From: Andi Kleen <ak@suse.de>
To: lenb@kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH] [18/20] x86: Don't disable TSC in any C states on AMD Fam10h
Date: Thu, 3 Jan 2008 01:50:14 +0100 (CET) [thread overview]
Message-ID: <20080103005014.2F86314D40@wotan.suse.de> (raw)
In-Reply-To: <20080103149.088038000@suse.de>
The ACPI code currently disables TSC use in any C2 and C3
states. But the AMD Fam10h BKDG documents that the TSC
will never stop in any C states when the CONSTANT_TSC bit is
set. Make this disabling conditional on CONSTANT_TSC
not set on AMD.
I actually think this is true on Intel too for C2 states
on CPUs with p-state invariant TSC, but this needs
further discussions with Len to really confirm :-)
So far it is only enabled on AMD.
Cc: lenb@kernel.org
Signed-off-by: Andi Kleen <ak@suse.de>
---
drivers/acpi/processor_idle.c | 32 ++++++++++++++++++++++++++++----
1 file changed, 28 insertions(+), 4 deletions(-)
Index: linux/drivers/acpi/processor_idle.c
===================================================================
--- linux.orig/drivers/acpi/processor_idle.c
+++ linux/drivers/acpi/processor_idle.c
@@ -353,6 +353,26 @@ int acpi_processor_resume(struct acpi_de
return 0;
}
+#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
+static int tsc_halts_in_c(int state)
+{
+ switch (boot_cpu_data.x86_vendor) {
+ case X86_VENDOR_AMD:
+ /*
+ * AMD Fam10h TSC will tick in all
+ * C/P/S0/S1 states when this bit is set.
+ */
+ if (boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
+ return 0;
+ /*FALL THROUGH*/
+ case X86_VENDOR_INTEL:
+ /* Several cases known where TSC halts in C2 too */
+ default:
+ return state > ACPI_STATE_C1;
+ }
+}
+#endif
+
#ifndef CONFIG_CPU_IDLE
static void acpi_processor_idle(void)
{
@@ -512,7 +532,8 @@ static void acpi_processor_idle(void)
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
/* TSC halts in C2, so notify users */
- mark_tsc_unstable("possible TSC halt in C2");
+ if (tsc_halts_in_c(ACPI_STATE_C2))
+ mark_tsc_unstable("possible TSC halt in C2");
#endif
/* Compute time (ticks) that we were actually asleep */
sleep_ticks = ticks_elapsed(t1, t2);
@@ -576,7 +597,8 @@ static void acpi_processor_idle(void)
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
/* TSC halts in C3, so notify users */
- mark_tsc_unstable("TSC halts in C3");
+ if (tsc_halts_in_c(ACPI_STATE_C3))
+ mark_tsc_unstable("TSC halts in C3");
#endif
/* Compute time (ticks) that we were actually asleep */
sleep_ticks = ticks_elapsed(t1, t2);
@@ -1441,7 +1463,8 @@ static int acpi_idle_enter_simple(struct
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
/* TSC could halt in idle, so notify users */
- mark_tsc_unstable("TSC halts in idle");;
+ if (tsc_halts_in_c(cx->type))
+ mark_tsc_unstable("TSC halts in idle");;
#endif
sleep_ticks = ticks_elapsed(t1, t2);
@@ -1552,7 +1575,8 @@ static int acpi_idle_enter_bm(struct cpu
#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
/* TSC could halt in idle, so notify users */
- mark_tsc_unstable("TSC halts in idle");
+ if (tsc_halts_in_c(ACPI_STATE_C3))
+ mark_tsc_unstable("TSC halts in idle");
#endif
sleep_ticks = ticks_elapsed(t1, t2);
/* Tell the scheduler how much we idled: */
next prev parent reply other threads:[~2008-01-03 0:55 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-03 0:49 [PATCH] [1/20] x86: Make ptrace.h safe to include from assembler code Andi Kleen
2008-01-03 0:49 ` [PATCH] [2/20] x86: Implement support to synchronize RDTSC through MFENCE on AMD CPUs Andi Kleen
2008-01-03 0:49 ` [PATCH] [3/20] x86: Implement support to synchronize RDTSC with LFENCE on Intel CPUs Andi Kleen
2008-01-03 0:49 ` [PATCH] [4/20] x86: Move nop declarations into separate include file Andi Kleen
2008-01-03 0:50 ` [PATCH] [5/20] x86: Introduce nsec_barrier() Andi Kleen
2008-01-03 10:47 ` Ingo Molnar
2008-01-03 12:55 ` Andi Kleen
2008-01-07 20:01 ` [PATCH] [5/20] x86: Introduce nsec_barrier() II Andi Kleen
2008-01-03 0:50 ` [PATCH] [6/20] x86: Remove get_cycles_sync Andi Kleen
2008-01-03 0:50 ` [PATCH] [7/20] x86: Remove the now unused X86_FEATURE_SYNC_RDTSC Andi Kleen
2008-01-03 0:50 ` [PATCH] [8/20] x86: Make TIF_MCE_NOTIFY optional Andi Kleen
2008-01-03 0:50 ` [PATCH] [9/20] x86: Don't use oops_begin in 64bit mce code Andi Kleen
2008-01-03 10:39 ` Ingo Molnar
2008-01-03 12:52 ` Andi Kleen
2008-01-03 0:50 ` [PATCH] [10/20] i386: Move MWAIT idle check to generic CPU initialization Andi Kleen
2008-01-03 10:42 ` Ingo Molnar
2008-01-03 0:50 ` [PATCH] [11/20] x86: Use the correct cpuid method to detect MWAIT support for C states Andi Kleen
2008-01-03 10:45 ` Ingo Molnar
2008-01-03 12:53 ` Andi Kleen
2008-01-03 0:50 ` [PATCH] [12/20] x86: Use a per cpu timer for correctable machine check checking Andi Kleen
2008-01-03 10:49 ` Ingo Molnar
2008-01-03 12:56 ` Andi Kleen
2008-01-03 0:50 ` [PATCH] [13/20] x86: Use a deferrable timer for the correctable machine check poller Andi Kleen
2008-01-03 0:50 ` [PATCH] [14/20] x86: Add per cpu counters for machine check polls / machine check events Andi Kleen
2008-01-03 0:50 ` [PATCH] [15/20] x86: Move X86_FEATURE_CONSTANT_TSC into early cpu feature detection Andi Kleen
2008-01-03 11:03 ` Ingo Molnar
2008-01-03 0:50 ` [PATCH] [16/20] x86: Allow TSC clock source on AMD Fam10h and some cleanup Andi Kleen
2008-01-04 8:38 ` Ingo Molnar
2008-01-03 0:50 ` [PATCH] [17/20] x86: Remove explicit C3 TSC check on 64bit Andi Kleen
2008-01-04 8:38 ` Ingo Molnar
2008-01-03 0:50 ` Andi Kleen [this message]
2008-01-04 8:40 ` [PATCH] [18/20] x86: Don't disable TSC in any C states on AMD Fam10h Ingo Molnar
2008-01-03 0:50 ` [PATCH] [19/20] x86: Use shorter addresses in i386 segfault printks Andi Kleen
2008-01-03 10:56 ` Ingo Molnar
2008-01-03 12:56 ` Andi Kleen
2008-01-03 0:50 ` [PATCH] [20/20] x86: Print which shared library/executable faulted in segfault etc. messages Andi Kleen
2008-01-03 6:28 ` Eric Dumazet
2008-01-03 11:00 ` Ingo Molnar
2008-01-03 13:06 ` Andi Kleen
2008-01-03 9:54 ` [PATCH] [1/20] x86: Make ptrace.h safe to include from assembler code Ingo Molnar
2008-01-03 12:57 ` Andi Kleen
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=20080103005014.2F86314D40@wotan.suse.de \
--to=ak@suse.de \
--cc=lenb@kernel.org \
--cc=linux-kernel@vger.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.