UMEM teardown currently recomputes the munmap() length from frame
geometry, shared-UMEM adjustment, and hugepage rounding. This duplicates
setup-time logic in cleanup and relies on re-deriving the mapping size
instead of using the size originally established for the mapping.

Store the final mapping length in xsk_umem_info as mmap_size when the
UMEM mapping is created, and use that value during teardown.

Also join the RX worker thread before cleanup in the single-thread
path. This establishes synchronization before reading umem->mmap_size
in teardown and avoids a potential visibility race.

This removes duplicated size arithmetic in cleanup and makes munmap()
use the canonical mapping size recorded at setup time.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Tushar Vyavahare <tushar.vyavahare@intel.com>
---
 .../selftests/bpf/prog_tests/test_xsk.c       | 20 +++++++++----------
 .../selftests/bpf/prog_tests/test_xsk.h       |  1 +
 2 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.c b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
index f1730466ffd9..e94c38a1faf4 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.c
@@ -1581,7 +1581,7 @@ static int thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	struct xsk_umem_info *umem = ifobject->xsk->umem;
 	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
 	int mmap_flags;
-	u64 umem_sz;
+	u64 umem_sz, mmap_sz;
 	void *bufs;
 	int ret;
 	u32 i;
@@ -1595,10 +1595,15 @@ static int thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 	if (ifobject->shared_umem)
 		umem_sz *= 2;
 
-	bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+	mmap_sz = umem->unaligned_mode ?
+		ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE : umem_sz;
+
+	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
 	if (bufs == MAP_FAILED)
 		return -errno;
 
+	umem->mmap_size = mmap_sz;
+
 	ret = xsk_configure_umem(ifobject, umem, bufs, umem_sz);
 	if (ret)
 		return ret;
@@ -1706,15 +1711,9 @@ void *worker_testapp_validate_rx(void *arg)
 static void testapp_clean_xsk_umem(struct ifobject *ifobj)
 {
 	struct xsk_umem_info *umem = ifobj->xsk->umem;
-	u64 umem_sz = umem_size(umem);
-
-	if (ifobj->shared_umem)
-		umem_sz *= 2;
-
-	umem_sz = ceil_u64(umem_sz, HUGEPAGE_SIZE) * HUGEPAGE_SIZE;
 
 	xsk_umem__delete(umem->umem);
-	munmap(umem->buffer, umem_sz);
+	munmap(umem->buffer, umem->mmap_size);
 }
 
 static void handler(int signum)
@@ -1857,8 +1856,7 @@ static int __testapp_validate_traffic(struct test_spec *test, struct ifobject *i
 
 	if (!ifobj2)
 		pthread_kill(t0, SIGUSR1);
-	else
-		pthread_join(t0, NULL);
+	pthread_join(t0, NULL);
 
 	if (test->total_steps == test->current_step || test->fail) {
 		clean_sockets(test, ifobj1);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_xsk.h b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
index 99003995d7c3..4313d0d87235 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_xsk.h
+++ b/tools/testing/selftests/bpf/prog_tests/test_xsk.h
@@ -103,6 +103,7 @@ struct xsk_umem_info {
 	struct xsk_ring_cons cq;
 	struct xsk_umem *umem;
 	u64 next_buffer;
+	u64 mmap_size;
 	u32 num_frames;
 	u32 frame_headroom;
 	void *buffer;
-- 
2.43.0