From: Andy Lutomirski <luto@kernel.org>
To: Lai Jiangshan <jiangshanlai+lkml@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>,
Lai Jiangshan <laijs@linux.alibaba.com>,
LKML <linux-kernel@vger.kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Thomas Gleixner <tglx@linutronix.de>, X86 ML <x86@kernel.org>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
"H. Peter Anvin" <hpa@zytor.com>,
Alexandre Chartre <alexandre.chartre@oracle.com>,
Steven Rostedt <rostedt@goodmis.org>,
Masami Hiramatsu <mhiramat@kernel.org>
Subject: Re: [RFC PATCH V2 4/7] x86/hw_breakpoint: Prevent data breakpoints on user_pcid_flush_mask
Date: Mon, 25 May 2020 21:38:51 -0700 [thread overview]
Message-ID: <CALCETrW6mazV1JVXYtGW7tUXveNvMKnFwi4zqWUgwMXax_Ea_Q@mail.gmail.com> (raw)
In-Reply-To: <CAJhGHyC82f+=YXYmv8zC=zPxZmk+TW_n+5pjcBE-2T8S9t5K0g@mail.gmail.com>
On Mon, May 25, 2020 at 9:31 PM Lai Jiangshan
<jiangshanlai+lkml@gmail.com> wrote:
>
> On Tue, May 26, 2020 at 12:21 PM Andy Lutomirski <luto@kernel.org> wrote:
> >
> > On Mon, May 25, 2020 at 6:42 PM Lai Jiangshan <laijs@linux.alibaba.com> wrote:
> > >
> > > The percpu user_pcid_flush_mask is used for CPU entry
> > > If a data breakpoint on it, it will cause an unwanted #DB.
> > > Protect the full cpu_tlbstate structure to be sure.
> > >
> > > There are some other percpu data used in CPU entry, but they are
> > > either in already-protected cpu_tss_rw or are safe to trigger #DB
> > > (espfix_waddr, espfix_stack).
> >
> > How hard would it be to rework this to have DECLARE_PERCPU_NODEBUG()
> > and DEFINE_PERCPU_NODEBUG() or similar?
>
>
> I don't know, but it is an excellent idea. Although the patchset
> protects only 2 or 3 portions of percpu data, but there is many
> percpu data used in tracing or kprobe code. They are needed to be
> protected too.
>
> Adds CC:
> Steven Rostedt <rostedt@goodmis.org>
> Masami Hiramatsu <mhiramat@kernel.org>
PeterZ is moving things in the direction of more aggressively
disabling hardware breakpoints in the nasty paths where we won't
survive a hardware breakpoint. Does the tracing code have portions
that won't survive a limited amount of recursion?
I'm hoping that we can keep the number of no-breakpoint-here percpu
variables low. Maybe we could recruit objtool to help make sure we
got all of them, but that would be a much larger project.
Would we currently survive a breakpoint on the thread stack? I don't
see any extremely obvious reason that we wouldn't. Blocking such a
breakpoint would be annoying.
next prev parent reply other threads:[~2020-05-26 4:39 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-05-25 14:50 [RFC PATCH 0/5] x86/hw_breakpoint: protects more cpu entry data Lai Jiangshan
2020-05-25 14:50 ` [RFC PATCH 1/5] x86/hw_breakpoint: add within_area() to check data breakpoints Lai Jiangshan
2020-05-25 14:50 ` [RFC PATCH 2/5] x86/hw_breakpoint: Prevent data breakpoints on direct GDT Lai Jiangshan
2020-05-25 14:51 ` [RFC PATCH 3/5] x86/hw_breakpoint: Prevent data breakpoints on per_cpu cpu_tss_rw Lai Jiangshan
2020-05-25 14:51 ` [RFC PATCH 4/5] x86/hw_breakpoint: Prevent data breakpoints on user_pcid_flush_mask Lai Jiangshan
2020-05-25 14:51 ` [RFC PATCH 5/5] x86/hw_breakpoint: Prevent data breakpoints on debug_idt_table Lai Jiangshan
2020-05-25 15:25 ` [RFC PATCH 0/5] x86/hw_breakpoint: protects more cpu entry data Peter Zijlstra
2020-05-26 1:42 ` [RFC PATCH V2 0/7] x86/DB: protects more cpu entry data and Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 1/7] x86/hw_breakpoint: add within_area() to check data breakpoints Lai Jiangshan
2020-05-30 9:57 ` [tip: x86/entry] x86/hw_breakpoint: Add " tip-bot2 for Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 2/7] x86/hw_breakpoint: Prevent data breakpoints on direct GDT Lai Jiangshan
2020-05-30 9:57 ` [tip: x86/entry] " tip-bot2 for Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 3/7] x86/hw_breakpoint: Prevent data breakpoints on per_cpu cpu_tss_rw Lai Jiangshan
2020-05-30 9:57 ` [tip: x86/entry] " tip-bot2 for Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 4/7] x86/hw_breakpoint: Prevent data breakpoints on user_pcid_flush_mask Lai Jiangshan
2020-05-26 4:17 ` Andy Lutomirski
2020-05-26 4:31 ` Lai Jiangshan
2020-05-26 4:38 ` Andy Lutomirski [this message]
2020-05-26 5:48 ` Lai Jiangshan
2020-05-30 9:57 ` [tip: x86/entry] " tip-bot2 for Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 5/7] x86/entry: don't shift stack on #DB Lai Jiangshan
2020-05-26 9:10 ` Peter Zijlstra
2020-05-26 1:42 ` [RFC PATCH V2 6/7] x86/entry: is_debug_stack() don't check of DB1 stack Lai Jiangshan
2020-05-26 1:42 ` [RFC PATCH V2 7/7] x86/entry: remove DB1 stack and DB2 hole from cpu entry area Lai Jiangshan
2020-05-26 1:48 ` [RFC PATCH 0/5] x86/hw_breakpoint: protects more cpu entry data Lai Jiangshan
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=CALCETrW6mazV1JVXYtGW7tUXveNvMKnFwi4zqWUgwMXax_Ea_Q@mail.gmail.com \
--to=luto@kernel.org \
--cc=alexandre.chartre@oracle.com \
--cc=bp@alien8.de \
--cc=hpa@zytor.com \
--cc=jiangshanlai+lkml@gmail.com \
--cc=laijs@linux.alibaba.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mhiramat@kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.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;
as well as URLs for NNTP newsgroup(s).