ROCE uses IGMP for Multicast instead of the native Infiniband system where
joins are required in order to post messages on the Multicast group. On
Ethernet one can send Multicast messages to arbitrary addresses without
the need to subscribe to a group.
So ROCE correctly does not send IGMP joins during rdma_join_multicast().
F.e. in cma_iboe_join_multicast() we see:
if (addr->sa_family == AF_INET) {
if (gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP) {
ib.rec.hop_limit = IPV6_DEFAULT_HOPLIMIT;
if (!send_only) {
err = cma_igmp_send(ndev, &ib.rec.mgid,
true);
}
}
} else {
So the IGMP join is suppressed as it is unnecessary.
However no such check is done in destroy_mc(). And therefore leaving a
sendonly multicast group will send an IGMP leave.
This means that the following scenario can lead to a multicast receiver
unexpectedly being unsubscribed from a MC group:
1. Sender thread does a sendonly join on MC group X. No IGMP join
is sent.
2. Receiver thread does a regular join on the same MC Group x.
IGMP join is sent and the receiver begins to get messages.
3. Sender thread terminates and destroys MC group X.
IGMP leave is sent and the receiver no longer receives data.
This patch adds the same logic for sendonly joins to destroy_mc() that is
also used in cma_iboe_join_multicast().
Fixes: ab15c95a17 ("IB/core: Support for CMA multicast join flags")
Link: https://lore.kernel.org/r/alpine.DEB.2.22.394.2109081340540.668072@gentwo.de
Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
clang becomes confused due to the comparison to NULL in a integer constant
expression context:
>> drivers/infiniband/hw/qib/qib_sysfs.c:413:1: error: static_assert expression is not an integral constant expression
QIB_DIAGC_ATTR(rc_resends);
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/infiniband/hw/qib/qib_sysfs.c:406:16: note: expanded from macro 'QIB_DIAGC_ATTR'
static_assert(&((struct qib_ibport *)0)->rvp.n_##N != (u64 *)NULL); \
Nathan found __same_type that solves this problem nicely, so use it instead.
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pull rdma fixes from Jason Gunthorpe:
"I don't usually send a second PR in the merge window, but the fix to
mlx5 is significant enough that it should start going through the
process ASAP. Along with it comes some of the usual -rc stuff that
would normally wait for a -rc2 or so.
Summary:
Important error case regression fixes in mlx5:
- Wrong size used when computing the error path smaller allocation
request leads to corruption
- Confusing but ultimately harmless alignment mis-calculation
Static checker warning fixes:
- NULL pointer subtraction in qib
- kcalloc in bnxt_re
- Missing static on global variable in hfi1"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
IB/hfi1: make hist static
RDMA/bnxt_re: Prefer kcalloc over open coded arithmetic
IB/qib: Fix null pointer subtraction compiler warning
RDMA/mlx5: Fix xlt_chunk_align calculation
RDMA/mlx5: Fix number of allocated XLT entries
As noted in the "Deprecated Interfaces, Language Features, Attributes, and
Conventions" documentation [1], size calculations (especially
multiplication) should not be performed in memory allocator (or similar)
function arguments due to the risk of them overflowing. This could lead to
values wrapping around and a smaller allocation being made than the caller
was expecting. Using those allocations could lead to linear overflows of
heap memory and other misbehaviors.
In this case this is not actually dynamic sizes: both sides of the
multiplication are constant values. However it is best to refactor this
anyway, just to keep the open-coded math idiom out of code.
So, use the purpose specific kcalloc() function instead of the argument
size * count in the kzalloc() function.
Also, remove the unnecessary initialization of the sqp_tbl variable since
it is set a few lines later.
[1] https://www.kernel.org/doc/html/v5.14/process/deprecated.html#open-coded-arithmetic-in-allocator-arguments
Link: https://lore.kernel.org/r/20210905081812.17113-1-len.baker@gmx.com
Signed-off-by: Len Baker <len.baker@gmx.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
>> drivers/infiniband/hw/qib/qib_sysfs.c:411:1: warning: performing pointer subtraction with a null pointer has undefined behavior
+[-Wnull-pointer-subtraction]
QIB_DIAGC_ATTR(rc_resends);
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/infiniband/hw/qib/qib_sysfs.c:408:51: note: expanded from macro 'QIB_DIAGC_ATTR'
.counter = &((struct qib_ibport *)0)->rvp.n_##N - (u64 *)0, \
Use offsetof and accomplish the type check using static_assert.
Fixes: 4a7aaf88c8 ("RDMA/qib: Use attributes for the port sysfs")
Link: https://lore.kernel.org/r/0-v1-43ae3c759177+65-qib_type_jgg@nvidia.com
Reported-by: kernel test robot <lkp@intel.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The XLT chunk alignment depends on ent_size not sizeof(ent_size) aka
sizeof(size_t). The incoming ent_size is either 8 or 16, so the
miscalculation when 16 is required is only an over-alignment and
functional harmless.
Fixes: 8010d74b99 ("RDMA/mlx5: Split the WR setup out of mlx5_ib_update_xlt()")
Link: https://lore.kernel.org/r/20210908081849.7948-2-schnelle@linux.ibm.com
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In commit 8010d74b99 ("RDMA/mlx5: Split the WR setup out of
mlx5_ib_update_xlt()") the allocation logic was split out of
mlx5_ib_update_xlt() and the logic was changed to enable better OOM
handling. Sadly this change introduced a miscalculation of the number of
entries that were actually allocated when under memory pressure where it
can actually become 0 which on s390 lets dma_map_single() fail.
It can also lead to corruption of the free pages list when the wrong
number of entries is used in the calculation of sg->length which is used
as argument for free_pages().
Fix this by using the allocation size instead of misusing get_order(size).
Cc: stable@vger.kernel.org
Fixes: 8010d74b99 ("RDMA/mlx5: Split the WR setup out of mlx5_ib_update_xlt()")
Link: https://lore.kernel.org/r/20210908081849.7948-1-schnelle@linux.ibm.com
Signed-off-by: Niklas Schnelle <schnelle@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Pull SCSI updates from James Bottomley:
"This series consists of the usual driver updates (ufs, qla2xxx,
target, smartpqi, lpfc, mpt3sas).
The core change causing the most churn was replacing the command
request field request with a macro, allowing us to offset map to it
and remove the redundant field; the same was also done for the tag
field.
The most impactful change is the final removal of scsi_ioctl, which
has been deprecated for over a decade"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (293 commits)
scsi: ufs: Fix ufshcd_request_sense_async() for Samsung KLUFG8RHDA-B2D1
scsi: ufs: ufs-exynos: Fix static checker warning
scsi: mpt3sas: Use the proper SCSI midlayer interfaces for PI
scsi: lpfc: Use the proper SCSI midlayer interfaces for PI
scsi: lpfc: Copyright updates for 14.0.0.1 patches
scsi: lpfc: Update lpfc version to 14.0.0.1
scsi: lpfc: Add bsg support for retrieving adapter cmf data
scsi: lpfc: Add cmf_info sysfs entry
scsi: lpfc: Add debugfs support for cm framework buffers
scsi: lpfc: Add support for maintaining the cm statistics buffer
scsi: lpfc: Add rx monitoring statistics
scsi: lpfc: Add support for the CM framework
scsi: lpfc: Add cmfsync WQE support
scsi: lpfc: Add support for cm enablement buffer
scsi: lpfc: Add cm statistics buffer support
scsi: lpfc: Add EDC ELS support
scsi: lpfc: Expand FPIN and RDF receive logging
scsi: lpfc: Add MIB feature enablement support
scsi: lpfc: Add SET_HOST_DATA mbox cmd to pass date/time info to firmware
scsi: fc: Add EDC ELS definition
...
Pull rdma updates from Jason Gunthorpe:
"This is quite a small cycle, no major series stands out. The HNS and
rxe drivers saw the most activity this cycle, with rxe being broken
for a good chunk of time. The significant deleted line count is due to
a SPDX cleanup series.
Summary:
- Various cleanup and small features for rtrs
- kmap_local_page() conversions
- Driver updates and fixes for: efa, rxe, mlx5, hfi1, qed, hns
- Cache the IB subnet prefix
- Rework how CRC is calcuated in rxe
- Clean reference counting in iwpm's netlink
- Pull object allocation and lifecycle for user QPs to the uverbs
core code
- Several small hns features and continued general code cleanups
- Fix the scatterlist confusion of orig_nents/nents introduced in an
earlier patch creating the append operation"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (90 commits)
RDMA/mlx5: Relax DCS QP creation checks
RDMA/hns: Delete unnecessary blank lines.
RDMA/hns: Encapsulate the qp db as a function
RDMA/hns: Adjust the order in which irq are requested and enabled
RDMA/hns: Remove RST2RST error prints for hw v1
RDMA/hns: Remove dqpn filling when modify qp from Init to Init
RDMA/hns: Fix QP's resp incomplete assignment
RDMA/hns: Fix query destination qpn
RDMA/hfi1: Convert to SPDX identifier
IB/rdmavt: Convert to SPDX identifier
RDMA/hns: Bugfix for incorrect association between dip_idx and dgid
RDMA/hns: Bugfix for the missing assignment for dip_idx
RDMA/hns: Bugfix for data type of dip_idx
RDMA/hns: Fix incorrect lsn field
RDMA/irdma: Remove the repeated declaration
RDMA/core/sa_query: Retry SA queries
RDMA: Use the sg_table directly and remove the opencoded version from umem
lib/scatterlist: Fix wrong update of orig_nents
lib/scatterlist: Provide a dedicated function to support table append
RDMA/hns: Delete unused hns bitmap interface
...
From Maor Gottlieb
====================
Fix the use of nents and orig_nents in the sg table append helpers. The
nents should be used by the DMA layer to store the number of DMA mapped
sges, the orig_nents is the number of CPU sges.
Since the sg append logic doesn't always create a SGL with exactly
orig_nents entries store a total_nents as well to allow the table to be
properly free'd and reorganize the freeing logic to share across all the
use cases.
====================
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
* 'sg_nents':
RDMA: Use the sg_table directly and remove the opencoded version from umem
lib/scatterlist: Fix wrong update of orig_nents
lib/scatterlist: Provide a dedicated function to support table append
dip_idx and dgid should be a one-to-one mapping relationship, but when
qp_num loops back to the start number, it may happen that two different
dgid are assiociated to the same dip_idx incorrectly.
One solution is to store the qp_num that is not assigned to dip_idx in an
array. When a dip_idx needs to be allocated to a new dgid, an spare qp_num
is extracted and assigned to dip_idx.
Fixes: f91696f2f0 ("RDMA/hns: Support congestion control type selection according to the FW")
Link: https://lore.kernel.org/r/1629884592-23424-4-git-send-email-liangwenpeng@huawei.com
Signed-off-by: Junxian Huang <huangjunxian4@hisilicon.com>
Signed-off-by: Yangyang Li <liyangyang20@huawei.com>
Signed-off-by: Wenpeng Liang <liangwenpeng@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
A MAD packet is sent as an unreliable datagram (UD). SA requests are sent
as MAD packets. As such, SA requests or responses may be silently dropped.
IB Core's MAD layer has a timeout and retry mechanism, which amongst
other, is used by RDMA CM. But it is not used by SA queries. The lack of
retries of SA queries leads to long specified timeout, and error being
returned in case of packet loss. The ULP or user-land process has to
perform the retry.
Fix this by taking advantage of the MAD layer's retry mechanism.
First, a check against a zero timeout is added in rdma_resolve_route(). In
send_mad(), we set the MAD layer timeout to one tenth of the specified
timeout and the number of retries to 10. The special case when timeout is
less than 10 is handled.
With this fix:
# ucmatose -c 1000 -S 1024 -C 1
runs stable on an Infiniband fabric. Without this fix, we see an
intermittent behavior and it errors out with:
cmatose: event: RDMA_CM_EVENT_ROUTE_ERROR, error: -110
(110 is ETIMEDOUT)
Link: https://lore.kernel.org/r/1628784755-28316-1-git-send-email-haakon.bugge@oracle.com
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
orig_nents should represent the number of entries with pages,
but __sg_alloc_table_from_pages sets orig_nents as the number of
total entries in the table. This is wrong when the API is used for
dynamic allocation where not all the table entries are mapped with
pages. It wasn't observed until now, since RDMA umem who uses this
API in the dynamic form doesn't use orig_nents implicit or explicit
by the scatterlist APIs.
Fix it by changing the append API to track the SG append table
state and have an API to free the append table according to the
total number of entries in the table.
Now all APIs set orig_nents as number of enries with pages.
Fixes: 07da1223ec ("lib/scatterlist: Add support in dynamic allocation of SG table from pages")
Link: https://lore.kernel.org/r/20210824142531.3877007-3-maorg@nvidia.com
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
RDMA is the only in-kernel user that uses __sg_alloc_table_from_pages to
append pages dynamically. In the next patch. That mode will be extended
and that function will get more parameters. So separate it into a unique
function to make such change more clear.
Link: https://lore.kernel.org/r/20210824142531.3877007-2-maorg@nvidia.com
Signed-off-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In order to support more coalesce parameters through netlink,
add two new parameter kernel_coal and extack for .set_coalesce
and .get_coalesce, then some extra info can return to user with
the netlink API.
Signed-off-by: Yufeng Mo <moyufeng@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
There are mis-match at counting inflight IO after changing the multipath
policy.
For example, we started fio test with round-robin policy and then we
changed the policy to min-inflight. IOs created under the RR policy is
finished under the min-inflight policy and inflight counter only
decreased. So the counter would be negative value. And also we started
fio test with min-inflight policy and changed the policy to the
round-robin. IOs created under the min-inflight policy increased the
inflight IO counter but the inflight IO counter was not decreased because
the policy was the round-robin when IO was finished.
So it should count IOs only if the IO is created under the min-inflight
policy. It should not care the policy when the IO is finished.
This patch adds a field mp_policy in struct rtrs_clt_io_req and stores the
multipath policy when an object of rtrs_clt_io_req is created. Then
rtrs-clt checks the mp_policy of only struct rtrs_clt_io_req instead of
the struct rtrs_clt.
Link: https://lore.kernel.org/r/20210806112112.124313-6-haris.iqbal@ionos.com
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The IO performance test with fio after swapping the likely and unlikely
macros in all if-statement shows no difference. They do not help for the
performance of rtrs.
Thanks to Haakon Bugge for the test scenario.
The fio test did random read on 32 rnbd devices and 64 processes.
Test environment:
- Intel(R) Xeon(R) Gold 6130 CPU @ 2.10GHz
- 376G memory
- kernel version: 5.4.86
- gcc version: gcc (Debian 8.3.0-6) 8.3.0
- Infiniband controller: Mellanox Technologies MT27800 Family [ConnectX-5]
Test result:
- before swapping: IOPS=829k, BW=3239MiB/s
- after swapping: IOPS=829k, BW=3238MiB/s
- remove all (un)likely: IOPS=829k, BW=3238MiB/s
Link: https://lore.kernel.org/r/20210806112112.124313-5-haris.iqbal@ionos.com
Signed-off-by: Gioh Kim <gi-oh.kim@ionos.com>
Signed-off-by: Jack Wang <jinpu.wang@ionos.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Md Haris Iqbal <haris.iqbal@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
