linux-kernel - [tip:x86/timers] x86/tsc: Remove the TSC

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <tip-855615eee9b1989cac8ec5eaae4562db081a239b@git.kernel.org>
Date:   Sun, 4 Jun 2017 13:02:32 -0700
From:   tip-bot for Peter Zijlstra <tipbot@...or.com>
To:     linux-tip-commits@...r.kernel.org
Cc:     hpa@...or.com, mingo@...nel.org, linux-kernel@...r.kernel.org,
        tglx@...utronix.de, peterz@...radead.org
Subject: [tip:x86/timers] x86/tsc: Remove the TSC_ADJUST clamp

Commit-ID:  855615eee9b1989cac8ec5eaae4562db081a239b
Gitweb:     http://git.kernel.org/tip/855615eee9b1989cac8ec5eaae4562db081a239b
Author:     Peter Zijlstra <peterz@...radead.org>
AuthorDate: Wed, 31 May 2017 17:52:04 +0200
Committer:  Thomas Gleixner <tglx@...utronix.de>
CommitDate: Sun, 4 Jun 2017 21:55:53 +0200

x86/tsc: Remove the TSC_ADJUST clamp

Now that all affected platforms have a microcode update; and we check
this and disable TSC_DEADLINE and print a microcode revision update
error if its too old, we can remove the TSC_ADJUST clamp.

This should help with systems where the second socket runs ahead of
the first socket and needs a negative adjustment. In this case we'd
hit the 0 clamp and give up for not achieving synchronization.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Cc: kevin.b.stanton@...el.com
Link: http://lkml.kernel.org/r/20170531155306.100950003@infradead.org
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>

---
 arch/x86/kernel/tsc_sync.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 728f753..7842371 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -71,13 +71,8 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
 	 * non zero. We don't do that on non boot cpus because physical
 	 * hotplug should have set the ADJUST register to a value > 0 so
 	 * the TSC is in sync with the already running cpus.
-	 *
-	 * But we always force positive ADJUST values. Otherwise the TSC
-	 * deadline timer creates an interrupt storm. We also have to
-	 * prevent values > 0x7FFFFFFF as those wreckage the timer as well.
 	 */
-	if ((bootcpu && bootval != 0) || (!bootcpu && bootval < 0) ||
-	    (bootval > 0x7FFFFFFF)) {
+	if (bootcpu && bootval != 0) {
 		pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n", cpu,
 			bootval);
 		wrmsrl(MSR_IA32_TSC_ADJUST, 0);
@@ -451,20 +446,6 @@ retry:
 	 */
 	cur->adjusted += cur_max_warp;
 
-	/*
-	 * TSC deadline timer stops working or creates an interrupt storm
-	 * with adjust values < 0 and > x07ffffff.
-	 *
-	 * To allow adjust values > 0x7FFFFFFF we need to disable the
-	 * deadline timer and use the local APIC timer, but that requires
-	 * more intrusive changes and we do not have any useful information
-	 * from Intel about the underlying HW wreckage yet.
-	 */
-	if (cur->adjusted < 0)
-		cur->adjusted = 0;
-	if (cur->adjusted > 0x7FFFFFFF)
-		cur->adjusted = 0x7FFFFFFF;
-
 	pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n",
 		cpu, cur_max_warp, cur->adjusted);