ibmvnic: Properly dispose of all skbs during a failover.
authorRick Lindsley <ricklind@us.ibm.com>
Sat, 2 Jul 2022 10:37:12 +0000 (03:37 -0700)
committerDavid S. Miller <davem@davemloft.net>
Mon, 4 Jul 2022 10:09:57 +0000 (11:09 +0100)
commit1b18f09d31cfa7148df15a7d5c5e0e86f105f7d1
treef79a0e1940c77483593c0278d916bc1cf9c02ee6
parentea1c3b77bc0b2a414496b3fe988f3abba33db288
ibmvnic: Properly dispose of all skbs during a failover.

During a reset, there may have been transmits in flight that are no
longer valid and cannot be fulfilled.  Resetting and clearing the
queues is insufficient; each skb also needs to be explicitly freed
so that upper levels are not left waiting for confirmation of a
transmit that will never happen.  If this happens frequently enough,
the apparent backlog will cause TCP to begin "congestion control"
unnecessarily, culminating in permanently decreased throughput.

Fixes: d7c0ef36bde03 ("ibmvnic: Free and re-allocate scrqs when tx/rx scrqs change")
Tested-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Rick Lindsley <ricklind@us.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
drivers/net/ethernet/ibm/ibmvnic.c