Hi Hannes & Martin, Apologies for the extended delay on this. Comments below. On Mon, 2016-08-22 at 10:54 +0200, Hannes Reinecke wrote: > Hi Nic, > > here's a set of patches and fixes I've found during debugging > FCoE over virtio. > The first two fix a race condition I've encountered during starting > and stopping initiators; they are similar to your prior patches, > but I still think they should be applied to avoid any race issues. > The next three are just minor cleanups, but the last one is > _absolutely_ crucial. > With the current code tcm_fc will behave _very_ odd if you're > running in a virtualized environment, as the xid allocator in libfc > will be thouroughly thrashed by sending frames on _other_ cpus than > those the originator frame got received on. > This causes frames to be delayed (by up to several minutes) > leading to I/O errors on the initiator side. > Thanks for the heads up on #6. Applied with v4.5+ tag, the earliest stable where TARGET_SCF_USE_CPUID is available. > As usual, comments and reviews are welcome. > > Hannes Reinecke (6): > target: fix hang in target_wait_for_sess_cmds() > target: fix potential race window in target_sess_cmd_list_waiting() > target/tcm_fc: print command pointer in debug message > target/tcm_fc: return detailed error in ft_sess_create() > target/tcm_fc: Update debugging statements to match libfc usage > target/tcm_fc: use CPU affinity for responses > > drivers/target/target_core_transport.c | 28 ++++++++++++++--------- > drivers/target/tcm_fc/tfc_cmd.c | 4 ++-- > drivers/target/tcm_fc/tfc_sess.c | 42 +++++++++++++++++++++++----------- > 3 files changed, 48 insertions(+), 26 deletions(-) > Applied #3-6 to target-pending/master. Comments inline for #1 and #2. -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
