utils: do not use errno after success#2046
utils: do not use errno after success#2046eriksjolund wants to merge 1 commit intocontainers:mainfrom
Conversation
Signed-off-by: Erik Sjölund <erik.sjolund@gmail.com>
Summary of ChangesHello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request refines the error handling logic within a utility function by ensuring that the Highlights
🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console. Changelog
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
There was a problem hiding this comment.
Code Review
This pull request aims to fix incorrect errno usage after a successful function call. The change is correct in principle, but it leads to a loss of information in error messages. I've suggested an alternative approach that preserves the original error information while still being correct regarding errno usage.
| return 0; | ||
|
|
||
| return crun_make_error (err, errno, "create file `%s`", file); | ||
| return crun_make_error (err, ret ? errno : 0, "create file `%s`", file); |
There was a problem hiding this comment.
While this change correctly avoids using errno after a successful function call (get_file_type_at), it replaces the original error from openat with 0. This loses valuable information. For instance, if openat failed because a directory with the same name exists (EISDIR), this information would be lost.
A better approach, consistent with other parts of this file (e.g., line 227), is to save errno after the failing openat call and use it later.
I recommend an implementation like this:
if (fd_write < 0)
{
int saved_errno = errno;
mode_t tmp_mode;
int ret;
/* On errors, check if the file already exists. */
ret = get_file_type_at (dirfd, &tmp_mode, false, file);
if (ret == 0 && S_ISREG (tmp_mode))
return 0;
return crun_make_error (err, ret ? errno : saved_errno, "create file `%s`", file);
}Since I can only suggest a change to this specific line, my suggestion below assumes you've declared and assigned saved_errno earlier in the block.
return crun_make_error (err, ret ? errno : saved_errno, "create file `%s`", file);There was a problem hiding this comment.
Seems like a good advise. I'll check later.
I noticed this when reading the source code.