On Thu, Jan 16, 2020 at 07:11:36AM +0100, Christophe Leroy wrote:
> Hi Segher,
>
> I'm trying to see if we could enhance TCP checksum calculations by splitting
> inline assembly blocks to give GCC the opportunity to mix it with other
> stuff, but I'm getting difficulties with the carry.
>
> As fa
Hi Michael,
On 15/01/20 12:37 pm, Michael Ellerman wrote:
> Sandipan Das writes:
>> Both 4K and 64K pages are supported on powerpc. Parts of
>> the selftest code perform alignment computations based on
>> the PAGE_SIZE macro which is currently hardcoded to 64K
>> for powerpc. This causes some tes
Hello,
I am having an important trouble while communicating with my PCI Endpoint
devices MMIO. I am using T1042D4RDB-64B. PowerPC e5500 processor with
kernel version 4.19 and default PCI driver is 'pcieport'. Kernel is built
with Yocto 2.7.
I have a FPGA memory controller card which is programmed
Thomas, Andy,
Le 15/01/2020 à 07:15, Christophe Leroy a écrit :
Le 15/01/2020 à 00:06, Thomas Gleixner a écrit :
Christophe Leroy writes:
static __maybe_unused int
+#ifdef VDSO_GETS_VD_PTR_FROM_ARCH
+__cvdso_clock_gettime_common(const struct vdso_data *vd, clockid_t
clock,
+
On Thu, Jan 16, 2020 at 8:30 AM Thomas Gleixner wrote:
>
> Hsin-Yi Wang writes:
>
> > Currently system reboots uses architecture specific codes (smp_send_stop)
> > to offline non reboot CPUs. Most architecture's implementation is looping
> > through all non reboot online CPUs and call ipi functio
https://bugzilla.kernel.org/show_bug.cgi?id=205283
--- Comment #11 from Christophe Leroy (christophe.le...@c-s.fr) ---
Series at https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=153133
drops the buggy module_alloc() and forces CONFIG_KASAN_VMALLOC when
CONFIG_MODULES is selected.
--
On Wed, Jan 15, 2020 at 7:41 PM Sudeep Holla wrote:
>
> On Wed, Jan 15, 2020 at 02:34:10PM +0800, Hsin-Yi Wang wrote:
> > Currently system reboots uses architecture specific codes (smp_send_stop)
> > to offline non reboot CPUs. Most architecture's implementation is looping
> > through all non rebo
Le 09/01/2020 à 08:08, Daniel Axtens a écrit :
Building on the work of Christophe, Aneesh and Balbir, I've ported
KASAN to 64-bit Book3S kernels running on the Radix MMU.
This provides full inline instrumentation on radix, but does require
that you be able to specify the amount of physically
On Wed, Jan 15, 2020 at 01:19:41PM -0800, John Hubbard wrote:
> On 1/15/20 7:23 AM, Christoph Hellwig wrote:
> ...
> >
> > I'm really not sold on this scheme. Note that I think it is
> > particularly bad, but it also doesn't seem any better than what
> > we had before, and it introduced quite a b
>> You might want to use 'git tag --contains':
>>
>> [greg@bahia kernel-linus]$ git tag --contains da15c03b047d
>> for-linus
>> kvm-5.4-2
>> next-20191118
>> next-20191126
>> tags/kvm-5.4-1
>> tags/kvm-5.4-2
>> v5.4
>> v5.4-rc1
>
> Or:
>
> $ git describe --match "v[0-9]*" --contains da15c03b047
Christophe Leroy writes:
> Le 15/01/2020 à 07:15, Christophe Leroy a écrit :
> From your point of view, what should I do:
> A/ __arch_get_vdso_data() handled entirely at arch level and arches
> handing over the vdso data pointer to generic C VDSO functions all the
> time (as in my v2 series) ?
In KVM guests drmem structure is only zero initialized. Trying to
manipulate DLPAR parameters results in a crash in this environment.
$ echo "memory add count 1" > /sys/kernel/dlpar
Oops: Kernel access of bad area, sig: 11 [#1]
LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
Modules linked
Hi All,
We still need the attached patch for our onboard SD card interface
[1,2]. Could you please add this patch to the tree?
Thanks,
Christian
[1] https://www.spinics.net/lists/linux-mmc/msg56211.html
[2]
http://forum.hyperion-entertainment.com/viewtopic.php?f=58&t=4349&start=20#p49012
d
Hsin-Yi Wang writes:
> On Thu, Jan 16, 2020 at 8:30 AM Thomas Gleixner wrote:
> We saw this issue on regular reboot (not panic) on arm64: If tick
> broadcast and smp_send_stop() happen together and the first broadcast
> arrives to some idled CPU that hasn't already executed reboot ipi to
> run in
On Thu, Jan 16, 2020 at 09:06:08AM +0100, Gabriel Paubert wrote:
> On Thu, Jan 16, 2020 at 07:11:36AM +0100, Christophe Leroy wrote:
> > Hi Segher,
> >
> > I'm trying to see if we could enhance TCP checksum calculations by splitting
> > inline assembly blocks to give GCC the opportunity to mix it
Hi!
On Thu, Jan 16, 2020 at 07:11:36AM +0100, Christophe Leroy wrote:
> I'm trying to see if we could enhance TCP checksum calculations by
> splitting inline assembly blocks to give GCC the opportunity to mix it
> with other stuff, but I'm getting difficulties with the carry.
>
> As far as I ca
On Thu, 16 Jan 2020 at 12:18, Christian Zigotzky wrote:
>
> Hi All,
>
> We still need the attached patch for our onboard SD card interface
> [1,2]. Could you please add this patch to the tree?
No, because according to previous discussion that isn't the correct
solution and more importantly it wil
From: Christophe Leroy
> Sent: 16 January 2020 06:12
>
> I'm trying to see if we could enhance TCP checksum calculations by
> splitting inline assembly blocks to give GCC the opportunity to mix it
> with other stuff, but I'm getting difficulties with the carry.
if you are trying to 'loop carry' t
Hi!
On Thu, Jan 16, 2020 at 03:54:58PM +, David Laight wrote:
> if you are trying to 'loop carry' the 'carry flag' with 'add with carry'
> instructions you'll almost certainly need to write the loop in asm.
> Since the loop itself is simple, this probably doesn't matter.
Agreed.
> However a
From: Shengjiu Wang
[ Upstream commit 35dac627471938eda89fa39ee4ead1f7667e0f57 ]
xrun may happen at the end of stream, the
trigger->fsl_esai_trigger_stop maybe called in the middle of
fsl_esai_hw_reset, this may cause esai in wrong state
after stop, and there may be endless xrun interrupt.
This
From: Geert Uytterhoeven
[ Upstream commit 3b05a1e517e1a8cfda4866ec31d28b2bc4fee4c4 ]
"powerpc_security_features" is "unsigned long", i.e. 32-bit or 64-bit,
depending on the platform (PPC_FSL_BOOK3E or PPC_BOOK3S_64). Hence
casting its address to "u64 *", and calling debugfs_create_x64() is
wro
From: Segher Boessenkool
> Sent: 16 January 2020 16:22
...
> > However a loop of 'add with carry' instructions may not be the
> > fastest code by any means.
> > Because the carry flag is needed for every 'adc' you can't do more
> > that one adc per clock.
> > This limits you to 8 bytes/clock on a 6
From: Oliver O'Halloran
[ Upstream commit 9d72dcef891030545f39ad386a30cf91df517fb2 ]
On PowerNV the PCIe topology is (currently) managed by the powernv platform
code in Linux in cooperation with the platform firmware. Linux's native
PCIe port service drivers operate independently of both and thi
From: Christophe Leroy
[ Upstream commit 71eb40fc53371bc247c8066ae76ad9e22ae1e18d ]
When enabling CONFIG_RELOCATABLE and CONFIG_KASAN on FSL_BOOKE,
the kernel doesn't boot.
relocate_init() requires KASAN early shadow area to be set up because
it needs access to the device tree through generic f
From: Ard Biesheuvel
[ Upstream commit b6afd1234cf93aa0d71b4be4788c47534905f0be ]
Commit 01c9348c7620ec65
powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*
updated arch_get_random_[int|long]() to be NOPs, and moved the hardware
RNG backing to arch_get_random_seed_[in
From: Nicholas Mc Guire
[ Upstream commit 4ab2b48c98f2ec9712452d520a381917f91ac3d2 ]
The allocation with fsl_alloc_request() and kmalloc() were unchecked
fixed this up with a NULL check and appropriate cleanup.
Additionally udc->ep_qh_size was reset to 0 on failure of allocation.
Similar udc->p
From: YueHaibing
[ Upstream commit b45e9d761ba2d60044b610297e3ef9f947ac157f ]
The variable 'aa_index' is defined as an unsigned value in
update_lmb_associativity_index(), but find_aa_index() may return -1
when dlpar_clone_property() fails. So change find_aa_index() to return
a bool, which indica
From: Christophe Leroy
[ Upstream commit fb978ca207743badfe7efd9eebe68bcbb4969f79 ]
Generic implementation fails to remove breakpoints after init
when CONFIG_STRICT_KERNEL_RWX is selected:
[ 13.251285] KGDB: BP remove failed: c001c338
[ 13.259587] kgdbts: ERROR PUT: end of test buffer on 'd
Hi Christophe,
Christophe Leroy writes:
> To properly handle errors returned by gettimeofday(), the
> DO_VDSO_CALL() macro has to be used, otherwise vdsotest
> misinterpret VDSO function return on error.
>
> This has gone unnoticed until now because the powerpc VDSO
> gettimeofday() always succee
From: Stefan Agner
[ Upstream commit d9866572486802bc598a3e8576a5231378d190de ]
Make sure to properly put the of node in case finding the codec
fails.
Fixes: 81e8e4926167 ("ASoC: fsl: add sgtl5000 clock support for imx-sgtl5000")
Signed-off-by: Stefan Agner
Reviewed-by: Daniel Baluta
Acked-by
From: Alexey Kardashevskiy
[ Upstream commit a67614cc05a5052b265ea48196dab2fce11f5f2e ]
The SPAPR TCE KVM device references all hardware IOMMU tables assigned to
some IOMMU group to ensure that in-kernel KVM acceleration of H_PUT_TCE
can work. The tables are references when an IOMMU group gets r
From: Michael Ellerman
[ Upstream commit 8cfaf106918a8c13abb24c641556172afbb9545c ]
In cpufeatures_process_feature(), if a provided CPU feature is unknown and
enable_unknown is false, we erroneously print that the feature is being
enabled and return true, even though no feature has been enabled,
From: Rashmica Gupta
[ Upstream commit 790845e2f12709d273d08ea7a2af7c2593689519 ]
We were always calling base_hpte_find() with primary = true,
even when we wanted to check the secondary table.
mpe: I broke this when refactoring Rashmica's original patch.
Fixes: 1515ab932156 ("powerpc/mm: Dump
From: Dan Carpenter
[ Upstream commit 5674a92ca4b7e5a6a19231edd10298d30324cd27 ]
We forgot to set "err" on this error path.
Fixes: 1a2d397a6eb5 ("gpio/powerpc: Eliminate duplication of
of_get_named_gpio_flags()")
Signed-off-by: Dan Carpenter
Signed-off-by: Li Yang
Signed-off-by: Sasha Levin
From: Ben Hutchings
[ Upstream commit ff6d27823f619892ab96f7461764840e0d786b15 ]
The 32-bit vDSO is not needed and not normally built for 64-bit
little-endian configurations. However, the vdso_install target still
builds and installs it. Add the same config condition as is normally
used for th
From: Alexey Kardashevskiy
[ Upstream commit 3309bec85e60d60d6394802cb8e183a4f4a72def ]
The trace_hardirqs_on() sets current->hardirqs_enabled and from here
the lockdep assumes interrupts are enabled although they are remain
disabled until the context switches to the guest. Consequent
srcu_read_
From: Nathan Lynch
[ Upstream commit d4aa219a074a5abaf95a756b9f0d190b5c03a945 ]
Allow external callers to force the cacheinfo code to release all its
references to cache nodes, e.g. before processing device tree updates
post-migration, and to rebuild the hierarchy afterward.
CPU online/offline
From: Nathan Lynch
[ Upstream commit e610a466d16a086e321f0bd421e2fc75cff28605 ]
It's common for the platform to replace the cache device nodes after a
migration. Since the cacheinfo code is never informed about this, it
never drops its references to the source system's cache nodes, causing
it to
From: Ravi Bangoria
[ Upstream commit 913a90bc5a3a06b1f04c337320e9aeee2328dd77 ]
perf_event_open() limits the sample_period to 63 bits. See:
0819b2e30ccb ("perf: Limit perf_event_attr::sample_period to 63 bits")
Make ioctl() consistent with it.
Also on PowerPC, negative sample_period could
From: Johannes Berg
[ Upstream commit f474808acb3c4b30552d9c59b181244e0300d218 ]
A lot of places in the driver use onyx_read_register() without
checking the return value, and it's been working OK for ~10 years
or so, so probably never fails ... Rather than trying to check the
return value everyw
From: Nicholas Piggin
[ Upstream commit 31f210cf42d4b308eacef89b6cb0b1459338b8de ]
create_physical_mapping expects physical addresses, but splitting
these mapping on hot unplug is supplying virtual (effective)
addresses.
Fixes: 4dd5f8a99e791 ("powerpc/mm/radix: Split linear mapping on hot-unplu
Le 16/01/2020 à 17:21, Segher Boessenkool a écrit :
Christophe uses a very primitive 32-bit cpu, not even superscalar. A
loop doing adde is pretty much optimal, probably wants some unrolling
though.
You mean the mpc8xx , but I'm also using the mpc832x which has a e300c2
core and is capable
From: "Aneesh Kumar K.V"
[ Upstream commit d9101bfa6adc831bda8836c4d774820553c14942 ]
__find_linux_mm_pte() returns a page table entry pointer after walking
the page table without holding locks. To make it safe against a THP
split and/or collapse, we disable interrupts around the lockless page
t
From: Oliver O'Halloran
[ Upstream commit 9d72dcef891030545f39ad386a30cf91df517fb2 ]
On PowerNV the PCIe topology is (currently) managed by the powernv platform
code in Linux in cooperation with the platform firmware. Linux's native
PCIe port service drivers operate independently of both and thi
From: Ard Biesheuvel
[ Upstream commit b6afd1234cf93aa0d71b4be4788c47534905f0be ]
Commit 01c9348c7620ec65
powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*
updated arch_get_random_[int|long]() to be NOPs, and moved the hardware
RNG backing to arch_get_random_seed_[in
From: Christophe Leroy
[ Upstream commit fb978ca207743badfe7efd9eebe68bcbb4969f79 ]
Generic implementation fails to remove breakpoints after init
when CONFIG_STRICT_KERNEL_RWX is selected:
[ 13.251285] KGDB: BP remove failed: c001c338
[ 13.259587] kgdbts: ERROR PUT: end of test buffer on 'd
> You mean the mpc8xx , but I'm also using the mpc832x which has a e300c2
> core and is capable of executing 2 insns in parallel if not in the same
> Unit.
That should let you do a memory read and an add.
(I can't remember if the ppc has 'add from memory' but that is
likely to use both units anywa
From: Stefan Agner
[ Upstream commit d9866572486802bc598a3e8576a5231378d190de ]
Make sure to properly put the of node in case finding the codec
fails.
Fixes: 81e8e4926167 ("ASoC: fsl: add sgtl5000 clock support for imx-sgtl5000")
Signed-off-by: Stefan Agner
Reviewed-by: Daniel Baluta
Acked-by
From: Alexey Kardashevskiy
[ Upstream commit a67614cc05a5052b265ea48196dab2fce11f5f2e ]
The SPAPR TCE KVM device references all hardware IOMMU tables assigned to
some IOMMU group to ensure that in-kernel KVM acceleration of H_PUT_TCE
can work. The tables are references when an IOMMU group gets r
From: Michael Ellerman
[ Upstream commit 8cfaf106918a8c13abb24c641556172afbb9545c ]
In cpufeatures_process_feature(), if a provided CPU feature is unknown and
enable_unknown is false, we erroneously print that the feature is being
enabled and return true, even though no feature has been enabled,
From: Rashmica Gupta
[ Upstream commit 790845e2f12709d273d08ea7a2af7c2593689519 ]
We were always calling base_hpte_find() with primary = true,
even when we wanted to check the secondary table.
mpe: I broke this when refactoring Rashmica's original patch.
Fixes: 1515ab932156 ("powerpc/mm: Dump
From: Dan Carpenter
[ Upstream commit 5674a92ca4b7e5a6a19231edd10298d30324cd27 ]
We forgot to set "err" on this error path.
Fixes: 1a2d397a6eb5 ("gpio/powerpc: Eliminate duplication of
of_get_named_gpio_flags()")
Signed-off-by: Dan Carpenter
Signed-off-by: Li Yang
Signed-off-by: Sasha Levin
From: Ben Hutchings
[ Upstream commit ff6d27823f619892ab96f7461764840e0d786b15 ]
The 32-bit vDSO is not needed and not normally built for 64-bit
little-endian configurations. However, the vdso_install target still
builds and installs it. Add the same config condition as is normally
used for th
From: Nathan Lynch
[ Upstream commit d4aa219a074a5abaf95a756b9f0d190b5c03a945 ]
Allow external callers to force the cacheinfo code to release all its
references to cache nodes, e.g. before processing device tree updates
post-migration, and to rebuild the hierarchy afterward.
CPU online/offline
From: Nathan Lynch
[ Upstream commit e610a466d16a086e321f0bd421e2fc75cff28605 ]
It's common for the platform to replace the cache device nodes after a
migration. Since the cacheinfo code is never informed about this, it
never drops its references to the source system's cache nodes, causing
it to
From: Ravi Bangoria
[ Upstream commit 913a90bc5a3a06b1f04c337320e9aeee2328dd77 ]
perf_event_open() limits the sample_period to 63 bits. See:
0819b2e30ccb ("perf: Limit perf_event_attr::sample_period to 63 bits")
Make ioctl() consistent with it.
Also on PowerPC, negative sample_period could
From: Johannes Berg
[ Upstream commit f474808acb3c4b30552d9c59b181244e0300d218 ]
A lot of places in the driver use onyx_read_register() without
checking the return value, and it's been working OK for ~10 years
or so, so probably never fails ... Rather than trying to check the
return value everyw
From: Oliver O'Halloran
[ Upstream commit 9d72dcef891030545f39ad386a30cf91df517fb2 ]
On PowerNV the PCIe topology is (currently) managed by the powernv platform
code in Linux in cooperation with the platform firmware. Linux's native
PCIe port service drivers operate independently of both and thi
From: Ard Biesheuvel
[ Upstream commit b6afd1234cf93aa0d71b4be4788c47534905f0be ]
Commit 01c9348c7620ec65
powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*
updated arch_get_random_[int|long]() to be NOPs, and moved the hardware
RNG backing to arch_get_random_seed_[in
From: Stefan Agner
[ Upstream commit d9866572486802bc598a3e8576a5231378d190de ]
Make sure to properly put the of node in case finding the codec
fails.
Fixes: 81e8e4926167 ("ASoC: fsl: add sgtl5000 clock support for imx-sgtl5000")
Signed-off-by: Stefan Agner
Reviewed-by: Daniel Baluta
Acked-by
From: Dan Carpenter
[ Upstream commit 5674a92ca4b7e5a6a19231edd10298d30324cd27 ]
We forgot to set "err" on this error path.
Fixes: 1a2d397a6eb5 ("gpio/powerpc: Eliminate duplication of
of_get_named_gpio_flags()")
Signed-off-by: Dan Carpenter
Signed-off-by: Li Yang
Signed-off-by: Sasha Levin
From: Ben Hutchings
[ Upstream commit ff6d27823f619892ab96f7461764840e0d786b15 ]
The 32-bit vDSO is not needed and not normally built for 64-bit
little-endian configurations. However, the vdso_install target still
builds and installs it. Add the same config condition as is normally
used for th
From: Nathan Lynch
[ Upstream commit d4aa219a074a5abaf95a756b9f0d190b5c03a945 ]
Allow external callers to force the cacheinfo code to release all its
references to cache nodes, e.g. before processing device tree updates
post-migration, and to rebuild the hierarchy afterward.
CPU online/offline
From: Ravi Bangoria
[ Upstream commit 913a90bc5a3a06b1f04c337320e9aeee2328dd77 ]
perf_event_open() limits the sample_period to 63 bits. See:
0819b2e30ccb ("perf: Limit perf_event_attr::sample_period to 63 bits")
Make ioctl() consistent with it.
Also on PowerPC, negative sample_period could
From: Johannes Berg
[ Upstream commit f474808acb3c4b30552d9c59b181244e0300d218 ]
A lot of places in the driver use onyx_read_register() without
checking the return value, and it's been working OK for ~10 years
or so, so probably never fails ... Rather than trying to check the
return value everyw
From: Oliver O'Halloran
[ Upstream commit 9d72dcef891030545f39ad386a30cf91df517fb2 ]
On PowerNV the PCIe topology is (currently) managed by the powernv platform
code in Linux in cooperation with the platform firmware. Linux's native
PCIe port service drivers operate independently of both and thi
From: Ard Biesheuvel
[ Upstream commit b6afd1234cf93aa0d71b4be4788c47534905f0be ]
Commit 01c9348c7620ec65
powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*
updated arch_get_random_[int|long]() to be NOPs, and moved the hardware
RNG backing to arch_get_random_seed_[in
On Thu, Jan 16, 2020 at 07:57:29AM -0600, Segher Boessenkool wrote:
> On Thu, Jan 16, 2020 at 09:06:08AM +0100, Gabriel Paubert wrote:
> > On Thu, Jan 16, 2020 at 07:11:36AM +0100, Christophe Leroy wrote:
> > > Hi Segher,
> > >
> > > I'm trying to see if we could enhance TCP checksum calculations
From: Stefan Agner
[ Upstream commit d9866572486802bc598a3e8576a5231378d190de ]
Make sure to properly put the of node in case finding the codec
fails.
Fixes: 81e8e4926167 ("ASoC: fsl: add sgtl5000 clock support for imx-sgtl5000")
Signed-off-by: Stefan Agner
Reviewed-by: Daniel Baluta
Acked-by
From: Dan Carpenter
[ Upstream commit 5674a92ca4b7e5a6a19231edd10298d30324cd27 ]
We forgot to set "err" on this error path.
Fixes: 1a2d397a6eb5 ("gpio/powerpc: Eliminate duplication of
of_get_named_gpio_flags()")
Signed-off-by: Dan Carpenter
Signed-off-by: Li Yang
Signed-off-by: Sasha Levin
From: Ben Hutchings
[ Upstream commit ff6d27823f619892ab96f7461764840e0d786b15 ]
The 32-bit vDSO is not needed and not normally built for 64-bit
little-endian configurations. However, the vdso_install target still
builds and installs it. Add the same config condition as is normally
used for th
Hi Abdul,
I think the problem is that mpt3sas has some convoluted logic to do
some DMA allocations with a 32-bit coherent mask, and then switches
to a 63 or 64 bit mask, which is not supported by the DMA API.
Can you try the patch below?
---
>From 0738b1704ed528497b41b0408325f6828a8e51f6 Mon Sep
From: Nathan Lynch
[ Upstream commit d4aa219a074a5abaf95a756b9f0d190b5c03a945 ]
Allow external callers to force the cacheinfo code to release all its
references to cache nodes, e.g. before processing device tree updates
post-migration, and to rebuild the hierarchy afterward.
CPU online/offline
From: Johannes Berg
[ Upstream commit f474808acb3c4b30552d9c59b181244e0300d218 ]
A lot of places in the driver use onyx_read_register() without
checking the return value, and it's been working OK for ~10 years
or so, so probably never fails ... Rather than trying to check the
return value everyw
From: Ard Biesheuvel
[ Upstream commit b6afd1234cf93aa0d71b4be4788c47534905f0be ]
Commit 01c9348c7620ec65
powerpc: Use hardware RNG for arch_get_random_seed_* not arch_get_random_*
updated arch_get_random_[int|long]() to be NOPs, and moved the hardware
RNG backing to arch_get_random_seed_[in
This is a fourth tentative to switch powerpc VDSO to generic C implementation.
This version should work on PPC64 (untested). VDSO32 for PPC64 is
impossible to build and has been de-activated, because the powerpc
ASM header files for C are not prepared to build 32 bits code with CONFIG_PPC64.
powe
In order to allow use of generic C VDSO, remove time functions
from the 32 bits VDSO on PPC64.
This (temporary) removal is needed because powerpc kernel C headers
are not prepared for building 32 bits code on PPC64.
Signed-off-by: Christophe Leroy
---
arch/powerpc/kernel/vdso32/Makefile | 3
This is a minimalistic conversion to VDSO generic C implementation.
On powerpc 8xx, performance is degraded by 40-45% for gettime and
by 50% for getres.
Optimisations will follow in next patches, some in the core
VDSO functions, some in the powerpc arch.
powerpc is a bit special for VDSO as well
Only perform READ_ONCE(vd[CS_HRES_COARSE].hrtimer_res) for
HRES and RAW clocks.
Signed-off-by: Christophe Leroy
---
lib/vdso/gettimeofday.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/lib/vdso/gettimeofday.c b/lib/vdso/gettimeofday.c
index 9563be3cb5fa..8b3084d9a3ec 10
The VDSO datapage and the text pages are always located immediately
next to each other, so it can be hardcoded without an indirection
through __kernel_datapage_offset
In order to ease things, move the data page in front like other
arches, that way there is no need to know the size of the library
t
On powerpc, __arch_get_vdso_data() clobbers the link register,
requiring the caller to save it.
As the parent function already has to set a stack frame and saves
the link register before calling the C vdso function, retriving the
vdso data pointer there is lighter.
Give arches the opportunity to
__get_datapage() is only a few instructions to retrieve the
address of the page where the kernel stores data to the VDSO.
By inlining this function into its users, a bl/blr pair and
a mflr/mtlr pair is avoided, plus a few reg moves.
The improvement is noticeable (about 55 nsec/call on an 8xx)
Wi
__arch_get_vdso_data() clobbers the link register, requiring
the caller to save it.
As the ASM calling function already has to set a stack frame and
saves the link register before calling the C vdso function,
retriving the vdso data pointer there is lighter.
The improvement is significant:
Befor
On arches like POWERPC, the clock is always the timebase, it
cannot be changed on the fly and it is always VDSO capable.
Therefore, give arches the opportunity to redefine the way
clock_mode is checked by moving the check into an overridable
__arch_vdso_capable() macro.
Signed-off-by: Christophe
When the timebase is used, make __arch_vdso_capable() always
return true. When the RTC clock is used, make __arch_vdso_capable()
always return false.
Before the patch:
clock-gettime-realtime:vdso: 1086 nsec/call
After the patch:
clock-gettime-realtime:vdso: 1033 nsec/call
Signed-off-by:
On powerpc/32, GCC (8.1) generates pretty bad code for the
ns >>= vd->shift operation taking into account that the
shift is always < 32 and the upper part of the result is
likely to be nul. GCC makes reversed assumptions considering
the shift to be likely >= 32 and the upper part to be like not nul
The generic x >> s gives the following result:
18: 35 25 ff e0 addic. r9,r5,-32
1c: 41 80 00 10 blt 2c
20: 7c 64 4c 30 srw r4,r3,r9
24: 38 60 00 00 li r3,0
...
2c: 54 69 08 3c rlwinm r9,r3,1,0,30
30: 21 45 00 1f subfic r10,r5,31
34
Le 16/01/2020 à 17:56, Nathan Lynch a écrit :
Hi Christophe,
Christophe Leroy writes:
To properly handle errors returned by gettimeofday(), the
DO_VDSO_CALL() macro has to be used, otherwise vdsotest
misinterpret VDSO function return on error.
This has gone unnoticed until now because the
On Thu, Jan 16, 2020 at 9:58 AM Christophe Leroy
wrote:
>
> On powerpc/32, GCC (8.1) generates pretty bad code for the
> ns >>= vd->shift operation taking into account that the
> shift is always < 32 and the upper part of the result is
> likely to be nul. GCC makes reversed assumptions considering
Hi Stephen,
On 1/15/20 6:39 PM, Stephen Rothwell wrote:
Hi Alexandre,
Thanks for sorting this out. Just a few comments below.
On Wed, 15 Jan 2020 15:46:48 -0500 Alexandre Ghiti wrote:
# Have Kbuild supply the path to objdump so we handle cross compilation.
Andy Lutomirski writes:
> On Thu, Jan 16, 2020 at 9:58 AM Christophe Leroy
>
> Would mul_u64_u64_shr() be a good alternative? Could we adjust it to
> assume the shift is less than 32? That function exists to benefit
> 32-bit arches.
We'd want mul_u64_u32_shr() for this. The rules for mult and s
Christophe Leroy writes:
Can you please adjust the prefix for future patches to lib/vdso: and
start the sentence after the colon with an uppercase letter?
> On arches like POWERPC, the clock is always the timebase, it
Please spell out architectures. Changelogs are not space constraint.
> canno
On Thu, Jan 16, 2020 at 12:14 PM Thomas Gleixner wrote:
>
> Christophe Leroy writes:
>
> Can you please adjust the prefix for future patches to lib/vdso: and
> start the sentence after the colon with an uppercase letter?
>
> > On arches like POWERPC, the clock is always the timebase, it
>
> Pleas
On Thu, Jan 16, 2020 at 11:57 AM Thomas Gleixner wrote:
>
> Andy Lutomirski writes:
> > On Thu, Jan 16, 2020 at 9:58 AM Christophe Leroy
> >
> > Would mul_u64_u64_shr() be a good alternative? Could we adjust it to
> > assume the shift is less than 32? That function exists to benefit
> > 32-bit
On Thu, Jan 16, 2020 at 2:35 AM Thomas Gleixner wrote:
>
> static __maybe_unused int
> __cvdso_data_clock_gettime(clockid_t clock, struct __kernel_timespec *ts,
>const struct vdso_data *vd)
> {
> .
> }
>
> static __maybe_unused int
> __cvdso_clock_gettime(cl
On 1/16/20 1:37 AM, Christoph Hellwig wrote:
On Wed, Jan 15, 2020 at 01:19:41PM -0800, John Hubbard wrote:
On 1/15/20 7:23 AM, Christoph Hellwig wrote:
...
I'm really not sold on this scheme. Note that I think it is
particularly bad, but it also doesn't seem any better than what
we had before
Andy Lutomirski writes:
> On Thu, Jan 16, 2020 at 12:14 PM Thomas Gleixner wrote:
>> Some architectures have a fixed clocksource which is known at compile
>> time and cannot be replaced or disabled at runtime, e.g. timebase on
>> PowerPC. For such cases the clock mode check in the VDSO code is
>>
On 1/15/20 11:53 PM, Michael Ellerman wrote:
> Michael Bringmann writes:
>> Correct overflow problem in calculation+display of Maximum Memory
>> value to syscfg where 32bits is insufficient.
>>
>> Signed-off-by: Michael Bringmann
>> ---
>> arch/powerpc/platforms/pseries/lparcfg.c | 8
>>
This test triggers a TM Bad Thing by raising a signal in transactional state
and forcing a pagefault to happen in kernelspace when the kernel signal
handling code first touches the user signal stack.
This is inspired by the test tm-signal-context-force-tm but uses userfaultfd to
make the test dete
The test case tm-signal-context-force-tm expects a segfault to happen on
returning from signal handler, and then does a setcontext() to run the test
again. However, the test doesn't always segfault, causing the test to run a
single time.
This patch fixes the test by putting it within a loop and ju
1 - 100 of 107 matches
Mail list logo
