Spawn PublishSlashReportTask

Updates it so that it'll try for every network instead of returning after any
network fails.

Uses the SlashReport type throughout the codebase.

coordinator/substrate/src/lib.rs

@@ -6,8 +6,8 @@ use scale::{Encode, Decode};
 use borsh::{io, BorshSerialize, BorshDeserialize};
 
 use serai_client::{
-  primitives::{NetworkId, PublicKey, Signature, SeraiAddress},
-  validator_sets::primitives::{Session, ValidatorSet, KeyPair},
+  primitives::{NetworkId, PublicKey, Signature},
+  validator_sets::primitives::{Session, ValidatorSet, KeyPair, SlashReport},
   in_instructions::primitives::SignedBatch,
   Transaction,
 };
@@ -183,10 +183,6 @@ impl SignedBatches {
   }
 }
 
-/// The slash report was invalid.
-#[derive(Debug)]
-pub struct InvalidSlashReport;
-
 /// The slash reports to publish onto Serai.
 pub struct SlashReports;
 impl SlashReports {
@@ -194,30 +190,25 @@ impl SlashReports {
   ///
   /// This only saves the most recent slashes as only a single session is eligible to have its
   /// slashes reported at once.
-  ///
-  /// Returns Err if the slashes are invalid. Returns Ok if the slashes weren't detected as
-  /// invalid. Slashes may be considered invalid by the Serai blockchain later even if not detected
-  /// as invalid here.
   pub fn set(
     txn: &mut impl DbTxn,
     set: ValidatorSet,
-    slashes: Vec<(SeraiAddress, u32)>,
+    slash_report: SlashReport,
     signature: Signature,
-  ) -> Result<(), InvalidSlashReport> {
+  ) {
     // If we have a more recent slash report, don't write this historic one
     if let Some((existing_session, _)) = _public_db::SlashReports::get(txn, set.network) {
       if existing_session.0 >= set.session.0 {
-        return Ok(());
+        return;
       }
     }
 
     let tx = serai_client::validator_sets::SeraiValidatorSets::report_slashes(
       set.network,
-      slashes.try_into().map_err(|_| InvalidSlashReport)?,
+      slash_report,
       signature,
     );
     _public_db::SlashReports::set(txn, set.network, &(set.session, tx.encode()));
-    Ok(())
   }
   pub(crate) fn take(txn: &mut impl DbTxn, network: NetworkId) -> Option<(Session, Transaction)> {
     let (session, tx) = _public_db::SlashReports::take(txn, network)?;

coordinator/substrate/src/publish_slash_report.rs

@@ -22,66 +22,80 @@ impl<D: Db> PublishSlashReportTask<D> {
   }
 }
 
+impl<D: Db> PublishSlashReportTask<D> {
+  // Returns if a slash report was successfully published
+  async fn publish(&mut self, network: NetworkId) -> Result<bool, String> {
+    let mut txn = self.db.txn();
+    let Some((session, slash_report)) = SlashReports::take(&mut txn, network) else {
+      // No slash report to publish
+      return Ok(false);
+    };
+
+    let serai = self.serai.as_of_latest_finalized_block().await.map_err(|e| format!("{e:?}"))?;
+    let serai = serai.validator_sets();
+    let session_after_slash_report = Session(session.0 + 1);
+    let current_session = serai.session(network).await.map_err(|e| format!("{e:?}"))?;
+    let current_session = current_session.map(|session| session.0);
+    // Only attempt to publish the slash report for session #n while session #n+1 is still
+    // active
+    let session_after_slash_report_retired = current_session > Some(session_after_slash_report.0);
+    if session_after_slash_report_retired {
+      // Commit the txn to drain this slash report from the database and not try it again later
+      txn.commit();
+      return Ok(false);
+    }
+
+    if Some(session_after_slash_report.0) != current_session {
+      // We already checked the current session wasn't greater, and they're not equal
+      assert!(current_session < Some(session_after_slash_report.0));
+      // This would mean the Serai node is resyncing and is behind where it prior was
+      Err("have a slash report for a session Serai has yet to retire".to_string())?;
+    }
+
+    // If this session which should publish a slash report already has, move on
+    let key_pending_slash_report =
+      serai.key_pending_slash_report(network).await.map_err(|e| format!("{e:?}"))?;
+    if key_pending_slash_report.is_none() {
+      txn.commit();
+      return Ok(false);
+    };
+
+    match self.serai.publish(&slash_report).await {
+      Ok(()) => {
+        txn.commit();
+        Ok(true)
+      }
+      // This could be specific to this TX (such as an already in mempool error) and it may be
+      // worthwhile to continue iteration with the other pending slash reports. We assume this
+      // error ephemeral and that the latency incurred for this ephemeral error to resolve is
+      // miniscule compared to the window available to publish the slash report. That makes
+      // this a non-issue.
+      Err(e) => Err(format!("couldn't publish slash report transaction: {e:?}")),
+    }
+  }
+}
+
 impl<D: Db> ContinuallyRan for PublishSlashReportTask<D> {
   type Error = String;
 
   fn run_iteration(&mut self) -> impl Send + Future<Output = Result<bool, Self::Error>> {
     async move {
       let mut made_progress = false;
+      let mut error = None;
       for network in serai_client::primitives::NETWORKS {
         if network == NetworkId::Serai {
           continue;
         };
 
-        let mut txn = self.db.txn();
-        let Some((session, slash_report)) = SlashReports::take(&mut txn, network) else {
-          // No slash report to publish
-          continue;
-        };
-
-        let serai =
-          self.serai.as_of_latest_finalized_block().await.map_err(|e| format!("{e:?}"))?;
-        let serai = serai.validator_sets();
-        let session_after_slash_report = Session(session.0 + 1);
-        let current_session = serai.session(network).await.map_err(|e| format!("{e:?}"))?;
-        let current_session = current_session.map(|session| session.0);
-        // Only attempt to publish the slash report for session #n while session #n+1 is still
-        // active
-        let session_after_slash_report_retired =
-          current_session > Some(session_after_slash_report.0);
-        if session_after_slash_report_retired {
-          // Commit the txn to drain this slash report from the database and not try it again later
-          txn.commit();
-          continue;
-        }
-
-        if Some(session_after_slash_report.0) != current_session {
-          // We already checked the current session wasn't greater, and they're not equal
-          assert!(current_session < Some(session_after_slash_report.0));
-          // This would mean the Serai node is resyncing and is behind where it prior was
-          Err("have a slash report for a session Serai has yet to retire".to_string())?;
-        }
-
-        // If this session which should publish a slash report already has, move on
-        let key_pending_slash_report =
-          serai.key_pending_slash_report(network).await.map_err(|e| format!("{e:?}"))?;
-        if key_pending_slash_report.is_none() {
-          txn.commit();
-          continue;
-        };
-
-        match self.serai.publish(&slash_report).await {
-          Ok(()) => {
-            txn.commit();
-            made_progress = true;
-          }
-          // This could be specific to this TX (such as an already in mempool error) and it may be
-          // worthwhile to continue iteration with the other pending slash reports. We assume this
-          // error ephemeral and that the latency incurred for this ephemeral error to resolve is
-          // miniscule compared to the window available to publish the slash report. That makes
-          // this a non-issue.
-          Err(e) => Err(format!("couldn't publish slash report transaction: {e:?}"))?,
-        }
+        let network_res = self.publish(network).await;
+        // We made progress if any network successfully published their slash report
+        made_progress |= network_res == Ok(true);
+        // We want to yield the first error *after* attempting for every network
+        error = error.or(network_res.err());
+      }
+      // Yield the error
+      if let Some(error) = error {
+        Err(error)?
       }
       Ok(made_progress)
     }