| Age | Commit message (Collapse) | Author |
|---|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
- Switch to the generic C VDSO, as well as some cleanups of our VDSO
setup/handling code.
- Support for KUAP (Kernel User Access Prevention) on systems using the
hashed page table MMU, using memory protection keys.
- Better handling of PowerVM SMT8 systems where all threads of a core
do not share an L2, allowing the scheduler to make better scheduling
decisions.
- Further improvements to our machine check handling.
- Show registers when unwinding interrupt frames during stack traces.
- Improvements to our pseries (PowerVM) partition migration code.
- Several series from Christophe refactoring and cleaning up various
parts of the 32-bit code.
- Other smaller features, fixes & cleanups.
Thanks to: Alan Modra, Alexey Kardashevskiy, Andrew Donnellan, Aneesh
Kumar K.V, Ard Biesheuvel, Athira Rajeev, Balamuruhan S, Bill Wendling,
Cédric Le Goater, Christophe Leroy, Christophe Lombard, Colin Ian King,
Daniel Axtens, David Hildenbrand, Frederic Barrat, Ganesh Goudar,
Gautham R. Shenoy, Geert Uytterhoeven, Giuseppe Sacco, Greg Kurz,
Harish, Jan Kratochvil, Jordan Niethe, Kaixu Xia, Laurent Dufour,
Leonardo Bras, Madhavan Srinivasan, Mahesh Salgaonkar, Mathieu
Desnoyers, Nathan Lynch, Nicholas Piggin, Oleg Nesterov, Oliver
O'Halloran, Oscar Salvador, Po-Hsu Lin, Qian Cai, Qinglang Miao, Randy
Dunlap, Ravi Bangoria, Sachin Sant, Sandipan Das, Sebastian Andrzej
Siewior , Segher Boessenkool, Srikar Dronamraju, Tyrel Datwyler, Uwe
Kleine-König, Vincent Stehlé, Youling Tang, and Zhang Xiaoxu.
* tag 'powerpc-5.11-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (304 commits)
powerpc/32s: Fix cleanup_cpu_mmu_context() compile bug
powerpc: Add config fragment for disabling -Werror
powerpc/configs: Add ppc64le_allnoconfig target
powerpc/powernv: Rate limit opal-elog read failure message
powerpc/pseries/memhotplug: Quieten some DLPAR operations
powerpc/ps3: use dma_mapping_error()
powerpc: force inlining of csum_partial() to avoid multiple csum_partial() with GCC10
powerpc/perf: Fix Threshold Event Counter Multiplier width for P10
powerpc/mm: Fix hugetlb_free_pmd_range() and hugetlb_free_pud_range()
KVM: PPC: Book3S HV: Fix mask size for emulated msgsndp
KVM: PPC: fix comparison to bool warning
KVM: PPC: Book3S: Assign boolean values to a bool variable
powerpc: Inline setup_kup()
powerpc/64s: Mark the kuap/kuep functions non __init
KVM: PPC: Book3S HV: XIVE: Add a comment regarding VP numbering
powerpc/xive: Improve error reporting of OPAL calls
powerpc/xive: Simplify xive_do_source_eoi()
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_EOI_FW
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_MASK_FW
powerpc/xive: Remove P9 DD1 flag XIVE_IRQ_FLAG_SHIFT_BUG
...
|
|
When attempting to remove by index a set of LMBs a lot of messages are
displayed on the console, even when everything goes fine:
pseries-hotplug-mem: Attempting to hot-remove LMB, drc index 8000002d
Offlined Pages 4096
pseries-hotplug-mem: Memory at 2d0000000 was hot-removed
The 2 messages prefixed by "pseries-hotplug-mem" are not really
helpful for the end user, they should be debug outputs.
In case of error, because some of the LMB's pages couldn't be
offlined, the following is displayed on the console:
pseries-hotplug-mem: Attempting to hot-remove LMB, drc index 8000003e
pseries-hotplug-mem: Failed to hot-remove memory at 3e0000000
dlpar: Could not handle DLPAR request "memory remove index 0x8000003e"
Again, the 2 messages prefixed by "pseries-hotplug-mem" are useless,
and the generic DLPAR prefixed message should be enough.
These 2 first changes are mainly triggered by the changes introduced
in drmgr:
https://groups.google.com/g/powerpc-utils-devel/c/Y6ef4NB3EzM/m/9cu5JHRxAQAJ
Also, when adding a bunch of LMBs, a message is displayed in the console per LMB
like these ones:
pseries-hotplug-mem: Memory at 7e0000000 (drc index 8000007e) was hot-added
pseries-hotplug-mem: Memory at 7f0000000 (drc index 8000007f) was hot-added
pseries-hotplug-mem: Memory at 800000000 (drc index 80000080) was hot-added
pseries-hotplug-mem: Memory at 810000000 (drc index 80000081) was hot-added
When adding 1TB of memory and LMB size is 256MB, this leads to 4096
messages to be displayed on the console. These messages are not really
helpful for the end user, so moving them to the DEBUG level.
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
[mpe: Tweak change log wording]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201211145954.90143-1-ldufour@linux.ibm.com
|
|
In pseries_devicetree_update(), with each call to ibm,update-nodes the
partition firmware communicates the node to be deleted or updated by
placing its phandle in the work buffer. Each of delete_dt_node(),
update_dt_node(), and add_dt_node() have duplicate lookups using the
phandle value and corresponding refcount management.
Move the lookup and of_node_put() into pseries_devicetree_update(),
and emit a warning on any failed lookups.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-29-nathanl@linux.ibm.com
|
|
The pseries hibernate code no longer calls into the original
join/suspend code in kernel/rtas.c, so pseries_prepare_late() and
related code don't accomplish anything now.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-27-nathanl@linux.ibm.com
|
|
The pseries hibernate code calls post_mobility_fixup() which is sort
of a dumping ground of fixups that need to run after resuming from
suspend regardless of whether suspend was a hibernation or a
migration. Calling post_mobility_fixup() from
pseries_suspend_enable_irqs() runs this code early in resume with
devices suspended and only one CPU up, while the much more commonly
used migration case runs these fixups in a more typical process
context.
Call post_mobility_fixup() after the suspend core returns a success
status to the hibernate sysfs store method and remove
pseries_suspend_enable_irqs().
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-26-nathanl@linux.ibm.com
|
|
Partitions with cache nodes in the device tree can encounter the
following warning on resume:
CPU 0 already accounted in PowerPC,POWER9@0(Data)
WARNING: CPU: 0 PID: 3177 at arch/powerpc/kernel/cacheinfo.c:197 cacheinfo_cpu_online+0x640/0x820
These calls to cacheinfo_cpu_offline/online have been redundant since
commit e610a466d16a ("powerpc/pseries/mobility: rebuild cacheinfo
hierarchy post-migration").
Fixes: e610a466d16a ("powerpc/pseries/mobility: rebuild cacheinfo hierarchy post-migration")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-25-nathanl@linux.ibm.com
|
|
rtas_suspend_last_cpu() and related code perform a lot of work that
isn't relevant to the hibernation workflow. All other CPUs are offline
when called so there is no need to place them in H_JOIN or prod them
on resume, nor is there need for retries or operations on shared
state.
Call the rtas_ibm_suspend_me() wrapper function directly from
pseries_suspend_enter() instead of using rtas_suspend_last_cpu().
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-23-nathanl@linux.ibm.com
|
|
Since commit 48f6e7f6d948 ("powerpc/pseries: remove cede offline state
for CPUs"), ppc_md.suspend_disable_cpu() is no longer used and all
CPUs (save one) are placed into true offline state as opposed to
H_JOIN. So pseries_suspend_cpu() is effectively unused; remove it.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-20-nathanl@linux.ibm.com
|
|
There is no need for the stream id to be a file-global variable; pass
it from hibernate_store() to pseries_suspend_begin() for the
H_VASI_STATE call.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-19-nathanl@linux.ibm.com
|
|
There are three ways pseries_suspend_begin() can be reached:
1. When "mem" is written to /sys/power/state:
kobj_attr_store()
-> state_store()
-> pm_suspend()
-> suspend_devices_and_enter()
-> pseries_suspend_begin()
This never works because there is no way to supply a valid stream id
using this interface, and H_VASI_STATE is called with a stream id of
zero. So this call path is useless at best.
2. When a stream id is written to /sys/devices/system/power/hibernate.
pseries_suspend_begin() is polled directly from store_hibernate()
until the stream is in the "Suspending" state (i.e. the platform is
ready for the OS to suspend execution):
dev_attr_store()
-> store_hibernate()
-> pseries_suspend_begin()
3. When a stream id is written to /sys/devices/system/power/hibernate
(continued). After #2, pseries_suspend_begin() is called once again
from the pm core:
dev_attr_store()
-> store_hibernate()
-> pm_suspend()
-> suspend_devices_and_enter()
-> pseries_suspend_begin()
This is redundant because the VASI suspend state is already known to
be Suspending.
The begin() callback of platform_suspend_ops is optional, so we can
simply remove that assignment with no loss of function.
Fixes: 32d8ad4e621d ("powerpc/pseries: Partition hibernation support")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-18-nathanl@linux.ibm.com
|
|
sys_rtas() cannot call ibm,suspend-me directly in the same way it
handles other inputs. Instead it must dispatch the request to code
that can first perform the H_JOIN sequence before any call to
ibm,suspend-me can succeed. Over time kernel/rtas.c has accreted a fair
amount of platform-specific code to implement this.
Since a different, more robust implementation of the suspend sequence
is now in the pseries platform code, we want to dispatch the request
there.
Note that invoking ibm,suspend-me via the RTAS syscall is all but
deprecated; this change preserves ABI compatibility for old programs
while providing to them the benefit of the new partition suspend
implementation. This is a behavior change in that the kernel performs
the device tree update and firmware activation before returning, but
experimentation indicates this is tolerated fine by legacy user space.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-16-nathanl@linux.ibm.com
|
|
This is a mitigation for the relatively rare occurrence where a
virtual IOA can be in a transient state that prevents the
suspend/migration from succeeding, resulting in an error from
ibm,suspend-me.
If the join/suspend sequence returns an error, it is acceptable to
retry as long as the VASI suspend session state is still
"Suspending" (i.e. the platform is still waiting for the OS to
suspend).
Retry a few times on suspend failure while this condition holds,
progressively increasing the delay between attempts. We don't want to
retry indefinitey because firmware emits an error log event on each
unsuccessful attempt.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-15-nathanl@linux.ibm.com
|
|
If we're returning an error to user space, use H_VASI_SIGNAL to send a
cancellation request to the platform. This isn't strictly required but
it communicates that Linux will not attempt to complete the suspend,
which allows the various entities involved to promptly end the
operation in progress.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-14-nathanl@linux.ibm.com
|
|
The partition suspend sequence as specified in the platform
architecture requires that all active processor threads call
H_JOIN, which:
- suspends the calling thread until it is the target of
an H_PROD; or
- immediately returns H_CONTINUE, if the calling thread is the last to
call H_JOIN. This thread is expected to call ibm,suspend-me to
completely suspend the partition.
Upon returning from ibm,suspend-me the calling thread must wake all
others using H_PROD.
rtas_ibm_suspend_me_unsafe() uses on_each_cpu() to implement this
protocol, but because of its synchronizing nature this is susceptible
to deadlock versus users of stop_machine() or other callers of
on_each_cpu().
Not only is stop_machine() intended for use cases like this, it
handles error propagation and allows us to keep the data shared
between CPUs minimal: a single atomic counter which ensures exactly
one CPU will wake the others from their joined states.
Switch the migration code to use stop_machine() and a less complex
local implementation of the H_JOIN/ibm,suspend-me logic, which
carries additional benefits:
- more informative error reporting, appropriately ratelimited
- resets the lockup detector / watchdog on resume to prevent lockup
warnings when the OS has been suspended for a time exceeding the
threshold.
Fixes: 91dc182ca6e2 ("[PATCH] powerpc: special-case ibm,suspend-me RTAS call")
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-13-nathanl@linux.ibm.com
|
|
The behavior of rtas_ibm_suspend_me_unsafe() is to return -EAGAIN to
the caller until the specified VASI suspend session state makes the
transition from H_VASI_ENABLED to H_VASI_SUSPENDING. In the interest
of separating concerns to prepare for a new implementation of the
join/suspend sequence, extract VASI session polling logic into a
couple of local functions. Waiting for the session state to reach
H_VASI_SUSPENDING before calling rtas_ibm_suspend_me_unsafe() ensures
that we will never get an EAGAIN result necessitating a retry. No
user-visible change in behavior is intended.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-12-nathanl@linux.ibm.com
|
|
It's incorrect to abort post-suspend processing if
ibm,activate-firmware isn't available. Use rtas_activate_firmware(),
which logs this condition appropriately and allows us to proceed.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-11-nathanl@linux.ibm.com
|
|
- Convert printk(KERN_ERR) to pr_err().
- Include errno in property update failure message.
- Remove reference to "Post-mobility" from device tree update message:
with pr_err() it will have a "mobility:" prefix.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-10-nathanl@linux.ibm.com
|
|
update_dt_node() has a switch statement where the default case lacks a
break statement.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-9-nathanl@linux.ibm.com
|
|
Treat the absence of the ibm,update-nodes function as benign instead
of reporting an error. If the platform does not provide that facility,
it's not a problem for Linux.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-8-nathanl@linux.ibm.com
|
|
The pseries partition suspend sequence requires that all active CPUs
call H_JOIN, which suspends all but one of them with interrupts
disabled. The "chosen" CPU is then to call ibm,suspend-me to complete
the suspend. Upon returning from ibm,suspend-me, the chosen CPU is to
use H_PROD to wake the joined CPUs.
Using on_each_cpu() for this, as rtas_ibm_suspend_me() does to
implement partition migration, is susceptible to deadlock with other
users of on_each_cpu() and with users of stop_machine APIs. The
callback passed to on_each_cpu() is not allowed to synchronize with
other CPUs in the way it is used here.
Complicating the fix is the fact that rtas_ibm_suspend_me() also
occupies the function name that should be used to provide a more
conventional wrapper for ibm,suspend-me. Rename rtas_ibm_suspend_me()
to rtas_ibm_suspend_me_unsafe() to free up the name and indicate that
it should not gain users.
Signed-off-by: Nathan Lynch <nathanl@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201207215200.1785968-4-nathanl@linux.ibm.com
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq fixes from Thomas Gleixner:
"A set of updates for the interrupt subsystem:
- Make multiqueue devices which use the managed interrupt affinity
infrastructure work on PowerPC/Pseries. PowerPC does not use the
generic infrastructure for setting up PCI/MSI interrupts and the
multiqueue changes failed to update the legacy PCI/MSI
infrastructure. Make this work by passing the affinity setup
information down to the mapping and allocation functions.
- Move Jason Cooper from MAINTAINERS to CREDITS as his mail is
bouncing and he's not reachable. We hope all is well with him and
say thanks for his work over the years"
* tag 'irq-urgent-2020-12-06' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
powerpc/pseries: Pass MSI affinity to irq_create_mapping()
genirq/irqdomain: Add an irq_create_mapping_affinity() function
MAINTAINERS: Move Jason Cooper to CREDITS
|
|
Don't treat ERAT MCEs as SLB, don't save the SLB and use a specific
ERAT flush to recover it.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201128070728.825934-7-npiggin@gmail.com
|
|
We want to reuse the is_kvm_guest() name in a subsequent patch but
with a new body. Hence rename is_kvm_guest() to check_kvm_guest(). No
additional changes.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: kernel test robot <lkp@intel.com> # int -> bool fix
[mpe: Fold in fix from lkp to use true/false not 0/1]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201202050456.164005-3-srikar@linux.vnet.ibm.com
|
|
Only code/declaration movement, in anticipation of doing a KVM-aware
vcpu_is_preempted(). No additional changes.
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201202050456.164005-2-srikar@linux.vnet.ibm.com
|
|
Update bus speed definition for PCI Gen4 and 5.
Signed-off-by: Frederic Barrat <fbarrat@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201130152949.26467-1-fbarrat@linux.ibm.com
|
|
With virtio multiqueue, normally each queue IRQ is mapped to a CPU.
Commit 0d9f0a52c8b9f ("virtio_scsi: use virtio IRQ affinity") exposed
an existing shortcoming of the arch code by moving virtio_scsi to
the automatic IRQ affinity assignment.
The affinity is correctly computed in msi_desc but this is not applied
to the system IRQs.
It appears the affinity is correctly passed to rtas_setup_msi_irqs() but
lost at this point and never passed to irq_domain_alloc_descs()
(see commit 06ee6d571f0e ("genirq: Add affinity hint to irq allocation"))
because irq_create_mapping() doesn't take an affinity parameter.
Use the new irq_create_mapping_affinity() function, which allows to forward
the affinity setting from rtas_setup_msi_irqs() to irq_domain_alloc_descs().
With this change, the virtqueues are correctly dispatched between the CPUs
on pseries.
Fixes: e75eafb9b039 ("genirq/msi: Switch to new irq spreading infrastructure")
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kurz <groug@kaod.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20201126082852.1178497-3-lvivier@redhat.com
|
|
So far we have been using huge DMA windows to map all the RAM available.
The RAM is normally mapped to the VM address space contiguously, and
there is always a reasonable upper limit for possible future hot plugged
RAM which makes it easy to map all RAM via IOMMU.
Now there is persistent memory ("ibm,pmemory" in the FDT) which (unlike
normal RAM) can map anywhere in the VM space beyond the maximum RAM size
and since it can be used for DMA, it requires extending the huge window
up to MAX_PHYSMEM_BITS which requires hypervisor support for:
1. huge TCE tables;
2. multilevel TCE tables;
3. huge IOMMU pages.
Certain hypervisors cannot do either so the only option left is
restricting the huge DMA window to include only RAM and fallback to
the default DMA window for persistent memory.
This defines arch_dma_map_direct/etc to allow generic DMA code perform
additional checks on whether direct DMA is still possible.
This checks if the system has persistent memory. If it does not,
the DMA bypass mode is selected, i.e.
* dev->bus_dma_limit = 0
* dev->dma_ops_bypass = true <- this avoid calling dma_ops for mapping.
If there is such memory, this creates identity mapping only for RAM and
sets the dev->bus_dma_limit to let the generic code decide whether to
call into the direct DMA or the indirect DMA ops.
This should not change the existing behaviour when no persistent memory
as dev->dma_ops_bypass is expected to be set.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Christoph Hellwig <hch@lst.de>
|
|
When offlining a CPU, powerpc/64s does not flush TLBs, rather it just
leaves the CPU set in mm_cpumasks, so it continues to receive TLBIEs
to manage its TLBs.
However the exit_flush_lazy_tlbs() function expects that after
returning, all CPUs (except self) have flushed TLBs for that mm, in
which case TLBIEL can be used for this flush. This breaks for offline
CPUs because they don't get the IPI to flush their TLB. This can lead
to stale translations.
Fix this by clearing the CPU from mm_cpumasks, then flushing all TLBs
before going offline.
These offlined CPU bits stuck in the cpumask also prevents the cpumask
from being trimmed back to local mode, which means continual broadcast
IPIs or TLBIEs are needed for TLB flushing. This patch prevents that
situation too.
A cast of many were involved in working this out, but in particular
Milton, Aneesh, Paul made key discoveries.
Fixes: 0cef77c7798a7 ("powerpc/64s/radix: flush remote CPUs out of single-threaded mm_cpumask")
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Debugged-by: Milton Miller <miltonm@us.ibm.com>
Debugged-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Debugged-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201126102530.691335-5-npiggin@gmail.com
|
|
Merge our fixes branch, in particular to bring in the changes for the
entry/uaccess flush.
|
|
pseries|pnv_setup_rfi_flush already does the count cache flush setup, and
we just added entry and uaccess flushes. So the name is not very accurate
any more. In both platforms we then also immediately setup the STF flush.
Rename them to _setup_security_mitigations and fold the STF flush in.
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
IBM Power9 processors can speculatively operate on data in the L1 cache
before it has been completely validated, via a way-prediction mechanism. It
is not possible for an attacker to determine the contents of impermissible
memory using this method, since these systems implement a combination of
hardware and software security measures to prevent scenarios where
protected data could be leaked.
However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that
the attacker controls. This can be used for example to speculatively bypass
"kernel user access prevention" techniques, as discovered by Anthony
Steinhauser of Google's Safeside Project. This is not an attack by itself,
but there is a possibility it could be used in conjunction with
side-channels or other weaknesses in the privileged code to construct an
attack.
This issue can be mitigated by flushing the L1 cache between privilege
boundaries of concern. This patch flushes the L1 cache after user accesses.
This is part of the fix for CVE-2020-4788.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
IBM Power9 processors can speculatively operate on data in the L1 cache
before it has been completely validated, via a way-prediction mechanism. It
is not possible for an attacker to determine the contents of impermissible
memory using this method, since these systems implement a combination of
hardware and software security measures to prevent scenarios where
protected data could be leaked.
However these measures don't address the scenario where an attacker induces
the operating system to speculatively execute instructions using data that
the attacker controls. This can be used for example to speculatively bypass
"kernel user access prevention" techniques, as discovered by Anthony
Steinhauser of Google's Safeside Project. This is not an attack by itself,
but there is a possibility it could be used in conjunction with
side-channels or other weaknesses in the privileged code to construct an
attack.
This issue can be mitigated by flushing the L1 cache between privilege
boundaries of concern. This patch flushes the L1 cache on kernel entry.
This is part of the fix for CVE-2020-4788.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
|
|
This reverts commit a0ff72f9f5a780341e7ff5e9ba50a0dad5fa1980.
Since the commit b015f6bc9547 ("powerpc/pseries: Add cpu DLPAR
support for drc-info property"), the 'cpu_drcs' wouldn't be double
freed when the 'cpus' node not found.
So we needn't apply this patch, otherwise, the memory will be leaked.
Fixes: a0ff72f9f5a7 ("powerpc/pseries/hotplug-cpu: Remove double free in error path")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zhang Xiaoxu <zhangxiaoxu5@huawei.com>
[mpe: Caused by me applying a patch to a function that had changed in the interim]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201111020752.1686139-1-zhangxiaoxu5@huawei.com
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc fixes from Michael Ellerman:
- A fix for undetected data corruption on Power9 Nimbus <= DD2.1 in the
emulation of VSX loads. The affected CPUs were not widely available.
- Two fixes for machine check handling in guests under PowerVM.
- A fix for our recent changes to SMP setup, when
CONFIG_CPUMASK_OFFSTACK=y.
- Three fixes for races in the handling of some of our powernv sysfs
attributes.
- One change to remove TM from the set of Power10 CPU features.
- A couple of other minor fixes.
Thanks to: Aneesh Kumar K.V, Christophe Leroy, Ganesh Goudar, Jordan
Niethe, Mahesh Salgaonkar, Michael Neuling, Oliver O'Halloran, Qian Cai,
Srikar Dronamraju, Vasant Hegde.
* tag 'powerpc-5.10-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
powerpc/pseries: Avoid using addr_to_pfn in real mode
powerpc/uaccess: Don't use "m<>" constraint with GCC 4.9
powerpc/eeh: Fix eeh_dev_check_failure() for PE#0
powerpc/64s: Remove TM from Power10 features
selftests/powerpc: Make alignment handler test P9N DD2.1 vector CI load workaround
powerpc: Fix undetected data corruption with P9N DD2.1 VSX CI load emulation
powerpc/powernv/dump: Handle multiple writes to ack attribute
powerpc/powernv/dump: Fix race while processing OPAL dump
powerpc/smp: Use GFP_ATOMIC while allocating tmp mask
powerpc/smp: Remove unnecessary variable
powerpc/mce: Avoid nmi_enter/exit in real mode on pseries hash
powerpc/opal_elog: Handle multiple writes to ack attribute
|
|
When an UE or memory error exception is encountered the MCE handler
tries to find the pfn using addr_to_pfn() which takes effective
address as an argument, later pfn is used to poison the page where
memory error occurred, recent rework in this area made addr_to_pfn
to run in real mode, which can be fatal as it may try to access
memory outside RMO region.
Have two helper functions to separate things to be done in real mode
and virtual mode without changing any functionality. This also fixes
the following error as the use of addr_to_pfn is now moved to virtual
mode.
Without this change following kernel crash is seen on hitting UE.
[ 485.128036] Oops: Kernel access of bad area, sig: 11 [#1]
[ 485.128040] LE SMP NR_CPUS=2048 NUMA pSeries
[ 485.128047] Modules linked in:
[ 485.128067] CPU: 15 PID: 6536 Comm: insmod Kdump: loaded Tainted: G OE 5.7.0 #22
[ 485.128074] NIP: c00000000009b24c LR: c0000000000398d8 CTR: c000000000cd57c0
[ 485.128078] REGS: c000000003f1f970 TRAP: 0300 Tainted: G OE (5.7.0)
[ 485.128082] MSR: 8000000000001003 <SF,ME,RI,LE> CR: 28008284 XER: 00000001
[ 485.128088] CFAR: c00000000009b190 DAR: c0000001fab00000 DSISR: 40000000 IRQMASK: 1
[ 485.128088] GPR00: 0000000000000001 c000000003f1fbf0 c000000001634300 0000b0fa01000000
[ 485.128088] GPR04: d000000002220000 0000000000000000 00000000fab00000 0000000000000022
[ 485.128088] GPR08: c0000001fab00000 0000000000000000 c0000001fab00000 c000000003f1fc14
[ 485.128088] GPR12: 0000000000000008 c000000003ff5880 d000000002100008 0000000000000000
[ 485.128088] GPR16: 000000000000ff20 000000000000fff1 000000000000fff2 d0000000021a1100
[ 485.128088] GPR20: d000000002200000 c00000015c893c50 c000000000d49b28 c00000015c893c50
[ 485.128088] GPR24: d0000000021a0d08 c0000000014e5da8 d0000000021a0818 000000000000000a
[ 485.128088] GPR28: 0000000000000008 000000000000000a c0000000017e2970 000000000000000a
[ 485.128125] NIP [c00000000009b24c] __find_linux_pte+0x11c/0x310
[ 485.128130] LR [c0000000000398d8] addr_to_pfn+0x138/0x170
[ 485.128133] Call Trace:
[ 485.128135] Instruction dump:
[ 485.128138] 3929ffff 7d4a3378 7c883c36 7d2907b4 794a1564 7d294038 794af082 3900ffff
[ 485.128144] 79291f24 790af00e 78e70020 7d095214 <7c69502a> 2fa30000 419e011c 70690040
[ 485.128152] ---[ end trace d34b27e29ae0e340 ]---
Fixes: 9ca766f9891d ("powerpc/64s/pseries: machine check convert to use common event code")
Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200724063946.21378-1-ganeshgr@linux.ibm.com
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux
Pull powerpc updates from Michael Ellerman:
- A series from Nick adding ARCH_WANT_IRQS_OFF_ACTIVATE_MM & selecting
it for powerpc, as well as a related fix for sparc.
- Remove support for PowerPC 601.
- Some fixes for watchpoints & addition of a new ptrace flag for
detecting ISA v3.1 (Power10) watchpoint features.
- A fix for kernels using 4K pages and the hash MMU on bare metal
Power9 systems with > 16TB of RAM, or RAM on the 2nd node.
- A basic idle driver for shallow stop states on Power10.
- Tweaks to our sched domains code to better inform the scheduler about
the hardware topology on Power9/10, where two SMT4 cores can be
presented by firmware as an SMT8 core.
- A series doing further reworks & cleanups of our EEH code.
- Addition of a filter for RTAS (firmware) calls done via sys_rtas(),
to prevent root from overwriting kernel memory.
- Other smaller features, fixes & cleanups.
Thanks to: Alexey Kardashevskiy, Andrew Donnellan, Aneesh Kumar K.V,
Athira Rajeev, Biwen Li, Cameron Berkenpas, Cédric Le Goater, Christophe
Leroy, Christoph Hellwig, Colin Ian King, Daniel Axtens, David Dai, Finn
Thain, Frederic Barrat, Gautham R. Shenoy, Greg Kurz, Gustavo Romero,
Ira Weiny, Jason Yan, Joel Stanley, Jordan Niethe, Kajol Jain, Konrad
Rzeszutek Wilk, Laurent Dufour, Leonardo Bras, Liu Shixin, Luca
Ceresoli, Madhavan Srinivasan, Mahesh Salgaonkar, Nathan Lynch, Nicholas
Mc Guire, Nicholas Piggin, Nick Desaulniers, Oliver O'Halloran, Pedro
Miraglia Franco de Carvalho, Pratik Rajesh Sampat, Qian Cai, Qinglang
Miao, Ravi Bangoria, Russell Currey, Satheesh Rajendran, Scott Cheloha,
Segher Boessenkool, Srikar Dronamraju, Stan Johnson, Stephen Kitt,
Stephen Rothwell, Thiago Jung Bauermann, Tyrel Datwyler, Vaibhav Jain,
Vaidyanathan Srinivasan, Vasant Hegde, Wang Wensheng, Wolfram Sang, Yang
Yingliang, zhengbin.
* tag 'powerpc-5.10-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (228 commits)
Revert "powerpc/pci: unmap legacy INTx interrupts when a PHB is removed"
selftests/powerpc: Fix eeh-basic.sh exit codes
cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_reboot_notifier
powerpc/time: Make get_tb() common to PPC32 and PPC64
powerpc/time: Make get_tbl() common to PPC32 and PPC64
powerpc/time: Remove get_tbu()
powerpc/time: Avoid using get_tbl() and get_tbu() internally
powerpc/time: Make mftb() common to PPC32 and PPC64
powerpc/time: Rename mftbl() to mftb()
powerpc/32s: Remove #ifdef CONFIG_PPC_BOOK3S_32 in head_book3s_32.S
powerpc/32s: Rename head_32.S to head_book3s_32.S
powerpc/32s: Setup the early hash table at all time.
powerpc/time: Remove ifdef in get_dec() and set_dec()
powerpc: Remove get_tb_or_rtc()
powerpc: Remove __USE_RTC()
powerpc: Tidy up a bit after removal of PowerPC 601.
powerpc: Remove support for PowerPC 601
powerpc: Remove PowerPC 601
powerpc: Drop SYNC_601() ISYNC_601() and SYNC()
powerpc: Remove CONFIG_PPC601_SYNC_FIX
...
|
|
We soon want to pass flags, e.g., to mark added System RAM resources.
mergeable. Prepare for that.
This patch is based on a similar patch by Oscar Salvador:
https://lkml.kernel.org/r/20190625075227.15193-3-osalvador@suse.de
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Juergen Gross <jgross@suse.com> # Xen related part
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Baoquan He <bhe@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: Wei Liu <wei.liu@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: "Oliver O'Halloran" <oohall@gmail.com>
Cc: Pingfan Liu <kernelfans@gmail.com>
Cc: Nathan Lynch <nathanl@linux.ibm.com>
Cc: Libor Pechacek <lpechacek@suse.cz>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Leonardo Bras <leobras.c@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Julien Grall <julien@xen.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richardw.yang@linux.intel.com>
Link: https://lkml.kernel.org/r/20200911103459.10306-5-david@redhat.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Add NVDIMM_FAMILY_PAPR to the list of valid 'dimm_family_mask'
acceptable by papr_scm. This is needed as since commit
92fe2aa859f5 ("libnvdimm: Validate command family indices") libnvdimm
performs a validation of 'nd_cmd_pkg.nd_family' received as part of
ND_CMD_CALL processing to ensure only known command families can use
the general ND_CMD_CALL pass-through functionality.
Without this change the ND_CMD_CALL pass-through targeting
NVDIMM_FAMILY_PAPR error out with -EINVAL.
Fixes: 92fe2aa859f5 ("libnvdimm: Validate command family indices")
Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200913211904.24472-1-vaibhav@linux.ibm.com
|
|
Make it consistent with other usages.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201007114836.282468-5-aneesh.kumar@linux.ibm.com
|
|
Similar to commit 89c140bbaeee ("pseries: Fix 64 bit logical memory block panic")
make sure different variables tracking lmb_size are updated to be 64 bit.
This was found by code audit.
Cc: stable@vger.kernel.org
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201007114836.282468-3-aneesh.kumar@linux.ibm.com
|
|
If the RTAS call to query the PE address for a device fails we jump the
err: label where an error message is printed along with the return code.
However, the printed return code is from the "ret" variable which isn't set
at that point since we assigned the result to "addr" instead. Fix this by
consistently using the "ret" variable for the result of the RTAS call
helpers an dropping the "addr" local variable"
Fixes: 98ba956f6a38 ("powerpc/pseries/eeh: Rework device EEH PE determination")
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20201007040903.819081-2-oohall@gmail.com
|
|
During memory hot-add, dlpar_add_lmb() calls memory_add_physaddr_to_nid()
to determine which node id (nid) to use when later calling __add_memory().
This is wasteful. On pseries, memory_add_physaddr_to_nid() finds an
appropriate nid for a given address by looking up the LMB containing the
address and then passing that LMB to of_drconf_to_nid_single() to get the
nid. In dlpar_add_lmb() we get this address from the LMB itself.
In short, we have a pointer to an LMB and then we are searching for
that LMB *again* in order to find its nid.
If we call of_drconf_to_nid_single() directly from dlpar_add_lmb() we
can skip the redundant lookup. The only error handling we need to
duplicate from memory_add_physaddr_to_nid() is the fallback to the
default nid when drconf_to_nid_single() returns -1 (NUMA_NO_NODE) or
an invalid nid.
Skipping the extra lookup makes hot-add operations faster, especially
on machines with many LMBs.
Consider an LPAR with 126976 LMBs. In one test, hot-adding 126000
LMBs on an upatched kernel took ~3.5 hours while a patched kernel
completed the same operation in ~2 hours:
Unpatched (12450 seconds):
Sep 9 04:06:31 ltc-brazos1 drmgr[810169]: drmgr: -c mem -a -q 126000
Sep 9 04:06:31 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s)
[...]
Sep 9 07:34:01 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added
Patched (7065 seconds):
Sep 8 21:49:57 ltc-brazos1 drmgr[877703]: drmgr: -c mem -a -q 126000
Sep 8 21:49:57 ltc-brazos1 kernel: pseries-hotplug-mem: Attempting to hot-add 126000 LMB(s)
[...]
Sep 8 23:27:42 ltc-brazos1 kernel: pseries-hotplug-mem: Memory at 20000000 (drc index 80000002) was hot-added
It should be noted that the speedup grows more substantial when
hot-adding LMBs at the end of the drconf range. This is because we
are skipping a linear LMB search.
To see the distinction, consider smaller hot-add test on the same
LPAR. A perf-stat run with 10 iterations showed that hot-adding 4096
LMBs completed less than 1 second faster on a patched kernel:
Unpatched:
Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs):
104,753.42 msec task-clock # 0.992 CPUs utilized ( +- 0.55% )
4,708 context-switches # 0.045 K/sec ( +- 0.69% )
2,444 cpu-migrations # 0.023 K/sec ( +- 1.25% )
394 page-faults # 0.004 K/sec ( +- 0.22% )
445,902,503,057 cycles # 4.257 GHz ( +- 0.55% ) (66.67%)
8,558,376,740 stalled-cycles-frontend # 1.92% frontend cycles idle ( +- 0.88% ) (49.99%)
300,346,181,651 stalled-cycles-backend # 67.36% backend cycles idle ( +- 0.76% ) (50.01%)
258,091,488,691 instructions # 0.58 insn per cycle
# 1.16 stalled cycles per insn ( +- 0.22% ) (66.67%)
70,568,169,256 branches # 673.660 M/sec ( +- 0.17% ) (50.01%)
3,100,725,426 branch-misses # 4.39% of all branches ( +- 0.20% ) (49.99%)
105.583 +- 0.589 seconds time elapsed ( +- 0.56% )
Patched:
Performance counter stats for 'drmgr -c mem -a -q 4096' (10 runs):
104,055.69 msec task-clock # 0.993 CPUs utilized ( +- 0.32% )
4,606 context-switches # 0.044 K/sec ( +- 0.20% )
2,463 cpu-migrations # 0.024 K/sec ( +- 0.93% )
394 page-faults # 0.004 K/sec ( +- 0.25% )
442,951,129,921 cycles # 4.257 GHz ( +- 0.32% ) (66.66%)
8,710,413,329 stalled-cycles-frontend # 1.97% frontend cycles idle ( +- 0.47% ) (50.06%)
299,656,905,836 stalled-cycles-backend # 67.65% backend cycles idle ( +- 0.39% ) (50.02%)
252,731,168,193 instructions # 0.57 insn per cycle
# 1.19 stalled cycles per insn ( +- 0.20% ) (66.66%)
68,902,851,121 branches # 662.173 M/sec ( +- 0.13% ) (49.94%)
3,100,242,882 branch-misses # 4.50% of all branches ( +- 0.15% ) (49.98%)
104.829 +- 0.325 seconds time elapsed ( +- 0.31% )
This is consistent. An add-by-count hot-add operation adds LMBs
greedily, so LMBs near the start of the drconf range are considered
first. On an otherwise idle LPAR with so many LMBs we would expect to
find the LMBs we need near the start of the drconf range, hence the
smaller speedup.
Signed-off-by: Scott Cheloha <cheloha@linux.ibm.com>
Reviewed-by: Laurent Dufour <ldufour@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200916145122.3408129-1-cheloha@linux.ibm.com
|
|
When support for EEH on PowerNV was added a lot of pseries specific code
was made "generic" and some of the quirks of pseries EEH came along for the
ride. One of the stranger quirks is eeh_pe containing two types of PE
address: pe->addr and pe->config_addr. There reason for this appears to be
historical baggage rather than any real requirements.
On pseries EEH PEs are manipulated using RTAS calls. Each EEH RTAS call
takes a "PE configuration address" as an input which is used to identify
which EEH PE is being manipulated by the call. When initialising the EEH
state for a device the first thing we need to do is determine the
configuration address for the PE which contains the device so we can enable
EEH on that PE. This process is outlined in PAPR which is the modern
(i.e post-2003) FW specification for pseries. However, EEH support was
first described in the pSeries RISC Platform Architecture (RPA) and
although they are mostly compatible EEH is one of the areas where they are
not.
The major difference is that RPA doesn't actually have the concept of a PE.
On RPA systems the EEH RTAS calls are done on a per-device basis using the
same config_addr that would be passed to the RTAS functions to access PCI
config space (e.g. ibm,read-pci-config). The config_addr is not identical
since the function and config register offsets of the config_addr must be
set to zero. EEH operations being done on a per-device basis doesn't make a
whole lot of sense when you consider how EEH was implemented on legacy PCI
systems.
For legacy PCI(-X) systems EEH was implemented using special PCI-PCI
bridges which contained logic to detect errors and freeze the secondary
bus when one occurred. This means that the EEH enabled state is shared
among all devices behind that EEH bridge. As a result there's no way to
implement the per-device control required for the semantics specified by
RPA. It can be made to work if we assume that a separate EEH bridge exists
for each EEH capable PCI slot and there are no bridges behind those slots.
However, RPA also specifies the ibm,configure-bridge RTAS call for
re-initalising bridges behind EEH capable slots after they are reset due
to an EEH event so that is probably not a valid assumption. This
incoherence was fixed in later PAPR, which succeeded RPA. Unfortunately,
since Linux EEH support seems to have been implemented based on the RPA
spec some of the legacy assumptions were carried over (probably for POWER4
compatibility).
The fix made in PAPR was the introduction of the "PE" concept and
redefining the EEH RTAS calls (set-eeh-option, reset-slot, etc) to operate
on a per-PE basis so all devices behind an EEH bride would share the same
EEH state. The "config_addr" argument to the EEH RTAS calls became the
"PE_config_addr" and the OS was required to use the
ibm,get-config-addr-info RTAS call to find the correct PE address for the
device. When support for the new interfaces was added to Linux it was
implemented using something like:
At probe time:
pdn->eeh_config_addr = rtas_config_addr(pdn);
pdn->eeh_pe_config_addr = rtas_get_config_addr_info(pdn);
When performing an RTAS call:
config_addr = pdn->eeh_config_addr;
if (pdn->eeh_pe_config_addr)
config_addr = pdn->eeh_pe_config_addr;
rtas_call(..., config_addr, ...);
In other words, if the ibm,get-config-addr-info RTAS call is implemented
and returned a valid result we'd use that as the argument to the EEH
RTAS calls. If not, Linux would fall back to using the device's
config_addr. Over time these addresses have moved around going from pci_dn
to eeh_dev and finally into eeh_pe. Today the users look like this:
config_addr = pe->config_addr;
if (pe->addr)
config_addr = pe->addr;
rtas_call(..., config_addr, ...);
However, considering the EEH core always operates on a per-PE basis and
even on pseries the only per-device operation is the initial call to
ibm,set-eeh-option I'm not sure if any of this actually works on an RPA
system today. It doesn't make much sense to have the fallback address in
a generic structure either since the bulk of the code which reference it
is in pseries anyway.
The EEH core makes a token effort to support looking up a PE using the
config_addr by having two arguments to eeh_pe_get(). However, a survey of
all the callers to eeh_pe_get() shows that all bar one have the config_addr
argument hard-coded to zero.The only caller that doesn't is in
eeh_pe_tree_insert() which has:
if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr)
return -EINVAL;
pe = eeh_pe_get(hose, edev->pe_config_addr, edev->bdfn);
The third argument (config_addr) is only used if the second (pe->addr)
argument is invalid. The preceding check ensures that the call to
eeh_pe_get() will never happen if edev->pe_config_addr is invalid so there
is no situation where eeh_pe_get() will search for a PE based on the 3rd
argument. The check also means that we'll never insert a PE into the tree
where pe_config_addr is zero since EEH_VALID_PE_ZERO is never set on
pseries. All the users of the fallback address on pseries never actually
use the fallback and all the only caller that supplies something for the
config_addr argument to eeh_pe_get() never use it either. It's all dead
code.
This patch removes the fallback address from eeh_pe since nothing uses it.
Specificly, we do this by:
1) Removing pe->config_addr
2) Removing the EEH_VALID_PE_ZERO flag
3) Removing the fallback address argument to eeh_pe_get().
4) Removing all the checks for pe->addr being zero in the pseries EEH code.
This leaves us with PE's only being identified by what's in their pe->addr
field and the EEH core relying on the platform to ensure that eeh_dev's are
only inserted into the EEH tree if they're actually inside a PE.
No functional changes, I hope.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-9-oohall@gmail.com
|
|
There's no real reason why zero can't be a valid PE configuration address.
Under qemu each sPAPR PHB (i.e. EEH supporting) has the passed-though
devices on bus zero, so the PE address of bus <dddd>:00 should be zero.
However, all previous versions of Linux will reject that, so Qemu at least
goes out of it's way to avoid it. The Qemu implementation of
ibm,get-config-addr-info2 RTAS has the following comment:
> /*
> * We always have PE address of form "00BB0001". "BB"
> * represents the bus number of PE's primary bus.
> */
So qemu puts a one into the register portion of the PE's config_addr to
avoid it being zero. The whole is pretty silly considering that RTAS will
return a negative error code if it can't map the device's config_addr to a
PE.
This patch fixes Linux to treat zero as a valid PE address. This shouldn't
have any real effects due to the Qemu hack mentioned above. And the fact
that Linux EEH has worked historically on PowerVM means they never pass
through devices on bus zero so we would never see the problem there either.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-8-oohall@gmail.com
|
|
The process Linux uses for determining if a device supports EEH or not
appears to be at odds with what PAPR says the OS should be doing. The
current flow is something like:
1. Assume pe_config_addr is equal the the device's config_addr.
2. Attempt to enable EEH on that PE
3. Verify EEH was enabled (POWER4 bug workaround)
4. Try find the pe_config_addr using the ibm,get-config-addr-info2 RTAS
call.
5. If that fails walk the pci_dn tree upwards trying to find a parent
device with EEH support. If we find one then add the device to that PE.
The first major problem with this process is that we need the PE config
address in step 2) since its needs to be passed to the ibm,set-eeh-option
RTAS call when enabling EEH for th PE. We hack around this requirement in
by making the assumption in 1) and delay finding the actual PE address
until 4). This is fine if:
a) The PCI device is the 0th function, and
b) The device is on the PE's root bus.
Granted, the current sequence does appear to work on most systems even when
these conditions are false. At a guess PowerVM's RTAS has workarounds to
accommodate Linux's quirks or the RTAS call to enable EEH is treated as
no-op on most platforms since EEH is usually enabled by default. However,
what is currently implemented is a bit sketch and is downright confusing
since it doesn't match up with what what PAPR suggests we should be doing.
This patch re-works how we handle EEH init so that we find the PE config
address using the ibm,get-config-addr-info2 RTAS call first, then use the
found address to finish the EEH init process. It also drops the Power4
workaround since as of commit 471d7ff8b51b ("powerpc/64s: Remove POWER4
support") the kernel does not support running on a Power4 CPU so there's
no need to support the Power4 platform's quirks either. With the patch
applied the sequence is now:
1. Find the pe_config_addr from the device using the RTAS call.
2. Enable the PE.
3. Insert the edev into the tree and create an eeh_pe if needed.
The other change made here is ignoring unsupported devices entirely.
Currently the device's BARs are saved to the eeh_dev even if the device is
not part of an EEH PE. Not being part of a PE means that an EEH recovery
pass will never see that device so the saving the BARs is pointless.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-7-oohall@gmail.com
|
|
De-duplicate, and fix up the comments, and make the prototype just take a
pci_dn since the job of the function is to return the pe_config_addr of the
PE which contains a given device.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-6-oohall@gmail.com
|
|
The initialisation of EEH mostly happens in a core_initcall_sync initcall,
followed by registering a bus notifier later on in an arch_initcall.
Anything involving initcall dependecies is mostly incomprehensible unless
you've spent a while staring at code so here's the full sequence:
ppc_md.setup_arch <-- pci_controllers are created here
...time passes...
core_initcall <-- pci_dns are created from DT nodes
core_initcall_sync <-- platforms call eeh_init()
postcore_initcall <-- PCI bus type is registered
postcore_initcall_sync
arch_initcall <-- EEH pci_bus notifier registered
subsys_initcall <-- PHBs are scanned here
There's no real requirement to do the EEH setup at the core_initcall_sync
level. It just needs to be done after pci_dn's are created and before we
start scanning PHBs. Simplify the flow a bit by moving the platform EEH
inititalisation to an arch_initcall so we can fold the bus notifier
registration into eeh_init().
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-5-oohall@gmail.com
|
|
Fold pseries_eeh_init() into eeh_pseries_init() rather than having
eeh_init() call it via eeh_ops->init(). It's simpler and it'll let us
delete eeh_ops.init.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-3-oohall@gmail.com
|
|
Drop the EEH register / unregister ops thing and have the platform pass the
ops structure into eeh_init() directly. This takes one initcall out of the
EEH setup path and it means we're only doing EEH setup on the platforms
which actually support it. It's also less code and generally easier to
follow.
No functional changes.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918093050.37344-1-oohall@gmail.com
|
|
Build the kernel with 'make C=2':
arch/powerpc/platforms/pseries/papr_scm.c:825:1: warning: symbol
'dev_attr_perf_stats' was not declared. Should it be static?
Signed-off-by: Wang Wensheng <wangwensheng4@huawei.com>
Reviewed-by: Vaibhav Jain <vaibhav@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200918085951.44983-1-wangwensheng4@huawei.com
|
