[Qemu-devel] [PULL 0/6] target-arm queue
[PULL 00/24] target-arm queue
1
Last lot of patches for arm before softfreeze tomorrow...
1
The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df:
2
2
3
thanks
3
Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100)
4
-- PMM
5
6
The following changes since commit ef3a6af5e789ff078d1fef880f9dfb6adf18e8f1:
7
8
Merge remote-tracking branch 'remotes/kraxel/tags/vga-20181029-pull-request' into staging (2018-10-29 12:59:15 +0000)
9
4
10
are available in the Git repository at:
5
are available in the Git repository at:
11
6
12
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20181029
7
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702
13
8
14
for you to fetch changes up to 20cf5663734310a282e27b7389bc9f53ffe227e6:
9
for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8:
15
10
16
tests/boot-serial-test: Add microbit board testcase (2018-10-29 15:19:48 +0000)
11
target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100)
17
12
18
----------------------------------------------------------------
13
----------------------------------------------------------------
19
target-arm queue:
14
target-arm queue:
20
* microbit: Add the UART to our nRF51 SoC model
15
* more MVE instructions
21
* Add a virtual Xilinx Versal board "xlnx-versal-virt"
16
* hw/gpio/gpio_pwr: use shutdown function for reboot
22
* hw/arm/virt: Set VIRT_COMPAT_3_0 compat
17
* target/arm: Check NaN mode before silencing NaN
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
23
21
24
----------------------------------------------------------------
22
----------------------------------------------------------------
25
Edgar E. Iglesias (2):
23
Joe Komlodi (1):
26
hw/arm: versal: Add a model of Xilinx Versal SoC
24
target/arm: Check NaN mode before silencing NaN
27
hw/arm: versal: Add a virtual Xilinx Versal board
28
25
29
Eric Auger (1):
26
Maxim Uvarov (1):
30
hw/arm/virt: Set VIRT_COMPAT_3_0 compat
27
hw/gpio/gpio_pwr: use shutdown function for reboot
31
28
32
Julia Suvorova (3):
29
Nolan Leake (1):
33
hw/char: Implement nRF51 SoC UART
30
hw/arm: Add basic power management to raspi.
34
hw/arm/nrf51_soc: Connect UART to nRF51 SoC
35
tests/boot-serial-test: Add microbit board testcase
36
31
37
hw/arm/Makefile.objs | 1 +
32
Patrick Venture (2):
38
hw/char/Makefile.objs | 1 +
33
docs/system/arm: Add quanta-q7l1-bmc reference
39
include/hw/arm/nrf51_soc.h | 3 +
34
docs/system/arm: Add quanta-gbs-bmc reference
40
include/hw/arm/xlnx-versal.h | 122 +++++++++
41
include/hw/char/nrf51_uart.h | 78 ++++++
42
hw/arm/microbit.c | 2 +
43
hw/arm/nrf51_soc.c | 20 ++
44
hw/arm/virt.c | 4 +
45
hw/arm/xlnx-versal-virt.c | 493 ++++++++++++++++++++++++++++++++++++
46
hw/arm/xlnx-versal.c | 323 +++++++++++++++++++++++
47
hw/char/nrf51_uart.c | 330 ++++++++++++++++++++++++
48
tests/boot-serial-test.c | 19 ++
49
default-configs/aarch64-softmmu.mak | 1 +
50
hw/char/trace-events | 4 +
51
14 files changed, 1401 insertions(+)
52
create mode 100644 include/hw/arm/xlnx-versal.h
53
create mode 100644 include/hw/char/nrf51_uart.h
54
create mode 100644 hw/arm/xlnx-versal-virt.c
55
create mode 100644 hw/arm/xlnx-versal.c
56
create mode 100644 hw/char/nrf51_uart.c
57
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
[PULL 01/24] docs/system/arm: Add quanta-q7l1-bmc reference
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
[PULL 02/24] docs/system/arm: Add quanta-gbs-bmc reference
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
[Qemu-devel] [PULL 4/6] hw/char: Implement nRF51 SoC UART
[PULL 03/24] hw/arm: Add basic power management to raspi.
1
From: Julia Suvorova via Qemu-devel <qemu-devel@nongnu.org>
1
From: Nolan Leake <nolan@sigbus.net>
2
2
3
Not implemented: CTS/NCTS, PSEL*.
3
This is just enough to make reboot and poweroff work. Works for
4
4
linux, u-boot, and the arm trusted firmware. Not tested, but should
5
Signed-off-by: Julia Suvorova <jusual@mail.ru>
5
work for plan9, and bare-metal/hobby OSes, since they seem to generally
6
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
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/]
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
---
18
---
9
hw/char/Makefile.objs | 1 +
19
include/hw/arm/bcm2835_peripherals.h | 3 +-
10
include/hw/char/nrf51_uart.h | 78 +++++++++
20
include/hw/misc/bcm2835_powermgt.h | 29 +++++
11
hw/char/nrf51_uart.c | 330 +++++++++++++++++++++++++++++++++++
21
hw/arm/bcm2835_peripherals.c | 13 ++-
12
hw/char/trace-events | 4 +
22
hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++
13
4 files changed, 413 insertions(+)
23
hw/misc/meson.build | 1 +
14
create mode 100644 include/hw/char/nrf51_uart.h
24
5 files changed, 204 insertions(+), 2 deletions(-)
15
create mode 100644 hw/char/nrf51_uart.c
25
create mode 100644 include/hw/misc/bcm2835_powermgt.h
16
26
create mode 100644 hw/misc/bcm2835_powermgt.c
17
diff --git a/hw/char/Makefile.objs b/hw/char/Makefile.objs
27
28
diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h
18
index XXXXXXX..XXXXXXX 100644
29
index XXXXXXX..XXXXXXX 100644
19
--- a/hw/char/Makefile.objs
30
--- a/include/hw/arm/bcm2835_peripherals.h
20
+++ b/hw/char/Makefile.objs
31
+++ b/include/hw/arm/bcm2835_peripherals.h
21
@@ -XXX,XX +XXX,XX @@
32
@@ -XXX,XX +XXX,XX @@
22
common-obj-$(CONFIG_IPACK) += ipoctal232.o
33
#include "hw/misc/bcm2835_mphi.h"
23
common-obj-$(CONFIG_ESCC) += escc.o
34
#include "hw/misc/bcm2835_thermal.h"
24
+common-obj-$(CONFIG_NRF51_SOC) += nrf51_uart.o
35
#include "hw/misc/bcm2835_cprman.h"
25
common-obj-$(CONFIG_PARALLEL) += parallel.o
36
+#include "hw/misc/bcm2835_powermgt.h"
26
common-obj-$(CONFIG_PARALLEL) += parallel-isa.o
37
#include "hw/sd/sdhci.h"
27
common-obj-$(CONFIG_PL011) += pl011.o
38
#include "hw/sd/bcm2835_sdhost.h"
28
diff --git a/include/hw/char/nrf51_uart.h b/include/hw/char/nrf51_uart.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
29
new file mode 100644
50
new file mode 100644
30
index XXXXXXX..XXXXXXX
51
index XXXXXXX..XXXXXXX
31
--- /dev/null
52
--- /dev/null
32
+++ b/include/hw/char/nrf51_uart.h
53
+++ b/include/hw/misc/bcm2835_powermgt.h
33
@@ -XXX,XX +XXX,XX @@
54
@@ -XXX,XX +XXX,XX @@
34
+/*
55
+/*
35
+ * nRF51 SoC UART emulation
56
+ * BCM2835 Power Management emulation
36
+ *
57
+ *
37
+ * Copyright (c) 2018 Julia Suvorova <jusual@mail.ru>
58
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
38
+ *
59
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
39
+ * This program is free software; you can redistribute it and/or modify
60
+ *
40
+ * it under the terms of the GNU General Public License version 2 or
61
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
41
+ * (at your option) any later version.
62
+ * See the COPYING file in the top-level directory.
42
+ */
63
+ */
43
+
64
+
44
+#ifndef NRF51_UART_H
65
+#ifndef BCM2835_POWERMGT_H
45
+#define NRF51_UART_H
66
+#define BCM2835_POWERMGT_H
46
+
67
+
47
+#include "hw/sysbus.h"
68
+#include "hw/sysbus.h"
48
+#include "chardev/char-fe.h"
69
+#include "qom/object.h"
49
+#include "hw/registerfields.h"
70
+
50
+
71
+#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt"
51
+#define UART_FIFO_LENGTH 6
72
+OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT)
52
+#define UART_BASE 0x40002000
73
+
53
+#define UART_SIZE 0x1000
74
+struct BCM2835PowerMgtState {
54
+
75
+ SysBusDevice busdev;
55
+#define TYPE_NRF51_UART "nrf51_soc.uart"
56
+#define NRF51_UART(obj) OBJECT_CHECK(NRF51UARTState, (obj), TYPE_NRF51_UART)
57
+
58
+REG32(UART_STARTRX, 0x000)
59
+REG32(UART_STOPRX, 0x004)
60
+REG32(UART_STARTTX, 0x008)
61
+REG32(UART_STOPTX, 0x00C)
62
+REG32(UART_SUSPEND, 0x01C)
63
+
64
+REG32(UART_CTS, 0x100)
65
+REG32(UART_NCTS, 0x104)
66
+REG32(UART_RXDRDY, 0x108)
67
+REG32(UART_TXDRDY, 0x11C)
68
+REG32(UART_ERROR, 0x124)
69
+REG32(UART_RXTO, 0x144)
70
+
71
+REG32(UART_INTEN, 0x300)
72
+ FIELD(UART_INTEN, CTS, 0, 1)
73
+ FIELD(UART_INTEN, NCTS, 1, 1)
74
+ FIELD(UART_INTEN, RXDRDY, 2, 1)
75
+ FIELD(UART_INTEN, TXDRDY, 7, 1)
76
+ FIELD(UART_INTEN, ERROR, 9, 1)
77
+ FIELD(UART_INTEN, RXTO, 17, 1)
78
+REG32(UART_INTENSET, 0x304)
79
+REG32(UART_INTENCLR, 0x308)
80
+REG32(UART_ERRORSRC, 0x480)
81
+REG32(UART_ENABLE, 0x500)
82
+REG32(UART_PSELRTS, 0x508)
83
+REG32(UART_PSELTXD, 0x50C)
84
+REG32(UART_PSELCTS, 0x510)
85
+REG32(UART_PSELRXD, 0x514)
86
+REG32(UART_RXD, 0x518)
87
+REG32(UART_TXD, 0x51C)
88
+REG32(UART_BAUDRATE, 0x524)
89
+REG32(UART_CONFIG, 0x56C)
90
+
91
+typedef struct NRF51UARTState {
92
+ SysBusDevice parent_obj;
93
+
94
+ MemoryRegion iomem;
76
+ MemoryRegion iomem;
95
+ CharBackend chr;
77
+
96
+ qemu_irq irq;
78
+ uint32_t rstc;
97
+ guint watch_tag;
79
+ uint32_t rsts;
98
+
80
+ uint32_t wdog;
99
+ uint8_t rx_fifo[UART_FIFO_LENGTH];
81
+};
100
+ unsigned int rx_fifo_pos;
101
+ unsigned int rx_fifo_len;
102
+
103
+ uint32_t reg[0x56C];
104
+
105
+ bool rx_started;
106
+ bool tx_started;
107
+ bool pending_tx_byte;
108
+ bool enabled;
109
+} NRF51UARTState;
110
+
82
+
111
+#endif
83
+#endif
112
diff --git a/hw/char/nrf51_uart.c b/hw/char/nrf51_uart.c
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
113
new file mode 100644
118
new file mode 100644
114
index XXXXXXX..XXXXXXX
119
index XXXXXXX..XXXXXXX
115
--- /dev/null
120
--- /dev/null
116
+++ b/hw/char/nrf51_uart.c
121
+++ b/hw/misc/bcm2835_powermgt.c
117
@@ -XXX,XX +XXX,XX @@
122
@@ -XXX,XX +XXX,XX @@
118
+/*
123
+/*
119
+ * nRF51 SoC UART emulation
124
+ * BCM2835 Power Management emulation
120
+ *
125
+ *
121
+ * See nRF51 Series Reference Manual, "29 Universal Asynchronous
126
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
122
+ * Receiver/Transmitter" for hardware specifications:
127
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
123
+ * http://infocenter.nordicsemi.com/pdf/nRF51_RM_v3.0.pdf
128
+ *
124
+ *
129
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
125
+ * Copyright (c) 2018 Julia Suvorova <jusual@mail.ru>
130
+ * See the COPYING file in the top-level directory.
126
+ *
127
+ * This program is free software; you can redistribute it and/or modify
128
+ * it under the terms of the GNU General Public License version 2 or
129
+ * (at your option) any later version.
130
+ */
131
+ */
131
+
132
+
132
+#include "qemu/osdep.h"
133
+#include "qemu/osdep.h"
133
+#include "qemu/log.h"
134
+#include "qemu/log.h"
134
+#include "hw/char/nrf51_uart.h"
135
+#include "qemu/module.h"
135
+#include "trace.h"
136
+#include "hw/misc/bcm2835_powermgt.h"
136
+
137
+#include "migration/vmstate.h"
137
+static void nrf51_uart_update_irq(NRF51UARTState *s)
138
+#include "sysemu/runstate.h"
138
+{
139
+
139
+ bool irq = false;
140
+#define PASSWORD 0x5a000000
140
+
141
+#define PASSWORD_MASK 0xff000000
141
+ irq |= (s->reg[R_UART_RXDRDY] &&
142
+
142
+ (s->reg[R_UART_INTEN] & R_UART_INTEN_RXDRDY_MASK));
143
+#define R_RSTC 0x1c
143
+ irq |= (s->reg[R_UART_TXDRDY] &&
144
+#define V_RSTC_RESET 0x20
144
+ (s->reg[R_UART_INTEN] & R_UART_INTEN_TXDRDY_MASK));
145
+#define R_RSTS 0x20
145
+ irq |= (s->reg[R_UART_ERROR] &&
146
+#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */
146
+ (s->reg[R_UART_INTEN] & R_UART_INTEN_ERROR_MASK));
147
+#define R_WDOG 0x24
147
+ irq |= (s->reg[R_UART_RXTO] &&
148
+
148
+ (s->reg[R_UART_INTEN] & R_UART_INTEN_RXTO_MASK));
149
+static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset,
149
+
150
+ unsigned size)
150
+ qemu_set_irq(s->irq, irq);
151
+{
151
+}
152
+ BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque;
152
+
153
+ uint32_t res = 0;
153
+static uint64_t uart_read(void *opaque, hwaddr addr, unsigned int size)
154
+
154
+{
155
+ switch (offset) {
155
+ NRF51UARTState *s = NRF51_UART(opaque);
156
+ case R_RSTC:
156
+ uint64_t r;
157
+ res = s->rstc;
157
+
158
+ break;
158
+ if (!s->enabled) {
159
+ case R_RSTS:
159
+ return 0;
160
+ res = s->rsts;
160
+ }
161
+ break;
161
+
162
+ case R_WDOG:
162
+ switch (addr) {
163
+ res = s->wdog;
163
+ case A_UART_RXD:
164
+ break;
164
+ r = s->rx_fifo[s->rx_fifo_pos];
165
+
165
+ if (s->rx_started && s->rx_fifo_len) {
166
+ default:
166
+ s->rx_fifo_pos = (s->rx_fifo_pos + 1) % UART_FIFO_LENGTH;
167
+ qemu_log_mask(LOG_UNIMP,
167
+ s->rx_fifo_len--;
168
+ "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx
168
+ if (s->rx_fifo_len) {
169
+ "\n", offset);
169
+ s->reg[R_UART_RXDRDY] = 1;
170
+ res = 0;
170
+ nrf51_uart_update_irq(s);
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);
171
+ }
200
+ }
172
+ qemu_chr_fe_accept_input(&s->chr);
173
+ }
201
+ }
174
+ break;
202
+ break;
175
+ case A_UART_INTENSET:
203
+ case R_RSTS:
176
+ case A_UART_INTENCLR:
204
+ qemu_log_mask(LOG_UNIMP,
177
+ case A_UART_INTEN:
205
+ "bcm2835_powermgt_write: RSTS\n");
178
+ r = s->reg[R_UART_INTEN];
206
+ s->rsts = value;
179
+ break;
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
+
180
+ default:
214
+ default:
181
+ r = s->reg[addr / 4];
215
+ qemu_log_mask(LOG_UNIMP,
182
+ break;
216
+ "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx
183
+ }
217
+ "\n", offset);
184
+
218
+ break;
185
+ trace_nrf51_uart_read(addr, r, size);
219
+ }
186
+
220
+}
187
+ return r;
221
+
188
+}
222
+static const MemoryRegionOps bcm2835_powermgt_ops = {
189
+
223
+ .read = bcm2835_powermgt_read,
190
+static gboolean uart_transmit(GIOChannel *chan, GIOCondition cond, void *opaque)
224
+ .write = bcm2835_powermgt_write,
191
+{
225
+ .endianness = DEVICE_NATIVE_ENDIAN,
192
+ NRF51UARTState *s = NRF51_UART(opaque);
226
+ .impl.min_access_size = 4,
193
+ int r;
227
+ .impl.max_access_size = 4,
194
+ uint8_t c = s->reg[R_UART_TXD];
228
+};
195
+
229
+
196
+ s->watch_tag = 0;
230
+static const VMStateDescription vmstate_bcm2835_powermgt = {
197
+
231
+ .name = TYPE_BCM2835_POWERMGT,
198
+ r = qemu_chr_fe_write(&s->chr, &c, 1);
232
+ .version_id = 1,
199
+ if (r <= 0) {
233
+ .minimum_version_id = 1,
200
+ s->watch_tag = qemu_chr_fe_add_watch(&s->chr, G_IO_OUT | G_IO_HUP,
201
+ uart_transmit, s);
202
+ if (!s->watch_tag) {
203
+ /* The hardware has no transmit error reporting,
204
+ * so silently drop the byte
205
+ */
206
+ goto buffer_drained;
207
+ }
208
+ return FALSE;
209
+ }
210
+
211
+buffer_drained:
212
+ s->reg[R_UART_TXDRDY] = 1;
213
+ s->pending_tx_byte = false;
214
+ return FALSE;
215
+}
216
+
217
+static void uart_cancel_transmit(NRF51UARTState *s)
218
+{
219
+ if (s->watch_tag) {
220
+ g_source_remove(s->watch_tag);
221
+ s->watch_tag = 0;
222
+ }
223
+}
224
+
225
+static void uart_write(void *opaque, hwaddr addr,
226
+ uint64_t value, unsigned int size)
227
+{
228
+ NRF51UARTState *s = NRF51_UART(opaque);
229
+
230
+ trace_nrf51_uart_write(addr, value, size);
231
+
232
+ if (!s->enabled && (addr != A_UART_ENABLE)) {
233
+ return;
234
+ }
235
+
236
+ switch (addr) {
237
+ case A_UART_TXD:
238
+ if (!s->pending_tx_byte && s->tx_started) {
239
+ s->reg[R_UART_TXD] = value;
240
+ s->pending_tx_byte = true;
241
+ uart_transmit(NULL, G_IO_OUT, s);
242
+ }
243
+ break;
244
+ case A_UART_INTEN:
245
+ s->reg[R_UART_INTEN] = value;
246
+ break;
247
+ case A_UART_INTENSET:
248
+ s->reg[R_UART_INTEN] |= value;
249
+ break;
250
+ case A_UART_INTENCLR:
251
+ s->reg[R_UART_INTEN] &= ~value;
252
+ break;
253
+ case A_UART_TXDRDY ... A_UART_RXTO:
254
+ s->reg[addr / 4] = value;
255
+ break;
256
+ case A_UART_ERRORSRC:
257
+ s->reg[addr / 4] &= ~value;
258
+ break;
259
+ case A_UART_RXD:
260
+ break;
261
+ case A_UART_RXDRDY:
262
+ if (value == 0) {
263
+ s->reg[R_UART_RXDRDY] = 0;
264
+ }
265
+ break;
266
+ case A_UART_STARTTX:
267
+ if (value == 1) {
268
+ s->tx_started = true;
269
+ }
270
+ break;
271
+ case A_UART_STARTRX:
272
+ if (value == 1) {
273
+ s->rx_started = true;
274
+ }
275
+ break;
276
+ case A_UART_ENABLE:
277
+ if (value) {
278
+ if (value == 4) {
279
+ s->enabled = true;
280
+ }
281
+ break;
282
+ }
283
+ s->enabled = false;
284
+ value = 1;
285
+ /* fall through */
286
+ case A_UART_SUSPEND:
287
+ case A_UART_STOPTX:
288
+ if (value == 1) {
289
+ s->tx_started = false;
290
+ }
291
+ /* fall through */
292
+ case A_UART_STOPRX:
293
+ if (addr != A_UART_STOPTX && value == 1) {
294
+ s->rx_started = false;
295
+ s->reg[R_UART_RXTO] = 1;
296
+ }
297
+ break;
298
+ default:
299
+ s->reg[addr / 4] = value;
300
+ break;
301
+ }
302
+ nrf51_uart_update_irq(s);
303
+}
304
+
305
+static const MemoryRegionOps uart_ops = {
306
+ .read = uart_read,
307
+ .write = uart_write,
308
+ .endianness = DEVICE_LITTLE_ENDIAN,
309
+};
310
+
311
+static void nrf51_uart_reset(DeviceState *dev)
312
+{
313
+ NRF51UARTState *s = NRF51_UART(dev);
314
+
315
+ s->pending_tx_byte = 0;
316
+
317
+ uart_cancel_transmit(s);
318
+
319
+ memset(s->reg, 0, sizeof(s->reg));
320
+
321
+ s->reg[R_UART_PSELRTS] = 0xFFFFFFFF;
322
+ s->reg[R_UART_PSELTXD] = 0xFFFFFFFF;
323
+ s->reg[R_UART_PSELCTS] = 0xFFFFFFFF;
324
+ s->reg[R_UART_PSELRXD] = 0xFFFFFFFF;
325
+ s->reg[R_UART_BAUDRATE] = 0x4000000;
326
+
327
+ s->rx_fifo_len = 0;
328
+ s->rx_fifo_pos = 0;
329
+ s->rx_started = false;
330
+ s->tx_started = false;
331
+ s->enabled = false;
332
+}
333
+
334
+static void uart_receive(void *opaque, const uint8_t *buf, int size)
335
+{
336
+
337
+ NRF51UARTState *s = NRF51_UART(opaque);
338
+ int i;
339
+
340
+ if (size == 0 || s->rx_fifo_len >= UART_FIFO_LENGTH) {
341
+ return;
342
+ }
343
+
344
+ for (i = 0; i < size; i++) {
345
+ uint32_t pos = (s->rx_fifo_pos + s->rx_fifo_len) % UART_FIFO_LENGTH;
346
+ s->rx_fifo[pos] = buf[i];
347
+ s->rx_fifo_len++;
348
+ }
349
+
350
+ s->reg[R_UART_RXDRDY] = 1;
351
+ nrf51_uart_update_irq(s);
352
+}
353
+
354
+static int uart_can_receive(void *opaque)
355
+{
356
+ NRF51UARTState *s = NRF51_UART(opaque);
357
+
358
+ return s->rx_started ? (UART_FIFO_LENGTH - s->rx_fifo_len) : 0;
359
+}
360
+
361
+static void uart_event(void *opaque, int event)
362
+{
363
+ NRF51UARTState *s = NRF51_UART(opaque);
364
+
365
+ if (event == CHR_EVENT_BREAK) {
366
+ s->reg[R_UART_ERRORSRC] |= 3;
367
+ s->reg[R_UART_ERROR] = 1;
368
+ nrf51_uart_update_irq(s);
369
+ }
370
+}
371
+
372
+static void nrf51_uart_realize(DeviceState *dev, Error **errp)
373
+{
374
+ NRF51UARTState *s = NRF51_UART(dev);
375
+
376
+ qemu_chr_fe_set_handlers(&s->chr, uart_can_receive, uart_receive,
377
+ uart_event, NULL, s, NULL, true);
378
+}
379
+
380
+static void nrf51_uart_init(Object *obj)
381
+{
382
+ NRF51UARTState *s = NRF51_UART(obj);
383
+ SysBusDevice *sbd = SYS_BUS_DEVICE(obj);
384
+
385
+ memory_region_init_io(&s->iomem, obj, &uart_ops, s,
386
+ "nrf51_soc.uart", UART_SIZE);
387
+ sysbus_init_mmio(sbd, &s->iomem);
388
+ sysbus_init_irq(sbd, &s->irq);
389
+}
390
+
391
+static int nrf51_uart_post_load(void *opaque, int version_id)
392
+{
393
+ NRF51UARTState *s = NRF51_UART(opaque);
394
+
395
+ if (s->pending_tx_byte) {
396
+ s->watch_tag = qemu_chr_fe_add_watch(&s->chr, G_IO_OUT | G_IO_HUP,
397
+ uart_transmit, s);
398
+ }
399
+
400
+ return 0;
401
+}
402
+
403
+static const VMStateDescription nrf51_uart_vmstate = {
404
+ .name = "nrf51_soc.uart",
405
+ .post_load = nrf51_uart_post_load,
406
+ .fields = (VMStateField[]) {
234
+ .fields = (VMStateField[]) {
407
+ VMSTATE_UINT32_ARRAY(reg, NRF51UARTState, 0x56C),
235
+ VMSTATE_UINT32(rstc, BCM2835PowerMgtState),
408
+ VMSTATE_UINT8_ARRAY(rx_fifo, NRF51UARTState, UART_FIFO_LENGTH),
236
+ VMSTATE_UINT32(rsts, BCM2835PowerMgtState),
409
+ VMSTATE_UINT32(rx_fifo_pos, NRF51UARTState),
237
+ VMSTATE_UINT32(wdog, BCM2835PowerMgtState),
410
+ VMSTATE_UINT32(rx_fifo_len, NRF51UARTState),
411
+ VMSTATE_BOOL(rx_started, NRF51UARTState),
412
+ VMSTATE_BOOL(tx_started, NRF51UARTState),
413
+ VMSTATE_BOOL(pending_tx_byte, NRF51UARTState),
414
+ VMSTATE_BOOL(enabled, NRF51UARTState),
415
+ VMSTATE_END_OF_LIST()
238
+ VMSTATE_END_OF_LIST()
416
+ }
239
+ }
417
+};
240
+};
418
+
241
+
419
+static Property nrf51_uart_properties[] = {
242
+static void bcm2835_powermgt_init(Object *obj)
420
+ DEFINE_PROP_CHR("chardev", NRF51UARTState, chr),
243
+{
421
+ DEFINE_PROP_END_OF_LIST(),
244
+ BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj);
422
+};
245
+
423
+
246
+ memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s,
424
+static void nrf51_uart_class_init(ObjectClass *klass, void *data)
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)
425
+{
262
+{
426
+ DeviceClass *dc = DEVICE_CLASS(klass);
263
+ DeviceClass *dc = DEVICE_CLASS(klass);
427
+
264
+
428
+ dc->reset = nrf51_uart_reset;
265
+ dc->reset = bcm2835_powermgt_reset;
429
+ dc->realize = nrf51_uart_realize;
266
+ dc->vmsd = &vmstate_bcm2835_powermgt;
430
+ dc->props = nrf51_uart_properties;
267
+}
431
+ dc->vmsd = &nrf51_uart_vmstate;
268
+
432
+}
269
+static TypeInfo bcm2835_powermgt_info = {
433
+
270
+ .name = TYPE_BCM2835_POWERMGT,
434
+static const TypeInfo nrf51_uart_info = {
271
+ .parent = TYPE_SYS_BUS_DEVICE,
435
+ .name = TYPE_NRF51_UART,
272
+ .instance_size = sizeof(BCM2835PowerMgtState),
436
+ .parent = TYPE_SYS_BUS_DEVICE,
273
+ .class_init = bcm2835_powermgt_class_init,
437
+ .instance_size = sizeof(NRF51UARTState),
274
+ .instance_init = bcm2835_powermgt_init,
438
+ .instance_init = nrf51_uart_init,
275
+};
439
+ .class_init = nrf51_uart_class_init
276
+
440
+};
277
+static void bcm2835_powermgt_register_types(void)
441
+
278
+{
442
+static void nrf51_uart_register_types(void)
279
+ type_register_static(&bcm2835_powermgt_info);
443
+{
280
+}
444
+ type_register_static(&nrf51_uart_info);
281
+
445
+}
282
+type_init(bcm2835_powermgt_register_types)
446
+
283
diff --git a/hw/misc/meson.build b/hw/misc/meson.build
447
+type_init(nrf51_uart_register_types)
448
diff --git a/hw/char/trace-events b/hw/char/trace-events
449
index XXXXXXX..XXXXXXX 100644
284
index XXXXXXX..XXXXXXX 100644
450
--- a/hw/char/trace-events
285
--- a/hw/misc/meson.build
451
+++ b/hw/char/trace-events
286
+++ b/hw/misc/meson.build
452
@@ -XXX,XX +XXX,XX @@ cmsdk_apb_uart_receive(uint8_t c) "CMSDK APB UART: got character 0x%x from backe
287
@@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files(
453
cmsdk_apb_uart_tx_pending(void) "CMSDK APB UART: character send to backend pending"
288
'bcm2835_rng.c',
454
cmsdk_apb_uart_tx(uint8_t c) "CMSDK APB UART: character 0x%x sent to backend"
289
'bcm2835_thermal.c',
455
cmsdk_apb_uart_set_params(int speed) "CMSDK APB UART: params set to %d 8N1"
290
'bcm2835_cprman.c',
456
+
291
+ 'bcm2835_powermgt.c',
457
+# hw/char/nrf51_uart.c
292
))
458
+nrf51_uart_read(uint64_t addr, uint64_t r, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx64 " size %u"
293
softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c'))
459
+nrf51_uart_write(uint64_t addr, uint64_t value, unsigned int size) "addr 0x%" PRIx64 " value 0x%" PRIx64 " size %u"
294
softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c'))
460
--
295
--
461
2.19.1
296
2.20.1
462
297
463
298
diff view generated by jsdifflib
[Qemu-devel] [PULL 6/6] tests/boot-serial-test: Add microbit board testcase
[PULL 04/24] tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine
1
From: Julia Suvorova via Qemu-devel <qemu-devel@nongnu.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
New mini-kernel test for nRF51 SoC UART.
3
Add a test booting and quickly shutdown a raspi2 machine,
4
to test the power management model:
4
5
5
Signed-off-by: Julia Suvorova <jusual@mail.ru>
6
(1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd:
6
Acked-by: Thomas Huth <thuth@redhat.com>
7
console: [ 0.000000] Booting Linux on physical CPU 0xf00
7
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
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
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
48
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
---
49
---
10
tests/boot-serial-test.c | 19 +++++++++++++++++++
50
tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++
11
1 file changed, 19 insertions(+)
51
1 file changed, 43 insertions(+)
12
52
13
diff --git a/tests/boot-serial-test.c b/tests/boot-serial-test.c
53
diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py
14
index XXXXXXX..XXXXXXX 100644
54
index XXXXXXX..XXXXXXX 100644
15
--- a/tests/boot-serial-test.c
55
--- a/tests/acceptance/boot_linux_console.py
16
+++ b/tests/boot-serial-test.c
56
+++ b/tests/acceptance/boot_linux_console.py
17
@@ -XXX,XX +XXX,XX @@ static const uint8_t kernel_aarch64[] = {
57
@@ -XXX,XX +XXX,XX @@
18
0xfd, 0xff, 0xff, 0x17, /* b -12 (loop) */
58
from avocado import skip
19
};
59
from avocado import skipUnless
20
60
from avocado_qemu import Test
21
+static const uint8_t kernel_nrf51[] = {
61
+from avocado_qemu import exec_command
22
+ 0x00, 0x00, 0x00, 0x00, /* Stack top address */
62
from avocado_qemu import exec_command_and_wait_for_pattern
23
+ 0x09, 0x00, 0x00, 0x00, /* Reset handler address */
63
from avocado_qemu import interrupt_interactive_console_until_pattern
24
+ 0x04, 0x4a, /* ldr r2, [pc, #16] Get ENABLE */
64
from avocado_qemu import wait_for_console_pattern
25
+ 0x04, 0x21, /* movs r1, #4 */
65
@@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self):
26
+ 0x11, 0x60, /* str r1, [r2] */
66
"""
27
+ 0x04, 0x4a, /* ldr r2, [pc, #16] Get STARTTX */
67
self.do_test_arm_raspi2(0)
28
+ 0x01, 0x21, /* movs r1, #1 */
68
29
+ 0x11, 0x60, /* str r1, [r2] */
69
+ def test_arm_raspi2_initrd(self):
30
+ 0x03, 0x4a, /* ldr r2, [pc, #12] Get TXD */
70
+ """
31
+ 0x54, 0x21, /* movs r1, 'T' */
71
+ :avocado: tags=arch:arm
32
+ 0x11, 0x60, /* str r1, [r2] */
72
+ :avocado: tags=machine:raspi2
33
+ 0xfe, 0xe7, /* b . */
73
+ """
34
+ 0x00, 0x25, 0x00, 0x40, /* 0x40002500 = UART ENABLE */
74
+ deb_url = ('http://archive.raspberrypi.org/debian/'
35
+ 0x08, 0x20, 0x00, 0x40, /* 0x40002008 = UART STARTTX */
75
+ 'pool/main/r/raspberrypi-firmware/'
36
+ 0x1c, 0x25, 0x00, 0x40 /* 0x4000251c = UART TXD */
76
+ 'raspberrypi-kernel_1.20190215-1_armhf.deb')
37
+};
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')
38
+
81
+
39
typedef struct testdef {
82
+ initrd_url = ('https://github.com/groeck/linux-build-test/raw/'
40
const char *arch; /* Target architecture */
83
+ '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/'
41
const char *machine; /* Name of the machine */
84
+ 'arm/rootfs-armv7a.cpio.gz')
42
@@ -XXX,XX +XXX,XX @@ static testdef_t tests[] = {
85
+ initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c'
43
{ "hppa", "hppa", "", "SeaBIOS wants SYSTEM HALT" },
86
+ initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash)
44
{ "aarch64", "virt", "-cpu cortex-a57", "TT", sizeof(kernel_aarch64),
87
+ initrd_path = os.path.join(self.workdir, 'rootfs.cpio')
45
kernel_aarch64 },
88
+ archive.gzip_uncompress(initrd_path_gz, initrd_path)
46
+ { "arm", "microbit", "", "T", sizeof(kernel_nrf51), kernel_nrf51 },
89
+
47
90
+ self.vm.set_console()
48
{ NULL }
91
+ kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
49
};
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
50
--
114
--
51
2.19.1
115
2.20.1
52
116
53
117
diff view generated by jsdifflib
[Qemu-devel] [PULL 5/6] hw/arm/nrf51_soc: Connect UART to nRF51 SoC
[PULL 05/24] target/arm: Check NaN mode before silencing NaN
1
From: Julia Suvorova via Qemu-devel <qemu-devel@nongnu.org>
1
From: Joe Komlodi <joe.komlodi@xilinx.com>
2
2
3
Wire up nRF51 UART in the corresponding SoC.
3
If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute
4
FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will
5
assert due to fpst->default_nan_mode being set.
4
6
5
Signed-off-by: Julia Suvorova <jusual@mail.ru>
7
To avoid this, we check to see what NaN mode we're running in before we call
6
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
8
floatxx_silence_nan().
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
9
10
Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
15
---
11
include/hw/arm/nrf51_soc.h | 3 +++
16
target/arm/helper-a64.c | 12 +++++++++---
12
hw/arm/microbit.c | 2 ++
17
target/arm/vfp_helper.c | 24 ++++++++++++++++++------
13
hw/arm/nrf51_soc.c | 20 ++++++++++++++++++++
18
2 files changed, 27 insertions(+), 9 deletions(-)
14
3 files changed, 25 insertions(+)
15
19
16
diff --git a/include/hw/arm/nrf51_soc.h b/include/hw/arm/nrf51_soc.h
20
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
17
index XXXXXXX..XXXXXXX 100644
21
index XXXXXXX..XXXXXXX 100644
18
--- a/include/hw/arm/nrf51_soc.h
22
--- a/target/arm/helper-a64.c
19
+++ b/include/hw/arm/nrf51_soc.h
23
+++ b/target/arm/helper-a64.c
20
@@ -XXX,XX +XXX,XX @@
24
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp)
21
25
float16 nan = a;
22
#include "hw/sysbus.h"
26
if (float16_is_signaling_nan(a, fpst)) {
23
#include "hw/arm/armv7m.h"
27
float_raise(float_flag_invalid, fpst);
24
+#include "hw/char/nrf51_uart.h"
28
- nan = float16_silence_nan(a, fpst);
25
29
+ if (!fpst->default_nan_mode) {
26
#define TYPE_NRF51_SOC "nrf51-soc"
30
+ nan = float16_silence_nan(a, fpst);
27
#define NRF51_SOC(obj) \
31
+ }
28
@@ -XXX,XX +XXX,XX @@ typedef struct NRF51State {
32
}
29
/*< public >*/
33
if (fpst->default_nan_mode) {
30
ARMv7MState cpu;
34
nan = float16_default_nan(fpst);
31
35
@@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp)
32
+ NRF51UARTState uart;
36
float32 nan = a;
33
+
37
if (float32_is_signaling_nan(a, fpst)) {
34
MemoryRegion iomem;
38
float_raise(float_flag_invalid, fpst);
35
MemoryRegion sram;
39
- nan = float32_silence_nan(a, fpst);
36
MemoryRegion flash;
40
+ if (!fpst->default_nan_mode) {
37
diff --git a/hw/arm/microbit.c b/hw/arm/microbit.c
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
38
index XXXXXXX..XXXXXXX 100644
58
index XXXXXXX..XXXXXXX 100644
39
--- a/hw/arm/microbit.c
59
--- a/target/arm/vfp_helper.c
40
+++ b/hw/arm/microbit.c
60
+++ b/target/arm/vfp_helper.c
41
@@ -XXX,XX +XXX,XX @@
61
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp)
42
#include "qapi/error.h"
62
float16 nan = f16;
43
#include "hw/boards.h"
63
if (float16_is_signaling_nan(f16, fpst)) {
44
#include "hw/arm/arm.h"
64
float_raise(float_flag_invalid, fpst);
45
+#include "sysemu/sysemu.h"
65
- nan = float16_silence_nan(f16, fpst);
46
#include "exec/address-spaces.h"
66
+ if (!fpst->default_nan_mode) {
47
67
+ nan = float16_silence_nan(f16, fpst);
48
#include "hw/arm/nrf51_soc.h"
68
+ }
49
@@ -XXX,XX +XXX,XX @@ static void microbit_init(MachineState *machine)
69
}
50
70
if (fpst->default_nan_mode) {
51
sysbus_init_child_obj(OBJECT(machine), "nrf51", soc, sizeof(s->nrf51),
71
nan = float16_default_nan(fpst);
52
TYPE_NRF51_SOC);
72
@@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp)
53
+ qdev_prop_set_chr(DEVICE(&s->nrf51), "serial0", serial_hd(0));
73
float32 nan = f32;
54
object_property_set_link(soc, OBJECT(system_memory), "memory",
74
if (float32_is_signaling_nan(f32, fpst)) {
55
&error_fatal);
75
float_raise(float_flag_invalid, fpst);
56
object_property_set_bool(soc, true, "realized", &error_fatal);
76
- nan = float32_silence_nan(f32, fpst);
57
diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c
77
+ if (!fpst->default_nan_mode) {
58
index XXXXXXX..XXXXXXX 100644
78
+ nan = float32_silence_nan(f32, fpst);
59
--- a/hw/arm/nrf51_soc.c
79
+ }
60
+++ b/hw/arm/nrf51_soc.c
80
}
61
@@ -XXX,XX +XXX,XX @@
81
if (fpst->default_nan_mode) {
62
#define NRF51822_FLASH_SIZE (256 * 1024)
82
nan = float32_default_nan(fpst);
63
#define NRF51822_SRAM_SIZE (16 * 1024)
83
@@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp)
64
84
float64 nan = f64;
65
+#define BASE_TO_IRQ(base) ((base >> 12) & 0x1F)
85
if (float64_is_signaling_nan(f64, fpst)) {
66
+
86
float_raise(float_flag_invalid, fpst);
67
static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp)
87
- nan = float64_silence_nan(f64, fpst);
68
{
88
+ if (!fpst->default_nan_mode) {
69
NRF51State *s = NRF51_SOC(dev_soc);
89
+ nan = float64_silence_nan(f64, fpst);
70
+ MemoryRegion *mr;
90
+ }
71
Error *err = NULL;
91
}
72
92
if (fpst->default_nan_mode) {
73
if (!s->board_memory) {
93
nan = float64_default_nan(fpst);
74
@@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp)
94
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp)
75
}
95
float16 nan = f16;
76
memory_region_add_subregion(&s->container, SRAM_BASE, &s->sram);
96
if (float16_is_signaling_nan(f16, s)) {
77
97
float_raise(float_flag_invalid, s);
78
+ /* UART */
98
- nan = float16_silence_nan(f16, s);
79
+ object_property_set_bool(OBJECT(&s->uart), true, "realized", &err);
99
+ if (!s->default_nan_mode) {
80
+ if (err) {
100
+ nan = float16_silence_nan(f16, fpstp);
81
+ error_propagate(errp, err);
101
+ }
82
+ return;
102
}
83
+ }
103
if (s->default_nan_mode) {
84
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->uart), 0);
104
nan = float16_default_nan(s);
85
+ memory_region_add_subregion_overlap(&s->container, UART_BASE, mr, 0);
105
@@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp)
86
+ sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 0,
106
float32 nan = f32;
87
+ qdev_get_gpio_in(DEVICE(&s->cpu),
107
if (float32_is_signaling_nan(f32, s)) {
88
+ BASE_TO_IRQ(UART_BASE)));
108
float_raise(float_flag_invalid, s);
89
+
109
- nan = float32_silence_nan(f32, s);
90
create_unimplemented_device("nrf51_soc.io", IOMEM_BASE, IOMEM_SIZE);
110
+ if (!s->default_nan_mode) {
91
create_unimplemented_device("nrf51_soc.ficr", FICR_BASE, FICR_SIZE);
111
+ nan = float32_silence_nan(f32, fpstp);
92
create_unimplemented_device("nrf51_soc.private",
112
+ }
93
@@ -XXX,XX +XXX,XX @@ static void nrf51_soc_init(Object *obj)
113
}
94
qdev_prop_set_string(DEVICE(&s->cpu), "cpu-type",
114
if (s->default_nan_mode) {
95
ARM_CPU_TYPE_NAME("cortex-m0"));
115
nan = float32_default_nan(s);
96
qdev_prop_set_uint32(DEVICE(&s->cpu), "num-irq", 32);
116
@@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp)
97
+
117
float64 nan = f64;
98
+ sysbus_init_child_obj(obj, "uart", &s->uart, sizeof(s->uart),
118
if (float64_is_signaling_nan(f64, s)) {
99
+ TYPE_NRF51_UART);
119
float_raise(float_flag_invalid, s);
100
+ object_property_add_alias(obj, "serial0", OBJECT(&s->uart), "chardev",
120
- nan = float64_silence_nan(f64, s);
101
+ &error_abort);
121
+ if (!s->default_nan_mode) {
102
}
122
+ nan = float64_silence_nan(f64, fpstp);
103
123
+ }
104
static Property nrf51_soc_properties[] = {
124
}
125
if (s->default_nan_mode) {
126
nan = float64_default_nan(s);
105
--
127
--
106
2.19.1
128
2.20.1
107
129
108
130
diff view generated by jsdifflib
[Qemu-devel] [PULL 1/6] hw/arm/virt: Set VIRT_COMPAT_3_0 compat
[PULL 06/24] hw/gpio/gpio_pwr: use shutdown function for reboot
1
From: Eric Auger <eric.auger@redhat.com>
1
From: Maxim Uvarov <maxim.uvarov@linaro.org>
2
2
3
We are missing the VIRT_COMPAT_3_0 definition and setting.
3
qemu has 2 type of functions: shutdown and reboot. Shutdown
4
Let's add them.
4
function has to be used for machine shutdown. Otherwise we cause
5
a reset with a bogus "cause" value, when we intended a shutdown.
5
6
6
Signed-off-by: Eric Auger <eric.auger@redhat.com>
7
Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org>
7
Reviewed-by: Andrew Jones <drjones@redhat.com>
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Message-id: 20181024085602.16611-1-eric.auger@redhat.com
9
Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org
10
[PMM: tweaked commit message]
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
12
---
11
hw/arm/virt.c | 4 ++++
13
hw/gpio/gpio_pwr.c | 2 +-
12
1 file changed, 4 insertions(+)
14
1 file changed, 1 insertion(+), 1 deletion(-)
13
15
14
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
16
diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c
15
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/arm/virt.c
18
--- a/hw/gpio/gpio_pwr.c
17
+++ b/hw/arm/virt.c
19
+++ b/hw/gpio/gpio_pwr.c
18
@@ -XXX,XX +XXX,XX @@ static void virt_machine_3_1_options(MachineClass *mc)
20
@@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level)
21
static void gpio_pwr_shutdown(void *opaque, int n, int level)
22
{
23
if (level) {
24
- qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
25
+ qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
26
}
19
}
27
}
20
DEFINE_VIRT_MACHINE_AS_LATEST(3, 1)
21
22
+#define VIRT_COMPAT_3_0 \
23
+ HW_COMPAT_3_0
24
+
25
static void virt_3_0_instance_init(Object *obj)
26
{
27
virt_3_1_instance_init(obj);
28
@@ -XXX,XX +XXX,XX @@ static void virt_3_0_instance_init(Object *obj)
29
static void virt_machine_3_0_options(MachineClass *mc)
30
{
31
virt_machine_3_1_options(mc);
32
+ SET_MACHINE_COMPAT(mc, VIRT_COMPAT_3_0);
33
}
34
DEFINE_VIRT_MACHINE(3, 0)
35
28
36
--
29
--
37
2.19.1
30
2.20.1
38
31
39
32
diff view generated by jsdifflib
New patch
[PULL 07/24] target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation
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
[PULL 08/24] target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH
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
New patch
[PULL 09/24] target/arm: Make asimd_imm_const() public
1
The function asimd_imm_const() in translate-neon.c is an
2
implementation of the pseudocode AdvSIMDExpandImm(), which we will
3
also want for MVE. Move the implementation to translate.c, with a
4
prototype in translate.h.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-4-peter.maydell@linaro.org
9
---
10
target/arm/translate.h | 16 ++++++++++
11
target/arm/translate-neon.c | 63 -------------------------------------
12
target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++
13
3 files changed, 73 insertions(+), 63 deletions(-)
14
15
diff --git a/target/arm/translate.h b/target/arm/translate.h
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate.h
18
+++ b/target/arm/translate.h
19
@@ -XXX,XX +XXX,XX @@ 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
{
114
diff --git a/target/arm/translate.c b/target/arm/translate.c
115
index XXXXXXX..XXXXXXX 100644
116
--- a/target/arm/translate.c
117
+++ b/target/arm/translate.c
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)
181
{
182
--
183
2.20.1
184
185
diff view generated by jsdifflib
New patch
[PULL 10/24] target/arm: Use asimd_imm_const for A64 decode
1
The A64 AdvSIMD modified-immediate grouping uses almost the same
2
constant encoding that A32 Neon does; reuse asimd_imm_const() (to
3
which we add the AArch64-specific case for cmode 15 op 1) instead of
4
reimplementing it all.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-5-peter.maydell@linaro.org
9
---
10
target/arm/translate.h | 3 +-
11
target/arm/translate-a64.c | 86 ++++----------------------------------
12
target/arm/translate.c | 17 +++++++-
13
3 files changed, 24 insertions(+), 82 deletions(-)
14
15
diff --git a/target/arm/translate.h b/target/arm/translate.h
16
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate.h
18
+++ b/target/arm/translate.h
19
@@ -XXX,XX +XXX,XX @@ 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)) {
133
diff --git a/target/arm/translate.c b/target/arm/translate.c
134
index XXXXXXX..XXXXXXX 100644
135
--- a/target/arm/translate.c
136
+++ b/target/arm/translate.c
137
@@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
138
case 14:
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.
145
*/
146
uint64_t imm64 = 0;
147
int n;
148
@@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op)
149
imm |= (imm << 8) | (imm << 16) | (imm << 24);
150
break;
151
case 15:
152
+ if (op) {
153
+ /* Reserved encoding for AArch32; valid for AArch64 */
154
+ uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48;
155
+ if (imm & 0x80) {
156
+ imm64 |= 0x8000000000000000ULL;
157
+ }
158
+ if (imm & 0x40) {
159
+ imm64 |= 0x3fc0000000000000ULL;
160
+ } else {
161
+ imm64 |= 0x4000000000000000ULL;
162
+ }
163
+ return imm64;
164
+ }
165
imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19)
166
| ((imm & 0x40) ? (0x1f << 25) : (1 << 30));
167
break;
168
--
169
2.20.1
170
171
diff view generated by jsdifflib
New patch
[PULL 11/24] target/arm: Use dup_const() instead of bitfield_replicate()
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
New patch
[PULL 12/24] target/arm: Implement MVE logical immediate insns
1
Implement the MVE logical-immediate insns (VMOV, VMVN,
2
VORR and VBIC). These have essentially the same encoding
3
as their Neon equivalents, and we implement the decode
4
in the same way.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-7-peter.maydell@linaro.org
9
---
10
target/arm/helper-mve.h | 4 +++
11
target/arm/mve.decode | 17 +++++++++++++
12
target/arm/mve_helper.c | 24 ++++++++++++++++++
13
target/arm/translate-mve.c | 50 ++++++++++++++++++++++++++++++++++++++
14
4 files changed, 95 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_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32)
21
DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
22
DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32)
23
DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
24
+
25
+DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
26
+DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
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.
82
+ */
83
+#define DO_1OP_IMM(OP, FN) \
84
+ void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \
85
+ { \
86
+ uint64_t *da = vda; \
87
+ uint16_t mask = mve_element_mask(env); \
88
+ unsigned e; \
89
+ for (e = 0; e < 16 / 8; e++, mask >>= 8) { \
90
+ mergemask(&da[H8(e)], FN(da[H8(e)], imm), mask); \
91
+ } \
92
+ mve_advance_vpt(env); \
93
+ }
94
+
95
+#define DO_MOVI(N, I) (I)
96
+#define DO_ANDI(N, I) ((N) & (I))
97
+#define DO_ORRI(N, I) ((N) | (I))
98
+
99
+DO_1OP_IMM(vmovi, DO_MOVI)
100
+DO_1OP_IMM(vandi, DO_ANDI)
101
+DO_1OP_IMM(vorri, DO_ORRI)
102
+
103
#define DO_2OP(OP, ESIZE, TYPE, FN) \
104
void HELPER(glue(mve_, OP))(CPUARMState *env, \
105
void *vd, void *vn, void *vm) \
106
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
107
index XXXXXXX..XXXXXXX 100644
108
--- a/target/arm/translate-mve.c
109
+++ b/target/arm/translate-mve.c
110
@@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr);
111
typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32);
112
typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64);
113
typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32);
114
+typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64);
115
116
/* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */
117
static inline long mve_qreg_offset(unsigned reg)
118
@@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a)
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;
132
+ }
133
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
134
+ return true;
135
+ }
136
+
137
+ imm = asimd_imm_const(a->imm, a->cmode, a->op);
138
+
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);
143
+ return true;
144
+}
145
+
146
+static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a)
147
+{
148
+ /* Handle decode of cmode/op here between VORR/VBIC/VMOV */
149
+ MVEGenOneOpImmFn *fn;
150
+
151
+ if ((a->cmode & 1) && a->cmode < 12) {
152
+ if (a->op) {
153
+ /*
154
+ * For op=1, the immediate will be inverted by asimd_imm_const(),
155
+ * so the VBIC becomes a logical AND operation.
156
+ */
157
+ fn = gen_helper_mve_vandi;
158
+ } else {
159
+ fn = gen_helper_mve_vorri;
160
+ }
161
+ } else {
162
+ /* There is one unallocated cmode/op combination in this space */
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;
168
+ }
169
+ return do_1imm(s, a, fn);
170
+}
171
--
172
2.20.1
173
174
diff view generated by jsdifflib
New patch
[PULL 13/24] target/arm: Implement MVE vector shift left by immediate insns
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
New patch
[PULL 14/24] target/arm: Implement MVE vector shift right by immediate insns
1
Implement the MVE vector shift right by immediate insns VSHRI and
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.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-9-peter.maydell@linaro.org
9
---
10
target/arm/helper-mve.h | 12 ++++++++++++
11
target/arm/translate.h | 20 ++++++++++++++++++++
12
target/arm/mve.decode | 28 ++++++++++++++++++++++++++++
13
target/arm/mve_helper.c | 7 +++++++
14
target/arm/translate-mve.c | 5 +++++
15
target/arm/translate-neon.c | 18 ------------------
16
6 files changed, 72 insertions(+), 18 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_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_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+
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
46
index XXXXXXX..XXXXXXX 100644
47
--- a/target/arm/translate.h
48
+++ b/target/arm/translate.h
49
@@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x)
50
return x * 2 + 1;
51
}
52
53
+static inline int rsub_64(DisasContext *s, int x)
54
+{
55
+ return 64 - x;
56
+}
57
+
58
+static inline int rsub_32(DisasContext *s, int x)
59
+{
60
+ return 32 - x;
61
+}
62
+
63
+static inline int rsub_16(DisasContext *s, int x)
64
+{
65
+ return 16 - x;
66
+}
67
+
68
+static inline int rsub_8(DisasContext *s, int x)
69
+{
70
+ return 8 - x;
71
+}
72
+
73
static inline int arm_dc_feature(DisasContext *dc, int feature)
74
{
75
return (dc->features & (1ULL << feature)) != 0;
76
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
77
index XXXXXXX..XXXXXXX 100644
78
--- a/target/arm/mve.decode
79
+++ b/target/arm/mve.decode
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 */
186
--
187
2.20.1
188
189
diff view generated by jsdifflib
New patch
[PULL 15/24] target/arm: Implement MVE VSHLL
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
[PULL 16/24] target/arm: Implement MVE VSRI, VSLI
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
[Qemu-devel] [PULL 3/6] hw/arm: versal: Add a virtual Xilinx Versal board
[PULL 17/24] target/arm: Implement MVE VSHRN, VRSHRN
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN.
2
2
3
Add a virtual Xilinx Versal board.
3
do_urshr() is borrowed from sve_helper.c.
4
4
5
This board is based on the Xilinx Versal SoC. The exact
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
details of what peripherals are attached to this board
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
will remain in control of QEMU. QEMU will generate an
7
Message-id: 20210628135835.6690-12-peter.maydell@linaro.org
8
FDT on the fly for Linux and other software to auto-discover
8
---
9
peripherals.
9
target/arm/helper-mve.h | 10 ++++++++++
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(+)
10
14
11
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
12
[PMM: removed stray blank line at EOF]
13
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
15
---
16
hw/arm/Makefile.objs | 2 +-
17
hw/arm/xlnx-versal-virt.c | 493 ++++++++++++++++++++++++++++++++++++++
18
2 files changed, 494 insertions(+), 1 deletion(-)
19
create mode 100644 hw/arm/xlnx-versal-virt.c
20
21
diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs
22
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
23
--- a/hw/arm/Makefile.objs
17
--- a/target/arm/helper-mve.h
24
+++ b/hw/arm/Makefile.objs
18
+++ b/target/arm/helper-mve.h
25
@@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o
20
DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o
21
DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
obj-$(CONFIG_XLNX_ZYNQMP_ARM) += xlnx-zynqmp.o xlnx-zcu102.o
22
DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
-obj-$(CONFIG_XLNX_VERSAL) += xlnx-versal.o
23
+
30
+obj-$(CONFIG_XLNX_VERSAL) += xlnx-versal.o xlnx-versal-virt.o
24
+DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
obj-$(CONFIG_FSL_IMX25) += fsl-imx25.o imx25_pdk.o
25
+DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
obj-$(CONFIG_FSL_IMX31) += fsl-imx31.o kzm.o
26
+DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
obj-$(CONFIG_FSL_IMX6) += fsl-imx6.o sabrelite.o
27
+DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
34
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
28
+
35
new file mode 100644
29
+DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
index XXXXXXX..XXXXXXX
30
+DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
--- /dev/null
31
+DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
38
+++ b/hw/arm/xlnx-versal-virt.c
32
+DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
39
@@ -XXX,XX +XXX,XX @@
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 @@ 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
+
40
+/*
61
+/*
41
+ * Xilinx Versal Virtual board.
62
+ * Narrowing right shifts, taking a double sized input, shifting it
42
+ *
63
+ * and putting the result in either the top or bottom half of the output.
43
+ * Copyright (c) 2018 Xilinx Inc.
64
+ * ESIZE, TYPE are the output, and LESIZE, LTYPE the input.
44
+ * Written by Edgar E. Iglesias
45
+ *
46
+ * This program is free software; you can redistribute it and/or modify
47
+ * it under the terms of the GNU General Public License version 2 or
48
+ * (at your option) any later version.
49
+ */
65
+ */
50
+
66
+#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \
51
+#include "qemu/osdep.h"
67
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
52
+#include "qemu/log.h"
68
+ void *vm, uint32_t shift) \
53
+#include "qemu/error-report.h"
69
+ { \
54
+#include "qapi/error.h"
70
+ LTYPE *m = vm; \
55
+#include "sysemu/device_tree.h"
71
+ TYPE *d = vd; \
56
+#include "exec/address-spaces.h"
72
+ uint16_t mask = mve_element_mask(env); \
57
+#include "hw/boards.h"
73
+ unsigned le; \
58
+#include "hw/sysbus.h"
74
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
59
+#include "hw/arm/sysbus-fdt.h"
75
+ TYPE r = FN(m[H##LESIZE(le)], shift); \
60
+#include "hw/arm/fdt.h"
76
+ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
61
+#include "cpu.h"
77
+ } \
62
+#include "hw/arm/xlnx-versal.h"
78
+ mve_advance_vpt(env); \
63
+
64
+#define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt")
65
+#define XLNX_VERSAL_VIRT_MACHINE(obj) \
66
+ OBJECT_CHECK(VersalVirt, (obj), TYPE_XLNX_VERSAL_VIRT_MACHINE)
67
+
68
+typedef struct VersalVirt {
69
+ MachineState parent_obj;
70
+
71
+ Versal soc;
72
+ MemoryRegion mr_ddr;
73
+
74
+ void *fdt;
75
+ int fdt_size;
76
+ struct {
77
+ uint32_t gic;
78
+ uint32_t ethernet_phy[2];
79
+ uint32_t clk_125Mhz;
80
+ uint32_t clk_25Mhz;
81
+ } phandle;
82
+ struct arm_boot_info binfo;
83
+
84
+ struct {
85
+ bool secure;
86
+ } cfg;
87
+} VersalVirt;
88
+
89
+static void fdt_create(VersalVirt *s)
90
+{
91
+ MachineClass *mc = MACHINE_GET_CLASS(s);
92
+ int i;
93
+
94
+ s->fdt = create_device_tree(&s->fdt_size);
95
+ if (!s->fdt) {
96
+ error_report("create_device_tree() failed");
97
+ exit(1);
98
+ }
79
+ }
99
+
80
+
100
+ /* Allocate all phandles. */
81
+#define DO_VSHRN_ALL(OP, FN) \
101
+ s->phandle.gic = qemu_fdt_alloc_phandle(s->fdt);
82
+ DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \
102
+ for (i = 0; i < ARRAY_SIZE(s->phandle.ethernet_phy); i++) {
83
+ DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \
103
+ s->phandle.ethernet_phy[i] = qemu_fdt_alloc_phandle(s->fdt);
84
+ DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \
104
+ }
85
+ DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
105
+ s->phandle.clk_25Mhz = qemu_fdt_alloc_phandle(s->fdt);
106
+ s->phandle.clk_125Mhz = qemu_fdt_alloc_phandle(s->fdt);
107
+
86
+
108
+ /* Create /chosen node for load_dtb. */
87
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
109
+ qemu_fdt_add_subnode(s->fdt, "/chosen");
110
+
111
+ /* Header */
112
+ qemu_fdt_setprop_cell(s->fdt, "/", "interrupt-parent", s->phandle.gic);
113
+ qemu_fdt_setprop_cell(s->fdt, "/", "#size-cells", 0x2);
114
+ qemu_fdt_setprop_cell(s->fdt, "/", "#address-cells", 0x2);
115
+ qemu_fdt_setprop_string(s->fdt, "/", "model", mc->desc);
116
+ qemu_fdt_setprop_string(s->fdt, "/", "compatible", "xlnx-versal-virt");
117
+}
118
+
119
+static void fdt_add_clk_node(VersalVirt *s, const char *name,
120
+ unsigned int freq_hz, uint32_t phandle)
121
+{
88
+{
122
+ qemu_fdt_add_subnode(s->fdt, name);
89
+ if (likely(sh < 64)) {
123
+ qemu_fdt_setprop_cell(s->fdt, name, "phandle", phandle);
90
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
124
+ qemu_fdt_setprop_cell(s->fdt, name, "clock-frequency", freq_hz);
91
+ } else if (sh == 64) {
125
+ qemu_fdt_setprop_cell(s->fdt, name, "#clock-cells", 0x0);
92
+ return x >> 63;
126
+ qemu_fdt_setprop_string(s->fdt, name, "compatible", "fixed-clock");
93
+ } else {
127
+ qemu_fdt_setprop(s->fdt, name, "u-boot,dm-pre-reloc", NULL, 0);
94
+ return 0;
128
+}
129
+
130
+static void fdt_add_cpu_nodes(VersalVirt *s, uint32_t psci_conduit)
131
+{
132
+ int i;
133
+
134
+ qemu_fdt_add_subnode(s->fdt, "/cpus");
135
+ qemu_fdt_setprop_cell(s->fdt, "/cpus", "#size-cells", 0x0);
136
+ qemu_fdt_setprop_cell(s->fdt, "/cpus", "#address-cells", 1);
137
+
138
+ for (i = XLNX_VERSAL_NR_ACPUS - 1; i >= 0; i--) {
139
+ char *name = g_strdup_printf("/cpus/cpu@%d", i);
140
+ ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(i));
141
+
142
+ qemu_fdt_add_subnode(s->fdt, name);
143
+ qemu_fdt_setprop_cell(s->fdt, name, "reg", armcpu->mp_affinity);
144
+ if (psci_conduit != QEMU_PSCI_CONDUIT_DISABLED) {
145
+ qemu_fdt_setprop_string(s->fdt, name, "enable-method", "psci");
146
+ }
147
+ qemu_fdt_setprop_string(s->fdt, name, "device_type", "cpu");
148
+ qemu_fdt_setprop_string(s->fdt, name, "compatible",
149
+ armcpu->dtb_compatible);
150
+ g_free(name);
151
+ }
95
+ }
152
+}
96
+}
153
+
97
+
154
+static void fdt_add_gic_nodes(VersalVirt *s)
98
+DO_VSHRN_ALL(vshrn, DO_SHR)
155
+{
99
+DO_VSHRN_ALL(vrshrn, do_urshr)
156
+ char *nodename;
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)
157
+
108
+
158
+ nodename = g_strdup_printf("/gic@%x", MM_GIC_APU_DIST_MAIN);
109
+#define DO_2SHIFT_N(INSN, FN) \
159
+ qemu_fdt_add_subnode(s->fdt, nodename);
110
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
160
+ qemu_fdt_setprop_cell(s->fdt, nodename, "phandle", s->phandle.gic);
111
+ { \
161
+ qemu_fdt_setprop_cells(s->fdt, nodename, "interrupts",
112
+ static MVEGenTwoOpShiftFn * const fns[] = { \
162
+ GIC_FDT_IRQ_TYPE_PPI, VERSAL_GIC_MAINT_IRQ,
113
+ gen_helper_mve_##FN##b, \
163
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI);
114
+ gen_helper_mve_##FN##h, \
164
+ qemu_fdt_setprop(s->fdt, nodename, "interrupt-controller", NULL, 0);
115
+ }; \
165
+ qemu_fdt_setprop_sized_cells(s->fdt, nodename, "reg",
116
+ return do_2shift(s, a, fns[a->size], false); \
166
+ 2, MM_GIC_APU_DIST_MAIN,
167
+ 2, MM_GIC_APU_DIST_MAIN_SIZE,
168
+ 2, MM_GIC_APU_REDIST_0,
169
+ 2, MM_GIC_APU_REDIST_0_SIZE);
170
+ qemu_fdt_setprop_cell(s->fdt, nodename, "#interrupt-cells", 3);
171
+ qemu_fdt_setprop_string(s->fdt, nodename, "compatible", "arm,gic-v3");
172
+}
173
+
174
+static void fdt_add_timer_nodes(VersalVirt *s)
175
+{
176
+ const char compat[] = "arm,armv8-timer";
177
+ uint32_t irqflags = GIC_FDT_IRQ_FLAGS_LEVEL_HI;
178
+
179
+ qemu_fdt_add_subnode(s->fdt, "/timer");
180
+ qemu_fdt_setprop_cells(s->fdt, "/timer", "interrupts",
181
+ GIC_FDT_IRQ_TYPE_PPI, VERSAL_TIMER_S_EL1_IRQ, irqflags,
182
+ GIC_FDT_IRQ_TYPE_PPI, VERSAL_TIMER_NS_EL1_IRQ, irqflags,
183
+ GIC_FDT_IRQ_TYPE_PPI, VERSAL_TIMER_VIRT_IRQ, irqflags,
184
+ GIC_FDT_IRQ_TYPE_PPI, VERSAL_TIMER_NS_EL2_IRQ, irqflags);
185
+ qemu_fdt_setprop(s->fdt, "/timer", "compatible",
186
+ compat, sizeof(compat));
187
+}
188
+
189
+static void fdt_add_uart_nodes(VersalVirt *s)
190
+{
191
+ uint64_t addrs[] = { MM_UART1, MM_UART0 };
192
+ unsigned int irqs[] = { VERSAL_UART1_IRQ_0, VERSAL_UART0_IRQ_0 };
193
+ const char compat[] = "arm,pl011\0arm,sbsa-uart";
194
+ const char clocknames[] = "uartclk\0apb_pclk";
195
+ int i;
196
+
197
+ for (i = 0; i < ARRAY_SIZE(addrs); i++) {
198
+ char *name = g_strdup_printf("/uart@%" PRIx64, addrs[i]);
199
+ qemu_fdt_add_subnode(s->fdt, name);
200
+ qemu_fdt_setprop_cell(s->fdt, name, "current-speed", 115200);
201
+ qemu_fdt_setprop_cells(s->fdt, name, "clocks",
202
+ s->phandle.clk_125Mhz, s->phandle.clk_125Mhz);
203
+ qemu_fdt_setprop(s->fdt, name, "clock-names",
204
+ clocknames, sizeof(clocknames));
205
+
206
+ qemu_fdt_setprop_cells(s->fdt, name, "interrupts",
207
+ GIC_FDT_IRQ_TYPE_SPI, irqs[i],
208
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI);
209
+ qemu_fdt_setprop_sized_cells(s->fdt, name, "reg",
210
+ 2, addrs[i], 2, 0x1000);
211
+ qemu_fdt_setprop(s->fdt, name, "compatible",
212
+ compat, sizeof(compat));
213
+ qemu_fdt_setprop(s->fdt, name, "u-boot,dm-pre-reloc", NULL, 0);
214
+
215
+ if (addrs[i] == MM_UART0) {
216
+ /* Select UART0. */
217
+ qemu_fdt_setprop_string(s->fdt, "/chosen", "stdout-path", name);
218
+ }
219
+ g_free(name);
220
+ }
221
+}
222
+
223
+static void fdt_add_fixed_link_nodes(VersalVirt *s, char *gemname,
224
+ uint32_t phandle)
225
+{
226
+ char *name = g_strdup_printf("%s/fixed-link", gemname);
227
+
228
+ qemu_fdt_add_subnode(s->fdt, name);
229
+ qemu_fdt_setprop_cell(s->fdt, name, "phandle", phandle);
230
+ qemu_fdt_setprop_cells(s->fdt, name, "full-duplex");
231
+ qemu_fdt_setprop_cell(s->fdt, name, "speed", 1000);
232
+ g_free(name);
233
+}
234
+
235
+static void fdt_add_gem_nodes(VersalVirt *s)
236
+{
237
+ uint64_t addrs[] = { MM_GEM1, MM_GEM0 };
238
+ unsigned int irqs[] = { VERSAL_GEM1_IRQ_0, VERSAL_GEM0_IRQ_0 };
239
+ const char clocknames[] = "pclk\0hclk\0tx_clk\0rx_clk";
240
+ const char compat_gem[] = "cdns,zynqmp-gem\0cdns,gem";
241
+ int i;
242
+
243
+ for (i = 0; i < ARRAY_SIZE(addrs); i++) {
244
+ char *name = g_strdup_printf("/ethernet@%" PRIx64, addrs[i]);
245
+ qemu_fdt_add_subnode(s->fdt, name);
246
+
247
+ fdt_add_fixed_link_nodes(s, name, s->phandle.ethernet_phy[i]);
248
+ qemu_fdt_setprop_string(s->fdt, name, "phy-mode", "rgmii-id");
249
+ qemu_fdt_setprop_cell(s->fdt, name, "phy-handle",
250
+ s->phandle.ethernet_phy[i]);
251
+ qemu_fdt_setprop_cells(s->fdt, name, "clocks",
252
+ s->phandle.clk_25Mhz, s->phandle.clk_25Mhz,
253
+ s->phandle.clk_25Mhz, s->phandle.clk_25Mhz);
254
+ qemu_fdt_setprop(s->fdt, name, "clock-names",
255
+ clocknames, sizeof(clocknames));
256
+ qemu_fdt_setprop_cells(s->fdt, name, "interrupts",
257
+ GIC_FDT_IRQ_TYPE_SPI, irqs[i],
258
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI,
259
+ GIC_FDT_IRQ_TYPE_SPI, irqs[i],
260
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI);
261
+ qemu_fdt_setprop_sized_cells(s->fdt, name, "reg",
262
+ 2, addrs[i], 2, 0x1000);
263
+ qemu_fdt_setprop(s->fdt, name, "compatible",
264
+ compat_gem, sizeof(compat_gem));
265
+ qemu_fdt_setprop_cell(s->fdt, name, "#address-cells", 1);
266
+ qemu_fdt_setprop_cell(s->fdt, name, "#size-cells", 0);
267
+ g_free(name);
268
+ }
269
+}
270
+
271
+static void fdt_nop_memory_nodes(void *fdt, Error **errp)
272
+{
273
+ Error *err = NULL;
274
+ char **node_path;
275
+ int n = 0;
276
+
277
+ node_path = qemu_fdt_node_unit_path(fdt, "memory", &err);
278
+ if (err) {
279
+ error_propagate(errp, err);
280
+ return;
281
+ }
282
+ while (node_path[n]) {
283
+ if (g_str_has_prefix(node_path[n], "/memory")) {
284
+ qemu_fdt_nop_node(fdt, node_path[n]);
285
+ }
286
+ n++;
287
+ }
288
+ g_strfreev(node_path);
289
+}
290
+
291
+static void fdt_add_memory_nodes(VersalVirt *s, void *fdt, uint64_t ram_size)
292
+{
293
+ /* Describes the various split DDR access regions. */
294
+ static const struct {
295
+ uint64_t base;
296
+ uint64_t size;
297
+ } addr_ranges[] = {
298
+ { MM_TOP_DDR, MM_TOP_DDR_SIZE },
299
+ { MM_TOP_DDR_2, MM_TOP_DDR_2_SIZE },
300
+ { MM_TOP_DDR_3, MM_TOP_DDR_3_SIZE },
301
+ { MM_TOP_DDR_4, MM_TOP_DDR_4_SIZE }
302
+ };
303
+ uint64_t mem_reg_prop[8] = {0};
304
+ uint64_t size = ram_size;
305
+ Error *err = NULL;
306
+ char *name;
307
+ int i;
308
+
309
+ fdt_nop_memory_nodes(fdt, &err);
310
+ if (err) {
311
+ error_report_err(err);
312
+ return;
313
+ }
117
+ }
314
+
118
+
315
+ name = g_strdup_printf("/memory@%x", MM_TOP_DDR);
119
+DO_2SHIFT_N(VSHRNB, vshrnb)
316
+ for (i = 0; i < ARRAY_SIZE(addr_ranges) && size; i++) {
120
+DO_2SHIFT_N(VSHRNT, vshrnt)
317
+ uint64_t mapsize;
121
+DO_2SHIFT_N(VRSHRNB, vrshrnb)
318
+
122
+DO_2SHIFT_N(VRSHRNT, vrshrnt)
319
+ mapsize = size < addr_ranges[i].size ? size : addr_ranges[i].size;
320
+
321
+ mem_reg_prop[i * 2] = addr_ranges[i].base;
322
+ mem_reg_prop[i * 2 + 1] = mapsize;
323
+ size -= mapsize;
324
+ }
325
+ qemu_fdt_add_subnode(fdt, name);
326
+ qemu_fdt_setprop_string(fdt, name, "device_type", "memory");
327
+
328
+ switch (i) {
329
+ case 1:
330
+ qemu_fdt_setprop_sized_cells(fdt, name, "reg",
331
+ 2, mem_reg_prop[0],
332
+ 2, mem_reg_prop[1]);
333
+ break;
334
+ case 2:
335
+ qemu_fdt_setprop_sized_cells(fdt, name, "reg",
336
+ 2, mem_reg_prop[0],
337
+ 2, mem_reg_prop[1],
338
+ 2, mem_reg_prop[2],
339
+ 2, mem_reg_prop[3]);
340
+ break;
341
+ case 3:
342
+ qemu_fdt_setprop_sized_cells(fdt, name, "reg",
343
+ 2, mem_reg_prop[0],
344
+ 2, mem_reg_prop[1],
345
+ 2, mem_reg_prop[2],
346
+ 2, mem_reg_prop[3],
347
+ 2, mem_reg_prop[4],
348
+ 2, mem_reg_prop[5]);
349
+ break;
350
+ case 4:
351
+ qemu_fdt_setprop_sized_cells(fdt, name, "reg",
352
+ 2, mem_reg_prop[0],
353
+ 2, mem_reg_prop[1],
354
+ 2, mem_reg_prop[2],
355
+ 2, mem_reg_prop[3],
356
+ 2, mem_reg_prop[4],
357
+ 2, mem_reg_prop[5],
358
+ 2, mem_reg_prop[6],
359
+ 2, mem_reg_prop[7]);
360
+ break;
361
+ default:
362
+ g_assert_not_reached();
363
+ }
364
+ g_free(name);
365
+}
366
+
367
+static void versal_virt_modify_dtb(const struct arm_boot_info *binfo,
368
+ void *fdt)
369
+{
370
+ VersalVirt *s = container_of(binfo, VersalVirt, binfo);
371
+
372
+ fdt_add_memory_nodes(s, fdt, binfo->ram_size);
373
+}
374
+
375
+static void *versal_virt_get_dtb(const struct arm_boot_info *binfo,
376
+ int *fdt_size)
377
+{
378
+ const VersalVirt *board = container_of(binfo, VersalVirt, binfo);
379
+
380
+ *fdt_size = board->fdt_size;
381
+ return board->fdt;
382
+}
383
+
384
+#define NUM_VIRTIO_TRANSPORT 32
385
+static void create_virtio_regions(VersalVirt *s)
386
+{
387
+ int virtio_mmio_size = 0x200;
388
+ int i;
389
+
390
+ for (i = 0; i < NUM_VIRTIO_TRANSPORT; i++) {
391
+ char *name = g_strdup_printf("virtio%d", i);;
392
+ hwaddr base = MM_TOP_RSVD + i * virtio_mmio_size;
393
+ int irq = VERSAL_RSVD_HIGH_IRQ_FIRST + i;
394
+ MemoryRegion *mr;
395
+ DeviceState *dev;
396
+ qemu_irq pic_irq;
397
+
398
+ pic_irq = qdev_get_gpio_in(DEVICE(&s->soc.fpd.apu.gic), irq);
399
+ dev = qdev_create(NULL, "virtio-mmio");
400
+ object_property_add_child(OBJECT(&s->soc), name, OBJECT(dev),
401
+ &error_fatal);
402
+ qdev_init_nofail(dev);
403
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic_irq);
404
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
405
+ memory_region_add_subregion(&s->soc.mr_ps, base, mr);
406
+ sysbus_create_simple("virtio-mmio", base, pic_irq);
407
+ }
408
+
409
+ for (i = 0; i < NUM_VIRTIO_TRANSPORT; i++) {
410
+ hwaddr base = MM_TOP_RSVD + i * virtio_mmio_size;
411
+ int irq = VERSAL_RSVD_HIGH_IRQ_FIRST + i;
412
+ char *name = g_strdup_printf("/virtio_mmio@%" PRIx64, base);
413
+
414
+ qemu_fdt_add_subnode(s->fdt, name);
415
+ qemu_fdt_setprop(s->fdt, name, "dma-coherent", NULL, 0);
416
+ qemu_fdt_setprop_cells(s->fdt, name, "interrupts",
417
+ GIC_FDT_IRQ_TYPE_SPI, irq,
418
+ GIC_FDT_IRQ_FLAGS_EDGE_LO_HI);
419
+ qemu_fdt_setprop_sized_cells(s->fdt, name, "reg",
420
+ 2, base, 2, virtio_mmio_size);
421
+ qemu_fdt_setprop_string(s->fdt, name, "compatible", "virtio,mmio");
422
+ g_free(name);
423
+ }
424
+}
425
+
426
+static void versal_virt_init(MachineState *machine)
427
+{
428
+ VersalVirt *s = XLNX_VERSAL_VIRT_MACHINE(machine);
429
+ int psci_conduit = QEMU_PSCI_CONDUIT_DISABLED;
430
+
431
+ /*
432
+ * If the user provides an Operating System to be loaded, we expect them
433
+ * to use the -kernel command line option.
434
+ *
435
+ * Users can load firmware or boot-loaders with the -device loader options.
436
+ *
437
+ * When loading an OS, we generate a dtb and let arm_load_kernel() select
438
+ * where it gets loaded. This dtb will be passed to the kernel in x0.
439
+ *
440
+ * If there's no -kernel option, we generate a DTB and place it at 0x1000
441
+ * for the bootloaders or firmware to pick up.
442
+ *
443
+ * If users want to provide their own DTB, they can use the -dtb option.
444
+ * These dtb's will have their memory nodes modified to match QEMU's
445
+ * selected ram_size option before they get passed to the kernel or fw.
446
+ *
447
+ * When loading an OS, we turn on QEMU's PSCI implementation with SMC
448
+ * as the PSCI conduit. When there's no -kernel, we assume the user
449
+ * provides EL3 firmware to handle PSCI.
450
+ */
451
+ if (machine->kernel_filename) {
452
+ psci_conduit = QEMU_PSCI_CONDUIT_SMC;
453
+ }
454
+
455
+ memory_region_allocate_system_memory(&s->mr_ddr, NULL, "ddr",
456
+ machine->ram_size);
457
+
458
+ sysbus_init_child_obj(OBJECT(machine), "xlnx-ve", &s->soc,
459
+ sizeof(s->soc), TYPE_XLNX_VERSAL);
460
+ object_property_set_link(OBJECT(&s->soc), OBJECT(&s->mr_ddr),
461
+ "ddr", &error_abort);
462
+ object_property_set_int(OBJECT(&s->soc), psci_conduit,
463
+ "psci-conduit", &error_abort);
464
+ object_property_set_bool(OBJECT(&s->soc), true, "realized", &error_fatal);
465
+
466
+ fdt_create(s);
467
+ create_virtio_regions(s);
468
+ fdt_add_gem_nodes(s);
469
+ fdt_add_uart_nodes(s);
470
+ fdt_add_gic_nodes(s);
471
+ fdt_add_timer_nodes(s);
472
+ fdt_add_cpu_nodes(s, psci_conduit);
473
+ fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz);
474
+ fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz);
475
+
476
+ /* Make the APU cpu address space visible to virtio and other
477
+ * modules unaware of muliple address-spaces. */
478
+ memory_region_add_subregion_overlap(get_system_memory(),
479
+ 0, &s->soc.fpd.apu.mr, 0);
480
+
481
+ s->binfo.ram_size = machine->ram_size;
482
+ s->binfo.kernel_filename = machine->kernel_filename;
483
+ s->binfo.kernel_cmdline = machine->kernel_cmdline;
484
+ s->binfo.initrd_filename = machine->initrd_filename;
485
+ s->binfo.loader_start = 0x0;
486
+ s->binfo.get_dtb = versal_virt_get_dtb;
487
+ s->binfo.modify_dtb = versal_virt_modify_dtb;
488
+ if (machine->kernel_filename) {
489
+ arm_load_kernel(s->soc.fpd.apu.cpu[0], &s->binfo);
490
+ } else {
491
+ AddressSpace *as = arm_boot_address_space(s->soc.fpd.apu.cpu[0],
492
+ &s->binfo);
493
+ /* Some boot-loaders (e.g u-boot) don't like blobs at address 0 (NULL).
494
+ * Offset things by 4K. */
495
+ s->binfo.loader_start = 0x1000;
496
+ s->binfo.dtb_limit = 0x1000000;
497
+ if (arm_load_dtb(s->binfo.loader_start,
498
+ &s->binfo, s->binfo.dtb_limit, as) < 0) {
499
+ exit(EXIT_FAILURE);
500
+ }
501
+ }
502
+}
503
+
504
+static void versal_virt_machine_instance_init(Object *obj)
505
+{
506
+}
507
+
508
+static void versal_virt_machine_class_init(ObjectClass *oc, void *data)
509
+{
510
+ MachineClass *mc = MACHINE_CLASS(oc);
511
+
512
+ mc->desc = "Xilinx Versal Virtual development board";
513
+ mc->init = versal_virt_init;
514
+ mc->max_cpus = XLNX_VERSAL_NR_ACPUS;
515
+ mc->default_cpus = XLNX_VERSAL_NR_ACPUS;
516
+ mc->no_cdrom = true;
517
+}
518
+
519
+static const TypeInfo versal_virt_machine_init_typeinfo = {
520
+ .name = TYPE_XLNX_VERSAL_VIRT_MACHINE,
521
+ .parent = TYPE_MACHINE,
522
+ .class_init = versal_virt_machine_class_init,
523
+ .instance_init = versal_virt_machine_instance_init,
524
+ .instance_size = sizeof(VersalVirt),
525
+};
526
+
527
+static void versal_virt_machine_init_register_types(void)
528
+{
529
+ type_register_static(&versal_virt_machine_init_typeinfo);
530
+}
531
+
532
+type_init(versal_virt_machine_init_register_types)
533
--
123
--
534
2.19.1
124
2.20.1
535
125
536
126
diff view generated by jsdifflib
New patch
[PULL 18/24] target/arm: Implement MVE saturating narrowing shifts
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
New patch
[PULL 19/24] target/arm: Implement MVE VSHLC
1
Implement the MVE VSHLC insn, which performs a shift left of the
2
entire vector with carry in bits provided from a general purpose
3
register and carry out bits written back to that register.
1
4
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20210628135835.6690-14-peter.maydell@linaro.org
8
---
9
target/arm/helper-mve.h | 2 ++
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(+)
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_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
20
DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
+
24
+DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32)
25
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
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
+}
119
--
120
2.20.1
121
122
diff view generated by jsdifflib
New patch
[PULL 20/24] target/arm: Implement MVE VADDLV
1
Implement the MVE VADDLV insn; this is similar to VADDV, except
2
that it accumulates 32-bit elements into a 64-bit accumulator
3
stored in a pair of general-purpose registers.
1
4
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20210628135835.6690-15-peter.maydell@linaro.org
8
---
9
target/arm/helper-mve.h | 3 ++
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(-)
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_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
20
DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32)
21
DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32)
22
23
+DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64)
24
+DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64)
25
+
26
DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64)
27
DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64)
28
DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64)
29
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
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;
82
}
83
84
+static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a)
85
+{
86
+ /*
87
+ * Vector Add Long Across Vector: accumulate the 32-bit
88
+ * elements of the vector into a 64-bit result stored in
89
+ * a pair of general-purpose registers.
90
+ * No need to check Qm's bank: it is only 3 bits in decode.
91
+ */
92
+ TCGv_ptr qm;
93
+ TCGv_i64 rda;
94
+ TCGv_i32 rdalo, rdahi;
95
+
96
+ if (!dc_isar_feature(aa32_mve, s)) {
97
+ return false;
98
+ }
99
+ /*
100
+ * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related
101
+ * encoding; rdalo always has bit 0 clear so cannot be 13 or 15.
102
+ */
103
+ if (a->rdahi == 13 || a->rdahi == 15) {
104
+ return false;
105
+ }
106
+ if (!mve_eci_check(s) || !vfp_access_check(s)) {
107
+ return true;
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);
144
+ return true;
145
+}
146
+
147
static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn)
148
{
149
TCGv_ptr qd;
150
--
151
2.20.1
152
153
diff view generated by jsdifflib
New patch
[PULL 21/24] target/arm: Implement MVE long shifts by immediate
1
1
The MVE extension to v8.1M includes some new shift instructions which
2
sit entirely within the non-coprocessor part of the encoding space
3
and which operate only on general-purpose registers. They take up
4
the space which was previously UNPREDICTABLE MOVS and ORRS encodings
5
with Rm == 13 or 15.
6
7
Implement the long shifts by immediate, which perform shifts on a
8
pair of general-purpose registers treated as a 64-bit quantity, with
9
an immediate shift count between 1 and 32.
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.
23
24
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
25
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
26
Message-id: 20210628135835.6690-16-peter.maydell@linaro.org
27
---
28
target/arm/helper-mve.h | 3 ++
29
target/arm/translate.h | 1 +
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
+}
128
diff --git a/target/arm/translate.c b/target/arm/translate.c
129
index XXXXXXX..XXXXXXX 100644
130
--- a/target/arm/translate.c
131
+++ b/target/arm/translate.c
132
@@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a)
133
return true;
134
}
135
136
+/*
137
+ * v8.1M MVE wide-shifts
138
+ */
139
+static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a,
140
+ WideShiftImmFn *fn)
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
*/
229
--
230
2.20.1
231
232
diff view generated by jsdifflib
New patch
[PULL 22/24] target/arm: Implement MVE long shifts by register
1
1
Implement the MVE long shifts by register, which perform shifts on a
2
pair of general-purpose registers treated as a 64-bit quantity, with
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.
11
12
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 20210628135835.6690-17-peter.maydell@linaro.org
15
---
16
target/arm/helper-mve.h | 6 +++
17
target/arm/translate.h | 1 +
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
+}
211
diff --git a/target/arm/translate.c b/target/arm/translate.c
212
index XXXXXXX..XXXXXXX 100644
213
--- a/target/arm/translate.c
214
+++ b/target/arm/translate.c
215
@@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a)
216
return do_mve_shl_ri(s, a, gen_urshr64_i64);
217
}
218
219
+static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn)
220
+{
221
+ TCGv_i64 rda;
222
+ TCGv_i32 rdalo, rdahi;
223
+
224
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
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
*/
291
--
292
2.20.1
293
294
diff view generated by jsdifflib
New patch
[PULL 23/24] target/arm: Implement MVE shifts by immediate
1
1
Implement the MVE shifts by immediate, which perform shifts
2
on a single general-purpose register.
3
4
These patterns overlap with the long-shift-by-immediates,
5
so we have to rearrange the grouping a little here.
6
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
Message-id: 20210628135835.6690-18-peter.maydell@linaro.org
10
---
11
target/arm/helper-mve.h | 3 ++
12
target/arm/translate.h | 1 +
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
+}
116
diff --git a/target/arm/translate.c b/target/arm/translate.c
117
index XXXXXXX..XXXXXXX 100644
118
--- a/target/arm/translate.c
119
+++ b/target/arm/translate.c
120
@@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh)
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);
154
}
155
156
+static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn)
157
+{
158
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
159
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
160
+ return false;
161
+ }
162
+ if (!dc_isar_feature(aa32_mve, s) ||
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);
167
+ return true;
168
+ }
169
+
170
+ if (a->shim == 0) {
171
+ a->shim = 32;
172
+ }
173
+ fn(cpu_R[a->rda], cpu_R[a->rda], a->shim);
174
+
175
+ return true;
176
+}
177
+
178
+static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
179
+{
180
+ return do_mve_sh_ri(s, a, gen_urshr32_i32);
181
+}
182
+
183
+static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a)
184
+{
185
+ return do_mve_sh_ri(s, a, gen_srshr32_i32);
186
+}
187
+
188
+static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
189
+{
190
+ gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift));
191
+}
192
+
193
+static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
194
+{
195
+ return do_mve_sh_ri(s, a, gen_mve_sqshl);
196
+}
197
+
198
+static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift)
199
+{
200
+ gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift));
201
+}
202
+
203
+static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
204
+{
205
+ return do_mve_sh_ri(s, a, gen_mve_uqshl);
206
+}
207
+
208
/*
209
* Multiply and multiply accumulate
210
*/
211
--
212
2.20.1
213
214
diff view generated by jsdifflib
[Qemu-devel] [PULL 2/6] hw/arm: versal: Add a model of Xilinx Versal SoC
[PULL 24/24] target/arm: Implement MVE shifts by register
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
Implement the MVE shifts by register, which perform
2
shifts on a single general-purpose register.
2
3
3
Add a model of Xilinx Versal SoC.
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20210628135835.6690-19-peter.maydell@linaro.org
7
---
8
target/arm/helper-mve.h | 2 ++
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(-)
4
14
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
6
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
---
9
hw/arm/Makefile.objs | 1 +
10
include/hw/arm/xlnx-versal.h | 122 +++++++++++
11
hw/arm/xlnx-versal.c | 323 ++++++++++++++++++++++++++++
12
default-configs/aarch64-softmmu.mak | 1 +
13
4 files changed, 447 insertions(+)
14
create mode 100644 include/hw/arm/xlnx-versal.h
15
create mode 100644 hw/arm/xlnx-versal.c
16
17
diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs
18
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
19
--- a/hw/arm/Makefile.objs
17
--- a/target/arm/helper-mve.h
20
+++ b/hw/arm/Makefile.objs
18
+++ b/target/arm/helper-mve.h
21
@@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
22
obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o
20
23
obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o
21
DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
24
obj-$(CONFIG_XLNX_ZYNQMP_ARM) += xlnx-zynqmp.o xlnx-zcu102.o
22
DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
25
+obj-$(CONFIG_XLNX_VERSAL) += xlnx-versal.o
23
+DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
26
obj-$(CONFIG_FSL_IMX25) += fsl-imx25.o imx25_pdk.o
24
+DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32)
27
obj-$(CONFIG_FSL_IMX31) += fsl-imx31.o kzm.o
25
diff --git a/target/arm/translate.h b/target/arm/translate.h
28
obj-$(CONFIG_FSL_IMX6) += fsl-imx6.o sabrelite.o
26
index XXXXXXX..XXXXXXX 100644
29
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
27
--- a/target/arm/translate.h
30
new file mode 100644
28
+++ b/target/arm/translate.h
31
index XXXXXXX..XXXXXXX
29
@@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
32
--- /dev/null
30
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
33
+++ b/include/hw/arm/xlnx-versal.h
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
34
@@ -XXX,XX +XXX,XX @@
41
@@ -XXX,XX +XXX,XX @@
35
+/*
42
&mve_shl_ri rdalo rdahi shim
36
+ * Model of the Xilinx Versal
43
&mve_shl_rr rdalo rdahi rm
37
+ *
44
&mve_sh_ri rda shim
38
+ * Copyright (c) 2018 Xilinx Inc.
45
+&mve_sh_rr rda rm
39
+ * Written by Edgar E. Iglesias
46
40
+ *
47
# rdahi: bits [3:1] from insn, bit 0 is 1
41
+ * This program is free software; you can redistribute it and/or modify
48
# rdalo: bits [3:1] from insn, bit 0 is 0
42
+ * it under the terms of the GNU General Public License version 2 or
49
@@ -XXX,XX +XXX,XX @@
43
+ * (at your option) any later version.
50
&mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
44
+ */
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
+ }
45
+
70
+
46
+#ifndef XLNX_VERSAL_H
71
+ {
47
+#define XLNX_VERSAL_H
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
+ }
48
+
76
+
49
+#include "hw/sysbus.h"
77
UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr
50
+#include "hw/arm/arm.h"
78
SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr
51
+#include "hw/intc/arm_gicv3.h"
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
}
52
+
88
+
53
+#define TYPE_XLNX_VERSAL "xlnx-versal"
89
+uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift)
54
+#define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL)
55
+
56
+#define XLNX_VERSAL_NR_ACPUS 2
57
+#define XLNX_VERSAL_NR_UARTS 2
58
+#define XLNX_VERSAL_NR_GEMS 2
59
+#define XLNX_VERSAL_NR_IRQS 256
60
+
61
+typedef struct Versal {
62
+ /*< private >*/
63
+ SysBusDevice parent_obj;
64
+
65
+ /*< public >*/
66
+ struct {
67
+ struct {
68
+ MemoryRegion mr;
69
+ ARMCPU *cpu[XLNX_VERSAL_NR_ACPUS];
70
+ GICv3State gic;
71
+ } apu;
72
+ } fpd;
73
+
74
+ MemoryRegion mr_ps;
75
+
76
+ struct {
77
+ /* 4 ranges to access DDR. */
78
+ MemoryRegion mr_ddr_ranges[4];
79
+ } noc;
80
+
81
+ struct {
82
+ MemoryRegion mr_ocm;
83
+
84
+ struct {
85
+ SysBusDevice *uart[XLNX_VERSAL_NR_UARTS];
86
+ SysBusDevice *gem[XLNX_VERSAL_NR_GEMS];
87
+ } iou;
88
+ } lpd;
89
+
90
+ struct {
91
+ MemoryRegion *mr_ddr;
92
+ uint32_t psci_conduit;
93
+ } cfg;
94
+} Versal;
95
+
96
+/* Memory-map and IRQ definitions. Copied a subset from
97
+ * auto-generated files. */
98
+
99
+#define VERSAL_GIC_MAINT_IRQ 9
100
+#define VERSAL_TIMER_VIRT_IRQ 11
101
+#define VERSAL_TIMER_S_EL1_IRQ 13
102
+#define VERSAL_TIMER_NS_EL1_IRQ 14
103
+#define VERSAL_TIMER_NS_EL2_IRQ 10
104
+
105
+#define VERSAL_UART0_IRQ_0 18
106
+#define VERSAL_UART1_IRQ_0 19
107
+#define VERSAL_GEM0_IRQ_0 56
108
+#define VERSAL_GEM0_WAKE_IRQ_0 57
109
+#define VERSAL_GEM1_IRQ_0 58
110
+#define VERSAL_GEM1_WAKE_IRQ_0 59
111
+
112
+/* Architecturally eserved IRQs suitable for virtualization. */
113
+#define VERSAL_RSVD_HIGH_IRQ_FIRST 160
114
+#define VERSAL_RSVD_HIGH_IRQ_LAST 255
115
+
116
+#define MM_TOP_RSVD 0xa0000000U
117
+#define MM_TOP_RSVD_SIZE 0x4000000
118
+#define MM_GIC_APU_DIST_MAIN 0xf9000000U
119
+#define MM_GIC_APU_DIST_MAIN_SIZE 0x10000
120
+#define MM_GIC_APU_REDIST_0 0xf9080000U
121
+#define MM_GIC_APU_REDIST_0_SIZE 0x80000
122
+
123
+#define MM_UART0 0xff000000U
124
+#define MM_UART0_SIZE 0x10000
125
+#define MM_UART1 0xff010000U
126
+#define MM_UART1_SIZE 0x10000
127
+
128
+#define MM_GEM0 0xff0c0000U
129
+#define MM_GEM0_SIZE 0x10000
130
+#define MM_GEM1 0xff0d0000U
131
+#define MM_GEM1_SIZE 0x10000
132
+
133
+#define MM_OCM 0xfffc0000U
134
+#define MM_OCM_SIZE 0x40000
135
+
136
+#define MM_TOP_DDR 0x0
137
+#define MM_TOP_DDR_SIZE 0x80000000U
138
+#define MM_TOP_DDR_2 0x800000000ULL
139
+#define MM_TOP_DDR_2_SIZE 0x800000000ULL
140
+#define MM_TOP_DDR_3 0xc000000000ULL
141
+#define MM_TOP_DDR_3_SIZE 0x4000000000ULL
142
+#define MM_TOP_DDR_4 0x10000000000ULL
143
+#define MM_TOP_DDR_4_SIZE 0xb780000000ULL
144
+
145
+#define MM_PSM_START 0xffc80000U
146
+#define MM_PSM_END 0xffcf0000U
147
+
148
+#define MM_CRL 0xff5e0000U
149
+#define MM_CRL_SIZE 0x300000
150
+#define MM_IOU_SCNTR 0xff130000U
151
+#define MM_IOU_SCNTR_SIZE 0x10000
152
+#define MM_IOU_SCNTRS 0xff140000U
153
+#define MM_IOU_SCNTRS_SIZE 0x10000
154
+#define MM_FPD_CRF 0xfd1a0000U
155
+#define MM_FPD_CRF_SIZE 0x140000
156
+#endif
157
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
158
new file mode 100644
159
index XXXXXXX..XXXXXXX
160
--- /dev/null
161
+++ b/hw/arm/xlnx-versal.c
162
@@ -XXX,XX +XXX,XX @@
163
+/*
164
+ * Xilinx Versal SoC model.
165
+ *
166
+ * Copyright (c) 2018 Xilinx Inc.
167
+ * Written by Edgar E. Iglesias
168
+ *
169
+ * This program is free software; you can redistribute it and/or modify
170
+ * it under the terms of the GNU General Public License version 2 or
171
+ * (at your option) any later version.
172
+ */
173
+
174
+#include "qemu/osdep.h"
175
+#include "qapi/error.h"
176
+#include "qemu-common.h"
177
+#include "qemu/log.h"
178
+#include "hw/sysbus.h"
179
+#include "net/net.h"
180
+#include "sysemu/sysemu.h"
181
+#include "sysemu/kvm.h"
182
+#include "hw/arm/arm.h"
183
+#include "kvm_arm.h"
184
+#include "hw/misc/unimp.h"
185
+#include "hw/intc/arm_gicv3_common.h"
186
+#include "hw/arm/xlnx-versal.h"
187
+
188
+#define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72")
189
+#define GEM_REVISION 0x40070106
190
+
191
+static void versal_create_apu_cpus(Versal *s)
192
+{
90
+{
193
+ int i;
91
+ return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF);
194
+
195
+ for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) {
196
+ Object *obj;
197
+ char *name;
198
+
199
+ obj = object_new(XLNX_VERSAL_ACPU_TYPE);
200
+ if (!obj) {
201
+ /* Secondary CPUs start in PSCI powered-down state */
202
+ error_report("Unable to create apu.cpu[%d] of type %s",
203
+ i, XLNX_VERSAL_ACPU_TYPE);
204
+ exit(EXIT_FAILURE);
205
+ }
206
+
207
+ name = g_strdup_printf("apu-cpu[%d]", i);
208
+ object_property_add_child(OBJECT(s), name, obj, &error_fatal);
209
+ g_free(name);
210
+
211
+ object_property_set_int(obj, s->cfg.psci_conduit,
212
+ "psci-conduit", &error_abort);
213
+ if (i) {
214
+ object_property_set_bool(obj, true,
215
+ "start-powered-off", &error_abort);
216
+ }
217
+
218
+ object_property_set_int(obj, ARRAY_SIZE(s->fpd.apu.cpu),
219
+ "core-count", &error_abort);
220
+ object_property_set_link(obj, OBJECT(&s->fpd.apu.mr), "memory",
221
+ &error_abort);
222
+ object_property_set_bool(obj, true, "realized", &error_fatal);
223
+ s->fpd.apu.cpu[i] = ARM_CPU(obj);
224
+ }
225
+}
92
+}
226
+
93
+
227
+static void versal_create_apu_gic(Versal *s, qemu_irq *pic)
94
+uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift)
228
+{
95
+{
229
+ static const uint64_t addrs[] = {
96
+ return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF);
230
+ MM_GIC_APU_DIST_MAIN,
97
+}
231
+ MM_GIC_APU_REDIST_0
98
diff --git a/target/arm/translate.c b/target/arm/translate.c
232
+ };
99
index XXXXXXX..XXXXXXX 100644
233
+ SysBusDevice *gicbusdev;
100
--- a/target/arm/translate.c
234
+ DeviceState *gicdev;
101
+++ b/target/arm/translate.c
235
+ int nr_apu_cpus = ARRAY_SIZE(s->fpd.apu.cpu);
102
@@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
236
+ int i;
103
return do_mve_sh_ri(s, a, gen_mve_uqshl);
237
+
104
}
238
+ sysbus_init_child_obj(OBJECT(s), "apu-gic",
105
239
+ &s->fpd.apu.gic, sizeof(s->fpd.apu.gic),
106
+static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn)
240
+ gicv3_class_name());
107
+{
241
+ gicbusdev = SYS_BUS_DEVICE(&s->fpd.apu.gic);
108
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
242
+ gicdev = DEVICE(&s->fpd.apu.gic);
109
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
243
+ qdev_prop_set_uint32(gicdev, "revision", 3);
110
+ return false;
244
+ qdev_prop_set_uint32(gicdev, "num-cpu", 2);
111
+ }
245
+ qdev_prop_set_uint32(gicdev, "num-irq", XLNX_VERSAL_NR_IRQS + 32);
112
+ if (!dc_isar_feature(aa32_mve, s) ||
246
+ qdev_prop_set_uint32(gicdev, "len-redist-region-count", 1);
113
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
247
+ qdev_prop_set_uint32(gicdev, "redist-region-count[0]", 2);
114
+ a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 ||
248
+ qdev_prop_set_bit(gicdev, "has-security-extensions", true);
115
+ a->rm == a->rda) {
249
+
116
+ /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */
250
+ object_property_set_bool(OBJECT(&s->fpd.apu.gic), true, "realized",
117
+ unallocated_encoding(s);
251
+ &error_fatal);
118
+ return true;
252
+
253
+ for (i = 0; i < ARRAY_SIZE(addrs); i++) {
254
+ MemoryRegion *mr;
255
+
256
+ mr = sysbus_mmio_get_region(gicbusdev, i);
257
+ memory_region_add_subregion(&s->fpd.apu.mr, addrs[i], mr);
258
+ }
119
+ }
259
+
120
+
260
+ for (i = 0; i < nr_apu_cpus; i++) {
121
+ /* The helper takes care of the sign-extension of the low 8 bits of Rm */
261
+ DeviceState *cpudev = DEVICE(s->fpd.apu.cpu[i]);
122
+ fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]);
262
+ int ppibase = XLNX_VERSAL_NR_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS;
123
+ return true;
263
+ qemu_irq maint_irq;
264
+ int ti;
265
+ /* Mapping from the output timer irq lines from the CPU to the
266
+ * GIC PPI inputs.
267
+ */
268
+ const int timer_irq[] = {
269
+ [GTIMER_PHYS] = VERSAL_TIMER_NS_EL1_IRQ,
270
+ [GTIMER_VIRT] = VERSAL_TIMER_VIRT_IRQ,
271
+ [GTIMER_HYP] = VERSAL_TIMER_NS_EL2_IRQ,
272
+ [GTIMER_SEC] = VERSAL_TIMER_S_EL1_IRQ,
273
+ };
274
+
275
+ for (ti = 0; ti < ARRAY_SIZE(timer_irq); ti++) {
276
+ qdev_connect_gpio_out(cpudev, ti,
277
+ qdev_get_gpio_in(gicdev,
278
+ ppibase + timer_irq[ti]));
279
+ }
280
+ maint_irq = qdev_get_gpio_in(gicdev,
281
+ ppibase + VERSAL_GIC_MAINT_IRQ);
282
+ qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt",
283
+ 0, maint_irq);
284
+ sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ));
285
+ sysbus_connect_irq(gicbusdev, i + nr_apu_cpus,
286
+ qdev_get_gpio_in(cpudev, ARM_CPU_FIQ));
287
+ sysbus_connect_irq(gicbusdev, i + 2 * nr_apu_cpus,
288
+ qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ));
289
+ sysbus_connect_irq(gicbusdev, i + 3 * nr_apu_cpus,
290
+ qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ));
291
+ }
292
+
293
+ for (i = 0; i < XLNX_VERSAL_NR_IRQS; i++) {
294
+ pic[i] = qdev_get_gpio_in(gicdev, i);
295
+ }
296
+}
124
+}
297
+
125
+
298
+static void versal_create_uarts(Versal *s, qemu_irq *pic)
126
+static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a)
299
+{
127
+{
300
+ int i;
128
+ return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr);
301
+
302
+ for (i = 0; i < ARRAY_SIZE(s->lpd.iou.uart); i++) {
303
+ static const int irqs[] = { VERSAL_UART0_IRQ_0, VERSAL_UART1_IRQ_0};
304
+ static const uint64_t addrs[] = { MM_UART0, MM_UART1 };
305
+ char *name = g_strdup_printf("uart%d", i);
306
+ DeviceState *dev;
307
+ MemoryRegion *mr;
308
+
309
+ dev = qdev_create(NULL, "pl011");
310
+ s->lpd.iou.uart[i] = SYS_BUS_DEVICE(dev);
311
+ qdev_prop_set_chr(dev, "chardev", serial_hd(i));
312
+ object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
313
+ qdev_init_nofail(dev);
314
+
315
+ mr = sysbus_mmio_get_region(s->lpd.iou.uart[i], 0);
316
+ memory_region_add_subregion(&s->mr_ps, addrs[i], mr);
317
+
318
+ sysbus_connect_irq(s->lpd.iou.uart[i], 0, pic[irqs[i]]);
319
+ g_free(name);
320
+ }
321
+}
129
+}
322
+
130
+
323
+static void versal_create_gems(Versal *s, qemu_irq *pic)
131
+static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a)
324
+{
132
+{
325
+ int i;
133
+ return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl);
326
+
327
+ for (i = 0; i < ARRAY_SIZE(s->lpd.iou.gem); i++) {
328
+ static const int irqs[] = { VERSAL_GEM0_IRQ_0, VERSAL_GEM1_IRQ_0};
329
+ static const uint64_t addrs[] = { MM_GEM0, MM_GEM1 };
330
+ char *name = g_strdup_printf("gem%d", i);
331
+ NICInfo *nd = &nd_table[i];
332
+ DeviceState *dev;
333
+ MemoryRegion *mr;
334
+
335
+ dev = qdev_create(NULL, "cadence_gem");
336
+ s->lpd.iou.gem[i] = SYS_BUS_DEVICE(dev);
337
+ object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
338
+ if (nd->used) {
339
+ qemu_check_nic_model(nd, "cadence_gem");
340
+ qdev_set_nic_properties(dev, nd);
341
+ }
342
+ object_property_set_int(OBJECT(s->lpd.iou.gem[i]),
343
+ 2, "num-priority-queues",
344
+ &error_abort);
345
+ object_property_set_link(OBJECT(s->lpd.iou.gem[i]),
346
+ OBJECT(&s->mr_ps), "dma",
347
+ &error_abort);
348
+ qdev_init_nofail(dev);
349
+
350
+ mr = sysbus_mmio_get_region(s->lpd.iou.gem[i], 0);
351
+ memory_region_add_subregion(&s->mr_ps, addrs[i], mr);
352
+
353
+ sysbus_connect_irq(s->lpd.iou.gem[i], 0, pic[irqs[i]]);
354
+ g_free(name);
355
+ }
356
+}
134
+}
357
+
135
+
358
+/* This takes the board allocated linear DDR memory and creates aliases
136
/*
359
+ * for each split DDR range/aperture on the Versal address map.
137
* Multiply and multiply accumulate
360
+ */
138
*/
361
+static void versal_map_ddr(Versal *s)
362
+{
363
+ uint64_t size = memory_region_size(s->cfg.mr_ddr);
364
+ /* Describes the various split DDR access regions. */
365
+ static const struct {
366
+ uint64_t base;
367
+ uint64_t size;
368
+ } addr_ranges[] = {
369
+ { MM_TOP_DDR, MM_TOP_DDR_SIZE },
370
+ { MM_TOP_DDR_2, MM_TOP_DDR_2_SIZE },
371
+ { MM_TOP_DDR_3, MM_TOP_DDR_3_SIZE },
372
+ { MM_TOP_DDR_4, MM_TOP_DDR_4_SIZE }
373
+ };
374
+ uint64_t offset = 0;
375
+ int i;
376
+
377
+ assert(ARRAY_SIZE(addr_ranges) == ARRAY_SIZE(s->noc.mr_ddr_ranges));
378
+ for (i = 0; i < ARRAY_SIZE(addr_ranges) && size; i++) {
379
+ char *name;
380
+ uint64_t mapsize;
381
+
382
+ mapsize = size < addr_ranges[i].size ? size : addr_ranges[i].size;
383
+ name = g_strdup_printf("noc-ddr-range%d", i);
384
+ /* Create the MR alias. */
385
+ memory_region_init_alias(&s->noc.mr_ddr_ranges[i], OBJECT(s),
386
+ name, s->cfg.mr_ddr,
387
+ offset, mapsize);
388
+
389
+ /* Map it onto the NoC MR. */
390
+ memory_region_add_subregion(&s->mr_ps, addr_ranges[i].base,
391
+ &s->noc.mr_ddr_ranges[i]);
392
+ offset += mapsize;
393
+ size -= mapsize;
394
+ g_free(name);
395
+ }
396
+}
397
+
398
+static void versal_unimp_area(Versal *s, const char *name,
399
+ MemoryRegion *mr,
400
+ hwaddr base, hwaddr size)
401
+{
402
+ DeviceState *dev = qdev_create(NULL, TYPE_UNIMPLEMENTED_DEVICE);
403
+ MemoryRegion *mr_dev;
404
+
405
+ qdev_prop_set_string(dev, "name", name);
406
+ qdev_prop_set_uint64(dev, "size", size);
407
+ object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
408
+ qdev_init_nofail(dev);
409
+
410
+ mr_dev = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
411
+ memory_region_add_subregion(mr, base, mr_dev);
412
+}
413
+
414
+static void versal_unimp(Versal *s)
415
+{
416
+ versal_unimp_area(s, "psm", &s->mr_ps,
417
+ MM_PSM_START, MM_PSM_END - MM_PSM_START);
418
+ versal_unimp_area(s, "crl", &s->mr_ps,
419
+ MM_CRL, MM_CRL_SIZE);
420
+ versal_unimp_area(s, "crf", &s->mr_ps,
421
+ MM_FPD_CRF, MM_FPD_CRF_SIZE);
422
+ versal_unimp_area(s, "iou-scntr", &s->mr_ps,
423
+ MM_IOU_SCNTR, MM_IOU_SCNTR_SIZE);
424
+ versal_unimp_area(s, "iou-scntr-seucre", &s->mr_ps,
425
+ MM_IOU_SCNTRS, MM_IOU_SCNTRS_SIZE);
426
+}
427
+
428
+static void versal_realize(DeviceState *dev, Error **errp)
429
+{
430
+ Versal *s = XLNX_VERSAL(dev);
431
+ qemu_irq pic[XLNX_VERSAL_NR_IRQS];
432
+
433
+ versal_create_apu_cpus(s);
434
+ versal_create_apu_gic(s, pic);
435
+ versal_create_uarts(s, pic);
436
+ versal_create_gems(s, pic);
437
+ versal_map_ddr(s);
438
+ versal_unimp(s);
439
+
440
+ /* Create the On Chip Memory (OCM). */
441
+ memory_region_init_ram(&s->lpd.mr_ocm, OBJECT(s), "ocm",
442
+ MM_OCM_SIZE, &error_fatal);
443
+
444
+ memory_region_add_subregion_overlap(&s->mr_ps, MM_OCM, &s->lpd.mr_ocm, 0);
445
+ memory_region_add_subregion_overlap(&s->fpd.apu.mr, 0, &s->mr_ps, 0);
446
+}
447
+
448
+static void versal_init(Object *obj)
449
+{
450
+ Versal *s = XLNX_VERSAL(obj);
451
+
452
+ memory_region_init(&s->fpd.apu.mr, obj, "mr-apu", UINT64_MAX);
453
+ memory_region_init(&s->mr_ps, obj, "mr-ps-switch", UINT64_MAX);
454
+}
455
+
456
+static Property versal_properties[] = {
457
+ DEFINE_PROP_LINK("ddr", Versal, cfg.mr_ddr, TYPE_MEMORY_REGION,
458
+ MemoryRegion *),
459
+ DEFINE_PROP_UINT32("psci-conduit", Versal, cfg.psci_conduit, 0),
460
+ DEFINE_PROP_END_OF_LIST()
461
+};
462
+
463
+static void versal_class_init(ObjectClass *klass, void *data)
464
+{
465
+ DeviceClass *dc = DEVICE_CLASS(klass);
466
+
467
+ dc->realize = versal_realize;
468
+ dc->props = versal_properties;
469
+ /* No VMSD since we haven't got any top-level SoC state to save. */
470
+}
471
+
472
+static const TypeInfo versal_info = {
473
+ .name = TYPE_XLNX_VERSAL,
474
+ .parent = TYPE_SYS_BUS_DEVICE,
475
+ .instance_size = sizeof(Versal),
476
+ .instance_init = versal_init,
477
+ .class_init = versal_class_init,
478
+};
479
+
480
+static void versal_register_types(void)
481
+{
482
+ type_register_static(&versal_info);
483
+}
484
+
485
+type_init(versal_register_types);
486
diff --git a/default-configs/aarch64-softmmu.mak b/default-configs/aarch64-softmmu.mak
487
index XXXXXXX..XXXXXXX 100644
488
--- a/default-configs/aarch64-softmmu.mak
489
+++ b/default-configs/aarch64-softmmu.mak
490
@@ -XXX,XX +XXX,XX @@ CONFIG_DDC=y
491
CONFIG_DPCD=y
492
CONFIG_XLNX_ZYNQMP=y
493
CONFIG_XLNX_ZYNQMP_ARM=y
494
+CONFIG_XLNX_VERSAL=y
495
CONFIG_ARM_SMMUV3=y
496
--
139
--
497
2.19.1
140
2.20.1
498
141
499
142
diff view generated by jsdifflib

Patchew 2.1-devel-b67e4c2

© 2016 - 2025 Red Hat, Inc.