1. 20 7月, 2018 1 次提交
  2. 02 7月, 2018 1 次提交
  3. 20 6月, 2018 1 次提交
  4. 05 6月, 2018 1 次提交
  5. 23 5月, 2018 2 次提交
  6. 11 5月, 2018 1 次提交
  7. 08 5月, 2018 2 次提交
  8. 24 4月, 2018 1 次提交
  9. 30 3月, 2018 1 次提交
  10. 27 7月, 2017 4 次提交
  11. 03 7月, 2017 1 次提交
  12. 05 6月, 2017 1 次提交
    • M
      qed: VFs to try utilizing the doorbell bar · 1a850bfc
      Mintz, Yuval 提交于
      VFs are currently not mapping their doorbell bar, instead relying
      on the small doorbell window they have in their limited regview bar.
      
      In order to increase the number of possible Tx connections [queues]
      employeed by VF past 16, we need to start using the doorbell bar if
      one such is exposed - VF would communicate this fact to PF which would
      return the size-bar internally configured into chip, according to
      which the VF would decide whether to actually utilize the doorbell
      bar.
      Signed-off-by: NYuval Mintz <Yuval.Mintz@cavium.com>
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      1a850bfc
  13. 02 6月, 2017 3 次提交
  14. 31 5月, 2017 1 次提交
    • M
      qed: Don't log missing periodic stats by default · 512c7840
      Mintz, Yuval 提交于
      Current implementation lacks the logic for providing management
      firmware with RDMA-related statistics; [much] worse than that -
      it logs such events by default to system logs.
      
      Since the statistics' gathering is done periodically, using sufficiently
      new management firmware the system logs would get filled with these
      unnecessary prints.
      
      For now, reduce the verbosity of the log so that it would not be
      logged by default.
      
      Fixes: 6c754246 ("qed: Add support for NCSI statistics")
      Signed-off-by: NYuval Mintz <Yuval.Mintz@cavium.com>
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      512c7840
  15. 25 5月, 2017 3 次提交
  16. 19 5月, 2017 1 次提交
  17. 09 5月, 2017 2 次提交
  18. 05 5月, 2017 2 次提交
  19. 01 5月, 2017 1 次提交
  20. 28 4月, 2017 1 次提交
  21. 25 4月, 2017 3 次提交
  22. 18 4月, 2017 1 次提交
  23. 07 4月, 2017 2 次提交
  24. 04 4月, 2017 1 次提交
  25. 29 3月, 2017 2 次提交
    • T
      qed: Move to new load request scheme · 5d24bcf1
      Tomer Tayar 提交于
      Management firmware is used as an arbiter between the various PFs
      in regard to loading - it causes the various PFs to load/unload
      sequentially and informs each of its appropriate rule in the init.
      
      But the existing flow is too weak to handle some scenarios where
      PFs aren't properly cleaned prior to loading.
      The significant scenarios falling under this criteria:
        a. Preboot drivers in some environment can't properly unload.
        b. Unexpected driver replacement [kdump, PDA].
      
      Modern management firmware supports a more intricate loading flow,
      where the driver has the ability to overcome previous limitations.
      This moves qed into using this newer scheme.
      
      Notice new scheme is backward compatible, so new drivers would
      still be able to load properly on top of older management firmwares
      and vice versa.
      Signed-off-by: NTomer Tayar <Tomer.Tayar@cavium.com>
      Signed-off-by: NYuval Mintz <Yuval.Mintz@cavium.com>
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      5d24bcf1
    • M
      qed: hw_init() to receive parameter-struct · c0c2d0b4
      Mintz, Yuval 提交于
      We'll soon need additional information, so start by changing
      the infrastructure to receive the initializing variables
      via a parameter struct.
      Signed-off-by: NYuval Mintz <Yuval.Mintz@cavium.com>
      Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      c0c2d0b4