> > From: Dean Luick
> >
> > Correctly reduce the number of VLs when limited by the number of SDMA
> > engines.
>
> why? What does this "solve"?
The hardware has multiple egress mechanisms, SDMA and pio, and multiples of
those.
These mechanisms are chosen using the VL
> > + dd_dev_info(dd, "%s: program XMT margin, CcePcieCtrl 0x%llx\n",
> > + fname, pcie_ctrl);
>
> Why spam the log with this all the time? Shouldn't this be a debug line
> instead?
The current implementation is layered on dev_info().
Are you saying dev_dbg() is a better
> > Add CNP opcode decode
>
> Why?
Prior to this patch the trace appeared like:
-0 [001] d.h. 94062.578932: input_ibhdr: [:05:00.0] vl 0 lver 0
sl 0 lnh 2,LRH_BTH dlid 0003 len 6 slid 0001 op 0x80,0x80 se 0 m 0 pad 0 tver 0
pkey 0x8001 f 0 b 0 qpn 0x001234 a 0 psn 0x
Note the
> > Clean up comments
>
> In what way?
>
The patch deleted numbering and terms internal to intel.
The information on the actual bugs is not deleted.
Mike
___
devel mailing list
de...@linuxdriverproject.org
On 11/20/15, Xose Vazquez Perez wrote:
> Hi,
>
> From https://lwn.net/Articles/662979/
>
> --cut--
> Christoph complained a bit about the staging tree. He said that it
> breaks allmodconfig builds, but that problem was evidently fixed a while
> ago. He also dislikes the
At the beginning when hfi1 was put into staging, then it was easy enough
for Greg to take those patches but now it feels awkward. Probably
Doug and the linux-r...@vger.kernel.org people should start maintaining
the drivers/staging/rdma directory. Like merge Greg's tree and pull in
whatever
Hi,
>From https://lwn.net/Articles/662979/
--cut--
Christoph complained a bit about the staging tree. He said that it
breaks allmodconfig builds, but that problem was evidently fixed a while
ago. He also dislikes the Lustre filesystem, which has been in staging
for some time now; Greg agreed and
Removed the blank line before the close brace to remove the check
detected by the checkpatch.pl
CHECK: Blank lines aren't necessary before a close brace '}'
Signed-off-by: Anjali Menon
---
drivers/staging/unisys/visornic/visornic_main.c | 1 -
1 file changed, 1
On 11/20/2015 11:39 AM, Greg KH wrote:
> On Fri, Nov 20, 2015 at 10:41:16AM -0500, Doug Ledford wrote:
>> To that end, I've opened my 4.4-rc branch and deleted the three
>> deprecated drivers from staging and moved hfi1 to the rdma tree. I've
>> sent an email to Linus to see if he's ok taking
> > drivers/staging/rdma/hfi1/sdma.c | 12 ++--
> > 1 files changed, 10 insertions(+), 2 deletions(-)
>
> Doesn't apply to my tree :(
Ok.
Is the inprocess branch available?
Mike
___
devel mailing list
de...@linuxdriverproject.org
>
> To that end, I've opened my 4.4-rc branch and deleted the three deprecated
> drivers from staging and moved hfi1 to the rdma tree. I've sent an email to
> Linus to see if he's ok taking those changes, and if so, I'll get them
> submitted
> and then open up my for-4.5 branch early to be able
> That sounds like a horrid hack, and this implies that a slower machine will
> still have this problem...
Greg,
I'm NAK'ing this patch for two reasons:
1. Code underneath the CONFIG option is only used during rework
2. It is a hack as you have noted
We are going to take this up internally to
Hi Doug,
before the drivers stops overloading writev vs write (hfi1_file_ops)
it MUST not be moved to the main tree.
___
devel mailing list
de...@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel
> >
> > Is the inprocess branch available?
>
> I do not understand what you mean here :(
Does it fail to apply to staging-next or staging-testing or something else?
Mike
___
devel mailing list
de...@linuxdriverproject.org
On Fri, Nov 20, 2015 at 04:43:56PM +, Marciniszyn, Mike wrote:
> > >
> > > Is the inprocess branch available?
> >
> > I do not understand what you mean here :(
>
> Does it fail to apply to staging-next or staging-testing or something else?
As both trees are now the same, it fails to apply
> > The longest quiet timeout is now 6s. Extend the driver wait.
>
> To what? And why? What does this fix?
>
The driver wasn't following the our internal specification: 6 seconds.
The patch corrects that issue.
Mike
___
devel mailing list
> > Are you saying dev_dbg() is a better choice?
>
> Yes, why would a user ever want to see that above line? What can they do
> with it?
Will do.
Mike
___
devel mailing list
de...@linuxdriverproject.org
On 11/19/2015 05:23 PM, Dennis Dalessandro wrote:
> On Thu, Nov 12, 2015 at 04:13:18PM -0500, Dennis Dalessandro wrote:
>> The major todo for the hfi1 driver in staging is getting rid of the
>> verbs code duplication between ipath, qib, and now hfi1. The ipath
>> driver has been deprecated and is
On Fri, Nov 20, 2015 at 10:41:16AM -0500, Doug Ledford wrote:
> On 11/19/2015 05:23 PM, Dennis Dalessandro wrote:
> > On Thu, Nov 12, 2015 at 04:13:18PM -0500, Dennis Dalessandro wrote:
> >> The major todo for the hfi1 driver in staging is getting rid of the
> >> verbs code duplication between
On Fri, Nov 20, 2015 at 03:23:55PM +, Marciniszyn, Mike wrote:
> > > drivers/staging/rdma/hfi1/sdma.c | 12 ++--
> > > 1 files changed, 10 insertions(+), 2 deletions(-)
> >
> > Doesn't apply to my tree :(
>
> Ok.
>
> Is the inprocess branch available?
I do not understand what
On Fri, Nov 20, 2015 at 10:41:16AM -0500, Doug Ledford wrote:
> To that end, I've opened my 4.4-rc branch and deleted the three
> deprecated drivers from staging and moved hfi1 to the rdma tree. I've
> sent an email to Linus to see if he's ok taking those changes, and if
> so, I'll get them
On Fri, Nov 20, 2015 at 03:14:19PM +, Marciniszyn, Mike wrote:
> > > + dd_dev_info(dd, "%s: program XMT margin, CcePcieCtrl 0x%llx\n",
> > > + fname, pcie_ctrl);
> >
> > Why spam the log with this all the time? Shouldn't this be a debug line
> > instead?
>
> The current
On Fri, Nov 20, 2015 at 11:58:18AM -0500, Doug Ledford wrote:
> On 11/20/2015 11:39 AM, Greg KH wrote:
> > On Fri, Nov 20, 2015 at 10:41:16AM -0500, Doug Ledford wrote:
> >> To that end, I've opened my 4.4-rc branch and deleted the three
> >> deprecated drivers from staging and moved hfi1 to the
On 11/20/2015 12:13 PM, Greg KH wrote:
>>> I think it's too late for that, especially given that I have 34+ patches
>>> for the staging rdma drivers already in my tree in linux-next.
>>
>> For hfi1 rename detection should work, for the other three, patches to
>> removed files are easily resolved
On Fri, Nov 20, 2015 at 04:01:18PM +, Marciniszyn, Mike wrote:
> > That sounds like a horrid hack, and this implies that a slower machine will
> > still have this problem...
>
> Greg,
>
> I'm NAK'ing this patch for two reasons:
> 1. Code underneath the CONFIG option is only used during
On 11/17/2015 05:18 PM, Greg KH wrote:
On Tue, Nov 17, 2015 at 09:57:58AM -0500, Benjamin Romer wrote:
This patch series adds a centralized infrastructure and device support
for channel interrupts sent to s-Par virtual devices. With these changes,
the visorhba device is ~80% faster than with
On Fri, Nov 20, 2015 at 01:59:02PM -0500, Ben Romer wrote:
> On 11/17/2015 05:18 PM, Greg KH wrote:
> >On Tue, Nov 17, 2015 at 09:57:58AM -0500, Benjamin Romer wrote:
> >>This patch series adds a centralized infrastructure and device support
> >>for channel interrupts sent to s-Par virtual
On Fri, Nov 20, 2015 at 03:21:14PM +, Marciniszyn, Mike wrote:
> > > The longest quiet timeout is now 6s. Extend the driver wait.
> >
> > To what? And why? What does this fix?
> >
>
> The driver wasn't following the our internal specification: 6 seconds.
>
> The patch corrects that
Beloved in Christ,
I am Mrs Arcelia Santos and was married to Late Mariano Santos who was a farmer
and a wine producer in Spain before he died after a few days in the hospital.
I have been suffering from cancer, I have a serious issue to discuss with you
about my donation project of
> > Add aeth name syndrome decode
>
> Again, why?
>
This fix is to enhance debugging.
The IBTA RC ACK contains an ACK extended transport header.
Part of that header is the syndrome field that qualifies the RC ACK as an ACK,
NAK, or RNR NAK.
Without the patch here is the syndrome decode:
The rmi4 touchscreen driver encloses the power-management
functions in #ifdef CONFIG_PM, but the smtcfb_pci_suspend/resume
functions are only really used when CONFIG_PM_SLEEP is also
set, as a frequent gcc warning shows:
ste_rmi4/synaptics_i2c_rmi4.c:1050:12: warning: 'synaptics_rmi4_suspend'
From: frank zago
This reduces the code size by about 400 bytes.
Signed-off-by: frank zago
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5396
Reviewed-on: http://review.whamcloud.com/11306
Reviewed-by: James Simmons
Reviewed-by: Patrick
From: John L. Hammond
Remove LUSTRE_LNET_PID (12354) and LUSTRE_SRV_LNET_PID (12345) from
the libcfs headers and replace their uses with a new macro
LNET_PID_LUSTRE (also 12345) in lnet/types.h.
Signed-off-by: John L. Hammond
Intel-bug-id:
From: Amir Shehata
This is the fifth patch of a set of patches that enables DLC.
This patch adds the new structures which will be used
in the IOCTL communication. It also added a set of
show operations to show buffers, networks, statistics
and peer information.
From: Amir Shehata
When loading Lustre modules without proper network configuration,
it always hit the following kernel panic:
LNetError: 105-4: Error -100 starting up LNI tcp
LNetError: 2145:0:(api-ni.c:823:lnet_unprepare())
ASSERTION( list_empty(_lnet.ln_nis) ) failed:
From: Amir Shehata
This patch addresses a set of related issues: LU-5734, LU-5839,
LU-5849, LU-5850.
Create the local lnet_startup_lndni() API. This function starts
up one LND. lnet_startup_lndnis() calls this function in a loop
on every ni in the list passed in.
From: Frank Zago
LIBCFS_ALLOC already zero out the memory allocated, so there is no
need to zero out the memory again.
Signed-off-by: Frank Zago
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5304
Reviewed-on: http://review.whamcloud.com/11012
Reviewed-by:
From: Amir Shehata
This is the fourth patch of a set of patches that enables DLC.
This patch changes the IOCTL infrastructure in preparation of
adding extra IOCTL communication between user and kernel space.
The changes include:
- adding a common header to be passed to
From: Amir Shehata
If there is an invalid networks or ip2nets lnet_parse_networks()
gets called with a NULL 'network' string parameter
lnet_parse_networks() needs to sanitize its input string now that
it's being called from multiple places. Instead, check for
a NULL
Like Lustre external infiniband stacks create a compatibility
layer to handle various distributions and kernel versions.
Due to this besides the linux kernel sk_sleep can also be
defined by the external infiniband stack. We need to examine
the infiniband stack's headers to see if sk_sleep is
From: Amir Shehata
In LNetCtl():IOC_LIBCFS_GET_NET there is a check for config == NULL
This is not necessary as it'll never be NULL. That's ensured before
the call to LNetCtl.
Signed-off-by: Amir Shehata
Intel-bug-id:
From: Ira Weiny
sdma_select_engine_vl only needs to protect itself from an invalid VL.
Something higher up the stack should be warning the user when they try
to use an SL which maps to an invalid VL.
Reviewed-by: Dean Luick
Reviewed-by: Mike Marciniszyn
From: Chris Horn
We consider routes "down" if the router is down or the router
NI for the target network is down. This should be reflected
in the output of /proc/sys/lnet/routes
Signed-off-by: Chris Horn
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-3679
Remove the bulk of code for the no longer supported
SeaStar interconnect found on older Cray systems.
Signed-off-by: James Simmons
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-1422
Reviewed-on: http://review.whamcloud.com/7469
Reviewed-by: Liang Zhen
From: Liang Zhen
returned value of lnet_post_send_locked and
lnet_post_routed_recv_locked are changed to -ve by:
http://review.whamcloud.com/#/c/9369/
this is wrong because callers rely on +ve to identify blocked
message which is not a failure.
To respect linux kernel
When lnet_text_buf data structure was transform from typedef
to struct the *_t which is typical of typedef was not drop.
This patch removes the *_t to be consistent.
Signed-off-by: James Simmons
---
drivers/staging/lustre/lnet/lnet/config.c | 57
On Fri, Nov 20, 2015 at 10:41:16AM -0500, Doug Ledford wrote:
> So, as to the hfi1/qib/rxe transport library. The qib driver is in the
> rdma tree, and we aren't going to move it to staging just because it
> depends on something in staging, so we need to start adding the library
> in the core
hfi1 driver build fails with the following error:
In function ‘handle_receive_interrupt’:
error: implicit declaration of function ‘skip_rcv_packet’
[-Werror=implicit-function-declaration]
last = skip_rcv_packet(, thread);
^
This is due to the inclusion of the skip_rcv_packet() in the
This is the majority of the fixes that have gone into the LNet layer.
Outside a few remaining patches this brings LNet close to what is
running in production world wide.
This patch series needs the remove IOC_LIBCFS_PING_TEST ioctl patch
landed first.
Amir Shehata (19):
staging: lustre:
From: Amir Shehata
This is the second patch of a set of patches that enables DLC.
This patch adds the following features to LNET. Currently these
features are not driven by user space.
- Enabling Routing on Demand. The default number of router
buffers are allocated.
From: John L. Hammond
Remove most uses of IS_ERR_VALUE(). This macro was often given an int
argument coming from PTR_ERR(). This invokes implementation defined
behavior since the long value gotten by applying PTR_ERR() to a kernel
pointer will usually not be representable
From: Amir Shehata
This is the third patch of a set of patches that enables DLC.
This patch adds the following features to LNET. Currently these
features are not driven by user space.
- Adding/Deleting Networks dynamically
Two new functions were added:
-
From: Liang Zhen
error handler of lnet_create_reply_msg() didn't release lnet_res_lock
if lnet_msg_alloc() failed.
It can be fixed by moving validation check of msg out from lock.
Signed-off-by: Liang Zhen
Intel-bug-id:
From: Liang Zhen
- libcfs_ioctl_popdata should copy out inline buffers.
- code cleanup for libcfs ioctl handler
- error number fix for obd_ioctl_getdata
- add new function libcfs_ioctl_unpack for upcoming patches
Signed-off-by: Liang Zhen
From: frank zago
This fixes sparse warnings such as:
.../api-ni.c:1639:33: warning: incorrect type in argument 3
(different address spaces)
.../api-ni.c:1639:33: expected struct lnet_process_id_t
[noderef]
During testing of the lnetctl utility I ran into some
issues. One of the problems is when you print out help
for peer_credits you get help for stats. With this patch
the help option for peer_credits is set to return the
proper help message.
The second problem was for grabbing stats data. No data
From: Amir Shehata
This is the sixth patch of a set of patches that enables DLC.
This patch enables the user space to call into the kernel space
DLC code. Added handlers in the LNetCtl function to call
the new functions added for Dynamic Lnet Configuration
From: Amir Shehata
When adding route it ignored specific scenarios, namely:
1. route already exists
2. route is on a local net
3. route is unreacheable
This patch returns the appropriate return codes from the lower level
function lnet_add_route(), and then ignores the
From: frank zago
Some functions and variables are only used in their C file, so reduce
their scope. This reduces the code size, and fixes sparse warnings
such as:
warning: symbol 'proc_lnet_routes' was not declared.
Should it be static?
warning: symbol
From: Amir Shehata
There is a use case where lnet can be unloaded while there are
no NIs configured. Removing lnet in this case will cause
LNetFini() to be called without a prior call to LNetNIFini().
This will cause the LASSERT(the_lnet.ln_refcount == 0) to be
From: Chris Horn
lctl show_route and lctl route_list will output router aliveness
information via lnet_get_route(). lnet_get_route() should use the
lnet_is_route_alive() function, introduced in e8a1124
http://review.whamcloud.com/7857, to determine route aliveness.
From: Doug Oucharek
In lnet_router_checker(), there are two LASSERTS. Neither protects
us from anything and one of them triggered for a customer crashing
the system unecessarily. This patch removes them.
Signed-off-by: Doug Oucharek
From: Bruno Faccini
This patch will avoid potential race, around socket sleepers
wait list, during acceptor thread termination and using
sk_callback_lock RW-Lock protection.
Signed-off-by: Bruno Faccini
Intel-bug-id:
From: John L. Hammond
In lnet/lnet/ and lnet/selftest/ assume a kernel build (assume that
__KERNEL__ is defined). Remove some common code only needed for user
space LNet.
Only part of the work of this patch got merged. This is the final
bits.
Signed-off-by: John L.
From: Amir Shehata
This patch starts router checker thread all the time.
The router checker only checks routes by ping if
live_router_check_interval or dead_router_check_interval are set
to something other than 0, and there are routes configured.
If these conditions are
From: Amir Shehata
Currently if there exists a route that goes over a
remote net and then this net is added dynamically as
a local net, then traffic stops because the code in
lnet_send() determines that the destination nid
can be reached from another local_ni, but the
From: frank zago
A lot of symbols don't need to be exported at all because they are
only used in the module they belong to.
Signed-off-by: frank zago
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5829
Reviewed-on: http://review.whamcloud.com/13320
From: frank zago
It is preferable to use NULL instead of 0 for pointers. This fixes sparse
warnings such as:
lustre/fld/fld_request.c:126:17: warning: Using plain integer as NULL pointer
The second parameter of class_match_param() was changed to a const, to
be able to remove a
From: Amir Shehata
With DLC it's possible to start up a system with no NIs that require
the acceptor thread, and thus it won't start. Later on the user
can add an NI that requires the acceptor thread to start, it is
then necessary to start it up.
If the user removes a
From: Amir Shehata
Return -EEXIST and not -EINVAL when trying to add a
network interface which is not unique.
Some minor cleanup in api-ni.c
Signed-off-by: Amir Shehata
Intel-bug-id: https://jira.hpdd.intel.com/browse/LU-5875
Reviewed-on:
From: Amir Shehata
This patch ensures that the correct number of router buffers are
allocated. It keeps a count that keeps track of the number of
buffers allocated. Another count keeps the number of buffers
requested. The number of buffers allocated is set when creating
From: Amir Shehata
After adding a route, lnet_check_routes() is called to ensure that
the route added doesn't invalidate the routing configuration. If
lnet_check_routes() fails then the route just added, which caused the
current configuration to be invalidated is
From: Sebastien Buisson
Fix 'NULL pointer dereference' defects found by Coverity version
6.5.3:
Dereference after null check (FORWARD_NULL)
For instance, Passing null pointer to a function which dereferences
it.
Dereference before null check (REVERSE_INULL)
From: Amir Shehata
When shutting down an NI in a busy system, some messages received
on this NI, might be on the lazy portal. They would have grabbed
a ref count on the NI. Therefore NI will not be removed until
messages are processed.
In order to avoid this scenario,
On Fri, Nov 20, 2015 at 09:00:23AM -0800, Greg KH wrote:
> On Fri, Nov 20, 2015 at 04:43:56PM +, Marciniszyn, Mike wrote:
> > > >
> > > > Is the inprocess branch available?
> > >
> > > I do not understand what you mean here :(
> >
> > Does it fail to apply to staging-next or staging-testing
On Fri, Nov 20, 2015 at 3:06 AM, Greg Kroah-Hartman
wrote:
> On Thu, Nov 12, 2015 at 07:58:54AM +0200, Or Gerlitz wrote:
>> On Sat, Oct 31, 2015 at 12:41 AM, wrote:
>> So this is an wholy orthogonal mechanism for memory registrations or
>>
Moved the comments to the next line to remove the warning
detected by the checkpatch.pl.
WARNING: line over 80 characters
Signed-off-by: Anjali Menon
---
drivers/staging/panel/panel.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git
77 matches
Mail list logo