Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Mon, 11 May 2020 16:13:48 +0200
From:   Peter Zijlstra <peterz@infradead.org>
To:     Alexandre Chartre <alexandre.chartre@oracle.com>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        LKML <linux-kernel@vger.kernel.org>, x86@kernel.org,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Andy Lutomirski <luto@kernel.org>,
        Frederic Weisbecker <frederic@kernel.org>,
        Paolo Bonzini <pbonzini@redhat.com>,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Masami Hiramatsu <mhiramat@kernel.org>,
        Petr Mladek <pmladek@suse.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Joel Fernandes <joel@joelfernandes.org>,
        Boris Ostrovsky <boris.ostrovsky@oracle.com>,
        Juergen Gross <jgross@suse.com>,
        Brian Gerst <brgerst@gmail.com>,
        Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
        Josh Poimboeuf <jpoimboe@redhat.com>,
        Will Deacon <will@kernel.org>
Subject: Re: [patch V4 part 5 07/31] x86/entry: Provide
 idtentry_entry/exit_cond_rcu()
Message-ID: <20200511141348.GH2957@hirez.programming.kicks-ass.net>
References: <20200505135341.730586321@linutronix.de>
 <20200505135828.808686575@linutronix.de>
 <72cb3e24-3f82-7e2a-7630-233749c780c4@oracle.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <72cb3e24-3f82-7e2a-7630-233749c780c4@oracle.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Mon, May 11, 2020 at 03:53:17PM +0200, Alexandre Chartre wrote:
> 
> On 5/5/20 3:53 PM, Thomas Gleixner wrote:
> > The pagefault handler cannot use the regular idtentry_enter() because on
> > that invokes rcu_irq_enter() the pagefault was caused in the kernel.
> 
> I am struggling to understand this part of the sentence: "because on
> that invokes rcu_irq_enter() the pagefault was caused in the kernel."
> 
> Do you mean: "because that invokes rcu_irq_enter() if the pagefault was
> caused in the kernel." ?

The problem is that rcu_irq_enter() uses per-cpu state and expect
rcu_irq_exit() to be called on the very same cpu we did enter on.

However, #PF likes to schedule and breaks that expectation.

While there are more exceptions that schedule when from userspace, #PF
is the only one that does so when from kernel space, which makes is
'special'.