From: Fenghua Yu <fenghua.yu@intel.com>
To: "Thomas Gleixner" <tglx@linutronix.de>,
"Ingo Molnar" <mingo@elte.hu>,
"H. Peter Anvin" <hpa@linux.intel.com>
Cc: "Ashok Raj" <ashok.raj@intel.com>,
"Dave Hansen" <dave.hansen@intel.com>,
"Rafael Wysocki" <rafael.j.wysocki@intel.com>,
"Tony Luck" <tony.luck@intel.com>,
"Alan Cox" <alan@linux.intel.com>,
"Ravi V Shankar" <ravi.v.shankar@intel.com>,
"Arjan van de Ven" <arjan@infradead.org>,
"linux-kernel" <linux-kernel@vger.kernel.org>,
"x86" <x86@kernel.org>, Fenghua Yu <fenghua.yu@intel.com>
Subject: [RFC PATCH 05/16] x86/split_lock: Use non atomic set and clear bit instructions in clear_cpufeature()
Date: Sun, 27 May 2018 08:45:54 -0700 [thread overview]
Message-ID: <1527435965-202085-6-git-send-email-fenghua.yu@intel.com> (raw)
In-Reply-To: <1527435965-202085-1-git-send-email-fenghua.yu@intel.com>
x86_capability can span two cache lines depending on kernel configuration
and building environment. When #AC exception is enabled for split locked
accesses, clear_cpufeature() may generate #AC exception because of atomic
setting or clearing bits in x86_capability.
But kernel clears cpufeature only during a CPU is booting up. Therefore,
there is no racing condition when clear_cpufeature() is called and no need
to atomically clear or set bits in x86_capability.
To avoid #AC exception caused by split lock, call non atomic __set_bit()
and __clear_bit(). They are faster than atomic set_bit() and clear_bit()
as well.
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
---
arch/x86/kernel/cpu/cpuid-deps.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 2c0bd38a44ab..b2c2a004c769 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -65,15 +65,15 @@ static const struct cpuid_dep cpuid_deps[] = {
static inline void clear_feature(struct cpuinfo_x86 *c, unsigned int feature)
{
/*
- * Note: This could use the non atomic __*_bit() variants, but the
- * rest of the cpufeature code uses atomics as well, so keep it for
- * consistency. Cleanup all of it separately.
+ * Because this code is only called during boot time and there
+ * is no need to be atomic, use non atomic __*_bit() for better
+ * performance and to avoid #AC exception for split locked access.
*/
if (!c) {
clear_cpu_cap(&boot_cpu_data, feature);
- set_bit(feature, (unsigned long *)cpu_caps_cleared);
+ __set_bit(feature, (unsigned long *)cpu_caps_cleared);
} else {
- clear_bit(feature, (unsigned long *)c->x86_capability);
+ __clear_bit(feature, (unsigned long *)c->x86_capability);
}
}
--
2.5.0
next prev parent reply other threads:[~2018-05-27 15:49 UTC|newest]
Thread overview: 73+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-27 15:45 [RFC PATCH 00/16] x86/split_lock: Enable #AC exception for split locked accesses Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 01/16] x86/split_lock: Add CONFIG and enumerate #AC exception for split locked access feature Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 02/16] x86/split_lock: Handle #AC exception for split lock in kernel mode Fenghua Yu
2018-06-21 19:46 ` Peter Zijlstra
2018-06-22 10:49 ` Thomas Gleixner
2018-06-22 11:59 ` Thomas Gleixner
2018-06-22 22:41 ` Fenghua Yu
2018-06-22 22:57 ` Thomas Gleixner
2018-06-22 23:03 ` Thomas Gleixner
2018-06-22 23:18 ` Fenghua Yu
2018-06-23 9:08 ` Thomas Gleixner
2018-06-23 4:20 ` Fenghua Yu
2018-06-23 9:17 ` Thomas Gleixner
2018-06-23 15:05 ` Fenghua Yu
2018-06-24 0:55 ` Thomas Gleixner
2018-06-24 1:17 ` Fenghua Yu
2018-06-24 6:43 ` Thomas Gleixner
2018-05-27 15:45 ` [RFC PATCH 03/16] x86/split_lock: Set up #AC exception for split locked accesses on all CPUs Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 04/16] x86/split_lock: Use non locked bit set instruction in set_cpu_cap Fenghua Yu
2018-06-21 19:55 ` Peter Zijlstra
2018-06-21 20:37 ` Thomas Gleixner
2018-06-27 23:35 ` Fenghua Yu
2018-06-28 7:53 ` Thomas Gleixner
2018-06-28 14:23 ` Fenghua Yu
2018-06-28 14:54 ` Fenghua Yu
2018-05-27 15:45 ` Fenghua Yu [this message]
2018-05-27 15:45 ` [RFC PATCH 06/16] x86/split_lock: Save #AC setting for split lock in firmware in boot time and restore the setting in reboot Fenghua Yu
2018-06-21 19:58 ` Peter Zijlstra
2018-06-22 15:11 ` Alan Cox
2018-06-26 9:05 ` Peter Zijlstra
2018-06-26 9:40 ` Thomas Gleixner
2018-06-26 11:02 ` Alan Cox
2018-06-26 11:31 ` Peter Zijlstra
2018-05-27 15:45 ` [RFC PATCH 07/16] x86/split_lock: Handle suspend/hibernate and resume Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 08/16] x86/split_lock: Set split lock during EFI runtime service Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 09/16] x86/split_lock: Add CONFIG to control #AC for split lock at boot time Fenghua Yu
2018-05-27 15:45 ` [RFC PATCH 10/16] x86/split_lock: Add a debugfs interface to allow user to enable or disable #AC for split lock during run time Fenghua Yu
2018-05-29 18:43 ` Greg KH
2018-05-27 15:46 ` [RFC PATCH 11/16] x86/split_lock: Add CONFIG to control #AC for split lock from kernel at boot time Fenghua Yu
2018-05-27 15:46 ` [RFC PATCH 12/16] x86/split_lock: Add a debugfs interface to allow user to change how to handle split lock in kernel mode during run time Fenghua Yu
2018-05-27 15:46 ` [RFC PATCH 13/16] x86/split_lock: Add debugfs interface to control user mode behavior Fenghua Yu
2018-05-27 15:46 ` [RFC PATCH 14/16] x86/split_lock: Add debugfs interface to show and control firmware setting for split lock Fenghua Yu
2018-05-27 15:46 ` [RFC PATCH 15/16] x86/split_lock: Add CONFIG and debugfs interface for testing #AC for split lock in kernel mode Fenghua Yu
2018-05-27 15:46 ` [RFC PATCH 16/16] x86/split_lock: Add user space split lock test in selftest Fenghua Yu
2018-05-29 16:39 ` [RFC PATCH 00/16] x86/split_lock: Enable #AC exception for split locked accesses Dave Hansen
2018-05-29 17:25 ` Fenghua Yu
2018-05-29 17:28 ` Dave Hansen
2018-05-29 17:40 ` Fenghua Yu
2018-05-29 16:40 ` Dave Hansen
2018-05-29 17:38 ` Fenghua Yu
2018-06-21 20:06 ` Peter Zijlstra
2018-06-21 19:37 ` Peter Zijlstra
2018-06-21 20:18 ` Fenghua Yu
2018-06-21 20:32 ` Thomas Gleixner
2018-06-21 22:00 ` Fenghua Yu
2018-06-21 22:07 ` Peter Zijlstra
2018-06-21 22:08 ` Peter Zijlstra
2018-06-21 22:18 ` Dave Hansen
2018-06-21 22:42 ` Fenghua Yu
2018-06-22 8:11 ` Peter Zijlstra
2018-06-22 9:30 ` Thomas Gleixner
2018-06-21 22:10 ` Peter Zijlstra
2018-06-21 23:05 ` Fenghua Yu
2018-06-22 8:19 ` Peter Zijlstra
2018-06-21 22:11 ` Peter Zijlstra
2018-06-21 22:43 ` Fenghua Yu
2018-06-21 22:13 ` Peter Zijlstra
2018-06-23 18:47 ` Fenghua Yu
2018-06-22 9:18 ` Thomas Gleixner
2018-06-22 9:22 ` Thomas Gleixner
2018-06-22 9:25 ` Thomas Gleixner
2018-06-22 9:28 ` Thomas Gleixner
2018-06-21 20:36 ` Peter Zijlstra
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=1527435965-202085-6-git-send-email-fenghua.yu@intel.com \
--to=fenghua.yu@intel.com \
--cc=alan@linux.intel.com \
--cc=arjan@infradead.org \
--cc=ashok.raj@intel.com \
--cc=dave.hansen@intel.com \
--cc=hpa@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rafael.j.wysocki@intel.com \
--cc=ravi.v.shankar@intel.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
/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).