summaryrefslogtreecommitdiff
path: root/Documentation/accel
diff options
context:
space:
mode:
authorJeffrey Hugo <jhugo@codeaurora.org>2025-10-31 10:41:02 -0700
committerJeff Hugo <jeff.hugo@oss.qualcomm.com>2025-11-07 11:01:18 -0700
commit9675093acea04c7b51ac3a646c7d0ba376b000d6 (patch)
tree2eb8a9c95628c700e18d3bbec3cc9ecdc9e639bc /Documentation/accel
parentf286066ed9df38637eb6c12fb2856f1e0b9731d4 (diff)
accel/qaic: Implement basic SSR handling
Subsystem restart (SSR) for a qaic device means that a NSP has crashed, and will be restarted. However the restart process will lose any state associated with activation, so the user will need to do some recovery. While SSR has the provision to collect a crash dump, this patch does not implement support for it. Co-developed-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Signed-off-by: Jeffrey Hugo <quic_jhugo@quicinc.com> Co-developed-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com> Signed-off-by: Pranjal Ramajor Asha Kanojiya <quic_pkanojiy@quicinc.com> Co-developed-by: Troy Hanson <quic_thanson@quicinc.com> Signed-off-by: Troy Hanson <quic_thanson@quicinc.com> Co-developed-by: Aswin Venkatesan <aswivenk@qti.qualcomm.com> Signed-off-by: Aswin Venkatesan <aswivenk@qti.qualcomm.com> Signed-off-by: Jeffrey Hugo <jhugo@codeaurora.org> Signed-off-by: Youssef Samir <youssef.abdulrahman@oss.qualcomm.com> Signed-off-by: Zack McKevitt <zachary.mckevitt@oss.qualcomm.com> Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> [jhugo: Fix minor checkpatch whitespace issues] Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> Link: https://patch.msgid.link/20251031174059.2814445-3-zachary.mckevitt@oss.qualcomm.com
Diffstat (limited to 'Documentation/accel')
-rw-r--r--Documentation/accel/qaic/aic100.rst24
1 files changed, 22 insertions, 2 deletions
diff --git a/Documentation/accel/qaic/aic100.rst b/Documentation/accel/qaic/aic100.rst
index 273da6192fb3..3b287c3987d2 100644
--- a/Documentation/accel/qaic/aic100.rst
+++ b/Documentation/accel/qaic/aic100.rst
@@ -487,8 +487,8 @@ one user crashes, the fallout of that should be limited to that workload and not
impact other workloads. SSR accomplishes this.
If a particular workload crashes, QSM notifies the host via the QAIC_SSR MHI
-channel. This notification identifies the workload by it's assigned DBC. A
-multi-stage recovery process is then used to cleanup both sides, and get the
+channel. This notification identifies the workload by its assigned DBC. A
+multi-stage recovery process is then used to cleanup both sides, and gets the
DBC/NSPs into a working state.
When SSR occurs, any state in the workload is lost. Any inputs that were in
@@ -496,6 +496,26 @@ process, or queued by not yet serviced, are lost. The loaded artifacts will
remain in on-card DDR, but the host will need to re-activate the workload if
it desires to recover the workload.
+When SSR occurs for a specific NSP, the assigned DBC goes through the
+following state transactions in order:
+DBC_STATE_BEFORE_SHUTDOWN
+ Indicates that the affected NSP was found in an unrecoverable error
+ condition.
+DBC_STATE_AFTER_SHUTDOWN
+ Indicates that the NSP is under reset.
+DBC_STATE_BEFORE_POWER_UP
+ Indicates that the NSP's debug information has been collected, and is
+ ready to be collected by the host (if desired). At that stage the NSP
+ is restarted by QSM.
+DBC_STATE_AFTER_POWER_UP
+ Indicates that the NSP has been restarted, fully operational and is
+ in idle state.
+
+SSR also has an optional crashdump collection feature. If enabled, the host can
+collect the memory dump for the crashed NSP and dump it to the user space via
+the dev_coredump subsystem. The host can also decline the crashdump collection
+request from the device.
+
Reliability, Accessibility, Serviceability (RAS)
================================================