i40e: Fix DMA mappings leak

During reallocation of RX buffers, new DMA mappings are created for
those buffers.

steps for reproduction:
while :
do
for ((i=0; i<=8160; i=i+32))
do
ethtool -G enp130s0f0 rx $i tx $i
sleep 0.5
ethtool -g enp130s0f0
done
done

This resulted in crash:
i40e 0000:01:00.1: Unable to allocate memory for the Rx descriptor ring, size=65536
Driver BUG
WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:141 xdp_rxq_info_unreg+0x43/0x50
Call Trace:
i40e_free_rx_resources+0x70/0x80 [i40e]
i40e_set_ringparam+0x27c/0x800 [i40e]
ethnl_set_rings+0x1b2/0x290
genl_family_rcv_msg_doit.isra.15+0x10f/0x150
genl_family_rcv_msg+0xb3/0x160
? rings_fill_reply+0x1a0/0x1a0
genl_rcv_msg+0x47/0x90
? genl_family_rcv_msg+0x160/0x160
netlink_rcv_skb+0x4c/0x120
genl_rcv+0x24/0x40
netlink_unicast+0x196/0x230
netlink_sendmsg+0x204/0x3d0
sock_sendmsg+0x4c/0x50
__sys_sendto+0xee/0x160
? handle_mm_fault+0xbe/0x1e0
? syscall_trace_enter+0x1d3/0x2c0
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
RIP: 0033:0x7f5eac8b035b
Missing register, driver bug
WARNING: CPU: 0 PID: 4300 at net/core/xdp.c:119 xdp_rxq_info_unreg_mem_model+0x69/0x140
Call Trace:
xdp_rxq_info_unreg+0x1e/0x50
i40e_free_rx_resources+0x70/0x80 [i40e]
i40e_set_ringparam+0x27c/0x800 [i40e]
ethnl_set_rings+0x1b2/0x290
genl_family_rcv_msg_doit.isra.15+0x10f/0x150
genl_family_rcv_msg+0xb3/0x160
? rings_fill_reply+0x1a0/0x1a0
genl_rcv_msg+0x47/0x90
? genl_family_rcv_msg+0x160/0x160
netlink_rcv_skb+0x4c/0x120
genl_rcv+0x24/0x40
netlink_unicast+0x196/0x230
netlink_sendmsg+0x204/0x3d0
sock_sendmsg+0x4c/0x50
__sys_sendto+0xee/0x160
? handle_mm_fault+0xbe/0x1e0
? syscall_trace_enter+0x1d3/0x2c0
__x64_sys_sendto+0x24/0x30
do_syscall_64+0x5b/0x1a0
entry_SYSCALL_64_after_hwframe+0x65/0xca
RIP: 0033:0x7f5eac8b035b

This was caused because of new buffers with different RX ring count should
substitute older ones, but those buffers were freed in
i40e_configure_rx_ring and reallocated again with i40e_alloc_rx_bi,
thus kfree on rx_bi caused leak of already mapped DMA.

Fix this by reallocating ZC with rx_bi_zc struct when BPF program loads. Additionally
reallocate back to rx_bi when BPF program unloads.

If BPF program is loaded/unloaded and XSK pools are created, reallocate
RX queues accordingly in XSP_SETUP_XSK_POOL handler.

Fixes: be1222b585fd ("i40e: Separate kernel allocated rx_bi rings from AF_XDP rings")
Signed-off-by: Jan Sokolowski <jan.sokolowski@intel.com>
Signed-off-by: Mateusz Palczewski <mateusz.palczewski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Chandan <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Tested-by: Gurucharan <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 59 insertions, 8 deletions

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index 6d4009e0cbd6..cd7b52fb6b46 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -10,14 +10,6 @@
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
 
-int i40e_alloc_rx_bi_zc(struct i40e_ring *rx_ring)
-{
-	unsigned long sz = sizeof(*rx_ring->rx_bi_zc) * rx_ring->count;
-
-	rx_ring->rx_bi_zc = kzalloc(sz, GFP_KERNEL);
-	return rx_ring->rx_bi_zc ? 0 : -ENOMEM;
-}
-
 void i40e_clear_rx_bi_zc(struct i40e_ring *rx_ring)
 {
 	memset(rx_ring->rx_bi_zc, 0,
@@ -30,6 +22,58 @@ static struct xdp_buff **i40e_rx_bi(struct i40e_ring *rx_ring, u32 idx)
 }
 
 /**
+ * i40e_realloc_rx_xdp_bi - reallocate SW ring for either XSK or normal buffer
+ * @rx_ring: Current rx ring
+ * @pool_present: is pool for XSK present
+ *
+ * Try allocating memory and return ENOMEM, if failed to allocate.
+ * If allocation was successful, substitute buffer with allocated one.
+ * Returns 0 on success, negative on failure
+ */
+static int i40e_realloc_rx_xdp_bi(struct i40e_ring *rx_ring, bool pool_present)
+{
+	size_t elem_size = pool_present ? sizeof(*rx_ring->rx_bi_zc) :
+					  sizeof(*rx_ring->rx_bi);
+	void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL);
+
+	if (!sw_ring)
+		return -ENOMEM;
+
+	if (pool_present) {
+		kfree(rx_ring->rx_bi);
+		rx_ring->rx_bi = NULL;
+		rx_ring->rx_bi_zc = sw_ring;
+	} else {
+		kfree(rx_ring->rx_bi_zc);
+		rx_ring->rx_bi_zc = NULL;
+		rx_ring->rx_bi = sw_ring;
+	}
+	return 0;
+}
+
+/**
+ * i40e_realloc_rx_bi_zc - reallocate rx SW rings
+ * @vsi: Current VSI
+ * @zc: is zero copy set
+ *
+ * Reallocate buffer for rx_rings that might be used by XSK.
+ * XDP requires more memory, than rx_buf provides.
+ * Returns 0 on success, negative on failure
+ */
+int i40e_realloc_rx_bi_zc(struct i40e_vsi *vsi, bool zc)
+{
+	struct i40e_ring *rx_ring;
+	unsigned long q;
+
+	for_each_set_bit(q, vsi->af_xdp_zc_qps, vsi->alloc_queue_pairs) {
+		rx_ring = vsi->rx_rings[q];
+		if (i40e_realloc_rx_xdp_bi(rx_ring, zc))
+			return -ENOMEM;
+	}
+	return 0;
+}
+
+/**
  * i40e_xsk_pool_enable - Enable/associate an AF_XDP buffer pool to a
  * certain ring/qid
  * @vsi: Current VSI
@@ -69,6 +113,10 @@ static int i40e_xsk_pool_enable(struct i40e_vsi *vsi,
 		if (err)
 			return err;
 
+		err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], true);
+		if (err)
+			return err;
+
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;
@@ -113,6 +161,9 @@ static int i40e_xsk_pool_disable(struct i40e_vsi *vsi, u16 qid)
 	xsk_pool_dma_unmap(pool, I40E_RX_DMA_ATTR);
 
 	if (if_running) {
+		err = i40e_realloc_rx_xdp_bi(vsi->rx_rings[qid], false);
+		if (err)
+			return err;
 		err = i40e_queue_pair_enable(vsi, qid);
 		if (err)
 			return err;