1
The following changes since commit 61fee7f45955cd0bf9b79be9fa9c7ebabb5e6a85:
1
Patches for rc1: nothing major, just some minor bugfixes and
2
code cleanups.
2
3
3
Merge remote-tracking branch 'remotes/philmd-gitlab/tags/acceptance-testing-20200622' into staging (2020-06-22 20:50:10 +0100)
4
-- PMM
5
6
The following changes since commit f7e1914adad8885a5d4c70239ab90d901ed97e9f:
7
8
Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20201109' into staging (2020-11-10 09:24:56 +0000)
4
9
5
are available in the Git repository at:
10
are available in the Git repository at:
6
11
7
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200623
12
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201110
8
13
9
for you to fetch changes up to 539533b85fbd269f777bed931de8ccae1dd837e9:
14
for you to fetch changes up to b6c56c8a9a4064ea783f352f43c5df6231a110fa:
10
15
11
arm/virt: Add memory hot remove support (2020-06-23 11:39:48 +0100)
16
target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check (2020-11-10 11:03:48 +0000)
12
17
13
----------------------------------------------------------------
18
----------------------------------------------------------------
14
target-arm queue:
19
target-arm queue:
15
* util/oslib-posix : qemu_init_exec_dir implementation for Mac
20
* hw/arm/Kconfig: ARM_V7M depends on PTIMER
16
* target/arm: Last parts of neon decodetree conversion
21
* Minor coding style fixes
17
* hw/arm/virt: Add 5.0 HW compat props
22
* docs: add some notes on the sbsa-ref machine
18
* hw/watchdog/cmsdk-apb-watchdog: Add trace event for lock status
23
* hw/arm/virt: Remove dependency on Cortex-A15 MPCore peripherals
19
* mps2: Add CMSDK APB watchdog, FPGAIO block, S2I devices and I2C devices
24
* target/arm: Fix neon VTBL/VTBX for len > 1
20
* mps2: Add some unimplemented-device stubs for audio and GPIO
25
* hw/arm/armsse: Correct expansion MPC interrupt lines
21
* mps2-tz: Use the ARM SBCon two-wire serial bus interface
26
* hw/misc/stm32f2xx_syscfg: Remove extraneous IRQ
22
* target/arm: Check supported KVM features globally (not per vCPU)
27
* hw/arm/nseries: Remove invalid/unnecessary n8x0_uart_setup()
23
* tests/qtest/arm-cpu-features: Add feature setting tests
28
* hw/arm/musicpal: Don't connect two qemu_irqs directly to the same input
24
* arm/virt: Add memory hot remove support
29
* hw/arm/musicpal: Only use qdev_get_gpio_in() when necessary
30
* hw/arm/nseries: Check return value from load_image_targphys()
31
* tests/qtest/npcm7xx_rng-test: count runs properly
32
* target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check
25
33
26
----------------------------------------------------------------
34
----------------------------------------------------------------
27
Andrew Jones (2):
35
Alex Bennée (1):
28
hw/arm/virt: Add 5.0 HW compat props
36
docs: add some notes on the sbsa-ref machine
29
tests/qtest/arm-cpu-features: Add feature setting tests
30
37
31
David CARLIER (1):
38
AlexChen (1):
32
util/oslib-posix : qemu_init_exec_dir implementation for Mac
39
ssi: Fix bad printf format specifiers
33
40
34
Peter Maydell (23):
41
Andrew Jones (1):
35
target/arm: Convert Neon 2-reg-misc VREV64 to decodetree
42
hw/arm/Kconfig: ARM_V7M depends on PTIMER
36
target/arm: Convert Neon 2-reg-misc pairwise ops to decodetree
37
target/arm: Convert VZIP, VUZP to decodetree
38
target/arm: Convert Neon narrowing moves to decodetree
39
target/arm: Convert Neon 2-reg-misc VSHLL to decodetree
40
target/arm: Convert Neon VCVT f16/f32 insns to decodetree
41
target/arm: Convert vectorised 2-reg-misc Neon ops to decodetree
42
target/arm: Convert Neon 2-reg-misc crypto operations to decodetree
43
target/arm: Rename NeonGenOneOpFn to NeonGenOne64OpFn
44
target/arm: Fix capitalization in NeonGenTwo{Single, Double}OPFn typedefs
45
target/arm: Make gen_swap_half() take separate src and dest
46
target/arm: Convert Neon 2-reg-misc VREV32 and VREV16 to decodetree
47
target/arm: Convert remaining simple 2-reg-misc Neon ops
48
target/arm: Convert Neon VQABS, VQNEG to decodetree
49
target/arm: Convert simple fp Neon 2-reg-misc insns
50
target/arm: Convert Neon 2-reg-misc fp-compare-with-zero insns to decodetree
51
target/arm: Convert Neon 2-reg-misc VRINT insns to decodetree
52
target/arm: Convert Neon 2-reg-misc VCVT insns to decodetree
53
target/arm: Convert Neon VSWP to decodetree
54
target/arm: Convert Neon VTRN to decodetree
55
target/arm: Move some functions used only in translate-neon.inc.c to that file
56
target/arm: Remove unnecessary gen_io_end() calls
57
target/arm: Remove dead code relating to SABA and UABA
58
43
59
Philippe Mathieu-Daudé (15):
44
Havard Skinnemoen (1):
60
hw/watchdog/cmsdk-apb-watchdog: Add trace event for lock status
45
tests/qtest/npcm7xx_rng-test: count runs properly
61
hw/i2c/versatile_i2c: Add definitions for register addresses
62
hw/i2c/versatile_i2c: Add SCL/SDA definitions
63
hw/i2c: Add header for ARM SBCon two-wire serial bus interface
64
hw/arm: Use TYPE_VERSATILE_I2C instead of hardcoded string
65
hw/arm/mps2: Document CMSDK/FPGA APB subsystem sections
66
hw/arm/mps2: Rename CMSDK AHB peripheral region
67
hw/arm/mps2: Add CMSDK APB watchdog device
68
hw/arm/mps2: Add CMSDK AHB GPIO peripherals as unimplemented devices
69
hw/arm/mps2: Map the FPGA I/O block
70
hw/arm/mps2: Add SPI devices
71
hw/arm/mps2: Add I2C devices
72
hw/arm/mps2: Add audio I2S interface as unimplemented device
73
hw/arm/mps2-tz: Use the ARM SBCon two-wire serial bus interface
74
target/arm: Check supported KVM features globally (not per vCPU)
75
46
76
Shameer Kolothum (1):
47
Peter Maydell (2):
77
arm/virt: Add memory hot remove support
48
hw/arm/nseries: Check return value from load_image_targphys()
49
target/arm/translate-neon.c: Handle VTBL UNDEF case before VFP access check
78
50
79
include/hw/i2c/arm_sbcon_i2c.h | 35 ++
51
Philippe Mathieu-Daudé (6):
80
target/arm/cpu.h | 2 +-
52
hw/arm/virt: Remove dependency on Cortex-A15 MPCore peripherals
81
target/arm/kvm_arm.h | 21 +-
53
hw/arm/armsse: Correct expansion MPC interrupt lines
82
target/arm/translate.h | 8 +-
54
hw/misc/stm32f2xx_syscfg: Remove extraneous IRQ
83
target/arm/neon-dp.decode | 106 ++++
55
hw/arm/nseries: Remove invalid/unnecessary n8x0_uart_setup()
84
hw/acpi/generic_event_device.c | 29 +
56
hw/arm/musicpal: Don't connect two qemu_irqs directly to the same input
85
hw/arm/mps2-tz.c | 23 +-
57
hw/arm/musicpal: Only use qdev_get_gpio_in() when necessary
86
hw/arm/mps2.c | 65 ++-
87
hw/arm/realview.c | 3 +-
88
hw/arm/versatilepb.c | 3 +-
89
hw/arm/vexpress.c | 3 +-
90
hw/arm/virt.c | 63 +-
91
hw/i2c/versatile_i2c.c | 38 +-
92
hw/watchdog/cmsdk-apb-watchdog.c | 1 +
93
target/arm/cpu.c | 2 +-
94
target/arm/cpu64.c | 10 +-
95
target/arm/kvm.c | 4 +-
96
target/arm/kvm64.c | 14 +-
97
target/arm/translate-a64.c | 20 +-
98
target/arm/translate-neon.inc.c | 1191 +++++++++++++++++++++++++++++++++++++-
99
target/arm/translate-vfp.inc.c | 7 +-
100
target/arm/translate.c | 1064 +---------------------------------
101
tests/qtest/arm-cpu-features.c | 38 +-
102
util/oslib-posix.c | 15 +
103
MAINTAINERS | 1 +
104
hw/arm/Kconfig | 8 +-
105
hw/watchdog/trace-events | 1 +
106
27 files changed, 1624 insertions(+), 1151 deletions(-)
107
create mode 100644 include/hw/i2c/arm_sbcon_i2c.h
108
58
59
Richard Henderson (1):
60
target/arm: Fix neon VTBL/VTBX for len > 1
61
62
Xinhao Zhang (3):
63
target/arm: add spaces around operator
64
target/arm: Don't use '#' flag of printf format
65
target/arm: add space before the open parenthesis '('
66
67
docs/system/arm/sbsa.rst | 32 ++++++++++++++++++++++
68
docs/system/target-arm.rst | 1 +
69
include/hw/misc/stm32f2xx_syscfg.h | 2 --
70
target/arm/helper.h | 2 +-
71
hw/arm/armsse.c | 3 +-
72
hw/arm/musicpal.c | 40 +++++++++++++++++----------
73
hw/arm/nseries.c | 26 ++++++++----------
74
hw/arm/stm32f205_soc.c | 1 -
75
hw/misc/stm32f2xx_syscfg.c | 2 --
76
hw/ssi/imx_spi.c | 2 +-
77
hw/ssi/xilinx_spi.c | 2 +-
78
target/arm/arch_dump.c | 8 +++---
79
target/arm/arm-semi.c | 8 +++---
80
target/arm/helper.c | 2 +-
81
target/arm/op_helper.c | 23 +++++++++-------
82
target/arm/translate-a64.c | 4 +--
83
target/arm/translate.c | 2 +-
84
tests/qtest/npcm7xx_rng-test.c | 2 +-
85
hw/arm/Kconfig | 3 +-
86
target/arm/translate-neon.c.inc | 56 ++++++++++++++------------------------
87
20 files changed, 123 insertions(+), 98 deletions(-)
88
create mode 100644 docs/system/arm/sbsa.rst
89
diff view generated by jsdifflib
Deleted patch
1
From: Andrew Jones <drjones@redhat.com>
2
1
3
Cc: Cornelia Huck <cohuck@redhat.com>
4
Signed-off-by: Andrew Jones <drjones@redhat.com>
5
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
6
Message-id: 20200616140803.25515-1-drjones@redhat.com
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
---
9
hw/arm/virt.c | 1 +
10
1 file changed, 1 insertion(+)
11
12
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
13
index XXXXXXX..XXXXXXX 100644
14
--- a/hw/arm/virt.c
15
+++ b/hw/arm/virt.c
16
@@ -XXX,XX +XXX,XX @@ DEFINE_VIRT_MACHINE_AS_LATEST(5, 1)
17
static void virt_machine_5_0_options(MachineClass *mc)
18
{
19
virt_machine_5_1_options(mc);
20
+ compat_props_add(mc->compat_props, hw_compat_5_0, hw_compat_5_0_len);
21
}
22
DEFINE_VIRT_MACHINE(5, 0)
23
24
--
25
2.20.1
26
27
diff view generated by jsdifflib
Deleted patch
1
From: David CARLIER <devnexen@gmail.com>
2
1
3
From 3025a0ce3fdf7d3559fc35a52c659f635f5c750c Mon Sep 17 00:00:00 2001
4
From: David Carlier <devnexen@gmail.com>
5
Date: Tue, 26 May 2020 21:35:27 +0100
6
Subject: [PATCH] util/oslib-posix : qemu_init_exec_dir implementation for Mac
7
8
Using dyld API to get the full path of the current process.
9
10
Signed-off-by: David Carlier <devnexen@gmail.com>
11
Message-id: CA+XhMqxwC10XHVs4Z-JfE0-WLAU3ztDuU9QKVi31mjr59HWCxg@mail.gmail.com
12
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
---
15
util/oslib-posix.c | 15 +++++++++++++++
16
1 file changed, 15 insertions(+)
17
18
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
19
index XXXXXXX..XXXXXXX 100644
20
--- a/util/oslib-posix.c
21
+++ b/util/oslib-posix.c
22
@@ -XXX,XX +XXX,XX @@
23
#include <lwp.h>
24
#endif
25
26
+#ifdef __APPLE__
27
+#include <mach-o/dyld.h>
28
+#endif
29
+
30
#include "qemu/mmap-alloc.h"
31
32
#ifdef CONFIG_DEBUG_STACK_USAGE
33
@@ -XXX,XX +XXX,XX @@ void qemu_init_exec_dir(const char *argv0)
34
p = buf;
35
}
36
}
37
+#elif defined(__APPLE__)
38
+ {
39
+ char fpath[PATH_MAX];
40
+ uint32_t len = sizeof(fpath);
41
+ if (_NSGetExecutablePath(fpath, &len) == 0) {
42
+ p = realpath(fpath, buf);
43
+ if (!p) {
44
+ return;
45
+ }
46
+ }
47
+ }
48
#endif
49
/* If we don't have any way of figuring out the actual executable
50
location then try argv[0]. */
51
--
52
2.20.1
53
54
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Andrew Jones <drjones@redhat.com>
2
2
3
From 'Application Note AN385', chapter 3.14:
3
commit 32bd322a0134 ("hw/timer/armv7m_systick: Rewrite to use ptimers")
4
changed armv7m_systick to build on ptimers. Make sure we have ptimers
5
in the build when building armv7m_systick.
4
6
5
The SMM implements a simple SBCon interface based on I2C.
7
Signed-off-by: Andrew Jones <drjones@redhat.com>
6
8
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
7
There are 4 SBCon interfaces on the FPGA APB subsystem.
9
Message-id: 20201104103343.30392-1-drjones@redhat.com
8
9
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
10
Message-id: 20200617072539.32686-13-f4bug@amsat.org
11
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
---
11
---
14
hw/arm/mps2.c | 8 ++++++++
15
hw/arm/Kconfig | 1 +
12
hw/arm/Kconfig | 1 +
16
2 files changed, 9 insertions(+)
13
1 file changed, 1 insertion(+)
17
14
18
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
19
index XXXXXXX..XXXXXXX 100644
20
--- a/hw/arm/mps2.c
21
+++ b/hw/arm/mps2.c
22
@@ -XXX,XX +XXX,XX @@
23
#include "hw/misc/mps2-scc.h"
24
#include "hw/misc/mps2-fpgaio.h"
25
#include "hw/ssi/pl022.h"
26
+#include "hw/i2c/arm_sbcon_i2c.h"
27
#include "hw/net/lan9118.h"
28
#include "net/net.h"
29
#include "hw/watchdog/cmsdk-apb-watchdog.h"
30
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
31
qdev_get_gpio_in(orgate_dev, j));
32
}
33
}
34
+ for (i = 0; i < 4; i++) {
35
+ static const hwaddr i2cbase[] = {0x40022000, /* Touch */
36
+ 0x40023000, /* Audio */
37
+ 0x40029000, /* Shield0 */
38
+ 0x4002a000}; /* Shield1 */
39
+ sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL);
40
+ }
41
42
/* In hardware this is a LAN9220; the LAN9118 is software compatible
43
* except that it doesn't support the checksum-offload feature.
44
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
15
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
45
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
46
--- a/hw/arm/Kconfig
17
--- a/hw/arm/Kconfig
47
+++ b/hw/arm/Kconfig
18
+++ b/hw/arm/Kconfig
48
@@ -XXX,XX +XXX,XX @@ config MPS2
19
@@ -XXX,XX +XXX,XX @@ config ZYNQ
49
select SPLIT_IRQ
20
50
select UNIMP
21
config ARM_V7M
51
select CMSDK_APB_WATCHDOG
22
bool
52
+ select VERSATILE_I2C
23
+ select PTIMER
53
24
54
config FSL_IMX7
25
config ALLWINNER_A10
55
bool
26
bool
56
--
27
--
57
2.20.1
28
2.20.1
58
29
59
30
diff view generated by jsdifflib
1
From: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
1
From: AlexChen <alex.chen@huawei.com>
2
2
3
This adds support for memory(pc-dimm) hot remove on arm/virt that
3
We should use printf format specifier "%u" instead of "%d" for
4
uses acpi ged device.
4
argument of type "unsigned int".
5
5
6
NVDIMM hot removal is not yet supported.
6
Reported-by: Euler Robot <euler.robot@huawei.com>
7
7
Signed-off-by: Alex Chen <alex.chen@huawei.com>
8
Signed-off-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
8
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
9
Message-id: 20200622124157.20360-1-shameerali.kolothum.thodi@huawei.com
9
Message-id: 5FA280F5.8060902@huawei.com
10
Reviewed-by: Eric Auger <eric.auger@redhat.com>
11
Tested-by: Eric Auger <eric.auger@redhat.com>
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
---
11
---
14
hw/acpi/generic_event_device.c | 29 ++++++++++++++++
12
hw/ssi/imx_spi.c | 2 +-
15
hw/arm/virt.c | 62 ++++++++++++++++++++++++++++++++--
13
hw/ssi/xilinx_spi.c | 2 +-
16
2 files changed, 89 insertions(+), 2 deletions(-)
14
2 files changed, 2 insertions(+), 2 deletions(-)
17
15
18
diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c
16
diff --git a/hw/ssi/imx_spi.c b/hw/ssi/imx_spi.c
19
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
20
--- a/hw/acpi/generic_event_device.c
18
--- a/hw/ssi/imx_spi.c
21
+++ b/hw/acpi/generic_event_device.c
19
+++ b/hw/ssi/imx_spi.c
22
@@ -XXX,XX +XXX,XX @@ static void acpi_ged_device_plug_cb(HotplugHandler *hotplug_dev,
20
@@ -XXX,XX +XXX,XX @@ static const char *imx_spi_reg_name(uint32_t reg)
21
case ECSPI_MSGDATA:
22
return "ECSPI_MSGDATA";
23
default:
24
- sprintf(unknown, "%d ?", reg);
25
+ sprintf(unknown, "%u ?", reg);
26
return unknown;
23
}
27
}
24
}
28
}
25
29
diff --git a/hw/ssi/xilinx_spi.c b/hw/ssi/xilinx_spi.c
26
+static void acpi_ged_unplug_request_cb(HotplugHandler *hotplug_dev,
27
+ DeviceState *dev, Error **errp)
28
+{
29
+ AcpiGedState *s = ACPI_GED(hotplug_dev);
30
+
31
+ if ((object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) &&
32
+ !(object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)))) {
33
+ acpi_memory_unplug_request_cb(hotplug_dev, &s->memhp_state, dev, errp);
34
+ } else {
35
+ error_setg(errp, "acpi: device unplug request for unsupported device"
36
+ " type: %s", object_get_typename(OBJECT(dev)));
37
+ }
38
+}
39
+
40
+static void acpi_ged_unplug_cb(HotplugHandler *hotplug_dev,
41
+ DeviceState *dev, Error **errp)
42
+{
43
+ AcpiGedState *s = ACPI_GED(hotplug_dev);
44
+
45
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
46
+ acpi_memory_unplug_cb(&s->memhp_state, dev, errp);
47
+ } else {
48
+ error_setg(errp, "acpi: device unplug for unsupported device"
49
+ " type: %s", object_get_typename(OBJECT(dev)));
50
+ }
51
+}
52
+
53
static void acpi_ged_send_event(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
54
{
55
AcpiGedState *s = ACPI_GED(adev);
56
@@ -XXX,XX +XXX,XX @@ static void acpi_ged_class_init(ObjectClass *class, void *data)
57
dc->vmsd = &vmstate_acpi_ged;
58
59
hc->plug = acpi_ged_device_plug_cb;
60
+ hc->unplug_request = acpi_ged_unplug_request_cb;
61
+ hc->unplug = acpi_ged_unplug_cb;
62
63
adevc->send_event = acpi_ged_send_event;
64
}
65
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
66
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
67
--- a/hw/arm/virt.c
31
--- a/hw/ssi/xilinx_spi.c
68
+++ b/hw/arm/virt.c
32
+++ b/hw/ssi/xilinx_spi.c
69
@@ -XXX,XX +XXX,XX @@ static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev,
33
@@ -XXX,XX +XXX,XX @@ static void xlx_spi_update_irq(XilinxSPI *s)
34
irq chain unless things really changed. */
35
if (pending != s->irqline) {
36
s->irqline = pending;
37
- DB_PRINT("irq_change of state %d ISR:%x IER:%X\n",
38
+ DB_PRINT("irq_change of state %u ISR:%x IER:%X\n",
39
pending, s->regs[R_IPISR], s->regs[R_IPIER]);
40
qemu_set_irq(s->irq, pending);
70
}
41
}
71
}
72
73
+static void virt_dimm_unplug_request(HotplugHandler *hotplug_dev,
74
+ DeviceState *dev, Error **errp)
75
+{
76
+ VirtMachineState *vms = VIRT_MACHINE(hotplug_dev);
77
+ Error *local_err = NULL;
78
+
79
+ if (!vms->acpi_dev) {
80
+ error_setg(&local_err,
81
+ "memory hotplug is not enabled: missing acpi-ged device");
82
+ goto out;
83
+ }
84
+
85
+ if (object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM)) {
86
+ error_setg(&local_err,
87
+ "nvdimm device hot unplug is not supported yet.");
88
+ goto out;
89
+ }
90
+
91
+ hotplug_handler_unplug_request(HOTPLUG_HANDLER(vms->acpi_dev), dev,
92
+ &local_err);
93
+out:
94
+ error_propagate(errp, local_err);
95
+}
96
+
97
+static void virt_dimm_unplug(HotplugHandler *hotplug_dev,
98
+ DeviceState *dev, Error **errp)
99
+{
100
+ VirtMachineState *vms = VIRT_MACHINE(hotplug_dev);
101
+ Error *local_err = NULL;
102
+
103
+ hotplug_handler_unplug(HOTPLUG_HANDLER(vms->acpi_dev), dev, &local_err);
104
+ if (local_err) {
105
+ goto out;
106
+ }
107
+
108
+ pc_dimm_unplug(PC_DIMM(dev), MACHINE(vms));
109
+ qdev_unrealize(dev);
110
+
111
+out:
112
+ error_propagate(errp, local_err);
113
+}
114
+
115
static void virt_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev,
116
DeviceState *dev, Error **errp)
117
{
118
- error_setg(errp, "device unplug request for unsupported device"
119
- " type: %s", object_get_typename(OBJECT(dev)));
120
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
121
+ virt_dimm_unplug_request(hotplug_dev, dev, errp);
122
+ } else {
123
+ error_setg(errp, "device unplug request for unsupported device"
124
+ " type: %s", object_get_typename(OBJECT(dev)));
125
+ }
126
+}
127
+
128
+static void virt_machine_device_unplug_cb(HotplugHandler *hotplug_dev,
129
+ DeviceState *dev, Error **errp)
130
+{
131
+ if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
132
+ virt_dimm_unplug(hotplug_dev, dev, errp);
133
+ } else {
134
+ error_setg(errp, "virt: device unplug for unsupported device"
135
+ " type: %s", object_get_typename(OBJECT(dev)));
136
+ }
137
}
138
139
static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine,
140
@@ -XXX,XX +XXX,XX @@ static void virt_machine_class_init(ObjectClass *oc, void *data)
141
hc->pre_plug = virt_machine_device_pre_plug_cb;
142
hc->plug = virt_machine_device_plug_cb;
143
hc->unplug_request = virt_machine_device_unplug_request_cb;
144
+ hc->unplug = virt_machine_device_unplug_cb;
145
mc->numa_mem_supported = true;
146
mc->nvdimm_supported = true;
147
mc->auto_enable_numa_with_memhp = true;
148
--
42
--
149
2.20.1
43
2.20.1
150
44
151
45
diff view generated by jsdifflib
1
From: Andrew Jones <drjones@redhat.com>
1
From: Xinhao Zhang <zhangxinhao1@huawei.com>
2
2
3
Some cpu features may be enabled and disabled for all configurations
3
Fix code style. Operator needs spaces both sides.
4
that support the feature. Let's test that.
5
4
6
A recent regression[*] inspired adding these tests.
5
Signed-off-by: Xinhao Zhang <zhangxinhao1@huawei.com>
7
6
Signed-off-by: Kai Deng <dengkai1@huawei.com>
8
[*] '-cpu host,pmu=on' caused a segfault
7
Message-id: 20201103114529.638233-1-zhangxinhao1@huawei.com
9
10
Signed-off-by: Andrew Jones <drjones@redhat.com>
11
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
12
Message-id: 20200623090622.30365-2-philmd@redhat.com
13
Message-Id: <20200623082310.17577-1-drjones@redhat.com>
14
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
15
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
16
---
10
---
17
tests/qtest/arm-cpu-features.c | 38 ++++++++++++++++++++++++++++++----
11
target/arm/arch_dump.c | 8 ++++----
18
1 file changed, 34 insertions(+), 4 deletions(-)
12
target/arm/arm-semi.c | 8 ++++----
13
target/arm/helper.c | 2 +-
14
3 files changed, 9 insertions(+), 9 deletions(-)
19
15
20
diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c
16
diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c
21
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
22
--- a/tests/qtest/arm-cpu-features.c
18
--- a/target/arm/arch_dump.c
23
+++ b/tests/qtest/arm-cpu-features.c
19
+++ b/target/arm/arch_dump.c
24
@@ -XXX,XX +XXX,XX @@ static bool resp_get_feature(QDict *resp, const char *feature)
20
@@ -XXX,XX +XXX,XX @@ static int aarch64_write_elf64_prfpreg(WriteCoreDumpFunction f,
25
qobject_unref(_resp); \
21
26
})
22
for (i = 0; i < 32; ++i) {
27
23
uint64_t *q = aa64_vfp_qreg(env, i);
28
-#define assert_feature(qts, cpu_type, feature, expected_value) \
24
- note.vfp.vregs[2*i + 0] = cpu_to_dump64(s, q[0]);
29
+#define resp_assert_feature(resp, feature, expected_value) \
25
- note.vfp.vregs[2*i + 1] = cpu_to_dump64(s, q[1]);
30
({ \
26
+ note.vfp.vregs[2 * i + 0] = cpu_to_dump64(s, q[0]);
31
- QDict *_resp, *_props; \
27
+ note.vfp.vregs[2 * i + 1] = cpu_to_dump64(s, q[1]);
32
+ QDict *_props; \
33
\
34
- _resp = do_query_no_props(qts, cpu_type); \
35
g_assert(_resp); \
36
g_assert(resp_has_props(_resp)); \
37
_props = resp_get_props(_resp); \
38
g_assert(qdict_get(_props, feature)); \
39
g_assert(qdict_get_bool(_props, feature) == (expected_value)); \
40
+})
41
+
42
+#define assert_feature(qts, cpu_type, feature, expected_value) \
43
+({ \
44
+ QDict *_resp; \
45
+ \
46
+ _resp = do_query_no_props(qts, cpu_type); \
47
+ g_assert(_resp); \
48
+ resp_assert_feature(_resp, feature, expected_value); \
49
+ qobject_unref(_resp); \
50
+})
51
+
52
+#define assert_set_feature(qts, cpu_type, feature, value) \
53
+({ \
54
+ const char *_fmt = (value) ? "{ %s: true }" : "{ %s: false }"; \
55
+ QDict *_resp; \
56
+ \
57
+ _resp = do_query(qts, cpu_type, _fmt, feature); \
58
+ g_assert(_resp); \
59
+ resp_assert_feature(_resp, feature, value); \
60
qobject_unref(_resp); \
61
})
62
63
@@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data)
64
assert_error(qts, "host", "The CPU type 'host' requires KVM", NULL);
65
66
/* Test expected feature presence/absence for some cpu types */
67
- assert_has_feature_enabled(qts, "max", "pmu");
68
assert_has_feature_enabled(qts, "cortex-a15", "pmu");
69
assert_has_not_feature(qts, "cortex-a15", "aarch64");
70
71
+ /* Enabling and disabling pmu should always work. */
72
+ assert_has_feature_enabled(qts, "max", "pmu");
73
+ assert_set_feature(qts, "max", "pmu", false);
74
+ assert_set_feature(qts, "max", "pmu", true);
75
+
76
assert_has_not_feature(qts, "max", "kvm-no-adjvtime");
77
78
if (g_str_equal(qtest_get_arch(), "aarch64")) {
79
@@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data)
80
return;
81
}
28
}
82
29
83
+ /* Enabling and disabling kvm-no-adjvtime should always work. */
30
if (s->dump_info.d_endian == ELFDATA2MSB) {
84
assert_has_feature_disabled(qts, "host", "kvm-no-adjvtime");
31
@@ -XXX,XX +XXX,XX @@ static int aarch64_write_elf64_prfpreg(WriteCoreDumpFunction f,
85
+ assert_set_feature(qts, "host", "kvm-no-adjvtime", true);
32
*/
86
+ assert_set_feature(qts, "host", "kvm-no-adjvtime", false);
33
for (i = 0; i < 32; ++i) {
87
34
uint64_t tmp = note.vfp.vregs[2*i];
88
if (g_str_equal(qtest_get_arch(), "aarch64")) {
35
- note.vfp.vregs[2*i] = note.vfp.vregs[2*i+1];
89
bool kvm_supports_sve;
36
- note.vfp.vregs[2*i+1] = tmp;
90
@@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data)
37
+ note.vfp.vregs[2 * i] = note.vfp.vregs[2 * i + 1];
91
char *error;
38
+ note.vfp.vregs[2 * i + 1] = tmp;
92
39
}
93
assert_has_feature_enabled(qts, "host", "aarch64");
40
}
94
+
41
95
+ /* Enabling and disabling pmu should always work. */
42
diff --git a/target/arm/arm-semi.c b/target/arm/arm-semi.c
96
assert_has_feature_enabled(qts, "host", "pmu");
43
index XXXXXXX..XXXXXXX 100644
97
+ assert_set_feature(qts, "host", "pmu", false);
44
--- a/target/arm/arm-semi.c
98
+ assert_set_feature(qts, "host", "pmu", true);
45
+++ b/target/arm/arm-semi.c
99
46
@@ -XXX,XX +XXX,XX @@ target_ulong do_arm_semihosting(CPUARMState *env)
100
assert_error(qts, "cortex-a15",
47
if (use_gdb_syscalls()) {
101
"We cannot guarantee the CPU type 'cortex-a15' works "
48
arm_semi_open_guestfd = guestfd;
49
ret = arm_gdb_syscall(cpu, arm_semi_open_cb, "open,%s,%x,1a4", arg0,
50
- (int)arg2+1, gdb_open_modeflags[arg1]);
51
+ (int)arg2 + 1, gdb_open_modeflags[arg1]);
52
} else {
53
ret = set_swi_errno(env, open(s, open_modeflags[arg1], 0644));
54
if (ret == (uint32_t)-1) {
55
@@ -XXX,XX +XXX,XX @@ target_ulong do_arm_semihosting(CPUARMState *env)
56
GET_ARG(1);
57
if (use_gdb_syscalls()) {
58
ret = arm_gdb_syscall(cpu, arm_semi_cb, "unlink,%s",
59
- arg0, (int)arg1+1);
60
+ arg0, (int)arg1 + 1);
61
} else {
62
s = lock_user_string(arg0);
63
if (!s) {
64
@@ -XXX,XX +XXX,XX @@ target_ulong do_arm_semihosting(CPUARMState *env)
65
GET_ARG(3);
66
if (use_gdb_syscalls()) {
67
return arm_gdb_syscall(cpu, arm_semi_cb, "rename,%s,%s",
68
- arg0, (int)arg1+1, arg2, (int)arg3+1);
69
+ arg0, (int)arg1 + 1, arg2, (int)arg3 + 1);
70
} else {
71
char *s2;
72
s = lock_user_string(arg0);
73
@@ -XXX,XX +XXX,XX @@ target_ulong do_arm_semihosting(CPUARMState *env)
74
GET_ARG(1);
75
if (use_gdb_syscalls()) {
76
return arm_gdb_syscall(cpu, arm_semi_cb, "system,%s",
77
- arg0, (int)arg1+1);
78
+ arg0, (int)arg1 + 1);
79
} else {
80
s = lock_user_string(arg0);
81
if (!s) {
82
diff --git a/target/arm/helper.c b/target/arm/helper.c
83
index XXXXXXX..XXXXXXX 100644
84
--- a/target/arm/helper.c
85
+++ b/target/arm/helper.c
86
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(usad8)(uint32_t a, uint32_t b)
87
uint32_t sum;
88
sum = do_usad(a, b);
89
sum += do_usad(a >> 8, b >> 8);
90
- sum += do_usad(a >> 16, b >>16);
91
+ sum += do_usad(a >> 16, b >> 16);
92
sum += do_usad(a >> 24, b >> 24);
93
return sum;
94
}
102
--
95
--
103
2.20.1
96
2.20.1
104
97
105
98
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Xinhao Zhang <zhangxinhao1@huawei.com>
2
2
3
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
3
Fix code style. Don't use '#' flag of printf format ('%#') in
4
Message-id: 20200617072539.32686-7-f4bug@amsat.org
4
format strings, use '0x' prefix instead
5
6
Signed-off-by: Xinhao Zhang <zhangxinhao1@huawei.com>
7
Signed-off-by: Kai Deng <dengkai1@huawei.com>
8
Message-id: 20201103114529.638233-2-zhangxinhao1@huawei.com
5
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
---
11
---
8
hw/arm/mps2.c | 5 ++++-
12
target/arm/translate-a64.c | 4 ++--
9
1 file changed, 4 insertions(+), 1 deletion(-)
13
1 file changed, 2 insertions(+), 2 deletions(-)
10
14
11
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
15
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
12
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
13
--- a/hw/arm/mps2.c
17
--- a/target/arm/translate-a64.c
14
+++ b/hw/arm/mps2.c
18
+++ b/target/arm/translate-a64.c
15
@@ -XXX,XX +XXX,XX @@ typedef struct {
19
@@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
16
MemoryRegion blockram_m2;
20
gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
17
MemoryRegion blockram_m3;
21
break;
18
MemoryRegion sram;
22
default:
19
+ /* FPGA APB subsystem */
23
- fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
20
MPS2SCC scc;
24
+ fprintf(stderr, "%s: insn 0x%04x, fpop 0x%2x @ 0x%" PRIx64 "\n",
21
+ /* CMSDK APB subsystem */
25
__func__, insn, fpopcode, s->pc_curr);
22
CMSDKAPBDualTimer dualtimer;
26
g_assert_not_reached();
23
} MPS2MachineState;
27
}
24
28
@@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
25
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
29
case 0x7f: /* FSQRT (vector) */
30
break;
31
default:
32
- fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop);
33
+ fprintf(stderr, "%s: insn 0x%04x fpop 0x%2x\n", __func__, insn, fpop);
26
g_assert_not_reached();
34
g_assert_not_reached();
27
}
35
}
28
36
29
+ /* CMSDK APB subsystem */
30
cmsdk_apb_timer_create(0x40000000, qdev_get_gpio_in(armv7m, 8), SYSCLK_FRQ);
31
cmsdk_apb_timer_create(0x40001000, qdev_get_gpio_in(armv7m, 9), SYSCLK_FRQ);
32
-
33
object_initialize_child(OBJECT(mms), "dualtimer", &mms->dualtimer,
34
TYPE_CMSDK_APB_DUALTIMER);
35
qdev_prop_set_uint32(DEVICE(&mms->dualtimer), "pclk-frq", SYSCLK_FRQ);
36
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
37
qdev_get_gpio_in(armv7m, 10));
38
sysbus_mmio_map(SYS_BUS_DEVICE(&mms->dualtimer), 0, 0x40002000);
39
40
+ /* FPGA APB subsystem */
41
object_initialize_child(OBJECT(mms), "scc", &mms->scc, TYPE_MPS2_SCC);
42
sccdev = DEVICE(&mms->scc);
43
qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2);
44
--
37
--
45
2.20.1
38
2.20.1
46
39
47
40
diff view generated by jsdifflib
1
Convert the pairwise ops VPADDL and VPADAL in the 2-reg-misc grouping
1
From: Xinhao Zhang <zhangxinhao1@huawei.com>
2
to decodetree.
3
2
4
At this point we can get rid of the weird CPU_V001 #define that was
3
Fix code style. Space required before the open parenthesis '('.
5
used to avoid having to explicitly list all the arguments being
6
passed to some TCG gen/helper functions.
7
4
5
Signed-off-by: Xinhao Zhang <zhangxinhao1@huawei.com>
6
Signed-off-by: Kai Deng <dengkai1@huawei.com>
7
Message-id: 20201103114529.638233-3-zhangxinhao1@huawei.com
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
10
Message-id: 20200616170844.13318-3-peter.maydell@linaro.org
11
---
10
---
12
target/arm/neon-dp.decode | 6 ++
11
target/arm/translate.c | 2 +-
13
target/arm/translate-neon.inc.c | 149 ++++++++++++++++++++++++++++++++
12
1 file changed, 1 insertion(+), 1 deletion(-)
14
target/arm/translate.c | 35 +-------
15
3 files changed, 157 insertions(+), 33 deletions(-)
16
13
17
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
18
index XXXXXXX..XXXXXXX 100644
19
--- a/target/arm/neon-dp.decode
20
+++ b/target/arm/neon-dp.decode
21
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
22
&2misc vm=%vm_dp vd=%vd_dp
23
24
VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
25
+
26
+ VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc
27
+ VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc
28
+
29
+ VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
30
+ VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc
31
]
32
33
# Subgroup for size != 0b11
34
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
35
index XXXXXXX..XXXXXXX 100644
36
--- a/target/arm/translate-neon.inc.c
37
+++ b/target/arm/translate-neon.inc.c
38
@@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
39
}
40
return true;
41
}
42
+
43
+static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a,
44
+ NeonGenWidenFn *widenfn,
45
+ NeonGenTwo64OpFn *opfn,
46
+ NeonGenTwo64OpFn *accfn)
47
+{
48
+ /*
49
+ * Pairwise long operations: widen both halves of the pair,
50
+ * combine the pairs with the opfn, and then possibly accumulate
51
+ * into the destination with the accfn.
52
+ */
53
+ int pass;
54
+
55
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
56
+ return false;
57
+ }
58
+
59
+ /* UNDEF accesses to D16-D31 if they don't exist. */
60
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
61
+ ((a->vd | a->vm) & 0x10)) {
62
+ return false;
63
+ }
64
+
65
+ if ((a->vd | a->vm) & a->q) {
66
+ return false;
67
+ }
68
+
69
+ if (!widenfn) {
70
+ return false;
71
+ }
72
+
73
+ if (!vfp_access_check(s)) {
74
+ return true;
75
+ }
76
+
77
+ for (pass = 0; pass < a->q + 1; pass++) {
78
+ TCGv_i32 tmp;
79
+ TCGv_i64 rm0_64, rm1_64, rd_64;
80
+
81
+ rm0_64 = tcg_temp_new_i64();
82
+ rm1_64 = tcg_temp_new_i64();
83
+ rd_64 = tcg_temp_new_i64();
84
+ tmp = neon_load_reg(a->vm, pass * 2);
85
+ widenfn(rm0_64, tmp);
86
+ tcg_temp_free_i32(tmp);
87
+ tmp = neon_load_reg(a->vm, pass * 2 + 1);
88
+ widenfn(rm1_64, tmp);
89
+ tcg_temp_free_i32(tmp);
90
+ opfn(rd_64, rm0_64, rm1_64);
91
+ tcg_temp_free_i64(rm0_64);
92
+ tcg_temp_free_i64(rm1_64);
93
+
94
+ if (accfn) {
95
+ TCGv_i64 tmp64 = tcg_temp_new_i64();
96
+ neon_load_reg64(tmp64, a->vd + pass);
97
+ accfn(rd_64, tmp64, rd_64);
98
+ tcg_temp_free_i64(tmp64);
99
+ }
100
+ neon_store_reg64(rd_64, a->vd + pass);
101
+ tcg_temp_free_i64(rd_64);
102
+ }
103
+ return true;
104
+}
105
+
106
+static bool trans_VPADDL_S(DisasContext *s, arg_2misc *a)
107
+{
108
+ static NeonGenWidenFn * const widenfn[] = {
109
+ gen_helper_neon_widen_s8,
110
+ gen_helper_neon_widen_s16,
111
+ tcg_gen_ext_i32_i64,
112
+ NULL,
113
+ };
114
+ static NeonGenTwo64OpFn * const opfn[] = {
115
+ gen_helper_neon_paddl_u16,
116
+ gen_helper_neon_paddl_u32,
117
+ tcg_gen_add_i64,
118
+ NULL,
119
+ };
120
+
121
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL);
122
+}
123
+
124
+static bool trans_VPADDL_U(DisasContext *s, arg_2misc *a)
125
+{
126
+ static NeonGenWidenFn * const widenfn[] = {
127
+ gen_helper_neon_widen_u8,
128
+ gen_helper_neon_widen_u16,
129
+ tcg_gen_extu_i32_i64,
130
+ NULL,
131
+ };
132
+ static NeonGenTwo64OpFn * const opfn[] = {
133
+ gen_helper_neon_paddl_u16,
134
+ gen_helper_neon_paddl_u32,
135
+ tcg_gen_add_i64,
136
+ NULL,
137
+ };
138
+
139
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL);
140
+}
141
+
142
+static bool trans_VPADAL_S(DisasContext *s, arg_2misc *a)
143
+{
144
+ static NeonGenWidenFn * const widenfn[] = {
145
+ gen_helper_neon_widen_s8,
146
+ gen_helper_neon_widen_s16,
147
+ tcg_gen_ext_i32_i64,
148
+ NULL,
149
+ };
150
+ static NeonGenTwo64OpFn * const opfn[] = {
151
+ gen_helper_neon_paddl_u16,
152
+ gen_helper_neon_paddl_u32,
153
+ tcg_gen_add_i64,
154
+ NULL,
155
+ };
156
+ static NeonGenTwo64OpFn * const accfn[] = {
157
+ gen_helper_neon_addl_u16,
158
+ gen_helper_neon_addl_u32,
159
+ tcg_gen_add_i64,
160
+ NULL,
161
+ };
162
+
163
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size],
164
+ accfn[a->size]);
165
+}
166
+
167
+static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a)
168
+{
169
+ static NeonGenWidenFn * const widenfn[] = {
170
+ gen_helper_neon_widen_u8,
171
+ gen_helper_neon_widen_u16,
172
+ tcg_gen_extu_i32_i64,
173
+ NULL,
174
+ };
175
+ static NeonGenTwo64OpFn * const opfn[] = {
176
+ gen_helper_neon_paddl_u16,
177
+ gen_helper_neon_paddl_u32,
178
+ tcg_gen_add_i64,
179
+ NULL,
180
+ };
181
+ static NeonGenTwo64OpFn * const accfn[] = {
182
+ gen_helper_neon_addl_u16,
183
+ gen_helper_neon_addl_u32,
184
+ tcg_gen_add_i64,
185
+ NULL,
186
+ };
187
+
188
+ return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size],
189
+ accfn[a->size]);
190
+}
191
diff --git a/target/arm/translate.c b/target/arm/translate.c
14
diff --git a/target/arm/translate.c b/target/arm/translate.c
192
index XXXXXXX..XXXXXXX 100644
15
index XXXXXXX..XXXXXXX 100644
193
--- a/target/arm/translate.c
16
--- a/target/arm/translate.c
194
+++ b/target/arm/translate.c
17
+++ b/target/arm/translate.c
195
@@ -XXX,XX +XXX,XX @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
18
@@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_stop(DisasContextBase *dcbase, CPUState *cpu)
196
gen_rfe(s, pc, load_cpu_field(spsr));
19
- Hardware watchpoints.
197
}
20
Hardware breakpoints have already been handled and skip this code.
198
21
*/
199
-#define CPU_V001 cpu_V0, cpu_V0, cpu_V1
22
- switch(dc->base.is_jmp) {
200
-
23
+ switch (dc->base.is_jmp) {
201
static int gen_neon_unzip(int rd, int rm, int size, int q)
24
case DISAS_NEXT:
202
{
25
case DISAS_TOO_MANY:
203
TCGv_ptr pd, pm;
26
gen_goto_tb(dc, 1, dc->base.pc_next);
204
@@ -XXX,XX +XXX,XX @@ static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
205
tcg_temp_free_i32(src);
206
}
207
208
-static inline void gen_neon_addl(int size)
209
-{
210
- switch (size) {
211
- case 0: gen_helper_neon_addl_u16(CPU_V001); break;
212
- case 1: gen_helper_neon_addl_u32(CPU_V001); break;
213
- case 2: tcg_gen_add_i64(CPU_V001); break;
214
- default: abort();
215
- }
216
-}
217
-
218
static void gen_neon_narrow_op(int op, int u, int size,
219
TCGv_i32 dest, TCGv_i64 src)
220
{
221
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
222
}
223
switch (op) {
224
case NEON_2RM_VREV64:
225
- /* handled by decodetree */
226
- return 1;
227
case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U:
228
case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
229
- for (pass = 0; pass < q + 1; pass++) {
230
- tmp = neon_load_reg(rm, pass * 2);
231
- gen_neon_widen(cpu_V0, tmp, size, op & 1);
232
- tmp = neon_load_reg(rm, pass * 2 + 1);
233
- gen_neon_widen(cpu_V1, tmp, size, op & 1);
234
- switch (size) {
235
- case 0: gen_helper_neon_paddl_u16(CPU_V001); break;
236
- case 1: gen_helper_neon_paddl_u32(CPU_V001); break;
237
- case 2: tcg_gen_add_i64(CPU_V001); break;
238
- default: abort();
239
- }
240
- if (op >= NEON_2RM_VPADAL) {
241
- /* Accumulate. */
242
- neon_load_reg64(cpu_V1, rd + pass);
243
- gen_neon_addl(size);
244
- }
245
- neon_store_reg64(cpu_V0, rd + pass);
246
- }
247
- break;
248
+ /* handled by decodetree */
249
+ return 1;
250
case NEON_2RM_VTRN:
251
if (size == 2) {
252
int n;
253
--
27
--
254
2.20.1
28
2.20.1
255
29
256
30
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Alex Bennée <alex.bennee@linaro.org>
2
2
3
'ARM SBCon two-wire serial bus interface' is the official
3
We should at least document what this machine is about.
4
name describing the pair of registers used to bitbanging
5
I2C in the Versatile boards.
6
4
7
Make the private VersatileI2CState structure as public
5
Reviewed-by: Graeme Gregory <graeme@nuviainc.com>
8
ArmSbconI2CState.
6
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
9
Add the TYPE_ARM_SBCON_I2C, alias to our current
7
Message-id: 20201104165254.24822-1-alex.bennee@linaro.org
10
TYPE_VERSATILE_I2C model.
8
Cc: Leif Lindholm <leif@nuviainc.com>
11
Rename the memory region description as 'arm_sbcon_i2c'.
9
Cc: Shashi Mallela <shashi.mallela@linaro.org>
12
10
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
13
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
11
[PMM: fixed filename mismatch]
14
Message-id: 20200617072539.32686-5-f4bug@amsat.org
15
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
---
13
---
18
include/hw/i2c/arm_sbcon_i2c.h | 35 ++++++++++++++++++++++++++++++++++
14
docs/system/arm/sbsa.rst | 32 ++++++++++++++++++++++++++++++++
19
hw/i2c/versatile_i2c.c | 17 +++++------------
15
docs/system/target-arm.rst | 1 +
20
MAINTAINERS | 1 +
16
2 files changed, 33 insertions(+)
21
3 files changed, 41 insertions(+), 12 deletions(-)
17
create mode 100644 docs/system/arm/sbsa.rst
22
create mode 100644 include/hw/i2c/arm_sbcon_i2c.h
23
18
24
diff --git a/include/hw/i2c/arm_sbcon_i2c.h b/include/hw/i2c/arm_sbcon_i2c.h
19
diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst
25
new file mode 100644
20
new file mode 100644
26
index XXXXXXX..XXXXXXX
21
index XXXXXXX..XXXXXXX
27
--- /dev/null
22
--- /dev/null
28
+++ b/include/hw/i2c/arm_sbcon_i2c.h
23
+++ b/docs/system/arm/sbsa.rst
29
@@ -XXX,XX +XXX,XX @@
24
@@ -XXX,XX +XXX,XX @@
30
+/*
25
+Arm Server Base System Architecture Reference board (``sbsa-ref``)
31
+ * ARM SBCon two-wire serial bus interface (I2C bitbang)
26
+==================================================================
32
+ * a.k.a.
33
+ * ARM Versatile I2C controller
34
+ *
35
+ * Copyright (c) 2006-2007 CodeSourcery.
36
+ * Copyright (c) 2012 Oskar Andero <oskar.andero@gmail.com>
37
+ * Copyright (C) 2020 Philippe Mathieu-Daudé <f4bug@amsat.org>
38
+ *
39
+ * SPDX-License-Identifier: GPL-2.0-or-later
40
+ */
41
+#ifndef HW_I2C_ARM_SBCON_H
42
+#define HW_I2C_ARM_SBCON_H
43
+
27
+
44
+#include "hw/sysbus.h"
28
+While the `virt` board is a generic board platform that doesn't match
45
+#include "hw/i2c/bitbang_i2c.h"
29
+any real hardware the `sbsa-ref` board intends to look like real
30
+hardware. The `Server Base System Architecture
31
+<https://developer.arm.com/documentation/den0029/latest>` defines a
32
+minimum base line of hardware support and importantly how the firmware
33
+reports that to any operating system. It is a static system that
34
+reports a very minimal DT to the firmware for non-discoverable
35
+information about components affected by the qemu command line (i.e.
36
+cpus and memory). As a result it must have a firmware specifically
37
+built to expect a certain hardware layout (as you would in a real
38
+machine).
46
+
39
+
47
+#define TYPE_VERSATILE_I2C "versatile_i2c"
40
+It is intended to be a machine for developing firmware and testing
48
+#define TYPE_ARM_SBCON_I2C TYPE_VERSATILE_I2C
41
+standards compliance with operating systems.
49
+
42
+
50
+#define ARM_SBCON_I2C(obj) \
43
+Supported devices
51
+ OBJECT_CHECK(ArmSbconI2CState, (obj), TYPE_ARM_SBCON_I2C)
44
+"""""""""""""""""
52
+
45
+
53
+typedef struct ArmSbconI2CState {
46
+The sbsa-ref board supports:
54
+ /*< private >*/
55
+ SysBusDevice parent_obj;
56
+ /*< public >*/
57
+
47
+
58
+ MemoryRegion iomem;
48
+ - A configurable number of AArch64 CPUs
59
+ bitbang_i2c_interface bitbang;
49
+ - GIC version 3
60
+ int out;
50
+ - System bus AHCI controller
61
+ int in;
51
+ - System bus EHCI controller
62
+} ArmSbconI2CState;
52
+ - CDROM and hard disc on AHCI bus
53
+ - E1000E ethernet card on PCIe bus
54
+ - VGA display adaptor on PCIe bus
55
+ - A generic SBSA watchdog device
63
+
56
+
64
+#endif /* HW_I2C_ARM_SBCON_H */
57
diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst
65
diff --git a/hw/i2c/versatile_i2c.c b/hw/i2c/versatile_i2c.c
66
index XXXXXXX..XXXXXXX 100644
58
index XXXXXXX..XXXXXXX 100644
67
--- a/hw/i2c/versatile_i2c.c
59
--- a/docs/system/target-arm.rst
68
+++ b/hw/i2c/versatile_i2c.c
60
+++ b/docs/system/target-arm.rst
69
@@ -XXX,XX +XXX,XX @@
61
@@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running
70
/*
62
arm/mps2
71
- * ARM Versatile I2C controller
63
arm/musca
72
+ * ARM SBCon two-wire serial bus interface (I2C bitbang)
64
arm/realview
73
+ * a.k.a. ARM Versatile I2C controller
65
+ arm/sbsa
74
*
66
arm/versatile
75
* Copyright (c) 2006-2007 CodeSourcery.
67
arm/vexpress
76
* Copyright (c) 2012 Oskar Andero <oskar.andero@gmail.com>
68
arm/aspeed
77
@@ -XXX,XX +XXX,XX @@
78
*/
79
80
#include "qemu/osdep.h"
81
-#include "hw/sysbus.h"
82
-#include "hw/i2c/bitbang_i2c.h"
83
+#include "hw/i2c/arm_sbcon_i2c.h"
84
#include "hw/registerfields.h"
85
#include "qemu/log.h"
86
#include "qemu/module.h"
87
88
-#define TYPE_VERSATILE_I2C "versatile_i2c"
89
#define VERSATILE_I2C(obj) \
90
OBJECT_CHECK(VersatileI2CState, (obj), TYPE_VERSATILE_I2C)
91
92
-typedef struct VersatileI2CState {
93
- SysBusDevice parent_obj;
94
+typedef ArmSbconI2CState VersatileI2CState;
95
96
- MemoryRegion iomem;
97
- bitbang_i2c_interface bitbang;
98
- int out;
99
- int in;
100
-} VersatileI2CState;
101
102
REG32(CONTROL_GET, 0)
103
REG32(CONTROL_SET, 0)
104
@@ -XXX,XX +XXX,XX @@ static void versatile_i2c_init(Object *obj)
105
bus = i2c_init_bus(dev, "i2c");
106
bitbang_i2c_init(&s->bitbang, bus);
107
memory_region_init_io(&s->iomem, obj, &versatile_i2c_ops, s,
108
- "versatile_i2c", 0x1000);
109
+ "arm_sbcon_i2c", 0x1000);
110
sysbus_init_mmio(sbd, &s->iomem);
111
}
112
113
diff --git a/MAINTAINERS b/MAINTAINERS
114
index XXXXXXX..XXXXXXX 100644
115
--- a/MAINTAINERS
116
+++ b/MAINTAINERS
117
@@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org>
118
L: qemu-arm@nongnu.org
119
S: Maintained
120
F: hw/*/versatile*
121
+F: include/hw/i2c/arm_sbcon_i2c.h
122
F: hw/misc/arm_sysctl.c
123
F: docs/system/arm/versatile.rst
124
125
--
69
--
126
2.20.1
70
2.20.1
127
71
128
72
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
2
2
3
From 'Application Note AN385', chapter 3.9, SPI:
3
When using a Cortex-A15, the Virt machine does not use any
4
MPCore peripherals. Remove the dependency.
4
5
5
The SMM implements five PL022 SPI modules.
6
Fixes: 7951c7b7c05 ("hw/arm: Express dependencies of the virt machine with Kconfig")
6
7
Reported-by: Miroslav Rezanina <mrezanin@redhat.com>
7
Two pairs of modules share the same OR-gated IRQ.
8
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
8
9
Message-id: 20201107114852.271922-1-philmd@redhat.com
9
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
10
Message-id: 20200617072539.32686-12-f4bug@amsat.org
11
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
---
12
---
14
hw/arm/mps2.c | 24 ++++++++++++++++++++++++
13
hw/arm/Kconfig | 1 -
15
hw/arm/Kconfig | 6 +++---
14
1 file changed, 1 deletion(-)
16
2 files changed, 27 insertions(+), 3 deletions(-)
17
15
18
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
19
index XXXXXXX..XXXXXXX 100644
20
--- a/hw/arm/mps2.c
21
+++ b/hw/arm/mps2.c
22
@@ -XXX,XX +XXX,XX @@
23
#include "hw/timer/cmsdk-apb-dualtimer.h"
24
#include "hw/misc/mps2-scc.h"
25
#include "hw/misc/mps2-fpgaio.h"
26
+#include "hw/ssi/pl022.h"
27
#include "hw/net/lan9118.h"
28
#include "net/net.h"
29
#include "hw/watchdog/cmsdk-apb-watchdog.h"
30
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
31
qdev_prop_set_uint32(DEVICE(&mms->fpgaio), "prescale-clk", 25000000);
32
sysbus_realize(SYS_BUS_DEVICE(&mms->fpgaio), &error_fatal);
33
sysbus_mmio_map(SYS_BUS_DEVICE(&mms->fpgaio), 0, 0x40028000);
34
+ sysbus_create_simple(TYPE_PL022, 0x40025000, /* External ADC */
35
+ qdev_get_gpio_in(armv7m, 22));
36
+ for (i = 0; i < 2; i++) {
37
+ static const int spi_irqno[] = {11, 24};
38
+ static const hwaddr spibase[] = {0x40020000, /* APB */
39
+ 0x40021000, /* LCD */
40
+ 0x40026000, /* Shield0 */
41
+ 0x40027000}; /* Shield1 */
42
+ DeviceState *orgate_dev;
43
+ Object *orgate;
44
+ int j;
45
+
46
+ orgate = object_new(TYPE_OR_IRQ);
47
+ object_property_set_int(orgate, 2, "num-lines", &error_fatal);
48
+ orgate_dev = DEVICE(orgate);
49
+ qdev_realize(orgate_dev, NULL, &error_fatal);
50
+ qdev_connect_gpio_out(orgate_dev, 0,
51
+ qdev_get_gpio_in(armv7m, spi_irqno[i]));
52
+ for (j = 0; j < 2; j++) {
53
+ sysbus_create_simple(TYPE_PL022, spibase[2 * i + j],
54
+ qdev_get_gpio_in(orgate_dev, j));
55
+ }
56
+ }
57
58
/* In hardware this is a LAN9220; the LAN9118 is software compatible
59
* except that it doesn't support the checksum-offload feature.
60
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
16
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
61
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
62
--- a/hw/arm/Kconfig
18
--- a/hw/arm/Kconfig
63
+++ b/hw/arm/Kconfig
19
+++ b/hw/arm/Kconfig
64
@@ -XXX,XX +XXX,XX @@ config HIGHBANK
20
@@ -XXX,XX +XXX,XX @@ config ARM_VIRT
65
select ARM_TIMER # sp804
21
imply VFIO_PLATFORM
66
select ARM_V7M
22
imply VFIO_XGMAC
67
select PL011 # UART
23
imply TPM_TIS_SYSBUS
68
- select PL022 # Serial port
24
- select A15MPCORE
69
+ select PL022 # SPI
25
select ACPI
70
select PL031 # RTC
26
select ARM_SMMUV3
71
select PL061 # GPIO
27
select GPIO_KEY
72
select PL310 # cache controller
73
@@ -XXX,XX +XXX,XX @@ config STELLARIS
74
select CMSDK_APB_WATCHDOG
75
select I2C
76
select PL011 # UART
77
- select PL022 # Serial port
78
+ select PL022 # SPI
79
select PL061 # GPIO
80
select SSD0303 # OLED display
81
select SSD0323 # OLED display
82
@@ -XXX,XX +XXX,XX @@ config MPS2
83
select MPS2_FPGAIO
84
select MPS2_SCC
85
select OR_IRQ
86
- select PL022 # Serial port
87
+ select PL022 # SPI
88
select PL080 # DMA controller
89
select SPLIT_IRQ
90
select UNIMP
91
--
28
--
92
2.20.1
29
2.20.1
93
30
94
31
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
1
From: Richard Henderson <richard.henderson@linaro.org>
2
2
3
Since commit d70c996df23f, when enabling the PMU we get:
3
The helper function did not get updated when we reorganized
4
the vector register file for SVE. Since then, the neon dregs
5
are non-sequential and cannot be simply indexed.
4
6
5
$ qemu-system-aarch64 -cpu host,pmu=on -M virt,accel=kvm,gic-version=3
7
At the same time, make the helper function operate on 64-bit
6
Segmentation fault (core dumped)
8
quantities so that we do not have to call it twice.
7
9
8
Thread 1 "qemu-system-aar" received signal SIGSEGV, Segmentation fault.
10
Fixes: c39c2b9043e
9
0x0000aaaaaae356d0 in kvm_ioctl (s=0x0, type=44547) at accel/kvm/kvm-all.c:2588
11
Reported-by: Ard Biesheuvel <ardb@kernel.org>
10
2588 ret = ioctl(s->fd, type, arg);
12
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
11
(gdb) bt
13
[PMM: use aa32_vfp_dreg() rather than opencoding]
12
#0 0x0000aaaaaae356d0 in kvm_ioctl (s=0x0, type=44547) at accel/kvm/kvm-all.c:2588
14
Message-id: 20201105171126.88014-1-richard.henderson@linaro.org
13
#1 0x0000aaaaaae31568 in kvm_check_extension (s=0x0, extension=126) at accel/kvm/kvm-all.c:916
15
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
14
#2 0x0000aaaaaafce254 in kvm_arm_pmu_supported (cpu=0xaaaaac214ab0) at target/arm/kvm.c:213
15
#3 0x0000aaaaaafc0f94 in arm_set_pmu (obj=0xaaaaac214ab0, value=true, errp=0xffffffffe438) at target/arm/cpu.c:1111
16
#4 0x0000aaaaab5533ac in property_set_bool (obj=0xaaaaac214ab0, v=0xaaaaac223a80, name=0xaaaaac11a970 "pmu", opaque=0xaaaaac222730, errp=0xffffffffe438) at qom/object.c:2170
17
#5 0x0000aaaaab5512f0 in object_property_set (obj=0xaaaaac214ab0, v=0xaaaaac223a80, name=0xaaaaac11a970 "pmu", errp=0xffffffffe438) at qom/object.c:1328
18
#6 0x0000aaaaab551e10 in object_property_parse (obj=0xaaaaac214ab0, string=0xaaaaac11b4c0 "on", name=0xaaaaac11a970 "pmu", errp=0xffffffffe438) at qom/object.c:1561
19
#7 0x0000aaaaab54ee8c in object_apply_global_props (obj=0xaaaaac214ab0, props=0xaaaaac018e20, errp=0xaaaaabd6fd88 <error_fatal>) at qom/object.c:407
20
#8 0x0000aaaaab1dd5a4 in qdev_prop_set_globals (dev=0xaaaaac214ab0) at hw/core/qdev-properties.c:1218
21
#9 0x0000aaaaab1d9fac in device_post_init (obj=0xaaaaac214ab0) at hw/core/qdev.c:1050
22
...
23
#15 0x0000aaaaab54f310 in object_initialize_with_type (obj=0xaaaaac214ab0, size=52208, type=0xaaaaabe237f0) at qom/object.c:512
24
#16 0x0000aaaaab54fa24 in object_new_with_type (type=0xaaaaabe237f0) at qom/object.c:687
25
#17 0x0000aaaaab54fa80 in object_new (typename=0xaaaaabe23970 "host-arm-cpu") at qom/object.c:702
26
#18 0x0000aaaaaaf04a74 in machvirt_init (machine=0xaaaaac0a8550) at hw/arm/virt.c:1770
27
#19 0x0000aaaaab1e8720 in machine_run_board_init (machine=0xaaaaac0a8550) at hw/core/machine.c:1138
28
#20 0x0000aaaaaaf95394 in qemu_init (argc=5, argv=0xffffffffea58, envp=0xffffffffea88) at softmmu/vl.c:4348
29
#21 0x0000aaaaaada3f74 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at softmmu/main.c:48
30
31
This is because in frame #2, cpu->kvm_state is still NULL
32
(the vCPU is not yet realized).
33
34
KVM has a hard requirement of all cores supporting the same
35
feature set. We only need to check if the accelerator supports
36
a feature, not each vCPU individually.
37
38
Fix by removing the 'CPUState *cpu' argument from the
39
kvm_arm_<FEATURE>_supported() functions.
40
41
Fixes: d70c996df23f ('Use CPUState::kvm_state in kvm_arm_pmu_supported')
42
Reported-by: Haibo Xu <haibo.xu@linaro.org>
43
Reviewed-by: Andrew Jones <drjones@redhat.com>
44
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
45
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
46
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
47
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
48
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
49
---
17
---
50
target/arm/kvm_arm.h | 21 +++++++++------------
18
target/arm/helper.h | 2 +-
51
target/arm/cpu.c | 2 +-
19
target/arm/op_helper.c | 23 +++++++++--------
52
target/arm/cpu64.c | 10 +++++-----
20
target/arm/translate-neon.c.inc | 44 +++++++++++----------------------
53
target/arm/kvm.c | 4 ++--
21
3 files changed, 29 insertions(+), 40 deletions(-)
54
target/arm/kvm64.c | 14 +++++---------
55
5 files changed, 22 insertions(+), 29 deletions(-)
56
22
57
diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h
23
diff --git a/target/arm/helper.h b/target/arm/helper.h
58
index XXXXXXX..XXXXXXX 100644
24
index XXXXXXX..XXXXXXX 100644
59
--- a/target/arm/kvm_arm.h
25
--- a/target/arm/helper.h
60
+++ b/target/arm/kvm_arm.h
26
+++ b/target/arm/helper.h
61
@@ -XXX,XX +XXX,XX @@ void kvm_arm_add_vcpu_properties(Object *obj);
27
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, ptr)
62
28
DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, ptr)
63
/**
29
DEF_HELPER_FLAGS_1(recpe_u32, TCG_CALL_NO_RWG, i32, i32)
64
* kvm_arm_aarch32_supported:
30
DEF_HELPER_FLAGS_1(rsqrte_u32, TCG_CALL_NO_RWG, i32, i32)
65
- * @cs: CPUState
31
-DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i32, i32, i32, ptr, i32)
66
*
32
+DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i64, env, i32, i64, i64)
67
- * Returns: true if the KVM VCPU can enable AArch32 mode
33
68
+ * Returns: true if KVM can enable AArch32 mode
34
DEF_HELPER_3(shl_cc, i32, env, i32, i32)
69
* and false otherwise.
35
DEF_HELPER_3(shr_cc, i32, env, i32, i32)
70
*/
36
diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c
71
-bool kvm_arm_aarch32_supported(CPUState *cs);
37
index XXXXXXX..XXXXXXX 100644
72
+bool kvm_arm_aarch32_supported(void);
38
--- a/target/arm/op_helper.c
73
39
+++ b/target/arm/op_helper.c
74
/**
40
@@ -XXX,XX +XXX,XX @@ void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome,
75
* kvm_arm_pmu_supported:
41
cpu_loop_exit_restore(cs, ra);
76
- * @cs: CPUState
42
}
77
*
43
78
- * Returns: true if the KVM VCPU can enable its PMU
44
-uint32_t HELPER(neon_tbl)(uint32_t ireg, uint32_t def, void *vn,
79
+ * Returns: true if KVM can enable the PMU
45
- uint32_t maxindex)
80
* and false otherwise.
46
+uint64_t HELPER(neon_tbl)(CPUARMState *env, uint32_t desc,
81
*/
47
+ uint64_t ireg, uint64_t def)
82
-bool kvm_arm_pmu_supported(CPUState *cs);
83
+bool kvm_arm_pmu_supported(void);
84
85
/**
86
* kvm_arm_sve_supported:
87
- * @cs: CPUState
88
*
89
- * Returns true if the KVM VCPU can enable SVE and false otherwise.
90
+ * Returns true if KVM can enable SVE and false otherwise.
91
*/
92
-bool kvm_arm_sve_supported(CPUState *cs);
93
+bool kvm_arm_sve_supported(void);
94
95
/**
96
* kvm_arm_get_max_vm_ipa_size:
97
@@ -XXX,XX +XXX,XX @@ static inline void kvm_arm_set_cpu_features_from_host(ARMCPU *cpu)
98
99
static inline void kvm_arm_add_vcpu_properties(Object *obj) {}
100
101
-static inline bool kvm_arm_aarch32_supported(CPUState *cs)
102
+static inline bool kvm_arm_aarch32_supported(void)
103
{
48
{
104
return false;
49
- uint32_t val, shift;
50
- uint64_t *table = vn;
51
+ uint64_t tmp, val = 0;
52
+ uint32_t maxindex = ((desc & 3) + 1) * 8;
53
+ uint32_t base_reg = desc >> 2;
54
+ uint32_t shift, index, reg;
55
56
- val = 0;
57
- for (shift = 0; shift < 32; shift += 8) {
58
- uint32_t index = (ireg >> shift) & 0xff;
59
+ for (shift = 0; shift < 64; shift += 8) {
60
+ index = (ireg >> shift) & 0xff;
61
if (index < maxindex) {
62
- uint32_t tmp = (table[index >> 3] >> ((index & 7) << 3)) & 0xff;
63
- val |= tmp << shift;
64
+ reg = base_reg + (index >> 3);
65
+ tmp = *aa32_vfp_dreg(env, reg);
66
+ tmp = ((tmp >> ((index & 7) << 3)) & 0xff) << shift;
67
} else {
68
- val |= def & (0xff << shift);
69
+ tmp = def & (0xffull << shift);
70
}
71
+ val |= tmp;
72
}
73
return val;
105
}
74
}
106
75
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
107
-static inline bool kvm_arm_pmu_supported(CPUState *cs)
76
index XXXXXXX..XXXXXXX 100644
108
+static inline bool kvm_arm_pmu_supported(void)
77
--- a/target/arm/translate-neon.c.inc
78
+++ b/target/arm/translate-neon.c.inc
79
@@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a)
80
81
static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
109
{
82
{
110
return false;
83
- int n;
111
}
84
- TCGv_i32 tmp, tmp2, tmp3, tmp4;
112
85
- TCGv_ptr ptr1;
113
-static inline bool kvm_arm_sve_supported(CPUState *cs)
86
+ TCGv_i64 val, def;
114
+static inline bool kvm_arm_sve_supported(void)
87
+ TCGv_i32 desc;
115
{
88
116
return false;
89
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
117
}
90
return false;
118
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
91
@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
119
index XXXXXXX..XXXXXXX 100644
92
return true;
120
--- a/target/arm/cpu.c
121
+++ b/target/arm/cpu.c
122
@@ -XXX,XX +XXX,XX @@ static void arm_set_pmu(Object *obj, bool value, Error **errp)
123
ARMCPU *cpu = ARM_CPU(obj);
124
125
if (value) {
126
- if (kvm_enabled() && !kvm_arm_pmu_supported(CPU(cpu))) {
127
+ if (kvm_enabled() && !kvm_arm_pmu_supported()) {
128
error_setg(errp, "'pmu' feature not supported by KVM on this host");
129
return;
130
}
131
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
132
index XXXXXXX..XXXXXXX 100644
133
--- a/target/arm/cpu64.c
134
+++ b/target/arm/cpu64.c
135
@@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp)
136
137
/* Collect the set of vector lengths supported by KVM. */
138
bitmap_zero(kvm_supported, ARM_MAX_VQ);
139
- if (kvm_enabled() && kvm_arm_sve_supported(CPU(cpu))) {
140
+ if (kvm_enabled() && kvm_arm_sve_supported()) {
141
kvm_arm_sve_get_vls(CPU(cpu), kvm_supported);
142
} else if (kvm_enabled()) {
143
assert(!cpu_isar_feature(aa64_sve, cpu));
144
@@ -XXX,XX +XXX,XX @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name,
145
return;
146
}
93
}
147
94
148
- if (kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
95
- n = a->len + 1;
149
+ if (kvm_enabled() && !kvm_arm_sve_supported()) {
96
- if ((a->vn + n) > 32) {
150
error_setg(errp, "cannot set sve-max-vq");
97
+ if ((a->vn + a->len + 1) > 32) {
151
error_append_hint(errp, "SVE not supported by KVM on this host\n");
98
/*
152
return;
99
* This is UNPREDICTABLE; we choose to UNDEF to avoid the
153
@@ -XXX,XX +XXX,XX @@ static void cpu_arm_set_sve_vq(Object *obj, Visitor *v, const char *name,
100
* helper function running off the end of the register file.
154
return;
101
*/
102
return false;
155
}
103
}
156
104
- n <<= 3;
157
- if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
105
- tmp = tcg_temp_new_i32();
158
+ if (value && kvm_enabled() && !kvm_arm_sve_supported()) {
106
- if (a->op) {
159
error_setg(errp, "cannot enable %s", name);
107
- read_neon_element32(tmp, a->vd, 0, MO_32);
160
error_append_hint(errp, "SVE not supported by KVM on this host\n");
108
- } else {
161
return;
109
- tcg_gen_movi_i32(tmp, 0);
162
@@ -XXX,XX +XXX,XX @@ static void cpu_arm_set_sve(Object *obj, Visitor *v, const char *name,
110
- }
163
return;
111
- tmp2 = tcg_temp_new_i32();
112
- read_neon_element32(tmp2, a->vm, 0, MO_32);
113
- ptr1 = vfp_reg_ptr(true, a->vn);
114
- tmp4 = tcg_const_i32(n);
115
- gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4);
116
117
+ desc = tcg_const_i32((a->vn << 2) | a->len);
118
+ def = tcg_temp_new_i64();
119
if (a->op) {
120
- read_neon_element32(tmp, a->vd, 1, MO_32);
121
+ read_neon_element64(def, a->vd, 0, MO_64);
122
} else {
123
- tcg_gen_movi_i32(tmp, 0);
124
+ tcg_gen_movi_i64(def, 0);
164
}
125
}
165
126
- tmp3 = tcg_temp_new_i32();
166
- if (value && kvm_enabled() && !kvm_arm_sve_supported(CPU(cpu))) {
127
- read_neon_element32(tmp3, a->vm, 1, MO_32);
167
+ if (value && kvm_enabled() && !kvm_arm_sve_supported()) {
128
- gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4);
168
error_setg(errp, "'sve' feature not supported by KVM on this host");
129
- tcg_temp_free_i32(tmp);
169
return;
130
- tcg_temp_free_i32(tmp4);
170
}
131
- tcg_temp_free_ptr(ptr1);
171
@@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp)
132
+ val = tcg_temp_new_i64();
172
* uniform execution state like do_interrupt.
133
+ read_neon_element64(val, a->vm, 0, MO_64);
173
*/
134
174
if (value == false) {
135
- write_neon_element32(tmp2, a->vd, 0, MO_32);
175
- if (!kvm_enabled() || !kvm_arm_aarch32_supported(CPU(cpu))) {
136
- write_neon_element32(tmp3, a->vd, 1, MO_32);
176
+ if (!kvm_enabled() || !kvm_arm_aarch32_supported()) {
137
- tcg_temp_free_i32(tmp2);
177
error_setg(errp, "'aarch64' feature cannot be disabled "
138
- tcg_temp_free_i32(tmp3);
178
"unless KVM is enabled and 32-bit EL1 "
139
+ gen_helper_neon_tbl(val, cpu_env, desc, val, def);
179
"is supported");
140
+ write_neon_element64(val, a->vd, 0, MO_64);
180
diff --git a/target/arm/kvm.c b/target/arm/kvm.c
141
+
181
index XXXXXXX..XXXXXXX 100644
142
+ tcg_temp_free_i64(def);
182
--- a/target/arm/kvm.c
143
+ tcg_temp_free_i64(val);
183
+++ b/target/arm/kvm.c
144
+ tcg_temp_free_i32(desc);
184
@@ -XXX,XX +XXX,XX @@ void kvm_arm_add_vcpu_properties(Object *obj)
185
}
186
}
187
188
-bool kvm_arm_pmu_supported(CPUState *cpu)
189
+bool kvm_arm_pmu_supported(void)
190
{
191
- return kvm_check_extension(cpu->kvm_state, KVM_CAP_ARM_PMU_V3);
192
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_PMU_V3);
193
}
194
195
int kvm_arm_get_max_vm_ipa_size(MachineState *ms)
196
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
197
index XXXXXXX..XXXXXXX 100644
198
--- a/target/arm/kvm64.c
199
+++ b/target/arm/kvm64.c
200
@@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
201
return true;
145
return true;
202
}
146
}
203
204
-bool kvm_arm_aarch32_supported(CPUState *cpu)
205
+bool kvm_arm_aarch32_supported(void)
206
{
207
- KVMState *s = KVM_STATE(current_accel());
208
-
209
- return kvm_check_extension(s, KVM_CAP_ARM_EL1_32BIT);
210
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_EL1_32BIT);
211
}
212
213
-bool kvm_arm_sve_supported(CPUState *cpu)
214
+bool kvm_arm_sve_supported(void)
215
{
216
- KVMState *s = KVM_STATE(current_accel());
217
-
218
- return kvm_check_extension(s, KVM_CAP_ARM_SVE);
219
+ return kvm_check_extension(kvm_state, KVM_CAP_ARM_SVE);
220
}
221
222
QEMU_BUILD_BUG_ON(KVM_ARM64_SVE_VQ_MIN != 1);
223
@@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs)
224
env->features &= ~(1ULL << ARM_FEATURE_PMU);
225
}
226
if (cpu_isar_feature(aa64_sve, cpu)) {
227
- assert(kvm_arm_sve_supported(cs));
228
+ assert(kvm_arm_sve_supported());
229
cpu->kvm_init_features[0] |= 1 << KVM_ARM_VCPU_SVE;
230
}
231
147
232
--
148
--
233
2.20.1
149
2.20.1
234
150
235
151
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
We can use one MPC per SRAM bank, but we currently only wire the
4
IRQ from the first expansion MPC to the IRQ splitter. Fix that.
5
6
Fixes: bb75e16d5e6 ("hw/arm/iotkit: Wire up MPC interrupt lines")
3
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
7
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
4
Message-id: 20200617072539.32686-14-f4bug@amsat.org
8
Message-id: 20201107193403.436146-2-f4bug@amsat.org
5
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
---
11
---
8
hw/arm/mps2.c | 1 +
12
hw/arm/armsse.c | 3 ++-
9
1 file changed, 1 insertion(+)
13
1 file changed, 2 insertions(+), 1 deletion(-)
10
14
11
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
15
diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c
12
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
13
--- a/hw/arm/mps2.c
17
--- a/hw/arm/armsse.c
14
+++ b/hw/arm/mps2.c
18
+++ b/hw/arm/armsse.c
15
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
19
@@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp)
16
0x4002a000}; /* Shield1 */
20
qdev_get_gpio_in(dev_splitter, 0));
17
sysbus_create_simple(TYPE_ARM_SBCON_I2C, i2cbase[i], NULL);
21
qdev_connect_gpio_out(dev_splitter, 0,
18
}
22
qdev_get_gpio_in_named(dev_secctl,
19
+ create_unimplemented_device("i2s", 0x40024000, 0x400);
23
- "mpc_status", 0));
20
24
+ "mpc_status",
21
/* In hardware this is a LAN9220; the LAN9118 is software compatible
25
+ i - IOTS_NUM_EXP_MPC));
22
* except that it doesn't support the checksum-offload feature.
26
}
27
28
qdev_connect_gpio_out(dev_splitter, 1,
23
--
29
--
24
2.20.1
30
2.20.1
25
31
26
32
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
The system configuration controller (SYSCFG) doesn't have
4
any output IRQ (and the INTC input #71 belongs to the UART6).
5
Remove the invalid code.
6
7
Fixes: db635521a02 ("stm32f205: Add the stm32f205 SoC")
3
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
8
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
4
Message-id: 20200617072539.32686-11-f4bug@amsat.org
9
Message-id: 20201107193403.436146-3-f4bug@amsat.org
5
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
---
12
---
8
hw/arm/mps2.c | 9 +++++++++
13
include/hw/misc/stm32f2xx_syscfg.h | 2 --
9
1 file changed, 9 insertions(+)
14
hw/arm/stm32f205_soc.c | 1 -
15
hw/misc/stm32f2xx_syscfg.c | 2 --
16
3 files changed, 5 deletions(-)
10
17
11
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
18
diff --git a/include/hw/misc/stm32f2xx_syscfg.h b/include/hw/misc/stm32f2xx_syscfg.h
12
index XXXXXXX..XXXXXXX 100644
19
index XXXXXXX..XXXXXXX 100644
13
--- a/hw/arm/mps2.c
20
--- a/include/hw/misc/stm32f2xx_syscfg.h
14
+++ b/hw/arm/mps2.c
21
+++ b/include/hw/misc/stm32f2xx_syscfg.h
15
@@ -XXX,XX +XXX,XX @@
22
@@ -XXX,XX +XXX,XX @@ struct STM32F2XXSyscfgState {
16
#include "hw/timer/cmsdk-apb-timer.h"
23
uint32_t syscfg_exticr3;
17
#include "hw/timer/cmsdk-apb-dualtimer.h"
24
uint32_t syscfg_exticr4;
18
#include "hw/misc/mps2-scc.h"
25
uint32_t syscfg_cmpcr;
19
+#include "hw/misc/mps2-fpgaio.h"
26
-
20
#include "hw/net/lan9118.h"
27
- qemu_irq irq;
21
#include "net/net.h"
28
};
22
+#include "hw/watchdog/cmsdk-apb-watchdog.h"
29
23
30
#endif /* HW_STM32F2XX_SYSCFG_H */
24
typedef enum MPS2FPGAType {
31
diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c
25
FPGA_AN385,
32
index XXXXXXX..XXXXXXX 100644
26
@@ -XXX,XX +XXX,XX @@ typedef struct {
33
--- a/hw/arm/stm32f205_soc.c
27
MemoryRegion sram;
34
+++ b/hw/arm/stm32f205_soc.c
28
/* FPGA APB subsystem */
35
@@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp)
29
MPS2SCC scc;
36
}
30
+ MPS2FPGAIO fpgaio;
37
busdev = SYS_BUS_DEVICE(dev);
31
/* CMSDK APB subsystem */
38
sysbus_mmio_map(busdev, 0, 0x40013800);
32
CMSDKAPBDualTimer dualtimer;
39
- sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, 71));
33
+ CMSDKAPBWatchdog watchdog;
40
34
} MPS2MachineState;
41
/* Attach UART (uses USART registers) and USART controllers */
35
42
for (i = 0; i < STM_NUM_USARTS; i++) {
36
#define TYPE_MPS2_MACHINE "mps2"
43
diff --git a/hw/misc/stm32f2xx_syscfg.c b/hw/misc/stm32f2xx_syscfg.c
37
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
44
index XXXXXXX..XXXXXXX 100644
38
qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id);
45
--- a/hw/misc/stm32f2xx_syscfg.c
39
sysbus_realize(SYS_BUS_DEVICE(&mms->scc), &error_fatal);
46
+++ b/hw/misc/stm32f2xx_syscfg.c
40
sysbus_mmio_map(SYS_BUS_DEVICE(sccdev), 0, 0x4002f000);
47
@@ -XXX,XX +XXX,XX @@ static void stm32f2xx_syscfg_init(Object *obj)
41
+ object_initialize_child(OBJECT(mms), "fpgaio",
48
{
42
+ &mms->fpgaio, TYPE_MPS2_FPGAIO);
49
STM32F2XXSyscfgState *s = STM32F2XX_SYSCFG(obj);
43
+ qdev_prop_set_uint32(DEVICE(&mms->fpgaio), "prescale-clk", 25000000);
50
44
+ sysbus_realize(SYS_BUS_DEVICE(&mms->fpgaio), &error_fatal);
51
- sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq);
45
+ sysbus_mmio_map(SYS_BUS_DEVICE(&mms->fpgaio), 0, 0x40028000);
52
-
46
53
memory_region_init_io(&s->mmio, obj, &stm32f2xx_syscfg_ops, s,
47
/* In hardware this is a LAN9220; the LAN9118 is software compatible
54
TYPE_STM32F2XX_SYSCFG, 0x400);
48
* except that it doesn't support the checksum-offload feature.
55
sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio);
49
--
56
--
50
2.20.1
57
2.20.1
51
58
52
59
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
From 'Application Note AN521', chapter 4.7:
3
omap2420_mpu_init() introduced in commit 827df9f3c5f ("Add basic
4
OMAP2 chip support") takes care of creating the 3 UARTs.
4
5
5
The SMM implements four SBCon serial modules:
6
Then commit 58a26b477e9 ("Emulate a serial bluetooth HCI with H4+
7
extensions and attach to n8x0's UART") added n8x0_uart_setup()
8
which create the UART and connects it to an IRQ output,
9
overwritting the existing peripheral and its IRQ connection.
10
This is incorrect.
6
11
7
One SBCon module for use by the Color LCD touch interface.
12
Fortunately we don't need to fix this, because commit 6da68df7f9b
8
One SBCon module to configure the audio controller.
13
("hw/arm/nseries: Replace the bluetooth chardev with a "null"
9
Two general purpose SBCon modules, that connect to the
14
chardev") removed the use of this peripheral. We can simply
10
Expansion headers J7 and J8, are intended for use with the
15
remove the code.
11
V2C-Shield1 which provide an I2C interface on the headers.
12
16
13
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
17
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
14
Message-id: 20200617072539.32686-15-f4bug@amsat.org
18
Message-id: 20201107193403.436146-4-f4bug@amsat.org
15
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
19
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
20
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
---
21
---
18
hw/arm/mps2-tz.c | 23 ++++++++++++++++++-----
22
hw/arm/nseries.c | 11 -----------
19
1 file changed, 18 insertions(+), 5 deletions(-)
23
1 file changed, 11 deletions(-)
20
24
21
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
25
diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c
22
index XXXXXXX..XXXXXXX 100644
26
index XXXXXXX..XXXXXXX 100644
23
--- a/hw/arm/mps2-tz.c
27
--- a/hw/arm/nseries.c
24
+++ b/hw/arm/mps2-tz.c
28
+++ b/hw/arm/nseries.c
25
@@ -XXX,XX +XXX,XX @@
29
@@ -XXX,XX +XXX,XX @@ static void n8x0_cbus_setup(struct n800_s *s)
26
#include "hw/arm/armsse.h"
30
cbus_attach(cbus, s->tahvo = tahvo_init(tahvo_irq, 1));
27
#include "hw/dma/pl080.h"
28
#include "hw/ssi/pl022.h"
29
+#include "hw/i2c/arm_sbcon_i2c.h"
30
#include "hw/net/lan9118.h"
31
#include "net/net.h"
32
#include "hw/core/split-irq.h"
33
@@ -XXX,XX +XXX,XX @@ typedef struct {
34
TZPPC ppc[5];
35
TZMPC ssram_mpc[3];
36
PL022State spi[5];
37
- UnimplementedDeviceState i2c[4];
38
+ ArmSbconI2CState i2c[4];
39
UnimplementedDeviceState i2s_audio;
40
UnimplementedDeviceState gpio[4];
41
UnimplementedDeviceState gfx;
42
@@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque,
43
return sysbus_mmio_get_region(s, 0);
44
}
31
}
45
32
46
+static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque,
33
-static void n8x0_uart_setup(struct n800_s *s)
47
+ const char *name, hwaddr size)
34
-{
48
+{
35
- Chardev *radio = qemu_chr_new("bt-dummy-uart", "null", NULL);
49
+ ArmSbconI2CState *i2c = opaque;
36
- /*
50
+ SysBusDevice *s;
37
- * Note: We used to connect N8X0_BT_RESET_GPIO and N8X0_BT_WKUP_GPIO
51
+
38
- * here, but this code has been removed with the bluetooth backend.
52
+ object_initialize_child(OBJECT(mms), name, i2c, TYPE_ARM_SBCON_I2C);
39
- */
53
+ s = SYS_BUS_DEVICE(i2c);
40
- omap_uart_attach(s->mpu->uart[BT_UART], radio);
54
+ sysbus_realize(s, &error_fatal);
41
-}
55
+ return sysbus_mmio_get_region(s, 0);
42
-
56
+}
43
static void n8x0_usb_setup(struct n800_s *s)
57
+
58
static void mps2tz_common_init(MachineState *machine)
59
{
44
{
60
MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine);
45
SysBusDevice *dev;
61
@@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine)
46
@@ -XXX,XX +XXX,XX @@ static void n8x0_init(MachineState *machine,
62
{ "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000 },
47
n8x0_spi_setup(s);
63
{ "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000 },
48
n8x0_dss_setup(s);
64
{ "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000 },
49
n8x0_cbus_setup(s);
65
- { "i2c0", make_unimp_dev, &mms->i2c[0], 0x40207000, 0x1000 },
50
- n8x0_uart_setup(s);
66
- { "i2c1", make_unimp_dev, &mms->i2c[1], 0x40208000, 0x1000 },
51
if (machine_usb(machine)) {
67
- { "i2c2", make_unimp_dev, &mms->i2c[2], 0x4020c000, 0x1000 },
52
n8x0_usb_setup(s);
68
- { "i2c3", make_unimp_dev, &mms->i2c[3], 0x4020d000, 0x1000 },
53
}
69
+ { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 },
70
+ { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 },
71
+ { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 },
72
+ { "i2c3", make_i2c, &mms->i2c[3], 0x4020d000, 0x1000 },
73
},
74
}, {
75
.name = "apb_ppcexp2",
76
--
54
--
77
2.20.1
55
2.20.1
78
56
79
57
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
We already model the CMSDK APB watchdog device, let's use it!
3
The MusicPal board code connects both of the IRQ outputs of the UART
4
to the same INTC qemu_irq. Connecting two qemu_irqs outputs directly
5
to the same input is not valid as it produces subtly wrong behaviour
6
(for instance if both the IRQ lines are high, and then one goes
7
low, the INTC input will see this as a high-to-low transition
8
even though the second IRQ line should still be holding it high).
4
9
5
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
10
This kind of wiring needs an explicitly created OR gate; add one.
11
12
Inspired-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
13
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
7
Message-id: 20200617072539.32686-9-f4bug@amsat.org
14
Message-id: 20201107193403.436146-5-f4bug@amsat.org
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
15
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
17
---
11
hw/arm/mps2.c | 7 +++++++
18
hw/arm/musicpal.c | 17 +++++++++++++----
12
hw/arm/Kconfig | 1 +
19
hw/arm/Kconfig | 1 +
13
2 files changed, 8 insertions(+)
20
2 files changed, 14 insertions(+), 4 deletions(-)
14
21
15
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
22
diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c
16
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/arm/mps2.c
24
--- a/hw/arm/musicpal.c
18
+++ b/hw/arm/mps2.c
25
+++ b/hw/arm/musicpal.c
19
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
26
@@ -XXX,XX +XXX,XX @@
20
sysbus_connect_irq(SYS_BUS_DEVICE(&mms->dualtimer), 0,
27
#include "ui/console.h"
21
qdev_get_gpio_in(armv7m, 10));
28
#include "hw/i2c/i2c.h"
22
sysbus_mmio_map(SYS_BUS_DEVICE(&mms->dualtimer), 0, 0x40002000);
29
#include "hw/irq.h"
23
+ object_initialize_child(OBJECT(mms), "watchdog", &mms->watchdog,
30
+#include "hw/or-irq.h"
24
+ TYPE_CMSDK_APB_WATCHDOG);
31
#include "hw/audio/wm8750.h"
25
+ qdev_prop_set_uint32(DEVICE(&mms->watchdog), "wdogclk-frq", SYSCLK_FRQ);
32
#include "sysemu/block-backend.h"
26
+ sysbus_realize(SYS_BUS_DEVICE(&mms->watchdog), &error_fatal);
33
#include "sysemu/runstate.h"
27
+ sysbus_connect_irq(SYS_BUS_DEVICE(&mms->watchdog), 0,
34
@@ -XXX,XX +XXX,XX @@
28
+ qdev_get_gpio_in_named(armv7m, "NMI", 0));
35
#define MP_TIMER4_IRQ 7
29
+ sysbus_mmio_map(SYS_BUS_DEVICE(&mms->watchdog), 0, 0x40008000);
36
#define MP_EHCI_IRQ 8
30
37
#define MP_ETH_IRQ 9
31
/* FPGA APB subsystem */
38
-#define MP_UART1_IRQ 11
32
object_initialize_child(OBJECT(mms), "scc", &mms->scc, TYPE_MPS2_SCC);
39
-#define MP_UART2_IRQ 11
40
+#define MP_UART_SHARED_IRQ 11
41
#define MP_GPIO_IRQ 12
42
#define MP_RTC_IRQ 28
43
#define MP_AUDIO_IRQ 30
44
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
45
ARMCPU *cpu;
46
qemu_irq pic[32];
47
DeviceState *dev;
48
+ DeviceState *uart_orgate;
49
DeviceState *i2c_dev;
50
DeviceState *lcd_dev;
51
DeviceState *key_dev;
52
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
53
pic[MP_TIMER2_IRQ], pic[MP_TIMER3_IRQ],
54
pic[MP_TIMER4_IRQ], NULL);
55
56
- serial_mm_init(address_space_mem, MP_UART1_BASE, 2, pic[MP_UART1_IRQ],
57
+ /* Logically OR both UART IRQs together */
58
+ uart_orgate = DEVICE(object_new(TYPE_OR_IRQ));
59
+ object_property_set_int(OBJECT(uart_orgate), "num-lines", 2, &error_fatal);
60
+ qdev_realize_and_unref(uart_orgate, NULL, &error_fatal);
61
+ qdev_connect_gpio_out(DEVICE(uart_orgate), 0, pic[MP_UART_SHARED_IRQ]);
62
+
63
+ serial_mm_init(address_space_mem, MP_UART1_BASE, 2,
64
+ qdev_get_gpio_in(uart_orgate, 0),
65
1825000, serial_hd(0), DEVICE_NATIVE_ENDIAN);
66
- serial_mm_init(address_space_mem, MP_UART2_BASE, 2, pic[MP_UART2_IRQ],
67
+ serial_mm_init(address_space_mem, MP_UART2_BASE, 2,
68
+ qdev_get_gpio_in(uart_orgate, 1),
69
1825000, serial_hd(1), DEVICE_NATIVE_ENDIAN);
70
71
/* Register flash */
33
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
72
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
34
index XXXXXXX..XXXXXXX 100644
73
index XXXXXXX..XXXXXXX 100644
35
--- a/hw/arm/Kconfig
74
--- a/hw/arm/Kconfig
36
+++ b/hw/arm/Kconfig
75
+++ b/hw/arm/Kconfig
37
@@ -XXX,XX +XXX,XX @@ config MPS2
76
@@ -XXX,XX +XXX,XX @@ config MUSCA
38
select PL080 # DMA controller
77
39
select SPLIT_IRQ
78
config MUSICPAL
40
select UNIMP
41
+ select CMSDK_APB_WATCHDOG
42
43
config FSL_IMX7
44
bool
79
bool
80
+ select OR_IRQ
81
select BITBANG_I2C
82
select MARVELL_88W8618
83
select PTIMER
45
--
84
--
46
2.20.1
85
2.20.1
47
86
48
87
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
Use self-explicit definitions instead of magic values.
3
We don't need to fill the full pic[] array if we only use
4
few of the interrupt lines. Directly call qdev_get_gpio_in()
5
when necessary.
4
6
5
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
7
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
6
Message-id: 20200617072539.32686-4-f4bug@amsat.org
8
Message-id: 20201107193403.436146-6-f4bug@amsat.org
7
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
---
11
---
10
hw/i2c/versatile_i2c.c | 7 +++++--
12
hw/arm/musicpal.c | 25 +++++++++++++------------
11
1 file changed, 5 insertions(+), 2 deletions(-)
13
1 file changed, 13 insertions(+), 12 deletions(-)
12
14
13
diff --git a/hw/i2c/versatile_i2c.c b/hw/i2c/versatile_i2c.c
15
diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c
14
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
15
--- a/hw/i2c/versatile_i2c.c
17
--- a/hw/arm/musicpal.c
16
+++ b/hw/i2c/versatile_i2c.c
18
+++ b/hw/arm/musicpal.c
17
@@ -XXX,XX +XXX,XX @@ REG32(CONTROL_GET, 0)
19
@@ -XXX,XX +XXX,XX @@ static struct arm_boot_info musicpal_binfo = {
18
REG32(CONTROL_SET, 0)
20
static void musicpal_init(MachineState *machine)
19
REG32(CONTROL_CLR, 4)
20
21
+#define SCL BIT(0)
22
+#define SDA BIT(1)
23
+
24
static uint64_t versatile_i2c_read(void *opaque, hwaddr offset,
25
unsigned size)
26
{
21
{
27
@@ -XXX,XX +XXX,XX @@ static void versatile_i2c_write(void *opaque, hwaddr offset,
22
ARMCPU *cpu;
28
qemu_log_mask(LOG_GUEST_ERROR,
23
- qemu_irq pic[32];
29
"%s: Bad offset 0x%x\n", __func__, (int)offset);
24
DeviceState *dev;
30
}
25
+ DeviceState *pic;
31
- bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SCL, (s->out & 1) != 0);
26
DeviceState *uart_orgate;
32
- s->in = bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SDA, (s->out & 2) != 0);
27
DeviceState *i2c_dev;
33
+ bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SCL, (s->out & SCL) != 0);
28
DeviceState *lcd_dev;
34
+ s->in = bitbang_i2c_set(&s->bitbang, BITBANG_I2C_SDA, (s->out & SDA) != 0);
29
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
35
}
30
&error_fatal);
36
31
memory_region_add_subregion(address_space_mem, MP_SRAM_BASE, sram);
37
static const MemoryRegionOps versatile_i2c_ops = {
32
33
- dev = sysbus_create_simple(TYPE_MV88W8618_PIC, MP_PIC_BASE,
34
+ pic = sysbus_create_simple(TYPE_MV88W8618_PIC, MP_PIC_BASE,
35
qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ));
36
- for (i = 0; i < 32; i++) {
37
- pic[i] = qdev_get_gpio_in(dev, i);
38
- }
39
- sysbus_create_varargs(TYPE_MV88W8618_PIT, MP_PIT_BASE, pic[MP_TIMER1_IRQ],
40
- pic[MP_TIMER2_IRQ], pic[MP_TIMER3_IRQ],
41
- pic[MP_TIMER4_IRQ], NULL);
42
+ sysbus_create_varargs(TYPE_MV88W8618_PIT, MP_PIT_BASE,
43
+ qdev_get_gpio_in(pic, MP_TIMER1_IRQ),
44
+ qdev_get_gpio_in(pic, MP_TIMER2_IRQ),
45
+ qdev_get_gpio_in(pic, MP_TIMER3_IRQ),
46
+ qdev_get_gpio_in(pic, MP_TIMER4_IRQ), NULL);
47
48
/* Logically OR both UART IRQs together */
49
uart_orgate = DEVICE(object_new(TYPE_OR_IRQ));
50
object_property_set_int(OBJECT(uart_orgate), "num-lines", 2, &error_fatal);
51
qdev_realize_and_unref(uart_orgate, NULL, &error_fatal);
52
- qdev_connect_gpio_out(DEVICE(uart_orgate), 0, pic[MP_UART_SHARED_IRQ]);
53
+ qdev_connect_gpio_out(DEVICE(uart_orgate), 0,
54
+ qdev_get_gpio_in(pic, MP_UART_SHARED_IRQ));
55
56
serial_mm_init(address_space_mem, MP_UART1_BASE, 2,
57
qdev_get_gpio_in(uart_orgate, 0),
58
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
59
OBJECT(get_system_memory()), &error_fatal);
60
sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal);
61
sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, MP_ETH_BASE);
62
- sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[MP_ETH_IRQ]);
63
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0,
64
+ qdev_get_gpio_in(pic, MP_ETH_IRQ));
65
66
sysbus_create_simple("mv88w8618_wlan", MP_WLAN_BASE, NULL);
67
68
sysbus_create_simple(TYPE_MUSICPAL_MISC, MP_MISC_BASE, NULL);
69
70
dev = sysbus_create_simple(TYPE_MUSICPAL_GPIO, MP_GPIO_BASE,
71
- pic[MP_GPIO_IRQ]);
72
+ qdev_get_gpio_in(pic, MP_GPIO_IRQ));
73
i2c_dev = sysbus_create_simple("gpio_i2c", -1, NULL);
74
i2c = (I2CBus *)qdev_get_child_bus(i2c_dev, "i2c");
75
76
@@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine)
77
NULL);
78
sysbus_realize_and_unref(s, &error_fatal);
79
sysbus_mmio_map(s, 0, MP_AUDIO_BASE);
80
- sysbus_connect_irq(s, 0, pic[MP_AUDIO_IRQ]);
81
+ sysbus_connect_irq(s, 0, qdev_get_gpio_in(pic, MP_AUDIO_IRQ));
82
83
musicpal_binfo.ram_size = MP_RAM_DEFAULT_SIZE;
84
arm_load_kernel(cpu, machine, &musicpal_binfo);
38
--
85
--
39
2.20.1
86
2.20.1
40
87
41
88
diff view generated by jsdifflib
1
In commit cfdb2c0c95ae9205b0 ("target/arm: Vectorize SABA/UABA") we
1
The nseries machines have a codepath that allows them to load a
2
replaced the old handling of SABA/UABA with a vectorized implementation
2
secondary bootloader. This code wasn't checking that the
3
which returns early rather than falling into the loop-ever-elements
3
load_image_targphys() succeeded. Check the return value and report
4
code. We forgot to delete the part of the old looping code that
4
the error to the user.
5
did the accumulate step, and Coverity correctly warns (CID 1428955)
6
that this code is now dead. Delete it.
7
5
8
Fixes: cfdb2c0c95ae9205b0
6
While we're in the vicinity, fix the comment style of the
7
comment documenting what this image load is doing.
8
9
Fixes: Coverity CID 1192904
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
11
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 20201103114918.11807-1-peter.maydell@linaro.org
12
Message-id: 20200619171547.29780-1-peter.maydell@linaro.org
13
---
13
---
14
target/arm/translate-a64.c | 12 ------------
14
hw/arm/nseries.c | 15 +++++++++++----
15
1 file changed, 12 deletions(-)
15
1 file changed, 11 insertions(+), 4 deletions(-)
16
16
17
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
17
diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c
18
index XXXXXXX..XXXXXXX 100644
18
index XXXXXXX..XXXXXXX 100644
19
--- a/target/arm/translate-a64.c
19
--- a/hw/arm/nseries.c
20
+++ b/target/arm/translate-a64.c
20
+++ b/hw/arm/nseries.c
21
@@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn)
21
@@ -XXX,XX +XXX,XX @@ static void n8x0_init(MachineState *machine,
22
genfn(tcg_res, tcg_op1, tcg_op2);
22
/* No, wait, better start at the ROM. */
23
}
23
s->mpu->cpu->env.regs[15] = OMAP2_Q2_BASE + 0x400000;
24
24
25
- if (opcode == 0xf) {
25
- /* This is intended for loading the `secondary.bin' program from
26
- /* SABA, UABA: accumulating ops */
26
+ /*
27
- static NeonGenTwoOpFn * const fns[3] = {
27
+ * This is intended for loading the `secondary.bin' program from
28
- gen_helper_neon_add_u8,
28
* Nokia images (the NOLO bootloader). The entry point seems
29
- gen_helper_neon_add_u16,
29
* to be at OMAP2_Q2_BASE + 0x400000.
30
- tcg_gen_add_i32,
30
*
31
- };
31
@@ -XXX,XX +XXX,XX @@ static void n8x0_init(MachineState *machine,
32
-
32
* for them the entry point needs to be set to OMAP2_SRAM_BASE.
33
- read_vec_element_i32(s, tcg_op1, rd, pass, MO_32);
33
*
34
- fns[size](tcg_res, tcg_op1, tcg_res);
34
* The code above is for loading the `zImage' file from Nokia
35
- }
35
- * images. */
36
-
36
- load_image_targphys(option_rom[0].name, OMAP2_Q2_BASE + 0x400000,
37
write_vec_element_i32(s, tcg_res, rd, pass, MO_32);
37
- machine->ram_size - 0x400000);
38
38
+ * images.
39
tcg_temp_free_i32(tcg_res);
39
+ */
40
+ if (load_image_targphys(option_rom[0].name,
41
+ OMAP2_Q2_BASE + 0x400000,
42
+ machine->ram_size - 0x400000) < 0) {
43
+ error_report("Failed to load secondary bootloader %s",
44
+ option_rom[0].name);
45
+ exit(EXIT_FAILURE);
46
+ }
47
48
n800_setup_nolo_tags(nolo_tags);
49
cpu_physical_memory_write(OMAP2_SRAM_BASE, nolo_tags, 0x10000);
40
--
50
--
41
2.20.1
51
2.20.1
42
52
43
53
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Havard Skinnemoen <hskinnemoen@google.com>
2
2
3
By using the TYPE_* definitions for devices, we can:
3
The number of runs is equal to the number of 0-1 and 1-0 transitions,
4
- quickly find where devices are used with 'git-grep'
4
plus one. Currently, it's counting the number of times these transitions
5
- easily rename a device (one-line change).
5
do _not_ happen, plus one.
6
6
7
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
7
Source:
8
Message-id: 20200617072539.32686-6-f4bug@amsat.org
8
https://nvlpubs.nist.gov/nistpubs/Legacy/SP/nistspecialpublication800-22r1a.pdf
9
section 2.3.4 point (3).
10
11
Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com>
12
Message-id: 20201103011457.2959989-2-hskinnemoen@google.com
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
15
---
12
hw/arm/realview.c | 3 ++-
16
tests/qtest/npcm7xx_rng-test.c | 2 +-
13
hw/arm/versatilepb.c | 3 ++-
17
1 file changed, 1 insertion(+), 1 deletion(-)
14
hw/arm/vexpress.c | 3 ++-
15
3 files changed, 6 insertions(+), 3 deletions(-)
16
18
17
diff --git a/hw/arm/realview.c b/hw/arm/realview.c
19
diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c
18
index XXXXXXX..XXXXXXX 100644
20
index XXXXXXX..XXXXXXX 100644
19
--- a/hw/arm/realview.c
21
--- a/tests/qtest/npcm7xx_rng-test.c
20
+++ b/hw/arm/realview.c
22
+++ b/tests/qtest/npcm7xx_rng-test.c
21
@@ -XXX,XX +XXX,XX @@
23
@@ -XXX,XX +XXX,XX @@ static double calc_runs_p(const unsigned long *buf, unsigned int nr_bits)
22
#include "hw/cpu/a9mpcore.h"
24
pi = (double)nr_ones / nr_bits;
23
#include "hw/intc/realview_gic.h"
25
24
#include "hw/irq.h"
26
for (k = 0; k < nr_bits - 1; k++) {
25
+#include "hw/i2c/arm_sbcon_i2c.h"
27
- vn_obs += !(test_bit(k, buf) ^ test_bit(k + 1, buf));
26
28
+ vn_obs += (test_bit(k, buf) ^ test_bit(k + 1, buf));
27
#define SMP_BOOT_ADDR 0xe0000000
28
#define SMP_BOOTREG_ADDR 0x10000030
29
@@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine,
30
}
31
}
29
}
32
30
vn_obs += 1;
33
- dev = sysbus_create_simple("versatile_i2c", 0x10002000, NULL);
34
+ dev = sysbus_create_simple(TYPE_VERSATILE_I2C, 0x10002000, NULL);
35
i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c");
36
i2c_create_slave(i2c, "ds1338", 0x68);
37
38
diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c
39
index XXXXXXX..XXXXXXX 100644
40
--- a/hw/arm/versatilepb.c
41
+++ b/hw/arm/versatilepb.c
42
@@ -XXX,XX +XXX,XX @@
43
#include "sysemu/sysemu.h"
44
#include "hw/pci/pci.h"
45
#include "hw/i2c/i2c.h"
46
+#include "hw/i2c/arm_sbcon_i2c.h"
47
#include "hw/irq.h"
48
#include "hw/boards.h"
49
#include "exec/address-spaces.h"
50
@@ -XXX,XX +XXX,XX @@ static void versatile_init(MachineState *machine, int board_id)
51
/* Add PL031 Real Time Clock. */
52
sysbus_create_simple("pl031", 0x101e8000, pic[10]);
53
54
- dev = sysbus_create_simple("versatile_i2c", 0x10002000, NULL);
55
+ dev = sysbus_create_simple(TYPE_VERSATILE_I2C, 0x10002000, NULL);
56
i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c");
57
i2c_create_slave(i2c, "ds1338", 0x68);
58
59
diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c
60
index XXXXXXX..XXXXXXX 100644
61
--- a/hw/arm/vexpress.c
62
+++ b/hw/arm/vexpress.c
63
@@ -XXX,XX +XXX,XX @@
64
#include "hw/char/pl011.h"
65
#include "hw/cpu/a9mpcore.h"
66
#include "hw/cpu/a15mpcore.h"
67
+#include "hw/i2c/arm_sbcon_i2c.h"
68
69
#define VEXPRESS_BOARD_ID 0x8e0
70
#define VEXPRESS_FLASH_SIZE (64 * 1024 * 1024)
71
@@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine)
72
sysbus_create_simple("sp804", map[VE_TIMER01], pic[2]);
73
sysbus_create_simple("sp804", map[VE_TIMER23], pic[3]);
74
75
- dev = sysbus_create_simple("versatile_i2c", map[VE_SERIALDVI], NULL);
76
+ dev = sysbus_create_simple(TYPE_VERSATILE_I2C, map[VE_SERIALDVI], NULL);
77
i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c");
78
i2c_create_slave(i2c, "sii9022", 0x39);
79
31
80
--
32
--
81
2.20.1
33
2.20.1
82
34
83
35
diff view generated by jsdifflib
1
Convert the Neon VREV64 insn from the 2-reg-misc grouping to decodetree.
1
Checks for UNDEF cases should go before the "is VFP enabled?" access
2
check, except in special cases. Move a stray UNDEF check in the VTBL
3
trans function up above the access check.
2
4
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200616170844.13318-2-peter.maydell@linaro.org
7
Message-id: 20201109145324.2859-1-peter.maydell@linaro.org
6
---
8
---
7
target/arm/neon-dp.decode | 12 ++++++++
9
target/arm/translate-neon.c.inc | 8 ++++----
8
target/arm/translate-neon.inc.c | 50 +++++++++++++++++++++++++++++++++
10
1 file changed, 4 insertions(+), 4 deletions(-)
9
target/arm/translate.c | 24 ++--------------
10
3 files changed, 64 insertions(+), 22 deletions(-)
11
11
12
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
12
diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc
13
index XXXXXXX..XXXXXXX 100644
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-dp.decode
14
--- a/target/arm/translate-neon.c.inc
15
+++ b/target/arm/neon-dp.decode
15
+++ b/target/arm/translate-neon.c.inc
16
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
16
@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
17
vm=%vm_dp vd=%vd_dp size=1
17
return false;
18
VDUP_scalar 1111 001 1 1 . 11 index:1 100 .... 11 000 q:1 . 0 .... \
18
}
19
vm=%vm_dp vd=%vd_dp size=2
19
20
+
20
- if (!vfp_access_check(s)) {
21
+ ##################################################################
21
- return true;
22
+ # 2-reg-misc grouping:
22
- }
23
+ # 1111 001 11 D 11 size:2 opc1:2 Vd:4 0 opc2:4 q:1 M 0 Vm:4
23
-
24
+ ##################################################################
24
if ((a->vn + a->len + 1) > 32) {
25
+
25
/*
26
+ &2misc vd vm q size
26
* This is UNPREDICTABLE; we choose to UNDEF to avoid the
27
+
27
@@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a)
28
+ @2misc .... ... .. . .. size:2 .. .... . .... q:1 . . .... \
28
return false;
29
+ &2misc vm=%vm_dp vd=%vd_dp
29
}
30
+
30
31
+ VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
32
]
33
34
# Subgroup for size != 0b11
35
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
36
index XXXXXXX..XXXXXXX 100644
37
--- a/target/arm/translate-neon.inc.c
38
+++ b/target/arm/translate-neon.inc.c
39
@@ -XXX,XX +XXX,XX @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a)
40
a->q ? 16 : 8, a->q ? 16 : 8);
41
return true;
42
}
43
+
44
+static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
45
+{
46
+ int pass, half;
47
+
48
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
49
+ return false;
50
+ }
51
+
52
+ /* UNDEF accesses to D16-D31 if they don't exist. */
53
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
54
+ ((a->vd | a->vm) & 0x10)) {
55
+ return false;
56
+ }
57
+
58
+ if ((a->vd | a->vm) & a->q) {
59
+ return false;
60
+ }
61
+
62
+ if (a->size == 3) {
63
+ return false;
64
+ }
65
+
66
+ if (!vfp_access_check(s)) {
31
+ if (!vfp_access_check(s)) {
67
+ return true;
32
+ return true;
68
+ }
33
+ }
69
+
34
+
70
+ for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
35
desc = tcg_const_i32((a->vn << 2) | a->len);
71
+ TCGv_i32 tmp[2];
36
def = tcg_temp_new_i64();
72
+
37
if (a->op) {
73
+ for (half = 0; half < 2; half++) {
74
+ tmp[half] = neon_load_reg(a->vm, pass * 2 + half);
75
+ switch (a->size) {
76
+ case 0:
77
+ tcg_gen_bswap32_i32(tmp[half], tmp[half]);
78
+ break;
79
+ case 1:
80
+ gen_swap_half(tmp[half]);
81
+ break;
82
+ case 2:
83
+ break;
84
+ default:
85
+ g_assert_not_reached();
86
+ }
87
+ }
88
+ neon_store_reg(a->vd, pass * 2, tmp[1]);
89
+ neon_store_reg(a->vd, pass * 2 + 1, tmp[0]);
90
+ }
91
+ return true;
92
+}
93
diff --git a/target/arm/translate.c b/target/arm/translate.c
94
index XXXXXXX..XXXXXXX 100644
95
--- a/target/arm/translate.c
96
+++ b/target/arm/translate.c
97
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
98
}
99
switch (op) {
100
case NEON_2RM_VREV64:
101
- for (pass = 0; pass < (q ? 2 : 1); pass++) {
102
- tmp = neon_load_reg(rm, pass * 2);
103
- tmp2 = neon_load_reg(rm, pass * 2 + 1);
104
- switch (size) {
105
- case 0: tcg_gen_bswap32_i32(tmp, tmp); break;
106
- case 1: gen_swap_half(tmp); break;
107
- case 2: /* no-op */ break;
108
- default: abort();
109
- }
110
- neon_store_reg(rd, pass * 2 + 1, tmp);
111
- if (size == 2) {
112
- neon_store_reg(rd, pass * 2, tmp2);
113
- } else {
114
- switch (size) {
115
- case 0: tcg_gen_bswap32_i32(tmp2, tmp2); break;
116
- case 1: gen_swap_half(tmp2); break;
117
- default: abort();
118
- }
119
- neon_store_reg(rd, pass * 2, tmp2);
120
- }
121
- }
122
- break;
123
+ /* handled by decodetree */
124
+ return 1;
125
case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U:
126
case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
127
for (pass = 0; pass < q + 1; pass++) {
128
--
38
--
129
2.20.1
39
2.20.1
130
40
131
41
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon VZIP and VUZP insns in the 2-reg-misc group to
2
decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-4-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 3 ++
9
target/arm/translate-neon.inc.c | 74 ++++++++++++++++++++++++++
10
target/arm/translate.c | 92 +--------------------------------
11
3 files changed, 79 insertions(+), 90 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
19
VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
20
VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc
21
+
22
+ VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
23
+ VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
24
]
25
26
# Subgroup for size != 0b11
27
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
28
index XXXXXXX..XXXXXXX 100644
29
--- a/target/arm/translate-neon.inc.c
30
+++ b/target/arm/translate-neon.inc.c
31
@@ -XXX,XX +XXX,XX @@ static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a)
32
return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size],
33
accfn[a->size]);
34
}
35
+
36
+typedef void ZipFn(TCGv_ptr, TCGv_ptr);
37
+
38
+static bool do_zip_uzp(DisasContext *s, arg_2misc *a,
39
+ ZipFn *fn)
40
+{
41
+ TCGv_ptr pd, pm;
42
+
43
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
44
+ return false;
45
+ }
46
+
47
+ /* UNDEF accesses to D16-D31 if they don't exist. */
48
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
49
+ ((a->vd | a->vm) & 0x10)) {
50
+ return false;
51
+ }
52
+
53
+ if ((a->vd | a->vm) & a->q) {
54
+ return false;
55
+ }
56
+
57
+ if (!fn) {
58
+ /* Bad size or size/q combination */
59
+ return false;
60
+ }
61
+
62
+ if (!vfp_access_check(s)) {
63
+ return true;
64
+ }
65
+
66
+ pd = vfp_reg_ptr(true, a->vd);
67
+ pm = vfp_reg_ptr(true, a->vm);
68
+ fn(pd, pm);
69
+ tcg_temp_free_ptr(pd);
70
+ tcg_temp_free_ptr(pm);
71
+ return true;
72
+}
73
+
74
+static bool trans_VUZP(DisasContext *s, arg_2misc *a)
75
+{
76
+ static ZipFn * const fn[2][4] = {
77
+ {
78
+ gen_helper_neon_unzip8,
79
+ gen_helper_neon_unzip16,
80
+ NULL,
81
+ NULL,
82
+ }, {
83
+ gen_helper_neon_qunzip8,
84
+ gen_helper_neon_qunzip16,
85
+ gen_helper_neon_qunzip32,
86
+ NULL,
87
+ }
88
+ };
89
+ return do_zip_uzp(s, a, fn[a->q][a->size]);
90
+}
91
+
92
+static bool trans_VZIP(DisasContext *s, arg_2misc *a)
93
+{
94
+ static ZipFn * const fn[2][4] = {
95
+ {
96
+ gen_helper_neon_zip8,
97
+ gen_helper_neon_zip16,
98
+ NULL,
99
+ NULL,
100
+ }, {
101
+ gen_helper_neon_qzip8,
102
+ gen_helper_neon_qzip16,
103
+ gen_helper_neon_qzip32,
104
+ NULL,
105
+ }
106
+ };
107
+ return do_zip_uzp(s, a, fn[a->q][a->size]);
108
+}
109
diff --git a/target/arm/translate.c b/target/arm/translate.c
110
index XXXXXXX..XXXXXXX 100644
111
--- a/target/arm/translate.c
112
+++ b/target/arm/translate.c
113
@@ -XXX,XX +XXX,XX @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
114
gen_rfe(s, pc, load_cpu_field(spsr));
115
}
116
117
-static int gen_neon_unzip(int rd, int rm, int size, int q)
118
-{
119
- TCGv_ptr pd, pm;
120
-
121
- if (!q && size == 2) {
122
- return 1;
123
- }
124
- pd = vfp_reg_ptr(true, rd);
125
- pm = vfp_reg_ptr(true, rm);
126
- if (q) {
127
- switch (size) {
128
- case 0:
129
- gen_helper_neon_qunzip8(pd, pm);
130
- break;
131
- case 1:
132
- gen_helper_neon_qunzip16(pd, pm);
133
- break;
134
- case 2:
135
- gen_helper_neon_qunzip32(pd, pm);
136
- break;
137
- default:
138
- abort();
139
- }
140
- } else {
141
- switch (size) {
142
- case 0:
143
- gen_helper_neon_unzip8(pd, pm);
144
- break;
145
- case 1:
146
- gen_helper_neon_unzip16(pd, pm);
147
- break;
148
- default:
149
- abort();
150
- }
151
- }
152
- tcg_temp_free_ptr(pd);
153
- tcg_temp_free_ptr(pm);
154
- return 0;
155
-}
156
-
157
-static int gen_neon_zip(int rd, int rm, int size, int q)
158
-{
159
- TCGv_ptr pd, pm;
160
-
161
- if (!q && size == 2) {
162
- return 1;
163
- }
164
- pd = vfp_reg_ptr(true, rd);
165
- pm = vfp_reg_ptr(true, rm);
166
- if (q) {
167
- switch (size) {
168
- case 0:
169
- gen_helper_neon_qzip8(pd, pm);
170
- break;
171
- case 1:
172
- gen_helper_neon_qzip16(pd, pm);
173
- break;
174
- case 2:
175
- gen_helper_neon_qzip32(pd, pm);
176
- break;
177
- default:
178
- abort();
179
- }
180
- } else {
181
- switch (size) {
182
- case 0:
183
- gen_helper_neon_zip8(pd, pm);
184
- break;
185
- case 1:
186
- gen_helper_neon_zip16(pd, pm);
187
- break;
188
- default:
189
- abort();
190
- }
191
- }
192
- tcg_temp_free_ptr(pd);
193
- tcg_temp_free_ptr(pm);
194
- return 0;
195
-}
196
-
197
static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1)
198
{
199
TCGv_i32 rd, tmp;
200
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
201
case NEON_2RM_VREV64:
202
case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U:
203
case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
204
+ case NEON_2RM_VUZP:
205
+ case NEON_2RM_VZIP:
206
/* handled by decodetree */
207
return 1;
208
case NEON_2RM_VTRN:
209
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
210
goto elementwise;
211
}
212
break;
213
- case NEON_2RM_VUZP:
214
- if (gen_neon_unzip(rd, rm, size, q)) {
215
- return 1;
216
- }
217
- break;
218
- case NEON_2RM_VZIP:
219
- if (gen_neon_zip(rd, rm, size, q)) {
220
- return 1;
221
- }
222
- break;
223
case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
224
/* also VQMOVUN; op field and mnemonics don't line up */
225
if (rm & 1) {
226
--
227
2.20.1
228
229
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon narrowing moves VMQNV, VQMOVN, VQMOVUN in the 2-reg-misc
2
group to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-5-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 9 ++++
9
target/arm/translate-neon.inc.c | 59 ++++++++++++++++++++++++
10
target/arm/translate.c | 81 +--------------------------------
11
3 files changed, 70 insertions(+), 79 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
19
@2misc .... ... .. . .. size:2 .. .... . .... q:1 . . .... \
20
&2misc vm=%vm_dp vd=%vd_dp
21
+ @2misc_q0 .... ... .. . .. size:2 .. .... . .... . . . .... \
22
+ &2misc vm=%vm_dp vd=%vd_dp q=0
23
24
VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
25
26
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
27
28
VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
29
VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
30
+
31
+ VMOVN 1111 001 11 . 11 .. 10 .... 0 0100 0 . 0 .... @2misc_q0
32
+ # VQMOVUN: unsigned result (source is always signed)
33
+ VQMOVUN 1111 001 11 . 11 .. 10 .... 0 0100 1 . 0 .... @2misc_q0
34
+ # VQMOVN: signed result, source may be signed (_S) or unsigned (_U)
35
+ VQMOVN_S 1111 001 11 . 11 .. 10 .... 0 0101 0 . 0 .... @2misc_q0
36
+ VQMOVN_U 1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0
37
]
38
39
# Subgroup for size != 0b11
40
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
41
index XXXXXXX..XXXXXXX 100644
42
--- a/target/arm/translate-neon.inc.c
43
+++ b/target/arm/translate-neon.inc.c
44
@@ -XXX,XX +XXX,XX @@ static bool trans_VZIP(DisasContext *s, arg_2misc *a)
45
};
46
return do_zip_uzp(s, a, fn[a->q][a->size]);
47
}
48
+
49
+static bool do_vmovn(DisasContext *s, arg_2misc *a,
50
+ NeonGenNarrowEnvFn *narrowfn)
51
+{
52
+ TCGv_i64 rm;
53
+ TCGv_i32 rd0, rd1;
54
+
55
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
56
+ return false;
57
+ }
58
+
59
+ /* UNDEF accesses to D16-D31 if they don't exist. */
60
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
61
+ ((a->vd | a->vm) & 0x10)) {
62
+ return false;
63
+ }
64
+
65
+ if (a->vm & 1) {
66
+ return false;
67
+ }
68
+
69
+ if (!narrowfn) {
70
+ return false;
71
+ }
72
+
73
+ if (!vfp_access_check(s)) {
74
+ return true;
75
+ }
76
+
77
+ rm = tcg_temp_new_i64();
78
+ rd0 = tcg_temp_new_i32();
79
+ rd1 = tcg_temp_new_i32();
80
+
81
+ neon_load_reg64(rm, a->vm);
82
+ narrowfn(rd0, cpu_env, rm);
83
+ neon_load_reg64(rm, a->vm + 1);
84
+ narrowfn(rd1, cpu_env, rm);
85
+ neon_store_reg(a->vd, 0, rd0);
86
+ neon_store_reg(a->vd, 1, rd1);
87
+ tcg_temp_free_i64(rm);
88
+ return true;
89
+}
90
+
91
+#define DO_VMOVN(INSN, FUNC) \
92
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
93
+ { \
94
+ static NeonGenNarrowEnvFn * const narrowfn[] = { \
95
+ FUNC##8, \
96
+ FUNC##16, \
97
+ FUNC##32, \
98
+ NULL, \
99
+ }; \
100
+ return do_vmovn(s, a, narrowfn[a->size]); \
101
+ }
102
+
103
+DO_VMOVN(VMOVN, gen_neon_narrow_u)
104
+DO_VMOVN(VQMOVUN, gen_helper_neon_unarrow_sat)
105
+DO_VMOVN(VQMOVN_S, gen_helper_neon_narrow_sat_s)
106
+DO_VMOVN(VQMOVN_U, gen_helper_neon_narrow_sat_u)
107
diff --git a/target/arm/translate.c b/target/arm/translate.c
108
index XXXXXXX..XXXXXXX 100644
109
--- a/target/arm/translate.c
110
+++ b/target/arm/translate.c
111
@@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
112
tcg_temp_free_i32(rd);
113
}
114
115
-static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src)
116
-{
117
- switch (size) {
118
- case 0: gen_helper_neon_narrow_u8(dest, src); break;
119
- case 1: gen_helper_neon_narrow_u16(dest, src); break;
120
- case 2: tcg_gen_extrl_i64_i32(dest, src); break;
121
- default: abort();
122
- }
123
-}
124
-
125
-static inline void gen_neon_narrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
126
-{
127
- switch (size) {
128
- case 0: gen_helper_neon_narrow_sat_s8(dest, cpu_env, src); break;
129
- case 1: gen_helper_neon_narrow_sat_s16(dest, cpu_env, src); break;
130
- case 2: gen_helper_neon_narrow_sat_s32(dest, cpu_env, src); break;
131
- default: abort();
132
- }
133
-}
134
-
135
-static inline void gen_neon_narrow_satu(int size, TCGv_i32 dest, TCGv_i64 src)
136
-{
137
- switch (size) {
138
- case 0: gen_helper_neon_narrow_sat_u8(dest, cpu_env, src); break;
139
- case 1: gen_helper_neon_narrow_sat_u16(dest, cpu_env, src); break;
140
- case 2: gen_helper_neon_narrow_sat_u32(dest, cpu_env, src); break;
141
- default: abort();
142
- }
143
-}
144
-
145
-static inline void gen_neon_unarrow_sats(int size, TCGv_i32 dest, TCGv_i64 src)
146
-{
147
- switch (size) {
148
- case 0: gen_helper_neon_unarrow_sat8(dest, cpu_env, src); break;
149
- case 1: gen_helper_neon_unarrow_sat16(dest, cpu_env, src); break;
150
- case 2: gen_helper_neon_unarrow_sat32(dest, cpu_env, src); break;
151
- default: abort();
152
- }
153
-}
154
-
155
static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
156
{
157
if (u) {
158
@@ -XXX,XX +XXX,XX @@ static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
159
tcg_temp_free_i32(src);
160
}
161
162
-static void gen_neon_narrow_op(int op, int u, int size,
163
- TCGv_i32 dest, TCGv_i64 src)
164
-{
165
- if (op) {
166
- if (u) {
167
- gen_neon_unarrow_sats(size, dest, src);
168
- } else {
169
- gen_neon_narrow(size, dest, src);
170
- }
171
- } else {
172
- if (u) {
173
- gen_neon_narrow_satu(size, dest, src);
174
- } else {
175
- gen_neon_narrow_sats(size, dest, src);
176
- }
177
- }
178
-}
179
-
180
/* Symbolic constants for op fields for Neon 2-register miscellaneous.
181
* The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B
182
* table A7-13.
183
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
184
!arm_dc_feature(s, ARM_FEATURE_V8)) {
185
return 1;
186
}
187
- if ((op != NEON_2RM_VMOVN && op != NEON_2RM_VQMOVN) &&
188
- q && ((rm | rd) & 1)) {
189
+ if (q && ((rm | rd) & 1)) {
190
return 1;
191
}
192
switch (op) {
193
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
194
case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
195
case NEON_2RM_VUZP:
196
case NEON_2RM_VZIP:
197
+ case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
198
/* handled by decodetree */
199
return 1;
200
case NEON_2RM_VTRN:
201
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
202
goto elementwise;
203
}
204
break;
205
- case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
206
- /* also VQMOVUN; op field and mnemonics don't line up */
207
- if (rm & 1) {
208
- return 1;
209
- }
210
- tmp2 = NULL;
211
- for (pass = 0; pass < 2; pass++) {
212
- neon_load_reg64(cpu_V0, rm + pass);
213
- tmp = tcg_temp_new_i32();
214
- gen_neon_narrow_op(op == NEON_2RM_VMOVN, q, size,
215
- tmp, cpu_V0);
216
- if (pass == 0) {
217
- tmp2 = tmp;
218
- } else {
219
- neon_store_reg(rd, 0, tmp2);
220
- neon_store_reg(rd, 1, tmp);
221
- }
222
- }
223
- break;
224
case NEON_2RM_VSHLL:
225
if (q || (rd & 1)) {
226
return 1;
227
--
228
2.20.1
229
230
diff view generated by jsdifflib
Deleted patch
1
Convert the VSHLL insn in the 2-reg-misc Neon group to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200616170844.13318-6-peter.maydell@linaro.org
6
---
7
target/arm/neon-dp.decode | 2 ++
8
target/arm/translate-neon.inc.c | 52 +++++++++++++++++++++++++++++++++
9
target/arm/translate.c | 35 +---------------------
10
3 files changed, 55 insertions(+), 34 deletions(-)
11
12
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-dp.decode
15
+++ b/target/arm/neon-dp.decode
16
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
17
# VQMOVN: signed result, source may be signed (_S) or unsigned (_U)
18
VQMOVN_S 1111 001 11 . 11 .. 10 .... 0 0101 0 . 0 .... @2misc_q0
19
VQMOVN_U 1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0
20
+
21
+ VSHLL 1111 001 11 . 11 .. 10 .... 0 0110 0 . 0 .... @2misc_q0
22
]
23
24
# Subgroup for size != 0b11
25
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
26
index XXXXXXX..XXXXXXX 100644
27
--- a/target/arm/translate-neon.inc.c
28
+++ b/target/arm/translate-neon.inc.c
29
@@ -XXX,XX +XXX,XX @@ DO_VMOVN(VMOVN, gen_neon_narrow_u)
30
DO_VMOVN(VQMOVUN, gen_helper_neon_unarrow_sat)
31
DO_VMOVN(VQMOVN_S, gen_helper_neon_narrow_sat_s)
32
DO_VMOVN(VQMOVN_U, gen_helper_neon_narrow_sat_u)
33
+
34
+static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
35
+{
36
+ TCGv_i32 rm0, rm1;
37
+ TCGv_i64 rd;
38
+ static NeonGenWidenFn * const widenfns[] = {
39
+ gen_helper_neon_widen_u8,
40
+ gen_helper_neon_widen_u16,
41
+ tcg_gen_extu_i32_i64,
42
+ NULL,
43
+ };
44
+ NeonGenWidenFn *widenfn = widenfns[a->size];
45
+
46
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
47
+ return false;
48
+ }
49
+
50
+ /* UNDEF accesses to D16-D31 if they don't exist. */
51
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
52
+ ((a->vd | a->vm) & 0x10)) {
53
+ return false;
54
+ }
55
+
56
+ if (a->vd & 1) {
57
+ return false;
58
+ }
59
+
60
+ if (!widenfn) {
61
+ return false;
62
+ }
63
+
64
+ if (!vfp_access_check(s)) {
65
+ return true;
66
+ }
67
+
68
+ rd = tcg_temp_new_i64();
69
+
70
+ rm0 = neon_load_reg(a->vm, 0);
71
+ rm1 = neon_load_reg(a->vm, 1);
72
+
73
+ widenfn(rd, rm0);
74
+ tcg_gen_shli_i64(rd, rd, 8 << a->size);
75
+ neon_store_reg64(rd, a->vd);
76
+ widenfn(rd, rm1);
77
+ tcg_gen_shli_i64(rd, rd, 8 << a->size);
78
+ neon_store_reg64(rd, a->vd + 1);
79
+
80
+ tcg_temp_free_i64(rd);
81
+ tcg_temp_free_i32(rm0);
82
+ tcg_temp_free_i32(rm1);
83
+ return true;
84
+}
85
diff --git a/target/arm/translate.c b/target/arm/translate.c
86
index XXXXXXX..XXXXXXX 100644
87
--- a/target/arm/translate.c
88
+++ b/target/arm/translate.c
89
@@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
90
tcg_temp_free_i32(rd);
91
}
92
93
-static inline void gen_neon_widen(TCGv_i64 dest, TCGv_i32 src, int size, int u)
94
-{
95
- if (u) {
96
- switch (size) {
97
- case 0: gen_helper_neon_widen_u8(dest, src); break;
98
- case 1: gen_helper_neon_widen_u16(dest, src); break;
99
- case 2: tcg_gen_extu_i32_i64(dest, src); break;
100
- default: abort();
101
- }
102
- } else {
103
- switch (size) {
104
- case 0: gen_helper_neon_widen_s8(dest, src); break;
105
- case 1: gen_helper_neon_widen_s16(dest, src); break;
106
- case 2: tcg_gen_ext_i32_i64(dest, src); break;
107
- default: abort();
108
- }
109
- }
110
- tcg_temp_free_i32(src);
111
-}
112
-
113
/* Symbolic constants for op fields for Neon 2-register miscellaneous.
114
* The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B
115
* table A7-13.
116
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
117
case NEON_2RM_VUZP:
118
case NEON_2RM_VZIP:
119
case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
120
+ case NEON_2RM_VSHLL:
121
/* handled by decodetree */
122
return 1;
123
case NEON_2RM_VTRN:
124
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
125
goto elementwise;
126
}
127
break;
128
- case NEON_2RM_VSHLL:
129
- if (q || (rd & 1)) {
130
- return 1;
131
- }
132
- tmp = neon_load_reg(rm, 0);
133
- tmp2 = neon_load_reg(rm, 1);
134
- for (pass = 0; pass < 2; pass++) {
135
- if (pass == 1)
136
- tmp = tmp2;
137
- gen_neon_widen(cpu_V0, tmp, size, 1);
138
- tcg_gen_shli_i64(cpu_V0, cpu_V0, 8 << size);
139
- neon_store_reg64(cpu_V0, rd + pass);
140
- }
141
- break;
142
case NEON_2RM_VCVT_F16_F32:
143
{
144
TCGv_ptr fpst;
145
--
146
2.20.1
147
148
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon insns in the 2-reg-misc group which are
2
VCVT between f32 and f16 to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-7-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 3 ++
9
target/arm/translate-neon.inc.c | 96 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 65 ++--------------------
11
3 files changed, 102 insertions(+), 62 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
VQMOVN_U 1111 001 11 . 11 .. 10 .... 0 0101 1 . 0 .... @2misc_q0
19
20
VSHLL 1111 001 11 . 11 .. 10 .... 0 0110 0 . 0 .... @2misc_q0
21
+
22
+ VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
23
+ VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
24
]
25
26
# Subgroup for size != 0b11
27
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
28
index XXXXXXX..XXXXXXX 100644
29
--- a/target/arm/translate-neon.inc.c
30
+++ b/target/arm/translate-neon.inc.c
31
@@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL(DisasContext *s, arg_2misc *a)
32
tcg_temp_free_i32(rm1);
33
return true;
34
}
35
+
36
+static bool trans_VCVT_F16_F32(DisasContext *s, arg_2misc *a)
37
+{
38
+ TCGv_ptr fpst;
39
+ TCGv_i32 ahp, tmp, tmp2, tmp3;
40
+
41
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
42
+ !dc_isar_feature(aa32_fp16_spconv, s)) {
43
+ return false;
44
+ }
45
+
46
+ /* UNDEF accesses to D16-D31 if they don't exist. */
47
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
48
+ ((a->vd | a->vm) & 0x10)) {
49
+ return false;
50
+ }
51
+
52
+ if ((a->vm & 1) || (a->size != 1)) {
53
+ return false;
54
+ }
55
+
56
+ if (!vfp_access_check(s)) {
57
+ return true;
58
+ }
59
+
60
+ fpst = get_fpstatus_ptr(true);
61
+ ahp = get_ahp_flag();
62
+ tmp = neon_load_reg(a->vm, 0);
63
+ gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
64
+ tmp2 = neon_load_reg(a->vm, 1);
65
+ gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp);
66
+ tcg_gen_shli_i32(tmp2, tmp2, 16);
67
+ tcg_gen_or_i32(tmp2, tmp2, tmp);
68
+ tcg_temp_free_i32(tmp);
69
+ tmp = neon_load_reg(a->vm, 2);
70
+ gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
71
+ tmp3 = neon_load_reg(a->vm, 3);
72
+ neon_store_reg(a->vd, 0, tmp2);
73
+ gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp);
74
+ tcg_gen_shli_i32(tmp3, tmp3, 16);
75
+ tcg_gen_or_i32(tmp3, tmp3, tmp);
76
+ neon_store_reg(a->vd, 1, tmp3);
77
+ tcg_temp_free_i32(tmp);
78
+ tcg_temp_free_i32(ahp);
79
+ tcg_temp_free_ptr(fpst);
80
+
81
+ return true;
82
+}
83
+
84
+static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
85
+{
86
+ TCGv_ptr fpst;
87
+ TCGv_i32 ahp, tmp, tmp2, tmp3;
88
+
89
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
90
+ !dc_isar_feature(aa32_fp16_spconv, s)) {
91
+ return false;
92
+ }
93
+
94
+ /* UNDEF accesses to D16-D31 if they don't exist. */
95
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
96
+ ((a->vd | a->vm) & 0x10)) {
97
+ return false;
98
+ }
99
+
100
+ if ((a->vd & 1) || (a->size != 1)) {
101
+ return false;
102
+ }
103
+
104
+ if (!vfp_access_check(s)) {
105
+ return true;
106
+ }
107
+
108
+ fpst = get_fpstatus_ptr(true);
109
+ ahp = get_ahp_flag();
110
+ tmp3 = tcg_temp_new_i32();
111
+ tmp = neon_load_reg(a->vm, 0);
112
+ tmp2 = neon_load_reg(a->vm, 1);
113
+ tcg_gen_ext16u_i32(tmp3, tmp);
114
+ gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
115
+ neon_store_reg(a->vd, 0, tmp3);
116
+ tcg_gen_shri_i32(tmp, tmp, 16);
117
+ gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp);
118
+ neon_store_reg(a->vd, 1, tmp);
119
+ tmp3 = tcg_temp_new_i32();
120
+ tcg_gen_ext16u_i32(tmp3, tmp2);
121
+ gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
122
+ neon_store_reg(a->vd, 2, tmp3);
123
+ tcg_gen_shri_i32(tmp2, tmp2, 16);
124
+ gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp);
125
+ neon_store_reg(a->vd, 3, tmp2);
126
+ tcg_temp_free_i32(ahp);
127
+ tcg_temp_free_ptr(fpst);
128
+
129
+ return true;
130
+}
131
diff --git a/target/arm/translate.c b/target/arm/translate.c
132
index XXXXXXX..XXXXXXX 100644
133
--- a/target/arm/translate.c
134
+++ b/target/arm/translate.c
135
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
136
int pass;
137
int u;
138
int vec_size;
139
- TCGv_i32 tmp, tmp2, tmp3;
140
+ TCGv_i32 tmp, tmp2;
141
142
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
143
return 1;
144
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
145
case NEON_2RM_VZIP:
146
case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
147
case NEON_2RM_VSHLL:
148
+ case NEON_2RM_VCVT_F16_F32:
149
+ case NEON_2RM_VCVT_F32_F16:
150
/* handled by decodetree */
151
return 1;
152
case NEON_2RM_VTRN:
153
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
154
goto elementwise;
155
}
156
break;
157
- case NEON_2RM_VCVT_F16_F32:
158
- {
159
- TCGv_ptr fpst;
160
- TCGv_i32 ahp;
161
-
162
- if (!dc_isar_feature(aa32_fp16_spconv, s) ||
163
- q || (rm & 1)) {
164
- return 1;
165
- }
166
- fpst = get_fpstatus_ptr(true);
167
- ahp = get_ahp_flag();
168
- tmp = neon_load_reg(rm, 0);
169
- gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
170
- tmp2 = neon_load_reg(rm, 1);
171
- gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp);
172
- tcg_gen_shli_i32(tmp2, tmp2, 16);
173
- tcg_gen_or_i32(tmp2, tmp2, tmp);
174
- tcg_temp_free_i32(tmp);
175
- tmp = neon_load_reg(rm, 2);
176
- gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp);
177
- tmp3 = neon_load_reg(rm, 3);
178
- neon_store_reg(rd, 0, tmp2);
179
- gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp);
180
- tcg_gen_shli_i32(tmp3, tmp3, 16);
181
- tcg_gen_or_i32(tmp3, tmp3, tmp);
182
- neon_store_reg(rd, 1, tmp3);
183
- tcg_temp_free_i32(tmp);
184
- tcg_temp_free_i32(ahp);
185
- tcg_temp_free_ptr(fpst);
186
- break;
187
- }
188
- case NEON_2RM_VCVT_F32_F16:
189
- {
190
- TCGv_ptr fpst;
191
- TCGv_i32 ahp;
192
- if (!dc_isar_feature(aa32_fp16_spconv, s) ||
193
- q || (rd & 1)) {
194
- return 1;
195
- }
196
- fpst = get_fpstatus_ptr(true);
197
- ahp = get_ahp_flag();
198
- tmp3 = tcg_temp_new_i32();
199
- tmp = neon_load_reg(rm, 0);
200
- tmp2 = neon_load_reg(rm, 1);
201
- tcg_gen_ext16u_i32(tmp3, tmp);
202
- gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
203
- neon_store_reg(rd, 0, tmp3);
204
- tcg_gen_shri_i32(tmp, tmp, 16);
205
- gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp);
206
- neon_store_reg(rd, 1, tmp);
207
- tmp3 = tcg_temp_new_i32();
208
- tcg_gen_ext16u_i32(tmp3, tmp2);
209
- gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp);
210
- neon_store_reg(rd, 2, tmp3);
211
- tcg_gen_shri_i32(tmp2, tmp2, 16);
212
- gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp);
213
- neon_store_reg(rd, 3, tmp2);
214
- tcg_temp_free_i32(ahp);
215
- tcg_temp_free_ptr(fpst);
216
- break;
217
- }
218
case NEON_2RM_AESE: case NEON_2RM_AESMC:
219
if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) {
220
return 1;
221
--
222
2.20.1
223
224
diff view generated by jsdifflib
Deleted patch
1
Convert to decodetree the insns in the Neon 2-reg-misc grouping which
2
we implement using gvec.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-8-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 11 +++++++
9
target/arm/translate-neon.inc.c | 55 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 35 +++++----------------
11
3 files changed, 74 insertions(+), 27 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc
19
VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc
20
21
+ VMVN 1111 001 11 . 11 .. 00 .... 0 1011 . . 0 .... @2misc
22
+
23
VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
24
VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc
25
26
+ VCGT0 1111 001 11 . 11 .. 01 .... 0 0000 . . 0 .... @2misc
27
+ VCGE0 1111 001 11 . 11 .. 01 .... 0 0001 . . 0 .... @2misc
28
+ VCEQ0 1111 001 11 . 11 .. 01 .... 0 0010 . . 0 .... @2misc
29
+ VCLE0 1111 001 11 . 11 .. 01 .... 0 0011 . . 0 .... @2misc
30
+ VCLT0 1111 001 11 . 11 .. 01 .... 0 0100 . . 0 .... @2misc
31
+
32
+ VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc
33
+ VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc
34
+
35
VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
36
VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
37
38
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
39
index XXXXXXX..XXXXXXX 100644
40
--- a/target/arm/translate-neon.inc.c
41
+++ b/target/arm/translate-neon.inc.c
42
@@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_F32_F16(DisasContext *s, arg_2misc *a)
43
44
return true;
45
}
46
+
47
+static bool do_2misc_vec(DisasContext *s, arg_2misc *a, GVecGen2Fn *fn)
48
+{
49
+ int vec_size = a->q ? 16 : 8;
50
+ int rd_ofs = neon_reg_offset(a->vd, 0);
51
+ int rm_ofs = neon_reg_offset(a->vm, 0);
52
+
53
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
54
+ return false;
55
+ }
56
+
57
+ /* UNDEF accesses to D16-D31 if they don't exist. */
58
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
59
+ ((a->vd | a->vm) & 0x10)) {
60
+ return false;
61
+ }
62
+
63
+ if (a->size == 3) {
64
+ return false;
65
+ }
66
+
67
+ if ((a->vd | a->vm) & a->q) {
68
+ return false;
69
+ }
70
+
71
+ if (!vfp_access_check(s)) {
72
+ return true;
73
+ }
74
+
75
+ fn(a->size, rd_ofs, rm_ofs, vec_size, vec_size);
76
+
77
+ return true;
78
+}
79
+
80
+#define DO_2MISC_VEC(INSN, FN) \
81
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
82
+ { \
83
+ return do_2misc_vec(s, a, FN); \
84
+ }
85
+
86
+DO_2MISC_VEC(VNEG, tcg_gen_gvec_neg)
87
+DO_2MISC_VEC(VABS, tcg_gen_gvec_abs)
88
+DO_2MISC_VEC(VCEQ0, gen_gvec_ceq0)
89
+DO_2MISC_VEC(VCGT0, gen_gvec_cgt0)
90
+DO_2MISC_VEC(VCLE0, gen_gvec_cle0)
91
+DO_2MISC_VEC(VCGE0, gen_gvec_cge0)
92
+DO_2MISC_VEC(VCLT0, gen_gvec_clt0)
93
+
94
+static bool trans_VMVN(DisasContext *s, arg_2misc *a)
95
+{
96
+ if (a->size != 0) {
97
+ return false;
98
+ }
99
+ return do_2misc_vec(s, a, tcg_gen_gvec_not);
100
+}
101
diff --git a/target/arm/translate.c b/target/arm/translate.c
102
index XXXXXXX..XXXXXXX 100644
103
--- a/target/arm/translate.c
104
+++ b/target/arm/translate.c
105
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
106
int size;
107
int pass;
108
int u;
109
- int vec_size;
110
TCGv_i32 tmp, tmp2;
111
112
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
113
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
114
VFP_DREG_D(rd, insn);
115
VFP_DREG_M(rm, insn);
116
size = (insn >> 20) & 3;
117
- vec_size = q ? 16 : 8;
118
rd_ofs = neon_reg_offset(rd, 0);
119
rm_ofs = neon_reg_offset(rm, 0);
120
121
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
122
case NEON_2RM_VSHLL:
123
case NEON_2RM_VCVT_F16_F32:
124
case NEON_2RM_VCVT_F32_F16:
125
+ case NEON_2RM_VMVN:
126
+ case NEON_2RM_VNEG:
127
+ case NEON_2RM_VABS:
128
+ case NEON_2RM_VCEQ0:
129
+ case NEON_2RM_VCGT0:
130
+ case NEON_2RM_VCLE0:
131
+ case NEON_2RM_VCGE0:
132
+ case NEON_2RM_VCLT0:
133
/* handled by decodetree */
134
return 1;
135
case NEON_2RM_VTRN:
136
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
137
q ? gen_helper_crypto_sha256su0
138
: gen_helper_crypto_sha1su1);
139
break;
140
- case NEON_2RM_VMVN:
141
- tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size);
142
- break;
143
- case NEON_2RM_VNEG:
144
- tcg_gen_gvec_neg(size, rd_ofs, rm_ofs, vec_size, vec_size);
145
- break;
146
- case NEON_2RM_VABS:
147
- tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size);
148
- break;
149
-
150
- case NEON_2RM_VCEQ0:
151
- gen_gvec_ceq0(size, rd_ofs, rm_ofs, vec_size, vec_size);
152
- break;
153
- case NEON_2RM_VCGT0:
154
- gen_gvec_cgt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
155
- break;
156
- case NEON_2RM_VCLE0:
157
- gen_gvec_cle0(size, rd_ofs, rm_ofs, vec_size, vec_size);
158
- break;
159
- case NEON_2RM_VCGE0:
160
- gen_gvec_cge0(size, rd_ofs, rm_ofs, vec_size, vec_size);
161
- break;
162
- case NEON_2RM_VCLT0:
163
- gen_gvec_clt0(size, rd_ofs, rm_ofs, vec_size, vec_size);
164
- break;
165
166
default:
167
elementwise:
168
--
169
2.20.1
170
171
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon-2-reg misc crypto ops (AESE, AESMC, SHA1H, SHA1SU1)
2
to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-9-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 12 ++++++++
9
target/arm/translate-neon.inc.c | 42 ++++++++++++++++++++++++++
10
target/arm/translate.c | 52 +++------------------------------
11
3 files changed, 58 insertions(+), 48 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
&2misc vm=%vm_dp vd=%vd_dp
19
@2misc_q0 .... ... .. . .. size:2 .. .... . .... . . . .... \
20
&2misc vm=%vm_dp vd=%vd_dp q=0
21
+ @2misc_q1 .... ... .. . .. size:2 .. .... . .... . . . .... \
22
+ &2misc vm=%vm_dp vd=%vd_dp q=1
23
24
VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
25
26
VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc
27
VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc
28
29
+ AESE 1111 001 11 . 11 .. 00 .... 0 0110 0 . 0 .... @2misc_q1
30
+ AESD 1111 001 11 . 11 .. 00 .... 0 0110 1 . 0 .... @2misc_q1
31
+ AESMC 1111 001 11 . 11 .. 00 .... 0 0111 0 . 0 .... @2misc_q1
32
+ AESIMC 1111 001 11 . 11 .. 00 .... 0 0111 1 . 0 .... @2misc_q1
33
+
34
VMVN 1111 001 11 . 11 .. 00 .... 0 1011 . . 0 .... @2misc
35
36
VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
37
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
38
VCLE0 1111 001 11 . 11 .. 01 .... 0 0011 . . 0 .... @2misc
39
VCLT0 1111 001 11 . 11 .. 01 .... 0 0100 . . 0 .... @2misc
40
41
+ SHA1H 1111 001 11 . 11 .. 01 .... 0 0101 1 . 0 .... @2misc_q1
42
+
43
VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc
44
VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc
45
46
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
47
48
VSHLL 1111 001 11 . 11 .. 10 .... 0 0110 0 . 0 .... @2misc_q0
49
50
+ SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1
51
+ SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1
52
+
53
VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
54
VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
55
]
56
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
57
index XXXXXXX..XXXXXXX 100644
58
--- a/target/arm/translate-neon.inc.c
59
+++ b/target/arm/translate-neon.inc.c
60
@@ -XXX,XX +XXX,XX @@ static bool trans_VMVN(DisasContext *s, arg_2misc *a)
61
}
62
return do_2misc_vec(s, a, tcg_gen_gvec_not);
63
}
64
+
65
+#define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \
66
+ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
67
+ uint32_t rm_ofs, uint32_t oprsz, \
68
+ uint32_t maxsz) \
69
+ { \
70
+ tcg_gen_gvec_3_ool(rd_ofs, rd_ofs, rm_ofs, oprsz, maxsz, \
71
+ DATA, FUNC); \
72
+ }
73
+
74
+#define WRAP_2M_2_OOL_FN(WRAPNAME, FUNC, DATA) \
75
+ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \
76
+ uint32_t rm_ofs, uint32_t oprsz, \
77
+ uint32_t maxsz) \
78
+ { \
79
+ tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, oprsz, maxsz, DATA, FUNC); \
80
+ }
81
+
82
+WRAP_2M_3_OOL_FN(gen_AESE, gen_helper_crypto_aese, 0)
83
+WRAP_2M_3_OOL_FN(gen_AESD, gen_helper_crypto_aese, 1)
84
+WRAP_2M_2_OOL_FN(gen_AESMC, gen_helper_crypto_aesmc, 0)
85
+WRAP_2M_2_OOL_FN(gen_AESIMC, gen_helper_crypto_aesmc, 1)
86
+WRAP_2M_2_OOL_FN(gen_SHA1H, gen_helper_crypto_sha1h, 0)
87
+WRAP_2M_2_OOL_FN(gen_SHA1SU1, gen_helper_crypto_sha1su1, 0)
88
+WRAP_2M_2_OOL_FN(gen_SHA256SU0, gen_helper_crypto_sha256su0, 0)
89
+
90
+#define DO_2M_CRYPTO(INSN, FEATURE, SIZE) \
91
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
92
+ { \
93
+ if (!dc_isar_feature(FEATURE, s) || a->size != SIZE) { \
94
+ return false; \
95
+ } \
96
+ return do_2misc_vec(s, a, gen_##INSN); \
97
+ }
98
+
99
+DO_2M_CRYPTO(AESE, aa32_aes, 0)
100
+DO_2M_CRYPTO(AESD, aa32_aes, 0)
101
+DO_2M_CRYPTO(AESMC, aa32_aes, 0)
102
+DO_2M_CRYPTO(AESIMC, aa32_aes, 0)
103
+DO_2M_CRYPTO(SHA1H, aa32_sha1, 2)
104
+DO_2M_CRYPTO(SHA1SU1, aa32_sha1, 2)
105
+DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2)
106
diff --git a/target/arm/translate.c b/target/arm/translate.c
107
index XXXXXXX..XXXXXXX 100644
108
--- a/target/arm/translate.c
109
+++ b/target/arm/translate.c
110
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
111
{
112
int op;
113
int q;
114
- int rd, rm, rd_ofs, rm_ofs;
115
+ int rd, rm;
116
int size;
117
int pass;
118
int u;
119
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
120
VFP_DREG_D(rd, insn);
121
VFP_DREG_M(rm, insn);
122
size = (insn >> 20) & 3;
123
- rd_ofs = neon_reg_offset(rd, 0);
124
- rm_ofs = neon_reg_offset(rm, 0);
125
126
if ((insn & (1 << 23)) == 0) {
127
/* Three register same length: handled by decodetree */
128
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
129
case NEON_2RM_VCLE0:
130
case NEON_2RM_VCGE0:
131
case NEON_2RM_VCLT0:
132
+ case NEON_2RM_AESE: case NEON_2RM_AESMC:
133
+ case NEON_2RM_SHA1H:
134
+ case NEON_2RM_SHA1SU1:
135
/* handled by decodetree */
136
return 1;
137
case NEON_2RM_VTRN:
138
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
139
goto elementwise;
140
}
141
break;
142
- case NEON_2RM_AESE: case NEON_2RM_AESMC:
143
- if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) {
144
- return 1;
145
- }
146
- /*
147
- * Bit 6 is the lowest opcode bit; it distinguishes
148
- * between encryption (AESE/AESMC) and decryption
149
- * (AESD/AESIMC).
150
- */
151
- if (op == NEON_2RM_AESE) {
152
- tcg_gen_gvec_3_ool(vfp_reg_offset(true, rd),
153
- vfp_reg_offset(true, rd),
154
- vfp_reg_offset(true, rm),
155
- 16, 16, extract32(insn, 6, 1),
156
- gen_helper_crypto_aese);
157
- } else {
158
- tcg_gen_gvec_2_ool(vfp_reg_offset(true, rd),
159
- vfp_reg_offset(true, rm),
160
- 16, 16, extract32(insn, 6, 1),
161
- gen_helper_crypto_aesmc);
162
- }
163
- break;
164
- case NEON_2RM_SHA1H:
165
- if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) {
166
- return 1;
167
- }
168
- tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0,
169
- gen_helper_crypto_sha1h);
170
- break;
171
- case NEON_2RM_SHA1SU1:
172
- if ((rm | rd) & 1) {
173
- return 1;
174
- }
175
- /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */
176
- if (q) {
177
- if (!dc_isar_feature(aa32_sha2, s)) {
178
- return 1;
179
- }
180
- } else if (!dc_isar_feature(aa32_sha1, s)) {
181
- return 1;
182
- }
183
- tcg_gen_gvec_2_ool(rd_ofs, rm_ofs, 16, 16, 0,
184
- q ? gen_helper_crypto_sha256su0
185
- : gen_helper_crypto_sha1su1);
186
- break;
187
188
default:
189
elementwise:
190
--
191
2.20.1
192
193
diff view generated by jsdifflib
Deleted patch
1
The NeonGenOneOpFn typedef breaks with the pattern of the other
2
NeonGen*Fn typedefs, because it is a TCGv_i64 -> TCGv_i64 operation
3
but it does not have '64' in its name. Rename it to NeonGenOne64OpFn,
4
so that the old name is available for a TCGv_i32 -> TCGv_i32 operation
5
(which we will need in a subsequent commit).
6
1
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
Message-id: 20200616170844.13318-10-peter.maydell@linaro.org
10
---
11
target/arm/translate.h | 2 +-
12
target/arm/translate-a64.c | 4 ++--
13
2 files changed, 3 insertions(+), 3 deletions(-)
14
15
diff --git a/target/arm/translate.h b/target/arm/translate.h
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate.h
18
+++ b/target/arm/translate.h
19
@@ -XXX,XX +XXX,XX @@ typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
20
typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32);
21
typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
22
typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
23
-typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64);
24
+typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64);
25
typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
26
typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
27
typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
28
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
29
index XXXXXXX..XXXXXXX 100644
30
--- a/target/arm/translate-a64.c
31
+++ b/target/arm/translate-a64.c
32
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u,
33
} else {
34
for (pass = 0; pass < maxpass; pass++) {
35
TCGv_i64 tcg_op = tcg_temp_new_i64();
36
- NeonGenOneOpFn *genfn;
37
- static NeonGenOneOpFn * const fns[2][2] = {
38
+ NeonGenOne64OpFn *genfn;
39
+ static NeonGenOne64OpFn * const fns[2][2] = {
40
{ gen_helper_neon_addlp_s8, gen_helper_neon_addlp_u8 },
41
{ gen_helper_neon_addlp_s16, gen_helper_neon_addlp_u16 },
42
};
43
--
44
2.20.1
45
46
diff view generated by jsdifflib
Deleted patch
1
All the other typedefs like these spell "Op" with a lowercase 'p';
2
remane the NeonGenTwoSingleOPFn and NeonGenTwoDoubleOPFn typedefs to
3
match.
4
1
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20200616170844.13318-11-peter.maydell@linaro.org
8
---
9
target/arm/translate.h | 4 ++--
10
target/arm/translate-a64.c | 4 ++--
11
target/arm/translate-neon.inc.c | 2 +-
12
3 files changed, 5 insertions(+), 5 deletions(-)
13
14
diff --git a/target/arm/translate.h b/target/arm/translate.h
15
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/translate.h
17
+++ b/target/arm/translate.h
18
@@ -XXX,XX +XXX,XX @@ typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
19
typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
20
typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
21
typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32);
22
-typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
23
-typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
24
+typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
25
+typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
26
typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64);
27
typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
28
typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
29
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
30
index XXXXXXX..XXXXXXX 100644
31
--- a/target/arm/translate-a64.c
32
+++ b/target/arm/translate-a64.c
33
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
34
TCGv_i64 tcg_op = tcg_temp_new_i64();
35
TCGv_i64 tcg_zero = tcg_const_i64(0);
36
TCGv_i64 tcg_res = tcg_temp_new_i64();
37
- NeonGenTwoDoubleOPFn *genfn;
38
+ NeonGenTwoDoubleOpFn *genfn;
39
bool swap = false;
40
int pass;
41
42
@@ -XXX,XX +XXX,XX @@ static void handle_2misc_fcmp_zero(DisasContext *s, int opcode,
43
TCGv_i32 tcg_op = tcg_temp_new_i32();
44
TCGv_i32 tcg_zero = tcg_const_i32(0);
45
TCGv_i32 tcg_res = tcg_temp_new_i32();
46
- NeonGenTwoSingleOPFn *genfn;
47
+ NeonGenTwoSingleOpFn *genfn;
48
bool swap = false;
49
int pass, maxpasses;
50
51
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
52
index XXXXXXX..XXXXXXX 100644
53
--- a/target/arm/translate-neon.inc.c
54
+++ b/target/arm/translate-neon.inc.c
55
@@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a)
56
}
57
58
static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
59
- NeonGenTwoSingleOPFn *fn)
60
+ NeonGenTwoSingleOpFn *fn)
61
{
62
/* FP operations in 2-reg-and-shift group */
63
TCGv_i32 tmp, shiftv;
64
--
65
2.20.1
66
67
diff view generated by jsdifflib
Deleted patch
1
Make gen_swap_half() take a source and destination TCGv_i32 rather
2
than modifying the input TCGv_i32; we're going to want to be able to
3
use it with the more flexible function signature, and this also
4
brings it into line with other functions like gen_rev16() and
5
gen_revsh().
6
1
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
Message-id: 20200616170844.13318-12-peter.maydell@linaro.org
10
---
11
target/arm/translate-neon.inc.c | 2 +-
12
target/arm/translate.c | 10 +++++-----
13
2 files changed, 6 insertions(+), 6 deletions(-)
14
15
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate-neon.inc.c
18
+++ b/target/arm/translate-neon.inc.c
19
@@ -XXX,XX +XXX,XX @@ static bool trans_VREV64(DisasContext *s, arg_VREV64 *a)
20
tcg_gen_bswap32_i32(tmp[half], tmp[half]);
21
break;
22
case 1:
23
- gen_swap_half(tmp[half]);
24
+ gen_swap_half(tmp[half], tmp[half]);
25
break;
26
case 2:
27
break;
28
diff --git a/target/arm/translate.c b/target/arm/translate.c
29
index XXXXXXX..XXXXXXX 100644
30
--- a/target/arm/translate.c
31
+++ b/target/arm/translate.c
32
@@ -XXX,XX +XXX,XX @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var)
33
}
34
35
/* Swap low and high halfwords. */
36
-static void gen_swap_half(TCGv_i32 var)
37
+static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var)
38
{
39
- tcg_gen_rotri_i32(var, var, 16);
40
+ tcg_gen_rotri_i32(dest, var, 16);
41
}
42
43
/* Dual 16-bit add. Result placed in t0 and t1 is marked as dead.
44
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
45
case NEON_2RM_VREV32:
46
switch (size) {
47
case 0: tcg_gen_bswap32_i32(tmp, tmp); break;
48
- case 1: gen_swap_half(tmp); break;
49
+ case 1: gen_swap_half(tmp, tmp); break;
50
default: abort();
51
}
52
break;
53
@@ -XXX,XX +XXX,XX @@ static bool op_smlad(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
54
t1 = load_reg(s, a->rn);
55
t2 = load_reg(s, a->rm);
56
if (m_swap) {
57
- gen_swap_half(t2);
58
+ gen_swap_half(t2, t2);
59
}
60
gen_smul_dual(t1, t2);
61
62
@@ -XXX,XX +XXX,XX @@ static bool op_smlald(DisasContext *s, arg_rrrr *a, bool m_swap, bool sub)
63
t1 = load_reg(s, a->rn);
64
t2 = load_reg(s, a->rm);
65
if (m_swap) {
66
- gen_swap_half(t2);
67
+ gen_swap_half(t2, t2);
68
}
69
gen_smul_dual(t1, t2);
70
71
--
72
2.20.1
73
74
diff view generated by jsdifflib
Deleted patch
1
Convert the VREV32 and VREV16 insns in the Neon 2-reg-misc group
2
to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-13-peter.maydell@linaro.org
7
---
8
target/arm/translate.h | 1 +
9
target/arm/neon-dp.decode | 2 ++
10
target/arm/translate-neon.inc.c | 55 +++++++++++++++++++++++++++++++++
11
target/arm/translate.c | 12 ++-----
12
4 files changed, 60 insertions(+), 10 deletions(-)
13
14
diff --git a/target/arm/translate.h b/target/arm/translate.h
15
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/translate.h
17
+++ b/target/arm/translate.h
18
@@ -XXX,XX +XXX,XX @@ typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
19
uint32_t, uint32_t, uint32_t);
20
21
/* Function prototype for gen_ functions for calling Neon helpers */
22
+typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32);
23
typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
24
typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
25
typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
26
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
27
index XXXXXXX..XXXXXXX 100644
28
--- a/target/arm/neon-dp.decode
29
+++ b/target/arm/neon-dp.decode
30
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
31
&2misc vm=%vm_dp vd=%vd_dp q=1
32
33
VREV64 1111 001 11 . 11 .. 00 .... 0 0000 . . 0 .... @2misc
34
+ VREV32 1111 001 11 . 11 .. 00 .... 0 0001 . . 0 .... @2misc
35
+ VREV16 1111 001 11 . 11 .. 00 .... 0 0010 . . 0 .... @2misc
36
37
VPADDL_S 1111 001 11 . 11 .. 00 .... 0 0100 . . 0 .... @2misc
38
VPADDL_U 1111 001 11 . 11 .. 00 .... 0 0101 . . 0 .... @2misc
39
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
40
index XXXXXXX..XXXXXXX 100644
41
--- a/target/arm/translate-neon.inc.c
42
+++ b/target/arm/translate-neon.inc.c
43
@@ -XXX,XX +XXX,XX @@ DO_2M_CRYPTO(AESIMC, aa32_aes, 0)
44
DO_2M_CRYPTO(SHA1H, aa32_sha1, 2)
45
DO_2M_CRYPTO(SHA1SU1, aa32_sha1, 2)
46
DO_2M_CRYPTO(SHA256SU0, aa32_sha2, 2)
47
+
48
+static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn)
49
+{
50
+ int pass;
51
+
52
+ /* Handle a 2-reg-misc operation by iterating 32 bits at a time */
53
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
54
+ return false;
55
+ }
56
+
57
+ /* UNDEF accesses to D16-D31 if they don't exist. */
58
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
59
+ ((a->vd | a->vm) & 0x10)) {
60
+ return false;
61
+ }
62
+
63
+ if (!fn) {
64
+ return false;
65
+ }
66
+
67
+ if ((a->vd | a->vm) & a->q) {
68
+ return false;
69
+ }
70
+
71
+ if (!vfp_access_check(s)) {
72
+ return true;
73
+ }
74
+
75
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
76
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
77
+ fn(tmp, tmp);
78
+ neon_store_reg(a->vd, pass, tmp);
79
+ }
80
+
81
+ return true;
82
+}
83
+
84
+static bool trans_VREV32(DisasContext *s, arg_2misc *a)
85
+{
86
+ static NeonGenOneOpFn * const fn[] = {
87
+ tcg_gen_bswap32_i32,
88
+ gen_swap_half,
89
+ NULL,
90
+ NULL,
91
+ };
92
+ return do_2misc(s, a, fn[a->size]);
93
+}
94
+
95
+static bool trans_VREV16(DisasContext *s, arg_2misc *a)
96
+{
97
+ if (a->size != 0) {
98
+ return false;
99
+ }
100
+ return do_2misc(s, a, gen_rev16);
101
+}
102
diff --git a/target/arm/translate.c b/target/arm/translate.c
103
index XXXXXXX..XXXXXXX 100644
104
--- a/target/arm/translate.c
105
+++ b/target/arm/translate.c
106
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
107
case NEON_2RM_AESE: case NEON_2RM_AESMC:
108
case NEON_2RM_SHA1H:
109
case NEON_2RM_SHA1SU1:
110
+ case NEON_2RM_VREV32:
111
+ case NEON_2RM_VREV16:
112
/* handled by decodetree */
113
return 1;
114
case NEON_2RM_VTRN:
115
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
116
for (pass = 0; pass < (q ? 4 : 2); pass++) {
117
tmp = neon_load_reg(rm, pass);
118
switch (op) {
119
- case NEON_2RM_VREV32:
120
- switch (size) {
121
- case 0: tcg_gen_bswap32_i32(tmp, tmp); break;
122
- case 1: gen_swap_half(tmp, tmp); break;
123
- default: abort();
124
- }
125
- break;
126
- case NEON_2RM_VREV16:
127
- gen_rev16(tmp, tmp);
128
- break;
129
case NEON_2RM_VCLS:
130
switch (size) {
131
case 0: gen_helper_neon_cls_s8(tmp, tmp); break;
132
--
133
2.20.1
134
135
diff view generated by jsdifflib
Deleted patch
1
Convert the remaining ops in the Neon 2-reg-misc group which
2
can be implemented simply with our do_2misc() helper.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-14-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 10 +++++
9
target/arm/translate-neon.inc.c | 69 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 38 ++++--------------
11
3 files changed, 86 insertions(+), 31 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
AESMC 1111 001 11 . 11 .. 00 .... 0 0111 0 . 0 .... @2misc_q1
19
AESIMC 1111 001 11 . 11 .. 00 .... 0 0111 1 . 0 .... @2misc_q1
20
21
+ VCLS 1111 001 11 . 11 .. 00 .... 0 1000 . . 0 .... @2misc
22
+ VCLZ 1111 001 11 . 11 .. 00 .... 0 1001 . . 0 .... @2misc
23
+ VCNT 1111 001 11 . 11 .. 00 .... 0 1010 . . 0 .... @2misc
24
+
25
VMVN 1111 001 11 . 11 .. 00 .... 0 1011 . . 0 .... @2misc
26
27
VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
28
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
29
VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc
30
VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc
31
32
+ VABS_F 1111 001 11 . 11 .. 01 .... 0 1110 . . 0 .... @2misc
33
+ VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc
34
+
35
VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
36
VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
37
38
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
39
40
VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
41
VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
42
+
43
+ VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc
44
+ VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc
45
]
46
47
# Subgroup for size != 0b11
48
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
49
index XXXXXXX..XXXXXXX 100644
50
--- a/target/arm/translate-neon.inc.c
51
+++ b/target/arm/translate-neon.inc.c
52
@@ -XXX,XX +XXX,XX @@ static bool trans_VREV16(DisasContext *s, arg_2misc *a)
53
}
54
return do_2misc(s, a, gen_rev16);
55
}
56
+
57
+static bool trans_VCLS(DisasContext *s, arg_2misc *a)
58
+{
59
+ static NeonGenOneOpFn * const fn[] = {
60
+ gen_helper_neon_cls_s8,
61
+ gen_helper_neon_cls_s16,
62
+ gen_helper_neon_cls_s32,
63
+ NULL,
64
+ };
65
+ return do_2misc(s, a, fn[a->size]);
66
+}
67
+
68
+static void do_VCLZ_32(TCGv_i32 rd, TCGv_i32 rm)
69
+{
70
+ tcg_gen_clzi_i32(rd, rm, 32);
71
+}
72
+
73
+static bool trans_VCLZ(DisasContext *s, arg_2misc *a)
74
+{
75
+ static NeonGenOneOpFn * const fn[] = {
76
+ gen_helper_neon_clz_u8,
77
+ gen_helper_neon_clz_u16,
78
+ do_VCLZ_32,
79
+ NULL,
80
+ };
81
+ return do_2misc(s, a, fn[a->size]);
82
+}
83
+
84
+static bool trans_VCNT(DisasContext *s, arg_2misc *a)
85
+{
86
+ if (a->size != 0) {
87
+ return false;
88
+ }
89
+ return do_2misc(s, a, gen_helper_neon_cnt_u8);
90
+}
91
+
92
+static bool trans_VABS_F(DisasContext *s, arg_2misc *a)
93
+{
94
+ if (a->size != 2) {
95
+ return false;
96
+ }
97
+ /* TODO: FP16 : size == 1 */
98
+ return do_2misc(s, a, gen_helper_vfp_abss);
99
+}
100
+
101
+static bool trans_VNEG_F(DisasContext *s, arg_2misc *a)
102
+{
103
+ if (a->size != 2) {
104
+ return false;
105
+ }
106
+ /* TODO: FP16 : size == 1 */
107
+ return do_2misc(s, a, gen_helper_vfp_negs);
108
+}
109
+
110
+static bool trans_VRECPE(DisasContext *s, arg_2misc *a)
111
+{
112
+ if (a->size != 2) {
113
+ return false;
114
+ }
115
+ return do_2misc(s, a, gen_helper_recpe_u32);
116
+}
117
+
118
+static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a)
119
+{
120
+ if (a->size != 2) {
121
+ return false;
122
+ }
123
+ return do_2misc(s, a, gen_helper_rsqrte_u32);
124
+}
125
diff --git a/target/arm/translate.c b/target/arm/translate.c
126
index XXXXXXX..XXXXXXX 100644
127
--- a/target/arm/translate.c
128
+++ b/target/arm/translate.c
129
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
130
case NEON_2RM_SHA1SU1:
131
case NEON_2RM_VREV32:
132
case NEON_2RM_VREV16:
133
+ case NEON_2RM_VCLS:
134
+ case NEON_2RM_VCLZ:
135
+ case NEON_2RM_VCNT:
136
+ case NEON_2RM_VABS_F:
137
+ case NEON_2RM_VNEG_F:
138
+ case NEON_2RM_VRECPE:
139
+ case NEON_2RM_VRSQRTE:
140
/* handled by decodetree */
141
return 1;
142
case NEON_2RM_VTRN:
143
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
144
for (pass = 0; pass < (q ? 4 : 2); pass++) {
145
tmp = neon_load_reg(rm, pass);
146
switch (op) {
147
- case NEON_2RM_VCLS:
148
- switch (size) {
149
- case 0: gen_helper_neon_cls_s8(tmp, tmp); break;
150
- case 1: gen_helper_neon_cls_s16(tmp, tmp); break;
151
- case 2: gen_helper_neon_cls_s32(tmp, tmp); break;
152
- default: abort();
153
- }
154
- break;
155
- case NEON_2RM_VCLZ:
156
- switch (size) {
157
- case 0: gen_helper_neon_clz_u8(tmp, tmp); break;
158
- case 1: gen_helper_neon_clz_u16(tmp, tmp); break;
159
- case 2: tcg_gen_clzi_i32(tmp, tmp, 32); break;
160
- default: abort();
161
- }
162
- break;
163
- case NEON_2RM_VCNT:
164
- gen_helper_neon_cnt_u8(tmp, tmp);
165
- break;
166
case NEON_2RM_VQABS:
167
switch (size) {
168
case 0:
169
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
170
tcg_temp_free_ptr(fpstatus);
171
break;
172
}
173
- case NEON_2RM_VABS_F:
174
- gen_helper_vfp_abss(tmp, tmp);
175
- break;
176
- case NEON_2RM_VNEG_F:
177
- gen_helper_vfp_negs(tmp, tmp);
178
- break;
179
case NEON_2RM_VSWP:
180
tmp2 = neon_load_reg(rd, pass);
181
neon_store_reg(rm, pass, tmp2);
182
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
183
tcg_temp_free_ptr(fpst);
184
break;
185
}
186
- case NEON_2RM_VRECPE:
187
- gen_helper_recpe_u32(tmp, tmp);
188
- break;
189
- case NEON_2RM_VRSQRTE:
190
- gen_helper_rsqrte_u32(tmp, tmp);
191
- break;
192
case NEON_2RM_VRECPE_F:
193
{
194
TCGv_ptr fpstatus = get_fpstatus_ptr(1);
195
--
196
2.20.1
197
198
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon VQABS and VQNEG insns to decodetree.
2
Since these are the only ones which need cpu_env passing to
3
the helper, we wrap the helper rather than creating a whole
4
new do_2misc_env() function.
5
1
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20200616170844.13318-15-peter.maydell@linaro.org
9
---
10
target/arm/neon-dp.decode | 3 +++
11
target/arm/translate-neon.inc.c | 35 +++++++++++++++++++++++++++++++++
12
target/arm/translate.c | 30 ++--------------------------
13
3 files changed, 40 insertions(+), 28 deletions(-)
14
15
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/neon-dp.decode
18
+++ b/target/arm/neon-dp.decode
19
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
20
VPADAL_S 1111 001 11 . 11 .. 00 .... 0 1100 . . 0 .... @2misc
21
VPADAL_U 1111 001 11 . 11 .. 00 .... 0 1101 . . 0 .... @2misc
22
23
+ VQABS 1111 001 11 . 11 .. 00 .... 0 1110 . . 0 .... @2misc
24
+ VQNEG 1111 001 11 . 11 .. 00 .... 0 1111 . . 0 .... @2misc
25
+
26
VCGT0 1111 001 11 . 11 .. 01 .... 0 0000 . . 0 .... @2misc
27
VCGE0 1111 001 11 . 11 .. 01 .... 0 0001 . . 0 .... @2misc
28
VCEQ0 1111 001 11 . 11 .. 01 .... 0 0010 . . 0 .... @2misc
29
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
30
index XXXXXXX..XXXXXXX 100644
31
--- a/target/arm/translate-neon.inc.c
32
+++ b/target/arm/translate-neon.inc.c
33
@@ -XXX,XX +XXX,XX @@ static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a)
34
}
35
return do_2misc(s, a, gen_helper_rsqrte_u32);
36
}
37
+
38
+#define WRAP_1OP_ENV_FN(WRAPNAME, FUNC) \
39
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m) \
40
+ { \
41
+ FUNC(d, cpu_env, m); \
42
+ }
43
+
44
+WRAP_1OP_ENV_FN(gen_VQABS_s8, gen_helper_neon_qabs_s8)
45
+WRAP_1OP_ENV_FN(gen_VQABS_s16, gen_helper_neon_qabs_s16)
46
+WRAP_1OP_ENV_FN(gen_VQABS_s32, gen_helper_neon_qabs_s32)
47
+WRAP_1OP_ENV_FN(gen_VQNEG_s8, gen_helper_neon_qneg_s8)
48
+WRAP_1OP_ENV_FN(gen_VQNEG_s16, gen_helper_neon_qneg_s16)
49
+WRAP_1OP_ENV_FN(gen_VQNEG_s32, gen_helper_neon_qneg_s32)
50
+
51
+static bool trans_VQABS(DisasContext *s, arg_2misc *a)
52
+{
53
+ static NeonGenOneOpFn * const fn[] = {
54
+ gen_VQABS_s8,
55
+ gen_VQABS_s16,
56
+ gen_VQABS_s32,
57
+ NULL,
58
+ };
59
+ return do_2misc(s, a, fn[a->size]);
60
+}
61
+
62
+static bool trans_VQNEG(DisasContext *s, arg_2misc *a)
63
+{
64
+ static NeonGenOneOpFn * const fn[] = {
65
+ gen_VQNEG_s8,
66
+ gen_VQNEG_s16,
67
+ gen_VQNEG_s32,
68
+ NULL,
69
+ };
70
+ return do_2misc(s, a, fn[a->size]);
71
+}
72
diff --git a/target/arm/translate.c b/target/arm/translate.c
73
index XXXXXXX..XXXXXXX 100644
74
--- a/target/arm/translate.c
75
+++ b/target/arm/translate.c
76
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
77
case NEON_2RM_VNEG_F:
78
case NEON_2RM_VRECPE:
79
case NEON_2RM_VRSQRTE:
80
+ case NEON_2RM_VQABS:
81
+ case NEON_2RM_VQNEG:
82
/* handled by decodetree */
83
return 1;
84
case NEON_2RM_VTRN:
85
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
86
for (pass = 0; pass < (q ? 4 : 2); pass++) {
87
tmp = neon_load_reg(rm, pass);
88
switch (op) {
89
- case NEON_2RM_VQABS:
90
- switch (size) {
91
- case 0:
92
- gen_helper_neon_qabs_s8(tmp, cpu_env, tmp);
93
- break;
94
- case 1:
95
- gen_helper_neon_qabs_s16(tmp, cpu_env, tmp);
96
- break;
97
- case 2:
98
- gen_helper_neon_qabs_s32(tmp, cpu_env, tmp);
99
- break;
100
- default: abort();
101
- }
102
- break;
103
- case NEON_2RM_VQNEG:
104
- switch (size) {
105
- case 0:
106
- gen_helper_neon_qneg_s8(tmp, cpu_env, tmp);
107
- break;
108
- case 1:
109
- gen_helper_neon_qneg_s16(tmp, cpu_env, tmp);
110
- break;
111
- case 2:
112
- gen_helper_neon_qneg_s32(tmp, cpu_env, tmp);
113
- break;
114
- default: abort();
115
- }
116
- break;
117
case NEON_2RM_VCGT0_F:
118
{
119
TCGv_ptr fpstatus = get_fpstatus_ptr(1);
120
--
121
2.20.1
122
123
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon 2-reg-misc insns which are implemented with
2
simple calls to functions that take the input, output and
3
fpstatus pointer.
4
1
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20200616170844.13318-16-peter.maydell@linaro.org
8
---
9
target/arm/translate.h | 1 +
10
target/arm/neon-dp.decode | 8 +++++
11
target/arm/translate-neon.inc.c | 62 +++++++++++++++++++++++++++++++++
12
target/arm/translate.c | 56 ++++-------------------------
13
4 files changed, 78 insertions(+), 49 deletions(-)
14
15
diff --git a/target/arm/translate.h b/target/arm/translate.h
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate.h
18
+++ b/target/arm/translate.h
19
@@ -XXX,XX +XXX,XX @@ typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
20
typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
21
typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
22
typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32);
23
+typedef void NeonGenOneSingleOpFn(TCGv_i32, TCGv_i32, TCGv_ptr);
24
typedef void NeonGenTwoSingleOpFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
25
typedef void NeonGenTwoDoubleOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
26
typedef void NeonGenOne64OpFn(TCGv_i64, TCGv_i64);
27
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
28
index XXXXXXX..XXXXXXX 100644
29
--- a/target/arm/neon-dp.decode
30
+++ b/target/arm/neon-dp.decode
31
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
32
SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1
33
SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1
34
35
+ VRINTX 1111 001 11 . 11 .. 10 .... 0 1001 . . 0 .... @2misc
36
+
37
VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
38
VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
39
40
VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc
41
VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc
42
+ VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc
43
+ VRSQRTE_F 1111 001 11 . 11 .. 11 .... 0 1011 . . 0 .... @2misc
44
+ VCVT_FS 1111 001 11 . 11 .. 11 .... 0 1100 . . 0 .... @2misc
45
+ VCVT_FU 1111 001 11 . 11 .. 11 .... 0 1101 . . 0 .... @2misc
46
+ VCVT_SF 1111 001 11 . 11 .. 11 .... 0 1110 . . 0 .... @2misc
47
+ VCVT_UF 1111 001 11 . 11 .. 11 .... 0 1111 . . 0 .... @2misc
48
]
49
50
# Subgroup for size != 0b11
51
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
52
index XXXXXXX..XXXXXXX 100644
53
--- a/target/arm/translate-neon.inc.c
54
+++ b/target/arm/translate-neon.inc.c
55
@@ -XXX,XX +XXX,XX @@ static bool trans_VQNEG(DisasContext *s, arg_2misc *a)
56
};
57
return do_2misc(s, a, fn[a->size]);
58
}
59
+
60
+static bool do_2misc_fp(DisasContext *s, arg_2misc *a,
61
+ NeonGenOneSingleOpFn *fn)
62
+{
63
+ int pass;
64
+ TCGv_ptr fpst;
65
+
66
+ /* Handle a 2-reg-misc operation by iterating 32 bits at a time */
67
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
68
+ return false;
69
+ }
70
+
71
+ /* UNDEF accesses to D16-D31 if they don't exist. */
72
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
73
+ ((a->vd | a->vm) & 0x10)) {
74
+ return false;
75
+ }
76
+
77
+ if (a->size != 2) {
78
+ /* TODO: FP16 will be the size == 1 case */
79
+ return false;
80
+ }
81
+
82
+ if ((a->vd | a->vm) & a->q) {
83
+ return false;
84
+ }
85
+
86
+ if (!vfp_access_check(s)) {
87
+ return true;
88
+ }
89
+
90
+ fpst = get_fpstatus_ptr(1);
91
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
92
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
93
+ fn(tmp, tmp, fpst);
94
+ neon_store_reg(a->vd, pass, tmp);
95
+ }
96
+ tcg_temp_free_ptr(fpst);
97
+
98
+ return true;
99
+}
100
+
101
+#define DO_2MISC_FP(INSN, FUNC) \
102
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
103
+ { \
104
+ return do_2misc_fp(s, a, FUNC); \
105
+ }
106
+
107
+DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32)
108
+DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32)
109
+DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos)
110
+DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos)
111
+DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs)
112
+DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs)
113
+
114
+static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
115
+{
116
+ if (!arm_dc_feature(s, ARM_FEATURE_V8)) {
117
+ return false;
118
+ }
119
+ return do_2misc_fp(s, a, gen_helper_rints_exact);
120
+}
121
diff --git a/target/arm/translate.c b/target/arm/translate.c
122
index XXXXXXX..XXXXXXX 100644
123
--- a/target/arm/translate.c
124
+++ b/target/arm/translate.c
125
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
126
case NEON_2RM_VRSQRTE:
127
case NEON_2RM_VQABS:
128
case NEON_2RM_VQNEG:
129
+ case NEON_2RM_VRECPE_F:
130
+ case NEON_2RM_VRSQRTE_F:
131
+ case NEON_2RM_VCVT_FS:
132
+ case NEON_2RM_VCVT_FU:
133
+ case NEON_2RM_VCVT_SF:
134
+ case NEON_2RM_VCVT_UF:
135
+ case NEON_2RM_VRINTX:
136
/* handled by decodetree */
137
return 1;
138
case NEON_2RM_VTRN:
139
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
140
tcg_temp_free_i32(tcg_rmode);
141
break;
142
}
143
- case NEON_2RM_VRINTX:
144
- {
145
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
146
- gen_helper_rints_exact(tmp, tmp, fpstatus);
147
- tcg_temp_free_ptr(fpstatus);
148
- break;
149
- }
150
case NEON_2RM_VCVTAU:
151
case NEON_2RM_VCVTAS:
152
case NEON_2RM_VCVTNU:
153
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
154
tcg_temp_free_ptr(fpst);
155
break;
156
}
157
- case NEON_2RM_VRECPE_F:
158
- {
159
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
160
- gen_helper_recpe_f32(tmp, tmp, fpstatus);
161
- tcg_temp_free_ptr(fpstatus);
162
- break;
163
- }
164
- case NEON_2RM_VRSQRTE_F:
165
- {
166
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
167
- gen_helper_rsqrte_f32(tmp, tmp, fpstatus);
168
- tcg_temp_free_ptr(fpstatus);
169
- break;
170
- }
171
- case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */
172
- {
173
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
174
- gen_helper_vfp_sitos(tmp, tmp, fpstatus);
175
- tcg_temp_free_ptr(fpstatus);
176
- break;
177
- }
178
- case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */
179
- {
180
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
181
- gen_helper_vfp_uitos(tmp, tmp, fpstatus);
182
- tcg_temp_free_ptr(fpstatus);
183
- break;
184
- }
185
- case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */
186
- {
187
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
188
- gen_helper_vfp_tosizs(tmp, tmp, fpstatus);
189
- tcg_temp_free_ptr(fpstatus);
190
- break;
191
- }
192
- case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */
193
- {
194
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
195
- gen_helper_vfp_touizs(tmp, tmp, fpstatus);
196
- tcg_temp_free_ptr(fpstatus);
197
- break;
198
- }
199
default:
200
/* Reserved op values were caught by the
201
* neon_2rm_sizes[] check earlier.
202
--
203
2.20.1
204
205
diff view generated by jsdifflib
Deleted patch
1
Convert the fp-compare-with-zero insns in the Neon 2-reg-misc group to
2
decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-17-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 6 ++++
9
target/arm/translate-neon.inc.c | 28 ++++++++++++++++++
10
target/arm/translate.c | 50 ++++-----------------------------
11
3 files changed, 39 insertions(+), 45 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
VABS 1111 001 11 . 11 .. 01 .... 0 0110 . . 0 .... @2misc
19
VNEG 1111 001 11 . 11 .. 01 .... 0 0111 . . 0 .... @2misc
20
21
+ VCGT0_F 1111 001 11 . 11 .. 01 .... 0 1000 . . 0 .... @2misc
22
+ VCGE0_F 1111 001 11 . 11 .. 01 .... 0 1001 . . 0 .... @2misc
23
+ VCEQ0_F 1111 001 11 . 11 .. 01 .... 0 1010 . . 0 .... @2misc
24
+ VCLE0_F 1111 001 11 . 11 .. 01 .... 0 1011 . . 0 .... @2misc
25
+ VCLT0_F 1111 001 11 . 11 .. 01 .... 0 1100 . . 0 .... @2misc
26
+
27
VABS_F 1111 001 11 . 11 .. 01 .... 0 1110 . . 0 .... @2misc
28
VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc
29
30
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
31
index XXXXXXX..XXXXXXX 100644
32
--- a/target/arm/translate-neon.inc.c
33
+++ b/target/arm/translate-neon.inc.c
34
@@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX(DisasContext *s, arg_2misc *a)
35
}
36
return do_2misc_fp(s, a, gen_helper_rints_exact);
37
}
38
+
39
+#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \
40
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \
41
+ { \
42
+ TCGv_i32 zero = tcg_const_i32(0); \
43
+ FUNC(d, m, zero, fpst); \
44
+ tcg_temp_free_i32(zero); \
45
+ }
46
+#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \
47
+ static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \
48
+ { \
49
+ TCGv_i32 zero = tcg_const_i32(0); \
50
+ FUNC(d, zero, m, fpst); \
51
+ tcg_temp_free_i32(zero); \
52
+ }
53
+
54
+#define DO_FP_CMP0(INSN, FUNC, REV) \
55
+ WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \
56
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
57
+ { \
58
+ return do_2misc_fp(s, a, gen_##INSN); \
59
+ }
60
+
61
+DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD)
62
+DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD)
63
+DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD)
64
+DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV)
65
+DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV)
66
diff --git a/target/arm/translate.c b/target/arm/translate.c
67
index XXXXXXX..XXXXXXX 100644
68
--- a/target/arm/translate.c
69
+++ b/target/arm/translate.c
70
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
71
case NEON_2RM_VCVT_SF:
72
case NEON_2RM_VCVT_UF:
73
case NEON_2RM_VRINTX:
74
+ case NEON_2RM_VCGT0_F:
75
+ case NEON_2RM_VCGE0_F:
76
+ case NEON_2RM_VCEQ0_F:
77
+ case NEON_2RM_VCLE0_F:
78
+ case NEON_2RM_VCLT0_F:
79
/* handled by decodetree */
80
return 1;
81
case NEON_2RM_VTRN:
82
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
83
for (pass = 0; pass < (q ? 4 : 2); pass++) {
84
tmp = neon_load_reg(rm, pass);
85
switch (op) {
86
- case NEON_2RM_VCGT0_F:
87
- {
88
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
89
- tmp2 = tcg_const_i32(0);
90
- gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
91
- tcg_temp_free_i32(tmp2);
92
- tcg_temp_free_ptr(fpstatus);
93
- break;
94
- }
95
- case NEON_2RM_VCGE0_F:
96
- {
97
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
98
- tmp2 = tcg_const_i32(0);
99
- gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
100
- tcg_temp_free_i32(tmp2);
101
- tcg_temp_free_ptr(fpstatus);
102
- break;
103
- }
104
- case NEON_2RM_VCEQ0_F:
105
- {
106
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
107
- tmp2 = tcg_const_i32(0);
108
- gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
109
- tcg_temp_free_i32(tmp2);
110
- tcg_temp_free_ptr(fpstatus);
111
- break;
112
- }
113
- case NEON_2RM_VCLE0_F:
114
- {
115
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
116
- tmp2 = tcg_const_i32(0);
117
- gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus);
118
- tcg_temp_free_i32(tmp2);
119
- tcg_temp_free_ptr(fpstatus);
120
- break;
121
- }
122
- case NEON_2RM_VCLT0_F:
123
- {
124
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
125
- tmp2 = tcg_const_i32(0);
126
- gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus);
127
- tcg_temp_free_i32(tmp2);
128
- tcg_temp_free_ptr(fpstatus);
129
- break;
130
- }
131
case NEON_2RM_VSWP:
132
tmp2 = neon_load_reg(rd, pass);
133
neon_store_reg(rm, pass, tmp2);
134
--
135
2.20.1
136
137
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon 2-reg-misc VRINT insns to decodetree.
2
Giving these insns their own do_vrint() function allows us
3
to change the rounding mode just once at the start and end
4
rather than doing it for every element in the vector.
5
1
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20200616170844.13318-18-peter.maydell@linaro.org
9
---
10
target/arm/neon-dp.decode | 8 +++++
11
target/arm/translate-neon.inc.c | 61 +++++++++++++++++++++++++++++++++
12
target/arm/translate.c | 31 +++--------------
13
3 files changed, 74 insertions(+), 26 deletions(-)
14
15
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/neon-dp.decode
18
+++ b/target/arm/neon-dp.decode
19
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
20
SHA1SU1 1111 001 11 . 11 .. 10 .... 0 0111 0 . 0 .... @2misc_q1
21
SHA256SU0 1111 001 11 . 11 .. 10 .... 0 0111 1 . 0 .... @2misc_q1
22
23
+ VRINTN 1111 001 11 . 11 .. 10 .... 0 1000 . . 0 .... @2misc
24
VRINTX 1111 001 11 . 11 .. 10 .... 0 1001 . . 0 .... @2misc
25
+ VRINTA 1111 001 11 . 11 .. 10 .... 0 1010 . . 0 .... @2misc
26
+ VRINTZ 1111 001 11 . 11 .. 10 .... 0 1011 . . 0 .... @2misc
27
28
VCVT_F16_F32 1111 001 11 . 11 .. 10 .... 0 1100 0 . 0 .... @2misc_q0
29
+
30
+ VRINTM 1111 001 11 . 11 .. 10 .... 0 1101 . . 0 .... @2misc
31
+
32
VCVT_F32_F16 1111 001 11 . 11 .. 10 .... 0 1110 0 . 0 .... @2misc_q0
33
34
+ VRINTP 1111 001 11 . 11 .. 10 .... 0 1111 . . 0 .... @2misc
35
+
36
VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc
37
VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc
38
VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc
39
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
40
index XXXXXXX..XXXXXXX 100644
41
--- a/target/arm/translate-neon.inc.c
42
+++ b/target/arm/translate-neon.inc.c
43
@@ -XXX,XX +XXX,XX @@ DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD)
44
DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD)
45
DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV)
46
DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV)
47
+
48
+static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode)
49
+{
50
+ /*
51
+ * Handle a VRINT* operation by iterating 32 bits at a time,
52
+ * with a specified rounding mode in operation.
53
+ */
54
+ int pass;
55
+ TCGv_ptr fpst;
56
+ TCGv_i32 tcg_rmode;
57
+
58
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
59
+ !arm_dc_feature(s, ARM_FEATURE_V8)) {
60
+ return false;
61
+ }
62
+
63
+ /* UNDEF accesses to D16-D31 if they don't exist. */
64
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
65
+ ((a->vd | a->vm) & 0x10)) {
66
+ return false;
67
+ }
68
+
69
+ if (a->size != 2) {
70
+ /* TODO: FP16 will be the size == 1 case */
71
+ return false;
72
+ }
73
+
74
+ if ((a->vd | a->vm) & a->q) {
75
+ return false;
76
+ }
77
+
78
+ if (!vfp_access_check(s)) {
79
+ return true;
80
+ }
81
+
82
+ fpst = get_fpstatus_ptr(1);
83
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
84
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
85
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
86
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
87
+ gen_helper_rints(tmp, tmp, fpst);
88
+ neon_store_reg(a->vd, pass, tmp);
89
+ }
90
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
91
+ tcg_temp_free_i32(tcg_rmode);
92
+ tcg_temp_free_ptr(fpst);
93
+
94
+ return true;
95
+}
96
+
97
+#define DO_VRINT(INSN, RMODE) \
98
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
99
+ { \
100
+ return do_vrint(s, a, RMODE); \
101
+ }
102
+
103
+DO_VRINT(VRINTN, FPROUNDING_TIEEVEN)
104
+DO_VRINT(VRINTA, FPROUNDING_TIEAWAY)
105
+DO_VRINT(VRINTZ, FPROUNDING_ZERO)
106
+DO_VRINT(VRINTM, FPROUNDING_NEGINF)
107
+DO_VRINT(VRINTP, FPROUNDING_POSINF)
108
diff --git a/target/arm/translate.c b/target/arm/translate.c
109
index XXXXXXX..XXXXXXX 100644
110
--- a/target/arm/translate.c
111
+++ b/target/arm/translate.c
112
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
113
case NEON_2RM_VCEQ0_F:
114
case NEON_2RM_VCLE0_F:
115
case NEON_2RM_VCLT0_F:
116
+ case NEON_2RM_VRINTN:
117
+ case NEON_2RM_VRINTA:
118
+ case NEON_2RM_VRINTM:
119
+ case NEON_2RM_VRINTP:
120
+ case NEON_2RM_VRINTZ:
121
/* handled by decodetree */
122
return 1;
123
case NEON_2RM_VTRN:
124
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
125
}
126
neon_store_reg(rm, pass, tmp2);
127
break;
128
- case NEON_2RM_VRINTN:
129
- case NEON_2RM_VRINTA:
130
- case NEON_2RM_VRINTM:
131
- case NEON_2RM_VRINTP:
132
- case NEON_2RM_VRINTZ:
133
- {
134
- TCGv_i32 tcg_rmode;
135
- TCGv_ptr fpstatus = get_fpstatus_ptr(1);
136
- int rmode;
137
-
138
- if (op == NEON_2RM_VRINTZ) {
139
- rmode = FPROUNDING_ZERO;
140
- } else {
141
- rmode = fp_decode_rm[((op & 0x6) >> 1) ^ 1];
142
- }
143
-
144
- tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
145
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
146
- cpu_env);
147
- gen_helper_rints(tmp, tmp, fpstatus);
148
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
149
- cpu_env);
150
- tcg_temp_free_ptr(fpstatus);
151
- tcg_temp_free_i32(tcg_rmode);
152
- break;
153
- }
154
case NEON_2RM_VCVTAU:
155
case NEON_2RM_VCVTAS:
156
case NEON_2RM_VCVTNU:
157
--
158
2.20.1
159
160
diff view generated by jsdifflib
Deleted patch
1
Convert the VCVT instructions in the 2-reg-misc grouping to
2
decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200616170844.13318-19-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 9 +++++
9
target/arm/translate-neon.inc.c | 70 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 70 ++++-----------------------------
11
3 files changed, 87 insertions(+), 62 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
18
19
VRINTP 1111 001 11 . 11 .. 10 .... 0 1111 . . 0 .... @2misc
20
21
+ VCVTAS 1111 001 11 . 11 .. 11 .... 0 0000 . . 0 .... @2misc
22
+ VCVTAU 1111 001 11 . 11 .. 11 .... 0 0001 . . 0 .... @2misc
23
+ VCVTNS 1111 001 11 . 11 .. 11 .... 0 0010 . . 0 .... @2misc
24
+ VCVTNU 1111 001 11 . 11 .. 11 .... 0 0011 . . 0 .... @2misc
25
+ VCVTPS 1111 001 11 . 11 .. 11 .... 0 0100 . . 0 .... @2misc
26
+ VCVTPU 1111 001 11 . 11 .. 11 .... 0 0101 . . 0 .... @2misc
27
+ VCVTMS 1111 001 11 . 11 .. 11 .... 0 0110 . . 0 .... @2misc
28
+ VCVTMU 1111 001 11 . 11 .. 11 .... 0 0111 . . 0 .... @2misc
29
+
30
VRECPE 1111 001 11 . 11 .. 11 .... 0 1000 . . 0 .... @2misc
31
VRSQRTE 1111 001 11 . 11 .. 11 .... 0 1001 . . 0 .... @2misc
32
VRECPE_F 1111 001 11 . 11 .. 11 .... 0 1010 . . 0 .... @2misc
33
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
34
index XXXXXXX..XXXXXXX 100644
35
--- a/target/arm/translate-neon.inc.c
36
+++ b/target/arm/translate-neon.inc.c
37
@@ -XXX,XX +XXX,XX @@ DO_VRINT(VRINTA, FPROUNDING_TIEAWAY)
38
DO_VRINT(VRINTZ, FPROUNDING_ZERO)
39
DO_VRINT(VRINTM, FPROUNDING_NEGINF)
40
DO_VRINT(VRINTP, FPROUNDING_POSINF)
41
+
42
+static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed)
43
+{
44
+ /*
45
+ * Handle a VCVT* operation by iterating 32 bits at a time,
46
+ * with a specified rounding mode in operation.
47
+ */
48
+ int pass;
49
+ TCGv_ptr fpst;
50
+ TCGv_i32 tcg_rmode, tcg_shift;
51
+
52
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON) ||
53
+ !arm_dc_feature(s, ARM_FEATURE_V8)) {
54
+ return false;
55
+ }
56
+
57
+ /* UNDEF accesses to D16-D31 if they don't exist. */
58
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
59
+ ((a->vd | a->vm) & 0x10)) {
60
+ return false;
61
+ }
62
+
63
+ if (a->size != 2) {
64
+ /* TODO: FP16 will be the size == 1 case */
65
+ return false;
66
+ }
67
+
68
+ if ((a->vd | a->vm) & a->q) {
69
+ return false;
70
+ }
71
+
72
+ if (!vfp_access_check(s)) {
73
+ return true;
74
+ }
75
+
76
+ fpst = get_fpstatus_ptr(1);
77
+ tcg_shift = tcg_const_i32(0);
78
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
79
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
80
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
81
+ TCGv_i32 tmp = neon_load_reg(a->vm, pass);
82
+ if (is_signed) {
83
+ gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst);
84
+ } else {
85
+ gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst);
86
+ }
87
+ neon_store_reg(a->vd, pass, tmp);
88
+ }
89
+ gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env);
90
+ tcg_temp_free_i32(tcg_rmode);
91
+ tcg_temp_free_i32(tcg_shift);
92
+ tcg_temp_free_ptr(fpst);
93
+
94
+ return true;
95
+}
96
+
97
+#define DO_VCVT(INSN, RMODE, SIGNED) \
98
+ static bool trans_##INSN(DisasContext *s, arg_2misc *a) \
99
+ { \
100
+ return do_vcvt(s, a, RMODE, SIGNED); \
101
+ }
102
+
103
+DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false)
104
+DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true)
105
+DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false)
106
+DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true)
107
+DO_VCVT(VCVTPU, FPROUNDING_POSINF, false)
108
+DO_VCVT(VCVTPS, FPROUNDING_POSINF, true)
109
+DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false)
110
+DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true)
111
diff --git a/target/arm/translate.c b/target/arm/translate.c
112
index XXXXXXX..XXXXXXX 100644
113
--- a/target/arm/translate.c
114
+++ b/target/arm/translate.c
115
@@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
116
#define NEON_2RM_VCVT_SF 62
117
#define NEON_2RM_VCVT_UF 63
118
119
-static bool neon_2rm_is_v8_op(int op)
120
-{
121
- /* Return true if this neon 2reg-misc op is ARMv8 and up */
122
- switch (op) {
123
- case NEON_2RM_VRINTN:
124
- case NEON_2RM_VRINTA:
125
- case NEON_2RM_VRINTM:
126
- case NEON_2RM_VRINTP:
127
- case NEON_2RM_VRINTZ:
128
- case NEON_2RM_VRINTX:
129
- case NEON_2RM_VCVTAU:
130
- case NEON_2RM_VCVTAS:
131
- case NEON_2RM_VCVTNU:
132
- case NEON_2RM_VCVTNS:
133
- case NEON_2RM_VCVTPU:
134
- case NEON_2RM_VCVTPS:
135
- case NEON_2RM_VCVTMU:
136
- case NEON_2RM_VCVTMS:
137
- return true;
138
- default:
139
- return false;
140
- }
141
-}
142
-
143
/* Each entry in this array has bit n set if the insn allows
144
* size value n (otherwise it will UNDEF). Since unallocated
145
* op values will have no bits set they always UNDEF.
146
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
147
if ((neon_2rm_sizes[op] & (1 << size)) == 0) {
148
return 1;
149
}
150
- if (neon_2rm_is_v8_op(op) &&
151
- !arm_dc_feature(s, ARM_FEATURE_V8)) {
152
- return 1;
153
- }
154
if (q && ((rm | rd) & 1)) {
155
return 1;
156
}
157
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
158
case NEON_2RM_VRINTM:
159
case NEON_2RM_VRINTP:
160
case NEON_2RM_VRINTZ:
161
+ case NEON_2RM_VCVTAU:
162
+ case NEON_2RM_VCVTAS:
163
+ case NEON_2RM_VCVTNU:
164
+ case NEON_2RM_VCVTNS:
165
+ case NEON_2RM_VCVTPU:
166
+ case NEON_2RM_VCVTPS:
167
+ case NEON_2RM_VCVTMU:
168
+ case NEON_2RM_VCVTMS:
169
/* handled by decodetree */
170
return 1;
171
case NEON_2RM_VTRN:
172
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
173
}
174
neon_store_reg(rm, pass, tmp2);
175
break;
176
- case NEON_2RM_VCVTAU:
177
- case NEON_2RM_VCVTAS:
178
- case NEON_2RM_VCVTNU:
179
- case NEON_2RM_VCVTNS:
180
- case NEON_2RM_VCVTPU:
181
- case NEON_2RM_VCVTPS:
182
- case NEON_2RM_VCVTMU:
183
- case NEON_2RM_VCVTMS:
184
- {
185
- bool is_signed = !extract32(insn, 7, 1);
186
- TCGv_ptr fpst = get_fpstatus_ptr(1);
187
- TCGv_i32 tcg_rmode, tcg_shift;
188
- int rmode = fp_decode_rm[extract32(insn, 8, 2)];
189
-
190
- tcg_shift = tcg_const_i32(0);
191
- tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
192
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
193
- cpu_env);
194
-
195
- if (is_signed) {
196
- gen_helper_vfp_tosls(tmp, tmp,
197
- tcg_shift, fpst);
198
- } else {
199
- gen_helper_vfp_touls(tmp, tmp,
200
- tcg_shift, fpst);
201
- }
202
-
203
- gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode,
204
- cpu_env);
205
- tcg_temp_free_i32(tcg_rmode);
206
- tcg_temp_free_i32(tcg_shift);
207
- tcg_temp_free_ptr(fpst);
208
- break;
209
- }
210
default:
211
/* Reserved op values were caught by the
212
* neon_2rm_sizes[] check earlier.
213
--
214
2.20.1
215
216
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon VSWP insn to decodetree. Since the new implementation
2
doesn't have to share a pass-loop with the other 2-reg-misc operations
3
we can implement the swap with 64-bit accesses rather than 32-bits
4
(which brings us into line with the pseudocode and is more efficient).
5
1
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20200616170844.13318-20-peter.maydell@linaro.org
9
---
10
target/arm/neon-dp.decode | 2 ++
11
target/arm/translate-neon.inc.c | 41 +++++++++++++++++++++++++++++++++
12
target/arm/translate.c | 5 +---
13
3 files changed, 44 insertions(+), 4 deletions(-)
14
15
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/neon-dp.decode
18
+++ b/target/arm/neon-dp.decode
19
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
20
VABS_F 1111 001 11 . 11 .. 01 .... 0 1110 . . 0 .... @2misc
21
VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc
22
23
+ VSWP 1111 001 11 . 11 .. 10 .... 0 0000 . . 0 .... @2misc
24
+
25
VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
26
VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
27
28
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
29
index XXXXXXX..XXXXXXX 100644
30
--- a/target/arm/translate-neon.inc.c
31
+++ b/target/arm/translate-neon.inc.c
32
@@ -XXX,XX +XXX,XX @@ DO_VCVT(VCVTPU, FPROUNDING_POSINF, false)
33
DO_VCVT(VCVTPS, FPROUNDING_POSINF, true)
34
DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false)
35
DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true)
36
+
37
+static bool trans_VSWP(DisasContext *s, arg_2misc *a)
38
+{
39
+ TCGv_i64 rm, rd;
40
+ int pass;
41
+
42
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
43
+ return false;
44
+ }
45
+
46
+ /* UNDEF accesses to D16-D31 if they don't exist. */
47
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
48
+ ((a->vd | a->vm) & 0x10)) {
49
+ return false;
50
+ }
51
+
52
+ if (a->size != 0) {
53
+ return false;
54
+ }
55
+
56
+ if ((a->vd | a->vm) & a->q) {
57
+ return false;
58
+ }
59
+
60
+ if (!vfp_access_check(s)) {
61
+ return true;
62
+ }
63
+
64
+ rm = tcg_temp_new_i64();
65
+ rd = tcg_temp_new_i64();
66
+ for (pass = 0; pass < (a->q ? 2 : 1); pass++) {
67
+ neon_load_reg64(rm, a->vm + pass);
68
+ neon_load_reg64(rd, a->vd + pass);
69
+ neon_store_reg64(rm, a->vd + pass);
70
+ neon_store_reg64(rd, a->vm + pass);
71
+ }
72
+ tcg_temp_free_i64(rm);
73
+ tcg_temp_free_i64(rd);
74
+
75
+ return true;
76
+}
77
diff --git a/target/arm/translate.c b/target/arm/translate.c
78
index XXXXXXX..XXXXXXX 100644
79
--- a/target/arm/translate.c
80
+++ b/target/arm/translate.c
81
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
82
case NEON_2RM_VCVTPS:
83
case NEON_2RM_VCVTMU:
84
case NEON_2RM_VCVTMS:
85
+ case NEON_2RM_VSWP:
86
/* handled by decodetree */
87
return 1;
88
case NEON_2RM_VTRN:
89
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
90
for (pass = 0; pass < (q ? 4 : 2); pass++) {
91
tmp = neon_load_reg(rm, pass);
92
switch (op) {
93
- case NEON_2RM_VSWP:
94
- tmp2 = neon_load_reg(rd, pass);
95
- neon_store_reg(rm, pass, tmp2);
96
- break;
97
case NEON_2RM_VTRN:
98
tmp2 = neon_load_reg(rd, pass);
99
switch (size) {
100
--
101
2.20.1
102
103
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon VTRN insn to decodetree. This is the last insn in the
2
Neon data-processing group, so we can remove all the now-unused old
3
decoder framework.
4
1
5
It's possible that there's a more efficient implementation of
6
VTRN, but for this conversion we just copy the existing approach.
7
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
10
Message-id: 20200616170844.13318-21-peter.maydell@linaro.org
11
---
12
target/arm/neon-dp.decode | 2 +-
13
target/arm/translate-neon.inc.c | 90 ++++++++
14
target/arm/translate.c | 363 +-------------------------------
15
3 files changed, 93 insertions(+), 362 deletions(-)
16
17
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
18
index XXXXXXX..XXXXXXX 100644
19
--- a/target/arm/neon-dp.decode
20
+++ b/target/arm/neon-dp.decode
21
@@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm
22
VNEG_F 1111 001 11 . 11 .. 01 .... 0 1111 . . 0 .... @2misc
23
24
VSWP 1111 001 11 . 11 .. 10 .... 0 0000 . . 0 .... @2misc
25
-
26
+ VTRN 1111 001 11 . 11 .. 10 .... 0 0001 . . 0 .... @2misc
27
VUZP 1111 001 11 . 11 .. 10 .... 0 0010 . . 0 .... @2misc
28
VZIP 1111 001 11 . 11 .. 10 .... 0 0011 . . 0 .... @2misc
29
30
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
31
index XXXXXXX..XXXXXXX 100644
32
--- a/target/arm/translate-neon.inc.c
33
+++ b/target/arm/translate-neon.inc.c
34
@@ -XXX,XX +XXX,XX @@ static bool trans_VSWP(DisasContext *s, arg_2misc *a)
35
36
return true;
37
}
38
+static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1)
39
+{
40
+ TCGv_i32 rd, tmp;
41
+
42
+ rd = tcg_temp_new_i32();
43
+ tmp = tcg_temp_new_i32();
44
+
45
+ tcg_gen_shli_i32(rd, t0, 8);
46
+ tcg_gen_andi_i32(rd, rd, 0xff00ff00);
47
+ tcg_gen_andi_i32(tmp, t1, 0x00ff00ff);
48
+ tcg_gen_or_i32(rd, rd, tmp);
49
+
50
+ tcg_gen_shri_i32(t1, t1, 8);
51
+ tcg_gen_andi_i32(t1, t1, 0x00ff00ff);
52
+ tcg_gen_andi_i32(tmp, t0, 0xff00ff00);
53
+ tcg_gen_or_i32(t1, t1, tmp);
54
+ tcg_gen_mov_i32(t0, rd);
55
+
56
+ tcg_temp_free_i32(tmp);
57
+ tcg_temp_free_i32(rd);
58
+}
59
+
60
+static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
61
+{
62
+ TCGv_i32 rd, tmp;
63
+
64
+ rd = tcg_temp_new_i32();
65
+ tmp = tcg_temp_new_i32();
66
+
67
+ tcg_gen_shli_i32(rd, t0, 16);
68
+ tcg_gen_andi_i32(tmp, t1, 0xffff);
69
+ tcg_gen_or_i32(rd, rd, tmp);
70
+ tcg_gen_shri_i32(t1, t1, 16);
71
+ tcg_gen_andi_i32(tmp, t0, 0xffff0000);
72
+ tcg_gen_or_i32(t1, t1, tmp);
73
+ tcg_gen_mov_i32(t0, rd);
74
+
75
+ tcg_temp_free_i32(tmp);
76
+ tcg_temp_free_i32(rd);
77
+}
78
+
79
+static bool trans_VTRN(DisasContext *s, arg_2misc *a)
80
+{
81
+ TCGv_i32 tmp, tmp2;
82
+ int pass;
83
+
84
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
85
+ return false;
86
+ }
87
+
88
+ /* UNDEF accesses to D16-D31 if they don't exist. */
89
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
90
+ ((a->vd | a->vm) & 0x10)) {
91
+ return false;
92
+ }
93
+
94
+ if ((a->vd | a->vm) & a->q) {
95
+ return false;
96
+ }
97
+
98
+ if (a->size == 3) {
99
+ return false;
100
+ }
101
+
102
+ if (!vfp_access_check(s)) {
103
+ return true;
104
+ }
105
+
106
+ if (a->size == 2) {
107
+ for (pass = 0; pass < (a->q ? 4 : 2); pass += 2) {
108
+ tmp = neon_load_reg(a->vm, pass);
109
+ tmp2 = neon_load_reg(a->vd, pass + 1);
110
+ neon_store_reg(a->vm, pass, tmp2);
111
+ neon_store_reg(a->vd, pass + 1, tmp);
112
+ }
113
+ } else {
114
+ for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
115
+ tmp = neon_load_reg(a->vm, pass);
116
+ tmp2 = neon_load_reg(a->vd, pass);
117
+ if (a->size == 0) {
118
+ gen_neon_trn_u8(tmp, tmp2);
119
+ } else {
120
+ gen_neon_trn_u16(tmp, tmp2);
121
+ }
122
+ neon_store_reg(a->vm, pass, tmp2);
123
+ neon_store_reg(a->vd, pass, tmp);
124
+ }
125
+ }
126
+ return true;
127
+}
128
diff --git a/target/arm/translate.c b/target/arm/translate.c
129
index XXXXXXX..XXXXXXX 100644
130
--- a/target/arm/translate.c
131
+++ b/target/arm/translate.c
132
@@ -XXX,XX +XXX,XX @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc)
133
gen_rfe(s, pc, load_cpu_field(spsr));
134
}
135
136
-static void gen_neon_trn_u8(TCGv_i32 t0, TCGv_i32 t1)
137
-{
138
- TCGv_i32 rd, tmp;
139
-
140
- rd = tcg_temp_new_i32();
141
- tmp = tcg_temp_new_i32();
142
-
143
- tcg_gen_shli_i32(rd, t0, 8);
144
- tcg_gen_andi_i32(rd, rd, 0xff00ff00);
145
- tcg_gen_andi_i32(tmp, t1, 0x00ff00ff);
146
- tcg_gen_or_i32(rd, rd, tmp);
147
-
148
- tcg_gen_shri_i32(t1, t1, 8);
149
- tcg_gen_andi_i32(t1, t1, 0x00ff00ff);
150
- tcg_gen_andi_i32(tmp, t0, 0xff00ff00);
151
- tcg_gen_or_i32(t1, t1, tmp);
152
- tcg_gen_mov_i32(t0, rd);
153
-
154
- tcg_temp_free_i32(tmp);
155
- tcg_temp_free_i32(rd);
156
-}
157
-
158
-static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
159
-{
160
- TCGv_i32 rd, tmp;
161
-
162
- rd = tcg_temp_new_i32();
163
- tmp = tcg_temp_new_i32();
164
-
165
- tcg_gen_shli_i32(rd, t0, 16);
166
- tcg_gen_andi_i32(tmp, t1, 0xffff);
167
- tcg_gen_or_i32(rd, rd, tmp);
168
- tcg_gen_shri_i32(t1, t1, 16);
169
- tcg_gen_andi_i32(tmp, t0, 0xffff0000);
170
- tcg_gen_or_i32(t1, t1, tmp);
171
- tcg_gen_mov_i32(t0, rd);
172
-
173
- tcg_temp_free_i32(tmp);
174
- tcg_temp_free_i32(rd);
175
-}
176
-
177
-/* Symbolic constants for op fields for Neon 2-register miscellaneous.
178
- * The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B
179
- * table A7-13.
180
- */
181
-#define NEON_2RM_VREV64 0
182
-#define NEON_2RM_VREV32 1
183
-#define NEON_2RM_VREV16 2
184
-#define NEON_2RM_VPADDL 4
185
-#define NEON_2RM_VPADDL_U 5
186
-#define NEON_2RM_AESE 6 /* Includes AESD */
187
-#define NEON_2RM_AESMC 7 /* Includes AESIMC */
188
-#define NEON_2RM_VCLS 8
189
-#define NEON_2RM_VCLZ 9
190
-#define NEON_2RM_VCNT 10
191
-#define NEON_2RM_VMVN 11
192
-#define NEON_2RM_VPADAL 12
193
-#define NEON_2RM_VPADAL_U 13
194
-#define NEON_2RM_VQABS 14
195
-#define NEON_2RM_VQNEG 15
196
-#define NEON_2RM_VCGT0 16
197
-#define NEON_2RM_VCGE0 17
198
-#define NEON_2RM_VCEQ0 18
199
-#define NEON_2RM_VCLE0 19
200
-#define NEON_2RM_VCLT0 20
201
-#define NEON_2RM_SHA1H 21
202
-#define NEON_2RM_VABS 22
203
-#define NEON_2RM_VNEG 23
204
-#define NEON_2RM_VCGT0_F 24
205
-#define NEON_2RM_VCGE0_F 25
206
-#define NEON_2RM_VCEQ0_F 26
207
-#define NEON_2RM_VCLE0_F 27
208
-#define NEON_2RM_VCLT0_F 28
209
-#define NEON_2RM_VABS_F 30
210
-#define NEON_2RM_VNEG_F 31
211
-#define NEON_2RM_VSWP 32
212
-#define NEON_2RM_VTRN 33
213
-#define NEON_2RM_VUZP 34
214
-#define NEON_2RM_VZIP 35
215
-#define NEON_2RM_VMOVN 36 /* Includes VQMOVN, VQMOVUN */
216
-#define NEON_2RM_VQMOVN 37 /* Includes VQMOVUN */
217
-#define NEON_2RM_VSHLL 38
218
-#define NEON_2RM_SHA1SU1 39 /* Includes SHA256SU0 */
219
-#define NEON_2RM_VRINTN 40
220
-#define NEON_2RM_VRINTX 41
221
-#define NEON_2RM_VRINTA 42
222
-#define NEON_2RM_VRINTZ 43
223
-#define NEON_2RM_VCVT_F16_F32 44
224
-#define NEON_2RM_VRINTM 45
225
-#define NEON_2RM_VCVT_F32_F16 46
226
-#define NEON_2RM_VRINTP 47
227
-#define NEON_2RM_VCVTAU 48
228
-#define NEON_2RM_VCVTAS 49
229
-#define NEON_2RM_VCVTNU 50
230
-#define NEON_2RM_VCVTNS 51
231
-#define NEON_2RM_VCVTPU 52
232
-#define NEON_2RM_VCVTPS 53
233
-#define NEON_2RM_VCVTMU 54
234
-#define NEON_2RM_VCVTMS 55
235
-#define NEON_2RM_VRECPE 56
236
-#define NEON_2RM_VRSQRTE 57
237
-#define NEON_2RM_VRECPE_F 58
238
-#define NEON_2RM_VRSQRTE_F 59
239
-#define NEON_2RM_VCVT_FS 60
240
-#define NEON_2RM_VCVT_FU 61
241
-#define NEON_2RM_VCVT_SF 62
242
-#define NEON_2RM_VCVT_UF 63
243
-
244
-/* Each entry in this array has bit n set if the insn allows
245
- * size value n (otherwise it will UNDEF). Since unallocated
246
- * op values will have no bits set they always UNDEF.
247
- */
248
-static const uint8_t neon_2rm_sizes[] = {
249
- [NEON_2RM_VREV64] = 0x7,
250
- [NEON_2RM_VREV32] = 0x3,
251
- [NEON_2RM_VREV16] = 0x1,
252
- [NEON_2RM_VPADDL] = 0x7,
253
- [NEON_2RM_VPADDL_U] = 0x7,
254
- [NEON_2RM_AESE] = 0x1,
255
- [NEON_2RM_AESMC] = 0x1,
256
- [NEON_2RM_VCLS] = 0x7,
257
- [NEON_2RM_VCLZ] = 0x7,
258
- [NEON_2RM_VCNT] = 0x1,
259
- [NEON_2RM_VMVN] = 0x1,
260
- [NEON_2RM_VPADAL] = 0x7,
261
- [NEON_2RM_VPADAL_U] = 0x7,
262
- [NEON_2RM_VQABS] = 0x7,
263
- [NEON_2RM_VQNEG] = 0x7,
264
- [NEON_2RM_VCGT0] = 0x7,
265
- [NEON_2RM_VCGE0] = 0x7,
266
- [NEON_2RM_VCEQ0] = 0x7,
267
- [NEON_2RM_VCLE0] = 0x7,
268
- [NEON_2RM_VCLT0] = 0x7,
269
- [NEON_2RM_SHA1H] = 0x4,
270
- [NEON_2RM_VABS] = 0x7,
271
- [NEON_2RM_VNEG] = 0x7,
272
- [NEON_2RM_VCGT0_F] = 0x4,
273
- [NEON_2RM_VCGE0_F] = 0x4,
274
- [NEON_2RM_VCEQ0_F] = 0x4,
275
- [NEON_2RM_VCLE0_F] = 0x4,
276
- [NEON_2RM_VCLT0_F] = 0x4,
277
- [NEON_2RM_VABS_F] = 0x4,
278
- [NEON_2RM_VNEG_F] = 0x4,
279
- [NEON_2RM_VSWP] = 0x1,
280
- [NEON_2RM_VTRN] = 0x7,
281
- [NEON_2RM_VUZP] = 0x7,
282
- [NEON_2RM_VZIP] = 0x7,
283
- [NEON_2RM_VMOVN] = 0x7,
284
- [NEON_2RM_VQMOVN] = 0x7,
285
- [NEON_2RM_VSHLL] = 0x7,
286
- [NEON_2RM_SHA1SU1] = 0x4,
287
- [NEON_2RM_VRINTN] = 0x4,
288
- [NEON_2RM_VRINTX] = 0x4,
289
- [NEON_2RM_VRINTA] = 0x4,
290
- [NEON_2RM_VRINTZ] = 0x4,
291
- [NEON_2RM_VCVT_F16_F32] = 0x2,
292
- [NEON_2RM_VRINTM] = 0x4,
293
- [NEON_2RM_VCVT_F32_F16] = 0x2,
294
- [NEON_2RM_VRINTP] = 0x4,
295
- [NEON_2RM_VCVTAU] = 0x4,
296
- [NEON_2RM_VCVTAS] = 0x4,
297
- [NEON_2RM_VCVTNU] = 0x4,
298
- [NEON_2RM_VCVTNS] = 0x4,
299
- [NEON_2RM_VCVTPU] = 0x4,
300
- [NEON_2RM_VCVTPS] = 0x4,
301
- [NEON_2RM_VCVTMU] = 0x4,
302
- [NEON_2RM_VCVTMS] = 0x4,
303
- [NEON_2RM_VRECPE] = 0x4,
304
- [NEON_2RM_VRSQRTE] = 0x4,
305
- [NEON_2RM_VRECPE_F] = 0x4,
306
- [NEON_2RM_VRSQRTE_F] = 0x4,
307
- [NEON_2RM_VCVT_FS] = 0x4,
308
- [NEON_2RM_VCVT_FU] = 0x4,
309
- [NEON_2RM_VCVT_SF] = 0x4,
310
- [NEON_2RM_VCVT_UF] = 0x4,
311
-};
312
-
313
static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs,
314
uint32_t opr_sz, uint32_t max_sz,
315
gen_helper_gvec_3_ptr *fn)
316
@@ -XXX,XX +XXX,XX @@ void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
317
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]);
318
}
319
320
-/* Translate a NEON data processing instruction. Return nonzero if the
321
- instruction is invalid.
322
- We process data in a mixture of 32-bit and 64-bit chunks.
323
- Mostly we use 32-bit chunks so we can use normal scalar instructions. */
324
-
325
-static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
326
-{
327
- int op;
328
- int q;
329
- int rd, rm;
330
- int size;
331
- int pass;
332
- int u;
333
- TCGv_i32 tmp, tmp2;
334
-
335
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
336
- return 1;
337
- }
338
-
339
- /* FIXME: this access check should not take precedence over UNDEF
340
- * for invalid encodings; we will generate incorrect syndrome information
341
- * for attempts to execute invalid vfp/neon encodings with FP disabled.
342
- */
343
- if (s->fp_excp_el) {
344
- gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
345
- syn_simd_access_trap(1, 0xe, false), s->fp_excp_el);
346
- return 0;
347
- }
348
-
349
- if (!s->vfp_enabled)
350
- return 1;
351
- q = (insn & (1 << 6)) != 0;
352
- u = (insn >> 24) & 1;
353
- VFP_DREG_D(rd, insn);
354
- VFP_DREG_M(rm, insn);
355
- size = (insn >> 20) & 3;
356
-
357
- if ((insn & (1 << 23)) == 0) {
358
- /* Three register same length: handled by decodetree */
359
- return 1;
360
- } else if (insn & (1 << 4)) {
361
- /* Two registers and shift or reg and imm: handled by decodetree */
362
- return 1;
363
- } else { /* (insn & 0x00800010 == 0x00800000) */
364
- if (size != 3) {
365
- /*
366
- * Three registers of different lengths, or two registers and
367
- * a scalar: handled by decodetree
368
- */
369
- return 1;
370
- } else { /* size == 3 */
371
- if (!u) {
372
- /* Extract: handled by decodetree */
373
- return 1;
374
- } else if ((insn & (1 << 11)) == 0) {
375
- /* Two register misc. */
376
- op = ((insn >> 12) & 0x30) | ((insn >> 7) & 0xf);
377
- size = (insn >> 18) & 3;
378
- /* UNDEF for unknown op values and bad op-size combinations */
379
- if ((neon_2rm_sizes[op] & (1 << size)) == 0) {
380
- return 1;
381
- }
382
- if (q && ((rm | rd) & 1)) {
383
- return 1;
384
- }
385
- switch (op) {
386
- case NEON_2RM_VREV64:
387
- case NEON_2RM_VPADDL: case NEON_2RM_VPADDL_U:
388
- case NEON_2RM_VPADAL: case NEON_2RM_VPADAL_U:
389
- case NEON_2RM_VUZP:
390
- case NEON_2RM_VZIP:
391
- case NEON_2RM_VMOVN: case NEON_2RM_VQMOVN:
392
- case NEON_2RM_VSHLL:
393
- case NEON_2RM_VCVT_F16_F32:
394
- case NEON_2RM_VCVT_F32_F16:
395
- case NEON_2RM_VMVN:
396
- case NEON_2RM_VNEG:
397
- case NEON_2RM_VABS:
398
- case NEON_2RM_VCEQ0:
399
- case NEON_2RM_VCGT0:
400
- case NEON_2RM_VCLE0:
401
- case NEON_2RM_VCGE0:
402
- case NEON_2RM_VCLT0:
403
- case NEON_2RM_AESE: case NEON_2RM_AESMC:
404
- case NEON_2RM_SHA1H:
405
- case NEON_2RM_SHA1SU1:
406
- case NEON_2RM_VREV32:
407
- case NEON_2RM_VREV16:
408
- case NEON_2RM_VCLS:
409
- case NEON_2RM_VCLZ:
410
- case NEON_2RM_VCNT:
411
- case NEON_2RM_VABS_F:
412
- case NEON_2RM_VNEG_F:
413
- case NEON_2RM_VRECPE:
414
- case NEON_2RM_VRSQRTE:
415
- case NEON_2RM_VQABS:
416
- case NEON_2RM_VQNEG:
417
- case NEON_2RM_VRECPE_F:
418
- case NEON_2RM_VRSQRTE_F:
419
- case NEON_2RM_VCVT_FS:
420
- case NEON_2RM_VCVT_FU:
421
- case NEON_2RM_VCVT_SF:
422
- case NEON_2RM_VCVT_UF:
423
- case NEON_2RM_VRINTX:
424
- case NEON_2RM_VCGT0_F:
425
- case NEON_2RM_VCGE0_F:
426
- case NEON_2RM_VCEQ0_F:
427
- case NEON_2RM_VCLE0_F:
428
- case NEON_2RM_VCLT0_F:
429
- case NEON_2RM_VRINTN:
430
- case NEON_2RM_VRINTA:
431
- case NEON_2RM_VRINTM:
432
- case NEON_2RM_VRINTP:
433
- case NEON_2RM_VRINTZ:
434
- case NEON_2RM_VCVTAU:
435
- case NEON_2RM_VCVTAS:
436
- case NEON_2RM_VCVTNU:
437
- case NEON_2RM_VCVTNS:
438
- case NEON_2RM_VCVTPU:
439
- case NEON_2RM_VCVTPS:
440
- case NEON_2RM_VCVTMU:
441
- case NEON_2RM_VCVTMS:
442
- case NEON_2RM_VSWP:
443
- /* handled by decodetree */
444
- return 1;
445
- case NEON_2RM_VTRN:
446
- if (size == 2) {
447
- int n;
448
- for (n = 0; n < (q ? 4 : 2); n += 2) {
449
- tmp = neon_load_reg(rm, n);
450
- tmp2 = neon_load_reg(rd, n + 1);
451
- neon_store_reg(rm, n, tmp2);
452
- neon_store_reg(rd, n + 1, tmp);
453
- }
454
- } else {
455
- goto elementwise;
456
- }
457
- break;
458
-
459
- default:
460
- elementwise:
461
- for (pass = 0; pass < (q ? 4 : 2); pass++) {
462
- tmp = neon_load_reg(rm, pass);
463
- switch (op) {
464
- case NEON_2RM_VTRN:
465
- tmp2 = neon_load_reg(rd, pass);
466
- switch (size) {
467
- case 0: gen_neon_trn_u8(tmp, tmp2); break;
468
- case 1: gen_neon_trn_u16(tmp, tmp2); break;
469
- default: abort();
470
- }
471
- neon_store_reg(rm, pass, tmp2);
472
- break;
473
- default:
474
- /* Reserved op values were caught by the
475
- * neon_2rm_sizes[] check earlier.
476
- */
477
- abort();
478
- }
479
- neon_store_reg(rd, pass, tmp);
480
- }
481
- break;
482
- }
483
- } else {
484
- /* VTBL, VTBX, VDUP: handled by decodetree */
485
- return 1;
486
- }
487
- }
488
- }
489
- return 0;
490
-}
491
-
492
static int disas_coproc_insn(DisasContext *s, uint32_t insn)
493
{
494
int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2;
495
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
496
}
497
/* fall back to legacy decoder */
498
499
- if (((insn >> 25) & 7) == 1) {
500
- /* NEON Data processing. */
501
- if (disas_neon_data_insn(s, insn)) {
502
- goto illegal_op;
503
- }
504
- return;
505
- }
506
if ((insn & 0x0e000f00) == 0x0c000100) {
507
if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) {
508
/* iWMMXt register transfer. */
509
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
510
break;
511
}
512
if (((insn >> 24) & 3) == 3) {
513
- /* Translate into the equivalent ARM encoding. */
514
- insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28);
515
- if (disas_neon_data_insn(s, insn)) {
516
- goto illegal_op;
517
- }
518
+ /* Neon DP, but failed disas_neon_dp() */
519
+ goto illegal_op;
520
} else if (((insn >> 8) & 0xe) == 10) {
521
/* VFP, but failed disas_vfp. */
522
goto illegal_op;
523
--
524
2.20.1
525
526
diff view generated by jsdifflib
Deleted patch
1
The functions neon_element_offset(), neon_load_element(),
2
neon_load_element64(), neon_store_element() and
3
neon_store_element64() are used only in the translate-neon.inc.c
4
file, so move their definitions there.
5
1
6
Since the .inc.c file is #included in translate.c this doesn't make
7
much difference currently, but it's a more logical place to put the
8
functions and it might be helpful if we ever decide to try to make
9
the .inc.c files genuinely separate compilation units.
10
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
13
Message-id: 20200616170844.13318-22-peter.maydell@linaro.org
14
---
15
target/arm/translate-neon.inc.c | 101 ++++++++++++++++++++++++++++++++
16
target/arm/translate.c | 101 --------------------------------
17
2 files changed, 101 insertions(+), 101 deletions(-)
18
19
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
20
index XXXXXXX..XXXXXXX 100644
21
--- a/target/arm/translate-neon.inc.c
22
+++ b/target/arm/translate-neon.inc.c
23
@@ -XXX,XX +XXX,XX @@ static inline int rsub_8(DisasContext *s, int x)
24
#include "decode-neon-ls.inc.c"
25
#include "decode-neon-shared.inc.c"
26
27
+/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
28
+ * where 0 is the least significant end of the register.
29
+ */
30
+static inline long
31
+neon_element_offset(int reg, int element, MemOp size)
32
+{
33
+ int element_size = 1 << size;
34
+ int ofs = element * element_size;
35
+#ifdef HOST_WORDS_BIGENDIAN
36
+ /* Calculate the offset assuming fully little-endian,
37
+ * then XOR to account for the order of the 8-byte units.
38
+ */
39
+ if (element_size < 8) {
40
+ ofs ^= 8 - element_size;
41
+ }
42
+#endif
43
+ return neon_reg_offset(reg, 0) + ofs;
44
+}
45
+
46
+static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
47
+{
48
+ long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
49
+
50
+ switch (mop) {
51
+ case MO_UB:
52
+ tcg_gen_ld8u_i32(var, cpu_env, offset);
53
+ break;
54
+ case MO_UW:
55
+ tcg_gen_ld16u_i32(var, cpu_env, offset);
56
+ break;
57
+ case MO_UL:
58
+ tcg_gen_ld_i32(var, cpu_env, offset);
59
+ break;
60
+ default:
61
+ g_assert_not_reached();
62
+ }
63
+}
64
+
65
+static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
66
+{
67
+ long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
68
+
69
+ switch (mop) {
70
+ case MO_UB:
71
+ tcg_gen_ld8u_i64(var, cpu_env, offset);
72
+ break;
73
+ case MO_UW:
74
+ tcg_gen_ld16u_i64(var, cpu_env, offset);
75
+ break;
76
+ case MO_UL:
77
+ tcg_gen_ld32u_i64(var, cpu_env, offset);
78
+ break;
79
+ case MO_Q:
80
+ tcg_gen_ld_i64(var, cpu_env, offset);
81
+ break;
82
+ default:
83
+ g_assert_not_reached();
84
+ }
85
+}
86
+
87
+static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
88
+{
89
+ long offset = neon_element_offset(reg, ele, size);
90
+
91
+ switch (size) {
92
+ case MO_8:
93
+ tcg_gen_st8_i32(var, cpu_env, offset);
94
+ break;
95
+ case MO_16:
96
+ tcg_gen_st16_i32(var, cpu_env, offset);
97
+ break;
98
+ case MO_32:
99
+ tcg_gen_st_i32(var, cpu_env, offset);
100
+ break;
101
+ default:
102
+ g_assert_not_reached();
103
+ }
104
+}
105
+
106
+static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
107
+{
108
+ long offset = neon_element_offset(reg, ele, size);
109
+
110
+ switch (size) {
111
+ case MO_8:
112
+ tcg_gen_st8_i64(var, cpu_env, offset);
113
+ break;
114
+ case MO_16:
115
+ tcg_gen_st16_i64(var, cpu_env, offset);
116
+ break;
117
+ case MO_32:
118
+ tcg_gen_st32_i64(var, cpu_env, offset);
119
+ break;
120
+ case MO_64:
121
+ tcg_gen_st_i64(var, cpu_env, offset);
122
+ break;
123
+ default:
124
+ g_assert_not_reached();
125
+ }
126
+}
127
+
128
static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
129
{
130
int opr_sz;
131
diff --git a/target/arm/translate.c b/target/arm/translate.c
132
index XXXXXXX..XXXXXXX 100644
133
--- a/target/arm/translate.c
134
+++ b/target/arm/translate.c
135
@@ -XXX,XX +XXX,XX @@ neon_reg_offset (int reg, int n)
136
return vfp_reg_offset(0, sreg);
137
}
138
139
-/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE,
140
- * where 0 is the least significant end of the register.
141
- */
142
-static inline long
143
-neon_element_offset(int reg, int element, MemOp size)
144
-{
145
- int element_size = 1 << size;
146
- int ofs = element * element_size;
147
-#ifdef HOST_WORDS_BIGENDIAN
148
- /* Calculate the offset assuming fully little-endian,
149
- * then XOR to account for the order of the 8-byte units.
150
- */
151
- if (element_size < 8) {
152
- ofs ^= 8 - element_size;
153
- }
154
-#endif
155
- return neon_reg_offset(reg, 0) + ofs;
156
-}
157
-
158
static TCGv_i32 neon_load_reg(int reg, int pass)
159
{
160
TCGv_i32 tmp = tcg_temp_new_i32();
161
@@ -XXX,XX +XXX,XX @@ static TCGv_i32 neon_load_reg(int reg, int pass)
162
return tmp;
163
}
164
165
-static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop)
166
-{
167
- long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
168
-
169
- switch (mop) {
170
- case MO_UB:
171
- tcg_gen_ld8u_i32(var, cpu_env, offset);
172
- break;
173
- case MO_UW:
174
- tcg_gen_ld16u_i32(var, cpu_env, offset);
175
- break;
176
- case MO_UL:
177
- tcg_gen_ld_i32(var, cpu_env, offset);
178
- break;
179
- default:
180
- g_assert_not_reached();
181
- }
182
-}
183
-
184
-static void neon_load_element64(TCGv_i64 var, int reg, int ele, MemOp mop)
185
-{
186
- long offset = neon_element_offset(reg, ele, mop & MO_SIZE);
187
-
188
- switch (mop) {
189
- case MO_UB:
190
- tcg_gen_ld8u_i64(var, cpu_env, offset);
191
- break;
192
- case MO_UW:
193
- tcg_gen_ld16u_i64(var, cpu_env, offset);
194
- break;
195
- case MO_UL:
196
- tcg_gen_ld32u_i64(var, cpu_env, offset);
197
- break;
198
- case MO_Q:
199
- tcg_gen_ld_i64(var, cpu_env, offset);
200
- break;
201
- default:
202
- g_assert_not_reached();
203
- }
204
-}
205
-
206
static void neon_store_reg(int reg, int pass, TCGv_i32 var)
207
{
208
tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass));
209
tcg_temp_free_i32(var);
210
}
211
212
-static void neon_store_element(int reg, int ele, MemOp size, TCGv_i32 var)
213
-{
214
- long offset = neon_element_offset(reg, ele, size);
215
-
216
- switch (size) {
217
- case MO_8:
218
- tcg_gen_st8_i32(var, cpu_env, offset);
219
- break;
220
- case MO_16:
221
- tcg_gen_st16_i32(var, cpu_env, offset);
222
- break;
223
- case MO_32:
224
- tcg_gen_st_i32(var, cpu_env, offset);
225
- break;
226
- default:
227
- g_assert_not_reached();
228
- }
229
-}
230
-
231
-static void neon_store_element64(int reg, int ele, MemOp size, TCGv_i64 var)
232
-{
233
- long offset = neon_element_offset(reg, ele, size);
234
-
235
- switch (size) {
236
- case MO_8:
237
- tcg_gen_st8_i64(var, cpu_env, offset);
238
- break;
239
- case MO_16:
240
- tcg_gen_st16_i64(var, cpu_env, offset);
241
- break;
242
- case MO_32:
243
- tcg_gen_st32_i64(var, cpu_env, offset);
244
- break;
245
- case MO_64:
246
- tcg_gen_st_i64(var, cpu_env, offset);
247
- break;
248
- default:
249
- g_assert_not_reached();
250
- }
251
-}
252
-
253
static inline void neon_load_reg64(TCGv_i64 var, int reg)
254
{
255
tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg));
256
--
257
2.20.1
258
259
diff view generated by jsdifflib
Deleted patch
1
Since commit ba3e7926691ed3 it has been unnecessary for target code
2
to call gen_io_end() after an IO instruction in icount mode; it is
3
sufficient to call gen_io_start() before it and to force the end of
4
the TB.
5
1
6
Many now-unnecessary calls to gen_io_end() were removed in commit
7
9e9b10c6491153b, but some were missed or accidentally added later.
8
Remove unneeded calls from the arm target:
9
10
* the call in the handling of exception-return-via-LDM is
11
unnecessary, and the code is already forcing end-of-TB
12
* the call in the VFP access check code is more complicated:
13
we weren't ending the TB, so we need to add the code to
14
force that by setting DISAS_UPDATE
15
* the doc comment for ARM_CP_IO doesn't need to mention
16
gen_io_end() any more
17
18
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
19
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
20
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
21
Reviewed-by: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru>
22
Message-id: 20200619170324.12093-1-peter.maydell@linaro.org
23
---
24
target/arm/cpu.h | 2 +-
25
target/arm/translate-vfp.inc.c | 7 +++----
26
target/arm/translate.c | 3 ---
27
3 files changed, 4 insertions(+), 8 deletions(-)
28
29
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
30
index XXXXXXX..XXXXXXX 100644
31
--- a/target/arm/cpu.h
32
+++ b/target/arm/cpu.h
33
@@ -XXX,XX +XXX,XX @@ static inline uint64_t cpreg_to_kvm_id(uint32_t cpregid)
34
* migration or KVM state synchronization. (Typically this is for "registers"
35
* which are actually used as instructions for cache maintenance and so on.)
36
* IO indicates that this register does I/O and therefore its accesses
37
- * need to be surrounded by gen_io_start()/gen_io_end(). In particular,
38
+ * need to be marked with gen_io_start() and also end the TB. In particular,
39
* registers which implement clocks or timers require this.
40
* RAISES_EXC is for when the read or write hook might raise an exception;
41
* the generated code will synchronize the CPU state before calling the hook
42
diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
43
index XXXXXXX..XXXXXXX 100644
44
--- a/target/arm/translate-vfp.inc.c
45
+++ b/target/arm/translate-vfp.inc.c
46
@@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled)
47
if (s->v7m_lspact) {
48
/*
49
* Lazy state saving affects external memory and also the NVIC,
50
- * so we must mark it as an IO operation for icount.
51
+ * so we must mark it as an IO operation for icount (and cause
52
+ * this to be the last insn in the TB).
53
*/
54
if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
55
+ s->base.is_jmp = DISAS_UPDATE;
56
gen_io_start();
57
}
58
gen_helper_v7m_preserve_fp_state(cpu_env);
59
- if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
60
- gen_io_end();
61
- }
62
/*
63
* If the preserve_fp_state helper doesn't throw an exception
64
* then it will clear LSPACT; we don't need to repeat this for
65
diff --git a/target/arm/translate.c b/target/arm/translate.c
66
index XXXXXXX..XXXXXXX 100644
67
--- a/target/arm/translate.c
68
+++ b/target/arm/translate.c
69
@@ -XXX,XX +XXX,XX @@ static bool do_ldm(DisasContext *s, arg_ldst_block *a, int min_n)
70
gen_io_start();
71
}
72
gen_helper_cpsr_write_eret(cpu_env, tmp);
73
- if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
74
- gen_io_end();
75
- }
76
tcg_temp_free_i32(tmp);
77
/* Must exit loop to check un-masked IRQs */
78
s->base.is_jmp = DISAS_EXIT;
79
--
80
2.20.1
81
82
diff view generated by jsdifflib
Deleted patch
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
1
3
Add a trace event to see when a guest disable/enable the watchdog.
4
5
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
6
Message-id: 20200617072539.32686-2-f4bug@amsat.org
7
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
---
10
hw/watchdog/cmsdk-apb-watchdog.c | 1 +
11
hw/watchdog/trace-events | 1 +
12
2 files changed, 2 insertions(+)
13
14
diff --git a/hw/watchdog/cmsdk-apb-watchdog.c b/hw/watchdog/cmsdk-apb-watchdog.c
15
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/watchdog/cmsdk-apb-watchdog.c
17
+++ b/hw/watchdog/cmsdk-apb-watchdog.c
18
@@ -XXX,XX +XXX,XX @@ static void cmsdk_apb_watchdog_write(void *opaque, hwaddr offset,
19
break;
20
case A_WDOGLOCK:
21
s->lock = (value != WDOG_UNLOCK_VALUE);
22
+ trace_cmsdk_apb_watchdog_lock(s->lock);
23
break;
24
case A_WDOGITCR:
25
if (s->is_luminary) {
26
diff --git a/hw/watchdog/trace-events b/hw/watchdog/trace-events
27
index XXXXXXX..XXXXXXX 100644
28
--- a/hw/watchdog/trace-events
29
+++ b/hw/watchdog/trace-events
30
@@ -XXX,XX +XXX,XX @@
31
cmsdk_apb_watchdog_read(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u"
32
cmsdk_apb_watchdog_write(uint64_t offset, uint64_t data, unsigned size) "CMSDK APB watchdog write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u"
33
cmsdk_apb_watchdog_reset(void) "CMSDK APB watchdog: reset"
34
+cmsdk_apb_watchdog_lock(uint32_t lock) "CMSDK APB watchdog: lock %" PRIu32
35
--
36
2.20.1
37
38
diff view generated by jsdifflib
Deleted patch
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
1
3
Use self-explicit definitions instead of magic values.
4
5
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
6
Message-id: 20200617072539.32686-3-f4bug@amsat.org
7
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
---
10
hw/i2c/versatile_i2c.c | 14 ++++++++++----
11
1 file changed, 10 insertions(+), 4 deletions(-)
12
13
diff --git a/hw/i2c/versatile_i2c.c b/hw/i2c/versatile_i2c.c
14
index XXXXXXX..XXXXXXX 100644
15
--- a/hw/i2c/versatile_i2c.c
16
+++ b/hw/i2c/versatile_i2c.c
17
@@ -XXX,XX +XXX,XX @@
18
#include "qemu/osdep.h"
19
#include "hw/sysbus.h"
20
#include "hw/i2c/bitbang_i2c.h"
21
+#include "hw/registerfields.h"
22
#include "qemu/log.h"
23
#include "qemu/module.h"
24
25
@@ -XXX,XX +XXX,XX @@ typedef struct VersatileI2CState {
26
int in;
27
} VersatileI2CState;
28
29
+REG32(CONTROL_GET, 0)
30
+REG32(CONTROL_SET, 0)
31
+REG32(CONTROL_CLR, 4)
32
+
33
static uint64_t versatile_i2c_read(void *opaque, hwaddr offset,
34
unsigned size)
35
{
36
VersatileI2CState *s = (VersatileI2CState *)opaque;
37
38
- if (offset == 0) {
39
+ switch (offset) {
40
+ case A_CONTROL_SET:
41
return (s->out & 1) | (s->in << 1);
42
- } else {
43
+ default:
44
qemu_log_mask(LOG_GUEST_ERROR,
45
"%s: Bad offset 0x%x\n", __func__, (int)offset);
46
return -1;
47
@@ -XXX,XX +XXX,XX @@ static void versatile_i2c_write(void *opaque, hwaddr offset,
48
VersatileI2CState *s = (VersatileI2CState *)opaque;
49
50
switch (offset) {
51
- case 0:
52
+ case A_CONTROL_SET:
53
s->out |= value & 3;
54
break;
55
- case 4:
56
+ case A_CONTROL_CLR:
57
s->out &= ~value;
58
break;
59
default:
60
--
61
2.20.1
62
63
diff view generated by jsdifflib
Deleted patch
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
1
3
To differenciate with the CMSDK APB peripheral region,
4
rename this region 'CMSDK AHB peripheral region'.
5
6
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
7
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
8
Message-id: 20200617072539.32686-8-f4bug@amsat.org
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
11
hw/arm/mps2.c | 3 ++-
12
1 file changed, 2 insertions(+), 1 deletion(-)
13
14
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
15
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/arm/mps2.c
17
+++ b/hw/arm/mps2.c
18
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
19
*/
20
create_unimplemented_device("CMSDK APB peripheral region @0x40000000",
21
0x40000000, 0x00010000);
22
- create_unimplemented_device("CMSDK peripheral region @0x40010000",
23
+ create_unimplemented_device("CMSDK AHB peripheral region @0x40010000",
24
0x40010000, 0x00010000);
25
create_unimplemented_device("Extra peripheral region @0x40020000",
26
0x40020000, 0x00010000);
27
+
28
create_unimplemented_device("RESERVED 4", 0x40030000, 0x001D0000);
29
create_unimplemented_device("VGA", 0x41000000, 0x0200000);
30
31
--
32
2.20.1
33
34
diff view generated by jsdifflib
Deleted patch
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
1
3
Register the GPIO peripherals as unimplemented to better
4
follow their accesses, for example booting Zephyr:
5
6
----------------
7
IN: arm_mps2_pinmux_init
8
0x00001160: f64f 0231 movw r2, #0xf831
9
0x00001164: 4b06 ldr r3, [pc, #0x18]
10
0x00001166: 2000 movs r0, #0
11
0x00001168: 619a str r2, [r3, #0x18]
12
0x0000116a: f24c 426f movw r2, #0xc46f
13
0x0000116e: f503 5380 add.w r3, r3, #0x1000
14
0x00001172: 619a str r2, [r3, #0x18]
15
0x00001174: f44f 529e mov.w r2, #0x13c0
16
0x00001178: f503 5380 add.w r3, r3, #0x1000
17
0x0000117c: 619a str r2, [r3, #0x18]
18
0x0000117e: 4770 bx lr
19
cmsdk-ahb-gpio: unimplemented device write (size 4, value 0xf831, offset 0x18)
20
cmsdk-ahb-gpio: unimplemented device write (size 4, value 0xc46f, offset 0x18)
21
cmsdk-ahb-gpio: unimplemented device write (size 4, value 0x13c0, offset 0x18)
22
23
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
24
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
25
Message-id: 20200617072539.32686-10-f4bug@amsat.org
26
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
27
---
28
hw/arm/mps2.c | 8 ++++++--
29
1 file changed, 6 insertions(+), 2 deletions(-)
30
31
diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c
32
index XXXXXXX..XXXXXXX 100644
33
--- a/hw/arm/mps2.c
34
+++ b/hw/arm/mps2.c
35
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
36
MemoryRegion *system_memory = get_system_memory();
37
MachineClass *mc = MACHINE_GET_CLASS(machine);
38
DeviceState *armv7m, *sccdev;
39
+ int i;
40
41
if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) {
42
error_report("This board can only be used with CPU %s",
43
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
44
*/
45
Object *orgate;
46
DeviceState *orgate_dev;
47
- int i;
48
49
orgate = object_new(TYPE_OR_IRQ);
50
object_property_set_int(orgate, 6, "num-lines", &error_fatal);
51
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
52
*/
53
Object *orgate;
54
DeviceState *orgate_dev;
55
- int i;
56
57
orgate = object_new(TYPE_OR_IRQ);
58
object_property_set_int(orgate, 10, "num-lines", &error_fatal);
59
@@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine)
60
default:
61
g_assert_not_reached();
62
}
63
+ for (i = 0; i < 4; i++) {
64
+ static const hwaddr gpiobase[] = {0x40010000, 0x40011000,
65
+ 0x40012000, 0x40013000};
66
+ create_unimplemented_device("cmsdk-ahb-gpio", gpiobase[i], 0x1000);
67
+ }
68
69
/* CMSDK APB subsystem */
70
cmsdk_apb_timer_create(0x40000000, qdev_get_gpio_in(armv7m, 8), SYSCLK_FRQ);
71
--
72
2.20.1
73
74
diff view generated by jsdifflib