* [PATCH v10 01/25] mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT
From: Laurent Dufour @ 2018-04-17 14:33 UTC (permalink / raw)
To: akpm, mhocko, peterz, kirill, ak, dave, jack, Matthew Wilcox,
benh, mpe, paulus, Thomas Gleixner, Ingo Molnar, hpa, Will Deacon,
Sergey Senozhatsky, Andrea Arcangeli, Alexei Starovoitov,
kemi.wang, sergey.senozhatsky.work, Daniel Jordan, David Rientjes,
Jerome Glisse, Ganesh Mahendran
Cc: linux-kernel, linux-mm, haren, khandual, npiggin, bsingharora,
paulmck, Tim Chen, linuxppc-dev, x86
In-Reply-To: <1523975611-15978-1-git-send-email-ldufour@linux.vnet.ibm.com>
This configuration variable will be used to build the code needed to
handle speculative page fault.
By default it is turned off, and activated depending on architecture
support, SMP and MMU.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: David Rientjes <rientjes@google.com>
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
mm/Kconfig | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/mm/Kconfig b/mm/Kconfig
index d5004d82a1d6..5484dca11199 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -752,3 +752,25 @@ config GUP_BENCHMARK
performance of get_user_pages_fast().
See tools/testing/selftests/vm/gup_benchmark.c
+
+config ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT
+ def_bool n
+
+config SPECULATIVE_PAGE_FAULT
+ bool "Speculative page faults"
+ default y
+ depends on ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT
+ depends on MMU && SMP
+ help
+ Try to handle user space page faults without holding the mmap_sem.
+
+ This should allow better concurrency for massively threaded process
+ since the page fault handler will not wait for other threads memory
+ layout change to be done, assuming that this change is done in another
+ part of the process's memory space. This type of page fault is named
+ speculative page fault.
+
+ If the speculative page fault fails because of a concurrency is
+ detected or because underlying PMD or PTE tables are not yet
+ allocating, it is failing its processing and a classic page fault
+ is then tried.
--
2.7.4
^ permalink raw reply related
* [PATCH v10 00/25] Speculative page faults
From: Laurent Dufour @ 2018-04-17 14:33 UTC (permalink / raw)
To: akpm, mhocko, peterz, kirill, ak, dave, jack, Matthew Wilcox,
benh, mpe, paulus, Thomas Gleixner, Ingo Molnar, hpa, Will Deacon,
Sergey Senozhatsky, Andrea Arcangeli, Alexei Starovoitov,
kemi.wang, sergey.senozhatsky.work, Daniel Jordan, David Rientjes,
Jerome Glisse, Ganesh Mahendran
Cc: linux-kernel, linux-mm, haren, khandual, npiggin, bsingharora,
paulmck, Tim Chen, linuxppc-dev, x86
This is a port on kernel 4.16 of the work done by Peter Zijlstra to
handle page fault without holding the mm semaphore [1].
The idea is to try to handle user space page faults without holding the
mmap_sem. This should allow better concurrency for massively threaded
process since the page fault handler will not wait for other threads memory
layout change to be done, assuming that this change is done in another part
of the process's memory space. This type page fault is named speculative
page fault. If the speculative page fault fails because of a concurrency is
detected or because underlying PMD or PTE tables are not yet allocating, it
is failing its processing and a classic page fault is then tried.
The speculative page fault (SPF) has to look for the VMA matching the fault
address without holding the mmap_sem, this is done by introducing a rwlock
which protects the access to the mm_rb tree. Previously this was done using
SRCU but it was introducing a lot of scheduling to process the VMA's
freeing
operation which was hitting the performance by 20% as reported by Kemi Wang
[2].Using a rwlock to protect access to the mm_rb tree is limiting the
locking contention to these operations which are expected to be in a O(log
n)
order. In addition to ensure that the VMA is not freed in our back a
reference count is added and 2 services (get_vma() and put_vma()) are
introduced to handle the reference count. When a VMA is fetch from the RB
tree using get_vma() is must be later freeed using put_vma(). Furthermore,
to allow the VMA to be used again by the classic page fault handler a
service is introduced can_reuse_spf_vma(). This service is expected to be
called with the mmap_sem hold. It checked that the VMA is still matching
the specified address and is releasing its reference count as the mmap_sem
is hold it is ensure that it will not be freed in our back. In general, the
VMA's reference count could be decremented when holding the mmap_sem but it
should not be increased as holding the mmap_sem is ensuring that the VMA is
stable. I can't see anymore the overhead I got while will-it-scale
benchmark anymore.
The VMA's attributes checked during the speculative page fault processing
have to be protected against parallel changes. This is done by using a per
VMA sequence lock. This sequence lock allows the speculative page fault
handler to fast check for parallel changes in progress and to abort the
speculative page fault in that case.
Once the VMA is found, the speculative page fault handler would check for
the VMA's attributes to verify that the page fault has to be handled
correctly or not. Thus the VMA is protected through a sequence lock which
allows fast detection of concurrent VMA changes. If such a change is
detected, the speculative page fault is aborted and a *classic* page fault
is tried. VMA sequence lockings are added when VMA attributes which are
checked during the page fault are modified.
When the PTE is fetched, the VMA is checked to see if it has been changed,
so once the page table is locked, the VMA is valid, so any other changes
leading to touching this PTE will need to lock the page table, so no
parallel change is possible at this time.
The locking of the PTE is done with interrupts disabled, this allows to
check for the PMD to ensure that there is not an ongoing collapsing
operation. Since khugepaged is firstly set the PMD to pmd_none and then is
waiting for the other CPU to have catch the IPI interrupt, if the pmd is
valid at the time the PTE is locked, we have the guarantee that the
collapsing opertion will have to wait on the PTE lock to move foward. This
allows the SPF handler to map the PTE safely. If the PMD value is different
than the one recorded at the beginning of the SPF operation, the classic
page fault handler will be called to handle the operation while holding the
mmap_sem. As the PTE lock is done with the interrupts disabled, the lock is
done using spin_trylock() to avoid dead lock when handling a page fault
while a TLB invalidate is requested by an other CPU holding the PTE.
In pseudo code, this could be seen as:
speculative_page_fault()
{
vma = GET_VMA_vma()
check vma sequence count
check vma's support
disable interrupt
check pgd,p4d,...,pte
save pmd and pte in vmf
save vma sequence counter in vmf
enable interrupt
check vma sequence count
handle_pte_fault(vma)
..
page = alloc_page()
pte_map_lock()
disable interrupt
abort if sequence counter has changed
abort if pmd or pte has changed
pte map and lock
enable interrupt
if abort
free page
abort
...
}
arch_fault_handler()
{
if (speculative_page_fault(&vma)) goto done
again:
lock(mmap_sem)
if (!vma)
try_to_reuse(vma)
else
vma = find_vma();
handle_pte_fault(vma);
if retry
unlock(mmap_sem)
vma = NULL;
goto again;
done
handle fault error
}
Support for THP is not done because when checking for the PMD, we can be
confused by an in progress collapsing operation done by khugepaged. The
issue is that pmd_none() could be true either if the PMD is not already
populated or if the underlying PTE are in the way to be collapsed. So we
cannot safely allocate a PMD if pmd_none() is true.
This series add a new software performance event named 'speculative-faults'
or 'spf'. It counts the number of successful page fault event handled in a
speculative way. When recording 'faults,spf' events, the faults one is
counting the total number of page fault events while 'spf' is only counting
the part of the faults processed in a speculative way.
There are some trace events introduced by this series. They allow to
identify why the page faults where not processed in a speculative way. This
doesn't take in account the faults generated by a monothreaded process
which directly processed while holding the mmap_sem. This trace events are
grouped in a system named 'pagefault', they are:
- pagefault:spf_pte_lock : if the pte was already locked by another thread
- pagefault:spf_vma_changed : if the VMA has been changed in our back
- pagefault:spf_vma_noanon : the vma->anon_vma field was not yet set.
- pagefault:spf_vma_notsup : the VMA's type is not supported
- pagefault:spf_vma_access : the VMA's access right are not respected
- pagefault:spf_pmd_changed : the upper PMD pointer has changed in our
back.
To record all the related events, the easier is to run perf with the
following arguments :
$ perf stat -e 'faults,spf,pagefault:*' <command>
There is also a dedicated vmstat counter showing the number of successful
page fault handled in a speculative way. I can be seen this way:
$ grep speculative_pgfault /proc/vmstat
This series builds on top of v4.16-mmotm-2018-04-13-17-28 and is
functional on x86 and PowerPC.
---------------------
Real Workload results
As mentioned in previous email, we did non official runs using a "popular
in memory multithreaded database product" on 176 cores SMT8 Power system
which showed a 30% improvements in the number of transaction processed per
second. This run has been done on the v6 series, but changes introduced in
this new verion should not impact the performance boost seen.
Here are the perf data captured during 2 of these runs on top of the v8
series:
vanilla spf
faults 89.418 101.364
spf n/a 97.989
With the SPF kernel, most of the page fault were processed in a speculative
way.
Ganesh Mahendran had backported the series on top of a 4.9 kernel and give
it
a try on an android device. He reported that the application launch time
was
improved by 15%, and for large applications (~100 threads) by 20% [3].
------------------
Benchmarks results
Base kernel is v4.16
SPF is BASE + this series
Kernbench:
----------
Here are the results on a 16 CPUs X86 guest using kernbench on a 4.15
kernel (kernel is build 5 times):
Average Half load -j 8
Run (std deviation)
BASE SPF
Elapsed Time 152.5 (0.631585) 151.406 (0.391446) -0.72%
User Time 1036.4 (2.42065) 1025.2 (1.9909) -1.08%
System Time 125.688 (0.403695) 126.794 (0.716715) 0.88%
Percent CPU 761.4 (2.07364) 760.4 (1.34164) -0.13%
Context Switches 51429 (804.93) 51435.6 (1108.12) 0.01%
Sleeps 104625 (510.468) 105877 (703.774) 1.20%
Average Optimal load -j 16
Run (std deviation)
BASE SPF
Elapsed Time 75.51 (0.576498) 74.684 (0.279159) -1.09%
User Time 970.701 (69.2768) 964.945 (63.5283) -0.59%
System Time 111.965 (14.4711) 112.465 (15.1159) 0.45%
Percent CPU 1044.8 (298.806) 1051.3 (306.658) 0.62%
Context Switches 75261.5 (25129.6) 75387.4 (25264.8) 0.17%
Sleeps 109660 (5349.62) 110279 (4704.95) 0.56%
During a run on the SPF, perf events were captured:
Performance counter stats for '../kernbench -M':
513045402 faults
202 spf
0 pagefault:spf_pte_lock
0 pagefault:spf_vma_changed
0 pagefault:spf_vma_noanon
2210 pagefault:spf_vma_notsup
0 pagefault:spf_vma_access
0 pagefault:spf_pmd_changed
1837.394054020 seconds time elapsed
Very few speculative page fault were recorded as most of the processes
involved are monothreaded (sounds that on this architecture some threads
were created during the kernel build processing).
Here are the kerbench results on a 80 CPUs Power8 system:
Average Half load -j 40
Run (std deviation)
BASE SPF
Elapsed Time 117.222 (0.733294) 116.784 (0.452139) -0.37%
User Time 4485.58 (27.1243) 4473.9 (8.0409) -0.26%
System Time 134.228 (0.601764) 134.874 (0.680169) 0.48%
Percent CPU 3940.4 (12.4218) 3945.8 (12.5579) 0.14%
Context Switches 92414.8 (689.529) 92448.6 (511.846) 0.04%
Sleeps 318388 (758.783) 318758 (1758.96) 0.12%
Average Optimal load -j 80
Run (std deviation)
BASE SPF
Elapsed Time 107.102 (0.73605) 107.872 (1.08573) 0.72%
User Time 5875.13 (1464.89) 5862.59 (1463.87) -0.21%
System Time 157.006 (24.0146) 157.731 (24.1209) 0.46%
Percent CPU 5445.4 (1587.03) 5417.6 (1552.41) -0.51%
Context Switches 221714 (136312) 221526 (136071) -0.08%
Sleeps 332500 (15173.2) 332037 (14202.1) -0.14%
During a run on the SPF, perf events were captured:
Performance counter stats for '../kernbench -M':
116933988 faults
0 spf
0 pagefault:spf_pte_lock
0 pagefault:spf_vma_changed
0 pagefault:spf_vma_noanon
476 pagefault:spf_vma_notsup
0 pagefault:spf_vma_access
0 pagefault:spf_pmd_changed
Most of the processes involved are monothreaded so SPF is not activated but
there is no impact on the performance.
Ebizzy:
-------
The test is counting the number of records per second it can manage, the
higher is the best. I run it like this 'ebizzy -mTRp'. To get consistent
result I repeated the test 100 times and measure the average result. The
number is the record processes per second, the higher is the best.
BASE SPF delta
16 CPUs x86 VM 12405.52 91104.52 634.39%
80 CPUs P8 node 37880.01 76201.05 101.16%
Here are the performance counter read during a run on a 16 CPUs x86 VM:
Performance counter stats for './ebizzy -mRTp':
860074 faults
856866 spf
285 pagefault:spf_pte_lock
1506 pagefault:spf_vma_changed
0 pagefault:spf_vma_noanon
73 pagefault:spf_vma_notsup
0 pagefault:spf_vma_access
0 pagefault:spf_pmd_changed
And the ones captured during a run on a 80 CPUs Power node:
Performance counter stats for './ebizzy -mRTp':
722695 faults
699402 spf
16048 pagefault:spf_pte_lock
6838 pagefault:spf_vma_changed
0 pagefault:spf_vma_noanon
277 pagefault:spf_vma_notsup
0 pagefault:spf_vma_access
0 pagefault:spf_pmd_changed
In ebizzy's case most of the page fault were handled in a speculative way,
leading the ebizzy performance boost.
------------------
Changes since v9:
- Accounted for all review feedback from David Rientjes and Jerome Glisse,
hopefully
- Fix a lockdep warning when populate_vma_page_range() is called by
mprotect_fixup(). The call to vm_write_end(vma) is now made before
calling
populate_vma_page_range() since vma locking is not required here.
- Introduce INIT_VMA() move VMA's sequence and refcount initialization out
of __vma_link_rb(). This fix various lockdep warning raised when
unmap_region() may be called before vma_link() (patch 7 & 8)
- Allow CONFIG_SPECULATIVE_PAGE_FAULT to be switched off
- Pass VMA's flag value to maybe_mkwrite() allowing to use the cached ones
(patch 12)
- Make CONFIG_SPECULATIVE_PAGE_FAULT user configurable
- Add speculative page fault vmstats
- Remove #ifdef in arch/*/mm/fault.c
Changes since v8:
- Don't check PMD when locking the pte when THP is disabled
Thanks to Daniel Jordan for reporting this.
- Rebase on 4.16
Changes since v7:
- move pte_map_lock() and pte_spinlock() upper in mm/memory.c (patch 4 &
5)
- make pte_unmap_same() compatible with the speculative page fault (patch
6)
Changes since v6:
- Rename config variable to CONFIG_SPECULATIVE_PAGE_FAULT (patch 1)
- Review the way the config variable is set (patch 1 to 3)
- Introduce mm_rb_write_*lock() in mm/mmap.c (patch 18)
- Merge patch introducing pte try locking in the patch 18.
Changes since v5:
- use rwlock agains the mm RB tree in place of SRCU
- add a VMA's reference count to protect VMA while using it without
holding the mmap_sem.
- check PMD value to detect collapsing operation
- don't try speculative page fault for mono threaded processes
- try to reuse the fetched VMA if VM_RETRY is returned
- go directly to the error path if an error is detected during the SPF
path
- fix race window when moving VMA in move_vma()
Changes since v4:
- As requested by Andrew Morton, use CONFIG_SPF and define it earlier in
the series to ease bisection.
Changes since v3:
- Don't build when CONFIG_SMP is not set
- Fixed a lock dependency warning in __vma_adjust()
- Use READ_ONCE to access p*d values in handle_speculative_fault()
- Call memcp_oom() service in handle_speculative_fault()
Changes since v2:
- Perf event is renamed in PERF_COUNT_SW_SPF
- On Power handle do_page_fault()'s cleaning
- On Power if the VM_FAULT_ERROR is returned by
handle_speculative_fault(), do not retry but jump to the error path
- If VMA's flags are not matching the fault, directly returns
VM_FAULT_SIGSEGV and not VM_FAULT_RETRY
- Check for pud_trans_huge() to avoid speculative path
- Handles _vm_normal_page()'s introduced by 6f16211df3bf
("mm/device-public-memory: device memory cache coherent with CPU")
- add and review few comments in the code
Changes since v1:
- Remove PERF_COUNT_SW_SPF_FAILED perf event.
- Add tracing events to details speculative page fault failures.
- Cache VMA fields values which are used once the PTE is unlocked at the
end of the page fault events.
- Ensure that fields read during the speculative path are written and read
using WRITE_ONCE and READ_ONCE.
- Add checks at the beginning of the speculative path to abort it if the
VMA is known to not be supported.
Changes since RFC V5 [5]
- Port to 4.13 kernel
- Merging patch fixing lock dependency into the original patch
- Replace the 2 parameters of vma_has_changed() with the vmf pointer
- In patch 7, don't call __do_fault() in the speculative path as it may
want to unlock the mmap_sem.
- In patch 11-12, don't check for vma boundaries when
page_add_new_anon_rmap() is called during the spf path and protect against
anon_vma pointer's update.
- In patch 13-16, add performance events to report number of successful
and failed speculative events.
[1]
http://linux-kernel.2935.n7.nabble.com/RFC-PATCH-0-6-Another-go-at-speculative-page-faults-tt965642.html#none
[2] https://patchwork.kernel.org/patch/9999687/
[3] https://lkml.org/lkml/2018/3/21/894
Laurent Dufour (21):
mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT
x86/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT
powerpc/mm: set ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT
mm: introduce pte_spinlock for FAULT_FLAG_SPECULATIVE
mm: make pte_unmap_same compatible with SPF
mm: introduce INIT_VMA()
mm: protect VMA modifications using VMA sequence count
mm: protect mremap() against SPF hanlder
mm: protect SPF handler against anon_vma changes
mm: cache some VMA fields in the vm_fault structure
mm/migrate: Pass vm_fault pointer to migrate_misplaced_page()
mm: introduce __lru_cache_add_active_or_unevictable
mm: introduce __vm_normal_page()
mm: introduce __page_add_new_anon_rmap()
mm: protect mm_rb tree with a rwlock
mm: adding speculative page fault failure trace events
perf: add a speculative page fault sw event
perf tools: add support for the SPF perf event
mm: speculative page fault handler return VMA
mm: add speculative page fault vmstats
powerpc/mm: add speculative page fault
Peter Zijlstra (4):
mm: prepare for FAULT_FLAG_SPECULATIVE
mm: VMA sequence count
mm: provide speculative fault infrastructure
x86/mm: add speculative pagefault handling
arch/powerpc/Kconfig | 1 +
arch/powerpc/mm/fault.c | 33 +-
arch/x86/Kconfig | 1 +
arch/x86/mm/fault.c | 42 ++-
fs/exec.c | 2 +-
fs/proc/task_mmu.c | 5 +-
fs/userfaultfd.c | 17 +-
include/linux/hugetlb_inline.h | 2 +-
include/linux/migrate.h | 4 +-
include/linux/mm.h | 145 +++++++-
include/linux/mm_types.h | 7 +
include/linux/pagemap.h | 4 +-
include/linux/rmap.h | 12 +-
include/linux/swap.h | 10 +-
include/linux/vm_event_item.h | 3 +
include/trace/events/pagefault.h | 88 +++++
include/uapi/linux/perf_event.h | 1 +
kernel/fork.c | 5 +-
mm/Kconfig | 22 ++
mm/huge_memory.c | 6 +-
mm/hugetlb.c | 2 +
mm/init-mm.c | 3 +
mm/internal.h | 20 ++
mm/khugepaged.c | 5 +
mm/madvise.c | 6 +-
mm/memory.c | 649 +++++++++++++++++++++++++++++-----
mm/mempolicy.c | 51 ++-
mm/migrate.c | 6 +-
mm/mlock.c | 13 +-
mm/mmap.c | 229 +++++++++---
mm/mprotect.c | 4 +-
mm/mremap.c | 13 +
mm/nommu.c | 2 +-
mm/rmap.c | 5 +-
mm/swap.c | 6 +-
mm/swap_state.c | 8 +-
mm/vmstat.c | 5 +-
tools/include/uapi/linux/perf_event.h | 1 +
tools/perf/util/evsel.c | 1 +
tools/perf/util/parse-events.c | 4 +
tools/perf/util/parse-events.l | 1 +
tools/perf/util/python.c | 1 +
42 files changed, 1231 insertions(+), 214 deletions(-)
create mode 100644 include/trace/events/pagefault.h
--
2.7.4
^ permalink raw reply
* Re: [RFC PATCH 1/3] signal: Ensure every siginfo we send has all bits initialized
From: Dave Martin @ 2018-04-17 13:23 UTC (permalink / raw)
To: Eric W. Biederman
Cc: Linus Torvalds, linux-arch, Linux Kernel Mailing List,
Dmitry V. Levin, sparclinux, Russell King - ARM Linux, ppc-dev,
linux-arm-kernel
In-Reply-To: <87zi248nte.fsf_-_@xmission.com>
On Sun, Apr 15, 2018 at 10:57:33AM -0500, Eric W. Biederman wrote:
>
> Call clear_siginfo to ensure every stack allocated siginfo is properly
> initialized before being passed to the signal sending functions.
>
> Note: It is not safe to depend on C initializers to initialize struct
> siginfo on the stack because C is allowed to skip holes when
> initializing a structure.
>
> The initialization of struct siginfo in tracehook_report_syscall_exit
> was moved from the helper user_single_step_siginfo into
> tracehook_report_syscall_exit itself, to make it clear that the local
> variable siginfo gets fully initialized.
>
> In a few cases the scope of struct siginfo has been reduced to make it
> clear that siginfo siginfo is not used on other paths in the function
> in which it is declared.
>
> Instances of using memset to initialize siginfo have been replaced
> with calls clear_siginfo for clarity.
>
> Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
[...]
Hmmm
memset()/clear_siginfo() may ensure that there are no uninitialised
explicit fields except for those in inactive union members, but I'm not
sure that this approach is guaranteed to sanitise the padding seen by
userspace.
Rationale below, though it's a bit theoretical...
With this in mind, I tend agree with Linus that hiding memset() calls
from the maintainer may be a bad idea unless they are also hidden from
the compiler. If the compiler sees the memset() it may be able to
optimise it in ways that wouldn't be possible for some other random
external function call, including optimising all or part of the call
out.
As a result, the breakdown into individual put_user()s etc. in
copy_siginfo_to_user() may still be valuable even if all paths have the
memset().
(Rationale for an arch/arm example:)
> diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
> index 4c375e11ae95..adda3fc2dde8 100644
> --- a/arch/arm/vfp/vfpmodule.c
> +++ b/arch/arm/vfp/vfpmodule.c
> @@ -218,8 +218,7 @@ static void vfp_raise_sigfpe(unsigned int sicode, struct pt_regs *regs)
> {
> siginfo_t info;
>
> - memset(&info, 0, sizeof(info));
> -
> + clear_siginfo(&info);
> info.si_signo = SIGFPE;
/* by c11 (n1570) 6.2.6.1 para 6 [1], all padding bytes in info now take
unspecified values */
> info.si_code = sicode;
> info.si_addr = (void __user *)(instruction_pointer(regs) - 4);
/* by c11 (n1570) 6.2.6.1 para 7 [2], all bytes of the union info._sifields
other than than those corresponding to _sigfault take unspecified
values */
So I don't see why the compiler needs to ensure that any of the affected
bytes are zero: it could potentially skip a lot of the memset() as a
result, in theory.
I've not seen a compiler actually take advantage of that, but I'm now
not sure what forbids it.
If this can happen, I only see two watertight workarounds:
1) Ensure that there is no implicit padding in any UAPI structure, e.g.
aeb1f39d814b: ("arm64/ptrace: Avoid uninitialised struct padding in
fpr_set()"). This would include tail-padding of any union member that
is smaller than the containing union.
It would be significantly more effort to ensure this for siginfo though.
2) Poke all values directly into allocated or user memory directly
via pointers to paddingless types; never assign to objects on the kernel
stack if you care what ends up in the padding, e.g., what your
copy_siginfo_to_user() does prior to this series.
If I'm not barking up the wrong tree, memset() cannot generally be
used to determine the value of padding bytes, but it may still be
useful for forcing otherwise uninitialised members to sane initial
values.
This likely affects many more things than just siginfo.
[...]
Cheers
---Dave
[1] n1570 6.2.6.1.6: When a value is stored in an object of structure or
union type, including in a member object, the bytes of the object
representation that correspond to any padding bytes take unspecified
values [...]
[2] n1570 6.2.6.1.7: When a value is stored in a member of an object of
union type, the bytes of the object representation that do not
correspond to that member but do correspond to other members take
unspecified values.
^ permalink raw reply
* [PATCH] powerpc/time: remove to_tm and use RTC_LIB
From: Christophe Leroy @ 2018-04-17 13:02 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Vitaly Bordug, Geoff Levand
Cc: linux-kernel, linuxppc-dev
RTC_LIB includes a generic function to convert
RTC data into struct rtc_time. Use it and remove to_tm().
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/time.h | 1 -
arch/powerpc/kernel/rtas-proc.c | 4 +--
arch/powerpc/kernel/time.c | 52 +--------------------------------
arch/powerpc/platforms/8xx/m8xx_setup.c | 2 +-
arch/powerpc/platforms/powermac/time.c | 2 +-
arch/powerpc/platforms/ps3/time.c | 2 +-
7 files changed, 7 insertions(+), 57 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index edbbd2ea1298..e1fac49cf465 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -232,6 +232,7 @@ config PPC
select OF_RESERVED_MEM
select OLD_SIGACTION if PPC32
select OLD_SIGSUSPEND
+ select RTC_LIB
select SPARSE_IRQ
select SYSCTL_EXCEPTION_TRACE
select VIRT_TO_BUS if !PPC64
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index db546c034905..0ad1cf2285b1 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -27,7 +27,6 @@ extern unsigned long tb_ticks_per_sec;
extern struct clock_event_device decrementer_clockevent;
struct rtc_time;
-extern void to_tm(int tim, struct rtc_time * tm);
extern void tick_broadcast_ipi_handler(void);
extern void generic_calibrate_decr(void);
diff --git a/arch/powerpc/kernel/rtas-proc.c b/arch/powerpc/kernel/rtas-proc.c
index fb070d8cad07..6de77f9434b0 100644
--- a/arch/powerpc/kernel/rtas-proc.c
+++ b/arch/powerpc/kernel/rtas-proc.c
@@ -314,7 +314,7 @@ static ssize_t ppc_rtas_poweron_write(struct file *file,
power_on_time = nowtime; /* save the time */
- to_tm(nowtime, &tm);
+ rtc_time64_to_tm(nowtime, &tm);
error = rtas_call(rtas_token("set-time-for-power-on"), 7, 1, NULL,
tm.tm_year, tm.tm_mon, tm.tm_mday,
@@ -378,7 +378,7 @@ static ssize_t ppc_rtas_clock_write(struct file *file,
if (error)
return error;
- to_tm(nowtime, &tm);
+ rtc_time64_to_tm(nowtime, &tm);
error = rtas_call(rtas_token("set-time-of-day"), 7, 1, NULL,
tm.tm_year, tm.tm_mon, tm.tm_mday,
tm.tm_hour, tm.tm_min, tm.tm_sec, 0);
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 56869fd879ed..362673cc09f2 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -788,7 +788,7 @@ int update_persistent_clock(struct timespec now)
if (!ppc_md.set_rtc_time)
return -ENODEV;
- to_tm(now.tv_sec + 1 + timezone_offset, &tm);
+ rtc_time64_to_tm(now.tv_sec + 1 + timezone_offset, &tm);
tm.tm_year -= 1900;
tm.tm_mon -= 1;
@@ -1141,56 +1141,6 @@ void __init time_init(void)
#endif
}
-
-#define FEBRUARY 2
-#define STARTOFTIME 1970
-#define SECDAY 86400L
-#define SECYR (SECDAY * 365)
-#define leapyear(year) ((year) % 4 == 0 && \
- ((year) % 100 != 0 || (year) % 400 == 0))
-#define days_in_year(a) (leapyear(a) ? 366 : 365)
-#define days_in_month(a) (month_days[(a) - 1])
-
-static int month_days[12] = {
- 31, 28, 31, 30, 31, 30, 31, 31, 30, 31, 30, 31
-};
-
-void to_tm(int tim, struct rtc_time * tm)
-{
- register int i;
- register long hms, day;
-
- day = tim / SECDAY;
- hms = tim % SECDAY;
-
- /* Hours, minutes, seconds are easy */
- tm->tm_hour = hms / 3600;
- tm->tm_min = (hms % 3600) / 60;
- tm->tm_sec = (hms % 3600) % 60;
-
- /* Number of years in days */
- for (i = STARTOFTIME; day >= days_in_year(i); i++)
- day -= days_in_year(i);
- tm->tm_year = i;
-
- /* Number of months in days left */
- if (leapyear(tm->tm_year))
- days_in_month(FEBRUARY) = 29;
- for (i = 1; day >= days_in_month(i); i++)
- day -= days_in_month(i);
- days_in_month(FEBRUARY) = 28;
- tm->tm_mon = i;
-
- /* Days are what is left over (+1) from all that. */
- tm->tm_mday = day + 1;
-
- /*
- * No-one uses the day of the week.
- */
- tm->tm_wday = -1;
-}
-EXPORT_SYMBOL(to_tm);
-
/*
* Divide a 128-bit dividend by a 32-bit divisor, leaving a 128 bit
* result.
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index 2188d691a40f..0f9740185eb9 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -192,7 +192,7 @@ void mpc8xx_get_rtc_time(struct rtc_time *tm)
/* Get time from the RTC. */
data = in_be32(&sys_tmr->sit_rtc);
- to_tm(data, tm);
+ rtc_time64_to_tm(data, tm);
tm->tm_year -= 1900;
tm->tm_mon -= 1;
immr_unmap(sys_tmr);
diff --git a/arch/powerpc/platforms/powermac/time.c b/arch/powerpc/platforms/powermac/time.c
index 274af6fa388e..6db8cdacbf3d 100644
--- a/arch/powerpc/platforms/powermac/time.c
+++ b/arch/powerpc/platforms/powermac/time.c
@@ -87,7 +87,7 @@ long __init pmac_time_init(void)
#if defined(CONFIG_ADB_CUDA) || defined(CONFIG_ADB_PMU)
static void to_rtc_time(unsigned long now, struct rtc_time *tm)
{
- to_tm(now, tm);
+ rtc_time64_to_tm(now, tm);
tm->tm_year -= 1900;
tm->tm_mon -= 1;
}
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index 11b45b58c81b..4455abf707ae 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -46,7 +46,7 @@ static void __maybe_unused _dump_time(int time, const char *func,
{
struct rtc_time tm;
- to_tm(time, &tm);
+ rtc_time64_to_tm(time, &tm);
pr_debug("%s:%d time %d\n", func, line, time);
_dump_tm(&tm, func, line);
--
2.13.3
^ permalink raw reply related
* Re: [PATCH] powerpc/8xx: Build fix with Hugetlbfs enabled
From: Christophe LEROY @ 2018-04-17 12:48 UTC (permalink / raw)
To: Aneesh Kumar K.V, benh, paulus, mpe; +Cc: linuxppc-dev
In-Reply-To: <20180416112724.9677-2-aneesh.kumar@linux.ibm.com>
Le 16/04/2018 à 13:27, Aneesh Kumar K.V a écrit :
> 8xx use slice code when hugetlbfs is enabled. We missed a header include on
> 8xx which resulted in the below build failure.
>
> config: mpc885_ads_defconfig + CONFIG_HUGETLBFS
>
> CC arch/powerpc/mm/slice.o
> arch/powerpc/mm/slice.c: In function 'slice_get_unmapped_area':
> arch/powerpc/mm/slice.c:655:2: error: implicit declaration of function 'need_extra_context' [-Werror=implicit-function-declaration]
> arch/powerpc/mm/slice.c:656:3: error: implicit declaration of function 'alloc_extended_context' [-Werror=implicit-function-declaration]
> cc1: all warnings being treated as errors
> make[1]: *** [arch/powerpc/mm/slice.o] Error 1
> make: *** [arch/powerpc/mm] Error 2
>
> on PPC64 the mmu_context.h was included via linux/pkeys.h
>
> CC: Christophe LEROY <christophe.leroy@c-s.fr>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Tested-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> arch/powerpc/mm/slice.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/slice.c
> index 9cd87d11fe4e..205fe557ca10 100644
> --- a/arch/powerpc/mm/slice.c
> +++ b/arch/powerpc/mm/slice.c
> @@ -35,6 +35,7 @@
> #include <asm/mmu.h>
> #include <asm/copro.h>
> #include <asm/hugetlb.h>
> +#include <asm/mmu_context.h>
>
> static DEFINE_SPINLOCK(slice_convert_lock);
>
>
^ permalink raw reply
* [PATCH] powerpc/8xx: Remove RTC clock on 88x
From: Christophe Leroy @ 2018-04-17 12:47 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
Vitaly Bordug
Cc: linux-kernel, linuxppc-dev
The 885 familly processors don't have the Real Time Clock
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/platforms/8xx/adder875.c | 2 --
arch/powerpc/platforms/8xx/ep88xc.c | 2 --
arch/powerpc/platforms/8xx/mpc885ads_setup.c | 2 --
3 files changed, 6 deletions(-)
diff --git a/arch/powerpc/platforms/8xx/adder875.c b/arch/powerpc/platforms/8xx/adder875.c
index 333dece79394..bcef9f66191e 100644
--- a/arch/powerpc/platforms/8xx/adder875.c
+++ b/arch/powerpc/platforms/8xx/adder875.c
@@ -111,7 +111,5 @@ define_machine(adder875) {
.get_irq = mpc8xx_get_irq,
.restart = mpc8xx_restart,
.calibrate_decr = generic_calibrate_decr,
- .set_rtc_time = mpc8xx_set_rtc_time,
- .get_rtc_time = mpc8xx_get_rtc_time,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/8xx/ep88xc.c b/arch/powerpc/platforms/8xx/ep88xc.c
index cd0d90f1fb1c..ebcf34a14789 100644
--- a/arch/powerpc/platforms/8xx/ep88xc.c
+++ b/arch/powerpc/platforms/8xx/ep88xc.c
@@ -170,7 +170,5 @@ define_machine(ep88xc) {
.get_irq = mpc8xx_get_irq,
.restart = mpc8xx_restart,
.calibrate_decr = mpc8xx_calibrate_decr,
- .set_rtc_time = mpc8xx_set_rtc_time,
- .get_rtc_time = mpc8xx_get_rtc_time,
.progress = udbg_progress,
};
diff --git a/arch/powerpc/platforms/8xx/mpc885ads_setup.c b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
index e821a42d5816..a0c83c1905c6 100644
--- a/arch/powerpc/platforms/8xx/mpc885ads_setup.c
+++ b/arch/powerpc/platforms/8xx/mpc885ads_setup.c
@@ -220,7 +220,5 @@ define_machine(mpc885_ads) {
.get_irq = mpc8xx_get_irq,
.restart = mpc8xx_restart,
.calibrate_decr = mpc8xx_calibrate_decr,
- .set_rtc_time = mpc8xx_set_rtc_time,
- .get_rtc_time = mpc8xx_get_rtc_time,
.progress = udbg_progress,
};
--
2.13.3
^ permalink raw reply related
* [PATCH] powerpc/boot: remove unused variable in mpc8xx
From: Christophe Leroy @ 2018-04-17 12:36 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
Variable div is set but never used. Remove it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/boot/mpc8xx.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/arch/powerpc/boot/mpc8xx.c b/arch/powerpc/boot/mpc8xx.c
index add55a7f184f..c9bd9285c548 100644
--- a/arch/powerpc/boot/mpc8xx.c
+++ b/arch/powerpc/boot/mpc8xx.c
@@ -24,7 +24,7 @@ u32 mpc885_get_clock(u32 crystal)
{
u32 *immr;
u32 plprcr;
- int mfi, mfn, mfd, pdf, div;
+ int mfi, mfn, mfd, pdf;
u32 ret;
immr = fsl_get_immr();
@@ -43,7 +43,6 @@ u32 mpc885_get_clock(u32 crystal)
}
pdf = (plprcr >> 1) & 0xf;
- div = (plprcr >> 20) & 3;
mfd = (plprcr >> 22) & 0x1f;
mfn = (plprcr >> 27) & 0x1f;
--
2.13.3
^ permalink raw reply related
* [PATCH] powerpc/misc: merge reloc_offset() and add_reloc_offset()
From: Christophe Leroy @ 2018-04-17 11:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
reloc_offset() is the same as add_reloc_offset(0)
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/kernel/misc.S | 17 +++--------------
1 file changed, 3 insertions(+), 14 deletions(-)
diff --git a/arch/powerpc/kernel/misc.S b/arch/powerpc/kernel/misc.S
index 384357cb8bc0..e1f3a5d054c4 100644
--- a/arch/powerpc/kernel/misc.S
+++ b/arch/powerpc/kernel/misc.S
@@ -25,23 +25,12 @@
/*
* Returns (address we are running at) - (address we were linked at)
* for use before the text and data are mapped to KERNELBASE.
- */
-
-_GLOBAL(reloc_offset)
- mflr r0
- bl 1f
-1: mflr r3
- PPC_LL r4,(2f-1b)(r3)
- subf r3,r4,r3
- mtlr r0
- blr
- .align 3
-2: PPC_LONG 1b
-
-/*
* add_reloc_offset(x) returns x + reloc_offset().
*/
+
+_GLOBAL(reloc_offset)
+ li r3, 0
_GLOBAL(add_reloc_offset)
mflr r0
bl 1f
--
2.13.3
^ permalink raw reply related
* [PATCH] powerpc: Allow selection of CONFIG_LD_DEAD_CODE_DATA_ELIMINATION
From: Christophe Leroy @ 2018-04-17 10:49 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman
Cc: linux-kernel, linuxppc-dev
This option does dead code and data elimination with the linker by
compiling with -ffunction-sections -fdata-sections and linking with
--gc-sections.
By selecting this option on mpc885_ads_defconfig,
vmlinux LOAD segment size gets reduced by 10%
Program Header before the patch:
LOAD off 0x00010000 vaddr 0xc0000000 paddr 0x00000000 align 2**16
filesz 0x0036eda4 memsz 0x0038de04 flags rwx
Program Header after the patch:
LOAD off 0x00010000 vaddr 0xc0000000 paddr 0x00000000 align 2**16
filesz 0x00316da4 memsz 0x00334268 flags rwx
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/Kconfig | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8fe4353be5e3..e1fac49cf465 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -888,6 +888,14 @@ config PPC_MEM_KEYS
If unsure, say y.
+config PPC_UNUSED_ELIMINATION
+ bool "Eliminate unused functions and data from vmlinux"
+ default n
+ select LD_DEAD_CODE_DATA_ELIMINATION
+ help
+ Select this to do dead code and data elimination with the linker
+ by compiling with -ffunction-sections -fdata-sections and linking
+ with --gc-sections.
endmenu
config ISA_DMA_API
--
2.13.3
^ permalink raw reply related
* [PATCH 6/6 v2] arm64: dts: ls208xa: comply with the iommu map binding for fsl_mc
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
Fsl-mc bus now support the iommu-map property. Comply to this binding for
fsl_mc bus. This patch also updates the dts w.r.t. the DMA configuration.
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
index f3a40af..1b1c5eb 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi
@@ -135,6 +135,7 @@
#address-cells = <2>;
#size-cells = <2>;
ranges;
+ dma-ranges = <0x0 0x0 0x0 0x0 0x10000 0x00000000>;
clockgen: clocking@1300000 {
compatible = "fsl,ls2080a-clockgen";
@@ -357,6 +358,8 @@
reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */
<0x00000000 0x08340000 0 0x40000>; /* MC control reg */
msi-parent = <&its>;
+ iommu-map = <0 &smmu 0 0>; /* This is fixed-up by u-boot */
+ dma-coherent;
#address-cells = <3>;
#size-cells = <1>;
@@ -460,6 +463,8 @@
compatible = "arm,mmu-500";
reg = <0 0x5000000 0 0x800000>;
#global-interrupts = <12>;
+ #iommu-cells = <1>;
+ stream-match-mask = <0x7C00>;
interrupts = <0 13 4>, /* global secure fault */
<0 14 4>, /* combined secure interrupt */
<0 15 4>, /* global non-secure fault */
@@ -502,7 +507,6 @@
<0 204 4>, <0 205 4>,
<0 206 4>, <0 207 4>,
<0 208 4>, <0 209 4>;
- mmu-masters = <&fsl_mc 0x300 0>;
};
dspi: dspi@2100000 {
--
1.9.1
^ permalink raw reply related
* [PATCH 5/6 v2] bus: fsl-mc: supoprt dma configure for devices on fsl-mc bus
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
drivers/bus/fsl-mc/fsl-mc-bus.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff --git a/drivers/bus/fsl-mc/fsl-mc-bus.c b/drivers/bus/fsl-mc/fsl-mc-bus.c
index 5d8266c..624828b 100644
--- a/drivers/bus/fsl-mc/fsl-mc-bus.c
+++ b/drivers/bus/fsl-mc/fsl-mc-bus.c
@@ -127,6 +127,16 @@ static int fsl_mc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
return 0;
}
+static int fsl_mc_dma_configure(struct device *dev)
+{
+ struct device *dma_dev = dev;
+
+ while (dev_is_fsl_mc(dma_dev))
+ dma_dev = dma_dev->parent;
+
+ return of_dma_configure(dev, dma_dev->of_node, 0);
+}
+
static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
@@ -148,6 +158,7 @@ struct bus_type fsl_mc_bus_type = {
.name = "fsl-mc",
.match = fsl_mc_bus_match,
.uevent = fsl_mc_bus_uevent,
+ .dma_configure = fsl_mc_dma_configure,
.dev_groups = fsl_mc_dev_groups,
};
EXPORT_SYMBOL_GPL(fsl_mc_bus_type);
@@ -616,6 +627,7 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
mc_dev->icid = parent_mc_dev->icid;
mc_dev->dma_mask = FSL_MC_DEFAULT_DMA_MASK;
mc_dev->dev.dma_mask = &mc_dev->dma_mask;
+ mc_dev->dev.coherent_dma_mask = mc_dev->dma_mask;
dev_set_msi_domain(&mc_dev->dev,
dev_get_msi_domain(&parent_mc_dev->dev));
}
@@ -633,10 +645,6 @@ int fsl_mc_device_add(struct fsl_mc_obj_desc *obj_desc,
goto error_cleanup_dev;
}
- /* Objects are coherent, unless 'no shareability' flag set. */
- if (!(obj_desc->flags & FSL_MC_OBJ_FLAG_NO_MEM_SHAREABILITY))
- arch_setup_dma_ops(&mc_dev->dev, 0, 0, NULL, true);
-
/*
* The device-specific probe callback will get invoked by device_add()
*/
--
1.9.1
^ permalink raw reply related
* [PATCH 4/6 v2] iommu: arm-smmu: Add support for the fsl-mc bus
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
Implement bus specific support for the fsl-mc bus including
registering arm_smmu_ops and bus specific device add operations.
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
drivers/iommu/arm-smmu.c | 7 +++++++
drivers/iommu/iommu.c | 21 +++++++++++++++++++++
include/linux/fsl/mc.h | 8 ++++++++
include/linux/iommu.h | 2 ++
4 files changed, 38 insertions(+)
diff --git a/drivers/iommu/arm-smmu.c b/drivers/iommu/arm-smmu.c
index 69e7c60..e1d5090 100644
--- a/drivers/iommu/arm-smmu.c
+++ b/drivers/iommu/arm-smmu.c
@@ -52,6 +52,7 @@
#include <linux/spinlock.h>
#include <linux/amba/bus.h>
+#include <linux/fsl/mc.h>
#include "io-pgtable.h"
#include "arm-smmu-regs.h"
@@ -1459,6 +1460,8 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev)
if (dev_is_pci(dev))
group = pci_device_group(dev);
+ else if (dev_is_fsl_mc(dev))
+ group = fsl_mc_device_group(dev);
else
group = generic_device_group(dev);
@@ -2037,6 +2040,10 @@ static void arm_smmu_bus_init(void)
bus_set_iommu(&pci_bus_type, &arm_smmu_ops);
}
#endif
+#ifdef CONFIG_FSL_MC_BUS
+ if (!iommu_present(&fsl_mc_bus_type))
+ bus_set_iommu(&fsl_mc_bus_type, &arm_smmu_ops);
+#endif
}
static int arm_smmu_device_probe(struct platform_device *pdev)
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 69fef99..fbeebb2 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -32,6 +32,7 @@
#include <linux/pci.h>
#include <linux/bitops.h>
#include <linux/property.h>
+#include <linux/fsl/mc.h>
#include <trace/events/iommu.h>
static struct kset *iommu_group_kset;
@@ -987,6 +988,26 @@ struct iommu_group *pci_device_group(struct device *dev)
return iommu_group_alloc();
}
+/* Get the IOMMU group for device on fsl-mc bus */
+struct iommu_group *fsl_mc_device_group(struct device *dev)
+{
+ struct device *cont_dev = fsl_mc_cont_dev(dev);
+ struct iommu_group *group;
+
+ /* Container device is responsible for creating the iommu group */
+ if (fsl_mc_is_cont_dev(dev)) {
+ group = iommu_group_alloc();
+ if (IS_ERR(group))
+ return NULL;
+ } else {
+ get_device(cont_dev);
+ group = iommu_group_get(cont_dev);
+ put_device(cont_dev);
+ }
+
+ return group;
+}
+
/**
* iommu_group_get_for_dev - Find or create the IOMMU group for a device
* @dev: target device
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index f27cb14..dddaca1 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -351,6 +351,14 @@ struct fsl_mc_io {
#define dev_is_fsl_mc(_dev) (0)
#endif
+/* Macro to check if a device is a container device */
+#define fsl_mc_is_cont_dev(_dev) (to_fsl_mc_device(_dev)->flags & \
+ FSL_MC_IS_DPRC)
+
+/* Macro to get the container device of a MC device */
+#define fsl_mc_cont_dev(_dev) (fsl_mc_is_cont_dev(_dev) ? \
+ (_dev) : (_dev)->parent)
+
/*
* module_fsl_mc_driver() - Helper macro for drivers that don't do
* anything special in module init/exit. This eliminates a lot of
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 41b8c57..00a460b 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -389,6 +389,8 @@ static inline size_t iommu_map_sg(struct iommu_domain *domain,
extern struct iommu_group *pci_device_group(struct device *dev);
/* Generic device grouping function */
extern struct iommu_group *generic_device_group(struct device *dev);
+/* FSL-MC device grouping function */
+struct iommu_group *fsl_mc_device_group(struct device *dev);
/**
* struct iommu_fwspec - per-device IOMMU instance data
--
1.9.1
^ permalink raw reply related
* [PATCH 3/6 v2] iommu: support iommu configuration for fsl-mc devices
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
drivers/iommu/of_iommu.c | 20 ++++++++++++++++++++
1 file changed, 20 insertions(+)
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 4e7712f..af4fc3b 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -24,6 +24,7 @@
#include <linux/of_iommu.h>
#include <linux/of_pci.h>
#include <linux/slab.h>
+#include <linux/fsl/mc.h>
#define NO_IOMMU 1
@@ -260,6 +261,23 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
return err;
}
+static int of_fsl_mc_iommu_init(struct fsl_mc_device *mc_dev,
+ struct device_node *master_np)
+{
+ struct of_phandle_args iommu_spec = { .args_count = 1 };
+ int err;
+
+ err = of_map_rid(master_np, mc_dev->icid, "iommu-map",
+ "iommu-map-mask", &iommu_spec.np,
+ iommu_spec.args);
+ if (err)
+ return err == -ENODEV ? NO_IOMMU : err;
+
+ err = of_iommu_xlate(&mc_dev->dev, &iommu_spec);
+ of_node_put(iommu_spec.np);
+ return err;
+}
+
const struct iommu_ops *of_iommu_configure(struct device *dev,
struct device_node *master_np)
{
@@ -291,6 +309,8 @@ const struct iommu_ops *of_iommu_configure(struct device *dev,
err = pci_for_each_dma_alias(to_pci_dev(dev),
of_pci_iommu_init, &info);
+ } else if (dev_is_fsl_mc(dev)) {
+ err = of_fsl_mc_iommu_init(to_fsl_mc_device(dev), master_np);
} else {
struct of_phandle_args iommu_spec;
int idx = 0;
--
1.9.1
^ permalink raw reply related
* [PATCH 2/6 v2] iommu: of: make of_pci_map_rid() available for other devices too
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
iommu-map property is also used by devices with fsl-mc. This
patch moves the of_pci_map_rid to generic location, so that it
can be used by other busses too.
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
drivers/iommu/of_iommu.c | 106 +++++++++++++++++++++++++++++++++++++++++++++--
drivers/of/irq.c | 6 +--
drivers/pci/of.c | 101 --------------------------------------------
include/linux/of_iommu.h | 11 +++++
include/linux/of_pci.h | 10 -----
5 files changed, 117 insertions(+), 117 deletions(-)
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 5c36a8b..4e7712f 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -138,6 +138,106 @@ static int of_iommu_xlate(struct device *dev,
return ops->of_xlate(dev, iommu_spec);
}
+/**
+ * of_map_rid - Translate a requester ID through a downstream mapping.
+ * @np: root complex device node.
+ * @rid: device requester ID to map.
+ * @map_name: property name of the map to use.
+ * @map_mask_name: optional property name of the mask to use.
+ * @target: optional pointer to a target device node.
+ * @id_out: optional pointer to receive the translated ID.
+ *
+ * Given a device requester ID, look up the appropriate implementation-defined
+ * platform ID and/or the target device which receives transactions on that
+ * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
+ * @id_out may be NULL if only the other is required. If @target points to
+ * a non-NULL device node pointer, only entries targeting that node will be
+ * matched; if it points to a NULL value, it will receive the device node of
+ * the first matching target phandle, with a reference held.
+ *
+ * Return: 0 on success or a standard error code on failure.
+ */
+int of_map_rid(struct device_node *np, u32 rid,
+ const char *map_name, const char *map_mask_name,
+ struct device_node **target, u32 *id_out)
+{
+ u32 map_mask, masked_rid;
+ int map_len;
+ const __be32 *map = NULL;
+
+ if (!np || !map_name || (!target && !id_out))
+ return -EINVAL;
+
+ map = of_get_property(np, map_name, &map_len);
+ if (!map) {
+ if (target)
+ return -ENODEV;
+ /* Otherwise, no map implies no translation */
+ *id_out = rid;
+ return 0;
+ }
+
+ if (!map_len || map_len % (4 * sizeof(*map))) {
+ pr_err("%pOF: Error: Bad %s length: %d\n", np,
+ map_name, map_len);
+ return -EINVAL;
+ }
+
+ /* The default is to select all bits. */
+ map_mask = 0xffffffff;
+
+ /*
+ * Can be overridden by "{iommu,msi}-map-mask" property.
+ */
+ if (map_mask_name)
+ of_property_read_u32(np, map_mask_name, &map_mask);
+
+ masked_rid = map_mask & rid;
+ for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
+ struct device_node *phandle_node;
+ u32 rid_base = be32_to_cpup(map + 0);
+ u32 phandle = be32_to_cpup(map + 1);
+ u32 out_base = be32_to_cpup(map + 2);
+ u32 rid_len = be32_to_cpup(map + 3);
+
+ if (rid_base & ~map_mask) {
+ pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
+ np, map_name, map_name,
+ map_mask, rid_base);
+ return -EFAULT;
+ }
+
+ if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
+ continue;
+
+ phandle_node = of_find_node_by_phandle(phandle);
+ if (!phandle_node)
+ return -ENODEV;
+
+ if (target) {
+ if (*target)
+ of_node_put(phandle_node);
+ else
+ *target = phandle_node;
+
+ if (*target != phandle_node)
+ continue;
+ }
+
+ if (id_out)
+ *id_out = masked_rid - rid_base + out_base;
+
+ pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
+ np, map_name, map_mask, rid_base, out_base,
+ rid_len, rid, masked_rid - rid_base + out_base);
+ return 0;
+ }
+
+ pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n",
+ np, map_name, rid, target && *target ? *target : NULL);
+ return -EFAULT;
+}
+
struct of_pci_iommu_alias_info {
struct device *dev;
struct device_node *np;
@@ -149,9 +249,9 @@ static int of_pci_iommu_init(struct pci_dev *pdev, u16 alias, void *data)
struct of_phandle_args iommu_spec = { .args_count = 1 };
int err;
- err = of_pci_map_rid(info->np, alias, "iommu-map",
- "iommu-map-mask", &iommu_spec.np,
- iommu_spec.args);
+ err = of_map_rid(info->np, alias, "iommu-map",
+ "iommu-map-mask", &iommu_spec.np,
+ iommu_spec.args);
if (err)
return err == -ENODEV ? NO_IOMMU : err;
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 02ad93a..b72eeec 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -22,7 +22,7 @@
#include <linux/module.h>
#include <linux/of.h>
#include <linux/of_irq.h>
-#include <linux/of_pci.h>
+#include <linux/of_iommu.h>
#include <linux/string.h>
#include <linux/slab.h>
@@ -588,8 +588,8 @@ static u32 __of_msi_map_rid(struct device *dev, struct device_node **np,
* "msi-map" property.
*/
for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
- if (!of_pci_map_rid(parent_dev->of_node, rid_in, "msi-map",
- "msi-map-mask", np, &rid_out))
+ if (!of_map_rid(parent_dev->of_node, rid_in, "msi-map",
+ "msi-map-mask", np, &rid_out))
break;
return rid_out;
}
diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index a28355c..d2cebbe 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -362,107 +362,6 @@ int of_pci_get_host_bridge_resources(struct device_node *dev,
EXPORT_SYMBOL_GPL(of_pci_get_host_bridge_resources);
#endif /* CONFIG_OF_ADDRESS */
-/**
- * of_pci_map_rid - Translate a requester ID through a downstream mapping.
- * @np: root complex device node.
- * @rid: PCI requester ID to map.
- * @map_name: property name of the map to use.
- * @map_mask_name: optional property name of the mask to use.
- * @target: optional pointer to a target device node.
- * @id_out: optional pointer to receive the translated ID.
- *
- * Given a PCI requester ID, look up the appropriate implementation-defined
- * platform ID and/or the target device which receives transactions on that
- * ID, as per the "iommu-map" and "msi-map" bindings. Either of @target or
- * @id_out may be NULL if only the other is required. If @target points to
- * a non-NULL device node pointer, only entries targeting that node will be
- * matched; if it points to a NULL value, it will receive the device node of
- * the first matching target phandle, with a reference held.
- *
- * Return: 0 on success or a standard error code on failure.
- */
-int of_pci_map_rid(struct device_node *np, u32 rid,
- const char *map_name, const char *map_mask_name,
- struct device_node **target, u32 *id_out)
-{
- u32 map_mask, masked_rid;
- int map_len;
- const __be32 *map = NULL;
-
- if (!np || !map_name || (!target && !id_out))
- return -EINVAL;
-
- map = of_get_property(np, map_name, &map_len);
- if (!map) {
- if (target)
- return -ENODEV;
- /* Otherwise, no map implies no translation */
- *id_out = rid;
- return 0;
- }
-
- if (!map_len || map_len % (4 * sizeof(*map))) {
- pr_err("%pOF: Error: Bad %s length: %d\n", np,
- map_name, map_len);
- return -EINVAL;
- }
-
- /* The default is to select all bits. */
- map_mask = 0xffffffff;
-
- /*
- * Can be overridden by "{iommu,msi}-map-mask" property.
- * If of_property_read_u32() fails, the default is used.
- */
- if (map_mask_name)
- of_property_read_u32(np, map_mask_name, &map_mask);
-
- masked_rid = map_mask & rid;
- for ( ; map_len > 0; map_len -= 4 * sizeof(*map), map += 4) {
- struct device_node *phandle_node;
- u32 rid_base = be32_to_cpup(map + 0);
- u32 phandle = be32_to_cpup(map + 1);
- u32 out_base = be32_to_cpup(map + 2);
- u32 rid_len = be32_to_cpup(map + 3);
-
- if (rid_base & ~map_mask) {
- pr_err("%pOF: Invalid %s translation - %s-mask (0x%x) ignores rid-base (0x%x)\n",
- np, map_name, map_name,
- map_mask, rid_base);
- return -EFAULT;
- }
-
- if (masked_rid < rid_base || masked_rid >= rid_base + rid_len)
- continue;
-
- phandle_node = of_find_node_by_phandle(phandle);
- if (!phandle_node)
- return -ENODEV;
-
- if (target) {
- if (*target)
- of_node_put(phandle_node);
- else
- *target = phandle_node;
-
- if (*target != phandle_node)
- continue;
- }
-
- if (id_out)
- *id_out = masked_rid - rid_base + out_base;
-
- pr_debug("%pOF: %s, using mask %08x, rid-base: %08x, out-base: %08x, length: %08x, rid: %08x -> %08x\n",
- np, map_name, map_mask, rid_base, out_base,
- rid_len, rid, masked_rid - rid_base + out_base);
- return 0;
- }
-
- pr_err("%pOF: Invalid %s translation - no match for rid 0x%x on %pOF\n",
- np, map_name, rid, target && *target ? *target : NULL);
- return -EFAULT;
-}
-
#if IS_ENABLED(CONFIG_OF_IRQ)
/**
* of_irq_parse_pci - Resolve the interrupt for a PCI device
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 4fa654e..432b53c 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -15,6 +15,10 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
extern const struct iommu_ops *of_iommu_configure(struct device *dev,
struct device_node *master_np);
+int of_map_rid(struct device_node *np, u32 rid,
+ const char *map_name, const char *map_mask_name,
+ struct device_node **target, u32 *id_out);
+
#else
static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
@@ -30,6 +34,13 @@ static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
return NULL;
}
+static inline int of_map_rid(struct device_node *np, u32 rid,
+ const char *map_name, const char *map_mask_name,
+ struct device_node **target, u32 *id_out)
+{
+ return -EINVAL;
+}
+
#endif /* CONFIG_OF_IOMMU */
extern struct of_device_id __iommu_of_table;
diff --git a/include/linux/of_pci.h b/include/linux/of_pci.h
index 091033a..a23b44a 100644
--- a/include/linux/of_pci.h
+++ b/include/linux/of_pci.h
@@ -17,9 +17,6 @@ struct device_node *of_pci_find_child_device(struct device_node *parent,
int of_get_pci_domain_nr(struct device_node *node);
int of_pci_get_max_link_speed(struct device_node *node);
void of_pci_check_probe_only(void);
-int of_pci_map_rid(struct device_node *np, u32 rid,
- const char *map_name, const char *map_mask_name,
- struct device_node **target, u32 *id_out);
#else
static inline struct device_node *of_pci_find_child_device(struct device_node *parent,
unsigned int devfn)
@@ -44,13 +41,6 @@ static inline int of_pci_get_devfn(struct device_node *np)
return -1;
}
-static inline int of_pci_map_rid(struct device_node *np, u32 rid,
- const char *map_name, const char *map_mask_name,
- struct device_node **target, u32 *id_out)
-{
- return -EINVAL;
-}
-
static inline int
of_pci_get_max_link_speed(struct device_node *node)
{
--
1.9.1
^ permalink raw reply related
* [PATCH 1/6 v2] Docs: dt: add fsl-mc iommu-map device-tree binding
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1523960514-25457-1-git-send-email-nipun.gupta@nxp.com>
The existing IOMMU bindings cannot be used to specify the relationship
between fsl-mc devices and IOMMUs. This patch adds a generic binding for
mapping fsl-mc devices to IOMMUs, using iommu-map property.
Signed-off-by: Nipun Gupta <nipun.gupta@nxp.com>
---
.../devicetree/bindings/misc/fsl,qoriq-mc.txt | 39 ++++++++++++++++++++++
1 file changed, 39 insertions(+)
diff --git a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
index 6611a7c..8cbed4f 100644
--- a/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
+++ b/Documentation/devicetree/bindings/misc/fsl,qoriq-mc.txt
@@ -9,6 +9,25 @@ blocks that can be used to create functional hardware objects/devices
such as network interfaces, crypto accelerator instances, L2 switches,
etc.
+For an overview of the DPAA2 architecture and fsl-mc bus see:
+drivers/staging/fsl-mc/README.txt
+
+As described in the above overview, all DPAA2 objects in a DPRC share the
+same hardware "isolation context" and a 10-bit value called an ICID
+(isolation context id) is expressed by the hardware to identify
+the requester.
+
+The generic 'iommus' property is insufficient to describe the relationship
+between ICIDs and IOMMUs, so an iommu-map property is used to define
+the set of possible ICIDs under a root DPRC and how they map to
+an IOMMU.
+
+For generic IOMMU bindings, see
+Documentation/devicetree/bindings/iommu/iommu.txt.
+
+For arm-smmu binding, see:
+Documentation/devicetree/bindings/iommu/arm,smmu.txt.
+
Required properties:
- compatible
@@ -88,14 +107,34 @@ Sub-nodes:
Value type: <phandle>
Definition: Specifies the phandle to the PHY device node associated
with the this dpmac.
+Optional properties:
+
+- iommu-map: Maps an ICID to an IOMMU and associated iommu-specifier
+ data.
+
+ The property is an arbitrary number of tuples of
+ (icid-base,iommu,iommu-base,length).
+
+ Any ICID i in the interval [icid-base, icid-base + length) is
+ associated with the listed IOMMU, with the iommu-specifier
+ (i - icid-base + iommu-base).
Example:
+ smmu: iommu@5000000 {
+ compatible = "arm,mmu-500";
+ #iommu-cells = <2>;
+ stream-match-mask = <0x7C00>;
+ ...
+ };
+
fsl_mc: fsl-mc@80c000000 {
compatible = "fsl,qoriq-mc";
reg = <0x00000008 0x0c000000 0 0x40>, /* MC portal base */
<0x00000000 0x08340000 0 0x40000>; /* MC control reg */
msi-parent = <&its>;
+ /* define map for ICIDs 23-64 */
+ iommu-map = <23 &smmu 23 41>;
#address-cells = <3>;
#size-cells = <1>;
--
1.9.1
^ permalink raw reply related
* [PATCH 0/6 v2] Support for fsl-mc bus and its devices in SMMU
From: Nipun Gupta @ 2018-04-17 10:21 UTC (permalink / raw)
To: robin.murphy, will.deacon, mark.rutland, catalin.marinas
Cc: hch, gregkh, joro, robh+dt, m.szyprowski, shawnguo, frowand.list,
bhelgaas, iommu, linux-kernel, devicetree, linux-arm-kernel,
linuxppc-dev, linux-pci, bharat.bhushan, stuyoder,
laurentiu.tudor, leoyang.li, Nipun Gupta
In-Reply-To: <1520260166-29387-1-git-send-email-nipun.gupta@nxp.com>
This patchset defines IOMMU DT binding for fsl-mc bus and adds
support in SMMU for fsl-mc bus.
This patch series is dependent on patset:
https://patchwork.kernel.org/patch/10317337/
These patches
- Define property 'iommu-map' for fsl-mc bus (patch 1)
- Integrates the fsl-mc bus with the SMMU using this
IOMMU binding (patch 2,3,4)
- Adds the dma configuration support for fsl-mc bus (patch 5)
- Updates the fsl-mc device node with iommu/dma related changes (patch6)
Nipun Gupta (6):
Docs: dt: add fsl-mc iommu-map device-tree binding
iommu: of: make of_pci_map_rid() available for other devices too
iommu: support iommu configuration for fsl-mc devices
iommu: arm-smmu: Add support for the fsl-mc bus
bus: fsl-mc: supoprt dma configure for devices on fsl-mc bus
arm64: dts: ls208xa: comply with the iommu map binding for fsl_mc
Changes in v2:
- use iommu-map property for fsl-mc bus
- rebase over patchset https://patchwork.kernel.org/patch/10317337/
and make corresponding changes for dma configuration of devices on
fsl-mc bus
.../devicetree/bindings/misc/fsl,qoriq-mc.txt | 39 +++++++
arch/arm64/boot/dts/freescale/fsl-ls208xa.dtsi | 6 +-
drivers/bus/fsl-mc/fsl-mc-bus.c | 16 ++-
drivers/iommu/arm-smmu.c | 7 ++
drivers/iommu/iommu.c | 21 ++++
drivers/iommu/of_iommu.c | 126 ++++++++++++++++++++-
drivers/of/irq.c | 6 +-
drivers/pci/of.c | 101 -----------------
include/linux/fsl/mc.h | 8 ++
include/linux/iommu.h | 2 +
include/linux/of_iommu.h | 11 ++
include/linux/of_pci.h | 10 --
12 files changed, 231 insertions(+), 122 deletions(-)
--
1.9.1
^ permalink raw reply
* Re: [1/5] powerpc/lib: Fix off-by-one in alternate feature patching
From: Michael Ellerman @ 2018-04-17 10:13 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev; +Cc: aik, paulus
In-Reply-To: <20180416143905.2716-1-mpe@ellerman.id.au>
On Mon, 2018-04-16 at 14:39:01 UTC, Michael Ellerman wrote:
> When we patch an alternate feature section, we have to adjust any
> relative branches that branch out of the alternate section.
>
> But currently we have a bug if we have a branch that points to past
> the last instruction of the alternate section, eg:
>
> FTR_SECTION_ELSE
> 1: b 2f
> or 6,6,6
> 2:
> ALT_FTR_SECTION_END(...)
> nop
>
> This will result in a relative branch at 1 with a target that equals
> the end of the alternate section.
>
> That branch does not need adjusting when it's moved to the non-else
> location. Currently we do adjust it, resulting in a branch that goes
> off into the link-time location of the else section, which is junk.
>
> The fix is to not patch branches that have a target == end of the
> alternate section.
>
> Fixes: d20fe50a7b3c ("KVM: PPC: Book3S HV: Branch inside feature section")
> Fixes: 9b1a735de64c ("powerpc: Add logic to patch alternative feature sections")
> Cc: stable@vger.kernel.org # v2.6.27+
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Applied to powerpc fixes.
https://git.kernel.org/powerpc/c/b8858581febb050688e276b956796b
cheers
^ permalink raw reply
* Re: powerpc/64s: Default l1d_size to 64K in RFI fallback flush
From: Michael Ellerman @ 2018-04-17 10:13 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev; +Cc: maddy
In-Reply-To: <20180417014920.21450-1-mpe@ellerman.id.au>
On Tue, 2018-04-17 at 01:49:20 UTC, Michael Ellerman wrote:
> From: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
>
> If there is no d-cache-size property in the device tree, l1d_size could
> be zero. We don't actually expect that to happen, it's only been seen
> on mambo (simulator) in some configurations.
>
> A zero-size l1d_size leads to the loop in the asm wrapping around to
> 2^64-1, and then walking off the end of the fallback area and
> eventually causing a page fault which is fatal.
>
> Just default to 64K which is correct on some CPUs, and sane enough to
> not cause a crash on others.
>
> Fixes: aa8a5e0062ac9 ('powerpc/64s: Add support for RFI flush of L1-D cache')
> Signed-off-by: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
> [mpe: Rewrite comment and change log]
> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Applied to powerpc fixes.
https://git.kernel.org/powerpc/c/9dfbf78e4114fcaf4ef61c49885c3a
cheers
^ permalink raw reply
* [RESEND PATCH 3/3] powerpc: dts: use a correct at24 compatible fallback in ac14xx
From: Bartosz Golaszewski @ 2018-04-17 9:40 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, David S . Miller, Holger Brunck
Cc: devicetree, linuxppc-dev, linux-kernel, Bartosz Golaszewski
In-Reply-To: <20180417094030.7224-1-brgl@bgdev.pl>
Using 'at24' as fallback is now deprecated - use the full
'atmel,<model>' string.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
arch/powerpc/boot/dts/ac14xx.dts | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/arch/powerpc/boot/dts/ac14xx.dts b/arch/powerpc/boot/dts/ac14xx.dts
index 83bcfd865167..0be5c4f3265d 100644
--- a/arch/powerpc/boot/dts/ac14xx.dts
+++ b/arch/powerpc/boot/dts/ac14xx.dts
@@ -176,12 +176,12 @@
clock-frequency = <400000>;
at24@30 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x30>;
};
at24@31 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x31>;
};
@@ -191,42 +191,42 @@
};
at24@50 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x50>;
};
at24@51 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x51>;
};
at24@52 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x52>;
};
at24@53 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x53>;
};
at24@54 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x54>;
};
at24@55 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x55>;
};
at24@56 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x56>;
};
at24@57 {
- compatible = "at24,24c01";
+ compatible = "atmel,24c01";
reg = <0x57>;
};
--
2.17.0
^ permalink raw reply related
* [RESEND PATCH 2/3] powerpc: dts: use 'atmel' as at24 manufacturer for kmcent2
From: Bartosz Golaszewski @ 2018-04-17 9:40 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, David S . Miller, Holger Brunck
Cc: devicetree, linuxppc-dev, linux-kernel, Bartosz Golaszewski
In-Reply-To: <20180417094030.7224-1-brgl@bgdev.pl>
Using compatible strings without the <manufacturer> part for at24 is
now deprecated. Use a correct 'atmel,<model>' value.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
arch/powerpc/boot/dts/fsl/kmcent2.dts | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/boot/dts/fsl/kmcent2.dts b/arch/powerpc/boot/dts/fsl/kmcent2.dts
index 5922c1ea0e96..3094df05f5ea 100644
--- a/arch/powerpc/boot/dts/fsl/kmcent2.dts
+++ b/arch/powerpc/boot/dts/fsl/kmcent2.dts
@@ -130,7 +130,7 @@
#size-cells = <0>;
eeprom@54 {
- compatible = "24c02";
+ compatible = "atmel,24c02";
reg = <0x54>;
pagesize = <2>;
read-only;
--
2.17.0
^ permalink raw reply related
* [RESEND PATCH 1/3] powerpc: dts: use 'atmel' as at24 anufacturer for pdm360ng
From: Bartosz Golaszewski @ 2018-04-17 9:40 UTC (permalink / raw)
To: Rob Herring, Mark Rutland, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, David S . Miller, Holger Brunck
Cc: devicetree, linuxppc-dev, linux-kernel, Bartosz Golaszewski
Using 'at' as the <manufacturer> part of the compatible string is now
deprecated. Use a correct string: 'atmel,<model>'.
Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
---
arch/powerpc/boot/dts/pdm360ng.dts | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/powerpc/boot/dts/pdm360ng.dts b/arch/powerpc/boot/dts/pdm360ng.dts
index 445b88114009..df1283b63d9b 100644
--- a/arch/powerpc/boot/dts/pdm360ng.dts
+++ b/arch/powerpc/boot/dts/pdm360ng.dts
@@ -98,7 +98,7 @@
fsl,preserve-clocking;
eeprom@50 {
- compatible = "at,24c01";
+ compatible = "atmel,24c01";
reg = <0x50>;
};
--
2.17.0
^ permalink raw reply related
* Re: [PATCH] powerpc/misc: get rid of add_reloc_offset()
From: Paul Mackerras @ 2018-04-17 9:30 UTC (permalink / raw)
To: Christophe Leroy
Cc: Benjamin Herrenschmidt, Michael Ellerman, linux-kernel,
linuxppc-dev
In-Reply-To: <20180417075624.962AB6C038@po15720vm.idsi0.si.c-s.fr>
On Tue, Apr 17, 2018 at 09:56:24AM +0200, Christophe Leroy wrote:
> add_reloc_offset() is almost redundant with reloc_offset()
>
> Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
> ---
> arch/powerpc/include/asm/setup.h | 3 +--
> arch/powerpc/kernel/misc.S | 16 ----------------
> arch/powerpc/kernel/prom_init_check.sh | 2 +-
> 3 files changed, 2 insertions(+), 19 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
> index 27fa52ed6d00..115e0896ffa7 100644
> --- a/arch/powerpc/include/asm/setup.h
> +++ b/arch/powerpc/include/asm/setup.h
> @@ -17,10 +17,9 @@ extern void note_scsi_host(struct device_node *, void *);
>
> /* Used in very early kernel initialization. */
> extern unsigned long reloc_offset(void);
> -extern unsigned long add_reloc_offset(unsigned long);
> extern void reloc_got2(unsigned long);
>
> -#define PTRRELOC(x) ((typeof(x)) add_reloc_offset((unsigned long)(x)))
> +#define PTRRELOC(x) ((typeof(x)) ((unsigned long)(x) + reloc_offset()))
NAK. This is how it used to be, and we changed it in order to prevent
gcc from making incorrect assumptions. If you use the form with the
explicit addition, and x is the address of an array, gcc will assume
that the result is within the bounds of the array (apparently the C
standard says it can do that) and potentially generate incorrect
code. I recall that we had an actual case where gcc was generating
incorrect code, though I don't recall the details, as this was some
time before 2002.
Paul.
^ permalink raw reply
* Re: [PATCH 1/2] powernv/npu: Do a PID GPU TLB flush when invalidating a large address range
From: Balbir Singh @ 2018-04-17 9:17 UTC (permalink / raw)
To: Alistair Popple
Cc: open list:LINUX FOR POWERPC (32-BIT AND 64-BIT), Michael Ellerman,
Mark Hairgrove, arbab
In-Reply-To: <20180417091129.23069-1-alistair@popple.id.au>
On Tue, Apr 17, 2018 at 7:11 PM, Alistair Popple <alistair@popple.id.au> wrote:
> The NPU has a limited number of address translation shootdown (ATSD)
> registers and the GPU has limited bandwidth to process ATSDs. This can
> result in contention of ATSD registers leading to soft lockups on some
> threads, particularly when invalidating a large address range in
> pnv_npu2_mn_invalidate_range().
>
> At some threshold it becomes more efficient to flush the entire GPU TLB for
> the given MM context (PID) than individually flushing each address in the
> range. This patch will result in ranges greater than 2MB being converted
> from 32+ ATSDs into a single ATSD which will flush the TLB for the given
> PID on each GPU.
>
> Signed-off-by: Alistair Popple <alistair@popple.id.au>
> ---
> arch/powerpc/platforms/powernv/npu-dma.c | 23 +++++++++++++++++++----
> 1 file changed, 19 insertions(+), 4 deletions(-)
>
> diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
> index 94801d8e7894..dc34662e9df9 100644
> --- a/arch/powerpc/platforms/powernv/npu-dma.c
> +++ b/arch/powerpc/platforms/powernv/npu-dma.c
> @@ -40,6 +40,13 @@
> DEFINE_SPINLOCK(npu_context_lock);
>
> /*
> + * When an address shootdown range exceeds this threshold we invalidate the
> + * entire TLB on the GPU for the given PID rather than each specific address in
> + * the range.
> + */
> +#define ATSD_THRESHOLD (2*1024*1024)
> +
> +/*
> * Other types of TCE cache invalidation are not functional in the
> * hardware.
> */
> @@ -675,11 +682,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
> struct npu_context *npu_context = mn_to_npu_context(mn);
> unsigned long address;
>
> - for (address = start; address < end; address += PAGE_SIZE)
> - mmio_invalidate(npu_context, 1, address, false);
> + if (end - start > ATSD_THRESHOLD) {
I'm nitpicking, but (end - start) > ATSD_THRESHOLD is clearer
> + /*
> + * Just invalidate the entire PID if the address range is too
> + * large.
> + */
> + mmio_invalidate(npu_context, 0, 0, true);
> + } else {
> + for (address = start; address < end; address += PAGE_SIZE)
> + mmio_invalidate(npu_context, 1, address, false);
>
> - /* Do the flush only on the final addess == end */
> - mmio_invalidate(npu_context, 1, address, true);
> + /* Do the flush only on the final addess == end */
> + mmio_invalidate(npu_context, 1, address, true);
> + }
> }
>
Acked-by: Balbir Singh <bsingharora@gmail.com>
^ permalink raw reply
* [PATCH 2/2] powernv/npu: Add a debugfs setting to change ATSD threshold
From: Alistair Popple @ 2018-04-17 9:11 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: mhairgrove, arbab, bsingharora, Alistair Popple
In-Reply-To: <20180417091129.23069-1-alistair@popple.id.au>
The threshold at which it becomes more efficient to coalesce a range of
ATSDs into a single per-PID ATSD is currently not well understood due to a
lack of real-world work loads. This patch adds a debugfs parameter allowing
the threshold to be altered at runtime in order to aid future development
and refinement of the value.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
---
arch/powerpc/platforms/powernv/npu-dma.c | 12 ++++++++++--
1 file changed, 10 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index dc34662e9df9..a765bf576c14 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -17,7 +17,9 @@
#include <linux/pci.h>
#include <linux/memblock.h>
#include <linux/iommu.h>
+#include <linux/debugfs.h>
+#include <asm/debugfs.h>
#include <asm/tlb.h>
#include <asm/powernv.h>
#include <asm/reg.h>
@@ -44,7 +46,8 @@ DEFINE_SPINLOCK(npu_context_lock);
* entire TLB on the GPU for the given PID rather than each specific address in
* the range.
*/
-#define ATSD_THRESHOLD (2*1024*1024)
+static uint64_t atsd_threshold = 2 * 1024 * 1024;
+static struct dentry *atsd_threshold_dentry;
/*
* Other types of TCE cache invalidation are not functional in the
@@ -682,7 +685,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- if (end - start > ATSD_THRESHOLD) {
+ if (end - start > atsd_threshold) {
/*
* Just invalidate the entire PID if the address range is too
* large.
@@ -956,6 +959,11 @@ int pnv_npu2_init(struct pnv_phb *phb)
static int npu_index;
uint64_t rc = 0;
+ if (!atsd_threshold_dentry) {
+ atsd_threshold_dentry = debugfs_create_x64("atsd_threshold",
+ 0600, powerpc_debugfs_root, &atsd_threshold);
+ }
+
phb->npu.nmmu_flush =
of_property_read_bool(phb->hose->dn, "ibm,nmmu-flush");
for_each_child_of_node(phb->hose->dn, dn) {
--
2.11.0
^ permalink raw reply related
* [PATCH 1/2] powernv/npu: Do a PID GPU TLB flush when invalidating a large address range
From: Alistair Popple @ 2018-04-17 9:11 UTC (permalink / raw)
To: linuxppc-dev, mpe; +Cc: mhairgrove, arbab, bsingharora, Alistair Popple
The NPU has a limited number of address translation shootdown (ATSD)
registers and the GPU has limited bandwidth to process ATSDs. This can
result in contention of ATSD registers leading to soft lockups on some
threads, particularly when invalidating a large address range in
pnv_npu2_mn_invalidate_range().
At some threshold it becomes more efficient to flush the entire GPU TLB for
the given MM context (PID) than individually flushing each address in the
range. This patch will result in ranges greater than 2MB being converted
from 32+ ATSDs into a single ATSD which will flush the TLB for the given
PID on each GPU.
Signed-off-by: Alistair Popple <alistair@popple.id.au>
---
arch/powerpc/platforms/powernv/npu-dma.c | 23 +++++++++++++++++++----
1 file changed, 19 insertions(+), 4 deletions(-)
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 94801d8e7894..dc34662e9df9 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -40,6 +40,13 @@
DEFINE_SPINLOCK(npu_context_lock);
/*
+ * When an address shootdown range exceeds this threshold we invalidate the
+ * entire TLB on the GPU for the given PID rather than each specific address in
+ * the range.
+ */
+#define ATSD_THRESHOLD (2*1024*1024)
+
+/*
* Other types of TCE cache invalidation are not functional in the
* hardware.
*/
@@ -675,11 +682,19 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct npu_context *npu_context = mn_to_npu_context(mn);
unsigned long address;
- for (address = start; address < end; address += PAGE_SIZE)
- mmio_invalidate(npu_context, 1, address, false);
+ if (end - start > ATSD_THRESHOLD) {
+ /*
+ * Just invalidate the entire PID if the address range is too
+ * large.
+ */
+ mmio_invalidate(npu_context, 0, 0, true);
+ } else {
+ for (address = start; address < end; address += PAGE_SIZE)
+ mmio_invalidate(npu_context, 1, address, false);
- /* Do the flush only on the final addess == end */
- mmio_invalidate(npu_context, 1, address, true);
+ /* Do the flush only on the final addess == end */
+ mmio_invalidate(npu_context, 1, address, true);
+ }
}
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
--
2.11.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox