linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Waiman Long <longman@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	"H. Peter Anvin" <hpa@zytor.com>,
	Josh Poimboeuf <jpoimboe@kernel.org>,
	Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	Len Brown <lenb@kernel.org>
Cc: linux-kernel@vger.kernel.org, x86@kernel.org,
	linux-pm@vger.kernel.org, Robin Jarry <rjarry@redhat.com>,
	Joe Mario <jmario@redhat.com>, Waiman Long <longman@redhat.com>
Subject: [PATCH v2 4/5] intel_idle: Add no_ibrs module parameter to force disable IBRS
Date: Tue, 20 Jun 2023 10:06:24 -0400	[thread overview]
Message-ID: <20230620140625.1001886-5-longman@redhat.com> (raw)
In-Reply-To: <20230620140625.1001886-1-longman@redhat.com>

Commit bf5835bcdb96 ("intel_idle: Disable IBRS during long idle")
disables IBRS when the cstate is 6 or lower. However, there are
some use cases where a customer may want to use max_cstate=1 to
lower latency. Such use cases will suffer from the performance
degradation caused by the enabling of IBRS in the sibling idle thread.
Add a "no_ibrs" module parameter to force disable IBRS and the
CPUIDLE_FLAG_IRQ_ENABLE flag if set.

In the case of a Skylake server with max_cstate=1, this new no_ibrs
option will increase the IRQ response latency as IRQ will now be
disabled.

Signed-off-by: Waiman Long <longman@redhat.com>
---
 drivers/idle/intel_idle.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 07fa23707b3c..366dacccc971 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -69,6 +69,7 @@ static int max_cstate = CPUIDLE_STATE_MAX - 1;
 static unsigned int disabled_states_mask __read_mostly;
 static unsigned int preferred_states_mask __read_mostly;
 static bool force_irq_on __read_mostly;
+static bool no_ibrs __read_mostly;
 
 static struct cpuidle_device __percpu *intel_idle_cpuidle_devices;
 
@@ -1907,12 +1908,15 @@ static void __init intel_idle_init_cstates_icpu(struct cpuidle_driver *drv)
 			WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
 			state->enter = intel_idle_xstate;
 		} else if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) &&
-			   state->flags & CPUIDLE_FLAG_IBRS) {
+			  ((state->flags & CPUIDLE_FLAG_IBRS) || no_ibrs)) {
 			/*
 			 * IBRS mitigation requires that C-states are entered
 			 * with interrupts disabled.
 			 */
-			WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
+			if (no_ibrs && (state->flags & CPUIDLE_FLAG_IRQ_ENABLE))
+				state->flags &= ~CPUIDLE_FLAG_IRQ_ENABLE;
+			else
+				WARN_ON_ONCE(state->flags & CPUIDLE_FLAG_IRQ_ENABLE);
 			state->enter = intel_idle_ibrs;
 		} else if (state->flags & CPUIDLE_FLAG_IRQ_ENABLE) {
 			state->enter = intel_idle_irq;
@@ -2165,3 +2169,9 @@ MODULE_PARM_DESC(preferred_cstates, "Mask of preferred idle states");
  * 'CPUIDLE_FLAG_INIT_XSTATE' and 'CPUIDLE_FLAG_IBRS' flags.
  */
 module_param(force_irq_on, bool, 0444);
+/*
+ * Force the disabling of IBRS when X86_FEATURE_KERNEL_IBRS is on and
+ * CPUIDLE_FLAG_IRQ_ENABLE isn't set.
+ */
+module_param(no_ibrs, bool, 0444);
+MODULE_PARM_DESC(no_ibrs, "Disable IBRS when idle");
-- 
2.31.1


  parent reply	other threads:[~2023-06-20 14:10 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-06-20 14:06 [PATCH v2 0/5] x86/speculation: Disable IBRS when idle Waiman Long
2023-06-20 14:06 ` [PATCH v2 1/5] x86/speculation: Provide a debugfs file to dump SPEC_CTRL MSRs Waiman Long
2023-06-21  7:41   ` Peter Zijlstra
2023-06-21  8:24     ` Borislav Petkov
2023-06-21 14:02       ` Waiman Long
2023-06-21 13:47     ` Waiman Long
2023-06-20 14:06 ` [PATCH v2 2/5] x86/idle: Disable IBRS when cpu is offline Waiman Long
2023-06-21  7:23   ` Peter Zijlstra
2023-06-21 13:59     ` Waiman Long
2023-06-21 14:36       ` Peter Zijlstra
2023-06-21 14:44         ` Waiman Long
2023-06-21 14:48           ` Peter Zijlstra
2023-06-21 14:51             ` Waiman Long
2023-06-21 14:54               ` Peter Zijlstra
2023-06-21 15:42                 ` Waiman Long
2023-06-20 14:06 ` [PATCH v2 3/5] intel_idle: Sync up the SPEC_CTRL MSR value to x86_spec_ctrl_current Waiman Long
2023-06-21  7:38   ` Peter Zijlstra
2023-06-20 14:06 ` Waiman Long [this message]
2023-06-21  7:30   ` [PATCH v2 4/5] intel_idle: Add no_ibrs module parameter to force disable IBRS Peter Zijlstra
2023-06-20 14:06 ` [PATCH v2 5/5] x86/idle: Disable IBRS entering mwait idle and enable it on wakeup Waiman Long
2023-06-21  7:32   ` Peter Zijlstra
2023-06-21 14:05     ` Waiman Long

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=20230620140625.1001886-5-longman@redhat.com \
    --to=longman@redhat.com \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --cc=jmario@redhat.com \
    --cc=jpoimboe@kernel.org \
    --cc=lenb@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pawan.kumar.gupta@linux.intel.com \
    --cc=peterz@infradead.org \
    --cc=rjarry@redhat.com \
    --cc=tglx@linutronix.de \
    --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).