Nicholas Piggin [Tue, 9 May 2017 03:17:08 +0000 (13:17 +1000)]
powerpc: Don't print cpu_spec->cpu_name if it's NULL
Currently we assume that if the cpu_spec has a pvr_mask then it must also have a
cpu_name. But that will change in a subsequent commit when we do CPU feature
discovery via the device tree, so check explicitly if cpu_name is NULL.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Tue, 18 Apr 2017 19:12:18 +0000 (05:12 +1000)]
of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle
Introduce primitives for FDT parsing. These will be used for powerpc
cpufeatures node scanning, which has quite complex structure but should
be processed early.
Cc: devicetree@vger.kernel.org Acked-by: Rob Herring <robh@kernel.org> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/scottwood/linux into next
Freescale updates from Scott:
"Includes a fix for a powerpc/next mm regression on 64e, a fix for a
kernel hang on 64e when using a debugger inside a relocated kernel, a
qman fix, and misc qe improvements."
Similarly to commit 2563a70c3b ("powerpc/64s: Remove unnecessary relocation
branch from idle handler"), the machine check handler has a BRANCH_TO from
relocated to relocated code, which is unnecessary.
It has also caused build errors with some toolchains:
arch/powerpc/kernel/exceptions-64s.S: Assembler messages:
arch/powerpc/kernel/exceptions-64s.S:395: Error: operand out of range
(0xffffffffffff8280 is not between 0x0000000000000000 and
0x000000000000ffff)
Fixes: 1945bc4549e5 ("powerpc/64s: Fix POWER9 machine check handler from stop state") Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Reported-and-tested-by : Abdul Haleem <abdhalee@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/mm/book3s/64: Rework page table geometry for lower memory usage
Recently in commit f6eedbba7a26 ("powerpc/mm/hash: Increase VA range to 128TB")
we increased the virtual address space for user processes to 128TB by default,
and up to 512TB if user space opts in.
This obviously required expanding the range of the Linux page tables. For Book3s
64-bit using hash and with PAGE_SIZE=64K, we increased the PGD to 2^15 entries.
This meant we could cover the full address range, while still being able to
insert a 16G hugepage at the PGD level and a 16M hugepage in the PMD.
The downside of that geometry is that it uses a lot of memory for the PGD, and
in particular makes the PGD a 4-page allocation, which means it's much more
likely to fail under memory pressure.
Instead we can make the PMD larger, so that a single PUD entry maps 16G,
allowing the 16G hugepages to sit at that level in the tree. We're then able to
split the remaining bits between the PUG and PGD. We make the PGD slightly
larger as that results in lower memory usage for typical programs.
When THP is enabled the PMD actually doubles in size, to 2^11 entries, or 2^14
bytes, which is large but still < PAGE_SIZE.
Horia Geantă [Mon, 8 May 2017 08:50:16 +0000 (11:50 +0300)]
powerpc: Fix distclean with Makefile.postlink
Makefile.postlink always includes include/config/auto.conf, however
this file is not present in a clean kernel tree, causing make to fail:
$ git clone linuxppc.git
$ cd linuxppc.git
$ make distclean
arch/powerpc/Makefile.postlink:10: include/config/auto.conf: No such file or directory
make[1]: *** No rule to make target `include/config/auto.conf'. Stop.
make: *** [vmlinuxclean] Error 2
Equally running 'make distclean; make distclean' will trip the error case.
Change the inclusion such that file not being found does not trigger an error.
Fixes: f188d0524d7e ("powerpc: Use the new post-link pass to check relocations") Reported-by: Mircea Pop <mircea.pop@nxp.com> Signed-off-by: Horia Geantă <horia.geanta@nxp.com> Tested-by: Justin M. Forbes <jforbes@fedoraproject.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Scott Wood [Fri, 5 May 2017 06:22:06 +0000 (01:22 -0500)]
powerpc/64e: Don't place the stack beyond TASK_SIZE
Commit f4ea6dcb08ea ("powerpc/mm: Enable mappings above 128TB") increased
the task size on book3s, and introduced a mechanism to dynamically
control whether a task uses these larger addresses. While the change to
the task size itself was ifdef-protected to only apply on book3s, the
change to STACK_TOP_USER64 was not. On book3e, this had the effect of
trying to use addresses up to 128TiB for the stack despite a 64TiB task
size limit -- which broke 64-bit userspace producing the following errors:
Starting init: /sbin/init exists but couldn't execute it (error -14)
Starting init: /bin/sh exists but couldn't execute it (error -14)
Kernel panic - not syncing: No working init found. Try passing init= option to kernel. See Linux Documentation/admin-guide/init.rst for guidance.
powerpc/powernv: Block PCI config access on BCM5718 during EEH recovery
Similar to what is done in commit b6541db13952 ("powerpc/eeh: Block
PCI config access upon frozen PE"), we need block PCI config access
for BCM5719 when recovering frozen error on them. Otherwise, an
unexpected recursive fenced PHB error is observed.
Alistair Popple [Wed, 3 May 2017 03:24:08 +0000 (13:24 +1000)]
powerpc/powernv: Fix TCE kill on NVLink2
Commit 616badd2fb49 ("powerpc/powernv: Use OPAL call for TCE kill on
NVLink2") forced all TCE kills to go via the OPAL call for
NVLink2. However the PHB3 implementation of TCE kill was still being
called directly from some functions which in some circumstances caused
a machine check.
This patch adds an equivalent IODA2 version of the function which uses
the correct invalidation method depending on PHB model and changes all
external callers to use it instead.
Fixes: 616badd2fb49 ("powerpc/powernv: Use OPAL call for TCE kill on NVLink2") Cc: stable@vger.kernel.org # v4.11+ Signed-off-by: Alistair Popple <alistair@popple.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/mm/radix: Drop support for CPUs without lockless tlbie
Currently the radix TLB code includes support for CPUs that do *not*
have MMU_FTR_LOCKLESS_TLBIE. On those CPUs we are required to take a
global spinlock before issuing a tlbie.
Radix can only be built for 64-bit Book3s CPUs, and of those, only
POWER4, 970, Cell and PA6T do not have MMU_FTR_LOCKLESS_TLBIE. Although
it's possible to build a kernel with Radix support that can also boot on
those CPUs, we happen to know that in reality none of those CPUs support
the Radix MMU, so the code can never actually run on those CPUs.
So remove the native_tlbie_lock in the Radix TLB code.
Note that there is another lock of the same name in the hash code, which
is unaffected by this patch.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/book3s/mce: Move add_taint() later in virtual mode
machine_check_early() gets called in real mode. The very first time when
add_taint() is called, it prints a warning which ends up calling opal
call (that uses OPAL_CALL wrapper) for writing it to console. If we get a
very first machine check while we are in opal we are doomed. OPAL_CALL
overwrites the PACASAVEDMSR in r13 and in this case when we are done with
MCE handling the original opal call will use this new MSR on it's way
back to opal_return. This usually leads to unexpected behaviour or the
kernel to panic. Instead move the add_taint() call later in the virtual
mode where it is safe to call.
This is broken with current FW level. We got lucky so far for not getting
very first MCE hit while in OPAL. But easily reproducible on Mambo.
Fixes: 27ea2c420cad ("powerpc: Set the correct kernel taint on machine check errors.") Cc: stable@vger.kernel.org # v4.2+ Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Mon, 24 Apr 2017 10:46:59 +0000 (20:46 +1000)]
powerpc/sysfs: Move #ifdef CONFIG_HOTPLUG_CPU out of the function body
The entire body of unregister_cpu_online() is inside an #ifdef
CONFIG_HOTPLUG_CPU block. This is ugly and means we create an empty function
when hotplug is disabled for no reason.
Instead move the #ifdef out of the function body and define the function to be
NULL in the else case. This means we'll pass NULL to cpuhp_setup_state(), but
that's fine because it accepts NULL to mean there is no teardown callback, which
is exactly what we want.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Wed, 15 Feb 2017 09:49:54 +0000 (20:49 +1100)]
powerpc/smp: Document irq enable/disable after migrating IRQs
This code was until recently completely undocumented and even now the comment is
not very verbose.
We've already had one patch sent to remove the IRQ enable/disable because it's
"paradoxical and unnecessary". So document it thoroughly to save anyone else
from puzzling over it.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Andrew Donnellan [Fri, 22 Jul 2016 07:16:35 +0000 (17:16 +1000)]
powerpc/powernv: Document cxl dependency on special case in pnv_eeh_reset()
pnv_eeh_reset() has special handling for PEs whose primary bus is the
root bus or the bus immediately underneath the root port.
The cxl bi-modal card support added in b0b5e5918ad1 ("cxl: Add
cxl_check_and_switch_mode() API to switch bi-modal cards") relies on
this behaviour when hot-resetting the CAPI adapter following a mode
switch. Document this in pnv_eeh_reset() so we don't accidentally break
it.
Suggested-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This patch allows the use of IRQ to notify the change of GPIO status
on MPC8xx CPM IO ports. This then allows to associate IRQs to GPIOs
in the Device Tree.
Russell Currey [Wed, 19 Apr 2017 07:39:27 +0000 (17:39 +1000)]
powerpc/eeh: Clean up and document event handling functions
Remove unnecessary tags in eeh_handle_normal_event(), and add function
comments for eeh_handle_normal_event() and eeh_handle_special_event().
The only functional difference is that in the case of a PE reaching the
maximum number of failures, rather than one message telling you of this
and suggesting you reseat the device, there are two separate messages.
Suggested-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Russell Currey <ruscur@russell.cc> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Russell Currey [Wed, 19 Apr 2017 07:39:26 +0000 (17:39 +1000)]
powerpc/eeh: Avoid use after free in eeh_handle_special_event()
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") Cc: stable@vger.kernel.org # v3.11+ Reported-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Russell Currey <ruscur@russell.cc> Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
cxl: Mask slice error interrupts after first occurrence
In some situations, a faulty AFU slice may create an interrupt storm of
slice errors, rendering the machine unusable. Since these interrupts are
informational only, present the interrupt once, then mask it off to
prevent it from being retriggered until the AFU is reset.
Signed-off-by: Alastair D'Silva <alastair@d-silva.org> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Reviewed-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
cxl: Route eeh events to all drivers in cxl_pci_error_detected()
Fix a boundary condition where in some cases an eeh event that results
in card reset isn't passed on to a driver attached to the virtual PCI
device associated with a slice. This will happen in case when a slice
attached device driver returns a value other than
PCI_ERS_RESULT_NEED_RESET from the eeh error_detected() callback. This
would result in an early return from cxl_pci_error_detected() and
other drivers attached to other AFUs on the card wont be notified.
The patch fixes this by making sure that all slice attached
device-drivers are notified and the return values from
error_detected() callback are aggregated in a scheme where request for
'disconnect' trumps all and 'none' trumps 'need_reset'.
During an eeh event when the cxl card is fenced and card sysfs attr
perst_reloads_same_image is set following warning message is seen in the
kernel logs:
Adapter context unlocked with 0 active contexts
------------[ cut here ]------------
WARNING: CPU: 12 PID: 627 at
../drivers/misc/cxl/main.c:325 cxl_adapter_context_unlock+0x60/0x80 [cxl]
Even though this warning is harmless, it clutters the kernel log
during an eeh event. This warning is triggered as the EEH callback
cxl_pci_error_detected doesn't obtain a context-lock before forcibly
detaching all active context and when context-lock is released during
call to cxl_configure_adapter from cxl_pci_slot_reset, a warning in
cxl_adapter_context_unlock is triggered.
To fix this warning, we acquire the adapter context-lock via
cxl_adapter_context_lock() in the eeh callback
cxl_pci_error_detected() once all the virtual AFU PHBs are notified
and their contexts detached. The context-lock is released in
cxl_pci_slot_reset() after the adapter is successfully reconfigured
and before the we call the slot_reset callback on slice attached
device-drivers.
Fixes: 70b565bbdb91 ("cxl: Prevent adapter reset if an active context exists") Cc: stable@vger.kernel.org # v4.9+ Reported-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Tested-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Oct 2016 03:16:00 +0000 (14:16 +1100)]
powerpc/64: Allow CONFIG_RELOCATABLE if COMPILE_TEST
This was a hack we added to work around the allmodconfig build breaking, see
commit fb43e8477ed9 ("powerpc: Disable RELOCATABLE for COMPILE_TEST with
PPC64").
Since we merged the thin archives support in commit 43c9127d94d6 ("powerpc: Add
option to use thin archives") this hasn't been necessary, so remove it.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Neuling [Thu, 16 Mar 2017 03:04:40 +0000 (14:04 +1100)]
powerpc/xmon: Teach xmon oops about radix vectors
Currently if we take an oops caused by an 0x380 or 0x480 exception, we get a
print which assumes SLB problems. With radix, these vectors have different
meanings.
This patch updates the oops message to reflect these different meanings.
Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Roy Pledge [Mon, 17 Apr 2017 20:55:19 +0000 (16:55 -0400)]
soc/fsl/qbman: Disable IRQs for deferred QBMan work
Work for Congestion State Notifications (CSCN) and Message Ring (MR)
handling is handled via the workqueue mechanism. This requires the
driver to disable those IRQs before scheduling the work and re-enabling
it once the work is completed so that the interrupt doesn't continually
fire.
Signed-off-by: Roy Pledge <roy.pledge@nxp.com> Signed-off-by: Scott Wood <oss@buserror.net>
soc/fsl/qe: only apply QE_General4 workaround on affected SoCs
The QE_General4 workaround is only valid for the MPC832x and MPC836x
SoCs. The other SoCs that embed a QUICC engine are not affected by this
hardware bug and thus can use the computed divisors (this was
successfully tested on the T1040).
Similalry to what was done in commit 8ce795cb0c6b ("i2c: mpc: assign the
correct prescaler from SVR") in order to avoid changes in
the device tree nodes of the QE (with maybe a variant of the compatible
property), the PVR reg is read out to find out if the workaround must be
applied or not.
Signed-off-by: Valentin Longchamp <valentin.longchamp@keymile.com> Signed-off-by: Scott Wood <oss@buserror.net>
Because of integer computation rounding in u-boot (that sets the QE
brg-frequency DTS prop), the clk value is 99999999 Hz even though it is
100 MHz.
When setting brg clks that are exact divisors of 100 MHz, this small
differnce plays a role and can result in lower clks to be output (for
instance 20 MHz - divide by 5 - results in 16.666 MHz - divide by 6).
This patch fixes that by "forcing" the brg_clk to the nearest kHz when
the difference is below 2 integer rounding errors (i.e. 4).
Signed-off-by: Valentin Longchamp <valentin.longchamp@keymile.com> Signed-off-by: Scott Wood <oss@buserror.net>
Since commit 5093bb965a163 ("powerpc/QE: switch to the cpm_muram
implementation"), muram area is not part of immrbar mapping anymore
so immrbar_virt_to_phys() is not usable anymore.
Fixes: 5093bb965a163 ("powerpc/QE: switch to the cpm_muram implementation") Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Li Yang <pku.leo@gmail.com> Signed-off-by: Scott Wood <oss@buserror.net>
LiuHailong [Tue, 7 Feb 2017 02:35:52 +0000 (10:35 +0800)]
powerpc/64e: Fix hang when debugging programs with relocated kernel
Debug interrupts can be taken during interrupt entry, since interrupt
entry does not automatically turn them off. The kernel will check
whether the faulting instruction is between [interrupt_base_book3e,
__end_interrupts], and if so clear MSR[DE] and return.
However, when the kernel is built with CONFIG_RELOCATABLE, it can't use
LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e) and
LOAD_REG_IMMEDIATE(r15,__end_interrupts), as they ignore relocation.
Thus, if the kernel is actually running at a different address than it
was built at, the address comparison will fail, and the exception entry
code will hang at kernel_dbg_exc.
r2(toc) is also not usable here, as r2 still holds data from the
interrupted context, so LOAD_REG_ADDR() doesn't work either. So we use
the *name@got* to get the EV of two labels directly.
Test programs test.c shows as follows:
int main(int argc, char *argv[])
{
if (access("/proc/sys/kernel/perf_event_paranoid", F_OK) == -1)
printf("Kernel doesn't have perf_event support\n");
}
Steps to reproduce the bug, for example:
1) ./gdb ./test
2) (gdb) b access
3) (gdb) r
4) (gdb) s
Signed-off-by: Liu Hailong <liu.hailong6@zte.com.cn> Signed-off-by: Jiang Xuexin <jiang.xuexin@zte.com.cn> Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn> Reviewed-by: Liu Song <liu.song11@zte.com.cn> Reviewed-by: Huang Jian <huang.jian@zte.com.cn>
[scottwood: cleaned up commit message, and specified bad behavior
as a hang rather than an oops to correspond to mainline kernel behavior] Fixes: 1cb6e0649248 ("powerpc/book3e: support CONFIG_RELOCATABLE") Cc: <stable@vger.kernel.org> # 4.4.x- Signed-off-by: Scott Wood <oss@buserror.net>
Michael Ellerman [Fri, 28 Apr 2017 11:57:22 +0000 (21:57 +1000)]
powerpc/mm/hash: Fix off-by-one in comment about kernel contexts ids
Michal Suchánek noticed a comment in book3s/64/mmu-hash.h about the context ids
we use for the kernel was inconsistent with the code and other comments in the
same file.
It should read 1-4 not 1-5.
While we're touching it, update "address" to "addresses" which makes more sense
as it's referring to more than one address below.
Reported-by: Michal Suchánek <msuchanek@suse.de> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This enables VFIO on pseries host in order to allow VFIO in nested guest under
PR KVM or DPDK in a HV guest. This adds support of the VFIO_SPAPR_TCE_IOMMU
type.
This adds exchange() callback to allow TCE updates by the SPAPR TCE IOMMU
driver in VFIO.
This initializes DMA32 window parameters in iommu_table_group as as this does
not implement VFIO_SPAPR_TCE_v2_IOMMU and VFIO_SPAPR_TCE_IOMMU just reuses the
existing DMA32 window.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/powernv: Fix iommu table size calculation hook for small tables
When the userspace requests a small TCE table (which takes less than
the system page size) and more than 1 TCE level, the existing code
returns a single page size which is a bug as each additional TCE level
requires at least one page and this is what
pnv_pci_ioda2_table_alloc_pages() does. And we end up seeing
WARN_ON(!ret && ((*ptbl)->it_allocated_size != table_size))
in drivers/vfio/vfio_iommu_spapr_tce.c.
This replaces incorrect _ALIGN_UP() (which aligns zero up to zero) with
max_t() to fix the bug.
Besides removing WARN_ON(), there should be no other changes in
behaviour.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/powernv: Check kzalloc() return value in pnv_pci_table_alloc
pnv_pci_table_alloc() ignores possible failure from kzalloc_node(),
this adds a check. There are 2 callers of pnv_pci_table_alloc(),
one already checks for tbl!=NULL, this adds WARN_ON() to the other path
which only happens during boot time in IODA1 and not expected to fail.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Sat, 26 Nov 2016 03:26:09 +0000 (14:26 +1100)]
powerpc: Use the new post-link pass to check relocations
Currently powerpc has to introduce a dependency on its default build
target zImage in order to run a relocation check pass over the linked
vmlinux. This is deficient because the check is not run if the plain
vmlinux target is built, or if one of the other boot targets is built.
Switch to using the kbuild post-link pass, added in commit fbe6e37dab97
("kbuild: add arch specific post-link Makefile") in order to run this
check. In future powerpc will use this to do more complicated operations,
but initially using it for something simple is a good first step.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 19 Dec 2016 18:30:11 +0000 (04:30 +1000)]
powerpc/xmon: Wait for secondaries before IPI'ing on system reset
An externally triggered system reset (e.g., via QEMU nmi command, or pseries
reset button) can cause system reset interrupts on all CPUs. In case this causes
xmon to be entered, it is undesirable for the primary (first) CPU into xmon to
trigger an NMI IPI to others, because this may cause a nested system reset
interrupt.
So spin for a time waiting for secondaries to join xmon before performing the
NMI IPI, similarly to what the crash dump code does.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Only do it when we come in from system reset, not via sysrq etc.] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 19 Dec 2016 18:30:08 +0000 (04:30 +1000)]
powerpc: Add NMI IPI infrastructure
Add a simple NMI IPI system that handles concurrency and reentrancy.
The platform does not have to implement a true non-maskable interrupt,
the default is to simply use the debugger break IPI message. This has
now been co-opted for a general IPI message, and users (debugger and
crash) have been reimplemented on top of the NMI system.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Incorporate incremental fixes from Nick] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 19 Dec 2016 18:30:06 +0000 (04:30 +1000)]
powerpc/64s: Dedicated system reset interrupt stack
The system reset interrupt is used for crash/debug situations, so it is
desirable to have as little impact on the normal state of the system as
possible.
Currently it uses the current kernel stack to process the exception.
This stores into the stack which may be involved with the crash. The
stack pointer may be corrupted, or it may have overflowed.
Avoid or minimise these problems by creating a dedicated NMI stack for
the system reset interrupt to use.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 19 Dec 2016 18:30:05 +0000 (04:30 +1000)]
powerpc/64s: Disallow system reset vs system reset reentrancy
In preparation for using a dedicated stack for system reset interrupts,
prevent a nested system reset from recovering, in order to simplify
code that is called in crash/debug path. This allows a system reset
interrupt to just use the base stack pointer.
Keep an in_nmi nesting counter similarly to the in_mce counter. Consider
the interrrupt non-recoverable if it is taken inside another system
reset.
Interrupt nesting could be allowed similarly to MCE, but system reset
is a special case that's not for normal operation, so simplicity wins
until there is requirement for nested system reset interrupts.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 19 Dec 2016 18:30:04 +0000 (04:30 +1000)]
powerpc/64s: Fix system reset vs general interrupt reentrancy
The system reset interrupt can occur when MSR_EE=0, and it currently
uses the PACA_EXGEN save area.
Some PACA_EXGEN interrupts have a window where MSR_RI=1 and MSR_EE=0
when the save area is still in use. A system reset interrupt in this
window can lead to undetected corruption when the save area gets
overwritten.
This patch introduces PACA_EXNMI save area for system reset exceptions,
which closes this corruption window. It's also helpful to retain the
EXGEN state for debugging situations, even if not considering the
recoverability aspect.
This patch also moves the PACA_EXMC area down to a less frequently used
part of the paca with the new save area.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 20 Mar 2017 06:31:49 +0000 (16:31 +1000)]
powerpc/cbe: Do not process external or decremeter interrupts from sreset
Cell will wake from low power state at the system reset interrupt,
with the event encoded in SRR1, rather than waking at the interrupt
vector that corresponds to that event.
The system reset handler for this platform decodes SRR1 event reason
and calls the interrupt handler to process it directly from the system
reset handlre.
A subsequent change will treat the system reset interrupt as a Linux NMI
with its own per-CPU stack, and this will no longer work. Remove the
external and decrementer handlers from the system reset handler.
- The external exception remains raised and will fire again at the
EE interrupt vector when system reset returns.
- The decrementer is set to 1 so it will be raised again and fire when
the system reset returns.
It is possible to branch to an idle handler from the system reset
interrupt (like POWER does), then restore a normal stack and restore
this optimisation. But simplicity wins for now.
Tested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Mon, 20 Mar 2017 06:31:48 +0000 (16:31 +1000)]
powerpc/pasemi: Do not process external or decrementer interrupts from sreset
PA Semi will wake from low power state at the system reset interrupt,
with the event encoded in SRR1, rather than waking at the interrupt
vector that corresponds to that event.
The system reset handler for this platform decodes SRR1 event reason
and calls the interrupt handler to process it directly from the system
reset handlre.
A subsequent change will treat the system reset interrupt as a Linux NMI
with its own per-CPU stack, and this will no longer work. Remove the
external and decrementer handlers from the system reset handler.
- The external exception remains raised and will fire again at the
EE interrupt vector when system reset returns.
- The decrementer is set to 1 so it will be raised again and fire when
the system reset returns.
It is possible to branch to an idle handler from the system reset
interrupt (like POWER does), then restore a normal stack and restore
this optimisation. But simplicity wins for now.
Tested-by: Christian Zigotzky <chzigotzky@xenosoft.de> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/ftrace/64: Split further based on -mprofile-kernel
Split ftrace_64.S further retaining the core ftrace 64-bit aspects
in ftrace_64.S and moving ftrace_caller() and ftrace_graph_caller() into
separate files based on -mprofile-kernel. The livepatch routines are all
now contained within the mprofile file.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
entry_*.S now includes a lot more than just kernel entry/exit code. As a
first step at cleaning this up, let's split out the ftrace bits into
separate files. Also move all related tracing code into a new trace/
subdirectory.
No functional changes.
Suggested-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Page table dump debugfs file is named 'kernel_page_tables' on
all other architectures implementing it, while is is named
'kernel_pagetables' on powerpc. This patch renames it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
On PPC32 (eg. mpc885_ads_defconfig), page table dump compilation fails as
follows. This is because the memory layout is slightly different on PPC32. This
patch adapts it.
arch/powerpc/mm/dump_linuxpagetables.c: In function 'walk_pagetables':
arch/powerpc/mm/dump_linuxpagetables.c:369:10: error: 'KERN_VIRT_START' undeclared (first use in this function)
...
Fixes: 8eb07b187000d ("powerpc/mm: Dump linux pagetables") Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
_tlbiel_pid() is called with a ric (Radix Invalidation Control) argument of
either RIC_FLUSH_TLB or RIC_FLUSH_ALL.
RIC_FLUSH_ALL says to invalidate the entire TLB and the Page Walk Cache (PWC).
To flush the whole TLB, we have to iterate over each set (congruence class) of
the TLB. Currently we do that and pass RIC_FLUSH_ALL each time. That is not
incorrect but it means we flush the PWC 128 times, when once would suffice.
Fix it by doing the first flush with the ric value we're passed, and then if it
was RIC_FLUSH_ALL, we downgrade it to RIC_FLUSH_TLB, because we know we have
just flushed the PWC and don't need to do it again.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Split out of combined patch, tweak logic, rewrite change log] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently we implement flushing of the page walk cache (PWC) by calling
_tlbiel_pid() with a RIC (Radix Invalidation Control) value of 1 which says to
only flush the PWC.
But _tlbiel_pid() loops over each set (congruence class) of the TLB, which is
not necessary when we're just flushing the PWC.
In fact the set argument is ignored for a PWC flush, so essentially we're just
flushing the PWC 127 extra times for no benefit.
Fix it by adding tlbiel_pwc() which just does a single flush of the PWC.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Split out of combined patch, drop _ in name, rewrite change log] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Wed, 26 Apr 2017 07:32:38 +0000 (17:32 +1000)]
powerpc/powernv: Fix oops on P9 DD1 in cause_ipi()
Recently we merged the native xive support for Power9, and then separately some
reworks for doorbell IPI support. In isolation both series were OK, but the
merged result had a bug in one case.
On P9 DD1 we use pnv_p9_dd1_cause_ipi() which tries to use doorbells, and then
falls back to the interrupt controller. However the fallback is implemented by
calling icp_ops->cause_ipi. But now that xive support is merged we might be
using xive, in which case icp_ops is not initialised, it's a xics specific
structure. This leads to an oops such as:
Unable to handle kernel paging request for data at address 0x00000028
Oops: Kernel access of bad area, sig: 11 [#1]
NIP pnv_p9_dd1_cause_ipi+0x74/0xe0
LR smp_muxed_ipi_message_pass+0x54/0x70
To fix it, rather than using icp_ops which might be NULL, have both xics and
xive set smp_ops->cause_ipi, and then in the powernv code we save that as
ic_cause_ipi before overriding smp_ops->cause_ipi. For paranoia add a WARN_ON()
to check if somehow smp_ops->cause_ipi is NULL.
Fixes: b866cc2199d6 ("powerpc: Change the doorbell IPI calling convention") Tested-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Wed, 26 Apr 2017 05:57:19 +0000 (15:57 +1000)]
powerpc/powernv: Fix missing attr initialisation in opal_export_attrs()
In opal_export_attrs() we dynamically allocate some bin_attributes. They're
allocated with kmalloc() and although we initialise most of the fields, we don't
initialise write() or mmap(), and in particular we don't initialise the lockdep
related fields in the embedded struct attribute.
This leads to a lockdep warning at boot:
BUG: key c0000000f11906d8 not in .data!
WARNING: CPU: 0 PID: 1 at ../kernel/locking/lockdep.c:3136 lockdep_init_map+0x28c/0x2a0
...
Call Trace:
lockdep_init_map+0x288/0x2a0 (unreliable)
__kernfs_create_file+0x8c/0x170
sysfs_add_file_mode_ns+0xc8/0x240
__machine_initcall_powernv_opal_init+0x60c/0x684
do_one_initcall+0x60/0x1c0
kernel_init_freeable+0x2f4/0x3d4
kernel_init+0x24/0x160
ret_from_kernel_thread+0x5c/0xb0
Fix it by kzalloc'ing the attr, which fixes the uninitialised write() and
mmap(), and calling sysfs_bin_attr_init() on it to initialise the lockdep
fields.
Fixes: 11fe909d2362 ("powerpc/powernv: Add OPAL exports attributes to sysfs") Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Tue, 25 Apr 2017 10:49:24 +0000 (20:49 +1000)]
powerpc/mm: Fix possible out-of-bounds shift in arch_mmap_rnd()
The recent patch to add runtime configuration of the ASLR limits added a bug in
arch_mmap_rnd() where we may shift an integer (32-bits) by up to 33 bits,
leading to undefined behaviour.
In practice it exhibits as every process seg faulting instantly, presumably
because the rnd value hasn't been restricited by the modulus at all. We didn't
notice because it only happens under certain kernel configurations and if the
number of bits is actually set to a large value.
Fix it by switching to unsigned long.
Fixes: 9fea59bd7ca5 ("powerpc/mm: Add support for runtime configuration of ASLR limits") Reported-by: Balbir Singh <bsingharora@gmail.com> Reviewed-by: Kees Cook <keescook@chromium.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
David Gibson [Wed, 19 Apr 2017 06:38:26 +0000 (16:38 +1000)]
powerpc/mm: Ensure IRQs are off in switch_mm()
powerpc expects IRQs to already be (soft) disabled when switch_mm() is
called, as made clear in the commit message of 9c1e105238c4 ("powerpc: Allow
perf_counters to access user memory at interrupt time").
Aside from any race conditions that might exist between switch_mm() and an IRQ,
there is also an unconditional hard_irq_disable() in switch_slb(). If that isn't
followed at some point by an IRQ enable then interrupts will remain disabled
until we return to userspace.
It is true that when switch_mm() is called from the scheduler IRQs are off, but
not when it's called by use_mm(). Looking closer we see that last year in commit f98db6013c55 ("sched/core: Add switch_mm_irqs_off() and use it in the scheduler")
this was made more explicit by the addition of switch_mm_irqs_off() which is now
called by the scheduler, vs switch_mm() which is used by use_mm().
Arguably it is a bug in use_mm() to call switch_mm() in a different context than
it expects, but fixing that will take time.
This was discovered recently when vhost started throwing warnings such as:
BUG: sleeping function called from invalid context at kernel/mutex.c:578
in_atomic(): 0, irqs_disabled(): 1, pid: 10768, name: vhost-10760
no locks held by vhost-10760/10768.
irq event stamp: 10
hardirqs last enabled at (9): _raw_spin_unlock_irq+0x40/0x80
hardirqs last disabled at (10): switch_slb+0x2e4/0x490
softirqs last enabled at (0): copy_process+0x5e8/0x1260
softirqs last disabled at (0): (null)
Call Trace:
show_stack+0x88/0x390 (unreliable)
dump_stack+0x30/0x44
__might_sleep+0x1c4/0x2d0
mutex_lock_nested+0x74/0x5c0
cgroup_attach_task_all+0x5c/0x180
vhost_attach_cgroups_work+0x58/0x80 [vhost]
vhost_worker+0x24c/0x3d0 [vhost]
kthread+0xec/0x100
ret_from_kernel_thread+0x5c/0xd4
Prior to commit 04b96e5528ca ("vhost: lockless enqueuing") (Aug 2016) the
vhost_worker() would do a spin_unlock_irq() not long after calling use_mm(),
which had the effect of reenabling IRQs. Since that commit removed the locking
in vhost_worker() the body of the vhost_worker() loop now runs with interrupts
off causing the warnings.
This patch addresses the problem by making the powerpc code mirror the x86 code,
ie. we disable interrupts in switch_mm(), and optimise the scheduler case by
defining switch_mm_irqs_off().
Cc: stable@vger.kernel.org # v4.7+ Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
[mpe: Flesh out/rewrite change log, add stable] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/sysfs: Fix reference leak of cpu device_nodes present at boot
For CPUs present at boot each logical CPU acquires a reference to the
associated device node of the core. This happens in register_cpu() which
is called by topology_init(). The result of this is that we end up with
a reference held by each thread of the core. However, these references
are never freed if the CPU core is DLPAR removed.
This patch fixes the reference leaks by acquiring and releasing the references
in the CPU hotplug callbacks un/register_cpu_online(). With this patch symmetric
reference counting is observed with both CPUs present at boot, and those DLPAR
added after boot.
powerpc/pseries: Fix of_node_put() underflow during DLPAR remove
Historically struct device_node references were tracked using a kref embedded as
a struct field. Commit 75b57ecf9d1d ("of: Make device nodes kobjects so they
show up in sysfs") (Mar 2014) refactored device_nodes to be kobjects such that
the device tree could by more simply exposed to userspace using sysfs.
Commit 0829f6d1f69e ("of: device_node kobject lifecycle fixes") (Mar 2014)
followed up these changes to better control the kobject lifecycle and in
particular the referecne counting via of_node_get(), of_node_put(), and
of_node_init().
A result of this second commit was that it introduced an of_node_put() call when
a dynamic node is detached, in of_node_remove(), that removes the initial kobj
reference created by of_node_init().
Traditionally as the original dynamic device node user the pseries code had
assumed responsibilty for releasing this final reference in its platform
specific DLPAR detach code.
This patch fixes a refcount underflow introduced by commit 0829f6d1f6, and
recently exposed by the upstreaming of the recount API.
Messages like the following are no longer seen in the kernel log with this
patch following DLPAR remove operations of cpus and pci devices.
rpadlpar_io: slot PHB 72 removed
refcount_t: underflow; use-after-free.
------------[ cut here ]------------
WARNING: CPU: 5 PID: 3335 at lib/refcount.c:128 refcount_sub_and_test+0xf4/0x110
Fixes: 0829f6d1f69e ("of: device_node kobject lifecycle fixes") Cc: stable@vger.kernel.org # v3.15+ Signed-off-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
[mpe: Make change log commit references more verbose] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Mon, 24 Apr 2017 00:35:14 +0000 (10:35 +1000)]
powerpc/xmon: Deindent the SLB dumping logic
Currently the code that dumps SLB entries uses a double-nested if. This
means the actual dumping logic is a bit squashed. Deindent it by using
continue.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Reviewed-by: Rashmica Gupta <rashmica.g@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Mon, 24 Apr 2017 14:24:04 +0000 (00:24 +1000)]
Merge branch 'topic/kprobes' into next
Although most of these kprobes patches are powerpc specific, there's a couple
that touch generic code (with Acks). At the moment there's one conflict with
acme's tree, but it's not too bad. Still just in case some other conflicts show
up, we've put these in a topic branch so another tree could merge some or all of
it if necessary.
powerpc/kprobes: Prefer ftrace when probing function entry
KPROBES_ON_FTRACE avoids much of the overhead of regular kprobes as it
eliminates the need for a trap, as well as the need to emulate or single-step
instructions.
Though OPTPROBES provides us with similar performance, we have limited
optprobes trampoline slots. As such, when asked to probe at a function
entry, default to using the ftrace infrastructure.
With:
# cd /sys/kernel/debug/tracing
# echo 'p _do_fork' > kprobe_events
before patch:
# cat ../kprobes/list c0000000000daf08 k _do_fork+0x8 [DISABLED] c000000000044fc0 k kretprobe_trampoline+0x0 [OPTIMIZED]
and after patch:
# cat ../kprobes/list c0000000000d074c k _do_fork+0xc [DISABLED][FTRACE] c0000000000412b0 k kretprobe_trampoline+0x0 [OPTIMIZED]
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc: Introduce a new helper to obtain function entry points
kprobe_lookup_name() is specific to the kprobe subsystem and may not always
return the function entry point (in a subsequent patch for KPROBES_ON_FTRACE).
For looking up function entry points, introduce a separate helper and use it
in optprobes.c
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Pass the real LR to the ftrace handler. This is needed for KPROBES_ON_FTRACE for
the pre handlers.
Also, with KPROBES_ON_FTRACE, the link register may be updated by the pre
handlers or by a registed kretprobe. Honor updated LR by restoring it from
pt_regs, rather than from the stack save area.
Live patch and function graph continue to work fine with this change.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Introduce __head_end to mark end of the early fixed sections and use it to
blacklist all exception handlers from kprobes.
mpe: We do not need to do anything special for relocatable kernels, where the
exception vectors are split from the main kernel, as the split vectors are
already excluded by the check for kernel_text_address().
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
[mpe: Move __head_end outside #ifdef 64-bit to unbreak the 32-bit build] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/kprobes: Convert __kprobes to NOKPROBE_SYMBOL()
Along similar lines as commit 9326638cbee2 ("kprobes, x86: Use NOKPROBE_SYMBOL()
instead of __kprobes annotation"), convert __kprobes annotation to either
NOKPROBE_SYMBOL() or nokprobe_inline. The latter forces inlining, in which case
the caller needs to be added to NOKPROBE_SYMBOL().
Also:
- blacklist arch_deref_entry_point(), and
- convert a few regular inlines to nokprobe_inline in lib/sstep.c
A key benefit is the ability to detect such symbols as being
blacklisted. Before this patch:
$ cat /sys/kernel/debug/kprobes/blacklist | grep read_mem
$ perf probe read_mem
Failed to write event: Invalid argument
Error: Failed to add events.
$ dmesg | tail -1
[ 3736.112815] Could not insert probe at _text+10014968: -22
After patch:
$ cat /sys/kernel/debug/kprobes/blacklist | grep read_mem
0xc000000000072b50-0xc000000000072d20 read_mem
$ perf probe read_mem
read_mem is blacklisted function, skip it.
Added new events:
(null):(null) (on read_mem)
probe:read_mem (on read_mem)
Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
[mpe: Minor change log formatting, fix up some conflicts] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/ftrace: Move stack setup and teardown code into ftrace_graph_caller()
Move the stack setup and teardown code into ftrace_graph_caller(). This way, we
don't incur the cost of setting it up unless function graph is enabled for this
function.
Also, remove the extraneous LR restore code after the function graph stub. LR
has previously been restored and neither livepatch_handler() nor
ftrace_graph_caller() return back here.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
[mpe: Drop bad change to non-mprofile-kernel version of ftrace_graph_caller] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The idle workaround does not need to load PACATOC, and it does not
need to be called within a nested function that requires LR to be
saved.
Load the PACATOC at entry to the idle wakeup. It does not matter which
PACA this comes from, so it's okay to call before the workaround. Then
apply the workaround to get the right PACA.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:50 +0000 (23:05 +1000)]
powerpc/64s: Idle POWER8 avoid full state loss recovery where possible
If not all threads were in winkle, full state loss recovery is not
necessary and can be avoided. A previous patch removed this optimisation
due to some complexity with the implementation. Re-implement it by
counting the number of threads in winkle with the per-core idle state.
Only restore full state loss if all threads were in winkle.
This has a small window of false positives right before threads execute
winkle and just after they wake up, when the winkle count does not
reflect the true number of threads in winkle. This is not a significant
problem in comparison with even the minimum winkle duration. For
correctness, a false positive is not a problem (only false negatives
would be).
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:49 +0000 (23:05 +1000)]
powerpc/64s: Idle do not hold reservation longer than required
When taking the core idle state lock, grab it immediately like a regular
lock, rather than adding more tests in there. Holding the lock keeps it
stable, so there is no need to do it whole holding the reservation.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:48 +0000 (23:05 +1000)]
powerpc/64s: Expand core idle state bits
In preparation for adding more bits to the core idle state word, move
the lock bit up, and unlock by flipping the lock bit rather than masking
off all but the thread bits.
Add branch hints for atomic operations while we're here.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:47 +0000 (23:05 +1000)]
powerpc/64s: Fix POWER9 machine check handler from stop state
The ISA specifies power save wakeup due to a machine check exception can
cause a machine check interrupt (rather than the usual system reset
interrupt).
The machine check handler copes with this by doing low level machine
check recovery without restoring full state from idle, then queues up a
machine check event for logging, then directly executes the same idle
instruction it woke from. This minimises the work done before recovery
is performed.
The problem is that it requires machine specific instructions and
knowledge of the book3s idle code. Currently it only has code to handle
POWER8 idle, so POWER9 crashes when trying to execute the P8 idle
instructions which don't exist in ISAv3.0B.
Instead of going to sleep after recovery, do the usual idle wakeup and
state restoration by calling into the normal idle wakeup path. This
reuses the normal idle wakeup paths.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Reviewed-by: Mahesh J Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:46 +0000 (23:05 +1000)]
powerpc/64s: Use alternative feature patching
This reduces the number of nops for POWER8.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:45 +0000 (23:05 +1000)]
powerpc/64s: Stop using bit in HSPRG0 to test winkle
The POWER8 idle code has a neat trick of programming the power on engine
to restore a low bit into HSPRG0, so idle wakeup code can test and see
if it has been programmed this way and therefore lost all state. Restore
time can be reduced if winkle has not been reached.
However this messes with our r13 PACA pointer, and requires HSPRG0 to be
written to. It also optimizes the slowest and most uncommon case at the
expense of another SPR write in the common nap state wakeup.
Remove this complexity and assume winkle sleeps always require a state
restore. This speedup could be made entirely contained within the winkle
idle code by counting per-core winkles and setting a thread bitmap when
all have gone to winkle.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:44 +0000 (23:05 +1000)]
powerpc/64s: Move remaining system reset idle code into idle_book3s.S
No functional change.
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com> Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 13:05:43 +0000 (23:05 +1000)]
powerpc/64s: Remove unnecessary relocation branch from idle handler
The system reset idle handler system_reset_idle_common is relocated, so
relocation is not required to branch to kvm_start_guest. The superfluous
relocation does not result in incorrect code, but it does not compile
outside of exception-64s.S (with fixed section definitions).
Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Thu, 20 Apr 2017 14:36:20 +0000 (00:36 +1000)]
powerpc/mm: Add support for runtime configuration of ASLR limits
Add powerpc support for mmap_rnd_bits and mmap_rnd_compat_bits, which are two
sysctls that allow a user to configure the number of bits of randomness used for
ASLR.
Because of the way the Kconfig for ARCH_MMAP_RND_BITS is defined, we have to
construct at least the MIN value in Kconfig, vs in a header which would be more
natural. Given that we just go ahead and do it all in Kconfig.
At least according to the code (the documentation makes no mention of it), the
value is defined as the number of bits of randomisation *of the page*, not the
address. This makes some sense, with larger page sizes more of the low bits are
forced to zero, which would reduce the randomisation if we didn't take the
PAGE_SIZE into account. However it does mean the min/max values have to change
depending on the PAGE_SIZE in order to actually limit the amount of address
space consumed by the randomisation.
The result of that is that we have to define the default values based on both
32-bit vs 64-bit, but also the configured PAGE_SIZE. Furthermore now that we
have 128TB address space support on Book3S, we also have to take that into
account.
Finally we can wire up the value in arch_mmap_rnd().
The default implementation of ioremap_cache() is aliased to ioremap().
On powerpc ioremap() creates cache-inhibited mappings by default which
is almost certainly not what you wanted.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/kprobes: Emulate instructions on kprobe handler re-entry
On kprobe handler re-entry, try to emulate the instruction rather than single
stepping always.
Acked-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/kprobes: Factor out code to emulate instruction into a helper
Factor out code to emulate instruction into a try_to_emulate()
helper function. This makes no functional changes.
Acked-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Naveen N. Rao [Wed, 8 Mar 2017 08:26:07 +0000 (13:56 +0530)]
powerpc/kretprobes: Override default function entry offset
With ABIv2, we offset 8 bytes into a function to get at the local entry
point.
mpe: NB this function is currently not called, the change to generic code to
call it is being merged via the tip tree.
Acked-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Acked-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/kprobes: Fix handling of function offsets on ABIv2
commit 239aeba76409 ("perf powerpc: Fix kprobe and kretprobe handling with
kallsyms on ppc64le") changed how we use the offset field in struct kprobe on
ABIv2. perf now offsets from the global entry point if an offset is specified
and otherwise chooses the local entry point.
Fix the same in kernel for kprobe API users. We do this by extending
kprobe_lookup_name() to accept an additional parameter to indicate the offset
specified with the kprobe registration. If offset is 0, we return the local
function entry and return the global entry point otherwise.
Acked-by: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
kprobes: Convert kprobe_lookup_name() to a function
The macro is now pretty long and ugly on powerpc. In the light of further
changes needed here, convert it to a __weak variant to be over-ridden with a
nicer looking function.
Suggested-by: Masami Hiramatsu <mhiramat@kernel.org> Acked-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Thu, 13 Apr 2017 09:45:48 +0000 (19:45 +1000)]
powerpc/64s: Use relon prolog for EXC_VIRT_OOL_MASKABLE_HV handlers
Hypervisor Virtualization and Directed Hypervisor Doorbell interrupt handlers
use the macro EXC_VIRT_OOL_MASKABLE_HV for their relocation-on handlers, which
calls MASKABLE_RELON_EXCEPTION_HV_OOL, which uses the *real mode* interrupt
prolog. This means we needlessly rfid from virtual mode to virtual mode.
For POWER8 it only affects doorbell IPIs. Context switch microbenchmark between
threads with snooze disabled (which causes IPI) gets about 3% faster, about 370
cycles. Should be more important on POWER9 with global doorbells and HVI for
host interrupts.
Use the RELON variant instead to reduce overhead.
Fixes: 1707dd1613 ("powerpc: Save CFAR before branching in interrupt entry paths") Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fold some more detail into the change log] Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Michael Ellerman [Thu, 20 Apr 2017 04:43:19 +0000 (14:43 +1000)]
powerpc/xive: Fix missing check of rc != OPAL_BUSY
Dan Carpenter noticed that the code in __xive_native_disable_queue() has a for
loop with an unconditional break in the middle, which doesn't make a lot of
sense.
What the code's supposed to do is loop as long as OPAL says it's busy, if we get
any other return code, either success or failure, then we should break the loop.
So add the missing check.
Fixes: 243e25112d06 ("powerpc/xive: Native exploitation of the XIVE interrupt controller") Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 02:27:38 +0000 (12:27 +1000)]
powerpc/64s: Remove SAO feature from Power9 DD1
Power9 DD1 does not implement SAO. Although it's not widely used, its presence
or absence is visible to user space via arch_validate_prot() so it's moderately
important that we get the value right.
Fixes: 7dccfbc325bb ("powerpc/book3s: Add a cpu table entry for different POWER9 revs") Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nicholas Piggin [Wed, 19 Apr 2017 02:27:37 +0000 (12:27 +1000)]
powerpc/64s: Remove ICSWX feature from Power9
Power9 does not implement the icswx instruction. This CPU feature is not visible
to userspace and is only used in the CONFIG_PPC_ICSWX code, which is generally
not enabled, and can only be triggered by other code using icswx, which should
not happen on Power9 systems in the first place. So impact should be minimal.
Fixes: c3ab300ea5 ("powerpc: Add POWER9 cputable entry") Signed-off-by: Nicholas Piggin <npiggin@gmail.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/perf: Add Power8 mem_access event to sysfs
Patch add "mem_access" event to sysfs. This as-is not a raw event
supported by Power8 pmu. Instead, it is formed based on
raw event encoding specificed in isa207-common.h.
Primary PMU event used here is PM_MRK_INST_CMPL.
This event tracks only the completed marked instructions.
Random sampling mode (MMCRA[SM]) with Random Instruction
Sampling (RIS) is enabled to mark type of instructions.
With Random sampling in RLS mode with PM_MRK_INST_CMPL event,
the LDST /DATA_SRC fields in SIER identifies the memory
hierarchy level (eg: L1, L2 etc) statisfied a data-cache
miss for a marked instruction.
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc/perf: Support to export MMCRA[TEC*] field to userspace
Threshold feature when used with MMCRA [Threshold Event Counter Event],
MMCRA[Threshold Start event] and MMCRA[Threshold End event] will update
MMCRA[Threashold Event Counter Exponent] and MMCRA[Threshold Event
Counter Multiplier] with the corresponding threshold event count values.
Patch to export MMCRA[TECX/TECM] to userspace in 'weight' field of
struct perf_sample_data.
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
projects / karo-tx-linux.git / log