fix: add concurrency fence on traceContext to avoid data races (#11117)

See #11114 for more info.



## Description

Closes: #11114



---

### Author Checklist

*All items are required. Please add a note to the item if the item is not applicable and
please add links to any relevant follow up issues.*

I have...

- [ ] included the correct [type prefix](https://github.com/commitizen/conventional-commit-types/blob/v3.0.0/index.json) in the PR title
- [ ] added `!` to the type prefix if API or client breaking change
- [ ] targeted the correct branch (see [PR Targeting](https://github.com/cosmos/cosmos-sdk/blob/master/CONTRIBUTING.md#pr-targeting))
- [ ] provided a link to the relevant issue or specification
- [ ] followed the guidelines for [building modules](https://github.com/cosmos/cosmos-sdk/blob/master/docs/building-modules)
- [ ] included the necessary unit and integration [tests](https://github.com/cosmos/cosmos-sdk/blob/master/CONTRIBUTING.md#testing)
- [ ] added a changelog entry to `CHANGELOG.md`
- [ ] included comments for [documenting Go code](https://blog.golang.org/godoc)
- [ ] updated the relevant documentation or specification
- [ ] reviewed "Files changed" and left comments if necessary
- [ ] confirmed all CI checks have passed

### Reviewers Checklist

*All items are required. Please add a note if the item is not applicable and please add
your handle next to the items reviewed if you only reviewed selected items.*

I have...

- [ ] confirmed the correct [type prefix](https://github.com/commitizen/conventional-commit-types/blob/v3.0.0/index.json) in the PR title
- [ ] confirmed `!` in the type prefix if API or client breaking change
- [ ] confirmed all author checklist items have been addressed 
- [ ] reviewed state machine logic
- [ ] reviewed API design and naming
- [ ] reviewed documentation is accurate
- [ ] reviewed tests and test coverage
- [ ] manually tested (if applicable)

CHANGELOG.md

@@ -158,6 +158,7 @@ Ref: https://keepachangelog.com/en/1.0.0/
 
 ### Bug Fixes
 
+* (store) [\#11117](https://github.com/cosmos/cosmos-sdk/pull/11117) Fix data race in store trace component
 * (cli) [\#11065](https://github.com/cosmos/cosmos-sdk/pull/11065) Ensure the `tendermint-validator-set` query command respects the `-o` output flag.
 * (grpc) [\#10985](https://github.com/cosmos/cosmos-sdk/pull/10992) The `/cosmos/tx/v1beta1/txs/{hash}` endpoint returns a 404 when a tx does not exist.
 * (rosetta) [\#10340](https://github.com/cosmos/cosmos-sdk/pull/10340) Use `GenesisChunked(ctx)` instead `Genesis(ctx)` to get genesis block height

store/rootmulti/store.go

@@ -9,6 +9,7 @@ import (
 	"math"
 	"sort"
 	"strings"
+	"sync"
 
 	iavltree "github.com/cosmos/iavl"
 	protoio "github.com/gogo/protobuf/io"
@@ -57,8 +58,9 @@ type Store struct {
 	initialVersion int64
 	removalMap     map[types.StoreKey]bool
 
-	traceWriter  io.Writer
-	traceContext types.TraceContext
+	traceWriter       io.Writer
+	traceContext      types.TraceContext
+	traceContextMutex sync.Mutex
 
 	interBlockCache types.MultiStorePersistentCache
 
@@ -329,6 +331,8 @@ func (rs *Store) SetTracer(w io.Writer) types.MultiStore {
 // be overwritten. It is implied that the caller should update the context when
 // necessary between tracing operations. It returns a modified MultiStore.
 func (rs *Store) SetTracingContext(tc types.TraceContext) types.MultiStore {
+	rs.traceContextMutex.Lock()
+	defer rs.traceContextMutex.Unlock()
 	if rs.traceContext != nil {
 		for k, v := range tc {
 			rs.traceContext[k] = v
@@ -340,6 +344,22 @@ func (rs *Store) SetTracingContext(tc types.TraceContext) types.MultiStore {
 	return rs
 }
 
+func (rs *Store) getTracingContext() types.TraceContext {
+	rs.traceContextMutex.Lock()
+	defer rs.traceContextMutex.Unlock()
+
+	if rs.traceContext == nil {
+		return nil
+	}
+
+	ctx := types.TraceContext{}
+	for k, v := range rs.traceContext {
+		ctx[k] = v
+	}
+
+	return ctx
+}
+
 // TracingEnabled returns if tracing is enabled for the MultiStore.
 func (rs *Store) TracingEnabled() bool {
 	return rs.traceWriter != nil
@@ -477,7 +497,7 @@ func (rs *Store) CacheMultiStore() types.CacheMultiStore {
 	for k, v := range rs.stores {
 		stores[k] = v
 	}
-	return cachemulti.NewStore(rs.db, stores, rs.keysByName, rs.traceWriter, rs.traceContext, rs.listeners)
+	return cachemulti.NewStore(rs.db, stores, rs.keysByName, rs.traceWriter, rs.getTracingContext(), rs.listeners)
 }
 
 // CacheMultiStoreWithVersion is analogous to CacheMultiStore except that it
@@ -507,7 +527,7 @@ func (rs *Store) CacheMultiStoreWithVersion(version int64) (types.CacheMultiStor
 		}
 	}
 
-	return cachemulti.NewStore(rs.db, cachedStores, rs.keysByName, rs.traceWriter, rs.traceContext, rs.listeners), nil
+	return cachemulti.NewStore(rs.db, cachedStores, rs.keysByName, rs.traceWriter, rs.getTracingContext(), rs.listeners), nil
 }
 
 // GetStore returns a mounted Store for a given StoreKey. If the StoreKey does
@@ -539,7 +559,7 @@ func (rs *Store) GetKVStore(key types.StoreKey) types.KVStore {
 	store := s.(types.KVStore)
 
 	if rs.TracingEnabled() {
-		store = tracekv.NewStore(store, rs.traceWriter, rs.traceContext)
+		store = tracekv.NewStore(store, rs.traceWriter, rs.getTracingContext())
 	}
 	if rs.ListeningEnabled(key) {
 		store = listenkv.NewStore(store, key, rs.listeners[key])

store/rootmulti/store_test.go

@@ -10,6 +10,7 @@ import (
 	"io"
 	"math/rand"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -803,6 +804,56 @@ func TestCacheWraps(t *testing.T) {
 	require.IsType(t, cachemulti.Store{}, cacheWrappedWithListeners)
 }
 
+func TestTraceConcurrency(t *testing.T) {
+	db := dbm.NewMemDB()
+	multi := newMultiStoreWithMounts(db, types.PruneNothing)
+	err := multi.LoadLatestVersion()
+	require.NoError(t, err)
+
+	b := &bytes.Buffer{}
+	key := multi.keysByName["store1"]
+	tc := types.TraceContext(map[string]interface{}{"blockHeight": 64})
+
+	multi.SetTracer(b)
+	multi.SetTracingContext(tc)
+
+	cms := multi.CacheMultiStore()
+	store1 := cms.GetKVStore(key)
+	cw := store1.CacheWrapWithTrace(b, tc)
+	_ = cw
+	require.NotNil(t, store1)
+
+	stop := make(chan struct{})
+	stopW := make(chan struct{})
+
+	go func(stop chan struct{}) {
+		for {
+			select {
+			case <-stop:
+				return
+			default:
+				store1.Set([]byte{1}, []byte{1})
+				cms.Write()
+			}
+		}
+	}(stop)
+
+	go func(stop chan struct{}) {
+		for {
+			select {
+			case <-stop:
+				return
+			default:
+				multi.SetTracingContext(tc)
+			}
+		}
+	}(stopW)
+
+	time.Sleep(3 * time.Second)
+	stop <- struct{}{}
+	stopW <- struct{}{}
+}
+
 func BenchmarkMultistoreSnapshot100K(b *testing.B) {
 	benchmarkMultistoreSnapshot(b, 10, 10000)
 }