From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, laijs@cn.fujitsu.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, mathieu.desnoyers@efficios.com,
josh@joshtriplett.org, niv@us.ibm.com, tglx@linutronix.de,
peterz@infradead.org, rostedt@goodmis.org, dhowells@redhat.com,
edumazet@google.com, dvhart@linux.intel.com, fweisbec@gmail.com,
oleg@redhat.com, sbw@mit.edu,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Shan Wei <davidshan@tencent.com>,
Pranith Kumar <bobby.prani@gmail.com>
Subject: [PATCH tip/core/rcu 13/17] rcu: Use __this_cpu_read() instead of per_cpu_ptr()
Date: Mon, 7 Jul 2014 15:38:17 -0700 [thread overview]
Message-ID: <1404772701-8804-13-git-send-email-paulmck@linux.vnet.ibm.com> (raw)
In-Reply-To: <1404772701-8804-1-git-send-email-paulmck@linux.vnet.ibm.com>
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
The __this_cpu_read() function produces better code than does
per_cpu_ptr() on both ARM and x86. For example, gcc (Ubuntu/Linaro
4.7.3-12ubuntu1) 4.7.3 produces the following:
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 __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
Because this change produces significant benefits for these two very
diverse architectures, this commit makes this change.
Signed-off-by: Shan Wei <davidshan@tencent.com>
Acked-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Pranith Kumar <bobby.prani@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
---
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 8f3e4d43d736..a6c5424ffa38 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2487,7 +2487,7 @@ 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);
--
1.8.1.5
next prev parent reply other threads:[~2014-07-07 22:39 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-07-07 22:37 [PATCH tip/core/rcu 0/17] Miscellaneous fixes for 3.17 Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 01/17] rcu: Document deadlock-avoidance information for rcu_read_unlock() Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 02/17] rcu: Handle obsolete references to TINY_PREEMPT_RCU Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 03/17] signal: Explain local_irq_save() call Paul E. McKenney
2014-07-08 9:01 ` Lai Jiangshan
2014-07-08 15:50 ` Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 04/17] rcu: Make rcu node arrays static const char * const Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 05/17] rcu: remove redundant ACCESS_ONCE() from tick_do_timer_cpu Paul E. McKenney
2014-07-08 14:46 ` Frederic Weisbecker
2014-07-07 22:38 ` [PATCH tip/core/rcu 06/17] rcu: Eliminate read-modify-write ACCESS_ONCE() calls Paul E. McKenney
2014-07-08 16:59 ` Pranith Kumar
2014-07-08 20:35 ` Paul E. McKenney
2014-07-08 20:43 ` Pranith Kumar
2014-07-08 21:40 ` Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 07/17] rcu: Loosen __call_rcu()'s rcu_head alignment constraint Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 08/17] rcu: Allow post-unlock reference for rt_mutex Paul E. McKenney
2014-07-09 1:50 ` Lai Jiangshan
2014-07-09 16:04 ` Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 09/17] rcu: Check both root and current rcu_node when setting up future grace period Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 10/17] rcu: Simplify priority boosting by putting rt_mutex in rcu_node Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 11/17] rcu: Bind grace-period kthreads to non-NO_HZ_FULL CPUs Paul E. McKenney
2014-07-08 15:24 ` Frederic Weisbecker
2014-07-08 15:47 ` Paul E. McKenney
2014-07-08 18:38 ` Frederic Weisbecker
2014-07-08 19:58 ` Paul E. McKenney
2014-07-08 20:40 ` Frederic Weisbecker
2014-07-08 22:05 ` Paul E. McKenney
2014-07-09 15:40 ` Frederic Weisbecker
2014-07-11 18:10 ` Christoph Lameter
2014-07-11 18:25 ` Frederic Weisbecker
2014-07-11 18:45 ` Paul E. McKenney
2014-07-11 18:57 ` Frederic Weisbecker
2014-07-11 19:08 ` Paul E. McKenney
2014-07-11 19:26 ` Frederic Weisbecker
2014-07-11 19:43 ` Paul E. McKenney
2014-07-11 19:55 ` Frederic Weisbecker
2014-07-11 19:05 ` Christoph Lameter
2014-07-11 19:11 ` Frederic Weisbecker
2014-07-11 20:35 ` Paul E. McKenney
2014-07-11 20:45 ` Frederic Weisbecker
2014-07-12 1:39 ` Paul E. McKenney
2014-07-14 13:52 ` Christoph Lameter
2014-07-11 20:15 ` Peter Zijlstra
2014-07-14 13:53 ` Christoph Lameter
2014-07-11 18:29 ` Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 12/17] rcu: Don't use NMIs to dump other CPUs' stacks Paul E. McKenney
2014-07-07 22:38 ` Paul E. McKenney [this message]
2014-07-07 22:38 ` [PATCH tip/core/rcu 14/17] rcu: remove CONFIG_PROVE_RCU_DELAY Paul E. McKenney
2014-07-08 8:11 ` Paul Bolle
2014-07-08 13:56 ` Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 15/17] rcu: Fix __rcu_reclaim() to use true/false for bool Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 16/17] rcu: Fix a sparse warning in rcu_initiate_boost() Paul E. McKenney
2014-07-07 22:38 ` [PATCH tip/core/rcu 17/17] rcu: Fix a sparse warning in rcu_report_unblock_qs_rnp() Paul E. McKenney
2014-07-09 2:14 ` [PATCH tip/core/rcu 0/17] Miscellaneous fixes for 3.17 Lai Jiangshan
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=1404772701-8804-13-git-send-email-paulmck@linux.vnet.ibm.com \
--to=paulmck@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=bobby.prani@gmail.com \
--cc=davidshan@tencent.com \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=dvhart@linux.intel.com \
--cc=edumazet@google.com \
--cc=fweisbec@gmail.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@kernel.org \
--cc=niv@us.ibm.com \
--cc=oleg@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=sbw@mit.edu \
--cc=tglx@linutronix.de \
/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
all inboxes | Powered by JetHome®