1 | Arm patch queue -- these are all bug fix patches but we might | 1 | Most of this is the Neon decodetree patches, followed by Edgar's versal cleanups. |
---|---|---|---|
2 | as well put them in to rc0... | ||
3 | 2 | ||
4 | thanks | 3 | thanks |
5 | -- PMM | 4 | -- PMM |
6 | 5 | ||
7 | The following changes since commit 2c8cfc0b52b5a4d123c26c0b5fdf941be24805be: | ||
8 | 6 | ||
9 | Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging (2018-03-19 11:44:26 +0000) | 7 | The following changes since commit 2ef486e76d64436be90f7359a3071fb2a56ce835: |
8 | |||
9 | Merge remote-tracking branch 'remotes/marcel/tags/rdma-pull-request' into staging (2020-05-03 14:12:56 +0100) | ||
10 | 10 | ||
11 | are available in the Git repository at: | 11 | are available in the Git repository at: |
12 | 12 | ||
13 | git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180319 | 13 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200504 |
14 | 14 | ||
15 | for you to fetch changes up to ff72cb6b46b95bb530787add5277c211af3d31c6: | 15 | for you to fetch changes up to 9aefc6cf9b73f66062d2f914a0136756e7a28211: |
16 | 16 | ||
17 | hw/arm/raspi: Provide spin-loop code for AArch64 CPUs (2018-03-19 18:23:24 +0000) | 17 | target/arm: Move gen_ function typedefs to translate.h (2020-05-04 12:59:26 +0100) |
18 | 18 | ||
19 | ---------------------------------------------------------------- | 19 | ---------------------------------------------------------------- |
20 | target-arm queue: | 20 | target-arm queue: |
21 | * fsl-imx6: Fix incorrect Ethernet interrupt defines | 21 | * Start of conversion of Neon insns to decodetree |
22 | * dump: Update correct kdump phys_base field for AArch64 | 22 | * versal board: support SD and RTC |
23 | * char: i.MX: Add support for "TX complete" interrupt | 23 | * Implement ARMv8.2-TTS2UXN |
24 | * bcm2836/raspi: Fix various bugs resulting in panics trying | 24 | * Make VQDMULL undefined when U=1 |
25 | to boot a Debian Linux kernel on raspi3 | 25 | * Some minor code cleanups |
26 | 26 | ||
27 | ---------------------------------------------------------------- | 27 | ---------------------------------------------------------------- |
28 | Andrey Smirnov (2): | 28 | Edgar E. Iglesias (11): |
29 | char: i.MX: Simplify imx_update() | 29 | hw/arm: versal: Remove inclusion of arm_gicv3_common.h |
30 | char: i.MX: Add support for "TX complete" interrupt | 30 | hw/arm: versal: Move misplaced comment |
31 | hw/arm: versal-virt: Fix typo xlnx-ve -> xlnx-versal | ||
32 | hw/arm: versal: Embed the UARTs into the SoC type | ||
33 | hw/arm: versal: Embed the GEMs into the SoC type | ||
34 | hw/arm: versal: Embed the ADMAs into the SoC type | ||
35 | hw/arm: versal: Embed the APUs into the SoC type | ||
36 | hw/arm: versal: Add support for SD | ||
37 | hw/arm: versal: Add support for the RTC | ||
38 | hw/arm: versal-virt: Add support for SD | ||
39 | hw/arm: versal-virt: Add support for the RTC | ||
31 | 40 | ||
32 | Guenter Roeck (1): | 41 | Fredrik Strupe (1): |
33 | fsl-imx6: Swap Ethernet interrupt defines | 42 | target/arm: Make VQDMULL undefined when U=1 |
34 | 43 | ||
35 | Peter Maydell (9): | 44 | Peter Maydell (25): |
36 | hw/arm/raspi: Don't do board-setup or secure-boot for raspi3 | 45 | target/arm: Don't use a TLB for ARMMMUIdx_Stage2 |
37 | hw/arm/boot: assert that secure_boot and secure_board_setup are false for AArch64 | 46 | target/arm: Use enum constant in get_phys_addr_lpae() call |
38 | hw/arm/boot: If booting a kernel in EL2, set SCR_EL3.HCE | 47 | target/arm: Add new 's1_is_el0' argument to get_phys_addr_lpae() |
39 | hw/arm/bcm2386: Fix parent type of bcm2386 | 48 | target/arm: Implement ARMv8.2-TTS2UXN |
40 | hw/arm/bcm2836: Rename bcm2836 type/struct to bcm283x | 49 | target/arm: Use correct variable for setting 'max' cpu's ID_AA64DFR0 |
41 | hw/arm/bcm2836: Create proper bcm2837 device | 50 | target/arm/translate-vfp.inc.c: Remove duplicate simd_r32 check |
42 | hw/arm/bcm2836: Use correct affinity values for BCM2837 | 51 | target/arm: Don't allow Thumb Neon insns without FEATURE_NEON |
43 | hw/arm/bcm2836: Hardcode correct CPU type | 52 | target/arm: Add stubs for AArch32 Neon decodetree |
44 | hw/arm/raspi: Provide spin-loop code for AArch64 CPUs | 53 | target/arm: Convert VCMLA (vector) to decodetree |
54 | target/arm: Convert VCADD (vector) to decodetree | ||
55 | target/arm: Convert V[US]DOT (vector) to decodetree | ||
56 | target/arm: Convert VFM[AS]L (vector) to decodetree | ||
57 | target/arm: Convert VCMLA (scalar) to decodetree | ||
58 | target/arm: Convert V[US]DOT (scalar) to decodetree | ||
59 | target/arm: Convert VFM[AS]L (scalar) to decodetree | ||
60 | target/arm: Convert Neon load/store multiple structures to decodetree | ||
61 | target/arm: Convert Neon 'load single structure to all lanes' to decodetree | ||
62 | target/arm: Convert Neon 'load/store single structure' to decodetree | ||
63 | target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree | ||
64 | target/arm: Convert Neon 3-reg-same logic ops to decodetree | ||
65 | target/arm: Convert Neon 3-reg-same VMAX/VMIN to decodetree | ||
66 | target/arm: Convert Neon 3-reg-same comparisons to decodetree | ||
67 | target/arm: Convert Neon 3-reg-same VQADD/VQSUB to decodetree | ||
68 | target/arm: Convert Neon 3-reg-same VMUL, VMLA, VMLS, VSHL to decodetree | ||
69 | target/arm: Move gen_ function typedefs to translate.h | ||
45 | 70 | ||
46 | Wei Huang (1): | 71 | Philippe Mathieu-Daudé (2): |
47 | dump: Update correct kdump phys_base field for AArch64 | 72 | hw/arm/mps2-tz: Use TYPE_IOTKIT instead of hardcoded string |
73 | target/arm: Use uint64_t for midr field in CPU state struct | ||
48 | 74 | ||
49 | include/hw/arm/bcm2836.h | 31 +++++++++++++--- | 75 | include/hw/arm/xlnx-versal.h | 31 +- |
50 | include/hw/arm/fsl-imx6.h | 4 +- | 76 | target/arm/cpu-param.h | 2 +- |
51 | include/hw/char/imx_serial.h | 3 ++ | 77 | target/arm/cpu.h | 38 ++- |
52 | dump.c | 14 +++++-- | 78 | target/arm/translate-a64.h | 9 - |
53 | hw/arm/bcm2836.c | 87 +++++++++++++++++++++++++++++++------------- | 79 | target/arm/translate.h | 26 ++ |
54 | hw/arm/boot.c | 12 ++++++ | 80 | target/arm/neon-dp.decode | 86 +++++ |
55 | hw/arm/raspi.c | 77 +++++++++++++++++++++++++++++++-------- | 81 | target/arm/neon-ls.decode | 52 +++ |
56 | hw/char/imx_serial.c | 44 ++++++++++++++++------ | 82 | target/arm/neon-shared.decode | 66 ++++ |
57 | hw/net/imx_fec.c | 28 +++++++++++++- | 83 | hw/arm/mps2-tz.c | 2 +- |
58 | 9 files changed, 237 insertions(+), 63 deletions(-) | 84 | hw/arm/xlnx-versal-virt.c | 74 ++++- |
85 | hw/arm/xlnx-versal.c | 115 +++++-- | ||
86 | target/arm/cpu.c | 3 +- | ||
87 | target/arm/cpu64.c | 8 +- | ||
88 | target/arm/helper.c | 183 ++++------ | ||
89 | target/arm/translate-a64.c | 17 - | ||
90 | target/arm/translate-neon.inc.c | 714 +++++++++++++++++++++++++++++++++++++++ | ||
91 | target/arm/translate-vfp.inc.c | 6 - | ||
92 | target/arm/translate.c | 716 +++------------------------------------- | ||
93 | target/arm/Makefile.objs | 18 + | ||
94 | 19 files changed, 1302 insertions(+), 864 deletions(-) | ||
95 | create mode 100644 target/arm/neon-dp.decode | ||
96 | create mode 100644 target/arm/neon-ls.decode | ||
97 | create mode 100644 target/arm/neon-shared.decode | ||
98 | create mode 100644 target/arm/translate-neon.inc.c | ||
59 | 99 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: Fredrik Strupe <fredrik@strupe.net> | ||
1 | 2 | ||
3 | According to Arm ARM, VQDMULL is only valid when U=0, while having | ||
4 | U=1 is unallocated. | ||
5 | |||
6 | Signed-off-by: Fredrik Strupe <fredrik@strupe.net> | ||
7 | Fixes: 695272dcb976 ("target-arm: Handle UNDEF cases for Neon 3-regs-different-widths") | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | target/arm/translate.c | 2 +- | ||
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
13 | |||
14 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/target/arm/translate.c | ||
17 | +++ b/target/arm/translate.c | ||
18 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
19 | {0, 0, 0, 0}, /* VMLSL */ | ||
20 | {0, 0, 0, 9}, /* VQDMLSL */ | ||
21 | {0, 0, 0, 0}, /* Integer VMULL */ | ||
22 | - {0, 0, 0, 1}, /* VQDMULL */ | ||
23 | + {0, 0, 0, 9}, /* VQDMULL */ | ||
24 | {0, 0, 0, 0xa}, /* Polynomial VMULL */ | ||
25 | {0, 0, 0, 7}, /* Reserved: always UNDEF */ | ||
26 | }; | ||
27 | -- | ||
28 | 2.20.1 | ||
29 | |||
30 | diff view generated by jsdifflib |
1 | From: Andrey Smirnov <andrew.smirnov@gmail.com> | 1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> |
---|---|---|---|
2 | 2 | ||
3 | Add support for "TX complete"/TXDC interrupt generate by real HW since | 3 | By using the TYPE_* definitions for devices, we can: |
4 | it is needed to support guests other than Linux. | 4 | - quickly find where devices are used with 'git-grep' |
5 | - easily rename a device (one-line change). | ||
5 | 6 | ||
6 | Based on the patch by Bill Paul as found here: | 7 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
7 | https://bugs.launchpad.net/qemu/+bug/1753314 | 8 | Message-id: 20200428154650.21991-1-f4bug@amsat.org |
8 | |||
9 | Cc: qemu-devel@nongnu.org | ||
10 | Cc: qemu-arm@nongnu.org | ||
11 | Cc: Bill Paul <wpaul@windriver.com> | ||
12 | Cc: Peter Maydell <peter.maydell@linaro.org> | ||
13 | Signed-off-by: Bill Paul <wpaul@windriver.com> | ||
14 | Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> | ||
15 | Message-id: 20180315191141.6789-2-andrew.smirnov@gmail.com | ||
16 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
18 | --- | 11 | --- |
19 | include/hw/char/imx_serial.h | 3 +++ | 12 | hw/arm/mps2-tz.c | 2 +- |
20 | hw/char/imx_serial.c | 20 +++++++++++++++++--- | 13 | 1 file changed, 1 insertion(+), 1 deletion(-) |
21 | 2 files changed, 20 insertions(+), 3 deletions(-) | ||
22 | 14 | ||
23 | diff --git a/include/hw/char/imx_serial.h b/include/hw/char/imx_serial.h | 15 | diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c |
24 | index XXXXXXX..XXXXXXX 100644 | 16 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/include/hw/char/imx_serial.h | 17 | --- a/hw/arm/mps2-tz.c |
26 | +++ b/include/hw/char/imx_serial.h | 18 | +++ b/hw/arm/mps2-tz.c |
27 | @@ -XXX,XX +XXX,XX @@ | 19 | @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) |
28 | #define UCR2_RXEN (1<<1) /* Receiver enable */ | 20 | exit(EXIT_FAILURE); |
29 | #define UCR2_SRST (1<<0) /* Reset complete */ | 21 | } |
30 | 22 | ||
31 | +#define UCR4_TCEN BIT(3) /* TX complete interrupt enable */ | 23 | - sysbus_init_child_obj(OBJECT(machine), "iotkit", &mms->iotkit, |
32 | + | 24 | + sysbus_init_child_obj(OBJECT(machine), TYPE_IOTKIT, &mms->iotkit, |
33 | #define UTS1_TXEMPTY (1<<6) | 25 | sizeof(mms->iotkit), mmc->armsse_type); |
34 | #define UTS1_RXEMPTY (1<<5) | 26 | iotkitdev = DEVICE(&mms->iotkit); |
35 | #define UTS1_TXFULL (1<<4) | 27 | object_property_set_link(OBJECT(&mms->iotkit), OBJECT(system_memory), |
36 | @@ -XXX,XX +XXX,XX @@ typedef struct IMXSerialState { | ||
37 | uint32_t ubmr; | ||
38 | uint32_t ubrc; | ||
39 | uint32_t ucr3; | ||
40 | + uint32_t ucr4; | ||
41 | |||
42 | qemu_irq irq; | ||
43 | CharBackend chr; | ||
44 | diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c | ||
45 | index XXXXXXX..XXXXXXX 100644 | ||
46 | --- a/hw/char/imx_serial.c | ||
47 | +++ b/hw/char/imx_serial.c | ||
48 | @@ -XXX,XX +XXX,XX @@ | ||
49 | |||
50 | static const VMStateDescription vmstate_imx_serial = { | ||
51 | .name = TYPE_IMX_SERIAL, | ||
52 | - .version_id = 1, | ||
53 | - .minimum_version_id = 1, | ||
54 | + .version_id = 2, | ||
55 | + .minimum_version_id = 2, | ||
56 | .fields = (VMStateField[]) { | ||
57 | VMSTATE_INT32(readbuff, IMXSerialState), | ||
58 | VMSTATE_UINT32(usr1, IMXSerialState), | ||
59 | @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_serial = { | ||
60 | VMSTATE_UINT32(ubmr, IMXSerialState), | ||
61 | VMSTATE_UINT32(ubrc, IMXSerialState), | ||
62 | VMSTATE_UINT32(ucr3, IMXSerialState), | ||
63 | + VMSTATE_UINT32(ucr4, IMXSerialState), | ||
64 | VMSTATE_END_OF_LIST() | ||
65 | }, | ||
66 | }; | ||
67 | @@ -XXX,XX +XXX,XX @@ static void imx_update(IMXSerialState *s) | ||
68 | * unfortunately. | ||
69 | */ | ||
70 | mask = (s->ucr1 & UCR1_TXMPTYEN) ? USR2_TXFE : 0; | ||
71 | + /* | ||
72 | + * TCEN and TXDC are both bit 3 | ||
73 | + */ | ||
74 | + mask |= s->ucr4 & UCR4_TCEN; | ||
75 | + | ||
76 | usr2 = s->usr2 & mask; | ||
77 | |||
78 | qemu_set_irq(s->irq, usr1 || usr2); | ||
79 | @@ -XXX,XX +XXX,XX @@ static uint64_t imx_serial_read(void *opaque, hwaddr offset, | ||
80 | return s->ucr3; | ||
81 | |||
82 | case 0x23: /* UCR4 */ | ||
83 | + return s->ucr4; | ||
84 | + | ||
85 | case 0x29: /* BRM Incremental */ | ||
86 | return 0x0; /* TODO */ | ||
87 | |||
88 | @@ -XXX,XX +XXX,XX @@ static void imx_serial_write(void *opaque, hwaddr offset, | ||
89 | * qemu_chr_fe_write and background I/O callbacks */ | ||
90 | qemu_chr_fe_write_all(&s->chr, &ch, 1); | ||
91 | s->usr1 &= ~USR1_TRDY; | ||
92 | + s->usr2 &= ~USR2_TXDC; | ||
93 | imx_update(s); | ||
94 | s->usr1 |= USR1_TRDY; | ||
95 | + s->usr2 |= USR2_TXDC; | ||
96 | imx_update(s); | ||
97 | } | ||
98 | break; | ||
99 | @@ -XXX,XX +XXX,XX @@ static void imx_serial_write(void *opaque, hwaddr offset, | ||
100 | s->ucr3 = value & 0xffff; | ||
101 | break; | ||
102 | |||
103 | - case 0x2d: /* UTS1 */ | ||
104 | case 0x23: /* UCR4 */ | ||
105 | + s->ucr4 = value & 0xffff; | ||
106 | + imx_update(s); | ||
107 | + break; | ||
108 | + | ||
109 | + case 0x2d: /* UTS1 */ | ||
110 | qemu_log_mask(LOG_UNIMP, "[%s]%s: Unimplemented reg 0x%" | ||
111 | HWADDR_PRIx "\n", TYPE_IMX_SERIAL, __func__, offset); | ||
112 | /* TODO */ | ||
113 | -- | 28 | -- |
114 | 2.16.2 | 29 | 2.20.1 |
115 | 30 | ||
116 | 31 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | We define ARMMMUIdx_Stage2 as being an MMU index which uses a QEMU | |
2 | TLB. However we never actually use the TLB -- all stage 2 lookups | ||
3 | are done by direct calls to get_phys_addr_lpae() followed by a | ||
4 | physical address load via address_space_ld*(). | ||
5 | |||
6 | Remove Stage2 from the list of ARM MMU indexes which correspond to | ||
7 | real core MMU indexes, and instead put it in the set of "NOTLB" ARM | ||
8 | MMU indexes. | ||
9 | |||
10 | This allows us to drop NB_MMU_MODES to 11. It also means we can | ||
11 | safely add support for the ARMv8.3-TTS2UXN extension, which adds | ||
12 | permission bits to the stage 2 descriptors which define execute | ||
13 | permission separatel for EL0 and EL1; supporting that while keeping | ||
14 | Stage2 in a QEMU TLB would require us to use separate TLBs for | ||
15 | "Stage2 for an EL0 access" and "Stage2 for an EL1 access", which is a | ||
16 | lot of extra complication given we aren't even using the QEMU TLB. | ||
17 | |||
18 | In the process of updating the comment on our MMU index use, | ||
19 | fix a couple of other minor errors: | ||
20 | * NS EL2 EL2&0 was missing from the list in the comment | ||
21 | * some text hadn't been updated from when we bumped NB_MMU_MODES | ||
22 | above 8 | ||
23 | |||
24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
25 | Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
26 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
27 | Message-id: 20200330210400.11724-2-peter.maydell@linaro.org | ||
28 | --- | ||
29 | target/arm/cpu-param.h | 2 +- | ||
30 | target/arm/cpu.h | 21 +++++--- | ||
31 | target/arm/helper.c | 112 ++++------------------------------------- | ||
32 | 3 files changed, 27 insertions(+), 108 deletions(-) | ||
33 | |||
34 | diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h | ||
35 | index XXXXXXX..XXXXXXX 100644 | ||
36 | --- a/target/arm/cpu-param.h | ||
37 | +++ b/target/arm/cpu-param.h | ||
38 | @@ -XXX,XX +XXX,XX @@ | ||
39 | # define TARGET_PAGE_BITS_MIN 10 | ||
40 | #endif | ||
41 | |||
42 | -#define NB_MMU_MODES 12 | ||
43 | +#define NB_MMU_MODES 11 | ||
44 | |||
45 | #endif | ||
46 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/target/arm/cpu.h | ||
49 | +++ b/target/arm/cpu.h | ||
50 | @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); | ||
51 | * handling via the TLB. The only way to do a stage 1 translation without | ||
52 | * the immediate stage 2 translation is via the ATS or AT system insns, | ||
53 | * which can be slow-pathed and always do a page table walk. | ||
54 | + * The only use of stage 2 translations is either as part of an s1+2 | ||
55 | + * lookup or when loading the descriptors during a stage 1 page table walk, | ||
56 | + * and in both those cases we don't use the TLB. | ||
57 | * 4. we can also safely fold together the "32 bit EL3" and "64 bit EL3" | ||
58 | * translation regimes, because they map reasonably well to each other | ||
59 | * and they can't both be active at the same time. | ||
60 | @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); | ||
61 | * NS EL1 EL1&0 stage 1+2 (aka NS PL1) | ||
62 | * NS EL1 EL1&0 stage 1+2 +PAN | ||
63 | * NS EL0 EL2&0 | ||
64 | + * NS EL2 EL2&0 | ||
65 | * NS EL2 EL2&0 +PAN | ||
66 | * NS EL2 (aka NS PL2) | ||
67 | * S EL0 EL1&0 (aka S PL0) | ||
68 | * S EL1 EL1&0 (not used if EL3 is 32 bit) | ||
69 | * S EL1 EL1&0 +PAN | ||
70 | * S EL3 (aka S PL1) | ||
71 | - * NS EL1&0 stage 2 | ||
72 | * | ||
73 | - * for a total of 12 different mmu_idx. | ||
74 | + * for a total of 11 different mmu_idx. | ||
75 | * | ||
76 | * R profile CPUs have an MPU, but can use the same set of MMU indexes | ||
77 | * as A profile. They only need to distinguish NS EL0 and NS EL1 (and | ||
78 | @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); | ||
79 | * are not quite the same -- different CPU types (most notably M profile | ||
80 | * vs A/R profile) would like to use MMU indexes with different semantics, | ||
81 | * but since we don't ever need to use all of those in a single CPU we | ||
82 | - * can avoid setting NB_MMU_MODES to more than 8. The lower bits of | ||
83 | + * can avoid having to set NB_MMU_MODES to "total number of A profile MMU | ||
84 | + * modes + total number of M profile MMU modes". The lower bits of | ||
85 | * ARMMMUIdx are the core TLB mmu index, and the higher bits are always | ||
86 | * the same for any particular CPU. | ||
87 | * Variables of type ARMMUIdx are always full values, and the core | ||
88 | @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { | ||
89 | ARMMMUIdx_SE10_1_PAN = 9 | ARM_MMU_IDX_A, | ||
90 | ARMMMUIdx_SE3 = 10 | ARM_MMU_IDX_A, | ||
91 | |||
92 | - ARMMMUIdx_Stage2 = 11 | ARM_MMU_IDX_A, | ||
93 | - | ||
94 | /* | ||
95 | * These are not allocated TLBs and are used only for AT system | ||
96 | * instructions or for the first stage of an S12 page table walk. | ||
97 | @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx { | ||
98 | ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB, | ||
99 | ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB, | ||
100 | ARMMMUIdx_Stage1_E1_PAN = 2 | ARM_MMU_IDX_NOTLB, | ||
101 | + /* | ||
102 | + * Not allocated a TLB: used only for second stage of an S12 page | ||
103 | + * table walk, or for descriptor loads during first stage of an S1 | ||
104 | + * page table walk. Note that if we ever want to have a TLB for this | ||
105 | + * then various TLB flush insns which currently are no-ops or flush | ||
106 | + * only stage 1 MMU indexes will need to change to flush stage 2. | ||
107 | + */ | ||
108 | + ARMMMUIdx_Stage2 = 3 | ARM_MMU_IDX_NOTLB, | ||
109 | |||
110 | /* | ||
111 | * M-profile. | ||
112 | @@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit { | ||
113 | TO_CORE_BIT(SE10_1), | ||
114 | TO_CORE_BIT(SE10_1_PAN), | ||
115 | TO_CORE_BIT(SE3), | ||
116 | - TO_CORE_BIT(Stage2), | ||
117 | |||
118 | TO_CORE_BIT(MUser), | ||
119 | TO_CORE_BIT(MPriv), | ||
120 | diff --git a/target/arm/helper.c b/target/arm/helper.c | ||
121 | index XXXXXXX..XXXXXXX 100644 | ||
122 | --- a/target/arm/helper.c | ||
123 | +++ b/target/arm/helper.c | ||
124 | @@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
125 | tlb_flush_by_mmuidx(cs, | ||
126 | ARMMMUIdxBit_E10_1 | | ||
127 | ARMMMUIdxBit_E10_1_PAN | | ||
128 | - ARMMMUIdxBit_E10_0 | | ||
129 | - ARMMMUIdxBit_Stage2); | ||
130 | + ARMMMUIdxBit_E10_0); | ||
131 | } | ||
132 | |||
133 | static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
134 | @@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
135 | tlb_flush_by_mmuidx_all_cpus_synced(cs, | ||
136 | ARMMMUIdxBit_E10_1 | | ||
137 | ARMMMUIdxBit_E10_1_PAN | | ||
138 | - ARMMMUIdxBit_E10_0 | | ||
139 | - ARMMMUIdxBit_Stage2); | ||
140 | + ARMMMUIdxBit_E10_0); | ||
141 | } | ||
142 | |||
143 | -static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
144 | - uint64_t value) | ||
145 | -{ | ||
146 | - /* Invalidate by IPA. This has to invalidate any structures that | ||
147 | - * contain only stage 2 translation information, but does not need | ||
148 | - * to apply to structures that contain combined stage 1 and stage 2 | ||
149 | - * translation information. | ||
150 | - * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero. | ||
151 | - */ | ||
152 | - CPUState *cs = env_cpu(env); | ||
153 | - uint64_t pageaddr; | ||
154 | - | ||
155 | - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { | ||
156 | - return; | ||
157 | - } | ||
158 | - | ||
159 | - pageaddr = sextract64(value << 12, 0, 40); | ||
160 | - | ||
161 | - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); | ||
162 | -} | ||
163 | - | ||
164 | -static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
165 | - uint64_t value) | ||
166 | -{ | ||
167 | - CPUState *cs = env_cpu(env); | ||
168 | - uint64_t pageaddr; | ||
169 | - | ||
170 | - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { | ||
171 | - return; | ||
172 | - } | ||
173 | - | ||
174 | - pageaddr = sextract64(value << 12, 0, 40); | ||
175 | - | ||
176 | - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, | ||
177 | - ARMMMUIdxBit_Stage2); | ||
178 | -} | ||
179 | |||
180 | static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
181 | uint64_t value) | ||
182 | @@ -XXX,XX +XXX,XX @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
183 | tlb_flush_by_mmuidx(cs, | ||
184 | ARMMMUIdxBit_E10_1 | | ||
185 | ARMMMUIdxBit_E10_1_PAN | | ||
186 | - ARMMMUIdxBit_E10_0 | | ||
187 | - ARMMMUIdxBit_Stage2); | ||
188 | + ARMMMUIdxBit_E10_0); | ||
189 | raw_write(env, ri, value); | ||
190 | } | ||
191 | } | ||
192 | @@ -XXX,XX +XXX,XX @@ static int alle1_tlbmask(CPUARMState *env) | ||
193 | return ARMMMUIdxBit_SE10_1 | | ||
194 | ARMMMUIdxBit_SE10_1_PAN | | ||
195 | ARMMMUIdxBit_SE10_0; | ||
196 | - } else if (arm_feature(env, ARM_FEATURE_EL2)) { | ||
197 | - return ARMMMUIdxBit_E10_1 | | ||
198 | - ARMMMUIdxBit_E10_1_PAN | | ||
199 | - ARMMMUIdxBit_E10_0 | | ||
200 | - ARMMMUIdxBit_Stage2; | ||
201 | } else { | ||
202 | return ARMMMUIdxBit_E10_1 | | ||
203 | ARMMMUIdxBit_E10_1_PAN | | ||
204 | @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
205 | ARMMMUIdxBit_SE3); | ||
206 | } | ||
207 | |||
208 | -static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
209 | - uint64_t value) | ||
210 | -{ | ||
211 | - /* Invalidate by IPA. This has to invalidate any structures that | ||
212 | - * contain only stage 2 translation information, but does not need | ||
213 | - * to apply to structures that contain combined stage 1 and stage 2 | ||
214 | - * translation information. | ||
215 | - * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero. | ||
216 | - */ | ||
217 | - ARMCPU *cpu = env_archcpu(env); | ||
218 | - CPUState *cs = CPU(cpu); | ||
219 | - uint64_t pageaddr; | ||
220 | - | ||
221 | - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { | ||
222 | - return; | ||
223 | - } | ||
224 | - | ||
225 | - pageaddr = sextract64(value << 12, 0, 48); | ||
226 | - | ||
227 | - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); | ||
228 | -} | ||
229 | - | ||
230 | -static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, | ||
231 | - uint64_t value) | ||
232 | -{ | ||
233 | - CPUState *cs = env_cpu(env); | ||
234 | - uint64_t pageaddr; | ||
235 | - | ||
236 | - if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) { | ||
237 | - return; | ||
238 | - } | ||
239 | - | ||
240 | - pageaddr = sextract64(value << 12, 0, 48); | ||
241 | - | ||
242 | - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, | ||
243 | - ARMMMUIdxBit_Stage2); | ||
244 | -} | ||
245 | - | ||
246 | static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, | ||
247 | bool isread) | ||
248 | { | ||
249 | @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { | ||
250 | .writefn = tlbi_aa64_vae1_write }, | ||
251 | { .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64, | ||
252 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, | ||
253 | - .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
254 | - .writefn = tlbi_aa64_ipas2e1is_write }, | ||
255 | + .access = PL2_W, .type = ARM_CP_NOP }, | ||
256 | { .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64, | ||
257 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, | ||
258 | - .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
259 | - .writefn = tlbi_aa64_ipas2e1is_write }, | ||
260 | + .access = PL2_W, .type = ARM_CP_NOP }, | ||
261 | { .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64, | ||
262 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, | ||
263 | .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
264 | @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { | ||
265 | .writefn = tlbi_aa64_alle1is_write }, | ||
266 | { .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64, | ||
267 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, | ||
268 | - .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
269 | - .writefn = tlbi_aa64_ipas2e1_write }, | ||
270 | + .access = PL2_W, .type = ARM_CP_NOP }, | ||
271 | { .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64, | ||
272 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, | ||
273 | - .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
274 | - .writefn = tlbi_aa64_ipas2e1_write }, | ||
275 | + .access = PL2_W, .type = ARM_CP_NOP }, | ||
276 | { .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64, | ||
277 | .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, | ||
278 | .access = PL2_W, .type = ARM_CP_NO_RAW, | ||
279 | @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = { | ||
280 | .writefn = tlbimva_hyp_is_write }, | ||
281 | { .name = "TLBIIPAS2", | ||
282 | .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, | ||
283 | - .type = ARM_CP_NO_RAW, .access = PL2_W, | ||
284 | - .writefn = tlbiipas2_write }, | ||
285 | + .type = ARM_CP_NOP, .access = PL2_W }, | ||
286 | { .name = "TLBIIPAS2IS", | ||
287 | .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, | ||
288 | - .type = ARM_CP_NO_RAW, .access = PL2_W, | ||
289 | - .writefn = tlbiipas2_is_write }, | ||
290 | + .type = ARM_CP_NOP, .access = PL2_W }, | ||
291 | { .name = "TLBIIPAS2L", | ||
292 | .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, | ||
293 | - .type = ARM_CP_NO_RAW, .access = PL2_W, | ||
294 | - .writefn = tlbiipas2_write }, | ||
295 | + .type = ARM_CP_NOP, .access = PL2_W }, | ||
296 | { .name = "TLBIIPAS2LIS", | ||
297 | .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, | ||
298 | - .type = ARM_CP_NO_RAW, .access = PL2_W, | ||
299 | - .writefn = tlbiipas2_is_write }, | ||
300 | + .type = ARM_CP_NOP, .access = PL2_W }, | ||
301 | /* 32 bit cache operations */ | ||
302 | { .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0, | ||
303 | .type = ARM_CP_NOP, .access = PL1_W, .accessfn = aa64_cacheop_pou_access }, | ||
304 | -- | ||
305 | 2.20.1 | ||
306 | |||
307 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The access_type argument to get_phys_addr_lpae() is an MMUAccessType; | ||
2 | use the enum constant MMU_DATA_LOAD rather than a literal 0 when we | ||
3 | call it in S1_ptw_translate(). | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Message-id: 20200330210400.11724-3-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/helper.c | 5 +++-- | ||
11 | 1 file changed, 3 insertions(+), 2 deletions(-) | ||
12 | |||
13 | diff --git a/target/arm/helper.c b/target/arm/helper.c | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/target/arm/helper.c | ||
16 | +++ b/target/arm/helper.c | ||
17 | @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, | ||
18 | pcacheattrs = &cacheattrs; | ||
19 | } | ||
20 | |||
21 | - ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_Stage2, &s2pa, | ||
22 | - &txattrs, &s2prot, &s2size, fi, pcacheattrs); | ||
23 | + ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2, | ||
24 | + &s2pa, &txattrs, &s2prot, &s2size, fi, | ||
25 | + pcacheattrs); | ||
26 | if (ret) { | ||
27 | assert(fi->type != ARMFault_None); | ||
28 | fi->s2addr = addr; | ||
29 | -- | ||
30 | 2.20.1 | ||
31 | |||
32 | diff view generated by jsdifflib |
1 | Now we have separate types for BCM2386 and BCM2387, we might as well | 1 | For ARMv8.2-TTS2UXN, the stage 2 page table walk wants to know |
---|---|---|---|
2 | just hard-code the CPU type they use rather than having it passed | 2 | whether the stage 1 access is for EL0 or not, because whether |
3 | through as an object property. This then lets us put the initialization | 3 | exec permission is given can depend on whether this is an EL0 |
4 | of the CPU object in init rather than realize. | 4 | or EL1 access. Add a new argument to get_phys_addr_lpae() so |
5 | the call sites can pass this information in. | ||
5 | 6 | ||
6 | Note that this change means that it's no longer possible on | 7 | Since get_phys_addr_lpae() doesn't already have a doc comment, |
7 | the command line to use -cpu to ask for a different kind of | 8 | add one so we have a place to put the documentation of the |
8 | CPU than the SoC supports. This was never a supported thing to | 9 | semantics of the new s1_is_el0 argument. |
9 | do anyway; we were just not sanity-checking the command line. | ||
10 | |||
11 | This does require us to only build the bcm2837 object on | ||
12 | TARGET_AARCH64 configs, since otherwise it won't instantiate | ||
13 | due to the missing cortex-a53 device and "make check" will fail. | ||
14 | 10 | ||
15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
16 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 12 | Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> |
17 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
18 | Message-id: 20180313153458.26822-9-peter.maydell@linaro.org | 14 | Message-id: 20200330210400.11724-4-peter.maydell@linaro.org |
19 | --- | 15 | --- |
20 | hw/arm/bcm2836.c | 24 +++++++++++++++--------- | 16 | target/arm/helper.c | 29 ++++++++++++++++++++++++++++- |
21 | hw/arm/raspi.c | 2 -- | 17 | 1 file changed, 28 insertions(+), 1 deletion(-) |
22 | 2 files changed, 15 insertions(+), 11 deletions(-) | ||
23 | 18 | ||
24 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 19 | diff --git a/target/arm/helper.c b/target/arm/helper.c |
25 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
26 | --- a/hw/arm/bcm2836.c | 21 | --- a/target/arm/helper.c |
27 | +++ b/hw/arm/bcm2836.c | 22 | +++ b/target/arm/helper.c |
28 | @@ -XXX,XX +XXX,XX @@ | 23 | @@ -XXX,XX +XXX,XX @@ |
29 | 24 | ||
30 | struct BCM283XInfo { | 25 | static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, |
31 | const char *name; | 26 | MMUAccessType access_type, ARMMMUIdx mmu_idx, |
32 | + const char *cpu_type; | 27 | + bool s1_is_el0, |
33 | int clusterid; | 28 | hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, |
34 | }; | 29 | target_ulong *page_size_ptr, |
35 | 30 | ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs); | |
36 | static const BCM283XInfo bcm283x_socs[] = { | 31 | @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, |
37 | { | 32 | } |
38 | .name = TYPE_BCM2836, | 33 | |
39 | + .cpu_type = ARM_CPU_TYPE_NAME("cortex-a15"), | 34 | ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2, |
40 | .clusterid = 0xf, | 35 | + false, |
41 | }, | 36 | &s2pa, &txattrs, &s2prot, &s2size, fi, |
42 | +#ifdef TARGET_AARCH64 | 37 | pcacheattrs); |
43 | { | 38 | if (ret) { |
44 | .name = TYPE_BCM2837, | 39 | @@ -XXX,XX +XXX,XX @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, |
45 | + .cpu_type = ARM_CPU_TYPE_NAME("cortex-a53"), | 40 | }; |
46 | .clusterid = 0x0, | ||
47 | }, | ||
48 | +#endif | ||
49 | }; | ||
50 | |||
51 | static void bcm2836_init(Object *obj) | ||
52 | { | ||
53 | BCM283XState *s = BCM283X(obj); | ||
54 | + BCM283XClass *bc = BCM283X_GET_CLASS(obj); | ||
55 | + const BCM283XInfo *info = bc->info; | ||
56 | + int n; | ||
57 | + | ||
58 | + for (n = 0; n < BCM283X_NCPUS; n++) { | ||
59 | + object_initialize(&s->cpus[n], sizeof(s->cpus[n]), | ||
60 | + info->cpu_type); | ||
61 | + object_property_add_child(obj, "cpu[*]", OBJECT(&s->cpus[n]), | ||
62 | + &error_abort); | ||
63 | + } | ||
64 | |||
65 | object_initialize(&s->control, sizeof(s->control), TYPE_BCM2836_CONTROL); | ||
66 | object_property_add_child(obj, "control", OBJECT(&s->control), NULL); | ||
67 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
68 | |||
69 | /* common peripherals from bcm2835 */ | ||
70 | |||
71 | - obj = OBJECT(dev); | ||
72 | - for (n = 0; n < BCM283X_NCPUS; n++) { | ||
73 | - object_initialize(&s->cpus[n], sizeof(s->cpus[n]), | ||
74 | - s->cpu_type); | ||
75 | - object_property_add_child(obj, "cpu[*]", OBJECT(&s->cpus[n]), | ||
76 | - &error_abort); | ||
77 | - } | ||
78 | - | ||
79 | obj = object_property_get_link(OBJECT(dev), "ram", &err); | ||
80 | if (obj == NULL) { | ||
81 | error_setg(errp, "%s: required ram link not found: %s", | ||
82 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
83 | } | 41 | } |
84 | 42 | ||
85 | static Property bcm2836_props[] = { | 43 | +/** |
86 | - DEFINE_PROP_STRING("cpu-type", BCM283XState, cpu_type), | 44 | + * get_phys_addr_lpae: perform one stage of page table walk, LPAE format |
87 | DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, | 45 | + * |
88 | BCM283X_NCPUS), | 46 | + * Returns false if the translation was successful. Otherwise, phys_ptr, attrs, |
89 | DEFINE_PROP_END_OF_LIST() | 47 | + * prot and page_size may not be filled in, and the populated fsr value provides |
90 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 48 | + * information on why the translation aborted, in the format of a long-format |
91 | index XXXXXXX..XXXXXXX 100644 | 49 | + * DFSR/IFSR fault register, with the following caveats: |
92 | --- a/hw/arm/raspi.c | 50 | + * * the WnR bit is never set (the caller must do this). |
93 | +++ b/hw/arm/raspi.c | 51 | + * |
94 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | 52 | + * @env: CPUARMState |
95 | /* Setup the SOC */ | 53 | + * @address: virtual address to get physical address for |
96 | object_property_add_const_link(OBJECT(&s->soc), "ram", OBJECT(&s->ram), | 54 | + * @access_type: MMU_DATA_LOAD, MMU_DATA_STORE or MMU_INST_FETCH |
97 | &error_abort); | 55 | + * @mmu_idx: MMU index indicating required translation regime |
98 | - object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type", | 56 | + * @s1_is_el0: if @mmu_idx is ARMMMUIdx_Stage2 (so this is a stage 2 page table |
99 | - &error_abort); | 57 | + * walk), must be true if this is stage 2 of a stage 1+2 walk for an |
100 | object_property_set_int(OBJECT(&s->soc), smp_cpus, "enabled-cpus", | 58 | + * EL0 access). If @mmu_idx is anything else, @s1_is_el0 is ignored. |
101 | &error_abort); | 59 | + * @phys_ptr: set to the physical address corresponding to the virtual address |
102 | int board_rev = version == 3 ? 0xa02082 : 0xa21041; | 60 | + * @attrs: set to the memory transaction attributes to use |
61 | + * @prot: set to the permissions for the page containing phys_ptr | ||
62 | + * @page_size_ptr: set to the size of the page containing phys_ptr | ||
63 | + * @fi: set to fault info if the translation fails | ||
64 | + * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes | ||
65 | + */ | ||
66 | static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, | ||
67 | MMUAccessType access_type, ARMMMUIdx mmu_idx, | ||
68 | + bool s1_is_el0, | ||
69 | hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, | ||
70 | target_ulong *page_size_ptr, | ||
71 | ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs) | ||
72 | @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, | ||
73 | |||
74 | /* S1 is done. Now do S2 translation. */ | ||
75 | ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_Stage2, | ||
76 | + mmu_idx == ARMMMUIdx_E10_0, | ||
77 | phys_ptr, attrs, &s2_prot, | ||
78 | page_size, fi, | ||
79 | cacheattrs != NULL ? &cacheattrs2 : NULL); | ||
80 | @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, | ||
81 | } | ||
82 | |||
83 | if (regime_using_lpae_format(env, mmu_idx)) { | ||
84 | - return get_phys_addr_lpae(env, address, access_type, mmu_idx, | ||
85 | + return get_phys_addr_lpae(env, address, access_type, mmu_idx, false, | ||
86 | phys_ptr, attrs, prot, page_size, | ||
87 | fi, cacheattrs); | ||
88 | } else if (regime_sctlr(env, mmu_idx) & SCTLR_XP) { | ||
103 | -- | 89 | -- |
104 | 2.16.2 | 90 | 2.20.1 |
105 | 91 | ||
106 | 92 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The ARMv8.2-TTS2UXN feature extends the XN field in stage 2 | ||
2 | translation table descriptors from just bit [54] to bits [54:53], | ||
3 | allowing stage 2 to control execution permissions separately for EL0 | ||
4 | and EL1. Implement the new semantics of the XN field and enable | ||
5 | the feature for our 'max' CPU. | ||
1 | 6 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
8 | Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
10 | Message-id: 20200330210400.11724-5-peter.maydell@linaro.org | ||
11 | --- | ||
12 | target/arm/cpu.h | 15 +++++++++++++++ | ||
13 | target/arm/cpu.c | 1 + | ||
14 | target/arm/cpu64.c | 2 ++ | ||
15 | target/arm/helper.c | 37 +++++++++++++++++++++++++++++++------ | ||
16 | 4 files changed, 49 insertions(+), 6 deletions(-) | ||
17 | |||
18 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
19 | index XXXXXXX..XXXXXXX 100644 | ||
20 | --- a/target/arm/cpu.h | ||
21 | +++ b/target/arm/cpu.h | ||
22 | @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) | ||
23 | return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; | ||
24 | } | ||
25 | |||
26 | +static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id) | ||
27 | +{ | ||
28 | + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0; | ||
29 | +} | ||
30 | + | ||
31 | /* | ||
32 | * 64-bit feature tests via id registers. | ||
33 | */ | ||
34 | @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) | ||
35 | return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; | ||
36 | } | ||
37 | |||
38 | +static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id) | ||
39 | +{ | ||
40 | + return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0; | ||
41 | +} | ||
42 | + | ||
43 | /* | ||
44 | * Feature tests for "does this exist in either 32-bit or 64-bit?" | ||
45 | */ | ||
46 | @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) | ||
47 | return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); | ||
48 | } | ||
49 | |||
50 | +static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id) | ||
51 | +{ | ||
52 | + return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id); | ||
53 | +} | ||
54 | + | ||
55 | /* | ||
56 | * Forward to the above feature tests given an ARMCPU pointer. | ||
57 | */ | ||
58 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | ||
59 | index XXXXXXX..XXXXXXX 100644 | ||
60 | --- a/target/arm/cpu.c | ||
61 | +++ b/target/arm/cpu.c | ||
62 | @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) | ||
63 | t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */ | ||
64 | t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ | ||
65 | t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */ | ||
66 | + t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */ | ||
67 | cpu->isar.id_mmfr4 = t; | ||
68 | } | ||
69 | #endif | ||
70 | diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c | ||
71 | index XXXXXXX..XXXXXXX 100644 | ||
72 | --- a/target/arm/cpu64.c | ||
73 | +++ b/target/arm/cpu64.c | ||
74 | @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) | ||
75 | t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); | ||
76 | t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* ATS1E1 */ | ||
77 | t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* VMID16 */ | ||
78 | + t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* TTS2UXN */ | ||
79 | cpu->isar.id_aa64mmfr1 = t; | ||
80 | |||
81 | t = cpu->isar.id_aa64mmfr2; | ||
82 | @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) | ||
83 | u = FIELD_DP32(u, ID_MMFR4, HPDS, 1); /* AA32HPD */ | ||
84 | u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ | ||
85 | u = FIELD_DP32(u, ID_MMFR4, CNP, 1); /* TTCNP */ | ||
86 | + u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */ | ||
87 | cpu->isar.id_mmfr4 = u; | ||
88 | |||
89 | u = cpu->isar.id_aa64dfr0; | ||
90 | diff --git a/target/arm/helper.c b/target/arm/helper.c | ||
91 | index XXXXXXX..XXXXXXX 100644 | ||
92 | --- a/target/arm/helper.c | ||
93 | +++ b/target/arm/helper.c | ||
94 | @@ -XXX,XX +XXX,XX @@ simple_ap_to_rw_prot(CPUARMState *env, ARMMMUIdx mmu_idx, int ap) | ||
95 | * | ||
96 | * @env: CPUARMState | ||
97 | * @s2ap: The 2-bit stage2 access permissions (S2AP) | ||
98 | - * @xn: XN (execute-never) bit | ||
99 | + * @xn: XN (execute-never) bits | ||
100 | + * @s1_is_el0: true if this is S2 of an S1+2 walk for EL0 | ||
101 | */ | ||
102 | -static int get_S2prot(CPUARMState *env, int s2ap, int xn) | ||
103 | +static int get_S2prot(CPUARMState *env, int s2ap, int xn, bool s1_is_el0) | ||
104 | { | ||
105 | int prot = 0; | ||
106 | |||
107 | @@ -XXX,XX +XXX,XX @@ static int get_S2prot(CPUARMState *env, int s2ap, int xn) | ||
108 | if (s2ap & 2) { | ||
109 | prot |= PAGE_WRITE; | ||
110 | } | ||
111 | - if (!xn) { | ||
112 | - if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) { | ||
113 | + | ||
114 | + if (cpu_isar_feature(any_tts2uxn, env_archcpu(env))) { | ||
115 | + switch (xn) { | ||
116 | + case 0: | ||
117 | prot |= PAGE_EXEC; | ||
118 | + break; | ||
119 | + case 1: | ||
120 | + if (s1_is_el0) { | ||
121 | + prot |= PAGE_EXEC; | ||
122 | + } | ||
123 | + break; | ||
124 | + case 2: | ||
125 | + break; | ||
126 | + case 3: | ||
127 | + if (!s1_is_el0) { | ||
128 | + prot |= PAGE_EXEC; | ||
129 | + } | ||
130 | + break; | ||
131 | + default: | ||
132 | + g_assert_not_reached(); | ||
133 | + } | ||
134 | + } else { | ||
135 | + if (!extract32(xn, 1, 1)) { | ||
136 | + if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) { | ||
137 | + prot |= PAGE_EXEC; | ||
138 | + } | ||
139 | } | ||
140 | } | ||
141 | return prot; | ||
142 | @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, | ||
143 | } | ||
144 | |||
145 | ap = extract32(attrs, 4, 2); | ||
146 | - xn = extract32(attrs, 12, 1); | ||
147 | |||
148 | if (mmu_idx == ARMMMUIdx_Stage2) { | ||
149 | ns = true; | ||
150 | - *prot = get_S2prot(env, ap, xn); | ||
151 | + xn = extract32(attrs, 11, 2); | ||
152 | + *prot = get_S2prot(env, ap, xn, s1_is_el0); | ||
153 | } else { | ||
154 | ns = extract32(attrs, 3, 1); | ||
155 | + xn = extract32(attrs, 12, 1); | ||
156 | pxn = extract32(attrs, 11, 1); | ||
157 | *prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn); | ||
158 | } | ||
159 | -- | ||
160 | 2.20.1 | ||
161 | |||
162 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | In aarch64_max_initfn() we update both 32-bit and 64-bit ID | ||
2 | registers. The intended pattern is that for 64-bit ID registers we | ||
3 | use FIELD_DP64 and the uint64_t 't' register, while 32-bit ID | ||
4 | registers use FIELD_DP32 and the uint32_t 'u' register. For | ||
5 | ID_AA64DFR0 we accidentally used 'u', meaning that the top 32 bits of | ||
6 | this 64-bit ID register would end up always zero. Luckily at the | ||
7 | moment that's what they should be anyway, so this bug has no visible | ||
8 | effects. | ||
1 | 9 | ||
10 | Use the right-sized variable. | ||
11 | |||
12 | Fixes: 3bec78447a958d481991 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> | ||
15 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
16 | Message-id: 20200423110915.10527-1-peter.maydell@linaro.org | ||
17 | --- | ||
18 | target/arm/cpu64.c | 6 +++--- | ||
19 | 1 file changed, 3 insertions(+), 3 deletions(-) | ||
20 | |||
21 | diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c | ||
22 | index XXXXXXX..XXXXXXX 100644 | ||
23 | --- a/target/arm/cpu64.c | ||
24 | +++ b/target/arm/cpu64.c | ||
25 | @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) | ||
26 | u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */ | ||
27 | cpu->isar.id_mmfr4 = u; | ||
28 | |||
29 | - u = cpu->isar.id_aa64dfr0; | ||
30 | - u = FIELD_DP64(u, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ | ||
31 | - cpu->isar.id_aa64dfr0 = u; | ||
32 | + t = cpu->isar.id_aa64dfr0; | ||
33 | + t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */ | ||
34 | + cpu->isar.id_aa64dfr0 = t; | ||
35 | |||
36 | u = cpu->isar.id_dfr0; | ||
37 | u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ | ||
38 | -- | ||
39 | 2.20.1 | ||
40 | |||
41 | diff view generated by jsdifflib |
1 | From: Guenter Roeck <linux@roeck-us.net> | 1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> |
---|---|---|---|
2 | 2 | ||
3 | The sabrelite machine model used by qemu-system-arm is based on the | 3 | MIDR_EL1 is a 64-bit system register with the top 32-bit being RES0. |
4 | Freescale/NXP i.MX6Q processor. This SoC has an on-board ethernet | 4 | Represent it in QEMU's ARMCPU struct with a uint64_t, not a |
5 | controller which is supported in QEMU using the imx_fec.c module | 5 | uint32_t. |
6 | (actually called imx.enet for this model.) | ||
7 | 6 | ||
8 | The include/hw/arm/fsm-imx6.h file defines the interrupt vectors for the | 7 | This fixes an error when compiling with -Werror=conversion |
9 | imx.enet device like this: | 8 | because we were manipulating the register value using a |
9 | local uint64_t variable: | ||
10 | 10 | ||
11 | #define FSL_IMX6_ENET_MAC_1588_IRQ 118 | 11 | target/arm/cpu64.c: In function ‘aarch64_max_initfn’: |
12 | #define FSL_IMX6_ENET_MAC_IRQ 119 | 12 | target/arm/cpu64.c:628:21: error: conversion from ‘uint64_t’ {aka ‘long unsigned int’} to ‘uint32_t’ {aka ‘unsigned int’} may change value [-Werror=conversion] |
13 | 628 | cpu->midr = t; | ||
14 | | ^ | ||
13 | 15 | ||
14 | According to https://www.nxp.com/docs/en/reference-manual/IMX6DQRM.pdf, | 16 | and future-proofs us against a possible future architecture |
15 | page 225, in Table 3-1. ARM Cortex A9 domain interrupt summary, | 17 | change using some of the top 32 bits. |
16 | interrupts are as follows. | ||
17 | 18 | ||
18 | 150 ENET MAC 0 IRQ | 19 | Suggested-by: Laurent Desnogues <laurent.desnogues@gmail.com> |
19 | 151 ENET MAC 0 1588 Timer interrupt | 20 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> |
20 | 21 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | |
21 | where | 22 | Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> |
22 | 23 | Message-id: 20200428172634.29707-1-f4bug@amsat.org | |
23 | 150 - 32 == 118 | ||
24 | 151 - 32 == 119 | ||
25 | |||
26 | In other words, the vector definitions in the fsl-imx6.h file are reversed. | ||
27 | |||
28 | Fixing the interrupts alone causes problems with older Linux kernels: | ||
29 | The Ethernet interface will fail to probe with Linux v4.9 and earlier. | ||
30 | Linux v4.1 and earlier will crash due to a bug in Ethernet driver probe | ||
31 | error handling. This is a Linux kernel problem, not a qemu problem: | ||
32 | the Linux kernel only worked by accident since it requested both interrupts. | ||
33 | |||
34 | For backward compatibility, generate the Ethernet interrupt on both interrupt | ||
35 | lines. This was shown to work from all Linux kernel releases starting with | ||
36 | v3.16. | ||
37 | |||
38 | Link: https://bugs.launchpad.net/qemu/+bug/1753309 | ||
39 | Signed-off-by: Guenter Roeck <linux@roeck-us.net> | ||
40 | Message-id: 1520723090-22130-1-git-send-email-linux@roeck-us.net | ||
41 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
42 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 25 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
43 | --- | 26 | --- |
44 | include/hw/arm/fsl-imx6.h | 4 ++-- | 27 | target/arm/cpu.h | 2 +- |
45 | hw/net/imx_fec.c | 28 +++++++++++++++++++++++++++- | 28 | target/arm/cpu.c | 2 +- |
46 | 2 files changed, 29 insertions(+), 3 deletions(-) | 29 | 2 files changed, 2 insertions(+), 2 deletions(-) |
47 | 30 | ||
48 | diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h | 31 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h |
49 | index XXXXXXX..XXXXXXX 100644 | 32 | index XXXXXXX..XXXXXXX 100644 |
50 | --- a/include/hw/arm/fsl-imx6.h | 33 | --- a/target/arm/cpu.h |
51 | +++ b/include/hw/arm/fsl-imx6.h | 34 | +++ b/target/arm/cpu.h |
52 | @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX6State { | 35 | @@ -XXX,XX +XXX,XX @@ struct ARMCPU { |
53 | #define FSL_IMX6_HDMI_MASTER_IRQ 115 | 36 | uint64_t id_aa64dfr0; |
54 | #define FSL_IMX6_HDMI_CEC_IRQ 116 | 37 | uint64_t id_aa64dfr1; |
55 | #define FSL_IMX6_MLB150_LOW_IRQ 117 | 38 | } isar; |
56 | -#define FSL_IMX6_ENET_MAC_1588_IRQ 118 | 39 | - uint32_t midr; |
57 | -#define FSL_IMX6_ENET_MAC_IRQ 119 | 40 | + uint64_t midr; |
58 | +#define FSL_IMX6_ENET_MAC_IRQ 118 | 41 | uint32_t revidr; |
59 | +#define FSL_IMX6_ENET_MAC_1588_IRQ 119 | 42 | uint32_t reset_fpsid; |
60 | #define FSL_IMX6_PCIE1_IRQ 120 | 43 | uint32_t ctr; |
61 | #define FSL_IMX6_PCIE2_IRQ 121 | 44 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c |
62 | #define FSL_IMX6_PCIE3_IRQ 122 | ||
63 | diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c | ||
64 | index XXXXXXX..XXXXXXX 100644 | 45 | index XXXXXXX..XXXXXXX 100644 |
65 | --- a/hw/net/imx_fec.c | 46 | --- a/target/arm/cpu.c |
66 | +++ b/hw/net/imx_fec.c | 47 | +++ b/target/arm/cpu.c |
67 | @@ -XXX,XX +XXX,XX @@ static void imx_enet_write_bd(IMXENETBufDesc *bd, dma_addr_t addr) | 48 | @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = { |
68 | 49 | static Property arm_cpu_properties[] = { | |
69 | static void imx_eth_update(IMXFECState *s) | 50 | DEFINE_PROP_BOOL("start-powered-off", ARMCPU, start_powered_off, false), |
70 | { | 51 | DEFINE_PROP_UINT32("psci-conduit", ARMCPU, psci_conduit, 0), |
71 | - if (s->regs[ENET_EIR] & s->regs[ENET_EIMR] & ENET_INT_TS_TIMER) { | 52 | - DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0), |
72 | + /* | 53 | + DEFINE_PROP_UINT64("midr", ARMCPU, midr, 0), |
73 | + * Previous versions of qemu had the ENET_INT_MAC and ENET_INT_TS_TIMER | 54 | DEFINE_PROP_UINT64("mp-affinity", ARMCPU, |
74 | + * interrupts swapped. This worked with older versions of Linux (4.14 | 55 | mp_affinity, ARM64_AFFINITY_INVALID), |
75 | + * and older) since Linux associated both interrupt lines with Ethernet | 56 | DEFINE_PROP_INT32("node-id", ARMCPU, node_id, CPU_UNSET_NUMA_NODE_ID), |
76 | + * MAC interrupts. Specifically, | ||
77 | + * - Linux 4.15 and later have separate interrupt handlers for the MAC and | ||
78 | + * timer interrupts. Those versions of Linux fail with versions of QEMU | ||
79 | + * with swapped interrupt assignments. | ||
80 | + * - In linux 4.14, both interrupt lines were registered with the Ethernet | ||
81 | + * MAC interrupt handler. As a result, all versions of qemu happen to | ||
82 | + * work, though that is accidental. | ||
83 | + * - In Linux 4.9 and older, the timer interrupt was registered directly | ||
84 | + * with the Ethernet MAC interrupt handler. The MAC interrupt was | ||
85 | + * redirected to a GPIO interrupt to work around erratum ERR006687. | ||
86 | + * This was implemented using the SOC's IOMUX block. In qemu, this GPIO | ||
87 | + * interrupt never fired since IOMUX is currently not supported in qemu. | ||
88 | + * Linux instead received MAC interrupts on the timer interrupt. | ||
89 | + * As a result, qemu versions with the swapped interrupt assignment work, | ||
90 | + * albeit accidentally, but qemu versions with the correct interrupt | ||
91 | + * assignment fail. | ||
92 | + * | ||
93 | + * To ensure that all versions of Linux work, generate ENET_INT_MAC | ||
94 | + * interrrupts on both interrupt lines. This should be changed if and when | ||
95 | + * qemu supports IOMUX. | ||
96 | + */ | ||
97 | + if (s->regs[ENET_EIR] & s->regs[ENET_EIMR] & | ||
98 | + (ENET_INT_MAC | ENET_INT_TS_TIMER)) { | ||
99 | qemu_set_irq(s->irq[1], 1); | ||
100 | } else { | ||
101 | qemu_set_irq(s->irq[1], 0); | ||
102 | -- | 57 | -- |
103 | 2.16.2 | 58 | 2.20.1 |
104 | 59 | ||
105 | 60 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Remove inclusion of arm_gicv3_common.h, this already gets | ||
4 | included via xlnx-versal.h. | ||
5 | |||
6 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
9 | Message-id: 20200427181649.26851-2-edgar.iglesias@gmail.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | hw/arm/xlnx-versal.c | 1 - | ||
13 | 1 file changed, 1 deletion(-) | ||
14 | |||
15 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/hw/arm/xlnx-versal.c | ||
18 | +++ b/hw/arm/xlnx-versal.c | ||
19 | @@ -XXX,XX +XXX,XX @@ | ||
20 | #include "hw/arm/boot.h" | ||
21 | #include "kvm_arm.h" | ||
22 | #include "hw/misc/unimp.h" | ||
23 | -#include "hw/intc/arm_gicv3_common.h" | ||
24 | #include "hw/arm/xlnx-versal.h" | ||
25 | #include "hw/char/pl011.h" | ||
26 | |||
27 | -- | ||
28 | 2.20.1 | ||
29 | |||
30 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Move misplaced comment. | ||
4 | |||
5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
8 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
9 | Message-id: 20200427181649.26851-3-edgar.iglesias@gmail.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | hw/arm/xlnx-versal.c | 2 +- | ||
13 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
14 | |||
15 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/hw/arm/xlnx-versal.c | ||
18 | +++ b/hw/arm/xlnx-versal.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) | ||
20 | |||
21 | obj = object_new(XLNX_VERSAL_ACPU_TYPE); | ||
22 | if (!obj) { | ||
23 | - /* Secondary CPUs start in PSCI powered-down state */ | ||
24 | error_report("Unable to create apu.cpu[%d] of type %s", | ||
25 | i, XLNX_VERSAL_ACPU_TYPE); | ||
26 | exit(EXIT_FAILURE); | ||
27 | @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) | ||
28 | object_property_set_int(obj, s->cfg.psci_conduit, | ||
29 | "psci-conduit", &error_abort); | ||
30 | if (i) { | ||
31 | + /* Secondary CPUs start in PSCI powered-down state */ | ||
32 | object_property_set_bool(obj, true, | ||
33 | "start-powered-off", &error_abort); | ||
34 | } | ||
35 | -- | ||
36 | 2.20.1 | ||
37 | |||
38 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Fix typo xlnx-ve -> xlnx-versal. | ||
4 | |||
5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
8 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
9 | Message-id: 20200427181649.26851-4-edgar.iglesias@gmail.com | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | hw/arm/xlnx-versal-virt.c | 2 +- | ||
13 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
14 | |||
15 | diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/hw/arm/xlnx-versal-virt.c | ||
18 | +++ b/hw/arm/xlnx-versal-virt.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) | ||
20 | psci_conduit = QEMU_PSCI_CONDUIT_SMC; | ||
21 | } | ||
22 | |||
23 | - sysbus_init_child_obj(OBJECT(machine), "xlnx-ve", &s->soc, | ||
24 | + sysbus_init_child_obj(OBJECT(machine), "xlnx-versal", &s->soc, | ||
25 | sizeof(s->soc), TYPE_XLNX_VERSAL); | ||
26 | object_property_set_link(OBJECT(&s->soc), OBJECT(machine->ram), | ||
27 | "ddr", &error_abort); | ||
28 | -- | ||
29 | 2.20.1 | ||
30 | |||
31 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Embed the UARTs into the SoC type. | ||
4 | |||
5 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
9 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
10 | Message-id: 20200427181649.26851-5-edgar.iglesias@gmail.com | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | include/hw/arm/xlnx-versal.h | 3 ++- | ||
14 | hw/arm/xlnx-versal.c | 12 ++++++------ | ||
15 | 2 files changed, 8 insertions(+), 7 deletions(-) | ||
16 | |||
17 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h | ||
18 | index XXXXXXX..XXXXXXX 100644 | ||
19 | --- a/include/hw/arm/xlnx-versal.h | ||
20 | +++ b/include/hw/arm/xlnx-versal.h | ||
21 | @@ -XXX,XX +XXX,XX @@ | ||
22 | #include "hw/sysbus.h" | ||
23 | #include "hw/arm/boot.h" | ||
24 | #include "hw/intc/arm_gicv3.h" | ||
25 | +#include "hw/char/pl011.h" | ||
26 | |||
27 | #define TYPE_XLNX_VERSAL "xlnx-versal" | ||
28 | #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) | ||
29 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
30 | MemoryRegion mr_ocm; | ||
31 | |||
32 | struct { | ||
33 | - SysBusDevice *uart[XLNX_VERSAL_NR_UARTS]; | ||
34 | + PL011State uart[XLNX_VERSAL_NR_UARTS]; | ||
35 | SysBusDevice *gem[XLNX_VERSAL_NR_GEMS]; | ||
36 | SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; | ||
37 | } iou; | ||
38 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
39 | index XXXXXXX..XXXXXXX 100644 | ||
40 | --- a/hw/arm/xlnx-versal.c | ||
41 | +++ b/hw/arm/xlnx-versal.c | ||
42 | @@ -XXX,XX +XXX,XX @@ | ||
43 | #include "kvm_arm.h" | ||
44 | #include "hw/misc/unimp.h" | ||
45 | #include "hw/arm/xlnx-versal.h" | ||
46 | -#include "hw/char/pl011.h" | ||
47 | |||
48 | #define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72") | ||
49 | #define GEM_REVISION 0x40070106 | ||
50 | @@ -XXX,XX +XXX,XX @@ static void versal_create_uarts(Versal *s, qemu_irq *pic) | ||
51 | DeviceState *dev; | ||
52 | MemoryRegion *mr; | ||
53 | |||
54 | - dev = qdev_create(NULL, TYPE_PL011); | ||
55 | - s->lpd.iou.uart[i] = SYS_BUS_DEVICE(dev); | ||
56 | + sysbus_init_child_obj(OBJECT(s), name, | ||
57 | + &s->lpd.iou.uart[i], sizeof(s->lpd.iou.uart[i]), | ||
58 | + TYPE_PL011); | ||
59 | + dev = DEVICE(&s->lpd.iou.uart[i]); | ||
60 | qdev_prop_set_chr(dev, "chardev", serial_hd(i)); | ||
61 | - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); | ||
62 | qdev_init_nofail(dev); | ||
63 | |||
64 | - mr = sysbus_mmio_get_region(s->lpd.iou.uart[i], 0); | ||
65 | + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); | ||
66 | memory_region_add_subregion(&s->mr_ps, addrs[i], mr); | ||
67 | |||
68 | - sysbus_connect_irq(s->lpd.iou.uart[i], 0, pic[irqs[i]]); | ||
69 | + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]); | ||
70 | g_free(name); | ||
71 | } | ||
72 | } | ||
73 | -- | ||
74 | 2.20.1 | ||
75 | |||
76 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Embed the GEMs into the SoC type. | ||
4 | |||
5 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
9 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
10 | Message-id: 20200427181649.26851-6-edgar.iglesias@gmail.com | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | include/hw/arm/xlnx-versal.h | 3 ++- | ||
14 | hw/arm/xlnx-versal.c | 15 ++++++++------- | ||
15 | 2 files changed, 10 insertions(+), 8 deletions(-) | ||
16 | |||
17 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h | ||
18 | index XXXXXXX..XXXXXXX 100644 | ||
19 | --- a/include/hw/arm/xlnx-versal.h | ||
20 | +++ b/include/hw/arm/xlnx-versal.h | ||
21 | @@ -XXX,XX +XXX,XX @@ | ||
22 | #include "hw/arm/boot.h" | ||
23 | #include "hw/intc/arm_gicv3.h" | ||
24 | #include "hw/char/pl011.h" | ||
25 | +#include "hw/net/cadence_gem.h" | ||
26 | |||
27 | #define TYPE_XLNX_VERSAL "xlnx-versal" | ||
28 | #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) | ||
29 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
30 | |||
31 | struct { | ||
32 | PL011State uart[XLNX_VERSAL_NR_UARTS]; | ||
33 | - SysBusDevice *gem[XLNX_VERSAL_NR_GEMS]; | ||
34 | + CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; | ||
35 | SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; | ||
36 | } iou; | ||
37 | } lpd; | ||
38 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
39 | index XXXXXXX..XXXXXXX 100644 | ||
40 | --- a/hw/arm/xlnx-versal.c | ||
41 | +++ b/hw/arm/xlnx-versal.c | ||
42 | @@ -XXX,XX +XXX,XX @@ static void versal_create_gems(Versal *s, qemu_irq *pic) | ||
43 | DeviceState *dev; | ||
44 | MemoryRegion *mr; | ||
45 | |||
46 | - dev = qdev_create(NULL, "cadence_gem"); | ||
47 | - s->lpd.iou.gem[i] = SYS_BUS_DEVICE(dev); | ||
48 | - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); | ||
49 | + sysbus_init_child_obj(OBJECT(s), name, | ||
50 | + &s->lpd.iou.gem[i], sizeof(s->lpd.iou.gem[i]), | ||
51 | + TYPE_CADENCE_GEM); | ||
52 | + dev = DEVICE(&s->lpd.iou.gem[i]); | ||
53 | if (nd->used) { | ||
54 | qemu_check_nic_model(nd, "cadence_gem"); | ||
55 | qdev_set_nic_properties(dev, nd); | ||
56 | } | ||
57 | - object_property_set_int(OBJECT(s->lpd.iou.gem[i]), | ||
58 | + object_property_set_int(OBJECT(dev), | ||
59 | 2, "num-priority-queues", | ||
60 | &error_abort); | ||
61 | - object_property_set_link(OBJECT(s->lpd.iou.gem[i]), | ||
62 | + object_property_set_link(OBJECT(dev), | ||
63 | OBJECT(&s->mr_ps), "dma", | ||
64 | &error_abort); | ||
65 | qdev_init_nofail(dev); | ||
66 | |||
67 | - mr = sysbus_mmio_get_region(s->lpd.iou.gem[i], 0); | ||
68 | + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); | ||
69 | memory_region_add_subregion(&s->mr_ps, addrs[i], mr); | ||
70 | |||
71 | - sysbus_connect_irq(s->lpd.iou.gem[i], 0, pic[irqs[i]]); | ||
72 | + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]); | ||
73 | g_free(name); | ||
74 | } | ||
75 | } | ||
76 | -- | ||
77 | 2.20.1 | ||
78 | |||
79 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Embed the ADMAs into the SoC type. | ||
4 | |||
5 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
9 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
10 | Message-id: 20200427181649.26851-7-edgar.iglesias@gmail.com | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | include/hw/arm/xlnx-versal.h | 3 ++- | ||
14 | hw/arm/xlnx-versal.c | 14 +++++++------- | ||
15 | 2 files changed, 9 insertions(+), 8 deletions(-) | ||
16 | |||
17 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h | ||
18 | index XXXXXXX..XXXXXXX 100644 | ||
19 | --- a/include/hw/arm/xlnx-versal.h | ||
20 | +++ b/include/hw/arm/xlnx-versal.h | ||
21 | @@ -XXX,XX +XXX,XX @@ | ||
22 | #include "hw/arm/boot.h" | ||
23 | #include "hw/intc/arm_gicv3.h" | ||
24 | #include "hw/char/pl011.h" | ||
25 | +#include "hw/dma/xlnx-zdma.h" | ||
26 | #include "hw/net/cadence_gem.h" | ||
27 | |||
28 | #define TYPE_XLNX_VERSAL "xlnx-versal" | ||
29 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
30 | struct { | ||
31 | PL011State uart[XLNX_VERSAL_NR_UARTS]; | ||
32 | CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; | ||
33 | - SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS]; | ||
34 | + XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; | ||
35 | } iou; | ||
36 | } lpd; | ||
37 | |||
38 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
39 | index XXXXXXX..XXXXXXX 100644 | ||
40 | --- a/hw/arm/xlnx-versal.c | ||
41 | +++ b/hw/arm/xlnx-versal.c | ||
42 | @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) | ||
43 | DeviceState *dev; | ||
44 | MemoryRegion *mr; | ||
45 | |||
46 | - dev = qdev_create(NULL, "xlnx.zdma"); | ||
47 | - s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev); | ||
48 | - object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width", | ||
49 | - &error_abort); | ||
50 | - object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); | ||
51 | + sysbus_init_child_obj(OBJECT(s), name, | ||
52 | + &s->lpd.iou.adma[i], sizeof(s->lpd.iou.adma[i]), | ||
53 | + TYPE_XLNX_ZDMA); | ||
54 | + dev = DEVICE(&s->lpd.iou.adma[i]); | ||
55 | + object_property_set_int(OBJECT(dev), 128, "bus-width", &error_abort); | ||
56 | qdev_init_nofail(dev); | ||
57 | |||
58 | - mr = sysbus_mmio_get_region(s->lpd.iou.adma[i], 0); | ||
59 | + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); | ||
60 | memory_region_add_subregion(&s->mr_ps, | ||
61 | MM_ADMA_CH0 + i * MM_ADMA_CH0_SIZE, mr); | ||
62 | |||
63 | - sysbus_connect_irq(s->lpd.iou.adma[i], 0, pic[VERSAL_ADMA_IRQ_0 + i]); | ||
64 | + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[VERSAL_ADMA_IRQ_0 + i]); | ||
65 | g_free(name); | ||
66 | } | ||
67 | } | ||
68 | -- | ||
69 | 2.20.1 | ||
70 | |||
71 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Embed the APUs into the SoC type. | ||
4 | |||
5 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
9 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
10 | Message-id: 20200427181649.26851-8-edgar.iglesias@gmail.com | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | include/hw/arm/xlnx-versal.h | 2 +- | ||
14 | hw/arm/xlnx-versal-virt.c | 4 ++-- | ||
15 | hw/arm/xlnx-versal.c | 19 +++++-------------- | ||
16 | 3 files changed, 8 insertions(+), 17 deletions(-) | ||
17 | |||
18 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h | ||
19 | index XXXXXXX..XXXXXXX 100644 | ||
20 | --- a/include/hw/arm/xlnx-versal.h | ||
21 | +++ b/include/hw/arm/xlnx-versal.h | ||
22 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
23 | struct { | ||
24 | struct { | ||
25 | MemoryRegion mr; | ||
26 | - ARMCPU *cpu[XLNX_VERSAL_NR_ACPUS]; | ||
27 | + ARMCPU cpu[XLNX_VERSAL_NR_ACPUS]; | ||
28 | GICv3State gic; | ||
29 | } apu; | ||
30 | } fpd; | ||
31 | diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c | ||
32 | index XXXXXXX..XXXXXXX 100644 | ||
33 | --- a/hw/arm/xlnx-versal-virt.c | ||
34 | +++ b/hw/arm/xlnx-versal-virt.c | ||
35 | @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) | ||
36 | s->binfo.get_dtb = versal_virt_get_dtb; | ||
37 | s->binfo.modify_dtb = versal_virt_modify_dtb; | ||
38 | if (machine->kernel_filename) { | ||
39 | - arm_load_kernel(s->soc.fpd.apu.cpu[0], machine, &s->binfo); | ||
40 | + arm_load_kernel(&s->soc.fpd.apu.cpu[0], machine, &s->binfo); | ||
41 | } else { | ||
42 | - AddressSpace *as = arm_boot_address_space(s->soc.fpd.apu.cpu[0], | ||
43 | + AddressSpace *as = arm_boot_address_space(&s->soc.fpd.apu.cpu[0], | ||
44 | &s->binfo); | ||
45 | /* Some boot-loaders (e.g u-boot) don't like blobs at address 0 (NULL). | ||
46 | * Offset things by 4K. */ | ||
47 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
48 | index XXXXXXX..XXXXXXX 100644 | ||
49 | --- a/hw/arm/xlnx-versal.c | ||
50 | +++ b/hw/arm/xlnx-versal.c | ||
51 | @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) | ||
52 | |||
53 | for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) { | ||
54 | Object *obj; | ||
55 | - char *name; | ||
56 | - | ||
57 | - obj = object_new(XLNX_VERSAL_ACPU_TYPE); | ||
58 | - if (!obj) { | ||
59 | - error_report("Unable to create apu.cpu[%d] of type %s", | ||
60 | - i, XLNX_VERSAL_ACPU_TYPE); | ||
61 | - exit(EXIT_FAILURE); | ||
62 | - } | ||
63 | - | ||
64 | - name = g_strdup_printf("apu-cpu[%d]", i); | ||
65 | - object_property_add_child(OBJECT(s), name, obj, &error_fatal); | ||
66 | - g_free(name); | ||
67 | |||
68 | + object_initialize_child(OBJECT(s), "apu-cpu[*]", | ||
69 | + &s->fpd.apu.cpu[i], sizeof(s->fpd.apu.cpu[i]), | ||
70 | + XLNX_VERSAL_ACPU_TYPE, &error_abort, NULL); | ||
71 | + obj = OBJECT(&s->fpd.apu.cpu[i]); | ||
72 | object_property_set_int(obj, s->cfg.psci_conduit, | ||
73 | "psci-conduit", &error_abort); | ||
74 | if (i) { | ||
75 | @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) | ||
76 | object_property_set_link(obj, OBJECT(&s->fpd.apu.mr), "memory", | ||
77 | &error_abort); | ||
78 | object_property_set_bool(obj, true, "realized", &error_fatal); | ||
79 | - s->fpd.apu.cpu[i] = ARM_CPU(obj); | ||
80 | } | ||
81 | } | ||
82 | |||
83 | @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_gic(Versal *s, qemu_irq *pic) | ||
84 | } | ||
85 | |||
86 | for (i = 0; i < nr_apu_cpus; i++) { | ||
87 | - DeviceState *cpudev = DEVICE(s->fpd.apu.cpu[i]); | ||
88 | + DeviceState *cpudev = DEVICE(&s->fpd.apu.cpu[i]); | ||
89 | int ppibase = XLNX_VERSAL_NR_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; | ||
90 | qemu_irq maint_irq; | ||
91 | int ti; | ||
92 | -- | ||
93 | 2.20.1 | ||
94 | |||
95 | diff view generated by jsdifflib |
1 | The bcm2837 is pretty similar to the bcm2836, but it does have | 1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> |
---|---|---|---|
2 | some differences. Notably, the MPIDR affinity aff1 values it | ||
3 | sets for the CPUs are 0x0, rather than the 0xf that the bcm2836 | ||
4 | uses, and if this is wrong Linux will not boot. | ||
5 | 2 | ||
6 | Rather than trying to have one device with properties that | 3 | Add support for SD. |
7 | configure it differently for the two cases, create two | ||
8 | separate QOM devices for the two SoCs. We use the same approach | ||
9 | as hw/arm/aspeed_soc.c and share code and have a data table | ||
10 | that might differ per-SoC. For the moment the two types don't | ||
11 | actually have different behaviour. | ||
12 | 4 | ||
5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
8 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
9 | Message-id: 20200427181649.26851-9-edgar.iglesias@gmail.com | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
15 | Message-id: 20180313153458.26822-7-peter.maydell@linaro.org | ||
16 | --- | 11 | --- |
17 | include/hw/arm/bcm2836.h | 19 +++++++++++++++++++ | 12 | include/hw/arm/xlnx-versal.h | 12 ++++++++++++ |
18 | hw/arm/bcm2836.c | 37 ++++++++++++++++++++++++++++++++----- | 13 | hw/arm/xlnx-versal.c | 31 +++++++++++++++++++++++++++++++ |
19 | hw/arm/raspi.c | 3 ++- | 14 | 2 files changed, 43 insertions(+) |
20 | 3 files changed, 53 insertions(+), 6 deletions(-) | ||
21 | 15 | ||
22 | diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h | 16 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h |
23 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/include/hw/arm/bcm2836.h | 18 | --- a/include/hw/arm/xlnx-versal.h |
25 | +++ b/include/hw/arm/bcm2836.h | 19 | +++ b/include/hw/arm/xlnx-versal.h |
26 | @@ -XXX,XX +XXX,XX @@ | 20 | @@ -XXX,XX +XXX,XX @@ |
27 | 21 | ||
28 | #define BCM283X_NCPUS 4 | 22 | #include "hw/sysbus.h" |
29 | 23 | #include "hw/arm/boot.h" | |
30 | +/* These type names are for specific SoCs; other than instantiating | 24 | +#include "hw/sd/sdhci.h" |
31 | + * them, code using these devices should always handle them via the | 25 | #include "hw/intc/arm_gicv3.h" |
32 | + * BCM283x base class, so they have no BCM2836(obj) etc macros. | 26 | #include "hw/char/pl011.h" |
33 | + */ | 27 | #include "hw/dma/xlnx-zdma.h" |
34 | +#define TYPE_BCM2836 "bcm2836" | 28 | @@ -XXX,XX +XXX,XX @@ |
35 | +#define TYPE_BCM2837 "bcm2837" | 29 | #define XLNX_VERSAL_NR_UARTS 2 |
30 | #define XLNX_VERSAL_NR_GEMS 2 | ||
31 | #define XLNX_VERSAL_NR_ADMAS 8 | ||
32 | +#define XLNX_VERSAL_NR_SDS 2 | ||
33 | #define XLNX_VERSAL_NR_IRQS 192 | ||
34 | |||
35 | typedef struct Versal { | ||
36 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
37 | } iou; | ||
38 | } lpd; | ||
39 | |||
40 | + /* The Platform Management Controller subsystem. */ | ||
41 | + struct { | ||
42 | + struct { | ||
43 | + SDHCIState sd[XLNX_VERSAL_NR_SDS]; | ||
44 | + } iou; | ||
45 | + } pmc; | ||
36 | + | 46 | + |
37 | typedef struct BCM283XState { | 47 | struct { |
38 | /*< private >*/ | 48 | MemoryRegion *mr_ddr; |
39 | DeviceState parent_obj; | 49 | uint32_t psci_conduit; |
40 | @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XState { | 50 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { |
41 | BCM2835PeripheralState peripherals; | 51 | #define VERSAL_GEM1_IRQ_0 58 |
42 | } BCM283XState; | 52 | #define VERSAL_GEM1_WAKE_IRQ_0 59 |
43 | 53 | #define VERSAL_ADMA_IRQ_0 60 | |
44 | +typedef struct BCM283XInfo BCM283XInfo; | 54 | +#define VERSAL_SD0_IRQ_0 126 |
45 | + | 55 | |
46 | +typedef struct BCM283XClass { | 56 | /* Architecturally reserved IRQs suitable for virtualization. */ |
47 | + DeviceClass parent_class; | 57 | #define VERSAL_RSVD_IRQ_FIRST 111 |
48 | + const BCM283XInfo *info; | 58 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { |
49 | +} BCM283XClass; | 59 | #define MM_FPD_CRF 0xfd1a0000U |
50 | + | 60 | #define MM_FPD_CRF_SIZE 0x140000 |
51 | +#define BCM283X_CLASS(klass) \ | 61 | |
52 | + OBJECT_CLASS_CHECK(BCM283XClass, (klass), TYPE_BCM283X) | 62 | +#define MM_PMC_SD0 0xf1040000U |
53 | +#define BCM283X_GET_CLASS(obj) \ | 63 | +#define MM_PMC_SD0_SIZE 0x10000 |
54 | + OBJECT_GET_CLASS(BCM283XClass, (obj), TYPE_BCM283X) | 64 | #define MM_PMC_CRP 0xf1260000U |
55 | + | 65 | #define MM_PMC_CRP_SIZE 0x10000 |
56 | #endif /* BCM2836_H */ | 66 | #endif |
57 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 67 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c |
58 | index XXXXXXX..XXXXXXX 100644 | 68 | index XXXXXXX..XXXXXXX 100644 |
59 | --- a/hw/arm/bcm2836.c | 69 | --- a/hw/arm/xlnx-versal.c |
60 | +++ b/hw/arm/bcm2836.c | 70 | +++ b/hw/arm/xlnx-versal.c |
61 | @@ -XXX,XX +XXX,XX @@ | 71 | @@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic) |
62 | /* "QA7" (Pi2) interrupt controller and mailboxes etc. */ | 72 | } |
63 | #define BCM2836_CONTROL_BASE 0x40000000 | ||
64 | |||
65 | +struct BCM283XInfo { | ||
66 | + const char *name; | ||
67 | +}; | ||
68 | + | ||
69 | +static const BCM283XInfo bcm283x_socs[] = { | ||
70 | + { | ||
71 | + .name = TYPE_BCM2836, | ||
72 | + }, | ||
73 | + { | ||
74 | + .name = TYPE_BCM2837, | ||
75 | + }, | ||
76 | +}; | ||
77 | + | ||
78 | static void bcm2836_init(Object *obj) | ||
79 | { | ||
80 | BCM283XState *s = BCM283X(obj); | ||
81 | @@ -XXX,XX +XXX,XX @@ static Property bcm2836_props[] = { | ||
82 | DEFINE_PROP_END_OF_LIST() | ||
83 | }; | ||
84 | |||
85 | -static void bcm2836_class_init(ObjectClass *oc, void *data) | ||
86 | +static void bcm283x_class_init(ObjectClass *oc, void *data) | ||
87 | { | ||
88 | DeviceClass *dc = DEVICE_CLASS(oc); | ||
89 | + BCM283XClass *bc = BCM283X_CLASS(oc); | ||
90 | |||
91 | - dc->props = bcm2836_props; | ||
92 | + bc->info = data; | ||
93 | dc->realize = bcm2836_realize; | ||
94 | + dc->props = bcm2836_props; | ||
95 | } | 73 | } |
96 | 74 | ||
97 | -static const TypeInfo bcm2836_type_info = { | 75 | +#define SDHCI_CAPABILITIES 0x280737ec6481 /* Same as on ZynqMP. */ |
98 | +static const TypeInfo bcm283x_type_info = { | 76 | +static void versal_create_sds(Versal *s, qemu_irq *pic) |
99 | .name = TYPE_BCM283X, | 77 | +{ |
100 | .parent = TYPE_DEVICE, | ||
101 | .instance_size = sizeof(BCM283XState), | ||
102 | .instance_init = bcm2836_init, | ||
103 | - .class_init = bcm2836_class_init, | ||
104 | + .class_size = sizeof(BCM283XClass), | ||
105 | + .abstract = true, | ||
106 | }; | ||
107 | |||
108 | static void bcm2836_register_types(void) | ||
109 | { | ||
110 | - type_register_static(&bcm2836_type_info); | ||
111 | + int i; | 78 | + int i; |
112 | + | 79 | + |
113 | + type_register_static(&bcm283x_type_info); | 80 | + for (i = 0; i < ARRAY_SIZE(s->pmc.iou.sd); i++) { |
114 | + for (i = 0; i < ARRAY_SIZE(bcm283x_socs); i++) { | 81 | + DeviceState *dev; |
115 | + TypeInfo ti = { | 82 | + MemoryRegion *mr; |
116 | + .name = bcm283x_socs[i].name, | 83 | + |
117 | + .parent = TYPE_BCM283X, | 84 | + sysbus_init_child_obj(OBJECT(s), "sd[*]", |
118 | + .class_init = bcm283x_class_init, | 85 | + &s->pmc.iou.sd[i], sizeof(s->pmc.iou.sd[i]), |
119 | + .class_data = (void *) &bcm283x_socs[i], | 86 | + TYPE_SYSBUS_SDHCI); |
120 | + }; | 87 | + dev = DEVICE(&s->pmc.iou.sd[i]); |
121 | + type_register(&ti); | 88 | + |
89 | + object_property_set_uint(OBJECT(dev), | ||
90 | + 3, "sd-spec-version", &error_fatal); | ||
91 | + object_property_set_uint(OBJECT(dev), SDHCI_CAPABILITIES, "capareg", | ||
92 | + &error_fatal); | ||
93 | + object_property_set_uint(OBJECT(dev), UHS_I, "uhs", &error_fatal); | ||
94 | + qdev_init_nofail(dev); | ||
95 | + | ||
96 | + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); | ||
97 | + memory_region_add_subregion(&s->mr_ps, | ||
98 | + MM_PMC_SD0 + i * MM_PMC_SD0_SIZE, mr); | ||
99 | + | ||
100 | + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, | ||
101 | + pic[VERSAL_SD0_IRQ_0 + i * 2]); | ||
122 | + } | 102 | + } |
123 | } | 103 | +} |
124 | 104 | + | |
125 | type_init(bcm2836_register_types) | 105 | /* This takes the board allocated linear DDR memory and creates aliases |
126 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 106 | * for each split DDR range/aperture on the Versal address map. |
127 | index XXXXXXX..XXXXXXX 100644 | 107 | */ |
128 | --- a/hw/arm/raspi.c | 108 | @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) |
129 | +++ b/hw/arm/raspi.c | 109 | versal_create_uarts(s, pic); |
130 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | 110 | versal_create_gems(s, pic); |
131 | BusState *bus; | 111 | versal_create_admas(s, pic); |
132 | DeviceState *carddev; | 112 | + versal_create_sds(s, pic); |
133 | 113 | versal_map_ddr(s); | |
134 | - object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM283X); | 114 | versal_unimp(s); |
135 | + object_initialize(&s->soc, sizeof(s->soc), | ||
136 | + version == 3 ? TYPE_BCM2837 : TYPE_BCM2836); | ||
137 | object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc), | ||
138 | &error_abort); | ||
139 | 115 | ||
140 | -- | 116 | -- |
141 | 2.16.2 | 117 | 2.20.1 |
142 | 118 | ||
143 | 119 | diff view generated by jsdifflib |
1 | The raspi3 has AArch64 CPUs, which means that our smpboot | 1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> |
---|---|---|---|
2 | code for keeping the secondary CPUs in a pen needs to have | ||
3 | a version for A64 as well as A32. Without this, the | ||
4 | secondary CPUs go into an infinite loop of taking undefined | ||
5 | instruction exceptions. | ||
6 | 2 | ||
3 | hw/arm: versal: Add support for the RTC. | ||
4 | |||
5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
6 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
7 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
8 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
9 | Message-id: 20200427181649.26851-10-edgar.iglesias@gmail.com | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
9 | Message-id: 20180313153458.26822-10-peter.maydell@linaro.org | ||
10 | --- | 11 | --- |
11 | hw/arm/raspi.c | 41 ++++++++++++++++++++++++++++++++++++++++- | 12 | include/hw/arm/xlnx-versal.h | 8 ++++++++ |
12 | 1 file changed, 40 insertions(+), 1 deletion(-) | 13 | hw/arm/xlnx-versal.c | 21 +++++++++++++++++++++ |
14 | 2 files changed, 29 insertions(+) | ||
13 | 15 | ||
14 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 16 | diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h |
15 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/hw/arm/raspi.c | 18 | --- a/include/hw/arm/xlnx-versal.h |
17 | +++ b/hw/arm/raspi.c | 19 | +++ b/include/hw/arm/xlnx-versal.h |
18 | @@ -XXX,XX +XXX,XX @@ | 20 | @@ -XXX,XX +XXX,XX @@ |
19 | #define BOARDSETUP_ADDR (MVBAR_ADDR + 0x20) /* board setup code */ | 21 | #include "hw/char/pl011.h" |
20 | #define FIRMWARE_ADDR_2 0x8000 /* Pi 2 loads kernel.img here by default */ | 22 | #include "hw/dma/xlnx-zdma.h" |
21 | #define FIRMWARE_ADDR_3 0x80000 /* Pi 3 loads kernel.img here by default */ | 23 | #include "hw/net/cadence_gem.h" |
22 | +#define SPINTABLE_ADDR 0xd8 /* Pi 3 bootloader spintable */ | 24 | +#include "hw/rtc/xlnx-zynqmp-rtc.h" |
23 | 25 | ||
24 | /* Table of Linux board IDs for different Pi versions */ | 26 | #define TYPE_XLNX_VERSAL "xlnx-versal" |
25 | static const int raspi_boardid[] = {[1] = 0xc42, [2] = 0xc43, [3] = 0xc44}; | 27 | #define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL) |
26 | @@ -XXX,XX +XXX,XX @@ static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) | 28 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { |
27 | info->smp_loader_start); | 29 | struct { |
30 | SDHCIState sd[XLNX_VERSAL_NR_SDS]; | ||
31 | } iou; | ||
32 | + | ||
33 | + XlnxZynqMPRTC rtc; | ||
34 | } pmc; | ||
35 | |||
36 | struct { | ||
37 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
38 | #define VERSAL_GEM1_IRQ_0 58 | ||
39 | #define VERSAL_GEM1_WAKE_IRQ_0 59 | ||
40 | #define VERSAL_ADMA_IRQ_0 60 | ||
41 | +#define VERSAL_RTC_APB_ERR_IRQ 121 | ||
42 | #define VERSAL_SD0_IRQ_0 126 | ||
43 | +#define VERSAL_RTC_ALARM_IRQ 142 | ||
44 | +#define VERSAL_RTC_SECONDS_IRQ 143 | ||
45 | |||
46 | /* Architecturally reserved IRQs suitable for virtualization. */ | ||
47 | #define VERSAL_RSVD_IRQ_FIRST 111 | ||
48 | @@ -XXX,XX +XXX,XX @@ typedef struct Versal { | ||
49 | #define MM_PMC_SD0_SIZE 0x10000 | ||
50 | #define MM_PMC_CRP 0xf1260000U | ||
51 | #define MM_PMC_CRP_SIZE 0x10000 | ||
52 | +#define MM_PMC_RTC 0xf12a0000 | ||
53 | +#define MM_PMC_RTC_SIZE 0x10000 | ||
54 | #endif | ||
55 | diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c | ||
56 | index XXXXXXX..XXXXXXX 100644 | ||
57 | --- a/hw/arm/xlnx-versal.c | ||
58 | +++ b/hw/arm/xlnx-versal.c | ||
59 | @@ -XXX,XX +XXX,XX @@ static void versal_create_sds(Versal *s, qemu_irq *pic) | ||
60 | } | ||
28 | } | 61 | } |
29 | 62 | ||
30 | +static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) | 63 | +static void versal_create_rtc(Versal *s, qemu_irq *pic) |
31 | +{ | 64 | +{ |
32 | + /* Unlike the AArch32 version we don't need to call the board setup hook. | 65 | + SysBusDevice *sbd; |
33 | + * The mechanism for doing the spin-table is also entirely different. | 66 | + MemoryRegion *mr; |
34 | + * We must have four 64-bit fields at absolute addresses | 67 | + |
35 | + * 0xd8, 0xe0, 0xe8, 0xf0 in RAM, which are the flag variables for | 68 | + sysbus_init_child_obj(OBJECT(s), "rtc", &s->pmc.rtc, sizeof(s->pmc.rtc), |
36 | + * our CPUs, and which we must ensure are zero initialized before | 69 | + TYPE_XLNX_ZYNQMP_RTC); |
37 | + * the primary CPU goes into the kernel. We put these variables inside | 70 | + sbd = SYS_BUS_DEVICE(&s->pmc.rtc); |
38 | + * a rom blob, so that the reset for ROM contents zeroes them for us. | 71 | + qdev_init_nofail(DEVICE(sbd)); |
72 | + | ||
73 | + mr = sysbus_mmio_get_region(sbd, 0); | ||
74 | + memory_region_add_subregion(&s->mr_ps, MM_PMC_RTC, mr); | ||
75 | + | ||
76 | + /* | ||
77 | + * TODO: Connect the ALARM and SECONDS interrupts once our RTC model | ||
78 | + * supports them. | ||
39 | + */ | 79 | + */ |
40 | + static const uint32_t smpboot[] = { | 80 | + sysbus_connect_irq(sbd, 1, pic[VERSAL_RTC_APB_ERR_IRQ]); |
41 | + 0xd2801b05, /* mov x5, 0xd8 */ | ||
42 | + 0xd53800a6, /* mrs x6, mpidr_el1 */ | ||
43 | + 0x924004c6, /* and x6, x6, #0x3 */ | ||
44 | + 0xd503205f, /* spin: wfe */ | ||
45 | + 0xf86678a4, /* ldr x4, [x5,x6,lsl #3] */ | ||
46 | + 0xb4ffffc4, /* cbz x4, spin */ | ||
47 | + 0xd2800000, /* mov x0, #0x0 */ | ||
48 | + 0xd2800001, /* mov x1, #0x0 */ | ||
49 | + 0xd2800002, /* mov x2, #0x0 */ | ||
50 | + 0xd2800003, /* mov x3, #0x0 */ | ||
51 | + 0xd61f0080, /* br x4 */ | ||
52 | + }; | ||
53 | + | ||
54 | + static const uint64_t spintables[] = { | ||
55 | + 0, 0, 0, 0 | ||
56 | + }; | ||
57 | + | ||
58 | + rom_add_blob_fixed("raspi_smpboot", smpboot, sizeof(smpboot), | ||
59 | + info->smp_loader_start); | ||
60 | + rom_add_blob_fixed("raspi_spintables", spintables, sizeof(spintables), | ||
61 | + SPINTABLE_ADDR); | ||
62 | +} | 81 | +} |
63 | + | 82 | + |
64 | static void write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) | 83 | /* This takes the board allocated linear DDR memory and creates aliases |
65 | { | 84 | * for each split DDR range/aperture on the Versal address map. |
66 | arm_write_secure_board_setup_dummy_smc(cpu, info, MVBAR_ADDR); | 85 | */ |
67 | @@ -XXX,XX +XXX,XX @@ static void setup_boot(MachineState *machine, int version, size_t ram_size) | 86 | @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) |
68 | /* Pi2 and Pi3 requires SMP setup */ | 87 | versal_create_gems(s, pic); |
69 | if (version >= 2) { | 88 | versal_create_admas(s, pic); |
70 | binfo.smp_loader_start = SMPBOOT_ADDR; | 89 | versal_create_sds(s, pic); |
71 | - binfo.write_secondary_boot = write_smpboot; | 90 | + versal_create_rtc(s, pic); |
72 | + if (version == 2) { | 91 | versal_map_ddr(s); |
73 | + binfo.write_secondary_boot = write_smpboot; | 92 | versal_unimp(s); |
74 | + } else { | ||
75 | + binfo.write_secondary_boot = write_smpboot64; | ||
76 | + } | ||
77 | binfo.secondary_cpu_reset_hook = reset_secondary; | ||
78 | } | ||
79 | 93 | ||
80 | -- | 94 | -- |
81 | 2.16.2 | 95 | 2.20.1 |
82 | 96 | ||
83 | 97 | diff view generated by jsdifflib |
1 | From: Andrey Smirnov <andrew.smirnov@gmail.com> | 1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> |
---|---|---|---|
2 | 2 | ||
3 | Code of imx_update() is slightly confusing since the "flags" variable | 3 | Add support for SD. |
4 | doesn't really corespond to anything in real hardware and server as a | ||
5 | kitchensink accumulating events normally reported via USR1 and USR2 | ||
6 | registers. | ||
7 | 4 | ||
8 | Change the code to explicitly evaluate state of interrupts reported | 5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> |
9 | via USR1 and USR2 against corresponding masking bits and use the to | 6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> |
10 | detemine if IRQ line should be asserted or not. | 7 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> |
11 | 8 | Message-id: 20200427181649.26851-11-edgar.iglesias@gmail.com | |
12 | NOTE: Check for UTS1_TXEMPTY being set has been dropped for two | ||
13 | reasons: | ||
14 | |||
15 | 1. Emulation code implements a single character FIFO, so this flag | ||
16 | will always be set since characters are trasmitted as a part of | ||
17 | the code emulating "push" into the FIFO | ||
18 | |||
19 | 2. imx_update() is really just a function doing ORing and maksing | ||
20 | of reported events, so checking for UTS1_TXEMPTY should happen, | ||
21 | if it's ever really needed should probably happen outside of | ||
22 | it. | ||
23 | |||
24 | Cc: qemu-devel@nongnu.org | ||
25 | Cc: qemu-arm@nongnu.org | ||
26 | Cc: Bill Paul <wpaul@windriver.com> | ||
27 | Cc: Peter Maydell <peter.maydell@linaro.org> | ||
28 | Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com> | ||
29 | Message-id: 20180315191141.6789-1-andrew.smirnov@gmail.com | ||
30 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
31 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
32 | --- | 10 | --- |
33 | hw/char/imx_serial.c | 24 ++++++++++++++++-------- | 11 | hw/arm/xlnx-versal-virt.c | 46 +++++++++++++++++++++++++++++++++++++++ |
34 | 1 file changed, 16 insertions(+), 8 deletions(-) | 12 | 1 file changed, 46 insertions(+) |
35 | 13 | ||
36 | diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c | 14 | diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c |
37 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
38 | --- a/hw/char/imx_serial.c | 16 | --- a/hw/arm/xlnx-versal-virt.c |
39 | +++ b/hw/char/imx_serial.c | 17 | +++ b/hw/arm/xlnx-versal-virt.c |
40 | @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_serial = { | 18 | @@ -XXX,XX +XXX,XX @@ |
41 | 19 | #include "hw/arm/sysbus-fdt.h" | |
42 | static void imx_update(IMXSerialState *s) | 20 | #include "hw/arm/fdt.h" |
21 | #include "cpu.h" | ||
22 | +#include "hw/qdev-properties.h" | ||
23 | #include "hw/arm/xlnx-versal.h" | ||
24 | |||
25 | #define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt") | ||
26 | @@ -XXX,XX +XXX,XX @@ static void fdt_add_zdma_nodes(VersalVirt *s) | ||
27 | } | ||
28 | } | ||
29 | |||
30 | +static void fdt_add_sd_nodes(VersalVirt *s) | ||
31 | +{ | ||
32 | + const char clocknames[] = "clk_xin\0clk_ahb"; | ||
33 | + const char compat[] = "arasan,sdhci-8.9a"; | ||
34 | + int i; | ||
35 | + | ||
36 | + for (i = ARRAY_SIZE(s->soc.pmc.iou.sd) - 1; i >= 0; i--) { | ||
37 | + uint64_t addr = MM_PMC_SD0 + MM_PMC_SD0_SIZE * i; | ||
38 | + char *name = g_strdup_printf("/sdhci@%" PRIx64, addr); | ||
39 | + | ||
40 | + qemu_fdt_add_subnode(s->fdt, name); | ||
41 | + | ||
42 | + qemu_fdt_setprop_cells(s->fdt, name, "clocks", | ||
43 | + s->phandle.clk_25Mhz, s->phandle.clk_25Mhz); | ||
44 | + qemu_fdt_setprop(s->fdt, name, "clock-names", | ||
45 | + clocknames, sizeof(clocknames)); | ||
46 | + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", | ||
47 | + GIC_FDT_IRQ_TYPE_SPI, VERSAL_SD0_IRQ_0 + i * 2, | ||
48 | + GIC_FDT_IRQ_FLAGS_LEVEL_HI); | ||
49 | + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", | ||
50 | + 2, addr, 2, MM_PMC_SD0_SIZE); | ||
51 | + qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat)); | ||
52 | + g_free(name); | ||
53 | + } | ||
54 | +} | ||
55 | + | ||
56 | static void fdt_nop_memory_nodes(void *fdt, Error **errp) | ||
43 | { | 57 | { |
44 | - uint32_t flags; | 58 | Error *err = NULL; |
45 | + uint32_t usr1; | 59 | @@ -XXX,XX +XXX,XX @@ static void create_virtio_regions(VersalVirt *s) |
46 | + uint32_t usr2; | 60 | } |
47 | + uint32_t mask; | ||
48 | |||
49 | - flags = (s->usr1 & s->ucr1) & (USR1_TRDY|USR1_RRDY); | ||
50 | - if (s->ucr1 & UCR1_TXMPTYEN) { | ||
51 | - flags |= (s->uts1 & UTS1_TXEMPTY); | ||
52 | - } else { | ||
53 | - flags &= ~USR1_TRDY; | ||
54 | - } | ||
55 | + /* | ||
56 | + * Lucky for us TRDY and RRDY has the same offset in both USR1 and | ||
57 | + * UCR1, so we can get away with something as simple as the | ||
58 | + * following: | ||
59 | + */ | ||
60 | + usr1 = s->usr1 & s->ucr1 & (USR1_TRDY | USR1_RRDY); | ||
61 | + /* | ||
62 | + * Bits that we want in USR2 are not as conveniently laid out, | ||
63 | + * unfortunately. | ||
64 | + */ | ||
65 | + mask = (s->ucr1 & UCR1_TXMPTYEN) ? USR2_TXFE : 0; | ||
66 | + usr2 = s->usr2 & mask; | ||
67 | |||
68 | - qemu_set_irq(s->irq, !!flags); | ||
69 | + qemu_set_irq(s->irq, usr1 || usr2); | ||
70 | } | 61 | } |
71 | 62 | ||
72 | static void imx_serial_reset(IMXSerialState *s) | 63 | +static void sd_plugin_card(SDHCIState *sd, DriveInfo *di) |
64 | +{ | ||
65 | + BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL; | ||
66 | + DeviceState *card; | ||
67 | + | ||
68 | + card = qdev_create(qdev_get_child_bus(DEVICE(sd), "sd-bus"), TYPE_SD_CARD); | ||
69 | + object_property_add_child(OBJECT(sd), "card[*]", OBJECT(card), | ||
70 | + &error_fatal); | ||
71 | + qdev_prop_set_drive(card, "drive", blk, &error_fatal); | ||
72 | + object_property_set_bool(OBJECT(card), true, "realized", &error_fatal); | ||
73 | +} | ||
74 | + | ||
75 | static void versal_virt_init(MachineState *machine) | ||
76 | { | ||
77 | VersalVirt *s = XLNX_VERSAL_VIRT_MACHINE(machine); | ||
78 | int psci_conduit = QEMU_PSCI_CONDUIT_DISABLED; | ||
79 | + int i; | ||
80 | |||
81 | /* | ||
82 | * If the user provides an Operating System to be loaded, we expect them | ||
83 | @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) | ||
84 | fdt_add_gic_nodes(s); | ||
85 | fdt_add_timer_nodes(s); | ||
86 | fdt_add_zdma_nodes(s); | ||
87 | + fdt_add_sd_nodes(s); | ||
88 | fdt_add_cpu_nodes(s, psci_conduit); | ||
89 | fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz); | ||
90 | fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz); | ||
91 | @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) | ||
92 | memory_region_add_subregion_overlap(get_system_memory(), | ||
93 | 0, &s->soc.fpd.apu.mr, 0); | ||
94 | |||
95 | + /* Plugin SD cards. */ | ||
96 | + for (i = 0; i < ARRAY_SIZE(s->soc.pmc.iou.sd); i++) { | ||
97 | + sd_plugin_card(&s->soc.pmc.iou.sd[i], drive_get_next(IF_SD)); | ||
98 | + } | ||
99 | + | ||
100 | s->binfo.ram_size = machine->ram_size; | ||
101 | s->binfo.loader_start = 0x0; | ||
102 | s->binfo.get_dtb = versal_virt_get_dtb; | ||
73 | -- | 103 | -- |
74 | 2.16.2 | 104 | 2.20.1 |
75 | 105 | ||
76 | 106 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> | ||
1 | 2 | ||
3 | Add support for the RTC. | ||
4 | |||
5 | Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
6 | Reviewed-by: Alistair Francis <alistair.francis@wdc.com> | ||
7 | Reviewed-by: Luc Michel <luc.michel@greensocs.com> | ||
8 | Message-id: 20200427181649.26851-12-edgar.iglesias@gmail.com | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | hw/arm/xlnx-versal-virt.c | 22 ++++++++++++++++++++++ | ||
12 | 1 file changed, 22 insertions(+) | ||
13 | |||
14 | diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/hw/arm/xlnx-versal-virt.c | ||
17 | +++ b/hw/arm/xlnx-versal-virt.c | ||
18 | @@ -XXX,XX +XXX,XX @@ static void fdt_add_sd_nodes(VersalVirt *s) | ||
19 | } | ||
20 | } | ||
21 | |||
22 | +static void fdt_add_rtc_node(VersalVirt *s) | ||
23 | +{ | ||
24 | + const char compat[] = "xlnx,zynqmp-rtc"; | ||
25 | + const char interrupt_names[] = "alarm\0sec"; | ||
26 | + char *name = g_strdup_printf("/rtc@%x", MM_PMC_RTC); | ||
27 | + | ||
28 | + qemu_fdt_add_subnode(s->fdt, name); | ||
29 | + | ||
30 | + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", | ||
31 | + GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_ALARM_IRQ, | ||
32 | + GIC_FDT_IRQ_FLAGS_LEVEL_HI, | ||
33 | + GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_SECONDS_IRQ, | ||
34 | + GIC_FDT_IRQ_FLAGS_LEVEL_HI); | ||
35 | + qemu_fdt_setprop(s->fdt, name, "interrupt-names", | ||
36 | + interrupt_names, sizeof(interrupt_names)); | ||
37 | + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", | ||
38 | + 2, MM_PMC_RTC, 2, MM_PMC_RTC_SIZE); | ||
39 | + qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat)); | ||
40 | + g_free(name); | ||
41 | +} | ||
42 | + | ||
43 | static void fdt_nop_memory_nodes(void *fdt, Error **errp) | ||
44 | { | ||
45 | Error *err = NULL; | ||
46 | @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) | ||
47 | fdt_add_timer_nodes(s); | ||
48 | fdt_add_zdma_nodes(s); | ||
49 | fdt_add_sd_nodes(s); | ||
50 | + fdt_add_rtc_node(s); | ||
51 | fdt_add_cpu_nodes(s, psci_conduit); | ||
52 | fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz); | ||
53 | fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz); | ||
54 | -- | ||
55 | 2.20.1 | ||
56 | |||
57 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Somewhere along theline we accidentally added a duplicate | ||
2 | "using D16-D31 when they don't exist" check to do_vfm_dp() | ||
3 | (probably an artifact of a patchseries rebase). Remove it. | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
8 | Message-id: 20200430181003.21682-2-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/translate-vfp.inc.c | 6 ------ | ||
11 | 1 file changed, 6 deletions(-) | ||
12 | |||
13 | diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/target/arm/translate-vfp.inc.c | ||
16 | +++ b/target/arm/translate-vfp.inc.c | ||
17 | @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) | ||
18 | return false; | ||
19 | } | ||
20 | |||
21 | - /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
22 | - if (!dc_isar_feature(aa32_simd_r32, s) && | ||
23 | - ((a->vd | a->vn | a->vm) & 0x10)) { | ||
24 | - return false; | ||
25 | - } | ||
26 | - | ||
27 | if (!vfp_access_check(s)) { | ||
28 | return true; | ||
29 | } | ||
30 | -- | ||
31 | 2.20.1 | ||
32 | |||
33 | diff view generated by jsdifflib |
1 | From: Wei Huang <wei@redhat.com> | 1 | We were accidentally permitting decode of Thumb Neon insns even if |
---|---|---|---|
2 | the CPU didn't have the FEATURE_NEON bit set, because the feature | ||
3 | check was being done before the call to disas_neon_data_insn() and | ||
4 | disas_neon_ls_insn() in the Arm decoder but was omitted from the | ||
5 | Thumb decoder. Push the feature bit check down into the called | ||
6 | functions so it is done for both Arm and Thumb encodings. | ||
2 | 7 | ||
3 | For guest kernel that supports KASLR, the load address can change every | 8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | time when guest VM runs. To find the physical base address correctly, | 9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | current QEMU dump searches VMCOREINFO for the string "NUMBER(phys_base)=". | 10 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> |
6 | However this string pattern is only available on x86_64. AArch64 uses a | 11 | Message-id: 20200430181003.21682-3-peter.maydell@linaro.org |
7 | different field, called "NUMBER(PHYS_OFFSET)=". This patch makes sure | 12 | --- |
8 | QEMU dump uses the correct string on AArch64. | 13 | target/arm/translate.c | 16 ++++++++-------- |
14 | 1 file changed, 8 insertions(+), 8 deletions(-) | ||
9 | 15 | ||
10 | Signed-off-by: Wei Huang <wei@redhat.com> | 16 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
11 | Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com> | ||
12 | Message-id: 1520615003-20869-1-git-send-email-wei@redhat.com | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | --- | ||
15 | dump.c | 14 +++++++++++--- | ||
16 | 1 file changed, 11 insertions(+), 3 deletions(-) | ||
17 | |||
18 | diff --git a/dump.c b/dump.c | ||
19 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/dump.c | 18 | --- a/target/arm/translate.c |
21 | +++ b/dump.c | 19 | +++ b/target/arm/translate.c |
22 | @@ -XXX,XX +XXX,XX @@ static void vmcoreinfo_update_phys_base(DumpState *s) | 20 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) |
23 | 21 | TCGv_i32 tmp2; | |
24 | lines = g_strsplit((char *)vmci, "\n", -1); | 22 | TCGv_i64 tmp64; |
25 | for (i = 0; lines[i]; i++) { | 23 | |
26 | - if (g_str_has_prefix(lines[i], "NUMBER(phys_base)=")) { | 24 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { |
27 | - if (qemu_strtou64(lines[i] + 18, NULL, 16, | 25 | + return 1; |
28 | + const char *prefix = NULL; | 26 | + } |
29 | + | 27 | + |
30 | + if (s->dump_info.d_machine == EM_X86_64) { | 28 | /* FIXME: this access check should not take precedence over UNDEF |
31 | + prefix = "NUMBER(phys_base)="; | 29 | * for invalid encodings; we will generate incorrect syndrome information |
32 | + } else if (s->dump_info.d_machine == EM_AARCH64) { | 30 | * for attempts to execute invalid vfp/neon encodings with FP disabled. |
33 | + prefix = "NUMBER(PHYS_OFFSET)="; | 31 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
34 | + } | 32 | TCGv_ptr ptr1, ptr2, ptr3; |
33 | TCGv_i64 tmp64; | ||
34 | |||
35 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
36 | + return 1; | ||
37 | + } | ||
35 | + | 38 | + |
36 | + if (prefix && g_str_has_prefix(lines[i], prefix)) { | 39 | /* FIXME: this access check should not take precedence over UNDEF |
37 | + if (qemu_strtou64(lines[i] + strlen(prefix), NULL, 16, | 40 | * for invalid encodings; we will generate incorrect syndrome information |
38 | &phys_base) < 0) { | 41 | * for attempts to execute invalid vfp/neon encodings with FP disabled. |
39 | - warn_report("Failed to read NUMBER(phys_base)="); | 42 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) |
40 | + warn_report("Failed to read %s", prefix); | 43 | |
41 | } else { | 44 | if (((insn >> 25) & 7) == 1) { |
42 | s->dump_info.phys_base = phys_base; | 45 | /* NEON Data processing. */ |
46 | - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
47 | - goto illegal_op; | ||
48 | - } | ||
49 | - | ||
50 | if (disas_neon_data_insn(s, insn)) { | ||
51 | goto illegal_op; | ||
52 | } | ||
53 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) | ||
54 | } | ||
55 | if ((insn & 0x0f100000) == 0x04000000) { | ||
56 | /* NEON load/store. */ | ||
57 | - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
58 | - goto illegal_op; | ||
59 | - } | ||
60 | - | ||
61 | if (disas_neon_ls_insn(s, insn)) { | ||
62 | goto illegal_op; | ||
43 | } | 63 | } |
44 | -- | 64 | -- |
45 | 2.16.2 | 65 | 2.20.1 |
46 | 66 | ||
47 | 67 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | Add the infrastructure for building and invoking a decodetree decoder | |
2 | for the AArch32 Neon encodings. At the moment the new decoder covers | ||
3 | nothing, so we always fall back to the existing hand-written decode. | ||
4 | |||
5 | We follow the same pattern we did for the VFP decodetree conversion | ||
6 | (commit 78e138bc1f672c145ef6ace74617d and following): code that deals | ||
7 | with Neon will be moving gradually out to translate-neon.vfp.inc, | ||
8 | which we #include into translate.c. | ||
9 | |||
10 | In order to share the decode files between A32 and T32, we | ||
11 | split Neon into 3 parts: | ||
12 | * data-processing | ||
13 | * load-store | ||
14 | * 'shared' encodings | ||
15 | |||
16 | The first two groups of instructions have similar but not identical | ||
17 | A32 and T32 encodings, so we need to manually transform the T32 | ||
18 | encoding into the A32 one before calling the decoder; the third group | ||
19 | covers the Neon instructions which are identical in A32 and T32. | ||
20 | |||
21 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
22 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
23 | Message-id: 20200430181003.21682-4-peter.maydell@linaro.org | ||
24 | --- | ||
25 | target/arm/neon-dp.decode | 29 ++++++++++++++++++++++++++ | ||
26 | target/arm/neon-ls.decode | 29 ++++++++++++++++++++++++++ | ||
27 | target/arm/neon-shared.decode | 27 +++++++++++++++++++++++++ | ||
28 | target/arm/translate-neon.inc.c | 32 +++++++++++++++++++++++++++++ | ||
29 | target/arm/translate.c | 36 +++++++++++++++++++++++++++++++-- | ||
30 | target/arm/Makefile.objs | 18 +++++++++++++++++ | ||
31 | 6 files changed, 169 insertions(+), 2 deletions(-) | ||
32 | create mode 100644 target/arm/neon-dp.decode | ||
33 | create mode 100644 target/arm/neon-ls.decode | ||
34 | create mode 100644 target/arm/neon-shared.decode | ||
35 | create mode 100644 target/arm/translate-neon.inc.c | ||
36 | |||
37 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode | ||
38 | new file mode 100644 | ||
39 | index XXXXXXX..XXXXXXX | ||
40 | --- /dev/null | ||
41 | +++ b/target/arm/neon-dp.decode | ||
42 | @@ -XXX,XX +XXX,XX @@ | ||
43 | +# AArch32 Neon data-processing instruction descriptions | ||
44 | +# | ||
45 | +# Copyright (c) 2020 Linaro, Ltd | ||
46 | +# | ||
47 | +# This library is free software; you can redistribute it and/or | ||
48 | +# modify it under the terms of the GNU Lesser General Public | ||
49 | +# License as published by the Free Software Foundation; either | ||
50 | +# version 2 of the License, or (at your option) any later version. | ||
51 | +# | ||
52 | +# This library 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 GNU | ||
55 | +# Lesser General Public License for more details. | ||
56 | +# | ||
57 | +# You should have received a copy of the GNU Lesser General Public | ||
58 | +# License along with this library; if not, see <http://www.gnu.org/licenses/>. | ||
59 | + | ||
60 | +# | ||
61 | +# This file is processed by scripts/decodetree.py | ||
62 | +# | ||
63 | + | ||
64 | +# Encodings for Neon data processing instructions where the T32 encoding | ||
65 | +# is a simple transformation of the A32 encoding. | ||
66 | +# More specifically, this file covers instructions where the A32 encoding is | ||
67 | +# 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq | ||
68 | +# and the T32 encoding is | ||
69 | +# 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq | ||
70 | +# This file works on the A32 encoding only; calling code for T32 has to | ||
71 | +# transform the insn into the A32 version first. | ||
72 | diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode | ||
73 | new file mode 100644 | ||
74 | index XXXXXXX..XXXXXXX | ||
75 | --- /dev/null | ||
76 | +++ b/target/arm/neon-ls.decode | ||
77 | @@ -XXX,XX +XXX,XX @@ | ||
78 | +# AArch32 Neon load/store instruction descriptions | ||
79 | +# | ||
80 | +# Copyright (c) 2020 Linaro, Ltd | ||
81 | +# | ||
82 | +# This library is free software; you can redistribute it and/or | ||
83 | +# modify it under the terms of the GNU Lesser General Public | ||
84 | +# License as published by the Free Software Foundation; either | ||
85 | +# version 2 of the License, or (at your option) any later version. | ||
86 | +# | ||
87 | +# This library is distributed in the hope that it will be useful, | ||
88 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
89 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
90 | +# Lesser General Public License for more details. | ||
91 | +# | ||
92 | +# You should have received a copy of the GNU Lesser General Public | ||
93 | +# License along with this library; if not, see <http://www.gnu.org/licenses/>. | ||
94 | + | ||
95 | +# | ||
96 | +# This file is processed by scripts/decodetree.py | ||
97 | +# | ||
98 | + | ||
99 | +# Encodings for Neon load/store instructions where the T32 encoding | ||
100 | +# is a simple transformation of the A32 encoding. | ||
101 | +# More specifically, this file covers instructions where the A32 encoding is | ||
102 | +# 0b1111_0100_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx | ||
103 | +# and the T32 encoding is | ||
104 | +# 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx | ||
105 | +# This file works on the A32 encoding only; calling code for T32 has to | ||
106 | +# transform the insn into the A32 version first. | ||
107 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
108 | new file mode 100644 | ||
109 | index XXXXXXX..XXXXXXX | ||
110 | --- /dev/null | ||
111 | +++ b/target/arm/neon-shared.decode | ||
112 | @@ -XXX,XX +XXX,XX @@ | ||
113 | +# AArch32 Neon instruction descriptions | ||
114 | +# | ||
115 | +# Copyright (c) 2020 Linaro, Ltd | ||
116 | +# | ||
117 | +# This library is free software; you can redistribute it and/or | ||
118 | +# modify it under the terms of the GNU Lesser General Public | ||
119 | +# License as published by the Free Software Foundation; either | ||
120 | +# version 2 of the License, or (at your option) any later version. | ||
121 | +# | ||
122 | +# This library is distributed in the hope that it will be useful, | ||
123 | +# but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
124 | +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
125 | +# Lesser General Public License for more details. | ||
126 | +# | ||
127 | +# You should have received a copy of the GNU Lesser General Public | ||
128 | +# License along with this library; if not, see <http://www.gnu.org/licenses/>. | ||
129 | + | ||
130 | +# | ||
131 | +# This file is processed by scripts/decodetree.py | ||
132 | +# | ||
133 | + | ||
134 | +# Encodings for Neon instructions whose encoding is the same for | ||
135 | +# both A32 and T32. | ||
136 | + | ||
137 | +# More specifically, this covers: | ||
138 | +# 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx | ||
139 | +# 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx | ||
140 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
141 | new file mode 100644 | ||
142 | index XXXXXXX..XXXXXXX | ||
143 | --- /dev/null | ||
144 | +++ b/target/arm/translate-neon.inc.c | ||
145 | @@ -XXX,XX +XXX,XX @@ | ||
146 | +/* | ||
147 | + * ARM translation: AArch32 Neon instructions | ||
148 | + * | ||
149 | + * Copyright (c) 2003 Fabrice Bellard | ||
150 | + * Copyright (c) 2005-2007 CodeSourcery | ||
151 | + * Copyright (c) 2007 OpenedHand, Ltd. | ||
152 | + * Copyright (c) 2020 Linaro, Ltd. | ||
153 | + * | ||
154 | + * This library is free software; you can redistribute it and/or | ||
155 | + * modify it under the terms of the GNU Lesser General Public | ||
156 | + * License as published by the Free Software Foundation; either | ||
157 | + * version 2 of the License, or (at your option) any later version. | ||
158 | + * | ||
159 | + * This library is distributed in the hope that it will be useful, | ||
160 | + * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
161 | + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU | ||
162 | + * Lesser General Public License for more details. | ||
163 | + * | ||
164 | + * You should have received a copy of the GNU Lesser General Public | ||
165 | + * License along with this library; if not, see <http://www.gnu.org/licenses/>. | ||
166 | + */ | ||
167 | + | ||
168 | +/* | ||
169 | + * This file is intended to be included from translate.c; it uses | ||
170 | + * some macros and definitions provided by that file. | ||
171 | + * It might be possible to convert it to a standalone .c file eventually. | ||
172 | + */ | ||
173 | + | ||
174 | +/* Include the generated Neon decoder */ | ||
175 | +#include "decode-neon-dp.inc.c" | ||
176 | +#include "decode-neon-ls.inc.c" | ||
177 | +#include "decode-neon-shared.inc.c" | ||
178 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
179 | index XXXXXXX..XXXXXXX 100644 | ||
180 | --- a/target/arm/translate.c | ||
181 | +++ b/target/arm/translate.c | ||
182 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) | ||
183 | |||
184 | #define ARM_CP_RW_BIT (1 << 20) | ||
185 | |||
186 | -/* Include the VFP decoder */ | ||
187 | +/* Include the VFP and Neon decoders */ | ||
188 | #include "translate-vfp.inc.c" | ||
189 | +#include "translate-neon.inc.c" | ||
190 | |||
191 | static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) | ||
192 | { | ||
193 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) | ||
194 | /* Unconditional instructions. */ | ||
195 | /* TODO: Perhaps merge these into one decodetree output file. */ | ||
196 | if (disas_a32_uncond(s, insn) || | ||
197 | - disas_vfp_uncond(s, insn)) { | ||
198 | + disas_vfp_uncond(s, insn) || | ||
199 | + disas_neon_dp(s, insn) || | ||
200 | + disas_neon_ls(s, insn) || | ||
201 | + disas_neon_shared(s, insn)) { | ||
202 | return; | ||
203 | } | ||
204 | /* fall back to legacy decoder */ | ||
205 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | ||
206 | ARCH(6T2); | ||
207 | } | ||
208 | |||
209 | + if ((insn & 0xef000000) == 0xef000000) { | ||
210 | + /* | ||
211 | + * T32 encodings 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq | ||
212 | + * transform into | ||
213 | + * A32 encodings 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq | ||
214 | + */ | ||
215 | + uint32_t a32_insn = (insn & 0xe2ffffff) | | ||
216 | + ((insn & (1 << 28)) >> 4) | (1 << 28); | ||
217 | + | ||
218 | + if (disas_neon_dp(s, a32_insn)) { | ||
219 | + return; | ||
220 | + } | ||
221 | + } | ||
222 | + | ||
223 | + if ((insn & 0xff100000) == 0xf9000000) { | ||
224 | + /* | ||
225 | + * T32 encodings 0b1111_1001_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq | ||
226 | + * transform into | ||
227 | + * A32 encodings 0b1111_0100_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq | ||
228 | + */ | ||
229 | + uint32_t a32_insn = (insn & 0x00ffffff) | 0xf4000000; | ||
230 | + | ||
231 | + if (disas_neon_ls(s, a32_insn)) { | ||
232 | + return; | ||
233 | + } | ||
234 | + } | ||
235 | + | ||
236 | /* | ||
237 | * TODO: Perhaps merge these into one decodetree output file. | ||
238 | * Note disas_vfp is written for a32 with cond field in the | ||
239 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | ||
240 | */ | ||
241 | if (disas_t32(s, insn) || | ||
242 | disas_vfp_uncond(s, insn) || | ||
243 | + disas_neon_shared(s, insn) || | ||
244 | ((insn >> 28) == 0xe && disas_vfp(s, insn))) { | ||
245 | return; | ||
246 | } | ||
247 | diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs | ||
248 | index XXXXXXX..XXXXXXX 100644 | ||
249 | --- a/target/arm/Makefile.objs | ||
250 | +++ b/target/arm/Makefile.objs | ||
251 | @@ -XXX,XX +XXX,XX @@ target/arm/decode-sve.inc.c: $(SRC_PATH)/target/arm/sve.decode $(DECODETREE) | ||
252 | $(PYTHON) $(DECODETREE) --decode disas_sve -o $@ $<,\ | ||
253 | "GEN", $(TARGET_DIR)$@) | ||
254 | |||
255 | +target/arm/decode-neon-shared.inc.c: $(SRC_PATH)/target/arm/neon-shared.decode $(DECODETREE) | ||
256 | + $(call quiet-command,\ | ||
257 | + $(PYTHON) $(DECODETREE) --static-decode disas_neon_shared -o $@ $<,\ | ||
258 | + "GEN", $(TARGET_DIR)$@) | ||
259 | + | ||
260 | +target/arm/decode-neon-dp.inc.c: $(SRC_PATH)/target/arm/neon-dp.decode $(DECODETREE) | ||
261 | + $(call quiet-command,\ | ||
262 | + $(PYTHON) $(DECODETREE) --static-decode disas_neon_dp -o $@ $<,\ | ||
263 | + "GEN", $(TARGET_DIR)$@) | ||
264 | + | ||
265 | +target/arm/decode-neon-ls.inc.c: $(SRC_PATH)/target/arm/neon-ls.decode $(DECODETREE) | ||
266 | + $(call quiet-command,\ | ||
267 | + $(PYTHON) $(DECODETREE) --static-decode disas_neon_ls -o $@ $<,\ | ||
268 | + "GEN", $(TARGET_DIR)$@) | ||
269 | + | ||
270 | target/arm/decode-vfp.inc.c: $(SRC_PATH)/target/arm/vfp.decode $(DECODETREE) | ||
271 | $(call quiet-command,\ | ||
272 | $(PYTHON) $(DECODETREE) --static-decode disas_vfp -o $@ $<,\ | ||
273 | @@ -XXX,XX +XXX,XX @@ target/arm/decode-t16.inc.c: $(SRC_PATH)/target/arm/t16.decode $(DECODETREE) | ||
274 | "GEN", $(TARGET_DIR)$@) | ||
275 | |||
276 | target/arm/translate-sve.o: target/arm/decode-sve.inc.c | ||
277 | +target/arm/translate.o: target/arm/decode-neon-shared.inc.c | ||
278 | +target/arm/translate.o: target/arm/decode-neon-dp.inc.c | ||
279 | +target/arm/translate.o: target/arm/decode-neon-ls.inc.c | ||
280 | target/arm/translate.o: target/arm/decode-vfp.inc.c | ||
281 | target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c | ||
282 | target/arm/translate.o: target/arm/decode-a32.inc.c | ||
283 | -- | ||
284 | 2.20.1 | ||
285 | |||
286 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the VCMLA (vector) insns in the 3same extension group to | ||
2 | decodetree. | ||
1 | 3 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
6 | Message-id: 20200430181003.21682-5-peter.maydell@linaro.org | ||
7 | --- | ||
8 | target/arm/neon-shared.decode | 11 ++++++++++ | ||
9 | target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++ | ||
10 | target/arm/translate.c | 11 +--------- | ||
11 | 3 files changed, 49 insertions(+), 10 deletions(-) | ||
12 | |||
13 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/target/arm/neon-shared.decode | ||
16 | +++ b/target/arm/neon-shared.decode | ||
17 | @@ -XXX,XX +XXX,XX @@ | ||
18 | # More specifically, this covers: | ||
19 | # 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx | ||
20 | # 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx | ||
21 | + | ||
22 | +# VFP/Neon register fields; same as vfp.decode | ||
23 | +%vm_dp 5:1 0:4 | ||
24 | +%vm_sp 0:4 5:1 | ||
25 | +%vn_dp 7:1 16:4 | ||
26 | +%vn_sp 16:4 7:1 | ||
27 | +%vd_dp 22:1 12:4 | ||
28 | +%vd_sp 12:4 22:1 | ||
29 | + | ||
30 | +VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ | ||
31 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
32 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
33 | index XXXXXXX..XXXXXXX 100644 | ||
34 | --- a/target/arm/translate-neon.inc.c | ||
35 | +++ b/target/arm/translate-neon.inc.c | ||
36 | @@ -XXX,XX +XXX,XX @@ | ||
37 | #include "decode-neon-dp.inc.c" | ||
38 | #include "decode-neon-ls.inc.c" | ||
39 | #include "decode-neon-shared.inc.c" | ||
40 | + | ||
41 | +static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) | ||
42 | +{ | ||
43 | + int opr_sz; | ||
44 | + TCGv_ptr fpst; | ||
45 | + gen_helper_gvec_3_ptr *fn_gvec_ptr; | ||
46 | + | ||
47 | + if (!dc_isar_feature(aa32_vcma, s) | ||
48 | + || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { | ||
49 | + return false; | ||
50 | + } | ||
51 | + | ||
52 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
53 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
54 | + ((a->vd | a->vn | a->vm) & 0x10)) { | ||
55 | + return false; | ||
56 | + } | ||
57 | + | ||
58 | + if ((a->vn | a->vm | a->vd) & a->q) { | ||
59 | + return false; | ||
60 | + } | ||
61 | + | ||
62 | + if (!vfp_access_check(s)) { | ||
63 | + return true; | ||
64 | + } | ||
65 | + | ||
66 | + opr_sz = (1 + a->q) * 8; | ||
67 | + fpst = get_fpstatus_ptr(1); | ||
68 | + fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; | ||
69 | + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), | ||
70 | + vfp_reg_offset(1, a->vn), | ||
71 | + vfp_reg_offset(1, a->vm), | ||
72 | + fpst, opr_sz, opr_sz, a->rot, | ||
73 | + fn_gvec_ptr); | ||
74 | + tcg_temp_free_ptr(fpst); | ||
75 | + return true; | ||
76 | +} | ||
77 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
78 | index XXXXXXX..XXXXXXX 100644 | ||
79 | --- a/target/arm/translate.c | ||
80 | +++ b/target/arm/translate.c | ||
81 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) | ||
82 | bool is_long = false, q = extract32(insn, 6, 1); | ||
83 | bool ptr_is_env = false; | ||
84 | |||
85 | - if ((insn & 0xfe200f10) == 0xfc200800) { | ||
86 | - /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */ | ||
87 | - int size = extract32(insn, 20, 1); | ||
88 | - data = extract32(insn, 23, 2); /* rot */ | ||
89 | - if (!dc_isar_feature(aa32_vcma, s) | ||
90 | - || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { | ||
91 | - return 1; | ||
92 | - } | ||
93 | - fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; | ||
94 | - } else if ((insn & 0xfea00f10) == 0xfc800800) { | ||
95 | + if ((insn & 0xfea00f10) == 0xfc800800) { | ||
96 | /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ | ||
97 | int size = extract32(insn, 20, 1); | ||
98 | data = extract32(insn, 24, 1); /* rot */ | ||
99 | -- | ||
100 | 2.20.1 | ||
101 | |||
102 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the VCADD (vector) insns to decodetree. | ||
1 | 2 | ||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Message-id: 20200430181003.21682-6-peter.maydell@linaro.org | ||
6 | --- | ||
7 | target/arm/neon-shared.decode | 3 +++ | ||
8 | target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++ | ||
9 | target/arm/translate.c | 11 +--------- | ||
10 | 3 files changed, 41 insertions(+), 10 deletions(-) | ||
11 | |||
12 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/target/arm/neon-shared.decode | ||
15 | +++ b/target/arm/neon-shared.decode | ||
16 | @@ -XXX,XX +XXX,XX @@ | ||
17 | |||
18 | VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ | ||
19 | vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
20 | + | ||
21 | +VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ | ||
22 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
23 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
24 | index XXXXXXX..XXXXXXX 100644 | ||
25 | --- a/target/arm/translate-neon.inc.c | ||
26 | +++ b/target/arm/translate-neon.inc.c | ||
27 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a) | ||
28 | tcg_temp_free_ptr(fpst); | ||
29 | return true; | ||
30 | } | ||
31 | + | ||
32 | +static bool trans_VCADD(DisasContext *s, arg_VCADD *a) | ||
33 | +{ | ||
34 | + int opr_sz; | ||
35 | + TCGv_ptr fpst; | ||
36 | + gen_helper_gvec_3_ptr *fn_gvec_ptr; | ||
37 | + | ||
38 | + if (!dc_isar_feature(aa32_vcma, s) | ||
39 | + || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) { | ||
40 | + return false; | ||
41 | + } | ||
42 | + | ||
43 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
44 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
45 | + ((a->vd | a->vn | a->vm) & 0x10)) { | ||
46 | + return false; | ||
47 | + } | ||
48 | + | ||
49 | + if ((a->vn | a->vm | a->vd) & a->q) { | ||
50 | + return false; | ||
51 | + } | ||
52 | + | ||
53 | + if (!vfp_access_check(s)) { | ||
54 | + return true; | ||
55 | + } | ||
56 | + | ||
57 | + opr_sz = (1 + a->q) * 8; | ||
58 | + fpst = get_fpstatus_ptr(1); | ||
59 | + fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; | ||
60 | + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), | ||
61 | + vfp_reg_offset(1, a->vn), | ||
62 | + vfp_reg_offset(1, a->vm), | ||
63 | + fpst, opr_sz, opr_sz, a->rot, | ||
64 | + fn_gvec_ptr); | ||
65 | + tcg_temp_free_ptr(fpst); | ||
66 | + return true; | ||
67 | +} | ||
68 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
69 | index XXXXXXX..XXXXXXX 100644 | ||
70 | --- a/target/arm/translate.c | ||
71 | +++ b/target/arm/translate.c | ||
72 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) | ||
73 | bool is_long = false, q = extract32(insn, 6, 1); | ||
74 | bool ptr_is_env = false; | ||
75 | |||
76 | - if ((insn & 0xfea00f10) == 0xfc800800) { | ||
77 | - /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ | ||
78 | - int size = extract32(insn, 20, 1); | ||
79 | - data = extract32(insn, 24, 1); /* rot */ | ||
80 | - if (!dc_isar_feature(aa32_vcma, s) | ||
81 | - || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { | ||
82 | - return 1; | ||
83 | - } | ||
84 | - fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; | ||
85 | - } else if ((insn & 0xfeb00f00) == 0xfc200d00) { | ||
86 | + if ((insn & 0xfeb00f00) == 0xfc200d00) { | ||
87 | /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ | ||
88 | bool u = extract32(insn, 4, 1); | ||
89 | if (!dc_isar_feature(aa32_dp, s)) { | ||
90 | -- | ||
91 | 2.20.1 | ||
92 | |||
93 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the V[US]DOT (vector) insns to decodetree. | ||
1 | 2 | ||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Message-id: 20200430181003.21682-7-peter.maydell@linaro.org | ||
6 | --- | ||
7 | target/arm/neon-shared.decode | 4 ++++ | ||
8 | target/arm/translate-neon.inc.c | 32 ++++++++++++++++++++++++++++++++ | ||
9 | target/arm/translate.c | 9 +-------- | ||
10 | 3 files changed, 37 insertions(+), 8 deletions(-) | ||
11 | |||
12 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/target/arm/neon-shared.decode | ||
15 | +++ b/target/arm/neon-shared.decode | ||
16 | @@ -XXX,XX +XXX,XX @@ VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \ | ||
17 | |||
18 | VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ | ||
19 | vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
20 | + | ||
21 | +# VUDOT and VSDOT | ||
22 | +VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ | ||
23 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
24 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
25 | index XXXXXXX..XXXXXXX 100644 | ||
26 | --- a/target/arm/translate-neon.inc.c | ||
27 | +++ b/target/arm/translate-neon.inc.c | ||
28 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a) | ||
29 | tcg_temp_free_ptr(fpst); | ||
30 | return true; | ||
31 | } | ||
32 | + | ||
33 | +static bool trans_VDOT(DisasContext *s, arg_VDOT *a) | ||
34 | +{ | ||
35 | + int opr_sz; | ||
36 | + gen_helper_gvec_3 *fn_gvec; | ||
37 | + | ||
38 | + if (!dc_isar_feature(aa32_dp, s)) { | ||
39 | + return false; | ||
40 | + } | ||
41 | + | ||
42 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
43 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
44 | + ((a->vd | a->vn | a->vm) & 0x10)) { | ||
45 | + return false; | ||
46 | + } | ||
47 | + | ||
48 | + if ((a->vn | a->vm | a->vd) & a->q) { | ||
49 | + return false; | ||
50 | + } | ||
51 | + | ||
52 | + if (!vfp_access_check(s)) { | ||
53 | + return true; | ||
54 | + } | ||
55 | + | ||
56 | + opr_sz = (1 + a->q) * 8; | ||
57 | + fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; | ||
58 | + tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), | ||
59 | + vfp_reg_offset(1, a->vn), | ||
60 | + vfp_reg_offset(1, a->vm), | ||
61 | + opr_sz, opr_sz, 0, fn_gvec); | ||
62 | + return true; | ||
63 | +} | ||
64 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
65 | index XXXXXXX..XXXXXXX 100644 | ||
66 | --- a/target/arm/translate.c | ||
67 | +++ b/target/arm/translate.c | ||
68 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) | ||
69 | bool is_long = false, q = extract32(insn, 6, 1); | ||
70 | bool ptr_is_env = false; | ||
71 | |||
72 | - if ((insn & 0xfeb00f00) == 0xfc200d00) { | ||
73 | - /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ | ||
74 | - bool u = extract32(insn, 4, 1); | ||
75 | - if (!dc_isar_feature(aa32_dp, s)) { | ||
76 | - return 1; | ||
77 | - } | ||
78 | - fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; | ||
79 | - } else if ((insn & 0xff300f10) == 0xfc200810) { | ||
80 | + if ((insn & 0xff300f10) == 0xfc200810) { | ||
81 | /* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */ | ||
82 | int is_s = extract32(insn, 23, 1); | ||
83 | if (!dc_isar_feature(aa32_fhm, s)) { | ||
84 | -- | ||
85 | 2.20.1 | ||
86 | |||
87 | diff view generated by jsdifflib |
1 | Our BCM2836 type is really a generic one that can be any of | 1 | Convert the VFM[AS]L (vector) insns to decodetree. This is the last |
---|---|---|---|
2 | the bcm283x family. Rename it accordingly. We change only | 2 | insn in the legacy decoder for the 3same_ext group, so we can |
3 | the names which are visible via the header file to the | 3 | delete the legacy decoder function for the group entirely. |
4 | rest of the QEMU code, leaving private function names | ||
5 | in bcm2836.c as they are. | ||
6 | 4 | ||
7 | This is a preliminary to making bcm283x be an abstract | 5 | Note that in disas_thumb2_insn() the parts of this encoding space |
8 | parent class to specific types for the bcm2836 and bcm2837. | 6 | where the decodetree decoder returns false will correctly be directed |
7 | to illegal_op by the "(insn & (1 << 28))" check so they won't fall | ||
8 | into disas_coproc_insn() by mistake. | ||
9 | 9 | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 11 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 12 | Message-id: 20200430181003.21682-8-peter.maydell@linaro.org |
13 | Message-id: 20180313153458.26822-6-peter.maydell@linaro.org | ||
14 | --- | 13 | --- |
15 | include/hw/arm/bcm2836.h | 12 ++++++------ | 14 | target/arm/neon-shared.decode | 6 +++ |
16 | hw/arm/bcm2836.c | 17 +++++++++-------- | 15 | target/arm/translate-neon.inc.c | 31 +++++++++++ |
17 | hw/arm/raspi.c | 16 ++++++++-------- | 16 | target/arm/translate.c | 92 +-------------------------------- |
18 | 3 files changed, 23 insertions(+), 22 deletions(-) | 17 | 3 files changed, 38 insertions(+), 91 deletions(-) |
19 | 18 | ||
20 | diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h | 19 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode |
21 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/include/hw/arm/bcm2836.h | 21 | --- a/target/arm/neon-shared.decode |
23 | +++ b/include/hw/arm/bcm2836.h | 22 | +++ b/target/arm/neon-shared.decode |
24 | @@ -XXX,XX +XXX,XX @@ | 23 | @@ -XXX,XX +XXX,XX @@ VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \ |
25 | #include "hw/arm/bcm2835_peripherals.h" | 24 | # VUDOT and VSDOT |
26 | #include "hw/intc/bcm2836_control.h" | 25 | VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \ |
27 | 26 | vm=%vm_dp vn=%vn_dp vd=%vd_dp | |
28 | -#define TYPE_BCM2836 "bcm2836" | 27 | + |
29 | -#define BCM2836(obj) OBJECT_CHECK(BCM2836State, (obj), TYPE_BCM2836) | 28 | +# VFM[AS]L |
30 | +#define TYPE_BCM283X "bcm283x" | 29 | +VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ |
31 | +#define BCM283X(obj) OBJECT_CHECK(BCM283XState, (obj), TYPE_BCM283X) | 30 | + vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0 |
32 | 31 | +VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ | |
33 | -#define BCM2836_NCPUS 4 | 32 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 |
34 | +#define BCM283X_NCPUS 4 | 33 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c |
35 | |||
36 | -typedef struct BCM2836State { | ||
37 | +typedef struct BCM283XState { | ||
38 | /*< private >*/ | ||
39 | DeviceState parent_obj; | ||
40 | /*< public >*/ | ||
41 | @@ -XXX,XX +XXX,XX @@ typedef struct BCM2836State { | ||
42 | char *cpu_type; | ||
43 | uint32_t enabled_cpus; | ||
44 | |||
45 | - ARMCPU cpus[BCM2836_NCPUS]; | ||
46 | + ARMCPU cpus[BCM283X_NCPUS]; | ||
47 | BCM2836ControlState control; | ||
48 | BCM2835PeripheralState peripherals; | ||
49 | -} BCM2836State; | ||
50 | +} BCM283XState; | ||
51 | |||
52 | #endif /* BCM2836_H */ | ||
53 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | ||
54 | index XXXXXXX..XXXXXXX 100644 | 34 | index XXXXXXX..XXXXXXX 100644 |
55 | --- a/hw/arm/bcm2836.c | 35 | --- a/target/arm/translate-neon.inc.c |
56 | +++ b/hw/arm/bcm2836.c | 36 | +++ b/target/arm/translate-neon.inc.c |
57 | @@ -XXX,XX +XXX,XX @@ | 37 | @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a) |
58 | 38 | opr_sz, opr_sz, 0, fn_gvec); | |
59 | static void bcm2836_init(Object *obj) | 39 | return true; |
60 | { | ||
61 | - BCM2836State *s = BCM2836(obj); | ||
62 | + BCM283XState *s = BCM283X(obj); | ||
63 | |||
64 | object_initialize(&s->control, sizeof(s->control), TYPE_BCM2836_CONTROL); | ||
65 | object_property_add_child(obj, "control", OBJECT(&s->control), NULL); | ||
66 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_init(Object *obj) | ||
67 | |||
68 | static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
69 | { | ||
70 | - BCM2836State *s = BCM2836(dev); | ||
71 | + BCM283XState *s = BCM283X(dev); | ||
72 | Object *obj; | ||
73 | Error *err = NULL; | ||
74 | int n; | ||
75 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
76 | /* common peripherals from bcm2835 */ | ||
77 | |||
78 | obj = OBJECT(dev); | ||
79 | - for (n = 0; n < BCM2836_NCPUS; n++) { | ||
80 | + for (n = 0; n < BCM283X_NCPUS; n++) { | ||
81 | object_initialize(&s->cpus[n], sizeof(s->cpus[n]), | ||
82 | s->cpu_type); | ||
83 | object_property_add_child(obj, "cpu[*]", OBJECT(&s->cpus[n]), | ||
84 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
85 | sysbus_connect_irq(SYS_BUS_DEVICE(&s->peripherals), 1, | ||
86 | qdev_get_gpio_in_named(DEVICE(&s->control), "gpu-fiq", 0)); | ||
87 | |||
88 | - for (n = 0; n < BCM2836_NCPUS; n++) { | ||
89 | + for (n = 0; n < BCM283X_NCPUS; n++) { | ||
90 | /* Mirror bcm2836, which has clusterid set to 0xf | ||
91 | * TODO: this should be converted to a property of ARM_CPU | ||
92 | */ | ||
93 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | ||
94 | } | 40 | } |
95 | 41 | + | |
96 | static Property bcm2836_props[] = { | 42 | +static bool trans_VFML(DisasContext *s, arg_VFML *a) |
97 | - DEFINE_PROP_STRING("cpu-type", BCM2836State, cpu_type), | 43 | +{ |
98 | - DEFINE_PROP_UINT32("enabled-cpus", BCM2836State, enabled_cpus, BCM2836_NCPUS), | 44 | + int opr_sz; |
99 | + DEFINE_PROP_STRING("cpu-type", BCM283XState, cpu_type), | 45 | + |
100 | + DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, | 46 | + if (!dc_isar_feature(aa32_fhm, s)) { |
101 | + BCM283X_NCPUS), | 47 | + return false; |
102 | DEFINE_PROP_END_OF_LIST() | 48 | + } |
103 | }; | 49 | + |
104 | 50 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | |
105 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_class_init(ObjectClass *oc, void *data) | 51 | + if (!dc_isar_feature(aa32_simd_r32, s) && |
52 | + (a->vd & 0x10)) { | ||
53 | + return false; | ||
54 | + } | ||
55 | + | ||
56 | + if (a->vd & a->q) { | ||
57 | + return false; | ||
58 | + } | ||
59 | + | ||
60 | + if (!vfp_access_check(s)) { | ||
61 | + return true; | ||
62 | + } | ||
63 | + | ||
64 | + opr_sz = (1 + a->q) * 8; | ||
65 | + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), | ||
66 | + vfp_reg_offset(a->q, a->vn), | ||
67 | + vfp_reg_offset(a->q, a->vm), | ||
68 | + cpu_env, opr_sz, opr_sz, a->s, /* is_2 == 0 */ | ||
69 | + gen_helper_gvec_fmlal_a32); | ||
70 | + return true; | ||
71 | +} | ||
72 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
73 | index XXXXXXX..XXXXXXX 100644 | ||
74 | --- a/target/arm/translate.c | ||
75 | +++ b/target/arm/translate.c | ||
76 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
77 | return 0; | ||
106 | } | 78 | } |
107 | 79 | ||
108 | static const TypeInfo bcm2836_type_info = { | 80 | -/* Advanced SIMD three registers of the same length extension. |
109 | - .name = TYPE_BCM2836, | 81 | - * 31 25 23 22 20 16 12 11 10 9 8 3 0 |
110 | + .name = TYPE_BCM283X, | 82 | - * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+ |
111 | .parent = TYPE_DEVICE, | 83 | - * | 1 1 1 1 1 1 0 | op1 | D | op2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm | |
112 | - .instance_size = sizeof(BCM2836State), | 84 | - * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+ |
113 | + .instance_size = sizeof(BCM283XState), | 85 | - */ |
114 | .instance_init = bcm2836_init, | 86 | -static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) |
115 | .class_init = bcm2836_class_init, | 87 | -{ |
116 | }; | 88 | - gen_helper_gvec_3 *fn_gvec = NULL; |
117 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 89 | - gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; |
118 | index XXXXXXX..XXXXXXX 100644 | 90 | - int rd, rn, rm, opr_sz; |
119 | --- a/hw/arm/raspi.c | 91 | - int data = 0; |
120 | +++ b/hw/arm/raspi.c | 92 | - int off_rn, off_rm; |
121 | @@ -XXX,XX +XXX,XX @@ | 93 | - bool is_long = false, q = extract32(insn, 6, 1); |
122 | static const int raspi_boardid[] = {[1] = 0xc42, [2] = 0xc43, [3] = 0xc44}; | 94 | - bool ptr_is_env = false; |
123 | 95 | - | |
124 | typedef struct RasPiState { | 96 | - if ((insn & 0xff300f10) == 0xfc200810) { |
125 | - BCM2836State soc; | 97 | - /* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */ |
126 | + BCM283XState soc; | 98 | - int is_s = extract32(insn, 23, 1); |
127 | MemoryRegion ram; | 99 | - if (!dc_isar_feature(aa32_fhm, s)) { |
128 | } RasPiState; | 100 | - return 1; |
129 | 101 | - } | |
130 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | 102 | - is_long = true; |
131 | BusState *bus; | 103 | - data = is_s; /* is_2 == 0 */ |
132 | DeviceState *carddev; | 104 | - fn_gvec_ptr = gen_helper_gvec_fmlal_a32; |
133 | 105 | - ptr_is_env = true; | |
134 | - object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM2836); | 106 | - } else { |
135 | + object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM283X); | 107 | - return 1; |
136 | object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc), | 108 | - } |
137 | &error_abort); | 109 | - |
138 | 110 | - VFP_DREG_D(rd, insn); | |
139 | @@ -XXX,XX +XXX,XX @@ static void raspi2_machine_init(MachineClass *mc) | 111 | - if (rd & q) { |
140 | mc->no_floppy = 1; | 112 | - return 1; |
141 | mc->no_cdrom = 1; | 113 | - } |
142 | mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15"); | 114 | - if (q || !is_long) { |
143 | - mc->max_cpus = BCM2836_NCPUS; | 115 | - VFP_DREG_N(rn, insn); |
144 | - mc->min_cpus = BCM2836_NCPUS; | 116 | - VFP_DREG_M(rm, insn); |
145 | - mc->default_cpus = BCM2836_NCPUS; | 117 | - if ((rn | rm) & q & !is_long) { |
146 | + mc->max_cpus = BCM283X_NCPUS; | 118 | - return 1; |
147 | + mc->min_cpus = BCM283X_NCPUS; | 119 | - } |
148 | + mc->default_cpus = BCM283X_NCPUS; | 120 | - off_rn = vfp_reg_offset(1, rn); |
149 | mc->default_ram_size = 1024 * 1024 * 1024; | 121 | - off_rm = vfp_reg_offset(1, rm); |
150 | mc->ignore_memory_transaction_failures = true; | 122 | - } else { |
151 | }; | 123 | - rn = VFP_SREG_N(insn); |
152 | @@ -XXX,XX +XXX,XX @@ static void raspi3_machine_init(MachineClass *mc) | 124 | - rm = VFP_SREG_M(insn); |
153 | mc->no_floppy = 1; | 125 | - off_rn = vfp_reg_offset(0, rn); |
154 | mc->no_cdrom = 1; | 126 | - off_rm = vfp_reg_offset(0, rm); |
155 | mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a53"); | 127 | - } |
156 | - mc->max_cpus = BCM2836_NCPUS; | 128 | - |
157 | - mc->min_cpus = BCM2836_NCPUS; | 129 | - if (s->fp_excp_el) { |
158 | - mc->default_cpus = BCM2836_NCPUS; | 130 | - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, |
159 | + mc->max_cpus = BCM283X_NCPUS; | 131 | - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); |
160 | + mc->min_cpus = BCM283X_NCPUS; | 132 | - return 0; |
161 | + mc->default_cpus = BCM283X_NCPUS; | 133 | - } |
162 | mc->default_ram_size = 1024 * 1024 * 1024; | 134 | - if (!s->vfp_enabled) { |
163 | } | 135 | - return 1; |
164 | DEFINE_MACHINE("raspi3", raspi3_machine_init) | 136 | - } |
137 | - | ||
138 | - opr_sz = (1 + q) * 8; | ||
139 | - if (fn_gvec_ptr) { | ||
140 | - TCGv_ptr ptr; | ||
141 | - if (ptr_is_env) { | ||
142 | - ptr = cpu_env; | ||
143 | - } else { | ||
144 | - ptr = get_fpstatus_ptr(1); | ||
145 | - } | ||
146 | - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr, | ||
147 | - opr_sz, opr_sz, data, fn_gvec_ptr); | ||
148 | - if (!ptr_is_env) { | ||
149 | - tcg_temp_free_ptr(ptr); | ||
150 | - } | ||
151 | - } else { | ||
152 | - tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm, | ||
153 | - opr_sz, opr_sz, data, fn_gvec); | ||
154 | - } | ||
155 | - return 0; | ||
156 | -} | ||
157 | - | ||
158 | /* Advanced SIMD two registers and a scalar extension. | ||
159 | * 31 24 23 22 20 16 12 11 10 9 8 3 0 | ||
160 | * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ | ||
161 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) | ||
162 | } | ||
163 | } | ||
164 | } | ||
165 | - } else if ((insn & 0x0e000a00) == 0x0c000800 | ||
166 | - && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
167 | - if (disas_neon_insn_3same_ext(s, insn)) { | ||
168 | - goto illegal_op; | ||
169 | - } | ||
170 | - return; | ||
171 | } else if ((insn & 0x0f000a00) == 0x0e000800 | ||
172 | && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
173 | if (disas_neon_insn_2reg_scalar_ext(s, insn)) { | ||
174 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | ||
175 | } | ||
176 | break; | ||
177 | } | ||
178 | - if ((insn & 0xfe000a00) == 0xfc000800 | ||
179 | + if ((insn & 0xff000a00) == 0xfe000800 | ||
180 | && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
181 | /* The Thumb2 and ARM encodings are identical. */ | ||
182 | - if (disas_neon_insn_3same_ext(s, insn)) { | ||
183 | - goto illegal_op; | ||
184 | - } | ||
185 | - } else if ((insn & 0xff000a00) == 0xfe000800 | ||
186 | - && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
187 | - /* The Thumb2 and ARM encodings are identical. */ | ||
188 | if (disas_neon_insn_2reg_scalar_ext(s, insn)) { | ||
189 | goto illegal_op; | ||
190 | } | ||
165 | -- | 191 | -- |
166 | 2.16.2 | 192 | 2.20.1 |
167 | 193 | ||
168 | 194 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert VCMLA (scalar) in the 2reg-scalar-ext group to decodetree. | ||
1 | 2 | ||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Message-id: 20200430181003.21682-9-peter.maydell@linaro.org | ||
6 | --- | ||
7 | target/arm/neon-shared.decode | 5 +++++ | ||
8 | target/arm/translate-neon.inc.c | 40 +++++++++++++++++++++++++++++++++ | ||
9 | target/arm/translate.c | 26 +-------------------- | ||
10 | 3 files changed, 46 insertions(+), 25 deletions(-) | ||
11 | |||
12 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/target/arm/neon-shared.decode | ||
15 | +++ b/target/arm/neon-shared.decode | ||
16 | @@ -XXX,XX +XXX,XX @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \ | ||
17 | vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0 | ||
18 | VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \ | ||
19 | vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1 | ||
20 | + | ||
21 | +VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ | ||
22 | + vn=%vn_dp vd=%vd_dp size=0 | ||
23 | +VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ | ||
24 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 | ||
25 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
26 | index XXXXXXX..XXXXXXX 100644 | ||
27 | --- a/target/arm/translate-neon.inc.c | ||
28 | +++ b/target/arm/translate-neon.inc.c | ||
29 | @@ -XXX,XX +XXX,XX @@ static bool trans_VFML(DisasContext *s, arg_VFML *a) | ||
30 | gen_helper_gvec_fmlal_a32); | ||
31 | return true; | ||
32 | } | ||
33 | + | ||
34 | +static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) | ||
35 | +{ | ||
36 | + gen_helper_gvec_3_ptr *fn_gvec_ptr; | ||
37 | + int opr_sz; | ||
38 | + TCGv_ptr fpst; | ||
39 | + | ||
40 | + if (!dc_isar_feature(aa32_vcma, s)) { | ||
41 | + return false; | ||
42 | + } | ||
43 | + if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) { | ||
44 | + return false; | ||
45 | + } | ||
46 | + | ||
47 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
48 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
49 | + ((a->vd | a->vn | a->vm) & 0x10)) { | ||
50 | + return false; | ||
51 | + } | ||
52 | + | ||
53 | + if ((a->vd | a->vn) & a->q) { | ||
54 | + return false; | ||
55 | + } | ||
56 | + | ||
57 | + if (!vfp_access_check(s)) { | ||
58 | + return true; | ||
59 | + } | ||
60 | + | ||
61 | + fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx | ||
62 | + : gen_helper_gvec_fcmlah_idx); | ||
63 | + opr_sz = (1 + a->q) * 8; | ||
64 | + fpst = get_fpstatus_ptr(1); | ||
65 | + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), | ||
66 | + vfp_reg_offset(1, a->vn), | ||
67 | + vfp_reg_offset(1, a->vm), | ||
68 | + fpst, opr_sz, opr_sz, | ||
69 | + (a->index << 2) | a->rot, fn_gvec_ptr); | ||
70 | + tcg_temp_free_ptr(fpst); | ||
71 | + return true; | ||
72 | +} | ||
73 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
74 | index XXXXXXX..XXXXXXX 100644 | ||
75 | --- a/target/arm/translate.c | ||
76 | +++ b/target/arm/translate.c | ||
77 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) | ||
78 | bool is_long = false, q = extract32(insn, 6, 1); | ||
79 | bool ptr_is_env = false; | ||
80 | |||
81 | - if ((insn & 0xff000f10) == 0xfe000800) { | ||
82 | - /* VCMLA (indexed) -- 1111 1110 S.RR .... .... 1000 ...0 .... */ | ||
83 | - int rot = extract32(insn, 20, 2); | ||
84 | - int size = extract32(insn, 23, 1); | ||
85 | - int index; | ||
86 | - | ||
87 | - if (!dc_isar_feature(aa32_vcma, s)) { | ||
88 | - return 1; | ||
89 | - } | ||
90 | - if (size == 0) { | ||
91 | - if (!dc_isar_feature(aa32_fp16_arith, s)) { | ||
92 | - return 1; | ||
93 | - } | ||
94 | - /* For fp16, rm is just Vm, and index is M. */ | ||
95 | - rm = extract32(insn, 0, 4); | ||
96 | - index = extract32(insn, 5, 1); | ||
97 | - } else { | ||
98 | - /* For fp32, rm is the usual M:Vm, and index is 0. */ | ||
99 | - VFP_DREG_M(rm, insn); | ||
100 | - index = 0; | ||
101 | - } | ||
102 | - data = (index << 2) | rot; | ||
103 | - fn_gvec_ptr = (size ? gen_helper_gvec_fcmlas_idx | ||
104 | - : gen_helper_gvec_fcmlah_idx); | ||
105 | - } else if ((insn & 0xffb00f00) == 0xfe200d00) { | ||
106 | + if ((insn & 0xffb00f00) == 0xfe200d00) { | ||
107 | /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ | ||
108 | int u = extract32(insn, 4, 1); | ||
109 | |||
110 | -- | ||
111 | 2.20.1 | ||
112 | |||
113 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the V[US]DOT (scalar) insns in the 2reg-scalar-ext group | ||
2 | to decodetree. | ||
1 | 3 | ||
4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
6 | Message-id: 20200430181003.21682-10-peter.maydell@linaro.org | ||
7 | --- | ||
8 | target/arm/neon-shared.decode | 3 +++ | ||
9 | target/arm/translate-neon.inc.c | 35 +++++++++++++++++++++++++++++++++ | ||
10 | target/arm/translate.c | 13 +----------- | ||
11 | 3 files changed, 39 insertions(+), 12 deletions(-) | ||
12 | |||
13 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/target/arm/neon-shared.decode | ||
16 | +++ b/target/arm/neon-shared.decode | ||
17 | @@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \ | ||
18 | vn=%vn_dp vd=%vd_dp size=0 | ||
19 | VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ | ||
20 | vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0 | ||
21 | + | ||
22 | +VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ | ||
23 | + vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
24 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
25 | index XXXXXXX..XXXXXXX 100644 | ||
26 | --- a/target/arm/translate-neon.inc.c | ||
27 | +++ b/target/arm/translate-neon.inc.c | ||
28 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a) | ||
29 | tcg_temp_free_ptr(fpst); | ||
30 | return true; | ||
31 | } | ||
32 | + | ||
33 | +static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) | ||
34 | +{ | ||
35 | + gen_helper_gvec_3 *fn_gvec; | ||
36 | + int opr_sz; | ||
37 | + TCGv_ptr fpst; | ||
38 | + | ||
39 | + if (!dc_isar_feature(aa32_dp, s)) { | ||
40 | + return false; | ||
41 | + } | ||
42 | + | ||
43 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
44 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
45 | + ((a->vd | a->vn) & 0x10)) { | ||
46 | + return false; | ||
47 | + } | ||
48 | + | ||
49 | + if ((a->vd | a->vn) & a->q) { | ||
50 | + return false; | ||
51 | + } | ||
52 | + | ||
53 | + if (!vfp_access_check(s)) { | ||
54 | + return true; | ||
55 | + } | ||
56 | + | ||
57 | + fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; | ||
58 | + opr_sz = (1 + a->q) * 8; | ||
59 | + fpst = get_fpstatus_ptr(1); | ||
60 | + tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd), | ||
61 | + vfp_reg_offset(1, a->vn), | ||
62 | + vfp_reg_offset(1, a->rm), | ||
63 | + opr_sz, opr_sz, a->index, fn_gvec); | ||
64 | + tcg_temp_free_ptr(fpst); | ||
65 | + return true; | ||
66 | +} | ||
67 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
68 | index XXXXXXX..XXXXXXX 100644 | ||
69 | --- a/target/arm/translate.c | ||
70 | +++ b/target/arm/translate.c | ||
71 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) | ||
72 | bool is_long = false, q = extract32(insn, 6, 1); | ||
73 | bool ptr_is_env = false; | ||
74 | |||
75 | - if ((insn & 0xffb00f00) == 0xfe200d00) { | ||
76 | - /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ | ||
77 | - int u = extract32(insn, 4, 1); | ||
78 | - | ||
79 | - if (!dc_isar_feature(aa32_dp, s)) { | ||
80 | - return 1; | ||
81 | - } | ||
82 | - fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; | ||
83 | - /* rm is just Vm, and index is M. */ | ||
84 | - data = extract32(insn, 5, 1); /* index */ | ||
85 | - rm = extract32(insn, 0, 4); | ||
86 | - } else if ((insn & 0xffa00f10) == 0xfe000810) { | ||
87 | + if ((insn & 0xffa00f10) == 0xfe000810) { | ||
88 | /* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */ | ||
89 | int is_s = extract32(insn, 20, 1); | ||
90 | int vm20 = extract32(insn, 0, 3); | ||
91 | -- | ||
92 | 2.20.1 | ||
93 | |||
94 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | Convert the VFM[AS]L (scalar) insns in the 2reg-scalar-ext group | |
2 | to decodetree. These are the last ones in the group so we can remove | ||
3 | all the legacy decode for the group. | ||
4 | |||
5 | Note that in disas_thumb2_insn() the parts of this encoding space | ||
6 | where the decodetree decoder returns false will correctly be directed | ||
7 | to illegal_op by the "(insn & (1 << 28))" check so they won't fall | ||
8 | into disas_coproc_insn() by mistake. | ||
9 | |||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
12 | Message-id: 20200430181003.21682-11-peter.maydell@linaro.org | ||
13 | --- | ||
14 | target/arm/neon-shared.decode | 7 +++ | ||
15 | target/arm/translate-neon.inc.c | 32 ++++++++++ | ||
16 | target/arm/translate.c | 107 +------------------------------- | ||
17 | 3 files changed, 40 insertions(+), 106 deletions(-) | ||
18 | |||
19 | diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode | ||
20 | index XXXXXXX..XXXXXXX 100644 | ||
21 | --- a/target/arm/neon-shared.decode | ||
22 | +++ b/target/arm/neon-shared.decode | ||
23 | @@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \ | ||
24 | |||
25 | VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \ | ||
26 | vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
27 | + | ||
28 | +%vfml_scalar_q0_rm 0:3 5:1 | ||
29 | +%vfml_scalar_q1_index 5:1 3:1 | ||
30 | +VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 0 . 1 index:1 ... \ | ||
31 | + rm=%vfml_scalar_q0_rm vn=%vn_sp vd=%vd_dp q=0 | ||
32 | +VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 1 . 1 . rm:3 \ | ||
33 | + index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp q=1 | ||
34 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
35 | index XXXXXXX..XXXXXXX 100644 | ||
36 | --- a/target/arm/translate-neon.inc.c | ||
37 | +++ b/target/arm/translate-neon.inc.c | ||
38 | @@ -XXX,XX +XXX,XX @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a) | ||
39 | tcg_temp_free_ptr(fpst); | ||
40 | return true; | ||
41 | } | ||
42 | + | ||
43 | +static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) | ||
44 | +{ | ||
45 | + int opr_sz; | ||
46 | + | ||
47 | + if (!dc_isar_feature(aa32_fhm, s)) { | ||
48 | + return false; | ||
49 | + } | ||
50 | + | ||
51 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
52 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
53 | + ((a->vd & 0x10) || (a->q && (a->vn & 0x10)))) { | ||
54 | + return false; | ||
55 | + } | ||
56 | + | ||
57 | + if (a->vd & a->q) { | ||
58 | + return false; | ||
59 | + } | ||
60 | + | ||
61 | + if (!vfp_access_check(s)) { | ||
62 | + return true; | ||
63 | + } | ||
64 | + | ||
65 | + opr_sz = (1 + a->q) * 8; | ||
66 | + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), | ||
67 | + vfp_reg_offset(a->q, a->vn), | ||
68 | + vfp_reg_offset(a->q, a->rm), | ||
69 | + cpu_env, opr_sz, opr_sz, | ||
70 | + (a->index << 2) | a->s, /* is_2 == 0 */ | ||
71 | + gen_helper_gvec_fmlal_idx_a32); | ||
72 | + return true; | ||
73 | +} | ||
74 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
75 | index XXXXXXX..XXXXXXX 100644 | ||
76 | --- a/target/arm/translate.c | ||
77 | +++ b/target/arm/translate.c | ||
78 | @@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) | ||
79 | } | ||
80 | |||
81 | #define VFP_REG_SHR(x, n) (((n) > 0) ? (x) >> (n) : (x) << -(n)) | ||
82 | -#define VFP_SREG(insn, bigbit, smallbit) \ | ||
83 | - ((VFP_REG_SHR(insn, bigbit - 1) & 0x1e) | (((insn) >> (smallbit)) & 1)) | ||
84 | #define VFP_DREG(reg, insn, bigbit, smallbit) do { \ | ||
85 | if (dc_isar_feature(aa32_simd_r32, s)) { \ | ||
86 | reg = (((insn) >> (bigbit)) & 0x0f) \ | ||
87 | @@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) | ||
88 | reg = ((insn) >> (bigbit)) & 0x0f; \ | ||
89 | }} while (0) | ||
90 | |||
91 | -#define VFP_SREG_D(insn) VFP_SREG(insn, 12, 22) | ||
92 | #define VFP_DREG_D(reg, insn) VFP_DREG(reg, insn, 12, 22) | ||
93 | -#define VFP_SREG_N(insn) VFP_SREG(insn, 16, 7) | ||
94 | #define VFP_DREG_N(reg, insn) VFP_DREG(reg, insn, 16, 7) | ||
95 | -#define VFP_SREG_M(insn) VFP_SREG(insn, 0, 5) | ||
96 | #define VFP_DREG_M(reg, insn) VFP_DREG(reg, insn, 0, 5) | ||
97 | |||
98 | static void gen_neon_dup_low16(TCGv_i32 var) | ||
99 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
100 | return 0; | ||
101 | } | ||
102 | |||
103 | -/* Advanced SIMD two registers and a scalar extension. | ||
104 | - * 31 24 23 22 20 16 12 11 10 9 8 3 0 | ||
105 | - * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ | ||
106 | - * | 1 1 1 1 1 1 1 0 | o1 | D | o2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm | | ||
107 | - * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+ | ||
108 | - * | ||
109 | - */ | ||
110 | - | ||
111 | -static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) | ||
112 | -{ | ||
113 | - gen_helper_gvec_3 *fn_gvec = NULL; | ||
114 | - gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; | ||
115 | - int rd, rn, rm, opr_sz, data; | ||
116 | - int off_rn, off_rm; | ||
117 | - bool is_long = false, q = extract32(insn, 6, 1); | ||
118 | - bool ptr_is_env = false; | ||
119 | - | ||
120 | - if ((insn & 0xffa00f10) == 0xfe000810) { | ||
121 | - /* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */ | ||
122 | - int is_s = extract32(insn, 20, 1); | ||
123 | - int vm20 = extract32(insn, 0, 3); | ||
124 | - int vm3 = extract32(insn, 3, 1); | ||
125 | - int m = extract32(insn, 5, 1); | ||
126 | - int index; | ||
127 | - | ||
128 | - if (!dc_isar_feature(aa32_fhm, s)) { | ||
129 | - return 1; | ||
130 | - } | ||
131 | - if (q) { | ||
132 | - rm = vm20; | ||
133 | - index = m * 2 + vm3; | ||
134 | - } else { | ||
135 | - rm = vm20 * 2 + m; | ||
136 | - index = vm3; | ||
137 | - } | ||
138 | - is_long = true; | ||
139 | - data = (index << 2) | is_s; /* is_2 == 0 */ | ||
140 | - fn_gvec_ptr = gen_helper_gvec_fmlal_idx_a32; | ||
141 | - ptr_is_env = true; | ||
142 | - } else { | ||
143 | - return 1; | ||
144 | - } | ||
145 | - | ||
146 | - VFP_DREG_D(rd, insn); | ||
147 | - if (rd & q) { | ||
148 | - return 1; | ||
149 | - } | ||
150 | - if (q || !is_long) { | ||
151 | - VFP_DREG_N(rn, insn); | ||
152 | - if (rn & q & !is_long) { | ||
153 | - return 1; | ||
154 | - } | ||
155 | - off_rn = vfp_reg_offset(1, rn); | ||
156 | - off_rm = vfp_reg_offset(1, rm); | ||
157 | - } else { | ||
158 | - rn = VFP_SREG_N(insn); | ||
159 | - off_rn = vfp_reg_offset(0, rn); | ||
160 | - off_rm = vfp_reg_offset(0, rm); | ||
161 | - } | ||
162 | - if (s->fp_excp_el) { | ||
163 | - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, | ||
164 | - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); | ||
165 | - return 0; | ||
166 | - } | ||
167 | - if (!s->vfp_enabled) { | ||
168 | - return 1; | ||
169 | - } | ||
170 | - | ||
171 | - opr_sz = (1 + q) * 8; | ||
172 | - if (fn_gvec_ptr) { | ||
173 | - TCGv_ptr ptr; | ||
174 | - if (ptr_is_env) { | ||
175 | - ptr = cpu_env; | ||
176 | - } else { | ||
177 | - ptr = get_fpstatus_ptr(1); | ||
178 | - } | ||
179 | - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr, | ||
180 | - opr_sz, opr_sz, data, fn_gvec_ptr); | ||
181 | - if (!ptr_is_env) { | ||
182 | - tcg_temp_free_ptr(ptr); | ||
183 | - } | ||
184 | - } else { | ||
185 | - tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm, | ||
186 | - opr_sz, opr_sz, data, fn_gvec); | ||
187 | - } | ||
188 | - return 0; | ||
189 | -} | ||
190 | - | ||
191 | static int disas_coproc_insn(DisasContext *s, uint32_t insn) | ||
192 | { | ||
193 | int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2; | ||
194 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) | ||
195 | } | ||
196 | } | ||
197 | } | ||
198 | - } else if ((insn & 0x0f000a00) == 0x0e000800 | ||
199 | - && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
200 | - if (disas_neon_insn_2reg_scalar_ext(s, insn)) { | ||
201 | - goto illegal_op; | ||
202 | - } | ||
203 | - return; | ||
204 | } | ||
205 | goto illegal_op; | ||
206 | } | ||
207 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | ||
208 | } | ||
209 | break; | ||
210 | } | ||
211 | - if ((insn & 0xff000a00) == 0xfe000800 | ||
212 | - && arm_dc_feature(s, ARM_FEATURE_V8)) { | ||
213 | - /* The Thumb2 and ARM encodings are identical. */ | ||
214 | - if (disas_neon_insn_2reg_scalar_ext(s, insn)) { | ||
215 | - goto illegal_op; | ||
216 | - } | ||
217 | - } else if (((insn >> 24) & 3) == 3) { | ||
218 | + if (((insn >> 24) & 3) == 3) { | ||
219 | /* Translate into the equivalent ARM encoding. */ | ||
220 | insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28); | ||
221 | if (disas_neon_data_insn(s, insn)) { | ||
222 | -- | ||
223 | 2.20.1 | ||
224 | |||
225 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | Convert the Neon "load/store multiple structures" insns to decodetree. | |
2 | |||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Message-id: 20200430181003.21682-12-peter.maydell@linaro.org | ||
6 | --- | ||
7 | target/arm/neon-ls.decode | 7 ++ | ||
8 | target/arm/translate-neon.inc.c | 124 ++++++++++++++++++++++++++++++++ | ||
9 | target/arm/translate.c | 91 +---------------------- | ||
10 | 3 files changed, 133 insertions(+), 89 deletions(-) | ||
11 | |||
12 | diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/target/arm/neon-ls.decode | ||
15 | +++ b/target/arm/neon-ls.decode | ||
16 | @@ -XXX,XX +XXX,XX @@ | ||
17 | # 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx | ||
18 | # This file works on the A32 encoding only; calling code for T32 has to | ||
19 | # transform the insn into the A32 version first. | ||
20 | + | ||
21 | +%vd_dp 22:1 12:4 | ||
22 | + | ||
23 | +# Neon load/store multiple structures | ||
24 | + | ||
25 | +VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ | ||
26 | + vd=%vd_dp | ||
27 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
28 | index XXXXXXX..XXXXXXX 100644 | ||
29 | --- a/target/arm/translate-neon.inc.c | ||
30 | +++ b/target/arm/translate-neon.inc.c | ||
31 | @@ -XXX,XX +XXX,XX @@ static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a) | ||
32 | gen_helper_gvec_fmlal_idx_a32); | ||
33 | return true; | ||
34 | } | ||
35 | + | ||
36 | +static struct { | ||
37 | + int nregs; | ||
38 | + int interleave; | ||
39 | + int spacing; | ||
40 | +} const neon_ls_element_type[11] = { | ||
41 | + {1, 4, 1}, | ||
42 | + {1, 4, 2}, | ||
43 | + {4, 1, 1}, | ||
44 | + {2, 2, 2}, | ||
45 | + {1, 3, 1}, | ||
46 | + {1, 3, 2}, | ||
47 | + {3, 1, 1}, | ||
48 | + {1, 1, 1}, | ||
49 | + {1, 2, 1}, | ||
50 | + {1, 2, 2}, | ||
51 | + {2, 1, 1} | ||
52 | +}; | ||
53 | + | ||
54 | +static void gen_neon_ldst_base_update(DisasContext *s, int rm, int rn, | ||
55 | + int stride) | ||
56 | +{ | ||
57 | + if (rm != 15) { | ||
58 | + TCGv_i32 base; | ||
59 | + | ||
60 | + base = load_reg(s, rn); | ||
61 | + if (rm == 13) { | ||
62 | + tcg_gen_addi_i32(base, base, stride); | ||
63 | + } else { | ||
64 | + TCGv_i32 index; | ||
65 | + index = load_reg(s, rm); | ||
66 | + tcg_gen_add_i32(base, base, index); | ||
67 | + tcg_temp_free_i32(index); | ||
68 | + } | ||
69 | + store_reg(s, rn, base); | ||
70 | + } | ||
71 | +} | ||
72 | + | ||
73 | +static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) | ||
74 | +{ | ||
75 | + /* Neon load/store multiple structures */ | ||
76 | + int nregs, interleave, spacing, reg, n; | ||
77 | + MemOp endian = s->be_data; | ||
78 | + int mmu_idx = get_mem_index(s); | ||
79 | + int size = a->size; | ||
80 | + TCGv_i64 tmp64; | ||
81 | + TCGv_i32 addr, tmp; | ||
82 | + | ||
83 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
84 | + return false; | ||
85 | + } | ||
86 | + | ||
87 | + /* UNDEF accesses to D16-D31 if they don't exist */ | ||
88 | + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { | ||
89 | + return false; | ||
90 | + } | ||
91 | + if (a->itype > 10) { | ||
92 | + return false; | ||
93 | + } | ||
94 | + /* Catch UNDEF cases for bad values of align field */ | ||
95 | + switch (a->itype & 0xc) { | ||
96 | + case 4: | ||
97 | + if (a->align >= 2) { | ||
98 | + return false; | ||
99 | + } | ||
100 | + break; | ||
101 | + case 8: | ||
102 | + if (a->align == 3) { | ||
103 | + return false; | ||
104 | + } | ||
105 | + break; | ||
106 | + default: | ||
107 | + break; | ||
108 | + } | ||
109 | + nregs = neon_ls_element_type[a->itype].nregs; | ||
110 | + interleave = neon_ls_element_type[a->itype].interleave; | ||
111 | + spacing = neon_ls_element_type[a->itype].spacing; | ||
112 | + if (size == 3 && (interleave | spacing) != 1) { | ||
113 | + return false; | ||
114 | + } | ||
115 | + | ||
116 | + if (!vfp_access_check(s)) { | ||
117 | + return true; | ||
118 | + } | ||
119 | + | ||
120 | + /* For our purposes, bytes are always little-endian. */ | ||
121 | + if (size == 0) { | ||
122 | + endian = MO_LE; | ||
123 | + } | ||
124 | + /* | ||
125 | + * Consecutive little-endian elements from a single register | ||
126 | + * can be promoted to a larger little-endian operation. | ||
127 | + */ | ||
128 | + if (interleave == 1 && endian == MO_LE) { | ||
129 | + size = 3; | ||
130 | + } | ||
131 | + tmp64 = tcg_temp_new_i64(); | ||
132 | + addr = tcg_temp_new_i32(); | ||
133 | + tmp = tcg_const_i32(1 << size); | ||
134 | + load_reg_var(s, addr, a->rn); | ||
135 | + for (reg = 0; reg < nregs; reg++) { | ||
136 | + for (n = 0; n < 8 >> size; n++) { | ||
137 | + int xs; | ||
138 | + for (xs = 0; xs < interleave; xs++) { | ||
139 | + int tt = a->vd + reg + spacing * xs; | ||
140 | + | ||
141 | + if (a->l) { | ||
142 | + gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); | ||
143 | + neon_store_element64(tt, n, size, tmp64); | ||
144 | + } else { | ||
145 | + neon_load_element64(tmp64, tt, n, size); | ||
146 | + gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); | ||
147 | + } | ||
148 | + tcg_gen_add_i32(addr, addr, tmp); | ||
149 | + } | ||
150 | + } | ||
151 | + } | ||
152 | + tcg_temp_free_i32(addr); | ||
153 | + tcg_temp_free_i32(tmp); | ||
154 | + tcg_temp_free_i64(tmp64); | ||
155 | + | ||
156 | + gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8); | ||
157 | + return true; | ||
158 | +} | ||
159 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
160 | index XXXXXXX..XXXXXXX 100644 | ||
161 | --- a/target/arm/translate.c | ||
162 | +++ b/target/arm/translate.c | ||
163 | @@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) | ||
164 | } | ||
165 | |||
166 | |||
167 | -static struct { | ||
168 | - int nregs; | ||
169 | - int interleave; | ||
170 | - int spacing; | ||
171 | -} const neon_ls_element_type[11] = { | ||
172 | - {1, 4, 1}, | ||
173 | - {1, 4, 2}, | ||
174 | - {4, 1, 1}, | ||
175 | - {2, 2, 2}, | ||
176 | - {1, 3, 1}, | ||
177 | - {1, 3, 2}, | ||
178 | - {3, 1, 1}, | ||
179 | - {1, 1, 1}, | ||
180 | - {1, 2, 1}, | ||
181 | - {1, 2, 2}, | ||
182 | - {2, 1, 1} | ||
183 | -}; | ||
184 | - | ||
185 | /* Translate a NEON load/store element instruction. Return nonzero if the | ||
186 | instruction is invalid. */ | ||
187 | static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) | ||
188 | { | ||
189 | int rd, rn, rm; | ||
190 | - int op; | ||
191 | int nregs; | ||
192 | - int interleave; | ||
193 | - int spacing; | ||
194 | int stride; | ||
195 | int size; | ||
196 | int reg; | ||
197 | int load; | ||
198 | - int n; | ||
199 | int vec_size; | ||
200 | - int mmu_idx; | ||
201 | - MemOp endian; | ||
202 | TCGv_i32 addr; | ||
203 | TCGv_i32 tmp; | ||
204 | - TCGv_i32 tmp2; | ||
205 | - TCGv_i64 tmp64; | ||
206 | |||
207 | if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
208 | return 1; | ||
209 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) | ||
210 | rn = (insn >> 16) & 0xf; | ||
211 | rm = insn & 0xf; | ||
212 | load = (insn & (1 << 21)) != 0; | ||
213 | - endian = s->be_data; | ||
214 | - mmu_idx = get_mem_index(s); | ||
215 | if ((insn & (1 << 23)) == 0) { | ||
216 | - /* Load store all elements. */ | ||
217 | - op = (insn >> 8) & 0xf; | ||
218 | - size = (insn >> 6) & 3; | ||
219 | - if (op > 10) | ||
220 | - return 1; | ||
221 | - /* Catch UNDEF cases for bad values of align field */ | ||
222 | - switch (op & 0xc) { | ||
223 | - case 4: | ||
224 | - if (((insn >> 5) & 1) == 1) { | ||
225 | - return 1; | ||
226 | - } | ||
227 | - break; | ||
228 | - case 8: | ||
229 | - if (((insn >> 4) & 3) == 3) { | ||
230 | - return 1; | ||
231 | - } | ||
232 | - break; | ||
233 | - default: | ||
234 | - break; | ||
235 | - } | ||
236 | - nregs = neon_ls_element_type[op].nregs; | ||
237 | - interleave = neon_ls_element_type[op].interleave; | ||
238 | - spacing = neon_ls_element_type[op].spacing; | ||
239 | - if (size == 3 && (interleave | spacing) != 1) { | ||
240 | - return 1; | ||
241 | - } | ||
242 | - /* For our purposes, bytes are always little-endian. */ | ||
243 | - if (size == 0) { | ||
244 | - endian = MO_LE; | ||
245 | - } | ||
246 | - /* Consecutive little-endian elements from a single register | ||
247 | - * can be promoted to a larger little-endian operation. | ||
248 | - */ | ||
249 | - if (interleave == 1 && endian == MO_LE) { | ||
250 | - size = 3; | ||
251 | - } | ||
252 | - tmp64 = tcg_temp_new_i64(); | ||
253 | - addr = tcg_temp_new_i32(); | ||
254 | - tmp2 = tcg_const_i32(1 << size); | ||
255 | - load_reg_var(s, addr, rn); | ||
256 | - for (reg = 0; reg < nregs; reg++) { | ||
257 | - for (n = 0; n < 8 >> size; n++) { | ||
258 | - int xs; | ||
259 | - for (xs = 0; xs < interleave; xs++) { | ||
260 | - int tt = rd + reg + spacing * xs; | ||
261 | - | ||
262 | - if (load) { | ||
263 | - gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); | ||
264 | - neon_store_element64(tt, n, size, tmp64); | ||
265 | - } else { | ||
266 | - neon_load_element64(tmp64, tt, n, size); | ||
267 | - gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); | ||
268 | - } | ||
269 | - tcg_gen_add_i32(addr, addr, tmp2); | ||
270 | - } | ||
271 | - } | ||
272 | - } | ||
273 | - tcg_temp_free_i32(addr); | ||
274 | - tcg_temp_free_i32(tmp2); | ||
275 | - tcg_temp_free_i64(tmp64); | ||
276 | - stride = nregs * interleave * 8; | ||
277 | + /* Load store all elements -- handled already by decodetree */ | ||
278 | + return 1; | ||
279 | } else { | ||
280 | size = (insn >> 10) & 3; | ||
281 | if (size == 3) { | ||
282 | -- | ||
283 | 2.20.1 | ||
284 | |||
285 | diff view generated by jsdifflib |
1 | The BCM2837 sets the Aff1 field of the MPIDR affinity values for the | 1 | Convert the Neon "load single structure to all lanes" insns to |
---|---|---|---|
2 | CPUs to 0, whereas the BCM2836 uses 0xf. Set this correctly, as it | 2 | decodetree. |
3 | is required for Linux to boot. | ||
4 | 3 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 6 | Message-id: 20200430181003.21682-13-peter.maydell@linaro.org |
8 | Message-id: 20180313153458.26822-8-peter.maydell@linaro.org | ||
9 | --- | 7 | --- |
10 | hw/arm/bcm2836.c | 11 +++++++---- | 8 | target/arm/neon-ls.decode | 5 +++ |
11 | 1 file changed, 7 insertions(+), 4 deletions(-) | 9 | target/arm/translate-neon.inc.c | 73 +++++++++++++++++++++++++++++++++ |
10 | target/arm/translate.c | 55 +------------------------ | ||
11 | 3 files changed, 80 insertions(+), 53 deletions(-) | ||
12 | 12 | ||
13 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 13 | diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode |
14 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/hw/arm/bcm2836.c | 15 | --- a/target/arm/neon-ls.decode |
16 | +++ b/hw/arm/bcm2836.c | 16 | +++ b/target/arm/neon-ls.decode |
17 | @@ -XXX,XX +XXX,XX @@ | 17 | @@ -XXX,XX +XXX,XX @@ |
18 | 18 | ||
19 | struct BCM283XInfo { | 19 | VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ |
20 | const char *name; | 20 | vd=%vd_dp |
21 | + int clusterid; | 21 | + |
22 | }; | 22 | +# Neon load single element to all lanes |
23 | 23 | + | |
24 | static const BCM283XInfo bcm283x_socs[] = { | 24 | +VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \ |
25 | { | 25 | + vd=%vd_dp |
26 | .name = TYPE_BCM2836, | 26 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c |
27 | + .clusterid = 0xf, | 27 | index XXXXXXX..XXXXXXX 100644 |
28 | }, | 28 | --- a/target/arm/translate-neon.inc.c |
29 | { | 29 | +++ b/target/arm/translate-neon.inc.c |
30 | .name = TYPE_BCM2837, | 30 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a) |
31 | + .clusterid = 0x0, | 31 | gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8); |
32 | }, | 32 | return true; |
33 | }; | 33 | } |
34 | 34 | + | |
35 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_init(Object *obj) | 35 | +static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) |
36 | static void bcm2836_realize(DeviceState *dev, Error **errp) | 36 | +{ |
37 | { | 37 | + /* Neon load single structure to all lanes */ |
38 | BCM283XState *s = BCM283X(dev); | 38 | + int reg, stride, vec_size; |
39 | + BCM283XClass *bc = BCM283X_GET_CLASS(dev); | 39 | + int vd = a->vd; |
40 | + const BCM283XInfo *info = bc->info; | 40 | + int size = a->size; |
41 | Object *obj; | 41 | + int nregs = a->n + 1; |
42 | Error *err = NULL; | 42 | + TCGv_i32 addr, tmp; |
43 | int n; | 43 | + |
44 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | 44 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { |
45 | qdev_get_gpio_in_named(DEVICE(&s->control), "gpu-fiq", 0)); | 45 | + return false; |
46 | 46 | + } | |
47 | for (n = 0; n < BCM283X_NCPUS; n++) { | 47 | + |
48 | - /* Mirror bcm2836, which has clusterid set to 0xf | 48 | + /* UNDEF accesses to D16-D31 if they don't exist */ |
49 | - * TODO: this should be converted to a property of ARM_CPU | 49 | + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { |
50 | - */ | 50 | + return false; |
51 | - s->cpus[n].mp_affinity = 0xF00 | n; | 51 | + } |
52 | + /* TODO: this should be converted to a property of ARM_CPU */ | 52 | + |
53 | + s->cpus[n].mp_affinity = (info->clusterid << 8) | n; | 53 | + if (size == 3) { |
54 | 54 | + if (nregs != 4 || a->a == 0) { | |
55 | /* set periphbase/CBAR value for CPU-local registers */ | 55 | + return false; |
56 | object_property_set_int(OBJECT(&s->cpus[n]), | 56 | + } |
57 | + /* For VLD4 size == 3 a == 1 means 32 bits at 16 byte alignment */ | ||
58 | + size = 2; | ||
59 | + } | ||
60 | + if (nregs == 1 && a->a == 1 && size == 0) { | ||
61 | + return false; | ||
62 | + } | ||
63 | + if (nregs == 3 && a->a == 1) { | ||
64 | + return false; | ||
65 | + } | ||
66 | + | ||
67 | + if (!vfp_access_check(s)) { | ||
68 | + return true; | ||
69 | + } | ||
70 | + | ||
71 | + /* | ||
72 | + * VLD1 to all lanes: T bit indicates how many Dregs to write. | ||
73 | + * VLD2/3/4 to all lanes: T bit indicates register stride. | ||
74 | + */ | ||
75 | + stride = a->t ? 2 : 1; | ||
76 | + vec_size = nregs == 1 ? stride * 8 : 8; | ||
77 | + | ||
78 | + tmp = tcg_temp_new_i32(); | ||
79 | + addr = tcg_temp_new_i32(); | ||
80 | + load_reg_var(s, addr, a->rn); | ||
81 | + for (reg = 0; reg < nregs; reg++) { | ||
82 | + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), | ||
83 | + s->be_data | size); | ||
84 | + if ((vd & 1) && vec_size == 16) { | ||
85 | + /* | ||
86 | + * We cannot write 16 bytes at once because the | ||
87 | + * destination is unaligned. | ||
88 | + */ | ||
89 | + tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), | ||
90 | + 8, 8, tmp); | ||
91 | + tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0), | ||
92 | + neon_reg_offset(vd, 0), 8, 8); | ||
93 | + } else { | ||
94 | + tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0), | ||
95 | + vec_size, vec_size, tmp); | ||
96 | + } | ||
97 | + tcg_gen_addi_i32(addr, addr, 1 << size); | ||
98 | + vd += stride; | ||
99 | + } | ||
100 | + tcg_temp_free_i32(tmp); | ||
101 | + tcg_temp_free_i32(addr); | ||
102 | + | ||
103 | + gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << size) * nregs); | ||
104 | + | ||
105 | + return true; | ||
106 | +} | ||
107 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
108 | index XXXXXXX..XXXXXXX 100644 | ||
109 | --- a/target/arm/translate.c | ||
110 | +++ b/target/arm/translate.c | ||
111 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) | ||
112 | int size; | ||
113 | int reg; | ||
114 | int load; | ||
115 | - int vec_size; | ||
116 | TCGv_i32 addr; | ||
117 | TCGv_i32 tmp; | ||
118 | |||
119 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) | ||
120 | } else { | ||
121 | size = (insn >> 10) & 3; | ||
122 | if (size == 3) { | ||
123 | - /* Load single element to all lanes. */ | ||
124 | - int a = (insn >> 4) & 1; | ||
125 | - if (!load) { | ||
126 | - return 1; | ||
127 | - } | ||
128 | - size = (insn >> 6) & 3; | ||
129 | - nregs = ((insn >> 8) & 3) + 1; | ||
130 | - | ||
131 | - if (size == 3) { | ||
132 | - if (nregs != 4 || a == 0) { | ||
133 | - return 1; | ||
134 | - } | ||
135 | - /* For VLD4 size==3 a == 1 means 32 bits at 16 byte alignment */ | ||
136 | - size = 2; | ||
137 | - } | ||
138 | - if (nregs == 1 && a == 1 && size == 0) { | ||
139 | - return 1; | ||
140 | - } | ||
141 | - if (nregs == 3 && a == 1) { | ||
142 | - return 1; | ||
143 | - } | ||
144 | - addr = tcg_temp_new_i32(); | ||
145 | - load_reg_var(s, addr, rn); | ||
146 | - | ||
147 | - /* VLD1 to all lanes: bit 5 indicates how many Dregs to write. | ||
148 | - * VLD2/3/4 to all lanes: bit 5 indicates register stride. | ||
149 | - */ | ||
150 | - stride = (insn & (1 << 5)) ? 2 : 1; | ||
151 | - vec_size = nregs == 1 ? stride * 8 : 8; | ||
152 | - | ||
153 | - tmp = tcg_temp_new_i32(); | ||
154 | - for (reg = 0; reg < nregs; reg++) { | ||
155 | - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), | ||
156 | - s->be_data | size); | ||
157 | - if ((rd & 1) && vec_size == 16) { | ||
158 | - /* We cannot write 16 bytes at once because the | ||
159 | - * destination is unaligned. | ||
160 | - */ | ||
161 | - tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), | ||
162 | - 8, 8, tmp); | ||
163 | - tcg_gen_gvec_mov(0, neon_reg_offset(rd + 1, 0), | ||
164 | - neon_reg_offset(rd, 0), 8, 8); | ||
165 | - } else { | ||
166 | - tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), | ||
167 | - vec_size, vec_size, tmp); | ||
168 | - } | ||
169 | - tcg_gen_addi_i32(addr, addr, 1 << size); | ||
170 | - rd += stride; | ||
171 | - } | ||
172 | - tcg_temp_free_i32(tmp); | ||
173 | - tcg_temp_free_i32(addr); | ||
174 | - stride = (1 << size) * nregs; | ||
175 | + /* Load single element to all lanes -- handled by decodetree */ | ||
176 | + return 1; | ||
177 | } else { | ||
178 | /* Single element. */ | ||
179 | int idx = (insn >> 4) & 0xf; | ||
57 | -- | 180 | -- |
58 | 2.16.2 | 181 | 2.20.1 |
59 | 182 | ||
60 | 183 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | Convert the Neon "load/store single structure to one lane" insns to | |
2 | decodetree. | ||
3 | |||
4 | As this is the last set of insns in the neon load/store group, | ||
5 | we can remove the whole disas_neon_ls_insn() function. | ||
6 | |||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
9 | Message-id: 20200430181003.21682-14-peter.maydell@linaro.org | ||
10 | --- | ||
11 | target/arm/neon-ls.decode | 11 +++ | ||
12 | target/arm/translate-neon.inc.c | 89 +++++++++++++++++++ | ||
13 | target/arm/translate.c | 147 -------------------------------- | ||
14 | 3 files changed, 100 insertions(+), 147 deletions(-) | ||
15 | |||
16 | diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/target/arm/neon-ls.decode | ||
19 | +++ b/target/arm/neon-ls.decode | ||
20 | @@ -XXX,XX +XXX,XX @@ VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \ | ||
21 | |||
22 | VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \ | ||
23 | vd=%vd_dp | ||
24 | + | ||
25 | +# Neon load/store single structure to one lane | ||
26 | +%imm1_5_p1 5:1 !function=plus1 | ||
27 | +%imm1_6_p1 6:1 !function=plus1 | ||
28 | + | ||
29 | +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 00 n:2 reg_idx:3 align:1 rm:4 \ | ||
30 | + vd=%vd_dp size=0 stride=1 | ||
31 | +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 01 n:2 reg_idx:2 align:2 rm:4 \ | ||
32 | + vd=%vd_dp size=1 stride=%imm1_5_p1 | ||
33 | +VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 10 n:2 reg_idx:1 align:3 rm:4 \ | ||
34 | + vd=%vd_dp size=2 stride=%imm1_6_p1 | ||
35 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/target/arm/translate-neon.inc.c | ||
38 | +++ b/target/arm/translate-neon.inc.c | ||
39 | @@ -XXX,XX +XXX,XX @@ | ||
40 | * It might be possible to convert it to a standalone .c file eventually. | ||
41 | */ | ||
42 | |||
43 | +static inline int plus1(DisasContext *s, int x) | ||
44 | +{ | ||
45 | + return x + 1; | ||
46 | +} | ||
47 | + | ||
48 | /* Include the generated Neon decoder */ | ||
49 | #include "decode-neon-dp.inc.c" | ||
50 | #include "decode-neon-ls.inc.c" | ||
51 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a) | ||
52 | |||
53 | return true; | ||
54 | } | ||
55 | + | ||
56 | +static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) | ||
57 | +{ | ||
58 | + /* Neon load/store single structure to one lane */ | ||
59 | + int reg; | ||
60 | + int nregs = a->n + 1; | ||
61 | + int vd = a->vd; | ||
62 | + TCGv_i32 addr, tmp; | ||
63 | + | ||
64 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
65 | + return false; | ||
66 | + } | ||
67 | + | ||
68 | + /* UNDEF accesses to D16-D31 if they don't exist */ | ||
69 | + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { | ||
70 | + return false; | ||
71 | + } | ||
72 | + | ||
73 | + /* Catch the UNDEF cases. This is unavoidably a bit messy. */ | ||
74 | + switch (nregs) { | ||
75 | + case 1: | ||
76 | + if (((a->align & (1 << a->size)) != 0) || | ||
77 | + (a->size == 2 && ((a->align & 3) == 1 || (a->align & 3) == 2))) { | ||
78 | + return false; | ||
79 | + } | ||
80 | + break; | ||
81 | + case 3: | ||
82 | + if ((a->align & 1) != 0) { | ||
83 | + return false; | ||
84 | + } | ||
85 | + /* fall through */ | ||
86 | + case 2: | ||
87 | + if (a->size == 2 && (a->align & 2) != 0) { | ||
88 | + return false; | ||
89 | + } | ||
90 | + break; | ||
91 | + case 4: | ||
92 | + if ((a->size == 2) && ((a->align & 3) == 3)) { | ||
93 | + return false; | ||
94 | + } | ||
95 | + break; | ||
96 | + default: | ||
97 | + abort(); | ||
98 | + } | ||
99 | + if ((vd + a->stride * (nregs - 1)) > 31) { | ||
100 | + /* | ||
101 | + * Attempts to write off the end of the register file are | ||
102 | + * UNPREDICTABLE; we choose to UNDEF because otherwise we would | ||
103 | + * access off the end of the array that holds the register data. | ||
104 | + */ | ||
105 | + return false; | ||
106 | + } | ||
107 | + | ||
108 | + if (!vfp_access_check(s)) { | ||
109 | + return true; | ||
110 | + } | ||
111 | + | ||
112 | + tmp = tcg_temp_new_i32(); | ||
113 | + addr = tcg_temp_new_i32(); | ||
114 | + load_reg_var(s, addr, a->rn); | ||
115 | + /* | ||
116 | + * TODO: if we implemented alignment exceptions, we should check | ||
117 | + * addr against the alignment encoded in a->align here. | ||
118 | + */ | ||
119 | + for (reg = 0; reg < nregs; reg++) { | ||
120 | + if (a->l) { | ||
121 | + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), | ||
122 | + s->be_data | a->size); | ||
123 | + neon_store_element(vd, a->reg_idx, a->size, tmp); | ||
124 | + } else { /* Store */ | ||
125 | + neon_load_element(tmp, vd, a->reg_idx, a->size); | ||
126 | + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), | ||
127 | + s->be_data | a->size); | ||
128 | + } | ||
129 | + vd += a->stride; | ||
130 | + tcg_gen_addi_i32(addr, addr, 1 << a->size); | ||
131 | + } | ||
132 | + tcg_temp_free_i32(addr); | ||
133 | + tcg_temp_free_i32(tmp); | ||
134 | + | ||
135 | + gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << a->size) * nregs); | ||
136 | + | ||
137 | + return true; | ||
138 | +} | ||
139 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
140 | index XXXXXXX..XXXXXXX 100644 | ||
141 | --- a/target/arm/translate.c | ||
142 | +++ b/target/arm/translate.c | ||
143 | @@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1) | ||
144 | tcg_temp_free_i32(rd); | ||
145 | } | ||
146 | |||
147 | - | ||
148 | -/* Translate a NEON load/store element instruction. Return nonzero if the | ||
149 | - instruction is invalid. */ | ||
150 | -static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) | ||
151 | -{ | ||
152 | - int rd, rn, rm; | ||
153 | - int nregs; | ||
154 | - int stride; | ||
155 | - int size; | ||
156 | - int reg; | ||
157 | - int load; | ||
158 | - TCGv_i32 addr; | ||
159 | - TCGv_i32 tmp; | ||
160 | - | ||
161 | - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
162 | - return 1; | ||
163 | - } | ||
164 | - | ||
165 | - /* FIXME: this access check should not take precedence over UNDEF | ||
166 | - * for invalid encodings; we will generate incorrect syndrome information | ||
167 | - * for attempts to execute invalid vfp/neon encodings with FP disabled. | ||
168 | - */ | ||
169 | - if (s->fp_excp_el) { | ||
170 | - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, | ||
171 | - syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); | ||
172 | - return 0; | ||
173 | - } | ||
174 | - | ||
175 | - if (!s->vfp_enabled) | ||
176 | - return 1; | ||
177 | - VFP_DREG_D(rd, insn); | ||
178 | - rn = (insn >> 16) & 0xf; | ||
179 | - rm = insn & 0xf; | ||
180 | - load = (insn & (1 << 21)) != 0; | ||
181 | - if ((insn & (1 << 23)) == 0) { | ||
182 | - /* Load store all elements -- handled already by decodetree */ | ||
183 | - return 1; | ||
184 | - } else { | ||
185 | - size = (insn >> 10) & 3; | ||
186 | - if (size == 3) { | ||
187 | - /* Load single element to all lanes -- handled by decodetree */ | ||
188 | - return 1; | ||
189 | - } else { | ||
190 | - /* Single element. */ | ||
191 | - int idx = (insn >> 4) & 0xf; | ||
192 | - int reg_idx; | ||
193 | - switch (size) { | ||
194 | - case 0: | ||
195 | - reg_idx = (insn >> 5) & 7; | ||
196 | - stride = 1; | ||
197 | - break; | ||
198 | - case 1: | ||
199 | - reg_idx = (insn >> 6) & 3; | ||
200 | - stride = (insn & (1 << 5)) ? 2 : 1; | ||
201 | - break; | ||
202 | - case 2: | ||
203 | - reg_idx = (insn >> 7) & 1; | ||
204 | - stride = (insn & (1 << 6)) ? 2 : 1; | ||
205 | - break; | ||
206 | - default: | ||
207 | - abort(); | ||
208 | - } | ||
209 | - nregs = ((insn >> 8) & 3) + 1; | ||
210 | - /* Catch the UNDEF cases. This is unavoidably a bit messy. */ | ||
211 | - switch (nregs) { | ||
212 | - case 1: | ||
213 | - if (((idx & (1 << size)) != 0) || | ||
214 | - (size == 2 && ((idx & 3) == 1 || (idx & 3) == 2))) { | ||
215 | - return 1; | ||
216 | - } | ||
217 | - break; | ||
218 | - case 3: | ||
219 | - if ((idx & 1) != 0) { | ||
220 | - return 1; | ||
221 | - } | ||
222 | - /* fall through */ | ||
223 | - case 2: | ||
224 | - if (size == 2 && (idx & 2) != 0) { | ||
225 | - return 1; | ||
226 | - } | ||
227 | - break; | ||
228 | - case 4: | ||
229 | - if ((size == 2) && ((idx & 3) == 3)) { | ||
230 | - return 1; | ||
231 | - } | ||
232 | - break; | ||
233 | - default: | ||
234 | - abort(); | ||
235 | - } | ||
236 | - if ((rd + stride * (nregs - 1)) > 31) { | ||
237 | - /* Attempts to write off the end of the register file | ||
238 | - * are UNPREDICTABLE; we choose to UNDEF because otherwise | ||
239 | - * the neon_load_reg() would write off the end of the array. | ||
240 | - */ | ||
241 | - return 1; | ||
242 | - } | ||
243 | - tmp = tcg_temp_new_i32(); | ||
244 | - addr = tcg_temp_new_i32(); | ||
245 | - load_reg_var(s, addr, rn); | ||
246 | - for (reg = 0; reg < nregs; reg++) { | ||
247 | - if (load) { | ||
248 | - gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), | ||
249 | - s->be_data | size); | ||
250 | - neon_store_element(rd, reg_idx, size, tmp); | ||
251 | - } else { /* Store */ | ||
252 | - neon_load_element(tmp, rd, reg_idx, size); | ||
253 | - gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), | ||
254 | - s->be_data | size); | ||
255 | - } | ||
256 | - rd += stride; | ||
257 | - tcg_gen_addi_i32(addr, addr, 1 << size); | ||
258 | - } | ||
259 | - tcg_temp_free_i32(addr); | ||
260 | - tcg_temp_free_i32(tmp); | ||
261 | - stride = nregs * (1 << size); | ||
262 | - } | ||
263 | - } | ||
264 | - if (rm != 15) { | ||
265 | - TCGv_i32 base; | ||
266 | - | ||
267 | - base = load_reg(s, rn); | ||
268 | - if (rm == 13) { | ||
269 | - tcg_gen_addi_i32(base, base, stride); | ||
270 | - } else { | ||
271 | - TCGv_i32 index; | ||
272 | - index = load_reg(s, rm); | ||
273 | - tcg_gen_add_i32(base, base, index); | ||
274 | - tcg_temp_free_i32(index); | ||
275 | - } | ||
276 | - store_reg(s, rn, base); | ||
277 | - } | ||
278 | - return 0; | ||
279 | -} | ||
280 | - | ||
281 | static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src) | ||
282 | { | ||
283 | switch (size) { | ||
284 | @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) | ||
285 | } | ||
286 | return; | ||
287 | } | ||
288 | - if ((insn & 0x0f100000) == 0x04000000) { | ||
289 | - /* NEON load/store. */ | ||
290 | - if (disas_neon_ls_insn(s, insn)) { | ||
291 | - goto illegal_op; | ||
292 | - } | ||
293 | - return; | ||
294 | - } | ||
295 | if ((insn & 0x0e000f00) == 0x0c000100) { | ||
296 | if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { | ||
297 | /* iWMMXt register transfer. */ | ||
298 | @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) | ||
299 | } | ||
300 | break; | ||
301 | case 12: | ||
302 | - if ((insn & 0x01100000) == 0x01000000) { | ||
303 | - if (disas_neon_ls_insn(s, insn)) { | ||
304 | - goto illegal_op; | ||
305 | - } | ||
306 | - break; | ||
307 | - } | ||
308 | goto illegal_op; | ||
309 | default: | ||
310 | illegal_op: | ||
311 | -- | ||
312 | 2.20.1 | ||
313 | |||
314 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the Neon 3-reg-same VADD and VSUB insns to decodetree. | ||
1 | 2 | ||
3 | Note that we don't need the neon_3r_sizes[op] check here because all | ||
4 | size values are OK for VADD and VSUB; we'll add this when we convert | ||
5 | the first insn that has size restrictions. | ||
6 | |||
7 | For this we need one of the GVecGen*Fn typedefs currently in | ||
8 | translate-a64.h; move them all to translate.h as a block so they | ||
9 | are visible to the 32-bit decoder. | ||
10 | |||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
13 | Message-id: 20200430181003.21682-15-peter.maydell@linaro.org | ||
14 | --- | ||
15 | target/arm/translate-a64.h | 9 -------- | ||
16 | target/arm/translate.h | 9 ++++++++ | ||
17 | target/arm/neon-dp.decode | 17 +++++++++++++++ | ||
18 | target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++ | ||
19 | target/arm/translate.c | 14 ++++-------- | ||
20 | 5 files changed, 68 insertions(+), 19 deletions(-) | ||
21 | |||
22 | diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h | ||
23 | index XXXXXXX..XXXXXXX 100644 | ||
24 | --- a/target/arm/translate-a64.h | ||
25 | +++ b/target/arm/translate-a64.h | ||
26 | @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) | ||
27 | |||
28 | bool disas_sve(DisasContext *, uint32_t); | ||
29 | |||
30 | -/* Note that the gvec expanders operate on offsets + sizes. */ | ||
31 | -typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t); | ||
32 | -typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t, | ||
33 | - uint32_t, uint32_t); | ||
34 | -typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, | ||
35 | - uint32_t, uint32_t, uint32_t); | ||
36 | -typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, | ||
37 | - uint32_t, uint32_t, uint32_t); | ||
38 | - | ||
39 | #endif /* TARGET_ARM_TRANSLATE_A64_H */ | ||
40 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
41 | index XXXXXXX..XXXXXXX 100644 | ||
42 | --- a/target/arm/translate.h | ||
43 | +++ b/target/arm/translate.h | ||
44 | @@ -XXX,XX +XXX,XX @@ void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); | ||
45 | #define dc_isar_feature(name, ctx) \ | ||
46 | ({ DisasContext *ctx_ = (ctx); isar_feature_##name(ctx_->isar); }) | ||
47 | |||
48 | +/* Note that the gvec expanders operate on offsets + sizes. */ | ||
49 | +typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t); | ||
50 | +typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t, | ||
51 | + uint32_t, uint32_t); | ||
52 | +typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, | ||
53 | + uint32_t, uint32_t, uint32_t); | ||
54 | +typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, | ||
55 | + uint32_t, uint32_t, uint32_t); | ||
56 | + | ||
57 | #endif /* TARGET_ARM_TRANSLATE_H */ | ||
58 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode | ||
59 | index XXXXXXX..XXXXXXX 100644 | ||
60 | --- a/target/arm/neon-dp.decode | ||
61 | +++ b/target/arm/neon-dp.decode | ||
62 | @@ -XXX,XX +XXX,XX @@ | ||
63 | # | ||
64 | # This file is processed by scripts/decodetree.py | ||
65 | # | ||
66 | +# VFP/Neon register fields; same as vfp.decode | ||
67 | +%vm_dp 5:1 0:4 | ||
68 | +%vn_dp 7:1 16:4 | ||
69 | +%vd_dp 22:1 12:4 | ||
70 | |||
71 | # Encodings for Neon data processing instructions where the T32 encoding | ||
72 | # is a simple transformation of the A32 encoding. | ||
73 | @@ -XXX,XX +XXX,XX @@ | ||
74 | # 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq | ||
75 | # This file works on the A32 encoding only; calling code for T32 has to | ||
76 | # transform the insn into the A32 version first. | ||
77 | + | ||
78 | +###################################################################### | ||
79 | +# 3-reg-same grouping: | ||
80 | +# 1111 001 U 0 D sz:2 Vn:4 Vd:4 opc:4 N Q M op Vm:4 | ||
81 | +###################################################################### | ||
82 | + | ||
83 | +&3same vm vn vd q size | ||
84 | + | ||
85 | +@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ | ||
86 | + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
87 | + | ||
88 | +VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same | ||
89 | +VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same | ||
90 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
91 | index XXXXXXX..XXXXXXX 100644 | ||
92 | --- a/target/arm/translate-neon.inc.c | ||
93 | +++ b/target/arm/translate-neon.inc.c | ||
94 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a) | ||
95 | |||
96 | return true; | ||
97 | } | ||
98 | + | ||
99 | +static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) | ||
100 | +{ | ||
101 | + int vec_size = a->q ? 16 : 8; | ||
102 | + int rd_ofs = neon_reg_offset(a->vd, 0); | ||
103 | + int rn_ofs = neon_reg_offset(a->vn, 0); | ||
104 | + int rm_ofs = neon_reg_offset(a->vm, 0); | ||
105 | + | ||
106 | + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { | ||
107 | + return false; | ||
108 | + } | ||
109 | + | ||
110 | + /* UNDEF accesses to D16-D31 if they don't exist. */ | ||
111 | + if (!dc_isar_feature(aa32_simd_r32, s) && | ||
112 | + ((a->vd | a->vn | a->vm) & 0x10)) { | ||
113 | + return false; | ||
114 | + } | ||
115 | + | ||
116 | + if ((a->vn | a->vm | a->vd) & a->q) { | ||
117 | + return false; | ||
118 | + } | ||
119 | + | ||
120 | + if (!vfp_access_check(s)) { | ||
121 | + return true; | ||
122 | + } | ||
123 | + | ||
124 | + fn(a->size, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); | ||
125 | + return true; | ||
126 | +} | ||
127 | + | ||
128 | +#define DO_3SAME(INSN, FUNC) \ | ||
129 | + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ | ||
130 | + { \ | ||
131 | + return do_3same(s, a, FUNC); \ | ||
132 | + } | ||
133 | + | ||
134 | +DO_3SAME(VADD, tcg_gen_gvec_add) | ||
135 | +DO_3SAME(VSUB, tcg_gen_gvec_sub) | ||
136 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
137 | index XXXXXXX..XXXXXXX 100644 | ||
138 | --- a/target/arm/translate.c | ||
139 | +++ b/target/arm/translate.c | ||
140 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
141 | } | ||
142 | return 0; | ||
143 | |||
144 | - case NEON_3R_VADD_VSUB: | ||
145 | - if (u) { | ||
146 | - tcg_gen_gvec_sub(size, rd_ofs, rn_ofs, rm_ofs, | ||
147 | - vec_size, vec_size); | ||
148 | - } else { | ||
149 | - tcg_gen_gvec_add(size, rd_ofs, rn_ofs, rm_ofs, | ||
150 | - vec_size, vec_size); | ||
151 | - } | ||
152 | - return 0; | ||
153 | - | ||
154 | case NEON_3R_VQADD: | ||
155 | tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | ||
156 | rn_ofs, rm_ofs, vec_size, vec_size, | ||
157 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
158 | tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, | ||
159 | u ? &ushl_op[size] : &sshl_op[size]); | ||
160 | return 0; | ||
161 | + | ||
162 | + case NEON_3R_VADD_VSUB: | ||
163 | + /* Already handled by decodetree */ | ||
164 | + return 1; | ||
165 | } | ||
166 | |||
167 | if (size == 3) { | ||
168 | -- | ||
169 | 2.20.1 | ||
170 | |||
171 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the Neon logic ops in the 3-reg-same grouping to decodetree. | ||
2 | Note that for the logic ops the 'size' field forms part of their | ||
3 | decode and the actual operations are always bitwise. | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Message-id: 20200430181003.21682-16-peter.maydell@linaro.org | ||
8 | --- | ||
9 | target/arm/neon-dp.decode | 12 +++++++++++ | ||
10 | target/arm/translate-neon.inc.c | 19 +++++++++++++++++ | ||
11 | target/arm/translate.c | 38 +-------------------------------- | ||
12 | 3 files changed, 32 insertions(+), 37 deletions(-) | ||
13 | |||
14 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/target/arm/neon-dp.decode | ||
17 | +++ b/target/arm/neon-dp.decode | ||
18 | @@ -XXX,XX +XXX,XX @@ | ||
19 | @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ | ||
20 | &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp | ||
21 | |||
22 | +@3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \ | ||
23 | + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 | ||
24 | + | ||
25 | +VAND_3s 1111 001 0 0 . 00 .... .... 0001 ... 1 .... @3same_logic | ||
26 | +VBIC_3s 1111 001 0 0 . 01 .... .... 0001 ... 1 .... @3same_logic | ||
27 | +VORR_3s 1111 001 0 0 . 10 .... .... 0001 ... 1 .... @3same_logic | ||
28 | +VORN_3s 1111 001 0 0 . 11 .... .... 0001 ... 1 .... @3same_logic | ||
29 | +VEOR_3s 1111 001 1 0 . 00 .... .... 0001 ... 1 .... @3same_logic | ||
30 | +VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic | ||
31 | +VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic | ||
32 | +VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic | ||
33 | + | ||
34 | VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same | ||
35 | VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same | ||
36 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/target/arm/translate-neon.inc.c | ||
39 | +++ b/target/arm/translate-neon.inc.c | ||
40 | @@ -XXX,XX +XXX,XX @@ static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn) | ||
41 | |||
42 | DO_3SAME(VADD, tcg_gen_gvec_add) | ||
43 | DO_3SAME(VSUB, tcg_gen_gvec_sub) | ||
44 | +DO_3SAME(VAND, tcg_gen_gvec_and) | ||
45 | +DO_3SAME(VBIC, tcg_gen_gvec_andc) | ||
46 | +DO_3SAME(VORR, tcg_gen_gvec_or) | ||
47 | +DO_3SAME(VORN, tcg_gen_gvec_orc) | ||
48 | +DO_3SAME(VEOR, tcg_gen_gvec_xor) | ||
49 | + | ||
50 | +/* These insns are all gvec_bitsel but with the inputs in various orders. */ | ||
51 | +#define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ | ||
52 | + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
53 | + uint32_t rn_ofs, uint32_t rm_ofs, \ | ||
54 | + uint32_t oprsz, uint32_t maxsz) \ | ||
55 | + { \ | ||
56 | + tcg_gen_gvec_bitsel(vece, rd_ofs, O1, O2, O3, oprsz, maxsz); \ | ||
57 | + } \ | ||
58 | + DO_3SAME(INSN, gen_##INSN##_3s) | ||
59 | + | ||
60 | +DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs) | ||
61 | +DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs) | ||
62 | +DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs) | ||
63 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
64 | index XXXXXXX..XXXXXXX 100644 | ||
65 | --- a/target/arm/translate.c | ||
66 | +++ b/target/arm/translate.c | ||
67 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
68 | } | ||
69 | return 1; | ||
70 | |||
71 | - case NEON_3R_LOGIC: /* Logic ops. */ | ||
72 | - switch ((u << 2) | size) { | ||
73 | - case 0: /* VAND */ | ||
74 | - tcg_gen_gvec_and(0, rd_ofs, rn_ofs, rm_ofs, | ||
75 | - vec_size, vec_size); | ||
76 | - break; | ||
77 | - case 1: /* VBIC */ | ||
78 | - tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs, | ||
79 | - vec_size, vec_size); | ||
80 | - break; | ||
81 | - case 2: /* VORR */ | ||
82 | - tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, | ||
83 | - vec_size, vec_size); | ||
84 | - break; | ||
85 | - case 3: /* VORN */ | ||
86 | - tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs, | ||
87 | - vec_size, vec_size); | ||
88 | - break; | ||
89 | - case 4: /* VEOR */ | ||
90 | - tcg_gen_gvec_xor(0, rd_ofs, rn_ofs, rm_ofs, | ||
91 | - vec_size, vec_size); | ||
92 | - break; | ||
93 | - case 5: /* VBSL */ | ||
94 | - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rd_ofs, rn_ofs, rm_ofs, | ||
95 | - vec_size, vec_size); | ||
96 | - break; | ||
97 | - case 6: /* VBIT */ | ||
98 | - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rn_ofs, rd_ofs, | ||
99 | - vec_size, vec_size); | ||
100 | - break; | ||
101 | - case 7: /* VBIF */ | ||
102 | - tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rd_ofs, rn_ofs, | ||
103 | - vec_size, vec_size); | ||
104 | - break; | ||
105 | - } | ||
106 | - return 0; | ||
107 | - | ||
108 | case NEON_3R_VQADD: | ||
109 | tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | ||
110 | rn_ofs, rm_ofs, vec_size, vec_size, | ||
111 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
112 | return 0; | ||
113 | |||
114 | case NEON_3R_VADD_VSUB: | ||
115 | + case NEON_3R_LOGIC: | ||
116 | /* Already handled by decodetree */ | ||
117 | return 1; | ||
118 | } | ||
119 | -- | ||
120 | 2.20.1 | ||
121 | |||
122 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Convert the Neon 3-reg-same VMAX and VMIN insns to decodetree. | ||
1 | 2 | ||
3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
5 | Message-id: 20200430181003.21682-17-peter.maydell@linaro.org | ||
6 | --- | ||
7 | target/arm/neon-dp.decode | 5 +++++ | ||
8 | target/arm/translate-neon.inc.c | 14 ++++++++++++++ | ||
9 | target/arm/translate.c | 21 ++------------------- | ||
10 | 3 files changed, 21 insertions(+), 19 deletions(-) | ||
11 | |||
12 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode | ||
13 | index XXXXXXX..XXXXXXX 100644 | ||
14 | --- a/target/arm/neon-dp.decode | ||
15 | +++ b/target/arm/neon-dp.decode | ||
16 | @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic | ||
17 | VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic | ||
18 | VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic | ||
19 | |||
20 | +VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same | ||
21 | +VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same | ||
22 | +VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same | ||
23 | +VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same | ||
24 | + | ||
25 | VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same | ||
26 | VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same | ||
27 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
28 | index XXXXXXX..XXXXXXX 100644 | ||
29 | --- a/target/arm/translate-neon.inc.c | ||
30 | +++ b/target/arm/translate-neon.inc.c | ||
31 | @@ -XXX,XX +XXX,XX @@ DO_3SAME(VEOR, tcg_gen_gvec_xor) | ||
32 | DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs) | ||
33 | DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs) | ||
34 | DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs) | ||
35 | + | ||
36 | +#define DO_3SAME_NO_SZ_3(INSN, FUNC) \ | ||
37 | + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ | ||
38 | + { \ | ||
39 | + if (a->size == 3) { \ | ||
40 | + return false; \ | ||
41 | + } \ | ||
42 | + return do_3same(s, a, FUNC); \ | ||
43 | + } | ||
44 | + | ||
45 | +DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) | ||
46 | +DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) | ||
47 | +DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) | ||
48 | +DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) | ||
49 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
50 | index XXXXXXX..XXXXXXX 100644 | ||
51 | --- a/target/arm/translate.c | ||
52 | +++ b/target/arm/translate.c | ||
53 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
54 | rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); | ||
55 | return 0; | ||
56 | |||
57 | - case NEON_3R_VMAX: | ||
58 | - if (u) { | ||
59 | - tcg_gen_gvec_umax(size, rd_ofs, rn_ofs, rm_ofs, | ||
60 | - vec_size, vec_size); | ||
61 | - } else { | ||
62 | - tcg_gen_gvec_smax(size, rd_ofs, rn_ofs, rm_ofs, | ||
63 | - vec_size, vec_size); | ||
64 | - } | ||
65 | - return 0; | ||
66 | - case NEON_3R_VMIN: | ||
67 | - if (u) { | ||
68 | - tcg_gen_gvec_umin(size, rd_ofs, rn_ofs, rm_ofs, | ||
69 | - vec_size, vec_size); | ||
70 | - } else { | ||
71 | - tcg_gen_gvec_smin(size, rd_ofs, rn_ofs, rm_ofs, | ||
72 | - vec_size, vec_size); | ||
73 | - } | ||
74 | - return 0; | ||
75 | - | ||
76 | case NEON_3R_VSHL: | ||
77 | /* Note the operation is vshl vd,vm,vn */ | ||
78 | tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, | ||
79 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
80 | |||
81 | case NEON_3R_VADD_VSUB: | ||
82 | case NEON_3R_LOGIC: | ||
83 | + case NEON_3R_VMAX: | ||
84 | + case NEON_3R_VMIN: | ||
85 | /* Already handled by decodetree */ | ||
86 | return 1; | ||
87 | } | ||
88 | -- | ||
89 | 2.20.1 | ||
90 | |||
91 | diff view generated by jsdifflib |
1 | The TypeInfo and state struct for bcm2386 disagree about what the | 1 | Convert the Neon comparison ops in the 3-reg-same grouping |
---|---|---|---|
2 | parent class is -- the TypeInfo says it's TYPE_SYS_BUS_DEVICE, | 2 | to decodetree. |
3 | but the BCM2386State struct only defines the parent_obj field | ||
4 | as DeviceState. This would have caused problems if anything | ||
5 | actually tried to treat the object as a TYPE_SYS_BUS_DEVICE. | ||
6 | Fix the TypeInfo to use TYPE_DEVICE as the parent, since we don't | ||
7 | need any of the additional functionality TYPE_SYS_BUS_DEVICE | ||
8 | provides. | ||
9 | 3 | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 6 | Message-id: 20200430181003.21682-18-peter.maydell@linaro.org |
13 | Message-id: 20180313153458.26822-5-peter.maydell@linaro.org | ||
14 | --- | 7 | --- |
15 | hw/arm/bcm2836.c | 2 +- | 8 | target/arm/neon-dp.decode | 8 ++++++++ |
16 | 1 file changed, 1 insertion(+), 1 deletion(-) | 9 | target/arm/translate-neon.inc.c | 22 ++++++++++++++++++++++ |
10 | target/arm/translate.c | 23 +++-------------------- | ||
11 | 3 files changed, 33 insertions(+), 20 deletions(-) | ||
17 | 12 | ||
18 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 13 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode |
19 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/hw/arm/bcm2836.c | 15 | --- a/target/arm/neon-dp.decode |
21 | +++ b/hw/arm/bcm2836.c | 16 | +++ b/target/arm/neon-dp.decode |
22 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_class_init(ObjectClass *oc, void *data) | 17 | @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic |
23 | 18 | VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic | |
24 | static const TypeInfo bcm2836_type_info = { | 19 | VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic |
25 | .name = TYPE_BCM2836, | 20 | |
26 | - .parent = TYPE_SYS_BUS_DEVICE, | 21 | +VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same |
27 | + .parent = TYPE_DEVICE, | 22 | +VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same |
28 | .instance_size = sizeof(BCM2836State), | 23 | +VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same |
29 | .instance_init = bcm2836_init, | 24 | +VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same |
30 | .class_init = bcm2836_class_init, | 25 | + |
26 | VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same | ||
27 | VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same | ||
28 | VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same | ||
29 | @@ -XXX,XX +XXX,XX @@ VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same | ||
30 | |||
31 | VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same | ||
32 | VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same | ||
33 | + | ||
34 | +VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same | ||
35 | +VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same | ||
36 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/target/arm/translate-neon.inc.c | ||
39 | +++ b/target/arm/translate-neon.inc.c | ||
40 | @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) | ||
41 | DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) | ||
42 | DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) | ||
43 | DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) | ||
44 | + | ||
45 | +#define DO_3SAME_CMP(INSN, COND) \ | ||
46 | + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
47 | + uint32_t rn_ofs, uint32_t rm_ofs, \ | ||
48 | + uint32_t oprsz, uint32_t maxsz) \ | ||
49 | + { \ | ||
50 | + tcg_gen_gvec_cmp(COND, vece, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz); \ | ||
51 | + } \ | ||
52 | + DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s) | ||
53 | + | ||
54 | +DO_3SAME_CMP(VCGT_S, TCG_COND_GT) | ||
55 | +DO_3SAME_CMP(VCGT_U, TCG_COND_GTU) | ||
56 | +DO_3SAME_CMP(VCGE_S, TCG_COND_GE) | ||
57 | +DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) | ||
58 | +DO_3SAME_CMP(VCEQ, TCG_COND_EQ) | ||
59 | + | ||
60 | +static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, | ||
61 | + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) | ||
62 | +{ | ||
63 | + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]); | ||
64 | +} | ||
65 | +DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s) | ||
66 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
67 | index XXXXXXX..XXXXXXX 100644 | ||
68 | --- a/target/arm/translate.c | ||
69 | +++ b/target/arm/translate.c | ||
70 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
71 | u ? &mls_op[size] : &mla_op[size]); | ||
72 | return 0; | ||
73 | |||
74 | - case NEON_3R_VTST_VCEQ: | ||
75 | - if (u) { /* VCEQ */ | ||
76 | - tcg_gen_gvec_cmp(TCG_COND_EQ, size, rd_ofs, rn_ofs, rm_ofs, | ||
77 | - vec_size, vec_size); | ||
78 | - } else { /* VTST */ | ||
79 | - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, | ||
80 | - vec_size, vec_size, &cmtst_op[size]); | ||
81 | - } | ||
82 | - return 0; | ||
83 | - | ||
84 | - case NEON_3R_VCGT: | ||
85 | - tcg_gen_gvec_cmp(u ? TCG_COND_GTU : TCG_COND_GT, size, | ||
86 | - rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); | ||
87 | - return 0; | ||
88 | - | ||
89 | - case NEON_3R_VCGE: | ||
90 | - tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size, | ||
91 | - rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); | ||
92 | - return 0; | ||
93 | - | ||
94 | case NEON_3R_VSHL: | ||
95 | /* Note the operation is vshl vd,vm,vn */ | ||
96 | tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, | ||
97 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
98 | case NEON_3R_LOGIC: | ||
99 | case NEON_3R_VMAX: | ||
100 | case NEON_3R_VMIN: | ||
101 | + case NEON_3R_VTST_VCEQ: | ||
102 | + case NEON_3R_VCGT: | ||
103 | + case NEON_3R_VCGE: | ||
104 | /* Already handled by decodetree */ | ||
105 | return 1; | ||
106 | } | ||
31 | -- | 107 | -- |
32 | 2.16.2 | 108 | 2.20.1 |
33 | 109 | ||
34 | 110 | diff view generated by jsdifflib |
1 | If we're directly booting a Linux kernel and the CPU supports both | 1 | Convert the Neon VQADD/VQSUB insns in the 3-reg-same grouping |
---|---|---|---|
2 | EL3 and EL2, we start the kernel in EL2, as it expects. We must also | 2 | to decodetree. |
3 | set the SCR_EL3.HCE bit in this situation, so that the HVC | ||
4 | instruction is enabled rather than UNDEFing. Otherwise at least some | ||
5 | kernels will panic when trying to initialize KVM in the guest. | ||
6 | 3 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Message-id: 20180313153458.26822-4-peter.maydell@linaro.org | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
6 | Message-id: 20200430181003.21682-19-peter.maydell@linaro.org | ||
9 | --- | 7 | --- |
10 | hw/arm/boot.c | 5 +++++ | 8 | target/arm/neon-dp.decode | 6 ++++++ |
11 | 1 file changed, 5 insertions(+) | 9 | target/arm/translate-neon.inc.c | 15 +++++++++++++++ |
10 | target/arm/translate.c | 14 ++------------ | ||
11 | 3 files changed, 23 insertions(+), 12 deletions(-) | ||
12 | 12 | ||
13 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | 13 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode |
14 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/hw/arm/boot.c | 15 | --- a/target/arm/neon-dp.decode |
16 | +++ b/hw/arm/boot.c | 16 | +++ b/target/arm/neon-dp.decode |
17 | @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) | 17 | @@ -XXX,XX +XXX,XX @@ |
18 | assert(!info->secure_board_setup); | 18 | @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ |
19 | } | 19 | &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp |
20 | 20 | ||
21 | + if (arm_feature(env, ARM_FEATURE_EL2)) { | 21 | +VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same |
22 | + /* If we have EL2 then Linux expects the HVC insn to work */ | 22 | +VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same |
23 | + env->cp15.scr_el3 |= SCR_HCE; | ||
24 | + } | ||
25 | + | 23 | + |
26 | /* Set to non-secure if not a secure boot */ | 24 | @3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \ |
27 | if (!info->secure_boot && | 25 | &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 |
28 | (cs != first_cpu || !info->secure_board_setup)) { | 26 | |
27 | @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic | ||
28 | VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic | ||
29 | VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic | ||
30 | |||
31 | +VQSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 1 .... @3same | ||
32 | +VQSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 1 .... @3same | ||
33 | + | ||
34 | VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same | ||
35 | VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same | ||
36 | VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same | ||
37 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/target/arm/translate-neon.inc.c | ||
40 | +++ b/target/arm/translate-neon.inc.c | ||
41 | @@ -XXX,XX +XXX,XX @@ static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, | ||
42 | tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]); | ||
43 | } | ||
44 | DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s) | ||
45 | + | ||
46 | +#define DO_3SAME_GVEC4(INSN, OPARRAY) \ | ||
47 | + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
48 | + uint32_t rn_ofs, uint32_t rm_ofs, \ | ||
49 | + uint32_t oprsz, uint32_t maxsz) \ | ||
50 | + { \ | ||
51 | + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), \ | ||
52 | + rn_ofs, rm_ofs, oprsz, maxsz, &OPARRAY[vece]); \ | ||
53 | + } \ | ||
54 | + DO_3SAME(INSN, gen_##INSN##_3s) | ||
55 | + | ||
56 | +DO_3SAME_GVEC4(VQADD_S, sqadd_op) | ||
57 | +DO_3SAME_GVEC4(VQADD_U, uqadd_op) | ||
58 | +DO_3SAME_GVEC4(VQSUB_S, sqsub_op) | ||
59 | +DO_3SAME_GVEC4(VQSUB_U, uqsub_op) | ||
60 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
61 | index XXXXXXX..XXXXXXX 100644 | ||
62 | --- a/target/arm/translate.c | ||
63 | +++ b/target/arm/translate.c | ||
64 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
65 | } | ||
66 | return 1; | ||
67 | |||
68 | - case NEON_3R_VQADD: | ||
69 | - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | ||
70 | - rn_ofs, rm_ofs, vec_size, vec_size, | ||
71 | - (u ? uqadd_op : sqadd_op) + size); | ||
72 | - return 0; | ||
73 | - | ||
74 | - case NEON_3R_VQSUB: | ||
75 | - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), | ||
76 | - rn_ofs, rm_ofs, vec_size, vec_size, | ||
77 | - (u ? uqsub_op : sqsub_op) + size); | ||
78 | - return 0; | ||
79 | - | ||
80 | case NEON_3R_VMUL: /* VMUL */ | ||
81 | if (u) { | ||
82 | /* Polynomial case allows only P8. */ | ||
83 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
84 | case NEON_3R_VTST_VCEQ: | ||
85 | case NEON_3R_VCGT: | ||
86 | case NEON_3R_VCGE: | ||
87 | + case NEON_3R_VQADD: | ||
88 | + case NEON_3R_VQSUB: | ||
89 | /* Already handled by decodetree */ | ||
90 | return 1; | ||
91 | } | ||
29 | -- | 92 | -- |
30 | 2.16.2 | 93 | 2.20.1 |
31 | 94 | ||
32 | 95 | diff view generated by jsdifflib |
1 | Add some assertions that if we're about to boot an AArch64 kernel, | 1 | Convert the Neon VMUL, VMLA, VMLS and VSHL insns in the |
---|---|---|---|
2 | the board code has not mistakenly set either secure_boot or | 2 | 3-reg-same grouping to decodetree. |
3 | secure_board_setup. It doesn't make sense to set secure_boot, | ||
4 | because all AArch64 kernels must be booted in non-secure mode. | ||
5 | |||
6 | It might in theory make sense to set secure_board_setup, but | ||
7 | we don't currently support that, because only the AArch32 | ||
8 | bootloader[] code calls this hook; bootloader_aarch64[] does not. | ||
9 | Since we don't have a current need for this functionality, just | ||
10 | assert that we don't try to use it. If it's needed we'll add | ||
11 | it later. | ||
12 | 3 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 4 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 5 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
15 | Message-id: 20180313153458.26822-3-peter.maydell@linaro.org | 6 | Message-id: 20200430181003.21682-20-peter.maydell@linaro.org |
16 | --- | 7 | --- |
17 | hw/arm/boot.c | 7 +++++++ | 8 | target/arm/neon-dp.decode | 9 +++++++ |
18 | 1 file changed, 7 insertions(+) | 9 | target/arm/translate-neon.inc.c | 44 +++++++++++++++++++++++++++++++++ |
10 | target/arm/translate.c | 28 +++------------------ | ||
11 | 3 files changed, 56 insertions(+), 25 deletions(-) | ||
19 | 12 | ||
20 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | 13 | diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode |
21 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/hw/arm/boot.c | 15 | --- a/target/arm/neon-dp.decode |
23 | +++ b/hw/arm/boot.c | 16 | +++ b/target/arm/neon-dp.decode |
24 | @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) | 17 | @@ -XXX,XX +XXX,XX @@ VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same |
25 | } else { | 18 | VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same |
26 | env->pstate = PSTATE_MODE_EL1h; | 19 | VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same |
27 | } | 20 | |
28 | + /* AArch64 kernels never boot in secure mode */ | 21 | +VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same |
29 | + assert(!info->secure_boot); | 22 | +VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same |
30 | + /* This hook is only supported for AArch32 currently: | 23 | + |
31 | + * bootloader_aarch64[] will not call the hook, and | 24 | VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same |
32 | + * the code above has already dropped us into EL2 or EL1. | 25 | VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same |
33 | + */ | 26 | VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same |
34 | + assert(!info->secure_board_setup); | 27 | @@ -XXX,XX +XXX,XX @@ VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same |
35 | } | 28 | |
36 | 29 | VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same | |
37 | /* Set to non-secure if not a secure boot */ | 30 | VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same |
31 | + | ||
32 | +VMLA_3s 1111 001 0 0 . .. .... .... 1001 . . . 0 .... @3same | ||
33 | +VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same | ||
34 | + | ||
35 | +VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same | ||
36 | +VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same | ||
37 | diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c | ||
38 | index XXXXXXX..XXXXXXX 100644 | ||
39 | --- a/target/arm/translate-neon.inc.c | ||
40 | +++ b/target/arm/translate-neon.inc.c | ||
41 | @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax) | ||
42 | DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) | ||
43 | DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) | ||
44 | DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) | ||
45 | +DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul) | ||
46 | |||
47 | #define DO_3SAME_CMP(INSN, COND) \ | ||
48 | static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
49 | @@ -XXX,XX +XXX,XX @@ DO_3SAME_GVEC4(VQADD_S, sqadd_op) | ||
50 | DO_3SAME_GVEC4(VQADD_U, uqadd_op) | ||
51 | DO_3SAME_GVEC4(VQSUB_S, sqsub_op) | ||
52 | DO_3SAME_GVEC4(VQSUB_U, uqsub_op) | ||
53 | + | ||
54 | +static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, | ||
55 | + uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) | ||
56 | +{ | ||
57 | + tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, | ||
58 | + 0, gen_helper_gvec_pmul_b); | ||
59 | +} | ||
60 | + | ||
61 | +static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) | ||
62 | +{ | ||
63 | + if (a->size != 0) { | ||
64 | + return false; | ||
65 | + } | ||
66 | + return do_3same(s, a, gen_VMUL_p_3s); | ||
67 | +} | ||
68 | + | ||
69 | +#define DO_3SAME_GVEC3_NO_SZ_3(INSN, OPARRAY) \ | ||
70 | + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
71 | + uint32_t rn_ofs, uint32_t rm_ofs, \ | ||
72 | + uint32_t oprsz, uint32_t maxsz) \ | ||
73 | + { \ | ||
74 | + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \ | ||
75 | + oprsz, maxsz, &OPARRAY[vece]); \ | ||
76 | + } \ | ||
77 | + DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s) | ||
78 | + | ||
79 | + | ||
80 | +DO_3SAME_GVEC3_NO_SZ_3(VMLA, mla_op) | ||
81 | +DO_3SAME_GVEC3_NO_SZ_3(VMLS, mls_op) | ||
82 | + | ||
83 | +#define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY) \ | ||
84 | + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ | ||
85 | + uint32_t rn_ofs, uint32_t rm_ofs, \ | ||
86 | + uint32_t oprsz, uint32_t maxsz) \ | ||
87 | + { \ | ||
88 | + /* Note the operation is vshl vd,vm,vn */ \ | ||
89 | + tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, \ | ||
90 | + oprsz, maxsz, &OPARRAY[vece]); \ | ||
91 | + } \ | ||
92 | + DO_3SAME(INSN, gen_##INSN##_3s) | ||
93 | + | ||
94 | +DO_3SAME_GVEC3_SHIFT(VSHL_S, sshl_op) | ||
95 | +DO_3SAME_GVEC3_SHIFT(VSHL_U, ushl_op) | ||
96 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
97 | index XXXXXXX..XXXXXXX 100644 | ||
98 | --- a/target/arm/translate.c | ||
99 | +++ b/target/arm/translate.c | ||
100 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
101 | } | ||
102 | return 1; | ||
103 | |||
104 | - case NEON_3R_VMUL: /* VMUL */ | ||
105 | - if (u) { | ||
106 | - /* Polynomial case allows only P8. */ | ||
107 | - if (size != 0) { | ||
108 | - return 1; | ||
109 | - } | ||
110 | - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, | ||
111 | - 0, gen_helper_gvec_pmul_b); | ||
112 | - } else { | ||
113 | - tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs, | ||
114 | - vec_size, vec_size); | ||
115 | - } | ||
116 | - return 0; | ||
117 | - | ||
118 | - case NEON_3R_VML: /* VMLA, VMLS */ | ||
119 | - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, | ||
120 | - u ? &mls_op[size] : &mla_op[size]); | ||
121 | - return 0; | ||
122 | - | ||
123 | - case NEON_3R_VSHL: | ||
124 | - /* Note the operation is vshl vd,vm,vn */ | ||
125 | - tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size, | ||
126 | - u ? &ushl_op[size] : &sshl_op[size]); | ||
127 | - return 0; | ||
128 | - | ||
129 | case NEON_3R_VADD_VSUB: | ||
130 | case NEON_3R_LOGIC: | ||
131 | case NEON_3R_VMAX: | ||
132 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
133 | case NEON_3R_VCGE: | ||
134 | case NEON_3R_VQADD: | ||
135 | case NEON_3R_VQSUB: | ||
136 | + case NEON_3R_VMUL: | ||
137 | + case NEON_3R_VML: | ||
138 | + case NEON_3R_VSHL: | ||
139 | /* Already handled by decodetree */ | ||
140 | return 1; | ||
141 | } | ||
38 | -- | 142 | -- |
39 | 2.16.2 | 143 | 2.20.1 |
40 | 144 | ||
41 | 145 | diff view generated by jsdifflib |
1 | For the rpi1 and 2 we want to boot the Linux kernel via some | 1 | We're going to want at least some of the NeonGen* typedefs |
---|---|---|---|
2 | custom setup code that makes sure that the SMC instruction | 2 | for the refactored 32-bit Neon decoder, so move them all |
3 | acts as a no-op, because it's used for cache maintenance. | 3 | to translate.h since it makes more sense to keep them in |
4 | The rpi3 boots AArch64 kernels, which don't need SMC for | 4 | one group. |
5 | cache maintenance and always expect to be booted non-secure. | ||
6 | Don't fill in the aarch32-specific parts of the binfo struct. | ||
7 | 5 | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
10 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 8 | Message-id: 20200430181003.21682-23-peter.maydell@linaro.org |
11 | Message-id: 20180313153458.26822-2-peter.maydell@linaro.org | ||
12 | --- | 9 | --- |
13 | hw/arm/raspi.c | 17 +++++++++++++---- | 10 | target/arm/translate.h | 17 +++++++++++++++++ |
14 | 1 file changed, 13 insertions(+), 4 deletions(-) | 11 | target/arm/translate-a64.c | 17 ----------------- |
12 | 2 files changed, 17 insertions(+), 17 deletions(-) | ||
15 | 13 | ||
16 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 14 | diff --git a/target/arm/translate.h b/target/arm/translate.h |
17 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/hw/arm/raspi.c | 16 | --- a/target/arm/translate.h |
19 | +++ b/hw/arm/raspi.c | 17 | +++ b/target/arm/translate.h |
20 | @@ -XXX,XX +XXX,XX @@ static void setup_boot(MachineState *machine, int version, size_t ram_size) | 18 | @@ -XXX,XX +XXX,XX @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t, |
21 | binfo.board_id = raspi_boardid[version]; | 19 | typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t, |
22 | binfo.ram_size = ram_size; | 20 | uint32_t, uint32_t, uint32_t); |
23 | binfo.nb_cpus = smp_cpus; | 21 | |
24 | - binfo.board_setup_addr = BOARDSETUP_ADDR; | 22 | +/* Function prototype for gen_ functions for calling Neon helpers */ |
25 | - binfo.write_board_setup = write_board_setup; | 23 | +typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); |
26 | - binfo.secure_board_setup = true; | 24 | +typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); |
27 | - binfo.secure_boot = true; | 25 | +typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); |
26 | +typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); | ||
27 | +typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); | ||
28 | +typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); | ||
29 | +typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); | ||
30 | +typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); | ||
31 | +typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); | ||
32 | +typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); | ||
33 | +typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); | ||
34 | +typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); | ||
35 | +typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
36 | +typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
37 | +typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
28 | + | 38 | + |
29 | + if (version <= 2) { | 39 | #endif /* TARGET_ARM_TRANSLATE_H */ |
30 | + /* The rpi1 and 2 require some custom setup code to run in Secure | 40 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c |
31 | + * mode before booting a kernel (to set up the SMC vectors so | 41 | index XXXXXXX..XXXXXXX 100644 |
32 | + * that we get a no-op SMC; this is used by Linux to call the | 42 | --- a/target/arm/translate-a64.c |
33 | + * firmware for some cache maintenance operations. | 43 | +++ b/target/arm/translate-a64.c |
34 | + * The rpi3 doesn't need this. | 44 | @@ -XXX,XX +XXX,XX @@ typedef struct AArch64DecodeTable { |
35 | + */ | 45 | AArch64DecodeFn *disas_fn; |
36 | + binfo.board_setup_addr = BOARDSETUP_ADDR; | 46 | } AArch64DecodeTable; |
37 | + binfo.write_board_setup = write_board_setup; | 47 | |
38 | + binfo.secure_board_setup = true; | 48 | -/* Function prototype for gen_ functions for calling Neon helpers */ |
39 | + binfo.secure_boot = true; | 49 | -typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); |
40 | + } | 50 | -typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); |
41 | 51 | -typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); | |
42 | /* Pi2 and Pi3 requires SMP setup */ | 52 | -typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); |
43 | if (version >= 2) { | 53 | -typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); |
54 | -typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); | ||
55 | -typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); | ||
56 | -typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); | ||
57 | -typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); | ||
58 | -typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); | ||
59 | -typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); | ||
60 | -typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr); | ||
61 | -typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32); | ||
62 | -typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); | ||
63 | -typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp); | ||
64 | - | ||
65 | /* initialize TCG globals. */ | ||
66 | void a64_translate_init(void) | ||
67 | { | ||
44 | -- | 68 | -- |
45 | 2.16.2 | 69 | 2.20.1 |
46 | 70 | ||
47 | 71 | diff view generated by jsdifflib |