From 018e0e3594f7dcd029d258e368c485e742fa9cdb 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 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 --- drivers/misc/habanalabs/command_submission.c | 5 +++-- drivers/misc/habanalabs/context.c | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/drivers/misc/habanalabs/command_submission.c b/drivers/misc/habanalabs/command_submission.c index 8850f47..0bf0867 100644 --- a/drivers/misc/habanalabs/command_submission.c +++ b/drivers/misc/habanalabs/command_submission.c @@ -824,8 +824,9 @@ 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) { args->out.status = HL_WAIT_CS_STATUS_INTERRUPTED; rc = -EINTR; diff --git a/drivers/misc/habanalabs/context.c b/drivers/misc/habanalabs/context.c index 17db7b3..2df6fb8 100644 --- a/drivers/misc/habanalabs/context.c +++ b/drivers/misc/habanalabs/context.c @@ -176,7 +176,7 @@ struct dma_fence *hl_ctx_get_fence(struct hl_ctx *ctx, u64 seq) spin_lock(&ctx->cs_lock); 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); spin_unlock(&ctx->cs_lock); -- 2.7.4