From: Chen Gong <gong.chen@linux.intel.com>
To: venki@google.com, shaohua.li@intel.com
Cc: len.brown@intel.com, linux-acpi@vger.kernel.org,
Chen Gong <gong.chen@linux.intel.com>
Subject: [PATCH] ACPI: Don't let acpi_pad needlessly mark LAPIC unstable
Date: Sun, 30 May 2010 11:37:08 +0800 [thread overview]
Message-ID: <1275190628-18265-1-git-send-email-gong.chen@linux.intel.com> (raw)
according to Venki's suggestion in the commit 0dc698b,
adding LAPIC unstable detection in the acpi_pad drvier too.
Signed-off-by: Chen Gong <gong.chen@linux.intel.com>
---
drivers/acpi/acpi_pad.c | 36 ++++++++++++++++++++++++------------
1 files changed, 24 insertions(+), 12 deletions(-)
diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c
index d269a8f..446aced 100644
--- a/drivers/acpi/acpi_pad.c
+++ b/drivers/acpi/acpi_pad.c
@@ -46,6 +46,8 @@ static unsigned long power_saving_mwait_eax;
static unsigned char tsc_detected_unstable;
static unsigned char tsc_marked_unstable;
+static unsigned char lapic_detected_unstable;
+static unsigned char lapic_marked_unstable;
static void power_saving_mwait_init(void)
{
@@ -75,9 +77,6 @@ static void power_saving_mwait_init(void)
power_saving_mwait_eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
(highest_subcstate - 1);
- for_each_online_cpu(i)
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ON, &i);
-
#if defined(CONFIG_GENERIC_TIME) && defined(CONFIG_X86)
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
@@ -86,13 +85,15 @@ static void power_saving_mwait_init(void)
* AMD Fam10h TSC will tick in all
* C/P/S0/S1 states when this bit is set.
*/
- if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
- return;
-
- /*FALL THROUGH*/
+ if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+ tsc_detected_unstable = 1;
+ if (!boot_cpu_has(X86_FEATURE_ARAT))
+ lapic_detected_unstable = 1;
+ break;
default:
- /* TSC could halt in idle */
+ /* TSC & LAPIC could halt in idle */
tsc_detected_unstable = 1;
+ lapic_detected_unstable = 1;
}
#endif
}
@@ -180,10 +181,20 @@ static int power_saving_thread(void *data)
mark_tsc_unstable("TSC halts in idle");
tsc_marked_unstable = 1;
}
+ if (lapic_detected_unstable && !lapic_marked_unstable) {
+ int i;
+ /* LAPIC could halt in idle, so notify users */
+ for_each_online_cpu(i)
+ clockevents_notify(
+ CLOCK_EVT_NOTIFY_BROADCAST_ON,
+ &i);
+ lapic_marked_unstable = 1;
+ }
local_irq_disable();
cpu = smp_processor_id();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
- &cpu);
+ if (lapic_marked_unstable)
+ clockevents_notify(
+ CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &cpu);
stop_critical_timings();
__monitor((void *)¤t_thread_info()->flags, 0, 0);
@@ -192,8 +203,9 @@ static int power_saving_thread(void *data)
__mwait(power_saving_mwait_eax, 1);
start_critical_timings();
- clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
- &cpu);
+ if (lapic_marked_unstable)
+ clockevents_notify(
+ CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &cpu);
local_irq_enable();
if (jiffies > expire_time) {
--
1.7.0.2.279.gf1ba1c
next reply other threads:[~2010-05-30 3:34 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-05-30 3:37 Chen Gong [this message]
2010-06-02 6:30 ` [PATCH] ACPI: Don't let acpi_pad needlessly mark LAPIC unstable chen gong
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=1275190628-18265-1-git-send-email-gong.chen@linux.intel.com \
--to=gong.chen@linux.intel.com \
--cc=len.brown@intel.com \
--cc=linux-acpi@vger.kernel.org \
--cc=shaohua.li@intel.com \
--cc=venki@google.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).