Skip to content

L
linux
Switch branch/tag
  1. 31 Mar, 2018 15 commits
    • Nicholas Piggin's avatar
      powerpc/64s: return more carefully from sreset NMI · 15b4dd79
      Nicholas Piggin authored 
      System Reset, being an NMI, must return more carefully than other
interrupts. It has traditionally returned via the nromal return
from exception path, but that has a number of problems.

- r13 does not get restored if returning to kernel. This is for
  interrupts which may cause a context switch, which sreset will
  never do. Interrupting OPAL (which uses a different r13) is one
  place where this causes breakage.

- It may cause several other problems returning to kernel with
  preempt or TIF_EMULATE_STACK_STORE if it hits at the wrong time.

It's safer just to have a simple restore and return, like machine
check which is the other NMI.
Signed-off-by: default avatarNicholas Piggin <npiggin@gmail.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      15b4dd79
    • Michael Neuling's avatar
      powerpc/eeh: Fix race with driver un/bind · f0295e04
      Michael Neuling authored 
      The current EEH callbacks can race with a driver unbind. This can
result in a backtraces like this:

  EEH: Frozen PHB#0-PE#1fc detected
  EEH: PE location: S000009, PHB location: N/A
  CPU: 2 PID: 2312 Comm: kworker/u258:3 Not tainted 4.15.6-openpower1 #2
  Workqueue: nvme-wq nvme_reset_work [nvme]
  Call Trace:
    dump_stack+0x9c/0xd0 (unreliable)
    eeh_dev_check_failure+0x420/0x470
    eeh_check_failure+0xa0/0xa4
    nvme_reset_work+0x138/0x1414 [nvme]
    process_one_work+0x1ec/0x328
    worker_thread+0x2e4/0x3a8
    kthread+0x14c/0x154
    ret_from_kernel_thread+0x5c/0xc8
  nvme nvme1: Removing after probe failure status: -19
  <snip>
  cpu 0x23: Vector: 300 (Data Access) at [c000000ff50f3800]
      pc: c0080000089a0eb0: nvme_error_detected+0x4c/0x90 [nvme]
      lr: c000000000026564: eeh_report_error+0xe0/0x110
      sp: c000000ff50f3a80
     msr: 9000000000009033
     dar: 400
   dsisr: 40000000
    current = 0xc000000ff507c000
    paca    = 0xc00000000fdc9d80   softe: 0        irq_happened: 0x01
      pid   = 782, comm = eehd
  Linux version 4.15.6-openpower1 (smc@smc-desktop) (gcc version 6.4.0 (Buildroot 2017.11.2-00008-g4b6188e)) #2 SM                                             P Tue Feb 27 12:33:27 PST 2018
  enter ? for help
    eeh_report_error+0xe0/0x110
    eeh_pe_dev_traverse+0xc0/0xdc
    eeh_handle_normal_event+0x184/0x4c4
    eeh_handle_event+0x30/0x288
    eeh_event_handler+0x124/0x170
    kthread+0x14c/0x154
    ret_from_kernel_thread+0x5c/0xc8

The first part is an EEH (on boot), the second half is the resulting
crash. nvme probe starts the nvme_reset_work() worker thread. This
worker thread starts touching the device which see a device error
(EEH) and hence queues up an event in the powerpc EEH worker
thread. nvme_reset_work() then continues and runs
nvme_remove_dead_ctrl_work() which results in unbinding the driver
from the device and hence releases all resources. At the same time,
the EEH worker thread starts doing the EEH .error_detected() driver
callback, which no longer works since the resources have been freed.

This fixes the problem in the same way the generic PCIe AER code (in
drivers/pci/pcie/aer/aerdrv_core.c) does. It makes the EEH code hold
the device_lock() while performing the driver EEH callbacks and
associated code. This ensures either the callbacks are no longer
register, or if they are registered the driver will not be removed
from underneath us.

This has been broken forever. The EEH call backs were first introduced
in 2005 (in 77bd7415) but it's not clear if a lock was needed back
then.

Fixes: 77bd7415 ("[PATCH] powerpc: PCI Error Recovery: PPC64 core recovery routines")
Cc: stable@vger.kernel.org # v2.6.16+
Signed-off-by: default avatarMichael Neuling <mikey@neuling.org>
Reviewed-by: default avatarBenjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      f0295e04
    • Thiago Jung Bauermann's avatar
      powerpc/kexec_file: Fix error code when trying to load kdump kernel · bf8a1abc
      Thiago Jung Bauermann authored 
      kexec_file_load() on powerpc doesn't support kdump kernels yet, so it
returns -ENOTSUPP in that case.

I've recently learned that this errno is internal to the kernel and
isn't supposed to be exposed to userspace. Therefore, change to
-EOPNOTSUPP which is defined in an uapi header.

This does indeed make kexec-tools happier. Before the patch, on
ppc64le:

  # ~bauermann/src/kexec-tools/build/sbin/kexec -s -p /boot/vmlinuz
  kexec_file_load failed: Unknown error 524

After the patch:

  # ~bauermann/src/kexec-tools/build/sbin/kexec -s -p /boot/vmlinuz
  kexec_file_load failed: Operation not supported

Fixes: a0458284 ("powerpc: Add support code for kexec_file_load()")
Cc: stable@vger.kernel.org # v4.10+
Reported-by: default avatarDave Young <dyoung@redhat.com>
Signed-off-by: default avatarThiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
Reviewed-by: default avatarSimon Horman <horms@verge.net.au>
Reviewed-by: default avatarDave Young <dyoung@redhat.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      bf8a1abc
    • Jonathan Neuschäfer's avatar
      powerpc/mm/32: Remove the reserved memory hack · 7e140591
      Jonathan Neuschäfer authored 
      This hack, introduced in commit c5df7f77 ("powerpc: allow ioremap
within reserved memory regions") is now unnecessary.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      7e140591
    • Jonathan Neuschäfer's avatar
      powerpc/wii: Don't rely on the reserved memory hack · 57deb8fe
      Jonathan Neuschäfer authored 
      Because the two memory blocks (usually called MEM1 and MEM2) are not
merged anymore, __request_region in kernel/resource.c will correctly
allow reserving regions in the physical address space between MEM1 and
MEM2, where many important peripherals are (GPIO, MMC, USB, ...).

A previous change to __ioremap_caller in arch/powerpc/mm/pgtable_32.c
ensures that multiple memblocks are properly considered in ioremap; this
makes it unnecessary to set __allow_ioremap_reserved.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      57deb8fe
    • Jonathan Neuschäfer's avatar
      powerpc/mm/32: Use page_is_ram to check for RAM · 2bbf6326
      Jonathan Neuschäfer authored 
      On systems where there is MMIO space between different blocks of RAM in
the physical address space, __ioremap_caller did not allow mapping these
MMIO areas, because they were below the end RAM and thus considered RAM
as well.  Use the memblock-based page_is_ram function, which returns
false for such MMIO holes.

v2:
  Keep the check for p < virt_to_phys(high_memory). On 32-bit systems
  with high memory (memory above physical address 4GiB), the high memory
  is expected to be available though ioremap. The high_memory variable
  marks the end of low memory; comparing against it means that only
  ioremap requests for low RAM will be denied.
  Reported by Michael Ellerman.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      2bbf6326
    • Jonathan Neuschäfer's avatar
      powerpc/mm: Use memblock API for PPC32 page_is_ram · f65e67c7
      Jonathan Neuschäfer authored 
      To support accurate checking for different blocks of memory on PPC32,
use the same memblock-based approach that's already used on PPC64 also
on PPC32.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      f65e67c7
    • Jonathan Neuschäfer's avatar
      powerpc/mm: Simplify page_is_ram by using memblock_is_memory · 2615c93e
      Jonathan Neuschäfer authored 
      Instead of open-coding the search in page_is_ram, call memblock_is_memory.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      2615c93e
    • Jonathan Neuschäfer's avatar
      powerpc/wii.dts: Add drive slot LED · 041413b8
      Jonathan Neuschäfer authored 
      The Wii has a blue LED in the disk drive slot, which is controlled via a
GPIO line. Add this LED to wii.dts, and mark it as a panic-indicator.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      041413b8
    • Jonathan Neuschäfer's avatar
      powerpc/wii.dts: Add GPIO line names · 80873a0b
      Jonathan Neuschäfer authored 
      These are the GPIO line names on a Nintendo Wii, as documented in:
https://wiibrew.org/wiki/Hardware/Hollywood_GPIOsSigned-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      80873a0b
    • Jonathan Neuschäfer's avatar
      powerpc/wii.dts: Add ngpios property · 9693d570
      Jonathan Neuschäfer authored 
      The Hollywood GPIO controller supports 32 GPIOs, but on the Wii, only 24
are used.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      9693d570
    • Jonathan Neuschäfer's avatar
      powerpc/wii: Explicitly configure GPIO owner for poweroff pin · 9cbaaec1
      Jonathan Neuschäfer authored 
      The Hollywood chipset's GPIO controller has two sets of registers: One
for access by the PowerPC CPU, and one for access by the ARM coprocessor
(but both are accessible from the PPC because the memory firewall
(AHBPROT) is usually disabled when booting Linux, today).

The wii_power_off function currently assumes that the poweroff GPIO pin
is configured for use via the ARM side, but the upcoming GPIO driver
configures all pins for use via the PPC side, breaking poweroff.

Configure the owner register explicitly in wii_power_off to make
wii_power_off work with and without the new GPIO driver.

I think the Wii can be switched to the generic gpio-poweroff driver,
after the GPIO driver is merged.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      9cbaaec1
    • Jonathan Neuschäfer's avatar
      powerpc/wii: Probe the whole devicetree · 7ab96c0a
      Jonathan Neuschäfer authored 
      Previously, wii_device_probe would only initialize devices under the
/hollywood node. After this patch, platform devices placed outside of
/hollywood will also be initialized.

The intended usecase for this are devices located outside of the
Hollywood chip, such as GPIO LEDs and GPIO buttons.
Signed-off-by: default avatarJonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      7ab96c0a
    • Michael Ellerman's avatar
      powerpc/64e: Fix oops due to deferral of paca allocation · 1d0afc0d
      Michael Ellerman authored 
      On 64-bit Book3E systems, in setup_tlb_core_data() we reference other
CPUs pacas. But in commit 59f57774 ("powerpc/64: Defer paca
allocation until memory topology is discovered") the allocation of
non-boot-CPU pacas was deferred until later in boot.

This leads to an oops:

  CPU maps initialized for 1 thread per core
  Unable to handle kernel paging request for data at address 0x8888888888888918
  Faulting instruction address: 0xc000000000e2f0d0
  Oops: Kernel access of bad area, sig: 11 [#1]
  NIP .setup_tlb_core_data+0xdc/0x160
  Call Trace:
    .setup_tlb_core_data+0x5c/0x160 (unreliable)
    .setup_arch+0x80/0x348
    .start_kernel+0x7c/0x598
    start_here_common+0x1c/0x40

Luckily setup_tlb_core_data() is called immediately prior to
smp_setup_pacas(). So simply switching their order is sufficient to
fix the oops and seems unlikely to have any other unwanted side
effects.

Fixes: 59f57774 ("powerpc/64: Defer paca allocation until memory topology is discovered")
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      1d0afc0d
    • Aneesh Kumar K.V's avatar
      powerpc/kvm: Fix guest boot failure on Power9 since DAWR changes · ca9a16c3
      Aneesh Kumar K.V authored 
      SLOF checks for 'sc 1' (hypercall) support by issuing a hcall with
H_SET_DABR. Since the recent commit e8ebedbf ("KVM: PPC: Book3S
HV: Return error from h_set_dabr() on POWER9") changed H_SET_DABR to
return H_UNSUPPORTED on Power9, we see guest boot failures, the
symptom is the boot seems to just stop in SLOF, eg:

  SLOF ***************************************************************
  QEMU Starting
   Build Date = Sep 24 2017 12:23:07
   FW Version = buildd@ release 20170724
  <no further output>

SLOF can cope if H_SET_DABR returns H_HARDWARE. So wwitch the return
value to H_HARDWARE instead of H_UNSUPPORTED so that we don't break
the guest boot.

That does mean we return a different error to PowerVM in this case,
but that's probably not a big concern.

Fixes: e8ebedbf ("KVM: PPC: Book3S HV: Return error from h_set_dabr() on POWER9")
Signed-off-by: default avatarAneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: default avatarMichael Ellerman <mpe@ellerman.id.au>
      ca9a16c3
  3. 30 Mar, 2018 25 commits
GitLab Nexedi Edition | About GitLab | About Nexedi | 沪ICP备2021021310号-2 | 沪ICP备2021021310号-7