blob: d08107e66e75c307dca06aec3c996bd71725842b [file] [log] [blame]
From 0e80b18d188e1ba0eb38ffdc8ffbbf2e4eea085b Mon Sep 17 00:00:00 2001
From: Oded Gabbay <>
Date: Tue, 3 Dec 2019 10:12:10 +0200
Subject: [PATCH] habanalabs: rate limit error msg on waiting for CS
commit 018e0e3594f7dcd029d258e368c485e742fa9cdb upstream.
In case a user submits a CS, and the submission fails, and the user doesn't
check the return value and instead use the error return value as a valid
sequence number of a CS and ask to wait on it, the driver will print an
error and return an error code for that wait.
The real problem happens if now the user ignores the error of the wait, and
try to wait again and again. This can lead to a flood of error messages
from the driver and even soft lockup event.
Signed-off-by: Oded Gabbay <>
Reviewed-by: Tomer Tayar <>
Signed-off-by: Paul Gortmaker <>
diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c
index 6fe785e26859..52fd0229c4f7 100644
--- a/drivers/misc/habanalabs/command_submission.c
+++ b/drivers/misc/habanalabs/command_submission.c
@@ -764,8 +764,9 @@ int hl_cs_wait_ioctl(struct hl_fpriv *hpriv, void *data)
memset(args, 0, sizeof(*args));
if (rc < 0) {
- dev_err(hdev->dev, "Error %ld on waiting for CS handle %llu\n",
- rc, seq);
+ dev_err_ratelimited(hdev->dev,
+ "Error %ld on waiting for CS handle %llu\n",
+ rc, seq);
if (rc == -ERESTARTSYS) {
rc = -EINTR;
diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c
index f4c92f110a72..4d5a0454208e 100644
--- a/drivers/misc/habanalabs/context.c
+++ b/drivers/misc/habanalabs/context.c
@@ -159,7 +159,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq)
if (seq >= ctx->cs_sequence) {
- dev_notice(hdev->dev,
+ dev_notice_ratelimited(hdev->dev,
"Can't wait on seq %llu because current CS is at seq %llu\n",
seq, ctx->cs_sequence);