Implement the architecture specific portitions of the UACCESS_FLUSHCACHE
API. This provides functions for the copy_user_flushcache iterator that
ensure that when the copy is finished the destination buffer contains
a copy of the original and that the destination buffer is clean in the
processor caches.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Implement the architecture specific cache maintence functions that make
up the "PMEM API". Currently the writeback and invalidate functions
are the same since the function of the DCBST (data cache block store)
instruction is typically interpreted as "writeback to the point of
coherency" rather than to memory. As a result implementing the API
requires a full cache flush rather than just a cache write back. This
will probably change in the not-too-distant future.
Signed-off-by: Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The nest mmu required an explicit flush as a tlbi would not flush it in the
same way as the core. However an alternate firmware fix exists which should
eliminate the need for this flush, so instead add a device-tree property
(ibm,nmmu-flush) on the NVLink2 PHB to enable it only if required.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
Reviewed-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
With the optimisations introduced by commit a46cc7a908 ("powerpc/mm/radix:
Improve TLB/PWC flushes"), flush_tlb_mm() no longer flushes the page walk
cache with radix. Switch to using flush_all_mm() to ensure the pwc and tlb
are properly flushed on the nmmu.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
On PowerNV platforms, firmware provides exit latency and
target residency for each of the idle states in nano
seconds. Cpuidle framework expects the values in micro
seconds. Round up to nearest micro seconds to avoid errors
in cases where the values are defined as fractional micro
seconds.
Default idle state of 'snooze' has exit latency of zero. If
other states have fractional micro second exit latency, they
would get rounded down to zero micro second and make cpuidle
framework choose deeper idle state when snooze loop is the
right choice.
Reported-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Reviewed-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Use safer string manipulation functions when dealing with a
user-provided string in kprobe_lookup_name().
Reported-by: David Laight <David.Laight@ACULAB.COM>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Commit 3cdfcbfd32 ("powerpc: Change analyse_instr so it doesn't
modify *regs") introduced emulate_update_regs() to perform part of what
emulate_step() was doing earlier. However, this function was not added
to the kprobes blacklist. Add it so as to prevent it from being probed.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Per Documentation/kprobes.txt, we don't necessarily need to disable
interrupts before invoking the kprobe handlers. Masami submitted
similar changes for x86 via commit a19b2e3d78 ("kprobes/x86: Remove
IRQ disabling from ftrace-based/optimized kprobes"). Do the same for
powerpc.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Per Documentation/kprobes.txt, probe handlers need to be invoked with
preemption disabled. Update optimized_callback() to do so. Also move
get_kprobe_ctlblk() invocation post preemption disable, since it
accesses pre-cpu data.
This was not an issue so far since optprobes wasn't selected if
CONFIG_PREEMPT was enabled. Commit a30b85df7d ("kprobes: Use
synchronize_rcu_tasks() for optprobe with CONFIG_PREEMPT=y") changes
this.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Masami Hiramatsu <mhiramat@kernel.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Commit 78adf6c214 ("powerpc/64s: Implement system reset idle wakeup
reason"), added a call to ppc_save_regs() in the book3s code.
ppc_save_regs() is only built if XMON and/or KEXEC_CORE are enabled,
which is usually the case, however if they're not enabled then the
build breaks.
Fix it by making the Makefile check also build ppc_save_regs.o if
CONFIG_PPC_BOOK3S is enabled.
Fixes: 78adf6c214 ("powerpc/64s: Implement system reset idle wakeup reason")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
[mpe: Write change log]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
When using the radix MMU on Power9 DD1, to work around a hardware
problem, radix__pte_update() is required to do a two stage update of
the PTE. First we write a zero value into the PTE, then we flush the
TLB, and then we write the new PTE value.
In the normal case that works OK, but it does not work if we're
updating the PTE that maps the code we're executing, because the
mapping is removed by the TLB flush and we can no longer execute from
it. Unfortunately the STRICT_RWX code needs to do exactly that.
The exact symptoms when we hit this case vary, sometimes we print an
oops and then get stuck after that, but I've also seen a machine just
get stuck continually page faulting with no oops printed. The variance
is presumably due to the exact layout of the text and the page size
used for the mappings. In all cases we are unable to boot to a shell.
There are possible solutions such as creating a second mapping of the
TLB flush code, executing from that, and then jumping back to the
original. However we don't want to add that level of complexity for a
DD1 work around.
So just detect that we're running on Power9 DD1 and refrain from
changing the permissions, effectively disabling STRICT_RWX on Power9
DD1.
Fixes: 7614ff3272 ("powerpc/mm/radix: Implement STRICT_RWX/mark_rodata_ro() for Radix")
Cc: stable@vger.kernel.org # v4.13+
Reported-by: Andrew Jeffery <andrew@aj.id.au>
[Changelog as suggested by Michael Ellerman <mpe@ellerman.id.au>]
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We are using percpu send window on P9 NX (powerNV) instead of opening
/ closing per each crypto session. Means txwin is removed from
workmem. So we do not need to initialize workmem for each request.
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
For P9 NX, the send window is opened for each crypto session and
closed upon free. But VAS supports 64K windows per chip for all
coprocessors including in user space support. So there is a
possibility of not getting the window for kernel requests.
This patch reserves windows for each coprocessor type (NX842) and are
available forever for kernel requests, Opens each window for each CPU
on the corresponding chip during driver initialization. So then use
the percpu txwin for NX requests depends on the CPU on which the
process is executing.
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Add support for user space receive window (for the Fast thread-wakeup
coprocessor type)
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Define an interface to return a system-wide unique id for a given VAS
window.
The vas_win_id() will be used in a follow-on patch to generate an unique
handle for a user space receive window. Applications can use this handle
to pair send and receive windows for fast thread-wakeup.
The hardware refers to this system-wide unique id as a Partition Send
Window ID which is expected to be used during fault handling. Hence the
"pswid" in the function names.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Define an interface that the NX drivers can use to find the physical
paste address of a send window. This interface is expected to be used
with the mmap() operation of the NX driver's device. i.e the user space
process can use driver's mmap() operation to map the send window's paste
address into their address space and then use copy and paste instructions
to submit the CRBs to the NX engine.
Note that kernel drivers will use vas_paste_crb() directly and don't need
this interface.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
A CP_ABORT instruction is required in processes that have mapped a VAS
"paste address" with the intention of using COPY/PASTE instructions.
But since CP_ABORT is expensive, we want to restrict it to only
processes that use/intend to use COPY/PASTE.
Define an interface, set_thread_uses_vas(), that VAS can use to
indicate that the current process opened a send window. During context
switch, issue CP_ABORT only for processes that have the flag set.
Thanks for input from Nick Piggin, Michael Ellerman.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
[mpe: Fix to not use new_thread after _switch() returns]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We need the SPRN_TIDR to be set for use with fast thread-wakeup (core-
to-core wakeup) and also with CAPI.
Each thread in a process needs to have a unique id within the process.
But for now, we assign globally unique thread ids to all threads in
the system.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
Signed-off-by: Christophe Lombard <clombard@linux.vnet.ibm.com>
[mpe: Simplify tidr clearing on fork() and ctx switch code]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Export the VAS Window context information to debugfs.
We need to hold a mutex when closing the window to prevent a race
with the debugfs read(). Rather than introduce a per-instance mutex,
we use the global vas_mutex for now, since it is not heavily contended.
The window->cop field is only relevant to a receive window so we were
not setting it for a send window (which is is paired to a receive window
anyway). But to simplify reporting in debugfs, set the 'cop' field for the
send window also.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Define a helper, chip_to_vas_id() to map a given chip id to corresponding
vas id.
Normally, callers of vas_rx_win_open() and vas_tx_win_open() want the VAS
window to be on the same chip where the calling thread is executing. These
callers can pass in -1 for the VAS id.
This interface will be useful if a thread running on one chip wants to open
a window on another chip (like the NX-842 driver does during start up).
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Create a cpu to vasid mapping so callers can specify -1 instead of
trying to find a VAS id.
Changelog[v2]
[Michael Ellerman] Use per-cpu variables to simplify code.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Normally, the NX driver waits for the CRBs to be processed before closing
the window. But it is better to ensure that the credits are returned before
the window gets reassigned later.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Save the configured max window credits for a window in the vas_window
structure. We will need this when polling for return of window credits.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
A VAS window is normally in "busy" state for only a short duration.
Reduce the time we wait for the window to go to "not-busy" state to
speed-up vas_win_close() a bit.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Use a helper to have the hardware unpin and mark a window closed.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Polling for window cast out is listed in the spec, but turns out that
it is not strictly necessary and slows down window close. Making it a
stub for now.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Clean up vas.h and the debug code around ifdef vas_debug.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
NX-842, the only user of VAS, sets the window credits to default values
but VAS should check the credits against the possible max values.
The VAS_WCREDS_MIN is not needed and can be dropped.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Initialize a few missing window context fields from the window attributes
specified by the caller. These fields are currently set to their default
values by the caller (NX-842), but would be good to apply them anyway.
Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Take the DSCR value set by firmware as the dscr_default value,
rather than zero.
POWER9 recommends DSCR default to a non-zero value.
Signed-off-by: From: Nicholas Piggin <npiggin@gmail.com>
[mpe: Make record_spr_defaults() __init]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
OPAL boot does not insert secondaries at 0x60 to wait at the secondary
hold spinloop. Instead they are started later, and inserted at
generic_secondary_smp_init(), which is after the secondary hold
spinloop.
Avoid waiting on this spinloop when booting with OPAL firmware. This
wait always times out that case.
This saves 100ms boot time on powernv, and 10s of seconds of real time
when booting on the simulator in SMP.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Unmaps that free page tables always flush the entire PID, which is
sub-optimal. Provide TLB range flushing with an additional PWC flush
that can be use for va range invalidations with PWC flush.
Time to munmap N pages of memory including last level page table
teardown (after mmap, touch), local invalidate:
N 1 2 4 8 16 32 64
vanilla 3.2us 3.3us 3.4us 3.6us 4.1us 5.2us 7.2us
patched 1.4us 1.5us 1.7us 1.9us 2.6us 3.7us 6.2us
Global invalidate:
N 1 2 4 8 16 32 64
vanilla 2.2us 2.3us 2.4us 2.6us 3.2us 4.1us 6.2us
patched 2.1us 2.5us 3.4us 5.2us 8.7us 15.7us 6.2us
Local invalidates get much better across the board. Global ones have
the same issue where multiple tlbies for va flush do get slower than
the single tlbie to invalidate the PID. None of this test captures
the TLB benefits of avoiding killing everything.
Global gets worse, but it is brought in to line with global invalidate
for munmap()s that do not free page tables.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The single page flush ceiling is the cut-off point at which we switch
from invalidating individual pages, to invalidating the entire process
address space in response to a range flush.
Introduce a local variant of this heuristic because local and global
tlbie have significantly different properties:
- Local tlbiel requires 128 instructions to invalidate a PID, global
tlbie only 1 instruction.
- Global tlbie instructions are expensive broadcast operations.
The local ceiling has been made much higher, 2x the number of
instructions required to invalidate the entire PID (i.e., 256 pages).
Time to mprotect N pages of memory (after mmap, touch), local invalidate:
N 32 34 64 128 256 512
vanilla 7.4us 9.0us 14.6us 26.4us 50.2us 98.3us
patched 7.4us 7.8us 13.8us 26.4us 51.9us 98.3us
The behaviour of both is identical at N=32 and N=512. Between there,
the vanilla kernel does a PID invalidate and the patched kernel does
a va range invalidate.
At N=128, these require the same number of tlbiel instructions, so
the patched version can be sen to be cheaper when < 128, and more
expensive when > 128. However this does not well capture the cost
of invalidated TLB.
The additional cost at 256 pages does not seem prohibitive. It may
be the case that increasing the limit further would continue to be
beneficial to avoid invalidating all of the process's TLB entries.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Currently for radix, flush_tlb_range flushes the entire PID, because
the Linux mm code does not tell us about page size here for THP vs
regular pages. This is quite sub-optimal for small mremap / mprotect
/ change_protection.
So implement va range flushes with two flush passes, one for each
page size (regular and THP). The second flush has an order of matnitude
fewer tlbie instructions than the first, so it is a relatively small
additional cost.
There is still room for improvement here with some changes to generic
APIs, particularly if there are mostly THP pages to be invalidated,
the small page flushes could be reduced.
Time to mprotect 1 page of memory (after mmap, touch):
vanilla 2.9us 1.8us
patched 1.2us 1.6us
Time to mprotect 30 pages of memory (after mmap, touch):
vanilla 8.2us 7.2us
patched 6.9us 17.9us
Time to mprotect 34 pages of memory (after mmap, touch):
vanilla 9.1us 8.0us
patched 9.0us 8.0us
34 pages is the point at which the invalidation switches from va
to entire PID, which tlbie can do in a single instruction. This is
why in the case of 30 pages, the new code runs slower for this test.
This is a deliberate tradeoff already present in the unmap and THP
promotion code, the idea is that the benefit from avoiding flushing
entire TLB for this PID on all threads in the system.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Move the barriers and range iteration down into the _tlbie* level,
which improves readability.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Short range flushes issue a sequences of tlbie(l) instructions for
individual effective addresses. These do not all require individual
barrier sequences, only one covering all tlbie(l) instructions.
Commit f7327e0ba3 ("powerpc/mm/radix: Remove unnecessary ptesync")
made a similar optimization for tlbiel for PID flushing.
For tlbie, the ISA says:
The tlbsync instruction provides an ordering function for the
effects of all tlbie instructions executed by the thread executing
the tlbsync instruction, with respect to the memory barrier
created by a subsequent ptesync instruction executed by the same
thread.
Time to munmap 30 pages of memory (after mmap, touch):
local global
vanilla 10.9us 22.3us
patched 3.4us 14.4us
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
We have some dependencies & conflicts between patches in fixes and
things to go in next, both in the radix TLB flush code and the IMC PMU
driver. So merge fixes into next.
Add a self test to check if FP/VEC/VSX registers are sane (restored
correctly) after a FP/VEC/VSX unavailable exception is caught during a
transaction.
This test checks all possibilities in a thread regarding the combination
of MSR.[FP|VEC] states in a thread and for each scenario raises a
FP/VEC/VSX unavailable exception in transactional state, verifying if
vs0 and vs32 registers, which are representatives of FP/VEC/VSX reg
sets, are not corrupted.
Signed-off-by: Gustavo Romero <gromero@linux.vnet.ibm.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
It would be nice to be able to dump page tables in a particular
context.
eg: dumping vmalloc space:
0:mon> dv 0xd00037fffff00000
pgd @ 0xc0000000017c0000
pgdp @ 0xc0000000017c00d8 = 0x00000000f10b1000
pudp @ 0xc0000000f10b13f8 = 0x00000000f10d0000
pmdp @ 0xc0000000f10d1ff8 = 0x00000000f1102000
ptep @ 0xc0000000f1102780 = 0xc0000000f1ba018e
Maps physical address = 0x00000000f1ba0000
Flags = Accessed Dirty Read Write
This patch does not replicate the complex code of dump_pagetable and
has no support for bolted linear mapping, thats why I've it's called
dump virtual page table support. The format of the PTE can be expanded
even further to add more useful information about the flags in the PTE
if required.
Signed-off-by: Balbir Singh <bsingharora@gmail.com>
[mpe: Bike shed the output format, show the pgdir, fix build failures]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
In commit e6f81a9201 ("powerpc/mm/hash: Support 68 bit VA") the
masking is folded into ASM_VSID_SCRAMBLE but the comment about masking
is removed only from the firt use of ASM_VSID_SCRAMBLE.
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
DMA windows can only have a size of power of two on IODA2 hardware and
using memory_hotplug_max() to determine the upper limit won't work
correcly if it returns not power of two value.
This removes the check as the platform code does this check in
pnv_pci_ioda2_setup_default_config() anyway; the other client is VFIO
and that thing checks against locked_vm limit which prevents the userspace
from locking too much memory.
It is expected to impact DPDK on machines with non-power-of-two RAM size,
mostly. KVM guests are less likely to be affected as usually guests get
less than half of hosts RAM.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The call to /proc/cpuinfo in turn calls cpufreq_quick_get() which
returns the last frequency requested by the kernel, but may not
reflect the actual frequency the processor is running at. This patch
makes a call to cpufreq_get() instead which returns the current
frequency reported by the hardware.
Fixes: fb5153d05a ("powerpc: powernv: Implement ppc_md.get_proc_freq()")
Signed-off-by: Shriya <shriyak@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
DD2.1 does not have to save MMCR0 for all state-loss idle states,
only after deep idle states (like other PMU registers).
Reviewed-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
DD2.1 does not have to flush the ERAT after a state-loss idle.
Performance testing was done on a DD2.1 using only the stop0 idle state
(the shallowest state which supports state loss), using context_switch
selftest configured to ping-poing between two threads on the same core
and two different cores.
Performance improvement for same core is 7.0%, different cores is 14.8%.
Reviewed-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
After handling a transactional FP, Altivec or VSX unavailable exception.
The return to userspace code will detect that the TIF_RESTORE_TM bit is
set and call restore_tm_state(). restore_tm_state() will call
restore_math() to ensure that the correct facilities are loaded.
This means that all the loadup code in {fp,altivec,vsx}_unavailable_tm()
is doing pointless work and can simply be removed.
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Lazy save and restore of FP/Altivec means that a userspace process can
be sent to userspace with FP or Altivec disabled and loaded only as
required (by way of an FP/Altivec unavailable exception). Transactional
Memory complicates this situation as a transaction could be started
without FP/Altivec being loaded up. This causes the hardware to
checkpoint incorrect registers. Handling FP/Altivec unavailable
exceptions while a thread is transactional requires a reclaim and
recheckpoint to ensure the CPU has correct state for both sets of
registers.
tm_reclaim() has optimisations to not always save the FP/Altivec
registers to the checkpointed save area. This was originally done
because the caller might have information that the checkpointed
registers aren't valid due to lazy save and restore. We've also been a
little vague as to how tm_reclaim() leaves the FP/Altivec state since it
doesn't necessarily always save it to the thread struct. This has lead
to an (incorrect) assumption that it leaves the checkpointed state on
the CPU.
tm_recheckpoint() has similar optimisations in reverse. It may not
always reload the checkpointed FP/Altivec registers from the thread
struct before the trecheckpoint. It is therefore quite unclear where it
expects to get the state from. This didn't help with the assumption
made about tm_reclaim().
These optimisations sit in what is by definition a slow path. If a
process has to go through a reclaim/recheckpoint then its transaction
will be doomed on returning to userspace. This mean that the process
will be unable to complete its transaction and be forced to its failure
handler. This is already an out if line case for userspace. Furthermore,
the cost of copying 64 times 128 bits from registers isn't very long[0]
(at all) on modern processors. As such it appears these optimisations
have only served to increase code complexity and are unlikely to have
had a measurable performance impact.
Our transactional memory handling has been riddled with bugs. A cause
of this has been difficulty in following the code flow, code complexity
has not been our friend here. It makes sense to remove these
optimisations in favour of a (hopefully) more stable implementation.
This patch does mean that some times the assembly will needlessly save
'junk' registers which will subsequently get overwritten with the
correct value by the C code which calls the assembly function. This
small inefficiency is far outweighed by the reduction in complexity for
general TM code, context switching paths, and transactional facility
unavailable exception handler.
0: I tried to measure it once for other work and found that it was
hiding in the noise of everything else I was working with. I find it
exceedingly likely this will be the case here.
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Lazy save and restore of FP/Altivec means that a userspace process can
be sent to userspace with FP or Altivec disabled and loaded only as
required (by way of an FP/Altivec unavailable exception). Transactional
Memory complicates this situation as a transaction could be started
without FP/Altivec being loaded up. This causes the hardware to
checkpoint incorrect registers. Handling FP/Altivec unavailable
exceptions while a thread is transactional requires a reclaim and
recheckpoint to ensure the CPU has correct state for both sets of
registers.
tm_reclaim() has optimisations to not always save the FP/Altivec
registers to the checkpointed save area. This was originally done
because the caller might have information that the checkpointed
registers aren't valid due to lazy save and restore. We've also been a
little vague as to how tm_reclaim() leaves the FP/Altivec state since it
doesn't necessarily always save it to the thread struct. This has lead
to an (incorrect) assumption that it leaves the checkpointed state on
the CPU.
tm_recheckpoint() has similar optimisations in reverse. It may not
always reload the checkpointed FP/Altivec registers from the thread
struct before the trecheckpoint. It is therefore quite unclear where it
expects to get the state from. This didn't help with the assumption
made about tm_reclaim().
This patch is a minimal fix for ease of backporting. A more correct fix
which removes the msr parameter to tm_reclaim() and tm_recheckpoint()
altogether has been upstreamed to apply on top of this patch.
Fixes: dc3106690b ("powerpc: tm: Always use fp_state and vr_state to
store live registers")
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Lazy save and restore of FP/Altivec means that a userspace process can
be sent to userspace with FP or Altivec disabled and loaded only as
required (by way of an FP/Altivec unavailable exception). Transactional
Memory complicates this situation as a transaction could be started
without FP/Altivec being loaded up. This causes the hardware to
checkpoint incorrect registers. Handling FP/Altivec unavailable
exceptions while a thread is transactional requires a reclaim and
recheckpoint to ensure the CPU has correct state for both sets of
registers.
Lazy save and restore of FP/Altivec cannot be done if a process is
transactional. If a facility was enabled it must remain enabled whenever
a thread is transactional.
Commit dc16b553c9 ("powerpc: Always restore FPU/VEC/VSX if hardware
transactional memory in use") ensures that the facilities are always
enabled if a thread is transactional. A bug in the introduced code may
cause it to inadvertently enable a facility that was (and should remain)
disabled. The problem with this extraneous enablement is that the
registers for the erroneously enabled facility have not been correctly
recheckpointed - the recheckpointing code assumed the facility would
remain disabled.
Further compounding the issue, the transactional {fp,altivec,vsx}
unavailable code has been incorrectly using the MSR to enable
facilities. The presence of the {FP,VEC,VSX} bit in the regs->msr simply
means if the registers are live on the CPU, not if the kernel should
load them before returning to userspace. This has worked due to the bug
mentioned above.
This causes transactional threads which return to their failure handler
to observe incorrect checkpointed registers. Perhaps an example will
help illustrate the problem:
A userspace process is running and uses both FP and Altivec registers.
This process then continues to run for some time without touching
either sets of registers. The kernel subsequently disables the
facilities as part of lazy save and restore. The userspace process then
performs a tbegin and the CPU checkpoints 'junk' FP and Altivec
registers. The process then performs a floating point instruction
triggering a fp unavailable exception in the kernel.
The kernel then loads the FP registers - and only the FP registers.
Since the thread is transactional it must perform a reclaim and
recheckpoint to ensure both the checkpointed registers and the
transactional registers are correct. It then (correctly) enables
MSR[FP] for the process. Later (on exception exist) the kernel also
(inadvertently) enables MSR[VEC]. The process is then returned to
userspace.
Since the act of loading the FP registers doomed the transaction we know
CPU will fail the transaction, restore its checkpointed registers, and
return the process to its failure handler. The problem is that we're
now running with Altivec enabled and the 'junk' checkpointed registers
are restored. The kernel had only recheckpointed FP.
This patch solves this by only activating FP/Altivec if userspace was
using them when it entered the kernel and not simply if the process is
transactional.
Fixes: dc16b553c9 ("powerpc: Always restore FPU/VEC/VSX if hardware
transactional memory in use")
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
The OPAL calls performed in this driver shouldn't be using
opal_async_wait_response() as this performs a wait_event() which, on
long running OPAL calls could result in hung task warnings. wait_event()
prevents timely signal delivery which is also undesirable.
This patch also attempts to quieten down the use of dev_err() when
errors haven't actually occurred and also to return better information up
the stack rather than always -EIO.
Signed-off-by: Cyril Bur <cyrilbur@gmail.com>
Acked-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
