On Mon, Jan 31, 2022 at 12:54:53AM -0700, Thomas Frohwein wrote:
> On Sat, 29 Jan 2022 12:15:10 -0300
> Martin Pieuchot <m...@openbsd.org> wrote:
>
> > On 28/01/22(Fri) 23:03, Thomas Frohwein wrote:
> > > On Sat, 29 Jan 2022 15:19:20 +1100
> > > Jonathan Gray <j...@jsg.id.au> wrote:
> > >
> > > > does this diff to revert uvm_fault.c rev 1.124 change anything?
> > >
> > > Unfortunately no. Same pmap error as in the original bug report occurs
> > > with a kernel with this diff.
> >
> > Could you submit a new bug report? Could you manage to include ps and the
> > trace of all the CPUs when the pmap corruption occurs?
>
> See below
>
> >
> > Do you have some steps to reproduce the corruption? Which program is
> > currently running? Is it multi-threaded? What is the simplest scenario
> > to trigger the corruption?
>
> It's during boot of the MP kernel. The only scenario I can provide is
> booting this machine with an MP kernel from January 18 or newer. If I
> boot SP kernel, or build an MP kernel with jsg@'s diff that adds
> `pool_debug = 2`, the panic does _not_ occur.
>
> Here some new (hand-typed from a picture) output when I boot a freshly
> downloaded snapshot MP kernel from January 30th (note this is an 8 core/16
> hyperthreads CPU; I have _not_ enabled hyperthreading). I attached dmesg from
> booting bsd.sp, too.
>
> ... (boot, see dmesg in original bugs@ submission)
> wsdisplay0: screen 1-5 added (std, vt100 emulation)
> iwm0: hw rev 0x200, fw ver 36.ca7b901d.0, address [...]
> va 7f7fffffb000 ppa ffffffffff000
> panic: pmap_get_ptp: unmanaged user PTP
> Stopped at db_enter+0x10: popq %rbp
> TID PID UID PRFLAGS PFLAGS CPU COMMAND
> * 28644 1 0 0 0 2K swapper
> db_enter() at db_enter+0x10
> panic(ffffffff81f3dd1f) at panic+0xbf
> pmap_get_ptp(fffffd888e52ee58,7f7fffffb000) at pmap_get_ptp+0x303
> pmap_enter(fffffd888e52ee58,7f7fffffb000,13d151000,3,22) at pmap_enter+0x188
> uvm_fault_lower(ffff8000156852a0,ffff8000156852d8,ffff800015685220,0) at
> uvm_fault_lower+0x63d
> uvm_fault(fffffd888e52fdd0,7f7fffffb000,0,2) at uvm_fault+0x1b3
> kpageflttrap(ffff800015685420,7f7fffffbff5) at kpageflttrap+0x12c
> kerntrap(ffff800015685420) at kerntrap+0x91
> alltraps_kern_meltdown() at alltraps_kern_meltdown+0x7b
> copyout() at copyout+0x53
> end trace frame: 0x0, count: 5
does this diff to provide stolen memory data help?
Index: sys/dev/pci/drm/i915/i915_drv.c
===================================================================
RCS file: /cvs/src/sys/dev/pci/drm/i915/i915_drv.c,v
retrieving revision 1.135
diff -u -p -r1.135 i915_drv.c
--- sys/dev/pci/drm/i915/i915_drv.c 19 Jan 2022 02:20:06 -0000 1.135
+++ sys/dev/pci/drm/i915/i915_drv.c 31 Jan 2022 11:20:04 -0000
@@ -2350,6 +2350,7 @@ inteldrm_match(struct device *parent, vo
}
int drm_gem_init(struct drm_device *);
+void intel_init_stolen_res(struct inteldrm_softc *);
void
inteldrm_attach(struct device *parent, struct device *self, void *aux)
@@ -2469,6 +2470,7 @@ inteldrm_attach(struct device *parent, s
return;
}
dev->pdev->irq = -1;
+ intel_init_stolen_res(dev_priv);
config_mountroot(self, inteldrm_attachhook);
}
Index: sys/dev/pci/drm/i915/intel_stolen.c
===================================================================
RCS file: /cvs/src/sys/dev/pci/drm/i915/intel_stolen.c,v
retrieving revision 1.2
diff -u -p -r1.2 intel_stolen.c
--- sys/dev/pci/drm/i915/intel_stolen.c 14 Jan 2022 06:53:11 -0000 1.2
+++ sys/dev/pci/drm/i915/intel_stolen.c 31 Jan 2022 11:25:37 -0000
@@ -163,7 +163,7 @@ intel_init_stolen_res(struct inteldrm_so
if (GRAPHICS_VER(dev_priv) >= 3 && GRAPHICS_VER(dev_priv) < 11)
stolen_base = gen3_stolen_base(dev_priv);
- else if (GRAPHICS_VER(dev_priv) == 11)
+ else if (GRAPHICS_VER(dev_priv) == 11 || GRAPHICS_VER(dev_priv) == 12)
stolen_base = gen11_stolen_base(dev_priv);
if (IS_I830(dev_priv) || IS_I845G(dev_priv))
@@ -177,7 +177,7 @@ intel_init_stolen_res(struct inteldrm_so
stolen_size = gen6_stolen_size(dev_priv);
else if (GRAPHICS_VER(dev_priv) == 8)
stolen_size = gen8_stolen_size(dev_priv);
- else if (GRAPHICS_VER(dev_priv) >= 9 && GRAPHICS_VER(dev_priv) < 12)
+ else if (GRAPHICS_VER(dev_priv) >= 9 && GRAPHICS_VER(dev_priv) <= 12)
stolen_size = gen9_stolen_size(dev_priv);
if (stolen_base == 0 || stolen_size == 0)
Index: sys/dev/pci/drm/i915/gt/intel_ggtt.c
===================================================================
RCS file: /cvs/src/sys/dev/pci/drm/i915/gt/intel_ggtt.c,v
retrieving revision 1.4
diff -u -p -r1.4 intel_ggtt.c
--- sys/dev/pci/drm/i915/gt/intel_ggtt.c 26 Jan 2022 01:46:12 -0000
1.4
+++ sys/dev/pci/drm/i915/gt/intel_ggtt.c 31 Jan 2022 11:33:05 -0000
@@ -1320,10 +1320,10 @@ static int ggtt_probe_hw(struct i915_ggt
}
/* GMADR is the PCI mmio aperture into the global GTT. */
- drm_dbg(&i915->drm, "GGTT size = %lluM\n", ggtt->vm.total >> 20);
- drm_dbg(&i915->drm, "GMADR size = %lluM\n",
+ drm_warn(&i915->drm, "GGTT size = %lluM\n", ggtt->vm.total >> 20);
+ drm_warn(&i915->drm, "GMADR size = %lluM\n",
(u64)ggtt->mappable_end >> 20);
- drm_dbg(&i915->drm, "DSM size = %lluM\n",
+ drm_warn(&i915->drm, "DSM size = %lluM\n",
(u64)resource_size(&intel_graphics_stolen_res) >> 20);
return 0;
