Yishai Hadas Says:
====================
Expose raw packet pacing APIs to be used by DEVX based applications. The
existing code was refactored to have a single flow with the new raw APIs.
====================
Based on the mlx5-next branch at
git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux
Due to dependencies
* branch 'mlx5_packet_pacing':
IB/mlx5: Introduce UAPIs to manage packet pacing
net/mlx5: Expose raw packet pacing APIs
Add two debugfs parameters described below.
np_min_time_between_cnps - Minimum time between sending CNPs from the
port.
Unit = microseconds.
Default = 0 (no min wait time; generated
based on incoming ECN marked packets).
rp_max_rate - Maximum rate at which reaction point node can transmit.
Once this limit is reached, RP is no longer rate limited.
Unit = Mbits/sec
Default = 0 (full speed)
Link: https://lore.kernel.org/r/20200227125246.99472-1-leon@kernel.org
Signed-off-by: Parav Pandit <parav@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Following race may occur because of the call_srcu and the placement of
the synchronize_srcu vs the xa_erase.
CPU0 CPU1
mlx5_ib_free_implicit_mr: destroy_unused_implicit_child_mr:
xa_erase(odp_mkeys)
synchronize_srcu()
xa_lock(implicit_children)
if (still in xarray)
atomic_inc()
call_srcu()
xa_unlock(implicit_children)
xa_erase(implicit_children):
xa_lock(implicit_children)
__xa_erase()
xa_unlock(implicit_children)
flush_workqueue()
[..]
free_implicit_child_mr_rcu:
(via call_srcu)
queue_work()
WARN_ON(atomic_read())
[..]
free_implicit_child_mr_work:
(via wq)
free_implicit_child_mr()
mlx5_mr_cache_invalidate()
mlx5_ib_update_xlt() <-- UMR QP fail
atomic_dec()
The wait_event() solves the race because it blocks until
free_implicit_child_mr_work() completes.
Fixes: 5256edcb98 ("RDMA/mlx5: Rework implicit ODP destroy")
Link: https://lore.kernel.org/r/20200227113918.94432-1-leon@kernel.org
Signed-off-by: Artemy Kovalyov <artemyko@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Commit f164be8c03 ("IB/mlx5: Extend caps stage to handle VAR
capabilities") introduced a straight "/" division of the u64 variable
"bar_size".
This was fixed with commit 685eff5131 ("IB/mlx5: Use div64_u64 for
num_var_hw_entries calculation"). However, div64_u64() is redundant here
as mlx5_var_table::stride_size is of type u32. Make the actual code way
more optimized on 32-bit kernels using div_u64() and fix 80 chars
break-through by the way.
Fixes: 685eff5131 ("IB/mlx5: Use div64_u64 for num_var_hw_entries calculation")
Link: https://lore.kernel.org/r/20200217073629.8051-1-alobakin@dlink.ru
Signed-off-by: Alexander Lobakin <alobakin@dlink.ru>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Relaxed ordering is not supported in UMR so we are disabling UMR usage
when user passes relaxed ordering access flag.
Enable using UMR when user requested relaxed ordering but there are no
relaxed ordering capabilities.
This will prevent user from unnecessarily registering a new mkey.
Fixes: d6de0bb185 ("RDMA/mlx5: Set relaxed ordering when requested")
Link: https://lore.kernel.org/r/20200227113834.94233-1-leon@kernel.org
Signed-off-by: Michael Guralnik <michaelgur@mellanox.com>
Reviewed-by: Maor Gottlieb <maorg@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c: In function '__send_message':
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c:101:10: warning:
variable 'idx' set but not used [-Wunused-but-set-variable]
drivers/infiniband/hw/bnxt_re/qplib_rcfw.c:101:6: warning:
variable 'pg' set but not used [-Wunused-but-set-variable]
commit cee0c7bba4 ("RDMA/bnxt_re: Refactor command queue management
code") involved this, but not used.
Link: https://lore.kernel.org/r/20200227064900.92255-1-yuehaibing@huawei.com
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/infiniband/hw/bnxt_re/ib_verbs.c: In function 'bnxt_re_create_gsi_qp':
drivers/infiniband/hw/bnxt_re/ib_verbs.c:1283:30: warning:
variable 'dev_attr' set but not used [-Wunused-but-set-variable]
commit 8dae419f9e ("RDMA/bnxt_re: Refactor queue pair creation code")
involved this, but not used, so remove it.
Link: https://lore.kernel.org/r/20200227064542.91205-1-yuehaibing@huawei.com
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/infiniband/hw/bnxt_re/qplib_res.c: In function '__alloc_pbl':
drivers/infiniband/hw/bnxt_re/qplib_res.c:109:13: warning:
variable 'pg_size' set but not used [-Wunused-but-set-variable]
commit 0c4dcd6028 ("RDMA/bnxt_re: Refactor hardware queue memory
allocation") involved this, but not used, so remove it.
Link: https://lore.kernel.org/r/20200227064209.87893-1-yuehaibing@huawei.com
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Using the new unregister APIs provided by the core. Provide the
dealloc_driver hook for the core to callback at the time of device
un-registration.
bnxt_re VF resources are created by the corresponding PF driver. During
ib_unregister_driver, PF might get removed before VF and this could cause
failure when VFs are removed. Driver is explicitly queuing the removal of
VF devices before calling ib_unregister_driver.
Link: https://lore.kernel.org/r/1582731932-26574-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
- bnxt_re_ib_reg() handles two main functionalities - initializing the
device and registering with the IB stack. Split it into 2 functions
i.e. bnxt_re_dev_init() and bnxt_re_ib_init() to account for the same
thereby improve modularity. Do the same for
bnxt_re_ib_unreg()i.e. split into two functions - bnxt_re_dev_uninit()
and bnxt_re_ib_uninit().
- Simplify the code by combining the different steps to add and remove
the device into two functions.
- Report correct netdev link state during device register
Link: https://lore.kernel.org/r/1582731932-26574-2-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 packet handling function, specifically the iteration of the qp list
for mad packet processing misses locking RCU before running through the
list. Not only is this incorrect, but the list_for_each_entry_rcu() call
can not be called with a conditional check for lock dependency. Remedy
this by invoking the rcu lock and unlock around the critical section.
This brings MAD packet processing in line with what is done for non-MAD
packets.
Fixes: 7724105686 ("IB/hfi1: add driver files")
Link: https://lore.kernel.org/r/20200225195445.140896.41873.stgit@awfm-01.aw.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@mellanox.com>
When destroying a DMA mmapped object, there is no need to artificially
delay the freeing of the pages to the mmap entry removal. Since the vma
keeps a reference count on these pages, free_pages_exact can be called on
the destroy verb as it won't really free the pages until the reference
count is cleared (in case the user hasn't called munmap yet).
Remove the special handling of DMA pages and call free_pages_exact on
destroy_qp/cq. The mmap entry removal is moved to the beginning of the
destroy flows, so the driver can safely free the pages.
Link: https://lore.kernel.org/r/20200225114010.21790-4-galpress@amazon.com
Reviewed-by: Firas JahJah <firasj@amazon.com>
Reviewed-by: Yossi Leybovich <sleybo@amazon.com>
Signed-off-by: Gal Pressman <galpress@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
There are two paths to update qp producer index into hardware now, one
path is doorbell in post verbs (send and recv), the another is mailbox in
modify qp verb which is called by flush process. This will lead the
hardware to be broken to correctly generate flush cqe. With stopping
doorbell update and holding qp spinlock in modify qp during flush process,
the problem can be solved.
Fixes: 0425e3e6e0 ("RDMA/hns: Support flush cqe for hip08 in kernel space")
Link: https://lore.kernel.org/r/1582367158-27030-3-git-send-email-liuyixian@huawei.com
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Pull EFI updates for v5.7 from Ard Biesheuvel:
This time, the set of changes for the EFI subsystem is much larger than
usual. The main reasons are:
- Get things cleaned up before EFI support for RISC-V arrives, which will
increase the size of the validation matrix, and therefore the threshold to
making drastic changes,
- After years of defunct maintainership, the GRUB project has finally started
to consider changes from the distros regarding UEFI boot, some of which are
highly specific to the way x86 does UEFI secure boot and measured boot,
based on knowledge of both shim internals and the layout of bootparams and
the x86 setup header. Having this maintenance burden on other architectures
(which don't need shim in the first place) is hard to justify, so instead,
we are introducing a generic Linux/UEFI boot protocol.
Summary of changes:
- Boot time GDT handling changes (Arvind)
- Simplify handling of EFI properties table on arm64
- Generic EFI stub cleanups, to improve command line handling, file I/O,
memory allocation, etc.
- Introduce a generic initrd loading method based on calling back into
the firmware, instead of relying on the x86 EFI handover protocol or
device tree.
- Introduce a mixed mode boot method that does not rely on the x86 EFI
handover protocol either, and could potentially be adopted by other
architectures (if another one ever surfaces where one execution mode
is a superset of another)
- Clean up the contents of struct efi, and move out everything that
doesn't need to be stored there.
- Incorporate support for UEFI spec v2.8A changes that permit firmware
implementations to return EFI_UNSUPPORTED from UEFI runtime services at
OS runtime, and expose a mask of which ones are supported or unsupported
via a configuration table.
- Various documentation updates and minor code cleanups (Heinrich)
- Partial fix for the lack of by-VA cache maintenance in the decompressor
on 32-bit ARM. Note that these patches were deliberately put at the
beginning so they can be used as a stable branch that will be shared with
a PR containing the complete fix, which I will send to the ARM tree.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Moving all the fast path doorbell functions at one place under
qplib_res.h. To pass doorbell record information a new structure
bnxt_qplib_db_info has been introduced. Every roce object holds an
instance of this structure and doorbell information is initialized during
resource creation.
When DB is rung only the current queue index is read from hardware ring
and rest of the data is taken from pre-initialized dbinfo structure.
Link: https://lore.kernel.org/r/1581786665-23705-8-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Refactoring the command queue (rcfw) management code. A new data-structure
is introduced to describe the bar register. each object which deals with
mmio space should have a descriptor structure. This structure specifically
hold DB register information. Thus, slow path creq structure now hold a
bar register descriptor.
Further cleanup the rcfw structure to introduce the command queue context
and command response event queue context structures. Rest of the rcfw
related code has been touched to incorporate these three structures.
Link: https://lore.kernel.org/r/1581786665-23705-6-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Naresh Kumar PBS <nareshkumar.pbs@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
At top level there are three major data structure addition. viz
bnxt_qplib_hwq_attr, bnxt_qplib_sg_info and bnxt_qplib_tqm_ctx
Intorduction of first data structure reduces the arguments list to
bnxt_re_alloc_init_hwq() function. There are changes all over the driver
code to incorporate this new structure. The caller needs to fill the
attribute data structure and pass to this function.
The second data structure is to pass memory region description
viz. sghead, page_size and page_shift. There are changes all over the
driver code to initialize bnxt_re_sg_info data structure. The new data
structure helps to reduce the argument list of __alloc_pbl() function
call.
Till now the TQM rings related members were not collected under any
specific data-structure making it hard to manage. The third data
sctructure bnxt_qplib_tqm_ctx is added to refactor the TQM queue
allocation and initialization.
Link: https://lore.kernel.org/r/1581786665-23705-4-git-send-email-devesh.sharma@broadcom.com
Signed-off-by: Naresh Kumar PBS <nareshkumar.pbs@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Devesh Sharma <devesh.sharma@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
The current codebase makes use of the zero-length array language
extension to the C90 standard, but the preferred mechanism to declare
variable-length types such as these ones is a flexible array member[1][2],
introduced in C99:
struct foo {
int stuff;
struct boo array[];
};
By making use of the mechanism above, we will get a compiler warning
in case the flexible array does not occur last in the structure, which
will help us prevent some kind of undefined behavior bugs from being
inadvertently introduced[3] to the codebase from now on.
Also, notice that, dynamic memory allocations won't be affected by
this change:
"Flexible array members have incomplete type, and so the sizeof operator
may not be applied. As a quirk of the original implementation of
zero-length arrays, sizeof evaluates to zero."[1]
This issue was found with the help of Coccinelle.
[1] https://gcc.gnu.org/onlinedocs/gcc/Zero-Length.html
[2] https://github.com/KSPP/linux/issues/21
[3] commit 7649773293 ("cxgb3/l2t: Fix undefined behaviour")
Link: https://lore.kernel.org/r/20200213010425.GA13068@embeddedor.com
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> # added a few more
Multi chain support requires the miss path to continue the processing
from the last chain id, and for that we need to save the chain
miss tag (a mapping for 32bit chain id) on reg_c0 which will
come in a next patch.
Currently reg_c0 is exclusively used to store the source port
metadata, giving it 32bit, it is created from 16bits of vcha_id,
and 16bits of vport number.
We will move this source port metadata to upper 16bits, and leave the
lower bits for the chain miss tag. We compress the reg_c0 source port
metadata to 16bits by taking 8 bits from vhca_id, and 8bits from
the vport number.
Since we compress the vport number to 8bits statically, and leave two
top ids for special PF/ECPF numbers, we will only support a max of 254
vports with this strategy.
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
HiP08 RoCE hardware lacks ability(a known hardware problem) to flush
outstanding WQEs if QP state gets into errored mode for some reason. To
overcome this hardware problem and as a workaround, when QP is detected to
be in errored state during various legs like post send, post receive
etc[1], flush needs to be performed from the driver.
The earlier patch[1] sent to solve the hardware limitation explained in
the cover-letter had a bug in the software flushing leg. It acquired mutex
while modifying QP state to errored state and while conveying it to the
hardware using the mailbox. This caused leg to sleep while holding
spin-lock and caused crash.
Suggested Solution: we have proposed to defer the flushing of the QP in
the Errored state using the workqueue to get around with the limitation of
our hardware.
This patch specifically adds the calls to the flush handler from where
parts of the code like post_send/post_recv etc. when the QP state gets
into the errored mode.
[1] https://patchwork.kernel.org/patch/10534271/
Link: https://lore.kernel.org/r/1580983005-13899-3-git-send-email-liuyixian@huawei.com
Signed-off-by: Yixian Liu <liuyixian@huawei.com>
Reviewed-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
