ianfar-tbi) of the fsl_pq_mdio_match array.
Note: This patch may break MDIO functionallity of some old Freescale's SoC
until Freescale will fix their device tree files. Basically, every device tree
which contains an mdio device that is compatible to "fsl,gianfar-tbi" should be
exam
Oded Gabbay wrote:
Note: This patch may break MDIO functionallity of some old
Freescale's SoC
until Freescale will fix their device tree files. Basically, every
device tree
which contains an mdio device that is compatible to "fsl,gianfar-tbi"
should be
examined.
On 06/1
ction detecs if the non-removable property is set in the device tree.
The function esdhc_pltfm_bus_width was added because the bus width configuration
is platform specific.
Signed-off-by: Oded Gabbay
---
drivers/mmc/host/sdhci-esdhc.h| 7 +++
drivers/mmc/host/sdhci-of-esdhc.c
tch depends on the first patch of this set (total of 2 patches)
Signed-off-by: Oded Gabbay
---
drivers/mmc/host/sdhci-of-esdhc.c | 14 ++
include/linux/mmc/sdhci.h | 2 ++
2 files changed, 16 insertions(+)
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c
b/drivers/mmc/host/sd
On 06/12/2013 09:31 PM, Scott Wood wrote:
On 06/12/2013 10:08:29 AM, Sebastian Andrzej Siewior wrote:
On 06/12/2013 02:47 PM, Oded Gabbay wrote:
> This patch fixes a bug in the fsl_pq_mdio.c module and in relevant
device-tree
> files regarding the correct offset of the tbipa register
ction detecs if the non-removable property is set in the device tree.
The function esdhc_pltfm_bus_width was added because the bus width configuration
is platform specific.
Signed-off-by: Oded Gabbay
Reviewed-by: Anton Vorontsov
---
drivers/mmc/host/sdhci-esdhc.h| 7 +++
drivers/mmc/host/
tch depends on the first patch of this set (total of 2 patches)
Signed-off-by: Oded Gabbay
Reviewed-by: Anton Vorontsov
---
drivers/mmc/host/sdhci-of-esdhc.c | 14 ++
include/linux/mmc/sdhci.h | 2 ++
2 files changed, 16 insertions(+)
diff --git a/drivers/mmc/host/sdhci
Signed-off-by: Oded Gabbay
---
Documentation/devicetree/bindings/mmc/fsl-esdhc.txt | 3 +++
drivers/mmc/host/sdhci-of-esdhc.c | 4
2 files changed, 7 insertions(+)
diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
b/Documentation/devicetree/bindings/mmc/fsl-
off-by: Oded Gabbay
---
drivers/mmc/host/sdhci-of-esdhc.c | 10 ++
include/linux/mmc/sdhci.h | 2 ++
2 files changed, 12 insertions(+)
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c
b/drivers/mmc/host/sdhci-of-esdhc.c
index 6f433b8..e70f22f 100644
--- a/drivers/mmc/host/sdhci
ff-by: Oded Gabbay
---
drivers/mmc/host/sdhci-esdhc.h| 7 ++
drivers/mmc/host/sdhci-of-esdhc.c | 49 ++-
2 files changed, 55 insertions(+), 1 deletion(-)
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index d25f9ab..6f
:
On 02.06.2013 08:38, Oded Gabbay wrote:
This patch adds support of recognizing hard-wired (permanent) cards
to Freescale's SDHC host driver. This is done by adding the option
"fsl,card-wired" to the SDHC device-tree entry. Detection of this
option is done in the probe function. Upd
Hi All,
Just noticed that 3.4.47/8 doesn't have the mmc_of_parse (compared to
3.9.4).
Therefore, I will not use it and just fix the code to recognize the
property "non-removable"
Best regards,
Oded
On 06/10/2013 04:43 PM, Oded Gabbay wrote:
Hi Dirk,
You are absolutely right
tead of patch[3/3] from 6-jun-2013:
https://patchwork.kernel.org/patch/2649231/
Signed-off-by: Oded Gabbay
---
drivers/mmc/host/sdhci-of-esdhc.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/mmc/host/sdhci-of-esdhc.c
b/drivers/mmc/host/sdhci-of-esdhc.c
index e70f22f..a6e06
clude of linux/sched.h to mmu_context_mm.h to avoid
such errors.
Signed-off-by: Oded Gabbay
---
arch/microblaze/include/asm/mmu_context_mm.h | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/microblaze/include/asm/mmu_context_mm.h
b/arch/microblaze/include/asm/mmu_context_mm.h
11: 0202 R12:
> 7fff8740efc0
> [ 947.650314] R13: R14: 006231c0 R15:
> 00623010
> [ 947.650316] Code: 00 00 55 49 89 d1 48 89 e5 53 48 89 fb 48 83 ec 18 48 85
> f6 74 5f 4c 8b 46 50 4d 85 c0 74 2b 48 8b 86 88 00 00 00 48 85 c0 74
On Mon, Nov 13, 2017 at 2:35 AM, Dmitry V. Levin wrote:
> Consistently use types provided by via
> to fix the following linux/kfd_ioctl.h userspace compilation errors:
>
> /usr/include/linux/kfd_ioctl.h:236:2: error: unknown type name 'uint64_t'
> uint64_t va_addr; /* to KFD */
> /usr/include/
On Fri, Aug 28, 2015 at 10:27 AM, Christoph Hellwig wrote:
>
> The latter is a default version of and not for driver use.
>
> Signed-off-by: Christoph Hellwig
> ---
> drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 2 +-
> drivers/gpu/drm/amd/amdkfd/kfd_flat_memory.c | 2 +-
> 2 files changed, 2
amp;p->mutex);
> pdd = kfd_get_process_device_data(dev, p);
>
> + if (WARN_ON(!pdd)) {
> + mutex_unlock(&p->mutex);
> + continue;
> + }
> +
> if (pdd->bound == PDD_BOUND)
> pdd->bound = PDD_BOUND_SUSPENDED;
> mutex_unlock(&p->mutex);
> --
> 2.7.4
>
This patch is:
Reviewed-by: Oded Gabbay
On Sat, Jan 20, 2018 at 12:30 AM, Gustavo A. R. Silva
wrote:
>
> Quoting Felix Kuehling :
>
>> Looks good. This change is Reviewed-by: Felix Kuehling
>>
>>
>
> Thanks Felix.
> --
> Gustavo
>
Applied to -next
Oded
>
>
>
>
On Thu, May 3, 2018 at 12:49 AM, Kees Cook wrote:
> On Fri, Apr 13, 2018 at 2:24 PM, Laura Abbott wrote:
>>
>> There's an ongoing effort to remove VLAs[1] from the kernel to eventually
>> turn on -Wvla. Switch to a constant value that covers all hardware.
>>
>> [1] https://lkml.org/lkml/2018/3/7/
gt; remove the saved pointer as well, saving a tiny bit of memory and logic.
>
> Cc: Oded Gabbay
> Cc: Arnd Bergmann
> Cc: Tomer Tayar
> Cc: Moti Haimovski
> Cc: Omer Shpigelman
> Cc: Ofir Bitton
> Cc: linux-kernel@vger.kernel.org
> Signed-off-by: Greg Kroah-Hartman
&g
hl_eq_inc_ptr() is not called from anywhere outside irq.c so mark
it as static
Reported-by: kernel test robot
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/irq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/misc/habanalabs/common/irq.c
b/drivers
From: farah kassabri
currently we support only 2 asids in all asics.
asid 0 for driver, and asic 1 for user.
no need to setup 1024 asids configurations at init phase.
Signed-off-by: farah kassabri
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/include/gaudi
From: Tomer Tayar
Clearing QM errors by the driver will prevent these H/W blocks from
stopping in case they are configured to stop on errors, so perform this
clearing only if this mode is not in use.
Signed-off-by: Tomer Tayar
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers
From: Ohad Sharabi
In order to minimize hard coded values between F/W and the driver, we
send msi-x indexes dynamically to the F/W.
Signed-off-by: Ohad Sharabi
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/firmware_if.c | 67
Jauhari
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/memory.c | 87 ++---
1 file changed, 48 insertions(+), 39 deletions(-)
diff --git a/drivers/misc/habanalabs/common/memory.c
b/drivers/misc/habanalabs/common/memory.c
index 6530fddbbc21
From: Ofir Bitton
As F/ security indication must be available before driver approaches
PCI bus, F/W security should be derived from PCI id rather than be
fetched during boot handshake with F/W.
Signed-off-by: Ofir Bitton
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers/misc
From: Ofir Bitton
As part of the securing GAUDI, the F/W will configure the PCI iATU
regions. If the driver identifies a secured PCI ID, it will know to
skip iATU configuration in a very early stage.
Signed-off-by: Ofir Bitton
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
drivers
We need to print a message to the kernel log in case we encounter
an unknown error in the f/w boot to help the user understand what
happened.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/common/firmware_if.c | 6 +-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a
From: Ohad Sharabi
update files to latest version from F/W team.
Signed-off-by: Ohad Sharabi
Reviewed-by: Oded Gabbay
Signed-off-by: Oded Gabbay
---
.../misc/habanalabs/include/common/cpucp_if.h | 3 +-
.../habanalabs/include/common/hl_boot_if.h| 198 ++
2 files
On 01/04/2015 01:31 AM, Alexey Khoroshilov wrote:
> If timeout happens, kgd_hqd_destroy() just returns -ETIME leaving queue
> acquired.
> It may cause a deadlock, so the patch proposes to release queue before return.
>
> Found by Linux Driver Verification project (linuxtesting.org).
>
> Signed
On 12/03/2014 04:26 PM, Sasha Levin wrote:
All the bit operations (such as find_first_zero_bit()) read sizeof(long) bytes
at a time. If we allocated less than sizeof(long) bytes for the bitmask we
would be accessing invalid memory when working with the bitmask.
Change the allocator to allocate
On 12/03/2014 05:19 PM, Sasha Levin wrote:
srcu callbacks are running in atomic context, we can't allocate using
__GFP_WAIT.
Signed-off-by: Sasha Levin
---
drivers/gpu/drm/amd/amdkfd/kfd_process.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/amd/amdkf
Hello Linus,
Dave Airlie asked me to send this patch to you for review.
See link below for cover-letter for this patch that explains the background a
bit more:
http://lists.freedesktop.org/archives/dri-devel/2014-December/074452.html
Thanks,
Oded
On 12/22/2014 01:07 PM, Oded Gabbay
On 12/25/2014 02:31 PM, Christian König wrote:
Am 22.12.2014 um 20:18 schrieb Oded Gabbay:
On 12/22/2014 09:00 PM, Andi Kleen wrote:
On Mon, Dec 22, 2014 at 10:49:40AM -0800, Andi Kleen wrote:
On Mon, Dec 22, 2014 at 11:58:43AM -0500, Alex Deucher wrote:
On Mon, Dec 22, 2014 at 6:11 AM
On 12/26/2014 11:19 AM, Laurent Pinchart wrote:
Hi Thierry,
On Thursday 25 December 2014 14:20:59 Thierry Reding wrote:
On Mon, Dec 22, 2014 at 01:07:13PM +0200, Oded Gabbay wrote:
This small patch-set, was created to solve the bug described at
https://bugzilla.kernel.org/show_bug.cgi?id
On 12/28/2014 06:44 PM, Sasha Levin wrote:
Commit "amdkfd: use sizeof(long) granularity for the pasid bitmask" calculated
the number of longs it will need, but ended up allocating that number of
bytes rather than longs.
Fix that silly error and allocate the amount of data really required.
Sig
symbol_request() doesn't work as expected - it doesn't return
NULL if the symbol doesn't exists - which makes the kernel panic.
Signed-off-by: Oded Gabbay
---
drivers/gpu/drm/radeon/radeon_kfd.c | 12
1 file changed, 12 insertions(+)
diff --git a/drivers/gpu/drm/radeon/
On 12/29/2014 02:41 PM, Christian König wrote:
Am 29.12.2014 um 09:59 schrieb Oded Gabbay:
This patch changes the radeon_kfd_init(), which is used to initialize the
interface between radeon and amdkfd, so the interface will be initialized only
if amdkfd was build, either as module or inside
update the appropriate task stats after the
fault has been handled, and may aid with debug in the future as well.
v2: drop task accounting; GPU activity may have been submitted by a
different thread than the one binding the PASID (Joerg)
Tested-by: Oded Gabbay
Signed-off-by: Jesse Barnes
Hi
, 2014 at 10:34:32AM +0100, Christian König wrote:
Am 29.12.2014 um 09:16 schrieb Laurent Pinchart:
Hi Oded,
On Sunday 28 December 2014 13:36:50 Oded Gabbay wrote:
On 12/26/2014 11:19 AM, Laurent Pinchart wrote:
On Thursday 25 December 2014 14:20:59 Thierry Reding wrote:
On Mon, Dec 22, 2014
Hi,
Commit d75b1ade567ffab085e8adbbdacf0092d10cd09c breaks my "Qualcomm Atheros
AR8161 Gigabit Ethernet (rev 10)" Ethernet controller, which is handled by
the alx network driver.
ogabbay@odedg-ubuntu:~$ lspci -s 01:00.0 -k
01:00.0 Ethernet controller:
Qualcomm Atheros AR8161 Gigabit Ether
On 01/10/2015 10:58 PM, Eric Dumazet wrote:
> On Sat, 2015-01-10 at 22:39 +0200, Oded Gabbay wrote:
>> Hi,
>>
>> Commit d75b1ade567ffab085e8adbbdacf0092d10cd09c breaks my "Qualcomm Atheros
>> AR8161 Gigabit Ethernet (rev 10)" Ethernet controller, which is
On 01/10/2015 11:30 PM, Oded Gabbay wrote:
>
>
> On 01/10/2015 10:58 PM, Eric Dumazet wrote:
>> On Sat, 2015-01-10 at 22:39 +0200, Oded Gabbay wrote:
>>> Hi,
>>>
>>> Commit d75b1ade567ffab085e8adbbdacf0092d10cd09c breaks my "Qualcomm Atheros
On 01/10/2015 11:50 PM, Eric Dumazet wrote:
> On Sat, 2015-01-10 at 23:30 +0200, Oded Gabbay wrote:
>
>> Yes, no problem.
>> I will update on the result.
>
> Please try this more complete patch, solving the TX pressure problem as
> well, and not lying about NAPI bu
On 01/11/2015 12:05 AM, Oded Gabbay wrote:
>
>
> On 01/10/2015 11:50 PM, Eric Dumazet wrote:
>> On Sat, 2015-01-10 at 23:30 +0200, Oded Gabbay wrote:
>>
>>> Yes, no problem.
>>> I will update on the result.
>>
>> Please try this more complet
Hello,
Today I took latest branch from Linus repo to check for amdkfd regressions
due to my fixes pulled for 3.19-rc4, and I got a kernel bug (see below dmesg
output).
I did a bisect and the first bad commit is:
7a3ef208e662f4b63d43a23f61a64a129c525bbc is the first bad commit
commit 7a3ef208e662
%r9b,-0x73(%r8)
> 12: 55 push %rbp
> 13: 10 48 83 adc%cl,-0x7d(%rax)
> 16: e8 10 49 39 d6 callq 0xd639492b
> 1b: 74 54 je 0x71
> 1d: 48 8b 7d 08 mov0x8(%rbp),%rdi
> 21
;>>> 38: 66 data16
>>>> 39: 0f .byte 0xf
>>>> 3a: 1f (bad)
>>>> 3b: 84 00 test %al,(%rax)
>>>> 3d: 00 00 add%al,(%rax)
>>>> ...
&
On 01/07/2015 12:58 AM, Rusty Russell wrote:
> Kees Cook writes:
>> On Sun, Jan 4, 2015 at 8:28 PM, Rusty Russell wrote:
>>> Kees, as far as I can tell you need another 0-terminated vmlinux.relocs
>>> section for weak symbols. These should not be relocated if already 0.
>>
>> A few questions:
On 01/06/2015 12:44 AM, j.gli...@gmail.com wrote:
> From: Jérôme Glisse
>
> The event information will be useful for new user of mmu_notifier API.
> The event argument differentiate between a vma disappearing, a page
> being write protected or simply a page being unmaped. This allow new
> user
On 01/11/2015 02:24 PM, Oded Gabbay wrote:
>
>
> On 01/06/2015 12:44 AM, j.gli...@gmail.com wrote:
>> From: Jérôme Glisse
>>
>> The event information will be useful for new user of mmu_notifier API.
>> The event argument differentiate between a vma di
On 01/06/2015 12:44 AM, j.gli...@gmail.com wrote:
> From: Jérôme Glisse
>
> This patch only introduce core HMM functions for registering a new mirror and
> stopping a mirror as well as registering and unregistering a device.
>
> The lifecycle of HMM object is handled differently then one of mm
On 01/12/2015 05:46 PM, Jerome Glisse wrote:
> On Sun, Jan 11, 2015 at 03:24:42PM +0200, Oded Gabbay wrote:
>>
>>
>> On 01/06/2015 12:44 AM, j.gli...@gmail.com wrote:
>>> From: Jérôme Glisse
>>>
>>> This patch only introduce core HMM functions fo
On 01/16/2015 02:27 AM, Kees Cook wrote:
> On Sun, Jan 4, 2015 at 8:28 PM, Rusty Russell wrote:
>> Oded Gabbay writes:
>>> On 12/24/2014 01:01 AM, Rusty Russell wrote:
>>>> Oded Gabbay writes:
>>>>> I didn't say it doesn't always work.
as inline because it calls BUG_ON()
Signed-off-by: Oded Gabbay
Cc: sta...@vger.kernel.org
Tested-by: Michel Dänzer
---
drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_ma
wait_event.
Signed-off-by: Oded Gabbay
Cc: sta...@vger.kernel.org
---
drivers/iommu/amd_iommu_v2.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 6d5a5c4..173e70d 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/a
On 04/23/2015 07:22 PM, Jerome Glisse wrote:
On Thu, Apr 23, 2015 at 09:20:55AM -0500, Christoph Lameter wrote:
On Thu, 23 Apr 2015, Benjamin Herrenschmidt wrote:
There are hooks in glibc where you can replace the memory
management of the apps if you want that.
We don't control the app. Le
Hi Joerg,
Could you please take a look at this patch ?
I want it to be included in stable asap so Fedora 22 will pick it up.
Thanks,
Oded
On 04/16/2015 05:08 PM, Oded Gabbay wrote:
This patch fixes a bug in put_pasid_state_wait that appeared in kernel 4.0
The bug is that pasid_state
Hi Joerg,
I sent to you (cc iommu mailing list) an important fix on Apr-16 for a bug in
amd_iommu_v2.c (from kernel 4.0). See:
http://lists.linuxfoundation.org/pipermail/iommu/2015-April/012757.html
Could you please add that to the pull request ?
Its creating problems when running HSA applicat
Cc: sta...@vger.kernel.org
Signed-off-by: Oded Gabbay
---
drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c | 22 +-
1 file changed, 13 insertions(+), 9 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index
On Thu, Jun 11, 2015 at 6:19 PM, Dan Carpenter wrote:
> #include "kfd_dbgmgr.h"
> +#include "../../radeon/cik_reg.h"
>
> static long kfd_ioctl(struct file *, unsigned int, unsigned long);
We can't include radeon files in kfd_chardev.c, because amdkfd works
with two device drivers - radeon and a
On Thu, Jun 11, 2015 at 6:19 PM, Dan Carpenter wrote:
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> index 96c904b..54a608a 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
> @@ -553,
On Fri, Jun 5, 2015 at 11:27 AM, Valentin Rothberg
wrote:
> The CONFIG_ prefix is reserved for Kconfig options in Make and CPP
> syntax. Various static analysis tools rely on this naming convention
> and check if CONFIG_ prefixed symbols are defined Kconfig. Hence add
> yet another prefix AMD_ t
_REG_OFFSET(GC, 0, mmCP_PQ_WPTR_POLL_CNTL1),
>get_queue_mask(adev, pipe_id, queue_id));
> }
> --
> 2.9.0
>
There is a change scheduled for the next merge window that will cause
this file to not build anymore on 32-bit targets (because the amdkfd
driver is not supported on 32 bit targets).
Never the less I'm taking the patch for good measure.
This patch is:
Reviewed-by: Oded Gabbay
mdgpu: include pagemap.h for release_pages()
>
> Fixes: 5ae0283e831a ("drm/amdgpu: Add userptr support for KFD"
> Cc: Felix Kuehling
> Cc: Oded Gabbay
> Signed-off-by: Stephen Rothwell
> ---
> drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 1 +
> 1 file changed
).
Thanks,
Oded
Oded Gabbay (10):
habanalabs: disable CPU access on timeouts
habanalabs: fix mmu cache registers init
habanalabs: fix validation of WREG32 to DMA completion
habanalabs: set DMA0 completion to SOB 1007
habanalabs: add comments in uapi/misc/habanalabs.h
habanalabs: fix memory
From: Omer Shpigelman
This patch fix a bug where the timeout for sending a job on QMAN0 by KMD
wasn't enough in palladium environment.
Signed-off-by: Omer Shpigelman
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 12 +---
1 file changed, 9 insertions(
is to do a soft-reset of the device in case the context-switch
fails, because the device should be IDLE during context-switch. If it is
not IDLE, then something is wrong and we should reset the compute engines.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/command_submiss
Add __cpu_to_le16/32/64 and __le16/32/64_to_cpu where needed according to
sparse.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/debugfs.c | 15 ---
drivers/misc/habanalabs/habanalabs_ioctl.c | 2 +-
drivers/misc/habanalabs/hw_queue.c | 23 +-
drivers/misc
ed in time, mark the state as
"cpu_disabled" and prevent sending further requests from KMD to the F/W.
This will eventually lead to a heartbeat failure and hard reset of the
device.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/debugfs.c| 6 --
drivers/misc/habanalabs/d
From: Tomer Tayar
Add __cpu_to_le16/32/64 and __le16/32/64_to_cpu where needed according to
sparse.
Signed-off-by: Tomer Tayar
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 223
1 file changed, 125 insertions(+), 98 deletions(-)
diff --git
from the event entries we receive
without looking at the RAZWI logger at all.
Signed-off-by: Tomer Tayar
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 227
1 file changed, 127 insertions(+), 100 deletions(-)
diff --git a/drivers/misc/haban
This patch fix a bug when a command buffer with unaligned size (with
regard to PAGE_SIZE) was used. The accounting for the unmap operation
wasn't done correctly and could result in a memory leak.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/command_buffer.c | 9 ++---
1
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers/misc/habanalabs/goya/goya.c
b/drivers/misc/habanalabs/goya/goya.c
index 13923f4127af..39824214ce61 100644
--- a/drivers/misc/habanalabs/goya/goya.c
From: Omer Shpigelman
This patch fix a bug where EINVAL was returned instead of -EINVAL.
Signed-off-by: Omer Shpigelman
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/mmu.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/misc/habanalabs/mmu.c b/drivers
This patch fix a bug where DMA channel 0 completion address wasn't
initialized by the driver.
The patch sets the address to Sync Object no. 1007
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c| 14 +++---
.../habanalabs/include/goya/asi
This patch fixes the following sparse warnings:
drivers/misc/habanalabs/hwmon.c:20:56: warning: Using plain integer as NULL
pointer
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/hwmon.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/misc/habanalabs
: Omer Shpigelman
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 190 +---
drivers/misc/habanalabs/goya/goyaP.h | 29 +-
drivers/misc/habanalabs/habanalabs.h | 12 +-
.../include/hw_ip/mmu/mmu_general.h | 1 +
drivers/misc
This patch fix a bug in the validation of WREG32 in DMA queues. The
validation was too strict. It allowed the user to set the completion
address only for DMA channel 1.
The fix allows the user to set the completion address for all 5 DMA
channels.
Signed-off-by: Oded Gabbay
---
drivers/misc
This patch fix an incorrect initialization of the MMU cache registers. The
shift operation was done in the wrong direction.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/drivers/misc/habanalabs/goya
Signed-off-by: Oded Gabbay
---
include/uapi/misc/habanalabs.h | 10 +-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/include/uapi/misc/habanalabs.h b/include/uapi/misc/habanalabs.h
index 23d6ad3459cb..7fd6f633534c 100644
--- a/include/uapi/misc/habanalabs.h
+++ b/include
On Thu, Feb 28, 2019 at 11:31 AM Greg KH wrote:
>
> On Thu, Feb 28, 2019 at 10:46:20AM +0200, Oded Gabbay wrote:
> > Signed-off-by: Oded Gabbay
>
> I can't take patches without any changelog text :(
>
ah, didn't know it was required for even this trivial chang
Add comment about minimum and maximum size of command buffer.
Add some text about the expected input of CS IOCTL.
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Add changelog in the commit message
include/uapi/misc/habanalabs.h | 10 +-
1 file changed, 9 insertions(+), 1 deletion
Don't cast pointer to u64 to print it. Instead, print the pointer using
%p.
Signed-off-by: Oded Gabbay
---
Changes in v2:
- Add changelog in the commit message
drivers/misc/habanalabs/goya/goya.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/drivers
On Thu, Feb 28, 2019 at 2:02 PM Greg KH wrote:
>
> On Thu, Feb 28, 2019 at 11:55:45AM +0200, Oded Gabbay wrote:
> > Don't cast pointer to u64 to print it. Instead, print the pointer using
> > %p.
> >
> > Signed-off-by: Oded Gabbay
> > ---
> > Cha
This patch fix compilation error in 32-bit ARM architecture regarding
division of 2 64-bit variables.
Use the kernel do_div() macro, which is implemented per architecture, for
doing these divisions instead of using the / operator.
Reported-by: kbuild test robot
Signed-off-by: Oded Gabbay
Hi Greg and Olof,
I wanted to let you know that I put the sources of our new userspace
thunk library in GitHub, as we discussed a few weeks ago during the
review of the driver.
The link is: https://github.com/HabanaAI/hl-thunk
As this library was written from scratch in the past month, it is
still
s
dependency on HAS_IOMEM because HWMON is dependent on HAS_IOMEM.
Reported-by: kbuild test robot
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/Kconfig | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/misc/habanalabs/Kconfig b/drivers/misc/habanalab
On Sat, Mar 2, 2019 at 3:00 AM Joe Perches wrote:
>
> On Thu, 2019-02-28 at 11:55 +0200, Oded Gabbay wrote:
> > Don't cast pointer to u64 to print it. Instead, print the pointer using
> > %p.
>
> You might want to use %px here if you _really_
> want the actual a
get a clue regarding the origin of his
error.
Note that if the print occurs, the pointer that is printed is a
user's virtual address and not some kind of physical address.
Suggested-by: Joe Perches
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/goya/goya.c | 2 +-
1 file changed, 1
This patch only does renaming of certain variables and structure members,
and their accompanied comments.
This is done to better reflect the actions these variables and members
represent.
There is no functional change in this patch.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs
This patch adds the habanalabs skeleton driver. The driver does nothing at
this stage except very basic operations. It contains the minimal code to
insmod and rmmod the driver and to create a /dev/hlX file per PCI device.
Signed-off-by: Oded Gabbay
---
drivers/misc/Kconfig
appricate any feedback, question and/or review.
Thanks,
Oded
p.s. for those who prefer to clone the tree instead of looking at the
emails, you can grab a copy from our company's page in GitHub:
https://github.com/HabanaAI/linux/releases/tag/hl_patchset_v3_20190204
Oded Gabbay (14):
habanalabs
r that was given to
it. The internal QMAN doesn't do that.
Signed-off-by: Oded Gabbay
---
Changes in v3:
- Fix the return value in goya_stop_external_queues()
- Remove hdev->ifh field as it was used for debugging
drivers/misc/habanalabs/Makefile |2 +-
drive
This patch adds a basic support for the Goya device. The code initializes
the device's PCI controller and PCI bars. It also initializes various S/W
structures and adds some basic helper functions.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/Makefile| 4 +
drivers
freeing memory on the DDR
upon user request. It also provides an interface to map and unmap DDR and
Host memory to the device address space.
Signed-off-by: Omer Shpigelman
Signed-off-by: Oded Gabbay
---
Changes in v3:
- Remove use of three exclamation marks
- Add optimization - support mapping
evice (operational, malfunction, in_reset)
- How many processes are open on the device's file
Signed-off-by: Oded Gabbay
---
.../ABI/testing/sysfs-driver-habanalabs | 190 ++
drivers/misc/habanalabs/Makefile | 2 +-
drivers/misc/habanalabs/device.c
will restore the max power attribute and in
case of manual power management, the frequencies that were set.
This patch also adds two entries to the sysfs, which allows the root user
to initiate a soft or hard reset.
Signed-off-by: Oded Gabbay
---
Changes in v3:
- Remove use of three exclamation
erature. After writing the new entry to the EQ, the control CPU will
trigger its dedicated MSI-X entry to signal the driver that there is a new
entry in the EQ. The driver will then read the entry and act accordingly.
Signed-off-by: Oded Gabbay
---
drivers/misc/habanalabs/device.c | 34 +-
1 - 100 of 1271 matches
Mail list logo
