rework resume token validation to allow resuming from raw sends of unencrypted datasets
Before this change, resuming from an unencrypted dataset with send.raw=true specified wouldn't work with zrepl due to overly restrictive resume token checking. An initial PR to fix this was made in https://github.com/zrepl/zrepl/pull/503 but it didn't address the core of the problem. The core of the problem was that zrepl assumed that if a resume token contained `rawok=true, compressok=true`, the resulting send would be encrypted. But if the sender dataset was unencrypted, such a resume would actually result in an unencrypted send. Which could be totally legitimate but zrepl failed to recognize that. BACKGROUND ========== The following snippets of OpenZFS code are insightful regarding how the various ${X}ok values in the resume token are handled: - https://github.com/openzfs/zfs/blob/6c3c5fcfbe27d9193cd131753cc7e47ee2784621/module/zfs/dmu_send.c#L1947-L2012 - https://github.com/openzfs/zfs/blob/6c3c5fcfbe27d9193cd131753cc7e47ee2784621/module/zfs/dmu_recv.c#L877-L891 - https://github.com/openzfs/zfs/blob/6c3c5fc/lib/libzfs/libzfs_sendrecv.c#L1663-L1672 Basically, some zfs send flags make the DMU send code set some DMU send stream featureflags, although it's not a pure mapping, i.e, which DMU send stream flags are used depends somewhat on the dataset (e.g., is it encrypted or not, or, does it use zstd or not). Then, the receiver looks at some (but not all) feature flags and maps them to ${X}ok dataset zap attributes. These are funnelled back to the sender 1:1 through the resume_token. And the sender turns them into lzc flags. As an example, let's look at zfs send --raw. if the sender requests a raw send on an unencrypted dataset, the send stream (and hence the resume token) will not have the raw stream featureflag set, and hence the resume token will not have the rawok field set. Instead, it will have compressok, embedok, and depending on whether large blocks are present in the dataset, largeblockok set. WHAT'S ZREPL'S ROLE IN THIS? ============================ zrepl provides a virtual encrypted sendflag that is like `raw`, but further ensures that we only send encrypted datasets. For any other resume token stuff, it shoudn't do any checking, because it's a futile effort to keep up with ZFS send/recv features that are orthogonal to encryption. CHANGES MADE IN THIS COMMIT =========================== - Rip out a bunch of needless checking that zrepl would do during planning. These checks were there to give better error messages, but actually, the error messages created by the endpoint.Sender.Send RPC upon send args validation failure are good enough. - Add platformtests to validate all combinations of (Unencrypted/Encrypted FS) x (send.encrypted = true | false) x (send.raw = true | false) for cases both non-resuming and resuming send. Additional manual testing done: 1. With zrepl 0.5, setup with unencrypted dataset, send.raw=true specified, no send.encrypted specified. 2. Observe that regular non-resuming send works, but resuming doesn't work. 3. Upgrade zrepl to this change. 4. Observe that both regular and resuming send works. closes https://github.com/zrepl/zrepl/pull/613
This commit is contained in:
@@ -156,8 +156,7 @@ type Step struct {
|
||||
|
||||
parent *Filesystem
|
||||
from, to *pdu.FilesystemVersion // from may be nil, indicating full send
|
||||
encrypt tri
|
||||
resumeToken string // empty means no resume token shall be used
|
||||
resumeToken string // empty means no resume token shall be used
|
||||
|
||||
expectedSize uint64 // 0 means no size estimate present / possible
|
||||
|
||||
@@ -201,22 +200,10 @@ func (s *Step) ReportInfo() *report.StepInfo {
|
||||
if s.from != nil {
|
||||
from = s.from.RelName()
|
||||
}
|
||||
var encrypted report.EncryptedEnum
|
||||
switch s.encrypt {
|
||||
case DontCare:
|
||||
encrypted = report.EncryptedSenderDependent
|
||||
case True:
|
||||
encrypted = report.EncryptedTrue
|
||||
case False:
|
||||
encrypted = report.EncryptedFalse
|
||||
default:
|
||||
panic(fmt.Sprintf("unknown variant %s", s.encrypt))
|
||||
}
|
||||
return &report.StepInfo{
|
||||
From: from,
|
||||
To: s.to.RelName(),
|
||||
Resumed: s.resumeToken != "",
|
||||
Encrypted: encrypted,
|
||||
BytesExpected: s.expectedSize,
|
||||
BytesReplicated: byteCounter,
|
||||
}
|
||||
@@ -346,10 +333,6 @@ func (fs *Filesystem) doPlanning(ctx context.Context) ([]*Step, error) {
|
||||
|
||||
log(ctx).Debug("assessing filesystem")
|
||||
|
||||
if fs.policy.EncryptedSend == True && !fs.senderFS.GetIsEncrypted() {
|
||||
return nil, fmt.Errorf("sender filesystem is not encrypted but policy mandates encrypted send")
|
||||
}
|
||||
|
||||
sfsvsres, err := fs.sender.ListFilesystemVersions(ctx, &pdu.ListFilesystemVersionsReq{Filesystem: fs.Path})
|
||||
if err != nil {
|
||||
log(ctx).WithError(err).Error("cannot get remote filesystem versions")
|
||||
@@ -423,24 +406,7 @@ func (fs *Filesystem) doPlanning(ctx context.Context) ([]*Step, error) {
|
||||
}
|
||||
}
|
||||
|
||||
encryptionMatches := false
|
||||
switch fs.policy.EncryptedSend {
|
||||
case True:
|
||||
encryptionMatches = resumeToken.RawOK && resumeToken.CompressOK
|
||||
case False:
|
||||
encryptionMatches = !resumeToken.RawOK && !resumeToken.CompressOK
|
||||
case DontCare:
|
||||
encryptionMatches = true
|
||||
}
|
||||
|
||||
log(ctx).WithField("fromVersion", fromVersion).
|
||||
WithField("toVersion", toVersion).
|
||||
WithField("encryptionMatches", encryptionMatches).
|
||||
Debug("result of resume-token-matching to sender's versions")
|
||||
|
||||
if !encryptionMatches {
|
||||
return nil, fmt.Errorf("resume token `rawok`=%v and `compressok`=%v are incompatible with encryption policy=%v", resumeToken.RawOK, resumeToken.CompressOK, fs.policy.EncryptedSend)
|
||||
} else if toVersion == nil {
|
||||
if toVersion == nil {
|
||||
return nil, fmt.Errorf("resume token `toguid` = %v not found on sender (`toname` = %q)", resumeToken.ToGUID, resumeToken.ToName)
|
||||
} else if fromVersion == toVersion {
|
||||
return nil, fmt.Errorf("resume token `fromguid` and `toguid` match same version on sener")
|
||||
@@ -452,9 +418,8 @@ func (fs *Filesystem) doPlanning(ctx context.Context) ([]*Step, error) {
|
||||
sender: fs.sender,
|
||||
receiver: fs.receiver,
|
||||
|
||||
from: fromVersion,
|
||||
to: toVersion,
|
||||
encrypt: fs.policy.EncryptedSend,
|
||||
from: fromVersion,
|
||||
to: toVersion,
|
||||
|
||||
resumeToken: resumeTokenRaw,
|
||||
}
|
||||
@@ -480,7 +445,6 @@ func (fs *Filesystem) doPlanning(ctx context.Context) ([]*Step, error) {
|
||||
receiver: fs.receiver,
|
||||
from: remainingSFSVs[i],
|
||||
to: remainingSFSVs[i+1],
|
||||
encrypt: fs.policy.EncryptedSend,
|
||||
})
|
||||
}
|
||||
} else { // resumeToken == nil
|
||||
@@ -510,9 +474,8 @@ func (fs *Filesystem) doPlanning(ctx context.Context) ([]*Step, error) {
|
||||
sender: fs.sender,
|
||||
receiver: fs.receiver,
|
||||
|
||||
from: path[i], // nil in case of initial repl
|
||||
to: path[i+1],
|
||||
encrypt: fs.policy.EncryptedSend,
|
||||
from: path[i], // nil in case of initial repl
|
||||
to: path[i+1],
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -592,7 +555,6 @@ func (s *Step) buildSendRequest() (sr *pdu.SendReq) {
|
||||
Filesystem: fs,
|
||||
From: s.from, // may be nil
|
||||
To: s.to,
|
||||
Encrypted: s.encrypt.ToPDU(),
|
||||
ResumeToken: s.resumeToken,
|
||||
ReplicationConfig: s.parent.policy.ReplicationConfig,
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user