rds_ib_set_wr_signal_state() function.
However, this function is not always used which yields inaccurate
accounting. This commit fixes this, re-factors a code bloat related to
the matter, and makes the actual parameter type to the function
consistent.
Signed-off-by: Håkon Bugge
---
net/rds/ib_send.c | 15
send_flags needs to be initialized before calling
rds_ib_set_wr_signal_state().
Signed-off-by: Håkon Bugge
---
net/rds/ib_send.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 6ab39db..8f46755 100644
--- a/net/rds/ib_send.c
+++ b/net/rds
send_flags needs to be initialized before calling
rds_ib_set_wr_signal_state().
Signed-off-by: Håkon Bugge
---
net/rds/ib_send.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 6ab39db..8f46755 100644
--- a/net/rds/ib_send.c
+++ b/net/rds
Ignore this, sent the old one.
Håkon
> On 24 Oct 2017, at 18:07, Håkon Bugge wrote:
>
> send_flags needs to be initialized before calling
> rds_ib_set_wr_signal_state().
>
> Signed-off-by: Håkon Bugge
> ---
> net/rds/ib_send.c | 1 +
> 1 file changed, 1 insertion(+
send_flags needs to be initialized before calling
rds_ib_set_wr_signal_state().
Signed-off-by: Håkon Bugge
Acked-by: Santosh Shilimkar
---
net/rds/ib_send.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 6ab39db..8f46755 100644
--- a/net/rds
> On 10 May 2018, at 18:54, Hal Rosenstock wrote:
>
> On 5/10/2018 11:16 AM, Håkon Bugge wrote:
>>
>>
>>> On 10 May 2018, at 16:01, Hal Rosenstock wrote:
>>>
>>> On 5/10/2018 5:16 AM, Håkon Bugge wrote:
>>>>
>>>>
&
> On 29 May 2018, at 18:40, Jason Gunthorpe wrote:
>
> On Tue, May 29, 2018 at 06:16:14PM +0200, Håkon Bugge wrote:
>>
>>> On 29 May 2018, at 17:49, Jason Gunthorpe wrote:
>>>
>>> On Tue, May 29, 2018 at 09:38:08AM +0200, Hans Westgaard Ry wrote:
> On 30 May 2018, at 17:10, Jason Gunthorpe wrote:
>
> On Wed, May 30, 2018 at 02:22:56PM +0200, Hans Westgaard Ry wrote:
>
>> We came up with this code snippet which we think handles both preventing
>> immediate re-use and too big/wrapping...
>
> Isn't this basically the same as idr_alloc_c
> On 31 May 2018, at 00:09, Jason Gunthorpe wrote:
>
> On Wed, May 30, 2018 at 10:07:16PM +0200, Håkon Bugge wrote:
>>
>>
>>> On 30 May 2018, at 17:10, Jason Gunthorpe wrote:
>>>
>>> On Wed, May 30, 2018 at 02:22:56PM +0200, Hans Westgaa
enum.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/core/cm.c | 14 ++
drivers/infiniband/core/cm_msgs.h | 7 ---
2 files changed, 6 insertions(+), 15 deletions(-)
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index de699f67a755..4724cb09b69d
SMPs were not printed at all. Added printing of port number and TID to
all MADs
Håkon Bugge (2):
IB/mlx4: Enable debug print of SMPs
IB/mlx4: Add port and TID to MAD debug print
drivers/infiniband/hw/mlx4/mad.c | 20 +++-
1 file changed, 11 insertions(+), 9 deletions
IB Subnet Management Packets (SMPs) were excluded from debug prints.
Fixed by enabling print even on QP0 MADs.
Signed-off-by: Håkon Bugge
---
v1 -> v3:
* No changes
---
drivers/infiniband/hw/mlx4/mad.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infinib
Add said information and make the debug print format consistent.
Signed-off-by: Håkon Bugge
Acked-by: Leon Romanovsky
---
v1 -> v2:
* Fixed incorrect format for printing the TID
v2 -> v3:
* Added Leon's a-b
---
drivers/infiniband/hw/mlx4/mad.c | 18 ++
1 f
Let uapi/linux/if_arp.h include uapi/linux/if.h, where IFNAMSIZ is
defined. Then, use it in this file instead of hard-coded value.
This way, we are using an uapi defined constant, and as such,
user-space should be good.
Signed-off-by: Håkon Bugge
Tested-by: Stephen Hemminger
---
v1 ->
Commit f27b4746f378 ("i40iw: add connection management code") uses an
incorrect rcu iterator, whilst holding the rtnl_lock. Since the
critical region invokes i40iw_manage_qhash(), which is a sleeping
function, the rcu locking and traversal cannot be used.
Signed-off-by: Håkon Bugge
--
SMPs were not printed at all. Added printing of port number and TID to
all MADs
Håkon Bugge (2):
IB/mlx4: Enable debug print of SMPs
IB/mlx4: Add port and TID to MAD debug print
drivers/infiniband/hw/mlx4/mad.c | 20 +++-
1 file changed, 11 insertions(+), 9 deletions
IB Subnet Management Packets (SMPs) were excluded from debug prints.
Fixed by enabling print even on QP0 MADs.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/hw/mlx4/mad.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers
Add said information and make the debug print format consistent.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/hw/mlx4/mad.c | 18 ++
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index
Add said information and make the debug print format consistent.
Signed-off-by: Håkon Bugge
--
v1 -> v2
* Fixed incorrect format for printing the TID
---
drivers/infiniband/hw/mlx4/mad.c | 18 ++
1 file changed, 10 insertions(+), 8 deletions(-)
diff --git a/driv
IB Subnet Management Packets (SMPs) were excluded from debug prints.
Fixed by enabling print even on QP0 MADs.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/hw/mlx4/mad.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers
SMPs were not printed at all. Added printing of port number and TID to
all MADs
Håkon Bugge (2):
IB/mlx4: Enable debug print of SMPs
IB/mlx4: Add port and TID to MAD debug print
drivers/infiniband/hw/mlx4/mad.c | 20 +++-
1 file changed, 11 insertions(+), 9 deletions
tion and could be
>> safely allocated by vmalloc.
>>
>> Signed-off-by: Jan Dakinevich
lgtm,
Reviewed-by: Håkon Bugge
Thxs, Håkon
>> ---
>> drivers/infiniband/ulp/ipoib/ipoib_main.c | 4 ++--
>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
&
> On 23 Apr 2018, at 21:16, jackm wrote:
>
> On Mon, 23 Apr 2018 16:19:57 +0200
> Håkon Bugge wrote:
>
>
>>>
>>> This actually looks like a genuine bug, why is it described only as
>>> 'confusing'? ib_register_mad_agent is callable f
> On 27 Apr 2018, at 21:08, Doug Ledford wrote:
>
> On Thu, 2018-04-26 at 20:51 +0200, Håkon Bugge wrote:
>>> Jason is out this week. I'll end up processing this one (probably later
>>> today). But I’ll fix up the commit message to suit my tastes when I do.
le for two threads on different ports to end up with the same
>> TID.
>>
>> As this can be confusing (regardless of it being legal according to
>> the IB Spec 1.3, C13-18.1.1, in section 13.4.6.4 - TransactionID
>> usage), and as the rdma-core user space API for /de
> On 29 May 2018, at 17:49, Jason Gunthorpe wrote:
>
> On Tue, May 29, 2018 at 09:38:08AM +0200, Hans Westgaard Ry wrote:
>> The agent TID is a 64 bit value split in two dwords. The least
>> significant dword is the TID running counter. The most significant
>> dword is the agent number. In th
> On 15 May 2018, at 02:38, Hal Rosenstock wrote:
>
> On 5/14/2018 5:02 PM, Jason Gunthorpe wrote:
>> On Thu, May 10, 2018 at 05:16:28PM +0200, Håkon Bugge wrote:
>>
>>> We are talking about two things here. The PKey in the BTH and the
>>> PKey in the
> On 15 May 2018, at 21:04, Jason Gunthorpe wrote:
>
> On Tue, May 15, 2018 at 08:11:09PM +0200, Håkon Bugge wrote:
>>> On 15 May 2018, at 02:38, Hal Rosenstock wrote:
>>>
>>> On 5/14/2018 5:02 PM, Jason Gunthorpe wrote:
>>>> On Thu, May
> On 16 May 2018, at 20:01, Jason Gunthorpe wrote:
>
> On Wed, May 16, 2018 at 07:46:10PM +0200, Håkon Bugge wrote:
>
>> OK. Lets take one example. The pkey table contains 0x, 0x8001,
>> 0x0001.
>>
>> The wce.pkey_index is 1 (i.e., po
c29 ("rds: ib: add error handle")
>
> Signed-off-by: Dag Moxnes
Reviewed-by: Håkon Bugge
Thxs, Håkon
> ---
> net/rds/ib_cm.c |3 ++-
> 1 files changed, 2 insertions(+), 1 deletions(-)
>
> diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
> index eea1d86..13
> On 5 Feb 2019, at 23:36, Jason Gunthorpe wrote:
>
> On Thu, Jan 31, 2019 at 06:09:51PM +0100, Håkon Bugge wrote:
>> Using CX-3 virtual functions, either from a bare-metal machine or
>> pass-through from a VM, MAD packets are proxied through the PF driver.
>>
>
> On 6 Feb 2019, at 09:50, Håkon Bugge wrote:
>
>
>
>> On 5 Feb 2019, at 23:36, Jason Gunthorpe wrote:
>>
>> On Thu, Jan 31, 2019 at 06:09:51PM +0100, Håkon Bugge wrote:
>>> Using CX-3 virtual functions, either from a bare-metal machine or
>
> On 6 Feb 2019, at 19:02, jackm wrote:
>
> On Wed, 6 Feb 2019 16:40:14 +0100
> Håkon Bugge wrote:
>
>> Jack,
>>
>> A major contributor to the long processing time in the PF driver
>> proxying QP1 packets is:
>>
>> c
son Gunthorpe wrote:
>>>> On Sun, Feb 17, 2019 at 06:09:09PM +0100, Håkon Bugge wrote:
>>>>> During certain workloads, the default CM response timeout is too
>>>>> short, leading to excessive retries. Hence, make it configurable
>>>>>
During certain workloads, the default CM response timeout is too
short, leading to excessive retries. Hence, make it configurable
through sysctl. While at it, also make number of CM retries
configurable.
The defaults are not changed.
Signed-off-by: Håkon Bugge
---
v1 -> v2:
* Ad
> On 31 Jul 2020, at 11:59, Dan Carpenter wrote:
>
> On Fri, Jul 31, 2020 at 07:53:01AM +0300, Leon Romanovsky wrote:
>> On Thu, Jul 30, 2020 at 03:20:26PM -0400, Peilin Ye wrote:
>>> rds_notify_queue_get() is potentially copying uninitialized kernel stack
>>> memory to userspace since the com
> On 31 Jul 2020, at 13:59, Greg Kroah-Hartman
> wrote:
>
> On Fri, Jul 31, 2020 at 01:14:09PM +0200, Håkon Bugge wrote:
>>
>>
>>> On 31 Jul 2020, at 11:59, Dan Carpenter wrote:
>>>
>>> On Fri, Jul 31, 2020 at 07:53:01AM +0300, Leon R
ime value before retrying the send.
The 5-bit value to be supplied to the rdma_set_min_rnr_timer() is
documented in IBTA Table 45: "Encoding for RNR NAK Timer Field".
Signed-off-by: Håkon Bugge
Acked-by: Jason Gunthorpe
---
drivers/infiniband/core/cm
ib_modify_qp() is an expensive operation on some HCAs running
virtualized. This series removes two ib_modify_qp() calls from RDS.
I am sending this as a v3, even though it is the first sent to
net. This because the IB Core commit has reach v3.
Håkon Bugge (2):
IB/cma: Introduce
rface to shave off another ib_modify_qp().
Fixes: ec16227e1414 ("RDS/IB: Infiniband transport")
Signed-off-by: Håkon Bugge
---
net/rds/ib_cm.c | 35 +--
net/rds/rdma_transport.c | 1 +
2 files changed, 2 insertions(+), 34 deletions(-)
diff --git a
In addr_handler(), assuming status == 0 and the device already has
been acquired (id_priv->cma_dev != NULL), we get the following
incorrect "error" message:
RDMA CM: ADDR_ERROR: failed to resolve IP. status 0
Signed-off-by: Håkon Bugge
---
drivers/infiniband/core/cma.c | 2 +-
1
> On 20 Feb 2019, at 18:14, Jason Gunthorpe wrote:
>
> On Tue, Feb 19, 2019 at 06:32:50PM +0100, Håkon Bugge wrote:
>> Anyway, Jason mentioned in a private email that maybe we could use the
>> new completion API or something? I am not familiar with that one
>>
Sorry,
I posted this as if it a net patch. It isn't, hence resend with correct
recipients.
Thxs, Håkon
> On 31 Jan 2019, at 18:09, Håkon Bugge wrote:
>
> Using CX-3 virtual functions, either from a bare-metal machine or
> pass-through from a VM, MAD packets are proxi
> On 10 Jun 2019, at 19:53, Jason Gunthorpe wrote:
>
> On Mon, Feb 18, 2019 at 07:33:02PM +0100, Håkon Bugge wrote:
>> MAD packet sending/receiving is not properly virtualized in
>> CX-3. Hence, these are proxied through the PF driver. The proxying
>> uses UD
idn't help, as these duplicates and
retries stems from a too short CMA timeout, which was 20 (~4 seconds)
on the systems. By increasing the CMA timeout to 22 (~17 seconds), the
numbers fell down to about 10 for both of them.
Adjustment of the CMA timeout is not part of this commit.
Signed-off
During certain workloads, the default CM response timeout is too
short, leading to excessive retries. Hence, make it configurable
through sysctl. While at it, also make number of CM retries
configurable.
The defaults are not changed.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/core/cma.c
:4, num_comp_vectors:62
create_pv_resources: slave:1 port:2, vector:5, num_comp_vectors:62
[]
create_pv_resources: slave:8 port:2, vector:18, num_comp_vectors:62
create_pv_resources: slave:8 port:1, vector:19, num_comp_vectors:62
Signed-off-by: Håkon Bugge
---
drivers/infiniband/hw/mlx4/mad.c | 4
Hi Faisal,
In commit f27b4746f378 ("i40iw: add connection management code") you have in
i40iw_add_mqh_6():
rtnl_lock();
for_each_netdev_rcu(...) {
[]
}
rtnl_unlock();
Shouldn't this read:
rtnl_lock();
for_each_netdev(...) {
[]
}
rtnl_unlock();
or
rcu_read_lock();
for_each_ne
Hi Greg,
I hope you will find this note appropriate.
The stable cherry-pick of upstream commit ebeeb1ad9b8a ("rds: tcp: use
rds_destroy_pending() to synchronize netns/module teardown and rds
connection/workq management") provokes the following stack trace when running
with debug:
kernel: BU
> On 7 Jun 2018, at 17:37, Matthew Wilcox wrote:
>
> Why do you need the ID to increment like this? Why can't you just use a
> unique ID?
Hans first patch did that, but it was "beaten" up. Turns out, MAD packets can
be hiding and lingering in the fabric, hence, when an ID is released after
+Jack
> On 20 Apr 2018, at 17:34, Jason Gunthorpe wrote:
>
> On Thu, Apr 19, 2018 at 11:55:55PM -0400, Doug Ledford wrote:
>> On Wed, 2018-04-18 at 16:24 +0200, Håkon Bugge wrote:
>>> Two kernel threads may get the same value for agent.hi_tid, if the
>>> ag
introduced, which requires at least
one of the pkeys to be a full member, in order to return success.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/core/cache.c | 32 +++-
include/rdma/ib_cache.h | 18 ++
2 files changed, 45 insertions(+), 5
first commit in the
second commit message with a correct 12 chars SHA]
Håkon Bugge (2):
IB/core: A full pkey is required to match a limited one
IB/cm: Send authentic pkey in REQ msg and check eligibility of the
pkeys
drivers/infiniband/core/cache.c | 32
s the full-member bit.
In the limited-to-limited case, this will prohibit the connection to
be formed, and thus, Pkey Violation Traps will not be sent to the SM.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/core/cm.c | 39 ---
include/rdma/ib_cm.h |
> On 9 May 2018, at 13:28, Hal Rosenstock wrote:
>
> On 5/9/2018 5:30 AM, Håkon Bugge wrote:
>> There is no point in using RDMA CM to establish a connection between
>> two QPs that cannot possible communicate. Particularly, if both the
>> active and passive side use
> On 10 May 2018, at 16:01, Hal Rosenstock wrote:
>
> On 5/10/2018 5:16 AM, Håkon Bugge wrote:
>>
>>
>>> On 9 May 2018, at 13:28, Hal Rosenstock wrote:
>>>
>>> On 5/9/2018 5:30 AM, Håkon Bugge wrote:
>>>> There is no point in
> On 11 May 2018, at 01:31, Qing Huang wrote:
>
> When a system is under memory presure (high usage with fragments),
> the original 256KB ICM chunk allocations will likely trigger kernel
> memory management to enter slow path doing memory compact/migration
> ops in order to complete high order
Two kernel threads may get the same value for agent.hi_tid, if the
agents are registered for different ports. As of now, this works, as
the agent list is per port.
It is however confusing and not future robust. Hence, making it
atomic.
Signed-off-by: Håkon Bugge
Reviewed-by: Jack Morgenstein
> On 21 Aug 2020, at 10:10, Dinghao Liu wrote:
>
> When ida_alloc_max() fails, uverbs_dev should be freed
> just like when init_srcu_struct() fails. It's the same
> for the error paths after this call.
>
> Signed-off-by: Dinghao Liu
> ---
> drivers/infiniband/core/uverbs_main.c | 1 +
> 1 fil
> On 13 Jun 2019, at 19:23, Jason Gunthorpe wrote:
>
> On Thu, Jun 13, 2019 at 06:58:30PM +0200, Håkon Bugge wrote:
>
>> If you refer to the backlog parameter in rdma_listen(), I cannot see
>> it being used at all for IB.
>>
>> For CX-3, which is paravir
> On 13 Jun 2019, at 16:25, Doug Ledford wrote:
>
> On Tue, 2019-02-26 at 08:57 +0100, Håkon Bugge wrote:
>> During certain workloads, the default CM response timeout is too
>> short, leading to excessive retries. Hence, make it configurable
>> through sysctl. While
> On 13 Jun 2019, at 22:25, Doug Ledford wrote:
>
> On Thu, 2019-06-13 at 18:58 +0200, Håkon Bugge wrote:
>>> On 13 Jun 2019, at 16:25, Doug Ledford wrote:
>>>
>>> On Tue, 2019-02-26 at 08:57 +0100, Håkon Bugge wrote:
>>>> During certain w
he
numbers fell down to about one hundred for both of them.
Adjustment of the CMA timeout is _not_ part of this commit.
Signed-off-by: Håkon Bugge
---
drivers/infiniband/hw/mlx4/cm.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/hw/mlx4/cm.c b/drivers/inf
del:
Loads from and stores to shared (but non-atomic) variables should
be protected with the READ_ONCE(), WRITE_ONCE(), and
ACCESS_ONCE().
Clause 5.1.2.4/25 in the C standard is also relevant.
Signed-off-by: Håkon Bugge
Reviewed-by: Knut Omang
---
net/rds/send.c | 6 +++---
1 f
> On 20 Jul 2017, at 13:02, Sowmini Varadhan
> wrote:
>
> On (07/20/17 12:28), H??kon Bugge wrote:
>> cp->cp_send_gen is treated as a normal variable, although it may be
>> used by different threads.
>
> I'm confused by that assertion. If you look at the comments right
> above the change in yo
The bits in m_flags in struct rds_message are used for a plurality of
reasons, and from different contexts. To avoid any missing updates to
m_flags, use the atomic set_bit() instead of the non-atomic equivalent.
Signed-off-by: Håkon Bugge
Reviewed-by: Knut Omang
Reviewed-by: Wei Lin Guay
the race and
increments the statistics counter correctly.
Signed-off-by: Håkon Bugge
Reviewed-by: Knut Omang
---
net/rds/send.c | 16 +---
1 file changed, 13 insertions(+), 3 deletions(-)
diff --git a/net/rds/send.c b/net/rds/send.c
index 058a407..ecfe0b5 100644
--- a/net/rds/send.c
> On 6 Sep 2017, at 17:58, Santosh Shilimkar
> wrote:
>
> On 9/6/2017 8:29 AM, Håkon Bugge wrote:
>> In rds_send_xmit() there is logic to batch the sends. However, if
>> another thread has acquired the lock, it is considered a race and we
>> yi
counts the race condition correctly.
Changes from v1:
- Removed check for *someone_on_xmit()*
- Fixed incorrect indentation
Signed-off-by: Håkon Bugge
Reviewed-by: Knut Omang
---
net/rds/send.c | 10 +++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/net/rds/send.c b/net/rds
re-introduces filling the receive queue from rds_ib_recv(), but does
not add the statistics counter. rds_ib_recv() was later renamed to
rds_ib_recv_path().
This commit reintroduces the statistics counting of
s_ib_rx_refill_from_thread and s_ib_rx_refill_from_cq.
Signed-off-by: Håkon Bugge
Reviewed
02 00 00 48
89 55 d0 48 89 4d c8 85 c0 0f 84 2d 03 00 00 48 8b 87 00 03 00 00 <48>
83 b8 c0 00 00 00 00 0f 84 25 03 00 0 0 48 8b 06 48 8b 56 08
The fix is to check the existence of an underlying transport in
__rds_rdma_map().
Signed-off-by: Håkon Bugge
Reported-by: syzbot
---
net/rds/rdma
ag->f_sg),
(long) ib_sg_dma_address(
The fix is simply to move the rdsdebug() statement up before the
ib_post_recv() and remove the printing of ret, which is taken care of
anyway by the non-debug code.
Signed-off-by: Håkon Bugge
Reviewed-by: Knut Omang
Reviewed-by: Wei L
72 matches
Mail list logo
