1 | Not very much here, but several people have fallen over | 1 | The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df: |
---|---|---|---|
2 | the vector operation segfault bug, so let's get the fix | ||
3 | into master. | ||
4 | 2 | ||
5 | thanks | 3 | Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100) |
6 | -- PMM | ||
7 | |||
8 | The following changes since commit d418238dca7b4e0b124135827ead3076233052b1: | ||
9 | |||
10 | Merge remote-tracking branch 'remotes/rth/tags/pull-rng-20190522' into staging (2019-05-23 12:57:17 +0100) | ||
11 | 4 | ||
12 | are available in the Git repository at: | 5 | are available in the Git repository at: |
13 | 6 | ||
14 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190523 | 7 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702 |
15 | 8 | ||
16 | for you to fetch changes up to 98e4f4fdb8ea05d840f51f47125924c2bb9df2df: | 9 | for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8: |
17 | 10 | ||
18 | hw/arm/exynos4210: QOM'ify the Exynos4210 SoC (2019-05-23 14:47:44 +0100) | 11 | target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100) |
19 | 12 | ||
20 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
21 | target-arm queue: | 14 | target-arm queue: |
22 | * exynos4210: QOM'ify the Exynos4210 SoC | 15 | * more MVE instructions |
23 | * exynos4210: Add DMA support for the Exynos4210 | 16 | * hw/gpio/gpio_pwr: use shutdown function for reboot |
24 | * arm_gicv3: Fix writes to ICC_CTLR_EL3 | 17 | * target/arm: Check NaN mode before silencing NaN |
25 | * arm_gicv3: Fix write of ICH_VMCR_EL2.{VBPR0, VBPR1} | 18 | * tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
26 | * target/arm: Fix vector operation segfault | 19 | * hw/arm: Add basic power management to raspi. |
27 | * target/arm: Minor improvements to BFXIL, EXTR | 20 | * docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc |
28 | 21 | ||
29 | ---------------------------------------------------------------- | 22 | ---------------------------------------------------------------- |
30 | Alistair Francis (1): | 23 | Joe Komlodi (1): |
31 | target/arm: Fix vector operation segfault | 24 | target/arm: Check NaN mode before silencing NaN |
32 | 25 | ||
33 | Guenter Roeck (1): | 26 | Maxim Uvarov (1): |
34 | hw/arm/exynos4210: Add DMA support for the Exynos4210 | 27 | hw/gpio/gpio_pwr: use shutdown function for reboot |
35 | 28 | ||
36 | Peter Maydell (5): | 29 | Nolan Leake (1): |
37 | arm: Move system_clock_scale to armv7m_systick.h | 30 | hw/arm: Add basic power management to raspi. |
38 | arm: Remove unnecessary includes of hw/arm/arm.h | ||
39 | arm: Rename hw/arm/arm.h to hw/arm/boot.h | ||
40 | hw/intc/arm_gicv3: Fix write of ICH_VMCR_EL2.{VBPR0, VBPR1} | ||
41 | hw/intc/arm_gicv3: Fix writes to ICC_CTLR_EL3 | ||
42 | 31 | ||
43 | Philippe Mathieu-Daudé (3): | 32 | Patrick Venture (2): |
44 | hw/arm/exynos4: Remove unuseful debug code | 33 | docs/system/arm: Add quanta-q7l1-bmc reference |
45 | hw/arm/exynos4: Use the IEC binary prefix definitions | 34 | docs/system/arm: Add quanta-gbs-bmc reference |
46 | hw/arm/exynos4210: QOM'ify the Exynos4210 SoC | ||
47 | 35 | ||
48 | Richard Henderson (2): | 36 | Peter Maydell (18): |
49 | target/arm: Use extract2 for EXTR | 37 | target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation |
50 | target/arm: Simplify BFXIL expansion | 38 | target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH |
39 | target/arm: Make asimd_imm_const() public | ||
40 | target/arm: Use asimd_imm_const for A64 decode | ||
41 | target/arm: Use dup_const() instead of bitfield_replicate() | ||
42 | target/arm: Implement MVE logical immediate insns | ||
43 | target/arm: Implement MVE vector shift left by immediate insns | ||
44 | target/arm: Implement MVE vector shift right by immediate insns | ||
45 | target/arm: Implement MVE VSHLL | ||
46 | target/arm: Implement MVE VSRI, VSLI | ||
47 | target/arm: Implement MVE VSHRN, VRSHRN | ||
48 | target/arm: Implement MVE saturating narrowing shifts | ||
49 | target/arm: Implement MVE VSHLC | ||
50 | target/arm: Implement MVE VADDLV | ||
51 | target/arm: Implement MVE long shifts by immediate | ||
52 | target/arm: Implement MVE long shifts by register | ||
53 | target/arm: Implement MVE shifts by immediate | ||
54 | target/arm: Implement MVE shifts by register | ||
51 | 55 | ||
52 | include/hw/arm/allwinner-a10.h | 2 +- | 56 | Philippe Mathieu-Daudé (1): |
53 | include/hw/arm/aspeed_soc.h | 1 - | 57 | tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
54 | include/hw/arm/bcm2836.h | 1 - | ||
55 | include/hw/arm/{arm.h => boot.h} | 12 +++------ | ||
56 | include/hw/arm/exynos4210.h | 9 +++++-- | ||
57 | include/hw/arm/fsl-imx25.h | 2 +- | ||
58 | include/hw/arm/fsl-imx31.h | 2 +- | ||
59 | include/hw/arm/fsl-imx6.h | 2 +- | ||
60 | include/hw/arm/fsl-imx6ul.h | 2 +- | ||
61 | include/hw/arm/fsl-imx7.h | 2 +- | ||
62 | include/hw/arm/virt.h | 2 +- | ||
63 | include/hw/arm/xlnx-versal.h | 2 +- | ||
64 | include/hw/arm/xlnx-zynqmp.h | 2 +- | ||
65 | include/hw/timer/armv7m_systick.h | 22 ++++++++++++++++ | ||
66 | hw/arm/armsse.c | 2 +- | ||
67 | hw/arm/armv7m.c | 2 +- | ||
68 | hw/arm/aspeed.c | 2 +- | ||
69 | hw/arm/boot.c | 2 +- | ||
70 | hw/arm/collie.c | 2 +- | ||
71 | hw/arm/exynos4210.c | 54 ++++++++++++++++++++++++++++++++++++--- | ||
72 | hw/arm/exynos4_boards.c | 40 ++++++++--------------------- | ||
73 | hw/arm/highbank.c | 2 +- | ||
74 | hw/arm/integratorcp.c | 2 +- | ||
75 | hw/arm/mainstone.c | 2 +- | ||
76 | hw/arm/microbit.c | 2 +- | ||
77 | hw/arm/mps2-tz.c | 2 +- | ||
78 | hw/arm/mps2.c | 2 +- | ||
79 | hw/arm/msf2-soc.c | 1 - | ||
80 | hw/arm/msf2-som.c | 2 +- | ||
81 | hw/arm/musca.c | 2 +- | ||
82 | hw/arm/musicpal.c | 2 +- | ||
83 | hw/arm/netduino2.c | 2 +- | ||
84 | hw/arm/nrf51_soc.c | 2 +- | ||
85 | hw/arm/nseries.c | 2 +- | ||
86 | hw/arm/omap1.c | 2 +- | ||
87 | hw/arm/omap2.c | 2 +- | ||
88 | hw/arm/omap_sx1.c | 2 +- | ||
89 | hw/arm/palm.c | 2 +- | ||
90 | hw/arm/raspi.c | 2 +- | ||
91 | hw/arm/realview.c | 2 +- | ||
92 | hw/arm/spitz.c | 2 +- | ||
93 | hw/arm/stellaris.c | 2 +- | ||
94 | hw/arm/stm32f205_soc.c | 2 +- | ||
95 | hw/arm/strongarm.c | 2 +- | ||
96 | hw/arm/tosa.c | 2 +- | ||
97 | hw/arm/versatilepb.c | 2 +- | ||
98 | hw/arm/vexpress.c | 2 +- | ||
99 | hw/arm/virt.c | 2 +- | ||
100 | hw/arm/xilinx_zynq.c | 2 +- | ||
101 | hw/arm/xlnx-versal.c | 2 +- | ||
102 | hw/arm/z2.c | 2 +- | ||
103 | hw/intc/arm_gicv3_cpuif.c | 6 ++--- | ||
104 | hw/intc/armv7m_nvic.c | 1 - | ||
105 | target/arm/arm-semi.c | 1 - | ||
106 | target/arm/cpu.c | 1 - | ||
107 | target/arm/cpu64.c | 1 - | ||
108 | target/arm/kvm.c | 1 - | ||
109 | target/arm/kvm32.c | 1 - | ||
110 | target/arm/kvm64.c | 1 - | ||
111 | target/arm/translate-a64.c | 44 ++++++++++++++++--------------- | ||
112 | target/arm/translate.c | 4 +-- | ||
113 | 61 files changed, 164 insertions(+), 123 deletions(-) | ||
114 | rename include/hw/arm/{arm.h => boot.h} (96%) | ||
115 | 58 | ||
59 | docs/system/arm/aspeed.rst | 1 + | ||
60 | docs/system/arm/nuvoton.rst | 5 +- | ||
61 | include/hw/arm/bcm2835_peripherals.h | 3 +- | ||
62 | include/hw/misc/bcm2835_powermgt.h | 29 ++ | ||
63 | target/arm/helper-mve.h | 108 +++++++ | ||
64 | target/arm/translate.h | 41 +++ | ||
65 | target/arm/mve.decode | 177 ++++++++++- | ||
66 | target/arm/t32.decode | 71 ++++- | ||
67 | hw/arm/bcm2835_peripherals.c | 13 +- | ||
68 | hw/gpio/gpio_pwr.c | 2 +- | ||
69 | hw/misc/bcm2835_powermgt.c | 160 ++++++++++ | ||
70 | target/arm/helper-a64.c | 12 +- | ||
71 | target/arm/mve_helper.c | 524 +++++++++++++++++++++++++++++++-- | ||
72 | target/arm/translate-a64.c | 86 +----- | ||
73 | target/arm/translate-mve.c | 261 +++++++++++++++- | ||
74 | target/arm/translate-neon.c | 81 ----- | ||
75 | target/arm/translate.c | 327 +++++++++++++++++++- | ||
76 | target/arm/vfp_helper.c | 24 +- | ||
77 | hw/misc/meson.build | 1 + | ||
78 | tests/acceptance/boot_linux_console.py | 43 +++ | ||
79 | 20 files changed, 1760 insertions(+), 209 deletions(-) | ||
80 | create mode 100644 include/hw/misc/bcm2835_powermgt.h | ||
81 | create mode 100644 hw/misc/bcm2835_powermgt.c | ||
82 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Patrick Venture <venture@google.com> | ||
1 | 2 | ||
3 | Adds a line-item reference to the supported quanta-q71l-bmc aspeed | ||
4 | entry. | ||
5 | |||
6 | Signed-off-by: Patrick Venture <venture@google.com> | ||
7 | Reviewed-by: Cédric Le Goater <clg@kaod.org> | ||
8 | Message-id: 20210615192848.1065297-2-venture@google.com | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | docs/system/arm/aspeed.rst | 1 + | ||
12 | 1 file changed, 1 insertion(+) | ||
13 | |||
14 | diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/docs/system/arm/aspeed.rst | ||
17 | +++ b/docs/system/arm/aspeed.rst | ||
18 | @@ -XXX,XX +XXX,XX @@ etc. | ||
19 | AST2400 SoC based machines : | ||
20 | |||
21 | - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC | ||
22 | +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC | ||
23 | |||
24 | AST2500 SoC based machines : | ||
25 | |||
26 | -- | ||
27 | 2.20.1 | ||
28 | |||
29 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Patrick Venture <venture@google.com> | ||
1 | 2 | ||
3 | Add line item reference to quanta-gbs-bmc machine. | ||
4 | |||
5 | Signed-off-by: Patrick Venture <venture@google.com> | ||
6 | Reviewed-by: Cédric Le Goater <clg@kaod.org> | ||
7 | Message-id: 20210615192848.1065297-3-venture@google.com | ||
8 | [PMM: fixed underline Sphinx warning] | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | docs/system/arm/nuvoton.rst | 5 +++-- | ||
12 | 1 file changed, 3 insertions(+), 2 deletions(-) | ||
13 | |||
14 | diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/docs/system/arm/nuvoton.rst | ||
17 | +++ b/docs/system/arm/nuvoton.rst | ||
18 | @@ -XXX,XX +XXX,XX @@ | ||
19 | -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) | ||
20 | -===================================================== | ||
21 | +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) | ||
22 | +================================================================ | ||
23 | |||
24 | The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are | ||
25 | designed to be used as Baseboard Management Controllers (BMCs) in various | ||
26 | @@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip : | ||
27 | The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and | ||
28 | Hyperscale applications. The following machines are based on this chip : | ||
29 | |||
30 | +- ``quanta-gbs-bmc`` Quanta GBS server BMC | ||
31 | - ``quanta-gsj`` Quanta GSJ server BMC | ||
32 | |||
33 | There are also two more SoCs, NPCM710 and NPCM705, which are single-core | ||
34 | -- | ||
35 | 2.20.1 | ||
36 | |||
37 | diff view generated by jsdifflib |
1 | From: Philippe Mathieu-Daudé <philmd@redhat.com> | 1 | From: Nolan Leake <nolan@sigbus.net> |
---|---|---|---|
2 | 2 | ||
3 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 3 | This is just enough to make reboot and poweroff work. Works for |
4 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | 4 | linux, u-boot, and the arm trusted firmware. Not tested, but should |
5 | Message-id: 20190520214342.13709-5-philmd@redhat.com | 5 | work for plan9, and bare-metal/hobby OSes, since they seem to generally |
6 | do what linux does for reset. | ||
7 | |||
8 | The watchdog timer functionality is not yet implemented. | ||
9 | |||
10 | Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64 | ||
11 | Signed-off-by: Nolan Leake <nolan@sigbus.net> | ||
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
13 | Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
14 | Message-id: 20210625210209.1870217-1-nolan@sigbus.net | ||
15 | [PMM: tweaked commit title; fixed region size to 0x200; | ||
16 | moved header file to include/] | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
7 | --- | 18 | --- |
8 | include/hw/arm/exynos4210.h | 9 +++++++-- | 19 | include/hw/arm/bcm2835_peripherals.h | 3 +- |
9 | hw/arm/exynos4210.c | 28 ++++++++++++++++++++++++---- | 20 | include/hw/misc/bcm2835_powermgt.h | 29 +++++ |
10 | hw/arm/exynos4_boards.c | 9 ++++++--- | 21 | hw/arm/bcm2835_peripherals.c | 13 ++- |
11 | 3 files changed, 37 insertions(+), 9 deletions(-) | 22 | hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++ |
12 | 23 | hw/misc/meson.build | 1 + | |
13 | diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.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 | ||
14 | index XXXXXXX..XXXXXXX 100644 | 29 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/include/hw/arm/exynos4210.h | 30 | --- a/include/hw/arm/bcm2835_peripherals.h |
16 | +++ b/include/hw/arm/exynos4210.h | 31 | +++ b/include/hw/arm/bcm2835_peripherals.h |
17 | @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { | 32 | @@ -XXX,XX +XXX,XX @@ |
18 | } Exynos4210Irq; | 33 | #include "hw/misc/bcm2835_mphi.h" |
19 | 34 | #include "hw/misc/bcm2835_thermal.h" | |
20 | typedef struct Exynos4210State { | 35 | #include "hw/misc/bcm2835_cprman.h" |
21 | + /*< private >*/ | 36 | +#include "hw/misc/bcm2835_powermgt.h" |
22 | + SysBusDevice parent_obj; | 37 | #include "hw/sd/sdhci.h" |
23 | + /*< public >*/ | 38 | #include "hw/sd/bcm2835_sdhost.h" |
24 | ARMCPU *cpu[EXYNOS4210_NCPUS]; | 39 | #include "hw/gpio/bcm2835_gpio.h" |
25 | Exynos4210Irq irqs; | 40 | @@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState { |
26 | qemu_irq *irq_table; | 41 | BCM2835MphiState mphi; |
27 | @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210State { | 42 | UnimplementedDeviceState txp; |
28 | I2CBus *i2c_if[EXYNOS4210_I2C_NUMBER]; | 43 | UnimplementedDeviceState armtmr; |
29 | } Exynos4210State; | 44 | - UnimplementedDeviceState powermgt; |
30 | 45 | + BCM2835PowerMgtState powermgt; | |
31 | +#define TYPE_EXYNOS4210_SOC "exynos4210" | 46 | BCM2835CprmanState cprman; |
32 | +#define EXYNOS4210_SOC(obj) \ | 47 | PL011State uart0; |
33 | + OBJECT_CHECK(Exynos4210State, obj, TYPE_EXYNOS4210_SOC) | 48 | BCM2835AuxState aux; |
34 | + | 49 | diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h |
35 | void exynos4210_write_secondary(ARMCPU *cpu, | 50 | new file mode 100644 |
36 | const struct arm_boot_info *info); | 51 | index XXXXXXX..XXXXXXX |
37 | 52 | --- /dev/null | |
38 | -Exynos4210State *exynos4210_init(MemoryRegion *system_mem); | 53 | +++ b/include/hw/misc/bcm2835_powermgt.h |
39 | - | 54 | @@ -XXX,XX +XXX,XX @@ |
40 | /* Initialize exynos4210 IRQ subsystem stub */ | 55 | +/* |
41 | qemu_irq *exynos4210_init_irq(Exynos4210Irq *env); | 56 | + * BCM2835 Power Management emulation |
42 | 57 | + * | |
43 | diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c | 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 | ||
44 | index XXXXXXX..XXXXXXX 100644 | 85 | index XXXXXXX..XXXXXXX 100644 |
45 | --- a/hw/arm/exynos4210.c | 86 | --- a/hw/arm/bcm2835_peripherals.c |
46 | +++ b/hw/arm/exynos4210.c | 87 | +++ b/hw/arm/bcm2835_peripherals.c |
47 | @@ -XXX,XX +XXX,XX @@ static void pl330_create(uint32_t base, qemu_irq irq, int nreq) | 88 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) |
48 | sysbus_connect_irq(busdev, 0, irq); | 89 | |
90 | object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", | ||
91 | OBJECT(&s->gpu_bus_mr)); | ||
92 | + | ||
93 | + /* Power Management */ | ||
94 | + object_initialize_child(obj, "powermgt", &s->powermgt, | ||
95 | + TYPE_BCM2835_POWERMGT); | ||
49 | } | 96 | } |
50 | 97 | ||
51 | -Exynos4210State *exynos4210_init(MemoryRegion *system_mem) | 98 | static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) |
52 | +static void exynos4210_realize(DeviceState *socdev, Error **errp) | 99 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) |
53 | { | 100 | qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, |
54 | - Exynos4210State *s = g_new0(Exynos4210State, 1); | 101 | INTERRUPT_USB)); |
55 | + Exynos4210State *s = EXYNOS4210_SOC(socdev); | 102 | |
56 | + MemoryRegion *system_mem = get_system_memory(); | 103 | + /* Power Management */ |
57 | qemu_irq gate_irq[EXYNOS4210_NCPUS][EXYNOS4210_IRQ_GATE_NINPUTS]; | 104 | + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { |
58 | SysBusDevice *busdev; | 105 | + return; |
59 | DeviceState *dev; | 106 | + } |
60 | @@ -XXX,XX +XXX,XX @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem) | 107 | + |
61 | qemu_irq_invert(s->irq_table[exynos4210_get_irq(36, 1)]), 32); | 108 | + memory_region_add_subregion(&s->peri_mr, PM_OFFSET, |
62 | pl330_create(EXYNOS4210_PL330_BASE2_ADDR, | 109 | + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0)); |
63 | qemu_irq_invert(s->irq_table[exynos4210_get_irq(34, 1)]), 1); | 110 | + |
64 | - | 111 | create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); |
65 | - return s; | 112 | create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); |
66 | } | 113 | - create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114); |
67 | + | 114 | create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); |
68 | +static void exynos4210_class_init(ObjectClass *klass, void *data) | 115 | create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); |
116 | create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20); | ||
117 | diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c | ||
118 | new file mode 100644 | ||
119 | index XXXXXXX..XXXXXXX | ||
120 | --- /dev/null | ||
121 | +++ b/hw/misc/bcm2835_powermgt.c | ||
122 | @@ -XXX,XX +XXX,XX @@ | ||
123 | +/* | ||
124 | + * BCM2835 Power Management emulation | ||
125 | + * | ||
126 | + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> | ||
127 | + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> | ||
128 | + * | ||
129 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. | ||
130 | + * See the COPYING file in the top-level directory. | ||
131 | + */ | ||
132 | + | ||
133 | +#include "qemu/osdep.h" | ||
134 | +#include "qemu/log.h" | ||
135 | +#include "qemu/module.h" | ||
136 | +#include "hw/misc/bcm2835_powermgt.h" | ||
137 | +#include "migration/vmstate.h" | ||
138 | +#include "sysemu/runstate.h" | ||
139 | + | ||
140 | +#define PASSWORD 0x5a000000 | ||
141 | +#define PASSWORD_MASK 0xff000000 | ||
142 | + | ||
143 | +#define R_RSTC 0x1c | ||
144 | +#define V_RSTC_RESET 0x20 | ||
145 | +#define R_RSTS 0x20 | ||
146 | +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ | ||
147 | +#define R_WDOG 0x24 | ||
148 | + | ||
149 | +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, | ||
150 | + unsigned size) | ||
151 | +{ | ||
152 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; | ||
153 | + uint32_t res = 0; | ||
154 | + | ||
155 | + switch (offset) { | ||
156 | + case R_RSTC: | ||
157 | + res = s->rstc; | ||
158 | + break; | ||
159 | + case R_RSTS: | ||
160 | + res = s->rsts; | ||
161 | + break; | ||
162 | + case R_WDOG: | ||
163 | + res = s->wdog; | ||
164 | + break; | ||
165 | + | ||
166 | + default: | ||
167 | + qemu_log_mask(LOG_UNIMP, | ||
168 | + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx | ||
169 | + "\n", offset); | ||
170 | + res = 0; | ||
171 | + break; | ||
172 | + } | ||
173 | + | ||
174 | + return res; | ||
175 | +} | ||
176 | + | ||
177 | +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, | ||
178 | + uint64_t value, unsigned size) | ||
179 | +{ | ||
180 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; | ||
181 | + | ||
182 | + if ((value & PASSWORD_MASK) != PASSWORD) { | ||
183 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
184 | + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 | ||
185 | + " at offset 0x%08"HWADDR_PRIx"\n", | ||
186 | + value, offset); | ||
187 | + return; | ||
188 | + } | ||
189 | + | ||
190 | + value = value & ~PASSWORD_MASK; | ||
191 | + | ||
192 | + switch (offset) { | ||
193 | + case R_RSTC: | ||
194 | + s->rstc = value; | ||
195 | + if (value & V_RSTC_RESET) { | ||
196 | + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { | ||
197 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); | ||
198 | + } else { | ||
199 | + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); | ||
200 | + } | ||
201 | + } | ||
202 | + break; | ||
203 | + case R_RSTS: | ||
204 | + qemu_log_mask(LOG_UNIMP, | ||
205 | + "bcm2835_powermgt_write: RSTS\n"); | ||
206 | + s->rsts = value; | ||
207 | + break; | ||
208 | + case R_WDOG: | ||
209 | + qemu_log_mask(LOG_UNIMP, | ||
210 | + "bcm2835_powermgt_write: WDOG\n"); | ||
211 | + s->wdog = value; | ||
212 | + break; | ||
213 | + | ||
214 | + default: | ||
215 | + qemu_log_mask(LOG_UNIMP, | ||
216 | + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx | ||
217 | + "\n", offset); | ||
218 | + break; | ||
219 | + } | ||
220 | +} | ||
221 | + | ||
222 | +static const MemoryRegionOps bcm2835_powermgt_ops = { | ||
223 | + .read = bcm2835_powermgt_read, | ||
224 | + .write = bcm2835_powermgt_write, | ||
225 | + .endianness = DEVICE_NATIVE_ENDIAN, | ||
226 | + .impl.min_access_size = 4, | ||
227 | + .impl.max_access_size = 4, | ||
228 | +}; | ||
229 | + | ||
230 | +static const VMStateDescription vmstate_bcm2835_powermgt = { | ||
231 | + .name = TYPE_BCM2835_POWERMGT, | ||
232 | + .version_id = 1, | ||
233 | + .minimum_version_id = 1, | ||
234 | + .fields = (VMStateField[]) { | ||
235 | + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), | ||
236 | + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), | ||
237 | + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), | ||
238 | + VMSTATE_END_OF_LIST() | ||
239 | + } | ||
240 | +}; | ||
241 | + | ||
242 | +static void bcm2835_powermgt_init(Object *obj) | ||
243 | +{ | ||
244 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); | ||
245 | + | ||
246 | + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, | ||
247 | + TYPE_BCM2835_POWERMGT, 0x200); | ||
248 | + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); | ||
249 | +} | ||
250 | + | ||
251 | +static void bcm2835_powermgt_reset(DeviceState *dev) | ||
252 | +{ | ||
253 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); | ||
254 | + | ||
255 | + /* https://elinux.org/BCM2835_registers#PM */ | ||
256 | + s->rstc = 0x00000102; | ||
257 | + s->rsts = 0x00001000; | ||
258 | + s->wdog = 0x00000000; | ||
259 | +} | ||
260 | + | ||
261 | +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) | ||
69 | +{ | 262 | +{ |
70 | + DeviceClass *dc = DEVICE_CLASS(klass); | 263 | + DeviceClass *dc = DEVICE_CLASS(klass); |
71 | + | 264 | + |
72 | + dc->realize = exynos4210_realize; | 265 | + dc->reset = bcm2835_powermgt_reset; |
73 | +} | 266 | + dc->vmsd = &vmstate_bcm2835_powermgt; |
74 | + | 267 | +} |
75 | +static const TypeInfo exynos4210_info = { | 268 | + |
76 | + .name = TYPE_EXYNOS4210_SOC, | 269 | +static TypeInfo bcm2835_powermgt_info = { |
77 | + .parent = TYPE_SYS_BUS_DEVICE, | 270 | + .name = TYPE_BCM2835_POWERMGT, |
78 | + .instance_size = sizeof(Exynos4210State), | 271 | + .parent = TYPE_SYS_BUS_DEVICE, |
79 | + .class_init = exynos4210_class_init, | 272 | + .instance_size = sizeof(BCM2835PowerMgtState), |
80 | +}; | 273 | + .class_init = bcm2835_powermgt_class_init, |
81 | + | 274 | + .instance_init = bcm2835_powermgt_init, |
82 | +static void exynos4210_register_types(void) | 275 | +}; |
83 | +{ | 276 | + |
84 | + type_register_static(&exynos4210_info); | 277 | +static void bcm2835_powermgt_register_types(void) |
85 | +} | 278 | +{ |
86 | + | 279 | + type_register_static(&bcm2835_powermgt_info); |
87 | +type_init(exynos4210_register_types) | 280 | +} |
88 | diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c | 281 | + |
282 | +type_init(bcm2835_powermgt_register_types) | ||
283 | diff --git a/hw/misc/meson.build b/hw/misc/meson.build | ||
89 | index XXXXXXX..XXXXXXX 100644 | 284 | index XXXXXXX..XXXXXXX 100644 |
90 | --- a/hw/arm/exynos4_boards.c | 285 | --- a/hw/misc/meson.build |
91 | +++ b/hw/arm/exynos4_boards.c | 286 | +++ b/hw/misc/meson.build |
92 | @@ -XXX,XX +XXX,XX @@ typedef enum Exynos4BoardType { | 287 | @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( |
93 | } Exynos4BoardType; | 288 | 'bcm2835_rng.c', |
94 | 289 | 'bcm2835_thermal.c', | |
95 | typedef struct Exynos4BoardState { | 290 | 'bcm2835_cprman.c', |
96 | - Exynos4210State *soc; | 291 | + 'bcm2835_powermgt.c', |
97 | + Exynos4210State soc; | 292 | )) |
98 | MemoryRegion dram0_mem; | 293 | softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) |
99 | MemoryRegion dram1_mem; | 294 | softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) |
100 | } Exynos4BoardState; | ||
101 | @@ -XXX,XX +XXX,XX @@ exynos4_boards_init_common(MachineState *machine, | ||
102 | exynos4_boards_init_ram(s, get_system_memory(), | ||
103 | exynos4_board_ram_size[board_type]); | ||
104 | |||
105 | - s->soc = exynos4210_init(get_system_memory()); | ||
106 | + object_initialize(&s->soc, sizeof(s->soc), TYPE_EXYNOS4210_SOC); | ||
107 | + qdev_set_parent_bus(DEVICE(&s->soc), sysbus_get_default()); | ||
108 | + object_property_set_bool(OBJECT(&s->soc), true, "realized", | ||
109 | + &error_fatal); | ||
110 | |||
111 | return s; | ||
112 | } | ||
113 | @@ -XXX,XX +XXX,XX @@ static void smdkc210_init(MachineState *machine) | ||
114 | EXYNOS4_BOARD_SMDKC210); | ||
115 | |||
116 | lan9215_init(SMDK_LAN9118_BASE_ADDR, | ||
117 | - qemu_irq_invert(s->soc->irq_table[exynos4210_get_irq(37, 1)])); | ||
118 | + qemu_irq_invert(s->soc.irq_table[exynos4210_get_irq(37, 1)])); | ||
119 | arm_load_kernel(ARM_CPU(first_cpu), &exynos4_board_binfo); | ||
120 | } | ||
121 | |||
122 | -- | 295 | -- |
123 | 2.20.1 | 296 | 2.20.1 |
124 | 297 | ||
125 | 298 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
1 | 2 | ||
3 | Add a test booting and quickly shutdown a raspi2 machine, | ||
4 | to test the power management model: | ||
5 | |||
6 | (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd: | ||
7 | console: [ 0.000000] Booting Linux on physical CPU 0xf00 | ||
8 | console: [ 0.000000] Linux version 4.14.98-v7+ (dom@dom-XPS-13-9370) (gcc version 4.9.3 (crosstool-NG crosstool-ng-1.22.0-88-g8460611)) #1200 SMP Tue Feb 12 20:27:48 GMT 2019 | ||
9 | console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d | ||
10 | console: [ 0.000000] CPU: div instructions available: patching division code | ||
11 | console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache | ||
12 | console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B | ||
13 | ... | ||
14 | console: Boot successful. | ||
15 | console: cat /proc/cpuinfo | ||
16 | console: / # cat /proc/cpuinfo | ||
17 | ... | ||
18 | console: processor : 3 | ||
19 | console: model name : ARMv7 Processor rev 5 (v7l) | ||
20 | console: BogoMIPS : 125.00 | ||
21 | console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm | ||
22 | console: CPU implementer : 0x41 | ||
23 | console: CPU architecture: 7 | ||
24 | console: CPU variant : 0x0 | ||
25 | console: CPU part : 0xc07 | ||
26 | console: CPU revision : 5 | ||
27 | console: Hardware : BCM2835 | ||
28 | console: Revision : 0000 | ||
29 | console: Serial : 0000000000000000 | ||
30 | console: cat /proc/iomem | ||
31 | console: / # cat /proc/iomem | ||
32 | console: 00000000-3bffffff : System RAM | ||
33 | console: 00008000-00afffff : Kernel code | ||
34 | console: 00c00000-00d468ef : Kernel data | ||
35 | console: 3f006000-3f006fff : dwc_otg | ||
36 | console: 3f007000-3f007eff : /soc/dma@7e007000 | ||
37 | console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880 | ||
38 | console: 3f100000-3f100027 : /soc/watchdog@7e100000 | ||
39 | console: 3f101000-3f102fff : /soc/cprman@7e101000 | ||
40 | console: 3f200000-3f2000b3 : /soc/gpio@7e200000 | ||
41 | PASS (24.59 s) | ||
42 | RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 | ||
43 | JOB TIME : 25.02 s | ||
44 | |||
45 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
46 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> | ||
47 | Message-id: 20210531113837.1689775-1-f4bug@amsat.org | ||
48 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
49 | --- | ||
50 | tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++ | ||
51 | 1 file changed, 43 insertions(+) | ||
52 | |||
53 | diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py | ||
54 | index XXXXXXX..XXXXXXX 100644 | ||
55 | --- a/tests/acceptance/boot_linux_console.py | ||
56 | +++ b/tests/acceptance/boot_linux_console.py | ||
57 | @@ -XXX,XX +XXX,XX @@ | ||
58 | from avocado import skip | ||
59 | from avocado import skipUnless | ||
60 | from avocado_qemu import Test | ||
61 | +from avocado_qemu import exec_command | ||
62 | from avocado_qemu import exec_command_and_wait_for_pattern | ||
63 | from avocado_qemu import interrupt_interactive_console_until_pattern | ||
64 | from avocado_qemu import wait_for_console_pattern | ||
65 | @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): | ||
66 | """ | ||
67 | self.do_test_arm_raspi2(0) | ||
68 | |||
69 | + def test_arm_raspi2_initrd(self): | ||
70 | + """ | ||
71 | + :avocado: tags=arch:arm | ||
72 | + :avocado: tags=machine:raspi2 | ||
73 | + """ | ||
74 | + deb_url = ('http://archive.raspberrypi.org/debian/' | ||
75 | + 'pool/main/r/raspberrypi-firmware/' | ||
76 | + 'raspberrypi-kernel_1.20190215-1_armhf.deb') | ||
77 | + deb_hash = 'cd284220b32128c5084037553db3c482426f3972' | ||
78 | + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) | ||
79 | + kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img') | ||
80 | + dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb') | ||
81 | + | ||
82 | + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' | ||
83 | + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' | ||
84 | + 'arm/rootfs-armv7a.cpio.gz') | ||
85 | + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' | ||
86 | + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) | ||
87 | + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') | ||
88 | + archive.gzip_uncompress(initrd_path_gz, initrd_path) | ||
89 | + | ||
90 | + self.vm.set_console() | ||
91 | + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + | ||
92 | + 'earlycon=pl011,0x3f201000 console=ttyAMA0 ' | ||
93 | + 'panic=-1 noreboot ' + | ||
94 | + 'dwc_otg.fiq_fsm_enable=0') | ||
95 | + self.vm.add_args('-kernel', kernel_path, | ||
96 | + '-dtb', dtb_path, | ||
97 | + '-initrd', initrd_path, | ||
98 | + '-append', kernel_command_line, | ||
99 | + '-no-reboot') | ||
100 | + self.vm.launch() | ||
101 | + self.wait_for_console_pattern('Boot successful.') | ||
102 | + | ||
103 | + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', | ||
104 | + 'BCM2835') | ||
105 | + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', | ||
106 | + '/soc/cprman@7e101000') | ||
107 | + exec_command(self, 'halt') | ||
108 | + # Wait for VM to shut down gracefully | ||
109 | + self.vm.wait() | ||
110 | + | ||
111 | def test_arm_exynos4210_initrd(self): | ||
112 | """ | ||
113 | :avocado: tags=arch:arm | ||
114 | -- | ||
115 | 2.20.1 | ||
116 | |||
117 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Joe Komlodi <joe.komlodi@xilinx.com> | ||
1 | 2 | ||
3 | If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute | ||
4 | FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will | ||
5 | assert due to fpst->default_nan_mode being set. | ||
6 | |||
7 | To avoid this, we check to see what NaN mode we're running in before we call | ||
8 | floatxx_silence_nan(). | ||
9 | |||
10 | Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com> | ||
11 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
12 | Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com | ||
13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
15 | --- | ||
16 | target/arm/helper-a64.c | 12 +++++++++--- | ||
17 | target/arm/vfp_helper.c | 24 ++++++++++++++++++------ | ||
18 | 2 files changed, 27 insertions(+), 9 deletions(-) | ||
19 | |||
20 | diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c | ||
21 | index XXXXXXX..XXXXXXX 100644 | ||
22 | --- a/target/arm/helper-a64.c | ||
23 | +++ b/target/arm/helper-a64.c | ||
24 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) | ||
25 | float16 nan = a; | ||
26 | if (float16_is_signaling_nan(a, fpst)) { | ||
27 | float_raise(float_flag_invalid, fpst); | ||
28 | - nan = float16_silence_nan(a, fpst); | ||
29 | + if (!fpst->default_nan_mode) { | ||
30 | + nan = float16_silence_nan(a, fpst); | ||
31 | + } | ||
32 | } | ||
33 | if (fpst->default_nan_mode) { | ||
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); | ||
127 | -- | ||
128 | 2.20.1 | ||
129 | |||
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 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 3 | qemu has 2 type of functions: shutdown and reboot. Shutdown |
4 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | 4 | function has to be used for machine shutdown. Otherwise we cause |
5 | Message-id: 20190520214342.13709-2-philmd@redhat.com | 5 | a reset with a bogus "cause" value, when we intended a shutdown. |
6 | |||
7 | Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org> | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org | ||
10 | [PMM: tweaked commit message] | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
7 | --- | 12 | --- |
8 | hw/arm/exynos4_boards.c | 24 ------------------------ | 13 | hw/gpio/gpio_pwr.c | 2 +- |
9 | 1 file changed, 24 deletions(-) | 14 | 1 file changed, 1 insertion(+), 1 deletion(-) |
10 | 15 | ||
11 | diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c | 16 | diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c |
12 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/hw/arm/exynos4_boards.c | 18 | --- a/hw/gpio/gpio_pwr.c |
14 | +++ b/hw/arm/exynos4_boards.c | 19 | +++ b/hw/gpio/gpio_pwr.c |
15 | @@ -XXX,XX +XXX,XX @@ | 20 | @@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level) |
16 | #include "hw/net/lan9118.h" | 21 | static void gpio_pwr_shutdown(void *opaque, int n, int level) |
17 | #include "hw/boards.h" | 22 | { |
18 | 23 | if (level) { | |
19 | -#undef DEBUG | 24 | - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
20 | - | 25 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
21 | -//#define DEBUG | 26 | } |
22 | - | 27 | } |
23 | -#ifdef DEBUG | ||
24 | - #undef PRINT_DEBUG | ||
25 | - #define PRINT_DEBUG(fmt, args...) \ | ||
26 | - do { \ | ||
27 | - fprintf(stderr, " [%s:%d] "fmt, __func__, __LINE__, ##args); \ | ||
28 | - } while (0) | ||
29 | -#else | ||
30 | - #define PRINT_DEBUG(fmt, args...) do {} while (0) | ||
31 | -#endif | ||
32 | - | ||
33 | #define SMDK_LAN9118_BASE_ADDR 0x05000000 | ||
34 | |||
35 | typedef enum Exynos4BoardType { | ||
36 | @@ -XXX,XX +XXX,XX @@ exynos4_boards_init_common(MachineState *machine, | ||
37 | exynos4_board_binfo.gic_cpu_if_addr = | ||
38 | EXYNOS4210_SMP_PRIVATE_BASE_ADDR + 0x100; | ||
39 | |||
40 | - PRINT_DEBUG("\n ram_size: %luMiB [0x%08lx]\n" | ||
41 | - " kernel_filename: %s\n" | ||
42 | - " kernel_cmdline: %s\n" | ||
43 | - " initrd_filename: %s\n", | ||
44 | - exynos4_board_ram_size[board_type] / 1048576, | ||
45 | - exynos4_board_ram_size[board_type], | ||
46 | - machine->kernel_filename, | ||
47 | - machine->kernel_cmdline, | ||
48 | - machine->initrd_filename); | ||
49 | - | ||
50 | exynos4_boards_init_ram(s, get_system_memory(), | ||
51 | exynos4_board_ram_size[board_type]); | ||
52 | 28 | ||
53 | -- | 29 | -- |
54 | 2.20.1 | 30 | 2.20.1 |
55 | 31 | ||
56 | 32 | diff view generated by jsdifflib |
1 | The ICC_CTLR_EL3 register includes some bits which are aliases | 1 | In do_ldst(), the calculation of the offset needs to be based on the |
---|---|---|---|
2 | of bits in the ICC_CTLR_EL1(S) and (NS) registers. QEMU chooses | 2 | size of the memory access, not the size of the elements in the |
3 | to keep those bits in the cs->icc_ctlr_el1[] struct fields. | 3 | vector. This meant we were getting it wrong for the widening and |
4 | Unfortunately a missing '~' in the code to update the bits | 4 | narrowing variants of the various VLDR and VSTR insns. |
5 | in those fields meant that writing to ICC_CTLR_EL3 would corrupt | ||
6 | the ICC_CLTR_EL1 register values. | ||
7 | 5 | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
10 | Message-id: 20190520162809.2677-5-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-2-peter.maydell@linaro.org |
11 | --- | 9 | --- |
12 | hw/intc/arm_gicv3_cpuif.c | 4 ++-- | 10 | target/arm/translate-mve.c | 17 +++++++++-------- |
13 | 1 file changed, 2 insertions(+), 2 deletions(-) | 11 | 1 file changed, 9 insertions(+), 8 deletions(-) |
14 | 12 | ||
15 | diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c | 13 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c |
16 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/hw/intc/arm_gicv3_cpuif.c | 15 | --- a/target/arm/translate-mve.c |
18 | +++ b/hw/intc/arm_gicv3_cpuif.c | 16 | +++ b/target/arm/translate-mve.c |
19 | @@ -XXX,XX +XXX,XX @@ static void icc_ctlr_el3_write(CPUARMState *env, const ARMCPRegInfo *ri, | 17 | @@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s) |
20 | trace_gicv3_icc_ctlr_el3_write(gicv3_redist_affid(cs), value); | ||
21 | |||
22 | /* *_EL1NS and *_EL1S bits are aliases into the ICC_CTLR_EL1 bits. */ | ||
23 | - cs->icc_ctlr_el1[GICV3_NS] &= (ICC_CTLR_EL1_CBPR | ICC_CTLR_EL1_EOIMODE); | ||
24 | + cs->icc_ctlr_el1[GICV3_NS] &= ~(ICC_CTLR_EL1_CBPR | ICC_CTLR_EL1_EOIMODE); | ||
25 | if (value & ICC_CTLR_EL3_EOIMODE_EL1NS) { | ||
26 | cs->icc_ctlr_el1[GICV3_NS] |= ICC_CTLR_EL1_EOIMODE; | ||
27 | } | 18 | } |
28 | @@ -XXX,XX +XXX,XX @@ static void icc_ctlr_el3_write(CPUARMState *env, const ARMCPRegInfo *ri, | 19 | } |
29 | cs->icc_ctlr_el1[GICV3_NS] |= ICC_CTLR_EL1_CBPR; | 20 | |
21 | -static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) | ||
22 | +static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn, | ||
23 | + unsigned msize) | ||
24 | { | ||
25 | TCGv_i32 addr; | ||
26 | uint32_t offset; | ||
27 | @@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) | ||
28 | return true; | ||
30 | } | 29 | } |
31 | 30 | ||
32 | - cs->icc_ctlr_el1[GICV3_S] &= (ICC_CTLR_EL1_CBPR | ICC_CTLR_EL1_EOIMODE); | 31 | - offset = a->imm << a->size; |
33 | + cs->icc_ctlr_el1[GICV3_S] &= ~(ICC_CTLR_EL1_CBPR | ICC_CTLR_EL1_EOIMODE); | 32 | + offset = a->imm << msize; |
34 | if (value & ICC_CTLR_EL3_EOIMODE_EL1S) { | 33 | if (!a->a) { |
35 | cs->icc_ctlr_el1[GICV3_S] |= ICC_CTLR_EL1_EOIMODE; | 34 | offset = -offset; |
36 | } | 35 | } |
36 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a) | ||
37 | { gen_helper_mve_vstrw, gen_helper_mve_vldrw }, | ||
38 | { NULL, NULL } | ||
39 | }; | ||
40 | - return do_ldst(s, a, ldstfns[a->size][a->l]); | ||
41 | + return do_ldst(s, a, ldstfns[a->size][a->l], a->size); | ||
42 | } | ||
43 | |||
44 | -#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \ | ||
45 | +#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \ | ||
46 | static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \ | ||
47 | { \ | ||
48 | static MVEGenLdStFn * const ldstfns[2][2] = { \ | ||
49 | { gen_helper_mve_##ST, gen_helper_mve_##SLD }, \ | ||
50 | { NULL, gen_helper_mve_##ULD }, \ | ||
51 | }; \ | ||
52 | - return do_ldst(s, a, ldstfns[a->u][a->l]); \ | ||
53 | + return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \ | ||
54 | } | ||
55 | |||
56 | -DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h) | ||
57 | -DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w) | ||
58 | -DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w) | ||
59 | +DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) | ||
60 | +DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) | ||
61 | +DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) | ||
62 | |||
63 | static bool trans_VDUP(DisasContext *s, arg_VDUP *a) | ||
64 | { | ||
37 | -- | 65 | -- |
38 | 2.20.1 | 66 | 2.20.1 |
39 | 67 | ||
40 | 68 | diff view generated by jsdifflib |
1 | From: Philippe Mathieu-Daudé <philmd@redhat.com> | 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 | ||
2 | 9 | ||
3 | It eases code review, unit is explicit. | 10 | In particular, fixing the second of these allows us to recast |
11 | the implementation to avoid 128-bit arithmetic entirely. | ||
4 | 12 | ||
5 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 13 | Since the element size here is always 4, we can also drop the |
6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | 14 | parameterization of ESIZE to make the code a little more readable. |
7 | Message-id: 20190520214342.13709-3-philmd@redhat.com | 15 | |
16 | Suggested-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@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 | ||
9 | --- | 20 | --- |
10 | hw/arm/exynos4_boards.c | 5 +++-- | 21 | target/arm/mve_helper.c | 38 +++++++++++++++++++++----------------- |
11 | 1 file changed, 3 insertions(+), 2 deletions(-) | 22 | 1 file changed, 21 insertions(+), 17 deletions(-) |
12 | 23 | ||
13 | diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c | 24 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
14 | index XXXXXXX..XXXXXXX 100644 | 25 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/hw/arm/exynos4_boards.c | 26 | --- a/target/arm/mve_helper.c |
16 | +++ b/hw/arm/exynos4_boards.c | 27 | +++ b/target/arm/mve_helper.c |
17 | @@ -XXX,XX +XXX,XX @@ | 28 | @@ -XXX,XX +XXX,XX @@ |
18 | */ | 29 | */ |
19 | 30 | ||
20 | #include "qemu/osdep.h" | 31 | #include "qemu/osdep.h" |
21 | +#include "qemu/units.h" | 32 | -#include "qemu/int128.h" |
22 | #include "qapi/error.h" | 33 | #include "cpu.h" |
23 | #include "qemu/error-report.h" | 34 | #include "internals.h" |
24 | #include "qemu-common.h" | 35 | #include "vec_internal.h" |
25 | @@ -XXX,XX +XXX,XX @@ static int exynos4_board_smp_bootreg_addr[EXYNOS4_NUM_OF_BOARDS] = { | 36 | @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) |
26 | }; | 37 | DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) |
27 | 38 | ||
28 | static unsigned long exynos4_board_ram_size[EXYNOS4_NUM_OF_BOARDS] = { | 39 | /* |
29 | - [EXYNOS4_BOARD_NURI] = 0x40000000, | 40 | - * Rounding multiply add long dual accumulate high: we must keep |
30 | - [EXYNOS4_BOARD_SMDKC210] = 0x40000000, | 41 | - * a 72-bit internal accumulator value and return the top 64 bits. |
31 | + [EXYNOS4_BOARD_NURI] = 1 * GiB, | 42 | + * Rounding multiply add long dual accumulate high. In the pseudocode |
32 | + [EXYNOS4_BOARD_SMDKC210] = 1 * GiB, | 43 | + * this is implemented with a 72-bit internal accumulator value of which |
33 | }; | 44 | + * the top 64 bits are returned. We optimize this to avoid having to |
34 | 45 | + * use 128-bit arithmetic -- we can do this because the 74-bit accumulator | |
35 | static struct arm_boot_info exynos4_board_binfo = { | 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) \ | ||
36 | -- | 98 | -- |
37 | 2.20.1 | 99 | 2.20.1 |
38 | 100 | ||
39 | 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 |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 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. | ||
2 | 5 | ||
3 | The mask implied by the extract is redundant with the one | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | implied by the deposit. Also, fix spelling of BFXIL. | 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(-) | ||
5 | 14 | ||
6 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 15 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
7 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 16 | index XXXXXXX..XXXXXXX 100644 |
8 | Message-id: 20190514011129.11330-3-richard.henderson@linaro.org | 17 | --- a/target/arm/translate.h |
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 18 | +++ b/target/arm/translate.h |
10 | --- | 19 | @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) |
11 | target/arm/translate-a64.c | 6 +++--- | 20 | * VMVN and VBIC (when cmode < 14 && op == 1). |
12 | 1 file changed, 3 insertions(+), 3 deletions(-) | 21 | * |
13 | 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; | ||
14 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 29 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c |
15 | index XXXXXXX..XXXXXXX 100644 | 30 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/target/arm/translate-a64.c | 31 | --- a/target/arm/translate-a64.c |
17 | +++ b/target/arm/translate-a64.c | 32 | +++ b/target/arm/translate-a64.c |
18 | @@ -XXX,XX +XXX,XX @@ static void disas_bitfield(DisasContext *s, uint32_t insn) | 33 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
19 | tcg_gen_extract_i64(tcg_rd, tcg_tmp, ri, len); | 34 | { |
20 | return; | 35 | int rd = extract32(insn, 0, 5); |
21 | } | 36 | int cmode = extract32(insn, 12, 4); |
22 | - /* opc == 1, BXFIL fall through to deposit */ | 37 | - int cmode_3_1 = extract32(cmode, 1, 3); |
23 | - tcg_gen_extract_i64(tcg_tmp, tcg_tmp, ri, len); | 38 | - int cmode_0 = extract32(cmode, 0, 1); |
24 | + /* opc == 1, BFXIL fall through to deposit */ | 39 | int o2 = extract32(insn, 11, 1); |
25 | + tcg_gen_shri_i64(tcg_tmp, tcg_tmp, ri); | 40 | uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5); |
26 | pos = 0; | 41 | bool is_neg = extract32(insn, 29, 1); |
27 | } else { | 42 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
28 | /* Handle the ri > si case with a deposit | 43 | return; |
29 | @@ -XXX,XX +XXX,XX @@ static void disas_bitfield(DisasContext *s, uint32_t insn) | ||
30 | len = ri; | ||
31 | } | 44 | } |
32 | 45 | ||
33 | - if (opc == 1) { /* BFM, BXFIL */ | 46 | - /* See AdvSIMDExpandImm() in ARM ARM */ |
34 | + if (opc == 1) { /* BFM, BFXIL */ | 47 | - switch (cmode_3_1) { |
35 | tcg_gen_deposit_i64(tcg_rd, tcg_rd, tcg_tmp, pos, len); | 48 | - case 0: /* Replicate(Zeros(24):imm8, 2) */ |
36 | } else { | 49 | - case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */ |
37 | /* SBFM or UBFM: We start with zero, and we haven't modified | 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; | ||
38 | -- | 168 | -- |
39 | 2.20.1 | 169 | 2.20.1 |
40 | 170 | ||
41 | 171 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | Use dup_const() instead of bitfield_replicate() in |
---|---|---|---|
2 | disas_simd_mod_imm(). | ||
2 | 3 | ||
3 | This is, after all, how we implement extract2 in tcg/aarch64. | 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.) | ||
4 | 7 | ||
5 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Message-id: 20190514011129.11330-2-richard.henderson@linaro.org | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 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 | ||
9 | --- | 11 | --- |
10 | target/arm/translate-a64.c | 38 ++++++++++++++++++++------------------ | 12 | target/arm/translate-a64.c | 2 +- |
11 | 1 file changed, 20 insertions(+), 18 deletions(-) | 13 | 1 file changed, 1 insertion(+), 1 deletion(-) |
12 | 14 | ||
13 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c |
14 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/target/arm/translate-a64.c | 17 | --- a/target/arm/translate-a64.c |
16 | +++ b/target/arm/translate-a64.c | 18 | +++ b/target/arm/translate-a64.c |
17 | @@ -XXX,XX +XXX,XX @@ static void disas_extract(DisasContext *s, uint32_t insn) | 19 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
18 | } else { | 20 | /* FMOV (vector, immediate) - half-precision */ |
19 | tcg_gen_ext32u_i64(tcg_rd, cpu_reg(s, rm)); | 21 | imm = vfp_expand_imm(MO_16, abcdefgh); |
20 | } | 22 | /* now duplicate across the lanes */ |
21 | - } else if (rm == rn) { /* ROR */ | 23 | - imm = bitfield_replicate(imm, 16); |
22 | - tcg_rm = cpu_reg(s, rm); | 24 | + imm = dup_const(MO_16, imm); |
23 | - if (sf) { | 25 | } else { |
24 | - tcg_gen_rotri_i64(tcg_rd, tcg_rm, imm); | 26 | imm = asimd_imm_const(abcdefgh, cmode, is_neg); |
25 | - } else { | ||
26 | - TCGv_i32 tmp = tcg_temp_new_i32(); | ||
27 | - tcg_gen_extrl_i64_i32(tmp, tcg_rm); | ||
28 | - tcg_gen_rotri_i32(tmp, tmp, imm); | ||
29 | - tcg_gen_extu_i32_i64(tcg_rd, tmp); | ||
30 | - tcg_temp_free_i32(tmp); | ||
31 | - } | ||
32 | } else { | ||
33 | - tcg_rm = read_cpu_reg(s, rm, sf); | ||
34 | - tcg_rn = read_cpu_reg(s, rn, sf); | ||
35 | - tcg_gen_shri_i64(tcg_rm, tcg_rm, imm); | ||
36 | - tcg_gen_shli_i64(tcg_rn, tcg_rn, bitsize - imm); | ||
37 | - tcg_gen_or_i64(tcg_rd, tcg_rm, tcg_rn); | ||
38 | - if (!sf) { | ||
39 | - tcg_gen_ext32u_i64(tcg_rd, tcg_rd); | ||
40 | + tcg_rm = cpu_reg(s, rm); | ||
41 | + tcg_rn = cpu_reg(s, rn); | ||
42 | + | ||
43 | + if (sf) { | ||
44 | + /* Specialization to ROR happens in EXTRACT2. */ | ||
45 | + tcg_gen_extract2_i64(tcg_rd, tcg_rm, tcg_rn, imm); | ||
46 | + } else { | ||
47 | + TCGv_i32 t0 = tcg_temp_new_i32(); | ||
48 | + | ||
49 | + tcg_gen_extrl_i64_i32(t0, tcg_rm); | ||
50 | + if (rm == rn) { | ||
51 | + tcg_gen_rotri_i32(t0, t0, imm); | ||
52 | + } else { | ||
53 | + TCGv_i32 t1 = tcg_temp_new_i32(); | ||
54 | + tcg_gen_extrl_i64_i32(t1, tcg_rn); | ||
55 | + tcg_gen_extract2_i32(t0, t0, t1, imm); | ||
56 | + tcg_temp_free_i32(t1); | ||
57 | + } | ||
58 | + tcg_gen_extu_i32_i64(tcg_rd, t0); | ||
59 | + tcg_temp_free_i32(t0); | ||
60 | } | ||
61 | } | ||
62 | } | 27 | } |
63 | -- | 28 | -- |
64 | 2.20.1 | 29 | 2.20.1 |
65 | 30 | ||
66 | 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 |
New patch | |||
---|---|---|---|
1 | 1 | Implement the MVE saturating shift-right-and-narrow insns | |
2 | VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. | ||
3 | |||
4 | do_srshr() is borrowed from sve_helper.c. | ||
5 | |||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Message-id: 20210628135835.6690-13-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/helper-mve.h | 30 +++++++++++ | ||
11 | target/arm/mve.decode | 28 ++++++++++ | ||
12 | target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++ | ||
13 | target/arm/translate-mve.c | 12 +++++ | ||
14 | 4 files changed, 174 insertions(+) | ||
15 | |||
16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/target/arm/helper-mve.h | ||
19 | +++ b/target/arm/helper-mve.h | ||
20 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
21 | DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
22 | DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
23 | DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
24 | + | ||
25 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
26 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
27 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
28 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
29 | + | ||
30 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
31 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
32 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
33 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
34 | + | ||
35 | +DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
36 | +DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
37 | +DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
38 | +DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
39 | + | ||
40 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
41 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
42 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
43 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
44 | + | ||
45 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
46 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
47 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
48 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
49 | + | ||
50 | +DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
51 | +DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
52 | +DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
53 | +DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
54 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/target/arm/mve.decode | ||
57 | +++ b/target/arm/mve.decode | ||
58 | @@ -XXX,XX +XXX,XX @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b | ||
59 | VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h | ||
60 | VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b | ||
61 | VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h | ||
62 | + | ||
63 | +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b | ||
64 | +VQSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h | ||
65 | +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b | ||
66 | +VQSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h | ||
67 | +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_b | ||
68 | +VQSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 0 @2_shr_h | ||
69 | +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_b | ||
70 | +VQSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 0 @2_shr_h | ||
71 | + | ||
72 | +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b | ||
73 | +VQSHRUNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h | ||
74 | +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b | ||
75 | +VQSHRUNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h | ||
76 | + | ||
77 | +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b | ||
78 | +VQRSHRNB_S 111 0 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h | ||
79 | +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b | ||
80 | +VQRSHRNT_S 111 0 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h | ||
81 | +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_b | ||
82 | +VQRSHRNB_U 111 1 1110 1 . ... ... ... 0 1111 0 1 . 0 ... 1 @2_shr_h | ||
83 | +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_b | ||
84 | +VQRSHRNT_U 111 1 1110 1 . ... ... ... 1 1111 0 1 . 0 ... 1 @2_shr_h | ||
85 | + | ||
86 | +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b | ||
87 | +VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h | ||
88 | +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b | ||
89 | +VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h | ||
90 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
91 | index XXXXXXX..XXXXXXX 100644 | ||
92 | --- a/target/arm/mve_helper.c | ||
93 | +++ b/target/arm/mve_helper.c | ||
94 | @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_urshr(uint64_t x, unsigned sh) | ||
95 | } | ||
96 | } | ||
97 | |||
98 | +static inline int64_t do_srshr(int64_t x, unsigned sh) | ||
99 | +{ | ||
100 | + if (likely(sh < 64)) { | ||
101 | + return (x >> sh) + ((x >> (sh - 1)) & 1); | ||
102 | + } else { | ||
103 | + /* Rounding the sign bit always produces 0. */ | ||
104 | + return 0; | ||
105 | + } | ||
106 | +} | ||
107 | + | ||
108 | DO_VSHRN_ALL(vshrn, DO_SHR) | ||
109 | DO_VSHRN_ALL(vrshrn, do_urshr) | ||
110 | + | ||
111 | +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, | ||
112 | + bool *satp) | ||
113 | +{ | ||
114 | + if (val > max) { | ||
115 | + *satp = true; | ||
116 | + return max; | ||
117 | + } else if (val < min) { | ||
118 | + *satp = true; | ||
119 | + return min; | ||
120 | + } else { | ||
121 | + return val; | ||
122 | + } | ||
123 | +} | ||
124 | + | ||
125 | +/* Saturating narrowing right shifts */ | ||
126 | +#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ | ||
127 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
128 | + void *vm, uint32_t shift) \ | ||
129 | + { \ | ||
130 | + LTYPE *m = vm; \ | ||
131 | + TYPE *d = vd; \ | ||
132 | + uint16_t mask = mve_element_mask(env); \ | ||
133 | + bool qc = false; \ | ||
134 | + unsigned le; \ | ||
135 | + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ | ||
136 | + bool sat = false; \ | ||
137 | + TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ | ||
138 | + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ | ||
139 | + qc |= sat && (mask & 1 << (TOP * ESIZE)); \ | ||
140 | + } \ | ||
141 | + if (qc) { \ | ||
142 | + env->vfp.qc[0] = qc; \ | ||
143 | + } \ | ||
144 | + mve_advance_vpt(env); \ | ||
145 | + } | ||
146 | + | ||
147 | +#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \ | ||
148 | + DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ | ||
149 | + DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) | ||
150 | + | ||
151 | +#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \ | ||
152 | + DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ | ||
153 | + DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) | ||
154 | + | ||
155 | +#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \ | ||
156 | + DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ | ||
157 | + DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) | ||
158 | + | ||
159 | +#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \ | ||
160 | + DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ | ||
161 | + DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) | ||
162 | + | ||
163 | +#define DO_SHRN_SB(N, M, SATP) \ | ||
164 | + do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP) | ||
165 | +#define DO_SHRN_UB(N, M, SATP) \ | ||
166 | + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT8_MAX, SATP) | ||
167 | +#define DO_SHRUN_B(N, M, SATP) \ | ||
168 | + do_sat_bhs((int64_t)(N) >> (M), 0, UINT8_MAX, SATP) | ||
169 | + | ||
170 | +#define DO_SHRN_SH(N, M, SATP) \ | ||
171 | + do_sat_bhs((int64_t)(N) >> (M), INT16_MIN, INT16_MAX, SATP) | ||
172 | +#define DO_SHRN_UH(N, M, SATP) \ | ||
173 | + do_sat_bhs((uint64_t)(N) >> (M), 0, UINT16_MAX, SATP) | ||
174 | +#define DO_SHRUN_H(N, M, SATP) \ | ||
175 | + do_sat_bhs((int64_t)(N) >> (M), 0, UINT16_MAX, SATP) | ||
176 | + | ||
177 | +#define DO_RSHRN_SB(N, M, SATP) \ | ||
178 | + do_sat_bhs(do_srshr(N, M), INT8_MIN, INT8_MAX, SATP) | ||
179 | +#define DO_RSHRN_UB(N, M, SATP) \ | ||
180 | + do_sat_bhs(do_urshr(N, M), 0, UINT8_MAX, SATP) | ||
181 | +#define DO_RSHRUN_B(N, M, SATP) \ | ||
182 | + do_sat_bhs(do_srshr(N, M), 0, UINT8_MAX, SATP) | ||
183 | + | ||
184 | +#define DO_RSHRN_SH(N, M, SATP) \ | ||
185 | + do_sat_bhs(do_srshr(N, M), INT16_MIN, INT16_MAX, SATP) | ||
186 | +#define DO_RSHRN_UH(N, M, SATP) \ | ||
187 | + do_sat_bhs(do_urshr(N, M), 0, UINT16_MAX, SATP) | ||
188 | +#define DO_RSHRUN_H(N, M, SATP) \ | ||
189 | + do_sat_bhs(do_srshr(N, M), 0, UINT16_MAX, SATP) | ||
190 | + | ||
191 | +DO_VSHRN_SAT_SB(vqshrnb_sb, vqshrnt_sb, DO_SHRN_SB) | ||
192 | +DO_VSHRN_SAT_SH(vqshrnb_sh, vqshrnt_sh, DO_SHRN_SH) | ||
193 | +DO_VSHRN_SAT_UB(vqshrnb_ub, vqshrnt_ub, DO_SHRN_UB) | ||
194 | +DO_VSHRN_SAT_UH(vqshrnb_uh, vqshrnt_uh, DO_SHRN_UH) | ||
195 | +DO_VSHRN_SAT_SB(vqshrunbb, vqshruntb, DO_SHRUN_B) | ||
196 | +DO_VSHRN_SAT_SH(vqshrunbh, vqshrunth, DO_SHRUN_H) | ||
197 | + | ||
198 | +DO_VSHRN_SAT_SB(vqrshrnb_sb, vqrshrnt_sb, DO_RSHRN_SB) | ||
199 | +DO_VSHRN_SAT_SH(vqrshrnb_sh, vqrshrnt_sh, DO_RSHRN_SH) | ||
200 | +DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) | ||
201 | +DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) | ||
202 | +DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) | ||
203 | +DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) | ||
204 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c | ||
205 | index XXXXXXX..XXXXXXX 100644 | ||
206 | --- a/target/arm/translate-mve.c | ||
207 | +++ b/target/arm/translate-mve.c | ||
208 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VSHRNB, vshrnb) | ||
209 | DO_2SHIFT_N(VSHRNT, vshrnt) | ||
210 | DO_2SHIFT_N(VRSHRNB, vrshrnb) | ||
211 | DO_2SHIFT_N(VRSHRNT, vrshrnt) | ||
212 | +DO_2SHIFT_N(VQSHRNB_S, vqshrnb_s) | ||
213 | +DO_2SHIFT_N(VQSHRNT_S, vqshrnt_s) | ||
214 | +DO_2SHIFT_N(VQSHRNB_U, vqshrnb_u) | ||
215 | +DO_2SHIFT_N(VQSHRNT_U, vqshrnt_u) | ||
216 | +DO_2SHIFT_N(VQSHRUNB, vqshrunb) | ||
217 | +DO_2SHIFT_N(VQSHRUNT, vqshrunt) | ||
218 | +DO_2SHIFT_N(VQRSHRNB_S, vqrshrnb_s) | ||
219 | +DO_2SHIFT_N(VQRSHRNT_S, vqrshrnt_s) | ||
220 | +DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) | ||
221 | +DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) | ||
222 | +DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) | ||
223 | +DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) | ||
224 | -- | ||
225 | 2.20.1 | ||
226 | |||
227 | diff view generated by jsdifflib |
1 | In ich_vmcr_write() we enforce "writes of BPR fields to less than | 1 | Implement the MVE VSHLC insn, which performs a shift left of the |
---|---|---|---|
2 | their minimum sets them to the minimum" by doing a "read vbpr and | 2 | entire vector with carry in bits provided from a general purpose |
3 | write it back" operation. A typo here meant that we weren't handling | 3 | register and carry out bits written back to that register. |
4 | writes to these fields correctly, because we were reading from VBPR0 | ||
5 | but writing to VBPR1. | ||
6 | 4 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
9 | Message-id: 20190520162809.2677-4-peter.maydell@linaro.org | 7 | Message-id: 20210628135835.6690-14-peter.maydell@linaro.org |
10 | --- | 8 | --- |
11 | hw/intc/arm_gicv3_cpuif.c | 2 +- | 9 | target/arm/helper-mve.h | 2 ++ |
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | 10 | target/arm/mve.decode | 2 ++ |
11 | target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++ | ||
12 | target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++ | ||
13 | 4 files changed, 72 insertions(+) | ||
13 | 14 | ||
14 | diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
15 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/hw/intc/arm_gicv3_cpuif.c | 17 | --- a/target/arm/helper-mve.h |
17 | +++ b/hw/intc/arm_gicv3_cpuif.c | 18 | +++ b/target/arm/helper-mve.h |
18 | @@ -XXX,XX +XXX,XX @@ static void ich_vmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
19 | /* Enforce "writing BPRs to less than minimum sets them to the minimum" | 20 | DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
20 | * by reading and writing back the fields. | 21 | DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
21 | */ | 22 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
22 | - write_vbpr(cs, GICV3_G1, read_vbpr(cs, GICV3_G0)); | 23 | + |
23 | + write_vbpr(cs, GICV3_G0, read_vbpr(cs, GICV3_G0)); | 24 | +DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) |
24 | write_vbpr(cs, GICV3_G1, read_vbpr(cs, GICV3_G1)); | 25 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
25 | 26 | index XXXXXXX..XXXXXXX 100644 | |
26 | gicv3_cpuif_virt_update(cs); | 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 | +} | ||
27 | -- | 119 | -- |
28 | 2.20.1 | 120 | 2.20.1 |
29 | 121 | ||
30 | 122 | diff view generated by jsdifflib |
1 | From: Guenter Roeck <linux@roeck-us.net> | 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 | QEMU already supports pl330. Instantiate it for Exynos4210. | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Message-id: 20210628135835.6690-15-peter.maydell@linaro.org | ||
8 | --- | ||
9 | target/arm/helper-mve.h | 3 ++ | ||
10 | target/arm/mve.decode | 6 +++- | ||
11 | target/arm/mve_helper.c | 19 ++++++++++++ | ||
12 | target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++ | ||
13 | 4 files changed, 90 insertions(+), 1 deletion(-) | ||
4 | 14 | ||
5 | Relevant part of Linux arch/arm/boot/dts/exynos4.dtsi: | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
6 | |||
7 | / { | ||
8 | soc: soc { | ||
9 | amba { | ||
10 | pdma0: pdma@12680000 { | ||
11 | compatible = "arm,pl330", "arm,primecell"; | ||
12 | reg = <0x12680000 0x1000>; | ||
13 | interrupts = <GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>; | ||
14 | clocks = <&clock CLK_PDMA0>; | ||
15 | clock-names = "apb_pclk"; | ||
16 | #dma-cells = <1>; | ||
17 | #dma-channels = <8>; | ||
18 | #dma-requests = <32>; | ||
19 | }; | ||
20 | pdma1: pdma@12690000 { | ||
21 | compatible = "arm,pl330", "arm,primecell"; | ||
22 | reg = <0x12690000 0x1000>; | ||
23 | interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>; | ||
24 | clocks = <&clock CLK_PDMA1>; | ||
25 | clock-names = "apb_pclk"; | ||
26 | #dma-cells = <1>; | ||
27 | #dma-channels = <8>; | ||
28 | #dma-requests = <32>; | ||
29 | }; | ||
30 | mdma1: mdma@12850000 { | ||
31 | compatible = "arm,pl330", "arm,primecell"; | ||
32 | reg = <0x12850000 0x1000>; | ||
33 | interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>; | ||
34 | clocks = <&clock CLK_MDMA>; | ||
35 | clock-names = "apb_pclk"; | ||
36 | #dma-cells = <1>; | ||
37 | #dma-channels = <8>; | ||
38 | #dma-requests = <1>; | ||
39 | }; | ||
40 | }; | ||
41 | }; | ||
42 | }; | ||
43 | |||
44 | Signed-off-by: Guenter Roeck <linux@roeck-us.net> | ||
45 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
46 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
47 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
48 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
49 | Message-id: 20190520214342.13709-4-philmd@redhat.com | ||
50 | [PMD: Do not set default qdev properties, create the controllers in the SoC | ||
51 | rather than the board (Peter Maydell), add dtsi in commit message] | ||
52 | Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
53 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
54 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
55 | --- | ||
56 | hw/arm/exynos4210.c | 26 ++++++++++++++++++++++++++ | ||
57 | 1 file changed, 26 insertions(+) | ||
58 | |||
59 | diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c | ||
60 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
61 | --- a/hw/arm/exynos4210.c | 17 | --- a/target/arm/helper-mve.h |
62 | +++ b/hw/arm/exynos4210.c | 18 | +++ b/target/arm/helper-mve.h |
63 | @@ -XXX,XX +XXX,XX @@ | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) |
64 | /* EHCI */ | 20 | DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
65 | #define EXYNOS4210_EHCI_BASE_ADDR 0x12580000 | 21 | DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
66 | 22 | ||
67 | +/* DMA */ | 23 | +DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) |
68 | +#define EXYNOS4210_PL330_BASE0_ADDR 0x12680000 | 24 | +DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) |
69 | +#define EXYNOS4210_PL330_BASE1_ADDR 0x12690000 | ||
70 | +#define EXYNOS4210_PL330_BASE2_ADDR 0x12850000 | ||
71 | + | 25 | + |
72 | static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, | 26 | DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) |
73 | 0x09, 0x00, 0x00, 0x00 }; | 27 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) |
74 | 28 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) | |
75 | @@ -XXX,XX +XXX,XX @@ static uint64_t exynos4210_calc_affinity(int cpu) | 29 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
76 | return (0x9 << ARM_AFF1_SHIFT) | cpu; | 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; | ||
77 | } | 82 | } |
78 | 83 | ||
79 | +static void pl330_create(uint32_t base, qemu_irq irq, int nreq) | 84 | +static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a) |
80 | +{ | 85 | +{ |
81 | + SysBusDevice *busdev; | 86 | + /* |
82 | + DeviceState *dev; | 87 | + * Vector Add Long Across Vector: accumulate the 32-bit |
88 | + * elements of the vector into a 64-bit result stored in | ||
89 | + * a pair of general-purpose registers. | ||
90 | + * No need to check Qm's bank: it is only 3 bits in decode. | ||
91 | + */ | ||
92 | + TCGv_ptr qm; | ||
93 | + TCGv_i64 rda; | ||
94 | + TCGv_i32 rdalo, rdahi; | ||
83 | + | 95 | + |
84 | + dev = qdev_create(NULL, "pl330"); | 96 | + if (!dc_isar_feature(aa32_mve, s)) { |
85 | + qdev_prop_set_uint8(dev, "num_periph_req", nreq); | 97 | + return false; |
86 | + qdev_init_nofail(dev); | 98 | + } |
87 | + busdev = SYS_BUS_DEVICE(dev); | 99 | + /* |
88 | + sysbus_mmio_map(busdev, 0, base); | 100 | + * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related |
89 | + sysbus_connect_irq(busdev, 0, irq); | 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; | ||
90 | +} | 145 | +} |
91 | + | 146 | + |
92 | Exynos4210State *exynos4210_init(MemoryRegion *system_mem) | 147 | static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) |
93 | { | 148 | { |
94 | Exynos4210State *s = g_new0(Exynos4210State, 1); | 149 | TCGv_ptr qd; |
95 | @@ -XXX,XX +XXX,XX @@ Exynos4210State *exynos4210_init(MemoryRegion *system_mem) | ||
96 | sysbus_create_simple(TYPE_EXYNOS4210_EHCI, EXYNOS4210_EHCI_BASE_ADDR, | ||
97 | s->irq_table[exynos4210_get_irq(28, 3)]); | ||
98 | |||
99 | + /*** DMA controllers ***/ | ||
100 | + pl330_create(EXYNOS4210_PL330_BASE0_ADDR, | ||
101 | + qemu_irq_invert(s->irq_table[exynos4210_get_irq(35, 1)]), 32); | ||
102 | + pl330_create(EXYNOS4210_PL330_BASE1_ADDR, | ||
103 | + qemu_irq_invert(s->irq_table[exynos4210_get_irq(36, 1)]), 32); | ||
104 | + pl330_create(EXYNOS4210_PL330_BASE2_ADDR, | ||
105 | + qemu_irq_invert(s->irq_table[exynos4210_get_irq(34, 1)]), 1); | ||
106 | + | ||
107 | return s; | ||
108 | } | ||
109 | -- | 150 | -- |
110 | 2.20.1 | 151 | 2.20.1 |
111 | 152 | ||
112 | 153 | diff view generated by jsdifflib |
1 | The system_clock_scale global is used only by the armv7m systick | 1 | The MVE extension to v8.1M includes some new shift instructions which |
---|---|---|---|
2 | device; move the extern declaration to the armv7m_systick.h header, | 2 | sit entirely within the non-coprocessor part of the encoding space |
3 | and expand the comment to explain what it is and that it should | 3 | and which operate only on general-purpose registers. They take up |
4 | ideally be replaced with a different approach. | 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. | ||
5 | 23 | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
7 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 25 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 26 | Message-id: 20210628135835.6690-16-peter.maydell@linaro.org |
9 | Message-id: 20190516163857.6430-2-peter.maydell@linaro.org | ||
10 | --- | 27 | --- |
11 | include/hw/arm/arm.h | 4 ---- | 28 | target/arm/helper-mve.h | 3 ++ |
12 | include/hw/timer/armv7m_systick.h | 22 ++++++++++++++++++++++ | 29 | target/arm/translate.h | 1 + |
13 | 2 files changed, 22 insertions(+), 4 deletions(-) | 30 | target/arm/t32.decode | 28 +++++++++++++ |
14 | 31 | target/arm/mve_helper.c | 10 +++++ | |
15 | diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h | 32 | target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++ |
16 | index XXXXXXX..XXXXXXX 100644 | 33 | 5 files changed, 132 insertions(+) |
17 | --- a/include/hw/arm/arm.h | 34 | |
18 | +++ b/include/hw/arm/arm.h | 35 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
19 | @@ -XXX,XX +XXX,XX @@ void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu, | 36 | index XXXXXXX..XXXXXXX 100644 |
20 | const struct arm_boot_info *info, | 37 | --- a/target/arm/helper-mve.h |
21 | hwaddr mvbar_addr); | 38 | +++ b/target/arm/helper-mve.h |
22 | 39 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
23 | -/* Multiplication factor to convert from system clock ticks to qemu timer | 40 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
24 | - ticks. */ | 41 | |
25 | -extern int system_clock_scale; | 42 | DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) |
26 | - | 43 | + |
27 | #endif /* HW_ARM_H */ | 44 | +DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
28 | diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h | 45 | +DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
29 | index XXXXXXX..XXXXXXX 100644 | 46 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
30 | --- a/include/hw/timer/armv7m_systick.h | 47 | index XXXXXXX..XXXXXXX 100644 |
31 | +++ b/include/hw/timer/armv7m_systick.h | 48 | --- a/target/arm/translate.h |
32 | @@ -XXX,XX +XXX,XX @@ typedef struct SysTickState { | 49 | +++ b/target/arm/translate.h |
33 | qemu_irq irq; | 50 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); |
34 | } SysTickState; | 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 | } | ||
35 | 135 | ||
36 | +/* | 136 | +/* |
37 | + * Multiplication factor to convert from system clock ticks to qemu timer | 137 | + * v8.1M MVE wide-shifts |
38 | + * ticks. This should be set (by board code, usually) to a value | ||
39 | + * equal to NANOSECONDS_PER_SECOND / frq, where frq is the clock frequency | ||
40 | + * in Hz of the CPU. | ||
41 | + * | ||
42 | + * This value is used by the systick device when it is running in | ||
43 | + * its "use the CPU clock" mode (ie when SYST_CSR.CLKSOURCE == 1) to | ||
44 | + * set how fast the timer should tick. | ||
45 | + * | ||
46 | + * TODO: we should refactor this so that rather than using a global | ||
47 | + * we use a device property or something similar. This is complicated | ||
48 | + * because (a) the property would need to be plumbed through from the | ||
49 | + * board code down through various layers to the systick device | ||
50 | + * and (b) the property needs to be modifiable after realize, because | ||
51 | + * the stellaris board uses this to implement the behaviour where the | ||
52 | + * guest can reprogram the PLL registers to downclock the CPU, and the | ||
53 | + * systick device needs to react accordingly. Possibly this should | ||
54 | + * be deferred until we have a good API for modelling clock trees. | ||
55 | + */ | 138 | + */ |
56 | +extern int system_clock_scale; | 139 | +static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a, |
57 | + | 140 | + WideShiftImmFn *fn) |
58 | #endif | 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 | */ | ||
59 | -- | 229 | -- |
60 | 2.20.1 | 230 | 2.20.1 |
61 | 231 | ||
62 | 232 | diff view generated by jsdifflib |
1 | The header file hw/arm/arm.h now includes only declarations | 1 | Implement the MVE long shifts by register, which perform shifts on a |
---|---|---|---|
2 | relating to hw/arm/boot.c functionality. Rename it accordingly, | 2 | pair of general-purpose registers treated as a 64-bit quantity, with |
3 | and adjust its header comment. | 3 | the shift count in another general-purpose register, which might be |
4 | 4 | either positive or negative. | |
5 | The bulk of this commit was created via | 5 | |
6 | perl -pi -e 's|hw/arm/arm.h|hw/arm/boot.h|' hw/arm/*.c include/hw/arm/*.h | 6 | Like the long-shifts-by-immediate, these encodings sit in the space |
7 | 7 | that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15. | |
8 | In a few cases we can just delete the #include: | 8 | Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and |
9 | hw/arm/msf2-soc.c, include/hw/arm/aspeed_soc.h and | 9 | also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases), |
10 | include/hw/arm/bcm2836.h did not require it. | 10 | we have to move the CSEL pattern into the same decodetree group. |
11 | 11 | ||
12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
13 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
14 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 14 | Message-id: 20210628135835.6690-17-peter.maydell@linaro.org |
15 | Message-id: 20190516163857.6430-4-peter.maydell@linaro.org | ||
16 | --- | 15 | --- |
17 | include/hw/arm/allwinner-a10.h | 2 +- | 16 | target/arm/helper-mve.h | 6 +++ |
18 | include/hw/arm/aspeed_soc.h | 1 - | 17 | target/arm/translate.h | 1 + |
19 | include/hw/arm/bcm2836.h | 1 - | 18 | target/arm/t32.decode | 16 +++++-- |
20 | include/hw/arm/{arm.h => boot.h} | 8 ++++---- | 19 | target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++ |
21 | include/hw/arm/fsl-imx25.h | 2 +- | 20 | target/arm/translate.c | 69 ++++++++++++++++++++++++++++++ |
22 | include/hw/arm/fsl-imx31.h | 2 +- | 21 | 5 files changed, 182 insertions(+), 3 deletions(-) |
23 | include/hw/arm/fsl-imx6.h | 2 +- | 22 | |
24 | include/hw/arm/fsl-imx6ul.h | 2 +- | 23 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
25 | include/hw/arm/fsl-imx7.h | 2 +- | 24 | index XXXXXXX..XXXXXXX 100644 |
26 | include/hw/arm/virt.h | 2 +- | 25 | --- a/target/arm/helper-mve.h |
27 | include/hw/arm/xlnx-versal.h | 2 +- | 26 | +++ b/target/arm/helper-mve.h |
28 | include/hw/arm/xlnx-zynqmp.h | 2 +- | 27 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
29 | hw/arm/armsse.c | 2 +- | 28 | |
30 | hw/arm/armv7m.c | 2 +- | 29 | DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) |
31 | hw/arm/aspeed.c | 2 +- | 30 | |
32 | hw/arm/boot.c | 2 +- | 31 | +DEF_HELPER_FLAGS_3(mve_sshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) |
33 | hw/arm/collie.c | 2 +- | 32 | +DEF_HELPER_FLAGS_3(mve_ushll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
34 | hw/arm/exynos4210.c | 2 +- | 33 | DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
35 | hw/arm/exynos4_boards.c | 2 +- | 34 | DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
36 | hw/arm/highbank.c | 2 +- | 35 | +DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) |
37 | hw/arm/integratorcp.c | 2 +- | 36 | +DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) |
38 | hw/arm/mainstone.c | 2 +- | 37 | +DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
39 | hw/arm/microbit.c | 2 +- | 38 | +DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
40 | hw/arm/mps2-tz.c | 2 +- | 39 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
41 | hw/arm/mps2.c | 2 +- | 40 | index XXXXXXX..XXXXXXX 100644 |
42 | hw/arm/msf2-soc.c | 1 - | 41 | --- a/target/arm/translate.h |
43 | hw/arm/msf2-som.c | 2 +- | 42 | +++ b/target/arm/translate.h |
44 | hw/arm/musca.c | 2 +- | 43 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); |
45 | hw/arm/musicpal.c | 2 +- | 44 | typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); |
46 | hw/arm/netduino2.c | 2 +- | 45 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); |
47 | hw/arm/nrf51_soc.c | 2 +- | 46 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); |
48 | hw/arm/nseries.c | 2 +- | 47 | +typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); |
49 | hw/arm/omap1.c | 2 +- | 48 | |
50 | hw/arm/omap2.c | 2 +- | 49 | /** |
51 | hw/arm/omap_sx1.c | 2 +- | 50 | * arm_tbflags_from_tb: |
52 | hw/arm/palm.c | 2 +- | 51 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode |
53 | hw/arm/raspi.c | 2 +- | 52 | index XXXXXXX..XXXXXXX 100644 |
54 | hw/arm/realview.c | 2 +- | 53 | --- a/target/arm/t32.decode |
55 | hw/arm/spitz.c | 2 +- | 54 | +++ b/target/arm/t32.decode |
56 | hw/arm/stellaris.c | 2 +- | ||
57 | hw/arm/stm32f205_soc.c | 2 +- | ||
58 | hw/arm/strongarm.c | 2 +- | ||
59 | hw/arm/tosa.c | 2 +- | ||
60 | hw/arm/versatilepb.c | 2 +- | ||
61 | hw/arm/vexpress.c | 2 +- | ||
62 | hw/arm/virt.c | 2 +- | ||
63 | hw/arm/xilinx_zynq.c | 2 +- | ||
64 | hw/arm/xlnx-versal.c | 2 +- | ||
65 | hw/arm/z2.c | 2 +- | ||
66 | 49 files changed, 49 insertions(+), 52 deletions(-) | ||
67 | rename include/hw/arm/{arm.h => boot.h} (98%) | ||
68 | |||
69 | diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h | ||
70 | index XXXXXXX..XXXXXXX 100644 | ||
71 | --- a/include/hw/arm/allwinner-a10.h | ||
72 | +++ b/include/hw/arm/allwinner-a10.h | ||
73 | @@ -XXX,XX +XXX,XX @@ | 55 | @@ -XXX,XX +XXX,XX @@ |
74 | #include "qemu-common.h" | 56 | &mcrr !extern cp opc1 crm rt rt2 |
75 | #include "qemu/error-report.h" | 57 | |
76 | #include "hw/char/serial.h" | 58 | &mve_shl_ri rdalo rdahi shim |
77 | -#include "hw/arm/arm.h" | 59 | +&mve_shl_rr rdalo rdahi rm |
78 | +#include "hw/arm/boot.h" | 60 | |
79 | #include "hw/timer/allwinner-a10-pit.h" | 61 | # rdahi: bits [3:1] from insn, bit 0 is 1 |
80 | #include "hw/intc/allwinner-a10-pic.h" | 62 | # rdalo: bits [3:1] from insn, bit 0 is 0 |
81 | #include "hw/net/allwinner_emac.h" | ||
82 | diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h | ||
83 | index XXXXXXX..XXXXXXX 100644 | ||
84 | --- a/include/hw/arm/aspeed_soc.h | ||
85 | +++ b/include/hw/arm/aspeed_soc.h | ||
86 | @@ -XXX,XX +XXX,XX @@ | 63 | @@ -XXX,XX +XXX,XX @@ |
87 | #ifndef ASPEED_SOC_H | 64 | |
88 | #define ASPEED_SOC_H | 65 | @mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ |
89 | 66 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 | |
90 | -#include "hw/arm/arm.h" | 67 | +@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ |
91 | #include "hw/intc/aspeed_vic.h" | 68 | + &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 |
92 | #include "hw/misc/aspeed_scu.h" | 69 | |
93 | #include "hw/misc/aspeed_sdmc.h" | 70 | { |
94 | diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h | 71 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi |
95 | index XXXXXXX..XXXXXXX 100644 | 72 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi |
96 | --- a/include/hw/arm/bcm2836.h | 73 | URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
97 | +++ b/include/hw/arm/bcm2836.h | 74 | SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
98 | @@ -XXX,XX +XXX,XX @@ | 75 | SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
99 | #ifndef BCM2836_H | 76 | + |
100 | #define BCM2836_H | 77 | + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr |
101 | 78 | + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | |
102 | -#include "hw/arm/arm.h" | 79 | + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr |
103 | #include "hw/arm/bcm2835_peripherals.h" | 80 | + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr |
104 | #include "hw/intc/bcm2836_control.h" | 81 | + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr |
105 | 82 | + SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr | |
106 | diff --git a/include/hw/arm/arm.h b/include/hw/arm/boot.h | 83 | ] |
107 | similarity index 98% | 84 | |
108 | rename from include/hw/arm/arm.h | 85 | MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi |
109 | rename to include/hw/arm/boot.h | 86 | ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi |
110 | index XXXXXXX..XXXXXXX 100644 | 87 | + |
111 | --- a/include/hw/arm/arm.h | 88 | + # v8.1M CSEL and friends |
112 | +++ b/include/hw/arm/boot.h | 89 | + CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 |
113 | @@ -XXX,XX +XXX,XX @@ | 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 | + | ||
114 | /* | 288 | /* |
115 | - * Misc ARM declarations | 289 | * Multiply and multiply accumulate |
116 | + * ARM kernel loader. | ||
117 | * | ||
118 | * Copyright (c) 2006 CodeSourcery. | ||
119 | * Written by Paul Brook | ||
120 | @@ -XXX,XX +XXX,XX @@ | ||
121 | * | ||
122 | */ | 290 | */ |
123 | |||
124 | -#ifndef HW_ARM_H | ||
125 | -#define HW_ARM_H | ||
126 | +#ifndef HW_ARM_BOOT_H | ||
127 | +#define HW_ARM_BOOT_H | ||
128 | |||
129 | #include "exec/memory.h" | ||
130 | #include "target/arm/cpu-qom.h" | ||
131 | @@ -XXX,XX +XXX,XX @@ void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu, | ||
132 | const struct arm_boot_info *info, | ||
133 | hwaddr mvbar_addr); | ||
134 | |||
135 | -#endif /* HW_ARM_H */ | ||
136 | +#endif /* HW_ARM_BOOT_H */ | ||
137 | diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h | ||
138 | index XXXXXXX..XXXXXXX 100644 | ||
139 | --- a/include/hw/arm/fsl-imx25.h | ||
140 | +++ b/include/hw/arm/fsl-imx25.h | ||
141 | @@ -XXX,XX +XXX,XX @@ | ||
142 | #ifndef FSL_IMX25_H | ||
143 | #define FSL_IMX25_H | ||
144 | |||
145 | -#include "hw/arm/arm.h" | ||
146 | +#include "hw/arm/boot.h" | ||
147 | #include "hw/intc/imx_avic.h" | ||
148 | #include "hw/misc/imx25_ccm.h" | ||
149 | #include "hw/char/imx_serial.h" | ||
150 | diff --git a/include/hw/arm/fsl-imx31.h b/include/hw/arm/fsl-imx31.h | ||
151 | index XXXXXXX..XXXXXXX 100644 | ||
152 | --- a/include/hw/arm/fsl-imx31.h | ||
153 | +++ b/include/hw/arm/fsl-imx31.h | ||
154 | @@ -XXX,XX +XXX,XX @@ | ||
155 | #ifndef FSL_IMX31_H | ||
156 | #define FSL_IMX31_H | ||
157 | |||
158 | -#include "hw/arm/arm.h" | ||
159 | +#include "hw/arm/boot.h" | ||
160 | #include "hw/intc/imx_avic.h" | ||
161 | #include "hw/misc/imx31_ccm.h" | ||
162 | #include "hw/char/imx_serial.h" | ||
163 | diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h | ||
164 | index XXXXXXX..XXXXXXX 100644 | ||
165 | --- a/include/hw/arm/fsl-imx6.h | ||
166 | +++ b/include/hw/arm/fsl-imx6.h | ||
167 | @@ -XXX,XX +XXX,XX @@ | ||
168 | #ifndef FSL_IMX6_H | ||
169 | #define FSL_IMX6_H | ||
170 | |||
171 | -#include "hw/arm/arm.h" | ||
172 | +#include "hw/arm/boot.h" | ||
173 | #include "hw/cpu/a9mpcore.h" | ||
174 | #include "hw/misc/imx6_ccm.h" | ||
175 | #include "hw/misc/imx6_src.h" | ||
176 | diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h | ||
177 | index XXXXXXX..XXXXXXX 100644 | ||
178 | --- a/include/hw/arm/fsl-imx6ul.h | ||
179 | +++ b/include/hw/arm/fsl-imx6ul.h | ||
180 | @@ -XXX,XX +XXX,XX @@ | ||
181 | #ifndef FSL_IMX6UL_H | ||
182 | #define FSL_IMX6UL_H | ||
183 | |||
184 | -#include "hw/arm/arm.h" | ||
185 | +#include "hw/arm/boot.h" | ||
186 | #include "hw/cpu/a15mpcore.h" | ||
187 | #include "hw/misc/imx6ul_ccm.h" | ||
188 | #include "hw/misc/imx6_src.h" | ||
189 | diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h | ||
190 | index XXXXXXX..XXXXXXX 100644 | ||
191 | --- a/include/hw/arm/fsl-imx7.h | ||
192 | +++ b/include/hw/arm/fsl-imx7.h | ||
193 | @@ -XXX,XX +XXX,XX @@ | ||
194 | #ifndef FSL_IMX7_H | ||
195 | #define FSL_IMX7_H | ||
196 | |||
197 | -#include "hw/arm/arm.h" | ||
198 | +#include "hw/arm/boot.h" | ||
199 | #include "hw/cpu/a15mpcore.h" | ||
200 | #include "hw/intc/imx_gpcv2.h" | ||
201 | #include "hw/misc/imx7_ccm.h" | ||
202 | diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h | ||
203 | index XXXXXXX..XXXXXXX 100644 | ||
204 | --- a/include/hw/arm/virt.h | ||
205 | +++ b/include/hw/arm/virt.h | ||
206 | @@ -XXX,XX +XXX,XX @@ | ||
207 | #include "exec/hwaddr.h" | ||
208 | #include "qemu/notify.h" | ||
209 | #include "hw/boards.h" | ||
210 | -#include "hw/arm/arm.h" | ||
211 | +#include "hw/arm/boot.h" | ||
212 | #include "hw/block/flash.h" | ||
213 | #include "sysemu/kvm.h" | ||
214 | #include "hw/intc/arm_gicv3_common.h" | ||
215 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h | ||
216 | index XXXXXXX..XXXXXXX 100644 | ||
217 | --- a/include/hw/arm/xlnx-versal.h | ||
218 | +++ b/include/hw/arm/xlnx-versal.h | ||
219 | @@ -XXX,XX +XXX,XX @@ | ||
220 | #define XLNX_VERSAL_H | ||
221 | |||
222 | #include "hw/sysbus.h" | ||
223 | -#include "hw/arm/arm.h" | ||
224 | +#include "hw/arm/boot.h" | ||
225 | #include "hw/intc/arm_gicv3.h" | ||
226 | |||
227 | #define TYPE_XLNX_VERSAL "xlnx-versal" | ||
228 | diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h | ||
229 | index XXXXXXX..XXXXXXX 100644 | ||
230 | --- a/include/hw/arm/xlnx-zynqmp.h | ||
231 | +++ b/include/hw/arm/xlnx-zynqmp.h | ||
232 | @@ -XXX,XX +XXX,XX @@ | ||
233 | #ifndef XLNX_ZYNQMP_H | ||
234 | |||
235 | #include "qemu-common.h" | ||
236 | -#include "hw/arm/arm.h" | ||
237 | +#include "hw/arm/boot.h" | ||
238 | #include "hw/intc/arm_gic.h" | ||
239 | #include "hw/net/cadence_gem.h" | ||
240 | #include "hw/char/cadence_uart.h" | ||
241 | diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c | ||
242 | index XXXXXXX..XXXXXXX 100644 | ||
243 | --- a/hw/arm/armsse.c | ||
244 | +++ b/hw/arm/armsse.c | ||
245 | @@ -XXX,XX +XXX,XX @@ | ||
246 | #include "hw/sysbus.h" | ||
247 | #include "hw/registerfields.h" | ||
248 | #include "hw/arm/armsse.h" | ||
249 | -#include "hw/arm/arm.h" | ||
250 | +#include "hw/arm/boot.h" | ||
251 | |||
252 | /* Format of the System Information block SYS_CONFIG register */ | ||
253 | typedef enum SysConfigFormat { | ||
254 | diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c | ||
255 | index XXXXXXX..XXXXXXX 100644 | ||
256 | --- a/hw/arm/armv7m.c | ||
257 | +++ b/hw/arm/armv7m.c | ||
258 | @@ -XXX,XX +XXX,XX @@ | ||
259 | #include "qemu-common.h" | ||
260 | #include "cpu.h" | ||
261 | #include "hw/sysbus.h" | ||
262 | -#include "hw/arm/arm.h" | ||
263 | +#include "hw/arm/boot.h" | ||
264 | #include "hw/loader.h" | ||
265 | #include "elf.h" | ||
266 | #include "sysemu/qtest.h" | ||
267 | diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c | ||
268 | index XXXXXXX..XXXXXXX 100644 | ||
269 | --- a/hw/arm/aspeed.c | ||
270 | +++ b/hw/arm/aspeed.c | ||
271 | @@ -XXX,XX +XXX,XX @@ | ||
272 | #include "qemu-common.h" | ||
273 | #include "cpu.h" | ||
274 | #include "exec/address-spaces.h" | ||
275 | -#include "hw/arm/arm.h" | ||
276 | +#include "hw/arm/boot.h" | ||
277 | #include "hw/arm/aspeed.h" | ||
278 | #include "hw/arm/aspeed_soc.h" | ||
279 | #include "hw/boards.h" | ||
280 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | ||
281 | index XXXXXXX..XXXXXXX 100644 | ||
282 | --- a/hw/arm/boot.c | ||
283 | +++ b/hw/arm/boot.c | ||
284 | @@ -XXX,XX +XXX,XX @@ | ||
285 | #include "qapi/error.h" | ||
286 | #include <libfdt.h> | ||
287 | #include "hw/hw.h" | ||
288 | -#include "hw/arm/arm.h" | ||
289 | +#include "hw/arm/boot.h" | ||
290 | #include "hw/arm/linux-boot-if.h" | ||
291 | #include "sysemu/kvm.h" | ||
292 | #include "sysemu/sysemu.h" | ||
293 | diff --git a/hw/arm/collie.c b/hw/arm/collie.c | ||
294 | index XXXXXXX..XXXXXXX 100644 | ||
295 | --- a/hw/arm/collie.c | ||
296 | +++ b/hw/arm/collie.c | ||
297 | @@ -XXX,XX +XXX,XX @@ | ||
298 | #include "hw/sysbus.h" | ||
299 | #include "hw/boards.h" | ||
300 | #include "strongarm.h" | ||
301 | -#include "hw/arm/arm.h" | ||
302 | +#include "hw/arm/boot.h" | ||
303 | #include "hw/block/flash.h" | ||
304 | #include "exec/address-spaces.h" | ||
305 | #include "cpu.h" | ||
306 | diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c | ||
307 | index XXXXXXX..XXXXXXX 100644 | ||
308 | --- a/hw/arm/exynos4210.c | ||
309 | +++ b/hw/arm/exynos4210.c | ||
310 | @@ -XXX,XX +XXX,XX @@ | ||
311 | #include "hw/boards.h" | ||
312 | #include "sysemu/sysemu.h" | ||
313 | #include "hw/sysbus.h" | ||
314 | -#include "hw/arm/arm.h" | ||
315 | +#include "hw/arm/boot.h" | ||
316 | #include "hw/loader.h" | ||
317 | #include "hw/arm/exynos4210.h" | ||
318 | #include "hw/sd/sdhci.h" | ||
319 | diff --git a/hw/arm/exynos4_boards.c b/hw/arm/exynos4_boards.c | ||
320 | index XXXXXXX..XXXXXXX 100644 | ||
321 | --- a/hw/arm/exynos4_boards.c | ||
322 | +++ b/hw/arm/exynos4_boards.c | ||
323 | @@ -XXX,XX +XXX,XX @@ | ||
324 | #include "sysemu/sysemu.h" | ||
325 | #include "hw/sysbus.h" | ||
326 | #include "net/net.h" | ||
327 | -#include "hw/arm/arm.h" | ||
328 | +#include "hw/arm/boot.h" | ||
329 | #include "exec/address-spaces.h" | ||
330 | #include "hw/arm/exynos4210.h" | ||
331 | #include "hw/net/lan9118.h" | ||
332 | diff --git a/hw/arm/highbank.c b/hw/arm/highbank.c | ||
333 | index XXXXXXX..XXXXXXX 100644 | ||
334 | --- a/hw/arm/highbank.c | ||
335 | +++ b/hw/arm/highbank.c | ||
336 | @@ -XXX,XX +XXX,XX @@ | ||
337 | #include "qemu/osdep.h" | ||
338 | #include "qapi/error.h" | ||
339 | #include "hw/sysbus.h" | ||
340 | -#include "hw/arm/arm.h" | ||
341 | +#include "hw/arm/boot.h" | ||
342 | #include "hw/loader.h" | ||
343 | #include "net/net.h" | ||
344 | #include "sysemu/kvm.h" | ||
345 | diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c | ||
346 | index XXXXXXX..XXXXXXX 100644 | ||
347 | --- a/hw/arm/integratorcp.c | ||
348 | +++ b/hw/arm/integratorcp.c | ||
349 | @@ -XXX,XX +XXX,XX @@ | ||
350 | #include "cpu.h" | ||
351 | #include "hw/sysbus.h" | ||
352 | #include "hw/boards.h" | ||
353 | -#include "hw/arm/arm.h" | ||
354 | +#include "hw/arm/boot.h" | ||
355 | #include "hw/misc/arm_integrator_debug.h" | ||
356 | #include "hw/net/smc91c111.h" | ||
357 | #include "net/net.h" | ||
358 | diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c | ||
359 | index XXXXXXX..XXXXXXX 100644 | ||
360 | --- a/hw/arm/mainstone.c | ||
361 | +++ b/hw/arm/mainstone.c | ||
362 | @@ -XXX,XX +XXX,XX @@ | ||
363 | #include "qapi/error.h" | ||
364 | #include "hw/hw.h" | ||
365 | #include "hw/arm/pxa.h" | ||
366 | -#include "hw/arm/arm.h" | ||
367 | +#include "hw/arm/boot.h" | ||
368 | #include "net/net.h" | ||
369 | #include "hw/net/smc91c111.h" | ||
370 | #include "hw/boards.h" | ||
371 | diff --git a/hw/arm/microbit.c b/hw/arm/microbit.c | ||
372 | index XXXXXXX..XXXXXXX 100644 | ||
373 | --- a/hw/arm/microbit.c | ||
374 | +++ b/hw/arm/microbit.c | ||
375 | @@ -XXX,XX +XXX,XX @@ | ||
376 | #include "qemu/osdep.h" | ||
377 | #include "qapi/error.h" | ||
378 | #include "hw/boards.h" | ||
379 | -#include "hw/arm/arm.h" | ||
380 | +#include "hw/arm/boot.h" | ||
381 | #include "sysemu/sysemu.h" | ||
382 | #include "exec/address-spaces.h" | ||
383 | |||
384 | diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c | ||
385 | index XXXXXXX..XXXXXXX 100644 | ||
386 | --- a/hw/arm/mps2-tz.c | ||
387 | +++ b/hw/arm/mps2-tz.c | ||
388 | @@ -XXX,XX +XXX,XX @@ | ||
389 | #include "qemu/osdep.h" | ||
390 | #include "qapi/error.h" | ||
391 | #include "qemu/error-report.h" | ||
392 | -#include "hw/arm/arm.h" | ||
393 | +#include "hw/arm/boot.h" | ||
394 | #include "hw/arm/armv7m.h" | ||
395 | #include "hw/or-irq.h" | ||
396 | #include "hw/boards.h" | ||
397 | diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c | ||
398 | index XXXXXXX..XXXXXXX 100644 | ||
399 | --- a/hw/arm/mps2.c | ||
400 | +++ b/hw/arm/mps2.c | ||
401 | @@ -XXX,XX +XXX,XX @@ | ||
402 | #include "qemu/osdep.h" | ||
403 | #include "qapi/error.h" | ||
404 | #include "qemu/error-report.h" | ||
405 | -#include "hw/arm/arm.h" | ||
406 | +#include "hw/arm/boot.h" | ||
407 | #include "hw/arm/armv7m.h" | ||
408 | #include "hw/or-irq.h" | ||
409 | #include "hw/boards.h" | ||
410 | diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c | ||
411 | index XXXXXXX..XXXXXXX 100644 | ||
412 | --- a/hw/arm/msf2-soc.c | ||
413 | +++ b/hw/arm/msf2-soc.c | ||
414 | @@ -XXX,XX +XXX,XX @@ | ||
415 | #include "qemu/units.h" | ||
416 | #include "qapi/error.h" | ||
417 | #include "qemu-common.h" | ||
418 | -#include "hw/arm/arm.h" | ||
419 | #include "exec/address-spaces.h" | ||
420 | #include "hw/char/serial.h" | ||
421 | #include "hw/boards.h" | ||
422 | diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c | ||
423 | index XXXXXXX..XXXXXXX 100644 | ||
424 | --- a/hw/arm/msf2-som.c | ||
425 | +++ b/hw/arm/msf2-som.c | ||
426 | @@ -XXX,XX +XXX,XX @@ | ||
427 | #include "qapi/error.h" | ||
428 | #include "qemu/error-report.h" | ||
429 | #include "hw/boards.h" | ||
430 | -#include "hw/arm/arm.h" | ||
431 | +#include "hw/arm/boot.h" | ||
432 | #include "exec/address-spaces.h" | ||
433 | #include "hw/arm/msf2-soc.h" | ||
434 | #include "cpu.h" | ||
435 | diff --git a/hw/arm/musca.c b/hw/arm/musca.c | ||
436 | index XXXXXXX..XXXXXXX 100644 | ||
437 | --- a/hw/arm/musca.c | ||
438 | +++ b/hw/arm/musca.c | ||
439 | @@ -XXX,XX +XXX,XX @@ | ||
440 | #include "qapi/error.h" | ||
441 | #include "exec/address-spaces.h" | ||
442 | #include "sysemu/sysemu.h" | ||
443 | -#include "hw/arm/arm.h" | ||
444 | +#include "hw/arm/boot.h" | ||
445 | #include "hw/arm/armsse.h" | ||
446 | #include "hw/boards.h" | ||
447 | #include "hw/char/pl011.h" | ||
448 | diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c | ||
449 | index XXXXXXX..XXXXXXX 100644 | ||
450 | --- a/hw/arm/musicpal.c | ||
451 | +++ b/hw/arm/musicpal.c | ||
452 | @@ -XXX,XX +XXX,XX @@ | ||
453 | #include "qemu-common.h" | ||
454 | #include "cpu.h" | ||
455 | #include "hw/sysbus.h" | ||
456 | -#include "hw/arm/arm.h" | ||
457 | +#include "hw/arm/boot.h" | ||
458 | #include "net/net.h" | ||
459 | #include "sysemu/sysemu.h" | ||
460 | #include "hw/boards.h" | ||
461 | diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c | ||
462 | index XXXXXXX..XXXXXXX 100644 | ||
463 | --- a/hw/arm/netduino2.c | ||
464 | +++ b/hw/arm/netduino2.c | ||
465 | @@ -XXX,XX +XXX,XX @@ | ||
466 | #include "hw/boards.h" | ||
467 | #include "qemu/error-report.h" | ||
468 | #include "hw/arm/stm32f205_soc.h" | ||
469 | -#include "hw/arm/arm.h" | ||
470 | +#include "hw/arm/boot.h" | ||
471 | |||
472 | static void netduino2_init(MachineState *machine) | ||
473 | { | ||
474 | diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c | ||
475 | index XXXXXXX..XXXXXXX 100644 | ||
476 | --- a/hw/arm/nrf51_soc.c | ||
477 | +++ b/hw/arm/nrf51_soc.c | ||
478 | @@ -XXX,XX +XXX,XX @@ | ||
479 | #include "qemu/osdep.h" | ||
480 | #include "qapi/error.h" | ||
481 | #include "qemu-common.h" | ||
482 | -#include "hw/arm/arm.h" | ||
483 | +#include "hw/arm/boot.h" | ||
484 | #include "hw/sysbus.h" | ||
485 | #include "hw/boards.h" | ||
486 | #include "hw/misc/unimp.h" | ||
487 | diff --git a/hw/arm/nseries.c b/hw/arm/nseries.c | ||
488 | index XXXXXXX..XXXXXXX 100644 | ||
489 | --- a/hw/arm/nseries.c | ||
490 | +++ b/hw/arm/nseries.c | ||
491 | @@ -XXX,XX +XXX,XX @@ | ||
492 | #include "qemu/bswap.h" | ||
493 | #include "sysemu/sysemu.h" | ||
494 | #include "hw/arm/omap.h" | ||
495 | -#include "hw/arm/arm.h" | ||
496 | +#include "hw/arm/boot.h" | ||
497 | #include "hw/irq.h" | ||
498 | #include "ui/console.h" | ||
499 | #include "hw/boards.h" | ||
500 | diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c | ||
501 | index XXXXXXX..XXXXXXX 100644 | ||
502 | --- a/hw/arm/omap1.c | ||
503 | +++ b/hw/arm/omap1.c | ||
504 | @@ -XXX,XX +XXX,XX @@ | ||
505 | #include "cpu.h" | ||
506 | #include "hw/boards.h" | ||
507 | #include "hw/hw.h" | ||
508 | -#include "hw/arm/arm.h" | ||
509 | +#include "hw/arm/boot.h" | ||
510 | #include "hw/arm/omap.h" | ||
511 | #include "sysemu/sysemu.h" | ||
512 | #include "hw/arm/soc_dma.h" | ||
513 | diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c | ||
514 | index XXXXXXX..XXXXXXX 100644 | ||
515 | --- a/hw/arm/omap2.c | ||
516 | +++ b/hw/arm/omap2.c | ||
517 | @@ -XXX,XX +XXX,XX @@ | ||
518 | #include "sysemu/qtest.h" | ||
519 | #include "hw/boards.h" | ||
520 | #include "hw/hw.h" | ||
521 | -#include "hw/arm/arm.h" | ||
522 | +#include "hw/arm/boot.h" | ||
523 | #include "hw/arm/omap.h" | ||
524 | #include "sysemu/sysemu.h" | ||
525 | #include "qemu/timer.h" | ||
526 | diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c | ||
527 | index XXXXXXX..XXXXXXX 100644 | ||
528 | --- a/hw/arm/omap_sx1.c | ||
529 | +++ b/hw/arm/omap_sx1.c | ||
530 | @@ -XXX,XX +XXX,XX @@ | ||
531 | #include "ui/console.h" | ||
532 | #include "hw/arm/omap.h" | ||
533 | #include "hw/boards.h" | ||
534 | -#include "hw/arm/arm.h" | ||
535 | +#include "hw/arm/boot.h" | ||
536 | #include "hw/block/flash.h" | ||
537 | #include "sysemu/qtest.h" | ||
538 | #include "exec/address-spaces.h" | ||
539 | diff --git a/hw/arm/palm.c b/hw/arm/palm.c | ||
540 | index XXXXXXX..XXXXXXX 100644 | ||
541 | --- a/hw/arm/palm.c | ||
542 | +++ b/hw/arm/palm.c | ||
543 | @@ -XXX,XX +XXX,XX @@ | ||
544 | #include "ui/console.h" | ||
545 | #include "hw/arm/omap.h" | ||
546 | #include "hw/boards.h" | ||
547 | -#include "hw/arm/arm.h" | ||
548 | +#include "hw/arm/boot.h" | ||
549 | #include "hw/input/tsc2xxx.h" | ||
550 | #include "hw/loader.h" | ||
551 | #include "exec/address-spaces.h" | ||
552 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | ||
553 | index XXXXXXX..XXXXXXX 100644 | ||
554 | --- a/hw/arm/raspi.c | ||
555 | +++ b/hw/arm/raspi.c | ||
556 | @@ -XXX,XX +XXX,XX @@ | ||
557 | #include "qemu/error-report.h" | ||
558 | #include "hw/boards.h" | ||
559 | #include "hw/loader.h" | ||
560 | -#include "hw/arm/arm.h" | ||
561 | +#include "hw/arm/boot.h" | ||
562 | #include "sysemu/sysemu.h" | ||
563 | |||
564 | #define SMPBOOT_ADDR 0x300 /* this should leave enough space for ATAGS */ | ||
565 | diff --git a/hw/arm/realview.c b/hw/arm/realview.c | ||
566 | index XXXXXXX..XXXXXXX 100644 | ||
567 | --- a/hw/arm/realview.c | ||
568 | +++ b/hw/arm/realview.c | ||
569 | @@ -XXX,XX +XXX,XX @@ | ||
570 | #include "qemu-common.h" | ||
571 | #include "cpu.h" | ||
572 | #include "hw/sysbus.h" | ||
573 | -#include "hw/arm/arm.h" | ||
574 | +#include "hw/arm/boot.h" | ||
575 | #include "hw/arm/primecell.h" | ||
576 | #include "hw/net/lan9118.h" | ||
577 | #include "hw/net/smc91c111.h" | ||
578 | diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c | ||
579 | index XXXXXXX..XXXXXXX 100644 | ||
580 | --- a/hw/arm/spitz.c | ||
581 | +++ b/hw/arm/spitz.c | ||
582 | @@ -XXX,XX +XXX,XX @@ | ||
583 | #include "qapi/error.h" | ||
584 | #include "hw/hw.h" | ||
585 | #include "hw/arm/pxa.h" | ||
586 | -#include "hw/arm/arm.h" | ||
587 | +#include "hw/arm/boot.h" | ||
588 | #include "sysemu/sysemu.h" | ||
589 | #include "hw/pcmcia.h" | ||
590 | #include "hw/i2c/i2c.h" | ||
591 | diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c | ||
592 | index XXXXXXX..XXXXXXX 100644 | ||
593 | --- a/hw/arm/stellaris.c | ||
594 | +++ b/hw/arm/stellaris.c | ||
595 | @@ -XXX,XX +XXX,XX @@ | ||
596 | #include "qapi/error.h" | ||
597 | #include "hw/sysbus.h" | ||
598 | #include "hw/ssi/ssi.h" | ||
599 | -#include "hw/arm/arm.h" | ||
600 | +#include "hw/arm/boot.h" | ||
601 | #include "qemu/timer.h" | ||
602 | #include "hw/i2c/i2c.h" | ||
603 | #include "net/net.h" | ||
604 | diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c | ||
605 | index XXXXXXX..XXXXXXX 100644 | ||
606 | --- a/hw/arm/stm32f205_soc.c | ||
607 | +++ b/hw/arm/stm32f205_soc.c | ||
608 | @@ -XXX,XX +XXX,XX @@ | ||
609 | #include "qemu/osdep.h" | ||
610 | #include "qapi/error.h" | ||
611 | #include "qemu-common.h" | ||
612 | -#include "hw/arm/arm.h" | ||
613 | +#include "hw/arm/boot.h" | ||
614 | #include "exec/address-spaces.h" | ||
615 | #include "hw/arm/stm32f205_soc.h" | ||
616 | |||
617 | diff --git a/hw/arm/strongarm.c b/hw/arm/strongarm.c | ||
618 | index XXXXXXX..XXXXXXX 100644 | ||
619 | --- a/hw/arm/strongarm.c | ||
620 | +++ b/hw/arm/strongarm.c | ||
621 | @@ -XXX,XX +XXX,XX @@ | ||
622 | #include "hw/sysbus.h" | ||
623 | #include "strongarm.h" | ||
624 | #include "qemu/error-report.h" | ||
625 | -#include "hw/arm/arm.h" | ||
626 | +#include "hw/arm/boot.h" | ||
627 | #include "chardev/char-fe.h" | ||
628 | #include "chardev/char-serial.h" | ||
629 | #include "sysemu/sysemu.h" | ||
630 | diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c | ||
631 | index XXXXXXX..XXXXXXX 100644 | ||
632 | --- a/hw/arm/tosa.c | ||
633 | +++ b/hw/arm/tosa.c | ||
634 | @@ -XXX,XX +XXX,XX @@ | ||
635 | #include "qapi/error.h" | ||
636 | #include "hw/hw.h" | ||
637 | #include "hw/arm/pxa.h" | ||
638 | -#include "hw/arm/arm.h" | ||
639 | +#include "hw/arm/boot.h" | ||
640 | #include "hw/arm/sharpsl.h" | ||
641 | #include "hw/pcmcia.h" | ||
642 | #include "hw/boards.h" | ||
643 | diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c | ||
644 | index XXXXXXX..XXXXXXX 100644 | ||
645 | --- a/hw/arm/versatilepb.c | ||
646 | +++ b/hw/arm/versatilepb.c | ||
647 | @@ -XXX,XX +XXX,XX @@ | ||
648 | #include "qemu-common.h" | ||
649 | #include "cpu.h" | ||
650 | #include "hw/sysbus.h" | ||
651 | -#include "hw/arm/arm.h" | ||
652 | +#include "hw/arm/boot.h" | ||
653 | #include "hw/net/smc91c111.h" | ||
654 | #include "net/net.h" | ||
655 | #include "sysemu/sysemu.h" | ||
656 | diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c | ||
657 | index XXXXXXX..XXXXXXX 100644 | ||
658 | --- a/hw/arm/vexpress.c | ||
659 | +++ b/hw/arm/vexpress.c | ||
660 | @@ -XXX,XX +XXX,XX @@ | ||
661 | #include "qemu-common.h" | ||
662 | #include "cpu.h" | ||
663 | #include "hw/sysbus.h" | ||
664 | -#include "hw/arm/arm.h" | ||
665 | +#include "hw/arm/boot.h" | ||
666 | #include "hw/arm/primecell.h" | ||
667 | #include "hw/net/lan9118.h" | ||
668 | #include "hw/i2c/i2c.h" | ||
669 | diff --git a/hw/arm/virt.c b/hw/arm/virt.c | ||
670 | index XXXXXXX..XXXXXXX 100644 | ||
671 | --- a/hw/arm/virt.c | ||
672 | +++ b/hw/arm/virt.c | ||
673 | @@ -XXX,XX +XXX,XX @@ | ||
674 | #include "qemu/option.h" | ||
675 | #include "qapi/error.h" | ||
676 | #include "hw/sysbus.h" | ||
677 | -#include "hw/arm/arm.h" | ||
678 | +#include "hw/arm/boot.h" | ||
679 | #include "hw/arm/primecell.h" | ||
680 | #include "hw/arm/virt.h" | ||
681 | #include "hw/block/flash.h" | ||
682 | diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c | ||
683 | index XXXXXXX..XXXXXXX 100644 | ||
684 | --- a/hw/arm/xilinx_zynq.c | ||
685 | +++ b/hw/arm/xilinx_zynq.c | ||
686 | @@ -XXX,XX +XXX,XX @@ | ||
687 | #include "qemu-common.h" | ||
688 | #include "cpu.h" | ||
689 | #include "hw/sysbus.h" | ||
690 | -#include "hw/arm/arm.h" | ||
691 | +#include "hw/arm/boot.h" | ||
692 | #include "net/net.h" | ||
693 | #include "exec/address-spaces.h" | ||
694 | #include "sysemu/sysemu.h" | ||
695 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
696 | index XXXXXXX..XXXXXXX 100644 | ||
697 | --- a/hw/arm/xlnx-versal.c | ||
698 | +++ b/hw/arm/xlnx-versal.c | ||
699 | @@ -XXX,XX +XXX,XX @@ | ||
700 | #include "net/net.h" | ||
701 | #include "sysemu/sysemu.h" | ||
702 | #include "sysemu/kvm.h" | ||
703 | -#include "hw/arm/arm.h" | ||
704 | +#include "hw/arm/boot.h" | ||
705 | #include "kvm_arm.h" | ||
706 | #include "hw/misc/unimp.h" | ||
707 | #include "hw/intc/arm_gicv3_common.h" | ||
708 | diff --git a/hw/arm/z2.c b/hw/arm/z2.c | ||
709 | index XXXXXXX..XXXXXXX 100644 | ||
710 | --- a/hw/arm/z2.c | ||
711 | +++ b/hw/arm/z2.c | ||
712 | @@ -XXX,XX +XXX,XX @@ | ||
713 | #include "qemu/osdep.h" | ||
714 | #include "hw/hw.h" | ||
715 | #include "hw/arm/pxa.h" | ||
716 | -#include "hw/arm/arm.h" | ||
717 | +#include "hw/arm/boot.h" | ||
718 | #include "hw/i2c/i2c.h" | ||
719 | #include "hw/ssi/ssi.h" | ||
720 | #include "hw/boards.h" | ||
721 | -- | 291 | -- |
722 | 2.20.1 | 292 | 2.20.1 |
723 | 293 | ||
724 | 294 | diff view generated by jsdifflib |
1 | The hw/arm/arm.h header now only includes declarations relating | 1 | Implement the MVE shifts by immediate, which perform shifts |
---|---|---|---|
2 | to boot.c code, so it is only needed by Arm board or SoC code. | 2 | on a single general-purpose register. |
3 | Remove some unnecessary inclusions of it from target/arm files | 3 | |
4 | and from hw/intc/armv7m_nvic.c. | 4 | These patterns overlap with the long-shift-by-immediates, |
5 | so we have to rearrange the grouping a little here. | ||
5 | 6 | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
7 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 9 | Message-id: 20210628135835.6690-18-peter.maydell@linaro.org |
9 | Message-id: 20190516163857.6430-3-peter.maydell@linaro.org | ||
10 | --- | 10 | --- |
11 | hw/intc/armv7m_nvic.c | 1 - | 11 | target/arm/helper-mve.h | 3 ++ |
12 | target/arm/arm-semi.c | 1 - | 12 | target/arm/translate.h | 1 + |
13 | target/arm/cpu.c | 1 - | 13 | target/arm/t32.decode | 31 ++++++++++++++----- |
14 | target/arm/cpu64.c | 1 - | 14 | target/arm/mve_helper.c | 10 ++++++ |
15 | target/arm/kvm.c | 1 - | 15 | target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- |
16 | target/arm/kvm32.c | 1 - | 16 | 5 files changed, 104 insertions(+), 9 deletions(-) |
17 | target/arm/kvm64.c | 1 - | 17 | |
18 | 7 files changed, 7 deletions(-) | 18 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
19 | 19 | index XXXXXXX..XXXXXXX 100644 | |
20 | diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c | 20 | --- a/target/arm/helper-mve.h |
21 | index XXXXXXX..XXXXXXX 100644 | 21 | +++ b/target/arm/helper-mve.h |
22 | --- a/hw/intc/armv7m_nvic.c | 22 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) |
23 | +++ b/hw/intc/armv7m_nvic.c | 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 | ||
24 | @@ -XXX,XX +XXX,XX @@ | 45 | @@ -XXX,XX +XXX,XX @@ |
25 | #include "cpu.h" | 46 | |
26 | #include "hw/sysbus.h" | 47 | &mve_shl_ri rdalo rdahi shim |
27 | #include "qemu/timer.h" | 48 | &mve_shl_rr rdalo rdahi rm |
28 | -#include "hw/arm/arm.h" | 49 | +&mve_sh_ri rda shim |
29 | #include "hw/intc/armv7m_nvic.h" | 50 | |
30 | #include "target/arm/cpu.h" | 51 | # rdahi: bits [3:1] from insn, bit 0 is 1 |
31 | #include "exec/exec-all.h" | 52 | # rdalo: bits [3:1] from insn, bit 0 is 0 |
32 | diff --git a/target/arm/arm-semi.c b/target/arm/arm-semi.c | ||
33 | index XXXXXXX..XXXXXXX 100644 | ||
34 | --- a/target/arm/arm-semi.c | ||
35 | +++ b/target/arm/arm-semi.c | ||
36 | @@ -XXX,XX +XXX,XX @@ | 53 | @@ -XXX,XX +XXX,XX @@ |
37 | #else | 54 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 |
38 | #include "qemu-common.h" | 55 | @mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ |
39 | #include "exec/gdbstub.h" | 56 | &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 |
40 | -#include "hw/arm/arm.h" | 57 | +@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ |
41 | #include "qemu/cutils.h" | 58 | + &mve_sh_ri shim=%imm5_12_6 |
42 | #endif | 59 | |
43 | 60 | { | |
44 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | 61 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi |
45 | index XXXXXXX..XXXXXXX 100644 | 62 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi |
46 | --- a/target/arm/cpu.c | 63 | # the rest fall through (where ORR_rrri and MOV_rxri will end up |
47 | +++ b/target/arm/cpu.c | 64 | # handling them as r13 and r15 accesses with the same semantics as A32). |
48 | @@ -XXX,XX +XXX,XX @@ | 65 | [ |
49 | #if !defined(CONFIG_USER_ONLY) | 66 | - LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
50 | #include "hw/loader.h" | 67 | - LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri |
51 | #endif | 68 | - ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri |
52 | -#include "hw/arm/arm.h" | 69 | + { |
53 | #include "sysemu/sysemu.h" | 70 | + UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri |
54 | #include "sysemu/hw_accel.h" | 71 | + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
55 | #include "kvm_arm.h" | 72 | + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri |
56 | diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c | 73 | + } |
57 | index XXXXXXX..XXXXXXX 100644 | 74 | |
58 | --- a/target/arm/cpu64.c | 75 | - UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri |
59 | +++ b/target/arm/cpu64.c | 76 | - URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
60 | @@ -XXX,XX +XXX,XX @@ | 77 | - SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
61 | #if !defined(CONFIG_USER_ONLY) | 78 | - SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
62 | #include "hw/loader.h" | 79 | + { |
63 | #endif | 80 | + URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri |
64 | -#include "hw/arm/arm.h" | 81 | + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri |
65 | #include "sysemu/sysemu.h" | 82 | + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
66 | #include "sysemu/kvm.h" | 83 | + } |
67 | #include "kvm_arm.h" | 84 | + |
68 | diff --git a/target/arm/kvm.c b/target/arm/kvm.c | 85 | + { |
69 | index XXXXXXX..XXXXXXX 100644 | 86 | + SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri |
70 | --- a/target/arm/kvm.c | 87 | + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri |
71 | +++ b/target/arm/kvm.c | 88 | + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
72 | @@ -XXX,XX +XXX,XX @@ | 89 | + } |
73 | #include "cpu.h" | 90 | + |
74 | #include "trace.h" | 91 | + { |
75 | #include "internals.h" | 92 | + SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri |
76 | -#include "hw/arm/arm.h" | 93 | + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
77 | #include "hw/pci/pci.h" | 94 | + } |
78 | #include "exec/memattrs.h" | 95 | |
79 | #include "exec/address-spaces.h" | 96 | LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr |
80 | diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c | 97 | ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr |
81 | index XXXXXXX..XXXXXXX 100644 | 98 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
82 | --- a/target/arm/kvm32.c | 99 | index XXXXXXX..XXXXXXX 100644 |
83 | +++ b/target/arm/kvm32.c | 100 | --- a/target/arm/mve_helper.c |
84 | @@ -XXX,XX +XXX,XX @@ | 101 | +++ b/target/arm/mve_helper.c |
85 | #include "sysemu/kvm.h" | 102 | @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) |
86 | #include "kvm_arm.h" | 103 | { |
87 | #include "internals.h" | 104 | return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); |
88 | -#include "hw/arm/arm.h" | 105 | } |
89 | #include "qemu/log.h" | 106 | + |
90 | 107 | +uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift) | |
91 | static inline void set_feature(uint64_t *features, int feature) | 108 | +{ |
92 | diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c | 109 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); |
93 | index XXXXXXX..XXXXXXX 100644 | 110 | +} |
94 | --- a/target/arm/kvm64.c | 111 | + |
95 | +++ b/target/arm/kvm64.c | 112 | +uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) |
96 | @@ -XXX,XX +XXX,XX @@ | 113 | +{ |
97 | #include "sysemu/kvm.h" | 114 | + return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); |
98 | #include "kvm_arm.h" | 115 | +} |
99 | #include "internals.h" | 116 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
100 | -#include "hw/arm/arm.h" | 117 | index XXXXXXX..XXXXXXX 100644 |
101 | 118 | --- a/target/arm/translate.c | |
102 | static bool have_guest_debug; | 119 | +++ b/target/arm/translate.c |
103 | 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 | */ | ||
104 | -- | 211 | -- |
105 | 2.20.1 | 212 | 2.20.1 |
106 | 213 | ||
107 | 214 | diff view generated by jsdifflib |
1 | From: Alistair Francis <alistair.francis@wdc.com> | 1 | Implement the MVE shifts by register, which perform |
---|---|---|---|
2 | shifts on a single general-purpose register. | ||
2 | 3 | ||
3 | Commit 89e68b575 "target/arm: Use vector operations for saturation" | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | causes this abort() when booting QEMU ARM with a Cortex-A15: | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20210628135835.6690-19-peter.maydell@linaro.org | ||
7 | --- | ||
8 | target/arm/helper-mve.h | 2 ++ | ||
9 | target/arm/translate.h | 1 + | ||
10 | target/arm/t32.decode | 18 ++++++++++++++---- | ||
11 | target/arm/mve_helper.c | 10 ++++++++++ | ||
12 | target/arm/translate.c | 30 ++++++++++++++++++++++++++++++ | ||
13 | 5 files changed, 57 insertions(+), 4 deletions(-) | ||
5 | 14 | ||
6 | 0 0x00007ffff4c2382f in raise () at /usr/lib/libc.so.6 | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
7 | 1 0x00007ffff4c0e672 in abort () at /usr/lib/libc.so.6 | 16 | index XXXXXXX..XXXXXXX 100644 |
8 | 2 0x00005555559c1839 in disas_neon_data_insn (insn=<optimized out>, s=<optimized out>) at ./target/arm/translate.c:6673 | 17 | --- a/target/arm/helper-mve.h |
9 | 3 0x00005555559c1839 in disas_neon_data_insn (s=<optimized out>, insn=<optimized out>) at ./target/arm/translate.c:6386 | 18 | +++ b/target/arm/helper-mve.h |
10 | 4 0x00005555559cd8a4 in disas_arm_insn (insn=4081107068, s=0x7fffe59a9510) at ./target/arm/translate.c:9289 | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
11 | 5 0x00005555559cd8a4 in arm_tr_translate_insn (dcbase=0x7fffe59a9510, cpu=<optimized out>) at ./target/arm/translate.c:13612 | 20 | |
12 | 6 0x00005555558d1d39 in translator_loop (ops=0x5555561cc580 <arm_translator_ops>, db=0x7fffe59a9510, cpu=0x55555686a2f0, tb=<optimized out>, max_insns=<optimized out>) at ./accel/tcg/translator.c:96 | 21 | DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) |
13 | 7 0x00005555559d10d4 in gen_intermediate_code (cpu=cpu@entry=0x55555686a2f0, tb=tb@entry=0x7fffd7840080 <code_gen_buffer+126091347>, max_insns=max_insns@entry=512) at ./target/arm/translate.c:13901 | 22 | DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) |
14 | 8 0x00005555558d06b9 in tb_gen_code (cpu=cpu@entry=0x55555686a2f0, pc=3067096216, cs_base=0, flags=192, cflags=-16252928, cflags@entry=524288) at ./accel/tcg/translate-all.c:1736 | 23 | +DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) |
15 | 9 0x00005555558ce467 in tb_find (cf_mask=524288, tb_exit=1, last_tb=0x7fffd783e640 <code_gen_buffer+126084627>, cpu=0x1) at ./accel/tcg/cpu-exec.c:407 | 24 | +DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) |
16 | 10 0x00005555558ce467 in cpu_exec (cpu=cpu@entry=0x55555686a2f0) at ./accel/tcg/cpu-exec.c:728 | 25 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
17 | 11 0x000055555588b0cf in tcg_cpu_exec (cpu=0x55555686a2f0) at ./cpus.c:1431 | 26 | index XXXXXXX..XXXXXXX 100644 |
18 | 12 0x000055555588d223 in qemu_tcg_cpu_thread_fn (arg=0x55555686a2f0) at ./cpus.c:1735 | 27 | --- a/target/arm/translate.h |
19 | 13 0x000055555588d223 in qemu_tcg_cpu_thread_fn (arg=arg@entry=0x55555686a2f0) at ./cpus.c:1709 | 28 | +++ b/target/arm/translate.h |
20 | 14 0x0000555555d2629a in qemu_thread_start (args=<optimized out>) at ./util/qemu-thread-posix.c:502 | 29 | @@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); |
21 | 15 0x00007ffff4db8a92 in start_thread () at /usr/lib/libpthread. | 30 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); |
22 | 31 | typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); | |
23 | This patch ensures that we don't hit the abort() in the second switch | 32 | typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); |
24 | case in disas_neon_data_insn() as we will return from the first case. | 33 | +typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); |
25 | 34 | ||
26 | Signed-off-by: Alistair Francis <alistair.francis@wdc.com> | 35 | /** |
27 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 36 | * arm_tbflags_from_tb: |
28 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | 37 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode |
29 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | 38 | index XXXXXXX..XXXXXXX 100644 |
30 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | 39 | --- a/target/arm/t32.decode |
31 | Message-id: ad91b397f360b2fc7f4087e476f7df5b04d42ddb.1558021877.git.alistair.francis@wdc.com | 40 | +++ b/target/arm/t32.decode |
32 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 41 | @@ -XXX,XX +XXX,XX @@ |
33 | --- | 42 | &mve_shl_ri rdalo rdahi shim |
34 | target/arm/translate.c | 4 ++-- | 43 | &mve_shl_rr rdalo rdahi rm |
35 | 1 file changed, 2 insertions(+), 2 deletions(-) | 44 | &mve_sh_ri rda shim |
36 | 45 | +&mve_sh_rr rda rm | |
46 | |||
47 | # rdahi: bits [3:1] from insn, bit 0 is 1 | ||
48 | # rdalo: bits [3:1] from insn, bit 0 is 0 | ||
49 | @@ -XXX,XX +XXX,XX @@ | ||
50 | &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 | ||
51 | @mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ | ||
52 | &mve_sh_ri shim=%imm5_12_6 | ||
53 | +@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr | ||
54 | |||
55 | { | ||
56 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi | ||
57 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi | ||
58 | SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
59 | } | ||
60 | |||
61 | - LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
62 | - ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
63 | - UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr | ||
64 | - SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr | ||
65 | + { | ||
66 | + UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr | ||
67 | + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
68 | + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr | ||
69 | + } | ||
70 | + | ||
71 | + { | ||
72 | + SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr | ||
73 | + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
74 | + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr | ||
75 | + } | ||
76 | + | ||
77 | UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr | ||
78 | SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr | ||
79 | ] | ||
80 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
81 | index XXXXXXX..XXXXXXX 100644 | ||
82 | --- a/target/arm/mve_helper.c | ||
83 | +++ b/target/arm/mve_helper.c | ||
84 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
85 | { | ||
86 | return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); | ||
87 | } | ||
88 | + | ||
89 | +uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
90 | +{ | ||
91 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF); | ||
92 | +} | ||
93 | + | ||
94 | +uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
95 | +{ | ||
96 | + return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); | ||
97 | +} | ||
37 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 98 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
38 | index XXXXXXX..XXXXXXX 100644 | 99 | index XXXXXXX..XXXXXXX 100644 |
39 | --- a/target/arm/translate.c | 100 | --- a/target/arm/translate.c |
40 | +++ b/target/arm/translate.c | 101 | +++ b/target/arm/translate.c |
41 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | 102 | @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) |
42 | tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | 103 | return do_mve_sh_ri(s, a, gen_mve_uqshl); |
43 | rn_ofs, rm_ofs, vec_size, vec_size, | 104 | } |
44 | (u ? uqadd_op : sqadd_op) + size); | 105 | |
45 | - break; | 106 | +static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn) |
46 | + return 0; | 107 | +{ |
47 | 108 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | |
48 | case NEON_3R_VQSUB: | 109 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ |
49 | tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | 110 | + return false; |
50 | rn_ofs, rm_ofs, vec_size, vec_size, | 111 | + } |
51 | (u ? uqsub_op : sqsub_op) + size); | 112 | + if (!dc_isar_feature(aa32_mve, s) || |
52 | - break; | 113 | + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || |
53 | + return 0; | 114 | + a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 || |
54 | 115 | + a->rm == a->rda) { | |
55 | case NEON_3R_VMUL: /* VMUL */ | 116 | + /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */ |
56 | if (u) { | 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 | */ | ||
57 | -- | 139 | -- |
58 | 2.20.1 | 140 | 2.20.1 |
59 | 141 | ||
60 | 142 | diff view generated by jsdifflib |