Prevent double use of git cat-file session. (#29298)

Fixes the reason why #29101 is hard to replicate.
Related #29297

Create a repo with a file with minimum size 4097 bytes (I use 10000) and
execute the following code:
```go
gitRepo, err := gitrepo.OpenRepository(db.DefaultContext, <repo>)
assert.NoError(t, err)

commit, err := gitRepo.GetCommit(<sha>)
assert.NoError(t, err)

entry, err := commit.GetTreeEntryByPath(<file>)
assert.NoError(t, err)

b := entry.Blob()

// Create a reader
r, err := b.DataAsync()
assert.NoError(t, err)
defer r.Close()

// Create a second reader
r2, err := b.DataAsync()
assert.NoError(t, err) // Should be no error but is ErrNotExist
defer r2.Close()
```

The problem is the check in `CatFileBatch`:

79217ea63c/modules/git/repo_base_nogogit.go (L81-L87)
`Buffered() > 0` is used to check if there is a "operation" in progress
at the moment. This is a problem because we can't control the internal
buffer in the `bufio.Reader`. The code above demonstrates a sequence
which initiates an operation for which the code thinks there is no
active processing. The second call to `DataAsync()` therefore reuses the
existing instances instead of creating a new batch reader.

(cherry picked from commit f74c869221624092999097af38b6f7fae4701420)
This commit is contained in:
KN4CK3R 2024-02-21 19:54:17 +01:00 committed by Earl Warren
parent c88ae2e382
commit 5f79550a0d
No known key found for this signature in database
GPG key ID: 0579CB2928A78A00
2 changed files with 59 additions and 6 deletions

View file

@ -4,6 +4,7 @@
package integration
import (
"bytes"
"encoding/hex"
"fmt"
"math/rand"
@ -26,9 +27,11 @@ import (
user_model "code.gitea.io/gitea/models/user"
gitea_context "code.gitea.io/gitea/modules/context"
"code.gitea.io/gitea/modules/git"
"code.gitea.io/gitea/modules/gitrepo"
"code.gitea.io/gitea/modules/lfs"
"code.gitea.io/gitea/modules/setting"
api "code.gitea.io/gitea/modules/structs"
files_service "code.gitea.io/gitea/services/repository/files"
"code.gitea.io/gitea/tests"
"github.com/stretchr/testify/assert"
@ -1034,3 +1037,44 @@ func doCreateAgitFlowPull(dstPath string, ctx *APITestContext, baseBranch, headB
t.Run("CheckoutMasterAgain", doGitCheckoutBranch(dstPath, "master"))
}
}
func TestDataAsync_Issue29101(t *testing.T) {
onGiteaRun(t, func(t *testing.T, u *url.URL) {
user := unittest.AssertExistsAndLoadBean(t, &user_model.User{ID: 2})
repo := unittest.AssertExistsAndLoadBean(t, &repo_model.Repository{ID: 1})
resp, err := files_service.ChangeRepoFiles(db.DefaultContext, repo, user, &files_service.ChangeRepoFilesOptions{
Files: []*files_service.ChangeRepoFile{
{
Operation: "create",
TreePath: "test.txt",
ContentReader: bytes.NewReader(make([]byte, 10000)),
},
},
OldBranch: repo.DefaultBranch,
NewBranch: repo.DefaultBranch,
})
assert.NoError(t, err)
sha := resp.Commit.SHA
gitRepo, err := gitrepo.OpenRepository(db.DefaultContext, repo)
assert.NoError(t, err)
commit, err := gitRepo.GetCommit(sha)
assert.NoError(t, err)
entry, err := commit.GetTreeEntryByPath("test.txt")
assert.NoError(t, err)
b := entry.Blob()
r, err := b.DataAsync()
assert.NoError(t, err)
defer r.Close()
r2, err := b.DataAsync()
assert.NoError(t, err)
defer r2.Close()
})
}