| Message ID | 20220715211313.143645-1-zhanjun.dong@intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | drm/i915/guc: Check for ct enabled while waiting for response | expand |
On Fri, 15 Jul 2022 14:13:13 -0700, Zhanjun Dong wrote: > > -static int wait_for_ct_request_update(struct ct_request *req, u32 *status) > +static int wait_for_ct_request_update(struct intel_guc_ct *ct, struct ct_request *req, u32 *status) > { > int err; > + bool ct_enabled; > > /* > * Fast commands should complete in less than 10us, so sample quickly > @@ -481,12 +483,15 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) > #define GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS 10 > #define GUC_CTB_RESPONSE_TIMEOUT_LONG_MS 1000 > #define done \ > - (FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \ > + (!(ct_enabled = intel_guc_ct_enabled(ct)) || \ > + FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \ > GUC_HXG_ORIGIN_GUC) > err = wait_for_us(done, GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS); > if (err) > err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS); > #undef done > + if (!ct_enabled) > + err = -ENODEV; Good, -ENODEV seems to be the correct return value in this case. > > *status = req->status; > return err; > @@ -703,11 +708,18 @@ static int ct_send(struct intel_guc_ct *ct, > > intel_guc_notify(ct_to_guc(ct)); > > - err = wait_for_ct_request_update(&request, status); > + err = wait_for_ct_request_update(ct, &request, status); > g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); > if (unlikely(err)) { > - CT_ERROR(ct, "No response for request %#x (fence %u)\n", > - action[0], request.fence); > + if (err == -ENODEV) > + /* wait_for_ct_request_update returns -ENODEV on reset/suspend in progress. > + * In this case, output is debug rather than error info > + */ > + CT_DEBUG(ct, "Request %#x (fence %u) cancelled as CTB is disabled\n", > + action[0], request.fence); > + else > + CT_ERROR(ct, "No response for request %#x (fence %u)\n", > + action[0], request.fence); A nit but I would probably prefer to move the CT_DEBUG() inside wait_for_ct_request_update() (so we only keep 'if (err != -ENODEV)' checks here) though it would mean adding the action argument also to wait_for_ct_request_update(). In any case, since we have discussed this patch ad nauseam previously, this is now: Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c index f01325cd1b62..74194c11234d 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c @@ -455,6 +455,7 @@ static int ct_write(struct intel_guc_ct *ct, /** * wait_for_ct_request_update - Wait for CT request state update. + * @ct: pointer to CT * @req: pointer to pending request * @status: placeholder for status * @@ -467,9 +468,10 @@ static int ct_write(struct intel_guc_ct *ct, * * 0 response received (status is valid) * * -ETIMEDOUT no response within hardcoded timeout */ -static int wait_for_ct_request_update(struct ct_request *req, u32 *status) +static int wait_for_ct_request_update(struct intel_guc_ct *ct, struct ct_request *req, u32 *status) { int err; + bool ct_enabled; /* * Fast commands should complete in less than 10us, so sample quickly @@ -481,12 +483,15 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status) #define GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS 10 #define GUC_CTB_RESPONSE_TIMEOUT_LONG_MS 1000 #define done \ - (FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \ + (!(ct_enabled = intel_guc_ct_enabled(ct)) || \ + FIELD_GET(GUC_HXG_MSG_0_ORIGIN, READ_ONCE(req->status)) == \ GUC_HXG_ORIGIN_GUC) err = wait_for_us(done, GUC_CTB_RESPONSE_TIMEOUT_SHORT_MS); if (err) err = wait_for(done, GUC_CTB_RESPONSE_TIMEOUT_LONG_MS); #undef done + if (!ct_enabled) + err = -ENODEV; *status = req->status; return err; @@ -703,11 +708,18 @@ static int ct_send(struct intel_guc_ct *ct, intel_guc_notify(ct_to_guc(ct)); - err = wait_for_ct_request_update(&request, status); + err = wait_for_ct_request_update(ct, &request, status); g2h_release_space(ct, GUC_CTB_HXG_MSG_MAX_LEN); if (unlikely(err)) { - CT_ERROR(ct, "No response for request %#x (fence %u)\n", - action[0], request.fence); + if (err == -ENODEV) + /* wait_for_ct_request_update returns -ENODEV on reset/suspend in progress. + * In this case, output is debug rather than error info + */ + CT_DEBUG(ct, "Request %#x (fence %u) cancelled as CTB is disabled\n", + action[0], request.fence); + else + CT_ERROR(ct, "No response for request %#x (fence %u)\n", + action[0], request.fence); goto unlink; } @@ -771,8 +783,9 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len, ret = ct_send(ct, action, len, response_buf, response_buf_size, &status); if (unlikely(ret < 0)) { - CT_ERROR(ct, "Sending action %#x failed (%pe) status=%#X\n", - action[0], ERR_PTR(ret), status); + if (ret != -ENODEV) + CT_ERROR(ct, "Sending action %#x failed (%pe) status=%#X\n", + action[0], ERR_PTR(ret), status); } else if (unlikely(ret)) { CT_DEBUG(ct, "send action %#x returned %d (%#x)\n", action[0], ret, ret);
We are seeing error message of "No response for request". Some cases happened while waiting for response and reset/suspend action was triggered. In this case, no response is not an error, active requests will be cancelled. This patch will handle this condition and change the error message into debug message. Signed-off-by: Zhanjun Dong <zhanjun.dong@intel.com> --- drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 27 +++++++++++++++++------ 1 file changed, 20 insertions(+), 7 deletions(-)