1
target-arm queue for rc1 -- these are all bug fixes.
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 b9404bf592e7ba74180e1a54ed7a266ec6ee67f2:
7
8
Merge remote-tracking branch 'remotes/dgilbert/tags/pull-hmp-20190715' into staging (2019-07-15 12:22:07 +0100)
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-20190715
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 51c9122e92b776a3f16af0b9282f1dc5012e2a19:
9
for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8:
15
10
16
target/arm: NS BusFault on vector table fetch escalates to NS HardFault (2019-07-15 14:17:04 +0100)
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
* report ARMv8-A FP support for AArch32 -cpu max
15
* more MVE instructions
21
* hw/ssi/xilinx_spips: Avoid AXI writes to the LQSPI linear memory
16
* hw/gpio/gpio_pwr: use shutdown function for reboot
22
* hw/ssi/xilinx_spips: Avoid out-of-bound access to lqspi_buf[]
17
* target/arm: Check NaN mode before silencing NaN
23
* hw/ssi/mss-spi: Avoid crash when reading empty RX FIFO
18
* tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine
24
* hw/display/xlnx_dp: Avoid crash when reading empty RX FIFO
19
* hw/arm: Add basic power management to raspi.
25
* hw/arm/virt: Fix non-secure flash mode
20
* docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc
26
* pl031: Correctly migrate state when using -rtc clock=host
27
* fix regression that meant arm926 and arm1026 lost VFP
28
double-precision support
29
* v8M: NS BusFault on vector table fetch escalates to NS HardFault
30
21
31
----------------------------------------------------------------
22
----------------------------------------------------------------
32
Alex Bennée (1):
23
Joe Komlodi (1):
33
target/arm: report ARMv8-A FP support for AArch32 -cpu max
24
target/arm: Check NaN mode before silencing NaN
34
25
35
David Engraf (1):
26
Maxim Uvarov (1):
36
hw/arm/virt: Fix non-secure flash mode
27
hw/gpio/gpio_pwr: use shutdown function for reboot
37
28
38
Peter Maydell (3):
29
Nolan Leake (1):
39
pl031: Correctly migrate state when using -rtc clock=host
30
hw/arm: Add basic power management to raspi.
40
target/arm: Set VFP-related MVFR0 fields for arm926 and arm1026
41
target/arm: NS BusFault on vector table fetch escalates to NS HardFault
42
31
43
Philippe Mathieu-Daudé (5):
32
Patrick Venture (2):
44
hw/ssi/xilinx_spips: Convert lqspi_read() to read_with_attrs
33
docs/system/arm: Add quanta-q7l1-bmc reference
45
hw/ssi/xilinx_spips: Avoid AXI writes to the LQSPI linear memory
34
docs/system/arm: Add quanta-gbs-bmc reference
46
hw/ssi/xilinx_spips: Avoid out-of-bound access to lqspi_buf[]
47
hw/ssi/mss-spi: Avoid crash when reading empty RX FIFO
48
hw/display/xlnx_dp: Avoid crash when reading empty RX FIFO
49
35
50
include/hw/timer/pl031.h | 2 ++
36
Peter Maydell (18):
51
hw/arm/virt.c | 2 +-
37
target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation
52
hw/core/machine.c | 1 +
38
target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH
53
hw/display/xlnx_dp.c | 15 +++++---
39
target/arm: Make asimd_imm_const() public
54
hw/ssi/mss-spi.c | 8 ++++-
40
target/arm: Use asimd_imm_const for A64 decode
55
hw/ssi/xilinx_spips.c | 43 +++++++++++++++-------
41
target/arm: Use dup_const() instead of bitfield_replicate()
56
hw/timer/pl031.c | 92 +++++++++++++++++++++++++++++++++++++++++++++---
42
target/arm: Implement MVE logical immediate insns
57
target/arm/cpu.c | 16 +++++++++
43
target/arm: Implement MVE vector shift left by immediate insns
58
target/arm/m_helper.c | 21 ++++++++---
44
target/arm: Implement MVE vector shift right by immediate insns
59
9 files changed, 174 insertions(+), 26 deletions(-)
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
60
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
1
From: David Engraf <david.engraf@sysgo.com>
1
From: Patrick Venture <venture@google.com>
2
2
3
Using the whole 128 MiB flash in non-secure mode is not working because
3
Adds a line-item reference to the supported quanta-q71l-bmc aspeed
4
virt_flash_fdt() expects the same address for secure_sysmem and sysmem.
4
entry.
5
This is not correctly handled by caller because it forwards NULL for
6
secure_sysmem in non-secure flash mode.
7
5
8
Fixed by using sysmem when secure_sysmem is NULL.
6
Signed-off-by: Patrick Venture <venture@google.com>
9
7
Reviewed-by: Cédric Le Goater <clg@kaod.org>
10
Signed-off-by: David Engraf <david.engraf@sysgo.com>
8
Message-id: 20210615192848.1065297-2-venture@google.com
11
Message-id: 20190712075002.14326-1-david.engraf@sysgo.com
12
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
---
10
---
15
hw/arm/virt.c | 2 +-
11
docs/system/arm/aspeed.rst | 1 +
16
1 file changed, 1 insertion(+), 1 deletion(-)
12
1 file changed, 1 insertion(+)
17
13
18
diff --git a/hw/arm/virt.c b/hw/arm/virt.c
14
diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst
19
index XXXXXXX..XXXXXXX 100644
15
index XXXXXXX..XXXXXXX 100644
20
--- a/hw/arm/virt.c
16
--- a/docs/system/arm/aspeed.rst
21
+++ b/hw/arm/virt.c
17
+++ b/docs/system/arm/aspeed.rst
22
@@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine)
18
@@ -XXX,XX +XXX,XX @@ etc.
23
&machine->device_memory->mr);
19
AST2400 SoC based machines :
24
}
20
25
21
- ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC
26
- virt_flash_fdt(vms, sysmem, secure_sysmem);
22
+- ``quanta-q71l-bmc`` OpenBMC Quanta BMC
27
+ virt_flash_fdt(vms, sysmem, secure_sysmem ?: sysmem);
23
28
24
AST2500 SoC based machines :
29
create_gic(vms, pic);
30
25
31
--
26
--
32
2.20.1
27
2.20.1
33
28
34
29
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
1
From: Patrick Venture <venture@google.com>
2
2
3
Reading the RX_DATA register when the RX_FIFO is empty triggers
3
Add line item reference to quanta-gbs-bmc machine.
4
an abort. This can be easily reproduced:
5
4
6
$ qemu-system-arm -M emcraft-sf2 -monitor stdio -S
5
Signed-off-by: Patrick Venture <venture@google.com>
7
QEMU 4.0.50 monitor - type 'help' for more information
6
Reviewed-by: Cédric Le Goater <clg@kaod.org>
8
(qemu) x 0x40001010
7
Message-id: 20210615192848.1065297-3-venture@google.com
9
Aborted (core dumped)
8
[PMM: fixed underline Sphinx warning]
10
11
(gdb) bt
12
#1 0x00007f035874f895 in abort () at /lib64/libc.so.6
13
#2 0x00005628686591ff in fifo8_pop (fifo=0x56286a9a4c68) at util/fifo8.c:66
14
#3 0x00005628683e0b8e in fifo32_pop (fifo=0x56286a9a4c68) at include/qemu/fifo32.h:137
15
#4 0x00005628683e0efb in spi_read (opaque=0x56286a9a4850, addr=4, size=4) at hw/ssi/mss-spi.c:168
16
#5 0x0000562867f96801 in memory_region_read_accessor (mr=0x56286a9a4b60, addr=16, value=0x7ffeecb0c5c8, size=4, shift=0, mask=4294967295, attrs=...) at memory.c:439
17
#6 0x0000562867f96cdb in access_with_adjusted_size (addr=16, value=0x7ffeecb0c5c8, size=4, access_size_min=1, access_size_max=4, access_fn=0x562867f967c3 <memory_region_read_accessor>, mr=0x56286a9a4b60, attrs=...) at memory.c:569
18
#7 0x0000562867f99940 in memory_region_dispatch_read1 (mr=0x56286a9a4b60, addr=16, pval=0x7ffeecb0c5c8, size=4, attrs=...) at memory.c:1420
19
#8 0x0000562867f99a08 in memory_region_dispatch_read (mr=0x56286a9a4b60, addr=16, pval=0x7ffeecb0c5c8, size=4, attrs=...) at memory.c:1447
20
#9 0x0000562867f38721 in flatview_read_continue (fv=0x56286aec6360, addr=1073745936, attrs=..., buf=0x7ffeecb0c7c0 "\340ǰ\354\376\177", len=4, addr1=16, l=4, mr=0x56286a9a4b60) at exec.c:3385
21
#10 0x0000562867f38874 in flatview_read (fv=0x56286aec6360, addr=1073745936, attrs=..., buf=0x7ffeecb0c7c0 "\340ǰ\354\376\177", len=4) at exec.c:3423
22
#11 0x0000562867f388ea in address_space_read_full (as=0x56286aa3e890, addr=1073745936, attrs=..., buf=0x7ffeecb0c7c0 "\340ǰ\354\376\177", len=4) at exec.c:3436
23
#12 0x0000562867f389c5 in address_space_rw (as=0x56286aa3e890, addr=1073745936, attrs=..., buf=0x7ffeecb0c7c0 "\340ǰ\354\376\177", len=4, is_write=false) at exec.c:3466
24
#13 0x0000562867f3bdd7 in cpu_memory_rw_debug (cpu=0x56286aa19d00, addr=1073745936, buf=0x7ffeecb0c7c0 "\340ǰ\354\376\177", len=4, is_write=0) at exec.c:3976
25
#14 0x000056286811ed51 in memory_dump (mon=0x56286a8c32d0, count=1, format=120, wsize=4, addr=1073745936, is_physical=0) at monitor/misc.c:730
26
#15 0x000056286811eff1 in hmp_memory_dump (mon=0x56286a8c32d0, qdict=0x56286b15c400) at monitor/misc.c:785
27
#16 0x00005628684740ee in handle_hmp_command (mon=0x56286a8c32d0, cmdline=0x56286a8caeb2 "0x40001010") at monitor/hmp.c:1082
28
29
From the datasheet "Actel SmartFusion Microcontroller Subsystem
30
User's Guide" Rev.1, Table 13-3 "SPI Register Summary", this
31
register has a reset value of 0.
32
33
Check the FIFO is not empty before accessing it, else log an
34
error message.
35
36
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
37
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
38
Message-id: 20190709113715.7761-3-philmd@redhat.com
39
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
40
---
10
---
41
hw/ssi/mss-spi.c | 8 +++++++-
11
docs/system/arm/nuvoton.rst | 5 +++--
42
1 file changed, 7 insertions(+), 1 deletion(-)
12
1 file changed, 3 insertions(+), 2 deletions(-)
43
13
44
diff --git a/hw/ssi/mss-spi.c b/hw/ssi/mss-spi.c
14
diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst
45
index XXXXXXX..XXXXXXX 100644
15
index XXXXXXX..XXXXXXX 100644
46
--- a/hw/ssi/mss-spi.c
16
--- a/docs/system/arm/nuvoton.rst
47
+++ b/hw/ssi/mss-spi.c
17
+++ b/docs/system/arm/nuvoton.rst
48
@@ -XXX,XX +XXX,XX @@ spi_read(void *opaque, hwaddr addr, unsigned int size)
18
@@ -XXX,XX +XXX,XX @@
49
case R_SPI_RX:
19
-Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``)
50
s->regs[R_SPI_STATUS] &= ~S_RXFIFOFUL;
20
-=====================================================
51
s->regs[R_SPI_STATUS] &= ~S_RXCHOVRF;
21
+Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``)
52
- ret = fifo32_pop(&s->rx_fifo);
22
+================================================================
53
+ if (fifo32_is_empty(&s->rx_fifo)) {
23
54
+ qemu_log_mask(LOG_GUEST_ERROR,
24
The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are
55
+ "%s: Reading empty RX_FIFO\n",
25
designed to be used as Baseboard Management Controllers (BMCs) in various
56
+ __func__);
26
@@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip :
57
+ } else {
27
The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and
58
+ ret = fifo32_pop(&s->rx_fifo);
28
Hyperscale applications. The following machines are based on this chip :
59
+ }
29
60
if (fifo32_is_empty(&s->rx_fifo)) {
30
+- ``quanta-gbs-bmc`` Quanta GBS server BMC
61
s->regs[R_SPI_STATUS] |= S_RXFIFOEMP;
31
- ``quanta-gsj`` Quanta GSJ server BMC
62
}
32
33
There are also two more SoCs, NPCM710 and NPCM705, which are single-core
63
--
34
--
64
2.20.1
35
2.20.1
65
36
66
37
diff view generated by jsdifflib
1
The PL031 RTC tracks the difference between the guest RTC
1
From: Nolan Leake <nolan@sigbus.net>
2
and the host RTC using a tick_offset field. For migration,
2
3
however, we currently always migrate the offset between
3
This is just enough to make reboot and poweroff work. Works for
4
the guest and the vm_clock, even if the RTC clock is not
4
linux, u-boot, and the arm trusted firmware. Not tested, but should
5
the same as the vm_clock; this was an attempt to retain
5
work for plan9, and bare-metal/hobby OSes, since they seem to generally
6
migration backwards compatibility.
6
do what linux does for reset.
7
7
8
Unfortunately this results in the RTC behaving oddly across
8
The watchdog timer functionality is not yet implemented.
9
a VM state save and restore -- since the VM clock stands still
9
10
across save-then-restore, regardless of how much real world
10
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64
11
time has elapsed, the guest RTC ends up out of sync with the
11
Signed-off-by: Nolan Leake <nolan@sigbus.net>
12
host RTC in the restored VM.
12
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
13
13
Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
14
Fix this by migrating the raw tick_offset. To retain migration
14
Message-id: 20210625210209.1870217-1-nolan@sigbus.net
15
compatibility as far as possible, we have a new property
15
[PMM: tweaked commit title; fixed region size to 0x200;
16
migrate-tick-offset; by default this is 'true' and we will
16
moved header file to include/]
17
migrate the true tick offset in a new subsection; if the
18
incoming data has no subsection we fall back to the old
19
vm_clock-based offset information, so old->new migration
20
compatibility is preserved. For complete new->old migration
21
compatibility, the property is set to 'false' for 4.0 and
22
earlier machine types (this will only affect 'virt-4.0'
23
and below, as none of the other pl031-using machines are
24
versioned).
25
26
Reported-by: Russell King <rmk@armlinux.org.uk>
27
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
28
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
29
Message-id: 20190709143912.28905-1-peter.maydell@linaro.org
30
---
18
---
31
include/hw/timer/pl031.h | 2 +
19
include/hw/arm/bcm2835_peripherals.h | 3 +-
32
hw/core/machine.c | 1 +
20
include/hw/misc/bcm2835_powermgt.h | 29 +++++
33
hw/timer/pl031.c | 92 ++++++++++++++++++++++++++++++++++++++--
21
hw/arm/bcm2835_peripherals.c | 13 ++-
34
3 files changed, 91 insertions(+), 4 deletions(-)
22
hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++
35
23
hw/misc/meson.build | 1 +
36
diff --git a/include/hw/timer/pl031.h b/include/hw/timer/pl031.h
24
5 files changed, 204 insertions(+), 2 deletions(-)
25
create mode 100644 include/hw/misc/bcm2835_powermgt.h
26
create mode 100644 hw/misc/bcm2835_powermgt.c
27
28
diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h
37
index XXXXXXX..XXXXXXX 100644
29
index XXXXXXX..XXXXXXX 100644
38
--- a/include/hw/timer/pl031.h
30
--- a/include/hw/arm/bcm2835_peripherals.h
39
+++ b/include/hw/timer/pl031.h
31
+++ b/include/hw/arm/bcm2835_peripherals.h
40
@@ -XXX,XX +XXX,XX @@ typedef struct PL031State {
32
@@ -XXX,XX +XXX,XX @@
41
*/
33
#include "hw/misc/bcm2835_mphi.h"
42
uint32_t tick_offset_vmstate;
34
#include "hw/misc/bcm2835_thermal.h"
43
uint32_t tick_offset;
35
#include "hw/misc/bcm2835_cprman.h"
44
+ bool tick_offset_migrated;
36
+#include "hw/misc/bcm2835_powermgt.h"
45
+ bool migrate_tick_offset;
37
#include "hw/sd/sdhci.h"
46
38
#include "hw/sd/bcm2835_sdhost.h"
47
uint32_t mr;
39
#include "hw/gpio/bcm2835_gpio.h"
48
uint32_t lr;
40
@@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState {
49
diff --git a/hw/core/machine.c b/hw/core/machine.c
41
BCM2835MphiState mphi;
42
UnimplementedDeviceState txp;
43
UnimplementedDeviceState armtmr;
44
- UnimplementedDeviceState powermgt;
45
+ BCM2835PowerMgtState powermgt;
46
BCM2835CprmanState cprman;
47
PL011State uart0;
48
BCM2835AuxState aux;
49
diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h
50
new file mode 100644
51
index XXXXXXX..XXXXXXX
52
--- /dev/null
53
+++ b/include/hw/misc/bcm2835_powermgt.h
54
@@ -XXX,XX +XXX,XX @@
55
+/*
56
+ * BCM2835 Power Management emulation
57
+ *
58
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
59
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
60
+ *
61
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
62
+ * See the COPYING file in the top-level directory.
63
+ */
64
+
65
+#ifndef BCM2835_POWERMGT_H
66
+#define BCM2835_POWERMGT_H
67
+
68
+#include "hw/sysbus.h"
69
+#include "qom/object.h"
70
+
71
+#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt"
72
+OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT)
73
+
74
+struct BCM2835PowerMgtState {
75
+ SysBusDevice busdev;
76
+ MemoryRegion iomem;
77
+
78
+ uint32_t rstc;
79
+ uint32_t rsts;
80
+ uint32_t wdog;
81
+};
82
+
83
+#endif
84
diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c
50
index XXXXXXX..XXXXXXX 100644
85
index XXXXXXX..XXXXXXX 100644
51
--- a/hw/core/machine.c
86
--- a/hw/arm/bcm2835_peripherals.c
52
+++ b/hw/core/machine.c
87
+++ b/hw/arm/bcm2835_peripherals.c
53
@@ -XXX,XX +XXX,XX @@ GlobalProperty hw_compat_4_0[] = {
88
@@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj)
54
{ "virtio-gpu-pci", "edid", "false" },
89
55
{ "virtio-device", "use-started", "false" },
90
object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr",
56
{ "virtio-balloon-device", "qemu-4-0-config-size", "true" },
91
OBJECT(&s->gpu_bus_mr));
57
+ { "pl031", "migrate-tick-offset", "false" },
92
+
58
};
93
+ /* Power Management */
59
const size_t hw_compat_4_0_len = G_N_ELEMENTS(hw_compat_4_0);
94
+ object_initialize_child(obj, "powermgt", &s->powermgt,
60
95
+ TYPE_BCM2835_POWERMGT);
61
diff --git a/hw/timer/pl031.c b/hw/timer/pl031.c
62
index XXXXXXX..XXXXXXX 100644
63
--- a/hw/timer/pl031.c
64
+++ b/hw/timer/pl031.c
65
@@ -XXX,XX +XXX,XX @@ static int pl031_pre_save(void *opaque)
66
{
67
PL031State *s = opaque;
68
69
- /* tick_offset is base_time - rtc_clock base time. Instead, we want to
70
- * store the base time relative to the QEMU_CLOCK_VIRTUAL for backwards-compatibility. */
71
+ /*
72
+ * The PL031 device model code uses the tick_offset field, which is
73
+ * the offset between what the guest RTC should read and what the
74
+ * QEMU rtc_clock reads:
75
+ * guest_rtc = rtc_clock + tick_offset
76
+ * and so
77
+ * tick_offset = guest_rtc - rtc_clock
78
+ *
79
+ * We want to migrate this offset, which sounds straightforward.
80
+ * Unfortunately older versions of QEMU migrated a conversion of this
81
+ * offset into an offset from the vm_clock. (This was in turn an
82
+ * attempt to be compatible with even older QEMU versions, but it
83
+ * has incorrect behaviour if the rtc_clock is not the same as the
84
+ * vm_clock.) So we put the actual tick_offset into a migration
85
+ * subsection, and the backwards-compatible time-relative-to-vm_clock
86
+ * in the main migration state.
87
+ *
88
+ * Calculate base time relative to QEMU_CLOCK_VIRTUAL:
89
+ */
90
int64_t delta = qemu_clock_get_ns(rtc_clock) - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
91
s->tick_offset_vmstate = s->tick_offset + delta / NANOSECONDS_PER_SECOND;
92
93
return 0;
94
}
96
}
95
97
96
+static int pl031_pre_load(void *opaque)
98
static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
97
+{
99
@@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp)
98
+ PL031State *s = opaque;
100
qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ,
99
+
101
INTERRUPT_USB));
100
+ s->tick_offset_migrated = false;
102
101
+ return 0;
103
+ /* Power Management */
102
+}
104
+ if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) {
103
+
105
+ return;
104
static int pl031_post_load(void *opaque, int version_id)
106
+ }
105
{
107
+
106
PL031State *s = opaque;
108
+ memory_region_add_subregion(&s->peri_mr, PM_OFFSET,
107
109
+ sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0));
108
- int64_t delta = qemu_clock_get_ns(rtc_clock) - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
110
+
109
- s->tick_offset = s->tick_offset_vmstate - delta / NANOSECONDS_PER_SECOND;
111
create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000);
110
+ /*
112
create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40);
111
+ * If we got the tick_offset subsection, then we can just use
113
- create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114);
112
+ * the value in that. Otherwise the source is an older QEMU and
114
create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100);
113
+ * has given us the offset from the vm_clock; convert it back to
115
create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100);
114
+ * an offset from the rtc_clock. This will cause time to incorrectly
116
create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20);
115
+ * go backwards compared to the host RTC, but this is unavoidable.
117
diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c
116
+ */
118
new file mode 100644
117
+
119
index XXXXXXX..XXXXXXX
118
+ if (!s->tick_offset_migrated) {
120
--- /dev/null
119
+ int64_t delta = qemu_clock_get_ns(rtc_clock) -
121
+++ b/hw/misc/bcm2835_powermgt.c
120
+ qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL);
122
@@ -XXX,XX +XXX,XX @@
121
+ s->tick_offset = s->tick_offset_vmstate -
123
+/*
122
+ delta / NANOSECONDS_PER_SECOND;
124
+ * BCM2835 Power Management emulation
123
+ }
125
+ *
124
pl031_set_alarm(s);
126
+ * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com>
125
return 0;
127
+ * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net>
126
}
128
+ *
127
129
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
128
+static int pl031_tick_offset_post_load(void *opaque, int version_id)
130
+ * See the COPYING file in the top-level directory.
129
+{
131
+ */
130
+ PL031State *s = opaque;
132
+
131
+
133
+#include "qemu/osdep.h"
132
+ s->tick_offset_migrated = true;
134
+#include "qemu/log.h"
133
+ return 0;
135
+#include "qemu/module.h"
134
+}
136
+#include "hw/misc/bcm2835_powermgt.h"
135
+
137
+#include "migration/vmstate.h"
136
+static bool pl031_tick_offset_needed(void *opaque)
138
+#include "sysemu/runstate.h"
137
+{
139
+
138
+ PL031State *s = opaque;
140
+#define PASSWORD 0x5a000000
139
+
141
+#define PASSWORD_MASK 0xff000000
140
+ return s->migrate_tick_offset;
142
+
141
+}
143
+#define R_RSTC 0x1c
142
+
144
+#define V_RSTC_RESET 0x20
143
+static const VMStateDescription vmstate_pl031_tick_offset = {
145
+#define R_RSTS 0x20
144
+ .name = "pl031/tick-offset",
146
+#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */
147
+#define R_WDOG 0x24
148
+
149
+static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset,
150
+ unsigned size)
151
+{
152
+ BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque;
153
+ uint32_t res = 0;
154
+
155
+ switch (offset) {
156
+ case R_RSTC:
157
+ res = s->rstc;
158
+ break;
159
+ case R_RSTS:
160
+ res = s->rsts;
161
+ break;
162
+ case R_WDOG:
163
+ res = s->wdog;
164
+ break;
165
+
166
+ default:
167
+ qemu_log_mask(LOG_UNIMP,
168
+ "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx
169
+ "\n", offset);
170
+ res = 0;
171
+ break;
172
+ }
173
+
174
+ return res;
175
+}
176
+
177
+static void bcm2835_powermgt_write(void *opaque, hwaddr offset,
178
+ uint64_t value, unsigned size)
179
+{
180
+ BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque;
181
+
182
+ if ((value & PASSWORD_MASK) != PASSWORD) {
183
+ qemu_log_mask(LOG_GUEST_ERROR,
184
+ "bcm2835_powermgt_write: Bad password 0x%"PRIx64
185
+ " at offset 0x%08"HWADDR_PRIx"\n",
186
+ value, offset);
187
+ return;
188
+ }
189
+
190
+ value = value & ~PASSWORD_MASK;
191
+
192
+ switch (offset) {
193
+ case R_RSTC:
194
+ s->rstc = value;
195
+ if (value & V_RSTC_RESET) {
196
+ if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) {
197
+ qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
198
+ } else {
199
+ qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET);
200
+ }
201
+ }
202
+ break;
203
+ case R_RSTS:
204
+ qemu_log_mask(LOG_UNIMP,
205
+ "bcm2835_powermgt_write: RSTS\n");
206
+ s->rsts = value;
207
+ break;
208
+ case R_WDOG:
209
+ qemu_log_mask(LOG_UNIMP,
210
+ "bcm2835_powermgt_write: WDOG\n");
211
+ s->wdog = value;
212
+ break;
213
+
214
+ default:
215
+ qemu_log_mask(LOG_UNIMP,
216
+ "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx
217
+ "\n", offset);
218
+ break;
219
+ }
220
+}
221
+
222
+static const MemoryRegionOps bcm2835_powermgt_ops = {
223
+ .read = bcm2835_powermgt_read,
224
+ .write = bcm2835_powermgt_write,
225
+ .endianness = DEVICE_NATIVE_ENDIAN,
226
+ .impl.min_access_size = 4,
227
+ .impl.max_access_size = 4,
228
+};
229
+
230
+static const VMStateDescription vmstate_bcm2835_powermgt = {
231
+ .name = TYPE_BCM2835_POWERMGT,
145
+ .version_id = 1,
232
+ .version_id = 1,
146
+ .minimum_version_id = 1,
233
+ .minimum_version_id = 1,
147
+ .needed = pl031_tick_offset_needed,
148
+ .post_load = pl031_tick_offset_post_load,
149
+ .fields = (VMStateField[]) {
234
+ .fields = (VMStateField[]) {
150
+ VMSTATE_UINT32(tick_offset, PL031State),
235
+ VMSTATE_UINT32(rstc, BCM2835PowerMgtState),
236
+ VMSTATE_UINT32(rsts, BCM2835PowerMgtState),
237
+ VMSTATE_UINT32(wdog, BCM2835PowerMgtState),
151
+ VMSTATE_END_OF_LIST()
238
+ VMSTATE_END_OF_LIST()
152
+ }
239
+ }
153
+};
240
+};
154
+
241
+
155
static const VMStateDescription vmstate_pl031 = {
242
+static void bcm2835_powermgt_init(Object *obj)
156
.name = "pl031",
243
+{
157
.version_id = 1,
244
+ BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj);
158
.minimum_version_id = 1,
245
+
159
.pre_save = pl031_pre_save,
246
+ memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s,
160
+ .pre_load = pl031_pre_load,
247
+ TYPE_BCM2835_POWERMGT, 0x200);
161
.post_load = pl031_post_load,
248
+ sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem);
162
.fields = (VMStateField[]) {
249
+}
163
VMSTATE_UINT32(tick_offset_vmstate, PL031State),
250
+
164
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pl031 = {
251
+static void bcm2835_powermgt_reset(DeviceState *dev)
165
VMSTATE_UINT32(im, PL031State),
252
+{
166
VMSTATE_UINT32(is, PL031State),
253
+ BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev);
167
VMSTATE_END_OF_LIST()
254
+
168
+ },
255
+ /* https://elinux.org/BCM2835_registers#PM */
169
+ .subsections = (const VMStateDescription*[]) {
256
+ s->rstc = 0x00000102;
170
+ &vmstate_pl031_tick_offset,
257
+ s->rsts = 0x00001000;
171
+ NULL
258
+ s->wdog = 0x00000000;
172
}
259
+}
173
};
260
+
174
261
+static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data)
175
+static Property pl031_properties[] = {
262
+{
176
+ /*
263
+ DeviceClass *dc = DEVICE_CLASS(klass);
177
+ * True to correctly migrate the tick offset of the RTC. False to
264
+
178
+ * obtain backward migration compatibility with older QEMU versions,
265
+ dc->reset = bcm2835_powermgt_reset;
179
+ * at the expense of the guest RTC going backwards compared with the
266
+ dc->vmsd = &vmstate_bcm2835_powermgt;
180
+ * host RTC when the VM is saved/restored if using -rtc host.
267
+}
181
+ * (Even if set to 'true' older QEMU can migrate forward to newer QEMU;
268
+
182
+ * 'false' also permits newer QEMU to migrate to older QEMU.)
269
+static TypeInfo bcm2835_powermgt_info = {
183
+ */
270
+ .name = TYPE_BCM2835_POWERMGT,
184
+ DEFINE_PROP_BOOL("migrate-tick-offset",
271
+ .parent = TYPE_SYS_BUS_DEVICE,
185
+ PL031State, migrate_tick_offset, true),
272
+ .instance_size = sizeof(BCM2835PowerMgtState),
186
+ DEFINE_PROP_END_OF_LIST()
273
+ .class_init = bcm2835_powermgt_class_init,
187
+};
274
+ .instance_init = bcm2835_powermgt_init,
188
+
275
+};
189
static void pl031_class_init(ObjectClass *klass, void *data)
276
+
190
{
277
+static void bcm2835_powermgt_register_types(void)
191
DeviceClass *dc = DEVICE_CLASS(klass);
278
+{
192
279
+ type_register_static(&bcm2835_powermgt_info);
193
dc->vmsd = &vmstate_pl031;
280
+}
194
+ dc->props = pl031_properties;
281
+
195
}
282
+type_init(bcm2835_powermgt_register_types)
196
283
diff --git a/hw/misc/meson.build b/hw/misc/meson.build
197
static const TypeInfo pl031_info = {
284
index XXXXXXX..XXXXXXX 100644
285
--- a/hw/misc/meson.build
286
+++ b/hw/misc/meson.build
287
@@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files(
288
'bcm2835_rng.c',
289
'bcm2835_thermal.c',
290
'bcm2835_cprman.c',
291
+ 'bcm2835_powermgt.c',
292
))
293
softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c'))
294
softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c'))
198
--
295
--
199
2.20.1
296
2.20.1
200
297
201
298
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
Both lqspi_read() and lqspi_load_cache() expect a 32-bit
3
Add a test booting and quickly shutdown a raspi2 machine,
4
aligned address.
4
to test the power management model:
5
5
6
>From UG1085 datasheet [*] chapter on 'Quad-SPI Controller':
6
(1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd:
7
console: [ 0.000000] Booting Linux on physical CPU 0xf00
8
console: [ 0.000000] Linux version 4.14.98-v7+ (dom@dom-XPS-13-9370) (gcc version 4.9.3 (crosstool-NG crosstool-ng-1.22.0-88-g8460611)) #1200 SMP Tue Feb 12 20:27:48 GMT 2019
9
console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d
10
console: [ 0.000000] CPU: div instructions available: patching division code
11
console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache
12
console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B
13
...
14
console: Boot successful.
15
console: cat /proc/cpuinfo
16
console: / # cat /proc/cpuinfo
17
...
18
console: processor : 3
19
console: model name : ARMv7 Processor rev 5 (v7l)
20
console: BogoMIPS : 125.00
21
console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm
22
console: CPU implementer : 0x41
23
console: CPU architecture: 7
24
console: CPU variant : 0x0
25
console: CPU part : 0xc07
26
console: CPU revision : 5
27
console: Hardware : BCM2835
28
console: Revision : 0000
29
console: Serial : 0000000000000000
30
console: cat /proc/iomem
31
console: / # cat /proc/iomem
32
console: 00000000-3bffffff : System RAM
33
console: 00008000-00afffff : Kernel code
34
console: 00c00000-00d468ef : Kernel data
35
console: 3f006000-3f006fff : dwc_otg
36
console: 3f007000-3f007eff : /soc/dma@7e007000
37
console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880
38
console: 3f100000-3f100027 : /soc/watchdog@7e100000
39
console: 3f101000-3f102fff : /soc/cprman@7e101000
40
console: 3f200000-3f2000b3 : /soc/gpio@7e200000
41
PASS (24.59 s)
42
RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0
43
JOB TIME : 25.02 s
7
44
8
Transfer Size Limitations
45
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
9
46
Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com>
10
Because of the 32-bit wide TX, RX, and generic FIFO, all
47
Message-id: 20210531113837.1689775-1-f4bug@amsat.org
11
APB/AXI transfers must be an integer multiple of 4-bytes.
12
Shorter transfers are not possible.
13
14
Set MemoryRegionOps.impl values to force 32-bit accesses,
15
this way we are sure we do not access the lqspi_buf[] array
16
out of bound.
17
18
[*] https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf
19
20
Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com>
21
Tested-by: Francisco Iglesias <frasse.iglesias@gmail.com>
22
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
23
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
48
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
24
---
49
---
25
hw/ssi/xilinx_spips.c | 4 ++++
50
tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++
26
1 file changed, 4 insertions(+)
51
1 file changed, 43 insertions(+)
27
52
28
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
53
diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py
29
index XXXXXXX..XXXXXXX 100644
54
index XXXXXXX..XXXXXXX 100644
30
--- a/hw/ssi/xilinx_spips.c
55
--- a/tests/acceptance/boot_linux_console.py
31
+++ b/hw/ssi/xilinx_spips.c
56
+++ b/tests/acceptance/boot_linux_console.py
32
@@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps lqspi_ops = {
57
@@ -XXX,XX +XXX,XX @@
33
.read_with_attrs = lqspi_read,
58
from avocado import skip
34
.write_with_attrs = lqspi_write,
59
from avocado import skipUnless
35
.endianness = DEVICE_NATIVE_ENDIAN,
60
from avocado_qemu import Test
36
+ .impl = {
61
+from avocado_qemu import exec_command
37
+ .min_access_size = 4,
62
from avocado_qemu import exec_command_and_wait_for_pattern
38
+ .max_access_size = 4,
63
from avocado_qemu import interrupt_interactive_console_until_pattern
39
+ },
64
from avocado_qemu import wait_for_console_pattern
40
.valid = {
65
@@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self):
41
.min_access_size = 1,
66
"""
42
.max_access_size = 4
67
self.do_test_arm_raspi2(0)
68
69
+ def test_arm_raspi2_initrd(self):
70
+ """
71
+ :avocado: tags=arch:arm
72
+ :avocado: tags=machine:raspi2
73
+ """
74
+ deb_url = ('http://archive.raspberrypi.org/debian/'
75
+ 'pool/main/r/raspberrypi-firmware/'
76
+ 'raspberrypi-kernel_1.20190215-1_armhf.deb')
77
+ deb_hash = 'cd284220b32128c5084037553db3c482426f3972'
78
+ deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash)
79
+ kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img')
80
+ dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb')
81
+
82
+ initrd_url = ('https://github.com/groeck/linux-build-test/raw/'
83
+ '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/'
84
+ 'arm/rootfs-armv7a.cpio.gz')
85
+ initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c'
86
+ initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash)
87
+ initrd_path = os.path.join(self.workdir, 'rootfs.cpio')
88
+ archive.gzip_uncompress(initrd_path_gz, initrd_path)
89
+
90
+ self.vm.set_console()
91
+ kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE +
92
+ 'earlycon=pl011,0x3f201000 console=ttyAMA0 '
93
+ 'panic=-1 noreboot ' +
94
+ 'dwc_otg.fiq_fsm_enable=0')
95
+ self.vm.add_args('-kernel', kernel_path,
96
+ '-dtb', dtb_path,
97
+ '-initrd', initrd_path,
98
+ '-append', kernel_command_line,
99
+ '-no-reboot')
100
+ self.vm.launch()
101
+ self.wait_for_console_pattern('Boot successful.')
102
+
103
+ exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo',
104
+ 'BCM2835')
105
+ exec_command_and_wait_for_pattern(self, 'cat /proc/iomem',
106
+ '/soc/cprman@7e101000')
107
+ exec_command(self, 'halt')
108
+ # Wait for VM to shut down gracefully
109
+ self.vm.wait()
110
+
111
def test_arm_exynos4210_initrd(self):
112
"""
113
:avocado: tags=arch:arm
43
--
114
--
44
2.20.1
115
2.20.1
45
116
46
117
diff view generated by jsdifflib
1
From: Alex Bennée <alex.bennee@linaro.org>
1
From: Joe Komlodi <joe.komlodi@xilinx.com>
2
2
3
When we converted to using feature bits in 602f6e42cfbf we missed out
3
If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute
4
the fact (dp && arm_dc_feature(s, ARM_FEATURE_V8)) was supported for
4
FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will
5
-cpu max configurations. This caused a regression in the GCC test
5
assert due to fpst->default_nan_mode being set.
6
suite. Fix this by setting the appropriate bits in mvfr1.FPHP to
7
report ARMv8-A with FP support (but not ARMv8.2-FP16).
8
6
9
Fixes: https://bugs.launchpad.net/qemu/+bug/1836078
7
To avoid this, we check to see what NaN mode we're running in before we call
10
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
8
floatxx_silence_nan().
9
10
Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 20190711103737.10017-1-alex.bennee@linaro.org
12
Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com
13
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
---
15
---
15
target/arm/cpu.c | 4 ++++
16
target/arm/helper-a64.c | 12 +++++++++---
16
1 file changed, 4 insertions(+)
17
target/arm/vfp_helper.c | 24 ++++++++++++++++++------
18
2 files changed, 27 insertions(+), 9 deletions(-)
17
19
18
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
20
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
19
index XXXXXXX..XXXXXXX 100644
21
index XXXXXXX..XXXXXXX 100644
20
--- a/target/arm/cpu.c
22
--- a/target/arm/helper-a64.c
21
+++ b/target/arm/cpu.c
23
+++ b/target/arm/helper-a64.c
22
@@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj)
24
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp)
23
t = FIELD_DP32(t, ID_ISAR6, SPECRES, 1);
25
float16 nan = a;
24
cpu->isar.id_isar6 = t;
26
if (float16_is_signaling_nan(a, fpst)) {
25
27
float_raise(float_flag_invalid, fpst);
26
+ t = cpu->isar.mvfr1;
28
- nan = float16_silence_nan(a, fpst);
27
+ t = FIELD_DP32(t, MVFR1, FPHP, 2); /* v8.0 FP support */
29
+ if (!fpst->default_nan_mode) {
28
+ cpu->isar.mvfr1 = t;
30
+ nan = float16_silence_nan(a, fpst);
29
+
31
+ }
30
t = cpu->isar.mvfr2;
32
}
31
t = FIELD_DP32(t, MVFR2, SIMDMISC, 3); /* SIMD MaxNum */
33
if (fpst->default_nan_mode) {
32
t = FIELD_DP32(t, MVFR2, FPMISC, 4); /* FP MaxNum */
34
nan = float16_default_nan(fpst);
35
@@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp)
36
float32 nan = a;
37
if (float32_is_signaling_nan(a, fpst)) {
38
float_raise(float_flag_invalid, fpst);
39
- nan = float32_silence_nan(a, fpst);
40
+ if (!fpst->default_nan_mode) {
41
+ nan = float32_silence_nan(a, fpst);
42
+ }
43
}
44
if (fpst->default_nan_mode) {
45
nan = float32_default_nan(fpst);
46
@@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp)
47
float64 nan = a;
48
if (float64_is_signaling_nan(a, fpst)) {
49
float_raise(float_flag_invalid, fpst);
50
- nan = float64_silence_nan(a, fpst);
51
+ if (!fpst->default_nan_mode) {
52
+ nan = float64_silence_nan(a, fpst);
53
+ }
54
}
55
if (fpst->default_nan_mode) {
56
nan = float64_default_nan(fpst);
57
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
58
index XXXXXXX..XXXXXXX 100644
59
--- a/target/arm/vfp_helper.c
60
+++ b/target/arm/vfp_helper.c
61
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp)
62
float16 nan = f16;
63
if (float16_is_signaling_nan(f16, fpst)) {
64
float_raise(float_flag_invalid, fpst);
65
- nan = float16_silence_nan(f16, fpst);
66
+ if (!fpst->default_nan_mode) {
67
+ nan = float16_silence_nan(f16, fpst);
68
+ }
69
}
70
if (fpst->default_nan_mode) {
71
nan = float16_default_nan(fpst);
72
@@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp)
73
float32 nan = f32;
74
if (float32_is_signaling_nan(f32, fpst)) {
75
float_raise(float_flag_invalid, fpst);
76
- nan = float32_silence_nan(f32, fpst);
77
+ if (!fpst->default_nan_mode) {
78
+ nan = float32_silence_nan(f32, fpst);
79
+ }
80
}
81
if (fpst->default_nan_mode) {
82
nan = float32_default_nan(fpst);
83
@@ -XXX,XX +XXX,XX @@ float64 HELPER(recpe_f64)(float64 input, void *fpstp)
84
float64 nan = f64;
85
if (float64_is_signaling_nan(f64, fpst)) {
86
float_raise(float_flag_invalid, fpst);
87
- nan = float64_silence_nan(f64, fpst);
88
+ if (!fpst->default_nan_mode) {
89
+ nan = float64_silence_nan(f64, fpst);
90
+ }
91
}
92
if (fpst->default_nan_mode) {
93
nan = float64_default_nan(fpst);
94
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp)
95
float16 nan = f16;
96
if (float16_is_signaling_nan(f16, s)) {
97
float_raise(float_flag_invalid, s);
98
- nan = float16_silence_nan(f16, s);
99
+ if (!s->default_nan_mode) {
100
+ nan = float16_silence_nan(f16, fpstp);
101
+ }
102
}
103
if (s->default_nan_mode) {
104
nan = float16_default_nan(s);
105
@@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp)
106
float32 nan = f32;
107
if (float32_is_signaling_nan(f32, s)) {
108
float_raise(float_flag_invalid, s);
109
- nan = float32_silence_nan(f32, s);
110
+ if (!s->default_nan_mode) {
111
+ nan = float32_silence_nan(f32, fpstp);
112
+ }
113
}
114
if (s->default_nan_mode) {
115
nan = float32_default_nan(s);
116
@@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp)
117
float64 nan = f64;
118
if (float64_is_signaling_nan(f64, s)) {
119
float_raise(float_flag_invalid, s);
120
- nan = float64_silence_nan(f64, s);
121
+ if (!s->default_nan_mode) {
122
+ nan = float64_silence_nan(f64, fpstp);
123
+ }
124
}
125
if (s->default_nan_mode) {
126
nan = float64_default_nan(s);
33
--
127
--
34
2.20.1
128
2.20.1
35
129
36
130
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
1
From: Maxim Uvarov <maxim.uvarov@linaro.org>
2
2
3
In the previous commit we fixed a crash when the guest read a
3
qemu has 2 type of functions: shutdown and reboot. Shutdown
4
register that pop from an empty FIFO.
4
function has to be used for machine shutdown. Otherwise we cause
5
By auditing the repository, we found another similar use with
5
a reset with a bogus "cause" value, when we intended a shutdown.
6
an easy way to reproduce:
7
6
8
$ qemu-system-aarch64 -M xlnx-zcu102 -monitor stdio -S
7
Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org>
9
QEMU 4.0.50 monitor - type 'help' for more information
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
(qemu) xp/b 0xfd4a0134
9
Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org
11
Aborted (core dumped)
10
[PMM: tweaked commit message]
12
13
(gdb) bt
14
#0 0x00007f6936dea57f in raise () at /lib64/libc.so.6
15
#1 0x00007f6936dd4895 in abort () at /lib64/libc.so.6
16
#2 0x0000561ad32975ec in xlnx_dp_aux_pop_rx_fifo (s=0x7f692babee70) at hw/display/xlnx_dp.c:431
17
#3 0x0000561ad3297dc0 in xlnx_dp_read (opaque=0x7f692babee70, offset=77, size=4) at hw/display/xlnx_dp.c:667
18
#4 0x0000561ad321b896 in memory_region_read_accessor (mr=0x7f692babf620, addr=308, value=0x7ffe05c1db88, size=4, shift=0, mask=4294967295, attrs=...) at memory.c:439
19
#5 0x0000561ad321bd70 in access_with_adjusted_size (addr=308, value=0x7ffe05c1db88, size=1, access_size_min=4, access_size_max=4, access_fn=0x561ad321b858 <memory_region_read_accessor>, mr=0x7f692babf620, attrs=...) at memory.c:569
20
#6 0x0000561ad321e9d5 in memory_region_dispatch_read1 (mr=0x7f692babf620, addr=308, pval=0x7ffe05c1db88, size=1, attrs=...) at memory.c:1420
21
#7 0x0000561ad321ea9d in memory_region_dispatch_read (mr=0x7f692babf620, addr=308, pval=0x7ffe05c1db88, size=1, attrs=...) at memory.c:1447
22
#8 0x0000561ad31bd742 in flatview_read_continue (fv=0x561ad69c04f0, addr=4249485620, attrs=..., buf=0x7ffe05c1dcf0 "\020\335\301\005\376\177", len=1, addr1=308, l=1, mr=0x7f692babf620) at exec.c:3385
23
#9 0x0000561ad31bd895 in flatview_read (fv=0x561ad69c04f0, addr=4249485620, attrs=..., buf=0x7ffe05c1dcf0 "\020\335\301\005\376\177", len=1) at exec.c:3423
24
#10 0x0000561ad31bd90b in address_space_read_full (as=0x561ad5bb3020, addr=4249485620, attrs=..., buf=0x7ffe05c1dcf0 "\020\335\301\005\376\177", len=1) at exec.c:3436
25
#11 0x0000561ad33b1c42 in address_space_read (len=1, buf=0x7ffe05c1dcf0 "\020\335\301\005\376\177", attrs=..., addr=4249485620, as=0x561ad5bb3020) at include/exec/memory.h:2131
26
#12 0x0000561ad33b1c42 in memory_dump (mon=0x561ad59c4530, count=1, format=120, wsize=1, addr=4249485620, is_physical=1) at monitor/misc.c:723
27
#13 0x0000561ad33b1fc1 in hmp_physical_memory_dump (mon=0x561ad59c4530, qdict=0x561ad6c6fd00) at monitor/misc.c:795
28
#14 0x0000561ad37b4a9f in handle_hmp_command (mon=0x561ad59c4530, cmdline=0x561ad59d0f22 "/b 0x00000000fd4a0134") at monitor/hmp.c:1082
29
30
Fix by checking the FIFO is not empty before popping from it.
31
32
The datasheet is not clear about the reset value of this register,
33
we choose to return '0'.
34
35
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
36
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
37
Message-id: 20190709113715.7761-4-philmd@redhat.com
38
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
39
---
12
---
40
hw/display/xlnx_dp.c | 15 +++++++++++----
13
hw/gpio/gpio_pwr.c | 2 +-
41
1 file changed, 11 insertions(+), 4 deletions(-)
14
1 file changed, 1 insertion(+), 1 deletion(-)
42
15
43
diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c
16
diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c
44
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
45
--- a/hw/display/xlnx_dp.c
18
--- a/hw/gpio/gpio_pwr.c
46
+++ b/hw/display/xlnx_dp.c
19
+++ b/hw/gpio/gpio_pwr.c
47
@@ -XXX,XX +XXX,XX @@ static uint8_t xlnx_dp_aux_pop_rx_fifo(XlnxDPState *s)
20
@@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level)
48
uint8_t ret;
21
static void gpio_pwr_shutdown(void *opaque, int n, int level)
49
22
{
50
if (fifo8_is_empty(&s->rx_fifo)) {
23
if (level) {
51
- DPRINTF("rx_fifo underflow..\n");
24
- qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
52
- abort();
25
+ qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN);
53
+ qemu_log_mask(LOG_GUEST_ERROR,
54
+ "%s: Reading empty RX_FIFO\n",
55
+ __func__);
56
+ /*
57
+ * The datasheet is not clear about the reset value, it seems
58
+ * to be unspecified. We choose to return '0'.
59
+ */
60
+ ret = 0;
61
+ } else {
62
+ ret = fifo8_pop(&s->rx_fifo);
63
+ DPRINTF("pop 0x%" PRIX8 " from rx_fifo.\n", ret);
64
}
26
}
65
- ret = fifo8_pop(&s->rx_fifo);
66
- DPRINTF("pop 0x%" PRIX8 " from rx_fifo.\n", ret);
67
return ret;
68
}
27
}
69
28
70
--
29
--
71
2.20.1
30
2.20.1
72
31
73
32
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
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.
2
5
3
In the next commit we will implement the write_with_attrs()
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
handler. To avoid using different APIs, convert the read()
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
handler first.
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(-)
6
12
7
Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com>
13
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
8
Tested-by: Francisco Iglesias <frasse.iglesias@gmail.com>
9
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
12
hw/ssi/xilinx_spips.c | 23 +++++++++++------------
13
1 file changed, 11 insertions(+), 12 deletions(-)
14
15
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
16
index XXXXXXX..XXXXXXX 100644
14
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/ssi/xilinx_spips.c
15
--- a/target/arm/translate-mve.c
18
+++ b/hw/ssi/xilinx_spips.c
16
+++ b/target/arm/translate-mve.c
19
@@ -XXX,XX +XXX,XX @@ static void lqspi_load_cache(void *opaque, hwaddr addr)
17
@@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s)
20
}
18
}
21
}
19
}
22
20
23
-static uint64_t
21
-static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn)
24
-lqspi_read(void *opaque, hwaddr addr, unsigned int size)
22
+static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn,
25
+static MemTxResult lqspi_read(void *opaque, hwaddr addr, uint64_t *value,
23
+ unsigned msize)
26
+ unsigned size, MemTxAttrs attrs)
27
{
24
{
28
- XilinxQSPIPS *q = opaque;
25
TCGv_i32 addr;
29
- uint32_t ret;
26
uint32_t offset;
30
+ XilinxQSPIPS *q = XILINX_QSPIPS(opaque);
27
@@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn)
31
28
return true;
32
if (addr >= q->lqspi_cached_addr &&
33
addr <= q->lqspi_cached_addr + LQSPI_CACHE_SIZE - 4) {
34
uint8_t *retp = &q->lqspi_buf[addr - q->lqspi_cached_addr];
35
- ret = cpu_to_le32(*(uint32_t *)retp);
36
- DB_PRINT_L(1, "addr: %08x, data: %08x\n", (unsigned)addr,
37
- (unsigned)ret);
38
- return ret;
39
- } else {
40
- lqspi_load_cache(opaque, addr);
41
- return lqspi_read(opaque, addr, size);
42
+ *value = cpu_to_le32(*(uint32_t *)retp);
43
+ DB_PRINT_L(1, "addr: %08" HWADDR_PRIx ", data: %08" PRIx64 "\n",
44
+ addr, *value);
45
+ return MEMTX_OK;
46
}
29
}
47
+
30
48
+ lqspi_load_cache(opaque, addr);
31
- offset = a->imm << a->size;
49
+ return lqspi_read(opaque, addr, value, size, attrs);
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);
50
}
42
}
51
43
52
static const MemoryRegionOps lqspi_ops = {
44
-#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \
53
- .read = lqspi_read,
45
+#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \
54
+ .read_with_attrs = lqspi_read,
46
static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \
55
.endianness = DEVICE_NATIVE_ENDIAN,
47
{ \
56
.valid = {
48
static MVEGenLdStFn * const ldstfns[2][2] = { \
57
.min_access_size = 1,
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
{
58
--
65
--
59
2.20.1
66
2.20.1
60
67
61
68
diff view generated by jsdifflib
New patch
1
The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH
2
insns had some bugs:
3
* the 32x32 multiply of elements was being done as 32x32->32,
4
not 32x32->64
5
* we were incorrectly maintaining the accumulator in its full
6
72-bit form across all 4 beats of the insn; in the pseudocode
7
it is squashed back into the 64 bits of the RdaHi:RdaLo
8
registers after each beat
1
9
10
In particular, fixing the second of these allows us to recast
11
the implementation to avoid 128-bit arithmetic entirely.
12
13
Since the element size here is always 4, we can also drop the
14
parameterization of ESIZE to make the code a little more readable.
15
16
Suggested-by: Richard Henderson <richard.henderson@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
18
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
19
Message-id: 20210628135835.6690-3-peter.maydell@linaro.org
20
---
21
target/arm/mve_helper.c | 38 +++++++++++++++++++++-----------------
22
1 file changed, 21 insertions(+), 17 deletions(-)
23
24
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
25
index XXXXXXX..XXXXXXX 100644
26
--- a/target/arm/mve_helper.c
27
+++ b/target/arm/mve_helper.c
28
@@ -XXX,XX +XXX,XX @@
29
*/
30
31
#include "qemu/osdep.h"
32
-#include "qemu/int128.h"
33
#include "cpu.h"
34
#include "internals.h"
35
#include "vec_internal.h"
36
@@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=)
37
DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=)
38
39
/*
40
- * Rounding multiply add long dual accumulate high: we must keep
41
- * a 72-bit internal accumulator value and return the top 64 bits.
42
+ * Rounding multiply add long dual accumulate high. In the pseudocode
43
+ * this is implemented with a 72-bit internal accumulator value of which
44
+ * the top 64 bits are returned. We optimize this to avoid having to
45
+ * use 128-bit arithmetic -- we can do this because the 74-bit accumulator
46
+ * is squashed back into 64-bits after each beat.
47
*/
48
-#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \
49
+#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \
50
uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \
51
void *vm, uint64_t a) \
52
{ \
53
uint16_t mask = mve_element_mask(env); \
54
unsigned e; \
55
TYPE *n = vn, *m = vm; \
56
- Int128 acc = int128_lshift(TO128(a), 8); \
57
- for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \
58
+ for (e = 0; e < 16 / 4; e++, mask >>= 4) { \
59
if (mask & 1) { \
60
+ LTYPE mul; \
61
if (e & 1) { \
62
- acc = ODDACC(acc, TO128(n[H##ESIZE(e - 1 * XCHG)] * \
63
- m[H##ESIZE(e)])); \
64
+ mul = (LTYPE)n[H4(e - 1 * XCHG)] * m[H4(e)]; \
65
+ if (SUB) { \
66
+ mul = -mul; \
67
+ } \
68
} else { \
69
- acc = EVENACC(acc, TO128(n[H##ESIZE(e + 1 * XCHG)] * \
70
- m[H##ESIZE(e)])); \
71
+ mul = (LTYPE)n[H4(e + 1 * XCHG)] * m[H4(e)]; \
72
} \
73
- acc = int128_add(acc, int128_make64(1 << 7)); \
74
+ mul = (mul >> 8) + ((mul >> 7) & 1); \
75
+ a += mul; \
76
} \
77
} \
78
mve_advance_vpt(env); \
79
- return int128_getlo(int128_rshift(acc, 8)); \
80
+ return a; \
81
}
82
83
-DO_LDAVH(vrmlaldavhsw, 4, int32_t, false, int128_add, int128_add, int128_makes64)
84
-DO_LDAVH(vrmlaldavhxsw, 4, int32_t, true, int128_add, int128_add, int128_makes64)
85
+DO_LDAVH(vrmlaldavhsw, int32_t, int64_t, false, false)
86
+DO_LDAVH(vrmlaldavhxsw, int32_t, int64_t, true, false)
87
88
-DO_LDAVH(vrmlaldavhuw, 4, uint32_t, false, int128_add, int128_add, int128_make64)
89
+DO_LDAVH(vrmlaldavhuw, uint32_t, uint64_t, false, false)
90
91
-DO_LDAVH(vrmlsldavhsw, 4, int32_t, false, int128_add, int128_sub, int128_makes64)
92
-DO_LDAVH(vrmlsldavhxsw, 4, int32_t, true, int128_add, int128_sub, int128_makes64)
93
+DO_LDAVH(vrmlsldavhsw, int32_t, int64_t, false, true)
94
+DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true)
95
96
/* Vector add across vector */
97
#define DO_VADDV(OP, ESIZE, TYPE) \
98
--
99
2.20.1
100
101
diff view generated by jsdifflib
New patch
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
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
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
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
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
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
1
Implement the MVE VHLL (vector shift left long) insn. This has two
2
encodings: the T1 encoding is the usual shift-by-immediate format,
3
and the T2 encoding is a special case where the shift count is always
4
equal to the element size.
1
5
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20210628135835.6690-10-peter.maydell@linaro.org
9
---
10
target/arm/helper-mve.h | 9 +++++++
11
target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++---
12
target/arm/mve_helper.c | 32 +++++++++++++++++++++++
13
target/arm/translate-mve.c | 15 +++++++++++
14
4 files changed, 105 insertions(+), 4 deletions(-)
15
16
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
17
index XXXXXXX..XXXXXXX 100644
18
--- a/target/arm/helper-mve.h
19
+++ b/target/arm/helper-mve.h
20
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
+
25
+DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
+DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
+DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
+DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
33
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
34
index XXXXXXX..XXXXXXX 100644
35
--- a/target/arm/mve.decode
36
+++ b/target/arm/mve.decode
37
@@ -XXX,XX +XXX,XX @@
38
@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
39
@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2
40
41
+@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0
42
+@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1
43
+# VSHLL encoding T2 where shift == esize
44
+@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \
45
+ qd=%qd qm=%qm size=0 shift=8
46
+@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \
47
+ qd=%qd qm=%qm size=1 shift=16
48
+
49
# Right shifts are encoded as N - shift, where N is the element size in bits.
50
%rshift_i5 16:5 !function=rsub_32
51
%rshift_i4 16:4 !function=rsub_16
52
@@ -XXX,XX +XXX,XX @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
53
VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op
54
VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op
55
56
-VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
57
-VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
58
+# The VSHLL T2 encoding is not a @2op pattern, but is here because it
59
+# overlaps what would be size=0b11 VMULH/VRMULH
60
+{
61
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
62
+ VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
63
64
-VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
65
-VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
66
+ VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
67
+}
68
+
69
+{
70
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b
71
+ VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h
72
+
73
+ VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op
74
+}
75
+
76
+{
77
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
78
+ VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
79
+
80
+ VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
81
+}
82
+
83
+{
84
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b
85
+ VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h
86
+
87
+ VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op
88
+}
89
90
VMAX_S 111 0 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
91
VMAX_U 111 1 1111 0 . .. ... 0 ... 0 0110 . 1 . 0 ... 0 @2op
92
@@ -XXX,XX +XXX,XX @@ VRSHRI_S 111 0 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
93
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_b
94
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h
95
VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w
96
+
97
+# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file
98
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
99
+VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
100
+
101
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b
102
+VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h
103
+
104
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
105
+VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
106
+
107
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
108
+VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
109
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
110
index XXXXXXX..XXXXXXX 100644
111
--- a/target/arm/mve_helper.c
112
+++ b/target/arm/mve_helper.c
113
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP)
114
DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
115
DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
116
DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
117
+
118
+/*
119
+ * Long shifts taking half-sized inputs from top or bottom of the input
120
+ * vector and producing a double-width result. ESIZE, TYPE are for
121
+ * the input, and LESIZE, LTYPE for the output.
122
+ * Unlike the normal shift helpers, we do not handle negative shift counts,
123
+ * because the long shift is strictly left-only.
124
+ */
125
+#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \
126
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
127
+ void *vm, uint32_t shift) \
128
+ { \
129
+ LTYPE *d = vd; \
130
+ TYPE *m = vm; \
131
+ uint16_t mask = mve_element_mask(env); \
132
+ unsigned le; \
133
+ assert(shift <= 16); \
134
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
135
+ LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \
136
+ mergemask(&d[H##LESIZE(le)], r, mask); \
137
+ } \
138
+ mve_advance_vpt(env); \
139
+ }
140
+
141
+#define DO_VSHLL_ALL(OP, TOP) \
142
+ DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \
143
+ DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \
144
+ DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \
145
+ DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \
146
+
147
+DO_VSHLL_ALL(vshllb, false)
148
+DO_VSHLL_ALL(vshllt, true)
149
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
150
index XXXXXXX..XXXXXXX 100644
151
--- a/target/arm/translate-mve.c
152
+++ b/target/arm/translate-mve.c
153
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_S, vshli_s, true)
154
DO_2SHIFT(VSHRI_U, vshli_u, true)
155
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
156
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
157
+
158
+#define DO_VSHLL(INSN, FN) \
159
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
160
+ { \
161
+ static MVEGenTwoOpShiftFn * const fns[] = { \
162
+ gen_helper_mve_##FN##b, \
163
+ gen_helper_mve_##FN##h, \
164
+ }; \
165
+ return do_2shift(s, a, fns[a->size], false); \
166
+ }
167
+
168
+DO_VSHLL(VSHLL_BS, vshllbs)
169
+DO_VSHLL(VSHLL_BU, vshllbu)
170
+DO_VSHLL(VSHLL_TS, vshllts)
171
+DO_VSHLL(VSHLL_TU, vshlltu)
172
--
173
2.20.1
174
175
diff view generated by jsdifflib
New patch
1
Implement the MVE VSRI and VSLI insns, which perform a
2
shift-and-insert operation.
1
3
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20210628135835.6690-11-peter.maydell@linaro.org
7
---
8
target/arm/helper-mve.h | 8 ++++++++
9
target/arm/mve.decode | 9 ++++++++
10
target/arm/mve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++
11
target/arm/translate-mve.c | 3 +++
12
4 files changed, 62 insertions(+)
13
14
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
15
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/helper-mve.h
17
+++ b/target/arm/helper-mve.h
18
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
19
DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
20
DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
+
23
+DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
24
+DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
25
+DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+
27
+DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
29
+DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
diff --git a/target/arm/mve.decode b/target/arm/mve.decode
31
index XXXXXXX..XXXXXXX 100644
32
--- a/target/arm/mve.decode
33
+++ b/target/arm/mve.decode
34
@@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
35
36
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b
37
VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h
38
+
39
+# Shift-and-insert
40
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b
41
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h
42
+VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
43
+
44
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
45
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
46
+VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
47
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
48
index XXXXXXX..XXXXXXX 100644
49
--- a/target/arm/mve_helper.c
50
+++ b/target/arm/mve_helper.c
51
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP)
52
DO_2SHIFT_U(vrshli_u, DO_VRSHLU)
53
DO_2SHIFT_S(vrshli_s, DO_VRSHLS)
54
55
+/* Shift-and-insert; we always work with 64 bits at a time */
56
+#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \
57
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
58
+ void *vm, uint32_t shift) \
59
+ { \
60
+ uint64_t *d = vd, *m = vm; \
61
+ uint16_t mask; \
62
+ uint64_t shiftmask; \
63
+ unsigned e; \
64
+ if (shift == 0 || shift == ESIZE * 8) { \
65
+ /* \
66
+ * Only VSLI can shift by 0; only VSRI can shift by <dt>. \
67
+ * The generic logic would give the right answer for 0 but \
68
+ * fails for <dt>. \
69
+ */ \
70
+ goto done; \
71
+ } \
72
+ assert(shift < ESIZE * 8); \
73
+ mask = mve_element_mask(env); \
74
+ /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */ \
75
+ shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift)); \
76
+ for (e = 0; e < 16 / 8; e++, mask >>= 8) { \
77
+ uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) | \
78
+ (d[H8(e)] & ~shiftmask); \
79
+ mergemask(&d[H8(e)], r, mask); \
80
+ } \
81
+done: \
82
+ mve_advance_vpt(env); \
83
+ }
84
+
85
+#define DO_SHL(N, SHIFT) ((N) << (SHIFT))
86
+#define DO_SHR(N, SHIFT) ((N) >> (SHIFT))
87
+#define SHL_MASK(EBITS, SHIFT) MAKE_64BIT_MASK((SHIFT), (EBITS) - (SHIFT))
88
+#define SHR_MASK(EBITS, SHIFT) MAKE_64BIT_MASK(0, (EBITS) - (SHIFT))
89
+
90
+DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK)
91
+DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK)
92
+DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK)
93
+DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK)
94
+DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK)
95
+DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
96
+
97
/*
98
* Long shifts taking half-sized inputs from top or bottom of the input
99
* vector and producing a double-width result. ESIZE, TYPE are for
100
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
101
index XXXXXXX..XXXXXXX 100644
102
--- a/target/arm/translate-mve.c
103
+++ b/target/arm/translate-mve.c
104
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_U, vshli_u, true)
105
DO_2SHIFT(VRSHRI_S, vrshli_s, true)
106
DO_2SHIFT(VRSHRI_U, vrshli_u, true)
107
108
+DO_2SHIFT(VSRI, vsri, false)
109
+DO_2SHIFT(VSLI, vsli, false)
110
+
111
#define DO_VSHLL(INSN, FN) \
112
static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
113
{ \
114
--
115
2.20.1
116
117
diff view generated by jsdifflib
New patch
1
Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN.
1
2
3
do_urshr() is borrowed from sve_helper.c.
4
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20210628135835.6690-12-peter.maydell@linaro.org
8
---
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(+)
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_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
20
DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
21
DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
22
DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
23
+
24
+DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
25
+DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
26
+DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
27
+DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
28
+
29
+DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
30
+DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
31
+DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
32
+DEF_HELPER_FLAGS_4(mve_vrshrnth, 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 @@ VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w
38
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b
39
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h
40
VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w
41
+
42
+# Narrowing shifts (which only support b and h sizes)
43
+VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
44
+VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
45
+VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
46
+VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
47
+
48
+VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b
49
+VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h
50
+VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b
51
+VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h
52
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
53
index XXXXXXX..XXXXXXX 100644
54
--- a/target/arm/mve_helper.c
55
+++ b/target/arm/mve_helper.c
56
@@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK)
57
58
DO_VSHLL_ALL(vshllb, false)
59
DO_VSHLL_ALL(vshllt, true)
60
+
61
+/*
62
+ * Narrowing right shifts, taking a double sized input, shifting it
63
+ * and putting the result in either the top or bottom half of the output.
64
+ * ESIZE, TYPE are the output, and LESIZE, LTYPE the input.
65
+ */
66
+#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \
67
+ void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \
68
+ void *vm, uint32_t shift) \
69
+ { \
70
+ LTYPE *m = vm; \
71
+ TYPE *d = vd; \
72
+ uint16_t mask = mve_element_mask(env); \
73
+ unsigned le; \
74
+ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \
75
+ TYPE r = FN(m[H##LESIZE(le)], shift); \
76
+ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \
77
+ } \
78
+ mve_advance_vpt(env); \
79
+ }
80
+
81
+#define DO_VSHRN_ALL(OP, FN) \
82
+ DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \
83
+ DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \
84
+ DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \
85
+ DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN)
86
+
87
+static inline uint64_t do_urshr(uint64_t x, unsigned sh)
88
+{
89
+ if (likely(sh < 64)) {
90
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
91
+ } else if (sh == 64) {
92
+ return x >> 63;
93
+ } else {
94
+ return 0;
95
+ }
96
+}
97
+
98
+DO_VSHRN_ALL(vshrn, DO_SHR)
99
+DO_VSHRN_ALL(vrshrn, do_urshr)
100
diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c
101
index XXXXXXX..XXXXXXX 100644
102
--- a/target/arm/translate-mve.c
103
+++ b/target/arm/translate-mve.c
104
@@ -XXX,XX +XXX,XX @@ DO_VSHLL(VSHLL_BS, vshllbs)
105
DO_VSHLL(VSHLL_BU, vshllbu)
106
DO_VSHLL(VSHLL_TS, vshllts)
107
DO_VSHLL(VSHLL_TU, vshlltu)
108
+
109
+#define DO_2SHIFT_N(INSN, FN) \
110
+ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \
111
+ { \
112
+ static MVEGenTwoOpShiftFn * const fns[] = { \
113
+ gen_helper_mve_##FN##b, \
114
+ gen_helper_mve_##FN##h, \
115
+ }; \
116
+ return do_2shift(s, a, fns[a->size], false); \
117
+ }
118
+
119
+DO_2SHIFT_N(VSHRNB, vshrnb)
120
+DO_2SHIFT_N(VSHRNT, vshrnt)
121
+DO_2SHIFT_N(VRSHRNB, vrshrnb)
122
+DO_2SHIFT_N(VRSHRNT, vrshrnt)
123
--
124
2.20.1
125
126
diff view generated by jsdifflib
1
The ARMv5 architecture didn't specify detailed per-feature ID
1
Implement the MVE saturating shift-right-and-narrow insns
2
registers. Now that we're using the MVFR0 register fields to
2
VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN.
3
gate the existence of VFP instructions, we need to set up
3
4
the correct values in the cpu->isar structure so that we still
4
do_srshr() is borrowed from sve_helper.c.
5
provide an FPU to the guest.
5
6
7
This fixes a regression in the arm926 and arm1026 CPUs, which
8
are the only ones that both have VFP and are ARMv5 or earlier.
9
This regression was introduced by the VFP refactoring, and more
10
specifically by commits 1120827fa182f0e76 and 266bd25c485597c,
11
which accidentally disabled VFP short-vector support and
12
double-precision support on these CPUs.
13
14
Fixes: 1120827fa182f0e
15
Fixes: 266bd25c485597c
16
Fixes: https://bugs.launchpad.net/qemu/+bug/1836192
17
Reported-by: Christophe Lyon <christophe.lyon@linaro.org>
18
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
19
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
20
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
8
Message-id: 20210628135835.6690-13-peter.maydell@linaro.org
21
Tested-by: Christophe Lyon <christophe.lyon@linaro.org>
22
Message-id: 20190711131241.22231-1-peter.maydell@linaro.org
23
---
9
---
24
target/arm/cpu.c | 12 ++++++++++++
10
target/arm/helper-mve.h | 30 +++++++++++
25
1 file changed, 12 insertions(+)
11
target/arm/mve.decode | 28 ++++++++++
26
12
target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++
27
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
13
target/arm/translate-mve.c | 12 +++++
28
index XXXXXXX..XXXXXXX 100644
14
4 files changed, 174 insertions(+)
29
--- a/target/arm/cpu.c
15
30
+++ b/target/arm/cpu.c
16
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
31
@@ -XXX,XX +XXX,XX @@ static void arm926_initfn(Object *obj)
17
index XXXXXXX..XXXXXXX 100644
32
* set the field to indicate Jazelle support within QEMU.
18
--- a/target/arm/helper-mve.h
33
*/
19
+++ b/target/arm/helper-mve.h
34
cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
20
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
35
+ /*
21
DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
36
+ * Similarly, we need to set MVFR0 fields to enable double precision
22
DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
37
+ * and short vector support even though ARMv5 doesn't have this register.
23
DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
38
+ */
24
+
39
+ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
25
+DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32)
40
+ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
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
}
41
}
96
}
42
97
43
static void arm946_initfn(Object *obj)
98
+static inline int64_t do_srshr(int64_t x, unsigned sh)
44
@@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj)
99
+{
45
* set the field to indicate Jazelle support within QEMU.
100
+ if (likely(sh < 64)) {
46
*/
101
+ return (x >> sh) + ((x >> (sh - 1)) & 1);
47
cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1);
102
+ } else {
48
+ /*
103
+ /* Rounding the sign bit always produces 0. */
49
+ * Similarly, we need to set MVFR0 fields to enable double precision
104
+ return 0;
50
+ * and short vector support even though ARMv5 doesn't have this register.
105
+ }
51
+ */
106
+}
52
+ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPSHVEC, 1);
107
+
53
+ cpu->isar.mvfr0 = FIELD_DP32(cpu->isar.mvfr0, MVFR0, FPDP, 1);
108
DO_VSHRN_ALL(vshrn, DO_SHR)
54
109
DO_VSHRN_ALL(vrshrn, do_urshr)
55
{
110
+
56
/* The 1026 had an IFAR at c6,c0,0,1 rather than the ARMv6 c6,c0,0,2 */
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)
57
--
224
--
58
2.20.1
225
2.20.1
59
226
60
227
diff view generated by jsdifflib
New patch
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
1
From: Philippe Mathieu-Daudé <philmd@redhat.com>
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.
2
4
3
Lei Sun found while auditing the code that a CPU write would
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
trigger a NULL pointer dereference.
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(-)
5
14
6
>From UG1085 datasheet [*] AXI writes in this region are ignored
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
7
and generates an AXI Slave Error (SLVERR).
8
9
Fix by implementing the write_with_attrs() handler.
10
Return MEMTX_ERROR when the region is accessed (this error maps
11
to an AXI slave error).
12
13
[*] https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf
14
15
Reported-by: Lei Sun <slei.casper@gmail.com>
16
Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com>
17
Tested-by: Francisco Iglesias <frasse.iglesias@gmail.com>
18
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
19
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
20
---
21
hw/ssi/xilinx_spips.c | 16 ++++++++++++++++
22
1 file changed, 16 insertions(+)
23
24
diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c
25
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
26
--- a/hw/ssi/xilinx_spips.c
17
--- a/target/arm/helper-mve.h
27
+++ b/hw/ssi/xilinx_spips.c
18
+++ b/target/arm/helper-mve.h
28
@@ -XXX,XX +XXX,XX @@ static MemTxResult lqspi_read(void *opaque, hwaddr addr, uint64_t *value,
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32)
29
return lqspi_read(opaque, addr, value, size, attrs);
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;
30
}
82
}
31
83
32
+static MemTxResult lqspi_write(void *opaque, hwaddr offset, uint64_t value,
84
+static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a)
33
+ unsigned size, MemTxAttrs attrs)
34
+{
85
+{
35
+ /*
86
+ /*
36
+ * From UG1085, Chapter 24 (Quad-SPI controllers):
87
+ * Vector Add Long Across Vector: accumulate the 32-bit
37
+ * - Writes are ignored
88
+ * elements of the vector into a 64-bit result stored in
38
+ * - AXI writes generate an external AXI slave error (SLVERR)
89
+ * a pair of general-purpose registers.
90
+ * No need to check Qm's bank: it is only 3 bits in decode.
39
+ */
91
+ */
40
+ qemu_log_mask(LOG_GUEST_ERROR, "%s Unexpected %u-bit access to 0x%" PRIx64
92
+ TCGv_ptr qm;
41
+ " (value: 0x%" PRIx64 "\n",
93
+ TCGv_i64 rda;
42
+ __func__, size << 3, offset, value);
94
+ TCGv_i32 rdalo, rdahi;
43
+
95
+
44
+ return MEMTX_ERROR;
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;
45
+}
145
+}
46
+
146
+
47
static const MemoryRegionOps lqspi_ops = {
147
static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn)
48
.read_with_attrs = lqspi_read,
148
{
49
+ .write_with_attrs = lqspi_write,
149
TCGv_ptr qd;
50
.endianness = DEVICE_NATIVE_ENDIAN,
51
.valid = {
52
.min_access_size = 1,
53
--
150
--
54
2.20.1
151
2.20.1
55
152
56
153
diff view generated by jsdifflib
New patch
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
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
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
1
In the M-profile architecture, when we do a vector table fetch and it
1
Implement the MVE shifts by register, which perform
2
fails, we need to report a HardFault. Whether this is a Secure HF or
2
shifts on a single general-purpose register.
3
a NonSecure HF depends on several things. If AIRCR.BFHFNMINS is 0
4
then HF is always Secure, because there is no NonSecure HardFault.
5
Otherwise, the answer depends on whether the 'underlying exception'
6
(MemManage, BusFault, SecureFault) targets Secure or NonSecure. (In
7
the pseudocode, this is handled in the Vector() function: the final
8
exc.isSecure is calculated by looking at the exc.isSecure from the
9
exception returned from the memory access, not the isSecure input
10
argument.)
11
12
We weren't doing this correctly, because we were looking at
13
the target security domain of the exception we were trying to
14
load the vector table entry for. This produces errors of two kinds:
15
* a load from the NS vector table which hits the "NS access
16
to S memory" SecureFault should end up as a Secure HardFault,
17
but we were raising an NS HardFault
18
* a load from the S vector table which causes a BusFault
19
should raise an NS HardFault if BFHFNMINS == 1 (because
20
in that case all BusFaults are NonSecure), but we were raising
21
a Secure HardFault
22
23
Correct the logic.
24
25
We also fix a comment error where we claimed that we might
26
be escalating MemManage to HardFault, and forgot about SecureFault.
27
(Vector loads can never hit MPU access faults, because they're
28
always aligned and always use the default address map.)
29
3
30
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
31
Message-id: 20190705094823.28905-1-peter.maydell@linaro.org
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20210628135835.6690-19-peter.maydell@linaro.org
32
---
7
---
33
target/arm/m_helper.c | 21 +++++++++++++++++----
8
target/arm/helper-mve.h | 2 ++
34
1 file changed, 17 insertions(+), 4 deletions(-)
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(-)
35
14
36
diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c
15
diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h
37
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
38
--- a/target/arm/m_helper.c
17
--- a/target/arm/helper-mve.h
39
+++ b/target/arm/m_helper.c
18
+++ b/target/arm/helper-mve.h
40
@@ -XXX,XX +XXX,XX @@ static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure,
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32)
41
if (sattrs.ns) {
20
42
attrs.secure = false;
21
DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
43
} else if (!targets_secure) {
22
DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
44
- /* NS access to S memory */
23
+DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32)
45
+ /*
24
+DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32)
46
+ * NS access to S memory: the underlying exception which we escalate
25
diff --git a/target/arm/translate.h b/target/arm/translate.h
47
+ * to HardFault is SecureFault, which always targets Secure.
26
index XXXXXXX..XXXXXXX 100644
48
+ */
27
--- a/target/arm/translate.h
49
+ exc_secure = true;
28
+++ b/target/arm/translate.h
50
goto load_fail;
29
@@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
51
}
30
typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift);
31
typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32);
32
typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift);
33
+typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
34
35
/**
36
* arm_tbflags_from_tb:
37
diff --git a/target/arm/t32.decode b/target/arm/t32.decode
38
index XXXXXXX..XXXXXXX 100644
39
--- a/target/arm/t32.decode
40
+++ b/target/arm/t32.decode
41
@@ -XXX,XX +XXX,XX @@
42
&mve_shl_ri rdalo rdahi shim
43
&mve_shl_rr rdalo rdahi rm
44
&mve_sh_ri rda shim
45
+&mve_sh_rr rda rm
46
47
# rdahi: bits [3:1] from insn, bit 0 is 1
48
# rdalo: bits [3:1] from insn, bit 0 is 0
49
@@ -XXX,XX +XXX,XX @@
50
&mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9
51
@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \
52
&mve_sh_ri shim=%imm5_12_6
53
+@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr
54
55
{
56
TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi
57
@@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi
58
SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri
52
}
59
}
53
@@ -XXX,XX +XXX,XX @@ static bool arm_v7m_load_vector(ARMCPU *cpu, int exc, bool targets_secure,
60
54
vector_entry = address_space_ldl(arm_addressspace(cs, attrs), addr,
61
- LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
55
attrs, &result);
62
- ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
56
if (result != MEMTX_OK) {
63
- UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr
57
+ /*
64
- SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr
58
+ * Underlying exception is BusFault: its target security state
65
+ {
59
+ * depends on BFHFNMINS.
66
+ UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr
60
+ */
67
+ LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr
61
+ exc_secure = !(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK);
68
+ UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr
62
goto load_fail;
63
}
64
*pvec = vector_entry;
65
@@ -XXX,XX +XXX,XX @@ load_fail:
66
/*
67
* All vector table fetch fails are reported as HardFault, with
68
* HFSR.VECTTBL and .FORCED set. (FORCED is set because
69
- * technically the underlying exception is a MemManage or BusFault
70
+ * technically the underlying exception is a SecureFault or BusFault
71
* that is escalated to HardFault.) This is a terminal exception,
72
* so we will either take the HardFault immediately or else enter
73
* lockup (the latter case is handled in armv7m_nvic_set_pending_derived()).
74
+ * The HardFault is Secure if BFHFNMINS is 0 (meaning that all HFs are
75
+ * secure); otherwise it targets the same security state as the
76
+ * underlying exception.
77
*/
78
- exc_secure = targets_secure ||
79
- !(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK);
80
+ if (!(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) {
81
+ exc_secure = true;
82
+ }
69
+ }
83
env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK | R_V7M_HFSR_FORCED_MASK;
70
+
84
armv7m_nvic_set_pending_derived(env->nvic, ARMV7M_EXCP_HARD, exc_secure);
71
+ {
85
return false;
72
+ SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr
73
+ ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr
74
+ SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr
75
+ }
76
+
77
UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr
78
SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr
79
]
80
diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c
81
index XXXXXXX..XXXXXXX 100644
82
--- a/target/arm/mve_helper.c
83
+++ b/target/arm/mve_helper.c
84
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift)
85
{
86
return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF);
87
}
88
+
89
+uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift)
90
+{
91
+ return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF);
92
+}
93
+
94
+uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift)
95
+{
96
+ return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF);
97
+}
98
diff --git a/target/arm/translate.c b/target/arm/translate.c
99
index XXXXXXX..XXXXXXX 100644
100
--- a/target/arm/translate.c
101
+++ b/target/arm/translate.c
102
@@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a)
103
return do_mve_sh_ri(s, a, gen_mve_uqshl);
104
}
105
106
+static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn)
107
+{
108
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) {
109
+ /* Decode falls through to ORR/MOV UNPREDICTABLE handling */
110
+ return false;
111
+ }
112
+ if (!dc_isar_feature(aa32_mve, s) ||
113
+ !arm_dc_feature(s, ARM_FEATURE_M_MAIN) ||
114
+ a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 ||
115
+ a->rm == a->rda) {
116
+ /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */
117
+ unallocated_encoding(s);
118
+ return true;
119
+ }
120
+
121
+ /* The helper takes care of the sign-extension of the low 8 bits of Rm */
122
+ fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]);
123
+ return true;
124
+}
125
+
126
+static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a)
127
+{
128
+ return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr);
129
+}
130
+
131
+static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a)
132
+{
133
+ return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl);
134
+}
135
+
136
/*
137
* Multiply and multiply accumulate
138
*/
86
--
139
--
87
2.20.1
140
2.20.1
88
141
89
142
diff view generated by jsdifflib