From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
To: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>,
LKML <linux-kernel@vger.kernel.org>,
Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Christoph Hellwig <hch@infradead.org>,
Gregory Haskins <ghaskins@novell.com>,
Arnaldo Carvalho de Melo <acme@ghostprotocols.net>,
"William L. Irwin" <sparclinux@vger.kernel.org>,
Steven Rostedt <srostedt@redhat.com>
Subject: Re: [RFC PATCH 10/11] mcount tracer show task comm and pid
Date: Sun, 6 Jan 2008 23:45:07 -0500 [thread overview]
Message-ID: <20080107044506.GA1798@Krystal> (raw)
In-Reply-To: <20080106153758.GA27863@elte.hu>
* Ingo Molnar (mingo@elte.hu) wrote:
>
> * Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote:
>
> > > @@ -34,6 +34,7 @@ mctracer_add_trace_entry(struct mctracer
> > > {
> > > unsigned long idx, idx_next;
> > > struct mctracer_entry *entry;
> > > + struct task_struct *tsk = current;
> >
> > Aren't there situations, like in the middle of a context switch, where
> > current is not valid ? Is also poses a problem for early boot, and NMI
> > tracing.
>
> no such problems on x86.
>
> Ingo
I based my comments on the following code snippet, but I think I start
to understand what makes it "so special"
arch/x86/mm/fault_32.c :
static inline int vmalloc_fault(unsigned long address)
{
unsigned long pgd_paddr;
pmd_t *pmd_k;
pte_t *pte_k;
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*
----> * Do _not_ use "current" here. We might be inside
* an interrupt in the middle of a task switch..
*/
pgd_paddr = read_cr3();
pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
if (!pmd_k)
return -1;
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
return -1;
return 0;
}
At context switch on x86, loading the registers is done first, and only
after the is the current pointer set. However, for vmalloc faults, it's
the value in the cr3 register that is important, which may not
correspond to the cr3 value saved in "current".
So, I think using the "pid" and "comm" fields of current, even in NMI
context, is not a problem, just as you said. For early boot, the current
task will be init_task, which has pid = 0 and comm = "swapper", still
ok.
Thanks for pointing it out.
Mathieu
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
next prev parent reply other threads:[~2008-01-07 4:45 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-01-03 7:16 [RFC PATCH 00/11] mcount tracing utility Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 01/11] Add basic support for gcc profiler instrumentation Steven Rostedt
2008-01-03 8:31 ` Sam Ravnborg
2008-01-03 14:03 ` Steven Rostedt
2008-01-03 9:21 ` Ingo Molnar
2008-01-03 13:58 ` Steven Rostedt
2008-01-03 18:16 ` Chris Wright
2008-01-03 19:15 ` Steven Rostedt
2008-01-03 19:17 ` Chris Wright
2008-01-03 19:18 ` Jeremy Fitzhardinge
2008-01-03 16:01 ` Daniel Walker
2008-01-03 17:35 ` Mathieu Desnoyers
2008-01-03 17:55 ` Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 02/11] Add fastcall to do_IRQ for i386 Steven Rostedt
2008-01-03 17:36 ` Mathieu Desnoyers
2008-01-03 17:47 ` Steven Rostedt
2008-01-07 4:50 ` H. Peter Anvin
2008-01-07 12:42 ` Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 03/11] Annotate core code that should not be traced Steven Rostedt
2008-01-03 17:42 ` Mathieu Desnoyers
2008-01-03 18:07 ` Steven Rostedt
2008-01-03 18:34 ` Mathieu Desnoyers
2008-01-03 7:16 ` [RFC PATCH 04/11] i386: notrace annotations Steven Rostedt
2008-01-03 17:52 ` Mathieu Desnoyers
2008-01-03 7:16 ` [RFC PATCH 05/11] x86_64: " Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 06/11] add notrace annotations to vsyscall Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 07/11] mcount based trace in the form of a header file library Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 08/11] tracer add debugfs interface Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 09/11] mcount tracer output file Steven Rostedt
2008-01-03 7:16 ` [RFC PATCH 10/11] mcount tracer show task comm and pid Steven Rostedt
2008-01-03 17:56 ` Mathieu Desnoyers
2008-01-06 15:37 ` Ingo Molnar
2008-01-07 4:45 ` Mathieu Desnoyers [this message]
2008-01-09 16:45 ` Ingo Molnar
2008-01-03 7:16 ` [RFC PATCH 11/11] Add a symbol only trace output Steven Rostedt
2008-01-03 17:22 ` [RFC PATCH 00/11] mcount tracing utility Mathieu Desnoyers
2008-01-03 17:42 ` Steven Rostedt
2008-01-03 18:05 ` Andi Kleen
2008-01-04 6:42 ` Frank Ch. Eigler
2008-01-08 20:35 ` Tim Bird
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=20080107044506.GA1798@Krystal \
--to=mathieu.desnoyers@polymtl.ca \
--cc=a.p.zijlstra@chello.nl \
--cc=acme@ghostprotocols.net \
--cc=akpm@linux-foundation.org \
--cc=ghaskins@novell.com \
--cc=hch@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rostedt@goodmis.org \
--cc=sparclinux@vger.kernel.org \
--cc=srostedt@redhat.com \
--cc=torvalds@linux-foundation.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