Re: x86: Spurious vectors not handled robustly

2019-06-24 Thread Thomas Gleixner
On Mon, 24 Jun 2019, Thomas Gleixner wrote: > > +#ifdef CONFIG_X86_LOCAL_APIC > + .align 8 > +ENTRY(spurious_entries_start) > +vector=FIRST_SYSTEM_VECTOR > +.rept (NR_VECTORS - FIRST_SYSTEM_VECTOR) > + pushl $(~vector+0x80) /* Note: always in signed byte > range

Re: x86: Spurious vectors not handled robustly

2019-06-24 Thread Thomas Gleixner
On Mon, 24 Jun 2019, Thomas Gleixner wrote: > On Mon, 24 Jun 2019, Jan Kiszka wrote: > > On 24.06.19 12:09, Thomas Gleixner wrote: > > > If it is a vectored one it _IS_ acked. > > > > > > inc_irq_stat(irq_spurious_count); > > > > > > /* see sw-dev-man vol 3, chapter 7.4.13.5 */

Re: x86: Spurious vectors not handled robustly

2019-06-24 Thread Jan Kiszka
On 24.06.19 12:09, Thomas Gleixner wrote: Jan, On Mon, 24 Jun 2019, Jan Kiszka wrote: probably since "x86: Avoid building unused IRQ entry stubs" (2414e021ac8d), the kernel can no longer tell spurious IRQs by the APIC apart from spuriously triggered unused vectors. Err. It does. We've manag

Re: x86: Spurious vectors not handled robustly

2019-06-24 Thread Thomas Gleixner
On Mon, 24 Jun 2019, Jan Kiszka wrote: > On 24.06.19 12:09, Thomas Gleixner wrote: > > If it is a vectored one it _IS_ acked. > > > > inc_irq_stat(irq_spurious_count); > > > > /* see sw-dev-man vol 3, chapter 7.4.13.5 */ > > pr_info("spurious APIC interrupt through vector %0

Re: x86: Spurious vectors not handled robustly

2019-06-24 Thread Thomas Gleixner
Jan, On Mon, 24 Jun 2019, Jan Kiszka wrote: > probably since "x86: Avoid building unused IRQ entry stubs" (2414e021ac8d), > the kernel can no longer tell spurious IRQs by the APIC apart from spuriously > triggered unused vectors. Err. It does. > We've managed to trigger such a cause with the Jai