As of now bnxt_re_init_hwrm_hdr is taking only the opcode from the
caller. compl_ring and target_id field is always -1. These fields might be
changed when newer features are added. For now, removing these parameters
as they are hard coded. Also, remove the rdev field which is not used.
Also, initialize the structure bnxt_fw_msg during declaration itself.
Link: https://lore.kernel.org/r/1686679943-17117-4-git-send-email-selvin.xavier@broadcom.com
Suggested-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add driver disassociation support. Driver uses the APIs rdma_user_mmap_io
api while mapping the IO pages to user space. Add empty stub for
disassociate ucontext.
Link: https://lore.kernel.org/r/1686679943-17117-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace the mmap handling function with common code in IB core. Create
rdma_user_mmap_entry for each mmap resource and add to the ib_core mmap
list. Add mmap_free verb support. Also, use rdma_user_mmap_io while
mapping Doorbell pages.
Link: https://lore.kernel.org/r/1686679943-17117-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The call netdev_{put, hold} of dev_{put, hold} will check NULL, so there
is no need to check before using dev_{put, hold}, remove it to silence the
warning:
./drivers/infiniband/core/cma.c:4812:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed.
Link: https://lore.kernel.org/r/20230614014328.14007-1-yang.lee@linux.alibaba.com
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Closes: https://bugzilla.openanolis.cn/show_bug.cgi?id=5521
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The flags parameter to the request notify verb is a bitmask. But, rxe
driver treats cq->notify as an int. If someone ever set both the
IB_CQ_SOLICITED and the IB_CQ_NEXT_COMP bits rxe_cq_post could fail to
generate a completion event. This patch treats the notify flags as a bit
mask consistently and can handle the above case correctly.
Link: https://lore.kernel.org/r/20230612162244.20038-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
A recent patch incorrectly did not include IB_ACCESS_RELAXED_ORDERING in
the list of supported access flags for the rxe driver. The driver actually
does nothing related to relaxed ordering but it causes no problems to
include it as supported but with no effect. This change caused ib_send_bw
and friends to not run correctly.
The correct approach is for the driver to allow any of the optional access
flags and otherwise ignore them. This patch adds IB_ACCESS_OPTIONAL to the
list of rxe supported flags.
Fixes: 02ed253770 ("RDMA/rxe: Introduce rxe access supported flags")
Link: https://lore.kernel.org/r/20230613171654.19334-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
A recent patch replaced a tasklet execution of cq->comp_handler by a
direct call. While this made sense it let changes to cq->notify state be
unprotected and assumed that the cq completion machinery and the ulp done
callbacks were reentrant. The result is that in some cases completion
events can be lost. This patch moves the cq->comp_handler call inside of
the spinlock in rxe_cq_post which solves both issues. This is compatible
with the matching code in the request notify verb.
Fixes: 78b26a3353 ("RDMA/rxe: Remove tasklet call from rxe_cq.c")
Link: https://lore.kernel.org/r/20230612155032.17036-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Avoid passing arguments like Opcode which can be retrieved from
bnxt_qplib_crsqe structure.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-18-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
cmdq_bitmap is used to derive the next available index in the CMDQ.
This is not required as the we can get the next index
using the existing bnxt_qplib_crsqe array.
Driver will use bnxt_qplib_crsqe array and flag is_in_used to
derive valid entries. is_in_used is replacement of cmdq_bitmap.
There is no change in the existing mechanism of the circular buffer
used to get index.
Added opcode field in bnxt_qplib_crsqe array so that it is easy to map
opcode associated with pending rcfw command.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-17-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Firmware provides max request timeout value as part of hwrm_ver_get
API. Driver gets the timeout from firmware and if that interface is
not available then fall back to hardcoded timeout value.
Also, Add a helper function to check the FW status.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-16-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
When an error is detected in FW, wake up all the waiters as the
all of them need to be completed with timeout. Add the device
error state also as a wait condition.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-15-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
If destroy_ah is timed out, it is likely to be destroyed by firmware
but it is taking longer time due to temporary slowness
in processing the rcfw command. In worst case, there might be
AH resource leak in firmware.
Sending timeout return value can dump warning message from ib_core
which can be avoided if we map timeout of destroy_ah as success.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-14-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
AH create may be called from interrpt context and driver has a special
timeout (8 sec) for this command. This is to avoid soft lockups when
the FW command takes more time. Driver returns -ETIMEOUT and fail
create AH, without waiting for actual completion from firmware.
When FW completion is received, use is_waiter_alive flag to avoid
a regular completion path.
If create_ah opcode is detected in completion path which does not have
waiter alive, driver will fetch ah_id from successful firmware
completion in the interrupt context and sends destroy_ah command
for same ah_id. This special post is done in quick manner using helper
function __send_message_no_waiter.
timeout_send is only used for debugging purposes.
If timeout_send value keeps incrementing, it indicates out of sync
active ah counter between driver and firmware. This is a limitation
but graceful handling is possible in future.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-13-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Every completion will update last_seen value in the unit of jiffies.
last_seen field will be used to know if firmware is alive and
is useful to detect firmware stall.
Non blocking interface __wait_for_resp will have logic to detect
firmware stall. After every 10 second interval if __wait_for_resp
has not received completion for a given command it will check for
firmware stall condition.
If current jiffies is greater than last_seen
jiffies + RCFW_FW_STALL_TIMEOUT_SEC * HZ, it is a firmware stall.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-12-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
If calling context detect command timeout, associated memory stored on
stack will not be valid. If firmware complete the same command later,
this causes incorrect memory access by driver.
Added is_waiter_alive to handle delayed completion by firmware.
is_waiter_alive is set and reset under command queue lock.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-11-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
This interface will be used if the driver has not enabled interrupt
and/or interrupt is disabled for a short period of time.
Completion is not possible from interrupt so this interface does
self-polling.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-10-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
- Use __send_message_basic_sanity helper function.
- Do not retry posting same command if there is a queue full detection.
- ENXIO is used to indicate controller recovery.
- In the case of ERR_DEVICE_DETACHED state, the driver should not post
commands to the firmware, but also return fabricated written code.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-9-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Whenever there is a fast path IO and create/destroy resources from
the slow path is happening in parallel, we may notice high latency
of slow path command completion.
Introduces a shadow queue depth to prevent the outstanding requests
to the FW. Driver will not allow more than #RCFW_CMD_NON_BLOCKING_SHADOW_QD
non-blocking commands to the Firmware.
Shadow queue depth is a soft limit only for non-blocking
commands. Blocking commands will be posted to the firmware
as long as there is a free slot.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-8-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add a check to avoid waiting if driver already detects a
FW timeout. Return success for resource destroy in case
the device is detached. Add helper function to map timeout
error code to success.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-7-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Use jiffies based timewait instead of counting iteration for
commands that block for FW response.
Also add a poll routine for control path commands. This is for
polling completion if the waiting commands timeout. This avoids cases
where the driver misses completion interrupts.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-6-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
There is no need of setting max command queue entries based on
firmware version check.
Removing deperecated code.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-5-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
There is a common FW communication offset for both PF and VF.
Removed code around virt_fn check while creating FW channel.
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-4-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
bnxt_qplib_service_creq can be called from interrupt or tasklet or
process context. So the function take irq variant of spin_lock.
But when wake_up is invoked with the lock held, it is putting the
calling context to sleep.
[exception RIP: __wake_up_common+190]
RIP: ffffffffb7539d7e RSP: ffffa73300207ad8 RFLAGS: 00000083
RAX: 0000000000000001 RBX: ffff91fa295f69b8 RCX: dead000000000200
RDX: ffffa733344af940 RSI: ffffa73336527940 RDI: ffffa73336527940
RBP: 000000000000001c R8: 0000000000000002 R9: 00000000000299c0
R10: 0000017230de82c5 R11: 0000000000000002 R12: ffffa73300207b28
R13: 0000000000000000 R14: ffffa733341bf928 R15: 0000000000000000
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
Call the wakeup after releasing the lock.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Driver is not handling the wraparound of the mbox producer index correctly.
Currently the wraparound happens once u32 max is reached.
Bit 31 of the producer index register is special and should be set
only once for the first command. Because the producer index overflow
setting bit31 after a long time, FW goes to initialization sequence
and this causes FW hang.
Fix is to wraparound the mbox producer index once it reaches u16 max.
Fixes: cee0c7bba4 ("RDMA/bnxt_re: Refactor command queue management code")
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1686308514-11996-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The ib_isert module is releasing the isert connection both in
isert_wait_conn() handler as well as isert_free_conn() handler.
In isert_wait_conn() handler, it is expected to wait for iSCSI
session logout operation to complete. It should free the isert
connection only in isert_free_conn() handler.
When a bunch of iSER target is cleared, this issue can lead to
use-after-free memory issue as isert conn is twice released
Fixes: b02efbfc9a ("iser-target: Fix implicit termination of connections")
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/20230606102531.162967-4-saravanan.vajravel@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
When ib_isert module receives connection error event, it is
releasing the isert session and removes corresponding list
node but it doesn't take appropriate mutex lock to remove
the list node. This can lead to linked list corruption
Fixes: bd3792205a ("iser-target: Fix pending connections handling in target stack shutdown sequnce")
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Link: https://lore.kernel.org/r/20230606102531.162967-3-saravanan.vajravel@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The original doorbell allocation mechanism is complex and does not meet
the isolation requirement. So we introduce a new doorbell mechanism and the
original mechanism (only be used with CAP_SYS_RAWIO if hardware does not
support the new mechanism) needs to be kept as simple as possible for
compatibility.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230606055005.80729-5-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
For the isolation requirement, each QP/CQ can only issue doorbells from the
allocated mmio space. Configure the relationship between QPs/CQs and
mmio doorbell spaces to hardware in create_qp/create_cq interfaces.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230606055005.80729-4-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Each ucontext will try to allocate doorbell resources in the extended bar
space from hardware. For compatibility, we change nothing for the original
bar space, and it will be used only for applications with CAP_SYS_RAWIO
authority in the older HW/FW environments.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230606055005.80729-3-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add a new CMDQ message to configure hardware. Initially the page size (in
the format of shift) will be passed to hardware, so that hardware can
organize the mmio space properly. It's called only if hardware supports it.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230606055005.80729-2-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The cited commit aimed to ensure that Virtual Functions (VFs) assign a
queue affinity to a Queue Pair (QP) to distribute traffic when
the LAG master creates a hardware LAG. If the affinity was set while
the hardware was not in LAG, the firmware would ignore the affinity value.
However, this commit unintentionally assigned an affinity to QPs on the LAG
master's VPORT even if the RDMA device was not marked as LAG-enabled.
In most cases, this was not an issue because when the hardware entered
hardware LAG configuration, the RDMA device of the LAG master would be
destroyed and a new one would be created, marked as LAG-enabled.
The problem arises when a user configures Equal-Cost Multipath (ECMP).
In ECMP mode, traffic can be directed to different physical ports based on
the queue affinity, which is intended for use by VPORTS other than the
E-Switch manager. ECMP mode is supported only if both E-Switch managers are
in switchdev mode and the appropriate route is configured via IP. In this
configuration, the RDMA device is not destroyed, and we retain the RDMA
device that is not marked as LAG-enabled.
To ensure correct behavior, Send Queues (SQs) opened by the E-Switch
manager through verbs should be assigned strict affinity. This means they
will only be able to communicate through the native physical port
associated with the E-Switch manager. This will prevent the firmware from
assigning affinity and will not allow the SQs to be remapped in case of
failover.
Fixes: 802dcc7fc5 ("RDMA/mlx5: Support TX port affinity for VF drivers in LAG mode")
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://lore.kernel.org/r/425b05f4da840bc684b0f7e8ebf61aeb5cef09b0.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Fix ib_uverbs_event_read() to consider event queue closing also upon
non-blocking mode.
Once the queue is closed (e.g. hot-plug flow) all the existing events
are cleaned-up as part of ib_uverbs_free_event_queue().
An application that uses the non-blocking FD mode should get -EIO in
that case to let it knows that the device was removed already.
Otherwise, it can loose the indication that the device was removed and
won't recover.
As part of that, refactor the code to have a single flow with regards to
'is_closed' for both blocking and non-blocking modes.
Fixes: 14e23bd6d2 ("RDMA/core: Fix locking in ib_uverbs_event_read")
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/97b00116a1e1e13f8dc4ec38a5ea81cf8c030210.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
According to the IB specification rel-1.6, section 3.5.3:
"QKEYs with the most significant bit set are considered controlled
QKEYs, and a HCA does not allow a consumer to arbitrarily specify a
controlled QKEY."
Thus, block non-privileged users from setting such a QKEY.
Cc: stable@vger.kernel.org
Fixes: bc38a6abdd ("[PATCH] IB uverbs: core implementation")
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Link: https://lore.kernel.org/r/c00c809ddafaaf87d6f6cb827978670989a511b3.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Set static rate to 0 as it should be discovered by path query and
has no meaning for RoCE.
This also avoid of using the rtnl lock and ethtool API, which is
a bottleneck when try to setup many rdma-cm connections at the same
time, especially with multiple processes.
Fixes: 3c86aa70bf ("RDMA/cm: Add RDMA CM support for IBoE devices")
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/f72a4f8b667b803aee9fa794069f61afb5839ce4.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Previously we used the core device associated to the IB device in order
to do the Q-counters query to the FW, but in LAG mode it is possible
that the core device isn't the one that created this VF.
Hence instead of using the core device to query the Q-counters
we use the ESW core device which is guaranteed to be that of the VF.
Fixes: d22467a71e ("RDMA/mlx5: Expand switchdev Q-counters to expose representor statistics")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/778d7d7a24892348d0bdef17d2e5f9e044717e86.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Previously Q-counters data was being allocated over the PF for all of
the available vports, however that isn't necessary.
Since each VF or SF has a Q-counter allocated for itself.
So we only need to allocate two counters data structures, one for the
device counters, and one for all the other vports to expose the
representors, since they only need to read from it in order to
determine mainly counters numbers and names, so they can all share.
This in turn also solves a bug we previously had where we couldn't
switch the device to switchdev mode when there were more than 128 SF/VFs
configured, since that is the maximum amount of Q-counters available for
a single port
Fixes: d22467a71e ("RDMA/mlx5: Expand switchdev Q-counters to expose representor statistics")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/f54671df16e2227a069b229b33b62cd9ee24c475.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
A misbehaved user can create a steering anchor that points to a kernel
flow table and then destroy the anchor without freeing the associated
STC. This creates a problem as the kernel can't destroy the flow
table since there is still a reference to it. As a result, this can
exhaust all available flow table resources, preventing other users from
using the RDMA device.
To prevent this problem, a solution is implemented where a special flow
table with two steering rules is created when a user creates a steering
anchor for the first time. The rules include one that drops all traffic
and another that points to the kernel flow table. If the steering anchor
is destroyed, only the rule pointing to the kernel's flow table is removed.
Any traffic reaching the special flow table after that is dropped.
Since the special flow table is not destroyed when the steering anchor is
destroyed, any issues are prevented from occurring. The remaining resources
are only destroyed when the RDMA device is destroyed, which happens after
all DEVX objects are freed, including the STCs, thus mitigating the issue.
Fixes: 0c6ab0ca9a ("RDMA/mlx5: Expose steering anchor to userspace")
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://lore.kernel.org/r/b4a88a871d651fa4e8f98d552553c1cfe9ba2cd6.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Delay drop data is initiated for PFs that have the capability of
rq_delay_drop and are in roce profile.
However, PFs with RAW ethernet profile do not initiate delay drop data
on function load, causing kernel panic if delay drop struct members are
accessed later on in case a dropless RQ is created.
Thus, stage the delay drop initialization as part of RAW ethernet
PF loading process.
Fixes: b5ca15ad7e ("IB/mlx5: Add proper representors support")
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://lore.kernel.org/r/2e9d386785043d48c38711826eb910315c1de141.1685960567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
We are now in a position where no caller of pin_user_pages() requires the
vmas parameter at all, so eliminate this parameter from the function and
all callers.
This clears the way to removing the vmas parameter from GUP altogether.
Link: https://lkml.kernel.org/r/195a99ae949c9f5cb589d2222b736ced96ec199a.1684350871.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com> [qib]
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com> [drivers/media]
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Janosch Frank <frankja@linux.ibm.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The IBA requires:
o11-5.2.5: If the HCA supports SRQ, for RC and UD service,
the CI shall generate a Last WQE Reached Affiliated Asynchronous
Event on a QP that is in the Error State and is associated with
an SRQ when either:
• a CQE is generated for the last WQE, or
• the QP gets in the Error State and there are no more
WQEs on the RQ.
This patch implements this behavior in flush_recv_queue() which is called
as a result of rxe_qp_error() being called whenever the qp is put into the
error state. The rxe responder executes SRQ WQEs directly from the SRQ so
there are never more WQES on the RQ.
Link: https://lore.kernel.org/r/20230602164229.9277-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In the following:
Call Trace:
<TASK>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xd9/0x150 lib/dump_stack.c:106
assign_lock_key kernel/locking/lockdep.c:982 [inline]
register_lock_class+0xdb6/0x1120 kernel/locking/lockdep.c:1295
__lock_acquire+0x10a/0x5df0 kernel/locking/lockdep.c:4951
lock_acquire kernel/locking/lockdep.c:5691 [inline]
lock_acquire+0x1b1/0x520 kernel/locking/lockdep.c:5656
__raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
_raw_spin_lock_irqsave+0x3d/0x60 kernel/locking/spinlock.c:162
skb_dequeue+0x20/0x180 net/core/skbuff.c:3639
drain_resp_pkts drivers/infiniband/sw/rxe/rxe_comp.c:555 [inline]
rxe_completer+0x250d/0x3cc0 drivers/infiniband/sw/rxe/rxe_comp.c:652
rxe_qp_do_cleanup+0x1be/0x820 drivers/infiniband/sw/rxe/rxe_qp.c:761
execute_in_process_context+0x3b/0x150 kernel/workqueue.c:3473
__rxe_cleanup+0x21e/0x370 drivers/infiniband/sw/rxe/rxe_pool.c:233
rxe_create_qp+0x3f6/0x5f0 drivers/infiniband/sw/rxe/rxe_verbs.c:583
This is a use-before-initialization problem.
It happens because rxe_qp_do_cleanup is called during error unwind before
the struct has been fully initialized.
Move the initialization of the skb earlier.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20230602035408.741534-1-yanjun.zhu@intel.com
Reported-by: syzbot+eba589d8f49c73d356da@syzkaller.appspotmail.com
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In order to conform to other drivers stop using rkey == 0 as an indication
that there are no remote access flags set. Set rkey == lkey by default
for all MRs.
Link: https://lore.kernel.org/r/20230530221334.89432-6-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Introduce supported bit masks for setting the access attributes of MWs,
MRs, and QPs. Check these when attributes are set.
Link: https://lore.kernel.org/r/20230530221334.89432-5-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The subroutine rxe_check_bind_mw() in rxe_mw.c performs checks on the mw
access flags before they are set so they always succeed. This patch
instead checks the access flags passed in the send wqe.
Fixes: 32a577b4c3 ("RDMA/rxe: Add support for bind MW work requests")
Link: https://lore.kernel.org/r/20230530221334.89432-4-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Rename IB_ACCESS_REMOTE to RXE_ACCESS_REMOTE and move to rxe_verbs.h as an
enum instead of a #define. Shouldn't use IB_xxx for rxe symbols.
Link: https://lore.kernel.org/r/20230530221334.89432-2-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Introduce a generic APIs to iterate over all the devices which are part
of the LAG. This API replace mlx5_lag_get_peer_mdev() which retrieve
only a single peer device from the lag.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
The cited patch introduce ib port for the slave device uplink in
case of multiport eswitch. However, this ib port didn't perform
anything when unloaded.
Unload the new ib port properly.
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
After commit 6d758147c7 ("RDMA/bnxt_re: Use auxiliary driver interface")
the active_{speed, width} attributes are reported incorrectly, This is
happening because ib_get_eth_speed() is called only once from
bnxt_re_ib_init() - Fix this issue by calling ib_get_eth_speed() from
bnxt_re_query_port().
Fixes: 6d758147c7 ("RDMA/bnxt_re: Use auxiliary driver interface")
Link: https://lore.kernel.org/r/20230529153525.87254-1-kheib@redhat.com
Signed-off-by: Kamal Heib <kheib@redhat.com>
Acked-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The return value of set_hem has been fixed to ENODEV, which will lead a
diagnostic information missing.
Fixes: 9a4435375c ("IB/hns: Add driver files for hns RoCE driver")
Link: https://lore.kernel.org/r/20230523121641.3132102-3-huangjunxian6@hisilicon.com
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
It is not necessary to check the type of the queue on IO path because
unsupported QP type cannot be created.
Link: https://lore.kernel.org/r/20230523121641.3132102-2-huangjunxian6@hisilicon.com
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The struct mmu_rb_ops function pointers .insert, .invalidate were only
used to increment and decrement struct sdma_mmu_node.refcount.
With the deletion of struct sdma_mmu_node.refcount and the addition of
struct mmu_rb_node.refcount these function pointers are not called and
there are no implementations of them. So it is safe to delete these from
struct mmu_rb_ops.
Link: https://lore.kernel.org/r/168451526508.3702129.8677714753157495310.stgit@awfm-02.cornelisnetworks.com
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Add kref_read() of mmu_rb_node.refcount in hfi1_mmu_rb_template-type
tracepoint output.
Change hfi1_mmu_rb_template tracepoint to take a struct mmu_rb_node* and
record the values it needs from that. This makes the trace_hfi1_mmu*()
calls shorter and easier to read.
Add hfi1_mmu_release_node() tracepoint before all
mmu_rb_node->handler->ops->remove() calls.
Make hfi1_mmu_rb_search() tracepoint its own tracepoint type separate
from hfi1_mmu_rb_template since hfi1_mmu_rb_search() does not take a
struct mmu_rb_node*.
Link: https://lore.kernel.org/r/168451525987.3702129.12824880387615916700.stgit@awfm-02.cornelisnetworks.com
Reviewed-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The hfi1 user SDMA pinned-page cache will leave a stale cache entry when
the cache-entry's virtual address range is invalidated but that cache
entry is in-use by an outstanding SDMA request.
Subsequent user SDMA requests with buffers in or spanning the virtual
address range of the stale cache entry will result in packets constructed
from the wrong memory, the physical pages pointed to by the stale cache
entry.
To fix this, remove mmu_rb_node cache entries from the mmu_rb_handler
cache independent of the cache entry's refcount. Add 'struct kref
refcount' to struct mmu_rb_node and manage mmu_rb_node lifetime with
kref_get() and kref_put().
mmu_rb_node.refcount makes sdma_mmu_node.refcount redundant. Remove
'atomic_t refcount' from struct sdma_mmu_node and change sdma_mmu_node
code to use mmu_rb_node.refcount.
Move the mmu_rb_handler destructor call after a
wait-for-SDMA-request-completion call so mmu_rb_nodes that need
mmu_rb_handler's workqueue to queue themselves up for destruction from an
interrupt context may do so.
Fixes: f48ad614c1 ("IB/hfi1: Move driver out of staging")
Fixes: 00cbce5cbf ("IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests")
Link: https://lore.kernel.org/r/168451393605.3700681.13493776139032178861.stgit@awfm-02.cornelisnetworks.com
Reviewed-by: Dean Luick <dean.luick@cornelisnetworks.com>
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
There is a reference count error in error path code and a potential race
in check_rkey() in rxe_resp.c. When looking up the rkey for a memory
window the reference to the mw from rxe_lookup_mw() is dropped before a
reference is taken on the mr referenced by the mw. If the mr is destroyed
immediately after the call to rxe_put(mw) the mr pointer is unprotected
and may end up pointing at freed memory. The rxe_get(mr) call should take
place before the rxe_put(mw) call.
All errors in check_rkey() call rxe_put(mw) if mw is not NULL but it was
already called after the above. The mw pointer should be set to NULL after
the rxe_put(mw) call to prevent this from happening.
Fixes: cdd0b85675 ("RDMA/rxe: Implement memory access through MWs")
Link: https://lore.kernel.org/r/20230517211509.1819998-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In rxe_net.c a received packet, from udp or loopback, is passed to
rxe_rcv() in rxe_recv.c as a udp packet. I.e. skb->data is pointing at the
udp header. But rxe_rcv() makes length checks to verify the packet is long
enough to hold the roce headers as if it were a roce
packet. I.e. skb->data pointing at the bth header. A runt packet would
appear to have 8 more bytes than it actually does which may lead to
incorrect behavior.
This patch calls skb_pull() to adjust the skb to point at the bth header
before calling rxe_rcv() which fixes this error.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Link: https://lore.kernel.org/r/20230517172242.1806340-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
In current design:
1. PD and clt_path->s.dev are shared among connections.
2. every con[n]'s cleanup phase will call destroy_con_cq_qp()
3. clt_path->s.dev will be always decreased in destroy_con_cq_qp(), and
when clt_path->s.dev become zero, it will destroy PD.
4. when con[1] failed to create, con[1] will not take clt_path->s.dev,
but it try to decreased clt_path->s.dev
So, in case create_cm(con[0]) succeeds but create_cm(con[1]) fails,
destroy_con_cq_qp(con[1]) will be called first which will destroy the PD
while this PD is still taken by con[0].
Here, we refactor the error path of create_cm() and init_conns(), so that
we do the cleanup in the order they are created.
The warning occurs when destroying RXE PD whose reference count is not
zero.
rnbd_client L597: Mapping device /dev/nvme0n1 on session client, (access_mode: rw, nr_poll_queues: 0)
------------[ cut here ]------------
WARNING: CPU: 0 PID: 26407 at drivers/infiniband/sw/rxe/rxe_pool.c:256 __rxe_cleanup+0x13a/0x170 [rdma_rxe]
Modules linked in: rpcrdma rdma_ucm ib_iser rnbd_client libiscsi rtrs_client scsi_transport_iscsi rtrs_core rdma_cm iw_cm ib_cm crc32_generic rdma_rxe udp_tunnel ib_uverbs ib_core kmem device_dax nd_pmem dax_pmem nd_vme crc32c_intel fuse nvme_core nfit libnvdimm dm_multipath scsi_dh_rdac scsi_dh_emc scsi_dh_alua dm_mirror dm_region_hash dm_log dm_mod
CPU: 0 PID: 26407 Comm: rnbd-client.sh Kdump: loaded Not tainted 6.2.0-rc6-roce-flush+ #53
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
RIP: 0010:__rxe_cleanup+0x13a/0x170 [rdma_rxe]
Code: 45 84 e4 0f 84 5a ff ff ff 48 89 ef e8 5f 18 71 f9 84 c0 75 90 be c8 00 00 00 48 89 ef e8 be 89 1f fa 85 c0 0f 85 7b ff ff ff <0f> 0b 41 bc ea ff ff ff e9 71 ff ff ff e8 84 7f 1f fa e9 d0 fe ff
RSP: 0018:ffffb09880b6f5f0 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff99401f15d6a8 RCX: 0000000000000000
RDX: 0000000000000001 RSI: ffffffffbac8234b RDI: 00000000ffffffff
RBP: ffff99401f15d6d0 R08: 0000000000000001 R09: 0000000000000001
R10: 0000000000002d82 R11: 0000000000000000 R12: 0000000000000001
R13: ffff994101eff208 R14: ffffb09880b6f6a0 R15: 00000000fffffe00
FS: 00007fe113904740(0000) GS:ffff99413bc00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007ff6cde656c8 CR3: 000000001f108004 CR4: 00000000001706f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
rxe_dealloc_pd+0x16/0x20 [rdma_rxe]
ib_dealloc_pd_user+0x4b/0x80 [ib_core]
rtrs_ib_dev_put+0x79/0xd0 [rtrs_core]
destroy_con_cq_qp+0x8a/0xa0 [rtrs_client]
init_path+0x1e7/0x9a0 [rtrs_client]
? __pfx_autoremove_wake_function+0x10/0x10
? lock_is_held_type+0xd7/0x130
? rcu_read_lock_sched_held+0x43/0x80
? pcpu_alloc+0x3dd/0x7d0
? rtrs_clt_init_stats+0x18/0x40 [rtrs_client]
rtrs_clt_open+0x24f/0x5a0 [rtrs_client]
? __pfx_rnbd_clt_link_ev+0x10/0x10 [rnbd_client]
rnbd_clt_map_device+0x6a5/0xe10 [rnbd_client]
Fixes: 6a98d71dae ("RDMA/rtrs: client: main functionality")
Link: https://lore.kernel.org/r/1682384563-2-4-git-send-email-lizhijian@fujitsu.com
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Acked-by: Jack Wang <jinpu.wang@ionos.com>
Tested-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The last iu->buf will leak if ib_dma_mapping_error() fails.
Fixes: c0894b3ea6 ("RDMA/rtrs: core: lib functions shared between client and server modules")
Link: https://lore.kernel.org/r/1682384563-2-3-git-send-email-lizhijian@fujitsu.com
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Acked-by: Guoqing Jiang <guoqing.jiang@linux.dev>
Acked-by: Jack Wang <jinpu.wang@ionos.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
rxe_cq_disable() has been removed but not its declaration.
Fixes: 78b26a3353 ("RDMA/rxe: Remove tasklet call from rxe_cq.c")
Link: https://lore.kernel.org/r/4f20ffc5-b2c4-0c11-2883-a835caf01a94@suse.com
Signed-off-by: Nicolas Morey <nmorey@suse.com>
Acked-by: Zhu Yanjun <zyjzyj2000@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Commit df8fc4e934 ("kbuild: Enable -fstrict-flex-arrays=3") triggers a
warning for fortified memset():
In function 'fortify_memset_chk',
inlined from 'irdma_clr_wqes' at drivers/infiniband/hw/irdma/uk.c:103:4:
include/linux/fortify-string.h:493:25: error: call to '__write_overflow_field' declared with attribute warning: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror=attribute-warning]
493 | __write_overflow_field(p_size_field, size);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The problem here isthat the inner array only has four 8-byte elements, so
clearing 4096 bytes overflows that. As this structure is part of an outer
array, change the code to pass a pointer to the irdma_qp_quanta instead,
and change the size argument for readability, matching the comment above
it.
Fixes: 551c46edc7 ("RDMA/irdma: Add user/kernel shared libraries")
Link: https://lore.kernel.org/r/20230523111859.2197825-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
With RX coalescing, one CQE entry can be used to indicate multiple packets
on the receive queue. This saves processing time and PCI bandwidth over
the CQ.
The MANA Ethernet driver also uses the v2 version of the protocol. It
doesn't use RX coalescing and its behavior is not changed.
Link: https://lore.kernel.org/r/1684045095-31228-1-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Long Li <longli@microsoft.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
If the local invalidate fence is indicated in the WR, only the read fence
is currently being set in WQE. Fix this to set both the read and local
fence in the WQE.
Fixes: b48c24c2d7 ("RDMA/irdma: Implement device supported verb APIs")
Link: https://lore.kernel.org/r/20230522155654.1309-4-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
There is a window where the poll cq may use a QP that has been freed.
This can happen if a CQE is polled before irdma_clean_cqes() can clear the
CQE's related to the QP and the destroy QP races to free the QP memory.
then the QP structures are used in irdma_poll_cq. Fix this by moving the
clearing of CQE's before the reference is removed and the QP is destroyed.
Fixes: b48c24c2d7 ("RDMA/irdma: Implement device supported verb APIs")
Link: https://lore.kernel.org/r/20230522155654.1309-3-shiraz.saleem@intel.com
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
do_tcp_sendpages() is now just a small wrapper around tcp_sendmsg_locked(),
so inline it, allowing do_tcp_sendpages() to be removed. This is part of
replacing ->sendpage() with a call to sendmsg() with MSG_SPLICE_PAGES set.
Signed-off-by: David Howells <dhowells@redhat.com>
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Reviewed-by: Tom Talpey <tom@talpey.com>
cc: Jason Gunthorpe <jgg@ziepe.ca>
cc: Leon Romanovsky <leon@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The NULL check inside bnxt_qplib_del_sgid() and bnxt_qplib_add_sgid()
always return false as the "sgid_tbl" inside "rdev->qplib_res" is a static
memory.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684478897-12247-8-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When there is no cleanup to be done, return directly. This will help
eliminating unnecessary local variables and goto labels. This patch fixes
such occurrences in qplib_fp.c file.
Fixes: 37cb11acf1 ("RDMA/bnxt_re: Add SRQ support for Broadcom adapters")
Fixes: 159fb4ceac ("RDMA/bnxt_re: introduce a function to allocate swq")
Link: https://lore.kernel.org/r/1684478897-12247-7-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
During destroy_qp, driver sets the qp handle in the existing CQEs
belonging to the QP being destroyed to NULL. As a result, a poll_cq after
destroy_qp can report unnecessary messages. Remove this noise from system
logs.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684478897-12247-6-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The NULL check inside bnxt_re_update_gid() always return false. If
sgid_tbl->tbl is not allocated, then dev_init would have failed.
Fixes: 5fac5b1b29 ("RDMA/bnxt_re: Add vlan tag for untagged RoCE traffic when PFC is configured")
Link: https://lore.kernel.org/r/1684478897-12247-5-git-send-email-selvin.xavier@broadcom.com
Reviewed-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
bnxt_re currently uses the names "bnxt_qplib_creq" and "bnxt_qplib_nq-0"
while registering IRQs. There is no way to distinguish the IRQs of
different device ports when there are multiple IB devices registered.
This could make the scenarios worse where one want to pin IRQs of a device
port to certain CPUs.
Fixed the code to use unique names which has PCI BDF information while
registering interrupts like: "bnxt_re-nq-0@pci:0000:65:00.0" and
"bnxt_re-creq@pci:0000:65:00.1".
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684478897-12247-4-git-send-email-selvin.xavier@broadcom.com
Reviewed-by: Bhargava Chenna Marreddy <bhargava.marreddy@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
If there is no cleanup needed then just return directly. This cleans up
the code and improve readability.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684478897-12247-3-git-send-email-selvin.xavier@broadcom.com
Reviewed-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
When the ulp hook to start the IRQ fails because the rings are not
available, tasklets are not enabled. In this case when the driver is
unloaded, driver calls CREQ tasklet_kill. This causes an indefinite hang
as the tasklet is not enabled.
Driver shouldn't call tasklet_kill if it is not enabled. So using the
creq->requested and nq->requested flags to identify if both tasklets/irqs
are registered. Checking this flag while scheduling the tasklet from
ISR. Also, added a cleanup for disabling tasklet, in case request_irq
fails during start_irq.
Check for return value for bnxt_qplib_rcfw_start_irq and in case the
bnxt_qplib_rcfw_start_irq fails, return bnxt_re_start_irq without
attempting to start NQ IRQs.
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684478897-12247-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Congestion control needs to be enabled only on the PFs. FW fails the
command if issued on VFs. Avoid sending the command on VFs.
Fixes: f13bcef04b ("RDMA/bnxt_re: Enable congestion control by default")
Link: https://lore.kernel.org/r/1684397461-23082-4-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Selvin Thyparampil Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Inside bnxt_qplib_create_cq(), when the check for NULL DPI fails, driver
returns directly without freeing the memory allocated inside
bnxt_qplib_alloc_init_hwq() routine.
Fixed this by moving the check for NULL DPI before invoking
bnxt_qplib_alloc_init_hwq().
Fixes: 1ac5a40479 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Link: https://lore.kernel.org/r/1684397461-23082-2-git-send-email-selvin.xavier@broadcom.com
Reviewed-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The commit 9b4b7c1f9f ("RDMA/rxe: Add workqueue support for rxe tasks")
removed tasklets and replaced them with a workqueue, but relevant comments
are still remaining in the source code.
Fixes: 9b4b7c1f9f ("RDMA/rxe: Add workqueue support for rxe tasks")
Link: https://lore.kernel.org/r/20230518070027.942715-1-matsuda-daisuke@fujitsu.com
Signed-off-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Reviewed-by: Bob Pearson <rpearsonhpe@gmail.com>
Acked-by: Zhu Yanjun <zyjzyj2000@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Move the initialization of the iw device ops to be under the declaration
of the irdma_iw_dev_ops.
Link: https://lore.kernel.org/r/20230515191142.413633-4-kheib@redhat.com
Signed-off-by: Kamal Heib <kheib@redhat.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The return value from irdma_init_rdma_device() is always 0 - change it to
be void.
Link: https://lore.kernel.org/r/20230515191142.413633-3-kheib@redhat.com
Signed-off-by: Kamal Heib <kheib@redhat.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The return value from irdma_init_iw_device() is always 0 - change it to be
void.
Link: https://lore.kernel.org/r/20230515191142.413633-2-kheib@redhat.com
Signed-off-by: Kamal Heib <kheib@redhat.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Long message loopback slice is used for achieving traffic balance between
QPs. It prevents the problem that QPs with large traffic occupying the
hardware pipeline for a long time and QPs with small traffic cannot be
scheduled.
Currently, its maximum value is set to 16K, which means only after a QP
sends 16K will the second QP be scheduled. This value is too large, which
will lead to unbalanced traffic scheduling, and thus it needs to be
modified.
The setting range of the long message loopback slice is modified to be
from 1024 (the lower limit supported by hardware) to mtu. Actual testing
shows that this value can significantly reduce error in hardware traffic
scheduling.
This solution is compatible with both HIP08 and HIP09. The modified
lp_pktn_ini has a maximum value of 2 (when mtu is 256), so the range
checking code for lp_pktn_ini is no longer necessary and needs to be
deleted.
Fixes: 0e60778efb ("RDMA/hns: Modify the value of MAX_LP_MSG_LEN to meet hardware compatibility")
Link: https://lore.kernel.org/r/20230512092245.344442-4-huangjunxian6@hisilicon.com
Signed-off-by: Yangyang Li <liyangyang20@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
For hns, the specification of an entry like resource (E.g. WQE/CQE/EQE)
depends on BT page size, buf page size and hopnum. For user mode, the buf
page size depends on UMEM. Therefore, the actual specification is
controlled by BT page size and hopnum.
The current BT page size and hopnum are obtained from firmware. This makes
the driver inflexible and introduces unnecessary constraints. Resource
allocation failures occur in many scenarios.
This patch will calculate whether the BT page size set by firmware is
sufficient before allocating BT, and increase the BT page size if it is
insufficient.
Fixes: 1133401412 ("RDMA/hns: Optimize base address table config flow for qp buffer")
Link: https://lore.kernel.org/r/20230512092245.344442-3-huangjunxian6@hisilicon.com
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
On HIP08, the queried timeout attr is different from the timeout attr
configured by the user.
It is found by rdma-core testcase test_rdmacm_async_traffic:
======================================================================
FAIL: test_rdmacm_async_traffic (tests.test_rdmacm.CMTestCase)
----------------------------------------------------------------------
Traceback (most recent call last):
File "./tests/test_rdmacm.py", line 33, in test_rdmacm_async_traffic
self.two_nodes_rdmacm_traffic(CMAsyncConnection, self.rdmacm_traffic,
File "./tests/base.py", line 382, in two_nodes_rdmacm_traffic
raise(res)
AssertionError
Fixes: 926a01dc00 ("RDMA/hns: Add QP operations support for hip08 SoC")
Link: https://lore.kernel.org/r/20230512092245.344442-2-huangjunxian6@hisilicon.com
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace tasklets by work queues for the three main rxe tasklets:
rxe_requester, rxe_completer and rxe_responder.
work queues are a more modern way to process work from an IRQ and provide
more control over how that work is run for future patches.
Link: https://lore.kernel.org/r/20230428171321.5774-1-rpearsonhpe@gmail.com
Signed-off-by: Ian Ziemba <ian.ziemba@hpe.com>
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Reviewed-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Tested-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Device uses 4KB size blocks for user pages indirect list while the
driver creates those blocks with the size of PAGE_SIZE of the kernel. On
kernels with PAGE_SIZE different than 4KB (ARM RHEL), this leads to a
failure on register MR with indirect list because of the miss
communication between driver and device.
Fixes: 40909f664d ("RDMA/efa: Add EFA verbs implementation")
Link: https://lore.kernel.org/r/20230511115103.13876-1-ynachum@amazon.com
Reviewed-by: Firas Jahjah <firasj@amazon.com>
Reviewed-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Driver populates the list of pages used for Memory region wrongly when
page size is more than system page size. This is causing a failure when
some of the applications that creates MR with page size as 2M. Since HW
can support multiple page sizes, pass the correct page size while creating
the MR.
Also, driver need not adjust the number of pages when HW Queues are
created with user memory. It should work with the number of dma blocks
returned by ib_umem_num_dma_blocks. Fix this calculation also.
Fixes: 0c4dcd6028 ("RDMA/bnxt_re: Refactor hardware queue memory allocation")
Fixes: f6919d5638 ("RDMA/bnxt_re: Code refactor while populating user MRs")
Link: https://lore.kernel.org/r/1683484169-9539-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Usual wide collection of unrelated items in drivers:
- Driver bug fixes and treewide cleanups in hfi1, siw, qib, mlx5, rxe,
usnic, usnic, bnxt_re, ocrdma, iser
* Unnecessary NULL checks
* kmap obsolescence
* pci_enable_pcie_error_reporting() obsolescence
* Unused variables and macros
* trace event related warnings
* casting warnings
- Code cleanups for irdm and erdma
- EFA reporting of 128 byte PCIe TLP support
- mlx5 more agressively uses the out of order HW feature
- Big rework of how state machines and tasks work in rxe
- Fix a syzkaller found crash netdev refcount leak in siw
- bnxt_re revises their HW description header
- Congestion control for bnxt_re
- Use mmu_notifiers more safely in hfi1
- mlx5 gets better support for PCIe relaxed ordering inside VMs
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRRRCHOFoQz/8F5bUaFwuHvBreFYQUCZEva5wAKCRCFwuHvBreF
YZFmAQC9T3b/XQ3bRknYciuzbatC98o9xB0FTqmEFYGj+Y2lVAD9EEVe3HKfHfi3
t/GxXYB5r22oxg5bgsblZfEdEdTVCg8=
=akMm
-----END PGP SIGNATURE-----
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma
Pull rdma updates from Jason Gunthorpe:
"Usual wide collection of unrelated items in drivers:
- Driver bug fixes and treewide cleanups in hfi1, siw, qib, mlx5,
rxe, usnic, usnic, bnxt_re, ocrdma, iser:
- remove unnecessary NULL checks
- kmap obsolescence
- pci_enable_pcie_error_reporting() obsolescence
- unused variables and macros
- trace event related warnings
- casting warnings
- Code cleanups for irdm and erdma
- EFA reporting of 128 byte PCIe TLP support
- mlx5 more agressively uses the out of order HW feature
- Big rework of how state machines and tasks work in rxe
- Fix a syzkaller found crash netdev refcount leak in siw
- bnxt_re revises their HW description header
- Congestion control for bnxt_re
- Use mmu_notifiers more safely in hfi1
- mlx5 gets better support for PCIe relaxed ordering inside VMs"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (81 commits)
RDMA/efa: Add rdma write capability to device caps
RDMA/mlx5: Use correct device num_ports when modify DC
RDMA/irdma: Drop spurious WQ_UNBOUND from alloc_ordered_workqueue() call
RDMA/rxe: Fix spinlock recursion deadlock on requester
RDMA/mlx5: Fix flow counter query via DEVX
RDMA/rxe: Protect QP state with qp->state_lock
RDMA/rxe: Move code to check if drained to subroutine
RDMA/rxe: Remove qp->req.state
RDMA/rxe: Remove qp->comp.state
RDMA/rxe: Remove qp->resp.state
RDMA/mlx5: Allow relaxed ordering read in VFs and VMs
net/mlx5: Update relaxed ordering read HCA capabilities
RDMA/mlx5: Check pcie_relaxed_ordering_enabled() in UMR
RDMA/mlx5: Remove pcie_relaxed_ordering_enabled() check for RO write
RDMA: Add ib_virt_dma_to_page()
RDMA/rxe: Fix the error "trying to register non-static key in rxe_cleanup_task"
RDMA/irdma: Slightly optimize irdma_form_ah_cm_frame()
RDMA/rxe: Fix incorrect TASKLET_STATE_SCHED check in rxe_task.c
IB/hfi1: Place struct mmu_rb_handler on cache line start
IB/hfi1: Fix bugs with non-PAGE_SIZE-end multi-iovec user SDMA requests
...
The summary of the changes for this pull requests is:
* Song Liu's new struct module_memory replacement
* Nick Alcock's MODULE_LICENSE() removal for non-modules
* My cleanups and enhancements to reduce the areas where we vmalloc
module memory for duplicates, and the respective debug code which
proves the remaining vmalloc pressure comes from userspace.
Most of the changes have been in linux-next for quite some time except
the minor fixes I made to check if a module was already loaded
prior to allocating the final module memory with vmalloc and the
respective debug code it introduces to help clarify the issue. Although
the functional change is small it is rather safe as it can only *help*
reduce vmalloc space for duplicates and is confirmed to fix a bootup
issue with over 400 CPUs with KASAN enabled. I don't expect stable
kernels to pick up that fix as the cleanups would have also had to have
been picked up. Folks on larger CPU systems with modules will want to
just upgrade if vmalloc space has been an issue on bootup.
Given the size of this request, here's some more elaborate details
on this pull request.
The functional change change in this pull request is the very first
patch from Song Liu which replaces the struct module_layout with a new
struct module memory. The old data structure tried to put together all
types of supported module memory types in one data structure, the new
one abstracts the differences in memory types in a module to allow each
one to provide their own set of details. This paves the way in the
future so we can deal with them in a cleaner way. If you look at changes
they also provide a nice cleanup of how we handle these different memory
areas in a module. This change has been in linux-next since before the
merge window opened for v6.3 so to provide more than a full kernel cycle
of testing. It's a good thing as quite a bit of fixes have been found
for it.
Jason Baron then made dynamic debug a first class citizen module user by
using module notifier callbacks to allocate / remove module specific
dynamic debug information.
Nick Alcock has done quite a bit of work cross-tree to remove module
license tags from things which cannot possibly be module at my request
so to:
a) help him with his longer term tooling goals which require a
deterministic evaluation if a piece a symbol code could ever be
part of a module or not. But quite recently it is has been made
clear that tooling is not the only one that would benefit.
Disambiguating symbols also helps efforts such as live patching,
kprobes and BPF, but for other reasons and R&D on this area
is active with no clear solution in sight.
b) help us inch closer to the now generally accepted long term goal
of automating all the MODULE_LICENSE() tags from SPDX license tags
In so far as a) is concerned, although module license tags are a no-op
for non-modules, tools which would want create a mapping of possible
modules can only rely on the module license tag after the commit
8b41fc4454 ("kbuild: create modules.builtin without Makefile.modbuiltin
or tristate.conf"). Nick has been working on this *for years* and
AFAICT I was the only one to suggest two alternatives to this approach
for tooling. The complexity in one of my suggested approaches lies in
that we'd need a possible-obj-m and a could-be-module which would check
if the object being built is part of any kconfig build which could ever
lead to it being part of a module, and if so define a new define
-DPOSSIBLE_MODULE [0]. A more obvious yet theoretical approach I've
suggested would be to have a tristate in kconfig imply the same new
-DPOSSIBLE_MODULE as well but that means getting kconfig symbol names
mapping to modules always, and I don't think that's the case today. I am
not aware of Nick or anyone exploring either of these options. Quite
recently Josh Poimboeuf has pointed out that live patching, kprobes and
BPF would benefit from resolving some part of the disambiguation as
well but for other reasons. The function granularity KASLR (fgkaslr)
patches were mentioned but Joe Lawrence has clarified this effort has
been dropped with no clear solution in sight [1].
In the meantime removing module license tags from code which could never
be modules is welcomed for both objectives mentioned above. Some
developers have also welcomed these changes as it has helped clarify
when a module was never possible and they forgot to clean this up,
and so you'll see quite a bit of Nick's patches in other pull
requests for this merge window. I just picked up the stragglers after
rc3. LWN has good coverage on the motivation behind this work [2] and
the typical cross-tree issues he ran into along the way. The only
concrete blocker issue he ran into was that we should not remove the
MODULE_LICENSE() tags from files which have no SPDX tags yet, even if
they can never be modules. Nick ended up giving up on his efforts due
to having to do this vetting and backlash he ran into from folks who
really did *not understand* the core of the issue nor were providing
any alternative / guidance. I've gone through his changes and dropped
the patches which dropped the module license tags where an SPDX
license tag was missing, it only consisted of 11 drivers. To see
if a pull request deals with a file which lacks SPDX tags you
can just use:
./scripts/spdxcheck.py -f \
$(git diff --name-only commid-id | xargs echo)
You'll see a core module file in this pull request for the above,
but that's not related to his changes. WE just need to add the SPDX
license tag for the kernel/module/kmod.c file in the future but
it demonstrates the effectiveness of the script.
Most of Nick's changes were spread out through different trees,
and I just picked up the slack after rc3 for the last kernel was out.
Those changes have been in linux-next for over two weeks.
The cleanups, debug code I added and final fix I added for modules
were motivated by David Hildenbrand's report of boot failing on
a systems with over 400 CPUs when KASAN was enabled due to running
out of virtual memory space. Although the functional change only
consists of 3 lines in the patch "module: avoid allocation if module is
already present and ready", proving that this was the best we can
do on the modules side took quite a bit of effort and new debug code.
The initial cleanups I did on the modules side of things has been
in linux-next since around rc3 of the last kernel, the actual final
fix for and debug code however have only been in linux-next for about a
week or so but I think it is worth getting that code in for this merge
window as it does help fix / prove / evaluate the issues reported
with larger number of CPUs. Userspace is not yet fixed as it is taking
a bit of time for folks to understand the crux of the issue and find a
proper resolution. Worst come to worst, I have a kludge-of-concept [3]
of how to make kernel_read*() calls for modules unique / converge them,
but I'm currently inclined to just see if userspace can fix this
instead.
[0] https://lore.kernel.org/all/Y/kXDqW+7d71C4wz@bombadil.infradead.org/
[1] https://lkml.kernel.org/r/025f2151-ce7c-5630-9b90-98742c97ac65@redhat.com
[2] https://lwn.net/Articles/927569/
[3] https://lkml.kernel.org/r/20230414052840.1994456-3-mcgrof@kernel.org
-----BEGIN PGP SIGNATURE-----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=56WK
-----END PGP SIGNATURE-----
Merge tag 'modules-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux
Pull module updates from Luis Chamberlain:
"The summary of the changes for this pull requests is:
- Song Liu's new struct module_memory replacement
- Nick Alcock's MODULE_LICENSE() removal for non-modules
- My cleanups and enhancements to reduce the areas where we vmalloc
module memory for duplicates, and the respective debug code which
proves the remaining vmalloc pressure comes from userspace.
Most of the changes have been in linux-next for quite some time except
the minor fixes I made to check if a module was already loaded prior
to allocating the final module memory with vmalloc and the respective
debug code it introduces to help clarify the issue. Although the
functional change is small it is rather safe as it can only *help*
reduce vmalloc space for duplicates and is confirmed to fix a bootup
issue with over 400 CPUs with KASAN enabled. I don't expect stable
kernels to pick up that fix as the cleanups would have also had to
have been picked up. Folks on larger CPU systems with modules will
want to just upgrade if vmalloc space has been an issue on bootup.
Given the size of this request, here's some more elaborate details:
The functional change change in this pull request is the very first
patch from Song Liu which replaces the 'struct module_layout' with a
new 'struct module_memory'. The old data structure tried to put
together all types of supported module memory types in one data
structure, the new one abstracts the differences in memory types in a
module to allow each one to provide their own set of details. This
paves the way in the future so we can deal with them in a cleaner way.
If you look at changes they also provide a nice cleanup of how we
handle these different memory areas in a module. This change has been
in linux-next since before the merge window opened for v6.3 so to
provide more than a full kernel cycle of testing. It's a good thing as
quite a bit of fixes have been found for it.
Jason Baron then made dynamic debug a first class citizen module user
by using module notifier callbacks to allocate / remove module
specific dynamic debug information.
Nick Alcock has done quite a bit of work cross-tree to remove module
license tags from things which cannot possibly be module at my request
so to:
a) help him with his longer term tooling goals which require a
deterministic evaluation if a piece a symbol code could ever be
part of a module or not. But quite recently it is has been made
clear that tooling is not the only one that would benefit.
Disambiguating symbols also helps efforts such as live patching,
kprobes and BPF, but for other reasons and R&D on this area is
active with no clear solution in sight.
b) help us inch closer to the now generally accepted long term goal
of automating all the MODULE_LICENSE() tags from SPDX license tags
In so far as a) is concerned, although module license tags are a no-op
for non-modules, tools which would want create a mapping of possible
modules can only rely on the module license tag after the commit
8b41fc4454 ("kbuild: create modules.builtin without
Makefile.modbuiltin or tristate.conf").
Nick has been working on this *for years* and AFAICT I was the only
one to suggest two alternatives to this approach for tooling. The
complexity in one of my suggested approaches lies in that we'd need a
possible-obj-m and a could-be-module which would check if the object
being built is part of any kconfig build which could ever lead to it
being part of a module, and if so define a new define
-DPOSSIBLE_MODULE [0].
A more obvious yet theoretical approach I've suggested would be to
have a tristate in kconfig imply the same new -DPOSSIBLE_MODULE as
well but that means getting kconfig symbol names mapping to modules
always, and I don't think that's the case today. I am not aware of
Nick or anyone exploring either of these options. Quite recently Josh
Poimboeuf has pointed out that live patching, kprobes and BPF would
benefit from resolving some part of the disambiguation as well but for
other reasons. The function granularity KASLR (fgkaslr) patches were
mentioned but Joe Lawrence has clarified this effort has been dropped
with no clear solution in sight [1].
In the meantime removing module license tags from code which could
never be modules is welcomed for both objectives mentioned above. Some
developers have also welcomed these changes as it has helped clarify
when a module was never possible and they forgot to clean this up, and
so you'll see quite a bit of Nick's patches in other pull requests for
this merge window. I just picked up the stragglers after rc3. LWN has
good coverage on the motivation behind this work [2] and the typical
cross-tree issues he ran into along the way. The only concrete blocker
issue he ran into was that we should not remove the MODULE_LICENSE()
tags from files which have no SPDX tags yet, even if they can never be
modules. Nick ended up giving up on his efforts due to having to do
this vetting and backlash he ran into from folks who really did *not
understand* the core of the issue nor were providing any alternative /
guidance. I've gone through his changes and dropped the patches which
dropped the module license tags where an SPDX license tag was missing,
it only consisted of 11 drivers. To see if a pull request deals with a
file which lacks SPDX tags you can just use:
./scripts/spdxcheck.py -f \
$(git diff --name-only commid-id | xargs echo)
You'll see a core module file in this pull request for the above, but
that's not related to his changes. WE just need to add the SPDX
license tag for the kernel/module/kmod.c file in the future but it
demonstrates the effectiveness of the script.
Most of Nick's changes were spread out through different trees, and I
just picked up the slack after rc3 for the last kernel was out. Those
changes have been in linux-next for over two weeks.
The cleanups, debug code I added and final fix I added for modules
were motivated by David Hildenbrand's report of boot failing on a
systems with over 400 CPUs when KASAN was enabled due to running out
of virtual memory space. Although the functional change only consists
of 3 lines in the patch "module: avoid allocation if module is already
present and ready", proving that this was the best we can do on the
modules side took quite a bit of effort and new debug code.
The initial cleanups I did on the modules side of things has been in
linux-next since around rc3 of the last kernel, the actual final fix
for and debug code however have only been in linux-next for about a
week or so but I think it is worth getting that code in for this merge
window as it does help fix / prove / evaluate the issues reported with
larger number of CPUs. Userspace is not yet fixed as it is taking a
bit of time for folks to understand the crux of the issue and find a
proper resolution. Worst come to worst, I have a kludge-of-concept [3]
of how to make kernel_read*() calls for modules unique / converge
them, but I'm currently inclined to just see if userspace can fix this
instead"
Link: https://lore.kernel.org/all/Y/kXDqW+7d71C4wz@bombadil.infradead.org/ [0]
Link: https://lkml.kernel.org/r/025f2151-ce7c-5630-9b90-98742c97ac65@redhat.com [1]
Link: https://lwn.net/Articles/927569/ [2]
Link: https://lkml.kernel.org/r/20230414052840.1994456-3-mcgrof@kernel.org [3]
* tag 'modules-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: (121 commits)
module: add debugging auto-load duplicate module support
module: stats: fix invalid_mod_bytes typo
module: remove use of uninitialized variable len
module: fix building stats for 32-bit targets
module: stats: include uapi/linux/module.h
module: avoid allocation if module is already present and ready
module: add debug stats to help identify memory pressure
module: extract patient module check into helper
modules/kmod: replace implementation with a semaphore
Change DEFINE_SEMAPHORE() to take a number argument
module: fix kmemleak annotations for non init ELF sections
module: Ignore L0 and rename is_arm_mapping_symbol()
module: Move is_arm_mapping_symbol() to module_symbol.h
module: Sync code of is_arm_mapping_symbol()
scripts/gdb: use mem instead of core_layout to get the module address
interconnect: remove module-related code
interconnect: remove MODULE_LICENSE in non-modules
zswap: remove MODULE_LICENSE in non-modules
zpool: remove MODULE_LICENSE in non-modules
x86/mm/dump_pagetables: remove MODULE_LICENSE in non-modules
...
Here is the large set of driver core changes for 6.4-rc1.
Once again, a busy development cycle, with lots of changes happening in
the driver core in the quest to be able to move "struct bus" and "struct
class" into read-only memory, a task now complete with these changes.
This will make the future rust interactions with the driver core more
"provably correct" as well as providing more obvious lifetime rules for
all busses and classes in the kernel.
The changes required for this did touch many individual classes and
busses as many callbacks were changed to take const * parameters
instead. All of these changes have been submitted to the various
subsystem maintainers, giving them plenty of time to review, and most of
them actually did so.
Other than those changes, included in here are a small set of other
things:
- kobject logging improvements
- cacheinfo improvements and updates
- obligatory fw_devlink updates and fixes
- documentation updates
- device property cleanups and const * changes
- firwmare loader dependency fixes.
All of these have been in linux-next for a while with no reported
problems.
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-----BEGIN PGP SIGNATURE-----
iG0EABECAC0WIQT0tgzFv3jCIUoxPcsxR9QN2y37KQUCZEp7Sw8cZ3JlZ0Brcm9h
aC5jb20ACgkQMUfUDdst+ykitQCfamUHpxGcKOAGuLXMotXNakTEsxgAoIquENm5
LEGadNS38k5fs+73UaxV
=7K4B
-----END PGP SIGNATURE-----
Merge tag 'driver-core-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull driver core updates from Greg KH:
"Here is the large set of driver core changes for 6.4-rc1.
Once again, a busy development cycle, with lots of changes happening
in the driver core in the quest to be able to move "struct bus" and
"struct class" into read-only memory, a task now complete with these
changes.
This will make the future rust interactions with the driver core more
"provably correct" as well as providing more obvious lifetime rules
for all busses and classes in the kernel.
The changes required for this did touch many individual classes and
busses as many callbacks were changed to take const * parameters
instead. All of these changes have been submitted to the various
subsystem maintainers, giving them plenty of time to review, and most
of them actually did so.
Other than those changes, included in here are a small set of other
things:
- kobject logging improvements
- cacheinfo improvements and updates
- obligatory fw_devlink updates and fixes
- documentation updates
- device property cleanups and const * changes
- firwmare loader dependency fixes.
All of these have been in linux-next for a while with no reported
problems"
* tag 'driver-core-6.4-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (120 commits)
device property: make device_property functions take const device *
driver core: update comments in device_rename()
driver core: Don't require dynamic_debug for initcall_debug probe timing
firmware_loader: rework crypto dependencies
firmware_loader: Strip off \n from customized path
zram: fix up permission for the hot_add sysfs file
cacheinfo: Add use_arch[|_cache]_info field/function
arch_topology: Remove early cacheinfo error message if -ENOENT
cacheinfo: Check cache properties are present in DT
cacheinfo: Check sib_leaf in cache_leaves_are_shared()
cacheinfo: Allow early level detection when DT/ACPI info is missing/broken
cacheinfo: Add arm64 early level initializer implementation
cacheinfo: Add arch specific early level initializer
tty: make tty_class a static const structure
driver core: class: remove struct class_interface * from callbacks
driver core: class: mark the struct class in struct class_interface constant
driver core: class: make class_register() take a const *
driver core: class: mark class_release() as taking a const *
driver core: remove incorrect comment for device_create*
MIPS: vpe-cmp: remove module owner pointer from struct class usage.
...
Updates to the usual drivers (megaraid_sas, scsi_debug, lpfc, target,
mpi3mr, hisi_sas, arcmsr). The major core change is the
constification of the host templates (which touches everything) along
with other minor fixups and clean ups.
Signed-off-by: James E.J. Bottomley <jejb@linux.ibm.com>
-----BEGIN PGP SIGNATURE-----
iJwEABMIAEQWIQTnYEDbdso9F2cI+arnQslM7pishQUCZEmJACYcamFtZXMuYm90
dG9tbGV5QGhhbnNlbnBhcnRuZXJzaGlwLmNvbQAKCRDnQslM7pishU4FAP0WYhFC
rkbY203/+ErUuwvOKum0VwJKUowCaUD0MBwScAD+Ok/NWobmjdXUBbPUbvVkr+hE
8B/xs9hodX+1fVJcVG0=
=fS/j
-----END PGP SIGNATURE-----
Merge tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi
Pull SCSI updates from James Bottomley:
"Updates to the usual drivers (megaraid_sas, scsi_debug, lpfc, target,
mpi3mr, hisi_sas, arcmsr).
The major core change is the constification of the host templates
(which touches everything) along with other minor fixups and clean
ups"
* tag 'scsi-misc' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: (207 commits)
scsi: ufs: mcq: Use pointer arithmetic in ufshcd_send_command()
scsi: ufs: mcq: Annotate ufshcd_inc_sq_tail() appropriately
scsi: cxlflash: s/semahpore/semaphore/
scsi: lpfc: Silence an incorrect device output
scsi: mpi3mr: Use IRQ save variants of spinlock to protect chain frame allocation
scsi: scsi_debug: Fix missing error code in scsi_debug_init()
scsi: hisi_sas: Work around build failure in suspend function
scsi: lpfc: Fix ioremap issues in lpfc_sli4_pci_mem_setup()
scsi: mpt3sas: Fix an issue when driver is being removed
scsi: mpt3sas: Remove HBA BIOS version in the kernel log
scsi: target: core: Fix invalid memory access
scsi: scsi_debug: Drop sdebug_queue
scsi: scsi_debug: Only allow sdebug_max_queue be modified when no shosts
scsi: scsi_debug: Use scsi_host_busy() in delay_store() and ndelay_store()
scsi: scsi_debug: Use blk_mq_tagset_busy_iter() in stop_all_queued()
scsi: scsi_debug: Use blk_mq_tagset_busy_iter() in sdebug_blk_mq_poll()
scsi: scsi_debug: Dynamically allocate sdebug_queued_cmd
scsi: scsi_debug: Use scsi_block_requests() to block queues
scsi: scsi_debug: Protect block_unblock_all_queues() with mutex
scsi: scsi_debug: Change shost list lock to a mutex
...
Merge my x86 user copy updates branch.
This cleans up a lot of our x86 memory copy code, particularly for user
accesses. I've been pushing for microarchitectural support for good
memory copying and clearing for a long while, and it's been visible in
how the kernel has aggressively used 'rep movs' and 'rep stos' whenever
possible.
And that micro-architectural support has been improving over the years,
to the point where on modern CPU's the best option for a memory copy
that would become a function call (as opposed to being something that
can just be turned into individual 'mov' instructions) is now to inline
the string instruction sequence instead.
However, that only makes sense when we have the modern markers for this:
the x86 FSRM and FSRS capabilities ("Fast Short REP MOVS/STOS").
So this cleans up a lot of our historical code, gets rid of the legacy
marker use ("REP_GOOD" and "ERMS") from the memcpy/memset cases, and
replaces it with that modern reality. Note that REP_GOOD and ERMS end
up still being used by the known large cases (ie page copyin gand
clearing).
The reason much of this ends up being about user memory accesses is that
the normal in-kernel cases are done by the compiler (__builtin_memcpy()
and __builtin_memset()) and getting to the point where we can use our
instruction rewriting to inline those to be string instructions will
need some compiler support.
In contrast, the user accessor functions are all entirely controlled by
the kernel code, so we can change those arbitrarily.
Thanks to Borislav Petkov for feedback on the series, and Jens testing
some of this on micro-architectures I didn't personally have access to.
* x86-rep-insns:
x86: rewrite '__copy_user_nocache' function
x86: remove 'zerorest' argument from __copy_user_nocache()
x86: set FSRS automatically on AMD CPUs that have FSRM
x86: improve on the non-rep 'copy_user' function
x86: improve on the non-rep 'clear_user' function
x86: inline the 'rep movs' in user copies for the FSRM case
x86: move stac/clac from user copy routines into callers
x86: don't use REP_GOOD or ERMS for user memory clearing
x86: don't use REP_GOOD or ERMS for user memory copies
x86: don't use REP_GOOD or ERMS for small memory clearing
x86: don't use REP_GOOD or ERMS for small memory copies
-----BEGIN PGP SIGNATURE-----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=EaE9
-----END PGP SIGNATURE-----
Merge tag 'iter-ubuf.2-2023-04-21' of git://git.kernel.dk/linux
Pull ITER_UBUF updates from Jens Axboe:
"This turns singe vector imports into ITER_UBUF, rather than
ITER_IOVEC.
The former is more trivial to iterate and advance, and hence a bit
more efficient. From some very unscientific testing, ~60% of all iovec
imports are single vector"
* tag 'iter-ubuf.2-2023-04-21' of git://git.kernel.dk/linux:
iov_iter: Mark copy_compat_iovec_from_user() noinline
iov_iter: import single vector iovecs as ITER_UBUF
iov_iter: convert import_single_range() to ITER_UBUF
iov_iter: overlay struct iovec and ubuf/len
iov_iter: set nr_segs = 1 for ITER_UBUF
iov_iter: remove iov_iter_iovec()
iov_iter: add iter_iov_addr() and iter_iov_len() helpers
ALSA: pcm: check for user backed iterator, not specific iterator type
IB/qib: check for user backed iterator, not specific iterator type
IB/hfi1: check for user backed iterator, not specific iterator type
iov_iter: add iter_iovec() helper
block: ensure bio_alloc_map_data() deals with ITER_UBUF correctly
Add rdma write capability that is propagated from the device to rdma-core.
Enable MR creation with remote write permissions according to this device
capability.
Link: https://lore.kernel.org/r/20230404154313.35194-1-ynachum@amazon.com
Reviewed-by: Firas Jahjah <firasj@amazon.com>
Reviewed-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Just like other QP types, when modify DC, the port_num should be compared
with dev->num_ports, instead of HCA_CAP.num_ports. Otherwise Multi-port
vHCA on DC may not work.
Fixes: 776a3906b6 ("IB/mlx5: Add support for DC target QP")
Link: https://lore.kernel.org/r/20230420013906.1244185-1-markzhang@nvidia.com
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Workqueue is in the process of cleaning up the distinction between unbound
workqueues w/ @nr_active==1 and ordered workqueues. Explicit WQ_UNBOUND
isn't needed for alloc_ordered_workqueue() and will trigger a warning in
the future. Let's remove it. This doesn't cause any functional changes.
Link: https://lore.kernel.org/r/ZEGW-IcFReR1juVM@slm.duckdns.org
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Every caller passes in zero, meaning they don't want any partial copy to
zero the remainder of the destination buffer.
Which is just as well, because the implementation of that function
didn't actually even look at that argument, and wasn't even aware it
existed, although some misleading comments did mention it still.
The 'zerorest' thing is a historical artifact of how "copy_from_user()"
worked, in that it would zero the rest of the kernel buffer that it
copied into.
That zeroing still exists, but it's long since been moved to generic
code, and the raw architecture-specific code doesn't do it. See
_copy_from_user() in lib/usercopy.c for this all.
However, while __copy_user_nocache() shares some history and superficial
other similarities with copy_from_user(), it is in many ways also very
different.
In particular, while the code makes it *look* similar to the generic
user copy functions that can copy both to and from user space, and take
faults on both reads and writes as a result, __copy_user_nocache() does
no such thing at all.
__copy_user_nocache() always copies to kernel space, and will never take
a page fault on the destination. What *can* happen, though, is that the
non-temporal stores take a machine check because one of the use cases is
for writing to stable memory, and any memory errors would then take
synchronous faults.
So __copy_user_nocache() does look a lot like copy_from_user(), but has
faulting behavior that is more akin to our old copy_in_user() (which no
longer exists, but copied from user space to user space and could fault
on both source and destination).
And it very much does not have the "zero the end of the destination
buffer", since a problem with the destination buffer is very possibly
the very source of the partial copy.
So this whole thing was just a confusing historical artifact from having
shared some code with a completely different function with completely
different use cases.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit cited in "fixes" tag added bulk support for flow counters but it
didn't account that's also possible to query a counter using a non-base id
if the counter was allocated as bulk.
When a user performs a query, validate the flow counter id given in the
mailbox is inside the valid range taking bulk value into account.
Fixes: 208d70f562 ("IB/mlx5: Support flow counters offset for bulk counters")
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://lore.kernel.org/r/79d7fbe291690128e44672418934256254d93115.1681377114.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Currently the rxe driver makes little effort to make the changes to qp
state (which includes qp->attr.qp_state, qp->attr.sq_draining and
qp->valid) atomic between different client threads and IO threads. In
particular a common template is for an RDMA application to call
ib_modify_qp() to move a qp to ERR state and then wait until all the
packet and work queues have drained before calling ib_destroy_qp(). None
of these state changes are protected by locks to assure that the changes
are executed atomically and that memory barriers are included. This has
been observed to lead to incorrect behavior around qp cleanup.
This patch continues the work of the previous patches in this series and
adds locking code around qp state changes and lookups.
Link: https://lore.kernel.org/r/20230405042611.6467-5-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Move two blocks of code in rxe_comp.c and rxe_req.c to subroutines that
check if draining is complete in the SQD state and, if so, generate a
SQ_DRAINED event.
Link: https://lore.kernel.org/r/20230405042611.6467-4-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The rxe driver has four different QP state variables,
qp->attr.qp_state,
qp->req.state,
qp->comp.state, and
qp->resp.state.
All of these basically carry the same information.
This patch replaces uses of qp->req.state by qp->attr.qp_state and enum
rxe_qp_state. This is the third of three patches which will remove all
but the qp->attr.qp_state variable. This will bring the driver closer to
the IBA description.
Link: https://lore.kernel.org/r/20230405042611.6467-3-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The rxe driver has four different QP state variables,
qp->attr.qp_state,
qp->req.state,
qp->comp.state, and
qp->resp.state.
All of these basically carry the same information.
This patch replaces uses of qp->comp.state by qp->attr.qp_state. This is
the second of three patches which will remove all but the
qp->attr.qp_state variable. This will bring the driver closer to the IBA
description.
Link: https://lore.kernel.org/r/20230405042611.6467-2-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The rxe driver has four different QP state variables,
qp->attr.qp_state,
qp->req.state,
qp->comp.state, and
qp->resp.state.
All of these basically carry the same information.
This patch replaces uses of qp->resp.state by qp->attr.qp_state. This is
the first of three patches which will remove all but the qp->attr.qp_state
variable. This will bring the driver closer to the IBA description.
Link: https://lore.kernel.org/r/20230405042611.6467-1-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
According to PCIe spec, Enable Relaxed Ordering value in the VF's PCI
config space is wired to 0 and PF relaxed ordering (RO) setting should
be applied to the VF. In QEMU (and maybe others), when assigning VFs,
the RO bit in PCI config space is not emulated properly and is always
set to 0.
Therefore, pcie_relaxed_ordering_enabled() always returns 0 for VFs and
VMs and thus MKeys can't be created with RO read even if the PF supports
it.
pcie_relaxed_ordering_enabled() check was added to avoid a syndrome when
creating a MKey with relaxed ordering (RO) enabled when the driver's
relaxed_ordering_read_pci_enabled HCA capability is out of sync with FW.
With the new relaxed_ordering_read capability this can't happen, as it's
set regardless of RO value in PCI config space and thus can't change
during runtime.
Hence, to allow RO read in VFs and VMs, use the new HCA capability
relaxed_ordering_read without checking pcie_relaxed_ordering_enabled().
The old capability checks are kept for backward compatibility with older
FWs.
Allowing RO in VFs and VMs is valuable since it can greatly improve
performance on some setups. For example, testing throughput of a VF on
an AMD EPYC 7763 and ConnectX-6 Dx setup showed roughly 60% performance
improvement.
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Link: https://lore.kernel.org/r/e7048640d66c341a8fa0465e099926e7989184bc.1681131553.git.leon@kernel.org
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Rename existing HCA capability relaxed_ordering_read to
relaxed_ordering_read_pci_enabled. This is in accordance with recent PRM
change to better describe the capability, as it's set only if both the
device supports relaxed ordering (RO) read and RO is enabled in PCI
config space.
In addition, add new HCA capability relaxed_ordering_read which is set
if the device supports RO read, regardless of RO in PCI config space.
This will be used in the following patch to allow RO in VFs and VMs.
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Link: https://lore.kernel.org/r/caa0002fd8135086357dfcc368e2f5cc73b08480.1681131553.git.leon@kernel.org
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
relaxed_ordering_read HCA capability is set if both the device supports
relaxed ordering (RO) read and RO is set in PCI config space.
RO in PCI config space can change during runtime. This will change the
value of relaxed_ordering_read HCA capability in FW, but the driver will
not see it since it queries the capabilities only once.
This can lead to the following scenario:
1. RO in PCI config space is enabled.
2. User creates MKey without RO.
3. RO in PCI config space is disabled.
As a result, relaxed_ordering_read HCA capability is turned off in FW
but remains on in driver copy of the capabilities.
4. User requests to reconfig the MKey with RO via UMR.
5. Driver will try to reconfig the MKey with RO read although it
shouldn't (as relaxed_ordering_read HCA capability is really off).
To fix this, check pcie_relaxed_ordering_enabled() before setting RO
read in UMR.
Fixes: 896ec97353 ("RDMA/mlx5: Set mkey relaxed ordering by UMR with ConnectX-7")
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Link: https://lore.kernel.org/r/8d39eb8317e7bed1a354311a20ae707788fd94ed.1681131553.git.leon@kernel.org
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
pcie_relaxed_ordering_enabled() check was added to avoid a syndrome when
creating a MKey with relaxed ordering (RO) enabled when the driver's
relaxed_ordering_{read,write} HCA capabilities are out of sync with FW.
While this can happen with relaxed_ordering_read, it can't happen with
relaxed_ordering_write as it's set if the device supports RO write,
regardless of RO in PCI config space, and thus can't change during
runtime.
Therefore, drop the pcie_relaxed_ordering_enabled() check for
relaxed_ordering_write while keeping it for relaxed_ordering_read.
Doing so will also allow the usage of RO write in VFs and VMs (where RO
in PCI config space is not reported/emulated properly).
Signed-off-by: Avihai Horon <avihaih@nvidia.com>
Reviewed-by: Shay Drory <shayd@nvidia.com>
Link: https://lore.kernel.org/r/7e8f55e31572c1702d69cae015a395d3a824a38a.1681131553.git.leon@kernel.org
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Make it clearer what is going on by adding a function to go back from the
"virtual" dma_addr to a kva and another to a struct page. This is used in the
ib_uses_virt_dma() style drivers (siw, rxe, hfi, qib).
Call them instead of a naked casting and virt_to_page() when working with dma_addr
values encoded by the various ib_map functions.
This also fixes the virt_to_page() casting problem Linus Walleij has been
chasing.
Cc: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/0-v2-05ea785520ed+10-ib_virt_page_jgg@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
There is no need to zero 'pktsize' bytes of 'buf', only the header needs
to be cleared, to be safe.
All the other bytes are already written with some memcpy() at the end of
the function.
Doing so also gives the opportunity to the compiler to avoid the memset()
call. It can be inlined now that the length is known as compile time.
Link: https://lore.kernel.org/r/098e3c397be0436f1867899245ecfe656c472110.1675369386.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Place struct mmu_rb_handler on cache line start like so:
struct mmu_rb_handler *h;
void *free_ptr;
int ret;
free_ptr = kzalloc(sizeof(*h) + cache_line_size() - 1, GFP_KERNEL);
if (!free_ptr)
return -ENOMEM;
h = PTR_ALIGN(free_ptr, cache_line_size());
Additionally, move struct mmu_rb_handler fields "root" and "ops_args" to
start after the next cacheline using the "____cacheline_aligned_in_smp"
annotation.
Allocating an additional cache_line_size() - 1 bytes to place
struct mmu_rb_handler on a cache line start does increase memory
consumption.
However, few struct mmu_rb_handler are created when hfi1 is in use.
As mmu_rb_handler->root and mmu_rb_handler->ops_args are accessed
frequently, the advantage of having them both within a cache line is
expected to outweigh the disadvantage of the additional memory
consumption per struct mmu_rb_handler.
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Patrick Kelsey <pat.kelsey@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/168088636963.3027109.16959757980497822530.stgit@252.162.96.66.static.eigbox.net
Signed-off-by: Leon Romanovsky <leon@kernel.org>
hfi1 user SDMA request processing has two bugs that can cause data
corruption for user SDMA requests that have multiple payload iovecs
where an iovec other than the tail iovec does not run up to the page
boundary for the buffer pointed to by that iovec.a
Here are the specific bugs:
1. user_sdma_txadd() does not use struct user_sdma_iovec->iov.iov_len.
Rather, user_sdma_txadd() will add up to PAGE_SIZE bytes from iovec
to the packet, even if some of those bytes are past
iovec->iov.iov_len and are thus not intended to be in the packet.
2. user_sdma_txadd() and user_sdma_send_pkts() fail to advance to the
next iovec in user_sdma_request->iovs when the current iovec
is not PAGE_SIZE and does not contain enough data to complete the
packet. The transmitted packet will contain the wrong data from the
iovec pages.
This has not been an issue with SDMA packets from hfi1 Verbs or PSM2
because they only produce iovecs that end short of PAGE_SIZE as the tail
iovec of an SDMA request.
Fixing these bugs exposes other bugs with the SDMA pin cache
(struct mmu_rb_handler) that get in way of supporting user SDMA requests
with multiple payload iovecs whose buffers do not end at PAGE_SIZE. So
this commit fixes those issues as well.
Here are the mmu_rb_handler bugs that non-PAGE_SIZE-end multi-iovec
payload user SDMA requests can hit:
1. Overlapping memory ranges in mmu_rb_handler will result in duplicate
pinnings.
2. When extending an existing mmu_rb_handler entry (struct mmu_rb_node),
the mmu_rb code (1) removes the existing entry under a lock, (2)
releases that lock, pins the new pages, (3) then reacquires the lock
to insert the extended mmu_rb_node.
If someone else comes in and inserts an overlapping entry between (2)
and (3), insert in (3) will fail.
The failure path code in this case unpins _all_ pages in either the
original mmu_rb_node or the new mmu_rb_node that was inserted between
(2) and (3).
3. In hfi1_mmu_rb_remove_unless_exact(), mmu_rb_node->refcount is
incremented outside of mmu_rb_handler->lock. As a result, mmu_rb_node
could be evicted by another thread that gets mmu_rb_handler->lock and
checks mmu_rb_node->refcount before mmu_rb_node->refcount is
incremented.
4. Related to #2 above, SDMA request submission failure path does not
check mmu_rb_node->refcount before freeing mmu_rb_node object.
If there are other SDMA requests in progress whose iovecs have
pointers to the now-freed mmu_rb_node(s), those pointers to the
now-freed mmu_rb nodes will be dereferenced when those SDMA requests
complete.
Fixes: 7be85676f1 ("IB/hfi1: Don't remove RB entry when not needed.")
Fixes: 7724105686 ("IB/hfi1: add driver files")
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Patrick Kelsey <pat.kelsey@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/168088636445.3027109.10054635277810177889.stgit@252.162.96.66.static.eigbox.net
Signed-off-by: Leon Romanovsky <leon@kernel.org>
hfi1_mmu_rb_remove_unless_exact() did not move mmu_rb_node objects in
mmu_rb_handler->lru_list after getting a cache hit on an mmu_rb_node.
As a result, hfi1_mmu_rb_evict() was not guaranteed to evict truly
least-recently used nodes.
This could be a performance issue for an application when that
application:
- Uses some long-lived buffers frequently.
- Uses a large number of buffers once.
- Hits the mmu_rb_handler cache size or pinned-page limits, forcing
mmu_rb_handler cache entries to be evicted.
In this case, the one-time use buffers cause the long-lived buffer
entries to eventually filter to the end of the LRU list where
hfi1_mmu_rb_evict() will consider evicting a frequently-used long-lived
entry instead of evicting one of the one-time use entries.
Fix this by inserting new mmu_rb_node at the tail of
mmu_rb_handler->lru_list and move mmu_rb_ndoe to the tail of
mmu_rb_handler->lru_list when the mmu_rb_node is a hit in
hfi1_mmu_rb_remove_unless_exact(). Change hfi1_mmu_rb_evict() to evict
from the head of mmu_rb_handler->lru_list instead of the tail.
Fixes: 0636e9ab83 ("IB/hfi1: Add cache evict LRU list")
Signed-off-by: Brendan Cunningham <bcunningham@cornelisnetworks.com>
Signed-off-by: Patrick Kelsey <pat.kelsey@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/168088635931.3027109.10423156330761536044.stgit@252.162.96.66.static.eigbox.net
Signed-off-by: Leon Romanovsky <leon@kernel.org>
These warnings can cause build failure:
In file included from ./include/trace/define_trace.h:102,
from drivers/infiniband/hw/hfi1/trace_dbg.h:111,
from drivers/infiniband/hw/hfi1/trace.h:15,
from drivers/infiniband/hw/hfi1/trace.c:6:
drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘trace_event_get_offsets_hfi1_trace_template’:
./include/trace/trace_events.h:261:9: warning: function ‘trace_event_get_offsets_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format]
struct trace_event_raw_##call __maybe_unused *entry; \
^~~~~~~~~~~~~~~~
drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’
DECLARE_EVENT_CLASS(hfi1_trace_template,
^~~~~~~~~~~~~~~~~~~
In file included from ./include/trace/define_trace.h:102,
from drivers/infiniband/hw/hfi1/trace_dbg.h:111,
from drivers/infiniband/hw/hfi1/trace.h:15,
from drivers/infiniband/hw/hfi1/trace.c:6:
drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘trace_event_raw_event_hfi1_trace_template’:
./include/trace/trace_events.h:386:9: warning: function ‘trace_event_raw_event_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format]
struct trace_event_raw_##call *entry; \
^~~~~~~~~~~~~~~~
drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’
DECLARE_EVENT_CLASS(hfi1_trace_template,
^~~~~~~~~~~~~~~~~~~
In file included from ./include/trace/define_trace.h:103,
from drivers/infiniband/hw/hfi1/trace_dbg.h:111,
from drivers/infiniband/hw/hfi1/trace.h:15,
from drivers/infiniband/hw/hfi1/trace.c:6:
drivers/infiniband/hw/hfi1/./trace_dbg.h: In function ‘perf_trace_hfi1_trace_template’:
./include/trace/perf.h:70:9: warning: function ‘perf_trace_hfi1_trace_template’ might be a candidate for ‘gnu_printf’ format attribute [-Wsuggest-attribute=format]
struct hlist_head *head; \
^~~~~~~~~~
drivers/infiniband/hw/hfi1/./trace_dbg.h:25:1: note: in expansion of macro ‘DECLARE_EVENT_CLASS’
DECLARE_EVENT_CLASS(hfi1_trace_template,
^~~~~~~~~~~~~~~~~~~
Solution adapted here is similar to the one in fbbc95a49d
Signed-off-by: Ehab Ababneh <ehab.ababneh@cornelisnetworks.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Link: https://lore.kernel.org/r/168088635415.3027109.5711716700328939402.stgit@252.162.96.66.static.eigbox.net
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Trace icm_send_rej event before the cm state is reset to idle, so that
correct cm state will be logged. For example when an incoming request is
rejected, the old trace log was:
icm_send_rej: local_id=961102742 remote_id=3829151631 state=IDLE reason=REJ_CONSUMER_DEFINED
With this patch:
icm_send_rej: local_id=312971016 remote_id=3778819983 state=MRA_REQ_SENT reason=REJ_CONSUMER_DEFINED
Fixes: 8dc105befe ("RDMA/cm: Add tracepoints to track MAD send operations")
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/20230330072351.481200-1-markzhang@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Use the new TLV APIs for existing slow path commands. The TLV
APIs will be used to populate extended headers for some of the
Firmware commands, which will be introduced in the patches that
follow.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1680169540-10029-7-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Reducing the number of arguments to bnxt_qplib_rcfw_send_message
by enclosing all its arguments into a command message structure.
Use the same struct while passing the command information to
send_message.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1680169540-10029-5-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Updating the HW structures to the latest version.
This is copied from the code maintained internally. No functionality
changes in this patch. Code is re-organized to match the file maintained
in the internal tree. Also, New HW interface structures are added, which
will be used by the drivers in future.
CC: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1680169540-10029-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
syzbot is reporting that siw_netdev_event(NETDEV_UNREGISTER) cannot destroy
siw_device created after unshare(CLONE_NEWNET) due to net namespace check.
It seems that this check was by error there and should be removed.
Reported-by: syzbot <syzbot+5e70d01ee8985ae62a3b@syzkaller.appspotmail.com>
Link: https://syzkaller.appspot.com/bug?extid=5e70d01ee8985ae62a3b
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Suggested-by: Leon Romanovsky <leon@kernel.org>
Fixes: bdcf26bf9b ("rdma/siw: network and RDMA core interface")
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: https://lore.kernel.org/r/a44e9ac5-44e2-d575-9e30-02483cc7ffd1@I-love.SAKURA.ne.jp
Reviewed-by: Bernard Metzler <bmt@zurich.ibm.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The call netdev_{put, hold} of dev_{put, hold} will check NULL,
so there is no need to check before using dev_{put, hold},
remove it to silence the warnings:
./drivers/infiniband/core/cma.c:713:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed.
./drivers/infiniband/core/cma.c:2433:2-9: WARNING: NULL check before dev_{put, hold} functions is not needed.
Reported-by: Abaci Robot <abaci@linux.alibaba.com>
Link: https://bugzilla.openanolis.cn/show_bug.cgi?id=4668
Signed-off-by: Yang Li <yang.lee@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230331010633.63261-1-yang.lee@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
clang with W=1 reports
drivers/infiniband/hw/qib/qib_file_ops.c:487:20: error: variable
'cnt' set but not used [-Werror,-Wunused-but-set-variable]
u32 tid, ctxttid, cnt, limit, tidcnt;
^
drivers/infiniband/hw/qib/qib_file_ops.c:1771:9: error: variable
'cnt' set but not used [-Werror,-Wunused-but-set-variable]
int i, cnt = 0, maxtid = ctxt_tidbase + dd->rcvtidcnt;
^
This variable is not used so remove it.
Signed-off-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/20230330235800.1845815-1-trix@redhat.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
clang with W=1 reports
drivers/infiniband/hw/mlx5/devx.c:1996:6: error: variable
'num_alloc_xa_entries' set but not used [-Werror,-Wunused-but-set-variable]
int num_alloc_xa_entries = 0;
^
This variable is not used so remove it.
Signed-off-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/20230330153607.1838750-1-trix@redhat.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Move this common logic into iser_create_send_desc instead of duplicating
the code.
Reviewed-by: Sergey Gorenko <sergeygo@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Link: https://lore.kernel.org/r/20230330131333.37900-2-mgurtovoy@nvidia.com
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The removed macros are old leftovers.
Reviewed-by: Sergey Gorenko <sergeygo@nvidia.com>
Signed-off-by: Max Gurtovoy <mgurtovoy@nvidia.com>
Link: https://lore.kernel.org/r/20230330131333.37900-1-mgurtovoy@nvidia.com
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
In preparation for switching single segment iterators to using ITER_UBUF,
swap the check for whether we are user backed or not.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
In preparation for switching single segment iterators to using ITER_UBUF,
swap the check for whether we are user backed or not. While at it, move
it outside the srcu locking area to clean up the code a bit.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This returns a pointer to the current iovec entry in the iterator. Only
useful with ITER_IOVEC right now, but it prepares us to treat ITER_UBUF
and ITER_IOVEC identically for the first segment.
Rename struct iov_iter->iov to iov_iter->__iov to find any potentially
troublesome spots, and also to prevent anyone from adding new code that
accesses iter->iov directly.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Remove the tasklet call in rxe_cq.c and also the is_dying in the
cq struct. There is no reason for the rxe driver to defer the call
to the cq completion handler by scheduling a tasklet. rxe_cq_post()
is not called in a hard irq context.
The rxe driver currently is incorrect because the tasklet call is
made without protecting the cq pointer with a reference from having
the underlying memory freed before the deferred routine is called.
Executing the comp_handler inline fixes this problem.
Fixes: 8700e3e7c4 ("Soft RoCE driver")
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Link: https://lore.kernel.org/r/20230327215643.10410-1-rpearsonhpe@gmail.com
Acked-by: Zhu Yanjun <zyjzyj2000@gmail.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
clang with W=1 reports
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c:1592:6: error: variable
'discard_cnt' set but not used [-Werror,-Wunused-but-set-variable]
int discard_cnt = 0;
^
This variable is not used so remove it.
Signed-off-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/20230326120959.1351948-1-trix@redhat.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
clang with W=1 reports
drivers/infiniband/hw/bnxt_re/qplib_fp.c:303:6: error: variable
'num_srqne_processed' set but not used [-Werror,-Wunused-but-set-variable]
int num_srqne_processed = 0;
^
drivers/infiniband/hw/bnxt_re/qplib_fp.c:304:6: error: variable
'num_cqne_processed' set but not used [-Werror,-Wunused-but-set-variable]
int num_cqne_processed = 0;
^
These variables are not used so remove them.
Signed-off-by: Tom Rix <trix@redhat.com>
Link: https://lore.kernel.org/r/20230325140559.1336056-1-trix@redhat.com
Acked-by: Selvin Xavier <selvin.xavier@broadcom.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Remove pci_clear_master to simplify the code,
the bus-mastering is also cleared in do_pci_disable_device,
like this:
./drivers/pci/pci.c:2197
static void do_pci_disable_device(struct pci_dev *dev)
{
u16 pci_command;
pci_read_config_word(dev, PCI_COMMAND, &pci_command);
if (pci_command & PCI_COMMAND_MASTER) {
pci_command &= ~PCI_COMMAND_MASTER;
pci_write_config_word(dev, PCI_COMMAND, pci_command);
}
pcibios_disable_device(dev);
}.
And dev->is_busmaster is set to 0 in pci_disable_device.
Signed-off-by: Cai Huoqing <cai.huoqing@linux.dev>
Link: https://lore.kernel.org/r/20230323115742.13836-1-cai.huoqing@linux.dev
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Previously for switchdev only per device counters were supported.
Currently we allocate counters for switchdev per port, which also
includes the ports that belong to VF representors in order to expose
them to users through the rdma tool, allowing the host to track the VFs
statistics through their representors counters.
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Link: https://lore.kernel.org/r/ea31e1103c125cd27931ba213f307cde30d2eaed.1679566038.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add resize_cq verb support for user space CQs. Resize operation for
kernel CQs are not supported now.
Driver should free the current CQ only after user library polls
for all the completions and switch to new CQ. So after the resize_cq
is returned from the driver, user library polls for existing completions
and store it as temporary data. Once library reaps all completions in the
current CQ, it invokes the ibv_cmd_poll_cq to inform the driver about
the resize_cq completion. Adding a check for user CQs in driver's
poll_cq and complete the resize operation for user CQs.
Updating uverbs_cmd_mask with poll_cq to support this.
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://lore.kernel.org/r/1678868215-23626-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
struct class should never be modified in a sysfs callback as there is
nothing in the structure to modify, and frankly, the structure is almost
never used in a sysfs callback, so mark it as constant to allow struct
class to be moved to read-only memory.
While we are touching all class sysfs callbacks also mark the attribute
as constant as it can not be modified. The bonding code still uses this
structure so it can not be removed from the function callbacks.
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>
Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Linus Walleij <linus.walleij@linaro.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Miquel Raynal <miquel.raynal@bootlin.com>
Cc: Namjae Jeon <linkinjeon@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Russ Weight <russell.h.weight@intel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Steve French <sfrench@samba.org>
Cc: Vignesh Raghavendra <vigneshr@ti.com>
Cc: linux-cifs@vger.kernel.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-mtd@lists.infradead.org
Cc: linux-rdma@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: netdev@vger.kernel.org
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20230325084537.3622280-1-gregkh@linuxfoundation.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Bart Van Assche <bvanassche@acm.org> says:
It helps humans and the compiler if it is made explicit that SCSI host
templates are not modified. Hence this patch series that constifies most
SCSI host templates. Please consider this patch series for the next merge
window.
Link: https://lore.kernel.org/r/20230322195515.1267197-1-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Make it explicit that the SCSI host template is not modified.
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230322195515.1267197-50-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Make it explicit that the SRP host template is not modified.
Acked-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20230322195515.1267197-7-bvanassche@acm.org
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Mike Christie <michael.christie@oracle.com> says:
The following patches apply over Martin's 6.4 branches and Linus's tree.
They fix a couple regressions in iscsit that occur when there are TMRs
executing and a connection is closed. It also includes Dimitry's fixes in
related code paths for cmd cleanup when ERL2 is used and the write pending
hang during conn cleanup.
This version of the patchset brings it back to just regressions and fixes
for bugs we have a lot of users hitting. I'm going to fix isert and get it
hooked into iscsit properly in a second patchset, because this one was
getting so large. I've also moved my cleanup type of patches for a 3rd
patchset.
Link: https://lore.kernel.org/r/20230319015620.96006-1-michael.christie@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
This has iscsit allocate a per conn cmd counter and converts iscsit/isert
to use it instead of the per session one.
Signed-off-by: Mike Christie <michael.christie@oracle.com>
Link: https://lore.kernel.org/r/20230319015620.96006-5-michael.christie@oracle.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Hardware's page size is 4096, but the kernel's page size may vary. Driver
should use hardware's page size when communicating with hardware.
Fixes: 1550557717 ("RDMA/erdma: Add verbs implementation")
Link: https://lore.kernel.org/r/20230307102924.70577-2-chengyou@linux.alibaba.com
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This patch is a major rewrite of the tasklet routines in rxe_task.c. The
main motivation for this is the realization that the code violates the
safety of the qp pointer by correct reference counting. When a tasklet is
scheduled from a verbs API the calling thread has a valid reference to the
qp and schedules the tasklet to run at a later time carrying a pointer to
the qp. Once the calling code returns however the qp can be destroyed at
any time. In order to correct this a reference to the qp must be taken
when the task is scheduled and held until it finishes running. This is
complicated by the tasklet library not alwys running a task that is
scheduled depending on whether someone else has scheduled it.
This patch moves the logic for deciding whether to run or schedule a task
outside of do_task() and guarantees that there is only one copy of the
task scheduled or running at a time.
Secondly the separate flags controlling teardown and draining of the task
are included in the task state machine and all references to the state are
protected by spinlocks to avoid consistency and memory barrier issues.
Link: https://lore.kernel.org/r/20230304174533.11296-9-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace rxe_run_task() by rxe_sched_task() when tasks call each other.
These are not performance critical and mainly involve error paths but they
run the risk of causing deadlocks.
Link: https://lore.kernel.org/r/20230304174533.11296-8-rpearsonhpe@gmail.com
Signed-off-by: Ian Ziemba <ian.ziemba@hpe.com>
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
The subroutine __rxe_do_task is not thread safe and it has no way to
guarantee that the tasks, which are designed with the assumption that they
are non-reentrant, are not reentered. All of its uses are non-performance
critical.
This patch replaces calls to __rxe_do_task with calls to
rxe_sched_task. It also removes irrelevant or unneeded if tests.
Instead of calling the task machinery a single call to the tasklet
function (rxe_requester, etc.) is sufficient to draing the queues if task
execution has been disabled or stopped.
Together these changes allow the removal of __rxe_do_task.
Link: https://lore.kernel.org/r/20230304174533.11296-7-rpearsonhpe@gmail.com
Signed-off-by: Ian Ziemba <ian.ziemba@hpe.com>
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Currently each of the three tasklets requester, completer and responder in
the rxe driver take and release a reference to the qp argument at the
beginning and end of the subroutines. The caller passing in the qp
argument should be responsible for holding a reference to qp so these are
not required. Further doing so breaks the qp cleanup code in
rxe_qp_do_cleanup which calls these routines after all the references have
been dropped so they cannot drain the packet and work request queues as
intended.
In fact if these routines are deferred by calling tasklet_schedule there
is no guarantee that the calling code does have a qp reference. That is a
bug in rxe_task.c which will be fixed later in this series.
Link: https://lore.kernel.org/r/20230304174533.11296-6-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Cleanup the handling of qp in the error state, reset state and during
rxe_qp_do_cleanup. Make the same as rxe_resp.c
Link: https://lore.kernel.org/r/20230304174533.11296-5-rpearsonhpe@gmail.com
Signed-off-by: Ian Ziemba <ian.ziemba@hpe.com>
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Cleanup the handling of qp in the error state, reset state and during
rxe_qp_do_cleanup. The error state does about the same thing as the others
but has code spread all over.
This patch combines them in a cleaner way.
Link: https://lore.kernel.org/r/20230304174533.11296-4-rpearsonhpe@gmail.com
Signed-off-by: Ian Ziemba <ian.ziemba@hpe.com>
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Originally is was thought that the tasklet machinery in rxe_task.c would
be used in other applications but that has not happened for years. This
patch replaces the 'void *arg' by struct 'rxe_qp *qp' in the parameters to
the tasklet calls. This change will have no affect on performance but may
make the code a little clearer.
Link: https://lore.kernel.org/r/20230304174533.11296-2-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
This patch adds error and debug messages so that every interaction
with rdma-core through a verbs API call or a completion error return
will generate at least one error message backed up by debug messages
with more detail.
With dynamic debugging one can follow up after seeing an error message
by turning on the appropriate debug messages.
Link: https://lore.kernel.org/r/20230303221623.8053-5-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Extend the dbg log messages (e.g. rxe_dbg_xxx) to include
err and info types. rxe.c is modified to use these new log
messages as examples.
Link: https://lore.kernel.org/r/20230303221623.8053-4-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Replace the name rxe_dbg with rxe_dbg_dev which better matches
the remaining rxe_dbg_xxx macros for debug messages with a
rxe device parameter. Reuse the name rxe_dbg for debug messages
which do not have a rxe device parameter.
Link: https://lore.kernel.org/r/20230303221623.8053-3-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
'exists' looks like a boolean. This patch replaces it by the
normal name used for the rxe device, 'rxe', which should be a
little less confusing. The second rxe_dbg() message is
incorrect since rxe is known to be NULL and this will cause a
seg fault if this message were ever sent. Replace it by pr_debug
for the moment.
Fixes: c6aba5ea00 ("RDMA/rxe: Replace pr_xxx by rxe_dbg_xxx in rxe.c")
Link: https://lore.kernel.org/r/20230303221623.8053-2-rpearsonhpe@gmail.com
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
GCC-13 (and Clang)[1] does not like to access a partially allocated
object, since it cannot reason about it for bounds checking.
In this case 140 bytes are allocated for an object of type struct
ib_umad_packet:
packet = kzalloc(sizeof(*packet) + IB_MGMT_RMPP_HDR, GFP_KERNEL);
However, notice that sizeof(*packet) is only 104 bytes:
struct ib_umad_packet {
struct ib_mad_send_buf * msg; /* 0 8 */
struct ib_mad_recv_wc * recv_wc; /* 8 8 */
struct list_head list; /* 16 16 */
int length; /* 32 4 */
/* XXX 4 bytes hole, try to pack */
struct ib_user_mad mad __attribute__((__aligned__(8))); /* 40 64 */
/* size: 104, cachelines: 2, members: 5 */
/* sum members: 100, holes: 1, sum holes: 4 */
/* forced alignments: 1, forced holes: 1, sum forced holes: 4 */
/* last cacheline: 40 bytes */
} __attribute__((__aligned__(8)));
and 36 bytes extra bytes are allocated for a flexible-array member in
struct ib_user_mad:
include/rdma/ib_mad.h:
120 enum {
...
123 IB_MGMT_RMPP_HDR = 36,
... }
struct ib_user_mad {
struct ib_user_mad_hdr hdr; /* 0 64 */
/* --- cacheline 1 boundary (64 bytes) --- */
__u64 data[] __attribute__((__aligned__(8))); /* 64 0 */
/* size: 64, cachelines: 1, members: 2 */
/* forced alignments: 1 */
} __attribute__((__aligned__(8)));
So we have sizeof(*packet) + IB_MGMT_RMPP_HDR == 140 bytes
Then the address of the flex-array member (for which only 36 bytes were
allocated) is casted and copied into a pointer to struct ib_rmpp_mad,
which, in turn, is of size 256 bytes:
rmpp_mad = (struct ib_rmpp_mad *) packet->mad.data;
struct ib_rmpp_mad {
struct ib_mad_hdr mad_hdr; /* 0 24 */
struct ib_rmpp_hdr rmpp_hdr; /* 24 12 */
u8 data[220]; /* 36 220 */
/* size: 256, cachelines: 4, members: 3 */
};
The thing is that those 36 bytes allocated for flex-array member data
in struct ib_user_mad onlly account for the size of both struct ib_mad_hdr
and struct ib_rmpp_hdr, but nothing is left for array u8 data[220].
So, the compiler is legitimately complaining about accessing an object
for which not enough memory was allocated.
Apparently, the only members of struct ib_rmpp_mad that are relevant
(that are actually being used) in function ib_umad_write() are mad_hdr
and rmpp_hdr. So, instead of casting packet->mad.data to
(struct ib_rmpp_mad *) create a new structure
struct ib_rmpp_mad_hdr {
struct ib_mad_hdr mad_hdr;
struct ib_rmpp_hdr rmpp_hdr;
} __packed;
and cast packet->mad.data to (struct ib_rmpp_mad_hdr *).
Notice that
IB_MGMT_RMPP_HDR == sizeof(struct ib_rmpp_mad_hdr) == 36 bytes
Refactor the rest of the code, accordingly.
Fix the following warnings seen under GCC-13 and -Warray-bounds:
drivers/infiniband/core/user_mad.c:564:50: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=]
drivers/infiniband/core/user_mad.c:566:42: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=]
drivers/infiniband/core/user_mad.c:618:25: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=]
drivers/infiniband/core/user_mad.c:622:44: warning: array subscript ‘struct ib_rmpp_mad[0]’ is partly outside array bounds of ‘unsigned char[140]’ [-Warray-bounds=]
Link: https://github.com/KSPP/linux/issues/273
Link: https://godbolt.org/z/oYWaGM4Yb [1]
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/ZBpB91qQcB10m3Fw@work
Signed-off-by: Leon Romanovsky <leon@kernel.org>
As for multicast:
- The SIDR is the only mode that makes sense;
- Besides PS_UDP, other port spaces like PS_IB is also allowed, as it is
UD compatible. In this case qkey also needs to be set [1].
This patch allows only UD qp_type to join multicast, and set qkey to
default if it's not set, to fix an uninit-value error: the ib->rec.qkey
field is accessed without being initialized.
=====================================================
BUG: KMSAN: uninit-value in cma_set_qkey drivers/infiniband/core/cma.c:510 [inline]
BUG: KMSAN: uninit-value in cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570
cma_set_qkey drivers/infiniband/core/cma.c:510 [inline]
cma_make_mc_event+0xb73/0xe00 drivers/infiniband/core/cma.c:4570
cma_iboe_join_multicast drivers/infiniband/core/cma.c:4782 [inline]
rdma_join_multicast+0x2b83/0x30a0 drivers/infiniband/core/cma.c:4814
ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479
ucma_join_multicast+0x1e3/0x250 drivers/infiniband/core/ucma.c:1546
ucma_write+0x639/0x6d0 drivers/infiniband/core/ucma.c:1732
vfs_write+0x8ce/0x2030 fs/read_write.c:588
ksys_write+0x28c/0x520 fs/read_write.c:643
__do_sys_write fs/read_write.c:655 [inline]
__se_sys_write fs/read_write.c:652 [inline]
__ia32_sys_write+0xdb/0x120 fs/read_write.c:652
do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline]
__do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180
do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205
do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248
entry_SYSENTER_compat_after_hwframe+0x4d/0x5c
Local variable ib.i created at:
cma_iboe_join_multicast drivers/infiniband/core/cma.c:4737 [inline]
rdma_join_multicast+0x586/0x30a0 drivers/infiniband/core/cma.c:4814
ucma_process_join+0xa76/0xf60 drivers/infiniband/core/ucma.c:1479
CPU: 0 PID: 29874 Comm: syz-executor.3 Not tainted 5.16.0-rc3-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
=====================================================
[1] https://lore.kernel.org/linux-rdma/20220117183832.GD84788@nvidia.com/
Fixes: b5de0c60cc ("RDMA/cma: Fix use after free race in roce multicast join")
Reported-by: syzbot+8fcbb77276d43cc8b693@syzkaller.appspotmail.com
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/58a4a98323b5e6b1282e83f6b76960d06e43b9fa.1679309909.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
This series from Or changes default of IB out-of-order feature and
allows to the RDMA users to decide if they need to wait for completion
for all segments or it is enough to wait for last segment completion only.
Thanks
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Set retry_mode to GO_BACK_N when qp is created with INTEGRITY_EN flag
because out-of-order is not supported when doing HW offload of signature
operations.
Signed-off-by: Or Har-Toov <ohartoov@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/362de42cdc7a541afa5b1fd0ec6ae706061764a2.1679230449.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add feature bit to existing device caps field. EFA supports data polling
of 128 bytes blocks.
The flag indicates that the NIC guarentees that a 128 byte aligned block
is written in order, ie that observing the last 8 bits of the block mean
the prior 127 bytes are also written.
It is useful for "last data polling" acceleration techniques.
Link: https://lore.kernel.org/r/20230219081328.10419-1-mrgolin@amazon.com
Reviewed-by: Yehuda Yitschak <yehuday@amazon.com>
Reviewed-by: Yossi Leybovich <sleybo@amazon.com>
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Michael Margolin <mrgolin@amazon.com>
Acked-by: Gal Pressman <gal.pressman@linux.dev>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
After necessary configuration, driver should wait hardware finishing
initialization. The wait sets at CMDQ related function though it has
nothing to do with CMDQ. Refactor this part to make code cleaner.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230322093319.84045-4-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Using void * to define EQ doorbell pointer can eliminate unnecessary
casting when performing assignment. Also rename *db_addr* to *db* for a
shorter name.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230322093319.84045-3-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Replace __be32_to_cpu/__cpu_to_be16 with be32_to_cpu/cpu_to_be16.
And use be32_to_cpu_array to copy and swap byte order to hide the
loop.
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230322093319.84045-2-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
ERDMA device may be probed before its associated netdevice, returning
-EPROBE_DEFER allows OS try to probe erdma device later.
Fixes: d55e6fb480 ("RDMA/erdma: Add the erdma module")
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230320084652.16807-5-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
The max inline mtt count supported is ERDMA_MAX_INLINE_MTT_ENTRIES.
When mr->mem.mtt_nents == ERDMA_MAX_INLINE_MTT_ENTRIES, inline mtt
is also supported, fix it.
Fixes: 1550557717 ("RDMA/erdma: Add verbs implementation")
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230320084652.16807-4-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Max EQ depth of hardware is 32K, the current default EQ depth is too small
for some applications, so change the default depth to 4096.
Max send WRs the hardware can support is 8K, but the driver limits the
value to 4K. Remove this limitation.
Fixes: be3cff0f24 ("RDMA/erdma: Add the hardware related definitions")
Fixes: db23ae64ca ("RDMA/erdma: Add verbs header file")
Signed-off-by: Cheng Xu <chengyou@linux.alibaba.com>
Link: https://lore.kernel.org/r/20230320084652.16807-3-chengyou@linux.alibaba.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Currently, when driver queries PTYS to report which link speed is being
used on its RoCE ports, it does not check the case of having 400Gbps
transmitted over 8 lanes. Thus it fails to report the said speed and
instead it defaults to report 10G over 4 lanes.
Add a check for the said speed when querying PTYS and report it back
correctly when needed.
Fixes: 08e8676f16 ("IB/mlx5: Add support for 50Gbps per lane link modes")
Signed-off-by: Maher Sanalla <msanalla@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/ec9040548d119d22557d6a4b4070d6f421701fd4.1678973994.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Currently, in dynamic_debug.h we only provide
DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH()
definitions if CONFIG_DYNAMIC_CORE is enabled. Thus, drivers
such as infiniband srp (see: drivers/infiniband/ulp/srp/ib_srp.c)
must provide their own definitions for !CONFIG_DYNAMIC_CORE.
Thus, let's move this !CONFIG_DYNAMIC_CORE case into dynamic_debug.h.
However, the dynamic debug interfaces should really only be defined
if CONFIG_DYNAMIC_DEBUG is set or CONFIG_DYNAMIC_CORE is set along
with DYNAMIC_DEBUG_MODULE, (see:
Documentation/admin-guide/dynamic-debug-howto.rst). Thus, the
undefined case becomes: !((CONFIG_DYNAMIC_DEBUG ||
(CONFIG_DYNAMIC_CORE && DYNAMIC_DEBUG_MODULE)).
With those changes in place, we can remove the !CONFIG_DYNAMIC_CORE
case from ib_srp.c
This change was prompted by a build breakeage in ib_srp.c stemming
from the inclusion of dynamic_debug.h unconditionally in module.h, due
to commit 7deabd6749 ("dyndbg: use the module notifier callbacks").
In that case, if we have CONFIG_DYNAMIC_CORE=y and
CONFIG_DYNAMIC_DEBUG=n then the definitions for
DEFINE_DYNAMIC_DEBUG_METADATA() and DYNAMIC_DEBUG_BRANCH() are defined
once in ib_srp.c and then again in the dynamic_debug.h. This had been
working prior to the above referenced commit because dynamic_debug.h
was only pulled into ib_srp.c conditinally via printk.h if
CONFIG_DYNAMIC_DEBUG was set.
Also, the exported functions in lib/dynamic_debug.c itself may
not have a prototype if CONFIG_DYNAMIC_DEBUG=n and
CONFIG_DYNAMIC_CORE=y. This would trigger the -Wmissing-prototypes
warning.
The exported functions are behind (include/linux/dynamic_debug.h):
if defined(CONFIG_DYNAMIC_DEBUG) || \
(defined(CONFIG_DYNAMIC_DEBUG_CORE) && defined(DYNAMIC_DEBUG_MODULE))
Thus, by adding -DDYNAMIC_CONFIG_MODULE to the lib/Makefile we
can ensure that the exported functions have a prototype in all cases,
since lib/dynamic_debug.c is built whenever
CONFIG_DYNAMIC_DEBUG_CORE=y.
Fixes: 7deabd6749 ("dyndbg: use the module notifier callbacks")
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202303071444.sIbZTDCy-lkp@intel.com/
Signed-off-by: Jason Baron <jbaron@akamai.com>
[mcgrof: adjust commit log, and remove urldefense from URL]
Signed-off-by: Luis Chamberlain <mcgrof@kernel.org>
pci_enable_pcie_error_reporting() enables the device to send ERR_*
Messages. Since f26e58bf6f ("PCI/AER: Enable error reporting when AER is
native"), the PCI core does this for all devices during enumeration, so the
driver doesn't need to do it itself.
Remove the redundant pci_enable_pcie_error_reporting() call from the
driver.
Note that this only controls ERR_* Messages from the device. An ERR_*
Message may cause the Root Port to generate an interrupt, depending on the
AER Root Error Command register managed by the AER service driver.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
pci_enable_pcie_error_reporting() enables the device to send ERR_*
Messages. Since f26e58bf6f ("PCI/AER: Enable error reporting when AER is
native"), the PCI core does this for all devices during enumeration, so the
driver doesn't need to do it itself.
Remove the redundant pci_enable_pcie_error_reporting() call from the
driver.
Note that this only controls ERR_* Messages from the device. An ERR_*
Message may cause the Root Port to generate an interrupt, depending on the
AER Root Error Command register managed by the AER service driver.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Block comments should align the * on each line on line 2849
Avoid line continuations in quoted strings on line 3848
Signed-off-by: Rohit Chavan <roheetchavan@gmail.com>
Link: https://lore.kernel.org/r/20230319100847.5566-1-roheetchavan@gmail.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add ipv4 check to irdma_find_listener(). Otherwise the function
incorrectly finds and returns a listener with a different addr family for
the zero IP addr, if a listener with a zero IP addr and the same port as
the one searched for has already been created.
Fixes: 146b9756f1 ("RDMA/irdma: Add connection manager")
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145231.931-5-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
When running perftest with large number of connections in iWARP mode, the
passive side could be slow to respond. Increase the rexmit counter default
to allow scaling connections.
Fixes: 146b9756f1 ("RDMA/irdma: Add connection manager")
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145231.931-4-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
On rmmod of irdma, the PBLE object memory is not being freed. PBLE object
memory are not statically pre-allocated at function initialization time
unlike other HMC objects. PBLEs objects and the Segment Descriptors (SD)
for it can be dynamically allocated during scale up and SD's remain
allocated till function deinitialization.
Fix this leak by adding IRDMA_HMC_IW_PBLE to the iw_hmc_obj_types[] table
and skip pbles in irdma_create_hmc_obj but not in irdma_del_hmc_objects().
Fixes: 44d9e52977 ("RDMA/irdma: Implement device initialization definitions")
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145231.931-3-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Currently, artificial SW completions are generated for NOP wqes which can
generate unexpected completions with wr_id = 0. Skip the generation of
artificial completions for NOPs.
Fixes: 81091d7696 ("RDMA/irdma: Add SW mechanism to generate completions on error")
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145231.931-2-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Refactor PBLE functions using a bit mask to represent the PBLE level
desired versus 2 parameters use_pble and lvl_one_only which makes the
code confusing.
Signed-off-by: Mustafa Ismail <mustafa.ismail@intel.com>
Signed-off-by: Sindhu Devale <sindhu.devale@intel.com>
Link: https://lore.kernel.org/r/20230315145305.955-5-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Add more information in interrupt names.
Before this patch it was:
irdma
CEQ
CEQ
...
Now:
irdma-0000:18:00.0-AEQ
irdma-0000:18:00.0-CEQ-0
irdma-0000:18:00.0-CEQ-1
...
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Suggested-by: Piotr Raczynski <piotr.raczynski@intel.com>
Reviewed-by: Shiraz Saleem <shiraz.saleem@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145305.955-4-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Remove a redundant function call in irdma_modify_qp_roce, since
irdma_arp_table() with IRDMA_ARP_RESOLVE action is called after the if/else
ipv check as part of irdma_add_arp().
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145305.955-3-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Refactor HW statistics which,
- Unifies HW statistics support for all HW generations.
- Unifies support of 32- and 64-bit counters.
- Removes duplicated code and simplifies implementation.
- Fixes roll-over handling.
- Removes unneeded last_hw_stats.
With new implementation, there is no separate handling and no separate
arrays for 32- and 64-bit counters (offsets, regs, values). Instead,
there is a HW stats map array for each HW revision, which defines
HW-specific width and location of each counter in the statistics buffer.
Once the statistics are gathered (either via CQP op, or by reading HW
registers), counter values are extracted from the statistics buffer using
the stats map and the delta between the last and new values is computed.
Finally, the counter values in rdma_hw_stats are incremented by those
deltas.
From the OS perspective, all the counters are 64-bit and their order in
rdma_hw_stats->value[] array, as well as in irdma_hw_stat_names[], is the
same for all HW gens. New statistics should always be added at the end.
Signed-off-by: Krzysztof Czurylo <krzysztof.czurylo@intel.com>
Signed-off-by: Youvaraj Sagar <youvaraj.sagar@intel.com>
Signed-off-by: Shiraz Saleem <shiraz.saleem@intel.com>
Link: https://lore.kernel.org/r/20230315145305.955-2-shiraz.saleem@intel.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
kmap() has been deprecated in favor of the kmap_local_page() call.
kmap_local_page() is thread local.
In the sdma coalesce case the page allocated is potentially free'ed in a
different context through qib_sdma_get_complete() ->
qib_user_sdma_make_progress(). The use of kmap_local_page() is
inappropriate in this call path. However, the page is allocated using
GFP_KERNEL and will never be from highmem.
Remove the use of kmap calls and use page_address() in this case.
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/20230217-kmap-qib-v1-1-e5a6fde167e0@intel.com
Acked-by: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
