Commit Graph

2 Commits

Author SHA1 Message Date
Xu Yilun
8a5de2de03 fpga: dfl: change data type of feature id to u16
The feature id is stored in a 12 bit field in DFH. So a u16 variable is
enough for feature id.

This patch changes all feature id related places to fit u16.

Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Reviewed-by: Tom Rix <trix@redhat.com>
Acked-by: Wu Hao <hao.wu@intel.com>
Signed-off-by: Moritz Fischer <mdf@kernel.org>
2020-08-19 21:05:47 -07:00
Wu Hao
724142f8c4 fpga: dfl: fme: add performance reporting support
This patch adds support for performance reporting private feature
for FPGA Management Engine (FME). Now it supports several different
performance counters, including 'basic', 'cache', 'fabric', 'vtd'
and 'vtd_sip'. It allows user to use standard linux tools to access
these performance counters.

e.g. List all events by "perf list"

  perf list | grep fme

  dfl_fme0/cache_read_hit/                     [Kernel PMU event]
  dfl_fme0/cache_read_miss/                    [Kernel PMU event]
  ...

  dfl_fme0/fab_mmio_read/                      [Kernel PMU event]
  dfl_fme0/fab_mmio_write/                     [Kernel PMU event]
  ...

  dfl_fme0/fab_port_mmio_read,portid=?/        [Kernel PMU event]
  dfl_fme0/fab_port_mmio_write,portid=?/       [Kernel PMU event]
  ...

  dfl_fme0/vtd_port_devtlb_1g_fill,portid=?/   [Kernel PMU event]
  dfl_fme0/vtd_port_devtlb_2m_fill,portid=?/   [Kernel PMU event]
  ...

  dfl_fme0/vtd_sip_iotlb_1g_hit/               [Kernel PMU event]
  dfl_fme0/vtd_sip_iotlb_1g_miss/              [Kernel PMU event]
  ...

  dfl_fme0/clock                               [Kernel PMU event]
  ...

e.g. check increased counter value after run one application using
"perf stat" command.

 perf stat -e dfl_fme0/fab_mmio_read/,dfl_fme0/fab_mmio_write/ ./test

 Performance counter stats for './test':

                 1      dfl_fme0/fab_mmio_read/
                 2      dfl_fme0/fab_mmio_write/

       1.009496520 seconds time elapsed

Please note that fabric counters support both fab_* and fab_port_*, but
actually they are sharing one set of performance counters in hardware.
If user wants to monitor overall data events on fab_* then fab_port_*
can't be supported at the same time, see example below:

perf stat -e dfl_fme0/fab_mmio_read/,dfl_fme0/fab_port_mmio_write,portid=0/

 Performance counter stats for 'system wide':

                 0      dfl_fme0/fab_mmio_read/
   <not supported>      dfl_fme0/fab_port_mmio_write,portid=0/

       2.141064085 seconds time elapsed

Signed-off-by: Luwei Kang <luwei.kang@intel.com>
Signed-off-by: Xu Yilun <yilun.xu@intel.com>
Signed-off-by: Wu Hao <hao.wu@intel.com>
Link: https://lore.kernel.org/r/1587949583-12058-3-git-send-email-hao.wu@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-04-28 15:49:28 +02:00