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>
This commit is contained in:
Wu Hao 2020-04-27 09:06:23 +08:00 committed by Greg Kroah-Hartman
parent 1f03ac9460
commit 724142f8c4
7 changed files with 1134 additions and 1 deletions

View File

@ -0,0 +1,104 @@
What: /sys/bus/event_source/devices/dfl_fmeX/format
Date: April 2020
KernelVersion: 5.8
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. Attribute group to describe the magic bits
that go into perf_event_attr.config for a particular pmu.
(See ABI/testing/sysfs-bus-event_source-devices-format).
Each attribute under this group defines a bit range of the
perf_event_attr.config. All supported attributes are listed
below.
event = "config:0-11" - event ID
evtype = "config:12-15" - event type
portid = "config:16-23" - event source
For example,
fab_mmio_read = "event=0x06,evtype=0x02,portid=0xff"
It shows this fab_mmio_read is a fabric type (0x02) event with
0x06 local event id for overall monitoring (portid=0xff).
What: /sys/bus/event_source/devices/dfl_fmeX/cpumask
Date: April 2020
KernelVersion: 5.8
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. This file always returns cpu which the PMU is bound
for access to all fme pmu performance monitoring events.
What: /sys/bus/event_source/devices/dfl_fmeX/events
Date: April 2020
KernelVersion: 5.8
Contact: Wu Hao <hao.wu@intel.com>
Description: Read-only. Attribute group to describe performance monitoring
events specific to fme. Each attribute in this group describes
a single performance monitoring event supported by this fme pmu.
The name of the file is the name of the event.
(See ABI/testing/sysfs-bus-event_source-devices-events).
All supported performance monitoring events are listed below.
Basic events (evtype=0x00)
clock = "event=0x00,evtype=0x00,portid=0xff"
Cache events (evtype=0x01)
cache_read_hit = "event=0x00,evtype=0x01,portid=0xff"
cache_read_miss = "event=0x01,evtype=0x01,portid=0xff"
cache_write_hit = "event=0x02,evtype=0x01,portid=0xff"
cache_write_miss = "event=0x03,evtype=0x01,portid=0xff"
cache_hold_request = "event=0x05,evtype=0x01,portid=0xff"
cache_data_write_port_contention =
"event=0x06,evtype=0x01,portid=0xff"
cache_tag_write_port_contention =
"event=0x07,evtype=0x01,portid=0xff"
cache_tx_req_stall = "event=0x08,evtype=0x01,portid=0xff"
cache_rx_req_stall = "event=0x09,evtype=0x01,portid=0xff"
cache_eviction = "event=0x0a,evtype=0x01,portid=0xff"
Fabric events (evtype=0x02)
fab_pcie0_read = "event=0x00,evtype=0x02,portid=0xff"
fab_pcie0_write = "event=0x01,evtype=0x02,portid=0xff"
fab_pcie1_read = "event=0x02,evtype=0x02,portid=0xff"
fab_pcie1_write = "event=0x03,evtype=0x02,portid=0xff"
fab_upi_read = "event=0x04,evtype=0x02,portid=0xff"
fab_upi_write = "event=0x05,evtype=0x02,portid=0xff"
fab_mmio_read = "event=0x06,evtype=0x02,portid=0xff"
fab_mmio_write = "event=0x07,evtype=0x02,portid=0xff"
fab_port_pcie0_read = "event=0x00,evtype=0x02,portid=?"
fab_port_pcie0_write = "event=0x01,evtype=0x02,portid=?"
fab_port_pcie1_read = "event=0x02,evtype=0x02,portid=?"
fab_port_pcie1_write = "event=0x03,evtype=0x02,portid=?"
fab_port_upi_read = "event=0x04,evtype=0x02,portid=?"
fab_port_upi_write = "event=0x05,evtype=0x02,portid=?"
fab_port_mmio_read = "event=0x06,evtype=0x02,portid=?"
fab_port_mmio_write = "event=0x07,evtype=0x02,portid=?"
VTD events (evtype=0x03)
vtd_port_read_transaction = "event=0x00,evtype=0x03,portid=?"
vtd_port_write_transaction = "event=0x01,evtype=0x03,portid=?"
vtd_port_devtlb_read_hit = "event=0x02,evtype=0x03,portid=?"
vtd_port_devtlb_write_hit = "event=0x03,evtype=0x03,portid=?"
vtd_port_devtlb_4k_fill = "event=0x04,evtype=0x03,portid=?"
vtd_port_devtlb_2m_fill = "event=0x05,evtype=0x03,portid=?"
vtd_port_devtlb_1g_fill = "event=0x06,evtype=0x03,portid=?"
VTD SIP events (evtype=0x04)
vtd_sip_iotlb_4k_hit = "event=0x00,evtype=0x04,portid=0xff"
vtd_sip_iotlb_2m_hit = "event=0x01,evtype=0x04,portid=0xff"
vtd_sip_iotlb_1g_hit = "event=0x02,evtype=0x04,portid=0xff"
vtd_sip_slpwc_l3_hit = "event=0x03,evtype=0x04,portid=0xff"
vtd_sip_slpwc_l4_hit = "event=0x04,evtype=0x04,portid=0xff"
vtd_sip_rcc_hit = "event=0x05,evtype=0x04,portid=0xff"
vtd_sip_iotlb_4k_miss = "event=0x06,evtype=0x04,portid=0xff"
vtd_sip_iotlb_2m_miss = "event=0x07,evtype=0x04,portid=0xff"
vtd_sip_iotlb_1g_miss = "event=0x08,evtype=0x04,portid=0xff"
vtd_sip_slpwc_l3_miss = "event=0x09,evtype=0x04,portid=0xff"
vtd_sip_slpwc_l4_miss = "event=0x0a,evtype=0x04,portid=0xff"
vtd_sip_rcc_miss = "event=0x0b,evtype=0x04,portid=0xff"

View File

@ -156,7 +156,7 @@ config FPGA_DFL
config FPGA_DFL_FME
tristate "FPGA DFL FME Driver"
depends on FPGA_DFL && HWMON
depends on FPGA_DFL && HWMON && PERF_EVENTS
help
The FPGA Management Engine (FME) is a feature device implemented
under Device Feature List (DFL) framework. Select this option to

View File

@ -40,6 +40,7 @@ obj-$(CONFIG_FPGA_DFL_FME_REGION) += dfl-fme-region.o
obj-$(CONFIG_FPGA_DFL_AFU) += dfl-afu.o
dfl-fme-objs := dfl-fme-main.o dfl-fme-pr.o dfl-fme-error.o
dfl-fme-objs += dfl-fme-perf.o
dfl-afu-objs := dfl-afu-main.o dfl-afu-region.o dfl-afu-dma-region.o
dfl-afu-objs += dfl-afu-error.o

View File

@ -579,6 +579,10 @@ static struct dfl_feature_driver fme_feature_drvs[] = {
.id_table = fme_power_mgmt_id_table,
.ops = &fme_power_mgmt_ops,
},
{
.id_table = fme_perf_id_table,
.ops = &fme_perf_ops,
},
{
.ops = NULL,
},

1020
drivers/fpga/dfl-fme-perf.c Normal file

File diff suppressed because it is too large Load Diff

View File

@ -38,5 +38,7 @@ extern const struct dfl_feature_id fme_pr_mgmt_id_table[];
extern const struct dfl_feature_ops fme_global_err_ops;
extern const struct dfl_feature_id fme_global_err_id_table[];
extern const struct attribute_group fme_global_err_group;
extern const struct dfl_feature_ops fme_perf_ops;
extern const struct dfl_feature_id fme_perf_id_table[];
#endif /* __DFL_FME_H */

View File

@ -197,12 +197,14 @@ struct dfl_feature_driver {
* feature dev (platform device)'s reources.
* @ioaddr: mapped mmio resource address.
* @ops: ops of this sub feature.
* @priv: priv data of this feature.
*/
struct dfl_feature {
u64 id;
int resource_index;
void __iomem *ioaddr;
const struct dfl_feature_ops *ops;
void *priv;
};
#define DEV_STATUS_IN_USE 0