gpu: nvgpu: update error message to info.

These errors are now actually expected from code that counts number of
sys/gpc/fbp perfmons after first context creation. Nvgpu tries to count
them by register offset lookup in context image and counts perfmons until
invalid offset is found.

nvgpu_gr_hwmp_map_find_priv_offset no longer prints an error message.
The correct error condition is moved to gr_exec_reg_ops

Bug 200755537

Change-Id: Ib5c6ccd39275b2b06e3f8bce4878a3234478a780
Signed-off-by: Debarshi Dutta <ddutta@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/c/linux-nvgpu/+/2586228
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
Reviewed-by: svcacv <svcacv@nvidia.com>
Reviewed-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
This commit is contained in:
Debarshi Dutta
2021-08-17 15:40:55 +05:30
committed by mobile promotions
parent ab4aa0afba
commit a53ebf02d1
2 changed files with 1 additions and 3 deletions

View File

@@ -607,7 +607,6 @@ int nvgpu_gr_hwmp_map_find_priv_offset(struct gk20a *g,
if (result != NULL) {
*priv_offset = result->offset;
} else {
nvgpu_err(g, "Lookup failed for address 0x%x", addr);
err = -EINVAL;
}

View File

@@ -1532,8 +1532,7 @@ static int gr_exec_ctx_ops(struct nvgpu_tsg *tsg,
offsets, offset_addrs,
&num_offsets);
if (err != 0) {
nvgpu_log(g, gpu_dbg_gpu_dbg,
"ctx op invalid offset: offset=0x%x",
nvgpu_err(g, "ctx op invalid offset: offset=0x%x",
ctx_ops[i].offset);
ctx_ops[i].status =
REGOP(STATUS_INVALID_OFFSET);