From: Pranith Kumar <bobby.prani@gmail.com>
To: paulmck@linux.vnet.ibm.com, josh@joshtriplett.org,
davidshan@tencent.com, cl@linux.com
Cc: linux-kernel@vger.kernel.org
Subject: [PATCH 1/1] rcu: use __this_cpu_read helper instead of per_cpu_ptr(p, raw_smp_processor_id())
Date: Thu, 19 Jun 2014 16:12:46 -0400 [thread overview]
Message-ID: <53A3443E.8010102@gmail.com> (raw)
Use __this_cpu_read() instead of per_cpu_ptr() for optimized access.
Last time when Shan Wei posted this, you wanted before/after code for ARM and x86.
(http://lkml.iu.edu//hypermail/linux/kernel/1211.2/00498.html).
There are few other location which use per_cpu_ops instead of this_cpu_ops. I
can convert them accordingly if you are accept this :)
Using gcc (Ubuntu/Linaro 4.7.3-12ubuntu1) 4.7.3, I get (trimmed to relevant assembly, from make kernel/rcu/tree.s)
ARMv7 per_cpu_ptr():
force_quiescent_state:
mov r3, sp @,
bic r1, r3, #8128 @ tmp171,,
ldr r2, .L98 @ tmp169,
bic r1, r1, #63 @ tmp170, tmp171,
ldr r3, [r0, #220] @ __ptr, rsp_6(D)->rda
ldr r1, [r1, #20] @ D.35903_68->cpu, D.35903_68->cpu
mov r6, r0 @ rsp, rsp
ldr r2, [r2, r1, asl #2] @ tmp173, __per_cpu_offset
add r3, r3, r2 @ tmp175, __ptr, tmp173
ldr r5, [r3, #12] @ rnp_old, D.29162_13->mynode
ARMv7 using __this_cpu_read():
force_quiescent_state:
ldr r3, [r0, #220] @ rsp_7(D)->rda, rsp_7(D)->rda
mov r6, r0 @ rsp, rsp
add r3, r3, #12 @ __ptr, rsp_7(D)->rda,
ldr r5, [r2, r3] @ rnp_old, *D.29176_13
Using gcc 4.8.2:
x86_64 per_cpu_ptr():
movl %gs:cpu_number,%edx # cpu_number, pscr_ret__
movslq %edx, %rdx # pscr_ret__, pscr_ret__
movq __per_cpu_offset(,%rdx,8), %rdx # __per_cpu_offset, tmp93
movq %rdi, %r13 # rsp, rsp
movq 1000(%rdi), %rax # rsp_9(D)->rda, __ptr
movq 24(%rdx,%rax), %r12 # _15->mynode, rnp_old
x86_64 __this_cpu_read():
movq %rdi, %r13 # rsp, rsp
movq 1000(%rdi), %rax # rsp_9(D)->rda, rsp_9(D)->rda
movq %gs:24(%rax),%r12 # _10->mynode, rnp_old
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Shan Wei <davidshan@tencent.com>
Acked-by: Christoph Lameter <cl@linux.com>
---
kernel/rcu/tree.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index f1ba773..c6de285 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2404,7 +2404,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
struct rcu_node *rnp_old = NULL;
/* Funnel through hierarchy to reduce memory contention. */
- rnp = per_cpu_ptr(rsp->rda, raw_smp_processor_id())->mynode;
+ rnp = __this_cpu_read(rsp->rda->mynode);
for (; rnp != NULL; rnp = rnp->parent) {
ret = (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) ||
!raw_spin_trylock(&rnp->fqslock);
--
2.0.0
next reply other threads:[~2014-06-19 20:12 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-06-19 20:12 Pranith Kumar [this message]
2014-06-19 20:17 ` [PATCH 1/1] rcu: use __this_cpu_read helper instead of per_cpu_ptr(p, raw_smp_processor_id()) josh
2014-06-19 21:22 ` Paul E. McKenney
2014-06-19 21:04 ` Paul E. McKenney
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=53A3443E.8010102@gmail.com \
--to=bobby.prani@gmail.com \
--cc=cl@linux.com \
--cc=davidshan@tencent.com \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=paulmck@linux.vnet.ibm.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 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.