1
target-arm queue:
1
The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df:
2
* mostly my latest v8M stuff, plus a couple of minor patches
3
2
4
The following changes since commit a0b261db8c030813e30a39eae47359ac2a37f7e2:
3
Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100)
5
4
6
Merge remote-tracking branch 'remotes/ehabkost/tags/python-next-pull-request' into staging (2017-10-12 10:02:09 +0100)
5
are available in the Git repository at:
7
6
8
are available in the git repository at:
7
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702
9
8
10
git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20171012
9
for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8:
11
10
12
for you to fetch changes up to cf5f7937b05c84d5565134f058c00cd48304a117:
11
target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100)
13
14
nvic: Fix miscalculation of offsets into ITNS array (2017-10-12 16:33:16 +0100)
15
12
16
----------------------------------------------------------------
13
----------------------------------------------------------------
17
target-arm queue:
14
target-arm queue:
18
* v8M: SG, BLXNS, secure-return
15
* more MVE instructions
19
* v8M: fixes for coverity issues in previous patches
16
* hw/gpio/gpio_pwr: use shutdown function for reboot
20
* arm: fix armv7m_init() declaration to match definition
17
* target/arm: Check NaN mode before silencing NaN
21
* watchdog/aspeed: fix variable type to store reload value
18
* tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine
19
* hw/arm: Add basic power management to raspi.
20
* docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc
22
21
23
----------------------------------------------------------------
22
----------------------------------------------------------------
24
Cédric Le Goater (1):
23
Joe Komlodi (1):
25
watchdog/aspeed: fix variable type to store reload value
24
target/arm: Check NaN mode before silencing NaN
26
25
27
Igor Mammedov (1):
26
Maxim Uvarov (1):
28
arm: fix armv7m_init() declaration to match definition
27
hw/gpio/gpio_pwr: use shutdown function for reboot
29
28
30
Peter Maydell (11):
29
Nolan Leake (1):
31
target/arm: Add M profile secure MMU index values to get_a32_user_mem_index()
30
hw/arm: Add basic power management to raspi.
32
target/arm: Implement SG instruction
33
target/arm: Implement BLXNS
34
target/arm: Implement secure function return
35
target-arm: Don't check for "Thumb2 or M profile" for not-Thumb1
36
target/arm: Pull Thumb insn word loads up to top level
37
target-arm: Simplify insn_crosses_page()
38
target/arm: Support some Thumb insns being always unconditional
39
target/arm: Implement SG instruction corner cases
40
nvic: Add missing 'break'
41
nvic: Fix miscalculation of offsets into ITNS array
42
31
43
include/hw/arm/arm.h | 2 +-
32
Patrick Venture (2):
44
target/arm/helper.h | 1 +
33
docs/system/arm: Add quanta-q7l1-bmc reference
45
target/arm/internals.h | 8 ++
34
docs/system/arm: Add quanta-gbs-bmc reference
46
hw/intc/armv7m_nvic.c | 5 +-
47
hw/watchdog/wdt_aspeed.c | 4 +-
48
target/arm/helper.c | 306 ++++++++++++++++++++++++++++++++++++++++++++--
49
target/arm/translate.c | 310 ++++++++++++++++++++++++++++++++---------------
50
7 files changed, 521 insertions(+), 115 deletions(-)
51
35
36
Peter Maydell (18):
37
target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation
38
target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH
39
target/arm: Make asimd_imm_const() public
40
target/arm: Use asimd_imm_const for A64 decode
41
target/arm: Use dup_const() instead of bitfield_replicate()
42
target/arm: Implement MVE logical immediate insns
43
target/arm: Implement MVE vector shift left by immediate insns
44
target/arm: Implement MVE vector shift right by immediate insns
45
target/arm: Implement MVE VSHLL
46
target/arm: Implement MVE VSRI, VSLI
47
target/arm: Implement MVE VSHRN, VRSHRN
48
target/arm: Implement MVE saturating narrowing shifts
49
target/arm: Implement MVE VSHLC
50
target/arm: Implement MVE VADDLV
51
target/arm: Implement MVE long shifts by immediate
52
target/arm: Implement MVE long shifts by register
53
target/arm: Implement MVE shifts by immediate
54
target/arm: Implement MVE shifts by register
55
56
Philippe Mathieu-Daudé (1):
57
tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine
58
59
docs/system/arm/aspeed.rst | 1 +
60
docs/system/arm/nuvoton.rst | 5 +-
61
include/hw/arm/bcm2835_peripherals.h | 3 +-
62
include/hw/misc/bcm2835_powermgt.h | 29 ++
63
target/arm/helper-mve.h | 108 +++++++
64
target/arm/translate.h | 41 +++
65
target/arm/mve.decode | 177 ++++++++++-
66
target/arm/t32.decode | 71 ++++-
67
hw/arm/bcm2835_peripherals.c | 13 +-
68
hw/gpio/gpio_pwr.c | 2 +-
69
hw/misc/bcm2835_powermgt.c | 160 ++++++++++
70
target/arm/helper-a64.c | 12 +-
71
target/arm/mve_helper.c | 524 +++++++++++++++++++++++++++++++--
72
target/arm/translate-a64.c | 86 +-----
73
target/arm/translate-mve.c | 261 +++++++++++++++-
74
target/arm/translate-neon.c | 81 -----
75
target/arm/translate.c | 327 +++++++++++++++++++-
76
target/arm/vfp_helper.c | 24 +-
77
hw/misc/meson.build | 1 +
78
tests/acceptance/boot_linux_console.py | 43 +++
79
20 files changed, 1760 insertions(+), 209 deletions(-)
80
create mode 100644 include/hw/misc/bcm2835_powermgt.h
81
create mode 100644 hw/misc/bcm2835_powermgt.c
82
diff view generated by jsdifflib
New patch
1
From: Patrick Venture <venture@google.com>
1
2
3
Adds a line-item reference to the supported quanta-q71l-bmc aspeed
4
entry.
5
6
Signed-off-by: Patrick Venture <venture@google.com>
7
Reviewed-by: Cédric Le Goater <clg@kaod.org>
8
Message-id: 20210615192848.1065297-2-venture@google.com
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
11
docs/system/arm/aspeed.rst | 1 +
12
1 file changed, 1 insertion(+)
13
14
diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst
15
index XXXXXXX..XXXXXXX 100644
16
--- a/docs/system/arm/aspeed.rst
17
+++ b/docs/system/arm/aspeed.rst
18
@@ -XXX,XX +XXX,XX @@ etc.
19
AST2400 SoC based machines :
20
21
- ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC
22
+- ``quanta-q71l-bmc`` OpenBMC Quanta BMC
23
24
AST2500 SoC based machines :
25
26
--
27
2.20.1
28
29
diff view generated by jsdifflib
New patch
1
From: Patrick Venture <venture@google.com>
1
2
3
Add line item reference to quanta-gbs-bmc machine.
4
5
Signed-off-by: Patrick Venture <venture@google.com>
6
Reviewed-by: Cédric Le Goater <clg@kaod.org>
7
Message-id: 20210615192848.1065297-3-venture@google.com
8
[PMM: fixed underline Sphinx warning]
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
11
docs/system/arm/nuvoton.rst | 5 +++--
12
1 file changed, 3 insertions(+), 2 deletions(-)
13
14
diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst
15
index XXXXXXX..XXXXXXX 100644
16
--- a/docs/system/arm/nuvoton.rst
17
+++ b/docs/system/arm/nuvoton.rst
18
@@ -XXX,XX +XXX,XX @@
19
-Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``)
20
-=====================================================
21
+Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``)
22
+================================================================
23
24
The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are
25
designed to be used as Baseboard Management Controllers (BMCs) in various
26
@@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip :
27
The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and
28
Hyperscale applications. The following machines are based on this chip :
29
30
+- ``quanta-gbs-bmc`` Quanta GBS server BMC
31
- ``quanta-gsj`` Quanta GSJ server BMC
32
33
There are also two more SoCs, NPCM710 and NPCM705, which are single-core
34
--
35
2.20.1
36
37
diff view generated by jsdifflib
New patch
1
1
From: Nolan Leake <nolan@sigbus.net>
2
3
This is just enough to make reboot and poweroff work. Works for
4
linux, u-boot, and the arm trusted firmware. Not tested, but should
5
work for plan9, and bare-metal/hobby OSes, since they seem to generally
6
do what linux does for reset.
7
8
The watchdog timer functionality is not yet implemented.
9
10
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64
11
Signed-off-by: Nolan Leake <nolan@sigbus.net>
12
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
13
Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
14
Message-id: 20210625210209.1870217-1-nolan@sigbus.net
15
[PMM: tweaked commit title; fixed region size to 0x200;
16
moved header file to include/]
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
18
---
19
include/hw/arm/bcm2835_peripherals.h | 3 +-
20
include/hw/misc/bcm2835_powermgt.h | 29 +++++
21
hw/arm/bcm2835_peripherals.c | 13 ++-
22
hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++
23
hw/misc/meson.build | 1 +
24
5 files changed, 204 insertions(+), 2 deletions(-)
25
create mode 100644 include/hw/misc/bcm2835_powermgt.h
26
create mode 100644 hw/misc/bcm2835_powermgt.c
27
28
diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h
29
index XXXXXXX..XXXXXXX 100644
30
--- a/include/hw/arm/bcm2835_peripherals.h
31
+++ b/include/hw/arm/bcm2835_peripherals.h
32
@@ -XXX,XX +XXX,XX @@
33
#include "hw/misc/bcm2835_mphi.h"
34
#include "hw/misc/bcm2835_thermal.h"
35
#include "hw/misc/bcm2835_cprman.h"
36
+#include "hw/misc/bcm2835_powermgt.h"
37
#include "hw/sd/sdhci.h"
38
#include "hw/sd/bcm2835_sdhost.h"
39
#include "hw/gpio/bcm2835_gpio.h"
40
@@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState {
41
BCM2835MphiState mphi;
42
UnimplementedDeviceState txp;
43
UnimplementedDeviceState armtmr;
44
- UnimplementedDeviceState powermgt;
45
+ BCM2835PowerMgtState powermgt;
46
BCM2835CprmanState cprman;
47
PL011State uart0;
48
BCM2835AuxState aux;
49
diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h
50
new file mode 100644
51
index XXXXXXX..XXXXXXX
52
--- /dev/null
53
+++ b/include/hw/misc/bcm2835_powermgt.h
54
@@ -XXX,XX +XXX,XX @@
55
+/*
56
+ * BCM2835 Power Management emulation
57
+ *
58
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
59
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
60
+ *
61
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
62
+ * See the COPYING file in the top-level directory.
63
+ */
64
+
65
+#ifndef BCM2835_POWERMGT_H
66
+#define BCM2835_POWERMGT_H
67
+
68
+#include "hw/sysbus.h"
69
+#include "qom/object.h"
70
+
71
+#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt"
72
+OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT)
73
+
74
+struct BCM2835PowerMgtState {
75
+ SysBusDevice busdev;
76
+ MemoryRegion iomem;
77
+
78
+ uint32_t rstc;
79
+ uint32_t rsts;
80
+ uint32_t wdog;
81
+};
82
+
83
+#endif
84
diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c
85
index XXXXXXX..XXXXXXX 100644
86
--- a/hw/arm/bcm2835_peripherals.c
87
+++ b/hw/arm/bcm2835_peripherals.c
88
@@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj)
89
90
object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr",
91
OBJECT(&s->gpu_bus_mr));
92
+
93
+ /* Power Management */
94
+ object_initialize_child(obj, "powermgt", &s->powermgt,
95
+ TYPE_BCM2835_POWERMGT);
96
}
97
98
static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
99
@@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
100
qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
101
INTERRUPT_USB));
102
103
+ /* Power Management */
104
+ if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) {
105
+ return;
106
+ }
107
+
108
+ memory_region_add_subregion(&s->peri_mr, PM_OFFSET,
109
+ sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0));
110
+
111
create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000);
112
create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40);
113
- create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114);
114
create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100);
115
create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100);
116
create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20);
117
diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c
118
new file mode 100644
119
index XXXXXXX..XXXXXXX
120
--- /dev/null
121
+++ b/hw/misc/bcm2835_powermgt.c
122
@@ -XXX,XX +XXX,XX @@
123
+/*
124
+ * BCM2835 Power Management emulation
125
+ *
126
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
127
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
128
+ *
129
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
130
+ * See the COPYING file in the top-level directory.
131
+ */
132
+
133
+#include "qemu/osdep.h"
134
+#include "qemu/log.h"
135
+#include "qemu/module.h"
136
+#include "hw/misc/bcm2835_powermgt.h"
137
+#include "migration/vmstate.h"
138
+#include "sysemu/runstate.h"
139
+
140
+#define PASSWORD 0x5a000000
141
+#define PASSWORD_MASK 0xff000000
142
+
143
+#define R_RSTC 0x1c
144
+#define V_RSTC_RESET 0x20
145
+#define R_RSTS 0x20
146
+#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */
147
+#define R_WDOG 0x24
148
+
149
+static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset,
150
+ unsigned size)
151
+{
152
+ BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque;
153
+ uint32_t res = 0;
154
+
155
+ switch (offset) {
156
+ case R_RSTC:
157
+ res = s->rstc;
158
+ break;
159
+ case R_RSTS:
160
+ res = s->rsts;
161
+ break;
162
+ case R_WDOG:
163
+ res = s->wdog;
164
+ break;
165
+
166
+ default:
167
+ qemu_log_mask(LOG_UNIMP,
168
+ "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx
169
+ "\n", offset);
170
+ res = 0;
171
+ break;
172
+ }
173
+
174
+ return res;
175
+}
176
+
177
+static void bcm2835_powermgt_write(void *opaque, hwaddr offset,
178
+ uint64_t value, unsigned size)
179
+{
180
+ BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque;
181
+
182
+ if ((value & PASSWORD_MASK) != PASSWORD) {
183
+ qemu_log_mask(LOG_GUEST_ERROR,
184
+ "bcm2835_powermgt_write: Bad password 0x%"PRIx64
185
+ " at offset 0x%08"HWADDR_PRIx"\n",
186
+ value, offset);
187
+ return;
188
+ }
189
+
190
+ value = value & ~PASSWORD_MASK;
191
+
192
+ switch (offset) {
193
+ case R_RSTC:
194
+ s->rstc = value;
195
+ if (value & V_RSTC_RESET) {
196
+ if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) {
197
+ qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
198
+ } else {
199
+ qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
200
+ }
201
+ }
202
+ break;
203
+ case R_RSTS:
204
+ qemu_log_mask(LOG_UNIMP,
205
+ "bcm2835_powermgt_write: RSTS\n");
206
+ s->rsts = value;
207
+ break;
208
+ case R_WDOG:
209
+ qemu_log_mask(LOG_UNIMP,
210
+ "bcm2835_powermgt_write: WDOG\n");
211
+ s->wdog = value;
212
+ break;
213
+
214
+ default:
215
+ qemu_log_mask(LOG_UNIMP,
216
+ "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx
217
+ "\n", offset);
218
+ break;
219
+ }
220
+}
221
+
222
+static const MemoryRegionOps bcm2835_powermgt_ops = {
223
+ .read = bcm2835_powermgt_read,
224
+ .write = bcm2835_powermgt_write,
225
+ .endianness = DEVICE_NATIVE_ENDIAN,
226
+ .impl.min_access_size = 4,
227
+ .impl.max_access_size = 4,
228
+};
229
+
230
+static const VMStateDescription vmstate_bcm2835_powermgt = {
231
+ .name = TYPE_BCM2835_POWERMGT,
232
+ .version_id = 1,
233
+ .minimum_version_id = 1,
234
+ .fields = (VMStateField[]) {
235
+ VMSTATE_UINT32(rstc, BCM2835PowerMgtState),
236
+ VMSTATE_UINT32(rsts, BCM2835PowerMgtState),
237
+ VMSTATE_UINT32(wdog, BCM2835PowerMgtState),
238
+ VMSTATE_END_OF_LIST()
239
+ }
240
+};
241
+
242
+static void bcm2835_powermgt_init(Object *obj)
243
+{
244
+ BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj);
245
+
246
+ memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s,
247
+ TYPE_BCM2835_POWERMGT, 0x200);
248
+ sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
249
+}
250
+
251
+static void bcm2835_powermgt_reset(DeviceState *dev)
252
+{
253
+ BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev);
254
+
255
+ /* https://elinux.org/BCM2835_registers#PM */
256
+ s->rstc = 0x00000102;
257
+ s->rsts = 0x00001000;
258
+ s->wdog = 0x00000000;
259
+}
260
+
261
+static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data)
262
+{
263
+ DeviceClass *dc = DEVICE_CLASS(klass);
264
+
265
+ dc->reset = bcm2835_powermgt_reset;
266
+ dc->vmsd = &vmstate_bcm2835_powermgt;
267
+}
268
+
269
+static TypeInfo bcm2835_powermgt_info = {
270
+ .name = TYPE_BCM2835_POWERMGT,
271
+ .parent = TYPE_SYS_BUS_DEVICE,
272
+ .instance_size = sizeof(BCM2835PowerMgtState),
273
+ .class_init = bcm2835_powermgt_class_init,
274
+ .instance_init = bcm2835_powermgt_init,
275
+};
276
+
277
+static void bcm2835_powermgt_register_types(void)
278
+{
279
+ type_register_static(&bcm2835_powermgt_info);
280
+}
281
+
282
+type_init(bcm2835_powermgt_register_types)
283
diff --git a/hw/misc/meson.build b/hw/misc/meson.build
284
index XXXXXXX..XXXXXXX 100644
285
--- a/hw/misc/meson.build
286
+++ b/hw/misc/meson.build
287
@@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files(
288
'bcm2835_rng.c',
289
'bcm2835_thermal.c',
290
'bcm2835_cprman.c',
291
+ 'bcm2835_powermgt.c',
292
))
293
softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c'))
294
softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c'))
295
--
296
2.20.1
297
298
diff view generated by jsdifflib
New patch
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
2
3
Add a test booting and quickly shutdown a raspi2 machine,
4
to test the power management model:
5
6
(1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd:
7
console: [ 0.000000] Booting Linux on physical CPU 0xf00
8
console: [ 0.000000] Linux version 4.14.98-v7+ (dom@dom-XPS-13-9370) (gcc version 4.9.3 (crosstool-NG crosstool-ng-1.22.0-88-g8460611)) #1200 SMP Tue Feb 12 20:27:48 GMT 2019
9
console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d
10
console: [ 0.000000] CPU: div instructions available: patching division code
11
console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache
12
console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B
13
...
14
console: Boot successful.
15
console: cat /proc/cpuinfo
16
console: / # cat /proc/cpuinfo
17
...
18
console: processor : 3
19
console: model name : ARMv7 Processor rev 5 (v7l)
20
console: BogoMIPS : 125.00
21
console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm
22
console: CPU implementer : 0x41
23
console: CPU architecture: 7
24
console: CPU variant : 0x0
25
console: CPU part : 0xc07
26
console: CPU revision : 5
27
console: Hardware : BCM2835
28
console: Revision : 0000
29
console: Serial : 0000000000000000
30
console: cat /proc/iomem
31
console: / # cat /proc/iomem
32
console: 00000000-3bffffff : System RAM
33
console: 00008000-00afffff : Kernel code
34
console: 00c00000-00d468ef : Kernel data
35
console: 3f006000-3f006fff : dwc_otg
36
console: 3f007000-3f007eff : /soc/dma@7e007000
37
console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880
38
console: 3f100000-3f100027 : /soc/watchdog@7e100000
39
console: 3f101000-3f102fff : /soc/cprman@7e101000
40
console: 3f200000-3f2000b3 : /soc/gpio@7e200000
41
PASS (24.59 s)
42
RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0
43
JOB TIME : 25.02 s
44
45
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
46
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
47
Message-id: 20210531113837.1689775-1-f4bug@amsat.org
48
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
49
---
50
tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++
51
1 file changed, 43 insertions(+)
52
53
diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py
54
index XXXXXXX..XXXXXXX 100644
55
--- a/tests/acceptance/boot_linux_console.py
56
+++ b/tests/acceptance/boot_linux_console.py
57
@@ -XXX,XX +XXX,XX @@
58
from avocado import skip
59
from avocado import skipUnless
60
from avocado_qemu import Test
61
+from avocado_qemu import exec_command
62
from avocado_qemu import exec_command_and_wait_for_pattern
63
from avocado_qemu import interrupt_interactive_console_until_pattern
64
from avocado_qemu import wait_for_console_pattern
65
@@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self):
66
"""
67
self.do_test_arm_raspi2(0)
68
69
+ def test_arm_raspi2_initrd(self):
70
+ """
71
+ :avocado: tags=arch:arm
72
+ :avocado: tags=machine:raspi2
73
+ """
74
+ deb_url = ('http://archive.raspberrypi.org/debian/'
75
+ 'pool/main/r/raspberrypi-firmware/'
76
+ 'raspberrypi-kernel_1.20190215-1_armhf.deb')
77
+ deb_hash = 'cd284220b32128c5084037553db3c482426f3972'
78
+ deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash)
79
+ kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img')
80
+ dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb')
81
+
82
+ initrd_url = ('https://github.com/groeck/linux-build-test/raw/'
83
+ '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/'
84
+ 'arm/rootfs-armv7a.cpio.gz')
85
+ initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c'
86
+ initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash)
87
+ initrd_path = os.path.join(self.workdir, 'rootfs.cpio')
88
+ archive.gzip_uncompress(initrd_path_gz, initrd_path)
89
+
90
+ self.vm.set_console()
91
+ kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
92
+ 'earlycon=pl011,0x3f201000 console=ttyAMA0 '
93
+ 'panic=-1 noreboot ' +
94
+ 'dwc_otg.fiq_fsm_enable=0')
95
+ self.vm.add_args('-kernel', kernel_path,
96
+ '-dtb', dtb_path,
97
+ '-initrd', initrd_path,
98
+ '-append', kernel_command_line,
99
+ '-no-reboot')
100
+ self.vm.launch()
101
+ self.wait_for_console_pattern('Boot successful.')
102
+
103
+ exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo',
104
+ 'BCM2835')
105
+ exec_command_and_wait_for_pattern(self, 'cat /proc/iomem',
106
+ '/soc/cprman@7e101000')
107
+ exec_command(self, 'halt')
108
+ # Wait for VM to shut down gracefully
109
+ self.vm.wait()
110
+
111
def test_arm_exynos4210_initrd(self):
112
"""
113
:avocado: tags=arch:arm
114
--
115
2.20.1
116
117
diff view generated by jsdifflib
1
From: Cédric Le Goater <clg@kaod.org>
1
From: Joe Komlodi <joe.komlodi@xilinx.com>
2
2
3
Initially from Anton D. Kachalov" <mouse@yandex-team.ru> but the SoB was
3
If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute
4
missing.
4
FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will
5
assert due to fpst->default_nan_mode being set.
5
6
6
Signed-off-by: Cédric Le Goater <clg@kaod.org>
7
To avoid this, we check to see what NaN mode we're running in before we call
7
Acked-by: Andrew Jeffery <andrew@aj.id.au>
8
floatxx_silence_nan().
8
Message-id: 20170920064915.30027-1-clg@kaod.org
9
9
[clg: change commit log and subject
10
Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com>
10
replace UL suffix by ULL ]
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
11
Signed-off-by: Cédric Le Goater <clg@kaod.org>
12
Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com
12
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
---
15
---
15
hw/watchdog/wdt_aspeed.c | 4 ++--
16
target/arm/helper-a64.c | 12 +++++++++---
16
1 file changed, 2 insertions(+), 2 deletions(-)
17
target/arm/vfp_helper.c | 24 ++++++++++++++++++------
18
2 files changed, 27 insertions(+), 9 deletions(-)
17
19
18
diff --git a/hw/watchdog/wdt_aspeed.c b/hw/watchdog/wdt_aspeed.c
20
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
19
index XXXXXXX..XXXXXXX 100644
21
index XXXXXXX..XXXXXXX 100644
20
--- a/hw/watchdog/wdt_aspeed.c
22
--- a/target/arm/helper-a64.c
21
+++ b/hw/watchdog/wdt_aspeed.c
23
+++ b/target/arm/helper-a64.c
22
@@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_wdt_read(void *opaque, hwaddr offset, unsigned size)
24
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp)
23
25
float16 nan = a;
24
static void aspeed_wdt_reload(AspeedWDTState *s, bool pclk)
26
if (float16_is_signaling_nan(a, fpst)) {
25
{
27
float_raise(float_flag_invalid, fpst);
26
- uint32_t reload;
28
- nan = float16_silence_nan(a, fpst);
27
+ uint64_t reload;
29
+ if (!fpst->default_nan_mode) {
28
30
+ nan = float16_silence_nan(a, fpst);
29
if (pclk) {
31
+ }
30
reload = muldiv64(s->regs[WDT_RELOAD_VALUE], NANOSECONDS_PER_SECOND,
32
}
31
s->pclk_freq);
33
if (fpst->default_nan_mode) {
32
} else {
34
nan = float16_default_nan(fpst);
33
- reload = s->regs[WDT_RELOAD_VALUE] * 1000;
35
@@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp)
34
+ reload = s->regs[WDT_RELOAD_VALUE] * 1000ULL;
36
float32 nan = a;
35
}
37
if (float32_is_signaling_nan(a, fpst)) {
36
38
float_raise(float_flag_invalid, fpst);
37
if (aspeed_wdt_is_enabled(s)) {
39
- nan = float32_silence_nan(a, fpst);
40
+ if (!fpst->default_nan_mode) {
41
+ nan = float32_silence_nan(a, fpst);
42
+ }
43
}
44
if (fpst->default_nan_mode) {
45
nan = float32_default_nan(fpst);
46
@@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp)
47
float64 nan = a;
48
if (float64_is_signaling_nan(a, fpst)) {
49
float_raise(float_flag_invalid, fpst);
50
- nan = float64_silence_nan(a, fpst);
51
+ if (!fpst->default_nan_mode) {
52
+ nan = float64_silence_nan(a, fpst);
53
+ }
54
}
55
if (fpst->default_nan_mode) {
56
nan = float64_default_nan(fpst);
57
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
58
index XXXXXXX..XXXXXXX 100644
59
--- a/target/arm/vfp_helper.c
60
+++ b/target/arm/vfp_helper.c
61
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp)
62
float16 nan = f16;
63
if (float16_is_signaling_nan(f16, fpst)) {
64
float_raise(float_flag_invalid, fpst);
65
- nan = float16_silence_nan(f16, fpst);
66
+ if (!fpst->default_nan_mode) {
67
+ nan = float16_silence_nan(f16, fpst);
68
+ }
69
}
70
if (fpst->default_nan_mode) {
71
nan = float16_default_nan(fpst);
72
@@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp)
73
float32 nan = f32;
74
if (float32_is_signaling_nan(f32, fpst)) {
75
float_raise(float_flag_invalid, fpst);
76
- nan = float32_silence_nan(f32, fpst);
77
+ if (!fpst->default_nan_mode) {
78
+ nan = float32_silence_nan(f32, fpst);
79
+ }
80
}
81
if (fpst->default_nan_mode) {
82
nan = float32_default_nan(fpst);
83
@@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp)
84
float64 nan = f64;
85
if (float64_is_signaling_nan(f64, fpst)) {
86
float_raise(float_flag_invalid, fpst);
87
- nan = float64_silence_nan(f64, fpst);
88
+ if (!fpst->default_nan_mode) {
89
+ nan = float64_silence_nan(f64, fpst);
90
+ }
91
}
92
if (fpst->default_nan_mode) {
93
nan = float64_default_nan(fpst);
94
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp)
95
float16 nan = f16;
96
if (float16_is_signaling_nan(f16, s)) {
97
float_raise(float_flag_invalid, s);
98
- nan = float16_silence_nan(f16, s);
99
+ if (!s->default_nan_mode) {
100
+ nan = float16_silence_nan(f16, fpstp);
101
+ }
102
}
103
if (s->default_nan_mode) {
104
nan = float16_default_nan(s);
105
@@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp)
106
float32 nan = f32;
107
if (float32_is_signaling_nan(f32, s)) {
108
float_raise(float_flag_invalid, s);
109
- nan = float32_silence_nan(f32, s);
110
+ if (!s->default_nan_mode) {
111
+ nan = float32_silence_nan(f32, fpstp);
112
+ }
113
}
114
if (s->default_nan_mode) {
115
nan = float32_default_nan(s);
116
@@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp)
117
float64 nan = f64;
118
if (float64_is_signaling_nan(f64, s)) {
119
float_raise(float_flag_invalid, s);
120
- nan = float64_silence_nan(f64, s);
121
+ if (!s->default_nan_mode) {
122
+ nan = float64_silence_nan(f64, fpstp);
123
+ }
124
}
125
if (s->default_nan_mode) {
126
nan = float64_default_nan(s);
38
--
127
--
39
2.7.4
128
2.20.1
40
129
41
130
diff view generated by jsdifflib
1
From: Igor Mammedov <imammedo@redhat.com>
1
From: Maxim Uvarov <maxim.uvarov@linaro.org>
2
2
3
s/cpu_model/cpu_type/ that has been forgotten during
3
qemu has 2 type of functions: shutdown and reboot. Shutdown
4
conversion (ba1ba5cc), while touching the line also
4
function has to be used for machine shutdown. Otherwise we cause
5
fixup alignment.
5
a reset with a bogus "cause" value, when we intended a shutdown.
6
6
7
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
7
Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org>
8
Message-id: 1507710805-221721-1-git-send-email-imammedo@redhat.com
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org
10
[PMM: tweaked commit message]
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
12
---
12
include/hw/arm/arm.h | 2 +-
13
hw/gpio/gpio_pwr.c | 2 +-
13
1 file changed, 1 insertion(+), 1 deletion(-)
14
1 file changed, 1 insertion(+), 1 deletion(-)
14
15
15
diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h
16
diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c
16
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
17
--- a/include/hw/arm/arm.h
18
--- a/hw/gpio/gpio_pwr.c
18
+++ b/include/hw/arm/arm.h
19
+++ b/hw/gpio/gpio_pwr.c
19
@@ -XXX,XX +XXX,XX @@ typedef enum {
20
@@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level)
20
21
static void gpio_pwr_shutdown(void *opaque, int n, int level)
21
/* armv7m.c */
22
{
22
DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq,
23
if (level) {
23
- const char *kernel_filename, const char *cpu_model);
24
- qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
24
+ const char *kernel_filename, const char *cpu_type);
25
+ qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
25
/**
26
}
26
* armv7m_load_kernel:
27
}
27
* @cpu: CPU
28
28
--
29
--
29
2.7.4
30
2.20.1
30
31
31
32
diff view generated by jsdifflib
New patch
1
In do_ldst(), the calculation of the offset needs to be based on the
2
size of the memory access, not the size of the elements in the
3
vector. This meant we were getting it wrong for the widening and
4
narrowing variants of the various VLDR and VSTR insns.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-2-peter.maydell@linaro.org
9
---
10
target/arm/translate-mve.c | 17 +++++++++--------
11
1 file changed, 9 insertions(+), 8 deletions(-)
12
13
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/translate-mve.c
16
+++ b/target/arm/translate-mve.c
17
@@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s)
18
}
19
}
20
21
-static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn)
22
+static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn,
23
+ unsigned msize)
24
{
25
TCGv_i32 addr;
26
uint32_t offset;
27
@@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn)
28
return true;
29
}
30
31
- offset = a->imm << a->size;
32
+ offset = a->imm << msize;
33
if (!a->a) {
34
offset = -offset;
35
}
36
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a)
37
{ gen_helper_mve_vstrw, gen_helper_mve_vldrw },
38
{ NULL, NULL }
39
};
40
- return do_ldst(s, a, ldstfns[a->size][a->l]);
41
+ return do_ldst(s, a, ldstfns[a->size][a->l], a->size);
42
}
43
44
-#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \
45
+#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \
46
static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \
47
{ \
48
static MVEGenLdStFn * const ldstfns[2][2] = { \
49
{ gen_helper_mve_##ST, gen_helper_mve_##SLD }, \
50
{ NULL, gen_helper_mve_##ULD }, \
51
}; \
52
- return do_ldst(s, a, ldstfns[a->u][a->l]); \
53
+ return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \
54
}
55
56
-DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h)
57
-DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w)
58
-DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w)
59
+DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8)
60
+DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8)
61
+DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16)
62
63
static bool trans_VDUP(DisasContext *s, arg_VDUP *a)
64
{
65
--
66
2.20.1
67
68
diff view generated by jsdifflib
New patch
1
The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH
2
insns had some bugs:
3
* the 32x32 multiply of elements was being done as 32x32->32,
4
not 32x32->64
5
* we were incorrectly maintaining the accumulator in its full
6
72-bit form across all 4 beats of the insn; in the pseudocode
7
it is squashed back into the 64 bits of the RdaHi:RdaLo
8
registers after each beat
1
9
10
In particular, fixing the second of these allows us to recast
11
the implementation to avoid 128-bit arithmetic entirely.
12
13
Since the element size here is always 4, we can also drop the
14
parameterization of ESIZE to make the code a little more readable.
15
16
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
18
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
19
Message-id: 20210628135835.6690-3-peter.maydell@linaro.org
20
---
21
target/arm/mve_helper.c | 38 +++++++++++++++++++++-----------------
22
1 file changed, 21 insertions(+), 17 deletions(-)
23
24
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
25
index XXXXXXX..XXXXXXX 100644
26
--- a/target/arm/mve_helper.c
27
+++ b/target/arm/mve_helper.c
28
@@ -XXX,XX +XXX,XX @@
29
*/
30
31
#include "qemu/osdep.h"
32
-#include "qemu/int128.h"
33
#include "cpu.h"
34
#include "internals.h"
35
#include "vec_internal.h"
36
@@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=)
37
DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=)
38
39
/*
40
- * Rounding multiply add long dual accumulate high: we must keep
41
- * a 72-bit internal accumulator value and return the top 64 bits.
42
+ * Rounding multiply add long dual accumulate high. In the pseudocode
43
+ * this is implemented with a 72-bit internal accumulator value of which
44
+ * the top 64 bits are returned. We optimize this to avoid having to
45
+ * use 128-bit arithmetic -- we can do this because the 74-bit accumulator
46
+ * is squashed back into 64-bits after each beat.
47
*/
48
-#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \
49
+#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \
50
uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \
51
void *vm, uint64_t a) \
52
{ \
53
uint16_t mask = mve_element_mask(env); \
54
unsigned e; \
55
TYPE *n = vn, *m = vm; \
56
- Int128 acc = int128_lshift(TO128(a), 8); \
57
- for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
58
+ for (e = 0; e < 16 / 4; e++, mask >>= 4) { \
59
if (mask & 1) { \
60
+ LTYPE mul; \
61
if (e & 1) { \
62
- acc = ODDACC(acc, TO128(n[H##ESIZE(e - 1 * XCHG)] * \
63
- m[H##ESIZE(e)])); \
64
+ mul = (LTYPE)n[H4(e - 1 * XCHG)] * m[H4(e)]; \
65
+ if (SUB) { \
66
+ mul = -mul; \
67
+ } \
68
} else { \
69
- acc = EVENACC(acc, TO128(n[H##ESIZE(e + 1 * XCHG)] * \
70
- m[H##ESIZE(e)])); \
71
+ mul = (LTYPE)n[H4(e + 1 * XCHG)] * m[H4(e)]; \
72
} \
73
- acc = int128_add(acc, int128_make64(1 << 7)); \
74
+ mul = (mul >> 8) + ((mul >> 7) & 1); \
75
+ a += mul; \
76
} \
77
} \
78
mve_advance_vpt(env); \
79
- return int128_getlo(int128_rshift(acc, 8)); \
80
+ return a; \
81
}
82
83
-DO_LDAVH(vrmlaldavhsw, 4, int32_t, false, int128_add, int128_add, int128_makes64)
84
-DO_LDAVH(vrmlaldavhxsw, 4, int32_t, true, int128_add, int128_add, int128_makes64)
85
+DO_LDAVH(vrmlaldavhsw, int32_t, int64_t, false, false)
86
+DO_LDAVH(vrmlaldavhxsw, int32_t, int64_t, true, false)
87
88
-DO_LDAVH(vrmlaldavhuw, 4, uint32_t, false, int128_add, int128_add, int128_make64)
89
+DO_LDAVH(vrmlaldavhuw, uint32_t, uint64_t, false, false)
90
91
-DO_LDAVH(vrmlsldavhsw, 4, int32_t, false, int128_add, int128_sub, int128_makes64)
92
-DO_LDAVH(vrmlsldavhxsw, 4, int32_t, true, int128_add, int128_sub, int128_makes64)
93
+DO_LDAVH(vrmlsldavhsw, int32_t, int64_t, false, true)
94
+DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true)
95
96
/* Vector add across vector */
97
#define DO_VADDV(OP, ESIZE, TYPE) \
98
--
99
2.20.1
100
101
diff view generated by jsdifflib
1
Recent changes have left insn_crosses_page() more complicated
1
The function asimd_imm_const() in translate-neon.c is an
2
than it needed to be:
2
implementation of the pseudocode AdvSIMDExpandImm(), which we will
3
* it's only called from thumb_tr_translate_insn() so we know
3
also want for MVE. Move the implementation to translate.c, with a
4
for certain that we're looking at a Thumb insn
4
prototype in translate.h.
5
* the caller's check for dc->pc >= dc->next_page_start - 3
6
means that dc->pc can't possibly be 4 aligned, so there's
7
no need to check that (the check was partly there to ensure
8
that we didn't treat an ARM insn as Thumb, I think)
9
* we now have thumb_insn_is_16bit() which lets us do a precise
10
check of the length of the next insn, rather than opencoding
11
an inaccurate check
12
13
Simplify it down to just loading the first half of the insn
14
and calling thumb_insn_is_16bit() on it.
15
5
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
18
Message-id: 1507556919-24992-8-git-send-email-peter.maydell@linaro.org
8
Message-id: 20210628135835.6690-4-peter.maydell@linaro.org
19
---
9
---
20
target/arm/translate.c | 27 ++++++---------------------
10
target/arm/translate.h | 16 ++++++++++
21
1 file changed, 6 insertions(+), 21 deletions(-)
11
target/arm/translate-neon.c | 63 -------------------------------------
12
target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++
13
3 files changed, 73 insertions(+), 63 deletions(-)
22
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 @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc)
20
return opc | s->be_data;
21
}
22
23
+/**
24
+ * asimd_imm_const: Expand an encoded SIMD constant value
25
+ *
26
+ * Expand a SIMD constant value. This is essentially the pseudocode
27
+ * AdvSIMDExpandImm, except that we also perform the boolean NOT needed for
28
+ * VMVN and VBIC (when cmode < 14 && op == 1).
29
+ *
30
+ * The combination cmode == 15 op == 1 is a reserved encoding for AArch32;
31
+ * callers must catch this.
32
+ *
33
+ * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but
34
+ * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A;
35
+ * we produce an immediate constant value of 0 in these cases.
36
+ */
37
+uint64_t asimd_imm_const(uint32_t imm, int cmode, int op);
38
+
39
#endif /* TARGET_ARM_TRANSLATE_H */
40
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
41
index XXXXXXX..XXXXXXX 100644
42
--- a/target/arm/translate-neon.c
43
+++ b/target/arm/translate-neon.c
44
@@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh)
45
DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs)
46
DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu)
47
48
-static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
49
-{
50
- /*
51
- * Expand the encoded constant.
52
- * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE.
53
- * We choose to not special-case this and will behave as if a
54
- * valid constant encoding of 0 had been given.
55
- * cmode = 15 op = 1 must UNDEF; we assume decode has handled that.
56
- */
57
- switch (cmode) {
58
- case 0: case 1:
59
- /* no-op */
60
- break;
61
- case 2: case 3:
62
- imm <<= 8;
63
- break;
64
- case 4: case 5:
65
- imm <<= 16;
66
- break;
67
- case 6: case 7:
68
- imm <<= 24;
69
- break;
70
- case 8: case 9:
71
- imm |= imm << 16;
72
- break;
73
- case 10: case 11:
74
- imm = (imm << 8) | (imm << 24);
75
- break;
76
- case 12:
77
- imm = (imm << 8) | 0xff;
78
- break;
79
- case 13:
80
- imm = (imm << 16) | 0xffff;
81
- break;
82
- case 14:
83
- if (op) {
84
- /*
85
- * This is the only case where the top and bottom 32 bits
86
- * of the encoded constant differ.
87
- */
88
- uint64_t imm64 = 0;
89
- int n;
90
-
91
- for (n = 0; n < 8; n++) {
92
- if (imm & (1 << n)) {
93
- imm64 |= (0xffULL << (n * 8));
94
- }
95
- }
96
- return imm64;
97
- }
98
- imm |= (imm << 8) | (imm << 16) | (imm << 24);
99
- break;
100
- case 15:
101
- imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19)
102
- | ((imm & 0x40) ? (0x1f << 25) : (1 << 30));
103
- break;
104
- }
105
- if (op) {
106
- imm = ~imm;
107
- }
108
- return dup_const(MO_32, imm);
109
-}
110
-
111
static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a,
112
GVecGen2iFn *fn)
113
{
23
diff --git a/target/arm/translate.c b/target/arm/translate.c
114
diff --git a/target/arm/translate.c b/target/arm/translate.c
24
index XXXXXXX..XXXXXXX 100644
115
index XXXXXXX..XXXXXXX 100644
25
--- a/target/arm/translate.c
116
--- a/target/arm/translate.c
26
+++ b/target/arm/translate.c
117
+++ b/target/arm/translate.c
27
@@ -XXX,XX +XXX,XX @@ static bool insn_crosses_page(CPUARMState *env, DisasContext *s)
118
@@ -XXX,XX +XXX,XX @@ void arm_translate_init(void)
119
a64_translate_init();
120
}
121
122
+uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
123
+{
124
+ /* Expand the encoded constant as per AdvSIMDExpandImm pseudocode */
125
+ switch (cmode) {
126
+ case 0: case 1:
127
+ /* no-op */
128
+ break;
129
+ case 2: case 3:
130
+ imm <<= 8;
131
+ break;
132
+ case 4: case 5:
133
+ imm <<= 16;
134
+ break;
135
+ case 6: case 7:
136
+ imm <<= 24;
137
+ break;
138
+ case 8: case 9:
139
+ imm |= imm << 16;
140
+ break;
141
+ case 10: case 11:
142
+ imm = (imm << 8) | (imm << 24);
143
+ break;
144
+ case 12:
145
+ imm = (imm << 8) | 0xff;
146
+ break;
147
+ case 13:
148
+ imm = (imm << 16) | 0xffff;
149
+ break;
150
+ case 14:
151
+ if (op) {
152
+ /*
153
+ * This is the only case where the top and bottom 32 bits
154
+ * of the encoded constant differ.
155
+ */
156
+ uint64_t imm64 = 0;
157
+ int n;
158
+
159
+ for (n = 0; n < 8; n++) {
160
+ if (imm & (1 << n)) {
161
+ imm64 |= (0xffULL << (n * 8));
162
+ }
163
+ }
164
+ return imm64;
165
+ }
166
+ imm |= (imm << 8) | (imm << 16) | (imm << 24);
167
+ break;
168
+ case 15:
169
+ imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19)
170
+ | ((imm & 0x40) ? (0x1f << 25) : (1 << 30));
171
+ break;
172
+ }
173
+ if (op) {
174
+ imm = ~imm;
175
+ }
176
+ return dup_const(MO_32, imm);
177
+}
178
+
179
/* Generate a label used for skipping this instruction */
180
void arm_gen_condlabel(DisasContext *s)
28
{
181
{
29
/* Return true if the insn at dc->pc might cross a page boundary.
30
* (False positives are OK, false negatives are not.)
31
+ * We know this is a Thumb insn, and our caller ensures we are
32
+ * only called if dc->pc is less than 4 bytes from the page
33
+ * boundary, so we cross the page if the first 16 bits indicate
34
+ * that this is a 32 bit insn.
35
*/
36
- uint16_t insn;
37
+ uint16_t insn = arm_lduw_code(env, s->pc, s->sctlr_b);
38
39
- if ((s->pc & 3) == 0) {
40
- /* At a 4-aligned address we can't be crossing a page */
41
- return false;
42
- }
43
-
44
- /* This must be a Thumb insn */
45
- insn = arm_lduw_code(env, s->pc, s->sctlr_b);
46
-
47
- if ((insn >> 11) >= 0x1d) {
48
- /* Top five bits 0b11101 / 0b11110 / 0b11111 : this is the
49
- * First half of a 32-bit Thumb insn. Thumb-1 cores might
50
- * end up actually treating this as two 16-bit insns (see the
51
- * code at the start of disas_thumb2_insn()) but we don't bother
52
- * to check for that as it is unlikely, and false positives here
53
- * are harmless.
54
- */
55
- return true;
56
- }
57
- /* Definitely a 16-bit insn, can't be crossing a page. */
58
- return false;
59
+ return !thumb_insn_is_16bit(s, insn);
60
}
61
62
static int arm_tr_init_disas_context(DisasContextBase *dcbase,
63
--
182
--
64
2.7.4
183
2.20.1
65
184
66
185
diff view generated by jsdifflib
1
The common situation of the SG instruction is that it is
1
The A64 AdvSIMD modified-immediate grouping uses almost the same
2
executed from S&NSC memory by a CPU in NS state. That case
2
constant encoding that A32 Neon does; reuse asimd_imm_const() (to
3
is handled by v7m_handle_execute_nsc(). However the instruction
3
which we add the AArch64-specific case for cmode 15 op 1) instead of
4
also has defined behaviour in a couple of other cases:
4
reimplementing it all.
5
* SG instruction in NS memory (behaves as a NOP)
6
* SG in S memory but CPU already secure (clears IT bits and
7
does nothing else)
8
* SG instruction in v8M without Security Extension (NOP)
9
10
These can be implemented in translate.c.
11
5
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 1507556919-24992-10-git-send-email-peter.maydell@linaro.org
8
Message-id: 20210628135835.6690-5-peter.maydell@linaro.org
15
---
9
---
16
target/arm/translate.c | 23 ++++++++++++++++++++++-
10
target/arm/translate.h | 3 +-
17
1 file changed, 22 insertions(+), 1 deletion(-)
11
target/arm/translate-a64.c | 86 ++++----------------------------------
12
target/arm/translate.c | 17 +++++++-
13
3 files changed, 24 insertions(+), 82 deletions(-)
18
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 @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc)
20
* VMVN and VBIC (when cmode < 14 && op == 1).
21
*
22
* The combination cmode == 15 op == 1 is a reserved encoding for AArch32;
23
- * callers must catch this.
24
+ * callers must catch this; we return the 64-bit constant value defined
25
+ * for AArch64.
26
*
27
* cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but
28
* is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A;
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 disas_simd_mod_imm(DisasContext *s, uint32_t insn)
34
{
35
int rd = extract32(insn, 0, 5);
36
int cmode = extract32(insn, 12, 4);
37
- int cmode_3_1 = extract32(cmode, 1, 3);
38
- int cmode_0 = extract32(cmode, 0, 1);
39
int o2 = extract32(insn, 11, 1);
40
uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5);
41
bool is_neg = extract32(insn, 29, 1);
42
@@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
43
return;
44
}
45
46
- /* See AdvSIMDExpandImm() in ARM ARM */
47
- switch (cmode_3_1) {
48
- case 0: /* Replicate(Zeros(24):imm8, 2) */
49
- case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */
50
- case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */
51
- case 3: /* Replicate(imm8:Zeros(24), 2) */
52
- {
53
- int shift = cmode_3_1 * 8;
54
- imm = bitfield_replicate(abcdefgh << shift, 32);
55
- break;
56
- }
57
- case 4: /* Replicate(Zeros(8):imm8, 4) */
58
- case 5: /* Replicate(imm8:Zeros(8), 4) */
59
- {
60
- int shift = (cmode_3_1 & 0x1) * 8;
61
- imm = bitfield_replicate(abcdefgh << shift, 16);
62
- break;
63
- }
64
- case 6:
65
- if (cmode_0) {
66
- /* Replicate(Zeros(8):imm8:Ones(16), 2) */
67
- imm = (abcdefgh << 16) | 0xffff;
68
- } else {
69
- /* Replicate(Zeros(16):imm8:Ones(8), 2) */
70
- imm = (abcdefgh << 8) | 0xff;
71
- }
72
- imm = bitfield_replicate(imm, 32);
73
- break;
74
- case 7:
75
- if (!cmode_0 && !is_neg) {
76
- imm = bitfield_replicate(abcdefgh, 8);
77
- } else if (!cmode_0 && is_neg) {
78
- int i;
79
- imm = 0;
80
- for (i = 0; i < 8; i++) {
81
- if ((abcdefgh) & (1 << i)) {
82
- imm |= 0xffULL << (i * 8);
83
- }
84
- }
85
- } else if (cmode_0) {
86
- if (is_neg) {
87
- imm = (abcdefgh & 0x3f) << 48;
88
- if (abcdefgh & 0x80) {
89
- imm |= 0x8000000000000000ULL;
90
- }
91
- if (abcdefgh & 0x40) {
92
- imm |= 0x3fc0000000000000ULL;
93
- } else {
94
- imm |= 0x4000000000000000ULL;
95
- }
96
- } else {
97
- if (o2) {
98
- /* FMOV (vector, immediate) - half-precision */
99
- imm = vfp_expand_imm(MO_16, abcdefgh);
100
- /* now duplicate across the lanes */
101
- imm = bitfield_replicate(imm, 16);
102
- } else {
103
- imm = (abcdefgh & 0x3f) << 19;
104
- if (abcdefgh & 0x80) {
105
- imm |= 0x80000000;
106
- }
107
- if (abcdefgh & 0x40) {
108
- imm |= 0x3e000000;
109
- } else {
110
- imm |= 0x40000000;
111
- }
112
- imm |= (imm << 32);
113
- }
114
- }
115
- }
116
- break;
117
- default:
118
- g_assert_not_reached();
119
- }
120
-
121
- if (cmode_3_1 != 7 && is_neg) {
122
- imm = ~imm;
123
+ if (cmode == 15 && o2 && !is_neg) {
124
+ /* FMOV (vector, immediate) - half-precision */
125
+ imm = vfp_expand_imm(MO_16, abcdefgh);
126
+ /* now duplicate across the lanes */
127
+ imm = bitfield_replicate(imm, 16);
128
+ } else {
129
+ imm = asimd_imm_const(abcdefgh, cmode, is_neg);
130
}
131
132
if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) {
19
diff --git a/target/arm/translate.c b/target/arm/translate.c
133
diff --git a/target/arm/translate.c b/target/arm/translate.c
20
index XXXXXXX..XXXXXXX 100644
134
index XXXXXXX..XXXXXXX 100644
21
--- a/target/arm/translate.c
135
--- a/target/arm/translate.c
22
+++ b/target/arm/translate.c
136
+++ b/target/arm/translate.c
23
@@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
137
@@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
24
* - load/store doubleword, load/store exclusive, ldacq/strel,
138
case 14:
25
* table branch.
139
if (op) {
140
/*
141
- * This is the only case where the top and bottom 32 bits
142
- * of the encoded constant differ.
143
+ * This and cmode == 15 op == 1 are the only cases where
144
+ * the top and bottom 32 bits of the encoded constant differ.
26
*/
145
*/
27
- if (insn & 0x01200000) {
146
uint64_t imm64 = 0;
28
+ if (insn == 0xe97fe97f && arm_dc_feature(s, ARM_FEATURE_M) &&
147
int n;
29
+ arm_dc_feature(s, ARM_FEATURE_V8)) {
148
@@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
30
+ /* 0b1110_1001_0111_1111_1110_1001_0111_111
149
imm |= (imm << 8) | (imm << 16) | (imm << 24);
31
+ * - SG (v8M only)
150
break;
32
+ * The bulk of the behaviour for this instruction is implemented
151
case 15:
33
+ * in v7m_handle_execute_nsc(), which deals with the insn when
152
+ if (op) {
34
+ * it is executed by a CPU in non-secure state from memory
153
+ /* Reserved encoding for AArch32; valid for AArch64 */
35
+ * which is Secure & NonSecure-Callable.
154
+ uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48;
36
+ * Here we only need to handle the remaining cases:
155
+ if (imm & 0x80) {
37
+ * * in NS memory (including the "security extension not
156
+ imm64 |= 0x8000000000000000ULL;
38
+ * implemented" case) : NOP
157
+ }
39
+ * * in S memory but CPU already secure (clear IT bits)
158
+ if (imm & 0x40) {
40
+ * We know that the attribute for the memory this insn is
159
+ imm64 |= 0x3fc0000000000000ULL;
41
+ * in must match the current CPU state, because otherwise
160
+ } else {
42
+ * get_phys_addr_pmsav8 would have generated an exception.
161
+ imm64 |= 0x4000000000000000ULL;
43
+ */
162
+ }
44
+ if (s->v8m_secure) {
163
+ return imm64;
45
+ /* Like the IT insn, we don't need to generate any code */
164
+ }
46
+ s->condexec_cond = 0;
165
imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19)
47
+ s->condexec_mask = 0;
166
| ((imm & 0x40) ? (0x1f << 25) : (1 << 30));
48
+ }
167
break;
49
+ } else if (insn & 0x01200000) {
50
/* 0b1110_1000_x11x_xxxx_xxxx_xxxx_xxxx_xxxx
51
* - load/store dual (post-indexed)
52
* 0b1111_1001_x10x_xxxx_xxxx_xxxx_xxxx_xxxx
53
--
168
--
54
2.7.4
169
2.20.1
55
170
56
171
diff view generated by jsdifflib
New patch
1
Use dup_const() instead of bitfield_replicate() in
2
disas_simd_mod_imm().
1
3
4
(We can't replace the other use of bitfield_replicate() in this file,
5
in logic_imm_decode_wmask(), because that location needs to handle 2
6
and 4 bit elements, which dup_const() cannot.)
7
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
10
Message-id: 20210628135835.6690-6-peter.maydell@linaro.org
11
---
12
target/arm/translate-a64.c | 2 +-
13
1 file changed, 1 insertion(+), 1 deletion(-)
14
15
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate-a64.c
18
+++ b/target/arm/translate-a64.c
19
@@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn)
20
/* FMOV (vector, immediate) - half-precision */
21
imm = vfp_expand_imm(MO_16, abcdefgh);
22
/* now duplicate across the lanes */
23
- imm = bitfield_replicate(imm, 16);
24
+ imm = dup_const(MO_16, imm);
25
} else {
26
imm = asimd_imm_const(abcdefgh, cmode, is_neg);
27
}
28
--
29
2.20.1
30
31
diff view generated by jsdifflib
1
Secure function return happens when a non-secure function has been
1
Implement the MVE logical-immediate insns (VMOV, VMVN,
2
called using BLXNS and so has a particular magic LR value (either
2
VORR and VBIC). These have essentially the same encoding
3
0xfefffffe or 0xfeffffff). The function return via BX behaves
3
as their Neon equivalents, and we implement the decode
4
specially when the new PC value is this magic value, in the same
4
in the same way.
5
way that exception returns are handled.
6
7
Adjust our BX excret guards so that they recognize the function
8
return magic number as well, and perform the function-return
9
unstacking in do_v7m_exception_exit().
10
5
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Acked-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 1507556919-24992-5-git-send-email-peter.maydell@linaro.org
8
Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
15
---
9
---
16
target/arm/internals.h | 7 +++
10
target/arm/helper-mve.h | 4 +++
17
target/arm/helper.c | 115 +++++++++++++++++++++++++++++++++++++++++++++----
11
target/arm/mve.decode | 17 +++++++++++++
18
target/arm/translate.c | 14 +++++-
12
target/arm/mve_helper.c | 24 ++++++++++++++++++
19
3 files changed, 126 insertions(+), 10 deletions(-)
13
target/arm/translate-mve.c | 50 ++++++++++++++++++++++++++++++++++++++
14
4 files changed, 95 insertions(+)
20
15
21
diff --git a/target/arm/internals.h b/target/arm/internals.h
16
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
22
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
23
--- a/target/arm/internals.h
18
--- a/target/arm/helper-mve.h
24
+++ b/target/arm/internals.h
19
+++ b/target/arm/helper-mve.h
25
@@ -XXX,XX +XXX,XX @@ FIELD(V7M_EXCRET, DCRS, 5, 1)
20
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32)
26
FIELD(V7M_EXCRET, S, 6, 1)
21
DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
27
FIELD(V7M_EXCRET, RES1, 7, 25) /* including the must-be-1 prefix */
22
DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32)
28
23
DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
29
+/* Minimum value which is a magic number for exception return */
24
+
30
+#define EXC_RETURN_MIN_MAGIC 0xff000000
25
+DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
31
+/* Minimum number which is a magic number for function or exception return
26
+DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
32
+ * when using v8M security extension
27
+DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
28
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
29
index XXXXXXX..XXXXXXX 100644
30
--- a/target/arm/mve.decode
31
+++ b/target/arm/mve.decode
32
@@ -XXX,XX +XXX,XX @@
33
# VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit
34
%size_28 28:1 !function=plus_1
35
36
+# 1imm format immediate
37
+%imm_28_16_0 28:1 16:3 0:4
38
+
39
&vldr_vstr rn qd imm p a w size l u
40
&1op qd qm size
41
&2op qd qm qn size
42
&2scalar qd qn rm size
43
+&1imm qd imm cmode op
44
45
@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
46
# Note that both Rn and Qd are 3 bits only (no D bit)
47
@@ -XXX,XX +XXX,XX @@
48
@2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0
49
@2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \
50
size=%size_28
51
+@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0
52
53
# The _rev suffix indicates that Vn and Vm are reversed. This is
54
# the case for shifts. In the Arm ARM these insns are documented
55
@@ -XXX,XX +XXX,XX @@ VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rd
56
# Predicate operations
57
%mask_22_13 22:1 13:3
58
VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
59
+
60
+# Logical immediate operations (1 reg and modified-immediate)
61
+
62
+# The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but
63
+# not in a way we can conveniently represent in decodetree without
64
+# a lot of repetition:
65
+# VORR: op=0, (cmode & 1) && cmode < 12
66
+# VBIC: op=1, (cmode & 1) && cmode < 12
67
+# VMOV: everything else
68
+# So we have a single decode line and check the cmode/op in the
69
+# trans function.
70
+Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm
71
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
72
index XXXXXXX..XXXXXXX 100644
73
--- a/target/arm/mve_helper.c
74
+++ b/target/arm/mve_helper.c
75
@@ -XXX,XX +XXX,XX @@ DO_1OP(vnegw, 4, int32_t, DO_NEG)
76
DO_1OP(vfnegh, 8, uint64_t, DO_FNEGH)
77
DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS)
78
79
+/*
80
+ * 1 operand immediates: Vda is destination and possibly also one source.
81
+ * All these insns work at 64-bit widths.
33
+ */
82
+ */
34
+#define FNC_RETURN_MIN_MAGIC 0xfefffffe
83
+#define DO_1OP_IMM(OP, FN) \
35
+
84
+ void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \
36
/* We use a few fake FSR values for internal purposes in M profile.
85
+ { \
37
* M profile cores don't have A/R format FSRs, but currently our
86
+ uint64_t *da = vda; \
38
* get_phys_addr() code assumes A/R profile and reports failures via
87
+ uint16_t mask = mve_element_mask(env); \
39
diff --git a/target/arm/helper.c b/target/arm/helper.c
88
+ unsigned e; \
40
index XXXXXXX..XXXXXXX 100644
89
+ for (e = 0; e < 16 / 8; e++, mask >>= 8) { \
41
--- a/target/arm/helper.c
90
+ mergemask(&da[H8(e)], FN(da[H8(e)], imm), mask); \
42
+++ b/target/arm/helper.c
91
+ } \
43
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest)
92
+ mve_advance_vpt(env); \
44
* - if the return value is a magic value, do exception return (like BX)
45
* - otherwise bit 0 of the return value is the target security state
46
*/
47
- if (dest >= 0xff000000) {
48
+ uint32_t min_magic;
49
+
50
+ if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
51
+ /* Covers FNC_RETURN and EXC_RETURN magic */
52
+ min_magic = FNC_RETURN_MIN_MAGIC;
53
+ } else {
54
+ /* EXC_RETURN magic only */
55
+ min_magic = EXC_RETURN_MIN_MAGIC;
56
+ }
93
+ }
57
+
94
+
58
+ if (dest >= min_magic) {
95
+#define DO_MOVI(N, I) (I)
59
/* This is an exception return magic value; put it where
96
+#define DO_ANDI(N, I) ((N) & (I))
60
* do_v7m_exception_exit() expects and raise EXCEPTION_EXIT.
97
+#define DO_ORRI(N, I) ((N) | (I))
61
* Note that if we ever add gen_ss_advance() singlestep support to
98
+
62
@@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu)
99
+DO_1OP_IMM(vmovi, DO_MOVI)
63
bool exc_secure = false;
100
+DO_1OP_IMM(vandi, DO_ANDI)
64
bool return_to_secure;
101
+DO_1OP_IMM(vorri, DO_ORRI)
65
102
+
66
- /* We can only get here from an EXCP_EXCEPTION_EXIT, and
103
#define DO_2OP(OP, ESIZE, TYPE, FN) \
67
- * gen_bx_excret() enforces the architectural rule
104
void HELPER(glue(mve_, OP))(CPUARMState *env, \
68
- * that jumps to magic addresses don't have magic behaviour unless
105
void *vd, void *vn, void *vm) \
69
- * we're in Handler mode (compare pseudocode BXWritePC()).
106
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
70
+ /* If we're not in Handler mode then jumps to magic exception-exit
107
index XXXXXXX..XXXXXXX 100644
71
+ * addresses don't have magic behaviour. However for the v8M
108
--- a/target/arm/translate-mve.c
72
+ * security extensions the magic secure-function-return has to
109
+++ b/target/arm/translate-mve.c
73
+ * work in thread mode too, so to avoid doing an extra check in
110
@@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
74
+ * the generated code we allow exception-exit magic to also cause the
111
typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
75
+ * internal exception and bring us here in thread mode. Correct code
112
typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
76
+ * will never try to do this (the following insn fetch will always
113
typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
77
+ * fault) so we the overhead of having taken an unnecessary exception
114
+typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
78
+ * doesn't matter.
115
79
*/
116
/* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
80
- assert(arm_v7m_is_handler_mode(env));
117
static inline long mve_qreg_offset(unsigned reg)
81
+ if (!arm_v7m_is_handler_mode(env)) {
118
@@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
82
+ return;
119
mve_update_eci(s);
120
return true;
121
}
122
+
123
+static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn)
124
+{
125
+ TCGv_ptr qd;
126
+ uint64_t imm;
127
+
128
+ if (!dc_isar_feature(aa32_mve, s) ||
129
+ !mve_check_qreg_bank(s, a->qd) ||
130
+ !fn) {
131
+ return false;
83
+ }
132
+ }
84
133
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
85
/* In the spec pseudocode ExceptionReturn() is called directly
134
+ return true;
86
* from BXWritePC() and gets the full target PC value including
87
@@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu)
88
qemu_log_mask(CPU_LOG_INT, "...successful exception return\n");
89
}
90
91
+static bool do_v7m_function_return(ARMCPU *cpu)
92
+{
93
+ /* v8M security extensions magic function return.
94
+ * We may either:
95
+ * (1) throw an exception (longjump)
96
+ * (2) return true if we successfully handled the function return
97
+ * (3) return false if we failed a consistency check and have
98
+ * pended a UsageFault that needs to be taken now
99
+ *
100
+ * At this point the magic return value is split between env->regs[15]
101
+ * and env->thumb. We don't bother to reconstitute it because we don't
102
+ * need it (all values are handled the same way).
103
+ */
104
+ CPUARMState *env = &cpu->env;
105
+ uint32_t newpc, newpsr, newpsr_exc;
106
+
107
+ qemu_log_mask(CPU_LOG_INT, "...really v7M secure function return\n");
108
+
109
+ {
110
+ bool threadmode, spsel;
111
+ TCGMemOpIdx oi;
112
+ ARMMMUIdx mmu_idx;
113
+ uint32_t *frame_sp_p;
114
+ uint32_t frameptr;
115
+
116
+ /* Pull the return address and IPSR from the Secure stack */
117
+ threadmode = !arm_v7m_is_handler_mode(env);
118
+ spsel = env->v7m.control[M_REG_S] & R_V7M_CONTROL_SPSEL_MASK;
119
+
120
+ frame_sp_p = get_v7m_sp_ptr(env, true, threadmode, spsel);
121
+ frameptr = *frame_sp_p;
122
+
123
+ /* These loads may throw an exception (for MPU faults). We want to
124
+ * do them as secure, so work out what MMU index that is.
125
+ */
126
+ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true);
127
+ oi = make_memop_idx(MO_LE, arm_to_core_mmu_idx(mmu_idx));
128
+ newpc = helper_le_ldul_mmu(env, frameptr, oi, 0);
129
+ newpsr = helper_le_ldul_mmu(env, frameptr + 4, oi, 0);
130
+
131
+ /* Consistency checks on new IPSR */
132
+ newpsr_exc = newpsr & XPSR_EXCP;
133
+ if (!((env->v7m.exception == 0 && newpsr_exc == 0) ||
134
+ (env->v7m.exception == 1 && newpsr_exc != 0))) {
135
+ /* Pend the fault and tell our caller to take it */
136
+ env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_INVPC_MASK;
137
+ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE,
138
+ env->v7m.secure);
139
+ qemu_log_mask(CPU_LOG_INT,
140
+ "...taking INVPC UsageFault: "
141
+ "IPSR consistency check failed\n");
142
+ return false;
143
+ }
144
+
145
+ *frame_sp_p = frameptr + 8;
146
+ }
135
+ }
147
+
136
+
148
+ /* This invalidates frame_sp_p */
137
+ imm = asimd_imm_const(a->imm, a->cmode, a->op);
149
+ switch_v7m_security_state(env, true);
150
+ env->v7m.exception = newpsr_exc;
151
+ env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_SFPA_MASK;
152
+ if (newpsr & XPSR_SFPA) {
153
+ env->v7m.control[M_REG_S] |= R_V7M_CONTROL_SFPA_MASK;
154
+ }
155
+ xpsr_write(env, 0, XPSR_IT);
156
+ env->thumb = newpc & 1;
157
+ env->regs[15] = newpc & ~1;
158
+
138
+
159
+ qemu_log_mask(CPU_LOG_INT, "...function return successful\n");
139
+ qd = mve_qreg_ptr(a->qd);
140
+ fn(cpu_env, qd, tcg_constant_i64(imm));
141
+ tcg_temp_free_ptr(qd);
142
+ mve_update_eci(s);
160
+ return true;
143
+ return true;
161
+}
144
+}
162
+
145
+
163
static void arm_log_exception(int idx)
146
+static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a)
164
{
147
+{
165
if (qemu_loglevel_mask(CPU_LOG_INT)) {
148
+ /* Handle decode of cmode/op here between VORR/VBIC/VMOV */
166
@@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs)
149
+ MVEGenOneOpImmFn *fn;
167
case EXCP_IRQ:
150
+
168
break;
151
+ if ((a->cmode & 1) && a->cmode < 12) {
169
case EXCP_EXCEPTION_EXIT:
152
+ if (a->op) {
170
- do_v7m_exception_exit(cpu);
153
+ /*
171
- return;
154
+ * For op=1, the immediate will be inverted by asimd_imm_const(),
172
+ if (env->regs[15] < EXC_RETURN_MIN_MAGIC) {
155
+ * so the VBIC becomes a logical AND operation.
173
+ /* Must be v8M security extension function return */
156
+ */
174
+ assert(env->regs[15] >= FNC_RETURN_MIN_MAGIC);
157
+ fn = gen_helper_mve_vandi;
175
+ assert(arm_feature(env, ARM_FEATURE_M_SECURITY));
176
+ if (do_v7m_function_return(cpu)) {
177
+ return;
178
+ }
179
+ } else {
158
+ } else {
180
+ do_v7m_exception_exit(cpu);
159
+ fn = gen_helper_mve_vorri;
181
+ return;
182
+ }
160
+ }
183
+ break;
184
default:
185
cpu_abort(cs, "Unhandled exception 0x%x\n", cs->exception_index);
186
return; /* Never happens. Keep compiler happy. */
187
diff --git a/target/arm/translate.c b/target/arm/translate.c
188
index XXXXXXX..XXXXXXX 100644
189
--- a/target/arm/translate.c
190
+++ b/target/arm/translate.c
191
@@ -XXX,XX +XXX,XX @@ static inline void gen_bx_excret(DisasContext *s, TCGv_i32 var)
192
* s->base.is_jmp that we need to do the rest of the work later.
193
*/
194
gen_bx(s, var);
195
- if (s->v7m_handler_mode && arm_dc_feature(s, ARM_FEATURE_M)) {
196
+ if (arm_dc_feature(s, ARM_FEATURE_M_SECURITY) ||
197
+ (s->v7m_handler_mode && arm_dc_feature(s, ARM_FEATURE_M))) {
198
s->base.is_jmp = DISAS_BX_EXCRET;
199
}
200
}
201
@@ -XXX,XX +XXX,XX @@ static inline void gen_bx_excret_final_code(DisasContext *s)
202
{
203
/* Generate the code to finish possible exception return and end the TB */
204
TCGLabel *excret_label = gen_new_label();
205
+ uint32_t min_magic;
206
+
207
+ if (arm_dc_feature(s, ARM_FEATURE_M_SECURITY)) {
208
+ /* Covers FNC_RETURN and EXC_RETURN magic */
209
+ min_magic = FNC_RETURN_MIN_MAGIC;
210
+ } else {
161
+ } else {
211
+ /* EXC_RETURN magic only */
162
+ /* There is one unallocated cmode/op combination in this space */
212
+ min_magic = EXC_RETURN_MIN_MAGIC;
163
+ if (a->cmode == 15 && a->op == 1) {
164
+ return false;
165
+ }
166
+ /* asimd_imm_const() sorts out VMVNI vs VMOVI for us */
167
+ fn = gen_helper_mve_vmovi;
213
+ }
168
+ }
214
169
+ return do_1imm(s, a, fn);
215
/* Is the new PC value in the magic range indicating exception return? */
170
+}
216
- tcg_gen_brcondi_i32(TCG_COND_GEU, cpu_R[15], 0xff000000, excret_label);
217
+ tcg_gen_brcondi_i32(TCG_COND_GEU, cpu_R[15], min_magic, excret_label);
218
/* No: end the TB as we would for a DISAS_JMP */
219
if (is_singlestepping(s)) {
220
gen_singlestep_exception(s);
221
--
171
--
222
2.7.4
172
2.20.1
223
173
224
174
diff view generated by jsdifflib
New patch
1
1
Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL
2
and VQSHLU.
3
4
The size-and-immediate encoding here is the same as Neon, and we
5
handle it the same way neon-dp.decode does.
6
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
Message-id: 20210628135835.6690-8-peter.maydell@linaro.org
10
---
11
target/arm/helper-mve.h | 16 +++++++++++
12
target/arm/mve.decode | 23 +++++++++++++++
13
target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++
14
target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++
15
4 files changed, 147 insertions(+)
16
17
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
18
index XXXXXXX..XXXXXXX 100644
19
--- a/target/arm/helper-mve.h
20
+++ b/target/arm/helper-mve.h
21
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
22
DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
23
DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
24
DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
25
+
26
+DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+
30
+DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
+DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
+DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
+
34
+DEF_HELPER_FLAGS_4(mve_vqshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
35
+DEF_HELPER_FLAGS_4(mve_vqshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
+DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
+
38
+DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
39
+DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
40
+DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
41
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
42
index XXXXXXX..XXXXXXX 100644
43
--- a/target/arm/mve.decode
44
+++ b/target/arm/mve.decode
45
@@ -XXX,XX +XXX,XX @@
46
&2op qd qm qn size
47
&2scalar qd qn rm size
48
&1imm qd imm cmode op
49
+&2shift qd qm shift size
50
51
@vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0
52
# Note that both Rn and Qd are 3 bits only (no D bit)
53
@@ -XXX,XX +XXX,XX @@
54
@2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
55
@2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn
56
57
+@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
58
+@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
59
+@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
60
+
61
# Vector loads and stores
62
63
# Widening loads and narrowing stores:
64
@@ -XXX,XX +XXX,XX @@ VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13
65
# So we have a single decode line and check the cmode/op in the
66
# trans function.
67
Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm
68
+
69
+# Shifts by immediate
70
+
71
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
72
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
73
+VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
74
+
75
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
76
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
77
+VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
78
+
79
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b
80
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h
81
+VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
82
+
83
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b
84
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h
85
+VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w
86
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
87
index XXXXXXX..XXXXXXX 100644
88
--- a/target/arm/mve_helper.c
89
+++ b/target/arm/mve_helper.c
90
@@ -XXX,XX +XXX,XX @@ DO_2OP_SAT(vqsubsw, 4, int32_t, DO_SQSUB_W)
91
WRAP_QRSHL_HELPER(do_sqrshl_bhs, N, M, true, satp)
92
#define DO_UQRSHL_OP(N, M, satp) \
93
WRAP_QRSHL_HELPER(do_uqrshl_bhs, N, M, true, satp)
94
+#define DO_SUQSHL_OP(N, M, satp) \
95
+ WRAP_QRSHL_HELPER(do_suqrshl_bhs, N, M, false, satp)
96
97
DO_2OP_SAT_S(vqshls, DO_SQSHL_OP)
98
DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP)
99
@@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvsw, 4, uint32_t)
100
DO_VADDV(vaddvub, 1, uint8_t)
101
DO_VADDV(vaddvuh, 2, uint16_t)
102
DO_VADDV(vaddvuw, 4, uint32_t)
103
+
104
+/* Shifts by immediate */
105
+#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \
106
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
107
+ void *vm, uint32_t shift) \
108
+ { \
109
+ TYPE *d = vd, *m = vm; \
110
+ uint16_t mask = mve_element_mask(env); \
111
+ unsigned e; \
112
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
113
+ mergemask(&d[H##ESIZE(e)], \
114
+ FN(m[H##ESIZE(e)], shift), mask); \
115
+ } \
116
+ mve_advance_vpt(env); \
117
+ }
118
+
119
+#define DO_2SHIFT_SAT(OP, ESIZE, TYPE, FN) \
120
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
121
+ void *vm, uint32_t shift) \
122
+ { \
123
+ TYPE *d = vd, *m = vm; \
124
+ uint16_t mask = mve_element_mask(env); \
125
+ unsigned e; \
126
+ bool qc = false; \
127
+ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
128
+ bool sat = false; \
129
+ mergemask(&d[H##ESIZE(e)], \
130
+ FN(m[H##ESIZE(e)], shift, &sat), mask); \
131
+ qc |= sat & mask & 1; \
132
+ } \
133
+ if (qc) { \
134
+ env->vfp.qc[0] = qc; \
135
+ } \
136
+ mve_advance_vpt(env); \
137
+ }
138
+
139
+/* provide unsigned 2-op shift helpers for all sizes */
140
+#define DO_2SHIFT_U(OP, FN) \
141
+ DO_2SHIFT(OP##b, 1, uint8_t, FN) \
142
+ DO_2SHIFT(OP##h, 2, uint16_t, FN) \
143
+ DO_2SHIFT(OP##w, 4, uint32_t, FN)
144
+
145
+#define DO_2SHIFT_SAT_U(OP, FN) \
146
+ DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \
147
+ DO_2SHIFT_SAT(OP##h, 2, uint16_t, FN) \
148
+ DO_2SHIFT_SAT(OP##w, 4, uint32_t, FN)
149
+#define DO_2SHIFT_SAT_S(OP, FN) \
150
+ DO_2SHIFT_SAT(OP##b, 1, int8_t, FN) \
151
+ DO_2SHIFT_SAT(OP##h, 2, int16_t, FN) \
152
+ DO_2SHIFT_SAT(OP##w, 4, int32_t, FN)
153
+
154
+DO_2SHIFT_U(vshli_u, DO_VSHLU)
155
+DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP)
156
+DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
157
+DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
158
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
159
index XXXXXXX..XXXXXXX 100644
160
--- a/target/arm/translate-mve.c
161
+++ b/target/arm/translate-mve.c
162
@@ -XXX,XX +XXX,XX @@ typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
163
typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
164
typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
165
typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
166
+typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
167
typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
168
typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
169
typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
170
@@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a)
171
}
172
return do_1imm(s, a, fn);
173
}
174
+
175
+static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn,
176
+ bool negateshift)
177
+{
178
+ TCGv_ptr qd, qm;
179
+ int shift = a->shift;
180
+
181
+ if (!dc_isar_feature(aa32_mve, s) ||
182
+ !mve_check_qreg_bank(s, a->qd | a->qm) ||
183
+ !fn) {
184
+ return false;
185
+ }
186
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
187
+ return true;
188
+ }
189
+
190
+ /*
191
+ * When we handle a right shift insn using a left-shift helper
192
+ * which permits a negative shift count to indicate a right-shift,
193
+ * we must negate the shift count.
194
+ */
195
+ if (negateshift) {
196
+ shift = -shift;
197
+ }
198
+
199
+ qd = mve_qreg_ptr(a->qd);
200
+ qm = mve_qreg_ptr(a->qm);
201
+ fn(cpu_env, qd, qm, tcg_constant_i32(shift));
202
+ tcg_temp_free_ptr(qd);
203
+ tcg_temp_free_ptr(qm);
204
+ mve_update_eci(s);
205
+ return true;
206
+}
207
+
208
+#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \
209
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
210
+ { \
211
+ static MVEGenTwoOpShiftFn * const fns[] = { \
212
+ gen_helper_mve_##FN##b, \
213
+ gen_helper_mve_##FN##h, \
214
+ gen_helper_mve_##FN##w, \
215
+ NULL, \
216
+ }; \
217
+ return do_2shift(s, a, fns[a->size], NEGATESHIFT); \
218
+ }
219
+
220
+DO_2SHIFT(VSHLI, vshli_u, false)
221
+DO_2SHIFT(VQSHLI_S, vqshli_s, false)
222
+DO_2SHIFT(VQSHLI_U, vqshli_u, false)
223
+DO_2SHIFT(VQSHLUI, vqshlui_s, false)
224
--
225
2.20.1
226
227
diff view generated by jsdifflib
1
Implement the BLXNS instruction, which allows secure code to
1
Implement the MVE vector shift right by immediate insns VSHRI and
2
call non-secure code.
2
VRSHRI. As with Neon, we implement these by using helper functions
3
which perform left shifts but allow negative shift counts to indicate
4
right shifts.
3
5
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 1507556919-24992-4-git-send-email-peter.maydell@linaro.org
8
Message-id: 20210628135835.6690-9-peter.maydell@linaro.org
7
---
9
---
8
target/arm/helper.h | 1 +
10
target/arm/helper-mve.h | 12 ++++++++++++
9
target/arm/internals.h | 1 +
11
target/arm/translate.h | 20 ++++++++++++++++++++
10
target/arm/helper.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++++
12
target/arm/mve.decode | 28 ++++++++++++++++++++++++++++
11
target/arm/translate.c | 17 +++++++++++++--
13
target/arm/mve_helper.c | 7 +++++++
12
4 files changed, 76 insertions(+), 2 deletions(-)
14
target/arm/translate-mve.c | 5 +++++
15
target/arm/translate-neon.c | 18 ------------------
16
6 files changed, 72 insertions(+), 18 deletions(-)
13
17
14
diff --git a/target/arm/helper.h b/target/arm/helper.h
18
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
15
index XXXXXXX..XXXXXXX 100644
19
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/helper.h
20
--- a/target/arm/helper-mve.h
17
+++ b/target/arm/helper.h
21
+++ b/target/arm/helper-mve.h
18
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(v7m_msr, void, env, i32, i32)
22
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
19
DEF_HELPER_2(v7m_mrs, i32, env, i32)
23
DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
20
24
DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
21
DEF_HELPER_2(v7m_bxns, void, env, i32)
25
22
+DEF_HELPER_2(v7m_blxns, void, env, i32)
26
+DEF_HELPER_FLAGS_4(mve_vshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
27
+DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
DEF_HELPER_4(access_check_cp_reg, void, env, ptr, i32, i32)
28
+DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
25
DEF_HELPER_3(set_cp_reg, void, env, ptr, i32)
29
+
26
diff --git a/target/arm/internals.h b/target/arm/internals.h
30
DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
34
DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
35
DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
+
38
+DEF_HELPER_FLAGS_4(mve_vrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
39
+DEF_HELPER_FLAGS_4(mve_vrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
40
+DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
41
+
42
+DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
43
+DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
44
+DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
45
diff --git a/target/arm/translate.h b/target/arm/translate.h
27
index XXXXXXX..XXXXXXX 100644
46
index XXXXXXX..XXXXXXX 100644
28
--- a/target/arm/internals.h
47
--- a/target/arm/translate.h
29
+++ b/target/arm/internals.h
48
+++ b/target/arm/translate.h
30
@@ -XXX,XX +XXX,XX @@ static inline bool excp_is_internal(int excp)
49
@@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x)
31
FIELD(V7M_CONTROL, NPRIV, 0, 1)
50
return x * 2 + 1;
32
FIELD(V7M_CONTROL, SPSEL, 1, 1)
33
FIELD(V7M_CONTROL, FPCA, 2, 1)
34
+FIELD(V7M_CONTROL, SFPA, 3, 1)
35
36
/* Bit definitions for v7M exception return payload */
37
FIELD(V7M_EXCRET, ES, 0, 1)
38
diff --git a/target/arm/helper.c b/target/arm/helper.c
39
index XXXXXXX..XXXXXXX 100644
40
--- a/target/arm/helper.c
41
+++ b/target/arm/helper.c
42
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest)
43
g_assert_not_reached();
44
}
51
}
45
52
46
+void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
53
+static inline int rsub_64(DisasContext *s, int x)
47
+{
54
+{
48
+ /* translate.c should never generate calls here in user-only mode */
55
+ return 64 - x;
49
+ g_assert_not_reached();
50
+}
56
+}
51
+
57
+
52
void switch_mode(CPUARMState *env, int mode)
58
+static inline int rsub_32(DisasContext *s, int x)
53
{
54
ARMCPU *cpu = arm_env_get_cpu(env);
55
@@ -XXX,XX +XXX,XX @@ void HELPER(v7m_bxns)(CPUARMState *env, uint32_t dest)
56
env->regs[15] = dest & ~1;
57
}
58
59
+void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest)
60
+{
59
+{
61
+ /* Handle v7M BLXNS:
60
+ return 32 - x;
62
+ * - bit 0 of the destination address is the target security state
63
+ */
64
+
65
+ /* At this point regs[15] is the address just after the BLXNS */
66
+ uint32_t nextinst = env->regs[15] | 1;
67
+ uint32_t sp = env->regs[13] - 8;
68
+ uint32_t saved_psr;
69
+
70
+ /* translate.c will have made BLXNS UNDEF unless we're secure */
71
+ assert(env->v7m.secure);
72
+
73
+ if (dest & 1) {
74
+ /* target is Secure, so this is just a normal BLX,
75
+ * except that the low bit doesn't indicate Thumb/not.
76
+ */
77
+ env->regs[14] = nextinst;
78
+ env->thumb = 1;
79
+ env->regs[15] = dest & ~1;
80
+ return;
81
+ }
82
+
83
+ /* Target is non-secure: first push a stack frame */
84
+ if (!QEMU_IS_ALIGNED(sp, 8)) {
85
+ qemu_log_mask(LOG_GUEST_ERROR,
86
+ "BLXNS with misaligned SP is UNPREDICTABLE\n");
87
+ }
88
+
89
+ saved_psr = env->v7m.exception;
90
+ if (env->v7m.control[M_REG_S] & R_V7M_CONTROL_SFPA_MASK) {
91
+ saved_psr |= XPSR_SFPA;
92
+ }
93
+
94
+ /* Note that these stores can throw exceptions on MPU faults */
95
+ cpu_stl_data(env, sp, nextinst);
96
+ cpu_stl_data(env, sp + 4, saved_psr);
97
+
98
+ env->regs[13] = sp;
99
+ env->regs[14] = 0xfeffffff;
100
+ if (arm_v7m_is_handler_mode(env)) {
101
+ /* Write a dummy value to IPSR, to avoid leaking the current secure
102
+ * exception number to non-secure code. This is guaranteed not
103
+ * to cause write_v7m_exception() to actually change stacks.
104
+ */
105
+ write_v7m_exception(env, 1);
106
+ }
107
+ switch_v7m_security_state(env, 0);
108
+ env->thumb = 1;
109
+ env->regs[15] = dest;
110
+}
61
+}
111
+
62
+
112
static uint32_t *get_v7m_sp_ptr(CPUARMState *env, bool secure, bool threadmode,
63
+static inline int rsub_16(DisasContext *s, int x)
113
bool spsel)
114
{
115
diff --git a/target/arm/translate.c b/target/arm/translate.c
116
index XXXXXXX..XXXXXXX 100644
117
--- a/target/arm/translate.c
118
+++ b/target/arm/translate.c
119
@@ -XXX,XX +XXX,XX @@ static inline void gen_bxns(DisasContext *s, int rm)
120
s->base.is_jmp = DISAS_EXIT;
121
}
122
123
+static inline void gen_blxns(DisasContext *s, int rm)
124
+{
64
+{
125
+ TCGv_i32 var = load_reg(s, rm);
65
+ return 16 - x;
126
+
127
+ /* We don't need to sync condexec state, for the same reason as bxns.
128
+ * We do however need to set the PC, because the blxns helper reads it.
129
+ * The blxns helper may throw an exception.
130
+ */
131
+ gen_set_pc_im(s, s->pc);
132
+ gen_helper_v7m_blxns(cpu_env, var);
133
+ tcg_temp_free_i32(var);
134
+ s->base.is_jmp = DISAS_EXIT;
135
+}
66
+}
136
+
67
+
137
/* Variant of store_reg which uses branch&exchange logic when storing
68
+static inline int rsub_8(DisasContext *s, int x)
138
to r15 in ARM architecture v7 and above. The source must be a temporary
69
+{
139
and will be marked as dead. */
70
+ return 8 - x;
140
@@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
71
+}
141
goto undef;
72
+
142
}
73
static inline int arm_dc_feature(DisasContext *dc, int feature)
143
if (link) {
74
{
144
- /* BLXNS: not yet implemented */
75
return (dc->features & (1ULL << feature)) != 0;
145
- goto undef;
76
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
146
+ gen_blxns(s, rm);
77
index XXXXXXX..XXXXXXX 100644
147
} else {
78
--- a/target/arm/mve.decode
148
gen_bxns(s, rm);
79
+++ b/target/arm/mve.decode
149
}
80
@@ -XXX,XX +XXX,XX @@
81
@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
82
@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
83
84
+# Right shifts are encoded as N - shift, where N is the element size in bits.
85
+%rshift_i5 16:5 !function=rsub_32
86
+%rshift_i4 16:4 !function=rsub_16
87
+%rshift_i3 16:3 !function=rsub_8
88
+
89
+@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \
90
+ size=0 shift=%rshift_i3
91
+@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \
92
+ size=1 shift=%rshift_i4
93
+@2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \
94
+ size=2 shift=%rshift_i5
95
+
96
# Vector loads and stores
97
98
# Widening loads and narrowing stores:
99
@@ -XXX,XX +XXX,XX @@ VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w
100
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b
101
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h
102
VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w
103
+
104
+VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
105
+VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
106
+VSHRI_S 111 0 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
107
+
108
+VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_b
109
+VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_h
110
+VSHRI_U 111 1 1111 1 . ... ... ... 0 0000 0 1 . 1 ... 0 @2_shr_w
111
+
112
+VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
113
+VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
114
+VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
115
+
116
+VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
117
+VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
118
+VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
119
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
120
index XXXXXXX..XXXXXXX 100644
121
--- a/target/arm/mve_helper.c
122
+++ b/target/arm/mve_helper.c
123
@@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t)
124
DO_2SHIFT(OP##b, 1, uint8_t, FN) \
125
DO_2SHIFT(OP##h, 2, uint16_t, FN) \
126
DO_2SHIFT(OP##w, 4, uint32_t, FN)
127
+#define DO_2SHIFT_S(OP, FN) \
128
+ DO_2SHIFT(OP##b, 1, int8_t, FN) \
129
+ DO_2SHIFT(OP##h, 2, int16_t, FN) \
130
+ DO_2SHIFT(OP##w, 4, int32_t, FN)
131
132
#define DO_2SHIFT_SAT_U(OP, FN) \
133
DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \
134
@@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvuw, 4, uint32_t)
135
DO_2SHIFT_SAT(OP##w, 4, int32_t, FN)
136
137
DO_2SHIFT_U(vshli_u, DO_VSHLU)
138
+DO_2SHIFT_S(vshli_s, DO_VSHLS)
139
DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP)
140
DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
141
DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
142
+DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
143
+DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
144
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
145
index XXXXXXX..XXXXXXX 100644
146
--- a/target/arm/translate-mve.c
147
+++ b/target/arm/translate-mve.c
148
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHLI, vshli_u, false)
149
DO_2SHIFT(VQSHLI_S, vqshli_s, false)
150
DO_2SHIFT(VQSHLI_U, vqshli_u, false)
151
DO_2SHIFT(VQSHLUI, vqshlui_s, false)
152
+/* These right shifts use a left-shift helper with negated shift count */
153
+DO_2SHIFT(VSHRI_S, vshli_s, true)
154
+DO_2SHIFT(VSHRI_U, vshli_u, true)
155
+DO_2SHIFT(VRSHRI_S, vrshli_s, true)
156
+DO_2SHIFT(VRSHRI_U, vrshli_u, true)
157
diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c
158
index XXXXXXX..XXXXXXX 100644
159
--- a/target/arm/translate-neon.c
160
+++ b/target/arm/translate-neon.c
161
@@ -XXX,XX +XXX,XX @@ static inline int plus1(DisasContext *s, int x)
162
return x + 1;
163
}
164
165
-static inline int rsub_64(DisasContext *s, int x)
166
-{
167
- return 64 - x;
168
-}
169
-
170
-static inline int rsub_32(DisasContext *s, int x)
171
-{
172
- return 32 - x;
173
-}
174
-static inline int rsub_16(DisasContext *s, int x)
175
-{
176
- return 16 - x;
177
-}
178
-static inline int rsub_8(DisasContext *s, int x)
179
-{
180
- return 8 - x;
181
-}
182
-
183
static inline int neon_3same_fp_size(DisasContext *s, int x)
184
{
185
/* Convert 0==fp32, 1==fp16 into a MO_* value */
150
--
186
--
151
2.7.4
187
2.20.1
152
188
153
189
diff view generated by jsdifflib
New patch
1
Implement the MVE VHLL (vector shift left long) insn. This has two
2
encodings: the T1 encoding is the usual shift-by-immediate format,
3
and the T2 encoding is a special case where the shift count is always
4
equal to the element size.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
9
---
10
target/arm/helper-mve.h | 9 +++++++
11
target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++---
12
target/arm/mve_helper.c | 32 +++++++++++++++++++++++
13
target/arm/translate-mve.c | 15 +++++++++++
14
4 files changed, 105 insertions(+), 4 deletions(-)
15
16
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
17
index XXXXXXX..XXXXXXX 100644
18
--- a/target/arm/helper-mve.h
19
+++ b/target/arm/helper-mve.h
20
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
+
25
+DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
+DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
+DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
+DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
34
index XXXXXXX..XXXXXXX 100644
35
--- a/target/arm/mve.decode
36
+++ b/target/arm/mve.decode
37
@@ -XXX,XX +XXX,XX @@
38
@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
39
@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
40
41
+@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
42
+@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
43
+# VSHLL encoding T2 where shift == esize
44
+@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \
45
+ qd=%qd qm=%qm size=0 shift=8
46
+@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \
47
+ qd=%qd qm=%qm size=1 shift=16
48
+
49
# Right shifts are encoded as N - shift, where N is the element size in bits.
50
%rshift_i5 16:5 !function=rsub_32
51
%rshift_i4 16:4 !function=rsub_16
52
@@ -XXX,XX +XXX,XX @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
53
VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
54
VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
55
56
-VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
57
-VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
58
+# The VSHLL T2 encoding is not a @2op pattern, but is here because it
59
+# overlaps what would be size=0b11 VMULH/VRMULH
60
+{
61
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
62
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
63
64
-VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
65
-VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
66
+ VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
67
+}
68
+
69
+{
70
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
71
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
72
+
73
+ VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
74
+}
75
+
76
+{
77
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
78
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
79
+
80
+ VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
81
+}
82
+
83
+{
84
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
85
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
86
+
87
+ VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
88
+}
89
90
VMAX_S 111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
91
VMAX_U 111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
92
@@ -XXX,XX +XXX,XX @@ VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
93
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
94
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
95
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
96
+
97
+# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file
98
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
99
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
100
+
101
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
102
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
103
+
104
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
105
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
106
+
107
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
108
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
109
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
110
index XXXXXXX..XXXXXXX 100644
111
--- a/target/arm/mve_helper.c
112
+++ b/target/arm/mve_helper.c
113
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
114
DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
115
DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
116
DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
117
+
118
+/*
119
+ * Long shifts taking half-sized inputs from top or bottom of the input
120
+ * vector and producing a double-width result. ESIZE, TYPE are for
121
+ * the input, and LESIZE, LTYPE for the output.
122
+ * Unlike the normal shift helpers, we do not handle negative shift counts,
123
+ * because the long shift is strictly left-only.
124
+ */
125
+#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \
126
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
127
+ void *vm, uint32_t shift) \
128
+ { \
129
+ LTYPE *d = vd; \
130
+ TYPE *m = vm; \
131
+ uint16_t mask = mve_element_mask(env); \
132
+ unsigned le; \
133
+ assert(shift <= 16); \
134
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
135
+ LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \
136
+ mergemask(&d[H##LESIZE(le)], r, mask); \
137
+ } \
138
+ mve_advance_vpt(env); \
139
+ }
140
+
141
+#define DO_VSHLL_ALL(OP, TOP) \
142
+ DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \
143
+ DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \
144
+ DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \
145
+ DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \
146
+
147
+DO_VSHLL_ALL(vshllb, false)
148
+DO_VSHLL_ALL(vshllt, true)
149
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
150
index XXXXXXX..XXXXXXX 100644
151
--- a/target/arm/translate-mve.c
152
+++ b/target/arm/translate-mve.c
153
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_S, vshli_s, true)
154
DO_2SHIFT(VSHRI_U, vshli_u, true)
155
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
156
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
157
+
158
+#define DO_VSHLL(INSN, FN) \
159
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
160
+ { \
161
+ static MVEGenTwoOpShiftFn * const fns[] = { \
162
+ gen_helper_mve_##FN##b, \
163
+ gen_helper_mve_##FN##h, \
164
+ }; \
165
+ return do_2shift(s, a, fns[a->size], false); \
166
+ }
167
+
168
+DO_VSHLL(VSHLL_BS, vshllbs)
169
+DO_VSHLL(VSHLL_BU, vshllbu)
170
+DO_VSHLL(VSHLL_TS, vshllts)
171
+DO_VSHLL(VSHLL_TU, vshlltu)
172
--
173
2.20.1
174
175
diff view generated by jsdifflib
New patch
1
Implement the MVE VSRI and VSLI insns, which perform a
2
shift-and-insert operation.
1
3
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20210628135835.6690-11-peter.maydell@linaro.org
7
---
8
target/arm/helper-mve.h | 8 ++++++++
9
target/arm/mve.decode | 9 ++++++++
10
target/arm/mve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++
11
target/arm/translate-mve.c | 3 +++
12
4 files changed, 62 insertions(+)
13
14
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
15
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/helper-mve.h
17
+++ b/target/arm/helper-mve.h
18
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
19
DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
20
DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
+
23
+DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
+DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
25
+DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+
27
+DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
31
index XXXXXXX..XXXXXXX 100644
32
--- a/target/arm/mve.decode
33
+++ b/target/arm/mve.decode
34
@@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
35
36
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
37
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
38
+
39
+# Shift-and-insert
40
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b
41
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h
42
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
43
+
44
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
45
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
46
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
47
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
48
index XXXXXXX..XXXXXXX 100644
49
--- a/target/arm/mve_helper.c
50
+++ b/target/arm/mve_helper.c
51
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
52
DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
53
DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
54
55
+/* Shift-and-insert; we always work with 64 bits at a time */
56
+#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \
57
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
58
+ void *vm, uint32_t shift) \
59
+ { \
60
+ uint64_t *d = vd, *m = vm; \
61
+ uint16_t mask; \
62
+ uint64_t shiftmask; \
63
+ unsigned e; \
64
+ if (shift == 0 || shift == ESIZE * 8) { \
65
+ /* \
66
+ * Only VSLI can shift by 0; only VSRI can shift by <dt>. \
67
+ * The generic logic would give the right answer for 0 but \
68
+ * fails for <dt>. \
69
+ */ \
70
+ goto done; \
71
+ } \
72
+ assert(shift < ESIZE * 8); \
73
+ mask = mve_element_mask(env); \
74
+ /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */ \
75
+ shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift)); \
76
+ for (e = 0; e < 16 / 8; e++, mask >>= 8) { \
77
+ uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) | \
78
+ (d[H8(e)] & ~shiftmask); \
79
+ mergemask(&d[H8(e)], r, mask); \
80
+ } \
81
+done: \
82
+ mve_advance_vpt(env); \
83
+ }
84
+
85
+#define DO_SHL(N, SHIFT) ((N) << (SHIFT))
86
+#define DO_SHR(N, SHIFT) ((N) >> (SHIFT))
87
+#define SHL_MASK(EBITS, SHIFT) MAKE_64BIT_MASK((SHIFT), (EBITS) - (SHIFT))
88
+#define SHR_MASK(EBITS, SHIFT) MAKE_64BIT_MASK(0, (EBITS) - (SHIFT))
89
+
90
+DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK)
91
+DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK)
92
+DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK)
93
+DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK)
94
+DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK)
95
+DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
96
+
97
/*
98
* Long shifts taking half-sized inputs from top or bottom of the input
99
* vector and producing a double-width result. ESIZE, TYPE are for
100
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
101
index XXXXXXX..XXXXXXX 100644
102
--- a/target/arm/translate-mve.c
103
+++ b/target/arm/translate-mve.c
104
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_U, vshli_u, true)
105
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
106
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
107
108
+DO_2SHIFT(VSRI, vsri, false)
109
+DO_2SHIFT(VSLI, vsli, false)
110
+
111
#define DO_VSHLL(INSN, FN) \
112
static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
113
{ \
114
--
115
2.20.1
116
117
diff view generated by jsdifflib
1
This calculation of the first exception vector in
1
Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN.
2
the ITNS<n> register being accessed:
3
int startvec = 32 * (offset - 0x380) + NVIC_FIRST_IRQ;
4
2
5
is incorrect, because offset is in bytes, so we only want
3
do_urshr() is borrowed from sve_helper.c.
6
to multiply by 8.
7
8
Spotted by Coverity (CID 1381484, CID 1381488), though it is
9
not correct that it actually overflows the buffer, because
10
we have a 'startvec + i < s->num_irq' guard.
11
4
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 1507650856-11718-1-git-send-email-peter.maydell@linaro.org
7
Message-id: 20210628135835.6690-12-peter.maydell@linaro.org
15
---
8
---
16
hw/intc/armv7m_nvic.c | 4 ++--
9
target/arm/helper-mve.h | 10 ++++++++++
17
1 file changed, 2 insertions(+), 2 deletions(-)
10
target/arm/mve.decode | 11 +++++++++++
11
target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++
12
target/arm/translate-mve.c | 15 ++++++++++++++
13
4 files changed, 76 insertions(+)
18
14
19
diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
20
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
21
--- a/hw/intc/armv7m_nvic.c
17
--- a/target/arm/helper-mve.h
22
+++ b/hw/intc/armv7m_nvic.c
18
+++ b/target/arm/helper-mve.h
23
@@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs)
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
return ((s->num_irq - NVIC_FIRST_IRQ) / 32) - 1;
20
DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
25
case 0x380 ... 0x3bf: /* NVIC_ITNS<n> */
21
DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
{
22
DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
- int startvec = 32 * (offset - 0x380) + NVIC_FIRST_IRQ;
23
+
28
+ int startvec = 8 * (offset - 0x380) + NVIC_FIRST_IRQ;
24
+DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
int i;
25
+DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
26
+DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
if (!arm_feature(&cpu->env, ARM_FEATURE_V8)) {
27
+DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
@@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value,
28
+
33
switch (offset) {
29
+DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
34
case 0x380 ... 0x3bf: /* NVIC_ITNS<n> */
30
+DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
35
{
31
+DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
- int startvec = 32 * (offset - 0x380) + NVIC_FIRST_IRQ;
32
+DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
+ int startvec = 8 * (offset - 0x380) + NVIC_FIRST_IRQ;
33
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
38
int i;
34
index XXXXXXX..XXXXXXX 100644
39
35
--- a/target/arm/mve.decode
40
if (!arm_feature(&cpu->env, ARM_FEATURE_V8)) {
36
+++ b/target/arm/mve.decode
37
@@ -XXX,XX +XXX,XX @@ VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
38
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
39
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
40
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
41
+
42
+# Narrowing shifts (which only support b and h sizes)
43
+VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
44
+VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
45
+VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
46
+VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
47
+
48
+VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
49
+VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
50
+VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
51
+VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
52
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
53
index XXXXXXX..XXXXXXX 100644
54
--- a/target/arm/mve_helper.c
55
+++ b/target/arm/mve_helper.c
56
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
57
58
DO_VSHLL_ALL(vshllb, false)
59
DO_VSHLL_ALL(vshllt, true)
60
+
61
+/*
62
+ * Narrowing right shifts, taking a double sized input, shifting it
63
+ * and putting the result in either the top or bottom half of the output.
64
+ * ESIZE, TYPE are the output, and LESIZE, LTYPE the input.
65
+ */
66
+#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \
67
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
68
+ void *vm, uint32_t shift) \
69
+ { \
70
+ LTYPE *m = vm; \
71
+ TYPE *d = vd; \
72
+ uint16_t mask = mve_element_mask(env); \
73
+ unsigned le; \
74
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
75
+ TYPE r = FN(m[H##LESIZE(le)], shift); \
76
+ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
77
+ } \
78
+ mve_advance_vpt(env); \
79
+ }
80
+
81
+#define DO_VSHRN_ALL(OP, FN) \
82
+ DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \
83
+ DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \
84
+ DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \
85
+ DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
86
+
87
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
88
+{
89
+ if (likely(sh < 64)) {
90
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
91
+ } else if (sh == 64) {
92
+ return x >> 63;
93
+ } else {
94
+ return 0;
95
+ }
96
+}
97
+
98
+DO_VSHRN_ALL(vshrn, DO_SHR)
99
+DO_VSHRN_ALL(vrshrn, do_urshr)
100
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
101
index XXXXXXX..XXXXXXX 100644
102
--- a/target/arm/translate-mve.c
103
+++ b/target/arm/translate-mve.c
104
@@ -XXX,XX +XXX,XX @@ DO_VSHLL(VSHLL_BS, vshllbs)
105
DO_VSHLL(VSHLL_BU, vshllbu)
106
DO_VSHLL(VSHLL_TS, vshllts)
107
DO_VSHLL(VSHLL_TU, vshlltu)
108
+
109
+#define DO_2SHIFT_N(INSN, FN) \
110
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
111
+ { \
112
+ static MVEGenTwoOpShiftFn * const fns[] = { \
113
+ gen_helper_mve_##FN##b, \
114
+ gen_helper_mve_##FN##h, \
115
+ }; \
116
+ return do_2shift(s, a, fns[a->size], false); \
117
+ }
118
+
119
+DO_2SHIFT_N(VSHRNB, vshrnb)
120
+DO_2SHIFT_N(VSHRNT, vshrnt)
121
+DO_2SHIFT_N(VRSHRNB, vrshrnb)
122
+DO_2SHIFT_N(VRSHRNT, vrshrnt)
41
--
123
--
42
2.7.4
124
2.20.1
43
125
44
126
diff view generated by jsdifflib
New patch
1
1
Implement the MVE saturating shift-right-and-narrow insns
2
VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN.
3
4
do_srshr() is borrowed from sve_helper.c.
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-13-peter.maydell@linaro.org
9
---
10
target/arm/helper-mve.h | 30 +++++++++++
11
target/arm/mve.decode | 28 ++++++++++
12
target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++
13
target/arm/translate-mve.c | 12 +++++
14
4 files changed, 174 insertions(+)
15
16
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
17
index XXXXXXX..XXXXXXX 100644
18
--- a/target/arm/helper-mve.h
19
+++ b/target/arm/helper-mve.h
20
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
+
25
+DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+
30
+DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
+DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
+DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
+DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
34
+
35
+DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
+DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
+DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
38
+DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
39
+
40
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
41
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
42
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
43
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
44
+
45
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
46
+DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
47
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
48
+DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
49
+
50
+DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
51
+DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
52
+DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
53
+DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
54
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
55
index XXXXXXX..XXXXXXX 100644
56
--- a/target/arm/mve.decode
57
+++ b/target/arm/mve.decode
58
@@ -XXX,XX +XXX,XX @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
59
VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
60
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
61
VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
62
+
63
+VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
64
+VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
65
+VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
66
+VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
67
+VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b
68
+VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h
69
+VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b
70
+VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h
71
+
72
+VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
73
+VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
74
+VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
75
+VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
76
+
77
+VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
78
+VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
79
+VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
80
+VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
81
+VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b
82
+VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h
83
+VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b
84
+VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h
85
+
86
+VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
87
+VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
88
+VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
89
+VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
90
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
91
index XXXXXXX..XXXXXXX 100644
92
--- a/target/arm/mve_helper.c
93
+++ b/target/arm/mve_helper.c
94
@@ -XXX,XX +XXX,XX @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh)
95
}
96
}
97
98
+static inline int64_t do_srshr(int64_t x, unsigned sh)
99
+{
100
+ if (likely(sh < 64)) {
101
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
102
+ } else {
103
+ /* Rounding the sign bit always produces 0. */
104
+ return 0;
105
+ }
106
+}
107
+
108
DO_VSHRN_ALL(vshrn, DO_SHR)
109
DO_VSHRN_ALL(vrshrn, do_urshr)
110
+
111
+static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max,
112
+ bool *satp)
113
+{
114
+ if (val > max) {
115
+ *satp = true;
116
+ return max;
117
+ } else if (val < min) {
118
+ *satp = true;
119
+ return min;
120
+ } else {
121
+ return val;
122
+ }
123
+}
124
+
125
+/* Saturating narrowing right shifts */
126
+#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \
127
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
128
+ void *vm, uint32_t shift) \
129
+ { \
130
+ LTYPE *m = vm; \
131
+ TYPE *d = vd; \
132
+ uint16_t mask = mve_element_mask(env); \
133
+ bool qc = false; \
134
+ unsigned le; \
135
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
136
+ bool sat = false; \
137
+ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \
138
+ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
139
+ qc |= sat && (mask & 1 << (TOP * ESIZE)); \
140
+ } \
141
+ if (qc) { \
142
+ env->vfp.qc[0] = qc; \
143
+ } \
144
+ mve_advance_vpt(env); \
145
+ }
146
+
147
+#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \
148
+ DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \
149
+ DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN)
150
+
151
+#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \
152
+ DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \
153
+ DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN)
154
+
155
+#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \
156
+ DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \
157
+ DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN)
158
+
159
+#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \
160
+ DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \
161
+ DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN)
162
+
163
+#define DO_SHRN_SB(N, M, SATP) \
164
+ do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP)
165
+#define DO_SHRN_UB(N, M, SATP) \
166
+ do_sat_bhs((uint64_t)(N) >> (M), 0, UINT8_MAX, SATP)
167
+#define DO_SHRUN_B(N, M, SATP) \
168
+ do_sat_bhs((int64_t)(N) >> (M), 0, UINT8_MAX, SATP)
169
+
170
+#define DO_SHRN_SH(N, M, SATP) \
171
+ do_sat_bhs((int64_t)(N) >> (M), INT16_MIN, INT16_MAX, SATP)
172
+#define DO_SHRN_UH(N, M, SATP) \
173
+ do_sat_bhs((uint64_t)(N) >> (M), 0, UINT16_MAX, SATP)
174
+#define DO_SHRUN_H(N, M, SATP) \
175
+ do_sat_bhs((int64_t)(N) >> (M), 0, UINT16_MAX, SATP)
176
+
177
+#define DO_RSHRN_SB(N, M, SATP) \
178
+ do_sat_bhs(do_srshr(N, M), INT8_MIN, INT8_MAX, SATP)
179
+#define DO_RSHRN_UB(N, M, SATP) \
180
+ do_sat_bhs(do_urshr(N, M), 0, UINT8_MAX, SATP)
181
+#define DO_RSHRUN_B(N, M, SATP) \
182
+ do_sat_bhs(do_srshr(N, M), 0, UINT8_MAX, SATP)
183
+
184
+#define DO_RSHRN_SH(N, M, SATP) \
185
+ do_sat_bhs(do_srshr(N, M), INT16_MIN, INT16_MAX, SATP)
186
+#define DO_RSHRN_UH(N, M, SATP) \
187
+ do_sat_bhs(do_urshr(N, M), 0, UINT16_MAX, SATP)
188
+#define DO_RSHRUN_H(N, M, SATP) \
189
+ do_sat_bhs(do_srshr(N, M), 0, UINT16_MAX, SATP)
190
+
191
+DO_VSHRN_SAT_SB(vqshrnb_sb, vqshrnt_sb, DO_SHRN_SB)
192
+DO_VSHRN_SAT_SH(vqshrnb_sh, vqshrnt_sh, DO_SHRN_SH)
193
+DO_VSHRN_SAT_UB(vqshrnb_ub, vqshrnt_ub, DO_SHRN_UB)
194
+DO_VSHRN_SAT_UH(vqshrnb_uh, vqshrnt_uh, DO_SHRN_UH)
195
+DO_VSHRN_SAT_SB(vqshrunbb, vqshruntb, DO_SHRUN_B)
196
+DO_VSHRN_SAT_SH(vqshrunbh, vqshrunth, DO_SHRUN_H)
197
+
198
+DO_VSHRN_SAT_SB(vqrshrnb_sb, vqrshrnt_sb, DO_RSHRN_SB)
199
+DO_VSHRN_SAT_SH(vqrshrnb_sh, vqrshrnt_sh, DO_RSHRN_SH)
200
+DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB)
201
+DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH)
202
+DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B)
203
+DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H)
204
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
205
index XXXXXXX..XXXXXXX 100644
206
--- a/target/arm/translate-mve.c
207
+++ b/target/arm/translate-mve.c
208
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VSHRNB, vshrnb)
209
DO_2SHIFT_N(VSHRNT, vshrnt)
210
DO_2SHIFT_N(VRSHRNB, vrshrnb)
211
DO_2SHIFT_N(VRSHRNT, vrshrnt)
212
+DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s)
213
+DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s)
214
+DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u)
215
+DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u)
216
+DO_2SHIFT_N(VQSHRUNB, vqshrunb)
217
+DO_2SHIFT_N(VQSHRUNT, vqshrunt)
218
+DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s)
219
+DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s)
220
+DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u)
221
+DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u)
222
+DO_2SHIFT_N(VQRSHRUNB, vqrshrunb)
223
+DO_2SHIFT_N(VQRSHRUNT, vqrshrunt)
224
--
225
2.20.1
226
227
diff view generated by jsdifflib
1
Coverity points out that we forgot the 'break' for
1
Implement the MVE VSHLC insn, which performs a shift left of the
2
the SAU_CTRL write case (CID1381683). This has
2
entire vector with carry in bits provided from a general purpose
3
no actual visible consequences because it happens
3
register and carry out bits written back to that register.
4
that the following case is effectively a no-op.
5
4
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
8
Message-id: 1507742676-9908-1-git-send-email-peter.maydell@linaro.org
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20210628135835.6690-14-peter.maydell@linaro.org
10
---
8
---
11
hw/intc/armv7m_nvic.c | 1 +
9
target/arm/helper-mve.h | 2 ++
12
1 file changed, 1 insertion(+)
10
target/arm/mve.decode | 2 ++
11
target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++
12
target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++
13
4 files changed, 72 insertions(+)
13
14
14
diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
15
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/intc/armv7m_nvic.c
17
--- a/target/arm/helper-mve.h
17
+++ b/hw/intc/armv7m_nvic.c
18
+++ b/target/arm/helper-mve.h
18
@@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value,
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
19
return;
20
DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
20
}
21
DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
cpu->env.sau.ctrl = value & 3;
22
DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
+ break;
23
+
23
case 0xdd4: /* SAU_TYPE */
24
+DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32)
24
if (!arm_feature(&cpu->env, ARM_FEATURE_V8)) {
25
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
25
goto bad_offset;
26
index XXXXXXX..XXXXXXX 100644
27
--- a/target/arm/mve.decode
28
+++ b/target/arm/mve.decode
29
@@ -XXX,XX +XXX,XX @@ VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b
30
VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h
31
VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b
32
VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h
33
+
34
+VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd
35
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
36
index XXXXXXX..XXXXXXX 100644
37
--- a/target/arm/mve_helper.c
38
+++ b/target/arm/mve_helper.c
39
@@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB)
40
DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH)
41
DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B)
42
DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H)
43
+
44
+uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm,
45
+ uint32_t shift)
46
+{
47
+ uint32_t *d = vd;
48
+ uint16_t mask = mve_element_mask(env);
49
+ unsigned e;
50
+ uint32_t r;
51
+
52
+ /*
53
+ * For each 32-bit element, we shift it left, bringing in the
54
+ * low 'shift' bits of rdm at the bottom. Bits shifted out at
55
+ * the top become the new rdm, if the predicate mask permits.
56
+ * The final rdm value is returned to update the register.
57
+ * shift == 0 here means "shift by 32 bits".
58
+ */
59
+ if (shift == 0) {
60
+ for (e = 0; e < 16 / 4; e++, mask >>= 4) {
61
+ r = rdm;
62
+ if (mask & 1) {
63
+ rdm = d[H4(e)];
64
+ }
65
+ mergemask(&d[H4(e)], r, mask);
66
+ }
67
+ } else {
68
+ uint32_t shiftmask = MAKE_64BIT_MASK(0, shift);
69
+
70
+ for (e = 0; e < 16 / 4; e++, mask >>= 4) {
71
+ r = (d[H4(e)] << shift) | (rdm & shiftmask);
72
+ if (mask & 1) {
73
+ rdm = d[H4(e)] >> (32 - shift);
74
+ }
75
+ mergemask(&d[H4(e)], r, mask);
76
+ }
77
+ }
78
+ mve_advance_vpt(env);
79
+ return rdm;
80
+}
81
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
82
index XXXXXXX..XXXXXXX 100644
83
--- a/target/arm/translate-mve.c
84
+++ b/target/arm/translate-mve.c
85
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u)
86
DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u)
87
DO_2SHIFT_N(VQRSHRUNB, vqrshrunb)
88
DO_2SHIFT_N(VQRSHRUNT, vqrshrunt)
89
+
90
+static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a)
91
+{
92
+ /*
93
+ * Whole Vector Left Shift with Carry. The carry is taken
94
+ * from a general purpose register and written back there.
95
+ * An imm of 0 means "shift by 32".
96
+ */
97
+ TCGv_ptr qd;
98
+ TCGv_i32 rdm;
99
+
100
+ if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) {
101
+ return false;
102
+ }
103
+ if (a->rdm == 13 || a->rdm == 15) {
104
+ /* CONSTRAINED UNPREDICTABLE: we UNDEF */
105
+ return false;
106
+ }
107
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
108
+ return true;
109
+ }
110
+
111
+ qd = mve_qreg_ptr(a->qd);
112
+ rdm = load_reg(s, a->rdm);
113
+ gen_helper_mve_vshlc(rdm, cpu_env, qd, rdm, tcg_constant_i32(a->imm));
114
+ store_reg(s, a->rdm, rdm);
115
+ tcg_temp_free_ptr(qd);
116
+ mve_update_eci(s);
117
+ return true;
118
+}
26
--
119
--
27
2.7.4
120
2.20.1
28
121
29
122
diff view generated by jsdifflib
1
Implement the SG instruction, which we emulate 'by hand' in the
1
Implement the MVE VADDLV insn; this is similar to VADDV, except
2
exception handling code path.
2
that it accumulates 32-bit elements into a 64-bit accumulator
3
stored in a pair of general-purpose registers.
3
4
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 1507556919-24992-3-git-send-email-peter.maydell@linaro.org
7
Message-id: 20210628135835.6690-15-peter.maydell@linaro.org
7
---
8
---
8
target/arm/helper.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++--
9
target/arm/helper-mve.h | 3 ++
9
1 file changed, 127 insertions(+), 5 deletions(-)
10
target/arm/mve.decode | 6 +++-
11
target/arm/mve_helper.c | 19 ++++++++++++
12
target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++
13
4 files changed, 90 insertions(+), 1 deletion(-)
10
14
11
diff --git a/target/arm/helper.c b/target/arm/helper.c
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
12
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
13
--- a/target/arm/helper.c
17
--- a/target/arm/helper-mve.h
14
+++ b/target/arm/helper.c
18
+++ b/target/arm/helper-mve.h
15
@@ -XXX,XX +XXX,XX @@ typedef struct V8M_SAttributes {
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
16
bool irvalid;
20
DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32)
17
} V8M_SAttributes;
21
DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
18
22
19
+static void v8m_security_lookup(CPUARMState *env, uint32_t address,
23
+DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64)
20
+ MMUAccessType access_type, ARMMMUIdx mmu_idx,
24
+DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64)
21
+ V8M_SAttributes *sattrs);
22
+
25
+
23
/* Definitions for the PMCCNTR and PMCR registers */
26
DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
24
#define PMCRD 0x8
27
DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
25
#define PMCRC 0x4
28
DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
26
@@ -XXX,XX +XXX,XX @@ static void arm_log_exception(int idx)
29
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
27
}
30
index XXXXXXX..XXXXXXX 100644
31
--- a/target/arm/mve.decode
32
+++ b/target/arm/mve.decode
33
@@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
34
VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar
35
36
# Vector add across vector
37
-VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo
38
+{
39
+ VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo
40
+ VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \
41
+ rdahi=%rdahi rdalo=%rdalo
42
+}
43
44
# Predicate operations
45
%mask_22_13 22:1 13:3
46
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
47
index XXXXXXX..XXXXXXX 100644
48
--- a/target/arm/mve_helper.c
49
+++ b/target/arm/mve_helper.c
50
@@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t)
51
DO_VADDV(vaddvuh, 2, uint16_t)
52
DO_VADDV(vaddvuw, 4, uint32_t)
53
54
+#define DO_VADDLV(OP, TYPE, LTYPE) \
55
+ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \
56
+ uint64_t ra) \
57
+ { \
58
+ uint16_t mask = mve_element_mask(env); \
59
+ unsigned e; \
60
+ TYPE *m = vm; \
61
+ for (e = 0; e < 16 / 4; e++, mask >>= 4) { \
62
+ if (mask & 1) { \
63
+ ra += (LTYPE)m[H4(e)]; \
64
+ } \
65
+ } \
66
+ mve_advance_vpt(env); \
67
+ return ra; \
68
+ } \
69
+
70
+DO_VADDLV(vaddlv_s, int32_t, int64_t)
71
+DO_VADDLV(vaddlv_u, uint32_t, uint64_t)
72
+
73
/* Shifts by immediate */
74
#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \
75
void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
76
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
77
index XXXXXXX..XXXXXXX 100644
78
--- a/target/arm/translate-mve.c
79
+++ b/target/arm/translate-mve.c
80
@@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
81
return true;
28
}
82
}
29
83
30
+static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx,
84
+static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a)
31
+ uint32_t addr, uint16_t *insn)
32
+{
85
+{
33
+ /* Load a 16-bit portion of a v7M instruction, returning true on success,
86
+ /*
34
+ * or false on failure (in which case we will have pended the appropriate
87
+ * Vector Add Long Across Vector: accumulate the 32-bit
35
+ * exception).
88
+ * elements of the vector into a 64-bit result stored in
36
+ * We need to do the instruction fetch's MPU and SAU checks
89
+ * a pair of general-purpose registers.
37
+ * like this because there is no MMU index that would allow
90
+ * No need to check Qm's bank: it is only 3 bits in decode.
38
+ * doing the load with a single function call. Instead we must
39
+ * first check that the security attributes permit the load
40
+ * and that they don't mismatch on the two halves of the instruction,
41
+ * and then we do the load as a secure load (ie using the security
42
+ * attributes of the address, not the CPU, as architecturally required).
43
+ */
91
+ */
44
+ CPUState *cs = CPU(cpu);
92
+ TCGv_ptr qm;
45
+ CPUARMState *env = &cpu->env;
93
+ TCGv_i64 rda;
46
+ V8M_SAttributes sattrs = {};
94
+ TCGv_i32 rdalo, rdahi;
47
+ MemTxAttrs attrs = {};
48
+ ARMMMUFaultInfo fi = {};
49
+ MemTxResult txres;
50
+ target_ulong page_size;
51
+ hwaddr physaddr;
52
+ int prot;
53
+ uint32_t fsr;
54
+
95
+
55
+ v8m_security_lookup(env, addr, MMU_INST_FETCH, mmu_idx, &sattrs);
96
+ if (!dc_isar_feature(aa32_mve, s)) {
56
+ if (!sattrs.nsc || sattrs.ns) {
57
+ /* This must be the second half of the insn, and it straddles a
58
+ * region boundary with the second half not being S&NSC.
59
+ */
60
+ env->v7m.sfsr |= R_V7M_SFSR_INVEP_MASK;
61
+ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false);
62
+ qemu_log_mask(CPU_LOG_INT,
63
+ "...really SecureFault with SFSR.INVEP\n");
64
+ return false;
97
+ return false;
65
+ }
98
+ }
66
+ if (get_phys_addr(env, addr, MMU_INST_FETCH, mmu_idx,
99
+ /*
67
+ &physaddr, &attrs, &prot, &page_size, &fsr, &fi)) {
100
+ * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related
68
+ /* the MPU lookup failed */
101
+ * encoding; rdalo always has bit 0 clear so cannot be 13 or 15.
69
+ env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_IACCVIOL_MASK;
102
+ */
70
+ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, env->v7m.secure);
103
+ if (a->rdahi == 13 || a->rdahi == 15) {
71
+ qemu_log_mask(CPU_LOG_INT, "...really MemManage with CFSR.IACCVIOL\n");
72
+ return false;
104
+ return false;
73
+ }
105
+ }
74
+ *insn = address_space_lduw_le(arm_addressspace(cs, attrs), physaddr,
106
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
75
+ attrs, &txres);
107
+ return true;
76
+ if (txres != MEMTX_OK) {
77
+ env->v7m.cfsr[M_REG_NS] |= R_V7M_CFSR_IBUSERR_MASK;
78
+ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS, false);
79
+ qemu_log_mask(CPU_LOG_INT, "...really BusFault with CFSR.IBUSERR\n");
80
+ return false;
81
+ }
108
+ }
109
+
110
+ /*
111
+ * This insn is subject to beat-wise execution. Partial execution
112
+ * of an A=0 (no-accumulate) insn which does not execute the first
113
+ * beat must start with the current value of RdaHi:RdaLo, not zero.
114
+ */
115
+ if (a->a || mve_skip_first_beat(s)) {
116
+ /* Accumulate input from RdaHi:RdaLo */
117
+ rda = tcg_temp_new_i64();
118
+ rdalo = load_reg(s, a->rdalo);
119
+ rdahi = load_reg(s, a->rdahi);
120
+ tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
121
+ tcg_temp_free_i32(rdalo);
122
+ tcg_temp_free_i32(rdahi);
123
+ } else {
124
+ /* Accumulate starting at zero */
125
+ rda = tcg_const_i64(0);
126
+ }
127
+
128
+ qm = mve_qreg_ptr(a->qm);
129
+ if (a->u) {
130
+ gen_helper_mve_vaddlv_u(rda, cpu_env, qm, rda);
131
+ } else {
132
+ gen_helper_mve_vaddlv_s(rda, cpu_env, qm, rda);
133
+ }
134
+ tcg_temp_free_ptr(qm);
135
+
136
+ rdalo = tcg_temp_new_i32();
137
+ rdahi = tcg_temp_new_i32();
138
+ tcg_gen_extrl_i64_i32(rdalo, rda);
139
+ tcg_gen_extrh_i64_i32(rdahi, rda);
140
+ store_reg(s, a->rdalo, rdalo);
141
+ store_reg(s, a->rdahi, rdahi);
142
+ tcg_temp_free_i64(rda);
143
+ mve_update_eci(s);
82
+ return true;
144
+ return true;
83
+}
145
+}
84
+
146
+
85
+static bool v7m_handle_execute_nsc(ARMCPU *cpu)
147
static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn)
86
+{
87
+ /* Check whether this attempt to execute code in a Secure & NS-Callable
88
+ * memory region is for an SG instruction; if so, then emulate the
89
+ * effect of the SG instruction and return true. Otherwise pend
90
+ * the correct kind of exception and return false.
91
+ */
92
+ CPUARMState *env = &cpu->env;
93
+ ARMMMUIdx mmu_idx;
94
+ uint16_t insn;
95
+
96
+ /* We should never get here unless get_phys_addr_pmsav8() caused
97
+ * an exception for NS executing in S&NSC memory.
98
+ */
99
+ assert(!env->v7m.secure);
100
+ assert(arm_feature(env, ARM_FEATURE_M_SECURITY));
101
+
102
+ /* We want to do the MPU lookup as secure; work out what mmu_idx that is */
103
+ mmu_idx = arm_v7m_mmu_idx_for_secstate(env, true);
104
+
105
+ if (!v7m_read_half_insn(cpu, mmu_idx, env->regs[15], &insn)) {
106
+ return false;
107
+ }
108
+
109
+ if (!env->thumb) {
110
+ goto gen_invep;
111
+ }
112
+
113
+ if (insn != 0xe97f) {
114
+ /* Not an SG instruction first half (we choose the IMPDEF
115
+ * early-SG-check option).
116
+ */
117
+ goto gen_invep;
118
+ }
119
+
120
+ if (!v7m_read_half_insn(cpu, mmu_idx, env->regs[15] + 2, &insn)) {
121
+ return false;
122
+ }
123
+
124
+ if (insn != 0xe97f) {
125
+ /* Not an SG instruction second half (yes, both halves of the SG
126
+ * insn have the same hex value)
127
+ */
128
+ goto gen_invep;
129
+ }
130
+
131
+ /* OK, we have confirmed that we really have an SG instruction.
132
+ * We know we're NS in S memory so don't need to repeat those checks.
133
+ */
134
+ qemu_log_mask(CPU_LOG_INT, "...really an SG instruction at 0x%08" PRIx32
135
+ ", executing it\n", env->regs[15]);
136
+ env->regs[14] &= ~1;
137
+ switch_v7m_security_state(env, true);
138
+ xpsr_write(env, 0, XPSR_IT);
139
+ env->regs[15] += 4;
140
+ return true;
141
+
142
+gen_invep:
143
+ env->v7m.sfsr |= R_V7M_SFSR_INVEP_MASK;
144
+ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false);
145
+ qemu_log_mask(CPU_LOG_INT,
146
+ "...really SecureFault with SFSR.INVEP\n");
147
+ return false;
148
+}
149
+
150
void arm_v7m_cpu_do_interrupt(CPUState *cs)
151
{
148
{
152
ARMCPU *cpu = ARM_CPU(cs);
149
TCGv_ptr qd;
153
@@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs)
154
* the SG instruction have the same security attributes.)
155
* Everything else must generate an INVEP SecureFault, so we
156
* emulate the SG instruction here.
157
- * TODO: actually emulate SG.
158
*/
159
- env->v7m.sfsr |= R_V7M_SFSR_INVEP_MASK;
160
- armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false);
161
- qemu_log_mask(CPU_LOG_INT,
162
- "...really SecureFault with SFSR.INVEP\n");
163
+ if (v7m_handle_execute_nsc(cpu)) {
164
+ return;
165
+ }
166
break;
167
case M_FAKE_FSR_SFAULT:
168
/* Various flavours of SecureFault for attempts to execute or
169
--
150
--
170
2.7.4
151
2.20.1
171
152
172
153
diff view generated by jsdifflib
1
The code which implements the Thumb1 split BL/BLX instructions
1
The MVE extension to v8.1M includes some new shift instructions which
2
is guarded by a check on "not M or THUMB2". All we really need
2
sit entirely within the non-coprocessor part of the encoding space
3
to check here is "not THUMB2" (and we assume that elsewhere too,
3
and which operate only on general-purpose registers. They take up
4
eg in the ARCH(6T2) test that UNDEFs the Thumb2 insns).
4
the space which was previously UNPREDICTABLE MOVS and ORRS encodings
5
5
with Rm == 13 or 15.
6
This doesn't change behaviour because all M profile cores
6
7
have Thumb2 and so ARM_FEATURE_M implies ARM_FEATURE_THUMB2.
7
Implement the long shifts by immediate, which perform shifts on a
8
(v6M implements a very restricted subset of Thumb2, but we
8
pair of general-purpose registers treated as a 64-bit quantity, with
9
can cross that bridge when we get to it with appropriate
9
an immediate shift count between 1 and 32.
10
feature bits.)
10
11
Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for
12
the Rm==13,15 case, we need to explicitly emit code to UNDEF for the
13
cases where v8.1M now requires that. (Trying to change MOVS and ORRS
14
is too difficult, because the functions that generate the code are
15
shared between a dozen different kinds of arithmetic or logical
16
instruction for all A32, T16 and T32 encodings, and for some insns
17
and some encodings Rm==13,15 are valid.)
18
19
We make the helper functions we need for UQSHLL and SQSHLL take
20
a 32-bit value which the helper casts to int8_t because we'll need
21
these helpers also for the shift-by-register insns, where the shift
22
count might be < 0 or > 32.
11
23
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
24
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
25
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 1507556919-24992-6-git-send-email-peter.maydell@linaro.org
26
Message-id: 20210628135835.6690-16-peter.maydell@linaro.org
15
---
27
---
16
target/arm/translate.c | 3 +--
28
target/arm/helper-mve.h | 3 ++
17
1 file changed, 1 insertion(+), 2 deletions(-)
29
target/arm/translate.h | 1 +
18
30
target/arm/t32.decode | 28 +++++++++++++
31
target/arm/mve_helper.c | 10 +++++
32
target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++
33
5 files changed, 132 insertions(+)
34
35
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
36
index XXXXXXX..XXXXXXX 100644
37
--- a/target/arm/helper-mve.h
38
+++ b/target/arm/helper-mve.h
39
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
40
DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
41
42
DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32)
43
+
44
+DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
45
+DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
46
diff --git a/target/arm/translate.h b/target/arm/translate.h
47
index XXXXXXX..XXXXXXX 100644
48
--- a/target/arm/translate.h
49
+++ b/target/arm/translate.h
50
@@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
51
typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
52
typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
53
typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
54
+typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
55
56
/**
57
* arm_tbflags_from_tb:
58
diff --git a/target/arm/t32.decode b/target/arm/t32.decode
59
index XXXXXXX..XXXXXXX 100644
60
--- a/target/arm/t32.decode
61
+++ b/target/arm/t32.decode
62
@@ -XXX,XX +XXX,XX @@
63
&mcr !extern cp opc1 crn crm opc2 rt
64
&mcrr !extern cp opc1 crm rt rt2
65
66
+&mve_shl_ri rdalo rdahi shim
67
+
68
+# rdahi: bits [3:1] from insn, bit 0 is 1
69
+# rdalo: bits [3:1] from insn, bit 0 is 0
70
+%rdahi_9 9:3 !function=times_2_plus_1
71
+%rdalo_17 17:3 !function=times_2
72
+
73
# Data-processing (register)
74
75
%imm5_12_6 12:3 6:2
76
@@ -XXX,XX +XXX,XX @@
77
@S_xrr_shi ....... .... . rn:4 .... .... .. shty:2 rm:4 \
78
&s_rrr_shi shim=%imm5_12_6 s=1 rd=0
79
80
+@mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \
81
+ &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9
82
+
83
{
84
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
85
AND_rrri 1110101 0000 . .... 0 ... .... .... .... @s_rrr_shi
86
}
87
BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
88
{
89
+ # The v8.1M MVE shift insns overlap in encoding with MOVS/ORRS
90
+ # and are distinguished by having Rm==13 or 15. Those are UNPREDICTABLE
91
+ # cases for MOVS/ORRS. We decode the MVE cases first, ensuring that
92
+ # they explicitly call unallocated_encoding() for cases that must UNDEF
93
+ # (eg "using a new shift insn on a v8.1M CPU without MVE"), and letting
94
+ # the rest fall through (where ORR_rrri and MOV_rxri will end up
95
+ # handling them as r13 and r15 accesses with the same semantics as A32).
96
+ [
97
+ LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri
98
+ LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri
99
+ ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri
100
+
101
+ UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri
102
+ URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri
103
+ SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri
104
+ SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
105
+ ]
106
+
107
MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi
108
ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi
109
}
110
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
111
index XXXXXXX..XXXXXXX 100644
112
--- a/target/arm/mve_helper.c
113
+++ b/target/arm/mve_helper.c
114
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm,
115
mve_advance_vpt(env);
116
return rdm;
117
}
118
+
119
+uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
120
+{
121
+ return do_sqrshl_d(n, (int8_t)shift, false, &env->QF);
122
+}
123
+
124
+uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
125
+{
126
+ return do_uqrshl_d(n, (int8_t)shift, false, &env->QF);
127
+}
19
diff --git a/target/arm/translate.c b/target/arm/translate.c
128
diff --git a/target/arm/translate.c b/target/arm/translate.c
20
index XXXXXXX..XXXXXXX 100644
129
index XXXXXXX..XXXXXXX 100644
21
--- a/target/arm/translate.c
130
--- a/target/arm/translate.c
22
+++ b/target/arm/translate.c
131
+++ b/target/arm/translate.c
23
@@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
132
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a)
24
int conds;
133
return true;
25
int logic_cc;
134
}
26
135
27
- if (!(arm_dc_feature(s, ARM_FEATURE_THUMB2)
136
+/*
28
- || arm_dc_feature(s, ARM_FEATURE_M))) {
137
+ * v8.1M MVE wide-shifts
29
+ if (!arm_dc_feature(s, ARM_FEATURE_THUMB2)) {
138
+ */
30
/* Thumb-1 cores may need to treat bl and blx as a pair of
139
+static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a,
31
16-bit instructions to get correct prefetch abort behavior. */
140
+ WideShiftImmFn *fn)
32
insn = insn_hw1;
141
+{
142
+ TCGv_i64 rda;
143
+ TCGv_i32 rdalo, rdahi;
144
+
145
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
146
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
147
+ return false;
148
+ }
149
+ if (a->rdahi == 15) {
150
+ /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */
151
+ return false;
152
+ }
153
+ if (!dc_isar_feature(aa32_mve, s) ||
154
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
155
+ a->rdahi == 13) {
156
+ /* RdaHi == 13 is UNPREDICTABLE; we choose to UNDEF */
157
+ unallocated_encoding(s);
158
+ return true;
159
+ }
160
+
161
+ if (a->shim == 0) {
162
+ a->shim = 32;
163
+ }
164
+
165
+ rda = tcg_temp_new_i64();
166
+ rdalo = load_reg(s, a->rdalo);
167
+ rdahi = load_reg(s, a->rdahi);
168
+ tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
169
+
170
+ fn(rda, rda, a->shim);
171
+
172
+ tcg_gen_extrl_i64_i32(rdalo, rda);
173
+ tcg_gen_extrh_i64_i32(rdahi, rda);
174
+ store_reg(s, a->rdalo, rdalo);
175
+ store_reg(s, a->rdahi, rdahi);
176
+ tcg_temp_free_i64(rda);
177
+
178
+ return true;
179
+}
180
+
181
+static bool trans_ASRL_ri(DisasContext *s, arg_mve_shl_ri *a)
182
+{
183
+ return do_mve_shl_ri(s, a, tcg_gen_sari_i64);
184
+}
185
+
186
+static bool trans_LSLL_ri(DisasContext *s, arg_mve_shl_ri *a)
187
+{
188
+ return do_mve_shl_ri(s, a, tcg_gen_shli_i64);
189
+}
190
+
191
+static bool trans_LSRL_ri(DisasContext *s, arg_mve_shl_ri *a)
192
+{
193
+ return do_mve_shl_ri(s, a, tcg_gen_shri_i64);
194
+}
195
+
196
+static void gen_mve_sqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift)
197
+{
198
+ gen_helper_mve_sqshll(r, cpu_env, n, tcg_constant_i32(shift));
199
+}
200
+
201
+static bool trans_SQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a)
202
+{
203
+ return do_mve_shl_ri(s, a, gen_mve_sqshll);
204
+}
205
+
206
+static void gen_mve_uqshll(TCGv_i64 r, TCGv_i64 n, int64_t shift)
207
+{
208
+ gen_helper_mve_uqshll(r, cpu_env, n, tcg_constant_i32(shift));
209
+}
210
+
211
+static bool trans_UQSHLL_ri(DisasContext *s, arg_mve_shl_ri *a)
212
+{
213
+ return do_mve_shl_ri(s, a, gen_mve_uqshll);
214
+}
215
+
216
+static bool trans_SRSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
217
+{
218
+ return do_mve_shl_ri(s, a, gen_srshr64_i64);
219
+}
220
+
221
+static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
222
+{
223
+ return do_mve_shl_ri(s, a, gen_urshr64_i64);
224
+}
225
+
226
/*
227
* Multiply and multiply accumulate
228
*/
33
--
229
--
34
2.7.4
230
2.20.1
35
231
36
232
diff view generated by jsdifflib
1
Add the M profile secure MMU index values to the switch in
1
Implement the MVE long shifts by register, which perform shifts on a
2
get_a32_user_mem_index() so that LDRT/STRT work correctly
2
pair of general-purpose registers treated as a 64-bit quantity, with
3
rather than asserting at translate time.
3
the shift count in another general-purpose register, which might be
4
either positive or negative.
5
6
Like the long-shifts-by-immediate, these encodings sit in the space
7
that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15.
8
Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and
9
also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases),
10
we have to move the CSEL pattern into the same decodetree group.
4
11
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 1507556919-24992-2-git-send-email-peter.maydell@linaro.org
14
Message-id: 20210628135835.6690-17-peter.maydell@linaro.org
8
---
15
---
9
target/arm/translate.c | 4 ++++
16
target/arm/helper-mve.h | 6 +++
10
1 file changed, 4 insertions(+)
17
target/arm/translate.h | 1 +
11
18
target/arm/t32.decode | 16 +++++--
19
target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++
20
target/arm/translate.c | 69 ++++++++++++++++++++++++++++++
21
5 files changed, 182 insertions(+), 3 deletions(-)
22
23
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
24
index XXXXXXX..XXXXXXX 100644
25
--- a/target/arm/helper-mve.h
26
+++ b/target/arm/helper-mve.h
27
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
29
DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32)
30
31
+DEF_HELPER_FLAGS_3(mve_sshrl, TCG_CALL_NO_RWG, i64, env, i64, i32)
32
+DEF_HELPER_FLAGS_3(mve_ushll, TCG_CALL_NO_RWG, i64, env, i64, i32)
33
DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
34
DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
35
+DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32)
36
+DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
37
+DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32)
38
+DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
39
diff --git a/target/arm/translate.h b/target/arm/translate.h
40
index XXXXXXX..XXXXXXX 100644
41
--- a/target/arm/translate.h
42
+++ b/target/arm/translate.h
43
@@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
44
typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
45
typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
46
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
47
+typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32);
48
49
/**
50
* arm_tbflags_from_tb:
51
diff --git a/target/arm/t32.decode b/target/arm/t32.decode
52
index XXXXXXX..XXXXXXX 100644
53
--- a/target/arm/t32.decode
54
+++ b/target/arm/t32.decode
55
@@ -XXX,XX +XXX,XX @@
56
&mcrr !extern cp opc1 crm rt rt2
57
58
&mve_shl_ri rdalo rdahi shim
59
+&mve_shl_rr rdalo rdahi rm
60
61
# rdahi: bits [3:1] from insn, bit 0 is 1
62
# rdalo: bits [3:1] from insn, bit 0 is 0
63
@@ -XXX,XX +XXX,XX @@
64
65
@mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \
66
&mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9
67
+@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \
68
+ &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
69
70
{
71
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
72
@@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
73
URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri
74
SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri
75
SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
76
+
77
+ LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
78
+ ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
79
+ UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr
80
+ SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr
81
+ UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr
82
+ SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr
83
]
84
85
MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi
86
ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi
87
+
88
+ # v8.1M CSEL and friends
89
+ CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4
90
}
91
{
92
MVN_rxri 1110101 0011 . 1111 0 ... .... .... .... @s_rxr_shi
93
@@ -XXX,XX +XXX,XX @@ SBC_rrri 1110101 1011 . .... 0 ... .... .... .... @s_rrr_shi
94
}
95
RSB_rrri 1110101 1110 . .... 0 ... .... .... .... @s_rrr_shi
96
97
-# v8.1M CSEL and friends
98
-CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4
99
-
100
# Data-processing (register-shifted register)
101
102
MOV_rxrr 1111 1010 0 shty:2 s:1 rm:4 1111 rd:4 0000 rs:4 \
103
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
104
index XXXXXXX..XXXXXXX 100644
105
--- a/target/arm/mve_helper.c
106
+++ b/target/arm/mve_helper.c
107
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm,
108
return rdm;
109
}
110
111
+uint64_t HELPER(mve_sshrl)(CPUARMState *env, uint64_t n, uint32_t shift)
112
+{
113
+ return do_sqrshl_d(n, -(int8_t)shift, false, NULL);
114
+}
115
+
116
+uint64_t HELPER(mve_ushll)(CPUARMState *env, uint64_t n, uint32_t shift)
117
+{
118
+ return do_uqrshl_d(n, (int8_t)shift, false, NULL);
119
+}
120
+
121
uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
122
{
123
return do_sqrshl_d(n, (int8_t)shift, false, &env->QF);
124
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift)
125
{
126
return do_uqrshl_d(n, (int8_t)shift, false, &env->QF);
127
}
128
+
129
+uint64_t HELPER(mve_sqrshrl)(CPUARMState *env, uint64_t n, uint32_t shift)
130
+{
131
+ return do_sqrshl_d(n, -(int8_t)shift, true, &env->QF);
132
+}
133
+
134
+uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift)
135
+{
136
+ return do_uqrshl_d(n, (int8_t)shift, true, &env->QF);
137
+}
138
+
139
+/* Operate on 64-bit values, but saturate at 48 bits */
140
+static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift,
141
+ bool round, uint32_t *sat)
142
+{
143
+ if (shift <= -48) {
144
+ /* Rounding the sign bit always produces 0. */
145
+ if (round) {
146
+ return 0;
147
+ }
148
+ return src >> 63;
149
+ } else if (shift < 0) {
150
+ if (round) {
151
+ src >>= -shift - 1;
152
+ return (src >> 1) + (src & 1);
153
+ }
154
+ return src >> -shift;
155
+ } else if (shift < 48) {
156
+ int64_t val = src << shift;
157
+ int64_t extval = sextract64(val, 0, 48);
158
+ if (!sat || val == extval) {
159
+ return extval;
160
+ }
161
+ } else if (!sat || src == 0) {
162
+ return 0;
163
+ }
164
+
165
+ *sat = 1;
166
+ return (1ULL << 47) - (src >= 0);
167
+}
168
+
169
+/* Operate on 64-bit values, but saturate at 48 bits */
170
+static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift,
171
+ bool round, uint32_t *sat)
172
+{
173
+ uint64_t val, extval;
174
+
175
+ if (shift <= -(48 + round)) {
176
+ return 0;
177
+ } else if (shift < 0) {
178
+ if (round) {
179
+ val = src >> (-shift - 1);
180
+ val = (val >> 1) + (val & 1);
181
+ } else {
182
+ val = src >> -shift;
183
+ }
184
+ extval = extract64(val, 0, 48);
185
+ if (!sat || val == extval) {
186
+ return extval;
187
+ }
188
+ } else if (shift < 48) {
189
+ uint64_t val = src << shift;
190
+ uint64_t extval = extract64(val, 0, 48);
191
+ if (!sat || val == extval) {
192
+ return extval;
193
+ }
194
+ } else if (!sat || src == 0) {
195
+ return 0;
196
+ }
197
+
198
+ *sat = 1;
199
+ return MAKE_64BIT_MASK(0, 48);
200
+}
201
+
202
+uint64_t HELPER(mve_sqrshrl48)(CPUARMState *env, uint64_t n, uint32_t shift)
203
+{
204
+ return do_sqrshl48_d(n, -(int8_t)shift, true, &env->QF);
205
+}
206
+
207
+uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift)
208
+{
209
+ return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF);
210
+}
12
diff --git a/target/arm/translate.c b/target/arm/translate.c
211
diff --git a/target/arm/translate.c b/target/arm/translate.c
13
index XXXXXXX..XXXXXXX 100644
212
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/translate.c
213
--- a/target/arm/translate.c
15
+++ b/target/arm/translate.c
214
+++ b/target/arm/translate.c
16
@@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s)
215
@@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
17
case ARMMMUIdx_MPriv:
216
return do_mve_shl_ri(s, a, gen_urshr64_i64);
18
case ARMMMUIdx_MNegPri:
217
}
19
return arm_to_core_mmu_idx(ARMMMUIdx_MUser);
218
20
+ case ARMMMUIdx_MSUser:
219
+static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn)
21
+ case ARMMMUIdx_MSPriv:
220
+{
22
+ case ARMMMUIdx_MSNegPri:
221
+ TCGv_i64 rda;
23
+ return arm_to_core_mmu_idx(ARMMMUIdx_MSUser);
222
+ TCGv_i32 rdalo, rdahi;
24
case ARMMMUIdx_S2NS:
223
+
25
default:
224
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
26
g_assert_not_reached();
225
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
226
+ return false;
227
+ }
228
+ if (a->rdahi == 15) {
229
+ /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */
230
+ return false;
231
+ }
232
+ if (!dc_isar_feature(aa32_mve, s) ||
233
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
234
+ a->rdahi == 13 || a->rm == 13 || a->rm == 15 ||
235
+ a->rm == a->rdahi || a->rm == a->rdalo) {
236
+ /* These rdahi/rdalo/rm cases are UNPREDICTABLE; we choose to UNDEF */
237
+ unallocated_encoding(s);
238
+ return true;
239
+ }
240
+
241
+ rda = tcg_temp_new_i64();
242
+ rdalo = load_reg(s, a->rdalo);
243
+ rdahi = load_reg(s, a->rdahi);
244
+ tcg_gen_concat_i32_i64(rda, rdalo, rdahi);
245
+
246
+ /* The helper takes care of the sign-extension of the low 8 bits of Rm */
247
+ fn(rda, cpu_env, rda, cpu_R[a->rm]);
248
+
249
+ tcg_gen_extrl_i64_i32(rdalo, rda);
250
+ tcg_gen_extrh_i64_i32(rdahi, rda);
251
+ store_reg(s, a->rdalo, rdalo);
252
+ store_reg(s, a->rdahi, rdahi);
253
+ tcg_temp_free_i64(rda);
254
+
255
+ return true;
256
+}
257
+
258
+static bool trans_LSLL_rr(DisasContext *s, arg_mve_shl_rr *a)
259
+{
260
+ return do_mve_shl_rr(s, a, gen_helper_mve_ushll);
261
+}
262
+
263
+static bool trans_ASRL_rr(DisasContext *s, arg_mve_shl_rr *a)
264
+{
265
+ return do_mve_shl_rr(s, a, gen_helper_mve_sshrl);
266
+}
267
+
268
+static bool trans_UQRSHLL64_rr(DisasContext *s, arg_mve_shl_rr *a)
269
+{
270
+ return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll);
271
+}
272
+
273
+static bool trans_SQRSHRL64_rr(DisasContext *s, arg_mve_shl_rr *a)
274
+{
275
+ return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl);
276
+}
277
+
278
+static bool trans_UQRSHLL48_rr(DisasContext *s, arg_mve_shl_rr *a)
279
+{
280
+ return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll48);
281
+}
282
+
283
+static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a)
284
+{
285
+ return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48);
286
+}
287
+
288
/*
289
* Multiply and multiply accumulate
290
*/
27
--
291
--
28
2.7.4
292
2.20.1
29
293
30
294
diff view generated by jsdifflib
1
Refactor the Thumb decode to do the loads of the instruction words at
1
Implement the MVE shifts by immediate, which perform shifts
2
the top level rather than only loading the second half of a 32-bit
2
on a single general-purpose register.
3
Thumb insn in the middle of the decode.
3
4
4
These patterns overlap with the long-shift-by-immediates,
5
This is simple apart from the awkward case of Thumb1, where the
5
so we have to rearrange the grouping a little here.
6
BL/BLX prefix and suffix instructions live in what in Thumb2 is the
7
32-bit insn space. To handle these we decode enough to identify
8
whether we're looking at a prefix/suffix that we handle as a 16 bit
9
insn, or a prefix that we're going to merge with the following suffix
10
to consider as a 32 bit insn. The translation of the 16 bit cases
11
then moves from disas_thumb2_insn() to disas_thumb_insn().
12
13
The refactoring has the benefit that we don't need to pass the
14
CPUARMState* down into the decoder code any more, but the major
15
reason for doing this is that some Thumb instructions must be always
16
unconditional regardless of the IT state bits, so we need to know the
17
whole insn before we emit the "skip this insn if the IT bits and cond
18
state tell us to" code. (The always unconditional insns are BKPT,
19
HLT and SG; the last of these is 32 bits.)
20
6
21
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
22
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
23
Message-id: 1507556919-24992-7-git-send-email-peter.maydell@linaro.org
9
Message-id: 20210628135835.6690-18-peter.maydell@linaro.org
24
---
10
---
25
target/arm/translate.c | 178 ++++++++++++++++++++++++++++++-------------------
11
target/arm/helper-mve.h | 3 ++
26
1 file changed, 108 insertions(+), 70 deletions(-)
12
target/arm/translate.h | 1 +
27
13
target/arm/t32.decode | 31 ++++++++++++++-----
14
target/arm/mve_helper.c | 10 ++++++
15
target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++--
16
5 files changed, 104 insertions(+), 9 deletions(-)
17
18
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
19
index XXXXXXX..XXXXXXX 100644
20
--- a/target/arm/helper-mve.h
21
+++ b/target/arm/helper-mve.h
22
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32)
23
DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32)
24
DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32)
25
DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
26
+
27
+DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
28
+DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
29
diff --git a/target/arm/translate.h b/target/arm/translate.h
30
index XXXXXXX..XXXXXXX 100644
31
--- a/target/arm/translate.h
32
+++ b/target/arm/translate.h
33
@@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
34
typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
35
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
36
typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32);
37
+typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift);
38
39
/**
40
* arm_tbflags_from_tb:
41
diff --git a/target/arm/t32.decode b/target/arm/t32.decode
42
index XXXXXXX..XXXXXXX 100644
43
--- a/target/arm/t32.decode
44
+++ b/target/arm/t32.decode
45
@@ -XXX,XX +XXX,XX @@
46
47
&mve_shl_ri rdalo rdahi shim
48
&mve_shl_rr rdalo rdahi rm
49
+&mve_sh_ri rda shim
50
51
# rdahi: bits [3:1] from insn, bit 0 is 1
52
# rdalo: bits [3:1] from insn, bit 0 is 0
53
@@ -XXX,XX +XXX,XX @@
54
&mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9
55
@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \
56
&mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
57
+@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \
58
+ &mve_sh_ri shim=%imm5_12_6
59
60
{
61
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
62
@@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
63
# the rest fall through (where ORR_rrri and MOV_rxri will end up
64
# handling them as r13 and r15 accesses with the same semantics as A32).
65
[
66
- LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri
67
- LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri
68
- ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri
69
+ {
70
+ UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri
71
+ LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri
72
+ UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri
73
+ }
74
75
- UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri
76
- URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri
77
- SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri
78
- SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
79
+ {
80
+ URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri
81
+ LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri
82
+ URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri
83
+ }
84
+
85
+ {
86
+ SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri
87
+ ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri
88
+ SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri
89
+ }
90
+
91
+ {
92
+ SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri
93
+ SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
94
+ }
95
96
LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
97
ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
98
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
99
index XXXXXXX..XXXXXXX 100644
100
--- a/target/arm/mve_helper.c
101
+++ b/target/arm/mve_helper.c
102
@@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift)
103
{
104
return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF);
105
}
106
+
107
+uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
108
+{
109
+ return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
110
+}
111
+
112
+uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
113
+{
114
+ return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
115
+}
28
diff --git a/target/arm/translate.c b/target/arm/translate.c
116
diff --git a/target/arm/translate.c b/target/arm/translate.c
29
index XXXXXXX..XXXXXXX 100644
117
index XXXXXXX..XXXXXXX 100644
30
--- a/target/arm/translate.c
118
--- a/target/arm/translate.c
31
+++ b/target/arm/translate.c
119
+++ b/target/arm/translate.c
32
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
120
@@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
33
}
121
122
static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
123
{
124
- TCGv_i32 t = tcg_temp_new_i32();
125
+ TCGv_i32 t;
126
127
+ /* Handle shift by the input size for the benefit of trans_SRSHR_ri */
128
+ if (sh == 32) {
129
+ tcg_gen_movi_i32(d, 0);
130
+ return;
131
+ }
132
+ t = tcg_temp_new_i32();
133
tcg_gen_extract_i32(t, a, sh - 1, 1);
134
tcg_gen_sari_i32(d, a, sh);
135
tcg_gen_add_i32(d, d, t);
136
@@ -XXX,XX +XXX,XX @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
137
138
static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh)
139
{
140
- TCGv_i32 t = tcg_temp_new_i32();
141
+ TCGv_i32 t;
142
143
+ /* Handle shift by the input size for the benefit of trans_URSHR_ri */
144
+ if (sh == 32) {
145
+ tcg_gen_extract_i32(d, a, sh - 1, 1);
146
+ return;
147
+ }
148
+ t = tcg_temp_new_i32();
149
tcg_gen_extract_i32(t, a, sh - 1, 1);
150
tcg_gen_shri_i32(d, a, sh);
151
tcg_gen_add_i32(d, d, t);
152
@@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a)
153
return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48);
34
}
154
}
35
155
36
+static bool thumb_insn_is_16bit(DisasContext *s, uint32_t insn)
156
+static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn)
37
+{
157
+{
38
+ /* Return true if this is a 16 bit instruction. We must be precise
158
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
39
+ * about this (matching the decode). We assume that s->pc still
159
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
40
+ * points to the first 16 bits of the insn.
160
+ return false;
41
+ */
161
+ }
42
+ if ((insn >> 11) < 0x1d) {
162
+ if (!dc_isar_feature(aa32_mve, s) ||
43
+ /* Definitely a 16-bit instruction */
163
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
164
+ a->rda == 13 || a->rda == 15) {
165
+ /* These rda cases are UNPREDICTABLE; we choose to UNDEF */
166
+ unallocated_encoding(s);
44
+ return true;
167
+ return true;
45
+ }
168
+ }
46
+
169
+
47
+ /* Top five bits 0b11101 / 0b11110 / 0b11111 : this is the
170
+ if (a->shim == 0) {
48
+ * first half of a 32-bit Thumb insn. Thumb-1 cores might
171
+ a->shim = 32;
49
+ * end up actually treating this as two 16-bit insns, though,
172
+ }
50
+ * if it's half of a bl/blx pair that might span a page boundary.
173
+ fn(cpu_R[a->rda], cpu_R[a->rda], a->shim);
51
+ */
174
+
52
+ if (arm_dc_feature(s, ARM_FEATURE_THUMB2)) {
53
+ /* Thumb2 cores (including all M profile ones) always treat
54
+ * 32-bit insns as 32-bit.
55
+ */
56
+ return false;
57
+ }
58
+
59
+ if ((insn >> 11) == 0x1e && (s->pc < s->next_page_start - 3)) {
60
+ /* 0b1111_0xxx_xxxx_xxxx : BL/BLX prefix, and the suffix
61
+ * is not on the next page; we merge this into a 32-bit
62
+ * insn.
63
+ */
64
+ return false;
65
+ }
66
+ /* 0b1110_1xxx_xxxx_xxxx : BLX suffix (or UNDEF);
67
+ * 0b1111_1xxx_xxxx_xxxx : BL suffix;
68
+ * 0b1111_0xxx_xxxx_xxxx : BL/BLX prefix on the end of a page
69
+ * -- handle as single 16 bit insn
70
+ */
71
+ return true;
175
+ return true;
72
+}
176
+}
73
+
177
+
74
/* Return true if this is a Thumb-2 logical op. */
178
+static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
75
static int
179
+{
76
thumb2_logic_op(int op)
180
+ return do_mve_sh_ri(s, a, gen_urshr32_i32);
77
@@ -XXX,XX +XXX,XX @@ gen_thumb2_data_op(DisasContext *s, int op, int conds, uint32_t shifter_out,
181
+}
78
182
+
79
/* Translate a 32-bit thumb instruction. Returns nonzero if the instruction
183
+static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
80
is not legal. */
184
+{
81
-static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw1)
185
+ return do_mve_sh_ri(s, a, gen_srshr32_i32);
82
+static int disas_thumb2_insn(DisasContext *s, uint32_t insn)
186
+}
83
{
187
+
84
- uint32_t insn, imm, shift, offset;
188
+static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
85
+ uint32_t imm, shift, offset;
189
+{
86
uint32_t rd, rn, rm, rs;
190
+ gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift));
87
TCGv_i32 tmp;
191
+}
88
TCGv_i32 tmp2;
192
+
89
@@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw
193
+static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
90
int conds;
194
+{
91
int logic_cc;
195
+ return do_mve_sh_ri(s, a, gen_mve_sqshl);
92
196
+}
93
- if (!arm_dc_feature(s, ARM_FEATURE_THUMB2)) {
197
+
94
- /* Thumb-1 cores may need to treat bl and blx as a pair of
198
+static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
95
- 16-bit instructions to get correct prefetch abort behavior. */
199
+{
96
- insn = insn_hw1;
200
+ gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift));
97
- if ((insn & (1 << 12)) == 0) {
201
+}
98
- ARCH(5);
202
+
99
- /* Second half of blx. */
203
+static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
100
- offset = ((insn & 0x7ff) << 1);
204
+{
101
- tmp = load_reg(s, 14);
205
+ return do_mve_sh_ri(s, a, gen_mve_uqshl);
102
- tcg_gen_addi_i32(tmp, tmp, offset);
206
+}
103
- tcg_gen_andi_i32(tmp, tmp, 0xfffffffc);
207
+
104
-
208
/*
105
- tmp2 = tcg_temp_new_i32();
209
* Multiply and multiply accumulate
106
- tcg_gen_movi_i32(tmp2, s->pc | 1);
210
*/
107
- store_reg(s, 14, tmp2);
108
- gen_bx(s, tmp);
109
- return 0;
110
- }
111
- if (insn & (1 << 11)) {
112
- /* Second half of bl. */
113
- offset = ((insn & 0x7ff) << 1) | 1;
114
- tmp = load_reg(s, 14);
115
- tcg_gen_addi_i32(tmp, tmp, offset);
116
-
117
- tmp2 = tcg_temp_new_i32();
118
- tcg_gen_movi_i32(tmp2, s->pc | 1);
119
- store_reg(s, 14, tmp2);
120
- gen_bx(s, tmp);
121
- return 0;
122
- }
123
- if ((s->pc & ~TARGET_PAGE_MASK) == 0) {
124
- /* Instruction spans a page boundary. Implement it as two
125
- 16-bit instructions in case the second half causes an
126
- prefetch abort. */
127
- offset = ((int32_t)insn << 21) >> 9;
128
- tcg_gen_movi_i32(cpu_R[14], s->pc + 2 + offset);
129
- return 0;
130
- }
131
- /* Fall through to 32-bit decode. */
132
- }
133
-
134
- insn = arm_lduw_code(env, s->pc, s->sctlr_b);
135
- s->pc += 2;
136
- insn |= (uint32_t)insn_hw1 << 16;
137
-
138
+ /* The only 32 bit insn that's allowed for Thumb1 is the combined
139
+ * BL/BLX prefix and suffix.
140
+ */
141
if ((insn & 0xf800e800) != 0xf000e800) {
142
ARCH(6T2);
143
}
144
@@ -XXX,XX +XXX,XX @@ illegal_op:
145
return 1;
146
}
147
148
-static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
149
+static void disas_thumb_insn(DisasContext *s, uint32_t insn)
150
{
151
- uint32_t val, insn, op, rm, rn, rd, shift, cond;
152
+ uint32_t val, op, rm, rn, rd, shift, cond;
153
int32_t offset;
154
int i;
155
TCGv_i32 tmp;
156
TCGv_i32 tmp2;
157
TCGv_i32 addr;
158
159
- if (s->condexec_mask) {
160
- cond = s->condexec_cond;
161
- if (cond != 0x0e) { /* Skip conditional when condition is AL. */
162
- s->condlabel = gen_new_label();
163
- arm_gen_test_cc(cond ^ 1, s->condlabel);
164
- s->condjmp = 1;
165
- }
166
- }
167
-
168
- insn = arm_lduw_code(env, s->pc, s->sctlr_b);
169
- s->pc += 2;
170
-
171
switch (insn >> 12) {
172
case 0: case 1:
173
174
@@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
175
176
case 14:
177
if (insn & (1 << 11)) {
178
- if (disas_thumb2_insn(env, s, insn))
179
- goto undef32;
180
+ /* thumb_insn_is_16bit() ensures we can't get here for
181
+ * a Thumb2 CPU, so this must be a thumb1 split BL/BLX:
182
+ * 0b1110_1xxx_xxxx_xxxx : BLX suffix (or UNDEF)
183
+ */
184
+ assert(!arm_dc_feature(s, ARM_FEATURE_THUMB2));
185
+ ARCH(5);
186
+ offset = ((insn & 0x7ff) << 1);
187
+ tmp = load_reg(s, 14);
188
+ tcg_gen_addi_i32(tmp, tmp, offset);
189
+ tcg_gen_andi_i32(tmp, tmp, 0xfffffffc);
190
+
191
+ tmp2 = tcg_temp_new_i32();
192
+ tcg_gen_movi_i32(tmp2, s->pc | 1);
193
+ store_reg(s, 14, tmp2);
194
+ gen_bx(s, tmp);
195
break;
196
}
197
/* unconditional branch */
198
@@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s)
199
break;
200
201
case 15:
202
- if (disas_thumb2_insn(env, s, insn))
203
- goto undef32;
204
+ /* thumb_insn_is_16bit() ensures we can't get here for
205
+ * a Thumb2 CPU, so this must be a thumb1 split BL/BLX.
206
+ */
207
+ assert(!arm_dc_feature(s, ARM_FEATURE_THUMB2));
208
+
209
+ if (insn & (1 << 11)) {
210
+ /* 0b1111_1xxx_xxxx_xxxx : BL suffix */
211
+ offset = ((insn & 0x7ff) << 1) | 1;
212
+ tmp = load_reg(s, 14);
213
+ tcg_gen_addi_i32(tmp, tmp, offset);
214
+
215
+ tmp2 = tcg_temp_new_i32();
216
+ tcg_gen_movi_i32(tmp2, s->pc | 1);
217
+ store_reg(s, 14, tmp2);
218
+ gen_bx(s, tmp);
219
+ } else {
220
+ /* 0b1111_0xxx_xxxx_xxxx : BL/BLX prefix */
221
+ uint32_t uoffset = ((int32_t)insn << 21) >> 9;
222
+
223
+ tcg_gen_movi_i32(cpu_R[14], s->pc + 2 + uoffset);
224
+ }
225
break;
226
}
227
return;
228
-undef32:
229
- gen_exception_insn(s, 4, EXCP_UDEF, syn_uncategorized(),
230
- default_exception_el(s));
231
- return;
232
illegal_op:
233
undef:
234
gen_exception_insn(s, 2, EXCP_UDEF, syn_uncategorized(),
235
@@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
236
{
237
DisasContext *dc = container_of(dcbase, DisasContext, base);
238
CPUARMState *env = cpu->env_ptr;
239
+ uint32_t insn;
240
+ bool is_16bit;
241
242
if (arm_pre_translate_insn(dc)) {
243
return;
244
}
245
246
- disas_thumb_insn(env, dc);
247
+ insn = arm_lduw_code(env, dc->pc, dc->sctlr_b);
248
+ is_16bit = thumb_insn_is_16bit(dc, insn);
249
+ dc->pc += 2;
250
+ if (!is_16bit) {
251
+ uint32_t insn2 = arm_lduw_code(env, dc->pc, dc->sctlr_b);
252
+
253
+ insn = insn << 16 | insn2;
254
+ dc->pc += 2;
255
+ }
256
+
257
+ if (dc->condexec_mask) {
258
+ uint32_t cond = dc->condexec_cond;
259
+
260
+ if (cond != 0x0e) { /* Skip conditional when condition is AL. */
261
+ dc->condlabel = gen_new_label();
262
+ arm_gen_test_cc(cond ^ 1, dc->condlabel);
263
+ dc->condjmp = 1;
264
+ }
265
+ }
266
+
267
+ if (is_16bit) {
268
+ disas_thumb_insn(dc, insn);
269
+ } else {
270
+ disas_thumb2_insn(dc, insn);
271
+ }
272
273
/* Advance the Thumb condexec condition. */
274
if (dc->condexec_mask) {
275
--
211
--
276
2.7.4
212
2.20.1
277
213
278
214
diff view generated by jsdifflib
1
A few Thumb instructions are always unconditional even inside an
1
Implement the MVE shifts by register, which perform
2
IT block (as opposed to being UNPREDICTABLE if used inside an
2
shifts on a single general-purpose register.
3
IT block): BKPT, the v8M SG instruction, and the A profile
4
HLT (debug halt) instruction.
5
6
This means we need to suppress the jump-over-instruction-on-condfail
7
code generation (though the IT state still advances as usual and
8
subsequent insns in the IT block may be conditional).
9
3
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 1507556919-24992-9-git-send-email-peter.maydell@linaro.org
6
Message-id: 20210628135835.6690-19-peter.maydell@linaro.org
13
---
7
---
14
target/arm/translate.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
8
target/arm/helper-mve.h | 2 ++
15
1 file changed, 47 insertions(+), 1 deletion(-)
9
target/arm/translate.h | 1 +
10
target/arm/t32.decode | 18 ++++++++++++++----
11
target/arm/mve_helper.c | 10 ++++++++++
12
target/arm/translate.c | 30 ++++++++++++++++++++++++++++++
13
5 files changed, 57 insertions(+), 4 deletions(-)
16
14
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/helper-mve.h
18
+++ b/target/arm/helper-mve.h
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
20
21
DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
22
DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
23
+DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
24
+DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32)
25
diff --git a/target/arm/translate.h b/target/arm/translate.h
26
index XXXXXXX..XXXXXXX 100644
27
--- a/target/arm/translate.h
28
+++ b/target/arm/translate.h
29
@@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
30
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
31
typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32);
32
typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift);
33
+typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
34
35
/**
36
* arm_tbflags_from_tb:
37
diff --git a/target/arm/t32.decode b/target/arm/t32.decode
38
index XXXXXXX..XXXXXXX 100644
39
--- a/target/arm/t32.decode
40
+++ b/target/arm/t32.decode
41
@@ -XXX,XX +XXX,XX @@
42
&mve_shl_ri rdalo rdahi shim
43
&mve_shl_rr rdalo rdahi rm
44
&mve_sh_ri rda shim
45
+&mve_sh_rr rda rm
46
47
# rdahi: bits [3:1] from insn, bit 0 is 1
48
# rdalo: bits [3:1] from insn, bit 0 is 0
49
@@ -XXX,XX +XXX,XX @@
50
&mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
51
@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \
52
&mve_sh_ri shim=%imm5_12_6
53
+@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr
54
55
{
56
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
57
@@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
58
SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
59
}
60
61
- LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
62
- ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
63
- UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr
64
- SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr
65
+ {
66
+ UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr
67
+ LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
68
+ UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr
69
+ }
70
+
71
+ {
72
+ SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr
73
+ ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
74
+ SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr
75
+ }
76
+
77
UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr
78
SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr
79
]
80
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
81
index XXXXXXX..XXXXXXX 100644
82
--- a/target/arm/mve_helper.c
83
+++ b/target/arm/mve_helper.c
84
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
85
{
86
return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
87
}
88
+
89
+uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift)
90
+{
91
+ return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF);
92
+}
93
+
94
+uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift)
95
+{
96
+ return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF);
97
+}
17
diff --git a/target/arm/translate.c b/target/arm/translate.c
98
diff --git a/target/arm/translate.c b/target/arm/translate.c
18
index XXXXXXX..XXXXXXX 100644
99
index XXXXXXX..XXXXXXX 100644
19
--- a/target/arm/translate.c
100
--- a/target/arm/translate.c
20
+++ b/target/arm/translate.c
101
+++ b/target/arm/translate.c
21
@@ -XXX,XX +XXX,XX @@ static void arm_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
102
@@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
22
in init_disas_context by adjusting max_insns. */
103
return do_mve_sh_ri(s, a, gen_mve_uqshl);
23
}
104
}
24
105
25
+static bool thumb_insn_is_unconditional(DisasContext *s, uint32_t insn)
106
+static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn)
26
+{
107
+{
27
+ /* Return true if this Thumb insn is always unconditional,
108
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
28
+ * even inside an IT block. This is true of only a very few
109
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
29
+ * instructions: BKPT, HLT, and SG.
110
+ return false;
30
+ *
111
+ }
31
+ * A larger class of instructions are UNPREDICTABLE if used
112
+ if (!dc_isar_feature(aa32_mve, s) ||
32
+ * inside an IT block; we do not need to detect those here, because
113
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
33
+ * what we do by default (perform the cc check and update the IT
114
+ a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 ||
34
+ * bits state machine) is a permitted CONSTRAINED UNPREDICTABLE
115
+ a->rm == a->rda) {
35
+ * choice for those situations.
116
+ /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */
36
+ *
117
+ unallocated_encoding(s);
37
+ * insn is either a 16-bit or a 32-bit instruction; the two are
38
+ * distinguishable because for the 16-bit case the top 16 bits
39
+ * are zeroes, and that isn't a valid 32-bit encoding.
40
+ */
41
+ if ((insn & 0xffffff00) == 0xbe00) {
42
+ /* BKPT */
43
+ return true;
118
+ return true;
44
+ }
119
+ }
45
+
120
+
46
+ if ((insn & 0xffffffc0) == 0xba80 && arm_dc_feature(s, ARM_FEATURE_V8) &&
121
+ /* The helper takes care of the sign-extension of the low 8 bits of Rm */
47
+ !arm_dc_feature(s, ARM_FEATURE_M)) {
122
+ fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]);
48
+ /* HLT: v8A only. This is unconditional even when it is going to
123
+ return true;
49
+ * UNDEF; see the v8A ARM ARM DDI0487B.a H3.3.
50
+ * For v7 cores this was a plain old undefined encoding and so
51
+ * honours its cc check. (We might be using the encoding as
52
+ * a semihosting trap, but we don't change the cc check behaviour
53
+ * on that account, because a debugger connected to a real v7A
54
+ * core and emulating semihosting traps by catching the UNDEF
55
+ * exception would also only see cases where the cc check passed.
56
+ * No guest code should be trying to do a HLT semihosting trap
57
+ * in an IT block anyway.
58
+ */
59
+ return true;
60
+ }
61
+
62
+ if (insn == 0xe97fe97f && arm_dc_feature(s, ARM_FEATURE_V8) &&
63
+ arm_dc_feature(s, ARM_FEATURE_M)) {
64
+ /* SG: v8M only */
65
+ return true;
66
+ }
67
+
68
+ return false;
69
+}
124
+}
70
+
125
+
71
static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
126
+static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a)
72
{
127
+{
73
DisasContext *dc = container_of(dcbase, DisasContext, base);
128
+ return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr);
74
@@ -XXX,XX +XXX,XX @@ static void thumb_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
129
+}
75
dc->pc += 2;
130
+
76
}
131
+static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a)
77
132
+{
78
- if (dc->condexec_mask) {
133
+ return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl);
79
+ if (dc->condexec_mask && !thumb_insn_is_unconditional(dc, insn)) {
134
+}
80
uint32_t cond = dc->condexec_cond;
135
+
81
136
/*
82
if (cond != 0x0e) { /* Skip conditional when condition is AL. */
137
* Multiply and multiply accumulate
138
*/
83
--
139
--
84
2.7.4
140
2.20.1
85
141
86
142
diff view generated by jsdifflib