On Sun, Oct 11, 2015 at 11:58 PM, Or Gerlitz wrote:
> Hi Doug,
> As we're soon on 4.3-rc5, could you please update how things look for 4.4?
>
> The mutlicast loopback prevention patches from Eran were intially
> posted ~two months ago and went through testing by Christoph and Co.
[...]
Hi Doug,
On Tue, Oct 13, 2015 at 08:38:20AM -0400, Hal Rosenstock wrote:
>
> src/ibqueryerrors.c: In function ?print_port_config?:
> src/ibqueryerrors.c:176: warning: unused parameter ?node_name?
> src/ibqueryerrors.c: In function ?query_and_dump?:
> src/ibqueryerrors.c:367: warning: unused parameter ?node
On Tue, Oct 13, 2015 at 08:38:02AM -0400, Hal Rosenstock wrote:
>
> src/ibcacheedit.c: In function ?update_switchportguids?:
> src/ibcacheedit.c:168: warning: unused parameter ?guid?
>
> Signed-off-by: Hal Rosenstock
Thanks applied,
Ira
> ---
> diff --git a/src/ibcacheedit.c b/src/ibcacheedit.
> On Mon, Oct 12, 2015 at 7:42 PM, Hefty, Sean wrote:
> >> When IP based addressing was introduced, ib_create_ah_from_wc was
> >> changed in order to support a suitable AH. Since this AH should
> >> now contains the DMAC (which isn't a simple derivative of the GID).
> >> In order to find the DMAC,
> On Oct 13, 2015, at 12:11 PM, Sagi Grimberg wrote:
>
> Instead of maintaining a fastreg page list, keep an sg table
> and convert an array of pages to a sg list. Then call ib_map_mr_sg
> and construct ib_reg_wr.
>
> Signed-off-by: Sagi Grimberg
> Acked-by: Christoph Hellwig
> Tested-by: Ste
Support the new memory registration API by allocating a
private page list array in qib_mr and populate it when
qib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating qib_fastreg_mr just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (q
iser is perfectly capable supporting SG clustering as it translates
the SG list to a page vector. Enabling SG clustering can dramatically
reduce the number of SG elements, which doesn't make much of a difference
at this point, but with arbitrary SG list support, reducing the
number of SG elements c
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/cxgb3/iwch_cq.c | 2 +-
drivers/infiniband/hw/cxgb3/iwch_provider.c | 24 ---
drivers/infiniband/hw/cxgb3/iwch_qp.c | 47 --
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx4/cq.c | 3 +--
drivers/infiniband/hw/mlx4/main.c| 2 --
drivers/infiniband/hw/mlx4/mlx4_ib.h | 15 ---
drivers/infiniband/hw/mlx4/mr.c |
Remove fastreg page list allocation as the page vector
is now private to the provider. Instead of constructing
the page list and fast_req work request, call ib_map_mr_sg
and construct ib_reg_wr.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/ulp/iser/iscsi_iser.
Up until now, iser used bounce buffering to mitigate the
RDMA alignment limitations. Since kernel 4.3, the block layer
can reliably guarantee that SG lists won't contain gaps
(page alignment is not met) if a driver set a virt_boundary.
The block layer will:
- refuse merges if bios are not aligned
Remove fastreg page list allocation as the page vector
is now private to the provider. Instead of constructing
the page list and fast_req work request, call ib_map_mr_sg
and construct ib_reg_wr.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/ulp/isert/ib_isert.c
Instead of maintaining a fastreg page list, keep an sg table
and convert an array of pages to a sg list. Then call ib_map_mr_sg
and construct ib_reg_wr.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
Tested-by: Steve Wise
Tested-by: Selvin Xavier
---
include/linux/sunrpc/svc_rdma.h
The new fast registration API does not reuqire a page vector
so we can't avoid allocating it.
Signed-off-by: Sagi Grimberg
Tested-by: Bart Van Assche
---
drivers/infiniband/ulp/srp/ib_srp.c | 20 +++-
1 file changed, 11 insertions(+), 9 deletions(-)
diff --git a/drivers/infinib
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/qib/qib_keys.c | 56 ---
drivers/infiniband/hw/qib/qib_mr.c| 32 +---
drivers/infiniband/hw/qib/qib_verbs.c |
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/nes/nes_hw.h| 6 --
drivers/infiniband/hw/nes/nes_verbs.c | 162 +-
2 files changed, 1 insertion(+), 167 deletions(-)
diff --
No callers and no providers left, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/core/verbs.c | 25 ---
include/rdma/ib_verbs.h | 54 -
2 files changed, 79 deletions(-)
diff
This is a preparation patch for the new registration API
conversion. It splits srp_map_sg per registration strategy
(srp_map_sg[fmr|fr|dma]. On its own it adds some code duplication,
but it makes the API switch easier to comprehend.
Signed-off-by: Sagi Grimberg
Tested-by: Bart Van Assche
---
dr
The block layer can reliably guarantee that SG lists won't
contain gaps (page unaligned) if a driver set the queue
virt_boundary.
With this setting the block layer will:
- refuse merges if bios are not aligned to the virtual boundary
- split bios/requests that are not aligned to the virtual bounda
No ULP uses it anymore, go ahead and remove it.
Keep only the local invalidate part of the handlers.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx5/cq.c | 3 --
drivers/infiniband/hw/mlx5/main.c| 2 -
drivers/infiniband/hw/mlx5/mlx5_ib.h | 14
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/cxgb4/cq.c | 2 +-
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 18
drivers/infiniband/hw/cxgb4/mem.c | 45
drivers/infiniband
No ULP uses it anymore, go ahead and remove it.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/ocrdma/ocrdma_main.c | 2 -
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 104 +---
drivers/infiniband/hw/ocrdma/ocrdma_verbs.h | 4 --
Support the new memory registration API by allocating a
private page list array in mlx4_ib_mr and populate it when
mlx4_ib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by setting the exact WQE as IB_WR_FAST_REG_MR, just take the
needed information from different places:
- page_size, iova, lengt
Get rid of fast_reg page list and its construction.
Instead, just pass the RDS sg list to ib_map_mr_sg
and post the new ib_reg_wr.
This is done both for server IW RDMA_READ registration
and the client remote key registration.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
Acked-by: Sa
Instead of maintaining a fastreg page list, keep an sg table
and convert an array of pages to a sg list. Then call ib_map_mr_sg
and construct ib_reg_wr.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
Tested-by: Steve Wise
Tested-by: Selvin Xavier
---
net/sunrpc/xprtrdma/frwr_ops.c
Instead of constructing a page list, call ib_map_mr_sg
and post a new ib_reg_wr. srp_map_finish_fr now returns
the number of sg elements registered.
Remove srp_finish_mapping since no one is calling it.
Signed-off-by: Sagi Grimberg
Tested-by: Bart Van Assche
---
drivers/infiniband/ulp/srp/ib_s
No callers left, remove it.
Signed-off-by: Sagi Grimberg
Tested-by: Bart Van Assche
---
drivers/infiniband/ulp/srp/ib_srp.c | 10 --
1 file changed, 10 deletions(-)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c
b/drivers/infiniband/ulp/srp/ib_srp.c
index 6d399378928d..d4a5a9b86390
Support the new memory registration API by allocating a
private page list array in ocrdma_mr and populate it when
ocrdma_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR, but take the needed
information from different places:
- page_size, iova, length, access flags
Support the new memory registration API by allocating a
private page list array in mlx5_ib_mr and populate it when
mlx5_ib_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by setting the exact WQE as IB_WR_FAST_REG_MR, just take the
needed information from different places:
- page_size, iova, lengt
Hi all,
As discussed on the linux-rdma list, there is plenty of room for
improvement in our memory registration APIs. We keep finding
ULPs that are duplicating code, sometimes use wrong strategies
and mis-use our current API.
As a first step, this patch set replaces the fast registration API
to a
The new fast registration verb ib_map_mr_sg receives a scatterlist
and converts it to a page list under the verbs API thus hiding
the specific HW mapping details away from the consumer.
The provider drivers are provided with a generic helper ib_sg_to_pages
that converts a scatterlist into a vecto
Just function declarations - no need for those
laying arround. If for some reason someone will want
FMR support in mlx5, it should be easy enough to restore
a few structs.
Signed-off-by: Sagi Grimberg
Reviewed-by: Bart Van Assche
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx5/mlx5_
Support the new memory registration API by allocating a
private page list array in nes_mr and populate it when
nes_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating IB_WR_FAST_REG_MR handling and take the
needed information from different places:
- page_size, iova, length (ib_mr)
- pa
Support the new memory registration API by allocating a
private page list array in c4iw_mr and populate it when
c4iw_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (
Support the new memory registration API by allocating a
private page list array in iwch_mr and populate it when
iwch_map_mr_sg is invoked. Also, support IB_WR_REG_MR
by duplicating build_fastreg just take the needed information
from different places:
- page_size, iova, length (ib_mr)
- page array (
On 10/13/2015 9:25 AM, Jens Domke wrote:
> This is only a precautionary patch for a theoretical
> bug which would arise if someone redefines IB_SMP_DATA_SIZE
> to a values !=64.
>
> ucast_mgr_pipeline_fwd_tbl() calculates the max. number of
> blocks to update using 64 explicitly, while set_lft_blo
This is only a precautionary patch for a theoretical
bug which would arise if someone redefines IB_SMP_DATA_SIZE
to a values !=64.
ucast_mgr_pipeline_fwd_tbl() calculates the max. number of
blocks to update using 64 explicitly, while set_lft_block()
uses IB_SMP_DATA_SIZE.
If IB_SMP_DATA_SIZE != 64
src/ibqueryerrors.c: In function ?print_port_config?:
src/ibqueryerrors.c:176: warning: unused parameter ?node_name?
src/ibqueryerrors.c: In function ?query_and_dump?:
src/ibqueryerrors.c:367: warning: unused parameter ?node?
Signed-off-by: Hal Rosenstock
---
diff --git a/src/ibqueryerrors.c b/s
src/ibcacheedit.c: In function ?update_switchportguids?:
src/ibcacheedit.c:168: warning: unused parameter ?guid?
Signed-off-by: Hal Rosenstock
---
diff --git a/src/ibcacheedit.c b/src/ibcacheedit.c
index 983c0ab..b520839 100644
--- a/src/ibcacheedit.c
+++ b/src/ibcacheedit.c
@@ -165,7 +165,7 @@
On 10/12/2015 3:59 PM, Devesh Sharma wrote:
Looks good, just one doubt inline:
Thanks for looking at this patch.
On Sun, Oct 11, 2015 at 6:28 PM, Matan Barak wrote:
When IP based addressing was introduced, ib_create_ah_from_wc was
changed in order to support a suitable AH. Since this AH
On Mon, Oct 12, 2015 at 7:42 PM, Hefty, Sean wrote:
>> When IP based addressing was introduced, ib_create_ah_from_wc was
>> changed in order to support a suitable AH. Since this AH should
>> now contains the DMAC (which isn't a simple derivative of the GID).
>> In order to find the DMAC, an ARP sh
On Mon, Oct 12, 2015 at 5:41 PM, Doug Ledford wrote:
> On 10/11/2015 10:40 AM, Matan Barak wrote:
>
>> Hi,
>>
>> I've rebased the patches against your k.o/for-4.4 tree. I've also added
>> some fixes to bugs we found lately. I can re-spin the whole series if
>> necessary (with the fixes squashed).
42 matches
Mail list logo
