Content-Type: multipart/mixed; boundary="===============0191992668360117787==" MIME-Version: 1.0 From: Sean Christopherson To: lkp@lists.01.org Subject: Re: [x86/entry_32] aa93e2ad74: BUG:soft_lockup-CPU##stuck_for#s![systemd-logind:#] Date: Wed, 12 Jan 2022 16:14:19 +0000 Message-ID: In-Reply-To: List-Id: --===============0191992668360117787== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On Wed, Jan 12, 2022, Peter Zijlstra wrote: > On Wed, Jan 12, 2022 at 01:28:58AM +0000, Sean Christopherson wrote: > > The issue is that PARANOID_EXIT_TO_KERNEL_MODE in the handle_exception_= return > > path overwrites the entry stack data with the task stack data, restorin= g the "bad" > > segment value. > = > Oh gawd... that's terrible, and yes, that now makes perfect sense. > = > However did you find that? printf and running under QEMU, which has a interactive "monitor" that lets = you read/write guest memory and can also do VA=3D>PA translations. Code inspec= tion once I realized the value on the stack was being restored between the excep= tion fixup and the POP. --===============0191992668360117787==--