| 1 | Just 4 bug fixes here... | 1 | The following changes since commit 3214bec13d8d4c40f707d21d8350d04e4123ae97: |
|---|---|---|---|
| 2 | 2 | ||
| 3 | thanks | 3 | Merge tag 'migration-20250110-pull-request' of https://gitlab.com/farosas/qemu into staging (2025-01-10 13:39:19 -0500) |
| 4 | -- PMM | ||
| 5 | |||
| 6 | The following changes since commit e9d2db818ff934afb366aea566d0b33acf7bced1: | ||
| 7 | |||
| 8 | Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2024-08-01 07:31:49 +1000) | ||
| 9 | 4 | ||
| 10 | are available in the Git repository at: | 5 | are available in the Git repository at: |
| 11 | 6 | ||
| 12 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240801 | 7 | https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20250113 |
| 13 | 8 | ||
| 14 | for you to fetch changes up to 5e8e4f098d872818aa9a138a171200068b81c8d1: | 9 | for you to fetch changes up to 435d260e7ec5ff9c79e3e62f1d66ec82d2d691ae: |
| 15 | 10 | ||
| 16 | target/xtensa: Correct assert condition in handle_interrupt() (2024-08-01 10:59:01 +0100) | 11 | docs/system/arm/virt: mention specific migration information (2025-01-13 12:35:35 +0000) |
| 17 | 12 | ||
| 18 | ---------------------------------------------------------------- | 13 | ---------------------------------------------------------------- |
| 19 | target-arm queue: | 14 | target-arm queue: |
| 20 | * hw/arm/mps2-tz.c: fix RX/TX interrupts order | 15 | * hw/arm_sysctl: fix extracting 31th bit of val |
| 21 | * accel/kvm/kvm-all: Fixes the missing break in vCPU unpark logic | 16 | * hw/misc: cast rpm to uint64_t |
| 22 | * target/arm: Handle denormals correctly for FMOPA (widening) | 17 | * tests/qtest/boot-serial-test: Improve ASM |
| 23 | * target/xtensa: Correct assert condition in handle_interrupt() | 18 | * target/arm: Move minor arithmetic helpers out of helper.c |
| 19 | * target/arm: change default pauth algorithm to impdef | ||
| 24 | 20 | ||
| 25 | ---------------------------------------------------------------- | 21 | ---------------------------------------------------------------- |
| 26 | Marco Palumbi (1): | 22 | Anastasia Belova (1): |
| 27 | hw/arm/mps2-tz.c: fix RX/TX interrupts order | 23 | hw/arm_sysctl: fix extracting 31th bit of val |
| 28 | 24 | ||
| 29 | Peter Maydell (2): | 25 | Peter Maydell (2): |
| 30 | target/arm: Handle denormals correctly for FMOPA (widening) | 26 | target/arm: Move minor arithmetic helpers out of helper.c |
| 31 | target/xtensa: Correct assert condition in handle_interrupt() | 27 | tests/tcg/aarch64: force qarma5 for pauth-3 test |
| 32 | 28 | ||
| 33 | Salil Mehta (1): | 29 | Philippe Mathieu-Daudé (4): |
| 34 | accel/kvm/kvm-all: Fixes the missing break in vCPU unpark logic | 30 | tests/qtest/boot-serial-test: Improve ASM comments of PL011 tests |
| 31 | tests/qtest/boot-serial-test: Reduce for() loop in PL011 tests | ||
| 32 | tests/qtest/boot-serial-test: Reorder pair of instructions in PL011 test | ||
| 33 | tests/qtest/boot-serial-test: Initialize PL011 Control register | ||
| 35 | 34 | ||
| 36 | target/arm/tcg/helper-sme.h | 2 +- | 35 | Pierrick Bouvier (3): |
| 37 | accel/kvm/kvm-all.c | 1 + | 36 | target/arm: add new property to select pauth-qarma5 |
| 38 | hw/arm/mps2-tz.c | 6 +++--- | 37 | target/arm: change default pauth algorithm to impdef |
| 39 | target/arm/tcg/sme_helper.c | 39 +++++++++++++++++++++++++++------------ | 38 | docs/system/arm/virt: mention specific migration information |
| 40 | target/arm/tcg/translate-sme.c | 25 +++++++++++++++++++++++-- | 39 | |
| 41 | target/xtensa/exc_helper.c | 2 +- | 40 | Tigran Sogomonian (1): |
| 42 | 6 files changed, 56 insertions(+), 19 deletions(-) | 41 | hw/misc: cast rpm to uint64_t |
| 42 | |||
| 43 | docs/system/arm/cpu-features.rst | 7 +- | ||
| 44 | docs/system/arm/virt.rst | 4 + | ||
| 45 | docs/system/introduction.rst | 2 +- | ||
| 46 | target/arm/cpu.h | 4 + | ||
| 47 | hw/core/machine.c | 4 +- | ||
| 48 | hw/misc/arm_sysctl.c | 2 +- | ||
| 49 | hw/misc/npcm7xx_mft.c | 5 +- | ||
| 50 | target/arm/arm-qmp-cmds.c | 2 +- | ||
| 51 | target/arm/cpu.c | 2 + | ||
| 52 | target/arm/cpu64.c | 38 ++- | ||
| 53 | target/arm/helper.c | 285 ----------------------- | ||
| 54 | target/arm/tcg/arith_helper.c | 296 ++++++++++++++++++++++++ | ||
| 55 | tests/qtest/arm-cpu-features.c | 15 +- | ||
| 56 | tests/qtest/boot-serial-test.c | 23 +- | ||
| 57 | target/arm/{op_addsub.h => tcg/op_addsub.c.inc} | 0 | ||
| 58 | target/arm/tcg/meson.build | 1 + | ||
| 59 | tests/tcg/aarch64/Makefile.softmmu-target | 3 + | ||
| 60 | 17 files changed, 377 insertions(+), 316 deletions(-) | ||
| 61 | create mode 100644 target/arm/tcg/arith_helper.c | ||
| 62 | rename target/arm/{op_addsub.h => tcg/op_addsub.c.inc} (100%) | ||
| 63 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | From: Anastasia Belova <abelova@astralinux.ru> | ||
| 1 | 2 | ||
| 3 | 1 << 31 is casted to uint64_t while bitwise and with val. | ||
| 4 | So this value may become 0xffffffff80000000 but only | ||
| 5 | 31th "start" bit is required. | ||
| 6 | |||
| 7 | This is not possible in practice because the MemoryRegionOps | ||
| 8 | uses the default max access size of 4 bytes and so none | ||
| 9 | of the upper bytes of val will be set, but the bitfield | ||
| 10 | extract API is clearer anyway. | ||
| 11 | |||
| 12 | Use the bitfield extract() API instead. | ||
| 13 | |||
| 14 | Found by Linux Verification Center (linuxtesting.org) with SVACE. | ||
| 15 | |||
| 16 | Signed-off-by: Anastasia Belova <abelova@astralinux.ru> | ||
| 17 | Message-id: 20241220125429.7552-1-abelova@astralinux.ru | ||
| 18 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 19 | [PMM: add clarification to commit message] | ||
| 20 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 21 | --- | ||
| 22 | hw/misc/arm_sysctl.c | 2 +- | ||
| 23 | 1 file changed, 1 insertion(+), 1 deletion(-) | ||
| 24 | |||
| 25 | diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c | ||
| 26 | index XXXXXXX..XXXXXXX 100644 | ||
| 27 | --- a/hw/misc/arm_sysctl.c | ||
| 28 | +++ b/hw/misc/arm_sysctl.c | ||
| 29 | @@ -XXX,XX +XXX,XX @@ static void arm_sysctl_write(void *opaque, hwaddr offset, | ||
| 30 | * as zero. | ||
| 31 | */ | ||
| 32 | s->sys_cfgctrl = val & ~((3 << 18) | (1 << 31)); | ||
| 33 | - if (val & (1 << 31)) { | ||
| 34 | + if (extract64(val, 31, 1)) { | ||
| 35 | /* Start bit set -- actually do something */ | ||
| 36 | unsigned int dcc = extract32(s->sys_cfgctrl, 26, 4); | ||
| 37 | unsigned int function = extract32(s->sys_cfgctrl, 20, 6); | ||
| 38 | -- | ||
| 39 | 2.34.1 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | From: Tigran Sogomonian <tsogomonian@astralinux.ru> | ||
| 1 | 2 | ||
| 3 | The value of an arithmetic expression | ||
| 4 | 'rpm * NPCM7XX_MFT_PULSE_PER_REVOLUTION' is a subject | ||
| 5 | to overflow because its operands are not cast to | ||
| 6 | a larger data type before performing arithmetic. Thus, need | ||
| 7 | to cast rpm to uint64_t. | ||
| 8 | |||
| 9 | Found by Linux Verification Center (linuxtesting.org) with SVACE. | ||
| 10 | |||
| 11 | Signed-off-by: Tigran Sogomonian <tsogomonian@astralinux.ru> | ||
| 12 | Reviewed-by: Patrick Leis <venture@google.com> | ||
| 13 | Reviewed-by: Hao Wu <wuhaotsh@google.com> | ||
| 14 | Message-id: 20241226130311.1349-1-tsogomonian@astralinux.ru | ||
| 15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 16 | --- | ||
| 17 | hw/misc/npcm7xx_mft.c | 5 +++-- | ||
| 18 | 1 file changed, 3 insertions(+), 2 deletions(-) | ||
| 19 | |||
| 20 | diff --git a/hw/misc/npcm7xx_mft.c b/hw/misc/npcm7xx_mft.c | ||
| 21 | index XXXXXXX..XXXXXXX 100644 | ||
| 22 | --- a/hw/misc/npcm7xx_mft.c | ||
| 23 | +++ b/hw/misc/npcm7xx_mft.c | ||
| 24 | @@ -XXX,XX +XXX,XX @@ static NPCM7xxMFTCaptureState npcm7xx_mft_compute_cnt( | ||
| 25 | * RPM = revolution/min. The time for one revlution (in ns) is | ||
| 26 | * MINUTE_TO_NANOSECOND / RPM. | ||
| 27 | */ | ||
| 28 | - count = clock_ns_to_ticks(clock, (60 * NANOSECONDS_PER_SECOND) / | ||
| 29 | - (rpm * NPCM7XX_MFT_PULSE_PER_REVOLUTION)); | ||
| 30 | + count = clock_ns_to_ticks(clock, | ||
| 31 | + (uint64_t)(60 * NANOSECONDS_PER_SECOND) / | ||
| 32 | + ((uint64_t)rpm * NPCM7XX_MFT_PULSE_PER_REVOLUTION)); | ||
| 33 | } | ||
| 34 | |||
| 35 | if (count > NPCM7XX_MFT_MAX_CNT) { | ||
| 36 | -- | ||
| 37 | 2.34.1 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | From: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 1 | 2 | ||
| 3 | Re-indent ASM comments adding the 'loop:' label. | ||
| 4 | |||
| 5 | Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 6 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 7 | Reviewed-by: Fabiano Rosas <farosas@suse.de> | ||
| 8 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 9 | --- | ||
| 10 | tests/qtest/boot-serial-test.c | 18 +++++++++--------- | ||
| 11 | 1 file changed, 9 insertions(+), 9 deletions(-) | ||
| 12 | |||
| 13 | diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c | ||
| 14 | index XXXXXXX..XXXXXXX 100644 | ||
| 15 | --- a/tests/qtest/boot-serial-test.c | ||
| 16 | +++ b/tests/qtest/boot-serial-test.c | ||
| 17 | @@ -XXX,XX +XXX,XX @@ static const uint8_t kernel_plml605[] = { | ||
| 18 | }; | ||
| 19 | |||
| 20 | static const uint8_t bios_raspi2[] = { | ||
| 21 | - 0x08, 0x30, 0x9f, 0xe5, /* ldr r3,[pc,#8] Get base */ | ||
| 22 | - 0x54, 0x20, 0xa0, 0xe3, /* mov r2,#'T' */ | ||
| 23 | - 0x00, 0x20, 0xc3, 0xe5, /* strb r2,[r3] */ | ||
| 24 | - 0xfb, 0xff, 0xff, 0xea, /* b loop */ | ||
| 25 | - 0x00, 0x10, 0x20, 0x3f, /* 0x3f201000 = UART0 base addr */ | ||
| 26 | + 0x08, 0x30, 0x9f, 0xe5, /* loop: ldr r3, [pc, #8] Get &UART0 */ | ||
| 27 | + 0x54, 0x20, 0xa0, 0xe3, /* mov r2, #'T' */ | ||
| 28 | + 0x00, 0x20, 0xc3, 0xe5, /* strb r2, [r3] *TXDAT = 'T' */ | ||
| 29 | + 0xfb, 0xff, 0xff, 0xea, /* b -12 (loop) */ | ||
| 30 | + 0x00, 0x10, 0x20, 0x3f, /* UART0: 0x3f201000 */ | ||
| 31 | }; | ||
| 32 | |||
| 33 | static const uint8_t kernel_aarch64[] = { | ||
| 34 | - 0x81, 0x0a, 0x80, 0x52, /* mov w1, #0x54 */ | ||
| 35 | - 0x02, 0x20, 0xa1, 0xd2, /* mov x2, #0x9000000 */ | ||
| 36 | - 0x41, 0x00, 0x00, 0x39, /* strb w1, [x2] */ | ||
| 37 | - 0xfd, 0xff, 0xff, 0x17, /* b -12 (loop) */ | ||
| 38 | + 0x81, 0x0a, 0x80, 0x52, /* loop: mov w1, #'T' */ | ||
| 39 | + 0x02, 0x20, 0xa1, 0xd2, /* mov x2, #0x9000000 Load UART0 */ | ||
| 40 | + 0x41, 0x00, 0x00, 0x39, /* strb w1, [x2] *TXDAT = 'T' */ | ||
| 41 | + 0xfd, 0xff, 0xff, 0x17, /* b -12 (loop) */ | ||
| 42 | }; | ||
| 43 | |||
| 44 | static const uint8_t kernel_nrf51[] = { | ||
| 45 | -- | ||
| 46 | 2.34.1 | ||
| 47 | |||
| 48 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | From: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 1 | 2 | ||
| 3 | Since registers are not modified, we don't need | ||
| 4 | to refill their values. Directly jump to the previous | ||
| 5 | store instruction to keep filling the TXDAT register. | ||
| 6 | |||
| 7 | The equivalent C code remains: | ||
| 8 | |||
| 9 | while (true) { | ||
| 10 | *UART_DATA = 'T'; | ||
| 11 | } | ||
| 12 | |||
| 13 | Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 14 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 15 | Reviewed-by: Fabiano Rosas <farosas@suse.de> | ||
| 16 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 17 | --- | ||
| 18 | tests/qtest/boot-serial-test.c | 12 ++++++------ | ||
| 19 | 1 file changed, 6 insertions(+), 6 deletions(-) | ||
| 20 | |||
| 21 | diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c | ||
| 22 | index XXXXXXX..XXXXXXX 100644 | ||
| 23 | --- a/tests/qtest/boot-serial-test.c | ||
| 24 | +++ b/tests/qtest/boot-serial-test.c | ||
| 25 | @@ -XXX,XX +XXX,XX @@ static const uint8_t kernel_plml605[] = { | ||
| 26 | }; | ||
| 27 | |||
| 28 | static const uint8_t bios_raspi2[] = { | ||
| 29 | - 0x08, 0x30, 0x9f, 0xe5, /* loop: ldr r3, [pc, #8] Get &UART0 */ | ||
| 30 | + 0x08, 0x30, 0x9f, 0xe5, /* ldr r3, [pc, #8] Get &UART0 */ | ||
| 31 | 0x54, 0x20, 0xa0, 0xe3, /* mov r2, #'T' */ | ||
| 32 | - 0x00, 0x20, 0xc3, 0xe5, /* strb r2, [r3] *TXDAT = 'T' */ | ||
| 33 | - 0xfb, 0xff, 0xff, 0xea, /* b -12 (loop) */ | ||
| 34 | + 0x00, 0x20, 0xc3, 0xe5, /* loop: strb r2, [r3] *TXDAT = 'T' */ | ||
| 35 | + 0xff, 0xff, 0xff, 0xea, /* b -4 (loop) */ | ||
| 36 | 0x00, 0x10, 0x20, 0x3f, /* UART0: 0x3f201000 */ | ||
| 37 | }; | ||
| 38 | |||
| 39 | static const uint8_t kernel_aarch64[] = { | ||
| 40 | - 0x81, 0x0a, 0x80, 0x52, /* loop: mov w1, #'T' */ | ||
| 41 | + 0x81, 0x0a, 0x80, 0x52, /* mov w1, #'T' */ | ||
| 42 | 0x02, 0x20, 0xa1, 0xd2, /* mov x2, #0x9000000 Load UART0 */ | ||
| 43 | - 0x41, 0x00, 0x00, 0x39, /* strb w1, [x2] *TXDAT = 'T' */ | ||
| 44 | - 0xfd, 0xff, 0xff, 0x17, /* b -12 (loop) */ | ||
| 45 | + 0x41, 0x00, 0x00, 0x39, /* loop: strb w1, [x2] *TXDAT = 'T' */ | ||
| 46 | + 0xff, 0xff, 0xff, 0x17, /* b -4 (loop) */ | ||
| 47 | }; | ||
| 48 | |||
| 49 | static const uint8_t kernel_nrf51[] = { | ||
| 50 | -- | ||
| 51 | 2.34.1 | ||
| 52 | |||
| 53 | diff view generated by jsdifflib |
| 1 | In commit ad18376b90c8101 we added an assert that the level value was | 1 | From: Philippe Mathieu-Daudé <philmd@linaro.org> |
|---|---|---|---|
| 2 | in-bounds for the array we're about to index into. However, the | ||
| 3 | assert condition is wrong -- env->config->interrupt_vector is an | ||
| 4 | array of uint32_t, so we should bounds check the index against | ||
| 5 | ARRAY_SIZE(...), not against sizeof(). | ||
| 6 | 2 | ||
| 7 | Resolves: Coverity CID 1507131 | 3 | In the next commit we are going to use a different value |
| 8 | Fixes: ad18376b90c8101 ("target/xtensa: Assert that interrupt level is within bounds") | 4 | for the $w1 register, maintaining the same $x2 value. In |
| 5 | order to keep the next commit trivial to review, set $x2 | ||
| 6 | before $w1. | ||
| 7 | |||
| 8 | Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 10 | Reviewed-by: Fabiano Rosas <farosas@suse.de> | ||
| 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
| 10 | Acked-by: Max Filippov <jcmvbkbc@gmail.com> | ||
| 11 | Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 12 | Message-id: 20240731172246.3682311-1-peter.maydell@linaro.org | ||
| 13 | --- | 12 | --- |
| 14 | target/xtensa/exc_helper.c | 2 +- | 13 | tests/qtest/boot-serial-test.c | 2 +- |
| 15 | 1 file changed, 1 insertion(+), 1 deletion(-) | 14 | 1 file changed, 1 insertion(+), 1 deletion(-) |
| 16 | 15 | ||
| 17 | diff --git a/target/xtensa/exc_helper.c b/target/xtensa/exc_helper.c | 16 | diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c |
| 18 | index XXXXXXX..XXXXXXX 100644 | 17 | index XXXXXXX..XXXXXXX 100644 |
| 19 | --- a/target/xtensa/exc_helper.c | 18 | --- a/tests/qtest/boot-serial-test.c |
| 20 | +++ b/target/xtensa/exc_helper.c | 19 | +++ b/tests/qtest/boot-serial-test.c |
| 21 | @@ -XXX,XX +XXX,XX @@ static void handle_interrupt(CPUXtensaState *env) | 20 | @@ -XXX,XX +XXX,XX @@ static const uint8_t bios_raspi2[] = { |
| 22 | 21 | }; | |
| 23 | if (level > 1) { | 22 | |
| 24 | /* env->config->nlevel check should have ensured this */ | 23 | static const uint8_t kernel_aarch64[] = { |
| 25 | - assert(level < sizeof(env->config->interrupt_vector)); | 24 | - 0x81, 0x0a, 0x80, 0x52, /* mov w1, #'T' */ |
| 26 | + assert(level < ARRAY_SIZE(env->config->interrupt_vector)); | 25 | 0x02, 0x20, 0xa1, 0xd2, /* mov x2, #0x9000000 Load UART0 */ |
| 27 | 26 | + 0x81, 0x0a, 0x80, 0x52, /* mov w1, #'T' */ | |
| 28 | env->sregs[EPC1 + level - 1] = env->pc; | 27 | 0x41, 0x00, 0x00, 0x39, /* loop: strb w1, [x2] *TXDAT = 'T' */ |
| 29 | env->sregs[EPS2 + level - 2] = env->sregs[PS]; | 28 | 0xff, 0xff, 0xff, 0x17, /* b -4 (loop) */ |
| 29 | }; | ||
| 30 | -- | 30 | -- |
| 31 | 2.34.1 | 31 | 2.34.1 |
| 32 | 32 | ||
| 33 | 33 | diff view generated by jsdifflib |
| 1 | From: Salil Mehta <salil.mehta@huawei.com> | 1 | From: Philippe Mathieu-Daudé <philmd@linaro.org> |
|---|---|---|---|
| 2 | 2 | ||
| 3 | Loop should exit prematurely on successfully finding out the parked vCPU (struct | 3 | The tests using the PL011 UART of the virt and raspi machines |
| 4 | KVMParkedVcpu) in the 'struct KVMState' maintained 'kvm_parked_vcpus' list of | 4 | weren't properly enabling the UART and its transmitter previous |
| 5 | parked vCPUs. | 5 | to sending characters. Follow the PL011 manual initialization |
| 6 | recommendation by setting the proper bits of the control register. | ||
| 6 | 7 | ||
| 7 | Fixes: Coverity CID 1558552 | 8 | Update the ASM code prefixing: |
| 8 | Fixes: 08c3286822 ("accel/kvm: Extract common KVM vCPU {creation,parking} code") | 9 | |
| 9 | Reported-by: Peter Maydell <peter.maydell@linaro.org> | 10 | *UART_CTRL = UART_ENABLE | TX_ENABLE; |
| 10 | Signed-off-by: Salil Mehta <salil.mehta@huawei.com> | 11 | |
| 11 | Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> | 12 | to: |
| 12 | Reviewed-by: Gavin Shan <gshan@redhat.com> | 13 | |
| 13 | Reviewed-by: Zhao Liu <zhao1.liu@intel.com> | 14 | while (true) { |
| 14 | Reviewed-by: Igor Mammedov <imammedo@redhat.com> | 15 | *UART_DATA = 'T'; |
| 15 | Message-id: 20240725145132.99355-1-salil.mehta@huawei.com | 16 | } |
| 16 | Suggested-by: Peter Maydell <peter.maydell@linaro.org> | 17 | |
| 17 | Message-ID: <CAFEAcA-3_d1c7XSXWkFubD-LsW5c5i95e6xxV09r2C9yGtzcdA@mail.gmail.com> | 18 | Note, since commit 51b61dd4d56 ("hw/char/pl011: Warn when using |
| 18 | Signed-off-by: Salil Mehta <salil.mehta@huawei.com> | 19 | disabled transmitter") incomplete PL011 initialization can be |
| 20 | logged using the '-d guest_errors' command line option. | ||
| 21 | |||
| 22 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 23 | Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> | ||
| 19 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 24 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
| 20 | --- | 25 | --- |
| 21 | accel/kvm/kvm-all.c | 1 + | 26 | tests/qtest/boot-serial-test.c | 7 ++++++- |
| 22 | 1 file changed, 1 insertion(+) | 27 | 1 file changed, 6 insertions(+), 1 deletion(-) |
| 23 | 28 | ||
| 24 | diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c | 29 | diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c |
| 25 | index XXXXXXX..XXXXXXX 100644 | 30 | index XXXXXXX..XXXXXXX 100644 |
| 26 | --- a/accel/kvm/kvm-all.c | 31 | --- a/tests/qtest/boot-serial-test.c |
| 27 | +++ b/accel/kvm/kvm-all.c | 32 | +++ b/tests/qtest/boot-serial-test.c |
| 28 | @@ -XXX,XX +XXX,XX @@ int kvm_unpark_vcpu(KVMState *s, unsigned long vcpu_id) | 33 | @@ -XXX,XX +XXX,XX @@ static const uint8_t kernel_plml605[] = { |
| 29 | QLIST_REMOVE(cpu, node); | 34 | }; |
| 30 | kvm_fd = cpu->kvm_fd; | 35 | |
| 31 | g_free(cpu); | 36 | static const uint8_t bios_raspi2[] = { |
| 32 | + break; | 37 | - 0x08, 0x30, 0x9f, 0xe5, /* ldr r3, [pc, #8] Get &UART0 */ |
| 33 | } | 38 | + 0x10, 0x30, 0x9f, 0xe5, /* ldr r3, [pc, #16] Get &UART0 */ |
| 34 | } | 39 | + 0x10, 0x20, 0x9f, 0xe5, /* ldr r2, [pc, #16] Get &CR */ |
| 35 | 40 | + 0xb0, 0x23, 0xc3, 0xe1, /* strh r2, [r3, #48] Set CR */ | |
| 41 | 0x54, 0x20, 0xa0, 0xe3, /* mov r2, #'T' */ | ||
| 42 | 0x00, 0x20, 0xc3, 0xe5, /* loop: strb r2, [r3] *TXDAT = 'T' */ | ||
| 43 | 0xff, 0xff, 0xff, 0xea, /* b -4 (loop) */ | ||
| 44 | 0x00, 0x10, 0x20, 0x3f, /* UART0: 0x3f201000 */ | ||
| 45 | + 0x01, 0x01, 0x00, 0x00, /* CR: 0x101 = UARTEN|TXE */ | ||
| 46 | }; | ||
| 47 | |||
| 48 | static const uint8_t kernel_aarch64[] = { | ||
| 49 | 0x02, 0x20, 0xa1, 0xd2, /* mov x2, #0x9000000 Load UART0 */ | ||
| 50 | + 0x21, 0x20, 0x80, 0x52, /* mov w1, 0x101 CR = UARTEN|TXE */ | ||
| 51 | + 0x41, 0x60, 0x00, 0x79, /* strh w1, [x2, #48] Set CR */ | ||
| 52 | 0x81, 0x0a, 0x80, 0x52, /* mov w1, #'T' */ | ||
| 53 | 0x41, 0x00, 0x00, 0x39, /* loop: strb w1, [x2] *TXDAT = 'T' */ | ||
| 54 | 0xff, 0xff, 0xff, 0x17, /* b -4 (loop) */ | ||
| 36 | -- | 55 | -- |
| 37 | 2.34.1 | 56 | 2.34.1 |
| 38 | 57 | ||
| 39 | 58 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | helper.c includes some small TCG helper functions used for mostly | ||
| 2 | arithmetic instructions. These are TCG only and there's no need for | ||
| 3 | them to be in the large and unwieldy helper.c. Move them out to | ||
| 4 | their own source file in the tcg/ subdirectory, together with the | ||
| 5 | op_addsub.h multiply-included template header that they use. | ||
| 1 | 6 | ||
| 7 | Since we are moving op_addsub.h, we take the opportunity to | ||
| 8 | give it a name which matches our convention for files which | ||
| 9 | are not true header files but which are #included from other | ||
| 10 | C files: op_addsub.c.inc. | ||
| 11 | |||
| 12 | (Ironically, this means that helper.c no longer contains | ||
| 13 | any TCG helper function definitions at all.) | ||
| 14 | |||
| 15 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 16 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 17 | Message-id: 20250110131211.2546314-1-peter.maydell@linaro.org | ||
| 18 | Reviewed-by: Alex Bennée <alex.bennee@linaro.org> | ||
| 19 | --- | ||
| 20 | target/arm/helper.c | 285 ----------------- | ||
| 21 | target/arm/tcg/arith_helper.c | 296 ++++++++++++++++++ | ||
| 22 | .../arm/{op_addsub.h => tcg/op_addsub.c.inc} | 0 | ||
| 23 | target/arm/tcg/meson.build | 1 + | ||
| 24 | 4 files changed, 297 insertions(+), 285 deletions(-) | ||
| 25 | create mode 100644 target/arm/tcg/arith_helper.c | ||
| 26 | rename target/arm/{op_addsub.h => tcg/op_addsub.c.inc} (100%) | ||
| 27 | |||
| 28 | diff --git a/target/arm/helper.c b/target/arm/helper.c | ||
| 29 | index XXXXXXX..XXXXXXX 100644 | ||
| 30 | --- a/target/arm/helper.c | ||
| 31 | +++ b/target/arm/helper.c | ||
| 32 | @@ -XXX,XX +XXX,XX @@ | ||
| 33 | #include "qemu/main-loop.h" | ||
| 34 | #include "qemu/timer.h" | ||
| 35 | #include "qemu/bitops.h" | ||
| 36 | -#include "qemu/crc32c.h" | ||
| 37 | #include "qemu/qemu-print.h" | ||
| 38 | #include "exec/exec-all.h" | ||
| 39 | #include "exec/translation-block.h" | ||
| 40 | -#include <zlib.h> /* for crc32 */ | ||
| 41 | #include "hw/irq.h" | ||
| 42 | #include "system/cpu-timers.h" | ||
| 43 | #include "system/kvm.h" | ||
| 44 | @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, | ||
| 45 | }; | ||
| 46 | } | ||
| 47 | |||
| 48 | -/* | ||
| 49 | - * Note that signed overflow is undefined in C. The following routines are | ||
| 50 | - * careful to use unsigned types where modulo arithmetic is required. | ||
| 51 | - * Failure to do so _will_ break on newer gcc. | ||
| 52 | - */ | ||
| 53 | - | ||
| 54 | -/* Signed saturating arithmetic. */ | ||
| 55 | - | ||
| 56 | -/* Perform 16-bit signed saturating addition. */ | ||
| 57 | -static inline uint16_t add16_sat(uint16_t a, uint16_t b) | ||
| 58 | -{ | ||
| 59 | - uint16_t res; | ||
| 60 | - | ||
| 61 | - res = a + b; | ||
| 62 | - if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) { | ||
| 63 | - if (a & 0x8000) { | ||
| 64 | - res = 0x8000; | ||
| 65 | - } else { | ||
| 66 | - res = 0x7fff; | ||
| 67 | - } | ||
| 68 | - } | ||
| 69 | - return res; | ||
| 70 | -} | ||
| 71 | - | ||
| 72 | -/* Perform 8-bit signed saturating addition. */ | ||
| 73 | -static inline uint8_t add8_sat(uint8_t a, uint8_t b) | ||
| 74 | -{ | ||
| 75 | - uint8_t res; | ||
| 76 | - | ||
| 77 | - res = a + b; | ||
| 78 | - if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) { | ||
| 79 | - if (a & 0x80) { | ||
| 80 | - res = 0x80; | ||
| 81 | - } else { | ||
| 82 | - res = 0x7f; | ||
| 83 | - } | ||
| 84 | - } | ||
| 85 | - return res; | ||
| 86 | -} | ||
| 87 | - | ||
| 88 | -/* Perform 16-bit signed saturating subtraction. */ | ||
| 89 | -static inline uint16_t sub16_sat(uint16_t a, uint16_t b) | ||
| 90 | -{ | ||
| 91 | - uint16_t res; | ||
| 92 | - | ||
| 93 | - res = a - b; | ||
| 94 | - if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) { | ||
| 95 | - if (a & 0x8000) { | ||
| 96 | - res = 0x8000; | ||
| 97 | - } else { | ||
| 98 | - res = 0x7fff; | ||
| 99 | - } | ||
| 100 | - } | ||
| 101 | - return res; | ||
| 102 | -} | ||
| 103 | - | ||
| 104 | -/* Perform 8-bit signed saturating subtraction. */ | ||
| 105 | -static inline uint8_t sub8_sat(uint8_t a, uint8_t b) | ||
| 106 | -{ | ||
| 107 | - uint8_t res; | ||
| 108 | - | ||
| 109 | - res = a - b; | ||
| 110 | - if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) { | ||
| 111 | - if (a & 0x80) { | ||
| 112 | - res = 0x80; | ||
| 113 | - } else { | ||
| 114 | - res = 0x7f; | ||
| 115 | - } | ||
| 116 | - } | ||
| 117 | - return res; | ||
| 118 | -} | ||
| 119 | - | ||
| 120 | -#define ADD16(a, b, n) RESULT(add16_sat(a, b), n, 16); | ||
| 121 | -#define SUB16(a, b, n) RESULT(sub16_sat(a, b), n, 16); | ||
| 122 | -#define ADD8(a, b, n) RESULT(add8_sat(a, b), n, 8); | ||
| 123 | -#define SUB8(a, b, n) RESULT(sub8_sat(a, b), n, 8); | ||
| 124 | -#define PFX q | ||
| 125 | - | ||
| 126 | -#include "op_addsub.h" | ||
| 127 | - | ||
| 128 | -/* Unsigned saturating arithmetic. */ | ||
| 129 | -static inline uint16_t add16_usat(uint16_t a, uint16_t b) | ||
| 130 | -{ | ||
| 131 | - uint16_t res; | ||
| 132 | - res = a + b; | ||
| 133 | - if (res < a) { | ||
| 134 | - res = 0xffff; | ||
| 135 | - } | ||
| 136 | - return res; | ||
| 137 | -} | ||
| 138 | - | ||
| 139 | -static inline uint16_t sub16_usat(uint16_t a, uint16_t b) | ||
| 140 | -{ | ||
| 141 | - if (a > b) { | ||
| 142 | - return a - b; | ||
| 143 | - } else { | ||
| 144 | - return 0; | ||
| 145 | - } | ||
| 146 | -} | ||
| 147 | - | ||
| 148 | -static inline uint8_t add8_usat(uint8_t a, uint8_t b) | ||
| 149 | -{ | ||
| 150 | - uint8_t res; | ||
| 151 | - res = a + b; | ||
| 152 | - if (res < a) { | ||
| 153 | - res = 0xff; | ||
| 154 | - } | ||
| 155 | - return res; | ||
| 156 | -} | ||
| 157 | - | ||
| 158 | -static inline uint8_t sub8_usat(uint8_t a, uint8_t b) | ||
| 159 | -{ | ||
| 160 | - if (a > b) { | ||
| 161 | - return a - b; | ||
| 162 | - } else { | ||
| 163 | - return 0; | ||
| 164 | - } | ||
| 165 | -} | ||
| 166 | - | ||
| 167 | -#define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16); | ||
| 168 | -#define SUB16(a, b, n) RESULT(sub16_usat(a, b), n, 16); | ||
| 169 | -#define ADD8(a, b, n) RESULT(add8_usat(a, b), n, 8); | ||
| 170 | -#define SUB8(a, b, n) RESULT(sub8_usat(a, b), n, 8); | ||
| 171 | -#define PFX uq | ||
| 172 | - | ||
| 173 | -#include "op_addsub.h" | ||
| 174 | - | ||
| 175 | -/* Signed modulo arithmetic. */ | ||
| 176 | -#define SARITH16(a, b, n, op) do { \ | ||
| 177 | - int32_t sum; \ | ||
| 178 | - sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \ | ||
| 179 | - RESULT(sum, n, 16); \ | ||
| 180 | - if (sum >= 0) \ | ||
| 181 | - ge |= 3 << (n * 2); \ | ||
| 182 | - } while (0) | ||
| 183 | - | ||
| 184 | -#define SARITH8(a, b, n, op) do { \ | ||
| 185 | - int32_t sum; \ | ||
| 186 | - sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \ | ||
| 187 | - RESULT(sum, n, 8); \ | ||
| 188 | - if (sum >= 0) \ | ||
| 189 | - ge |= 1 << n; \ | ||
| 190 | - } while (0) | ||
| 191 | - | ||
| 192 | - | ||
| 193 | -#define ADD16(a, b, n) SARITH16(a, b, n, +) | ||
| 194 | -#define SUB16(a, b, n) SARITH16(a, b, n, -) | ||
| 195 | -#define ADD8(a, b, n) SARITH8(a, b, n, +) | ||
| 196 | -#define SUB8(a, b, n) SARITH8(a, b, n, -) | ||
| 197 | -#define PFX s | ||
| 198 | -#define ARITH_GE | ||
| 199 | - | ||
| 200 | -#include "op_addsub.h" | ||
| 201 | - | ||
| 202 | -/* Unsigned modulo arithmetic. */ | ||
| 203 | -#define ADD16(a, b, n) do { \ | ||
| 204 | - uint32_t sum; \ | ||
| 205 | - sum = (uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b); \ | ||
| 206 | - RESULT(sum, n, 16); \ | ||
| 207 | - if ((sum >> 16) == 1) \ | ||
| 208 | - ge |= 3 << (n * 2); \ | ||
| 209 | - } while (0) | ||
| 210 | - | ||
| 211 | -#define ADD8(a, b, n) do { \ | ||
| 212 | - uint32_t sum; \ | ||
| 213 | - sum = (uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b); \ | ||
| 214 | - RESULT(sum, n, 8); \ | ||
| 215 | - if ((sum >> 8) == 1) \ | ||
| 216 | - ge |= 1 << n; \ | ||
| 217 | - } while (0) | ||
| 218 | - | ||
| 219 | -#define SUB16(a, b, n) do { \ | ||
| 220 | - uint32_t sum; \ | ||
| 221 | - sum = (uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b); \ | ||
| 222 | - RESULT(sum, n, 16); \ | ||
| 223 | - if ((sum >> 16) == 0) \ | ||
| 224 | - ge |= 3 << (n * 2); \ | ||
| 225 | - } while (0) | ||
| 226 | - | ||
| 227 | -#define SUB8(a, b, n) do { \ | ||
| 228 | - uint32_t sum; \ | ||
| 229 | - sum = (uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b); \ | ||
| 230 | - RESULT(sum, n, 8); \ | ||
| 231 | - if ((sum >> 8) == 0) \ | ||
| 232 | - ge |= 1 << n; \ | ||
| 233 | - } while (0) | ||
| 234 | - | ||
| 235 | -#define PFX u | ||
| 236 | -#define ARITH_GE | ||
| 237 | - | ||
| 238 | -#include "op_addsub.h" | ||
| 239 | - | ||
| 240 | -/* Halved signed arithmetic. */ | ||
| 241 | -#define ADD16(a, b, n) \ | ||
| 242 | - RESULT(((int32_t)(int16_t)(a) + (int32_t)(int16_t)(b)) >> 1, n, 16) | ||
| 243 | -#define SUB16(a, b, n) \ | ||
| 244 | - RESULT(((int32_t)(int16_t)(a) - (int32_t)(int16_t)(b)) >> 1, n, 16) | ||
| 245 | -#define ADD8(a, b, n) \ | ||
| 246 | - RESULT(((int32_t)(int8_t)(a) + (int32_t)(int8_t)(b)) >> 1, n, 8) | ||
| 247 | -#define SUB8(a, b, n) \ | ||
| 248 | - RESULT(((int32_t)(int8_t)(a) - (int32_t)(int8_t)(b)) >> 1, n, 8) | ||
| 249 | -#define PFX sh | ||
| 250 | - | ||
| 251 | -#include "op_addsub.h" | ||
| 252 | - | ||
| 253 | -/* Halved unsigned arithmetic. */ | ||
| 254 | -#define ADD16(a, b, n) \ | ||
| 255 | - RESULT(((uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b)) >> 1, n, 16) | ||
| 256 | -#define SUB16(a, b, n) \ | ||
| 257 | - RESULT(((uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b)) >> 1, n, 16) | ||
| 258 | -#define ADD8(a, b, n) \ | ||
| 259 | - RESULT(((uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b)) >> 1, n, 8) | ||
| 260 | -#define SUB8(a, b, n) \ | ||
| 261 | - RESULT(((uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b)) >> 1, n, 8) | ||
| 262 | -#define PFX uh | ||
| 263 | - | ||
| 264 | -#include "op_addsub.h" | ||
| 265 | - | ||
| 266 | -static inline uint8_t do_usad(uint8_t a, uint8_t b) | ||
| 267 | -{ | ||
| 268 | - if (a > b) { | ||
| 269 | - return a - b; | ||
| 270 | - } else { | ||
| 271 | - return b - a; | ||
| 272 | - } | ||
| 273 | -} | ||
| 274 | - | ||
| 275 | -/* Unsigned sum of absolute byte differences. */ | ||
| 276 | -uint32_t HELPER(usad8)(uint32_t a, uint32_t b) | ||
| 277 | -{ | ||
| 278 | - uint32_t sum; | ||
| 279 | - sum = do_usad(a, b); | ||
| 280 | - sum += do_usad(a >> 8, b >> 8); | ||
| 281 | - sum += do_usad(a >> 16, b >> 16); | ||
| 282 | - sum += do_usad(a >> 24, b >> 24); | ||
| 283 | - return sum; | ||
| 284 | -} | ||
| 285 | - | ||
| 286 | -/* For ARMv6 SEL instruction. */ | ||
| 287 | -uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b) | ||
| 288 | -{ | ||
| 289 | - uint32_t mask; | ||
| 290 | - | ||
| 291 | - mask = 0; | ||
| 292 | - if (flags & 1) { | ||
| 293 | - mask |= 0xff; | ||
| 294 | - } | ||
| 295 | - if (flags & 2) { | ||
| 296 | - mask |= 0xff00; | ||
| 297 | - } | ||
| 298 | - if (flags & 4) { | ||
| 299 | - mask |= 0xff0000; | ||
| 300 | - } | ||
| 301 | - if (flags & 8) { | ||
| 302 | - mask |= 0xff000000; | ||
| 303 | - } | ||
| 304 | - return (a & mask) | (b & ~mask); | ||
| 305 | -} | ||
| 306 | - | ||
| 307 | -/* | ||
| 308 | - * CRC helpers. | ||
| 309 | - * The upper bytes of val (above the number specified by 'bytes') must have | ||
| 310 | - * been zeroed out by the caller. | ||
| 311 | - */ | ||
| 312 | -uint32_t HELPER(crc32)(uint32_t acc, uint32_t val, uint32_t bytes) | ||
| 313 | -{ | ||
| 314 | - uint8_t buf[4]; | ||
| 315 | - | ||
| 316 | - stl_le_p(buf, val); | ||
| 317 | - | ||
| 318 | - /* zlib crc32 converts the accumulator and output to one's complement. */ | ||
| 319 | - return crc32(acc ^ 0xffffffff, buf, bytes) ^ 0xffffffff; | ||
| 320 | -} | ||
| 321 | - | ||
| 322 | -uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) | ||
| 323 | -{ | ||
| 324 | - uint8_t buf[4]; | ||
| 325 | - | ||
| 326 | - stl_le_p(buf, val); | ||
| 327 | - | ||
| 328 | - /* Linux crc32c converts the output to one's complement. */ | ||
| 329 | - return crc32c(acc, buf, bytes) ^ 0xffffffff; | ||
| 330 | -} | ||
| 331 | |||
| 332 | /* | ||
| 333 | * Return the exception level to which FP-disabled exceptions should | ||
| 334 | diff --git a/target/arm/tcg/arith_helper.c b/target/arm/tcg/arith_helper.c | ||
| 335 | new file mode 100644 | ||
| 336 | index XXXXXXX..XXXXXXX | ||
| 337 | --- /dev/null | ||
| 338 | +++ b/target/arm/tcg/arith_helper.c | ||
| 339 | @@ -XXX,XX +XXX,XX @@ | ||
| 340 | +/* | ||
| 341 | + * ARM generic helpers for various arithmetical operations. | ||
| 342 | + * | ||
| 343 | + * This code is licensed under the GNU GPL v2 or later. | ||
| 344 | + * | ||
| 345 | + * SPDX-License-Identifier: GPL-2.0-or-later | ||
| 346 | + */ | ||
| 347 | +#include "qemu/osdep.h" | ||
| 348 | +#include "cpu.h" | ||
| 349 | +#include "exec/helper-proto.h" | ||
| 350 | +#include "qemu/crc32c.h" | ||
| 351 | +#include <zlib.h> /* for crc32 */ | ||
| 352 | + | ||
| 353 | +/* | ||
| 354 | + * Note that signed overflow is undefined in C. The following routines are | ||
| 355 | + * careful to use unsigned types where modulo arithmetic is required. | ||
| 356 | + * Failure to do so _will_ break on newer gcc. | ||
| 357 | + */ | ||
| 358 | + | ||
| 359 | +/* Signed saturating arithmetic. */ | ||
| 360 | + | ||
| 361 | +/* Perform 16-bit signed saturating addition. */ | ||
| 362 | +static inline uint16_t add16_sat(uint16_t a, uint16_t b) | ||
| 363 | +{ | ||
| 364 | + uint16_t res; | ||
| 365 | + | ||
| 366 | + res = a + b; | ||
| 367 | + if (((res ^ a) & 0x8000) && !((a ^ b) & 0x8000)) { | ||
| 368 | + if (a & 0x8000) { | ||
| 369 | + res = 0x8000; | ||
| 370 | + } else { | ||
| 371 | + res = 0x7fff; | ||
| 372 | + } | ||
| 373 | + } | ||
| 374 | + return res; | ||
| 375 | +} | ||
| 376 | + | ||
| 377 | +/* Perform 8-bit signed saturating addition. */ | ||
| 378 | +static inline uint8_t add8_sat(uint8_t a, uint8_t b) | ||
| 379 | +{ | ||
| 380 | + uint8_t res; | ||
| 381 | + | ||
| 382 | + res = a + b; | ||
| 383 | + if (((res ^ a) & 0x80) && !((a ^ b) & 0x80)) { | ||
| 384 | + if (a & 0x80) { | ||
| 385 | + res = 0x80; | ||
| 386 | + } else { | ||
| 387 | + res = 0x7f; | ||
| 388 | + } | ||
| 389 | + } | ||
| 390 | + return res; | ||
| 391 | +} | ||
| 392 | + | ||
| 393 | +/* Perform 16-bit signed saturating subtraction. */ | ||
| 394 | +static inline uint16_t sub16_sat(uint16_t a, uint16_t b) | ||
| 395 | +{ | ||
| 396 | + uint16_t res; | ||
| 397 | + | ||
| 398 | + res = a - b; | ||
| 399 | + if (((res ^ a) & 0x8000) && ((a ^ b) & 0x8000)) { | ||
| 400 | + if (a & 0x8000) { | ||
| 401 | + res = 0x8000; | ||
| 402 | + } else { | ||
| 403 | + res = 0x7fff; | ||
| 404 | + } | ||
| 405 | + } | ||
| 406 | + return res; | ||
| 407 | +} | ||
| 408 | + | ||
| 409 | +/* Perform 8-bit signed saturating subtraction. */ | ||
| 410 | +static inline uint8_t sub8_sat(uint8_t a, uint8_t b) | ||
| 411 | +{ | ||
| 412 | + uint8_t res; | ||
| 413 | + | ||
| 414 | + res = a - b; | ||
| 415 | + if (((res ^ a) & 0x80) && ((a ^ b) & 0x80)) { | ||
| 416 | + if (a & 0x80) { | ||
| 417 | + res = 0x80; | ||
| 418 | + } else { | ||
| 419 | + res = 0x7f; | ||
| 420 | + } | ||
| 421 | + } | ||
| 422 | + return res; | ||
| 423 | +} | ||
| 424 | + | ||
| 425 | +#define ADD16(a, b, n) RESULT(add16_sat(a, b), n, 16); | ||
| 426 | +#define SUB16(a, b, n) RESULT(sub16_sat(a, b), n, 16); | ||
| 427 | +#define ADD8(a, b, n) RESULT(add8_sat(a, b), n, 8); | ||
| 428 | +#define SUB8(a, b, n) RESULT(sub8_sat(a, b), n, 8); | ||
| 429 | +#define PFX q | ||
| 430 | + | ||
| 431 | +#include "op_addsub.c.inc" | ||
| 432 | + | ||
| 433 | +/* Unsigned saturating arithmetic. */ | ||
| 434 | +static inline uint16_t add16_usat(uint16_t a, uint16_t b) | ||
| 435 | +{ | ||
| 436 | + uint16_t res; | ||
| 437 | + res = a + b; | ||
| 438 | + if (res < a) { | ||
| 439 | + res = 0xffff; | ||
| 440 | + } | ||
| 441 | + return res; | ||
| 442 | +} | ||
| 443 | + | ||
| 444 | +static inline uint16_t sub16_usat(uint16_t a, uint16_t b) | ||
| 445 | +{ | ||
| 446 | + if (a > b) { | ||
| 447 | + return a - b; | ||
| 448 | + } else { | ||
| 449 | + return 0; | ||
| 450 | + } | ||
| 451 | +} | ||
| 452 | + | ||
| 453 | +static inline uint8_t add8_usat(uint8_t a, uint8_t b) | ||
| 454 | +{ | ||
| 455 | + uint8_t res; | ||
| 456 | + res = a + b; | ||
| 457 | + if (res < a) { | ||
| 458 | + res = 0xff; | ||
| 459 | + } | ||
| 460 | + return res; | ||
| 461 | +} | ||
| 462 | + | ||
| 463 | +static inline uint8_t sub8_usat(uint8_t a, uint8_t b) | ||
| 464 | +{ | ||
| 465 | + if (a > b) { | ||
| 466 | + return a - b; | ||
| 467 | + } else { | ||
| 468 | + return 0; | ||
| 469 | + } | ||
| 470 | +} | ||
| 471 | + | ||
| 472 | +#define ADD16(a, b, n) RESULT(add16_usat(a, b), n, 16); | ||
| 473 | +#define SUB16(a, b, n) RESULT(sub16_usat(a, b), n, 16); | ||
| 474 | +#define ADD8(a, b, n) RESULT(add8_usat(a, b), n, 8); | ||
| 475 | +#define SUB8(a, b, n) RESULT(sub8_usat(a, b), n, 8); | ||
| 476 | +#define PFX uq | ||
| 477 | + | ||
| 478 | +#include "op_addsub.c.inc" | ||
| 479 | + | ||
| 480 | +/* Signed modulo arithmetic. */ | ||
| 481 | +#define SARITH16(a, b, n, op) do { \ | ||
| 482 | + int32_t sum; \ | ||
| 483 | + sum = (int32_t)(int16_t)(a) op (int32_t)(int16_t)(b); \ | ||
| 484 | + RESULT(sum, n, 16); \ | ||
| 485 | + if (sum >= 0) \ | ||
| 486 | + ge |= 3 << (n * 2); \ | ||
| 487 | + } while (0) | ||
| 488 | + | ||
| 489 | +#define SARITH8(a, b, n, op) do { \ | ||
| 490 | + int32_t sum; \ | ||
| 491 | + sum = (int32_t)(int8_t)(a) op (int32_t)(int8_t)(b); \ | ||
| 492 | + RESULT(sum, n, 8); \ | ||
| 493 | + if (sum >= 0) \ | ||
| 494 | + ge |= 1 << n; \ | ||
| 495 | + } while (0) | ||
| 496 | + | ||
| 497 | + | ||
| 498 | +#define ADD16(a, b, n) SARITH16(a, b, n, +) | ||
| 499 | +#define SUB16(a, b, n) SARITH16(a, b, n, -) | ||
| 500 | +#define ADD8(a, b, n) SARITH8(a, b, n, +) | ||
| 501 | +#define SUB8(a, b, n) SARITH8(a, b, n, -) | ||
| 502 | +#define PFX s | ||
| 503 | +#define ARITH_GE | ||
| 504 | + | ||
| 505 | +#include "op_addsub.c.inc" | ||
| 506 | + | ||
| 507 | +/* Unsigned modulo arithmetic. */ | ||
| 508 | +#define ADD16(a, b, n) do { \ | ||
| 509 | + uint32_t sum; \ | ||
| 510 | + sum = (uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b); \ | ||
| 511 | + RESULT(sum, n, 16); \ | ||
| 512 | + if ((sum >> 16) == 1) \ | ||
| 513 | + ge |= 3 << (n * 2); \ | ||
| 514 | + } while (0) | ||
| 515 | + | ||
| 516 | +#define ADD8(a, b, n) do { \ | ||
| 517 | + uint32_t sum; \ | ||
| 518 | + sum = (uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b); \ | ||
| 519 | + RESULT(sum, n, 8); \ | ||
| 520 | + if ((sum >> 8) == 1) \ | ||
| 521 | + ge |= 1 << n; \ | ||
| 522 | + } while (0) | ||
| 523 | + | ||
| 524 | +#define SUB16(a, b, n) do { \ | ||
| 525 | + uint32_t sum; \ | ||
| 526 | + sum = (uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b); \ | ||
| 527 | + RESULT(sum, n, 16); \ | ||
| 528 | + if ((sum >> 16) == 0) \ | ||
| 529 | + ge |= 3 << (n * 2); \ | ||
| 530 | + } while (0) | ||
| 531 | + | ||
| 532 | +#define SUB8(a, b, n) do { \ | ||
| 533 | + uint32_t sum; \ | ||
| 534 | + sum = (uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b); \ | ||
| 535 | + RESULT(sum, n, 8); \ | ||
| 536 | + if ((sum >> 8) == 0) \ | ||
| 537 | + ge |= 1 << n; \ | ||
| 538 | + } while (0) | ||
| 539 | + | ||
| 540 | +#define PFX u | ||
| 541 | +#define ARITH_GE | ||
| 542 | + | ||
| 543 | +#include "op_addsub.c.inc" | ||
| 544 | + | ||
| 545 | +/* Halved signed arithmetic. */ | ||
| 546 | +#define ADD16(a, b, n) \ | ||
| 547 | + RESULT(((int32_t)(int16_t)(a) + (int32_t)(int16_t)(b)) >> 1, n, 16) | ||
| 548 | +#define SUB16(a, b, n) \ | ||
| 549 | + RESULT(((int32_t)(int16_t)(a) - (int32_t)(int16_t)(b)) >> 1, n, 16) | ||
| 550 | +#define ADD8(a, b, n) \ | ||
| 551 | + RESULT(((int32_t)(int8_t)(a) + (int32_t)(int8_t)(b)) >> 1, n, 8) | ||
| 552 | +#define SUB8(a, b, n) \ | ||
| 553 | + RESULT(((int32_t)(int8_t)(a) - (int32_t)(int8_t)(b)) >> 1, n, 8) | ||
| 554 | +#define PFX sh | ||
| 555 | + | ||
| 556 | +#include "op_addsub.c.inc" | ||
| 557 | + | ||
| 558 | +/* Halved unsigned arithmetic. */ | ||
| 559 | +#define ADD16(a, b, n) \ | ||
| 560 | + RESULT(((uint32_t)(uint16_t)(a) + (uint32_t)(uint16_t)(b)) >> 1, n, 16) | ||
| 561 | +#define SUB16(a, b, n) \ | ||
| 562 | + RESULT(((uint32_t)(uint16_t)(a) - (uint32_t)(uint16_t)(b)) >> 1, n, 16) | ||
| 563 | +#define ADD8(a, b, n) \ | ||
| 564 | + RESULT(((uint32_t)(uint8_t)(a) + (uint32_t)(uint8_t)(b)) >> 1, n, 8) | ||
| 565 | +#define SUB8(a, b, n) \ | ||
| 566 | + RESULT(((uint32_t)(uint8_t)(a) - (uint32_t)(uint8_t)(b)) >> 1, n, 8) | ||
| 567 | +#define PFX uh | ||
| 568 | + | ||
| 569 | +#include "op_addsub.c.inc" | ||
| 570 | + | ||
| 571 | +static inline uint8_t do_usad(uint8_t a, uint8_t b) | ||
| 572 | +{ | ||
| 573 | + if (a > b) { | ||
| 574 | + return a - b; | ||
| 575 | + } else { | ||
| 576 | + return b - a; | ||
| 577 | + } | ||
| 578 | +} | ||
| 579 | + | ||
| 580 | +/* Unsigned sum of absolute byte differences. */ | ||
| 581 | +uint32_t HELPER(usad8)(uint32_t a, uint32_t b) | ||
| 582 | +{ | ||
| 583 | + uint32_t sum; | ||
| 584 | + sum = do_usad(a, b); | ||
| 585 | + sum += do_usad(a >> 8, b >> 8); | ||
| 586 | + sum += do_usad(a >> 16, b >> 16); | ||
| 587 | + sum += do_usad(a >> 24, b >> 24); | ||
| 588 | + return sum; | ||
| 589 | +} | ||
| 590 | + | ||
| 591 | +/* For ARMv6 SEL instruction. */ | ||
| 592 | +uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b) | ||
| 593 | +{ | ||
| 594 | + uint32_t mask; | ||
| 595 | + | ||
| 596 | + mask = 0; | ||
| 597 | + if (flags & 1) { | ||
| 598 | + mask |= 0xff; | ||
| 599 | + } | ||
| 600 | + if (flags & 2) { | ||
| 601 | + mask |= 0xff00; | ||
| 602 | + } | ||
| 603 | + if (flags & 4) { | ||
| 604 | + mask |= 0xff0000; | ||
| 605 | + } | ||
| 606 | + if (flags & 8) { | ||
| 607 | + mask |= 0xff000000; | ||
| 608 | + } | ||
| 609 | + return (a & mask) | (b & ~mask); | ||
| 610 | +} | ||
| 611 | + | ||
| 612 | +/* | ||
| 613 | + * CRC helpers. | ||
| 614 | + * The upper bytes of val (above the number specified by 'bytes') must have | ||
| 615 | + * been zeroed out by the caller. | ||
| 616 | + */ | ||
| 617 | +uint32_t HELPER(crc32)(uint32_t acc, uint32_t val, uint32_t bytes) | ||
| 618 | +{ | ||
| 619 | + uint8_t buf[4]; | ||
| 620 | + | ||
| 621 | + stl_le_p(buf, val); | ||
| 622 | + | ||
| 623 | + /* zlib crc32 converts the accumulator and output to one's complement. */ | ||
| 624 | + return crc32(acc ^ 0xffffffff, buf, bytes) ^ 0xffffffff; | ||
| 625 | +} | ||
| 626 | + | ||
| 627 | +uint32_t HELPER(crc32c)(uint32_t acc, uint32_t val, uint32_t bytes) | ||
| 628 | +{ | ||
| 629 | + uint8_t buf[4]; | ||
| 630 | + | ||
| 631 | + stl_le_p(buf, val); | ||
| 632 | + | ||
| 633 | + /* Linux crc32c converts the output to one's complement. */ | ||
| 634 | + return crc32c(acc, buf, bytes) ^ 0xffffffff; | ||
| 635 | +} | ||
| 636 | diff --git a/target/arm/op_addsub.h b/target/arm/tcg/op_addsub.c.inc | ||
| 637 | similarity index 100% | ||
| 638 | rename from target/arm/op_addsub.h | ||
| 639 | rename to target/arm/tcg/op_addsub.c.inc | ||
| 640 | diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build | ||
| 641 | index XXXXXXX..XXXXXXX 100644 | ||
| 642 | --- a/target/arm/tcg/meson.build | ||
| 643 | +++ b/target/arm/tcg/meson.build | ||
| 644 | @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( | ||
| 645 | 'tlb_helper.c', | ||
| 646 | 'vec_helper.c', | ||
| 647 | 'tlb-insns.c', | ||
| 648 | + 'arith_helper.c', | ||
| 649 | )) | ||
| 650 | |||
| 651 | arm_ss.add(when: 'TARGET_AARCH64', if_true: files( | ||
| 652 | -- | ||
| 653 | 2.34.1 | ||
| 654 | |||
| 655 | diff view generated by jsdifflib |
| 1 | The FMOPA (widening) SME instruction takes pairs of half-precision | 1 | From: Pierrick Bouvier <pierrick.bouvier@linaro.org> |
|---|---|---|---|
| 2 | floating point values, widens them to single-precision, does a | ||
| 3 | two-way dot product and accumulates the results into a | ||
| 4 | single-precision destination. We don't quite correctly handle the | ||
| 5 | FPCR bits FZ and FZ16 which control flushing of denormal inputs and | ||
| 6 | outputs. This is because at the moment we pass a single float_status | ||
| 7 | value to the helper function, which then uses that configuration for | ||
| 8 | all the fp operations it does. However, because the inputs to this | ||
| 9 | operation are float16 and the outputs are float32 we need to use the | ||
| 10 | fp_status_f16 for the float16 input widening but the normal fp_status | ||
| 11 | for everything else. Otherwise we will apply the flushing control | ||
| 12 | FPCR.FZ16 to the 32-bit output rather than the FPCR.FZ control, and | ||
| 13 | incorrectly flush a denormal output to zero when we should not (or | ||
| 14 | vice-versa). | ||
| 15 | 2 | ||
| 16 | (In commit 207d30b5fdb5b we tried to fix the FZ handling but | 3 | Before changing default pauth algorithm, we need to make sure current |
| 17 | didn't get it right, switching from "use FPCR.FZ for everything" to | 4 | default one (QARMA5) can still be selected. |
| 18 | "use FPCR.FZ16 for everything".) | ||
| 19 | 5 | ||
| 20 | Pass the CPU env to the sme_fmopa_h helper instead of an fp_status | 6 | $ qemu-system-aarch64 -cpu max,pauth-qarma5=on ... |
| 21 | pointer, and have the helper pass an extra fp_status into the | ||
| 22 | f16_dotadd() function so that we can use the right status for the | ||
| 23 | right parts of this operation. | ||
| 24 | 7 | ||
| 25 | Cc: qemu-stable@nongnu.org | 8 | Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> |
| 26 | Fixes: 207d30b5fdb5 ("target/arm: Use FPST_F16 for SME FMOPA (widening)") | 9 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> |
| 27 | Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2373 | 10 | Message-id: 20241219183211.3493974-2-pierrick.bouvier@linaro.org |
| 28 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 11 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
| 29 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 30 | --- | 12 | --- |
| 31 | target/arm/tcg/helper-sme.h | 2 +- | 13 | docs/system/arm/cpu-features.rst | 5 ++++- |
| 32 | target/arm/tcg/sme_helper.c | 39 +++++++++++++++++++++++----------- | 14 | target/arm/cpu.h | 1 + |
| 33 | target/arm/tcg/translate-sme.c | 25 ++++++++++++++++++++-- | 15 | target/arm/arm-qmp-cmds.c | 2 +- |
| 34 | 3 files changed, 51 insertions(+), 15 deletions(-) | 16 | target/arm/cpu64.c | 20 ++++++++++++++------ |
| 17 | tests/qtest/arm-cpu-features.c | 15 +++++++++++---- | ||
| 18 | 5 files changed, 31 insertions(+), 12 deletions(-) | ||
| 35 | 19 | ||
| 36 | diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h | 20 | diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst |
| 37 | index XXXXXXX..XXXXXXX 100644 | 21 | index XXXXXXX..XXXXXXX 100644 |
| 38 | --- a/target/arm/tcg/helper-sme.h | 22 | --- a/docs/system/arm/cpu-features.rst |
| 39 | +++ b/target/arm/tcg/helper-sme.h | 23 | +++ b/docs/system/arm/cpu-features.rst |
| 40 | @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) | 24 | @@ -XXX,XX +XXX,XX @@ Below is the list of TCG VCPU features and their descriptions. |
| 41 | DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) | 25 | ``pauth-qarma3`` |
| 42 | 26 | When ``pauth`` is enabled, select the architected QARMA3 algorithm. | |
| 43 | DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, | 27 | |
| 44 | - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) | 28 | -Without either ``pauth-impdef`` or ``pauth-qarma3`` enabled, |
| 45 | + void, ptr, ptr, ptr, ptr, ptr, env, i32) | 29 | +``pauth-qarma5`` |
| 46 | DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, | 30 | + When ``pauth`` is enabled, select the architected QARMA5 algorithm. |
| 47 | void, ptr, ptr, ptr, ptr, ptr, ptr, i32) | 31 | + |
| 48 | DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, | 32 | +Without ``pauth-impdef``, ``pauth-qarma3`` or ``pauth-qarma5`` enabled, |
| 49 | diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c | 33 | the architected QARMA5 algorithm is used. The architected QARMA5 |
| 34 | and QARMA3 algorithms have good cryptographic properties, but can | ||
| 35 | be quite slow to emulate. The impdef algorithm used by QEMU is | ||
| 36 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
| 50 | index XXXXXXX..XXXXXXX 100644 | 37 | index XXXXXXX..XXXXXXX 100644 |
| 51 | --- a/target/arm/tcg/sme_helper.c | 38 | --- a/target/arm/cpu.h |
| 52 | +++ b/target/arm/tcg/sme_helper.c | 39 | +++ b/target/arm/cpu.h |
| 53 | @@ -XXX,XX +XXX,XX @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) | 40 | @@ -XXX,XX +XXX,XX @@ struct ArchCPU { |
| 41 | bool prop_pauth; | ||
| 42 | bool prop_pauth_impdef; | ||
| 43 | bool prop_pauth_qarma3; | ||
| 44 | + bool prop_pauth_qarma5; | ||
| 45 | bool prop_lpa2; | ||
| 46 | |||
| 47 | /* DCZ blocksize, in log_2(words), ie low 4 bits of DCZID_EL0 */ | ||
| 48 | diff --git a/target/arm/arm-qmp-cmds.c b/target/arm/arm-qmp-cmds.c | ||
| 49 | index XXXXXXX..XXXXXXX 100644 | ||
| 50 | --- a/target/arm/arm-qmp-cmds.c | ||
| 51 | +++ b/target/arm/arm-qmp-cmds.c | ||
| 52 | @@ -XXX,XX +XXX,XX @@ static const char *cpu_model_advertised_features[] = { | ||
| 53 | "sve640", "sve768", "sve896", "sve1024", "sve1152", "sve1280", | ||
| 54 | "sve1408", "sve1536", "sve1664", "sve1792", "sve1920", "sve2048", | ||
| 55 | "kvm-no-adjvtime", "kvm-steal-time", | ||
| 56 | - "pauth", "pauth-impdef", "pauth-qarma3", | ||
| 57 | + "pauth", "pauth-impdef", "pauth-qarma3", "pauth-qarma5", | ||
| 58 | NULL | ||
| 59 | }; | ||
| 60 | |||
| 61 | diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c | ||
| 62 | index XXXXXXX..XXXXXXX 100644 | ||
| 63 | --- a/target/arm/cpu64.c | ||
| 64 | +++ b/target/arm/cpu64.c | ||
| 65 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) | ||
| 66 | } | ||
| 67 | |||
| 68 | if (cpu->prop_pauth) { | ||
| 69 | - if (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) { | ||
| 70 | + if ((cpu->prop_pauth_impdef && cpu->prop_pauth_qarma3) || | ||
| 71 | + (cpu->prop_pauth_impdef && cpu->prop_pauth_qarma5) || | ||
| 72 | + (cpu->prop_pauth_qarma3 && cpu->prop_pauth_qarma5)) { | ||
| 73 | error_setg(errp, | ||
| 74 | - "cannot enable both pauth-impdef and pauth-qarma3"); | ||
| 75 | + "cannot enable pauth-impdef, pauth-qarma3 and " | ||
| 76 | + "pauth-qarma5 at the same time"); | ||
| 77 | return; | ||
| 78 | } | ||
| 79 | |||
| 80 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) | ||
| 81 | } else if (cpu->prop_pauth_qarma3) { | ||
| 82 | isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, features); | ||
| 83 | isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 1); | ||
| 84 | - } else { | ||
| 85 | + } else { /* default is pauth-qarma5 */ | ||
| 86 | isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); | ||
| 87 | isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); | ||
| 88 | } | ||
| 89 | - } else if (cpu->prop_pauth_impdef || cpu->prop_pauth_qarma3) { | ||
| 90 | - error_setg(errp, "cannot enable pauth-impdef or " | ||
| 91 | - "pauth-qarma3 without pauth"); | ||
| 92 | + } else if (cpu->prop_pauth_impdef || | ||
| 93 | + cpu->prop_pauth_qarma3 || | ||
| 94 | + cpu->prop_pauth_qarma5) { | ||
| 95 | + error_setg(errp, "cannot enable pauth-impdef, pauth-qarma3 or " | ||
| 96 | + "pauth-qarma5 without pauth"); | ||
| 97 | error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); | ||
| 98 | } | ||
| 99 | } | ||
| 100 | @@ -XXX,XX +XXX,XX @@ static const Property arm_cpu_pauth_impdef_property = | ||
| 101 | DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false); | ||
| 102 | static const Property arm_cpu_pauth_qarma3_property = | ||
| 103 | DEFINE_PROP_BOOL("pauth-qarma3", ARMCPU, prop_pauth_qarma3, false); | ||
| 104 | +static Property arm_cpu_pauth_qarma5_property = | ||
| 105 | + DEFINE_PROP_BOOL("pauth-qarma5", ARMCPU, prop_pauth_qarma5, false); | ||
| 106 | |||
| 107 | void aarch64_add_pauth_properties(Object *obj) | ||
| 108 | { | ||
| 109 | @@ -XXX,XX +XXX,XX @@ void aarch64_add_pauth_properties(Object *obj) | ||
| 110 | } else { | ||
| 111 | qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_impdef_property); | ||
| 112 | qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma3_property); | ||
| 113 | + qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_qarma5_property); | ||
| 114 | } | ||
| 54 | } | 115 | } |
| 55 | 116 | ||
| 56 | static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, | 117 | diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c |
| 57 | - float_status *s_std, float_status *s_odd) | 118 | index XXXXXXX..XXXXXXX 100644 |
| 58 | + float_status *s_f16, float_status *s_std, | 119 | --- a/tests/qtest/arm-cpu-features.c |
| 59 | + float_status *s_odd) | 120 | +++ b/tests/qtest/arm-cpu-features.c |
| 60 | { | 121 | @@ -XXX,XX +XXX,XX @@ static void pauth_tests_default(QTestState *qts, const char *cpu_type) |
| 61 | - float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std); | 122 | assert_has_feature_enabled(qts, cpu_type, "pauth"); |
| 62 | - float64 e1c = float16_to_float64(e1 >> 16, true, s_std); | 123 | assert_has_feature_disabled(qts, cpu_type, "pauth-impdef"); |
| 63 | - float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std); | 124 | assert_has_feature_disabled(qts, cpu_type, "pauth-qarma3"); |
| 64 | - float64 e2c = float16_to_float64(e2 >> 16, true, s_std); | 125 | + assert_has_feature_disabled(qts, cpu_type, "pauth-qarma5"); |
| 65 | + /* | 126 | assert_set_feature(qts, cpu_type, "pauth", false); |
| 66 | + * We need three different float_status for different parts of this | 127 | assert_set_feature(qts, cpu_type, "pauth", true); |
| 67 | + * operation: | 128 | assert_set_feature(qts, cpu_type, "pauth-impdef", true); |
| 68 | + * - the input conversion of the float16 values must use the | 129 | assert_set_feature(qts, cpu_type, "pauth-impdef", false); |
| 69 | + * f16-specific float_status, so that the FPCR.FZ16 control is applied | 130 | assert_set_feature(qts, cpu_type, "pauth-qarma3", true); |
| 70 | + * - operations on float32 including the final accumulation must use | 131 | assert_set_feature(qts, cpu_type, "pauth-qarma3", false); |
| 71 | + * the normal float_status, so that FPCR.FZ is applied | 132 | + assert_set_feature(qts, cpu_type, "pauth-qarma5", true); |
| 72 | + * - we have pre-set-up copy of s_std which is set to round-to-odd, | 133 | + assert_set_feature(qts, cpu_type, "pauth-qarma5", false); |
| 73 | + * for the multiply (see below) | 134 | assert_error(qts, cpu_type, |
| 74 | + */ | 135 | - "cannot enable pauth-impdef or pauth-qarma3 without pauth", |
| 75 | + float64 e1r = float16_to_float64(e1 & 0xffff, true, s_f16); | 136 | + "cannot enable pauth-impdef, pauth-qarma3 or pauth-qarma5 without pauth", |
| 76 | + float64 e1c = float16_to_float64(e1 >> 16, true, s_f16); | 137 | "{ 'pauth': false, 'pauth-impdef': true }"); |
| 77 | + float64 e2r = float16_to_float64(e2 & 0xffff, true, s_f16); | 138 | assert_error(qts, cpu_type, |
| 78 | + float64 e2c = float16_to_float64(e2 >> 16, true, s_f16); | 139 | - "cannot enable pauth-impdef or pauth-qarma3 without pauth", |
| 79 | float64 t64; | 140 | + "cannot enable pauth-impdef, pauth-qarma3 or pauth-qarma5 without pauth", |
| 80 | float32 t32; | 141 | "{ 'pauth': false, 'pauth-qarma3': true }"); |
| 81 | 142 | assert_error(qts, cpu_type, | |
| 82 | @@ -XXX,XX +XXX,XX @@ static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, | 143 | - "cannot enable both pauth-impdef and pauth-qarma3", |
| 144 | - "{ 'pauth': true, 'pauth-impdef': true, 'pauth-qarma3': true }"); | ||
| 145 | + "cannot enable pauth-impdef, pauth-qarma3 or pauth-qarma5 without pauth", | ||
| 146 | + "{ 'pauth': false, 'pauth-qarma5': true }"); | ||
| 147 | + assert_error(qts, cpu_type, | ||
| 148 | + "cannot enable pauth-impdef, pauth-qarma3 and pauth-qarma5 at the same time", | ||
| 149 | + "{ 'pauth': true, 'pauth-impdef': true, 'pauth-qarma3': true," | ||
| 150 | + " 'pauth-qarma5': true }"); | ||
| 83 | } | 151 | } |
| 84 | 152 | ||
| 85 | void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, | 153 | static void test_query_cpu_model_expansion(const void *data) |
| 86 | - void *vpm, void *vst, uint32_t desc) | ||
| 87 | + void *vpm, CPUARMState *env, uint32_t desc) | ||
| 88 | { | ||
| 89 | intptr_t row, col, oprsz = simd_maxsz(desc); | ||
| 90 | uint32_t neg = simd_data(desc) * 0x80008000u; | ||
| 91 | uint16_t *pn = vpn, *pm = vpm; | ||
| 92 | - float_status fpst_odd, fpst_std; | ||
| 93 | + float_status fpst_odd, fpst_std, fpst_f16; | ||
| 94 | |||
| 95 | /* | ||
| 96 | - * Make a copy of float_status because this operation does not | ||
| 97 | - * update the cumulative fp exception status. It also produces | ||
| 98 | - * default nans. Make a second copy with round-to-odd -- see above. | ||
| 99 | + * Make copies of fp_status and fp_status_f16, because this operation | ||
| 100 | + * does not update the cumulative fp exception status. It also | ||
| 101 | + * produces default NaNs. We also need a second copy of fp_status with | ||
| 102 | + * round-to-odd -- see above. | ||
| 103 | */ | ||
| 104 | - fpst_std = *(float_status *)vst; | ||
| 105 | + fpst_f16 = env->vfp.fp_status_f16; | ||
| 106 | + fpst_std = env->vfp.fp_status; | ||
| 107 | set_default_nan_mode(true, &fpst_std); | ||
| 108 | + set_default_nan_mode(true, &fpst_f16); | ||
| 109 | fpst_odd = fpst_std; | ||
| 110 | set_float_rounding_mode(float_round_to_odd, &fpst_odd); | ||
| 111 | |||
| 112 | @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, | ||
| 113 | uint32_t m = *(uint32_t *)(vzm + H1_4(col)); | ||
| 114 | |||
| 115 | m = f16mop_adj_pair(m, pcol, 0); | ||
| 116 | - *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd); | ||
| 117 | + *a = f16_dotadd(*a, n, m, | ||
| 118 | + &fpst_f16, &fpst_std, &fpst_odd); | ||
| 119 | } | ||
| 120 | col += 4; | ||
| 121 | pcol >>= 4; | ||
| 122 | diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c | ||
| 123 | index XXXXXXX..XXXXXXX 100644 | ||
| 124 | --- a/target/arm/tcg/translate-sme.c | ||
| 125 | +++ b/target/arm/tcg/translate-sme.c | ||
| 126 | @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, | ||
| 127 | return true; | ||
| 128 | } | ||
| 129 | |||
| 130 | -TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a, | ||
| 131 | - MO_32, FPST_FPCR_F16, gen_helper_sme_fmopa_h) | ||
| 132 | +static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, | ||
| 133 | + gen_helper_gvec_5_ptr *fn) | ||
| 134 | +{ | ||
| 135 | + int svl = streaming_vec_reg_size(s); | ||
| 136 | + uint32_t desc = simd_desc(svl, svl, a->sub); | ||
| 137 | + TCGv_ptr za, zn, zm, pn, pm; | ||
| 138 | + | ||
| 139 | + if (!sme_smza_enabled_check(s)) { | ||
| 140 | + return true; | ||
| 141 | + } | ||
| 142 | + | ||
| 143 | + za = get_tile(s, esz, a->zad); | ||
| 144 | + zn = vec_full_reg_ptr(s, a->zn); | ||
| 145 | + zm = vec_full_reg_ptr(s, a->zm); | ||
| 146 | + pn = pred_full_reg_ptr(s, a->pn); | ||
| 147 | + pm = pred_full_reg_ptr(s, a->pm); | ||
| 148 | + | ||
| 149 | + fn(za, zn, zm, pn, pm, tcg_env, tcg_constant_i32(desc)); | ||
| 150 | + return true; | ||
| 151 | +} | ||
| 152 | + | ||
| 153 | +TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a, | ||
| 154 | + MO_32, gen_helper_sme_fmopa_h) | ||
| 155 | TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, | ||
| 156 | MO_32, FPST_FPCR, gen_helper_sme_fmopa_s) | ||
| 157 | TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, | ||
| 158 | -- | 154 | -- |
| 159 | 2.34.1 | 155 | 2.34.1 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | The pauth-3 test explicitly tests that a computation of the | ||
| 2 | pointer-authentication produces the expected result. This means that | ||
| 3 | it must be run with the QARMA5 algorithm. | ||
| 1 | 4 | ||
| 5 | Explicitly set the pauth algorithm when running this test, so that it | ||
| 6 | doesn't break when we change the default algorithm the 'max' CPU | ||
| 7 | uses. | ||
| 8 | |||
| 9 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 10 | --- | ||
| 11 | tests/tcg/aarch64/Makefile.softmmu-target | 3 +++ | ||
| 12 | 1 file changed, 3 insertions(+) | ||
| 13 | |||
| 14 | diff --git a/tests/tcg/aarch64/Makefile.softmmu-target b/tests/tcg/aarch64/Makefile.softmmu-target | ||
| 15 | index XXXXXXX..XXXXXXX 100644 | ||
| 16 | --- a/tests/tcg/aarch64/Makefile.softmmu-target | ||
| 17 | +++ b/tests/tcg/aarch64/Makefile.softmmu-target | ||
| 18 | @@ -XXX,XX +XXX,XX @@ EXTRA_RUNS+=run-memory-replay | ||
| 19 | |||
| 20 | ifneq ($(CROSS_CC_HAS_ARMV8_3),) | ||
| 21 | pauth-3: CFLAGS += $(CROSS_CC_HAS_ARMV8_3) | ||
| 22 | +# This test explicitly checks the output of the pauth operation so we | ||
| 23 | +# must force the use of the QARMA5 algorithm for it. | ||
| 24 | +run-pauth-3: QEMU_BASE_MACHINE=-M virt -cpu max,pauth-qarma5=on -display none | ||
| 25 | else | ||
| 26 | pauth-3: | ||
| 27 | $(call skip-test, "BUILD of $@", "missing compiler support") | ||
| 28 | -- | ||
| 29 | 2.34.1 | diff view generated by jsdifflib |
New patch | |||
|---|---|---|---|
| 1 | From: Pierrick Bouvier <pierrick.bouvier@linaro.org> | ||
| 1 | 2 | ||
| 3 | Pointer authentication on aarch64 is pretty expensive (up to 50% of | ||
| 4 | execution time) when running a virtual machine with tcg and -cpu max | ||
| 5 | (which enables pauth=on). | ||
| 6 | |||
| 7 | The advice is always: use pauth-impdef=on. | ||
| 8 | Our documentation even mentions it "by default" in | ||
| 9 | docs/system/introduction.rst. | ||
| 10 | |||
| 11 | Thus, we change the default to use impdef by default. This does not | ||
| 12 | affect kvm or hvf acceleration, since pauth algorithm used is the one | ||
| 13 | from host cpu. | ||
| 14 | |||
| 15 | This change is retro compatible, in terms of cli, with previous | ||
| 16 | versions, as the semantic of using -cpu max,pauth-impdef=on, and -cpu | ||
| 17 | max,pauth-qarma3=on is preserved. | ||
| 18 | The new option introduced in previous patch and matching old default is | ||
| 19 | -cpu max,pauth-qarma5=on. | ||
| 20 | It is retro compatible with migration as well, by defining a backcompat | ||
| 21 | property, that will use qarma5 by default for virt machine <= 9.2. | ||
| 22 | Tested by saving and restoring a vm from qemu 9.2.0 into qemu-master | ||
| 23 | (10.0) for cpus neoverse-n2 and max. | ||
| 24 | |||
| 25 | Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> | ||
| 26 | Reviewed-by: Richard Henderson <richard.henderson@linaro.org> | ||
| 27 | Message-id: 20241219183211.3493974-3-pierrick.bouvier@linaro.org | ||
| 28 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 29 | --- | ||
| 30 | docs/system/arm/cpu-features.rst | 2 +- | ||
| 31 | docs/system/introduction.rst | 2 +- | ||
| 32 | target/arm/cpu.h | 3 +++ | ||
| 33 | hw/core/machine.c | 4 +++- | ||
| 34 | target/arm/cpu.c | 2 ++ | ||
| 35 | target/arm/cpu64.c | 22 ++++++++++++++++------ | ||
| 36 | 6 files changed, 26 insertions(+), 9 deletions(-) | ||
| 37 | |||
| 38 | diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst | ||
| 39 | index XXXXXXX..XXXXXXX 100644 | ||
| 40 | --- a/docs/system/arm/cpu-features.rst | ||
| 41 | +++ b/docs/system/arm/cpu-features.rst | ||
| 42 | @@ -XXX,XX +XXX,XX @@ Below is the list of TCG VCPU features and their descriptions. | ||
| 43 | When ``pauth`` is enabled, select the architected QARMA5 algorithm. | ||
| 44 | |||
| 45 | Without ``pauth-impdef``, ``pauth-qarma3`` or ``pauth-qarma5`` enabled, | ||
| 46 | -the architected QARMA5 algorithm is used. The architected QARMA5 | ||
| 47 | +the QEMU impdef algorithm is used. The architected QARMA5 | ||
| 48 | and QARMA3 algorithms have good cryptographic properties, but can | ||
| 49 | be quite slow to emulate. The impdef algorithm used by QEMU is | ||
| 50 | non-cryptographic but significantly faster. | ||
| 51 | diff --git a/docs/system/introduction.rst b/docs/system/introduction.rst | ||
| 52 | index XXXXXXX..XXXXXXX 100644 | ||
| 53 | --- a/docs/system/introduction.rst | ||
| 54 | +++ b/docs/system/introduction.rst | ||
| 55 | @@ -XXX,XX +XXX,XX @@ would default to it anyway. | ||
| 56 | |||
| 57 | .. code:: | ||
| 58 | |||
| 59 | - -cpu max,pauth-impdef=on \ | ||
| 60 | + -cpu max \ | ||
| 61 | -smp 4 \ | ||
| 62 | -accel tcg \ | ||
| 63 | |||
| 64 | diff --git a/target/arm/cpu.h b/target/arm/cpu.h | ||
| 65 | index XXXXXXX..XXXXXXX 100644 | ||
| 66 | --- a/target/arm/cpu.h | ||
| 67 | +++ b/target/arm/cpu.h | ||
| 68 | @@ -XXX,XX +XXX,XX @@ struct ArchCPU { | ||
| 69 | /* QOM property to indicate we should use the back-compat CNTFRQ default */ | ||
| 70 | bool backcompat_cntfrq; | ||
| 71 | |||
| 72 | + /* QOM property to indicate we should use the back-compat QARMA5 default */ | ||
| 73 | + bool backcompat_pauth_default_use_qarma5; | ||
| 74 | + | ||
| 75 | /* Specify the number of cores in this CPU cluster. Used for the L2CTLR | ||
| 76 | * register. | ||
| 77 | */ | ||
| 78 | diff --git a/hw/core/machine.c b/hw/core/machine.c | ||
| 79 | index XXXXXXX..XXXXXXX 100644 | ||
| 80 | --- a/hw/core/machine.c | ||
| 81 | +++ b/hw/core/machine.c | ||
| 82 | @@ -XXX,XX +XXX,XX @@ | ||
| 83 | #include "hw/virtio/virtio-iommu.h" | ||
| 84 | #include "audio/audio.h" | ||
| 85 | |||
| 86 | -GlobalProperty hw_compat_9_2[] = {}; | ||
| 87 | +GlobalProperty hw_compat_9_2[] = { | ||
| 88 | + {"arm-cpu", "backcompat-pauth-default-use-qarma5", "true"}, | ||
| 89 | +}; | ||
| 90 | const size_t hw_compat_9_2_len = G_N_ELEMENTS(hw_compat_9_2); | ||
| 91 | |||
| 92 | GlobalProperty hw_compat_9_1[] = { | ||
| 93 | diff --git a/target/arm/cpu.c b/target/arm/cpu.c | ||
| 94 | index XXXXXXX..XXXXXXX 100644 | ||
| 95 | --- a/target/arm/cpu.c | ||
| 96 | +++ b/target/arm/cpu.c | ||
| 97 | @@ -XXX,XX +XXX,XX @@ static const Property arm_cpu_properties[] = { | ||
| 98 | DEFINE_PROP_INT32("core-count", ARMCPU, core_count, -1), | ||
| 99 | /* True to default to the backward-compat old CNTFRQ rather than 1Ghz */ | ||
| 100 | DEFINE_PROP_BOOL("backcompat-cntfrq", ARMCPU, backcompat_cntfrq, false), | ||
| 101 | + DEFINE_PROP_BOOL("backcompat-pauth-default-use-qarma5", ARMCPU, | ||
| 102 | + backcompat_pauth_default_use_qarma5, false), | ||
| 103 | }; | ||
| 104 | |||
| 105 | static const gchar *arm_gdb_arch_name(CPUState *cs) | ||
| 106 | diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c | ||
| 107 | index XXXXXXX..XXXXXXX 100644 | ||
| 108 | --- a/target/arm/cpu64.c | ||
| 109 | +++ b/target/arm/cpu64.c | ||
| 110 | @@ -XXX,XX +XXX,XX @@ void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) | ||
| 111 | return; | ||
| 112 | } | ||
| 113 | |||
| 114 | - if (cpu->prop_pauth_impdef) { | ||
| 115 | - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features); | ||
| 116 | - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1); | ||
| 117 | + bool use_default = !cpu->prop_pauth_qarma5 && | ||
| 118 | + !cpu->prop_pauth_qarma3 && | ||
| 119 | + !cpu->prop_pauth_impdef; | ||
| 120 | + | ||
| 121 | + if (cpu->prop_pauth_qarma5 || | ||
| 122 | + (use_default && | ||
| 123 | + cpu->backcompat_pauth_default_use_qarma5)) { | ||
| 124 | + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); | ||
| 125 | + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); | ||
| 126 | } else if (cpu->prop_pauth_qarma3) { | ||
| 127 | isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, APA3, features); | ||
| 128 | isar2 = FIELD_DP64(isar2, ID_AA64ISAR2, GPA3, 1); | ||
| 129 | - } else { /* default is pauth-qarma5 */ | ||
| 130 | - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, APA, features); | ||
| 131 | - isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPA, 1); | ||
| 132 | + } else if (cpu->prop_pauth_impdef || | ||
| 133 | + (use_default && | ||
| 134 | + !cpu->backcompat_pauth_default_use_qarma5)) { | ||
| 135 | + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, API, features); | ||
| 136 | + isar1 = FIELD_DP64(isar1, ID_AA64ISAR1, GPI, 1); | ||
| 137 | + } else { | ||
| 138 | + g_assert_not_reached(); | ||
| 139 | } | ||
| 140 | } else if (cpu->prop_pauth_impdef || | ||
| 141 | cpu->prop_pauth_qarma3 || | ||
| 142 | -- | ||
| 143 | 2.34.1 | diff view generated by jsdifflib |
| 1 | From: Marco Palumbi <Marco.Palumbi@tii.ae> | 1 | From: Pierrick Bouvier <pierrick.bouvier@linaro.org> |
|---|---|---|---|
| 2 | 2 | ||
| 3 | The order of the RX and TX interrupts are swapped. | 3 | Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org> |
| 4 | This commit fixes the order as per the following documents: | 4 | Message-id: 20241219183211.3493974-4-pierrick.bouvier@linaro.org |
| 5 | * https://developer.arm.com/documentation/dai0505/latest/ | 5 | [PMM: Removed a paragraph about using non-versioned models.] |
| 6 | * https://developer.arm.com/documentation/dai0521/latest/ | ||
| 7 | * https://developer.arm.com/documentation/dai0524/latest/ | ||
| 8 | * https://developer.arm.com/documentation/dai0547/latest/ | ||
| 9 | |||
| 10 | Cc: qemu-stable@nongnu.org | ||
| 11 | Signed-off-by: Marco Palumbi <Marco.Palumbi@tii.ae> | ||
| 12 | Message-id: 20240730073123.72992-1-marco@palumbi.it | ||
| 13 | Reviewed-by: Peter Maydell <peter.maydell@linaro.org> | ||
| 14 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> | 6 | Signed-off-by: Peter Maydell <peter.maydell@linaro.org> |
| 15 | --- | 7 | --- |
| 16 | hw/arm/mps2-tz.c | 6 +++--- | 8 | docs/system/arm/virt.rst | 4 ++++ |
| 17 | 1 file changed, 3 insertions(+), 3 deletions(-) | 9 | 1 file changed, 4 insertions(+) |
| 18 | 10 | ||
| 19 | diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c | 11 | diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst |
| 20 | index XXXXXXX..XXXXXXX 100644 | 12 | index XXXXXXX..XXXXXXX 100644 |
| 21 | --- a/hw/arm/mps2-tz.c | 13 | --- a/docs/system/arm/virt.rst |
| 22 | +++ b/hw/arm/mps2-tz.c | 14 | +++ b/docs/system/arm/virt.rst |
| 23 | @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, | 15 | @@ -XXX,XX +XXX,XX @@ of the 5.0 release and ``virt-5.0`` of the 5.1 release. Migration |
| 24 | const char *name, hwaddr size, | 16 | is not guaranteed to work between different QEMU releases for |
| 25 | const int *irqs, const PPCExtraData *extradata) | 17 | the non-versioned ``virt`` machine type. |
| 26 | { | 18 | |
| 27 | - /* The irq[] array is tx, rx, combined, in that order */ | 19 | +VM migration is not guaranteed when using ``-cpu max``, as features |
| 28 | + /* The irq[] array is rx, tx, combined, in that order */ | 20 | +supported may change between QEMU versions. To ensure your VM can be |
| 29 | MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); | 21 | +migrated, it is recommended to use another cpu model instead. |
| 30 | CMSDKAPBUART *uart = opaque; | 22 | + |
| 31 | int i = uart - &mms->uart[0]; | 23 | Supported devices |
| 32 | @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, | 24 | """"""""""""""""" |
| 33 | qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->apb_periph_frq); | 25 | |
| 34 | sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal); | ||
| 35 | s = SYS_BUS_DEVICE(uart); | ||
| 36 | - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); | ||
| 37 | - sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1])); | ||
| 38 | + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[1])); | ||
| 39 | + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[0])); | ||
| 40 | sysbus_connect_irq(s, 2, qdev_get_gpio_in(orgate_dev, i * 2)); | ||
| 41 | sysbus_connect_irq(s, 3, qdev_get_gpio_in(orgate_dev, i * 2 + 1)); | ||
| 42 | sysbus_connect_irq(s, 4, get_sse_irq_in(mms, irqs[2])); | ||
| 43 | -- | 26 | -- |
| 44 | 2.34.1 | 27 | 2.34.1 | diff view generated by jsdifflib |