On Sat, May 27, 2023 at 03:40:02PM +0200, Thomas Gleixner wrote: > On Fri, May 26 2023 at 12:14, Thomas Gleixner wrote: > > On Wed, May 24 2023 at 23:48, Kirill A. Shutemov wrote: > >> This patch causes boot regression on TDX guest. The guest crashes on SMP > >> bring up. > > The below should fix that. Sigh... Okay, this gets me fixes the boot for TDX guest: Tested-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> But it gets broken again on "x86/smpboot: Implement a bit spinlock to protect the realmode stack" with [ 0.554079] .... node #0, CPUs: #1 #2 [ 0.738071] Callback from call_rcu_tasks() invoked. [ 10.562065] CPU2 failed to report alive state [ 10.566337] #3 [ 20.570066] CPU3 failed to report alive state [ 20.574268] #4 ... Notably CPU1 is missing from "failed to report" list. So CPU1 takes the lock fine, but seems never unlocks it. Maybe trampoline_lock(%rip) in head_64.S somehow is not the same as &tr_lock in trampoline_64.S. I donno. I haven't find the root cause yet. But bypassing locking in LOAD_REALMODE_ESP makes the issue go away. I will look more into it. -- Kiryl Shutsemau / Kirill A. Shutemov
