For one PCI error relevant OPAL event, we possibly have multiple
EEH errors for that. For example, multiple frozen PEs detected on
different PHBs. Unfortunately, we didn't cover the case. The patch
enumarates the return value from eeh_ops::next_error() and change
eeh_handle_special_event() and eeh_ops::next_error() to handle all
existing EEH errors.
As Ben pointed out, we needn't list_for_each_entry_safe() since we
are not deleting any PHB from the hose_list and the EEH serialized
lock should be held while purging EEH events. The patch covers those
suggestions as well.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Currently, when we have a process using the transactional memory
facilities on POWER8 (that is, the processor is in transactional
or suspended state), and the process enters the kernel and the
kernel then uses the floating-point or vector (VMX/Altivec) facility,
we end up corrupting the user-visible FP/VMX/VSX state. This
happens, for example, if a page fault causes a copy-on-write
operation, because the copy_page function will use VMX to do the
copy on POWER8. The test program below demonstrates the bug.
The bug happens because when FP/VMX state for a transactional process
is stored in the thread_struct, we store the checkpointed state in
.fp_state/.vr_state and the transactional (current) state in
.transact_fp/.transact_vr. However, when the kernel wants to use
FP/VMX, it calls enable_kernel_fp() or enable_kernel_altivec(),
which saves the current state in .fp_state/.vr_state. Furthermore,
when we return to the user process we return with FP/VMX/VSX
disabled. The next time the process uses FP/VMX/VSX, we don't know
which set of state (the current register values, .fp_state/.vr_state,
or .transact_fp/.transact_vr) we should be using, since we have no
way to tell if we are still in the same transaction, and if not,
whether the previous transaction succeeded or failed.
Thus it is necessary to strictly adhere to the rule that if FP has
been enabled at any point in a transaction, we must keep FP enabled
for the user process with the current transactional state in the
FP registers, until we detect that it is no longer in a transaction.
Similarly for VMX; once enabled it must stay enabled until the
process is no longer transactional.
In order to keep this rule, we add a new thread_info flag which we
test when returning from the kernel to userspace, called TIF_RESTORE_TM.
This flag indicates that there is FP/VMX/VSX state to be restored
before entering userspace, and when it is set the .tm_orig_msr field
in the thread_struct indicates what state needs to be restored.
The restoration is done by restore_tm_state(). The TIF_RESTORE_TM
bit is set by new giveup_fpu/altivec_maybe_transactional helpers,
which are called from enable_kernel_fp/altivec, giveup_vsx, and
flush_fp/altivec_to_thread instead of giveup_fpu/altivec.
The other thing to be done is to get the transactional FP/VMX/VSX
state from .fp_state/.vr_state when doing reclaim, if that state
has been saved there by giveup_fpu/altivec_maybe_transactional.
Having done this, we set the FP/VMX bit in the thread's MSR after
reclaim to indicate that that part of the state is now valid
(having been reclaimed from the processor's checkpointed state).
Finally, in the signal handling code, we move the clearing of the
transactional state bits in the thread's MSR a bit earlier, before
calling flush_fp_to_thread(), so that we don't unnecessarily set
the TIF_RESTORE_TM bit.
This is the test program:
/* Michael Neuling 4/12/2013
*
* See if the altivec state is leaked out of an aborted transaction due to
* kernel vmx copy loops.
*
* gcc -m64 htm_vmxcopy.c -o htm_vmxcopy
*
*/
/* We don't use all of these, but for reference: */
int main(int argc, char *argv[])
{
long double vecin = 1.3;
long double vecout;
unsigned long pgsize = getpagesize();
int i;
int fd;
int size = pgsize*16;
char tmpfile[] = "/tmp/page_faultXXXXXX";
char buf[pgsize];
char *a;
uint64_t aborted = 0;
fd = mkstemp(tmpfile);
assert(fd >= 0);
memset(buf, 0, pgsize);
for (i = 0; i < size; i += pgsize)
assert(write(fd, buf, pgsize) == pgsize);
unlink(tmpfile);
a = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE, fd, 0);
assert(a != MAP_FAILED);
asm __volatile__(
"lxvd2x 40,0,%[vecinptr] ; " // set 40 to initial value
TBEGIN
"beq 3f ;"
TSUSPEND
"xxlxor 40,40,40 ; " // set 40 to 0
"std 5, 0(%[map]) ;" // cause kernel vmx copy page
TABORT
TRESUME
TEND
"li %[res], 0 ;"
"b 5f ;"
"3: ;" // Abort handler
"li %[res], 1 ;"
"5: ;"
"stxvd2x 40,0,%[vecoutptr] ; "
: [res]"=r"(aborted)
: [vecinptr]"r"(&vecin),
[vecoutptr]"r"(&vecout),
[map]"r"(a)
: "memory", "r0", "r3", "r4", "r5", "r6", "r7");
if (aborted && (vecin != vecout)){
printf("FAILED: vector state leaked on abort %f != %f\n",
(double)vecin, (double)vecout);
exit(1);
}
munmap(a, size);
close(fd);
printf("PASSED!\n");
return 0;
}
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
TIF_PERFMON_WORK and TIF_PERFMON_CTXSW are completely unused. They
appear to be related to the old perfmon2 code, which has been
superseded by the perf_event infrastructure. This removes their
definitions so that the bits can be used for other purposes.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Huge Dickins reported an issue that b5ff4211a8
"powerpc/book3s: Queue up and process delayed MCE events" breaks the
PowerMac G5 boot. This patch fixes it by moving the mce even processing
away from syscall exit, which was wrong to do that in first place, and
using irq work framework to delay processing of mce event.
Reported-by: Hugh Dickins <hughd@google.com
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On POWER platforms, the hypervisor can notify the guest kernel about dynamic
changes in the cpu-numa associativity (VPHN topology update). Hence the
cpu-to-node mappings that we got from the firmware during boot, may no longer
be valid after such updates. This is handled using the arch_update_cpu_topology()
hook in the scheduler, and the sched-domains are rebuilt according to the new
mappings.
But unfortunately, at the moment, CPU hotplug ignores these updated mappings
and instead queries the firmware for the cpu-to-numa relationships and uses
them during CPU online. So the kernel can end up assigning wrong NUMA nodes
to CPUs during subsequent CPU hotplug online operations (after booting).
Further, a particularly problematic scenario can result from this bug:
On POWER platforms, the SMT mode can be switched between 1, 2, 4 (and even 8)
threads per core. The switch to Single-Threaded (ST) mode is performed by
offlining all except the first CPU thread in each core. Switching back to
SMT mode involves onlining those other threads back, in each core.
Now consider this scenario:
1. During boot, the kernel gets the cpu-to-node mappings from the firmware
and assigns the CPUs to NUMA nodes appropriately, during CPU online.
2. Later on, the hypervisor updates the cpu-to-node mappings dynamically and
communicates this update to the kernel. The kernel in turn updates its
cpu-to-node associations and rebuilds its sched domains. Everything is
fine so far.
3. Now, the user switches the machine from SMT to ST mode (say, by running
ppc64_cpu --smt=1). This involves offlining all except 1 thread in each
core.
4. The user then tries to switch back from ST to SMT mode (say, by running
ppc64_cpu --smt=4), and this involves onlining those threads back. Since
CPU hotplug ignores the new mappings, it queries the firmware and tries to
associate the newly onlined sibling threads to the old NUMA nodes. This
results in sibling threads within the same core getting associated with
different NUMA nodes, which is incorrect.
The scheduler's build-sched-domains code gets thoroughly confused with this
and enters an infinite loop and causes soft-lockups, as explained in detail
in commit 3be7db6ab (powerpc: VPHN topology change updates all siblings).
So to fix this, use the numa_cpu_lookup_table to remember the updated
cpu-to-node mappings, and use them during CPU hotplug online operations.
Further, we also need to ensure that all threads in a core are assigned to a
common NUMA node, irrespective of whether all those threads were online during
the topology update. To achieve this, we take care not to use cpu_sibling_mask()
since it is not hotplug invariant. Instead, we use cpu_first_sibling_thread()
and set up the mappings manually using the 'threads_per_core' value for that
particular platform. This helps us ensure that we don't hit this bug with any
combination of CPU hotplug and SMT mode switching.
Cc: stable@vger.kernel.org
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When EEH error comes to one specific PCI device before its driver
is loaded, we will apply hotplug to recover the error. During the
plug time, the PCI device will be probed and its driver is loaded.
Then we wrongly calls to the error handlers if the driver supports
EEH explicitly.
The patch intends to fix by introducing flag EEH_DEV_NO_HANDLER and
set it before we remove the PCI device. In turn, we can avoid wrongly
calls the error handlers of the PCI device after its driver loaded.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The patch implements the EEH operation backend restore_config()
for PowerNV platform. That relies on OPAL API opal_pci_reinit()
where we reinitialize the error reporting properly after PE or
PHB reset.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
After reset on the specific PE or PHB, we never configure AER
correctly on PowerNV platform. We needn't care it on pSeries
platform. The patch introduces additional EEH operation eeh_ops::
restore_config() so that we have chance to configure AER correctly
for PowerNV platform.
Signed-off-by: Gavin Shan <shangw@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
None of these files are actually using any __init type directives
and hence don't need to include <linux/init.h>. Most are just a
left over from __devinit and __cpuinit removal, or simply due to
code getting copied from one driver to the next.
The one instance where we add an include for init.h covers off
a case where that file was implicitly getting it from another
header which itself didn't need it.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On P1020, P1021, P1022, and P1023, eLBC event interrupts are routed
to internal interrupt 3 while ELBC error interrupts are routed to
internal interrupt 0. We need to call request_irq for each.
Signed-off-by: Shaohui Xie <Shaohui.Xie@freescale.com>
Signed-off-by: Wang Dongsheng <dongsheng.wang@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
[scottwood@freescale.com: reworded commit message and fixed author]
Signed-off-by: Scott Wood <scottwood@freescale.com>
There are a few things that make the existing hw tablewalk handlers
unsuitable for e6500:
- Indirect entries go in TLB1 (though the resulting direct entries go in
TLB0).
- It has threads, but no "tlbsrx." -- so we need a spinlock and
a normal "tlbsx". Because we need this lock, hardware tablewalk
is mandatory on e6500 unless we want to add spinlock+tlbsx to
the normal bolted TLB miss handler.
- TLB1 has no HES (nor next-victim hint) so we need software round robin
(TODO: integrate this round robin data with hugetlb/KVM)
- The existing tablewalk handlers map half of a page table at a time,
because IBM hardware has a fixed 1MiB indirect page size. e6500
has variable size indirect entries, with a minimum of 2MiB.
So we can't do the half-page indirect mapping, and even if we
could it would be less efficient than mapping the full page.
- Like on e5500, the linear mapping is bolted, so we don't need the
overhead of supporting nested tlb misses.
Note that hardware tablewalk does not work in rev1 of e6500.
We do not expect to support e6500 rev1 in mainline Linux.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Cc: Mihai Caraman <mihai.caraman@freescale.com>
This is used to get the address of a variable when the kernel is not
running at the linked or relocated address.
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
E6500 PVR and SPRN_PWRMGTCR0 will be used in subsequent pw20/altivec
idle patches.
Signed-off-by: Wang Dongsheng <dongsheng.wang@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
The e500 SPE floating-point emulation code clears existing exceptions
(__FPU_FPSCR &= ~FP_EX_MASK;) before ORing in the exceptions from the
emulated operation. However, these exception bits are the "sticky",
cumulative exception bits, and should only be cleared by the user
program setting SPEFSCR, not implicitly by any floating-point
instruction (whether executed purely by the hardware or emulated).
The spurious clearing of these bits shows up as missing exceptions in
glibc testing.
Fixing this, however, is not as simple as just not clearing the bits,
because while the bits may be from previous floating-point operations
(in which case they should not be cleared), the processor can also set
the sticky bits itself before the interrupt for an exception occurs,
and this can happen in cases when IEEE 754 semantics are that the
sticky bit should not be set. Specifically, the "invalid" sticky bit
is set in various cases with non-finite operands, where IEEE 754
semantics do not involve raising such an exception, and the
"underflow" sticky bit is set in cases of exact underflow, whereas
IEEE 754 semantics are that this flag is set only for inexact
underflow. Thus, for correct emulation the kernel needs to know the
setting of these two sticky bits before the instruction being
emulated.
When a floating-point operation raises an exception, the kernel can
note the state of the sticky bits immediately afterwards. Some
<fenv.h> functions that affect the state of these bits, such as
fesetenv and feholdexcept, need to use prctl with PR_GET_FPEXC and
PR_SET_FPEXC anyway, and so it is natural to record the state of those
bits during that call into the kernel and so avoid any need for a
separate call into the kernel to inform it of a change to those bits.
Thus, the interface I chose to use (in this patch and the glibc port)
is that one of those prctl calls must be made after any userspace
change to those sticky bits, other than through a floating-point
operation that traps into the kernel anyway. feclearexcept and
fesetexceptflag duly make those calls, which would not be required
were it not for this issue.
The previous EGLIBC port, and the uClibc code copied from it, is
fundamentally broken as regards any use of prctl for floating-point
exceptions because it didn't use the PR_FP_EXC_SW_ENABLE bit in its
prctl calls (and did various worse things, such as passing a pointer
when prctl expected an integer). If you avoid anything where prctl is
used, the clearing of sticky bits still means it will never give
anything approximating correct exception semantics with existing
kernels. I don't believe the patch makes things any worse for
existing code that doesn't try to inform the kernel of changes to
sticky bits - such code may get incorrect exceptions in some cases,
but it would have done so anyway in other cases.
Signed-off-by: Joseph Myers <joseph@codesourcery.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
LRAT (Logical to Real Address Translation) present in MMU v2 provides hardware
translation from a logical page number (LPN) to a real page number (RPN) when
tlbwe is executed by a guest or when a page table translation occurs from a
guest virtual address.
Add LRAT error exception handler to Booke3E 64-bit kernel and the basic KVM
handler to avoid build breakage. This is a prerequisite for KVM LRAT support
that will follow.
Signed-off-by: Mihai Caraman <mihai.caraman@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Merge a pile of fixes that went into the "merge" branch (3.13-rc's) such
as Anton Little Endian fixes.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch updates the generic iommu backend code to use the
it_page_shift field to determine the iommu page size instead of
using hardcoded values.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds a it_page_shift field to struct iommu_table and
initiliases it to 4K for all platforms.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The powerpc iommu uses a hardcoded page size of 4K. This patch changes
the name of the IOMMU_PAGE_* macros to reflect the hardcoded values. A
future patch will use the existing names to support dynamic page
sizes.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The generic put_unaligned/get_unaligned macros were made endian-safe by
calling the appropriate endian dependent macros based on the endian type
of the powerpc processor.
Signed-off-by: Rajesh B Prathipati <rprathip@linux.vnet.ibm.com>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
In EXCEPTION_PROLOG_COMMON() we check to see if the stack pointer (r1)
is valid when coming from the kernel. If it's not valid, we die but
with a nice oops message.
Currently we allocate a stack frame (subtract INT_FRAME_SIZE) before we
check to see if the stack pointer is negative. Unfortunately, this
won't detect a bad stack where r1 is less than INT_FRAME_SIZE.
This patch fixes the check to compare the modified r1 with
-INT_FRAME_SIZE. With this, bad kernel stack pointers (including NULL
pointers) are correctly detected again.
Kudos to Paulus for finding this.
Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: stable@vger.kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We are passing pointers to the firmware for reads, we need to properly
convert the result as OPAL is always BE.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
opal_xscom_read uses a pointer to return the data so we need
to byteswap it on LE builds.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
In pte_alloc_one(), pgtable_page_ctor() is passed an address that has
not been converted by page_address() to the newly allocated PTE page.
When the PTE is freed, __pte_free_tlb() calls pgtable_page_dtor()
with an address to the PTE page that has been converted by page_address().
The mismatch in the PTE's page address causes pgtable_page_dtor() to access
invalid memory, so resources for that PTE (such as the page lock) is not
properly cleaned up.
On PPC32, only SMP kernels are affected.
On PPC64, only SMP kernels with 4K page size are affected.
This bug was introduced by commit d614bb0412
"powerpc: Move the pte free routines from common header".
On a preempt-rt kernel, a spinlock is dynamically allocated for each
PTE in pgtable_page_ctor(). When the PTE is freed, calling
pgtable_page_dtor() with a mismatched page address causes a memory leak,
as the pointer to the PTE's spinlock is bogus.
On mainline, there isn't any immediately obvious symptoms, but the
problem still exists here.
Fixes: d614bb0412 "powerpc: Move the pte free routes from common header"
Cc: Paul Mackerras <paulus@samba.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: linux-stable <stable@vger.kernel.org> # v3.10+
Signed-off-by: Hong H. Pham <hong.pham@windriver.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Get the memory errors reported by opal and plumb it into memory poison
infrastructure. This patch uses new messaging channel infrastructure to
pull the fsp memory errors to linux.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We steal the _PAGE_COHERENCE bit and use that for indicating NUMA ptes.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Set memory coherence always on hash64 config. If
a platform cannot have memory coherence always set they
can infer that from _PAGE_NO_CACHE and _PAGE_WRITETHRU
like in lpar. So we dont' really need a separate bit
for tracking _PAGE_COHERENCE.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The only external user of slb_shadow is the pseries lpar code, and it
can access through the paca array instead.
Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
These accessors allow us to do cache inhibited accesses when in real
mode. They should only be used in real mode.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The current implementation of IOMMU on sPAPR does not use iommu_ops
and therefore does not call IOMMU API's bus_set_iommu() which
1) sets iommu_ops for a bus
2) registers a bus notifier
Instead, PCI devices are added to IOMMU groups from
subsys_initcall_sync(tce_iommu_init) which does basically the same
thing without using iommu_ops callbacks.
However Freescale PAMU driver (https://lkml.org/lkml/2013/7/1/158)
implements iommu_ops and when tce_iommu_init is called, every PCI device
is already added to some group so there is a conflict.
This patch does 2 things:
1. removes the loop in which PCI devices were added to groups and
adds explicit iommu_add_device() calls to add devices as soon as they get
the iommu_table pointer assigned to them.
2. moves a bus notifier to powernv code in order to avoid conflict with
the notifier from Freescale driver.
iommu_add_device() and iommu_del_device() are public now.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Move SG list and entry structure to header file so that
it can be used in other places as well.
Signed-off-by: Vasant Hegde <hegdevasant@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Opal now has a new messaging infrastructure to push the messages to
linux in a generic format for different type of messages using only one
event bit. The format of the opal message is as below:
struct opal_msg {
uint32_t msg_type;
uint32_t reserved;
uint64_t params[8];
};
This patch allows clients to subscribe for notification for specific
message type. It is upto the subscriber to decipher the messages who showed
interested in receiving specific message type.
The interface to subscribe for notification is:
int opal_message_notifier_register(enum OpalMessageType msg_type,
struct notifier_block *nb)
The notifier will fetch the opal message when available and notify the
subscriber with message type and the opal message. It is subscribers
responsibility to copy the message data before returning from notifier
callback.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Add basic error handling in machine check exception handler.
- If MSR_RI isn't set, we can not recover.
- Check if disposition set to OpalMCE_DISPOSITION_RECOVERED.
- Check if address at fault is inside kernel address space, if not then send
SIGBUS to process if we hit exception when in userspace.
- If address at fault is not provided then and if we get a synchronous machine
check while in userspace then kill the task.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When machine check real mode handler can not continue into host kernel
in V mode, it returns from the interrupt and we loose MCE event which
never gets logged. In such a situation queue up the MCE event so that
we can log it later when we get back into host kernel with r1 pointing to
kernel stack e.g. during syscall exit.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Now that we handle machine check in linux, the MCE decoding should also
take place in linux host. This info is crucial to log before we go down
in case we can not handle the machine check errors. This patch decodes
and populates a machine check event which contain high level meaning full
MCE information.
We do this in real mode C code with ME bit on. The MCE information is still
available on emergency stack (in pt_regs structure format). Even if we take
another exception at this point the MCE early handler will allocate a new
stack frame on top of current one. So when we return back here we still have
our MCE information safe on current stack.
We use per cpu buffer to save high level MCE information. Each per cpu buffer
is an array of machine check event structure indexed by per cpu counter
mce_nest_count. The mce_nest_count is incremented every time we enter
machine check early handler in real mode to get the current free slot
(index = mce_nest_count - 1). The mce_nest_count is decremented once the
MCE info is consumed by virtual mode machine exception handler.
This patch provides save_mce_event(), get_mce_event() and release_mce_event()
generic routines that can be used by machine check handlers to populate and
retrieve the event. The routine release_mce_event() will free the event slot so
that it can be reused. Caller can invoke get_mce_event() with a release flag
either to release the event slot immediately OR keep it so that it can be
fetched again. The event slot can be also released anytime by invoking
release_mce_event().
This patch also updates kvm code to invoke get_mce_event to retrieve generic
mce event rather than paca->opal_mce_evt.
The KVM code always calls get_mce_event() with release flags set to false so
that event is available for linus host machine
If machine check occurs while we are in guest, KVM tries to handle the error.
If KVM is able to handle MC error successfully, it enters the guest and
delivers the machine check to guest. If KVM is not able to handle MC error, it
exists the guest and passes the control to linux host machine check handler
which then logs MC event and decides how to handle it in linux host. In failure
case, KVM needs to make sure that the MC event is available for linux host to
consume. Hence KVM always calls get_mce_event() with release flags set to false
and later it invokes release_mce_event() only if it succeeds to handle error.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch handles the memory errors on power8. If we get a machine check
exception due to SLB or TLB errors, then flush SLBs/TLBs and reload SLBs to
recover.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
If we get a machine check exception due to SLB or TLB errors, then flush
SLBs/TLBs and reload SLBs to recover. We do this in real mode before turning
on MMU. Otherwise we would run into nested machine checks.
If we get a machine check when we are in guest, then just flush the
SLBs and continue. This patch handles errors for power7. The next
patch will handle errors for power8
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch introduces flush_tlb operation in cpu_spec structure. This will
help us to invoke appropriate CPU-side flush tlb routine. This patch
adds the foundation to invoke CPU specific flush routine for respective
architectures. Currently this patch introduce flush_tlb for p7 and p8.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds the early machine check function pointer in cputable for
CPU specific early machine check handling. The early machine handle routine
will be called in real mode to handle SLB and TLB errors. We can not reuse
the existing machine_check hook because it is always invoked in kernel
virtual mode and we would already be in trouble if we get SLB or TLB errors.
This patch just sets up a mechanism to invoke CPU specific handler. The
subsequent patches will populate the function pointer.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch introduces exclusive emergency stack for machine check exception.
We use emergency stack to handle machine check exception so that we can save
MCE information (srr1, srr0, dar and dsisr) before turning on ME bit and be
ready for re-entrancy. This helps us to prevent clobbering of MCE information
in case of nested machine checks.
The reason for using emergency stack over normal kernel stack is that the
machine check might occur in the middle of setting up a stack frame which may
result into improper use of kernel stack.
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch splits the common exception prolog logic into three parts to
facilitate reuse of existing code in the next patch. This patch also
re-arranges few instructions in such a way that the second part now deals
with saving register values from paca save area to stack frame, and
the third part deals with saving current register values to stack frame.
The second and third part will be reused in the machine check exception
routine in the subsequent patch.
Please note that this patch does not introduce or change existing code
logic. Instead it is just a code movement and instruction re-ordering.
Patch Acked-by Paul. But made some minor modification (explained above) to
address Paul's comment in the later patch(3).
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Current irq_stat.timers_irqs counting doesn't discriminate timer event handler
and other timer interrupt(like arch_irq_work_raise). Sometimes we need to know
exactly how much interrupts timer event handler fired, so let's be more specific
on this.
Signed-off-by: Fan Du <fan.du@windriver.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
As Benjamin Herrenschmidt has indicated, we still need a dummy icbi to
purge all the prefetched instructions from the ifetch buffers for the
snooping icache. We also need a sync before the icbi to order the
actual stores to memory that might have modified instructions with
the icbi.
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
So that it can be used by other codes. No function change.
Signed-off-by: Kevin Hao <haokexin@gmail.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When CONFIG_SPARSEMEM_VMEMMAP option is used in kernel, makedumpfile fails
to filter vmcore dump as it fails to do vmemmap translations. So far
dump filtering on ppc64 never had to deal with vmemmap addresses seperately
as vmemmap regions where mapped in zone normal. But with the inclusion of
CONFIG_SPARSEMEM_VMEMMAP config option in kernel, this vmemmap address
translation support becomes necessary for dump filtering. For vmemmap adress
translation, few kernel symbols are needed by dump filtering tool. This patch
adds those symbols to vmcoreinfo, which a dump filtering tool can use for
filtering the kernel dump. Tested this changes successfully with makedumpfile
tool that supports vmemmap to physical address translation outside zone normal.
[ Removed unneeded #ifdef as suggested by Michael Ellerman --BenH ]
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit beb2dc0a7a breaks the MPC8xx which
seems to not support using mfspr SPRN_TBRx instead of mftb/mftbu
despite what is written in the reference manual.
This patch reverts to the use of mftb/mftbu when CONFIG_8xx is
selected.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Pull third set of powerpc updates from Benjamin Herrenschmidt:
"This is a small collection of random bug fixes and a few improvements
of Oops output which I deemed valuable enough to include as well.
The fixes are essentially recent build breakage and regressions, and a
couple of older bugs such as the DTL log duplication, the EEH issue
with PCI_COMMAND_MASTER and the problem with small contexts passed to
get/set_context with VSX enabled"
* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc/signals: Mark VSX not saved with small contexts
powerpc/pseries: Fix SMP=n build of rng.c
powerpc: Make cpu_to_chip_id() available when SMP=n
powerpc/vio: Fix a dma_mask issue of vio
powerpc: booke: Fix build failures
powerpc: ppc64 address space capped at 32TB, mmap randomisation disabled
powerpc: Only print PACATMSCRATCH in oops when TM is active
powerpc/pseries: Duplicate dtl entries sometimes sent to userspace
powerpc: Remove a few lines of oops output
powerpc: Print DAR and DSISR on machine check oopses
powerpc: Fix __get_user_pages_fast() irq handling
powerpc/eeh: More accurate log
powerpc/eeh: Enable PCI_COMMAND_MASTER for PCI bridges
Up until now we have only used cpu_to_chip_id() in the topology code,
which is only used on SMP builds. However my recent commit a4da0d5
"Implement arch_get_random_long/int() for powernv" added a usage when
SMP=n, breaking the build.
Move cpu_to_chip_id() into prom.c so it is available for SMP=n builds.
We would move the extern to prom.h, but that breaks the include in
topology.h. Instead we leave it in smp.h, but move it out of the
CONFIG_SMP #ifdef. We also need to include asm/smp.h in rng.c, because
the linux version skips asm/smp.h on UP. What a mess.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Pull powerpc LE updates from Ben Herrenschmidt:
"With my previous pull request I mentioned some remaining Little Endian
patches, notably support for our new ABI, which I was sitting on
making sure it was all finalized.
The toolchain folks confirmed it now, the new ABI is stable and merged
with gcc, so we are all good. Oh and we actually missed the actual
Kconfig switch for LE so here it is, along with a couple more bug
fixes.
I have more fixes but not related to LE so I'll send them as a
separate pull request tomorrow, let's get this one out of the way.
Note that this supports running user space binaries using the new ABI,
but the kernel itself still needs to be built with the old one. We'll
bring fixes for that after -rc1.
Here's Anton log that goes with this series:
This patch series adds support for the new ABI, LPAR support for
H_SET_MODE and finally adds a kconfig option and defconfig.
ABIv2 support was recently committed to binutils and gcc, and should
be merged into glibc soon. There are a number of very nice
improvements including the removal of function descriptors. Rusty's
kernel patches allow binaries of either ABI to work, easing the
transition"
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
powerpc: Wrong DWARF CFI in the kernel vdso for little-endian / ELFv2
powerpc: Add pseries_le_defconfig
powerpc: Add CONFIG_CPU_LITTLE_ENDIAN kernel config option.
powerpc: Don't use ELFv2 ABI to build the kernel
powerpc: ELF2 binaries signal handling
powerpc: ELF2 binaries launched directly.
powerpc: Set eflags correctly for ELF ABIv2 core dumps.
powerpc: Add TIF_ELF2ABI flag.
pseries: Add H_SET_MODE to change exception endianness
powerpc/pseries: Fix endian issues in pseries EEH code
Gavin Shan