From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
To: linux-kernel@vger.kernel.org
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
stable@vger.kernel.org,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Finn Thain <fthain@telegraphics.com.au>,
Geert Uytterhoeven <geert@linux-m68k.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: [PATCH 3.14 21/23] futex: Allow architectures to skip futex_atomic_cmpxchg_inatomic() test
Date: Fri, 11 Apr 2014 09:12:10 -0700 [thread overview]
Message-ID: <20140411161203.147556327@linuxfoundation.org> (raw)
In-Reply-To: <20140411161200.236939691@linuxfoundation.org>
3.14-stable review patch. If anyone has any objections, please let me know.
------------------
From: Heiko Carstens <heiko.carstens@de.ibm.com>
commit 03b8c7b623c80af264c4c8d6111e5c6289933666 upstream.
If an architecture has futex_atomic_cmpxchg_inatomic() implemented and there
is no runtime check necessary, allow to skip the test within futex_init().
This allows to get rid of some code which would always give the same result,
and also allows the compiler to optimize a couple of if statements away.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Finn Thain <fthain@telegraphics.com.au>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Link: http://lkml.kernel.org/r/20140302120947.GA3641@osiris
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
arch/s390/Kconfig | 1 +
include/linux/futex.h | 4 ++++
init/Kconfig | 7 +++++++
kernel/futex.c | 37 ++++++++++++++++++++++++-------------
4 files changed, 36 insertions(+), 13 deletions(-)
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -117,6 +117,7 @@ config S390
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,7 +55,11 @@ union futex_key {
#ifdef CONFIG_FUTEX
extern void exit_robust_list(struct task_struct *curr);
extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
extern int futex_cmpxchg_enabled;
+#endif
#else
static inline void exit_robust_list(struct task_struct *curr)
{
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1387,6 +1387,13 @@ config FUTEX
support for "fast userspace mutexes". The resulting kernel may not
run glibc-based applications correctly.
+config HAVE_FUTEX_CMPXCHG
+ bool
+ help
+ Architectures should select this if futex_atomic_cmpxchg_inatomic()
+ is implemented and always working. This removes a couple of runtime
+ checks.
+
config EPOLL
bool "Enable eventpoll support" if EXPERT
default y
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -157,7 +157,9 @@
* enqueue.
*/
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
int __read_mostly futex_cmpxchg_enabled;
+#endif
/*
* Futex flags used to encode options to functions and preserve them across
@@ -2880,9 +2882,28 @@ SYSCALL_DEFINE6(futex, u32 __user *, uad
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
-static int __init futex_init(void)
+static void __init futex_detect_cmpxchg(void)
{
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
u32 curval;
+
+ /*
+ * This will fail and we want it. Some arch implementations do
+ * runtime detection of the futex_atomic_cmpxchg_inatomic()
+ * functionality. We want to know that before we call in any
+ * of the complex code paths. Also we want to prevent
+ * registration of robust lists in that case. NULL is
+ * guaranteed to fault and we get -EFAULT on functional
+ * implementation, the non-functional ones will return
+ * -ENOSYS.
+ */
+ if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+ futex_cmpxchg_enabled = 1;
+#endif
+}
+
+static int __init futex_init(void)
+{
unsigned int futex_shift;
unsigned long i;
@@ -2898,18 +2919,8 @@ static int __init futex_init(void)
&futex_shift, NULL,
futex_hashsize, futex_hashsize);
futex_hashsize = 1UL << futex_shift;
- /*
- * This will fail and we want it. Some arch implementations do
- * runtime detection of the futex_atomic_cmpxchg_inatomic()
- * functionality. We want to know that before we call in any
- * of the complex code paths. Also we want to prevent
- * registration of robust lists in that case. NULL is
- * guaranteed to fault and we get -EFAULT on functional
- * implementation, the non-functional ones will return
- * -ENOSYS.
- */
- if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
- futex_cmpxchg_enabled = 1;
+
+ futex_detect_cmpxchg();
for (i = 0; i < futex_hashsize; i++) {
atomic_set(&futex_queues[i].waiters, 0);
next prev parent reply other threads:[~2014-04-11 16:12 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-04-11 16:11 [PATCH 3.14 00/23] 3.14.1-stable review Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 01/23] Revert "ALSA: hda - Increment default stream numbers for AMD HDMI controllers" Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 02/23] selinux: correctly label /proc inodes in use before the policy is loaded Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 03/23] x86, pageattr: Export page unmapping interface Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 04/23] x86/efi: Make efi virtual runtime map passing more robust Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 05/23] futex: avoid race between requeue and wake Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 06/23] xen-netback: remove pointless clause from if statement Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 07/23] xen-netback: worse-case estimate in xenvif_rx_action is underestimating Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 08/23] xen-netback: BUG_ON in xenvif_rx_action() not catching overflow Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 09/23] ipv6: some ipv6 statistic counters failed to disable bh Greg Kroah-Hartman
2014-04-11 16:11 ` [PATCH 3.14 10/23] netlink: dont compare the nul-termination in nla_strcmp Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 11/23] xen-netback: disable rogue vif in kthread context Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 12/23] Call efx_set_channels() before efx->type->dimension_resources() Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 13/23] net: vxlan: fix crash when interface is created with no group Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 14/23] isdnloop: Validate NUL-terminated strings from user Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 15/23] isdnloop: several buffer overflows Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 16/23] rds: prevent dereference of a NULL device in rds_iw_laddr_check Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 17/23] net/at91_ether: avoid NULL pointer dereference Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 18/23] iwlwifi: mvm: rs: fix search cycle rules Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 19/23] ARC: [nsimosci] Change .dts to use generic 8250 UART Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 20/23] ARC: [nsimosci] Unbork console Greg Kroah-Hartman
2014-04-11 16:12 ` Greg Kroah-Hartman [this message]
2014-04-11 16:12 ` [PATCH 3.14 22/23] m68k: Skip futex_atomic_cmpxchg_inatomic() test Greg Kroah-Hartman
2014-04-11 16:12 ` [PATCH 3.14 23/23] crypto: ghash-clmulni-intel - use C implementation for setkey() Greg Kroah-Hartman
2014-04-11 21:49 ` [PATCH 3.14 00/23] 3.14.1-stable review Guenter Roeck
2014-04-12 1:58 ` Greg Kroah-Hartman
2014-04-11 23:46 ` Shuah Khan
2014-04-12 1:59 ` Greg Kroah-Hartman
2014-04-12 5:38 ` Satoru Takeuchi
2014-04-12 15:22 ` Greg Kroah-Hartman
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=20140411161203.147556327@linuxfoundation.org \
--to=gregkh@linuxfoundation.org \
--cc=fthain@telegraphics.com.au \
--cc=geert@linux-m68k.org \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=stable@vger.kernel.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