linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Jiri Kosina <jikos@kernel.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Ingo Molnar <mingo@redhat.com>,
	Josh Poimboeuf <jpoimboe@redhat.com>,
	Andrea Arcangeli <aarcange@redhat.com>,
	David Woodhouse <dwmw@amazon.co.uk>,
	Andi Kleen <ak@linux.intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Casey Schaufler <casey.schaufler@intel.com>,
	Asit Mallick <asit.k.mallick@intel.com>,
	Arjan van de Ven <arjan@linux.intel.com>,
	Jon Masters <jcm@redhat.com>, Waiman Long <longman9394@gmail.com>,
	linux-kernel@vger.kernel.org, x86@kernel.org
Subject: Re: [Patch v5 08/16] smt: Create cpu_smt_enabled static key for SMT specific code
Date: Mon, 19 Nov 2018 15:57:54 +0100	[thread overview]
Message-ID: <20181119145754.GA2131@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <91b719e53640f60666b40a3516da2b80703b2f76.1542418937.git.tim.c.chen@linux.intel.com>

On Fri, Nov 16, 2018 at 05:53:51PM -0800, Tim Chen wrote:
> In later code, STIBP will be turned on/off in the context switch code
> path when SMT is enabled.  Checks for SMT is best
> avoided on such hot paths.
> 
> Create cpu_smt_enabled static key to turn on such SMT specific code
> statically.

AFAICT this patch only follows the SMT control knob but not the actual
topology state.

And, as I previously wrote, we already have sched_smt_present, which is
supposed to do much the same.

All you need is the below to make it accurately track the topology.

---
Subject: sched/smt: Make sched_smt_present track topology

Currently the sched_smt_present static key is only enabled when we
encounter SMT topology. However there is demand to also disable the key
when the topology changes such that there is no SMT present anymore.

Implement this by making the key count the number of cores that have SMT
enabled.

In particular, the SMT topology bits are set before we enable
interrrupts and similarly, are cleared after we disable interrupts for
the last time and die.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f12225f26b70..77e552928c67 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5738,15 +5738,10 @@ int sched_cpu_activate(unsigned int cpu)
 
 #ifdef CONFIG_SCHED_SMT
 	/*
-	 * The sched_smt_present static key needs to be evaluated on every
-	 * hotplug event because at boot time SMT might be disabled when
-	 * the number of booted CPUs is limited.
-	 *
-	 * If then later a sibling gets hotplugged, then the key would stay
-	 * off and SMT scheduling would never be functional.
+	 * When going up, increment the number of cores with SMT present.
 	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
-		static_branch_enable_cpuslocked(&sched_smt_present);
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_inc_cpuslocked(&sched_smt_present);
 #endif
 	set_cpu_active(cpu, true);
 
@@ -5790,6 +5785,14 @@ int sched_cpu_deactivate(unsigned int cpu)
 	 */
 	synchronize_rcu_mult(call_rcu, call_rcu_sched);
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * When going down, decrement the number of cores with SMT present.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+		static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+
 	if (!sched_smp_initialized)
 		return 0;
 

  parent reply	other threads:[~2018-11-19 14:58 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-11-17  1:53 [Patch v5 00/16] Provide task property based options to enable Spectre v2 userspace-userspace protection Tim Chen
2018-11-17  1:53 ` [Patch v5 01/16] x86/speculation: Clean up spectre_v2_parse_cmdline() Tim Chen
2018-11-17  1:53 ` [Patch v5 02/16] x86/speculation: Remove unnecessary ret variable in cpu_show_common() Tim Chen
2018-11-17  1:53 ` [Patch v5 03/16] x86/speculation: Reorganize cpu_show_common() Tim Chen
2018-11-17  1:53 ` [Patch v5 04/16] x86/speculation: Add X86_FEATURE_USE_IBRS_ENHANCED Tim Chen
2018-11-17  1:53 ` [Patch v5 05/16] x86/speculation: Disable STIBP when enhanced IBRS is in use Tim Chen
2018-11-17  1:53 ` [Patch v5 06/16] x86/speculation: Rename SSBD update functions Tim Chen
2018-11-17  1:53 ` [Patch v5 07/16] x86/speculation: Reorganize speculation control MSRs update Tim Chen
2018-11-17  1:53 ` [Patch v5 08/16] smt: Create cpu_smt_enabled static key for SMT specific code Tim Chen
2018-11-19 12:58   ` Thomas Gleixner
2018-11-19 20:50     ` Tim Chen
2018-11-19 14:57   ` Peter Zijlstra [this message]
2018-11-19 18:08     ` Tim Chen
2018-11-19 19:03       ` Thomas Gleixner
2018-11-19 19:25         ` Tim Chen
2018-11-17  1:53 ` [Patch v5 09/16] x86/smt: Convert cpu_smt_control check to cpu_smt_enabled static key Tim Chen
2018-11-19 12:48   ` Thomas Gleixner
2018-11-19 12:59     ` Thomas Gleixner
2018-11-17  1:53 ` [Patch v5 10/16] x86/speculation: Turn on or off STIBP according to a task's TIF_STIBP Tim Chen
2018-11-17  1:53 ` [Patch v5 11/16] x86/speculation: Add Spectre v2 app to app protection modes Tim Chen
2018-11-17  9:47   ` Jiri Kosina
2018-11-18 22:59     ` Jiri Kosina
2018-11-19 13:36       ` Thomas Gleixner
2018-11-19 13:49         ` Jiri Kosina
2018-11-19 13:51           ` Thomas Gleixner
2018-11-19 14:00             ` Jiri Kosina
2018-11-19 18:31               ` Tim Chen
2018-11-19 19:32           ` Andrea Arcangeli
2018-11-19 19:39             ` Jiri Kosina
2018-11-19 21:40               ` Andrea Arcangeli
2018-11-19 21:33             ` Dave Hansen
2018-11-19 23:16               ` Andrea Arcangeli
2018-11-19 23:25                 ` Dave Hansen
2018-11-19 23:45                   ` Andrea Arcangeli
2018-11-20  0:22                 ` Thomas Gleixner
2018-11-19 13:32   ` Thomas Gleixner
2018-11-20  0:08     ` Tim Chen
2018-11-20  0:30       ` Thomas Gleixner
2018-11-20  1:14         ` Tim Chen
2018-11-20  1:17         ` Andi Kleen
2018-11-19 15:00   ` Thomas Gleixner
2018-11-19 18:27     ` Tim Chen
2018-11-19 18:31       ` Jiri Kosina
2018-11-19 20:21   ` Thomas Gleixner
2018-11-19 22:44     ` Tim Chen
2018-11-19 20:46   ` Thomas Gleixner
2018-11-19 20:55     ` Jiri Kosina
2018-11-19 21:12       ` Thomas Gleixner
2018-11-19 22:48       ` Tim Chen
2018-11-19 23:01         ` Thomas Gleixner
2018-11-19 23:23           ` Jiri Kosina
2018-11-20  0:00             ` Thomas Gleixner
2018-11-20  0:24               ` Tim Chen
2018-11-19 23:39           ` Dave Hansen
2018-11-19 23:49             ` Jiri Kosina
2018-11-20  0:02               ` Thomas Gleixner
2018-11-17  1:53 ` [Patch v5 12/16] x86/speculation: Create PRCTL interface to restrict indirect branch speculation Tim Chen
2018-11-17  9:53   ` Jiri Kosina
2018-11-19 18:29     ` Tim Chen
2018-11-17  1:53 ` [Patch v5 13/16] security: Update speculation restriction of a process when modifying its dumpability Tim Chen
2018-11-17  1:53 ` [Patch v5 14/16] x86/speculation: Use STIBP to restrict speculation on non-dumpable task Tim Chen
2018-11-17  1:53 ` [Patch v5 15/16] x86/speculation: Update comment on TIF_SSBD Tim Chen
2018-11-17  1:53 ` [Patch v5 16/16] x86: Group thread info flags by functionality Tim Chen
2018-11-17  9:34 ` [Patch v5 00/16] Provide task property based options to enable Spectre v2 userspace-userspace protection Jiri Kosina

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=20181119145754.GA2131@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=aarcange@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=arjan@linux.intel.com \
    --cc=asit.k.mallick@intel.com \
    --cc=casey.schaufler@intel.com \
    --cc=dave.hansen@intel.com \
    --cc=dwmw@amazon.co.uk \
    --cc=jcm@redhat.com \
    --cc=jikos@kernel.org \
    --cc=jpoimboe@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman9394@gmail.com \
    --cc=mingo@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tim.c.chen@linux.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).