1 | The following changes since commit 4cc10cae64c51e17844dc4358481c393d7bf1ed4: | 1 | The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df: |
---|---|---|---|
2 | 2 | ||
3 | Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging (2021-05-06 18:56:17 +0100) | 3 | Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100) |
4 | 4 | ||
5 | are available in the Git repository at: | 5 | are available in the Git repository at: |
6 | 6 | ||
7 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210510 | 7 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702 |
8 | 8 | ||
9 | for you to fetch changes up to 8f96812baa53005f32aece3e30b140826c20aa19: | 9 | for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8: |
10 | 10 | ||
11 | hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 (2021-05-10 13:24:09 +0100) | 11 | target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100) |
12 | 12 | ||
13 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
14 | target-arm queue: | 14 | target-arm queue: |
15 | * docs: fix link in sbsa description | 15 | * more MVE instructions |
16 | * linux-user/aarch64: Enable hwcap for RND, BTI, and MTE | 16 | * hw/gpio/gpio_pwr: use shutdown function for reboot |
17 | * target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() | 17 | * target/arm: Check NaN mode before silencing NaN |
18 | * target/arm: Split neon and vfp translation to their own | 18 | * tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
19 | compilation units | 19 | * hw/arm: Add basic power management to raspi. |
20 | * target/arm: Make WFI a NOP for userspace emulators | 20 | * docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc |
21 | * hw/sd/omap_mmc: Use device_cold_reset() instead of | ||
22 | device_legacy_reset() | ||
23 | * include: More fixes for 'extern "C"' block use | ||
24 | * hw/arm/imx25_pdk: Fix error message for invalid RAM size | ||
25 | * hw/arm/mps2-tz: Implement AN524 memory remapping via machine property | ||
26 | * hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 | ||
27 | 21 | ||
28 | ---------------------------------------------------------------- | 22 | ---------------------------------------------------------------- |
29 | Alex Bennée (1): | 23 | Joe Komlodi (1): |
30 | docs: fix link in sbsa description | 24 | target/arm: Check NaN mode before silencing NaN |
31 | 25 | ||
32 | Guenter Roeck (1): | 26 | Maxim Uvarov (1): |
33 | hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 | 27 | hw/gpio/gpio_pwr: use shutdown function for reboot |
34 | 28 | ||
35 | Peter Maydell (22): | 29 | Nolan Leake (1): |
36 | target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() | 30 | hw/arm: Add basic power management to raspi. |
37 | target/arm: Move constant expanders to translate.h | 31 | |
38 | target/arm: Share unallocated_encoding() and gen_exception_insn() | 32 | Patrick Venture (2): |
39 | target/arm: Make functions used by m-nocp global | 33 | docs/system/arm: Add quanta-q7l1-bmc reference |
40 | target/arm: Split m-nocp trans functions into their own file | 34 | docs/system/arm: Add quanta-gbs-bmc reference |
41 | target/arm: Move gen_aa32 functions to translate-a32.h | 35 | |
42 | target/arm: Move vfp_{load, store}_reg{32, 64} to translate-vfp.c.inc | 36 | Peter Maydell (18): |
43 | target/arm: Make functions used by translate-vfp global | 37 | target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation |
44 | target/arm: Make translate-vfp.c.inc its own compilation unit | 38 | target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH |
45 | target/arm: Move vfp_reg_ptr() to translate-neon.c.inc | 39 | target/arm: Make asimd_imm_const() public |
46 | target/arm: Delete unused typedef | 40 | target/arm: Use asimd_imm_const for A64 decode |
47 | target/arm: Move NeonGenThreeOpEnvFn typedef to translate.h | 41 | target/arm: Use dup_const() instead of bitfield_replicate() |
48 | target/arm: Make functions used by translate-neon global | 42 | target/arm: Implement MVE logical immediate insns |
49 | target/arm: Make translate-neon.c.inc its own compilation unit | 43 | target/arm: Implement MVE vector shift left by immediate insns |
50 | target/arm: Make WFI a NOP for userspace emulators | 44 | target/arm: Implement MVE vector shift right by immediate insns |
51 | hw/sd/omap_mmc: Use device_cold_reset() instead of device_legacy_reset() | 45 | target/arm: Implement MVE VSHLL |
52 | osdep: Make os-win32.h and os-posix.h handle 'extern "C"' themselves | 46 | target/arm: Implement MVE VSRI, VSLI |
53 | include/qemu/bswap.h: Handle being included outside extern "C" block | 47 | target/arm: Implement MVE VSHRN, VRSHRN |
54 | include/disas/dis-asm.h: Handle being included outside 'extern "C"' | 48 | target/arm: Implement MVE saturating narrowing shifts |
55 | hw/misc/mps2-scc: Add "QEMU interface" comment | 49 | target/arm: Implement MVE VSHLC |
56 | hw/misc/mps2-scc: Support using CFG0 bit 0 for remapping | 50 | target/arm: Implement MVE VADDLV |
57 | hw/arm/mps2-tz: Implement AN524 memory remapping via machine property | 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 | ||
58 | 55 | ||
59 | Philippe Mathieu-Daudé (1): | 56 | Philippe Mathieu-Daudé (1): |
60 | hw/arm/imx25_pdk: Fix error message for invalid RAM size | 57 | tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
61 | 58 | ||
62 | Richard Henderson (1): | 59 | docs/system/arm/aspeed.rst | 1 + |
63 | linux-user/aarch64: Enable hwcap for RND, BTI, and MTE | 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 | ||
64 | 82 | ||
65 | docs/system/arm/mps2.rst | 10 + | ||
66 | docs/system/arm/sbsa.rst | 2 +- | ||
67 | include/disas/dis-asm.h | 12 +- | ||
68 | include/hw/misc/mps2-scc.h | 21 ++ | ||
69 | include/qemu/bswap.h | 26 ++- | ||
70 | include/qemu/osdep.h | 8 +- | ||
71 | include/sysemu/os-posix.h | 8 + | ||
72 | include/sysemu/os-win32.h | 8 + | ||
73 | target/arm/translate-a32.h | 144 +++++++++++++ | ||
74 | target/arm/translate-a64.h | 2 - | ||
75 | target/arm/translate.h | 29 +++ | ||
76 | hw/arm/imx25_pdk.c | 5 +- | ||
77 | hw/arm/mps2-tz.c | 108 +++++++++- | ||
78 | hw/arm/xilinx_zynq.c | 2 +- | ||
79 | hw/misc/mps2-scc.c | 13 +- | ||
80 | hw/sd/omap_mmc.c | 2 +- | ||
81 | linux-user/elfload.c | 13 ++ | ||
82 | target/arm/helper.c | 2 +- | ||
83 | target/arm/op_helper.c | 12 ++ | ||
84 | target/arm/translate-a64.c | 15 -- | ||
85 | target/arm/translate-m-nocp.c | 221 ++++++++++++++++++++ | ||
86 | .../arm/{translate-neon.c.inc => translate-neon.c} | 19 +- | ||
87 | .../arm/{translate-vfp.c.inc => translate-vfp.c} | 230 +++------------------ | ||
88 | target/arm/translate.c | 200 ++++-------------- | ||
89 | disas/arm-a64.cc | 2 - | ||
90 | disas/nanomips.cpp | 2 - | ||
91 | target/arm/meson.build | 15 +- | ||
92 | 27 files changed, 718 insertions(+), 413 deletions(-) | ||
93 | create mode 100644 target/arm/translate-a32.h | ||
94 | create mode 100644 target/arm/translate-m-nocp.c | ||
95 | rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) | ||
96 | rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (94%) | ||
97 | diff view generated by jsdifflib |
1 | From: Guenter Roeck <linux@roeck-us.net> | 1 | From: Patrick Venture <venture@google.com> |
---|---|---|---|
2 | 2 | ||
3 | Commit dfc388797cc4 ("hw/arm: xlnx: Set all boards' GEM 'phy-addr' | 3 | Adds a line-item reference to the supported quanta-q71l-bmc aspeed |
4 | property value to 23") configured the PHY address for xilinx-zynq-a9 | 4 | entry. |
5 | to 23. When trying to boot xilinx-zynq-a9 with zynq-zc702.dtb or | ||
6 | zynq-zc706.dtb, this results in the following error message when | ||
7 | trying to use the Ethernet interface. | ||
8 | 5 | ||
9 | macb e000b000.ethernet eth0: Could not attach PHY (-19) | 6 | Signed-off-by: Patrick Venture <venture@google.com> |
10 | 7 | Reviewed-by: Cédric Le Goater <clg@kaod.org> | |
11 | The devicetree files for ZC702 and ZC706 configure PHY address 7. The | 8 | Message-id: 20210615192848.1065297-2-venture@google.com |
12 | documentation for the ZC702 and ZC706 evaluation boards suggest that the | ||
13 | PHY address is 7, not 23. Other boards use PHY address 0, 1, 3, or 7. | ||
14 | I was unable to find a documentation or a devicetree file suggesting | ||
15 | or using PHY address 23. The Ethernet interface starts working with | ||
16 | zynq-zc702.dtb and zynq-zc706.dtb when setting the PHY address to 7, | ||
17 | so let's use it. | ||
18 | |||
19 | Cc: Bin Meng <bin.meng@windriver.com> | ||
20 | Signed-off-by: Guenter Roeck <linux@roeck-us.net> | ||
21 | Reviewed-by: Bin Meng <bmeng.cn@gmail.com> | ||
22 | Acked-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
23 | Message-id: 20210504124140.1100346-1-linux@roeck-us.net | ||
24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
25 | --- | 10 | --- |
26 | hw/arm/xilinx_zynq.c | 2 +- | 11 | docs/system/arm/aspeed.rst | 1 + |
27 | 1 file changed, 1 insertion(+), 1 deletion(-) | 12 | 1 file changed, 1 insertion(+) |
28 | 13 | ||
29 | diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c | 14 | diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst |
30 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
31 | --- a/hw/arm/xilinx_zynq.c | 16 | --- a/docs/system/arm/aspeed.rst |
32 | +++ b/hw/arm/xilinx_zynq.c | 17 | +++ b/docs/system/arm/aspeed.rst |
33 | @@ -XXX,XX +XXX,XX @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq) | 18 | @@ -XXX,XX +XXX,XX @@ etc. |
34 | qemu_check_nic_model(nd, TYPE_CADENCE_GEM); | 19 | AST2400 SoC based machines : |
35 | qdev_set_nic_properties(dev, nd); | 20 | |
36 | } | 21 | - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC |
37 | - object_property_set_int(OBJECT(dev), "phy-addr", 23, &error_abort); | 22 | +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC |
38 | + object_property_set_int(OBJECT(dev), "phy-addr", 7, &error_abort); | 23 | |
39 | s = SYS_BUS_DEVICE(dev); | 24 | AST2500 SoC based machines : |
40 | sysbus_realize_and_unref(s, &error_fatal); | 25 | |
41 | sysbus_mmio_map(s, 0, base); | ||
42 | -- | 26 | -- |
43 | 2.20.1 | 27 | 2.20.1 |
44 | 28 | ||
45 | 29 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | From: Patrick Venture <venture@google.com> |
---|---|---|---|
2 | 2 | ||
3 | These three features are already enabled by TCG, but are missing | 3 | Add line item reference to quanta-gbs-bmc machine. |
4 | their hwcap bits. Update HWCAP2 from linux v5.12. | ||
5 | 4 | ||
6 | Cc: qemu-stable@nongnu.org (for 6.0.1) | 5 | Signed-off-by: Patrick Venture <venture@google.com> |
7 | Buglink: https://bugs.launchpad.net/bugs/1926044 | 6 | Reviewed-by: Cédric Le Goater <clg@kaod.org> |
8 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Message-id: 20210615192848.1065297-3-venture@google.com |
9 | Message-id: 20210427214108.88503-1-richard.henderson@linaro.org | 8 | [PMM: fixed underline Sphinx warning] |
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | --- | 10 | --- |
12 | linux-user/elfload.c | 13 +++++++++++++ | 11 | docs/system/arm/nuvoton.rst | 5 +++-- |
13 | 1 file changed, 13 insertions(+) | 12 | 1 file changed, 3 insertions(+), 2 deletions(-) |
14 | 13 | ||
15 | diff --git a/linux-user/elfload.c b/linux-user/elfload.c | 14 | diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst |
16 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/linux-user/elfload.c | 16 | --- a/docs/system/arm/nuvoton.rst |
18 | +++ b/linux-user/elfload.c | 17 | +++ b/docs/system/arm/nuvoton.rst |
19 | @@ -XXX,XX +XXX,XX @@ enum { | 18 | @@ -XXX,XX +XXX,XX @@ |
20 | ARM_HWCAP2_A64_SVESM4 = 1 << 6, | 19 | -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) |
21 | ARM_HWCAP2_A64_FLAGM2 = 1 << 7, | 20 | -===================================================== |
22 | ARM_HWCAP2_A64_FRINT = 1 << 8, | 21 | +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) |
23 | + ARM_HWCAP2_A64_SVEI8MM = 1 << 9, | 22 | +================================================================ |
24 | + ARM_HWCAP2_A64_SVEF32MM = 1 << 10, | 23 | |
25 | + ARM_HWCAP2_A64_SVEF64MM = 1 << 11, | 24 | The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are |
26 | + ARM_HWCAP2_A64_SVEBF16 = 1 << 12, | 25 | designed to be used as Baseboard Management Controllers (BMCs) in various |
27 | + ARM_HWCAP2_A64_I8MM = 1 << 13, | 26 | @@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip : |
28 | + ARM_HWCAP2_A64_BF16 = 1 << 14, | 27 | The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and |
29 | + ARM_HWCAP2_A64_DGH = 1 << 15, | 28 | Hyperscale applications. The following machines are based on this chip : |
30 | + ARM_HWCAP2_A64_RNG = 1 << 16, | 29 | |
31 | + ARM_HWCAP2_A64_BTI = 1 << 17, | 30 | +- ``quanta-gbs-bmc`` Quanta GBS server BMC |
32 | + ARM_HWCAP2_A64_MTE = 1 << 18, | 31 | - ``quanta-gsj`` Quanta GSJ server BMC |
33 | }; | 32 | |
34 | 33 | There are also two more SoCs, NPCM710 and NPCM705, which are single-core | |
35 | #define ELF_HWCAP get_elf_hwcap() | ||
36 | @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) | ||
37 | GET_FEATURE_ID(aa64_dcpodp, ARM_HWCAP2_A64_DCPODP); | ||
38 | GET_FEATURE_ID(aa64_condm_5, ARM_HWCAP2_A64_FLAGM2); | ||
39 | GET_FEATURE_ID(aa64_frint, ARM_HWCAP2_A64_FRINT); | ||
40 | + GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); | ||
41 | + GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); | ||
42 | + GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); | ||
43 | |||
44 | return hwcaps; | ||
45 | } | ||
46 | -- | 34 | -- |
47 | 2.20.1 | 35 | 2.20.1 |
48 | 36 | ||
49 | 37 | diff view generated by jsdifflib |
1 | We want to split out the .c.inc files which are currently included | 1 | From: Nolan Leake <nolan@sigbus.net> |
---|---|---|---|
2 | into translate.c so they are separate compilation units. To do this | 2 | |
3 | we need to make some functions which are currently file-local to | 3 | This is just enough to make reboot and poweroff work. Works for |
4 | translate.c have global scope; create a translate-a32.h paralleling | 4 | linux, u-boot, and the arm trusted firmware. Not tested, but should |
5 | the existing translate-a64.h as a place for these declarations to | 5 | work for plan9, and bare-metal/hobby OSes, since they seem to generally |
6 | live, so that code moved into the new compilation units can call | 6 | do what linux does for reset. |
7 | them. | 7 | |
8 | 8 | The watchdog timer functionality is not yet implemented. | |
9 | The functions made global here are those required by the | 9 | |
10 | m-nocp.decode functions, except that I have converted the whole | 10 | Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64 |
11 | family of {read,write}_neon_element* and also both the load_cpu and | 11 | Signed-off-by: Nolan Leake <nolan@sigbus.net> |
12 | store_cpu functions for consistency, even though m-nocp only wants a | 12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
13 | few functions from each. | 13 | Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
14 | 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/] | ||
15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
16 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
17 | Message-id: 20210430132740.10391-4-peter.maydell@linaro.org | ||
18 | --- | 18 | --- |
19 | target/arm/translate-a32.h | 57 ++++++++++++++++++++++++++++++++++ | 19 | include/hw/arm/bcm2835_peripherals.h | 3 +- |
20 | target/arm/translate.c | 39 +++++------------------ | 20 | include/hw/misc/bcm2835_powermgt.h | 29 +++++ |
21 | target/arm/translate-vfp.c.inc | 2 +- | 21 | hw/arm/bcm2835_peripherals.c | 13 ++- |
22 | 3 files changed, 65 insertions(+), 33 deletions(-) | 22 | hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++ |
23 | create mode 100644 target/arm/translate-a32.h | 23 | hw/misc/meson.build | 1 + |
24 | 24 | 5 files changed, 204 insertions(+), 2 deletions(-) | |
25 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 25 | create mode 100644 include/hw/misc/bcm2835_powermgt.h |
26 | create mode 100644 hw/misc/bcm2835_powermgt.c | ||
27 | |||
28 | diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h | ||
29 | index XXXXXXX..XXXXXXX 100644 | ||
30 | --- a/include/hw/arm/bcm2835_peripherals.h | ||
31 | +++ b/include/hw/arm/bcm2835_peripherals.h | ||
32 | @@ -XXX,XX +XXX,XX @@ | ||
33 | #include "hw/misc/bcm2835_mphi.h" | ||
34 | #include "hw/misc/bcm2835_thermal.h" | ||
35 | #include "hw/misc/bcm2835_cprman.h" | ||
36 | +#include "hw/misc/bcm2835_powermgt.h" | ||
37 | #include "hw/sd/sdhci.h" | ||
38 | #include "hw/sd/bcm2835_sdhost.h" | ||
39 | #include "hw/gpio/bcm2835_gpio.h" | ||
40 | @@ -XXX,XX +XXX,XX @@ struct BCM2835PeripheralState { | ||
41 | BCM2835MphiState mphi; | ||
42 | UnimplementedDeviceState txp; | ||
43 | UnimplementedDeviceState armtmr; | ||
44 | - UnimplementedDeviceState powermgt; | ||
45 | + BCM2835PowerMgtState powermgt; | ||
46 | BCM2835CprmanState cprman; | ||
47 | PL011State uart0; | ||
48 | BCM2835AuxState aux; | ||
49 | diff --git a/include/hw/misc/bcm2835_powermgt.h b/include/hw/misc/bcm2835_powermgt.h | ||
26 | new file mode 100644 | 50 | new file mode 100644 |
27 | index XXXXXXX..XXXXXXX | 51 | index XXXXXXX..XXXXXXX |
28 | --- /dev/null | 52 | --- /dev/null |
29 | +++ b/target/arm/translate-a32.h | 53 | +++ b/include/hw/misc/bcm2835_powermgt.h |
30 | @@ -XXX,XX +XXX,XX @@ | 54 | @@ -XXX,XX +XXX,XX @@ |
31 | +/* | 55 | +/* |
32 | + * AArch32 translation, common definitions. | 56 | + * BCM2835 Power Management emulation |
33 | + * | 57 | + * |
34 | + * Copyright (c) 2021 Linaro, Ltd. | 58 | + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> |
35 | + * | 59 | + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> |
36 | + * This library is free software; you can redistribute it and/or | 60 | + * |
37 | + * modify it under the terms of the GNU Lesser General Public | 61 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. |
38 | + * License as published by the Free Software Foundation; either | 62 | + * See the COPYING file in the top-level directory. |
39 | + * version 2.1 of the License, or (at your option) any later version. | ||
40 | + * | ||
41 | + * This library is distributed in the hope that it will be useful, | ||
42 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
43 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
44 | + * Lesser General Public License for more details. | ||
45 | + * | ||
46 | + * You should have received a copy of the GNU Lesser General Public | ||
47 | + * License along with this library; if not, see <http://www.gnu.org/licenses/>. | ||
48 | + */ | 63 | + */ |
49 | + | 64 | + |
50 | +#ifndef TARGET_ARM_TRANSLATE_A64_H | 65 | +#ifndef BCM2835_POWERMGT_H |
51 | +#define TARGET_ARM_TRANSLATE_A64_H | 66 | +#define BCM2835_POWERMGT_H |
52 | + | 67 | + |
53 | +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); | 68 | +#include "hw/sysbus.h" |
54 | +void arm_gen_condlabel(DisasContext *s); | 69 | +#include "qom/object.h" |
55 | +bool vfp_access_check(DisasContext *s); | 70 | + |
56 | +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); | 71 | +#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt" |
57 | +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); | 72 | +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT) |
58 | +void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); | 73 | + |
59 | +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); | 74 | +struct BCM2835PowerMgtState { |
60 | + | 75 | + SysBusDevice busdev; |
61 | +static inline TCGv_i32 load_cpu_offset(int offset) | 76 | + MemoryRegion iomem; |
62 | +{ | 77 | + |
63 | + TCGv_i32 tmp = tcg_temp_new_i32(); | 78 | + uint32_t rstc; |
64 | + tcg_gen_ld_i32(tmp, cpu_env, offset); | 79 | + uint32_t rsts; |
65 | + return tmp; | 80 | + uint32_t wdog; |
66 | +} | 81 | +}; |
67 | + | ||
68 | +#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) | ||
69 | + | ||
70 | +static inline void store_cpu_offset(TCGv_i32 var, int offset) | ||
71 | +{ | ||
72 | + tcg_gen_st_i32(var, cpu_env, offset); | ||
73 | + tcg_temp_free_i32(var); | ||
74 | +} | ||
75 | + | ||
76 | +#define store_cpu_field(var, name) \ | ||
77 | + store_cpu_offset(var, offsetof(CPUARMState, name)) | ||
78 | + | ||
79 | +/* Create a new temporary and set it to the value of a CPU register. */ | ||
80 | +static inline TCGv_i32 load_reg(DisasContext *s, int reg) | ||
81 | +{ | ||
82 | + TCGv_i32 tmp = tcg_temp_new_i32(); | ||
83 | + load_reg_var(s, tmp, reg); | ||
84 | + return tmp; | ||
85 | +} | ||
86 | + | 82 | + |
87 | +#endif | 83 | +#endif |
88 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 84 | diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c |
89 | index XXXXXXX..XXXXXXX 100644 | 85 | index XXXXXXX..XXXXXXX 100644 |
90 | --- a/target/arm/translate.c | 86 | --- a/hw/arm/bcm2835_peripherals.c |
91 | +++ b/target/arm/translate.c | 87 | +++ b/hw/arm/bcm2835_peripherals.c |
88 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) | ||
89 | |||
90 | object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", | ||
91 | OBJECT(&s->gpu_bus_mr)); | ||
92 | + | ||
93 | + /* Power Management */ | ||
94 | + object_initialize_child(obj, "powermgt", &s->powermgt, | ||
95 | + TYPE_BCM2835_POWERMGT); | ||
96 | } | ||
97 | |||
98 | static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) | ||
99 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) | ||
100 | qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, | ||
101 | INTERRUPT_USB)); | ||
102 | |||
103 | + /* Power Management */ | ||
104 | + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { | ||
105 | + return; | ||
106 | + } | ||
107 | + | ||
108 | + memory_region_add_subregion(&s->peri_mr, PM_OFFSET, | ||
109 | + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->powermgt), 0)); | ||
110 | + | ||
111 | create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); | ||
112 | create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); | ||
113 | - create_unimp(s, &s->powermgt, "bcm2835-powermgt", PM_OFFSET, 0x114); | ||
114 | create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); | ||
115 | create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); | ||
116 | create_unimp(s, &s->spi[0], "bcm2835-spi0", SPI0_OFFSET, 0x20); | ||
117 | diff --git a/hw/misc/bcm2835_powermgt.c b/hw/misc/bcm2835_powermgt.c | ||
118 | new file mode 100644 | ||
119 | index XXXXXXX..XXXXXXX | ||
120 | --- /dev/null | ||
121 | +++ b/hw/misc/bcm2835_powermgt.c | ||
92 | @@ -XXX,XX +XXX,XX @@ | 122 | @@ -XXX,XX +XXX,XX @@ |
93 | #define ENABLE_ARCH_8 arm_dc_feature(s, ARM_FEATURE_V8) | 123 | +/* |
94 | 124 | + * BCM2835 Power Management emulation | |
95 | #include "translate.h" | 125 | + * |
96 | +#include "translate-a32.h" | 126 | + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> |
97 | 127 | + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> | |
98 | #if defined(CONFIG_USER_ONLY) | 128 | + * |
99 | #define IS_USER(s) 1 | 129 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. |
100 | @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) | 130 | + * See the COPYING file in the top-level directory. |
101 | } | 131 | + */ |
102 | 132 | + | |
103 | /* Generate a label used for skipping this instruction */ | 133 | +#include "qemu/osdep.h" |
104 | -static void arm_gen_condlabel(DisasContext *s) | 134 | +#include "qemu/log.h" |
105 | +void arm_gen_condlabel(DisasContext *s) | 135 | +#include "qemu/module.h" |
106 | { | 136 | +#include "hw/misc/bcm2835_powermgt.h" |
107 | if (!s->condjmp) { | 137 | +#include "migration/vmstate.h" |
108 | s->condlabel = gen_new_label(); | 138 | +#include "sysemu/runstate.h" |
109 | @@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s) | 139 | + |
110 | } | 140 | +#define PASSWORD 0x5a000000 |
111 | } | 141 | +#define PASSWORD_MASK 0xff000000 |
112 | 142 | + | |
113 | -static inline TCGv_i32 load_cpu_offset(int offset) | 143 | +#define R_RSTC 0x1c |
114 | -{ | 144 | +#define V_RSTC_RESET 0x20 |
115 | - TCGv_i32 tmp = tcg_temp_new_i32(); | 145 | +#define R_RSTS 0x20 |
116 | - tcg_gen_ld_i32(tmp, cpu_env, offset); | 146 | +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ |
117 | - return tmp; | 147 | +#define R_WDOG 0x24 |
118 | -} | 148 | + |
119 | - | 149 | +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, |
120 | -#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) | 150 | + unsigned size) |
121 | - | 151 | +{ |
122 | -static inline void store_cpu_offset(TCGv_i32 var, int offset) | 152 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; |
123 | -{ | 153 | + uint32_t res = 0; |
124 | - tcg_gen_st_i32(var, cpu_env, offset); | 154 | + |
125 | - tcg_temp_free_i32(var); | 155 | + switch (offset) { |
126 | -} | 156 | + case R_RSTC: |
127 | - | 157 | + res = s->rstc; |
128 | -#define store_cpu_field(var, name) \ | 158 | + break; |
129 | - store_cpu_offset(var, offsetof(CPUARMState, name)) | 159 | + case R_RSTS: |
130 | - | 160 | + res = s->rsts; |
131 | /* The architectural value of PC. */ | 161 | + break; |
132 | static uint32_t read_pc(DisasContext *s) | 162 | + case R_WDOG: |
133 | { | 163 | + res = s->wdog; |
134 | @@ -XXX,XX +XXX,XX @@ static uint32_t read_pc(DisasContext *s) | 164 | + break; |
135 | } | 165 | + |
136 | 166 | + default: | |
137 | /* Set a variable to the value of a CPU register. */ | 167 | + qemu_log_mask(LOG_UNIMP, |
138 | -static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) | 168 | + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx |
139 | +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) | 169 | + "\n", offset); |
140 | { | 170 | + res = 0; |
141 | if (reg == 15) { | 171 | + break; |
142 | tcg_gen_movi_i32(var, read_pc(s)); | 172 | + } |
143 | @@ -XXX,XX +XXX,XX @@ static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) | 173 | + |
144 | } | 174 | + return res; |
145 | } | 175 | +} |
146 | 176 | + | |
147 | -/* Create a new temporary and set it to the value of a CPU register. */ | 177 | +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, |
148 | -static inline TCGv_i32 load_reg(DisasContext *s, int reg) | 178 | + uint64_t value, unsigned size) |
149 | -{ | 179 | +{ |
150 | - TCGv_i32 tmp = tcg_temp_new_i32(); | 180 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; |
151 | - load_reg_var(s, tmp, reg); | 181 | + |
152 | - return tmp; | 182 | + if ((value & PASSWORD_MASK) != PASSWORD) { |
153 | -} | 183 | + qemu_log_mask(LOG_GUEST_ERROR, |
154 | - | 184 | + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 |
155 | /* | 185 | + " at offset 0x%08"HWADDR_PRIx"\n", |
156 | * Create a new temp, REG + OFS, except PC is ALIGN(PC, 4). | 186 | + value, offset); |
157 | * This is used for load/store for which use of PC implies (literal), | 187 | + return; |
158 | @@ -XXX,XX +XXX,XX @@ static inline void vfp_store_reg32(TCGv_i32 var, int reg) | 188 | + } |
159 | tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); | 189 | + |
160 | } | 190 | + value = value & ~PASSWORD_MASK; |
161 | 191 | + | |
162 | -static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) | 192 | + switch (offset) { |
163 | +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) | 193 | + case R_RSTC: |
164 | { | 194 | + s->rstc = value; |
165 | long off = neon_element_offset(reg, ele, memop); | 195 | + if (value & V_RSTC_RESET) { |
166 | 196 | + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { | |
167 | @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) | 197 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
168 | } | 198 | + } else { |
169 | } | 199 | + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); |
170 | 200 | + } | |
171 | -static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) | 201 | + } |
172 | +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) | 202 | + break; |
173 | { | 203 | + case R_RSTS: |
174 | long off = neon_element_offset(reg, ele, memop); | 204 | + qemu_log_mask(LOG_UNIMP, |
175 | 205 | + "bcm2835_powermgt_write: RSTS\n"); | |
176 | @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) | 206 | + s->rsts = value; |
177 | } | 207 | + break; |
178 | } | 208 | + case R_WDOG: |
179 | 209 | + qemu_log_mask(LOG_UNIMP, | |
180 | -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) | 210 | + "bcm2835_powermgt_write: WDOG\n"); |
181 | +void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) | 211 | + s->wdog = value; |
182 | { | 212 | + break; |
183 | long off = neon_element_offset(reg, ele, memop); | 213 | + |
184 | 214 | + default: | |
185 | @@ -XXX,XX +XXX,XX @@ static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) | 215 | + qemu_log_mask(LOG_UNIMP, |
186 | } | 216 | + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx |
187 | } | 217 | + "\n", offset); |
188 | 218 | + break; | |
189 | -static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) | 219 | + } |
190 | +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) | 220 | +} |
191 | { | 221 | + |
192 | long off = neon_element_offset(reg, ele, memop); | 222 | +static const MemoryRegionOps bcm2835_powermgt_ops = { |
193 | 223 | + .read = bcm2835_powermgt_read, | |
194 | diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc | 224 | + .write = bcm2835_powermgt_write, |
225 | + .endianness = DEVICE_NATIVE_ENDIAN, | ||
226 | + .impl.min_access_size = 4, | ||
227 | + .impl.max_access_size = 4, | ||
228 | +}; | ||
229 | + | ||
230 | +static const VMStateDescription vmstate_bcm2835_powermgt = { | ||
231 | + .name = TYPE_BCM2835_POWERMGT, | ||
232 | + .version_id = 1, | ||
233 | + .minimum_version_id = 1, | ||
234 | + .fields = (VMStateField[]) { | ||
235 | + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), | ||
236 | + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), | ||
237 | + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), | ||
238 | + VMSTATE_END_OF_LIST() | ||
239 | + } | ||
240 | +}; | ||
241 | + | ||
242 | +static void bcm2835_powermgt_init(Object *obj) | ||
243 | +{ | ||
244 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); | ||
245 | + | ||
246 | + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, | ||
247 | + TYPE_BCM2835_POWERMGT, 0x200); | ||
248 | + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); | ||
249 | +} | ||
250 | + | ||
251 | +static void bcm2835_powermgt_reset(DeviceState *dev) | ||
252 | +{ | ||
253 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); | ||
254 | + | ||
255 | + /* https://elinux.org/BCM2835_registers#PM */ | ||
256 | + s->rstc = 0x00000102; | ||
257 | + s->rsts = 0x00001000; | ||
258 | + s->wdog = 0x00000000; | ||
259 | +} | ||
260 | + | ||
261 | +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) | ||
262 | +{ | ||
263 | + DeviceClass *dc = DEVICE_CLASS(klass); | ||
264 | + | ||
265 | + dc->reset = bcm2835_powermgt_reset; | ||
266 | + dc->vmsd = &vmstate_bcm2835_powermgt; | ||
267 | +} | ||
268 | + | ||
269 | +static TypeInfo bcm2835_powermgt_info = { | ||
270 | + .name = TYPE_BCM2835_POWERMGT, | ||
271 | + .parent = TYPE_SYS_BUS_DEVICE, | ||
272 | + .instance_size = sizeof(BCM2835PowerMgtState), | ||
273 | + .class_init = bcm2835_powermgt_class_init, | ||
274 | + .instance_init = bcm2835_powermgt_init, | ||
275 | +}; | ||
276 | + | ||
277 | +static void bcm2835_powermgt_register_types(void) | ||
278 | +{ | ||
279 | + type_register_static(&bcm2835_powermgt_info); | ||
280 | +} | ||
281 | + | ||
282 | +type_init(bcm2835_powermgt_register_types) | ||
283 | diff --git a/hw/misc/meson.build b/hw/misc/meson.build | ||
195 | index XXXXXXX..XXXXXXX 100644 | 284 | index XXXXXXX..XXXXXXX 100644 |
196 | --- a/target/arm/translate-vfp.c.inc | 285 | --- a/hw/misc/meson.build |
197 | +++ b/target/arm/translate-vfp.c.inc | 286 | +++ b/hw/misc/meson.build |
198 | @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) | 287 | @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( |
199 | * The most usual kind of VFP access check, for everything except | 288 | 'bcm2835_rng.c', |
200 | * FMXR/FMRX to the always-available special registers. | 289 | 'bcm2835_thermal.c', |
201 | */ | 290 | 'bcm2835_cprman.c', |
202 | -static bool vfp_access_check(DisasContext *s) | 291 | + 'bcm2835_powermgt.c', |
203 | +bool vfp_access_check(DisasContext *s) | 292 | )) |
204 | { | 293 | softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) |
205 | return full_vfp_access_check(s, false); | 294 | softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) |
206 | } | ||
207 | -- | 295 | -- |
208 | 2.20.1 | 296 | 2.20.1 |
209 | 297 | ||
210 | 298 | diff view generated by jsdifflib |
1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> | 1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> |
---|---|---|---|
2 | 2 | ||
3 | The i.MX25 PDK board has 2 banks for SDRAM, each can | 3 | Add a test booting and quickly shutdown a raspi2 machine, |
4 | address up to 256 MiB. So the total RAM usable for this | 4 | to test the power management model: |
5 | board is 512M. When we ask for more we get a misleading | ||
6 | error message: | ||
7 | 5 | ||
8 | $ qemu-system-arm -M imx25-pdk -m 513M | 6 | (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd: |
9 | qemu-system-arm: Invalid RAM size, should be 128 MiB | 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 | ||
10 | 44 | ||
11 | Update the error message to better match the reality: | ||
12 | |||
13 | $ qemu-system-arm -M imx25-pdk -m 513M | ||
14 | qemu-system-arm: RAM size more than 512 MiB is not supported | ||
15 | |||
16 | Fixes: bf350daae02 ("arm/imx25_pdk: drop RAM size fixup") | ||
17 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 45 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
18 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 46 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> |
19 | Reviewed-by: Igor Mammedov <imammedo@redhat.com> | 47 | Message-id: 20210531113837.1689775-1-f4bug@amsat.org |
20 | Message-id: 20210407225608.1882855-1-f4bug@amsat.org | ||
21 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 48 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
22 | --- | 49 | --- |
23 | hw/arm/imx25_pdk.c | 5 ++--- | 50 | tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++ |
24 | 1 file changed, 2 insertions(+), 3 deletions(-) | 51 | 1 file changed, 43 insertions(+) |
25 | 52 | ||
26 | diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c | 53 | diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py |
27 | index XXXXXXX..XXXXXXX 100644 | 54 | index XXXXXXX..XXXXXXX 100644 |
28 | --- a/hw/arm/imx25_pdk.c | 55 | --- a/tests/acceptance/boot_linux_console.py |
29 | +++ b/hw/arm/imx25_pdk.c | 56 | +++ b/tests/acceptance/boot_linux_console.py |
30 | @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info imx25_pdk_binfo; | 57 | @@ -XXX,XX +XXX,XX @@ |
31 | 58 | from avocado import skip | |
32 | static void imx25_pdk_init(MachineState *machine) | 59 | from avocado import skipUnless |
33 | { | 60 | from avocado_qemu import Test |
34 | - MachineClass *mc = MACHINE_GET_CLASS(machine); | 61 | +from avocado_qemu import exec_command |
35 | IMX25PDK *s = g_new0(IMX25PDK, 1); | 62 | from avocado_qemu import exec_command_and_wait_for_pattern |
36 | unsigned int ram_size; | 63 | from avocado_qemu import interrupt_interactive_console_until_pattern |
37 | unsigned int alias_offset; | 64 | from avocado_qemu import wait_for_console_pattern |
38 | @@ -XXX,XX +XXX,XX @@ static void imx25_pdk_init(MachineState *machine) | 65 | @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): |
39 | 66 | """ | |
40 | /* We need to initialize our memory */ | 67 | self.do_test_arm_raspi2(0) |
41 | if (machine->ram_size > (FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE)) { | 68 | |
42 | - char *sz = size_to_str(mc->default_ram_size); | 69 | + def test_arm_raspi2_initrd(self): |
43 | - error_report("Invalid RAM size, should be %s", sz); | 70 | + """ |
44 | + char *sz = size_to_str(FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE); | 71 | + :avocado: tags=arch:arm |
45 | + error_report("RAM size more than %s is not supported", sz); | 72 | + :avocado: tags=machine:raspi2 |
46 | g_free(sz); | 73 | + """ |
47 | exit(EXIT_FAILURE); | 74 | + deb_url = ('http://archive.raspberrypi.org/debian/' |
48 | } | 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 | ||
49 | -- | 114 | -- |
50 | 2.20.1 | 115 | 2.20.1 |
51 | 116 | ||
52 | 117 | diff view generated by jsdifflib |
1 | From: Alex Bennée <alex.bennee@linaro.org> | 1 | From: Joe Komlodi <joe.komlodi@xilinx.com> |
---|---|---|---|
2 | 2 | ||
3 | A trailing _ makes all the difference to the rendered link. | 3 | If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute |
4 | FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will | ||
5 | assert due to fpst->default_nan_mode being set. | ||
4 | 6 | ||
5 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | 7 | To avoid this, we check to see what NaN mode we're running in before we call |
6 | Message-id: 20210428131316.31390-1-alex.bennee@linaro.org | 8 | floatxx_silence_nan(). |
9 | |||
10 | Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com> | ||
11 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
12 | Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com | ||
7 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | --- | 15 | --- |
10 | docs/system/arm/sbsa.rst | 2 +- | 16 | target/arm/helper-a64.c | 12 +++++++++--- |
11 | 1 file changed, 1 insertion(+), 1 deletion(-) | 17 | target/arm/vfp_helper.c | 24 ++++++++++++++++++------ |
18 | 2 files changed, 27 insertions(+), 9 deletions(-) | ||
12 | 19 | ||
13 | diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst | 20 | diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c |
14 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/docs/system/arm/sbsa.rst | 22 | --- a/target/arm/helper-a64.c |
16 | +++ b/docs/system/arm/sbsa.rst | 23 | +++ b/target/arm/helper-a64.c |
17 | @@ -XXX,XX +XXX,XX @@ Arm Server Base System Architecture Reference board (``sbsa-ref``) | 24 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) |
18 | While the `virt` board is a generic board platform that doesn't match | 25 | float16 nan = a; |
19 | any real hardware the `sbsa-ref` board intends to look like real | 26 | if (float16_is_signaling_nan(a, fpst)) { |
20 | hardware. The `Server Base System Architecture | 27 | float_raise(float_flag_invalid, fpst); |
21 | -<https://developer.arm.com/documentation/den0029/latest>` defines a | 28 | - nan = float16_silence_nan(a, fpst); |
22 | +<https://developer.arm.com/documentation/den0029/latest>`_ defines a | 29 | + if (!fpst->default_nan_mode) { |
23 | minimum base line of hardware support and importantly how the firmware | 30 | + nan = float16_silence_nan(a, fpst); |
24 | reports that to any operating system. It is a static system that | 31 | + } |
25 | reports a very minimal DT to the firmware for non-discoverable | 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); | ||
26 | -- | 127 | -- |
27 | 2.20.1 | 128 | 2.20.1 |
28 | 129 | ||
29 | 130 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | In tlbi_aa64_vae2is_write() the calculation | ||
2 | bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, | ||
3 | pageaddr) | ||
4 | 1 | ||
5 | has the two arms of the ?: expression reversed. Fix the bug. | ||
6 | |||
7 | Fixes: b6ad6062f1e5 | ||
8 | Reported-by: Rebecca Cran <rebecca@nuviainc.com> | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
11 | Reviewed-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> | ||
12 | Reviewed-by: Rebecca Cran <rebecca@nuviainc.com> | ||
13 | Message-id: 20210420123106.10861-1-peter.maydell@linaro.org | ||
14 | --- | ||
15 | target/arm/helper.c | 2 +- | ||
16 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
17 | |||
18 | diff --git a/target/arm/helper.c b/target/arm/helper.c | ||
19 | index XXXXXXX..XXXXXXX 100644 | ||
20 | --- a/target/arm/helper.c | ||
21 | +++ b/target/arm/helper.c | ||
22 | @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
23 | uint64_t pageaddr = sextract64(value << 12, 0, 56); | ||
24 | bool secure = arm_is_secure_below_el3(env); | ||
25 | int mask = secure ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2; | ||
26 | - int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, | ||
27 | + int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_SE2 : ARMMMUIdx_E2, | ||
28 | pageaddr); | ||
29 | |||
30 | tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); | ||
31 | -- | ||
32 | 2.20.1 | ||
33 | |||
34 | diff view generated by jsdifflib |
1 | Make the remaining functions which are needed by translate-vfp.c.inc | 1 | From: Maxim Uvarov <maxim.uvarov@linaro.org> |
---|---|---|---|
2 | global. | ||
3 | 2 | ||
3 | qemu has 2 type of functions: shutdown and reboot. Shutdown | ||
4 | function has to be used for machine shutdown. Otherwise we cause | ||
5 | a reset with a bogus "cause" value, when we intended a shutdown. | ||
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] | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Message-id: 20210430132740.10391-8-peter.maydell@linaro.org | ||
8 | --- | 12 | --- |
9 | target/arm/translate-a32.h | 18 ++++++++++++++++++ | 13 | hw/gpio/gpio_pwr.c | 2 +- |
10 | target/arm/translate.c | 25 ++++++++----------------- | 14 | 1 file changed, 1 insertion(+), 1 deletion(-) |
11 | 2 files changed, 26 insertions(+), 17 deletions(-) | ||
12 | 15 | ||
13 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 16 | diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c |
14 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/target/arm/translate-a32.h | 18 | --- a/hw/gpio/gpio_pwr.c |
16 | +++ b/target/arm/translate-a32.h | 19 | +++ b/hw/gpio/gpio_pwr.c |
17 | @@ -XXX,XX +XXX,XX @@ void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); | 20 | @@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level) |
18 | void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); | 21 | static void gpio_pwr_shutdown(void *opaque, int n, int level) |
19 | void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); | ||
20 | void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); | ||
21 | +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs); | ||
22 | +void gen_set_cpsr(TCGv_i32 var, uint32_t mask); | ||
23 | +void gen_set_condexec(DisasContext *s); | ||
24 | +void gen_set_pc_im(DisasContext *s, target_ulong val); | ||
25 | +void gen_lookup_tb(DisasContext *s); | ||
26 | +long vfp_reg_offset(bool dp, unsigned reg); | ||
27 | +long neon_full_reg_offset(unsigned reg); | ||
28 | |||
29 | static inline TCGv_i32 load_cpu_offset(int offset) | ||
30 | { | 22 | { |
31 | @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) | 23 | if (level) { |
32 | return tmp; | 24 | - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
33 | } | 25 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
34 | |||
35 | +void store_reg(DisasContext *s, int reg, TCGv_i32 var); | ||
36 | + | ||
37 | void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, | ||
38 | TCGv_i32 a32, int index, MemOp opc); | ||
39 | void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, | ||
40 | @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) | ||
41 | #undef DO_GEN_LD | ||
42 | #undef DO_GEN_ST | ||
43 | |||
44 | +#if defined(CONFIG_USER_ONLY) | ||
45 | +#define IS_USER(s) 1 | ||
46 | +#else | ||
47 | +#define IS_USER(s) (s->user) | ||
48 | +#endif | ||
49 | + | ||
50 | +/* Set NZCV flags from the high 4 bits of var. */ | ||
51 | +#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) | ||
52 | + | ||
53 | #endif | ||
54 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
55 | index XXXXXXX..XXXXXXX 100644 | ||
56 | --- a/target/arm/translate.c | ||
57 | +++ b/target/arm/translate.c | ||
58 | @@ -XXX,XX +XXX,XX @@ | ||
59 | #include "translate.h" | ||
60 | #include "translate-a32.h" | ||
61 | |||
62 | -#if defined(CONFIG_USER_ONLY) | ||
63 | -#define IS_USER(s) 1 | ||
64 | -#else | ||
65 | -#define IS_USER(s) (s->user) | ||
66 | -#endif | ||
67 | - | ||
68 | /* These are TCG temporaries used only by the legacy iwMMXt decoder */ | ||
69 | static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; | ||
70 | /* These are TCG globals which alias CPUARMState fields */ | ||
71 | @@ -XXX,XX +XXX,XX @@ void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) | ||
72 | * This is used for load/store for which use of PC implies (literal), | ||
73 | * or ADD that implies ADR. | ||
74 | */ | ||
75 | -static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) | ||
76 | +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) | ||
77 | { | ||
78 | TCGv_i32 tmp = tcg_temp_new_i32(); | ||
79 | |||
80 | @@ -XXX,XX +XXX,XX @@ static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) | ||
81 | |||
82 | /* Set a CPU register. The source must be a temporary and will be | ||
83 | marked as dead. */ | ||
84 | -static void store_reg(DisasContext *s, int reg, TCGv_i32 var) | ||
85 | +void store_reg(DisasContext *s, int reg, TCGv_i32 var) | ||
86 | { | ||
87 | if (reg == 15) { | ||
88 | /* In Thumb mode, we must ignore bit 0. | ||
89 | @@ -XXX,XX +XXX,XX @@ static void store_sp_checked(DisasContext *s, TCGv_i32 var) | ||
90 | #define gen_sxtb16(var) gen_helper_sxtb16(var, var) | ||
91 | #define gen_uxtb16(var) gen_helper_uxtb16(var, var) | ||
92 | |||
93 | - | ||
94 | -static inline void gen_set_cpsr(TCGv_i32 var, uint32_t mask) | ||
95 | +void gen_set_cpsr(TCGv_i32 var, uint32_t mask) | ||
96 | { | ||
97 | TCGv_i32 tmp_mask = tcg_const_i32(mask); | ||
98 | gen_helper_cpsr_write(cpu_env, var, tmp_mask); | ||
99 | tcg_temp_free_i32(tmp_mask); | ||
100 | } | ||
101 | -/* Set NZCV flags from the high 4 bits of var. */ | ||
102 | -#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) | ||
103 | |||
104 | static void gen_exception_internal(int excp) | ||
105 | { | ||
106 | @@ -XXX,XX +XXX,XX @@ void arm_gen_test_cc(int cc, TCGLabel *label) | ||
107 | arm_free_cc(&cmp); | ||
108 | } | ||
109 | |||
110 | -static inline void gen_set_condexec(DisasContext *s) | ||
111 | +void gen_set_condexec(DisasContext *s) | ||
112 | { | ||
113 | if (s->condexec_mask) { | ||
114 | uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1); | ||
115 | @@ -XXX,XX +XXX,XX @@ static inline void gen_set_condexec(DisasContext *s) | ||
116 | } | 26 | } |
117 | } | 27 | } |
118 | 28 | ||
119 | -static inline void gen_set_pc_im(DisasContext *s, target_ulong val) | ||
120 | +void gen_set_pc_im(DisasContext *s, target_ulong val) | ||
121 | { | ||
122 | tcg_gen_movi_i32(cpu_R[15], val); | ||
123 | } | ||
124 | @@ -XXX,XX +XXX,XX @@ static void gen_exception_el(DisasContext *s, int excp, uint32_t syn, | ||
125 | } | ||
126 | |||
127 | /* Force a TB lookup after an instruction that changes the CPU state. */ | ||
128 | -static inline void gen_lookup_tb(DisasContext *s) | ||
129 | +void gen_lookup_tb(DisasContext *s) | ||
130 | { | ||
131 | tcg_gen_movi_i32(cpu_R[15], s->base.pc_next); | ||
132 | s->base.is_jmp = DISAS_EXIT; | ||
133 | @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) | ||
134 | /* | ||
135 | * Return the offset of a "full" NEON Dreg. | ||
136 | */ | ||
137 | -static long neon_full_reg_offset(unsigned reg) | ||
138 | +long neon_full_reg_offset(unsigned reg) | ||
139 | { | ||
140 | return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); | ||
141 | } | ||
142 | @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp memop) | ||
143 | } | ||
144 | |||
145 | /* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ | ||
146 | -static long vfp_reg_offset(bool dp, unsigned reg) | ||
147 | +long vfp_reg_offset(bool dp, unsigned reg) | ||
148 | { | ||
149 | if (dp) { | ||
150 | return neon_element_offset(reg, 0, MO_64); | ||
151 | -- | 29 | -- |
152 | 2.20.1 | 30 | 2.20.1 |
153 | 31 | ||
154 | 32 | diff view generated by jsdifflib |
1 | On some boards, SCC config register CFG0 bit 0 controls whether | 1 | In do_ldst(), the calculation of the offset needs to be based on the |
---|---|---|---|
2 | parts of the board memory map are remapped. Support this with: | 2 | size of the memory access, not the size of the elements in the |
3 | * a device property scc-cfg0 so the board can specify the | 3 | vector. This meant we were getting it wrong for the widening and |
4 | initial value of the CFG0 register | 4 | narrowing variants of the various VLDR and VSTR insns. |
5 | * an outbound GPIO line which tracks bit 0 and which the board | ||
6 | can wire up to provide the remapping | ||
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: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
10 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 8 | Message-id: 20210628135835.6690-2-peter.maydell@linaro.org |
11 | Message-id: 20210504120912.23094-3-peter.maydell@linaro.org | ||
12 | --- | 9 | --- |
13 | include/hw/misc/mps2-scc.h | 9 +++++++++ | 10 | target/arm/translate-mve.c | 17 +++++++++-------- |
14 | hw/misc/mps2-scc.c | 13 ++++++++++--- | 11 | 1 file changed, 9 insertions(+), 8 deletions(-) |
15 | 2 files changed, 19 insertions(+), 3 deletions(-) | ||
16 | 12 | ||
17 | diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h | 13 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c |
18 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/include/hw/misc/mps2-scc.h | 15 | --- a/target/arm/translate-mve.c |
20 | +++ b/include/hw/misc/mps2-scc.h | 16 | +++ b/target/arm/translate-mve.c |
21 | @@ -XXX,XX +XXX,XX @@ | 17 | @@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s) |
22 | * + QOM property "scc-cfg4": value of the read-only CFG4 register | 18 | } |
23 | * + QOM property "scc-aid": value of the read-only SCC_AID register | ||
24 | * + QOM property "scc-id": value of the read-only SCC_ID register | ||
25 | + * + QOM property "scc-cfg0": reset value of the CFG0 register | ||
26 | * + QOM property array "oscclk": reset values of the OSCCLK registers | ||
27 | * (which are accessed via the SYS_CFG channel provided by this device) | ||
28 | + * + named GPIO output "remap": this tracks the value of CFG0 register | ||
29 | + * bit 0. Boards where this bit controls memory remapping should | ||
30 | + * connect this GPIO line to a function performing that mapping. | ||
31 | + * Boards where bit 0 has no special function should leave the GPIO | ||
32 | + * output disconnected. | ||
33 | */ | ||
34 | #ifndef MPS2_SCC_H | ||
35 | #define MPS2_SCC_H | ||
36 | @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { | ||
37 | uint32_t num_oscclk; | ||
38 | uint32_t *oscclk; | ||
39 | uint32_t *oscclk_reset; | ||
40 | + uint32_t cfg0_reset; | ||
41 | + | ||
42 | + qemu_irq remap; | ||
43 | }; | ||
44 | |||
45 | #endif | ||
46 | diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/hw/misc/mps2-scc.c | ||
49 | +++ b/hw/misc/mps2-scc.c | ||
50 | @@ -XXX,XX +XXX,XX @@ | ||
51 | #include "qemu/bitops.h" | ||
52 | #include "trace.h" | ||
53 | #include "hw/sysbus.h" | ||
54 | +#include "hw/irq.h" | ||
55 | #include "migration/vmstate.h" | ||
56 | #include "hw/registerfields.h" | ||
57 | #include "hw/misc/mps2-scc.h" | ||
58 | @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, | ||
59 | switch (offset) { | ||
60 | case A_CFG0: | ||
61 | /* | ||
62 | - * TODO on some boards bit 0 controls RAM remapping; | ||
63 | - * on others bit 1 is CPU_WAIT. | ||
64 | + * On some boards bit 0 controls board-specific remapping; | ||
65 | + * we always reflect bit 0 in the 'remap' GPIO output line, | ||
66 | + * and let the board wire it up or not as it chooses. | ||
67 | + * TODO on some boards bit 1 is CPU_WAIT. | ||
68 | */ | ||
69 | s->cfg0 = value; | ||
70 | + qemu_set_irq(s->remap, s->cfg0 & 1); | ||
71 | break; | ||
72 | case A_CFG1: | ||
73 | s->cfg1 = value; | ||
74 | @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) | ||
75 | int i; | ||
76 | |||
77 | trace_mps2_scc_reset(); | ||
78 | - s->cfg0 = 0; | ||
79 | + s->cfg0 = s->cfg0_reset; | ||
80 | s->cfg1 = 0; | ||
81 | s->cfg2 = 0; | ||
82 | s->cfg5 = 0; | ||
83 | @@ -XXX,XX +XXX,XX @@ static void mps2_scc_init(Object *obj) | ||
84 | |||
85 | memory_region_init_io(&s->iomem, obj, &mps2_scc_ops, s, "mps2-scc", 0x1000); | ||
86 | sysbus_init_mmio(sbd, &s->iomem); | ||
87 | + qdev_init_gpio_out_named(DEVICE(obj), &s->remap, "remap", 1); | ||
88 | } | 19 | } |
89 | 20 | ||
90 | static void mps2_scc_realize(DeviceState *dev, Error **errp) | 21 | -static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) |
91 | @@ -XXX,XX +XXX,XX @@ static Property mps2_scc_properties[] = { | 22 | +static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn, |
92 | DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), | 23 | + unsigned msize) |
93 | DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), | 24 | { |
94 | DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), | 25 | TCGv_i32 addr; |
95 | + /* Reset value for CFG0 register */ | 26 | uint32_t offset; |
96 | + DEFINE_PROP_UINT32("scc-cfg0", MPS2SCC, cfg0_reset, 0), | 27 | @@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) |
97 | /* | 28 | return true; |
98 | * These are the initial settings for the source clocks on the board. | 29 | } |
99 | * In hardware they can be configured via a config file read by the | 30 | |
31 | - offset = a->imm << a->size; | ||
32 | + offset = a->imm << msize; | ||
33 | if (!a->a) { | ||
34 | offset = -offset; | ||
35 | } | ||
36 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a) | ||
37 | { gen_helper_mve_vstrw, gen_helper_mve_vldrw }, | ||
38 | { NULL, NULL } | ||
39 | }; | ||
40 | - return do_ldst(s, a, ldstfns[a->size][a->l]); | ||
41 | + return do_ldst(s, a, ldstfns[a->size][a->l], a->size); | ||
42 | } | ||
43 | |||
44 | -#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST) \ | ||
45 | +#define DO_VLDST_WIDE_NARROW(OP, SLD, ULD, ST, MSIZE) \ | ||
46 | static bool trans_##OP(DisasContext *s, arg_VLDR_VSTR *a) \ | ||
47 | { \ | ||
48 | static MVEGenLdStFn * const ldstfns[2][2] = { \ | ||
49 | { gen_helper_mve_##ST, gen_helper_mve_##SLD }, \ | ||
50 | { NULL, gen_helper_mve_##ULD }, \ | ||
51 | }; \ | ||
52 | - return do_ldst(s, a, ldstfns[a->u][a->l]); \ | ||
53 | + return do_ldst(s, a, ldstfns[a->u][a->l], MSIZE); \ | ||
54 | } | ||
55 | |||
56 | -DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h) | ||
57 | -DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w) | ||
58 | -DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w) | ||
59 | +DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) | ||
60 | +DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) | ||
61 | +DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) | ||
62 | |||
63 | static bool trans_VDUP(DisasContext *s, arg_VDUP *a) | ||
64 | { | ||
100 | -- | 65 | -- |
101 | 2.20.1 | 66 | 2.20.1 |
102 | 67 | ||
103 | 68 | diff view generated by jsdifflib |
1 | Make dis-asm.h handle being included outside an 'extern "C"' block; | 1 | The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH |
---|---|---|---|
2 | this allows us to remove the 'extern "C"' blocks that our two C++ | 2 | insns had some bugs: |
3 | files that include it are using. | 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 | ||
4 | 9 | ||
10 | In particular, fixing the second of these allows us to recast | ||
11 | the implementation to avoid 128-bit arithmetic entirely. | ||
12 | |||
13 | Since the element size here is always 4, we can also drop the | ||
14 | parameterization of ESIZE to make the code a little more readable. | ||
15 | |||
16 | Suggested-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 18 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
19 | Message-id: 20210628135835.6690-3-peter.maydell@linaro.org | ||
7 | --- | 20 | --- |
8 | include/disas/dis-asm.h | 12 ++++++++++-- | 21 | target/arm/mve_helper.c | 38 +++++++++++++++++++++----------------- |
9 | disas/arm-a64.cc | 2 -- | 22 | 1 file changed, 21 insertions(+), 17 deletions(-) |
10 | disas/nanomips.cpp | 2 -- | ||
11 | 3 files changed, 10 insertions(+), 6 deletions(-) | ||
12 | 23 | ||
13 | diff --git a/include/disas/dis-asm.h b/include/disas/dis-asm.h | 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/include/disas/dis-asm.h | 26 | --- a/target/arm/mve_helper.c |
16 | +++ b/include/disas/dis-asm.h | 27 | +++ b/target/arm/mve_helper.c |
17 | @@ -XXX,XX +XXX,XX @@ | ||
18 | #ifndef DISAS_DIS_ASM_H | ||
19 | #define DISAS_DIS_ASM_H | ||
20 | |||
21 | +#include "qemu/bswap.h" | ||
22 | + | ||
23 | +#ifdef __cplusplus | ||
24 | +extern "C" { | ||
25 | +#endif | ||
26 | + | ||
27 | typedef void *PTR; | ||
28 | typedef uint64_t bfd_vma; | ||
29 | typedef int64_t bfd_signed_vma; | ||
30 | @@ -XXX,XX +XXX,XX @@ bool cap_disas_plugin(disassemble_info *info, uint64_t pc, size_t size); | ||
31 | |||
32 | /* from libbfd */ | ||
33 | |||
34 | -#include "qemu/bswap.h" | ||
35 | - | ||
36 | static inline bfd_vma bfd_getl64(const bfd_byte *addr) | ||
37 | { | ||
38 | return ldq_le_p(addr); | ||
39 | @@ -XXX,XX +XXX,XX @@ static inline bfd_vma bfd_getb16(const bfd_byte *addr) | ||
40 | |||
41 | typedef bool bfd_boolean; | ||
42 | |||
43 | +#ifdef __cplusplus | ||
44 | +} | ||
45 | +#endif | ||
46 | + | ||
47 | #endif /* DISAS_DIS_ASM_H */ | ||
48 | diff --git a/disas/arm-a64.cc b/disas/arm-a64.cc | ||
49 | index XXXXXXX..XXXXXXX 100644 | ||
50 | --- a/disas/arm-a64.cc | ||
51 | +++ b/disas/arm-a64.cc | ||
52 | @@ -XXX,XX +XXX,XX @@ | 28 | @@ -XXX,XX +XXX,XX @@ |
53 | */ | 29 | */ |
54 | 30 | ||
55 | #include "qemu/osdep.h" | 31 | #include "qemu/osdep.h" |
56 | -extern "C" { | 32 | -#include "qemu/int128.h" |
57 | #include "disas/dis-asm.h" | 33 | #include "cpu.h" |
58 | -} | 34 | #include "internals.h" |
59 | 35 | #include "vec_internal.h" | |
60 | #include "vixl/a64/disasm-a64.h" | 36 | @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) |
61 | 37 | DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) | |
62 | diff --git a/disas/nanomips.cpp b/disas/nanomips.cpp | 38 | |
63 | index XXXXXXX..XXXXXXX 100644 | 39 | /* |
64 | --- a/disas/nanomips.cpp | 40 | - * Rounding multiply add long dual accumulate high: we must keep |
65 | +++ b/disas/nanomips.cpp | 41 | - * a 72-bit internal accumulator value and return the top 64 bits. |
66 | @@ -XXX,XX +XXX,XX @@ | 42 | + * Rounding multiply add long dual accumulate high. In the pseudocode |
43 | + * this is implemented with a 72-bit internal accumulator value of which | ||
44 | + * the top 64 bits are returned. We optimize this to avoid having to | ||
45 | + * use 128-bit arithmetic -- we can do this because the 74-bit accumulator | ||
46 | + * is squashed back into 64-bits after each beat. | ||
67 | */ | 47 | */ |
68 | 48 | -#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \ | |
69 | #include "qemu/osdep.h" | 49 | +#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \ |
70 | -extern "C" { | 50 | uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ |
71 | #include "disas/dis-asm.h" | 51 | void *vm, uint64_t a) \ |
72 | -} | 52 | { \ |
73 | 53 | uint16_t mask = mve_element_mask(env); \ | |
74 | #include <cstring> | 54 | unsigned e; \ |
75 | #include <stdexcept> | 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) \ | ||
76 | -- | 98 | -- |
77 | 2.20.1 | 99 | 2.20.1 |
78 | 100 | ||
79 | 101 | diff view generated by jsdifflib |
1 | Switch translate-neon.c.inc from being #included into translate.c | 1 | The function asimd_imm_const() in translate-neon.c is an |
---|---|---|---|
2 | to being its own compilation unit. | 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. | ||
3 | 5 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210430132740.10391-14-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-4-peter.maydell@linaro.org |
8 | --- | 9 | --- |
9 | target/arm/translate-a32.h | 3 +++ | 10 | target/arm/translate.h | 16 ++++++++++ |
10 | .../arm/{translate-neon.c.inc => translate-neon.c} | 12 +++++++----- | 11 | target/arm/translate-neon.c | 63 ------------------------------------- |
11 | target/arm/translate.c | 3 --- | 12 | target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++ |
12 | target/arm/meson.build | 7 ++++--- | 13 | 3 files changed, 73 insertions(+), 63 deletions(-) |
13 | 4 files changed, 14 insertions(+), 11 deletions(-) | ||
14 | rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) | ||
15 | 14 | ||
16 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 15 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
17 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/target/arm/translate-a32.h | 17 | --- a/target/arm/translate.h |
19 | +++ b/target/arm/translate-a32.h | 18 | +++ b/target/arm/translate.h |
20 | @@ -XXX,XX +XXX,XX @@ | 19 | @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) |
21 | bool disas_m_nocp(DisasContext *dc, uint32_t insn); | 20 | return opc | s->be_data; |
22 | bool disas_vfp(DisasContext *s, uint32_t insn); | 21 | } |
23 | bool disas_vfp_uncond(DisasContext *s, uint32_t insn); | 22 | |
24 | +bool disas_neon_dp(DisasContext *s, uint32_t insn); | 23 | +/** |
25 | +bool disas_neon_ls(DisasContext *s, uint32_t insn); | 24 | + * asimd_imm_const: Expand an encoded SIMD constant value |
26 | +bool disas_neon_shared(DisasContext *s, uint32_t insn); | 25 | + * |
27 | 26 | + * Expand a SIMD constant value. This is essentially the pseudocode | |
28 | void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); | 27 | + * AdvSIMDExpandImm, except that we also perform the boolean NOT needed for |
29 | void arm_gen_condlabel(DisasContext *s); | 28 | + * VMVN and VBIC (when cmode < 14 && op == 1). |
30 | diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c | 29 | + * |
31 | similarity index 99% | 30 | + * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; |
32 | rename from target/arm/translate-neon.c.inc | 31 | + * callers must catch this. |
33 | rename to target/arm/translate-neon.c | 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 | ||
34 | index XXXXXXX..XXXXXXX 100644 | 41 | index XXXXXXX..XXXXXXX 100644 |
35 | --- a/target/arm/translate-neon.c.inc | 42 | --- a/target/arm/translate-neon.c |
36 | +++ b/target/arm/translate-neon.c | 43 | +++ b/target/arm/translate-neon.c |
37 | @@ -XXX,XX +XXX,XX @@ | 44 | @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) |
38 | * License along with this library; if not, see <http://www.gnu.org/licenses/>. | 45 | DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) |
39 | */ | 46 | DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) |
40 | 47 | ||
41 | -/* | 48 | -static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) |
42 | - * This file is intended to be included from translate.c; it uses | 49 | -{ |
43 | - * some macros and definitions provided by that file. | 50 | - /* |
44 | - * It might be possible to convert it to a standalone .c file eventually. | 51 | - * Expand the encoded constant. |
45 | - */ | 52 | - * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. |
46 | +#include "qemu/osdep.h" | 53 | - * We choose to not special-case this and will behave as if a |
47 | +#include "tcg/tcg-op.h" | 54 | - * valid constant encoding of 0 had been given. |
48 | +#include "tcg/tcg-op-gvec.h" | 55 | - * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. |
49 | +#include "exec/exec-all.h" | 56 | - */ |
50 | +#include "exec/gen-icount.h" | 57 | - switch (cmode) { |
51 | +#include "translate.h" | 58 | - case 0: case 1: |
52 | +#include "translate-a32.h" | 59 | - /* no-op */ |
53 | 60 | - break; | |
54 | static inline int plus1(DisasContext *s, int x) | 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) | ||
55 | { | 113 | { |
56 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 114 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
57 | index XXXXXXX..XXXXXXX 100644 | 115 | index XXXXXXX..XXXXXXX 100644 |
58 | --- a/target/arm/translate.c | 116 | --- a/target/arm/translate.c |
59 | +++ b/target/arm/translate.c | 117 | +++ b/target/arm/translate.c |
60 | @@ -XXX,XX +XXX,XX @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) | 118 | @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) |
61 | 119 | a64_translate_init(); | |
62 | #define ARM_CP_RW_BIT (1 << 20) | 120 | } |
63 | 121 | ||
64 | -/* Include the Neon decoder */ | 122 | +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) |
65 | -#include "translate-neon.c.inc" | 123 | +{ |
66 | - | 124 | + /* Expand the encoded constant as per AdvSIMDExpandImm pseudocode */ |
67 | static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) | 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) | ||
68 | { | 181 | { |
69 | tcg_gen_ld_i64(var, cpu_env, offsetof(CPUARMState, iwmmxt.regs[reg])); | ||
70 | diff --git a/target/arm/meson.build b/target/arm/meson.build | ||
71 | index XXXXXXX..XXXXXXX 100644 | ||
72 | --- a/target/arm/meson.build | ||
73 | +++ b/target/arm/meson.build | ||
74 | @@ -XXX,XX +XXX,XX @@ | ||
75 | gen = [ | ||
76 | decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), | ||
77 | - decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), | ||
78 | - decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), | ||
79 | - decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), | ||
80 | + decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), | ||
81 | + decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), | ||
82 | + decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), | ||
83 | decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), | ||
84 | decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), | ||
85 | decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), | ||
86 | @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( | ||
87 | 'tlb_helper.c', | ||
88 | 'translate.c', | ||
89 | 'translate-m-nocp.c', | ||
90 | + 'translate-neon.c', | ||
91 | 'translate-vfp.c', | ||
92 | 'vec_helper.c', | ||
93 | 'vfp_helper.c', | ||
94 | -- | 182 | -- |
95 | 2.20.1 | 183 | 2.20.1 |
96 | 184 | ||
97 | 185 | diff view generated by jsdifflib |
1 | The unallocated_encoding() function is the same in both | 1 | The A64 AdvSIMD modified-immediate grouping uses almost the same |
---|---|---|---|
2 | translate-a64.c and translate.c; make the translate.c function global | 2 | constant encoding that A32 Neon does; reuse asimd_imm_const() (to |
3 | and drop the translate-a64.c version. To do this we need to also | 3 | which we add the AArch64-specific case for cmode 15 op 1) instead of |
4 | share gen_exception_insn(), which currently exists in two slightly | 4 | reimplementing it all. |
5 | different versions for A32 and A64: merge those into a single | ||
6 | function that can work for both. | ||
7 | |||
8 | This will be useful for splitting up translate.c, which will require | ||
9 | unallocated_encoding() to no longer be file-local. It's also | ||
10 | hopefully less confusing to have only one version of the function | ||
11 | rather than two. | ||
12 | 5 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
15 | Message-id: 20210430132740.10391-3-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-5-peter.maydell@linaro.org |
16 | --- | 9 | --- |
17 | target/arm/translate-a64.h | 2 -- | 10 | target/arm/translate.h | 3 +- |
18 | target/arm/translate.h | 3 +++ | 11 | target/arm/translate-a64.c | 86 ++++---------------------------------- |
19 | target/arm/translate-a64.c | 15 --------------- | 12 | target/arm/translate.c | 17 +++++++- |
20 | target/arm/translate.c | 14 +++++++++----- | 13 | 3 files changed, 24 insertions(+), 82 deletions(-) |
21 | 4 files changed, 12 insertions(+), 22 deletions(-) | ||
22 | 14 | ||
23 | diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | ||
25 | --- a/target/arm/translate-a64.h | ||
26 | +++ b/target/arm/translate-a64.h | ||
27 | @@ -XXX,XX +XXX,XX @@ | ||
28 | #ifndef TARGET_ARM_TRANSLATE_A64_H | ||
29 | #define TARGET_ARM_TRANSLATE_A64_H | ||
30 | |||
31 | -void unallocated_encoding(DisasContext *s); | ||
32 | - | ||
33 | #define unsupported_encoding(s, insn) \ | ||
34 | do { \ | ||
35 | qemu_log_mask(LOG_UNIMP, \ | ||
36 | diff --git a/target/arm/translate.h b/target/arm/translate.h | 15 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
37 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
38 | --- a/target/arm/translate.h | 17 | --- a/target/arm/translate.h |
39 | +++ b/target/arm/translate.h | 18 | +++ b/target/arm/translate.h |
40 | @@ -XXX,XX +XXX,XX @@ void arm_free_cc(DisasCompare *cmp); | 19 | @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) |
41 | void arm_jump_cc(DisasCompare *cmp, TCGLabel *label); | 20 | * VMVN and VBIC (when cmode < 14 && op == 1). |
42 | void arm_gen_test_cc(int cc, TCGLabel *label); | 21 | * |
43 | MemOp pow2_align(unsigned i); | 22 | * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; |
44 | +void unallocated_encoding(DisasContext *s); | 23 | - * callers must catch this. |
45 | +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, | 24 | + * callers must catch this; we return the 64-bit constant value defined |
46 | + uint32_t syn, uint32_t target_el); | 25 | + * for AArch64. |
47 | 26 | * | |
48 | /* Return state of Alternate Half-precision flag, caller frees result */ | 27 | * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but |
49 | static inline TCGv_i32 get_ahp_flag(void) | 28 | * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; |
50 | 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 |
51 | index XXXXXXX..XXXXXXX 100644 | 30 | index XXXXXXX..XXXXXXX 100644 |
52 | --- a/target/arm/translate-a64.c | 31 | --- a/target/arm/translate-a64.c |
53 | +++ b/target/arm/translate-a64.c | 32 | +++ b/target/arm/translate-a64.c |
54 | @@ -XXX,XX +XXX,XX @@ static void gen_exception_internal_insn(DisasContext *s, uint64_t pc, int excp) | 33 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
55 | s->base.is_jmp = DISAS_NORETURN; | 34 | { |
56 | } | 35 | int rd = extract32(insn, 0, 5); |
57 | 36 | int cmode = extract32(insn, 12, 4); | |
58 | -static void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, | 37 | - int cmode_3_1 = extract32(cmode, 1, 3); |
59 | - uint32_t syndrome, uint32_t target_el) | 38 | - int cmode_0 = extract32(cmode, 0, 1); |
60 | -{ | 39 | int o2 = extract32(insn, 11, 1); |
61 | - gen_a64_set_pc_im(pc); | 40 | uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5); |
62 | - gen_exception(excp, syndrome, target_el); | 41 | bool is_neg = extract32(insn, 29, 1); |
63 | - s->base.is_jmp = DISAS_NORETURN; | 42 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
64 | -} | 43 | return; |
44 | } | ||
45 | |||
46 | - /* See AdvSIMDExpandImm() in ARM ARM */ | ||
47 | - switch (cmode_3_1) { | ||
48 | - case 0: /* Replicate(Zeros(24):imm8, 2) */ | ||
49 | - case 1: /* Replicate(Zeros(16):imm8:Zeros(8), 2) */ | ||
50 | - case 2: /* Replicate(Zeros(8):imm8:Zeros(16), 2) */ | ||
51 | - case 3: /* Replicate(imm8:Zeros(24), 2) */ | ||
52 | - { | ||
53 | - int shift = cmode_3_1 * 8; | ||
54 | - imm = bitfield_replicate(abcdefgh << shift, 32); | ||
55 | - break; | ||
56 | - } | ||
57 | - case 4: /* Replicate(Zeros(8):imm8, 4) */ | ||
58 | - case 5: /* Replicate(imm8:Zeros(8), 4) */ | ||
59 | - { | ||
60 | - int shift = (cmode_3_1 & 0x1) * 8; | ||
61 | - imm = bitfield_replicate(abcdefgh << shift, 16); | ||
62 | - break; | ||
63 | - } | ||
64 | - case 6: | ||
65 | - if (cmode_0) { | ||
66 | - /* Replicate(Zeros(8):imm8:Ones(16), 2) */ | ||
67 | - imm = (abcdefgh << 16) | 0xffff; | ||
68 | - } else { | ||
69 | - /* Replicate(Zeros(16):imm8:Ones(8), 2) */ | ||
70 | - imm = (abcdefgh << 8) | 0xff; | ||
71 | - } | ||
72 | - imm = bitfield_replicate(imm, 32); | ||
73 | - break; | ||
74 | - case 7: | ||
75 | - if (!cmode_0 && !is_neg) { | ||
76 | - imm = bitfield_replicate(abcdefgh, 8); | ||
77 | - } else if (!cmode_0 && is_neg) { | ||
78 | - int i; | ||
79 | - imm = 0; | ||
80 | - for (i = 0; i < 8; i++) { | ||
81 | - if ((abcdefgh) & (1 << i)) { | ||
82 | - imm |= 0xffULL << (i * 8); | ||
83 | - } | ||
84 | - } | ||
85 | - } else if (cmode_0) { | ||
86 | - if (is_neg) { | ||
87 | - imm = (abcdefgh & 0x3f) << 48; | ||
88 | - if (abcdefgh & 0x80) { | ||
89 | - imm |= 0x8000000000000000ULL; | ||
90 | - } | ||
91 | - if (abcdefgh & 0x40) { | ||
92 | - imm |= 0x3fc0000000000000ULL; | ||
93 | - } else { | ||
94 | - imm |= 0x4000000000000000ULL; | ||
95 | - } | ||
96 | - } else { | ||
97 | - if (o2) { | ||
98 | - /* FMOV (vector, immediate) - half-precision */ | ||
99 | - imm = vfp_expand_imm(MO_16, abcdefgh); | ||
100 | - /* now duplicate across the lanes */ | ||
101 | - imm = bitfield_replicate(imm, 16); | ||
102 | - } else { | ||
103 | - imm = (abcdefgh & 0x3f) << 19; | ||
104 | - if (abcdefgh & 0x80) { | ||
105 | - imm |= 0x80000000; | ||
106 | - } | ||
107 | - if (abcdefgh & 0x40) { | ||
108 | - imm |= 0x3e000000; | ||
109 | - } else { | ||
110 | - imm |= 0x40000000; | ||
111 | - } | ||
112 | - imm |= (imm << 32); | ||
113 | - } | ||
114 | - } | ||
115 | - } | ||
116 | - break; | ||
117 | - default: | ||
118 | - g_assert_not_reached(); | ||
119 | - } | ||
65 | - | 120 | - |
66 | static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syndrome) | 121 | - if (cmode_3_1 != 7 && is_neg) { |
67 | { | 122 | - imm = ~imm; |
68 | TCGv_i32 tcg_syn; | 123 | + if (cmode == 15 && o2 && !is_neg) { |
69 | @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) | 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); | ||
70 | } | 130 | } |
71 | } | 131 | |
72 | 132 | if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) { | |
73 | -void unallocated_encoding(DisasContext *s) | ||
74 | -{ | ||
75 | - /* Unallocated and reserved encodings are uncategorized */ | ||
76 | - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), | ||
77 | - default_exception_el(s)); | ||
78 | -} | ||
79 | - | ||
80 | static void init_tmp_a64_array(DisasContext *s) | ||
81 | { | ||
82 | #ifdef CONFIG_DEBUG_TCG | ||
83 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 133 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
84 | index XXXXXXX..XXXXXXX 100644 | 134 | index XXXXXXX..XXXXXXX 100644 |
85 | --- a/target/arm/translate.c | 135 | --- a/target/arm/translate.c |
86 | +++ b/target/arm/translate.c | 136 | +++ b/target/arm/translate.c |
87 | @@ -XXX,XX +XXX,XX @@ static void gen_exception_internal_insn(DisasContext *s, uint32_t pc, int excp) | 137 | @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) |
88 | s->base.is_jmp = DISAS_NORETURN; | 138 | case 14: |
89 | } | 139 | if (op) { |
90 | 140 | /* | |
91 | -static void gen_exception_insn(DisasContext *s, uint32_t pc, int excp, | 141 | - * This is the only case where the top and bottom 32 bits |
92 | - int syn, uint32_t target_el) | 142 | - * of the encoded constant differ. |
93 | +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, | 143 | + * This and cmode == 15 op == 1 are the only cases where |
94 | + uint32_t syn, uint32_t target_el) | 144 | + * the top and bottom 32 bits of the encoded constant differ. |
95 | { | 145 | */ |
96 | - gen_set_condexec(s); | 146 | uint64_t imm64 = 0; |
97 | - gen_set_pc_im(s, pc); | 147 | int n; |
98 | + if (s->aarch64) { | 148 | @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) |
99 | + gen_a64_set_pc_im(pc); | 149 | imm |= (imm << 8) | (imm << 16) | (imm << 24); |
100 | + } else { | 150 | break; |
101 | + gen_set_condexec(s); | 151 | case 15: |
102 | + gen_set_pc_im(s, pc); | 152 | + if (op) { |
103 | + } | 153 | + /* Reserved encoding for AArch32; valid for AArch64 */ |
104 | gen_exception(excp, syn, target_el); | 154 | + uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48; |
105 | s->base.is_jmp = DISAS_NORETURN; | 155 | + if (imm & 0x80) { |
106 | } | 156 | + imm64 |= 0x8000000000000000ULL; |
107 | @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syn) | 157 | + } |
108 | s->base.is_jmp = DISAS_NORETURN; | 158 | + if (imm & 0x40) { |
109 | } | 159 | + imm64 |= 0x3fc0000000000000ULL; |
110 | 160 | + } else { | |
111 | -static void unallocated_encoding(DisasContext *s) | 161 | + imm64 |= 0x4000000000000000ULL; |
112 | +void unallocated_encoding(DisasContext *s) | 162 | + } |
113 | { | 163 | + return imm64; |
114 | /* Unallocated and reserved encodings are uncategorized */ | 164 | + } |
115 | gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), | 165 | imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) |
166 | | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); | ||
167 | break; | ||
116 | -- | 168 | -- |
117 | 2.20.1 | 169 | 2.20.1 |
118 | 170 | ||
119 | 171 | diff view generated by jsdifflib |
1 | The omap_mmc_reset() function resets its SD card via | 1 | Use dup_const() instead of bitfield_replicate() in |
---|---|---|---|
2 | device_legacy_reset(). We know that the SD card does not have a qbus | 2 | disas_simd_mod_imm(). |
3 | of its own, so the new device_cold_reset() function (which resets | 3 | |
4 | both the device and its child buses) is equivalent here to | 4 | (We can't replace the other use of bitfield_replicate() in this file, |
5 | device_legacy_reset() and we can just switch to the new API. | 5 | in logic_imm_decode_wmask(), because that location needs to handle 2 |
6 | and 4 bit elements, which dup_const() cannot.) | ||
6 | 7 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
9 | Message-id: 20210430222348.8514-1-peter.maydell@linaro.org | 10 | Message-id: 20210628135835.6690-6-peter.maydell@linaro.org |
10 | --- | 11 | --- |
11 | hw/sd/omap_mmc.c | 2 +- | 12 | target/arm/translate-a64.c | 2 +- |
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | 13 | 1 file changed, 1 insertion(+), 1 deletion(-) |
13 | 14 | ||
14 | diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c | 15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c |
15 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/hw/sd/omap_mmc.c | 17 | --- a/target/arm/translate-a64.c |
17 | +++ b/hw/sd/omap_mmc.c | 18 | +++ b/target/arm/translate-a64.c |
18 | @@ -XXX,XX +XXX,XX @@ void omap_mmc_reset(struct omap_mmc_s *host) | 19 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
19 | * into any bus, and we must reset it manually. When omap_mmc is | 20 | /* FMOV (vector, immediate) - half-precision */ |
20 | * QOMified this must move into the QOM reset function. | 21 | imm = vfp_expand_imm(MO_16, abcdefgh); |
21 | */ | 22 | /* now duplicate across the lanes */ |
22 | - device_legacy_reset(DEVICE(host->card)); | 23 | - imm = bitfield_replicate(imm, 16); |
23 | + device_cold_reset(DEVICE(host->card)); | 24 | + imm = dup_const(MO_16, imm); |
24 | } | 25 | } else { |
25 | 26 | imm = asimd_imm_const(abcdefgh, cmode, is_neg); | |
26 | static uint64_t omap_mmc_read(void *opaque, hwaddr offset, | 27 | } |
27 | -- | 28 | -- |
28 | 2.20.1 | 29 | 2.20.1 |
29 | 30 | ||
30 | 31 | diff view generated by jsdifflib |
1 | The MPS2 SCC device doesn't have any documentation of its properties; | 1 | Implement the MVE logical-immediate insns (VMOV, VMVN, |
---|---|---|---|
2 | add a "QEMU interface" format comment describing them. | 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. | ||
3 | 5 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20210504120912.23094-2-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-7-peter.maydell@linaro.org |
7 | --- | 9 | --- |
8 | include/hw/misc/mps2-scc.h | 12 ++++++++++++ | 10 | target/arm/helper-mve.h | 4 +++ |
9 | 1 file changed, 12 insertions(+) | 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(+) | ||
10 | 15 | ||
11 | diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
12 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/include/hw/misc/mps2-scc.h | 18 | --- a/target/arm/helper-mve.h |
14 | +++ b/include/hw/misc/mps2-scc.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 | ||
15 | @@ -XXX,XX +XXX,XX @@ | 32 | @@ -XXX,XX +XXX,XX @@ |
16 | * (at your option) any later version. | 33 | # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit |
17 | */ | 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) | ||
18 | 78 | ||
19 | +/* | 79 | +/* |
20 | + * This is a model of the Serial Communication Controller (SCC) | 80 | + * 1 operand immediates: Vda is destination and possibly also one source. |
21 | + * block found in most MPS FPGA images. | 81 | + * All these insns work at 64-bit widths. |
22 | + * | ||
23 | + * QEMU interface: | ||
24 | + * + sysbus MMIO region 0: the register bank | ||
25 | + * + QOM property "scc-cfg4": value of the read-only CFG4 register | ||
26 | + * + QOM property "scc-aid": value of the read-only SCC_AID register | ||
27 | + * + QOM property "scc-id": value of the read-only SCC_ID register | ||
28 | + * + QOM property array "oscclk": reset values of the OSCCLK registers | ||
29 | + * (which are accessed via the SYS_CFG channel provided by this device) | ||
30 | + */ | 82 | + */ |
31 | #ifndef MPS2_SCC_H | 83 | +#define DO_1OP_IMM(OP, FN) \ |
32 | #define MPS2_SCC_H | 84 | + void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \ |
33 | 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 | +} | ||
34 | -- | 171 | -- |
35 | 2.20.1 | 172 | 2.20.1 |
36 | 173 | ||
37 | 174 | diff view generated by jsdifflib |
1 | Make the remaining functions needed by the translate-neon code | 1 | Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL |
---|---|---|---|
2 | global. | 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. | ||
3 | 6 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210430132740.10391-13-peter.maydell@linaro.org | 9 | Message-id: 20210628135835.6690-8-peter.maydell@linaro.org |
8 | --- | 10 | --- |
9 | target/arm/translate-a32.h | 8 ++++++++ | 11 | target/arm/helper-mve.h | 16 +++++++++++ |
10 | target/arm/translate.c | 10 ++-------- | 12 | target/arm/mve.decode | 23 +++++++++++++++ |
11 | 2 files changed, 10 insertions(+), 8 deletions(-) | 13 | target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++ |
12 | 14 | target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++ | |
13 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 15 | 4 files changed, 147 insertions(+) |
14 | index XXXXXXX..XXXXXXX 100644 | 16 | |
15 | --- a/target/arm/translate-a32.h | 17 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
16 | +++ b/target/arm/translate-a32.h | 18 | index XXXXXXX..XXXXXXX 100644 |
17 | @@ -XXX,XX +XXX,XX @@ void gen_set_pc_im(DisasContext *s, target_ulong val); | 19 | --- a/target/arm/helper-mve.h |
18 | void gen_lookup_tb(DisasContext *s); | 20 | +++ b/target/arm/helper-mve.h |
19 | long vfp_reg_offset(bool dp, unsigned reg); | 21 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
20 | long neon_full_reg_offset(unsigned reg); | 22 | DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) |
21 | +long neon_element_offset(int reg, int element, MemOp memop); | 23 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) |
22 | +void gen_rev16(TCGv_i32 dest, TCGv_i32 var); | 24 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) |
23 | 25 | + | |
24 | static inline TCGv_i32 load_cpu_offset(int offset) | 26 | +DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
25 | { | 27 | +DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
26 | @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) | 28 | +DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
27 | /* Set NZCV flags from the high 4 bits of var. */ | 29 | + |
28 | #define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) | 30 | +DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
29 | 31 | +DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
30 | +/* Swap low and high halfwords. */ | 32 | +DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
31 | +static inline void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) | 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) | ||
32 | +{ | 177 | +{ |
33 | + tcg_gen_rotri_i32(dest, var, 16); | 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; | ||
34 | +} | 206 | +} |
35 | + | 207 | + |
36 | #endif | 208 | +#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \ |
37 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 209 | + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
38 | index XXXXXXX..XXXXXXX 100644 | 210 | + { \ |
39 | --- a/target/arm/translate.c | 211 | + static MVEGenTwoOpShiftFn * const fns[] = { \ |
40 | +++ b/target/arm/translate.c | 212 | + gen_helper_mve_##FN##b, \ |
41 | @@ -XXX,XX +XXX,XX @@ static void gen_smul_dual(TCGv_i32 a, TCGv_i32 b) | 213 | + gen_helper_mve_##FN##h, \ |
42 | } | 214 | + gen_helper_mve_##FN##w, \ |
43 | 215 | + NULL, \ | |
44 | /* Byteswap each halfword. */ | 216 | + }; \ |
45 | -static void gen_rev16(TCGv_i32 dest, TCGv_i32 var) | 217 | + return do_2shift(s, a, fns[a->size], NEGATESHIFT); \ |
46 | +void gen_rev16(TCGv_i32 dest, TCGv_i32 var) | 218 | + } |
47 | { | 219 | + |
48 | TCGv_i32 tmp = tcg_temp_new_i32(); | 220 | +DO_2SHIFT(VSHLI, vshli_u, false) |
49 | TCGv_i32 mask = tcg_const_i32(0x00ff00ff); | 221 | +DO_2SHIFT(VQSHLI_S, vqshli_s, false) |
50 | @@ -XXX,XX +XXX,XX @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var) | 222 | +DO_2SHIFT(VQSHLI_U, vqshli_u, false) |
51 | tcg_gen_ext16s_i32(dest, var); | 223 | +DO_2SHIFT(VQSHLUI, vqshlui_s, false) |
52 | } | ||
53 | |||
54 | -/* Swap low and high halfwords. */ | ||
55 | -static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) | ||
56 | -{ | ||
57 | - tcg_gen_rotri_i32(dest, var, 16); | ||
58 | -} | ||
59 | - | ||
60 | /* Dual 16-bit add. Result placed in t0 and t1 is marked as dead. | ||
61 | tmp = (t0 ^ t1) & 0x8000; | ||
62 | t0 &= ~0x8000; | ||
63 | @@ -XXX,XX +XXX,XX @@ long neon_full_reg_offset(unsigned reg) | ||
64 | * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, | ||
65 | * where 0 is the least significant end of the register. | ||
66 | */ | ||
67 | -static long neon_element_offset(int reg, int element, MemOp memop) | ||
68 | +long neon_element_offset(int reg, int element, MemOp memop) | ||
69 | { | ||
70 | int element_size = 1 << (memop & MO_SIZE); | ||
71 | int ofs = element * element_size; | ||
72 | -- | 224 | -- |
73 | 2.20.1 | 225 | 2.20.1 |
74 | 226 | ||
75 | 227 | diff view generated by jsdifflib |
1 | Some of the constant expanders defined in translate.c are generically | 1 | Implement the MVE vector shift right by immediate insns VSHRI and |
---|---|---|---|
2 | useful and will be used by the separate C files for VFP and Neon once | 2 | VRSHRI. As with Neon, we implement these by using helper functions |
3 | they are created; move the expander definitions to translate.h. | 3 | which perform left shifts but allow negative shift counts to indicate |
4 | right shifts. | ||
4 | 5 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Message-id: 20210430132740.10391-2-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-9-peter.maydell@linaro.org |
9 | --- | 9 | --- |
10 | target/arm/translate.h | 24 ++++++++++++++++++++++++ | 10 | target/arm/helper-mve.h | 12 ++++++++++++ |
11 | target/arm/translate.c | 24 ------------------------ | 11 | target/arm/translate.h | 20 ++++++++++++++++++++ |
12 | 2 files changed, 24 insertions(+), 24 deletions(-) | 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(-) | ||
13 | 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) | ||
14 | diff --git a/target/arm/translate.h b/target/arm/translate.h | 45 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
15 | index XXXXXXX..XXXXXXX 100644 | 46 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/target/arm/translate.h | 47 | --- a/target/arm/translate.h |
17 | +++ b/target/arm/translate.h | 48 | +++ b/target/arm/translate.h |
18 | @@ -XXX,XX +XXX,XX @@ extern TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF; | 49 | @@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x) |
19 | extern TCGv_i64 cpu_exclusive_addr; | 50 | return x * 2 + 1; |
20 | extern TCGv_i64 cpu_exclusive_val; | 51 | } |
21 | 52 | ||
22 | +/* | 53 | +static inline int rsub_64(DisasContext *s, int x) |
23 | + * Constant expanders for the decoders. | ||
24 | + */ | ||
25 | + | ||
26 | +static inline int negate(DisasContext *s, int x) | ||
27 | +{ | 54 | +{ |
28 | + return -x; | 55 | + return 64 - x; |
29 | +} | 56 | +} |
30 | + | 57 | + |
31 | +static inline int plus_2(DisasContext *s, int x) | 58 | +static inline int rsub_32(DisasContext *s, int x) |
32 | +{ | 59 | +{ |
33 | + return x + 2; | 60 | + return 32 - x; |
34 | +} | 61 | +} |
35 | + | 62 | + |
36 | +static inline int times_2(DisasContext *s, int x) | 63 | +static inline int rsub_16(DisasContext *s, int x) |
37 | +{ | 64 | +{ |
38 | + return x * 2; | 65 | + return 16 - x; |
39 | +} | 66 | +} |
40 | + | 67 | + |
41 | +static inline int times_4(DisasContext *s, int x) | 68 | +static inline int rsub_8(DisasContext *s, int x) |
42 | +{ | 69 | +{ |
43 | + return x * 4; | 70 | + return 8 - x; |
44 | +} | 71 | +} |
45 | + | 72 | + |
46 | static inline int arm_dc_feature(DisasContext *dc, int feature) | 73 | static inline int arm_dc_feature(DisasContext *dc, int feature) |
47 | { | 74 | { |
48 | return (dc->features & (1ULL << feature)) != 0; | 75 | return (dc->features & (1ULL << feature)) != 0; |
49 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 76 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
50 | index XXXXXXX..XXXXXXX 100644 | 77 | index XXXXXXX..XXXXXXX 100644 |
51 | --- a/target/arm/translate.c | 78 | --- a/target/arm/mve.decode |
52 | +++ b/target/arm/translate.c | 79 | +++ b/target/arm/mve.decode |
53 | @@ -XXX,XX +XXX,XX @@ static void arm_gen_condlabel(DisasContext *s) | 80 | @@ -XXX,XX +XXX,XX @@ |
54 | } | 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; | ||
55 | } | 163 | } |
56 | 164 | ||
57 | -/* | 165 | -static inline int rsub_64(DisasContext *s, int x) |
58 | - * Constant expanders for the decoders. | ||
59 | - */ | ||
60 | - | ||
61 | -static int negate(DisasContext *s, int x) | ||
62 | -{ | 166 | -{ |
63 | - return -x; | 167 | - return 64 - x; |
64 | -} | 168 | -} |
65 | - | 169 | - |
66 | -static int plus_2(DisasContext *s, int x) | 170 | -static inline int rsub_32(DisasContext *s, int x) |
67 | -{ | 171 | -{ |
68 | - return x + 2; | 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; | ||
69 | -} | 181 | -} |
70 | - | 182 | - |
71 | -static int times_2(DisasContext *s, int x) | 183 | static inline int neon_3same_fp_size(DisasContext *s, int x) |
72 | -{ | 184 | { |
73 | - return x * 2; | 185 | /* Convert 0==fp32, 1==fp16 into a MO_* value */ |
74 | -} | ||
75 | - | ||
76 | -static int times_4(DisasContext *s, int x) | ||
77 | -{ | ||
78 | - return x * 4; | ||
79 | -} | ||
80 | - | ||
81 | /* Flags for the disas_set_da_iss info argument: | ||
82 | * lower bits hold the Rt register number, higher bits are flags. | ||
83 | */ | ||
84 | -- | 186 | -- |
85 | 2.20.1 | 187 | 2.20.1 |
86 | 188 | ||
87 | 189 | diff view generated by jsdifflib |
1 | Move the various gen_aa32* functions and macros out of translate.c | 1 | Implement the MVE VHLL (vector shift left long) insn. This has two |
---|---|---|---|
2 | and into translate-a32.h. | 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. | ||
3 | 5 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210430132740.10391-6-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-10-peter.maydell@linaro.org |
8 | --- | 9 | --- |
9 | target/arm/translate-a32.h | 53 ++++++++++++++++++++++++++++++++++++++ | 10 | target/arm/helper-mve.h | 9 +++++++ |
10 | target/arm/translate.c | 51 ++++++++++++------------------------ | 11 | target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++--- |
11 | 2 files changed, 69 insertions(+), 35 deletions(-) | 12 | target/arm/mve_helper.c | 32 +++++++++++++++++++++++ |
13 | target/arm/translate-mve.c | 15 +++++++++++ | ||
14 | 4 files changed, 105 insertions(+), 4 deletions(-) | ||
12 | 15 | ||
13 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
14 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/target/arm/translate-a32.h | 18 | --- a/target/arm/helper-mve.h |
16 | +++ b/target/arm/translate-a32.h | 19 | +++ b/target/arm/helper-mve.h |
17 | @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) | 20 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
18 | return tmp; | 21 | DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
19 | } | 22 | DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
20 | 23 | DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
21 | +void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, | ||
22 | + TCGv_i32 a32, int index, MemOp opc); | ||
23 | +void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, | ||
24 | + TCGv_i32 a32, int index, MemOp opc); | ||
25 | +void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, | ||
26 | + TCGv_i32 a32, int index, MemOp opc); | ||
27 | +void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, | ||
28 | + TCGv_i32 a32, int index, MemOp opc); | ||
29 | +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
30 | + int index, MemOp opc); | ||
31 | +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
32 | + int index, MemOp opc); | ||
33 | +void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
34 | + int index, MemOp opc); | ||
35 | +void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
36 | + int index, MemOp opc); | ||
37 | + | 24 | + |
38 | +#define DO_GEN_LD(SUFF, OPC) \ | 25 | +DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
39 | + static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ | 26 | +DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
40 | + TCGv_i32 a32, int index) \ | 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) \ | ||
41 | + { \ | 128 | + { \ |
42 | + gen_aa32_ld_i32(s, val, a32, index, OPC); \ | 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); \ | ||
43 | + } | 139 | + } |
44 | + | 140 | + |
45 | +#define DO_GEN_ST(SUFF, OPC) \ | 141 | +#define DO_VSHLL_ALL(OP, TOP) \ |
46 | + static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \ | 142 | + DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \ |
47 | + TCGv_i32 a32, int index) \ | 143 | + DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \ |
48 | + { \ | 144 | + DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \ |
49 | + gen_aa32_st_i32(s, val, a32, index, OPC); \ | 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); \ | ||
50 | + } | 166 | + } |
51 | + | 167 | + |
52 | +static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val, | 168 | +DO_VSHLL(VSHLL_BS, vshllbs) |
53 | + TCGv_i32 a32, int index) | 169 | +DO_VSHLL(VSHLL_BU, vshllbu) |
54 | +{ | 170 | +DO_VSHLL(VSHLL_TS, vshllts) |
55 | + gen_aa32_ld_i64(s, val, a32, index, MO_Q); | 171 | +DO_VSHLL(VSHLL_TU, vshlltu) |
56 | +} | ||
57 | + | ||
58 | +static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val, | ||
59 | + TCGv_i32 a32, int index) | ||
60 | +{ | ||
61 | + gen_aa32_st_i64(s, val, a32, index, MO_Q); | ||
62 | +} | ||
63 | + | ||
64 | +DO_GEN_LD(8u, MO_UB) | ||
65 | +DO_GEN_LD(16u, MO_UW) | ||
66 | +DO_GEN_LD(32u, MO_UL) | ||
67 | +DO_GEN_ST(8, MO_UB) | ||
68 | +DO_GEN_ST(16, MO_UW) | ||
69 | +DO_GEN_ST(32, MO_UL) | ||
70 | + | ||
71 | +#undef DO_GEN_LD | ||
72 | +#undef DO_GEN_ST | ||
73 | + | ||
74 | #endif | ||
75 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
76 | index XXXXXXX..XXXXXXX 100644 | ||
77 | --- a/target/arm/translate.c | ||
78 | +++ b/target/arm/translate.c | ||
79 | @@ -XXX,XX +XXX,XX @@ static TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) | ||
80 | * Internal routines are used for NEON cases where the endianness | ||
81 | * and/or alignment has already been taken into account and manipulated. | ||
82 | */ | ||
83 | -static void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, | ||
84 | - TCGv_i32 a32, int index, MemOp opc) | ||
85 | +void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, | ||
86 | + TCGv_i32 a32, int index, MemOp opc) | ||
87 | { | ||
88 | TCGv addr = gen_aa32_addr(s, a32, opc); | ||
89 | tcg_gen_qemu_ld_i32(val, addr, index, opc); | ||
90 | tcg_temp_free(addr); | ||
91 | } | ||
92 | |||
93 | -static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, | ||
94 | - TCGv_i32 a32, int index, MemOp opc) | ||
95 | +void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, | ||
96 | + TCGv_i32 a32, int index, MemOp opc) | ||
97 | { | ||
98 | TCGv addr = gen_aa32_addr(s, a32, opc); | ||
99 | tcg_gen_qemu_st_i32(val, addr, index, opc); | ||
100 | tcg_temp_free(addr); | ||
101 | } | ||
102 | |||
103 | -static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, | ||
104 | - TCGv_i32 a32, int index, MemOp opc) | ||
105 | +void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, | ||
106 | + TCGv_i32 a32, int index, MemOp opc) | ||
107 | { | ||
108 | TCGv addr = gen_aa32_addr(s, a32, opc); | ||
109 | |||
110 | @@ -XXX,XX +XXX,XX @@ static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, | ||
111 | tcg_temp_free(addr); | ||
112 | } | ||
113 | |||
114 | -static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, | ||
115 | - TCGv_i32 a32, int index, MemOp opc) | ||
116 | +void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, | ||
117 | + TCGv_i32 a32, int index, MemOp opc) | ||
118 | { | ||
119 | TCGv addr = gen_aa32_addr(s, a32, opc); | ||
120 | |||
121 | @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, | ||
122 | tcg_temp_free(addr); | ||
123 | } | ||
124 | |||
125 | -static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
126 | - int index, MemOp opc) | ||
127 | +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
128 | + int index, MemOp opc) | ||
129 | { | ||
130 | gen_aa32_ld_internal_i32(s, val, a32, index, finalize_memop(s, opc)); | ||
131 | } | ||
132 | |||
133 | -static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
134 | - int index, MemOp opc) | ||
135 | +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, | ||
136 | + int index, MemOp opc) | ||
137 | { | ||
138 | gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc)); | ||
139 | } | ||
140 | |||
141 | -static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
142 | - int index, MemOp opc) | ||
143 | +void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
144 | + int index, MemOp opc) | ||
145 | { | ||
146 | gen_aa32_ld_internal_i64(s, val, a32, index, finalize_memop(s, opc)); | ||
147 | } | ||
148 | |||
149 | -static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
150 | - int index, MemOp opc) | ||
151 | +void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
152 | + int index, MemOp opc) | ||
153 | { | ||
154 | gen_aa32_st_internal_i64(s, val, a32, index, finalize_memop(s, opc)); | ||
155 | } | ||
156 | @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, | ||
157 | gen_aa32_st_i32(s, val, a32, index, OPC); \ | ||
158 | } | ||
159 | |||
160 | -static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val, | ||
161 | - TCGv_i32 a32, int index) | ||
162 | -{ | ||
163 | - gen_aa32_ld_i64(s, val, a32, index, MO_Q); | ||
164 | -} | ||
165 | - | ||
166 | -static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val, | ||
167 | - TCGv_i32 a32, int index) | ||
168 | -{ | ||
169 | - gen_aa32_st_i64(s, val, a32, index, MO_Q); | ||
170 | -} | ||
171 | - | ||
172 | -DO_GEN_LD(8u, MO_UB) | ||
173 | -DO_GEN_LD(16u, MO_UW) | ||
174 | -DO_GEN_LD(32u, MO_UL) | ||
175 | -DO_GEN_ST(8, MO_UB) | ||
176 | -DO_GEN_ST(16, MO_UW) | ||
177 | -DO_GEN_ST(32, MO_UL) | ||
178 | - | ||
179 | static inline void gen_hvc(DisasContext *s, int imm16) | ||
180 | { | ||
181 | /* The pre HVC helper handles cases when HVC gets trapped | ||
182 | -- | 172 | -- |
183 | 2.20.1 | 173 | 2.20.1 |
184 | 174 | ||
185 | 175 | diff view generated by jsdifflib |
1 | Make bswap.h handle being included outside an 'extern "C"' block: | 1 | Implement the MVE VSRI and VSLI insns, which perform a |
---|---|---|---|
2 | all system headers are included first, then all declarations are | 2 | shift-and-insert operation. |
3 | put inside an 'extern "C"' block. | ||
4 | |||
5 | This requires a little rearrangement as currently we have an ifdef | ||
6 | ladder that has some system includes and some local declarations | ||
7 | or definitions, and we need to separate those out. | ||
8 | |||
9 | We want to do this because dis-asm.h includes bswap.h, dis-asm.h | ||
10 | may need to be included from C++ files, and system headers should | ||
11 | not be included within 'extern "C"' blocks. | ||
12 | 3 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20210628135835.6690-11-peter.maydell@linaro.org | ||
15 | --- | 7 | --- |
16 | include/qemu/bswap.h | 26 ++++++++++++++++++++++---- | 8 | target/arm/helper-mve.h | 8 ++++++++ |
17 | 1 file changed, 22 insertions(+), 4 deletions(-) | 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(+) | ||
18 | 13 | ||
19 | diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h | 14 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
20 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/include/qemu/bswap.h | 16 | --- a/target/arm/helper-mve.h |
22 | +++ b/include/qemu/bswap.h | 17 | +++ b/target/arm/helper-mve.h |
23 | @@ -XXX,XX +XXX,XX @@ | 18 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
24 | #ifndef BSWAP_H | 19 | DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
25 | #define BSWAP_H | 20 | DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
26 | 21 | DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
27 | -#include "fpu/softfloat-types.h" | ||
28 | - | ||
29 | #ifdef CONFIG_MACHINE_BSWAP_H | ||
30 | # include <sys/endian.h> | ||
31 | # include <machine/bswap.h> | ||
32 | @@ -XXX,XX +XXX,XX @@ | ||
33 | # include <endian.h> | ||
34 | #elif defined(CONFIG_BYTESWAP_H) | ||
35 | # include <byteswap.h> | ||
36 | +#define BSWAP_FROM_BYTESWAP | ||
37 | +# else | ||
38 | +#define BSWAP_FROM_FALLBACKS | ||
39 | +#endif /* ! CONFIG_MACHINE_BSWAP_H */ | ||
40 | |||
41 | +#ifdef __cplusplus | ||
42 | +extern "C" { | ||
43 | +#endif | ||
44 | + | 22 | + |
45 | +#include "fpu/softfloat-types.h" | 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) | ||
46 | + | 26 | + |
47 | +#ifdef BSWAP_FROM_BYTESWAP | 27 | +DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
48 | static inline uint16_t bswap16(uint16_t x) | 28 | +DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
49 | { | 29 | +DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
50 | return bswap_16(x); | 30 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
51 | @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) | 31 | index XXXXXXX..XXXXXXX 100644 |
52 | { | 32 | --- a/target/arm/mve.decode |
53 | return bswap_64(x); | 33 | +++ b/target/arm/mve.decode |
54 | } | 34 | @@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h |
55 | -# else | 35 | |
56 | +#endif | 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 | ||
57 | + | 38 | + |
58 | +#ifdef BSWAP_FROM_FALLBACKS | 39 | +# Shift-and-insert |
59 | static inline uint16_t bswap16(uint16_t x) | 40 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b |
60 | { | 41 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h |
61 | return (((x & 0x00ff) << 8) | | 42 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w |
62 | @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) | ||
63 | ((x & 0x00ff000000000000ULL) >> 40) | | ||
64 | ((x & 0xff00000000000000ULL) >> 56)); | ||
65 | } | ||
66 | -#endif /* ! CONFIG_MACHINE_BSWAP_H */ | ||
67 | +#endif | ||
68 | + | 43 | + |
69 | +#undef BSWAP_FROM_BYTESWAP | 44 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b |
70 | +#undef BSWAP_FROM_FALLBACKS | 45 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h |
71 | 46 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w | |
72 | static inline void bswap16s(uint16_t *s) | 47 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
73 | { | 48 | index XXXXXXX..XXXXXXX 100644 |
74 | @@ -XXX,XX +XXX,XX @@ DO_STN_LDN_P(be) | 49 | --- a/target/arm/mve_helper.c |
75 | #undef le_bswaps | 50 | +++ b/target/arm/mve_helper.c |
76 | #undef be_bswaps | 51 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) |
77 | 52 | DO_2SHIFT_U(vrshli_u, DO_VRSHLU) | |
78 | +#ifdef __cplusplus | 53 | DO_2SHIFT_S(vrshli_s, DO_VRSHLS) |
79 | +} | 54 | |
80 | +#endif | 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 | + } | ||
81 | + | 84 | + |
82 | #endif /* BSWAP_H */ | 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 | { \ | ||
83 | -- | 114 | -- |
84 | 2.20.1 | 115 | 2.20.1 |
85 | 116 | ||
86 | 117 | diff view generated by jsdifflib |
1 | The AN524 FPGA image supports two memory maps, which differ in where | 1 | Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN. |
---|---|---|---|
2 | the QSPI and BRAM are. In the default map, the BRAM is at | ||
3 | 0x0000_0000, and the QSPI at 0x2800_0000. In the second map, they | ||
4 | are the other way around. | ||
5 | 2 | ||
6 | In hardware, the initial mapping can be selected by the user by | 3 | do_urshr() is borrowed from sve_helper.c. |
7 | writing either "REMAP: BRAM" (the default) or "REMAP: QSPI" in the | ||
8 | board configuration file. The board config file is acted on by the | ||
9 | "Motherboard Configuration Controller", which is an entirely separate | ||
10 | microcontroller on the dev board but outside the FPGA. | ||
11 | |||
12 | The guest can also dynamically change the mapping via the SCC | ||
13 | CFG_REG0 register. | ||
14 | |||
15 | Implement this functionality for QEMU, using a machine property | ||
16 | "remap" with valid values "BRAM" and "QSPI" to allow the user to set | ||
17 | the initial mapping, in the same way they can on the FPGA, and | ||
18 | wiring up the bit from the SCC register to also switch the mapping. | ||
19 | 4 | ||
20 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
21 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
22 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 7 | Message-id: 20210628135835.6690-12-peter.maydell@linaro.org |
23 | Message-id: 20210504120912.23094-4-peter.maydell@linaro.org | ||
24 | --- | 8 | --- |
25 | docs/system/arm/mps2.rst | 10 ++++ | 9 | target/arm/helper-mve.h | 10 ++++++++++ |
26 | hw/arm/mps2-tz.c | 108 ++++++++++++++++++++++++++++++++++++++- | 10 | target/arm/mve.decode | 11 +++++++++++ |
27 | 2 files changed, 117 insertions(+), 1 deletion(-) | 11 | target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++ |
12 | target/arm/translate-mve.c | 15 ++++++++++++++ | ||
13 | 4 files changed, 76 insertions(+) | ||
28 | 14 | ||
29 | diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
30 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
31 | --- a/docs/system/arm/mps2.rst | 17 | --- a/target/arm/helper-mve.h |
32 | +++ b/docs/system/arm/mps2.rst | 18 | +++ b/target/arm/helper-mve.h |
33 | @@ -XXX,XX +XXX,XX @@ Differences between QEMU and real hardware: | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
34 | flash, but only as simple ROM, so attempting to rewrite the flash | 20 | DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
35 | from the guest will fail | 21 | DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
36 | - QEMU does not model the USB controller in MPS3 boards | 22 | DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
37 | + | 23 | + |
38 | +Machine-specific options | 24 | +DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
39 | +"""""""""""""""""""""""" | 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) | ||
40 | + | 28 | + |
41 | +The following machine-specific options are supported: | 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 | ||
42 | + | 41 | + |
43 | +remap | 42 | +# Narrowing shifts (which only support b and h sizes) |
44 | + Supported for ``mps3-an524`` only. | 43 | +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b |
45 | + Set ``BRAM``/``QSPI`` to select the initial memory mapping. The | 44 | +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h |
46 | + default is ``BRAM``. | 45 | +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b |
47 | diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c | 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 | ||
48 | index XXXXXXX..XXXXXXX 100644 | 53 | index XXXXXXX..XXXXXXX 100644 |
49 | --- a/hw/arm/mps2-tz.c | 54 | --- a/target/arm/mve_helper.c |
50 | +++ b/hw/arm/mps2-tz.c | 55 | +++ b/target/arm/mve_helper.c |
51 | @@ -XXX,XX +XXX,XX @@ | 56 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) |
52 | #include "hw/boards.h" | 57 | |
53 | #include "exec/address-spaces.h" | 58 | DO_VSHLL_ALL(vshllb, false) |
54 | #include "sysemu/sysemu.h" | 59 | DO_VSHLL_ALL(vshllt, true) |
55 | +#include "sysemu/reset.h" | ||
56 | #include "hw/misc/unimp.h" | ||
57 | #include "hw/char/cmsdk-apb-uart.h" | ||
58 | #include "hw/timer/cmsdk-apb-timer.h" | ||
59 | @@ -XXX,XX +XXX,XX @@ | ||
60 | #include "hw/core/split-irq.h" | ||
61 | #include "hw/qdev-clock.h" | ||
62 | #include "qom/object.h" | ||
63 | +#include "hw/irq.h" | ||
64 | |||
65 | #define MPS2TZ_NUMIRQ_MAX 96 | ||
66 | #define MPS2TZ_RAM_MAX 5 | ||
67 | @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { | ||
68 | SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; | ||
69 | Clock *sysclk; | ||
70 | Clock *s32kclk; | ||
71 | + | 60 | + |
72 | + bool remap; | ||
73 | + qemu_irq remap_irq; | ||
74 | }; | ||
75 | |||
76 | #define TYPE_MPS2TZ_MACHINE "mps2tz" | ||
77 | @@ -XXX,XX +XXX,XX @@ static const RAMInfo an505_raminfo[] = { { | ||
78 | }, | ||
79 | }; | ||
80 | |||
81 | +/* | 61 | +/* |
82 | + * Note that the addresses and MPC numbering here should match up | 62 | + * Narrowing right shifts, taking a double sized input, shifting it |
83 | + * with those used in remap_memory(), which can swap the BRAM and QSPI. | 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. | ||
84 | + */ | 65 | + */ |
85 | static const RAMInfo an524_raminfo[] = { { | 66 | +#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ |
86 | .name = "bram", | 67 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ |
87 | .base = 0x00000000, | 68 | + void *vm, uint32_t shift) \ |
88 | @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, | 69 | + { \ |
89 | 70 | + LTYPE *m = vm; \ | |
90 | object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); | 71 | + TYPE *d = vd; \ |
91 | sccdev = DEVICE(scc); | 72 | + uint16_t mask = mve_element_mask(env); \ |
92 | + qdev_prop_set_uint32(sccdev, "scc-cfg0", mms->remap ? 1 : 0); | 73 | + unsigned le; \ |
93 | qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); | 74 | + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ |
94 | qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); | 75 | + TYPE r = FN(m[H##LESIZE(le)], shift); \ |
95 | qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); | 76 | + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ |
96 | @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, | 77 | + } \ |
97 | return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); | 78 | + mve_advance_vpt(env); \ |
98 | } | ||
99 | |||
100 | +static hwaddr boot_mem_base(MPS2TZMachineState *mms) | ||
101 | +{ | ||
102 | + /* | ||
103 | + * Return the canonical address of the block which will be mapped | ||
104 | + * at address 0x0 (i.e. where the vector table is). | ||
105 | + * This is usually 0, but if the AN524 alternate memory map is | ||
106 | + * enabled it will be the base address of the QSPI block. | ||
107 | + */ | ||
108 | + return mms->remap ? 0x28000000 : 0; | ||
109 | +} | ||
110 | + | ||
111 | +static void remap_memory(MPS2TZMachineState *mms, int map) | ||
112 | +{ | ||
113 | + /* | ||
114 | + * Remap the memory for the AN524. 'map' is the value of | ||
115 | + * SCC CFG_REG0 bit 0, i.e. 0 for the default map and 1 | ||
116 | + * for the "option 1" mapping where QSPI is at address 0. | ||
117 | + * | ||
118 | + * Effectively we need to swap around the "upstream" ends of | ||
119 | + * MPC 0 and MPC 1. | ||
120 | + */ | ||
121 | + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); | ||
122 | + int i; | ||
123 | + | ||
124 | + if (mmc->fpga_type != FPGA_AN524) { | ||
125 | + return; | ||
126 | + } | 79 | + } |
127 | + | 80 | + |
128 | + memory_region_transaction_begin(); | 81 | +#define DO_VSHRN_ALL(OP, FN) \ |
129 | + for (i = 0; i < 2; i++) { | 82 | + DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \ |
130 | + TZMPC *mpc = &mms->mpc[i]; | 83 | + DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \ |
131 | + MemoryRegion *upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); | 84 | + DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \ |
132 | + hwaddr addr = (i ^ map) ? 0x28000000 : 0; | 85 | + DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN) |
133 | + | 86 | + |
134 | + memory_region_set_address(upstream, addr); | 87 | +static inline uint64_t do_urshr(uint64_t x, unsigned sh) |
135 | + } | ||
136 | + memory_region_transaction_commit(); | ||
137 | +} | ||
138 | + | ||
139 | +static void remap_irq_fn(void *opaque, int n, int level) | ||
140 | +{ | 88 | +{ |
141 | + MPS2TZMachineState *mms = opaque; | 89 | + if (likely(sh < 64)) { |
142 | + | 90 | + return (x >> sh) + ((x >> (sh - 1)) & 1); |
143 | + remap_memory(mms, level); | 91 | + } else if (sh == 64) { |
144 | +} | 92 | + return x >> 63; |
145 | + | ||
146 | static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, | ||
147 | const char *name, hwaddr size, | ||
148 | const int *irqs) | ||
149 | @@ -XXX,XX +XXX,XX @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) | ||
150 | MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); | ||
151 | |||
152 | for (p = mmc->raminfo; p->name; p++) { | ||
153 | - if (p->base == 0) { | ||
154 | + if (p->base == boot_mem_base(mms)) { | ||
155 | return p->size; | ||
156 | } | ||
157 | } | ||
158 | @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) | ||
159 | |||
160 | create_non_mpc_ram(mms); | ||
161 | |||
162 | + if (mmc->fpga_type == FPGA_AN524) { | ||
163 | + /* | ||
164 | + * Connect the line from the SCC so that we can remap when the | ||
165 | + * guest updates that register. | ||
166 | + */ | ||
167 | + mms->remap_irq = qemu_allocate_irq(remap_irq_fn, mms, 0); | ||
168 | + qdev_connect_gpio_out_named(DEVICE(&mms->scc), "remap", 0, | ||
169 | + mms->remap_irq); | ||
170 | + } | ||
171 | + | ||
172 | armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, | ||
173 | boot_ram_size(mms)); | ||
174 | } | ||
175 | @@ -XXX,XX +XXX,XX @@ static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, | ||
176 | *iregion = region; | ||
177 | } | ||
178 | |||
179 | +static char *mps2_get_remap(Object *obj, Error **errp) | ||
180 | +{ | ||
181 | + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); | ||
182 | + const char *val = mms->remap ? "QSPI" : "BRAM"; | ||
183 | + return g_strdup(val); | ||
184 | +} | ||
185 | + | ||
186 | +static void mps2_set_remap(Object *obj, const char *value, Error **errp) | ||
187 | +{ | ||
188 | + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); | ||
189 | + | ||
190 | + if (!strcmp(value, "BRAM")) { | ||
191 | + mms->remap = false; | ||
192 | + } else if (!strcmp(value, "QSPI")) { | ||
193 | + mms->remap = true; | ||
194 | + } else { | 93 | + } else { |
195 | + error_setg(errp, "Invalid remap value"); | 94 | + return 0; |
196 | + error_append_hint(errp, "Valid values are BRAM and QSPI.\n"); | ||
197 | + } | 95 | + } |
198 | +} | 96 | +} |
199 | + | 97 | + |
200 | +static void mps2_machine_reset(MachineState *machine) | 98 | +DO_VSHRN_ALL(vshrn, DO_SHR) |
201 | +{ | 99 | +DO_VSHRN_ALL(vrshrn, do_urshr) |
202 | + MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); | 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) | ||
203 | + | 108 | + |
204 | + /* | 109 | +#define DO_2SHIFT_N(INSN, FN) \ |
205 | + * Set the initial memory mapping before triggering the reset of | 110 | + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
206 | + * the rest of the system, so that the guest image loader and CPU | 111 | + { \ |
207 | + * reset see the correct mapping. | 112 | + static MVEGenTwoOpShiftFn * const fns[] = { \ |
208 | + */ | 113 | + gen_helper_mve_##FN##b, \ |
209 | + remap_memory(mms, mms->remap); | 114 | + gen_helper_mve_##FN##h, \ |
210 | + qemu_devices_reset(); | 115 | + }; \ |
211 | +} | 116 | + return do_2shift(s, a, fns[a->size], false); \ |
117 | + } | ||
212 | + | 118 | + |
213 | static void mps2tz_class_init(ObjectClass *oc, void *data) | 119 | +DO_2SHIFT_N(VSHRNB, vshrnb) |
214 | { | 120 | +DO_2SHIFT_N(VSHRNT, vshrnt) |
215 | MachineClass *mc = MACHINE_CLASS(oc); | 121 | +DO_2SHIFT_N(VRSHRNB, vrshrnb) |
216 | IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); | 122 | +DO_2SHIFT_N(VRSHRNT, vrshrnt) |
217 | |||
218 | mc->init = mps2tz_common_init; | ||
219 | + mc->reset = mps2_machine_reset; | ||
220 | iic->check = mps2_tz_idau_check; | ||
221 | } | ||
222 | |||
223 | @@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) | ||
224 | mmc->raminfo = an524_raminfo; | ||
225 | mmc->armsse_type = TYPE_SSE200; | ||
226 | mps2tz_set_default_ram_info(mmc); | ||
227 | + | ||
228 | + object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); | ||
229 | + object_class_property_set_description(oc, "remap", | ||
230 | + "Set memory mapping. Valid values " | ||
231 | + "are BRAM (default) and QSPI."); | ||
232 | } | ||
233 | |||
234 | static void mps3tz_an547_class_init(ObjectClass *oc, void *data) | ||
235 | -- | 123 | -- |
236 | 2.20.1 | 124 | 2.20.1 |
237 | 125 | ||
238 | 126 | diff view generated by jsdifflib |
1 | The function vfp_reg_ptr() is used only in translate-neon.c.inc; | 1 | Implement the MVE saturating shift-right-and-narrow insns |
---|---|---|---|
2 | move it there. | 2 | VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. |
3 | |||
4 | do_srshr() is borrowed from sve_helper.c. | ||
3 | 5 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210430132740.10391-10-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-13-peter.maydell@linaro.org |
8 | --- | 9 | --- |
9 | target/arm/translate.c | 7 ------- | 10 | target/arm/helper-mve.h | 30 +++++++++++ |
10 | target/arm/translate-neon.c.inc | 7 +++++++ | 11 | target/arm/mve.decode | 28 ++++++++++ |
11 | 2 files changed, 7 insertions(+), 7 deletions(-) | 12 | target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++ |
12 | 13 | target/arm/translate-mve.c | 12 +++++ | |
13 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 14 | 4 files changed, 174 insertions(+) |
14 | index XXXXXXX..XXXXXXX 100644 | 15 | |
15 | --- a/target/arm/translate.c | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
16 | +++ b/target/arm/translate.c | 17 | index XXXXXXX..XXXXXXX 100644 |
17 | @@ -XXX,XX +XXX,XX @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) | 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) | ||
18 | } | 95 | } |
19 | } | 96 | } |
20 | 97 | ||
21 | -static TCGv_ptr vfp_reg_ptr(bool dp, int reg) | 98 | +static inline int64_t do_srshr(int64_t x, unsigned sh) |
22 | -{ | ||
23 | - TCGv_ptr ret = tcg_temp_new_ptr(); | ||
24 | - tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); | ||
25 | - return ret; | ||
26 | -} | ||
27 | - | ||
28 | #define ARM_CP_RW_BIT (1 << 20) | ||
29 | |||
30 | /* Include the Neon decoder */ | ||
31 | diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc | ||
32 | index XXXXXXX..XXXXXXX 100644 | ||
33 | --- a/target/arm/translate-neon.c.inc | ||
34 | +++ b/target/arm/translate-neon.c.inc | ||
35 | @@ -XXX,XX +XXX,XX @@ static inline int neon_3same_fp_size(DisasContext *s, int x) | ||
36 | #include "decode-neon-ls.c.inc" | ||
37 | #include "decode-neon-shared.c.inc" | ||
38 | |||
39 | +static TCGv_ptr vfp_reg_ptr(bool dp, int reg) | ||
40 | +{ | 99 | +{ |
41 | + TCGv_ptr ret = tcg_temp_new_ptr(); | 100 | + if (likely(sh < 64)) { |
42 | + tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); | 101 | + return (x >> sh) + ((x >> (sh - 1)) & 1); |
43 | + return ret; | 102 | + } else { |
103 | + /* Rounding the sign bit always produces 0. */ | ||
104 | + return 0; | ||
105 | + } | ||
44 | +} | 106 | +} |
45 | + | 107 | + |
46 | static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) | 108 | DO_VSHRN_ALL(vshrn, DO_SHR) |
47 | { | 109 | DO_VSHRN_ALL(vrshrn, do_urshr) |
48 | long offset = neon_element_offset(reg, ele, mop & MO_SIZE); | 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) | ||
49 | -- | 224 | -- |
50 | 2.20.1 | 225 | 2.20.1 |
51 | 226 | ||
52 | 227 | diff view generated by jsdifflib |
1 | Both os-win32.h and os-posix.h include system header files. Instead | 1 | Implement the MVE VSHLC insn, which performs a shift left of the |
---|---|---|---|
2 | of having osdep.h include them inside its 'extern "C"' block, make | 2 | entire vector with carry in bits provided from a general purpose |
3 | these headers handle that themselves, so that we don't include the | 3 | register and carry out bits written back to that register. |
4 | system headers inside 'extern "C"'. | ||
5 | |||
6 | This doesn't fix any current problems, but it's conceptually the | ||
7 | right way to handle system headers. | ||
8 | 4 | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
10 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210628135835.6690-14-peter.maydell@linaro.org | ||
11 | --- | 8 | --- |
12 | include/qemu/osdep.h | 8 ++++---- | 9 | target/arm/helper-mve.h | 2 ++ |
13 | include/sysemu/os-posix.h | 8 ++++++++ | 10 | target/arm/mve.decode | 2 ++ |
14 | include/sysemu/os-win32.h | 8 ++++++++ | 11 | target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++ |
15 | 3 files changed, 20 insertions(+), 4 deletions(-) | 12 | target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++ |
13 | 4 files changed, 72 insertions(+) | ||
16 | 14 | ||
17 | diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
18 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/include/qemu/osdep.h | 17 | --- a/target/arm/helper-mve.h |
20 | +++ b/include/qemu/osdep.h | 18 | +++ b/target/arm/helper-mve.h |
21 | @@ -XXX,XX +XXX,XX @@ QEMU_EXTERN_C int daemon(int, int); | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
22 | */ | 20 | DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
23 | #include "glib-compat.h" | 21 | DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
24 | 22 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
25 | -#ifdef __cplusplus | ||
26 | -extern "C" { | ||
27 | -#endif | ||
28 | - | ||
29 | #ifdef _WIN32 | ||
30 | #include "sysemu/os-win32.h" | ||
31 | #endif | ||
32 | @@ -XXX,XX +XXX,XX @@ extern "C" { | ||
33 | #include "sysemu/os-posix.h" | ||
34 | #endif | ||
35 | |||
36 | +#ifdef __cplusplus | ||
37 | +extern "C" { | ||
38 | +#endif | ||
39 | + | 23 | + |
40 | #include "qemu/typedefs.h" | 24 | +DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) |
41 | 25 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode | |
42 | /* | ||
43 | diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h | ||
44 | index XXXXXXX..XXXXXXX 100644 | 26 | index XXXXXXX..XXXXXXX 100644 |
45 | --- a/include/sysemu/os-posix.h | 27 | --- a/target/arm/mve.decode |
46 | +++ b/include/sysemu/os-posix.h | 28 | +++ b/target/arm/mve.decode |
47 | @@ -XXX,XX +XXX,XX @@ | 29 | @@ -XXX,XX +XXX,XX @@ VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b |
48 | #include <sys/sysmacros.h> | 30 | VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h |
49 | #endif | 31 | VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b |
50 | 32 | VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h | |
51 | +#ifdef __cplusplus | ||
52 | +extern "C" { | ||
53 | +#endif | ||
54 | + | 33 | + |
55 | void os_set_line_buffering(void); | 34 | +VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd |
56 | void os_set_proc_name(const char *s); | 35 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
57 | void os_setup_signal_handling(void); | 36 | index XXXXXXX..XXXXXXX 100644 |
58 | @@ -XXX,XX +XXX,XX @@ static inline void qemu_funlockfile(FILE *f) | 37 | --- a/target/arm/mve_helper.c |
59 | funlockfile(f); | 38 | +++ b/target/arm/mve_helper.c |
60 | } | 39 | @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) |
61 | 40 | DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) | |
62 | +#ifdef __cplusplus | 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; | ||
63 | +} | 80 | +} |
64 | +#endif | 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) | ||
65 | + | 89 | + |
66 | #endif | 90 | +static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) |
67 | diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h | 91 | +{ |
68 | index XXXXXXX..XXXXXXX 100644 | 92 | + /* |
69 | --- a/include/sysemu/os-win32.h | 93 | + * Whole Vector Left Shift with Carry. The carry is taken |
70 | +++ b/include/sysemu/os-win32.h | 94 | + * from a general purpose register and written back there. |
71 | @@ -XXX,XX +XXX,XX @@ | 95 | + * An imm of 0 means "shift by 32". |
72 | #include <windows.h> | 96 | + */ |
73 | #include <ws2tcpip.h> | 97 | + TCGv_ptr qd; |
74 | 98 | + TCGv_i32 rdm; | |
75 | +#ifdef __cplusplus | ||
76 | +extern "C" { | ||
77 | +#endif | ||
78 | + | 99 | + |
79 | #if defined(_WIN64) | 100 | + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { |
80 | /* On w64, setjmp is implemented by _setjmp which needs a second parameter. | 101 | + return false; |
81 | * If this parameter is NULL, longjump does no stack unwinding. | 102 | + } |
82 | @@ -XXX,XX +XXX,XX @@ ssize_t qemu_recv_wrap(int sockfd, void *buf, size_t len, int flags); | 103 | + if (a->rdm == 13 || a->rdm == 15) { |
83 | ssize_t qemu_recvfrom_wrap(int sockfd, void *buf, size_t len, int flags, | 104 | + /* CONSTRAINED UNPREDICTABLE: we UNDEF */ |
84 | struct sockaddr *addr, socklen_t *addrlen); | 105 | + return false; |
85 | 106 | + } | |
86 | +#ifdef __cplusplus | 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; | ||
87 | +} | 118 | +} |
88 | +#endif | ||
89 | + | ||
90 | #endif | ||
91 | -- | 119 | -- |
92 | 2.20.1 | 120 | 2.20.1 |
93 | 121 | ||
94 | 122 | diff view generated by jsdifflib |
1 | Currently the trans functions for m-nocp.decode all live in | 1 | Implement the MVE VADDLV insn; this is similar to VADDV, except |
---|---|---|---|
2 | translate-vfp.inc.c; move them out into their own translation unit, | 2 | that it accumulates 32-bit elements into a 64-bit accumulator |
3 | translate-m-nocp.c. | 3 | stored in a pair of general-purpose registers. |
4 | |||
5 | The trans_* functions here are pure code motion with no changes. | ||
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: Richard Henderson <richard.henderson@linaro.org> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
9 | Message-id: 20210430132740.10391-5-peter.maydell@linaro.org | 7 | Message-id: 20210628135835.6690-15-peter.maydell@linaro.org |
10 | --- | 8 | --- |
11 | target/arm/translate-a32.h | 3 + | 9 | target/arm/helper-mve.h | 3 ++ |
12 | target/arm/translate-m-nocp.c | 221 +++++++++++++++++++++++++++++++++ | 10 | target/arm/mve.decode | 6 +++- |
13 | target/arm/translate.c | 1 - | 11 | target/arm/mve_helper.c | 19 ++++++++++++ |
14 | target/arm/translate-vfp.c.inc | 196 ----------------------------- | 12 | target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++ |
15 | target/arm/meson.build | 3 +- | 13 | 4 files changed, 90 insertions(+), 1 deletion(-) |
16 | 5 files changed, 226 insertions(+), 198 deletions(-) | ||
17 | create mode 100644 target/arm/translate-m-nocp.c | ||
18 | 14 | ||
19 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
20 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/target/arm/translate-a32.h | 17 | --- a/target/arm/helper-mve.h |
22 | +++ b/target/arm/translate-a32.h | 18 | +++ b/target/arm/helper-mve.h |
23 | @@ -XXX,XX +XXX,XX @@ | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) |
24 | #ifndef TARGET_ARM_TRANSLATE_A64_H | 20 | DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
25 | #define TARGET_ARM_TRANSLATE_A64_H | 21 | DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
26 | 22 | ||
27 | +/* Prototypes for autogenerated disassembler functions */ | 23 | +DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) |
28 | +bool disas_m_nocp(DisasContext *dc, uint32_t insn); | 24 | +DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) |
29 | + | 25 | + |
30 | void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); | 26 | DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) |
31 | void arm_gen_condlabel(DisasContext *s); | 27 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) |
32 | bool vfp_access_check(DisasContext *s); | 28 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) |
33 | diff --git a/target/arm/translate-m-nocp.c b/target/arm/translate-m-nocp.c | 29 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
34 | new file mode 100644 | 30 | index XXXXXXX..XXXXXXX 100644 |
35 | index XXXXXXX..XXXXXXX | 31 | --- a/target/arm/mve.decode |
36 | --- /dev/null | 32 | +++ b/target/arm/mve.decode |
37 | +++ b/target/arm/translate-m-nocp.c | 33 | @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar |
38 | @@ -XXX,XX +XXX,XX @@ | 34 | VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar |
39 | +/* | 35 | |
40 | + * ARM translation: M-profile NOCP special-case instructions | 36 | # Vector add across vector |
41 | + * | 37 | -VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo |
42 | + * Copyright (c) 2020 Linaro, Ltd. | 38 | +{ |
43 | + * | 39 | + VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo |
44 | + * This library is free software; you can redistribute it and/or | 40 | + VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \ |
45 | + * modify it under the terms of the GNU Lesser General Public | 41 | + rdahi=%rdahi rdalo=%rdalo |
46 | + * License as published by the Free Software Foundation; either | 42 | +} |
47 | + * version 2.1 of the License, or (at your option) any later version. | 43 | |
48 | + * | 44 | # Predicate operations |
49 | + * This library is distributed in the hope that it will be useful, | 45 | %mask_22_13 22:1 13:3 |
50 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | 46 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
51 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | 47 | index XXXXXXX..XXXXXXX 100644 |
52 | + * Lesser General Public License for more details. | 48 | --- a/target/arm/mve_helper.c |
53 | + * | 49 | +++ b/target/arm/mve_helper.c |
54 | + * You should have received a copy of the GNU Lesser General Public | 50 | @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) |
55 | + * License along with this library; if not, see <http://www.gnu.org/licenses/>. | 51 | DO_VADDV(vaddvuh, 2, uint16_t) |
56 | + */ | 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 | + } \ | ||
57 | + | 69 | + |
58 | +#include "qemu/osdep.h" | 70 | +DO_VADDLV(vaddlv_s, int32_t, int64_t) |
59 | +#include "tcg/tcg-op.h" | 71 | +DO_VADDLV(vaddlv_u, uint32_t, uint64_t) |
60 | +#include "translate.h" | ||
61 | +#include "translate-a32.h" | ||
62 | + | 72 | + |
63 | +#include "decode-m-nocp.c.inc" | 73 | /* Shifts by immediate */ |
74 | #define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ | ||
75 | void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
76 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c | ||
77 | index XXXXXXX..XXXXXXX 100644 | ||
78 | --- a/target/arm/translate-mve.c | ||
79 | +++ b/target/arm/translate-mve.c | ||
80 | @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) | ||
81 | return true; | ||
82 | } | ||
83 | |||
84 | +static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a) | ||
85 | +{ | ||
86 | + /* | ||
87 | + * Vector Add Long Across Vector: accumulate the 32-bit | ||
88 | + * elements of the vector into a 64-bit result stored in | ||
89 | + * a pair of general-purpose registers. | ||
90 | + * No need to check Qm's bank: it is only 3 bits in decode. | ||
91 | + */ | ||
92 | + TCGv_ptr qm; | ||
93 | + TCGv_i64 rda; | ||
94 | + TCGv_i32 rdalo, rdahi; | ||
64 | + | 95 | + |
65 | +/* | 96 | + if (!dc_isar_feature(aa32_mve, s)) { |
66 | + * Decode VLLDM and VLSTM are nonstandard because: | ||
67 | + * * if there is no FPU then these insns must NOP in | ||
68 | + * Secure state and UNDEF in Nonsecure state | ||
69 | + * * if there is an FPU then these insns do not have | ||
70 | + * the usual behaviour that vfp_access_check() provides of | ||
71 | + * being controlled by CPACR/NSACR enable bits or the | ||
72 | + * lazy-stacking logic. | ||
73 | + */ | ||
74 | +static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) | ||
75 | +{ | ||
76 | + TCGv_i32 fptr; | ||
77 | + | ||
78 | + if (!arm_dc_feature(s, ARM_FEATURE_M) || | ||
79 | + !arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
80 | + return false; | 97 | + return false; |
81 | + } | 98 | + } |
82 | + | ||
83 | + if (a->op) { | ||
84 | + /* | ||
85 | + * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not | ||
86 | + * to take the IMPDEF option to make memory accesses to the stack | ||
87 | + * slots that correspond to the D16-D31 registers (discarding | ||
88 | + * read data and writing UNKNOWN values), so for us the T2 | ||
89 | + * encoding behaves identically to the T1 encoding. | ||
90 | + */ | ||
91 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | ||
92 | + return false; | ||
93 | + } | ||
94 | + } else { | ||
95 | + /* | ||
96 | + * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. | ||
97 | + * This is currently architecturally impossible, but we add the | ||
98 | + * check to stay in line with the pseudocode. Note that we must | ||
99 | + * emit code for the UNDEF so it takes precedence over the NOCP. | ||
100 | + */ | ||
101 | + if (dc_isar_feature(aa32_simd_r32, s)) { | ||
102 | + unallocated_encoding(s); | ||
103 | + return true; | ||
104 | + } | ||
105 | + } | ||
106 | + | ||
107 | + /* | 99 | + /* |
108 | + * If not secure, UNDEF. We must emit code for this | 100 | + * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related |
109 | + * rather than returning false so that this takes | 101 | + * encoding; rdalo always has bit 0 clear so cannot be 13 or 15. |
110 | + * precedence over the m-nocp.decode NOCP fallback. | ||
111 | + */ | 102 | + */ |
112 | + if (!s->v8m_secure) { | 103 | + if (a->rdahi == 13 || a->rdahi == 15) { |
113 | + unallocated_encoding(s); | ||
114 | + return true; | ||
115 | + } | ||
116 | + /* If no fpu, NOP. */ | ||
117 | + if (!dc_isar_feature(aa32_vfp, s)) { | ||
118 | + return true; | ||
119 | + } | ||
120 | + | ||
121 | + fptr = load_reg(s, a->rn); | ||
122 | + if (a->l) { | ||
123 | + gen_helper_v7m_vlldm(cpu_env, fptr); | ||
124 | + } else { | ||
125 | + gen_helper_v7m_vlstm(cpu_env, fptr); | ||
126 | + } | ||
127 | + tcg_temp_free_i32(fptr); | ||
128 | + | ||
129 | + /* End the TB, because we have updated FP control bits */ | ||
130 | + s->base.is_jmp = DISAS_UPDATE_EXIT; | ||
131 | + return true; | ||
132 | +} | ||
133 | + | ||
134 | +static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) | ||
135 | +{ | ||
136 | + int btmreg, topreg; | ||
137 | + TCGv_i64 zero; | ||
138 | + TCGv_i32 aspen, sfpa; | ||
139 | + | ||
140 | + if (!dc_isar_feature(aa32_m_sec_state, s)) { | ||
141 | + /* Before v8.1M, fall through in decode to NOCP check */ | ||
142 | + return false; | 104 | + return false; |
143 | + } | 105 | + } |
144 | + | 106 | + if (!mve_eci_check(s) || !vfp_access_check(s)) { |
145 | + /* Explicitly UNDEF because this takes precedence over NOCP */ | ||
146 | + if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { | ||
147 | + unallocated_encoding(s); | ||
148 | + return true; | ||
149 | + } | ||
150 | + | ||
151 | + if (!dc_isar_feature(aa32_vfp_simd, s)) { | ||
152 | + /* NOP if we have neither FP nor MVE */ | ||
153 | + return true; | 107 | + return true; |
154 | + } | 108 | + } |
155 | + | 109 | + |
156 | + /* | 110 | + /* |
157 | + * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no | 111 | + * This insn is subject to beat-wise execution. Partial execution |
158 | + * active floating point context so we must NOP (without doing | 112 | + * of an A=0 (no-accumulate) insn which does not execute the first |
159 | + * any lazy state preservation or the NOCP check). | 113 | + * beat must start with the current value of RdaHi:RdaLo, not zero. |
160 | + */ | 114 | + */ |
161 | + aspen = load_cpu_field(v7m.fpccr[M_REG_S]); | 115 | + if (a->a || mve_skip_first_beat(s)) { |
162 | + sfpa = load_cpu_field(v7m.control[M_REG_S]); | 116 | + /* Accumulate input from RdaHi:RdaLo */ |
163 | + tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); | 117 | + rda = tcg_temp_new_i64(); |
164 | + tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); | 118 | + rdalo = load_reg(s, a->rdalo); |
165 | + tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); | 119 | + rdahi = load_reg(s, a->rdahi); |
166 | + tcg_gen_or_i32(sfpa, sfpa, aspen); | 120 | + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); |
167 | + arm_gen_condlabel(s); | 121 | + tcg_temp_free_i32(rdalo); |
168 | + tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); | 122 | + tcg_temp_free_i32(rdahi); |
169 | + | 123 | + } else { |
170 | + if (s->fp_excp_el != 0) { | 124 | + /* Accumulate starting at zero */ |
171 | + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | 125 | + rda = tcg_const_i64(0); |
172 | + syn_uncategorized(), s->fp_excp_el); | ||
173 | + return true; | ||
174 | + } | 126 | + } |
175 | + | 127 | + |
176 | + topreg = a->vd + a->imm - 1; | 128 | + qm = mve_qreg_ptr(a->qm); |
177 | + btmreg = a->vd; | 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); | ||
178 | + | 135 | + |
179 | + /* Convert to Sreg numbers if the insn specified in Dregs */ | 136 | + rdalo = tcg_temp_new_i32(); |
180 | + if (a->size == 3) { | 137 | + rdahi = tcg_temp_new_i32(); |
181 | + topreg = topreg * 2 + 1; | 138 | + tcg_gen_extrl_i64_i32(rdalo, rda); |
182 | + btmreg *= 2; | 139 | + tcg_gen_extrh_i64_i32(rdahi, rda); |
183 | + } | 140 | + store_reg(s, a->rdalo, rdalo); |
184 | + | 141 | + store_reg(s, a->rdahi, rdahi); |
185 | + if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { | 142 | + tcg_temp_free_i64(rda); |
186 | + /* UNPREDICTABLE: we choose to undef */ | 143 | + mve_update_eci(s); |
187 | + unallocated_encoding(s); | ||
188 | + return true; | ||
189 | + } | ||
190 | + | ||
191 | + /* Silently ignore requests to clear D16-D31 if they don't exist */ | ||
192 | + if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { | ||
193 | + topreg = 31; | ||
194 | + } | ||
195 | + | ||
196 | + if (!vfp_access_check(s)) { | ||
197 | + return true; | ||
198 | + } | ||
199 | + | ||
200 | + /* Zero the Sregs from btmreg to topreg inclusive. */ | ||
201 | + zero = tcg_const_i64(0); | ||
202 | + if (btmreg & 1) { | ||
203 | + write_neon_element64(zero, btmreg >> 1, 1, MO_32); | ||
204 | + btmreg++; | ||
205 | + } | ||
206 | + for (; btmreg + 1 <= topreg; btmreg += 2) { | ||
207 | + write_neon_element64(zero, btmreg >> 1, 0, MO_64); | ||
208 | + } | ||
209 | + if (btmreg == topreg) { | ||
210 | + write_neon_element64(zero, btmreg >> 1, 0, MO_32); | ||
211 | + btmreg++; | ||
212 | + } | ||
213 | + assert(btmreg == topreg + 1); | ||
214 | + /* TODO: when MVE is implemented, zero VPR here */ | ||
215 | + return true; | 144 | + return true; |
216 | +} | 145 | +} |
217 | + | 146 | + |
218 | +static bool trans_NOCP(DisasContext *s, arg_nocp *a) | 147 | static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) |
219 | +{ | ||
220 | + /* | ||
221 | + * Handle M-profile early check for disabled coprocessor: | ||
222 | + * all we need to do here is emit the NOCP exception if | ||
223 | + * the coprocessor is disabled. Otherwise we return false | ||
224 | + * and the real VFP/etc decode will handle the insn. | ||
225 | + */ | ||
226 | + assert(arm_dc_feature(s, ARM_FEATURE_M)); | ||
227 | + | ||
228 | + if (a->cp == 11) { | ||
229 | + a->cp = 10; | ||
230 | + } | ||
231 | + if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && | ||
232 | + (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { | ||
233 | + /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ | ||
234 | + a->cp = 10; | ||
235 | + } | ||
236 | + | ||
237 | + if (a->cp != 10) { | ||
238 | + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | ||
239 | + syn_uncategorized(), default_exception_el(s)); | ||
240 | + return true; | ||
241 | + } | ||
242 | + | ||
243 | + if (s->fp_excp_el != 0) { | ||
244 | + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | ||
245 | + syn_uncategorized(), s->fp_excp_el); | ||
246 | + return true; | ||
247 | + } | ||
248 | + | ||
249 | + return false; | ||
250 | +} | ||
251 | + | ||
252 | +static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) | ||
253 | +{ | ||
254 | + /* This range needs a coprocessor check for v8.1M and later only */ | ||
255 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | ||
256 | + return false; | ||
257 | + } | ||
258 | + return trans_NOCP(s, a); | ||
259 | +} | ||
260 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
261 | index XXXXXXX..XXXXXXX 100644 | ||
262 | --- a/target/arm/translate.c | ||
263 | +++ b/target/arm/translate.c | ||
264 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) | ||
265 | #define ARM_CP_RW_BIT (1 << 20) | ||
266 | |||
267 | /* Include the VFP and Neon decoders */ | ||
268 | -#include "decode-m-nocp.c.inc" | ||
269 | #include "translate-vfp.c.inc" | ||
270 | #include "translate-neon.c.inc" | ||
271 | |||
272 | diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc | ||
273 | index XXXXXXX..XXXXXXX 100644 | ||
274 | --- a/target/arm/translate-vfp.c.inc | ||
275 | +++ b/target/arm/translate-vfp.c.inc | ||
276 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) | ||
277 | return true; | ||
278 | } | ||
279 | |||
280 | -/* | ||
281 | - * Decode VLLDM and VLSTM are nonstandard because: | ||
282 | - * * if there is no FPU then these insns must NOP in | ||
283 | - * Secure state and UNDEF in Nonsecure state | ||
284 | - * * if there is an FPU then these insns do not have | ||
285 | - * the usual behaviour that vfp_access_check() provides of | ||
286 | - * being controlled by CPACR/NSACR enable bits or the | ||
287 | - * lazy-stacking logic. | ||
288 | - */ | ||
289 | -static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) | ||
290 | -{ | ||
291 | - TCGv_i32 fptr; | ||
292 | - | ||
293 | - if (!arm_dc_feature(s, ARM_FEATURE_M) || | ||
294 | - !arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
295 | - return false; | ||
296 | - } | ||
297 | - | ||
298 | - if (a->op) { | ||
299 | - /* | ||
300 | - * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not | ||
301 | - * to take the IMPDEF option to make memory accesses to the stack | ||
302 | - * slots that correspond to the D16-D31 registers (discarding | ||
303 | - * read data and writing UNKNOWN values), so for us the T2 | ||
304 | - * encoding behaves identically to the T1 encoding. | ||
305 | - */ | ||
306 | - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | ||
307 | - return false; | ||
308 | - } | ||
309 | - } else { | ||
310 | - /* | ||
311 | - * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. | ||
312 | - * This is currently architecturally impossible, but we add the | ||
313 | - * check to stay in line with the pseudocode. Note that we must | ||
314 | - * emit code for the UNDEF so it takes precedence over the NOCP. | ||
315 | - */ | ||
316 | - if (dc_isar_feature(aa32_simd_r32, s)) { | ||
317 | - unallocated_encoding(s); | ||
318 | - return true; | ||
319 | - } | ||
320 | - } | ||
321 | - | ||
322 | - /* | ||
323 | - * If not secure, UNDEF. We must emit code for this | ||
324 | - * rather than returning false so that this takes | ||
325 | - * precedence over the m-nocp.decode NOCP fallback. | ||
326 | - */ | ||
327 | - if (!s->v8m_secure) { | ||
328 | - unallocated_encoding(s); | ||
329 | - return true; | ||
330 | - } | ||
331 | - /* If no fpu, NOP. */ | ||
332 | - if (!dc_isar_feature(aa32_vfp, s)) { | ||
333 | - return true; | ||
334 | - } | ||
335 | - | ||
336 | - fptr = load_reg(s, a->rn); | ||
337 | - if (a->l) { | ||
338 | - gen_helper_v7m_vlldm(cpu_env, fptr); | ||
339 | - } else { | ||
340 | - gen_helper_v7m_vlstm(cpu_env, fptr); | ||
341 | - } | ||
342 | - tcg_temp_free_i32(fptr); | ||
343 | - | ||
344 | - /* End the TB, because we have updated FP control bits */ | ||
345 | - s->base.is_jmp = DISAS_UPDATE_EXIT; | ||
346 | - return true; | ||
347 | -} | ||
348 | - | ||
349 | -static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) | ||
350 | -{ | ||
351 | - int btmreg, topreg; | ||
352 | - TCGv_i64 zero; | ||
353 | - TCGv_i32 aspen, sfpa; | ||
354 | - | ||
355 | - if (!dc_isar_feature(aa32_m_sec_state, s)) { | ||
356 | - /* Before v8.1M, fall through in decode to NOCP check */ | ||
357 | - return false; | ||
358 | - } | ||
359 | - | ||
360 | - /* Explicitly UNDEF because this takes precedence over NOCP */ | ||
361 | - if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { | ||
362 | - unallocated_encoding(s); | ||
363 | - return true; | ||
364 | - } | ||
365 | - | ||
366 | - if (!dc_isar_feature(aa32_vfp_simd, s)) { | ||
367 | - /* NOP if we have neither FP nor MVE */ | ||
368 | - return true; | ||
369 | - } | ||
370 | - | ||
371 | - /* | ||
372 | - * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no | ||
373 | - * active floating point context so we must NOP (without doing | ||
374 | - * any lazy state preservation or the NOCP check). | ||
375 | - */ | ||
376 | - aspen = load_cpu_field(v7m.fpccr[M_REG_S]); | ||
377 | - sfpa = load_cpu_field(v7m.control[M_REG_S]); | ||
378 | - tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); | ||
379 | - tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); | ||
380 | - tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); | ||
381 | - tcg_gen_or_i32(sfpa, sfpa, aspen); | ||
382 | - arm_gen_condlabel(s); | ||
383 | - tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); | ||
384 | - | ||
385 | - if (s->fp_excp_el != 0) { | ||
386 | - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | ||
387 | - syn_uncategorized(), s->fp_excp_el); | ||
388 | - return true; | ||
389 | - } | ||
390 | - | ||
391 | - topreg = a->vd + a->imm - 1; | ||
392 | - btmreg = a->vd; | ||
393 | - | ||
394 | - /* Convert to Sreg numbers if the insn specified in Dregs */ | ||
395 | - if (a->size == 3) { | ||
396 | - topreg = topreg * 2 + 1; | ||
397 | - btmreg *= 2; | ||
398 | - } | ||
399 | - | ||
400 | - if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { | ||
401 | - /* UNPREDICTABLE: we choose to undef */ | ||
402 | - unallocated_encoding(s); | ||
403 | - return true; | ||
404 | - } | ||
405 | - | ||
406 | - /* Silently ignore requests to clear D16-D31 if they don't exist */ | ||
407 | - if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { | ||
408 | - topreg = 31; | ||
409 | - } | ||
410 | - | ||
411 | - if (!vfp_access_check(s)) { | ||
412 | - return true; | ||
413 | - } | ||
414 | - | ||
415 | - /* Zero the Sregs from btmreg to topreg inclusive. */ | ||
416 | - zero = tcg_const_i64(0); | ||
417 | - if (btmreg & 1) { | ||
418 | - write_neon_element64(zero, btmreg >> 1, 1, MO_32); | ||
419 | - btmreg++; | ||
420 | - } | ||
421 | - for (; btmreg + 1 <= topreg; btmreg += 2) { | ||
422 | - write_neon_element64(zero, btmreg >> 1, 0, MO_64); | ||
423 | - } | ||
424 | - if (btmreg == topreg) { | ||
425 | - write_neon_element64(zero, btmreg >> 1, 0, MO_32); | ||
426 | - btmreg++; | ||
427 | - } | ||
428 | - assert(btmreg == topreg + 1); | ||
429 | - /* TODO: when MVE is implemented, zero VPR here */ | ||
430 | - return true; | ||
431 | -} | ||
432 | - | ||
433 | -static bool trans_NOCP(DisasContext *s, arg_nocp *a) | ||
434 | -{ | ||
435 | - /* | ||
436 | - * Handle M-profile early check for disabled coprocessor: | ||
437 | - * all we need to do here is emit the NOCP exception if | ||
438 | - * the coprocessor is disabled. Otherwise we return false | ||
439 | - * and the real VFP/etc decode will handle the insn. | ||
440 | - */ | ||
441 | - assert(arm_dc_feature(s, ARM_FEATURE_M)); | ||
442 | - | ||
443 | - if (a->cp == 11) { | ||
444 | - a->cp = 10; | ||
445 | - } | ||
446 | - if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && | ||
447 | - (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { | ||
448 | - /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ | ||
449 | - a->cp = 10; | ||
450 | - } | ||
451 | - | ||
452 | - if (a->cp != 10) { | ||
453 | - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | ||
454 | - syn_uncategorized(), default_exception_el(s)); | ||
455 | - return true; | ||
456 | - } | ||
457 | - | ||
458 | - if (s->fp_excp_el != 0) { | ||
459 | - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, | ||
460 | - syn_uncategorized(), s->fp_excp_el); | ||
461 | - return true; | ||
462 | - } | ||
463 | - | ||
464 | - return false; | ||
465 | -} | ||
466 | - | ||
467 | -static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) | ||
468 | -{ | ||
469 | - /* This range needs a coprocessor check for v8.1M and later only */ | ||
470 | - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | ||
471 | - return false; | ||
472 | - } | ||
473 | - return trans_NOCP(s, a); | ||
474 | -} | ||
475 | - | ||
476 | static bool trans_VINS(DisasContext *s, arg_VINS *a) | ||
477 | { | 148 | { |
478 | TCGv_i32 rd, rm; | 149 | TCGv_ptr qd; |
479 | diff --git a/target/arm/meson.build b/target/arm/meson.build | ||
480 | index XXXXXXX..XXXXXXX 100644 | ||
481 | --- a/target/arm/meson.build | ||
482 | +++ b/target/arm/meson.build | ||
483 | @@ -XXX,XX +XXX,XX @@ gen = [ | ||
484 | decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), | ||
485 | decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), | ||
486 | decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), | ||
487 | - decodetree.process('m-nocp.decode', extra_args: '--static-decode=disas_m_nocp'), | ||
488 | + decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), | ||
489 | decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), | ||
490 | decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), | ||
491 | decodetree.process('t32.decode', extra_args: '--static-decode=disas_t32'), | ||
492 | @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( | ||
493 | 'op_helper.c', | ||
494 | 'tlb_helper.c', | ||
495 | 'translate.c', | ||
496 | + 'translate-m-nocp.c', | ||
497 | 'vec_helper.c', | ||
498 | 'vfp_helper.c', | ||
499 | 'cpu_tcg.c', | ||
500 | -- | 150 | -- |
501 | 2.20.1 | 151 | 2.20.1 |
502 | 152 | ||
503 | 153 | diff view generated by jsdifflib |
1 | Move the NeonGenThreeOpEnvFn typedef to translate.h together | 1 | The MVE extension to v8.1M includes some new shift instructions which |
---|---|---|---|
2 | with the other similar typedefs. | 2 | sit entirely within the non-coprocessor part of the encoding space |
3 | and which operate only on general-purpose registers. They take up | ||
4 | the space which was previously UNPREDICTABLE MOVS and ORRS encodings | ||
5 | with Rm == 13 or 15. | ||
6 | |||
7 | Implement the long shifts by immediate, which perform shifts on a | ||
8 | pair of general-purpose registers treated as a 64-bit quantity, with | ||
9 | an immediate shift count between 1 and 32. | ||
10 | |||
11 | Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for | ||
12 | the Rm==13,15 case, we need to explicitly emit code to UNDEF for the | ||
13 | cases where v8.1M now requires that. (Trying to change MOVS and ORRS | ||
14 | is too difficult, because the functions that generate the code are | ||
15 | shared between a dozen different kinds of arithmetic or logical | ||
16 | instruction for all A32, T16 and T32 encodings, and for some insns | ||
17 | and some encodings Rm==13,15 are valid.) | ||
18 | |||
19 | We make the helper functions we need for UQSHLL and SQSHLL take | ||
20 | a 32-bit value which the helper casts to int8_t because we'll need | ||
21 | these helpers also for the shift-by-register insns, where the shift | ||
22 | count might be < 0 or > 32. | ||
3 | 23 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 25 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 26 | Message-id: 20210628135835.6690-16-peter.maydell@linaro.org |
7 | Message-id: 20210430132740.10391-12-peter.maydell@linaro.org | ||
8 | --- | 27 | --- |
9 | target/arm/translate.h | 2 ++ | 28 | target/arm/helper-mve.h | 3 ++ |
10 | target/arm/translate.c | 3 --- | 29 | target/arm/translate.h | 1 + |
11 | 2 files changed, 2 insertions(+), 3 deletions(-) | 30 | target/arm/t32.decode | 28 +++++++++++++ |
12 | 31 | target/arm/mve_helper.c | 10 +++++ | |
32 | target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++ | ||
33 | 5 files changed, 132 insertions(+) | ||
34 | |||
35 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h | ||
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/target/arm/helper-mve.h | ||
38 | +++ b/target/arm/helper-mve.h | ||
39 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
40 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
41 | |||
42 | DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) | ||
43 | + | ||
44 | +DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
45 | +DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
13 | diff --git a/target/arm/translate.h b/target/arm/translate.h | 46 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
14 | index XXXXXXX..XXXXXXX 100644 | 47 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/target/arm/translate.h | 48 | --- a/target/arm/translate.h |
16 | +++ b/target/arm/translate.h | 49 | +++ b/target/arm/translate.h |
17 | @@ -XXX,XX +XXX,XX @@ typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); | 50 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); |
18 | typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); | 51 | typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); |
19 | typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); | 52 | typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); |
20 | typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); | 53 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); |
21 | +typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, | 54 | +typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); |
22 | + TCGv_i32, TCGv_i32); | 55 | |
23 | typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); | 56 | /** |
24 | typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); | 57 | * arm_tbflags_from_tb: |
25 | typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); | 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 | +} | ||
26 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 128 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
27 | index XXXXXXX..XXXXXXX 100644 | 129 | index XXXXXXX..XXXXXXX 100644 |
28 | --- a/target/arm/translate.c | 130 | --- a/target/arm/translate.c |
29 | +++ b/target/arm/translate.c | 131 | +++ b/target/arm/translate.c |
30 | @@ -XXX,XX +XXX,XX @@ static const char * const regnames[] = | 132 | @@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a) |
31 | { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", | 133 | return true; |
32 | "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; | 134 | } |
33 | 135 | ||
34 | -/* Function prototypes for gen_ functions calling Neon helpers. */ | 136 | +/* |
35 | -typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, | 137 | + * v8.1M MVE wide-shifts |
36 | - TCGv_i32, TCGv_i32); | 138 | + */ |
37 | 139 | +static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a, | |
38 | /* initialize TCG globals. */ | 140 | + WideShiftImmFn *fn) |
39 | void arm_translate_init(void) | 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 | */ | ||
40 | -- | 229 | -- |
41 | 2.20.1 | 230 | 2.20.1 |
42 | 231 | ||
43 | 232 | diff view generated by jsdifflib |
1 | The VFPGenFixPointFn typedef is unused; delete it. | 1 | Implement the MVE long shifts by register, which perform shifts on a |
---|---|---|---|
2 | pair of general-purpose registers treated as a 64-bit quantity, with | ||
3 | the shift count in another general-purpose register, which might be | ||
4 | either positive or negative. | ||
5 | |||
6 | Like the long-shifts-by-immediate, these encodings sit in the space | ||
7 | that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15. | ||
8 | Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and | ||
9 | also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases), | ||
10 | we have to move the CSEL pattern into the same decodetree group. | ||
2 | 11 | ||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 14 | Message-id: 20210628135835.6690-17-peter.maydell@linaro.org |
6 | Message-id: 20210430132740.10391-11-peter.maydell@linaro.org | ||
7 | --- | 15 | --- |
8 | target/arm/translate.c | 2 -- | 16 | target/arm/helper-mve.h | 6 +++ |
9 | 1 file changed, 2 deletions(-) | 17 | target/arm/translate.h | 1 + |
10 | 18 | target/arm/t32.decode | 16 +++++-- | |
19 | target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++ | ||
20 | target/arm/translate.c | 69 ++++++++++++++++++++++++++++++ | ||
21 | 5 files changed, 182 insertions(+), 3 deletions(-) | ||
22 | |||
23 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | ||
25 | --- a/target/arm/helper-mve.h | ||
26 | +++ b/target/arm/helper-mve.h | ||
27 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
28 | |||
29 | DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) | ||
30 | |||
31 | +DEF_HELPER_FLAGS_3(mve_sshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
32 | +DEF_HELPER_FLAGS_3(mve_ushll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
33 | DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
34 | DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
35 | +DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
36 | +DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
37 | +DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
38 | +DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
39 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
40 | index XXXXXXX..XXXXXXX 100644 | ||
41 | --- a/target/arm/translate.h | ||
42 | +++ b/target/arm/translate.h | ||
43 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
44 | typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
45 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
46 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); | ||
47 | +typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); | ||
48 | |||
49 | /** | ||
50 | * arm_tbflags_from_tb: | ||
51 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode | ||
52 | index XXXXXXX..XXXXXXX 100644 | ||
53 | --- a/target/arm/t32.decode | ||
54 | +++ b/target/arm/t32.decode | ||
55 | @@ -XXX,XX +XXX,XX @@ | ||
56 | &mcrr !extern cp opc1 crm rt rt2 | ||
57 | |||
58 | &mve_shl_ri rdalo rdahi shim | ||
59 | +&mve_shl_rr rdalo rdahi rm | ||
60 | |||
61 | # rdahi: bits [3:1] from insn, bit 0 is 1 | ||
62 | # rdalo: bits [3:1] from insn, bit 0 is 0 | ||
63 | @@ -XXX,XX +XXX,XX @@ | ||
64 | |||
65 | @mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ | ||
66 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 | ||
67 | +@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ | ||
68 | + &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 | ||
69 | |||
70 | { | ||
71 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi | ||
72 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi | ||
73 | URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
74 | SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
75 | SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
76 | + | ||
77 | + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
78 | + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
79 | + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr | ||
80 | + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr | ||
81 | + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr | ||
82 | + SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr | ||
83 | ] | ||
84 | |||
85 | MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi | ||
86 | ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi | ||
87 | + | ||
88 | + # v8.1M CSEL and friends | ||
89 | + CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 | ||
90 | } | ||
91 | { | ||
92 | MVN_rxri 1110101 0011 . 1111 0 ... .... .... .... @s_rxr_shi | ||
93 | @@ -XXX,XX +XXX,XX @@ SBC_rrri 1110101 1011 . .... 0 ... .... .... .... @s_rrr_shi | ||
94 | } | ||
95 | RSB_rrri 1110101 1110 . .... 0 ... .... .... .... @s_rrr_shi | ||
96 | |||
97 | -# v8.1M CSEL and friends | ||
98 | -CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 | ||
99 | - | ||
100 | # Data-processing (register-shifted register) | ||
101 | |||
102 | MOV_rxrr 1111 1010 0 shty:2 s:1 rm:4 1111 rd:4 0000 rs:4 \ | ||
103 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
104 | index XXXXXXX..XXXXXXX 100644 | ||
105 | --- a/target/arm/mve_helper.c | ||
106 | +++ b/target/arm/mve_helper.c | ||
107 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, | ||
108 | return rdm; | ||
109 | } | ||
110 | |||
111 | +uint64_t HELPER(mve_sshrl)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
112 | +{ | ||
113 | + return do_sqrshl_d(n, -(int8_t)shift, false, NULL); | ||
114 | +} | ||
115 | + | ||
116 | +uint64_t HELPER(mve_ushll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
117 | +{ | ||
118 | + return do_uqrshl_d(n, (int8_t)shift, false, NULL); | ||
119 | +} | ||
120 | + | ||
121 | uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
122 | { | ||
123 | return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); | ||
124 | @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
125 | { | ||
126 | return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); | ||
127 | } | ||
128 | + | ||
129 | +uint64_t HELPER(mve_sqrshrl)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
130 | +{ | ||
131 | + return do_sqrshl_d(n, -(int8_t)shift, true, &env->QF); | ||
132 | +} | ||
133 | + | ||
134 | +uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
135 | +{ | ||
136 | + return do_uqrshl_d(n, (int8_t)shift, true, &env->QF); | ||
137 | +} | ||
138 | + | ||
139 | +/* Operate on 64-bit values, but saturate at 48 bits */ | ||
140 | +static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, | ||
141 | + bool round, uint32_t *sat) | ||
142 | +{ | ||
143 | + if (shift <= -48) { | ||
144 | + /* Rounding the sign bit always produces 0. */ | ||
145 | + if (round) { | ||
146 | + return 0; | ||
147 | + } | ||
148 | + return src >> 63; | ||
149 | + } else if (shift < 0) { | ||
150 | + if (round) { | ||
151 | + src >>= -shift - 1; | ||
152 | + return (src >> 1) + (src & 1); | ||
153 | + } | ||
154 | + return src >> -shift; | ||
155 | + } else if (shift < 48) { | ||
156 | + int64_t val = src << shift; | ||
157 | + int64_t extval = sextract64(val, 0, 48); | ||
158 | + if (!sat || val == extval) { | ||
159 | + return extval; | ||
160 | + } | ||
161 | + } else if (!sat || src == 0) { | ||
162 | + return 0; | ||
163 | + } | ||
164 | + | ||
165 | + *sat = 1; | ||
166 | + return (1ULL << 47) - (src >= 0); | ||
167 | +} | ||
168 | + | ||
169 | +/* Operate on 64-bit values, but saturate at 48 bits */ | ||
170 | +static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, | ||
171 | + bool round, uint32_t *sat) | ||
172 | +{ | ||
173 | + uint64_t val, extval; | ||
174 | + | ||
175 | + if (shift <= -(48 + round)) { | ||
176 | + return 0; | ||
177 | + } else if (shift < 0) { | ||
178 | + if (round) { | ||
179 | + val = src >> (-shift - 1); | ||
180 | + val = (val >> 1) + (val & 1); | ||
181 | + } else { | ||
182 | + val = src >> -shift; | ||
183 | + } | ||
184 | + extval = extract64(val, 0, 48); | ||
185 | + if (!sat || val == extval) { | ||
186 | + return extval; | ||
187 | + } | ||
188 | + } else if (shift < 48) { | ||
189 | + uint64_t val = src << shift; | ||
190 | + uint64_t extval = extract64(val, 0, 48); | ||
191 | + if (!sat || val == extval) { | ||
192 | + return extval; | ||
193 | + } | ||
194 | + } else if (!sat || src == 0) { | ||
195 | + return 0; | ||
196 | + } | ||
197 | + | ||
198 | + *sat = 1; | ||
199 | + return MAKE_64BIT_MASK(0, 48); | ||
200 | +} | ||
201 | + | ||
202 | +uint64_t HELPER(mve_sqrshrl48)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
203 | +{ | ||
204 | + return do_sqrshl48_d(n, -(int8_t)shift, true, &env->QF); | ||
205 | +} | ||
206 | + | ||
207 | +uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
208 | +{ | ||
209 | + return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); | ||
210 | +} | ||
11 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 211 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
12 | index XXXXXXX..XXXXXXX 100644 | 212 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/target/arm/translate.c | 213 | --- a/target/arm/translate.c |
14 | +++ b/target/arm/translate.c | 214 | +++ b/target/arm/translate.c |
15 | @@ -XXX,XX +XXX,XX @@ static const char * const regnames[] = | 215 | @@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) |
16 | /* Function prototypes for gen_ functions calling Neon helpers. */ | 216 | return do_mve_shl_ri(s, a, gen_urshr64_i64); |
17 | typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, | 217 | } |
18 | TCGv_i32, TCGv_i32); | 218 | |
19 | -/* Function prototypes for gen_ functions for fix point conversions */ | 219 | +static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn) |
20 | -typedef void VFPGenFixPointFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); | 220 | +{ |
21 | 221 | + TCGv_i64 rda; | |
22 | /* initialize TCG globals. */ | 222 | + TCGv_i32 rdalo, rdahi; |
23 | void arm_translate_init(void) | 223 | + |
224 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { | ||
225 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ | ||
226 | + return false; | ||
227 | + } | ||
228 | + if (a->rdahi == 15) { | ||
229 | + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ | ||
230 | + return false; | ||
231 | + } | ||
232 | + if (!dc_isar_feature(aa32_mve, s) || | ||
233 | + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || | ||
234 | + a->rdahi == 13 || a->rm == 13 || a->rm == 15 || | ||
235 | + a->rm == a->rdahi || a->rm == a->rdalo) { | ||
236 | + /* These rdahi/rdalo/rm cases are UNPREDICTABLE; we choose to UNDEF */ | ||
237 | + unallocated_encoding(s); | ||
238 | + return true; | ||
239 | + } | ||
240 | + | ||
241 | + rda = tcg_temp_new_i64(); | ||
242 | + rdalo = load_reg(s, a->rdalo); | ||
243 | + rdahi = load_reg(s, a->rdahi); | ||
244 | + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); | ||
245 | + | ||
246 | + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ | ||
247 | + fn(rda, cpu_env, rda, cpu_R[a->rm]); | ||
248 | + | ||
249 | + tcg_gen_extrl_i64_i32(rdalo, rda); | ||
250 | + tcg_gen_extrh_i64_i32(rdahi, rda); | ||
251 | + store_reg(s, a->rdalo, rdalo); | ||
252 | + store_reg(s, a->rdahi, rdahi); | ||
253 | + tcg_temp_free_i64(rda); | ||
254 | + | ||
255 | + return true; | ||
256 | +} | ||
257 | + | ||
258 | +static bool trans_LSLL_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
259 | +{ | ||
260 | + return do_mve_shl_rr(s, a, gen_helper_mve_ushll); | ||
261 | +} | ||
262 | + | ||
263 | +static bool trans_ASRL_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
264 | +{ | ||
265 | + return do_mve_shl_rr(s, a, gen_helper_mve_sshrl); | ||
266 | +} | ||
267 | + | ||
268 | +static bool trans_UQRSHLL64_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
269 | +{ | ||
270 | + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll); | ||
271 | +} | ||
272 | + | ||
273 | +static bool trans_SQRSHRL64_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
274 | +{ | ||
275 | + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl); | ||
276 | +} | ||
277 | + | ||
278 | +static bool trans_UQRSHLL48_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
279 | +{ | ||
280 | + return do_mve_shl_rr(s, a, gen_helper_mve_uqrshll48); | ||
281 | +} | ||
282 | + | ||
283 | +static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) | ||
284 | +{ | ||
285 | + return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); | ||
286 | +} | ||
287 | + | ||
288 | /* | ||
289 | * Multiply and multiply accumulate | ||
290 | */ | ||
24 | -- | 291 | -- |
25 | 2.20.1 | 292 | 2.20.1 |
26 | 293 | ||
27 | 294 | diff view generated by jsdifflib |
1 | Switch translate-vfp.c.inc from being #included into translate.c | 1 | Implement the MVE shifts by immediate, which perform shifts |
---|---|---|---|
2 | to being its own compilation unit. | 2 | on a single general-purpose register. |
3 | |||
4 | These patterns overlap with the long-shift-by-immediates, | ||
5 | so we have to rearrange the grouping a little here. | ||
3 | 6 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20210430132740.10391-9-peter.maydell@linaro.org | 9 | Message-id: 20210628135835.6690-18-peter.maydell@linaro.org |
8 | --- | 10 | --- |
9 | target/arm/translate-a32.h | 2 ++ | 11 | target/arm/helper-mve.h | 3 ++ |
10 | target/arm/{translate-vfp.c.inc => translate-vfp.c} | 12 +++++++----- | 12 | target/arm/translate.h | 1 + |
11 | target/arm/translate.c | 3 +-- | 13 | target/arm/t32.decode | 31 ++++++++++++++----- |
12 | target/arm/meson.build | 5 +++-- | 14 | target/arm/mve_helper.c | 10 ++++++ |
13 | 4 files changed, 13 insertions(+), 9 deletions(-) | 15 | target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- |
14 | rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (99%) | 16 | 5 files changed, 104 insertions(+), 9 deletions(-) |
15 | 17 | ||
16 | diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h | 18 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
17 | index XXXXXXX..XXXXXXX 100644 | 19 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/target/arm/translate-a32.h | 20 | --- a/target/arm/helper-mve.h |
19 | +++ b/target/arm/translate-a32.h | 21 | +++ b/target/arm/helper-mve.h |
22 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
23 | DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
24 | DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
25 | DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
26 | + | ||
27 | +DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
28 | +DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
29 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
30 | index XXXXXXX..XXXXXXX 100644 | ||
31 | --- a/target/arm/translate.h | ||
32 | +++ b/target/arm/translate.h | ||
33 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
34 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
35 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); | ||
36 | typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); | ||
37 | +typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); | ||
38 | |||
39 | /** | ||
40 | * arm_tbflags_from_tb: | ||
41 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode | ||
42 | index XXXXXXX..XXXXXXX 100644 | ||
43 | --- a/target/arm/t32.decode | ||
44 | +++ b/target/arm/t32.decode | ||
20 | @@ -XXX,XX +XXX,XX @@ | 45 | @@ -XXX,XX +XXX,XX @@ |
21 | 46 | ||
22 | /* Prototypes for autogenerated disassembler functions */ | 47 | &mve_shl_ri rdalo rdahi shim |
23 | bool disas_m_nocp(DisasContext *dc, uint32_t insn); | 48 | &mve_shl_rr rdalo rdahi rm |
24 | +bool disas_vfp(DisasContext *s, uint32_t insn); | 49 | +&mve_sh_ri rda shim |
25 | +bool disas_vfp_uncond(DisasContext *s, uint32_t insn); | 50 | |
26 | 51 | # rdahi: bits [3:1] from insn, bit 0 is 1 | |
27 | void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); | 52 | # rdalo: bits [3:1] from insn, bit 0 is 0 |
28 | void arm_gen_condlabel(DisasContext *s); | ||
29 | diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c | ||
30 | similarity index 99% | ||
31 | rename from target/arm/translate-vfp.c.inc | ||
32 | rename to target/arm/translate-vfp.c | ||
33 | index XXXXXXX..XXXXXXX 100644 | ||
34 | --- a/target/arm/translate-vfp.c.inc | ||
35 | +++ b/target/arm/translate-vfp.c | ||
36 | @@ -XXX,XX +XXX,XX @@ | 53 | @@ -XXX,XX +XXX,XX @@ |
37 | * License along with this library; if not, see <http://www.gnu.org/licenses/>. | 54 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 |
38 | */ | 55 | @mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ |
39 | 56 | &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 | |
40 | -/* | 57 | +@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ |
41 | - * This file is intended to be included from translate.c; it uses | 58 | + &mve_sh_ri shim=%imm5_12_6 |
42 | - * some macros and definitions provided by that file. | 59 | |
43 | - * It might be possible to convert it to a standalone .c file eventually. | 60 | { |
44 | - */ | 61 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi |
45 | +#include "qemu/osdep.h" | 62 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi |
46 | +#include "tcg/tcg-op.h" | 63 | # the rest fall through (where ORR_rrri and MOV_rxri will end up |
47 | +#include "tcg/tcg-op-gvec.h" | 64 | # handling them as r13 and r15 accesses with the same semantics as A32). |
48 | +#include "exec/exec-all.h" | 65 | [ |
49 | +#include "exec/gen-icount.h" | 66 | - LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
50 | +#include "translate.h" | 67 | - LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri |
51 | +#include "translate-a32.h" | 68 | - ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri |
52 | 69 | + { | |
53 | /* Include the generated VFP decoder */ | 70 | + UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri |
54 | #include "decode-vfp.c.inc" | 71 | + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
72 | + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri | ||
73 | + } | ||
74 | |||
75 | - UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri | ||
76 | - URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
77 | - SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
78 | - SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
79 | + { | ||
80 | + URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri | ||
81 | + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
82 | + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
83 | + } | ||
84 | + | ||
85 | + { | ||
86 | + SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri | ||
87 | + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
88 | + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
89 | + } | ||
90 | + | ||
91 | + { | ||
92 | + SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri | ||
93 | + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
94 | + } | ||
95 | |||
96 | LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
97 | ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
98 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
99 | index XXXXXXX..XXXXXXX 100644 | ||
100 | --- a/target/arm/mve_helper.c | ||
101 | +++ b/target/arm/mve_helper.c | ||
102 | @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
103 | { | ||
104 | return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); | ||
105 | } | ||
106 | + | ||
107 | +uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
108 | +{ | ||
109 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); | ||
110 | +} | ||
111 | + | ||
112 | +uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
113 | +{ | ||
114 | + return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); | ||
115 | +} | ||
55 | diff --git a/target/arm/translate.c b/target/arm/translate.c | 116 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
56 | index XXXXXXX..XXXXXXX 100644 | 117 | index XXXXXXX..XXXXXXX 100644 |
57 | --- a/target/arm/translate.c | 118 | --- a/target/arm/translate.c |
58 | +++ b/target/arm/translate.c | 119 | +++ b/target/arm/translate.c |
59 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) | 120 | @@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) |
60 | 121 | ||
61 | #define ARM_CP_RW_BIT (1 << 20) | 122 | static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) |
62 | 123 | { | |
63 | -/* Include the VFP and Neon decoders */ | 124 | - TCGv_i32 t = tcg_temp_new_i32(); |
64 | -#include "translate-vfp.c.inc" | 125 | + TCGv_i32 t; |
65 | +/* Include the Neon decoder */ | 126 | |
66 | #include "translate-neon.c.inc" | 127 | + /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ |
67 | 128 | + if (sh == 32) { | |
68 | static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) | 129 | + tcg_gen_movi_i32(d, 0); |
69 | diff --git a/target/arm/meson.build b/target/arm/meson.build | 130 | + return; |
70 | index XXXXXXX..XXXXXXX 100644 | 131 | + } |
71 | --- a/target/arm/meson.build | 132 | + t = tcg_temp_new_i32(); |
72 | +++ b/target/arm/meson.build | 133 | tcg_gen_extract_i32(t, a, sh - 1, 1); |
73 | @@ -XXX,XX +XXX,XX @@ gen = [ | 134 | tcg_gen_sari_i32(d, a, sh); |
74 | decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), | 135 | tcg_gen_add_i32(d, d, t); |
75 | decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), | 136 | @@ -XXX,XX +XXX,XX @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) |
76 | decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), | 137 | |
77 | - decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), | 138 | static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) |
78 | - decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), | 139 | { |
79 | + decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), | 140 | - TCGv_i32 t = tcg_temp_new_i32(); |
80 | + decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), | 141 | + TCGv_i32 t; |
81 | decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), | 142 | |
82 | decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), | 143 | + /* Handle shift by the input size for the benefit of trans_URSHR_ri */ |
83 | decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), | 144 | + if (sh == 32) { |
84 | @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( | 145 | + tcg_gen_extract_i32(d, a, sh - 1, 1); |
85 | 'tlb_helper.c', | 146 | + return; |
86 | 'translate.c', | 147 | + } |
87 | 'translate-m-nocp.c', | 148 | + t = tcg_temp_new_i32(); |
88 | + 'translate-vfp.c', | 149 | tcg_gen_extract_i32(t, a, sh - 1, 1); |
89 | 'vec_helper.c', | 150 | tcg_gen_shri_i32(d, a, sh); |
90 | 'vfp_helper.c', | 151 | tcg_gen_add_i32(d, d, t); |
91 | 'cpu_tcg.c', | 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 | */ | ||
92 | -- | 211 | -- |
93 | 2.20.1 | 212 | 2.20.1 |
94 | 213 | ||
95 | 214 | diff view generated by jsdifflib |
1 | The functions vfp_load_reg32(), vfp_load_reg64(), vfp_store_reg32() | 1 | Implement the MVE shifts by register, which perform |
---|---|---|---|
2 | and vfp_store_reg64() are used only in translate-vfp.c.inc. Move | 2 | shifts on a single general-purpose register. |
3 | them to that file. | ||
4 | 3 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Message-id: 20210430132740.10391-7-peter.maydell@linaro.org | 6 | Message-id: 20210628135835.6690-19-peter.maydell@linaro.org |
9 | --- | 7 | --- |
10 | target/arm/translate.c | 20 -------------------- | 8 | target/arm/helper-mve.h | 2 ++ |
11 | target/arm/translate-vfp.c.inc | 20 ++++++++++++++++++++ | 9 | target/arm/translate.h | 1 + |
12 | 2 files changed, 20 insertions(+), 20 deletions(-) | 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(-) | ||
13 | 14 | ||
15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/helper-mve.h | ||
18 | +++ b/target/arm/helper-mve.h | ||
19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
20 | |||
21 | DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
22 | DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
23 | +DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
24 | +DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) | ||
25 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
26 | index XXXXXXX..XXXXXXX 100644 | ||
27 | --- a/target/arm/translate.h | ||
28 | +++ b/target/arm/translate.h | ||
29 | @@ -XXX,XX +XXX,XX @@ typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
30 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); | ||
31 | typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); | ||
32 | typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); | ||
33 | +typedef void ShiftFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); | ||
34 | |||
35 | /** | ||
36 | * arm_tbflags_from_tb: | ||
37 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/target/arm/t32.decode | ||
40 | +++ b/target/arm/t32.decode | ||
41 | @@ -XXX,XX +XXX,XX @@ | ||
42 | &mve_shl_ri rdalo rdahi shim | ||
43 | &mve_shl_rr rdalo rdahi rm | ||
44 | &mve_sh_ri rda shim | ||
45 | +&mve_sh_rr rda rm | ||
46 | |||
47 | # rdahi: bits [3:1] from insn, bit 0 is 1 | ||
48 | # rdalo: bits [3:1] from insn, bit 0 is 0 | ||
49 | @@ -XXX,XX +XXX,XX @@ | ||
50 | &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 | ||
51 | @mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ | ||
52 | &mve_sh_ri shim=%imm5_12_6 | ||
53 | +@mve_sh_rr ....... .... . rda:4 rm:4 .... .... .... &mve_sh_rr | ||
54 | |||
55 | { | ||
56 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi | ||
57 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi | ||
58 | SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
59 | } | ||
60 | |||
61 | - LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
62 | - ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
63 | - UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr | ||
64 | - SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr | ||
65 | + { | ||
66 | + UQRSHL_rr 1110101 0010 1 .... .... 1111 0000 1101 @mve_sh_rr | ||
67 | + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr | ||
68 | + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr | ||
69 | + } | ||
70 | + | ||
71 | + { | ||
72 | + SQRSHR_rr 1110101 0010 1 .... .... 1111 0010 1101 @mve_sh_rr | ||
73 | + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr | ||
74 | + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr | ||
75 | + } | ||
76 | + | ||
77 | UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr | ||
78 | SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr | ||
79 | ] | ||
80 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
81 | index XXXXXXX..XXXXXXX 100644 | ||
82 | --- a/target/arm/mve_helper.c | ||
83 | +++ b/target/arm/mve_helper.c | ||
84 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
85 | { | ||
86 | return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); | ||
87 | } | ||
88 | + | ||
89 | +uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
90 | +{ | ||
91 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF); | ||
92 | +} | ||
93 | + | ||
94 | +uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) | ||
95 | +{ | ||
96 | + return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); | ||
97 | +} | ||
14 | 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 |
15 | index XXXXXXX..XXXXXXX 100644 | 99 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/target/arm/translate.c | 100 | --- a/target/arm/translate.c |
17 | +++ b/target/arm/translate.c | 101 | +++ b/target/arm/translate.c |
18 | @@ -XXX,XX +XXX,XX @@ static long vfp_reg_offset(bool dp, unsigned reg) | 102 | @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) |
19 | } | 103 | return do_mve_sh_ri(s, a, gen_mve_uqshl); |
20 | } | 104 | } |
21 | 105 | ||
22 | -static inline void vfp_load_reg64(TCGv_i64 var, int reg) | 106 | +static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn) |
23 | -{ | ||
24 | - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); | ||
25 | -} | ||
26 | - | ||
27 | -static inline void vfp_store_reg64(TCGv_i64 var, int reg) | ||
28 | -{ | ||
29 | - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); | ||
30 | -} | ||
31 | - | ||
32 | -static inline void vfp_load_reg32(TCGv_i32 var, int reg) | ||
33 | -{ | ||
34 | - tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); | ||
35 | -} | ||
36 | - | ||
37 | -static inline void vfp_store_reg32(TCGv_i32 var, int reg) | ||
38 | -{ | ||
39 | - tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); | ||
40 | -} | ||
41 | - | ||
42 | void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) | ||
43 | { | ||
44 | long off = neon_element_offset(reg, ele, memop); | ||
45 | diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc | ||
46 | index XXXXXXX..XXXXXXX 100644 | ||
47 | --- a/target/arm/translate-vfp.c.inc | ||
48 | +++ b/target/arm/translate-vfp.c.inc | ||
49 | @@ -XXX,XX +XXX,XX @@ | ||
50 | #include "decode-vfp.c.inc" | ||
51 | #include "decode-vfp-uncond.c.inc" | ||
52 | |||
53 | +static inline void vfp_load_reg64(TCGv_i64 var, int reg) | ||
54 | +{ | 107 | +{ |
55 | + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); | 108 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { |
109 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ | ||
110 | + return false; | ||
111 | + } | ||
112 | + if (!dc_isar_feature(aa32_mve, s) || | ||
113 | + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || | ||
114 | + a->rda == 13 || a->rda == 15 || a->rm == 13 || a->rm == 15 || | ||
115 | + a->rm == a->rda) { | ||
116 | + /* These rda/rm cases are UNPREDICTABLE; we choose to UNDEF */ | ||
117 | + unallocated_encoding(s); | ||
118 | + return true; | ||
119 | + } | ||
120 | + | ||
121 | + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ | ||
122 | + fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]); | ||
123 | + return true; | ||
56 | +} | 124 | +} |
57 | + | 125 | + |
58 | +static inline void vfp_store_reg64(TCGv_i64 var, int reg) | 126 | +static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a) |
59 | +{ | 127 | +{ |
60 | + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); | 128 | + return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr); |
61 | +} | 129 | +} |
62 | + | 130 | + |
63 | +static inline void vfp_load_reg32(TCGv_i32 var, int reg) | 131 | +static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a) |
64 | +{ | 132 | +{ |
65 | + tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); | 133 | + return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl); |
66 | +} | ||
67 | + | ||
68 | +static inline void vfp_store_reg32(TCGv_i32 var, int reg) | ||
69 | +{ | ||
70 | + tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); | ||
71 | +} | 134 | +} |
72 | + | 135 | + |
73 | /* | 136 | /* |
74 | * The imm8 encodes the sign bit, enough bits to represent an exponent in | 137 | * Multiply and multiply accumulate |
75 | * the range 01....1xx to 10....0xx, and the most significant 4 bits of | 138 | */ |
76 | -- | 139 | -- |
77 | 2.20.1 | 140 | 2.20.1 |
78 | 141 | ||
79 | 142 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | The WFI insn is not system-mode only, though it doesn't usually make | ||
2 | a huge amount of sense for userspace code to execute it. Currently | ||
3 | if you try it in qemu-arm then the helper function will raise an | ||
4 | EXCP_HLT exception, which is not covered by the switch in cpu_loop() | ||
5 | and results in an abort: | ||
6 | 1 | ||
7 | qemu: unhandled CPU exception 0x10001 - aborting | ||
8 | R00=00000001 R01=408003e4 R02=408003ec R03=000102ec | ||
9 | R04=00010a28 R05=00010158 R06=00087460 R07=00010158 | ||
10 | R08=00000000 R09=00000000 R10=00085b7c R11=408002a4 | ||
11 | R12=408002b8 R13=408002a0 R14=0001057c R15=000102f8 | ||
12 | PSR=60000010 -ZC- A usr32 | ||
13 | qemu:handle_cpu_signal received signal outside vCPU context @ pc=0x7fcbfa4f0a12 | ||
14 | |||
15 | Make the WFI helper function return immediately in the usermode | ||
16 | emulator. This turns WFI into a NOP, which is OK because: | ||
17 | * architecturally "WFI is a NOP" is a permitted implementation | ||
18 | * aarch64 Linux kernels use the SCTLR_EL1.nTWI bit to trap | ||
19 | userspace WFI and NOP it (though aarch32 kernels currently | ||
20 | just let WFI do whatever it would do) | ||
21 | |||
22 | We could in theory make the translate.c code special case user-mode | ||
23 | emulation and NOP the insn entirely rather than making the helper | ||
24 | do nothing, but because no real world code will be trying to | ||
25 | execute WFI we don't care about efficiency and the helper provides | ||
26 | a single place where we can make the change rather than having | ||
27 | to touch multiple places in translate.c and translate-a64.c. | ||
28 | |||
29 | Fixes: https://bugs.launchpad.net/qemu/+bug/1926759 | ||
30 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
31 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
32 | Message-id: 20210430162212.825-1-peter.maydell@linaro.org | ||
33 | --- | ||
34 | target/arm/op_helper.c | 12 ++++++++++++ | ||
35 | 1 file changed, 12 insertions(+) | ||
36 | |||
37 | diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/target/arm/op_helper.c | ||
40 | +++ b/target/arm/op_helper.c | ||
41 | @@ -XXX,XX +XXX,XX @@ static inline int check_wfx_trap(CPUARMState *env, bool is_wfe) | ||
42 | |||
43 | void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) | ||
44 | { | ||
45 | +#ifdef CONFIG_USER_ONLY | ||
46 | + /* | ||
47 | + * WFI in the user-mode emulator is technically permitted but not | ||
48 | + * something any real-world code would do. AArch64 Linux kernels | ||
49 | + * trap it via SCTRL_EL1.nTWI and make it an (expensive) NOP; | ||
50 | + * AArch32 kernels don't trap it so it will delay a bit. | ||
51 | + * For QEMU, make it NOP here, because trying to raise EXCP_HLT | ||
52 | + * would trigger an abort. | ||
53 | + */ | ||
54 | + return; | ||
55 | +#else | ||
56 | CPUState *cs = env_cpu(env); | ||
57 | int target_el = check_wfx_trap(env, false); | ||
58 | |||
59 | @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) | ||
60 | cs->exception_index = EXCP_HLT; | ||
61 | cs->halted = 1; | ||
62 | cpu_loop_exit(cs); | ||
63 | +#endif | ||
64 | } | ||
65 | |||
66 | void HELPER(wfe)(CPUARMState *env) | ||
67 | -- | ||
68 | 2.20.1 | ||
69 | |||
70 | diff view generated by jsdifflib |