[PATCH bpf 4/4] net/ixgbe: Fix concurrency issues between config flow and XSK

From: Maxim Mikityanskiy <maximmi@mellanox.com>
To: "Björn Töpel" <bjorn.topel@intel.com>,
	"Magnus Karlsson" <magnus.karlsson@intel.com>,
	"Jeff Kirsher" <jeffrey.t.kirsher@intel.com>
Cc: "bpf@vger.kernel.org" <bpf@vger.kernel.org>,
	"netdev@vger.kernel.org" <netdev@vger.kernel.org>,
	"intel-wired-lan@lists.osuosl.org"
	<intel-wired-lan@lists.osuosl.org>,
	"David S. Miller" <davem@davemloft.net>,
	Saeed Mahameed <saeedm@mellanox.com>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Jakub Kicinski <jakub.kicinski@netronome.com>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	John Fastabend <john.fastabend@gmail.com>,
	Jonathan Lemon <jonathan.lemon@gmail.com>,
	Maxim Mikityanskiy <maximmi@mellanox.com>
Subject: [PATCH bpf 4/4] net/ixgbe: Fix concurrency issues between config flow and XSK
Date: Thu, 5 Dec 2019 15:51:17 +0000	[thread overview]
Message-ID: <20191205155028.28854-5-maximmi@mellanox.com> (raw)
In-Reply-To: <20191205155028.28854-1-maximmi@mellanox.com>

Use synchronize_rcu to wait until the XSK wakeup function finishes
before destroying the resources it uses:

1. ixgbe_down already calls synchronize_rcu after setting __IXGBE_DOWN.

2. After switching the XDP program, call synchronize_rcu to let
ixgbe_xsk_async_xmit exit before the XDP program is freed.

3. Changing the number of channels brings the interface down.

4. Disabling UMEM sets __IXGBE_TX_DISABLED before closing hardware
resources and resetting xsk_umem. Check that bit in ixgbe_xsk_async_xmit
to avoid using the XDP ring when it's already destroyed. synchronize_rcu
is called from ixgbe_txrx_ring_disable.

Signed-off-by: Maxim Mikityanskiy <maximmi@mellanox.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +++++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c  | 8 ++++++--
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 25c097cd8100..60503318c7e5 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -10273,8 +10273,12 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog)
 			    adapter->xdp_prog);
 	}
 
-	if (old_prog)
+	if (old_prog) {
+		/* Wait until ndo_xsk_async_xmit completes. */
+		synchronize_rcu();
+
 		bpf_prog_put(old_prog);
+	}
 
 	/* Kick start the NAPI context if there is an AF_XDP socket open
 	 * on that queue id. This so that receiving will start.
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index d6feaacfbf89..b43be9f14105 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -709,10 +709,14 @@ int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 	if (qid >= adapter->num_xdp_queues)
 		return -ENXIO;
 
-	if (!adapter->xdp_ring[qid]->xsk_umem)
+	ring = adapter->xdp_ring[qid];
+
+	if (test_bit(__IXGBE_TX_DISABLED, &ring->state))
+		return -ENETDOWN;
+
+	if (!ring->xsk_umem)
 		return -ENXIO;
 
-	ring = adapter->xdp_ring[qid];
 	if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) {
 		u64 eics = BIT_ULL(ring->q_vector->v_idx);
 
-- 
2.20.1

