1
The following changes since commit ad1b4ec39caa5b3f17cbd8160283a03a3dcfe2ae:
1
The following changes since commit 7993b0f83fe5c3f8555e79781d5d098f99751a94:
2
2
3
Merge remote-tracking branch 'remotes/kraxel/tags/input-20180515-pull-request' into staging (2018-05-15 12:50:06 +0100)
3
Merge remote-tracking branch 'remotes/nvme/tags/nvme-fixes-for-6.0-pull-request' into staging (2021-03-29 18:45:12 +0100)
4
4
5
are available in the Git repository at:
5
are available in the Git repository at:
6
6
7
git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180515
7
https://git.linaro.org/people/pmaydell/qemu-arm.git pull-target-arm-20210330
8
8
9
for you to fetch changes up to ae7651804748c6b479d5ae09aeac4edb9c44f76e:
9
for you to fetch changes up to b9e3f1579a4b06fc63dfa8cdb68df1c58eeb0cf1:
10
10
11
tcg: Optionally log FPU state in TCG -d cpu logging (2018-05-15 14:58:44 +0100)
11
hw/timer/renesas_tmr: Add default-case asserts in read_tcnt() (2021-03-30 14:05:34 +0100)
12
12
13
----------------------------------------------------------------
13
----------------------------------------------------------------
14
target-arm queue:
14
* net/npcm7xx_emc.c: Fix handling of receiving packets when RSDR not set
15
* Fix coverity nit in int_to_float code
15
* hw/display/xlnx_dp: Free FIFOs adding xlnx_dp_finalize()
16
* Don't set Invalid for float-to-int(MAXINT)
16
* hw/arm/smmuv3: Drop unused CDM_VALID() and is_cd_valid()
17
* Fix fp_status_f16 tininess before rounding
17
* target/arm: Make number of counters in PMCR follow the CPU
18
* Add various missing insns from the v8.2-FP16 extension
18
* hw/timer/renesas_tmr: Add default-case asserts in read_tcnt()
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
19
23
----------------------------------------------------------------
20
----------------------------------------------------------------
24
Alex Bennée (5):
21
Doug Evans (1):
25
fpu/softfloat: int_to_float ensure r fully initialised
22
net/npcm7xx_emc.c: Fix handling of receiving packets when RSDR not set
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
23
31
Peter Maydell (3):
24
Peter Maydell (2):
32
fpu/softfloat: Don't set Invalid for float-to-int(MAXINT)
25
target/arm: Make number of counters in PMCR follow the CPU
33
target/arm: Fix fp_status_f16 tininess before rounding
26
hw/timer/renesas_tmr: Add default-case asserts in read_tcnt()
34
tcg: Optionally log FPU state in TCG -d cpu logging
35
27
36
Philippe Mathieu-Daudé (1):
28
Philippe Mathieu-Daudé (1):
37
sdcard: Correct CRC16 offset in sd_function_switch()
29
hw/display/xlnx_dp: Free FIFOs adding xlnx_dp_finalize()
38
30
39
Richard Henderson (7):
31
Zenghui Yu (1):
40
target/arm: Implement FMOV (general) for fp16
32
hw/arm/smmuv3: Drop unused CDM_VALID() and is_cd_valid()
41
target/arm: Early exit after unallocated_encoding in disas_fp_int_conv
42
target/arm: Implement FCVT (scalar, integer) for fp16
43
target/arm: Implement FCVT (scalar, fixed-point) for fp16
44
target/arm: Introduce and use read_fp_hreg
45
target/arm: Implement FP data-processing (2 source) for fp16
46
target/arm: Implement FP data-processing (3 source) for fp16
47
33
48
include/qemu/log.h | 1 +
34
hw/arm/smmuv3-internal.h | 7 -------
49
target/arm/helper-a64.h | 2 +
35
target/arm/cpu.h | 1 +
50
target/arm/helper.h | 6 +
36
hw/display/xlnx_dp.c | 9 +++++++++
51
accel/tcg/cpu-exec.c | 9 +-
37
hw/net/npcm7xx_emc.c | 4 +++-
52
fpu/softfloat.c | 6 +-
38
hw/timer/renesas_tmr.c | 4 ++++
53
hw/sd/sd.c | 2 +-
39
target/arm/cpu64.c | 3 +++
54
target/arm/cpu.c | 2 +
40
target/arm/cpu_tcg.c | 5 +++++
55
target/arm/helper-a64.c | 10 ++
41
target/arm/helper.c | 29 +++++++++++++++++------------
56
target/arm/helper.c | 38 +++-
42
target/arm/kvm64.c | 2 ++
57
target/arm/translate-a64.c | 421 ++++++++++++++++++++++++++++++++++++++-------
43
tests/qtest/npcm7xx_emc-test.c | 30 +++++++++++++++++++++---------
58
util/log.c | 2 +
44
10 files changed, 65 insertions(+), 29 deletions(-)
59
11 files changed, 428 insertions(+), 71 deletions(-)
60
45
diff view generated by jsdifflib
1
From: Richard Henderson <richard.henderson@linaro.org>
1
From: Doug Evans <dje@google.com>
2
2
3
We missed all of the scalar fp16 binary operations.
3
Turning REG_MCMDR_RXON is enough to start receiving packets.
4
4
5
Cc: qemu-stable@nongnu.org
5
Signed-off-by: Doug Evans <dje@google.com>
6
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
6
Message-id: 20210319195044.741821-1-dje@google.com
7
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Peter Maydell <peter.maydell@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>
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
9
---
12
target/arm/translate-a64.c | 65 ++++++++++++++++++++++++++++++++++++++
10
hw/net/npcm7xx_emc.c | 4 +++-
13
1 file changed, 65 insertions(+)
11
tests/qtest/npcm7xx_emc-test.c | 30 +++++++++++++++++++++---------
12
2 files changed, 24 insertions(+), 10 deletions(-)
14
13
15
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
14
diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c
16
index XXXXXXX..XXXXXXX 100644
15
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate-a64.c
16
--- a/hw/net/npcm7xx_emc.c
18
+++ b/target/arm/translate-a64.c
17
+++ b/hw/net/npcm7xx_emc.c
19
@@ -XXX,XX +XXX,XX @@ static void handle_fp_2src_double(DisasContext *s, int opcode,
18
@@ -XXX,XX +XXX,XX @@ static void npcm7xx_emc_write(void *opaque, hwaddr offset,
20
tcg_temp_free_i64(tcg_res);
19
!(value & REG_MCMDR_RXON)) {
20
emc->regs[REG_MGSTA] |= REG_MGSTA_RXHA;
21
}
22
- if (!(value & REG_MCMDR_RXON)) {
23
+ if (value & REG_MCMDR_RXON) {
24
+ emc->rx_active = true;
25
+ } else {
26
emc_halt_rx(emc, 0);
27
}
28
break;
29
diff --git a/tests/qtest/npcm7xx_emc-test.c b/tests/qtest/npcm7xx_emc-test.c
30
index XXXXXXX..XXXXXXX 100644
31
--- a/tests/qtest/npcm7xx_emc-test.c
32
+++ b/tests/qtest/npcm7xx_emc-test.c
33
@@ -XXX,XX +XXX,XX @@ static void enable_tx(QTestState *qts, const EMCModule *mod,
34
mcmdr |= REG_MCMDR_TXON;
35
emc_write(qts, mod, REG_MCMDR, mcmdr);
36
}
37
-
38
- /* Prod the device to send the packet. */
39
- emc_write(qts, mod, REG_TSDR, 1);
21
}
40
}
22
41
23
+/* Floating-point data-processing (2 source) - half precision */
42
static void emc_send_verify1(QTestState *qts, const EMCModule *mod, int fd,
24
+static void handle_fp_2src_half(DisasContext *s, int opcode,
43
@@ -XXX,XX +XXX,XX @@ static void emc_send_verify(QTestState *qts, const EMCModule *mod, int fd,
25
+ int rd, int rn, int rm)
44
enable_tx(qts, mod, &desc[0], NUM_TX_DESCRIPTORS, desc_addr,
26
+{
45
with_irq ? REG_MIEN_ENTXINTR : 0);
27
+ TCGv_i32 tcg_op1;
46
28
+ TCGv_i32 tcg_op2;
47
+ /* Prod the device to send the packet. */
29
+ TCGv_i32 tcg_res;
48
+ emc_write(qts, mod, REG_TSDR, 1);
30
+ TCGv_ptr fpst;
31
+
49
+
32
+ tcg_res = tcg_temp_new_i32();
50
/*
33
+ fpst = get_fpstatus_ptr(true);
51
* It's problematic to observe the interrupt for each packet.
34
+ tcg_op1 = read_fp_hreg(s, rn);
52
* Instead just wait until all the packets go out.
35
+ tcg_op2 = read_fp_hreg(s, rm);
53
@@ -XXX,XX +XXX,XX @@ static void enable_rx(QTestState *qts, const EMCModule *mod,
36
+
54
mcmdr |= REG_MCMDR_RXON | mcmdr_flags;
37
+ switch (opcode) {
55
emc_write(qts, mod, REG_MCMDR, mcmdr);
38
+ case 0x0: /* FMUL */
56
}
39
+ gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
57
-
40
+ break;
58
- /* Prod the device to accept a packet. */
41
+ case 0x1: /* FDIV */
59
- emc_write(qts, mod, REG_RSDR, 1);
42
+ gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
60
}
43
+ break;
61
44
+ case 0x2: /* FADD */
62
static void emc_recv_verify(QTestState *qts, const EMCModule *mod, int fd,
45
+ gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst);
63
- bool with_irq)
46
+ break;
64
+ bool with_irq, bool pump_rsdr)
47
+ case 0x3: /* FSUB */
65
{
48
+ gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
66
NPCM7xxEMCRxDesc desc[NUM_RX_DESCRIPTORS];
49
+ break;
67
uint32_t desc_addr = DESC_ADDR;
50
+ case 0x4: /* FMAX */
68
@@ -XXX,XX +XXX,XX @@ static void emc_recv_verify(QTestState *qts, const EMCModule *mod, int fd,
51
+ gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst);
69
enable_rx(qts, mod, &desc[0], NUM_RX_DESCRIPTORS, desc_addr,
52
+ break;
70
with_irq ? REG_MIEN_ENRXINTR : 0, 0);
53
+ case 0x5: /* FMIN */
71
54
+ gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst);
72
+ /*
55
+ break;
73
+ * If requested, prod the device to accept a packet.
56
+ case 0x6: /* FMAXNM */
74
+ * This isn't necessary, the linux driver doesn't do this.
57
+ gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst);
75
+ * Test doing/not-doing this for robustness.
58
+ break;
76
+ */
59
+ case 0x7: /* FMINNM */
77
+ if (pump_rsdr) {
60
+ gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst);
78
+ emc_write(qts, mod, REG_RSDR, 1);
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
+ }
79
+ }
69
+
80
+
70
+ write_fp_sreg(s, rd, tcg_res);
81
/* Send test packet to device's socket. */
71
+
82
ret = iov_send(fd, iov, 2, 0, sizeof(len) + sizeof(test));
72
+ tcg_temp_free_ptr(fpst);
83
g_assert_cmpint(ret, == , sizeof(test) + sizeof(len));
73
+ tcg_temp_free_i32(tcg_op1);
84
@@ -XXX,XX +XXX,XX @@ static void test_rx(gconstpointer test_data)
74
+ tcg_temp_free_i32(tcg_op2);
85
75
+ tcg_temp_free_i32(tcg_res);
86
qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic");
76
+}
87
77
+
88
- emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/false);
78
/* Floating point data-processing (2 source)
89
- emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/true);
79
* 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0
90
+ emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/false,
80
* +---+---+---+-----------+------+---+------+--------+-----+------+------+
91
+ /*pump_rsdr=*/false);
81
@@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn)
92
+ emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/false,
82
}
93
+ /*pump_rsdr=*/true);
83
handle_fp_2src_double(s, opcode, rd, rn, rm);
94
+ emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/true,
84
break;
95
+ /*pump_rsdr=*/false);
85
+ case 3:
96
+ emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/true,
86
+ if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
97
+ /*pump_rsdr=*/true);
87
+ unallocated_encoding(s);
98
emc_test_ptle(qts, td->module, test_sockets[0]);
88
+ return;
99
89
+ }
100
qtest_quit(qts);
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
--
101
--
99
2.17.0
102
2.20.1
100
103
101
104
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
2
2
3
Per the Physical Layer Simplified Spec. "4.3.10.4 Switch Function Status":
3
When building with --enable-sanitizers we get:
4
4
5
The block length is predefined to 512 bits
5
Direct leak of 16 byte(s) in 1 object(s) allocated from:
6
#0 0x5618479ec7cf in malloc (qemu-system-aarch64+0x233b7cf)
7
#1 0x7f675745f958 in g_malloc (/lib64/libglib-2.0.so.0+0x58958)
8
#2 0x561847c2dcc9 in xlnx_dp_init hw/display/xlnx_dp.c:1259:5
9
#3 0x56184a5bdab8 in object_init_with_type qom/object.c:375:9
10
#4 0x56184a5a2bda in object_initialize_with_type qom/object.c:517:5
11
#5 0x56184a5a24d5 in object_initialize qom/object.c:536:5
12
#6 0x56184a5a2f6c in object_initialize_child_with_propsv qom/object.c:566:5
13
#7 0x56184a5a2e60 in object_initialize_child_with_props qom/object.c:549:10
14
#8 0x56184a5a3a1e in object_initialize_child_internal qom/object.c:603:5
15
#9 0x5618495aa431 in xlnx_zynqmp_init hw/arm/xlnx-zynqmp.c:273:5
6
16
7
and "4.10.2 SD Status":
17
The RX/TX FIFOs are created in xlnx_dp_init(), add xlnx_dp_finalize()
18
to destroy them.
8
19
9
The SD Status contains status bits that are related to the SD Memory Card
20
Fixes: 58ac482a66d ("introduce xlnx-dp")
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>
21
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
17
Message-id: 20180509060104.4458-3-f4bug@amsat.org
22
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
18
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
23
Message-id: 20210323182958.277654-1-f4bug@amsat.org
19
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
24
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
20
---
25
---
21
hw/sd/sd.c | 2 +-
26
hw/display/xlnx_dp.c | 9 +++++++++
22
1 file changed, 1 insertion(+), 1 deletion(-)
27
1 file changed, 9 insertions(+)
23
28
24
diff --git a/hw/sd/sd.c b/hw/sd/sd.c
29
diff --git a/hw/display/xlnx_dp.c b/hw/display/xlnx_dp.c
25
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
26
--- a/hw/sd/sd.c
31
--- a/hw/display/xlnx_dp.c
27
+++ b/hw/sd/sd.c
32
+++ b/hw/display/xlnx_dp.c
28
@@ -XXX,XX +XXX,XX @@ static void sd_function_switch(SDState *sd, uint32_t arg)
33
@@ -XXX,XX +XXX,XX @@ static void xlnx_dp_init(Object *obj)
29
sd->data[14 + (i >> 1)] = new_func << ((i * 4) & 4);
34
fifo8_create(&s->tx_fifo, 16);
30
}
31
memset(&sd->data[17], 0, 47);
32
- stw_be_p(sd->data + 65, sd_crc16(sd->data, 64));
33
+ stw_be_p(sd->data + 64, sd_crc16(sd->data, 64));
34
}
35
}
35
36
36
static inline bool sd_wp_addr(SDState *sd, uint64_t addr)
37
+static void xlnx_dp_finalize(Object *obj)
38
+{
39
+ XlnxDPState *s = XLNX_DP(obj);
40
+
41
+ fifo8_destroy(&s->tx_fifo);
42
+ fifo8_destroy(&s->rx_fifo);
43
+}
44
+
45
static void xlnx_dp_realize(DeviceState *dev, Error **errp)
46
{
47
XlnxDPState *s = XLNX_DP(dev);
48
@@ -XXX,XX +XXX,XX @@ static const TypeInfo xlnx_dp_info = {
49
.parent = TYPE_SYS_BUS_DEVICE,
50
.instance_size = sizeof(XlnxDPState),
51
.instance_init = xlnx_dp_init,
52
+ .instance_finalize = xlnx_dp_finalize,
53
.class_init = xlnx_dp_class_init,
54
};
55
37
--
56
--
38
2.17.0
57
2.20.1
39
58
40
59
diff view generated by jsdifflib
1
From: Alex Bennée <alex.bennee@linaro.org>
1
From: Zenghui Yu <yuzenghui@huawei.com>
2
2
3
Reported by Coverity (CID1390635). We ensure this for uint_to_float
3
They were introduced in commit 9bde7f0674fe ("hw/arm/smmuv3: Implement
4
later on so we might as well mirror that.
4
translate callback") but never actually used. Drop them.
5
5
6
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
6
Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Acked-by: Eric Auger <eric.auger@redhat.com>
8
Message-id: 20210325142702.790-1-yuzenghui@huawei.com
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
11
---
11
fpu/softfloat.c | 2 +-
12
hw/arm/smmuv3-internal.h | 7 -------
12
1 file changed, 1 insertion(+), 1 deletion(-)
13
1 file changed, 7 deletions(-)
13
14
14
diff --git a/fpu/softfloat.c b/fpu/softfloat.c
15
diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h
15
index XXXXXXX..XXXXXXX 100644
16
index XXXXXXX..XXXXXXX 100644
16
--- a/fpu/softfloat.c
17
--- a/hw/arm/smmuv3-internal.h
17
+++ b/fpu/softfloat.c
18
+++ b/hw/arm/smmuv3-internal.h
18
@@ -XXX,XX +XXX,XX @@ FLOAT_TO_UINT(64, 64)
19
@@ -XXX,XX +XXX,XX @@ static inline int pa_range(STE *ste)
19
20
#define CD_A(x) extract32((x)->word[1], 14, 1)
20
static FloatParts int_to_float(int64_t a, float_status *status)
21
#define CD_AARCH64(x) extract32((x)->word[1], 9 , 1)
21
{
22
22
- FloatParts r;
23
-#define CDM_VALID(x) ((x)->word[0] & 0x1)
23
+ FloatParts r = {};
24
-
24
if (a == 0) {
25
-static inline int is_cd_valid(SMMUv3State *s, STE *ste, CD *cd)
25
r.cls = float_class_zero;
26
-{
26
r.sign = false;
27
- return CD_VALID(cd);
28
-}
29
-
30
/**
31
* tg2granule - Decodes the CD translation granule size field according
32
* to the ttbr in use
27
--
33
--
28
2.17.0
34
2.20.1
29
35
30
36
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
Currently we give all the v7-and-up CPUs a PMU with 4 counters. This
2
2
means that we don't provide the 6 counters that are required by the
3
Cc: qemu-stable@nongnu.org
3
Arm BSA (Base System Architecture) specification if the CPU supports
4
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
4
the Virtualization extensions.
5
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
5
6
Tested-by: Alex Bennée <alex.bennee@linaro.org>
6
Instead of having a single PMCR_NUM_COUNTERS, make each CPU type
7
Message-id: 20180512003217.9105-4-richard.henderson@linaro.org
7
specify the PMCR reset value (obtained from the appropriate TRM), and
8
use the 'N' field of that value to define the number of counters
9
provided.
10
11
This means that we now supply 6 counters for Cortex-A53, A57, A72,
12
A15 and A9 as well as '-cpu max'; Cortex-A7 and A8 stay at 4; and
13
Cortex-R5 goes down to 3.
14
15
Note that because we now use the PMCR reset value of the specific
16
implementation, we no longer set the LC bit out of reset. This has
17
an UNKNOWN value out of reset for all cores with any AArch32 support,
18
so guest software should be setting it anyway if it wants it.
19
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
20
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
21
Tested-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
22
Message-id: 20210311165947.27470-1-peter.maydell@linaro.org
23
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
---
24
---
10
target/arm/helper.h | 6 +++
25
target/arm/cpu.h | 1 +
11
target/arm/helper.c | 38 ++++++++++++++-
26
target/arm/cpu64.c | 3 +++
12
target/arm/translate-a64.c | 96 +++++++++++++++++++++++++++++++-------
27
target/arm/cpu_tcg.c | 5 +++++
13
3 files changed, 122 insertions(+), 18 deletions(-)
28
target/arm/helper.c | 29 +++++++++++++++++------------
14
29
target/arm/kvm64.c | 2 ++
15
diff --git a/target/arm/helper.h b/target/arm/helper.h
30
5 files changed, 28 insertions(+), 12 deletions(-)
16
index XXXXXXX..XXXXXXX 100644
31
17
--- a/target/arm/helper.h
32
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
18
+++ b/target/arm/helper.h
33
index XXXXXXX..XXXXXXX 100644
19
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr)
34
--- a/target/arm/cpu.h
20
DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr)
35
+++ b/target/arm/cpu.h
21
DEF_HELPER_3(vfp_touhh, i32, f16, i32, ptr)
36
@@ -XXX,XX +XXX,XX @@ struct ARMCPU {
22
DEF_HELPER_3(vfp_toshh, i32, f16, i32, ptr)
37
uint64_t id_aa64mmfr2;
23
+DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr)
38
uint64_t id_aa64dfr0;
24
+DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr)
39
uint64_t id_aa64dfr1;
25
+DEF_HELPER_3(vfp_touqh, i64, f16, i32, ptr)
40
+ uint64_t reset_pmcr_el0;
26
+DEF_HELPER_3(vfp_tosqh, i64, f16, i32, ptr)
41
} isar;
27
DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr)
42
uint64_t midr;
28
DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr)
43
uint32_t revidr;
29
DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr)
44
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
30
@@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr)
45
index XXXXXXX..XXXXXXX 100644
31
DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr)
46
--- a/target/arm/cpu64.c
32
DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr)
47
+++ b/target/arm/cpu64.c
33
DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr)
48
@@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj)
34
+DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr)
49
cpu->gic_num_lrs = 4;
35
+DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr)
50
cpu->gic_vpribits = 5;
36
51
cpu->gic_vprebits = 5;
37
DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr)
52
+ cpu->isar.reset_pmcr_el0 = 0x41013000;
38
DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env)
53
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
54
}
55
56
@@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj)
57
cpu->gic_num_lrs = 4;
58
cpu->gic_vpribits = 5;
59
cpu->gic_vprebits = 5;
60
+ cpu->isar.reset_pmcr_el0 = 0x41033000;
61
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
62
}
63
64
@@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj)
65
cpu->gic_num_lrs = 4;
66
cpu->gic_vpribits = 5;
67
cpu->gic_vprebits = 5;
68
+ cpu->isar.reset_pmcr_el0 = 0x41023000;
69
define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo);
70
}
71
72
diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c
73
index XXXXXXX..XXXXXXX 100644
74
--- a/target/arm/cpu_tcg.c
75
+++ b/target/arm/cpu_tcg.c
76
@@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj)
77
cpu->ccsidr[1] = 0x2007e01a; /* 16k L1 icache. */
78
cpu->ccsidr[2] = 0xf0000000; /* No L2 icache. */
79
cpu->reset_auxcr = 2;
80
+ cpu->isar.reset_pmcr_el0 = 0x41002000;
81
define_arm_cp_regs(cpu, cortexa8_cp_reginfo);
82
}
83
84
@@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj)
85
cpu->clidr = (1 << 27) | (1 << 24) | 3;
86
cpu->ccsidr[0] = 0xe00fe019; /* 16k L1 dcache. */
87
cpu->ccsidr[1] = 0x200fe019; /* 16k L1 icache. */
88
+ cpu->isar.reset_pmcr_el0 = 0x41093000;
89
define_arm_cp_regs(cpu, cortexa9_cp_reginfo);
90
}
91
92
@@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj)
93
cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
94
cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
95
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
96
+ cpu->isar.reset_pmcr_el0 = 0x41072000;
97
define_arm_cp_regs(cpu, cortexa15_cp_reginfo); /* Same as A15 */
98
}
99
100
@@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj)
101
cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */
102
cpu->ccsidr[1] = 0x201fe00a; /* 32K L1 icache */
103
cpu->ccsidr[2] = 0x711fe07a; /* 4096K L2 unified cache */
104
+ cpu->isar.reset_pmcr_el0 = 0x410F3000;
105
define_arm_cp_regs(cpu, cortexa15_cp_reginfo);
106
}
107
108
@@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj)
109
cpu->isar.id_isar6 = 0x0;
110
cpu->mp_is_up = true;
111
cpu->pmsav7_dregion = 16;
112
+ cpu->isar.reset_pmcr_el0 = 0x41151800;
113
define_arm_cp_regs(cpu, cortexr5_cp_reginfo);
114
}
115
39
diff --git a/target/arm/helper.c b/target/arm/helper.c
116
diff --git a/target/arm/helper.c b/target/arm/helper.c
40
index XXXXXXX..XXXXXXX 100644
117
index XXXXXXX..XXXXXXX 100644
41
--- a/target/arm/helper.c
118
--- a/target/arm/helper.c
42
+++ b/target/arm/helper.c
119
+++ b/target/arm/helper.c
43
@@ -XXX,XX +XXX,XX @@ VFP_CONV_FIX_A64(uq, s, 32, 64, uint64)
120
@@ -XXX,XX +XXX,XX @@
44
#undef VFP_CONV_FIX_A64
121
#endif
45
122
46
/* Conversion to/from f16 can overflow to infinity before/after scaling.
123
#define ARM_CPU_FREQ 1000000000 /* FIXME: 1 GHz, should be configurable */
47
- * Therefore we convert to f64 (which does not round), scale,
124
-#define PMCR_NUM_COUNTERS 4 /* QEMU IMPDEF choice */
48
- * and then convert f64 to f16 (which may round).
125
49
+ * Therefore we convert to f64, scale, and then convert f64 to f16; or
126
#ifndef CONFIG_USER_ONLY
50
+ * vice versa for conversion to integer.
127
51
+ *
128
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = {
52
+ * For 16- and 32-bit integers, the conversion to f64 never rounds.
129
53
+ * For 64-bit integers, any integer that would cause rounding will also
130
static inline uint32_t pmu_num_counters(CPUARMState *env)
54
+ * overflow to f16 infinity, so there is no double rounding problem.
131
{
55
*/
132
- return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT;
56
133
+ ARMCPU *cpu = env_archcpu(env);
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
+
134
+
67
+float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst)
135
+ return (cpu->isar.reset_pmcr_el0 & PMCRN_MASK) >> PMCRN_SHIFT;
68
+{
136
}
69
+ return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst);
137
70
+}
138
/* Bits allowed to be set/cleared for PMCNTEN* and PMINTEN* */
139
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = {
140
.resetvalue = 0,
141
.writefn = gt_hyp_ctl_write, .raw_writefn = raw_write },
142
#endif
143
- /* The only field of MDCR_EL2 that has a defined architectural reset value
144
- * is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N.
145
- */
146
- { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH,
147
- .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 1,
148
- .access = PL2_RW, .resetvalue = PMCR_NUM_COUNTERS,
149
- .fieldoffset = offsetof(CPUARMState, cp15.mdcr_el2), },
150
{ .name = "HPFAR", .state = ARM_CP_STATE_AA32,
151
.cp = 15, .opc1 = 4, .crn = 6, .crm = 0, .opc2 = 4,
152
.access = PL2_RW, .accessfn = access_el3_aa32ns,
153
@@ -XXX,XX +XXX,XX @@ static void define_pmu_regs(ARMCPU *cpu)
154
* field as main ID register, and we implement four counters in
155
* addition to the cycle count register.
156
*/
157
- unsigned int i, pmcrn = PMCR_NUM_COUNTERS;
158
+ unsigned int i, pmcrn = pmu_num_counters(&cpu->env);
159
ARMCPRegInfo pmcr = {
160
.name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0,
161
.access = PL0_RW,
162
@@ -XXX,XX +XXX,XX @@ static void define_pmu_regs(ARMCPU *cpu)
163
.access = PL0_RW, .accessfn = pmreg_access,
164
.type = ARM_CP_IO,
165
.fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr),
166
- .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT) |
167
- PMCRLC,
168
+ .resetvalue = cpu->isar.reset_pmcr_el0,
169
.writefn = pmcr_write, .raw_writefn = raw_write,
170
};
71
+
171
+
72
static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst)
172
define_one_arm_cp_reg(cpu, &pmcr);
73
{
173
define_one_arm_cp_reg(cpu, &pmcr64);
74
if (unlikely(float16_is_any_nan(f))) {
174
for (i = 0; i < pmcrn; i++) {
75
@@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst)
175
@@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu)
76
return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst);
176
.fieldoffset = offsetof(CPUARMState, cp15.vmpidr_el2) },
77
}
177
REGINFO_SENTINEL
78
178
};
79
+uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst)
179
+ /*
80
+{
180
+ * The only field of MDCR_EL2 that has a defined architectural reset
81
+ return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst);
181
+ * value is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N.
82
+}
182
+ */
83
+
183
+ ARMCPRegInfo mdcr_el2 = {
84
+uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst)
184
+ .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH,
85
+{
185
+ .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 1,
86
+ return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst);
186
+ .access = PL2_RW, .resetvalue = pmu_num_counters(env),
87
+}
187
+ .fieldoffset = offsetof(CPUARMState, cp15.mdcr_el2),
88
+
188
+ };
89
+uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst)
189
+ define_one_arm_cp_reg(cpu, &mdcr_el2);
90
+{
190
define_arm_cp_regs(cpu, vpidr_regs);
91
+ return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst);
191
define_arm_cp_regs(cpu, el2_cp_reginfo);
92
+}
192
if (arm_feature(env, ARM_FEATURE_V8)) {
93
+
193
diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c
94
+uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst)
194
index XXXXXXX..XXXXXXX 100644
95
+{
195
--- a/target/arm/kvm64.c
96
+ return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst);
196
+++ b/target/arm/kvm64.c
97
+}
197
@@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf)
98
+
198
ARM64_SYS_REG(3, 0, 0, 7, 1));
99
/* Set the current fp rounding mode and return the old one.
199
err |= read_sys_reg64(fdarray[2], &ahcf->isar.id_aa64mmfr2,
100
* The argument is a softfloat float_round_ value.
200
ARM64_SYS_REG(3, 0, 0, 7, 2));
101
*/
201
+ err |= read_sys_reg64(fdarray[2], &ahcf->isar.reset_pmcr_el0,
102
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
202
+ ARM64_SYS_REG(3, 3, 9, 12, 0));
103
index XXXXXXX..XXXXXXX 100644
203
104
--- a/target/arm/translate-a64.c
204
/*
105
+++ b/target/arm/translate-a64.c
205
* Note that if AArch32 support is not present in the host,
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
}
135
write_fp_dreg(s, rd, tcg_double);
136
tcg_temp_free_i64(tcg_double);
137
- } else {
138
- TCGv_i32 tcg_single = tcg_temp_new_i32();
139
+ break;
140
+
141
+ case 0: /* float32 */
142
+ tcg_single = tcg_temp_new_i32();
143
if (is_signed) {
144
gen_helper_vfp_sqtos(tcg_single, tcg_int,
145
tcg_shift, tcg_fpstatus);
146
@@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode,
147
}
148
write_fp_sreg(s, rd, tcg_single);
149
tcg_temp_free_i32(tcg_single);
150
+ break;
151
+
152
+ case 3: /* float16 */
153
+ tcg_single = tcg_temp_new_i32();
154
+ if (is_signed) {
155
+ gen_helper_vfp_sqtoh(tcg_single, tcg_int,
156
+ tcg_shift, tcg_fpstatus);
157
+ } else {
158
+ gen_helper_vfp_uqtoh(tcg_single, tcg_int,
159
+ tcg_shift, tcg_fpstatus);
160
+ }
161
+ write_fp_sreg(s, rd, tcg_single);
162
+ tcg_temp_free_i32(tcg_single);
163
+ break;
164
+
165
+ default:
166
+ g_assert_not_reached();
167
}
168
} else {
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
}
185
}
186
+ if (!sf) {
187
+ tcg_gen_ext32u_i64(tcg_int, tcg_int);
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
}
202
tcg_temp_free_i32(tcg_single);
203
+ break;
204
+
205
+ case 3: /* float16 */
206
+ tcg_single = read_fp_sreg(s, rn);
207
+ if (sf) {
208
+ if (is_signed) {
209
+ gen_helper_vfp_tosqh(tcg_int, tcg_single,
210
+ tcg_shift, tcg_fpstatus);
211
+ } else {
212
+ gen_helper_vfp_touqh(tcg_int, tcg_single,
213
+ tcg_shift, tcg_fpstatus);
214
+ }
215
+ } else {
216
+ TCGv_i32 tcg_dest = tcg_temp_new_i32();
217
+ if (is_signed) {
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
--
206
--
266
2.17.0
207
2.20.1
267
208
268
209
diff view generated by jsdifflib
1
From: Richard Henderson <richard.henderson@linaro.org>
1
In commit 81b3ddaf8772ec we fixed a use of uninitialized data
2
in read_tcnt(). However this change wasn't enough to placate
3
Coverity, which is not smart enough to see that if we read a
4
2 bit field and then handle cases 0, 1, 2 and 3 then there cannot
5
be a flow of execution through the switch default. Add explicit
6
default cases which assert that they can't be reached, which
7
should help silence Coverity.
2
8
3
Adding the fp16 moves to/from general registers.
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
11
Message-id: 20210319162458.13760-1-peter.maydell@linaro.org
12
---
13
hw/timer/renesas_tmr.c | 4 ++++
14
1 file changed, 4 insertions(+)
4
15
5
Cc: qemu-stable@nongnu.org
16
diff --git a/hw/timer/renesas_tmr.c b/hw/timer/renesas_tmr.c
6
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
7
Tested-by: Alex Bennée <alex.bennee@linaro.org>
8
Message-id: 20180512003217.9105-2-richard.henderson@linaro.org
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
12
target/arm/translate-a64.c | 21 +++++++++++++++++++++
13
1 file changed, 21 insertions(+)
14
15
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
16
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
17
--- a/target/arm/translate-a64.c
18
--- a/hw/timer/renesas_tmr.c
18
+++ b/target/arm/translate-a64.c
19
+++ b/hw/timer/renesas_tmr.c
19
@@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof)
20
@@ -XXX,XX +XXX,XX @@ static uint16_t read_tcnt(RTMRState *tmr, unsigned size, int ch)
20
tcg_gen_st_i64(tcg_rn, cpu_env, fp_reg_hi_offset(s, rd));
21
case CSS_CASCADING:
21
clear_vec_high(s, true, rd);
22
tcnt[1] = tmr->tcnt[1];
22
break;
23
break;
23
+ case 3:
24
+ default:
24
+ /* 16 bit */
25
+ g_assert_not_reached();
25
+ tmp = tcg_temp_new_i64();
26
}
26
+ tcg_gen_ext16u_i64(tmp, tcg_rn);
27
switch (FIELD_EX8(tmr->tccr[0], TCCR, CSS)) {
27
+ write_fp_dreg(s, rd, tmp);
28
case CSS_INTERNAL:
28
+ tcg_temp_free_i64(tmp);
29
@@ -XXX,XX +XXX,XX @@ static uint16_t read_tcnt(RTMRState *tmr, unsigned size, int ch)
29
+ break;
30
case CSS_EXTERNAL: /* QEMU doesn't implement this */
31
tcnt[0] = tmr->tcnt[0];
32
break;
30
+ default:
33
+ default:
31
+ g_assert_not_reached();
34
+ g_assert_not_reached();
32
}
35
}
33
} else {
36
} else {
34
TCGv_i64 tcg_rd = cpu_reg(s, rd);
37
tcnt[0] = tmr->tcnt[0];
35
@@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof)
36
/* 64 bits from top half */
37
tcg_gen_ld_i64(tcg_rd, cpu_env, fp_reg_hi_offset(s, rn));
38
break;
39
+ case 3:
40
+ /* 16 bit */
41
+ tcg_gen_ld16u_i64(tcg_rd, cpu_env, fp_reg_offset(s, rn, MO_16));
42
+ break;
43
+ default:
44
+ g_assert_not_reached();
45
}
46
}
47
}
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
--
38
--
62
2.17.0
39
2.20.1
63
40
64
41
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
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
Cc: qemu-stable@nongnu.org
4
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
5
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
6
Tested-by: Alex Bennée <alex.bennee@linaro.org>
7
Message-id: 20180512003217.9105-6-richard.henderson@linaro.org
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
---
10
target/arm/translate-a64.c | 30 ++++++++++++++----------------
11
1 file changed, 14 insertions(+), 16 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 TCGv_i32 read_fp_sreg(DisasContext *s, int reg)
18
return v;
19
}
20
21
+static TCGv_i32 read_fp_hreg(DisasContext *s, int reg)
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
--
91
2.17.0
92
93
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
Deleted patch
1
From: Alex Bennée <alex.bennee@linaro.org>
2
1
3
These where 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: 20180512003217.9105-9-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>
14
---
15
target/arm/helper-a64.h | 2 +
16
target/arm/helper-a64.c | 10 +++++
17
target/arm/translate-a64.c | 88 ++++++++++++++++++++++++++++++--------
18
3 files changed, 83 insertions(+), 17 deletions(-)
19
20
diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
21
index XXXXXXX..XXXXXXX 100644
22
--- a/target/arm/helper-a64.h
23
+++ b/target/arm/helper-a64.h
24
@@ -XXX,XX +XXX,XX @@
25
DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
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
}
40
41
+uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status)
42
+{
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
{
53
return float_rel_to_flags(float32_compare_quiet(x, y, fp_status));
54
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
55
index XXXXXXX..XXXXXXX 100644
56
--- a/target/arm/translate-a64.c
57
+++ b/target/arm/translate-a64.c
58
@@ -XXX,XX +XXX,XX @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn)
59
}
60
}
61
62
-static void handle_fp_compare(DisasContext *s, bool is_double,
63
+static void handle_fp_compare(DisasContext *s, int size,
64
unsigned int rn, unsigned int rm,
65
bool cmp_with_zero, bool signal_all_nans)
66
{
67
TCGv_i64 tcg_flags = tcg_temp_new_i64();
68
- TCGv_ptr fpst = get_fpstatus_ptr(false);
69
+ TCGv_ptr fpst = get_fpstatus_ptr(size == MO_16);
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
--
215
2.17.0
216
217
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