mainly fixes around display.

- use terminfo
- dynamically adjust column widths
- mode can be changed while running

add "top" subcommand to tprof(8)

split ksyms stuff into ksyms.[ch]

Support aarch64eb; just works fine.

Fix merge botch.

Merge the [pgoyette-compat] branch

Add ARMv7 support.

Add ARMv8 support.

Merge tpfmt(1) into tprof(8). We want to have access to everything with
only one tool. The code is copied mostly as-is, and the functionality is
available via the "analyze" command.

Eg:
tprof monitor -e llc-misses:k -o myfile.out sleep 20
tprof analyze < myfile.out

Will move soon, I don't like the reading via stdin.

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.3.38; 1.3.40;
man page

branches: 1.2.6;
Enable WARNS=4 by default, except for:
cpuctl dumplfs hprop ipf iprop-log kadmin kcm kdc kdigest
kimpersonate kstash ktutil makefs ndbootd ntp pppd quot
racoon racoonctl rtadvd sntp sup tcpdchk tcpdmatch tcpdump
traceroute traceroute6 user veriexecgen wsmoused zic
(Mostly third-party applications)

branches: 1.1.2; 1.1.14;
a dumb program to talk with the tprof driver.

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.9.66; 1.9.68;
Expunge references to lockmgr.

whitespace

add a script to produce something like opannotate.

rename fmt.sh to tpfmt.sh

branches: 1.5.2;
mention SIZEOF_PTR

PR/37662 was fixed.

note what's sampled.

explain the output of fmt.sh

minimum documentation.

rename fmt.sh to tpfmt.sh

branches: 1.3.2;
use the SIZEOF_PTR environment variable if set.

comment a usage.

a dumb formatter for tprof. should be rewritten.

elftoolchain: Be consistent about which ELF header files we use.

1. For tools that use elftoolchain: always use elftoolchain's
elfdefinitions.h. Don't even think about looking at the host's
sys/exec_elf.h, which makes no sense and should never happen.

(ELF tools that don't use elftoolchain, like m68k-elf2coff,
continue to use nbincludes/sys/exec_elf.h. But no more nbincludes
hacks in elftoolchain.)

2. For kernel components (solaris, zfs, dtrace): always use
sys/exec_elf.h, even in Solaris components via sys/elf.h.
elfdefinitions.h is not wired up in the kernel build at all.

3. For most userland components that involve libelf: use
elfdefinitions.h via libelf header files (libelf.h, gelf.h).

libdtrace in particular requires _all_ R_* reloc type definitions,
but sys/exec_elf.h brings in only the _current machine's_ R_*
reloc type definitions. (While here: Use uintptr_t instead of
Elf_Addr for pointer-to-integer cast, since Elf_Addr is MD and
provided only by sys/exec_elf.h, not by elfdefinitions.h.)

And most userland components using libelf don't rely on any
properties of the current machine from sys/exec_elf.h, so they can
use libelf's elfdefinition.h.

Exceptions:

- dtrace drti.c relies on link.h -> link_elf.h -> sys/exec_elf.h,
but it also relies on sys/dtrace.h -> sys/elf.h ->
elfdefinitions.h like other userland components using sys/elf.h.

- kdump-ioctl.c uses sys/exec_elf.h directly and sys/dtrace.h ->
sys/elf.h -> elfdefinitions like other userland components using
sys/elf.h.

- t_ptrace_wait.c (via t_ptrace_core_wait.h) uses libelf to parse
core files, but relies on sys/exec_elf.h for struct
netbsd_elfcore_procinfo.

None of these exceptions needs all R_* reloc type definitions, so
as a workaround, we can just suppress libelf's elfdefinitions.h by
defining _SYS_ELFDEFINITIONS_H_ and use sys/exec_elf.h in these
exceptions.

And undo the whole BUILTIN_ELF_HEADERS mistake. This was:

- half bogus workarounds for missing build_install dependencies in
tools/Makefile, which are no longer missing now, and
- half futile attempt to use src/sys/sys/exec_elf.h via nbincludes in
tools involving libelf instead of libelf's elfdefinitions.h, which
collides.

Longer-term, we may wish to unify sys/exec_elf.h and libelf's
elfdefinitions.h, so we don't have to play these games.

But at least now the games are limited to three .c files (one of
which is generated by Makefile.ioctl-c), rather than haphazardly
applied tree-wide by monstrous kludges in widely used .h files with
broken hackarounds to get the tools build lurching to completion.

add "top" subcommand to tprof(8)

split ksyms stuff into ksyms.[ch]

add "top" subcommand to tprof(8)

split ksyms stuff into ksyms.[ch]

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.2.4; 1.2.68; 1.2.70;
update comments

add a script to produce something like opannotate.

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.3.44; 1.3.46;
deal with the output of new objdump.

branches: 1.2.4;
update comments

rename fmt.sh to tpfmt.sh

tprof.8: fix typo, s/speficied/specified/

tprof(8): fix markup nits

tprof.8: new sentence, new line

Use the default counter if -e argument is not specified.

monitor command:
The default counter is selected if -e argument is not specified.
list command:
Print the name of the default counter for monitor and top command.

Add two note to the tprof(8)'s manual page.

- "list" command prints the maximum number of counters that can be used
simultaneously.
- multiple -e arguments can be specified.

Add Cometlake support.

branches: 1.24.2;
the "scale" option can be specified in the event name even in "tprof monitor"

- added 'c' command to tprof-top to show/hide event counter.
- column widths were not calculated correctly and sometimes displayed incorrectly.
- use putp() for terminfo str.
- fix build error with llvm.

supported AMD family added

mainly fixes around display.

- use terminfo
- dynamically adjust column widths
- mode can be changed while running

add accumulative mode. "tprof top -a"

add "top" subcommand to tprof(8)

Improve tprof(8)

- Added "tprof count" subcommand to perform counts only.
- Event options (u,k) are now optional. The default value is both userland and kernel. (:uk)
- Event counters can be displayed with SIGINFO during `tprof monitor' or `tprof count'.

Improve tprof(4)

- Multiple events can now be handled simultaneously.
- Counters should be configured with TPROF_IOC_CONFIGURE_EVENT in advance,
instead of being configured at TPROF_IOC_START.
- The configured counters can be started and stopped repeatedly by
PROF_IOC_START/TPROF_IOC_STOP.
- The value of the performance counter can be obtained at any timing as a 64bit
value with TPROF_IOC_GETCOUNTS.
- Backend common parts are handled in tprof.c as much as possible, and functions
on the tprof_backend side have been reimplemented to be more primitive.
- The reset value of counter overflows for profiling can now be adjusted.
It is calculated by default from the CPU clock (speed of cycle counter) and
TPROF_HZ, but for some events the value may be too large to be sufficient for
profiling. The event counter can be specified as a ratio to the default or as
an absolute value when configuring the event counter.
- Due to overall changes, API and ABI have been changed. TPROF_VERSION and
TPROF_BACKEND_VERSION were updated.

Add note about tprof(4) for people like me who forget to load tprof_x86.

Add AMD Family 15h to supported model list

branches: 1.14.2;
Add support for AMD Family 17h.

tprof: Add goldmont plus support. Tested by msaitoh@n.o, thanks.

tprof: Add goldmont support.

I tested on Atom C3558 (Denverton).

Note support for Intel Silvermont/Airmont.

Add a "support" section.

Various improvements to man page. Sync usage.

Ask for a file path with the "analyze" command, instead of reading stdin.

Remove tpfmt(1). Its code was merged into tprof(8).

Merge tpfmt(1) into tprof(8). We want to have access to everything with
only one tool. The code is copied mostly as-is, and the functionality is
available via the "analyze" command.

Eg:
tprof monitor -e llc-misses:k -o myfile.out sleep 20
tprof analyze < myfile.out

Will move soon, I don't like the reading via stdin.

Change the arguments of the tprof tool, to match the behavior of pmc(1) and
cpuctl(8). They become:

tprof list
tprof monitor -e name:option [-o outfile] command

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.3.4; 1.3.40; 1.3.42;
- add a CAVEATS
- fix a warning

Improve wording, sort sections, remove ls(1) escapee.

man page

Use the default counter if -e argument is not specified.

monitor command:
The default counter is selected if -e argument is not specified.
list command:
Print the name of the default counter for monitor and top command.

fixed parsing of event options.
if event option was specivied, it was stuck in a busy loop.

Reflect recent new options for top operation, add a and c

branches: 1.18.2;
the "scale" option can be specified in the event name even in "tprof monitor"

fix build error with llvm

add "top" subcommand to tprof(8)

Improve tprof(8)

- Added "tprof count" subcommand to perform counts only.
- Event options (u,k) are now optional. The default value is both userland and kernel. (:uk)
- Event counters can be displayed with SIGINFO during `tprof monitor' or `tprof count'.

Improve tprof(4)

- Multiple events can now be handled simultaneously.
- Counters should be configured with TPROF_IOC_CONFIGURE_EVENT in advance,
instead of being configured at TPROF_IOC_START.
- The configured counters can be started and stopped repeatedly by
PROF_IOC_START/TPROF_IOC_STOP.
- The value of the performance counter can be obtained at any timing as a 64bit
value with TPROF_IOC_GETCOUNTS.
- Backend common parts are handled in tprof.c as much as possible, and functions
on the tprof_backend side have been reimplemented to be more primitive.
- The reset value of counter overflows for profiling can now be adjusted.
It is calculated by default from the CPU clock (speed of cycle counter) and
TPROF_HZ, but for some events the value may be too large to be sufficient for
profiling. The event counter can be specified as a ratio to the default or as
an absolute value when configuring the event counter.
- Due to overall changes, API and ABI have been changed. TPROF_VERSION and
TPROF_BACKEND_VERSION were updated.

Use errx, there is no errno.

Various improvements to man page. Sync usage.

Fix a crash when running tprof with no arguments; check argc before accessing argv[0]

Mark tprof_monitor as dead

Ask for a file path with the "analyze" command, instead of reading stdin.

Merge tpfmt(1) into tprof(8). We want to have access to everything with
only one tool. The code is copied mostly as-is, and the functionality is
available via the "analyze" command.

Eg:
tprof monitor -e llc-misses:k -o myfile.out sleep 20
tprof analyze < myfile.out

Will move soon, I don't like the reading via stdin.

Change the arguments of the tprof tool, to match the behavior of pmc(1) and
cpuctl(8). They become:

tprof list
tprof monitor -e name:option [-o outfile] command

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

branches: 1.5.38; 1.5.40;
Use __dead

branches: 1.4.8;
fix an error message.

fix exit status values.

branches: 1.2.2;
usage: be a little more understandable.

a dumb program to talk with the tprof driver.

Use the default counter if -e argument is not specified.

monitor command:
The default counter is selected if -e argument is not specified.
list command:
Print the name of the default counter for monitor and top command.

branches: 1.4.2;
the "scale" option can be specified in the event name even in "tprof monitor"

add "top" subcommand to tprof(8)

branches: 1.2.2; 1.2.4;
Merge tpfmt(1) into tprof(8). We want to have access to everything with
only one tool. The code is copied mostly as-is, and the functionality is
available via the "analyze" command.

Eg:
tprof monitor -e llc-misses:k -o myfile.out sleep 20
tprof analyze < myfile.out

Will move soon, I don't like the reading via stdin.

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

sbin, usr.bin, usr.sbin: remove redundant getopt declarations

No binary change, except for assertion line numbers in tprof.

branches: 1.8.4;
add "top" subcommand to tprof(8)

split ksyms stuff into ksyms.[ch]

Improve tprof(4)

- Multiple events can now be handled simultaneously.
- Counters should be configured with TPROF_IOC_CONFIGURE_EVENT in advance,
instead of being configured at TPROF_IOC_START.
- The configured counters can be started and stopped repeatedly by
PROF_IOC_START/TPROF_IOC_STOP.
- The value of the performance counter can be obtained at any timing as a 64bit
value with TPROF_IOC_GETCOUNTS.
- Backend common parts are handled in tprof.c as much as possible, and functions
on the tprof_backend side have been reimplemented to be more primitive.
- The reset value of counter overflows for profiling can now be adjusted.
It is calculated by default from the CPU clock (speed of cycle counter) and
TPROF_HZ, but for some events the value may be too large to be sufficient for
profiling. The event counter can be specified as a ratio to the default or as
an absolute value when configuring the event counter.
- Due to overall changes, API and ABI have been changed. TPROF_VERSION and
TPROF_BACKEND_VERSION were updated.

Output alignement - give lwp 6 characters

Print the path that we failed to open on error

branches: 1.3.2; 1.3.4; 1.3.6;
Finish the Skylake/Kabylake table, and improve the output of "tprof analyze".

Ask for a file path with the "analyze" command, instead of reading stdin.

Merge tpfmt(1) into tprof(8). We want to have access to everything with
only one tool. The code is copied mostly as-is, and the functionality is
available via the "analyze" command.

Eg:
tprof monitor -e llc-misses:k -o myfile.out sleep 20
tprof analyze < myfile.out

Will move soon, I don't like the reading via stdin.

Remove ryo@'s mail addresses.

This needs <stdbool.h> - it used to come from <sys/rbtree.h> (inappropriately)
but no longer (normally). This should unbreak the builds.

Use the default counter if -e argument is not specified.

monitor command:
The default counter is selected if -e argument is not specified.
list command:
Print the name of the default counter for monitor and top command.

use malloc instead of alloca so that SSP works.

branches: 1.7.2;
the "scale" option can be specified in the event name even in "tprof monitor"

- added 'c' command to tprof-top to show/hide event counter.
- column widths were not calculated correctly and sometimes displayed incorrectly.
- use putp() for terminfo str.
- fix build error with llvm.

if column width changes, the screen must be updated.

mainly fixes around display.

- use terminfo
- dynamically adjust column widths
- mode can be changed while running

add accumulative mode. "tprof top -a"

fix build error of printf format

add "top" subcommand to tprof(8)

branches: 1.1.2; 1.1.4;
Add ARMv7 support.

branches: 1.1.2; 1.1.4;
Add ARMv8 support.

branches: 1.3.2; 1.3.4;
Mark tprof_event_init, tprof_event_list, tprof_event_lookup as dead

specialreg.h is x86-specific, don't include it

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).

tprof(8): Add support for Skylake-X and Cascade Lake.

Modify comment. No functional change.

KNF. No functional change.

Add Cometlake support.

branches: 1.15.2;
Add AMD family 19h (zen3 and zen4) support to tprof.

Use lowercase consistently for hexadecimal numbers. No functional change.

KNF. No functional change.

Disable the unsupported events from the bit vector length in EAX.

Add topdown-slots to Intel architectural performance monitoring version 1.

Fix typo in a comment.

Add support for AMD Family 15h

branches: 1.8.2; 1.8.4;
Add support for AMD Family 17h.

tprof: Add goldmont plus support. Tested by msaitoh@n.o, thanks.

tprof: Add goldmont support.

I tested on Atom C3558 (Denverton).

tprof: Add silvermont, airmont support.

I tested on Atom C2758 (Rangeley).

branches: 1.4.2;
Finish the Skylake/Kabylake table, and improve the output of "tprof analyze".

Skylake/Kabylake are family 6, so add a check for that. While here improve
the layout of "tprof list".

Inline the values in amd_f10h_names[], we're not going to use defines for
each CPU model found in the wild.

Revamp tprof.

Rewrite the Intel backend to use the generic PMC interface, which is
available on all Intel CPUs. Synchronize the AMD backend with the new
interface.

The kernel identifies the PMC interface, and gives its id to userland.
Userland then queries the events itself (via cpuid etc). These events
depend on the PMC interface.

The tprof utility is rewritten to allow the user to choose which event
to count (which was not possible until now, the event was hardcoded in
the backend). The command line format is based on usr.bin/pmc, eg:

tprof -e llc-misses:k -o output sleep 20

The man page is updated too, but the arguments will likely change soon
anyway so it doesn't matter a lot.

The tprof utility has three tables:

Intel Architectural Version 1
Intel Skylake/Kabylake
AMD Family 10h

A CPU can support a combination of tables. For example Kabylake has
Intel-Architectural-Version-1 and its own Intel-Kabylake table.

For now the Intel Skylake/Kabylake table contains only one event, just
to demonstrate that the combination of tables works. Tested on an
Intel Core i5 Kabylake.

The code for AMD Family 10h is taken from the code I had written for
usr.bin/pmc. I haven't tested it yet, but it's the same as pmc(1), so
I guess it works as-is.

The whole thing is written in such a way that (I think) it is not
complicated to add more CPU models, and more architectures (other than
x86).