Skip to content

Feature/nvmm support - #28

Open
michaelgruner wants to merge 5 commits into
dev-0.4from
feature/nvmm-support
Open

Feature/nvmm support#28
michaelgruner wants to merge 5 commits into
dev-0.4from
feature/nvmm-support

Conversation

@michaelgruner

Copy link
Copy Markdown
Contributor

No description provided.

@michaelgruner michaelgruner self-assigned this Jul 28, 2026

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 883deb5bd2

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread meson.build
Comment on lines +92 to +93
if cc.has_header('gstnvdsmeta.h',
include_directories : deepstream_incdir)

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Pass GStreamer headers into the DeepStream header check

In a normal Meson installation, gstnvdsmeta.h includes GStreamer headers from a pkg-config-provided directory such as /usr/include/gstreamer-1.0, but this compiler check receives only the DeepStream include directory. Although gst_dep was resolved earlier, Meson does not apply dependency flags to unrelated compiler checks automatically, so this test fails and silently leaves HAVE_DEEPSTREAM unset even when the full SDK is installed. Pass the GStreamer dependency to has_header, or probe the less-dependent nvdsmeta.h as the Autotools path does.

Useful? React with 👍 / 👎.

Comment thread plugins/gstperf.c Outdated
Comment on lines +649 to +650
idx += g_snprintf (&info[idx], GST_PERF_MSG_MAX_SIZE - idx,
"; ds-fps: %0.03f", ds_fps);

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Bound the offset before appending ds-fps

When a program assigns the element a name long enough to fill info, the first g_snprintf returns the number of characters it wanted to write, which can exceed GST_PERF_MSG_MAX_SIZE. This unconditional DeepStream append then evaluates &info[idx] beyond the array and underflows GST_PERF_MSG_MAX_SIZE - idx, causing an out-of-bounds write even with the default CPU-reporting setting; clamp or validate idx before appending.

Useful? React with 👍 / 👎.

@michaelgruner

Copy link
Copy Markdown
Contributor Author

@codex review

@chatgpt-codex-connector

Copy link
Copy Markdown

Codex Review: Didn't find any major issues. Breezy!

Reviewed commit: 15f8b2a623

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants