linux-kernel - [tip:tracing/core] x86, bts: wait until traced task has been scheduled out

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

Message-ID: <tip-8d99b3ac2726e5edd97ad147fa5c1f2acb63a745@git.kernel.org>
Date:	Thu, 7 May 2009 09:22:11 GMT
From:	tip-bot for Markus Metzger <markus.t.metzger@...el.com>
To:	linux-tip-commits@...r.kernel.org
Cc:	linux-kernel@...r.kernel.org, hpa@...or.com, mingo@...hat.com,
	markus.t.metzger@...el.com, oleg@...hat.com, tglx@...utronix.de,
	mingo@...e.hu
Subject: [tip:tracing/core] x86, bts: wait until traced task has been scheduled out

Commit-ID:  8d99b3ac2726e5edd97ad147fa5c1f2acb63a745
Gitweb:     http://git.kernel.org/tip/8d99b3ac2726e5edd97ad147fa5c1f2acb63a745
Author:     Markus Metzger <markus.t.metzger@...el.com>
AuthorDate: Fri, 3 Apr 2009 16:43:36 +0200
Committer:  Ingo Molnar <mingo@...e.hu>
CommitDate: Tue, 7 Apr 2009 13:36:15 +0200

x86, bts: wait until traced task has been scheduled out

In order to stop branch tracing for a running task, we need to first
clear the branch tracing control bits before we may free the tracing
buffer.

If the traced task is running, the cpu might still trace that task
after the branch trace control bits have cleared.

Wait until the traced task has been scheduled out before proceeding.

A similar problem affects the task debug store context. We first remove
the context, then we need to wait until the task has been scheduled
out before we can free the context memory.

Reviewed-by: Oleg Nesterov <oleg@...hat.com>
Signed-off-by: Markus Metzger <markus.t.metzger@...el.com>
Cc: roland@...hat.com
Cc: eranian@...glemail.com
Cc: juan.villacis@...el.com
Cc: ak@...ux.jf.intel.com
LKML-Reference: <20090403144551.919636000@...el.com>
Signed-off-by: Ingo Molnar <mingo@...e.hu>


---
 arch/x86/kernel/ds.c |   23 +++++++++++++++++++----
 1 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/ds.c b/arch/x86/kernel/ds.c
index c730155..5cd137a 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -299,6 +299,7 @@ static inline struct ds_context *ds_get_context(struct task_struct *task)
 
 static inline void ds_put_context(struct ds_context *context)
 {
+	struct task_struct *task;
 	unsigned long irq;
 
 	if (!context)
@@ -313,14 +314,20 @@ static inline void ds_put_context(struct ds_context *context)
 
 	*(context->this) = NULL;
 
-	if (context->task)
-		clear_tsk_thread_flag(context->task, TIF_DS_AREA_MSR);
+	task = context->task;
+
+	if (task)
+		clear_tsk_thread_flag(task, TIF_DS_AREA_MSR);
 
-	if (!context->task || (context->task == current))
+	if (!task || (task == current))
 		wrmsrl(MSR_IA32_DS_AREA, 0);
 
 	spin_unlock_irqrestore(&ds_lock, irq);
 
+	/* The context might still be in use for context switching. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
 	kfree(context);
 }
 
@@ -781,15 +788,23 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task,
 
 void ds_release_bts(struct bts_tracer *tracer)
 {
+	struct task_struct *task;
+
 	if (!tracer)
 		return;
 
+	task = tracer->ds.context->task;
+
 	ds_suspend_bts(tracer);
 
 	WARN_ON_ONCE(tracer->ds.context->bts_master != tracer);
 	tracer->ds.context->bts_master = NULL;
 
-	put_tracer(tracer->ds.context->task);
+	/* Make sure tracing stopped and the tracer is not in use. */
+	if (task && (task != current))
+		wait_task_context_switch(task);
+
+	put_tracer(task);
 	ds_put_context(tracer->ds.context);
 
 	kfree(tracer);
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/