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;
From:   Siarhei Liakh <Siarhei.Liakh@concurrent-rt.com>
To:     "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "x86@kernel.org" <x86@kernel.org>
CC:     Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Andy Lutomirski <luto@kernel.org>,
        "Borislav Petkov" <bpetkov@suse.de>
Subject: [PATCH] x86: Call fixup_exception() before notify_die() in
 math_error()
Thread-Topic: [PATCH] x86: Call fixup_exception() before notify_die() in
 math_error()
Thread-Index: AQHUBBaUW86w1+9ez0usdUxJuRkw3w==
Date:   Thu, 14 Jun 2018 19:36:07 +0000
Message-ID: <DM5PR11MB201156F1CAB2592B07C79A03B17D0@DM5PR11MB2011.namprd11.prod.outlook.com>
Accept-Language: en-US
Content-Language: en-US
received-spf: None (protection.outlook.com: concurrent-rt.com does not
 designate permitted sender hosts)
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 39e6f40c-13e6-4ffe-ef43-08d5d22e1309
X-MS-Exchange-CrossTenant-originalarrivaltime: 14 Jun 2018 19:36:07.0798
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 38747689-e6b0-4933-86c0-1116ee3ef93e
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DM5PR11MB1756
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

fpu__drop() has an explicit fwait which under some conditions can trigger
a fixable FPU exception while in kernel. Thus, we should attempt to fixup
the exception first, and only call notify_die() if the fixup failed just
like in do_general_protection(). The original call sequence incorrectly
triggers KDB entry on debug kernels under particular FPU-intensive
workloads. This issue had been privately observed, fixed, and tested=20
on 4.9.98, while this patch brings the fix to the upstream.

Signed-off-by: Siarhei Liakh <siarhei.liakh@concurrent-rt.com>
---

diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index a535dd6..68d77a3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -835,16 +835,18 @@ static void math_error(struct pt_regs *regs, int erro=
r_code, int trapnr)
 	char *str =3D (trapnr =3D=3D X86_TRAP_MF) ? "fpu exception" :
 						"simd exception";
=20
-	if (notify_die(DIE_TRAP, str, regs, error_code, trapnr, SIGFPE) =3D=3D NO=
TIFY_STOP)
-		return;
 	cond_local_irq_enable(regs);
=20
 	if (!user_mode(regs)) {
-		if (!fixup_exception(regs, trapnr)) {
-			task->thread.error_code =3D error_code;
-			task->thread.trap_nr =3D trapnr;
+		if (fixup_exception(regs, trapnr))
+			return;
+
+		task->thread.error_code =3D error_code;
+		task->thread.trap_nr =3D trapnr;
+
+		if (notify_die(DIE_TRAP, str, regs, error_code,
+					trapnr, SIGFPE) !=3D NOTIFY_STOP)
 			die(str, regs, error_code);
-		}
 		return;
 	}
 =