On 15/10/2015 12:26, Sagi Grimberg wrote:
When using work request based memory registration (fast_reg)
we must reserve SQ entries for registration and invalidation
in addition to send operations. Each IO consumes 3 SQ entries
(registration, send, invalidation) so we need to allocate 3x
larger
Can you spare a few words on this change in the change log?
Signed-off-by: Bart Van Assche
Cc: Sagi Grimberg
Cc: Sebastian Parschauer
---
drivers/infiniband/ulp/srp/ib_srp.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c
b/drivers/infiniband
Looks good,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On 28/10/2015 00:02, Bart Van Assche wrote:
Wait until memory registration has finished in the srp_queuecommand()
error path before invalidating memory regions to avoid a send queue
overflow.
This looks backwards to me... Why do we even post anything on our
queue-pair to begin with if we got
Looks good,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Looks good,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Looks good,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Hi Yuval,
The title prefix should be IB/mlx4:
Expose max_fmr so it will be available to ULPs.
max_fmr is num_mpts minus reserved.
Signed-off-by: Yuval Shaia
---
drivers/infiniband/hw/mlx4/main.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/drivers/infiniband/hw/
The driver does not support it anyway, and the support
should be added to a generic layer shared by both hfi1,
qib and softroce drivers.
Signed-off-by: Sagi Grimberg
---
drivers/staging/rdma/hfi1/keys.c | 55 -
drivers/staging/rdma/hfi1/mr.c| 33
The driver does not support it anyway, and the support
should be added to a generic layer shared by both hfi1,
qib and softroce drivers.
Signed-off-by: Sagi Grimberg
---
drivers/staging/rdma/ipath/ipath_verbs.c |3 ---
drivers/staging/rdma/ipath/ipath_verbs.h |1 -
2 files changed, 0
I can provide a patch for hfi, anything else needed?
It breaks all of them in staging, not just hgi1. So, hfi1, amso1100,
ipath, and ehca.
hfi1: Does not support FRWR at all, there are just some copy-paste
sections that supposedly handle it - so I'll drop any sign of it from
the code. We'll
On 29/10/2015 16:16, Doug Ledford wrote:
On 10/29/2015 01:42 AM, Or Gerlitz wrote:
On Thu, Oct 29, 2015 at 4:34 AM, Doug Ledford wrote:
Yes, I've pulled this in for 4.4. Thanks!
Doug, we want to run regression over the 4.4 bits, when do you expect
for them to show up @ your kernel.org tre
max_sge_rd = 1.
Sagi Grimberg (2):
mlx4: Expose correct max_sge_rd limit
iser-target: Remove explicit mlx4 work-around
drivers/infiniband/hw/mlx4/main.c |2 +-
drivers/infiniband/ulp/isert/ib_isert.c | 13 +++--
include/linux/mlx4/device.h | 11 +++
3
The driver now exposes sufficient limits so we can
avoid having mlx4 specific work-around.
Signed-off-by: Sagi Grimberg
Reviewed-by: Steve Wise
---
drivers/infiniband/ulp/isert/ib_isert.c | 13 +++--
1 files changed, 3 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband
= 30.
Signed-off-by: Sagi Grimberg
Reviewed-by: Steve Wise
---
drivers/infiniband/hw/mlx4/main.c |2 +-
include/linux/mlx4/device.h | 11 +++
2 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c
b/drivers/infiniband/hw/mlx4
Submitting a SCSI request through the SG_IO mechanism with a scatterlist
that is longer than what is supported by the SRP initiator triggers an
infinite loop. This patch series fixes that behavior.
The individual patches in this series are as follows:
0001-IB-srp-Fix-a-spelling-error.patch
0002-
Hi Arnd,
Since we want to make counting semaphores go away,
Why do we want to make counting semaphores go away? completely?
or just for binary use cases?
I have a use case in iser target code where a counting semaphore is the
best suited synchronizing mechanism.
I have a single thread handli
= 30.
Signed-off-by: Sagi Grimberg
---
drivers/infiniband/hw/mlx4/main.c |2 +-
include/linux/mlx4/device.h | 11 +++
2 files changed, 12 insertions(+), 1 deletions(-)
diff --git a/drivers/infiniband/hw/mlx4/main.c
b/drivers/infiniband/hw/mlx4/main.c
index 3889723..d8453f1
added
a root cause analysis to patch change log.
- Fixed isert qp creation to be max_sge but construct rdma
work request with the minimum of max_sge and max_sge_rd
as non-rdma sends (login rsp) take 2 sges (and some devices
have max_sge_rd = 1.
Sagi Grimberg (2):
mlx4: Expose correct
The driver now exposes sufficient limits so we can
avoid having mlx4 specific work-around.
Signed-off-by: Sagi Grimberg
---
drivers/infiniband/ulp/isert/ib_isert.c | 13 +++--
1 files changed, 3 insertions(+), 10 deletions(-)
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c
b
Hello Sagi,
Is this the same issue as what has been discussed in
http://www.spinics.net/lists/linux-rdma/msg21799.html ?
Looks like it.
I think this patch addresses this issue, but lets CC Eli
to comment if I'm missing something.
Thanks for digging this up...
Sagi.
--
To unsubscribe from thi
But AFAIR, the magic number was 28... how this goes hand in hand with
your findings?
mlx4 max_sge is 32, and isert does max_sge - 2 = 30.
So it always used 30... and I run it reliably with this for a while now.
This thing exists before I was involved so I might not be familiar with
all the deta
On 27/10/2015 16:39, Or Gerlitz wrote:
On 10/27/2015 11:40 AM, Sagi Grimberg wrote:
mlx4 devices (ConnectX-2, ConnectX-3) can not issue
max_sge in a single RDMA_READ request (resulting in
a completion error). Thus, expose lower max_sge_rd
to avoid this issue.
Sagi,
Hey Or,
Still, this
Did we converge on this?
Just a heads up to Doug, this conflicts with
[PATCH v4 11/16] xprtrdma: Pre-allocate Work Requests for backchannel
but it's trivial to sort out...
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.o
Detected this by compiling with W=1.
Signed-off-by: Bart Van Assche
Cc: Sagi Grimberg
FWIW,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majordomo inf
On 22/10/2015 21:14, Bart Van Assche wrote:
Detected this by compiling with W=1.
Signed-off-by: Bart Van Assche
Cc: Sagi Grimberg
FWIW,
Reviewed-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message
mlx4 devices (ConnectX-2, ConnectX-3) can not issue
max_sge in a single RDMA_READ request (resulting in
a completion error). Thus, expose lower max_sge_rd
to avoid this issue.
Signed-off-by: Sagi Grimberg
---
drivers/infiniband/hw/mlx4/main.c |3 ++-
1 files changed, 2 insertions(+), 1
This addresses a specific mlx4 issue where the max_sge_rd
is actually smaller than max_sge (rdma reads with max_sge
entries completes with error).
The second patch removes the explicit work-around from the
iser target code.
This applies on top of Christoph's device attributes modification.
The driver now exposes sufficient limits so we can
avoid having mlx4 specific work-around.
Signed-off-by: Sagi Grimberg
---
drivers/infiniband/ulp/isert/ib_isert.c | 10 ++
1 files changed, 2 insertions(+), 8 deletions(-)
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c
b
On 10/21/2015 1:04 PM, Or Gerlitz wrote:
On 10/21/2015 12:53 PM, Sagi Grimberg wrote:
On 10/15/2015 2:44 PM, Eran Ben Elisha wrote:
+struct ib_uverbs_ex_create_qp {
+__u64 user_handle;
+__u32 pd_handle;
+__u32 send_cq_handle;
+__u32 recv_cq_handle;
+__u32 srq_handle
On 10/15/2015 2:44 PM, Eran Ben Elisha wrote:
ib_uverbs_ex_create_qp follows the extension verbs
mechanism. New features (for example, QP creation flags
field which is added in a downstream patch) could used
via user-space libraries without breaking the ABI.
This is an important addition, I'll
But this makes struct ib_device much much bigger, and this structure
is used in **fast** path,
e.g the ULP traverses through a pointer from struct ib_device to
post_send/recv, poll_cq and friends.
Umm, all the caps are appended to the end of the ib_device structure so
I don't see how it will a
On 10/20/2015 5:08 PM, Or Gerlitz wrote:
On Tue, Oct 20, 2015 at 4:08 PM, Sagi Grimberg wrote:
I think this is very useful to have and I'd love having it in 4.4,
does anyone have any other comments on this patch?
Were we ever presented with performance gains achieved using the patch?
I think this is very useful to have and I'd love having it in 4.4,
does anyone have any other comments on this patch?
Were we ever presented with performance gains achieved using the patch?
Hi Or,
Can you explain what you mean by performance gains? My understanding is
that this patch is not
So this patch seems to work well for me. I've ran some kernel
applications (ipoib, iser, srp, nfs) and a user-space application
(ibsrpdm) over mlx4/mlx5 and didn't spot any issues.
I think this is very useful to have and I'd love having it in 4.4,
does anyone have any other comments on this patch
Doug, are you planning on taking this for 4.4?
I think this set has converged towards inclusion.
Reminder, this series goes on top of Christoph's
wr_cleanup patches and iser bounce buffering cleanup.
Sagi.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a
When using work request based memory registration (fast_reg)
we must reserve SQ entries for registration and invalidation
in addition to send operations. Each IO consumes 3 SQ entries
(registration, send, invalidation) so we need to allocate 3x
larger send-queue instead of 2x.
Signed-off-by: Sagi
Hi Yishai,
+/**
+ * ib_create_wq - Creates a WQ associated with the specified protection
+ * domain.
+ * @pd: The protection domain associated with the WQ.
+ * @wq_init_attr: A list of initial attributes required to create the
+ * WQ. If WQ creation succeeds, then the attributes are updated to
+
(qib_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/qib/qib_keys.c | 56 +++
drivers/infiniband/hw
ments can benefit greatly as as it would reduce
the length of the HW descriptors array.
Signed-off-by: Sagi Grimberg
Reviewed-by: Christoph Hellwig
---
drivers/infiniband/ulp/iser/iscsi_iser.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/infiniband/ulp/iser/iscsi_i
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
ports it.
This should be applied before the New memory registration
API patch set.
Changes from v1:
- Change logs
Changes from v0:
- Added Reviewed-by tags
- Fixed patch (1) title
Sagi Grimberg (2):
iser: set block queue_virt_boundary
IB/iser: Enable SG clustering
drivers/infiniband/ulp
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
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/dr
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
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
rtual boundary
- or, bounce buffer SG_IOs that are not aligned to the virtual boundary
Since iser is working in 4K page size, set the virt_boundary to
4K pages. With this setting, we can now safely remove the bounce
buffering logic in iser.
Signed-off-by: Sagi Grimberg
Reviewed-by: Christoph He
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
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
, length, access flags (ib_mr)
- page array (mlx4_ib_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Tested-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx4/cq.c | 1 +
drivers/infiniband/hw/mlx4
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
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
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
(ib_mr)
- page array (ocrdma_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/ocrdma/ocrdma.h | 2 +
drivers/infiniband/hw/ocrdma
, length, access flags (ib_mr)
- page array (mlx5_ib_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx5/cq.c | 3 ++
drivers/infiniband/hw/mlx5
de is available at: https://github.com/sagigrimberg/linux reg_api.6
Sagi Grimberg (26):
IB/core: Introduce new fast registration API
IB/mlx5: Remove dead fmr code
IB/mlx5: Support the new memory registration API
IB/mlx4: Support the new memory registration API
RDMA/ocrdma: Supp
.
This API will allow ULPs to remove the duplicated code of constructing
a page vector from a given sg list.
The send work request ib_reg_wr also shrinks as it will contain only
mr, key and access flags in addition.
Signed-off-by: Sagi Grimberg
Tested-by: Christoph Hellwig
---
drivers/infiniband
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
)
- page array (nes_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/nes/nes_verbs.c | 117 +-
drivers
(c4iw_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
Tested-by: Steve Wise
---
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 7
drivers/infiniband/hw/cxgb4
(iwch_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/cxgb3/iwch_provider.c | 33
drivers/infiniband/hw/cxgb3
(as it isn't supported
anyway). I assume that the correct place to get the support back would
be in a shared SW library (hfi1, qib, rxe).
- Updated the change logs
The code is available at: https://github.com/sagigrimberg/linux/tree/reg_api.6
Sagi Grimberg (26):
IB/core: Introduce new fas
(ib_mr)
- page array (ocrdma_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/ocrdma/ocrdma.h | 2 +
drivers/infiniband/hw/ocrdma
)
- page array (nes_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/nes/nes_verbs.c | 117 +-
drivers
, length, access flags (ib_mr)
- page array (mlx4_ib_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Tested-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx4/cq.c | 1 +
drivers/infiniband/hw/mlx4
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
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/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 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
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
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
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
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
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/dr
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
Acked-by: Anna Schumaker
Tested-by: Steve Wise
Tested-by: Selvin Xavier
---
Note
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
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
(c4iw_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
Tested-by: Steve Wise
---
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 7
drivers/infiniband/hw/cxgb4
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
, length, access flags (ib_mr)
- page array (mlx5_ib_mr)
- key (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/mlx5/cq.c | 3 ++
drivers/infiniband/hw/mlx5
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
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
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
.
This API will allow ULPs to remove the duplicated code of constructing
a page vector from a given sg list.
The send work request ib_reg_wr also shrinks as it will contain only
mr, key and access flags in addition.
Signed-off-by: Sagi Grimberg
Tested-by: Christoph Hellwig
---
drivers/infiniband
(iwch_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/cxgb3/iwch_provider.c | 33
drivers/infiniband/hw/cxgb3
(qib_mr)
- key, access flags (ib_reg_wr)
The IB_WR_FAST_REG_MR handlers will be removed later when
all the ULPs will be converted.
Signed-off-by: Sagi Grimberg
Acked-by: Christoph Hellwig
---
drivers/infiniband/hw/qib/qib_keys.c | 56 +++
drivers/infiniband/hw
On 10/12/2015 9:57 AM, Christoph Hellwig wrote:
This patch gets rid of struct ib_device_attr and cleans up drivers nicely.
It goes on top of my send_wr cleanups and the memory registration udpates
from Sagi.
Changes since V1:
- rebased on top of the Sagi's latest reg_api.6 branch
Christoph
Hey,
I stepped on this lockdep circular locking complaint on 4.3-rc when
unloading the device driver (mlx5 in my case). Has anyone seen this?
I have seen such warnings with kernfs_mutex when deleting iscsi
devices on the fly.
I wander if kernfs_remove() should use mutex_lock_nested?
output:
ke
struct net_device *dev = mcast->dev;
int tx_dropped = 0;
Hey Christoph,
Thanks for the quick patch. When you re-spin this as
a proper patch you can add my:
Tested-by: Sagi Grimberg
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma&qu
What happens now when an app wants to use 1K, 2K, 3K IOs? they can
only use 1/4, 1/2 or 3/4 of the available memory for these
transactions?
What? I'm not sure what you are talking about. what available memory?
and we are going to fix it with devices like mlx5 over
the new API you're proposing,
I can do a rebase to whatever you want. Initially this was
over your reg_api branch. Is a rebase to the latest reg_api.6
fine?
That would be great.
Sagi.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majord...@vger.kernel.org
More majord
201 - 300 of 1318 matches
Mail list logo