.\" Copyright (c) 2008, Sun Microsystems, Inc. All Rights Reserved.
.\" The contents of this file are subject to the terms of the Common Development and Distribution License (the "License").  You may not use this file except in compliance with the License.
.\" You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE or http://www.opensolaris.org/os/licensing.  See the License for the specific language governing permissions and limitations under the License.
.\" When distributing Covered Code, include this CDDL HEADER in each file and include the License file at usr/src/OPENSOLARIS.LICENSE.  If applicable, add the following below this CDDL HEADER, with the fields enclosed by brackets "[]" replaced with your own identifying information: Portions Copyright [yyyy] [name of copyright owner]
.\" Copyright (c) 2018, Joyent, Inc.
.Dd June 28, 2018
.Dt CPC 3CPC
.Os
.Sh NAME
.Nm cpc
.Nd hardware performance counters
.Sh DESCRIPTION
Modern microprocessors contain
.Em hardware performance counters
that allow
the measurement of many different hardware events related to CPU behavior,
including instruction and data cache misses as well as various internal states
of the processor.
The counters can be configured to count user events, system
events, or both.
Data from the performance counters can be used to analyze and
tune the behavior of software on a particular type of processor.
.Pp
Most processors are able to generate an interrupt on counter overflow, allowing
the counters to be used for various forms of profiling.
.Pp
This manual page describes a set of APIs that allow illumos applications to use
these counters.
Applications can measure their own behavior, the behavior of
other applications, or the behavior of the whole system.
.Ss Shared Counters or Private Counters
There are two principal models for using these performance counters.
Some users of these statistics want to observe system-wide behavior.
Other users want to view the performance counters as part of the register set
exported by each
.Sy LWP .
On a machine performing more than one activity, these two models are
in conflict because the counters represent a critical hardware resource that
cannot simultaneously be both shared and private.
.Ss Configuration Interfaces
The following configuration interfaces are provided:
.Bl -tag -width Xr
.It Xr cpc_open 3CPC
Check the version the application was compiled with against the version of the
.It Xr cpc_cciname 3CPC
Return a printable string to describe the performance counters of the
processor.
.It Xr cpc_npic 3CPC
Return the number of performance counters on the processor.
.It cpc_cpuref 3CPC
Return a reference to documentation that should be consulted to understand how
to use and interpret data from the performance counters.
.El
.Ss Performance Counter Access
Performance counters can be present in hardware but not acccessible because
either some of the necessary system software components are not available or
not installed, or the counters might be in use by other processes.
The
.Xr cpc_open 3CPC
function determines the accessibility of the counters and
must be invoked before any attempt to program the counters.
.Ss "Finding Events"
Each different type of processor has its own set of events available for
measurement.
The
.Xr cpc_walk_events_all 3CPC
and
.Xr cpc_walk_events_pic 3CPC
functions allow an application to determine the
names of events supported by the underlying processor.
A collection of generic, platform independent event names are defined by
.Xr generic_events 3CPC .
Each generic event maps to an underlying hardware event specific to the
underlying processor and any optional attributes.
The
.Xr cpc_walk_generic_events_all 3CPC
and
.Xr cpc_walk_generic_events_pic 3CPC
functions allow an application to determine the generic events supported
on the underlying platform.
.Ss Processor Specific Events
Manual pages specific to events for recent Intel processors are
available.
The following manual pages cover the following Intel processor models
which are listed in hexadecimal:
.Bl -tag -width Xr
.It Xr bdw_de_events 3CPC
Intel Broadwell-DE events; covers model 56h.
.It Xr bdw_events 3CPC
Intel Broadwell client events; covers models 3dh and 47h.
.It Xr bdx_events 3CPC
Intel Broadwell server events; covers model 4fh.
.It Xr bnl_events 3CPC
Intel Atom Bonnell events; covers models 35h, 36h, 27h, 26h, and 1ch.
.It Xr glm_events 3CPC
Intel Goldmont SoC events; covers models 5fh and 5ch.
.It Xr glp_events 3CPC
Intel Goldmont Plus SoC events; covers model 7ah.
.It Xr hsw_events 3CPC
Intel Haswell client events; covers models 46h, 45h, and 3ch.
.It Xr hsx_events 3CPC
Intel Haswell server events; covers model 3fh.
.It Xr ivb_events 3CPC
Intel Ivy Bridge client events; covers model 3ah.
.It Xr ivt_events 3CPC
Intel Ivy Bridge server events; covers model 3eh.
.It Xr jkt_events 3CPC
Intel Sandy Bridge server events; covers model 2dh.
.It Xr nhm_ep_events 3CPC
Intel Nehalem-EP events; covers models, 1ah, 1fh, and 1eh.
.It Xr nhm_ex_events 3CPC
Intel Sandy Bridge server events; covers model 23h.
.It Xr skl_events 3CPC
Intel Skylake client events; covers model 9eh, 8eh, 5e, and 4eh.
.It Xr skx_events 3CPC
Intel Skylake server events; covers model 55h.
.It Xr slm_events 3CPC
Intel Atom Silvermont events; covers models 4ch, 4dh, and 37h.
.It Xr snb_events 3CPC
Intel Sandy Bridge Client events; covers model 2ah.
.It Xr wsm_ep_dp_events 3CPC
Intel Westmere-EP-DP events; covers model 2ch.
.It Xr wsm_ep_sp_events 3CPC
Intel Westmere-EP-SP events; covers model 25h.
.It Xr wsm_ex_events 3CPC
Intel Westmere-EX events; covers model 2fh.
.El
.Ss Using Attributes
Some processors have advanced performance counter capabilities that are
configured with attributes.
The
.Xr cpc_walk_attrs 3CPC
function can be used to determine the names of attributes supported by
the underlying processor.
The documentation referenced by
.Xr cpc_cpuref 3CPC
should be consulted to understand the meaning of a processor's performance
counter attributes.
.Ss Performance Counter Context
Each processor on the system possesses its own set of performance counter
registers.
For a single process, it is often desirable to maintain the illusion
that the counters are an intrinsic part of that process (whichever processors
it runs on), since this allows the events to be directly attributed to the
process without having to make passive all other activity on the system.
.Pp
To achieve this behavior, the library associates
.Em performance counter context
with each
.Sy LWP
in the process.
The context consists of a small amount of kernel memory to hold the counter
values when the
.Sy BLWP
is not running, and some simple kernel functions to save and restore those counter
values from and to the hardware registers when the
.Sy LWP
performs a normal context switch.
A process can only observe and manipulate its own copy of the
performance counter control and data registers.
.Ss Performance Counters \&In Other Processes
Though applications can be modified to instrument themselves as demonstrated
above, it is frequently useful to be able to examine the behavior of an
existing application without changing the source code.
A separate library,
.Sy libpctx ,
provides a simple set of interfaces that use the facilities of
.Xr proc 4
to control a target process, and together with functions in
.Sy libcpc ,
allow
.Sy truss No -like
tools to be constructed to measure the performance counters in other
applications.
An example of one such application is
.Xr cputrack 1 .
.Pp
The functions in
.Sy libpctx
are independent of those in
.Sy libcpc .
These functions manage a process using an event-loop paradigm \(em that is, the
execution of certain system calls by the controlled process cause the library
to stop the controlled process and execute callback functions in the context of
the controlling process.
These handlers can perform various operations on the target process using APIs
in
.Sy libpctx
and
.Sy libcpc
that consume
.Vt pctx_t
handles.
.Sh SEE ALSO
.Xr cputrack 1 ,
.Xr cpustat 1M ,
.Xr cpc_bind_curlwp 3CPC ,
.Xr cpc_buf_create 3CPC ,
.Xr cpc_enable 3CPC ,
.Xr cpc_npic 3CPC ,
.Xr cpc_open 3CPC ,
.Xr cpc_set_create 3CPC ,
.Xr cpc_seterrhndlr 3CPC ,
.Xr generic_events 3CPC ,
.Xr pctx_capture 3CPC ,
.Xr pctx_set_events 3CPC ,
.Xr libcpc 3LIB ,
.Xr proc 4