On some targets, _PAGE_RW is 0 and this is _PAGE_RO which is used.
There is also _PAGE_SHARED that is missing.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc expects IRQs to already be (soft) disabled when switch_mm() is
called, as made clear in the commit message of 9c1e105238 ("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
f98db6013c ("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 04b96e5528 ("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>
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.
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>
Allow kprobes to be placed on ftrace _mcount() call sites. This optimization
avoids the use of a trap, by riding on ftrace infrastructure.
This depends on HAVE_DYNAMIC_FTRACE_WITH_REGS which depends on MPROFILE_KERNEL,
which is only currently enabled on powerpc64le with newer toolchains.
Based on the x86 code by Masami.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Blacklist all the exception common/OOL handlers as the kernel stack is not yet
setup, which means we can't take a trap at this point.
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>
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>
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>
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>
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.
cpu 0x0: Vector: e40 (Emulation Assist) at [c0000000008f3810]
pc: c000000000008380: machine_check_handle_early+0x130/0x2f0
lr: c00000000053a098: stop_loop+0x68/0xd0
sp: c0000000008f3a90
msr: 9000000000081001
current = 0xc0000000008a1080
paca = 0xc00000000ffd0000 softe: 0 irq_happened: 0x01
pid = 0, comm = swapper/0
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>
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>
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>
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>
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>
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>
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: 7dccfbc325 ("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>
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>
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>
The LDST field and DATA_SRC in SIER identifies the memory hierarchy level
(eg: L1, L2 etc), from which a data-cache miss for a marked instruction
was satisfied. Use the 'perf_mem_data_src' object to export this
hierarchy level to user space.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently powerpc's asm/io.h includes linux/io.h, and linux/io.h
includes asm/io.h.
This can cause problems because depending on which is included first the
order of definitions between the two files will change.
The include of linux/io.h was added back in 2008 in commit b41e5fffe8
("[POWERPC] devres: Add devm_ioremap_prot()"). It's not entirely clear
it was needed then, but devm_ioremap_prot() has since been removed
entirely as unused, in dedd24a12f ("powerpc: Remove unused
devm_ioremap_prot()").
So it seems to be unnecessary and can potentially cause problems, so
remove the include of linux/io.h from asm/io.h
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
POWER9 requires msgsync for receiver-side synchronization, and a DD1
workaround restricts IPIs to core-local.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Drop no longer needed asm feature macro changes]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
IPIs are a pretty hot path and we already have the ability to do asm feature
patching, so use it.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Change log detail]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
POWER9 changes requirements and adds new instructions for
synchronization.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Change the doorbell callers to know about their msgsnd addressing,
rather than have them set a per-cpu target data tag at boot that gets
sent to the cause_ipi functions. The data is only used for doorbell IPI
functions, no other IPI types, so it makes sense to keep that detail
local to doorbell.
Have the platform code understand doorbell IPIs, rather than the
interrupt controller code understand them. Platform code can look at
capabilities it has available and decide which to use.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add the bit definition and use it in facility_unavailable_exception() so we can
intelligently report the cause if we take a fault for SCV. This doesn't actually
enable SCV.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Drop whitespace changes to the existing entries, flush out change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently sys_mmap() and sys_mmap2() (32-bit only), are not visible to the
syscall tracing machinery. This means users are not able to see the execution of
mmap() syscalls using the syscall tracer.
Fix that by using SYSCALL_DEFINE6 for sys_mmap() and sys_mmap2() so that the
meta-data associated with these syscalls is visible to the syscall tracer.
A side-effect of this change is that the return type has changed from unsigned
long to long. However this should have no effect, the only code in the kernel
which uses the result of these syscalls is in the syscall return path, which is
written in asm and treats the result as unsigned regardless.
Example output:
cat-3399 [001] .... 196.542410: sys_mmap(addr: 7fff922a0000, len: 20000, prot: 3, flags: 812, fd: 3, offset: 1b0000)
cat-3399 [001] .... 196.542443: sys_mmap -> 0x7fff922a0000
cat-3399 [001] .... 196.542668: sys_munmap(addr: 7fff922c0000, len: 6d2c)
cat-3399 [001] .... 196.542677: sys_munmap -> 0x0
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[mpe: Massage change log, add detail on return type change]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Recently in commit f6eedbba7a ("powerpc/mm/hash: Increase VA range to 128TB"),
we increased H_PGD_INDEX_SIZE to 15 when we're building with 64K pages. This
makes it larger than RADIX_PGD_INDEX_SIZE (13), which means the logic to
calculate MAX_PGD_INDEX_SIZE in book3s/64/pgtable.h is wrong.
The end result is that the PGD (Page Global Directory, ie top level page table)
of the kernel (aka. swapper_pg_dir), is too small.
This generally doesn't lead to a crash, as we don't use the full range in normal
operation. However if we try to dump the kernel pagetables we can trigger a
crash because we walk off the end of the pgd into other memory and eventually
try to dereference something bogus:
$ cat /sys/kernel/debug/kernel_pagetables
Unable to handle kernel paging request for data at address 0xe8fece0000000000
Faulting instruction address: 0xc000000000072314
cpu 0xc: Vector: 380 (Data SLB Access) at [c0000000daa13890]
pc: c000000000072314: ptdump_show+0x164/0x430
lr: c000000000072550: ptdump_show+0x3a0/0x430
dar: e802cf0000000000
seq_read+0xf8/0x560
full_proxy_read+0x84/0xc0
__vfs_read+0x6c/0x1d0
vfs_read+0xbc/0x1b0
SyS_read+0x6c/0x110
system_call+0x38/0xfc
The root cause is that MAX_PGD_INDEX_SIZE isn't actually computed to be
the max of H_PGD_INDEX_SIZE or RADIX_PGD_INDEX_SIZE. To fix that move
the calculation into asm-offsets.c where we can do it easily using
max().
Fixes: f6eedbba7a ("powerpc/mm/hash: Increase VA range to 128TB")
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This merges the arch part of the XIVE support, leaving the final commit
with the KVM specific pieces dangling on the branch for Paul to merge
via the kvm-ppc tree.
POWER9 DD1.0 hardware has a bug where the SPRs of a thread waking up
from stop 0,1,2 with ESL=1 can endup being misplaced in the core. Thus
the HSPRG0 of a thread waking up from can contain the paca pointer of
its sibling.
This patch implements a context recovery framework within threads of a
core, by provisioning space in paca_struct for saving every sibling
threads's paca pointers. Basically, we should be able to arrive at the
right paca pointer from any of the thread's existing paca pointer.
At bootup, during powernv idle-init, we save the paca address of every
CPU in each one its siblings paca_struct in the slot corresponding to
this CPU's index in the core.
On wakeup from a stop, the thread will determine its index in the core
from the TIR register and recover its PACA pointer by indexing into
the correct slot in the provisioned space in the current PACA.
Furthermore, ensure that the NVGPRs are restored from the stack on the
way out by setting the NAPSTATELOST in paca.
[Changelog written with inputs from svaidy@linux.vnet.ibm.com]
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Call it a bug]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Move the piece of code in powernv/smp.c::pnv_smp_cpu_kill_self() which
transitions the CPU to the deepest available platform idle state to a
new function named pnv_cpu_offline() in powernv/idle.c. The rationale
behind this code movement is that the data required to determine the
deepest available platform state resides in powernv/idle.c.
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add user space exported API definitions for 512KB, 1MB, 2MB, 8MB, 16MB,
1GB, 16GB non default huge page sizes to be used with mmap() system
call.
Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
[mpe: Reword the comment to emphasise that these are only needed to use
the non-default huge page size, and updated the change log.]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
powerpc_debugfs_root is the dentry representing the root of the
"powerpc" directory tree in debugfs.
Currently it sits in asm/debug.h, a long with some other things that
have "debug" in the name, but are otherwise unrelated.
Pull it out into a separate header, which also includes linux/debugfs.h,
and convert all the users to include debugfs.h instead of debug.h.
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We need to set LPES in order for normal external interrupts (0x500)
to be directed to the guest while running in guest state.
We also need HEIC set to prevent them to be sent to the host while
in host state.
With XIVE the host never gets one of these and wouldn't know how to
handle it. All host external interrupts come in via the new
hypervisor virtualization interrupts vector.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We have all sort of variants of MMIO accessors for the real mode
instructions. This creates a clean set of accessors based on
Linux normal naming conventions, replacing all occurrences of
the old ones in the tree.
I have purposefully removed the "out/in" variants in favor of
only including __raw variants. Any code using these is already
pretty much hand tuned to operate in a very specific environment.
I've fixed up the 2 users (only one of them actually needed
a barrier in the first place).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The function doesn't exist anymore
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
It's only used within the same file it's defined
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The XIVE interrupt controller is the new interrupt controller
found in POWER9. It supports advanced virtualization capabilities
among other things.
Currently we use a set of firmware calls that simulate the old
"XICS" interrupt controller but this is fairly inefficient.
This adds the framework for using XIVE along with a native
backend which OPAL for configuration. Later, a backend allowing
the use in a KVM or PowerVM guest will also be provided.
This disables some fast path for interrupts in KVM when XIVE is
enabled as these rely on the firmware emulation code which is no
longer available when the XIVE is used natively by Linux.
A latter patch will make KVM also directly exploit the XIVE, thus
recovering the lost performance (and more).
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
[mpe: Fixup pr_xxx("XIVE:"...), don't split pr_xxx() strings,
tweak Kconfig so XIVE_NATIVE selects XIVE and depends on POWERNV,
fix build errors when SMP=n, fold in fixes from Ben:
Don't call cpu_online() on an invalid CPU number
Fix irq target selection returning out of bounds cpu#
Extra sanity checks on cpu numbers
]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Some powerpc platforms use this to move IRQs away from a CPU being
unplugged. This function has several bugs such as not taking the right
locks or failing to NULL check pointers.
There's a new generic function doing exactly the same thing without all
the bugs, so let's use it instead.
mpe: The obvious place for the select of GENERIC_IRQ_MIGRATION is on
HOTPLUG_CPU, but that doesn't work. On some configs PM_SLEEP_SMP will
select HOTPLUG_CPU even though its dependencies are not met, which means
the select of GENERIC_IRQ_MIGRATION doesn't happen. That leads to the
build breaking. Fix it by moving the select of GENERIC_IRQ_MIGRATION to
SMP.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Some platforms (will) need to perform allocations before bringing
a new CPU online. Doing it from smp_ops->setup_cpu is the wrong
thing to do:
- It has no useful failure path (too late)
- Calling any allocator will enable interrupts prematurely
causing problems with large decrementer among others
Instead, add a new callback that is called from __cpu_up (so from
the context trying to online the new CPU) at a point where we
can safely allocate and handle failures.
This will be used by XIVE support.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Nvlink2 supports address translation services (ATS) allowing devices
to request address translations from an mmu known as the nest MMU
which is setup to walk the CPU page tables.
To access this functionality certain firmware calls are required to
setup and manage hardware context tables in the nvlink processing unit
(NPU). The NPU also manages forwarding of TLB invalidates (known as
address translation shootdowns/ATSDs) to attached devices.
This patch exports several methods to allow device drivers to register
a process id (PASID/PID) in the hardware tables and to receive
notification of when a device should stop issuing address translation
requests (ATRs). It also adds a fault handler to allow device drivers
to demand fault pages in.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
[mpe: Fix up comment formatting, use flush_tlb_mm()]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
For an MCE (Machine Check Exception) that hits while in user mode
MSR(PR=1), print the task info to the console MCE error log. This may
help to identify an application that triggered the MCE.
After this patch the MCE console looks like:
Severe Machine check interrupt [Recovered]
NIP: [0000000010039778] PID: 762 Comm: ebizzy
Initiator: CPU
Error type: SLB [Multihit]
Effective address: 0000000010039778
Severe Machine check interrupt [Not recovered]
NIP: [0000000010039778] PID: 763 Comm: ebizzy
Initiator: CPU
Error type: UE [Page table walk ifetch]
Effective address: 0000000010039778
ebizzy[763]: unhandled signal 7 at 0000000010039778 nip 0000000010039778 lr 0000000010001b44 code 30004
Signed-off-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Not all user space application is ready to handle wide addresses. It's
known that at least some JIT compilers use higher bits in pointers to
encode their information. It collides with valid pointers with 512TB
addresses and leads to crashes.
To mitigate this, we are not going to allocate virtual address space
above 128TB by default.
But userspace can ask for allocation from full address space by
specifying hint address (with or without MAP_FIXED) above 128TB.
If hint address set above 128TB, but MAP_FIXED is not specified, we try
to look for unmapped area by specified address. If it's already
occupied, we look for unmapped area in *full* address space, rather than
from 128TB window.
This approach helps to easily make application's memory allocator aware
about large address space without manually tracking allocated virtual
address space.
This is going to be a per mmap decision. ie, we can have some mmaps with
larger addresses and other that do not.
A sample memory layout looks like:
10000000-10010000 r-xp 00000000 fc:00 9057045 /home/max_addr_512TB
10010000-10020000 r--p 00000000 fc:00 9057045 /home/max_addr_512TB
10020000-10030000 rw-p 00010000 fc:00 9057045 /home/max_addr_512TB
10029630000-10029660000 rw-p 00000000 00:00 0 [heap]
7fff834a0000-7fff834b0000 rw-p 00000000 00:00 0
7fff834b0000-7fff83670000 r-xp 00000000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so
7fff83670000-7fff83680000 r--p 001b0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so
7fff83680000-7fff83690000 rw-p 001c0000 fc:00 9177190 /lib/powerpc64le-linux-gnu/libc-2.23.so
7fff83690000-7fff836a0000 rw-p 00000000 00:00 0
7fff836a0000-7fff836c0000 r-xp 00000000 00:00 0 [vdso]
7fff836c0000-7fff83700000 r-xp 00000000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so
7fff83700000-7fff83710000 r--p 00030000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so
7fff83710000-7fff83720000 rw-p 00040000 fc:00 9177193 /lib/powerpc64le-linux-gnu/ld-2.23.so
7fffdccf0000-7fffdcd20000 rw-p 00000000 00:00 0 [stack]
1000000000000-1000000010000 rw-p 00000000 00:00 0
1ffff83710000-1ffff83720000 rw-p 00000000 00:00 0
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Now that we use all the available virtual address range, we need to make
sure we don't generate VSID such that it overlaps with the reserved vsid
range. Reserved vsid range include the virtual address range used by the
adjunct partition and also the VRMA virtual segment. We find the context
value that can result in generating such a VSID and reserve it early in
boot.
We don't look at the adjunct range, because for now we disable the
adjunct usage in a Linux LPAR via CAS interface.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Rewrite hash__reserve_context_id(), move the rest into pseries]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We optmize the slice page size array copy to paca by copying only the
range based on addr_limit. This will require us to not look at page size
array beyond addr_limit in PACA on slb fault. To enable that copy task
size to paca which will be used during slb fault.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
[mpe: Rename from task_size to addr_limit, consolidate #ifdefs]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In the followup patch, we will increase the slice array size to handle
512TB range, but will limit the max addr to 128TB. Avoid doing
unnecessary computation and avoid doing slice mask related operation
above address limit.
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We update the hash linux page table layout such that we can support
512TB. But we limit the TASK_SIZE to 128TB. We can switch to 128TB by
default without conditional because that is the max virtual address
supported by other architectures. We will later add a mechanism to
on-demand increase the application's effective address range to 512TB.
Having the page table layout changed to accommodate 512TB makes testing
large memory configuration easier with less code changes to kernel
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This doesn't have any functional change. But helps in avoiding mistakes
in case the shift bit changes
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
