1 | The following changes since commit ad1b4ec39caa5b3f17cbd8160283a03a3dcfe2ae: | 1 | target-arm queue for 3.0: |
---|---|---|---|
2 | 2 | ||
3 | Merge remote-tracking branch 'remotes/kraxel/tags/input-20180515-pull-request' into staging (2018-05-15 12:50:06 +0100) | 3 | Thomas' fixes for instrospection issues with a handful of |
4 | devices (including one microblaze one that I include in this | ||
5 | pullreq for convenience's sake), plus my bugfix for a | ||
6 | corner case of small MPU region support. | ||
7 | |||
8 | thanks | ||
9 | -- PMM | ||
10 | |||
11 | The following changes since commit 55b1f14cefcb19ce6d5e28c4c83404230888aa7e: | ||
12 | |||
13 | Merge remote-tracking branch 'remotes/vivier2/tags/linux-user-for-3.0-pull-request' into staging (2018-07-23 14:03:14 +0100) | ||
4 | 14 | ||
5 | are available in the Git repository at: | 15 | are available in the Git repository at: |
6 | 16 | ||
7 | git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180515 | 17 | git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180723 |
8 | 18 | ||
9 | for you to fetch changes up to ae7651804748c6b479d5ae09aeac4edb9c44f76e: | 19 | for you to fetch changes up to 1ddc9b98c3cb89fe23a55ba924000fd645253e87: |
10 | 20 | ||
11 | tcg: Optionally log FPU state in TCG -d cpu logging (2018-05-15 14:58:44 +0100) | 21 | hw/intc/exynos4210_gic: Turn instance_init into realize function (2018-07-23 15:21:27 +0100) |
12 | 22 | ||
13 | ---------------------------------------------------------------- | 23 | ---------------------------------------------------------------- |
14 | target-arm queue: | 24 | target-arm queue: |
15 | * Fix coverity nit in int_to_float code | 25 | * spitz, exynos: fix bugs when introspecting some devices |
16 | * Don't set Invalid for float-to-int(MAXINT) | 26 | * hw/microblaze/xlnx-zynqmp-pmu: Fix introspection problem in 'xlnx, zynqmp-pmu-soc' |
17 | * Fix fp_status_f16 tininess before rounding | 27 | * target/arm: Correctly handle overlapping small MPU regions |
18 | * Add various missing insns from the v8.2-FP16 extension | 28 | * hw/sd/bcm2835_sdhost: Fix PIO mode writes |
19 | * Fix sqrt_f16 exception raising | ||
20 | * sdcard: Correct CRC16 offset in sd_function_switch() | ||
21 | * tcg: Optionally log FPU state in TCG -d cpu logging | ||
22 | 29 | ||
23 | ---------------------------------------------------------------- | 30 | ---------------------------------------------------------------- |
24 | Alex Bennée (5): | 31 | Guenter Roeck (1): |
25 | fpu/softfloat: int_to_float ensure r fully initialised | 32 | hw/sd/bcm2835_sdhost: Fix PIO mode writes |
26 | target/arm: Implement FCMP for fp16 | ||
27 | target/arm: Implement FCSEL for fp16 | ||
28 | target/arm: Implement FMOV (immediate) for fp16 | ||
29 | target/arm: Fix sqrt_f16 exception raising | ||
30 | 33 | ||
31 | Peter Maydell (3): | 34 | Peter Maydell (1): |
32 | fpu/softfloat: Don't set Invalid for float-to-int(MAXINT) | 35 | target/arm: Correctly handle overlapping small MPU regions |
33 | target/arm: Fix fp_status_f16 tininess before rounding | ||
34 | tcg: Optionally log FPU state in TCG -d cpu logging | ||
35 | 36 | ||
36 | Philippe Mathieu-Daudé (1): | 37 | Thomas Huth (3): |
37 | sdcard: Correct CRC16 offset in sd_function_switch() | 38 | hw/microblaze/xlnx-zynqmp-pmu: Fix introspection problem in 'xlnx, zynqmp-pmu-soc' |
39 | hw/arm/spitz: Move problematic nand_init() code to realize function | ||
40 | hw/intc/exynos4210_gic: Turn instance_init into realize function | ||
38 | 41 | ||
39 | Richard Henderson (7): | 42 | hw/arm/spitz.c | 15 ++++++++++---- |
40 | target/arm: Implement FMOV (general) for fp16 | 43 | hw/intc/exynos4210_gic.c | 6 +++--- |
41 | target/arm: Early exit after unallocated_encoding in disas_fp_int_conv | 44 | hw/microblaze/xlnx-zynqmp-pmu.c | 10 ++++----- |
42 | target/arm: Implement FCVT (scalar, integer) for fp16 | 45 | hw/sd/bcm2835_sdhost.c | 20 ++++++++++++++---- |
43 | target/arm: Implement FCVT (scalar, fixed-point) for fp16 | 46 | target/arm/helper.c | 46 +++++++++++++++++++++++++++++++++++++++++ |
44 | target/arm: Introduce and use read_fp_hreg | 47 | 5 files changed, 80 insertions(+), 17 deletions(-) |
45 | target/arm: Implement FP data-processing (2 source) for fp16 | ||
46 | target/arm: Implement FP data-processing (3 source) for fp16 | ||
47 | 48 | ||
48 | include/qemu/log.h | 1 + | ||
49 | target/arm/helper-a64.h | 2 + | ||
50 | target/arm/helper.h | 6 + | ||
51 | accel/tcg/cpu-exec.c | 9 +- | ||
52 | fpu/softfloat.c | 6 +- | ||
53 | hw/sd/sd.c | 2 +- | ||
54 | target/arm/cpu.c | 2 + | ||
55 | target/arm/helper-a64.c | 10 ++ | ||
56 | target/arm/helper.c | 38 +++- | ||
57 | target/arm/translate-a64.c | 421 ++++++++++++++++++++++++++++++++++++++------- | ||
58 | util/log.c | 2 + | ||
59 | 11 files changed, 428 insertions(+), 71 deletions(-) | ||
60 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Alex Bennée <alex.bennee@linaro.org> | ||
2 | 1 | ||
3 | Reported by Coverity (CID1390635). We ensure this for uint_to_float | ||
4 | later on so we might as well mirror that. | ||
5 | |||
6 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | fpu/softfloat.c | 2 +- | ||
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
13 | |||
14 | diff --git a/fpu/softfloat.c b/fpu/softfloat.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/fpu/softfloat.c | ||
17 | +++ b/fpu/softfloat.c | ||
18 | @@ -XXX,XX +XXX,XX @@ FLOAT_TO_UINT(64, 64) | ||
19 | |||
20 | static FloatParts int_to_float(int64_t a, float_status *status) | ||
21 | { | ||
22 | - FloatParts r; | ||
23 | + FloatParts r = {}; | ||
24 | if (a == 0) { | ||
25 | r.cls = float_class_zero; | ||
26 | r.sign = false; | ||
27 | -- | ||
28 | 2.17.0 | ||
29 | |||
30 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | In float-to-integer conversion, if the floating point input | ||
2 | converts exactly to the largest or smallest integer that | ||
3 | fits in to the result type, this is not an overflow. | ||
4 | In this situation we were producing the correct result value, | ||
5 | but were incorrectly setting the Invalid flag. | ||
6 | For example for Arm A64, "FCVTAS w0, d0" on an input of | ||
7 | 0x41dfffffffc00000 should produce 0x7fffffff and set no flags. | ||
8 | 1 | ||
9 | Fix the boundary case to take the right half of the if() | ||
10 | statements. | ||
11 | |||
12 | This fixes a regression from 2.11 introduced by the softfloat | ||
13 | refactoring. | ||
14 | |||
15 | Cc: qemu-stable@nongnu.org | ||
16 | Fixes: ab52f973a50 | ||
17 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
18 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
19 | Message-id: 20180510140141.12120-1-peter.maydell@linaro.org | ||
20 | --- | ||
21 | fpu/softfloat.c | 4 ++-- | ||
22 | 1 file changed, 2 insertions(+), 2 deletions(-) | ||
23 | |||
24 | diff --git a/fpu/softfloat.c b/fpu/softfloat.c | ||
25 | index XXXXXXX..XXXXXXX 100644 | ||
26 | --- a/fpu/softfloat.c | ||
27 | +++ b/fpu/softfloat.c | ||
28 | @@ -XXX,XX +XXX,XX @@ static int64_t round_to_int_and_pack(FloatParts in, int rmode, | ||
29 | r = UINT64_MAX; | ||
30 | } | ||
31 | if (p.sign) { | ||
32 | - if (r < -(uint64_t) min) { | ||
33 | + if (r <= -(uint64_t) min) { | ||
34 | return -r; | ||
35 | } else { | ||
36 | s->float_exception_flags = orig_flags | float_flag_invalid; | ||
37 | return min; | ||
38 | } | ||
39 | } else { | ||
40 | - if (r < max) { | ||
41 | + if (r <= max) { | ||
42 | return r; | ||
43 | } else { | ||
44 | s->float_exception_flags = orig_flags | float_flag_invalid; | ||
45 | -- | ||
46 | 2.17.0 | ||
47 | |||
48 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | In commit d81ce0ef2c4f105 we added an extra float_status field | ||
2 | fp_status_fp16 for Arm, but forgot to initialize it correctly | ||
3 | by setting it to float_tininess_before_rounding. This currently | ||
4 | will only cause problems for the new V8_FP16 feature, since the | ||
5 | float-to-float conversion code doesn't use it yet. The effect | ||
6 | would be that we failed to set the Underflow IEEE exception flag | ||
7 | in all the cases where we should. | ||
8 | 1 | ||
9 | Add the missing initialization. | ||
10 | |||
11 | Fixes: d81ce0ef2c4f105 | ||
12 | Cc: qemu-stable@nongnu.org | ||
13 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
14 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
16 | Message-id: 20180512004311.9299-16-richard.henderson@linaro.org | ||
17 | --- | ||
18 | target/arm/cpu.c | 2 ++ | ||
19 | 1 file changed, 2 insertions(+) | ||
20 | |||
21 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | ||
22 | index XXXXXXX..XXXXXXX 100644 | ||
23 | --- a/target/arm/cpu.c | ||
24 | +++ b/target/arm/cpu.c | ||
25 | @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) | ||
26 | &env->vfp.fp_status); | ||
27 | set_float_detect_tininess(float_tininess_before_rounding, | ||
28 | &env->vfp.standard_fp_status); | ||
29 | + set_float_detect_tininess(float_tininess_before_rounding, | ||
30 | + &env->vfp.fp_status_f16); | ||
31 | #ifndef CONFIG_USER_ONLY | ||
32 | if (kvm_enabled()) { | ||
33 | kvm_arm_reset_vcpu(cpu); | ||
34 | -- | ||
35 | 2.17.0 | ||
36 | |||
37 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | From: Thomas Huth <thuth@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Cc: qemu-stable@nongnu.org | 3 | Valgrind complains: |
4 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 4 | |
5 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 5 | echo "{'execute':'qmp_capabilities'} {'execute':'device-list-properties'," \ |
6 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | 6 | "'arguments':{'typename':'xlnx,zynqmp-pmu-soc'}}" \ |
7 | Message-id: 20180512003217.9105-6-richard.henderson@linaro.org | 7 | "{'execute': 'human-monitor-command', " \ |
8 | "'arguments': {'command-line': 'info qtree'}}" | \ | ||
9 | valgrind -q microblazeel-softmmu/qemu-system-microblazeel -M none,accel=qtest -qmp stdio | ||
10 | [...] | ||
11 | ==13605== Invalid read of size 8 | ||
12 | ==13605== at 0x2AC69A: qdev_print (qdev-monitor.c:686) | ||
13 | ==13605== by 0x2AC69A: qbus_print (qdev-monitor.c:719) | ||
14 | ==13605== by 0x2591E8: handle_hmp_command (monitor.c:3446) | ||
15 | |||
16 | Use the new object_initialize_child() and sysbus_init_child_obj() to | ||
17 | fix the issue. | ||
18 | |||
19 | Signed-off-by: Thomas Huth <thuth@redhat.com> | ||
20 | Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> | ||
21 | Message-id: 1531839343-13828-1-git-send-email-thuth@redhat.com | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 22 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
9 | --- | 23 | --- |
10 | target/arm/translate-a64.c | 30 ++++++++++++++---------------- | 24 | hw/microblaze/xlnx-zynqmp-pmu.c | 10 ++++------ |
11 | 1 file changed, 14 insertions(+), 16 deletions(-) | 25 | 1 file changed, 4 insertions(+), 6 deletions(-) |
12 | 26 | ||
13 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 27 | diff --git a/hw/microblaze/xlnx-zynqmp-pmu.c b/hw/microblaze/xlnx-zynqmp-pmu.c |
14 | index XXXXXXX..XXXXXXX 100644 | 28 | index XXXXXXX..XXXXXXX 100644 |
15 | --- a/target/arm/translate-a64.c | 29 | --- a/hw/microblaze/xlnx-zynqmp-pmu.c |
16 | +++ b/target/arm/translate-a64.c | 30 | +++ b/hw/microblaze/xlnx-zynqmp-pmu.c |
17 | @@ -XXX,XX +XXX,XX @@ static TCGv_i32 read_fp_sreg(DisasContext *s, int reg) | 31 | @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_pmu_soc_init(Object *obj) |
18 | return v; | 32 | { |
33 | XlnxZynqMPPMUSoCState *s = XLNX_ZYNQMP_PMU_SOC(obj); | ||
34 | |||
35 | - object_initialize(&s->cpu, sizeof(s->cpu), | ||
36 | - TYPE_MICROBLAZE_CPU); | ||
37 | - object_property_add_child(obj, "pmu-cpu", OBJECT(&s->cpu), | ||
38 | - &error_abort); | ||
39 | + object_initialize_child(obj, "pmu-cpu", &s->cpu, sizeof(s->cpu), | ||
40 | + TYPE_MICROBLAZE_CPU, &error_abort, NULL); | ||
41 | |||
42 | - object_initialize(&s->intc, sizeof(s->intc), TYPE_XLNX_PMU_IO_INTC); | ||
43 | - qdev_set_parent_bus(DEVICE(&s->intc), sysbus_get_default()); | ||
44 | + sysbus_init_child_obj(obj, "intc", &s->intc, sizeof(s->intc), | ||
45 | + TYPE_XLNX_PMU_IO_INTC); | ||
19 | } | 46 | } |
20 | 47 | ||
21 | +static TCGv_i32 read_fp_hreg(DisasContext *s, int reg) | 48 | static void xlnx_zynqmp_pmu_soc_realize(DeviceState *dev, Error **errp) |
22 | +{ | ||
23 | + TCGv_i32 v = tcg_temp_new_i32(); | ||
24 | + | ||
25 | + tcg_gen_ld16u_i32(v, cpu_env, fp_reg_offset(s, reg, MO_16)); | ||
26 | + return v; | ||
27 | +} | ||
28 | + | ||
29 | /* Clear the bits above an N-bit vector, for N = (is_q ? 128 : 64). | ||
30 | * If SVE is not enabled, then there are only 128 bits in the vector. | ||
31 | */ | ||
32 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) | ||
33 | static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) | ||
34 | { | ||
35 | TCGv_ptr fpst = NULL; | ||
36 | - TCGv_i32 tcg_op = tcg_temp_new_i32(); | ||
37 | + TCGv_i32 tcg_op = read_fp_hreg(s, rn); | ||
38 | TCGv_i32 tcg_res = tcg_temp_new_i32(); | ||
39 | |||
40 | - read_vec_element_i32(s, tcg_op, rn, 0, MO_16); | ||
41 | - | ||
42 | switch (opcode) { | ||
43 | case 0x0: /* FMOV */ | ||
44 | tcg_gen_mov_i32(tcg_res, tcg_op); | ||
45 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) | ||
46 | tcg_temp_free_i64(tcg_op2); | ||
47 | tcg_temp_free_i64(tcg_res); | ||
48 | } else { | ||
49 | - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); | ||
50 | - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); | ||
51 | + TCGv_i32 tcg_op1 = read_fp_hreg(s, rn); | ||
52 | + TCGv_i32 tcg_op2 = read_fp_hreg(s, rm); | ||
53 | TCGv_i64 tcg_res = tcg_temp_new_i64(); | ||
54 | |||
55 | - read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); | ||
56 | - read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); | ||
57 | - | ||
58 | gen_helper_neon_mull_s16(tcg_res, tcg_op1, tcg_op2); | ||
59 | gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env, tcg_res, tcg_res); | ||
60 | |||
61 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, | ||
62 | |||
63 | fpst = get_fpstatus_ptr(true); | ||
64 | |||
65 | - tcg_op1 = tcg_temp_new_i32(); | ||
66 | - tcg_op2 = tcg_temp_new_i32(); | ||
67 | + tcg_op1 = read_fp_hreg(s, rn); | ||
68 | + tcg_op2 = read_fp_hreg(s, rm); | ||
69 | tcg_res = tcg_temp_new_i32(); | ||
70 | |||
71 | - read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); | ||
72 | - read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); | ||
73 | - | ||
74 | switch (fpopcode) { | ||
75 | case 0x03: /* FMULX */ | ||
76 | gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
77 | @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) | ||
78 | } | ||
79 | |||
80 | if (is_scalar) { | ||
81 | - TCGv_i32 tcg_op = tcg_temp_new_i32(); | ||
82 | + TCGv_i32 tcg_op = read_fp_hreg(s, rn); | ||
83 | TCGv_i32 tcg_res = tcg_temp_new_i32(); | ||
84 | |||
85 | - read_vec_element_i32(s, tcg_op, rn, 0, MO_16); | ||
86 | - | ||
87 | switch (fpop) { | ||
88 | case 0x1a: /* FCVTNS */ | ||
89 | case 0x1b: /* FCVTMS */ | ||
90 | -- | 49 | -- |
91 | 2.17.0 | 50 | 2.17.1 |
92 | 51 | ||
93 | 52 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | From: Guenter Roeck <linux@roeck-us.net> |
---|---|---|---|
2 | 2 | ||
3 | Adding the fp16 moves to/from general registers. | 3 | Writes in PIO mode have two requirements: |
4 | 4 | ||
5 | Cc: qemu-stable@nongnu.org | 5 | - A data interrupt must be generated after a write command has been |
6 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 6 | issued to indicate that the chip is ready to receive data. |
7 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | 7 | - A block interrupt must be generated after each block to indicate |
8 | Message-id: 20180512003217.9105-2-richard.henderson@linaro.org | 8 | that the chip is ready to receive the next data block. |
9 | |||
10 | Rearrange the code to make this happen. Tested on raspi3 (in PIO mode) | ||
11 | and raspi2 (in DMA mode). | ||
12 | |||
13 | Signed-off-by: Guenter Roeck <linux@roeck-us.net> | ||
14 | Message-id: 1531779837-20557-1-git-send-email-linux@roeck-us.net | ||
9 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 15 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 16 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
11 | --- | 17 | --- |
12 | target/arm/translate-a64.c | 21 +++++++++++++++++++++ | 18 | hw/sd/bcm2835_sdhost.c | 20 ++++++++++++++++---- |
13 | 1 file changed, 21 insertions(+) | 19 | 1 file changed, 16 insertions(+), 4 deletions(-) |
14 | 20 | ||
15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 21 | diff --git a/hw/sd/bcm2835_sdhost.c b/hw/sd/bcm2835_sdhost.c |
16 | index XXXXXXX..XXXXXXX 100644 | 22 | index XXXXXXX..XXXXXXX 100644 |
17 | --- a/target/arm/translate-a64.c | 23 | --- a/hw/sd/bcm2835_sdhost.c |
18 | +++ b/target/arm/translate-a64.c | 24 | +++ b/hw/sd/bcm2835_sdhost.c |
19 | @@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) | 25 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_fifo_run(BCM2835SDHostState *s) |
20 | tcg_gen_st_i64(tcg_rn, cpu_env, fp_reg_hi_offset(s, rd)); | 26 | uint32_t value = 0; |
21 | clear_vec_high(s, true, rd); | 27 | int n; |
22 | break; | 28 | int is_read; |
23 | + case 3: | 29 | + int is_write; |
24 | + /* 16 bit */ | 30 | |
25 | + tmp = tcg_temp_new_i64(); | 31 | is_read = (s->cmd & SDCMD_READ_CMD) != 0; |
26 | + tcg_gen_ext16u_i64(tmp, tcg_rn); | 32 | - if (s->datacnt != 0 && (!is_read || sdbus_data_ready(&s->sdbus))) { |
27 | + write_fp_dreg(s, rd, tmp); | 33 | + is_write = (s->cmd & SDCMD_WRITE_CMD) != 0; |
28 | + tcg_temp_free_i64(tmp); | 34 | + if (s->datacnt != 0 && (is_write || sdbus_data_ready(&s->sdbus))) { |
29 | + break; | 35 | if (is_read) { |
30 | + default: | 36 | n = 0; |
31 | + g_assert_not_reached(); | 37 | while (s->datacnt && s->fifo_len < BCM2835_SDHOST_FIFO_LEN) { |
32 | } | 38 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_fifo_run(BCM2835SDHostState *s) |
33 | } else { | 39 | if (n != 0) { |
34 | TCGv_i64 tcg_rd = cpu_reg(s, rd); | 40 | bcm2835_sdhost_fifo_push(s, value); |
35 | @@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) | 41 | s->status |= SDHSTS_DATA_FLAG; |
36 | /* 64 bits from top half */ | 42 | + if (s->config & SDHCFG_DATA_IRPT_EN) { |
37 | tcg_gen_ld_i64(tcg_rd, cpu_env, fp_reg_hi_offset(s, rn)); | 43 | + s->status |= SDHSTS_SDIO_IRPT; |
38 | break; | 44 | + } |
39 | + case 3: | 45 | } |
40 | + /* 16 bit */ | 46 | - } else { /* write */ |
41 | + tcg_gen_ld16u_i64(tcg_rd, cpu_env, fp_reg_offset(s, rn, MO_16)); | 47 | + } else if (is_write) { /* write */ |
42 | + break; | 48 | n = 0; |
43 | + default: | 49 | while (s->datacnt > 0 && (s->fifo_len > 0 || n > 0)) { |
44 | + g_assert_not_reached(); | 50 | if (n == 0) { |
51 | @@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_fifo_run(BCM2835SDHostState *s) | ||
52 | s->edm &= ~SDEDM_FSM_MASK; | ||
53 | s->edm |= SDEDM_FSM_DATAMODE; | ||
54 | trace_bcm2835_sdhost_edm_change("datacnt 0", s->edm); | ||
55 | - | ||
56 | - if ((s->cmd & SDCMD_WRITE_CMD) && | ||
57 | + } | ||
58 | + if (is_write) { | ||
59 | + /* set block interrupt at end of each block transfer */ | ||
60 | + if (s->hbct && s->datacnt % s->hbct == 0 && | ||
61 | (s->config & SDHCFG_BLOCK_IRPT_EN)) { | ||
62 | s->status |= SDHSTS_BLOCK_IRPT; | ||
63 | } | ||
64 | + /* set data interrupt after each transfer */ | ||
65 | + s->status |= SDHSTS_DATA_FLAG; | ||
66 | + if (s->config & SDHCFG_DATA_IRPT_EN) { | ||
67 | + s->status |= SDHSTS_SDIO_IRPT; | ||
68 | + } | ||
45 | } | 69 | } |
46 | } | 70 | } |
47 | } | 71 | |
48 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) | ||
49 | case 0xa: /* 64 bit */ | ||
50 | case 0xd: /* 64 bit to top half of quad */ | ||
51 | break; | ||
52 | + case 0x6: /* 16-bit float, 32-bit int */ | ||
53 | + case 0xe: /* 16-bit float, 64-bit int */ | ||
54 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
55 | + break; | ||
56 | + } | ||
57 | + /* fallthru */ | ||
58 | default: | ||
59 | /* all other sf/type/rmode combinations are invalid */ | ||
60 | unallocated_encoding(s); | ||
61 | -- | 72 | -- |
62 | 2.17.0 | 73 | 2.17.1 |
63 | 74 | ||
64 | 75 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Richard Henderson <richard.henderson@linaro.org> | ||
2 | 1 | ||
3 | No sense in emitting code after the exception. | ||
4 | |||
5 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
6 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Message-id: 20180512003217.9105-3-richard.henderson@linaro.org | ||
8 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
10 | --- | ||
11 | target/arm/translate-a64.c | 2 +- | ||
12 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
13 | |||
14 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
15 | index XXXXXXX..XXXXXXX 100644 | ||
16 | --- a/target/arm/translate-a64.c | ||
17 | +++ b/target/arm/translate-a64.c | ||
18 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) | ||
19 | default: | ||
20 | /* all other sf/type/rmode combinations are invalid */ | ||
21 | unallocated_encoding(s); | ||
22 | - break; | ||
23 | + return; | ||
24 | } | ||
25 | |||
26 | if (!fp_access_check(s)) { | ||
27 | -- | ||
28 | 2.17.0 | ||
29 | |||
30 | diff view generated by jsdifflib |
1 | From: Richard Henderson <richard.henderson@linaro.org> | 1 | To correctly handle small (less than TARGET_PAGE_SIZE) MPU regions, |
---|---|---|---|
2 | we must correctly handle the case where the address being looked | ||
3 | up hits in an MPU region that is not small but the address is | ||
4 | in the same page as a small region. For instance if MPU region | ||
5 | 1 covers an entire page from 0x2000 to 0x2400 and MPU region | ||
6 | 2 is small and covers only 0x2200 to 0x2280, then for an access | ||
7 | to 0x2000 we must not return a result covering the full page | ||
8 | even though we hit the page-sized region 1. Otherwise we will | ||
9 | then cache that result in the TLB and accesses that should | ||
10 | hit region 2 will incorrectly find the region 1 information. | ||
2 | 11 | ||
3 | Cc: qemu-stable@nongnu.org | 12 | Check for the case where we miss an MPU region but it is still |
4 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | 13 | within the same page, and in that case narrow the size we will |
5 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | 14 | pass to tlb_set_page_with_attrs() for whatever the final |
6 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | 15 | outcome is of the MPU lookup. |
7 | Message-id: 20180512003217.9105-4-richard.henderson@linaro.org | 16 | |
17 | Reported-by: Adithya Baglody <adithya.nagaraj.baglody@intel.com> | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 18 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
19 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
20 | Message-id: 20180716133302.25989-1-peter.maydell@linaro.org | ||
9 | --- | 21 | --- |
10 | target/arm/helper.h | 6 +++ | 22 | target/arm/helper.c | 46 +++++++++++++++++++++++++++++++++++++++++++++ |
11 | target/arm/helper.c | 38 ++++++++++++++- | 23 | 1 file changed, 46 insertions(+) |
12 | target/arm/translate-a64.c | 96 +++++++++++++++++++++++++++++++------- | ||
13 | 3 files changed, 122 insertions(+), 18 deletions(-) | ||
14 | 24 | ||
15 | diff --git a/target/arm/helper.h b/target/arm/helper.h | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/helper.h | ||
18 | +++ b/target/arm/helper.h | ||
19 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr) | ||
20 | DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr) | ||
21 | DEF_HELPER_3(vfp_touhh, i32, f16, i32, ptr) | ||
22 | DEF_HELPER_3(vfp_toshh, i32, f16, i32, ptr) | ||
23 | +DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr) | ||
24 | +DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr) | ||
25 | +DEF_HELPER_3(vfp_touqh, i64, f16, i32, ptr) | ||
26 | +DEF_HELPER_3(vfp_tosqh, i64, f16, i32, ptr) | ||
27 | DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr) | ||
28 | DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr) | ||
29 | DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr) | ||
30 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr) | ||
31 | DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr) | ||
32 | DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr) | ||
33 | DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) | ||
34 | +DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) | ||
35 | +DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) | ||
36 | |||
37 | DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) | ||
38 | DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) | ||
39 | diff --git a/target/arm/helper.c b/target/arm/helper.c | 25 | diff --git a/target/arm/helper.c b/target/arm/helper.c |
40 | index XXXXXXX..XXXXXXX 100644 | 26 | index XXXXXXX..XXXXXXX 100644 |
41 | --- a/target/arm/helper.c | 27 | --- a/target/arm/helper.c |
42 | +++ b/target/arm/helper.c | 28 | +++ b/target/arm/helper.c |
43 | @@ -XXX,XX +XXX,XX @@ VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) | 29 | @@ -XXX,XX +XXX,XX @@ |
44 | #undef VFP_CONV_FIX_A64 | 30 | #include "exec/semihost.h" |
45 | 31 | #include "sysemu/kvm.h" | |
46 | /* Conversion to/from f16 can overflow to infinity before/after scaling. | 32 | #include "fpu/softfloat.h" |
47 | - * Therefore we convert to f64 (which does not round), scale, | 33 | +#include "qemu/range.h" |
48 | - * and then convert f64 to f16 (which may round). | 34 | |
49 | + * Therefore we convert to f64, scale, and then convert f64 to f16; or | 35 | #define ARM_CPU_FREQ 1000000000 /* FIXME: 1 GHz, should be configurable */ |
50 | + * vice versa for conversion to integer. | 36 | |
51 | + * | 37 | @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, |
52 | + * For 16- and 32-bit integers, the conversion to f64 never rounds. | ||
53 | + * For 64-bit integers, any integer that would cause rounding will also | ||
54 | + * overflow to f16 infinity, so there is no double rounding problem. | ||
55 | */ | ||
56 | |||
57 | static float16 do_postscale_fp16(float64 f, int shift, float_status *fpst) | ||
58 | @@ -XXX,XX +XXX,XX @@ float16 HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) | ||
59 | return do_postscale_fp16(uint32_to_float64(x, fpst), shift, fpst); | ||
60 | } | ||
61 | |||
62 | +float16 HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) | ||
63 | +{ | ||
64 | + return do_postscale_fp16(int64_to_float64(x, fpst), shift, fpst); | ||
65 | +} | ||
66 | + | ||
67 | +float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) | ||
68 | +{ | ||
69 | + return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst); | ||
70 | +} | ||
71 | + | ||
72 | static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst) | ||
73 | { | ||
74 | if (unlikely(float16_is_any_nan(f))) { | ||
75 | @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst) | ||
76 | return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst); | ||
77 | } | ||
78 | |||
79 | +uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst) | ||
80 | +{ | ||
81 | + return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst); | ||
82 | +} | ||
83 | + | ||
84 | +uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst) | ||
85 | +{ | ||
86 | + return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst); | ||
87 | +} | ||
88 | + | ||
89 | +uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst) | ||
90 | +{ | ||
91 | + return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst); | ||
92 | +} | ||
93 | + | ||
94 | +uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst) | ||
95 | +{ | ||
96 | + return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst); | ||
97 | +} | ||
98 | + | ||
99 | /* Set the current fp rounding mode and return the old one. | ||
100 | * The argument is a softfloat float_round_ value. | ||
101 | */ | ||
102 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
103 | index XXXXXXX..XXXXXXX 100644 | ||
104 | --- a/target/arm/translate-a64.c | ||
105 | +++ b/target/arm/translate-a64.c | ||
106 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
107 | bool itof, int rmode, int scale, int sf, int type) | ||
108 | { | ||
109 | bool is_signed = !(opcode & 1); | ||
110 | - bool is_double = type; | ||
111 | TCGv_ptr tcg_fpstatus; | ||
112 | - TCGv_i32 tcg_shift; | ||
113 | + TCGv_i32 tcg_shift, tcg_single; | ||
114 | + TCGv_i64 tcg_double; | ||
115 | |||
116 | - tcg_fpstatus = get_fpstatus_ptr(false); | ||
117 | + tcg_fpstatus = get_fpstatus_ptr(type == 3); | ||
118 | |||
119 | tcg_shift = tcg_const_i32(64 - scale); | ||
120 | |||
121 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
122 | tcg_int = tcg_extend; | ||
123 | } | ||
124 | |||
125 | - if (is_double) { | ||
126 | - TCGv_i64 tcg_double = tcg_temp_new_i64(); | ||
127 | + switch (type) { | ||
128 | + case 1: /* float64 */ | ||
129 | + tcg_double = tcg_temp_new_i64(); | ||
130 | if (is_signed) { | ||
131 | gen_helper_vfp_sqtod(tcg_double, tcg_int, | ||
132 | tcg_shift, tcg_fpstatus); | ||
133 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
134 | } | 38 | } |
135 | write_fp_dreg(s, rd, tcg_double); | 39 | |
136 | tcg_temp_free_i64(tcg_double); | 40 | if (address < base || address > base + rmask) { |
137 | - } else { | 41 | + /* |
138 | - TCGv_i32 tcg_single = tcg_temp_new_i32(); | 42 | + * Address not in this region. We must check whether the |
139 | + break; | 43 | + * region covers addresses in the same page as our address. |
140 | + | 44 | + * In that case we must not report a size that covers the |
141 | + case 0: /* float32 */ | 45 | + * whole page for a subsequent hit against a different MPU |
142 | + tcg_single = tcg_temp_new_i32(); | 46 | + * region or the background region, because it would result in |
143 | if (is_signed) { | 47 | + * incorrect TLB hits for subsequent accesses to addresses that |
144 | gen_helper_vfp_sqtos(tcg_single, tcg_int, | 48 | + * are in this MPU region. |
145 | tcg_shift, tcg_fpstatus); | 49 | + */ |
146 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | 50 | + if (ranges_overlap(base, rmask, |
51 | + address & TARGET_PAGE_MASK, | ||
52 | + TARGET_PAGE_SIZE)) { | ||
53 | + *page_size = 1; | ||
54 | + } | ||
55 | continue; | ||
147 | } | 56 | } |
148 | write_fp_sreg(s, rd, tcg_single); | 57 | |
149 | tcg_temp_free_i32(tcg_single); | 58 | @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, |
150 | + break; | 59 | sattrs->srvalid = true; |
151 | + | 60 | sattrs->sregion = r; |
152 | + case 3: /* float16 */ | 61 | } |
153 | + tcg_single = tcg_temp_new_i32(); | 62 | + } else { |
154 | + if (is_signed) { | 63 | + /* |
155 | + gen_helper_vfp_sqtoh(tcg_single, tcg_int, | 64 | + * Address not in this region. We must check whether the |
156 | + tcg_shift, tcg_fpstatus); | 65 | + * region covers addresses in the same page as our address. |
157 | + } else { | 66 | + * In that case we must not report a size that covers the |
158 | + gen_helper_vfp_uqtoh(tcg_single, tcg_int, | 67 | + * whole page for a subsequent hit against a different MPU |
159 | + tcg_shift, tcg_fpstatus); | 68 | + * region or the background region, because it would result |
160 | + } | 69 | + * in incorrect TLB hits for subsequent accesses to |
161 | + write_fp_sreg(s, rd, tcg_single); | 70 | + * addresses that are in this MPU region. |
162 | + tcg_temp_free_i32(tcg_single); | 71 | + */ |
163 | + break; | 72 | + if (limit >= base && |
164 | + | 73 | + ranges_overlap(base, limit - base + 1, |
165 | + default: | 74 | + addr_page_base, |
166 | + g_assert_not_reached(); | 75 | + TARGET_PAGE_SIZE)) { |
167 | } | 76 | + sattrs->subpage = true; |
168 | } else { | 77 | + } |
169 | TCGv_i64 tcg_int = cpu_reg(s, rd); | ||
170 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
171 | |||
172 | gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); | ||
173 | |||
174 | - if (is_double) { | ||
175 | - TCGv_i64 tcg_double = read_fp_dreg(s, rn); | ||
176 | + switch (type) { | ||
177 | + case 1: /* float64 */ | ||
178 | + tcg_double = read_fp_dreg(s, rn); | ||
179 | if (is_signed) { | ||
180 | if (!sf) { | ||
181 | gen_helper_vfp_tosld(tcg_int, tcg_double, | ||
182 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
183 | tcg_shift, tcg_fpstatus); | ||
184 | } | 78 | } |
185 | } | 79 | } |
186 | + if (!sf) { | 80 | } |
187 | + tcg_gen_ext32u_i64(tcg_int, tcg_int); | 81 | @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, |
188 | + } | ||
189 | tcg_temp_free_i64(tcg_double); | ||
190 | - } else { | ||
191 | - TCGv_i32 tcg_single = read_fp_sreg(s, rn); | ||
192 | + break; | ||
193 | + | ||
194 | + case 0: /* float32 */ | ||
195 | + tcg_single = read_fp_sreg(s, rn); | ||
196 | if (sf) { | ||
197 | if (is_signed) { | ||
198 | gen_helper_vfp_tosqs(tcg_int, tcg_single, | ||
199 | @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, | ||
200 | tcg_temp_free_i32(tcg_dest); | ||
201 | } | 82 | } |
202 | tcg_temp_free_i32(tcg_single); | 83 | |
203 | + break; | 84 | if (address < base || address > limit) { |
204 | + | 85 | + /* |
205 | + case 3: /* float16 */ | 86 | + * Address not in this region. We must check whether the |
206 | + tcg_single = read_fp_sreg(s, rn); | 87 | + * region covers addresses in the same page as our address. |
207 | + if (sf) { | 88 | + * In that case we must not report a size that covers the |
208 | + if (is_signed) { | 89 | + * whole page for a subsequent hit against a different MPU |
209 | + gen_helper_vfp_tosqh(tcg_int, tcg_single, | 90 | + * region or the background region, because it would result in |
210 | + tcg_shift, tcg_fpstatus); | 91 | + * incorrect TLB hits for subsequent accesses to addresses that |
211 | + } else { | 92 | + * are in this MPU region. |
212 | + gen_helper_vfp_touqh(tcg_int, tcg_single, | 93 | + */ |
213 | + tcg_shift, tcg_fpstatus); | 94 | + if (limit >= base && |
95 | + ranges_overlap(base, limit - base + 1, | ||
96 | + addr_page_base, | ||
97 | + TARGET_PAGE_SIZE)) { | ||
98 | + *is_subpage = true; | ||
214 | + } | 99 | + } |
215 | + } else { | 100 | continue; |
216 | + TCGv_i32 tcg_dest = tcg_temp_new_i32(); | 101 | } |
217 | + if (is_signed) { | 102 | |
218 | + gen_helper_vfp_toslh(tcg_dest, tcg_single, | ||
219 | + tcg_shift, tcg_fpstatus); | ||
220 | + } else { | ||
221 | + gen_helper_vfp_toulh(tcg_dest, tcg_single, | ||
222 | + tcg_shift, tcg_fpstatus); | ||
223 | + } | ||
224 | + tcg_gen_extu_i32_i64(tcg_int, tcg_dest); | ||
225 | + tcg_temp_free_i32(tcg_dest); | ||
226 | + } | ||
227 | + tcg_temp_free_i32(tcg_single); | ||
228 | + break; | ||
229 | + | ||
230 | + default: | ||
231 | + g_assert_not_reached(); | ||
232 | } | ||
233 | |||
234 | gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); | ||
235 | tcg_temp_free_i32(tcg_rmode); | ||
236 | - | ||
237 | - if (!sf) { | ||
238 | - tcg_gen_ext32u_i64(tcg_int, tcg_int); | ||
239 | - } | ||
240 | } | ||
241 | |||
242 | tcg_temp_free_ptr(tcg_fpstatus); | ||
243 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) | ||
244 | /* actual FP conversions */ | ||
245 | bool itof = extract32(opcode, 1, 1); | ||
246 | |||
247 | - if (type > 1 || (rmode != 0 && opcode > 1)) { | ||
248 | + if (rmode != 0 && opcode > 1) { | ||
249 | + unallocated_encoding(s); | ||
250 | + return; | ||
251 | + } | ||
252 | + switch (type) { | ||
253 | + case 0: /* float32 */ | ||
254 | + case 1: /* float64 */ | ||
255 | + break; | ||
256 | + case 3: /* float16 */ | ||
257 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
258 | + break; | ||
259 | + } | ||
260 | + /* fallthru */ | ||
261 | + default: | ||
262 | unallocated_encoding(s); | ||
263 | return; | ||
264 | } | ||
265 | -- | 103 | -- |
266 | 2.17.0 | 104 | 2.17.1 |
267 | 105 | ||
268 | 106 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Richard Henderson <richard.henderson@linaro.org> | ||
2 | 1 | ||
3 | Cc: qemu-stable@nongnu.org | ||
4 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
5 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
6 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Message-id: 20180512003217.9105-5-richard.henderson@linaro.org | ||
8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
9 | --- | ||
10 | target/arm/translate-a64.c | 17 +++++++++++++++-- | ||
11 | 1 file changed, 15 insertions(+), 2 deletions(-) | ||
12 | |||
13 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
14 | index XXXXXXX..XXXXXXX 100644 | ||
15 | --- a/target/arm/translate-a64.c | ||
16 | +++ b/target/arm/translate-a64.c | ||
17 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_fixed_conv(DisasContext *s, uint32_t insn) | ||
18 | bool sf = extract32(insn, 31, 1); | ||
19 | bool itof; | ||
20 | |||
21 | - if (sbit || (type > 1) | ||
22 | - || (!sf && scale < 32)) { | ||
23 | + if (sbit || (!sf && scale < 32)) { | ||
24 | + unallocated_encoding(s); | ||
25 | + return; | ||
26 | + } | ||
27 | + | ||
28 | + switch (type) { | ||
29 | + case 0: /* float32 */ | ||
30 | + case 1: /* float64 */ | ||
31 | + break; | ||
32 | + case 3: /* float16 */ | ||
33 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
34 | + break; | ||
35 | + } | ||
36 | + /* fallthru */ | ||
37 | + default: | ||
38 | unallocated_encoding(s); | ||
39 | return; | ||
40 | } | ||
41 | -- | ||
42 | 2.17.0 | ||
43 | |||
44 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Richard Henderson <richard.henderson@linaro.org> | ||
2 | 1 | ||
3 | We missed all of the scalar fp16 binary operations. | ||
4 | |||
5 | Cc: qemu-stable@nongnu.org | ||
6 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Message-id: 20180512003217.9105-7-richard.henderson@linaro.org | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | target/arm/translate-a64.c | 65 ++++++++++++++++++++++++++++++++++++++ | ||
13 | 1 file changed, 65 insertions(+) | ||
14 | |||
15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/translate-a64.c | ||
18 | +++ b/target/arm/translate-a64.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_double(DisasContext *s, int opcode, | ||
20 | tcg_temp_free_i64(tcg_res); | ||
21 | } | ||
22 | |||
23 | +/* Floating-point data-processing (2 source) - half precision */ | ||
24 | +static void handle_fp_2src_half(DisasContext *s, int opcode, | ||
25 | + int rd, int rn, int rm) | ||
26 | +{ | ||
27 | + TCGv_i32 tcg_op1; | ||
28 | + TCGv_i32 tcg_op2; | ||
29 | + TCGv_i32 tcg_res; | ||
30 | + TCGv_ptr fpst; | ||
31 | + | ||
32 | + tcg_res = tcg_temp_new_i32(); | ||
33 | + fpst = get_fpstatus_ptr(true); | ||
34 | + tcg_op1 = read_fp_hreg(s, rn); | ||
35 | + tcg_op2 = read_fp_hreg(s, rm); | ||
36 | + | ||
37 | + switch (opcode) { | ||
38 | + case 0x0: /* FMUL */ | ||
39 | + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
40 | + break; | ||
41 | + case 0x1: /* FDIV */ | ||
42 | + gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
43 | + break; | ||
44 | + case 0x2: /* FADD */ | ||
45 | + gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
46 | + break; | ||
47 | + case 0x3: /* FSUB */ | ||
48 | + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
49 | + break; | ||
50 | + case 0x4: /* FMAX */ | ||
51 | + gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
52 | + break; | ||
53 | + case 0x5: /* FMIN */ | ||
54 | + gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
55 | + break; | ||
56 | + case 0x6: /* FMAXNM */ | ||
57 | + gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
58 | + break; | ||
59 | + case 0x7: /* FMINNM */ | ||
60 | + gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
61 | + break; | ||
62 | + case 0x8: /* FNMUL */ | ||
63 | + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); | ||
64 | + tcg_gen_xori_i32(tcg_res, tcg_res, 0x8000); | ||
65 | + break; | ||
66 | + default: | ||
67 | + g_assert_not_reached(); | ||
68 | + } | ||
69 | + | ||
70 | + write_fp_sreg(s, rd, tcg_res); | ||
71 | + | ||
72 | + tcg_temp_free_ptr(fpst); | ||
73 | + tcg_temp_free_i32(tcg_op1); | ||
74 | + tcg_temp_free_i32(tcg_op2); | ||
75 | + tcg_temp_free_i32(tcg_res); | ||
76 | +} | ||
77 | + | ||
78 | /* Floating point data-processing (2 source) | ||
79 | * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 | ||
80 | * +---+---+---+-----------+------+---+------+--------+-----+------+------+ | ||
81 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn) | ||
82 | } | ||
83 | handle_fp_2src_double(s, opcode, rd, rn, rm); | ||
84 | break; | ||
85 | + case 3: | ||
86 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
87 | + unallocated_encoding(s); | ||
88 | + return; | ||
89 | + } | ||
90 | + if (!fp_access_check(s)) { | ||
91 | + return; | ||
92 | + } | ||
93 | + handle_fp_2src_half(s, opcode, rd, rn, rm); | ||
94 | + break; | ||
95 | default: | ||
96 | unallocated_encoding(s); | ||
97 | } | ||
98 | -- | ||
99 | 2.17.0 | ||
100 | |||
101 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Richard Henderson <richard.henderson@linaro.org> | ||
2 | 1 | ||
3 | We missed all of the scalar fp16 fma operations. | ||
4 | |||
5 | Cc: qemu-stable@nongnu.org | ||
6 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Message-id: 20180512003217.9105-8-richard.henderson@linaro.org | ||
10 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
11 | --- | ||
12 | target/arm/translate-a64.c | 48 ++++++++++++++++++++++++++++++++++++++ | ||
13 | 1 file changed, 48 insertions(+) | ||
14 | |||
15 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
16 | index XXXXXXX..XXXXXXX 100644 | ||
17 | --- a/target/arm/translate-a64.c | ||
18 | +++ b/target/arm/translate-a64.c | ||
19 | @@ -XXX,XX +XXX,XX @@ static void handle_fp_3src_double(DisasContext *s, bool o0, bool o1, | ||
20 | tcg_temp_free_i64(tcg_res); | ||
21 | } | ||
22 | |||
23 | +/* Floating-point data-processing (3 source) - half precision */ | ||
24 | +static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1, | ||
25 | + int rd, int rn, int rm, int ra) | ||
26 | +{ | ||
27 | + TCGv_i32 tcg_op1, tcg_op2, tcg_op3; | ||
28 | + TCGv_i32 tcg_res = tcg_temp_new_i32(); | ||
29 | + TCGv_ptr fpst = get_fpstatus_ptr(true); | ||
30 | + | ||
31 | + tcg_op1 = read_fp_hreg(s, rn); | ||
32 | + tcg_op2 = read_fp_hreg(s, rm); | ||
33 | + tcg_op3 = read_fp_hreg(s, ra); | ||
34 | + | ||
35 | + /* These are fused multiply-add, and must be done as one | ||
36 | + * floating point operation with no rounding between the | ||
37 | + * multiplication and addition steps. | ||
38 | + * NB that doing the negations here as separate steps is | ||
39 | + * correct : an input NaN should come out with its sign bit | ||
40 | + * flipped if it is a negated-input. | ||
41 | + */ | ||
42 | + if (o1 == true) { | ||
43 | + tcg_gen_xori_i32(tcg_op3, tcg_op3, 0x8000); | ||
44 | + } | ||
45 | + | ||
46 | + if (o0 != o1) { | ||
47 | + tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); | ||
48 | + } | ||
49 | + | ||
50 | + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); | ||
51 | + | ||
52 | + write_fp_sreg(s, rd, tcg_res); | ||
53 | + | ||
54 | + tcg_temp_free_ptr(fpst); | ||
55 | + tcg_temp_free_i32(tcg_op1); | ||
56 | + tcg_temp_free_i32(tcg_op2); | ||
57 | + tcg_temp_free_i32(tcg_op3); | ||
58 | + tcg_temp_free_i32(tcg_res); | ||
59 | +} | ||
60 | + | ||
61 | /* Floating point data-processing (3 source) | ||
62 | * 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0 | ||
63 | * +---+---+---+-----------+------+----+------+----+------+------+------+ | ||
64 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) | ||
65 | } | ||
66 | handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra); | ||
67 | break; | ||
68 | + case 3: | ||
69 | + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
70 | + unallocated_encoding(s); | ||
71 | + return; | ||
72 | + } | ||
73 | + if (!fp_access_check(s)) { | ||
74 | + return; | ||
75 | + } | ||
76 | + handle_fp_3src_half(s, o0, o1, rd, rn, rm, ra); | ||
77 | + break; | ||
78 | default: | ||
79 | unallocated_encoding(s); | ||
80 | } | ||
81 | -- | ||
82 | 2.17.0 | ||
83 | |||
84 | diff view generated by jsdifflib |
1 | From: Philippe Mathieu-Daudé <f4bug@amsat.org> | 1 | From: Thomas Huth <thuth@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | Per the Physical Layer Simplified Spec. "4.3.10.4 Switch Function Status": | 3 | nand_init() does not only create the NAND device, it also realizes |
4 | the device with qdev_init_nofail() already. So we must not call | ||
5 | nand_init() from an instance_init function like sl_nand_init(), | ||
6 | otherwise we get superfluous NAND devices in the QOM tree after | ||
7 | introspecting the 'sl-nand' device. So move the nand_init() to the | ||
8 | realize function of 'sl-nand' instead. | ||
4 | 9 | ||
5 | The block length is predefined to 512 bits | 10 | Signed-off-by: Thomas Huth <thuth@redhat.com> |
6 | 11 | Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | |
7 | and "4.10.2 SD Status": | 12 | Message-id: 1532006134-7701-1-git-send-email-thuth@redhat.com |
8 | |||
9 | The SD Status contains status bits that are related to the SD Memory Card | ||
10 | proprietary features and may be used for future application-specific usage. | ||
11 | The size of the SD Status is one data block of 512 bit. The content of this | ||
12 | register is transmitted to the Host over the DAT bus along with a 16-bit CRC. | ||
13 | |||
14 | Thus the 16-bit CRC goes at offset 64. | ||
15 | |||
16 | Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> | ||
17 | Message-id: 20180509060104.4458-3-f4bug@amsat.org | ||
18 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
19 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
20 | --- | 15 | --- |
21 | hw/sd/sd.c | 2 +- | 16 | hw/arm/spitz.c | 15 +++++++++++---- |
22 | 1 file changed, 1 insertion(+), 1 deletion(-) | 17 | 1 file changed, 11 insertions(+), 4 deletions(-) |
23 | 18 | ||
24 | diff --git a/hw/sd/sd.c b/hw/sd/sd.c | 19 | diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c |
25 | index XXXXXXX..XXXXXXX 100644 | 20 | index XXXXXXX..XXXXXXX 100644 |
26 | --- a/hw/sd/sd.c | 21 | --- a/hw/arm/spitz.c |
27 | +++ b/hw/sd/sd.c | 22 | +++ b/hw/arm/spitz.c |
28 | @@ -XXX,XX +XXX,XX @@ static void sd_function_switch(SDState *sd, uint32_t arg) | 23 | @@ -XXX,XX +XXX,XX @@ static void sl_nand_init(Object *obj) |
29 | sd->data[14 + (i >> 1)] = new_func << ((i * 4) & 4); | 24 | { |
30 | } | 25 | SLNANDState *s = SL_NAND(obj); |
31 | memset(&sd->data[17], 0, 47); | 26 | SysBusDevice *dev = SYS_BUS_DEVICE(obj); |
32 | - stw_be_p(sd->data + 65, sd_crc16(sd->data, 64)); | 27 | - DriveInfo *nand; |
33 | + stw_be_p(sd->data + 64, sd_crc16(sd->data, 64)); | 28 | |
29 | s->ctl = 0; | ||
30 | + | ||
31 | + memory_region_init_io(&s->iomem, obj, &sl_ops, s, "sl", 0x40); | ||
32 | + sysbus_init_mmio(dev, &s->iomem); | ||
33 | +} | ||
34 | + | ||
35 | +static void sl_nand_realize(DeviceState *dev, Error **errp) | ||
36 | +{ | ||
37 | + SLNANDState *s = SL_NAND(dev); | ||
38 | + DriveInfo *nand; | ||
39 | + | ||
40 | /* FIXME use a qdev drive property instead of drive_get() */ | ||
41 | nand = drive_get(IF_MTD, 0, 0); | ||
42 | s->nand = nand_init(nand ? blk_by_legacy_dinfo(nand) : NULL, | ||
43 | s->manf_id, s->chip_id); | ||
44 | - | ||
45 | - memory_region_init_io(&s->iomem, obj, &sl_ops, s, "sl", 0x40); | ||
46 | - sysbus_init_mmio(dev, &s->iomem); | ||
34 | } | 47 | } |
35 | 48 | ||
36 | static inline bool sd_wp_addr(SDState *sd, uint64_t addr) | 49 | /* Spitz Keyboard */ |
50 | @@ -XXX,XX +XXX,XX @@ static void sl_nand_class_init(ObjectClass *klass, void *data) | ||
51 | |||
52 | dc->vmsd = &vmstate_sl_nand_info; | ||
53 | dc->props = sl_nand_properties; | ||
54 | + dc->realize = sl_nand_realize; | ||
55 | /* Reason: init() method uses drive_get() */ | ||
56 | dc->user_creatable = false; | ||
57 | } | ||
37 | -- | 58 | -- |
38 | 2.17.0 | 59 | 2.17.1 |
39 | 60 | ||
40 | 61 | diff view generated by jsdifflib |
1 | From: Alex Bennée <alex.bennee@linaro.org> | 1 | From: Thomas Huth <thuth@redhat.com> |
---|---|---|---|
2 | 2 | ||
3 | These where missed out from the rest of the half-precision work. | 3 | The instance_init function of the "exynos4210.gic" device creates a |
4 | new "arm_gic" device and immediately realizes it with qdev_init_nofail(). | ||
5 | This will leave a lot of object in the QOM tree during introspection of | ||
6 | the "exynos4210.gic" device, e.g. reproducible by starting QEMU like this: | ||
4 | 7 | ||
5 | Cc: qemu-stable@nongnu.org | 8 | qemu-system-aarch64 -M none -nodefaults -nographic -monitor stdio |
9 | |||
10 | And then by running "info qom-tree" at the HMP monitor, followed by | ||
11 | "device_add exynos4210.gic,help" and finally checking "info qom-tree" | ||
12 | again. | ||
13 | |||
14 | Also note that qdev_init_nofail() can exit QEMU in case of errors - and | ||
15 | this must never happen during an instance_init function, otherwise QEMU | ||
16 | could terminate unexpectedly during introspection of a device. | ||
17 | |||
18 | Since most of the code that follows the qdev_init_nofail() depends on | ||
19 | the realized "gicbusdev", the easiest solution to the problem is to | ||
20 | turn the whole instance_init function into a realize function instead. | ||
21 | |||
22 | Signed-off-by: Thomas Huth <thuth@redhat.com> | ||
23 | Message-id: 1532337784-334-1-git-send-email-thuth@redhat.com | ||
6 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> |
7 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | ||
8 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
10 | Message-id: 20180512003217.9105-9-richard.henderson@linaro.org | ||
11 | [rth: Diagnose lack of FP16 before fp_access_check] | ||
12 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 25 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
14 | --- | 26 | --- |
15 | target/arm/helper-a64.h | 2 + | 27 | hw/intc/exynos4210_gic.c | 6 +++--- |
16 | target/arm/helper-a64.c | 10 +++++ | 28 | 1 file changed, 3 insertions(+), 3 deletions(-) |
17 | target/arm/translate-a64.c | 88 ++++++++++++++++++++++++++++++-------- | ||
18 | 3 files changed, 83 insertions(+), 17 deletions(-) | ||
19 | 29 | ||
20 | diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h | 30 | diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c |
21 | index XXXXXXX..XXXXXXX 100644 | 31 | index XXXXXXX..XXXXXXX 100644 |
22 | --- a/target/arm/helper-a64.h | 32 | --- a/hw/intc/exynos4210_gic.c |
23 | +++ b/target/arm/helper-a64.h | 33 | +++ b/hw/intc/exynos4210_gic.c |
24 | @@ -XXX,XX +XXX,XX @@ | 34 | @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_set_irq(void *opaque, int irq, int level) |
25 | DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64) | 35 | qemu_set_irq(qdev_get_gpio_in(s->gic, irq), level); |
26 | DEF_HELPER_FLAGS_2(sdiv64, TCG_CALL_NO_RWG_SE, s64, s64, s64) | ||
27 | DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64) | ||
28 | +DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr) | ||
29 | +DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr) | ||
30 | DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) | ||
31 | DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) | ||
32 | DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) | ||
33 | diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c | ||
34 | index XXXXXXX..XXXXXXX 100644 | ||
35 | --- a/target/arm/helper-a64.c | ||
36 | +++ b/target/arm/helper-a64.c | ||
37 | @@ -XXX,XX +XXX,XX @@ static inline uint32_t float_rel_to_flags(int res) | ||
38 | return flags; | ||
39 | } | 36 | } |
40 | 37 | ||
41 | +uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status) | 38 | -static void exynos4210_gic_init(Object *obj) |
42 | +{ | 39 | +static void exynos4210_gic_realize(DeviceState *dev, Error **errp) |
43 | + return float_rel_to_flags(float16_compare_quiet(x, y, fp_status)); | ||
44 | +} | ||
45 | + | ||
46 | +uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status) | ||
47 | +{ | ||
48 | + return float_rel_to_flags(float16_compare(x, y, fp_status)); | ||
49 | +} | ||
50 | + | ||
51 | uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, void *fp_status) | ||
52 | { | 40 | { |
53 | return float_rel_to_flags(float32_compare_quiet(x, y, fp_status)); | 41 | - DeviceState *dev = DEVICE(obj); |
54 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | 42 | + Object *obj = OBJECT(dev); |
55 | index XXXXXXX..XXXXXXX 100644 | 43 | Exynos4210GicState *s = EXYNOS4210_GIC(obj); |
56 | --- a/target/arm/translate-a64.c | 44 | SysBusDevice *sbd = SYS_BUS_DEVICE(obj); |
57 | +++ b/target/arm/translate-a64.c | 45 | const char cpu_prefix[] = "exynos4210-gic-alias_cpu"; |
58 | @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) | 46 | @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_class_init(ObjectClass *klass, void *data) |
59 | } | 47 | DeviceClass *dc = DEVICE_CLASS(klass); |
48 | |||
49 | dc->props = exynos4210_gic_properties; | ||
50 | + dc->realize = exynos4210_gic_realize; | ||
60 | } | 51 | } |
61 | 52 | ||
62 | -static void handle_fp_compare(DisasContext *s, bool is_double, | 53 | static const TypeInfo exynos4210_gic_info = { |
63 | +static void handle_fp_compare(DisasContext *s, int size, | 54 | .name = TYPE_EXYNOS4210_GIC, |
64 | unsigned int rn, unsigned int rm, | 55 | .parent = TYPE_SYS_BUS_DEVICE, |
65 | bool cmp_with_zero, bool signal_all_nans) | 56 | .instance_size = sizeof(Exynos4210GicState), |
66 | { | 57 | - .instance_init = exynos4210_gic_init, |
67 | TCGv_i64 tcg_flags = tcg_temp_new_i64(); | 58 | .class_init = exynos4210_gic_class_init, |
68 | - TCGv_ptr fpst = get_fpstatus_ptr(false); | 59 | }; |
69 | + TCGv_ptr fpst = get_fpstatus_ptr(size == MO_16); | 60 | |
70 | |||
71 | - if (is_double) { | ||
72 | + if (size == MO_64) { | ||
73 | TCGv_i64 tcg_vn, tcg_vm; | ||
74 | |||
75 | tcg_vn = read_fp_dreg(s, rn); | ||
76 | @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, | ||
77 | tcg_temp_free_i64(tcg_vn); | ||
78 | tcg_temp_free_i64(tcg_vm); | ||
79 | } else { | ||
80 | - TCGv_i32 tcg_vn, tcg_vm; | ||
81 | + TCGv_i32 tcg_vn = tcg_temp_new_i32(); | ||
82 | + TCGv_i32 tcg_vm = tcg_temp_new_i32(); | ||
83 | |||
84 | - tcg_vn = read_fp_sreg(s, rn); | ||
85 | + read_vec_element_i32(s, tcg_vn, rn, 0, size); | ||
86 | if (cmp_with_zero) { | ||
87 | - tcg_vm = tcg_const_i32(0); | ||
88 | + tcg_gen_movi_i32(tcg_vm, 0); | ||
89 | } else { | ||
90 | - tcg_vm = read_fp_sreg(s, rm); | ||
91 | + read_vec_element_i32(s, tcg_vm, rm, 0, size); | ||
92 | } | ||
93 | - if (signal_all_nans) { | ||
94 | - gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
95 | - } else { | ||
96 | - gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
97 | + | ||
98 | + switch (size) { | ||
99 | + case MO_32: | ||
100 | + if (signal_all_nans) { | ||
101 | + gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
102 | + } else { | ||
103 | + gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
104 | + } | ||
105 | + break; | ||
106 | + case MO_16: | ||
107 | + if (signal_all_nans) { | ||
108 | + gen_helper_vfp_cmpeh_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
109 | + } else { | ||
110 | + gen_helper_vfp_cmph_a64(tcg_flags, tcg_vn, tcg_vm, fpst); | ||
111 | + } | ||
112 | + break; | ||
113 | + default: | ||
114 | + g_assert_not_reached(); | ||
115 | } | ||
116 | + | ||
117 | tcg_temp_free_i32(tcg_vn); | ||
118 | tcg_temp_free_i32(tcg_vm); | ||
119 | } | ||
120 | @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, | ||
121 | static void disas_fp_compare(DisasContext *s, uint32_t insn) | ||
122 | { | ||
123 | unsigned int mos, type, rm, op, rn, opc, op2r; | ||
124 | + int size; | ||
125 | |||
126 | mos = extract32(insn, 29, 3); | ||
127 | - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ | ||
128 | + type = extract32(insn, 22, 2); | ||
129 | rm = extract32(insn, 16, 5); | ||
130 | op = extract32(insn, 14, 2); | ||
131 | rn = extract32(insn, 5, 5); | ||
132 | opc = extract32(insn, 3, 2); | ||
133 | op2r = extract32(insn, 0, 3); | ||
134 | |||
135 | - if (mos || op || op2r || type > 1) { | ||
136 | + if (mos || op || op2r) { | ||
137 | + unallocated_encoding(s); | ||
138 | + return; | ||
139 | + } | ||
140 | + | ||
141 | + switch (type) { | ||
142 | + case 0: | ||
143 | + size = MO_32; | ||
144 | + break; | ||
145 | + case 1: | ||
146 | + size = MO_64; | ||
147 | + break; | ||
148 | + case 3: | ||
149 | + size = MO_16; | ||
150 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
151 | + break; | ||
152 | + } | ||
153 | + /* fallthru */ | ||
154 | + default: | ||
155 | unallocated_encoding(s); | ||
156 | return; | ||
157 | } | ||
158 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_compare(DisasContext *s, uint32_t insn) | ||
159 | return; | ||
160 | } | ||
161 | |||
162 | - handle_fp_compare(s, type, rn, rm, opc & 1, opc & 2); | ||
163 | + handle_fp_compare(s, size, rn, rm, opc & 1, opc & 2); | ||
164 | } | ||
165 | |||
166 | /* Floating point conditional compare | ||
167 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) | ||
168 | unsigned int mos, type, rm, cond, rn, op, nzcv; | ||
169 | TCGv_i64 tcg_flags; | ||
170 | TCGLabel *label_continue = NULL; | ||
171 | + int size; | ||
172 | |||
173 | mos = extract32(insn, 29, 3); | ||
174 | - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ | ||
175 | + type = extract32(insn, 22, 2); | ||
176 | rm = extract32(insn, 16, 5); | ||
177 | cond = extract32(insn, 12, 4); | ||
178 | rn = extract32(insn, 5, 5); | ||
179 | op = extract32(insn, 4, 1); | ||
180 | nzcv = extract32(insn, 0, 4); | ||
181 | |||
182 | - if (mos || type > 1) { | ||
183 | + if (mos) { | ||
184 | + unallocated_encoding(s); | ||
185 | + return; | ||
186 | + } | ||
187 | + | ||
188 | + switch (type) { | ||
189 | + case 0: | ||
190 | + size = MO_32; | ||
191 | + break; | ||
192 | + case 1: | ||
193 | + size = MO_64; | ||
194 | + break; | ||
195 | + case 3: | ||
196 | + size = MO_16; | ||
197 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
198 | + break; | ||
199 | + } | ||
200 | + /* fallthru */ | ||
201 | + default: | ||
202 | unallocated_encoding(s); | ||
203 | return; | ||
204 | } | ||
205 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) | ||
206 | gen_set_label(label_match); | ||
207 | } | ||
208 | |||
209 | - handle_fp_compare(s, type, rn, rm, false, op); | ||
210 | + handle_fp_compare(s, size, rn, rm, false, op); | ||
211 | |||
212 | if (cond < 0x0e) { | ||
213 | gen_set_label(label_continue); | ||
214 | -- | 61 | -- |
215 | 2.17.0 | 62 | 2.17.1 |
216 | 63 | ||
217 | 64 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Alex Bennée <alex.bennee@linaro.org> | ||
2 | 1 | ||
3 | These were missed out from the rest of the half-precision work. | ||
4 | |||
5 | Cc: qemu-stable@nongnu.org | ||
6 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
7 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | ||
8 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
10 | Message-id: 20180512003217.9105-10-richard.henderson@linaro.org | ||
11 | [rth: Fix erroneous check vs type] | ||
12 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
13 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
14 | --- | ||
15 | target/arm/translate-a64.c | 31 +++++++++++++++++++++++++------ | ||
16 | 1 file changed, 25 insertions(+), 6 deletions(-) | ||
17 | |||
18 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
19 | index XXXXXXX..XXXXXXX 100644 | ||
20 | --- a/target/arm/translate-a64.c | ||
21 | +++ b/target/arm/translate-a64.c | ||
22 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) | ||
23 | unsigned int mos, type, rm, cond, rn, rd; | ||
24 | TCGv_i64 t_true, t_false, t_zero; | ||
25 | DisasCompare64 c; | ||
26 | + TCGMemOp sz; | ||
27 | |||
28 | mos = extract32(insn, 29, 3); | ||
29 | - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ | ||
30 | + type = extract32(insn, 22, 2); | ||
31 | rm = extract32(insn, 16, 5); | ||
32 | cond = extract32(insn, 12, 4); | ||
33 | rn = extract32(insn, 5, 5); | ||
34 | rd = extract32(insn, 0, 5); | ||
35 | |||
36 | - if (mos || type > 1) { | ||
37 | + if (mos) { | ||
38 | + unallocated_encoding(s); | ||
39 | + return; | ||
40 | + } | ||
41 | + | ||
42 | + switch (type) { | ||
43 | + case 0: | ||
44 | + sz = MO_32; | ||
45 | + break; | ||
46 | + case 1: | ||
47 | + sz = MO_64; | ||
48 | + break; | ||
49 | + case 3: | ||
50 | + sz = MO_16; | ||
51 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
52 | + break; | ||
53 | + } | ||
54 | + /* fallthru */ | ||
55 | + default: | ||
56 | unallocated_encoding(s); | ||
57 | return; | ||
58 | } | ||
59 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) | ||
60 | return; | ||
61 | } | ||
62 | |||
63 | - /* Zero extend sreg inputs to 64 bits now. */ | ||
64 | + /* Zero extend sreg & hreg inputs to 64 bits now. */ | ||
65 | t_true = tcg_temp_new_i64(); | ||
66 | t_false = tcg_temp_new_i64(); | ||
67 | - read_vec_element(s, t_true, rn, 0, type ? MO_64 : MO_32); | ||
68 | - read_vec_element(s, t_false, rm, 0, type ? MO_64 : MO_32); | ||
69 | + read_vec_element(s, t_true, rn, 0, sz); | ||
70 | + read_vec_element(s, t_false, rm, 0, sz); | ||
71 | |||
72 | a64_test_cc(&c, cond); | ||
73 | t_zero = tcg_const_i64(0); | ||
74 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) | ||
75 | tcg_temp_free_i64(t_false); | ||
76 | a64_free_cc(&c); | ||
77 | |||
78 | - /* Note that sregs write back zeros to the high bits, | ||
79 | + /* Note that sregs & hregs write back zeros to the high bits, | ||
80 | and we've already done the zero-extension. */ | ||
81 | write_fp_dreg(s, rd, t_true); | ||
82 | tcg_temp_free_i64(t_true); | ||
83 | -- | ||
84 | 2.17.0 | ||
85 | |||
86 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Alex Bennée <alex.bennee@linaro.org> | ||
2 | 1 | ||
3 | All the hard work is already done by vfp_expand_imm, we just need to | ||
4 | make sure we pick up the correct size. | ||
5 | |||
6 | Cc: qemu-stable@nongnu.org | ||
7 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
8 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | ||
9 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
10 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
11 | Message-id: 20180512003217.9105-11-richard.henderson@linaro.org | ||
12 | [rth: Merge unallocated_encoding check with TCGMemOp conversion.] | ||
13 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
15 | --- | ||
16 | target/arm/translate-a64.c | 20 +++++++++++++++++--- | ||
17 | 1 file changed, 17 insertions(+), 3 deletions(-) | ||
18 | |||
19 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
20 | index XXXXXXX..XXXXXXX 100644 | ||
21 | --- a/target/arm/translate-a64.c | ||
22 | +++ b/target/arm/translate-a64.c | ||
23 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_imm(DisasContext *s, uint32_t insn) | ||
24 | { | ||
25 | int rd = extract32(insn, 0, 5); | ||
26 | int imm8 = extract32(insn, 13, 8); | ||
27 | - int is_double = extract32(insn, 22, 2); | ||
28 | + int type = extract32(insn, 22, 2); | ||
29 | uint64_t imm; | ||
30 | TCGv_i64 tcg_res; | ||
31 | + TCGMemOp sz; | ||
32 | |||
33 | - if (is_double > 1) { | ||
34 | + switch (type) { | ||
35 | + case 0: | ||
36 | + sz = MO_32; | ||
37 | + break; | ||
38 | + case 1: | ||
39 | + sz = MO_64; | ||
40 | + break; | ||
41 | + case 3: | ||
42 | + sz = MO_16; | ||
43 | + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { | ||
44 | + break; | ||
45 | + } | ||
46 | + /* fallthru */ | ||
47 | + default: | ||
48 | unallocated_encoding(s); | ||
49 | return; | ||
50 | } | ||
51 | @@ -XXX,XX +XXX,XX @@ static void disas_fp_imm(DisasContext *s, uint32_t insn) | ||
52 | return; | ||
53 | } | ||
54 | |||
55 | - imm = vfp_expand_imm(MO_32 + is_double, imm8); | ||
56 | + imm = vfp_expand_imm(sz, imm8); | ||
57 | |||
58 | tcg_res = tcg_const_i64(imm); | ||
59 | write_fp_dreg(s, rd, tcg_res); | ||
60 | -- | ||
61 | 2.17.0 | ||
62 | |||
63 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | From: Alex Bennée <alex.bennee@linaro.org> | ||
2 | 1 | ||
3 | We are meant to explicitly pass fpst, not cpu_env. | ||
4 | |||
5 | Cc: qemu-stable@nongnu.org | ||
6 | Signed-off-by: Alex Bennée <alex.bennee@linaro.org> | ||
7 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
8 | Signed-off-by: Richard Henderson <richard.henderson@linaro.org> | ||
9 | Tested-by: Alex Bennée <alex.bennee@linaro.org> | ||
10 | Message-id: 20180512003217.9105-12-richard.henderson@linaro.org | ||
11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
12 | --- | ||
13 | target/arm/translate-a64.c | 3 ++- | ||
14 | 1 file changed, 2 insertions(+), 1 deletion(-) | ||
15 | |||
16 | diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/target/arm/translate-a64.c | ||
19 | +++ b/target/arm/translate-a64.c | ||
20 | @@ -XXX,XX +XXX,XX @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) | ||
21 | tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); | ||
22 | break; | ||
23 | case 0x3: /* FSQRT */ | ||
24 | - gen_helper_sqrt_f16(tcg_res, tcg_op, cpu_env); | ||
25 | + fpst = get_fpstatus_ptr(true); | ||
26 | + gen_helper_sqrt_f16(tcg_res, tcg_op, fpst); | ||
27 | break; | ||
28 | case 0x8: /* FRINTN */ | ||
29 | case 0x9: /* FRINTP */ | ||
30 | -- | ||
31 | 2.17.0 | ||
32 | |||
33 | diff view generated by jsdifflib |
Deleted patch | |||
---|---|---|---|
1 | Usually the logging of the CPU state produced by -d cpu is sufficient | ||
2 | to diagnose problems, but sometimes you want to see the state of | ||
3 | the floating point registers as well. We don't want to enable that | ||
4 | by default as it adds a lot of extra data to the log; instead, | ||
5 | allow it to be optionally enabled via -d fpu. | ||
6 | 1 | ||
7 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
8 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
9 | Message-id: 20180510130024.31678-1-peter.maydell@linaro.org | ||
10 | --- | ||
11 | include/qemu/log.h | 1 + | ||
12 | accel/tcg/cpu-exec.c | 9 ++++++--- | ||
13 | util/log.c | 2 ++ | ||
14 | 3 files changed, 9 insertions(+), 3 deletions(-) | ||
15 | |||
16 | diff --git a/include/qemu/log.h b/include/qemu/log.h | ||
17 | index XXXXXXX..XXXXXXX 100644 | ||
18 | --- a/include/qemu/log.h | ||
19 | +++ b/include/qemu/log.h | ||
20 | @@ -XXX,XX +XXX,XX @@ static inline bool qemu_log_separate(void) | ||
21 | #define CPU_LOG_PAGE (1 << 14) | ||
22 | /* LOG_TRACE (1 << 15) is defined in log-for-trace.h */ | ||
23 | #define CPU_LOG_TB_OP_IND (1 << 16) | ||
24 | +#define CPU_LOG_TB_FPU (1 << 17) | ||
25 | |||
26 | /* Lock output for a series of related logs. Since this is not needed | ||
27 | * for a single qemu_log / qemu_log_mask / qemu_log_mask_and_addr, we | ||
28 | diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c | ||
29 | index XXXXXXX..XXXXXXX 100644 | ||
30 | --- a/accel/tcg/cpu-exec.c | ||
31 | +++ b/accel/tcg/cpu-exec.c | ||
32 | @@ -XXX,XX +XXX,XX @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb) | ||
33 | if (qemu_loglevel_mask(CPU_LOG_TB_CPU) | ||
34 | && qemu_log_in_addr_range(itb->pc)) { | ||
35 | qemu_log_lock(); | ||
36 | + int flags = 0; | ||
37 | + if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) { | ||
38 | + flags |= CPU_DUMP_FPU; | ||
39 | + } | ||
40 | #if defined(TARGET_I386) | ||
41 | - log_cpu_state(cpu, CPU_DUMP_CCOP); | ||
42 | -#else | ||
43 | - log_cpu_state(cpu, 0); | ||
44 | + flags |= CPU_DUMP_CCOP; | ||
45 | #endif | ||
46 | + log_cpu_state(cpu, flags); | ||
47 | qemu_log_unlock(); | ||
48 | } | ||
49 | #endif /* DEBUG_DISAS */ | ||
50 | diff --git a/util/log.c b/util/log.c | ||
51 | index XXXXXXX..XXXXXXX 100644 | ||
52 | --- a/util/log.c | ||
53 | +++ b/util/log.c | ||
54 | @@ -XXX,XX +XXX,XX @@ const QEMULogItem qemu_log_items[] = { | ||
55 | "show trace before each executed TB (lots of logs)" }, | ||
56 | { CPU_LOG_TB_CPU, "cpu", | ||
57 | "show CPU registers before entering a TB (lots of logs)" }, | ||
58 | + { CPU_LOG_TB_FPU, "fpu", | ||
59 | + "include FPU registers in the 'cpu' logging" }, | ||
60 | { CPU_LOG_MMU, "mmu", | ||
61 | "log MMU-related activities" }, | ||
62 | { CPU_LOG_PCALL, "pcall", | ||
63 | -- | ||
64 | 2.17.0 | ||
65 | |||
66 | diff view generated by jsdifflib |