Example #1
0
// validateBlob checks the data against the digest, returning an error if it
// does not match. The canonical descriptor is returned.
func (bw *blobWriter) validateBlob(ctx context.Context, desc distribution.Descriptor) (distribution.Descriptor, error) {
	var (
		verified, fullHash bool
		canonical          digest.Digest
	)

	if desc.Digest == "" {
		// if no descriptors are provided, we have nothing to validate
		// against. We don't really want to support this for the registry.
		return distribution.Descriptor{}, distribution.ErrBlobInvalidDigest{
			Reason: fmt.Errorf("cannot validate against empty digest"),
		}
	}

	// Stat the on disk file
	if fi, err := bw.bufferedFileWriter.driver.Stat(ctx, bw.path); err != nil {
		switch err := err.(type) {
		case storagedriver.PathNotFoundError:
			// NOTE(stevvooe): We really don't care if the file is
			// not actually present for the reader. We now assume
			// that the desc length is zero.
			desc.Size = 0
		default:
			// Any other error we want propagated up the stack.
			return distribution.Descriptor{}, err
		}
	} else {
		if fi.IsDir() {
			return distribution.Descriptor{}, fmt.Errorf("unexpected directory at upload location %q", bw.path)
		}

		bw.size = fi.Size()
	}

	if desc.Size > 0 {
		if desc.Size != bw.size {
			return distribution.Descriptor{}, distribution.ErrBlobInvalidLength
		}
	} else {
		// if provided 0 or negative length, we can assume caller doesn't know or
		// care about length.
		desc.Size = bw.size
	}

	// TODO(stevvooe): This section is very meandering. Need to be broken down
	// to be a lot more clear.

	if err := bw.resumeDigestAt(ctx, bw.size); err == nil {
		canonical = bw.digester.Digest()

		if canonical.Algorithm() == desc.Digest.Algorithm() {
			// Common case: client and server prefer the same canonical digest
			// algorithm - currently SHA256.
			verified = desc.Digest == canonical
		} else {
			// The client wants to use a different digest algorithm. They'll just
			// have to be patient and wait for us to download and re-hash the
			// uploaded content using that digest algorithm.
			fullHash = true
		}
	} else if err == errResumableDigestNotAvailable {
		// Not using resumable digests, so we need to hash the entire layer.
		fullHash = true
	} else {
		return distribution.Descriptor{}, err
	}

	if fullHash {
		// a fantastic optimization: if the the written data and the size are
		// the same, we don't need to read the data from the backend. This is
		// because we've written the entire file in the lifecycle of the
		// current instance.
		if bw.written == bw.size && digest.Canonical == desc.Digest.Algorithm() {
			canonical = bw.digester.Digest()
			verified = desc.Digest == canonical
		}

		// If the check based on size fails, we fall back to the slowest of
		// paths. We may be able to make the size-based check a stronger
		// guarantee, so this may be defensive.
		if !verified {
			digester := digest.Canonical.New()

			digestVerifier, err := digest.NewDigestVerifier(desc.Digest)
			if err != nil {
				return distribution.Descriptor{}, err
			}

			// Read the file from the backend driver and validate it.
			fr, err := newFileReader(ctx, bw.bufferedFileWriter.driver, bw.path, desc.Size)
			if err != nil {
				return distribution.Descriptor{}, err
			}

			tr := io.TeeReader(fr, digester.Hash())

			if _, err := io.Copy(digestVerifier, tr); err != nil {
				return distribution.Descriptor{}, err
			}

			canonical = digester.Digest()
			verified = digestVerifier.Verified()
		}
	}

	if !verified {
		context.GetLoggerWithFields(ctx,
			map[string]interface{}{
				"canonical": canonical,
				"provided":  desc.Digest,
			}, "canonical", "provided").
			Errorf("canonical digest does match provided digest")
		return distribution.Descriptor{}, distribution.ErrBlobInvalidDigest{
			Digest: desc.Digest,
			Reason: fmt.Errorf("content does not match digest"),
		}
	}

	// update desc with canonical hash
	desc.Digest = canonical

	if desc.MediaType == "" {
		desc.MediaType = "application/octet-stream"
	}

	return desc, nil
}