From: "Michael S. Tsirkin" <mst@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Jason Wang <jasowang@redhat.com>,
Alan Stern <stern@rowland.harvard.edu>,
Andrea Parri <andrea.parri@amarulasolutions.com>,
Will Deacon <will.deacon@arm.com>,
Peter Zijlstra <peterz@infradead.org>,
Boqun Feng <boqun.feng@gmail.com>,
Nicholas Piggin <npiggin@gmail.com>,
David Howells <dhowells@redhat.com>,
Jade Alglave <j.alglave@ucl.ac.uk>,
Luc Maranget <luc.maranget@inria.fr>,
"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
Akira Yokosawa <akiyks@gmail.com>,
Daniel Lustig <dlustig@nvidia.com>,
linux-arch@vger.kernel.org, netdev@vger.kernel.org,
virtualization@lists.linux-foundation.org,
Jonathan Corbet <corbet@lwn.net>,
Richard Henderson <rth@twiddle.net>,
Ivan Kokshaysky <ink@jurassic.park.msu.ru>,
Matt Turner <mattst88@gmail.com>, Arnd Bergmann <arnd@arndb.de>,
Luc Van Oostenryck <luc.vanoostenryck@gmail.com>,
linux-doc@vger.kernel.org, linux-alpha@vger.kernel.org,
linux-sparse@vger.kernel.org
Subject: [PATCH RFC 3/4] barriers: convert a control to a data dependency
Date: Wed, 2 Jan 2019 15:57:58 -0500 [thread overview]
Message-ID: <20190102205715.14054-4-mst@redhat.com> (raw)
In-Reply-To: <20190102205715.14054-1-mst@redhat.com>
It's not uncommon to have two access two unrelated memory locations in a
specific order. At the moment one has to use a memory barrier for this.
However, if the first access was a read and the second used an address
depending on the first one we would have a data dependency and no
barrier would be necessary.
This adds a new interface: dependent_ptr_mb which does exactly this: it
returns a pointer with a data dependency on the supplied value.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
Documentation/memory-barriers.txt | 20 ++++++++++++++++++++
arch/alpha/include/asm/barrier.h | 1 +
include/asm-generic/barrier.h | 18 ++++++++++++++++++
include/linux/compiler.h | 4 ++++
4 files changed, 43 insertions(+)
diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index c1d913944ad8..9dbaa2e1dbf6 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -691,6 +691,18 @@ case what's actually required is:
p = READ_ONCE(b);
}
+Alternatively, a control dependency can be converted to a data dependency,
+e.g.:
+
+ q = READ_ONCE(a);
+ if (q) {
+ b = dependent_ptr_mb(b, q);
+ p = READ_ONCE(b);
+ }
+
+Note how the result of dependent_ptr_mb must be used with the following
+accesses in order to have an effect.
+
However, stores are not speculated. This means that ordering -is- provided
for load-store control dependencies, as in the following example:
@@ -836,6 +848,12 @@ out-guess your code. More generally, although READ_ONCE() does force
the compiler to actually emit code for a given load, it does not force
the compiler to use the results.
+Converting to a data dependency helps with this too:
+
+ q = READ_ONCE(a);
+ b = dependent_ptr_mb(b, q);
+ WRITE_ONCE(b, 1);
+
In addition, control dependencies apply only to the then-clause and
else-clause of the if-statement in question. In particular, it does
not necessarily apply to code following the if-statement:
@@ -875,6 +893,8 @@ to the CPU containing it. See the section on "Multicopy atomicity"
for more information.
+
+
In summary:
(*) Control dependencies can order prior loads against later stores.
diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index 92ec486a4f9e..b4934e8c551b 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -59,6 +59,7 @@
* as Alpha, "y" could be set to 3 and "x" to 0. Use rmb()
* in cases like this where there are no data dependencies.
*/
+#define ARCH_NEEDS_READ_BARRIER_DEPENDS 1
#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
#ifdef CONFIG_SMP
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 2cafdbb9ae4c..fa2e2ef72b68 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -70,6 +70,24 @@
#define __smp_read_barrier_depends() read_barrier_depends()
#endif
+#if defined(COMPILER_HAS_OPTIMIZER_HIDE_VAR) && \
+ !defined(ARCH_NEEDS_READ_BARRIER_DEPENDS)
+
+#define dependent_ptr_mb(ptr, val) ({ \
+ long dependent_ptr_mb_val = (long)(val); \
+ long dependent_ptr_mb_ptr = (long)(ptr) - dependent_ptr_mb_val; \
+ \
+ BUILD_BUG_ON(sizeof(val) > sizeof(long)); \
+ OPTIMIZER_HIDE_VAR(dependent_ptr_mb_val); \
+ (typeof(ptr))(dependent_ptr_mb_ptr + dependent_ptr_mb_val); \
+})
+
+#else
+
+#define dependent_ptr_mb(ptr, val) ({ mb(); (ptr); })
+
+#endif
+
#ifdef CONFIG_SMP
#ifndef smp_mb
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6601d39e8c48..f599c30f1b28 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -152,9 +152,13 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
#endif
#ifndef OPTIMIZER_HIDE_VAR
+
/* Make the optimizer believe the variable can be manipulated arbitrarily. */
#define OPTIMIZER_HIDE_VAR(var) \
__asm__ ("" : "=rm" (var) : "0" (var))
+
+#define COMPILER_HAS_OPTIMIZER_HIDE_VAR 1
+
#endif
/* Not-quite-unique ID. */
--
MST
next prev parent reply other threads:[~2019-01-02 20:58 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-02 20:57 [PATCH RFC 0/4] barriers using data dependency Michael S. Tsirkin
2019-01-02 20:57 ` [PATCH RFC 1/4] include/linux/compiler*.h: fix OPTIMIZER_HIDE_VAR Michael S. Tsirkin
2019-01-08 17:44 ` Nick Desaulniers
2019-01-08 18:50 ` Michael S. Tsirkin
2019-01-09 10:35 ` Miguel Ojeda
2019-01-09 14:50 ` Michael S. Tsirkin
2019-01-19 18:35 ` Miguel Ojeda
2019-01-20 14:43 ` Michael S. Tsirkin
2019-01-20 15:36 ` Miguel Ojeda
2019-01-10 2:36 ` Michael S. Tsirkin
2019-01-10 13:41 ` Dan Carpenter
2019-01-10 14:08 ` Michael S. Tsirkin
2019-01-02 20:57 ` [PATCH RFC 2/4] include/linux/compiler.h: allow memory operands Michael S. Tsirkin
2019-01-07 17:54 ` Will Deacon
2019-01-07 18:16 ` Michael S. Tsirkin
2019-01-02 20:57 ` Michael S. Tsirkin [this message]
2019-01-02 21:00 ` [PATCH RFC 3/4] barriers: convert a control to a data dependency Matthew Wilcox
2019-01-02 21:24 ` Michael S. Tsirkin
2019-01-07 3:58 ` Jason Wang
2019-01-07 4:23 ` Michael S. Tsirkin
2019-01-07 6:50 ` Jason Wang
2019-01-07 9:46 ` Peter Zijlstra
2019-01-07 13:36 ` Michael S. Tsirkin
2019-01-07 15:54 ` Peter Zijlstra
2019-01-07 16:22 ` Michael S. Tsirkin
2019-01-07 19:02 ` Paul E. McKenney
2019-01-07 19:13 ` Michael S. Tsirkin
2019-01-07 19:25 ` Paul E. McKenney
2019-01-02 20:58 ` [PATCH RFC 4/4] virtio: use dependent_ptr_mb Michael S. Tsirkin
2019-01-02 21:36 ` [PATCH RFC 0/4] barriers using data dependency Alan Stern
2019-01-02 23:04 ` Michael S. Tsirkin
2019-01-03 15:11 ` Alan Stern
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=20190102205715.14054-4-mst@redhat.com \
--to=mst@redhat.com \
--cc=akiyks@gmail.com \
--cc=andrea.parri@amarulasolutions.com \
--cc=arnd@arndb.de \
--cc=boqun.feng@gmail.com \
--cc=corbet@lwn.net \
--cc=dhowells@redhat.com \
--cc=dlustig@nvidia.com \
--cc=ink@jurassic.park.msu.ru \
--cc=j.alglave@ucl.ac.uk \
--cc=jasowang@redhat.com \
--cc=linux-alpha@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-sparse@vger.kernel.org \
--cc=luc.maranget@inria.fr \
--cc=luc.vanoostenryck@gmail.com \
--cc=mattst88@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=npiggin@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=rth@twiddle.net \
--cc=stern@rowland.harvard.edu \
--cc=virtualization@lists.linux-foundation.org \
--cc=will.deacon@arm.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).