write>: > 19: e8 00 00 00 00 callq 1e <down_write+0x5> > 1e: 55 push %rbp > 1f: 48 b8 01 00 00 00 ff movabs $0xffffffff00000001,%rax > 26: ff ff ff > 29: 48 89 e5 mov %rsp,%rbp > 2c: 53 push %rbx > 2d: 48 89 fb mov %rdi,%rbx > 30: f0 48 0f c1 07 lock xadd %rax,(%rdi) > 35: 48 85 c0 test %rax,%rax > 38: 74 05 je 3f <down_write+0x26> > 3a: e8 00 00 00 00 callq 3f <down_write+0x26> > 3f: 65 48 8b 04 25 00 00 mov %gs:0x0,%rax > 46: 00 00 > 48: 48 89 43 38 mov %rax,0x38(%rbx) > 4c: 5b pop %rbx > 4d: 5d pop %rbp > 4e: c3 retq I'm not convinced about the removal of this optimization at all. > This doesn't seem to justify the code obfuscation and complexity. Use > the generic implementation instead. > > Signed-off-by: Michal Hocko <mhocko@suse.com> > --- > arch/x86/include/asm/rwsem.h | 17 +++++------------ > arch/x86/lib/rwsem.S | 9 --------- > 2 files changed, 5 insertions(+), 21 deletions(-) Turn the argument around, would we be willing to save two instructions off the fast path of a commonly used locking construct, with such a simple optimization: > arch/x86/include/asm/rwsem.h | 17 ++++++++++++----- > arch/x86/lib/rwsem.S | 9 +++++++++ > 2 files changed, 21 insertions(+), 5 deletions(-) ? Yes! So, if you want to remove the assembly code - can we achieve that without hurting the generated fast path, using the compiler? Thanks, Ingo
next prev parent reply other threads:[~2016-02-03 8:10 UTC|newest] Thread overview: 64+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-02-02 20:19 [RFC 0/12] introduce down_write_killable for rw_semaphore Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 01/12] locking, rwsem: get rid of __down_write_nested Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 02/12] locking, rwsem: drop explicit memory barriers Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 03/12] locking, rwsem: introduce basis for down_write_killable Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 04/12] alpha, rwsem: provide __down_write_killable Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 05/12] ia64, " Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 06/12] s390, " Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 07/12] sh, " Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-03 11:19 ` Sergei Shtylyov 2016-02-03 11:19 ` Sergei Shtylyov 2016-02-03 12:11 ` Michal Hocko 2016-02-03 12:11 ` Michal Hocko 2016-02-02 20:19 ` [RFC 08/12] sparc, " Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 09/12] xtensa, " Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-02 20:19 ` [RFC 10/12] x86, rwsem: simplify __down_write Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-03 8:10 ` Ingo Molnar [this message] 2016-02-03 8:10 ` Ingo Molnar 2016-02-03 12:10 ` Michal Hocko 2016-02-03 12:10 ` Michal Hocko 2016-06-03 16:13 ` Peter Zijlstra 2016-06-03 16:13 ` Peter Zijlstra 2016-06-03 22:34 ` Peter Zijlstra 2016-06-03 22:34 ` Peter Zijlstra 2016-06-09 14:40 ` David Howells 2016-06-09 14:40 ` David Howells 2016-06-09 17:36 ` Peter Zijlstra 2016-06-09 17:36 ` Peter Zijlstra 2016-06-10 16:39 ` Paul E. McKenney 2016-06-10 16:39 ` Paul E. McKenney 2016-02-02 20:19 ` [RFC 11/12] x86, rwsem: provide __down_write_killable Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-17 16:41 ` [RFC 11/12 v1] " Michal Hocko 2016-02-17 16:41 ` Michal Hocko 2016-02-17 16:41 ` Michal Hocko 2016-02-17 16:41 ` Michal Hocko 2016-02-02 20:19 ` [RFC 12/12] locking, rwsem: provide down_write_killable Michal Hocko 2016-02-02 20:19 ` Michal Hocko 2016-02-19 12:15 ` [RFC 0/12] introduce down_write_killable for rw_semaphore Michal Hocko 2016-02-19 12:15 ` Michal Hocko 2016-03-09 12:18 ` Ingo Molnar 2016-03-09 12:18 ` Ingo Molnar 2016-03-09 12:56 ` Michal Hocko 2016-03-09 12:56 ` Michal Hocko 2016-03-09 13:17 ` Ingo Molnar 2016-03-09 13:17 ` Ingo Molnar 2016-03-09 13:28 ` Michal Hocko 2016-03-09 13:28 ` Michal Hocko 2016-03-09 13:43 ` Ingo Molnar 2016-03-09 13:43 ` Ingo Molnar 2016-03-09 14:41 ` Michal Hocko 2016-03-09 14:41 ` Michal Hocko 2016-03-10 10:24 ` Ingo Molnar 2016-03-10 10:24 ` 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=20160203081016.GD32652@gmail.com \ --to=mingo@kernel.org \ --cc=a.p.zijlstra@chello.nl \ --cc=akpm@linux-foundation.org \ --cc=chris@zankel.net \ --cc=davem@davemloft.net \ --cc=hpa@zytor.com \ --cc=jcmvbkbc@gmail.com \ --cc=linux-alpha@vger.kernel.org \ --cc=linux-arch@vger.kernel.org \ --cc=linux-ia64@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-s390@vger.kernel.org \ --cc=linux-sh@vger.kernel.org \ --cc=linux-xtensa@linux-xtensa.org \ --cc=mhocko@kernel.org \ --cc=mhocko@suse.com \ --cc=mingo@redhat.com \ --cc=paulmck@us.ibm.com \ --cc=peterz@infradead.org \ --cc=sparclinux@vger.kernel.org \ --cc=tglx@linutronix.de \ --cc=tony.luck@intel.com \ --cc=torvalds@linux-foundation.org \ --cc=x86@kernel.org \ /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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.