From: Oleg Nesterov <oleg@redhat.com>
To: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Rabin Vincent <rabin@rab.in>,
linux-kernel@vger.kernel.org,
linux-arm-kernel@lists.infradead.org,
Peter Zijlstra <peterz@infradead.org>,
Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Subject: Re: [PATCH 6/9] uprobes: flush cache after xol write
Date: Fri, 26 Oct 2012 18:39:51 +0200 [thread overview]
Message-ID: <20121026163951.GA17742@redhat.com> (raw)
In-Reply-To: <20121026055239.GA4862@in.ibm.com>
On 10/26, Ananth N Mavinakayanahalli wrote:
>
> On Thu, Oct 25, 2012 at 04:58:39PM +0200, Oleg Nesterov wrote:
> > On 10/16, Rabin Vincent wrote:
> > >
> > > >> --- a/kernel/events/uprobes.c
> > > >> +++ b/kernel/events/uprobes.c
> > > >> @@ -1246,6 +1246,7 @@ static unsigned long xol_get_insn_slot(struct uprobe *uprobe, unsigned long slot
> > > >> offset = current->utask->xol_vaddr & ~PAGE_MASK;
> > > >> vaddr = kmap_atomic(area->page);
> > > >> arch_uprobe_xol_copy(&uprobe->arch, vaddr + offset);
> > > >> + flush_dcache_page(area->page);
> > > >> kunmap_atomic(vaddr);
> > > >
> > > > I agree... but why under kmap_atomic?
> > >
> > > No real reason; I'll move it to after the unmap.
> >
> > OK. I assume you will send v2.
> >
> > But this patch looks like a bugfix, flush_dcache_page() is not a nop
> > on powerpc. So perhaps we should apply this fix right now?
>
> Starting Power5, all Power processers have coherent caches.
>
> > OTOH, I do not understand this stuff, everything is nop on x86. And
> > when I look into Documentation/cachetlb.txt I am starting to think
> > that may be this needs flush_icache_user_range instead?
> >
> > Rabin, Ananth could you clarify this?
>
> Yes. We need flush_icache_user_range(). Though for x86 its always been a
> nop, one never knows if there is some Power4 or older machine out there
> that is still being used. We are fine for Power5 and later.
This is bad...
flush_icache_user needs vma. perhaps just to check VM_EXEC...
So let me repeat to be sure I really understand, do you confirm that
_in general_ flush_dcache_page() is not enough?
Oleg.
next prev parent reply other threads:[~2012-10-26 16:39 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-10-14 19:23 [PATCH 1/9] uprobes: move function declarations out of arch Rabin Vincent
2012-10-14 19:23 ` [PATCH 2/9] uprobes: check for single step support Rabin Vincent
2012-10-17 16:40 ` Srikar Dronamraju
2012-10-17 17:02 ` Oleg Nesterov
2012-10-14 19:23 ` [PATCH 3/9] uprobes: allow ignoring of probe hits Rabin Vincent
2012-10-15 16:52 ` Oleg Nesterov
2012-10-16 20:11 ` Rabin Vincent
2012-10-17 17:35 ` Oleg Nesterov
2012-10-21 18:15 ` Rabin Vincent
2012-10-21 19:40 ` Oleg Nesterov
2012-10-17 16:52 ` Srikar Dronamraju
2012-10-14 19:23 ` [PATCH 4/9] uprobes: allow arch access to xol slot Rabin Vincent
2012-10-17 17:17 ` Srikar Dronamraju
2012-10-14 19:23 ` [PATCH 5/9] uprobes: allow arch-specific initialization Rabin Vincent
2012-10-18 9:39 ` Srikar Dronamraju
2012-10-14 19:23 ` [PATCH 6/9] uprobes: flush cache after xol write Rabin Vincent
2012-10-15 16:57 ` Oleg Nesterov
2012-10-16 20:29 ` Rabin Vincent
2012-10-25 14:58 ` Oleg Nesterov
2012-10-26 5:52 ` Ananth N Mavinakayanahalli
2012-10-26 16:39 ` Oleg Nesterov [this message]
2012-10-29 5:35 ` Ananth N Mavinakayanahalli
2012-11-03 16:33 ` Oleg Nesterov
2012-11-04 14:29 ` Ananth N Mavinakayanahalli
2012-11-14 17:37 ` Oleg Nesterov
2012-10-14 19:23 ` [PATCH 7/9] uprobes: add arch write opcode hook Rabin Vincent
2012-10-14 19:23 ` [PATCH 8/9] ARM: support uprobe handling Rabin Vincent
2012-11-04 10:13 ` Russell King - ARM Linux
2012-11-12 17:26 ` Rabin Vincent
2012-10-14 19:23 ` [PATCH 9/9] ARM: add uprobes support Rabin Vincent
2012-10-15 11:14 ` Dave Martin
2012-10-15 11:44 ` Rabin Vincent
2012-10-15 17:44 ` Dave Martin
2012-10-17 14:50 ` Jon Medhurst (Tixy)
2012-10-21 18:43 ` Rabin Vincent
2012-10-21 18:59 ` Rabin Vincent
2012-10-15 17:31 ` Dave Martin
2012-10-21 18:27 ` Rabin Vincent
2012-10-17 17:54 ` Oleg Nesterov
2012-10-15 17:19 ` [PATCH 1/9] uprobes: move function declarations out of arch Srikar Dronamraju
2012-10-16 20:30 ` Rabin Vincent
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=20121026163951.GA17742@redhat.com \
--to=oleg@redhat.com \
--cc=ananth@in.ibm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=rabin@rab.in \
--cc=srikar@linux.vnet.ibm.com \
/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).