The RXE driver doesn't set sys_image_guid and user space applications see
zeros. This causes to pyverbs tests to fail with the following traceback,
because the IBTA spec requires to have valid sys_image_guid.
Traceback (most recent call last):
File "./tests/test_device.py", line 51, in test_query_device
self.verify_device_attr(attr)
File "./tests/test_device.py", line 74, in verify_device_attr
assert attr.sys_image_guid != 0
In order to fix it, set sys_image_guid to be equal to node_guid.
Before:
5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid
0000:0000:0000:0000
After:
5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid
5054:00ff:feaa:5363
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20200323112800.1444784-1-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@mellanox.com>
Since snprintf() returns the would-be-output size instead of the actual
output size, the succeeding calls may go beyond the given buffer limit.
Fix it by replacing with scnprintf().
Link: https://lore.kernel.org/r/20200319154641.23711-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Now that we have direct and reliable detection of WC support by the
system, use is broadly. The only case we have to worry about is when the
WC autodetector cannot run.
For this fringe case generally assume that that WC is available, except in
the well defined case of no PAT support on x86 which is tested by calling
arch_can_pci_mmap_wc().
If WC is wrongly assumed to be available then it causes a small
performance hit on paths in userspace that are tuned to the assumption
that WC is available. There is no functional loss.
It is very unlikely that any platforms exist that lack WC and also care
about the micro optimization of WC in the fringe case where autodetection
does not work.
By removing the fairly bogus CONFIG tests this makes WC work broadly on
all arches and all platforms.
Link: https://lore.kernel.org/r/20200318100323.46659-1-leon@kernel.org
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Reviewed-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Optimizes hns_roce_table_mhop_get() by encapsulating code about clearing
hem into clear_mhop_hem(), which will make the code flow clearer.
Link: https://lore.kernel.org/r/1584417324-2255-3-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@mellanox.com>
Destroy CQ command to firmware returns the num_cnq_events as a
response. This indicates the driver about the number of CQ events
generated for this CQ. Driver should wait for all these events before
freeing the CQ host structures. Also, add routine to clean all the
pending notification for the CQs getting destroyed. This avoids the
possibility of accessing the CQ data structures after its freed.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1584120842-3200-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The kzalloc() function returns NULL, not error pointers.
Fixes: 30f2fe40c7 ("IB/mlx5: Introduce UAPIs to manage packet pacing")
Link: https://lore.kernel.org/r/20200320132641.GF95012@mwanda
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
drivers/infiniband/sw/siw/siw_qp_rx.c: In function siw_proc_send:
./include/linux/spinlock.h:288:3: warning: flags may be used uninitialized in this function [-Wmaybe-uninitialized]
_raw_spin_unlock_irqrestore(lock, flags); \
^~~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/infiniband/sw/siw/siw_qp_rx.c:335:16: note: flags was declared here
unsigned long flags;
Link: https://lore.kernel.org/r/20200323184627.ZWPg91uin%akpm@linux-foundation.org
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Remove custom and duplicated variant of offsetofend().
Link: https://lore.kernel.org/r/20200310091438.248429-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Acked-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The field kobj was added to hfi1_devdata structure to manage the life time
of the hfi1_devdata structure for PSM accesses:
commit e11ffbd575 ("IB/hfi1: Do not free hfi1 cdev parent structure early")
Later another mechanism user_refcount/user_comp was introduced to provide
the same functionality:
commit acd7c8fe14 ("IB/hfi1: Fix an Oops on pci device force remove")
This patch will remove this kobj field, as it is no longer needed.
Link: https://lore.kernel.org/r/20200316210500.7753.4145.stgit@awfm-01.aw.intel.com
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@mellanox.com>
This routine was obsoleted by the patch below.
Delete it.
Fixes: a2a074ef39 ("RDMA: Handle ucontext allocations by IB/core")
Link: https://lore.kernel.org/r/20200316210454.7753.94689.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@mellanox.com>
Depth of qp shouldn't be allowed to be set to zero, after ensuring that,
subsequent process can be simplified. And when qp is changed from reset to
reset, the capability of minimum qp depth was used to identify hardware of
hip06, it should be changed into a more readable form.
Link: https://lore.kernel.org/r/1584006624-11846-1-git-send-email-liweihang@huawei.com
Signed-off-by: Lang Cheng <chenglang@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The driver uses a hard-coded value for FW version and reports an
inconsistent FW version between ibv_devinfo and
/sys/class/infiniband/i40iw/fw_ver.
Retrieve the FW version via a Control QP (CQP) operation and report it
consistently across sysfs and query device.
Fixes: d374984179 ("i40iw: add files for iwarp interface")
Link: https://lore.kernel.org/r/20200313214406.2159-1-shiraz.saleem@intel.com
Reported-by: Jarod Wilson <jarod@redhat.com>
Signed-off-by: Sindhu, Devale <sindhu.devale@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Splits hns_roce_v2_post_send() into three sub-functions: set_rc_wqe(),
set_ud_wqe() and update_sq_db() to simplify the code.
Link: https://lore.kernel.org/r/1583839084-31579-6-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently, before the qp is created, a page size needs to be calculated
for the base address table to store all base addresses in the mtr. As a
result, the parameter configuration of the mtr is complex. So integrate
the process of calculating the base table page size into the hem related
interface to simplify the process of using mtr.
Link: https://lore.kernel.org/r/1583839084-31579-5-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Simplify the wr opcode conversion from ib to hns by using a map table
instead of the switch-case statement.
Link: https://lore.kernel.org/r/1583839084-31579-4-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Encapsulates the wqe buffer process details for datagram seg, fast mr seg
and atomic seg.
Link: https://lore.kernel.org/r/1583839084-31579-3-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There are serval global functions related to wqe buffer in the hns driver
and are called in different files. These symbols cannot directly represent
the namespace they belong to. So add prefix 'hns_roce_' to 3 wqe buffer
related global functions: get_recv_wqe(), get_send_wqe(), and
get_send_extend_sge().
Link: https://lore.kernel.org/r/1583839084-31579-2-git-send-email-liweihang@huawei.com
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Weihang Li <liweihang@huawei.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
A work queue cannot just rely on the ib_device not being freed, it must
hold a kref on the memory so that the BNXT_RE_FLAG_IBDEV_REGISTERED check
works.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1584117207-2664-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There are a couple places in this driver running from a work queue that
need the ib_device to be registered. Instead of using a broken internal
bit rely on the new core code to guarantee device registration.
Link: https://lore.kernel.org/r/1584117207-2664-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The first switch statement in cm_destroy_id() tries to move the ID to
either IB_CM_IDLE or IB_CM_TIMEWAIT. Both states will block concurrent
MAD handlers from progressing.
Previous patches removed the unreliably lock/unlock sequences in this
flow, this patch removes the extra locking steps and adds the missing
parts to guarantee that destroy reaches IB_CM_IDLE. There is no point in
leaving the ID in the IB_CM_TIMEWAIT state the memory about to be kfreed.
Rework things to hold the lock across all the state transitions and
directly assert when done that it ended up in IB_CM_IDLE as expected.
This was accompanied by a careful audit of all the state transitions here,
which generally did end up in IDLE on their success and non-racy paths.
Link: https://lore.kernel.org/r/20200310092545.251365-16-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The first thing ib_send_cm_sidr_rep() does is obtain the lock, so use the
usual unlocked wrapper, locked actor pattern here.
Get rid of the cm_reject_sidr_req() wrapper so each call site can call the
locked or unlocked version as required.
This avoids a sketchy lock/unlock sequence (which could allow state to
change) during cm_destroy_id().
Link: https://lore.kernel.org/r/20200310092545.251365-15-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The first thing ib_send_cm_rej() does is obtain the lock, so use the usual
unlocked wrapper, locked actor pattern here.
This avoids a sketchy lock/unlock sequence (which could allow state to
change) during cm_destroy_id().
While here simplify some of the logic in the implementation.
Link: https://lore.kernel.org/r/20200310092545.251365-14-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The first thing ib_send_cm_drep() does is obtain the lock, so use the
usual unlocked wrapper, locked actor pattern here.
This avoids a sketchy lock/unlock sequence (which could allow state to
change) during cm_destroy_id().
Link: https://lore.kernel.org/r/20200310092545.251365-13-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The first thing ib_send_cm_dreq() does is obtain the lock, so use the
usual unlocked wrapper, locked actor pattern here.
This avoids a sketchy lock/unlock sequence (which could allow state to
change) during cm_destroy_id().
Link: https://lore.kernel.org/r/20200310092545.251365-12-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These functions all touch state, so must be called under the lock.
Inspection shows this is currently true.
Link: https://lore.kernel.org/r/20200310092545.251365-11-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
ib_crate_cm_id() immediately places the id in the xarray, and publishes it
into the remote_id and remote_qpn rbtrees. This makes it visible to other
threads before it is fully set up.
It appears the thinking here was that the states IB_CM_IDLE and
IB_CM_REQ_RCVD do not allow any MAD handler or lookup in the remote_id and
remote_qpn rbtrees to advance.
However, cm_rej_handler() does take an action on IB_CM_REQ_RCVD, which is
not really expected by the design.
Make the whole thing clearer:
- Keep the new cm_id out of the xarray until it is completely set up.
This directly prevents MAD handlers and all rbtree lookups from seeing
the pointer.
- Move all the trivial setup right to the top so it is obviously done
before any concurrency begins
- Move the mutation of the cm_id_priv out of cm_match_id() and into the
caller so the state transition is obvious
- Place the manipulation of the work_list at the end, under lock, after
the cm_id is placed in the xarray. The work_count cannot change on an
ID outside the xarray.
- Add some comments
Link: https://lore.kernel.org/r/20200310092545.251365-9-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
ib_create_cm_id() immediately places the id in the xarray, so it is visible
to network traffic.
The state is initially set to IB_CM_IDLE and all the MAD handlers will
test this state under lock and refuse to advance from IDLE, so adding to
the xarray is harmless.
Further, the set to IB_CM_SIDR_REQ_RCVD also excludes all MAD handlers.
However, the local_id isn't even used for SIDR mode, and there will be no
input MADs related to the newly created ID.
So, make the whole flow simpler so it can be understood:
- Do not put the SIDR cm_id in the xarray. This directly shows that there
is no concurrency
- Delete the confusing work_count and pending_list manipulations. This
mechanism is only used by MAD handlers and timewait, neither of which
apply to SIDR.
- Add a few comments and rename 'cur_cm_id_priv' to 'listen_cm_id_priv'
- Move other loose sets up to immediately after cm_id creation so that
the cm_id is fully configured right away. This fixes an oversight where
the service_id will not be returned back on a IB_SIDR_UNSUPPORTED
reject.
Link: https://lore.kernel.org/r/20200310092545.251365-8-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The lock should not be dropped before doing the pr_debug() print as it is
accessing data protected by the lock, such as id.state.
Fixes: 119bf81793 ("IB/cm: Add debug prints to ib_cm")
Link: https://lore.kernel.org/r/20200310092545.251365-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Any manipulation of cm_id->state must be done under the cm_id_priv->lock,
the two routines that added listens did not follow this rule, because they
never participate in any concurrent access around the state.
However, since this exception makes the code hard to understand, simplify
the flow so that it can be fully locked:
- Move manipulation of listen_sharecount into cm_insert_listen() so it is
trivially under the cm.lock without having to expose the cm.lock to the
caller.
- Push the cm.lock down into cm_insert_listen() and have the function
increment the reference count before returning an existing pointer.
- Split ib_cm_listen() into an cm_init_listen() and do not call
ib_cm_listen() from ib_cm_insert_listen()
- Make both ib_cm_listen() and ib_cm_insert_listen() directly call
cm_insert_listen() under their cm_id_priv->lock which does both a
collision detect and, if needed, the insert (atomically)
- Enclose all state manipulation within the cm_id_priv->lock, notice this
set can be done safely after cm_insert_listen() as no reader is allowed
to read the state without holding the lock.
- Do not set the listen cm_id in the xarray, as it is never correct to
look it up. This makes the concurrency simpler to understand.
Many needless error unwinds are removed in the process.
Link: https://lore.kernel.org/r/20200310092545.251365-6-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Too much of the destruction is very carefully sensitive to the state
and various other things. Move more code to the unconditional path and
add several WARN_ONs to check consistency.
Link: https://lore.kernel.org/r/20200310092545.251365-5-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
When creating a cm_id during REQ the id immediately becomes visible to the
other MAD handlers, and shortly after the state is moved to IB_CM_REQ_RCVD
This allows cm_rej_handler() to run concurrently and free the work:
CPU 0 CPU1
cm_req_handler()
ib_create_cm_id()
cm_match_req()
id_priv->state = IB_CM_REQ_RCVD
cm_rej_handler()
cm_acquire_id()
spin_lock(&id_priv->lock)
switch (id_priv->state)
case IB_CM_REQ_RCVD:
cm_reset_to_idle()
kfree(id_priv->timewait_info);
goto destroy
destroy:
kfree(id_priv->timewait_info);
id_priv->timewait_info = NULL
Causing a double free or worse.
Do not free the timewait_info without also holding the
id_priv->lock. Simplify this entire flow by making the free unconditional
during cm_destroy_id() and removing the confusing special case error
unwind during creation of the timewait_info.
This also fixes a leak of the timewait if cm_destroy_id() is called in
IB_CM_ESTABLISHED with an XRC TGT QP. The state machine will be left in
ESTABLISHED while it needed to transition through IB_CM_TIMEWAIT to
release the timewait pointer.
Also fix a leak of the timewait_info if the caller mis-uses the API and
does ib_send_cm_reqs().
Fixes: a977049dac ("[PATCH] IB: Add the kernel CM implementation")
Link: https://lore.kernel.org/r/20200310092545.251365-4-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The test here typod the cm_id_priv to use, it used the one that was
freshly allocated. By definition the allocated one has the matching
cm_handler and zero context, so the condition was always true.
Instead check that the existing listening ID is compatible with the
proposed handler so that it can be shared, as was originally intended.
Fixes: 067b171b86 ("IB/cm: Share listening CM IDs")
Link: https://lore.kernel.org/r/20200310092545.251365-3-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
xa_alloc_cyclic() is a SMP release to be paired with some later acquire
during xa_load() as part of cm_acquire_id().
As such, xa_alloc_cyclic() must be done after the cm_id is fully
initialized, in particular, it absolutely must be after the
refcount_set(), otherwise the refcount_inc() in cm_acquire_id() may not
see the set.
As there are several cases where a reader will be able to use the
id.local_id after cm_acquire_id in the IB_CM_IDLE state there needs to be
an unfortunate split into a NULL allocate and a finalizing xa_store.
Fixes: a977049dac ("[PATCH] IB: Add the kernel CM implementation")
Link: https://lore.kernel.org/r/20200310092545.251365-2-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
These judgments were used to keep the compatibility with older versions of
userspace that don't have the field named "cap_flags" in structure
hns_roce_ib_create_cq_resp. But it will be wrong to compare outlen with
the size of resp if another new field were added in resp. oulen should be
compared with the end offset of cap_flags in resp.
Fixes: 4f8f0d5e33 ("RDMA/hns: Package the flow of creating cq")
Link: https://lore.kernel.org/r/1583845569-47257-1-git-send-email-liweihang@huawei.com
Signed-off-by: Weihang Li <liweihang@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Leon Romanovsky says:
====================
This series fixes various corner cases in the mlx5_ib MR cache
implementation, see specific commit messages for more information.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
Due to dependencies
* branch 'mlx5_mr-cache':
RDMA/mlx5: Allow MRs to be created in the cache synchronously
RDMA/mlx5: Revise how the hysteresis scheme works for cache filling
RDMA/mlx5: Fix locking in MR cache work queue
RDMA/mlx5: Lock access to ent->available_mrs/limit when doing queue_work
RDMA/mlx5: Fix MR cache size and limit debugfs
RDMA/mlx5: Always remove MRs from the cache before destroying them
RDMA/mlx5: Simplify how the MR cache bucket is located
RDMA/mlx5: Rename the tracking variables for the MR cache
RDMA/mlx5: Replace spinlock protected write with atomic var
{IB,net}/mlx5: Move asynchronous mkey creation to mlx5_ib
{IB,net}/mlx5: Assign mkey variant in mlx5_ib only
{IB,net}/mlx5: Setup mkey variant before mr create command invocation
If the cache is completely out of MRs, and we are running in cache mode,
then directly, and synchronously, create an MR that is compatible with the
cache bucket using a sleeping mailbox command. This ensures that the
thread that is waiting for the MR absolutely will get one.
When a MR allocated in this way becomes freed then it is compatible with
the cache bucket and will be recycled back into it.
Deletes the very buggy ent->compl scheme to create a synchronous MR
allocation.
Link: https://lore.kernel.org/r/20200310082238.239865-13-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Currently if the work queue is running then it is in 'hysteresis' mode and
will fill until the cache reaches the high water mark. This implicit state
is very tricky and doesn't interact with pending very well.
Instead of self re-scheduling the work queue after the add_keys() has
started to create the new MR, have the queue scheduled from
reg_mr_callback() only after the requested MR has been added.
This avoids the bad design of an in-rush of queue'd work doing back to
back add_keys() until EAGAIN then sleeping. The add_keys() will be paced
one at a time as they complete, slowly filling up the cache.
Also, fix pending to be only manipulated under lock.
Link: https://lore.kernel.org/r/20200310082238.239865-12-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
All of the members of mlx5_cache_ent must be accessed while holding the
spinlock, add the missing spinlock in the __cache_work_func().
Using cache->stopped and flush_workqueue() is an inherently racy way to
shutdown self-scheduling work on a queue. Replace it with ent->disabled
under lock, and always check disabled before queuing any new work. Use
cancel_work_sync() to shutdown the queue.
Use READ_ONCE/WRITE_ONCE for dev->last_add to manage concurrency as
coherency is less important here.
Split fill_delay from the bitfield. C bitfield updates are not atomic and
this is just a mess. Use READ_ONCE/WRITE_ONCE, but this could also use
test_bit()/set_bit().
Link: https://lore.kernel.org/r/20200310082238.239865-11-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Accesses to these members needs to be locked. There is no reason not to
hold a spinlock while calling queue_work(), so move the tests into a
helper and always call it under lock.
The helper should be called when available_mrs is adjusted.
Link: https://lore.kernel.org/r/20200310082238.239865-10-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The size_write function is supposed to adjust the total_mr's to match the
user's request, but lacks locking and safety checking.
total_mrs can only be adjusted by at most available_mrs. mrs already
assigned to users cannot be revoked. Ensure that the user provides a
target value within the range of available_mrs and within the high/low
water mark.
limit_write has confusing and wrong sanity checking, and doesn't have the
ability to deallocate on limit reduction.
Since both functions use the same algorithm to adjust the available_mrs,
consolidate it into one function and write it correctly. Fix the locking
and by holding the spinlock for all accesses to ent->X.
Always fail if the user provides a malformed string.
Fixes: e126ba97db ("mlx5: Add driver for Mellanox Connect-IB adapters")
Link: https://lore.kernel.org/r/20200310082238.239865-9-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The cache bucket tracks the total number of MRs that exists, both inside
and outside of the cache. Removing a MR from the cache (by setting
cache_ent to NULL) without updating total_mrs will cause the tracking to
leak and be inflated.
Further fix the rereg_mr path to always destroy the MR. reg_create will
always overwrite all the MR data in mlx5_ib_mr, so the MR must be
completely destroyed, in all cases, before this function can be
called. Detach the MR from the cache and unconditionally destroy it to
avoid leaking HW mkeys.
Fixes: afd1417404 ("IB/mlx5: Use direct mkey destroy command upon UMR unreg failure")
Fixes: 56e11d628c ("IB/mlx5: Added support for re-registration of MRs")
Link: https://lore.kernel.org/r/20200310082238.239865-8-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There are many bad APIs here that are accepting a cache bucket index
instead of a bucket pointer. Many of the callers already have a bucket
pointer, so this results in a lot of confusing uses of order2idx().
Pass the struct mlx5_cache_ent into add_keys(), remove_keys(), and
alloc_cached_mr().
Once the MR is in the cache, store the cache bucket pointer directly in
the MR, replacing the 'bool allocated_from cache'.
In the end there is only one place that needs to form index from order,
alloc_mr_from_cache(). Increase the safety of this function by disallowing
it from accessing cache entries in the ODP special area.
Link: https://lore.kernel.org/r/20200310082238.239865-7-leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
mkey variant calculation was spinlock protected to make it atomic, replace
that with one atomic variable.
Link: https://lore.kernel.org/r/20200310082238.239865-4-leon@kernel.org
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
As mlx5_ib is the only user of the mlx5_core_create_mkey_cb, move the
logic inside mlx5_ib and cleanup the code in mlx5_core.
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
mkey variant is not required for mlx5_core use, move the mkey variant
counter to mlx5_ib.
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
