1 | target-arm queue: Eric's SMMUv3 patchset, and an array | 1 | The following changes since commit 5a67d7735d4162630769ef495cf813244fc850df: |
---|---|---|---|
2 | of minor bugfixes and improvements from various others. | ||
3 | 2 | ||
4 | thanks | 3 | Merge remote-tracking branch 'remotes/berrange-gitlab/tags/tls-deps-pull-request' into staging (2021-07-02 08:22:39 +0100) |
5 | -- PMM | ||
6 | |||
7 | The following changes since commit c8b7e627b4269a3bc3ae41d9f420547a47e6d9b9: | ||
8 | |||
9 | Merge remote-tracking branch 'remotes/ericb/tags/pull-nbd-2018-05-04' into staging (2018-05-04 14:42:46 +0100) | ||
10 | 4 | ||
11 | are available in the Git repository at: | 5 | are available in the Git repository at: |
12 | 6 | ||
13 | git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180504 | 7 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210702 |
14 | 8 | ||
15 | for you to fetch changes up to 5680740c92993e9b3f3e011f2a2c394070e33f56: | 9 | for you to fetch changes up to 04ea4d3cfd0a21b248ece8eb7a9436a3d9898dd8: |
16 | 10 | ||
17 | hw/arm/virt: Introduce the iommu option (2018-05-04 18:05:52 +0100) | 11 | target/arm: Implement MVE shifts by register (2021-07-02 11:48:38 +0100) |
18 | 12 | ||
19 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
20 | target-arm queue: | 14 | target-arm queue: |
21 | * Emulate the SMMUv3 (IOMMU); one will be created in the 'virt' board | 15 | * more MVE instructions |
22 | if the commandline includes "-machine iommu=smmuv3" | 16 | * hw/gpio/gpio_pwr: use shutdown function for reboot |
23 | * target/arm: Implement v8M VLLDM and VLSTM | 17 | * target/arm: Check NaN mode before silencing NaN |
24 | * hw/arm: Don't fail qtest due to missing SD card in -nodefaults mode | 18 | * tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
25 | * Some fixes to silence Coverity false-positives | 19 | * hw/arm: Add basic power management to raspi. |
26 | * arm: boot: set boot_info starting from first_cpu | 20 | * docs/system/arm: Add quanta-gbs-bmc, quanta-q7l1-bmc |
27 | (fixes a technical bug not visible in practice) | ||
28 | * hw/net/smc91c111: Convert away from old_mmio | ||
29 | * hw/usb/tusb6010: Convert away from old_mmio | ||
30 | * hw/char/cmsdk-apb-uart.c: Accept more input after character read | ||
31 | * target/arm: Make MPUIR write-ignored on OMAP, StrongARM | ||
32 | * hw/arm/virt: Add linux,pci-domain property | ||
33 | 21 | ||
34 | ---------------------------------------------------------------- | 22 | ---------------------------------------------------------------- |
35 | Eric Auger (11): | 23 | Joe Komlodi (1): |
36 | hw/arm/smmu-common: smmu base device and datatypes | 24 | target/arm: Check NaN mode before silencing NaN |
37 | hw/arm/smmu-common: IOMMU memory region and address space setup | ||
38 | hw/arm/smmu-common: VMSAv8-64 page table walk | ||
39 | hw/arm/smmuv3: Wired IRQ and GERROR helpers | ||
40 | hw/arm/smmuv3: Queue helpers | ||
41 | hw/arm/smmuv3: Implement MMIO write operations | ||
42 | hw/arm/smmuv3: Event queue recording helper | ||
43 | hw/arm/smmuv3: Implement translate callback | ||
44 | hw/arm/smmuv3: Abort on vfio or vhost case | ||
45 | target/arm/kvm: Translate the MSI doorbell in kvm_arch_fixup_msi_route | ||
46 | hw/arm/virt: Introduce the iommu option | ||
47 | 25 | ||
48 | Igor Mammedov (1): | 26 | Maxim Uvarov (1): |
49 | arm: boot: set boot_info starting from first_cpu | 27 | hw/gpio/gpio_pwr: use shutdown function for reboot |
50 | 28 | ||
51 | Jan Kiszka (1): | 29 | Nolan Leake (1): |
52 | hw/arm/virt: Add linux,pci-domain property | 30 | hw/arm: Add basic power management to raspi. |
53 | 31 | ||
54 | Mathew Maidment (1): | 32 | Patrick Venture (2): |
55 | target/arm: Correct MPUIR privilege level in register_cp_regs_for_features() conditional case | 33 | docs/system/arm: Add quanta-q7l1-bmc reference |
34 | docs/system/arm: Add quanta-gbs-bmc reference | ||
56 | 35 | ||
57 | Patrick Oppenlander (1): | 36 | Peter Maydell (18): |
58 | hw/char/cmsdk-apb-uart.c: Accept more input after character read | 37 | target/arm: Fix MVE widening/narrowing VLDR/VSTR offset calculation |
38 | target/arm: Fix bugs in MVE VRMLALDAVH, VRMLSLDAVH | ||
39 | target/arm: Make asimd_imm_const() public | ||
40 | target/arm: Use asimd_imm_const for A64 decode | ||
41 | target/arm: Use dup_const() instead of bitfield_replicate() | ||
42 | target/arm: Implement MVE logical immediate insns | ||
43 | target/arm: Implement MVE vector shift left by immediate insns | ||
44 | target/arm: Implement MVE vector shift right by immediate insns | ||
45 | target/arm: Implement MVE VSHLL | ||
46 | target/arm: Implement MVE VSRI, VSLI | ||
47 | target/arm: Implement MVE VSHRN, VRSHRN | ||
48 | target/arm: Implement MVE saturating narrowing shifts | ||
49 | target/arm: Implement MVE VSHLC | ||
50 | target/arm: Implement MVE VADDLV | ||
51 | target/arm: Implement MVE long shifts by immediate | ||
52 | target/arm: Implement MVE long shifts by register | ||
53 | target/arm: Implement MVE shifts by immediate | ||
54 | target/arm: Implement MVE shifts by register | ||
59 | 55 | ||
60 | Peter Maydell (3): | 56 | Philippe Mathieu-Daudé (1): |
61 | hw/usb/tusb6010: Convert away from old_mmio | 57 | tests: Boot and halt a Linux guest on the Raspberry Pi 2 machine |
62 | hw/net/smc91c111: Convert away from old_mmio | ||
63 | target/arm: Implement v8M VLLDM and VLSTM | ||
64 | 58 | ||
65 | Prem Mallappa (3): | 59 | docs/system/arm/aspeed.rst | 1 + |
66 | hw/arm/smmuv3: Skeleton | 60 | docs/system/arm/nuvoton.rst | 5 +- |
67 | hw/arm/virt: Add SMMUv3 to the virt board | 61 | include/hw/arm/bcm2835_peripherals.h | 3 +- |
68 | hw/arm/virt-acpi-build: Add smmuv3 node in IORT table | 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 | ||
69 | 82 | ||
70 | Richard Henderson (2): | ||
71 | target/arm: Tidy conditions in handle_vec_simd_shri | ||
72 | target/arm: Tidy condition in disas_simd_two_reg_misc | ||
73 | |||
74 | Thomas Huth (1): | ||
75 | hw/arm: Don't fail qtest due to missing SD card in -nodefaults mode | ||
76 | |||
77 | hw/arm/Makefile.objs | 1 + | ||
78 | hw/arm/smmu-internal.h | 99 +++ | ||
79 | hw/arm/smmuv3-internal.h | 621 ++++++++++++++++++ | ||
80 | include/hw/acpi/acpi-defs.h | 15 + | ||
81 | include/hw/arm/smmu-common.h | 145 +++++ | ||
82 | include/hw/arm/smmuv3.h | 87 +++ | ||
83 | include/hw/arm/virt.h | 10 + | ||
84 | hw/arm/boot.c | 2 +- | ||
85 | hw/arm/omap1.c | 8 +- | ||
86 | hw/arm/omap2.c | 8 +- | ||
87 | hw/arm/pxa2xx.c | 15 +- | ||
88 | hw/arm/smmu-common.c | 372 +++++++++++ | ||
89 | hw/arm/smmuv3.c | 1191 +++++++++++++++++++++++++++++++++++ | ||
90 | hw/arm/virt-acpi-build.c | 55 +- | ||
91 | hw/arm/virt.c | 101 ++- | ||
92 | hw/char/cmsdk-apb-uart.c | 1 + | ||
93 | hw/net/smc91c111.c | 54 +- | ||
94 | hw/usb/tusb6010.c | 40 +- | ||
95 | target/arm/helper.c | 2 +- | ||
96 | target/arm/kvm.c | 38 +- | ||
97 | target/arm/translate-a64.c | 12 +- | ||
98 | target/arm/translate.c | 17 +- | ||
99 | default-configs/aarch64-softmmu.mak | 1 + | ||
100 | hw/arm/trace-events | 37 ++ | ||
101 | target/arm/trace-events | 3 + | ||
102 | 25 files changed, 2868 insertions(+), 67 deletions(-) | ||
103 | create mode 100644 hw/arm/smmu-internal.h | ||
104 | create mode 100644 hw/arm/smmuv3-internal.h | ||
105 | create mode 100644 include/hw/arm/smmu-common.h | ||
106 | create mode 100644 include/hw/arm/smmuv3.h | ||
107 | create mode 100644 hw/arm/smmu-common.c | ||
108 | create mode 100644 hw/arm/smmuv3.c | ||
109 | diff view generated by jsdifflib |
1 | From: Patrick Oppenlander <patrick.oppenlander@gmail.com> | 1 | From: Patrick Venture <venture@google.com> |
---|---|---|---|
2 | 2 | ||
3 | The character frontend needs to be notified that the uart receive buffer | 3 | Adds a line-item reference to the supported quanta-q71l-bmc aspeed |
4 | is empty and ready to handle another character. | 4 | entry. |
5 | 5 | ||
6 | Previously, the uart only worked correctly when receiving one character | 6 | Signed-off-by: Patrick Venture <venture@google.com> |
7 | at a time. | 7 | Reviewed-by: Cédric Le Goater <clg@kaod.org> |
8 | 8 | Message-id: 20210615192848.1065297-2-venture@google.com | |
9 | Signed-off-by: Patrick Oppenlander <patrick.oppenlander@gmail.com> | ||
10 | Message-id: CAEg67GkRTw=cXei3o9hvpxG_L4zSrNzR0bFyAgny+sSEUb_kPw@mail.gmail.com | ||
11 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
13 | --- | 10 | --- |
14 | hw/char/cmsdk-apb-uart.c | 1 + | 11 | docs/system/arm/aspeed.rst | 1 + |
15 | 1 file changed, 1 insertion(+) | 12 | 1 file changed, 1 insertion(+) |
16 | 13 | ||
17 | diff --git a/hw/char/cmsdk-apb-uart.c b/hw/char/cmsdk-apb-uart.c | 14 | diff --git a/docs/system/arm/aspeed.rst b/docs/system/arm/aspeed.rst |
18 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/hw/char/cmsdk-apb-uart.c | 16 | --- a/docs/system/arm/aspeed.rst |
20 | +++ b/hw/char/cmsdk-apb-uart.c | 17 | +++ b/docs/system/arm/aspeed.rst |
21 | @@ -XXX,XX +XXX,XX @@ static uint64_t uart_read(void *opaque, hwaddr offset, unsigned size) | 18 | @@ -XXX,XX +XXX,XX @@ etc. |
22 | r = s->rxbuf; | 19 | AST2400 SoC based machines : |
23 | s->state &= ~R_STATE_RXFULL_MASK; | 20 | |
24 | cmsdk_apb_uart_update(s); | 21 | - ``palmetto-bmc`` OpenPOWER Palmetto POWER8 BMC |
25 | + qemu_chr_fe_accept_input(&s->chr); | 22 | +- ``quanta-q71l-bmc`` OpenBMC Quanta BMC |
26 | break; | 23 | |
27 | case A_STATE: | 24 | AST2500 SoC based machines : |
28 | r = s->state; | 25 | |
29 | -- | 26 | -- |
30 | 2.17.0 | 27 | 2.20.1 |
31 | 28 | ||
32 | 29 | diff view generated by jsdifflib |
1 | From: Jan Kiszka <jan.kiszka@siemens.com> | 1 | From: Patrick Venture <venture@google.com> |
---|---|---|---|
2 | 2 | ||
3 | This allows to pin the host controller in the Linux PCI domain space. | 3 | Add line item reference to quanta-gbs-bmc machine. |
4 | Linux requires that property to be available consistently or not at all, | ||
5 | in which case the domain number becomes unstable on additions/removals. | ||
6 | Adding it here won't make a difference in practice for most setups as we | ||
7 | only expose one controller. | ||
8 | 4 | ||
9 | However, enabling Jailhouse on top may introduce another controller, and | 5 | Signed-off-by: Patrick Venture <venture@google.com> |
10 | that one would like to have stable address as well. So the property is | 6 | Reviewed-by: Cédric Le Goater <clg@kaod.org> |
11 | needed for the first controller as well. | 7 | Message-id: 20210615192848.1065297-3-venture@google.com |
12 | 8 | [PMM: fixed underline Sphinx warning] | |
13 | Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> | ||
14 | Message-id: 3301c5bc-7b47-1b0e-8ce4-30435057a276@web.de | ||
15 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
16 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
17 | --- | 10 | --- |
18 | hw/arm/virt.c | 1 + | 11 | docs/system/arm/nuvoton.rst | 5 +++-- |
19 | 1 file changed, 1 insertion(+) | 12 | 1 file changed, 3 insertions(+), 2 deletions(-) |
20 | 13 | ||
21 | diff --git a/hw/arm/virt.c b/hw/arm/virt.c | 14 | diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst |
22 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/hw/arm/virt.c | 16 | --- a/docs/system/arm/nuvoton.rst |
24 | +++ b/hw/arm/virt.c | 17 | +++ b/docs/system/arm/nuvoton.rst |
25 | @@ -XXX,XX +XXX,XX @@ static void create_pcie(const VirtMachineState *vms, qemu_irq *pic) | 18 | @@ -XXX,XX +XXX,XX @@ |
26 | qemu_fdt_setprop_string(vms->fdt, nodename, "device_type", "pci"); | 19 | -Nuvoton iBMC boards (``npcm750-evb``, ``quanta-gsj``) |
27 | qemu_fdt_setprop_cell(vms->fdt, nodename, "#address-cells", 3); | 20 | -===================================================== |
28 | qemu_fdt_setprop_cell(vms->fdt, nodename, "#size-cells", 2); | 21 | +Nuvoton iBMC boards (``*-bmc``, ``npcm750-evb``, ``quanta-gsj``) |
29 | + qemu_fdt_setprop_cell(vms->fdt, nodename, "linux,pci-domain", 0); | 22 | +================================================================ |
30 | qemu_fdt_setprop_cells(vms->fdt, nodename, "bus-range", 0, | 23 | |
31 | nr_pcie_buses - 1); | 24 | The `Nuvoton iBMC`_ chips (NPCM7xx) are a family of ARM-based SoCs that are |
32 | qemu_fdt_setprop(vms->fdt, nodename, "dma-coherent", NULL, 0); | 25 | designed to be used as Baseboard Management Controllers (BMCs) in various |
26 | @@ -XXX,XX +XXX,XX @@ segment. The following machines are based on this chip : | ||
27 | The NPCM730 SoC has two Cortex-A9 cores and is targeted for Data Center and | ||
28 | Hyperscale applications. The following machines are based on this chip : | ||
29 | |||
30 | +- ``quanta-gbs-bmc`` Quanta GBS server BMC | ||
31 | - ``quanta-gsj`` Quanta GSJ server BMC | ||
32 | |||
33 | There are also two more SoCs, NPCM710 and NPCM705, which are single-core | ||
33 | -- | 34 | -- |
34 | 2.17.0 | 35 | 2.20.1 |
35 | 36 | ||
36 | 37 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | From: Nolan Leake <nolan@sigbus.net> |
---|---|---|---|
2 | 2 | ||
3 | The patch introduces the smmu base device and class for the ARM | 3 | This is just enough to make reboot and poweroff work. Works for |
4 | smmu. Devices for specific versions will be derived from this | 4 | linux, u-boot, and the arm trusted firmware. Not tested, but should |
5 | base device. | 5 | work for plan9, and bare-metal/hobby OSes, since they seem to generally |
6 | 6 | do what linux does for reset. | |
7 | We also introduce some important datatypes. | 7 | |
8 | 8 | The watchdog timer functionality is not yet implemented. | |
9 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 9 | |
10 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | 10 | Resolves: https://gitlab.com/qemu-project/qemu/-/issues/64 |
11 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Nolan Leake <nolan@sigbus.net> |
12 | Message-id: 1524665762-31355-2-git-send-email-eric.auger@redhat.com | 12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
13 | Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
14 | Message-id: 20210625210209.1870217-1-nolan@sigbus.net | ||
15 | [PMM: tweaked commit title; fixed region size to 0x200; | ||
16 | moved header file to include/] | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | --- | 18 | --- |
15 | hw/arm/Makefile.objs | 1 + | 19 | include/hw/arm/bcm2835_peripherals.h | 3 +- |
16 | include/hw/arm/smmu-common.h | 123 ++++++++++++++++++++++++++++ | 20 | include/hw/misc/bcm2835_powermgt.h | 29 +++++ |
17 | hw/arm/smmu-common.c | 81 ++++++++++++++++++ | 21 | hw/arm/bcm2835_peripherals.c | 13 ++- |
18 | default-configs/aarch64-softmmu.mak | 1 + | 22 | hw/misc/bcm2835_powermgt.c | 160 +++++++++++++++++++++++++++ |
19 | 4 files changed, 206 insertions(+) | 23 | hw/misc/meson.build | 1 + |
20 | create mode 100644 include/hw/arm/smmu-common.h | 24 | 5 files changed, 204 insertions(+), 2 deletions(-) |
21 | create mode 100644 hw/arm/smmu-common.c | 25 | create mode 100644 include/hw/misc/bcm2835_powermgt.h |
22 | 26 | create mode 100644 hw/misc/bcm2835_powermgt.c | |
23 | diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs | 27 | |
28 | diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | 29 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/hw/arm/Makefile.objs | 30 | --- a/include/hw/arm/bcm2835_peripherals.h |
26 | +++ b/hw/arm/Makefile.objs | 31 | +++ b/include/hw/arm/bcm2835_peripherals.h |
27 | @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_MPS2) += mps2-tz.o | 32 | @@ -XXX,XX +XXX,XX @@ |
28 | obj-$(CONFIG_MSF2) += msf2-soc.o msf2-som.o | 33 | #include "hw/misc/bcm2835_mphi.h" |
29 | obj-$(CONFIG_IOTKIT) += iotkit.o | 34 | #include "hw/misc/bcm2835_thermal.h" |
30 | obj-$(CONFIG_FSL_IMX7) += fsl-imx7.o mcimx7d-sabre.o | 35 | #include "hw/misc/bcm2835_cprman.h" |
31 | +obj-$(CONFIG_ARM_SMMUV3) += smmu-common.o | 36 | +#include "hw/misc/bcm2835_powermgt.h" |
32 | diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.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 | ||
33 | new file mode 100644 | 50 | new file mode 100644 |
34 | index XXXXXXX..XXXXXXX | 51 | index XXXXXXX..XXXXXXX |
35 | --- /dev/null | 52 | --- /dev/null |
36 | +++ b/include/hw/arm/smmu-common.h | 53 | +++ b/include/hw/misc/bcm2835_powermgt.h |
37 | @@ -XXX,XX +XXX,XX @@ | 54 | @@ -XXX,XX +XXX,XX @@ |
38 | +/* | 55 | +/* |
39 | + * ARM SMMU Support | 56 | + * BCM2835 Power Management emulation |
40 | + * | 57 | + * |
41 | + * Copyright (C) 2015-2016 Broadcom Corporation | 58 | + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> |
42 | + * Copyright (c) 2017 Red Hat, Inc. | 59 | + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> |
43 | + * Written by Prem Mallappa, Eric Auger | 60 | + * |
44 | + * | 61 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. |
45 | + * This program is free software; you can redistribute it and/or modify | 62 | + * See the COPYING file in the top-level directory. |
46 | + * it under the terms of the GNU General Public License version 2 as | ||
47 | + * published by the Free Software Foundation. | ||
48 | + * | ||
49 | + * This program is distributed in the hope that it will be useful, | ||
50 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
51 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
52 | + * GNU General Public License for more details. | ||
53 | + * | ||
54 | + */ | 63 | + */ |
55 | + | 64 | + |
56 | +#ifndef HW_ARM_SMMU_COMMON_H | 65 | +#ifndef BCM2835_POWERMGT_H |
57 | +#define HW_ARM_SMMU_COMMON_H | 66 | +#define BCM2835_POWERMGT_H |
58 | + | 67 | + |
59 | +#include "hw/sysbus.h" | 68 | +#include "hw/sysbus.h" |
60 | +#include "hw/pci/pci.h" | 69 | +#include "qom/object.h" |
61 | + | 70 | + |
62 | +#define SMMU_PCI_BUS_MAX 256 | 71 | +#define TYPE_BCM2835_POWERMGT "bcm2835-powermgt" |
63 | +#define SMMU_PCI_DEVFN_MAX 256 | 72 | +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835PowerMgtState, BCM2835_POWERMGT) |
64 | + | 73 | + |
65 | +#define SMMU_MAX_VA_BITS 48 | 74 | +struct BCM2835PowerMgtState { |
66 | + | 75 | + SysBusDevice busdev; |
67 | +/* | ||
68 | + * Page table walk error types | ||
69 | + */ | ||
70 | +typedef enum { | ||
71 | + SMMU_PTW_ERR_NONE, | ||
72 | + SMMU_PTW_ERR_WALK_EABT, /* Translation walk external abort */ | ||
73 | + SMMU_PTW_ERR_TRANSLATION, /* Translation fault */ | ||
74 | + SMMU_PTW_ERR_ADDR_SIZE, /* Address Size fault */ | ||
75 | + SMMU_PTW_ERR_ACCESS, /* Access fault */ | ||
76 | + SMMU_PTW_ERR_PERMISSION, /* Permission fault */ | ||
77 | +} SMMUPTWEventType; | ||
78 | + | ||
79 | +typedef struct SMMUPTWEventInfo { | ||
80 | + SMMUPTWEventType type; | ||
81 | + dma_addr_t addr; /* fetched address that induced an abort, if any */ | ||
82 | +} SMMUPTWEventInfo; | ||
83 | + | ||
84 | +typedef struct SMMUTransTableInfo { | ||
85 | + bool disabled; /* is the translation table disabled? */ | ||
86 | + uint64_t ttb; /* TT base address */ | ||
87 | + uint8_t tsz; /* input range, ie. 2^(64 -tsz)*/ | ||
88 | + uint8_t granule_sz; /* granule page shift */ | ||
89 | +} SMMUTransTableInfo; | ||
90 | + | ||
91 | +/* | ||
92 | + * Generic structure populated by derived SMMU devices | ||
93 | + * after decoding the configuration information and used as | ||
94 | + * input to the page table walk | ||
95 | + */ | ||
96 | +typedef struct SMMUTransCfg { | ||
97 | + int stage; /* translation stage */ | ||
98 | + bool aa64; /* arch64 or aarch32 translation table */ | ||
99 | + bool disabled; /* smmu is disabled */ | ||
100 | + bool bypassed; /* translation is bypassed */ | ||
101 | + bool aborted; /* translation is aborted */ | ||
102 | + uint64_t ttb; /* TT base address */ | ||
103 | + uint8_t oas; /* output address width */ | ||
104 | + uint8_t tbi; /* Top Byte Ignore */ | ||
105 | + uint16_t asid; | ||
106 | + SMMUTransTableInfo tt[2]; | ||
107 | +} SMMUTransCfg; | ||
108 | + | ||
109 | +typedef struct SMMUDevice { | ||
110 | + void *smmu; | ||
111 | + PCIBus *bus; | ||
112 | + int devfn; | ||
113 | + IOMMUMemoryRegion iommu; | ||
114 | + AddressSpace as; | ||
115 | +} SMMUDevice; | ||
116 | + | ||
117 | +typedef struct SMMUNotifierNode { | ||
118 | + SMMUDevice *sdev; | ||
119 | + QLIST_ENTRY(SMMUNotifierNode) next; | ||
120 | +} SMMUNotifierNode; | ||
121 | + | ||
122 | +typedef struct SMMUPciBus { | ||
123 | + PCIBus *bus; | ||
124 | + SMMUDevice *pbdev[0]; /* Parent array is sparse, so dynamically alloc */ | ||
125 | +} SMMUPciBus; | ||
126 | + | ||
127 | +typedef struct SMMUState { | ||
128 | + /* <private> */ | ||
129 | + SysBusDevice dev; | ||
130 | + const char *mrtypename; | ||
131 | + MemoryRegion iomem; | 76 | + MemoryRegion iomem; |
132 | + | 77 | + |
133 | + GHashTable *smmu_pcibus_by_busptr; | 78 | + uint32_t rstc; |
134 | + GHashTable *configs; /* cache for configuration data */ | 79 | + uint32_t rsts; |
135 | + GHashTable *iotlb; | 80 | + uint32_t wdog; |
136 | + SMMUPciBus *smmu_pcibus_by_bus_num[SMMU_PCI_BUS_MAX]; | 81 | +}; |
137 | + PCIBus *pci_bus; | 82 | + |
138 | + QLIST_HEAD(, SMMUNotifierNode) notifiers_list; | 83 | +#endif |
139 | + uint8_t bus_num; | 84 | diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c |
140 | + PCIBus *primary_bus; | 85 | index XXXXXXX..XXXXXXX 100644 |
141 | +} SMMUState; | 86 | --- a/hw/arm/bcm2835_peripherals.c |
142 | + | 87 | +++ b/hw/arm/bcm2835_peripherals.c |
143 | +typedef struct { | 88 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) |
144 | + /* <private> */ | 89 | |
145 | + SysBusDeviceClass parent_class; | 90 | object_property_add_const_link(OBJECT(&s->dwc2), "dma-mr", |
146 | + | 91 | OBJECT(&s->gpu_bus_mr)); |
147 | + /*< public >*/ | 92 | + |
148 | + | 93 | + /* Power Management */ |
149 | + DeviceRealize parent_realize; | 94 | + object_initialize_child(obj, "powermgt", &s->powermgt, |
150 | + | 95 | + TYPE_BCM2835_POWERMGT); |
151 | +} SMMUBaseClass; | 96 | } |
152 | + | 97 | |
153 | +#define TYPE_ARM_SMMU "arm-smmu" | 98 | static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) |
154 | +#define ARM_SMMU(obj) OBJECT_CHECK(SMMUState, (obj), TYPE_ARM_SMMU) | 99 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) |
155 | +#define ARM_SMMU_CLASS(klass) \ | 100 | qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, |
156 | + OBJECT_CLASS_CHECK(SMMUBaseClass, (klass), TYPE_ARM_SMMU) | 101 | INTERRUPT_USB)); |
157 | +#define ARM_SMMU_GET_CLASS(obj) \ | 102 | |
158 | + OBJECT_GET_CLASS(SMMUBaseClass, (obj), TYPE_ARM_SMMU) | 103 | + /* Power Management */ |
159 | + | 104 | + if (!sysbus_realize(SYS_BUS_DEVICE(&s->powermgt), errp)) { |
160 | +#endif /* HW_ARM_SMMU_COMMON */ | 105 | + return; |
161 | diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c | 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 | ||
162 | new file mode 100644 | 118 | new file mode 100644 |
163 | index XXXXXXX..XXXXXXX | 119 | index XXXXXXX..XXXXXXX |
164 | --- /dev/null | 120 | --- /dev/null |
165 | +++ b/hw/arm/smmu-common.c | 121 | +++ b/hw/misc/bcm2835_powermgt.c |
166 | @@ -XXX,XX +XXX,XX @@ | 122 | @@ -XXX,XX +XXX,XX @@ |
167 | +/* | 123 | +/* |
168 | + * Copyright (C) 2014-2016 Broadcom Corporation | 124 | + * BCM2835 Power Management emulation |
169 | + * Copyright (c) 2017 Red Hat, Inc. | 125 | + * |
170 | + * Written by Prem Mallappa, Eric Auger | 126 | + * Copyright (C) 2017 Marcin Chojnacki <marcinch7@gmail.com> |
171 | + * | 127 | + * Copyright (C) 2021 Nolan Leake <nolan@sigbus.net> |
172 | + * This program is free software; you can redistribute it and/or modify | 128 | + * |
173 | + * it under the terms of the GNU General Public License version 2 as | 129 | + * This work is licensed under the terms of the GNU GPL, version 2 or later. |
174 | + * published by the Free Software Foundation. | 130 | + * See the COPYING file in the top-level directory. |
175 | + * | ||
176 | + * This program is distributed in the hope that it will be useful, | ||
177 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
178 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
179 | + * GNU General Public License for more details. | ||
180 | + * | ||
181 | + * Author: Prem Mallappa <pmallapp@broadcom.com> | ||
182 | + * | ||
183 | + */ | 131 | + */ |
184 | + | 132 | + |
185 | +#include "qemu/osdep.h" | 133 | +#include "qemu/osdep.h" |
186 | +#include "sysemu/sysemu.h" | 134 | +#include "qemu/log.h" |
187 | +#include "exec/address-spaces.h" | 135 | +#include "qemu/module.h" |
188 | +#include "trace.h" | 136 | +#include "hw/misc/bcm2835_powermgt.h" |
189 | +#include "exec/target_page.h" | 137 | +#include "migration/vmstate.h" |
190 | +#include "qom/cpu.h" | 138 | +#include "sysemu/runstate.h" |
191 | +#include "hw/qdev-properties.h" | 139 | + |
192 | +#include "qapi/error.h" | 140 | +#define PASSWORD 0x5a000000 |
193 | + | 141 | +#define PASSWORD_MASK 0xff000000 |
194 | +#include "qemu/error-report.h" | 142 | + |
195 | +#include "hw/arm/smmu-common.h" | 143 | +#define R_RSTC 0x1c |
196 | + | 144 | +#define V_RSTC_RESET 0x20 |
197 | +static void smmu_base_realize(DeviceState *dev, Error **errp) | 145 | +#define R_RSTS 0x20 |
198 | +{ | 146 | +#define V_RSTS_POWEROFF 0x555 /* Linux uses partition 63 to indicate halt. */ |
199 | + SMMUBaseClass *sbc = ARM_SMMU_GET_CLASS(dev); | 147 | +#define R_WDOG 0x24 |
200 | + Error *local_err = NULL; | 148 | + |
201 | + | 149 | +static uint64_t bcm2835_powermgt_read(void *opaque, hwaddr offset, |
202 | + sbc->parent_realize(dev, &local_err); | 150 | + unsigned size) |
203 | + if (local_err) { | 151 | +{ |
204 | + error_propagate(errp, local_err); | 152 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; |
153 | + uint32_t res = 0; | ||
154 | + | ||
155 | + switch (offset) { | ||
156 | + case R_RSTC: | ||
157 | + res = s->rstc; | ||
158 | + break; | ||
159 | + case R_RSTS: | ||
160 | + res = s->rsts; | ||
161 | + break; | ||
162 | + case R_WDOG: | ||
163 | + res = s->wdog; | ||
164 | + break; | ||
165 | + | ||
166 | + default: | ||
167 | + qemu_log_mask(LOG_UNIMP, | ||
168 | + "bcm2835_powermgt_read: Unknown offset 0x%08"HWADDR_PRIx | ||
169 | + "\n", offset); | ||
170 | + res = 0; | ||
171 | + break; | ||
172 | + } | ||
173 | + | ||
174 | + return res; | ||
175 | +} | ||
176 | + | ||
177 | +static void bcm2835_powermgt_write(void *opaque, hwaddr offset, | ||
178 | + uint64_t value, unsigned size) | ||
179 | +{ | ||
180 | + BCM2835PowerMgtState *s = (BCM2835PowerMgtState *)opaque; | ||
181 | + | ||
182 | + if ((value & PASSWORD_MASK) != PASSWORD) { | ||
183 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
184 | + "bcm2835_powermgt_write: Bad password 0x%"PRIx64 | ||
185 | + " at offset 0x%08"HWADDR_PRIx"\n", | ||
186 | + value, offset); | ||
205 | + return; | 187 | + return; |
206 | + } | 188 | + } |
207 | +} | 189 | + |
208 | + | 190 | + value = value & ~PASSWORD_MASK; |
209 | +static void smmu_base_reset(DeviceState *dev) | 191 | + |
210 | +{ | 192 | + switch (offset) { |
211 | + /* will be filled later on */ | 193 | + case R_RSTC: |
212 | +} | 194 | + s->rstc = value; |
213 | + | 195 | + if (value & V_RSTC_RESET) { |
214 | +static Property smmu_dev_properties[] = { | 196 | + if ((s->rsts & 0xfff) == V_RSTS_POWEROFF) { |
215 | + DEFINE_PROP_UINT8("bus_num", SMMUState, bus_num, 0), | 197 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
216 | + DEFINE_PROP_LINK("primary-bus", SMMUState, primary_bus, "PCI", PCIBus *), | 198 | + } else { |
217 | + DEFINE_PROP_END_OF_LIST(), | 199 | + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); |
218 | +}; | 200 | + } |
219 | + | 201 | + } |
220 | +static void smmu_base_class_init(ObjectClass *klass, void *data) | 202 | + break; |
203 | + case R_RSTS: | ||
204 | + qemu_log_mask(LOG_UNIMP, | ||
205 | + "bcm2835_powermgt_write: RSTS\n"); | ||
206 | + s->rsts = value; | ||
207 | + break; | ||
208 | + case R_WDOG: | ||
209 | + qemu_log_mask(LOG_UNIMP, | ||
210 | + "bcm2835_powermgt_write: WDOG\n"); | ||
211 | + s->wdog = value; | ||
212 | + break; | ||
213 | + | ||
214 | + default: | ||
215 | + qemu_log_mask(LOG_UNIMP, | ||
216 | + "bcm2835_powermgt_write: Unknown offset 0x%08"HWADDR_PRIx | ||
217 | + "\n", offset); | ||
218 | + break; | ||
219 | + } | ||
220 | +} | ||
221 | + | ||
222 | +static const MemoryRegionOps bcm2835_powermgt_ops = { | ||
223 | + .read = bcm2835_powermgt_read, | ||
224 | + .write = bcm2835_powermgt_write, | ||
225 | + .endianness = DEVICE_NATIVE_ENDIAN, | ||
226 | + .impl.min_access_size = 4, | ||
227 | + .impl.max_access_size = 4, | ||
228 | +}; | ||
229 | + | ||
230 | +static const VMStateDescription vmstate_bcm2835_powermgt = { | ||
231 | + .name = TYPE_BCM2835_POWERMGT, | ||
232 | + .version_id = 1, | ||
233 | + .minimum_version_id = 1, | ||
234 | + .fields = (VMStateField[]) { | ||
235 | + VMSTATE_UINT32(rstc, BCM2835PowerMgtState), | ||
236 | + VMSTATE_UINT32(rsts, BCM2835PowerMgtState), | ||
237 | + VMSTATE_UINT32(wdog, BCM2835PowerMgtState), | ||
238 | + VMSTATE_END_OF_LIST() | ||
239 | + } | ||
240 | +}; | ||
241 | + | ||
242 | +static void bcm2835_powermgt_init(Object *obj) | ||
243 | +{ | ||
244 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(obj); | ||
245 | + | ||
246 | + memory_region_init_io(&s->iomem, obj, &bcm2835_powermgt_ops, s, | ||
247 | + TYPE_BCM2835_POWERMGT, 0x200); | ||
248 | + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); | ||
249 | +} | ||
250 | + | ||
251 | +static void bcm2835_powermgt_reset(DeviceState *dev) | ||
252 | +{ | ||
253 | + BCM2835PowerMgtState *s = BCM2835_POWERMGT(dev); | ||
254 | + | ||
255 | + /* https://elinux.org/BCM2835_registers#PM */ | ||
256 | + s->rstc = 0x00000102; | ||
257 | + s->rsts = 0x00001000; | ||
258 | + s->wdog = 0x00000000; | ||
259 | +} | ||
260 | + | ||
261 | +static void bcm2835_powermgt_class_init(ObjectClass *klass, void *data) | ||
221 | +{ | 262 | +{ |
222 | + DeviceClass *dc = DEVICE_CLASS(klass); | 263 | + DeviceClass *dc = DEVICE_CLASS(klass); |
223 | + SMMUBaseClass *sbc = ARM_SMMU_CLASS(klass); | 264 | + |
224 | + | 265 | + dc->reset = bcm2835_powermgt_reset; |
225 | + dc->props = smmu_dev_properties; | 266 | + dc->vmsd = &vmstate_bcm2835_powermgt; |
226 | + device_class_set_parent_realize(dc, smmu_base_realize, | 267 | +} |
227 | + &sbc->parent_realize); | 268 | + |
228 | + dc->reset = smmu_base_reset; | 269 | +static TypeInfo bcm2835_powermgt_info = { |
229 | +} | 270 | + .name = TYPE_BCM2835_POWERMGT, |
230 | + | ||
231 | +static const TypeInfo smmu_base_info = { | ||
232 | + .name = TYPE_ARM_SMMU, | ||
233 | + .parent = TYPE_SYS_BUS_DEVICE, | 271 | + .parent = TYPE_SYS_BUS_DEVICE, |
234 | + .instance_size = sizeof(SMMUState), | 272 | + .instance_size = sizeof(BCM2835PowerMgtState), |
235 | + .class_data = NULL, | 273 | + .class_init = bcm2835_powermgt_class_init, |
236 | + .class_size = sizeof(SMMUBaseClass), | 274 | + .instance_init = bcm2835_powermgt_init, |
237 | + .class_init = smmu_base_class_init, | 275 | +}; |
238 | + .abstract = true, | 276 | + |
239 | +}; | 277 | +static void bcm2835_powermgt_register_types(void) |
240 | + | 278 | +{ |
241 | +static void smmu_base_register_types(void) | 279 | + type_register_static(&bcm2835_powermgt_info); |
242 | +{ | 280 | +} |
243 | + type_register_static(&smmu_base_info); | 281 | + |
244 | +} | 282 | +type_init(bcm2835_powermgt_register_types) |
245 | + | 283 | diff --git a/hw/misc/meson.build b/hw/misc/meson.build |
246 | +type_init(smmu_base_register_types) | ||
247 | + | ||
248 | diff --git a/default-configs/aarch64-softmmu.mak b/default-configs/aarch64-softmmu.mak | ||
249 | index XXXXXXX..XXXXXXX 100644 | 284 | index XXXXXXX..XXXXXXX 100644 |
250 | --- a/default-configs/aarch64-softmmu.mak | 285 | --- a/hw/misc/meson.build |
251 | +++ b/default-configs/aarch64-softmmu.mak | 286 | +++ b/hw/misc/meson.build |
252 | @@ -XXX,XX +XXX,XX @@ CONFIG_DDC=y | 287 | @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( |
253 | CONFIG_DPCD=y | 288 | 'bcm2835_rng.c', |
254 | CONFIG_XLNX_ZYNQMP=y | 289 | 'bcm2835_thermal.c', |
255 | CONFIG_XLNX_ZYNQMP_ARM=y | 290 | 'bcm2835_cprman.c', |
256 | +CONFIG_ARM_SMMUV3=y | 291 | + 'bcm2835_powermgt.c', |
292 | )) | ||
293 | softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) | ||
294 | softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) | ||
257 | -- | 295 | -- |
258 | 2.17.0 | 296 | 2.20.1 |
259 | 297 | ||
260 | 298 | diff view generated by jsdifflib |
1 | From: Thomas Huth <thuth@redhat.com> | 1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> |
---|---|---|---|
2 | 2 | ||
3 | When running omap1/2 or pxa2xx based ARM machines with -nodefaults, | 3 | Add a test booting and quickly shutdown a raspi2 machine, |
4 | they bail out immediately complaining about a "missing SecureDigital | 4 | to test the power management model: |
5 | device". That's not how the "default" devices in vl.c are meant to | ||
6 | work - it should be possible for a board to also start up without | ||
7 | default devices. So let's turn the error message and exit() into | ||
8 | a warning instead. | ||
9 | 5 | ||
10 | Signed-off-by: Thomas Huth <thuth@redhat.com> | 6 | (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_raspi2_initrd: |
11 | Message-id: 1525326811-3233-1-git-send-email-thuth@redhat.com | 7 | console: [ 0.000000] Booting Linux on physical CPU 0xf00 |
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 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 |
13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 9 | console: [ 0.000000] CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=10c5387d |
10 | console: [ 0.000000] CPU: div instructions available: patching division code | ||
11 | console: [ 0.000000] CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache | ||
12 | console: [ 0.000000] OF: fdt: Machine model: Raspberry Pi 2 Model B | ||
13 | ... | ||
14 | console: Boot successful. | ||
15 | console: cat /proc/cpuinfo | ||
16 | console: / # cat /proc/cpuinfo | ||
17 | ... | ||
18 | console: processor : 3 | ||
19 | console: model name : ARMv7 Processor rev 5 (v7l) | ||
20 | console: BogoMIPS : 125.00 | ||
21 | console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm | ||
22 | console: CPU implementer : 0x41 | ||
23 | console: CPU architecture: 7 | ||
24 | console: CPU variant : 0x0 | ||
25 | console: CPU part : 0xc07 | ||
26 | console: CPU revision : 5 | ||
27 | console: Hardware : BCM2835 | ||
28 | console: Revision : 0000 | ||
29 | console: Serial : 0000000000000000 | ||
30 | console: cat /proc/iomem | ||
31 | console: / # cat /proc/iomem | ||
32 | console: 00000000-3bffffff : System RAM | ||
33 | console: 00008000-00afffff : Kernel code | ||
34 | console: 00c00000-00d468ef : Kernel data | ||
35 | console: 3f006000-3f006fff : dwc_otg | ||
36 | console: 3f007000-3f007eff : /soc/dma@7e007000 | ||
37 | console: 3f00b880-3f00b8bf : /soc/mailbox@7e00b880 | ||
38 | console: 3f100000-3f100027 : /soc/watchdog@7e100000 | ||
39 | console: 3f101000-3f102fff : /soc/cprman@7e101000 | ||
40 | console: 3f200000-3f2000b3 : /soc/gpio@7e200000 | ||
41 | PASS (24.59 s) | ||
42 | RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 | ||
43 | JOB TIME : 25.02 s | ||
44 | |||
45 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
46 | Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> | ||
47 | Message-id: 20210531113837.1689775-1-f4bug@amsat.org | ||
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 48 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
15 | --- | 49 | --- |
16 | hw/arm/omap1.c | 8 ++++---- | 50 | tests/acceptance/boot_linux_console.py | 43 ++++++++++++++++++++++++++ |
17 | hw/arm/omap2.c | 8 ++++---- | 51 | 1 file changed, 43 insertions(+) |
18 | hw/arm/pxa2xx.c | 15 +++++++-------- | ||
19 | 3 files changed, 15 insertions(+), 16 deletions(-) | ||
20 | 52 | ||
21 | diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c | 53 | diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py |
22 | index XXXXXXX..XXXXXXX 100644 | 54 | index XXXXXXX..XXXXXXX 100644 |
23 | --- a/hw/arm/omap1.c | 55 | --- a/tests/acceptance/boot_linux_console.py |
24 | +++ b/hw/arm/omap1.c | 56 | +++ b/tests/acceptance/boot_linux_console.py |
25 | @@ -XXX,XX +XXX,XX @@ | 57 | @@ -XXX,XX +XXX,XX @@ |
26 | #include "hw/arm/soc_dma.h" | 58 | from avocado import skip |
27 | #include "sysemu/block-backend.h" | 59 | from avocado import skipUnless |
28 | #include "sysemu/blockdev.h" | 60 | from avocado_qemu import Test |
29 | +#include "sysemu/qtest.h" | 61 | +from avocado_qemu import exec_command |
30 | #include "qemu/range.h" | 62 | from avocado_qemu import exec_command_and_wait_for_pattern |
31 | #include "hw/sysbus.h" | 63 | from avocado_qemu import interrupt_interactive_console_until_pattern |
32 | #include "qemu/cutils.h" | 64 | from avocado_qemu import wait_for_console_pattern |
33 | @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s *omap310_mpu_init(MemoryRegion *system_memory, | 65 | @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): |
34 | omap_findclk(s, "dpll3")); | 66 | """ |
35 | 67 | self.do_test_arm_raspi2(0) | |
36 | dinfo = drive_get(IF_SD, 0, 0); | 68 | |
37 | - if (!dinfo) { | 69 | + def test_arm_raspi2_initrd(self): |
38 | - error_report("missing SecureDigital device"); | 70 | + """ |
39 | - exit(1); | 71 | + :avocado: tags=arch:arm |
40 | + if (!dinfo && !qtest_enabled()) { | 72 | + :avocado: tags=machine:raspi2 |
41 | + warn_report("missing SecureDigital device"); | 73 | + """ |
42 | } | 74 | + deb_url = ('http://archive.raspberrypi.org/debian/' |
43 | s->mmc = omap_mmc_init(0xfffb7800, system_memory, | 75 | + 'pool/main/r/raspberrypi-firmware/' |
44 | - blk_by_legacy_dinfo(dinfo), | 76 | + 'raspberrypi-kernel_1.20190215-1_armhf.deb') |
45 | + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, | 77 | + deb_hash = 'cd284220b32128c5084037553db3c482426f3972' |
46 | qdev_get_gpio_in(s->ih[1], OMAP_INT_OQN), | 78 | + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) |
47 | &s->drq[OMAP_DMA_MMC_TX], | 79 | + kernel_path = self.extract_from_deb(deb_path, '/boot/kernel7.img') |
48 | omap_findclk(s, "mmc_ck")); | 80 | + dtb_path = self.extract_from_deb(deb_path, '/boot/bcm2709-rpi-2-b.dtb') |
49 | diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c | 81 | + |
50 | index XXXXXXX..XXXXXXX 100644 | 82 | + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' |
51 | --- a/hw/arm/omap2.c | 83 | + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' |
52 | +++ b/hw/arm/omap2.c | 84 | + 'arm/rootfs-armv7a.cpio.gz') |
53 | @@ -XXX,XX +XXX,XX @@ | 85 | + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' |
54 | #include "cpu.h" | 86 | + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) |
55 | #include "sysemu/block-backend.h" | 87 | + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') |
56 | #include "sysemu/blockdev.h" | 88 | + archive.gzip_uncompress(initrd_path_gz, initrd_path) |
57 | +#include "sysemu/qtest.h" | 89 | + |
58 | #include "hw/boards.h" | 90 | + self.vm.set_console() |
59 | #include "hw/hw.h" | 91 | + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + |
60 | #include "hw/arm/arm.h" | 92 | + 'earlycon=pl011,0x3f201000 console=ttyAMA0 ' |
61 | @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem, | 93 | + 'panic=-1 noreboot ' + |
62 | s->drq[OMAP24XX_DMA_GPMC]); | 94 | + 'dwc_otg.fiq_fsm_enable=0') |
63 | 95 | + self.vm.add_args('-kernel', kernel_path, | |
64 | dinfo = drive_get(IF_SD, 0, 0); | 96 | + '-dtb', dtb_path, |
65 | - if (!dinfo) { | 97 | + '-initrd', initrd_path, |
66 | - error_report("missing SecureDigital device"); | 98 | + '-append', kernel_command_line, |
67 | - exit(1); | 99 | + '-no-reboot') |
68 | + if (!dinfo && !qtest_enabled()) { | 100 | + self.vm.launch() |
69 | + warn_report("missing SecureDigital device"); | 101 | + self.wait_for_console_pattern('Boot successful.') |
70 | } | 102 | + |
71 | s->mmc = omap2_mmc_init(omap_l4tao(s->l4, 9), | 103 | + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', |
72 | - blk_by_legacy_dinfo(dinfo), | 104 | + 'BCM2835') |
73 | + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, | 105 | + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', |
74 | qdev_get_gpio_in(s->ih[0], OMAP_INT_24XX_MMC_IRQ), | 106 | + '/soc/cprman@7e101000') |
75 | &s->drq[OMAP24XX_DMA_MMC1_TX], | 107 | + exec_command(self, 'halt') |
76 | omap_findclk(s, "mmc_fclk"), omap_findclk(s, "mmc_iclk")); | 108 | + # Wait for VM to shut down gracefully |
77 | diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c | 109 | + self.vm.wait() |
78 | index XXXXXXX..XXXXXXX 100644 | 110 | + |
79 | --- a/hw/arm/pxa2xx.c | 111 | def test_arm_exynos4210_initrd(self): |
80 | +++ b/hw/arm/pxa2xx.c | 112 | """ |
81 | @@ -XXX,XX +XXX,XX @@ | 113 | :avocado: tags=arch:arm |
82 | #include "chardev/char-fe.h" | ||
83 | #include "sysemu/block-backend.h" | ||
84 | #include "sysemu/blockdev.h" | ||
85 | +#include "sysemu/qtest.h" | ||
86 | #include "qemu/cutils.h" | ||
87 | |||
88 | static struct { | ||
89 | @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(MemoryRegion *address_space, | ||
90 | s->gpio = pxa2xx_gpio_init(0x40e00000, s->cpu, s->pic, 121); | ||
91 | |||
92 | dinfo = drive_get(IF_SD, 0, 0); | ||
93 | - if (!dinfo) { | ||
94 | - error_report("missing SecureDigital device"); | ||
95 | - exit(1); | ||
96 | + if (!dinfo && !qtest_enabled()) { | ||
97 | + warn_report("missing SecureDigital device"); | ||
98 | } | ||
99 | s->mmc = pxa2xx_mmci_init(address_space, 0x41100000, | ||
100 | - blk_by_legacy_dinfo(dinfo), | ||
101 | + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, | ||
102 | qdev_get_gpio_in(s->pic, PXA2XX_PIC_MMC), | ||
103 | qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_MMCI), | ||
104 | qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_MMCI)); | ||
105 | @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size) | ||
106 | s->gpio = pxa2xx_gpio_init(0x40e00000, s->cpu, s->pic, 85); | ||
107 | |||
108 | dinfo = drive_get(IF_SD, 0, 0); | ||
109 | - if (!dinfo) { | ||
110 | - error_report("missing SecureDigital device"); | ||
111 | - exit(1); | ||
112 | + if (!dinfo && !qtest_enabled()) { | ||
113 | + warn_report("missing SecureDigital device"); | ||
114 | } | ||
115 | s->mmc = pxa2xx_mmci_init(address_space, 0x41100000, | ||
116 | - blk_by_legacy_dinfo(dinfo), | ||
117 | + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, | ||
118 | qdev_get_gpio_in(s->pic, PXA2XX_PIC_MMC), | ||
119 | qdev_get_gpio_in(s->dma, PXA2XX_RX_RQ_MMCI), | ||
120 | qdev_get_gpio_in(s->dma, PXA2XX_TX_RQ_MMCI)); | ||
121 | -- | 114 | -- |
122 | 2.17.0 | 115 | 2.20.1 |
123 | 116 | ||
124 | 117 | diff view generated by jsdifflib |
1 | From: Mathew Maidment <mathew1800@gmail.com> | 1 | From: Joe Komlodi <joe.komlodi@xilinx.com> |
---|---|---|---|
2 | 2 | ||
3 | The duplication of id_tlbtr_reginfo was unintentionally added within | 3 | If the CPU is running in default NaN mode (FPCR.DN == 1) and we execute |
4 | 3281af8114c6b8ead02f08b58e3c36895c1ea047 which should have been | 4 | FRSQRTE, FRECPE, or FRECPX with a signaling NaN, parts_silence_nan_frac() will |
5 | id_mpuir_reginfo. | 5 | assert due to fpst->default_nan_mode being set. |
6 | 6 | ||
7 | The effect was that for OMAP and StrongARM CPUs we would | 7 | To avoid this, we check to see what NaN mode we're running in before we call |
8 | incorrectly UNDEF writes to MPUIR rather than NOPing them. | 8 | floatxx_silence_nan(). |
9 | 9 | ||
10 | Signed-off-by: Mathew Maidment <mathew1800@gmail.com> | 10 | Signed-off-by: Joe Komlodi <joe.komlodi@xilinx.com> |
11 | Message-id: 20180501184933.37609-2-mathew1800@gmail.com | 11 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
12 | [PMM: tweak commit message] | 12 | Message-id: 1624662174-175828-2-git-send-email-joe.komlodi@xilinx.com |
13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
15 | --- | 15 | --- |
16 | target/arm/helper.c | 2 +- | 16 | target/arm/helper-a64.c | 12 +++++++++--- |
17 | 1 file changed, 1 insertion(+), 1 deletion(-) | 17 | target/arm/vfp_helper.c | 24 ++++++++++++++++++------ |
18 | 2 files changed, 27 insertions(+), 9 deletions(-) | ||
18 | 19 | ||
19 | diff --git a/target/arm/helper.c b/target/arm/helper.c | 20 | diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c |
20 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/target/arm/helper.c | 22 | --- a/target/arm/helper-a64.c |
22 | +++ b/target/arm/helper.c | 23 | +++ b/target/arm/helper-a64.c |
23 | @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) | 24 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) |
24 | for (r = id_cp_reginfo; r->type != ARM_CP_SENTINEL; r++) { | 25 | float16 nan = a; |
25 | r->access = PL1_RW; | 26 | if (float16_is_signaling_nan(a, fpst)) { |
26 | } | 27 | float_raise(float_flag_invalid, fpst); |
27 | - id_tlbtr_reginfo.access = PL1_RW; | 28 | - nan = float16_silence_nan(a, fpst); |
28 | + id_mpuir_reginfo.access = PL1_RW; | 29 | + if (!fpst->default_nan_mode) { |
29 | id_tlbtr_reginfo.access = PL1_RW; | 30 | + nan = float16_silence_nan(a, fpst); |
31 | + } | ||
30 | } | 32 | } |
31 | if (arm_feature(env, ARM_FEATURE_V8)) { | 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); | ||
32 | -- | 127 | -- |
33 | 2.17.0 | 128 | 2.20.1 |
34 | 129 | ||
35 | 130 | diff view generated by jsdifflib |
1 | From: Igor Mammedov <imammedo@redhat.com> | 1 | From: Maxim Uvarov <maxim.uvarov@linaro.org> |
---|---|---|---|
2 | 2 | ||
3 | Even though nothing is currently broken (since all boards | 3 | qemu has 2 type of functions: shutdown and reboot. Shutdown |
4 | use first_cpu as boot cpu), make sure that boot_info is set | 4 | function has to be used for machine shutdown. Otherwise we cause |
5 | on all CPUs. | 5 | a reset with a bogus "cause" value, when we intended a shutdown. |
6 | If some board would like support heterogenuos setup (i.e. | ||
7 | init boot_info on subset of CPUs) in future, it should add | ||
8 | a reasonable API to do it, instead of starting assigning | ||
9 | boot_info from some CPU and till the end of present CPUs | ||
10 | list. | ||
11 | 6 | ||
12 | Ref: | 7 | Signed-off-by: Maxim Uvarov <maxim.uvarov@linaro.org> |
13 | "Message-ID: <CAFEAcA_NMWuA8WSs3cNeY6xX1kerO_uAcN_3=fK02BEhHJW86g@mail.gmail.com>" | ||
14 | |||
15 | Signed-off-by: Igor Mammedov <imammedo@redhat.com> | ||
16 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
17 | Message-id: 1525176522-200354-5-git-send-email-imammedo@redhat.com | 9 | Message-id: 20210625111842.3790-3-maxim.uvarov@linaro.org |
10 | [PMM: tweaked commit message] | ||
18 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
19 | --- | 12 | --- |
20 | hw/arm/boot.c | 2 +- | 13 | hw/gpio/gpio_pwr.c | 2 +- |
21 | 1 file changed, 1 insertion(+), 1 deletion(-) | 14 | 1 file changed, 1 insertion(+), 1 deletion(-) |
22 | 15 | ||
23 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | 16 | diff --git a/hw/gpio/gpio_pwr.c b/hw/gpio/gpio_pwr.c |
24 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/hw/arm/boot.c | 18 | --- a/hw/gpio/gpio_pwr.c |
26 | +++ b/hw/arm/boot.c | 19 | +++ b/hw/gpio/gpio_pwr.c |
27 | @@ -XXX,XX +XXX,XX @@ static void arm_load_kernel_notify(Notifier *notifier, void *data) | 20 | @@ -XXX,XX +XXX,XX @@ static void gpio_pwr_reset(void *opaque, int n, int level) |
28 | } | 21 | static void gpio_pwr_shutdown(void *opaque, int n, int level) |
29 | info->is_linux = is_linux; | 22 | { |
30 | 23 | if (level) { | |
31 | - for (cs = CPU(cpu); cs; cs = CPU_NEXT(cs)) { | 24 | - qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
32 | + for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { | 25 | + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); |
33 | ARM_CPU(cs)->env.boot_info = info; | ||
34 | } | 26 | } |
35 | } | 27 | } |
28 | |||
36 | -- | 29 | -- |
37 | 2.17.0 | 30 | 2.20.1 |
38 | 31 | ||
39 | 32 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | In do_ldst(), the calculation of the offset needs to be based on the |
---|---|---|---|
2 | size of the memory access, not the size of the elements in the | ||
3 | vector. This meant we were getting it wrong for the widening and | ||
4 | narrowing variants of the various VLDR and VSTR insns. | ||
2 | 5 | ||
3 | ARM virt machine now exposes a new "iommu" option. | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | The SMMUv3 IOMMU is instantiated using -machine virt,iommu=smmuv3. | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Message-id: 20210628135835.6690-2-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/translate-mve.c | 17 +++++++++-------- | ||
11 | 1 file changed, 9 insertions(+), 8 deletions(-) | ||
5 | 12 | ||
6 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 13 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c |
7 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Message-id: 1524665762-31355-15-git-send-email-eric.auger@redhat.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | hw/arm/virt.c | 36 ++++++++++++++++++++++++++++++++++++ | ||
13 | 1 file changed, 36 insertions(+) | ||
14 | |||
15 | diff --git a/hw/arm/virt.c b/hw/arm/virt.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/hw/arm/virt.c | 15 | --- a/target/arm/translate-mve.c |
18 | +++ b/hw/arm/virt.c | 16 | +++ b/target/arm/translate-mve.c |
19 | @@ -XXX,XX +XXX,XX @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp) | 17 | @@ -XXX,XX +XXX,XX @@ static bool mve_skip_first_beat(DisasContext *s) |
20 | } | 18 | } |
21 | } | 19 | } |
22 | 20 | ||
23 | +static char *virt_get_iommu(Object *obj, Error **errp) | 21 | -static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) |
24 | +{ | 22 | +static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn, |
25 | + VirtMachineState *vms = VIRT_MACHINE(obj); | 23 | + unsigned msize) |
26 | + | ||
27 | + switch (vms->iommu) { | ||
28 | + case VIRT_IOMMU_NONE: | ||
29 | + return g_strdup("none"); | ||
30 | + case VIRT_IOMMU_SMMUV3: | ||
31 | + return g_strdup("smmuv3"); | ||
32 | + default: | ||
33 | + g_assert_not_reached(); | ||
34 | + } | ||
35 | +} | ||
36 | + | ||
37 | +static void virt_set_iommu(Object *obj, const char *value, Error **errp) | ||
38 | +{ | ||
39 | + VirtMachineState *vms = VIRT_MACHINE(obj); | ||
40 | + | ||
41 | + if (!strcmp(value, "smmuv3")) { | ||
42 | + vms->iommu = VIRT_IOMMU_SMMUV3; | ||
43 | + } else if (!strcmp(value, "none")) { | ||
44 | + vms->iommu = VIRT_IOMMU_NONE; | ||
45 | + } else { | ||
46 | + error_setg(errp, "Invalid iommu value"); | ||
47 | + error_append_hint(errp, "Valid values are none, smmuv3.\n"); | ||
48 | + } | ||
49 | +} | ||
50 | + | ||
51 | static CpuInstanceProperties | ||
52 | virt_cpu_index_to_props(MachineState *ms, unsigned cpu_index) | ||
53 | { | 24 | { |
54 | @@ -XXX,XX +XXX,XX @@ static void virt_2_12_instance_init(Object *obj) | 25 | TCGv_i32 addr; |
55 | NULL); | 26 | uint32_t offset; |
27 | @@ -XXX,XX +XXX,XX @@ static bool do_ldst(DisasContext *s, arg_VLDR_VSTR *a, MVEGenLdStFn *fn) | ||
28 | return true; | ||
56 | } | 29 | } |
57 | 30 | ||
58 | + /* Default disallows iommu instantiation */ | 31 | - offset = a->imm << a->size; |
59 | + vms->iommu = VIRT_IOMMU_NONE; | 32 | + offset = a->imm << msize; |
60 | + object_property_add_str(obj, "iommu", virt_get_iommu, virt_set_iommu, NULL); | 33 | if (!a->a) { |
61 | + object_property_set_description(obj, "iommu", | 34 | offset = -offset; |
62 | + "Set the IOMMU type. " | 35 | } |
63 | + "Valid values are none and smmuv3", | 36 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR(DisasContext *s, arg_VLDR_VSTR *a) |
64 | + NULL); | 37 | { gen_helper_mve_vstrw, gen_helper_mve_vldrw }, |
65 | + | 38 | { NULL, NULL } |
66 | vms->memmap = a15memmap; | 39 | }; |
67 | vms->irqmap = a15irqmap; | 40 | - return do_ldst(s, a, ldstfns[a->size][a->l]); |
41 | + return do_ldst(s, a, ldstfns[a->size][a->l], a->size); | ||
68 | } | 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 | { | ||
69 | -- | 65 | -- |
70 | 2.17.0 | 66 | 2.20.1 |
71 | 67 | ||
72 | 68 | diff view generated by jsdifflib |
1 | From: Prem Mallappa <prem.mallappa@broadcom.com> | 1 | The initial implementation of the MVE VRMLALDAVH and VRMLSLDAVH |
---|---|---|---|
2 | insns had some bugs: | ||
3 | * the 32x32 multiply of elements was being done as 32x32->32, | ||
4 | not 32x32->64 | ||
5 | * we were incorrectly maintaining the accumulator in its full | ||
6 | 72-bit form across all 4 beats of the insn; in the pseudocode | ||
7 | it is squashed back into the 64 bits of the RdaHi:RdaLo | ||
8 | registers after each beat | ||
2 | 9 | ||
3 | This patch builds the smmuv3 node in the ACPI IORT table. | 10 | In particular, fixing the second of these allows us to recast |
11 | the implementation to avoid 128-bit arithmetic entirely. | ||
4 | 12 | ||
5 | The RID space of the root complex, which spans 0x0-0x10000 | 13 | Since the element size here is always 4, we can also drop the |
6 | maps to streamid space 0x0-0x10000 in smmuv3, which in turn | 14 | parameterization of ESIZE to make the code a little more readable. |
7 | maps to deviceid space 0x0-0x10000 in the ITS group. | ||
8 | 15 | ||
9 | The guest must feature the IOMMU probe deferral series | 16 | Suggested-by: Richard Henderson <richard.henderson@linaro.org> |
10 | (https://lkml.org/lkml/2017/4/10/214) which fixes streamid | 17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | multiple lookup. This bug is not related to the SMMU emulation. | 18 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
19 | Message-id: 20210628135835.6690-3-peter.maydell@linaro.org | ||
20 | --- | ||
21 | target/arm/mve_helper.c | 38 +++++++++++++++++++++----------------- | ||
22 | 1 file changed, 21 insertions(+), 17 deletions(-) | ||
12 | 23 | ||
13 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | 24 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
14 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
15 | Reviewed-by: Shannon Zhao <zhaoshenglong@huawei.com> | ||
16 | Message-id: 1524665762-31355-14-git-send-email-eric.auger@redhat.com | ||
17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
18 | --- | ||
19 | include/hw/acpi/acpi-defs.h | 15 ++++++++++ | ||
20 | hw/arm/virt-acpi-build.c | 55 ++++++++++++++++++++++++++++++++----- | ||
21 | 2 files changed, 63 insertions(+), 7 deletions(-) | ||
22 | |||
23 | diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | 25 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/include/hw/acpi/acpi-defs.h | 26 | --- a/target/arm/mve_helper.c |
26 | +++ b/include/hw/acpi/acpi-defs.h | 27 | +++ b/target/arm/mve_helper.c |
27 | @@ -XXX,XX +XXX,XX @@ struct AcpiIortItsGroup { | 28 | @@ -XXX,XX +XXX,XX @@ |
28 | } QEMU_PACKED; | 29 | */ |
29 | typedef struct AcpiIortItsGroup AcpiIortItsGroup; | 30 | |
30 | 31 | #include "qemu/osdep.h" | |
31 | +struct AcpiIortSmmu3 { | 32 | -#include "qemu/int128.h" |
32 | + ACPI_IORT_NODE_HEADER_DEF | 33 | #include "cpu.h" |
33 | + uint64_t base_address; | 34 | #include "internals.h" |
34 | + uint32_t flags; | 35 | #include "vec_internal.h" |
35 | + uint32_t reserved2; | 36 | @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) |
36 | + uint64_t vatos_address; | 37 | DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) |
37 | + uint32_t model; | 38 | |
38 | + uint32_t event_gsiv; | 39 | /* |
39 | + uint32_t pri_gsiv; | 40 | - * Rounding multiply add long dual accumulate high: we must keep |
40 | + uint32_t gerr_gsiv; | 41 | - * a 72-bit internal accumulator value and return the top 64 bits. |
41 | + uint32_t sync_gsiv; | 42 | + * Rounding multiply add long dual accumulate high. In the pseudocode |
42 | + AcpiIortIdMapping id_mapping_array[0]; | 43 | + * this is implemented with a 72-bit internal accumulator value of which |
43 | +} QEMU_PACKED; | 44 | + * the top 64 bits are returned. We optimize this to avoid having to |
44 | +typedef struct AcpiIortSmmu3 AcpiIortSmmu3; | 45 | + * use 128-bit arithmetic -- we can do this because the 74-bit accumulator |
45 | + | 46 | + * is squashed back into 64-bits after each beat. |
46 | struct AcpiIortRC { | 47 | */ |
47 | ACPI_IORT_NODE_HEADER_DEF | 48 | -#define DO_LDAVH(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC, TO128) \ |
48 | AcpiIortMemoryAccess memory_properties; | 49 | +#define DO_LDAVH(OP, TYPE, LTYPE, XCHG, SUB) \ |
49 | diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c | 50 | uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ |
50 | index XXXXXXX..XXXXXXX 100644 | 51 | void *vm, uint64_t a) \ |
51 | --- a/hw/arm/virt-acpi-build.c | 52 | { \ |
52 | +++ b/hw/arm/virt-acpi-build.c | 53 | uint16_t mask = mve_element_mask(env); \ |
53 | @@ -XXX,XX +XXX,XX @@ build_rsdp(GArray *rsdp_table, BIOSLinker *linker, unsigned xsdt_tbl_offset) | 54 | unsigned e; \ |
54 | } | 55 | TYPE *n = vn, *m = vm; \ |
55 | 56 | - Int128 acc = int128_lshift(TO128(a), 8); \ | |
56 | static void | 57 | - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ |
57 | -build_iort(GArray *table_data, BIOSLinker *linker) | 58 | + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ |
58 | +build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) | 59 | if (mask & 1) { \ |
59 | { | 60 | + LTYPE mul; \ |
60 | - int iort_start = table_data->len; | 61 | if (e & 1) { \ |
61 | + int nb_nodes, iort_start = table_data->len; | 62 | - acc = ODDACC(acc, TO128(n[H##ESIZE(e - 1 * XCHG)] * \ |
62 | AcpiIortIdMapping *idmap; | 63 | - m[H##ESIZE(e)])); \ |
63 | AcpiIortItsGroup *its; | 64 | + mul = (LTYPE)n[H4(e - 1 * XCHG)] * m[H4(e)]; \ |
64 | AcpiIortTable *iort; | 65 | + if (SUB) { \ |
65 | - size_t node_size, iort_length; | 66 | + mul = -mul; \ |
66 | + AcpiIortSmmu3 *smmu; | 67 | + } \ |
67 | + size_t node_size, iort_length, smmu_offset = 0; | 68 | } else { \ |
68 | AcpiIortRC *rc; | 69 | - acc = EVENACC(acc, TO128(n[H##ESIZE(e + 1 * XCHG)] * \ |
69 | 70 | - m[H##ESIZE(e)])); \ | |
70 | iort = acpi_data_push(table_data, sizeof(*iort)); | 71 | + mul = (LTYPE)n[H4(e + 1 * XCHG)] * m[H4(e)]; \ |
71 | 72 | } \ | |
72 | + if (vms->iommu == VIRT_IOMMU_SMMUV3) { | 73 | - acc = int128_add(acc, int128_make64(1 << 7)); \ |
73 | + nb_nodes = 3; /* RC, ITS, SMMUv3 */ | 74 | + mul = (mul >> 8) + ((mul >> 7) & 1); \ |
74 | + } else { | 75 | + a += mul; \ |
75 | + nb_nodes = 2; /* RC, ITS */ | 76 | } \ |
76 | + } | 77 | } \ |
77 | + | 78 | mve_advance_vpt(env); \ |
78 | iort_length = sizeof(*iort); | 79 | - return int128_getlo(int128_rshift(acc, 8)); \ |
79 | - iort->node_count = cpu_to_le32(2); /* RC and ITS nodes */ | 80 | + return a; \ |
80 | + iort->node_count = cpu_to_le32(nb_nodes); | ||
81 | iort->node_offset = cpu_to_le32(sizeof(*iort)); | ||
82 | |||
83 | /* ITS group node */ | ||
84 | @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker) | ||
85 | its->its_count = cpu_to_le32(1); | ||
86 | its->identifiers[0] = 0; /* MADT translation_id */ | ||
87 | |||
88 | + if (vms->iommu == VIRT_IOMMU_SMMUV3) { | ||
89 | + int irq = vms->irqmap[VIRT_SMMU]; | ||
90 | + | ||
91 | + /* SMMUv3 node */ | ||
92 | + smmu_offset = iort->node_offset + node_size; | ||
93 | + node_size = sizeof(*smmu) + sizeof(*idmap); | ||
94 | + iort_length += node_size; | ||
95 | + smmu = acpi_data_push(table_data, node_size); | ||
96 | + | ||
97 | + smmu->type = ACPI_IORT_NODE_SMMU_V3; | ||
98 | + smmu->length = cpu_to_le16(node_size); | ||
99 | + smmu->mapping_count = cpu_to_le32(1); | ||
100 | + smmu->mapping_offset = cpu_to_le32(sizeof(*smmu)); | ||
101 | + smmu->base_address = cpu_to_le64(vms->memmap[VIRT_SMMU].base); | ||
102 | + smmu->event_gsiv = cpu_to_le32(irq); | ||
103 | + smmu->pri_gsiv = cpu_to_le32(irq + 1); | ||
104 | + smmu->gerr_gsiv = cpu_to_le32(irq + 2); | ||
105 | + smmu->sync_gsiv = cpu_to_le32(irq + 3); | ||
106 | + | ||
107 | + /* Identity RID mapping covering the whole input RID range */ | ||
108 | + idmap = &smmu->id_mapping_array[0]; | ||
109 | + idmap->input_base = 0; | ||
110 | + idmap->id_count = cpu_to_le32(0xFFFF); | ||
111 | + idmap->output_base = 0; | ||
112 | + /* output IORT node is the ITS group node (the first node) */ | ||
113 | + idmap->output_reference = cpu_to_le32(iort->node_offset); | ||
114 | + } | ||
115 | + | ||
116 | /* Root Complex Node */ | ||
117 | node_size = sizeof(*rc) + sizeof(*idmap); | ||
118 | iort_length += node_size; | ||
119 | @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker) | ||
120 | idmap->input_base = 0; | ||
121 | idmap->id_count = cpu_to_le32(0xFFFF); | ||
122 | idmap->output_base = 0; | ||
123 | - /* output IORT node is the ITS group node (the first node) */ | ||
124 | - idmap->output_reference = cpu_to_le32(iort->node_offset); | ||
125 | + | ||
126 | + if (vms->iommu == VIRT_IOMMU_SMMUV3) { | ||
127 | + /* output IORT node is the smmuv3 node */ | ||
128 | + idmap->output_reference = cpu_to_le32(smmu_offset); | ||
129 | + } else { | ||
130 | + /* output IORT node is the ITS group node (the first node) */ | ||
131 | + idmap->output_reference = cpu_to_le32(iort->node_offset); | ||
132 | + } | ||
133 | |||
134 | iort->length = cpu_to_le32(iort_length); | ||
135 | |||
136 | @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) | ||
137 | |||
138 | if (its_class_name() && !vmc->no_its) { | ||
139 | acpi_add_table(table_offsets, tables_blob); | ||
140 | - build_iort(tables_blob, tables->linker); | ||
141 | + build_iort(tables_blob, tables->linker, vms); | ||
142 | } | 81 | } |
143 | 82 | ||
144 | /* XSDT is pointed to by RSDP */ | 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) \ | ||
145 | -- | 98 | -- |
146 | 2.17.0 | 99 | 2.20.1 |
147 | 100 | ||
148 | 101 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | The function asimd_imm_const() in translate-neon.c is an |
---|---|---|---|
2 | implementation of the pseudocode AdvSIMDExpandImm(), which we will | ||
3 | also want for MVE. Move the implementation to translate.c, with a | ||
4 | prototype in translate.h. | ||
2 | 5 | ||
3 | At the moment, the SMMUv3 does not support notification on | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | TLB invalidation. So let's log an error as soon as such notifier | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | gets enabled. | 8 | Message-id: 20210628135835.6690-4-peter.maydell@linaro.org |
9 | --- | ||
10 | target/arm/translate.h | 16 ++++++++++ | ||
11 | target/arm/translate-neon.c | 63 ------------------------------------- | ||
12 | target/arm/translate.c | 57 +++++++++++++++++++++++++++++++++ | ||
13 | 3 files changed, 73 insertions(+), 63 deletions(-) | ||
6 | 14 | ||
7 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 15 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Message-id: 1524665762-31355-11-git-send-email-eric.auger@redhat.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | hw/arm/smmuv3.c | 11 +++++++++++ | ||
13 | 1 file changed, 11 insertions(+) | ||
14 | |||
15 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/hw/arm/smmuv3.c | 17 | --- a/target/arm/translate.h |
18 | +++ b/hw/arm/smmuv3.c | 18 | +++ b/target/arm/translate.h |
19 | @@ -XXX,XX +XXX,XX @@ static void smmuv3_class_init(ObjectClass *klass, void *data) | 19 | @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) |
20 | dc->realize = smmu_realize; | 20 | return opc | s->be_data; |
21 | } | 21 | } |
22 | 22 | ||
23 | +static void smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu, | 23 | +/** |
24 | + IOMMUNotifierFlag old, | 24 | + * asimd_imm_const: Expand an encoded SIMD constant value |
25 | + IOMMUNotifierFlag new) | 25 | + * |
26 | + * Expand a SIMD constant value. This is essentially the pseudocode | ||
27 | + * AdvSIMDExpandImm, except that we also perform the boolean NOT needed for | ||
28 | + * VMVN and VBIC (when cmode < 14 && op == 1). | ||
29 | + * | ||
30 | + * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; | ||
31 | + * callers must catch this. | ||
32 | + * | ||
33 | + * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but | ||
34 | + * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; | ||
35 | + * we produce an immediate constant value of 0 in these cases. | ||
36 | + */ | ||
37 | +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); | ||
38 | + | ||
39 | #endif /* TARGET_ARM_TRANSLATE_H */ | ||
40 | diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c | ||
41 | index XXXXXXX..XXXXXXX 100644 | ||
42 | --- a/target/arm/translate-neon.c | ||
43 | +++ b/target/arm/translate-neon.c | ||
44 | @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) | ||
45 | DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) | ||
46 | DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) | ||
47 | |||
48 | -static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) | ||
49 | -{ | ||
50 | - /* | ||
51 | - * Expand the encoded constant. | ||
52 | - * Note that cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 is UNPREDICTABLE. | ||
53 | - * We choose to not special-case this and will behave as if a | ||
54 | - * valid constant encoding of 0 had been given. | ||
55 | - * cmode = 15 op = 1 must UNDEF; we assume decode has handled that. | ||
56 | - */ | ||
57 | - switch (cmode) { | ||
58 | - case 0: case 1: | ||
59 | - /* no-op */ | ||
60 | - break; | ||
61 | - case 2: case 3: | ||
62 | - imm <<= 8; | ||
63 | - break; | ||
64 | - case 4: case 5: | ||
65 | - imm <<= 16; | ||
66 | - break; | ||
67 | - case 6: case 7: | ||
68 | - imm <<= 24; | ||
69 | - break; | ||
70 | - case 8: case 9: | ||
71 | - imm |= imm << 16; | ||
72 | - break; | ||
73 | - case 10: case 11: | ||
74 | - imm = (imm << 8) | (imm << 24); | ||
75 | - break; | ||
76 | - case 12: | ||
77 | - imm = (imm << 8) | 0xff; | ||
78 | - break; | ||
79 | - case 13: | ||
80 | - imm = (imm << 16) | 0xffff; | ||
81 | - break; | ||
82 | - case 14: | ||
83 | - if (op) { | ||
84 | - /* | ||
85 | - * This is the only case where the top and bottom 32 bits | ||
86 | - * of the encoded constant differ. | ||
87 | - */ | ||
88 | - uint64_t imm64 = 0; | ||
89 | - int n; | ||
90 | - | ||
91 | - for (n = 0; n < 8; n++) { | ||
92 | - if (imm & (1 << n)) { | ||
93 | - imm64 |= (0xffULL << (n * 8)); | ||
94 | - } | ||
95 | - } | ||
96 | - return imm64; | ||
97 | - } | ||
98 | - imm |= (imm << 8) | (imm << 16) | (imm << 24); | ||
99 | - break; | ||
100 | - case 15: | ||
101 | - imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) | ||
102 | - | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); | ||
103 | - break; | ||
104 | - } | ||
105 | - if (op) { | ||
106 | - imm = ~imm; | ||
107 | - } | ||
108 | - return dup_const(MO_32, imm); | ||
109 | -} | ||
110 | - | ||
111 | static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, | ||
112 | GVecGen2iFn *fn) | ||
113 | { | ||
114 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
115 | index XXXXXXX..XXXXXXX 100644 | ||
116 | --- a/target/arm/translate.c | ||
117 | +++ b/target/arm/translate.c | ||
118 | @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) | ||
119 | a64_translate_init(); | ||
120 | } | ||
121 | |||
122 | +uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) | ||
26 | +{ | 123 | +{ |
27 | + if (old == IOMMU_NOTIFIER_NONE) { | 124 | + /* Expand the encoded constant as per AdvSIMDExpandImm pseudocode */ |
28 | + warn_report("SMMUV3 does not support vhost/vfio integration yet: " | 125 | + switch (cmode) { |
29 | + "devices of those types will not function properly"); | 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; | ||
30 | + } | 172 | + } |
173 | + if (op) { | ||
174 | + imm = ~imm; | ||
175 | + } | ||
176 | + return dup_const(MO_32, imm); | ||
31 | +} | 177 | +} |
32 | + | 178 | + |
33 | static void smmuv3_iommu_memory_region_class_init(ObjectClass *klass, | 179 | /* Generate a label used for skipping this instruction */ |
34 | void *data) | 180 | void arm_gen_condlabel(DisasContext *s) |
35 | { | 181 | { |
36 | IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_CLASS(klass); | ||
37 | |||
38 | imrc->translate = smmuv3_translate; | ||
39 | + imrc->notify_flag_changed = smmuv3_notify_flag_changed; | ||
40 | } | ||
41 | |||
42 | static const TypeInfo smmuv3_type_info = { | ||
43 | -- | 182 | -- |
44 | 2.17.0 | 183 | 2.20.1 |
45 | 184 | ||
46 | 185 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | The A64 AdvSIMD modified-immediate grouping uses almost the same |
---|---|---|---|
2 | constant encoding that A32 Neon does; reuse asimd_imm_const() (to | ||
3 | which we add the AArch64-specific case for cmode 15 op 1) instead of | ||
4 | reimplementing it all. | ||
2 | 5 | ||
3 | The (size > 3 && !is_q) condition is identical to the preceeding test | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | of bit 3 in immh; eliminate it. For the benefit of Coverity, assert | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | that size is within the bounds we expect. | 8 | Message-id: 20210628135835.6690-5-peter.maydell@linaro.org |
9 | --- | ||
10 | target/arm/translate.h | 3 +- | ||
11 | target/arm/translate-a64.c | 86 ++++---------------------------------- | ||
12 | target/arm/translate.c | 17 +++++++- | ||
13 | 3 files changed, 24 insertions(+), 82 deletions(-) | ||
6 | 14 | ||
7 | Fixes: Coverity CID1385846 | 15 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
8 | Fixes: Coverity CID1385849 | 16 | index XXXXXXX..XXXXXXX 100644 |
9 | Fixes: Coverity CID1385852 | 17 | --- a/target/arm/translate.h |
10 | Fixes: Coverity CID1385857 | 18 | +++ b/target/arm/translate.h |
11 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 19 | @@ -XXX,XX +XXX,XX @@ static inline MemOp finalize_memop(DisasContext *s, MemOp opc) |
12 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | 20 | * VMVN and VBIC (when cmode < 14 && op == 1). |
13 | Message-id: 20180501180455.11214-2-richard.henderson@linaro.org | 21 | * |
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 22 | * The combination cmode == 15 op == 1 is a reserved encoding for AArch32; |
15 | --- | 23 | - * callers must catch this. |
16 | target/arm/translate-a64.c | 6 +----- | 24 | + * callers must catch this; we return the 64-bit constant value defined |
17 | 1 file changed, 1 insertion(+), 5 deletions(-) | 25 | + * for AArch64. |
18 | 26 | * | |
27 | * cmode = 2,3,4,5,6,7,10,11,12,13 imm=0 was UNPREDICTABLE in v7A but | ||
28 | * is either not unpredictable or merely CONSTRAINED UNPREDICTABLE in v8A; | ||
19 | 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 |
20 | index XXXXXXX..XXXXXXX 100644 | 30 | index XXXXXXX..XXXXXXX 100644 |
21 | --- a/target/arm/translate-a64.c | 31 | --- a/target/arm/translate-a64.c |
22 | +++ b/target/arm/translate-a64.c | 32 | +++ b/target/arm/translate-a64.c |
23 | @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, | 33 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
24 | unallocated_encoding(s); | 34 | { |
35 | int rd = extract32(insn, 0, 5); | ||
36 | int cmode = extract32(insn, 12, 4); | ||
37 | - int cmode_3_1 = extract32(cmode, 1, 3); | ||
38 | - int cmode_0 = extract32(cmode, 0, 1); | ||
39 | int o2 = extract32(insn, 11, 1); | ||
40 | uint64_t abcdefgh = extract32(insn, 5, 5) | (extract32(insn, 16, 3) << 5); | ||
41 | bool is_neg = extract32(insn, 29, 1); | ||
42 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) | ||
25 | return; | 43 | return; |
26 | } | 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 | - } | ||
27 | - | 120 | - |
28 | - if (size > 3 && !is_q) { | 121 | - if (cmode_3_1 != 7 && is_neg) { |
29 | - unallocated_encoding(s); | 122 | - imm = ~imm; |
30 | - return; | 123 | + if (cmode == 15 && o2 && !is_neg) { |
31 | - } | 124 | + /* FMOV (vector, immediate) - half-precision */ |
32 | + tcg_debug_assert(size <= 3); | 125 | + imm = vfp_expand_imm(MO_16, abcdefgh); |
33 | 126 | + /* now duplicate across the lanes */ | |
34 | if (!fp_access_check(s)) { | 127 | + imm = bitfield_replicate(imm, 16); |
35 | return; | 128 | + } else { |
129 | + imm = asimd_imm_const(abcdefgh, cmode, is_neg); | ||
130 | } | ||
131 | |||
132 | if (!((cmode & 0x9) == 0x1 || (cmode & 0xd) == 0x9)) { | ||
133 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
134 | index XXXXXXX..XXXXXXX 100644 | ||
135 | --- a/target/arm/translate.c | ||
136 | +++ b/target/arm/translate.c | ||
137 | @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) | ||
138 | case 14: | ||
139 | if (op) { | ||
140 | /* | ||
141 | - * This is the only case where the top and bottom 32 bits | ||
142 | - * of the encoded constant differ. | ||
143 | + * This and cmode == 15 op == 1 are the only cases where | ||
144 | + * the top and bottom 32 bits of the encoded constant differ. | ||
145 | */ | ||
146 | uint64_t imm64 = 0; | ||
147 | int n; | ||
148 | @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) | ||
149 | imm |= (imm << 8) | (imm << 16) | (imm << 24); | ||
150 | break; | ||
151 | case 15: | ||
152 | + if (op) { | ||
153 | + /* Reserved encoding for AArch32; valid for AArch64 */ | ||
154 | + uint64_t imm64 = (uint64_t)(imm & 0x3f) << 48; | ||
155 | + if (imm & 0x80) { | ||
156 | + imm64 |= 0x8000000000000000ULL; | ||
157 | + } | ||
158 | + if (imm & 0x40) { | ||
159 | + imm64 |= 0x3fc0000000000000ULL; | ||
160 | + } else { | ||
161 | + imm64 |= 0x4000000000000000ULL; | ||
162 | + } | ||
163 | + return imm64; | ||
164 | + } | ||
165 | imm = ((imm & 0x80) << 24) | ((imm & 0x3f) << 19) | ||
166 | | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); | ||
167 | break; | ||
36 | -- | 168 | -- |
37 | 2.17.0 | 169 | 2.20.1 |
38 | 170 | ||
39 | 171 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | Use dup_const() instead of bitfield_replicate() in |
---|---|---|---|
2 | disas_simd_mod_imm(). | ||
2 | 3 | ||
3 | Path analysis shows that size == 3 && !is_q has been eliminated. | 4 | (We can't replace the other use of bitfield_replicate() in this file, |
5 | in logic_imm_decode_wmask(), because that location needs to handle 2 | ||
6 | and 4 bit elements, which dup_const() cannot.) | ||
4 | 7 | ||
5 | Fixes: Coverity CID1385853 | ||
6 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
8 | Message-id: 20180501180455.11214-3-richard.henderson@linaro.org | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
10 | Message-id: 20210628135835.6690-6-peter.maydell@linaro.org | ||
10 | --- | 11 | --- |
11 | target/arm/translate-a64.c | 6 +++++- | 12 | target/arm/translate-a64.c | 2 +- |
12 | 1 file changed, 5 insertions(+), 1 deletion(-) | 13 | 1 file changed, 1 insertion(+), 1 deletion(-) |
13 | 14 | ||
14 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c |
15 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/target/arm/translate-a64.c | 17 | --- a/target/arm/translate-a64.c |
17 | +++ b/target/arm/translate-a64.c | 18 | +++ b/target/arm/translate-a64.c |
18 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) | 19 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) |
19 | /* All 64-bit element operations can be shared with scalar 2misc */ | 20 | /* FMOV (vector, immediate) - half-precision */ |
20 | int pass; | 21 | imm = vfp_expand_imm(MO_16, abcdefgh); |
21 | 22 | /* now duplicate across the lanes */ | |
22 | - for (pass = 0; pass < (is_q ? 2 : 1); pass++) { | 23 | - imm = bitfield_replicate(imm, 16); |
23 | + /* Coverity claims (size == 3 && !is_q) has been eliminated | 24 | + imm = dup_const(MO_16, imm); |
24 | + * from all paths leading to here. | 25 | } else { |
25 | + */ | 26 | imm = asimd_imm_const(abcdefgh, cmode, is_neg); |
26 | + tcg_debug_assert(is_q); | 27 | } |
27 | + for (pass = 0; pass < 2; pass++) { | ||
28 | TCGv_i64 tcg_op = tcg_temp_new_i64(); | ||
29 | TCGv_i64 tcg_res = tcg_temp_new_i64(); | ||
30 | |||
31 | -- | 28 | -- |
32 | 2.17.0 | 29 | 2.20.1 |
33 | 30 | ||
34 | 31 | diff view generated by jsdifflib |
1 | From: Prem Mallappa <prem.mallappa@broadcom.com> | 1 | Implement the MVE logical-immediate insns (VMOV, VMVN, |
---|---|---|---|
2 | VORR and VBIC). These have essentially the same encoding | ||
3 | as their Neon equivalents, and we implement the decode | ||
4 | in the same way. | ||
2 | 5 | ||
3 | Add code to instantiate an smmuv3 in virt machine. A new iommu | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | integer member is introduced in VirtMachineState to store the type | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | of the iommu in use. | 8 | Message-id: 20210628135835.6690-7-peter.maydell@linaro.org |
9 | --- | ||
10 | target/arm/helper-mve.h | 4 +++ | ||
11 | target/arm/mve.decode | 17 +++++++++++++ | ||
12 | target/arm/mve_helper.c | 24 ++++++++++++++++++ | ||
13 | target/arm/translate-mve.c | 50 ++++++++++++++++++++++++++++++++++++++ | ||
14 | 4 files changed, 95 insertions(+) | ||
6 | 15 | ||
7 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
8 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
9 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | Message-id: 1524665762-31355-13-git-send-email-eric.auger@redhat.com | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | include/hw/arm/virt.h | 10 +++++++ | ||
14 | hw/arm/virt.c | 64 ++++++++++++++++++++++++++++++++++++++++++- | ||
15 | 2 files changed, 73 insertions(+), 1 deletion(-) | ||
16 | |||
17 | diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h | ||
18 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/include/hw/arm/virt.h | 18 | --- a/target/arm/helper-mve.h |
20 | +++ b/include/hw/arm/virt.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 | ||
21 | @@ -XXX,XX +XXX,XX @@ | 32 | @@ -XXX,XX +XXX,XX @@ |
22 | 33 | # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit | |
23 | #define NUM_GICV2M_SPIS 64 | 34 | %size_28 28:1 !function=plus_1 |
24 | #define NUM_VIRTIO_TRANSPORTS 32 | 35 | |
25 | +#define NUM_SMMU_IRQS 4 | 36 | +# 1imm format immediate |
26 | 37 | +%imm_28_16_0 28:1 16:3 0:4 | |
27 | #define ARCH_GICV3_MAINT_IRQ 9 | ||
28 | |||
29 | @@ -XXX,XX +XXX,XX @@ enum { | ||
30 | VIRT_GIC_V2M, | ||
31 | VIRT_GIC_ITS, | ||
32 | VIRT_GIC_REDIST, | ||
33 | + VIRT_SMMU, | ||
34 | VIRT_UART, | ||
35 | VIRT_MMIO, | ||
36 | VIRT_RTC, | ||
37 | @@ -XXX,XX +XXX,XX @@ enum { | ||
38 | VIRT_SECURE_MEM, | ||
39 | }; | ||
40 | |||
41 | +typedef enum VirtIOMMUType { | ||
42 | + VIRT_IOMMU_NONE, | ||
43 | + VIRT_IOMMU_SMMUV3, | ||
44 | + VIRT_IOMMU_VIRTIO, | ||
45 | +} VirtIOMMUType; | ||
46 | + | 38 | + |
47 | typedef struct MemMapEntry { | 39 | &vldr_vstr rn qd imm p a w size l u |
48 | hwaddr base; | 40 | &1op qd qm size |
49 | hwaddr size; | 41 | &2op qd qm qn size |
50 | @@ -XXX,XX +XXX,XX @@ typedef struct { | 42 | &2scalar qd qn rm size |
51 | bool its; | 43 | +&1imm qd imm cmode op |
52 | bool virt; | 44 | |
53 | int32_t gic_version; | 45 | @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 |
54 | + VirtIOMMUType iommu; | 46 | # Note that both Rn and Qd are 3 bits only (no D bit) |
55 | struct arm_boot_info bootinfo; | 47 | @@ -XXX,XX +XXX,XX @@ |
56 | const MemMapEntry *memmap; | 48 | @2op_nosz .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn size=0 |
57 | const int *irqmap; | 49 | @2op_sz28 .... .... .... .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn \ |
58 | @@ -XXX,XX +XXX,XX @@ typedef struct { | 50 | size=%size_28 |
59 | uint32_t clock_phandle; | 51 | +@1imm .... .... .... .... .... cmode:4 .. op:1 . .... &1imm qd=%qd imm=%imm_28_16_0 |
60 | uint32_t gic_phandle; | 52 | |
61 | uint32_t msi_phandle; | 53 | # The _rev suffix indicates that Vn and Vm are reversed. This is |
62 | + uint32_t iommu_phandle; | 54 | # the case for shifts. In the Arm ARM these insns are documented |
63 | int psci_conduit; | 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 |
64 | } VirtMachineState; | 56 | # Predicate operations |
65 | 57 | %mask_22_13 22:1 13:3 | |
66 | diff --git a/hw/arm/virt.c b/hw/arm/virt.c | 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 | ||
67 | index XXXXXXX..XXXXXXX 100644 | 72 | index XXXXXXX..XXXXXXX 100644 |
68 | --- a/hw/arm/virt.c | 73 | --- a/target/arm/mve_helper.c |
69 | +++ b/hw/arm/virt.c | 74 | +++ b/target/arm/mve_helper.c |
70 | @@ -XXX,XX +XXX,XX @@ | 75 | @@ -XXX,XX +XXX,XX @@ DO_1OP(vnegw, 4, int32_t, DO_NEG) |
71 | #include "hw/smbios/smbios.h" | 76 | DO_1OP(vfnegh, 8, uint64_t, DO_FNEGH) |
72 | #include "qapi/visitor.h" | 77 | DO_1OP(vfnegs, 8, uint64_t, DO_FNEGS) |
73 | #include "standard-headers/linux/input.h" | 78 | |
74 | +#include "hw/arm/smmuv3.h" | 79 | +/* |
75 | 80 | + * 1 operand immediates: Vda is destination and possibly also one source. | |
76 | #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ | 81 | + * All these insns work at 64-bit widths. |
77 | static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ | 82 | + */ |
78 | @@ -XXX,XX +XXX,XX @@ static const MemMapEntry a15memmap[] = { | 83 | +#define DO_1OP_IMM(OP, FN) \ |
79 | [VIRT_FW_CFG] = { 0x09020000, 0x00000018 }, | 84 | + void HELPER(mve_##OP)(CPUARMState *env, void *vda, uint64_t imm) \ |
80 | [VIRT_GPIO] = { 0x09030000, 0x00001000 }, | 85 | + { \ |
81 | [VIRT_SECURE_UART] = { 0x09040000, 0x00001000 }, | 86 | + uint64_t *da = vda; \ |
82 | + [VIRT_SMMU] = { 0x09050000, 0x00020000 }, | 87 | + uint16_t mask = mve_element_mask(env); \ |
83 | [VIRT_MMIO] = { 0x0a000000, 0x00000200 }, | 88 | + unsigned e; \ |
84 | /* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */ | 89 | + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ |
85 | [VIRT_PLATFORM_BUS] = { 0x0c000000, 0x02000000 }, | 90 | + mergemask(&da[H8(e)], FN(da[H8(e)], imm), mask); \ |
86 | @@ -XXX,XX +XXX,XX @@ static const int a15irqmap[] = { | 91 | + } \ |
87 | [VIRT_SECURE_UART] = 8, | 92 | + mve_advance_vpt(env); \ |
88 | [VIRT_MMIO] = 16, /* ...to 16 + NUM_VIRTIO_TRANSPORTS - 1 */ | ||
89 | [VIRT_GIC_V2M] = 48, /* ...to 48 + NUM_GICV2M_SPIS - 1 */ | ||
90 | + [VIRT_SMMU] = 74, /* ...to 74 + NUM_SMMU_IRQS - 1 */ | ||
91 | [VIRT_PLATFORM_BUS] = 112, /* ...to 112 + PLATFORM_BUS_NUM_IRQS -1 */ | ||
92 | }; | ||
93 | |||
94 | @@ -XXX,XX +XXX,XX @@ static void create_pcie_irq_map(const VirtMachineState *vms, | ||
95 | 0x7 /* PCI irq */); | ||
96 | } | ||
97 | |||
98 | -static void create_pcie(const VirtMachineState *vms, qemu_irq *pic) | ||
99 | +static void create_smmu(const VirtMachineState *vms, qemu_irq *pic, | ||
100 | + PCIBus *bus) | ||
101 | +{ | ||
102 | + char *node; | ||
103 | + const char compat[] = "arm,smmu-v3"; | ||
104 | + int irq = vms->irqmap[VIRT_SMMU]; | ||
105 | + int i; | ||
106 | + hwaddr base = vms->memmap[VIRT_SMMU].base; | ||
107 | + hwaddr size = vms->memmap[VIRT_SMMU].size; | ||
108 | + const char irq_names[] = "eventq\0priq\0cmdq-sync\0gerror"; | ||
109 | + DeviceState *dev; | ||
110 | + | ||
111 | + if (vms->iommu != VIRT_IOMMU_SMMUV3 || !vms->iommu_phandle) { | ||
112 | + return; | ||
113 | + } | 93 | + } |
114 | + | 94 | + |
115 | + dev = qdev_create(NULL, "arm-smmuv3"); | 95 | +#define DO_MOVI(N, I) (I) |
96 | +#define DO_ANDI(N, I) ((N) & (I)) | ||
97 | +#define DO_ORRI(N, I) ((N) | (I)) | ||
116 | + | 98 | + |
117 | + object_property_set_link(OBJECT(dev), OBJECT(bus), "primary-bus", | 99 | +DO_1OP_IMM(vmovi, DO_MOVI) |
118 | + &error_abort); | 100 | +DO_1OP_IMM(vandi, DO_ANDI) |
119 | + qdev_init_nofail(dev); | 101 | +DO_1OP_IMM(vorri, DO_ORRI) |
120 | + sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, base); | 102 | + |
121 | + for (i = 0; i < NUM_SMMU_IRQS; i++) { | 103 | #define DO_2OP(OP, ESIZE, TYPE, FN) \ |
122 | + sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, pic[irq + i]); | 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; | ||
123 | + } | 135 | + } |
124 | + | 136 | + |
125 | + node = g_strdup_printf("/smmuv3@%" PRIx64, base); | 137 | + imm = asimd_imm_const(a->imm, a->cmode, a->op); |
126 | + qemu_fdt_add_subnode(vms->fdt, node); | ||
127 | + qemu_fdt_setprop(vms->fdt, node, "compatible", compat, sizeof(compat)); | ||
128 | + qemu_fdt_setprop_sized_cells(vms->fdt, node, "reg", 2, base, 2, size); | ||
129 | + | 138 | + |
130 | + qemu_fdt_setprop_cells(vms->fdt, node, "interrupts", | 139 | + qd = mve_qreg_ptr(a->qd); |
131 | + GIC_FDT_IRQ_TYPE_SPI, irq , GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, | 140 | + fn(cpu_env, qd, tcg_constant_i64(imm)); |
132 | + GIC_FDT_IRQ_TYPE_SPI, irq + 1, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, | 141 | + tcg_temp_free_ptr(qd); |
133 | + GIC_FDT_IRQ_TYPE_SPI, irq + 2, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, | 142 | + mve_update_eci(s); |
134 | + GIC_FDT_IRQ_TYPE_SPI, irq + 3, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI); | 143 | + return true; |
135 | + | ||
136 | + qemu_fdt_setprop(vms->fdt, node, "interrupt-names", irq_names, | ||
137 | + sizeof(irq_names)); | ||
138 | + | ||
139 | + qemu_fdt_setprop_cell(vms->fdt, node, "clocks", vms->clock_phandle); | ||
140 | + qemu_fdt_setprop_string(vms->fdt, node, "clock-names", "apb_pclk"); | ||
141 | + qemu_fdt_setprop(vms->fdt, node, "dma-coherent", NULL, 0); | ||
142 | + | ||
143 | + qemu_fdt_setprop_cell(vms->fdt, node, "#iommu-cells", 1); | ||
144 | + | ||
145 | + qemu_fdt_setprop_cell(vms->fdt, node, "phandle", vms->iommu_phandle); | ||
146 | + g_free(node); | ||
147 | +} | 144 | +} |
148 | + | 145 | + |
149 | +static void create_pcie(VirtMachineState *vms, qemu_irq *pic) | 146 | +static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) |
150 | { | 147 | +{ |
151 | hwaddr base_mmio = vms->memmap[VIRT_PCIE_MMIO].base; | 148 | + /* Handle decode of cmode/op here between VORR/VBIC/VMOV */ |
152 | hwaddr size_mmio = vms->memmap[VIRT_PCIE_MMIO].size; | 149 | + MVEGenOneOpImmFn *fn; |
153 | @@ -XXX,XX +XXX,XX @@ static void create_pcie(const VirtMachineState *vms, qemu_irq *pic) | ||
154 | qemu_fdt_setprop_cell(vms->fdt, nodename, "#interrupt-cells", 1); | ||
155 | create_pcie_irq_map(vms, vms->gic_phandle, irq, nodename); | ||
156 | |||
157 | + if (vms->iommu) { | ||
158 | + vms->iommu_phandle = qemu_fdt_alloc_phandle(vms->fdt); | ||
159 | + | 150 | + |
160 | + create_smmu(vms, pic, pci->bus); | 151 | + if ((a->cmode & 1) && a->cmode < 12) { |
161 | + | 152 | + if (a->op) { |
162 | + qemu_fdt_setprop_cells(vms->fdt, nodename, "iommu-map", | 153 | + /* |
163 | + 0x0, vms->iommu_phandle, 0x0, 0x10000); | 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; | ||
164 | + } | 168 | + } |
165 | + | 169 | + return do_1imm(s, a, fn); |
166 | g_free(nodename); | 170 | +} |
167 | } | ||
168 | |||
169 | -- | 171 | -- |
170 | 2.17.0 | 172 | 2.20.1 |
171 | 173 | ||
172 | 174 | diff view generated by jsdifflib |
1 | Convert the tusb6010 device away from using the old_mmio field | 1 | Implement the MVE shift-vector-left-by-immediate insns VSHL, VQSHL |
---|---|---|---|
2 | of MemoryRegionOps. This device is used only in the n800 and n810 | 2 | and VQSHLU. |
3 | boards. | 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. | ||
4 | 6 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Message-id: 20180427173611.10281-2-peter.maydell@linaro.org | 9 | Message-id: 20210628135835.6690-8-peter.maydell@linaro.org |
8 | --- | 10 | --- |
9 | hw/usb/tusb6010.c | 40 ++++++++++++++++++++++++++++++++++++---- | 11 | target/arm/helper-mve.h | 16 +++++++++++ |
10 | 1 file changed, 36 insertions(+), 4 deletions(-) | 12 | target/arm/mve.decode | 23 +++++++++++++++ |
11 | 13 | target/arm/mve_helper.c | 57 ++++++++++++++++++++++++++++++++++++++ | |
12 | diff --git a/hw/usb/tusb6010.c b/hw/usb/tusb6010.c | 14 | target/arm/translate-mve.c | 51 ++++++++++++++++++++++++++++++++++ |
13 | index XXXXXXX..XXXXXXX 100644 | 15 | 4 files changed, 147 insertions(+) |
14 | --- a/hw/usb/tusb6010.c | 16 | |
15 | +++ b/hw/usb/tusb6010.c | 17 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
16 | @@ -XXX,XX +XXX,XX @@ static void tusb_async_writew(void *opaque, hwaddr addr, | 18 | index XXXXXXX..XXXXXXX 100644 |
19 | --- a/target/arm/helper-mve.h | ||
20 | +++ b/target/arm/helper-mve.h | ||
21 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) | ||
22 | DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
23 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
24 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
25 | + | ||
26 | +DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
27 | +DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
28 | +DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
29 | + | ||
30 | +DEF_HELPER_FLAGS_4(mve_vqshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
31 | +DEF_HELPER_FLAGS_4(mve_vqshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
32 | +DEF_HELPER_FLAGS_4(mve_vqshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
33 | + | ||
34 | +DEF_HELPER_FLAGS_4(mve_vqshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
35 | +DEF_HELPER_FLAGS_4(mve_vqshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
36 | +DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
37 | + | ||
38 | +DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
39 | +DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
40 | +DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
41 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode | ||
42 | index XXXXXXX..XXXXXXX 100644 | ||
43 | --- a/target/arm/mve.decode | ||
44 | +++ b/target/arm/mve.decode | ||
45 | @@ -XXX,XX +XXX,XX @@ | ||
46 | &2op qd qm qn size | ||
47 | &2scalar qd qn rm size | ||
48 | &1imm qd imm cmode op | ||
49 | +&2shift qd qm shift size | ||
50 | |||
51 | @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 | ||
52 | # Note that both Rn and Qd are 3 bits only (no D bit) | ||
53 | @@ -XXX,XX +XXX,XX @@ | ||
54 | @2scalar .... .... .. size:2 .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn | ||
55 | @2scalar_nosz .... .... .... .... .... .... .... rm:4 &2scalar qd=%qd qn=%qn | ||
56 | |||
57 | +@2_shl_b .... .... .. 001 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 | ||
58 | +@2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 | ||
59 | +@2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 | ||
60 | + | ||
61 | # Vector loads and stores | ||
62 | |||
63 | # Widening loads and narrowing stores: | ||
64 | @@ -XXX,XX +XXX,XX @@ VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 | ||
65 | # So we have a single decode line and check the cmode/op in the | ||
66 | # trans function. | ||
67 | Vimm_1r 111 . 1111 1 . 00 0 ... ... 0 .... 0 1 . 1 .... @1imm | ||
68 | + | ||
69 | +# Shifts by immediate | ||
70 | + | ||
71 | +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b | ||
72 | +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h | ||
73 | +VSHLI 111 0 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w | ||
74 | + | ||
75 | +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b | ||
76 | +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h | ||
77 | +VQSHLI_S 111 0 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w | ||
78 | + | ||
79 | +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_b | ||
80 | +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_h | ||
81 | +VQSHLI_U 111 1 1111 1 . ... ... ... 0 0111 0 1 . 1 ... 0 @2_shl_w | ||
82 | + | ||
83 | +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_b | ||
84 | +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_h | ||
85 | +VQSHLUI 111 1 1111 1 . ... ... ... 0 0110 0 1 . 1 ... 0 @2_shl_w | ||
86 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
87 | index XXXXXXX..XXXXXXX 100644 | ||
88 | --- a/target/arm/mve_helper.c | ||
89 | +++ b/target/arm/mve_helper.c | ||
90 | @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT(vqsubsw, 4, int32_t, DO_SQSUB_W) | ||
91 | WRAP_QRSHL_HELPER(do_sqrshl_bhs, N, M, true, satp) | ||
92 | #define DO_UQRSHL_OP(N, M, satp) \ | ||
93 | WRAP_QRSHL_HELPER(do_uqrshl_bhs, N, M, true, satp) | ||
94 | +#define DO_SUQSHL_OP(N, M, satp) \ | ||
95 | + WRAP_QRSHL_HELPER(do_suqrshl_bhs, N, M, false, satp) | ||
96 | |||
97 | DO_2OP_SAT_S(vqshls, DO_SQSHL_OP) | ||
98 | DO_2OP_SAT_U(vqshlu, DO_UQSHL_OP) | ||
99 | @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvsw, 4, uint32_t) | ||
100 | DO_VADDV(vaddvub, 1, uint8_t) | ||
101 | DO_VADDV(vaddvuh, 2, uint16_t) | ||
102 | DO_VADDV(vaddvuw, 4, uint32_t) | ||
103 | + | ||
104 | +/* Shifts by immediate */ | ||
105 | +#define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ | ||
106 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
107 | + void *vm, uint32_t shift) \ | ||
108 | + { \ | ||
109 | + TYPE *d = vd, *m = vm; \ | ||
110 | + uint16_t mask = mve_element_mask(env); \ | ||
111 | + unsigned e; \ | ||
112 | + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ | ||
113 | + mergemask(&d[H##ESIZE(e)], \ | ||
114 | + FN(m[H##ESIZE(e)], shift), mask); \ | ||
115 | + } \ | ||
116 | + mve_advance_vpt(env); \ | ||
117 | + } | ||
118 | + | ||
119 | +#define DO_2SHIFT_SAT(OP, ESIZE, TYPE, FN) \ | ||
120 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
121 | + void *vm, uint32_t shift) \ | ||
122 | + { \ | ||
123 | + TYPE *d = vd, *m = vm; \ | ||
124 | + uint16_t mask = mve_element_mask(env); \ | ||
125 | + unsigned e; \ | ||
126 | + bool qc = false; \ | ||
127 | + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ | ||
128 | + bool sat = false; \ | ||
129 | + mergemask(&d[H##ESIZE(e)], \ | ||
130 | + FN(m[H##ESIZE(e)], shift, &sat), mask); \ | ||
131 | + qc |= sat & mask & 1; \ | ||
132 | + } \ | ||
133 | + if (qc) { \ | ||
134 | + env->vfp.qc[0] = qc; \ | ||
135 | + } \ | ||
136 | + mve_advance_vpt(env); \ | ||
137 | + } | ||
138 | + | ||
139 | +/* provide unsigned 2-op shift helpers for all sizes */ | ||
140 | +#define DO_2SHIFT_U(OP, FN) \ | ||
141 | + DO_2SHIFT(OP##b, 1, uint8_t, FN) \ | ||
142 | + DO_2SHIFT(OP##h, 2, uint16_t, FN) \ | ||
143 | + DO_2SHIFT(OP##w, 4, uint32_t, FN) | ||
144 | + | ||
145 | +#define DO_2SHIFT_SAT_U(OP, FN) \ | ||
146 | + DO_2SHIFT_SAT(OP##b, 1, uint8_t, FN) \ | ||
147 | + DO_2SHIFT_SAT(OP##h, 2, uint16_t, FN) \ | ||
148 | + DO_2SHIFT_SAT(OP##w, 4, uint32_t, FN) | ||
149 | +#define DO_2SHIFT_SAT_S(OP, FN) \ | ||
150 | + DO_2SHIFT_SAT(OP##b, 1, int8_t, FN) \ | ||
151 | + DO_2SHIFT_SAT(OP##h, 2, int16_t, FN) \ | ||
152 | + DO_2SHIFT_SAT(OP##w, 4, int32_t, FN) | ||
153 | + | ||
154 | +DO_2SHIFT_U(vshli_u, DO_VSHLU) | ||
155 | +DO_2SHIFT_SAT_U(vqshli_u, DO_UQSHL_OP) | ||
156 | +DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) | ||
157 | +DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) | ||
158 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c | ||
159 | index XXXXXXX..XXXXXXX 100644 | ||
160 | --- a/target/arm/translate-mve.c | ||
161 | +++ b/target/arm/translate-mve.c | ||
162 | @@ -XXX,XX +XXX,XX @@ typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
163 | typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
164 | typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
165 | typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
166 | +typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
167 | typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); | ||
168 | typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
169 | typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); | ||
170 | @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1imm *a) | ||
17 | } | 171 | } |
172 | return do_1imm(s, a, fn); | ||
18 | } | 173 | } |
19 | 174 | + | |
20 | +static uint64_t tusb_async_readfn(void *opaque, hwaddr addr, unsigned size) | 175 | +static bool do_2shift(DisasContext *s, arg_2shift *a, MVEGenTwoOpShiftFn fn, |
176 | + bool negateshift) | ||
21 | +{ | 177 | +{ |
22 | + switch (size) { | 178 | + TCGv_ptr qd, qm; |
23 | + case 1: | 179 | + int shift = a->shift; |
24 | + return tusb_async_readb(opaque, addr); | 180 | + |
25 | + case 2: | 181 | + if (!dc_isar_feature(aa32_mve, s) || |
26 | + return tusb_async_readh(opaque, addr); | 182 | + !mve_check_qreg_bank(s, a->qd | a->qm) || |
27 | + case 4: | 183 | + !fn) { |
28 | + return tusb_async_readw(opaque, addr); | 184 | + return false; |
29 | + default: | 185 | + } |
30 | + g_assert_not_reached(); | 186 | + if (!mve_eci_check(s) || !vfp_access_check(s)) { |
31 | + } | 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; | ||
32 | +} | 206 | +} |
33 | + | 207 | + |
34 | +static void tusb_async_writefn(void *opaque, hwaddr addr, | 208 | +#define DO_2SHIFT(INSN, FN, NEGATESHIFT) \ |
35 | + uint64_t value, unsigned size) | 209 | + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
36 | +{ | 210 | + { \ |
37 | + switch (size) { | 211 | + static MVEGenTwoOpShiftFn * const fns[] = { \ |
38 | + case 1: | 212 | + gen_helper_mve_##FN##b, \ |
39 | + tusb_async_writeb(opaque, addr, value); | 213 | + gen_helper_mve_##FN##h, \ |
40 | + break; | 214 | + gen_helper_mve_##FN##w, \ |
41 | + case 2: | 215 | + NULL, \ |
42 | + tusb_async_writeh(opaque, addr, value); | 216 | + }; \ |
43 | + break; | 217 | + return do_2shift(s, a, fns[a->size], NEGATESHIFT); \ |
44 | + case 4: | 218 | + } |
45 | + tusb_async_writew(opaque, addr, value); | 219 | + |
46 | + break; | 220 | +DO_2SHIFT(VSHLI, vshli_u, false) |
47 | + default: | 221 | +DO_2SHIFT(VQSHLI_S, vqshli_s, false) |
48 | + g_assert_not_reached(); | 222 | +DO_2SHIFT(VQSHLI_U, vqshli_u, false) |
49 | + } | 223 | +DO_2SHIFT(VQSHLUI, vqshlui_s, false) |
50 | +} | ||
51 | + | ||
52 | static const MemoryRegionOps tusb_async_ops = { | ||
53 | - .old_mmio = { | ||
54 | - .read = { tusb_async_readb, tusb_async_readh, tusb_async_readw, }, | ||
55 | - .write = { tusb_async_writeb, tusb_async_writeh, tusb_async_writew, }, | ||
56 | - }, | ||
57 | + .read = tusb_async_readfn, | ||
58 | + .write = tusb_async_writefn, | ||
59 | + .valid.min_access_size = 1, | ||
60 | + .valid.max_access_size = 4, | ||
61 | .endianness = DEVICE_NATIVE_ENDIAN, | ||
62 | }; | ||
63 | |||
64 | -- | 224 | -- |
65 | 2.17.0 | 225 | 2.20.1 |
66 | 226 | ||
67 | 227 | diff view generated by jsdifflib |
1 | Convert the smc91c111 device away from using the old_mmio field of | 1 | Implement the MVE vector shift right by immediate insns VSHRI and |
---|---|---|---|
2 | MemoryRegionOps. This device is used by several Arm board models. | 2 | VRSHRI. As with Neon, we implement these by using helper functions |
3 | which perform left shifts but allow negative shift counts to indicate | ||
4 | right shifts. | ||
3 | 5 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20180427173611.10281-3-peter.maydell@linaro.org | 8 | Message-id: 20210628135835.6690-9-peter.maydell@linaro.org |
7 | --- | 9 | --- |
8 | hw/net/smc91c111.c | 54 +++++++++++++++++++++------------------------- | 10 | target/arm/helper-mve.h | 12 ++++++++++++ |
9 | 1 file changed, 25 insertions(+), 29 deletions(-) | 11 | target/arm/translate.h | 20 ++++++++++++++++++++ |
12 | target/arm/mve.decode | 28 ++++++++++++++++++++++++++++ | ||
13 | target/arm/mve_helper.c | 7 +++++++ | ||
14 | target/arm/translate-mve.c | 5 +++++ | ||
15 | target/arm/translate-neon.c | 18 ------------------ | ||
16 | 6 files changed, 72 insertions(+), 18 deletions(-) | ||
10 | 17 | ||
11 | diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c | 18 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
12 | index XXXXXXX..XXXXXXX 100644 | 19 | index XXXXXXX..XXXXXXX 100644 |
13 | --- a/hw/net/smc91c111.c | 20 | --- a/target/arm/helper-mve.h |
14 | +++ b/hw/net/smc91c111.c | 21 | +++ b/target/arm/helper-mve.h |
15 | @@ -XXX,XX +XXX,XX @@ static uint32_t smc91c111_readb(void *opaque, hwaddr offset) | 22 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) |
16 | return 0; | 23 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) |
24 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
25 | |||
26 | +DEF_HELPER_FLAGS_4(mve_vshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
27 | +DEF_HELPER_FLAGS_4(mve_vshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
28 | +DEF_HELPER_FLAGS_4(mve_vshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
29 | + | ||
30 | DEF_HELPER_FLAGS_4(mve_vshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
31 | DEF_HELPER_FLAGS_4(mve_vshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
32 | DEF_HELPER_FLAGS_4(mve_vshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
33 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
34 | DEF_HELPER_FLAGS_4(mve_vqshlui_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
35 | DEF_HELPER_FLAGS_4(mve_vqshlui_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
36 | DEF_HELPER_FLAGS_4(mve_vqshlui_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
37 | + | ||
38 | +DEF_HELPER_FLAGS_4(mve_vrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
39 | +DEF_HELPER_FLAGS_4(mve_vrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
40 | +DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
41 | + | ||
42 | +DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
43 | +DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
44 | +DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
45 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
46 | index XXXXXXX..XXXXXXX 100644 | ||
47 | --- a/target/arm/translate.h | ||
48 | +++ b/target/arm/translate.h | ||
49 | @@ -XXX,XX +XXX,XX @@ static inline int times_2_plus_1(DisasContext *s, int x) | ||
50 | return x * 2 + 1; | ||
17 | } | 51 | } |
18 | 52 | ||
19 | -static void smc91c111_writew(void *opaque, hwaddr offset, | 53 | +static inline int rsub_64(DisasContext *s, int x) |
20 | - uint32_t value) | 54 | +{ |
21 | +static uint64_t smc91c111_readfn(void *opaque, hwaddr addr, unsigned size) | 55 | + return 64 - x; |
56 | +} | ||
57 | + | ||
58 | +static inline int rsub_32(DisasContext *s, int x) | ||
59 | +{ | ||
60 | + return 32 - x; | ||
61 | +} | ||
62 | + | ||
63 | +static inline int rsub_16(DisasContext *s, int x) | ||
64 | +{ | ||
65 | + return 16 - x; | ||
66 | +} | ||
67 | + | ||
68 | +static inline int rsub_8(DisasContext *s, int x) | ||
69 | +{ | ||
70 | + return 8 - x; | ||
71 | +} | ||
72 | + | ||
73 | static inline int arm_dc_feature(DisasContext *dc, int feature) | ||
22 | { | 74 | { |
23 | - smc91c111_writeb(opaque, offset, value & 0xff); | 75 | return (dc->features & (1ULL << feature)) != 0; |
24 | - smc91c111_writeb(opaque, offset + 1, value >> 8); | 76 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
25 | + int i; | 77 | index XXXXXXX..XXXXXXX 100644 |
26 | + uint32_t val = 0; | 78 | --- a/target/arm/mve.decode |
79 | +++ b/target/arm/mve.decode | ||
80 | @@ -XXX,XX +XXX,XX @@ | ||
81 | @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 | ||
82 | @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 | ||
83 | |||
84 | +# Right shifts are encoded as N - shift, where N is the element size in bits. | ||
85 | +%rshift_i5 16:5 !function=rsub_32 | ||
86 | +%rshift_i4 16:4 !function=rsub_16 | ||
87 | +%rshift_i3 16:3 !function=rsub_8 | ||
27 | + | 88 | + |
28 | + for (i = 0; i < size; i++) { | 89 | +@2_shr_b .... .... .. 001 ... .... .... .... .... &2shift qd=%qd qm=%qm \ |
29 | + val |= smc91c111_readb(opaque, addr + i) << (i * 8); | 90 | + size=0 shift=%rshift_i3 |
30 | + } | 91 | +@2_shr_h .... .... .. 01 .... .... .... .... .... &2shift qd=%qd qm=%qm \ |
31 | + return val; | 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; | ||
32 | } | 163 | } |
33 | 164 | ||
34 | -static void smc91c111_writel(void *opaque, hwaddr offset, | 165 | -static inline int rsub_64(DisasContext *s, int x) |
35 | - uint32_t value) | ||
36 | +static void smc91c111_writefn(void *opaque, hwaddr addr, | ||
37 | + uint64_t value, unsigned size) | ||
38 | { | ||
39 | + int i = 0; | ||
40 | + | ||
41 | /* 32-bit writes to offset 0xc only actually write to the bank select | ||
42 | - register (offset 0xe) */ | ||
43 | - if (offset != 0xc) | ||
44 | - smc91c111_writew(opaque, offset, value & 0xffff); | ||
45 | - smc91c111_writew(opaque, offset + 2, value >> 16); | ||
46 | -} | ||
47 | + * register (offset 0xe), so skip the first two bytes we would write. | ||
48 | + */ | ||
49 | + if (addr == 0xc && size == 4) { | ||
50 | + i += 2; | ||
51 | + } | ||
52 | |||
53 | -static uint32_t smc91c111_readw(void *opaque, hwaddr offset) | ||
54 | -{ | 166 | -{ |
55 | - uint32_t val; | 167 | - return 64 - x; |
56 | - val = smc91c111_readb(opaque, offset); | ||
57 | - val |= smc91c111_readb(opaque, offset + 1) << 8; | ||
58 | - return val; | ||
59 | -} | 168 | -} |
60 | - | 169 | - |
61 | -static uint32_t smc91c111_readl(void *opaque, hwaddr offset) | 170 | -static inline int rsub_32(DisasContext *s, int x) |
62 | -{ | 171 | -{ |
63 | - uint32_t val; | 172 | - return 32 - x; |
64 | - val = smc91c111_readw(opaque, offset); | 173 | -} |
65 | - val |= smc91c111_readw(opaque, offset + 2) << 16; | 174 | -static inline int rsub_16(DisasContext *s, int x) |
66 | - return val; | 175 | -{ |
67 | + for (; i < size; i++) { | 176 | - return 16 - x; |
68 | + smc91c111_writeb(opaque, addr + i, | 177 | -} |
69 | + extract32(value, i * 8, 8)); | 178 | -static inline int rsub_8(DisasContext *s, int x) |
70 | + } | 179 | -{ |
71 | } | 180 | - return 8 - x; |
72 | 181 | -} | |
73 | static int smc91c111_can_receive_nc(NetClientState *nc) | 182 | - |
74 | @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps smc91c111_mem_ops = { | 183 | static inline int neon_3same_fp_size(DisasContext *s, int x) |
75 | /* The special case for 32 bit writes to 0xc means we can't just | 184 | { |
76 | * set .impl.min/max_access_size to 1, unfortunately | 185 | /* Convert 0==fp32, 1==fp16 into a MO_* value */ |
77 | */ | ||
78 | - .old_mmio = { | ||
79 | - .read = { smc91c111_readb, smc91c111_readw, smc91c111_readl, }, | ||
80 | - .write = { smc91c111_writeb, smc91c111_writew, smc91c111_writel, }, | ||
81 | - }, | ||
82 | + .read = smc91c111_readfn, | ||
83 | + .write = smc91c111_writefn, | ||
84 | + .valid.min_access_size = 1, | ||
85 | + .valid.max_access_size = 4, | ||
86 | .endianness = DEVICE_NATIVE_ENDIAN, | ||
87 | }; | ||
88 | |||
89 | -- | 186 | -- |
90 | 2.17.0 | 187 | 2.20.1 |
91 | 188 | ||
92 | 189 | diff view generated by jsdifflib |
1 | From: Prem Mallappa <prem.mallappa@broadcom.com> | 1 | Implement the MVE VHLL (vector shift left long) insn. This has two |
---|---|---|---|
2 | encodings: the T1 encoding is the usual shift-by-immediate format, | ||
3 | and the T2 encoding is a special case where the shift count is always | ||
4 | equal to the element size. | ||
2 | 5 | ||
3 | This patch implements a skeleton for the smmuv3 device. | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | Datatypes and register definitions are introduced. The MMIO | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | region, the interrupts and the queue are initialized. | 8 | Message-id: 20210628135835.6690-10-peter.maydell@linaro.org |
9 | --- | ||
10 | target/arm/helper-mve.h | 9 +++++++ | ||
11 | target/arm/mve.decode | 53 +++++++++++++++++++++++++++++++++++--- | ||
12 | target/arm/mve_helper.c | 32 +++++++++++++++++++++++ | ||
13 | target/arm/translate-mve.c | 15 +++++++++++ | ||
14 | 4 files changed, 105 insertions(+), 4 deletions(-) | ||
6 | 15 | ||
7 | Only the MMIO read operation is implemented here. | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
8 | |||
9 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
10 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
11 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Message-id: 1524665762-31355-5-git-send-email-eric.auger@redhat.com | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | --- | ||
15 | hw/arm/Makefile.objs | 2 +- | ||
16 | hw/arm/smmuv3-internal.h | 142 +++++++++++++++ | ||
17 | include/hw/arm/smmuv3.h | 87 ++++++++++ | ||
18 | hw/arm/smmuv3.c | 366 +++++++++++++++++++++++++++++++++++++++ | ||
19 | hw/arm/trace-events | 3 + | ||
20 | 5 files changed, 599 insertions(+), 1 deletion(-) | ||
21 | create mode 100644 hw/arm/smmuv3-internal.h | ||
22 | create mode 100644 include/hw/arm/smmuv3.h | ||
23 | create mode 100644 hw/arm/smmuv3.c | ||
24 | |||
25 | diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs | ||
26 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
27 | --- a/hw/arm/Makefile.objs | 18 | --- a/target/arm/helper-mve.h |
28 | +++ b/hw/arm/Makefile.objs | 19 | +++ b/target/arm/helper-mve.h |
29 | @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_MPS2) += mps2-tz.o | 20 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
30 | obj-$(CONFIG_MSF2) += msf2-soc.o msf2-som.o | 21 | DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
31 | obj-$(CONFIG_IOTKIT) += iotkit.o | 22 | DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
32 | obj-$(CONFIG_FSL_IMX7) += fsl-imx7.o mcimx7d-sabre.o | 23 | DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
33 | -obj-$(CONFIG_ARM_SMMUV3) += smmu-common.o | 24 | + |
34 | +obj-$(CONFIG_ARM_SMMUV3) += smmu-common.o smmuv3.o | 25 | +DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
35 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | 26 | +DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
36 | new file mode 100644 | 27 | +DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
37 | index XXXXXXX..XXXXXXX | 28 | +DEF_HELPER_FLAGS_4(mve_vshllbuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
38 | --- /dev/null | 29 | +DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
39 | +++ b/hw/arm/smmuv3-internal.h | 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 | ||
40 | @@ -XXX,XX +XXX,XX @@ | 37 | @@ -XXX,XX +XXX,XX @@ |
41 | +/* | 38 | @2_shl_h .... .... .. 01 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 |
42 | + * ARM SMMUv3 support - Internal API | 39 | @2_shl_w .... .... .. 1 shift:5 .... .... .... .... &2shift qd=%qd qm=%qm size=2 |
43 | + * | 40 | |
44 | + * Copyright (C) 2014-2016 Broadcom Corporation | 41 | +@2_shll_b .... .... ... 01 shift:3 .... .... .... .... &2shift qd=%qd qm=%qm size=0 |
45 | + * Copyright (c) 2017 Red Hat, Inc. | 42 | +@2_shll_h .... .... ... 1 shift:4 .... .... .... .... &2shift qd=%qd qm=%qm size=1 |
46 | + * Written by Prem Mallappa, Eric Auger | 43 | +# VSHLL encoding T2 where shift == esize |
47 | + * | 44 | +@2_shll_esize_b .... .... .... 00 .. .... .... .... .... &2shift \ |
48 | + * This program is free software; you can redistribute it and/or modify | 45 | + qd=%qd qm=%qm size=0 shift=8 |
49 | + * it under the terms of the GNU General Public License version 2 as | 46 | +@2_shll_esize_h .... .... .... 01 .. .... .... .... .... &2shift \ |
50 | + * published by the Free Software Foundation. | 47 | + qd=%qd qm=%qm size=1 shift=16 |
51 | + * | ||
52 | + * This program is distributed in the hope that it will be useful, | ||
53 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
54 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
55 | + * GNU General Public License for more details. | ||
56 | + * | ||
57 | + * You should have received a copy of the GNU General Public License along | ||
58 | + * with this program; if not, see <http://www.gnu.org/licenses/>. | ||
59 | + */ | ||
60 | + | 48 | + |
61 | +#ifndef HW_ARM_SMMU_V3_INTERNAL_H | 49 | # Right shifts are encoded as N - shift, where N is the element size in bits. |
62 | +#define HW_ARM_SMMU_V3_INTERNAL_H | 50 | %rshift_i5 16:5 !function=rsub_32 |
63 | + | 51 | %rshift_i4 16:4 !function=rsub_16 |
64 | +#include "hw/arm/smmu-common.h" | 52 | @@ -XXX,XX +XXX,XX @@ VADD 1110 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op |
65 | + | 53 | VSUB 1111 1111 0 . .. ... 0 ... 0 1000 . 1 . 0 ... 0 @2op |
66 | +/* MMIO Registers */ | 54 | VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op |
67 | + | 55 | |
68 | +REG32(IDR0, 0x0) | 56 | -VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op |
69 | + FIELD(IDR0, S1P, 1 , 1) | 57 | -VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op |
70 | + FIELD(IDR0, TTF, 2 , 2) | 58 | +# The VSHLL T2 encoding is not a @2op pattern, but is here because it |
71 | + FIELD(IDR0, COHACC, 4 , 1) | 59 | +# overlaps what would be size=0b11 VMULH/VRMULH |
72 | + FIELD(IDR0, ASID16, 12, 1) | ||
73 | + FIELD(IDR0, TTENDIAN, 21, 2) | ||
74 | + FIELD(IDR0, STALL_MODEL, 24, 2) | ||
75 | + FIELD(IDR0, TERM_MODEL, 26, 1) | ||
76 | + FIELD(IDR0, STLEVEL, 27, 2) | ||
77 | + | ||
78 | +REG32(IDR1, 0x4) | ||
79 | + FIELD(IDR1, SIDSIZE, 0 , 6) | ||
80 | + FIELD(IDR1, EVENTQS, 16, 5) | ||
81 | + FIELD(IDR1, CMDQS, 21, 5) | ||
82 | + | ||
83 | +#define SMMU_IDR1_SIDSIZE 16 | ||
84 | +#define SMMU_CMDQS 19 | ||
85 | +#define SMMU_EVENTQS 19 | ||
86 | + | ||
87 | +REG32(IDR2, 0x8) | ||
88 | +REG32(IDR3, 0xc) | ||
89 | +REG32(IDR4, 0x10) | ||
90 | +REG32(IDR5, 0x14) | ||
91 | + FIELD(IDR5, OAS, 0, 3); | ||
92 | + FIELD(IDR5, GRAN4K, 4, 1); | ||
93 | + FIELD(IDR5, GRAN16K, 5, 1); | ||
94 | + FIELD(IDR5, GRAN64K, 6, 1); | ||
95 | + | ||
96 | +#define SMMU_IDR5_OAS 4 | ||
97 | + | ||
98 | +REG32(IIDR, 0x1c) | ||
99 | +REG32(CR0, 0x20) | ||
100 | + FIELD(CR0, SMMU_ENABLE, 0, 1) | ||
101 | + FIELD(CR0, EVENTQEN, 2, 1) | ||
102 | + FIELD(CR0, CMDQEN, 3, 1) | ||
103 | + | ||
104 | +REG32(CR0ACK, 0x24) | ||
105 | +REG32(CR1, 0x28) | ||
106 | +REG32(CR2, 0x2c) | ||
107 | +REG32(STATUSR, 0x40) | ||
108 | +REG32(IRQ_CTRL, 0x50) | ||
109 | + FIELD(IRQ_CTRL, GERROR_IRQEN, 0, 1) | ||
110 | + FIELD(IRQ_CTRL, PRI_IRQEN, 1, 1) | ||
111 | + FIELD(IRQ_CTRL, EVENTQ_IRQEN, 2, 1) | ||
112 | + | ||
113 | +REG32(IRQ_CTRL_ACK, 0x54) | ||
114 | +REG32(GERROR, 0x60) | ||
115 | + FIELD(GERROR, CMDQ_ERR, 0, 1) | ||
116 | + FIELD(GERROR, EVENTQ_ABT_ERR, 2, 1) | ||
117 | + FIELD(GERROR, PRIQ_ABT_ERR, 3, 1) | ||
118 | + FIELD(GERROR, MSI_CMDQ_ABT_ERR, 4, 1) | ||
119 | + FIELD(GERROR, MSI_EVENTQ_ABT_ERR, 5, 1) | ||
120 | + FIELD(GERROR, MSI_PRIQ_ABT_ERR, 6, 1) | ||
121 | + FIELD(GERROR, MSI_GERROR_ABT_ERR, 7, 1) | ||
122 | + FIELD(GERROR, MSI_SFM_ERR, 8, 1) | ||
123 | + | ||
124 | +REG32(GERRORN, 0x64) | ||
125 | + | ||
126 | +#define A_GERROR_IRQ_CFG0 0x68 /* 64b */ | ||
127 | +REG32(GERROR_IRQ_CFG1, 0x70) | ||
128 | +REG32(GERROR_IRQ_CFG2, 0x74) | ||
129 | + | ||
130 | +#define A_STRTAB_BASE 0x80 /* 64b */ | ||
131 | + | ||
132 | +#define SMMU_BASE_ADDR_MASK 0xffffffffffe0 | ||
133 | + | ||
134 | +REG32(STRTAB_BASE_CFG, 0x88) | ||
135 | + FIELD(STRTAB_BASE_CFG, FMT, 16, 2) | ||
136 | + FIELD(STRTAB_BASE_CFG, SPLIT, 6 , 5) | ||
137 | + FIELD(STRTAB_BASE_CFG, LOG2SIZE, 0 , 6) | ||
138 | + | ||
139 | +#define A_CMDQ_BASE 0x90 /* 64b */ | ||
140 | +REG32(CMDQ_PROD, 0x98) | ||
141 | +REG32(CMDQ_CONS, 0x9c) | ||
142 | + FIELD(CMDQ_CONS, ERR, 24, 7) | ||
143 | + | ||
144 | +#define A_EVENTQ_BASE 0xa0 /* 64b */ | ||
145 | +REG32(EVENTQ_PROD, 0xa8) | ||
146 | +REG32(EVENTQ_CONS, 0xac) | ||
147 | + | ||
148 | +#define A_EVENTQ_IRQ_CFG0 0xb0 /* 64b */ | ||
149 | +REG32(EVENTQ_IRQ_CFG1, 0xb8) | ||
150 | +REG32(EVENTQ_IRQ_CFG2, 0xbc) | ||
151 | + | ||
152 | +#define A_IDREGS 0xfd0 | ||
153 | + | ||
154 | +static inline int smmu_enabled(SMMUv3State *s) | ||
155 | +{ | 60 | +{ |
156 | + return FIELD_EX32(s->cr[0], CR0, SMMU_ENABLE); | 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 | ||
157 | +} | 67 | +} |
158 | + | 68 | + |
159 | +/* Command Queue Entry */ | 69 | +{ |
160 | +typedef struct Cmd { | 70 | + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b |
161 | + uint32_t word[4]; | 71 | + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h |
162 | +} Cmd; | ||
163 | + | 72 | + |
164 | +/* Event Queue Entry */ | 73 | + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op |
165 | +typedef struct Evt { | ||
166 | + uint32_t word[8]; | ||
167 | +} Evt; | ||
168 | + | ||
169 | +static inline uint32_t smmuv3_idreg(int regoffset) | ||
170 | +{ | ||
171 | + /* | ||
172 | + * Return the value of the Primecell/Corelink ID registers at the | ||
173 | + * specified offset from the first ID register. | ||
174 | + * These value indicate an ARM implementation of MMU600 p1 | ||
175 | + */ | ||
176 | + static const uint8_t smmuv3_ids[] = { | ||
177 | + 0x04, 0, 0, 0, 0x84, 0xB4, 0xF0, 0x10, 0x0D, 0xF0, 0x05, 0xB1 | ||
178 | + }; | ||
179 | + return smmuv3_ids[regoffset / 4]; | ||
180 | +} | 74 | +} |
181 | + | 75 | + |
182 | +#endif | 76 | +{ |
183 | diff --git a/include/hw/arm/smmuv3.h b/include/hw/arm/smmuv3.h | 77 | + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b |
184 | new file mode 100644 | 78 | + VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h |
185 | index XXXXXXX..XXXXXXX | ||
186 | --- /dev/null | ||
187 | +++ b/include/hw/arm/smmuv3.h | ||
188 | @@ -XXX,XX +XXX,XX @@ | ||
189 | +/* | ||
190 | + * Copyright (C) 2014-2016 Broadcom Corporation | ||
191 | + * Copyright (c) 2017 Red Hat, Inc. | ||
192 | + * Written by Prem Mallappa, Eric Auger | ||
193 | + * | ||
194 | + * This program is free software; you can redistribute it and/or modify | ||
195 | + * it under the terms of the GNU General Public License version 2 as | ||
196 | + * published by the Free Software Foundation. | ||
197 | + * | ||
198 | + * This program is distributed in the hope that it will be useful, | ||
199 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
200 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
201 | + * GNU General Public License for more details. | ||
202 | + * | ||
203 | + * You should have received a copy of the GNU General Public License along | ||
204 | + * with this program; if not, see <http://www.gnu.org/licenses/>. | ||
205 | + */ | ||
206 | + | 79 | + |
207 | +#ifndef HW_ARM_SMMUV3_H | 80 | + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op |
208 | +#define HW_ARM_SMMUV3_H | ||
209 | + | ||
210 | +#include "hw/arm/smmu-common.h" | ||
211 | +#include "hw/registerfields.h" | ||
212 | + | ||
213 | +#define TYPE_SMMUV3_IOMMU_MEMORY_REGION "smmuv3-iommu-memory-region" | ||
214 | + | ||
215 | +typedef struct SMMUQueue { | ||
216 | + uint64_t base; /* base register */ | ||
217 | + uint32_t prod; | ||
218 | + uint32_t cons; | ||
219 | + uint8_t entry_size; | ||
220 | + uint8_t log2size; | ||
221 | +} SMMUQueue; | ||
222 | + | ||
223 | +typedef struct SMMUv3State { | ||
224 | + SMMUState smmu_state; | ||
225 | + | ||
226 | + uint32_t features; | ||
227 | + uint8_t sid_size; | ||
228 | + uint8_t sid_split; | ||
229 | + | ||
230 | + uint32_t idr[6]; | ||
231 | + uint32_t iidr; | ||
232 | + uint32_t cr[3]; | ||
233 | + uint32_t cr0ack; | ||
234 | + uint32_t statusr; | ||
235 | + uint32_t irq_ctrl; | ||
236 | + uint32_t gerror; | ||
237 | + uint32_t gerrorn; | ||
238 | + uint64_t gerror_irq_cfg0; | ||
239 | + uint32_t gerror_irq_cfg1; | ||
240 | + uint32_t gerror_irq_cfg2; | ||
241 | + uint64_t strtab_base; | ||
242 | + uint32_t strtab_base_cfg; | ||
243 | + uint64_t eventq_irq_cfg0; | ||
244 | + uint32_t eventq_irq_cfg1; | ||
245 | + uint32_t eventq_irq_cfg2; | ||
246 | + | ||
247 | + SMMUQueue eventq, cmdq; | ||
248 | + | ||
249 | + qemu_irq irq[4]; | ||
250 | +} SMMUv3State; | ||
251 | + | ||
252 | +typedef enum { | ||
253 | + SMMU_IRQ_EVTQ, | ||
254 | + SMMU_IRQ_PRIQ, | ||
255 | + SMMU_IRQ_CMD_SYNC, | ||
256 | + SMMU_IRQ_GERROR, | ||
257 | +} SMMUIrq; | ||
258 | + | ||
259 | +typedef struct { | ||
260 | + /*< private >*/ | ||
261 | + SMMUBaseClass smmu_base_class; | ||
262 | + /*< public >*/ | ||
263 | + | ||
264 | + DeviceRealize parent_realize; | ||
265 | + DeviceReset parent_reset; | ||
266 | +} SMMUv3Class; | ||
267 | + | ||
268 | +#define TYPE_ARM_SMMUV3 "arm-smmuv3" | ||
269 | +#define ARM_SMMUV3(obj) OBJECT_CHECK(SMMUv3State, (obj), TYPE_ARM_SMMUV3) | ||
270 | +#define ARM_SMMUV3_CLASS(klass) \ | ||
271 | + OBJECT_CLASS_CHECK(SMMUv3Class, (klass), TYPE_ARM_SMMUV3) | ||
272 | +#define ARM_SMMUV3_GET_CLASS(obj) \ | ||
273 | + OBJECT_GET_CLASS(SMMUv3Class, (obj), TYPE_ARM_SMMUV3) | ||
274 | + | ||
275 | +#endif | ||
276 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
277 | new file mode 100644 | ||
278 | index XXXXXXX..XXXXXXX | ||
279 | --- /dev/null | ||
280 | +++ b/hw/arm/smmuv3.c | ||
281 | @@ -XXX,XX +XXX,XX @@ | ||
282 | +/* | ||
283 | + * Copyright (C) 2014-2016 Broadcom Corporation | ||
284 | + * Copyright (c) 2017 Red Hat, Inc. | ||
285 | + * Written by Prem Mallappa, Eric Auger | ||
286 | + * | ||
287 | + * This program is free software; you can redistribute it and/or modify | ||
288 | + * it under the terms of the GNU General Public License version 2 as | ||
289 | + * published by the Free Software Foundation. | ||
290 | + * | ||
291 | + * This program is distributed in the hope that it will be useful, | ||
292 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
293 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
294 | + * GNU General Public License for more details. | ||
295 | + * | ||
296 | + * You should have received a copy of the GNU General Public License along | ||
297 | + * with this program; if not, see <http://www.gnu.org/licenses/>. | ||
298 | + */ | ||
299 | + | ||
300 | +#include "qemu/osdep.h" | ||
301 | +#include "hw/boards.h" | ||
302 | +#include "sysemu/sysemu.h" | ||
303 | +#include "hw/sysbus.h" | ||
304 | +#include "hw/qdev-core.h" | ||
305 | +#include "hw/pci/pci.h" | ||
306 | +#include "exec/address-spaces.h" | ||
307 | +#include "trace.h" | ||
308 | +#include "qemu/log.h" | ||
309 | +#include "qemu/error-report.h" | ||
310 | +#include "qapi/error.h" | ||
311 | + | ||
312 | +#include "hw/arm/smmuv3.h" | ||
313 | +#include "smmuv3-internal.h" | ||
314 | + | ||
315 | +static void smmuv3_init_regs(SMMUv3State *s) | ||
316 | +{ | ||
317 | + /** | ||
318 | + * IDR0: stage1 only, AArch64 only, coherent access, 16b ASID, | ||
319 | + * multi-level stream table | ||
320 | + */ | ||
321 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, S1P, 1); /* stage 1 supported */ | ||
322 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, TTF, 2); /* AArch64 PTW only */ | ||
323 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, COHACC, 1); /* IO coherent */ | ||
324 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, ASID16, 1); /* 16-bit ASID */ | ||
325 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, TTENDIAN, 2); /* little endian */ | ||
326 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, STALL_MODEL, 1); /* No stall */ | ||
327 | + /* terminated transaction will always be aborted/error returned */ | ||
328 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, TERM_MODEL, 1); | ||
329 | + /* 2-level stream table supported */ | ||
330 | + s->idr[0] = FIELD_DP32(s->idr[0], IDR0, STLEVEL, 1); | ||
331 | + | ||
332 | + s->idr[1] = FIELD_DP32(s->idr[1], IDR1, SIDSIZE, SMMU_IDR1_SIDSIZE); | ||
333 | + s->idr[1] = FIELD_DP32(s->idr[1], IDR1, EVENTQS, SMMU_EVENTQS); | ||
334 | + s->idr[1] = FIELD_DP32(s->idr[1], IDR1, CMDQS, SMMU_CMDQS); | ||
335 | + | ||
336 | + /* 4K and 64K granule support */ | ||
337 | + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN4K, 1); | ||
338 | + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, GRAN64K, 1); | ||
339 | + s->idr[5] = FIELD_DP32(s->idr[5], IDR5, OAS, SMMU_IDR5_OAS); /* 44 bits */ | ||
340 | + | ||
341 | + s->cmdq.base = deposit64(s->cmdq.base, 0, 5, SMMU_CMDQS); | ||
342 | + s->cmdq.prod = 0; | ||
343 | + s->cmdq.cons = 0; | ||
344 | + s->cmdq.entry_size = sizeof(struct Cmd); | ||
345 | + s->eventq.base = deposit64(s->eventq.base, 0, 5, SMMU_EVENTQS); | ||
346 | + s->eventq.prod = 0; | ||
347 | + s->eventq.cons = 0; | ||
348 | + s->eventq.entry_size = sizeof(struct Evt); | ||
349 | + | ||
350 | + s->features = 0; | ||
351 | + s->sid_split = 0; | ||
352 | +} | 81 | +} |
353 | + | 82 | + |
354 | +static MemTxResult smmu_write_mmio(void *opaque, hwaddr offset, uint64_t data, | ||
355 | + unsigned size, MemTxAttrs attrs) | ||
356 | +{ | 83 | +{ |
357 | + /* not yet implemented */ | 84 | + VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b |
358 | + return MEMTX_ERROR; | 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 | ||
359 | +} | 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 | ||
360 | + | 96 | + |
361 | +static MemTxResult smmu_readll(SMMUv3State *s, hwaddr offset, | 97 | +# VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file |
362 | + uint64_t *data, MemTxAttrs attrs) | 98 | +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b |
363 | +{ | 99 | +VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h |
364 | + switch (offset) { | ||
365 | + case A_GERROR_IRQ_CFG0: | ||
366 | + *data = s->gerror_irq_cfg0; | ||
367 | + return MEMTX_OK; | ||
368 | + case A_STRTAB_BASE: | ||
369 | + *data = s->strtab_base; | ||
370 | + return MEMTX_OK; | ||
371 | + case A_CMDQ_BASE: | ||
372 | + *data = s->cmdq.base; | ||
373 | + return MEMTX_OK; | ||
374 | + case A_EVENTQ_BASE: | ||
375 | + *data = s->eventq.base; | ||
376 | + return MEMTX_OK; | ||
377 | + default: | ||
378 | + *data = 0; | ||
379 | + qemu_log_mask(LOG_UNIMP, | ||
380 | + "%s Unexpected 64-bit access to 0x%"PRIx64" (RAZ)\n", | ||
381 | + __func__, offset); | ||
382 | + return MEMTX_OK; | ||
383 | + } | ||
384 | +} | ||
385 | + | 100 | + |
386 | +static MemTxResult smmu_readl(SMMUv3State *s, hwaddr offset, | 101 | +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b |
387 | + uint64_t *data, MemTxAttrs attrs) | 102 | +VSHLL_BU 111 1 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h |
388 | +{ | ||
389 | + switch (offset) { | ||
390 | + case A_IDREGS ... A_IDREGS + 0x1f: | ||
391 | + *data = smmuv3_idreg(offset - A_IDREGS); | ||
392 | + return MEMTX_OK; | ||
393 | + case A_IDR0 ... A_IDR5: | ||
394 | + *data = s->idr[(offset - A_IDR0) / 4]; | ||
395 | + return MEMTX_OK; | ||
396 | + case A_IIDR: | ||
397 | + *data = s->iidr; | ||
398 | + return MEMTX_OK; | ||
399 | + case A_CR0: | ||
400 | + *data = s->cr[0]; | ||
401 | + return MEMTX_OK; | ||
402 | + case A_CR0ACK: | ||
403 | + *data = s->cr0ack; | ||
404 | + return MEMTX_OK; | ||
405 | + case A_CR1: | ||
406 | + *data = s->cr[1]; | ||
407 | + return MEMTX_OK; | ||
408 | + case A_CR2: | ||
409 | + *data = s->cr[2]; | ||
410 | + return MEMTX_OK; | ||
411 | + case A_STATUSR: | ||
412 | + *data = s->statusr; | ||
413 | + return MEMTX_OK; | ||
414 | + case A_IRQ_CTRL: | ||
415 | + case A_IRQ_CTRL_ACK: | ||
416 | + *data = s->irq_ctrl; | ||
417 | + return MEMTX_OK; | ||
418 | + case A_GERROR: | ||
419 | + *data = s->gerror; | ||
420 | + return MEMTX_OK; | ||
421 | + case A_GERRORN: | ||
422 | + *data = s->gerrorn; | ||
423 | + return MEMTX_OK; | ||
424 | + case A_GERROR_IRQ_CFG0: /* 64b */ | ||
425 | + *data = extract64(s->gerror_irq_cfg0, 0, 32); | ||
426 | + return MEMTX_OK; | ||
427 | + case A_GERROR_IRQ_CFG0 + 4: | ||
428 | + *data = extract64(s->gerror_irq_cfg0, 32, 32); | ||
429 | + return MEMTX_OK; | ||
430 | + case A_GERROR_IRQ_CFG1: | ||
431 | + *data = s->gerror_irq_cfg1; | ||
432 | + return MEMTX_OK; | ||
433 | + case A_GERROR_IRQ_CFG2: | ||
434 | + *data = s->gerror_irq_cfg2; | ||
435 | + return MEMTX_OK; | ||
436 | + case A_STRTAB_BASE: /* 64b */ | ||
437 | + *data = extract64(s->strtab_base, 0, 32); | ||
438 | + return MEMTX_OK; | ||
439 | + case A_STRTAB_BASE + 4: /* 64b */ | ||
440 | + *data = extract64(s->strtab_base, 32, 32); | ||
441 | + return MEMTX_OK; | ||
442 | + case A_STRTAB_BASE_CFG: | ||
443 | + *data = s->strtab_base_cfg; | ||
444 | + return MEMTX_OK; | ||
445 | + case A_CMDQ_BASE: /* 64b */ | ||
446 | + *data = extract64(s->cmdq.base, 0, 32); | ||
447 | + return MEMTX_OK; | ||
448 | + case A_CMDQ_BASE + 4: | ||
449 | + *data = extract64(s->cmdq.base, 32, 32); | ||
450 | + return MEMTX_OK; | ||
451 | + case A_CMDQ_PROD: | ||
452 | + *data = s->cmdq.prod; | ||
453 | + return MEMTX_OK; | ||
454 | + case A_CMDQ_CONS: | ||
455 | + *data = s->cmdq.cons; | ||
456 | + return MEMTX_OK; | ||
457 | + case A_EVENTQ_BASE: /* 64b */ | ||
458 | + *data = extract64(s->eventq.base, 0, 32); | ||
459 | + return MEMTX_OK; | ||
460 | + case A_EVENTQ_BASE + 4: /* 64b */ | ||
461 | + *data = extract64(s->eventq.base, 32, 32); | ||
462 | + return MEMTX_OK; | ||
463 | + case A_EVENTQ_PROD: | ||
464 | + *data = s->eventq.prod; | ||
465 | + return MEMTX_OK; | ||
466 | + case A_EVENTQ_CONS: | ||
467 | + *data = s->eventq.cons; | ||
468 | + return MEMTX_OK; | ||
469 | + default: | ||
470 | + *data = 0; | ||
471 | + qemu_log_mask(LOG_UNIMP, | ||
472 | + "%s unhandled 32-bit access at 0x%"PRIx64" (RAZ)\n", | ||
473 | + __func__, offset); | ||
474 | + return MEMTX_OK; | ||
475 | + } | ||
476 | +} | ||
477 | + | 103 | + |
478 | +static MemTxResult smmu_read_mmio(void *opaque, hwaddr offset, uint64_t *data, | 104 | +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b |
479 | + unsigned size, MemTxAttrs attrs) | 105 | +VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h |
480 | +{ | ||
481 | + SMMUState *sys = opaque; | ||
482 | + SMMUv3State *s = ARM_SMMUV3(sys); | ||
483 | + MemTxResult r; | ||
484 | + | 106 | + |
485 | + /* CONSTRAINED UNPREDICTABLE choice to have page0/1 be exact aliases */ | 107 | +VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b |
486 | + offset &= ~0x10000; | 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) | ||
487 | + | 117 | + |
488 | + switch (size) { | 118 | +/* |
489 | + case 8: | 119 | + * Long shifts taking half-sized inputs from top or bottom of the input |
490 | + r = smmu_readll(s, offset, data, attrs); | 120 | + * vector and producing a double-width result. ESIZE, TYPE are for |
491 | + break; | 121 | + * the input, and LESIZE, LTYPE for the output. |
492 | + case 4: | 122 | + * Unlike the normal shift helpers, we do not handle negative shift counts, |
493 | + r = smmu_readl(s, offset, data, attrs); | 123 | + * because the long shift is strictly left-only. |
494 | + break; | 124 | + */ |
495 | + default: | 125 | +#define DO_VSHLL(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ |
496 | + r = MEMTX_ERROR; | 126 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ |
497 | + break; | 127 | + void *vm, uint32_t shift) \ |
128 | + { \ | ||
129 | + LTYPE *d = vd; \ | ||
130 | + TYPE *m = vm; \ | ||
131 | + uint16_t mask = mve_element_mask(env); \ | ||
132 | + unsigned le; \ | ||
133 | + assert(shift <= 16); \ | ||
134 | + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ | ||
135 | + LTYPE r = (LTYPE)m[H##ESIZE(le * 2 + TOP)] << shift; \ | ||
136 | + mergemask(&d[H##LESIZE(le)], r, mask); \ | ||
137 | + } \ | ||
138 | + mve_advance_vpt(env); \ | ||
498 | + } | 139 | + } |
499 | + | 140 | + |
500 | + trace_smmuv3_read_mmio(offset, *data, size, r); | 141 | +#define DO_VSHLL_ALL(OP, TOP) \ |
501 | + return r; | 142 | + DO_VSHLL(OP##sb, TOP, 1, int8_t, 2, int16_t) \ |
502 | +} | 143 | + DO_VSHLL(OP##ub, TOP, 1, uint8_t, 2, uint16_t) \ |
144 | + DO_VSHLL(OP##sh, TOP, 2, int16_t, 4, int32_t) \ | ||
145 | + DO_VSHLL(OP##uh, TOP, 2, uint16_t, 4, uint32_t) \ | ||
503 | + | 146 | + |
504 | +static const MemoryRegionOps smmu_mem_ops = { | 147 | +DO_VSHLL_ALL(vshllb, false) |
505 | + .read_with_attrs = smmu_read_mmio, | 148 | +DO_VSHLL_ALL(vshllt, true) |
506 | + .write_with_attrs = smmu_write_mmio, | 149 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c |
507 | + .endianness = DEVICE_LITTLE_ENDIAN, | 150 | index XXXXXXX..XXXXXXX 100644 |
508 | + .valid = { | 151 | --- a/target/arm/translate-mve.c |
509 | + .min_access_size = 4, | 152 | +++ b/target/arm/translate-mve.c |
510 | + .max_access_size = 8, | 153 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VSHRI_S, vshli_s, true) |
511 | + }, | 154 | DO_2SHIFT(VSHRI_U, vshli_u, true) |
512 | + .impl = { | 155 | DO_2SHIFT(VRSHRI_S, vrshli_s, true) |
513 | + .min_access_size = 4, | 156 | DO_2SHIFT(VRSHRI_U, vrshli_u, true) |
514 | + .max_access_size = 8, | ||
515 | + }, | ||
516 | +}; | ||
517 | + | 157 | + |
518 | +static void smmu_init_irq(SMMUv3State *s, SysBusDevice *dev) | 158 | +#define DO_VSHLL(INSN, FN) \ |
519 | +{ | 159 | + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
520 | + int i; | 160 | + { \ |
521 | + | 161 | + static MVEGenTwoOpShiftFn * const fns[] = { \ |
522 | + for (i = 0; i < ARRAY_SIZE(s->irq); i++) { | 162 | + gen_helper_mve_##FN##b, \ |
523 | + sysbus_init_irq(dev, &s->irq[i]); | 163 | + gen_helper_mve_##FN##h, \ |
524 | + } | 164 | + }; \ |
525 | +} | 165 | + return do_2shift(s, a, fns[a->size], false); \ |
526 | + | ||
527 | +static void smmu_reset(DeviceState *dev) | ||
528 | +{ | ||
529 | + SMMUv3State *s = ARM_SMMUV3(dev); | ||
530 | + SMMUv3Class *c = ARM_SMMUV3_GET_CLASS(s); | ||
531 | + | ||
532 | + c->parent_reset(dev); | ||
533 | + | ||
534 | + smmuv3_init_regs(s); | ||
535 | +} | ||
536 | + | ||
537 | +static void smmu_realize(DeviceState *d, Error **errp) | ||
538 | +{ | ||
539 | + SMMUState *sys = ARM_SMMU(d); | ||
540 | + SMMUv3State *s = ARM_SMMUV3(sys); | ||
541 | + SMMUv3Class *c = ARM_SMMUV3_GET_CLASS(s); | ||
542 | + SysBusDevice *dev = SYS_BUS_DEVICE(d); | ||
543 | + Error *local_err = NULL; | ||
544 | + | ||
545 | + c->parent_realize(d, &local_err); | ||
546 | + if (local_err) { | ||
547 | + error_propagate(errp, local_err); | ||
548 | + return; | ||
549 | + } | 166 | + } |
550 | + | 167 | + |
551 | + memory_region_init_io(&sys->iomem, OBJECT(s), | 168 | +DO_VSHLL(VSHLL_BS, vshllbs) |
552 | + &smmu_mem_ops, sys, TYPE_ARM_SMMUV3, 0x20000); | 169 | +DO_VSHLL(VSHLL_BU, vshllbu) |
553 | + | 170 | +DO_VSHLL(VSHLL_TS, vshllts) |
554 | + sys->mrtypename = TYPE_SMMUV3_IOMMU_MEMORY_REGION; | 171 | +DO_VSHLL(VSHLL_TU, vshlltu) |
555 | + | ||
556 | + sysbus_init_mmio(dev, &sys->iomem); | ||
557 | + | ||
558 | + smmu_init_irq(s, dev); | ||
559 | +} | ||
560 | + | ||
561 | +static const VMStateDescription vmstate_smmuv3_queue = { | ||
562 | + .name = "smmuv3_queue", | ||
563 | + .version_id = 1, | ||
564 | + .minimum_version_id = 1, | ||
565 | + .fields = (VMStateField[]) { | ||
566 | + VMSTATE_UINT64(base, SMMUQueue), | ||
567 | + VMSTATE_UINT32(prod, SMMUQueue), | ||
568 | + VMSTATE_UINT32(cons, SMMUQueue), | ||
569 | + VMSTATE_UINT8(log2size, SMMUQueue), | ||
570 | + }, | ||
571 | +}; | ||
572 | + | ||
573 | +static const VMStateDescription vmstate_smmuv3 = { | ||
574 | + .name = "smmuv3", | ||
575 | + .version_id = 1, | ||
576 | + .minimum_version_id = 1, | ||
577 | + .fields = (VMStateField[]) { | ||
578 | + VMSTATE_UINT32(features, SMMUv3State), | ||
579 | + VMSTATE_UINT8(sid_size, SMMUv3State), | ||
580 | + VMSTATE_UINT8(sid_split, SMMUv3State), | ||
581 | + | ||
582 | + VMSTATE_UINT32_ARRAY(cr, SMMUv3State, 3), | ||
583 | + VMSTATE_UINT32(cr0ack, SMMUv3State), | ||
584 | + VMSTATE_UINT32(statusr, SMMUv3State), | ||
585 | + VMSTATE_UINT32(irq_ctrl, SMMUv3State), | ||
586 | + VMSTATE_UINT32(gerror, SMMUv3State), | ||
587 | + VMSTATE_UINT32(gerrorn, SMMUv3State), | ||
588 | + VMSTATE_UINT64(gerror_irq_cfg0, SMMUv3State), | ||
589 | + VMSTATE_UINT32(gerror_irq_cfg1, SMMUv3State), | ||
590 | + VMSTATE_UINT32(gerror_irq_cfg2, SMMUv3State), | ||
591 | + VMSTATE_UINT64(strtab_base, SMMUv3State), | ||
592 | + VMSTATE_UINT32(strtab_base_cfg, SMMUv3State), | ||
593 | + VMSTATE_UINT64(eventq_irq_cfg0, SMMUv3State), | ||
594 | + VMSTATE_UINT32(eventq_irq_cfg1, SMMUv3State), | ||
595 | + VMSTATE_UINT32(eventq_irq_cfg2, SMMUv3State), | ||
596 | + | ||
597 | + VMSTATE_STRUCT(cmdq, SMMUv3State, 0, vmstate_smmuv3_queue, SMMUQueue), | ||
598 | + VMSTATE_STRUCT(eventq, SMMUv3State, 0, vmstate_smmuv3_queue, SMMUQueue), | ||
599 | + | ||
600 | + VMSTATE_END_OF_LIST(), | ||
601 | + }, | ||
602 | +}; | ||
603 | + | ||
604 | +static void smmuv3_instance_init(Object *obj) | ||
605 | +{ | ||
606 | + /* Nothing much to do here as of now */ | ||
607 | +} | ||
608 | + | ||
609 | +static void smmuv3_class_init(ObjectClass *klass, void *data) | ||
610 | +{ | ||
611 | + DeviceClass *dc = DEVICE_CLASS(klass); | ||
612 | + SMMUv3Class *c = ARM_SMMUV3_CLASS(klass); | ||
613 | + | ||
614 | + dc->vmsd = &vmstate_smmuv3; | ||
615 | + device_class_set_parent_reset(dc, smmu_reset, &c->parent_reset); | ||
616 | + c->parent_realize = dc->realize; | ||
617 | + dc->realize = smmu_realize; | ||
618 | +} | ||
619 | + | ||
620 | +static void smmuv3_iommu_memory_region_class_init(ObjectClass *klass, | ||
621 | + void *data) | ||
622 | +{ | ||
623 | +} | ||
624 | + | ||
625 | +static const TypeInfo smmuv3_type_info = { | ||
626 | + .name = TYPE_ARM_SMMUV3, | ||
627 | + .parent = TYPE_ARM_SMMU, | ||
628 | + .instance_size = sizeof(SMMUv3State), | ||
629 | + .instance_init = smmuv3_instance_init, | ||
630 | + .class_size = sizeof(SMMUv3Class), | ||
631 | + .class_init = smmuv3_class_init, | ||
632 | +}; | ||
633 | + | ||
634 | +static const TypeInfo smmuv3_iommu_memory_region_info = { | ||
635 | + .parent = TYPE_IOMMU_MEMORY_REGION, | ||
636 | + .name = TYPE_SMMUV3_IOMMU_MEMORY_REGION, | ||
637 | + .class_init = smmuv3_iommu_memory_region_class_init, | ||
638 | +}; | ||
639 | + | ||
640 | +static void smmuv3_register_types(void) | ||
641 | +{ | ||
642 | + type_register(&smmuv3_type_info); | ||
643 | + type_register(&smmuv3_iommu_memory_region_info); | ||
644 | +} | ||
645 | + | ||
646 | +type_init(smmuv3_register_types) | ||
647 | + | ||
648 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
649 | index XXXXXXX..XXXXXXX 100644 | ||
650 | --- a/hw/arm/trace-events | ||
651 | +++ b/hw/arm/trace-events | ||
652 | @@ -XXX,XX +XXX,XX @@ smmu_ptw_invalid_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, | ||
653 | smmu_ptw_page_pte(int stage, int level, uint64_t iova, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t address) "stage=%d level=%d iova=0x%"PRIx64" base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" page address = 0x%"PRIx64 | ||
654 | smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t iova, uint64_t gpa, int bsize_mb) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" iova=0x%"PRIx64" block address = 0x%"PRIx64" block size = %d MiB" | ||
655 | smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "baseaddr=0x%"PRIx64" index=0x%x, pteaddr=0x%"PRIx64", pte=0x%"PRIx64 | ||
656 | + | ||
657 | +#hw/arm/smmuv3.c | ||
658 | +smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" | ||
659 | -- | 172 | -- |
660 | 2.17.0 | 173 | 2.20.1 |
661 | 174 | ||
662 | 175 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE VSRI and VSLI insns, which perform a |
---|---|---|---|
2 | shift-and-insert operation. | ||
2 | 3 | ||
3 | In case the MSI is translated by an IOMMU we need to fixup the | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | MSI route with the translated address. | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20210628135835.6690-11-peter.maydell@linaro.org | ||
7 | --- | ||
8 | target/arm/helper-mve.h | 8 ++++++++ | ||
9 | target/arm/mve.decode | 9 ++++++++ | ||
10 | target/arm/mve_helper.c | 42 ++++++++++++++++++++++++++++++++++++++ | ||
11 | target/arm/translate-mve.c | 3 +++ | ||
12 | 4 files changed, 62 insertions(+) | ||
5 | 13 | ||
6 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 14 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
7 | Signed-off-by: Bharat Bhushan <Bharat.Bhushan@nxp.com> | ||
8 | Message-id: 1524665762-31355-12-git-send-email-eric.auger@redhat.com | ||
9 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | target/arm/kvm.c | 38 +++++++++++++++++++++++++++++++++++++- | ||
13 | target/arm/trace-events | 3 +++ | ||
14 | 2 files changed, 40 insertions(+), 1 deletion(-) | ||
15 | |||
16 | diff --git a/target/arm/kvm.c b/target/arm/kvm.c | ||
17 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/target/arm/kvm.c | 16 | --- a/target/arm/helper-mve.h |
19 | +++ b/target/arm/kvm.c | 17 | +++ b/target/arm/helper-mve.h |
20 | @@ -XXX,XX +XXX,XX @@ | 18 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vshlltsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
21 | #include "sysemu/kvm.h" | 19 | DEF_HELPER_FLAGS_4(mve_vshlltsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
22 | #include "kvm_arm.h" | 20 | DEF_HELPER_FLAGS_4(mve_vshlltub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
23 | #include "cpu.h" | 21 | DEF_HELPER_FLAGS_4(mve_vshlltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
24 | +#include "trace.h" | ||
25 | #include "internals.h" | ||
26 | #include "hw/arm/arm.h" | ||
27 | +#include "hw/pci/pci.h" | ||
28 | #include "exec/memattrs.h" | ||
29 | #include "exec/address-spaces.h" | ||
30 | #include "hw/boards.h" | ||
31 | @@ -XXX,XX +XXX,XX @@ int kvm_arm_vgic_probe(void) | ||
32 | int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, | ||
33 | uint64_t address, uint32_t data, PCIDevice *dev) | ||
34 | { | ||
35 | - return 0; | ||
36 | + AddressSpace *as = pci_device_iommu_address_space(dev); | ||
37 | + hwaddr xlat, len, doorbell_gpa; | ||
38 | + MemoryRegionSection mrs; | ||
39 | + MemoryRegion *mr; | ||
40 | + int ret = 1; | ||
41 | + | 22 | + |
42 | + if (as == &address_space_memory) { | 23 | +DEF_HELPER_FLAGS_4(mve_vsrib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
43 | + return 0; | 24 | +DEF_HELPER_FLAGS_4(mve_vsrih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
25 | +DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
26 | + | ||
27 | +DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
28 | +DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
29 | +DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
30 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode | ||
31 | index XXXXXXX..XXXXXXX 100644 | ||
32 | --- a/target/arm/mve.decode | ||
33 | +++ b/target/arm/mve.decode | ||
34 | @@ -XXX,XX +XXX,XX @@ VSHLL_TS 111 0 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h | ||
35 | |||
36 | VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_b | ||
37 | VSHLL_TU 111 1 1110 1 . 1 .. ... ... 1 1111 0 1 . 0 ... 0 @2_shll_h | ||
38 | + | ||
39 | +# Shift-and-insert | ||
40 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_b | ||
41 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_h | ||
42 | +VSRI 111 1 1111 1 . ... ... ... 0 0100 0 1 . 1 ... 0 @2_shr_w | ||
43 | + | ||
44 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_b | ||
45 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_h | ||
46 | +VSLI 111 1 1111 1 . ... ... ... 0 0101 0 1 . 1 ... 0 @2_shl_w | ||
47 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/target/arm/mve_helper.c | ||
50 | +++ b/target/arm/mve_helper.c | ||
51 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) | ||
52 | DO_2SHIFT_U(vrshli_u, DO_VRSHLU) | ||
53 | DO_2SHIFT_S(vrshli_s, DO_VRSHLS) | ||
54 | |||
55 | +/* Shift-and-insert; we always work with 64 bits at a time */ | ||
56 | +#define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ | ||
57 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
58 | + void *vm, uint32_t shift) \ | ||
59 | + { \ | ||
60 | + uint64_t *d = vd, *m = vm; \ | ||
61 | + uint16_t mask; \ | ||
62 | + uint64_t shiftmask; \ | ||
63 | + unsigned e; \ | ||
64 | + if (shift == 0 || shift == ESIZE * 8) { \ | ||
65 | + /* \ | ||
66 | + * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ | ||
67 | + * The generic logic would give the right answer for 0 but \ | ||
68 | + * fails for <dt>. \ | ||
69 | + */ \ | ||
70 | + goto done; \ | ||
71 | + } \ | ||
72 | + assert(shift < ESIZE * 8); \ | ||
73 | + mask = mve_element_mask(env); \ | ||
74 | + /* ESIZE / 2 gives the MO_* value if ESIZE is in [1,2,4] */ \ | ||
75 | + shiftmask = dup_const(ESIZE / 2, MASKFN(ESIZE * 8, shift)); \ | ||
76 | + for (e = 0; e < 16 / 8; e++, mask >>= 8) { \ | ||
77 | + uint64_t r = (SHIFTFN(m[H8(e)], shift) & shiftmask) | \ | ||
78 | + (d[H8(e)] & ~shiftmask); \ | ||
79 | + mergemask(&d[H8(e)], r, mask); \ | ||
80 | + } \ | ||
81 | +done: \ | ||
82 | + mve_advance_vpt(env); \ | ||
44 | + } | 83 | + } |
45 | + | 84 | + |
46 | + /* MSI doorbell address is translated by an IOMMU */ | 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)) | ||
47 | + | 89 | + |
48 | + rcu_read_lock(); | 90 | +DO_2SHIFT_INSERT(vsrib, 1, DO_SHR, SHR_MASK) |
49 | + mr = address_space_translate(as, address, &xlat, &len, true); | 91 | +DO_2SHIFT_INSERT(vsrih, 2, DO_SHR, SHR_MASK) |
50 | + if (!mr) { | 92 | +DO_2SHIFT_INSERT(vsriw, 4, DO_SHR, SHR_MASK) |
51 | + goto unlock; | 93 | +DO_2SHIFT_INSERT(vslib, 1, DO_SHL, SHL_MASK) |
52 | + } | 94 | +DO_2SHIFT_INSERT(vslih, 2, DO_SHL, SHL_MASK) |
53 | + mrs = memory_region_find(mr, xlat, 1); | 95 | +DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) |
54 | + if (!mrs.mr) { | ||
55 | + goto unlock; | ||
56 | + } | ||
57 | + | 96 | + |
58 | + doorbell_gpa = mrs.offset_within_address_space; | 97 | /* |
59 | + memory_region_unref(mrs.mr); | 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) | ||
60 | + | 110 | + |
61 | + route->u.msi.address_lo = doorbell_gpa; | 111 | #define DO_VSHLL(INSN, FN) \ |
62 | + route->u.msi.address_hi = doorbell_gpa >> 32; | 112 | static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
63 | + | 113 | { \ |
64 | + trace_kvm_arm_fixup_msi_route(address, doorbell_gpa); | ||
65 | + | ||
66 | + ret = 0; | ||
67 | + | ||
68 | +unlock: | ||
69 | + rcu_read_unlock(); | ||
70 | + return ret; | ||
71 | } | ||
72 | |||
73 | int kvm_arch_add_msi_route_post(struct kvm_irq_routing_entry *route, | ||
74 | diff --git a/target/arm/trace-events b/target/arm/trace-events | ||
75 | index XXXXXXX..XXXXXXX 100644 | ||
76 | --- a/target/arm/trace-events | ||
77 | +++ b/target/arm/trace-events | ||
78 | @@ -XXX,XX +XXX,XX @@ arm_gt_tval_write(int timer, uint64_t value) "gt_tval_write: timer %d value 0x%" | ||
79 | arm_gt_ctl_write(int timer, uint64_t value) "gt_ctl_write: timer %d value 0x%" PRIx64 | ||
80 | arm_gt_imask_toggle(int timer, int irqstate) "gt_ctl_write: timer %d IMASK toggle, new irqstate %d" | ||
81 | arm_gt_cntvoff_write(uint64_t value) "gt_cntvoff_write: value 0x%" PRIx64 | ||
82 | + | ||
83 | +# target/arm/kvm.c | ||
84 | +kvm_arm_fixup_msi_route(uint64_t iova, uint64_t gpa) "MSI iova = 0x%"PRIx64" is translated into 0x%"PRIx64 | ||
85 | -- | 114 | -- |
86 | 2.17.0 | 115 | 2.20.1 |
87 | 116 | ||
88 | 117 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE shift-right-and-narrow insn VSHRN and VRSHRN. |
---|---|---|---|
2 | 2 | ||
3 | This patch implements the IOMMU Memory Region translate() | 3 | do_urshr() is borrowed from sve_helper.c. |
4 | callback. Most of the code relates to the translation | ||
5 | configuration decoding and check (STE, CD). | ||
6 | 4 | ||
7 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
8 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
9 | Message-id: 1524665762-31355-10-git-send-email-eric.auger@redhat.com | ||
10 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Message-id: 20210628135835.6690-12-peter.maydell@linaro.org | ||
12 | --- | 8 | --- |
13 | hw/arm/smmuv3-internal.h | 160 +++++++++++++++++ | 9 | target/arm/helper-mve.h | 10 ++++++++++ |
14 | hw/arm/smmuv3.c | 358 +++++++++++++++++++++++++++++++++++++++ | 10 | target/arm/mve.decode | 11 +++++++++++ |
15 | hw/arm/trace-events | 9 + | 11 | target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++ |
16 | 3 files changed, 527 insertions(+) | 12 | target/arm/translate-mve.c | 15 ++++++++++++++ |
13 | 4 files changed, 76 insertions(+) | ||
17 | 14 | ||
18 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
19 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/hw/arm/smmuv3-internal.h | 17 | --- a/target/arm/helper-mve.h |
21 | +++ b/hw/arm/smmuv3-internal.h | 18 | +++ b/target/arm/helper-mve.h |
22 | @@ -XXX,XX +XXX,XX @@ typedef struct SMMUEventInfo { | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vsriw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
23 | 20 | DEF_HELPER_FLAGS_4(mve_vslib, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
24 | void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *event); | 21 | DEF_HELPER_FLAGS_4(mve_vslih, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
25 | 22 | DEF_HELPER_FLAGS_4(mve_vsliw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
26 | +/* Configuration Data */ | ||
27 | + | 23 | + |
28 | +/* STE Level 1 Descriptor */ | 24 | +DEF_HELPER_FLAGS_4(mve_vshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
29 | +typedef struct STEDesc { | 25 | +DEF_HELPER_FLAGS_4(mve_vshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
30 | + uint32_t word[2]; | 26 | +DEF_HELPER_FLAGS_4(mve_vshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
31 | +} STEDesc; | 27 | +DEF_HELPER_FLAGS_4(mve_vshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
32 | + | 28 | + |
33 | +/* CD Level 1 Descriptor */ | 29 | +DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
34 | +typedef struct CDDesc { | 30 | +DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
35 | + uint32_t word[2]; | 31 | +DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
36 | +} CDDesc; | 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 | ||
37 | + | 41 | + |
38 | +/* Stream Table Entry(STE) */ | 42 | +# Narrowing shifts (which only support b and h sizes) |
39 | +typedef struct STE { | 43 | +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b |
40 | + uint32_t word[16]; | 44 | +VSHRNB 111 0 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h |
41 | +} STE; | 45 | +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b |
46 | +VSHRNT 111 0 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h | ||
42 | + | 47 | + |
43 | +/* Context Descriptor(CD) */ | 48 | +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b |
44 | +typedef struct CD { | 49 | +VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h |
45 | + uint32_t word[16]; | 50 | +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b |
46 | +} CD; | 51 | +VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_h |
52 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
53 | index XXXXXXX..XXXXXXX 100644 | ||
54 | --- a/target/arm/mve_helper.c | ||
55 | +++ b/target/arm/mve_helper.c | ||
56 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_INSERT(vsliw, 4, DO_SHL, SHL_MASK) | ||
57 | |||
58 | DO_VSHLL_ALL(vshllb, false) | ||
59 | DO_VSHLL_ALL(vshllt, true) | ||
47 | + | 60 | + |
48 | +/* STE fields */ | 61 | +/* |
49 | + | 62 | + * Narrowing right shifts, taking a double sized input, shifting it |
50 | +#define STE_VALID(x) extract32((x)->word[0], 0, 1) | 63 | + * and putting the result in either the top or bottom half of the output. |
51 | + | 64 | + * ESIZE, TYPE are the output, and LESIZE, LTYPE the input. |
52 | +#define STE_CONFIG(x) extract32((x)->word[0], 1, 3) | 65 | + */ |
53 | +#define STE_CFG_S1_ENABLED(config) (config & 0x1) | 66 | +#define DO_VSHRN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ |
54 | +#define STE_CFG_S2_ENABLED(config) (config & 0x2) | 67 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ |
55 | +#define STE_CFG_ABORT(config) (!(config & 0x4)) | 68 | + void *vm, uint32_t shift) \ |
56 | +#define STE_CFG_BYPASS(config) (config == 0x4) | 69 | + { \ |
57 | + | 70 | + LTYPE *m = vm; \ |
58 | +#define STE_S1FMT(x) extract32((x)->word[0], 4 , 2) | 71 | + TYPE *d = vd; \ |
59 | +#define STE_S1CDMAX(x) extract32((x)->word[1], 27, 5) | 72 | + uint16_t mask = mve_element_mask(env); \ |
60 | +#define STE_S1STALLD(x) extract32((x)->word[2], 27, 1) | 73 | + unsigned le; \ |
61 | +#define STE_EATS(x) extract32((x)->word[2], 28, 2) | 74 | + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ |
62 | +#define STE_STRW(x) extract32((x)->word[2], 30, 2) | 75 | + TYPE r = FN(m[H##LESIZE(le)], shift); \ |
63 | +#define STE_S2VMID(x) extract32((x)->word[4], 0 , 16) | 76 | + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ |
64 | +#define STE_S2T0SZ(x) extract32((x)->word[5], 0 , 6) | 77 | + } \ |
65 | +#define STE_S2SL0(x) extract32((x)->word[5], 6 , 2) | 78 | + mve_advance_vpt(env); \ |
66 | +#define STE_S2TG(x) extract32((x)->word[5], 14, 2) | ||
67 | +#define STE_S2PS(x) extract32((x)->word[5], 16, 3) | ||
68 | +#define STE_S2AA64(x) extract32((x)->word[5], 19, 1) | ||
69 | +#define STE_S2HD(x) extract32((x)->word[5], 24, 1) | ||
70 | +#define STE_S2HA(x) extract32((x)->word[5], 25, 1) | ||
71 | +#define STE_S2S(x) extract32((x)->word[5], 26, 1) | ||
72 | +#define STE_CTXPTR(x) \ | ||
73 | + ({ \ | ||
74 | + unsigned long addr; \ | ||
75 | + addr = (uint64_t)extract32((x)->word[1], 0, 16) << 32; \ | ||
76 | + addr |= (uint64_t)((x)->word[0] & 0xffffffc0); \ | ||
77 | + addr; \ | ||
78 | + }) | ||
79 | + | ||
80 | +#define STE_S2TTB(x) \ | ||
81 | + ({ \ | ||
82 | + unsigned long addr; \ | ||
83 | + addr = (uint64_t)extract32((x)->word[7], 0, 16) << 32; \ | ||
84 | + addr |= (uint64_t)((x)->word[6] & 0xfffffff0); \ | ||
85 | + addr; \ | ||
86 | + }) | ||
87 | + | ||
88 | +static inline int oas2bits(int oas_field) | ||
89 | +{ | ||
90 | + switch (oas_field) { | ||
91 | + case 0: | ||
92 | + return 32; | ||
93 | + case 1: | ||
94 | + return 36; | ||
95 | + case 2: | ||
96 | + return 40; | ||
97 | + case 3: | ||
98 | + return 42; | ||
99 | + case 4: | ||
100 | + return 44; | ||
101 | + case 5: | ||
102 | + return 48; | ||
103 | + } | ||
104 | + return -1; | ||
105 | +} | ||
106 | + | ||
107 | +static inline int pa_range(STE *ste) | ||
108 | +{ | ||
109 | + int oas_field = MIN(STE_S2PS(ste), SMMU_IDR5_OAS); | ||
110 | + | ||
111 | + if (!STE_S2AA64(ste)) { | ||
112 | + return 40; | ||
113 | + } | 79 | + } |
114 | + | 80 | + |
115 | + return oas2bits(oas_field); | 81 | +#define DO_VSHRN_ALL(OP, FN) \ |
116 | +} | 82 | + DO_VSHRN(OP##bb, false, 1, uint8_t, 2, uint16_t, FN) \ |
83 | + DO_VSHRN(OP##bh, false, 2, uint16_t, 4, uint32_t, FN) \ | ||
84 | + DO_VSHRN(OP##tb, true, 1, uint8_t, 2, uint16_t, FN) \ | ||
85 | + DO_VSHRN(OP##th, true, 2, uint16_t, 4, uint32_t, FN) | ||
117 | + | 86 | + |
118 | +#define MAX_PA(ste) ((1 << pa_range(ste)) - 1) | 87 | +static inline uint64_t do_urshr(uint64_t x, unsigned sh) |
119 | + | ||
120 | +/* CD fields */ | ||
121 | + | ||
122 | +#define CD_VALID(x) extract32((x)->word[0], 30, 1) | ||
123 | +#define CD_ASID(x) extract32((x)->word[1], 16, 16) | ||
124 | +#define CD_TTB(x, sel) \ | ||
125 | + ({ \ | ||
126 | + uint64_t hi, lo; \ | ||
127 | + hi = extract32((x)->word[(sel) * 2 + 3], 0, 19); \ | ||
128 | + hi <<= 32; \ | ||
129 | + lo = (x)->word[(sel) * 2 + 2] & ~0xfULL; \ | ||
130 | + hi | lo; \ | ||
131 | + }) | ||
132 | + | ||
133 | +#define CD_TSZ(x, sel) extract32((x)->word[0], (16 * (sel)) + 0, 6) | ||
134 | +#define CD_TG(x, sel) extract32((x)->word[0], (16 * (sel)) + 6, 2) | ||
135 | +#define CD_EPD(x, sel) extract32((x)->word[0], (16 * (sel)) + 14, 1) | ||
136 | +#define CD_ENDI(x) extract32((x)->word[0], 15, 1) | ||
137 | +#define CD_IPS(x) extract32((x)->word[1], 0 , 3) | ||
138 | +#define CD_TBI(x) extract32((x)->word[1], 6 , 2) | ||
139 | +#define CD_HD(x) extract32((x)->word[1], 10 , 1) | ||
140 | +#define CD_HA(x) extract32((x)->word[1], 11 , 1) | ||
141 | +#define CD_S(x) extract32((x)->word[1], 12, 1) | ||
142 | +#define CD_R(x) extract32((x)->word[1], 13, 1) | ||
143 | +#define CD_A(x) extract32((x)->word[1], 14, 1) | ||
144 | +#define CD_AARCH64(x) extract32((x)->word[1], 9 , 1) | ||
145 | + | ||
146 | +#define CDM_VALID(x) ((x)->word[0] & 0x1) | ||
147 | + | ||
148 | +static inline int is_cd_valid(SMMUv3State *s, STE *ste, CD *cd) | ||
149 | +{ | 88 | +{ |
150 | + return CD_VALID(cd); | 89 | + if (likely(sh < 64)) { |
151 | +} | 90 | + return (x >> sh) + ((x >> (sh - 1)) & 1); |
152 | + | 91 | + } else if (sh == 64) { |
153 | +/** | 92 | + return x >> 63; |
154 | + * tg2granule - Decodes the CD translation granule size field according | 93 | + } else { |
155 | + * to the ttbr in use | ||
156 | + * @bits: TG0/1 fields | ||
157 | + * @ttbr: ttbr index in use | ||
158 | + */ | ||
159 | +static inline int tg2granule(int bits, int ttbr) | ||
160 | +{ | ||
161 | + switch (bits) { | ||
162 | + case 0: | ||
163 | + return ttbr ? 0 : 12; | ||
164 | + case 1: | ||
165 | + return ttbr ? 14 : 16; | ||
166 | + case 2: | ||
167 | + return ttbr ? 12 : 14; | ||
168 | + case 3: | ||
169 | + return ttbr ? 16 : 0; | ||
170 | + default: | ||
171 | + return 0; | 94 | + return 0; |
172 | + } | 95 | + } |
173 | +} | 96 | +} |
174 | + | 97 | + |
175 | +static inline uint64_t l1std_l2ptr(STEDesc *desc) | 98 | +DO_VSHRN_ALL(vshrn, DO_SHR) |
176 | +{ | 99 | +DO_VSHRN_ALL(vrshrn, do_urshr) |
177 | + uint64_t hi, lo; | 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) | ||
178 | + | 108 | + |
179 | + hi = desc->word[1]; | 109 | +#define DO_2SHIFT_N(INSN, FN) \ |
180 | + lo = desc->word[0] & ~0x1fULL; | 110 | + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ |
181 | + return hi << 32 | lo; | 111 | + { \ |
182 | +} | 112 | + static MVEGenTwoOpShiftFn * const fns[] = { \ |
183 | + | 113 | + gen_helper_mve_##FN##b, \ |
184 | +#define L1STD_SPAN(stm) (extract32((stm)->word[0], 0, 4)) | 114 | + gen_helper_mve_##FN##h, \ |
185 | + | 115 | + }; \ |
186 | #endif | 116 | + return do_2shift(s, a, fns[a->size], false); \ |
187 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
188 | index XXXXXXX..XXXXXXX 100644 | ||
189 | --- a/hw/arm/smmuv3.c | ||
190 | +++ b/hw/arm/smmuv3.c | ||
191 | @@ -XXX,XX +XXX,XX @@ static void smmuv3_init_regs(SMMUv3State *s) | ||
192 | s->sid_split = 0; | ||
193 | } | ||
194 | |||
195 | +static int smmu_get_ste(SMMUv3State *s, dma_addr_t addr, STE *buf, | ||
196 | + SMMUEventInfo *event) | ||
197 | +{ | ||
198 | + int ret; | ||
199 | + | ||
200 | + trace_smmuv3_get_ste(addr); | ||
201 | + /* TODO: guarantee 64-bit single-copy atomicity */ | ||
202 | + ret = dma_memory_read(&address_space_memory, addr, | ||
203 | + (void *)buf, sizeof(*buf)); | ||
204 | + if (ret != MEMTX_OK) { | ||
205 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
206 | + "Cannot fetch pte at address=0x%"PRIx64"\n", addr); | ||
207 | + event->type = SMMU_EVT_F_STE_FETCH; | ||
208 | + event->u.f_ste_fetch.addr = addr; | ||
209 | + return -EINVAL; | ||
210 | + } | ||
211 | + return 0; | ||
212 | + | ||
213 | +} | ||
214 | + | ||
215 | +/* @ssid > 0 not supported yet */ | ||
216 | +static int smmu_get_cd(SMMUv3State *s, STE *ste, uint32_t ssid, | ||
217 | + CD *buf, SMMUEventInfo *event) | ||
218 | +{ | ||
219 | + dma_addr_t addr = STE_CTXPTR(ste); | ||
220 | + int ret; | ||
221 | + | ||
222 | + trace_smmuv3_get_cd(addr); | ||
223 | + /* TODO: guarantee 64-bit single-copy atomicity */ | ||
224 | + ret = dma_memory_read(&address_space_memory, addr, | ||
225 | + (void *)buf, sizeof(*buf)); | ||
226 | + if (ret != MEMTX_OK) { | ||
227 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
228 | + "Cannot fetch pte at address=0x%"PRIx64"\n", addr); | ||
229 | + event->type = SMMU_EVT_F_CD_FETCH; | ||
230 | + event->u.f_ste_fetch.addr = addr; | ||
231 | + return -EINVAL; | ||
232 | + } | ||
233 | + return 0; | ||
234 | +} | ||
235 | + | ||
236 | +/* Returns <0 if the caller has no need to continue the translation */ | ||
237 | +static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg, | ||
238 | + STE *ste, SMMUEventInfo *event) | ||
239 | +{ | ||
240 | + uint32_t config; | ||
241 | + int ret = -EINVAL; | ||
242 | + | ||
243 | + if (!STE_VALID(ste)) { | ||
244 | + goto bad_ste; | ||
245 | + } | 117 | + } |
246 | + | 118 | + |
247 | + config = STE_CONFIG(ste); | 119 | +DO_2SHIFT_N(VSHRNB, vshrnb) |
248 | + | 120 | +DO_2SHIFT_N(VSHRNT, vshrnt) |
249 | + if (STE_CFG_ABORT(config)) { | 121 | +DO_2SHIFT_N(VRSHRNB, vrshrnb) |
250 | + cfg->aborted = true; /* abort but don't record any event */ | 122 | +DO_2SHIFT_N(VRSHRNT, vrshrnt) |
251 | + return ret; | ||
252 | + } | ||
253 | + | ||
254 | + if (STE_CFG_BYPASS(config)) { | ||
255 | + cfg->bypassed = true; | ||
256 | + return ret; | ||
257 | + } | ||
258 | + | ||
259 | + if (STE_CFG_S2_ENABLED(config)) { | ||
260 | + qemu_log_mask(LOG_UNIMP, "SMMUv3 does not support stage 2 yet\n"); | ||
261 | + goto bad_ste; | ||
262 | + } | ||
263 | + | ||
264 | + if (STE_S1CDMAX(ste) != 0) { | ||
265 | + qemu_log_mask(LOG_UNIMP, | ||
266 | + "SMMUv3 does not support multiple context descriptors yet\n"); | ||
267 | + goto bad_ste; | ||
268 | + } | ||
269 | + | ||
270 | + if (STE_S1STALLD(ste)) { | ||
271 | + qemu_log_mask(LOG_UNIMP, | ||
272 | + "SMMUv3 S1 stalling fault model not allowed yet\n"); | ||
273 | + goto bad_ste; | ||
274 | + } | ||
275 | + return 0; | ||
276 | + | ||
277 | +bad_ste: | ||
278 | + event->type = SMMU_EVT_C_BAD_STE; | ||
279 | + return -EINVAL; | ||
280 | +} | ||
281 | + | ||
282 | +/** | ||
283 | + * smmu_find_ste - Return the stream table entry associated | ||
284 | + * to the sid | ||
285 | + * | ||
286 | + * @s: smmuv3 handle | ||
287 | + * @sid: stream ID | ||
288 | + * @ste: returned stream table entry | ||
289 | + * @event: handle to an event info | ||
290 | + * | ||
291 | + * Supports linear and 2-level stream table | ||
292 | + * Return 0 on success, -EINVAL otherwise | ||
293 | + */ | ||
294 | +static int smmu_find_ste(SMMUv3State *s, uint32_t sid, STE *ste, | ||
295 | + SMMUEventInfo *event) | ||
296 | +{ | ||
297 | + dma_addr_t addr; | ||
298 | + int ret; | ||
299 | + | ||
300 | + trace_smmuv3_find_ste(sid, s->features, s->sid_split); | ||
301 | + /* Check SID range */ | ||
302 | + if (sid > (1 << SMMU_IDR1_SIDSIZE)) { | ||
303 | + event->type = SMMU_EVT_C_BAD_STREAMID; | ||
304 | + return -EINVAL; | ||
305 | + } | ||
306 | + if (s->features & SMMU_FEATURE_2LVL_STE) { | ||
307 | + int l1_ste_offset, l2_ste_offset, max_l2_ste, span; | ||
308 | + dma_addr_t strtab_base, l1ptr, l2ptr; | ||
309 | + STEDesc l1std; | ||
310 | + | ||
311 | + strtab_base = s->strtab_base & SMMU_BASE_ADDR_MASK; | ||
312 | + l1_ste_offset = sid >> s->sid_split; | ||
313 | + l2_ste_offset = sid & ((1 << s->sid_split) - 1); | ||
314 | + l1ptr = (dma_addr_t)(strtab_base + l1_ste_offset * sizeof(l1std)); | ||
315 | + /* TODO: guarantee 64-bit single-copy atomicity */ | ||
316 | + ret = dma_memory_read(&address_space_memory, l1ptr, | ||
317 | + (uint8_t *)&l1std, sizeof(l1std)); | ||
318 | + if (ret != MEMTX_OK) { | ||
319 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
320 | + "Could not read L1PTR at 0X%"PRIx64"\n", l1ptr); | ||
321 | + event->type = SMMU_EVT_F_STE_FETCH; | ||
322 | + event->u.f_ste_fetch.addr = l1ptr; | ||
323 | + return -EINVAL; | ||
324 | + } | ||
325 | + | ||
326 | + span = L1STD_SPAN(&l1std); | ||
327 | + | ||
328 | + if (!span) { | ||
329 | + /* l2ptr is not valid */ | ||
330 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
331 | + "invalid sid=%d (L1STD span=0)\n", sid); | ||
332 | + event->type = SMMU_EVT_C_BAD_STREAMID; | ||
333 | + return -EINVAL; | ||
334 | + } | ||
335 | + max_l2_ste = (1 << span) - 1; | ||
336 | + l2ptr = l1std_l2ptr(&l1std); | ||
337 | + trace_smmuv3_find_ste_2lvl(s->strtab_base, l1ptr, l1_ste_offset, | ||
338 | + l2ptr, l2_ste_offset, max_l2_ste); | ||
339 | + if (l2_ste_offset > max_l2_ste) { | ||
340 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
341 | + "l2_ste_offset=%d > max_l2_ste=%d\n", | ||
342 | + l2_ste_offset, max_l2_ste); | ||
343 | + event->type = SMMU_EVT_C_BAD_STE; | ||
344 | + return -EINVAL; | ||
345 | + } | ||
346 | + addr = l2ptr + l2_ste_offset * sizeof(*ste); | ||
347 | + } else { | ||
348 | + addr = s->strtab_base + sid * sizeof(*ste); | ||
349 | + } | ||
350 | + | ||
351 | + if (smmu_get_ste(s, addr, ste, event)) { | ||
352 | + return -EINVAL; | ||
353 | + } | ||
354 | + | ||
355 | + return 0; | ||
356 | +} | ||
357 | + | ||
358 | +static int decode_cd(SMMUTransCfg *cfg, CD *cd, SMMUEventInfo *event) | ||
359 | +{ | ||
360 | + int ret = -EINVAL; | ||
361 | + int i; | ||
362 | + | ||
363 | + if (!CD_VALID(cd) || !CD_AARCH64(cd)) { | ||
364 | + goto bad_cd; | ||
365 | + } | ||
366 | + if (!CD_A(cd)) { | ||
367 | + goto bad_cd; /* SMMU_IDR0.TERM_MODEL == 1 */ | ||
368 | + } | ||
369 | + if (CD_S(cd)) { | ||
370 | + goto bad_cd; /* !STE_SECURE && SMMU_IDR0.STALL_MODEL == 1 */ | ||
371 | + } | ||
372 | + if (CD_HA(cd) || CD_HD(cd)) { | ||
373 | + goto bad_cd; /* HTTU = 0 */ | ||
374 | + } | ||
375 | + | ||
376 | + /* we support only those at the moment */ | ||
377 | + cfg->aa64 = true; | ||
378 | + cfg->stage = 1; | ||
379 | + | ||
380 | + cfg->oas = oas2bits(CD_IPS(cd)); | ||
381 | + cfg->oas = MIN(oas2bits(SMMU_IDR5_OAS), cfg->oas); | ||
382 | + cfg->tbi = CD_TBI(cd); | ||
383 | + cfg->asid = CD_ASID(cd); | ||
384 | + | ||
385 | + trace_smmuv3_decode_cd(cfg->oas); | ||
386 | + | ||
387 | + /* decode data dependent on TT */ | ||
388 | + for (i = 0; i <= 1; i++) { | ||
389 | + int tg, tsz; | ||
390 | + SMMUTransTableInfo *tt = &cfg->tt[i]; | ||
391 | + | ||
392 | + cfg->tt[i].disabled = CD_EPD(cd, i); | ||
393 | + if (cfg->tt[i].disabled) { | ||
394 | + continue; | ||
395 | + } | ||
396 | + | ||
397 | + tsz = CD_TSZ(cd, i); | ||
398 | + if (tsz < 16 || tsz > 39) { | ||
399 | + goto bad_cd; | ||
400 | + } | ||
401 | + | ||
402 | + tg = CD_TG(cd, i); | ||
403 | + tt->granule_sz = tg2granule(tg, i); | ||
404 | + if ((tt->granule_sz != 12 && tt->granule_sz != 16) || CD_ENDI(cd)) { | ||
405 | + goto bad_cd; | ||
406 | + } | ||
407 | + | ||
408 | + tt->tsz = tsz; | ||
409 | + tt->ttb = CD_TTB(cd, i); | ||
410 | + if (tt->ttb & ~(MAKE_64BIT_MASK(0, cfg->oas))) { | ||
411 | + goto bad_cd; | ||
412 | + } | ||
413 | + trace_smmuv3_decode_cd_tt(i, tt->tsz, tt->ttb, tt->granule_sz); | ||
414 | + } | ||
415 | + | ||
416 | + event->record_trans_faults = CD_R(cd); | ||
417 | + | ||
418 | + return 0; | ||
419 | + | ||
420 | +bad_cd: | ||
421 | + event->type = SMMU_EVT_C_BAD_CD; | ||
422 | + return ret; | ||
423 | +} | ||
424 | + | ||
425 | +/** | ||
426 | + * smmuv3_decode_config - Prepare the translation configuration | ||
427 | + * for the @mr iommu region | ||
428 | + * @mr: iommu memory region the translation config must be prepared for | ||
429 | + * @cfg: output translation configuration which is populated through | ||
430 | + * the different configuration decoding steps | ||
431 | + * @event: must be zero'ed by the caller | ||
432 | + * | ||
433 | + * return < 0 if the translation needs to be aborted (@event is filled | ||
434 | + * accordingly). Return 0 otherwise. | ||
435 | + */ | ||
436 | +static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg, | ||
437 | + SMMUEventInfo *event) | ||
438 | +{ | ||
439 | + SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); | ||
440 | + uint32_t sid = smmu_get_sid(sdev); | ||
441 | + SMMUv3State *s = sdev->smmu; | ||
442 | + int ret = -EINVAL; | ||
443 | + STE ste; | ||
444 | + CD cd; | ||
445 | + | ||
446 | + if (smmu_find_ste(s, sid, &ste, event)) { | ||
447 | + return ret; | ||
448 | + } | ||
449 | + | ||
450 | + if (decode_ste(s, cfg, &ste, event)) { | ||
451 | + return ret; | ||
452 | + } | ||
453 | + | ||
454 | + if (smmu_get_cd(s, &ste, 0 /* ssid */, &cd, event)) { | ||
455 | + return ret; | ||
456 | + } | ||
457 | + | ||
458 | + return decode_cd(cfg, &cd, event); | ||
459 | +} | ||
460 | + | ||
461 | +static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, | ||
462 | + IOMMUAccessFlags flag) | ||
463 | +{ | ||
464 | + SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); | ||
465 | + SMMUv3State *s = sdev->smmu; | ||
466 | + uint32_t sid = smmu_get_sid(sdev); | ||
467 | + SMMUEventInfo event = {.type = SMMU_EVT_OK, .sid = sid}; | ||
468 | + SMMUPTWEventInfo ptw_info = {}; | ||
469 | + SMMUTransCfg cfg = {}; | ||
470 | + IOMMUTLBEntry entry = { | ||
471 | + .target_as = &address_space_memory, | ||
472 | + .iova = addr, | ||
473 | + .translated_addr = addr, | ||
474 | + .addr_mask = ~(hwaddr)0, | ||
475 | + .perm = IOMMU_NONE, | ||
476 | + }; | ||
477 | + int ret = 0; | ||
478 | + | ||
479 | + if (!smmu_enabled(s)) { | ||
480 | + goto out; | ||
481 | + } | ||
482 | + | ||
483 | + ret = smmuv3_decode_config(mr, &cfg, &event); | ||
484 | + if (ret) { | ||
485 | + goto out; | ||
486 | + } | ||
487 | + | ||
488 | + if (cfg.aborted) { | ||
489 | + goto out; | ||
490 | + } | ||
491 | + | ||
492 | + ret = smmu_ptw(&cfg, addr, flag, &entry, &ptw_info); | ||
493 | + if (ret) { | ||
494 | + switch (ptw_info.type) { | ||
495 | + case SMMU_PTW_ERR_WALK_EABT: | ||
496 | + event.type = SMMU_EVT_F_WALK_EABT; | ||
497 | + event.u.f_walk_eabt.addr = addr; | ||
498 | + event.u.f_walk_eabt.rnw = flag & 0x1; | ||
499 | + event.u.f_walk_eabt.class = 0x1; | ||
500 | + event.u.f_walk_eabt.addr2 = ptw_info.addr; | ||
501 | + break; | ||
502 | + case SMMU_PTW_ERR_TRANSLATION: | ||
503 | + if (event.record_trans_faults) { | ||
504 | + event.type = SMMU_EVT_F_TRANSLATION; | ||
505 | + event.u.f_translation.addr = addr; | ||
506 | + event.u.f_translation.rnw = flag & 0x1; | ||
507 | + } | ||
508 | + break; | ||
509 | + case SMMU_PTW_ERR_ADDR_SIZE: | ||
510 | + if (event.record_trans_faults) { | ||
511 | + event.type = SMMU_EVT_F_ADDR_SIZE; | ||
512 | + event.u.f_addr_size.addr = addr; | ||
513 | + event.u.f_addr_size.rnw = flag & 0x1; | ||
514 | + } | ||
515 | + break; | ||
516 | + case SMMU_PTW_ERR_ACCESS: | ||
517 | + if (event.record_trans_faults) { | ||
518 | + event.type = SMMU_EVT_F_ACCESS; | ||
519 | + event.u.f_access.addr = addr; | ||
520 | + event.u.f_access.rnw = flag & 0x1; | ||
521 | + } | ||
522 | + break; | ||
523 | + case SMMU_PTW_ERR_PERMISSION: | ||
524 | + if (event.record_trans_faults) { | ||
525 | + event.type = SMMU_EVT_F_PERMISSION; | ||
526 | + event.u.f_permission.addr = addr; | ||
527 | + event.u.f_permission.rnw = flag & 0x1; | ||
528 | + } | ||
529 | + break; | ||
530 | + default: | ||
531 | + g_assert_not_reached(); | ||
532 | + } | ||
533 | + } | ||
534 | +out: | ||
535 | + if (ret) { | ||
536 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
537 | + "%s translation failed for iova=0x%"PRIx64"(%d)\n", | ||
538 | + mr->parent_obj.name, addr, ret); | ||
539 | + entry.perm = IOMMU_NONE; | ||
540 | + smmuv3_record_event(s, &event); | ||
541 | + } else if (!cfg.aborted) { | ||
542 | + entry.perm = flag; | ||
543 | + trace_smmuv3_translate(mr->parent_obj.name, sid, addr, | ||
544 | + entry.translated_addr, entry.perm); | ||
545 | + } | ||
546 | + | ||
547 | + return entry; | ||
548 | +} | ||
549 | + | ||
550 | static int smmuv3_cmdq_consume(SMMUv3State *s) | ||
551 | { | ||
552 | SMMUCmdError cmd_error = SMMU_CERROR_NONE; | ||
553 | @@ -XXX,XX +XXX,XX @@ static void smmuv3_class_init(ObjectClass *klass, void *data) | ||
554 | static void smmuv3_iommu_memory_region_class_init(ObjectClass *klass, | ||
555 | void *data) | ||
556 | { | ||
557 | + IOMMUMemoryRegionClass *imrc = IOMMU_MEMORY_REGION_CLASS(klass); | ||
558 | + | ||
559 | + imrc->translate = smmuv3_translate; | ||
560 | } | ||
561 | |||
562 | static const TypeInfo smmuv3_type_info = { | ||
563 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
564 | index XXXXXXX..XXXXXXX 100644 | ||
565 | --- a/hw/arm/trace-events | ||
566 | +++ b/hw/arm/trace-events | ||
567 | @@ -XXX,XX +XXX,XX @@ smmuv3_write_mmio_idr(uint64_t addr, uint64_t val) "write to RO/Unimpl reg 0x%lx | ||
568 | smmuv3_write_mmio_evtq_cons_bef_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "Before clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | ||
569 | smmuv3_write_mmio_evtq_cons_after_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "after clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | ||
570 | smmuv3_record_event(const char *type, uint32_t sid) "%s sid=%d" | ||
571 | +smmuv3_find_ste(uint16_t sid, uint32_t features, uint16_t sid_split) "SID:0x%x features:0x%x, sid_split:0x%x" | ||
572 | +smmuv3_find_ste_2lvl(uint64_t strtab_base, uint64_t l1ptr, int l1_ste_offset, uint64_t l2ptr, int l2_ste_offset, int max_l2_ste) "strtab_base:0x%lx l1ptr:0x%"PRIx64" l1_off:0x%x, l2ptr:0x%"PRIx64" l2_off:0x%x max_l2_ste:%d" | ||
573 | +smmuv3_get_ste(uint64_t addr) "STE addr: 0x%"PRIx64 | ||
574 | +smmuv3_translate_bypass(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d bypass iova:0x%"PRIx64" is_write=%d" | ||
575 | +smmuv3_translate_in(uint16_t sid, int pci_bus_num, uint64_t strtab_base) "SID:0x%x bus:%d strtab_base:0x%"PRIx64 | ||
576 | +smmuv3_get_cd(uint64_t addr) "CD addr: 0x%"PRIx64 | ||
577 | +smmuv3_translate(const char *n, uint16_t sid, uint64_t iova, uint64_t translated, int perm) "%s sid=%d iova=0x%"PRIx64" translated=0x%"PRIx64" perm=0x%x" | ||
578 | +smmuv3_decode_cd(uint32_t oas) "oas=%d" | ||
579 | +smmuv3_decode_cd_tt(int i, uint32_t tsz, uint64_t ttb, uint32_t granule_sz) "TT[%d]:tsz:%d ttb:0x%"PRIx64" granule_sz:%d" | ||
580 | -- | 123 | -- |
581 | 2.17.0 | 124 | 2.20.1 |
582 | 125 | ||
583 | 126 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE saturating shift-right-and-narrow insns |
---|---|---|---|
2 | 2 | VQSHRN, VQSHRUN, VQRSHRN and VQRSHRUN. | |
3 | Now we have relevant helpers for queue and irq | 3 | |
4 | management, let's implement MMIO write operations. | 4 | do_srshr() is borrowed from sve_helper.c. |
5 | 5 | ||
6 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
7 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Message-id: 1524665762-31355-8-git-send-email-eric.auger@redhat.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Message-id: 20210628135835.6690-13-peter.maydell@linaro.org | ||
11 | --- | 9 | --- |
12 | hw/arm/smmuv3-internal.h | 8 +- | 10 | target/arm/helper-mve.h | 30 +++++++++++ |
13 | hw/arm/smmuv3.c | 170 +++++++++++++++++++++++++++++++++++++-- | 11 | target/arm/mve.decode | 28 ++++++++++ |
14 | hw/arm/trace-events | 6 ++ | 12 | target/arm/mve_helper.c | 104 +++++++++++++++++++++++++++++++++++++ |
15 | 3 files changed, 174 insertions(+), 10 deletions(-) | 13 | target/arm/translate-mve.c | 12 +++++ |
16 | 14 | 4 files changed, 174 insertions(+) | |
17 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | 15 | |
18 | index XXXXXXX..XXXXXXX 100644 | 16 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
19 | --- a/hw/arm/smmuv3-internal.h | 17 | index XXXXXXX..XXXXXXX 100644 |
20 | +++ b/hw/arm/smmuv3-internal.h | 18 | --- a/target/arm/helper-mve.h |
21 | @@ -XXX,XX +XXX,XX @@ REG32(CR0, 0x20) | 19 | +++ b/target/arm/helper-mve.h |
22 | FIELD(CR0, EVENTQEN, 2, 1) | 20 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshrnbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
23 | FIELD(CR0, CMDQEN, 3, 1) | 21 | DEF_HELPER_FLAGS_4(mve_vrshrnbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
24 | 22 | DEF_HELPER_FLAGS_4(mve_vrshrntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
25 | +#define SMMU_CR0_RESERVED 0xFFFFFC20 | 23 | DEF_HELPER_FLAGS_4(mve_vrshrnth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
26 | + | 24 | + |
27 | REG32(CR0ACK, 0x24) | 25 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
28 | REG32(CR1, 0x28) | 26 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
29 | REG32(CR2, 0x2c) | 27 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
30 | @@ -XXX,XX +XXX,XX @@ static inline bool smmuv3_gerror_irq_enabled(SMMUv3State *s) | 28 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
31 | return FIELD_EX32(s->irq_ctrl, IRQ_CTRL, GERROR_IRQEN); | 29 | + |
32 | } | 30 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
33 | 31 | +DEF_HELPER_FLAGS_4(mve_vqshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
34 | -/* public until callers get introduced */ | 32 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
35 | -void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask); | 33 | +DEF_HELPER_FLAGS_4(mve_vqshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
36 | -void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t gerrorn); | 34 | + |
37 | - | 35 | +DEF_HELPER_FLAGS_4(mve_vqshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
38 | /* Queue Handling */ | 36 | +DEF_HELPER_FLAGS_4(mve_vqshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
39 | 37 | +DEF_HELPER_FLAGS_4(mve_vqshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
40 | #define Q_BASE(q) ((q)->base & SMMU_BASE_ADDR_MASK) | 38 | +DEF_HELPER_FLAGS_4(mve_vqshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
41 | @@ -XXX,XX +XXX,XX @@ enum { /* Command completion notification */ | 39 | + |
42 | addr; \ | 40 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
43 | }) | 41 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
44 | 42 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
45 | -int smmuv3_cmdq_consume(SMMUv3State *s); | 43 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
46 | +#define SMMU_FEATURE_2LVL_STE (1 << 0) | 44 | + |
47 | 45 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
48 | #endif | 46 | +DEF_HELPER_FLAGS_4(mve_vqrshrnb_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
49 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | 47 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
50 | index XXXXXXX..XXXXXXX 100644 | 48 | +DEF_HELPER_FLAGS_4(mve_vqrshrnt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
51 | --- a/hw/arm/smmuv3.c | 49 | + |
52 | +++ b/hw/arm/smmuv3.c | 50 | +DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
53 | @@ -XXX,XX +XXX,XX @@ | 51 | +DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
54 | * @irq: irq type | 52 | +DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
55 | * @gerror_mask: mask of gerrors to toggle (relevant if @irq is GERROR) | 53 | +DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
56 | */ | 54 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
57 | -void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask) | 55 | index XXXXXXX..XXXXXXX 100644 |
58 | +static void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, | 56 | --- a/target/arm/mve.decode |
59 | + uint32_t gerror_mask) | 57 | +++ b/target/arm/mve.decode |
60 | { | 58 | @@ -XXX,XX +XXX,XX @@ VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_b |
61 | 59 | VRSHRNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 1 @2_shr_h | |
62 | bool pulse = false; | 60 | VRSHRNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 1 @2_shr_b |
63 | @@ -XXX,XX +XXX,XX @@ void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask) | 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) | ||
64 | } | 95 | } |
65 | } | 96 | } |
66 | 97 | ||
67 | -void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t new_gerrorn) | 98 | +static inline int64_t do_srshr(int64_t x, unsigned sh) |
68 | +static void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t new_gerrorn) | ||
69 | { | ||
70 | uint32_t pending = s->gerror ^ s->gerrorn; | ||
71 | uint32_t toggled = s->gerrorn ^ new_gerrorn; | ||
72 | @@ -XXX,XX +XXX,XX @@ static void smmuv3_init_regs(SMMUv3State *s) | ||
73 | s->sid_split = 0; | ||
74 | } | ||
75 | |||
76 | -int smmuv3_cmdq_consume(SMMUv3State *s) | ||
77 | +static int smmuv3_cmdq_consume(SMMUv3State *s) | ||
78 | { | ||
79 | SMMUCmdError cmd_error = SMMU_CERROR_NONE; | ||
80 | SMMUQueue *q = &s->cmdq; | ||
81 | @@ -XXX,XX +XXX,XX @@ int smmuv3_cmdq_consume(SMMUv3State *s) | ||
82 | return 0; | ||
83 | } | ||
84 | |||
85 | +static MemTxResult smmu_writell(SMMUv3State *s, hwaddr offset, | ||
86 | + uint64_t data, MemTxAttrs attrs) | ||
87 | +{ | 99 | +{ |
88 | + switch (offset) { | 100 | + if (likely(sh < 64)) { |
89 | + case A_GERROR_IRQ_CFG0: | 101 | + return (x >> sh) + ((x >> (sh - 1)) & 1); |
90 | + s->gerror_irq_cfg0 = data; | 102 | + } else { |
91 | + return MEMTX_OK; | 103 | + /* Rounding the sign bit always produces 0. */ |
92 | + case A_STRTAB_BASE: | 104 | + return 0; |
93 | + s->strtab_base = data; | ||
94 | + return MEMTX_OK; | ||
95 | + case A_CMDQ_BASE: | ||
96 | + s->cmdq.base = data; | ||
97 | + s->cmdq.log2size = extract64(s->cmdq.base, 0, 5); | ||
98 | + if (s->cmdq.log2size > SMMU_CMDQS) { | ||
99 | + s->cmdq.log2size = SMMU_CMDQS; | ||
100 | + } | ||
101 | + return MEMTX_OK; | ||
102 | + case A_EVENTQ_BASE: | ||
103 | + s->eventq.base = data; | ||
104 | + s->eventq.log2size = extract64(s->eventq.base, 0, 5); | ||
105 | + if (s->eventq.log2size > SMMU_EVENTQS) { | ||
106 | + s->eventq.log2size = SMMU_EVENTQS; | ||
107 | + } | ||
108 | + return MEMTX_OK; | ||
109 | + case A_EVENTQ_IRQ_CFG0: | ||
110 | + s->eventq_irq_cfg0 = data; | ||
111 | + return MEMTX_OK; | ||
112 | + default: | ||
113 | + qemu_log_mask(LOG_UNIMP, | ||
114 | + "%s Unexpected 64-bit access to 0x%"PRIx64" (WI)\n", | ||
115 | + __func__, offset); | ||
116 | + return MEMTX_OK; | ||
117 | + } | 105 | + } |
118 | +} | 106 | +} |
119 | + | 107 | + |
120 | +static MemTxResult smmu_writel(SMMUv3State *s, hwaddr offset, | 108 | DO_VSHRN_ALL(vshrn, DO_SHR) |
121 | + uint64_t data, MemTxAttrs attrs) | 109 | DO_VSHRN_ALL(vrshrn, do_urshr) |
110 | + | ||
111 | +static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, | ||
112 | + bool *satp) | ||
122 | +{ | 113 | +{ |
123 | + switch (offset) { | 114 | + if (val > max) { |
124 | + case A_CR0: | 115 | + *satp = true; |
125 | + s->cr[0] = data; | 116 | + return max; |
126 | + s->cr0ack = data & ~SMMU_CR0_RESERVED; | 117 | + } else if (val < min) { |
127 | + /* in case the command queue has been enabled */ | 118 | + *satp = true; |
128 | + smmuv3_cmdq_consume(s); | 119 | + return min; |
129 | + return MEMTX_OK; | 120 | + } else { |
130 | + case A_CR1: | 121 | + return val; |
131 | + s->cr[1] = data; | ||
132 | + return MEMTX_OK; | ||
133 | + case A_CR2: | ||
134 | + s->cr[2] = data; | ||
135 | + return MEMTX_OK; | ||
136 | + case A_IRQ_CTRL: | ||
137 | + s->irq_ctrl = data; | ||
138 | + return MEMTX_OK; | ||
139 | + case A_GERRORN: | ||
140 | + smmuv3_write_gerrorn(s, data); | ||
141 | + /* | ||
142 | + * By acknowledging the CMDQ_ERR, SW may notify cmds can | ||
143 | + * be processed again | ||
144 | + */ | ||
145 | + smmuv3_cmdq_consume(s); | ||
146 | + return MEMTX_OK; | ||
147 | + case A_GERROR_IRQ_CFG0: /* 64b */ | ||
148 | + s->gerror_irq_cfg0 = deposit64(s->gerror_irq_cfg0, 0, 32, data); | ||
149 | + return MEMTX_OK; | ||
150 | + case A_GERROR_IRQ_CFG0 + 4: | ||
151 | + s->gerror_irq_cfg0 = deposit64(s->gerror_irq_cfg0, 32, 32, data); | ||
152 | + return MEMTX_OK; | ||
153 | + case A_GERROR_IRQ_CFG1: | ||
154 | + s->gerror_irq_cfg1 = data; | ||
155 | + return MEMTX_OK; | ||
156 | + case A_GERROR_IRQ_CFG2: | ||
157 | + s->gerror_irq_cfg2 = data; | ||
158 | + return MEMTX_OK; | ||
159 | + case A_STRTAB_BASE: /* 64b */ | ||
160 | + s->strtab_base = deposit64(s->strtab_base, 0, 32, data); | ||
161 | + return MEMTX_OK; | ||
162 | + case A_STRTAB_BASE + 4: | ||
163 | + s->strtab_base = deposit64(s->strtab_base, 32, 32, data); | ||
164 | + return MEMTX_OK; | ||
165 | + case A_STRTAB_BASE_CFG: | ||
166 | + s->strtab_base_cfg = data; | ||
167 | + if (FIELD_EX32(data, STRTAB_BASE_CFG, FMT) == 1) { | ||
168 | + s->sid_split = FIELD_EX32(data, STRTAB_BASE_CFG, SPLIT); | ||
169 | + s->features |= SMMU_FEATURE_2LVL_STE; | ||
170 | + } | ||
171 | + return MEMTX_OK; | ||
172 | + case A_CMDQ_BASE: /* 64b */ | ||
173 | + s->cmdq.base = deposit64(s->cmdq.base, 0, 32, data); | ||
174 | + s->cmdq.log2size = extract64(s->cmdq.base, 0, 5); | ||
175 | + if (s->cmdq.log2size > SMMU_CMDQS) { | ||
176 | + s->cmdq.log2size = SMMU_CMDQS; | ||
177 | + } | ||
178 | + return MEMTX_OK; | ||
179 | + case A_CMDQ_BASE + 4: /* 64b */ | ||
180 | + s->cmdq.base = deposit64(s->cmdq.base, 32, 32, data); | ||
181 | + return MEMTX_OK; | ||
182 | + case A_CMDQ_PROD: | ||
183 | + s->cmdq.prod = data; | ||
184 | + smmuv3_cmdq_consume(s); | ||
185 | + return MEMTX_OK; | ||
186 | + case A_CMDQ_CONS: | ||
187 | + s->cmdq.cons = data; | ||
188 | + return MEMTX_OK; | ||
189 | + case A_EVENTQ_BASE: /* 64b */ | ||
190 | + s->eventq.base = deposit64(s->eventq.base, 0, 32, data); | ||
191 | + s->eventq.log2size = extract64(s->eventq.base, 0, 5); | ||
192 | + if (s->eventq.log2size > SMMU_EVENTQS) { | ||
193 | + s->eventq.log2size = SMMU_EVENTQS; | ||
194 | + } | ||
195 | + return MEMTX_OK; | ||
196 | + case A_EVENTQ_BASE + 4: | ||
197 | + s->eventq.base = deposit64(s->eventq.base, 32, 32, data); | ||
198 | + return MEMTX_OK; | ||
199 | + case A_EVENTQ_PROD: | ||
200 | + s->eventq.prod = data; | ||
201 | + return MEMTX_OK; | ||
202 | + case A_EVENTQ_CONS: | ||
203 | + s->eventq.cons = data; | ||
204 | + return MEMTX_OK; | ||
205 | + case A_EVENTQ_IRQ_CFG0: /* 64b */ | ||
206 | + s->eventq_irq_cfg0 = deposit64(s->eventq_irq_cfg0, 0, 32, data); | ||
207 | + return MEMTX_OK; | ||
208 | + case A_EVENTQ_IRQ_CFG0 + 4: | ||
209 | + s->eventq_irq_cfg0 = deposit64(s->eventq_irq_cfg0, 32, 32, data); | ||
210 | + return MEMTX_OK; | ||
211 | + case A_EVENTQ_IRQ_CFG1: | ||
212 | + s->eventq_irq_cfg1 = data; | ||
213 | + return MEMTX_OK; | ||
214 | + case A_EVENTQ_IRQ_CFG2: | ||
215 | + s->eventq_irq_cfg2 = data; | ||
216 | + return MEMTX_OK; | ||
217 | + default: | ||
218 | + qemu_log_mask(LOG_UNIMP, | ||
219 | + "%s Unexpected 32-bit access to 0x%"PRIx64" (WI)\n", | ||
220 | + __func__, offset); | ||
221 | + return MEMTX_OK; | ||
222 | + } | 122 | + } |
223 | +} | 123 | +} |
224 | + | 124 | + |
225 | static MemTxResult smmu_write_mmio(void *opaque, hwaddr offset, uint64_t data, | 125 | +/* Saturating narrowing right shifts */ |
226 | unsigned size, MemTxAttrs attrs) | 126 | +#define DO_VSHRN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ |
227 | { | 127 | + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ |
228 | - /* not yet implemented */ | 128 | + void *vm, uint32_t shift) \ |
229 | - return MEMTX_ERROR; | 129 | + { \ |
230 | + SMMUState *sys = opaque; | 130 | + LTYPE *m = vm; \ |
231 | + SMMUv3State *s = ARM_SMMUV3(sys); | 131 | + TYPE *d = vd; \ |
232 | + MemTxResult r; | 132 | + uint16_t mask = mve_element_mask(env); \ |
233 | + | 133 | + bool qc = false; \ |
234 | + /* CONSTRAINED UNPREDICTABLE choice to have page0/1 be exact aliases */ | 134 | + unsigned le; \ |
235 | + offset &= ~0x10000; | 135 | + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ |
236 | + | 136 | + bool sat = false; \ |
237 | + switch (size) { | 137 | + TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ |
238 | + case 8: | 138 | + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ |
239 | + r = smmu_writell(s, offset, data, attrs); | 139 | + qc |= sat && (mask & 1 << (TOP * ESIZE)); \ |
240 | + break; | 140 | + } \ |
241 | + case 4: | 141 | + if (qc) { \ |
242 | + r = smmu_writel(s, offset, data, attrs); | 142 | + env->vfp.qc[0] = qc; \ |
243 | + break; | 143 | + } \ |
244 | + default: | 144 | + mve_advance_vpt(env); \ |
245 | + r = MEMTX_ERROR; | ||
246 | + break; | ||
247 | + } | 145 | + } |
248 | + | 146 | + |
249 | + trace_smmuv3_write_mmio(offset, data, size, r); | 147 | +#define DO_VSHRN_SAT_UB(BOP, TOP, FN) \ |
250 | + return r; | 148 | + DO_VSHRN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ |
251 | } | 149 | + DO_VSHRN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) |
252 | 150 | + | |
253 | static MemTxResult smmu_readll(SMMUv3State *s, hwaddr offset, | 151 | +#define DO_VSHRN_SAT_UH(BOP, TOP, FN) \ |
254 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | 152 | + DO_VSHRN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ |
255 | index XXXXXXX..XXXXXXX 100644 | 153 | + DO_VSHRN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) |
256 | --- a/hw/arm/trace-events | 154 | + |
257 | +++ b/hw/arm/trace-events | 155 | +#define DO_VSHRN_SAT_SB(BOP, TOP, FN) \ |
258 | @@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_consume(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t con | 156 | + DO_VSHRN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ |
259 | smmuv3_cmdq_opcode(const char *opcode) "<--- %s" | 157 | + DO_VSHRN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) |
260 | smmuv3_cmdq_consume_out(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "prod:%d, cons:%d, prod_wrap:%d, cons_wrap:%d " | 158 | + |
261 | smmuv3_cmdq_consume_error(const char *cmd_name, uint8_t cmd_error) "Error on %s command execution: %d" | 159 | +#define DO_VSHRN_SAT_SH(BOP, TOP, FN) \ |
262 | +smmuv3_update(bool is_empty, uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "q empty:%d prod:%d cons:%d p.wrap:%d p.cons:%d" | 160 | + DO_VSHRN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ |
263 | +smmuv3_update_check_cmd(int error) "cmdq not enabled or error :0x%x" | 161 | + DO_VSHRN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) |
264 | +smmuv3_write_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" | 162 | + |
265 | +smmuv3_write_mmio_idr(uint64_t addr, uint64_t val) "write to RO/Unimpl reg 0x%lx val64:0x%lx" | 163 | +#define DO_SHRN_SB(N, M, SATP) \ |
266 | +smmuv3_write_mmio_evtq_cons_bef_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "Before clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | 164 | + do_sat_bhs((int64_t)(N) >> (M), INT8_MIN, INT8_MAX, SATP) |
267 | +smmuv3_write_mmio_evtq_cons_after_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "after clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | 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) | ||
268 | -- | 224 | -- |
269 | 2.17.0 | 225 | 2.20.1 |
270 | 226 | ||
271 | 227 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE VSHLC insn, which performs a shift left of the |
---|---|---|---|
2 | entire vector with carry in bits provided from a general purpose | ||
3 | register and carry out bits written back to that register. | ||
2 | 4 | ||
3 | We set up the infrastructure to enumerate all the PCI devices | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | attached to the SMMU and create an associated IOMMU memory | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | region and address space. | 7 | Message-id: 20210628135835.6690-14-peter.maydell@linaro.org |
8 | --- | ||
9 | target/arm/helper-mve.h | 2 ++ | ||
10 | target/arm/mve.decode | 2 ++ | ||
11 | target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++++++++++++ | ||
12 | target/arm/translate-mve.c | 30 ++++++++++++++++++++++++++++++ | ||
13 | 4 files changed, 72 insertions(+) | ||
6 | 14 | ||
7 | Those info are stored in SMMUDevice objects. The devices are | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
8 | grouped according to the PCIBus they belong to. A hash table | ||
9 | indexed by the PCIBus pointer is used. Also an array indexed by | ||
10 | the bus number allows to find the list of SMMUDevices. | ||
11 | |||
12 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
13 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
14 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
15 | Message-id: 1524665762-31355-3-git-send-email-eric.auger@redhat.com | ||
16 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
17 | --- | ||
18 | include/hw/arm/smmu-common.h | 8 +++++ | ||
19 | hw/arm/smmu-common.c | 69 ++++++++++++++++++++++++++++++++++++ | ||
20 | hw/arm/trace-events | 3 ++ | ||
21 | 3 files changed, 80 insertions(+) | ||
22 | |||
23 | diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/include/hw/arm/smmu-common.h | 17 | --- a/target/arm/helper-mve.h |
26 | +++ b/include/hw/arm/smmu-common.h | 18 | +++ b/target/arm/helper-mve.h |
27 | @@ -XXX,XX +XXX,XX @@ typedef struct { | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshrunbb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
28 | #define ARM_SMMU_GET_CLASS(obj) \ | 20 | DEF_HELPER_FLAGS_4(mve_vqrshrunbh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
29 | OBJECT_GET_CLASS(SMMUBaseClass, (obj), TYPE_ARM_SMMU) | 21 | DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) |
30 | 22 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | |
31 | +/* Return the SMMUPciBus handle associated to a PCI bus number */ | ||
32 | +SMMUPciBus *smmu_find_smmu_pcibus(SMMUState *s, uint8_t bus_num); | ||
33 | + | 23 | + |
34 | +/* Return the stream ID of an SMMU device */ | 24 | +DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) |
35 | +static inline uint16_t smmu_get_sid(SMMUDevice *sdev) | 25 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode |
26 | index XXXXXXX..XXXXXXX 100644 | ||
27 | --- a/target/arm/mve.decode | ||
28 | +++ b/target/arm/mve.decode | ||
29 | @@ -XXX,XX +XXX,XX @@ VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_b | ||
30 | VQRSHRUNB 111 1 1110 1 . ... ... ... 0 1111 1 1 . 0 ... 0 @2_shr_h | ||
31 | VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b | ||
32 | VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h | ||
33 | + | ||
34 | +VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd | ||
35 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/target/arm/mve_helper.c | ||
38 | +++ b/target/arm/mve_helper.c | ||
39 | @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UB(vqrshrnb_ub, vqrshrnt_ub, DO_RSHRN_UB) | ||
40 | DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) | ||
41 | DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) | ||
42 | DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) | ||
43 | + | ||
44 | +uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, | ||
45 | + uint32_t shift) | ||
36 | +{ | 46 | +{ |
37 | + return PCI_BUILD_BDF(pci_bus_num(sdev->bus), sdev->devfn); | 47 | + uint32_t *d = vd; |
38 | +} | 48 | + uint16_t mask = mve_element_mask(env); |
39 | #endif /* HW_ARM_SMMU_COMMON */ | 49 | + unsigned e; |
40 | diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c | 50 | + uint32_t r; |
41 | index XXXXXXX..XXXXXXX 100644 | ||
42 | --- a/hw/arm/smmu-common.c | ||
43 | +++ b/hw/arm/smmu-common.c | ||
44 | @@ -XXX,XX +XXX,XX @@ | ||
45 | #include "qemu/error-report.h" | ||
46 | #include "hw/arm/smmu-common.h" | ||
47 | |||
48 | +/** | ||
49 | + * The bus number is used for lookup when SID based invalidation occurs. | ||
50 | + * In that case we lazily populate the SMMUPciBus array from the bus hash | ||
51 | + * table. At the time the SMMUPciBus is created (smmu_find_add_as), the bus | ||
52 | + * numbers may not be always initialized yet. | ||
53 | + */ | ||
54 | +SMMUPciBus *smmu_find_smmu_pcibus(SMMUState *s, uint8_t bus_num) | ||
55 | +{ | ||
56 | + SMMUPciBus *smmu_pci_bus = s->smmu_pcibus_by_bus_num[bus_num]; | ||
57 | + | 51 | + |
58 | + if (!smmu_pci_bus) { | 52 | + /* |
59 | + GHashTableIter iter; | 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); | ||
60 | + | 69 | + |
61 | + g_hash_table_iter_init(&iter, s->smmu_pcibus_by_busptr); | 70 | + for (e = 0; e < 16 / 4; e++, mask >>= 4) { |
62 | + while (g_hash_table_iter_next(&iter, NULL, (void **)&smmu_pci_bus)) { | 71 | + r = (d[H4(e)] << shift) | (rdm & shiftmask); |
63 | + if (pci_bus_num(smmu_pci_bus->bus) == bus_num) { | 72 | + if (mask & 1) { |
64 | + s->smmu_pcibus_by_bus_num[bus_num] = smmu_pci_bus; | 73 | + rdm = d[H4(e)] >> (32 - shift); |
65 | + return smmu_pci_bus; | ||
66 | + } | 74 | + } |
75 | + mergemask(&d[H4(e)], r, mask); | ||
67 | + } | 76 | + } |
68 | + } | 77 | + } |
69 | + return smmu_pci_bus; | 78 | + mve_advance_vpt(env); |
79 | + return rdm; | ||
70 | +} | 80 | +} |
81 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c | ||
82 | index XXXXXXX..XXXXXXX 100644 | ||
83 | --- a/target/arm/translate-mve.c | ||
84 | +++ b/target/arm/translate-mve.c | ||
85 | @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_N(VQRSHRNB_U, vqrshrnb_u) | ||
86 | DO_2SHIFT_N(VQRSHRNT_U, vqrshrnt_u) | ||
87 | DO_2SHIFT_N(VQRSHRUNB, vqrshrunb) | ||
88 | DO_2SHIFT_N(VQRSHRUNT, vqrshrunt) | ||
71 | + | 89 | + |
72 | +static AddressSpace *smmu_find_add_as(PCIBus *bus, void *opaque, int devfn) | 90 | +static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) |
73 | +{ | 91 | +{ |
74 | + SMMUState *s = opaque; | 92 | + /* |
75 | + SMMUPciBus *sbus = g_hash_table_lookup(s->smmu_pcibus_by_busptr, bus); | 93 | + * Whole Vector Left Shift with Carry. The carry is taken |
76 | + SMMUDevice *sdev; | 94 | + * from a general purpose register and written back there. |
95 | + * An imm of 0 means "shift by 32". | ||
96 | + */ | ||
97 | + TCGv_ptr qd; | ||
98 | + TCGv_i32 rdm; | ||
77 | + | 99 | + |
78 | + if (!sbus) { | 100 | + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { |
79 | + sbus = g_malloc0(sizeof(SMMUPciBus) + | 101 | + return false; |
80 | + sizeof(SMMUDevice *) * SMMU_PCI_DEVFN_MAX); | 102 | + } |
81 | + sbus->bus = bus; | 103 | + if (a->rdm == 13 || a->rdm == 15) { |
82 | + g_hash_table_insert(s->smmu_pcibus_by_busptr, bus, sbus); | 104 | + /* CONSTRAINED UNPREDICTABLE: we UNDEF */ |
105 | + return false; | ||
106 | + } | ||
107 | + if (!mve_eci_check(s) || !vfp_access_check(s)) { | ||
108 | + return true; | ||
83 | + } | 109 | + } |
84 | + | 110 | + |
85 | + sdev = sbus->pbdev[devfn]; | 111 | + qd = mve_qreg_ptr(a->qd); |
86 | + if (!sdev) { | 112 | + rdm = load_reg(s, a->rdm); |
87 | + char *name = g_strdup_printf("%s-%d-%d", | 113 | + gen_helper_mve_vshlc(rdm, cpu_env, qd, rdm, tcg_constant_i32(a->imm)); |
88 | + s->mrtypename, | 114 | + store_reg(s, a->rdm, rdm); |
89 | + pci_bus_num(bus), devfn); | 115 | + tcg_temp_free_ptr(qd); |
90 | + sdev = sbus->pbdev[devfn] = g_new0(SMMUDevice, 1); | 116 | + mve_update_eci(s); |
91 | + | 117 | + return true; |
92 | + sdev->smmu = s; | ||
93 | + sdev->bus = bus; | ||
94 | + sdev->devfn = devfn; | ||
95 | + | ||
96 | + memory_region_init_iommu(&sdev->iommu, sizeof(sdev->iommu), | ||
97 | + s->mrtypename, | ||
98 | + OBJECT(s), name, 1ULL << SMMU_MAX_VA_BITS); | ||
99 | + address_space_init(&sdev->as, | ||
100 | + MEMORY_REGION(&sdev->iommu), name); | ||
101 | + trace_smmu_add_mr(name); | ||
102 | + g_free(name); | ||
103 | + } | ||
104 | + | ||
105 | + return &sdev->as; | ||
106 | +} | 118 | +} |
107 | + | ||
108 | static void smmu_base_realize(DeviceState *dev, Error **errp) | ||
109 | { | ||
110 | + SMMUState *s = ARM_SMMU(dev); | ||
111 | SMMUBaseClass *sbc = ARM_SMMU_GET_CLASS(dev); | ||
112 | Error *local_err = NULL; | ||
113 | |||
114 | @@ -XXX,XX +XXX,XX @@ static void smmu_base_realize(DeviceState *dev, Error **errp) | ||
115 | error_propagate(errp, local_err); | ||
116 | return; | ||
117 | } | ||
118 | + | ||
119 | + s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL); | ||
120 | + | ||
121 | + if (s->primary_bus) { | ||
122 | + pci_setup_iommu(s->primary_bus, smmu_find_add_as, s); | ||
123 | + } else { | ||
124 | + error_setg(errp, "SMMU is not attached to any PCI bus!"); | ||
125 | + } | ||
126 | } | ||
127 | |||
128 | static void smmu_base_reset(DeviceState *dev) | ||
129 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
130 | index XXXXXXX..XXXXXXX 100644 | ||
131 | --- a/hw/arm/trace-events | ||
132 | +++ b/hw/arm/trace-events | ||
133 | @@ -XXX,XX +XXX,XX @@ | ||
134 | |||
135 | # hw/arm/virt-acpi-build.c | ||
136 | virt_acpi_setup(void) "No fw cfg or ACPI disabled. Bailing out." | ||
137 | + | ||
138 | +# hw/arm/smmu-common.c | ||
139 | +smmu_add_mr(const char *name) "%s" | ||
140 | \ No newline at end of file | ||
141 | -- | 119 | -- |
142 | 2.17.0 | 120 | 2.20.1 |
143 | 121 | ||
144 | 122 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE VADDLV insn; this is similar to VADDV, except |
---|---|---|---|
2 | that it accumulates 32-bit elements into a 64-bit accumulator | ||
3 | stored in a pair of general-purpose registers. | ||
2 | 4 | ||
3 | We introduce some helpers to handle wired IRQs and especially | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | GERROR interrupt. SMMU writes GERROR register on GERROR event | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | and SW acks GERROR interrupts by setting GERRORn. | 7 | Message-id: 20210628135835.6690-15-peter.maydell@linaro.org |
8 | --- | ||
9 | target/arm/helper-mve.h | 3 ++ | ||
10 | target/arm/mve.decode | 6 +++- | ||
11 | target/arm/mve_helper.c | 19 ++++++++++++ | ||
12 | target/arm/translate-mve.c | 63 ++++++++++++++++++++++++++++++++++++++ | ||
13 | 4 files changed, 90 insertions(+), 1 deletion(-) | ||
6 | 14 | ||
7 | The Wired interrupts are edge sensitive hence the pulse usage. | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
8 | |||
9 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
10 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
11 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Message-id: 1524665762-31355-6-git-send-email-eric.auger@redhat.com | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | --- | ||
15 | hw/arm/smmuv3-internal.h | 14 +++++++++ | ||
16 | hw/arm/smmuv3.c | 64 ++++++++++++++++++++++++++++++++++++++++ | ||
17 | hw/arm/trace-events | 3 ++ | ||
18 | 3 files changed, 81 insertions(+) | ||
19 | |||
20 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | ||
21 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/hw/arm/smmuv3-internal.h | 17 | --- a/target/arm/helper-mve.h |
23 | +++ b/hw/arm/smmuv3-internal.h | 18 | +++ b/target/arm/helper-mve.h |
24 | @@ -XXX,XX +XXX,XX @@ static inline uint32_t smmuv3_idreg(int regoffset) | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) |
25 | return smmuv3_ids[regoffset / 4]; | 20 | DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) |
21 | DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) | ||
22 | |||
23 | +DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) | ||
24 | +DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) | ||
25 | + | ||
26 | DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
27 | DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
28 | DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) | ||
29 | diff --git a/target/arm/mve.decode b/target/arm/mve.decode | ||
30 | index XXXXXXX..XXXXXXX 100644 | ||
31 | --- a/target/arm/mve.decode | ||
32 | +++ b/target/arm/mve.decode | ||
33 | @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar | ||
34 | VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar | ||
35 | |||
36 | # Vector add across vector | ||
37 | -VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo | ||
38 | +{ | ||
39 | + VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo | ||
40 | + VADDLV 111 u:1 1110 1 ... 1001 ... 0 1111 00 a:1 0 qm:3 0 \ | ||
41 | + rdahi=%rdahi rdalo=%rdalo | ||
42 | +} | ||
43 | |||
44 | # Predicate operations | ||
45 | %mask_22_13 22:1 13:3 | ||
46 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/target/arm/mve_helper.c | ||
49 | +++ b/target/arm/mve_helper.c | ||
50 | @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) | ||
51 | DO_VADDV(vaddvuh, 2, uint16_t) | ||
52 | DO_VADDV(vaddvuw, 4, uint32_t) | ||
53 | |||
54 | +#define DO_VADDLV(OP, TYPE, LTYPE) \ | ||
55 | + uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ | ||
56 | + uint64_t ra) \ | ||
57 | + { \ | ||
58 | + uint16_t mask = mve_element_mask(env); \ | ||
59 | + unsigned e; \ | ||
60 | + TYPE *m = vm; \ | ||
61 | + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ | ||
62 | + if (mask & 1) { \ | ||
63 | + ra += (LTYPE)m[H4(e)]; \ | ||
64 | + } \ | ||
65 | + } \ | ||
66 | + mve_advance_vpt(env); \ | ||
67 | + return ra; \ | ||
68 | + } \ | ||
69 | + | ||
70 | +DO_VADDLV(vaddlv_s, int32_t, int64_t) | ||
71 | +DO_VADDLV(vaddlv_u, uint32_t, uint64_t) | ||
72 | + | ||
73 | /* Shifts by immediate */ | ||
74 | #define DO_2SHIFT(OP, ESIZE, TYPE, FN) \ | ||
75 | void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, \ | ||
76 | diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c | ||
77 | index XXXXXXX..XXXXXXX 100644 | ||
78 | --- a/target/arm/translate-mve.c | ||
79 | +++ b/target/arm/translate-mve.c | ||
80 | @@ -XXX,XX +XXX,XX @@ static bool trans_VADDV(DisasContext *s, arg_VADDV *a) | ||
81 | return true; | ||
26 | } | 82 | } |
27 | 83 | ||
28 | +static inline bool smmuv3_eventq_irq_enabled(SMMUv3State *s) | 84 | +static bool trans_VADDLV(DisasContext *s, arg_VADDLV *a) |
29 | +{ | 85 | +{ |
30 | + return FIELD_EX32(s->irq_ctrl, IRQ_CTRL, EVENTQ_IRQEN); | 86 | + /* |
31 | +} | 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; | ||
32 | + | 95 | + |
33 | +static inline bool smmuv3_gerror_irq_enabled(SMMUv3State *s) | 96 | + if (!dc_isar_feature(aa32_mve, s)) { |
34 | +{ | 97 | + return false; |
35 | + return FIELD_EX32(s->irq_ctrl, IRQ_CTRL, GERROR_IRQEN); | ||
36 | +} | ||
37 | + | ||
38 | +/* public until callers get introduced */ | ||
39 | +void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask); | ||
40 | +void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t gerrorn); | ||
41 | + | ||
42 | #endif | ||
43 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
44 | index XXXXXXX..XXXXXXX 100644 | ||
45 | --- a/hw/arm/smmuv3.c | ||
46 | +++ b/hw/arm/smmuv3.c | ||
47 | @@ -XXX,XX +XXX,XX @@ | ||
48 | #include "hw/arm/smmuv3.h" | ||
49 | #include "smmuv3-internal.h" | ||
50 | |||
51 | +/** | ||
52 | + * smmuv3_trigger_irq - pulse @irq if enabled and update | ||
53 | + * GERROR register in case of GERROR interrupt | ||
54 | + * | ||
55 | + * @irq: irq type | ||
56 | + * @gerror_mask: mask of gerrors to toggle (relevant if @irq is GERROR) | ||
57 | + */ | ||
58 | +void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask) | ||
59 | +{ | ||
60 | + | ||
61 | + bool pulse = false; | ||
62 | + | ||
63 | + switch (irq) { | ||
64 | + case SMMU_IRQ_EVTQ: | ||
65 | + pulse = smmuv3_eventq_irq_enabled(s); | ||
66 | + break; | ||
67 | + case SMMU_IRQ_PRIQ: | ||
68 | + qemu_log_mask(LOG_UNIMP, "PRI not yet supported\n"); | ||
69 | + break; | ||
70 | + case SMMU_IRQ_CMD_SYNC: | ||
71 | + pulse = true; | ||
72 | + break; | ||
73 | + case SMMU_IRQ_GERROR: | ||
74 | + { | ||
75 | + uint32_t pending = s->gerror ^ s->gerrorn; | ||
76 | + uint32_t new_gerrors = ~pending & gerror_mask; | ||
77 | + | ||
78 | + if (!new_gerrors) { | ||
79 | + /* only toggle non pending errors */ | ||
80 | + return; | ||
81 | + } | ||
82 | + s->gerror ^= new_gerrors; | ||
83 | + trace_smmuv3_write_gerror(new_gerrors, s->gerror); | ||
84 | + | ||
85 | + pulse = smmuv3_gerror_irq_enabled(s); | ||
86 | + break; | ||
87 | + } | 98 | + } |
99 | + /* | ||
100 | + * rdahi == 13 is UNPREDICTABLE; rdahi == 15 is a related | ||
101 | + * encoding; rdalo always has bit 0 clear so cannot be 13 or 15. | ||
102 | + */ | ||
103 | + if (a->rdahi == 13 || a->rdahi == 15) { | ||
104 | + return false; | ||
88 | + } | 105 | + } |
89 | + if (pulse) { | 106 | + if (!mve_eci_check(s) || !vfp_access_check(s)) { |
90 | + trace_smmuv3_trigger_irq(irq); | 107 | + return true; |
91 | + qemu_irq_pulse(s->irq[irq]); | ||
92 | + } | ||
93 | +} | ||
94 | + | ||
95 | +void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t new_gerrorn) | ||
96 | +{ | ||
97 | + uint32_t pending = s->gerror ^ s->gerrorn; | ||
98 | + uint32_t toggled = s->gerrorn ^ new_gerrorn; | ||
99 | + | ||
100 | + if (toggled & ~pending) { | ||
101 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
102 | + "guest toggles non pending errors = 0x%x\n", | ||
103 | + toggled & ~pending); | ||
104 | + } | 108 | + } |
105 | + | 109 | + |
106 | + /* | 110 | + /* |
107 | + * We do not raise any error in case guest toggles bits corresponding | 111 | + * This insn is subject to beat-wise execution. Partial execution |
108 | + * to not active IRQs (CONSTRAINED UNPREDICTABLE) | 112 | + * of an A=0 (no-accumulate) insn which does not execute the first |
113 | + * beat must start with the current value of RdaHi:RdaLo, not zero. | ||
109 | + */ | 114 | + */ |
110 | + s->gerrorn = new_gerrorn; | 115 | + if (a->a || mve_skip_first_beat(s)) { |
116 | + /* Accumulate input from RdaHi:RdaLo */ | ||
117 | + rda = tcg_temp_new_i64(); | ||
118 | + rdalo = load_reg(s, a->rdalo); | ||
119 | + rdahi = load_reg(s, a->rdahi); | ||
120 | + tcg_gen_concat_i32_i64(rda, rdalo, rdahi); | ||
121 | + tcg_temp_free_i32(rdalo); | ||
122 | + tcg_temp_free_i32(rdahi); | ||
123 | + } else { | ||
124 | + /* Accumulate starting at zero */ | ||
125 | + rda = tcg_const_i64(0); | ||
126 | + } | ||
111 | + | 127 | + |
112 | + trace_smmuv3_write_gerrorn(toggled & pending, s->gerrorn); | 128 | + qm = mve_qreg_ptr(a->qm); |
129 | + if (a->u) { | ||
130 | + gen_helper_mve_vaddlv_u(rda, cpu_env, qm, rda); | ||
131 | + } else { | ||
132 | + gen_helper_mve_vaddlv_s(rda, cpu_env, qm, rda); | ||
133 | + } | ||
134 | + tcg_temp_free_ptr(qm); | ||
135 | + | ||
136 | + rdalo = tcg_temp_new_i32(); | ||
137 | + rdahi = tcg_temp_new_i32(); | ||
138 | + tcg_gen_extrl_i64_i32(rdalo, rda); | ||
139 | + tcg_gen_extrh_i64_i32(rdahi, rda); | ||
140 | + store_reg(s, a->rdalo, rdalo); | ||
141 | + store_reg(s, a->rdahi, rdahi); | ||
142 | + tcg_temp_free_i64(rda); | ||
143 | + mve_update_eci(s); | ||
144 | + return true; | ||
113 | +} | 145 | +} |
114 | + | 146 | + |
115 | static void smmuv3_init_regs(SMMUv3State *s) | 147 | static bool do_1imm(DisasContext *s, arg_1imm *a, MVEGenOneOpImmFn *fn) |
116 | { | 148 | { |
117 | /** | 149 | TCGv_ptr qd; |
118 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
119 | index XXXXXXX..XXXXXXX 100644 | ||
120 | --- a/hw/arm/trace-events | ||
121 | +++ b/hw/arm/trace-events | ||
122 | @@ -XXX,XX +XXX,XX @@ smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "base | ||
123 | |||
124 | #hw/arm/smmuv3.c | ||
125 | smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" | ||
126 | +smmuv3_trigger_irq(int irq) "irq=%d" | ||
127 | +smmuv3_write_gerror(uint32_t toggled, uint32_t gerror) "toggled=0x%x, new GERROR=0x%x" | ||
128 | +smmuv3_write_gerrorn(uint32_t acked, uint32_t gerrorn) "acked=0x%x, new GERRORN=0x%x" | ||
129 | -- | 150 | -- |
130 | 2.17.0 | 151 | 2.20.1 |
131 | 152 | ||
132 | 153 | diff view generated by jsdifflib |
1 | For v8M the instructions VLLDM and VLSTM support lazy saving | 1 | The MVE extension to v8.1M includes some new shift instructions which |
---|---|---|---|
2 | and restoring of the secure floating-point registers. Even | 2 | sit entirely within the non-coprocessor part of the encoding space |
3 | if the floating point extension is not implemented, these | 3 | and which operate only on general-purpose registers. They take up |
4 | instructions must act as NOPs in Secure state, so they can | 4 | the space which was previously UNPREDICTABLE MOVS and ORRS encodings |
5 | be used as part of the secure-to-nonsecure call sequence. | 5 | with Rm == 13 or 15. |
6 | 6 | ||
7 | Fixes: https://bugs.launchpad.net/qemu/+bug/1768295 | 7 | Implement the long shifts by immediate, which perform shifts on a |
8 | Cc: qemu-stable@nongnu.org | 8 | pair of general-purpose registers treated as a 64-bit quantity, with |
9 | an immediate shift count between 1 and 32. | ||
10 | |||
11 | Awkwardly, because the MOVS and ORRS trans functions do not UNDEF for | ||
12 | the Rm==13,15 case, we need to explicitly emit code to UNDEF for the | ||
13 | cases where v8.1M now requires that. (Trying to change MOVS and ORRS | ||
14 | is too difficult, because the functions that generate the code are | ||
15 | shared between a dozen different kinds of arithmetic or logical | ||
16 | instruction for all A32, T16 and T32 encodings, and for some insns | ||
17 | and some encodings Rm==13,15 are valid.) | ||
18 | |||
19 | We make the helper functions we need for UQSHLL and SQSHLL take | ||
20 | a 32-bit value which the helper casts to int8_t because we'll need | ||
21 | these helpers also for the shift-by-register insns, where the shift | ||
22 | count might be < 0 or > 32. | ||
23 | |||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
10 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | 25 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
11 | Message-id: 20180503105730.5958-1-peter.maydell@linaro.org | 26 | Message-id: 20210628135835.6690-16-peter.maydell@linaro.org |
12 | --- | 27 | --- |
13 | target/arm/translate.c | 17 ++++++++++++++++- | 28 | target/arm/helper-mve.h | 3 ++ |
14 | 1 file changed, 16 insertions(+), 1 deletion(-) | 29 | target/arm/translate.h | 1 + |
15 | 30 | target/arm/t32.decode | 28 +++++++++++++ | |
31 | target/arm/mve_helper.c | 10 +++++ | ||
32 | target/arm/translate.c | 90 +++++++++++++++++++++++++++++++++++++++++ | ||
33 | 5 files changed, 132 insertions(+) | ||
34 | |||
35 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h | ||
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/target/arm/helper-mve.h | ||
38 | +++ b/target/arm/helper-mve.h | ||
39 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqrshruntb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
40 | DEF_HELPER_FLAGS_4(mve_vqrshrunth, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) | ||
41 | |||
42 | DEF_HELPER_FLAGS_4(mve_vshlc, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) | ||
43 | + | ||
44 | +DEF_HELPER_FLAGS_3(mve_sqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
45 | +DEF_HELPER_FLAGS_3(mve_uqshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | ||
46 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/target/arm/translate.h | ||
49 | +++ b/target/arm/translate.h | ||
50 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); | ||
51 | typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
52 | typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
53 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
54 | +typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); | ||
55 | |||
56 | /** | ||
57 | * arm_tbflags_from_tb: | ||
58 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode | ||
59 | index XXXXXXX..XXXXXXX 100644 | ||
60 | --- a/target/arm/t32.decode | ||
61 | +++ b/target/arm/t32.decode | ||
62 | @@ -XXX,XX +XXX,XX @@ | ||
63 | &mcr !extern cp opc1 crn crm opc2 rt | ||
64 | &mcrr !extern cp opc1 crm rt rt2 | ||
65 | |||
66 | +&mve_shl_ri rdalo rdahi shim | ||
67 | + | ||
68 | +# rdahi: bits [3:1] from insn, bit 0 is 1 | ||
69 | +# rdalo: bits [3:1] from insn, bit 0 is 0 | ||
70 | +%rdahi_9 9:3 !function=times_2_plus_1 | ||
71 | +%rdalo_17 17:3 !function=times_2 | ||
72 | + | ||
73 | # Data-processing (register) | ||
74 | |||
75 | %imm5_12_6 12:3 6:2 | ||
76 | @@ -XXX,XX +XXX,XX @@ | ||
77 | @S_xrr_shi ....... .... . rn:4 .... .... .. shty:2 rm:4 \ | ||
78 | &s_rrr_shi shim=%imm5_12_6 s=1 rd=0 | ||
79 | |||
80 | +@mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ | ||
81 | + &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 | ||
82 | + | ||
83 | { | ||
84 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi | ||
85 | AND_rrri 1110101 0000 . .... 0 ... .... .... .... @s_rrr_shi | ||
86 | } | ||
87 | BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi | ||
88 | { | ||
89 | + # The v8.1M MVE shift insns overlap in encoding with MOVS/ORRS | ||
90 | + # and are distinguished by having Rm==13 or 15. Those are UNPREDICTABLE | ||
91 | + # cases for MOVS/ORRS. We decode the MVE cases first, ensuring that | ||
92 | + # they explicitly call unallocated_encoding() for cases that must UNDEF | ||
93 | + # (eg "using a new shift insn on a v8.1M CPU without MVE"), and letting | ||
94 | + # the rest fall through (where ORR_rrri and MOV_rxri will end up | ||
95 | + # handling them as r13 and r15 accesses with the same semantics as A32). | ||
96 | + [ | ||
97 | + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri | ||
98 | + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
99 | + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
100 | + | ||
101 | + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri | ||
102 | + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri | ||
103 | + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri | ||
104 | + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri | ||
105 | + ] | ||
106 | + | ||
107 | MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi | ||
108 | ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi | ||
109 | } | ||
110 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c | ||
111 | index XXXXXXX..XXXXXXX 100644 | ||
112 | --- a/target/arm/mve_helper.c | ||
113 | +++ b/target/arm/mve_helper.c | ||
114 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, | ||
115 | mve_advance_vpt(env); | ||
116 | return rdm; | ||
117 | } | ||
118 | + | ||
119 | +uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
120 | +{ | ||
121 | + return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); | ||
122 | +} | ||
123 | + | ||
124 | +uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) | ||
125 | +{ | ||
126 | + return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); | ||
127 | +} | ||
16 | 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 |
17 | index XXXXXXX..XXXXXXX 100644 | 129 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/target/arm/translate.c | 130 | --- a/target/arm/translate.c |
19 | +++ b/target/arm/translate.c | 131 | +++ b/target/arm/translate.c |
20 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | 132 | @@ -XXX,XX +XXX,XX @@ static bool trans_MOVT(DisasContext *s, arg_MOVW *a) |
21 | /* Coprocessor. */ | 133 | return true; |
22 | if (arm_dc_feature(s, ARM_FEATURE_M)) { | 134 | } |
23 | /* We don't currently implement M profile FP support, | 135 | |
24 | - * so this entire space should give a NOCP fault. | 136 | +/* |
25 | + * so this entire space should give a NOCP fault, with | 137 | + * v8.1M MVE wide-shifts |
26 | + * the exception of the v8M VLLDM and VLSTM insns, which | 138 | + */ |
27 | + * must be NOPs in Secure state and UNDEF in Nonsecure state. | 139 | +static bool do_mve_shl_ri(DisasContext *s, arg_mve_shl_ri *a, |
28 | */ | 140 | + WideShiftImmFn *fn) |
29 | + if (arm_dc_feature(s, ARM_FEATURE_V8) && | 141 | +{ |
30 | + (insn & 0xffa00f00) == 0xec200a00) { | 142 | + TCGv_i64 rda; |
31 | + /* 0b1110_1100_0x1x_xxxx_xxxx_1010_xxxx_xxxx | 143 | + TCGv_i32 rdalo, rdahi; |
32 | + * - VLLDM, VLSTM | 144 | + |
33 | + * We choose to UNDEF if the RAZ bits are non-zero. | 145 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { |
34 | + */ | 146 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ |
35 | + if (!s->v8m_secure || (insn & 0x0040f0ff)) { | 147 | + return false; |
36 | + goto illegal_op; | 148 | + } |
37 | + } | 149 | + if (a->rdahi == 15) { |
38 | + /* Just NOP since FP support is not implemented */ | 150 | + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ |
39 | + break; | 151 | + return false; |
40 | + } | 152 | + } |
41 | + /* All other insns: NOCP */ | 153 | + if (!dc_isar_feature(aa32_mve, s) || |
42 | gen_exception_insn(s, 4, EXCP_NOCP, syn_uncategorized(), | 154 | + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || |
43 | default_exception_el(s)); | 155 | + a->rdahi == 13) { |
44 | break; | 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 | */ | ||
45 | -- | 229 | -- |
46 | 2.17.0 | 230 | 2.20.1 |
47 | 231 | ||
48 | 232 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE long shifts by register, which perform shifts on a |
---|---|---|---|
2 | 2 | pair of general-purpose registers treated as a 64-bit quantity, with | |
3 | This patch implements the page table walk for VMSAv8-64. | 3 | the shift count in another general-purpose register, which might be |
4 | 4 | either positive or negative. | |
5 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 5 | |
6 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | 6 | Like the long-shifts-by-immediate, these encodings sit in the space |
7 | Message-id: 1524665762-31355-4-git-send-email-eric.auger@redhat.com | 7 | that was previously the UNPREDICTABLE MOVS/ORRS with Rm==13,15. |
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 8 | Because LSLL_rr and ASRL_rr overlap with both MOV_rxri/ORR_rrri and |
9 | also with CSEL (as one of the previously-UNPREDICTABLE Rm==13 cases), | ||
10 | we have to move the CSEL pattern into the same decodetree group. | ||
11 | |||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
14 | Message-id: 20210628135835.6690-17-peter.maydell@linaro.org | ||
10 | --- | 15 | --- |
11 | hw/arm/smmu-internal.h | 99 ++++++++++++++++ | 16 | target/arm/helper-mve.h | 6 +++ |
12 | include/hw/arm/smmu-common.h | 14 +++ | 17 | target/arm/translate.h | 1 + |
13 | hw/arm/smmu-common.c | 222 +++++++++++++++++++++++++++++++++++ | 18 | target/arm/t32.decode | 16 +++++-- |
14 | hw/arm/trace-events | 9 +- | 19 | target/arm/mve_helper.c | 93 +++++++++++++++++++++++++++++++++++++++++ |
15 | 4 files changed, 343 insertions(+), 1 deletion(-) | 20 | target/arm/translate.c | 69 ++++++++++++++++++++++++++++++ |
16 | create mode 100644 hw/arm/smmu-internal.h | 21 | 5 files changed, 182 insertions(+), 3 deletions(-) |
17 | 22 | ||
18 | diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h | 23 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
19 | new file mode 100644 | 24 | index XXXXXXX..XXXXXXX 100644 |
20 | index XXXXXXX..XXXXXXX | 25 | --- a/target/arm/helper-mve.h |
21 | --- /dev/null | 26 | +++ b/target/arm/helper-mve.h |
22 | +++ b/hw/arm/smmu-internal.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 | ||
23 | @@ -XXX,XX +XXX,XX @@ | 55 | @@ -XXX,XX +XXX,XX @@ |
24 | +/* | 56 | &mcrr !extern cp opc1 crm rt rt2 |
25 | + * ARM SMMU support - Internal API | 57 | |
26 | + * | 58 | &mve_shl_ri rdalo rdahi shim |
27 | + * Copyright (c) 2017 Red Hat, Inc. | 59 | +&mve_shl_rr rdalo rdahi rm |
28 | + * Copyright (C) 2014-2016 Broadcom Corporation | 60 | |
29 | + * Written by Prem Mallappa, Eric Auger | 61 | # rdahi: bits [3:1] from insn, bit 0 is 1 |
30 | + * | 62 | # rdalo: bits [3:1] from insn, bit 0 is 0 |
31 | + * This program is free software; you can redistribute it and/or modify | ||
32 | + * it under the terms of the GNU General Public License version 2 as | ||
33 | + * published by the Free Software Foundation. | ||
34 | + * | ||
35 | + * This program is distributed in the hope that it will be useful, | ||
36 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
37 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
38 | + * General Public License for more details. | ||
39 | + * | ||
40 | + * You should have received a copy of the GNU General Public License along | ||
41 | + * with this program; if not, see <http://www.gnu.org/licenses/>. | ||
42 | + */ | ||
43 | + | ||
44 | +#ifndef HW_ARM_SMMU_INTERNAL_H | ||
45 | +#define HW_ARM_SMMU_INTERNAL_H | ||
46 | + | ||
47 | +#define TBI0(tbi) ((tbi) & 0x1) | ||
48 | +#define TBI1(tbi) ((tbi) & 0x2 >> 1) | ||
49 | + | ||
50 | +/* PTE Manipulation */ | ||
51 | + | ||
52 | +#define ARM_LPAE_PTE_TYPE_SHIFT 0 | ||
53 | +#define ARM_LPAE_PTE_TYPE_MASK 0x3 | ||
54 | + | ||
55 | +#define ARM_LPAE_PTE_TYPE_BLOCK 1 | ||
56 | +#define ARM_LPAE_PTE_TYPE_TABLE 3 | ||
57 | + | ||
58 | +#define ARM_LPAE_L3_PTE_TYPE_RESERVED 1 | ||
59 | +#define ARM_LPAE_L3_PTE_TYPE_PAGE 3 | ||
60 | + | ||
61 | +#define ARM_LPAE_PTE_VALID (1 << 0) | ||
62 | + | ||
63 | +#define PTE_ADDRESS(pte, shift) \ | ||
64 | + (extract64(pte, shift, 47 - shift + 1) << shift) | ||
65 | + | ||
66 | +#define is_invalid_pte(pte) (!(pte & ARM_LPAE_PTE_VALID)) | ||
67 | + | ||
68 | +#define is_reserved_pte(pte, level) \ | ||
69 | + ((level == 3) && \ | ||
70 | + ((pte & ARM_LPAE_PTE_TYPE_MASK) == ARM_LPAE_L3_PTE_TYPE_RESERVED)) | ||
71 | + | ||
72 | +#define is_block_pte(pte, level) \ | ||
73 | + ((level < 3) && \ | ||
74 | + ((pte & ARM_LPAE_PTE_TYPE_MASK) == ARM_LPAE_PTE_TYPE_BLOCK)) | ||
75 | + | ||
76 | +#define is_table_pte(pte, level) \ | ||
77 | + ((level < 3) && \ | ||
78 | + ((pte & ARM_LPAE_PTE_TYPE_MASK) == ARM_LPAE_PTE_TYPE_TABLE)) | ||
79 | + | ||
80 | +#define is_page_pte(pte, level) \ | ||
81 | + ((level == 3) && \ | ||
82 | + ((pte & ARM_LPAE_PTE_TYPE_MASK) == ARM_LPAE_L3_PTE_TYPE_PAGE)) | ||
83 | + | ||
84 | +/* access permissions */ | ||
85 | + | ||
86 | +#define PTE_AP(pte) \ | ||
87 | + (extract64(pte, 6, 2)) | ||
88 | + | ||
89 | +#define PTE_APTABLE(pte) \ | ||
90 | + (extract64(pte, 61, 2)) | ||
91 | + | ||
92 | +/* | ||
93 | + * TODO: At the moment all transactions are considered as privileged (EL1) | ||
94 | + * as IOMMU translation callback does not pass user/priv attributes. | ||
95 | + */ | ||
96 | +#define is_permission_fault(ap, perm) \ | ||
97 | + (((perm) & IOMMU_WO) && ((ap) & 0x2)) | ||
98 | + | ||
99 | +#define PTE_AP_TO_PERM(ap) \ | ||
100 | + (IOMMU_ACCESS_FLAG(true, !((ap) & 0x2))) | ||
101 | + | ||
102 | +/* Level Indexing */ | ||
103 | + | ||
104 | +static inline int level_shift(int level, int granule_sz) | ||
105 | +{ | ||
106 | + return granule_sz + (3 - level) * (granule_sz - 3); | ||
107 | +} | ||
108 | + | ||
109 | +static inline uint64_t level_page_mask(int level, int granule_sz) | ||
110 | +{ | ||
111 | + return ~(MAKE_64BIT_MASK(0, level_shift(level, granule_sz))); | ||
112 | +} | ||
113 | + | ||
114 | +static inline | ||
115 | +uint64_t iova_level_offset(uint64_t iova, int inputsize, | ||
116 | + int level, int gsz) | ||
117 | +{ | ||
118 | + return ((iova & MAKE_64BIT_MASK(0, inputsize)) >> level_shift(level, gsz)) & | ||
119 | + MAKE_64BIT_MASK(0, gsz - 3); | ||
120 | +} | ||
121 | + | ||
122 | +#endif | ||
123 | diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h | ||
124 | index XXXXXXX..XXXXXXX 100644 | ||
125 | --- a/include/hw/arm/smmu-common.h | ||
126 | +++ b/include/hw/arm/smmu-common.h | ||
127 | @@ -XXX,XX +XXX,XX @@ static inline uint16_t smmu_get_sid(SMMUDevice *sdev) | ||
128 | { | ||
129 | return PCI_BUILD_BDF(pci_bus_num(sdev->bus), sdev->devfn); | ||
130 | } | ||
131 | + | ||
132 | +/** | ||
133 | + * smmu_ptw - Perform the page table walk for a given iova / access flags | ||
134 | + * pair, according to @cfg translation config | ||
135 | + */ | ||
136 | +int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm, | ||
137 | + IOMMUTLBEntry *tlbe, SMMUPTWEventInfo *info); | ||
138 | + | ||
139 | +/** | ||
140 | + * select_tt - compute which translation table shall be used according to | ||
141 | + * the input iova and translation config and return the TT specific info | ||
142 | + */ | ||
143 | +SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova); | ||
144 | + | ||
145 | #endif /* HW_ARM_SMMU_COMMON */ | ||
146 | diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c | ||
147 | index XXXXXXX..XXXXXXX 100644 | ||
148 | --- a/hw/arm/smmu-common.c | ||
149 | +++ b/hw/arm/smmu-common.c | ||
150 | @@ -XXX,XX +XXX,XX @@ | 63 | @@ -XXX,XX +XXX,XX @@ |
151 | 64 | ||
152 | #include "qemu/error-report.h" | 65 | @mve_shl_ri ....... .... . ... . . ... ... . .. .. .... \ |
153 | #include "hw/arm/smmu-common.h" | 66 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 |
154 | +#include "smmu-internal.h" | 67 | +@mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ |
155 | + | 68 | + &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 |
156 | +/* VMSAv8-64 Translation */ | 69 | |
157 | + | 70 | { |
158 | +/** | 71 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi |
159 | + * get_pte - Get the content of a page table entry located at | 72 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi |
160 | + * @base_addr[@index] | 73 | URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
161 | + */ | 74 | SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
162 | +static int get_pte(dma_addr_t baseaddr, uint32_t index, uint64_t *pte, | 75 | SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
163 | + SMMUPTWEventInfo *info) | 76 | + |
164 | +{ | 77 | + LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr |
165 | + int ret; | 78 | + ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr |
166 | + dma_addr_t addr = baseaddr + index * sizeof(*pte); | 79 | + UQRSHLL64_rr 1110101 0010 1 ... 1 .... ... 1 0000 1101 @mve_shl_rr |
167 | + | 80 | + SQRSHRL64_rr 1110101 0010 1 ... 1 .... ... 1 0010 1101 @mve_shl_rr |
168 | + /* TODO: guarantee 64-bit single-copy atomicity */ | 81 | + UQRSHLL48_rr 1110101 0010 1 ... 1 .... ... 1 1000 1101 @mve_shl_rr |
169 | + ret = dma_memory_read(&address_space_memory, addr, | 82 | + SQRSHRL48_rr 1110101 0010 1 ... 1 .... ... 1 1010 1101 @mve_shl_rr |
170 | + (uint8_t *)pte, sizeof(*pte)); | 83 | ] |
171 | + | 84 | |
172 | + if (ret != MEMTX_OK) { | 85 | MOV_rxri 1110101 0010 . 1111 0 ... .... .... .... @s_rxr_shi |
173 | + info->type = SMMU_PTW_ERR_WALK_EABT; | 86 | ORR_rrri 1110101 0010 . .... 0 ... .... .... .... @s_rrr_shi |
174 | + info->addr = addr; | 87 | + |
175 | + return -EINVAL; | 88 | + # v8.1M CSEL and friends |
176 | + } | 89 | + CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 |
177 | + trace_smmu_get_pte(baseaddr, index, addr, *pte); | 90 | } |
178 | + return 0; | 91 | { |
179 | +} | 92 | MVN_rxri 1110101 0011 . 1111 0 ... .... .... .... @s_rxr_shi |
180 | + | 93 | @@ -XXX,XX +XXX,XX @@ SBC_rrri 1110101 1011 . .... 0 ... .... .... .... @s_rrr_shi |
181 | +/* VMSAv8-64 Translation Table Format Descriptor Decoding */ | 94 | } |
182 | + | 95 | RSB_rrri 1110101 1110 . .... 0 ... .... .... .... @s_rrr_shi |
183 | +/** | 96 | |
184 | + * get_page_pte_address - returns the L3 descriptor output address, | 97 | -# v8.1M CSEL and friends |
185 | + * ie. the page frame | 98 | -CSEL 1110101 0010 1 rn:4 10 op:2 rd:4 fcond:4 rm:4 |
186 | + * ARM ARM spec: Figure D4-17 VMSAv8-64 level 3 descriptor format | 99 | - |
187 | + */ | 100 | # Data-processing (register-shifted register) |
188 | +static inline hwaddr get_page_pte_address(uint64_t pte, int granule_sz) | 101 | |
189 | +{ | 102 | MOV_rxrr 1111 1010 0 shty:2 s:1 rm:4 1111 rd:4 0000 rs:4 \ |
190 | + return PTE_ADDRESS(pte, granule_sz); | 103 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
191 | +} | 104 | index XXXXXXX..XXXXXXX 100644 |
192 | + | 105 | --- a/target/arm/mve_helper.c |
193 | +/** | 106 | +++ b/target/arm/mve_helper.c |
194 | + * get_table_pte_address - return table descriptor output address, | 107 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, |
195 | + * ie. address of next level table | 108 | return rdm; |
196 | + * ARM ARM Figure D4-16 VMSAv8-64 level0, level1, and level 2 descriptor formats | 109 | } |
197 | + */ | 110 | |
198 | +static inline hwaddr get_table_pte_address(uint64_t pte, int granule_sz) | 111 | +uint64_t HELPER(mve_sshrl)(CPUARMState *env, uint64_t n, uint32_t shift) |
199 | +{ | 112 | +{ |
200 | + return PTE_ADDRESS(pte, granule_sz); | 113 | + return do_sqrshl_d(n, -(int8_t)shift, false, NULL); |
201 | +} | 114 | +} |
202 | + | 115 | + |
203 | +/** | 116 | +uint64_t HELPER(mve_ushll)(CPUARMState *env, uint64_t n, uint32_t shift) |
204 | + * get_block_pte_address - return block descriptor output address and block size | 117 | +{ |
205 | + * ARM ARM Figure D4-16 VMSAv8-64 level0, level1, and level 2 descriptor formats | 118 | + return do_uqrshl_d(n, (int8_t)shift, false, NULL); |
206 | + */ | 119 | +} |
207 | +static inline hwaddr get_block_pte_address(uint64_t pte, int level, | 120 | + |
208 | + int granule_sz, uint64_t *bsz) | 121 | uint64_t HELPER(mve_sqshll)(CPUARMState *env, uint64_t n, uint32_t shift) |
209 | +{ | 122 | { |
210 | + int n = (granule_sz - 3) * (4 - level) + 3; | 123 | return do_sqrshl_d(n, (int8_t)shift, false, &env->QF); |
211 | + | 124 | @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqshll)(CPUARMState *env, uint64_t n, uint32_t shift) |
212 | + *bsz = 1 << n; | 125 | { |
213 | + return PTE_ADDRESS(pte, n); | 126 | return do_uqrshl_d(n, (int8_t)shift, false, &env->QF); |
214 | +} | 127 | } |
215 | + | 128 | + |
216 | +SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova) | 129 | +uint64_t HELPER(mve_sqrshrl)(CPUARMState *env, uint64_t n, uint32_t shift) |
217 | +{ | 130 | +{ |
218 | + bool tbi = extract64(iova, 55, 1) ? TBI1(cfg->tbi) : TBI0(cfg->tbi); | 131 | + return do_sqrshl_d(n, -(int8_t)shift, true, &env->QF); |
219 | + uint8_t tbi_byte = tbi * 8; | 132 | +} |
220 | + | 133 | + |
221 | + if (cfg->tt[0].tsz && | 134 | +uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) |
222 | + !extract64(iova, 64 - cfg->tt[0].tsz, cfg->tt[0].tsz - tbi_byte)) { | 135 | +{ |
223 | + /* there is a ttbr0 region and we are in it (high bits all zero) */ | 136 | + return do_uqrshl_d(n, (int8_t)shift, true, &env->QF); |
224 | + return &cfg->tt[0]; | 137 | +} |
225 | + } else if (cfg->tt[1].tsz && | 138 | + |
226 | + !extract64(iova, 64 - cfg->tt[1].tsz, cfg->tt[1].tsz - tbi_byte)) { | 139 | +/* Operate on 64-bit values, but saturate at 48 bits */ |
227 | + /* there is a ttbr1 region and we are in it (high bits all one) */ | 140 | +static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, |
228 | + return &cfg->tt[1]; | 141 | + bool round, uint32_t *sat) |
229 | + } else if (!cfg->tt[0].tsz) { | 142 | +{ |
230 | + /* ttbr0 region is "everything not in the ttbr1 region" */ | 143 | + if (shift <= -48) { |
231 | + return &cfg->tt[0]; | 144 | + /* Rounding the sign bit always produces 0. */ |
232 | + } else if (!cfg->tt[1].tsz) { | 145 | + if (round) { |
233 | + /* ttbr1 region is "everything not in the ttbr0 region" */ | ||
234 | + return &cfg->tt[1]; | ||
235 | + } | ||
236 | + /* in the gap between the two regions, this is a Translation fault */ | ||
237 | + return NULL; | ||
238 | +} | ||
239 | + | ||
240 | +/** | ||
241 | + * smmu_ptw_64 - VMSAv8-64 Walk of the page tables for a given IOVA | ||
242 | + * @cfg: translation config | ||
243 | + * @iova: iova to translate | ||
244 | + * @perm: access type | ||
245 | + * @tlbe: IOMMUTLBEntry (out) | ||
246 | + * @info: handle to an error info | ||
247 | + * | ||
248 | + * Return 0 on success, < 0 on error. In case of error, @info is filled | ||
249 | + * and tlbe->perm is set to IOMMU_NONE. | ||
250 | + * Upon success, @tlbe is filled with translated_addr and entry | ||
251 | + * permission rights. | ||
252 | + */ | ||
253 | +static int smmu_ptw_64(SMMUTransCfg *cfg, | ||
254 | + dma_addr_t iova, IOMMUAccessFlags perm, | ||
255 | + IOMMUTLBEntry *tlbe, SMMUPTWEventInfo *info) | ||
256 | +{ | ||
257 | + dma_addr_t baseaddr, indexmask; | ||
258 | + int stage = cfg->stage; | ||
259 | + SMMUTransTableInfo *tt = select_tt(cfg, iova); | ||
260 | + uint8_t level, granule_sz, inputsize, stride; | ||
261 | + | ||
262 | + if (!tt || tt->disabled) { | ||
263 | + info->type = SMMU_PTW_ERR_TRANSLATION; | ||
264 | + goto error; | ||
265 | + } | ||
266 | + | ||
267 | + granule_sz = tt->granule_sz; | ||
268 | + stride = granule_sz - 3; | ||
269 | + inputsize = 64 - tt->tsz; | ||
270 | + level = 4 - (inputsize - 4) / stride; | ||
271 | + indexmask = (1ULL << (inputsize - (stride * (4 - level)))) - 1; | ||
272 | + baseaddr = extract64(tt->ttb, 0, 48); | ||
273 | + baseaddr &= ~indexmask; | ||
274 | + | ||
275 | + tlbe->iova = iova; | ||
276 | + tlbe->addr_mask = (1 << granule_sz) - 1; | ||
277 | + | ||
278 | + while (level <= 3) { | ||
279 | + uint64_t subpage_size = 1ULL << level_shift(level, granule_sz); | ||
280 | + uint64_t mask = subpage_size - 1; | ||
281 | + uint32_t offset = iova_level_offset(iova, inputsize, level, granule_sz); | ||
282 | + uint64_t pte; | ||
283 | + dma_addr_t pte_addr = baseaddr + offset * sizeof(pte); | ||
284 | + uint8_t ap; | ||
285 | + | ||
286 | + if (get_pte(baseaddr, offset, &pte, info)) { | ||
287 | + goto error; | ||
288 | + } | ||
289 | + trace_smmu_ptw_level(level, iova, subpage_size, | ||
290 | + baseaddr, offset, pte); | ||
291 | + | ||
292 | + if (is_invalid_pte(pte) || is_reserved_pte(pte, level)) { | ||
293 | + trace_smmu_ptw_invalid_pte(stage, level, baseaddr, | ||
294 | + pte_addr, offset, pte); | ||
295 | + info->type = SMMU_PTW_ERR_TRANSLATION; | ||
296 | + goto error; | ||
297 | + } | ||
298 | + | ||
299 | + if (is_page_pte(pte, level)) { | ||
300 | + uint64_t gpa = get_page_pte_address(pte, granule_sz); | ||
301 | + | ||
302 | + ap = PTE_AP(pte); | ||
303 | + if (is_permission_fault(ap, perm)) { | ||
304 | + info->type = SMMU_PTW_ERR_PERMISSION; | ||
305 | + goto error; | ||
306 | + } | ||
307 | + | ||
308 | + tlbe->translated_addr = gpa + (iova & mask); | ||
309 | + tlbe->perm = PTE_AP_TO_PERM(ap); | ||
310 | + trace_smmu_ptw_page_pte(stage, level, iova, | ||
311 | + baseaddr, pte_addr, pte, gpa); | ||
312 | + return 0; | 146 | + return 0; |
313 | + } | 147 | + } |
314 | + if (is_block_pte(pte, level)) { | 148 | + return src >> 63; |
315 | + uint64_t block_size; | 149 | + } else if (shift < 0) { |
316 | + hwaddr gpa = get_block_pte_address(pte, level, granule_sz, | 150 | + if (round) { |
317 | + &block_size); | 151 | + src >>= -shift - 1; |
318 | + | 152 | + return (src >> 1) + (src & 1); |
319 | + ap = PTE_AP(pte); | 153 | + } |
320 | + if (is_permission_fault(ap, perm)) { | 154 | + return src >> -shift; |
321 | + info->type = SMMU_PTW_ERR_PERMISSION; | 155 | + } else if (shift < 48) { |
322 | + goto error; | 156 | + int64_t val = src << shift; |
323 | + } | 157 | + int64_t extval = sextract64(val, 0, 48); |
324 | + | 158 | + if (!sat || val == extval) { |
325 | + trace_smmu_ptw_block_pte(stage, level, baseaddr, | 159 | + return extval; |
326 | + pte_addr, pte, iova, gpa, | 160 | + } |
327 | + block_size >> 20); | 161 | + } else if (!sat || src == 0) { |
328 | + | 162 | + return 0; |
329 | + tlbe->translated_addr = gpa + (iova & mask); | 163 | + } |
330 | + tlbe->perm = PTE_AP_TO_PERM(ap); | 164 | + |
331 | + return 0; | 165 | + *sat = 1; |
332 | + } | 166 | + return (1ULL << 47) - (src >= 0); |
333 | + | 167 | +} |
334 | + /* table pte */ | 168 | + |
335 | + ap = PTE_APTABLE(pte); | 169 | +/* Operate on 64-bit values, but saturate at 48 bits */ |
336 | + | 170 | +static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, |
337 | + if (is_permission_fault(ap, perm)) { | 171 | + bool round, uint32_t *sat) |
338 | + info->type = SMMU_PTW_ERR_PERMISSION; | 172 | +{ |
339 | + goto error; | 173 | + uint64_t val, extval; |
340 | + } | 174 | + |
341 | + baseaddr = get_table_pte_address(pte, granule_sz); | 175 | + if (shift <= -(48 + round)) { |
342 | + level++; | 176 | + return 0; |
343 | + } | 177 | + } else if (shift < 0) { |
344 | + | 178 | + if (round) { |
345 | + info->type = SMMU_PTW_ERR_TRANSLATION; | 179 | + val = src >> (-shift - 1); |
346 | + | 180 | + val = (val >> 1) + (val & 1); |
347 | +error: | 181 | + } else { |
348 | + tlbe->perm = IOMMU_NONE; | 182 | + val = src >> -shift; |
349 | + return -EINVAL; | 183 | + } |
350 | +} | 184 | + extval = extract64(val, 0, 48); |
351 | + | 185 | + if (!sat || val == extval) { |
352 | +/** | 186 | + return extval; |
353 | + * smmu_ptw - Walk the page tables for an IOVA, according to @cfg | 187 | + } |
354 | + * | 188 | + } else if (shift < 48) { |
355 | + * @cfg: translation configuration | 189 | + uint64_t val = src << shift; |
356 | + * @iova: iova to translate | 190 | + uint64_t extval = extract64(val, 0, 48); |
357 | + * @perm: tentative access type | 191 | + if (!sat || val == extval) { |
358 | + * @tlbe: returned entry | 192 | + return extval; |
359 | + * @info: ptw event handle | 193 | + } |
360 | + * | 194 | + } else if (!sat || src == 0) { |
361 | + * return 0 on success | 195 | + return 0; |
362 | + */ | 196 | + } |
363 | +inline int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm, | 197 | + |
364 | + IOMMUTLBEntry *tlbe, SMMUPTWEventInfo *info) | 198 | + *sat = 1; |
365 | +{ | 199 | + return MAKE_64BIT_MASK(0, 48); |
366 | + if (!cfg->aa64) { | 200 | +} |
367 | + /* | 201 | + |
368 | + * This code path is not entered as we check this while decoding | 202 | +uint64_t HELPER(mve_sqrshrl48)(CPUARMState *env, uint64_t n, uint32_t shift) |
369 | + * the configuration data in the derived SMMU model. | 203 | +{ |
370 | + */ | 204 | + return do_sqrshl48_d(n, -(int8_t)shift, true, &env->QF); |
371 | + g_assert_not_reached(); | 205 | +} |
372 | + } | 206 | + |
373 | + | 207 | +uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) |
374 | + return smmu_ptw_64(cfg, iova, perm, tlbe, info); | 208 | +{ |
375 | +} | 209 | + return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); |
376 | 210 | +} | |
377 | /** | 211 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
378 | * The bus number is used for lookup when SID based invalidation occurs. | 212 | index XXXXXXX..XXXXXXX 100644 |
379 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | 213 | --- a/target/arm/translate.c |
380 | index XXXXXXX..XXXXXXX 100644 | 214 | +++ b/target/arm/translate.c |
381 | --- a/hw/arm/trace-events | 215 | @@ -XXX,XX +XXX,XX @@ static bool trans_URSHRL_ri(DisasContext *s, arg_mve_shl_ri *a) |
382 | +++ b/hw/arm/trace-events | 216 | return do_mve_shl_ri(s, a, gen_urshr64_i64); |
383 | @@ -XXX,XX +XXX,XX @@ | 217 | } |
384 | virt_acpi_setup(void) "No fw cfg or ACPI disabled. Bailing out." | 218 | |
385 | 219 | +static bool do_mve_shl_rr(DisasContext *s, arg_mve_shl_rr *a, WideShiftFn *fn) | |
386 | # hw/arm/smmu-common.c | 220 | +{ |
387 | -smmu_add_mr(const char *name) "%s" | 221 | + TCGv_i64 rda; |
388 | \ No newline at end of file | 222 | + TCGv_i32 rdalo, rdahi; |
389 | +smmu_add_mr(const char *name) "%s" | 223 | + |
390 | +smmu_page_walk(int stage, uint64_t baseaddr, int first_level, uint64_t start, uint64_t end) "stage=%d, baseaddr=0x%"PRIx64", first level=%d, start=0x%"PRIx64", end=0x%"PRIx64 | 224 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { |
391 | +smmu_lookup_table(int level, uint64_t baseaddr, int granule_sz, uint64_t start, uint64_t end, int flags, uint64_t subpage_size) "level=%d baseaddr=0x%"PRIx64" granule=%d, start=0x%"PRIx64" end=0x%"PRIx64" flags=%d subpage_size=0x%"PRIx64 | 225 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ |
392 | +smmu_ptw_level(int level, uint64_t iova, size_t subpage_size, uint64_t baseaddr, uint32_t offset, uint64_t pte) "level=%d iova=0x%"PRIx64" subpage_sz=0x%lx baseaddr=0x%"PRIx64" offset=%d => pte=0x%"PRIx64 | 226 | + return false; |
393 | +smmu_ptw_invalid_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint32_t offset, uint64_t pte) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" offset=%d pte=0x%"PRIx64 | 227 | + } |
394 | +smmu_ptw_page_pte(int stage, int level, uint64_t iova, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t address) "stage=%d level=%d iova=0x%"PRIx64" base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" page address = 0x%"PRIx64 | 228 | + if (a->rdahi == 15) { |
395 | +smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t iova, uint64_t gpa, int bsize_mb) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" iova=0x%"PRIx64" block address = 0x%"PRIx64" block size = %d MiB" | 229 | + /* These are a different encoding (SQSHL/SRSHR/UQSHL/URSHR) */ |
396 | +smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "baseaddr=0x%"PRIx64" index=0x%x, pteaddr=0x%"PRIx64", pte=0x%"PRIx64 | 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 | */ | ||
397 | -- | 291 | -- |
398 | 2.17.0 | 292 | 2.20.1 |
399 | 293 | ||
400 | 294 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE shifts by immediate, which perform shifts |
---|---|---|---|
2 | 2 | on a single general-purpose register. | |
3 | We introduce helpers to read/write into the command and event | 3 | |
4 | circular queues. | 4 | These patterns overlap with the long-shift-by-immediates, |
5 | 5 | so we have to rearrange the grouping a little here. | |
6 | smmuv3_write_eventq and smmuv3_cmq_consume will become static | 6 | |
7 | in subsequent patches. | ||
8 | |||
9 | Invalidation commands are not yet dealt with. We do not cache | ||
10 | data that need to be invalidated. This will change with vhost | ||
11 | integration. | ||
12 | |||
13 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | ||
14 | Signed-off-by: Prem Mallappa <prem.mallappa@broadcom.com> | ||
15 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
16 | Message-id: 1524665762-31355-7-git-send-email-eric.auger@redhat.com | ||
17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
9 | Message-id: 20210628135835.6690-18-peter.maydell@linaro.org | ||
18 | --- | 10 | --- |
19 | hw/arm/smmuv3-internal.h | 163 +++++++++++++++++++++++++++++++++++++++ | 11 | target/arm/helper-mve.h | 3 ++ |
20 | hw/arm/smmuv3.c | 136 ++++++++++++++++++++++++++++++++ | 12 | target/arm/translate.h | 1 + |
21 | hw/arm/trace-events | 5 ++ | 13 | target/arm/t32.decode | 31 ++++++++++++++----- |
22 | 3 files changed, 304 insertions(+) | 14 | target/arm/mve_helper.c | 10 ++++++ |
23 | 15 | target/arm/translate.c | 68 +++++++++++++++++++++++++++++++++++++++-- | |
24 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | 16 | 5 files changed, 104 insertions(+), 9 deletions(-) |
25 | index XXXXXXX..XXXXXXX 100644 | 17 | |
26 | --- a/hw/arm/smmuv3-internal.h | 18 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
27 | +++ b/hw/arm/smmuv3-internal.h | 19 | index XXXXXXX..XXXXXXX 100644 |
28 | @@ -XXX,XX +XXX,XX @@ static inline bool smmuv3_gerror_irq_enabled(SMMUv3State *s) | 20 | --- a/target/arm/helper-mve.h |
29 | void smmuv3_trigger_irq(SMMUv3State *s, SMMUIrq irq, uint32_t gerror_mask); | 21 | +++ b/target/arm/helper-mve.h |
30 | void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t gerrorn); | 22 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_sqrshrl, TCG_CALL_NO_RWG, i64, env, i64, i32) |
31 | 23 | DEF_HELPER_FLAGS_3(mve_uqrshll, TCG_CALL_NO_RWG, i64, env, i64, i32) | |
32 | +/* Queue Handling */ | 24 | DEF_HELPER_FLAGS_3(mve_sqrshrl48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
33 | + | 25 | DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
34 | +#define Q_BASE(q) ((q)->base & SMMU_BASE_ADDR_MASK) | 26 | + |
35 | +#define WRAP_MASK(q) (1 << (q)->log2size) | 27 | +DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) |
36 | +#define INDEX_MASK(q) (((1 << (q)->log2size)) - 1) | 28 | +DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) |
37 | +#define WRAP_INDEX_MASK(q) ((1 << ((q)->log2size + 1)) - 1) | 29 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
38 | + | 30 | index XXXXXXX..XXXXXXX 100644 |
39 | +#define Q_CONS(q) ((q)->cons & INDEX_MASK(q)) | 31 | --- a/target/arm/translate.h |
40 | +#define Q_PROD(q) ((q)->prod & INDEX_MASK(q)) | 32 | +++ b/target/arm/translate.h |
41 | + | 33 | @@ -XXX,XX +XXX,XX @@ typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); |
42 | +#define Q_CONS_ENTRY(q) (Q_BASE(q) + (q)->entry_size * Q_CONS(q)) | 34 | typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); |
43 | +#define Q_PROD_ENTRY(q) (Q_BASE(q) + (q)->entry_size * Q_PROD(q)) | 35 | typedef void WideShiftImmFn(TCGv_i64, TCGv_i64, int64_t shift); |
44 | + | 36 | typedef void WideShiftFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i32); |
45 | +#define Q_CONS_WRAP(q) (((q)->cons & WRAP_MASK(q)) >> (q)->log2size) | 37 | +typedef void ShiftImmFn(TCGv_i32, TCGv_i32, int32_t shift); |
46 | +#define Q_PROD_WRAP(q) (((q)->prod & WRAP_MASK(q)) >> (q)->log2size) | 38 | |
47 | + | 39 | /** |
48 | +static inline bool smmuv3_q_full(SMMUQueue *q) | 40 | * arm_tbflags_from_tb: |
49 | +{ | 41 | diff --git a/target/arm/t32.decode b/target/arm/t32.decode |
50 | + return ((q->cons ^ q->prod) & WRAP_INDEX_MASK(q)) == WRAP_MASK(q); | 42 | index XXXXXXX..XXXXXXX 100644 |
51 | +} | 43 | --- a/target/arm/t32.decode |
52 | + | 44 | +++ b/target/arm/t32.decode |
53 | +static inline bool smmuv3_q_empty(SMMUQueue *q) | 45 | @@ -XXX,XX +XXX,XX @@ |
54 | +{ | 46 | |
55 | + return (q->cons & WRAP_INDEX_MASK(q)) == (q->prod & WRAP_INDEX_MASK(q)); | 47 | &mve_shl_ri rdalo rdahi shim |
56 | +} | 48 | &mve_shl_rr rdalo rdahi rm |
57 | + | 49 | +&mve_sh_ri rda shim |
58 | +static inline void queue_prod_incr(SMMUQueue *q) | 50 | |
59 | +{ | 51 | # rdahi: bits [3:1] from insn, bit 0 is 1 |
60 | + q->prod = (q->prod + 1) & WRAP_INDEX_MASK(q); | 52 | # rdalo: bits [3:1] from insn, bit 0 is 0 |
61 | +} | 53 | @@ -XXX,XX +XXX,XX @@ |
62 | + | 54 | &mve_shl_ri shim=%imm5_12_6 rdalo=%rdalo_17 rdahi=%rdahi_9 |
63 | +static inline void queue_cons_incr(SMMUQueue *q) | 55 | @mve_shl_rr ....... .... . ... . rm:4 ... . .. .. .... \ |
64 | +{ | 56 | &mve_shl_rr rdalo=%rdalo_17 rdahi=%rdahi_9 |
65 | + /* | 57 | +@mve_sh_ri ....... .... . rda:4 . ... ... . .. .. .... \ |
66 | + * We have to use deposit for the CONS registers to preserve | 58 | + &mve_sh_ri shim=%imm5_12_6 |
67 | + * the ERR field in the high bits. | 59 | |
68 | + */ | 60 | { |
69 | + q->cons = deposit32(q->cons, 0, q->log2size + 1, q->cons + 1); | 61 | TST_xrri 1110101 0000 1 .... 0 ... 1111 .... .... @S_xrr_shi |
70 | +} | 62 | @@ -XXX,XX +XXX,XX @@ BIC_rrri 1110101 0001 . .... 0 ... .... .... .... @s_rrr_shi |
71 | + | 63 | # the rest fall through (where ORR_rrri and MOV_rxri will end up |
72 | +static inline bool smmuv3_cmdq_enabled(SMMUv3State *s) | 64 | # handling them as r13 and r15 accesses with the same semantics as A32). |
73 | +{ | 65 | [ |
74 | + return FIELD_EX32(s->cr[0], CR0, CMDQEN); | 66 | - LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
75 | +} | 67 | - LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri |
76 | + | 68 | - ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri |
77 | +static inline bool smmuv3_eventq_enabled(SMMUv3State *s) | 69 | + { |
78 | +{ | 70 | + UQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 00 1111 @mve_sh_ri |
79 | + return FIELD_EX32(s->cr[0], CR0, EVENTQEN); | 71 | + LSLL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 00 1111 @mve_shl_ri |
80 | +} | 72 | + UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri |
81 | + | 73 | + } |
82 | +static inline void smmu_write_cmdq_err(SMMUv3State *s, uint32_t err_type) | 74 | |
83 | +{ | 75 | - UQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 00 1111 @mve_shl_ri |
84 | + s->cmdq.cons = FIELD_DP32(s->cmdq.cons, CMDQ_CONS, ERR, err_type); | 76 | - URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
85 | +} | 77 | - SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
86 | + | 78 | - SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
87 | +void smmuv3_write_eventq(SMMUv3State *s, Evt *evt); | 79 | + { |
88 | + | 80 | + URSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 01 1111 @mve_sh_ri |
89 | +/* Commands */ | 81 | + LSRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 01 1111 @mve_shl_ri |
90 | + | 82 | + URSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 01 1111 @mve_shl_ri |
91 | +typedef enum SMMUCommandType { | 83 | + } |
92 | + SMMU_CMD_NONE = 0x00, | 84 | + |
93 | + SMMU_CMD_PREFETCH_CONFIG , | 85 | + { |
94 | + SMMU_CMD_PREFETCH_ADDR, | 86 | + SRSHR_ri 1110101 0010 1 .... 0 ... 1111 .. 10 1111 @mve_sh_ri |
95 | + SMMU_CMD_CFGI_STE, | 87 | + ASRL_ri 1110101 0010 1 ... 0 0 ... ... 1 .. 10 1111 @mve_shl_ri |
96 | + SMMU_CMD_CFGI_STE_RANGE, | 88 | + SRSHRL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 10 1111 @mve_shl_ri |
97 | + SMMU_CMD_CFGI_CD, | 89 | + } |
98 | + SMMU_CMD_CFGI_CD_ALL, | 90 | + |
99 | + SMMU_CMD_CFGI_ALL, | 91 | + { |
100 | + SMMU_CMD_TLBI_NH_ALL = 0x10, | 92 | + SQSHL_ri 1110101 0010 1 .... 0 ... 1111 .. 11 1111 @mve_sh_ri |
101 | + SMMU_CMD_TLBI_NH_ASID, | 93 | + SQSHLL_ri 1110101 0010 1 ... 1 0 ... ... 1 .. 11 1111 @mve_shl_ri |
102 | + SMMU_CMD_TLBI_NH_VA, | 94 | + } |
103 | + SMMU_CMD_TLBI_NH_VAA, | 95 | |
104 | + SMMU_CMD_TLBI_EL3_ALL = 0x18, | 96 | LSLL_rr 1110101 0010 1 ... 0 .... ... 1 0000 1101 @mve_shl_rr |
105 | + SMMU_CMD_TLBI_EL3_VA = 0x1a, | 97 | ASRL_rr 1110101 0010 1 ... 0 .... ... 1 0010 1101 @mve_shl_rr |
106 | + SMMU_CMD_TLBI_EL2_ALL = 0x20, | 98 | diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c |
107 | + SMMU_CMD_TLBI_EL2_ASID, | 99 | index XXXXXXX..XXXXXXX 100644 |
108 | + SMMU_CMD_TLBI_EL2_VA, | 100 | --- a/target/arm/mve_helper.c |
109 | + SMMU_CMD_TLBI_EL2_VAA, | 101 | +++ b/target/arm/mve_helper.c |
110 | + SMMU_CMD_TLBI_S12_VMALL = 0x28, | 102 | @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll48)(CPUARMState *env, uint64_t n, uint32_t shift) |
111 | + SMMU_CMD_TLBI_S2_IPA = 0x2a, | 103 | { |
112 | + SMMU_CMD_TLBI_NSNH_ALL = 0x30, | 104 | return do_uqrshl48_d(n, (int8_t)shift, true, &env->QF); |
113 | + SMMU_CMD_ATC_INV = 0x40, | ||
114 | + SMMU_CMD_PRI_RESP, | ||
115 | + SMMU_CMD_RESUME = 0x44, | ||
116 | + SMMU_CMD_STALL_TERM, | ||
117 | + SMMU_CMD_SYNC, | ||
118 | +} SMMUCommandType; | ||
119 | + | ||
120 | +static const char *cmd_stringify[] = { | ||
121 | + [SMMU_CMD_PREFETCH_CONFIG] = "SMMU_CMD_PREFETCH_CONFIG", | ||
122 | + [SMMU_CMD_PREFETCH_ADDR] = "SMMU_CMD_PREFETCH_ADDR", | ||
123 | + [SMMU_CMD_CFGI_STE] = "SMMU_CMD_CFGI_STE", | ||
124 | + [SMMU_CMD_CFGI_STE_RANGE] = "SMMU_CMD_CFGI_STE_RANGE", | ||
125 | + [SMMU_CMD_CFGI_CD] = "SMMU_CMD_CFGI_CD", | ||
126 | + [SMMU_CMD_CFGI_CD_ALL] = "SMMU_CMD_CFGI_CD_ALL", | ||
127 | + [SMMU_CMD_CFGI_ALL] = "SMMU_CMD_CFGI_ALL", | ||
128 | + [SMMU_CMD_TLBI_NH_ALL] = "SMMU_CMD_TLBI_NH_ALL", | ||
129 | + [SMMU_CMD_TLBI_NH_ASID] = "SMMU_CMD_TLBI_NH_ASID", | ||
130 | + [SMMU_CMD_TLBI_NH_VA] = "SMMU_CMD_TLBI_NH_VA", | ||
131 | + [SMMU_CMD_TLBI_NH_VAA] = "SMMU_CMD_TLBI_NH_VAA", | ||
132 | + [SMMU_CMD_TLBI_EL3_ALL] = "SMMU_CMD_TLBI_EL3_ALL", | ||
133 | + [SMMU_CMD_TLBI_EL3_VA] = "SMMU_CMD_TLBI_EL3_VA", | ||
134 | + [SMMU_CMD_TLBI_EL2_ALL] = "SMMU_CMD_TLBI_EL2_ALL", | ||
135 | + [SMMU_CMD_TLBI_EL2_ASID] = "SMMU_CMD_TLBI_EL2_ASID", | ||
136 | + [SMMU_CMD_TLBI_EL2_VA] = "SMMU_CMD_TLBI_EL2_VA", | ||
137 | + [SMMU_CMD_TLBI_EL2_VAA] = "SMMU_CMD_TLBI_EL2_VAA", | ||
138 | + [SMMU_CMD_TLBI_S12_VMALL] = "SMMU_CMD_TLBI_S12_VMALL", | ||
139 | + [SMMU_CMD_TLBI_S2_IPA] = "SMMU_CMD_TLBI_S2_IPA", | ||
140 | + [SMMU_CMD_TLBI_NSNH_ALL] = "SMMU_CMD_TLBI_NSNH_ALL", | ||
141 | + [SMMU_CMD_ATC_INV] = "SMMU_CMD_ATC_INV", | ||
142 | + [SMMU_CMD_PRI_RESP] = "SMMU_CMD_PRI_RESP", | ||
143 | + [SMMU_CMD_RESUME] = "SMMU_CMD_RESUME", | ||
144 | + [SMMU_CMD_STALL_TERM] = "SMMU_CMD_STALL_TERM", | ||
145 | + [SMMU_CMD_SYNC] = "SMMU_CMD_SYNC", | ||
146 | +}; | ||
147 | + | ||
148 | +static inline const char *smmu_cmd_string(SMMUCommandType type) | ||
149 | +{ | ||
150 | + if (type > SMMU_CMD_NONE && type < ARRAY_SIZE(cmd_stringify)) { | ||
151 | + return cmd_stringify[type] ? cmd_stringify[type] : "UNKNOWN"; | ||
152 | + } else { | ||
153 | + return "INVALID"; | ||
154 | + } | ||
155 | +} | ||
156 | + | ||
157 | +/* CMDQ fields */ | ||
158 | + | ||
159 | +typedef enum { | ||
160 | + SMMU_CERROR_NONE = 0, | ||
161 | + SMMU_CERROR_ILL, | ||
162 | + SMMU_CERROR_ABT, | ||
163 | + SMMU_CERROR_ATC_INV_SYNC, | ||
164 | +} SMMUCmdError; | ||
165 | + | ||
166 | +enum { /* Command completion notification */ | ||
167 | + CMD_SYNC_SIG_NONE, | ||
168 | + CMD_SYNC_SIG_IRQ, | ||
169 | + CMD_SYNC_SIG_SEV, | ||
170 | +}; | ||
171 | + | ||
172 | +#define CMD_TYPE(x) extract32((x)->word[0], 0 , 8) | ||
173 | +#define CMD_SSEC(x) extract32((x)->word[0], 10, 1) | ||
174 | +#define CMD_SSV(x) extract32((x)->word[0], 11, 1) | ||
175 | +#define CMD_RESUME_AC(x) extract32((x)->word[0], 12, 1) | ||
176 | +#define CMD_RESUME_AB(x) extract32((x)->word[0], 13, 1) | ||
177 | +#define CMD_SYNC_CS(x) extract32((x)->word[0], 12, 2) | ||
178 | +#define CMD_SSID(x) extract32((x)->word[0], 12, 20) | ||
179 | +#define CMD_SID(x) ((x)->word[1]) | ||
180 | +#define CMD_VMID(x) extract32((x)->word[1], 0 , 16) | ||
181 | +#define CMD_ASID(x) extract32((x)->word[1], 16, 16) | ||
182 | +#define CMD_RESUME_STAG(x) extract32((x)->word[2], 0 , 16) | ||
183 | +#define CMD_RESP(x) extract32((x)->word[2], 11, 2) | ||
184 | +#define CMD_LEAF(x) extract32((x)->word[2], 0 , 1) | ||
185 | +#define CMD_STE_RANGE(x) extract32((x)->word[2], 0 , 5) | ||
186 | +#define CMD_ADDR(x) ({ \ | ||
187 | + uint64_t high = (uint64_t)(x)->word[3]; \ | ||
188 | + uint64_t low = extract32((x)->word[2], 12, 20); \ | ||
189 | + uint64_t addr = high << 32 | (low << 12); \ | ||
190 | + addr; \ | ||
191 | + }) | ||
192 | + | ||
193 | +int smmuv3_cmdq_consume(SMMUv3State *s); | ||
194 | + | ||
195 | #endif | ||
196 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
197 | index XXXXXXX..XXXXXXX 100644 | ||
198 | --- a/hw/arm/smmuv3.c | ||
199 | +++ b/hw/arm/smmuv3.c | ||
200 | @@ -XXX,XX +XXX,XX @@ void smmuv3_write_gerrorn(SMMUv3State *s, uint32_t new_gerrorn) | ||
201 | trace_smmuv3_write_gerrorn(toggled & pending, s->gerrorn); | ||
202 | } | 105 | } |
203 | 106 | + | |
204 | +static inline MemTxResult queue_read(SMMUQueue *q, void *data) | 107 | +uint32_t HELPER(mve_uqshl)(CPUARMState *env, uint32_t n, uint32_t shift) |
205 | +{ | 108 | +{ |
206 | + dma_addr_t addr = Q_CONS_ENTRY(q); | 109 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); |
207 | + | 110 | +} |
208 | + return dma_memory_read(&address_space_memory, addr, data, q->entry_size); | 111 | + |
209 | +} | 112 | +uint32_t HELPER(mve_sqshl)(CPUARMState *env, uint32_t n, uint32_t shift) |
210 | + | 113 | +{ |
211 | +static MemTxResult queue_write(SMMUQueue *q, void *data) | 114 | + return do_sqrshl_bhs(n, (int8_t)shift, 32, false, &env->QF); |
212 | +{ | 115 | +} |
213 | + dma_addr_t addr = Q_PROD_ENTRY(q); | 116 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
214 | + MemTxResult ret; | 117 | index XXXXXXX..XXXXXXX 100644 |
215 | + | 118 | --- a/target/arm/translate.c |
216 | + ret = dma_memory_write(&address_space_memory, addr, data, q->entry_size); | 119 | +++ b/target/arm/translate.c |
217 | + if (ret != MEMTX_OK) { | 120 | @@ -XXX,XX +XXX,XX @@ static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) |
218 | + return ret; | 121 | |
219 | + } | 122 | static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) |
220 | + | 123 | { |
221 | + queue_prod_incr(q); | 124 | - TCGv_i32 t = tcg_temp_new_i32(); |
222 | + return MEMTX_OK; | 125 | + TCGv_i32 t; |
223 | +} | 126 | |
224 | + | 127 | + /* Handle shift by the input size for the benefit of trans_SRSHR_ri */ |
225 | +void smmuv3_write_eventq(SMMUv3State *s, Evt *evt) | 128 | + if (sh == 32) { |
226 | +{ | 129 | + tcg_gen_movi_i32(d, 0); |
227 | + SMMUQueue *q = &s->eventq; | ||
228 | + | ||
229 | + if (!smmuv3_eventq_enabled(s)) { | ||
230 | + return; | 130 | + return; |
231 | + } | 131 | + } |
232 | + | 132 | + t = tcg_temp_new_i32(); |
233 | + if (smmuv3_q_full(q)) { | 133 | tcg_gen_extract_i32(t, a, sh - 1, 1); |
134 | tcg_gen_sari_i32(d, a, sh); | ||
135 | tcg_gen_add_i32(d, d, t); | ||
136 | @@ -XXX,XX +XXX,XX @@ static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) | ||
137 | |||
138 | static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) | ||
139 | { | ||
140 | - TCGv_i32 t = tcg_temp_new_i32(); | ||
141 | + TCGv_i32 t; | ||
142 | |||
143 | + /* Handle shift by the input size for the benefit of trans_URSHR_ri */ | ||
144 | + if (sh == 32) { | ||
145 | + tcg_gen_extract_i32(d, a, sh - 1, 1); | ||
234 | + return; | 146 | + return; |
235 | + } | 147 | + } |
236 | + | 148 | + t = tcg_temp_new_i32(); |
237 | + queue_write(q, evt); | 149 | tcg_gen_extract_i32(t, a, sh - 1, 1); |
238 | + | 150 | tcg_gen_shri_i32(d, a, sh); |
239 | + if (smmuv3_q_empty(q)) { | 151 | tcg_gen_add_i32(d, d, t); |
240 | + smmuv3_trigger_irq(s, SMMU_IRQ_EVTQ, 0); | 152 | @@ -XXX,XX +XXX,XX @@ static bool trans_SQRSHRL48_rr(DisasContext *s, arg_mve_shl_rr *a) |
241 | + } | 153 | return do_mve_shl_rr(s, a, gen_helper_mve_sqrshrl48); |
242 | +} | ||
243 | + | ||
244 | static void smmuv3_init_regs(SMMUv3State *s) | ||
245 | { | ||
246 | /** | ||
247 | @@ -XXX,XX +XXX,XX @@ static void smmuv3_init_regs(SMMUv3State *s) | ||
248 | s->sid_split = 0; | ||
249 | } | 154 | } |
250 | 155 | ||
251 | +int smmuv3_cmdq_consume(SMMUv3State *s) | 156 | +static bool do_mve_sh_ri(DisasContext *s, arg_mve_sh_ri *a, ShiftImmFn *fn) |
252 | +{ | 157 | +{ |
253 | + SMMUCmdError cmd_error = SMMU_CERROR_NONE; | 158 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { |
254 | + SMMUQueue *q = &s->cmdq; | 159 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ |
255 | + SMMUCommandType type = 0; | 160 | + return false; |
256 | + | 161 | + } |
257 | + if (!smmuv3_cmdq_enabled(s)) { | 162 | + if (!dc_isar_feature(aa32_mve, s) || |
258 | + return 0; | 163 | + !arm_dc_feature(s, ARM_FEATURE_M_MAIN) || |
259 | + } | 164 | + a->rda == 13 || a->rda == 15) { |
260 | + /* | 165 | + /* These rda cases are UNPREDICTABLE; we choose to UNDEF */ |
261 | + * some commands depend on register values, typically CR0. In case those | 166 | + unallocated_encoding(s); |
262 | + * register values change while handling the command, spec says it | 167 | + return true; |
263 | + * is UNPREDICTABLE whether the command is interpreted under the new | 168 | + } |
264 | + * or old value. | 169 | + |
265 | + */ | 170 | + if (a->shim == 0) { |
266 | + | 171 | + a->shim = 32; |
267 | + while (!smmuv3_q_empty(q)) { | 172 | + } |
268 | + uint32_t pending = s->gerror ^ s->gerrorn; | 173 | + fn(cpu_R[a->rda], cpu_R[a->rda], a->shim); |
269 | + Cmd cmd; | 174 | + |
270 | + | 175 | + return true; |
271 | + trace_smmuv3_cmdq_consume(Q_PROD(q), Q_CONS(q), | 176 | +} |
272 | + Q_PROD_WRAP(q), Q_CONS_WRAP(q)); | 177 | + |
273 | + | 178 | +static bool trans_URSHR_ri(DisasContext *s, arg_mve_sh_ri *a) |
274 | + if (FIELD_EX32(pending, GERROR, CMDQ_ERR)) { | 179 | +{ |
275 | + break; | 180 | + return do_mve_sh_ri(s, a, gen_urshr32_i32); |
276 | + } | 181 | +} |
277 | + | 182 | + |
278 | + if (queue_read(q, &cmd) != MEMTX_OK) { | 183 | +static bool trans_SRSHR_ri(DisasContext *s, arg_mve_sh_ri *a) |
279 | + cmd_error = SMMU_CERROR_ABT; | 184 | +{ |
280 | + break; | 185 | + return do_mve_sh_ri(s, a, gen_srshr32_i32); |
281 | + } | 186 | +} |
282 | + | 187 | + |
283 | + type = CMD_TYPE(&cmd); | 188 | +static void gen_mve_sqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) |
284 | + | 189 | +{ |
285 | + trace_smmuv3_cmdq_opcode(smmu_cmd_string(type)); | 190 | + gen_helper_mve_sqshl(r, cpu_env, n, tcg_constant_i32(shift)); |
286 | + | 191 | +} |
287 | + switch (type) { | 192 | + |
288 | + case SMMU_CMD_SYNC: | 193 | +static bool trans_SQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) |
289 | + if (CMD_SYNC_CS(&cmd) & CMD_SYNC_SIG_IRQ) { | 194 | +{ |
290 | + smmuv3_trigger_irq(s, SMMU_IRQ_CMD_SYNC, 0); | 195 | + return do_mve_sh_ri(s, a, gen_mve_sqshl); |
291 | + } | 196 | +} |
292 | + break; | 197 | + |
293 | + case SMMU_CMD_PREFETCH_CONFIG: | 198 | +static void gen_mve_uqshl(TCGv_i32 r, TCGv_i32 n, int32_t shift) |
294 | + case SMMU_CMD_PREFETCH_ADDR: | 199 | +{ |
295 | + case SMMU_CMD_CFGI_STE: | 200 | + gen_helper_mve_uqshl(r, cpu_env, n, tcg_constant_i32(shift)); |
296 | + case SMMU_CMD_CFGI_STE_RANGE: /* same as SMMU_CMD_CFGI_ALL */ | 201 | +} |
297 | + case SMMU_CMD_CFGI_CD: | 202 | + |
298 | + case SMMU_CMD_CFGI_CD_ALL: | 203 | +static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) |
299 | + case SMMU_CMD_TLBI_NH_ALL: | 204 | +{ |
300 | + case SMMU_CMD_TLBI_NH_ASID: | 205 | + return do_mve_sh_ri(s, a, gen_mve_uqshl); |
301 | + case SMMU_CMD_TLBI_NH_VA: | 206 | +} |
302 | + case SMMU_CMD_TLBI_NH_VAA: | 207 | + |
303 | + case SMMU_CMD_TLBI_EL3_ALL: | 208 | /* |
304 | + case SMMU_CMD_TLBI_EL3_VA: | 209 | * Multiply and multiply accumulate |
305 | + case SMMU_CMD_TLBI_EL2_ALL: | 210 | */ |
306 | + case SMMU_CMD_TLBI_EL2_ASID: | ||
307 | + case SMMU_CMD_TLBI_EL2_VA: | ||
308 | + case SMMU_CMD_TLBI_EL2_VAA: | ||
309 | + case SMMU_CMD_TLBI_S12_VMALL: | ||
310 | + case SMMU_CMD_TLBI_S2_IPA: | ||
311 | + case SMMU_CMD_TLBI_NSNH_ALL: | ||
312 | + case SMMU_CMD_ATC_INV: | ||
313 | + case SMMU_CMD_PRI_RESP: | ||
314 | + case SMMU_CMD_RESUME: | ||
315 | + case SMMU_CMD_STALL_TERM: | ||
316 | + trace_smmuv3_unhandled_cmd(type); | ||
317 | + break; | ||
318 | + default: | ||
319 | + cmd_error = SMMU_CERROR_ILL; | ||
320 | + qemu_log_mask(LOG_GUEST_ERROR, | ||
321 | + "Illegal command type: %d\n", CMD_TYPE(&cmd)); | ||
322 | + break; | ||
323 | + } | ||
324 | + if (cmd_error) { | ||
325 | + break; | ||
326 | + } | ||
327 | + /* | ||
328 | + * We only increment the cons index after the completion of | ||
329 | + * the command. We do that because the SYNC returns immediately | ||
330 | + * and does not check the completion of previous commands | ||
331 | + */ | ||
332 | + queue_cons_incr(q); | ||
333 | + } | ||
334 | + | ||
335 | + if (cmd_error) { | ||
336 | + trace_smmuv3_cmdq_consume_error(smmu_cmd_string(type), cmd_error); | ||
337 | + smmu_write_cmdq_err(s, cmd_error); | ||
338 | + smmuv3_trigger_irq(s, SMMU_IRQ_GERROR, R_GERROR_CMDQ_ERR_MASK); | ||
339 | + } | ||
340 | + | ||
341 | + trace_smmuv3_cmdq_consume_out(Q_PROD(q), Q_CONS(q), | ||
342 | + Q_PROD_WRAP(q), Q_CONS_WRAP(q)); | ||
343 | + | ||
344 | + return 0; | ||
345 | +} | ||
346 | + | ||
347 | static MemTxResult smmu_write_mmio(void *opaque, hwaddr offset, uint64_t data, | ||
348 | unsigned size, MemTxAttrs attrs) | ||
349 | { | ||
350 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
351 | index XXXXXXX..XXXXXXX 100644 | ||
352 | --- a/hw/arm/trace-events | ||
353 | +++ b/hw/arm/trace-events | ||
354 | @@ -XXX,XX +XXX,XX @@ smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: | ||
355 | smmuv3_trigger_irq(int irq) "irq=%d" | ||
356 | smmuv3_write_gerror(uint32_t toggled, uint32_t gerror) "toggled=0x%x, new GERROR=0x%x" | ||
357 | smmuv3_write_gerrorn(uint32_t acked, uint32_t gerrorn) "acked=0x%x, new GERRORN=0x%x" | ||
358 | +smmuv3_unhandled_cmd(uint32_t type) "Unhandled command type=%d" | ||
359 | +smmuv3_cmdq_consume(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "prod=%d cons=%d prod.wrap=%d cons.wrap=%d" | ||
360 | +smmuv3_cmdq_opcode(const char *opcode) "<--- %s" | ||
361 | +smmuv3_cmdq_consume_out(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "prod:%d, cons:%d, prod_wrap:%d, cons_wrap:%d " | ||
362 | +smmuv3_cmdq_consume_error(const char *cmd_name, uint8_t cmd_error) "Error on %s command execution: %d" | ||
363 | -- | 211 | -- |
364 | 2.17.0 | 212 | 2.20.1 |
365 | 213 | ||
366 | 214 | diff view generated by jsdifflib |
1 | From: Eric Auger <eric.auger@redhat.com> | 1 | Implement the MVE shifts by register, which perform |
---|---|---|---|
2 | shifts on a single general-purpose register. | ||
2 | 3 | ||
3 | Let's introduce a helper function aiming at recording an | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | event in the event queue. | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20210628135835.6690-19-peter.maydell@linaro.org | ||
7 | --- | ||
8 | target/arm/helper-mve.h | 2 ++ | ||
9 | target/arm/translate.h | 1 + | ||
10 | target/arm/t32.decode | 18 ++++++++++++++---- | ||
11 | target/arm/mve_helper.c | 10 ++++++++++ | ||
12 | target/arm/translate.c | 30 ++++++++++++++++++++++++++++++ | ||
13 | 5 files changed, 57 insertions(+), 4 deletions(-) | ||
5 | 14 | ||
6 | Signed-off-by: Eric Auger <eric.auger@redhat.com> | 15 | diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h |
7 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
8 | Message-id: 1524665762-31355-9-git-send-email-eric.auger@redhat.com | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | hw/arm/smmuv3-internal.h | 148 ++++++++++++++++++++++++++++++++++++++- | ||
12 | hw/arm/smmuv3.c | 108 ++++++++++++++++++++++++++-- | ||
13 | hw/arm/trace-events | 1 + | ||
14 | 3 files changed, 249 insertions(+), 8 deletions(-) | ||
15 | |||
16 | diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h | ||
17 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/hw/arm/smmuv3-internal.h | 17 | --- a/target/arm/helper-mve.h |
19 | +++ b/hw/arm/smmuv3-internal.h | 18 | +++ b/target/arm/helper-mve.h |
20 | @@ -XXX,XX +XXX,XX @@ static inline void smmu_write_cmdq_err(SMMUv3State *s, uint32_t err_type) | 19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqrshll48, TCG_CALL_NO_RWG, i64, env, i64, i32) |
21 | s->cmdq.cons = FIELD_DP32(s->cmdq.cons, CMDQ_CONS, ERR, err_type); | 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); | ||
22 | } | 87 | } |
23 | |||
24 | -void smmuv3_write_eventq(SMMUv3State *s, Evt *evt); | ||
25 | - | ||
26 | /* Commands */ | ||
27 | |||
28 | typedef enum SMMUCommandType { | ||
29 | @@ -XXX,XX +XXX,XX @@ enum { /* Command completion notification */ | ||
30 | |||
31 | #define SMMU_FEATURE_2LVL_STE (1 << 0) | ||
32 | |||
33 | +/* Events */ | ||
34 | + | 88 | + |
35 | +typedef enum SMMUEventType { | 89 | +uint32_t HELPER(mve_uqrshl)(CPUARMState *env, uint32_t n, uint32_t shift) |
36 | + SMMU_EVT_OK = 0x00, | ||
37 | + SMMU_EVT_F_UUT , | ||
38 | + SMMU_EVT_C_BAD_STREAMID , | ||
39 | + SMMU_EVT_F_STE_FETCH , | ||
40 | + SMMU_EVT_C_BAD_STE , | ||
41 | + SMMU_EVT_F_BAD_ATS_TREQ , | ||
42 | + SMMU_EVT_F_STREAM_DISABLED , | ||
43 | + SMMU_EVT_F_TRANS_FORBIDDEN , | ||
44 | + SMMU_EVT_C_BAD_SUBSTREAMID , | ||
45 | + SMMU_EVT_F_CD_FETCH , | ||
46 | + SMMU_EVT_C_BAD_CD , | ||
47 | + SMMU_EVT_F_WALK_EABT , | ||
48 | + SMMU_EVT_F_TRANSLATION = 0x10, | ||
49 | + SMMU_EVT_F_ADDR_SIZE , | ||
50 | + SMMU_EVT_F_ACCESS , | ||
51 | + SMMU_EVT_F_PERMISSION , | ||
52 | + SMMU_EVT_F_TLB_CONFLICT = 0x20, | ||
53 | + SMMU_EVT_F_CFG_CONFLICT , | ||
54 | + SMMU_EVT_E_PAGE_REQ = 0x24, | ||
55 | +} SMMUEventType; | ||
56 | + | ||
57 | +static const char *event_stringify[] = { | ||
58 | + [SMMU_EVT_OK] = "SMMU_EVT_OK", | ||
59 | + [SMMU_EVT_F_UUT] = "SMMU_EVT_F_UUT", | ||
60 | + [SMMU_EVT_C_BAD_STREAMID] = "SMMU_EVT_C_BAD_STREAMID", | ||
61 | + [SMMU_EVT_F_STE_FETCH] = "SMMU_EVT_F_STE_FETCH", | ||
62 | + [SMMU_EVT_C_BAD_STE] = "SMMU_EVT_C_BAD_STE", | ||
63 | + [SMMU_EVT_F_BAD_ATS_TREQ] = "SMMU_EVT_F_BAD_ATS_TREQ", | ||
64 | + [SMMU_EVT_F_STREAM_DISABLED] = "SMMU_EVT_F_STREAM_DISABLED", | ||
65 | + [SMMU_EVT_F_TRANS_FORBIDDEN] = "SMMU_EVT_F_TRANS_FORBIDDEN", | ||
66 | + [SMMU_EVT_C_BAD_SUBSTREAMID] = "SMMU_EVT_C_BAD_SUBSTREAMID", | ||
67 | + [SMMU_EVT_F_CD_FETCH] = "SMMU_EVT_F_CD_FETCH", | ||
68 | + [SMMU_EVT_C_BAD_CD] = "SMMU_EVT_C_BAD_CD", | ||
69 | + [SMMU_EVT_F_WALK_EABT] = "SMMU_EVT_F_WALK_EABT", | ||
70 | + [SMMU_EVT_F_TRANSLATION] = "SMMU_EVT_F_TRANSLATION", | ||
71 | + [SMMU_EVT_F_ADDR_SIZE] = "SMMU_EVT_F_ADDR_SIZE", | ||
72 | + [SMMU_EVT_F_ACCESS] = "SMMU_EVT_F_ACCESS", | ||
73 | + [SMMU_EVT_F_PERMISSION] = "SMMU_EVT_F_PERMISSION", | ||
74 | + [SMMU_EVT_F_TLB_CONFLICT] = "SMMU_EVT_F_TLB_CONFLICT", | ||
75 | + [SMMU_EVT_F_CFG_CONFLICT] = "SMMU_EVT_F_CFG_CONFLICT", | ||
76 | + [SMMU_EVT_E_PAGE_REQ] = "SMMU_EVT_E_PAGE_REQ", | ||
77 | +}; | ||
78 | + | ||
79 | +static inline const char *smmu_event_string(SMMUEventType type) | ||
80 | +{ | 90 | +{ |
81 | + if (type < ARRAY_SIZE(event_stringify)) { | 91 | + return do_uqrshl_bhs(n, (int8_t)shift, 32, true, &env->QF); |
82 | + return event_stringify[type] ? event_stringify[type] : "UNKNOWN"; | ||
83 | + } else { | ||
84 | + return "INVALID"; | ||
85 | + } | ||
86 | +} | 92 | +} |
87 | + | 93 | + |
88 | +/* Encode an event record */ | 94 | +uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) |
89 | +typedef struct SMMUEventInfo { | 95 | +{ |
90 | + SMMUEventType type; | 96 | + return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); |
91 | + uint32_t sid; | 97 | +} |
92 | + bool recorded; | 98 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
93 | + bool record_trans_faults; | ||
94 | + union { | ||
95 | + struct { | ||
96 | + uint32_t ssid; | ||
97 | + bool ssv; | ||
98 | + dma_addr_t addr; | ||
99 | + bool rnw; | ||
100 | + bool pnu; | ||
101 | + bool ind; | ||
102 | + } f_uut; | ||
103 | + struct SSIDInfo { | ||
104 | + uint32_t ssid; | ||
105 | + bool ssv; | ||
106 | + } c_bad_streamid; | ||
107 | + struct SSIDAddrInfo { | ||
108 | + uint32_t ssid; | ||
109 | + bool ssv; | ||
110 | + dma_addr_t addr; | ||
111 | + } f_ste_fetch; | ||
112 | + struct SSIDInfo c_bad_ste; | ||
113 | + struct { | ||
114 | + dma_addr_t addr; | ||
115 | + bool rnw; | ||
116 | + } f_transl_forbidden; | ||
117 | + struct { | ||
118 | + uint32_t ssid; | ||
119 | + } c_bad_substream; | ||
120 | + struct SSIDAddrInfo f_cd_fetch; | ||
121 | + struct SSIDInfo c_bad_cd; | ||
122 | + struct FullInfo { | ||
123 | + bool stall; | ||
124 | + uint16_t stag; | ||
125 | + uint32_t ssid; | ||
126 | + bool ssv; | ||
127 | + bool s2; | ||
128 | + dma_addr_t addr; | ||
129 | + bool rnw; | ||
130 | + bool pnu; | ||
131 | + bool ind; | ||
132 | + uint8_t class; | ||
133 | + dma_addr_t addr2; | ||
134 | + } f_walk_eabt; | ||
135 | + struct FullInfo f_translation; | ||
136 | + struct FullInfo f_addr_size; | ||
137 | + struct FullInfo f_access; | ||
138 | + struct FullInfo f_permission; | ||
139 | + struct SSIDInfo f_cfg_conflict; | ||
140 | + /** | ||
141 | + * not supported yet: | ||
142 | + * F_BAD_ATS_TREQ | ||
143 | + * F_BAD_ATS_TREQ | ||
144 | + * F_TLB_CONFLICT | ||
145 | + * E_PAGE_REQUEST | ||
146 | + * IMPDEF_EVENTn | ||
147 | + */ | ||
148 | + } u; | ||
149 | +} SMMUEventInfo; | ||
150 | + | ||
151 | +/* EVTQ fields */ | ||
152 | + | ||
153 | +#define EVT_Q_OVERFLOW (1 << 31) | ||
154 | + | ||
155 | +#define EVT_SET_TYPE(x, v) deposit32((x)->word[0], 0 , 8 , v) | ||
156 | +#define EVT_SET_SSV(x, v) deposit32((x)->word[0], 11, 1 , v) | ||
157 | +#define EVT_SET_SSID(x, v) deposit32((x)->word[0], 12, 20, v) | ||
158 | +#define EVT_SET_SID(x, v) ((x)->word[1] = v) | ||
159 | +#define EVT_SET_STAG(x, v) deposit32((x)->word[2], 0 , 16, v) | ||
160 | +#define EVT_SET_STALL(x, v) deposit32((x)->word[2], 31, 1 , v) | ||
161 | +#define EVT_SET_PNU(x, v) deposit32((x)->word[3], 1 , 1 , v) | ||
162 | +#define EVT_SET_IND(x, v) deposit32((x)->word[3], 2 , 1 , v) | ||
163 | +#define EVT_SET_RNW(x, v) deposit32((x)->word[3], 3 , 1 , v) | ||
164 | +#define EVT_SET_S2(x, v) deposit32((x)->word[3], 7 , 1 , v) | ||
165 | +#define EVT_SET_CLASS(x, v) deposit32((x)->word[3], 8 , 2 , v) | ||
166 | +#define EVT_SET_ADDR(x, addr) \ | ||
167 | + do { \ | ||
168 | + (x)->word[5] = (uint32_t)(addr >> 32); \ | ||
169 | + (x)->word[4] = (uint32_t)(addr & 0xffffffff); \ | ||
170 | + } while (0) | ||
171 | +#define EVT_SET_ADDR2(x, addr) \ | ||
172 | + do { \ | ||
173 | + deposit32((x)->word[7], 3, 29, addr >> 16); \ | ||
174 | + deposit32((x)->word[7], 0, 16, addr & 0xffff);\ | ||
175 | + } while (0) | ||
176 | + | ||
177 | +void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *event); | ||
178 | + | ||
179 | #endif | ||
180 | diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c | ||
181 | index XXXXXXX..XXXXXXX 100644 | 99 | index XXXXXXX..XXXXXXX 100644 |
182 | --- a/hw/arm/smmuv3.c | 100 | --- a/target/arm/translate.c |
183 | +++ b/hw/arm/smmuv3.c | 101 | +++ b/target/arm/translate.c |
184 | @@ -XXX,XX +XXX,XX @@ static MemTxResult queue_write(SMMUQueue *q, void *data) | 102 | @@ -XXX,XX +XXX,XX @@ static bool trans_UQSHL_ri(DisasContext *s, arg_mve_sh_ri *a) |
185 | return MEMTX_OK; | 103 | return do_mve_sh_ri(s, a, gen_mve_uqshl); |
186 | } | 104 | } |
187 | 105 | ||
188 | -void smmuv3_write_eventq(SMMUv3State *s, Evt *evt) | 106 | +static bool do_mve_sh_rr(DisasContext *s, arg_mve_sh_rr *a, ShiftFn *fn) |
189 | +static MemTxResult smmuv3_write_eventq(SMMUv3State *s, Evt *evt) | 107 | +{ |
190 | { | 108 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { |
191 | SMMUQueue *q = &s->eventq; | 109 | + /* Decode falls through to ORR/MOV UNPREDICTABLE handling */ |
192 | + MemTxResult r; | 110 | + return false; |
193 | + | 111 | + } |
194 | + if (!smmuv3_eventq_enabled(s)) { | 112 | + if (!dc_isar_feature(aa32_mve, s) || |
195 | + return MEMTX_ERROR; | 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; | ||
196 | + } | 119 | + } |
197 | + | 120 | + |
198 | + if (smmuv3_q_full(q)) { | 121 | + /* The helper takes care of the sign-extension of the low 8 bits of Rm */ |
199 | + return MEMTX_ERROR; | 122 | + fn(cpu_R[a->rda], cpu_env, cpu_R[a->rda], cpu_R[a->rm]); |
200 | + } | 123 | + return true; |
201 | + | ||
202 | + r = queue_write(q, evt); | ||
203 | + if (r != MEMTX_OK) { | ||
204 | + return r; | ||
205 | + } | ||
206 | + | ||
207 | + if (smmuv3_q_empty(q)) { | ||
208 | + smmuv3_trigger_irq(s, SMMU_IRQ_EVTQ, 0); | ||
209 | + } | ||
210 | + return MEMTX_OK; | ||
211 | +} | 124 | +} |
212 | + | 125 | + |
213 | +void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *info) | 126 | +static bool trans_SQRSHR_rr(DisasContext *s, arg_mve_sh_rr *a) |
214 | +{ | 127 | +{ |
215 | + Evt evt; | 128 | + return do_mve_sh_rr(s, a, gen_helper_mve_sqrshr); |
216 | + MemTxResult r; | 129 | +} |
217 | |||
218 | if (!smmuv3_eventq_enabled(s)) { | ||
219 | return; | ||
220 | } | ||
221 | |||
222 | - if (smmuv3_q_full(q)) { | ||
223 | + EVT_SET_TYPE(&evt, info->type); | ||
224 | + EVT_SET_SID(&evt, info->sid); | ||
225 | + | 130 | + |
226 | + switch (info->type) { | 131 | +static bool trans_UQRSHL_rr(DisasContext *s, arg_mve_sh_rr *a) |
227 | + case SMMU_EVT_OK: | 132 | +{ |
228 | return; | 133 | + return do_mve_sh_rr(s, a, gen_helper_mve_uqrshl); |
229 | + case SMMU_EVT_F_UUT: | 134 | +} |
230 | + EVT_SET_SSID(&evt, info->u.f_uut.ssid); | 135 | + |
231 | + EVT_SET_SSV(&evt, info->u.f_uut.ssv); | 136 | /* |
232 | + EVT_SET_ADDR(&evt, info->u.f_uut.addr); | 137 | * Multiply and multiply accumulate |
233 | + EVT_SET_RNW(&evt, info->u.f_uut.rnw); | 138 | */ |
234 | + EVT_SET_PNU(&evt, info->u.f_uut.pnu); | ||
235 | + EVT_SET_IND(&evt, info->u.f_uut.ind); | ||
236 | + break; | ||
237 | + case SMMU_EVT_C_BAD_STREAMID: | ||
238 | + EVT_SET_SSID(&evt, info->u.c_bad_streamid.ssid); | ||
239 | + EVT_SET_SSV(&evt, info->u.c_bad_streamid.ssv); | ||
240 | + break; | ||
241 | + case SMMU_EVT_F_STE_FETCH: | ||
242 | + EVT_SET_SSID(&evt, info->u.f_ste_fetch.ssid); | ||
243 | + EVT_SET_SSV(&evt, info->u.f_ste_fetch.ssv); | ||
244 | + EVT_SET_ADDR(&evt, info->u.f_ste_fetch.addr); | ||
245 | + break; | ||
246 | + case SMMU_EVT_C_BAD_STE: | ||
247 | + EVT_SET_SSID(&evt, info->u.c_bad_ste.ssid); | ||
248 | + EVT_SET_SSV(&evt, info->u.c_bad_ste.ssv); | ||
249 | + break; | ||
250 | + case SMMU_EVT_F_STREAM_DISABLED: | ||
251 | + break; | ||
252 | + case SMMU_EVT_F_TRANS_FORBIDDEN: | ||
253 | + EVT_SET_ADDR(&evt, info->u.f_transl_forbidden.addr); | ||
254 | + EVT_SET_RNW(&evt, info->u.f_transl_forbidden.rnw); | ||
255 | + break; | ||
256 | + case SMMU_EVT_C_BAD_SUBSTREAMID: | ||
257 | + EVT_SET_SSID(&evt, info->u.c_bad_substream.ssid); | ||
258 | + break; | ||
259 | + case SMMU_EVT_F_CD_FETCH: | ||
260 | + EVT_SET_SSID(&evt, info->u.f_cd_fetch.ssid); | ||
261 | + EVT_SET_SSV(&evt, info->u.f_cd_fetch.ssv); | ||
262 | + EVT_SET_ADDR(&evt, info->u.f_cd_fetch.addr); | ||
263 | + break; | ||
264 | + case SMMU_EVT_C_BAD_CD: | ||
265 | + EVT_SET_SSID(&evt, info->u.c_bad_cd.ssid); | ||
266 | + EVT_SET_SSV(&evt, info->u.c_bad_cd.ssv); | ||
267 | + break; | ||
268 | + case SMMU_EVT_F_WALK_EABT: | ||
269 | + case SMMU_EVT_F_TRANSLATION: | ||
270 | + case SMMU_EVT_F_ADDR_SIZE: | ||
271 | + case SMMU_EVT_F_ACCESS: | ||
272 | + case SMMU_EVT_F_PERMISSION: | ||
273 | + EVT_SET_STALL(&evt, info->u.f_walk_eabt.stall); | ||
274 | + EVT_SET_STAG(&evt, info->u.f_walk_eabt.stag); | ||
275 | + EVT_SET_SSID(&evt, info->u.f_walk_eabt.ssid); | ||
276 | + EVT_SET_SSV(&evt, info->u.f_walk_eabt.ssv); | ||
277 | + EVT_SET_S2(&evt, info->u.f_walk_eabt.s2); | ||
278 | + EVT_SET_ADDR(&evt, info->u.f_walk_eabt.addr); | ||
279 | + EVT_SET_RNW(&evt, info->u.f_walk_eabt.rnw); | ||
280 | + EVT_SET_PNU(&evt, info->u.f_walk_eabt.pnu); | ||
281 | + EVT_SET_IND(&evt, info->u.f_walk_eabt.ind); | ||
282 | + EVT_SET_CLASS(&evt, info->u.f_walk_eabt.class); | ||
283 | + EVT_SET_ADDR2(&evt, info->u.f_walk_eabt.addr2); | ||
284 | + break; | ||
285 | + case SMMU_EVT_F_CFG_CONFLICT: | ||
286 | + EVT_SET_SSID(&evt, info->u.f_cfg_conflict.ssid); | ||
287 | + EVT_SET_SSV(&evt, info->u.f_cfg_conflict.ssv); | ||
288 | + break; | ||
289 | + /* rest is not implemented */ | ||
290 | + case SMMU_EVT_F_BAD_ATS_TREQ: | ||
291 | + case SMMU_EVT_F_TLB_CONFLICT: | ||
292 | + case SMMU_EVT_E_PAGE_REQ: | ||
293 | + default: | ||
294 | + g_assert_not_reached(); | ||
295 | } | ||
296 | |||
297 | - queue_write(q, evt); | ||
298 | - | ||
299 | - if (smmuv3_q_empty(q)) { | ||
300 | - smmuv3_trigger_irq(s, SMMU_IRQ_EVTQ, 0); | ||
301 | + trace_smmuv3_record_event(smmu_event_string(info->type), info->sid); | ||
302 | + r = smmuv3_write_eventq(s, &evt); | ||
303 | + if (r != MEMTX_OK) { | ||
304 | + smmuv3_trigger_irq(s, SMMU_IRQ_GERROR, R_GERROR_EVENTQ_ABT_ERR_MASK); | ||
305 | } | ||
306 | + info->recorded = true; | ||
307 | } | ||
308 | |||
309 | static void smmuv3_init_regs(SMMUv3State *s) | ||
310 | diff --git a/hw/arm/trace-events b/hw/arm/trace-events | ||
311 | index XXXXXXX..XXXXXXX 100644 | ||
312 | --- a/hw/arm/trace-events | ||
313 | +++ b/hw/arm/trace-events | ||
314 | @@ -XXX,XX +XXX,XX @@ smmuv3_write_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: | ||
315 | smmuv3_write_mmio_idr(uint64_t addr, uint64_t val) "write to RO/Unimpl reg 0x%lx val64:0x%lx" | ||
316 | smmuv3_write_mmio_evtq_cons_bef_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "Before clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | ||
317 | smmuv3_write_mmio_evtq_cons_after_clear(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "after clearing interrupt prod:0x%x cons:0x%x prod.w:%d cons.w:%d" | ||
318 | +smmuv3_record_event(const char *type, uint32_t sid) "%s sid=%d" | ||
319 | -- | 139 | -- |
320 | 2.17.0 | 140 | 2.20.1 |
321 | 141 | ||
322 | 142 | diff view generated by jsdifflib |