From: Arnd Bergmann <arnd@arndb.de>
To: paulmck@linux.vnet.ibm.com
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
linux-kernel@vger.kernel.org, mingo@elte.hu,
laijs@cn.fujitsu.com, dipankar@in.ibm.com,
akpm@linux-foundation.org, josh@joshtriplett.org,
dvhltc@us.ibm.com, niv@us.ibm.com, tglx@linutronix.de,
peterz@infradead.org, rostedt@goodmis.org,
Valdis.Kletnieks@vt.edu, dhowells@redhat.com
Subject: [PATCH 01/10] rcu: define __rcu address space modifier for sparse
Date: Wed, 24 Feb 2010 21:03:57 +0100 [thread overview]
Message-ID: <1267041846-10469-2-git-send-email-arnd@arndb.de> (raw)
In-Reply-To: <1267041846-10469-1-git-send-email-arnd@arndb.de>
In-Reply-To: <20100223180127.GF6700@linux.vnet.ibm.com>
This is a first attempt to define an __rcu annotation
that lets sparse check for correct use of rcu_assign_pointer()
and rcu_dereference(). Pointers that are annotated __rcu
must be dereferenced using rcu_dereference or the new
__rcu_dereference and must be assigned using rcu_assign_pointer
or the new __rcu_assign_pointer.
The new macros are used in cases where not using the
regular accessors is proven to be correct.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
include/linux/compiler.h | 2 ++
include/linux/rcupdate.h | 46 +++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 43 insertions(+), 5 deletions(-)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 188fcae..6cc0857 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -10,6 +10,7 @@
# define __force __attribute__((force))
# define __nocast __attribute__((nocast))
# define __iomem __attribute__((noderef, address_space(2)))
+# define __rcu __attribute__((noderef, address_space(3)))
# define __acquires(x) __attribute__((context(x,0,1)))
# define __releases(x) __attribute__((context(x,1,0)))
# define __acquire(x) __context__(x,1)
@@ -25,6 +26,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
# define __force
# define __nocast
# define __iomem
+# define __rcu
# define __chk_user_ptr(x) (void)0
# define __chk_io_ptr(x) (void)0
# define __builtin_warning(x, y...) (1)
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 24440f4..644e28c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -40,6 +40,7 @@
#include <linux/seqlock.h>
#include <linux/lockdep.h>
#include <linux/completion.h>
+#include <linux/compiler.h>
/**
* struct rcu_head - callback structure for use with RCU
@@ -225,13 +226,31 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
*
* Inserts memory barriers on architectures that require them
* (currently only the Alpha), and, more importantly, documents
- * exactly which pointers are protected by RCU.
+ * exactly which pointers are protected by RCU and checks that
+ * the pointer is annotated as __rcu.
*/
-
#define rcu_dereference(p) ({ \
- typeof(p) _________p1 = ACCESS_ONCE(p); \
+ typeof(*p) *_________p1 = (typeof(*p)*__force )ACCESS_ONCE(p); \
+ (void) (((typeof (*p) __rcu *)p) == p); \
smp_read_barrier_depends(); \
- (_________p1); \
+ ((typeof(*p) __force __kernel *)(_________p1)); \
+ })
+
+/**
+ * __rcu_dereference - fetch an __rcu pointer outside of a
+ * read-side critical section.
+ *
+ * __rcu_dereference does not contain any barrier but only
+ * converts a __rcu pointer to one that can be dereferenced.
+ * Use this for annotating code that operates on __rcu variables
+ * for checking with sparse in places where you can be sure
+ * that no writers exist, e.g. in a write-side critical section
+ * or in an RCU call.
+ */
+
+#define __rcu_dereference(p) ({ \
+ (void) (((typeof (*p) __rcu *)p) == p); \
+ ((typeof(*p) __force __kernel *)(p)); \
})
/**
@@ -252,9 +271,26 @@ static inline notrace void rcu_read_unlock_sched_notrace(void)
if (!__builtin_constant_p(v) || \
((v) != NULL)) \
smp_wmb(); \
- (p) = (v); \
+ (p) = (typeof(*v) __force __rcu *)(v); \
})
+/**
+ * __rcu_assign_pointer - assign a variable to an __rcu pointer
+ * without barriers.
+ * Using this is almost always a bug.
+ */
+#define __rcu_assign_pointer(p, v) \
+ ({ \
+ (p) = (typeof(*v) __force __rcu *)(v); \
+ })
+
+/**
+ * RCU_INIT_POINTER - initialize an RCU protected member
+ * in a statically allocated data structure.
+ */
+#define RCU_INIT_POINTER(p, v) \
+ p = (typeof(*v) __force __rcu *)(v)
+
/* Infrastructure to implement the synchronize_() primitives. */
struct rcu_synchronize {
--
1.6.3.3
next prev parent reply other threads:[~2010-02-24 20:06 UTC|newest]
Thread overview: 84+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-02-23 1:04 [PATCH tip/core/rcu 0/21] v6 add lockdep-based diagnostics to rcu_dereference() Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 01/21] rcu: introduce lockdep-based checking to RCU read-side primitives Paul E. McKenney
2010-02-25 10:09 ` [tip:core/rcu] rcu: Introduce " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 02/21] rcu: add lockdep-enabled variants of rcu_dereference() Paul E. McKenney
2010-02-25 10:09 ` [tip:core/rcu] rcu: Add " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 03/21] rcu: integrate rcu_dereference_check() message into lockdep Paul E. McKenney
2010-02-25 10:09 ` [tip:core/rcu] rcu: Integrate " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 04/21] rcu: disable lockdep checking in RCU list-traversal primitives Paul E. McKenney
2010-02-25 10:10 ` [tip:core/rcu] rcu: Disable " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 05/21] net: add checking to rcu_dereference() primitives Paul E. McKenney
2010-02-25 10:10 ` [tip:core/rcu] net: Add " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 06/21] sched: use lockdep-based checking on rcu_dereference() Paul E. McKenney
2010-02-25 10:11 ` [tip:core/rcu] sched: Use " tip-bot for Paul E. McKenney
2010-02-25 11:06 ` [tip:core/rcu] sched, cgroups: Fix module export tip-bot for Ingo Molnar
2010-02-23 1:04 ` [PATCH tip/core/rcu 07/21] sched: better name for for_each_domain_rd Paul E. McKenney
2010-02-25 10:11 ` [tip:core/rcu] sched: Better " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 08/21] vfs: apply lockdep-based checking to rcu_dereference() uses Paul E. McKenney
2010-02-25 10:11 ` [tip:core/rcu] vfs: Apply " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 09/21] vfs: abstract rcu_dereference_check for files-fdtable use Paul E. McKenney
2010-02-25 10:11 ` [tip:core/rcu] vfs: Abstract " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 10/21] radix-tree: disable RCU lockdep checking in radix tree Paul E. McKenney
2010-02-25 10:12 ` [tip:core/rcu] radix-tree: Disable " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 11/21] idr: apply lockdep-based diagnostics to rcu_dereference() uses Paul E. McKenney
2010-02-25 10:12 ` [tip:core/rcu] idr: Apply " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 12/21] security: apply lockdep-based checking " Paul E. McKenney
2010-02-25 10:12 ` [tip:core/rcu] security: Apply " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 13/21] rcu: documentation update for CONFIG_PROVE_RCU Paul E. McKenney
2010-02-25 10:12 ` [tip:core/rcu] rcu: Documentation " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 14/21] rcu: fix citation of Mathieu's dissertation Paul E. McKenney
2010-02-25 10:13 ` [tip:core/rcu] rcu: Fix " tip-bot for Paul E. McKenney
2010-02-23 1:04 ` [PATCH tip/core/rcu 15/21] rcu: accelerate grace period if last non-dynticked CPU Paul E. McKenney
2010-02-25 10:13 ` [tip:core/rcu] rcu: Accelerate " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 16/21] rcu: use canonical URL for Mathieu's dissertation Paul E. McKenney
2010-02-25 10:13 ` [tip:core/rcu] rcu: Use " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 17/21] rcu: stop overflowing signed integers Paul E. McKenney
2010-02-25 10:14 ` [tip:core/rcu] rcu: Stop " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 18/21] rcu: Convert to raw_spinlocks Paul E. McKenney
2010-02-25 10:14 ` [tip:core/rcu] " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 19/21] rcu: fix deadlock in TREE_PREEMPT_RCU CPU stall detection Paul E. McKenney
2010-02-25 10:14 ` [tip:core/rcu] rcu: Fix " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 20/21] rcu: fix rcutorture mod_timer argument to delay one jiffy Paul E. McKenney
2010-02-25 10:14 ` [tip:core/rcu] rcu: Fix " tip-bot for Paul E. McKenney
2010-02-23 1:05 ` [PATCH tip/core/rcu 21/21] rcu: add RCU_CPU_STALL_VERBOSE to dump detailed per-task information Paul E. McKenney
2010-02-25 10:15 ` [tip:core/rcu] rcu: Add " tip-bot for Paul E. McKenney
2010-02-23 12:59 ` [PATCH tip/core/rcu 0/21] v6 add lockdep-based diagnostics to rcu_dereference() Arnd Bergmann
2010-02-23 13:15 ` Mathieu Desnoyers
2010-02-23 14:35 ` Paul E. McKenney
2010-02-23 15:54 ` Arnd Bergmann
2010-02-23 16:16 ` Paul E. McKenney
2010-02-23 17:15 ` Arnd Bergmann
2010-02-23 18:01 ` Paul E. McKenney
2010-02-24 20:03 ` [PATCH 00/10] __rcu annotations, first draft Arnd Bergmann
2010-02-24 22:18 ` Paul E. McKenney
2010-02-25 8:37 ` Ingo Molnar
2010-02-24 20:03 ` Arnd Bergmann [this message]
2010-02-24 20:12 ` [PATCH 01/10] rcu: define __rcu address space modifier for sparse Mathieu Desnoyers
2010-02-24 20:22 ` Arnd Bergmann
2010-02-24 20:03 ` [PATCH 02/10] rcu: annotated list rcu code Arnd Bergmann
2010-02-24 20:15 ` Mathieu Desnoyers
2010-02-24 20:32 ` Arnd Bergmann
2010-02-24 20:03 ` [PATCH 03/10] cgroups: __rcu annotations Arnd Bergmann
2010-02-24 20:04 ` [PATCH 04/10] credentials: rcu annotation Arnd Bergmann
2010-02-24 20:04 ` [PATCH 05/10] perf_event: __rcu annotations Arnd Bergmann
2010-02-24 20:04 ` [PATCH 06/10] audit: " Arnd Bergmann
2010-02-24 20:04 ` [PATCH 07/10] module: " Arnd Bergmann
2010-02-24 20:13 ` Alexey Dobriyan
2010-02-24 20:26 ` Arnd Bergmann
2010-02-24 22:17 ` Paul E. McKenney
2010-02-24 23:07 ` Arnd Bergmann
2010-02-24 23:59 ` Paul E. McKenney
2010-02-25 17:06 ` Paul E. McKenney
2010-02-25 18:10 ` Arnd Bergmann
2010-02-25 20:05 ` Paul E. McKenney
2010-02-26 2:12 ` Paul E. McKenney
2010-02-24 20:04 ` [PATCH 08/10] pid: " Arnd Bergmann
2010-02-24 20:04 ` [PATCH 09/10] notifiers: " Arnd Bergmann
2010-02-24 20:04 ` [PATCH 10/10] scheduler: " Arnd Bergmann
2010-02-23 13:28 ` [PATCH tip/core/rcu 0/21] v6 add lockdep-based diagnostics to rcu_dereference() Paul E. McKenney
2010-02-25 10:00 ` Ingo Molnar
2010-02-25 10:01 ` Ingo Molnar
2010-02-25 12:04 ` Ingo Molnar
2010-02-25 18:18 ` Paul E. McKenney
2010-02-25 21:36 ` Paul E. McKenney
2010-02-25 21:22 ` 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=1267041846-10469-2-git-send-email-arnd@arndb.de \
--to=arnd@arndb.de \
--cc=Valdis.Kletnieks@vt.edu \
--cc=akpm@linux-foundation.org \
--cc=dhowells@redhat.com \
--cc=dipankar@in.ibm.com \
--cc=dvhltc@us.ibm.com \
--cc=josh@joshtriplett.org \
--cc=laijs@cn.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=mingo@elte.hu \
--cc=niv@us.ibm.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--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®