Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
MIME-Version: 1.0
References: <CADDKRnBD=cgptLmDMu0YiaUThO-1ydKaAD4X3sTWfLuP5M5BEw@mail.gmail.com>
 <alpine.DEB.2.21.1804302151530.1596@nanos.tec.linutronix.de>
 <CADDKRnAi69PFNH-hyxCTLckJ5UU6-DKWvzGNzxZZhD0sA215qg@mail.gmail.com> <alpine.DEB.2.21.1805011458390.1596@nanos.tec.linutronix.de>
In-Reply-To: <alpine.DEB.2.21.1805011458390.1596@nanos.tec.linutronix.de>
From:   Linus Torvalds <torvalds@linux-foundation.org>
Date:   Tue, 01 May 2018 20:14:37 +0000
Message-ID: <CA+55aFxKbPDrMQssyEtOnYZqE8HcOo=Zx6ASty6CybhwPfT9_g@mail.gmail.com>
Subject: Re: [v4.17-rcx] Lost IBPB, IBRS_FW support for spectre_v2 mitigation.
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     =?UTF-8?Q?J=C3=B6rg_Otte?= <jrg.otte@gmail.com>,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Borislav Petkov <bp@alien8.de>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, May 1, 2018 at 5:59 AM Thomas Gleixner <tglx@linutronix.de> wrote:

> Then I really have no idea how reverting the patch you pointed out would
> fix it.

So I do think that the original patch is buggy.

What I think *may* be going on is:

  - first we do that

                 get_cpu_cap(c);
                 get_cpu_address_sizes(c);

     but at that point, CPU levels may be masked, and that 0x80000008 leaf
isn't seen

  - then we do

                 if (this_cpu->c_early_init)
                         this_cpu->c_early_init(c);

    which calls early_init_intel(), which does that

                 if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
                                   MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) >
0) {

    which now raises the cpuid_level.

  - then we do

                         get_cpu_cap(c);

    again, because the cpuid level has been raised, and _now_ it used to ge=
t
that 0x80000008 leaf information.

But with the change, that second call to get_cpu_cap() didn't do anything,
because the 0x80000008 leaf handling had been moved away.

However, I agree that your patch to just do that CPUID_8000_0008_EBX in
get_cpu_cap() should have fixed it, and it's possible that J=C3=B6rg mis-te=
sted
it.

J=C3=B6rg, are you sure you didn't somehow get the wrong microcode? Because
another way for those bits to be cleared again is if
bad_spectre_microcode() triggers. That should show up in dmesg as "Intel
Spectre v2 broken microcode detected" though.

            Linus