Use generic mlx5 structure defined in mlx5_ifc.h to represent ConnectX
device data structures instead of using structure defined specifically for
mlx5_ib module.
Link: https://lore.kernel.org/r/20200716105248.1423452-3-leon@kernel.org
Signed-off-by: Meir Lichtinger <meirl@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The UDP reuseport conflict was a little bit tricky.
The net-next code, via bpf-next, extracted the reuseport handling
into a helper so that the BPF sk lookup code could invoke it.
At the same time, the logic for reuseport handling of unconnected
sockets changed via commit efc6b6f6c3
which changed the logic to carry on the reuseport result into the
rest of the lookup loop if we do not return immediately.
This requires moving the reuseport_has_conns() logic into the callers.
While we are here, get rid of inline directives as they do not belong
in foo.c files.
The other changes were cases of more straightforward overlapping
modifications.
Signed-off-by: David S. Miller <davem@davemloft.net>
Fix reported by kbuild warning.
drivers/infiniband/core/uverbs_cmd.c:1897:47: warning: Shifting signed 32-bit value by 31 bits is undefined behaviour [shiftTooManyBitsSigned]
BUILD_BUG_ON(IB_USER_LAST_QP_ATTR_MASK == (1 << 31));
^
Link: https://lore.kernel.org/r/20200720175627.1273096-3-leon@kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The kbuild reported the following warning, so clean whole uverbs_cmd.c
file.
drivers/infiniband/core/uverbs_cmd.c:1066:6: warning: Variable 'ret' is reassigned a value before the old one has been used. [redundantAssignment]
ret = uverbs_request(attrs, &cmd, sizeof(cmd));
^
drivers/infiniband/core/uverbs_cmd.c:1064:0: note: Variable 'ret' is reassigned a value before the old one has been used.
int ret = -EINVAL;
^
Link: https://lore.kernel.org/r/20200720175627.1273096-2-leon@kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The automatic object lifetime model allows us to change the write()
interface to have the same logic as the ioctl() path. Update the
create/alloc functions to be in the following format, so the code flow
will be the same:
* Allocate objects
* Initialize them
* Call to the drivers, this is last step that is allowed to fail
* Finalize object
* Return response and allow to core code to handle abort/commit
respectively.
Link: https://lore.kernel.org/r/20200719052223.75245-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Create the same logic flow for the write() interface as we have for the
ioctl() path by making sure that the object is committed or aborted
automatically after HW object creation.
Link: https://lore.kernel.org/r/20200719052223.75245-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Currently the SQ is set to a ready state when the RAW QP is modified to
INIT. When the TIS is modified, e.g. to change the lag_tx_affinity, then
SQs which are already in the ready state will not be affected.
Open a window to modify the SQ behavior by setting the SQ as ready only
when QP was modified to RTS.
Link: https://lore.kernel.org/r/20200716105416.1423826-1-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Zhang <markz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Extend current infrastructure to store chain page size in a struct
and use it in all functions instead of fixed QED_CHAIN_PAGE_SIZE.
Its value remains the default one, but can be overridden in
qed_chain_init_params before chain allocation.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
To simplify qed_chain_alloc() prototype and call sites, introduce struct
qed_chain_init_params to specify chain params, and pass a pointer to
filled struct to the actual qed_chain_alloc() instead of a long list
of separate arguments.
Signed-off-by: Alexander Lobakin <alobakin@marvell.com>
Signed-off-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Prefetch work in mlx5_ib_prefetch_mr_work can be queued and able to run
concurrently with destruction of the implicit MR. The num_deferred_work
was intended to serialize this, but there is a race:
CPU0 CPU1
mlx5_ib_free_implicit_mr()
xa_erase(odp_mkeys)
synchronize_srcu()
__xa_erase(implicit_children)
mlx5_ib_prefetch_mr_work()
pagefault_mr()
pagefault_implicit_mr()
implicit_get_child_mr()
xa_cmpxchg()
atomic_dec_and_test(num_deferred_mr)
wait_event(imr->q_deferred_work)
ib_umem_odp_release(odp_imr)
kfree(odp_imr)
At this point in mlx5_ib_free_implicit_mr() the implicit_children list is
supposed to be empty forever so that destroy_unused_implicit_child_mr()
and related are not and will not be running.
Since it is not empty the destroy_unused_implicit_child_mr() flow ends up
touching deallocated memory as mlx5_ib_free_implicit_mr() already tore down the
imr parent.
The solution is to flush out the prefetch wq by driving num_deferred_work
to zero after creation of new prefetch work is blocked.
Fixes: 5256edcb98 ("RDMA/mlx5: Rework implicit ODP destroy")
Link: https://lore.kernel.org/r/20200719065435.130722-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Modifying the post-send and post-recv to initialize the wqes slot by slot
dynamically depending on the number of max sges requested by consumer at
the time of QP creation.
Changed the QP creation logic to determine the size of SQ and RQ in 16B
slots based on the number of wqe and number of SGEs requested by consumer
Link: https://lore.kernel.org/r/1594822619-4098-6-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Adding few helper data structure which are useful to initialize hardware
send wqe in variable wqe mode.
Adding a qp flag in HSI to indicate variable wqe is enabled for this qp.
Link: https://lore.kernel.org/r/1594822619-4098-5-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Changing the PSN management memory buffers from statically initialized to
dynamic pull scheme.
During create qp only the start pointers are initialized and during
post-send the psn buffer is pulled based on current producer index.
Adjusting post_send code to accommodate dynamic psn-pull and changing
post_recv code to match post-send code wrt pseudo flush wqe generation.
Link: https://lore.kernel.org/r/1594822619-4098-4-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The bnxt_re driver now allocates shadow sq and rq to maintain per wqe
wr_id and few other flags required to support variable wqe. Segregated the
allocation of shadow queue in a separate function and adjust the cqe
polling logic. The new polling logic is based on shadow queue indices.
Link: https://lore.kernel.org/r/1594822619-4098-3-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The bnxt_re driver need to decide on how much SQ and RQ memory should to
be allocated and which wqe posting/polling algorithm to use.
Making changes to set the wqe-mode to a default value during device
registration sequence. The wqe-mode is passed to the lower layer driver as
well. Going forward in the lower layer driver wqe-mode will be used to
decide execution path. Initializing the wqe-mode to static wqe type for
now.
Link: https://lore.kernel.org/r/1594822619-4098-2-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that the query_pkey() isn't mandatory by the RDMA core for iwarp
providers, this callback can be removed from the common ops and moved to
the RoCE only ops within the qedr driver.
Link: https://lore.kernel.org/r/20200714183414.61069-8-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Acked-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that the query_pkey() isn't mandatory by the RDMA core for iwarp
providers, this callback can be removed.
Link: https://lore.kernel.org/r/20200714183414.61069-7-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that the query_pkey() isn't mandatory by the RDMA core for iwarp
providers, this callback can be removed.
Link: https://lore.kernel.org/r/20200714183414.61069-6-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Now that the query_pkey() isn't mandatory by the RDMA core for iwarp
providers, this callback can be removed.
Link: https://lore.kernel.org/r/20200714183414.61069-5-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Acked-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The query_pkey() isn't mandatory for the iwarp providers, so remove this
requirement from the RDMA core.
Link: https://lore.kernel.org/r/20200714183414.61069-4-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Allocate the pkey cache only if the pkey_tbl_len is set by the provider,
also add checks to avoid accessing the pkey cache when it not initialized.
Link: https://lore.kernel.org/r/20200714183414.61069-3-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Avoid the overhead of the dma ops support for tiny builds that only
use the direct mapping.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Using uninitialized_var() is dangerous as it papers over real bugs[1]
(or can in the future), and suppresses unrelated compiler warnings
(e.g. "unused variable"). If the compiler thinks it is uninitialized,
either simply initialize the variable or make compiler changes.
In preparation for removing[2] the[3] macro[4], remove all remaining
needless uses with the following script:
git grep '\buninitialized_var\b' | cut -d: -f1 | sort -u | \
xargs perl -pi -e \
's/\buninitialized_var\(([^\)]+)\)/\1/g;
s:\s*/\* (GCC be quiet|to make compiler happy) \*/$::g;'
drivers/video/fbdev/riva/riva_hw.c was manually tweaked to avoid
pathological white-space.
No outstanding warnings were found building allmodconfig with GCC 9.3.0
for x86_64, i386, arm64, arm, powerpc, powerpc64le, s390x, mips, sparc64,
alpha, and m68k.
[1] https://lore.kernel.org/lkml/20200603174714.192027-1-glider@google.com/
[2] https://lore.kernel.org/lkml/CA+55aFw+Vbj0i=1TGqCR5vQkCzWJ0QxK6CernOU6eedsudAixw@mail.gmail.com/
[3] https://lore.kernel.org/lkml/CA+55aFwgbgqhbp1fkxvRKEpzyR5J8n1vKT1VZdz9knmPuXhOeg@mail.gmail.com/
[4] https://lore.kernel.org/lkml/CA+55aFz2500WfbKXAx8s67wrm9=yVJu65TpLgN_ybYNv0VEOKA@mail.gmail.com/
Reviewed-by: Leon Romanovsky <leonro@mellanox.com> # drivers/infiniband and mlx4/mlx5
Acked-by: Jason Gunthorpe <jgg@mellanox.com> # IB
Acked-by: Kalle Valo <kvalo@codeaurora.org> # wireless drivers
Reviewed-by: Chao Yu <yuchao0@huawei.com> # erofs
Signed-off-by: Kees Cook <keescook@chromium.org>
rxe_post_send_kernel() iterates over linked list of wr's, until the
wr->next ptr is NULL. However if we've got an interrupt after last wr is
posted, control may be returned to the code after send completion callback
is executed and wr memory is freed.
As a result, wr->next pointer may contain incorrect value leading to
panic. Store the wr->next on the stack before posting it.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200716190340.23453-1-m.malygin@yadro.com
Signed-off-by: Mikhail Malygin <m.malygin@yadro.com>
Signed-off-by: Sergey Kojushev <s.kojushev@yadro.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
User space should receive the maximum edpm size from kernel driver,
similar to other edpm/ldpm related limits. Add an additional parameter to
the alloc_ucontext_resp structure for the edpm maximum size.
In addition, pass an indication from user-space to kernel
(and not just kernel to user) that the DPM sizes are supported.
This is for supporting backward-forward compatibility between driver and
lib for everything related to DPM transaction and limit sizes.
This should have been part of commit mentioned in Fixes tag.
Link: https://lore.kernel.org/r/20200707063100.3811-3-michal.kalderon@marvell.com
Fixes: 93a3d05f9d ("RDMA/qedr: Add kernel capability flags for dpm enabled mode")
Signed-off-by: Ariel Elior <ariel.elior@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In older FW versions the completion flag was treated as the ack flag in
edpm messages. commit ff937b916e ("qed: Add EDPM mode type for user-fw
compatibility") exposed the FW option of setting which mode the QP is in
by adding a flag to the qedr <-> qed API.
This patch adds the qedr <-> libqedr interface so that the libqedr can set
the flag appropriately and qedr can pass it down to FW. Flag is added for
backward compatibility with libqedr.
For older libs, this flag didn't exist and therefore set to zero.
Fixes: ac1b36e55a ("qedr: Add support for user context verbs")
Link: https://lore.kernel.org/r/20200707063100.3811-2-michal.kalderon@marvell.com
Signed-off-by: Yuval Bason <yuval.bason@marvell.com>
Signed-off-by: Michal Kalderon <michal.kalderon@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
QP's with the same SRQ, working on different CQs and running in parallel
on different CPUs could lead to a race when maintaining the SRQ consumer
count, and leads to FW running out of SRQs. Update the consumer
atomically. Make sure the wqe_prod is updated after the sge_prod due to
FW requirements.
Fixes: 3491c9e799 ("qedr: Add support for kernel mode SRQ's")
Link: https://lore.kernel.org/r/20200708195526.31040-1-ybason@marvell.com
Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Yuval Basson <ybason@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Current iSER target code allocates MR pool budget based on queue size.
Since there is no handshake between iSER initiator and target on max IO
size, we'll set the iSER target to support upto 16MiB IO operations and
allocate the correct number of RDMA ctxs according to the factor of MR's
per IO operation. This would guarantee sufficient size of the MR pool for
the required IO queue depth and IO size.
Link: https://lore.kernel.org/r/20200708091908.162263-1-maxg@mellanox.com
Reported-by: Krishnamraju Eraparaju <krishna2@chelsio.com>
Tested-by: Krishnamraju Eraparaju <krishna2@chelsio.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Acked-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When using action drop dest_type was never assigned to any value. Add
initialization of dest_type to -1 since 0 is valid.
Fixes: f29de9eee7 ("RDMA/mlx5: Add support for drop action in DV steering")
Link: https://lore.kernel.org/r/20200707110259.882276-1-leon@kernel.org
Signed-off-by: Daria Velikovsky <daria@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Instead of returning IB_LINK_LAYER_ETHERNET from rxe_link_layer, return it
directly from get_link_layer callback and remove rxe_link_layer().
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200705104313.283034-5-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The return value from rxe_mem_init_dma() is always 0 - change it to be
void and fix the callers accordingly.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200705104313.283034-4-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The return value from rxe_init_port_param() is always 0 - change it to be
void.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200705104313.283034-3-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Both pkey_tbl_len and gid_tbl_len are set in rxe_init_port_param() - so no
need to check if they aren't set.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200705104313.283034-2-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
ROCE uses "VA % buf_page_size" to caclulate the offset in the PBL's first
page, the actual PA corresponding to the MR's VA is equal to MR's PA plus
this offset. The first PA in PBL has already been aligned to PAGE_SIZE
after calling ib_umem_get(), but the MR's VA may not. If the buf_page_size
is smaller than the PAGE_SIZE, this will lead the HW to access the wrong
memory because the offset is smaller than expected.
Fixes: 9b2cf76c9f ("RDMA/hns: Optimize PBL buffer allocation process")
Link: https://lore.kernel.org/r/1594726935-45666-1-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The RoCE Engine will schedule to another QP after one has sent
(2 ^ lp_pktn_ini) packets. lp_pktn_ini is set in QPC and should be
calculated from 2 factors:
1. current MTU as a integer
2. the RoCE Engine's maximum slice length 64KB
But the driver use MTU as a enum ib_mtu and the max inline capability, the
lp_pktn_ini will be much bigger than expected which may cause traffic of
some QPs to never get scheduled.
Fixes: b713128de7 ("RDMA/hns: Adjust lp_pktn_ini dynamically")
Link: https://lore.kernel.org/r/1594726138-49294-1-git-send-email-liweihang@huawei.com
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In manual mode allow bind user QPs with different pids to same counter,
since this is allowed in auto mode.
Bind kernel QPs and user QPs to the same counter are not allowed.
Fixes: 1bd8e0a9d0 ("RDMA/counter: Allow manual mode configuration support")
Link: https://lore.kernel.org/r/20200702082933.424537-4-leon@kernel.org
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In auto mode only bind user QPs to a dynamic counter, since this feature
is mainly used for system statistic and diagnostic purpose, while there's
no need to counter kernel QPs so far.
Fixes: 99fa331dc8 ("RDMA/counter: Add "auto" configuration mode support")
Link: https://lore.kernel.org/r/20200702082933.424537-3-leon@kernel.org
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
With the "PID" category QPs have same PID will be bound to same counter;
If this category is not set then QPs have different PIDs will be bound
to same counter.
This is implemented for 2 reasons:
1. The counter is a limited resource, while there may be dozens of
applications, each of which creates several types of QPs, which means
it may doesn't have enough counter.
2. The system administrator needs all QPs created by all applications
with same type bound to one counter.
The counter name and PID is only make sense when "PID" category are
configured.
This category can also be used in combine with others, e.g. QP type.
Link: https://lore.kernel.org/r/20200702082933.424537-2-leon@kernel.org
Signed-off-by: Mark Zhang <markz@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Some released FW versions mistakenly don't set the capability that 50G per
lane link-modes are supported for VFs (ptys_extended_ethernet capability
bit).
Use PTYS.ext_eth_proto_capability instead, as this indication is always
accurate. If PTYS.ext_eth_proto_capability is valid
(has a non-zero value) conclude that the HCA supports 50G per lane.
Otherwise, conclude that the HCA doesn't support 50G per lane.
Fixes: 08e8676f16 ("IB/mlx5: Add support for 50Gbps per lane link modes")
Link: https://lore.kernel.org/r/20200707110612.882962-3-leon@kernel.org
Signed-off-by: Aya Levin <ayal@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Reviewed-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Move the initialization of the vendor_part_id to be before calling
ib_register_device(), this is needed because the query_device() callback
is called from the context of ib_register_device() before initializing the
vendor_part_id, so the reported value is wrong.
Fixes: bdcf26bf9b ("rdma/siw: network and RDMA core interface")
Link: https://lore.kernel.org/r/20200707130931.444724-1-kamalheib1@gmail.com
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Merge them into their callers, usually the only thing the caller did was
to call the one function, so this is clearer.
Link: https://lore.kernel.org/r/20200702081809.423482-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Move DEVX initialization and cleanup flows to the devx.c instead of having
almost empty functions in main.c
Link: https://lore.kernel.org/r/20200702081809.423482-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Move flow steering logic to be in separate file and rename flow.c to be
fs.c because it is better describe the content.
Link: https://lore.kernel.org/r/20200702081809.423482-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
There are number of counters types supported in mlx5_ib: HW counters,
congestion counters, Q-counters and flow counters. Almost all supporting
code was placed in main.c that made almost impossible to maintain the code
anymore. Let's create separate code namespace for the counters to easy
future generalization effort.
Link: https://lore.kernel.org/r/20200702081809.423482-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The restrack code has separate .c, so move callbacks initialization to
that file to improve code locality.
Link: https://lore.kernel.org/r/20200702081809.423482-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The mlx5_ib_enable_driver() is local function and doesn't need to be
shared in mlx5_ib, so change it's signature to have static keyword in it.
Link: https://lore.kernel.org/r/20200702081809.423482-2-leon@kernel.org
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
If hns ROCEE is set to level-0 addressing, the length of the entire buffer
can be used as the page size. The driver needn't to split the buffer into
small units because all pages are continuous.
Link: https://lore.kernel.org/r/1593525696-12570-1-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In the loopback tests, the following call trace occurs.
Call Trace:
__rxe_do_task+0x1a/0x30 [rdma_rxe]
rxe_qp_destroy+0x61/0xa0 [rdma_rxe]
rxe_destroy_qp+0x20/0x60 [rdma_rxe]
ib_destroy_qp_user+0xcc/0x220 [ib_core]
uverbs_free_qp+0x3c/0xc0 [ib_uverbs]
destroy_hw_idr_uobject+0x24/0x70 [ib_uverbs]
uverbs_destroy_uobject+0x43/0x1b0 [ib_uverbs]
uobj_destroy+0x41/0x70 [ib_uverbs]
__uobj_get_destroy+0x39/0x70 [ib_uverbs]
ib_uverbs_destroy_qp+0x88/0xc0 [ib_uverbs]
ib_uverbs_handler_UVERBS_METHOD_INVOKE_WRITE+0xb9/0xf0 [ib_uverbs]
ib_uverbs_cmd_verbs+0xb16/0xc30 [ib_uverbs]
The root cause is that the actual RDMA connection is not created in the
loopback tests and the rxe_match_dgid will fail randomly.
To fix this call trace which appear in the loopback tests, skip check of
the dgid.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200630123605.446959-1-leon@kernel.org
Signed-off-by: Zhu Yanjun <yanjunz@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Update the code to allocate and free ib_xrcd structure in the
ib_core instead of inside drivers.
Link: https://lore.kernel.org/r/20200630101855.368895-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Expose UAPI to query MR, this will let user space application that
didn't allocate the MR but has access to by owning the matching command
FD to retrieve its information.
Link: https://lore.kernel.org/r/20200630093916.332097-8-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Introduce UAPI to query PD attributes, this can be used to retrieve PD
attributes by having the PD handle of the created one and owning the
command FD for the ucontxet.
Link: https://lore.kernel.org/r/20200630093916.332097-7-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Implement the query ucontext functionality by returning the original
ucontext data as part of an extra mlx5 attribute that holds the driver
UAPI response.
Link: https://lore.kernel.org/r/20200630093916.332097-6-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Refactor mlx5_ib_alloc_ucontext() to set its response fields in a
cleaner way.
It includes,
- Move the relevant code to a self contained function.
- Calculate the response length once and drop redundant code all around.
- Reuse previously set ucontext fields once preparing the response.
The self contained function will be used in next patch as part of
implementing the query ucontext functionality.
Link: https://lore.kernel.org/r/20200630093916.332097-5-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Expose UAPI to query ucontext, this will let user space application that
didn't allocate the ucontext but has access to by owning the matching
command FD to retrieve the ucontext information.
Link: https://lore.kernel.org/r/20200630093916.332097-4-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Set IOVA on IB MR in uverbs layer to let all drivers have it, this
includes both reg/rereg MR flows.
As part of this change cleaned-up this setting from the drivers that
already did it by themselves in their user flows.
Fixes: e6f0330106 ("mlx4_ib: set user mr attributes in struct ib_mr")
Link: https://lore.kernel.org/r/20200630093916.332097-3-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Enable CQ ioctl commands by default, this functionality is fully mature
to be used over ioctl, no reason to maintain any more the EXP KCONFIG
entry to enable it.
Link: https://lore.kernel.org/r/20200630093916.332097-2-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace the mutex with read write semaphore and use xarray instead of
linked list for XRC target QPs. This will give faster XRC target
lookup. In addition, when QP is closed, don't insert it back to the xarray
if the destroy command failed.
Link: https://lore.kernel.org/r/20200706122716.647338-4-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
ib_alloc_xrcd() already does the required initialization, so move the
uverbs to call it and save code duplication, while cleaning the function
argument lists of that function.
Link: https://lore.kernel.org/r/20200706122716.647338-3-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The mlx5_ib creates XRC domain and uses for creating internal SRQ.
However all that is needed is XRCD number and not full blown ib_xrcd
objects.
Update the code to get and store the number only.
Link: https://lore.kernel.org/r/20200706122716.647338-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Allocating an MR flow can only be initiated by kernel users, and not from
userspace so a udata parameter is redundant.
Link: https://lore.kernel.org/r/20200706120343.10816-4-galpress@amazon.com
Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Allocating an MR flow can only be initiated by kernel users, and not from
userspace. As a result, the udata parameter is always being passed as
NULL. Rename ib_alloc_mr_user function to ib_alloc_mr and remove the udata
parameter.
Link: https://lore.kernel.org/r/20200706120343.10816-3-galpress@amazon.com
Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The common kernel pattern is to check for error, not success. Flip the if
statement accordingly and keep the main flow unindented.
Link: https://lore.kernel.org/r/20200706120343.10816-2-galpress@amazon.com
Signed-off-by: Gal Pressman <galpress@amazon.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Michael Guralnik says:
====================
This series handles IPoIB child interface creation with setting
interface's HW address.
In current implementation, lladdr requested by user is ignored and
overwritten. Child interface gets the same GID as the parent interface and
a QP number which is assigned by the underlying drivers.
In this series we fix this behavior so that user's requested address is
assigned to the newly created interface.
As specific QP number request is not supported for all vendors, QP number
requested by user will still be overwritten when this is not supported.
Behavior of creation of child interfaces through the sysfs mechanism or
without specifying a requested address, stays the same.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
due to dependencies.
* branch 'mlx5_ipoib_qpn':
RDMA/ipoib: Handle user-supplied address when creating child
net/mlx5: Enable QP number request when creating IPoIB underlay QP
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Use the address supplied by user when creating a child interface.
Previously, the address requested by the user was ignored and overridden
with parent's GID and the random QP number assigned to the child.
Link: https://lore.kernel.org/r/20200623110105.1225750-3-leon@kernel.org
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
For debugging purpose it will be easier to understand if prefetch works
okay if it has its own counter. Introduce ODP prefetch counter and count
per MR the total number of prefetched pages.
In addition remove comment which is not relevant anymore and anyway not in
the correct place.
Link: https://lore.kernel.org/r/20200621104147.53795-1-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
There is a race condition where ib_nl_make_request() inserts the request
data into the linked list but the timer in ib_nl_request_timeout() can see
it and destroy it before ib_nl_send_msg() is done touching it. This could
happen, for instance, if there is a long delay allocating memory during
nlmsg_new()
This causes a use-after-free in the send_mad() thread:
[<ffffffffa02f43cb>] ? ib_pack+0x17b/0x240 [ib_core]
[ <ffffffffa032aef1>] ib_sa_path_rec_get+0x181/0x200 [ib_sa]
[<ffffffffa0379db0>] rdma_resolve_route+0x3c0/0x8d0 [rdma_cm]
[<ffffffffa0374450>] ? cma_bind_port+0xa0/0xa0 [rdma_cm]
[<ffffffffa040f850>] ? rds_rdma_cm_event_handler_cmn+0x850/0x850 [rds_rdma]
[<ffffffffa040f22c>] rds_rdma_cm_event_handler_cmn+0x22c/0x850 [rds_rdma]
[<ffffffffa040f860>] rds_rdma_cm_event_handler+0x10/0x20 [rds_rdma]
[<ffffffffa037778e>] addr_handler+0x9e/0x140 [rdma_cm]
[<ffffffffa026cdb4>] process_req+0x134/0x190 [ib_addr]
[<ffffffff810a02f9>] process_one_work+0x169/0x4a0
[<ffffffff810a0b2b>] worker_thread+0x5b/0x560
[<ffffffff810a0ad0>] ? flush_delayed_work+0x50/0x50
[<ffffffff810a68fb>] kthread+0xcb/0xf0
[<ffffffff816ec49a>] ? __schedule+0x24a/0x810
[<ffffffff816ec49a>] ? __schedule+0x24a/0x810
[<ffffffff810a6830>] ? kthread_create_on_node+0x180/0x180
[<ffffffff816f25a7>] ret_from_fork+0x47/0x90
[<ffffffff810a6830>] ? kthread_create_on_node+0x180/0x180
The ownership rule is once the request is on the list, ownership transfers
to the list and the local thread can't touch it any more, just like for
the normal MAD case in send_mad().
Thus, instead of adding before send and then trying to delete after on
errors, move the entire thing under the spinlock so that the send and
update of the lists are atomic to the conurrent threads. Lightly reoganize
things so spinlock safe memory allocations are done in the final NL send
path and the rest of the setup work is done before and outside the lock.
Fixes: 3ebd2fd0d0 ("IB/sa: Put netlink request into the request list before sending")
Link: https://lore.kernel.org/r/1592964789-14533-1-git-send-email-divya.indi@oracle.com
Signed-off-by: Divya Indi <divya.indi@oracle.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
ib_unregister_device_queued() can only be used by drivers using the new
dealloc_device callback flow, and it has a safety WARN_ON to ensure
drivers are using it properly.
However, if unregister and register are raced there is a special
destruction path that maintains the uniform error handling semantic of
'caller does ib_dealloc_device() on failure'. This requires disabling the
dealloc_device callback which triggers the WARN_ON.
Instead of using NULL to disable the callback use a special function
pointer so the WARN_ON does not trigger.
Fixes: d0899892ed ("RDMA/device: Provide APIs from the core code to help unregistration")
Link: https://lore.kernel.org/r/0-v1-a36d512e0a99+762-syz_dealloc_driver_jgg@nvidia.com
Reported-by: syzbot+4088ed905e4ae2b0e13b@syzkaller.appspotmail.com
Suggested-by: Hillf Danton <hdanton@sina.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The workqueue link_wq should only be destroyed when the hfi1 driver is
unloaded, not when the device is shut down.
Fixes: 71d47008ca ("IB/hfi1: Create workqueue for link events")
Link: https://lore.kernel.org/r/20200623204053.107638.70315.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Legacy IPoIB sets IB_QP_CREATE_NETIF_QP QP create flag and because mlx5
doesn't use this flag, the process_create_flags() failed to create IPoIB
QPs.
Fixes: 2978975ce7 ("RDMA/mlx5: Process create QP flags in one place")
Link: https://lore.kernel.org/r/20200630122147.445847-1-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Clang warns:
drivers/infiniband/hw/hfi1/qp.c:198:9: warning: implicit conversion from enumeration type 'enum opa_mtu' to different enumeration type 'enum ib_mtu' [-Wenum-conversion]
mtu = OPA_MTU_8192;
~ ^~~~~~~~~~~~
enum opa_mtu extends enum ib_mtu. There are typically two ways to deal
with this:
* Remove the expected types and just use 'int' for all parameters and
types.
* Explicitly cast the enums between each other.
This driver chooses to do the later so do the same thing here.
Fixes: 6d72344cf6 ("IB/ipoib: Increase ipoib Datagram mode MTU's upper limit")
Link: https://lore.kernel.org/r/20200623005224.492239-1-natechancellor@gmail.com
Link: https://github.com/ClangBuiltLinux/linux/issues/1062
Link: https://lore.kernel.org/linux-rdma/20200527040350.GA3118979@ubuntu-s3-xlarge-x86/
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
ipoib_mcast_carrier_on_task() insanely open codes a rtnl_lock() such that
the only time flush_workqueue() can be called is if it also clears
IPOIB_FLAG_OPER_UP.
Thus the flush inside ipoib_flush_ah() will deadlock if it gets unlucky
enough, and lockdep doesn't help us to find it early:
CPU0 CPU1 CPU2
__ipoib_ib_dev_flush()
down_read(vlan_rwsem)
ipoib_vlan_add()
rtnl_trylock()
down_write(vlan_rwsem)
ipoib_mcast_carrier_on_task()
while (!rtnl_trylock())
msleep(20);
ipoib_flush_ah()
flush_workqueue(priv->wq)
Clean up the ah_reaper related functions and lifecycle to make sense:
- Start/Stop of the reaper should only be done in open/stop NDOs, not in
any other places
- cancel and flush of the reaper should only happen in the stop NDO.
cancel is only functional when combined with IPOIB_STOP_REAPER.
- Non-stop places were flushing the AH's just need to flush out dead AH's
synchronously and ignore the background task completely. It is fully
locked and harmless to leave running.
Which ultimately fixes the ABBA deadlock by removing the unnecessary
flush_workqueue() from the problematic place under the vlan_rwsem.
Fixes: efc82eeeae ("IB/ipoib: No longer use flush as a parameter")
Link: https://lore.kernel.org/r/20200625174219.290842-1-kamalheib1@gmail.com
Reported-by: Kamal Heib <kheib@redhat.com>
Tested-by: Kamal Heib <kheib@redhat.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
pcie_speeds() and restore_pci_variables() returns PCIBIOS_ error codes
from PCIe capability accessors.
PCIBIOS_ error codes have positive values. Passing on these values is
inconsistent with functions which return only a negative value on failure.
Before passing on the return value of PCIe capability accessors, call
pcibios_err_to_errno() to convert any positive PCIBIOS_ error codes to
negative generic error values.
Link: https://lore.kernel.org/r/20200615073225.24061-3-refactormyself@gmail.com
Suggested-by: Bjorn Helgaas <bjorn@helgaas.com>
Signed-off-by: Bolarinwa Olayemi Saheed <refactormyself@gmail.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Jeff Kirsher says:
====================
40GbE Intel Wired LAN Driver Updates 2020-06-25
This series contains updates to i40e driver and removes the individual
driver versions from all of the Intel wired LAN drivers.
Shiraz moves the client header so that it can easily be shared between
the i40e LAN driver and i40iw RDMA driver.
Jesse cleans up the unused defines, since they are just dead weight.
Alek reduces the unreasonably long wait time for a PF reset after reboot
by using jiffies to limit the maximum wait time for the PF reset to
succeed. Added additional logging to let the user know when the driver
transitions into recovery mode. Adds new device support for our 5 Gbps
NICs.
Todd adds a check to see if MFS is set after warm reboot and notifies
the user when MFS is set to anything lower than the default value.
Arkadiusz fixes a possible race condition, where were holding a
spin-lock while in atomic context.
v2: removed code comments that were no longer applicable in patch 2 of
the series. Also removed 'inline' from patch 4 and patch 8 of the
series. Also re-arranged code to be able to remove the forward
function declarations. Dropped patch 9 of the series, while the
author works on cleaning up the commit message.
v3: Updated patch 8 description to answer Jakub's questions
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Move i40e_client.h to include/linux/net/intel/*
since its shared between i40iw and i40e.
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
The RWQ table is used for RSS uverbs and not in used for the kernel
consumers, delete ib_create_rwq_ind_table() routine that is not
called at all.
Link: https://lore.kernel.org/r/20200624105422.1452290-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The cancel_delayed_work can be called under lock since it doesn't sleep.
This makes the RMPP_STATE_CANCELING state not needed anymore, remove it.
Link: https://lore.kernel.org/r/20200621104738.54850-5-leon@kernel.org
Signed-off-by: Shay Drory <shayd@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The refcount API provides better safety than atomics API. Therefore,
change atomic functions to refcount functions.
Link: https://lore.kernel.org/r/20200621104738.54850-4-leon@kernel.org
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace calls of atomic_dec() to mad_agent_priv->refcount with calls to
deref_mad_agent() in order to issue complete. Most likely the refcount is
> 1 at these points, but it is difficult to prove. Performance is not
important on these paths, so be obviously correct.
Link: https://lore.kernel.org/r/20200621104738.54850-3-leon@kernel.org
Signed-off-by: Shay Drory <shayd@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When running iperf in a two host configuration the following trace can
occur:
[ 319.728730] NETDEV WATCHDOG: ib0 (hfi1): transmit queue 0 timed out
The issue happens because the current implementation relies on the netif
txq being stopped to control the flushing of the tx list.
There are two resources that the transmit logic can wait on and stop the
txq:
- SDMA descriptors
- Ring space to hold completions
The ring space is tested on the sending side and relieved when the ring is
consumed in the napi tx reaping.
Unfortunately, that reaping can run conncurrently with the workqueue
flushing of the txlist. If the txq is started just before the workitem
executes, the txlist will never be flushed, leading to the txq being
stuck.
Fix by:
- Adding sleep/wakeup wrappers
* Use an atomic to control the call to the netif routines inside the
wrappers
- Use another atomic to record ring space exhaustion
* Only wakeup when the a ring space exhaustion has happened and it
relieved
Add additional wrappers to clarify the ring space resource handling.
Fixes: d99dc602e2 ("IB/hfi1: Add functions to transmit datagram ipoib packets")
Link: https://lore.kernel.org/r/20200623204327.108092.4024.stgit@awfm-01.aw.intel.com
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The current code mishandles -EBUSY in two ways:
- The flow change doesn't test the return from the flush and runs on to
process the current packet racing with the wakeup processing
- The -EBUSY handling for a single packet inserts the tx into the txlist
after the submit call, racing with the same wakeup processing
Fix the first by dropping the skb and returning NETDEV_TX_OK.
Fix the second by insuring the the list entry within the txreq is inited
when allocated. This enables the sleep routine to detect that the txreq
has used the non-list api and queue the packet to the txlist.
Both flaws can lead to having the flushing thread executing in causing two
threads to manipulate the txlist.
Fixes: d99dc602e2 ("IB/hfi1: Add functions to transmit datagram ipoib packets")
Link: https://lore.kernel.org/r/20200623204321.108092.83898.stgit@awfm-01.aw.intel.com
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When the try_module_get calls were removed from opening and closing of the
i2c debugfs file, the corresponding module_put calls were missed. This
results in an inaccurate module use count that requires a power cycle to
fix.
Fixes: 09fbca8e62 ("IB/hfi1: No need to use try_module_get for debugfs")
Link: https://lore.kernel.org/r/20200623203230.106975.76240.stgit@awfm-01.aw.intel.com
Cc: <stable@vger.kernel.org>
Reviewed-by: Kaike Wan <kaike.wan@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Maor Gottlieb says:
====================
The following series adds support to get the RDMA resource data in RAW
format. The main motivation for doing this is to enable vendors to return
the entire QP/CQ/MR data without a need from the vendor to set each
field separately.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
due to dependencies
* branch 'raw_dumps':
RDMA/mlx5: Add support to get MR resource in RAW format
RDMA/mlx5: Add support to get CQ resource in RAW format
RDMA/mlx5: Add support to get QP resource in RAW format
RDMA: Add support to dump resource tracker in RAW format
RDMA: Add dedicated CM_ID resource tracker function
RDMA: Add dedicated QP resource tracker function
RDMA: Add a dedicated CQ resource tracker function
RDMA: Add dedicated MR resource tracker function
RDMA/core: Don't call fill_res_entry for PD
net/mlx5: Add support in query QP, CQ and MKEY segments
net/mlx5: Export resource dump interface
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add support to get MR (mkey) resource dump in RAW format.
Link: https://lore.kernel.org/r/20200623113043.1228482-12-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add support to get CQ resource dump in RAW format.
Link: https://lore.kernel.org/r/20200623113043.1228482-11-leon@kernel.org
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
