1 | Arm patch queue -- these are all bug fix patches but we might | 1 | Latest arm queue, half minor code cleanups and half minor |
---|---|---|---|
2 | as well put them in to rc0... | 2 | bug fixes. |
3 | 3 | ||
4 | thanks | ||
5 | -- PMM | 4 | -- PMM |
6 | 5 | ||
7 | The following changes since commit 2c8cfc0b52b5a4d123c26c0b5fdf941be24805be: | 6 | The following changes since commit 5d0e5694470d2952b4f257bc985cac8c89b4fd92: |
8 | 7 | ||
9 | Merge remote-tracking branch 'remotes/kevin/tags/for-upstream' into staging (2018-03-19 11:44:26 +0000) | 8 | Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging (2019-06-17 11:55:14 +0100) |
10 | 9 | ||
11 | are available in the Git repository at: | 10 | are available in the Git repository at: |
12 | 11 | ||
13 | git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180319 | 12 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190617 |
14 | 13 | ||
15 | for you to fetch changes up to ff72cb6b46b95bb530787add5277c211af3d31c6: | 14 | for you to fetch changes up to 1120827fa182f0e76226df7ffe7a86598d1df54f: |
16 | 15 | ||
17 | hw/arm/raspi: Provide spin-loop code for AArch64 CPUs (2018-03-19 18:23:24 +0000) | 16 | target/arm: Only implement doubles if the FPU supports them (2019-06-17 15:15:06 +0100) |
18 | 17 | ||
19 | ---------------------------------------------------------------- | 18 | ---------------------------------------------------------------- |
20 | target-arm queue: | 19 | target-arm queue: |
21 | * fsl-imx6: Fix incorrect Ethernet interrupt defines | 20 | * support large kernel images in bootloader (by avoiding |
22 | * dump: Update correct kdump phys_base field for AArch64 | 21 | putting the initrd over the top of them) |
23 | * char: i.MX: Add support for "TX complete" interrupt | 22 | * correctly disable FPU/DSP in the CPU for the mps2-an521, musca-a boards |
24 | * bcm2836/raspi: Fix various bugs resulting in panics trying | 23 | * arm_gicv3: Fix decoding of ID register range |
25 | to boot a Debian Linux kernel on raspi3 | 24 | * arm_gicv3: GICD_TYPER.SecurityExtn is RAZ if GICD_CTLR.DS == 1 |
25 | * some code cleanups following on from the VFP decodetree conversion | ||
26 | * Only implement doubles if the FPU supports them | ||
27 | (so we now correctly model Cortex-M4, -M33 as single precision only) | ||
26 | 28 | ||
27 | ---------------------------------------------------------------- | 29 | ---------------------------------------------------------------- |
28 | Andrey Smirnov (2): | 30 | Peter Maydell (24): |
29 | char: i.MX: Simplify imx_update() | 31 | hw/arm/boot: Don't assume RAM starts at address zero |
30 | char: i.MX: Add support for "TX complete" interrupt | 32 | hw/arm/boot: Diagnose layouts that put initrd or DTB off the end of RAM |
33 | hw/arm/boot: Avoid placing the initrd on top of the kernel | ||
34 | hw/arm/boot: Honour image size field in AArch64 Image format kernels | ||
35 | target/arm: Allow VFP and Neon to be disabled via a CPU property | ||
36 | target/arm: Allow M-profile CPUs to disable the DSP extension via CPU property | ||
37 | hw/arm/armv7m: Forward "vfp" and "dsp" properties to CPU | ||
38 | hw/arm: Correctly disable FPU/DSP for some ARMSSE-based boards | ||
39 | hw/intc/arm_gicv3: Fix decoding of ID register range | ||
40 | hw/intc/arm_gicv3: GICD_TYPER.SecurityExtn is RAZ if GICD_CTLR.DS == 1 | ||
41 | target/arm: Move vfp_expand_imm() to translate.[ch] | ||
42 | target/arm: Use vfp_expand_imm() for AArch32 VFP VMOV_imm | ||
43 | target/arm: Stop using cpu_F0s for NEON_2RM_VABS_F | ||
44 | target/arm: Stop using cpu_F0s for NEON_2RM_VNEG_F | ||
45 | target/arm: Stop using cpu_F0s for NEON_2RM_VRINT* | ||
46 | target/arm: Stop using cpu_F0s for NEON_2RM_VCVT[ANPM][US] | ||
47 | target/arm: Stop using cpu_F0s for NEON_2RM_VRECPE_F and NEON_2RM_VRSQRTE_F | ||
48 | target/arm: Stop using cpu_F0s for Neon f32/s32 VCVT | ||
49 | target/arm: Stop using cpu_F0s in Neon VCVT fixed-point ops | ||
50 | target/arm: stop using deprecated functions in NEON_2RM_VCVT_F16_F32 | ||
51 | target/arm: Stop using deprecated functions in NEON_2RM_VCVT_F32_F16 | ||
52 | target/arm: Remove unused cpu_F0s, cpu_F0d, cpu_F1s, cpu_F1d | ||
53 | target/arm: Fix typos in trans function prototypes | ||
54 | target/arm: Only implement doubles if the FPU supports them | ||
31 | 55 | ||
32 | Guenter Roeck (1): | 56 | include/hw/arm/armsse.h | 7 ++ |
33 | fsl-imx6: Swap Ethernet interrupt defines | 57 | include/hw/arm/armv7m.h | 4 + |
58 | target/arm/cpu.h | 12 +++ | ||
59 | target/arm/translate-a64.h | 1 - | ||
60 | target/arm/translate.h | 7 ++ | ||
61 | hw/arm/armsse.c | 58 +++++++--- | ||
62 | hw/arm/armv7m.c | 18 ++++ | ||
63 | hw/arm/boot.c | 83 ++++++++++---- | ||
64 | hw/arm/musca.c | 8 ++ | ||
65 | hw/intc/arm_gicv3_dist.c | 12 ++- | ||
66 | hw/intc/arm_gicv3_redist.c | 4 +- | ||
67 | target/arm/cpu.c | 179 ++++++++++++++++++++++++++++-- | ||
68 | target/arm/translate-a64.c | 32 ------ | ||
69 | target/arm/translate-vfp.inc.c | 173 ++++++++++++++++++++++------- | ||
70 | target/arm/translate.c | 240 ++++++++++++++--------------------------- | ||
71 | target/arm/vfp.decode | 10 +- | ||
72 | 16 files changed, 572 insertions(+), 276 deletions(-) | ||
34 | 73 | ||
35 | Peter Maydell (9): | ||
36 | hw/arm/raspi: Don't do board-setup or secure-boot for raspi3 | ||
37 | hw/arm/boot: assert that secure_boot and secure_board_setup are false for AArch64 | ||
38 | hw/arm/boot: If booting a kernel in EL2, set SCR_EL3.HCE | ||
39 | hw/arm/bcm2386: Fix parent type of bcm2386 | ||
40 | hw/arm/bcm2836: Rename bcm2836 type/struct to bcm283x | ||
41 | hw/arm/bcm2836: Create proper bcm2837 device | ||
42 | hw/arm/bcm2836: Use correct affinity values for BCM2837 | ||
43 | hw/arm/bcm2836: Hardcode correct CPU type | ||
44 | hw/arm/raspi: Provide spin-loop code for AArch64 CPUs | ||
45 | |||
46 | Wei Huang (1): | ||
47 | dump: Update correct kdump phys_base field for AArch64 | ||
48 | |||
49 | include/hw/arm/bcm2836.h | 31 +++++++++++++--- | ||
50 | include/hw/arm/fsl-imx6.h | 4 +- | ||
51 | include/hw/char/imx_serial.h | 3 ++ | ||
52 | dump.c | 14 +++++-- | ||
53 | hw/arm/bcm2836.c | 87 +++++++++++++++++++++++++++++++------------- | ||
54 | hw/arm/boot.c | 12 ++++++ | ||
55 | hw/arm/raspi.c | 77 +++++++++++++++++++++++++++++++-------- | ||
56 | hw/char/imx_serial.c | 44 ++++++++++++++++------ | ||
57 | hw/net/imx_fec.c | 28 +++++++++++++- | ||
58 | 9 files changed, 237 insertions(+), 63 deletions(-) | ||
59 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | In the Arm kernel/initrd loading code, in some places we make the | ||
2 | incorrect assumption that info->ram_size can be treated as the | ||
3 | address of the end of RAM, as for instance when we calculate the | ||
4 | available space for the initrd using "info->ram_size - info->initrd_start". | ||
5 | This is wrong, because many Arm boards (including "virt") specify | ||
6 | a non-zero info->loader_start to indicate that their RAM area | ||
7 | starts at a non-zero physical address. | ||
1 | 8 | ||
9 | Correct the places which make this incorrect assumption. | ||
10 | |||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
13 | Tested-by: Mark Rutland <mark.rutland@arm.com> | ||
14 | Message-id: 20190516144733.32399-2-peter.maydell@linaro.org | ||
15 | --- | ||
16 | hw/arm/boot.c | 9 ++++----- | ||
17 | 1 file changed, 4 insertions(+), 5 deletions(-) | ||
18 | |||
19 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | ||
20 | index XXXXXXX..XXXXXXX 100644 | ||
21 | --- a/hw/arm/boot.c | ||
22 | +++ b/hw/arm/boot.c | ||
23 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
24 | int elf_machine; | ||
25 | hwaddr entry; | ||
26 | static const ARMInsnFixup *primary_loader; | ||
27 | + uint64_t ram_end = info->loader_start + info->ram_size; | ||
28 | |||
29 | if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { | ||
30 | primary_loader = bootloader_aarch64; | ||
31 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
32 | /* 32-bit ARM */ | ||
33 | entry = info->loader_start + KERNEL_LOAD_ADDR; | ||
34 | kernel_size = load_image_targphys_as(info->kernel_filename, entry, | ||
35 | - info->ram_size - KERNEL_LOAD_ADDR, | ||
36 | - as); | ||
37 | + ram_end - KERNEL_LOAD_ADDR, as); | ||
38 | is_linux = 1; | ||
39 | } | ||
40 | if (kernel_size < 0) { | ||
41 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
42 | if (info->initrd_filename) { | ||
43 | initrd_size = load_ramdisk_as(info->initrd_filename, | ||
44 | info->initrd_start, | ||
45 | - info->ram_size - info->initrd_start, | ||
46 | - as); | ||
47 | + ram_end - info->initrd_start, as); | ||
48 | if (initrd_size < 0) { | ||
49 | initrd_size = load_image_targphys_as(info->initrd_filename, | ||
50 | info->initrd_start, | ||
51 | - info->ram_size - | ||
52 | + ram_end - | ||
53 | info->initrd_start, | ||
54 | as); | ||
55 | } | ||
56 | -- | ||
57 | 2.20.1 | ||
58 | |||
59 | diff view generated by jsdifflib |
1 | If we're directly booting a Linux kernel and the CPU supports both | 1 | We calculate the locations in memory where we want to put the |
---|---|---|---|
2 | EL3 and EL2, we start the kernel in EL2, as it expects. We must also | 2 | initrd and the DTB based on the size of the kernel, since they |
3 | set the SCR_EL3.HCE bit in this situation, so that the HVC | 3 | come after it. Add some explicit checks that these aren't off the |
4 | instruction is enabled rather than UNDEFing. Otherwise at least some | 4 | end of RAM entirely. |
5 | kernels will panic when trying to initialize KVM in the guest. | 5 | |
6 | (At the moment the way we calculate the initrd_start means that | ||
7 | it can't ever be off the end of RAM, but that will change with | ||
8 | the next commit.) | ||
6 | 9 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Message-id: 20180313153458.26822-4-peter.maydell@linaro.org | 11 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> |
12 | Tested-by: Mark Rutland <mark.rutland@arm.com> | ||
13 | Message-id: 20190516144733.32399-3-peter.maydell@linaro.org | ||
9 | --- | 14 | --- |
10 | hw/arm/boot.c | 5 +++++ | 15 | hw/arm/boot.c | 23 +++++++++++++++++++++++ |
11 | 1 file changed, 5 insertions(+) | 16 | 1 file changed, 23 insertions(+) |
12 | 17 | ||
13 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | 18 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c |
14 | index XXXXXXX..XXXXXXX 100644 | 19 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/hw/arm/boot.c | 20 | --- a/hw/arm/boot.c |
16 | +++ b/hw/arm/boot.c | 21 | +++ b/hw/arm/boot.c |
17 | @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) | 22 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, |
18 | assert(!info->secure_board_setup); | 23 | error_report("could not load kernel '%s'", info->kernel_filename); |
19 | } | 24 | exit(1); |
20 | 25 | } | |
21 | + if (arm_feature(env, ARM_FEATURE_EL2)) { | ||
22 | + /* If we have EL2 then Linux expects the HVC insn to work */ | ||
23 | + env->cp15.scr_el3 |= SCR_HCE; | ||
24 | + } | ||
25 | + | 26 | + |
26 | /* Set to non-secure if not a secure boot */ | 27 | + if (kernel_size > info->ram_size) { |
27 | if (!info->secure_boot && | 28 | + error_report("kernel '%s' is too large to fit in RAM " |
28 | (cs != first_cpu || !info->secure_board_setup)) { | 29 | + "(kernel size %d, RAM size %" PRId64 ")", |
30 | + info->kernel_filename, kernel_size, info->ram_size); | ||
31 | + exit(1); | ||
32 | + } | ||
33 | + | ||
34 | info->entry = entry; | ||
35 | if (is_linux) { | ||
36 | uint32_t fixupcontext[FIXUP_MAX]; | ||
37 | |||
38 | if (info->initrd_filename) { | ||
39 | + | ||
40 | + if (info->initrd_start >= ram_end) { | ||
41 | + error_report("not enough space after kernel to load initrd"); | ||
42 | + exit(1); | ||
43 | + } | ||
44 | + | ||
45 | initrd_size = load_ramdisk_as(info->initrd_filename, | ||
46 | info->initrd_start, | ||
47 | ram_end - info->initrd_start, as); | ||
48 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
49 | info->initrd_filename); | ||
50 | exit(1); | ||
51 | } | ||
52 | + if (info->initrd_start + initrd_size > info->ram_size) { | ||
53 | + error_report("could not load initrd '%s': " | ||
54 | + "too big to fit into RAM after the kernel", | ||
55 | + info->initrd_filename); | ||
56 | + } | ||
57 | } else { | ||
58 | initrd_size = 0; | ||
59 | } | ||
60 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
61 | /* Place the DTB after the initrd in memory with alignment. */ | ||
62 | info->dtb_start = QEMU_ALIGN_UP(info->initrd_start + initrd_size, | ||
63 | align); | ||
64 | + if (info->dtb_start >= ram_end) { | ||
65 | + error_report("Not enough space for DTB after kernel/initrd"); | ||
66 | + exit(1); | ||
67 | + } | ||
68 | fixupcontext[FIXUP_ARGPTR_LO] = info->dtb_start; | ||
69 | fixupcontext[FIXUP_ARGPTR_HI] = info->dtb_start >> 32; | ||
70 | } else { | ||
29 | -- | 71 | -- |
30 | 2.16.2 | 72 | 2.20.1 |
31 | 73 | ||
32 | 74 | diff view generated by jsdifflib |
1 | Add some assertions that if we're about to boot an AArch64 kernel, | 1 | We currently put the initrd at the smaller of: |
---|---|---|---|
2 | the board code has not mistakenly set either secure_boot or | 2 | * 128MB into RAM |
3 | secure_board_setup. It doesn't make sense to set secure_boot, | 3 | * halfway into the RAM |
4 | because all AArch64 kernels must be booted in non-secure mode. | 4 | (with the dtb following it). |
5 | 5 | ||
6 | It might in theory make sense to set secure_board_setup, but | 6 | However for large kernels this might mean that the kernel |
7 | we don't currently support that, because only the AArch32 | 7 | overlaps the initrd. For some kinds of kernel (self-decompressing |
8 | bootloader[] code calls this hook; bootloader_aarch64[] does not. | 8 | 32-bit kernels, and ELF images with a BSS section at the end) |
9 | Since we don't have a current need for this functionality, just | 9 | we don't know the exact size, but even there we have a |
10 | assert that we don't try to use it. If it's needed we'll add | 10 | minimum size. Put the initrd at least further into RAM than |
11 | it later. | 11 | that. For image formats that can give us an exact kernel size, this |
12 | will mean that we definitely avoid overlaying kernel and initrd. | ||
12 | 13 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 15 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> |
15 | Message-id: 20180313153458.26822-3-peter.maydell@linaro.org | 16 | Tested-by: Mark Rutland <mark.rutland@arm.com> |
17 | Message-id: 20190516144733.32399-4-peter.maydell@linaro.org | ||
16 | --- | 18 | --- |
17 | hw/arm/boot.c | 7 +++++++ | 19 | hw/arm/boot.c | 34 ++++++++++++++++++++-------------- |
18 | 1 file changed, 7 insertions(+) | 20 | 1 file changed, 20 insertions(+), 14 deletions(-) |
19 | 21 | ||
20 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | 22 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c |
21 | index XXXXXXX..XXXXXXX 100644 | 23 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/hw/arm/boot.c | 24 | --- a/hw/arm/boot.c |
23 | +++ b/hw/arm/boot.c | 25 | +++ b/hw/arm/boot.c |
24 | @@ -XXX,XX +XXX,XX @@ static void do_cpu_reset(void *opaque) | 26 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, |
25 | } else { | 27 | if (info->nb_cpus == 0) |
26 | env->pstate = PSTATE_MODE_EL1h; | 28 | info->nb_cpus = 1; |
27 | } | 29 | |
28 | + /* AArch64 kernels never boot in secure mode */ | 30 | - /* |
29 | + assert(!info->secure_boot); | 31 | - * We want to put the initrd far enough into RAM that when the |
30 | + /* This hook is only supported for AArch32 currently: | 32 | - * kernel is uncompressed it will not clobber the initrd. However |
31 | + * bootloader_aarch64[] will not call the hook, and | 33 | - * on boards without much RAM we must ensure that we still leave |
32 | + * the code above has already dropped us into EL2 or EL1. | 34 | - * enough room for a decent sized initrd, and on boards with large |
33 | + */ | 35 | - * amounts of RAM we must avoid the initrd being so far up in RAM |
34 | + assert(!info->secure_board_setup); | 36 | - * that it is outside lowmem and inaccessible to the kernel. |
35 | } | 37 | - * So for boards with less than 256MB of RAM we put the initrd |
36 | 38 | - * halfway into RAM, and for boards with 256MB of RAM or more we put | |
37 | /* Set to non-secure if not a secure boot */ | 39 | - * the initrd at 128MB. |
40 | - */ | ||
41 | - info->initrd_start = info->loader_start + | ||
42 | - MIN(info->ram_size / 2, 128 * 1024 * 1024); | ||
43 | - | ||
44 | /* Assume that raw images are linux kernels, and ELF images are not. */ | ||
45 | kernel_size = arm_load_elf(info, &elf_entry, &elf_low_addr, | ||
46 | &elf_high_addr, elf_machine, as); | ||
47 | @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
48 | } | ||
49 | |||
50 | info->entry = entry; | ||
51 | + | ||
52 | + /* | ||
53 | + * We want to put the initrd far enough into RAM that when the | ||
54 | + * kernel is uncompressed it will not clobber the initrd. However | ||
55 | + * on boards without much RAM we must ensure that we still leave | ||
56 | + * enough room for a decent sized initrd, and on boards with large | ||
57 | + * amounts of RAM we must avoid the initrd being so far up in RAM | ||
58 | + * that it is outside lowmem and inaccessible to the kernel. | ||
59 | + * So for boards with less than 256MB of RAM we put the initrd | ||
60 | + * halfway into RAM, and for boards with 256MB of RAM or more we put | ||
61 | + * the initrd at 128MB. | ||
62 | + * We also refuse to put the initrd somewhere that will definitely | ||
63 | + * overlay the kernel we just loaded, though for kernel formats which | ||
64 | + * don't tell us their exact size (eg self-decompressing 32-bit kernels) | ||
65 | + * we might still make a bad choice here. | ||
66 | + */ | ||
67 | + info->initrd_start = info->loader_start + | ||
68 | + MAX(MIN(info->ram_size / 2, 128 * 1024 * 1024), kernel_size); | ||
69 | + info->initrd_start = TARGET_PAGE_ALIGN(info->initrd_start); | ||
70 | + | ||
71 | if (is_linux) { | ||
72 | uint32_t fixupcontext[FIXUP_MAX]; | ||
73 | |||
38 | -- | 74 | -- |
39 | 2.16.2 | 75 | 2.20.1 |
40 | 76 | ||
41 | 77 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Since Linux v3.17, the kernel's Image header includes a field image_size, | ||
2 | which gives the total size of the kernel including unpopulated data | ||
3 | sections such as the BSS). If this is present, then return it from | ||
4 | load_aarch64_image() as the true size of the kernel rather than | ||
5 | just using the size of the Image file itself. This allows the code | ||
6 | which calculates where to put the initrd to avoid putting it in | ||
7 | the kernel's BSS area. | ||
1 | 8 | ||
9 | This means that we should be able to reliably load kernel images | ||
10 | which are larger than 128MB without accidentally putting the | ||
11 | initrd or dtb in locations that clash with the kernel itself. | ||
12 | |||
13 | Fixes: https://bugs.launchpad.net/qemu/+bug/1823998 | ||
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
15 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
16 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
17 | Tested-by: Mark Rutland <mark.rutland@arm.com> | ||
18 | Message-id: 20190516144733.32399-5-peter.maydell@linaro.org | ||
19 | --- | ||
20 | hw/arm/boot.c | 17 +++++++++++++++-- | ||
21 | 1 file changed, 15 insertions(+), 2 deletions(-) | ||
22 | |||
23 | diff --git a/hw/arm/boot.c b/hw/arm/boot.c | ||
24 | index XXXXXXX..XXXXXXX 100644 | ||
25 | --- a/hw/arm/boot.c | ||
26 | +++ b/hw/arm/boot.c | ||
27 | @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, | ||
28 | hwaddr *entry, AddressSpace *as) | ||
29 | { | ||
30 | hwaddr kernel_load_offset = KERNEL64_LOAD_ADDR; | ||
31 | + uint64_t kernel_size = 0; | ||
32 | uint8_t *buffer; | ||
33 | int size; | ||
34 | |||
35 | @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, | ||
36 | * is only valid if the image_size is non-zero. | ||
37 | */ | ||
38 | memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals)); | ||
39 | - if (hdrvals[1] != 0) { | ||
40 | + | ||
41 | + kernel_size = le64_to_cpu(hdrvals[1]); | ||
42 | + | ||
43 | + if (kernel_size != 0) { | ||
44 | kernel_load_offset = le64_to_cpu(hdrvals[0]); | ||
45 | |||
46 | /* | ||
47 | @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, | ||
48 | } | ||
49 | } | ||
50 | |||
51 | + /* | ||
52 | + * Kernels before v3.17 don't populate the image_size field, and | ||
53 | + * raw images have no header. For those our best guess at the size | ||
54 | + * is the size of the Image file itself. | ||
55 | + */ | ||
56 | + if (kernel_size == 0) { | ||
57 | + kernel_size = size; | ||
58 | + } | ||
59 | + | ||
60 | *entry = mem_base + kernel_load_offset; | ||
61 | rom_add_blob_fixed_as(filename, buffer, size, *entry, as); | ||
62 | |||
63 | g_free(buffer); | ||
64 | |||
65 | - return size; | ||
66 | + return kernel_size; | ||
67 | } | ||
68 | |||
69 | static void arm_setup_direct_kernel_boot(ARMCPU *cpu, | ||
70 | -- | ||
71 | 2.20.1 | ||
72 | |||
73 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | Allow VFP and neon to be disabled via a CPU property. As with | |
2 | the "pmu" property, we only allow these features to be removed | ||
3 | from CPUs which have it by default, not added to CPUs which | ||
4 | don't have it. | ||
5 | |||
6 | The primary motivation here is to be able to optionally | ||
7 | create Cortex-M33 CPUs with no FPU, but we provide switches | ||
8 | for both VFP and Neon because the two interact: | ||
9 | * AArch64 can't have one without the other | ||
10 | * Some ID register fields only change if both are disabled | ||
11 | |||
12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
13 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
14 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
15 | Message-id: 20190517174046.11146-2-peter.maydell@linaro.org | ||
16 | --- | ||
17 | target/arm/cpu.h | 4 ++ | ||
18 | target/arm/cpu.c | 150 +++++++++++++++++++++++++++++++++++++++++++++-- | ||
19 | 2 files changed, 148 insertions(+), 6 deletions(-) | ||
20 | |||
21 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
22 | index XXXXXXX..XXXXXXX 100644 | ||
23 | --- a/target/arm/cpu.h | ||
24 | +++ b/target/arm/cpu.h | ||
25 | @@ -XXX,XX +XXX,XX @@ struct ARMCPU { | ||
26 | bool has_el3; | ||
27 | /* CPU has PMU (Performance Monitor Unit) */ | ||
28 | bool has_pmu; | ||
29 | + /* CPU has VFP */ | ||
30 | + bool has_vfp; | ||
31 | + /* CPU has Neon */ | ||
32 | + bool has_neon; | ||
33 | |||
34 | /* CPU has memory protection unit */ | ||
35 | bool has_mpu; | ||
36 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/target/arm/cpu.c | ||
39 | +++ b/target/arm/cpu.c | ||
40 | @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_cfgend_property = | ||
41 | static Property arm_cpu_has_pmu_property = | ||
42 | DEFINE_PROP_BOOL("pmu", ARMCPU, has_pmu, true); | ||
43 | |||
44 | +static Property arm_cpu_has_vfp_property = | ||
45 | + DEFINE_PROP_BOOL("vfp", ARMCPU, has_vfp, true); | ||
46 | + | ||
47 | +static Property arm_cpu_has_neon_property = | ||
48 | + DEFINE_PROP_BOOL("neon", ARMCPU, has_neon, true); | ||
49 | + | ||
50 | static Property arm_cpu_has_mpu_property = | ||
51 | DEFINE_PROP_BOOL("has-mpu", ARMCPU, has_mpu, true); | ||
52 | |||
53 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) | ||
54 | if (arm_feature(&cpu->env, ARM_FEATURE_M)) { | ||
55 | set_feature(&cpu->env, ARM_FEATURE_PMSA); | ||
56 | } | ||
57 | + /* Similarly for the VFP feature bits */ | ||
58 | + if (arm_feature(&cpu->env, ARM_FEATURE_VFP4)) { | ||
59 | + set_feature(&cpu->env, ARM_FEATURE_VFP3); | ||
60 | + } | ||
61 | + if (arm_feature(&cpu->env, ARM_FEATURE_VFP3)) { | ||
62 | + set_feature(&cpu->env, ARM_FEATURE_VFP); | ||
63 | + } | ||
64 | |||
65 | if (arm_feature(&cpu->env, ARM_FEATURE_CBAR) || | ||
66 | arm_feature(&cpu->env, ARM_FEATURE_CBAR_RO)) { | ||
67 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) | ||
68 | &error_abort); | ||
69 | } | ||
70 | |||
71 | + /* | ||
72 | + * Allow user to turn off VFP and Neon support, but only for TCG -- | ||
73 | + * KVM does not currently allow us to lie to the guest about its | ||
74 | + * ID/feature registers, so the guest always sees what the host has. | ||
75 | + */ | ||
76 | + if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { | ||
77 | + cpu->has_vfp = true; | ||
78 | + if (!kvm_enabled()) { | ||
79 | + qdev_property_add_static(DEVICE(obj), &arm_cpu_has_vfp_property, | ||
80 | + &error_abort); | ||
81 | + } | ||
82 | + } | ||
83 | + | ||
84 | + if (arm_feature(&cpu->env, ARM_FEATURE_NEON)) { | ||
85 | + cpu->has_neon = true; | ||
86 | + if (!kvm_enabled()) { | ||
87 | + qdev_property_add_static(DEVICE(obj), &arm_cpu_has_neon_property, | ||
88 | + &error_abort); | ||
89 | + } | ||
90 | + } | ||
91 | + | ||
92 | if (arm_feature(&cpu->env, ARM_FEATURE_PMSA)) { | ||
93 | qdev_property_add_static(DEVICE(obj), &arm_cpu_has_mpu_property, | ||
94 | &error_abort); | ||
95 | @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) | ||
96 | return; | ||
97 | } | ||
98 | |||
99 | + if (arm_feature(env, ARM_FEATURE_AARCH64) && | ||
100 | + cpu->has_vfp != cpu->has_neon) { | ||
101 | + /* | ||
102 | + * This is an architectural requirement for AArch64; AArch32 is | ||
103 | + * more flexible and permits VFP-no-Neon and Neon-no-VFP. | ||
104 | + */ | ||
105 | + error_setg(errp, | ||
106 | + "AArch64 CPUs must have both VFP and Neon or neither"); | ||
107 | + return; | ||
108 | + } | ||
109 | + | ||
110 | + if (!cpu->has_vfp) { | ||
111 | + uint64_t t; | ||
112 | + uint32_t u; | ||
113 | + | ||
114 | + unset_feature(env, ARM_FEATURE_VFP); | ||
115 | + unset_feature(env, ARM_FEATURE_VFP3); | ||
116 | + unset_feature(env, ARM_FEATURE_VFP4); | ||
117 | + | ||
118 | + t = cpu->isar.id_aa64isar1; | ||
119 | + t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 0); | ||
120 | + cpu->isar.id_aa64isar1 = t; | ||
121 | + | ||
122 | + t = cpu->isar.id_aa64pfr0; | ||
123 | + t = FIELD_DP64(t, ID_AA64PFR0, FP, 0xf); | ||
124 | + cpu->isar.id_aa64pfr0 = t; | ||
125 | + | ||
126 | + u = cpu->isar.id_isar6; | ||
127 | + u = FIELD_DP32(u, ID_ISAR6, JSCVT, 0); | ||
128 | + cpu->isar.id_isar6 = u; | ||
129 | + | ||
130 | + u = cpu->isar.mvfr0; | ||
131 | + u = FIELD_DP32(u, MVFR0, FPSP, 0); | ||
132 | + u = FIELD_DP32(u, MVFR0, FPDP, 0); | ||
133 | + u = FIELD_DP32(u, MVFR0, FPTRAP, 0); | ||
134 | + u = FIELD_DP32(u, MVFR0, FPDIVIDE, 0); | ||
135 | + u = FIELD_DP32(u, MVFR0, FPSQRT, 0); | ||
136 | + u = FIELD_DP32(u, MVFR0, FPSHVEC, 0); | ||
137 | + u = FIELD_DP32(u, MVFR0, FPROUND, 0); | ||
138 | + cpu->isar.mvfr0 = u; | ||
139 | + | ||
140 | + u = cpu->isar.mvfr1; | ||
141 | + u = FIELD_DP32(u, MVFR1, FPFTZ, 0); | ||
142 | + u = FIELD_DP32(u, MVFR1, FPDNAN, 0); | ||
143 | + u = FIELD_DP32(u, MVFR1, FPHP, 0); | ||
144 | + cpu->isar.mvfr1 = u; | ||
145 | + | ||
146 | + u = cpu->isar.mvfr2; | ||
147 | + u = FIELD_DP32(u, MVFR2, FPMISC, 0); | ||
148 | + cpu->isar.mvfr2 = u; | ||
149 | + } | ||
150 | + | ||
151 | + if (!cpu->has_neon) { | ||
152 | + uint64_t t; | ||
153 | + uint32_t u; | ||
154 | + | ||
155 | + unset_feature(env, ARM_FEATURE_NEON); | ||
156 | + | ||
157 | + t = cpu->isar.id_aa64isar0; | ||
158 | + t = FIELD_DP64(t, ID_AA64ISAR0, DP, 0); | ||
159 | + cpu->isar.id_aa64isar0 = t; | ||
160 | + | ||
161 | + t = cpu->isar.id_aa64isar1; | ||
162 | + t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 0); | ||
163 | + cpu->isar.id_aa64isar1 = t; | ||
164 | + | ||
165 | + t = cpu->isar.id_aa64pfr0; | ||
166 | + t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 0xf); | ||
167 | + cpu->isar.id_aa64pfr0 = t; | ||
168 | + | ||
169 | + u = cpu->isar.id_isar5; | ||
170 | + u = FIELD_DP32(u, ID_ISAR5, RDM, 0); | ||
171 | + u = FIELD_DP32(u, ID_ISAR5, VCMA, 0); | ||
172 | + cpu->isar.id_isar5 = u; | ||
173 | + | ||
174 | + u = cpu->isar.id_isar6; | ||
175 | + u = FIELD_DP32(u, ID_ISAR6, DP, 0); | ||
176 | + u = FIELD_DP32(u, ID_ISAR6, FHM, 0); | ||
177 | + cpu->isar.id_isar6 = u; | ||
178 | + | ||
179 | + u = cpu->isar.mvfr1; | ||
180 | + u = FIELD_DP32(u, MVFR1, SIMDLS, 0); | ||
181 | + u = FIELD_DP32(u, MVFR1, SIMDINT, 0); | ||
182 | + u = FIELD_DP32(u, MVFR1, SIMDSP, 0); | ||
183 | + u = FIELD_DP32(u, MVFR1, SIMDHP, 0); | ||
184 | + u = FIELD_DP32(u, MVFR1, SIMDFMAC, 0); | ||
185 | + cpu->isar.mvfr1 = u; | ||
186 | + | ||
187 | + u = cpu->isar.mvfr2; | ||
188 | + u = FIELD_DP32(u, MVFR2, SIMDMISC, 0); | ||
189 | + cpu->isar.mvfr2 = u; | ||
190 | + } | ||
191 | + | ||
192 | + if (!cpu->has_neon && !cpu->has_vfp) { | ||
193 | + uint64_t t; | ||
194 | + uint32_t u; | ||
195 | + | ||
196 | + t = cpu->isar.id_aa64isar0; | ||
197 | + t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 0); | ||
198 | + cpu->isar.id_aa64isar0 = t; | ||
199 | + | ||
200 | + t = cpu->isar.id_aa64isar1; | ||
201 | + t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 0); | ||
202 | + cpu->isar.id_aa64isar1 = t; | ||
203 | + | ||
204 | + u = cpu->isar.mvfr0; | ||
205 | + u = FIELD_DP32(u, MVFR0, SIMDREG, 0); | ||
206 | + cpu->isar.mvfr0 = u; | ||
207 | + } | ||
208 | + | ||
209 | /* Some features automatically imply others: */ | ||
210 | if (arm_feature(env, ARM_FEATURE_V8)) { | ||
211 | if (arm_feature(env, ARM_FEATURE_M)) { | ||
212 | @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) | ||
213 | if (arm_feature(env, ARM_FEATURE_V5)) { | ||
214 | set_feature(env, ARM_FEATURE_V4T); | ||
215 | } | ||
216 | - if (arm_feature(env, ARM_FEATURE_VFP4)) { | ||
217 | - set_feature(env, ARM_FEATURE_VFP3); | ||
218 | - } | ||
219 | - if (arm_feature(env, ARM_FEATURE_VFP3)) { | ||
220 | - set_feature(env, ARM_FEATURE_VFP); | ||
221 | - } | ||
222 | if (arm_feature(env, ARM_FEATURE_LPAE)) { | ||
223 | set_feature(env, ARM_FEATURE_V7MP); | ||
224 | set_feature(env, ARM_FEATURE_PXN); | ||
225 | -- | ||
226 | 2.20.1 | ||
227 | |||
228 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Allow the DSP extension to be disabled via a CPU property for | ||
2 | M-profile CPUs. (A and R-profile CPUs don't have this extension | ||
3 | as a defined separate optional architecture extension, so | ||
4 | they don't need the property.) | ||
1 | 5 | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
7 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
8 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Message-id: 20190517174046.11146-3-peter.maydell@linaro.org | ||
10 | --- | ||
11 | target/arm/cpu.h | 2 ++ | ||
12 | target/arm/cpu.c | 29 +++++++++++++++++++++++++++++ | ||
13 | 2 files changed, 31 insertions(+) | ||
14 | |||
15 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/cpu.h | ||
18 | +++ b/target/arm/cpu.h | ||
19 | @@ -XXX,XX +XXX,XX @@ struct ARMCPU { | ||
20 | bool has_vfp; | ||
21 | /* CPU has Neon */ | ||
22 | bool has_neon; | ||
23 | + /* CPU has M-profile DSP extension */ | ||
24 | + bool has_dsp; | ||
25 | |||
26 | /* CPU has memory protection unit */ | ||
27 | bool has_mpu; | ||
28 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | ||
29 | index XXXXXXX..XXXXXXX 100644 | ||
30 | --- a/target/arm/cpu.c | ||
31 | +++ b/target/arm/cpu.c | ||
32 | @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_has_vfp_property = | ||
33 | static Property arm_cpu_has_neon_property = | ||
34 | DEFINE_PROP_BOOL("neon", ARMCPU, has_neon, true); | ||
35 | |||
36 | +static Property arm_cpu_has_dsp_property = | ||
37 | + DEFINE_PROP_BOOL("dsp", ARMCPU, has_dsp, true); | ||
38 | + | ||
39 | static Property arm_cpu_has_mpu_property = | ||
40 | DEFINE_PROP_BOOL("has-mpu", ARMCPU, has_mpu, true); | ||
41 | |||
42 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) | ||
43 | } | ||
44 | } | ||
45 | |||
46 | + if (arm_feature(&cpu->env, ARM_FEATURE_M) && | ||
47 | + arm_feature(&cpu->env, ARM_FEATURE_THUMB_DSP)) { | ||
48 | + qdev_property_add_static(DEVICE(obj), &arm_cpu_has_dsp_property, | ||
49 | + &error_abort); | ||
50 | + } | ||
51 | + | ||
52 | if (arm_feature(&cpu->env, ARM_FEATURE_PMSA)) { | ||
53 | qdev_property_add_static(DEVICE(obj), &arm_cpu_has_mpu_property, | ||
54 | &error_abort); | ||
55 | @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) | ||
56 | cpu->isar.mvfr0 = u; | ||
57 | } | ||
58 | |||
59 | + if (arm_feature(env, ARM_FEATURE_M) && !cpu->has_dsp) { | ||
60 | + uint32_t u; | ||
61 | + | ||
62 | + unset_feature(env, ARM_FEATURE_THUMB_DSP); | ||
63 | + | ||
64 | + u = cpu->isar.id_isar1; | ||
65 | + u = FIELD_DP32(u, ID_ISAR1, EXTEND, 1); | ||
66 | + cpu->isar.id_isar1 = u; | ||
67 | + | ||
68 | + u = cpu->isar.id_isar2; | ||
69 | + u = FIELD_DP32(u, ID_ISAR2, MULTU, 1); | ||
70 | + u = FIELD_DP32(u, ID_ISAR2, MULTS, 1); | ||
71 | + cpu->isar.id_isar2 = u; | ||
72 | + | ||
73 | + u = cpu->isar.id_isar3; | ||
74 | + u = FIELD_DP32(u, ID_ISAR3, SIMD, 1); | ||
75 | + u = FIELD_DP32(u, ID_ISAR3, SATURATE, 0); | ||
76 | + cpu->isar.id_isar3 = u; | ||
77 | + } | ||
78 | + | ||
79 | /* Some features automatically imply others: */ | ||
80 | if (arm_feature(env, ARM_FEATURE_V8)) { | ||
81 | if (arm_feature(env, ARM_FEATURE_M)) { | ||
82 | -- | ||
83 | 2.20.1 | ||
84 | |||
85 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Create "vfp" and "dsp" properties on the armv7m container object | ||
2 | which will be forwarded to its CPU object, so that SoCs can | ||
3 | configure whether the CPU has these features. | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
7 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
8 | Message-id: 20190517174046.11146-4-peter.maydell@linaro.org | ||
9 | --- | ||
10 | include/hw/arm/armv7m.h | 4 ++++ | ||
11 | hw/arm/armv7m.c | 18 ++++++++++++++++++ | ||
12 | 2 files changed, 22 insertions(+) | ||
13 | |||
14 | diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/include/hw/arm/armv7m.h | ||
17 | +++ b/include/hw/arm/armv7m.h | ||
18 | @@ -XXX,XX +XXX,XX @@ typedef struct { | ||
19 | * devices will be automatically layered on top of this view.) | ||
20 | * + Property "idau": IDAU interface (forwarded to CPU object) | ||
21 | * + Property "init-svtor": secure VTOR reset value (forwarded to CPU object) | ||
22 | + * + Property "vfp": enable VFP (forwarded to CPU object) | ||
23 | + * + Property "dsp": enable DSP (forwarded to CPU object) | ||
24 | * + Property "enable-bitband": expose bitbanded IO | ||
25 | */ | ||
26 | typedef struct ARMv7MState { | ||
27 | @@ -XXX,XX +XXX,XX @@ typedef struct ARMv7MState { | ||
28 | uint32_t init_svtor; | ||
29 | bool enable_bitband; | ||
30 | bool start_powered_off; | ||
31 | + bool vfp; | ||
32 | + bool dsp; | ||
33 | } ARMv7MState; | ||
34 | |||
35 | #endif | ||
36 | diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/hw/arm/armv7m.c | ||
39 | +++ b/hw/arm/armv7m.c | ||
40 | @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) | ||
41 | return; | ||
42 | } | ||
43 | } | ||
44 | + if (object_property_find(OBJECT(s->cpu), "vfp", NULL)) { | ||
45 | + object_property_set_bool(OBJECT(s->cpu), s->vfp, | ||
46 | + "vfp", &err); | ||
47 | + if (err != NULL) { | ||
48 | + error_propagate(errp, err); | ||
49 | + return; | ||
50 | + } | ||
51 | + } | ||
52 | + if (object_property_find(OBJECT(s->cpu), "dsp", NULL)) { | ||
53 | + object_property_set_bool(OBJECT(s->cpu), s->dsp, | ||
54 | + "dsp", &err); | ||
55 | + if (err != NULL) { | ||
56 | + error_propagate(errp, err); | ||
57 | + return; | ||
58 | + } | ||
59 | + } | ||
60 | |||
61 | /* | ||
62 | * Tell the CPU where the NVIC is; it will fail realize if it doesn't | ||
63 | @@ -XXX,XX +XXX,XX @@ static Property armv7m_properties[] = { | ||
64 | DEFINE_PROP_BOOL("enable-bitband", ARMv7MState, enable_bitband, false), | ||
65 | DEFINE_PROP_BOOL("start-powered-off", ARMv7MState, start_powered_off, | ||
66 | false), | ||
67 | + DEFINE_PROP_BOOL("vfp", ARMv7MState, vfp, true), | ||
68 | + DEFINE_PROP_BOOL("dsp", ARMv7MState, dsp, true), | ||
69 | DEFINE_PROP_END_OF_LIST(), | ||
70 | }; | ||
71 | |||
72 | -- | ||
73 | 2.20.1 | ||
74 | |||
75 | diff view generated by jsdifflib |
1 | The BCM2837 sets the Aff1 field of the MPIDR affinity values for the | 1 | The SSE-200 hardware has configurable integration settings which |
---|---|---|---|
2 | CPUs to 0, whereas the BCM2836 uses 0xf. Set this correctly, as it | 2 | determine whether its two CPUs have the FPU and DSP: |
3 | is required for Linux to boot. | 3 | * CPU0_FPU (default 0) |
4 | * CPU0_DSP (default 0) | ||
5 | * CPU1_FPU (default 1) | ||
6 | * CPU1_DSP (default 1) | ||
7 | |||
8 | Similarly, the IoTKit has settings for its single CPU: | ||
9 | * CPU0_FPU (default 1) | ||
10 | * CPU0_DSP (default 1) | ||
11 | |||
12 | Of our four boards that use either the IoTKit or the SSE-200: | ||
13 | * mps2-an505, mps2-an521 and musca-a use the default settings | ||
14 | * musca-b1 enables FPU and DSP on both CPUs | ||
15 | |||
16 | Currently QEMU models all these boards using CPUs with | ||
17 | both FPU and DSP enabled. This means that we are incorrect | ||
18 | for mps2-an521 and musca-a, which should not have FPU or DSP | ||
19 | on CPU0. | ||
20 | |||
21 | Create QOM properties on the ARMSSE devices corresponding to the | ||
22 | default h/w integration settings, and make the Musca-B1 board | ||
23 | enable FPU and DSP on both CPUs. This fixes the mps2-an521 | ||
24 | and musca-a behaviour, and leaves the musca-b1 and mps2-an505 | ||
25 | behaviour unchanged. | ||
4 | 26 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 27 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
6 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 28 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> |
7 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 29 | Message-id: 20190517174046.11146-5-peter.maydell@linaro.org |
8 | Message-id: 20180313153458.26822-8-peter.maydell@linaro.org | ||
9 | --- | 30 | --- |
10 | hw/arm/bcm2836.c | 11 +++++++---- | 31 | include/hw/arm/armsse.h | 7 +++++ |
11 | 1 file changed, 7 insertions(+), 4 deletions(-) | 32 | hw/arm/armsse.c | 58 ++++++++++++++++++++++++++++++++--------- |
33 | hw/arm/musca.c | 8 ++++++ | ||
34 | 3 files changed, 61 insertions(+), 12 deletions(-) | ||
12 | 35 | ||
13 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 36 | diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h |
14 | index XXXXXXX..XXXXXXX 100644 | 37 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/hw/arm/bcm2836.c | 38 | --- a/include/hw/arm/armsse.h |
16 | +++ b/hw/arm/bcm2836.c | 39 | +++ b/include/hw/arm/armsse.h |
17 | @@ -XXX,XX +XXX,XX @@ | 40 | @@ -XXX,XX +XXX,XX @@ |
18 | 41 | * address of each SRAM bank (and thus the total amount of internal SRAM) | |
19 | struct BCM283XInfo { | 42 | * + QOM property "init-svtor" sets the initial value of the CPU SVTOR register |
20 | const char *name; | 43 | * (where it expects to load the PC and SP from the vector table on reset) |
21 | + int clusterid; | 44 | + * + QOM properties "CPU0_FPU", "CPU0_DSP", "CPU1_FPU" and "CPU1_DSP" which |
45 | + * set whether the CPUs have the FPU and DSP features present. The default | ||
46 | + * (matching the hardware) is that for CPU0 in an IoTKit and CPU1 in an | ||
47 | + * SSE-200 both are present; CPU0 in an SSE-200 has neither. | ||
48 | + * Since the IoTKit has only one CPU, it does not have the CPU1_* properties. | ||
49 | * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts for CPU 0, | ||
50 | * which are wired to its NVIC lines 32 .. n+32 | ||
51 | * + Named GPIO inputs "EXP_CPU1_IRQ" 0..n are the expansion interrupts for | ||
52 | @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { | ||
53 | uint32_t mainclk_frq; | ||
54 | uint32_t sram_addr_width; | ||
55 | uint32_t init_svtor; | ||
56 | + bool cpu_fpu[SSE_MAX_CPUS]; | ||
57 | + bool cpu_dsp[SSE_MAX_CPUS]; | ||
58 | } ARMSSE; | ||
59 | |||
60 | typedef struct ARMSSEInfo ARMSSEInfo; | ||
61 | diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c | ||
62 | index XXXXXXX..XXXXXXX 100644 | ||
63 | --- a/hw/arm/armsse.c | ||
64 | +++ b/hw/arm/armsse.c | ||
65 | @@ -XXX,XX +XXX,XX @@ struct ARMSSEInfo { | ||
66 | bool has_cachectrl; | ||
67 | bool has_cpusecctrl; | ||
68 | bool has_cpuid; | ||
69 | + Property *props; | ||
70 | +}; | ||
71 | + | ||
72 | +static Property iotkit_properties[] = { | ||
73 | + DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, | ||
74 | + MemoryRegion *), | ||
75 | + DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), | ||
76 | + DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), | ||
77 | + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), | ||
78 | + DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), | ||
79 | + DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], true), | ||
80 | + DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], true), | ||
81 | + DEFINE_PROP_END_OF_LIST() | ||
82 | +}; | ||
83 | + | ||
84 | +static Property armsse_properties[] = { | ||
85 | + DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, | ||
86 | + MemoryRegion *), | ||
87 | + DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), | ||
88 | + DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), | ||
89 | + DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), | ||
90 | + DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), | ||
91 | + DEFINE_PROP_BOOL("CPU0_FPU", ARMSSE, cpu_fpu[0], false), | ||
92 | + DEFINE_PROP_BOOL("CPU0_DSP", ARMSSE, cpu_dsp[0], false), | ||
93 | + DEFINE_PROP_BOOL("CPU1_FPU", ARMSSE, cpu_fpu[1], true), | ||
94 | + DEFINE_PROP_BOOL("CPU1_DSP", ARMSSE, cpu_dsp[1], true), | ||
95 | + DEFINE_PROP_END_OF_LIST() | ||
22 | }; | 96 | }; |
23 | 97 | ||
24 | static const BCM283XInfo bcm283x_socs[] = { | 98 | static const ARMSSEInfo armsse_variants[] = { |
25 | { | 99 | @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { |
26 | .name = TYPE_BCM2836, | 100 | .has_cachectrl = false, |
27 | + .clusterid = 0xf, | 101 | .has_cpusecctrl = false, |
102 | .has_cpuid = false, | ||
103 | + .props = iotkit_properties, | ||
28 | }, | 104 | }, |
29 | { | 105 | { |
30 | .name = TYPE_BCM2837, | 106 | .name = TYPE_SSE200, |
31 | + .clusterid = 0x0, | 107 | @@ -XXX,XX +XXX,XX @@ static const ARMSSEInfo armsse_variants[] = { |
108 | .has_cachectrl = true, | ||
109 | .has_cpusecctrl = true, | ||
110 | .has_cpuid = true, | ||
111 | + .props = armsse_properties, | ||
32 | }, | 112 | }, |
33 | }; | 113 | }; |
34 | 114 | ||
35 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_init(Object *obj) | 115 | @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) |
36 | static void bcm2836_realize(DeviceState *dev, Error **errp) | 116 | return; |
117 | } | ||
118 | } | ||
119 | + if (!s->cpu_fpu[i]) { | ||
120 | + object_property_set_bool(cpuobj, false, "vfp", &err); | ||
121 | + if (err) { | ||
122 | + error_propagate(errp, err); | ||
123 | + return; | ||
124 | + } | ||
125 | + } | ||
126 | + if (!s->cpu_dsp[i]) { | ||
127 | + object_property_set_bool(cpuobj, false, "dsp", &err); | ||
128 | + if (err) { | ||
129 | + error_propagate(errp, err); | ||
130 | + return; | ||
131 | + } | ||
132 | + } | ||
133 | |||
134 | if (i > 0) { | ||
135 | memory_region_add_subregion_overlap(&s->cpu_container[i], 0, | ||
136 | @@ -XXX,XX +XXX,XX @@ static const VMStateDescription armsse_vmstate = { | ||
137 | } | ||
138 | }; | ||
139 | |||
140 | -static Property armsse_properties[] = { | ||
141 | - DEFINE_PROP_LINK("memory", ARMSSE, board_memory, TYPE_MEMORY_REGION, | ||
142 | - MemoryRegion *), | ||
143 | - DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), | ||
144 | - DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), | ||
145 | - DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), | ||
146 | - DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), | ||
147 | - DEFINE_PROP_END_OF_LIST() | ||
148 | -}; | ||
149 | - | ||
150 | static void armsse_reset(DeviceState *dev) | ||
37 | { | 151 | { |
38 | BCM283XState *s = BCM283X(dev); | 152 | ARMSSE *s = ARMSSE(dev); |
39 | + BCM283XClass *bc = BCM283X_GET_CLASS(dev); | 153 | @@ -XXX,XX +XXX,XX @@ static void armsse_class_init(ObjectClass *klass, void *data) |
40 | + const BCM283XInfo *info = bc->info; | 154 | DeviceClass *dc = DEVICE_CLASS(klass); |
41 | Object *obj; | 155 | IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(klass); |
42 | Error *err = NULL; | 156 | ARMSSEClass *asc = ARMSSE_CLASS(klass); |
43 | int n; | 157 | + const ARMSSEInfo *info = data; |
44 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_realize(DeviceState *dev, Error **errp) | 158 | |
45 | qdev_get_gpio_in_named(DEVICE(&s->control), "gpu-fiq", 0)); | 159 | dc->realize = armsse_realize; |
46 | 160 | dc->vmsd = &armsse_vmstate; | |
47 | for (n = 0; n < BCM283X_NCPUS; n++) { | 161 | - dc->props = armsse_properties; |
48 | - /* Mirror bcm2836, which has clusterid set to 0xf | 162 | + dc->props = info->props; |
49 | - * TODO: this should be converted to a property of ARM_CPU | 163 | dc->reset = armsse_reset; |
50 | - */ | 164 | iic->check = armsse_idau_check; |
51 | - s->cpus[n].mp_affinity = 0xF00 | n; | 165 | - asc->info = data; |
52 | + /* TODO: this should be converted to a property of ARM_CPU */ | 166 | + asc->info = info; |
53 | + s->cpus[n].mp_affinity = (info->clusterid << 8) | n; | 167 | } |
54 | 168 | ||
55 | /* set periphbase/CBAR value for CPU-local registers */ | 169 | static const TypeInfo armsse_info = { |
56 | object_property_set_int(OBJECT(&s->cpus[n]), | 170 | diff --git a/hw/arm/musca.c b/hw/arm/musca.c |
171 | index XXXXXXX..XXXXXXX 100644 | ||
172 | --- a/hw/arm/musca.c | ||
173 | +++ b/hw/arm/musca.c | ||
174 | @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) | ||
175 | qdev_prop_set_uint32(ssedev, "init-svtor", mmc->init_svtor); | ||
176 | qdev_prop_set_uint32(ssedev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); | ||
177 | qdev_prop_set_uint32(ssedev, "MAINCLK", SYSCLK_FRQ); | ||
178 | + /* | ||
179 | + * Musca-A takes the default SSE-200 FPU/DSP settings (ie no for | ||
180 | + * CPU0 and yes for CPU1); Musca-B1 explicitly enables them for CPU0. | ||
181 | + */ | ||
182 | + if (mmc->type == MUSCA_B1) { | ||
183 | + qdev_prop_set_bit(ssedev, "CPU0_FPU", true); | ||
184 | + qdev_prop_set_bit(ssedev, "CPU0_DSP", true); | ||
185 | + } | ||
186 | object_property_set_bool(OBJECT(&mms->sse), true, "realized", | ||
187 | &error_fatal); | ||
188 | |||
57 | -- | 189 | -- |
58 | 2.16.2 | 190 | 2.20.1 |
59 | 191 | ||
60 | 192 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The GIC ID registers cover an area 0x30 bytes in size | ||
2 | (12 registers, 4 bytes each). We were incorrectly decoding | ||
3 | only the first 0x20 bytes. | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
7 | Message-id: 20190524124248.28394-2-peter.maydell@linaro.org | ||
8 | --- | ||
9 | hw/intc/arm_gicv3_dist.c | 4 ++-- | ||
10 | hw/intc/arm_gicv3_redist.c | 4 ++-- | ||
11 | 2 files changed, 4 insertions(+), 4 deletions(-) | ||
12 | |||
13 | diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/hw/intc/arm_gicv3_dist.c | ||
16 | +++ b/hw/intc/arm_gicv3_dist.c | ||
17 | @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, | ||
18 | } | ||
19 | return MEMTX_OK; | ||
20 | } | ||
21 | - case GICD_IDREGS ... GICD_IDREGS + 0x1f: | ||
22 | + case GICD_IDREGS ... GICD_IDREGS + 0x2f: | ||
23 | /* ID registers */ | ||
24 | *data = gicv3_idreg(offset - GICD_IDREGS); | ||
25 | return MEMTX_OK; | ||
26 | @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, | ||
27 | gicd_write_irouter(s, attrs, irq, r); | ||
28 | return MEMTX_OK; | ||
29 | } | ||
30 | - case GICD_IDREGS ... GICD_IDREGS + 0x1f: | ||
31 | + case GICD_IDREGS ... GICD_IDREGS + 0x2f: | ||
32 | case GICD_TYPER: | ||
33 | case GICD_IIDR: | ||
34 | /* RO registers, ignore the write */ | ||
35 | diff --git a/hw/intc/arm_gicv3_redist.c b/hw/intc/arm_gicv3_redist.c | ||
36 | index XXXXXXX..XXXXXXX 100644 | ||
37 | --- a/hw/intc/arm_gicv3_redist.c | ||
38 | +++ b/hw/intc/arm_gicv3_redist.c | ||
39 | @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_readl(GICv3CPUState *cs, hwaddr offset, | ||
40 | } | ||
41 | *data = cs->gicr_nsacr; | ||
42 | return MEMTX_OK; | ||
43 | - case GICR_IDREGS ... GICR_IDREGS + 0x1f: | ||
44 | + case GICR_IDREGS ... GICR_IDREGS + 0x2f: | ||
45 | *data = gicv3_idreg(offset - GICR_IDREGS); | ||
46 | return MEMTX_OK; | ||
47 | default: | ||
48 | @@ -XXX,XX +XXX,XX @@ static MemTxResult gicr_writel(GICv3CPUState *cs, hwaddr offset, | ||
49 | return MEMTX_OK; | ||
50 | case GICR_IIDR: | ||
51 | case GICR_TYPER: | ||
52 | - case GICR_IDREGS ... GICR_IDREGS + 0x1f: | ||
53 | + case GICR_IDREGS ... GICR_IDREGS + 0x2f: | ||
54 | /* RO registers, ignore the write */ | ||
55 | qemu_log_mask(LOG_GUEST_ERROR, | ||
56 | "%s: invalid guest write to RO register at offset " | ||
57 | -- | ||
58 | 2.20.1 | ||
59 | |||
60 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The GICv3 specification says that the GICD_TYPER.SecurityExtn bit | ||
2 | is RAZ if GICD_CTLR.DS is 1. We were incorrectly making it RAZ | ||
3 | if the security extension is unsupported. "Security extension | ||
4 | unsupported" always implies GICD_CTLR.DS == 1, but the guest can | ||
5 | also set DS on a GIC which does support the security extension. | ||
6 | Fix the condition to correctly check the GICD_CTLR.DS bit. | ||
1 | 7 | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Message-id: 20190524124248.28394-3-peter.maydell@linaro.org | ||
10 | --- | ||
11 | hw/intc/arm_gicv3_dist.c | 8 +++++++- | ||
12 | 1 file changed, 7 insertions(+), 1 deletion(-) | ||
13 | |||
14 | diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/hw/intc/arm_gicv3_dist.c | ||
17 | +++ b/hw/intc/arm_gicv3_dist.c | ||
18 | @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, | ||
19 | * ITLinesNumber == (num external irqs / 32) - 1 | ||
20 | */ | ||
21 | int itlinesnumber = ((s->num_irq - GIC_INTERNAL) / 32) - 1; | ||
22 | + /* | ||
23 | + * SecurityExtn must be RAZ if GICD_CTLR.DS == 1, and | ||
24 | + * "security extensions not supported" always implies DS == 1, | ||
25 | + * so we only need to check the DS bit. | ||
26 | + */ | ||
27 | + bool sec_extn = !(s->gicd_ctlr & GICD_CTLR_DS); | ||
28 | |||
29 | - *data = (1 << 25) | (1 << 24) | (s->security_extn << 10) | | ||
30 | + *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | | ||
31 | (0xf << 19) | itlinesnumber; | ||
32 | return MEMTX_OK; | ||
33 | } | ||
34 | -- | ||
35 | 2.20.1 | ||
36 | |||
37 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | We want to use vfp_expand_imm() in the AArch32 VFP decode; | ||
2 | move it from the a64-only header/source file to the | ||
3 | AArch32 one (which is always compiled even for AArch64). | ||
1 | 4 | ||
5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
7 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
8 | Message-id: 20190613163917.28589-2-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/translate-a64.h | 1 - | ||
11 | target/arm/translate.h | 7 +++++++ | ||
12 | target/arm/translate-a64.c | 32 -------------------------------- | ||
13 | target/arm/translate-vfp.inc.c | 33 +++++++++++++++++++++++++++++++++ | ||
14 | 4 files changed, 40 insertions(+), 33 deletions(-) | ||
15 | |||
16 | diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/target/arm/translate-a64.h | ||
19 | +++ b/target/arm/translate-a64.h | ||
20 | @@ -XXX,XX +XXX,XX @@ void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v); | ||
21 | TCGv_ptr get_fpstatus_ptr(bool); | ||
22 | bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, | ||
23 | unsigned int imms, unsigned int immr); | ||
24 | -uint64_t vfp_expand_imm(int size, uint8_t imm8); | ||
25 | bool sve_access_check(DisasContext *s); | ||
26 | |||
27 | /* We should have at some point before trying to access an FP register | ||
28 | diff --git a/target/arm/translate.h b/target/arm/translate.h | ||
29 | index XXXXXXX..XXXXXXX 100644 | ||
30 | --- a/target/arm/translate.h | ||
31 | +++ b/target/arm/translate.h | ||
32 | @@ -XXX,XX +XXX,XX @@ static inline void gen_ss_advance(DisasContext *s) | ||
33 | } | ||
34 | } | ||
35 | |||
36 | +/* | ||
37 | + * Given a VFP floating point constant encoded into an 8 bit immediate in an | ||
38 | + * instruction, expand it to the actual constant value of the specified | ||
39 | + * size, as per the VFPExpandImm() pseudocode in the Arm ARM. | ||
40 | + */ | ||
41 | +uint64_t vfp_expand_imm(int size, uint8_t imm8); | ||
42 | + | ||
43 | /* Vector operations shared between ARM and AArch64. */ | ||
44 | extern const GVecGen3 mla_op[4]; | ||
45 | extern const GVecGen3 mls_op[4]; | ||
46 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
47 | index XXXXXXX..XXXXXXX 100644 | ||
48 | --- a/target/arm/translate-a64.c | ||
49 | +++ b/target/arm/translate-a64.c | ||
50 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) | ||
51 | } | ||
52 | } | ||
53 | |||
54 | -/* The imm8 encodes the sign bit, enough bits to represent an exponent in | ||
55 | - * the range 01....1xx to 10....0xx, and the most significant 4 bits of | ||
56 | - * the mantissa; see VFPExpandImm() in the v8 ARM ARM. | ||
57 | - */ | ||
58 | -uint64_t vfp_expand_imm(int size, uint8_t imm8) | ||
59 | -{ | ||
60 | - uint64_t imm; | ||
61 | - | ||
62 | - switch (size) { | ||
63 | - case MO_64: | ||
64 | - imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
65 | - (extract32(imm8, 6, 1) ? 0x3fc0 : 0x4000) | | ||
66 | - extract32(imm8, 0, 6); | ||
67 | - imm <<= 48; | ||
68 | - break; | ||
69 | - case MO_32: | ||
70 | - imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
71 | - (extract32(imm8, 6, 1) ? 0x3e00 : 0x4000) | | ||
72 | - (extract32(imm8, 0, 6) << 3); | ||
73 | - imm <<= 16; | ||
74 | - break; | ||
75 | - case MO_16: | ||
76 | - imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
77 | - (extract32(imm8, 6, 1) ? 0x3000 : 0x4000) | | ||
78 | - (extract32(imm8, 0, 6) << 6); | ||
79 | - break; | ||
80 | - default: | ||
81 | - g_assert_not_reached(); | ||
82 | - } | ||
83 | - return imm; | ||
84 | -} | ||
85 | - | ||
86 | /* Floating point immediate | ||
87 | * 31 30 29 28 24 23 22 21 20 13 12 10 9 5 4 0 | ||
88 | * +---+---+---+-----------+------+---+------------+-------+------+------+ | ||
89 | diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c | ||
90 | index XXXXXXX..XXXXXXX 100644 | ||
91 | --- a/target/arm/translate-vfp.inc.c | ||
92 | +++ b/target/arm/translate-vfp.inc.c | ||
93 | @@ -XXX,XX +XXX,XX @@ | ||
94 | #include "decode-vfp.inc.c" | ||
95 | #include "decode-vfp-uncond.inc.c" | ||
96 | |||
97 | +/* | ||
98 | + * The imm8 encodes the sign bit, enough bits to represent an exponent in | ||
99 | + * the range 01....1xx to 10....0xx, and the most significant 4 bits of | ||
100 | + * the mantissa; see VFPExpandImm() in the v8 ARM ARM. | ||
101 | + */ | ||
102 | +uint64_t vfp_expand_imm(int size, uint8_t imm8) | ||
103 | +{ | ||
104 | + uint64_t imm; | ||
105 | + | ||
106 | + switch (size) { | ||
107 | + case MO_64: | ||
108 | + imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
109 | + (extract32(imm8, 6, 1) ? 0x3fc0 : 0x4000) | | ||
110 | + extract32(imm8, 0, 6); | ||
111 | + imm <<= 48; | ||
112 | + break; | ||
113 | + case MO_32: | ||
114 | + imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
115 | + (extract32(imm8, 6, 1) ? 0x3e00 : 0x4000) | | ||
116 | + (extract32(imm8, 0, 6) << 3); | ||
117 | + imm <<= 16; | ||
118 | + break; | ||
119 | + case MO_16: | ||
120 | + imm = (extract32(imm8, 7, 1) ? 0x8000 : 0) | | ||
121 | + (extract32(imm8, 6, 1) ? 0x3000 : 0x4000) | | ||
122 | + (extract32(imm8, 0, 6) << 6); | ||
123 | + break; | ||
124 | + default: | ||
125 | + g_assert_not_reached(); | ||
126 | + } | ||
127 | + return imm; | ||
128 | +} | ||
129 | + | ||
130 | /* | ||
131 | * Return the offset of a 16-bit half of the specified VFP single-precision | ||
132 | * register. If top is true, returns the top 16 bits; otherwise the bottom | ||
133 | -- | ||
134 | 2.20.1 | ||
135 | |||
136 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | The AArch32 VMOV (immediate) instruction uses the same VFP encoded | ||
2 | immediate format we already handle in vfp_expand_imm(). Use that | ||
3 | function rather than hand-decoding it. | ||
1 | 4 | ||
5 | Suggested-by: Richard Henderson <richard.henderson@linaro.org> | ||
6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
9 | Message-id: 20190613163917.28589-3-peter.maydell@linaro.org | ||
10 | --- | ||
11 | target/arm/translate-vfp.inc.c | 28 ++++------------------------ | ||
12 | target/arm/vfp.decode | 10 ++++++---- | ||
13 | 2 files changed, 10 insertions(+), 28 deletions(-) | ||
14 | |||
15 | diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/translate-vfp.inc.c | ||
18 | +++ b/target/arm/translate-vfp.inc.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) | ||
20 | uint32_t delta_d = 0; | ||
21 | int veclen = s->vec_len; | ||
22 | TCGv_i32 fd; | ||
23 | - uint32_t n, i, vd; | ||
24 | + uint32_t vd; | ||
25 | |||
26 | vd = a->vd; | ||
27 | |||
28 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) | ||
29 | } | ||
30 | } | ||
31 | |||
32 | - n = (a->imm4h << 28) & 0x80000000; | ||
33 | - i = ((a->imm4h << 4) & 0x70) | a->imm4l; | ||
34 | - if (i & 0x40) { | ||
35 | - i |= 0x780; | ||
36 | - } else { | ||
37 | - i |= 0x800; | ||
38 | - } | ||
39 | - n |= i << 19; | ||
40 | - | ||
41 | - fd = tcg_temp_new_i32(); | ||
42 | - tcg_gen_movi_i32(fd, n); | ||
43 | + fd = tcg_const_i32(vfp_expand_imm(MO_32, a->imm)); | ||
44 | |||
45 | for (;;) { | ||
46 | neon_store_reg32(fd, vd); | ||
47 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) | ||
48 | uint32_t delta_d = 0; | ||
49 | int veclen = s->vec_len; | ||
50 | TCGv_i64 fd; | ||
51 | - uint32_t n, i, vd; | ||
52 | + uint32_t vd; | ||
53 | |||
54 | vd = a->vd; | ||
55 | |||
56 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) | ||
57 | } | ||
58 | } | ||
59 | |||
60 | - n = (a->imm4h << 28) & 0x80000000; | ||
61 | - i = ((a->imm4h << 4) & 0x70) | a->imm4l; | ||
62 | - if (i & 0x40) { | ||
63 | - i |= 0x3f80; | ||
64 | - } else { | ||
65 | - i |= 0x4000; | ||
66 | - } | ||
67 | - n |= i << 16; | ||
68 | - | ||
69 | - fd = tcg_temp_new_i64(); | ||
70 | - tcg_gen_movi_i64(fd, ((uint64_t)n) << 32); | ||
71 | + fd = tcg_const_i64(vfp_expand_imm(MO_64, a->imm)); | ||
72 | |||
73 | for (;;) { | ||
74 | neon_store_reg64(fd, vd); | ||
75 | diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode | ||
76 | index XXXXXXX..XXXXXXX 100644 | ||
77 | --- a/target/arm/vfp.decode | ||
78 | +++ b/target/arm/vfp.decode | ||
79 | @@ -XXX,XX +XXX,XX @@ | ||
80 | %vmov_idx_b 21:1 5:2 | ||
81 | %vmov_idx_h 21:1 6:1 | ||
82 | |||
83 | +%vmov_imm 16:4 0:4 | ||
84 | + | ||
85 | # VMOV scalar to general-purpose register; note that this does | ||
86 | # include some Neon cases. | ||
87 | VMOV_to_gp ---- 1110 u:1 1. 1 .... rt:4 1011 ... 1 0000 \ | ||
88 | @@ -XXX,XX +XXX,XX @@ VFM_sp ---- 1110 1.10 .... .... 1010 . o2:1 . 0 .... \ | ||
89 | VFM_dp ---- 1110 1.10 .... .... 1011 . o2:1 . 0 .... \ | ||
90 | vm=%vm_dp vn=%vn_dp vd=%vd_dp o1=2 | ||
91 | |||
92 | -VMOV_imm_sp ---- 1110 1.11 imm4h:4 .... 1010 0000 imm4l:4 \ | ||
93 | - vd=%vd_sp | ||
94 | -VMOV_imm_dp ---- 1110 1.11 imm4h:4 .... 1011 0000 imm4l:4 \ | ||
95 | - vd=%vd_dp | ||
96 | +VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \ | ||
97 | + vd=%vd_sp imm=%vmov_imm | ||
98 | +VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ | ||
99 | + vd=%vd_dp imm=%vmov_imm | ||
100 | |||
101 | VMOV_reg_sp ---- 1110 1.11 0000 .... 1010 01.0 .... \ | ||
102 | vd=%vd_sp vm=%vm_sp | ||
103 | -- | ||
104 | 2.20.1 | ||
105 | |||
106 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | Where Neon instructions are floating point operations, we | ||
2 | mostly use the old VFP utility functions like gen_vfp_abs() | ||
3 | which work on the TCG globals cpu_F0s and cpu_F1s. The | ||
4 | Neon for-each-element loop conditionally loads the inputs | ||
5 | into either a plain old TCG temporary for most operations | ||
6 | or into cpu_F0s for float operations, and similarly stores | ||
7 | back either cpu_F0s or the temporary. | ||
1 | 8 | ||
9 | Switch NEON_2RM_VABS_F away from using cpu_F0s, and | ||
10 | update neon_2rm_is_float_op() accordingly. | ||
11 | |||
12 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
14 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
15 | Message-id: 20190613163917.28589-4-peter.maydell@linaro.org | ||
16 | --- | ||
17 | target/arm/translate.c | 19 ++++++++----------- | ||
18 | 1 file changed, 8 insertions(+), 11 deletions(-) | ||
19 | |||
20 | diff --git a/target/arm/translate.c b/target/arm/translate.c | ||
21 | index XXXXXXX..XXXXXXX 100644 | ||
22 | --- a/target/arm/translate.c | ||
23 | +++ b/target/arm/translate.c | ||
24 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_fpstatus_ptr(int neon) | ||
25 | return statusptr; | ||
26 | } | ||
27 | |||
28 | -static inline void gen_vfp_abs(int dp) | ||
29 | -{ | ||
30 | - if (dp) | ||
31 | - gen_helper_vfp_absd(cpu_F0d, cpu_F0d); | ||
32 | - else | ||
33 | - gen_helper_vfp_abss(cpu_F0s, cpu_F0s); | ||
34 | -} | ||
35 | - | ||
36 | static inline void gen_vfp_neg(int dp) | ||
37 | { | ||
38 | if (dp) | ||
39 | @@ -XXX,XX +XXX,XX @@ static const uint8_t neon_3r_sizes[] = { | ||
40 | |||
41 | static int neon_2rm_is_float_op(int op) | ||
42 | { | ||
43 | - /* Return true if this neon 2reg-misc op is float-to-float */ | ||
44 | - return (op == NEON_2RM_VABS_F || op == NEON_2RM_VNEG_F || | ||
45 | + /* | ||
46 | + * Return true if this neon 2reg-misc op is float-to-float. | ||
47 | + * This is not a property of the operation but of our code -- | ||
48 | + * what we are asking here is "does the code for this case in | ||
49 | + * the Neon for-each-pass loop use cpu_F0s?". | ||
50 | + */ | ||
51 | + return (op == NEON_2RM_VNEG_F || | ||
52 | (op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) || | ||
53 | op == NEON_2RM_VRINTM || | ||
54 | (op >= NEON_2RM_VRINTP && op <= NEON_2RM_VCVTMS) || | ||
55 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
56 | break; | ||
57 | } | ||
58 | case NEON_2RM_VABS_F: | ||
59 | - gen_vfp_abs(0); | ||
60 | + gen_helper_vfp_abss(tmp, tmp); | ||
61 | break; | ||
62 | case NEON_2RM_VNEG_F: | ||
63 | gen_vfp_neg(0); | ||
64 | -- | ||
65 | 2.20.1 | ||
66 | |||
67 | diff view generated by jsdifflib |
1 | The TypeInfo and state struct for bcm2386 disagree about what the | 1 | Switch NEON_2RM_VABS_F away from using cpu_F0s. |
---|---|---|---|
2 | parent class is -- the TypeInfo says it's TYPE_SYS_BUS_DEVICE, | ||
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 | 2 | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 5 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
13 | Message-id: 20180313153458.26822-5-peter.maydell@linaro.org | 6 | Message-id: 20190613163917.28589-5-peter.maydell@linaro.org |
14 | --- | 7 | --- |
15 | hw/arm/bcm2836.c | 2 +- | 8 | target/arm/translate.c | 13 ++----------- |
16 | 1 file changed, 1 insertion(+), 1 deletion(-) | 9 | 1 file changed, 2 insertions(+), 11 deletions(-) |
17 | 10 | ||
18 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 11 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
19 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/hw/arm/bcm2836.c | 13 | --- a/target/arm/translate.c |
21 | +++ b/hw/arm/bcm2836.c | 14 | +++ b/target/arm/translate.c |
22 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_class_init(ObjectClass *oc, void *data) | 15 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_fpstatus_ptr(int neon) |
23 | 16 | return statusptr; | |
24 | static const TypeInfo bcm2836_type_info = { | 17 | } |
25 | .name = TYPE_BCM2836, | 18 | |
26 | - .parent = TYPE_SYS_BUS_DEVICE, | 19 | -static inline void gen_vfp_neg(int dp) |
27 | + .parent = TYPE_DEVICE, | 20 | -{ |
28 | .instance_size = sizeof(BCM2836State), | 21 | - if (dp) |
29 | .instance_init = bcm2836_init, | 22 | - gen_helper_vfp_negd(cpu_F0d, cpu_F0d); |
30 | .class_init = bcm2836_class_init, | 23 | - else |
24 | - gen_helper_vfp_negs(cpu_F0s, cpu_F0s); | ||
25 | -} | ||
26 | - | ||
27 | #define VFP_GEN_ITOF(name) \ | ||
28 | static inline void gen_vfp_##name(int dp, int neon) \ | ||
29 | { \ | ||
30 | @@ -XXX,XX +XXX,XX @@ static int neon_2rm_is_float_op(int op) | ||
31 | * what we are asking here is "does the code for this case in | ||
32 | * the Neon for-each-pass loop use cpu_F0s?". | ||
33 | */ | ||
34 | - return (op == NEON_2RM_VNEG_F || | ||
35 | - (op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) || | ||
36 | + return ((op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) || | ||
37 | op == NEON_2RM_VRINTM || | ||
38 | (op >= NEON_2RM_VRINTP && op <= NEON_2RM_VCVTMS) || | ||
39 | op >= NEON_2RM_VRECPE_F); | ||
40 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
41 | gen_helper_vfp_abss(tmp, tmp); | ||
42 | break; | ||
43 | case NEON_2RM_VNEG_F: | ||
44 | - gen_vfp_neg(0); | ||
45 | + gen_helper_vfp_negs(tmp, tmp); | ||
46 | break; | ||
47 | case NEON_2RM_VSWP: | ||
48 | tmp2 = neon_load_reg(rd, pass); | ||
31 | -- | 49 | -- |
32 | 2.16.2 | 50 | 2.20.1 |
33 | 51 | ||
34 | 52 | diff view generated by jsdifflib |
1 | The raspi3 has AArch64 CPUs, which means that our smpboot | 1 | Switch NEON_2RM_VRINT* away from using cpu_F0s. |
---|---|---|---|
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 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
8 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
9 | Message-id: 20180313153458.26822-10-peter.maydell@linaro.org | 5 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
6 | Message-id: 20190613163917.28589-6-peter.maydell@linaro.org | ||
10 | --- | 7 | --- |
11 | hw/arm/raspi.c | 41 ++++++++++++++++++++++++++++++++++++++++- | 8 | target/arm/translate.c | 8 +++----- |
12 | 1 file changed, 40 insertions(+), 1 deletion(-) | 9 | 1 file changed, 3 insertions(+), 5 deletions(-) |
13 | 10 | ||
14 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 11 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
15 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
16 | --- a/hw/arm/raspi.c | 13 | --- a/target/arm/translate.c |
17 | +++ b/hw/arm/raspi.c | 14 | +++ b/target/arm/translate.c |
18 | @@ -XXX,XX +XXX,XX @@ | 15 | @@ -XXX,XX +XXX,XX @@ static int neon_2rm_is_float_op(int op) |
19 | #define BOARDSETUP_ADDR (MVBAR_ADDR + 0x20) /* board setup code */ | 16 | * what we are asking here is "does the code for this case in |
20 | #define FIRMWARE_ADDR_2 0x8000 /* Pi 2 loads kernel.img here by default */ | 17 | * the Neon for-each-pass loop use cpu_F0s?". |
21 | #define FIRMWARE_ADDR_3 0x80000 /* Pi 3 loads kernel.img here by default */ | 18 | */ |
22 | +#define SPINTABLE_ADDR 0xd8 /* Pi 3 bootloader spintable */ | 19 | - return ((op >= NEON_2RM_VRINTN && op <= NEON_2RM_VRINTZ) || |
23 | 20 | - op == NEON_2RM_VRINTM || | |
24 | /* Table of Linux board IDs for different Pi versions */ | 21 | - (op >= NEON_2RM_VRINTP && op <= NEON_2RM_VCVTMS) || |
25 | static const int raspi_boardid[] = {[1] = 0xc42, [2] = 0xc43, [3] = 0xc44}; | 22 | + return ((op >= NEON_2RM_VCVTAU && op <= NEON_2RM_VCVTMS) || |
26 | @@ -XXX,XX +XXX,XX @@ static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) | 23 | op >= NEON_2RM_VRECPE_F); |
27 | info->smp_loader_start); | ||
28 | } | 24 | } |
29 | 25 | ||
30 | +static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) | 26 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
31 | +{ | 27 | tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); |
32 | + /* Unlike the AArch32 version we don't need to call the board setup hook. | 28 | gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, |
33 | + * The mechanism for doing the spin-table is also entirely different. | 29 | cpu_env); |
34 | + * We must have four 64-bit fields at absolute addresses | 30 | - gen_helper_rints(cpu_F0s, cpu_F0s, fpstatus); |
35 | + * 0xd8, 0xe0, 0xe8, 0xf0 in RAM, which are the flag variables for | 31 | + gen_helper_rints(tmp, tmp, fpstatus); |
36 | + * our CPUs, and which we must ensure are zero initialized before | 32 | gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, |
37 | + * the primary CPU goes into the kernel. We put these variables inside | 33 | cpu_env); |
38 | + * a rom blob, so that the reset for ROM contents zeroes them for us. | 34 | tcg_temp_free_ptr(fpstatus); |
39 | + */ | 35 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
40 | + static const uint32_t smpboot[] = { | 36 | case NEON_2RM_VRINTX: |
41 | + 0xd2801b05, /* mov x5, 0xd8 */ | 37 | { |
42 | + 0xd53800a6, /* mrs x6, mpidr_el1 */ | 38 | TCGv_ptr fpstatus = get_fpstatus_ptr(1); |
43 | + 0x924004c6, /* and x6, x6, #0x3 */ | 39 | - gen_helper_rints_exact(cpu_F0s, cpu_F0s, fpstatus); |
44 | + 0xd503205f, /* spin: wfe */ | 40 | + gen_helper_rints_exact(tmp, tmp, fpstatus); |
45 | + 0xf86678a4, /* ldr x4, [x5,x6,lsl #3] */ | 41 | tcg_temp_free_ptr(fpstatus); |
46 | + 0xb4ffffc4, /* cbz x4, spin */ | 42 | break; |
47 | + 0xd2800000, /* mov x0, #0x0 */ | 43 | } |
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 | +} | ||
63 | + | ||
64 | static void write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) | ||
65 | { | ||
66 | arm_write_secure_board_setup_dummy_smc(cpu, info, MVBAR_ADDR); | ||
67 | @@ -XXX,XX +XXX,XX @@ static void setup_boot(MachineState *machine, int version, size_t ram_size) | ||
68 | /* Pi2 and Pi3 requires SMP setup */ | ||
69 | if (version >= 2) { | ||
70 | binfo.smp_loader_start = SMPBOOT_ADDR; | ||
71 | - binfo.write_secondary_boot = write_smpboot; | ||
72 | + if (version == 2) { | ||
73 | + binfo.write_secondary_boot = write_smpboot; | ||
74 | + } else { | ||
75 | + binfo.write_secondary_boot = write_smpboot64; | ||
76 | + } | ||
77 | binfo.secondary_cpu_reset_hook = reset_secondary; | ||
78 | } | ||
79 | |||
80 | -- | 44 | -- |
81 | 2.16.2 | 45 | 2.20.1 |
82 | 46 | ||
83 | 47 | diff view generated by jsdifflib |
1 | The bcm2837 is pretty similar to the bcm2836, but it does have | 1 | Stop using cpu_F0s for the NEON_2RM_VCVT[ANPM][US] ops. |
---|---|---|---|
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 | |||
6 | Rather than trying to have one device with properties that | ||
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 | 2 | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
15 | Message-id: 20180313153458.26822-7-peter.maydell@linaro.org | 5 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
6 | Message-id: 20190613163917.28589-7-peter.maydell@linaro.org | ||
16 | --- | 7 | --- |
17 | include/hw/arm/bcm2836.h | 19 +++++++++++++++++++ | 8 | target/arm/translate.c | 7 +++---- |
18 | hw/arm/bcm2836.c | 37 ++++++++++++++++++++++++++++++++----- | 9 | 1 file changed, 3 insertions(+), 4 deletions(-) |
19 | hw/arm/raspi.c | 3 ++- | ||
20 | 3 files changed, 53 insertions(+), 6 deletions(-) | ||
21 | 10 | ||
22 | diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h | 11 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
23 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
24 | --- a/include/hw/arm/bcm2836.h | 13 | --- a/target/arm/translate.c |
25 | +++ b/include/hw/arm/bcm2836.h | 14 | +++ b/target/arm/translate.c |
26 | @@ -XXX,XX +XXX,XX @@ | 15 | @@ -XXX,XX +XXX,XX @@ static int neon_2rm_is_float_op(int op) |
27 | 16 | * what we are asking here is "does the code for this case in | |
28 | #define BCM283X_NCPUS 4 | 17 | * the Neon for-each-pass loop use cpu_F0s?". |
29 | 18 | */ | |
30 | +/* These type names are for specific SoCs; other than instantiating | 19 | - return ((op >= NEON_2RM_VCVTAU && op <= NEON_2RM_VCVTMS) || |
31 | + * them, code using these devices should always handle them via the | 20 | - op >= NEON_2RM_VRECPE_F); |
32 | + * BCM283x base class, so they have no BCM2836(obj) etc macros. | 21 | + return op >= NEON_2RM_VRECPE_F; |
33 | + */ | ||
34 | +#define TYPE_BCM2836 "bcm2836" | ||
35 | +#define TYPE_BCM2837 "bcm2837" | ||
36 | + | ||
37 | typedef struct BCM283XState { | ||
38 | /*< private >*/ | ||
39 | DeviceState parent_obj; | ||
40 | @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XState { | ||
41 | BCM2835PeripheralState peripherals; | ||
42 | } BCM283XState; | ||
43 | |||
44 | +typedef struct BCM283XInfo BCM283XInfo; | ||
45 | + | ||
46 | +typedef struct BCM283XClass { | ||
47 | + DeviceClass parent_class; | ||
48 | + const BCM283XInfo *info; | ||
49 | +} BCM283XClass; | ||
50 | + | ||
51 | +#define BCM283X_CLASS(klass) \ | ||
52 | + OBJECT_CLASS_CHECK(BCM283XClass, (klass), TYPE_BCM283X) | ||
53 | +#define BCM283X_GET_CLASS(obj) \ | ||
54 | + OBJECT_GET_CLASS(BCM283XClass, (obj), TYPE_BCM283X) | ||
55 | + | ||
56 | #endif /* BCM2836_H */ | ||
57 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | ||
58 | index XXXXXXX..XXXXXXX 100644 | ||
59 | --- a/hw/arm/bcm2836.c | ||
60 | +++ b/hw/arm/bcm2836.c | ||
61 | @@ -XXX,XX +XXX,XX @@ | ||
62 | /* "QA7" (Pi2) interrupt controller and mailboxes etc. */ | ||
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 | } | 22 | } |
96 | 23 | ||
97 | -static const TypeInfo bcm2836_type_info = { | 24 | static bool neon_2rm_is_v8_op(int op) |
98 | +static const TypeInfo bcm283x_type_info = { | 25 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
99 | .name = TYPE_BCM283X, | 26 | cpu_env); |
100 | .parent = TYPE_DEVICE, | 27 | |
101 | .instance_size = sizeof(BCM283XState), | 28 | if (is_signed) { |
102 | .instance_init = bcm2836_init, | 29 | - gen_helper_vfp_tosls(cpu_F0s, cpu_F0s, |
103 | - .class_init = bcm2836_class_init, | 30 | + gen_helper_vfp_tosls(tmp, tmp, |
104 | + .class_size = sizeof(BCM283XClass), | 31 | tcg_shift, fpst); |
105 | + .abstract = true, | 32 | } else { |
106 | }; | 33 | - gen_helper_vfp_touls(cpu_F0s, cpu_F0s, |
107 | 34 | + gen_helper_vfp_touls(tmp, tmp, | |
108 | static void bcm2836_register_types(void) | 35 | tcg_shift, fpst); |
109 | { | 36 | } |
110 | - type_register_static(&bcm2836_type_info); | ||
111 | + int i; | ||
112 | + | ||
113 | + type_register_static(&bcm283x_type_info); | ||
114 | + for (i = 0; i < ARRAY_SIZE(bcm283x_socs); i++) { | ||
115 | + TypeInfo ti = { | ||
116 | + .name = bcm283x_socs[i].name, | ||
117 | + .parent = TYPE_BCM283X, | ||
118 | + .class_init = bcm283x_class_init, | ||
119 | + .class_data = (void *) &bcm283x_socs[i], | ||
120 | + }; | ||
121 | + type_register(&ti); | ||
122 | + } | ||
123 | } | ||
124 | |||
125 | type_init(bcm2836_register_types) | ||
126 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | ||
127 | index XXXXXXX..XXXXXXX 100644 | ||
128 | --- a/hw/arm/raspi.c | ||
129 | +++ b/hw/arm/raspi.c | ||
130 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | ||
131 | BusState *bus; | ||
132 | DeviceState *carddev; | ||
133 | |||
134 | - object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM283X); | ||
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 | 37 | ||
140 | -- | 38 | -- |
141 | 2.16.2 | 39 | 2.20.1 |
142 | 40 | ||
143 | 41 | diff view generated by jsdifflib |
1 | Now we have separate types for BCM2386 and BCM2387, we might as well | 1 | Stop using cpu_F0s for NEON_2RM_VRECPE_F and NEON_2RM_VRSQRTE_F. |
---|---|---|---|
2 | just hard-code the CPU type they use rather than having it passed | ||
3 | through as an object property. This then lets us put the initialization | ||
4 | of the CPU object in init rather than realize. | ||
5 | |||
6 | Note that this change means that it's no longer possible on | ||
7 | the command line to use -cpu to ask for a different kind of | ||
8 | CPU than the SoC supports. This was never a supported thing to | ||
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 | 2 | ||
15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
16 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
17 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 5 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
18 | Message-id: 20180313153458.26822-9-peter.maydell@linaro.org | 6 | Message-id: 20190613163917.28589-8-peter.maydell@linaro.org |
19 | --- | 7 | --- |
20 | hw/arm/bcm2836.c | 24 +++++++++++++++--------- | 8 | target/arm/translate.c | 6 +++--- |
21 | hw/arm/raspi.c | 2 -- | 9 | 1 file changed, 3 insertions(+), 3 deletions(-) |
22 | 2 files changed, 15 insertions(+), 11 deletions(-) | ||
23 | 10 | ||
24 | diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c | 11 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
25 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
26 | --- a/hw/arm/bcm2836.c | 13 | --- a/target/arm/translate.c |
27 | +++ b/hw/arm/bcm2836.c | 14 | +++ b/target/arm/translate.c |
28 | @@ -XXX,XX +XXX,XX @@ | 15 | @@ -XXX,XX +XXX,XX @@ static int neon_2rm_is_float_op(int op) |
29 | 16 | * what we are asking here is "does the code for this case in | |
30 | struct BCM283XInfo { | 17 | * the Neon for-each-pass loop use cpu_F0s?". |
31 | const char *name; | 18 | */ |
32 | + const char *cpu_type; | 19 | - return op >= NEON_2RM_VRECPE_F; |
33 | int clusterid; | 20 | + return op >= NEON_2RM_VCVT_FS; |
34 | }; | ||
35 | |||
36 | static const BCM283XInfo bcm283x_socs[] = { | ||
37 | { | ||
38 | .name = TYPE_BCM2836, | ||
39 | + .cpu_type = ARM_CPU_TYPE_NAME("cortex-a15"), | ||
40 | .clusterid = 0xf, | ||
41 | }, | ||
42 | +#ifdef TARGET_AARCH64 | ||
43 | { | ||
44 | .name = TYPE_BCM2837, | ||
45 | + .cpu_type = ARM_CPU_TYPE_NAME("cortex-a53"), | ||
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 | } | 21 | } |
84 | 22 | ||
85 | static Property bcm2836_props[] = { | 23 | static bool neon_2rm_is_v8_op(int op) |
86 | - DEFINE_PROP_STRING("cpu-type", BCM283XState, cpu_type), | 24 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
87 | DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, | 25 | case NEON_2RM_VRECPE_F: |
88 | BCM283X_NCPUS), | 26 | { |
89 | DEFINE_PROP_END_OF_LIST() | 27 | TCGv_ptr fpstatus = get_fpstatus_ptr(1); |
90 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 28 | - gen_helper_recpe_f32(cpu_F0s, cpu_F0s, fpstatus); |
91 | index XXXXXXX..XXXXXXX 100644 | 29 | + gen_helper_recpe_f32(tmp, tmp, fpstatus); |
92 | --- a/hw/arm/raspi.c | 30 | tcg_temp_free_ptr(fpstatus); |
93 | +++ b/hw/arm/raspi.c | 31 | break; |
94 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | 32 | } |
95 | /* Setup the SOC */ | 33 | case NEON_2RM_VRSQRTE_F: |
96 | object_property_add_const_link(OBJECT(&s->soc), "ram", OBJECT(&s->ram), | 34 | { |
97 | &error_abort); | 35 | TCGv_ptr fpstatus = get_fpstatus_ptr(1); |
98 | - object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type", | 36 | - gen_helper_rsqrte_f32(cpu_F0s, cpu_F0s, fpstatus); |
99 | - &error_abort); | 37 | + gen_helper_rsqrte_f32(tmp, tmp, fpstatus); |
100 | object_property_set_int(OBJECT(&s->soc), smp_cpus, "enabled-cpus", | 38 | tcg_temp_free_ptr(fpstatus); |
101 | &error_abort); | 39 | break; |
102 | int board_rev = version == 3 ? 0xa02082 : 0xa21041; | 40 | } |
103 | -- | 41 | -- |
104 | 2.16.2 | 42 | 2.20.1 |
105 | 43 | ||
106 | 44 | diff view generated by jsdifflib |
1 | For the rpi1 and 2 we want to boot the Linux kernel via some | 1 | Stop using cpu_F0s for the Neon f32/s32 VCVT operations. |
---|---|---|---|
2 | custom setup code that makes sure that the SMC instruction | 2 | Since this is the last user of cpu_F0s in the Neon 2rm-op |
3 | acts as a no-op, because it's used for cache maintenance. | 3 | loop, we can remove the handling code for it too. |
4 | The rpi3 boots AArch64 kernels, which don't need SMC for | ||
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 | 4 | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
10 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 7 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
11 | Message-id: 20180313153458.26822-2-peter.maydell@linaro.org | 8 | Message-id: 20190613163917.28589-9-peter.maydell@linaro.org |
12 | --- | 9 | --- |
13 | hw/arm/raspi.c | 17 +++++++++++++---- | 10 | target/arm/translate.c | 82 ++++++++++++------------------------------ |
14 | 1 file changed, 13 insertions(+), 4 deletions(-) | 11 | 1 file changed, 22 insertions(+), 60 deletions(-) |
15 | 12 | ||
16 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 13 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
17 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
18 | --- a/hw/arm/raspi.c | 15 | --- a/target/arm/translate.c |
19 | +++ b/hw/arm/raspi.c | 16 | +++ b/target/arm/translate.c |
20 | @@ -XXX,XX +XXX,XX @@ static void setup_boot(MachineState *machine, int version, size_t ram_size) | 17 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_fpstatus_ptr(int neon) |
21 | binfo.board_id = raspi_boardid[version]; | 18 | return statusptr; |
22 | binfo.ram_size = ram_size; | 19 | } |
23 | binfo.nb_cpus = smp_cpus; | 20 | |
24 | - binfo.board_setup_addr = BOARDSETUP_ADDR; | 21 | -#define VFP_GEN_ITOF(name) \ |
25 | - binfo.write_board_setup = write_board_setup; | 22 | -static inline void gen_vfp_##name(int dp, int neon) \ |
26 | - binfo.secure_board_setup = true; | 23 | -{ \ |
27 | - binfo.secure_boot = true; | 24 | - TCGv_ptr statusptr = get_fpstatus_ptr(neon); \ |
28 | + | 25 | - if (dp) { \ |
29 | + if (version <= 2) { | 26 | - gen_helper_vfp_##name##d(cpu_F0d, cpu_F0s, statusptr); \ |
30 | + /* The rpi1 and 2 require some custom setup code to run in Secure | 27 | - } else { \ |
31 | + * mode before booting a kernel (to set up the SMC vectors so | 28 | - gen_helper_vfp_##name##s(cpu_F0s, cpu_F0s, statusptr); \ |
32 | + * that we get a no-op SMC; this is used by Linux to call the | 29 | - } \ |
33 | + * firmware for some cache maintenance operations. | 30 | - tcg_temp_free_ptr(statusptr); \ |
34 | + * The rpi3 doesn't need this. | 31 | -} |
35 | + */ | 32 | - |
36 | + binfo.board_setup_addr = BOARDSETUP_ADDR; | 33 | -VFP_GEN_ITOF(uito) |
37 | + binfo.write_board_setup = write_board_setup; | 34 | -VFP_GEN_ITOF(sito) |
38 | + binfo.secure_board_setup = true; | 35 | -#undef VFP_GEN_ITOF |
39 | + binfo.secure_boot = true; | 36 | - |
40 | + } | 37 | -#define VFP_GEN_FTOI(name) \ |
41 | 38 | -static inline void gen_vfp_##name(int dp, int neon) \ | |
42 | /* Pi2 and Pi3 requires SMP setup */ | 39 | -{ \ |
43 | if (version >= 2) { | 40 | - TCGv_ptr statusptr = get_fpstatus_ptr(neon); \ |
41 | - if (dp) { \ | ||
42 | - gen_helper_vfp_##name##d(cpu_F0s, cpu_F0d, statusptr); \ | ||
43 | - } else { \ | ||
44 | - gen_helper_vfp_##name##s(cpu_F0s, cpu_F0s, statusptr); \ | ||
45 | - } \ | ||
46 | - tcg_temp_free_ptr(statusptr); \ | ||
47 | -} | ||
48 | - | ||
49 | -VFP_GEN_FTOI(touiz) | ||
50 | -VFP_GEN_FTOI(tosiz) | ||
51 | -#undef VFP_GEN_FTOI | ||
52 | - | ||
53 | #define VFP_GEN_FIX(name, round) \ | ||
54 | static inline void gen_vfp_##name(int dp, int shift, int neon) \ | ||
55 | { \ | ||
56 | @@ -XXX,XX +XXX,XX @@ static const uint8_t neon_3r_sizes[] = { | ||
57 | #define NEON_2RM_VCVT_SF 62 | ||
58 | #define NEON_2RM_VCVT_UF 63 | ||
59 | |||
60 | -static int neon_2rm_is_float_op(int op) | ||
61 | -{ | ||
62 | - /* | ||
63 | - * Return true if this neon 2reg-misc op is float-to-float. | ||
64 | - * This is not a property of the operation but of our code -- | ||
65 | - * what we are asking here is "does the code for this case in | ||
66 | - * the Neon for-each-pass loop use cpu_F0s?". | ||
67 | - */ | ||
68 | - return op >= NEON_2RM_VCVT_FS; | ||
69 | -} | ||
70 | - | ||
71 | static bool neon_2rm_is_v8_op(int op) | ||
72 | { | ||
73 | /* Return true if this neon 2reg-misc op is ARMv8 and up */ | ||
74 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
75 | default: | ||
76 | elementwise: | ||
77 | for (pass = 0; pass < (q ? 4 : 2); pass++) { | ||
78 | - if (neon_2rm_is_float_op(op)) { | ||
79 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, | ||
80 | - neon_reg_offset(rm, pass)); | ||
81 | - tmp = NULL; | ||
82 | - } else { | ||
83 | - tmp = neon_load_reg(rm, pass); | ||
84 | - } | ||
85 | + tmp = neon_load_reg(rm, pass); | ||
86 | switch (op) { | ||
87 | case NEON_2RM_VREV32: | ||
88 | switch (size) { | ||
89 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
90 | break; | ||
91 | } | ||
92 | case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */ | ||
93 | - gen_vfp_sito(0, 1); | ||
94 | + { | ||
95 | + TCGv_ptr fpstatus = get_fpstatus_ptr(1); | ||
96 | + gen_helper_vfp_sitos(tmp, tmp, fpstatus); | ||
97 | + tcg_temp_free_ptr(fpstatus); | ||
98 | break; | ||
99 | + } | ||
100 | case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */ | ||
101 | - gen_vfp_uito(0, 1); | ||
102 | + { | ||
103 | + TCGv_ptr fpstatus = get_fpstatus_ptr(1); | ||
104 | + gen_helper_vfp_uitos(tmp, tmp, fpstatus); | ||
105 | + tcg_temp_free_ptr(fpstatus); | ||
106 | break; | ||
107 | + } | ||
108 | case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */ | ||
109 | - gen_vfp_tosiz(0, 1); | ||
110 | + { | ||
111 | + TCGv_ptr fpstatus = get_fpstatus_ptr(1); | ||
112 | + gen_helper_vfp_tosizs(tmp, tmp, fpstatus); | ||
113 | + tcg_temp_free_ptr(fpstatus); | ||
114 | break; | ||
115 | + } | ||
116 | case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */ | ||
117 | - gen_vfp_touiz(0, 1); | ||
118 | + { | ||
119 | + TCGv_ptr fpstatus = get_fpstatus_ptr(1); | ||
120 | + gen_helper_vfp_touizs(tmp, tmp, fpstatus); | ||
121 | + tcg_temp_free_ptr(fpstatus); | ||
122 | break; | ||
123 | + } | ||
124 | default: | ||
125 | /* Reserved op values were caught by the | ||
126 | * neon_2rm_sizes[] check earlier. | ||
127 | */ | ||
128 | abort(); | ||
129 | } | ||
130 | - if (neon_2rm_is_float_op(op)) { | ||
131 | - tcg_gen_st_f32(cpu_F0s, cpu_env, | ||
132 | - neon_reg_offset(rd, pass)); | ||
133 | - } else { | ||
134 | - neon_store_reg(rd, pass, tmp); | ||
135 | - } | ||
136 | + neon_store_reg(rd, pass, tmp); | ||
137 | } | ||
138 | break; | ||
139 | } | ||
44 | -- | 140 | -- |
45 | 2.16.2 | 141 | 2.20.1 |
46 | 142 | ||
47 | 143 | diff view generated by jsdifflib |
1 | From: Wei Huang <wei@redhat.com> | 1 | Stop using cpu_F0s in the Neon VCVT fixed-point operations. |
---|---|---|---|
2 | 2 | ||
3 | For guest kernel that supports KASLR, the load address can change every | 3 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | time when guest VM runs. To find the physical base address correctly, | 4 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
5 | current QEMU dump searches VMCOREINFO for the string "NUMBER(phys_base)=". | 5 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
6 | However this string pattern is only available on x86_64. AArch64 uses a | 6 | Message-id: 20190613163917.28589-10-peter.maydell@linaro.org |
7 | different field, called "NUMBER(PHYS_OFFSET)=". This patch makes sure | 7 | --- |
8 | QEMU dump uses the correct string on AArch64. | 8 | target/arm/translate.c | 62 +++++++++++++++++++----------------------- |
9 | 1 file changed, 28 insertions(+), 34 deletions(-) | ||
9 | 10 | ||
10 | Signed-off-by: Wei Huang <wei@redhat.com> | 11 | 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 | 12 | index XXXXXXX..XXXXXXX 100644 |
20 | --- a/dump.c | 13 | --- a/target/arm/translate.c |
21 | +++ b/dump.c | 14 | +++ b/target/arm/translate.c |
22 | @@ -XXX,XX +XXX,XX @@ static void vmcoreinfo_update_phys_base(DumpState *s) | 15 | @@ -XXX,XX +XXX,XX @@ static const char * const regnames[] = |
23 | 16 | /* Function prototypes for gen_ functions calling Neon helpers. */ | |
24 | lines = g_strsplit((char *)vmci, "\n", -1); | 17 | typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, |
25 | for (i = 0; lines[i]; i++) { | 18 | TCGv_i32, TCGv_i32); |
26 | - if (g_str_has_prefix(lines[i], "NUMBER(phys_base)=")) { | 19 | +/* Function prototypes for gen_ functions for fix point conversions */ |
27 | - if (qemu_strtou64(lines[i] + 18, NULL, 16, | 20 | +typedef void VFPGenFixPointFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); |
28 | + const char *prefix = NULL; | 21 | |
22 | /* initialize TCG globals. */ | ||
23 | void arm_translate_init(void) | ||
24 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr get_fpstatus_ptr(int neon) | ||
25 | return statusptr; | ||
26 | } | ||
27 | |||
28 | -#define VFP_GEN_FIX(name, round) \ | ||
29 | -static inline void gen_vfp_##name(int dp, int shift, int neon) \ | ||
30 | -{ \ | ||
31 | - TCGv_i32 tmp_shift = tcg_const_i32(shift); \ | ||
32 | - TCGv_ptr statusptr = get_fpstatus_ptr(neon); \ | ||
33 | - if (dp) { \ | ||
34 | - gen_helper_vfp_##name##d##round(cpu_F0d, cpu_F0d, tmp_shift, \ | ||
35 | - statusptr); \ | ||
36 | - } else { \ | ||
37 | - gen_helper_vfp_##name##s##round(cpu_F0s, cpu_F0s, tmp_shift, \ | ||
38 | - statusptr); \ | ||
39 | - } \ | ||
40 | - tcg_temp_free_i32(tmp_shift); \ | ||
41 | - tcg_temp_free_ptr(statusptr); \ | ||
42 | -} | ||
43 | -VFP_GEN_FIX(tosl, _round_to_zero) | ||
44 | -VFP_GEN_FIX(toul, _round_to_zero) | ||
45 | -VFP_GEN_FIX(slto, ) | ||
46 | -VFP_GEN_FIX(ulto, ) | ||
47 | -#undef VFP_GEN_FIX | ||
48 | - | ||
49 | static inline long vfp_reg_offset(bool dp, unsigned reg) | ||
50 | { | ||
51 | if (dp) { | ||
52 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ||
53 | } | ||
54 | } else if (op >= 14) { | ||
55 | /* VCVT fixed-point. */ | ||
56 | + TCGv_ptr fpst; | ||
57 | + TCGv_i32 shiftv; | ||
58 | + VFPGenFixPointFn *fn; | ||
29 | + | 59 | + |
30 | + if (s->dump_info.d_machine == EM_X86_64) { | 60 | if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) { |
31 | + prefix = "NUMBER(phys_base)="; | 61 | return 1; |
32 | + } else if (s->dump_info.d_machine == EM_AARCH64) { | 62 | } |
33 | + prefix = "NUMBER(PHYS_OFFSET)="; | ||
34 | + } | ||
35 | + | 63 | + |
36 | + if (prefix && g_str_has_prefix(lines[i], prefix)) { | 64 | + if (!(op & 1)) { |
37 | + if (qemu_strtou64(lines[i] + strlen(prefix), NULL, 16, | 65 | + if (u) { |
38 | &phys_base) < 0) { | 66 | + fn = gen_helper_vfp_ultos; |
39 | - warn_report("Failed to read NUMBER(phys_base)="); | 67 | + } else { |
40 | + warn_report("Failed to read %s", prefix); | 68 | + fn = gen_helper_vfp_sltos; |
69 | + } | ||
70 | + } else { | ||
71 | + if (u) { | ||
72 | + fn = gen_helper_vfp_touls_round_to_zero; | ||
73 | + } else { | ||
74 | + fn = gen_helper_vfp_tosls_round_to_zero; | ||
75 | + } | ||
76 | + } | ||
77 | + | ||
78 | /* We have already masked out the must-be-1 top bit of imm6, | ||
79 | * hence this 32-shift where the ARM ARM has 64-imm6. | ||
80 | */ | ||
81 | shift = 32 - shift; | ||
82 | + fpst = get_fpstatus_ptr(1); | ||
83 | + shiftv = tcg_const_i32(shift); | ||
84 | for (pass = 0; pass < (q ? 4 : 2); pass++) { | ||
85 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, pass)); | ||
86 | - if (!(op & 1)) { | ||
87 | - if (u) | ||
88 | - gen_vfp_ulto(0, shift, 1); | ||
89 | - else | ||
90 | - gen_vfp_slto(0, shift, 1); | ||
91 | - } else { | ||
92 | - if (u) | ||
93 | - gen_vfp_toul(0, shift, 1); | ||
94 | - else | ||
95 | - gen_vfp_tosl(0, shift, 1); | ||
96 | - } | ||
97 | - tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, pass)); | ||
98 | + TCGv_i32 tmpf = neon_load_reg(rm, pass); | ||
99 | + fn(tmpf, tmpf, shiftv, fpst); | ||
100 | + neon_store_reg(rd, pass, tmpf); | ||
101 | } | ||
102 | + tcg_temp_free_ptr(fpst); | ||
103 | + tcg_temp_free_i32(shiftv); | ||
41 | } else { | 104 | } else { |
42 | s->dump_info.phys_base = phys_base; | 105 | return 1; |
43 | } | 106 | } |
44 | -- | 107 | -- |
45 | 2.16.2 | 108 | 2.20.1 |
46 | 109 | ||
47 | 110 | diff view generated by jsdifflib |
1 | Our BCM2836 type is really a generic one that can be any of | 1 | Remove some old constructs from NEON_2RM_VCVT_F16_F32 code: |
---|---|---|---|
2 | the bcm283x family. Rename it accordingly. We change only | 2 | * don't use cpu_F0s |
3 | the names which are visible via the header file to the | 3 | * don't use tcg_gen_ld_f32 |
4 | rest of the QEMU code, leaving private function names | ||
5 | in bcm2836.c as they are. | ||
6 | |||
7 | This is a preliminary to making bcm283x be an abstract | ||
8 | parent class to specific types for the bcm2836 and bcm2837. | ||
9 | 4 | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | Reviewed-by: Andrew Baumann <Andrew.Baumann@microsoft.com> | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
12 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | 7 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
13 | Message-id: 20180313153458.26822-6-peter.maydell@linaro.org | 8 | Message-id: 20190613163917.28589-11-peter.maydell@linaro.org |
14 | --- | 9 | --- |
15 | include/hw/arm/bcm2836.h | 12 ++++++------ | 10 | target/arm/translate.c | 27 ++++++++++++--------------- |
16 | hw/arm/bcm2836.c | 17 +++++++++-------- | 11 | 1 file changed, 12 insertions(+), 15 deletions(-) |
17 | hw/arm/raspi.c | 16 ++++++++-------- | ||
18 | 3 files changed, 23 insertions(+), 22 deletions(-) | ||
19 | 12 | ||
20 | diff --git a/include/hw/arm/bcm2836.h b/include/hw/arm/bcm2836.h | 13 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
21 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/include/hw/arm/bcm2836.h | 15 | --- a/target/arm/translate.c |
23 | +++ b/include/hw/arm/bcm2836.h | 16 | +++ b/target/arm/translate.c |
24 | @@ -XXX,XX +XXX,XX @@ | 17 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) |
25 | #include "hw/arm/bcm2835_peripherals.h" | 18 | return ret; |
26 | #include "hw/intc/bcm2836_control.h" | ||
27 | |||
28 | -#define TYPE_BCM2836 "bcm2836" | ||
29 | -#define BCM2836(obj) OBJECT_CHECK(BCM2836State, (obj), TYPE_BCM2836) | ||
30 | +#define TYPE_BCM283X "bcm283x" | ||
31 | +#define BCM283X(obj) OBJECT_CHECK(BCM283XState, (obj), TYPE_BCM283X) | ||
32 | |||
33 | -#define BCM2836_NCPUS 4 | ||
34 | +#define BCM283X_NCPUS 4 | ||
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 | ||
55 | --- a/hw/arm/bcm2836.c | ||
56 | +++ b/hw/arm/bcm2836.c | ||
57 | @@ -XXX,XX +XXX,XX @@ | ||
58 | |||
59 | static void bcm2836_init(Object *obj) | ||
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 | } | 19 | } |
95 | 20 | ||
96 | static Property bcm2836_props[] = { | 21 | -#define tcg_gen_ld_f32 tcg_gen_ld_i32 |
97 | - DEFINE_PROP_STRING("cpu-type", BCM2836State, cpu_type), | 22 | #define tcg_gen_st_f32 tcg_gen_st_i32 |
98 | - DEFINE_PROP_UINT32("enabled-cpus", BCM2836State, enabled_cpus, BCM2836_NCPUS), | 23 | |
99 | + DEFINE_PROP_STRING("cpu-type", BCM283XState, cpu_type), | 24 | #define ARM_CP_RW_BIT (1 << 20) |
100 | + DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, | 25 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
101 | + BCM283X_NCPUS), | 26 | q || (rm & 1)) { |
102 | DEFINE_PROP_END_OF_LIST() | 27 | return 1; |
103 | }; | 28 | } |
104 | 29 | - tmp = tcg_temp_new_i32(); | |
105 | @@ -XXX,XX +XXX,XX @@ static void bcm2836_class_init(ObjectClass *oc, void *data) | 30 | - tmp2 = tcg_temp_new_i32(); |
106 | } | 31 | fpst = get_fpstatus_ptr(true); |
107 | 32 | ahp = get_ahp_flag(); | |
108 | static const TypeInfo bcm2836_type_info = { | 33 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 0)); |
109 | - .name = TYPE_BCM2836, | 34 | - gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); |
110 | + .name = TYPE_BCM283X, | 35 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 1)); |
111 | .parent = TYPE_DEVICE, | 36 | - gen_helper_vfp_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); |
112 | - .instance_size = sizeof(BCM2836State), | 37 | + tmp = neon_load_reg(rm, 0); |
113 | + .instance_size = sizeof(BCM283XState), | 38 | + gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); |
114 | .instance_init = bcm2836_init, | 39 | + tmp2 = neon_load_reg(rm, 1); |
115 | .class_init = bcm2836_class_init, | 40 | + gen_helper_vfp_fcvt_f32_to_f16(tmp2, tmp2, fpst, ahp); |
116 | }; | 41 | tcg_gen_shli_i32(tmp2, tmp2, 16); |
117 | diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c | 42 | tcg_gen_or_i32(tmp2, tmp2, tmp); |
118 | index XXXXXXX..XXXXXXX 100644 | 43 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 2)); |
119 | --- a/hw/arm/raspi.c | 44 | - gen_helper_vfp_fcvt_f32_to_f16(tmp, cpu_F0s, fpst, ahp); |
120 | +++ b/hw/arm/raspi.c | 45 | - tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, 3)); |
121 | @@ -XXX,XX +XXX,XX @@ | 46 | + tcg_temp_free_i32(tmp); |
122 | static const int raspi_boardid[] = {[1] = 0xc42, [2] = 0xc43, [3] = 0xc44}; | 47 | + tmp = neon_load_reg(rm, 2); |
123 | 48 | + gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); | |
124 | typedef struct RasPiState { | 49 | + tmp3 = neon_load_reg(rm, 3); |
125 | - BCM2836State soc; | 50 | neon_store_reg(rd, 0, tmp2); |
126 | + BCM283XState soc; | 51 | - tmp2 = tcg_temp_new_i32(); |
127 | MemoryRegion ram; | 52 | - gen_helper_vfp_fcvt_f32_to_f16(tmp2, cpu_F0s, fpst, ahp); |
128 | } RasPiState; | 53 | - tcg_gen_shli_i32(tmp2, tmp2, 16); |
129 | 54 | - tcg_gen_or_i32(tmp2, tmp2, tmp); | |
130 | @@ -XXX,XX +XXX,XX @@ static void raspi_init(MachineState *machine, int version) | 55 | - neon_store_reg(rd, 1, tmp2); |
131 | BusState *bus; | 56 | + gen_helper_vfp_fcvt_f32_to_f16(tmp3, tmp3, fpst, ahp); |
132 | DeviceState *carddev; | 57 | + tcg_gen_shli_i32(tmp3, tmp3, 16); |
133 | 58 | + tcg_gen_or_i32(tmp3, tmp3, tmp); | |
134 | - object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM2836); | 59 | + neon_store_reg(rd, 1, tmp3); |
135 | + object_initialize(&s->soc, sizeof(s->soc), TYPE_BCM283X); | 60 | tcg_temp_free_i32(tmp); |
136 | object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc), | 61 | tcg_temp_free_i32(ahp); |
137 | &error_abort); | 62 | tcg_temp_free_ptr(fpst); |
138 | |||
139 | @@ -XXX,XX +XXX,XX @@ static void raspi2_machine_init(MachineClass *mc) | ||
140 | mc->no_floppy = 1; | ||
141 | mc->no_cdrom = 1; | ||
142 | mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a15"); | ||
143 | - mc->max_cpus = BCM2836_NCPUS; | ||
144 | - mc->min_cpus = BCM2836_NCPUS; | ||
145 | - mc->default_cpus = BCM2836_NCPUS; | ||
146 | + mc->max_cpus = BCM283X_NCPUS; | ||
147 | + mc->min_cpus = BCM283X_NCPUS; | ||
148 | + mc->default_cpus = BCM283X_NCPUS; | ||
149 | mc->default_ram_size = 1024 * 1024 * 1024; | ||
150 | mc->ignore_memory_transaction_failures = true; | ||
151 | }; | ||
152 | @@ -XXX,XX +XXX,XX @@ static void raspi3_machine_init(MachineClass *mc) | ||
153 | mc->no_floppy = 1; | ||
154 | mc->no_cdrom = 1; | ||
155 | mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a53"); | ||
156 | - mc->max_cpus = BCM2836_NCPUS; | ||
157 | - mc->min_cpus = BCM2836_NCPUS; | ||
158 | - mc->default_cpus = BCM2836_NCPUS; | ||
159 | + mc->max_cpus = BCM283X_NCPUS; | ||
160 | + mc->min_cpus = BCM283X_NCPUS; | ||
161 | + mc->default_cpus = BCM283X_NCPUS; | ||
162 | mc->default_ram_size = 1024 * 1024 * 1024; | ||
163 | } | ||
164 | DEFINE_MACHINE("raspi3", raspi3_machine_init) | ||
165 | -- | 63 | -- |
166 | 2.16.2 | 64 | 2.20.1 |
167 | 65 | ||
168 | 66 | diff view generated by jsdifflib |
1 | From: Andrey Smirnov <andrew.smirnov@gmail.com> | 1 | Remove some old constructns from NEON_2RM_VCVT_F16_F32 code: |
---|---|---|---|
2 | * don't use CPU_F0s | ||
3 | * don't use tcg_gen_st_f32 | ||
2 | 4 | ||
3 | Add support for "TX complete"/TXDC interrupt generate by real HW since | 5 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | it is needed to support guests other than Linux. | 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
7 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
8 | Message-id: 20190613163917.28589-12-peter.maydell@linaro.org | ||
9 | --- | ||
10 | target/arm/translate.c | 26 +++++++++++--------------- | ||
11 | 1 file changed, 11 insertions(+), 15 deletions(-) | ||
5 | 12 | ||
6 | Based on the patch by Bill Paul as found here: | 13 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
7 | https://bugs.launchpad.net/qemu/+bug/1753314 | ||
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> | ||
17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
18 | --- | ||
19 | include/hw/char/imx_serial.h | 3 +++ | ||
20 | hw/char/imx_serial.c | 20 +++++++++++++++++--- | ||
21 | 2 files changed, 20 insertions(+), 3 deletions(-) | ||
22 | |||
23 | diff --git a/include/hw/char/imx_serial.h b/include/hw/char/imx_serial.h | ||
24 | index XXXXXXX..XXXXXXX 100644 | 14 | index XXXXXXX..XXXXXXX 100644 |
25 | --- a/include/hw/char/imx_serial.h | 15 | --- a/target/arm/translate.c |
26 | +++ b/include/hw/char/imx_serial.h | 16 | +++ b/target/arm/translate.c |
27 | @@ -XXX,XX +XXX,XX @@ | 17 | @@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg) |
28 | #define UCR2_RXEN (1<<1) /* Receiver enable */ | 18 | return ret; |
29 | #define UCR2_SRST (1<<0) /* Reset complete */ | 19 | } |
30 | 20 | ||
31 | +#define UCR4_TCEN BIT(3) /* TX complete interrupt enable */ | 21 | -#define tcg_gen_st_f32 tcg_gen_st_i32 |
32 | + | 22 | - |
33 | #define UTS1_TXEMPTY (1<<6) | 23 | #define ARM_CP_RW_BIT (1 << 20) |
34 | #define UTS1_RXEMPTY (1<<5) | 24 | |
35 | #define UTS1_TXFULL (1<<4) | 25 | /* Include the VFP decoder */ |
36 | @@ -XXX,XX +XXX,XX @@ typedef struct IMXSerialState { | 26 | @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) |
37 | uint32_t ubmr; | 27 | tmp = neon_load_reg(rm, 0); |
38 | uint32_t ubrc; | 28 | tmp2 = neon_load_reg(rm, 1); |
39 | uint32_t ucr3; | 29 | tcg_gen_ext16u_i32(tmp3, tmp); |
40 | + uint32_t ucr4; | 30 | - gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); |
41 | 31 | - tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 0)); | |
42 | qemu_irq irq; | 32 | - tcg_gen_shri_i32(tmp3, tmp, 16); |
43 | CharBackend chr; | 33 | - gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); |
44 | diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c | 34 | - tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 1)); |
45 | index XXXXXXX..XXXXXXX 100644 | 35 | - tcg_temp_free_i32(tmp); |
46 | --- a/hw/char/imx_serial.c | 36 | + gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); |
47 | +++ b/hw/char/imx_serial.c | 37 | + neon_store_reg(rd, 0, tmp3); |
48 | @@ -XXX,XX +XXX,XX @@ | 38 | + tcg_gen_shri_i32(tmp, tmp, 16); |
49 | 39 | + gen_helper_vfp_fcvt_f16_to_f32(tmp, tmp, fpst, ahp); | |
50 | static const VMStateDescription vmstate_imx_serial = { | 40 | + neon_store_reg(rd, 1, tmp); |
51 | .name = TYPE_IMX_SERIAL, | 41 | + tmp3 = tcg_temp_new_i32(); |
52 | - .version_id = 1, | 42 | tcg_gen_ext16u_i32(tmp3, tmp2); |
53 | - .minimum_version_id = 1, | 43 | - gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); |
54 | + .version_id = 2, | 44 | - tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 2)); |
55 | + .minimum_version_id = 2, | 45 | - tcg_gen_shri_i32(tmp3, tmp2, 16); |
56 | .fields = (VMStateField[]) { | 46 | - gen_helper_vfp_fcvt_f16_to_f32(cpu_F0s, tmp3, fpst, ahp); |
57 | VMSTATE_INT32(readbuff, IMXSerialState), | 47 | - tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, 3)); |
58 | VMSTATE_UINT32(usr1, IMXSerialState), | 48 | - tcg_temp_free_i32(tmp2); |
59 | @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_serial = { | 49 | - tcg_temp_free_i32(tmp3); |
60 | VMSTATE_UINT32(ubmr, IMXSerialState), | 50 | + gen_helper_vfp_fcvt_f16_to_f32(tmp3, tmp3, fpst, ahp); |
61 | VMSTATE_UINT32(ubrc, IMXSerialState), | 51 | + neon_store_reg(rd, 2, tmp3); |
62 | VMSTATE_UINT32(ucr3, IMXSerialState), | 52 | + tcg_gen_shri_i32(tmp2, tmp2, 16); |
63 | + VMSTATE_UINT32(ucr4, IMXSerialState), | 53 | + gen_helper_vfp_fcvt_f16_to_f32(tmp2, tmp2, fpst, ahp); |
64 | VMSTATE_END_OF_LIST() | 54 | + neon_store_reg(rd, 3, tmp2); |
65 | }, | 55 | tcg_temp_free_i32(ahp); |
66 | }; | 56 | tcg_temp_free_ptr(fpst); |
67 | @@ -XXX,XX +XXX,XX @@ static void imx_update(IMXSerialState *s) | 57 | break; |
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 | -- | 58 | -- |
114 | 2.16.2 | 59 | 2.20.1 |
115 | 60 | ||
116 | 61 | diff view generated by jsdifflib |
1 | From: Guenter Roeck <linux@roeck-us.net> | 1 | Remove the now unused TCG globals cpu_F0s, cpu_F0d, cpu_F1s, cpu_F1d. |
---|---|---|---|
2 | 2 | ||
3 | The sabrelite machine model used by qemu-system-arm is based on the | 3 | cpu_M0 is still used by the iwmmxt code, and cpu_V0 and |
4 | Freescale/NXP i.MX6Q processor. This SoC has an on-board ethernet | 4 | cpu_V1 are used by both iwmmxt and Neon. |
5 | controller which is supported in QEMU using the imx_fec.c module | ||
6 | (actually called imx.enet for this model.) | ||
7 | 5 | ||
8 | The include/hw/arm/fsm-imx6.h file defines the interrupt vectors for the | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | imx.enet device like this: | 7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
8 | Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> | ||
9 | Message-id: 20190613163917.28589-13-peter.maydell@linaro.org | ||
10 | --- | ||
11 | target/arm/translate.c | 12 ++---------- | ||
12 | 1 file changed, 2 insertions(+), 10 deletions(-) | ||
10 | 13 | ||
11 | #define FSL_IMX6_ENET_MAC_1588_IRQ 118 | 14 | diff --git a/target/arm/translate.c b/target/arm/translate.c |
12 | #define FSL_IMX6_ENET_MAC_IRQ 119 | ||
13 | |||
14 | According to https://www.nxp.com/docs/en/reference-manual/IMX6DQRM.pdf, | ||
15 | page 225, in Table 3-1. ARM Cortex A9 domain interrupt summary, | ||
16 | interrupts are as follows. | ||
17 | |||
18 | 150 ENET MAC 0 IRQ | ||
19 | 151 ENET MAC 0 1588 Timer interrupt | ||
20 | |||
21 | where | ||
22 | |||
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> | ||
42 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
43 | --- | ||
44 | include/hw/arm/fsl-imx6.h | 4 ++-- | ||
45 | hw/net/imx_fec.c | 28 +++++++++++++++++++++++++++- | ||
46 | 2 files changed, 29 insertions(+), 3 deletions(-) | ||
47 | |||
48 | diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h | ||
49 | index XXXXXXX..XXXXXXX 100644 | 15 | index XXXXXXX..XXXXXXX 100644 |
50 | --- a/include/hw/arm/fsl-imx6.h | 16 | --- a/target/arm/translate.c |
51 | +++ b/include/hw/arm/fsl-imx6.h | 17 | +++ b/target/arm/translate.c |
52 | @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX6State { | 18 | @@ -XXX,XX +XXX,XX @@ TCGv_i32 cpu_CF, cpu_NF, cpu_VF, cpu_ZF; |
53 | #define FSL_IMX6_HDMI_MASTER_IRQ 115 | 19 | TCGv_i64 cpu_exclusive_addr; |
54 | #define FSL_IMX6_HDMI_CEC_IRQ 116 | 20 | TCGv_i64 cpu_exclusive_val; |
55 | #define FSL_IMX6_MLB150_LOW_IRQ 117 | 21 | |
56 | -#define FSL_IMX6_ENET_MAC_1588_IRQ 118 | 22 | -/* FIXME: These should be removed. */ |
57 | -#define FSL_IMX6_ENET_MAC_IRQ 119 | 23 | -static TCGv_i32 cpu_F0s, cpu_F1s; |
58 | +#define FSL_IMX6_ENET_MAC_IRQ 118 | 24 | -static TCGv_i64 cpu_F0d, cpu_F1d; |
59 | +#define FSL_IMX6_ENET_MAC_1588_IRQ 119 | 25 | - |
60 | #define FSL_IMX6_PCIE1_IRQ 120 | 26 | #include "exec/gen-icount.h" |
61 | #define FSL_IMX6_PCIE2_IRQ 121 | 27 | |
62 | #define FSL_IMX6_PCIE3_IRQ 122 | 28 | static const char * const regnames[] = |
63 | diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c | 29 | @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) |
64 | index XXXXXXX..XXXXXXX 100644 | 30 | dc->base.max_insns = MIN(dc->base.max_insns, bound); |
65 | --- a/hw/net/imx_fec.c | 31 | } |
66 | +++ b/hw/net/imx_fec.c | 32 | |
67 | @@ -XXX,XX +XXX,XX @@ static void imx_enet_write_bd(IMXENETBufDesc *bd, dma_addr_t addr) | 33 | - cpu_F0s = tcg_temp_new_i32(); |
68 | 34 | - cpu_F1s = tcg_temp_new_i32(); | |
69 | static void imx_eth_update(IMXFECState *s) | 35 | - cpu_F0d = tcg_temp_new_i64(); |
70 | { | 36 | - cpu_F1d = tcg_temp_new_i64(); |
71 | - if (s->regs[ENET_EIR] & s->regs[ENET_EIMR] & ENET_INT_TS_TIMER) { | 37 | - cpu_V0 = cpu_F0d; |
72 | + /* | 38 | - cpu_V1 = cpu_F1d; |
73 | + * Previous versions of qemu had the ENET_INT_MAC and ENET_INT_TS_TIMER | 39 | + cpu_V0 = tcg_temp_new_i64(); |
74 | + * interrupts swapped. This worked with older versions of Linux (4.14 | 40 | + cpu_V1 = tcg_temp_new_i64(); |
75 | + * and older) since Linux associated both interrupt lines with Ethernet | 41 | /* FIXME: cpu_M0 can probably be the same as cpu_V0. */ |
76 | + * MAC interrupts. Specifically, | 42 | cpu_M0 = tcg_temp_new_i64(); |
77 | + * - Linux 4.15 and later have separate interrupt handlers for the MAC and | 43 | } |
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 | -- | 44 | -- |
103 | 2.16.2 | 45 | 2.20.1 |
104 | 46 | ||
105 | 47 | diff view generated by jsdifflib |
1 | From: Andrey Smirnov <andrew.smirnov@gmail.com> | 1 | In several places cut and paste errors meant we were using the wrong |
---|---|---|---|
2 | type for the 'arg' struct in trans_ functions called by the | ||
3 | decodetree decoder, because we were using the _sp version of the | ||
4 | struct in the _dp function. These were harmless, because the two | ||
5 | structs were identical and so decodetree made them typedefs of the | ||
6 | same underlying structure (and we'd have had a compile error if they | ||
7 | were not harmless), but we should clean them up anyway. | ||
2 | 8 | ||
3 | Code of imx_update() is slightly confusing since the "flags" variable | 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
4 | doesn't really corespond to anything in real hardware and server as a | 10 | Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> |
5 | kitchensink accumulating events normally reported via USR1 and USR2 | 11 | Message-id: 20190614104457.24703-2-peter.maydell@linaro.org |
6 | registers. | 12 | --- |
13 | target/arm/translate-vfp.inc.c | 28 ++++++++++++++-------------- | ||
14 | 1 file changed, 14 insertions(+), 14 deletions(-) | ||
7 | 15 | ||
8 | Change the code to explicitly evaluate state of interrupts reported | 16 | diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c |
9 | via USR1 and USR2 against corresponding masking bits and use the to | ||
10 | detemine if IRQ line should be asserted or not. | ||
11 | |||
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> | ||
32 | --- | ||
33 | hw/char/imx_serial.c | 24 ++++++++++++++++-------- | ||
34 | 1 file changed, 16 insertions(+), 8 deletions(-) | ||
35 | |||
36 | diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
38 | --- a/hw/char/imx_serial.c | 18 | --- a/target/arm/translate-vfp.inc.c |
39 | +++ b/hw/char/imx_serial.c | 19 | +++ b/target/arm/translate-vfp.inc.c |
40 | @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_serial = { | 20 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) |
41 | 21 | return true; | |
42 | static void imx_update(IMXSerialState *s) | 22 | } |
23 | |||
24 | -static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_sp *a) | ||
25 | +static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) | ||
43 | { | 26 | { |
44 | - uint32_t flags; | 27 | TCGv_i32 tmp; |
45 | + uint32_t usr1; | 28 | |
46 | + uint32_t usr2; | 29 | @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) |
47 | + uint32_t mask; | 30 | return true; |
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 | } | 31 | } |
71 | 32 | ||
72 | static void imx_serial_reset(IMXSerialState *s) | 33 | -static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_sp *a) |
34 | +static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) | ||
35 | { | ||
36 | uint32_t offset; | ||
37 | TCGv_i32 addr; | ||
38 | @@ -XXX,XX +XXX,XX @@ static void gen_VMLA_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) | ||
39 | tcg_temp_free_i64(tmp); | ||
40 | } | ||
41 | |||
42 | -static bool trans_VMLA_dp(DisasContext *s, arg_VMLA_sp *a) | ||
43 | +static bool trans_VMLA_dp(DisasContext *s, arg_VMLA_dp *a) | ||
44 | { | ||
45 | return do_vfp_3op_dp(s, gen_VMLA_dp, a->vd, a->vn, a->vm, true); | ||
46 | } | ||
47 | @@ -XXX,XX +XXX,XX @@ static void gen_VMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) | ||
48 | tcg_temp_free_i64(tmp); | ||
49 | } | ||
50 | |||
51 | -static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_sp *a) | ||
52 | +static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_dp *a) | ||
53 | { | ||
54 | return do_vfp_3op_dp(s, gen_VMLS_dp, a->vd, a->vn, a->vm, true); | ||
55 | } | ||
56 | @@ -XXX,XX +XXX,XX @@ static void gen_VNMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) | ||
57 | tcg_temp_free_i64(tmp); | ||
58 | } | ||
59 | |||
60 | -static bool trans_VNMLS_dp(DisasContext *s, arg_VNMLS_sp *a) | ||
61 | +static bool trans_VNMLS_dp(DisasContext *s, arg_VNMLS_dp *a) | ||
62 | { | ||
63 | return do_vfp_3op_dp(s, gen_VNMLS_dp, a->vd, a->vn, a->vm, true); | ||
64 | } | ||
65 | @@ -XXX,XX +XXX,XX @@ static void gen_VNMLA_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) | ||
66 | tcg_temp_free_i64(tmp); | ||
67 | } | ||
68 | |||
69 | -static bool trans_VNMLA_dp(DisasContext *s, arg_VNMLA_sp *a) | ||
70 | +static bool trans_VNMLA_dp(DisasContext *s, arg_VNMLA_dp *a) | ||
71 | { | ||
72 | return do_vfp_3op_dp(s, gen_VNMLA_dp, a->vd, a->vn, a->vm, true); | ||
73 | } | ||
74 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_sp(DisasContext *s, arg_VMUL_sp *a) | ||
75 | return do_vfp_3op_sp(s, gen_helper_vfp_muls, a->vd, a->vn, a->vm, false); | ||
76 | } | ||
77 | |||
78 | -static bool trans_VMUL_dp(DisasContext *s, arg_VMUL_sp *a) | ||
79 | +static bool trans_VMUL_dp(DisasContext *s, arg_VMUL_dp *a) | ||
80 | { | ||
81 | return do_vfp_3op_dp(s, gen_helper_vfp_muld, a->vd, a->vn, a->vm, false); | ||
82 | } | ||
83 | @@ -XXX,XX +XXX,XX @@ static void gen_VNMUL_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst) | ||
84 | gen_helper_vfp_negd(vd, vd); | ||
85 | } | ||
86 | |||
87 | -static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_sp *a) | ||
88 | +static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_dp *a) | ||
89 | { | ||
90 | return do_vfp_3op_dp(s, gen_VNMUL_dp, a->vd, a->vn, a->vm, false); | ||
91 | } | ||
92 | @@ -XXX,XX +XXX,XX @@ static bool trans_VADD_sp(DisasContext *s, arg_VADD_sp *a) | ||
93 | return do_vfp_3op_sp(s, gen_helper_vfp_adds, a->vd, a->vn, a->vm, false); | ||
94 | } | ||
95 | |||
96 | -static bool trans_VADD_dp(DisasContext *s, arg_VADD_sp *a) | ||
97 | +static bool trans_VADD_dp(DisasContext *s, arg_VADD_dp *a) | ||
98 | { | ||
99 | return do_vfp_3op_dp(s, gen_helper_vfp_addd, a->vd, a->vn, a->vm, false); | ||
100 | } | ||
101 | @@ -XXX,XX +XXX,XX @@ static bool trans_VSUB_sp(DisasContext *s, arg_VSUB_sp *a) | ||
102 | return do_vfp_3op_sp(s, gen_helper_vfp_subs, a->vd, a->vn, a->vm, false); | ||
103 | } | ||
104 | |||
105 | -static bool trans_VSUB_dp(DisasContext *s, arg_VSUB_sp *a) | ||
106 | +static bool trans_VSUB_dp(DisasContext *s, arg_VSUB_dp *a) | ||
107 | { | ||
108 | return do_vfp_3op_dp(s, gen_helper_vfp_subd, a->vd, a->vn, a->vm, false); | ||
109 | } | ||
110 | @@ -XXX,XX +XXX,XX @@ static bool trans_VDIV_sp(DisasContext *s, arg_VDIV_sp *a) | ||
111 | return do_vfp_3op_sp(s, gen_helper_vfp_divs, a->vd, a->vn, a->vm, false); | ||
112 | } | ||
113 | |||
114 | -static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_sp *a) | ||
115 | +static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_dp *a) | ||
116 | { | ||
117 | return do_vfp_3op_dp(s, gen_helper_vfp_divd, a->vd, a->vn, a->vm, false); | ||
118 | } | ||
119 | @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) | ||
120 | return true; | ||
121 | } | ||
122 | |||
123 | -static bool trans_VFM_dp(DisasContext *s, arg_VFM_sp *a) | ||
124 | +static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) | ||
125 | { | ||
126 | /* | ||
127 | * VFNMA : fd = muladd(-fd, fn, fm) | ||
128 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) | ||
129 | return true; | ||
130 | } | ||
131 | |||
132 | -static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_sp *a) | ||
133 | +static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) | ||
134 | { | ||
135 | TCGv_ptr fpst; | ||
136 | TCGv_i64 tmp; | ||
137 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) | ||
138 | return true; | ||
139 | } | ||
140 | |||
141 | -static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_sp *a) | ||
142 | +static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) | ||
143 | { | ||
144 | TCGv_ptr fpst; | ||
145 | TCGv_i64 tmp; | ||
73 | -- | 146 | -- |
74 | 2.16.2 | 147 | 2.20.1 |
75 | 148 | ||
76 | 149 | diff view generated by jsdifflib |
New patch | |||
---|---|---|---|
1 | 1 | The architecture permits FPUs which have only single-precision | |
2 | support, not double-precision; Cortex-M4 and Cortex-M33 are | ||
3 | both like that. Add the necessary checks on the MVFR0 FPDP | ||
4 | field so that we UNDEF any double-precision instructions on | ||
5 | CPUs like this. | ||
6 | |||
7 | Note that even if FPDP==0 the insns like VMOV-to/from-gpreg, | ||
8 | VLDM/VSTM, VLDR/VSTR which take double precision registers | ||
9 | still exist. | ||
10 | |||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
13 | Message-id: 20190614104457.24703-3-peter.maydell@linaro.org | ||
14 | --- | ||
15 | target/arm/cpu.h | 6 +++ | ||
16 | target/arm/translate-vfp.inc.c | 84 ++++++++++++++++++++++++++++++++++ | ||
17 | 2 files changed, 90 insertions(+) | ||
18 | |||
19 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
20 | index XXXXXXX..XXXXXXX 100644 | ||
21 | --- a/target/arm/cpu.h | ||
22 | +++ b/target/arm/cpu.h | ||
23 | @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) | ||
24 | return FIELD_EX64(id->mvfr0, MVFR0, FPSHVEC) > 0; | ||
25 | } | ||
26 | |||
27 | +static inline bool isar_feature_aa32_fpdp(const ARMISARegisters *id) | ||
28 | +{ | ||
29 | + /* Return true if CPU supports double precision floating point */ | ||
30 | + return FIELD_EX64(id->mvfr0, MVFR0, FPDP) > 0; | ||
31 | +} | ||
32 | + | ||
33 | /* | ||
34 | * We always set the FP and SIMD FP16 fields to indicate identical | ||
35 | * levels of support (assuming SIMD is implemented at all), so | ||
36 | diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c | ||
37 | index XXXXXXX..XXXXXXX 100644 | ||
38 | --- a/target/arm/translate-vfp.inc.c | ||
39 | +++ b/target/arm/translate-vfp.inc.c | ||
40 | @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) | ||
41 | ((a->vm | a->vn | a->vd) & 0x10)) { | ||
42 | return false; | ||
43 | } | ||
44 | + | ||
45 | + if (dp && !dc_isar_feature(aa32_fpdp, s)) { | ||
46 | + return false; | ||
47 | + } | ||
48 | + | ||
49 | rd = a->vd; | ||
50 | rn = a->vn; | ||
51 | rm = a->vm; | ||
52 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMINMAXNM(DisasContext *s, arg_VMINMAXNM *a) | ||
53 | ((a->vm | a->vn | a->vd) & 0x10)) { | ||
54 | return false; | ||
55 | } | ||
56 | + | ||
57 | + if (dp && !dc_isar_feature(aa32_fpdp, s)) { | ||
58 | + return false; | ||
59 | + } | ||
60 | + | ||
61 | rd = a->vd; | ||
62 | rn = a->vn; | ||
63 | rm = a->vm; | ||
64 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) | ||
65 | ((a->vm | a->vd) & 0x10)) { | ||
66 | return false; | ||
67 | } | ||
68 | + | ||
69 | + if (dp && !dc_isar_feature(aa32_fpdp, s)) { | ||
70 | + return false; | ||
71 | + } | ||
72 | + | ||
73 | rd = a->vd; | ||
74 | rm = a->vm; | ||
75 | |||
76 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) | ||
77 | if (dp && !dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) { | ||
78 | return false; | ||
79 | } | ||
80 | + | ||
81 | + if (dp && !dc_isar_feature(aa32_fpdp, s)) { | ||
82 | + return false; | ||
83 | + } | ||
84 | + | ||
85 | rd = a->vd; | ||
86 | rm = a->vm; | ||
87 | |||
88 | @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, | ||
89 | return false; | ||
90 | } | ||
91 | |||
92 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
93 | + return false; | ||
94 | + } | ||
95 | + | ||
96 | if (!dc_isar_feature(aa32_fpshvec, s) && | ||
97 | (veclen != 0 || s->vec_stride != 0)) { | ||
98 | return false; | ||
99 | @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) | ||
100 | return false; | ||
101 | } | ||
102 | |||
103 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
104 | + return false; | ||
105 | + } | ||
106 | + | ||
107 | if (!dc_isar_feature(aa32_fpshvec, s) && | ||
108 | (veclen != 0 || s->vec_stride != 0)) { | ||
109 | return false; | ||
110 | @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) | ||
111 | return false; | ||
112 | } | ||
113 | |||
114 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
115 | + return false; | ||
116 | + } | ||
117 | + | ||
118 | if (!vfp_access_check(s)) { | ||
119 | return true; | ||
120 | } | ||
121 | @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) | ||
122 | return false; | ||
123 | } | ||
124 | |||
125 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
126 | + return false; | ||
127 | + } | ||
128 | + | ||
129 | if (!dc_isar_feature(aa32_fpshvec, s) && | ||
130 | (veclen != 0 || s->vec_stride != 0)) { | ||
131 | return false; | ||
132 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) | ||
133 | return false; | ||
134 | } | ||
135 | |||
136 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
137 | + return false; | ||
138 | + } | ||
139 | + | ||
140 | if (!vfp_access_check(s)) { | ||
141 | return true; | ||
142 | } | ||
143 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) | ||
144 | return false; | ||
145 | } | ||
146 | |||
147 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
148 | + return false; | ||
149 | + } | ||
150 | + | ||
151 | if (!vfp_access_check(s)) { | ||
152 | return true; | ||
153 | } | ||
154 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) | ||
155 | return false; | ||
156 | } | ||
157 | |||
158 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
159 | + return false; | ||
160 | + } | ||
161 | + | ||
162 | if (!vfp_access_check(s)) { | ||
163 | return true; | ||
164 | } | ||
165 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) | ||
166 | return false; | ||
167 | } | ||
168 | |||
169 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
170 | + return false; | ||
171 | + } | ||
172 | + | ||
173 | if (!vfp_access_check(s)) { | ||
174 | return true; | ||
175 | } | ||
176 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) | ||
177 | return false; | ||
178 | } | ||
179 | |||
180 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
181 | + return false; | ||
182 | + } | ||
183 | + | ||
184 | if (!vfp_access_check(s)) { | ||
185 | return true; | ||
186 | } | ||
187 | @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) | ||
188 | return false; | ||
189 | } | ||
190 | |||
191 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
192 | + return false; | ||
193 | + } | ||
194 | + | ||
195 | if (!vfp_access_check(s)) { | ||
196 | return true; | ||
197 | } | ||
198 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) | ||
199 | return false; | ||
200 | } | ||
201 | |||
202 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
203 | + return false; | ||
204 | + } | ||
205 | + | ||
206 | if (!vfp_access_check(s)) { | ||
207 | return true; | ||
208 | } | ||
209 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) | ||
210 | return false; | ||
211 | } | ||
212 | |||
213 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
214 | + return false; | ||
215 | + } | ||
216 | + | ||
217 | if (!vfp_access_check(s)) { | ||
218 | return true; | ||
219 | } | ||
220 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) | ||
221 | return false; | ||
222 | } | ||
223 | |||
224 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
225 | + return false; | ||
226 | + } | ||
227 | + | ||
228 | if (!vfp_access_check(s)) { | ||
229 | return true; | ||
230 | } | ||
231 | @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) | ||
232 | return false; | ||
233 | } | ||
234 | |||
235 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
236 | + return false; | ||
237 | + } | ||
238 | + | ||
239 | if (!vfp_access_check(s)) { | ||
240 | return true; | ||
241 | } | ||
242 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) | ||
243 | return false; | ||
244 | } | ||
245 | |||
246 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
247 | + return false; | ||
248 | + } | ||
249 | + | ||
250 | if (!vfp_access_check(s)) { | ||
251 | return true; | ||
252 | } | ||
253 | @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) | ||
254 | return false; | ||
255 | } | ||
256 | |||
257 | + if (!dc_isar_feature(aa32_fpdp, s)) { | ||
258 | + return false; | ||
259 | + } | ||
260 | + | ||
261 | if (!vfp_access_check(s)) { | ||
262 | return true; | ||
263 | } | ||
264 | -- | ||
265 | 2.20.1 | ||
266 | |||
267 | diff view generated by jsdifflib |