From: markus.t.metzger@intel.com
To: mingo@elte.hu, tglx@linutronix.de, hpa@zytor.com
Cc: markus.t.metzger@gmail.com, roland@redhat.com,
eranian@googlemail.com, oleg@redhat.com, juan.villacis@intel.com,
ak@linux.jf.intel.com, linux-kernel@vger.kernel.org,
Markus Metzger <markus.t.metzger@intel.com>
Subject: [patch 01/20] x86, bts: fix race when bts tracer is removed
Date: Fri, 03 Apr 2009 16:43:33 +0200 [thread overview]
Message-ID: <20090403144548.881338000@intel.com> (raw)
In-Reply-To: 20090403144332.799740000@intel.com
[-- Attachment #1: tip.master.ds.tracing_flags.patch --]
[-- Type: text/plain, Size: 3670 bytes --]
When the bts tracer is removed while the traced task is running,
the write to clear the bts tracer pointer races with context switch code.
Read the tracer once during a context switch.
When a new tracer is installed, the bts tracer is set in the ds context
before the tracer is initialized in order to claim the context for that
tracer.
This may result in write accesses using an uninitialized trace configuration
when scheduling timestamps have been requested.
Store active tracing flags separately and only set active flags after
the tracing configuration has been initialized.
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Markus Metzger <markus.t.metzger@intel.com>
---
arch/x86/kernel/ds.c | 58 37 + 21 - 0 !
1 file changed, 37 insertions(+), 21 deletions(-)
Index: b/arch/x86/kernel/ds.c
===================================================================
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -89,6 +89,9 @@ struct bts_tracer {
/* Buffer overflow notification function: */
bts_ovfl_callback_t ovfl;
+
+ /* Active flags affecting trace collection. */
+ unsigned int flags;
};
struct pebs_tracer {
@@ -799,6 +802,8 @@ void ds_suspend_bts(struct bts_tracer *t
if (!tracer)
return;
+ tracer->flags = 0;
+
task = tracer->ds.context->task;
if (!task || (task == current))
@@ -820,6 +825,8 @@ void ds_resume_bts(struct bts_tracer *tr
if (!tracer)
return;
+ tracer->flags = tracer->trace.ds.flags;
+
task = tracer->ds.context->task;
control = ds_cfg.ctl[dsf_bts];
@@ -1037,43 +1044,52 @@ void __cpuinit ds_init_intel(struct cpui
}
}
+static inline void ds_take_timestamp(struct ds_context *context,
+ enum bts_qualifier qualifier,
+ struct task_struct *task)
+{
+ struct bts_tracer *tracer = context->bts_master;
+ struct bts_struct ts;
+
+ /* Prevent compilers from reading the tracer pointer twice. */
+ barrier();
+
+ if (!tracer || !(tracer->flags & BTS_TIMESTAMPS))
+ return;
+
+ memset(&ts, 0, sizeof(ts));
+ ts.qualifier = qualifier;
+ ts.variant.timestamp.jiffies = jiffies_64;
+ ts.variant.timestamp.pid = task->pid;
+
+ bts_write(tracer, &ts);
+}
+
/*
* Change the DS configuration from tracing prev to tracing next.
*/
void ds_switch_to(struct task_struct *prev, struct task_struct *next)
{
- struct ds_context *prev_ctx = prev->thread.ds_ctx;
- struct ds_context *next_ctx = next->thread.ds_ctx;
+ struct ds_context *prev_ctx = prev->thread.ds_ctx;
+ struct ds_context *next_ctx = next->thread.ds_ctx;
+ unsigned long debugctlmsr = next->thread.debugctlmsr;
+
+ /* Make sure all data is read before we start. */
+ barrier();
if (prev_ctx) {
update_debugctlmsr(0);
- if (prev_ctx->bts_master &&
- (prev_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
- struct bts_struct ts = {
- .qualifier = bts_task_departs,
- .variant.timestamp.jiffies = jiffies_64,
- .variant.timestamp.pid = prev->pid
- };
- bts_write(prev_ctx->bts_master, &ts);
- }
+ ds_take_timestamp(prev_ctx, bts_task_departs, prev);
}
if (next_ctx) {
- if (next_ctx->bts_master &&
- (next_ctx->bts_master->trace.ds.flags & BTS_TIMESTAMPS)) {
- struct bts_struct ts = {
- .qualifier = bts_task_arrives,
- .variant.timestamp.jiffies = jiffies_64,
- .variant.timestamp.pid = next->pid
- };
- bts_write(next_ctx->bts_master, &ts);
- }
+ ds_take_timestamp(next_ctx, bts_task_arrives, next);
wrmsrl(MSR_IA32_DS_AREA, (unsigned long)next_ctx->ds);
}
- update_debugctlmsr(next->thread.debugctlmsr);
+ update_debugctlmsr(debugctlmsr);
}
void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
--
[-- Attachment #2: Type: text/plain, Size: 656 bytes --]
---------------------------------------------------------------------
Intel GmbH
Dornacher Strasse 1
85622 Feldkirchen/Muenchen Germany
Sitz der Gesellschaft: Feldkirchen bei Muenchen
Geschaeftsfuehrer: Douglas Lusk, Peter Gleissner, Hannes Schwaderer
Registergericht: Muenchen HRB 47456 Ust.-IdNr.
VAT Registration No.: DE129385895
Citibank Frankfurt (BLZ 502 109 00) 600119052
This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
next prev parent reply other threads:[~2009-04-03 14:46 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-04-03 14:43 [patch 00/20] x86, ptrace, bts, hw-branch-tracer: fixes and cleanups markus.t.metzger
2009-04-03 14:43 ` markus.t.metzger [this message]
2009-05-07 9:21 ` [tip:tracing/core] x86, bts: fix race when bts tracer is removed tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 02/20] sched: add wait_task_context_switch() fucntion to sched.h markus.t.metzger
2009-05-07 9:21 ` [tip:tracing/core] sched, hw-branch-tracer: add wait_task_context_switch() function " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 03/20] x86, ptrace, bts: defer branch trace stopping markus.t.metzger
2009-04-03 15:00 ` Peter Zijlstra
2009-04-04 7:17 ` Metzger, Markus T
2009-04-04 11:12 ` Peter Zijlstra
2009-04-07 8:12 ` Metzger, Markus T
2009-04-07 8:29 ` Peter Zijlstra
2009-04-07 9:09 ` Metzger, Markus T
2009-05-07 9:21 ` [tip:tracing/core] mm, " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 04/20] x86, bts: wait until traced task has been scheduled out markus.t.metzger
2009-05-07 9:22 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 05/20] x86, bts: fix race between per-task and per-cpu branch tracing markus.t.metzger
2009-05-07 9:22 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 06/20] x86, bts: use trace_clock_global() for timestamps markus.t.metzger
2009-05-07 9:22 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 07/20] x86, debugctlmsr: add _on_cpu variants to debugctlmsr functions markus.t.metzger
2009-05-07 9:22 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 08/20] x86, bts, hw-branch-tracer: add _noirq variants to the debug store interface markus.t.metzger
2009-05-07 9:22 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 09/20] x86, hw-branch-tracer: allocate selftest iterator on heap markus.t.metzger
2009-05-07 9:23 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 10/20] x86, ds: fix compiler warning markus.t.metzger
2009-05-07 9:23 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 11/20] x86, ds: fix bounds check in ds selftest markus.t.metzger
2009-05-07 9:23 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 12/20] x86, ds: selftest each cpu markus.t.metzger
2009-05-07 9:23 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 13/20] x86, ds: add task tracing selftest markus.t.metzger
2009-05-07 9:23 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 14/20] x86, ds: add leakage warning markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 15/20] x86, ds: use single debug store cpu configuration markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 16/20] x86, ptrace: add bts context unconditionally markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 17/20] x86, ds: dont use TIF_DEBUGCTLMSR markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 18/20] x86, ds: fix bad ds_reset_pebs() markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 19/20] x86, ds: allow small debug store buffers markus.t.metzger
2009-05-07 9:24 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 14:43 ` [patch 20/20] x86, ds: support Core i7 markus.t.metzger
2009-05-07 9:25 ` [tip:tracing/core] " tip-bot for Markus Metzger
2009-04-03 15:36 ` [patch 00/20] x86, ptrace, bts, hw-branch-tracer: fixes and cleanups Ingo Molnar
2009-04-03 17:44 ` Markus Metzger
2009-04-03 17:48 ` Ingo Molnar
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=20090403144548.881338000@intel.com \
--to=markus.t.metzger@intel.com \
--cc=ak@linux.jf.intel.com \
--cc=eranian@googlemail.com \
--cc=hpa@zytor.com \
--cc=juan.villacis@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=markus.t.metzger@gmail.com \
--cc=mingo@elte.hu \
--cc=oleg@redhat.com \
--cc=roland@redhat.com \
--cc=tglx@linutronix.de \
/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