linux-stable.git/arch/powerpc/kernel/eeh_driver.c, branch linux-3.16.y

powerpc/eeh: Fix race with driver un/bind

2018-10-21T07:45:08+00:00

commit f0295e047fcf52ccb42561fb7de6942f5201b676 upstream.

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
  
  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 77bd7415610) but it's not clear if a lock was needed back
then.

Fixes: 77bd74156101 ("[PATCH] powerpc: PCI Error Recovery: PPC64 core recovery routines")
Signed-off-by: Michael Neuling 
Reviewed-by: Benjamin Herrenschmidt 
Signed-off-by: Michael Ellerman 
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings

powerpc/eeh: Avoid use after free in eeh_handle_special_event()

2017-08-26T01:14:44+00:00

commit daeba2956f32f91f3493788ff6ee02fb1b2f02fa upstream.

eeh_handle_special_event() is called when an EEH event is detected but
can't be narrowed down to a specific PE.  This function looks through
every PE to find one in an erroneous state, then calls the regular event
handler eeh_handle_normal_event() once it knows which PE has an error.

However, if eeh_handle_normal_event() found that the PE cannot possibly
be recovered, it will free it, rendering the passed PE stale.
This leads to a use after free in eeh_handle_special_event() as it attempts to
clear the "recovering" state on the PE after eeh_handle_normal_event() returns.

Thus, make sure the PE is valid when attempting to clear state in
eeh_handle_special_event().

Fixes: 8a6b1bc70dbb ("powerpc/eeh: EEH core to handle special event")
Reported-by: Alexey Kardashevskiy 
Signed-off-by: Russell Currey 
Reviewed-by: Gavin Shan 
Signed-off-by: Michael Ellerman 
[bwh: Backported to 3.16: adjust context, indentation]
Signed-off-by: Ben Hutchings

powerpc/eeh: Fix deadlock when PE frozen state can't be cleared

2017-02-23T03:54:41+00:00

commit 409bf7f8a02ef88db5a0f2cdcf9489914f4b8508 upstream.

In eeh_reset_device(), we take the pci_rescan_remove_lock immediately after
after we call eeh_reset_pe() to reset the PCI controller. We then call
eeh_clear_pe_frozen_state(), which can return an error. In this case, we
bail out of eeh_reset_device() without calling pci_unlock_rescan_remove().

Add a call to pci_unlock_rescan_remove() in the eeh_clear_pe_frozen_state()
error path so that we don't cause a deadlock later on.

Reported-by: Pradipta Ghosh 
Fixes: 78954700631f ("powerpc/eeh: Avoid I/O access during PE reset")
Signed-off-by: Andrew Donnellan 
Acked-by: Russell Currey 
Signed-off-by: Michael Ellerman 
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings

powerpc/eeh: Null check uses of eeh_pe_bus_get

2017-02-23T03:54:02+00:00

commit 04fec21c06e35b169a83e75a84a015ab4606bf5e upstream.

eeh_pe_bus_get() can return NULL if a PCI bus isn't found for a given PE.
Some callers don't check this, and can cause a null pointer dereference
under certain circumstances.

Fix this by checking NULL everywhere eeh_pe_bus_get() is called.

Fixes: 8a6b1bc70dbb ("powerpc/eeh: EEH core to handle special event")
Signed-off-by: Russell Currey 
Reviewed-by: Andrew Donnellan 
Signed-off-by: Michael Ellerman 
Signed-off-by: Jiri Slaby 
Signed-off-by: Ben Hutchings

powerpc/powernv: Fix killed EEH event

2014-06-11T07:04:33+00:00

On PowerNV platform, EEH errors are reported by IO accessors or poller
driven by interrupt. After the PE is isolated, we won't produce EEH
event for the PE. The current implementation has possibility of EEH
event lost in this way:

The interrupt handler queues one "special" event, which drives the poller.
EEH thread doesn't pick the special event yet. IO accessors kicks in, the
frozen PE is marked as "isolated" and EEH event is queued to the list.
EEH thread runs because of special event and purge all existing EEH events.
However, we never produce an other EEH event for the frozen PE. Eventually,
the PE is marked as "isolated" and we don't have EEH event to recover it.

The patch fixes the issue to keep EEH events for PEs that have been
marked as "isolated" with the help of additional "force" help to
eeh_remove_event().

Reported-by: Rolf Brudeseth 
Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/eeh: Clear frozen state for child PE

2014-06-11T07:04:12+00:00

Since commit cb523e09 ("powerpc/eeh: Avoid I/O access during PE
reset"), the PE is kept as frozen state on hardware level until
the PE reset is done completely. After that, we explicitly clear
the frozen state of the affected PE. However, there might have
frozen child PEs of the affected PE and we also need clear their
frozen state as well. Otherwise, the recovery is going to fail.

Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/eeh: Can't recover from non-PE-reset case

2014-04-28T07:35:01+00:00

When PCI_ERS_RESULT_CAN_RECOVER returned from device drivers, the
EEH core should enable I/O and DMA for the affected PE. However,
it was missed to have DMA enabled in eeh_handle_normal_event().
Besides, the frozen state of the affected PE should be cleared
after successful recovery, but we didn't.

The patch fixes both of the issues as above.

Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/eeh: No hotplug on permanently removed dev

2014-04-28T07:34:32+00:00

The issue was detected in a bit complicated test case where
we have multiple hierarchical PEs shown as following figure:

                +-----------------+
                | PE#3     p2p#0  |
                |          p2p#1  |
                +-----------------+
                        |
                +-----------------+
                | PE#4     pdev#0 |
                |          pdev#1 |
                +-----------------+

PE#4 (have 2 PCI devices) is the child of PE#3, which has 2 p2p
bridges. We accidentally had less-known scenario: PE#4 was removed
permanently from the system because of permanent failure (e.g.
exceeding the max allowd failure times in last hour), then we detects
EEH errors on PE#3 and tried to recover it. However, eeh_dev instances
for pdev#0/1 were not detached from PE#4, which was still connected to
PE#3. All of that was because of the fact that we rely on count-based
pcibios_release_device(), which isn't reliable enough. When doing
recovery for PE#3, we still apply hotplug on PE#4 and pdev#0/1, which
are not valid any more. Eventually, we run into kernel crash.

The patch fixes above issue from two aspects. For unplug, we simply
skip those permanently removed PE, whose state is (EEH_PE_STATE_ISOLATED
&& !EEH_PE_STATE_RECOVERING) and its frozen count should be greater
than EEH_MAX_ALLOWED_FREEZES. For plug, we marked all permanently
removed EEH devices with EEH_DEV_REMOVED and return 0xFF's on read
its PCI config so that PCI core will omit them.

Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/eeh: Avoid I/O access during PE reset

2014-04-28T07:34:10+00:00

We have suffered recrusive frozen PE a lot, which was caused
by IO accesses during the PE reset. Ben came up with the good
idea to keep frozen PE until recovery (BAR restore) gets done.
With that, IO accesses during PE reset are dropped by hardware
and wouldn't incur the recrusive frozen PE any more.

The patch implements the idea. We don't clear the frozen state
until PE reset is done completely. During the period, the EEH
core expects unfrozen state from backend to keep going. So we
have to reuse EEH_PE_RESET flag, which has been set during PE
reset, to return normal state from backend. The side effect is
we have to clear frozen state for towice (PE reset and clear it
explicitly), but that's harmless.

We have some limitations on pHyp. pHyp doesn't allow to enable
IO or DMA for unfrozen PE. So we don't enable them on unfrozen PE
in eeh_pci_enable(). We have to enable IO before grabbing logs on
pHyp. Otherwise, 0xFF's is always returned from PCI config space.
Also, we had wrong return value from eeh_pci_enable() for
EEH_OPT_THAW_DMA case. The patch fixes it too.

Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt

powerpc/eeh: Block PCI-CFG access during PE reset

2014-04-28T07:34:02+00:00

We've observed multiple PE reset failures because of PCI-CFG
access during that period. Potentially, some device drivers
can't support EEH very well and they can't put the device to
motionless state before PE reset. So those device drivers might
produce PCI-CFG accesses during PE reset. Also, we could have
PCI-CFG access from user space (e.g. "lspci"). Since access to
frozen PE should return 0xFF's, we can block PCI-CFG access
during the period of PE reset so that we won't get recrusive EEH
errors.

The patch adds flag EEH_PE_RESET, which is kept during PE reset.
The PowerNV/pSeries PCI-CFG accessors reuse the flag to block
PCI-CFG accordingly.

Signed-off-by: Gavin Shan 
Signed-off-by: Benjamin Herrenschmidt