QAPI patches for 2018-12-18

# gpg: Signature made Tue 18 Dec 2018 07:20:11 GMT
# gpg:                using RSA key 3870B400EB918653
# gpg: Good signature from "Markus Armbruster <armbru@redhat.com>"
# gpg:                 aka "Markus Armbruster <armbru@pond.sub.org>"
# Primary key fingerprint: 354B C8B3 D7EB 2A6B 6867  4E5F 3870 B400 EB91 8653

* remotes/armbru/tags/pull-qapi-2018-12-18:
  qapi: fix flat union on uncovered branches conditionals
  qmp hmp: Make system_wakeup check wake-up support and run state
  qga: update guest-suspend-ram and guest-suspend-hybrid descriptions
  qmp: query-current-machine with wakeup-suspend-support
  qmp: Split ShutdownCause host-qmp into quit and system-reset
  qmp: Add reason to SHUTDOWN and RESET events
  qapi: Turn ShutdownCause into QAPI enum
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

- Replace global_qtest in some tests
- Exit boot-serial-test loop if child dies
- Sanitize verbose output in biot-tables-test

# gpg: Signature made Mon 17 Dec 2018 16:08:07 GMT
# gpg:                using RSA key 2ED9D774FE702DB5
# gpg: Good signature from "Thomas Huth <th.huth@gmx.de>"
# gpg:                 aka "Thomas Huth <thuth@redhat.com>"
# gpg:                 aka "Thomas Huth <huth@tuxfamily.org>"
# gpg:                 aka "Thomas Huth <th.huth@posteo.de>"
# Primary key fingerprint: 27B8 8847 EEE0 2501 18F3  EAB9 2ED9 D774 FE70 2DB5

* remotes/huth-gitlab/tags/pull-request-2018-12-17:
  tests/bios-tables-test: Sanitize test verbose output
  tests: acpi: remove not used ACPI_READ_GENERIC_ADDRESS macro
  tests: Exit boot-serial-test loop if child dies
  tests/pxe: Make test independent of global_qtest
  tests/prom-env: Make test independent of global_qtest
  tests/machine-none: Make test independent of global_qtest
  tests/test-filter: Make tests independent of global_qtest
  tests/boot-serial: Get rid of global_qtest variable
  tests/pvpanic: Make the pvpanic test independent of global_qtest
  tests/vmgenid: Make test independent of global_qtest
  tests/acpi-utils: Drop dependence on global_qtest
  ivshmem-test: Drop dependence on global_qtest
  tests/libqos/pci: Make PCI access functions independent of global_qtest
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

Default branches variant should use the member conditional.

This fixes compilation with --disable-replication.

Fixes: 335d10cdSigned-off-by: NMarc-André Lureau <marcandre.lureau@redhat.com>
Message-Id: <20181217204046.14861-1-marcandre.lureau@redhat.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
[Long line wrapped]
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

The qmp/hmp command 'system_wakeup' is simply a direct call to
'qemu_system_wakeup_request' from vl.c. This function verifies if
runstate is SUSPENDED and if the wake up reason is valid before
proceeding. However, no error or warning is thrown if any of those
pre-requirements isn't met. There is no way for the caller to
differentiate between a successful wakeup or an error state caused
when trying to wake up a guest that wasn't suspended.

This means that system_wakeup is silently failing, which can be
considered a bug. Adding error handling isn't an API break in this
case - applications that didn't check the result will remain broken,
the ones that check it will have a chance to deal with it.

Adding to that, the commit before previous created a new QMP API called
query-current-machine, with a new flag called wakeup-suspend-support,
that indicates if the guest has the capability of waking up from suspended
state. Although such guest will never reach SUSPENDED state and erroring
it out in this scenario would suffice, it is more informative for the user
to differentiate between a failure because the guest isn't suspended versus
a failure because the guest does not have support for wake up at all.

All this considered, this patch changes qmp_system_wakeup to check if
the guest is capable of waking up from suspend, and if it is suspended.
After this patch, this is the output of system_wakeup in a guest that
does not have wake-up from suspend support (ppc64):

(qemu) system_wakeup
wake-up from suspend is not supported by this guest
(qemu)

And this is the output of system_wakeup in a x86 guest that has the
support but isn't suspended:

(qemu) system_wakeup
Unable to wake up: guest is not in suspended state
(qemu)
Reported-by: NBalamuruhan S <bala24@linux.vnet.ibm.com>
Signed-off-by: NDaniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20181205194701.17836-4-danielhb413@gmail.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
Acked-by: NEduardo Habkost <ehabkost@redhat.com>
Reviewed-by: NMichael S. Tsirkin <mst@redhat.com>
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

This patch updates the descriptions of 'guest-suspend-ram' and
'guest-suspend-hybrid' to mention that both commands relies now
on the proper support for wake up from suspend, retrieved by the
'wakeup-suspend-support' attribute of the 'query-current-machine'
QMP command.
Reported-by: NBalamuruhan S <bala24@linux.vnet.ibm.com>
Signed-off-by: NDaniel Henrique Barboza <danielhb413@gmail.com>
Reviewed-by: NMichael Roth <mdroth@linux.vnet.ibm.com>
Message-Id: <20181205194701.17836-3-danielhb413@gmail.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
Acked-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

When issuing the qmp/hmp 'system_wakeup' command, what happens in a
nutshell is:

- qmp_system_wakeup_request set runstate to RUNNING, sets a wakeup_reason
and notify the event
- in the main_loop, all vcpus are paused, a system reset is issued, all
subscribers of wakeup_notifiers receives a notification, vcpus are then
resumed and the wake up QAPI event is fired

Note that this procedure alone doesn't ensure that the guest will awake
from SUSPENDED state - the subscribers of the wake up event must take
action to resume the guest, otherwise the guest will simply reboot. At
this moment, only the ACPI machines via acpi_pm1_cnt_init and xen_hvm_init
have wake-up from suspend support.

However, only the presence of 'system_wakeup' is required for QGA to
support 'guest-suspend-ram' and 'guest-suspend-hybrid' at this moment.
This means that the user/management will expect to suspend the guest using
one of those suspend commands and then resume execution using system_wakeup,
regardless of the support offered in system_wakeup in the first place.

This patch creates a new API called query-current-machine [1], that holds
a new flag called 'wakeup-suspend-support' that indicates if the guest
supports wake up from suspend via system_wakeup. The machine is considered
to implement wake-up support if a call to a new 'qemu_register_wakeup_support'
is made during its init, as it is now being done inside acpi_pm1_cnt_init
and xen_hvm_init. This allows for any other machine type to declare wake-up
support regardless of ACPI state or wakeup_notifiers subscription, making easier
for newer implementations that might have their own mechanisms in the future.

This is the expected output of query-current-machine when running a x86
guest:

{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": true}}

Running the same x86 guest, but with the --no-acpi option:

{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": false}}

This is the output when running a pseries guest:

{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": false}}

With this extra tool, management can avoid situations where a guest
that does not have proper suspend/wake capabilities ends up in
inconsistent state (e.g.
https://github.com/open-power-host-os/qemu/issues/31).

[1] the decision of creating the query-current-machine API is based
on discussions in the QEMU mailing list where it was decided that
query-target wasn't a proper place to store the wake-up flag, neither
was query-machines because this isn't a static property of the
machine object. This new API can then be used to store other
dynamic machine properties that are scattered around the code
ATM. More info at:
https://lists.gnu.org/archive/html/qemu-devel/2018-05/msg04235.htmlReported-by: NBalamuruhan S <bala24@linux.vnet.ibm.com>
Signed-off-by: NDaniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20181205194701.17836-2-danielhb413@gmail.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
Acked-by: NEduardo Habkost <ehabkost@redhat.com>
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

It is interesting to know whether the shutdown cause was 'quit' or
'reset', especially when using "--no-reboot". In that case, a management
layer can now determine if the guest wanted a reboot or shutdown, and
can act accordingly.

Changes the output of the reason in the iotests from 'host-qmp' to
'host-qmp-quit'. This does not break compatibility because
the field was introduced in the same version.
Signed-off-by: NDominik Csapak <d.csapak@proxmox.com>
Message-Id: <20181205110131.23049-4-d.csapak@proxmox.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
[Commit message tweaked]
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

This makes it possible to determine what the exact reason was for
a RESET or a SHUTDOWN. A management layer might need the specific reason
of those events to determine which cleanups or other actions it needs to do.

This patch also updates the iotests to the new expected output that includes
the reason.
Signed-off-by: NDominik Csapak <d.csapak@proxmox.com>
Message-Id: <20181205110131.23049-3-d.csapak@proxmox.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
[Commit message tweaked]
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

Needed so the patch after next can add ShutdownCause to QMP events
SHUTDOWN and RESET.
Signed-off-by: NDominik Csapak <d.csapak@proxmox.com>
Message-Id: <20181205110131.23049-2-d.csapak@proxmox.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>

Hardfloat + maintainers and gitdm

# gpg: Signature made Mon 17 Dec 2018 10:55:19 GMT
# gpg:                using RSA key FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>"
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-hardfloat-and-gitdm-171218-3:
  hardfloat: implement float32/64 comparison
  hardfloat: implement float32/64 square root
  hardfloat: implement float32/64 fused multiply-add
  hardfloat: implement float32/64 division
  hardfloat: implement float32/64 multiplication
  hardfloat: implement float32/64 addition and subtraction
  fpu: introduce hardfloat
  tests/fp: add fp-bench
  softfloat: add float{32,64}_is_zero_or_normal
  softfloat: rename canonicalize to sf_canonicalize
  target/tricore: use float32_is_denormal
  softfloat: add float{32,64}_is_{de,}normal
  fp-test: pick TARGET_ARM to get its specialization
  MAINTAINERS: update status of FPU emulation
  contrib: add a basic gitdm config
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

Fix the extraneous extra blank lines in the test output when running with V=1.

Before:

    TEST: tests/bios-tables-test... (pid=25678)
      /i386/acpi/piix4:
    Looking for expected file 'tests/acpi-test-data/pc/DSDT'

    Using expected file 'tests/acpi-test-data/pc/DSDT'

    Looking for expected file 'tests/acpi-test-data/pc/FACP'

    Using expected file 'tests/acpi-test-data/pc/FACP'

    Looking for expected file 'tests/acpi-test-data/pc/APIC'

    Using expected file 'tests/acpi-test-data/pc/APIC'

    Looking for expected file 'tests/acpi-test-data/pc/HPET'

    Using expected file 'tests/acpi-test-data/pc/HPET'
    OK

After:

    TEST: tests/bios-tables-test... (pid=667)
      /i386/acpi/piix4:
    Looking for expected file 'tests/acpi-test-data/pc/DSDT'
    Using expected file 'tests/acpi-test-data/pc/DSDT'
    Looking for expected file 'tests/acpi-test-data/pc/FACP'
    Using expected file 'tests/acpi-test-data/pc/FACP'
    Looking for expected file 'tests/acpi-test-data/pc/APIC'
    Using expected file 'tests/acpi-test-data/pc/APIC'
    Looking for expected file 'tests/acpi-test-data/pc/HPET'
    Using expected file 'tests/acpi-test-data/pc/HPET'
    OK
Suggested-by: NPeter Maydell <peter.maydell@linaro.org>
Signed-off-by: NPhilippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: NIgor Mammedov <imammedo@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

Signed-off-by: NIgor Mammedov <imammedo@redhat.com>
Reviewed-by: NPhilippe Mathieu-Daudé <philmd@redhat.com>
[thuth: Fixed conflicts with additional "qts" parameter]
Signed-off-by: NThomas Huth <thuth@redhat.com>

There's no point in waiting 5 full minutes when there will be
no more output.  Compute timeout based on elapsed wall clock
time instead of N * delays, as the delay is a minimum sleep time.

Cc: Thomas Huth <thuth@redhat.com>
Cc: Laurent Vivier <lvivier@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NRichard Henderson <richard.henderson@linaro.org>
Reviewed-by: NPhilippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: NWainer dos Santos Moschetta <wainersm@redhat.com>
[thuth: Replaced global_qtest with local qts variable]
Signed-off-by: NThomas Huth <thuth@redhat.com>

global_qtest is not really required here, since boot_sector_test()
is already independent from that global variable.
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

global_qtest is only needed here for one readl(). Let's replace it
with qtest_readl() and we can remove the global_qtest variable here.
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

Apart from using qmp() in one spot, this test does not have any
dependencies to the global_qtest variable, so we can simply get
rid of it here by replacing the qmp() with qtest_qmp().
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

Apart from using qmp() in the qmp_discard_response() macro, these
tests do not have any dependencies to the global_qtest variable,
so we can simply get rid of it here by replacing the qmp() with
qtest_qmp() in the macro.
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

The test does not use any of the functions that require global_qtest,
so we can simply get rid of this global variable here.
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

We want to get rid of global_qtest in the long run, thus do not
use the wrappers like inb() and outb() here anymore.
Reviewed-by: NEric Blake <eblake@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

The biggest part has already been done in the previous patch, we now
only have to replace some few qmp() and readb() calls with the
corresponding qtest_*() functions to get there.
Acked-by: NIgor Mammedov <imammedo@redhat.com>
Signed-off-by: NThomas Huth <thuth@redhat.com>

As a general rule, we prefer avoiding implicit global state
because it makes code harder to safely copy and paste without
thinking about the global state.  Adjust the helper code to
use explicit state instead, and update all callers.

bios-tables-test no longer depends on global_qtest, now that it
passes explicit state through the testsuite data; an assert
proves this fact (although we will get rid of it later, once
global_qtest is gone).
Signed-off-by: NEric Blake <eblake@redhat.com>
Acked-by: NIgor Mammedov <imammedo@redhat.com>
Tested-by: NIgor Mammedov <imammedo@redhat.com>
[thuth: adapted patch to current master branch]
Signed-off-by: NThomas Huth <thuth@redhat.com>

Managing parallel connections to two different monitors via
the implicit global_qtest makes it hard to copy-and-paste code
to tests that are not aware of the implicit state.  Since we
have already fixed qpci to avoid global_qtest, we can now
simplify by not using global_qtest anywhere in ivshmem-test.

We can assert that the conversion is correct by checking that
global_qtest remains NULL throughout the test (a later patch
that changes global_qtest to not be a public global variable
will drop the assertions).
Signed-off-by: NEric Blake <eblake@redhat.com>
[thuth: Dropped the changes to test_ivshmem_hotplug() - will be fixed later]
Signed-off-by: NThomas Huth <thuth@redhat.com>

QPCIBus already tracks QTestState, so use that state instead of an
implicit reliance on global_qtest.

Based on an earlier patch ("libqos: Use explicit QTestState for pci
operations") from Eric Blake.
Signed-off-by: NThomas Huth <thuth@redhat.com>

- Remove retranslation remenents
- Return success from patch_reloc
- Preserve 32-bit values as zero-extended on x86_64
- Make bswap during memory ops as optional
- Cleanup xxhash
- Revert constant pooling for tcg/sparc/

# gpg: Signature made Mon 17 Dec 2018 03:25:21 GMT
# gpg:                using RSA key 64DF38E8AF7E215F
# gpg: Good signature from "Richard Henderson <richard.henderson@linaro.org>"
# Primary key fingerprint: 7A48 1E78 868B 4DB6 A85A  05C0 64DF 38E8 AF7E 215F

* remotes/rth/tags/pull-tcg-20181216: (33 commits)
  xxhash: match output against the original xxhash32
  include: move exec/tb-hash-xx.h to qemu/xxhash.h
  exec: introduce qemu_xxhash{2,4,5,6,7}
  qht-bench: document -p flag
  tcg: Drop nargs from tcg_op_insert_{before,after}
  tcg/mips: Improve the add2/sub2 command to use TCG_TARGET_REG_BITS
  tcg: Add TCG_TARGET_HAS_MEMORY_BSWAP
  tcg/optimize: Optimize bswap
  tcg: Clean up generic bswap64
  tcg: Clean up generic bswap32
  tcg/i386: Add setup_guest_base_seg for FreeBSD
  tcg/i386: Precompute all guest_base parameters
  tcg/i386: Assume 32-bit values are zero-extended
  tcg/i386: Implement INDEX_op_extr{lh}_i64_i32 for 32-bit guests
  tcg/i386: Propagate is64 to tcg_out_qemu_ld_slow_path
  tcg/i386: Propagate is64 to tcg_out_qemu_ld_direct
  tcg/s390x: Return false on failure from patch_reloc
  tcg/ppc: Return false on failure from patch_reloc
  tcg/arm: Return false on failure from patch_reloc
  tcg/aarch64: Return false on failure from patch_reloc
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

The pkg.mxe.cc package repositories have been down for the last two
weeks causing the builds to fail when shippable re-builds the
containers.

This is really just a sticking plaster until we can get our own docker
hub images properly setup so we can avoid having dependencies on
external repos.
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>
Acked-by: NPhilippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20181214151718.5041-1-alex.bennee@linaro.org
Cc: Philippe Mathieu-Daudé <philmd@redhat.com>
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

Performance results for fp-bench:

Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
cmp-single: 110.98 MFlops
cmp-double: 107.12 MFlops
- after:
cmp-single: 506.28 MFlops
cmp-double: 524.77 MFlops

Note that flattening both eq and eq_signaling versions
would give us extra performance (695v506, 615v524 Mflops
for single/double, respectively) but this would emit two
essentially identical functions for each eq/signaling pair,
which is a waste.

Aggregate performance improvement for the last few patches:
[ all charts in png: https://imgur.com/a/4yV8p ]

1. Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz

                   qemu-aarch64 NBench score; higher is better
                 Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz

  16 +-+-----------+-------------+----===-------+---===-------+-----------+-+
  14 +-+..........................@@@&&.=.......@@@&&.=...................+-+
  12 +-+..........................@.@.&.=.......@.@.&.=.....+befor===     +-+
  10 +-+..........................@.@.&.=.......@.@.&.=.....+ad@@&& =     +-+
   8 +-+.......................$$$%.@.&.=.......@.@.&.=.....+  @@u& =     +-+
   6 +-+............@@@&&=+***##.$%.@.&.=***##$$%+@.&.=..###$$%%@i& =     +-+
   4 +-+.......###$%%.@.&=.*.*.#.$%.@.&.=*.*.#.$%.@.&.=+**.#+$ +@m& =     +-+
   2 +-+.....***.#$.%.@.&=.*.*.#.$%.@.&.=*.*.#.$%.@.&.=.**.#+$+sqr& =     +-+
   0 +-+-----***##$%%@@&&=-***##$$%@@&&==***##$$%@@&&==-**##$$%+cmp==-----+-+
            FOURIER    NEURAL NELU DECOMPOSITION         gmean

                              qemu-aarch64 SPEC06fp (test set) speedup over QEMU 4c2c1015
                                      Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
                                            error bars: 95% confidence interval

  4.5 +-+---+-----+----+-----+-----+-&---+-----+----+-----+-----+-----+----+-----+-----+-----+-----+----+-----+---+-+
    4 +-+..........................+@@+...........................................................................+-+
  3.5 +-+..............%%@&.........@@..............%%@&............................................+++dsub       +-+
  2.5 +-+....&&+.......%%@&.......+%%@..+%%&+..@@&+.%%@&....................................+%%&+.+%@&++%%@&      +-+
    2 +-+..+%%&..+%@&+.%%@&...+++..%%@...%%&.+$$@&..%%@&..%%@&.......+%%&+.%%@&+......+%%@&.+%%&++$$@&++d%@&  %%@&+-+
  1.5 +-+**#$%&**#$@&**#%@&**$%@**#$%@**#$%&**#$@&**$%@&*#$%@**#$%@**#$%&**#%@&**$%@&*#$%@**#$%&**#$@&*+f%@&**$%@&+-+
  0.5 +-+**#$%&**#$@&**#%@&**$%@**#$%@**#$%&**#$@&**$%@&*#$%@**#$%@**#$%&**#%@&**$%@&*#$%@**#$%&**#$@&+sqr@&**$%@&+-+
    0 +-+**#$%&**#$@&**#%@&**$%@**#$%@**#$%&**#$@&**$%@&*#$%@**#$%@**#$%&**#%@&**$%@&*#$%@**#$%&**#$@&*+cmp&**$%@&+-+
  410.bw416.gam433.434.z435.436.cac437.lesli444.447.de450.so453454.ca459.GemsF465.tont470.lb4482.sphinxgeomean

2. Host: ARM Aarch64 A57 @ 2.4GHz

                    qemu-aarch64 NBench score; higher is better
                 Host: Applied Micro X-Gene, Aarch64 A57 @ 2.4 GHz

    5 +-+-----------+-------------+-------------+-------------+-----------+-+
  4.5 +-+........................................@@@&==...................+-+
  3 4 +-+..........................@@@&==........@.@&.=.....+before       +-+
    3 +-+..........................@.@&.=........@.@&.=.....+ad@@@&==     +-+
  2.5 +-+.....................##$$%%.@&.=........@.@&.=.....+  @m@& =     +-+
    2 +-+............@@@&==.***#.$.%.@&.=.***#$$%%.@&.=.***#$$%%d@& =     +-+
  1.5 +-+.....***#$$%%.@&.=.*.*#.$.%.@&.=.*.*#.$.%.@&.=.*.*#+$ +f@& =     +-+
  0.5 +-+.....*.*#.$.%.@&.=.*.*#.$.%.@&.=.*.*#.$.%.@&.=.*.*#+$+sqr& =     +-+
    0 +-+-----***#$$%%@@&==-***#$$%%@@&==-***#$$%%@@&==-***#$$%+cmp==-----+-+
             FOURIER    NEURAL NLU DECOMPOSITION         gmean
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Performance results for fp-bench:

Host: Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
sqrt-single: 42.30 MFlops
sqrt-double: 22.97 MFlops
- after:
sqrt-single: 311.42 MFlops
sqrt-double: 311.08 MFlops

Here USE_FP makes a huge difference for f64's, with throughput
going from ~200 MFlops to ~300 MFlops.
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Performance results for fp-bench:

1. Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
fma-single: 74.73 MFlops
fma-double: 74.54 MFlops
- after:
fma-single: 203.37 MFlops
fma-double: 169.37 MFlops

2. ARM Aarch64 A57 @ 2.4GHz
- before:
fma-single: 23.24 MFlops
fma-double: 23.70 MFlops
- after:
fma-single: 66.14 MFlops
fma-double: 63.10 MFlops

3. IBM POWER8E @ 2.1 GHz
- before:
fma-single: 37.26 MFlops
fma-double: 37.29 MFlops
- after:
fma-single: 48.90 MFlops
fma-double: 59.51 MFlops

Here having 3FP64 set to 1 pays off for x86_64:
[1] 170.15 vs [0] 153.12 MFlops
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Performance results for fp-bench:

1. Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
div-single: 34.84 MFlops
div-double: 34.04 MFlops
- after:
div-single: 275.23 MFlops
div-double: 216.38 MFlops

2. ARM Aarch64 A57 @ 2.4GHz
- before:
div-single: 9.33 MFlops
div-double: 9.30 MFlops
- after:
div-single: 51.55 MFlops
div-double: 15.09 MFlops

3. IBM POWER8E @ 2.1 GHz
- before:
div-single: 25.65 MFlops
div-double: 24.91 MFlops
- after:
div-single: 96.83 MFlops
div-double: 31.01 MFlops

Here setting 2FP64_USE_FP to 1 pays off for x86_64:
[1] 215.97 vs [0] 62.15 MFlops
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Performance results for fp-bench:

1. Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
mul-single: 126.91 MFlops
mul-double: 118.28 MFlops
- after:
mul-single: 258.02 MFlops
mul-double: 197.96 MFlops

2. ARM Aarch64 A57 @ 2.4GHz
- before:
mul-single: 37.42 MFlops
mul-double: 38.77 MFlops
- after:
mul-single: 73.41 MFlops
mul-double: 76.93 MFlops

3. IBM POWER8E @ 2.1 GHz
- before:
mul-single: 58.40 MFlops
mul-double: 59.33 MFlops
- after:
mul-single: 60.25 MFlops
mul-double: 94.79 MFlops
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Performance results (single and double precision) for fp-bench:

1. Intel(R) Core(TM) i7-6700K CPU @ 4.00GHz
- before:
add-single: 135.07 MFlops
add-double: 131.60 MFlops
sub-single: 130.04 MFlops
sub-double: 133.01 MFlops
- after:
add-single: 443.04 MFlops
add-double: 301.95 MFlops
sub-single: 411.36 MFlops
sub-double: 293.15 MFlops

2. ARM Aarch64 A57 @ 2.4GHz
- before:
add-single: 44.79 MFlops
add-double: 49.20 MFlops
sub-single: 44.55 MFlops
sub-double: 49.06 MFlops
- after:
add-single: 93.28 MFlops
add-double: 88.27 MFlops
sub-single: 91.47 MFlops
sub-double: 88.27 MFlops

3. IBM POWER8E @ 2.1 GHz
- before:
add-single: 72.59 MFlops
add-double: 72.27 MFlops
sub-single: 75.33 MFlops
sub-double: 70.54 MFlops
- after:
add-single: 112.95 MFlops
add-double: 201.11 MFlops
sub-single: 116.80 MFlops
sub-double: 188.72 MFlops

Note that the IBM and ARM machines benefit from having
HARDFLOAT_2F{32,64}_USE_FP set to 0. Otherwise their performance
can suffer significantly:
- IBM Power8:
add-single: [1] 54.94 vs [0] 116.37 MFlops
add-double: [1] 58.92 vs [0] 201.44 MFlops
- Aarch64 A57:
add-single: [1] 80.72 vs [0] 93.24 MFlops
add-double: [1] 82.10 vs [0] 88.18 MFlops

On the Intel machine, having 2F64 set to 1 pays off, but it
doesn't for 2F32:
- Intel i7-6700K:
add-single: [1] 285.79 vs [0] 426.70 MFlops
add-double: [1] 302.15 vs [0] 278.82 MFlops
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

The appended paves the way for leveraging the host FPU for a subset
of guest FP operations. For most guest workloads (e.g. FP flags
aren't ever cleared, inexact occurs often and rounding is set to the
default [to nearest]) this will yield sizable performance speedups.

The approach followed here avoids checking the FP exception flags register.
See the added comment for details.

This assumes that QEMU is running on an IEEE754-compliant FPU and
that the rounding is set to the default (to nearest). The
implementation-dependent specifics of the FPU should not matter; things
like tininess detection and snan representation are still dealt with in
soft-fp. However, this approach will break on most hosts if we compile
QEMU with flags that break IEEE compatibility. There is no way to detect
all of these flags at compilation time, but at least we check for
-ffast-math (which defines __FAST_MATH__) and disable hardfloat
(plus emit a #warning) when it is set.

This patch just adds common code. Some operations will be migrated
to hardfloat in subsequent patches to ease bisection.

Note: some architectures (at least PPC, there might be others) clear
the status flags passed to softfloat before most FP operations. This
precludes the use of hardfloat, so to avoid introducing a performance
regression for those targets, we add a flag to disable hardfloat.
In the long run though it would be good to fix the targets so that
at least the inexact flag passed to softfloat is indeed sticky.
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

These microbenchmarks will allow us to measure the performance impact of
FP emulation optimizations. Note that we can measure both directly the impact
on the softfloat functions (with "-t soft"), or the impact on an
emulated workload (call with "-t host" and run under qemu user-mode).
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

These will gain some users very soon.
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

glibc >= 2.25 defines canonicalize in commit eaf5ad0
(Add canonicalize, canonicalizef, canonicalizel., 2016-10-26).

Given that we'll be including <math.h> soon, prepare
for this by prefixing our canonicalize() with sf_ to avoid
clashing with the libc's canonicalize().
Reported-by: NBastian Koppelmann <kbastian@mail.uni-paderborn.de>
Tested-by: NBastian Koppelmann <kbastian@mail.uni-paderborn.de>
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Reviewed-by: NBastian Koppelmann <kbastian@mail.uni-paderborn.de>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

This paves the way for upcoming work.
Reviewed-by: NBastian Koppelmann <kbastian@mail.uni-paderborn.de>
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

This gets rid of the muladd errors due to not raising the invalid flag.

- Before:
Errors found in f64_mulAdd, rounding near_even, tininess before rounding:
+000.0000000000000  +7FF.0000000000000  +7FF.FFFFFFFFFFFFF
        => +7FF.FFFFFFFFFFFFF .....  expected -7FF.FFFFFFFFFFFFF v....
[...]

- After:
In 6133248 tests, no errors found in f64_mulAdd, rounding near_even, tininess before rounding.
[...]
Reviewed-by: NAlex Bennée <alex.bennee@linaro.org>
Tested-by: NAlex Bennée <alex.bennee@linaro.org>
Signed-off-by: NEmilio G. Cota <cota@braap.org>
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>

Given I've spent a fair amount of time around this code now I'm
putting myself forward as a maintainer. Also given that the code has
been extensively re-written and has testing and new incoming features
it is probably more than just Odd Fixes.
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>
Reviewed-by: NPhilippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: NRichard Henderson <richard.henderson@linaro.org>

This is a QEMU specific version of a gitdm config for generating
reports on the contributor base of the project. I've added enough
group maps and domain aliases to ensure the current top ten is as
reflective as it can be. As of this commit running:

  git log --numstat --since "Last Year" | gitdm -n -l 10

Reports:

  Top changeset contributors by employer
  Red Hat                   3172 (44.3%)
  Linaro                    1153 (16.1%)
  (None)                     549 (7.7%)
  IBM                        348 (4.9%)
  Academics (various)        170 (2.4%)
  Virtuozzo                  168 (2.3%)
  Wave Computing             118 (1.6%)
  Xilinx                     102 (1.4%)
  Igalia                      93 (1.3%)
  Cadence Design Systems      88 (1.2%)

  Top lines changed by employer
  Red Hat                   144092 (28.1%)
  Cadence Design Systems    126554 (24.6%)
  Linaro                    77480 (15.1%)
  Wave Computing            33134 (6.5%)
  SiFive                    14392 (2.8%)
  IBM                       12219 (2.4%)
  (None)                    11948 (2.3%)
  Academics (various)       10447 (2.0%)
  Virtuozzo                 10445 (2.0%)
  CodeWeavers               9179 (1.8%)
Signed-off-by: NAlex Bennée <alex.bennee@linaro.org>
Reviewed-by: NDaniel P. Berrangé <berrange@redhat.com>
Reviewed-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NAleksandar Markovic <amarkovic@wavecomp.com>