1
Most of this is the Neon decodetree patches, followed by Edgar's versal cleanups.
1
Hi; here's the latest batch of arm changes. The big thing
2
in here is the SMMUv3 changes to add stage-2 translation support.
2
3
3
thanks
4
thanks
4
-- PMM
5
-- PMM
5
6
7
The following changes since commit aa9bbd865502ed517624ab6fe7d4b5d89ca95e43:
6
8
7
The following changes since commit 2ef486e76d64436be90f7359a3071fb2a56ce835:
9
Merge tag 'pull-ppc-20230528' of https://gitlab.com/danielhb/qemu into staging (2023-05-29 14:31:52 -0700)
8
9
Merge remote-tracking branch 'remotes/marcel/tags/rdma-pull-request' into staging (2020-05-03 14:12:56 +0100)
10
10
11
are available in the Git repository at:
11
are available in the Git repository at:
12
12
13
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200504
13
https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230530
14
14
15
for you to fetch changes up to 9aefc6cf9b73f66062d2f914a0136756e7a28211:
15
for you to fetch changes up to b03d0d4f531a8b867e0aac1fab0b876903015680:
16
16
17
target/arm: Move gen_ function typedefs to translate.h (2020-05-04 12:59:26 +0100)
17
docs: sbsa: correct graphics card name (2023-05-30 13:32:46 +0100)
18
18
19
----------------------------------------------------------------
19
----------------------------------------------------------------
20
target-arm queue:
20
target-arm queue:
21
* Start of conversion of Neon insns to decodetree
21
* fsl-imx6: Add SNVS support for i.MX6 boards
22
* versal board: support SD and RTC
22
* smmuv3: Add support for stage 2 translations
23
* Implement ARMv8.2-TTS2UXN
23
* hw/dma/xilinx_axidma: Check DMASR.HALTED to prevent infinite loop
24
* Make VQDMULL undefined when U=1
24
* hw/arm/xlnx-zynqmp: fix unsigned error when checking the RPUs number
25
* Some minor code cleanups
25
* cleanups for recent Kconfig changes
26
* target/arm: Explicitly select short-format FSR for M-profile
27
* tests/qtest: Run arm-specific tests only if the required machine is available
28
* hw/arm/sbsa-ref: add GIC node into DT
29
* docs: sbsa: correct graphics card name
30
* Update copyright dates to 2023
26
31
27
----------------------------------------------------------------
32
----------------------------------------------------------------
28
Edgar E. Iglesias (11):
33
Clément Chigot (1):
29
hw/arm: versal: Remove inclusion of arm_gicv3_common.h
34
hw/arm/xlnx-zynqmp: fix unsigned error when checking the RPUs number
30
hw/arm: versal: Move misplaced comment
31
hw/arm: versal-virt: Fix typo xlnx-ve -> xlnx-versal
32
hw/arm: versal: Embed the UARTs into the SoC type
33
hw/arm: versal: Embed the GEMs into the SoC type
34
hw/arm: versal: Embed the ADMAs into the SoC type
35
hw/arm: versal: Embed the APUs into the SoC type
36
hw/arm: versal: Add support for SD
37
hw/arm: versal: Add support for the RTC
38
hw/arm: versal-virt: Add support for SD
39
hw/arm: versal-virt: Add support for the RTC
40
35
41
Fredrik Strupe (1):
36
Enze Li (1):
42
target/arm: Make VQDMULL undefined when U=1
37
Update copyright dates to 2023
43
38
44
Peter Maydell (25):
39
Fabiano Rosas (3):
45
target/arm: Don't use a TLB for ARMMMUIdx_Stage2
40
target/arm: Explain why we need to select ARM_V7M
46
target/arm: Use enum constant in get_phys_addr_lpae() call
41
arm/Kconfig: Keep Kconfig default entries in default.mak as documentation
47
target/arm: Add new 's1_is_el0' argument to get_phys_addr_lpae()
42
arm/Kconfig: Make TCG dependence explicit
48
target/arm: Implement ARMv8.2-TTS2UXN
49
target/arm: Use correct variable for setting 'max' cpu's ID_AA64DFR0
50
target/arm/translate-vfp.inc.c: Remove duplicate simd_r32 check
51
target/arm: Don't allow Thumb Neon insns without FEATURE_NEON
52
target/arm: Add stubs for AArch32 Neon decodetree
53
target/arm: Convert VCMLA (vector) to decodetree
54
target/arm: Convert VCADD (vector) to decodetree
55
target/arm: Convert V[US]DOT (vector) to decodetree
56
target/arm: Convert VFM[AS]L (vector) to decodetree
57
target/arm: Convert VCMLA (scalar) to decodetree
58
target/arm: Convert V[US]DOT (scalar) to decodetree
59
target/arm: Convert VFM[AS]L (scalar) to decodetree
60
target/arm: Convert Neon load/store multiple structures to decodetree
61
target/arm: Convert Neon 'load single structure to all lanes' to decodetree
62
target/arm: Convert Neon 'load/store single structure' to decodetree
63
target/arm: Convert Neon 3-reg-same VADD/VSUB to decodetree
64
target/arm: Convert Neon 3-reg-same logic ops to decodetree
65
target/arm: Convert Neon 3-reg-same VMAX/VMIN to decodetree
66
target/arm: Convert Neon 3-reg-same comparisons to decodetree
67
target/arm: Convert Neon 3-reg-same VQADD/VQSUB to decodetree
68
target/arm: Convert Neon 3-reg-same VMUL, VMLA, VMLS, VSHL to decodetree
69
target/arm: Move gen_ function typedefs to translate.h
70
43
71
Philippe Mathieu-Daudé (2):
44
Marcin Juszkiewicz (2):
72
hw/arm/mps2-tz: Use TYPE_IOTKIT instead of hardcoded string
45
hw/arm/sbsa-ref: add GIC node into DT
73
target/arm: Use uint64_t for midr field in CPU state struct
46
docs: sbsa: correct graphics card name
74
47
75
include/hw/arm/xlnx-versal.h | 31 +-
48
Mostafa Saleh (10):
76
target/arm/cpu-param.h | 2 +-
49
hw/arm/smmuv3: Add missing fields for IDR0
77
target/arm/cpu.h | 38 ++-
50
hw/arm/smmuv3: Update translation config to hold stage-2
78
target/arm/translate-a64.h | 9 -
51
hw/arm/smmuv3: Refactor stage-1 PTW
79
target/arm/translate.h | 26 ++
52
hw/arm/smmuv3: Add page table walk for stage-2
80
target/arm/neon-dp.decode | 86 +++++
53
hw/arm/smmuv3: Parse STE config for stage-2
81
target/arm/neon-ls.decode | 52 +++
54
hw/arm/smmuv3: Make TLB lookup work for stage-2
82
target/arm/neon-shared.decode | 66 ++++
55
hw/arm/smmuv3: Add VMID to TLB tagging
83
hw/arm/mps2-tz.c | 2 +-
56
hw/arm/smmuv3: Add CMDs related to stage-2
84
hw/arm/xlnx-versal-virt.c | 74 ++++-
57
hw/arm/smmuv3: Add stage-2 support in iova notifier
85
hw/arm/xlnx-versal.c | 115 +++++--
58
hw/arm/smmuv3: Add knob to choose translation stage and enable stage-2
86
target/arm/cpu.c | 3 +-
87
target/arm/cpu64.c | 8 +-
88
target/arm/helper.c | 183 ++++------
89
target/arm/translate-a64.c | 17 -
90
target/arm/translate-neon.inc.c | 714 +++++++++++++++++++++++++++++++++++++++
91
target/arm/translate-vfp.inc.c | 6 -
92
target/arm/translate.c | 716 +++-------------------------------------
93
target/arm/Makefile.objs | 18 +
94
19 files changed, 1302 insertions(+), 864 deletions(-)
95
create mode 100644 target/arm/neon-dp.decode
96
create mode 100644 target/arm/neon-ls.decode
97
create mode 100644 target/arm/neon-shared.decode
98
create mode 100644 target/arm/translate-neon.inc.c
99
59
60
Peter Maydell (1):
61
target/arm: Explicitly select short-format FSR for M-profile
62
63
Thomas Huth (1):
64
tests/qtest: Run arm-specific tests only if the required machine is available
65
66
Tommy Wu (1):
67
hw/dma/xilinx_axidma: Check DMASR.HALTED to prevent infinite loop.
68
69
Vitaly Cheptsov (1):
70
fsl-imx6: Add SNVS support for i.MX6 boards
71
72
docs/conf.py | 2 +-
73
docs/system/arm/sbsa.rst | 2 +-
74
configs/devices/aarch64-softmmu/default.mak | 6 +
75
configs/devices/arm-softmmu/default.mak | 40 ++++
76
hw/arm/smmu-internal.h | 37 +++
77
hw/arm/smmuv3-internal.h | 12 +-
78
include/hw/arm/fsl-imx6.h | 2 +
79
include/hw/arm/smmu-common.h | 45 +++-
80
include/hw/arm/smmuv3.h | 4 +
81
include/qemu/help-texts.h | 2 +-
82
hw/arm/fsl-imx6.c | 8 +
83
hw/arm/sbsa-ref.c | 19 +-
84
hw/arm/smmu-common.c | 209 ++++++++++++++--
85
hw/arm/smmuv3.c | 357 ++++++++++++++++++++++++----
86
hw/arm/xlnx-zynqmp.c | 2 +-
87
hw/dma/xilinx_axidma.c | 11 +-
88
target/arm/tcg/tlb_helper.c | 13 +-
89
hw/arm/Kconfig | 123 ++++++----
90
hw/arm/trace-events | 14 +-
91
target/arm/Kconfig | 3 +
92
tests/qtest/meson.build | 7 +-
93
21 files changed, 773 insertions(+), 145 deletions(-)
94
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Vitaly Cheptsov <cheptsov@ispras.ru>
2
2
3
By using the TYPE_* definitions for devices, we can:
3
SNVS is supported on both i.MX6 and i.MX6UL and is needed
4
- quickly find where devices are used with 'git-grep'
4
to support shutdown on the board.
5
- easily rename a device (one-line change).
6
5
7
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
6
Cc: Peter Maydell <peter.maydell@linaro.org> (odd fixer:SABRELITE / i.MX6)
8
Message-id: 20200428154650.21991-1-f4bug@amsat.org
7
Cc: Jean-Christophe Dubois <jcd@tribudubois.net> (reviewer:SABRELITE / i.MX6)
8
Cc: qemu-arm@nongnu.org (open list:SABRELITE / i.MX6)
9
Cc: qemu-devel@nongnu.org (open list:All patches CC here)
10
Signed-off-by: Vitaly Cheptsov <cheptsov@ispras.ru>
11
Message-id: 20230515095015.66860-1-cheptsov@ispras.ru
9
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
12
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
14
---
12
hw/arm/mps2-tz.c | 2 +-
15
include/hw/arm/fsl-imx6.h | 2 ++
13
1 file changed, 1 insertion(+), 1 deletion(-)
16
hw/arm/fsl-imx6.c | 8 ++++++++
17
2 files changed, 10 insertions(+)
14
18
15
diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c
19
diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h
16
index XXXXXXX..XXXXXXX 100644
20
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/arm/mps2-tz.c
21
--- a/include/hw/arm/fsl-imx6.h
18
+++ b/hw/arm/mps2-tz.c
22
+++ b/include/hw/arm/fsl-imx6.h
19
@@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine)
23
@@ -XXX,XX +XXX,XX @@
20
exit(EXIT_FAILURE);
24
#include "hw/cpu/a9mpcore.h"
21
}
25
#include "hw/misc/imx6_ccm.h"
22
26
#include "hw/misc/imx6_src.h"
23
- sysbus_init_child_obj(OBJECT(machine), "iotkit", &mms->iotkit,
27
+#include "hw/misc/imx7_snvs.h"
24
+ sysbus_init_child_obj(OBJECT(machine), TYPE_IOTKIT, &mms->iotkit,
28
#include "hw/watchdog/wdt_imx2.h"
25
sizeof(mms->iotkit), mmc->armsse_type);
29
#include "hw/char/imx_serial.h"
26
iotkitdev = DEVICE(&mms->iotkit);
30
#include "hw/timer/imx_gpt.h"
27
object_property_set_link(OBJECT(&mms->iotkit), OBJECT(system_memory),
31
@@ -XXX,XX +XXX,XX @@ struct FslIMX6State {
32
A9MPPrivState a9mpcore;
33
IMX6CCMState ccm;
34
IMX6SRCState src;
35
+ IMX7SNVSState snvs;
36
IMXSerialState uart[FSL_IMX6_NUM_UARTS];
37
IMXGPTState gpt;
38
IMXEPITState epit[FSL_IMX6_NUM_EPITS];
39
diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c
40
index XXXXXXX..XXXXXXX 100644
41
--- a/hw/arm/fsl-imx6.c
42
+++ b/hw/arm/fsl-imx6.c
43
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6_init(Object *obj)
44
45
object_initialize_child(obj, "src", &s->src, TYPE_IMX6_SRC);
46
47
+ object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS);
48
+
49
for (i = 0; i < FSL_IMX6_NUM_UARTS; i++) {
50
snprintf(name, NAME_SIZE, "uart%d", i + 1);
51
object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL);
52
@@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp)
53
qdev_get_gpio_in(DEVICE(&s->a9mpcore),
54
FSL_IMX6_ENET_MAC_1588_IRQ));
55
56
+ /*
57
+ * SNVS
58
+ */
59
+ sysbus_realize(SYS_BUS_DEVICE(&s->snvs), &error_abort);
60
+ sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, FSL_IMX6_SNVSHP_ADDR);
61
+
62
/*
63
* Watchdog
64
*/
28
--
65
--
29
2.20.1
66
2.34.1
30
31
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Mostafa Saleh <smostafa@google.com>
2
2
3
Embed the ADMAs into the SoC type.
3
In preparation for adding stage-2 support.
4
Add IDR0 fields related to stage-2.
4
5
5
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
6
VMID16: 16-bit VMID supported.
6
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
7
S2P: Stage-2 translation supported.
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
8
8
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
9
They are described in 6.3.1 SMMU_IDR0.
9
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
10
10
Message-id: 20200427181649.26851-7-edgar.iglesias@gmail.com
11
No functional change intended.
12
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Reviewed-by: Eric Auger <eric.auger@redhat.com>
15
Signed-off-by: Mostafa Saleh <smostafa@google.com>
16
Tested-by: Eric Auger <eric.auger@redhat.com>
17
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
18
Message-id: 20230516203327.2051088-2-smostafa@google.com
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
19
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
---
20
---
13
include/hw/arm/xlnx-versal.h | 3 ++-
21
hw/arm/smmuv3-internal.h | 2 ++
14
hw/arm/xlnx-versal.c | 14 +++++++-------
22
1 file changed, 2 insertions(+)
15
2 files changed, 9 insertions(+), 8 deletions(-)
16
23
17
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
24
diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h
18
index XXXXXXX..XXXXXXX 100644
25
index XXXXXXX..XXXXXXX 100644
19
--- a/include/hw/arm/xlnx-versal.h
26
--- a/hw/arm/smmuv3-internal.h
20
+++ b/include/hw/arm/xlnx-versal.h
27
+++ b/hw/arm/smmuv3-internal.h
21
@@ -XXX,XX +XXX,XX @@
28
@@ -XXX,XX +XXX,XX @@ typedef enum SMMUTranslationStatus {
22
#include "hw/arm/boot.h"
29
/* MMIO Registers */
23
#include "hw/intc/arm_gicv3.h"
30
24
#include "hw/char/pl011.h"
31
REG32(IDR0, 0x0)
25
+#include "hw/dma/xlnx-zdma.h"
32
+ FIELD(IDR0, S2P, 0 , 1)
26
#include "hw/net/cadence_gem.h"
33
FIELD(IDR0, S1P, 1 , 1)
27
34
FIELD(IDR0, TTF, 2 , 2)
28
#define TYPE_XLNX_VERSAL "xlnx-versal"
35
FIELD(IDR0, COHACC, 4 , 1)
29
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
36
FIELD(IDR0, ASID16, 12, 1)
30
struct {
37
+ FIELD(IDR0, VMID16, 18, 1)
31
PL011State uart[XLNX_VERSAL_NR_UARTS];
38
FIELD(IDR0, TTENDIAN, 21, 2)
32
CadenceGEMState gem[XLNX_VERSAL_NR_GEMS];
39
FIELD(IDR0, STALL_MODEL, 24, 2)
33
- SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS];
40
FIELD(IDR0, TERM_MODEL, 26, 1)
34
+ XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS];
35
} iou;
36
} lpd;
37
38
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
39
index XXXXXXX..XXXXXXX 100644
40
--- a/hw/arm/xlnx-versal.c
41
+++ b/hw/arm/xlnx-versal.c
42
@@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic)
43
DeviceState *dev;
44
MemoryRegion *mr;
45
46
- dev = qdev_create(NULL, "xlnx.zdma");
47
- s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev);
48
- object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width",
49
- &error_abort);
50
- object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
51
+ sysbus_init_child_obj(OBJECT(s), name,
52
+ &s->lpd.iou.adma[i], sizeof(s->lpd.iou.adma[i]),
53
+ TYPE_XLNX_ZDMA);
54
+ dev = DEVICE(&s->lpd.iou.adma[i]);
55
+ object_property_set_int(OBJECT(dev), 128, "bus-width", &error_abort);
56
qdev_init_nofail(dev);
57
58
- mr = sysbus_mmio_get_region(s->lpd.iou.adma[i], 0);
59
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
60
memory_region_add_subregion(&s->mr_ps,
61
MM_ADMA_CH0 + i * MM_ADMA_CH0_SIZE, mr);
62
63
- sysbus_connect_irq(s->lpd.iou.adma[i], 0, pic[VERSAL_ADMA_IRQ_0 + i]);
64
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[VERSAL_ADMA_IRQ_0 + i]);
65
g_free(name);
66
}
67
}
68
--
41
--
69
2.20.1
42
2.34.1
70
71
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Mostafa Saleh <smostafa@google.com>
2
2
3
Embed the GEMs into the SoC type.
3
In preparation for adding stage-2 support, add a S2 config
4
struct(SMMUS2Cfg), composed of the following fields and embedded in
5
the main SMMUTransCfg:
6
-tsz: Size of IPA input region (S2T0SZ)
7
-sl0: Start level of translation (S2SL0)
8
-affd: AF Fault Disable (S2AFFD)
9
-record_faults: Record fault events (S2R)
10
-granule_sz: Granule page shift (based on S2TG)
11
-vmid: Virtual Machine ID (S2VMID)
12
-vttb: Address of translation table base (S2TTB)
13
-eff_ps: Effective PA output range (based on S2PS)
4
14
5
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
15
They will be used in the next patches in stage-2 address translation.
6
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
16
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
17
The fields in SMMUS2Cfg, are reordered to make the shared and stage-1
8
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
18
fields next to each other, this reordering didn't change the struct
9
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
19
size (104 bytes before and after).
10
Message-id: 20200427181649.26851-6-edgar.iglesias@gmail.com
20
21
Stage-1 only fields: aa64, asid, tt, ttb, tbi, record_faults, oas.
22
oas is stage-1 output address size. However, it is used to check
23
input address in case stage-1 is unimplemented or bypassed according
24
to SMMUv3 manual IHI0070.E "3.4. Address sizes"
25
26
Shared fields: stage, disabled, bypassed, aborted, iotlb_*.
27
28
No functional change intended.
29
30
Reviewed-by: Eric Auger <eric.auger@redhat.com>
31
Signed-off-by: Mostafa Saleh <smostafa@google.com>
32
Tested-by: Eric Auger <eric.auger@redhat.com>
33
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
34
Message-id: 20230516203327.2051088-3-smostafa@google.com
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
35
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
---
36
---
13
include/hw/arm/xlnx-versal.h | 3 ++-
37
include/hw/arm/smmu-common.h | 22 +++++++++++++++++++---
14
hw/arm/xlnx-versal.c | 15 ++++++++-------
38
1 file changed, 19 insertions(+), 3 deletions(-)
15
2 files changed, 10 insertions(+), 8 deletions(-)
16
39
17
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
40
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
18
index XXXXXXX..XXXXXXX 100644
41
index XXXXXXX..XXXXXXX 100644
19
--- a/include/hw/arm/xlnx-versal.h
42
--- a/include/hw/arm/smmu-common.h
20
+++ b/include/hw/arm/xlnx-versal.h
43
+++ b/include/hw/arm/smmu-common.h
21
@@ -XXX,XX +XXX,XX @@
44
@@ -XXX,XX +XXX,XX @@ typedef struct SMMUTLBEntry {
22
#include "hw/arm/boot.h"
45
uint8_t granule;
23
#include "hw/intc/arm_gicv3.h"
46
} SMMUTLBEntry;
24
#include "hw/char/pl011.h"
47
25
+#include "hw/net/cadence_gem.h"
48
+/* Stage-2 configuration. */
26
49
+typedef struct SMMUS2Cfg {
27
#define TYPE_XLNX_VERSAL "xlnx-versal"
50
+ uint8_t tsz; /* Size of IPA input region (S2T0SZ) */
28
#define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL)
51
+ uint8_t sl0; /* Start level of translation (S2SL0) */
29
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
52
+ bool affd; /* AF Fault Disable (S2AFFD) */
30
53
+ bool record_faults; /* Record fault events (S2R) */
31
struct {
54
+ uint8_t granule_sz; /* Granule page shift (based on S2TG) */
32
PL011State uart[XLNX_VERSAL_NR_UARTS];
55
+ uint8_t eff_ps; /* Effective PA output range (based on S2PS) */
33
- SysBusDevice *gem[XLNX_VERSAL_NR_GEMS];
56
+ uint16_t vmid; /* Virtual Machine ID (S2VMID) */
34
+ CadenceGEMState gem[XLNX_VERSAL_NR_GEMS];
57
+ uint64_t vttb; /* Address of translation table base (S2TTB) */
35
SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS];
58
+} SMMUS2Cfg;
36
} iou;
59
+
37
} lpd;
60
/*
38
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
61
* Generic structure populated by derived SMMU devices
39
index XXXXXXX..XXXXXXX 100644
62
* after decoding the configuration information and used as
40
--- a/hw/arm/xlnx-versal.c
63
* input to the page table walk
41
+++ b/hw/arm/xlnx-versal.c
64
*/
42
@@ -XXX,XX +XXX,XX @@ static void versal_create_gems(Versal *s, qemu_irq *pic)
65
typedef struct SMMUTransCfg {
43
DeviceState *dev;
66
+ /* Shared fields between stage-1 and stage-2. */
44
MemoryRegion *mr;
67
int stage; /* translation stage */
45
68
- bool aa64; /* arch64 or aarch32 translation table */
46
- dev = qdev_create(NULL, "cadence_gem");
69
bool disabled; /* smmu is disabled */
47
- s->lpd.iou.gem[i] = SYS_BUS_DEVICE(dev);
70
bool bypassed; /* translation is bypassed */
48
- object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
71
bool aborted; /* translation is aborted */
49
+ sysbus_init_child_obj(OBJECT(s), name,
72
+ uint32_t iotlb_hits; /* counts IOTLB hits */
50
+ &s->lpd.iou.gem[i], sizeof(s->lpd.iou.gem[i]),
73
+ uint32_t iotlb_misses; /* counts IOTLB misses*/
51
+ TYPE_CADENCE_GEM);
74
+ /* Used by stage-1 only. */
52
+ dev = DEVICE(&s->lpd.iou.gem[i]);
75
+ bool aa64; /* arch64 or aarch32 translation table */
53
if (nd->used) {
76
bool record_faults; /* record fault events */
54
qemu_check_nic_model(nd, "cadence_gem");
77
uint64_t ttb; /* TT base address */
55
qdev_set_nic_properties(dev, nd);
78
uint8_t oas; /* output address width */
56
}
79
uint8_t tbi; /* Top Byte Ignore */
57
- object_property_set_int(OBJECT(s->lpd.iou.gem[i]),
80
uint16_t asid;
58
+ object_property_set_int(OBJECT(dev),
81
SMMUTransTableInfo tt[2];
59
2, "num-priority-queues",
82
- uint32_t iotlb_hits; /* counts IOTLB hits for this asid */
60
&error_abort);
83
- uint32_t iotlb_misses; /* counts IOTLB misses for this asid */
61
- object_property_set_link(OBJECT(s->lpd.iou.gem[i]),
84
+ /* Used by stage-2 only. */
62
+ object_property_set_link(OBJECT(dev),
85
+ struct SMMUS2Cfg s2cfg;
63
OBJECT(&s->mr_ps), "dma",
86
} SMMUTransCfg;
64
&error_abort);
87
65
qdev_init_nofail(dev);
88
typedef struct SMMUDevice {
66
67
- mr = sysbus_mmio_get_region(s->lpd.iou.gem[i], 0);
68
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
69
memory_region_add_subregion(&s->mr_ps, addrs[i], mr);
70
71
- sysbus_connect_irq(s->lpd.iou.gem[i], 0, pic[irqs[i]]);
72
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]);
73
g_free(name);
74
}
75
}
76
--
89
--
77
2.20.1
90
2.34.1
78
79
diff view generated by jsdifflib
1
Somewhere along theline we accidentally added a duplicate
1
From: Mostafa Saleh <smostafa@google.com>
2
"using D16-D31 when they don't exist" check to do_vfm_dp()
3
(probably an artifact of a patchseries rebase). Remove it.
4
2
3
In preparation for adding stage-2 support, rename smmu_ptw_64 to
4
smmu_ptw_64_s1 and refactor some of the code so it can be reused in
5
stage-2 page table walk.
6
7
Remove AA64 check from PTW as decode_cd already ensures that AA64 is
8
used, otherwise it faults with C_BAD_CD.
9
10
A stage member is added to SMMUPTWEventInfo to differentiate
11
between stage-1 and stage-2 ptw faults.
12
13
Add stage argument to trace_smmu_ptw_level be consistent with other
14
trace events.
15
16
Signed-off-by: Mostafa Saleh <smostafa@google.com>
17
Reviewed-by: Eric Auger <eric.auger@redhat.com>
18
Tested-by: Eric Auger <eric.auger@redhat.com>
19
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
20
Message-id: 20230516203327.2051088-4-smostafa@google.com
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
21
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
8
Message-id: 20200430181003.21682-2-peter.maydell@linaro.org
9
---
22
---
10
target/arm/translate-vfp.inc.c | 6 ------
23
include/hw/arm/smmu-common.h | 16 +++++++++++++---
11
1 file changed, 6 deletions(-)
24
hw/arm/smmu-common.c | 27 ++++++++++-----------------
25
hw/arm/smmuv3.c | 2 ++
26
hw/arm/trace-events | 2 +-
27
4 files changed, 26 insertions(+), 21 deletions(-)
12
28
13
diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
29
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
14
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/translate-vfp.inc.c
31
--- a/include/hw/arm/smmu-common.h
16
+++ b/target/arm/translate-vfp.inc.c
32
+++ b/include/hw/arm/smmu-common.h
17
@@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d)
33
@@ -XXX,XX +XXX,XX @@
18
return false;
34
#include "hw/pci/pci.h"
35
#include "qom/object.h"
36
37
-#define SMMU_PCI_BUS_MAX 256
38
-#define SMMU_PCI_DEVFN_MAX 256
39
-#define SMMU_PCI_DEVFN(sid) (sid & 0xFF)
40
+#define SMMU_PCI_BUS_MAX 256
41
+#define SMMU_PCI_DEVFN_MAX 256
42
+#define SMMU_PCI_DEVFN(sid) (sid & 0xFF)
43
+
44
+/* VMSAv8-64 Translation constants and functions */
45
+#define VMSA_LEVELS 4
46
+
47
+#define VMSA_STRIDE(gran) ((gran) - VMSA_LEVELS + 1)
48
+#define VMSA_BIT_LVL(isz, strd, lvl) ((isz) - (strd) * \
49
+ (VMSA_LEVELS - (lvl)))
50
+#define VMSA_IDXMSK(isz, strd, lvl) ((1ULL << \
51
+ VMSA_BIT_LVL(isz, strd, lvl)) - 1)
52
53
/*
54
* Page table walk error types
55
@@ -XXX,XX +XXX,XX @@ typedef enum {
56
} SMMUPTWEventType;
57
58
typedef struct SMMUPTWEventInfo {
59
+ int stage;
60
SMMUPTWEventType type;
61
dma_addr_t addr; /* fetched address that induced an abort, if any */
62
} SMMUPTWEventInfo;
63
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
64
index XXXXXXX..XXXXXXX 100644
65
--- a/hw/arm/smmu-common.c
66
+++ b/hw/arm/smmu-common.c
67
@@ -XXX,XX +XXX,XX @@ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova)
68
}
69
70
/**
71
- * smmu_ptw_64 - VMSAv8-64 Walk of the page tables for a given IOVA
72
+ * smmu_ptw_64_s1 - VMSAv8-64 Walk of the page tables for a given IOVA
73
* @cfg: translation config
74
* @iova: iova to translate
75
* @perm: access type
76
@@ -XXX,XX +XXX,XX @@ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova)
77
* Upon success, @tlbe is filled with translated_addr and entry
78
* permission rights.
79
*/
80
-static int smmu_ptw_64(SMMUTransCfg *cfg,
81
- dma_addr_t iova, IOMMUAccessFlags perm,
82
- SMMUTLBEntry *tlbe, SMMUPTWEventInfo *info)
83
+static int smmu_ptw_64_s1(SMMUTransCfg *cfg,
84
+ dma_addr_t iova, IOMMUAccessFlags perm,
85
+ SMMUTLBEntry *tlbe, SMMUPTWEventInfo *info)
86
{
87
dma_addr_t baseaddr, indexmask;
88
int stage = cfg->stage;
89
@@ -XXX,XX +XXX,XX @@ static int smmu_ptw_64(SMMUTransCfg *cfg,
19
}
90
}
20
91
21
- /* UNDEF accesses to D16-D31 if they don't exist. */
92
granule_sz = tt->granule_sz;
22
- if (!dc_isar_feature(aa32_simd_r32, s) &&
93
- stride = granule_sz - 3;
23
- ((a->vd | a->vn | a->vm) & 0x10)) {
94
+ stride = VMSA_STRIDE(granule_sz);
24
- return false;
95
inputsize = 64 - tt->tsz;
96
level = 4 - (inputsize - 4) / stride;
97
- indexmask = (1ULL << (inputsize - (stride * (4 - level)))) - 1;
98
+ indexmask = VMSA_IDXMSK(inputsize, stride, level);
99
baseaddr = extract64(tt->ttb, 0, 48);
100
baseaddr &= ~indexmask;
101
102
- while (level <= 3) {
103
+ while (level < VMSA_LEVELS) {
104
uint64_t subpage_size = 1ULL << level_shift(level, granule_sz);
105
uint64_t mask = subpage_size - 1;
106
uint32_t offset = iova_level_offset(iova, inputsize, level, granule_sz);
107
@@ -XXX,XX +XXX,XX @@ static int smmu_ptw_64(SMMUTransCfg *cfg,
108
if (get_pte(baseaddr, offset, &pte, info)) {
109
goto error;
110
}
111
- trace_smmu_ptw_level(level, iova, subpage_size,
112
+ trace_smmu_ptw_level(stage, level, iova, subpage_size,
113
baseaddr, offset, pte);
114
115
if (is_invalid_pte(pte) || is_reserved_pte(pte, level)) {
116
@@ -XXX,XX +XXX,XX @@ static int smmu_ptw_64(SMMUTransCfg *cfg,
117
info->type = SMMU_PTW_ERR_TRANSLATION;
118
119
error:
120
+ info->stage = 1;
121
tlbe->entry.perm = IOMMU_NONE;
122
return -EINVAL;
123
}
124
@@ -XXX,XX +XXX,XX @@ error:
125
int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm,
126
SMMUTLBEntry *tlbe, SMMUPTWEventInfo *info)
127
{
128
- if (!cfg->aa64) {
129
- /*
130
- * This code path is not entered as we check this while decoding
131
- * the configuration data in the derived SMMU model.
132
- */
133
- g_assert_not_reached();
25
- }
134
- }
26
-
135
-
27
if (!vfp_access_check(s)) {
136
- return smmu_ptw_64(cfg, iova, perm, tlbe, info);
28
return true;
137
+ return smmu_ptw_64_s1(cfg, iova, perm, tlbe, info);
29
}
138
}
139
140
/**
141
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
142
index XXXXXXX..XXXXXXX 100644
143
--- a/hw/arm/smmuv3.c
144
+++ b/hw/arm/smmuv3.c
145
@@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
146
cached_entry = g_new0(SMMUTLBEntry, 1);
147
148
if (smmu_ptw(cfg, aligned_addr, flag, cached_entry, &ptw_info)) {
149
+ /* All faults from PTW has S2 field. */
150
+ event.u.f_walk_eabt.s2 = (ptw_info.stage == 2);
151
g_free(cached_entry);
152
switch (ptw_info.type) {
153
case SMMU_PTW_ERR_WALK_EABT:
154
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
155
index XXXXXXX..XXXXXXX 100644
156
--- a/hw/arm/trace-events
157
+++ b/hw/arm/trace-events
158
@@ -XXX,XX +XXX,XX @@ virt_acpi_setup(void) "No fw cfg or ACPI disabled. Bailing out."
159
160
# smmu-common.c
161
smmu_add_mr(const char *name) "%s"
162
-smmu_ptw_level(int level, uint64_t iova, size_t subpage_size, uint64_t baseaddr, uint32_t offset, uint64_t pte) "level=%d iova=0x%"PRIx64" subpage_sz=0x%zx baseaddr=0x%"PRIx64" offset=%d => pte=0x%"PRIx64
163
+smmu_ptw_level(int stage, int level, uint64_t iova, size_t subpage_size, uint64_t baseaddr, uint32_t offset, uint64_t pte) "stage=%d level=%d iova=0x%"PRIx64" subpage_sz=0x%zx baseaddr=0x%"PRIx64" offset=%d => pte=0x%"PRIx64
164
smmu_ptw_invalid_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint32_t offset, uint64_t pte) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" offset=%d pte=0x%"PRIx64
165
smmu_ptw_page_pte(int stage, int level, uint64_t iova, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t address) "stage=%d level=%d iova=0x%"PRIx64" base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" page address = 0x%"PRIx64
166
smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t iova, uint64_t gpa, int bsize_mb) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" iova=0x%"PRIx64" block address = 0x%"PRIx64" block size = %d MiB"
30
--
167
--
31
2.20.1
168
2.34.1
32
33
diff view generated by jsdifflib
1
The ARMv8.2-TTS2UXN feature extends the XN field in stage 2
1
From: Mostafa Saleh <smostafa@google.com>
2
translation table descriptors from just bit [54] to bits [54:53],
2
3
allowing stage 2 to control execution permissions separately for EL0
3
In preparation for adding stage-2 support, add Stage-2 PTW code.
4
and EL1. Implement the new semantics of the XN field and enable
4
Only Aarch64 format is supported as stage-1.
5
the feature for our 'max' CPU.
5
6
6
Nesting stage-1 and stage-2 is not supported right now.
7
8
HTTU is not supported, SW is expected to maintain the Access flag.
9
This is described in the SMMUv3 manual(IHI 0070.E.a)
10
"5.2. Stream Table Entry" in "[181] S2AFFD".
11
This flag determines the behavior on access of a stage-2 page whose
12
descriptor has AF == 0:
13
- 0b0: An Access flag fault occurs (stall not supported).
14
- 0b1: An Access flag fault never occurs.
15
An Access fault takes priority over a Permission fault.
16
17
There are 3 address size checks for stage-2 according to
18
(IHI 0070.E.a) in "3.4. Address sizes".
19
- As nesting is not supported, input address is passed directly to
20
stage-2, and is checked against IAS.
21
We use cfg->oas to hold the OAS when stage-1 is not used, this is set
22
in the next patch.
23
This check is done outside of smmu_ptw_64_s2 as it is not part of
24
stage-2(it throws stage-1 fault), and the stage-2 function shouldn't
25
change it's behavior when nesting is supported.
26
When nesting is supported and we figure out how to combine TLB for
27
stage-1 and stage-2 we can move this check into the stage-1 function
28
as described in ARM DDI0487I.a in pseudocode
29
aarch64/translation/vmsa_translation/AArch64.S1Translate
30
aarch64/translation/vmsa_translation/AArch64.S1DisabledOutput
31
32
- Input to stage-2 is checked against s2t0sz, and throws stage-2
33
transaltion fault if exceeds it.
34
35
- Output of stage-2 is checked against effective PA output range.
36
37
Reviewed-by: Eric Auger <eric.auger@redhat.com>
38
Signed-off-by: Mostafa Saleh <smostafa@google.com>
39
Tested-by: Eric Auger <eric.auger@redhat.com>
40
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
41
Message-id: 20230516203327.2051088-5-smostafa@google.com
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
42
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
10
Message-id: 20200330210400.11724-5-peter.maydell@linaro.org
11
---
43
---
12
target/arm/cpu.h | 15 +++++++++++++++
44
hw/arm/smmu-internal.h | 35 ++++++++++
13
target/arm/cpu.c | 1 +
45
hw/arm/smmu-common.c | 142 ++++++++++++++++++++++++++++++++++++++++-
14
target/arm/cpu64.c | 2 ++
46
2 files changed, 176 insertions(+), 1 deletion(-)
15
target/arm/helper.c | 37 +++++++++++++++++++++++++++++++------
47
16
4 files changed, 49 insertions(+), 6 deletions(-)
48
diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h
17
18
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
19
index XXXXXXX..XXXXXXX 100644
49
index XXXXXXX..XXXXXXX 100644
20
--- a/target/arm/cpu.h
50
--- a/hw/arm/smmu-internal.h
21
+++ b/target/arm/cpu.h
51
+++ b/hw/arm/smmu-internal.h
22
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id)
52
@@ -XXX,XX +XXX,XX @@
23
return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0;
53
#define PTE_APTABLE(pte) \
54
(extract64(pte, 61, 2))
55
56
+#define PTE_AF(pte) \
57
+ (extract64(pte, 10, 1))
58
/*
59
* TODO: At the moment all transactions are considered as privileged (EL1)
60
* as IOMMU translation callback does not pass user/priv attributes.
61
@@ -XXX,XX +XXX,XX @@
62
#define is_permission_fault(ap, perm) \
63
(((perm) & IOMMU_WO) && ((ap) & 0x2))
64
65
+#define is_permission_fault_s2(s2ap, perm) \
66
+ (!(((s2ap) & (perm)) == (perm)))
67
+
68
#define PTE_AP_TO_PERM(ap) \
69
(IOMMU_ACCESS_FLAG(true, !((ap) & 0x2)))
70
71
@@ -XXX,XX +XXX,XX @@ uint64_t iova_level_offset(uint64_t iova, int inputsize,
72
MAKE_64BIT_MASK(0, gsz - 3);
24
}
73
}
25
74
26
+static inline bool isar_feature_aa32_tts2uxn(const ARMISARegisters *id)
75
+/* FEAT_LPA2 and FEAT_TTST are not implemented. */
76
+static inline int get_start_level(int sl0 , int granule_sz)
27
+{
77
+{
28
+ return FIELD_EX32(id->id_mmfr4, ID_MMFR4, XNX) != 0;
78
+ /* ARM DDI0487I.a: Table D8-12. */
79
+ if (granule_sz == 12) {
80
+ return 2 - sl0;
81
+ }
82
+ /* ARM DDI0487I.a: Table D8-22 and Table D8-31. */
83
+ return 3 - sl0;
29
+}
84
+}
30
+
85
+
31
/*
86
+/*
32
* 64-bit feature tests via id registers.
87
+ * Index in a concatenated first level stage-2 page table.
33
*/
88
+ * ARM DDI0487I.a: D8.2.2 Concatenated translation tables.
34
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id)
89
+ */
35
return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0;
90
+static inline int pgd_concat_idx(int start_level, int granule_sz,
91
+ dma_addr_t ipa)
92
+{
93
+ uint64_t ret;
94
+ /*
95
+ * Get the number of bits handled by next levels, then any extra bits in
96
+ * the address should index the concatenated tables. This relation can be
97
+ * deduced from tables in ARM DDI0487I.a: D8.2.7-9
98
+ */
99
+ int shift = level_shift(start_level - 1, granule_sz);
100
+
101
+ ret = ipa >> shift;
102
+ return ret;
103
+}
104
+
105
#define SMMU_IOTLB_ASID(key) ((key).asid)
106
107
typedef struct SMMUIOTLBPageInvInfo {
108
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
109
index XXXXXXX..XXXXXXX 100644
110
--- a/hw/arm/smmu-common.c
111
+++ b/hw/arm/smmu-common.c
112
@@ -XXX,XX +XXX,XX @@ error:
113
return -EINVAL;
36
}
114
}
37
115
38
+static inline bool isar_feature_aa64_tts2uxn(const ARMISARegisters *id)
116
+/**
117
+ * smmu_ptw_64_s2 - VMSAv8-64 Walk of the page tables for a given ipa
118
+ * for stage-2.
119
+ * @cfg: translation config
120
+ * @ipa: ipa to translate
121
+ * @perm: access type
122
+ * @tlbe: SMMUTLBEntry (out)
123
+ * @info: handle to an error info
124
+ *
125
+ * Return 0 on success, < 0 on error. In case of error, @info is filled
126
+ * and tlbe->perm is set to IOMMU_NONE.
127
+ * Upon success, @tlbe is filled with translated_addr and entry
128
+ * permission rights.
129
+ */
130
+static int smmu_ptw_64_s2(SMMUTransCfg *cfg,
131
+ dma_addr_t ipa, IOMMUAccessFlags perm,
132
+ SMMUTLBEntry *tlbe, SMMUPTWEventInfo *info)
39
+{
133
+{
40
+ return FIELD_EX64(id->id_aa64mmfr1, ID_AA64MMFR1, XNX) != 0;
134
+ const int stage = 2;
135
+ int granule_sz = cfg->s2cfg.granule_sz;
136
+ /* ARM DDI0487I.a: Table D8-7. */
137
+ int inputsize = 64 - cfg->s2cfg.tsz;
138
+ int level = get_start_level(cfg->s2cfg.sl0, granule_sz);
139
+ int stride = VMSA_STRIDE(granule_sz);
140
+ int idx = pgd_concat_idx(level, granule_sz, ipa);
141
+ /*
142
+ * Get the ttb from concatenated structure.
143
+ * The offset is the idx * size of each ttb(number of ptes * (sizeof(pte))
144
+ */
145
+ uint64_t baseaddr = extract64(cfg->s2cfg.vttb, 0, 48) + (1 << stride) *
146
+ idx * sizeof(uint64_t);
147
+ dma_addr_t indexmask = VMSA_IDXMSK(inputsize, stride, level);
148
+
149
+ baseaddr &= ~indexmask;
150
+
151
+ /*
152
+ * On input, a stage 2 Translation fault occurs if the IPA is outside the
153
+ * range configured by the relevant S2T0SZ field of the STE.
154
+ */
155
+ if (ipa >= (1ULL << inputsize)) {
156
+ info->type = SMMU_PTW_ERR_TRANSLATION;
157
+ goto error;
158
+ }
159
+
160
+ while (level < VMSA_LEVELS) {
161
+ uint64_t subpage_size = 1ULL << level_shift(level, granule_sz);
162
+ uint64_t mask = subpage_size - 1;
163
+ uint32_t offset = iova_level_offset(ipa, inputsize, level, granule_sz);
164
+ uint64_t pte, gpa;
165
+ dma_addr_t pte_addr = baseaddr + offset * sizeof(pte);
166
+ uint8_t s2ap;
167
+
168
+ if (get_pte(baseaddr, offset, &pte, info)) {
169
+ goto error;
170
+ }
171
+ trace_smmu_ptw_level(stage, level, ipa, subpage_size,
172
+ baseaddr, offset, pte);
173
+ if (is_invalid_pte(pte) || is_reserved_pte(pte, level)) {
174
+ trace_smmu_ptw_invalid_pte(stage, level, baseaddr,
175
+ pte_addr, offset, pte);
176
+ break;
177
+ }
178
+
179
+ if (is_table_pte(pte, level)) {
180
+ baseaddr = get_table_pte_address(pte, granule_sz);
181
+ level++;
182
+ continue;
183
+ } else if (is_page_pte(pte, level)) {
184
+ gpa = get_page_pte_address(pte, granule_sz);
185
+ trace_smmu_ptw_page_pte(stage, level, ipa,
186
+ baseaddr, pte_addr, pte, gpa);
187
+ } else {
188
+ uint64_t block_size;
189
+
190
+ gpa = get_block_pte_address(pte, level, granule_sz,
191
+ &block_size);
192
+ trace_smmu_ptw_block_pte(stage, level, baseaddr,
193
+ pte_addr, pte, ipa, gpa,
194
+ block_size >> 20);
195
+ }
196
+
197
+ /*
198
+ * If S2AFFD and PTE.AF are 0 => fault. (5.2. Stream Table Entry)
199
+ * An Access fault takes priority over a Permission fault.
200
+ */
201
+ if (!PTE_AF(pte) && !cfg->s2cfg.affd) {
202
+ info->type = SMMU_PTW_ERR_ACCESS;
203
+ goto error;
204
+ }
205
+
206
+ s2ap = PTE_AP(pte);
207
+ if (is_permission_fault_s2(s2ap, perm)) {
208
+ info->type = SMMU_PTW_ERR_PERMISSION;
209
+ goto error;
210
+ }
211
+
212
+ /*
213
+ * The address output from the translation causes a stage 2 Address
214
+ * Size fault if it exceeds the effective PA output range.
215
+ */
216
+ if (gpa >= (1ULL << cfg->s2cfg.eff_ps)) {
217
+ info->type = SMMU_PTW_ERR_ADDR_SIZE;
218
+ goto error;
219
+ }
220
+
221
+ tlbe->entry.translated_addr = gpa;
222
+ tlbe->entry.iova = ipa & ~mask;
223
+ tlbe->entry.addr_mask = mask;
224
+ tlbe->entry.perm = s2ap;
225
+ tlbe->level = level;
226
+ tlbe->granule = granule_sz;
227
+ return 0;
228
+ }
229
+ info->type = SMMU_PTW_ERR_TRANSLATION;
230
+
231
+error:
232
+ info->stage = 2;
233
+ tlbe->entry.perm = IOMMU_NONE;
234
+ return -EINVAL;
41
+}
235
+}
42
+
236
+
43
/*
237
/**
44
* Feature tests for "does this exist in either 32-bit or 64-bit?"
238
* smmu_ptw - Walk the page tables for an IOVA, according to @cfg
45
*/
239
*
46
@@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_any_ccidx(const ARMISARegisters *id)
240
@@ -XXX,XX +XXX,XX @@ error:
47
return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id);
241
int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm,
242
SMMUTLBEntry *tlbe, SMMUPTWEventInfo *info)
243
{
244
- return smmu_ptw_64_s1(cfg, iova, perm, tlbe, info);
245
+ if (cfg->stage == 1) {
246
+ return smmu_ptw_64_s1(cfg, iova, perm, tlbe, info);
247
+ } else if (cfg->stage == 2) {
248
+ /*
249
+ * If bypassing stage 1(or unimplemented), the input address is passed
250
+ * directly to stage 2 as IPA. If the input address of a transaction
251
+ * exceeds the size of the IAS, a stage 1 Address Size fault occurs.
252
+ * For AA64, IAS = OAS according to (IHI 0070.E.a) "3.4 Address sizes"
253
+ */
254
+ if (iova >= (1ULL << cfg->oas)) {
255
+ info->type = SMMU_PTW_ERR_ADDR_SIZE;
256
+ info->stage = 1;
257
+ tlbe->entry.perm = IOMMU_NONE;
258
+ return -EINVAL;
259
+ }
260
+
261
+ return smmu_ptw_64_s2(cfg, iova, perm, tlbe, info);
262
+ }
263
+
264
+ g_assert_not_reached();
48
}
265
}
49
266
50
+static inline bool isar_feature_any_tts2uxn(const ARMISARegisters *id)
267
/**
51
+{
52
+ return isar_feature_aa64_tts2uxn(id) || isar_feature_aa32_tts2uxn(id);
53
+}
54
+
55
/*
56
* Forward to the above feature tests given an ARMCPU pointer.
57
*/
58
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
59
index XXXXXXX..XXXXXXX 100644
60
--- a/target/arm/cpu.c
61
+++ b/target/arm/cpu.c
62
@@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj)
63
t = FIELD_DP32(t, ID_MMFR4, HPDS, 1); /* AA32HPD */
64
t = FIELD_DP32(t, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */
65
t = FIELD_DP32(t, ID_MMFR4, CNP, 1); /* TTCNP */
66
+ t = FIELD_DP32(t, ID_MMFR4, XNX, 1); /* TTS2UXN */
67
cpu->isar.id_mmfr4 = t;
68
}
69
#endif
70
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
71
index XXXXXXX..XXXXXXX 100644
72
--- a/target/arm/cpu64.c
73
+++ b/target/arm/cpu64.c
74
@@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj)
75
t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1);
76
t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 2); /* ATS1E1 */
77
t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* VMID16 */
78
+ t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* TTS2UXN */
79
cpu->isar.id_aa64mmfr1 = t;
80
81
t = cpu->isar.id_aa64mmfr2;
82
@@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj)
83
u = FIELD_DP32(u, ID_MMFR4, HPDS, 1); /* AA32HPD */
84
u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */
85
u = FIELD_DP32(u, ID_MMFR4, CNP, 1); /* TTCNP */
86
+ u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */
87
cpu->isar.id_mmfr4 = u;
88
89
u = cpu->isar.id_aa64dfr0;
90
diff --git a/target/arm/helper.c b/target/arm/helper.c
91
index XXXXXXX..XXXXXXX 100644
92
--- a/target/arm/helper.c
93
+++ b/target/arm/helper.c
94
@@ -XXX,XX +XXX,XX @@ simple_ap_to_rw_prot(CPUARMState *env, ARMMMUIdx mmu_idx, int ap)
95
*
96
* @env: CPUARMState
97
* @s2ap: The 2-bit stage2 access permissions (S2AP)
98
- * @xn: XN (execute-never) bit
99
+ * @xn: XN (execute-never) bits
100
+ * @s1_is_el0: true if this is S2 of an S1+2 walk for EL0
101
*/
102
-static int get_S2prot(CPUARMState *env, int s2ap, int xn)
103
+static int get_S2prot(CPUARMState *env, int s2ap, int xn, bool s1_is_el0)
104
{
105
int prot = 0;
106
107
@@ -XXX,XX +XXX,XX @@ static int get_S2prot(CPUARMState *env, int s2ap, int xn)
108
if (s2ap & 2) {
109
prot |= PAGE_WRITE;
110
}
111
- if (!xn) {
112
- if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) {
113
+
114
+ if (cpu_isar_feature(any_tts2uxn, env_archcpu(env))) {
115
+ switch (xn) {
116
+ case 0:
117
prot |= PAGE_EXEC;
118
+ break;
119
+ case 1:
120
+ if (s1_is_el0) {
121
+ prot |= PAGE_EXEC;
122
+ }
123
+ break;
124
+ case 2:
125
+ break;
126
+ case 3:
127
+ if (!s1_is_el0) {
128
+ prot |= PAGE_EXEC;
129
+ }
130
+ break;
131
+ default:
132
+ g_assert_not_reached();
133
+ }
134
+ } else {
135
+ if (!extract32(xn, 1, 1)) {
136
+ if (arm_el_is_aa64(env, 2) || prot & PAGE_READ) {
137
+ prot |= PAGE_EXEC;
138
+ }
139
}
140
}
141
return prot;
142
@@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
143
}
144
145
ap = extract32(attrs, 4, 2);
146
- xn = extract32(attrs, 12, 1);
147
148
if (mmu_idx == ARMMMUIdx_Stage2) {
149
ns = true;
150
- *prot = get_S2prot(env, ap, xn);
151
+ xn = extract32(attrs, 11, 2);
152
+ *prot = get_S2prot(env, ap, xn, s1_is_el0);
153
} else {
154
ns = extract32(attrs, 3, 1);
155
+ xn = extract32(attrs, 12, 1);
156
pxn = extract32(attrs, 11, 1);
157
*prot = get_S1prot(env, mmu_idx, aarch64, ap, ns, xn, pxn);
158
}
159
--
268
--
160
2.20.1
269
2.34.1
161
162
diff view generated by jsdifflib
1
Convert the Neon 3-reg-same VADD and VSUB insns to decodetree.
1
From: Mostafa Saleh <smostafa@google.com>
2
2
3
Note that we don't need the neon_3r_sizes[op] check here because all
3
Parse stage-2 configuration from STE and populate it in SMMUS2Cfg.
4
size values are OK for VADD and VSUB; we'll add this when we convert
4
Validity of field values are checked when possible.
5
the first insn that has size restrictions.
5
6
6
Only AA64 tables are supported and Small Translation Tables (STT) are
7
For this we need one of the GVecGen*Fn typedefs currently in
7
not supported.
8
translate-a64.h; move them all to translate.h as a block so they
8
9
are visible to the 32-bit decoder.
9
According to SMMUv3 UM(IHI0070E) "5.2 Stream Table Entry": All fields
10
10
with an S2 prefix (with the exception of S2VMID) are IGNORED when
11
stage-2 bypasses translation (Config[1] == 0).
12
13
Which means that VMID can be used(for TLB tagging) even if stage-2 is
14
bypassed, so we parse it unconditionally when S2P exists. Otherwise
15
it is set to -1.(only S1P)
16
17
As stall is not supported, if S2S is set the translation would abort.
18
For S2R, we reuse the same code used for stage-1 with flag
19
record_faults. However when nested translation is supported we would
20
need to separate stage-1 and stage-2 faults.
21
22
Fix wrong shift in STE_S2HD, STE_S2HA, STE_S2S.
23
24
Signed-off-by: Mostafa Saleh <smostafa@google.com>
25
Tested-by: Eric Auger <eric.auger@redhat.com>
26
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
27
Reviewed-by: Eric Auger <eric.auger@redhat.com>
28
Message-id: 20230516203327.2051088-6-smostafa@google.com
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
29
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
13
Message-id: 20200430181003.21682-15-peter.maydell@linaro.org
14
---
30
---
15
target/arm/translate-a64.h | 9 --------
31
hw/arm/smmuv3-internal.h | 10 +-
16
target/arm/translate.h | 9 ++++++++
32
include/hw/arm/smmu-common.h | 1 +
17
target/arm/neon-dp.decode | 17 +++++++++++++++
33
include/hw/arm/smmuv3.h | 3 +
18
target/arm/translate-neon.inc.c | 38 +++++++++++++++++++++++++++++++++
34
hw/arm/smmuv3.c | 181 +++++++++++++++++++++++++++++++++--
19
target/arm/translate.c | 14 ++++--------
35
4 files changed, 185 insertions(+), 10 deletions(-)
20
5 files changed, 68 insertions(+), 19 deletions(-)
36
21
37
diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h
22
diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h
23
index XXXXXXX..XXXXXXX 100644
38
index XXXXXXX..XXXXXXX 100644
24
--- a/target/arm/translate-a64.h
39
--- a/hw/arm/smmuv3-internal.h
25
+++ b/target/arm/translate-a64.h
40
+++ b/hw/arm/smmuv3-internal.h
26
@@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s)
41
@@ -XXX,XX +XXX,XX @@ typedef struct CD {
27
42
#define STE_S2TG(x) extract32((x)->word[5], 14, 2)
28
bool disas_sve(DisasContext *, uint32_t);
43
#define STE_S2PS(x) extract32((x)->word[5], 16, 3)
29
44
#define STE_S2AA64(x) extract32((x)->word[5], 19, 1)
30
-/* Note that the gvec expanders operate on offsets + sizes. */
45
-#define STE_S2HD(x) extract32((x)->word[5], 24, 1)
31
-typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t);
46
-#define STE_S2HA(x) extract32((x)->word[5], 25, 1)
32
-typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t,
47
-#define STE_S2S(x) extract32((x)->word[5], 26, 1)
33
- uint32_t, uint32_t);
48
+#define STE_S2ENDI(x) extract32((x)->word[5], 20, 1)
34
-typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
49
+#define STE_S2AFFD(x) extract32((x)->word[5], 21, 1)
35
- uint32_t, uint32_t, uint32_t);
50
+#define STE_S2HD(x) extract32((x)->word[5], 23, 1)
36
-typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
51
+#define STE_S2HA(x) extract32((x)->word[5], 24, 1)
37
- uint32_t, uint32_t, uint32_t);
52
+#define STE_S2S(x) extract32((x)->word[5], 25, 1)
38
-
53
+#define STE_S2R(x) extract32((x)->word[5], 26, 1)
39
#endif /* TARGET_ARM_TRANSLATE_A64_H */
54
+
40
diff --git a/target/arm/translate.h b/target/arm/translate.h
55
#define STE_CTXPTR(x) \
56
({ \
57
unsigned long addr; \
58
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
41
index XXXXXXX..XXXXXXX 100644
59
index XXXXXXX..XXXXXXX 100644
42
--- a/target/arm/translate.h
60
--- a/include/hw/arm/smmu-common.h
43
+++ b/target/arm/translate.h
61
+++ b/include/hw/arm/smmu-common.h
44
@@ -XXX,XX +XXX,XX @@ void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b);
62
@@ -XXX,XX +XXX,XX @@
45
#define dc_isar_feature(name, ctx) \
63
46
({ DisasContext *ctx_ = (ctx); isar_feature_##name(ctx_->isar); })
64
/* VMSAv8-64 Translation constants and functions */
47
65
#define VMSA_LEVELS 4
48
+/* Note that the gvec expanders operate on offsets + sizes. */
66
+#define VMSA_MAX_S2_CONCAT 16
49
+typedef void GVecGen2Fn(unsigned, uint32_t, uint32_t, uint32_t, uint32_t);
67
50
+typedef void GVecGen2iFn(unsigned, uint32_t, uint32_t, int64_t,
68
#define VMSA_STRIDE(gran) ((gran) - VMSA_LEVELS + 1)
51
+ uint32_t, uint32_t);
69
#define VMSA_BIT_LVL(isz, strd, lvl) ((isz) - (strd) * \
52
+typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
70
diff --git a/include/hw/arm/smmuv3.h b/include/hw/arm/smmuv3.h
53
+ uint32_t, uint32_t, uint32_t);
54
+typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
55
+ uint32_t, uint32_t, uint32_t);
56
+
57
#endif /* TARGET_ARM_TRANSLATE_H */
58
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
59
index XXXXXXX..XXXXXXX 100644
71
index XXXXXXX..XXXXXXX 100644
60
--- a/target/arm/neon-dp.decode
72
--- a/include/hw/arm/smmuv3.h
61
+++ b/target/arm/neon-dp.decode
73
+++ b/include/hw/arm/smmuv3.h
74
@@ -XXX,XX +XXX,XX @@ struct SMMUv3Class {
75
#define TYPE_ARM_SMMUV3 "arm-smmuv3"
76
OBJECT_DECLARE_TYPE(SMMUv3State, SMMUv3Class, ARM_SMMUV3)
77
78
+#define STAGE1_SUPPORTED(s) FIELD_EX32(s->idr[0], IDR0, S1P)
79
+#define STAGE2_SUPPORTED(s) FIELD_EX32(s->idr[0], IDR0, S2P)
80
+
81
#endif
82
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
83
index XXXXXXX..XXXXXXX 100644
84
--- a/hw/arm/smmuv3.c
85
+++ b/hw/arm/smmuv3.c
62
@@ -XXX,XX +XXX,XX @@
86
@@ -XXX,XX +XXX,XX @@
63
#
87
#include "smmuv3-internal.h"
64
# This file is processed by scripts/decodetree.py
88
#include "smmu-internal.h"
65
#
89
66
+# VFP/Neon register fields; same as vfp.decode
90
+#define PTW_RECORD_FAULT(cfg) (((cfg)->stage == 1) ? (cfg)->record_faults : \
67
+%vm_dp 5:1 0:4
91
+ (cfg)->s2cfg.record_faults)
68
+%vn_dp 7:1 16:4
92
+
69
+%vd_dp 22:1 12:4
93
/**
70
94
* smmuv3_trigger_irq - pulse @irq if enabled and update
71
# Encodings for Neon data processing instructions where the T32 encoding
95
* GERROR register in case of GERROR interrupt
72
# is a simple transformation of the A32 encoding.
96
@@ -XXX,XX +XXX,XX @@ static int smmu_get_cd(SMMUv3State *s, STE *ste, uint32_t ssid,
73
@@ -XXX,XX +XXX,XX @@
97
return 0;
74
# 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
75
# This file works on the A32 encoding only; calling code for T32 has to
76
# transform the insn into the A32 version first.
77
+
78
+######################################################################
79
+# 3-reg-same grouping:
80
+# 1111 001 U 0 D sz:2 Vn:4 Vd:4 opc:4 N Q M op Vm:4
81
+######################################################################
82
+
83
+&3same vm vn vd q size
84
+
85
+@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \
86
+ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
87
+
88
+VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same
89
+VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
90
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
91
index XXXXXXX..XXXXXXX 100644
92
--- a/target/arm/translate-neon.inc.c
93
+++ b/target/arm/translate-neon.inc.c
94
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
95
96
return true;
97
}
98
}
98
+
99
99
+static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn)
100
+/*
101
+ * Max valid value is 39 when SMMU_IDR3.STT == 0.
102
+ * In architectures after SMMUv3.0:
103
+ * - If STE.S2TG selects a 4KB or 16KB granule, the minimum valid value for this
104
+ * field is MAX(16, 64-IAS)
105
+ * - If STE.S2TG selects a 64KB granule, the minimum valid value for this field
106
+ * is (64-IAS).
107
+ * As we only support AA64, IAS = OAS.
108
+ */
109
+static bool s2t0sz_valid(SMMUTransCfg *cfg)
100
+{
110
+{
101
+ int vec_size = a->q ? 16 : 8;
111
+ if (cfg->s2cfg.tsz > 39) {
102
+ int rd_ofs = neon_reg_offset(a->vd, 0);
103
+ int rn_ofs = neon_reg_offset(a->vn, 0);
104
+ int rm_ofs = neon_reg_offset(a->vm, 0);
105
+
106
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
107
+ return false;
112
+ return false;
108
+ }
113
+ }
109
+
114
+
110
+ /* UNDEF accesses to D16-D31 if they don't exist. */
115
+ if (cfg->s2cfg.granule_sz == 16) {
111
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
116
+ return (cfg->s2cfg.tsz >= 64 - oas2bits(SMMU_IDR5_OAS));
112
+ ((a->vd | a->vn | a->vm) & 0x10)) {
117
+ }
113
+ return false;
118
+
114
+ }
119
+ return (cfg->s2cfg.tsz >= MAX(64 - oas2bits(SMMU_IDR5_OAS), 16));
115
+
116
+ if ((a->vn | a->vm | a->vd) & a->q) {
117
+ return false;
118
+ }
119
+
120
+ if (!vfp_access_check(s)) {
121
+ return true;
122
+ }
123
+
124
+ fn(a->size, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size);
125
+ return true;
126
+}
120
+}
127
+
121
+
128
+#define DO_3SAME(INSN, FUNC) \
122
+/*
129
+ static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \
123
+ * Return true if s2 page table config is valid.
130
+ { \
124
+ * This checks with the configured start level, ias_bits and granularity we can
131
+ return do_3same(s, a, FUNC); \
125
+ * have a valid page table as described in ARM ARM D8.2 Translation process.
132
+ }
126
+ * The idea here is to see for the highest possible number of IPA bits, how
133
+
127
+ * many concatenated tables we would need, if it is more than 16, then this is
134
+DO_3SAME(VADD, tcg_gen_gvec_add)
128
+ * not possible.
135
+DO_3SAME(VSUB, tcg_gen_gvec_sub)
129
+ */
136
diff --git a/target/arm/translate.c b/target/arm/translate.c
130
+static bool s2_pgtable_config_valid(uint8_t sl0, uint8_t t0sz, uint8_t gran)
137
index XXXXXXX..XXXXXXX 100644
131
+{
138
--- a/target/arm/translate.c
132
+ int level = get_start_level(sl0, gran);
139
+++ b/target/arm/translate.c
133
+ uint64_t ipa_bits = 64 - t0sz;
140
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
134
+ uint64_t max_ipa = (1ULL << ipa_bits) - 1;
135
+ int nr_concat = pgd_concat_idx(level, gran, max_ipa) + 1;
136
+
137
+ return nr_concat <= VMSA_MAX_S2_CONCAT;
138
+}
139
+
140
+static int decode_ste_s2_cfg(SMMUTransCfg *cfg, STE *ste)
141
+{
142
+ cfg->stage = 2;
143
+
144
+ if (STE_S2AA64(ste) == 0x0) {
145
+ qemu_log_mask(LOG_UNIMP,
146
+ "SMMUv3 AArch32 tables not supported\n");
147
+ g_assert_not_reached();
148
+ }
149
+
150
+ switch (STE_S2TG(ste)) {
151
+ case 0x0: /* 4KB */
152
+ cfg->s2cfg.granule_sz = 12;
153
+ break;
154
+ case 0x1: /* 64KB */
155
+ cfg->s2cfg.granule_sz = 16;
156
+ break;
157
+ case 0x2: /* 16KB */
158
+ cfg->s2cfg.granule_sz = 14;
159
+ break;
160
+ default:
161
+ qemu_log_mask(LOG_GUEST_ERROR,
162
+ "SMMUv3 bad STE S2TG: %x\n", STE_S2TG(ste));
163
+ goto bad_ste;
164
+ }
165
+
166
+ cfg->s2cfg.vttb = STE_S2TTB(ste);
167
+
168
+ cfg->s2cfg.sl0 = STE_S2SL0(ste);
169
+ /* FEAT_TTST not supported. */
170
+ if (cfg->s2cfg.sl0 == 0x3) {
171
+ qemu_log_mask(LOG_UNIMP, "SMMUv3 S2SL0 = 0x3 has no meaning!\n");
172
+ goto bad_ste;
173
+ }
174
+
175
+ /* For AA64, The effective S2PS size is capped to the OAS. */
176
+ cfg->s2cfg.eff_ps = oas2bits(MIN(STE_S2PS(ste), SMMU_IDR5_OAS));
177
+ /*
178
+ * It is ILLEGAL for the address in S2TTB to be outside the range
179
+ * described by the effective S2PS value.
180
+ */
181
+ if (cfg->s2cfg.vttb & ~(MAKE_64BIT_MASK(0, cfg->s2cfg.eff_ps))) {
182
+ qemu_log_mask(LOG_GUEST_ERROR,
183
+ "SMMUv3 S2TTB too large 0x%lx, effective PS %d bits\n",
184
+ cfg->s2cfg.vttb, cfg->s2cfg.eff_ps);
185
+ goto bad_ste;
186
+ }
187
+
188
+ cfg->s2cfg.tsz = STE_S2T0SZ(ste);
189
+
190
+ if (!s2t0sz_valid(cfg)) {
191
+ qemu_log_mask(LOG_GUEST_ERROR, "SMMUv3 bad STE S2T0SZ = %d\n",
192
+ cfg->s2cfg.tsz);
193
+ goto bad_ste;
194
+ }
195
+
196
+ if (!s2_pgtable_config_valid(cfg->s2cfg.sl0, cfg->s2cfg.tsz,
197
+ cfg->s2cfg.granule_sz)) {
198
+ qemu_log_mask(LOG_GUEST_ERROR,
199
+ "SMMUv3 STE stage 2 config not valid!\n");
200
+ goto bad_ste;
201
+ }
202
+
203
+ /* Only LE supported(IDR0.TTENDIAN). */
204
+ if (STE_S2ENDI(ste)) {
205
+ qemu_log_mask(LOG_GUEST_ERROR,
206
+ "SMMUv3 STE_S2ENDI only supports LE!\n");
207
+ goto bad_ste;
208
+ }
209
+
210
+ cfg->s2cfg.affd = STE_S2AFFD(ste);
211
+
212
+ cfg->s2cfg.record_faults = STE_S2R(ste);
213
+ /* As stall is not supported. */
214
+ if (STE_S2S(ste)) {
215
+ qemu_log_mask(LOG_UNIMP, "SMMUv3 Stall not implemented!\n");
216
+ goto bad_ste;
217
+ }
218
+
219
+ /* This is still here as stage 2 has not been fully enabled yet. */
220
+ qemu_log_mask(LOG_UNIMP, "SMMUv3 does not support stage 2 yet\n");
221
+ goto bad_ste;
222
+
223
+ return 0;
224
+
225
+bad_ste:
226
+ return -EINVAL;
227
+}
228
+
229
/* Returns < 0 in case of invalid STE, 0 otherwise */
230
static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg,
231
STE *ste, SMMUEventInfo *event)
232
{
233
uint32_t config;
234
+ int ret;
235
236
if (!STE_VALID(ste)) {
237
if (!event->inval_ste_allowed) {
238
@@ -XXX,XX +XXX,XX @@ static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg,
239
return 0;
240
}
241
242
- if (STE_CFG_S2_ENABLED(config)) {
243
- qemu_log_mask(LOG_UNIMP, "SMMUv3 does not support stage 2 yet\n");
244
+ /*
245
+ * If a stage is enabled in SW while not advertised, throw bad ste
246
+ * according to user manual(IHI0070E) "5.2 Stream Table Entry".
247
+ */
248
+ if (!STAGE1_SUPPORTED(s) && STE_CFG_S1_ENABLED(config)) {
249
+ qemu_log_mask(LOG_GUEST_ERROR, "SMMUv3 S1 used but not supported.\n");
250
goto bad_ste;
251
}
252
+ if (!STAGE2_SUPPORTED(s) && STE_CFG_S2_ENABLED(config)) {
253
+ qemu_log_mask(LOG_GUEST_ERROR, "SMMUv3 S2 used but not supported.\n");
254
+ goto bad_ste;
255
+ }
256
+
257
+ if (STAGE2_SUPPORTED(s)) {
258
+ /* VMID is considered even if s2 is disabled. */
259
+ cfg->s2cfg.vmid = STE_S2VMID(ste);
260
+ } else {
261
+ /* Default to -1 */
262
+ cfg->s2cfg.vmid = -1;
263
+ }
264
+
265
+ if (STE_CFG_S2_ENABLED(config)) {
266
+ /*
267
+ * Stage-1 OAS defaults to OAS even if not enabled as it would be used
268
+ * in input address check for stage-2.
269
+ */
270
+ cfg->oas = oas2bits(SMMU_IDR5_OAS);
271
+ ret = decode_ste_s2_cfg(cfg, ste);
272
+ if (ret) {
273
+ goto bad_ste;
274
+ }
275
+ }
276
277
if (STE_S1CDMAX(ste) != 0) {
278
qemu_log_mask(LOG_UNIMP,
279
@@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
280
if (cached_entry) {
281
if ((flag & IOMMU_WO) && !(cached_entry->entry.perm & IOMMU_WO)) {
282
status = SMMU_TRANS_ERROR;
283
- if (cfg->record_faults) {
284
+ /*
285
+ * We know that the TLB only contains either stage-1 or stage-2 as
286
+ * nesting is not supported. So it is sufficient to check the
287
+ * translation stage to know the TLB stage for now.
288
+ */
289
+ event.u.f_walk_eabt.s2 = (cfg->stage == 2);
290
+ if (PTW_RECORD_FAULT(cfg)) {
291
event.type = SMMU_EVT_F_PERMISSION;
292
event.u.f_permission.addr = addr;
293
event.u.f_permission.rnw = flag & 0x1;
294
@@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
295
event.u.f_walk_eabt.addr2 = ptw_info.addr;
296
break;
297
case SMMU_PTW_ERR_TRANSLATION:
298
- if (cfg->record_faults) {
299
+ if (PTW_RECORD_FAULT(cfg)) {
300
event.type = SMMU_EVT_F_TRANSLATION;
301
event.u.f_translation.addr = addr;
302
event.u.f_translation.rnw = flag & 0x1;
141
}
303
}
142
return 0;
304
break;
143
305
case SMMU_PTW_ERR_ADDR_SIZE:
144
- case NEON_3R_VADD_VSUB:
306
- if (cfg->record_faults) {
145
- if (u) {
307
+ if (PTW_RECORD_FAULT(cfg)) {
146
- tcg_gen_gvec_sub(size, rd_ofs, rn_ofs, rm_ofs,
308
event.type = SMMU_EVT_F_ADDR_SIZE;
147
- vec_size, vec_size);
309
event.u.f_addr_size.addr = addr;
148
- } else {
310
event.u.f_addr_size.rnw = flag & 0x1;
149
- tcg_gen_gvec_add(size, rd_ofs, rn_ofs, rm_ofs,
311
}
150
- vec_size, vec_size);
312
break;
151
- }
313
case SMMU_PTW_ERR_ACCESS:
152
- return 0;
314
- if (cfg->record_faults) {
153
-
315
+ if (PTW_RECORD_FAULT(cfg)) {
154
case NEON_3R_VQADD:
316
event.type = SMMU_EVT_F_ACCESS;
155
tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
317
event.u.f_access.addr = addr;
156
rn_ofs, rm_ofs, vec_size, vec_size,
318
event.u.f_access.rnw = flag & 0x1;
157
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
319
}
158
tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size,
320
break;
159
u ? &ushl_op[size] : &sshl_op[size]);
321
case SMMU_PTW_ERR_PERMISSION:
160
return 0;
322
- if (cfg->record_faults) {
161
+
323
+ if (PTW_RECORD_FAULT(cfg)) {
162
+ case NEON_3R_VADD_VSUB:
324
event.type = SMMU_EVT_F_PERMISSION;
163
+ /* Already handled by decodetree */
325
event.u.f_permission.addr = addr;
164
+ return 1;
326
event.u.f_permission.rnw = flag & 0x1;
165
}
166
167
if (size == 3) {
168
--
327
--
169
2.20.1
328
2.34.1
170
171
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Mostafa Saleh <smostafa@google.com>
2
2
3
Fix typo xlnx-ve -> xlnx-versal.
3
Right now, either stage-1 or stage-2 are supported, this simplifies
4
how we can deal with TLBs.
5
This patch makes TLB lookup work if stage-2 is enabled instead of
6
stage-1.
7
TLB lookup is done before a PTW, if a valid entry is found we won't
8
do the PTW.
9
To be able to do TLB lookup, we need the correct tagging info, as
10
granularity and input size, so we get this based on the supported
11
translation stage. The TLB entries are added correctly from each
12
stage PTW.
4
13
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
14
When nested translation is supported, this would need to change, for
6
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
15
example if we go with a combined TLB implementation, we would need to
7
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
16
use the min of the granularities in TLB.
8
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
17
9
Message-id: 20200427181649.26851-4-edgar.iglesias@gmail.com
18
As stage-2 shouldn't be tagged by ASID, it will be set to -1 if S1P
19
is not enabled.
20
21
Signed-off-by: Mostafa Saleh <smostafa@google.com>
22
Reviewed-by: Eric Auger <eric.auger@redhat.com>
23
Tested-by: Eric Auger <eric.auger@redhat.com>
24
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
25
Message-id: 20230516203327.2051088-7-smostafa@google.com
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
26
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
27
---
12
hw/arm/xlnx-versal-virt.c | 2 +-
28
hw/arm/smmuv3.c | 44 +++++++++++++++++++++++++++++++++-----------
13
1 file changed, 1 insertion(+), 1 deletion(-)
29
1 file changed, 33 insertions(+), 11 deletions(-)
14
30
15
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
31
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
16
index XXXXXXX..XXXXXXX 100644
32
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/arm/xlnx-versal-virt.c
33
--- a/hw/arm/smmuv3.c
18
+++ b/hw/arm/xlnx-versal-virt.c
34
+++ b/hw/arm/smmuv3.c
19
@@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine)
35
@@ -XXX,XX +XXX,XX @@ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg,
20
psci_conduit = QEMU_PSCI_CONDUIT_SMC;
36
STE ste;
37
CD cd;
38
39
+ /* ASID defaults to -1 (if s1 is not supported). */
40
+ cfg->asid = -1;
41
+
42
ret = smmu_find_ste(s, sid, &ste, event);
43
if (ret) {
44
return ret;
45
@@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
46
.addr_mask = ~(hwaddr)0,
47
.perm = IOMMU_NONE,
48
};
49
+ /*
50
+ * Combined attributes used for TLB lookup, as only one stage is supported,
51
+ * it will hold attributes based on the enabled stage.
52
+ */
53
+ SMMUTransTableInfo tt_combined;
54
55
qemu_mutex_lock(&s->mutex);
56
57
@@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr,
58
goto epilogue;
21
}
59
}
22
60
23
- sysbus_init_child_obj(OBJECT(machine), "xlnx-ve", &s->soc,
61
- tt = select_tt(cfg, addr);
24
+ sysbus_init_child_obj(OBJECT(machine), "xlnx-versal", &s->soc,
62
- if (!tt) {
25
sizeof(s->soc), TYPE_XLNX_VERSAL);
63
- if (cfg->record_faults) {
26
object_property_set_link(OBJECT(&s->soc), OBJECT(machine->ram),
64
- event.type = SMMU_EVT_F_TRANSLATION;
27
"ddr", &error_abort);
65
- event.u.f_translation.addr = addr;
66
- event.u.f_translation.rnw = flag & 0x1;
67
+ if (cfg->stage == 1) {
68
+ /* Select stage1 translation table. */
69
+ tt = select_tt(cfg, addr);
70
+ if (!tt) {
71
+ if (cfg->record_faults) {
72
+ event.type = SMMU_EVT_F_TRANSLATION;
73
+ event.u.f_translation.addr = addr;
74
+ event.u.f_translation.rnw = flag & 0x1;
75
+ }
76
+ status = SMMU_TRANS_ERROR;
77
+ goto epilogue;
78
}
79
- status = SMMU_TRANS_ERROR;
80
- goto epilogue;
81
- }
82
+ tt_combined.granule_sz = tt->granule_sz;
83
+ tt_combined.tsz = tt->tsz;
84
85
- page_mask = (1ULL << (tt->granule_sz)) - 1;
86
+ } else {
87
+ /* Stage2. */
88
+ tt_combined.granule_sz = cfg->s2cfg.granule_sz;
89
+ tt_combined.tsz = cfg->s2cfg.tsz;
90
+ }
91
+ /*
92
+ * TLB lookup looks for granule and input size for a translation stage,
93
+ * as only one stage is supported right now, choose the right values
94
+ * from the configuration.
95
+ */
96
+ page_mask = (1ULL << tt_combined.granule_sz) - 1;
97
aligned_addr = addr & ~page_mask;
98
99
- cached_entry = smmu_iotlb_lookup(bs, cfg, tt, aligned_addr);
100
+ cached_entry = smmu_iotlb_lookup(bs, cfg, &tt_combined, aligned_addr);
101
if (cached_entry) {
102
if ((flag & IOMMU_WO) && !(cached_entry->entry.perm & IOMMU_WO)) {
103
status = SMMU_TRANS_ERROR;
28
--
104
--
29
2.20.1
105
2.34.1
30
31
diff view generated by jsdifflib
1
Convert the Neon VMUL, VMLA, VMLS and VSHL insns in the
1
From: Mostafa Saleh <smostafa@google.com>
2
3-reg-same grouping to decodetree.
2
3
3
Allow TLB to be tagged with VMID.
4
5
If stage-1 is only supported, VMID is set to -1 and ignored from STE
6
and CMD_TLBI_NH* cmds.
7
8
Update smmu_iotlb_insert trace event to have vmid.
9
10
Signed-off-by: Mostafa Saleh <smostafa@google.com>
11
Reviewed-by: Eric Auger <eric.auger@redhat.com>
12
Tested-by: Eric Auger <eric.auger@redhat.com>
13
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
14
Message-id: 20230516203327.2051088-8-smostafa@google.com
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
15
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-20-peter.maydell@linaro.org
7
---
16
---
8
target/arm/neon-dp.decode | 9 +++++++
17
hw/arm/smmu-internal.h | 2 ++
9
target/arm/translate-neon.inc.c | 44 +++++++++++++++++++++++++++++++++
18
include/hw/arm/smmu-common.h | 5 +++--
10
target/arm/translate.c | 28 +++------------------
19
hw/arm/smmu-common.c | 36 ++++++++++++++++++++++--------------
11
3 files changed, 56 insertions(+), 25 deletions(-)
20
hw/arm/smmuv3.c | 12 +++++++++---
12
21
hw/arm/trace-events | 6 +++---
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
22
5 files changed, 39 insertions(+), 22 deletions(-)
14
index XXXXXXX..XXXXXXX 100644
23
15
--- a/target/arm/neon-dp.decode
24
diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h
16
+++ b/target/arm/neon-dp.decode
25
index XXXXXXX..XXXXXXX 100644
17
@@ -XXX,XX +XXX,XX @@ VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same
26
--- a/hw/arm/smmu-internal.h
18
VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
27
+++ b/hw/arm/smmu-internal.h
19
VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
28
@@ -XXX,XX +XXX,XX @@ static inline int pgd_concat_idx(int start_level, int granule_sz,
20
29
}
21
+VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same
30
22
+VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same
31
#define SMMU_IOTLB_ASID(key) ((key).asid)
23
+
32
+#define SMMU_IOTLB_VMID(key) ((key).vmid)
24
VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
33
25
VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
34
typedef struct SMMUIOTLBPageInvInfo {
26
VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
35
int asid;
27
@@ -XXX,XX +XXX,XX @@ VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
36
+ int vmid;
28
37
uint64_t iova;
29
VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same
38
uint64_t mask;
30
VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same
39
} SMMUIOTLBPageInvInfo;
31
+
40
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
32
+VMLA_3s 1111 001 0 0 . .. .... .... 1001 . . . 0 .... @3same
41
index XXXXXXX..XXXXXXX 100644
33
+VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same
42
--- a/include/hw/arm/smmu-common.h
34
+
43
+++ b/include/hw/arm/smmu-common.h
35
+VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same
44
@@ -XXX,XX +XXX,XX @@ typedef struct SMMUPciBus {
36
+VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same
45
typedef struct SMMUIOTLBKey {
37
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
46
uint64_t iova;
38
index XXXXXXX..XXXXXXX 100644
47
uint16_t asid;
39
--- a/target/arm/translate-neon.inc.c
48
+ uint16_t vmid;
40
+++ b/target/arm/translate-neon.inc.c
49
uint8_t tg;
41
@@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax)
50
uint8_t level;
42
DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax)
51
} SMMUIOTLBKey;
43
DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin)
52
@@ -XXX,XX +XXX,XX @@ IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid);
44
DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin)
53
SMMUTLBEntry *smmu_iotlb_lookup(SMMUState *bs, SMMUTransCfg *cfg,
45
+DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul)
54
SMMUTransTableInfo *tt, hwaddr iova);
46
55
void smmu_iotlb_insert(SMMUState *bs, SMMUTransCfg *cfg, SMMUTLBEntry *entry);
47
#define DO_3SAME_CMP(INSN, COND) \
56
-SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint64_t iova,
48
static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
57
+SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint16_t vmid, uint64_t iova,
49
@@ -XXX,XX +XXX,XX @@ DO_3SAME_GVEC4(VQADD_S, sqadd_op)
58
uint8_t tg, uint8_t level);
50
DO_3SAME_GVEC4(VQADD_U, uqadd_op)
59
void smmu_iotlb_inv_all(SMMUState *s);
51
DO_3SAME_GVEC4(VQSUB_S, sqsub_op)
60
void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid);
52
DO_3SAME_GVEC4(VQSUB_U, uqsub_op)
61
-void smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova,
53
+
62
+void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
54
+static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
63
uint8_t tg, uint64_t num_pages, uint8_t ttl);
55
+ uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz)
64
56
+{
65
/* Unmap the range of all the notifiers registered to any IOMMU mr */
57
+ tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz,
66
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
58
+ 0, gen_helper_gvec_pmul_b);
67
index XXXXXXX..XXXXXXX 100644
59
+}
68
--- a/hw/arm/smmu-common.c
60
+
69
+++ b/hw/arm/smmu-common.c
61
+static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a)
70
@@ -XXX,XX +XXX,XX @@ static guint smmu_iotlb_key_hash(gconstpointer v)
62
+{
71
63
+ if (a->size != 0) {
72
/* Jenkins hash */
73
a = b = c = JHASH_INITVAL + sizeof(*key);
74
- a += key->asid + key->level + key->tg;
75
+ a += key->asid + key->vmid + key->level + key->tg;
76
b += extract64(key->iova, 0, 32);
77
c += extract64(key->iova, 32, 32);
78
79
@@ -XXX,XX +XXX,XX @@ static gboolean smmu_iotlb_key_equal(gconstpointer v1, gconstpointer v2)
80
SMMUIOTLBKey *k1 = (SMMUIOTLBKey *)v1, *k2 = (SMMUIOTLBKey *)v2;
81
82
return (k1->asid == k2->asid) && (k1->iova == k2->iova) &&
83
- (k1->level == k2->level) && (k1->tg == k2->tg);
84
+ (k1->level == k2->level) && (k1->tg == k2->tg) &&
85
+ (k1->vmid == k2->vmid);
86
}
87
88
-SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint64_t iova,
89
+SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint16_t vmid, uint64_t iova,
90
uint8_t tg, uint8_t level)
91
{
92
- SMMUIOTLBKey key = {.asid = asid, .iova = iova, .tg = tg, .level = level};
93
+ SMMUIOTLBKey key = {.asid = asid, .vmid = vmid, .iova = iova,
94
+ .tg = tg, .level = level};
95
96
return key;
97
}
98
@@ -XXX,XX +XXX,XX @@ SMMUTLBEntry *smmu_iotlb_lookup(SMMUState *bs, SMMUTransCfg *cfg,
99
uint64_t mask = subpage_size - 1;
100
SMMUIOTLBKey key;
101
102
- key = smmu_get_iotlb_key(cfg->asid, iova & ~mask, tg, level);
103
+ key = smmu_get_iotlb_key(cfg->asid, cfg->s2cfg.vmid,
104
+ iova & ~mask, tg, level);
105
entry = g_hash_table_lookup(bs->iotlb, &key);
106
if (entry) {
107
break;
108
@@ -XXX,XX +XXX,XX @@ SMMUTLBEntry *smmu_iotlb_lookup(SMMUState *bs, SMMUTransCfg *cfg,
109
110
if (entry) {
111
cfg->iotlb_hits++;
112
- trace_smmu_iotlb_lookup_hit(cfg->asid, iova,
113
+ trace_smmu_iotlb_lookup_hit(cfg->asid, cfg->s2cfg.vmid, iova,
114
cfg->iotlb_hits, cfg->iotlb_misses,
115
100 * cfg->iotlb_hits /
116
(cfg->iotlb_hits + cfg->iotlb_misses));
117
} else {
118
cfg->iotlb_misses++;
119
- trace_smmu_iotlb_lookup_miss(cfg->asid, iova,
120
+ trace_smmu_iotlb_lookup_miss(cfg->asid, cfg->s2cfg.vmid, iova,
121
cfg->iotlb_hits, cfg->iotlb_misses,
122
100 * cfg->iotlb_hits /
123
(cfg->iotlb_hits + cfg->iotlb_misses));
124
@@ -XXX,XX +XXX,XX @@ void smmu_iotlb_insert(SMMUState *bs, SMMUTransCfg *cfg, SMMUTLBEntry *new)
125
smmu_iotlb_inv_all(bs);
126
}
127
128
- *key = smmu_get_iotlb_key(cfg->asid, new->entry.iova, tg, new->level);
129
- trace_smmu_iotlb_insert(cfg->asid, new->entry.iova, tg, new->level);
130
+ *key = smmu_get_iotlb_key(cfg->asid, cfg->s2cfg.vmid, new->entry.iova,
131
+ tg, new->level);
132
+ trace_smmu_iotlb_insert(cfg->asid, cfg->s2cfg.vmid, new->entry.iova,
133
+ tg, new->level);
134
g_hash_table_insert(bs->iotlb, key, new);
135
}
136
137
@@ -XXX,XX +XXX,XX @@ static gboolean smmu_hash_remove_by_asid(gpointer key, gpointer value,
138
139
return SMMU_IOTLB_ASID(*iotlb_key) == asid;
140
}
141
-
142
-static gboolean smmu_hash_remove_by_asid_iova(gpointer key, gpointer value,
143
+static gboolean smmu_hash_remove_by_asid_vmid_iova(gpointer key, gpointer value,
144
gpointer user_data)
145
{
146
SMMUTLBEntry *iter = (SMMUTLBEntry *)value;
147
@@ -XXX,XX +XXX,XX @@ static gboolean smmu_hash_remove_by_asid_iova(gpointer key, gpointer value,
148
if (info->asid >= 0 && info->asid != SMMU_IOTLB_ASID(iotlb_key)) {
149
return false;
150
}
151
+ if (info->vmid >= 0 && info->vmid != SMMU_IOTLB_VMID(iotlb_key)) {
64
+ return false;
152
+ return false;
65
+ }
153
+ }
66
+ return do_3same(s, a, gen_VMUL_p_3s);
154
return ((info->iova & ~entry->addr_mask) == entry->iova) ||
67
+}
155
((entry->iova & ~info->mask) == info->iova);
156
}
157
158
-void smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova,
159
+void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
160
uint8_t tg, uint64_t num_pages, uint8_t ttl)
161
{
162
/* if tg is not set we use 4KB range invalidation */
163
uint8_t granule = tg ? tg * 2 + 10 : 12;
164
165
if (ttl && (num_pages == 1) && (asid >= 0)) {
166
- SMMUIOTLBKey key = smmu_get_iotlb_key(asid, iova, tg, ttl);
167
+ SMMUIOTLBKey key = smmu_get_iotlb_key(asid, vmid, iova, tg, ttl);
168
169
if (g_hash_table_remove(s->iotlb, &key)) {
170
return;
171
@@ -XXX,XX +XXX,XX @@ void smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova,
172
173
SMMUIOTLBPageInvInfo info = {
174
.asid = asid, .iova = iova,
175
+ .vmid = vmid,
176
.mask = (num_pages * 1 << granule) - 1};
177
178
g_hash_table_foreach_remove(s->iotlb,
179
- smmu_hash_remove_by_asid_iova,
180
+ smmu_hash_remove_by_asid_vmid_iova,
181
&info);
182
}
183
184
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
185
index XXXXXXX..XXXXXXX 100644
186
--- a/hw/arm/smmuv3.c
187
+++ b/hw/arm/smmuv3.c
188
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
189
{
190
dma_addr_t end, addr = CMD_ADDR(cmd);
191
uint8_t type = CMD_TYPE(cmd);
192
- uint16_t vmid = CMD_VMID(cmd);
193
+ int vmid = -1;
194
uint8_t scale = CMD_SCALE(cmd);
195
uint8_t num = CMD_NUM(cmd);
196
uint8_t ttl = CMD_TTL(cmd);
197
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
198
uint64_t num_pages;
199
uint8_t granule;
200
int asid = -1;
201
+ SMMUv3State *smmuv3 = ARM_SMMUV3(s);
68
+
202
+
69
+#define DO_3SAME_GVEC3_NO_SZ_3(INSN, OPARRAY) \
203
+ /* Only consider VMID if stage-2 is supported. */
70
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
204
+ if (STAGE2_SUPPORTED(smmuv3)) {
71
+ uint32_t rn_ofs, uint32_t rm_ofs, \
205
+ vmid = CMD_VMID(cmd);
72
+ uint32_t oprsz, uint32_t maxsz) \
206
+ }
73
+ { \
207
74
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \
208
if (type == SMMU_CMD_TLBI_NH_VA) {
75
+ oprsz, maxsz, &OPARRAY[vece]); \
209
asid = CMD_ASID(cmd);
76
+ } \
210
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
77
+ DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s)
211
if (!tg) {
78
+
212
trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
79
+
213
smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1);
80
+DO_3SAME_GVEC3_NO_SZ_3(VMLA, mla_op)
214
- smmu_iotlb_inv_iova(s, asid, addr, tg, 1, ttl);
81
+DO_3SAME_GVEC3_NO_SZ_3(VMLS, mls_op)
215
+ smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, 1, ttl);
82
+
216
return;
83
+#define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY) \
217
}
84
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
218
85
+ uint32_t rn_ofs, uint32_t rm_ofs, \
219
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
86
+ uint32_t oprsz, uint32_t maxsz) \
220
num_pages = (mask + 1) >> granule;
87
+ { \
221
trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
88
+ /* Note the operation is vshl vd,vm,vn */ \
222
smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
89
+ tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, \
223
- smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl);
90
+ oprsz, maxsz, &OPARRAY[vece]); \
224
+ smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, num_pages, ttl);
91
+ } \
225
addr += mask + 1;
92
+ DO_3SAME(INSN, gen_##INSN##_3s)
226
}
93
+
227
}
94
+DO_3SAME_GVEC3_SHIFT(VSHL_S, sshl_op)
228
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
95
+DO_3SAME_GVEC3_SHIFT(VSHL_U, ushl_op)
229
index XXXXXXX..XXXXXXX 100644
96
diff --git a/target/arm/translate.c b/target/arm/translate.c
230
--- a/hw/arm/trace-events
97
index XXXXXXX..XXXXXXX 100644
231
+++ b/hw/arm/trace-events
98
--- a/target/arm/translate.c
232
@@ -XXX,XX +XXX,XX @@ smmu_iotlb_inv_all(void) "IOTLB invalidate all"
99
+++ b/target/arm/translate.c
233
smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d"
100
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
234
smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64
101
}
235
smmu_inv_notifiers_mr(const char *name) "iommu mr=%s"
102
return 1;
236
-smmu_iotlb_lookup_hit(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
103
237
-smmu_iotlb_lookup_miss(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
104
- case NEON_3R_VMUL: /* VMUL */
238
-smmu_iotlb_insert(uint16_t asid, uint64_t addr, uint8_t tg, uint8_t level) "IOTLB ++ asid=%d addr=0x%"PRIx64" tg=%d level=%d"
105
- if (u) {
239
+smmu_iotlb_lookup_hit(uint16_t asid, uint16_t vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
106
- /* Polynomial case allows only P8. */
240
+smmu_iotlb_lookup_miss(uint16_t asid, uint16_t vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
107
- if (size != 0) {
241
+smmu_iotlb_insert(uint16_t asid, uint16_t vmid, uint64_t addr, uint8_t tg, uint8_t level) "IOTLB ++ asid=%d vmid=%d addr=0x%"PRIx64" tg=%d level=%d"
108
- return 1;
242
109
- }
243
# smmuv3.c
110
- tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size,
244
smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)"
111
- 0, gen_helper_gvec_pmul_b);
112
- } else {
113
- tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs,
114
- vec_size, vec_size);
115
- }
116
- return 0;
117
-
118
- case NEON_3R_VML: /* VMLA, VMLS */
119
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size,
120
- u ? &mls_op[size] : &mla_op[size]);
121
- return 0;
122
-
123
- case NEON_3R_VSHL:
124
- /* Note the operation is vshl vd,vm,vn */
125
- tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size,
126
- u ? &ushl_op[size] : &sshl_op[size]);
127
- return 0;
128
-
129
case NEON_3R_VADD_VSUB:
130
case NEON_3R_LOGIC:
131
case NEON_3R_VMAX:
132
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
133
case NEON_3R_VCGE:
134
case NEON_3R_VQADD:
135
case NEON_3R_VQSUB:
136
+ case NEON_3R_VMUL:
137
+ case NEON_3R_VML:
138
+ case NEON_3R_VSHL:
139
/* Already handled by decodetree */
140
return 1;
141
}
142
--
245
--
143
2.20.1
246
2.34.1
144
145
diff view generated by jsdifflib
1
Convert the VFM[AS]L (scalar) insns in the 2reg-scalar-ext group
1
From: Mostafa Saleh <smostafa@google.com>
2
to decodetree. These are the last ones in the group so we can remove
2
3
all the legacy decode for the group.
3
CMD_TLBI_S2_IPA: As S1+S2 is not enabled, for now this can be the
4
4
same as CMD_TLBI_NH_VAA.
5
Note that in disas_thumb2_insn() the parts of this encoding space
5
6
where the decodetree decoder returns false will correctly be directed
6
CMD_TLBI_S12_VMALL: Added new function to invalidate TLB by VMID.
7
to illegal_op by the "(insn & (1 << 28))" check so they won't fall
7
8
into disas_coproc_insn() by mistake.
8
For stage-1 only commands, add a check to throw CERROR_ILL if used
9
9
when stage-1 is not supported.
10
11
Reviewed-by: Eric Auger <eric.auger@redhat.com>
12
Signed-off-by: Mostafa Saleh <smostafa@google.com>
13
Tested-by: Eric Auger <eric.auger@redhat.com>
14
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
15
Message-id: 20230516203327.2051088-9-smostafa@google.com
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 20200430181003.21682-11-peter.maydell@linaro.org
13
---
17
---
14
target/arm/neon-shared.decode | 7 +++
18
include/hw/arm/smmu-common.h | 1 +
15
target/arm/translate-neon.inc.c | 32 ++++++++++
19
hw/arm/smmu-common.c | 16 +++++++++++
16
target/arm/translate.c | 107 +-------------------------------
20
hw/arm/smmuv3.c | 55 ++++++++++++++++++++++++++++++------
17
3 files changed, 40 insertions(+), 106 deletions(-)
21
hw/arm/trace-events | 4 ++-
18
22
4 files changed, 67 insertions(+), 9 deletions(-)
19
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
23
20
index XXXXXXX..XXXXXXX 100644
24
diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h
21
--- a/target/arm/neon-shared.decode
25
index XXXXXXX..XXXXXXX 100644
22
+++ b/target/arm/neon-shared.decode
26
--- a/include/hw/arm/smmu-common.h
23
@@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
27
+++ b/include/hw/arm/smmu-common.h
24
28
@@ -XXX,XX +XXX,XX @@ SMMUIOTLBKey smmu_get_iotlb_key(uint16_t asid, uint16_t vmid, uint64_t iova,
25
VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \
29
uint8_t tg, uint8_t level);
26
vm=%vm_dp vn=%vn_dp vd=%vd_dp
30
void smmu_iotlb_inv_all(SMMUState *s);
27
+
31
void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid);
28
+%vfml_scalar_q0_rm 0:3 5:1
32
+void smmu_iotlb_inv_vmid(SMMUState *s, uint16_t vmid);
29
+%vfml_scalar_q1_index 5:1 3:1
33
void smmu_iotlb_inv_iova(SMMUState *s, int asid, int vmid, dma_addr_t iova,
30
+VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 0 . 1 index:1 ... \
34
uint8_t tg, uint64_t num_pages, uint8_t ttl);
31
+ rm=%vfml_scalar_q0_rm vn=%vn_sp vd=%vd_dp q=0
35
32
+VFML_scalar 1111 1110 0 . 0 s:1 .... .... 1000 . 1 . 1 . rm:3 \
36
diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c
33
+ index=%vfml_scalar_q1_index vn=%vn_dp vd=%vd_dp q=1
37
index XXXXXXX..XXXXXXX 100644
34
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
38
--- a/hw/arm/smmu-common.c
35
index XXXXXXX..XXXXXXX 100644
39
+++ b/hw/arm/smmu-common.c
36
--- a/target/arm/translate-neon.inc.c
40
@@ -XXX,XX +XXX,XX @@ static gboolean smmu_hash_remove_by_asid(gpointer key, gpointer value,
37
+++ b/target/arm/translate-neon.inc.c
41
38
@@ -XXX,XX +XXX,XX @@ static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
42
return SMMU_IOTLB_ASID(*iotlb_key) == asid;
39
tcg_temp_free_ptr(fpst);
40
return true;
41
}
43
}
42
+
44
+
43
+static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)
45
+static gboolean smmu_hash_remove_by_vmid(gpointer key, gpointer value,
46
+ gpointer user_data)
44
+{
47
+{
45
+ int opr_sz;
48
+ uint16_t vmid = *(uint16_t *)user_data;
46
+
49
+ SMMUIOTLBKey *iotlb_key = (SMMUIOTLBKey *)key;
47
+ if (!dc_isar_feature(aa32_fhm, s)) {
50
+
48
+ return false;
51
+ return SMMU_IOTLB_VMID(*iotlb_key) == vmid;
49
+ }
50
+
51
+ /* UNDEF accesses to D16-D31 if they don't exist. */
52
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
53
+ ((a->vd & 0x10) || (a->q && (a->vn & 0x10)))) {
54
+ return false;
55
+ }
56
+
57
+ if (a->vd & a->q) {
58
+ return false;
59
+ }
60
+
61
+ if (!vfp_access_check(s)) {
62
+ return true;
63
+ }
64
+
65
+ opr_sz = (1 + a->q) * 8;
66
+ tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
67
+ vfp_reg_offset(a->q, a->vn),
68
+ vfp_reg_offset(a->q, a->rm),
69
+ cpu_env, opr_sz, opr_sz,
70
+ (a->index << 2) | a->s, /* is_2 == 0 */
71
+ gen_helper_gvec_fmlal_idx_a32);
72
+ return true;
73
+}
52
+}
74
diff --git a/target/arm/translate.c b/target/arm/translate.c
53
+
75
index XXXXXXX..XXXXXXX 100644
54
static gboolean smmu_hash_remove_by_asid_vmid_iova(gpointer key, gpointer value,
76
--- a/target/arm/translate.c
55
gpointer user_data)
77
+++ b/target/arm/translate.c
56
{
78
@@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn)
57
@@ -XXX,XX +XXX,XX @@ void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid)
58
g_hash_table_foreach_remove(s->iotlb, smmu_hash_remove_by_asid, &asid);
79
}
59
}
80
60
81
#define VFP_REG_SHR(x, n) (((n) > 0) ? (x) >> (n) : (x) << -(n))
61
+inline void smmu_iotlb_inv_vmid(SMMUState *s, uint16_t vmid)
82
-#define VFP_SREG(insn, bigbit, smallbit) \
62
+{
83
- ((VFP_REG_SHR(insn, bigbit - 1) & 0x1e) | (((insn) >> (smallbit)) & 1))
63
+ trace_smmu_iotlb_inv_vmid(vmid);
84
#define VFP_DREG(reg, insn, bigbit, smallbit) do { \
64
+ g_hash_table_foreach_remove(s->iotlb, smmu_hash_remove_by_vmid, &vmid);
85
if (dc_isar_feature(aa32_simd_r32, s)) { \
65
+}
86
reg = (((insn) >> (bigbit)) & 0x0f) \
66
+
87
@@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn)
67
/* VMSAv8-64 Translation */
88
reg = ((insn) >> (bigbit)) & 0x0f; \
68
89
}} while (0)
69
/**
90
70
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
91
-#define VFP_SREG_D(insn) VFP_SREG(insn, 12, 22)
71
index XXXXXXX..XXXXXXX 100644
92
#define VFP_DREG_D(reg, insn) VFP_DREG(reg, insn, 12, 22)
72
--- a/hw/arm/smmuv3.c
93
-#define VFP_SREG_N(insn) VFP_SREG(insn, 16, 7)
73
+++ b/hw/arm/smmuv3.c
94
#define VFP_DREG_N(reg, insn) VFP_DREG(reg, insn, 16, 7)
74
@@ -XXX,XX +XXX,XX @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova,
95
-#define VFP_SREG_M(insn) VFP_SREG(insn, 0, 5)
75
}
96
#define VFP_DREG_M(reg, insn) VFP_DREG(reg, insn, 0, 5)
97
98
static void gen_neon_dup_low16(TCGv_i32 var)
99
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
100
return 0;
101
}
76
}
102
77
103
-/* Advanced SIMD two registers and a scalar extension.
78
-static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
104
- * 31 24 23 22 20 16 12 11 10 9 8 3 0
79
+static void smmuv3_range_inval(SMMUState *s, Cmd *cmd)
105
- * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+
106
- * | 1 1 1 1 1 1 1 0 | o1 | D | o2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm |
107
- * +-----------------+----+---+----+----+----+---+----+---+----+---------+----+
108
- *
109
- */
110
-
111
-static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn)
112
-{
113
- gen_helper_gvec_3 *fn_gvec = NULL;
114
- gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL;
115
- int rd, rn, rm, opr_sz, data;
116
- int off_rn, off_rm;
117
- bool is_long = false, q = extract32(insn, 6, 1);
118
- bool ptr_is_env = false;
119
-
120
- if ((insn & 0xffa00f10) == 0xfe000810) {
121
- /* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */
122
- int is_s = extract32(insn, 20, 1);
123
- int vm20 = extract32(insn, 0, 3);
124
- int vm3 = extract32(insn, 3, 1);
125
- int m = extract32(insn, 5, 1);
126
- int index;
127
-
128
- if (!dc_isar_feature(aa32_fhm, s)) {
129
- return 1;
130
- }
131
- if (q) {
132
- rm = vm20;
133
- index = m * 2 + vm3;
134
- } else {
135
- rm = vm20 * 2 + m;
136
- index = vm3;
137
- }
138
- is_long = true;
139
- data = (index << 2) | is_s; /* is_2 == 0 */
140
- fn_gvec_ptr = gen_helper_gvec_fmlal_idx_a32;
141
- ptr_is_env = true;
142
- } else {
143
- return 1;
144
- }
145
-
146
- VFP_DREG_D(rd, insn);
147
- if (rd & q) {
148
- return 1;
149
- }
150
- if (q || !is_long) {
151
- VFP_DREG_N(rn, insn);
152
- if (rn & q & !is_long) {
153
- return 1;
154
- }
155
- off_rn = vfp_reg_offset(1, rn);
156
- off_rm = vfp_reg_offset(1, rm);
157
- } else {
158
- rn = VFP_SREG_N(insn);
159
- off_rn = vfp_reg_offset(0, rn);
160
- off_rm = vfp_reg_offset(0, rm);
161
- }
162
- if (s->fp_excp_el) {
163
- gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
164
- syn_simd_access_trap(1, 0xe, false), s->fp_excp_el);
165
- return 0;
166
- }
167
- if (!s->vfp_enabled) {
168
- return 1;
169
- }
170
-
171
- opr_sz = (1 + q) * 8;
172
- if (fn_gvec_ptr) {
173
- TCGv_ptr ptr;
174
- if (ptr_is_env) {
175
- ptr = cpu_env;
176
- } else {
177
- ptr = get_fpstatus_ptr(1);
178
- }
179
- tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr,
180
- opr_sz, opr_sz, data, fn_gvec_ptr);
181
- if (!ptr_is_env) {
182
- tcg_temp_free_ptr(ptr);
183
- }
184
- } else {
185
- tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm,
186
- opr_sz, opr_sz, data, fn_gvec);
187
- }
188
- return 0;
189
-}
190
-
191
static int disas_coproc_insn(DisasContext *s, uint32_t insn)
192
{
80
{
193
int cpnum, is64, crn, crm, opc1, opc2, isread, rt, rt2;
81
dma_addr_t end, addr = CMD_ADDR(cmd);
194
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
82
uint8_t type = CMD_TYPE(cmd);
195
}
83
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
196
}
84
}
197
}
85
198
- } else if ((insn & 0x0f000a00) == 0x0e000800
86
if (!tg) {
199
- && arm_dc_feature(s, ARM_FEATURE_V8)) {
87
- trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
200
- if (disas_neon_insn_2reg_scalar_ext(s, insn)) {
88
+ trace_smmuv3_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
201
- goto illegal_op;
89
smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1);
202
- }
90
smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, 1, ttl);
203
- return;
91
return;
92
@@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd)
93
uint64_t mask = dma_aligned_pow2_mask(addr, end, 64);
94
95
num_pages = (mask + 1) >> granule;
96
- trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
97
+ trace_smmuv3_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
98
smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
99
smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, num_pages, ttl);
100
addr += mask + 1;
101
@@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
102
{
103
uint16_t asid = CMD_ASID(&cmd);
104
105
+ if (!STAGE1_SUPPORTED(s)) {
106
+ cmd_error = SMMU_CERROR_ILL;
107
+ break;
108
+ }
109
+
110
trace_smmuv3_cmdq_tlbi_nh_asid(asid);
111
smmu_inv_notifiers_all(&s->smmu_state);
112
smmu_iotlb_inv_asid(bs, asid);
113
break;
204
}
114
}
205
goto illegal_op;
115
case SMMU_CMD_TLBI_NH_ALL:
206
}
116
+ if (!STAGE1_SUPPORTED(s)) {
207
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
117
+ cmd_error = SMMU_CERROR_ILL;
208
}
118
+ break;
119
+ }
120
+ QEMU_FALLTHROUGH;
121
case SMMU_CMD_TLBI_NSNH_ALL:
122
trace_smmuv3_cmdq_tlbi_nh();
123
smmu_inv_notifiers_all(&s->smmu_state);
124
@@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
125
break;
126
case SMMU_CMD_TLBI_NH_VAA:
127
case SMMU_CMD_TLBI_NH_VA:
128
- smmuv3_s1_range_inval(bs, &cmd);
129
+ if (!STAGE1_SUPPORTED(s)) {
130
+ cmd_error = SMMU_CERROR_ILL;
131
+ break;
132
+ }
133
+ smmuv3_range_inval(bs, &cmd);
134
+ break;
135
+ case SMMU_CMD_TLBI_S12_VMALL:
136
+ {
137
+ uint16_t vmid = CMD_VMID(&cmd);
138
+
139
+ if (!STAGE2_SUPPORTED(s)) {
140
+ cmd_error = SMMU_CERROR_ILL;
141
+ break;
142
+ }
143
+
144
+ trace_smmuv3_cmdq_tlbi_s12_vmid(vmid);
145
+ smmu_inv_notifiers_all(&s->smmu_state);
146
+ smmu_iotlb_inv_vmid(bs, vmid);
147
+ break;
148
+ }
149
+ case SMMU_CMD_TLBI_S2_IPA:
150
+ if (!STAGE2_SUPPORTED(s)) {
151
+ cmd_error = SMMU_CERROR_ILL;
152
+ break;
153
+ }
154
+ /*
155
+ * As currently only either s1 or s2 are supported
156
+ * we can reuse same function for s2.
157
+ */
158
+ smmuv3_range_inval(bs, &cmd);
159
break;
160
case SMMU_CMD_TLBI_EL3_ALL:
161
case SMMU_CMD_TLBI_EL3_VA:
162
@@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
163
case SMMU_CMD_TLBI_EL2_ASID:
164
case SMMU_CMD_TLBI_EL2_VA:
165
case SMMU_CMD_TLBI_EL2_VAA:
166
- case SMMU_CMD_TLBI_S12_VMALL:
167
- case SMMU_CMD_TLBI_S2_IPA:
168
case SMMU_CMD_ATC_INV:
169
case SMMU_CMD_PRI_RESP:
170
case SMMU_CMD_RESUME:
171
@@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s)
172
break;
173
default:
174
cmd_error = SMMU_CERROR_ILL;
175
- qemu_log_mask(LOG_GUEST_ERROR,
176
- "Illegal command type: %d\n", CMD_TYPE(&cmd));
209
break;
177
break;
210
}
178
}
211
- if ((insn & 0xff000a00) == 0xfe000800
179
qemu_mutex_unlock(&s->mutex);
212
- && arm_dc_feature(s, ARM_FEATURE_V8)) {
180
if (cmd_error) {
213
- /* The Thumb2 and ARM encodings are identical. */
181
+ if (cmd_error == SMMU_CERROR_ILL) {
214
- if (disas_neon_insn_2reg_scalar_ext(s, insn)) {
182
+ qemu_log_mask(LOG_GUEST_ERROR,
215
- goto illegal_op;
183
+ "Illegal command type: %d\n", CMD_TYPE(&cmd));
216
- }
184
+ }
217
- } else if (((insn >> 24) & 3) == 3) {
185
break;
218
+ if (((insn >> 24) & 3) == 3) {
186
}
219
/* Translate into the equivalent ARM encoding. */
187
/*
220
insn = (insn & 0xe2ffffff) | ((insn & (1 << 28)) >> 4) | (1 << 28);
188
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
221
if (disas_neon_data_insn(s, insn)) {
189
index XXXXXXX..XXXXXXX 100644
190
--- a/hw/arm/trace-events
191
+++ b/hw/arm/trace-events
192
@@ -XXX,XX +XXX,XX @@ smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, ui
193
smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "baseaddr=0x%"PRIx64" index=0x%x, pteaddr=0x%"PRIx64", pte=0x%"PRIx64
194
smmu_iotlb_inv_all(void) "IOTLB invalidate all"
195
smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d"
196
+smmu_iotlb_inv_vmid(uint16_t vmid) "IOTLB invalidate vmid=%d"
197
smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64
198
smmu_inv_notifiers_mr(const char *name) "iommu mr=%s"
199
smmu_iotlb_lookup_hit(uint16_t asid, uint16_t vmid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d vmid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d"
200
@@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_cfgi_ste_range(int start, int end) "start=0x%x - end=0x%x"
201
smmuv3_cmdq_cfgi_cd(uint32_t sid) "sid=0x%x"
202
smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid=0x%x (hits=%d, misses=%d, hit rate=%d)"
203
smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid=0x%x (hits=%d, misses=%d, hit rate=%d)"
204
-smmuv3_s1_range_inval(int vmid, int asid, uint64_t addr, uint8_t tg, uint64_t num_pages, uint8_t ttl, bool leaf) "vmid=%d asid=%d addr=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64" ttl=%d leaf=%d"
205
+smmuv3_range_inval(int vmid, int asid, uint64_t addr, uint8_t tg, uint64_t num_pages, uint8_t ttl, bool leaf) "vmid=%d asid=%d addr=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64" ttl=%d leaf=%d"
206
smmuv3_cmdq_tlbi_nh(void) ""
207
smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d"
208
+smmuv3_cmdq_tlbi_s12_vmid(uint16_t vmid) "vmid=%d"
209
smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid=0x%x"
210
smmuv3_notify_flag_add(const char *iommu) "ADD SMMUNotifier node for iommu mr=%s"
211
smmuv3_notify_flag_del(const char *iommu) "DEL SMMUNotifier node for iommu mr=%s"
222
--
212
--
223
2.20.1
213
2.34.1
224
225
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Mostafa Saleh <smostafa@google.com>
2
2
3
hw/arm: versal: Add support for the RTC.
3
In smmuv3_notify_iova, read the granule based on translation stage
4
and use VMID if valid value is sent.
4
5
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
6
Signed-off-by: Mostafa Saleh <smostafa@google.com>
6
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
7
Reviewed-by: Eric Auger <eric.auger@redhat.com>
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
8
Tested-by: Eric Auger <eric.auger@redhat.com>
8
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
9
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
9
Message-id: 20200427181649.26851-10-edgar.iglesias@gmail.com
10
Message-id: 20230516203327.2051088-10-smostafa@google.com
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
12
---
12
include/hw/arm/xlnx-versal.h | 8 ++++++++
13
hw/arm/smmuv3.c | 39 ++++++++++++++++++++++++++-------------
13
hw/arm/xlnx-versal.c | 21 +++++++++++++++++++++
14
hw/arm/trace-events | 2 +-
14
2 files changed, 29 insertions(+)
15
2 files changed, 27 insertions(+), 14 deletions(-)
15
16
16
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
17
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
17
index XXXXXXX..XXXXXXX 100644
18
index XXXXXXX..XXXXXXX 100644
18
--- a/include/hw/arm/xlnx-versal.h
19
--- a/hw/arm/smmuv3.c
19
+++ b/include/hw/arm/xlnx-versal.h
20
+++ b/hw/arm/smmuv3.c
20
@@ -XXX,XX +XXX,XX @@
21
@@ -XXX,XX +XXX,XX @@ epilogue:
21
#include "hw/char/pl011.h"
22
* @mr: IOMMU mr region handle
22
#include "hw/dma/xlnx-zdma.h"
23
* @n: notifier to be called
23
#include "hw/net/cadence_gem.h"
24
* @asid: address space ID or negative value if we don't care
24
+#include "hw/rtc/xlnx-zynqmp-rtc.h"
25
+ * @vmid: virtual machine ID or negative value if we don't care
25
26
* @iova: iova
26
#define TYPE_XLNX_VERSAL "xlnx-versal"
27
* @tg: translation granule (if communicated through range invalidation)
27
#define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL)
28
* @num_pages: number of @granule sized pages (if tg != 0), otherwise 1
28
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
29
*/
29
struct {
30
static void smmuv3_notify_iova(IOMMUMemoryRegion *mr,
30
SDHCIState sd[XLNX_VERSAL_NR_SDS];
31
IOMMUNotifier *n,
31
} iou;
32
- int asid, dma_addr_t iova,
33
- uint8_t tg, uint64_t num_pages)
34
+ int asid, int vmid,
35
+ dma_addr_t iova, uint8_t tg,
36
+ uint64_t num_pages)
37
{
38
SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu);
39
IOMMUTLBEvent event;
40
uint8_t granule;
41
+ SMMUv3State *s = sdev->smmu;
42
43
if (!tg) {
44
SMMUEventInfo event = {.inval_ste_allowed = true};
45
@@ -XXX,XX +XXX,XX @@ static void smmuv3_notify_iova(IOMMUMemoryRegion *mr,
46
return;
47
}
48
49
- tt = select_tt(cfg, iova);
50
- if (!tt) {
51
+ if (vmid >= 0 && cfg->s2cfg.vmid != vmid) {
52
return;
53
}
54
- granule = tt->granule_sz;
32
+
55
+
33
+ XlnxZynqMPRTC rtc;
56
+ if (STAGE1_SUPPORTED(s)) {
34
} pmc;
57
+ tt = select_tt(cfg, iova);
35
58
+ if (!tt) {
36
struct {
59
+ return;
37
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
60
+ }
38
#define VERSAL_GEM1_IRQ_0 58
61
+ granule = tt->granule_sz;
39
#define VERSAL_GEM1_WAKE_IRQ_0 59
62
+ } else {
40
#define VERSAL_ADMA_IRQ_0 60
63
+ granule = cfg->s2cfg.granule_sz;
41
+#define VERSAL_RTC_APB_ERR_IRQ 121
64
+ }
42
#define VERSAL_SD0_IRQ_0 126
65
+
43
+#define VERSAL_RTC_ALARM_IRQ 142
66
} else {
44
+#define VERSAL_RTC_SECONDS_IRQ 143
67
granule = tg * 2 + 10;
45
68
}
46
/* Architecturally reserved IRQs suitable for virtualization. */
69
@@ -XXX,XX +XXX,XX @@ static void smmuv3_notify_iova(IOMMUMemoryRegion *mr,
47
#define VERSAL_RSVD_IRQ_FIRST 111
70
memory_region_notify_iommu_one(n, &event);
48
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
71
}
49
#define MM_PMC_SD0_SIZE 0x10000
72
50
#define MM_PMC_CRP 0xf1260000U
73
-/* invalidate an asid/iova range tuple in all mr's */
51
#define MM_PMC_CRP_SIZE 0x10000
74
-static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova,
52
+#define MM_PMC_RTC 0xf12a0000
75
- uint8_t tg, uint64_t num_pages)
53
+#define MM_PMC_RTC_SIZE 0x10000
76
+/* invalidate an asid/vmid/iova range tuple in all mr's */
54
#endif
77
+static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, int vmid,
55
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
78
+ dma_addr_t iova, uint8_t tg,
56
index XXXXXXX..XXXXXXX 100644
79
+ uint64_t num_pages)
57
--- a/hw/arm/xlnx-versal.c
80
{
58
+++ b/hw/arm/xlnx-versal.c
81
SMMUDevice *sdev;
59
@@ -XXX,XX +XXX,XX @@ static void versal_create_sds(Versal *s, qemu_irq *pic)
82
83
@@ -XXX,XX +XXX,XX @@ static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova,
84
IOMMUMemoryRegion *mr = &sdev->iommu;
85
IOMMUNotifier *n;
86
87
- trace_smmuv3_inv_notifiers_iova(mr->parent_obj.name, asid, iova,
88
- tg, num_pages);
89
+ trace_smmuv3_inv_notifiers_iova(mr->parent_obj.name, asid, vmid,
90
+ iova, tg, num_pages);
91
92
IOMMU_NOTIFIER_FOREACH(n, mr) {
93
- smmuv3_notify_iova(mr, n, asid, iova, tg, num_pages);
94
+ smmuv3_notify_iova(mr, n, asid, vmid, iova, tg, num_pages);
95
}
60
}
96
}
61
}
97
}
62
98
@@ -XXX,XX +XXX,XX @@ static void smmuv3_range_inval(SMMUState *s, Cmd *cmd)
63
+static void versal_create_rtc(Versal *s, qemu_irq *pic)
99
64
+{
100
if (!tg) {
65
+ SysBusDevice *sbd;
101
trace_smmuv3_range_inval(vmid, asid, addr, tg, 1, ttl, leaf);
66
+ MemoryRegion *mr;
102
- smmuv3_inv_notifiers_iova(s, asid, addr, tg, 1);
67
+
103
+ smmuv3_inv_notifiers_iova(s, asid, vmid, addr, tg, 1);
68
+ sysbus_init_child_obj(OBJECT(s), "rtc", &s->pmc.rtc, sizeof(s->pmc.rtc),
104
smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, 1, ttl);
69
+ TYPE_XLNX_ZYNQMP_RTC);
105
return;
70
+ sbd = SYS_BUS_DEVICE(&s->pmc.rtc);
106
}
71
+ qdev_init_nofail(DEVICE(sbd));
107
@@ -XXX,XX +XXX,XX @@ static void smmuv3_range_inval(SMMUState *s, Cmd *cmd)
72
+
108
73
+ mr = sysbus_mmio_get_region(sbd, 0);
109
num_pages = (mask + 1) >> granule;
74
+ memory_region_add_subregion(&s->mr_ps, MM_PMC_RTC, mr);
110
trace_smmuv3_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf);
75
+
111
- smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages);
76
+ /*
112
+ smmuv3_inv_notifiers_iova(s, asid, vmid, addr, tg, num_pages);
77
+ * TODO: Connect the ALARM and SECONDS interrupts once our RTC model
113
smmu_iotlb_inv_iova(s, asid, vmid, addr, tg, num_pages, ttl);
78
+ * supports them.
114
addr += mask + 1;
79
+ */
115
}
80
+ sysbus_connect_irq(sbd, 1, pic[VERSAL_RTC_APB_ERR_IRQ]);
116
diff --git a/hw/arm/trace-events b/hw/arm/trace-events
81
+}
117
index XXXXXXX..XXXXXXX 100644
82
+
118
--- a/hw/arm/trace-events
83
/* This takes the board allocated linear DDR memory and creates aliases
119
+++ b/hw/arm/trace-events
84
* for each split DDR range/aperture on the Versal address map.
120
@@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_tlbi_s12_vmid(uint16_t vmid) "vmid=%d"
85
*/
121
smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid=0x%x"
86
@@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp)
122
smmuv3_notify_flag_add(const char *iommu) "ADD SMMUNotifier node for iommu mr=%s"
87
versal_create_gems(s, pic);
123
smmuv3_notify_flag_del(const char *iommu) "DEL SMMUNotifier node for iommu mr=%s"
88
versal_create_admas(s, pic);
124
-smmuv3_inv_notifiers_iova(const char *name, uint16_t asid, uint64_t iova, uint8_t tg, uint64_t num_pages) "iommu mr=%s asid=%d iova=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64
89
versal_create_sds(s, pic);
125
+smmuv3_inv_notifiers_iova(const char *name, uint16_t asid, uint16_t vmid, uint64_t iova, uint8_t tg, uint64_t num_pages) "iommu mr=%s asid=%d vmid=%d iova=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64
90
+ versal_create_rtc(s, pic);
91
versal_map_ddr(s);
92
versal_unimp(s);
93
126
94
--
127
--
95
2.20.1
128
2.34.1
96
97
diff view generated by jsdifflib
1
Convert the Neon "load/store single structure to one lane" insns to
1
From: Mostafa Saleh <smostafa@google.com>
2
decodetree.
3
2
4
As this is the last set of insns in the neon load/store group,
3
As everything is in place, we can use a new system property to
5
we can remove the whole disas_neon_ls_insn() function.
4
advertise which stage is supported and remove bad_ste from STE
5
stage2 config.
6
6
7
The property added arm-smmuv3.stage can have 3 values:
8
- "1": Stage-1 only is advertised.
9
- "2": Stage-2 only is advertised.
10
11
If not passed or an unsupported value is passed, it will default to
12
stage-1.
13
14
Advertise VMID16.
15
16
Don't try to decode CD, if stage-2 is configured.
17
18
Reviewed-by: Eric Auger <eric.auger@redhat.com>
19
Signed-off-by: Mostafa Saleh <smostafa@google.com>
20
Tested-by: Eric Auger <eric.auger@redhat.com>
21
Tested-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
22
Message-id: 20230516203327.2051088-11-smostafa@google.com
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
23
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
9
Message-id: 20200430181003.21682-14-peter.maydell@linaro.org
10
---
24
---
11
target/arm/neon-ls.decode | 11 +++
25
include/hw/arm/smmuv3.h | 1 +
12
target/arm/translate-neon.inc.c | 89 +++++++++++++++++++
26
hw/arm/smmuv3.c | 32 ++++++++++++++++++++++----------
13
target/arm/translate.c | 147 --------------------------------
27
2 files changed, 23 insertions(+), 10 deletions(-)
14
3 files changed, 100 insertions(+), 147 deletions(-)
15
28
16
diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode
29
diff --git a/include/hw/arm/smmuv3.h b/include/hw/arm/smmuv3.h
17
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
18
--- a/target/arm/neon-ls.decode
31
--- a/include/hw/arm/smmuv3.h
19
+++ b/target/arm/neon-ls.decode
32
+++ b/include/hw/arm/smmuv3.h
20
@@ -XXX,XX +XXX,XX @@ VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \
33
@@ -XXX,XX +XXX,XX @@ struct SMMUv3State {
21
34
22
VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \
35
qemu_irq irq[4];
23
vd=%vd_dp
36
QemuMutex mutex;
24
+
37
+ char *stage;
25
+# Neon load/store single structure to one lane
38
};
26
+%imm1_5_p1 5:1 !function=plus1
39
27
+%imm1_6_p1 6:1 !function=plus1
40
typedef enum {
28
+
41
diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c
29
+VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 00 n:2 reg_idx:3 align:1 rm:4 \
30
+ vd=%vd_dp size=0 stride=1
31
+VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 01 n:2 reg_idx:2 align:2 rm:4 \
32
+ vd=%vd_dp size=1 stride=%imm1_5_p1
33
+VLDST_single 1111 0100 1 . l:1 0 rn:4 .... 10 n:2 reg_idx:1 align:3 rm:4 \
34
+ vd=%vd_dp size=2 stride=%imm1_6_p1
35
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
36
index XXXXXXX..XXXXXXX 100644
42
index XXXXXXX..XXXXXXX 100644
37
--- a/target/arm/translate-neon.inc.c
43
--- a/hw/arm/smmuv3.c
38
+++ b/target/arm/translate-neon.inc.c
44
+++ b/hw/arm/smmuv3.c
39
@@ -XXX,XX +XXX,XX @@
45
@@ -XXX,XX +XXX,XX @@
40
* It might be possible to convert it to a standalone .c file eventually.
46
#include "hw/irq.h"
41
*/
47
#include "hw/sysbus.h"
42
48
#include "migration/vmstate.h"
43
+static inline int plus1(DisasContext *s, int x)
49
+#include "hw/qdev-properties.h"
44
+{
50
#include "hw/qdev-core.h"
45
+ return x + 1;
51
#include "hw/pci/pci.h"
46
+}
52
#include "cpu.h"
47
+
53
@@ -XXX,XX +XXX,XX @@ void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *info)
48
/* Include the generated Neon decoder */
54
49
#include "decode-neon-dp.inc.c"
55
static void smmuv3_init_regs(SMMUv3State *s)
50
#include "decode-neon-ls.inc.c"
56
{
51
@@ -XXX,XX +XXX,XX @@ static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a)
57
- /**
52
58
- * IDR0: stage1 only, AArch64 only, coherent access, 16b ASID,
53
return true;
59
- * multi-level stream table
54
}
60
- */
55
+
61
- s->idr[0] = FIELD_DP32(s->idr[0], IDR0, S1P, 1); /* stage 1 supported */
56
+static bool trans_VLDST_single(DisasContext *s, arg_VLDST_single *a)
62
+ /* Based on sys property, the stages supported in smmu will be advertised.*/
57
+{
63
+ if (s->stage && !strcmp("2", s->stage)) {
58
+ /* Neon load/store single structure to one lane */
64
+ s->idr[0] = FIELD_DP32(s->idr[0], IDR0, S2P, 1);
59
+ int reg;
65
+ } else {
60
+ int nregs = a->n + 1;
66
+ s->idr[0] = FIELD_DP32(s->idr[0], IDR0, S1P, 1);
61
+ int vd = a->vd;
62
+ TCGv_i32 addr, tmp;
63
+
64
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
65
+ return false;
66
+ }
67
+ }
67
+
68
+
68
+ /* UNDEF accesses to D16-D31 if they don't exist */
69
s->idr[0] = FIELD_DP32(s->idr[0], IDR0, TTF, 2); /* AArch64 PTW only */
69
+ if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) {
70
s->idr[0] = FIELD_DP32(s->idr[0], IDR0, COHACC, 1); /* IO coherent */
70
+ return false;
71
s->idr[0] = FIELD_DP32(s->idr[0], IDR0, ASID16, 1); /* 16-bit ASID */
71
+ }
72
+ s->idr[0] = FIELD_DP32(s->idr[0], IDR0, VMID16, 1); /* 16-bit VMID */
73
s->idr[0] = FIELD_DP32(s->idr[0], IDR0, TTENDIAN, 2); /* little endian */
74
s->idr[0] = FIELD_DP32(s->idr[0], IDR0, STALL_MODEL, 1); /* No stall */
75
/* terminated transaction will always be aborted/error returned */
76
@@ -XXX,XX +XXX,XX @@ static int decode_ste_s2_cfg(SMMUTransCfg *cfg, STE *ste)
77
goto bad_ste;
78
}
79
80
- /* This is still here as stage 2 has not been fully enabled yet. */
81
- qemu_log_mask(LOG_UNIMP, "SMMUv3 does not support stage 2 yet\n");
82
- goto bad_ste;
83
-
84
return 0;
85
86
bad_ste:
87
@@ -XXX,XX +XXX,XX @@ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg,
88
return ret;
89
}
90
91
- if (cfg->aborted || cfg->bypassed) {
92
+ if (cfg->aborted || cfg->bypassed || (cfg->stage == 2)) {
93
return 0;
94
}
95
96
@@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_smmuv3 = {
97
}
98
};
99
100
+static Property smmuv3_properties[] = {
101
+ /*
102
+ * Stages of translation advertised.
103
+ * "1": Stage 1
104
+ * "2": Stage 2
105
+ * Defaults to stage 1
106
+ */
107
+ DEFINE_PROP_STRING("stage", SMMUv3State, stage),
108
+ DEFINE_PROP_END_OF_LIST()
109
+};
72
+
110
+
73
+ /* Catch the UNDEF cases. This is unavoidably a bit messy. */
111
static void smmuv3_instance_init(Object *obj)
74
+ switch (nregs) {
112
{
75
+ case 1:
113
/* Nothing much to do here as of now */
76
+ if (((a->align & (1 << a->size)) != 0) ||
114
@@ -XXX,XX +XXX,XX @@ static void smmuv3_class_init(ObjectClass *klass, void *data)
77
+ (a->size == 2 && ((a->align & 3) == 1 || (a->align & 3) == 2))) {
115
&c->parent_phases);
78
+ return false;
116
c->parent_realize = dc->realize;
79
+ }
117
dc->realize = smmu_realize;
80
+ break;
118
+ device_class_set_props(dc, smmuv3_properties);
81
+ case 3:
82
+ if ((a->align & 1) != 0) {
83
+ return false;
84
+ }
85
+ /* fall through */
86
+ case 2:
87
+ if (a->size == 2 && (a->align & 2) != 0) {
88
+ return false;
89
+ }
90
+ break;
91
+ case 4:
92
+ if ((a->size == 2) && ((a->align & 3) == 3)) {
93
+ return false;
94
+ }
95
+ break;
96
+ default:
97
+ abort();
98
+ }
99
+ if ((vd + a->stride * (nregs - 1)) > 31) {
100
+ /*
101
+ * Attempts to write off the end of the register file are
102
+ * UNPREDICTABLE; we choose to UNDEF because otherwise we would
103
+ * access off the end of the array that holds the register data.
104
+ */
105
+ return false;
106
+ }
107
+
108
+ if (!vfp_access_check(s)) {
109
+ return true;
110
+ }
111
+
112
+ tmp = tcg_temp_new_i32();
113
+ addr = tcg_temp_new_i32();
114
+ load_reg_var(s, addr, a->rn);
115
+ /*
116
+ * TODO: if we implemented alignment exceptions, we should check
117
+ * addr against the alignment encoded in a->align here.
118
+ */
119
+ for (reg = 0; reg < nregs; reg++) {
120
+ if (a->l) {
121
+ gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
122
+ s->be_data | a->size);
123
+ neon_store_element(vd, a->reg_idx, a->size, tmp);
124
+ } else { /* Store */
125
+ neon_load_element(tmp, vd, a->reg_idx, a->size);
126
+ gen_aa32_st_i32(s, tmp, addr, get_mem_index(s),
127
+ s->be_data | a->size);
128
+ }
129
+ vd += a->stride;
130
+ tcg_gen_addi_i32(addr, addr, 1 << a->size);
131
+ }
132
+ tcg_temp_free_i32(addr);
133
+ tcg_temp_free_i32(tmp);
134
+
135
+ gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << a->size) * nregs);
136
+
137
+ return true;
138
+}
139
diff --git a/target/arm/translate.c b/target/arm/translate.c
140
index XXXXXXX..XXXXXXX 100644
141
--- a/target/arm/translate.c
142
+++ b/target/arm/translate.c
143
@@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
144
tcg_temp_free_i32(rd);
145
}
119
}
146
120
147
-
121
static int smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu,
148
-/* Translate a NEON load/store element instruction. Return nonzero if the
149
- instruction is invalid. */
150
-static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
151
-{
152
- int rd, rn, rm;
153
- int nregs;
154
- int stride;
155
- int size;
156
- int reg;
157
- int load;
158
- TCGv_i32 addr;
159
- TCGv_i32 tmp;
160
-
161
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
162
- return 1;
163
- }
164
-
165
- /* FIXME: this access check should not take precedence over UNDEF
166
- * for invalid encodings; we will generate incorrect syndrome information
167
- * for attempts to execute invalid vfp/neon encodings with FP disabled.
168
- */
169
- if (s->fp_excp_el) {
170
- gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
171
- syn_simd_access_trap(1, 0xe, false), s->fp_excp_el);
172
- return 0;
173
- }
174
-
175
- if (!s->vfp_enabled)
176
- return 1;
177
- VFP_DREG_D(rd, insn);
178
- rn = (insn >> 16) & 0xf;
179
- rm = insn & 0xf;
180
- load = (insn & (1 << 21)) != 0;
181
- if ((insn & (1 << 23)) == 0) {
182
- /* Load store all elements -- handled already by decodetree */
183
- return 1;
184
- } else {
185
- size = (insn >> 10) & 3;
186
- if (size == 3) {
187
- /* Load single element to all lanes -- handled by decodetree */
188
- return 1;
189
- } else {
190
- /* Single element. */
191
- int idx = (insn >> 4) & 0xf;
192
- int reg_idx;
193
- switch (size) {
194
- case 0:
195
- reg_idx = (insn >> 5) & 7;
196
- stride = 1;
197
- break;
198
- case 1:
199
- reg_idx = (insn >> 6) & 3;
200
- stride = (insn & (1 << 5)) ? 2 : 1;
201
- break;
202
- case 2:
203
- reg_idx = (insn >> 7) & 1;
204
- stride = (insn & (1 << 6)) ? 2 : 1;
205
- break;
206
- default:
207
- abort();
208
- }
209
- nregs = ((insn >> 8) & 3) + 1;
210
- /* Catch the UNDEF cases. This is unavoidably a bit messy. */
211
- switch (nregs) {
212
- case 1:
213
- if (((idx & (1 << size)) != 0) ||
214
- (size == 2 && ((idx & 3) == 1 || (idx & 3) == 2))) {
215
- return 1;
216
- }
217
- break;
218
- case 3:
219
- if ((idx & 1) != 0) {
220
- return 1;
221
- }
222
- /* fall through */
223
- case 2:
224
- if (size == 2 && (idx & 2) != 0) {
225
- return 1;
226
- }
227
- break;
228
- case 4:
229
- if ((size == 2) && ((idx & 3) == 3)) {
230
- return 1;
231
- }
232
- break;
233
- default:
234
- abort();
235
- }
236
- if ((rd + stride * (nregs - 1)) > 31) {
237
- /* Attempts to write off the end of the register file
238
- * are UNPREDICTABLE; we choose to UNDEF because otherwise
239
- * the neon_load_reg() would write off the end of the array.
240
- */
241
- return 1;
242
- }
243
- tmp = tcg_temp_new_i32();
244
- addr = tcg_temp_new_i32();
245
- load_reg_var(s, addr, rn);
246
- for (reg = 0; reg < nregs; reg++) {
247
- if (load) {
248
- gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
249
- s->be_data | size);
250
- neon_store_element(rd, reg_idx, size, tmp);
251
- } else { /* Store */
252
- neon_load_element(tmp, rd, reg_idx, size);
253
- gen_aa32_st_i32(s, tmp, addr, get_mem_index(s),
254
- s->be_data | size);
255
- }
256
- rd += stride;
257
- tcg_gen_addi_i32(addr, addr, 1 << size);
258
- }
259
- tcg_temp_free_i32(addr);
260
- tcg_temp_free_i32(tmp);
261
- stride = nregs * (1 << size);
262
- }
263
- }
264
- if (rm != 15) {
265
- TCGv_i32 base;
266
-
267
- base = load_reg(s, rn);
268
- if (rm == 13) {
269
- tcg_gen_addi_i32(base, base, stride);
270
- } else {
271
- TCGv_i32 index;
272
- index = load_reg(s, rm);
273
- tcg_gen_add_i32(base, base, index);
274
- tcg_temp_free_i32(index);
275
- }
276
- store_reg(s, rn, base);
277
- }
278
- return 0;
279
-}
280
-
281
static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src)
282
{
283
switch (size) {
284
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
285
}
286
return;
287
}
288
- if ((insn & 0x0f100000) == 0x04000000) {
289
- /* NEON load/store. */
290
- if (disas_neon_ls_insn(s, insn)) {
291
- goto illegal_op;
292
- }
293
- return;
294
- }
295
if ((insn & 0x0e000f00) == 0x0c000100) {
296
if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) {
297
/* iWMMXt register transfer. */
298
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
299
}
300
break;
301
case 12:
302
- if ((insn & 0x01100000) == 0x01000000) {
303
- if (disas_neon_ls_insn(s, insn)) {
304
- goto illegal_op;
305
- }
306
- break;
307
- }
308
goto illegal_op;
309
default:
310
illegal_op:
311
--
122
--
312
2.20.1
123
2.34.1
313
314
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Tommy Wu <tommy.wu@sifive.com>
2
2
3
Add support for SD.
3
When we receive a packet from the xilinx_axienet and then try to s2mem
4
through the xilinx_axidma, if the descriptor ring buffer is full in the
5
xilinx axidma driver, we’ll assert the DMASR.HALTED in the
6
function : stream_process_s2mem and return 0. In the end, we’ll be stuck in
7
an infinite loop in axienet_eth_rx_notify.
4
8
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
9
This patch checks the DMASR.HALTED state when we try to push data
6
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
10
from xilinx axi-enet to xilinx axi-dma. When the DMASR.HALTED is asserted,
7
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
11
we will not keep pushing the data and then prevent the infinte loop.
8
Message-id: 20200427181649.26851-11-edgar.iglesias@gmail.com
12
13
Signed-off-by: Tommy Wu <tommy.wu@sifive.com>
14
Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com>
15
Reviewed-by: Frank Chang <frank.chang@sifive.com>
16
Message-id: 20230519062137.1251741-1-tommy.wu@sifive.com
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
18
---
11
hw/arm/xlnx-versal-virt.c | 46 +++++++++++++++++++++++++++++++++++++++
19
hw/dma/xilinx_axidma.c | 11 ++++++++---
12
1 file changed, 46 insertions(+)
20
1 file changed, 8 insertions(+), 3 deletions(-)
13
21
14
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
22
diff --git a/hw/dma/xilinx_axidma.c b/hw/dma/xilinx_axidma.c
15
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/arm/xlnx-versal-virt.c
24
--- a/hw/dma/xilinx_axidma.c
17
+++ b/hw/arm/xlnx-versal-virt.c
25
+++ b/hw/dma/xilinx_axidma.c
18
@@ -XXX,XX +XXX,XX @@
26
@@ -XXX,XX +XXX,XX @@ static inline int stream_idle(struct Stream *s)
19
#include "hw/arm/sysbus-fdt.h"
27
return !!(s->regs[R_DMASR] & DMASR_IDLE);
20
#include "hw/arm/fdt.h"
21
#include "cpu.h"
22
+#include "hw/qdev-properties.h"
23
#include "hw/arm/xlnx-versal.h"
24
25
#define TYPE_XLNX_VERSAL_VIRT_MACHINE MACHINE_TYPE_NAME("xlnx-versal-virt")
26
@@ -XXX,XX +XXX,XX @@ static void fdt_add_zdma_nodes(VersalVirt *s)
27
}
28
}
28
}
29
29
30
+static void fdt_add_sd_nodes(VersalVirt *s)
30
+static inline int stream_halted(struct Stream *s)
31
+{
31
+{
32
+ const char clocknames[] = "clk_xin\0clk_ahb";
32
+ return !!(s->regs[R_DMASR] & DMASR_HALTED);
33
+ const char compat[] = "arasan,sdhci-8.9a";
34
+ int i;
35
+
36
+ for (i = ARRAY_SIZE(s->soc.pmc.iou.sd) - 1; i >= 0; i--) {
37
+ uint64_t addr = MM_PMC_SD0 + MM_PMC_SD0_SIZE * i;
38
+ char *name = g_strdup_printf("/sdhci@%" PRIx64, addr);
39
+
40
+ qemu_fdt_add_subnode(s->fdt, name);
41
+
42
+ qemu_fdt_setprop_cells(s->fdt, name, "clocks",
43
+ s->phandle.clk_25Mhz, s->phandle.clk_25Mhz);
44
+ qemu_fdt_setprop(s->fdt, name, "clock-names",
45
+ clocknames, sizeof(clocknames));
46
+ qemu_fdt_setprop_cells(s->fdt, name, "interrupts",
47
+ GIC_FDT_IRQ_TYPE_SPI, VERSAL_SD0_IRQ_0 + i * 2,
48
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI);
49
+ qemu_fdt_setprop_sized_cells(s->fdt, name, "reg",
50
+ 2, addr, 2, MM_PMC_SD0_SIZE);
51
+ qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat));
52
+ g_free(name);
53
+ }
54
+}
33
+}
55
+
34
+
56
static void fdt_nop_memory_nodes(void *fdt, Error **errp)
35
static void stream_reset(struct Stream *s)
57
{
36
{
58
Error *err = NULL;
37
s->regs[R_DMASR] = DMASR_HALTED; /* starts up halted. */
59
@@ -XXX,XX +XXX,XX @@ static void create_virtio_regions(VersalVirt *s)
38
@@ -XXX,XX +XXX,XX @@ static void stream_process_mem2s(struct Stream *s, StreamSink *tx_data_dev,
39
uint64_t addr;
40
bool eop;
41
42
- if (!stream_running(s) || stream_idle(s)) {
43
+ if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
44
return;
60
}
45
}
61
}
46
62
47
@@ -XXX,XX +XXX,XX @@ static size_t stream_process_s2mem(struct Stream *s, unsigned char *buf,
63
+static void sd_plugin_card(SDHCIState *sd, DriveInfo *di)
48
unsigned int rxlen;
64
+{
49
size_t pos = 0;
65
+ BlockBackend *blk = di ? blk_by_legacy_dinfo(di) : NULL;
50
66
+ DeviceState *card;
51
- if (!stream_running(s) || stream_idle(s)) {
67
+
52
+ if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
68
+ card = qdev_create(qdev_get_child_bus(DEVICE(sd), "sd-bus"), TYPE_SD_CARD);
53
return 0;
69
+ object_property_add_child(OBJECT(sd), "card[*]", OBJECT(card),
54
}
70
+ &error_fatal);
55
71
+ qdev_prop_set_drive(card, "drive", blk, &error_fatal);
56
@@ -XXX,XX +XXX,XX @@ xilinx_axidma_data_stream_can_push(StreamSink *obj,
72
+ object_property_set_bool(OBJECT(card), true, "realized", &error_fatal);
57
XilinxAXIDMAStreamSink *ds = XILINX_AXI_DMA_DATA_STREAM(obj);
73
+}
58
struct Stream *s = &ds->dma->streams[1];
74
+
59
75
static void versal_virt_init(MachineState *machine)
60
- if (!stream_running(s) || stream_idle(s)) {
76
{
61
+ if (!stream_running(s) || stream_idle(s) || stream_halted(s)) {
77
VersalVirt *s = XLNX_VERSAL_VIRT_MACHINE(machine);
62
ds->dma->notify = notify;
78
int psci_conduit = QEMU_PSCI_CONDUIT_DISABLED;
63
ds->dma->notify_opaque = notify_opaque;
79
+ int i;
64
return false;
80
81
/*
82
* If the user provides an Operating System to be loaded, we expect them
83
@@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine)
84
fdt_add_gic_nodes(s);
85
fdt_add_timer_nodes(s);
86
fdt_add_zdma_nodes(s);
87
+ fdt_add_sd_nodes(s);
88
fdt_add_cpu_nodes(s, psci_conduit);
89
fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz);
90
fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz);
91
@@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine)
92
memory_region_add_subregion_overlap(get_system_memory(),
93
0, &s->soc.fpd.apu.mr, 0);
94
95
+ /* Plugin SD cards. */
96
+ for (i = 0; i < ARRAY_SIZE(s->soc.pmc.iou.sd); i++) {
97
+ sd_plugin_card(&s->soc.pmc.iou.sd[i], drive_get_next(IF_SD));
98
+ }
99
+
100
s->binfo.ram_size = machine->ram_size;
101
s->binfo.loader_start = 0x0;
102
s->binfo.get_dtb = versal_virt_get_dtb;
103
--
65
--
104
2.20.1
66
2.34.1
105
67
106
68
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Clément Chigot <chigot@adacore.com>
2
2
3
Move misplaced comment.
3
When passing --smp with a number lower than XLNX_ZYNQMP_NUM_APU_CPUS,
4
the expression (ms->smp.cpus - XLNX_ZYNQMP_NUM_APU_CPUS) will result
5
in a positive number as ms->smp.cpus is a unsigned int.
6
This will raise the following error afterwards, as Qemu will try to
7
instantiate some additional RPUs.
8
| $ qemu-system-aarch64 --smp 1 -M xlnx-zcu102
9
| **
10
| ERROR:../src/tcg/tcg.c:777:tcg_register_thread:
11
| assertion failed: (n < tcg_max_ctxs)
4
12
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
13
Signed-off-by: Clément Chigot <chigot@adacore.com>
6
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
14
Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com>
7
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
15
Tested-by: Francisco Iglesias <frasse.iglesias@gmail.com>
8
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
16
Message-id: 20230524143714.565792-1-chigot@adacore.com
9
Message-id: 20200427181649.26851-3-edgar.iglesias@gmail.com
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
17
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
18
---
12
hw/arm/xlnx-versal.c | 2 +-
19
hw/arm/xlnx-zynqmp.c | 2 +-
13
1 file changed, 1 insertion(+), 1 deletion(-)
20
1 file changed, 1 insertion(+), 1 deletion(-)
14
21
15
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
22
diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c
16
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/arm/xlnx-versal.c
24
--- a/hw/arm/xlnx-zynqmp.c
18
+++ b/hw/arm/xlnx-versal.c
25
+++ b/hw/arm/xlnx-zynqmp.c
19
@@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s)
26
@@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_create_rpu(MachineState *ms, XlnxZynqMPState *s,
20
27
const char *boot_cpu, Error **errp)
21
obj = object_new(XLNX_VERSAL_ACPU_TYPE);
28
{
22
if (!obj) {
29
int i;
23
- /* Secondary CPUs start in PSCI powered-down state */
30
- int num_rpus = MIN(ms->smp.cpus - XLNX_ZYNQMP_NUM_APU_CPUS,
24
error_report("Unable to create apu.cpu[%d] of type %s",
31
+ int num_rpus = MIN((int)(ms->smp.cpus - XLNX_ZYNQMP_NUM_APU_CPUS),
25
i, XLNX_VERSAL_ACPU_TYPE);
32
XLNX_ZYNQMP_NUM_RPU_CPUS);
26
exit(EXIT_FAILURE);
33
27
@@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s)
34
if (num_rpus <= 0) {
28
object_property_set_int(obj, s->cfg.psci_conduit,
29
"psci-conduit", &error_abort);
30
if (i) {
31
+ /* Secondary CPUs start in PSCI powered-down state */
32
object_property_set_bool(obj, true,
33
"start-powered-off", &error_abort);
34
}
35
--
35
--
36
2.20.1
36
2.34.1
37
37
38
38
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Thomas Huth <thuth@redhat.com>
2
2
3
Embed the UARTs into the SoC type.
3
pflash-cfi02-test.c always uses the "musicpal" machine for testing,
4
test-arm-mptimer.c always uses the "vexpress-a9" machine, and
5
microbit-test.c requires the "microbit" machine, so we should only
6
run these tests if the machines have been enabled in the configuration.
4
7
5
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
8
Signed-off-by: Thomas Huth <thuth@redhat.com>
6
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
9
Reviewed-by: Fabiano Rosas <farosas@suse.de>
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
10
Message-id: 20230524080600.1618137-1-thuth@redhat.com
8
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
9
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
10
Message-id: 20200427181649.26851-5-edgar.iglesias@gmail.com
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
---
12
---
13
include/hw/arm/xlnx-versal.h | 3 ++-
13
tests/qtest/meson.build | 7 ++++---
14
hw/arm/xlnx-versal.c | 12 ++++++------
14
1 file changed, 4 insertions(+), 3 deletions(-)
15
2 files changed, 8 insertions(+), 7 deletions(-)
16
15
17
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
16
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
18
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
19
--- a/include/hw/arm/xlnx-versal.h
18
--- a/tests/qtest/meson.build
20
+++ b/include/hw/arm/xlnx-versal.h
19
+++ b/tests/qtest/meson.build
21
@@ -XXX,XX +XXX,XX @@
20
@@ -XXX,XX +XXX,XX @@ qtests_arm = \
22
#include "hw/sysbus.h"
21
(config_all_devices.has_key('CONFIG_CMSDK_APB_DUALTIMER') ? ['cmsdk-apb-dualtimer-test'] : []) + \
23
#include "hw/arm/boot.h"
22
(config_all_devices.has_key('CONFIG_CMSDK_APB_TIMER') ? ['cmsdk-apb-timer-test'] : []) + \
24
#include "hw/intc/arm_gicv3.h"
23
(config_all_devices.has_key('CONFIG_CMSDK_APB_WATCHDOG') ? ['cmsdk-apb-watchdog-test'] : []) + \
25
+#include "hw/char/pl011.h"
24
- (config_all_devices.has_key('CONFIG_PFLASH_CFI02') ? ['pflash-cfi02-test'] : []) + \
26
25
+ (config_all_devices.has_key('CONFIG_PFLASH_CFI02') and
27
#define TYPE_XLNX_VERSAL "xlnx-versal"
26
+ config_all_devices.has_key('CONFIG_MUSICPAL') ? ['pflash-cfi02-test'] : []) + \
28
#define XLNX_VERSAL(obj) OBJECT_CHECK(Versal, (obj), TYPE_XLNX_VERSAL)
27
(config_all_devices.has_key('CONFIG_ASPEED_SOC') ? qtests_aspeed : []) + \
29
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
28
(config_all_devices.has_key('CONFIG_NPCM7XX') ? qtests_npcm7xx : []) + \
30
MemoryRegion mr_ocm;
29
(config_all_devices.has_key('CONFIG_GENERIC_LOADER') ? ['hexloader-test'] : []) + \
31
30
(config_all_devices.has_key('CONFIG_TPM_TIS_I2C') ? ['tpm-tis-i2c-test'] : []) + \
32
struct {
31
+ (config_all_devices.has_key('CONFIG_VEXPRESS') ? ['test-arm-mptimer'] : []) + \
33
- SysBusDevice *uart[XLNX_VERSAL_NR_UARTS];
32
+ (config_all_devices.has_key('CONFIG_MICROBIT') ? ['microbit-test'] : []) + \
34
+ PL011State uart[XLNX_VERSAL_NR_UARTS];
33
['arm-cpu-features',
35
SysBusDevice *gem[XLNX_VERSAL_NR_GEMS];
34
- 'microbit-test',
36
SysBusDevice *adma[XLNX_VERSAL_NR_ADMAS];
35
- 'test-arm-mptimer',
37
} iou;
36
'boot-serial-test']
38
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
37
39
index XXXXXXX..XXXXXXX 100644
38
# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make bios-tables-test unconditional
40
--- a/hw/arm/xlnx-versal.c
41
+++ b/hw/arm/xlnx-versal.c
42
@@ -XXX,XX +XXX,XX @@
43
#include "kvm_arm.h"
44
#include "hw/misc/unimp.h"
45
#include "hw/arm/xlnx-versal.h"
46
-#include "hw/char/pl011.h"
47
48
#define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72")
49
#define GEM_REVISION 0x40070106
50
@@ -XXX,XX +XXX,XX @@ static void versal_create_uarts(Versal *s, qemu_irq *pic)
51
DeviceState *dev;
52
MemoryRegion *mr;
53
54
- dev = qdev_create(NULL, TYPE_PL011);
55
- s->lpd.iou.uart[i] = SYS_BUS_DEVICE(dev);
56
+ sysbus_init_child_obj(OBJECT(s), name,
57
+ &s->lpd.iou.uart[i], sizeof(s->lpd.iou.uart[i]),
58
+ TYPE_PL011);
59
+ dev = DEVICE(&s->lpd.iou.uart[i]);
60
qdev_prop_set_chr(dev, "chardev", serial_hd(i));
61
- object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal);
62
qdev_init_nofail(dev);
63
64
- mr = sysbus_mmio_get_region(s->lpd.iou.uart[i], 0);
65
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
66
memory_region_add_subregion(&s->mr_ps, addrs[i], mr);
67
68
- sysbus_connect_irq(s->lpd.iou.uart[i], 0, pic[irqs[i]]);
69
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[irqs[i]]);
70
g_free(name);
71
}
72
}
73
--
39
--
74
2.20.1
40
2.34.1
75
76
diff view generated by jsdifflib
1
We're going to want at least some of the NeonGen* typedefs
1
For M-profile, there is no guest-facing A-profile format FSR, but we
2
for the refactored 32-bit Neon decoder, so move them all
2
still use the env->exception.fsr field to pass fault information from
3
to translate.h since it makes more sense to keep them in
3
the point where a fault is raised to the code in
4
one group.
4
arm_v7m_cpu_do_interrupt() which interprets it and sets the M-profile
5
specific fault status registers. So it doesn't matter whether we
6
fill in env->exception.fsr in the short format or the LPAE format, as
7
long as both sides agree. As it happens arm_v7m_cpu_do_interrupt()
8
assumes short-form.
5
9
10
In compute_fsr_fsc() we weren't explicitly choosing short-form for
11
M-profile, but instead relied on it falling out in the wash because
12
arm_s1_regime_using_lpae_format() would be false. This was broken in
13
commit 452c67a4 when we added v8R support, because we said "PMSAv8 is
14
always LPAE format" (as it is for v8R), forgetting that we were
15
implicitly using this code path on M-profile. At that point we would
16
hit a g_assert_not_reached():
17
ERROR:../../target/arm/internals.h:549:arm_fi_to_lfsc: code should not be reached
18
19
#7 0x0000555555e055f7 in arm_fi_to_lfsc (fi=0x7fffecff9a90) at ../../target/arm/internals.h:549
20
#8 0x0000555555e05a27 in compute_fsr_fsc (env=0x555557356670, fi=0x7fffecff9a90, target_el=1, mmu_idx=1, ret_fsc=0x7fffecff9a1c)
21
at ../../target/arm/tlb_helper.c:95
22
#9 0x0000555555e05b62 in arm_deliver_fault (cpu=0x555557354800, addr=268961344, access_type=MMU_INST_FETCH, mmu_idx=1, fi=0x7fffecff9a90)
23
at ../../target/arm/tlb_helper.c:132
24
#10 0x0000555555e06095 in arm_cpu_tlb_fill (cs=0x555557354800, address=268961344, size=1, access_type=MMU_INST_FETCH, mmu_idx=1, probe=false, retaddr=0)
25
at ../../target/arm/tlb_helper.c:260
26
27
The specific assertion changed when commit fcc7404eff24b4c added
28
"assert not M-profile" to arm_is_secure_below_el3(), because the
29
conditions being checked in compute_fsr_fsc() include
30
arm_el_is_aa64(), which will end up calling arm_is_secure_below_el3()
31
and asserting before we try to call arm_fi_to_lfsc():
32
33
#7 0x0000555555efaf43 in arm_is_secure_below_el3 (env=0x5555574665a0) at ../../target/arm/cpu.h:2396
34
#8 0x0000555555efb103 in arm_is_el2_enabled (env=0x5555574665a0) at ../../target/arm/cpu.h:2448
35
#9 0x0000555555efb204 in arm_el_is_aa64 (env=0x5555574665a0, el=1) at ../../target/arm/cpu.h:2509
36
#10 0x0000555555efbdfd in compute_fsr_fsc (env=0x5555574665a0, fi=0x7fffecff99e0, target_el=1, mmu_idx=1, ret_fsc=0x7fffecff996c)
37
38
Avoid the assertion and the incorrect FSR format selection by
39
explicitly making M-profile use the short-format in this function.
40
41
Fixes: 452c67a42704 ("target/arm: Enable TTBCR_EAE for ARMv8-R AArch32")a
42
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1658
43
Cc: qemu-stable@nongnu.org
6
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
44
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
45
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20200430181003.21682-23-peter.maydell@linaro.org
46
Message-id: 20230523131726.866635-1-peter.maydell@linaro.org
9
---
47
---
10
target/arm/translate.h | 17 +++++++++++++++++
48
target/arm/tcg/tlb_helper.c | 13 +++++++++++--
11
target/arm/translate-a64.c | 17 -----------------
49
1 file changed, 11 insertions(+), 2 deletions(-)
12
2 files changed, 17 insertions(+), 17 deletions(-)
13
50
14
diff --git a/target/arm/translate.h b/target/arm/translate.h
51
diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c
15
index XXXXXXX..XXXXXXX 100644
52
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/translate.h
53
--- a/target/arm/tcg/tlb_helper.c
17
+++ b/target/arm/translate.h
54
+++ b/target/arm/tcg/tlb_helper.c
18
@@ -XXX,XX +XXX,XX @@ typedef void GVecGen3Fn(unsigned, uint32_t, uint32_t,
55
@@ -XXX,XX +XXX,XX @@ static uint32_t compute_fsr_fsc(CPUARMState *env, ARMMMUFaultInfo *fi,
19
typedef void GVecGen4Fn(unsigned, uint32_t, uint32_t, uint32_t,
56
ARMMMUIdx arm_mmu_idx = core_to_arm_mmu_idx(env, mmu_idx);
20
uint32_t, uint32_t, uint32_t);
57
uint32_t fsr, fsc;
21
58
22
+/* Function prototype for gen_ functions for calling Neon helpers */
59
- if (target_el == 2 || arm_el_is_aa64(env, target_el) ||
23
+typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
60
- arm_s1_regime_using_lpae_format(env, arm_mmu_idx)) {
24
+typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
61
+ /*
25
+typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
62
+ * For M-profile there is no guest-facing FSR. We compute a
26
+typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64);
63
+ * short-form value for env->exception.fsr which we will then
27
+typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64);
64
+ * examine in arm_v7m_cpu_do_interrupt(). In theory we could
28
+typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
65
+ * use the LPAE format instead as long as both bits of code agree
29
+typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
66
+ * (and arm_fi_to_lfsc() handled the M-profile specific
30
+typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
67
+ * ARMFault_QEMU_NSCExec and ARMFault_QEMU_SFault cases).
31
+typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
68
+ */
32
+typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
69
+ if (!arm_feature(env, ARM_FEATURE_M) &&
33
+typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64);
70
+ (target_el == 2 || arm_el_is_aa64(env, target_el) ||
34
+typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
71
+ arm_s1_regime_using_lpae_format(env, arm_mmu_idx))) {
35
+typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
72
/*
36
+typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
73
* LPAE format fault status register : bottom 6 bits are
37
+typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
74
* status code in the same form as needed for syndrome
38
+
39
#endif /* TARGET_ARM_TRANSLATE_H */
40
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
41
index XXXXXXX..XXXXXXX 100644
42
--- a/target/arm/translate-a64.c
43
+++ b/target/arm/translate-a64.c
44
@@ -XXX,XX +XXX,XX @@ typedef struct AArch64DecodeTable {
45
AArch64DecodeFn *disas_fn;
46
} AArch64DecodeTable;
47
48
-/* Function prototype for gen_ functions for calling Neon helpers */
49
-typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32);
50
-typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32);
51
-typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
52
-typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64);
53
-typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64);
54
-typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64);
55
-typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64);
56
-typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32);
57
-typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr);
58
-typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr);
59
-typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64);
60
-typedef void CryptoTwoOpFn(TCGv_ptr, TCGv_ptr);
61
-typedef void CryptoThreeOpIntFn(TCGv_ptr, TCGv_ptr, TCGv_i32);
62
-typedef void CryptoThreeOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr);
63
-typedef void AtomicThreeOpFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGArg, MemOp);
64
-
65
/* initialize TCG globals. */
66
void a64_translate_init(void)
67
{
68
--
75
--
69
2.20.1
76
2.34.1
70
71
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Fabiano Rosas <farosas@suse.de>
2
2
3
Add support for the RTC.
3
We currently need to select ARM_V7M unconditionally when TCG is
4
present in the build because some translate.c helpers and the whole of
5
m_helpers.c are not yet under CONFIG_ARM_V7M.
4
6
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
7
Suggested-by: Philippe Mathieu-Daudé <philmd@linaro.org>
6
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
8
Signed-off-by: Fabiano Rosas <farosas@suse.de>
7
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
9
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
8
Message-id: 20200427181649.26851-12-edgar.iglesias@gmail.com
10
Message-id: 20230523180525.29994-2-farosas@suse.de
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
12
---
11
hw/arm/xlnx-versal-virt.c | 22 ++++++++++++++++++++++
13
target/arm/Kconfig | 3 +++
12
1 file changed, 22 insertions(+)
14
1 file changed, 3 insertions(+)
13
15
14
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
16
diff --git a/target/arm/Kconfig b/target/arm/Kconfig
15
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
16
--- a/hw/arm/xlnx-versal-virt.c
18
--- a/target/arm/Kconfig
17
+++ b/hw/arm/xlnx-versal-virt.c
19
+++ b/target/arm/Kconfig
18
@@ -XXX,XX +XXX,XX @@ static void fdt_add_sd_nodes(VersalVirt *s)
20
@@ -XXX,XX +XXX,XX @@
19
}
21
config ARM
20
}
22
bool
21
23
select ARM_COMPATIBLE_SEMIHOSTING if TCG
22
+static void fdt_add_rtc_node(VersalVirt *s)
23
+{
24
+ const char compat[] = "xlnx,zynqmp-rtc";
25
+ const char interrupt_names[] = "alarm\0sec";
26
+ char *name = g_strdup_printf("/rtc@%x", MM_PMC_RTC);
27
+
24
+
28
+ qemu_fdt_add_subnode(s->fdt, name);
25
+ # We need to select this until we move m_helper.c and the
29
+
26
+ # translate.c v7m helpers under ARM_V7M.
30
+ qemu_fdt_setprop_cells(s->fdt, name, "interrupts",
27
select ARM_V7M if TCG
31
+ GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_ALARM_IRQ,
28
32
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI,
29
config AARCH64
33
+ GIC_FDT_IRQ_TYPE_SPI, VERSAL_RTC_SECONDS_IRQ,
34
+ GIC_FDT_IRQ_FLAGS_LEVEL_HI);
35
+ qemu_fdt_setprop(s->fdt, name, "interrupt-names",
36
+ interrupt_names, sizeof(interrupt_names));
37
+ qemu_fdt_setprop_sized_cells(s->fdt, name, "reg",
38
+ 2, MM_PMC_RTC, 2, MM_PMC_RTC_SIZE);
39
+ qemu_fdt_setprop(s->fdt, name, "compatible", compat, sizeof(compat));
40
+ g_free(name);
41
+}
42
+
43
static void fdt_nop_memory_nodes(void *fdt, Error **errp)
44
{
45
Error *err = NULL;
46
@@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine)
47
fdt_add_timer_nodes(s);
48
fdt_add_zdma_nodes(s);
49
fdt_add_sd_nodes(s);
50
+ fdt_add_rtc_node(s);
51
fdt_add_cpu_nodes(s, psci_conduit);
52
fdt_add_clk_node(s, "/clk125", 125000000, s->phandle.clk_125Mhz);
53
fdt_add_clk_node(s, "/clk25", 25000000, s->phandle.clk_25Mhz);
54
--
30
--
55
2.20.1
31
2.34.1
56
32
57
33
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Fabiano Rosas <farosas@suse.de>
2
2
3
Add support for SD.
3
When we moved the arm default CONFIGs into Kconfig and removed them
4
from default.mak, we made it harder to identify which CONFIGs are
5
selected by default in case users want to disable them.
4
6
5
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
7
Bring back the default entries into default.mak, but keep them
6
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
8
commented out. This way users can keep their workflows of editing
7
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
9
default.mak to remove build options without needing to search through
8
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
10
Kconfig.
9
Message-id: 20200427181649.26851-9-edgar.iglesias@gmail.com
11
12
Reported-by: Thomas Huth <thuth@redhat.com>
13
Signed-off-by: Fabiano Rosas <farosas@suse.de>
14
Reviewed-by: Thomas Huth <thuth@redhat.com>
15
Message-id: 20230523180525.29994-3-farosas@suse.de
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
16
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
17
---
12
include/hw/arm/xlnx-versal.h | 12 ++++++++++++
18
configs/devices/aarch64-softmmu/default.mak | 6 ++++
13
hw/arm/xlnx-versal.c | 31 +++++++++++++++++++++++++++++++
19
configs/devices/arm-softmmu/default.mak | 40 +++++++++++++++++++++
14
2 files changed, 43 insertions(+)
20
2 files changed, 46 insertions(+)
15
21
16
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
22
diff --git a/configs/devices/aarch64-softmmu/default.mak b/configs/devices/aarch64-softmmu/default.mak
17
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
18
--- a/include/hw/arm/xlnx-versal.h
24
--- a/configs/devices/aarch64-softmmu/default.mak
19
+++ b/include/hw/arm/xlnx-versal.h
25
+++ b/configs/devices/aarch64-softmmu/default.mak
20
@@ -XXX,XX +XXX,XX @@
26
@@ -XXX,XX +XXX,XX @@
21
27
22
#include "hw/sysbus.h"
28
# We support all the 32 bit boards so need all their config
23
#include "hw/arm/boot.h"
29
include ../arm-softmmu/default.mak
24
+#include "hw/sd/sdhci.h"
30
+
25
#include "hw/intc/arm_gicv3.h"
31
+# These are selected by default when TCG is enabled, uncomment them to
26
#include "hw/char/pl011.h"
32
+# keep out of the build.
27
#include "hw/dma/xlnx-zdma.h"
33
+# CONFIG_XLNX_ZYNQMP_ARM=n
34
+# CONFIG_XLNX_VERSAL=n
35
+# CONFIG_SBSA_REF=n
36
diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak
37
index XXXXXXX..XXXXXXX 100644
38
--- a/configs/devices/arm-softmmu/default.mak
39
+++ b/configs/devices/arm-softmmu/default.mak
28
@@ -XXX,XX +XXX,XX @@
40
@@ -XXX,XX +XXX,XX @@
29
#define XLNX_VERSAL_NR_UARTS 2
41
# CONFIG_TEST_DEVICES=n
30
#define XLNX_VERSAL_NR_GEMS 2
42
31
#define XLNX_VERSAL_NR_ADMAS 8
43
CONFIG_ARM_VIRT=y
32
+#define XLNX_VERSAL_NR_SDS 2
33
#define XLNX_VERSAL_NR_IRQS 192
34
35
typedef struct Versal {
36
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
37
} iou;
38
} lpd;
39
40
+ /* The Platform Management Controller subsystem. */
41
+ struct {
42
+ struct {
43
+ SDHCIState sd[XLNX_VERSAL_NR_SDS];
44
+ } iou;
45
+ } pmc;
46
+
44
+
47
struct {
45
+# These are selected by default when TCG is enabled, uncomment them to
48
MemoryRegion *mr_ddr;
46
+# keep out of the build.
49
uint32_t psci_conduit;
47
+# CONFIG_CUBIEBOARD=n
50
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
48
+# CONFIG_EXYNOS4=n
51
#define VERSAL_GEM1_IRQ_0 58
49
+# CONFIG_HIGHBANK=n
52
#define VERSAL_GEM1_WAKE_IRQ_0 59
50
+# CONFIG_INTEGRATOR=n
53
#define VERSAL_ADMA_IRQ_0 60
51
+# CONFIG_FSL_IMX31=n
54
+#define VERSAL_SD0_IRQ_0 126
52
+# CONFIG_MUSICPAL=n
55
53
+# CONFIG_MUSCA=n
56
/* Architecturally reserved IRQs suitable for virtualization. */
54
+# CONFIG_CHEETAH=n
57
#define VERSAL_RSVD_IRQ_FIRST 111
55
+# CONFIG_SX1=n
58
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
56
+# CONFIG_NSERIES=n
59
#define MM_FPD_CRF 0xfd1a0000U
57
+# CONFIG_STELLARIS=n
60
#define MM_FPD_CRF_SIZE 0x140000
58
+# CONFIG_STM32VLDISCOVERY=n
61
59
+# CONFIG_REALVIEW=n
62
+#define MM_PMC_SD0 0xf1040000U
60
+# CONFIG_VERSATILE=n
63
+#define MM_PMC_SD0_SIZE 0x10000
61
+# CONFIG_VEXPRESS=n
64
#define MM_PMC_CRP 0xf1260000U
62
+# CONFIG_ZYNQ=n
65
#define MM_PMC_CRP_SIZE 0x10000
63
+# CONFIG_MAINSTONE=n
66
#endif
64
+# CONFIG_GUMSTIX=n
67
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
65
+# CONFIG_SPITZ=n
68
index XXXXXXX..XXXXXXX 100644
66
+# CONFIG_TOSA=n
69
--- a/hw/arm/xlnx-versal.c
67
+# CONFIG_Z2=n
70
+++ b/hw/arm/xlnx-versal.c
68
+# CONFIG_NPCM7XX=n
71
@@ -XXX,XX +XXX,XX @@ static void versal_create_admas(Versal *s, qemu_irq *pic)
69
+# CONFIG_COLLIE=n
72
}
70
+# CONFIG_ASPEED_SOC=n
73
}
71
+# CONFIG_NETDUINO2=n
74
72
+# CONFIG_NETDUINOPLUS2=n
75
+#define SDHCI_CAPABILITIES 0x280737ec6481 /* Same as on ZynqMP. */
73
+# CONFIG_OLIMEX_STM32_H405=n
76
+static void versal_create_sds(Versal *s, qemu_irq *pic)
74
+# CONFIG_MPS2=n
77
+{
75
+# CONFIG_RASPI=n
78
+ int i;
76
+# CONFIG_DIGIC=n
79
+
77
+# CONFIG_SABRELITE=n
80
+ for (i = 0; i < ARRAY_SIZE(s->pmc.iou.sd); i++) {
78
+# CONFIG_EMCRAFT_SF2=n
81
+ DeviceState *dev;
79
+# CONFIG_MICROBIT=n
82
+ MemoryRegion *mr;
80
+# CONFIG_FSL_IMX25=n
83
+
81
+# CONFIG_FSL_IMX7=n
84
+ sysbus_init_child_obj(OBJECT(s), "sd[*]",
82
+# CONFIG_FSL_IMX6UL=n
85
+ &s->pmc.iou.sd[i], sizeof(s->pmc.iou.sd[i]),
83
+# CONFIG_ALLWINNER_H3=n
86
+ TYPE_SYSBUS_SDHCI);
87
+ dev = DEVICE(&s->pmc.iou.sd[i]);
88
+
89
+ object_property_set_uint(OBJECT(dev),
90
+ 3, "sd-spec-version", &error_fatal);
91
+ object_property_set_uint(OBJECT(dev), SDHCI_CAPABILITIES, "capareg",
92
+ &error_fatal);
93
+ object_property_set_uint(OBJECT(dev), UHS_I, "uhs", &error_fatal);
94
+ qdev_init_nofail(dev);
95
+
96
+ mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0);
97
+ memory_region_add_subregion(&s->mr_ps,
98
+ MM_PMC_SD0 + i * MM_PMC_SD0_SIZE, mr);
99
+
100
+ sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0,
101
+ pic[VERSAL_SD0_IRQ_0 + i * 2]);
102
+ }
103
+}
104
+
105
/* This takes the board allocated linear DDR memory and creates aliases
106
* for each split DDR range/aperture on the Versal address map.
107
*/
108
@@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp)
109
versal_create_uarts(s, pic);
110
versal_create_gems(s, pic);
111
versal_create_admas(s, pic);
112
+ versal_create_sds(s, pic);
113
versal_map_ddr(s);
114
versal_unimp(s);
115
116
--
84
--
117
2.20.1
85
2.34.1
118
119
diff view generated by jsdifflib
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
1
From: Fabiano Rosas <farosas@suse.de>
2
2
3
Remove inclusion of arm_gicv3_common.h, this already gets
3
Replace the 'default y if TCG' pattern with 'default y; depends on
4
included via xlnx-versal.h.
4
TCG'.
5
5
6
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
6
That makes explict that there is a dependence on TCG and enabling
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
7
these CONFIGs via .mak files without TCG present will fail earlier.
8
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
8
9
Message-id: 20200427181649.26851-2-edgar.iglesias@gmail.com
9
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
10
Signed-off-by: Fabiano Rosas <farosas@suse.de>
11
Reviewed-by: Thomas Huth <thuth@redhat.com>
12
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
13
Message-id: 20230523180525.29994-4-farosas@suse.de
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
---
15
---
12
hw/arm/xlnx-versal.c | 1 -
16
hw/arm/Kconfig | 123 ++++++++++++++++++++++++++++++++-----------------
13
1 file changed, 1 deletion(-)
17
1 file changed, 82 insertions(+), 41 deletions(-)
14
18
15
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
19
diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig
16
index XXXXXXX..XXXXXXX 100644
20
index XXXXXXX..XXXXXXX 100644
17
--- a/hw/arm/xlnx-versal.c
21
--- a/hw/arm/Kconfig
18
+++ b/hw/arm/xlnx-versal.c
22
+++ b/hw/arm/Kconfig
19
@@ -XXX,XX +XXX,XX @@
23
@@ -XXX,XX +XXX,XX @@ config ARM_VIRT
20
#include "hw/arm/boot.h"
24
21
#include "kvm_arm.h"
25
config CHEETAH
22
#include "hw/misc/unimp.h"
26
bool
23
-#include "hw/intc/arm_gicv3_common.h"
27
- default y if TCG && ARM
24
#include "hw/arm/xlnx-versal.h"
28
+ default y
25
#include "hw/char/pl011.h"
29
+ depends on TCG && ARM
30
select OMAP
31
select TSC210X
32
33
config CUBIEBOARD
34
bool
35
- default y if TCG && ARM
36
+ default y
37
+ depends on TCG && ARM
38
select ALLWINNER_A10
39
40
config DIGIC
41
bool
42
- default y if TCG && ARM
43
+ default y
44
+ depends on TCG && ARM
45
select PTIMER
46
select PFLASH_CFI02
47
48
config EXYNOS4
49
bool
50
- default y if TCG && ARM
51
+ default y
52
+ depends on TCG && ARM
53
imply I2C_DEVICES
54
select A9MPCORE
55
select I2C
56
@@ -XXX,XX +XXX,XX @@ config EXYNOS4
57
58
config HIGHBANK
59
bool
60
- default y if TCG && ARM
61
+ default y
62
+ depends on TCG && ARM
63
select A9MPCORE
64
select A15MPCORE
65
select AHCI
66
@@ -XXX,XX +XXX,XX @@ config HIGHBANK
67
68
config INTEGRATOR
69
bool
70
- default y if TCG && ARM
71
+ default y
72
+ depends on TCG && ARM
73
select ARM_TIMER
74
select INTEGRATOR_DEBUG
75
select PL011 # UART
76
@@ -XXX,XX +XXX,XX @@ config INTEGRATOR
77
78
config MAINSTONE
79
bool
80
- default y if TCG && ARM
81
+ default y
82
+ depends on TCG && ARM
83
select PXA2XX
84
select PFLASH_CFI01
85
select SMC91C111
86
87
config MUSCA
88
bool
89
- default y if TCG && ARM
90
+ default y
91
+ depends on TCG && ARM
92
select ARMSSE
93
select PL011
94
select PL031
95
@@ -XXX,XX +XXX,XX @@ config MARVELL_88W8618
96
97
config MUSICPAL
98
bool
99
- default y if TCG && ARM
100
+ default y
101
+ depends on TCG && ARM
102
select OR_IRQ
103
select BITBANG_I2C
104
select MARVELL_88W8618
105
@@ -XXX,XX +XXX,XX @@ config MUSICPAL
106
107
config NETDUINO2
108
bool
109
- default y if TCG && ARM
110
+ default y
111
+ depends on TCG && ARM
112
select STM32F205_SOC
113
114
config NETDUINOPLUS2
115
bool
116
- default y if TCG && ARM
117
+ default y
118
+ depends on TCG && ARM
119
select STM32F405_SOC
120
121
config OLIMEX_STM32_H405
122
bool
123
- default y if TCG && ARM
124
+ default y
125
+ depends on TCG && ARM
126
select STM32F405_SOC
127
128
config NSERIES
129
bool
130
- default y if TCG && ARM
131
+ default y
132
+ depends on TCG && ARM
133
select OMAP
134
select TMP105 # temperature sensor
135
select BLIZZARD # LCD/TV controller
136
@@ -XXX,XX +XXX,XX @@ config PXA2XX
137
138
config GUMSTIX
139
bool
140
- default y if TCG && ARM
141
+ default y
142
+ depends on TCG && ARM
143
select PFLASH_CFI01
144
select SMC91C111
145
select PXA2XX
146
147
config TOSA
148
bool
149
- default y if TCG && ARM
150
+ default y
151
+ depends on TCG && ARM
152
select ZAURUS # scoop
153
select MICRODRIVE
154
select PXA2XX
155
@@ -XXX,XX +XXX,XX @@ config TOSA
156
157
config SPITZ
158
bool
159
- default y if TCG && ARM
160
+ default y
161
+ depends on TCG && ARM
162
select ADS7846 # touch-screen controller
163
select MAX111X # A/D converter
164
select WM8750 # audio codec
165
@@ -XXX,XX +XXX,XX @@ config SPITZ
166
167
config Z2
168
bool
169
- default y if TCG && ARM
170
+ default y
171
+ depends on TCG && ARM
172
select PFLASH_CFI01
173
select WM8750
174
select PL011 # UART
175
@@ -XXX,XX +XXX,XX @@ config Z2
176
177
config REALVIEW
178
bool
179
- default y if TCG && ARM
180
+ default y
181
+ depends on TCG && ARM
182
imply PCI_DEVICES
183
imply PCI_TESTDEV
184
imply I2C_DEVICES
185
@@ -XXX,XX +XXX,XX @@ config REALVIEW
186
187
config SBSA_REF
188
bool
189
- default y if TCG && AARCH64
190
+ default y
191
+ depends on TCG && AARCH64
192
imply PCI_DEVICES
193
select AHCI
194
select ARM_SMMUV3
195
@@ -XXX,XX +XXX,XX @@ config SBSA_REF
196
197
config SABRELITE
198
bool
199
- default y if TCG && ARM
200
+ default y
201
+ depends on TCG && ARM
202
select FSL_IMX6
203
select SSI_M25P80
204
205
config STELLARIS
206
bool
207
- default y if TCG && ARM
208
+ default y
209
+ depends on TCG && ARM
210
imply I2C_DEVICES
211
select ARM_V7M
212
select CMSDK_APB_WATCHDOG
213
@@ -XXX,XX +XXX,XX @@ config STELLARIS
214
215
config STM32VLDISCOVERY
216
bool
217
- default y if TCG && ARM
218
+ default y
219
+ depends on TCG && ARM
220
select STM32F100_SOC
221
222
config STRONGARM
223
@@ -XXX,XX +XXX,XX @@ config STRONGARM
224
225
config COLLIE
226
bool
227
- default y if TCG && ARM
228
+ default y
229
+ depends on TCG && ARM
230
select PFLASH_CFI01
231
select ZAURUS # scoop
232
select STRONGARM
233
234
config SX1
235
bool
236
- default y if TCG && ARM
237
+ default y
238
+ depends on TCG && ARM
239
select OMAP
240
241
config VERSATILE
242
bool
243
- default y if TCG && ARM
244
+ default y
245
+ depends on TCG && ARM
246
select ARM_TIMER # sp804
247
select PFLASH_CFI01
248
select LSI_SCSI_PCI
249
@@ -XXX,XX +XXX,XX @@ config VERSATILE
250
251
config VEXPRESS
252
bool
253
- default y if TCG && ARM
254
+ default y
255
+ depends on TCG && ARM
256
select A9MPCORE
257
select A15MPCORE
258
select ARM_MPTIMER
259
@@ -XXX,XX +XXX,XX @@ config VEXPRESS
260
261
config ZYNQ
262
bool
263
- default y if TCG && ARM
264
+ default y
265
+ depends on TCG && ARM
266
select A9MPCORE
267
select CADENCE # UART
268
select PFLASH_CFI02
269
@@ -XXX,XX +XXX,XX @@ config ZYNQ
270
config ARM_V7M
271
bool
272
# currently v7M must be included in a TCG build due to translate.c
273
- default y if TCG && ARM
274
+ default y
275
+ depends on TCG && ARM
276
select PTIMER
277
278
config ALLWINNER_A10
279
@@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10
280
281
config ALLWINNER_H3
282
bool
283
- default y if TCG && ARM
284
+ default y
285
+ depends on TCG && ARM
286
select ALLWINNER_A10_PIT
287
select ALLWINNER_SUN8I_EMAC
288
select ALLWINNER_I2C
289
@@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3
290
291
config RASPI
292
bool
293
- default y if TCG && ARM
294
+ default y
295
+ depends on TCG && ARM
296
select FRAMEBUFFER
297
select PL011 # UART
298
select SDHCI
299
@@ -XXX,XX +XXX,XX @@ config STM32F405_SOC
300
301
config XLNX_ZYNQMP_ARM
302
bool
303
- default y if TCG && AARCH64
304
+ default y
305
+ depends on TCG && AARCH64
306
select AHCI
307
select ARM_GIC
308
select CADENCE
309
@@ -XXX,XX +XXX,XX @@ config XLNX_ZYNQMP_ARM
310
311
config XLNX_VERSAL
312
bool
313
- default y if TCG && AARCH64
314
+ default y
315
+ depends on TCG && AARCH64
316
select ARM_GIC
317
select PL011
318
select CADENCE
319
@@ -XXX,XX +XXX,XX @@ config XLNX_VERSAL
320
321
config NPCM7XX
322
bool
323
- default y if TCG && ARM
324
+ default y
325
+ depends on TCG && ARM
326
select A9MPCORE
327
select ADM1272
328
select ARM_GIC
329
@@ -XXX,XX +XXX,XX @@ config NPCM7XX
330
331
config FSL_IMX25
332
bool
333
- default y if TCG && ARM
334
+ default y
335
+ depends on TCG && ARM
336
imply I2C_DEVICES
337
select IMX
338
select IMX_FEC
339
@@ -XXX,XX +XXX,XX @@ config FSL_IMX25
340
341
config FSL_IMX31
342
bool
343
- default y if TCG && ARM
344
+ default y
345
+ depends on TCG && ARM
346
imply I2C_DEVICES
347
select SERIAL
348
select IMX
349
@@ -XXX,XX +XXX,XX @@ config FSL_IMX6
350
351
config ASPEED_SOC
352
bool
353
- default y if TCG && ARM
354
+ default y
355
+ depends on TCG && ARM
356
select DS1338
357
select FTGMAC100
358
select I2C
359
@@ -XXX,XX +XXX,XX @@ config ASPEED_SOC
360
361
config MPS2
362
bool
363
- default y if TCG && ARM
364
+ default y
365
+ depends on TCG && ARM
366
imply I2C_DEVICES
367
select ARMSSE
368
select LAN9118
369
@@ -XXX,XX +XXX,XX @@ config MPS2
370
371
config FSL_IMX7
372
bool
373
- default y if TCG && ARM
374
+ default y
375
+ depends on TCG && ARM
376
imply PCI_DEVICES
377
imply TEST_DEVICES
378
imply I2C_DEVICES
379
@@ -XXX,XX +XXX,XX @@ config ARM_SMMUV3
380
381
config FSL_IMX6UL
382
bool
383
- default y if TCG && ARM
384
+ default y
385
+ depends on TCG && ARM
386
imply I2C_DEVICES
387
select A15MPCORE
388
select IMX
389
@@ -XXX,XX +XXX,XX @@ config FSL_IMX6UL
390
391
config MICROBIT
392
bool
393
- default y if TCG && ARM
394
+ default y
395
+ depends on TCG && ARM
396
select NRF51_SOC
397
398
config NRF51_SOC
399
@@ -XXX,XX +XXX,XX @@ config NRF51_SOC
400
401
config EMCRAFT_SF2
402
bool
403
- default y if TCG && ARM
404
+ default y
405
+ depends on TCG && ARM
406
select MSF2
407
select SSI_M25P80
26
408
27
--
409
--
28
2.20.1
410
2.34.1
29
411
30
412
diff view generated by jsdifflib
1
From: Philippe Mathieu-Daudé <f4bug@amsat.org>
1
From: Enze Li <lienze@kylinos.cn>
2
2
3
MIDR_EL1 is a 64-bit system register with the top 32-bit being RES0.
3
I noticed that in the latest version, the copyright string is still
4
Represent it in QEMU's ARMCPU struct with a uint64_t, not a
4
2022, even though 2023 is halfway through. This patch fixes that and
5
uint32_t.
5
fixes the documentation along with it.
6
6
7
This fixes an error when compiling with -Werror=conversion
7
Signed-off-by: Enze Li <lienze@kylinos.cn>
8
because we were manipulating the register value using a
9
local uint64_t variable:
10
11
target/arm/cpu64.c: In function ‘aarch64_max_initfn’:
12
target/arm/cpu64.c:628:21: error: conversion from ‘uint64_t’ {aka ‘long unsigned int’} to ‘uint32_t’ {aka ‘unsigned int’} may change value [-Werror=conversion]
13
628 | cpu->midr = t;
14
| ^
15
16
and future-proofs us against a possible future architecture
17
change using some of the top 32 bits.
18
19
Suggested-by: Laurent Desnogues <laurent.desnogues@gmail.com>
20
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
21
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
22
Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com>
23
Message-id: 20200428172634.29707-1-f4bug@amsat.org
24
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Message-id: 20230525064345.1152801-1-lienze@kylinos.cn
25
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
26
---
11
---
27
target/arm/cpu.h | 2 +-
12
docs/conf.py | 2 +-
28
target/arm/cpu.c | 2 +-
13
include/qemu/help-texts.h | 2 +-
29
2 files changed, 2 insertions(+), 2 deletions(-)
14
2 files changed, 2 insertions(+), 2 deletions(-)
30
15
31
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
16
diff --git a/docs/conf.py b/docs/conf.py
32
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
33
--- a/target/arm/cpu.h
18
--- a/docs/conf.py
34
+++ b/target/arm/cpu.h
19
+++ b/docs/conf.py
35
@@ -XXX,XX +XXX,XX @@ struct ARMCPU {
20
@@ -XXX,XX +XXX,XX @@
36
uint64_t id_aa64dfr0;
21
37
uint64_t id_aa64dfr1;
22
# General information about the project.
38
} isar;
23
project = u'QEMU'
39
- uint32_t midr;
24
-copyright = u'2022, The QEMU Project Developers'
40
+ uint64_t midr;
25
+copyright = u'2023, The QEMU Project Developers'
41
uint32_t revidr;
26
author = u'The QEMU Project Developers'
42
uint32_t reset_fpsid;
27
43
uint32_t ctr;
28
# The version info for the project you're documenting, acts as replacement for
44
diff --git a/target/arm/cpu.c b/target/arm/cpu.c
29
diff --git a/include/qemu/help-texts.h b/include/qemu/help-texts.h
45
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
46
--- a/target/arm/cpu.c
31
--- a/include/qemu/help-texts.h
47
+++ b/target/arm/cpu.c
32
+++ b/include/qemu/help-texts.h
48
@@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = {
33
@@ -XXX,XX +XXX,XX @@
49
static Property arm_cpu_properties[] = {
34
#define QEMU_HELP_TEXTS_H
50
DEFINE_PROP_BOOL("start-powered-off", ARMCPU, start_powered_off, false),
35
51
DEFINE_PROP_UINT32("psci-conduit", ARMCPU, psci_conduit, 0),
36
/* Copyright string for -version arguments, About dialogs, etc */
52
- DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0),
37
-#define QEMU_COPYRIGHT "Copyright (c) 2003-2022 " \
53
+ DEFINE_PROP_UINT64("midr", ARMCPU, midr, 0),
38
+#define QEMU_COPYRIGHT "Copyright (c) 2003-2023 " \
54
DEFINE_PROP_UINT64("mp-affinity", ARMCPU,
39
"Fabrice Bellard and the QEMU Project developers"
55
mp_affinity, ARM64_AFFINITY_INVALID),
40
56
DEFINE_PROP_INT32("node-id", ARMCPU, node_id, CPU_UNSET_NUMA_NODE_ID),
41
/* Bug reporting information for --help arguments, About dialogs, etc */
57
--
42
--
58
2.20.1
43
2.34.1
59
60
diff view generated by jsdifflib
1
We define ARMMMUIdx_Stage2 as being an MMU index which uses a QEMU
1
From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
2
TLB. However we never actually use the TLB -- all stage 2 lookups
3
are done by direct calls to get_phys_addr_lpae() followed by a
4
physical address load via address_space_ld*().
5
2
6
Remove Stage2 from the list of ARM MMU indexes which correspond to
3
Let add GIC information into DeviceTree as part of SBSA-REF versioning.
7
real core MMU indexes, and instead put it in the set of "NOTLB" ARM
8
MMU indexes.
9
4
10
This allows us to drop NB_MMU_MODES to 11. It also means we can
5
Trusted Firmware will read it and provide to next firmware level.
11
safely add support for the ARMv8.3-TTS2UXN extension, which adds
12
permission bits to the stage 2 descriptors which define execute
13
permission separatel for EL0 and EL1; supporting that while keeping
14
Stage2 in a QEMU TLB would require us to use separate TLBs for
15
"Stage2 for an EL0 access" and "Stage2 for an EL1 access", which is a
16
lot of extra complication given we aren't even using the QEMU TLB.
17
6
18
In the process of updating the comment on our MMU index use,
7
Bumps platform version to 0.1 one so we can check is node is present.
19
fix a couple of other minor errors:
20
* NS EL2 EL2&0 was missing from the list in the comment
21
* some text hadn't been updated from when we bumped NB_MMU_MODES
22
above 8
23
8
9
Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
10
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
24
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
25
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
26
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
27
Message-id: 20200330210400.11724-2-peter.maydell@linaro.org
28
---
12
---
29
target/arm/cpu-param.h | 2 +-
13
hw/arm/sbsa-ref.c | 19 ++++++++++++++++++-
30
target/arm/cpu.h | 21 +++++---
14
1 file changed, 18 insertions(+), 1 deletion(-)
31
target/arm/helper.c | 112 ++++-------------------------------------
32
3 files changed, 27 insertions(+), 108 deletions(-)
33
15
34
diff --git a/target/arm/cpu-param.h b/target/arm/cpu-param.h
16
diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c
35
index XXXXXXX..XXXXXXX 100644
17
index XXXXXXX..XXXXXXX 100644
36
--- a/target/arm/cpu-param.h
18
--- a/hw/arm/sbsa-ref.c
37
+++ b/target/arm/cpu-param.h
19
+++ b/hw/arm/sbsa-ref.c
38
@@ -XXX,XX +XXX,XX @@
20
@@ -XXX,XX +XXX,XX @@
39
# define TARGET_PAGE_BITS_MIN 10
21
#include "exec/hwaddr.h"
40
#endif
22
#include "kvm_arm.h"
41
23
#include "hw/arm/boot.h"
42
-#define NB_MMU_MODES 12
24
+#include "hw/arm/fdt.h"
43
+#define NB_MMU_MODES 11
25
#include "hw/arm/smmuv3.h"
44
26
#include "hw/block/flash.h"
45
#endif
27
#include "hw/boards.h"
46
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
28
@@ -XXX,XX +XXX,XX @@ static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx)
47
index XXXXXXX..XXXXXXX 100644
29
return arm_cpu_mp_affinity(idx, clustersz);
48
--- a/target/arm/cpu.h
49
+++ b/target/arm/cpu.h
50
@@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
51
* handling via the TLB. The only way to do a stage 1 translation without
52
* the immediate stage 2 translation is via the ATS or AT system insns,
53
* which can be slow-pathed and always do a page table walk.
54
+ * The only use of stage 2 translations is either as part of an s1+2
55
+ * lookup or when loading the descriptors during a stage 1 page table walk,
56
+ * and in both those cases we don't use the TLB.
57
* 4. we can also safely fold together the "32 bit EL3" and "64 bit EL3"
58
* translation regimes, because they map reasonably well to each other
59
* and they can't both be active at the same time.
60
@@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
61
* NS EL1 EL1&0 stage 1+2 (aka NS PL1)
62
* NS EL1 EL1&0 stage 1+2 +PAN
63
* NS EL0 EL2&0
64
+ * NS EL2 EL2&0
65
* NS EL2 EL2&0 +PAN
66
* NS EL2 (aka NS PL2)
67
* S EL0 EL1&0 (aka S PL0)
68
* S EL1 EL1&0 (not used if EL3 is 32 bit)
69
* S EL1 EL1&0 +PAN
70
* S EL3 (aka S PL1)
71
- * NS EL1&0 stage 2
72
*
73
- * for a total of 12 different mmu_idx.
74
+ * for a total of 11 different mmu_idx.
75
*
76
* R profile CPUs have an MPU, but can use the same set of MMU indexes
77
* as A profile. They only need to distinguish NS EL0 and NS EL1 (and
78
@@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync);
79
* are not quite the same -- different CPU types (most notably M profile
80
* vs A/R profile) would like to use MMU indexes with different semantics,
81
* but since we don't ever need to use all of those in a single CPU we
82
- * can avoid setting NB_MMU_MODES to more than 8. The lower bits of
83
+ * can avoid having to set NB_MMU_MODES to "total number of A profile MMU
84
+ * modes + total number of M profile MMU modes". The lower bits of
85
* ARMMMUIdx are the core TLB mmu index, and the higher bits are always
86
* the same for any particular CPU.
87
* Variables of type ARMMUIdx are always full values, and the core
88
@@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx {
89
ARMMMUIdx_SE10_1_PAN = 9 | ARM_MMU_IDX_A,
90
ARMMMUIdx_SE3 = 10 | ARM_MMU_IDX_A,
91
92
- ARMMMUIdx_Stage2 = 11 | ARM_MMU_IDX_A,
93
-
94
/*
95
* These are not allocated TLBs and are used only for AT system
96
* instructions or for the first stage of an S12 page table walk.
97
@@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdx {
98
ARMMMUIdx_Stage1_E0 = 0 | ARM_MMU_IDX_NOTLB,
99
ARMMMUIdx_Stage1_E1 = 1 | ARM_MMU_IDX_NOTLB,
100
ARMMMUIdx_Stage1_E1_PAN = 2 | ARM_MMU_IDX_NOTLB,
101
+ /*
102
+ * Not allocated a TLB: used only for second stage of an S12 page
103
+ * table walk, or for descriptor loads during first stage of an S1
104
+ * page table walk. Note that if we ever want to have a TLB for this
105
+ * then various TLB flush insns which currently are no-ops or flush
106
+ * only stage 1 MMU indexes will need to change to flush stage 2.
107
+ */
108
+ ARMMMUIdx_Stage2 = 3 | ARM_MMU_IDX_NOTLB,
109
110
/*
111
* M-profile.
112
@@ -XXX,XX +XXX,XX @@ typedef enum ARMMMUIdxBit {
113
TO_CORE_BIT(SE10_1),
114
TO_CORE_BIT(SE10_1_PAN),
115
TO_CORE_BIT(SE3),
116
- TO_CORE_BIT(Stage2),
117
118
TO_CORE_BIT(MUser),
119
TO_CORE_BIT(MPriv),
120
diff --git a/target/arm/helper.c b/target/arm/helper.c
121
index XXXXXXX..XXXXXXX 100644
122
--- a/target/arm/helper.c
123
+++ b/target/arm/helper.c
124
@@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri,
125
tlb_flush_by_mmuidx(cs,
126
ARMMMUIdxBit_E10_1 |
127
ARMMMUIdxBit_E10_1_PAN |
128
- ARMMMUIdxBit_E10_0 |
129
- ARMMMUIdxBit_Stage2);
130
+ ARMMMUIdxBit_E10_0);
131
}
30
}
132
31
133
static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
32
+static void sbsa_fdt_add_gic_node(SBSAMachineState *sms)
134
@@ -XXX,XX +XXX,XX @@ static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
33
+{
135
tlb_flush_by_mmuidx_all_cpus_synced(cs,
34
+ char *nodename;
136
ARMMMUIdxBit_E10_1 |
35
+
137
ARMMMUIdxBit_E10_1_PAN |
36
+ nodename = g_strdup_printf("/intc");
138
- ARMMMUIdxBit_E10_0 |
37
+ qemu_fdt_add_subnode(sms->fdt, nodename);
139
- ARMMMUIdxBit_Stage2);
38
+ qemu_fdt_setprop_sized_cells(sms->fdt, nodename, "reg",
140
+ ARMMMUIdxBit_E10_0);
39
+ 2, sbsa_ref_memmap[SBSA_GIC_DIST].base,
40
+ 2, sbsa_ref_memmap[SBSA_GIC_DIST].size,
41
+ 2, sbsa_ref_memmap[SBSA_GIC_REDIST].base,
42
+ 2, sbsa_ref_memmap[SBSA_GIC_REDIST].size);
43
+
44
+ g_free(nodename);
45
+}
46
/*
47
* Firmware on this machine only uses ACPI table to load OS, these limited
48
* device tree nodes are just to let firmware know the info which varies from
49
@@ -XXX,XX +XXX,XX @@ static void create_fdt(SBSAMachineState *sms)
50
* fw compatibility.
51
*/
52
qemu_fdt_setprop_cell(fdt, "/", "machine-version-major", 0);
53
- qemu_fdt_setprop_cell(fdt, "/", "machine-version-minor", 0);
54
+ qemu_fdt_setprop_cell(fdt, "/", "machine-version-minor", 1);
55
56
if (ms->numa_state->have_numa_distance) {
57
int size = nb_numa_nodes * nb_numa_nodes * 3 * sizeof(uint32_t);
58
@@ -XXX,XX +XXX,XX @@ static void create_fdt(SBSAMachineState *sms)
59
60
g_free(nodename);
61
}
62
+
63
+ sbsa_fdt_add_gic_node(sms);
141
}
64
}
142
65
143
-static void tlbiipas2_write(CPUARMState *env, const ARMCPRegInfo *ri,
66
#define SBSA_FLASH_SECTOR_SIZE (256 * KiB)
144
- uint64_t value)
145
-{
146
- /* Invalidate by IPA. This has to invalidate any structures that
147
- * contain only stage 2 translation information, but does not need
148
- * to apply to structures that contain combined stage 1 and stage 2
149
- * translation information.
150
- * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero.
151
- */
152
- CPUState *cs = env_cpu(env);
153
- uint64_t pageaddr;
154
-
155
- if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
156
- return;
157
- }
158
-
159
- pageaddr = sextract64(value << 12, 0, 40);
160
-
161
- tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2);
162
-}
163
-
164
-static void tlbiipas2_is_write(CPUARMState *env, const ARMCPRegInfo *ri,
165
- uint64_t value)
166
-{
167
- CPUState *cs = env_cpu(env);
168
- uint64_t pageaddr;
169
-
170
- if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
171
- return;
172
- }
173
-
174
- pageaddr = sextract64(value << 12, 0, 40);
175
-
176
- tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
177
- ARMMMUIdxBit_Stage2);
178
-}
179
180
static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri,
181
uint64_t value)
182
@@ -XXX,XX +XXX,XX @@ static void vttbr_write(CPUARMState *env, const ARMCPRegInfo *ri,
183
tlb_flush_by_mmuidx(cs,
184
ARMMMUIdxBit_E10_1 |
185
ARMMMUIdxBit_E10_1_PAN |
186
- ARMMMUIdxBit_E10_0 |
187
- ARMMMUIdxBit_Stage2);
188
+ ARMMMUIdxBit_E10_0);
189
raw_write(env, ri, value);
190
}
191
}
192
@@ -XXX,XX +XXX,XX @@ static int alle1_tlbmask(CPUARMState *env)
193
return ARMMMUIdxBit_SE10_1 |
194
ARMMMUIdxBit_SE10_1_PAN |
195
ARMMMUIdxBit_SE10_0;
196
- } else if (arm_feature(env, ARM_FEATURE_EL2)) {
197
- return ARMMMUIdxBit_E10_1 |
198
- ARMMMUIdxBit_E10_1_PAN |
199
- ARMMMUIdxBit_E10_0 |
200
- ARMMMUIdxBit_Stage2;
201
} else {
202
return ARMMMUIdxBit_E10_1 |
203
ARMMMUIdxBit_E10_1_PAN |
204
@@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri,
205
ARMMMUIdxBit_SE3);
206
}
207
208
-static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri,
209
- uint64_t value)
210
-{
211
- /* Invalidate by IPA. This has to invalidate any structures that
212
- * contain only stage 2 translation information, but does not need
213
- * to apply to structures that contain combined stage 1 and stage 2
214
- * translation information.
215
- * This must NOP if EL2 isn't implemented or SCR_EL3.NS is zero.
216
- */
217
- ARMCPU *cpu = env_archcpu(env);
218
- CPUState *cs = CPU(cpu);
219
- uint64_t pageaddr;
220
-
221
- if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
222
- return;
223
- }
224
-
225
- pageaddr = sextract64(value << 12, 0, 48);
226
-
227
- tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2);
228
-}
229
-
230
-static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri,
231
- uint64_t value)
232
-{
233
- CPUState *cs = env_cpu(env);
234
- uint64_t pageaddr;
235
-
236
- if (!arm_feature(env, ARM_FEATURE_EL2) || !(env->cp15.scr_el3 & SCR_NS)) {
237
- return;
238
- }
239
-
240
- pageaddr = sextract64(value << 12, 0, 48);
241
-
242
- tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr,
243
- ARMMMUIdxBit_Stage2);
244
-}
245
-
246
static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri,
247
bool isread)
248
{
249
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = {
250
.writefn = tlbi_aa64_vae1_write },
251
{ .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64,
252
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1,
253
- .access = PL2_W, .type = ARM_CP_NO_RAW,
254
- .writefn = tlbi_aa64_ipas2e1is_write },
255
+ .access = PL2_W, .type = ARM_CP_NOP },
256
{ .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64,
257
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5,
258
- .access = PL2_W, .type = ARM_CP_NO_RAW,
259
- .writefn = tlbi_aa64_ipas2e1is_write },
260
+ .access = PL2_W, .type = ARM_CP_NOP },
261
{ .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64,
262
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4,
263
.access = PL2_W, .type = ARM_CP_NO_RAW,
264
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = {
265
.writefn = tlbi_aa64_alle1is_write },
266
{ .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64,
267
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1,
268
- .access = PL2_W, .type = ARM_CP_NO_RAW,
269
- .writefn = tlbi_aa64_ipas2e1_write },
270
+ .access = PL2_W, .type = ARM_CP_NOP },
271
{ .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64,
272
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5,
273
- .access = PL2_W, .type = ARM_CP_NO_RAW,
274
- .writefn = tlbi_aa64_ipas2e1_write },
275
+ .access = PL2_W, .type = ARM_CP_NOP },
276
{ .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64,
277
.opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4,
278
.access = PL2_W, .type = ARM_CP_NO_RAW,
279
@@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v8_cp_reginfo[] = {
280
.writefn = tlbimva_hyp_is_write },
281
{ .name = "TLBIIPAS2",
282
.cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1,
283
- .type = ARM_CP_NO_RAW, .access = PL2_W,
284
- .writefn = tlbiipas2_write },
285
+ .type = ARM_CP_NOP, .access = PL2_W },
286
{ .name = "TLBIIPAS2IS",
287
.cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1,
288
- .type = ARM_CP_NO_RAW, .access = PL2_W,
289
- .writefn = tlbiipas2_is_write },
290
+ .type = ARM_CP_NOP, .access = PL2_W },
291
{ .name = "TLBIIPAS2L",
292
.cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5,
293
- .type = ARM_CP_NO_RAW, .access = PL2_W,
294
- .writefn = tlbiipas2_write },
295
+ .type = ARM_CP_NOP, .access = PL2_W },
296
{ .name = "TLBIIPAS2LIS",
297
.cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5,
298
- .type = ARM_CP_NO_RAW, .access = PL2_W,
299
- .writefn = tlbiipas2_is_write },
300
+ .type = ARM_CP_NOP, .access = PL2_W },
301
/* 32 bit cache operations */
302
{ .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0,
303
.type = ARM_CP_NOP, .access = PL1_W, .accessfn = aa64_cacheop_pou_access },
304
--
67
--
305
2.20.1
68
2.34.1
306
307
diff view generated by jsdifflib
1
From: Fredrik Strupe <fredrik@strupe.net>
1
From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
2
2
3
According to Arm ARM, VQDMULL is only valid when U=0, while having
3
We moved from VGA to Bochs to have PCIe card.
4
U=1 is unallocated.
5
4
6
Signed-off-by: Fredrik Strupe <fredrik@strupe.net>
5
Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org>
7
Fixes: 695272dcb976 ("target-arm: Handle UNDEF cases for Neon 3-regs-different-widths")
8
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
9
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
7
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
10
---
8
---
11
target/arm/translate.c | 2 +-
9
docs/system/arm/sbsa.rst | 2 +-
12
1 file changed, 1 insertion(+), 1 deletion(-)
10
1 file changed, 1 insertion(+), 1 deletion(-)
13
11
14
diff --git a/target/arm/translate.c b/target/arm/translate.c
12
diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst
15
index XXXXXXX..XXXXXXX 100644
13
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/translate.c
14
--- a/docs/system/arm/sbsa.rst
17
+++ b/target/arm/translate.c
15
+++ b/docs/system/arm/sbsa.rst
18
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
16
@@ -XXX,XX +XXX,XX @@ The sbsa-ref board supports:
19
{0, 0, 0, 0}, /* VMLSL */
17
- System bus EHCI controller
20
{0, 0, 0, 9}, /* VQDMLSL */
18
- CDROM and hard disc on AHCI bus
21
{0, 0, 0, 0}, /* Integer VMULL */
19
- E1000E ethernet card on PCIe bus
22
- {0, 0, 0, 1}, /* VQDMULL */
20
- - VGA display adaptor on PCIe bus
23
+ {0, 0, 0, 9}, /* VQDMULL */
21
+ - Bochs display adapter on PCIe bus
24
{0, 0, 0, 0xa}, /* Polynomial VMULL */
22
- A generic SBSA watchdog device
25
{0, 0, 0, 7}, /* Reserved: always UNDEF */
23
26
};
27
--
24
--
28
2.20.1
25
2.34.1
29
30
diff view generated by jsdifflib
Deleted patch
1
The access_type argument to get_phys_addr_lpae() is an MMUAccessType;
2
use the enum constant MMU_DATA_LOAD rather than a literal 0 when we
3
call it in S1_ptw_translate().
4
1
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
7
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
8
Message-id: 20200330210400.11724-3-peter.maydell@linaro.org
9
---
10
target/arm/helper.c | 5 +++--
11
1 file changed, 3 insertions(+), 2 deletions(-)
12
13
diff --git a/target/arm/helper.c b/target/arm/helper.c
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/helper.c
16
+++ b/target/arm/helper.c
17
@@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
18
pcacheattrs = &cacheattrs;
19
}
20
21
- ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_Stage2, &s2pa,
22
- &txattrs, &s2prot, &s2size, fi, pcacheattrs);
23
+ ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2,
24
+ &s2pa, &txattrs, &s2prot, &s2size, fi,
25
+ pcacheattrs);
26
if (ret) {
27
assert(fi->type != ARMFault_None);
28
fi->s2addr = addr;
29
--
30
2.20.1
31
32
diff view generated by jsdifflib
Deleted patch
1
For ARMv8.2-TTS2UXN, the stage 2 page table walk wants to know
2
whether the stage 1 access is for EL0 or not, because whether
3
exec permission is given can depend on whether this is an EL0
4
or EL1 access. Add a new argument to get_phys_addr_lpae() so
5
the call sites can pass this information in.
6
1
7
Since get_phys_addr_lpae() doesn't already have a doc comment,
8
add one so we have a place to put the documentation of the
9
semantics of the new s1_is_el0 argument.
10
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
13
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
14
Message-id: 20200330210400.11724-4-peter.maydell@linaro.org
15
---
16
target/arm/helper.c | 29 ++++++++++++++++++++++++++++-
17
1 file changed, 28 insertions(+), 1 deletion(-)
18
19
diff --git a/target/arm/helper.c b/target/arm/helper.c
20
index XXXXXXX..XXXXXXX 100644
21
--- a/target/arm/helper.c
22
+++ b/target/arm/helper.c
23
@@ -XXX,XX +XXX,XX @@
24
25
static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
26
MMUAccessType access_type, ARMMMUIdx mmu_idx,
27
+ bool s1_is_el0,
28
hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot,
29
target_ulong *page_size_ptr,
30
ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs);
31
@@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx,
32
}
33
34
ret = get_phys_addr_lpae(env, addr, MMU_DATA_LOAD, ARMMMUIdx_Stage2,
35
+ false,
36
&s2pa, &txattrs, &s2prot, &s2size, fi,
37
pcacheattrs);
38
if (ret) {
39
@@ -XXX,XX +XXX,XX @@ static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va,
40
};
41
}
42
43
+/**
44
+ * get_phys_addr_lpae: perform one stage of page table walk, LPAE format
45
+ *
46
+ * Returns false if the translation was successful. Otherwise, phys_ptr, attrs,
47
+ * prot and page_size may not be filled in, and the populated fsr value provides
48
+ * information on why the translation aborted, in the format of a long-format
49
+ * DFSR/IFSR fault register, with the following caveats:
50
+ * * the WnR bit is never set (the caller must do this).
51
+ *
52
+ * @env: CPUARMState
53
+ * @address: virtual address to get physical address for
54
+ * @access_type: MMU_DATA_LOAD, MMU_DATA_STORE or MMU_INST_FETCH
55
+ * @mmu_idx: MMU index indicating required translation regime
56
+ * @s1_is_el0: if @mmu_idx is ARMMMUIdx_Stage2 (so this is a stage 2 page table
57
+ * walk), must be true if this is stage 2 of a stage 1+2 walk for an
58
+ * EL0 access). If @mmu_idx is anything else, @s1_is_el0 is ignored.
59
+ * @phys_ptr: set to the physical address corresponding to the virtual address
60
+ * @attrs: set to the memory transaction attributes to use
61
+ * @prot: set to the permissions for the page containing phys_ptr
62
+ * @page_size_ptr: set to the size of the page containing phys_ptr
63
+ * @fi: set to fault info if the translation fails
64
+ * @cacheattrs: (if non-NULL) set to the cacheability/shareability attributes
65
+ */
66
static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address,
67
MMUAccessType access_type, ARMMMUIdx mmu_idx,
68
+ bool s1_is_el0,
69
hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot,
70
target_ulong *page_size_ptr,
71
ARMMMUFaultInfo *fi, ARMCacheAttrs *cacheattrs)
72
@@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
73
74
/* S1 is done. Now do S2 translation. */
75
ret = get_phys_addr_lpae(env, ipa, access_type, ARMMMUIdx_Stage2,
76
+ mmu_idx == ARMMMUIdx_E10_0,
77
phys_ptr, attrs, &s2_prot,
78
page_size, fi,
79
cacheattrs != NULL ? &cacheattrs2 : NULL);
80
@@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address,
81
}
82
83
if (regime_using_lpae_format(env, mmu_idx)) {
84
- return get_phys_addr_lpae(env, address, access_type, mmu_idx,
85
+ return get_phys_addr_lpae(env, address, access_type, mmu_idx, false,
86
phys_ptr, attrs, prot, page_size,
87
fi, cacheattrs);
88
} else if (regime_sctlr(env, mmu_idx) & SCTLR_XP) {
89
--
90
2.20.1
91
92
diff view generated by jsdifflib
Deleted patch
1
In aarch64_max_initfn() we update both 32-bit and 64-bit ID
2
registers. The intended pattern is that for 64-bit ID registers we
3
use FIELD_DP64 and the uint64_t 't' register, while 32-bit ID
4
registers use FIELD_DP32 and the uint32_t 'u' register. For
5
ID_AA64DFR0 we accidentally used 'u', meaning that the top 32 bits of
6
this 64-bit ID register would end up always zero. Luckily at the
7
moment that's what they should be anyway, so this bug has no visible
8
effects.
9
1
10
Use the right-sized variable.
11
12
Fixes: 3bec78447a958d481991
13
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
14
Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com>
15
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
16
Message-id: 20200423110915.10527-1-peter.maydell@linaro.org
17
---
18
target/arm/cpu64.c | 6 +++---
19
1 file changed, 3 insertions(+), 3 deletions(-)
20
21
diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c
22
index XXXXXXX..XXXXXXX 100644
23
--- a/target/arm/cpu64.c
24
+++ b/target/arm/cpu64.c
25
@@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj)
26
u = FIELD_DP32(u, ID_MMFR4, XNX, 1); /* TTS2UXN */
27
cpu->isar.id_mmfr4 = u;
28
29
- u = cpu->isar.id_aa64dfr0;
30
- u = FIELD_DP64(u, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */
31
- cpu->isar.id_aa64dfr0 = u;
32
+ t = cpu->isar.id_aa64dfr0;
33
+ t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* v8.4-PMU */
34
+ cpu->isar.id_aa64dfr0 = t;
35
36
u = cpu->isar.id_dfr0;
37
u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */
38
--
39
2.20.1
40
41
diff view generated by jsdifflib
Deleted patch
1
From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com>
2
1
3
Embed the APUs into the SoC type.
4
5
Suggested-by: Peter Maydell <peter.maydell@linaro.org>
6
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
7
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
8
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
9
Reviewed-by: Luc Michel <luc.michel@greensocs.com>
10
Message-id: 20200427181649.26851-8-edgar.iglesias@gmail.com
11
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
12
---
13
include/hw/arm/xlnx-versal.h | 2 +-
14
hw/arm/xlnx-versal-virt.c | 4 ++--
15
hw/arm/xlnx-versal.c | 19 +++++--------------
16
3 files changed, 8 insertions(+), 17 deletions(-)
17
18
diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h
19
index XXXXXXX..XXXXXXX 100644
20
--- a/include/hw/arm/xlnx-versal.h
21
+++ b/include/hw/arm/xlnx-versal.h
22
@@ -XXX,XX +XXX,XX @@ typedef struct Versal {
23
struct {
24
struct {
25
MemoryRegion mr;
26
- ARMCPU *cpu[XLNX_VERSAL_NR_ACPUS];
27
+ ARMCPU cpu[XLNX_VERSAL_NR_ACPUS];
28
GICv3State gic;
29
} apu;
30
} fpd;
31
diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c
32
index XXXXXXX..XXXXXXX 100644
33
--- a/hw/arm/xlnx-versal-virt.c
34
+++ b/hw/arm/xlnx-versal-virt.c
35
@@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine)
36
s->binfo.get_dtb = versal_virt_get_dtb;
37
s->binfo.modify_dtb = versal_virt_modify_dtb;
38
if (machine->kernel_filename) {
39
- arm_load_kernel(s->soc.fpd.apu.cpu[0], machine, &s->binfo);
40
+ arm_load_kernel(&s->soc.fpd.apu.cpu[0], machine, &s->binfo);
41
} else {
42
- AddressSpace *as = arm_boot_address_space(s->soc.fpd.apu.cpu[0],
43
+ AddressSpace *as = arm_boot_address_space(&s->soc.fpd.apu.cpu[0],
44
&s->binfo);
45
/* Some boot-loaders (e.g u-boot) don't like blobs at address 0 (NULL).
46
* Offset things by 4K. */
47
diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c
48
index XXXXXXX..XXXXXXX 100644
49
--- a/hw/arm/xlnx-versal.c
50
+++ b/hw/arm/xlnx-versal.c
51
@@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s)
52
53
for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) {
54
Object *obj;
55
- char *name;
56
-
57
- obj = object_new(XLNX_VERSAL_ACPU_TYPE);
58
- if (!obj) {
59
- error_report("Unable to create apu.cpu[%d] of type %s",
60
- i, XLNX_VERSAL_ACPU_TYPE);
61
- exit(EXIT_FAILURE);
62
- }
63
-
64
- name = g_strdup_printf("apu-cpu[%d]", i);
65
- object_property_add_child(OBJECT(s), name, obj, &error_fatal);
66
- g_free(name);
67
68
+ object_initialize_child(OBJECT(s), "apu-cpu[*]",
69
+ &s->fpd.apu.cpu[i], sizeof(s->fpd.apu.cpu[i]),
70
+ XLNX_VERSAL_ACPU_TYPE, &error_abort, NULL);
71
+ obj = OBJECT(&s->fpd.apu.cpu[i]);
72
object_property_set_int(obj, s->cfg.psci_conduit,
73
"psci-conduit", &error_abort);
74
if (i) {
75
@@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s)
76
object_property_set_link(obj, OBJECT(&s->fpd.apu.mr), "memory",
77
&error_abort);
78
object_property_set_bool(obj, true, "realized", &error_fatal);
79
- s->fpd.apu.cpu[i] = ARM_CPU(obj);
80
}
81
}
82
83
@@ -XXX,XX +XXX,XX @@ static void versal_create_apu_gic(Versal *s, qemu_irq *pic)
84
}
85
86
for (i = 0; i < nr_apu_cpus; i++) {
87
- DeviceState *cpudev = DEVICE(s->fpd.apu.cpu[i]);
88
+ DeviceState *cpudev = DEVICE(&s->fpd.apu.cpu[i]);
89
int ppibase = XLNX_VERSAL_NR_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS;
90
qemu_irq maint_irq;
91
int ti;
92
--
93
2.20.1
94
95
diff view generated by jsdifflib
Deleted patch
1
We were accidentally permitting decode of Thumb Neon insns even if
2
the CPU didn't have the FEATURE_NEON bit set, because the feature
3
check was being done before the call to disas_neon_data_insn() and
4
disas_neon_ls_insn() in the Arm decoder but was omitted from the
5
Thumb decoder. Push the feature bit check down into the called
6
functions so it is done for both Arm and Thumb encodings.
7
1
8
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
9
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
10
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
11
Message-id: 20200430181003.21682-3-peter.maydell@linaro.org
12
---
13
target/arm/translate.c | 16 ++++++++--------
14
1 file changed, 8 insertions(+), 8 deletions(-)
15
16
diff --git a/target/arm/translate.c b/target/arm/translate.c
17
index XXXXXXX..XXXXXXX 100644
18
--- a/target/arm/translate.c
19
+++ b/target/arm/translate.c
20
@@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
21
TCGv_i32 tmp2;
22
TCGv_i64 tmp64;
23
24
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
25
+ return 1;
26
+ }
27
+
28
/* FIXME: this access check should not take precedence over UNDEF
29
* for invalid encodings; we will generate incorrect syndrome information
30
* for attempts to execute invalid vfp/neon encodings with FP disabled.
31
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
32
TCGv_ptr ptr1, ptr2, ptr3;
33
TCGv_i64 tmp64;
34
35
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
36
+ return 1;
37
+ }
38
+
39
/* FIXME: this access check should not take precedence over UNDEF
40
* for invalid encodings; we will generate incorrect syndrome information
41
* for attempts to execute invalid vfp/neon encodings with FP disabled.
42
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
43
44
if (((insn >> 25) & 7) == 1) {
45
/* NEON Data processing. */
46
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
47
- goto illegal_op;
48
- }
49
-
50
if (disas_neon_data_insn(s, insn)) {
51
goto illegal_op;
52
}
53
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
54
}
55
if ((insn & 0x0f100000) == 0x04000000) {
56
/* NEON load/store. */
57
- if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
58
- goto illegal_op;
59
- }
60
-
61
if (disas_neon_ls_insn(s, insn)) {
62
goto illegal_op;
63
}
64
--
65
2.20.1
66
67
diff view generated by jsdifflib
Deleted patch
1
Add the infrastructure for building and invoking a decodetree decoder
2
for the AArch32 Neon encodings. At the moment the new decoder covers
3
nothing, so we always fall back to the existing hand-written decode.
4
1
5
We follow the same pattern we did for the VFP decodetree conversion
6
(commit 78e138bc1f672c145ef6ace74617d and following): code that deals
7
with Neon will be moving gradually out to translate-neon.vfp.inc,
8
which we #include into translate.c.
9
10
In order to share the decode files between A32 and T32, we
11
split Neon into 3 parts:
12
* data-processing
13
* load-store
14
* 'shared' encodings
15
16
The first two groups of instructions have similar but not identical
17
A32 and T32 encodings, so we need to manually transform the T32
18
encoding into the A32 one before calling the decoder; the third group
19
covers the Neon instructions which are identical in A32 and T32.
20
21
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
22
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
23
Message-id: 20200430181003.21682-4-peter.maydell@linaro.org
24
---
25
target/arm/neon-dp.decode | 29 ++++++++++++++++++++++++++
26
target/arm/neon-ls.decode | 29 ++++++++++++++++++++++++++
27
target/arm/neon-shared.decode | 27 +++++++++++++++++++++++++
28
target/arm/translate-neon.inc.c | 32 +++++++++++++++++++++++++++++
29
target/arm/translate.c | 36 +++++++++++++++++++++++++++++++--
30
target/arm/Makefile.objs | 18 +++++++++++++++++
31
6 files changed, 169 insertions(+), 2 deletions(-)
32
create mode 100644 target/arm/neon-dp.decode
33
create mode 100644 target/arm/neon-ls.decode
34
create mode 100644 target/arm/neon-shared.decode
35
create mode 100644 target/arm/translate-neon.inc.c
36
37
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
38
new file mode 100644
39
index XXXXXXX..XXXXXXX
40
--- /dev/null
41
+++ b/target/arm/neon-dp.decode
42
@@ -XXX,XX +XXX,XX @@
43
+# AArch32 Neon data-processing instruction descriptions
44
+#
45
+# Copyright (c) 2020 Linaro, Ltd
46
+#
47
+# This library is free software; you can redistribute it and/or
48
+# modify it under the terms of the GNU Lesser General Public
49
+# License as published by the Free Software Foundation; either
50
+# version 2 of the License, or (at your option) any later version.
51
+#
52
+# This library is distributed in the hope that it will be useful,
53
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
54
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
55
+# Lesser General Public License for more details.
56
+#
57
+# You should have received a copy of the GNU Lesser General Public
58
+# License along with this library; if not, see <http://www.gnu.org/licenses/>.
59
+
60
+#
61
+# This file is processed by scripts/decodetree.py
62
+#
63
+
64
+# Encodings for Neon data processing instructions where the T32 encoding
65
+# is a simple transformation of the A32 encoding.
66
+# More specifically, this file covers instructions where the A32 encoding is
67
+# 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
68
+# and the T32 encoding is
69
+# 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
70
+# This file works on the A32 encoding only; calling code for T32 has to
71
+# transform the insn into the A32 version first.
72
diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode
73
new file mode 100644
74
index XXXXXXX..XXXXXXX
75
--- /dev/null
76
+++ b/target/arm/neon-ls.decode
77
@@ -XXX,XX +XXX,XX @@
78
+# AArch32 Neon load/store instruction descriptions
79
+#
80
+# Copyright (c) 2020 Linaro, Ltd
81
+#
82
+# This library is free software; you can redistribute it and/or
83
+# modify it under the terms of the GNU Lesser General Public
84
+# License as published by the Free Software Foundation; either
85
+# version 2 of the License, or (at your option) any later version.
86
+#
87
+# This library is distributed in the hope that it will be useful,
88
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
89
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
90
+# Lesser General Public License for more details.
91
+#
92
+# You should have received a copy of the GNU Lesser General Public
93
+# License along with this library; if not, see <http://www.gnu.org/licenses/>.
94
+
95
+#
96
+# This file is processed by scripts/decodetree.py
97
+#
98
+
99
+# Encodings for Neon load/store instructions where the T32 encoding
100
+# is a simple transformation of the A32 encoding.
101
+# More specifically, this file covers instructions where the A32 encoding is
102
+# 0b1111_0100_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx
103
+# and the T32 encoding is
104
+# 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx
105
+# This file works on the A32 encoding only; calling code for T32 has to
106
+# transform the insn into the A32 version first.
107
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
108
new file mode 100644
109
index XXXXXXX..XXXXXXX
110
--- /dev/null
111
+++ b/target/arm/neon-shared.decode
112
@@ -XXX,XX +XXX,XX @@
113
+# AArch32 Neon instruction descriptions
114
+#
115
+# Copyright (c) 2020 Linaro, Ltd
116
+#
117
+# This library is free software; you can redistribute it and/or
118
+# modify it under the terms of the GNU Lesser General Public
119
+# License as published by the Free Software Foundation; either
120
+# version 2 of the License, or (at your option) any later version.
121
+#
122
+# This library is distributed in the hope that it will be useful,
123
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
124
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
125
+# Lesser General Public License for more details.
126
+#
127
+# You should have received a copy of the GNU Lesser General Public
128
+# License along with this library; if not, see <http://www.gnu.org/licenses/>.
129
+
130
+#
131
+# This file is processed by scripts/decodetree.py
132
+#
133
+
134
+# Encodings for Neon instructions whose encoding is the same for
135
+# both A32 and T32.
136
+
137
+# More specifically, this covers:
138
+# 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx
139
+# 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx
140
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
141
new file mode 100644
142
index XXXXXXX..XXXXXXX
143
--- /dev/null
144
+++ b/target/arm/translate-neon.inc.c
145
@@ -XXX,XX +XXX,XX @@
146
+/*
147
+ * ARM translation: AArch32 Neon instructions
148
+ *
149
+ * Copyright (c) 2003 Fabrice Bellard
150
+ * Copyright (c) 2005-2007 CodeSourcery
151
+ * Copyright (c) 2007 OpenedHand, Ltd.
152
+ * Copyright (c) 2020 Linaro, Ltd.
153
+ *
154
+ * This library is free software; you can redistribute it and/or
155
+ * modify it under the terms of the GNU Lesser General Public
156
+ * License as published by the Free Software Foundation; either
157
+ * version 2 of the License, or (at your option) any later version.
158
+ *
159
+ * This library is distributed in the hope that it will be useful,
160
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
161
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
162
+ * Lesser General Public License for more details.
163
+ *
164
+ * You should have received a copy of the GNU Lesser General Public
165
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
166
+ */
167
+
168
+/*
169
+ * This file is intended to be included from translate.c; it uses
170
+ * some macros and definitions provided by that file.
171
+ * It might be possible to convert it to a standalone .c file eventually.
172
+ */
173
+
174
+/* Include the generated Neon decoder */
175
+#include "decode-neon-dp.inc.c"
176
+#include "decode-neon-ls.inc.c"
177
+#include "decode-neon-shared.inc.c"
178
diff --git a/target/arm/translate.c b/target/arm/translate.c
179
index XXXXXXX..XXXXXXX 100644
180
--- a/target/arm/translate.c
181
+++ b/target/arm/translate.c
182
@@ -XXX,XX +XXX,XX @@ static TCGv_ptr vfp_reg_ptr(bool dp, int reg)
183
184
#define ARM_CP_RW_BIT (1 << 20)
185
186
-/* Include the VFP decoder */
187
+/* Include the VFP and Neon decoders */
188
#include "translate-vfp.inc.c"
189
+#include "translate-neon.inc.c"
190
191
static inline void iwmmxt_load_reg(TCGv_i64 var, int reg)
192
{
193
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
194
/* Unconditional instructions. */
195
/* TODO: Perhaps merge these into one decodetree output file. */
196
if (disas_a32_uncond(s, insn) ||
197
- disas_vfp_uncond(s, insn)) {
198
+ disas_vfp_uncond(s, insn) ||
199
+ disas_neon_dp(s, insn) ||
200
+ disas_neon_ls(s, insn) ||
201
+ disas_neon_shared(s, insn)) {
202
return;
203
}
204
/* fall back to legacy decoder */
205
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
206
ARCH(6T2);
207
}
208
209
+ if ((insn & 0xef000000) == 0xef000000) {
210
+ /*
211
+ * T32 encodings 0b111p_1111_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
212
+ * transform into
213
+ * A32 encodings 0b1111_001p_qqqq_qqqq_qqqq_qqqq_qqqq_qqqq
214
+ */
215
+ uint32_t a32_insn = (insn & 0xe2ffffff) |
216
+ ((insn & (1 << 28)) >> 4) | (1 << 28);
217
+
218
+ if (disas_neon_dp(s, a32_insn)) {
219
+ return;
220
+ }
221
+ }
222
+
223
+ if ((insn & 0xff100000) == 0xf9000000) {
224
+ /*
225
+ * T32 encodings 0b1111_1001_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq
226
+ * transform into
227
+ * A32 encodings 0b1111_0100_ppp0_qqqq_qqqq_qqqq_qqqq_qqqq
228
+ */
229
+ uint32_t a32_insn = (insn & 0x00ffffff) | 0xf4000000;
230
+
231
+ if (disas_neon_ls(s, a32_insn)) {
232
+ return;
233
+ }
234
+ }
235
+
236
/*
237
* TODO: Perhaps merge these into one decodetree output file.
238
* Note disas_vfp is written for a32 with cond field in the
239
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
240
*/
241
if (disas_t32(s, insn) ||
242
disas_vfp_uncond(s, insn) ||
243
+ disas_neon_shared(s, insn) ||
244
((insn >> 28) == 0xe && disas_vfp(s, insn))) {
245
return;
246
}
247
diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs
248
index XXXXXXX..XXXXXXX 100644
249
--- a/target/arm/Makefile.objs
250
+++ b/target/arm/Makefile.objs
251
@@ -XXX,XX +XXX,XX @@ target/arm/decode-sve.inc.c: $(SRC_PATH)/target/arm/sve.decode $(DECODETREE)
252
     $(PYTHON) $(DECODETREE) --decode disas_sve -o $@ $<,\
253
     "GEN", $(TARGET_DIR)$@)
254
255
+target/arm/decode-neon-shared.inc.c: $(SRC_PATH)/target/arm/neon-shared.decode $(DECODETREE)
256
+    $(call quiet-command,\
257
+     $(PYTHON) $(DECODETREE) --static-decode disas_neon_shared -o $@ $<,\
258
+     "GEN", $(TARGET_DIR)$@)
259
+
260
+target/arm/decode-neon-dp.inc.c: $(SRC_PATH)/target/arm/neon-dp.decode $(DECODETREE)
261
+    $(call quiet-command,\
262
+     $(PYTHON) $(DECODETREE) --static-decode disas_neon_dp -o $@ $<,\
263
+     "GEN", $(TARGET_DIR)$@)
264
+
265
+target/arm/decode-neon-ls.inc.c: $(SRC_PATH)/target/arm/neon-ls.decode $(DECODETREE)
266
+    $(call quiet-command,\
267
+     $(PYTHON) $(DECODETREE) --static-decode disas_neon_ls -o $@ $<,\
268
+     "GEN", $(TARGET_DIR)$@)
269
+
270
target/arm/decode-vfp.inc.c: $(SRC_PATH)/target/arm/vfp.decode $(DECODETREE)
271
    $(call quiet-command,\
272
     $(PYTHON) $(DECODETREE) --static-decode disas_vfp -o $@ $<,\
273
@@ -XXX,XX +XXX,XX @@ target/arm/decode-t16.inc.c: $(SRC_PATH)/target/arm/t16.decode $(DECODETREE)
274
     "GEN", $(TARGET_DIR)$@)
275
276
target/arm/translate-sve.o: target/arm/decode-sve.inc.c
277
+target/arm/translate.o: target/arm/decode-neon-shared.inc.c
278
+target/arm/translate.o: target/arm/decode-neon-dp.inc.c
279
+target/arm/translate.o: target/arm/decode-neon-ls.inc.c
280
target/arm/translate.o: target/arm/decode-vfp.inc.c
281
target/arm/translate.o: target/arm/decode-vfp-uncond.inc.c
282
target/arm/translate.o: target/arm/decode-a32.inc.c
283
--
284
2.20.1
285
286
diff view generated by jsdifflib
Deleted patch
1
Convert the VCMLA (vector) insns in the 3same extension group to
2
decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-5-peter.maydell@linaro.org
7
---
8
target/arm/neon-shared.decode | 11 ++++++++++
9
target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 11 +---------
11
3 files changed, 49 insertions(+), 10 deletions(-)
12
13
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-shared.decode
16
+++ b/target/arm/neon-shared.decode
17
@@ -XXX,XX +XXX,XX @@
18
# More specifically, this covers:
19
# 2reg scalar ext: 0b1111_1110_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx
20
# 3same ext: 0b1111_110x_xxxx_xxxx_xxxx_1x0x_xxxx_xxxx
21
+
22
+# VFP/Neon register fields; same as vfp.decode
23
+%vm_dp 5:1 0:4
24
+%vm_sp 0:4 5:1
25
+%vn_dp 7:1 16:4
26
+%vn_sp 16:4 7:1
27
+%vd_dp 22:1 12:4
28
+%vd_sp 12:4 22:1
29
+
30
+VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \
31
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp
32
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
33
index XXXXXXX..XXXXXXX 100644
34
--- a/target/arm/translate-neon.inc.c
35
+++ b/target/arm/translate-neon.inc.c
36
@@ -XXX,XX +XXX,XX @@
37
#include "decode-neon-dp.inc.c"
38
#include "decode-neon-ls.inc.c"
39
#include "decode-neon-shared.inc.c"
40
+
41
+static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
42
+{
43
+ int opr_sz;
44
+ TCGv_ptr fpst;
45
+ gen_helper_gvec_3_ptr *fn_gvec_ptr;
46
+
47
+ if (!dc_isar_feature(aa32_vcma, s)
48
+ || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) {
49
+ return false;
50
+ }
51
+
52
+ /* UNDEF accesses to D16-D31 if they don't exist. */
53
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
54
+ ((a->vd | a->vn | a->vm) & 0x10)) {
55
+ return false;
56
+ }
57
+
58
+ if ((a->vn | a->vm | a->vd) & a->q) {
59
+ return false;
60
+ }
61
+
62
+ if (!vfp_access_check(s)) {
63
+ return true;
64
+ }
65
+
66
+ opr_sz = (1 + a->q) * 8;
67
+ fpst = get_fpstatus_ptr(1);
68
+ fn_gvec_ptr = a->size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah;
69
+ tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
70
+ vfp_reg_offset(1, a->vn),
71
+ vfp_reg_offset(1, a->vm),
72
+ fpst, opr_sz, opr_sz, a->rot,
73
+ fn_gvec_ptr);
74
+ tcg_temp_free_ptr(fpst);
75
+ return true;
76
+}
77
diff --git a/target/arm/translate.c b/target/arm/translate.c
78
index XXXXXXX..XXXXXXX 100644
79
--- a/target/arm/translate.c
80
+++ b/target/arm/translate.c
81
@@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn)
82
bool is_long = false, q = extract32(insn, 6, 1);
83
bool ptr_is_env = false;
84
85
- if ((insn & 0xfe200f10) == 0xfc200800) {
86
- /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */
87
- int size = extract32(insn, 20, 1);
88
- data = extract32(insn, 23, 2); /* rot */
89
- if (!dc_isar_feature(aa32_vcma, s)
90
- || (!size && !dc_isar_feature(aa32_fp16_arith, s))) {
91
- return 1;
92
- }
93
- fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah;
94
- } else if ((insn & 0xfea00f10) == 0xfc800800) {
95
+ if ((insn & 0xfea00f10) == 0xfc800800) {
96
/* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */
97
int size = extract32(insn, 20, 1);
98
data = extract32(insn, 24, 1); /* rot */
99
--
100
2.20.1
101
102
diff view generated by jsdifflib
Deleted patch
1
Convert the VCADD (vector) insns to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200430181003.21682-6-peter.maydell@linaro.org
6
---
7
target/arm/neon-shared.decode | 3 +++
8
target/arm/translate-neon.inc.c | 37 +++++++++++++++++++++++++++++++++
9
target/arm/translate.c | 11 +---------
10
3 files changed, 41 insertions(+), 10 deletions(-)
11
12
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-shared.decode
15
+++ b/target/arm/neon-shared.decode
16
@@ -XXX,XX +XXX,XX @@
17
18
VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \
19
vm=%vm_dp vn=%vn_dp vd=%vd_dp
20
+
21
+VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \
22
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp
23
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
24
index XXXXXXX..XXXXXXX 100644
25
--- a/target/arm/translate-neon.inc.c
26
+++ b/target/arm/translate-neon.inc.c
27
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
28
tcg_temp_free_ptr(fpst);
29
return true;
30
}
31
+
32
+static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
33
+{
34
+ int opr_sz;
35
+ TCGv_ptr fpst;
36
+ gen_helper_gvec_3_ptr *fn_gvec_ptr;
37
+
38
+ if (!dc_isar_feature(aa32_vcma, s)
39
+ || (!a->size && !dc_isar_feature(aa32_fp16_arith, s))) {
40
+ return false;
41
+ }
42
+
43
+ /* UNDEF accesses to D16-D31 if they don't exist. */
44
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
45
+ ((a->vd | a->vn | a->vm) & 0x10)) {
46
+ return false;
47
+ }
48
+
49
+ if ((a->vn | a->vm | a->vd) & a->q) {
50
+ return false;
51
+ }
52
+
53
+ if (!vfp_access_check(s)) {
54
+ return true;
55
+ }
56
+
57
+ opr_sz = (1 + a->q) * 8;
58
+ fpst = get_fpstatus_ptr(1);
59
+ fn_gvec_ptr = a->size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh;
60
+ tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
61
+ vfp_reg_offset(1, a->vn),
62
+ vfp_reg_offset(1, a->vm),
63
+ fpst, opr_sz, opr_sz, a->rot,
64
+ fn_gvec_ptr);
65
+ tcg_temp_free_ptr(fpst);
66
+ return true;
67
+}
68
diff --git a/target/arm/translate.c b/target/arm/translate.c
69
index XXXXXXX..XXXXXXX 100644
70
--- a/target/arm/translate.c
71
+++ b/target/arm/translate.c
72
@@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn)
73
bool is_long = false, q = extract32(insn, 6, 1);
74
bool ptr_is_env = false;
75
76
- if ((insn & 0xfea00f10) == 0xfc800800) {
77
- /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */
78
- int size = extract32(insn, 20, 1);
79
- data = extract32(insn, 24, 1); /* rot */
80
- if (!dc_isar_feature(aa32_vcma, s)
81
- || (!size && !dc_isar_feature(aa32_fp16_arith, s))) {
82
- return 1;
83
- }
84
- fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh;
85
- } else if ((insn & 0xfeb00f00) == 0xfc200d00) {
86
+ if ((insn & 0xfeb00f00) == 0xfc200d00) {
87
/* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */
88
bool u = extract32(insn, 4, 1);
89
if (!dc_isar_feature(aa32_dp, s)) {
90
--
91
2.20.1
92
93
diff view generated by jsdifflib
Deleted patch
1
Convert the V[US]DOT (vector) insns to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200430181003.21682-7-peter.maydell@linaro.org
6
---
7
target/arm/neon-shared.decode | 4 ++++
8
target/arm/translate-neon.inc.c | 32 ++++++++++++++++++++++++++++++++
9
target/arm/translate.c | 9 +--------
10
3 files changed, 37 insertions(+), 8 deletions(-)
11
12
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-shared.decode
15
+++ b/target/arm/neon-shared.decode
16
@@ -XXX,XX +XXX,XX @@ VCMLA 1111 110 rot:2 . 1 size:1 .... .... 1000 . q:1 . 0 .... \
17
18
VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \
19
vm=%vm_dp vn=%vn_dp vd=%vd_dp
20
+
21
+# VUDOT and VSDOT
22
+VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \
23
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp
24
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
25
index XXXXXXX..XXXXXXX 100644
26
--- a/target/arm/translate-neon.inc.c
27
+++ b/target/arm/translate-neon.inc.c
28
@@ -XXX,XX +XXX,XX @@ static bool trans_VCADD(DisasContext *s, arg_VCADD *a)
29
tcg_temp_free_ptr(fpst);
30
return true;
31
}
32
+
33
+static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
34
+{
35
+ int opr_sz;
36
+ gen_helper_gvec_3 *fn_gvec;
37
+
38
+ if (!dc_isar_feature(aa32_dp, s)) {
39
+ return false;
40
+ }
41
+
42
+ /* UNDEF accesses to D16-D31 if they don't exist. */
43
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
44
+ ((a->vd | a->vn | a->vm) & 0x10)) {
45
+ return false;
46
+ }
47
+
48
+ if ((a->vn | a->vm | a->vd) & a->q) {
49
+ return false;
50
+ }
51
+
52
+ if (!vfp_access_check(s)) {
53
+ return true;
54
+ }
55
+
56
+ opr_sz = (1 + a->q) * 8;
57
+ fn_gvec = a->u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b;
58
+ tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
59
+ vfp_reg_offset(1, a->vn),
60
+ vfp_reg_offset(1, a->vm),
61
+ opr_sz, opr_sz, 0, fn_gvec);
62
+ return true;
63
+}
64
diff --git a/target/arm/translate.c b/target/arm/translate.c
65
index XXXXXXX..XXXXXXX 100644
66
--- a/target/arm/translate.c
67
+++ b/target/arm/translate.c
68
@@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn)
69
bool is_long = false, q = extract32(insn, 6, 1);
70
bool ptr_is_env = false;
71
72
- if ((insn & 0xfeb00f00) == 0xfc200d00) {
73
- /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */
74
- bool u = extract32(insn, 4, 1);
75
- if (!dc_isar_feature(aa32_dp, s)) {
76
- return 1;
77
- }
78
- fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b;
79
- } else if ((insn & 0xff300f10) == 0xfc200810) {
80
+ if ((insn & 0xff300f10) == 0xfc200810) {
81
/* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */
82
int is_s = extract32(insn, 23, 1);
83
if (!dc_isar_feature(aa32_fhm, s)) {
84
--
85
2.20.1
86
87
diff view generated by jsdifflib
Deleted patch
1
Convert the VFM[AS]L (vector) insns to decodetree. This is the last
2
insn in the legacy decoder for the 3same_ext group, so we can
3
delete the legacy decoder function for the group entirely.
4
1
5
Note that in disas_thumb2_insn() the parts of this encoding space
6
where the decodetree decoder returns false will correctly be directed
7
to illegal_op by the "(insn & (1 << 28))" check so they won't fall
8
into disas_coproc_insn() by mistake.
9
10
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
11
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
12
Message-id: 20200430181003.21682-8-peter.maydell@linaro.org
13
---
14
target/arm/neon-shared.decode | 6 +++
15
target/arm/translate-neon.inc.c | 31 +++++++++++
16
target/arm/translate.c | 92 +--------------------------------
17
3 files changed, 38 insertions(+), 91 deletions(-)
18
19
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
20
index XXXXXXX..XXXXXXX 100644
21
--- a/target/arm/neon-shared.decode
22
+++ b/target/arm/neon-shared.decode
23
@@ -XXX,XX +XXX,XX @@ VCADD 1111 110 rot:1 1 . 0 size:1 .... .... 1000 . q:1 . 0 .... \
24
# VUDOT and VSDOT
25
VDOT 1111 110 00 . 10 .... .... 1101 . q:1 . u:1 .... \
26
vm=%vm_dp vn=%vn_dp vd=%vd_dp
27
+
28
+# VFM[AS]L
29
+VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \
30
+ vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0
31
+VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \
32
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1
33
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
34
index XXXXXXX..XXXXXXX 100644
35
--- a/target/arm/translate-neon.inc.c
36
+++ b/target/arm/translate-neon.inc.c
37
@@ -XXX,XX +XXX,XX @@ static bool trans_VDOT(DisasContext *s, arg_VDOT *a)
38
opr_sz, opr_sz, 0, fn_gvec);
39
return true;
40
}
41
+
42
+static bool trans_VFML(DisasContext *s, arg_VFML *a)
43
+{
44
+ int opr_sz;
45
+
46
+ if (!dc_isar_feature(aa32_fhm, s)) {
47
+ return false;
48
+ }
49
+
50
+ /* UNDEF accesses to D16-D31 if they don't exist. */
51
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
52
+ (a->vd & 0x10)) {
53
+ return false;
54
+ }
55
+
56
+ if (a->vd & a->q) {
57
+ return false;
58
+ }
59
+
60
+ if (!vfp_access_check(s)) {
61
+ return true;
62
+ }
63
+
64
+ opr_sz = (1 + a->q) * 8;
65
+ tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
66
+ vfp_reg_offset(a->q, a->vn),
67
+ vfp_reg_offset(a->q, a->vm),
68
+ cpu_env, opr_sz, opr_sz, a->s, /* is_2 == 0 */
69
+ gen_helper_gvec_fmlal_a32);
70
+ return true;
71
+}
72
diff --git a/target/arm/translate.c b/target/arm/translate.c
73
index XXXXXXX..XXXXXXX 100644
74
--- a/target/arm/translate.c
75
+++ b/target/arm/translate.c
76
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
77
return 0;
78
}
79
80
-/* Advanced SIMD three registers of the same length extension.
81
- * 31 25 23 22 20 16 12 11 10 9 8 3 0
82
- * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+
83
- * | 1 1 1 1 1 1 0 | op1 | D | op2 | Vn | Vd | 1 | o3 | 0 | o4 | N Q M U | Vm |
84
- * +---------------+-----+---+-----+----+----+---+----+---+----+---------+----+
85
- */
86
-static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn)
87
-{
88
- gen_helper_gvec_3 *fn_gvec = NULL;
89
- gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL;
90
- int rd, rn, rm, opr_sz;
91
- int data = 0;
92
- int off_rn, off_rm;
93
- bool is_long = false, q = extract32(insn, 6, 1);
94
- bool ptr_is_env = false;
95
-
96
- if ((insn & 0xff300f10) == 0xfc200810) {
97
- /* VFM[AS]L -- 1111 1100 S.10 .... .... 1000 .Q.1 .... */
98
- int is_s = extract32(insn, 23, 1);
99
- if (!dc_isar_feature(aa32_fhm, s)) {
100
- return 1;
101
- }
102
- is_long = true;
103
- data = is_s; /* is_2 == 0 */
104
- fn_gvec_ptr = gen_helper_gvec_fmlal_a32;
105
- ptr_is_env = true;
106
- } else {
107
- return 1;
108
- }
109
-
110
- VFP_DREG_D(rd, insn);
111
- if (rd & q) {
112
- return 1;
113
- }
114
- if (q || !is_long) {
115
- VFP_DREG_N(rn, insn);
116
- VFP_DREG_M(rm, insn);
117
- if ((rn | rm) & q & !is_long) {
118
- return 1;
119
- }
120
- off_rn = vfp_reg_offset(1, rn);
121
- off_rm = vfp_reg_offset(1, rm);
122
- } else {
123
- rn = VFP_SREG_N(insn);
124
- rm = VFP_SREG_M(insn);
125
- off_rn = vfp_reg_offset(0, rn);
126
- off_rm = vfp_reg_offset(0, rm);
127
- }
128
-
129
- if (s->fp_excp_el) {
130
- gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
131
- syn_simd_access_trap(1, 0xe, false), s->fp_excp_el);
132
- return 0;
133
- }
134
- if (!s->vfp_enabled) {
135
- return 1;
136
- }
137
-
138
- opr_sz = (1 + q) * 8;
139
- if (fn_gvec_ptr) {
140
- TCGv_ptr ptr;
141
- if (ptr_is_env) {
142
- ptr = cpu_env;
143
- } else {
144
- ptr = get_fpstatus_ptr(1);
145
- }
146
- tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), off_rn, off_rm, ptr,
147
- opr_sz, opr_sz, data, fn_gvec_ptr);
148
- if (!ptr_is_env) {
149
- tcg_temp_free_ptr(ptr);
150
- }
151
- } else {
152
- tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), off_rn, off_rm,
153
- opr_sz, opr_sz, data, fn_gvec);
154
- }
155
- return 0;
156
-}
157
-
158
/* Advanced SIMD two registers and a scalar extension.
159
* 31 24 23 22 20 16 12 11 10 9 8 3 0
160
* +-----------------+----+---+----+----+----+---+----+---+----+---------+----+
161
@@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn)
162
}
163
}
164
}
165
- } else if ((insn & 0x0e000a00) == 0x0c000800
166
- && arm_dc_feature(s, ARM_FEATURE_V8)) {
167
- if (disas_neon_insn_3same_ext(s, insn)) {
168
- goto illegal_op;
169
- }
170
- return;
171
} else if ((insn & 0x0f000a00) == 0x0e000800
172
&& arm_dc_feature(s, ARM_FEATURE_V8)) {
173
if (disas_neon_insn_2reg_scalar_ext(s, insn)) {
174
@@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn)
175
}
176
break;
177
}
178
- if ((insn & 0xfe000a00) == 0xfc000800
179
+ if ((insn & 0xff000a00) == 0xfe000800
180
&& arm_dc_feature(s, ARM_FEATURE_V8)) {
181
/* The Thumb2 and ARM encodings are identical. */
182
- if (disas_neon_insn_3same_ext(s, insn)) {
183
- goto illegal_op;
184
- }
185
- } else if ((insn & 0xff000a00) == 0xfe000800
186
- && arm_dc_feature(s, ARM_FEATURE_V8)) {
187
- /* The Thumb2 and ARM encodings are identical. */
188
if (disas_neon_insn_2reg_scalar_ext(s, insn)) {
189
goto illegal_op;
190
}
191
--
192
2.20.1
193
194
diff view generated by jsdifflib
Deleted patch
1
Convert VCMLA (scalar) in the 2reg-scalar-ext group to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200430181003.21682-9-peter.maydell@linaro.org
6
---
7
target/arm/neon-shared.decode | 5 +++++
8
target/arm/translate-neon.inc.c | 40 +++++++++++++++++++++++++++++++++
9
target/arm/translate.c | 26 +--------------------
10
3 files changed, 46 insertions(+), 25 deletions(-)
11
12
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-shared.decode
15
+++ b/target/arm/neon-shared.decode
16
@@ -XXX,XX +XXX,XX @@ VFML 1111 110 0 s:1 . 10 .... .... 1000 . 0 . 1 .... \
17
vm=%vm_sp vn=%vn_sp vd=%vd_dp q=0
18
VFML 1111 110 0 s:1 . 10 .... .... 1000 . 1 . 1 .... \
19
vm=%vm_dp vn=%vn_dp vd=%vd_dp q=1
20
+
21
+VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
22
+ vn=%vn_dp vd=%vd_dp size=0
23
+VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
24
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0
25
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
26
index XXXXXXX..XXXXXXX 100644
27
--- a/target/arm/translate-neon.inc.c
28
+++ b/target/arm/translate-neon.inc.c
29
@@ -XXX,XX +XXX,XX @@ static bool trans_VFML(DisasContext *s, arg_VFML *a)
30
gen_helper_gvec_fmlal_a32);
31
return true;
32
}
33
+
34
+static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
35
+{
36
+ gen_helper_gvec_3_ptr *fn_gvec_ptr;
37
+ int opr_sz;
38
+ TCGv_ptr fpst;
39
+
40
+ if (!dc_isar_feature(aa32_vcma, s)) {
41
+ return false;
42
+ }
43
+ if (a->size == 0 && !dc_isar_feature(aa32_fp16_arith, s)) {
44
+ return false;
45
+ }
46
+
47
+ /* UNDEF accesses to D16-D31 if they don't exist. */
48
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
49
+ ((a->vd | a->vn | a->vm) & 0x10)) {
50
+ return false;
51
+ }
52
+
53
+ if ((a->vd | a->vn) & a->q) {
54
+ return false;
55
+ }
56
+
57
+ if (!vfp_access_check(s)) {
58
+ return true;
59
+ }
60
+
61
+ fn_gvec_ptr = (a->size ? gen_helper_gvec_fcmlas_idx
62
+ : gen_helper_gvec_fcmlah_idx);
63
+ opr_sz = (1 + a->q) * 8;
64
+ fpst = get_fpstatus_ptr(1);
65
+ tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
66
+ vfp_reg_offset(1, a->vn),
67
+ vfp_reg_offset(1, a->vm),
68
+ fpst, opr_sz, opr_sz,
69
+ (a->index << 2) | a->rot, fn_gvec_ptr);
70
+ tcg_temp_free_ptr(fpst);
71
+ return true;
72
+}
73
diff --git a/target/arm/translate.c b/target/arm/translate.c
74
index XXXXXXX..XXXXXXX 100644
75
--- a/target/arm/translate.c
76
+++ b/target/arm/translate.c
77
@@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn)
78
bool is_long = false, q = extract32(insn, 6, 1);
79
bool ptr_is_env = false;
80
81
- if ((insn & 0xff000f10) == 0xfe000800) {
82
- /* VCMLA (indexed) -- 1111 1110 S.RR .... .... 1000 ...0 .... */
83
- int rot = extract32(insn, 20, 2);
84
- int size = extract32(insn, 23, 1);
85
- int index;
86
-
87
- if (!dc_isar_feature(aa32_vcma, s)) {
88
- return 1;
89
- }
90
- if (size == 0) {
91
- if (!dc_isar_feature(aa32_fp16_arith, s)) {
92
- return 1;
93
- }
94
- /* For fp16, rm is just Vm, and index is M. */
95
- rm = extract32(insn, 0, 4);
96
- index = extract32(insn, 5, 1);
97
- } else {
98
- /* For fp32, rm is the usual M:Vm, and index is 0. */
99
- VFP_DREG_M(rm, insn);
100
- index = 0;
101
- }
102
- data = (index << 2) | rot;
103
- fn_gvec_ptr = (size ? gen_helper_gvec_fcmlas_idx
104
- : gen_helper_gvec_fcmlah_idx);
105
- } else if ((insn & 0xffb00f00) == 0xfe200d00) {
106
+ if ((insn & 0xffb00f00) == 0xfe200d00) {
107
/* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */
108
int u = extract32(insn, 4, 1);
109
110
--
111
2.20.1
112
113
diff view generated by jsdifflib
Deleted patch
1
Convert the V[US]DOT (scalar) insns in the 2reg-scalar-ext group
2
to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-10-peter.maydell@linaro.org
7
---
8
target/arm/neon-shared.decode | 3 +++
9
target/arm/translate-neon.inc.c | 35 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 13 +-----------
11
3 files changed, 39 insertions(+), 12 deletions(-)
12
13
diff --git a/target/arm/neon-shared.decode b/target/arm/neon-shared.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-shared.decode
16
+++ b/target/arm/neon-shared.decode
17
@@ -XXX,XX +XXX,XX @@ VCMLA_scalar 1111 1110 0 . rot:2 .... .... 1000 . q:1 index:1 0 vm:4 \
18
vn=%vn_dp vd=%vd_dp size=0
19
VCMLA_scalar 1111 1110 1 . rot:2 .... .... 1000 . q:1 . 0 .... \
20
vm=%vm_dp vn=%vn_dp vd=%vd_dp size=1 index=0
21
+
22
+VDOT_scalar 1111 1110 0 . 10 .... .... 1101 . q:1 index:1 u:1 rm:4 \
23
+ vm=%vm_dp vn=%vn_dp vd=%vd_dp
24
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
25
index XXXXXXX..XXXXXXX 100644
26
--- a/target/arm/translate-neon.inc.c
27
+++ b/target/arm/translate-neon.inc.c
28
@@ -XXX,XX +XXX,XX @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
29
tcg_temp_free_ptr(fpst);
30
return true;
31
}
32
+
33
+static bool trans_VDOT_scalar(DisasContext *s, arg_VDOT_scalar *a)
34
+{
35
+ gen_helper_gvec_3 *fn_gvec;
36
+ int opr_sz;
37
+ TCGv_ptr fpst;
38
+
39
+ if (!dc_isar_feature(aa32_dp, s)) {
40
+ return false;
41
+ }
42
+
43
+ /* UNDEF accesses to D16-D31 if they don't exist. */
44
+ if (!dc_isar_feature(aa32_simd_r32, s) &&
45
+ ((a->vd | a->vn) & 0x10)) {
46
+ return false;
47
+ }
48
+
49
+ if ((a->vd | a->vn) & a->q) {
50
+ return false;
51
+ }
52
+
53
+ if (!vfp_access_check(s)) {
54
+ return true;
55
+ }
56
+
57
+ fn_gvec = a->u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b;
58
+ opr_sz = (1 + a->q) * 8;
59
+ fpst = get_fpstatus_ptr(1);
60
+ tcg_gen_gvec_3_ool(vfp_reg_offset(1, a->vd),
61
+ vfp_reg_offset(1, a->vn),
62
+ vfp_reg_offset(1, a->rm),
63
+ opr_sz, opr_sz, a->index, fn_gvec);
64
+ tcg_temp_free_ptr(fpst);
65
+ return true;
66
+}
67
diff --git a/target/arm/translate.c b/target/arm/translate.c
68
index XXXXXXX..XXXXXXX 100644
69
--- a/target/arm/translate.c
70
+++ b/target/arm/translate.c
71
@@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn)
72
bool is_long = false, q = extract32(insn, 6, 1);
73
bool ptr_is_env = false;
74
75
- if ((insn & 0xffb00f00) == 0xfe200d00) {
76
- /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */
77
- int u = extract32(insn, 4, 1);
78
-
79
- if (!dc_isar_feature(aa32_dp, s)) {
80
- return 1;
81
- }
82
- fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b;
83
- /* rm is just Vm, and index is M. */
84
- data = extract32(insn, 5, 1); /* index */
85
- rm = extract32(insn, 0, 4);
86
- } else if ((insn & 0xffa00f10) == 0xfe000810) {
87
+ if ((insn & 0xffa00f10) == 0xfe000810) {
88
/* VFM[AS]L -- 1111 1110 0.0S .... .... 1000 .Q.1 .... */
89
int is_s = extract32(insn, 20, 1);
90
int vm20 = extract32(insn, 0, 3);
91
--
92
2.20.1
93
94
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon "load/store multiple structures" insns to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200430181003.21682-12-peter.maydell@linaro.org
6
---
7
target/arm/neon-ls.decode | 7 ++
8
target/arm/translate-neon.inc.c | 124 ++++++++++++++++++++++++++++++++
9
target/arm/translate.c | 91 +----------------------
10
3 files changed, 133 insertions(+), 89 deletions(-)
11
12
diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-ls.decode
15
+++ b/target/arm/neon-ls.decode
16
@@ -XXX,XX +XXX,XX @@
17
# 0b1111_1001_xxx0_xxxx_xxxx_xxxx_xxxx_xxxx
18
# This file works on the A32 encoding only; calling code for T32 has to
19
# transform the insn into the A32 version first.
20
+
21
+%vd_dp 22:1 12:4
22
+
23
+# Neon load/store multiple structures
24
+
25
+VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \
26
+ vd=%vd_dp
27
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
28
index XXXXXXX..XXXXXXX 100644
29
--- a/target/arm/translate-neon.inc.c
30
+++ b/target/arm/translate-neon.inc.c
31
@@ -XXX,XX +XXX,XX @@ static bool trans_VFML_scalar(DisasContext *s, arg_VFML_scalar *a)
32
gen_helper_gvec_fmlal_idx_a32);
33
return true;
34
}
35
+
36
+static struct {
37
+ int nregs;
38
+ int interleave;
39
+ int spacing;
40
+} const neon_ls_element_type[11] = {
41
+ {1, 4, 1},
42
+ {1, 4, 2},
43
+ {4, 1, 1},
44
+ {2, 2, 2},
45
+ {1, 3, 1},
46
+ {1, 3, 2},
47
+ {3, 1, 1},
48
+ {1, 1, 1},
49
+ {1, 2, 1},
50
+ {1, 2, 2},
51
+ {2, 1, 1}
52
+};
53
+
54
+static void gen_neon_ldst_base_update(DisasContext *s, int rm, int rn,
55
+ int stride)
56
+{
57
+ if (rm != 15) {
58
+ TCGv_i32 base;
59
+
60
+ base = load_reg(s, rn);
61
+ if (rm == 13) {
62
+ tcg_gen_addi_i32(base, base, stride);
63
+ } else {
64
+ TCGv_i32 index;
65
+ index = load_reg(s, rm);
66
+ tcg_gen_add_i32(base, base, index);
67
+ tcg_temp_free_i32(index);
68
+ }
69
+ store_reg(s, rn, base);
70
+ }
71
+}
72
+
73
+static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
74
+{
75
+ /* Neon load/store multiple structures */
76
+ int nregs, interleave, spacing, reg, n;
77
+ MemOp endian = s->be_data;
78
+ int mmu_idx = get_mem_index(s);
79
+ int size = a->size;
80
+ TCGv_i64 tmp64;
81
+ TCGv_i32 addr, tmp;
82
+
83
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
84
+ return false;
85
+ }
86
+
87
+ /* UNDEF accesses to D16-D31 if they don't exist */
88
+ if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) {
89
+ return false;
90
+ }
91
+ if (a->itype > 10) {
92
+ return false;
93
+ }
94
+ /* Catch UNDEF cases for bad values of align field */
95
+ switch (a->itype & 0xc) {
96
+ case 4:
97
+ if (a->align >= 2) {
98
+ return false;
99
+ }
100
+ break;
101
+ case 8:
102
+ if (a->align == 3) {
103
+ return false;
104
+ }
105
+ break;
106
+ default:
107
+ break;
108
+ }
109
+ nregs = neon_ls_element_type[a->itype].nregs;
110
+ interleave = neon_ls_element_type[a->itype].interleave;
111
+ spacing = neon_ls_element_type[a->itype].spacing;
112
+ if (size == 3 && (interleave | spacing) != 1) {
113
+ return false;
114
+ }
115
+
116
+ if (!vfp_access_check(s)) {
117
+ return true;
118
+ }
119
+
120
+ /* For our purposes, bytes are always little-endian. */
121
+ if (size == 0) {
122
+ endian = MO_LE;
123
+ }
124
+ /*
125
+ * Consecutive little-endian elements from a single register
126
+ * can be promoted to a larger little-endian operation.
127
+ */
128
+ if (interleave == 1 && endian == MO_LE) {
129
+ size = 3;
130
+ }
131
+ tmp64 = tcg_temp_new_i64();
132
+ addr = tcg_temp_new_i32();
133
+ tmp = tcg_const_i32(1 << size);
134
+ load_reg_var(s, addr, a->rn);
135
+ for (reg = 0; reg < nregs; reg++) {
136
+ for (n = 0; n < 8 >> size; n++) {
137
+ int xs;
138
+ for (xs = 0; xs < interleave; xs++) {
139
+ int tt = a->vd + reg + spacing * xs;
140
+
141
+ if (a->l) {
142
+ gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size);
143
+ neon_store_element64(tt, n, size, tmp64);
144
+ } else {
145
+ neon_load_element64(tmp64, tt, n, size);
146
+ gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size);
147
+ }
148
+ tcg_gen_add_i32(addr, addr, tmp);
149
+ }
150
+ }
151
+ }
152
+ tcg_temp_free_i32(addr);
153
+ tcg_temp_free_i32(tmp);
154
+ tcg_temp_free_i64(tmp64);
155
+
156
+ gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8);
157
+ return true;
158
+}
159
diff --git a/target/arm/translate.c b/target/arm/translate.c
160
index XXXXXXX..XXXXXXX 100644
161
--- a/target/arm/translate.c
162
+++ b/target/arm/translate.c
163
@@ -XXX,XX +XXX,XX @@ static void gen_neon_trn_u16(TCGv_i32 t0, TCGv_i32 t1)
164
}
165
166
167
-static struct {
168
- int nregs;
169
- int interleave;
170
- int spacing;
171
-} const neon_ls_element_type[11] = {
172
- {1, 4, 1},
173
- {1, 4, 2},
174
- {4, 1, 1},
175
- {2, 2, 2},
176
- {1, 3, 1},
177
- {1, 3, 2},
178
- {3, 1, 1},
179
- {1, 1, 1},
180
- {1, 2, 1},
181
- {1, 2, 2},
182
- {2, 1, 1}
183
-};
184
-
185
/* Translate a NEON load/store element instruction. Return nonzero if the
186
instruction is invalid. */
187
static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
188
{
189
int rd, rn, rm;
190
- int op;
191
int nregs;
192
- int interleave;
193
- int spacing;
194
int stride;
195
int size;
196
int reg;
197
int load;
198
- int n;
199
int vec_size;
200
- int mmu_idx;
201
- MemOp endian;
202
TCGv_i32 addr;
203
TCGv_i32 tmp;
204
- TCGv_i32 tmp2;
205
- TCGv_i64 tmp64;
206
207
if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
208
return 1;
209
@@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
210
rn = (insn >> 16) & 0xf;
211
rm = insn & 0xf;
212
load = (insn & (1 << 21)) != 0;
213
- endian = s->be_data;
214
- mmu_idx = get_mem_index(s);
215
if ((insn & (1 << 23)) == 0) {
216
- /* Load store all elements. */
217
- op = (insn >> 8) & 0xf;
218
- size = (insn >> 6) & 3;
219
- if (op > 10)
220
- return 1;
221
- /* Catch UNDEF cases for bad values of align field */
222
- switch (op & 0xc) {
223
- case 4:
224
- if (((insn >> 5) & 1) == 1) {
225
- return 1;
226
- }
227
- break;
228
- case 8:
229
- if (((insn >> 4) & 3) == 3) {
230
- return 1;
231
- }
232
- break;
233
- default:
234
- break;
235
- }
236
- nregs = neon_ls_element_type[op].nregs;
237
- interleave = neon_ls_element_type[op].interleave;
238
- spacing = neon_ls_element_type[op].spacing;
239
- if (size == 3 && (interleave | spacing) != 1) {
240
- return 1;
241
- }
242
- /* For our purposes, bytes are always little-endian. */
243
- if (size == 0) {
244
- endian = MO_LE;
245
- }
246
- /* Consecutive little-endian elements from a single register
247
- * can be promoted to a larger little-endian operation.
248
- */
249
- if (interleave == 1 && endian == MO_LE) {
250
- size = 3;
251
- }
252
- tmp64 = tcg_temp_new_i64();
253
- addr = tcg_temp_new_i32();
254
- tmp2 = tcg_const_i32(1 << size);
255
- load_reg_var(s, addr, rn);
256
- for (reg = 0; reg < nregs; reg++) {
257
- for (n = 0; n < 8 >> size; n++) {
258
- int xs;
259
- for (xs = 0; xs < interleave; xs++) {
260
- int tt = rd + reg + spacing * xs;
261
-
262
- if (load) {
263
- gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size);
264
- neon_store_element64(tt, n, size, tmp64);
265
- } else {
266
- neon_load_element64(tmp64, tt, n, size);
267
- gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size);
268
- }
269
- tcg_gen_add_i32(addr, addr, tmp2);
270
- }
271
- }
272
- }
273
- tcg_temp_free_i32(addr);
274
- tcg_temp_free_i32(tmp2);
275
- tcg_temp_free_i64(tmp64);
276
- stride = nregs * interleave * 8;
277
+ /* Load store all elements -- handled already by decodetree */
278
+ return 1;
279
} else {
280
size = (insn >> 10) & 3;
281
if (size == 3) {
282
--
283
2.20.1
284
285
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon "load single structure to all lanes" insns to
2
decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-13-peter.maydell@linaro.org
7
---
8
target/arm/neon-ls.decode | 5 +++
9
target/arm/translate-neon.inc.c | 73 +++++++++++++++++++++++++++++++++
10
target/arm/translate.c | 55 +------------------------
11
3 files changed, 80 insertions(+), 53 deletions(-)
12
13
diff --git a/target/arm/neon-ls.decode b/target/arm/neon-ls.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-ls.decode
16
+++ b/target/arm/neon-ls.decode
17
@@ -XXX,XX +XXX,XX @@
18
19
VLDST_multiple 1111 0100 0 . l:1 0 rn:4 .... itype:4 size:2 align:2 rm:4 \
20
vd=%vd_dp
21
+
22
+# Neon load single element to all lanes
23
+
24
+VLD_all_lanes 1111 0100 1 . 1 0 rn:4 .... 11 n:2 size:2 t:1 a:1 rm:4 \
25
+ vd=%vd_dp
26
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
27
index XXXXXXX..XXXXXXX 100644
28
--- a/target/arm/translate-neon.inc.c
29
+++ b/target/arm/translate-neon.inc.c
30
@@ -XXX,XX +XXX,XX @@ static bool trans_VLDST_multiple(DisasContext *s, arg_VLDST_multiple *a)
31
gen_neon_ldst_base_update(s, a->rm, a->rn, nregs * interleave * 8);
32
return true;
33
}
34
+
35
+static bool trans_VLD_all_lanes(DisasContext *s, arg_VLD_all_lanes *a)
36
+{
37
+ /* Neon load single structure to all lanes */
38
+ int reg, stride, vec_size;
39
+ int vd = a->vd;
40
+ int size = a->size;
41
+ int nregs = a->n + 1;
42
+ TCGv_i32 addr, tmp;
43
+
44
+ if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
45
+ return false;
46
+ }
47
+
48
+ /* UNDEF accesses to D16-D31 if they don't exist */
49
+ if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) {
50
+ return false;
51
+ }
52
+
53
+ if (size == 3) {
54
+ if (nregs != 4 || a->a == 0) {
55
+ return false;
56
+ }
57
+ /* For VLD4 size == 3 a == 1 means 32 bits at 16 byte alignment */
58
+ size = 2;
59
+ }
60
+ if (nregs == 1 && a->a == 1 && size == 0) {
61
+ return false;
62
+ }
63
+ if (nregs == 3 && a->a == 1) {
64
+ return false;
65
+ }
66
+
67
+ if (!vfp_access_check(s)) {
68
+ return true;
69
+ }
70
+
71
+ /*
72
+ * VLD1 to all lanes: T bit indicates how many Dregs to write.
73
+ * VLD2/3/4 to all lanes: T bit indicates register stride.
74
+ */
75
+ stride = a->t ? 2 : 1;
76
+ vec_size = nregs == 1 ? stride * 8 : 8;
77
+
78
+ tmp = tcg_temp_new_i32();
79
+ addr = tcg_temp_new_i32();
80
+ load_reg_var(s, addr, a->rn);
81
+ for (reg = 0; reg < nregs; reg++) {
82
+ gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
83
+ s->be_data | size);
84
+ if ((vd & 1) && vec_size == 16) {
85
+ /*
86
+ * We cannot write 16 bytes at once because the
87
+ * destination is unaligned.
88
+ */
89
+ tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
90
+ 8, 8, tmp);
91
+ tcg_gen_gvec_mov(0, neon_reg_offset(vd + 1, 0),
92
+ neon_reg_offset(vd, 0), 8, 8);
93
+ } else {
94
+ tcg_gen_gvec_dup_i32(size, neon_reg_offset(vd, 0),
95
+ vec_size, vec_size, tmp);
96
+ }
97
+ tcg_gen_addi_i32(addr, addr, 1 << size);
98
+ vd += stride;
99
+ }
100
+ tcg_temp_free_i32(tmp);
101
+ tcg_temp_free_i32(addr);
102
+
103
+ gen_neon_ldst_base_update(s, a->rm, a->rn, (1 << size) * nregs);
104
+
105
+ return true;
106
+}
107
diff --git a/target/arm/translate.c b/target/arm/translate.c
108
index XXXXXXX..XXXXXXX 100644
109
--- a/target/arm/translate.c
110
+++ b/target/arm/translate.c
111
@@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
112
int size;
113
int reg;
114
int load;
115
- int vec_size;
116
TCGv_i32 addr;
117
TCGv_i32 tmp;
118
119
@@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn)
120
} else {
121
size = (insn >> 10) & 3;
122
if (size == 3) {
123
- /* Load single element to all lanes. */
124
- int a = (insn >> 4) & 1;
125
- if (!load) {
126
- return 1;
127
- }
128
- size = (insn >> 6) & 3;
129
- nregs = ((insn >> 8) & 3) + 1;
130
-
131
- if (size == 3) {
132
- if (nregs != 4 || a == 0) {
133
- return 1;
134
- }
135
- /* For VLD4 size==3 a == 1 means 32 bits at 16 byte alignment */
136
- size = 2;
137
- }
138
- if (nregs == 1 && a == 1 && size == 0) {
139
- return 1;
140
- }
141
- if (nregs == 3 && a == 1) {
142
- return 1;
143
- }
144
- addr = tcg_temp_new_i32();
145
- load_reg_var(s, addr, rn);
146
-
147
- /* VLD1 to all lanes: bit 5 indicates how many Dregs to write.
148
- * VLD2/3/4 to all lanes: bit 5 indicates register stride.
149
- */
150
- stride = (insn & (1 << 5)) ? 2 : 1;
151
- vec_size = nregs == 1 ? stride * 8 : 8;
152
-
153
- tmp = tcg_temp_new_i32();
154
- for (reg = 0; reg < nregs; reg++) {
155
- gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s),
156
- s->be_data | size);
157
- if ((rd & 1) && vec_size == 16) {
158
- /* We cannot write 16 bytes at once because the
159
- * destination is unaligned.
160
- */
161
- tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0),
162
- 8, 8, tmp);
163
- tcg_gen_gvec_mov(0, neon_reg_offset(rd + 1, 0),
164
- neon_reg_offset(rd, 0), 8, 8);
165
- } else {
166
- tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0),
167
- vec_size, vec_size, tmp);
168
- }
169
- tcg_gen_addi_i32(addr, addr, 1 << size);
170
- rd += stride;
171
- }
172
- tcg_temp_free_i32(tmp);
173
- tcg_temp_free_i32(addr);
174
- stride = (1 << size) * nregs;
175
+ /* Load single element to all lanes -- handled by decodetree */
176
+ return 1;
177
} else {
178
/* Single element. */
179
int idx = (insn >> 4) & 0xf;
180
--
181
2.20.1
182
183
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon logic ops in the 3-reg-same grouping to decodetree.
2
Note that for the logic ops the 'size' field forms part of their
3
decode and the actual operations are always bitwise.
4
1
5
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
6
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
7
Message-id: 20200430181003.21682-16-peter.maydell@linaro.org
8
---
9
target/arm/neon-dp.decode | 12 +++++++++++
10
target/arm/translate-neon.inc.c | 19 +++++++++++++++++
11
target/arm/translate.c | 38 +--------------------------------
12
3 files changed, 32 insertions(+), 37 deletions(-)
13
14
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
15
index XXXXXXX..XXXXXXX 100644
16
--- a/target/arm/neon-dp.decode
17
+++ b/target/arm/neon-dp.decode
18
@@ -XXX,XX +XXX,XX @@
19
@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \
20
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
21
22
+@3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \
23
+ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0
24
+
25
+VAND_3s 1111 001 0 0 . 00 .... .... 0001 ... 1 .... @3same_logic
26
+VBIC_3s 1111 001 0 0 . 01 .... .... 0001 ... 1 .... @3same_logic
27
+VORR_3s 1111 001 0 0 . 10 .... .... 0001 ... 1 .... @3same_logic
28
+VORN_3s 1111 001 0 0 . 11 .... .... 0001 ... 1 .... @3same_logic
29
+VEOR_3s 1111 001 1 0 . 00 .... .... 0001 ... 1 .... @3same_logic
30
+VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic
31
+VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic
32
+VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic
33
+
34
VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same
35
VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
36
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
37
index XXXXXXX..XXXXXXX 100644
38
--- a/target/arm/translate-neon.inc.c
39
+++ b/target/arm/translate-neon.inc.c
40
@@ -XXX,XX +XXX,XX @@ static bool do_3same(DisasContext *s, arg_3same *a, GVecGen3Fn fn)
41
42
DO_3SAME(VADD, tcg_gen_gvec_add)
43
DO_3SAME(VSUB, tcg_gen_gvec_sub)
44
+DO_3SAME(VAND, tcg_gen_gvec_and)
45
+DO_3SAME(VBIC, tcg_gen_gvec_andc)
46
+DO_3SAME(VORR, tcg_gen_gvec_or)
47
+DO_3SAME(VORN, tcg_gen_gvec_orc)
48
+DO_3SAME(VEOR, tcg_gen_gvec_xor)
49
+
50
+/* These insns are all gvec_bitsel but with the inputs in various orders. */
51
+#define DO_3SAME_BITSEL(INSN, O1, O2, O3) \
52
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
53
+ uint32_t rn_ofs, uint32_t rm_ofs, \
54
+ uint32_t oprsz, uint32_t maxsz) \
55
+ { \
56
+ tcg_gen_gvec_bitsel(vece, rd_ofs, O1, O2, O3, oprsz, maxsz); \
57
+ } \
58
+ DO_3SAME(INSN, gen_##INSN##_3s)
59
+
60
+DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs)
61
+DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs)
62
+DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs)
63
diff --git a/target/arm/translate.c b/target/arm/translate.c
64
index XXXXXXX..XXXXXXX 100644
65
--- a/target/arm/translate.c
66
+++ b/target/arm/translate.c
67
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
68
}
69
return 1;
70
71
- case NEON_3R_LOGIC: /* Logic ops. */
72
- switch ((u << 2) | size) {
73
- case 0: /* VAND */
74
- tcg_gen_gvec_and(0, rd_ofs, rn_ofs, rm_ofs,
75
- vec_size, vec_size);
76
- break;
77
- case 1: /* VBIC */
78
- tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs,
79
- vec_size, vec_size);
80
- break;
81
- case 2: /* VORR */
82
- tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs,
83
- vec_size, vec_size);
84
- break;
85
- case 3: /* VORN */
86
- tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs,
87
- vec_size, vec_size);
88
- break;
89
- case 4: /* VEOR */
90
- tcg_gen_gvec_xor(0, rd_ofs, rn_ofs, rm_ofs,
91
- vec_size, vec_size);
92
- break;
93
- case 5: /* VBSL */
94
- tcg_gen_gvec_bitsel(MO_8, rd_ofs, rd_ofs, rn_ofs, rm_ofs,
95
- vec_size, vec_size);
96
- break;
97
- case 6: /* VBIT */
98
- tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rn_ofs, rd_ofs,
99
- vec_size, vec_size);
100
- break;
101
- case 7: /* VBIF */
102
- tcg_gen_gvec_bitsel(MO_8, rd_ofs, rm_ofs, rd_ofs, rn_ofs,
103
- vec_size, vec_size);
104
- break;
105
- }
106
- return 0;
107
-
108
case NEON_3R_VQADD:
109
tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
110
rn_ofs, rm_ofs, vec_size, vec_size,
111
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
112
return 0;
113
114
case NEON_3R_VADD_VSUB:
115
+ case NEON_3R_LOGIC:
116
/* Already handled by decodetree */
117
return 1;
118
}
119
--
120
2.20.1
121
122
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon 3-reg-same VMAX and VMIN insns to decodetree.
2
1
3
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
4
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
5
Message-id: 20200430181003.21682-17-peter.maydell@linaro.org
6
---
7
target/arm/neon-dp.decode | 5 +++++
8
target/arm/translate-neon.inc.c | 14 ++++++++++++++
9
target/arm/translate.c | 21 ++-------------------
10
3 files changed, 21 insertions(+), 19 deletions(-)
11
12
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
13
index XXXXXXX..XXXXXXX 100644
14
--- a/target/arm/neon-dp.decode
15
+++ b/target/arm/neon-dp.decode
16
@@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic
17
VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic
18
VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic
19
20
+VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
21
+VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
22
+VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
23
+VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same
24
+
25
VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same
26
VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
27
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
28
index XXXXXXX..XXXXXXX 100644
29
--- a/target/arm/translate-neon.inc.c
30
+++ b/target/arm/translate-neon.inc.c
31
@@ -XXX,XX +XXX,XX @@ DO_3SAME(VEOR, tcg_gen_gvec_xor)
32
DO_3SAME_BITSEL(VBSL, rd_ofs, rn_ofs, rm_ofs)
33
DO_3SAME_BITSEL(VBIT, rm_ofs, rn_ofs, rd_ofs)
34
DO_3SAME_BITSEL(VBIF, rm_ofs, rd_ofs, rn_ofs)
35
+
36
+#define DO_3SAME_NO_SZ_3(INSN, FUNC) \
37
+ static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \
38
+ { \
39
+ if (a->size == 3) { \
40
+ return false; \
41
+ } \
42
+ return do_3same(s, a, FUNC); \
43
+ }
44
+
45
+DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax)
46
+DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax)
47
+DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin)
48
+DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin)
49
diff --git a/target/arm/translate.c b/target/arm/translate.c
50
index XXXXXXX..XXXXXXX 100644
51
--- a/target/arm/translate.c
52
+++ b/target/arm/translate.c
53
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
54
rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size);
55
return 0;
56
57
- case NEON_3R_VMAX:
58
- if (u) {
59
- tcg_gen_gvec_umax(size, rd_ofs, rn_ofs, rm_ofs,
60
- vec_size, vec_size);
61
- } else {
62
- tcg_gen_gvec_smax(size, rd_ofs, rn_ofs, rm_ofs,
63
- vec_size, vec_size);
64
- }
65
- return 0;
66
- case NEON_3R_VMIN:
67
- if (u) {
68
- tcg_gen_gvec_umin(size, rd_ofs, rn_ofs, rm_ofs,
69
- vec_size, vec_size);
70
- } else {
71
- tcg_gen_gvec_smin(size, rd_ofs, rn_ofs, rm_ofs,
72
- vec_size, vec_size);
73
- }
74
- return 0;
75
-
76
case NEON_3R_VSHL:
77
/* Note the operation is vshl vd,vm,vn */
78
tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size,
79
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
80
81
case NEON_3R_VADD_VSUB:
82
case NEON_3R_LOGIC:
83
+ case NEON_3R_VMAX:
84
+ case NEON_3R_VMIN:
85
/* Already handled by decodetree */
86
return 1;
87
}
88
--
89
2.20.1
90
91
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon comparison ops in the 3-reg-same grouping
2
to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-18-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 8 ++++++++
9
target/arm/translate-neon.inc.c | 22 ++++++++++++++++++++++
10
target/arm/translate.c | 23 +++--------------------
11
3 files changed, 33 insertions(+), 20 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic
18
VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic
19
VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic
20
21
+VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same
22
+VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same
23
+VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
24
+VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same
25
+
26
VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same
27
VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same
28
VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same
29
@@ -XXX,XX +XXX,XX @@ VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same
30
31
VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same
32
VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same
33
+
34
+VTST_3s 1111 001 0 0 . .. .... .... 1000 . . . 1 .... @3same
35
+VCEQ_3s 1111 001 1 0 . .. .... .... 1000 . . . 1 .... @3same
36
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
37
index XXXXXXX..XXXXXXX 100644
38
--- a/target/arm/translate-neon.inc.c
39
+++ b/target/arm/translate-neon.inc.c
40
@@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_S, tcg_gen_gvec_smax)
41
DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax)
42
DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin)
43
DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin)
44
+
45
+#define DO_3SAME_CMP(INSN, COND) \
46
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
47
+ uint32_t rn_ofs, uint32_t rm_ofs, \
48
+ uint32_t oprsz, uint32_t maxsz) \
49
+ { \
50
+ tcg_gen_gvec_cmp(COND, vece, rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz); \
51
+ } \
52
+ DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s)
53
+
54
+DO_3SAME_CMP(VCGT_S, TCG_COND_GT)
55
+DO_3SAME_CMP(VCGT_U, TCG_COND_GTU)
56
+DO_3SAME_CMP(VCGE_S, TCG_COND_GE)
57
+DO_3SAME_CMP(VCGE_U, TCG_COND_GEU)
58
+DO_3SAME_CMP(VCEQ, TCG_COND_EQ)
59
+
60
+static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
61
+ uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz)
62
+{
63
+ tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]);
64
+}
65
+DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s)
66
diff --git a/target/arm/translate.c b/target/arm/translate.c
67
index XXXXXXX..XXXXXXX 100644
68
--- a/target/arm/translate.c
69
+++ b/target/arm/translate.c
70
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
71
u ? &mls_op[size] : &mla_op[size]);
72
return 0;
73
74
- case NEON_3R_VTST_VCEQ:
75
- if (u) { /* VCEQ */
76
- tcg_gen_gvec_cmp(TCG_COND_EQ, size, rd_ofs, rn_ofs, rm_ofs,
77
- vec_size, vec_size);
78
- } else { /* VTST */
79
- tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs,
80
- vec_size, vec_size, &cmtst_op[size]);
81
- }
82
- return 0;
83
-
84
- case NEON_3R_VCGT:
85
- tcg_gen_gvec_cmp(u ? TCG_COND_GTU : TCG_COND_GT, size,
86
- rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size);
87
- return 0;
88
-
89
- case NEON_3R_VCGE:
90
- tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size,
91
- rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size);
92
- return 0;
93
-
94
case NEON_3R_VSHL:
95
/* Note the operation is vshl vd,vm,vn */
96
tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, vec_size, vec_size,
97
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
98
case NEON_3R_LOGIC:
99
case NEON_3R_VMAX:
100
case NEON_3R_VMIN:
101
+ case NEON_3R_VTST_VCEQ:
102
+ case NEON_3R_VCGT:
103
+ case NEON_3R_VCGE:
104
/* Already handled by decodetree */
105
return 1;
106
}
107
--
108
2.20.1
109
110
diff view generated by jsdifflib
Deleted patch
1
Convert the Neon VQADD/VQSUB insns in the 3-reg-same grouping
2
to decodetree.
3
1
4
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
5
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
6
Message-id: 20200430181003.21682-19-peter.maydell@linaro.org
7
---
8
target/arm/neon-dp.decode | 6 ++++++
9
target/arm/translate-neon.inc.c | 15 +++++++++++++++
10
target/arm/translate.c | 14 ++------------
11
3 files changed, 23 insertions(+), 12 deletions(-)
12
13
diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode
14
index XXXXXXX..XXXXXXX 100644
15
--- a/target/arm/neon-dp.decode
16
+++ b/target/arm/neon-dp.decode
17
@@ -XXX,XX +XXX,XX @@
18
@3same .... ... . . . size:2 .... .... .... . q:1 . . .... \
19
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp
20
21
+VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same
22
+VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same
23
+
24
@3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \
25
&3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0
26
27
@@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic
28
VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic
29
VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic
30
31
+VQSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 1 .... @3same
32
+VQSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 1 .... @3same
33
+
34
VCGT_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 0 .... @3same
35
VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same
36
VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same
37
diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c
38
index XXXXXXX..XXXXXXX 100644
39
--- a/target/arm/translate-neon.inc.c
40
+++ b/target/arm/translate-neon.inc.c
41
@@ -XXX,XX +XXX,XX @@ static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs,
42
tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]);
43
}
44
DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s)
45
+
46
+#define DO_3SAME_GVEC4(INSN, OPARRAY) \
47
+ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \
48
+ uint32_t rn_ofs, uint32_t rm_ofs, \
49
+ uint32_t oprsz, uint32_t maxsz) \
50
+ { \
51
+ tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), \
52
+ rn_ofs, rm_ofs, oprsz, maxsz, &OPARRAY[vece]); \
53
+ } \
54
+ DO_3SAME(INSN, gen_##INSN##_3s)
55
+
56
+DO_3SAME_GVEC4(VQADD_S, sqadd_op)
57
+DO_3SAME_GVEC4(VQADD_U, uqadd_op)
58
+DO_3SAME_GVEC4(VQSUB_S, sqsub_op)
59
+DO_3SAME_GVEC4(VQSUB_U, uqsub_op)
60
diff --git a/target/arm/translate.c b/target/arm/translate.c
61
index XXXXXXX..XXXXXXX 100644
62
--- a/target/arm/translate.c
63
+++ b/target/arm/translate.c
64
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
65
}
66
return 1;
67
68
- case NEON_3R_VQADD:
69
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
70
- rn_ofs, rm_ofs, vec_size, vec_size,
71
- (u ? uqadd_op : sqadd_op) + size);
72
- return 0;
73
-
74
- case NEON_3R_VQSUB:
75
- tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc),
76
- rn_ofs, rm_ofs, vec_size, vec_size,
77
- (u ? uqsub_op : sqsub_op) + size);
78
- return 0;
79
-
80
case NEON_3R_VMUL: /* VMUL */
81
if (u) {
82
/* Polynomial case allows only P8. */
83
@@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
84
case NEON_3R_VTST_VCEQ:
85
case NEON_3R_VCGT:
86
case NEON_3R_VCGE:
87
+ case NEON_3R_VQADD:
88
+ case NEON_3R_VQSUB:
89
/* Already handled by decodetree */
90
return 1;
91
}
92
--
93
2.20.1
94
95
diff view generated by jsdifflib