First set of arm patches for 6.2. I have a lot more in my to-review queue still... -- PMM The following changes since commit d42685765653ec155fdf60910662f8830bdb2cef: Open 6.2 development tree (2021-08-25 10:25:12 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210825 for you to fetch changes up to 24b1a6aa43615be22c7ee66bd68ec5675f6a6a9a: docs: Document how to use gdb with unix sockets (2021-08-25 10:48:51 +0100) ---------------------------------------------------------------- target-arm queue: * More MVE emulation work * Implement M-profile trapping on division by zero * kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() * hw/char/pl011: add support for sending break * fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices * hw/dma/pl330: Add memory region to replace default * sbsa-ref: Rename SBSA_GWDT enum value * fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices * docs: Document how to use gdb with unix sockets ---------------------------------------------------------------- Eduardo Habkost (1): sbsa-ref: Rename SBSA_GWDT enum value Guenter Roeck (2): fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices Hamza Mahfooz (1): target/arm: kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() Jan Luebbe (1): hw/char/pl011: add support for sending break Peter Maydell (37): target/arm: Note that we handle VMOVL as a special case of VSHLL target/arm: Print MVE VPR in CPU dumps target/arm: Fix MVE VSLI by 0 and VSRI by <dt> target/arm: Fix signed VADDV target/arm: Fix mask handling for MVE narrowing operations target/arm: Fix 48-bit saturating shifts target/arm: Fix MVE 48-bit SQRSHRL for small right shifts target/arm: Fix calculation of LTP mask when LR is 0 target/arm: Factor out mve_eci_mask() target/arm: Fix VPT advance when ECI is non-zero target/arm: Fix VLDRB/H/W for predicated elements target/arm: Implement MVE VMULL (polynomial) target/arm: Implement MVE incrementing/decrementing dup insns target/arm: Factor out gen_vpst() target/arm: Implement MVE integer vector comparisons target/arm: Implement MVE integer vector-vs-scalar comparisons target/arm: Implement MVE VPSEL target/arm: Implement MVE VMLAS target/arm: Implement MVE shift-by-scalar target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats target/arm: Implement MVE integer min/max across vector target/arm: Implement MVE VABAV target/arm: Implement MVE narrowing moves target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn target/arm: Implement MVE VMLADAV and VMLSLDAV target/arm: Implement MVE VMLA target/arm: Implement MVE saturating doubling multiply accumulates target/arm: Implement MVE VQABS, VQNEG target/arm: Implement MVE VMAXA, VMINA target/arm: Implement MVE VMOV to/from 2 general-purpose registers target/arm: Implement MVE VPNOT target/arm: Implement MVE VCTP target/arm: Implement MVE scatter-gather insns target/arm: Implement MVE scatter-gather immediate forms target/arm: Implement MVE interleaving loads/stores target/arm: Re-indent sdiv and udiv helpers target/arm: Implement M-profile trapping on division by zero Sebastian Meyer (1): docs: Document how to use gdb with unix sockets Wen, Jianxian (1): hw/dma/pl330: Add memory region to replace default docs/system/gdb.rst | 26 +- include/hw/arm/fsl-imx7.h | 5 + target/arm/cpu.h | 1 + target/arm/helper-mve.h | 283 ++++++++++ target/arm/helper.h | 4 +- target/arm/translate-a32.h | 2 + target/arm/vec_internal.h | 11 + target/arm/mve.decode | 226 +++++++- target/arm/t32.decode | 1 + hw/arm/exynos4210.c | 3 + hw/arm/fsl-imx6ul.c | 12 + hw/arm/fsl-imx7.c | 7 + hw/arm/sbsa-ref.c | 6 +- hw/arm/xilinx_zynq.c | 3 + hw/char/pl011.c | 6 + hw/dma/pl330.c | 26 +- target/arm/cpu.c | 3 + target/arm/helper.c | 34 +- target/arm/kvm.c | 17 +- target/arm/m_helper.c | 4 + target/arm/mve_helper.c | 1254 ++++++++++++++++++++++++++++++++++++++++++-- target/arm/translate-mve.c | 877 ++++++++++++++++++++++++++++++- target/arm/translate-vfp.c | 2 +- target/arm/translate.c | 37 +- target/arm/vec_helper.c | 14 +- 25 files changed, 2746 insertions(+), 118 deletions(-) Although the architecture doesn't define it as an alias, VMOVL (vector move long) is encoded as a VSHLL with a zero shift. Add a comment in the decode file noting that we handle VMOVL as part of VSHLL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w # VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +# Note that VMOVL is encoded as "VSHLL with a zero shift count"; we +# implement it that way rather than special-casing it in the decode. VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h -- 2.20.1 Include the MVE VPR register value in the CPU dumps produced by arm_cpu_dump_state() if we are printing FPU information. This makes it easier to interpret debug logs when predication is active. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, v); } qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); + if (cpu_isar_feature(aa32_mve, cpu)) { + qemu_fprintf(f, "VPR: %08x\n", env->v7m.vpr); + } } } -- 2.20.1 In the MVE shift-and-insert insns, we special case VSLI by 0 and VSRI by <dt>. VSRI by <dt> means "don't update the destination", which is what we've implemented. However VSLI by 0 is "set destination to the input", so we don't want to use the same special-casing that we do for VSRI by <dt>. Since the generic logic gives the right answer for a shift by 0, just use that. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_S(vrshli_s, DO_VRSHLS) uint16_t mask; \ uint64_t shiftmask; \ unsigned e; \ - if (shift == 0 || shift == ESIZE * 8) { \ + if (shift == ESIZE * 8) { \ /* \ - * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ - * The generic logic would give the right answer for 0 but \ - * fails for <dt>. \ + * Only VSRI can shift by <dt>; it should mean "don't \ + * update the destination". The generic logic can't handle \ + * this because it would try to shift by an out-of-range \ + * amount, so special case it here. \ */ \ goto done; \ } \ -- 2.20.1 A cut-and-paste error meant we handled signed VADDV like unsigned VADDV; fix the type used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) return ra; \ } \ -DO_VADDV(vaddvsb, 1, uint8_t) -DO_VADDV(vaddvsh, 2, uint16_t) -DO_VADDV(vaddvsw, 4, uint32_t) +DO_VADDV(vaddvsb, 1, int8_t) +DO_VADDV(vaddvsh, 2, int16_t) +DO_VADDV(vaddvsw, 4, int32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) -- 2.20.1 In the MVE helpers for the narrowing operations (DO_VSHRN and DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for the 'top' versions of the insn. This is because the loop works over the double-sized input elements and shifts the predicate mask by that many bits each time, but when we write out the half-sized output we must look at the mask bits for whichever half of the element we are writing to. Correct this by shifting the whole mask right by ESIZE bits for the 'top' insns. This allows us also to simplify the saturation bit checking (where we had noticed that we needed to look at a different mask bit for the 'top' insn.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true) TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ TYPE r = FN(m[H##LESIZE(le)], shift); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ @@ -XXX,XX +XXX,XX @@ static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, uint16_t mask = mve_element_mask(env); \ bool qc = false; \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ bool sat = false; \ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ - qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + qc |= sat & mask & 1; \ } \ if (qc) { \ env->vfp.qc[0] = qc; \ -- 2.20.1 In do_sqrshl48_d() and do_uqrshl48_d() we got some of the edge cases wrong and failed to saturate correctly: (1) In do_sqrshl48_d() we used the same code that do_shrshl_bhs() does to obtain the saturated most-negative and most-positive 48-bit signed values for the large-shift-left case. This gives (1 << 47) for saturate-to-most-negative, but we weren't sign-extending this value to the 64-bit output as the pseudocode requires. (2) For left shifts by less than 48, we copied the "8/16 bit" code from do_sqrshl_bhs() and do_uqrshl_bhs(). This doesn't do the right thing because it assumes the C type we're working with is at least twice the number of bits we're saturating to (so that a shift left by bits-1 can't shift anything off the top of the value). This isn't true for bits == 48, so we would incorrectly return 0 rather than the most-positive value for situations like "shift (1 << 44) right by 20". Instead check for saturation by doing the shift and signextend and then testing whether shifting back left again gives the original value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } return src >> -shift; } else if (shift < 48) { - int64_t val = src << shift; - int64_t extval = sextract64(val, 0, 48); - if (!sat || val == extval) { + int64_t extval = sextract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } *sat = 1; - return (1ULL << 47) - (src >= 0); + return src >= 0 ? MAKE_64BIT_MASK(0, 47) : MAKE_64BIT_MASK(47, 17); } /* Operate on 64-bit values, but saturate at 48 bits */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, return extval; } } else if (shift < 48) { - uint64_t val = src << shift; - uint64_t extval = extract64(val, 0, 48); - if (!sat || val == extval) { + uint64_t extval = extract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { -- 2.20.1 We got an edge case wrong in the 48-bit SQRSHRL implementation: if the shift is to the right, although it always makes the result smaller than the input value it might not be within the 48-bit range the result is supposed to be if the input had some bits in [63..48] set and the shift didn't bring all of those within the [47..0] range. Handle this similarly to the way we already do for this case in do_uqrshl48_d(): extend the calculated result from 48 bits, and return that if not saturating or if it doesn't change the result; otherwise fall through to return a saturated value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, bool round, uint32_t *sat) { + int64_t val, extval; + if (shift <= -48) { /* Rounding the sign bit always produces 0. */ if (round) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } else if (shift < 0) { if (round) { src >>= -shift - 1; - return (src >> 1) + (src & 1); + val = (src >> 1) + (src & 1); + } else { + val = src >> -shift; + } + extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; } - return src >> -shift; } else if (shift < 48) { int64_t extval = sextract64(src << shift, 0, 48); if (!sat || src == (extval >> shift)) { -- 2.20.1 In mve_element_mask(), we calculate a mask for tail predication which should have a number of 1 bits based on the value of LR. However, our MAKE_64BIT_MASK() macro has undefined behaviour when passed a zero length. Special case this to give the all-zeroes mask we require. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) */ int masklen = env->regs[14] << env->v7m.ltpsize; assert(masklen <= 16); - mask &= MAKE_64BIT_MASK(0, masklen); + uint16_t ltpmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + mask &= ltpmask; } if ((env->condexec_bits & 0xf) == 0) { -- 2.20.1 In some situations we need a mask telling us which parts of the vector correspond to beats that are not being executed because of ECI, separately from the combined "which bytes are predicated away" mask. Factor this mask calculation out of mve_element_mask() into its own function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 58 ++++++++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" +static uint16_t mve_eci_mask(CPUARMState *env) +{ + /* + * Return the mask of which elements in the MVE vector correspond + * to beats being executed. The mask has 1 bits for executed lanes + * and 0 bits where ECI says this beat was already executed. + */ + int eci; + + if ((env->condexec_bits & 0xf) != 0) { + return 0xffff; + } + + eci = env->condexec_bits >> 4; + switch (eci) { + case ECI_NONE: + return 0xffff; + case ECI_A0: + return 0xfff0; + case ECI_A0A1: + return 0xff00; + case ECI_A0A1A2: + case ECI_A0A1A2B0: + return 0xf000; + default: + g_assert_not_reached(); + } +} + static uint16_t mve_element_mask(CPUARMState *env) { /* @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) mask &= ltpmask; } - if ((env->condexec_bits & 0xf) == 0) { - /* - * ECI bits indicate which beats are already executed; - * we handle this by effectively predicating them out. - */ - int eci = env->condexec_bits >> 4; - switch (eci) { - case ECI_NONE: - break; - case ECI_A0: - mask &= 0xfff0; - break; - case ECI_A0A1: - mask &= 0xff00; - break; - case ECI_A0A1A2: - case ECI_A0A1A2B0: - mask &= 0xf000; - break; - default: - g_assert_not_reached(); - } - } - + /* + * ECI bits indicate which beats are already executed; + * we handle this by effectively predicating them out. + */ + mask &= mve_eci_mask(env); return mask; } -- 2.20.1 We were not paying attention to the ECI state when advancing the VPT state. Architecturally, VPT state advance happens for every beat (see the pseudocode VPTAdvance()), so on every beat the 4 bits of VPR.P0 corresponding to the current beat are inverted if required, and at the end of beats 1 and 3 the VPR MASK fields are updated. This means that if the ECI state says we should not be executing all 4 beats then we need to skip some of the updating of the VPR that we currently do in mve_advance_vpt(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) /* Advance the VPT and ECI state if necessary */ uint32_t vpr = env->v7m.vpr; unsigned mask01, mask23; + uint16_t inv_mask; + uint16_t eci_mask = mve_eci_mask(env); if ((env->condexec_bits & 0xf) == 0) { env->condexec_bits = (env->condexec_bits == (ECI_A0A1A2B0 << 4)) ? @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) return; } + /* Invert P0 bits if needed, but only for beats we actually executed */ mask01 = FIELD_EX32(vpr, V7M_VPR, MASK01); mask23 = FIELD_EX32(vpr, V7M_VPR, MASK23); - if (mask01 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff; + /* Start by assuming we invert all bits corresponding to executed beats */ + inv_mask = eci_mask; + if (mask01 <= 8) { + /* MASK01 says don't invert low half of P0 */ + inv_mask &= ~0xff; } - if (mask23 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff00; + if (mask23 <= 8) { + /* MASK23 says don't invert high half of P0 */ + inv_mask &= ~0xff00; } - vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + vpr ^= inv_mask; + /* Only update MASK01 if beat 1 executed */ + if (eci_mask & 0xf0) { + vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + } + /* Beat 3 always executes, so update MASK23 */ vpr = FIELD_DP32(vpr, V7M_VPR, MASK23, mask23 << 1); env->v7m.vpr = vpr; } -- 2.20.1 For vector loads, predicated elements are zeroed, instead of retaining their previous values (as happens for most data processing operations). This means we need to distinguish "beat not executed due to ECI" (don't touch destination element) from "beat executed but predicated out" (zero destination element). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) env->v7m.vpr = vpr; } - +/* For loads, predicated lanes are zeroed instead of keeping their old values */ #define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) * then take an exception. \ */ \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ - if (mask & (1 << b)) { \ - d[H##ESIZE(e)] = cpu_##LDTYPE##_data_ra(env, addr, GETPC()); \ + if (eci_mask & (1 << b)) { \ + d[H##ESIZE(e)] = (mask & (1 << b)) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ } \ addr += MSIZE; \ } \ -- 2.20.1 Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the inputs are in either the low or the high half of each double-width element. The assembler for this insn indicates the size with "P8" or "P16", encoded into bit 28 as size = 0 or 1. We choose to follow the same encoding as VQDMULL and decode this into a->size as MO_16 or MO_32 indicating the size of the result elements. This then carries through to the helper function names where it then matches up with the existing pmull_h() which does an 8x8->16 operation and a new pmull_w() which does the 16x16->32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++++ target/arm/vec_internal.h | 11 +++++++++++ target/arm/mve.decode | 14 ++++++++++---- target/arm/mve_helper.c | 16 ++++++++++++++++ target/arm/translate-mve.c | 28 ++++++++++++++++++++++++++++ target/arm/vec_helper.c | 14 +++++++++++++- 6 files changed, 83 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmulltub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpth, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullptw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vqdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_internal.h +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +/* + * 8 x 8 -> 16 vector polynomial multiply where the inputs are + * in the low 8 bits of each 16-bit element +*/ +uint64_t pmull_h(uint64_t op1, uint64_t op2); +/* + * 16 x 16 -> 32 vector polynomial multiply where the inputs are + * in the low 16 bits of each 32-bit element + */ +uint64_t pmull_w(uint64_t op1, uint64_t op2); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VHADD_U 111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op VHSUB_S 111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op VHSUB_U 111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op -VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op -VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +{ + VMULLP_B 111 . 1110 0 . 11 ... 1 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op + VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op +} +{ + VMULLP_T 111 . 1110 0 . 11 ... 1 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op + VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +} VQDMULH 1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op VQRDMULH 1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_L(vmulltub, 1, 1, uint8_t, 2, uint16_t, DO_MUL) DO_2OP_L(vmulltuh, 1, 2, uint16_t, 4, uint32_t, DO_MUL) DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL) +/* + * Polynomial multiply. We can always do this generating 64 bits + * of the result at a time, so we don't need to use DO_2OP_L. + */ +#define VMULLPH_MASK 0x00ff00ff00ff00ffULL +#define VMULLPW_MASK 0x0000ffff0000ffffULL +#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK) +#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8) +#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK) +#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16) + +DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH) +DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH) +DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW) +DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW) + /* * Because the computation type is at least twice as large as required, * these work for both signed and unsigned source types. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT(DisasContext *s, arg_2op *a) return do_2op(s, a, fns[a->size]); } +static bool trans_VMULLP_B(DisasContext *s, arg_2op *a) +{ + /* + * Note that a->size indicates the output size, ie VMULL.P8 + * is the 8x8->16 operation and a->size is MO_16; VMULL.P16 + * is the 16x16->32 operation and a->size is MO_32. + */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpbh, + gen_helper_mve_vmullpbw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + +static bool trans_VMULLP_T(DisasContext *s, arg_2op *a) +{ + /* a->size is as for trans_VMULLP_B */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpth, + gen_helper_mve_vmullptw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + /* * VADC and VSBC: these perform an add-with-carry or subtract-with-carry * of the 32-bit elements in each lane of the input vectors, where the diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t expand_byte_to_half(uint64_t x) | ((x & 0xff000000) << 24); } -static uint64_t pmull_h(uint64_t op1, uint64_t op2) +uint64_t pmull_w(uint64_t op1, uint64_t op2) { uint64_t result = 0; int i; + for (i = 0; i < 16; ++i) { + uint64_t mask = (op1 & 0x0000000100000001ull) * 0xffffffff; + result ^= op2 & mask; + op1 >>= 1; + op2 <<= 1; + } + return result; +} +uint64_t pmull_h(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; for (i = 0; i < 8; ++i) { uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff; result ^= op2 & mask; -- 2.20.1 Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 12 ++++ target/arm/mve.decode | 25 ++++++++ target/arm/mve_helper.c | 63 +++++++++++++++++++ target/arm/translate-mve.c | 120 +++++++++++++++++++++++++++++++++++++ 4 files changed, 220 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_viduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_vidupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_5(mve_viwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + +DEF_HELPER_FLAGS_5(mve_vdwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + DEF_HELPER_FLAGS_3(mve_vclsb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsw, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2scalar qd qn rm size &1imm qd imm cmode op &2shift qd qm shift size +&vidup qd rn size imm +&viwdup qd rn rm size imm @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 1 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=0 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 1 1 0000 @vdup size=1 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 +# Incrementing and decrementing dup + +# VIDUP, VDDUP format immediate: 1 << (immh:imml) +%imm_vidup 7:1 0:1 !function=vidup_imm + +# VIDUP, VDDUP registers: Rm bits [3:1] from insn, bit 0 is 1; +# Rn bits [3:1] from insn, bit 0 is 0 +%vidup_rm 1:3 !function=times_2_plus_1 +%vidup_rn 17:3 !function=times_2 + +@vidup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rn=%vidup_rn &vidup +@viwdup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rm=%vidup_rm rn=%vidup_rn &viwdup +{ + VIDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 111 . @vidup + VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup +} +{ + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup +} + # multiply-add long dual accumulate # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); } + +#define DO_VIDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIWDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t wrap, \ + uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, wrap, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIDUP_ALL(OP, FN) \ + DO_VIDUP(OP##b, 1, int8_t, FN) \ + DO_VIDUP(OP##h, 2, int16_t, FN) \ + DO_VIDUP(OP##w, 4, int32_t, FN) + +#define DO_VIWDUP_ALL(OP, FN) \ + DO_VIWDUP(OP##b, 1, int8_t, FN) \ + DO_VIWDUP(OP##h, 2, int16_t, FN) \ + DO_VIWDUP(OP##w, 4, int32_t, FN) + +static uint32_t do_add_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + offset += imm; + if (offset == wrap) { + offset = 0; + } + return offset; +} + +static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + if (offset == 0) { + offset = wrap; + } + offset -= imm; + return offset; +} + +DO_VIDUP_ALL(vidup, DO_ADD) +DO_VIWDUP_ALL(viwdup, do_add_wrap) +DO_VIWDUP_ALL(vdwdup, do_sub_wrap) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" +static inline int vidup_imm(DisasContext *s, int x) +{ + return 1 << x; +} + /* Include the generated decoder */ #include "decode-mve.c.inc" @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) mve_update_eci(s); return true; } + +static bool do_vidup(DisasContext *s, arg_vidup *a, MVEGenVIDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn; + + /* + * Vector increment/decrement with wrap and duplicate (VIDUP, VDDUP). + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->size == MO_64) { + /* size 0b11 is another encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + fn(rn, cpu_env, qd, rn, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool do_viwdup(DisasContext *s, arg_viwdup *a, MVEGenVIWDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn, rm; + + /* + * Vector increment/decrement with wrap and duplicate (VIWDUp, VDWDUP) + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. Rm specifies a point where + * the count wraps back around to 0. The updated offset is written back + * to Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (!fn || a->rm == 13 || a->rm == 15) { + /* + * size 0b11 is another encoding; Rm == 13 is UNPREDICTABLE; + * Rm == 13 is VIWDUP, VDWDUP. + */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + rm = load_reg(s, a->rm); + fn(rn, cpu_env, qd, rn, rm, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +static bool trans_VIDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VDDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + /* VDDUP is just like VIDUP but with a negative immediate */ + a->imm = -a->imm; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VIWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_viwdupb, + gen_helper_mve_viwduph, + gen_helper_mve_viwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} + +static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_vdwdupb, + gen_helper_mve_vdwduph, + gen_helper_mve_vdwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} -- 2.20.1 Factor out the "generate code to update VPR.MASK01/MASK23" part of trans_VPST(); we are going to want to reuse it for the VPT insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } -static bool trans_VPST(DisasContext *s, arg_VPST *a) +static void gen_vpst(DisasContext *s, uint32_t mask) { - TCGv_i32 vpr; - - /* mask == 0 is a "related encoding" */ - if (!dc_isar_feature(aa32_mve, s) || !a->mask) { - return false; - } - if (!mve_eci_check(s) || !vfp_access_check(s)) { - return true; - } /* * Set the VPR mask fields. We take advantage of MASK01 and MASK23 * being adjacent fields in the register. * - * This insn is not predicated, but it is subject to beat-wise + * Updating the masks is not predicated, but it is subject to beat-wise * execution, and the mask is updated on the odd-numbered beats. * So if PSR.ECI says we should skip beat 1, we mustn't update the * 01 mask field. */ - vpr = load_cpu_field(v7m.vpr); + TCGv_i32 vpr = load_cpu_field(v7m.vpr); switch (s->eci) { case ECI_NONE: case ECI_A0: /* Update both 01 and 23 fields */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask | (a->mask << 4)), + tcg_constant_i32(mask | (mask << 4)), R_V7M_VPR_MASK01_SHIFT, R_V7M_VPR_MASK01_LENGTH + R_V7M_VPR_MASK23_LENGTH); break; @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) case ECI_A0A1A2B0: /* Update only the 23 mask field */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask), + tcg_constant_i32(mask), R_V7M_VPR_MASK23_SHIFT, R_V7M_VPR_MASK23_LENGTH); break; default: g_assert_not_reached(); } store_cpu_field(vpr, v7m.vpr); +} + +static bool trans_VPST(DisasContext *s, arg_VPST *a) +{ + /* mask == 0 is a "related encoding" */ + if (!dc_isar_feature(aa32_mve, s) || !a->mask) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + gen_vpst(s, a->mask); mve_update_and_store_eci(s); return true; } -- 2.20.1 Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 ++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++- target/arm/mve_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 47 ++++++++++++++++++++++++++++++++ 4 files changed, 152 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpeqb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpneb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpnew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpcsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmphib, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphih, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphiw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgeb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpltb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpltw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgtb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2shift qd qm shift size &vidup qd rn size imm &viwdup qd rn rm size imm +&vcmp qm qn size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +# Vector comparison; 4-bit Qm but 3-bit Qn +%mask_22_13 22:1 13:3 +@vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar } # Predicate operations -%mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # Logical immediate operations (1 reg and modified-immediate) @@ -XXX,XX +XXX,XX @@ VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd + +# Comparisons. We expand out the conditions which are split across +# encodings T1, T2, T3 and the fc bits. These include VPT, which is +# effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. +VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp +VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) DO_VIDUP_ALL(vidup, DO_ADD) DO_VIWDUP_ALL(viwdup, do_add_wrap) DO_VIWDUP_ALL(vdwdup, do_sub_wrap) + +/* + * Vector comparison. + * P0 bits for non-executed beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed beats (where mask is 0) are 0. + * P0 bits otherwise are updated with the results of the comparisons. + * We must also keep unchanged the MASK fields at the top of v7m.vpr. + */ +#define DO_VCMP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)]); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) + +#define DO_EQ(N, M) ((N) == (M)) +#define DO_NE(N, M) ((N) != (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_GE(N, M) ((N) >= (M)) +#define DO_LT(N, M) ((N) < (M)) +#define DO_GT(N, M) ((N) > (M)) +#define DO_LE(N, M) ((N) <= (M)) + +DO_VCMP_U(vcmpeq, DO_EQ) +DO_VCMP_U(vcmpne, DO_NE) +DO_VCMP_U(vcmpcs, DO_GE) +DO_VCMP_U(vcmphi, DO_GT) +DO_VCMP_S(vcmpge, DO_GE) +DO_VCMP_S(vcmplt, DO_LT) +DO_VCMP_S(vcmpgt, DO_GT) +DO_VCMP_S(vcmple, DO_LE) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); +typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) }; return do_viwdup(s, a, fns[a->size]); } + +static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) +{ + TCGv_ptr qn, qm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qn, qm); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + +#define DO_VCMP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vcmp(s, a, fns[a->size]); \ + } + +DO_VCMP(VCMPEQ, vcmpeq) +DO_VCMP(VCMPNE, vcmpne) +DO_VCMP(VCMPCS, vcmpcs) +DO_VCMP(VCMPHI, vcmphi) +DO_VCMP(VCMPGE, vcmpge) +DO_VCMP(VCMPLT, vcmplt) +DO_VCMP(VCMPGT, vcmpgt) +DO_VCMP(VCMPLE, vcmple) -- 2.20.1 Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++++--- target/arm/mve_helper.c | 44 +++++++++++++++++++++++++++++++------- target/arm/translate-mve.c | 43 +++++++++++++++++++++++++++++++++++++ 4 files changed, 126 insertions(+), 11 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vidup qd rn size imm &viwdup qd rn rm size imm &vcmp qm qn size mask +&vcmp_scalar qn rm size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 +@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 # Vector loads and stores @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar rdahi=%rdahi rdalo=%rdalo } -# Predicate operations -VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but @@ -XXX,XX +XXX,XX @@ VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp + +{ + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar +} +VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar +VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar +VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar +VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar +VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar +VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VIWDUP_ALL(vdwdup, do_sub_wrap) mve_advance_vpt(env); \ } -#define DO_VCMP_S(OP, FN) \ - DO_VCMP(OP##b, 1, int8_t, FN) \ - DO_VCMP(OP##h, 2, int16_t, FN) \ - DO_VCMP(OP##w, 4, int32_t, FN) +#define DO_VCMP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], (TYPE)rm); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } -#define DO_VCMP_U(OP, FN) \ - DO_VCMP(OP##b, 1, uint8_t, FN) \ - DO_VCMP(OP##h, 2, uint16_t, FN) \ - DO_VCMP(OP##w, 4, uint32_t, FN) +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, int8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, int16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, uint8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, uint16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, uint32_t, FN) #define DO_EQ(N, M) ((N) == (M)) #define DO_NE(N, M) ((N) != (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); +typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) return true; } +static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a, + MVEGenScalarCmpFn *fn) +{ + TCGv_ptr qn; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + if (a->rm == 15) { + /* Encoding Rm=0b1111 means "constant zero" */ + rm = tcg_constant_i32(0); + } else { + rm = load_reg(s, a->rm); + } + fn(cpu_env, qn, rm); + tcg_temp_free_ptr(qn); + tcg_temp_free_i32(rm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + #define DO_VCMP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) NULL, \ }; \ return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + gen_helper_mve_##FN##_scalarb, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalarw, \ + NULL, \ + }; \ + return do_vcmp_scalar(s, a, fns[a->size]); \ } DO_VCMP(VCMPEQ, vcmpeq) -- 2.20.1 Implement the MVE VPSEL insn, which sets each byte of the destination vector Qd to the byte from either Qn or Qm depending on the value of the corresponding bit in VPR.P0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 7 +++++-- target/arm/mve_helper.c | 19 +++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 28 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp -VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp -VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +{ + VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz + VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp + VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +} VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMP_S(vcmpge, DO_GE) DO_VCMP_S(vcmplt, DO_LT) DO_VCMP_S(vcmpgt, DO_GT) DO_VCMP_S(vcmple, DO_LE) + +void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) +{ + /* + * Qd[n] = VPR.P0[n] ? Qn[n] : Qm[n] + * but note that whether bytes are written to Qd is still subject + * to (all forms of) predication in the usual way. + */ + uint64_t *d = vd, *n = vn, *m = vm; + uint16_t mask = mve_element_mask(env); + uint16_t p0 = FIELD_EX32(env->v7m.vpr, V7M_VPR, P0); + unsigned e; + for (e = 0; e < 16 / 8; e++, mask >>= 8, p0 >>= 8) { + uint64_t r = m[H8(e)]; + mergemask(&r, n[H8(e)], p0); + mergemask(&d[H8(e)], r, mask); + } + mve_advance_vpt(env); +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_LOGIC(VORR, gen_helper_mve_vorr) DO_LOGIC(VORN, gen_helper_mve_vorn) DO_LOGIC(VEOR, gen_helper_mve_veor) +DO_LOGIC(VPSEL, gen_helper_mve_vpsel) + #define DO_2OP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2op *a) \ { \ -- 2.20.1 Implement the MVE VMLAS insn, which multiplies a vector by a vector and adds a scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 1 + 4 files changed, 34 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +# The U bit (28) is don't-care because it does not affect the result +VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +/* "accumulating" version where FN takes d as well as n and m */ +#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask); \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) DO_2OP_SCALAR(OP##h, 2, int16_t, FN) \ DO_2OP_SCALAR(OP##w, 4, int32_t, FN) +#define DO_2OP_ACC_SCALAR_U(OP, FN) \ + DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN) \ + DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN) \ + DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN) + DO_2OP_SCALAR_U(vadd_scalar, DO_ADD) DO_2OP_SCALAR_U(vsub_scalar, DO_SUB) DO_2OP_SCALAR_U(vmul_scalar, DO_MUL) @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by vector plus scalar */ +#define DO_VMLAS(D, N, M) ((N) * (D) + (M)) + +DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS) + /* * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 +++++++ target/arm/mve.decode | 23 ++++++++++++++++--- target/arm/mve_helper.c | 2 ++ target/arm/translate-mve.c | 46 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 76 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &viwdup qd rn rm size imm &vcmp qm qn size mask &vcmp_scalar qn rm size mask +&shl_scalar qda rm size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +@shl_scalar .... .... .... size:2 .. .... .... .... rm:4 &shl_scalar qda=%qd + # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 @@ -XXX,XX +XXX,XX @@ VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_no VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar -VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar + +{ + VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + +{ + VSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar @@ -XXX,XX +XXX,XX @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar - VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +DO_2SHIFT_SAT_U(vqrshli_u, DO_UQRSHL_OP) +DO_2SHIFT_SAT_S(vqrshli_s, DO_SQRSHL_OP) /* Shift-and-insert; we always work with 64 bits at a time */ #define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, + MVEGenTwoOpShiftFn *fn) +{ + TCGv_ptr qda; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qda) || + a->rm == 13 || a->rm == 15 || !fn) { + /* Rm cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qda = mve_qreg_ptr(a->qda); + rm = load_reg(s, a->rm); + fn(cpu_env, qda, qda, rm); + tcg_temp_free_ptr(qda); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_shl_scalar *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift_scalar(s, a, fns[a->size]); \ + } + +DO_2SHIFT_SCALAR(VSHL_S_scalar, vshli_s) +DO_2SHIFT_SCALAR(VSHL_U_scalar, vshli_u) +DO_2SHIFT_SCALAR(VRSHL_S_scalar, vrshli_s) +DO_2SHIFT_SCALAR(VRSHL_U_scalar, vrshli_u) +DO_2SHIFT_SCALAR(VQSHL_S_scalar, vqshli_s) +DO_2SHIFT_SCALAR(VQSHL_U_scalar, vqshli_u) +DO_2SHIFT_SCALAR(VQRSHL_S_scalar, vqrshli_s) +DO_2SHIFT_SCALAR(VQRSHL_U_scalar, vqrshli_u) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 &vmlaldav rdahi rdalo size qn qm x a -@vmlaldav .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav -@vmlaldav_nosz .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav +VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLSLDAV 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav +VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_nosz +VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz # Scalar operations -- 2.20.1 Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++++ target/arm/mve.decode | 18 +++++++++-- target/arm/mve_helper.c | 66 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 48 +++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp qm qn size mask &vcmp_scalar qn rm size mask &shl_scalar qda rm size +&vmaxv qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +{ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} + +{ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +/* + * Vector max/min across vector. Unlike VADDV, we must + * read ra as the element size, not its full width. + * We work with int64_t internally for simplicity. + */ +#define DO_VMAXMINV(OP, ESIZE, TYPE, RATYPE, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + int64_t ra = (RATYPE)ra_in; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + ra = FN(ra, m[H##ESIZE(e)]); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define DO_VMAXMINV_U(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, uint8_t, uint8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, uint16_t, uint16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, uint32_t, uint32_t, FN) +#define DO_VMAXMINV_S(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, int8_t, int8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, int16_t, int16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, int32_t, int32_t, FN) + +/* + * Helpers for max and min of absolute values across vector: + * note that we only take the absolute value of 'm', not 'n' + */ +static int64_t do_maxa(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MAX(n, m); +} + +static int64_t do_mina(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MIN(n, m); +} + +DO_VMAXMINV_S(vmaxvs, DO_MAX) +DO_VMAXMINV_U(vmaxvu, DO_MAX) +DO_VMAXMINV_S(vminvs, DO_MIN) +DO_VMAXMINV_U(vminvu, DO_MIN) +/* + * VMAXAV, VMINAV treat the general purpose input as unsigned + * and the vector elements as signed. + */ +DO_VMAXMINV(vmaxavb, 1, int8_t, uint8_t, do_maxa) +DO_VMAXMINV(vmaxavh, 2, int16_t, uint16_t, do_maxa) +DO_VMAXMINV(vmaxavw, 4, int32_t, uint32_t, do_maxa) +DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) +DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) +DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPGE, vcmpge) DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) + +static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) +{ + /* + * MIN/MAX operations across a vector: compute the min or + * max of the initial value in a general purpose register + * and all the elements in the vector, and store it back + * into the general purpose register. + */ + TCGv_ptr qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VMAXV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV(VMAXV_S, vmaxvs) +DO_VMAXV(VMAXV_U, vmaxvu) +DO_VMAXV(VMAXAV, vmaxav) +DO_VMAXV(VMINV_S, vminvs) +DO_VMAXV(VMINV_U, vminvu) +DO_VMAXV(VMINAV, vminav) -- 2.20.1 Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 7 +++++++ target/arm/mve.decode | 6 ++++++ target/arm/mve_helper.c | 26 +++++++++++++++++++++++ target/arm/translate-mve.c | 43 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vabavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp_scalar qn rm size mask &shl_scalar qda rm size &vmaxv qm rda size +&vabav qn qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar rdahi=%rdahi rdalo=%rdalo } +@vabav .... .... .. size:2 .... rda:4 .... .... .... &vabav qn=%qn qm=%qm + +VABAV_S 111 0 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav +VABAV_U 111 1 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav + # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) +#define DO_VABAV(OP, ESIZE, TYPE) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm, *n = vn; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + int64_t n0 = n[H##ESIZE(e)]; \ + int64_t m0 = m[H##ESIZE(e)]; \ + uint32_t r = n0 >= m0 ? (n0 - m0) : (m0 - n0); \ + ra += r; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } + +DO_VABAV(vabavsb, 1, int8_t) +DO_VABAV(vabavsh, 2, int16_t) +DO_VABAV(vabavsw, 4, int32_t) +DO_VABAV(vabavub, 1, uint8_t) +DO_VABAV(vabavuh, 2, uint16_t) +DO_VABAV(vabavuw, 4, uint32_t) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ DO_VMAXV(VMAXAV, vmaxav) DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) + +static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) +{ + /* Absolute difference accumulated across vector */ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qm | a->qn) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + qn = mve_qreg_ptr(a->qn); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + tcg_temp_free_ptr(qn); + mve_update_eci(s); + return true; +} + +#define DO_VABAV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vabav *a) \ + { \ + static MVEGenVABAVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vabav(s, a, fns[a->size]); \ + } + +DO_VABAV(VABAV_S, vabavs) +DO_VABAV(VABAV_U, vabavu) -- 2.20.1 Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++ target/arm/mve.decode | 12 ++++++ target/arm/mve_helper.c | 78 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 22 +++++++++++ 4 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovunbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovuntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsh, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbuh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntuh, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vand, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vbic, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNB 111 1 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BU 111 1 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNT 111 1 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TU 111 1 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) +#define DO_VMOVN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], \ + m[H##LESIZE(le)], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMOVN(vmovnbb, false, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnbh, false, 2, uint16_t, 4, uint32_t) +DO_VMOVN(vmovntb, true, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnth, true, 2, uint16_t, 4, uint32_t) + +#define DO_VMOVN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VMOVN_SAT_UB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VMOVN_SAT_UH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VMOVN_SAT_SB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VMOVN_SAT_SH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_VQMOVN_SB(N, SATP) \ + do_sat_bhs((int64_t)(N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQMOVN_UB(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT8_MAX, SATP) +#define DO_VQMOVUN_B(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT8_MAX, SATP) + +#define DO_VQMOVN_SH(N, SATP) \ + do_sat_bhs((int64_t)(N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQMOVN_UH(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT16_MAX, SATP) +#define DO_VQMOVUN_H(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT16_MAX, SATP) + +DO_VMOVN_SAT_SB(vqmovnbsb, vqmovntsb, DO_VQMOVN_SB) +DO_VMOVN_SAT_SH(vqmovnbsh, vqmovntsh, DO_VQMOVN_SH) +DO_VMOVN_SAT_UB(vqmovnbub, vqmovntub, DO_VQMOVN_UB) +DO_VMOVN_SAT_UH(vqmovnbuh, vqmovntuh, DO_VQMOVN_UH) +DO_VMOVN_SAT_SB(vqmovunbb, vqmovuntb, DO_VQMOVUN_B) +DO_VMOVN_SAT_SH(vqmovunbh, vqmovunth, DO_VQMOVUN_H) + uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, uint32_t shift) { diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +/* Narrowing moves: only size 0 and 1 are valid */ +#define DO_VMOVN(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + NULL, \ + NULL, \ + }; \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VMOVN(VMOVNB, vmovnb) +DO_VMOVN(VMOVNT, vmovnt) +DO_VMOVN(VQMOVUNB, vqmovunb) +DO_VMOVN(VQMOVUNT, vqmovunt) +DO_VMOVN(VQMOVN_BS, vqmovnbs) +DO_VMOVN(VQMOVN_TS, vqmovnts) +DO_VMOVN(VQMOVN_BU, vqmovnbu) +DO_VMOVN(VQMOVN_TU, vqmovntu) + static bool trans_VREV16(DisasContext *s, arg_1op *a) { static MVEGenOneOpFn * const fns[] = { -- 2.20.1 The MVEGenDualAccOpFn is a bit misnamed, since it is used for the "long dual accumulate" operations that use a 64-bit accumulator. Rename it to MVEGenLongDualAccOpFn so we can use the former name for the 32-bit accumulator insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenLongDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) } static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, - MVEGenDualAccOpFn *fn) + MVEGenLongDualAccOpFn *fn) { TCGv_ptr qn, qm; TCGv_i64 rda; @@ -XXX,XX +XXX,XX @@ static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavsh, gen_helper_mve_vmlaldavxsh }, { gen_helper_mve_vmlaldavsw, gen_helper_mve_vmlaldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavuh, NULL }, { gen_helper_mve_vmlaldavuw, NULL }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh }, { gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhsw, gen_helper_mve_vrmlaldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhuw, NULL, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlsldavhsw, gen_helper_mve_vrmlsldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); -- 2.20.1 Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 17 ++++++++++ target/arm/mve.decode | 33 +++++++++++++++++--- target/arm/mve_helper.c | 41 ++++++++++++++++++++++++ target/arm/translate-mve.c | 64 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrmlaldavhuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vmladavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vmladavsxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvub, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 %size_16 16:1 !function=plus_1 &vmlaldav rdahi rdalo size qn qm x a +&vmladav rda size qn qm x a @vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav @vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +@vmladav .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=%size_16 &vmladav +@vmladav_nosz .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=0 &vmladav -VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +{ + VMLADAV_S 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} +{ + VMLADAV_U 1111 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} + +{ + VMLSDAV 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 1 @vmladav + VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +} + +{ + VMLSDAV 1111 1110 1111 ... 0 ... . 1110 . 0 . 0 ... 1 @vmladav_nosz + VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz +} + +VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz +VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } -VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz - # Scalar operations VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavxsh, 2, int16_t, true, +=, -=) DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) +/* + * Multiply add dual accumulate ops + */ +#define DO_DAV(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t a) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *n = vn, *m = vm; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + if (e & 1) { \ + a ODDACC \ + n[H##ESIZE(e - 1 * XCHG)] * m[H##ESIZE(e)]; \ + } else { \ + a EVENACC \ + n[H##ESIZE(e + 1 * XCHG)] * m[H##ESIZE(e)]; \ + } \ + } \ + } \ + mve_advance_vpt(env); \ + return a; \ + } + +#define DO_DAV_S(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, int8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, int16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, int32_t, XCHG, EVENACC, ODDACC) + +#define DO_DAV_U(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, uint8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, uint16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, uint32_t, XCHG, EVENACC, ODDACC) + +DO_DAV_S(vmladavs, false, +=, +=) +DO_DAV_U(vmladavu, false, +=, +=) +DO_DAV_S(vmlsdav, false, +=, -=) +DO_DAV_S(vmladavsx, true, +=, +=) +DO_DAV_S(vmlsdavx, true, +=, -=) + /* * Rounding multiply add long dual accumulate high. In the pseudocode * this is implemented with a 72-bit internal accumulator value of which diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TC typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } +static bool do_dual_acc(DisasContext *s, arg_vmladav *a, MVEGenDualAccOpFn *fn) +{ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qn) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current rda value, not 0. + */ + if (a->a || mve_skip_first_beat(s)) { + rda = load_reg(s, a->rda); + } else { + rda = tcg_const_i32(0); + } + + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + + mve_update_eci(s); + return true; +} + +#define DO_DUAL_ACC(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmladav *a) \ + { \ + static MVEGenDualAccOpFn * const fns[4][2] = { \ + { gen_helper_mve_##FN##b, gen_helper_mve_##FN##xb }, \ + { gen_helper_mve_##FN##h, gen_helper_mve_##FN##xh }, \ + { gen_helper_mve_##FN##w, gen_helper_mve_##FN##xw }, \ + { NULL, NULL }, \ + }; \ + return do_dual_acc(s, a, fns[a->size][a->x]); \ + } + +DO_DUAL_ACC(VMLADAV_S, vmladavs) +DO_DUAL_ACC(VMLSDAV, vmlsdav) + +static bool trans_VMLADAV_U(DisasContext *s, arg_vmladav *a) +{ + static MVEGenDualAccOpFn * const fns[4][2] = { + { gen_helper_mve_vmladavub, NULL }, + { gen_helper_mve_vmladavuh, NULL }, + { gen_helper_mve_vmladavuw, NULL }, + { NULL, NULL }, + }; + return do_dual_acc(s, a, fns[a->size][a->x]); +} + static void gen_vpst(DisasContext *s, uint32_t mask) { /* -- 2.20.1 Implement the MVE VMLA insn, which multiplies a vector by a scalar and accumulates into another vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 1 + target/arm/mve_helper.c | 5 +++++ target/arm/translate-mve.c | 1 + 4 files changed, 11 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlab, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlah, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlaw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # The U bit (28) is don't-care because it does not affect the result +VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar # Vector add across vector diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by scalar plus vector */ +#define DO_VMLA(D, N, M) ((N) * (M) + (D)) + +DO_2OP_ACC_SCALAR_U(vmla, DO_VMLA) + /* Vector by vector plus scalar */ #define DO_VMLAS(D, N, M) ((N) * (D) + (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) -- 2.20.1 Implement the MVE saturating doubling multiply accumulate insns VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply, double, add the accumulator shifted by the element size, possibly round, saturate to twice the element size, then take the high half of the result. The *MLAH insns do vector * scalar + vector, and the *MLASH insns do vector * vector + scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 16 +++++++ target/arm/mve.decode | 5 ++ target/arm/mve_helper.c | 95 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 4 ++ 4 files changed, 120 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar +VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar +VQDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 110 .... @2scalar +VQDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 110 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +#define DO_2OP_SAT_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m, &sat), \ + mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +static int8_t do_vqdmlah_b(int8_t a, int8_t b, int8_t c, int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 8) + (round << 7); + return do_sat_bhw(r, INT16_MIN, INT16_MAX, sat) >> 8; +} + +static int16_t do_vqdmlah_h(int16_t a, int16_t b, int16_t c, + int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 16) + (round << 15); + return do_sat_bhw(r, INT32_MIN, INT32_MAX, sat) >> 16; +} + +static int32_t do_vqdmlah_w(int32_t a, int32_t b, int32_t c, + int round, bool *sat) +{ + /* + * Architecturally we should do the entire add, double, round + * and then check for saturation. We do three saturating adds, + * but we need to be careful about the order. If the first + * m1 + m2 saturates then it's impossible for the *2+rc to + * bring it back into the non-saturated range. However, if + * m1 + m2 is negative then it's possible that doing the doubling + * would take the intermediate result below INT64_MAX and the + * addition of the rounding constant then brings it back in range. + * So we add half the rounding constant and half the "c << esize" + * before doubling rather than adding the rounding constant after + * the doubling. + */ + int64_t m1 = (int64_t)a * b; + int64_t m2 = (int64_t)c << 31; + int64_t r; + if (sadd64_overflow(m1, m2, &r) || + sadd64_overflow(r, (round << 30), &r) || + sadd64_overflow(r, r, &r)) { + *sat = true; + return r < 0 ? INT32_MAX : INT32_MIN; + } + return r >> 32; +} + +/* + * The *MLAH insns are vector * scalar + vector; + * the *MLASH insns are vector * vector + scalar + */ +#define DO_VQDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 0, S) +#define DO_VQDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 0, S) +#define DO_VQDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 0, S) +#define DO_VQRDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 1, S) +#define DO_VQRDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 1, S) +#define DO_VQRDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 1, S) + +#define DO_VQDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 0, S) +#define DO_VQDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 0, S) +#define DO_VQDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 0, S) +#define DO_VQRDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 1, S) +#define DO_VQRDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 1, S) +#define DO_VQRDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 1, S) + +DO_2OP_SAT_ACC_SCALAR(vqdmlahb, 1, int8_t, DO_VQDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlahh, 2, int16_t, DO_VQDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlahw, 4, int32_t, DO_VQDMLAH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahb, 1, int8_t, DO_VQRDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahh, 2, int16_t, DO_VQRDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahw, 4, int32_t, DO_VQRDMLAH_W) + +DO_2OP_SAT_ACC_SCALAR(vqdmlashb, 1, int8_t, DO_VQDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlashh, 2, int16_t, DO_VQDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlashw, 4, int32_t, DO_VQDMLASH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashb, 1, int8_t, DO_VQRDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashh, 2, int16_t, DO_VQRDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashw, 4, int32_t, DO_VQRDMLASH_W) + /* Vector by scalar plus vector */ #define DO_VMLA(D, N, M) ((N) * (M) + (D)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) +DO_2OP_SCALAR(VQDMLAH, vqdmlah) +DO_2OP_SCALAR(VQRDMLAH, vqrdmlah) +DO_2OP_SCALAR(VQDMLASH, vqdmlash) +DO_2OP_SCALAR(VQRDMLASH, vqrdmlash) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE 1-operand saturating operations VQABS and VQNEG. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 50 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VABS_fp 1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 ... 0 @1op VNEG 1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op VNEG_fp 1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op +VQABS 1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op +VQNEG 1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op + &vdup qd rt size # Qd is in the fields usually named Qn @vdup .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) } mve_advance_vpt(env); } + +#define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], FN(m[H##ESIZE(e)], &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VQABS_B(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQABS_H(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQABS_W(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT32_MIN, INT32_MAX, SATP) + +#define DO_VQNEG_B(N, SATP) do_sat_bhs(-(int64_t)N, INT8_MIN, INT8_MAX, SATP) +#define DO_VQNEG_H(N, SATP) do_sat_bhs(-(int64_t)N, INT16_MIN, INT16_MAX, SATP) +#define DO_VQNEG_W(N, SATP) do_sat_bhs(-(int64_t)N, INT32_MIN, INT32_MAX, SATP) + +DO_1OP_SAT(vqabsb, 1, int8_t, DO_VQABS_B) +DO_1OP_SAT(vqabsh, 2, int16_t, DO_VQABS_H) +DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) + +DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) +DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) +DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLZ, vclz) DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +DO_1OP(VQABS, vqabs) +DO_1OP(VQNEG, vqneg) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 4 ++++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 40 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMAXA 111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VMINA 111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) + +/* + * VMAXA, VMINA: vd is unsigned; vm is signed, and we take its + * absolute value; we then do an unsigned comparison. + */ +#define DO_VMAXMINA(OP, ESIZE, STYPE, UTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + UTYPE *d = vd; \ + STYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + UTYPE r = DO_ABS(m[H##ESIZE(e)]); \ + r = FN(d[H##ESIZE(e)], r); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMAXMINA(vmaxab, 1, int8_t, uint8_t, DO_MAX) +DO_VMAXMINA(vmaxah, 2, int16_t, uint16_t, DO_MAX) +DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) +DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) +DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) +DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) DO_1OP(VQABS, vqabs) DO_1OP(VQNEG, vqneg) +DO_1OP(VMAXA, vmaxa) +DO_1OP(VMINA, vmina) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMOV forms that move data between 2 general-purpose registers and 2 32-bit lanes in a vector register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a32.h | 1 + target/arm/mve.decode | 4 ++ target/arm/translate-mve.c | 85 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-vfp.c | 2 +- 4 files changed, 91 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); static inline TCGv_i32 load_cpu_offset(int offset) { diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# Moves between 2 32-bit vector lanes and 2 general purpose registers +VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd +VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd + # Vector 2-op VAND 1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz VBIC 1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) DO_VABAV(VABAV_S, vabavs) DO_VABAV(VABAV_U, vabavu) + +static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two 32-bit vector lanes to two general-purpose registers. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 || + a->rt == a->rt2) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg index to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd, a->idx, MO_32); + store_reg(s, a->rt, tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd + 1, a->idx, MO_32); + store_reg(s, a->rt2, tmp); + } + + mve_update_and_store_eci(s); + return true; +} + +static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two general-purpose registers to two 32-bit vector lanes. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg idx to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = load_reg(s, a->rt); + write_neon_element32(tmp, vd, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = load_reg(s, a->rt2); + write_neon_element32(tmp, vd + 1, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + + mve_update_and_store_eci(s); + return true; +} diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } -static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) { /* * In a CPU with MVE, the VMOV (vector lane to general-purpose register) -- 2.20.1 Implement the MVE VPNOT insn, which inverts the bits in VPR.P0 (subject to both predication and to beatwise execution). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 1 + target/arm/mve.decode | 1 + target/arm/mve_helper.c | 17 +++++++++++++++++ target/arm/translate-mve.c | 19 +++++++++++++++++++ 4 files changed, 38 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) mve_advance_vpt(env); } +void HELPER(mve_vpnot)(CPUARMState *env) +{ + /* + * P0 bits for unexecuted beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed bits (where mask is 0) are 0. + * P0 bits otherwise are inverted. + * (This is the same logic as VCMP.) + * This insn is itself subject to predication and to beat-wise execution, + * and after it executes VPT state advances in the usual way. + */ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t beatpred = ~env->v7m.vpr & mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (beatpred & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) return true; } +static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a) +{ + /* + * Invert the predicate in VPR.P0. We have call out to + * a helper because this insn itself is beatwise and can + * be predicated. + */ + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + gen_helper_mve_vpnot(cpu_env); + mve_update_eci(s); + return true; +} + static bool trans_VADDV(DisasContext *s, arg_VADDV *a) { /* VADDV: vector add across vector */ -- 2.20.1 Implement the MVE VCTP insn, which sets the VPR.P0 predicate bits so as to predicate any element at index Rn or greater is predicated. As with VPNOT, this insn itself is predicable and subject to beatwise execution. The calculation of the mask is the same as is used to determine ltpmask in mve_element_mask(), but we precalculate masklen in generated code to avoid having to have 4 helpers specialized by size. We put the decode line in with the low-overhead-loop insns in t32.decode because it's logically part of that collection of insn patterns, even though it is an MVE only insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/translate-a32.h | 1 + target/arm/t32.decode | 1 + target/arm/mve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-mve.c | 2 +- target/arm/translate.c | 33 +++++++++++++++++++++++++++++++++ 6 files changed, 58 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) +DEF_HELPER_FLAGS_2(mve_vctp, TCG_CALL_NO_WG, void, env, i32) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ long neon_element_offset(int reg, int element, MemOp memop); void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); +void mve_update_eci(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ BL 1111 0. .......... 11.1 ............ @branch24 # This is DLSTP DLS 1111 0 0000 0 size:2 rn:4 1110 0000 0000 0001 } + VCTP 1111 0 0000 0 size:2 rn:4 1110 1000 0000 0001 ] } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpnot)(CPUARMState *env) mve_advance_vpt(env); } +/* + * VCTP: P0 unexecuted bits unchanged, predicated bits zeroed, + * otherwise set according to value of Rn. The calculation of + * newmask here works in the same way as the calculation of the + * ltpmask in mve_element_mask(), but we have pre-calculated + * the masklen in the generated code. + */ +void HELPER(mve_vctp)(CPUARMState *env, uint32_t masklen) +{ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t newmask; + + assert(masklen <= 16); + newmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + newmask &= mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (newmask & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ bool mve_eci_check(DisasContext *s) } } -static void mve_update_eci(DisasContext *s) +void mve_update_eci(DisasContext *s) { /* * The helper function will always update the CPUState field, diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_LCTP(DisasContext *s, arg_LCTP *a) return true; } +static bool trans_VCTP(DisasContext *s, arg_VCTP *a) +{ + /* + * M-profile Create Vector Tail Predicate. This insn is itself + * predicated and is subject to beatwise execution. + */ + TCGv_i32 rn_shifted, masklen; + + if (!dc_isar_feature(aa32_mve, s) || a->rn == 13 || a->rn == 15) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * We pre-calculate the mask length here to avoid having + * to have multiple helpers specialized for size. + * We pass the helper "rn <= (1 << (4 - size)) ? (rn << size) : 16". + */ + rn_shifted = tcg_temp_new_i32(); + masklen = load_reg(s, a->rn); + tcg_gen_shli_i32(rn_shifted, masklen, a->size); + tcg_gen_movcond_i32(TCG_COND_LEU, masklen, + masklen, tcg_constant_i32(1 << (4 - a->size)), + rn_shifted, tcg_constant_i32(16)); + gen_helper_mve_vctp(cpu_env, masklen); + tcg_temp_free_i32(masklen); + tcg_temp_free_i32(rn_shifted); + mve_update_eci(s); + return true; +} static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half) { -- 2.20.1 Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++ target/arm/mve.decode | 12 ++++ target/arm/mve_helper.c | 129 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 97 ++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrb_h, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrb_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &shl_scalar qda rm size &vmaxv qm rda size &vabav qn qm rda size +&vldst_sg qd qm rn size msize os + +# scatter-gather memory size is in bits 6:4 +%sg_msize 6:1 4:1 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr +@vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ + qd=%qd qm=%qm msize=%sg_msize + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# gather loads/scatter stores +VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR +/* + * Gather loads/scatter stores. Here each element of Qm specifies + * an offset to use from the base register Rm. In the _os_ versions + * that offset is scaled by the element size. + * For loads, predicated lanes are zeroed instead of retaining + * their previous values. + */ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + OFFTYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + d[H##ESIZE(e)] = (mask & 1) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +/* We know here TYPE is unsigned so always the same as the offset type */ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + if (mask & 1) { \ + cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +/* + * 64-bit accesses are slightly different: they are done as two 32-bit + * accesses, controlled by the predicate mask for the relevant beat, + * and with a single 32-bit offset in the first of the two Qm elements. + * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + */ +#define DO_VLDR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSTR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + if (mask & 1) { \ + cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +#define ADDR_ADD(BASE, OFFSET) ((BASE) + (OFFSET)) +#define ADDR_ADD_OSH(BASE, OFFSET) ((BASE) + ((OFFSET) << 1)) +#define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) +#define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) + +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) + +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) + +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) + +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) + +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) #include "decode-mve.c.inc" typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) +static bool do_ldst_sg(DisasContext *s, arg_vldst_sg *a, MVEGenLdStSGFn fn) +{ + TCGv_i32 addr; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn || a->rn == 15) { + /* Rn case is UNPREDICTABLE */ + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + addr = load_reg(s, a->rn); + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, addr); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + tcg_temp_free_i32(addr); + mve_update_eci(s); + return true; +} + +/* + * The naming scheme here is "vldrb_sg_sh == in-memory byte loads + * signextended to halfword elements in register". _os_ indicates that + * the offsets in Qm should be scaled by the element size. + */ +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +/* VLDRB/VSTRB (ie msize 1) with OS=1 is UNPREDICTABLE; we UNDEF */ +static bool trans_VLDR_S_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { NULL, F(vldrb_sg_sh), F(vldrb_sg_sw), NULL }, + { NULL, NULL, F(vldrh_sg_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, NULL, F(vldrh_sg_os_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VLDR_U_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vldrb_sg_ub), F(vldrb_sg_uh), F(vldrb_sg_uw), NULL }, + { NULL, F(vldrh_sg_uh), F(vldrh_sg_uw), NULL }, + { NULL, NULL, F(vldrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vldrh_sg_os_uh), F(vldrh_sg_os_uw), NULL }, + { NULL, NULL, F(vldrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_os_ud) } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vstrb_sg_ub), F(vstrb_sg_uh), F(vstrb_sg_uw), NULL }, + { NULL, F(vstrh_sg_uh), F(vstrh_sg_uw), NULL }, + { NULL, NULL, F(vstrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vstrh_sg_os_uh), F(vstrh_sg_os_uw), NULL }, + { NULL, NULL, F(vstrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_os_ud) } + } + }; + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++ target/arm/mve.decode | 10 +++++ target/arm/mve_helper.c | 91 ++++++++++++++++++++++++-------------- target/arm/translate-mve.c | 72 ++++++++++++++++++++++++++++++ 4 files changed, 146 insertions(+), 32 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vmaxv qm rda size &vabav qn qm rda size &vldst_sg qd qm rn size msize os +&vldst_sg_imm qd qm a w imm # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ qd=%qd qm=%qm msize=%sg_msize +# Qm is in the fields usually labeled Qn +@vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ + qd=%qd qm=%qn + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg +VLDRW_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm +VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ TYPE *d = vd; \ TYPE *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ } \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * accesses, controlled by the predicate mask for the relevant beat, * and with a single 32-bit offset in the first of the two Qm elements. * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + * Address writeback happens on the odd beats and updates the address + * stored in the even-beat element. */ -#define DO_VLDR64_SG(OP, ADDRFN) \ +#define DO_VLDR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } -#define DO_VSTR64_SG(OP, ADDRFN) \ +#define DO_VSTR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ uint32_t *d = vd; \ uint32_t *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ } \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) -DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) -DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) -DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) + +DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* * The mergemask(D, R, M) macro performs the operation "*D = R" but diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) #undef F +static bool do_ldst_sg_imm(DisasContext *s, arg_vldst_sg_imm *a, + MVEGenLdStSGFn *fn, unsigned msize) +{ + uint32_t offset; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + offset = a->imm << msize; + if (!a->a) { + offset = -offset; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(offset)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +static bool trans_VLDRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrw_sg_uw, + gen_helper_mve_vldrw_sg_wb_uw, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VLDRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrd_sg_ud, + gen_helper_mve_vldrd_sg_wb_ud, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + +static bool trans_VSTRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrw_sg_uw, + gen_helper_mve_vstrw_sg_wb_uw, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrd_sg_ud, + gen_helper_mve_vstrd_sg_wb_ud, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE interleaving load/store functions VLD2, VLD4, VST2 and VST4. VLD2 loads 16 bytes of data from memory and writes to 2 consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes to 4 consecutive Qregs. The 'pattern' field in the encoding determines the offset into memory which is accessed and also which elements in the Qregs are written to. (The intention is that a sequence of four consecutive VLD4 with different pattern values performs a complete de-interleaving load of 64 bytes into all elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 48 ++++++ target/arm/mve.decode | 11 ++ target/arm/mve_helper.c | 342 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 94 ++++++++++ 4 files changed, 495 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vld20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43w, TCG_CALL_NO_WG, void, env, i32, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vabav qn qm rda size &vldst_sg qd qm rn size msize os &vldst_sg_imm qd qm a w imm +&vldst_il qd rn size pat w # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ qd=%qd qm=%qn +# Deinterleaving load/interleaving store +@vldst_il .... .... .. w:1 . rn:4 .... ... size:2 pat:2 ..... &vldst_il \ + qd=%qd + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm +# deinterleaving loads/interleaving stores +VLD2 1111 1100 1 .. 1 .... ... 1 111 .. .. 00000 @vldst_il +VLD4 1111 1100 1 .. 1 .... ... 1 111 .. .. 00001 @vldst_il +VST2 1111 1100 1 .. 0 .... ... 1 111 .. .. 00000 @vldst_il +VST4 1111 1100 1 .. 0 .... ... 1 111 .. .. 00001 @vldst_il + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) +/* + * Deinterleaving loads/interleaving stores. + * + * For these helpers we are passed the index of the first Qreg + * (VLD2/VST2 will also access Qn+1, VLD4/VST4 access Qn .. Qn+3) + * and the value of the base address register Rn. + * The helpers are specialized for pattern and element size, so + * for instance vld42h is VLD4 with pattern 2, element size MO_16. + * + * These insns are beatwise but not predicated, so we must honour ECI, + * but need not look at mve_element_mask(). + * + * The pseudocode implements these insns with multiple memory accesses + * of the element size, but rules R_VVVG and R_FXDM permit us to make + * one 32-bit memory access per beat. + */ +#define DO_VLD4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H1(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H2(off[beat])] = data; \ + data >>= 16; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + qd[H2(off[beat])] = data; \ + } \ + } + +#define DO_VLD4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H4(off[beat] >> 2)] = data; \ + } \ + } + +DO_VLD4B(vld40b, 0, 1, 10, 11) +DO_VLD4B(vld41b, 2, 3, 12, 13) +DO_VLD4B(vld42b, 4, 5, 14, 15) +DO_VLD4B(vld43b, 6, 7, 8, 9) + +DO_VLD4H(vld40h, 0, 5) +DO_VLD4H(vld41h, 1, 6) +DO_VLD4H(vld42h, 2, 7) +DO_VLD4H(vld43h, 3, 4) + +DO_VLD4W(vld40w, 0, 1, 10, 11) +DO_VLD4W(vld41w, 2, 3, 12, 13) +DO_VLD4W(vld42w, 4, 5, 14, 15) +DO_VLD4W(vld43w, 6, 7, 8, 9) + +#define DO_VLD2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + qd[H1(off[beat] + (e >> 1))] = data; \ + } \ + } \ + } + +#define DO_VLD2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 2; e++, data >>= 16) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H2(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + qd[H4(off[beat] >> 3)] = data; \ + } \ + } + +DO_VLD2B(vld20b, 0, 2, 12, 14) +DO_VLD2B(vld21b, 4, 6, 8, 10) + +DO_VLD2H(vld20h, 0, 1, 6, 7) +DO_VLD2H(vld21h, 2, 3, 4, 5) + +DO_VLD2W(vld20w, 0, 4, 24, 28) +DO_VLD2W(vld21w, 8, 12, 16, 20) + +#define DO_VST4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 8) | qd[H1(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H2(off[beat])]; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + data |= qd[H2(off[beat])] << 16; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H4(off[beat] >> 2)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST4B(vst40b, 0, 1, 10, 11) +DO_VST4B(vst41b, 2, 3, 12, 13) +DO_VST4B(vst42b, 4, 5, 14, 15) +DO_VST4B(vst43b, 6, 7, 8, 9) + +DO_VST4H(vst40h, 0, 5) +DO_VST4H(vst41h, 1, 6) +DO_VST4H(vst42h, 2, 7) +DO_VST4H(vst43h, 3, 4) + +DO_VST4W(vst40w, 0, 1, 10, 11) +DO_VST4W(vst41w, 2, 3, 12, 13) +DO_VST4W(vst42w, 4, 5, 14, 15) +DO_VST4W(vst43w, 6, 7, 8, 9) + +#define DO_VST2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 1; e >= 0; e--) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 16) | qd[H2(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + data = qd[H4(off[beat] >> 3)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST2B(vst20b, 0, 2, 12, 14) +DO_VST2B(vst21b, 4, 6, 8, 10) + +DO_VST2H(vst20h, 0, 1, 6, 7) +DO_VST2H(vst21h, 2, 3, 4, 5) + +DO_VST2W(vst20w, 0, 4, 24, 28) +DO_VST2W(vst21w, 8, 12, 16, 20) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStIlFn(TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) return do_ldst_sg_imm(s, a, fns[a->w], MO_64); } +static bool do_vldst_il(DisasContext *s, arg_vldst_il *a, MVEGenLdStIlFn *fn, + int addrinc) +{ + TCGv_i32 rn; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn || (a->rn == 13 && a->w) || a->rn == 15) { + /* Variously UNPREDICTABLE or UNDEF or related-encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + rn = load_reg(s, a->rn); + /* + * We pass the index of Qd, not a pointer, because the helper must + * access multiple Q registers starting at Qd and working up. + */ + fn(cpu_env, tcg_constant_i32(a->qd), rn); + + if (a->w) { + tcg_gen_addi_i32(rn, rn, addrinc); + store_reg(s, a->rn, rn); + } else { + tcg_temp_free_i32(rn); + } + mve_update_and_store_eci(s); + return true; +} + +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +static bool trans_VLD2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld20b), F(vld20h), F(vld20w), NULL, }, + { F(vld21b), F(vld21h), F(vld21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VLD4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld40b), F(vld40h), F(vld40w), NULL, }, + { F(vld41b), F(vld41h), F(vld41w), NULL, }, + { F(vld42b), F(vld42h), F(vld42w), NULL, }, + { F(vld43b), F(vld43h), F(vld43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +static bool trans_VST2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst20b), F(vst20h), F(vst20w), NULL, }, + { F(vst21b), F(vst21h), F(vst21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VST4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst40b), F(vst40h), F(vst40w), NULL, }, + { F(vst41b), F(vst41h), F(vst41w), NULL, }, + { F(vst42b), F(vst42h), F(vst42w), NULL, }, + { F(vst43b), F(vst43h), F(vst43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 We're about to make a code change to the sdiv and udiv helper functions, so first fix their indentation and coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-2-peter.maydell@linaro.org --- target/arm/helper.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) int32_t HELPER(sdiv)(int32_t num, int32_t den) { - if (den == 0) - return 0; - if (num == INT_MIN && den == -1) - return INT_MIN; + if (den == 0) { + return 0; + } + if (num == INT_MIN && den == -1) { + return INT_MIN; + } return num / den; } uint32_t HELPER(udiv)(uint32_t num, uint32_t den) { - if (den == 0) - return 0; + if (den == 0) { + return 0; + } return num / den; } -- 2.20.1 Unlike A-profile, for M-profile the UDIV and SDIV insns can be configured to raise an exception on division by zero, using the CCR DIV_0_TRP bit. Implement support for setting this bit by making the helper functions raise the appropriate exception. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-3-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/helper.h | 4 ++-- target/arm/helper.c | 19 +++++++++++++++++-- target/arm/m_helper.c | 4 ++++ target/arm/translate.c | 4 ++-- 5 files changed, 26 insertions(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ #define EXCP_LAZYFP 20 /* v7M fault during lazy FP stacking */ #define EXCP_LSERR 21 /* v8M LSERR SecureFault */ #define EXCP_UNALIGNED 22 /* v7M UNALIGNED UsageFault */ +#define EXCP_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(add_saturate, i32, env, i32, i32) DEF_HELPER_3(sub_saturate, i32, env, i32, i32) DEF_HELPER_3(add_usaturate, i32, env, i32, i32) DEF_HELPER_3(sub_usaturate, i32, env, i32, i32) -DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_NO_RWG_SE, s32, s32, s32) -DEF_HELPER_FLAGS_2(udiv, TCG_CALL_NO_RWG_SE, i32, i32, i32) +DEF_HELPER_FLAGS_3(sdiv, TCG_CALL_NO_RWG, s32, env, s32, s32) +DEF_HELPER_FLAGS_3(udiv, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_1(rbit, TCG_CALL_NO_RWG_SE, i32, i32) #define PAS_OP(pfx) \ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sxtb16)(uint32_t x) return res; } +static void handle_possible_div0_trap(CPUARMState *env, uintptr_t ra) +{ + /* + * Take a division-by-zero exception if necessary; otherwise return + * to get the usual non-trapping division behaviour (result of 0) + */ + if (arm_feature(env, ARM_FEATURE_M) + && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_DIV_0_TRP_MASK)) { + raise_exception_ra(env, EXCP_DIVBYZERO, 0, 1, ra); + } +} + uint32_t HELPER(uxtb16)(uint32_t x) { uint32_t res; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) return res; } -int32_t HELPER(sdiv)(int32_t num, int32_t den) +int32_t HELPER(sdiv)(CPUARMState *env, int32_t num, int32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } if (num == INT_MIN && den == -1) { @@ -XXX,XX +XXX,XX @@ int32_t HELPER(sdiv)(int32_t num, int32_t den) return num / den; } -uint32_t HELPER(udiv)(uint32_t num, uint32_t den) +uint32_t HELPER(udiv)(CPUARMState *env, uint32_t num, uint32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } return num / den; @@ -XXX,XX +XXX,XX @@ void arm_log_exception(int idx) [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", [EXCP_LSERR] = "v8M LSERR UsageFault", [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", + [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_UNALIGNED_MASK; break; + case EXCP_DIVBYZERO: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_DIVBYZERO_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool op_div(DisasContext *s, arg_rrr *a, bool u) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (u) { - gen_helper_udiv(t1, t1, t2); + gen_helper_udiv(t1, cpu_env, t1, t2); } else { - gen_helper_sdiv(t1, t1, t2); + gen_helper_sdiv(t1, cpu_env, t1, t2); } tcg_temp_free_i32(t2); store_reg(s, a->rd, t1); -- 2.20.1 From: Hamza Mahfooz <someguy@effective-light.com> As per commit 5626f8c6d468 ("rcu: Add automatically released rcu_read_lock variants"), RCU_READ_LOCK_GUARD() should be used instead of rcu_read_{un}lock(). Signed-off-by: Hamza Mahfooz <someguy@effective-light.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20210727235201.11491-1-someguy@effective-light.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, hwaddr xlat, len, doorbell_gpa; MemoryRegionSection mrs; MemoryRegion *mr; - int ret = 1; if (as == &address_space_memory) { return 0; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, /* MSI doorbell address is translated by an IOMMU */ - rcu_read_lock(); + RCU_READ_LOCK_GUARD(); + mr = address_space_translate(as, address, &xlat, &len, true, MEMTXATTRS_UNSPECIFIED); + if (!mr) { - goto unlock; + return 1; } + mrs = memory_region_find(mr, xlat, 1); + if (!mrs.mr) { - goto unlock; + return 1; } doorbell_gpa = mrs.offset_within_address_space; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, trace_kvm_arm_fixup_msi_route(address, doorbell_gpa); - ret = 0; - -unlock: - rcu_read_unlock(); - return ret; + return 0; } int kvm_arch_add_msi_route_post(struct kvm_irq_routing_entry *route, -- 2.20.1 From: Jan Luebbe <jlu@pengutronix.de> Break events are currently only handled by chardev/char-serial.c, so we just ignore errors, which results in no behaviour change for other chardevs. Signed-off-by: Jan Luebbe <jlu@pengutronix.de> Message-id: 20210806144700.3751979-1-jlu@pengutronix.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/pl011.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties-system.h" #include "migration/vmstate.h" #include "chardev/char-fe.h" +#include "chardev/char-serial.h" #include "qemu/log.h" #include "qemu/module.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, s->read_count = 0; s->read_pos = 0; } + if ((s->lcr ^ value) & 0x1) { + int break_enable = value & 0x1; + qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_BREAK, + &break_enable); + } s->lcr = value; pl011_set_read_trigger(s); break; -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 and ASRC as unimplemented devices to avoid random Linux kernel crashes, such as Unhandled fault: external abort on non-linefetch (0x808) at 0xd1580010 pgd = (ptrval) [d1580010] *pgd=8231b811, *pte=02034653, *ppte=02034453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c095837c>] (_regmap_update_bits+0xe4/0xec) [<c095837c>] (_regmap_update_bits) from [<c09599b4>] (regmap_update_bits_base+0x50/0x74) [<c09599b4>] (regmap_update_bits_base) from [<c0d3e9e4>] (fsl_asrc_runtime_resume+0x1e4/0x21c) [<c0d3e9e4>] (fsl_asrc_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d3ecc4>] (fsl_asrc_probe+0x2a8/0x708) [<c0d3ecc4>] (fsl_asrc_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) or Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810160318.87376-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6ul.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) */ create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, 0x4000); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX6UL_SAI1_ADDR, 0x4000); + create_unimplemented_device("sai2", FSL_IMX6UL_SAI2_ADDR, 0x4000); + create_unimplemented_device("sai3", FSL_IMX6UL_SAI3_ADDR, 0x4000); + /* * PWM */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) create_unimplemented_device("pwm3", FSL_IMX6UL_PWM3_ADDR, 0x4000); create_unimplemented_device("pwm4", FSL_IMX6UL_PWM4_ADDR, 0x4000); + /* + * Audio ASRC (asynchronous sample rate converter) + */ + create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, 0x4000); + /* * CAN */ -- 2.20.1 From: "Wen, Jianxian" <Jianxian.Wen@verisilicon.com> Add property memory region which can connect with IOMMU region to support SMMU translate. Signed-off-by: Jianxian Wen <jianxian.wen@verisilicon.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 4C23C17B8E87E74E906A25A3254A03F4FA1FEC31@SHASXM03.verisilicon.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/exynos4210.c | 3 +++ hw/arm/xilinx_zynq.c | 3 +++ hw/dma/pl330.c | 26 ++++++++++++++++++++++---- 3 files changed, 28 insertions(+), 4 deletions(-) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static DeviceState *pl330_create(uint32_t base, qemu_or_irq *orgate, int i; dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(get_system_memory()), + &error_fatal); qdev_prop_set_uint8(dev, "num_events", nevents); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", nreq); diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[39-IRQ_OFFSET]); dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(address_space_mem), + &error_fatal); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", 4); qdev_prop_set_uint8(dev, "num_events", 16); diff --git a/hw/dma/pl330.c b/hw/dma/pl330.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/pl330.c +++ b/hw/dma/pl330.c @@ -XXX,XX +XXX,XX @@ struct PL330State { uint8_t num_faulting; uint8_t periph_busy[PL330_PERIPH_NUM]; + /* Memory region that DMA operation access */ + MemoryRegion *mem_mr; + AddressSpace *mem_as; }; #define TYPE_PL330 "pl330" @@ -XXX,XX +XXX,XX @@ static inline const PL330InsnDesc *pl330_fetch_insn(PL330Chan *ch) uint8_t opcode; int i; - dma_memory_read(&address_space_memory, ch->pc, &opcode, 1); + dma_memory_read(ch->parent->mem_as, ch->pc, &opcode, 1); for (i = 0; insn_desc[i].size; i++) { if ((opcode & insn_desc[i].opmask) == insn_desc[i].opcode) { return &insn_desc[i]; @@ -XXX,XX +XXX,XX @@ static inline void pl330_exec_insn(PL330Chan *ch, const PL330InsnDesc *insn) uint8_t buf[PL330_INSN_MAXSIZE]; assert(insn->size <= PL330_INSN_MAXSIZE); - dma_memory_read(&address_space_memory, ch->pc, buf, insn->size); + dma_memory_read(ch->parent->mem_as, ch->pc, buf, insn->size); insn->exec(ch, buf[0], &buf[1], insn->size - 1); } @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) if (q != NULL && q->len <= pl330_fifo_num_free(&s->fifo)) { int len = q->len - (q->addr & (q->len - 1)); - dma_memory_read(&address_space_memory, q->addr, buf, len); + dma_memory_read(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) fifo_res = pl330_fifo_get(&s->fifo, buf, len, q->tag); } if (fifo_res == PL330_FIFO_OK || q->z) { - dma_memory_write(&address_space_memory, q->addr, buf, len); + dma_memory_write(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static void pl330_realize(DeviceState *dev, Error **errp) "dma", PL330_IOMEM_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + if (!s->mem_mr) { + error_setg(errp, "'memory' link is not set"); + return; + } else if (s->mem_mr == get_system_memory()) { + /* Avoid creating new AS for system memory. */ + s->mem_as = &address_space_memory; + } else { + s->mem_as = g_new0(AddressSpace, 1); + address_space_init(s->mem_as, s->mem_mr, + memory_region_name(s->mem_mr)); + } + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pl330_exec_cycle_timer, s); s->cfg[0] = (s->mgr_ns_at_rst ? 0x4 : 0) | @@ -XXX,XX +XXX,XX @@ static Property pl330_properties[] = { DEFINE_PROP_UINT8("rd_q_dep", PL330State, rd_q_dep, 16), DEFINE_PROP_UINT16("data_buffer_dep", PL330State, data_buffer_dep, 256), + DEFINE_PROP_LINK("memory", PL330State, mem_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Eduardo Habkost <ehabkost@redhat.com> The SBSA_GWDT enum value conflicts with the SBSA_GWDT() QOM type checking helper, preventing us from using a OBJECT_DEFINE* or DEFINE_INSTANCE_CHECKER macro for the SBSA_GWDT() wrapper. If I understand the SBSA 6.0 specification correctly, the signal being connected to IRQ 16 is the WS0 output signal from the Generic Watchdog. Rename the enum value to SBSA_GWDT_WS0 to be more explicit and avoid the name conflict. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20210806023119.431680-1-ehabkost@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ enum { SBSA_GIC_DIST, SBSA_GIC_REDIST, SBSA_SECURE_EC, - SBSA_GWDT, + SBSA_GWDT_WS0, SBSA_GWDT_REFRESH, SBSA_GWDT_CONTROL, SBSA_SMMU, @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_AHCI] = 10, [SBSA_EHCI] = 11, [SBSA_SMMU] = 12, /* ... to 15 */ - [SBSA_GWDT] = 16, + [SBSA_GWDT_WS0] = 16, }; static const char * const valid_cpus[] = { @@ -XXX,XX +XXX,XX @@ static void create_wdt(const SBSAMachineState *sms) hwaddr cbase = sbsa_ref_memmap[SBSA_GWDT_CONTROL].base; DeviceState *dev = qdev_new(TYPE_WDT_SBSA); SysBusDevice *s = SYS_BUS_DEVICE(dev); - int irq = sbsa_ref_irqmap[SBSA_GWDT]; + int irq = sbsa_ref_irqmap[SBSA_GWDT_WS0]; sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, rbase); -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 as unimplemented devices to avoid Linux kernel crashes such as the following. Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0-rc5 #1 ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810175607.538090-1-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 5 +++++ hw/arm/fsl-imx7.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_UART6_ADDR = 0x30A80000, FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_SAI1_ADDR = 0x308A0000, + FSL_IMX7_SAI2_ADDR = 0x308B0000, + FSL_IMX7_SAI3_ADDR = 0x308C0000, + FSL_IMX7_SAIn_SIZE = 0x10000, + FSL_IMX7_ENET1_ADDR = 0x30BE0000, FSL_IMX7_ENET2_ADDR = 0x30BF0000, diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) create_unimplemented_device("can1", FSL_IMX7_CAN1_ADDR, FSL_IMX7_CANn_SIZE); create_unimplemented_device("can2", FSL_IMX7_CAN2_ADDR, FSL_IMX7_CANn_SIZE); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX7_SAI1_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI2_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI3_ADDR, FSL_IMX7_SAIn_SIZE); + /* * OCOTP */ -- 2.20.1 From: Sebastian Meyer <meyer@absint.com> With gdb 9.0 and better it is possible to connect to a gdbstub over unix sockets, which is better than a TCP socket connection in some situations. The QEMU command line to set this up is non-obvious; document it. Signed-off-by: Sebastian Meyer <meyer@absint.com> Message-id: 162867284829.27377.4784930719350564918-0@git.sr.ht [PMM: Tweaked commit message; adjusted wording in a couple of places; fixed rST formatting issue; moved section up out of the 'advanced debugging options' subsection] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/gdb.rst | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/system/gdb.rst b/docs/system/gdb.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/gdb.rst +++ b/docs/system/gdb.rst @@ -XXX,XX +XXX,XX @@ The ``-s`` option will make QEMU listen for an incoming connection from gdb on TCP port 1234, and ``-S`` will make QEMU not start the guest until you tell it to from gdb. (If you want to specify which TCP port to use or to use something other than TCP for the gdbstub -connection, use the ``-gdb dev`` option instead of ``-s``.) +connection, use the ``-gdb dev`` option instead of ``-s``. See +`Using unix sockets`_ for an example.) .. parsed-literal:: @@ -XXX,XX +XXX,XX @@ not just those in the cluster you are currently working on:: (gdb) set schedule-multiple on +Using unix sockets +================== + +An alternate method for connecting gdb to the QEMU gdbstub is to use +a unix socket (if supported by your operating system). This is useful when +running several tests in parallel, or if you do not have a known free TCP +port (e.g. when running automated tests). + +First create a chardev with the appropriate options, then +instruct the gdbserver to use that device: + +.. parsed-literal:: + + |qemu_system| -chardev socket,path=/tmp/gdb-socket,server=on,wait=off,id=gdb0 -gdb chardev:gdb0 -S ... + +Start gdb as before, but this time connect using the path to +the socket:: + + (gdb) target remote /tmp/gdb-socket + +Note that to use a unix socket for the connection you will need +gdb version 9.0 or newer. + Advanced debugging options ========================== -- 2.20.1 The following changes since commit 3db29dcac23da85486704ef9e7a8e7217f7829cd: Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2023-01-12 13:51:36 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230113 for you to fetch changes up to 08899b5c68a55a3780d707e2464073c8f2670d31: target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled (2023-01-13 13:19:36 +0000) ---------------------------------------------------------------- target-arm queue: hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 board cubieboard: Support booting from an SD card image with u-boot on it target/arm: Fix sve_probe_page target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled various code cleanups ---------------------------------------------------------------- Evgeny Iakovlev (1): target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled Felipe Balbi (2): hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 Philippe Mathieu-Daudé (27): hw/arm/pxa2xx: Simplify pxa255_init() hw/arm/pxa2xx: Simplify pxa270_init() hw/arm/collie: Use the IEC binary prefix definitions hw/arm/collie: Simplify flash creation using for() loop hw/arm/gumstix: Improve documentation hw/arm/gumstix: Use the IEC binary prefix definitions hw/arm/mainstone: Use the IEC binary prefix definitions hw/arm/musicpal: Use the IEC binary prefix definitions hw/arm/omap_sx1: Remove unused 'total_ram' definitions hw/arm/omap_sx1: Use the IEC binary prefix definitions hw/arm/z2: Use the IEC binary prefix definitions hw/arm/vexpress: Remove dead code in vexpress_common_init() hw/arm: Remove unreachable code calling pflash_cfi01_register() hw/arm/pxa: Avoid forward-declaring PXA2xxI2CState hw/gpio/omap_gpio: Add local variable to avoid embedded cast hw/arm/omap: Drop useless casts from void * to pointer hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP1_GPIO type name hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP2_GPIO type name hw/intc/omap_intc: Use CamelCase for TYPE_OMAP_INTC type name hw/arm/stellaris: Drop useless casts from void * to pointer hw/arm/stellaris: Use CamelCase for STELLARIS_ADC type name hw/arm/bcm2836: Remove definitions generated by OBJECT_DECLARE_TYPE() hw/arm/npcm7xx: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/misc/sbsa_ec: Rename TYPE_SBSA_EC -> TYPE_SBSA_SECURE_EC hw/misc/sbsa_ec: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/intc/xilinx_intc: Use 'XpsIntc' typedef instead of 'struct xlx_pic' hw/timer/xilinx_timer: Use XpsTimerState instead of 'struct timerblock' Richard Henderson (1): target/arm: Fix sve_probe_page Strahinja Jankovic (7): hw/misc: Allwinner-A10 Clock Controller Module Emulation hw/misc: Allwinner A10 DRAM Controller Emulation {hw/i2c,docs/system/arm}: Allwinner TWI/I2C Emulation hw/misc: AXP209 PMU Emulation hw/arm: Add AXP209 to Cubieboard hw/arm: Allwinner A10 enable SPL load from MMC tests/avocado: Add SD boot test to Cubieboard docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + include/hw/adc/npcm7xx_adc.h | 7 +- include/hw/arm/allwinner-a10.h | 27 ++ include/hw/arm/allwinner-h3.h | 3 + include/hw/arm/npcm7xx.h | 18 +- include/hw/arm/omap.h | 24 +- include/hw/arm/pxa.h | 11 +- include/hw/arm/stm32f405_soc.h | 5 +- include/hw/i2c/allwinner-i2c.h | 55 ++++ include/hw/i2c/npcm7xx_smbus.h | 7 +- include/hw/misc/allwinner-a10-ccm.h | 67 +++++ include/hw/misc/allwinner-a10-dramc.h | 68 +++++ include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +- include/hw/misc/npcm7xx_mft.h | 7 +- include/hw/misc/npcm7xx_pwm.h | 3 +- include/hw/misc/npcm7xx_rng.h | 6 +- include/hw/net/npcm7xx_emc.h | 5 +- include/hw/sd/npcm7xx_sdhci.h | 4 +- hw/arm/allwinner-a10.c | 40 +++ hw/arm/allwinner-h3.c | 11 +- hw/arm/bcm2836.c | 9 +- hw/arm/collie.c | 25 +- hw/arm/cubieboard.c | 11 + hw/arm/gumstix.c | 45 ++-- hw/arm/mainstone.c | 37 ++- hw/arm/musicpal.c | 9 +- hw/arm/olimex-stm32-h405.c | 69 +++++ hw/arm/omap1.c | 115 ++++---- hw/arm/omap2.c | 40 ++- hw/arm/omap_sx1.c | 53 ++-- hw/arm/palm.c | 2 +- hw/arm/pxa2xx.c | 8 +- hw/arm/spitz.c | 6 +- hw/arm/stellaris.c | 73 +++-- hw/arm/stm32f405_soc.c | 8 + hw/arm/tosa.c | 2 +- hw/arm/versatilepb.c | 6 +- hw/arm/vexpress.c | 10 +- hw/arm/z2.c | 16 +- hw/char/omap_uart.c | 7 +- hw/display/omap_dss.c | 15 +- hw/display/omap_lcdc.c | 9 +- hw/dma/omap_dma.c | 15 +- hw/gpio/omap_gpio.c | 48 ++-- hw/i2c/allwinner-i2c.c | 459 ++++++++++++++++++++++++++++++++ hw/intc/omap_intc.c | 38 +-- hw/intc/xilinx_intc.c | 28 +- hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++ hw/misc/allwinner-a10-dramc.c | 179 +++++++++++++ hw/misc/axp209.c | 238 +++++++++++++++++ hw/misc/omap_gpmc.c | 12 +- hw/misc/omap_l4.c | 7 +- hw/misc/omap_sdrc.c | 7 +- hw/misc/omap_tap.c | 5 +- hw/misc/sbsa_ec.c | 12 +- hw/sd/omap_mmc.c | 9 +- hw/ssi/omap_spi.c | 7 +- hw/timer/omap_gptimer.c | 22 +- hw/timer/omap_synctimer.c | 4 +- hw/timer/xilinx_timer.c | 27 +- target/arm/helper.c | 3 + target/arm/sve_helper.c | 14 +- MAINTAINERS | 8 + hw/arm/Kconfig | 9 + hw/arm/meson.build | 1 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + hw/misc/Kconfig | 10 + hw/misc/meson.build | 3 + hw/misc/trace-events | 5 + tests/avocado/boot_linux_console.py | 47 ++++ 76 files changed, 1951 insertions(+), 455 deletions(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/arm/olimex-stm32-h405.c create mode 100644 hw/i2c/allwinner-i2c.c create mode 100644 hw/misc/allwinner-a10-ccm.c create mode 100644 hw/misc/allwinner-a10-dramc.c create mode 100644 hw/misc/axp209.c From: Felipe Balbi <balbi@kernel.org> STM32F405 has 128K of SRAM and another 64K of CCM (Core-coupled Memory) at a different base address. Correctly describe the memory layout to give existing FW images a chance to run unmodified. Reviewed-by: Alistair Francis <alistair@alistair23.me> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Felipe Balbi <balbi@kernel.org> Message-id: 20221230145733.200496-2-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/stm32f405_soc.h | 5 ++++- hw/arm/stm32f405_soc.c | 8 ++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/stm32f405_soc.h b/include/hw/arm/stm32f405_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f405_soc.h +++ b/include/hw/arm/stm32f405_soc.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(STM32F405State, STM32F405_SOC) #define FLASH_BASE_ADDRESS 0x08000000 #define FLASH_SIZE (1024 * 1024) #define SRAM_BASE_ADDRESS 0x20000000 -#define SRAM_SIZE (192 * 1024) +#define SRAM_SIZE (128 * 1024) +#define CCM_BASE_ADDRESS 0x10000000 +#define CCM_SIZE (64 * 1024) struct STM32F405State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ struct STM32F405State { STM32F2XXADCState adc[STM_NUM_ADCS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; + MemoryRegion ccm; MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) } memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); + memory_region_init_ram(&s->ccm, NULL, "STM32F405.ccm", CCM_SIZE, + &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + memory_region_add_subregion(system_memory, CCM_BASE_ADDRESS, &s->ccm); + armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); -- 2.34.1 From: Felipe Balbi <balbi@kernel.org> Olimex makes a series of low-cost STM32 boards. This commit introduces the minimum setup to support SMT32-H405. See [1] for details [1] https://www.olimex.com/Products/ARM/ST/STM32-H405/ Signed-off-by: Felipe Balbi <balbi@kernel.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20221230145733.200496-3-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + hw/arm/olimex-stm32-h405.c | 69 +++++++++++++++++++++++++ MAINTAINERS | 6 +++ hw/arm/Kconfig | 4 ++ hw/arm/meson.build | 1 + 6 files changed, 82 insertions(+) create mode 100644 hw/arm/olimex-stm32-h405.c diff --git a/docs/system/arm/stm32.rst b/docs/system/arm/stm32.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/stm32.rst +++ b/docs/system/arm/stm32.rst @@ -XXX,XX +XXX,XX @@ The STM32F4 series is based on ARM Cortex-M4F core. This series is pin-to-pin compatible with STM32F2 series. The following machines are based on this chip : - ``netduinoplus2`` Netduino Plus 2 board with STM32F405RGT6 microcontroller +- ``olimex-stm32-h405`` Olimex STM32 H405 board with STM32F405RGT6 microcontroller There are many other STM32 series that are currently not supported by QEMU. diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ CONFIG_COLLIE=y CONFIG_ASPEED_SOC=y CONFIG_NETDUINO2=y CONFIG_NETDUINOPLUS2=y +CONFIG_OLIMEX_STM32_H405=y CONFIG_MPS2=y CONFIG_RASPI=y CONFIG_DIGIC=y diff --git a/hw/arm/olimex-stm32-h405.c b/hw/arm/olimex-stm32-h405.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/olimex-stm32-h405.c @@ -XXX,XX +XXX,XX @@ +/* + * ST STM32VLDISCOVERY machine + * Olimex STM32-H405 machine + * + * Copyright (c) 2022 Felipe Balbi <balbi@kernel.org> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" +#include "qemu/error-report.h" +#include "hw/arm/stm32f405_soc.h" +#include "hw/arm/boot.h" + +/* olimex-stm32-h405 implementation is derived from netduinoplus2 */ + +/* Main SYSCLK frequency in Hz (168MHz) */ +#define SYSCLK_FRQ 168000000ULL + +static void olimex_stm32_h405_init(MachineState *machine) +{ + DeviceState *dev; + Clock *sysclk; + + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + + dev = qdev_new(TYPE_STM32F405_SOC); + qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); + qdev_connect_clock_in(dev, "sysclk", sysclk); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + + armv7m_load_kernel(ARM_CPU(first_cpu), + machine->kernel_filename, + 0, FLASH_SIZE); +} + +static void olimex_stm32_h405_machine_init(MachineClass *mc) +{ + mc->desc = "Olimex STM32-H405 (Cortex-M4)"; + mc->init = olimex_stm32_h405_init; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); + + /* SRAM pre-allocated as part of the SoC instantiation */ + mc->default_ram_size = 0; +} + +DEFINE_MACHINE("olimex-stm32-h405", olimex_stm32_h405_machine_init) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Maintained F: hw/arm/netduinoplus2.c +Olimex STM32 H405 +M: Felipe Balbi <balbi@kernel.org> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/olimex-stm32-h405.c + SmartFusion2 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config NETDUINOPLUS2 bool select STM32F405_SOC +config OLIMEX_STM32_H405 + bool + select STM32F405_SOC + config NSERIES bool select OMAP diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) +arm_ss.add(when: 'CONFIG_OLIMEX_STM32_H405', if_true: files('olimex-stm32-h405.c')) arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several Clock Controller Module (CCM) registers are read, most important are PLL and Tuning, as well as divisor registers. This patch adds these registers and initializes reset values from user's guide. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-2-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-ccm.h | 67 +++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 305 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 hw/misc/allwinner-a10-ccm.c diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/misc/allwinner-a10-ccm.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { /*< public >*/ ARMCPU cpu; + AwA10ClockCtlState ccm; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-ccm.h b/include/hw/misc/allwinner-a10-ccm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-ccm.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_A10_CCM_H +#define HW_MISC_ALLWINNER_A10_CCM_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCM device */ +#define AW_A10_CCM_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_A10_CCM_REGS_NUM (AW_A10_CCM_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_CCM "allwinner-a10-ccm" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10ClockCtlState, AW_A10_CCM) + +/** @} */ + +/** + * Allwinner A10 CCM object instance state. + */ +struct AwA10ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_CCM_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_H3_CCU_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ohci.h" #define AW_A10_MMC0_BASE 0x01c0f000 +#define AW_A10_CCM_BASE 0x01c20000 #define AW_A10_PIC_REG_BASE 0x01c20400 #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "timer", &s->timer, TYPE_AW_A10_PIT); + object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), 0x00000000, &s->sram_a); create_unimplemented_device("a10-sram-ctrl", 0x01c00000, 4 * KiB); + /* Clock Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-ccm.c b/hw/misc/allwinner-a10-ccm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-ccm.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-a10-ccm.h" + +/* CCM register offsets */ +enum { + REG_PLL1_CFG = 0x0000, /* PLL1 Control */ + REG_PLL1_TUN = 0x0004, /* PLL1 Tuning */ + REG_PLL2_CFG = 0x0008, /* PLL2 Control */ + REG_PLL2_TUN = 0x000C, /* PLL2 Tuning */ + REG_PLL3_CFG = 0x0010, /* PLL3 Control */ + REG_PLL4_CFG = 0x0018, /* PLL4 Control */ + REG_PLL5_CFG = 0x0020, /* PLL5 Control */ + REG_PLL5_TUN = 0x0024, /* PLL5 Tuning */ + REG_PLL6_CFG = 0x0028, /* PLL6 Control */ + REG_PLL6_TUN = 0x002C, /* PLL6 Tuning */ + REG_PLL7_CFG = 0x0030, /* PLL7 Control */ + REG_PLL1_TUN2 = 0x0038, /* PLL1 Tuning2 */ + REG_PLL5_TUN2 = 0x003C, /* PLL5 Tuning2 */ + REG_PLL8_CFG = 0x0040, /* PLL8 Control */ + REG_OSC24M_CFG = 0x0050, /* OSC24M Control */ + REG_CPU_AHB_APB0_CFG = 0x0054, /* CPU, AHB and APB0 Divide Ratio */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCM register reset values */ +enum { + REG_PLL1_CFG_RST = 0x21005000, + REG_PLL1_TUN_RST = 0x0A101000, + REG_PLL2_CFG_RST = 0x08100010, + REG_PLL2_TUN_RST = 0x00000000, + REG_PLL3_CFG_RST = 0x0010D063, + REG_PLL4_CFG_RST = 0x21009911, + REG_PLL5_CFG_RST = 0x11049280, + REG_PLL5_TUN_RST = 0x14888000, + REG_PLL6_CFG_RST = 0x21009911, + REG_PLL6_TUN_RST = 0x00000000, + REG_PLL7_CFG_RST = 0x0010D063, + REG_PLL1_TUN2_RST = 0x00000000, + REG_PLL5_TUN2_RST = 0x00000000, + REG_PLL8_CFG_RST = 0x21009911, + REG_OSC24M_CFG_RST = 0x00138013, + REG_CPU_AHB_APB0_CFG_RST = 0x00010010, +}; + +static uint64_t allwinner_a10_ccm_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_ccm_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_a10_ccm_ops = { + .read = allwinner_a10_ccm_read, + .write = allwinner_a10_ccm_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_ccm_reset_enter(Object *obj, ResetType type) +{ + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL1_CFG)] = REG_PLL1_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN)] = REG_PLL1_TUN_RST; + s->regs[REG_INDEX(REG_PLL2_CFG)] = REG_PLL2_CFG_RST; + s->regs[REG_INDEX(REG_PLL2_TUN)] = REG_PLL2_TUN_RST; + s->regs[REG_INDEX(REG_PLL3_CFG)] = REG_PLL3_CFG_RST; + s->regs[REG_INDEX(REG_PLL4_CFG)] = REG_PLL4_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_CFG)] = REG_PLL5_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_TUN)] = REG_PLL5_TUN_RST; + s->regs[REG_INDEX(REG_PLL6_CFG)] = REG_PLL6_CFG_RST; + s->regs[REG_INDEX(REG_PLL6_TUN)] = REG_PLL6_TUN_RST; + s->regs[REG_INDEX(REG_PLL7_CFG)] = REG_PLL7_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN2)] = REG_PLL1_TUN2_RST; + s->regs[REG_INDEX(REG_PLL5_TUN2)] = REG_PLL5_TUN2_RST; + s->regs[REG_INDEX(REG_PLL8_CFG)] = REG_PLL8_CFG_RST; + s->regs[REG_INDEX(REG_OSC24M_CFG)] = REG_OSC24M_CFG_RST; + s->regs[REG_INDEX(REG_CPU_AHB_APB0_CFG)] = REG_CPU_AHB_APB0_CFG_RST; +} + +static void allwinner_a10_ccm_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_ccm_ops, s, + TYPE_AW_A10_CCM, AW_A10_CCM_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_ccm_vmstate = { + .name = "allwinner-a10-ccm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10ClockCtlState, AW_A10_CCM_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_ccm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_ccm_reset_enter; + dc->vmsd = &allwinner_a10_ccm_vmstate; +} + +static const TypeInfo allwinner_a10_ccm_info = { + .name = TYPE_AW_A10_CCM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_ccm_init, + .instance_size = sizeof(AwA10ClockCtlState), + .class_init = allwinner_a10_ccm_class_init, +}; + +static void allwinner_a10_ccm_register(void) +{ + type_register_static(&allwinner_a10_ccm_info); +} + +type_init(allwinner_a10_ccm_register) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select AHCI select ALLWINNER_A10_PIT select ALLWINNER_A10_PIC + select ALLWINNER_A10_CCM select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config VIRT_CTRL config LASI bool +config ALLWINNER_A10_CCM + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several DRAM Controller registers are used. Most important registers are those related to DRAM initialization and calibration, where SPL initiates process and waits until certain bit is set/cleared. This patch adds these registers, initializes reset values from user's guide and updates state of registers as SPL expects it. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-3-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-dramc.h | 68 ++++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-dramc.c | 179 ++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 261 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/misc/allwinner-a10-dramc.c diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" +#include "hw/misc/allwinner-a10-dramc.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { ARMCPU cpu; AwA10ClockCtlState ccm; + AwA10DramControllerState dramc; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-dramc.h b/include/hw/misc/allwinner-a10-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_A10_DRAMC_H +#define HW_MISC_ALLWINNER_A10_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/register.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by DRAMC device */ +#define AW_A10_DRAMC_IOSIZE (0x1000) + +/** Total number of known registers */ +#define AW_A10_DRAMC_REGS_NUM (AW_A10_DRAMC_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_DRAMC "allwinner-a10-dramc" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10DramControllerState, AW_A10_DRAMC) + +/** @} */ + +/** + * Allwinner A10 DRAMC object instance state. + */ +struct AwA10DramControllerState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_DRAMC_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_A10_DRAMC_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#define AW_A10_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 #define AW_A10_PIC_REG_BASE 0x01c20400 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "dramc", &s->dramc, TYPE_AW_A10_DRAMC); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* DRAM Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->dramc), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, AW_A10_DRAMC_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-dramc.c b/hw/misc/allwinner-a10-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-a10-dramc.h" + +/* DRAMC register offsets */ +enum { + REG_SDR_CCR = 0x0000, + REG_SDR_ZQCR0 = 0x00a8, + REG_SDR_ZQSR = 0x00b0 +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMC register flags */ +enum { + REG_SDR_CCR_DATA_TRAINING = (1 << 30), + REG_SDR_CCR_DRAM_INIT = (1 << 31), +}; +enum { + REG_SDR_ZQSR_ZCAL = (1 << 31), +}; + +/* DRAMC register reset values */ +enum { + REG_SDR_CCR_RESET = 0x80020000, + REG_SDR_ZQCR0_RESET = 0x07b00000, + REG_SDR_ZQSR_RESET = 0x80000000 +}; + +static uint64_t allwinner_a10_dramc_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + case REG_SDR_ZQCR0: + case REG_SDR_ZQSR: + break; + case 0x2e4 ... AW_A10_DRAMC_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_dramc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + if (val & REG_SDR_CCR_DRAM_INIT) { + /* Clear DRAM_INIT to indicate process is done. */ + val &= ~REG_SDR_CCR_DRAM_INIT; + } + if (val & REG_SDR_CCR_DATA_TRAINING) { + /* Clear DATA_TRAINING to indicate process is done. */ + val &= ~REG_SDR_CCR_DATA_TRAINING; + } + break; + case REG_SDR_ZQCR0: + /* Set ZCAL in ZQSR to indicate calibration is done. */ + s->regs[REG_INDEX(REG_SDR_ZQSR)] |= REG_SDR_ZQSR_ZCAL; + break; + case 0x2e4 ... AW_A10_DRAMC_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_a10_dramc_ops = { + .read = allwinner_a10_dramc_read, + .write = allwinner_a10_dramc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_dramc_reset_enter(Object *obj, ResetType type) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_SDR_CCR)] = REG_SDR_CCR_RESET; + s->regs[REG_INDEX(REG_SDR_ZQCR0)] = REG_SDR_ZQCR0_RESET; + s->regs[REG_INDEX(REG_SDR_ZQSR)] = REG_SDR_ZQSR_RESET; +} + +static void allwinner_a10_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_dramc_ops, s, + TYPE_AW_A10_DRAMC, AW_A10_DRAMC_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_dramc_vmstate = { + .name = "allwinner-a10-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10DramControllerState, + AW_A10_DRAMC_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_dramc_reset_enter; + dc->vmsd = &allwinner_a10_dramc_vmstate; +} + +static const TypeInfo allwinner_a10_dramc_info = { + .name = TYPE_AW_A10_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_dramc_init, + .instance_size = sizeof(AwA10DramControllerState), + .class_init = allwinner_a10_dramc_class_init, +}; + +static void allwinner_a10_dramc_register(void) +{ + type_register_static(&allwinner_a10_dramc_info); +} + +type_init(allwinner_a10_dramc_register) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_PIT select ALLWINNER_A10_PIC select ALLWINNER_A10_CCM + select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config LASI config ALLWINNER_A10_CCM bool +config ALLWINNER_A10_DRAMC + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_DRAMC', if_true: files('allwinner-a10-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch implements Allwinner TWI/I2C controller emulation. Only master-mode functionality is implemented. The SPL boot for Cubieboard expects AXP209 PMIC on TWI0/I2C0 bus, so this is first part enabling the TWI/I2C bus operation. Since both Allwinner A10 and H3 use the same module, it is added for both boards. Docs are also updated for Cubieboard and Orangepi-PC board to indicate I2C availability. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-4-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/i2c/allwinner-i2c.h | 55 ++++ hw/arm/allwinner-a10.c | 8 + hw/arm/allwinner-h3.c | 11 +- hw/i2c/allwinner-i2c.c | 459 +++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 2 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + 12 files changed, 551 insertions(+), 1 deletion(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 hw/i2c/allwinner-i2c.c diff --git a/docs/system/arm/cubieboard.rst b/docs/system/arm/cubieboard.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/cubieboard.rst +++ b/docs/system/arm/cubieboard.rst @@ -XXX,XX +XXX,XX @@ Emulated devices: - SDHCI - USB controller - SATA controller +- TWI (I2C) controller diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/orangepi.rst +++ b/docs/system/arm/orangepi.rst @@ -XXX,XX +XXX,XX @@ The Orange Pi PC machine supports the following devices: * Clock Control Unit * System Control module * Security Identifier device + * TWI (I2C) Limitations """"""""""" diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; AwSdHostState mmc0; + AWI2CState i2c0; AwRtcState rtc; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_DEV_UART2, AW_H3_DEV_UART3, AW_H3_DEV_EMAC, + AW_H3_DEV_TWI0, AW_H3_DEV_DRAMCOM, AW_H3_DEV_DRAMCTL, AW_H3_DEV_DRAMPHY, @@ -XXX,XX +XXX,XX @@ struct AwH3State { AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; + AWI2CState i2c0; AwSun8iEmacState emac; AwRtcState rtc; GICState gic; diff --git a/include/hw/i2c/allwinner-i2c.h b/include/hw/i2c/allwinner-i2c.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/i2c/allwinner-i2c.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface registers definition + * + * Copyright (C) 2022 Strahinja Jankovic. <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef ALLWINNER_I2C_H +#define ALLWINNER_I2C_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_AW_I2C "allwinner.i2c" +OBJECT_DECLARE_SIMPLE_TYPE(AWI2CState, AW_I2C) + +#define AW_I2C_MEM_SIZE 0x24 + +struct AWI2CState { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + I2CBus *bus; + qemu_irq irq; + + uint8_t addr; + uint8_t xaddr; + uint8_t data; + uint8_t cntr; + uint8_t stat; + uint8_t ccr; + uint8_t srst; + uint8_t efr; + uint8_t lcr; +}; + +#endif /* ALLWINNER_I2C_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #define AW_A10_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 #define AW_A10_RTC_BASE 0x01c20d00 +#define AW_A10_I2C0_BASE 0x01c2ac00 static void aw_a10_init(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); + object_initialize_child(obj, "i2c0", &s->i2c0, TYPE_AW_I2C); + if (machine_usb(current_machine)) { int i; @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) /* RTC */ sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->rtc), 0, AW_A10_RTC_BASE, 10); + + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, AW_A10_I2C0_BASE); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, qdev_get_gpio_in(dev, 7)); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_DEV_UART1] = 0x01c28400, [AW_H3_DEV_UART2] = 0x01c28800, [AW_H3_DEV_UART3] = 0x01c28c00, + [AW_H3_DEV_TWI0] = 0x01c2ac00, [AW_H3_DEV_EMAC] = 0x01c30000, [AW_H3_DEV_DRAMCOM] = 0x01c62000, [AW_H3_DEV_DRAMCTL] = 0x01c63000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "uart1", 0x01c28400, 1 * KiB }, { "uart2", 0x01c28800, 1 * KiB }, { "uart3", 0x01c28c00, 1 * KiB }, - { "twi0", 0x01c2ac00, 1 * KiB }, { "twi1", 0x01c2b000, 1 * KiB }, { "twi2", 0x01c2b400, 1 * KiB }, { "scr", 0x01c2c400, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART1 = 1, AW_H3_GIC_SPI_UART2 = 2, AW_H3_GIC_SPI_UART3 = 3, + AW_H3_GIC_SPI_TWI0 = 6, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, AW_H3_GIC_SPI_MMC0 = 60, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "ram-size"); object_initialize_child(obj, "rtc", &s->rtc, TYPE_AW_RTC_SUN6I); + + object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, s->memmap[AW_H3_DEV_RTC]); + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, s->memmap[AW_H3_DEV_TWI0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI0)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "hw/i2c/allwinner-i2c.h" +#include "hw/irq.h" +#include "migration/vmstate.h" +#include "hw/i2c/i2c.h" +#include "qemu/log.h" +#include "trace.h" +#include "qemu/module.h" + +/* Allwinner I2C memory map */ +#define TWI_ADDR_REG 0x00 /* slave address register */ +#define TWI_XADDR_REG 0x04 /* extended slave address register */ +#define TWI_DATA_REG 0x08 /* data register */ +#define TWI_CNTR_REG 0x0c /* control register */ +#define TWI_STAT_REG 0x10 /* status register */ +#define TWI_CCR_REG 0x14 /* clock control register */ +#define TWI_SRST_REG 0x18 /* software reset register */ +#define TWI_EFR_REG 0x1c /* enhance feature register */ +#define TWI_LCR_REG 0x20 /* line control register */ + +/* Used only in slave mode, do not set */ +#define TWI_ADDR_RESET 0 +#define TWI_XADDR_RESET 0 + +/* Data register */ +#define TWI_DATA_MASK 0xFF +#define TWI_DATA_RESET 0 + +/* Control register */ +#define TWI_CNTR_INT_EN (1 << 7) +#define TWI_CNTR_BUS_EN (1 << 6) +#define TWI_CNTR_M_STA (1 << 5) +#define TWI_CNTR_M_STP (1 << 4) +#define TWI_CNTR_INT_FLAG (1 << 3) +#define TWI_CNTR_A_ACK (1 << 2) +#define TWI_CNTR_MASK 0xFC +#define TWI_CNTR_RESET 0 + +/* Status register */ +#define TWI_STAT_MASK 0xF8 +#define TWI_STAT_RESET 0xF8 + +/* Clock register */ +#define TWI_CCR_CLK_M_MASK 0x78 +#define TWI_CCR_CLK_N_MASK 0x07 +#define TWI_CCR_MASK 0x7F +#define TWI_CCR_RESET 0 + +/* Soft reset */ +#define TWI_SRST_MASK 0x01 +#define TWI_SRST_RESET 0 + +/* Enhance feature */ +#define TWI_EFR_MASK 0x03 +#define TWI_EFR_RESET 0 + +/* Line control */ +#define TWI_LCR_SCL_STATE (1 << 5) +#define TWI_LCR_SDA_STATE (1 << 4) +#define TWI_LCR_SCL_CTL (1 << 3) +#define TWI_LCR_SCL_CTL_EN (1 << 2) +#define TWI_LCR_SDA_CTL (1 << 1) +#define TWI_LCR_SDA_CTL_EN (1 << 0) +#define TWI_LCR_MASK 0x3F +#define TWI_LCR_RESET 0x3A + +/* Status value in STAT register is shifted by 3 bits */ +#define TWI_STAT_SHIFT 3 +#define STAT_FROM_STA(x) ((x) << TWI_STAT_SHIFT) +#define STAT_TO_STA(x) ((x) >> TWI_STAT_SHIFT) + +enum { + STAT_BUS_ERROR = 0, + /* Master mode */ + STAT_M_STA_TX, + STAT_M_RSTA_TX, + STAT_M_ADDR_WR_ACK, + STAT_M_ADDR_WR_NACK, + STAT_M_DATA_TX_ACK, + STAT_M_DATA_TX_NACK, + STAT_M_ARB_LOST, + STAT_M_ADDR_RD_ACK, + STAT_M_ADDR_RD_NACK, + STAT_M_DATA_RX_ACK, + STAT_M_DATA_RX_NACK, + /* Slave mode */ + STAT_S_ADDR_WR_ACK, + STAT_S_ARB_LOST_AW_ACK, + STAT_S_GCA_ACK, + STAT_S_ARB_LOST_GCA_ACK, + STAT_S_DATA_RX_SA_ACK, + STAT_S_DATA_RX_SA_NACK, + STAT_S_DATA_RX_GCA_ACK, + STAT_S_DATA_RX_GCA_NACK, + STAT_S_STP_RSTA, + STAT_S_ADDR_RD_ACK, + STAT_S_ARB_LOST_AR_ACK, + STAT_S_DATA_TX_ACK, + STAT_S_DATA_TX_NACK, + STAT_S_LB_TX_ACK, + /* Master mode, 10-bit */ + STAT_M_2ND_ADDR_WR_ACK, + STAT_M_2ND_ADDR_WR_NACK, + /* Idle */ + STAT_IDLE = 0x1f +} TWI_STAT_STA; + +static const char *allwinner_i2c_get_regname(unsigned offset) +{ + switch (offset) { + case TWI_ADDR_REG: + return "ADDR"; + case TWI_XADDR_REG: + return "XADDR"; + case TWI_DATA_REG: + return "DATA"; + case TWI_CNTR_REG: + return "CNTR"; + case TWI_STAT_REG: + return "STAT"; + case TWI_CCR_REG: + return "CCR"; + case TWI_SRST_REG: + return "SRST"; + case TWI_EFR_REG: + return "EFR"; + case TWI_LCR_REG: + return "LCR"; + default: + return "[?]"; + } +} + +static inline bool allwinner_i2c_is_reset(AWI2CState *s) +{ + return s->srst & TWI_SRST_MASK; +} + +static inline bool allwinner_i2c_bus_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_BUS_EN; +} + +static inline bool allwinner_i2c_interrupt_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_INT_EN; +} + +static void allwinner_i2c_reset_hold(Object *obj) +{ + AWI2CState *s = AW_I2C(obj); + + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + i2c_end_transfer(s->bus); + } + + s->addr = TWI_ADDR_RESET; + s->xaddr = TWI_XADDR_RESET; + s->data = TWI_DATA_RESET; + s->cntr = TWI_CNTR_RESET; + s->stat = TWI_STAT_RESET; + s->ccr = TWI_CCR_RESET; + s->srst = TWI_SRST_RESET; + s->efr = TWI_EFR_RESET; + s->lcr = TWI_LCR_RESET; +} + +static inline void allwinner_i2c_raise_interrupt(AWI2CState *s) +{ + /* + * Raise an interrupt if the device is not reset and it is configured + * to generate some interrupts. + */ + if (!allwinner_i2c_is_reset(s) && allwinner_i2c_bus_is_enabled(s)) { + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + s->cntr |= TWI_CNTR_INT_FLAG; + if (allwinner_i2c_interrupt_is_enabled(s)) { + qemu_irq_raise(s->irq); + } + } + } +} + +static uint64_t allwinner_i2c_read(void *opaque, hwaddr offset, + unsigned size) +{ + uint16_t value; + AWI2CState *s = AW_I2C(opaque); + + switch (offset) { + case TWI_ADDR_REG: + value = s->addr; + break; + case TWI_XADDR_REG: + value = s->xaddr; + break; + case TWI_DATA_REG: + if ((STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK)) { + /* Get the next byte */ + s->data = i2c_recv(s->bus); + + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + value = s->data; + break; + case TWI_CNTR_REG: + value = s->cntr; + break; + case TWI_STAT_REG: + value = s->stat; + /* + * If polling when reading then change state to indicate data + * is available + */ + if (STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) { + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case TWI_CCR_REG: + value = s->ccr; + break; + case TWI_SRST_REG: + value = s->srst; + break; + case TWI_EFR_REG: + value = s->efr; + break; + case TWI_LCR_REG: + value = s->lcr; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + value = 0; + break; + } + + trace_allwinner_i2c_read(allwinner_i2c_get_regname(offset), offset, value); + + return (uint64_t)value; +} + +static void allwinner_i2c_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AWI2CState *s = AW_I2C(opaque); + + value &= 0xff; + + trace_allwinner_i2c_write(allwinner_i2c_get_regname(offset), offset, value); + + switch (offset) { + case TWI_ADDR_REG: + s->addr = (uint8_t)value; + break; + case TWI_XADDR_REG: + s->xaddr = (uint8_t)value; + break; + case TWI_DATA_REG: + /* If the device is in reset or not enabled, nothing to do */ + if (allwinner_i2c_is_reset(s) || (!allwinner_i2c_bus_is_enabled(s))) { + break; + } + + s->data = value & TWI_DATA_MASK; + + switch (STAT_TO_STA(s->stat)) { + case STAT_M_STA_TX: + case STAT_M_RSTA_TX: + /* Send address */ + if (i2c_start_transfer(s->bus, extract32(s->data, 1, 7), + extract32(s->data, 0, 1))) { + /* If non zero is returned, the address is not valid */ + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_NACK); + } else { + /* Determine if read of write */ + if (extract32(s->data, 0, 1)) { + s->stat = STAT_FROM_STA(STAT_M_ADDR_RD_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_ACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case STAT_M_ADDR_WR_ACK: + case STAT_M_DATA_TX_ACK: + if (i2c_send(s->bus, s->data)) { + /* If the target return non zero then end the transfer */ + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_NACK); + i2c_end_transfer(s->bus); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_ACK); + allwinner_i2c_raise_interrupt(s); + } + break; + default: + break; + } + break; + case TWI_CNTR_REG: + if (!allwinner_i2c_is_reset(s)) { + /* Do something only if not in software reset */ + s->cntr = value & TWI_CNTR_MASK; + + /* Check if start condition should be sent */ + if (s->cntr & TWI_CNTR_M_STA) { + /* Update status */ + if (STAT_TO_STA(s->stat) == STAT_IDLE) { + /* Send start condition */ + s->stat = STAT_FROM_STA(STAT_M_STA_TX); + } else { + /* Send repeated start condition */ + s->stat = STAT_FROM_STA(STAT_M_RSTA_TX); + } + /* Clear start condition */ + s->cntr &= ~TWI_CNTR_M_STA; + } + if (s->cntr & TWI_CNTR_M_STP) { + /* Update status */ + i2c_end_transfer(s->bus); + s->stat = STAT_FROM_STA(STAT_IDLE); + s->cntr &= ~TWI_CNTR_M_STP; + } + if ((s->cntr & TWI_CNTR_INT_FLAG) == 0) { + /* Interrupt flag cleared */ + qemu_irq_lower(s->irq); + } + if ((s->cntr & TWI_CNTR_A_ACK) == 0) { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + } else { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } + } + allwinner_i2c_raise_interrupt(s); + + } + break; + case TWI_CCR_REG: + s->ccr = value & TWI_CCR_MASK; + break; + case TWI_SRST_REG: + if (((value & TWI_SRST_MASK) == 0) && (s->srst & TWI_SRST_MASK)) { + /* Perform reset */ + allwinner_i2c_reset_hold(OBJECT(s)); + } + s->srst = value & TWI_SRST_MASK; + break; + case TWI_EFR_REG: + s->efr = value & TWI_EFR_MASK; + break; + case TWI_LCR_REG: + s->lcr = value & TWI_LCR_MASK; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + break; + } +} + +static const MemoryRegionOps allwinner_i2c_ops = { + .read = allwinner_i2c_read, + .write = allwinner_i2c_write, + .valid.min_access_size = 1, + .valid.max_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription allwinner_i2c_vmstate = { + .name = TYPE_AW_I2C, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8(addr, AWI2CState), + VMSTATE_UINT8(xaddr, AWI2CState), + VMSTATE_UINT8(data, AWI2CState), + VMSTATE_UINT8(cntr, AWI2CState), + VMSTATE_UINT8(ccr, AWI2CState), + VMSTATE_UINT8(srst, AWI2CState), + VMSTATE_UINT8(efr, AWI2CState), + VMSTATE_UINT8(lcr, AWI2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_i2c_realize(DeviceState *dev, Error **errp) +{ + AWI2CState *s = AW_I2C(dev); + + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_i2c_ops, s, + TYPE_AW_I2C, AW_I2C_MEM_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); + s->bus = i2c_init_bus(dev, "i2c"); +} + +static void allwinner_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = allwinner_i2c_reset_hold; + dc->vmsd = &allwinner_i2c_vmstate; + dc->realize = allwinner_i2c_realize; + dc->desc = "Allwinner I2C Controller"; +} + +static const TypeInfo allwinner_i2c_type_info = { + .name = TYPE_AW_I2C, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AWI2CState), + .class_init = allwinner_i2c_class_init, +}; + +static void allwinner_i2c_register_types(void) +{ + type_register_static(&allwinner_i2c_type_info); +} + +type_init(allwinner_i2c_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_CCM select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC + select ALLWINNER_I2C select SERIAL select UNIMP @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 bool select ALLWINNER_A10_PIT select ALLWINNER_SUN8I_EMAC + select ALLWINNER_I2C select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/i2c/Kconfig b/hw/i2c/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/Kconfig +++ b/hw/i2c/Kconfig @@ -XXX,XX +XXX,XX @@ config MPC_I2C bool select I2C +config ALLWINNER_I2C + bool + select I2C + config PCA954X bool select I2C diff --git a/hw/i2c/meson.build b/hw/i2c/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/meson.build +++ b/hw/i2c/meson.build @@ -XXX,XX +XXX,XX @@ i2c_ss.add(when: 'CONFIG_BITBANG_I2C', if_true: files('bitbang_i2c.c')) i2c_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_i2c.c')) i2c_ss.add(when: 'CONFIG_IMX_I2C', if_true: files('imx_i2c.c')) i2c_ss.add(when: 'CONFIG_MPC_I2C', if_true: files('mpc_i2c.c')) +i2c_ss.add(when: 'CONFIG_ALLWINNER_I2C', if_true: files('allwinner-i2c.c')) i2c_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('microbit_i2c.c')) i2c_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_smbus.c')) i2c_ss.add(when: 'CONFIG_SMBUS_EEPROM', if_true: files('smbus_eeprom.c')) diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -XXX,XX +XXX,XX @@ i2c_send_async(uint8_t address, uint8_t data) "send_async(addr:0x%02x) data:0x%0 i2c_recv(uint8_t address, uint8_t data) "recv(addr:0x%02x) data:0x%02x" i2c_ack(void) "" +# allwinner_i2c.c + +allwinner_i2c_read(const char* reg_name, uint64_t offset, uint64_t value) "read %s [0x%" PRIx64 "]: -> 0x%" PRIx64 +allwinner_i2c_write(const char* reg_name, uint64_t offset, uint64_t value) "write %s [0x%" PRIx64 "]: <- 0x%" PRIx64 + # aspeed_i2c.c aspeed_i2c_bus_cmd(uint32_t cmd, const char *cmd_flags, uint32_t count, uint32_t intr_status) "handling cmd=0x%x %s count=%d intr=0x%x" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch adds minimal support for AXP-209 PMU. Most important is chip ID since U-Boot SPL expects version 0x1. Besides the chip ID register, reset values for two more registers used by A10 U-Boot SPL are covered. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Message-id: 20221226220303.14420-5-strahinja.p.jankovic@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/axp209.c | 238 +++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + hw/misc/Kconfig | 4 + hw/misc/meson.build | 1 + hw/misc/trace-events | 5 + 5 files changed, 250 insertions(+) create mode 100644 hw/misc/axp209.c diff --git a/hw/misc/axp209.c b/hw/misc/axp209.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/axp209.c @@ -XXX,XX +XXX,XX @@ +/* + * AXP-209 PMU Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "trace.h" +#include "hw/i2c/i2c.h" +#include "migration/vmstate.h" + +#define TYPE_AXP209_PMU "axp209_pmu" + +#define AXP209(obj) \ + OBJECT_CHECK(AXP209I2CState, (obj), TYPE_AXP209_PMU) + +/* registers */ +enum { + REG_POWER_STATUS = 0x0u, + REG_OPERATING_MODE, + REG_OTG_VBUS_STATUS, + REG_CHIP_VERSION, + REG_DATA_CACHE_0, + REG_DATA_CACHE_1, + REG_DATA_CACHE_2, + REG_DATA_CACHE_3, + REG_DATA_CACHE_4, + REG_DATA_CACHE_5, + REG_DATA_CACHE_6, + REG_DATA_CACHE_7, + REG_DATA_CACHE_8, + REG_DATA_CACHE_9, + REG_DATA_CACHE_A, + REG_DATA_CACHE_B, + REG_POWER_OUTPUT_CTRL = 0x12u, + REG_DC_DC2_OUT_V_CTRL = 0x23u, + REG_DC_DC2_DVS_CTRL = 0x25u, + REG_DC_DC3_OUT_V_CTRL = 0x27u, + REG_LDO2_4_OUT_V_CTRL, + REG_LDO3_OUT_V_CTRL, + REG_VBUS_CH_MGMT = 0x30u, + REG_SHUTDOWN_V_CTRL, + REG_SHUTDOWN_CTRL, + REG_CHARGE_CTRL_1, + REG_CHARGE_CTRL_2, + REG_SPARE_CHARGE_CTRL, + REG_PEK_KEY_CTRL, + REG_DC_DC_FREQ_SET, + REG_CHR_TEMP_TH_SET, + REG_CHR_HIGH_TEMP_TH_CTRL, + REG_IPSOUT_WARN_L1, + REG_IPSOUT_WARN_L2, + REG_DISCHR_TEMP_TH_SET, + REG_DISCHR_HIGH_TEMP_TH_CTRL, + REG_IRQ_BANK_1_CTRL = 0x40u, + REG_IRQ_BANK_2_CTRL, + REG_IRQ_BANK_3_CTRL, + REG_IRQ_BANK_4_CTRL, + REG_IRQ_BANK_5_CTRL, + REG_IRQ_BANK_1_STAT = 0x48u, + REG_IRQ_BANK_2_STAT, + REG_IRQ_BANK_3_STAT, + REG_IRQ_BANK_4_STAT, + REG_IRQ_BANK_5_STAT, + REG_ADC_ACIN_V_H = 0x56u, + REG_ADC_ACIN_V_L, + REG_ADC_ACIN_CURR_H, + REG_ADC_ACIN_CURR_L, + REG_ADC_VBUS_V_H, + REG_ADC_VBUS_V_L, + REG_ADC_VBUS_CURR_H, + REG_ADC_VBUS_CURR_L, + REG_ADC_INT_TEMP_H, + REG_ADC_INT_TEMP_L, + REG_ADC_TEMP_SENS_V_H = 0x62u, + REG_ADC_TEMP_SENS_V_L, + REG_ADC_BAT_V_H = 0x78u, + REG_ADC_BAT_V_L, + REG_ADC_BAT_DISCHR_CURR_H, + REG_ADC_BAT_DISCHR_CURR_L, + REG_ADC_BAT_CHR_CURR_H, + REG_ADC_BAT_CHR_CURR_L, + REG_ADC_IPSOUT_V_H, + REG_ADC_IPSOUT_V_L, + REG_DC_DC_MOD_SEL = 0x80u, + REG_ADC_EN_1, + REG_ADC_EN_2, + REG_ADC_SR_CTRL, + REG_ADC_IN_RANGE, + REG_GPIO1_ADC_IRQ_RISING_TH, + REG_GPIO1_ADC_IRQ_FALLING_TH, + REG_TIMER_CTRL = 0x8au, + REG_VBUS_CTRL_MON_SRP, + REG_OVER_TEMP_SHUTDOWN = 0x8fu, + REG_GPIO0_FEAT_SET, + REG_GPIO_OUT_HIGH_SET, + REG_GPIO1_FEAT_SET, + REG_GPIO2_FEAT_SET, + REG_GPIO_SIG_STATE_SET_MON, + REG_GPIO3_SET, + REG_COULOMB_CNTR_CTRL = 0xb8u, + REG_POWER_MEAS_RES, + NR_REGS +}; + +#define AXP209_CHIP_VERSION_ID (0x01) +#define AXP209_DC_DC2_OUT_V_CTRL_RESET (0x16) +#define AXP209_IRQ_BANK_1_CTRL_RESET (0xd8) + +/* A simple I2C slave which returns values of ID or CNT register. */ +typedef struct AXP209I2CState { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + uint8_t regs[NR_REGS]; /* peripheral registers */ + uint8_t ptr; /* current register index */ + uint8_t count; /* counter used for tx/rx */ +} AXP209I2CState; + +/* Reset all counters and load ID register */ +static void axp209_reset_enter(Object *obj, ResetType type) +{ + AXP209I2CState *s = AXP209(obj); + + memset(s->regs, 0, NR_REGS); + s->ptr = 0; + s->count = 0; + s->regs[REG_CHIP_VERSION] = AXP209_CHIP_VERSION_ID; + s->regs[REG_DC_DC2_OUT_V_CTRL] = AXP209_DC_DC2_OUT_V_CTRL_RESET; + s->regs[REG_IRQ_BANK_1_CTRL] = AXP209_IRQ_BANK_1_CTRL_RESET; +} + +/* Handle events from master. */ +static int axp209_event(I2CSlave *i2c, enum i2c_event event) +{ + AXP209I2CState *s = AXP209(i2c); + + s->count = 0; + + return 0; +} + +/* Called when master requests read */ +static uint8_t axp209_rx(I2CSlave *i2c) +{ + AXP209I2CState *s = AXP209(i2c); + uint8_t ret = 0xff; + + if (s->ptr < NR_REGS) { + ret = s->regs[s->ptr++]; + } + + trace_axp209_rx(s->ptr - 1, ret); + + return ret; +} + +/* + * Called when master sends write. + * Update ptr with byte 0, then perform write with second byte. + */ +static int axp209_tx(I2CSlave *i2c, uint8_t data) +{ + AXP209I2CState *s = AXP209(i2c); + + if (s->count == 0) { + /* Store register address */ + s->ptr = data; + s->count++; + trace_axp209_select(data); + } else { + trace_axp209_tx(s->ptr, data); + if (s->ptr == REG_DC_DC2_OUT_V_CTRL) { + s->regs[s->ptr++] = data; + } + } + + return 0; +} + +static const VMStateDescription vmstate_axp209 = { + .name = TYPE_AXP209_PMU, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(regs, AXP209I2CState, NR_REGS), + VMSTATE_UINT8(count, AXP209I2CState), + VMSTATE_UINT8(ptr, AXP209I2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void axp209_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); + + rc->phases.enter = axp209_reset_enter; + dc->vmsd = &vmstate_axp209; + isc->event = axp209_event; + isc->recv = axp209_rx; + isc->send = axp209_tx; +} + +static const TypeInfo axp209_info = { + .name = TYPE_AXP209_PMU, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(AXP209I2CState), + .class_init = axp209_class_init +}; + +static void axp209_register_devices(void) +{ + type_register_static(&axp209_info); +} + +type_init(axp209_register_devices); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ ARM Machines Allwinner-a10 M: Beniamino Galvani <b.galvani@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> +R: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c F: docs/system/arm/cubieboard.rst +F: hw/misc/axp209.c Allwinner-h3 M: Niek Linnenbank <nieklinnenbank@gmail.com> diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10_CCM config ALLWINNER_A10_DRAMC bool +config AXP209_PMU + bool + depends on I2C + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c' softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) +softmmu_ss.add(when: 'CONFIG_AXP209_PMU', if_true: files('axp209.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) softmmu_ss.add(when: 'CONFIG_ECCMEMCTL', if_true: files('eccmemctl.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" avr_power_read(uint8_t value) "power_reduc read value:%u" avr_power_write(uint8_t value) "power_reduc write value:%u" +# axp209.c +axp209_rx(uint8_t reg, uint8_t data) "Read reg 0x%" PRIx8 " : 0x%" PRIx8 +axp209_select(uint8_t reg) "Accessing reg 0x%" PRIx8 +axp209_tx(uint8_t reg, uint8_t data) "Write reg 0x%" PRIx8 " : 0x%" PRIx8 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> SPL Boot for Cubieboard expects AXP209 connected to I2C0 bus. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20221226220303.14420-6-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/cubieboard.c | 6 ++++++ hw/arm/Kconfig | 1 + 2 files changed, 7 insertions(+) diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" +#include "hw/i2c/i2c.h" static struct arm_boot_info cubieboard_binfo = { .loader_start = AW_A10_SDRAM_BASE, @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) BlockBackend *blk; BusState *bus; DeviceState *carddev; + I2CBus *i2c; /* BIOS is not supported by this board */ if (machine->firmware) { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) exit(1); } + /* Connect AXP 209 */ + i2c = I2C_BUS(qdev_get_child_bus(DEVICE(&a10->i2c0), "i2c")); + i2c_slave_create_simple(i2c, "axp209_pmu", 0x34); + /* Retrieve SD bus */ di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select ALLWINNER_I2C + select AXP209_PMU select SERIAL select UNIMP -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch enables copying of SPL from MMC if `-kernel` parameter is not passed when starting QEMU. SPL is copied to SRAM_A. The approach is reused from Allwinner H3 implementation. Tested with Armbian and custom Yocto image. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-7-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 21 +++++++++++++++++++++ hw/arm/allwinner-a10.c | 18 ++++++++++++++++++ hw/arm/cubieboard.c | 5 +++++ 3 files changed, 44 insertions(+) diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" #include "hw/i2c/allwinner-i2c.h" +#include "sysemu/block-backend.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { OHCISysBusState ohci[AW_A10_NUM_USB]; }; +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner A10 SoC contains a Boot ROM + * which is the first code that runs right after + * the SoC is powered on. The Boot ROM is responsible + * for loading user code (e.g. a bootloader) from any + * of the supported external devices and writing the + * downloaded code to internal SRAM. After loading the SoC + * begins executing the code written to SRAM. + * + * This function emulates the Boot ROM by copying 32 KiB + * of data at offset 8 KiB from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner A10 state object pointer + * @blk: Block backend device object pointer + */ +void allwinner_a10_bootrom_setup(AwA10State *s, BlockBackend *blk); + #endif diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#include "hw/loader.h" +#define AW_A10_SRAM_A_BASE 0x00000000 #define AW_A10_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 @@ -XXX,XX +XXX,XX @@ #define AW_A10_RTC_BASE 0x01c20d00 #define AW_A10_I2C0_BASE 0x01c2ac00 +void allwinner_a10_bootrom_setup(AwA10State *s, BlockBackend *blk) +{ + const int64_t rom_size = 32 * KiB; + g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); + + if (blk_pread(blk, 8 * KiB, rom_size, buffer, 0) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return; + } + + rom_add_blob("allwinner-a10.bootrom", buffer, rom_size, + rom_size, AW_A10_SRAM_A_BASE, + NULL, NULL, NULL, NULL, false); +} + static void aw_a10_init(Object *obj) { AwA10State *s = AW_A10(obj); diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE, machine->ram); + /* Load target kernel or start using BootROM */ + if (!machine->kernel_filename && blk && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + allwinner_a10_bootrom_setup(a10, blk); + } /* TODO create and connect IDE devices for ide_drive_get() */ cubieboard_binfo.ram_size = machine->ram_size; -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> Cubieboard now can boot directly from SD card, without the need to pass `-kernel` parameter. Update Avocado tests to cover this functionality. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-8-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/boot_linux_console.py | 47 +++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_sata(self): 'sda') # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_cubieboard_openwrt_22_03_2(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:cubieboard + :avocado: tags=device:sd + """ + + # This test download a 7.5 MiB compressed image and expand it + # to 126 MiB. + image_url = ('https://downloads.openwrt.org/releases/22.03.2/targets/' + 'sunxi/cortexa8/openwrt-22.03.2-sunxi-cortexa8-' + 'cubietech_a10-cubieboard-ext4-sdcard.img.gz') + image_hash = ('94b5ecbfbc0b3b56276e5146b899eafa' + '2ac5dc2d08733d6705af9f144f39f554') + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash, + algorithm='sha256') + image_path = archive.extract(image_path_gz, self.workdir) + image_pow2ceil_expand(image_path) + + self.vm.set_console() + self.vm.add_args('-drive', 'file=' + image_path + ',if=sd,format=raw', + '-nic', 'user', + '-no-reboot') + self.vm.launch() + + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'usbcore.nousb ' + 'noreboot') + + self.wait_for_console_pattern('U-Boot SPL') + + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', '=>') + exec_command_and_wait_for_pattern(self, "setenv extraargs '" + + kernel_command_line + "'", '=>') + exec_command_and_wait_for_pattern(self, 'boot', 'Starting kernel ...'); + + self.wait_for_console_pattern( + 'Please press Enter to activate this console.') + + exec_command_and_wait_for_pattern(self, ' ', 'root@') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun4i/sun5i') + # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_TIMEOUT_EXPECTED'), 'Test might timeout') def test_arm_quanta_gsj(self): """ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Don't dereference CPUTLBEntryFull until we verify that the page is valid. Move the other user-only info field updates after the valid check to match. Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1412 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230104190056.305143-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, #ifdef CONFIG_USER_ONLY flags = probe_access_flags(env, addr, access_type, mmu_idx, nofault, &info->host, retaddr); - memset(&info->attrs, 0, sizeof(info->attrs)); - /* Require both ANON and MTE; see allocation_tag_mem(). */ - info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); #else CPUTLBEntryFull *full; flags = probe_access_full(env, addr, access_type, mmu_idx, nofault, &info->host, &full, retaddr); - info->attrs = full->attrs; - info->tagged = full->pte_attrs == 0xf0; #endif info->flags = flags; @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, return false; } +#ifdef CONFIG_USER_ONLY + memset(&info->attrs, 0, sizeof(info->attrs)); + /* Require both ANON and MTE; see allocation_tag_mem(). */ + info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); +#else + info->attrs = full->attrs; + info->tagged = full->pte_attrs == 0xf0; +#endif + /* Ensure that info->host[] is relative to addr, not addr + mem_off. */ info->host -= mem_off; return true; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa255_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 2 +- hw/arm/gumstix.c | 3 +-- hw/arm/pxa2xx.c | 4 +++- hw/arm/tosa.c | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, const char *revision); -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size); +PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t connex_rom = 0x01000000; uint32_t connex_ram = 0x04000000; - cpu = pxa255_init(address_space_mem, connex_ram); + cpu = pxa255_init(connex_ram); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" +#include "exec/address-spaces.h" #include "cpu.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(MemoryRegion *address_space, } /* Initialise a PXA255 integrated chip (ARM based core). */ -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size) +PXA2xxState *pxa255_init(unsigned int sdram_size) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/tosa.c +++ b/hw/arm/tosa.c @@ -XXX,XX +XXX,XX @@ static void tosa_init(MachineState *machine) TC6393xbState *tmio; DeviceState *scp0, *scp1; - mpu = pxa255_init(address_space_mem, tosa_binfo.ram_size); + mpu = pxa255_init(tosa_binfo.ram_size); memory_region_init_rom(rom, NULL, "tosa.rom", TOSA_ROM, &error_fatal); memory_region_add_subregion(address_space_mem, 0, rom); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa270_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 3 +-- hw/arm/gumstix.c | 3 +-- hw/arm/mainstone.c | 10 ++++------ hw/arm/pxa2xx.c | 4 ++-- hw/arm/spitz.c | 6 ++---- hw/arm/z2.c | 3 +-- 6 files changed, 11 insertions(+), 18 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { # define PA_FMT "0x%08lx" -PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, - const char *revision); +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *revision); PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t verdex_rom = 0x02000000; uint32_t verdex_ram = 0x10000000; - cpu = pxa270_init(address_space_mem, verdex_ram, machine->cpu_type); + cpu = pxa270_init(verdex_ram, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info mainstone_binfo = { .ram_size = 0x04000000, }; -static void mainstone_common_init(MemoryRegion *address_space_mem, - MachineState *machine, +static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { uint32_t sector_len = 256 * 1024; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, mainstone_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0x00000000, rom); /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, static void mainstone_init(MachineState *machine) { - mainstone_common_init(get_system_memory(), machine, mainstone, 0x196); + mainstone_common_init(machine, mainstone, 0x196); } static void mainstone2_machine_init(MachineClass *mc) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_reset(void *opaque, int line, int level) } /* Initialise a PXA270 integrated chip (ARM based core). */ -PXA2xxState *pxa270_init(MemoryRegion *address_space, - unsigned int sdram_size, const char *cpu_type) +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -XXX,XX +XXX,XX @@ static void spitz_common_init(MachineState *machine) SpitzMachineState *sms = SPITZ_MACHINE(machine); enum spitz_model_e model = smc->model; PXA2xxState *mpu; - MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, spitz_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(spitz_binfo.ram_size, machine->cpu_type); sms->mpu = mpu; sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M); memory_region_init_rom(rom, NULL, "spitz.rom", SPITZ_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0, rom); /* Setup peripherals */ spitz_keyboard_register(mpu); diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { static void z2_init(MachineState *machine) { - MemoryRegion *address_space_mem = get_system_memory(); uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) DeviceState *wm; /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, z2_binfo.ram_size, machine->cpu_type); + mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "qom/object.h" +#define RAM_SIZE (512 * MiB) +#define FLASH_SIZE (32 * MiB) +#define FLASH_SECTOR_SIZE (64 * KiB) + struct CollieMachineState { MachineState parent; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(CollieMachineState, COLLIE_MACHINE) static struct arm_boot_info collie_binfo = { .loader_start = SA_SDCS0, - .ram_size = 0x20000000, + .ram_size = RAM_SIZE, }; static void collie_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", 0x02000000, + pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", 0x02000000, + pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); sysbus_create_simple("scoop", 0x40800000, NULL); @@ -XXX,XX +XXX,XX @@ static void collie_machine_class_init(ObjectClass *oc, void *data) mc->init = collie_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("sa1110"); - mc->default_ram_size = 0x20000000; + mc->default_ram_size = RAM_SIZE; mc->default_ram_id = "strongarm.sdram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info collie_binfo = { static void collie_init(MachineState *machine) { - DriveInfo *dinfo; MachineClass *mc = MACHINE_GET_CLASS(machine); CollieMachineState *cms = COLLIE_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); - dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); - - dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + for (unsigned i = 0; i < 2; i++) { + DriveInfo *dinfo = drive_get(IF_PFLASH, 0, i); + pflash_cfi01_register(i ? SA_CS1 : SA_CS0, + i ? "collie.fl2" : "collie.fl1", FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + } sysbus_create_simple("scoop", 0x40800000, NULL); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a comment describing the Connex uses a Numonyx RC28F128J3F75 flash, and the Verdex uses a Micron RC28F256P30TFA. Correct the Verdex machine description (we model the 'Pro' board). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-6-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ * Contributions after 2012-01-13 are licensed under the terms of the * GNU GPL, version 2 or (at your option) any later version. */ - + /* * Example usage: * @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) exit(1); } + /* Numonyx RC28F128J3F75 */ if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) exit(1); } + /* Micron RC28F256P30TFA */ if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); - mc->desc = "Gumstix Verdex (PXA270)"; + mc->desc = "Gumstix Verdex Pro XL6P COMs (PXA270)"; mc->init = verdex_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-7-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "hw/arm/pxa.h" #include "net/net.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "cpu.h" -static const int sector_len = 128 * 1024; +#define CONNEX_FLASH_SIZE (16 * MiB) +#define CONNEX_RAM_SIZE (64 * MiB) + +#define VERDEX_FLASH_SIZE (32 * MiB) +#define VERDEX_RAM_SIZE (256 * MiB) + +#define FLASH_SECTOR_SIZE (128 * KiB) static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t connex_rom = 0x01000000; - uint32_t connex_ram = 0x04000000; - - cpu = pxa255_init(connex_ram); + cpu = pxa255_init(CONNEX_RAM_SIZE); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, + if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t verdex_rom = 0x02000000; - uint32_t verdex_ram = 0x10000000; - - cpu = pxa270_init(verdex_ram, machine->cpu_type); + cpu = pxa270_init(VERDEX_RAM_SIZE, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, + if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mainstone.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ * GNU GPL, version 2 or (at your option) any later version. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/arm/pxa.h" @@ -XXX,XX +XXX,XX @@ static const struct keymap map[0xE0] = { enum mainstone_model_e { mainstone }; -#define MAINSTONE_RAM 0x04000000 -#define MAINSTONE_ROM 0x00800000 -#define MAINSTONE_FLASH 0x02000000 +#define MAINSTONE_RAM_SIZE (64 * MiB) +#define MAINSTONE_ROM_SIZE (8 * MiB) +#define MAINSTONE_FLASH_SIZE (32 * MiB) static struct arm_boot_info mainstone_binfo = { .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = 0x04000000, + .ram_size = MAINSTONE_RAM_SIZE, }; +#define FLASH_SECTOR_SIZE (256 * KiB) + static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { - uint32_t sector_len = 256 * 1024; hwaddr mainstone_flash_base[] = { MST_FLASH_0, MST_FLASH_1 }; PXA2xxState *mpu; DeviceState *mst_irq; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* Setup CPU & memory */ mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); - memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, + memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM_SIZE, &error_fatal); memory_region_add_subregion(get_system_memory(), 0x00000000, rom); @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, dinfo = drive_get(IF_PFLASH, 0, i); if (!pflash_cfi01_register(mainstone_flash_base[i], i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH, + MAINSTONE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/musicpal.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "cpu.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo musicpal_key_info = { .class_init = musicpal_key_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static struct arm_boot_info musicpal_binfo = { .loader_start = 0x0, .board_id = 0x20e, @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) BlockBackend *blk = blk_by_legacy_dinfo(dinfo); flash_size = blk_getlength(blk); - if (flash_size != 8*1024*1024 && flash_size != 16*1024*1024 && - flash_size != 32*1024*1024) { + if (flash_size != 8 * MiB && flash_size != 16 * MiB && + flash_size != 32 * MiB) { error_report("Invalid flash image size"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) */ pflash_cfi02_register(0x100000000ULL - MP_FLASH_SIZE_MAX, "musicpal.flash", flash_size, - blk, 0x10000, + blk, FLASH_SECTOR_SIZE, MP_FLASH_SIZE_MAX / flash_size, 2, 0x00BF, 0x236D, 0x0000, 0x0000, 0x5555, 0x2AAA, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The total_ram_v1/total_ram_v2 definitions were never used. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { #define flash0_size (16 * 1024 * 1024) #define flash1_size ( 8 * 1024 * 1024) #define flash2_size (32 * 1024 * 1024) -#define total_ram_v1 (sdram_size + flash0_size + flash1_size + OMAP15XX_SRAM_SIZE) -#define total_ram_v2 (sdram_size + flash2_size + OMAP15XX_SRAM_SIZE) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "ui/console.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -#define sdram_size 0x02000000 -#define sector_size (128 * 1024) -#define flash0_size (16 * 1024 * 1024) -#define flash1_size ( 8 * 1024 * 1024) -#define flash2_size (32 * 1024 * 1024) +#define SDRAM_SIZE (32 * MiB) +#define SECTOR_SIZE (128 * KiB) +#define FLASH0_SIZE (16 * MiB) +#define FLASH1_SIZE (8 * MiB) +#define FLASH2_SIZE (32 * MiB) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, - .ram_size = sdram_size, + .ram_size = SDRAM_SIZE, .board_id = 0x265, }; @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) static uint32_t cs3val = 0x00001139; DriveInfo *dinfo; int fl_idx; - uint32_t flash_size = flash0_size; + uint32_t flash_size = FLASH0_SIZE; if (machine->ram_size != mc->default_ram_size) { char *sz = size_to_str(mc->default_ram_size); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) } if (version == 2) { - flash_size = flash2_size; + flash_size = FLASH2_SIZE; } memory_region_add_subregion(address_space, OMAP_EMIFF_BASE, machine->ram); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) if (!pflash_cfi01_register(OMAP_CS0_BASE, "omap_sx1.flash0-1", flash_size, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) (dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { MemoryRegion *flash_1 = g_new(MemoryRegion, 1); memory_region_init_rom(flash_1, NULL, "omap_sx1.flash1-0", - flash1_size, &error_fatal); + FLASH1_SIZE, &error_fatal); memory_region_add_subregion(address_space, OMAP_CS1_BASE, flash_1); memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, - "sx1.cs1", OMAP_CS1_SIZE - flash1_size); + "sx1.cs1", OMAP_CS1_SIZE - FLASH1_SIZE); memory_region_add_subregion(address_space, - OMAP_CS1_BASE + flash1_size, &cs[1]); + OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", flash1_size, + "omap_sx1.flash1-1", FLASH1_SIZE, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v2_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v2; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v1_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v1; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/z2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "hw/arm/pxa.h" #include "hw/arm/boot.h" #include "hw/i2c/i2c.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { .class_init = aer915_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static void z2_init(MachineState *machine) { - uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; void *z2_lcd; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Upon introduction in commit b8433303fb ("Set proper device-width for vexpress flash"), ve_pflash_cfi01_register() was calling qdev_init_nofail() which can not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/vexpress.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); pflash0 = ve_pflash_cfi01_register(map[VE_NORFLASH0], "vexpress.flash0", dinfo); - if (!pflash0) { - error_report("vexpress: error registering flash 0"); - exit(1); - } if (map[VE_NORFLASHALIAS] != -1) { /* Map flash 0 as an alias into low memory */ @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) } dinfo = drive_get(IF_PFLASH, 0, 1); - if (!ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", - dinfo)) { - error_report("vexpress: error registering flash 1"); - exit(1); - } + ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", dinfo); sram_size = 0x2000000; memory_region_init_ram(sram, NULL, "vexpress.sram", sram_size, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since its QOM'ification in commit 368a354f02 ("pflash_cfi0x: QOMified") the pflash_cfi01_register() function does not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 18 ++++++------------ hw/arm/mainstone.c | 13 +++++-------- hw/arm/omap_sx1.c | 22 ++++++++-------------- hw/arm/versatilepb.c | 6 ++---- hw/arm/z2.c | 9 +++------ 5 files changed, 24 insertions(+), 44 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 36 */ smc91c111_init(&nd_table[0], 0x04000300, @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 99 */ smc91c111_init(&nd_table[0], 0x04000300, diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { dinfo = drive_get(IF_PFLASH, 0, i); - if (!pflash_cfi01_register(mainstone_flash_base[i], - i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(mainstone_flash_base[i], + i ? "mainstone.flash1" : "mainstone.flash0", + MAINSTONE_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); } mst_irq = sysbus_create_simple("mainstone-fpga", MST_FPGA_PHYS, diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) fl_idx = 0; if ((dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { - if (!pflash_cfi01_register(OMAP_CS0_BASE, - "omap_sx1.flash0-1", flash_size, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS0_BASE, + "omap_sx1.flash0-1", flash_size, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) memory_region_add_subregion(address_space, OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); - if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", FLASH1_SIZE, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS1_BASE, + "omap_sx1.flash1-1", FLASH1_SIZE, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } else { memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -XXX,XX +XXX,XX @@ static void versatile_init(MachineState *machine, int board_id) /* 0x34000000 NOR Flash */ dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", + pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", VERSATILE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, VERSATILE_FLASH_SECT_SIZE, - 4, 0x0089, 0x0018, 0x0000, 0x0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory.\n"); - } + 4, 0x0089, 0x0018, 0x0000, 0x0, 0); versatile_binfo.ram_size = machine->ram_size; versatile_binfo.board_id = board_id; diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); /* setup keypad */ pxa27x_register_keypad(mpu->kp, map, 0x100); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> To avoid forward-declaring PXA2xxI2CState, declare PXA2XX_I2C before its use in pxa2xx_i2c_init() prototype. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ void pxa27x_register_keypad(PXA2xxKeyPadState *kp, const struct keymap *map, int size); /* pxa2xx.c */ -typedef struct PXA2xxI2CState PXA2xxI2CState; +#define TYPE_PXA2XX_I2C "pxa2xx_i2c" +OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) + PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, qemu_irq irq, uint32_t page_size); I2CBus *pxa2xx_i2c_bus(PXA2xxI2CState *s); -#define TYPE_PXA2XX_I2C "pxa2xx_i2c" typedef struct PXA2xxI2SState PXA2xxI2SState; -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) #define TYPE_PXA2XX_FIR "pxa2xx-fir" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxFIrState, PXA2XX_FIR) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add a local 'struct omap_gpif_s *' variable to improve readability. (This also eases next commit conversion). Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/omap_gpio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpio_s *s = &((struct omap_gpif_s *) opaque)->omap1; + struct omap_gpif_s *p = opaque; + struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; if (level) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap1.c | 115 ++++++++++++++++++-------------------- hw/arm/omap2.c | 40 ++++++------- hw/arm/omap_sx1.c | 2 +- hw/arm/palm.c | 2 +- hw/char/omap_uart.c | 7 +-- hw/display/omap_dss.c | 15 +++-- hw/display/omap_lcdc.c | 9 ++- hw/dma/omap_dma.c | 15 +++-- hw/gpio/omap_gpio.c | 15 +++-- hw/intc/omap_intc.c | 12 ++-- hw/misc/omap_gpmc.c | 12 ++-- hw/misc/omap_l4.c | 7 +-- hw/misc/omap_sdrc.c | 7 +-- hw/misc/omap_tap.c | 5 +- hw/sd/omap_mmc.c | 9 ++- hw/ssi/omap_spi.c | 7 +-- hw/timer/omap_gptimer.c | 22 ++++---- hw/timer/omap_synctimer.c | 4 +- 18 files changed, 142 insertions(+), 163 deletions(-) diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap1.c +++ b/hw/arm/omap1.c @@ -XXX,XX +XXX,XX @@ static void omap_timer_fire(void *opaque) static void omap_timer_tick(void *opaque) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); omap_timer_fire(timer); @@ -XXX,XX +XXX,XX @@ static void omap_timer_tick(void *opaque) static void omap_timer_clk_update(void *opaque, int line, int on) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ static void omap_timer_clk_setup(struct omap_mpu_timer_s *timer) static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, static void omap_mpu_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_watchdog_timer_s { static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, static void omap_wd_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_32khz_timer_s { static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, static void omap_os_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static struct omap_32khz_timer_s *omap_os_timer_init(MemoryRegion *memory, static uint64_t omap_ulpd_pm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_ulpd_req_update(struct omap_mpu_state_s *s, static void omap_ulpd_pm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; int64_t now, ticks; int div, mult; static const int bypass_div[4] = { 1, 2, 4, 4 }; @@ -XXX,XX +XXX,XX @@ static void omap_ulpd_pm_init(MemoryRegion *system_memory, static uint64_t omap_pin_cfg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_pin_modconf1_update(struct omap_mpu_state_s *s, static void omap_pin_cfg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t diff; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_pin_cfg_init(MemoryRegion *system_memory, static uint64_t omap_id_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static void omap_id_init(MemoryRegion *memory, struct omap_mpu_state_s *mpu) static uint64_t omap_mpui_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpui_read(void *opaque, hwaddr addr, static void omap_mpui_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_tipb_bridge_s { static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, static void omap_tipb_bridge_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static struct omap_tipb_bridge_s *omap_tipb_bridge_init( static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, static void omap_tcmi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct dpll_ctl_s { static uint64_t omap_dpll_read(void *opaque, hwaddr addr, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dpll_read(void *opaque, hwaddr addr, static void omap_dpll_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; uint16_t diff; static const int bypass_div[4] = { 1, 2, 4, 4 }; int div, mult; @@ -XXX,XX +XXX,XX @@ static struct dpll_ctl_s *omap_dpll_init(MemoryRegion *memory, static uint64_t omap_clkm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_clkm_ckout1_update(struct omap_mpu_state_s *s, static void omap_clkm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; omap_clk clk; static const char *clkschemename[8] = { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_clkm_ops = { static uint64_t omap_clkdsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; CPUState *cpu = CPU(s->cpu); if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_clkdsp_idlect2_update(struct omap_mpu_state_s *s, static void omap_clkdsp_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; if (size != 2) { @@ -XXX,XX +XXX,XX @@ struct omap_mpuio_s { static void omap_mpuio_set(void *opaque, int line, int level) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; uint16_t prev = s->inputs; if (level) @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_kbd_update(struct omap_mpuio_s *s) static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, static void omap_mpuio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_reset(struct omap_mpuio_s *s) static void omap_mpuio_onoff(void *opaque, int line, int on) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; s->clk = on; if (on) @@ -XXX,XX +XXX,XX @@ static void omap_uwire_transfer_start(struct omap_uwire_s *s) } } -static uint64_t omap_uwire_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uwire_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uwire_read(void *opaque, hwaddr addr, static void omap_uwire_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_update(struct omap_pwl_s *s) } } -static uint64_t omap_pwl_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwl_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwl_read(void *opaque, hwaddr addr, static void omap_pwl_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_reset(struct omap_pwl_s *s) static void omap_pwl_clk_update(void *opaque, int line, int on) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; s->clk = on; omap_pwl_update(s); @@ -XXX,XX +XXX,XX @@ struct omap_pwt_s { omap_clk clk; }; -static uint64_t omap_pwt_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwt_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwt_read(void *opaque, hwaddr addr, static void omap_pwt_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_rtc_alarm_update(struct omap_rtc_s *s) printf("%s: conversion failed\n", __func__); } -static uint64_t omap_rtc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rtc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint8_t i; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rtc_read(void *opaque, hwaddr addr, static void omap_rtc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; struct tm new_tm; time_t ti[2]; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_rx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_source_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->rx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_tx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_sink_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->tx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_req_update(struct omap_mcbsp_s *s) static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, static void omap_mcbsp_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; switch (offset) { @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_writeh(void *opaque, hwaddr addr, static void omap_mcbsp_writew(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (offset == 0x04) { /* DXR */ @@ -XXX,XX +XXX,XX @@ static struct omap_mcbsp_s *omap_mcbsp_init(MemoryRegion *system_memory, static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->rx_rate) { s->rx_req = s->codec->in.len; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) static void omap_mcbsp_i2s_start(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->tx_rate) { s->tx_req = s->codec->out.size; @@ -XXX,XX +XXX,XX @@ static void omap_lpg_reset(struct omap_lpg_s *s) omap_lpg_update(s); } -static uint64_t omap_lpg_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lpg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lpg_read(void *opaque, hwaddr addr, static void omap_lpg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_lpg_ops = { static void omap_lpg_clk_update(void *opaque, int line, int on) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; s->clk = on; omap_lpg_update(s); @@ -XXX,XX +XXX,XX @@ static void omap_setup_mpui_io(MemoryRegion *system_memory, /* General chip reset */ static void omap1_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_mpu_timer_reset(mpu->timer[0]); @@ -XXX,XX +XXX,XX @@ static void omap_setup_dsp_mapping(MemoryRegion *system_memory, void omap_mpu_wakeup(void *opaque, int irq, int req) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; CPUState *cpu = CPU(mpu->cpu); if (cpu->halted) { diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap2.c +++ b/hw/arm/omap2.c @@ -XXX,XX +XXX,XX @@ static inline void omap_eac_out_empty(struct omap_eac_s *s) static void omap_eac_in_cb(void *opaque, int avail_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.rxavail = avail_b >> 2; omap_eac_in_refill(s); @@ -XXX,XX +XXX,XX @@ static void omap_eac_in_cb(void *opaque, int avail_b) static void omap_eac_out_cb(void *opaque, int free_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.txavail = free_b >> 2; if (s->codec.txlen) @@ -XXX,XX +XXX,XX @@ static void omap_eac_reset(struct omap_eac_s *s) omap_eac_interrupt_update(s); } -static uint64_t omap_eac_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_eac_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; uint32_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_eac_read(void *opaque, hwaddr addr, static void omap_eac_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_sti_reset(struct omap_sti_s *s) static uint64_t omap_sti_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_read(void *opaque, hwaddr addr, static void omap_sti_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_sti_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, unsigned size) { OMAP_BAD_REG(addr); return 0; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, static void omap_sti_fifo_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; int ch = addr >> 6; uint8_t byte = value; @@ -XXX,XX +XXX,XX @@ static void omap_prcm_int_update(struct omap_prcm_s *s, int dom) static uint64_t omap_prcm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_prcm_dpll_update(struct omap_prcm_s *s) static void omap_prcm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_sysctl_s { static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int value; @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) return 0; } -static void omap_sysctl_write8(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write8(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int prev_value; @@ -XXX,XX +XXX,XX @@ static void omap_sysctl_write8(void *opaque, hwaddr addr, } } -static void omap_sysctl_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static struct omap_sysctl_s *omap_sysctl_init(struct omap_target_agent_s *ta, /* General chip reset */ static void omap2_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_prcm_reset(mpu->prcm); diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static uint64_t static_read(void *opaque, hwaddr offset, unsigned size) { - uint32_t *val = (uint32_t *) opaque; + uint32_t *val = opaque; uint32_t mask = (4 / size) - 1; return *val >> ((offset & mask) << 3); diff --git a/hw/arm/palm.c b/hw/arm/palm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/palm.c +++ b/hw/arm/palm.c @@ -XXX,XX +XXX,XX @@ static struct { static void palmte_button_event(void *opaque, int keycode) { - struct omap_mpu_state_s *cpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *cpu = opaque; if (palmte_keymap[keycode & 0x7f].row != -1) omap_mpuio_key(cpu->mpuio, diff --git a/hw/char/omap_uart.c b/hw/char/omap_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/omap_uart.c +++ b/hw/char/omap_uart.c @@ -XXX,XX +XXX,XX @@ struct omap_uart_s *omap_uart_init(hwaddr base, return s; } -static uint64_t omap_uart_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uart_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { return omap_badwidth_read8(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uart_read(void *opaque, hwaddr addr, static void omap_uart_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { omap_badwidth_write8(opaque, addr, value); diff --git a/hw/display/omap_dss.c b/hw/display/omap_dss.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_dss.c +++ b/hw/display/omap_dss.c @@ -XXX,XX +XXX,XX @@ void omap_dss_reset(struct omap_dss_s *s) static uint64_t omap_diss_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_diss_read(void *opaque, hwaddr addr, static void omap_diss_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_diss_ops = { static uint64_t omap_disc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_disc_read(void *opaque, hwaddr addr, static void omap_disc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_rfbi_transfer_start(struct omap_dss_s *s) omap_dispc_interrupt_update(s); } -static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, static void omap_rfbi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, static void omap_update_display(void *opaque) { - struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *omap_lcd = opaque; DisplaySurface *surface; drawfn draw_line; int size, height, first, last; @@ -XXX,XX +XXX,XX @@ static void omap_lcd_update(struct omap_lcd_panel_s *s) { } } -static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, static void omap_lcdc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ static int omap_dma_sys_read(struct omap_dma_s *s, int offset, return 0; } -static uint64_t omap_dma_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_dma_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma_read(void *opaque, hwaddr addr, static void omap_dma_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_dma_ops = { static void omap_dma_request(void *opaque, int drq, int req) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; /* The request pins are level triggered in QEMU. */ if (req) { if (~s->dma->drqbmp & (1ULL << drq)) { @@ -XXX,XX +XXX,XX @@ static void omap_dma_request(void *opaque, int drq, int req) /* XXX: this won't be needed once soc_dma knows about clocks. */ static void omap_dma_clk_update(void *opaque, int line, int on) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int i; s->dma->freq = omap_clk_getrate(s->clk); @@ -XXX,XX +XXX,XX @@ static void omap_dma_interrupts_4_update(struct omap_dma_s *s) static uint64_t omap_dma4_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int irqn = 0, chnum; struct omap_dma_channel_s *ch; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma4_read(void *opaque, hwaddr addr, static void omap_dma4_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int chnum, irqn = 0; struct omap_dma_channel_s *ch; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ static void omap_gpio_set(void *opaque, int line, int level) static uint64_t omap_gpio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpio_read(void *opaque, hwaddr addr, static void omap_gpio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_module_reset(struct omap2_gpio_s *s) static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; switch (addr) { case 0x00: /* GPIO_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) static void omap2_gpio_module_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; uint32_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) s->gpo = 0; } -static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; diff --git a/hw/misc/omap_gpmc.c b/hw/misc/omap_gpmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_gpmc.c +++ b/hw/misc/omap_gpmc.c @@ -XXX,XX +XXX,XX @@ static void omap_gpmc_dma_update(struct omap_gpmc_s *s, int value) static uint64_t omap_nand_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; uint64_t v; nand_setpins(f->dev, 0, 0, 0, 1, 0); switch (omap_gpmc_devsize(f)) { @@ -XXX,XX +XXX,XX @@ static void omap_nand_setio(DeviceState *dev, uint64_t value, static void omap_nand_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; nand_setpins(f->dev, 0, 0, 0, 1, 0); omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); } @@ -XXX,XX +XXX,XX @@ static void fill_prefetch_fifo(struct omap_gpmc_s *s) static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; uint32_t data; if (s->prefetch.config1 & 1) { /* The TRM doesn't define the behaviour if you read from the @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, static void omap_gpmc_prefetch_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs = prefetch_cs(s->prefetch.config1); if ((s->prefetch.config1 & 1) == 0) { /* The TRM doesn't define the behaviour of writing to the @@ -XXX,XX +XXX,XX @@ static int gpmc_wordaccess_only(hwaddr addr) static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, static void omap_gpmc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; diff --git a/hw/misc/omap_l4.c b/hw/misc/omap_l4.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_l4.c +++ b/hw/misc/omap_l4.c @@ -XXX,XX +XXX,XX @@ hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, return ta->start[region].size; } -static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, static void omap_l4ta_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_sdrc.c b/hw/misc/omap_sdrc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_sdrc.c +++ b/hw/misc/omap_sdrc.c @@ -XXX,XX +XXX,XX @@ void omap_sdrc_reset(struct omap_sdrc_s *s) s->config = 0x10; } -static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, static void omap_sdrc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_tap.c b/hw/misc/omap_tap.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_tap.c +++ b/hw/misc/omap_tap.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/omap.h" /* TEST-Chip-level TAP */ -static uint64_t omap_tap_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_tap_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ void omap_mmc_reset(struct omap_mmc_s *host) device_cold_reset(DEVICE(host->card)); } -static uint64_t omap_mmc_read(void *opaque, hwaddr offset, - unsigned size) +static uint64_t omap_mmc_read(void *opaque, hwaddr offset, unsigned size) { uint16_t i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, offset); @@ -XXX,XX +XXX,XX @@ static void omap_mmc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { int i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, offset, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_mmc_ops = { static void omap_mmc_cover_cb(void *opaque, int line, int level) { - struct omap_mmc_s *host = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *host = opaque; if (!host->cdet_state && level) { host->status |= 0x0002; diff --git a/hw/ssi/omap_spi.c b/hw/ssi/omap_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/omap_spi.c +++ b/hw/ssi/omap_spi.c @@ -XXX,XX +XXX,XX @@ void omap_mcspi_reset(struct omap_mcspi_s *s) omap_mcspi_interrupt_update(s); } -static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; uint32_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, static void omap_mcspi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; if (size != 4) { diff --git a/hw/timer/omap_gptimer.c b/hw/timer/omap_gptimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_gptimer.c +++ b/hw/timer/omap_gptimer.c @@ -XXX,XX +XXX,XX @@ static inline void omap_gp_timer_trigger(struct omap_gp_timer_s *timer) static void omap_gp_timer_tick(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (!timer->ar) { timer->st = 0; @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_tick(void *opaque) static void omap_gp_timer_match(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (timer->trigger == gpt_trigger_both) omap_gp_timer_trigger(timer); @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_match(void *opaque) static void omap_gp_timer_input(void *opaque, int line, int on) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; int trigger; switch (s->capture) { @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_input(void *opaque, int line, int on) static void omap_gp_timer_clk_update(void *opaque, int line, int on) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; omap_gp_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ void omap_gp_timer_reset(struct omap_gp_timer_s *s) static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; uint32_t ret; if (addr & 2) @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) } } -static void omap_gp_timer_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_write(void *opaque, hwaddr addr, } } -static void omap_gp_timer_writeh(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; if (addr & 2) omap_gp_timer_write(opaque, addr, (value << 16) | s->writeh); diff --git a/hw/timer/omap_synctimer.c b/hw/timer/omap_synctimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_synctimer.c +++ b/hw/timer/omap_synctimer.c @@ -XXX,XX +XXX,XX @@ void omap_synctimer_reset(struct omap_synctimer_s *s) static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; switch (addr) { case 0x00: /* 32KSYNCNT_REV */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) static uint32_t omap_synctimer_readh(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; uint32_t ret; if (addr & 2) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_gpif_s -> Omap1GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 6 +++--- hw/gpio/omap_gpio.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_i2c_set_fclk(OMAPI2CState *i2c, omap_clk clk); /* omap_gpio.c */ #define TYPE_OMAP1_GPIO "omap-gpio" -DECLARE_INSTANCE_CHECKER(struct omap_gpif_s, OMAP1_GPIO, +typedef struct Omap1GpioState Omap1GpioState; +DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap_gpif_s omap_gpif; typedef struct omap2_gpif_s omap2_gpif; /* TODO: clock framework (see above) */ -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk); +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpio_s { uint16_t pins; }; -struct omap_gpif_s { +struct Omap1GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpif_s *p = opaque; + Omap1GpioState *p = opaque; struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpio_module_ops = { static void omap_gpif_reset(DeviceState *dev) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); omap_gpio_reset(&s->omap1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpif_top_ops = { static void omap_gpio_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_gpif_s *s = OMAP1_GPIO(obj); + Omap1GpioState *s = OMAP1_GPIO(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); qdev_init_gpio_in(dev, omap_gpio_set, 16); @@ -XXX,XX +XXX,XX @@ static void omap_gpio_init(Object *obj) static void omap_gpio_realize(DeviceState *dev, Error **errp) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); if (!s->clk) { error_setg(errp, "omap-gpio: clk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_realize(DeviceState *dev, Error **errp) } } -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk) +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk) { gpio->clk = clk; } static Property omap_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap1GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap_gpio_info = { .name = TYPE_OMAP1_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap_gpif_s), + .instance_size = sizeof(Omap1GpioState), .instance_init = omap_gpio_init, .class_init = omap_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap2_gpif_s -> Omap2GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/gpio/omap_gpio.c | 20 ++++++++++---------- 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" -DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, +typedef struct Omap2GpioState Omap2GpioState; +DECLARE_INSTANCE_CHECKER(Omap2GpioState, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap2_gpif_s omap2_gpif; - /* TODO: clock framework (see above) */ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk); +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk); /* OMAP2 l4 Interconnect */ struct omap_l4_s; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap2_gpio_s { uint8_t delay; }; -struct omap2_gpif_s { +struct Omap2GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ static inline void omap2_gpio_module_int(struct omap2_gpio_s *s, int line) static void omap2_gpio_set(void *opaque, int line, int level) { - struct omap2_gpif_s *p = opaque; + Omap2GpioState *p = opaque; struct omap2_gpio_s *s = &p->modules[line >> 5]; line &= 31; @@ -XXX,XX +XXX,XX @@ static void omap_gpif_reset(DeviceState *dev) static void omap2_gpif_reset(DeviceState *dev) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); int i; for (i = 0; i < s->modulecount; i++) { @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static void omap_gpio_realize(DeviceState *dev, Error **errp) static void omap2_gpio_realize(DeviceState *dev, Error **errp) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); SysBusDevice *sbd = SYS_BUS_DEVICE(dev); int i; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_gpio_info = { .class_init = omap_gpio_class_init, }; -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk) +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk) { gpio->iclk = clk; } -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk) +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk) { assert(i <= 5); gpio->fclk[i] = clk; } static Property omap2_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap2_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap2GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap2_gpio_info = { .name = TYPE_OMAP2_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap2_gpif_s), + .instance_size = sizeof(Omap2GpioState), .class_init = omap2_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_intr_handler_s -> OMAPIntcState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/intc/omap_intc.c | 38 +++++++++++++++++++------------------- 2 files changed, 23 insertions(+), 24 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_clk_reparent(omap_clk clk, omap_clk parent); /* omap_intc.c */ #define TYPE_OMAP_INTC "common-omap-intc" -typedef struct omap_intr_handler_s omap_intr_handler; -DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, - TYPE_OMAP_INTC) +typedef struct OMAPIntcState OMAPIntcState; +DECLARE_INSTANCE_CHECKER(OMAPIntcState, OMAP_INTC, TYPE_OMAP_INTC) /* @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, * (ie the struct omap_mpu_state_s*) to do the clockname to pointer * translation.) */ -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk); -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk); +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk); +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk); /* omap_i2c.c */ #define TYPE_OMAP_I2C "omap_i2c" diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_bank_s { unsigned char priority[32]; }; -struct omap_intr_handler_s { +struct OMAPIntcState { SysBusDevice parent_obj; qemu_irq *pins; @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_s { struct omap_intr_handler_bank_s bank[3]; }; -static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) +static void omap_inth_sir_update(OMAPIntcState *s, int is_fiq) { int i, j, sir_intr, p_intr, p; uint32_t level; @@ -XXX,XX +XXX,XX @@ static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) s->sir_intr[is_fiq] = sir_intr; } -static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) +static inline void omap_inth_update(OMAPIntcState *s, int is_fiq) { int i; uint32_t has_intr = 0; @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_inth_mem_ops = { static void omap_inth_reset(DeviceState *dev) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); int i; for (i = 0; i < s->nbanks; ++i){ @@ -XXX,XX +XXX,XX @@ static void omap_inth_reset(DeviceState *dev) static void omap_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->nbanks = 1; @@ -XXX,XX +XXX,XX @@ static void omap_intc_init(Object *obj) static void omap_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap-intc: clk not connected"); } } -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk) { intc->iclk = clk; } -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk) { intc->fclk = clk; } static Property omap_intc_properties[] = { - DEFINE_PROP_UINT32("size", struct omap_intr_handler_s, size, 0x100), + DEFINE_PROP_UINT32("size", OMAPIntcState, size, 0x100), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_inth_mem_ops = { static void omap2_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->level_only = 1; @@ -XXX,XX +XXX,XX @@ static void omap2_intc_init(Object *obj) static void omap2_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap2-intc: iclk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_intc_realize(DeviceState *dev, Error **errp) } static Property omap2_intc_properties[] = { - DEFINE_PROP_UINT8("revision", struct omap_intr_handler_s, + DEFINE_PROP_UINT8("revision", OMAPIntcState, revision, 0x21), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap2_intc_info = { static const TypeInfo omap_intc_type_info = { .name = TYPE_OMAP_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(omap_intr_handler), + .instance_size = sizeof(OMAPIntcState), .abstract = true, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename stellaris_adc_state -> StellarisADCState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 73 +++++++++++++++++++++++----------------------- 1 file changed, 36 insertions(+), 37 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_init(Object *obj) #define STELLARIS_ADC_FIFO_FULL 0x1000 #define TYPE_STELLARIS_ADC "stellaris-adc" -typedef struct StellarisADCState stellaris_adc_state; -DECLARE_INSTANCE_CHECKER(stellaris_adc_state, STELLARIS_ADC, - TYPE_STELLARIS_ADC) +typedef struct StellarisADCState StellarisADCState; +DECLARE_INSTANCE_CHECKER(StellarisADCState, STELLARIS_ADC, TYPE_STELLARIS_ADC) struct StellarisADCState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct StellarisADCState { qemu_irq irq[4]; }; -static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) +static uint32_t stellaris_adc_fifo_read(StellarisADCState *s, int n) { int tail; @@ -XXX,XX +XXX,XX @@ static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) return s->fifo[n].data[tail]; } -static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, +static void stellaris_adc_fifo_write(StellarisADCState *s, int n, uint32_t value) { int head; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, s->fifo[n].state |= STELLARIS_ADC_FIFO_FULL; } -static void stellaris_adc_update(stellaris_adc_state *s) +static void stellaris_adc_update(StellarisADCState *s) { int level; int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_trigger(void *opaque, int irq, int level) } } -static void stellaris_adc_reset(stellaris_adc_state *s) +static void stellaris_adc_reset(StellarisADCState *s) { int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_UINT32(actss, stellaris_adc_state), - VMSTATE_UINT32(ris, stellaris_adc_state), - VMSTATE_UINT32(im, stellaris_adc_state), - VMSTATE_UINT32(emux, stellaris_adc_state), - VMSTATE_UINT32(ostat, stellaris_adc_state), - VMSTATE_UINT32(ustat, stellaris_adc_state), - VMSTATE_UINT32(sspri, stellaris_adc_state), - VMSTATE_UINT32(sac, stellaris_adc_state), - VMSTATE_UINT32(fifo[0].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[0].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[0], stellaris_adc_state), - VMSTATE_UINT32(ssctl[0], stellaris_adc_state), - VMSTATE_UINT32(fifo[1].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[1].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[1], stellaris_adc_state), - VMSTATE_UINT32(ssctl[1], stellaris_adc_state), - VMSTATE_UINT32(fifo[2].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[2].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[2], stellaris_adc_state), - VMSTATE_UINT32(ssctl[2], stellaris_adc_state), - VMSTATE_UINT32(fifo[3].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[3].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[3], stellaris_adc_state), - VMSTATE_UINT32(ssctl[3], stellaris_adc_state), - VMSTATE_UINT32(noise, stellaris_adc_state), + VMSTATE_UINT32(actss, StellarisADCState), + VMSTATE_UINT32(ris, StellarisADCState), + VMSTATE_UINT32(im, StellarisADCState), + VMSTATE_UINT32(emux, StellarisADCState), + VMSTATE_UINT32(ostat, StellarisADCState), + VMSTATE_UINT32(ustat, StellarisADCState), + VMSTATE_UINT32(sspri, StellarisADCState), + VMSTATE_UINT32(sac, StellarisADCState), + VMSTATE_UINT32(fifo[0].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[0].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[0], StellarisADCState), + VMSTATE_UINT32(ssctl[0], StellarisADCState), + VMSTATE_UINT32(fifo[1].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[1].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[1], StellarisADCState), + VMSTATE_UINT32(ssctl[1], StellarisADCState), + VMSTATE_UINT32(fifo[2].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[2].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[2], StellarisADCState), + VMSTATE_UINT32(ssctl[2], StellarisADCState), + VMSTATE_UINT32(fifo[3].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[3].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[3], StellarisADCState), + VMSTATE_UINT32(ssctl[3], StellarisADCState), + VMSTATE_UINT32(noise, StellarisADCState), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { static void stellaris_adc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - stellaris_adc_state *s = STELLARIS_ADC(obj); + StellarisADCState *s = STELLARIS_ADC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_class_init(ObjectClass *klass, void *data) static const TypeInfo stellaris_adc_info = { .name = TYPE_STELLARIS_ADC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(stellaris_adc_state), + .instance_size = sizeof(StellarisADCState), .instance_init = stellaris_adc_init, .class_init = stellaris_adc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The typedef and definitions are generated by the OBJECT_DECLARE_TYPE macro in "hw/arm/bcm2836.h": 20 #define TYPE_BCM283X "bcm283x" 21 OBJECT_DECLARE_TYPE(BCM283XState, BCM283XClass, BCM283X) The script ran in commit a489d1951c ("Use OBJECT_DECLARE_TYPE when possible") missed them because they are declared in a different file unit. Remove them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bcm2836.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/raspi_platform.h" #include "hw/sysbus.h" -typedef struct BCM283XClass { +struct BCM283XClass { /*< private >*/ DeviceClass parent_class; /*< public >*/ @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XClass { hwaddr peri_base; /* Peripheral base address seen by the CPU */ hwaddr ctrl_base; /* Interrupt controller and mailboxes etc. */ int clusterid; -} BCM283XClass; - -#define BCM283X_CLASS(klass) \ - OBJECT_CLASS_CHECK(BCM283XClass, (klass), TYPE_BCM283X) -#define BCM283X_GET_CLASS(obj) \ - OBJECT_GET_CLASS(BCM283XClass, (obj), TYPE_BCM283X) +}; static Property bcm2836_enabled_cores_property = DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> NPCM7XX models have been commited after the conversion from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible"). Manually convert them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/adc/npcm7xx_adc.h | 7 +++---- include/hw/arm/npcm7xx.h | 18 ++++++------------ include/hw/i2c/npcm7xx_smbus.h | 7 +++---- include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +++--- include/hw/misc/npcm7xx_mft.h | 7 +++---- include/hw/misc/npcm7xx_pwm.h | 3 +-- include/hw/misc/npcm7xx_rng.h | 6 +++--- include/hw/net/npcm7xx_emc.h | 5 +---- include/hw/sd/npcm7xx_sdhci.h | 4 ++-- 10 files changed, 26 insertions(+), 39 deletions(-) diff --git a/include/hw/adc/npcm7xx_adc.h b/include/hw/adc/npcm7xx_adc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/adc/npcm7xx_adc.h +++ b/include/hw/adc/npcm7xx_adc.h @@ -XXX,XX +XXX,XX @@ * @iref: The internal reference voltage, initialized at launch time. * @rv: The calibrated output values of 0.5V and 1.5V for the ADC. */ -typedef struct { +struct NPCM7xxADCState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct { uint32_t iref; uint16_t calibration_r_values[NPCM7XX_ADC_NUM_CALIB]; -} NPCM7xxADCState; +}; #define TYPE_NPCM7XX_ADC "npcm7xx-adc" -#define NPCM7XX_ADC(obj) \ - OBJECT_CHECK(NPCM7xxADCState, (obj), TYPE_NPCM7XX_ADC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxADCState, NPCM7XX_ADC) #endif /* NPCM7XX_ADC_H */ diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_NR_PWM_MODULES 2 -typedef struct NPCM7xxMachine { +struct NPCM7xxMachine { MachineState parent; /* * PWM fan splitter. each splitter connects to one PWM output and @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachine { */ SplitIRQ fan_splitter[NPCM7XX_NR_PWM_MODULES * NPCM7XX_PWM_PER_MODULE]; -} NPCM7xxMachine; +}; #define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") -#define NPCM7XX_MACHINE(obj) \ - OBJECT_CHECK(NPCM7xxMachine, (obj), TYPE_NPCM7XX_MACHINE) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMachine, NPCM7XX_MACHINE) typedef struct NPCM7xxMachineClass { MachineClass parent; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachineClass { #define NPCM7XX_MACHINE_GET_CLASS(obj) \ OBJECT_GET_CLASS(NPCM7xxMachineClass, (obj), TYPE_NPCM7XX_MACHINE) -typedef struct NPCM7xxState { +struct NPCM7xxState { DeviceState parent; ARMCPU cpu[NPCM7XX_MAX_NUM_CPUS]; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxFIUState fiu[2]; NPCM7xxEMCState emc[2]; NPCM7xxSDHCIState mmc; -} NPCM7xxState; +}; #define TYPE_NPCM7XX "npcm7xx" -#define NPCM7XX(obj) OBJECT_CHECK(NPCM7xxState, (obj), TYPE_NPCM7XX) +OBJECT_DECLARE_TYPE(NPCM7xxState, NPCM7xxClass, NPCM7XX) #define TYPE_NPCM730 "npcm730" #define TYPE_NPCM750 "npcm750" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxClass { uint32_t num_cpus; } NPCM7xxClass; -#define NPCM7XX_CLASS(klass) \ - OBJECT_CLASS_CHECK(NPCM7xxClass, (klass), TYPE_NPCM7XX) -#define NPCM7XX_GET_CLASS(obj) \ - OBJECT_GET_CLASS(NPCM7xxClass, (obj), TYPE_NPCM7XX) - /** * npcm7xx_load_kernel - Loads memory with everything needed to boot * @machine - The machine containing the SoC to be booted. diff --git a/include/hw/i2c/npcm7xx_smbus.h b/include/hw/i2c/npcm7xx_smbus.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/npcm7xx_smbus.h +++ b/include/hw/i2c/npcm7xx_smbus.h @@ -XXX,XX +XXX,XX @@ typedef enum NPCM7xxSMBusStatus { * @rx_cur: The current position of rx_fifo. * @status: The current status of the SMBus. */ -typedef struct NPCM7xxSMBusState { +struct NPCM7xxSMBusState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSMBusState { uint8_t rx_cur; NPCM7xxSMBusStatus status; -} NPCM7xxSMBusState; +}; #define TYPE_NPCM7XX_SMBUS "npcm7xx-smbus" -#define NPCM7XX_SMBUS(obj) OBJECT_CHECK(NPCM7xxSMBusState, (obj), \ - TYPE_NPCM7XX_SMBUS) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxSMBusState, NPCM7XX_SMBUS) #endif /* NPCM7XX_SMBUS_H */ diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_clk.h +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxCLKState { }; #define TYPE_NPCM7XX_CLK "npcm7xx-clk" -#define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxCLKState, NPCM7XX_CLK) #endif /* NPCM7XX_CLK_H */ diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_gcr.h +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ */ #define NPCM7XX_GCR_NR_REGS (0x148 / sizeof(uint32_t)) -typedef struct NPCM7xxGCRState { +struct NPCM7xxGCRState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxGCRState { uint32_t reset_pwron; uint32_t reset_mdlr; uint32_t reset_intcr3; -} NPCM7xxGCRState; +}; #define TYPE_NPCM7XX_GCR "npcm7xx-gcr" -#define NPCM7XX_GCR(obj) OBJECT_CHECK(NPCM7xxGCRState, (obj), TYPE_NPCM7XX_GCR) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxGCRState, NPCM7XX_GCR) #endif /* NPCM7XX_GCR_H */ diff --git a/include/hw/misc/npcm7xx_mft.h b/include/hw/misc/npcm7xx_mft.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_mft.h +++ b/include/hw/misc/npcm7xx_mft.h @@ -XXX,XX +XXX,XX @@ * @max_rpm: The maximum rpm for fans. Order: A0, B0, A1, B1. * @duty: The duty cycles for fans, relative to NPCM7XX_PWM_MAX_DUTY. */ -typedef struct NPCM7xxMFTState { +struct NPCM7xxMFTState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMFTState { uint32_t max_rpm[NPCM7XX_MFT_FANIN_COUNT]; uint32_t duty[NPCM7XX_MFT_FANIN_COUNT]; -} NPCM7xxMFTState; +}; #define TYPE_NPCM7XX_MFT "npcm7xx-mft" -#define NPCM7XX_MFT(obj) \ - OBJECT_CHECK(NPCM7xxMFTState, (obj), TYPE_NPCM7XX_MFT) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMFTState, NPCM7XX_MFT) #endif /* NPCM7XX_MFT_H */ diff --git a/include/hw/misc/npcm7xx_pwm.h b/include/hw/misc/npcm7xx_pwm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_pwm.h +++ b/include/hw/misc/npcm7xx_pwm.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxPWMState { }; #define TYPE_NPCM7XX_PWM "npcm7xx-pwm" -#define NPCM7XX_PWM(obj) \ - OBJECT_CHECK(NPCM7xxPWMState, (obj), TYPE_NPCM7XX_PWM) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxPWMState, NPCM7XX_PWM) #endif /* NPCM7XX_PWM_H */ diff --git a/include/hw/misc/npcm7xx_rng.h b/include/hw/misc/npcm7xx_rng.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_rng.h +++ b/include/hw/misc/npcm7xx_rng.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" -typedef struct NPCM7xxRNGState { +struct NPCM7xxRNGState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRNGState { uint8_t rngcs; uint8_t rngd; uint8_t rngmode; -} NPCM7xxRNGState; +}; #define TYPE_NPCM7XX_RNG "npcm7xx-rng" -#define NPCM7XX_RNG(obj) OBJECT_CHECK(NPCM7xxRNGState, (obj), TYPE_NPCM7XX_RNG) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxRNGState, NPCM7XX_RNG) #endif /* NPCM7XX_RNG_H */ diff --git a/include/hw/net/npcm7xx_emc.h b/include/hw/net/npcm7xx_emc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/npcm7xx_emc.h +++ b/include/hw/net/npcm7xx_emc.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxEMCState { bool rx_active; }; -typedef struct NPCM7xxEMCState NPCM7xxEMCState; - #define TYPE_NPCM7XX_EMC "npcm7xx-emc" -#define NPCM7XX_EMC(obj) \ - OBJECT_CHECK(NPCM7xxEMCState, (obj), TYPE_NPCM7XX_EMC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxEMCState, NPCM7XX_EMC) #endif /* NPCM7XX_EMC_H */ diff --git a/include/hw/sd/npcm7xx_sdhci.h b/include/hw/sd/npcm7xx_sdhci.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/npcm7xx_sdhci.h +++ b/include/hw/sd/npcm7xx_sdhci.h @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRegs { uint32_t boottoctrl; } NPCM7xxRegisters; -typedef struct NPCM7xxSDHCIState { +struct NPCM7xxSDHCIState { SysBusDevice parent; MemoryRegion container; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSDHCIState { NPCM7xxRegisters regs; SDHCIState sdhci; -} NPCM7xxSDHCIState; +}; #endif /* NPCM7XX_SDHCI_H */ -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The structure is named SECUREECState. Rename the type accordingly. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "sysemu/runstate.h" -typedef struct { +typedef struct SECUREECState { SysBusDevice parent_obj; MemoryRegion iomem; } SECUREECState; -#define TYPE_SBSA_EC "sbsa-ec" -#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC) +#define TYPE_SBSA_SECURE_EC "sbsa-ec" +#define SBSA_SECURE_EC(obj) \ + OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, @@ -XXX,XX +XXX,XX @@ static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size) } static void sbsa_ec_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) + uint64_t value, unsigned size) { if (offset == 0) { /* PSCI machine power command register */ switch (value) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps sbsa_ec_ops = { static void sbsa_ec_init(Object *obj) { - SECUREECState *s = SECURE_EC(obj); + SECUREECState *s = SBSA_SECURE_EC(obj); SysBusDevice *dev = SYS_BUS_DEVICE(obj); memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec", @@ -XXX,XX +XXX,XX @@ static void sbsa_ec_class_init(ObjectClass *klass, void *data) } static const TypeInfo sbsa_ec_info = { - .name = TYPE_SBSA_EC, + .name = TYPE_SBSA_SECURE_EC, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(SECUREECState), .instance_init = sbsa_ec_init, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This model was merged few days before the QOM cleanup from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible") was pulled and merged. Manually adapt. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ typedef struct SECUREECState { } SECUREECState; #define TYPE_SBSA_SECURE_EC "sbsa-ec" -#define SBSA_SECURE_EC(obj) \ - OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) +OBJECT_DECLARE_SIMPLE_TYPE(SECUREECState, SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/intc/xilinx_intc.c:45:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/xilinx_intc.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/hw/intc/xilinx_intc.c b/hw/intc/xilinx_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/xilinx_intc.c +++ b/hw/intc/xilinx_intc.c @@ -XXX,XX +XXX,XX @@ #define R_MAX 8 #define TYPE_XILINX_INTC "xlnx.xps-intc" -DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, - TYPE_XILINX_INTC) +typedef struct XpsIntc XpsIntc; +DECLARE_INSTANCE_CHECKER(XpsIntc, XILINX_INTC, TYPE_XILINX_INTC) -struct xlx_pic +struct XpsIntc { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct xlx_pic uint32_t irq_pin_state; }; -static void update_irq(struct xlx_pic *p) +static void update_irq(XpsIntc *p) { uint32_t i; @@ -XXX,XX +XXX,XX @@ static void update_irq(struct xlx_pic *p) qemu_set_irq(p->parent_irq, (p->regs[R_MER] & 1) && p->regs[R_IPR]); } -static uint64_t -pic_read(void *opaque, hwaddr addr, unsigned int size) +static uint64_t pic_read(void *opaque, hwaddr addr, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t r = 0; addr >>= 2; @@ -XXX,XX +XXX,XX @@ pic_read(void *opaque, hwaddr addr, unsigned int size) return r; } -static void -pic_write(void *opaque, hwaddr addr, - uint64_t val64, unsigned int size) +static void pic_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t value = val64; addr >>= 2; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps pic_ops = { static void irq_handler(void *opaque, int irq, int level) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; /* edge triggered interrupt */ if (p->c_kind_of_intr & (1 << irq) && p->regs[R_MER] & 2) { @@ -XXX,XX +XXX,XX @@ static void irq_handler(void *opaque, int irq, int level) static void xilinx_intc_init(Object *obj) { - struct xlx_pic *p = XILINX_INTC(obj); + XpsIntc *p = XILINX_INTC(obj); qdev_init_gpio_in(DEVICE(obj), irq_handler, 32); sysbus_init_irq(SYS_BUS_DEVICE(obj), &p->parent_irq); @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_init(Object *obj) } static Property xilinx_intc_properties[] = { - DEFINE_PROP_UINT32("kind-of-intr", struct xlx_pic, c_kind_of_intr, 0), + DEFINE_PROP_UINT32("kind-of-intr", XpsIntc, c_kind_of_intr, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_intc_info = { .name = TYPE_XILINX_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct xlx_pic), + .instance_size = sizeof(XpsIntc), .instance_init = xilinx_intc_init, .class_init = xilinx_intc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/timer/xilinx_timer.c:65:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-15-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/xilinx_timer.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/hw/timer/xilinx_timer.c b/hw/timer/xilinx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/xilinx_timer.c +++ b/hw/timer/xilinx_timer.c @@ -XXX,XX +XXX,XX @@ struct xlx_timer }; #define TYPE_XILINX_TIMER "xlnx.xps-timer" -DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, - TYPE_XILINX_TIMER) +typedef struct XpsTimerState XpsTimerState; +DECLARE_INSTANCE_CHECKER(XpsTimerState, XILINX_TIMER, TYPE_XILINX_TIMER) -struct timerblock +struct XpsTimerState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct timerblock struct xlx_timer *timers; }; -static inline unsigned int num_timers(struct timerblock *t) +static inline unsigned int num_timers(XpsTimerState *t) { return 2 - t->one_timer_only; } @@ -XXX,XX +XXX,XX @@ static inline unsigned int timer_from_addr(hwaddr addr) return addr >> 2; } -static void timer_update_irq(struct timerblock *t) +static void timer_update_irq(XpsTimerState *t) { unsigned int i, irq = 0; uint32_t csr; @@ -XXX,XX +XXX,XX @@ static void timer_update_irq(struct timerblock *t) static uint64_t timer_read(void *opaque, hwaddr addr, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; uint32_t r = 0; unsigned int timer; @@ -XXX,XX +XXX,XX @@ static void timer_write(void *opaque, hwaddr addr, uint64_t val64, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; unsigned int timer; uint32_t value = val64; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps timer_ops = { static void timer_hit(void *opaque) { struct xlx_timer *xt = opaque; - struct timerblock *t = xt->parent; + XpsTimerState *t = xt->parent; D(fprintf(stderr, "%s %d\n", __func__, xt->nr)); xt->regs[R_TCSR] |= TCSR_TINT; @@ -XXX,XX +XXX,XX @@ static void timer_hit(void *opaque) static void xilinx_timer_realize(DeviceState *dev, Error **errp) { - struct timerblock *t = XILINX_TIMER(dev); + XpsTimerState *t = XILINX_TIMER(dev); unsigned int i; /* Init all the ptimers. */ @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_realize(DeviceState *dev, Error **errp) static void xilinx_timer_init(Object *obj) { - struct timerblock *t = XILINX_TIMER(obj); + XpsTimerState *t = XILINX_TIMER(obj); /* All timers share a single irq line. */ sysbus_init_irq(SYS_BUS_DEVICE(obj), &t->irq); } static Property xilinx_timer_properties[] = { - DEFINE_PROP_UINT32("clock-frequency", struct timerblock, freq_hz, - 62 * 1000000), - DEFINE_PROP_UINT8("one-timer-only", struct timerblock, one_timer_only, 0), + DEFINE_PROP_UINT32("clock-frequency", XpsTimerState, freq_hz, 62 * 1000000), + DEFINE_PROP_UINT8("one-timer-only", XpsTimerState, one_timer_only, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_timer_info = { .name = TYPE_XILINX_TIMER, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct timerblock), + .instance_size = sizeof(XpsTimerState), .instance_init = xilinx_timer_init, .class_init = xilinx_timer_class_init, }; -- 2.34.1 From: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> ARM trusted firmware, when built with FEAT_HCX support, sets SCR_EL3.HXEn bit to allow EL2 to modify HCRX_EL2 register without trapping it in EL3. Qemu uses a valid mask to clear unsupported SCR_EL3 bits when emulating SCR_EL3 write, and that mask doesn't include SCR_EL3.HXEn bit even if FEAT_HCX is enabled and exposed to the guest. As a result EL3 writes of that bit are ignored. Cc: qemu-stable@nongnu.org Signed-off-by: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> Message-id: 20230105221251.17896-4-eiakovlev@linux.microsoft.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) if (cpu_isar_feature(aa64_sme, cpu)) { valid_mask |= SCR_ENTP2; } + if (cpu_isar_feature(aa64_hcx, cpu)) { + valid_mask |= SCR_HXEN; + } } else { valid_mask &= ~(SCR_RW | SCR_ST); if (cpu_isar_feature(aa32_ras, cpu)) { -- 2.34.1