intel-ethernet: software timestamp skbs as late as possible
authorJacob Keller <jacob.e.keller@intel.com>
Fri, 5 Oct 2018 16:33:56 +0000 (09:33 -0700)
committerJeff Kirsher <jeffrey.t.kirsher@intel.com>
Wed, 7 Nov 2018 17:47:01 +0000 (09:47 -0800)
commita9e510589d7017ee4e82800d0a1d78a694772787
treed38e8d0791cfeb12f7a1e5927f6866a57ea8ef94
parent9fc145fcb5fbf2e10ad5e4b31a011b5cecb77b10
intel-ethernet: software timestamp skbs as late as possible

Many of the Intel Ethernet drivers call skb_tx_timestamp() earlier than
necessary. Move the calls to this function to the latest point possible,
just prior to notifying hardware of the new Tx packet when we bump the
tail register.

This affects i40e, iavf, igb, igc, and ixgbe.

The e100, e1000, e1000e, fm10k, and ice drivers already call the
skb_tx_timestamp() function just prior to indicating the Tx packet to
hardware, so they do not need to be changed.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
drivers/net/ethernet/intel/i40e/i40e_txrx.c
drivers/net/ethernet/intel/iavf/iavf_txrx.c
drivers/net/ethernet/intel/igb/igb_main.c
drivers/net/ethernet/intel/igc/igc_main.c
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c