With lazy interrupt, we always call __check_irq_replaysome with
decrementers_next_tb to check if we need to replay timer interrupt.
So in hotplug case we also need to set decrementers_next_tb as MAX
to make sure __check_irq_replay don't replay timer interrupt
when return as we expect, otherwise we'll trap here infinitely.
Signed-off-by: Tiejun Chen <tiejun.chen@windriver.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
the variable backup_current_thread_info isn't freed before existing the
function.
Signed-off-by: Cong Ding <dinggnu@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
In preempt case current arch_local_irq_restore() from
preempt_schedule_irq() may enable hard interrupt but we really
should disable interrupts when we return from the interrupt,
and so that we don't get interrupted after loading SRR0/1.
Signed-off-by: Tiejun Chen <tiejun.chen@windriver.com>
CC: <stable@vger.kernel.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The calculation for the left shift of the mask OPROFILE_PM_PMCSEL_MSK has an
error. The calculation is should be to shift left by (max_cntrs - cntr) times
the width of the pmsel field width. However, the #define OPROFILE_MAX_PMC_NUM
was used instead of OPROFILE_PMSEL_FIELD_WIDTH. This patch fixes the
calculation.
Signed-off-by: Carl Love <cel@us.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
commit f96972f2dc "kernel/sys.c: call disable_nonboot_cpus() in
kernel_restart()"
added a call to disable_nonboot_cpus() on kernel_restart(), which tries
to shutdown all the CPUs except the first one. The issue with the PA
Semi, is that it does not support CPU hotplug.
When the call is made to __cpu_down(), it calls the notifiers
CPU_DOWN_PREPARE, and then tries to take the CPU down.
One of the notifiers to the CPU hotplug code, is the cpufreq. The
DOWN_PREPARE will call __cpufreq_remove_dev() which calls
cpufreq_driver->exit. The PA Semi exit handler unmaps regions of I/O
that is used by an interrupt that goes off constantly
(system_reset_common, but it goes off during normal system operations
too). I'm not sure exactly what this interrupt does.
Running a simple function trace, you can see it goes off quite a bit:
# tracer: function
#
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
<idle>-0 [001] 1558.859363: .pasemi_system_reset_exception <-.system_reset_exception
<idle>-0 [000] 1558.860112: .pasemi_system_reset_exception <-.system_reset_exception
<idle>-0 [000] 1558.861109: .pasemi_system_reset_exception <-.system_reset_exception
<idle>-0 [001] 1558.861361: .pasemi_system_reset_exception <-.system_reset_exception
<idle>-0 [000] 1558.861437: .pasemi_system_reset_exception <-.system_reset_exception
When the region is unmapped, the system crashes with:
Disabling non-boot CPUs ...
Error taking CPU1 down: -38
Unable to handle kernel paging request for data at address 0xd0000800903a0100
Faulting instruction address: 0xc000000000055fcc
Oops: Kernel access of bad area, sig: 11 [#1]
PREEMPT SMP NR_CPUS=64 NUMA PA Semi PWRficient
Modules linked in: shpchp
NIP: c000000000055fcc LR: c000000000055fb4 CTR: c0000000000df1fc
REGS: c0000000012175d0 TRAP: 0300 Not tainted (3.8.0-rc4-test-dirty)
MSR: 9000000000009032 <SF,HV,EE,ME,IR,DR,RI> CR: 24000088 XER: 00000000
SOFTE: 0
DAR: d0000800903a0100, DSISR: 42000000
TASK = c0000000010e9008[0] 'swapper/0' THREAD: c000000001214000 CPU: 0
GPR00: d0000800903a0000 c000000001217850 c0000000012167e0 0000000000000000
GPR04: 0000000000000000 0000000000000724 0000000000000724 0000000000000000
GPR08: 0000000000000000 0000000000000000 0000000000000001 0000000000a70000
GPR12: 0000000024000080 c00000000fff0000 ffffffffffffffff 000000003ffffae0
GPR16: ffffffffffffffff 0000000000a21198 0000000000000060 0000000000000000
GPR20: 00000000008fdd35 0000000000a21258 000000003ffffaf0 0000000000000417
GPR24: 0000000000a226d0 c000000000000000 0000000000000000 0000000000000000
GPR28: c00000000138b358 0000000000000000 c000000001144818 d0000800903a0100
NIP [c000000000055fcc] .set_astate+0x5c/0xa4
LR [c000000000055fb4] .set_astate+0x44/0xa4
Call Trace:
[c000000001217850] [c000000000055fb4] .set_astate+0x44/0xa4 (unreliable)
[c0000000012178f0] [c00000000005647c] .restore_astate+0x2c/0x34
[c000000001217980] [c000000000054668] .pasemi_system_reset_exception+0x6c/0x88
[c000000001217a00] [c000000000019ef0] .system_reset_exception+0x48/0x84
[c000000001217a80] [c000000000001e40] system_reset_common+0x140/0x180
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch fixes MAX_STACK_TRACE_ENTRIES too low warning for ppc32,
which is similar to commit 12660b17.
Reported-by: Christian Kujau <lists@nerdbynature.de>
Signed-off-by: Li Zhong <zhong@linux.vnet.ibm.com>
Tested-by: Christian Kujau <lists@nerdbynature.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Do some ground preparatory work before adding guest_enter()
and guest_exit() context tracking callbacks. Those will
be later used to read the guest cputime safely when we
run in full dynticks mode.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Gleb Natapov <gleb@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
If we want to stop the tick further idle, we need to be
able to account the cputime without using the tick.
Virtual based cputime accounting solves that problem by
hooking into kernel/user boundaries.
However implementing CONFIG_VIRT_CPU_ACCOUNTING require
low level hooks and involves more overhead. But we already
have a generic context tracking subsystem that is required
for RCU needs by archs which plan to shut down the tick
outside idle.
This patch implements a generic virtual based cputime
accounting that relies on these generic kernel/user hooks.
There are some upsides of doing this:
- This requires no arch code to implement CONFIG_VIRT_CPU_ACCOUNTING
if context tracking is already built (already necessary for RCU in full
tickless mode).
- We can rely on the generic context tracking subsystem to dynamically
(de)activate the hooks, so that we can switch anytime between virtual
and tick based accounting. This way we don't have the overhead
of the virtual accounting when the tick is running periodically.
And one downside:
- There is probably more overhead than a native virtual based cputime
accounting. But this relies on hooks that are already set anyway.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Li Zhong <zhong@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung.kim@lge.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
The guest TLB handling code should not have any insight into how the host
TLB shadow code works.
kvmppc_e500_tlbil_all() is a function that is used for distinction between
e500v2 and e500mc (E.HV) on how to flush shadow entries. This function really
is private between the e500.c/e500mc.c file and e500_mmu_host.c.
Instead of this one, use the public kvmppc_core_flush_tlb() function to flush
all shadow TLB entries. As a nice side effect, with this we also end up
flushing TLB1 entries which we forgot to do before.
Signed-off-by: Alexander Graf <agraf@suse.de>
Host shadow TLB flushing is logic that the guest TLB code should have
no insight about. Declare the internal clear_tlb_refs and clear_tlb1_bitmap
functions static to the host TLB handling file.
Instead of these, we can use the already exported kvmppc_core_flush_tlb().
This gives us a common API across the board to say "please flush any
pending host shadow translation".
Signed-off-by: Alexander Graf <agraf@suse.de>
When a host mapping fault happens in a guest TLB1 entry today, we
map the translated guest entry into the host's TLB1.
This isn't particularly clever when the guest is mapped by normal 4k
pages, since these would be a lot better to put into TLB0 instead.
This patch adds the required logic to map 4k TLB1 shadow maps into
the host's TLB0.
Signed-off-by: Alexander Graf <agraf@suse.de>
This patch splits the file e500_tlb.c into e500_mmu.c (guest TLB handling)
and e500_mmu_host.c (host TLB handling).
The main benefit of this split is readability and maintainability. It's
just a lot harder to write dirty code :).
Signed-off-by: Alexander Graf <agraf@suse.de>
When emulating tlbwe, we want to automatically map the entry that just got
written in our shadow TLB map, because chances are quite high that it's
going to be used very soon.
Today this happens explicitly, duplicating all the logic that is in
kvmppc_mmu_map() already. Just call that one instead.
Signed-off-by: Alexander Graf <agraf@suse.de>
When shadow mapping a page, mapping this page can fail. In that case we
don't have a shadow map.
Take this case into account, otherwise we might end up writing bogus TLB
entries into the host TLB.
While at it, also move the write_stlbe() calls into the respective TLBn
handlers.
Signed-off-by: Alexander Graf <agraf@suse.de>
When we invalidate shadow TLB maps on the host, we don't mark them
as not valid. But we should.
Fix this by removing the E500_TLB_VALID from their flags when
invalidating.
Signed-off-by: Alexander Graf <agraf@suse.de>
Later patches want to call the function and it doesn't have
dependencies on anything below write_host_tlbe.
Move it higher up in the file.
Signed-off-by: Alexander Graf <agraf@suse.de>
Definitions and macros for implementing soreusport.
Signed-off-by: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The CONFIG_EXPERIMENTAL config item has not carried much meaning for a
while now and is almost always enabled by default. As agreed during the
Linux kernel summit, remove it from any "depends on" lines in Kconfigs.
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The CONFIG_EXPERIMENTAL config item has not carried much meaning for a
while now and is almost always enabled by default. As agreed during the
Linux kernel summit, remove it from any "depends on" lines in Kconfigs.
CC: Arnd Bergmann <arnd@arndb.de>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The CONFIG_EXPERIMENTAL config item has not carried much meaning for a
while now and is almost always enabled by default. As agreed during the
Linux kernel summit, remove it from any "depends on" lines in Kconfigs.
CC: Kumar Gala <galak@kernel.crashing.org>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
The CONFIG_EXPERIMENTAL config item has not carried much meaning for a
while now and is almost always enabled by default. As agreed during the
Linux kernel summit, remove it from any "depends on" lines in Kconfigs.
CC: Alexander Graf <agraf@suse.de>
CC: Avi Kivity <avi@redhat.com>
CC: Marcelo Tosatti <mtosatti@redhat.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Fix up all callers as they were before, with make one change: an
unsigned module taints the kernel, but doesn't turn off lockdep.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
This is to fix up a build problem with a wireless driver due to the
dynamic-debug patches in this branch.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Guests can trigger MMIO exits using dcbf. Since we don't emulate cache
incoherent MMIO, just do nothing and move on.
Reported-by: Ben Collins <ben.c@servergy.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Tested-by: Ben Collins <ben.c@servergy.com>
CC: stable@vger.kernel.org
While a privileged program can open a raw socket, attach some
restrictive filter and drop its privileges (or send the socket to an
unprivileged program through some Unix socket), the filter can still
be removed or modified by the unprivileged program. This commit adds a
socket option to lock the filter (SO_LOCK_FILTER) preventing any
modification of a socket filter program.
This is similar to OpenBSD BIOCLOCK ioctl on bpf sockets, except even
root is not allowed change/drop the filter.
The state of the lock can be read with getsockopt(). No error is
triggered if the state is not changed. -EPERM is returned when a user
tries to remove the lock or to change/remove the filter while the lock
is active. The check is done directly in sk_attach_filter() and
sk_detach_filter() and does not affect only setsockopt() syscall.
Signed-off-by: Vincent Bernat <bernat@luffy.cx>
Signed-off-by: David S. Miller <davem@davemloft.net>
The purpose of this option is to allow ARM/etc systems that rely on the
class RTC subsystem to have the same kind of automatic NTP based
synchronization that we have on PC platforms. Today ARM does not
implement update_persistent_clock and makes extensive use of the class
RTC system.
When enabled CONFIG_RTC_SYSTOHC will provide a generic
rtc_update_persistent_clock that stores the current time in the RTC and
is intended complement the existing CONFIG_RTC_HCTOSYS option that loads
the RTC at boot.
Like with RTC_HCTOSYS the platform's update_persistent_clock is used
first, if it works. Platforms with mixed class RTC and non-RTC drivers
need to return ENODEV when class RTC should be used. Such an update for
PPC is included in this patch.
Long term, implementations of update_persistent_clock should migrate to
proper class RTC drivers and use CONFIG_RTC_SYSTOHC instead.
Tested on ARM kirkwood and PPC405
Signed-off-by: Jason Gunthorpe <jgunthorpe@obsidianresearch.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
The .dtsi now names all PSC nodes as "psc", so this ac97
check won't work. Check for ac97 PSC using compatible
property.
Signed-off-by: Anatolij Gustschin <agust@denx.de>
With allmodconfig we are getting:
drivers/tty/synclink_gt.c:160:12: error: conflicting types for 'set_break'
arch/powerpc/include/asm/debug.h:49:5: note: previous declaration of 'set_break' was here
drivers/tty/synclinkmp.c:526:12: error: conflicting types for 'set_break'
arch/powerpc/include/asm/debug.h:49:5: note: previous declaration of 'set_break' was here
This renames set_break to set_breakpoint to avoid this naming conflict
Signed-off-by: Michael Neuling <mikey@neuling.org>
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently we are getting:
arch/powerpc/kernel/kgdb.c: In function 'kgdb_arch_exit':
arch/powerpc/kernel/kgdb.c:492:2: error: '__debugger_breakx_match' undeclared (first use in this function)
arch/powerpc/kernel/kgdb.c:492:2: note: each undeclared identifier is reported only once for each function it appears in
Fix the typo.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The DSCR (aka Data Stream Control Register) is supported on some
server PowerPC chips and allow some control over the prefetch
of data streams.
The kernel already supports DSCR value per thread but there is also
a need in a ability to change it from an external process for
the specific pid.
The patch adds new register index PT_DSCR (index=44) which can be
set/get by:
ptrace(PTRACE_POKEUSER, traced_process, PT_DSCR << 3, dscr);
dscr = ptrace(PTRACE_PEEKUSER, traced_process, PT_DSCR << 3, NULL);
The patch does not increase PT_REGS_COUNT as the pt_regs struct has not
been changed.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The CONFIG_EXPERIMENTAL config item has not carried much meaning for a
while now and is almost always enabled by default. As agreed during the
Linux kernel summit, remove it from any "depends on" lines in Kconfigs.
CC: Geoff Levand <geoff@infradead.org>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Geoff Levand <geoff@infradead.org>
Pull KVM bugfixes from Marcelo Tosatti.
* git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: use dynamic percpu allocations for shared msrs area
KVM: PPC: Book3S HV: Fix compilation without CONFIG_PPC_POWERNV
powerpc: Corrected include header path in kvm_para.h
Add rcu user eqs exception hooks for async page fault
We need to be able to read and write the contents of the EPR register
from user space.
This patch implements that logic through the ONE_REG API and declares
its (never implemented) SREGS counterpart as deprecated.
Signed-off-by: Alexander Graf <agraf@suse.de>
The External Proxy Facility in FSL BookE chips allows the interrupt
controller to automatically acknowledge an interrupt as soon as a
core gets its pending external interrupt delivered.
Today, user space implements the interrupt controller, so we need to
check on it during such a cycle.
This patch implements logic for user space to enable EPR exiting,
disable EPR exiting and EPR exiting itself, so that user space can
acknowledge an interrupt when an external interrupt has successfully
been delivered into the guest vcpu.
Signed-off-by: Alexander Graf <agraf@suse.de>
The EPR register is potentially valid for PR KVM as well, so we need
to emulate accesses to it. It's only defined for reading, so only
handle the mfspr case.
Signed-off-by: Alexander Graf <agraf@suse.de>
When injecting an interrupt into guest context, we usually don't need
to check for requests anymore. At least not until today.
With the introduction of EPR, we will have to create a request when the
guest has successfully accepted an external interrupt though.
So we need to prepare the interrupt delivery to abort guest entry
gracefully. Otherwise we'd delay the EPR request.
Signed-off-by: Alexander Graf <agraf@suse.de>
On mfspr/mtspr emulation path Book3E's MMUCFG SPR with value 1015 clashes
with G4's MSSSR0 SPR. Move MSSSR0 emulation from generic part to Books3S.
MSSSR0 also clashes with Book3S's DABRX SPR. DABRX was not explicitly
handled so Book3S execution flow will behave as before.
Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
When running on top of pHyp, the hypercall instruction "sc 1" goes
straight into pHyp without trapping in supervisor mode.
So if we want to support PAPR guest in this configuration we need to
add a second way of accessing PAPR hypercalls, preferably with the
exact same semantics except for the instruction.
So let's overlay an officially reserved instruction and emulate PAPR
hypercalls whenever we hit that one.
Signed-off-by: Alexander Graf <agraf@suse.de>
When we hit an emulation result that we didn't expect, that is an error,
but it's nothing that warrants a BUG(), because it can be guest triggered.
So instead, let's only WARN() the user that this happened.
Signed-off-by: Alexander Graf <agraf@suse.de>
The FWNMI region is fixed at 0x7000 and the vector are now
overflowing that with some configurations. Fix that by moving
some hash management code out of that region as it doesn't need
to be that close to the call sites (isn't accessed using
conditional branches).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On POWER7 when we have really small counts left before overflow, we can take a
PMU IRQ, but the PMC gets wound back to just before the overflow.
If the kernel is setting the PMC to a value just before the overflow, we can
get interrupted again without the PMC making any progress (ie another buggy
overflow). In this case, we can end up making no forward progress, with the
PMC interrupt returning us to the same count over and over.
The below detects when we are making no forward progress (ie. delta = 0) and
then increases the amount left before the overflow. This stops us from locking
up.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Reviewed-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
cc: Paul Mackerras <paulus@samba.org>
cc: Anton Blanchard <anton@samba.org>
cc: Linux PPC dev <linuxppc-dev@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
If a PMC is about to overflow on a counter that's on an active perf event
(ie. less than 256 from the end) and a _different_ PMC overflows just at this
time (a PMC that's not on an active perf event), we currently mark the event as
found, but in reality it's not as it's likely the other PMC that caused the
IRQ. Since we mark it as found the second catch all for overflows doesn't run,
and we don't reset the overflowing PMC ever. Hence we keep hitting that same
PMC IRQ over and over and don't reset the actual overflowing counter.
This is a rewrite of the perf interrupt handler for book3s to get around this.
We now check to see if any of the PMCs have actually overflowed (ie >=
0x80000000). If yes, record it for active counters and just reset it for
inactive counters. If it's not overflowed, then we check to see if it's one of
the buggy power7 counters and if it is, record it and continue. If none of the
PMCs match this, then we make note that we couldn't find the PMC that caused
the IRQ.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Reviewed-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
cc: Paul Mackerras <paulus@samba.org>
cc: Anton Blanchard <anton@samba.org>
cc: Linux PPC dev <linuxppc-dev@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The DDW code uses a eeh_dev struct from the pci_dev. However, this is
not set until eeh_add_device_late is called.
Since pci_bus_add_devices is called before eeh_add_device_late, the PCI
devices are added to the bus, making drivers' probe hooks to be called.
These will call set_dma_mask, which will call the DDW code, which will
require the eeh_dev struct from pci_dev. This would result in a crash,
due to a NULL dereference.
Calling eeh_add_device_late after pci_bus_add_devices would make the
system BUG, because device files shouldn't be added to devices there
were not added to the system. So, a new function is needed to add such
files only after pci_bus_add_devices have been called.
Cc: stable@vger.kernel.org
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Acked-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The functions used are already defined as empty inline functions for the
case where EEH is disabled.
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@linux.vnet.ibm.com>
Acked-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
