target-arm queue. This has the "plumb txattrs through various bits of exec.c" patches, and a collection of bug fixes from various people. thanks -- PMM The following changes since commit a3ac12fba028df90f7b3dbec924995c126c41022: Merge remote-tracking branch 'remotes/ehabkost/tags/numa-next-pull-request' into staging (2018-05-31 11:12:36 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180531 for you to fetch changes up to 49d1dca0520ea71bc21867fab6647f474fcf857b: KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice (2018-05-31 14:52:53 +0100) ---------------------------------------------------------------- target-arm queue: * target/arm: Honour FPCR.FZ in FRECPX * MAINTAINERS: Add entries for newer MPS2 boards and devices * hw/intc/arm_gicv3: Fix APxR<n> register dispatching * arm_gicv3_kvm: fix bug in writing zero bits back to the in-kernel GIC state * tcg: Fix helper function vs host abi for float16 * arm: fix qemu crash on startup with -bios option * arm: fix malloc type mismatch * xlnx-zdma: Correct mem leaks and memset to zero on desc unaligned errors * Correct CPACR reset value for v7 cores * memory.h: Improve IOMMU related documentation * exec: Plumb transaction attributes through various functions in preparation for allowing IOMMUs to see them * vmstate.h: Provide VMSTATE_BOOL_SUB_ARRAY * ARM: ACPI: Fix use-after-free due to memory realloc * KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice ---------------------------------------------------------------- Francisco Iglesias (1): xlnx-zdma: Correct mem leaks and memset to zero on desc unaligned errors Igor Mammedov (1): arm: fix qemu crash on startup with -bios option Jan Kiszka (1): hw/intc/arm_gicv3: Fix APxR<n> register dispatching Paolo Bonzini (1): arm: fix malloc type mismatch Peter Maydell (17): target/arm: Honour FPCR.FZ in FRECPX MAINTAINERS: Add entries for newer MPS2 boards and devices Correct CPACR reset value for v7 cores memory.h: Improve IOMMU related documentation Make tb_invalidate_phys_addr() take a MemTxAttrs argument Make address_space_translate{, _cached}() take a MemTxAttrs argument Make address_space_map() take a MemTxAttrs argument Make address_space_access_valid() take a MemTxAttrs argument Make flatview_extend_translation() take a MemTxAttrs argument Make memory_region_access_valid() take a MemTxAttrs argument Make MemoryRegion valid.accepts callback take a MemTxAttrs argument Make flatview_access_valid() take a MemTxAttrs argument Make flatview_translate() take a MemTxAttrs argument Make address_space_get_iotlb_entry() take a MemTxAttrs argument Make flatview_do_translate() take a MemTxAttrs argument Make address_space_translate_iommu take a MemTxAttrs argument vmstate.h: Provide VMSTATE_BOOL_SUB_ARRAY Richard Henderson (1): tcg: Fix helper function vs host abi for float16 Shannon Zhao (3): arm_gicv3_kvm: increase clroffset accordingly ARM: ACPI: Fix use-after-free due to memory realloc KVM: GIC: Fix memory leak due to calling kvm_init_irq_routing twice include/exec/exec-all.h | 5 +- include/exec/helper-head.h | 2 +- include/exec/memory-internal.h | 3 +- include/exec/memory.h | 128 +++++++++++++++++++++++++++++++++++------ include/migration/vmstate.h | 3 + include/sysemu/dma.h | 6 +- accel/tcg/translate-all.c | 4 +- exec.c | 95 ++++++++++++++++++------------ hw/arm/boot.c | 18 +++--- hw/arm/virt-acpi-build.c | 20 +++++-- hw/dma/xlnx-zdma.c | 10 +++- hw/hppa/dino.c | 3 +- hw/intc/arm_gic_kvm.c | 1 - hw/intc/arm_gicv3_cpuif.c | 12 ++-- hw/intc/arm_gicv3_kvm.c | 2 +- hw/nvram/fw_cfg.c | 12 ++-- hw/s390x/s390-pci-inst.c | 3 +- hw/scsi/esp.c | 3 +- hw/vfio/common.c | 3 +- hw/virtio/vhost.c | 3 +- hw/xen/xen_pt_msi.c | 3 +- memory.c | 12 ++-- memory_ldst.inc.c | 18 +++--- target/arm/gdbstub.c | 3 +- target/arm/helper-a64.c | 41 +++++++------ target/arm/helper.c | 90 ++++++++++++++++------------- target/ppc/mmu-hash64.c | 3 +- target/riscv/helper.c | 2 +- target/s390x/diag.c | 6 +- target/s390x/excp_helper.c | 3 +- target/s390x/mmu_helper.c | 3 +- target/s390x/sigp.c | 3 +- target/xtensa/op_helper.c | 3 +- MAINTAINERS | 9 ++- 34 files changed, 353 insertions(+), 182 deletions(-) The FRECPX instructions should (like most other floating point operations) honour the FPCR.FZ bit which specifies whether input denormals should be flushed to zero (or FZ16 for the half-precision version). We forgot to implement this, which doesn't affect the results (since the calculation doesn't actually care about the mantissa bits) but did mean we were failing to set the FPSR.IDC bit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521172712.19930-1-peter.maydell@linaro.org --- target/arm/helper-a64.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ float16 HELPER(frecpx_f16)(float16 a, void *fpstp) return nan; } + a = float16_squash_input_denormal(a, fpst); + val16 = float16_val(a); sbit = 0x8000 & val16; exp = extract32(val16, 10, 5); @@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) return nan; } + a = float32_squash_input_denormal(a, fpst); + val32 = float32_val(a); sbit = 0x80000000ULL & val32; exp = extract32(val32, 23, 8); @@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) return nan; } + a = float64_squash_input_denormal(a, fpst); + val64 = float64_val(a); sbit = 0x8000000000000000ULL & val64; exp = extract64(float64_val(a), 52, 11); -- 2.17.1 Add entries to MAINTAINERS to cover the newer MPS2 boards and the new devices they use. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180518153157.14899-1-peter.maydell@linaro.org --- MAINTAINERS | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/timer/cmsdk-apb-timer.c F: include/hw/timer/cmsdk-apb-timer.h F: hw/char/cmsdk-apb-uart.c F: include/hw/char/cmsdk-apb-uart.h +F: hw/misc/tz-ppc.c +F: include/hw/misc/tz-ppc.h ARM cores M: Peter Maydell <peter.maydell@linaro.org> @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/mps2.c -F: hw/misc/mps2-scc.c -F: include/hw/misc/mps2-scc.h +F: hw/arm/mps2-tz.c +F: hw/misc/mps2-*.c +F: include/hw/misc/mps2-*.h +F: hw/arm/iotkit.c +F: include/hw/arm/iotkit.h Musicpal M: Jan Kiszka <jan.kiszka@web.de> -- 2.17.1 From: Jan Kiszka <jan.kiszka@siemens.com> There was a nasty flip in identifying which register group an access is targeting. The issue caused spuriously raised priorities of the guest when handing CPUs over in the Jailhouse hypervisor. Cc: qemu-stable@nongnu.org Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com> Message-id: 28b927d3-da58-bce4-cc13-bfec7f9b1cb9@siemens.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_cpuif.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ static uint64_t icv_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; uint64_t value = cs->ich_apr[grp][regno]; trace_gicv3_icv_ap_read(ri->crm & 1, regno, gicv3_redist_affid(cs), value); @@ -XXX,XX +XXX,XX @@ static void icv_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; trace_gicv3_icv_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); @@ -XXX,XX +XXX,XX @@ static uint64_t icc_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) uint64_t value; int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + int grp = (ri->crm & 1) ? GICV3_G1 : GICV3_G0; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { return icv_ap_read(env, ri); @@ -XXX,XX +XXX,XX @@ static void icc_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1; + int grp = (ri->crm & 1) ? GICV3_G1 : GICV3_G0; if (icv_access(env, grp == GICV3_G0 ? HCR_FMO : HCR_IMO)) { icv_ap_write(env, ri, value); @@ -XXX,XX +XXX,XX @@ static uint64_t ich_ap_read(CPUARMState *env, const ARMCPRegInfo *ri) { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; uint64_t value; value = cs->ich_apr[grp][regno]; @@ -XXX,XX +XXX,XX @@ static void ich_ap_write(CPUARMState *env, const ARMCPRegInfo *ri, { GICv3CPUState *cs = icc_cs_from_env(env); int regno = ri->opc2 & 3; - int grp = ri->crm & 1 ? GICV3_G0 : GICV3_G1NS; + int grp = (ri->crm & 1) ? GICV3_G1NS : GICV3_G0; trace_gicv3_ich_ap_write(ri->crm & 1, regno, gicv3_redist_affid(cs), value); -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> It forgot to increase clroffset during the loop. So it only clear the first 4 bytes. Fixes: 367b9f527becdd20ddf116e17a3c0c2bbc486920 Cc: qemu-stable@nongnu.org Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527047633-12368-1-git-send-email-zhaoshenglong@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_dist_putbmp(GICv3State *s, uint32_t offset, if (clroffset != 0) { reg = 0; kvm_gicd_access(s, clroffset, &reg, true); + clroffset += 4; } reg = *gic_bmp_ptr32(bmp, irq); kvm_gicd_access(s, offset, &reg, true); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Depending on the host abi, float16, aka uint16_t, values are passed and returned either zero-extended in the host register or with garbage at the top of the host register. The tcg code generator has so far been assuming garbage, as that matches the x86 abi, but this is incorrect for other host abis. Further, target/arm has so far been assuming zero-extended results, so that it may store the 16-bit value into a 32-bit slot with the high 16-bits already clear. Rectify both problems by mapping "f16" in the helper definition to uint32_t instead of (a typedef for) uint16_t. This forces the host compiler to assume garbage in the upper 16 bits on input and to zero-extend the result on output. Cc: qemu-stable@nongnu.org Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20180522175629.24932-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/helper-head.h | 2 +- target/arm/helper-a64.c | 35 +++++++++-------- target/arm/helper.c | 80 +++++++++++++++++++------------------- 3 files changed, 59 insertions(+), 58 deletions(-) diff --git a/include/exec/helper-head.h b/include/exec/helper-head.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/helper-head.h +++ b/include/exec/helper-head.h @@ -XXX,XX +XXX,XX @@ #define dh_ctype_int int #define dh_ctype_i64 uint64_t #define dh_ctype_s64 int64_t -#define dh_ctype_f16 float16 +#define dh_ctype_f16 uint32_t #define dh_ctype_f32 float32 #define dh_ctype_f64 float64 #define dh_ctype_ptr void * diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t float_rel_to_flags(int res) return flags; } -uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status) +uint64_t HELPER(vfp_cmph_a64)(uint32_t x, uint32_t y, void *fp_status) { return float_rel_to_flags(float16_compare_quiet(x, y, fp_status)); } -uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status) +uint64_t HELPER(vfp_cmpeh_a64)(uint32_t x, uint32_t y, void *fp_status) { return float_rel_to_flags(float16_compare(x, y, fp_status)); } @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) #define float64_three make_float64(0x4008000000000000ULL) #define float64_one_point_five make_float64(0x3FF8000000000000ULL) -float16 HELPER(recpsf_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_two, 0, fpst); } -float16 HELPER(rsqrtsf_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_addlp_u16)(uint64_t a) } /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */ -float16 HELPER(frecpx_f16)(float16 a, void *fpstp) +uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; uint16_t val16, sbit; @@ -XXX,XX +XXX,XX @@ void HELPER(casp_be_parallel)(CPUARMState *env, uint32_t rs, uint64_t addr, #define ADVSIMD_HELPER(name, suffix) HELPER(glue(glue(advsimd_, name), suffix)) #define ADVSIMD_HALFOP(name) \ -float16 ADVSIMD_HELPER(name, h)(float16 a, float16 b, void *fpstp) \ +uint32_t ADVSIMD_HELPER(name, h)(uint32_t a, uint32_t b, void *fpstp) \ { \ float_status *fpst = fpstp; \ return float16_ ## name(a, b, fpst); \ @@ -XXX,XX +XXX,XX @@ ADVSIMD_HALFOP(mulx) ADVSIMD_TWOHALFOP(mulx) /* fused multiply-accumulate */ -float16 HELPER(advsimd_muladdh)(float16 a, float16 b, float16 c, void *fpstp) +uint32_t HELPER(advsimd_muladdh)(uint32_t a, uint32_t b, uint32_t c, + void *fpstp) { float_status *fpst = fpstp; return float16_muladd(a, b, c, 0, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_muladd2h)(uint32_t two_a, uint32_t two_b, #define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0 -uint32_t HELPER(advsimd_ceq_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_ceq_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare_quiet(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_equal); } -uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_cge_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_cge_f16)(float16 a, float16 b, void *fpstp) compare == float_relation_equal); } -uint32_t HELPER(advsimd_cgt_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_cgt_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_greater); } -uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_acge_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; float16 f0 = float16_abs(a); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acge_f16)(float16 a, float16 b, void *fpstp) compare == float_relation_equal); } -uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp) +uint32_t HELPER(advsimd_acgt_f16)(uint32_t a, uint32_t b, void *fpstp) { float_status *fpst = fpstp; float16 f0 = float16_abs(a); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b, void *fpstp) } /* round to integral */ -float16 HELPER(advsimd_rinth_exact)(float16 x, void *fp_status) +uint32_t HELPER(advsimd_rinth_exact)(uint32_t x, void *fp_status) { return float16_round_to_int(x, fp_status); } -float16 HELPER(advsimd_rinth)(float16 x, void *fp_status) +uint32_t HELPER(advsimd_rinth)(uint32_t x, void *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float16 ret; @@ -XXX,XX +XXX,XX @@ float16 HELPER(advsimd_rinth)(float16 x, void *fp_status) * setting the mode appropriately before calling the helper. */ -uint32_t HELPER(advsimd_f16tosinth)(float16 a, void *fpstp) +uint32_t HELPER(advsimd_f16tosinth)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_f16tosinth)(float16 a, void *fpstp) return float16_to_int16(a, fpst); } -uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp) +uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp) { float_status *fpst = fpstp; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_f16touinth)(float16 a, void *fpstp) * Square Root and Reciprocal square root */ -float16 HELPER(sqrt_f16)(float16 a, void *fpstp) +uint32_t HELPER(sqrt_f16)(uint32_t a, void *fpstp) { float_status *s = fpstp; 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 @@ DO_VFP_cmp(d, float64) /* Integer to float and float to integer conversions */ -#define CONV_ITOF(name, fsz, sign) \ - float##fsz HELPER(name)(uint32_t x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ +#define CONV_ITOF(name, ftype, fsz, sign) \ +ftype HELPER(name)(uint32_t x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ } -#define CONV_FTOI(name, fsz, sign, round) \ -uint32_t HELPER(name)(float##fsz x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - if (float##fsz##_is_any_nan(x)) { \ - float_raise(float_flag_invalid, fpst); \ - return 0; \ - } \ - return float##fsz##_to_##sign##int32##round(x, fpst); \ +#define CONV_FTOI(name, ftype, fsz, sign, round) \ +uint32_t HELPER(name)(ftype x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + if (float##fsz##_is_any_nan(x)) { \ + float_raise(float_flag_invalid, fpst); \ + return 0; \ + } \ + return float##fsz##_to_##sign##int32##round(x, fpst); \ } -#define FLOAT_CONVS(name, p, fsz, sign) \ -CONV_ITOF(vfp_##name##to##p, fsz, sign) \ -CONV_FTOI(vfp_to##name##p, fsz, sign, ) \ -CONV_FTOI(vfp_to##name##z##p, fsz, sign, _round_to_zero) +#define FLOAT_CONVS(name, p, ftype, fsz, sign) \ + CONV_ITOF(vfp_##name##to##p, ftype, fsz, sign) \ + CONV_FTOI(vfp_to##name##p, ftype, fsz, sign, ) \ + CONV_FTOI(vfp_to##name##z##p, ftype, fsz, sign, _round_to_zero) -FLOAT_CONVS(si, h, 16, ) -FLOAT_CONVS(si, s, 32, ) -FLOAT_CONVS(si, d, 64, ) -FLOAT_CONVS(ui, h, 16, u) -FLOAT_CONVS(ui, s, 32, u) -FLOAT_CONVS(ui, d, 64, u) +FLOAT_CONVS(si, h, uint32_t, 16, ) +FLOAT_CONVS(si, s, float32, 32, ) +FLOAT_CONVS(si, d, float64, 64, ) +FLOAT_CONVS(ui, h, uint32_t, 16, u) +FLOAT_CONVS(ui, s, float32, 32, u) +FLOAT_CONVS(ui, d, float64, 64, u) #undef CONV_ITOF #undef CONV_FTOI @@ -XXX,XX +XXX,XX @@ static float16 do_postscale_fp16(float64 f, int shift, float_status *fpst) return float64_to_float16(float64_scalbn(f, -shift, fpst), true, fpst); } -float16 HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(int32_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(uint32_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(int64_to_float64(x, fpst), shift, fpst); } -float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) { return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst); } @@ -XXX,XX +XXX,XX @@ static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst) } } -uint32_t HELPER(vfp_toshh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toshh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int16(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_touhh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toslh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst); } -uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst) +uint32_t HELPER(vfp_toulh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst); } -uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst) +uint64_t HELPER(vfp_tosqh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst); } -uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst) +uint64_t HELPER(vfp_touqh)(uint32_t x, uint32_t shift, void *fpst) { return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst); } @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) } /* Half precision conversions. */ -float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) +float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. @@ -XXX,XX +XXX,XX @@ float32 HELPER(vfp_fcvt_f16_to_f32)(float16 a, void *fpstp, uint32_t ahp_mode) return r; } -float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. @@ -XXX,XX +XXX,XX @@ float16 HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) return r; } -float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) +float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. @@ -XXX,XX +XXX,XX @@ float64 HELPER(vfp_fcvt_f16_to_f64)(float16 a, void *fpstp, uint32_t ahp_mode) return r; } -float16 HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. @@ -XXX,XX +XXX,XX @@ static bool round_to_inf(float_status *fpst, bool sign_bit) g_assert_not_reached(); } -float16 HELPER(recpe_f16)(float16 input, void *fpstp) +uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) { float_status *fpst = fpstp; float16 f16 = float16_squash_input_denormal(input, fpst); @@ -XXX,XX +XXX,XX @@ static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) return extract64(estimate, 0, 8) << 44; } -float16 HELPER(rsqrte_f16)(float16 input, void *fpstp) +uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) { float_status *s = fpstp; float16 f16 = float16_squash_input_denormal(input, s); -- 2.17.1 From: Igor Mammedov <imammedo@redhat.com> When QEMU is started with following CLI -machine virt,gic-version=3,accel=kvm -cpu host -bios AAVMF_CODE.fd it crashes with abort at accel/kvm/kvm-all.c:2164: KVM_SET_DEVICE_ATTR failed: Group 6 attr 0x000000000000c665: Invalid argument Which is caused by implicit dependency of kvm_arm_gicv3_reset() on arm_gicv3_icc_reset() where the later is called by CPU reset reset callback. However commit: 3b77f6c arm/boot: split load_dtb() from arm_load_kernel() broke CPU reset callback registration in case arm_load_kernel() ... if (!info->kernel_filename || info->firmware_loaded) branch is taken, i.e. it's sufficient to provide a firmware or do not provide kernel on CLI to skip cpu reset callback registration, where before offending commit the callback has been registered unconditionally. Fix it by registering the callback right at the beginning of arm_load_kernel() unconditionally instead of doing it at the end. NOTE: we probably should eliminate that dependency anyways as well as separate arch CPU reset parts from arm_load_kernel() into CPU itself, but that refactoring that I probably would have to do anyways later for CPU hotplug to work. Reported-by: Auger Eric <eric.auger@redhat.com> Signed-off-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527070950-208350-1-git-send-email-imammedo@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) static const ARMInsnFixup *primary_loader; AddressSpace *as = arm_boot_address_space(cpu, info); + /* CPU objects (unlike devices) are not automatically reset on system + * reset, so we must always register a handler to do so. If we're + * actually loading a kernel, the handler is also responsible for + * arranging that we start it correctly. + */ + for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { + qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); + } + /* The board code is not supposed to set secure_board_setup unless * running its code in secure mode is actually possible, and KVM * doesn't support secure. @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, struct arm_boot_info *info) ARM_CPU(cs)->env.boot_info = info; } - /* CPU objects (unlike devices) are not automatically reset on system - * reset, so we must always register a handler to do so. If we're - * actually loading a kernel, the handler is also responsible for - * arranging that we start it correctly. - */ - for (cs = first_cpu; cs; cs = CPU_NEXT(cs)) { - qemu_register_reset(do_cpu_reset, ARM_CPU(cs)); - } - if (!info->skip_dtb_autoload && have_dtb(info)) { if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as) < 0) { exit(1); -- 2.17.1 From: Paolo Bonzini <pbonzini@redhat.com> cpregs_keys is an uint32_t* so the allocation should use uint32_t. g_new is even better because it is type-safe. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/gdbstub.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ int arm_gen_dynamic_xml(CPUState *cs) RegisterSysregXmlParam param = {cs, s}; cpu->dyn_xml.num_cpregs = 0; - cpu->dyn_xml.cpregs_keys = g_malloc(sizeof(uint32_t *) * - g_hash_table_size(cpu->cp_regs)); + cpu->dyn_xml.cpregs_keys = g_new(uint32_t, g_hash_table_size(cpu->cp_regs)); g_string_printf(s, "<?xml version=\"1.0\"?>"); g_string_append_printf(s, "<!DOCTYPE target SYSTEM \"gdb-target.dtd\">"); g_string_append_printf(s, "<feature name=\"org.qemu.gdb.arm.sys.regs\">"); -- 2.17.1 From: Francisco Iglesias <frasse.iglesias@gmail.com> Coverity found that the string return by 'object_get_canonical_path' was not being freed at two locations in the model (CID 1391294 and CID 1391293) and also that a memset was being called with a value greater than the max of a byte on the second argument (CID 1391286). This patch corrects this by adding the freeing of the strings and also changing to memset to zero instead on descriptor unaligned errors. Signed-off-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180528184859.3530-1-frasse.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/hw/dma/xlnx-zdma.c b/hw/dma/xlnx-zdma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/xlnx-zdma.c +++ b/hw/dma/xlnx-zdma.c @@ -XXX,XX +XXX,XX @@ static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, void *buf) qemu_log_mask(LOG_GUEST_ERROR, "zdma: unaligned descriptor at %" PRIx64, addr); - memset(buf, 0xdeadbeef, sizeof(XlnxZDMADescr)); + memset(buf, 0x0, sizeof(XlnxZDMADescr)); s->error = true; return false; } @@ -XXX,XX +XXX,XX @@ static uint64_t zdma_read(void *opaque, hwaddr addr, unsigned size) RegisterInfo *r = &s->regs_info[addr / 4]; if (!r->data) { + gchar *path = object_get_canonical_path(OBJECT(s)); qemu_log("%s: Decode error: read from %" HWADDR_PRIx "\n", - object_get_canonical_path(OBJECT(s)), + path, addr); + g_free(path); ARRAY_FIELD_DP32(s->regs, ZDMA_CH_ISR, INV_APB, true); zdma_ch_imr_update_irq(s); return 0; @@ -XXX,XX +XXX,XX @@ static void zdma_write(void *opaque, hwaddr addr, uint64_t value, RegisterInfo *r = &s->regs_info[addr / 4]; if (!r->data) { + gchar *path = object_get_canonical_path(OBJECT(s)); qemu_log("%s: Decode error: write to %" HWADDR_PRIx "=%" PRIx64 "\n", - object_get_canonical_path(OBJECT(s)), + path, addr, value); + g_free(path); ARRAY_FIELD_DP32(s->regs, ZDMA_CH_ISR, INV_APB, true); zdma_ch_imr_update_irq(s); return; -- 2.17.1 In commit f0aff255700 we made cpacr_write() enforce that some CPACR bits are RAZ/WI and some are RAO/WI for ARMv7 cores. Unfortunately we forgot to also update the register's reset value. The effect was that (a) a guest that read CPACR on reset would not see ones in the RAO bits, and (b) if you did a migration before the guest did a write to the CPACR then the migration would fail because the destination would enforce the RAO bits and then complain that they didn't match the zero value from the source. Implement reset for the CPACR using a custom reset function that just calls cpacr_write(), to avoid having to duplicate the logic for which bits are RAO. This bug would affect migration for TCG CPUs which are ARMv7 with VFP but without one of Neon or VFPv3. Reported-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Cédric Le Goater <clg@kaod.org> Message-id: 20180522173713.26282-1-peter.maydell@linaro.org --- target/arm/helper.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) 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 cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.cpacr_el1 = value; } +static void cpacr_reset(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* Call cpacr_write() so that we reset with the correct RAO bits set + * for our CPU features. + */ + cpacr_write(env, ri, 0); +} + static CPAccessResult cpacr_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = { { .name = "CPACR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 2, .accessfn = cpacr_access, .access = PL1_RW, .fieldoffset = offsetof(CPUARMState, cp15.cpacr_el1), - .resetvalue = 0, .writefn = cpacr_write }, + .resetfn = cpacr_reset, .writefn = cpacr_write }, REGINFO_SENTINEL }; -- 2.17.1 Add more detail to the documentation for memory_region_init_iommu() and other IOMMU-related functions and data structures. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 20180521140402.23318-2-peter.maydell@linaro.org --- include/exec/memory.h | 105 ++++++++++++++++++++++++++++++++++++++---- 1 file changed, 95 insertions(+), 10 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ enum IOMMUMemoryRegionAttr { IOMMU_ATTR_SPAPR_TCE_FD }; +/** + * IOMMUMemoryRegionClass: + * + * All IOMMU implementations need to subclass TYPE_IOMMU_MEMORY_REGION + * and provide an implementation of at least the @translate method here + * to handle requests to the memory region. Other methods are optional. + * + * The IOMMU implementation must use the IOMMU notifier infrastructure + * to report whenever mappings are changed, by calling + * memory_region_notify_iommu() (or, if necessary, by calling + * memory_region_notify_one() for each registered notifier). + */ typedef struct IOMMUMemoryRegionClass { /* private */ struct DeviceClass parent_class; /* - * Return a TLB entry that contains a given address. Flag should - * be the access permission of this translation operation. We can - * set flag to IOMMU_NONE to mean that we don't need any - * read/write permission checks, like, when for region replay. + * Return a TLB entry that contains a given address. + * + * The IOMMUAccessFlags indicated via @flag are optional and may + * be specified as IOMMU_NONE to indicate that the caller needs + * the full translation information for both reads and writes. If + * the access flags are specified then the IOMMU implementation + * may use this as an optimization, to stop doing a page table + * walk as soon as it knows that the requested permissions are not + * allowed. If IOMMU_NONE is passed then the IOMMU must do the + * full page table walk and report the permissions in the returned + * IOMMUTLBEntry. (Note that this implies that an IOMMU may not + * return different mappings for reads and writes.) + * + * The returned information remains valid while the caller is + * holding the big QEMU lock or is inside an RCU critical section; + * if the caller wishes to cache the mapping beyond that it must + * register an IOMMU notifier so it can invalidate its cached + * information when the IOMMU mapping changes. + * + * @iommu: the IOMMUMemoryRegion + * @hwaddr: address to be translated within the memory region + * @flag: requested access permissions */ IOMMUTLBEntry (*translate)(IOMMUMemoryRegion *iommu, hwaddr addr, IOMMUAccessFlags flag); - /* Returns minimum supported page size */ + /* Returns minimum supported page size in bytes. + * If this method is not provided then the minimum is assumed to + * be TARGET_PAGE_SIZE. + * + * @iommu: the IOMMUMemoryRegion + */ uint64_t (*get_min_page_size)(IOMMUMemoryRegion *iommu); - /* Called when IOMMU Notifier flag changed */ + /* Called when IOMMU Notifier flag changes (ie when the set of + * events which IOMMU users are requesting notification for changes). + * Optional method -- need not be provided if the IOMMU does not + * need to know exactly which events must be notified. + * + * @iommu: the IOMMUMemoryRegion + * @old_flags: events which previously needed to be notified + * @new_flags: events which now need to be notified + */ void (*notify_flag_changed)(IOMMUMemoryRegion *iommu, IOMMUNotifierFlag old_flags, IOMMUNotifierFlag new_flags); - /* Set this up to provide customized IOMMU replay function */ + /* Called to handle memory_region_iommu_replay(). + * + * The default implementation of memory_region_iommu_replay() is to + * call the IOMMU translate method for every page in the address space + * with flag == IOMMU_NONE and then call the notifier if translate + * returns a valid mapping. If this method is implemented then it + * overrides the default behaviour, and must provide the full semantics + * of memory_region_iommu_replay(), by calling @notifier for every + * translation present in the IOMMU. + * + * Optional method -- an IOMMU only needs to provide this method + * if the default is inefficient or produces undesirable side effects. + * + * Note: this is not related to record-and-replay functionality. + */ void (*replay)(IOMMUMemoryRegion *iommu, IOMMUNotifier *notifier); - /* Get IOMMU misc attributes */ - int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr, + /* Get IOMMU misc attributes. This is an optional method that + * can be used to allow users of the IOMMU to get implementation-specific + * information. The IOMMU implements this method to handle calls + * by IOMMU users to memory_region_iommu_get_attr() by filling in + * the arbitrary data pointer for any IOMMUMemoryRegionAttr values that + * the IOMMU supports. If the method is unimplemented then + * memory_region_iommu_get_attr() will always return -EINVAL. + * + * @iommu: the IOMMUMemoryRegion + * @attr: attribute being queried + * @data: memory to fill in with the attribute data + * + * Returns 0 on success, or a negative errno; in particular + * returns -EINVAL for unrecognized or unimplemented attribute types. + */ + int (*get_attr)(IOMMUMemoryRegion *iommu, enum IOMMUMemoryRegionAttr attr, void *data); } IOMMUMemoryRegionClass; @@ -XXX,XX +XXX,XX @@ static inline void memory_region_init_reservation(MemoryRegion *mr, * An IOMMU region translates addresses and forwards accesses to a target * memory region. * + * The IOMMU implementation must define a subclass of TYPE_IOMMU_MEMORY_REGION. + * @_iommu_mr should be a pointer to enough memory for an instance of + * that subclass, @instance_size is the size of that subclass, and + * @mrtypename is its name. This function will initialize @_iommu_mr as an + * instance of the subclass, and its methods will then be called to handle + * accesses to the memory region. See the documentation of + * #IOMMUMemoryRegionClass for further details. + * * @_iommu_mr: the #IOMMUMemoryRegion to be initialized * @instance_size: the IOMMUMemoryRegion subclass instance size * @mrtypename: the type name of the #IOMMUMemoryRegion @@ -XXX,XX +XXX,XX @@ void memory_region_register_iommu_notifier(MemoryRegion *mr, * a notifier with the minimum page granularity returned by * mr->iommu_ops->get_page_size(). * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe * @n: the notifier to which to replay iommu mappings */ @@ -XXX,XX +XXX,XX @@ void memory_region_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n); * memory_region_iommu_replay_all: replay existing IOMMU translations * to all the notifiers registered. * + * Note: this is not related to record-and-replay functionality. + * * @iommu_mr: the memory region to observe */ void memory_region_iommu_replay_all(IOMMUMemoryRegion *iommu_mr); @@ -XXX,XX +XXX,XX @@ void memory_region_unregister_iommu_notifier(MemoryRegion *mr, * memory_region_iommu_get_attr: return an IOMMU attr if get_attr() is * defined on the IOMMU. * - * Returns 0 if succeded, error code otherwise. + * Returns 0 on success, or a negative errno otherwise. In particular, + * -EINVAL indicates that the IOMMU does not support the requested + * attribute. * * @iommu_mr: the memory region * @attr: the requested attribute -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to tb_invalidate_phys_addr(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180521140402.23318-3-peter.maydell@linaro.org --- include/exec/exec-all.h | 5 +++-- accel/tcg/translate-all.c | 2 +- exec.c | 2 +- target/xtensa/op_helper.c | 3 ++- 4 files changed, 7 insertions(+), 5 deletions(-) diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/exec-all.h +++ b/include/exec/exec-all.h @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, void tlb_set_page(CPUState *cpu, target_ulong vaddr, hwaddr paddr, int prot, int mmu_idx, target_ulong size); -void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr); +void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs); void probe_write(CPUArchState *env, target_ulong addr, int size, int mmu_idx, uintptr_t retaddr); #else @@ -XXX,XX +XXX,XX @@ static inline void tlb_flush_by_mmuidx_all_cpus_synced(CPUState *cpu, uint16_t idxmap) { } -static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) +static inline void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, + MemTxAttrs attrs) { } #endif diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ static TranslationBlock *tb_find_pc(uintptr_t tc_ptr) } #if !defined(CONFIG_USER_ONLY) -void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr) +void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) { ram_addr_t ram_addr; MemoryRegion *mr; diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void breakpoint_invalidate(CPUState *cpu, target_ulong pc) if (phys != -1) { /* Locks grabbed by tb_invalidate_phys_addr */ tb_invalidate_phys_addr(cpu->cpu_ases[asidx].as, - phys | (pc & ~TARGET_PAGE_MASK)); + phys | (pc & ~TARGET_PAGE_MASK), attrs); } } #endif diff --git a/target/xtensa/op_helper.c b/target/xtensa/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/op_helper.c +++ b/target/xtensa/op_helper.c @@ -XXX,XX +XXX,XX @@ static void tb_invalidate_virtual_addr(CPUXtensaState *env, uint32_t vaddr) int ret = xtensa_get_physical_addr(env, false, vaddr, 2, 0, &paddr, &page_size, &access); if (ret == 0) { - tb_invalidate_phys_addr(&address_space_memory, paddr); + tb_invalidate_phys_addr(&address_space_memory, paddr, + MEMTXATTRS_UNSPECIFIED); } } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_translate() and address_space_translate_cached(). Callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-4-peter.maydell@linaro.org --- include/exec/memory.h | 4 +++- accel/tcg/translate-all.c | 2 +- exec.c | 14 +++++++++----- hw/vfio/common.c | 3 ++- memory_ldst.inc.c | 18 +++++++++--------- target/riscv/helper.c | 2 +- 6 files changed, 25 insertions(+), 18 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, * #MemoryRegion. * @len: pointer to length * @is_write: indicates the transfer direction + * @attrs: memory attributes */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, @@ -XXX,XX +XXX,XX @@ MemoryRegion *flatview_translate(FlatView *fv, static inline MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write) + hwaddr *len, bool is_write, + MemTxAttrs attrs) { return flatview_translate(address_space_to_flatview(as), addr, xlat, len, is_write); diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/translate-all.c +++ b/accel/tcg/translate-all.c @@ -XXX,XX +XXX,XX @@ void tb_invalidate_phys_addr(AddressSpace *as, hwaddr addr, MemTxAttrs attrs) hwaddr l = 1; rcu_read_lock(); - mr = address_space_translate(as, addr, &addr, &l, false); + mr = address_space_translate(as, addr, &addr, &l, false, attrs); if (!(memory_region_is_ram(mr) || memory_region_is_romd(mr))) { rcu_read_unlock(); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static inline void cpu_physical_memory_write_rom_internal(AddressSpace *as, rcu_read_lock(); while (len > 0) { l = len; - mr = address_space_translate(as, addr, &addr1, &l, true); + mr = address_space_translate(as, addr, &addr1, &l, true, + MEMTXATTRS_UNSPECIFIED); if (!(memory_region_is_ram(mr) || memory_region_is_romd(mr))) { @@ -XXX,XX +XXX,XX @@ void address_space_cache_destroy(MemoryRegionCache *cache) */ static inline MemoryRegion *address_space_translate_cached( MemoryRegionCache *cache, hwaddr addr, hwaddr *xlat, - hwaddr *plen, bool is_write) + hwaddr *plen, bool is_write, MemTxAttrs attrs) { MemoryRegionSection section; MemoryRegion *mr; @@ -XXX,XX +XXX,XX @@ address_space_read_cached_slow(MemoryRegionCache *cache, hwaddr addr, MemoryRegion *mr; l = len; - mr = address_space_translate_cached(cache, addr, &addr1, &l, false); + mr = address_space_translate_cached(cache, addr, &addr1, &l, false, + MEMTXATTRS_UNSPECIFIED); flatview_read_continue(cache->fv, addr, MEMTXATTRS_UNSPECIFIED, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ address_space_write_cached_slow(MemoryRegionCache *cache, hwaddr addr, MemoryRegion *mr; l = len; - mr = address_space_translate_cached(cache, addr, &addr1, &l, true); + mr = address_space_translate_cached(cache, addr, &addr1, &l, true, + MEMTXATTRS_UNSPECIFIED); flatview_write_continue(cache->fv, addr, MEMTXATTRS_UNSPECIFIED, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ bool cpu_physical_memory_is_io(hwaddr phys_addr) rcu_read_lock(); mr = address_space_translate(&address_space_memory, - phys_addr, &phys_addr, &l, false); + phys_addr, &phys_addr, &l, false, + MEMTXATTRS_UNSPECIFIED); res = !(memory_region_is_ram(mr) || memory_region_is_romd(mr)); rcu_read_unlock(); diff --git a/hw/vfio/common.c b/hw/vfio/common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -XXX,XX +XXX,XX @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr, */ mr = address_space_translate(&address_space_memory, iotlb->translated_addr, - &xlat, &len, writable); + &xlat, &len, writable, + MEMTXATTRS_UNSPECIFIED); if (!memory_region_is_ram(mr)) { error_report("iommu map to non memory area %"HWADDR_PRIx"", xlat); diff --git a/memory_ldst.inc.c b/memory_ldst.inc.c index XXXXXXX..XXXXXXX 100644 --- a/memory_ldst.inc.c +++ b/memory_ldst.inc.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t glue(address_space_ldl_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 4 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline uint64_t glue(address_space_ldq_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 8 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ uint32_t glue(address_space_ldub, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (!IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline uint32_t glue(address_space_lduw_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, false); + mr = TRANSLATE(addr, &addr1, &l, false, attrs); if (l < 2 || !IS_DIRECT(mr, false)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ void glue(address_space_stl_notdirty, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 4 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static inline void glue(address_space_stl_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 4 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ void glue(address_space_stb, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (!IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); r = memory_region_dispatch_write(mr, addr1, val, 1, attrs); @@ -XXX,XX +XXX,XX @@ static inline void glue(address_space_stw_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 2 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); @@ -XXX,XX +XXX,XX @@ static void glue(address_space_stq_internal, SUFFIX)(ARG1_DECL, bool release_lock = false; RCU_READ_LOCK(); - mr = TRANSLATE(addr, &addr1, &l, true); + mr = TRANSLATE(addr, &addr1, &l, true, attrs); if (l < 8 || !IS_DIRECT(mr, true)) { release_lock |= prepare_mmio_access(mr); diff --git a/target/riscv/helper.c b/target/riscv/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/helper.c +++ b/target/riscv/helper.c @@ -XXX,XX +XXX,XX @@ restart: MemoryRegion *mr; hwaddr l = sizeof(target_ulong), addr1; mr = address_space_translate(cs->as, pte_addr, - &addr1, &l, false); + &addr1, &l, false, MEMTXATTRS_UNSPECIFIED); if (memory_access_is_direct(mr, true)) { target_ulong *pte_pa = qemu_map_ram_ptr(mr->ram_block, addr1); -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_map(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-5-peter.maydell@linaro.org --- include/exec/memory.h | 3 ++- include/sysemu/dma.h | 3 ++- exec.c | 6 ++++-- target/ppc/mmu-hash64.c | 3 ++- 4 files changed, 10 insertions(+), 5 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_ * @addr: address within that address space * @plen: pointer to length of buffer; updated on return * @is_write: indicates the transfer direction + * @attrs: memory attributes */ void *address_space_map(AddressSpace *as, hwaddr addr, - hwaddr *plen, bool is_write); + hwaddr *plen, bool is_write, MemTxAttrs attrs); /* address_space_unmap: Unmaps a memory region previously mapped by address_space_map() * diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -XXX,XX +XXX,XX @@ static inline void *dma_memory_map(AddressSpace *as, hwaddr xlen = *len; void *p; - p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE); + p = address_space_map(as, addr, &xlen, dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); *len = xlen; return p; } diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ flatview_extend_translation(FlatView *fv, hwaddr addr, void *address_space_map(AddressSpace *as, hwaddr addr, hwaddr *plen, - bool is_write) + bool is_write, + MemTxAttrs attrs) { hwaddr len = *plen; hwaddr l, xlat; @@ -XXX,XX +XXX,XX @@ void *cpu_physical_memory_map(hwaddr addr, hwaddr *plen, int is_write) { - return address_space_map(&address_space_memory, addr, plen, is_write); + return address_space_map(&address_space_memory, addr, plen, is_write, + MEMTXATTRS_UNSPECIFIED); } void cpu_physical_memory_unmap(void *buffer, hwaddr len, diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -XXX,XX +XXX,XX @@ const ppc_hash_pte64_t *ppc_hash64_map_hptes(PowerPCCPU *cpu, return NULL; } - hptes = address_space_map(CPU(cpu)->as, base + pte_offset, &plen, false); + hptes = address_space_map(CPU(cpu)->as, base + pte_offset, &plen, false, + MEMTXATTRS_UNSPECIFIED); if (plen < (n * HASH_PTE_SIZE_64)) { hw_error("%s: Unable to map all requested HPTEs\n", __func__); } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_access_valid(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-6-peter.maydell@linaro.org --- include/exec/memory.h | 4 +++- include/sysemu/dma.h | 3 ++- exec.c | 3 ++- target/s390x/diag.c | 6 ++++-- target/s390x/excp_helper.c | 3 ++- target/s390x/mmu_helper.c | 3 ++- target/s390x/sigp.c | 3 ++- 7 files changed, 17 insertions(+), 8 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, * @addr: address within that address space * @len: length of the area to be checked * @is_write: indicates the transfer direction + * @attrs: memory attributes */ -bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, bool is_write); +bool address_space_access_valid(AddressSpace *as, hwaddr addr, int len, + bool is_write, MemTxAttrs attrs); /* address_space_map: map a physical memory region into a host virtual address * diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -XXX,XX +XXX,XX @@ static inline bool dma_memory_valid(AddressSpace *as, DMADirection dir) { return address_space_access_valid(as, addr, len, - dir == DMA_DIRECTION_FROM_DEVICE); + dir == DMA_DIRECTION_FROM_DEVICE, + MEMTXATTRS_UNSPECIFIED); } static inline int dma_memory_rw_relaxed(AddressSpace *as, dma_addr_t addr, diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, } bool address_space_access_valid(AddressSpace *as, hwaddr addr, - int len, bool is_write) + int len, bool is_write, + MemTxAttrs attrs) { FlatView *fv; bool result; diff --git a/target/s390x/diag.c b/target/s390x/diag.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/diag.c +++ b/target/s390x/diag.c @@ -XXX,XX +XXX,XX @@ void handle_diag_308(CPUS390XState *env, uint64_t r1, uint64_t r3, uintptr_t ra) return; } if (!address_space_access_valid(&address_space_memory, addr, - sizeof(IplParameterBlock), false)) { + sizeof(IplParameterBlock), false, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_ADDRESSING, ILEN_AUTO, ra); return; } @@ -XXX,XX +XXX,XX @@ out: return; } if (!address_space_access_valid(&address_space_memory, addr, - sizeof(IplParameterBlock), true)) { + sizeof(IplParameterBlock), true, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_ADDRESSING, ILEN_AUTO, ra); return; } diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/excp_helper.c +++ b/target/s390x/excp_helper.c @@ -XXX,XX +XXX,XX @@ int s390_cpu_handle_mmu_fault(CPUState *cs, vaddr orig_vaddr, int size, /* check out of RAM access */ if (!address_space_access_valid(&address_space_memory, raddr, - TARGET_PAGE_SIZE, rw)) { + TARGET_PAGE_SIZE, rw, + MEMTXATTRS_UNSPECIFIED)) { DPRINTF("%s: raddr %" PRIx64 " > ram_size %" PRIx64 "\n", __func__, (uint64_t)raddr, (uint64_t)ram_size); trigger_pgm_exception(env, PGM_ADDRESSING, ILEN_AUTO); diff --git a/target/s390x/mmu_helper.c b/target/s390x/mmu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/mmu_helper.c +++ b/target/s390x/mmu_helper.c @@ -XXX,XX +XXX,XX @@ static int translate_pages(S390CPU *cpu, vaddr addr, int nr_pages, return ret; } if (!address_space_access_valid(&address_space_memory, pages[i], - TARGET_PAGE_SIZE, is_write)) { + TARGET_PAGE_SIZE, is_write, + MEMTXATTRS_UNSPECIFIED)) { trigger_access_exception(env, PGM_ADDRESSING, ILEN_AUTO, 0); return -EFAULT; } diff --git a/target/s390x/sigp.c b/target/s390x/sigp.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/sigp.c +++ b/target/s390x/sigp.c @@ -XXX,XX +XXX,XX @@ static void sigp_set_prefix(CPUState *cs, run_on_cpu_data arg) cpu_synchronize_state(cs); if (!address_space_access_valid(&address_space_memory, addr, - sizeof(struct LowCore), false)) { + sizeof(struct LowCore), false, + MEMTXATTRS_UNSPECIFIED)) { set_sigp_status(si, SIGP_STAT_INVALID_PARAMETER); return; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_extend_translation(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-7-peter.maydell@linaro.org --- exec.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, static hwaddr flatview_extend_translation(FlatView *fv, hwaddr addr, - hwaddr target_len, - MemoryRegion *mr, hwaddr base, hwaddr len, - bool is_write) + hwaddr target_len, + MemoryRegion *mr, hwaddr base, hwaddr len, + bool is_write, MemTxAttrs attrs) { hwaddr done = 0; hwaddr xlat; @@ -XXX,XX +XXX,XX @@ void *address_space_map(AddressSpace *as, memory_region_ref(mr); *plen = flatview_extend_translation(fv, addr, len, mr, xlat, - l, is_write); + l, is_write, attrs); ptr = qemu_ram_ptr_length(mr->ram_block, xlat, plen, true); rcu_read_unlock(); @@ -XXX,XX +XXX,XX @@ int64_t address_space_cache_init(MemoryRegionCache *cache, mr = cache->mrs.mr; memory_region_ref(mr); if (memory_access_is_direct(mr, is_write)) { + /* We don't care about the memory attributes here as we're only + * doing this if we found actual RAM, which behaves the same + * regardless of attributes; so UNSPECIFIED is fine. + */ l = flatview_extend_translation(cache->fv, addr, len, mr, - cache->xlat, l, is_write); + cache->xlat, l, is_write, + MEMTXATTRS_UNSPECIFIED); cache->ptr = qemu_ram_ptr_length(mr->ram_block, cache->xlat, &l, true); } else { cache->ptr = NULL; -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to memory_region_access_valid(). Its callers either have an attrs value to hand, or don't care and can use MEMTXATTRS_UNSPECIFIED. The callsite in flatview_access_valid() is part of a recursive loop flatview_access_valid() -> memory_region_access_valid() -> subpage_accepts() -> flatview_access_valid(); we make it pass MEMTXATTRS_UNSPECIFIED for now, until the next several commits have plumbed an attrs parameter through the rest of the loop and we can add an attrs parameter to flatview_access_valid(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-8-peter.maydell@linaro.org --- include/exec/memory-internal.h | 3 ++- exec.c | 4 +++- hw/s390x/s390-pci-inst.c | 3 ++- memory.c | 7 ++++--- 4 files changed, 11 insertions(+), 6 deletions(-) diff --git a/include/exec/memory-internal.h b/include/exec/memory-internal.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory-internal.h +++ b/include/exec/memory-internal.h @@ -XXX,XX +XXX,XX @@ void flatview_unref(FlatView *view); extern const MemoryRegionOps unassigned_mem_ops; bool memory_region_access_valid(MemoryRegion *mr, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); void flatview_add_to_dispatch(FlatView *fv, MemoryRegionSection *section); AddressSpaceDispatch *address_space_dispatch_new(FlatView *fv); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, mr = flatview_translate(fv, addr, &xlat, &l, is_write); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); - if (!memory_region_access_valid(mr, xlat, l, is_write)) { + /* When our callers all have attrs we'll pass them through here */ + if (!memory_region_access_valid(mr, xlat, l, is_write, + MEMTXATTRS_UNSPECIFIED)) { return false; } } diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -XXX,XX +XXX,XX @@ int pcistb_service_call(S390CPU *cpu, uint8_t r1, uint8_t r3, uint64_t gaddr, mr = s390_get_subregion(mr, offset, len); offset -= mr->addr; - if (!memory_region_access_valid(mr, offset, len, true)) { + if (!memory_region_access_valid(mr, offset, len, true, + MEMTXATTRS_UNSPECIFIED)) { s390_program_interrupt(env, PGM_OPERAND, 6, ra); return 0; } diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps ram_device_mem_ops = { bool memory_region_access_valid(MemoryRegion *mr, hwaddr addr, unsigned size, - bool is_write) + bool is_write, + MemTxAttrs attrs) { int access_size_min, access_size_max; int access_size, i; @@ -XXX,XX +XXX,XX @@ MemTxResult memory_region_dispatch_read(MemoryRegion *mr, { MemTxResult r; - if (!memory_region_access_valid(mr, addr, size, false)) { + if (!memory_region_access_valid(mr, addr, size, false, attrs)) { *pval = unassigned_mem_read(mr, addr, size); return MEMTX_DECODE_ERROR; } @@ -XXX,XX +XXX,XX @@ MemTxResult memory_region_dispatch_write(MemoryRegion *mr, unsigned size, MemTxAttrs attrs) { - if (!memory_region_access_valid(mr, addr, size, true)) { + if (!memory_region_access_valid(mr, addr, size, true, attrs)) { unassigned_mem_write(mr, addr, data, size); return MEMTX_DECODE_ERROR; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to the MemoryRegion valid.accepts callback. We'll need this for subpage_accepts(). We could take the approach we used with the read and write callbacks and add new a new _with_attrs version, but since there are so few implementations of the accepts hook we just change them all. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-9-peter.maydell@linaro.org --- include/exec/memory.h | 3 ++- exec.c | 9 ++++++--- hw/hppa/dino.c | 3 ++- hw/nvram/fw_cfg.c | 12 ++++++++---- hw/scsi/esp.c | 3 ++- hw/xen/xen_pt_msi.c | 3 ++- memory.c | 5 +++-- 7 files changed, 25 insertions(+), 13 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ struct MemoryRegionOps { * as a machine check exception). */ bool (*accepts)(void *opaque, hwaddr addr, - unsigned size, bool is_write); + unsigned size, bool is_write, + MemTxAttrs attrs); } valid; /* Internal implementation constraints: */ struct { diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void notdirty_mem_write(void *opaque, hwaddr ram_addr, } static bool notdirty_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write; } @@ -XXX,XX +XXX,XX @@ static MemTxResult subpage_write(void *opaque, hwaddr addr, } static bool subpage_accepts(void *opaque, hwaddr addr, - unsigned len, bool is_write) + unsigned len, bool is_write, + MemTxAttrs attrs) { subpage_t *subpage = opaque; #if defined(DEBUG_SUBPAGE) @@ -XXX,XX +XXX,XX @@ static void readonly_mem_write(void *opaque, hwaddr addr, } static bool readonly_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write; } diff --git a/hw/hppa/dino.c b/hw/hppa/dino.c index XXXXXXX..XXXXXXX 100644 --- a/hw/hppa/dino.c +++ b/hw/hppa/dino.c @@ -XXX,XX +XXX,XX @@ static void gsc_to_pci_forwarding(DinoState *s) } static bool dino_chip_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { switch (addr) { case DINO_IAR0: diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -XXX,XX +XXX,XX @@ static void fw_cfg_dma_mem_write(void *opaque, hwaddr addr, } static bool fw_cfg_dma_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return !is_write || ((size == 4 && (addr == 0 || addr == 4)) || (size == 8 && addr == 0)); } static bool fw_cfg_data_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return addr == 0; } @@ -XXX,XX +XXX,XX @@ static void fw_cfg_ctl_mem_write(void *opaque, hwaddr addr, } static bool fw_cfg_ctl_mem_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return is_write && size == 2; } @@ -XXX,XX +XXX,XX @@ static void fw_cfg_comb_write(void *opaque, hwaddr addr, } static bool fw_cfg_comb_valid(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return (size == 1) || (is_write && size == 2); } diff --git a/hw/scsi/esp.c b/hw/scsi/esp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/esp.c +++ b/hw/scsi/esp.c @@ -XXX,XX +XXX,XX @@ void esp_reg_write(ESPState *s, uint32_t saddr, uint64_t val) } static bool esp_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return (size == 1) || (is_write && size == 4); } diff --git a/hw/xen/xen_pt_msi.c b/hw/xen/xen_pt_msi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/xen/xen_pt_msi.c +++ b/hw/xen/xen_pt_msi.c @@ -XXX,XX +XXX,XX @@ static uint64_t pci_msix_read(void *opaque, hwaddr addr, } static bool pci_msix_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return !(addr & (size - 1)); } diff --git a/memory.c b/memory.c index XXXXXXX..XXXXXXX 100644 --- a/memory.c +++ b/memory.c @@ -XXX,XX +XXX,XX @@ static void unassigned_mem_write(void *opaque, hwaddr addr, } static bool unassigned_mem_accepts(void *opaque, hwaddr addr, - unsigned size, bool is_write) + unsigned size, bool is_write, + MemTxAttrs attrs) { return false; } @@ -XXX,XX +XXX,XX @@ bool memory_region_access_valid(MemoryRegion *mr, access_size = MAX(MIN(size, access_size_max), access_size_min); for (i = 0; i < size; i += access_size) { if (!mr->ops->valid.accepts(mr->opaque, addr + i, access_size, - is_write)) { + is_write, attrs)) { return false; } } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_access_valid(). Its callers now all have an attrs value to hand, so we can correct our earlier temporary use of MEMTXATTRS_UNSPECIFIED. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-10-peter.maydell@linaro.org --- exec.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, const uint8_t *buf, int len); static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, - bool is_write); + bool is_write, MemTxAttrs attrs); static MemTxResult subpage_read(void *opaque, hwaddr addr, uint64_t *data, unsigned len, MemTxAttrs attrs) @@ -XXX,XX +XXX,XX @@ static bool subpage_accepts(void *opaque, hwaddr addr, #endif return flatview_access_valid(subpage->fv, addr + subpage->base, - len, is_write); + len, is_write, attrs); } static const MemoryRegionOps subpage_ops = { @@ -XXX,XX +XXX,XX @@ static void cpu_notify_map_clients(void) } static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, - bool is_write) + bool is_write, MemTxAttrs attrs) { MemoryRegion *mr; hwaddr l, xlat; @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, mr = flatview_translate(fv, addr, &xlat, &l, is_write); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); - /* When our callers all have attrs we'll pass them through here */ - if (!memory_region_access_valid(mr, xlat, l, is_write, - MEMTXATTRS_UNSPECIFIED)) { + if (!memory_region_access_valid(mr, xlat, l, is_write, attrs)) { return false; } } @@ -XXX,XX +XXX,XX @@ bool address_space_access_valid(AddressSpace *as, hwaddr addr, rcu_read_lock(); fv = address_space_to_flatview(as); - result = flatview_access_valid(fv, addr, len, is_write); + result = flatview_access_valid(fv, addr, len, is_write, attrs); rcu_read_unlock(); return result; } -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_translate(); all its callers now have attrs available. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-11-peter.maydell@linaro.org --- include/exec/memory.h | 7 ++++--- exec.c | 17 +++++++++-------- 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, - hwaddr *len, bool is_write); + hwaddr *len, bool is_write, + MemTxAttrs attrs); static inline MemoryRegion *address_space_translate(AddressSpace *as, hwaddr addr, hwaddr *xlat, @@ -XXX,XX +XXX,XX @@ static inline MemoryRegion *address_space_translate(AddressSpace *as, MemTxAttrs attrs) { return flatview_translate(address_space_to_flatview(as), - addr, xlat, len, is_write); + addr, xlat, len, is_write, attrs); } /* address_space_access_valid: check for validity of accessing an address @@ -XXX,XX +XXX,XX @@ MemTxResult address_space_read(AddressSpace *as, hwaddr addr, rcu_read_lock(); fv = address_space_to_flatview(as); l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); if (len == l && memory_access_is_direct(mr, false)) { ptr = qemu_map_ram_ptr(mr->ram_block, addr1); memcpy(buf, ptr, len); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ iotlb_fail: /* Called from RCU critical section */ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, - hwaddr *plen, bool is_write) + hwaddr *plen, bool is_write, + MemTxAttrs attrs) { MemoryRegion *mr; MemoryRegionSection section; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_write_continue(FlatView *fv, hwaddr addr, } l = len; - mr = flatview_translate(fv, addr, &addr1, &l, true); + mr = flatview_translate(fv, addr, &addr1, &l, true, attrs); } return result; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_write(FlatView *fv, hwaddr addr, MemTxAttrs attrs, MemTxResult result = MEMTX_OK; l = len; - mr = flatview_translate(fv, addr, &addr1, &l, true); + mr = flatview_translate(fv, addr, &addr1, &l, true, attrs); result = flatview_write_continue(fv, addr, attrs, buf, len, addr1, l, mr); @@ -XXX,XX +XXX,XX @@ MemTxResult flatview_read_continue(FlatView *fv, hwaddr addr, } l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); } return result; @@ -XXX,XX +XXX,XX @@ static MemTxResult flatview_read(FlatView *fv, hwaddr addr, MemoryRegion *mr; l = len; - mr = flatview_translate(fv, addr, &addr1, &l, false); + mr = flatview_translate(fv, addr, &addr1, &l, false, attrs); return flatview_read_continue(fv, addr, attrs, buf, len, addr1, l, mr); } @@ -XXX,XX +XXX,XX @@ static bool flatview_access_valid(FlatView *fv, hwaddr addr, int len, while (len > 0) { l = len; - mr = flatview_translate(fv, addr, &xlat, &l, is_write); + mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs); if (!memory_access_is_direct(mr, is_write)) { l = memory_access_size(mr, l, addr); if (!memory_region_access_valid(mr, xlat, l, is_write, attrs)) { @@ -XXX,XX +XXX,XX @@ flatview_extend_translation(FlatView *fv, hwaddr addr, len = target_len; this_mr = flatview_translate(fv, addr, &xlat, - &len, is_write); + &len, is_write, attrs); if (this_mr != mr || xlat != base + done) { return done; } @@ -XXX,XX +XXX,XX @@ void *address_space_map(AddressSpace *as, l = len; rcu_read_lock(); fv = address_space_to_flatview(as); - mr = flatview_translate(fv, addr, &xlat, &l, is_write); + mr = flatview_translate(fv, addr, &xlat, &l, is_write, attrs); if (!memory_access_is_direct(mr, is_write)) { if (atomic_xchg(&bounce.in_use, true)) { -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_get_iotlb_entry(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-12-peter.maydell@linaro.org --- include/exec/memory.h | 2 +- exec.c | 2 +- hw/virtio/vhost.c | 3 ++- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ void address_space_cache_destroy(MemoryRegionCache *cache); * entry. Should be called from an RCU critical section. */ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, - bool is_write); + bool is_write, MemTxAttrs attrs); /* address_space_translate: translate an address range into an address space * into a MemoryRegion and an address range into that section. Should be diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, /* Called from RCU critical section */ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, - bool is_write) + bool is_write, MemTxAttrs attrs) { MemoryRegionSection section; hwaddr xlat, page_mask; diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -XXX,XX +XXX,XX @@ int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write) trace_vhost_iotlb_miss(dev, 1); iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as, - iova, write); + iova, write, + MEMTXATTRS_UNSPECIFIED); if (iotlb.target_as != NULL) { ret = vhost_memory_region_lookup(dev, iotlb.translated_addr, &uaddr, &len); -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to flatview_do_translate(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-13-peter.maydell@linaro.org --- exec.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ unassigned: * @is_write: whether the translation operation is for write * @is_mmio: whether this can be MMIO, set true if it can * @target_as: the address space targeted by the IOMMU + * @attrs: memory transaction attributes * * This function is called from RCU critical section */ @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, hwaddr *page_mask_out, bool is_write, bool is_mmio, - AddressSpace **target_as) + AddressSpace **target_as, + MemTxAttrs attrs) { MemoryRegionSection *section; IOMMUMemoryRegion *iommu_mr; @@ -XXX,XX +XXX,XX @@ IOMMUTLBEntry address_space_get_iotlb_entry(AddressSpace *as, hwaddr addr, * but page mask. */ section = flatview_do_translate(address_space_to_flatview(as), addr, &xlat, - NULL, &page_mask, is_write, false, &as); + NULL, &page_mask, is_write, false, &as, + attrs); /* Illegal translation */ if (section.mr == &io_mem_unassigned) { @@ -XXX,XX +XXX,XX @@ MemoryRegion *flatview_translate(FlatView *fv, hwaddr addr, hwaddr *xlat, /* This can be MMIO, so setup MMIO bit. */ section = flatview_do_translate(fv, addr, xlat, plen, NULL, - is_write, true, &as); + is_write, true, &as, attrs); mr = section.mr; if (xen_enabled() && memory_access_is_direct(mr, is_write)) { -- 2.17.1 As part of plumbing MemTxAttrs down to the IOMMU translate method, add MemTxAttrs as an argument to address_space_translate_iommu(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180521140402.23318-14-peter.maydell@linaro.org --- exec.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ address_space_translate_internal(AddressSpaceDispatch *d, hwaddr addr, hwaddr *x * @is_write: whether the translation operation is for write * @is_mmio: whether this can be MMIO, set true if it can * @target_as: the address space targeted by the IOMMU + * @attrs: transaction attributes * * This function is called from RCU critical section. It is the common * part of flatview_do_translate and address_space_translate_cached. @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection address_space_translate_iommu(IOMMUMemoryRegion *iomm hwaddr *page_mask_out, bool is_write, bool is_mmio, - AddressSpace **target_as) + AddressSpace **target_as, + MemTxAttrs attrs) { MemoryRegionSection *section; hwaddr page_mask = (hwaddr)-1; @@ -XXX,XX +XXX,XX @@ static MemoryRegionSection flatview_do_translate(FlatView *fv, return address_space_translate_iommu(iommu_mr, xlat, plen_out, page_mask_out, is_write, is_mmio, - target_as); + target_as, attrs); } if (page_mask_out) { /* Not behind an IOMMU, use default page size. */ @@ -XXX,XX +XXX,XX @@ static inline MemoryRegion *address_space_translate_cached( section = address_space_translate_iommu(iommu_mr, xlat, plen, NULL, is_write, true, - &target_as); + &target_as, attrs); return section.mr; } -- 2.17.1 Provide a VMSTATE_BOOL_SUB_ARRAY to go with VMSTATE_UINT8_SUB_ARRAY and friends. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180521140402.23318-23-peter.maydell@linaro.org --- include/migration/vmstate.h | 3 +++ 1 file changed, 3 insertions(+) diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index XXXXXXX..XXXXXXX 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -XXX,XX +XXX,XX @@ extern const VMStateInfo vmstate_info_qtailq; #define VMSTATE_BOOL_ARRAY(_f, _s, _n) \ VMSTATE_BOOL_ARRAY_V(_f, _s, _n, 0) +#define VMSTATE_BOOL_SUB_ARRAY(_f, _s, _start, _num) \ + VMSTATE_SUB_ARRAY(_f, _s, _start, _num, 0, vmstate_info_bool, bool) + #define VMSTATE_UINT16_ARRAY_V(_f, _s, _n, _v) \ VMSTATE_ARRAY(_f, _s, _n, _v, vmstate_info_uint16, uint16_t) -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> acpi_data_push uses g_array_set_size to resize the memory size. If there is no enough contiguous memory, the address will be changed. So previous pointer could not be used any more. It must update the pointer and use the new one. Also, previous codes wrongly use le32 conversion of iort->node_offset for subsequent computations that will result incorrect value if host is not litlle endian. So use the non-converted one instead. Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527663951-14552-1-git-send-email-zhaoshenglong@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt-acpi-build.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) AcpiIortItsGroup *its; AcpiIortTable *iort; AcpiIortSmmu3 *smmu; - size_t node_size, iort_length, smmu_offset = 0; + size_t node_size, iort_node_offset, iort_length, smmu_offset = 0; AcpiIortRC *rc; iort = acpi_data_push(table_data, sizeof(*iort)); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) iort_length = sizeof(*iort); iort->node_count = cpu_to_le32(nb_nodes); - iort->node_offset = cpu_to_le32(sizeof(*iort)); + /* + * Use a copy in case table_data->data moves during acpi_data_push + * operations. + */ + iort_node_offset = sizeof(*iort); + iort->node_offset = cpu_to_le32(iort_node_offset); /* ITS group node */ node_size = sizeof(*its) + sizeof(uint32_t); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) int irq = vms->irqmap[VIRT_SMMU]; /* SMMUv3 node */ - smmu_offset = iort->node_offset + node_size; + smmu_offset = iort_node_offset + node_size; node_size = sizeof(*smmu) + sizeof(*idmap); iort_length += node_size; smmu = acpi_data_push(table_data, node_size); @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) idmap->id_count = cpu_to_le32(0xFFFF); idmap->output_base = 0; /* output IORT node is the ITS group node (the first node) */ - idmap->output_reference = cpu_to_le32(iort->node_offset); + idmap->output_reference = cpu_to_le32(iort_node_offset); } /* Root Complex Node */ @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) idmap->output_reference = cpu_to_le32(smmu_offset); } else { /* output IORT node is the ITS group node (the first node) */ - idmap->output_reference = cpu_to_le32(iort->node_offset); + idmap->output_reference = cpu_to_le32(iort_node_offset); } + /* + * Update the pointer address in case table_data->data moves during above + * acpi_data_push operations. + */ + iort = (AcpiIortTable *)(table_data->data + iort_start); iort->length = cpu_to_le32(iort_length); build_header(linker, table_data, (void *)(table_data->data + iort_start), -- 2.17.1 From: Shannon Zhao <zhaoshenglong@huawei.com> kvm_irqchip_create called by kvm_init will call kvm_init_irq_routing to initialize global capability variables. If we call kvm_init_irq_routing in GIC realize function, previous allocated memory will leak. Fix this by deleting the unnecessary call. Signed-off-by: Shannon Zhao <zhaoshenglong@huawei.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1527750994-14360-1-git-send-email-zhaoshenglong@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gic_kvm.c | 1 - hw/intc/arm_gicv3_kvm.c | 1 - 2 files changed, 2 deletions(-) diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp) if (kvm_has_gsi_routing()) { /* set up irq routing */ - kvm_init_irq_routing(kvm_state); for (i = 0; i < s->num_irq - GIC_INTERNAL; ++i) { kvm_irqchip_add_irq_route(kvm_state, i, 0, i); } diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) if (kvm_has_gsi_routing()) { /* set up irq routing */ - kvm_init_irq_routing(kvm_state); for (i = 0; i < s->num_irq - GIC_INTERNAL; ++i) { kvm_irqchip_add_irq_route(kvm_state, i, 0, i); } -- 2.17.1 Last pullreq before 6.0 softfreeze: a few minor feature patches, some bugfixes, some cleanups. -- PMM The following changes since commit 6f34661b6c97a37a5efc27d31c037ddeda4547e2: Merge remote-tracking branch 'remotes/vivier2/tags/trivial-branch-for-6.0-pull-request' into staging (2021-03-11 18:55:27 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210312-1 for you to fetch changes up to 41f09f2e9f09e4dd386d84174a6dcb5136af17ca: hw/display/pxa2xx: Inline template header (2021-03-12 13:26:08 +0000) ---------------------------------------------------------------- target-arm queue: * versal: Support XRAMs and XRAM controller * smmu: Various minor bug fixes * SVE emulation: fix bugs handling odd vector lengths * allwinner-sun8i-emac: traverse transmit queue using TX_CUR_DESC register value * tests/acceptance: fix orangepi-pc acceptance tests * hw/timer/sse-timer: Propagate eventual error in sse_timer_realize() * hw/arm/virt: KVM: The IPA lower bound is 32 * npcm7xx: support MFT module * pl110, pxa2xx_lcd: tidy up template headers ---------------------------------------------------------------- Andrew Jones (2): accel: kvm: Fix kvm_type invocation hw/arm/virt: KVM: The IPA lower bound is 32 Edgar E. Iglesias (2): hw/misc: versal: Add a model of the XRAM controller hw/arm: versal: Add support for the XRAMs Eric Auger (7): intel_iommu: Fix mask may be uninitialized in vtd_context_device_invalidate dma: Introduce dma_aligned_pow2_mask() virtio-iommu: Handle non power of 2 range invalidations hw/arm/smmu-common: Fix smmu_iotlb_inv_iova when asid is not set hw/arm/smmuv3: Enforce invalidation on a power of two range hw/arm/smmuv3: Fix SMMU_CMD_CFGI_STE_RANGE handling hw/arm/smmuv3: Uniformize sid traces Hao Wu (5): hw/misc: Add GPIOs for duty in NPCM7xx PWM hw/misc: Add NPCM7XX MFT Module hw/arm: Add MFT device to NPCM7xx Soc hw/arm: Connect PWM fans in NPCM7XX boards tests/qtest: Test PWM fan RPM using MFT in PWM test Niek Linnenbank (5): hw/net/allwinner-sun8i-emac: traverse transmit queue using TX_CUR_DESC register value tests/acceptance/boot_linux_console: remove Armbian 19.11.3 bionic test for orangepi-pc machine tests/acceptance/boot_linux_console: change URL for test_arm_orangepi_bionic_20_08 tests/acceptance: update sunxi kernel from armbian to 5.10.16 tests/acceptance: drop ARMBIAN_ARTIFACTS_CACHED condition for orangepi-pc, cubieboard tests Peter Maydell (9): hw/display/pl110: Remove dead code for non-32-bpp surfaces hw/display/pl110: Pull included-once parts of template header into pl110.c hw/display/pl110: Remove use of BITS from pl110_template.h hw/display/pxa2xx_lcd: Remove dead code for non-32-bpp surfaces hw/display/pxa2xx_lcd: Remove dest_width state field hw/display/pxa2xx: Remove use of BITS in pxa2xx_template.h hw/display/pxa2xx: Apply brace-related coding style fixes to template header hw/display/pxa2xx: Apply whitespace-only coding style fixes to template header hw/display/pxa2xx: Inline template header Philippe Mathieu-Daudé (1): hw/timer/sse-timer: Propagate eventual error in sse_timer_realize() Richard Henderson (8): target/arm: Fix sve_uzp_p vs odd vector lengths target/arm: Fix sve_zip_p vs odd vector lengths target/arm: Fix sve_punpk_p vs odd vector lengths target/arm: Update find_last_active for PREDDESC target/arm: Update BRKA, BRKB, BRKN for PREDDESC target/arm: Update CNTP for PREDDESC target/arm: Update WHILE for PREDDESC target/arm: Update sve reduction vs simd_desc docs/system/arm/nuvoton.rst | 2 +- docs/system/arm/xlnx-versal-virt.rst | 1 + hw/arm/smmu-internal.h | 5 + hw/display/pl110_template.h | 120 +------- hw/display/pxa2xx_template.h | 447 --------------------------- include/hw/arm/npcm7xx.h | 13 +- include/hw/arm/xlnx-versal.h | 13 + include/hw/boards.h | 1 + include/hw/misc/npcm7xx_mft.h | 70 +++++ include/hw/misc/npcm7xx_pwm.h | 4 +- include/hw/misc/xlnx-versal-xramc.h | 97 ++++++ include/sysemu/dma.h | 12 + target/arm/kvm_arm.h | 6 +- accel/kvm/kvm-all.c | 2 + hw/arm/npcm7xx.c | 45 ++- hw/arm/npcm7xx_boards.c | 99 ++++++ hw/arm/smmu-common.c | 32 +- hw/arm/smmuv3.c | 58 ++-- hw/arm/virt.c | 23 +- hw/arm/xlnx-versal.c | 36 +++ hw/display/pl110.c | 123 +++++--- hw/display/pxa2xx_lcd.c | 520 ++++++++++++++++++++++++++----- hw/i386/intel_iommu.c | 32 +- hw/misc/npcm7xx_mft.c | 540 +++++++++++++++++++++++++++++++++ hw/misc/npcm7xx_pwm.c | 4 + hw/misc/xlnx-versal-xramc.c | 253 +++++++++++++++ hw/net/allwinner-sun8i-emac.c | 62 ++-- hw/timer/sse-timer.c | 1 + hw/virtio/virtio-iommu.c | 19 +- softmmu/dma-helpers.c | 26 ++ target/arm/kvm.c | 4 +- target/arm/sve_helper.c | 107 ++++--- target/arm/translate-sve.c | 26 +- tests/qtest/npcm7xx_pwm-test.c | 205 ++++++++++++- hw/arm/trace-events | 24 +- hw/misc/meson.build | 2 + hw/misc/trace-events | 8 + tests/acceptance/boot_linux_console.py | 120 +++----- tests/acceptance/replay_kernel.py | 10 +- 39 files changed, 2235 insertions(+), 937 deletions(-) delete mode 100644 hw/display/pxa2xx_template.h create mode 100644 include/hw/misc/npcm7xx_mft.h create mode 100644 include/hw/misc/xlnx-versal-xramc.h create mode 100644 hw/misc/npcm7xx_mft.c create mode 100644 hw/misc/xlnx-versal-xramc.c From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Add a model of the Xilinx Versal Accelerator RAM (XRAM). This is mainly a stub to make firmware happy. The size of the RAMs can be probed. The interrupt mask logic is modelled but none of the interrups will ever be raised unless injected. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210308224637.2949533-2-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/xlnx-versal-xramc.h | 97 +++++++++++ hw/misc/xlnx-versal-xramc.c | 253 ++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 3 files changed, 351 insertions(+) create mode 100644 include/hw/misc/xlnx-versal-xramc.h create mode 100644 hw/misc/xlnx-versal-xramc.c diff --git a/include/hw/misc/xlnx-versal-xramc.h b/include/hw/misc/xlnx-versal-xramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/xlnx-versal-xramc.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx XRAM Controller. + * + * Copyright (c) 2021 Xilinx Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * Written by Edgar E. Iglesias <edgar.iglesias@xilinx.com> + */ + +#ifndef XLNX_VERSAL_XRAMC_H +#define XLNX_VERSAL_XRAMC_H + +#include "hw/sysbus.h" +#include "hw/register.h" + +#define TYPE_XLNX_XRAM_CTRL "xlnx.versal-xramc" + +#define XLNX_XRAM_CTRL(obj) \ + OBJECT_CHECK(XlnxXramCtrl, (obj), TYPE_XLNX_XRAM_CTRL) + +REG32(XRAM_ERR_CTRL, 0x0) + FIELD(XRAM_ERR_CTRL, UE_RES, 3, 1) + FIELD(XRAM_ERR_CTRL, PWR_ERR_RES, 2, 1) + FIELD(XRAM_ERR_CTRL, PZ_ERR_RES, 1, 1) + FIELD(XRAM_ERR_CTRL, APB_ERR_RES, 0, 1) +REG32(XRAM_ISR, 0x4) + FIELD(XRAM_ISR, INV_APB, 0, 1) +REG32(XRAM_IMR, 0x8) + FIELD(XRAM_IMR, INV_APB, 0, 1) +REG32(XRAM_IEN, 0xc) + FIELD(XRAM_IEN, INV_APB, 0, 1) +REG32(XRAM_IDS, 0x10) + FIELD(XRAM_IDS, INV_APB, 0, 1) +REG32(XRAM_ECC_CNTL, 0x14) + FIELD(XRAM_ECC_CNTL, FI_MODE, 2, 1) + FIELD(XRAM_ECC_CNTL, DET_ONLY, 1, 1) + FIELD(XRAM_ECC_CNTL, ECC_ON_OFF, 0, 1) +REG32(XRAM_CLR_EXE, 0x18) + FIELD(XRAM_CLR_EXE, MON_7, 7, 1) + FIELD(XRAM_CLR_EXE, MON_6, 6, 1) + FIELD(XRAM_CLR_EXE, MON_5, 5, 1) + FIELD(XRAM_CLR_EXE, MON_4, 4, 1) + FIELD(XRAM_CLR_EXE, MON_3, 3, 1) + FIELD(XRAM_CLR_EXE, MON_2, 2, 1) + FIELD(XRAM_CLR_EXE, MON_1, 1, 1) + FIELD(XRAM_CLR_EXE, MON_0, 0, 1) +REG32(XRAM_CE_FFA, 0x1c) + FIELD(XRAM_CE_FFA, ADDR, 0, 20) +REG32(XRAM_CE_FFD0, 0x20) +REG32(XRAM_CE_FFD1, 0x24) +REG32(XRAM_CE_FFD2, 0x28) +REG32(XRAM_CE_FFD3, 0x2c) +REG32(XRAM_CE_FFE, 0x30) + FIELD(XRAM_CE_FFE, SYNDROME, 0, 16) +REG32(XRAM_UE_FFA, 0x34) + FIELD(XRAM_UE_FFA, ADDR, 0, 20) +REG32(XRAM_UE_FFD0, 0x38) +REG32(XRAM_UE_FFD1, 0x3c) +REG32(XRAM_UE_FFD2, 0x40) +REG32(XRAM_UE_FFD3, 0x44) +REG32(XRAM_UE_FFE, 0x48) + FIELD(XRAM_UE_FFE, SYNDROME, 0, 16) +REG32(XRAM_FI_D0, 0x4c) +REG32(XRAM_FI_D1, 0x50) +REG32(XRAM_FI_D2, 0x54) +REG32(XRAM_FI_D3, 0x58) +REG32(XRAM_FI_SY, 0x5c) + FIELD(XRAM_FI_SY, DATA, 0, 16) +REG32(XRAM_RMW_UE_FFA, 0x70) + FIELD(XRAM_RMW_UE_FFA, ADDR, 0, 20) +REG32(XRAM_FI_CNTR, 0x74) + FIELD(XRAM_FI_CNTR, COUNT, 0, 24) +REG32(XRAM_IMP, 0x80) + FIELD(XRAM_IMP, SIZE, 0, 4) +REG32(XRAM_PRDY_DBG, 0x84) + FIELD(XRAM_PRDY_DBG, ISLAND3, 12, 4) + FIELD(XRAM_PRDY_DBG, ISLAND2, 8, 4) + FIELD(XRAM_PRDY_DBG, ISLAND1, 4, 4) + FIELD(XRAM_PRDY_DBG, ISLAND0, 0, 4) +REG32(XRAM_SAFETY_CHK, 0xff8) + +#define XRAM_CTRL_R_MAX (R_XRAM_SAFETY_CHK + 1) + +typedef struct XlnxXramCtrl { + SysBusDevice parent_obj; + MemoryRegion ram; + qemu_irq irq; + + struct { + uint64_t size; + unsigned int encoded_size; + } cfg; + + RegisterInfoArray *reg_array; + uint32_t regs[XRAM_CTRL_R_MAX]; + RegisterInfo regs_info[XRAM_CTRL_R_MAX]; +} XlnxXramCtrl; +#endif diff --git a/hw/misc/xlnx-versal-xramc.c b/hw/misc/xlnx-versal-xramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/xlnx-versal-xramc.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx XRAM Controller. + * + * Copyright (c) 2021 Xilinx Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * Written by Edgar E. Iglesias <edgar.iglesias@xilinx.com> + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "migration/vmstate.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/qdev-properties.h" +#include "hw/irq.h" +#include "hw/misc/xlnx-versal-xramc.h" + +#ifndef XLNX_XRAM_CTRL_ERR_DEBUG +#define XLNX_XRAM_CTRL_ERR_DEBUG 0 +#endif + +static void xram_update_irq(XlnxXramCtrl *s) +{ + bool pending = s->regs[R_XRAM_ISR] & ~s->regs[R_XRAM_IMR]; + qemu_set_irq(s->irq, pending); +} + +static void xram_isr_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(reg->opaque); + xram_update_irq(s); +} + +static uint64_t xram_ien_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_XRAM_IMR] &= ~val; + xram_update_irq(s); + return 0; +} + +static uint64_t xram_ids_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_XRAM_IMR] |= val; + xram_update_irq(s); + return 0; +} + +static const RegisterAccessInfo xram_ctrl_regs_info[] = { + { .name = "XRAM_ERR_CTRL", .addr = A_XRAM_ERR_CTRL, + .reset = 0xf, + .rsvd = 0xfffffff0, + },{ .name = "XRAM_ISR", .addr = A_XRAM_ISR, + .rsvd = 0xfffff800, + .w1c = 0x7ff, + .post_write = xram_isr_postw, + },{ .name = "XRAM_IMR", .addr = A_XRAM_IMR, + .reset = 0x7ff, + .rsvd = 0xfffff800, + .ro = 0x7ff, + },{ .name = "XRAM_IEN", .addr = A_XRAM_IEN, + .rsvd = 0xfffff800, + .pre_write = xram_ien_prew, + },{ .name = "XRAM_IDS", .addr = A_XRAM_IDS, + .rsvd = 0xfffff800, + .pre_write = xram_ids_prew, + },{ .name = "XRAM_ECC_CNTL", .addr = A_XRAM_ECC_CNTL, + .rsvd = 0xfffffff8, + },{ .name = "XRAM_CLR_EXE", .addr = A_XRAM_CLR_EXE, + .rsvd = 0xffffff00, + },{ .name = "XRAM_CE_FFA", .addr = A_XRAM_CE_FFA, + .rsvd = 0xfff00000, + .ro = 0xfffff, + },{ .name = "XRAM_CE_FFD0", .addr = A_XRAM_CE_FFD0, + .ro = 0xffffffff, + },{ .name = "XRAM_CE_FFD1", .addr = A_XRAM_CE_FFD1, + .ro = 0xffffffff, + },{ .name = "XRAM_CE_FFD2", .addr = A_XRAM_CE_FFD2, + .ro = 0xffffffff, + },{ .name = "XRAM_CE_FFD3", .addr = A_XRAM_CE_FFD3, + .ro = 0xffffffff, + },{ .name = "XRAM_CE_FFE", .addr = A_XRAM_CE_FFE, + .rsvd = 0xffff0000, + .ro = 0xffff, + },{ .name = "XRAM_UE_FFA", .addr = A_XRAM_UE_FFA, + .rsvd = 0xfff00000, + .ro = 0xfffff, + },{ .name = "XRAM_UE_FFD0", .addr = A_XRAM_UE_FFD0, + .ro = 0xffffffff, + },{ .name = "XRAM_UE_FFD1", .addr = A_XRAM_UE_FFD1, + .ro = 0xffffffff, + },{ .name = "XRAM_UE_FFD2", .addr = A_XRAM_UE_FFD2, + .ro = 0xffffffff, + },{ .name = "XRAM_UE_FFD3", .addr = A_XRAM_UE_FFD3, + .ro = 0xffffffff, + },{ .name = "XRAM_UE_FFE", .addr = A_XRAM_UE_FFE, + .rsvd = 0xffff0000, + .ro = 0xffff, + },{ .name = "XRAM_FI_D0", .addr = A_XRAM_FI_D0, + },{ .name = "XRAM_FI_D1", .addr = A_XRAM_FI_D1, + },{ .name = "XRAM_FI_D2", .addr = A_XRAM_FI_D2, + },{ .name = "XRAM_FI_D3", .addr = A_XRAM_FI_D3, + },{ .name = "XRAM_FI_SY", .addr = A_XRAM_FI_SY, + .rsvd = 0xffff0000, + },{ .name = "XRAM_RMW_UE_FFA", .addr = A_XRAM_RMW_UE_FFA, + .rsvd = 0xfff00000, + .ro = 0xfffff, + },{ .name = "XRAM_FI_CNTR", .addr = A_XRAM_FI_CNTR, + .rsvd = 0xff000000, + },{ .name = "XRAM_IMP", .addr = A_XRAM_IMP, + .reset = 0x4, + .rsvd = 0xfffffff0, + .ro = 0xf, + },{ .name = "XRAM_PRDY_DBG", .addr = A_XRAM_PRDY_DBG, + .reset = 0xffff, + .rsvd = 0xffff0000, + .ro = 0xffff, + },{ .name = "XRAM_SAFETY_CHK", .addr = A_XRAM_SAFETY_CHK, + } +}; + +static void xram_ctrl_reset_enter(Object *obj, ResetType type) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(obj); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } + + ARRAY_FIELD_DP32(s->regs, XRAM_IMP, SIZE, s->cfg.encoded_size); +} + +static void xram_ctrl_reset_hold(Object *obj) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(obj); + + xram_update_irq(s); +} + +static const MemoryRegionOps xram_ctrl_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void xram_ctrl_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + XlnxXramCtrl *s = XLNX_XRAM_CTRL(dev); + + switch (s->cfg.size) { + case 64 * KiB: + s->cfg.encoded_size = 0; + break; + case 128 * KiB: + s->cfg.encoded_size = 1; + break; + case 256 * KiB: + s->cfg.encoded_size = 2; + break; + case 512 * KiB: + s->cfg.encoded_size = 3; + break; + case 1 * MiB: + s->cfg.encoded_size = 4; + break; + default: + error_setg(errp, "Unsupported XRAM size %" PRId64, s->cfg.size); + return; + } + + memory_region_init_ram(&s->ram, OBJECT(s), + object_get_canonical_path_component(OBJECT(s)), + s->cfg.size, &error_fatal); + sysbus_init_mmio(sbd, &s->ram); +} + +static void xram_ctrl_init(Object *obj) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + s->reg_array = + register_init_block32(DEVICE(obj), xram_ctrl_regs_info, + ARRAY_SIZE(xram_ctrl_regs_info), + s->regs_info, s->regs, + &xram_ctrl_ops, + XLNX_XRAM_CTRL_ERR_DEBUG, + XRAM_CTRL_R_MAX * 4); + sysbus_init_mmio(sbd, &s->reg_array->mem); + sysbus_init_irq(sbd, &s->irq); +} + +static void xram_ctrl_finalize(Object *obj) +{ + XlnxXramCtrl *s = XLNX_XRAM_CTRL(obj); + register_finalize_block(s->reg_array); +} + +static const VMStateDescription vmstate_xram_ctrl = { + .name = TYPE_XLNX_XRAM_CTRL, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, XlnxXramCtrl, XRAM_CTRL_R_MAX), + VMSTATE_END_OF_LIST(), + } +}; + +static Property xram_ctrl_properties[] = { + DEFINE_PROP_UINT64("size", XlnxXramCtrl, cfg.size, 1 * MiB), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xram_ctrl_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = xram_ctrl_realize; + dc->vmsd = &vmstate_xram_ctrl; + device_class_set_props(dc, xram_ctrl_properties); + + rc->phases.enter = xram_ctrl_reset_enter; + rc->phases.hold = xram_ctrl_reset_hold; +} + +static const TypeInfo xram_ctrl_info = { + .name = TYPE_XLNX_XRAM_CTRL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxXramCtrl), + .class_init = xram_ctrl_class_init, + .instance_init = xram_ctrl_init, + .instance_finalize = xram_ctrl_finalize, +}; + +static void xram_ctrl_register_types(void) +{ + type_register_static(&xram_ctrl_info); +} + +type_init(xram_ctrl_register_types) 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 @@ softmmu_ss.add(when: 'CONFIG_RASPI', if_true: files( )) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c', 'zynq-xadc.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-xramc.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_SYSCFG', if_true: files('stm32f2xx_syscfg.c')) softmmu_ss.add(when: 'CONFIG_STM32F4XX_SYSCFG', if_true: files('stm32f4xx_syscfg.c')) softmmu_ss.add(when: 'CONFIG_STM32F4XX_EXTI', if_true: files('stm32f4xx_exti.c')) -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Connect the support for the Versal Accelerator RAMs (XRAMs). Reviewed-by: Luc Michel <luc@lmichel.fr> Acked-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210308224637.2949533-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/xlnx-versal-virt.rst | 1 + include/hw/arm/xlnx-versal.h | 13 ++++++++++ hw/arm/xlnx-versal.c | 36 ++++++++++++++++++++++++++++ 3 files changed, 50 insertions(+) diff --git a/docs/system/arm/xlnx-versal-virt.rst b/docs/system/arm/xlnx-versal-virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/xlnx-versal-virt.rst +++ b/docs/system/arm/xlnx-versal-virt.rst @@ -XXX,XX +XXX,XX @@ Implemented devices: - 8 ADMA (Xilinx zDMA) channels - 2 SD Controllers - OCM (256KB of On Chip Memory) +- XRAM (4MB of on chip Accelerator RAM) - DDR memory QEMU does not yet model any other devices, including the PL and the AI Engine. diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" +#include "hw/or-irq.h" #include "hw/sd/sdhci.h" #include "hw/intc/arm_gicv3.h" #include "hw/char/pl011.h" @@ -XXX,XX +XXX,XX @@ #include "hw/rtc/xlnx-zynqmp-rtc.h" #include "qom/object.h" #include "hw/usb/xlnx-usb-subsystem.h" +#include "hw/misc/xlnx-versal-xramc.h" #define TYPE_XLNX_VERSAL "xlnx-versal" OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) #define XLNX_VERSAL_NR_GEMS 2 #define XLNX_VERSAL_NR_ADMAS 8 #define XLNX_VERSAL_NR_SDS 2 +#define XLNX_VERSAL_NR_XRAM 4 #define XLNX_VERSAL_NR_IRQS 192 struct Versal { @@ -XXX,XX +XXX,XX @@ struct Versal { XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; VersalUsb2 usb; } iou; + + struct { + qemu_or_irq irq_orgate; + XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; + } xram; } lpd; /* The Platform Management Controller subsystem. */ @@ -XXX,XX +XXX,XX @@ struct Versal { #define VERSAL_GEM1_IRQ_0 58 #define VERSAL_GEM1_WAKE_IRQ_0 59 #define VERSAL_ADMA_IRQ_0 60 +#define VERSAL_XRAM_IRQ_0 79 #define VERSAL_RTC_APB_ERR_IRQ 121 #define VERSAL_SD0_IRQ_0 126 #define VERSAL_RTC_ALARM_IRQ 142 @@ -XXX,XX +XXX,XX @@ struct Versal { #define MM_OCM 0xfffc0000U #define MM_OCM_SIZE 0x40000 +#define MM_XRAM 0xfe800000 +#define MM_XRAMC 0xff8e0000 +#define MM_XRAMC_SIZE 0x10000 + #define MM_USB2_CTRL_REGS 0xFF9D0000 #define MM_USB2_CTRL_REGS_SIZE 0x10000 diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void versal_create_rtc(Versal *s, qemu_irq *pic) sysbus_connect_irq(sbd, 1, pic[VERSAL_RTC_APB_ERR_IRQ]); } +static void versal_create_xrams(Versal *s, qemu_irq *pic) +{ + int nr_xrams = ARRAY_SIZE(s->lpd.xram.ctrl); + DeviceState *orgate; + int i; + + /* XRAM IRQs get ORed into a single line. */ + object_initialize_child(OBJECT(s), "xram-irq-orgate", + &s->lpd.xram.irq_orgate, TYPE_OR_IRQ); + orgate = DEVICE(&s->lpd.xram.irq_orgate); + object_property_set_int(OBJECT(orgate), + "num-lines", nr_xrams, &error_fatal); + qdev_realize(orgate, NULL, &error_fatal); + qdev_connect_gpio_out(orgate, 0, pic[VERSAL_XRAM_IRQ_0]); + + for (i = 0; i < ARRAY_SIZE(s->lpd.xram.ctrl); i++) { + SysBusDevice *sbd; + MemoryRegion *mr; + + object_initialize_child(OBJECT(s), "xram[*]", &s->lpd.xram.ctrl[i], + TYPE_XLNX_XRAM_CTRL); + sbd = SYS_BUS_DEVICE(&s->lpd.xram.ctrl[i]); + sysbus_realize(sbd, &error_fatal); + + mr = sysbus_mmio_get_region(sbd, 0); + memory_region_add_subregion(&s->mr_ps, + MM_XRAMC + i * MM_XRAMC_SIZE, mr); + mr = sysbus_mmio_get_region(sbd, 1); + memory_region_add_subregion(&s->mr_ps, MM_XRAM + i * MiB, mr); + + sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(orgate, i)); + } +} + /* This takes the board allocated linear DDR memory and creates aliases * for each split DDR range/aperture on the Versal address map. */ @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_admas(s, pic); versal_create_sds(s, pic); versal_create_rtc(s, pic); + versal_create_xrams(s, pic); versal_map_ddr(s); versal_unimp(s); -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> With -Werror=maybe-uninitialized configuration we get ../hw/i386/intel_iommu.c: In function ‘vtd_context_device_invalidate’: ../hw/i386/intel_iommu.c:1888:10: error: ‘mask’ may be used uninitialized in this function [-Werror=maybe-uninitialized] 1888 | mask = ~mask; | ~~~~~^~~~~~~ Add a g_assert_not_reached() to avoid the error. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Xu <peterx@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210309102742.30442-2-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i386/intel_iommu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -XXX,XX +XXX,XX @@ static void vtd_context_device_invalidate(IntelIOMMUState *s, case 3: mask = 7; /* Mask bit 2:0 in the SID field */ break; + default: + g_assert_not_reached(); } mask = ~mask; -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Currently get_naturally_aligned_size() is used by the intel iommu to compute the maximum invalidation range based on @size which is a power of 2 while being aligned with the @start address and less than the maximum range defined by @gaw. This helper is also useful for other iommu devices (virtio-iommu, SMMUv3) to make sure IOMMU UNMAP notifiers only are called with power of 2 range sizes. Let's move this latter into dma-helpers.c and rename it into dma_aligned_pow2_mask(). Also rewrite the helper so that it accomodates UINT64_MAX values for the size mask and max mask. It now returns a mask instead of a size. Change the caller. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Xu <peterx@redhat.com> Message-id: 20210309102742.30442-3-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/dma.h | 12 ++++++++++++ hw/i386/intel_iommu.c | 30 +++++++----------------------- softmmu/dma-helpers.c | 26 ++++++++++++++++++++++++++ 3 files changed, 45 insertions(+), 23 deletions(-) diff --git a/include/sysemu/dma.h b/include/sysemu/dma.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/dma.h +++ b/include/sysemu/dma.h @@ -XXX,XX +XXX,XX @@ uint64_t dma_buf_write(uint8_t *ptr, int32_t len, QEMUSGList *sg); void dma_acct_start(BlockBackend *blk, BlockAcctCookie *cookie, QEMUSGList *sg, enum BlockAcctType type); +/** + * dma_aligned_pow2_mask: Return the address bit mask of the largest + * power of 2 size less or equal than @end - @start + 1, aligned with @start, + * and bounded by 1 << @max_addr_bits bits. + * + * @start: range start address + * @end: range end address (greater than @start) + * @max_addr_bits: max address bits (<= 64) + */ +uint64_t dma_aligned_pow2_mask(uint64_t start, uint64_t end, + int max_addr_bits); + #endif diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -XXX,XX +XXX,XX @@ #include "hw/i386/x86-iommu.h" #include "hw/pci-host/q35.h" #include "sysemu/kvm.h" +#include "sysemu/dma.h" #include "sysemu/sysemu.h" #include "hw/i386/apic_internal.h" #include "kvm/kvm_i386.h" @@ -XXX,XX +XXX,XX @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus, int devfn) return vtd_dev_as; } -static uint64_t get_naturally_aligned_size(uint64_t start, - uint64_t size, int gaw) -{ - uint64_t max_mask = 1ULL << gaw; - uint64_t alignment = start ? start & -start : max_mask; - - alignment = MIN(alignment, max_mask); - size = MIN(size, max_mask); - - if (alignment <= size) { - /* Increase the alignment of start */ - return alignment; - } else { - /* Find the largest page mask from size */ - return 1ULL << (63 - clz64(size)); - } -} - /* Unmap the whole range in the notifier's scope. */ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n) { @@ -XXX,XX +XXX,XX @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n) while (remain >= VTD_PAGE_SIZE) { IOMMUTLBEvent event; - uint64_t mask = get_naturally_aligned_size(start, remain, s->aw_bits); + uint64_t mask = dma_aligned_pow2_mask(start, end, s->aw_bits); + uint64_t size = mask + 1; - assert(mask); + assert(size); event.type = IOMMU_NOTIFIER_UNMAP; event.entry.iova = start; - event.entry.addr_mask = mask - 1; + event.entry.addr_mask = mask; event.entry.target_as = &address_space_memory; event.entry.perm = IOMMU_NONE; /* This field is meaningless for unmap */ @@ -XXX,XX +XXX,XX @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n) memory_region_notify_iommu_one(n, &event); - start += mask; - remain -= mask; + start += size; + remain -= size; } assert(!remain); diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/dma-helpers.c +++ b/softmmu/dma-helpers.c @@ -XXX,XX +XXX,XX @@ void dma_acct_start(BlockBackend *blk, BlockAcctCookie *cookie, { block_acct_start(blk_get_stats(blk), cookie, sg->size, type); } + +uint64_t dma_aligned_pow2_mask(uint64_t start, uint64_t end, int max_addr_bits) +{ + uint64_t max_mask = UINT64_MAX, addr_mask = end - start; + uint64_t alignment_mask, size_mask; + + if (max_addr_bits != 64) { + max_mask = (1ULL << max_addr_bits) - 1; + } + + alignment_mask = start ? (start & -start) - 1 : max_mask; + alignment_mask = MIN(alignment_mask, max_mask); + size_mask = MIN(addr_mask, max_mask); + + if (alignment_mask <= size_mask) { + /* Increase the alignment of start */ + return alignment_mask; + } else { + /* Find the largest page mask from size */ + if (addr_mask == UINT64_MAX) { + return UINT64_MAX; + } + return (1ULL << (63 - clz64(addr_mask + 1))) - 1; + } +} + -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Unmap notifiers work with an address mask assuming an invalidation range of a power of 2. Nothing mandates this in the VIRTIO-IOMMU spec. So in case the range is not a power of 2, split it into several invalidations. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Xu <peterx@redhat.com> Message-id: 20210309102742.30442-4-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/virtio/virtio-iommu.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -XXX,XX +XXX,XX @@ static void virtio_iommu_notify_unmap(IOMMUMemoryRegion *mr, hwaddr virt_start, hwaddr virt_end) { IOMMUTLBEvent event; + uint64_t delta = virt_end - virt_start; if (!(mr->iommu_notify_flags & IOMMU_NOTIFIER_UNMAP)) { return; @@ -XXX,XX +XXX,XX @@ static void virtio_iommu_notify_unmap(IOMMUMemoryRegion *mr, hwaddr virt_start, event.type = IOMMU_NOTIFIER_UNMAP; event.entry.target_as = &address_space_memory; - event.entry.addr_mask = virt_end - virt_start; - event.entry.iova = virt_start; event.entry.perm = IOMMU_NONE; event.entry.translated_addr = 0; + event.entry.addr_mask = delta; + event.entry.iova = virt_start; - memory_region_notify_iommu(mr, 0, event); + if (delta == UINT64_MAX) { + memory_region_notify_iommu(mr, 0, event); + } + + + while (virt_start != virt_end + 1) { + uint64_t mask = dma_aligned_pow2_mask(virt_start, virt_end, 64); + + event.entry.addr_mask = mask; + event.entry.iova = virt_start; + memory_region_notify_iommu(mr, 0, event); + virt_start += mask + 1; + } } static gboolean virtio_iommu_notify_unmap_cb(gpointer key, gpointer value, -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> If the asid is not set, do not attempt to locate the key directly as all inserted keys have a valid asid. Use g_hash_table_foreach_remove instead. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20210309102742.30442-5-eric.auger@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmu-common.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ inline void smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova, uint8_t tg, uint64_t num_pages, uint8_t ttl) { - if (ttl && (num_pages == 1)) { + if (ttl && (num_pages == 1) && (asid >= 0)) { SMMUIOTLBKey key = smmu_get_iotlb_key(asid, iova, tg, ttl); g_hash_table_remove(s->iotlb, &key); -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> As of today, the driver can invalidate a number of pages that is not a power of 2. However IOTLB unmap notifications and internal IOTLB invalidations work with masks leading to erroneous invalidations. In case the range is not a power of 2, split invalidations into power of 2 invalidations. When looking for a single page entry in the vSMMU internal IOTLB, let's make sure that if the entry is not found using a g_hash_table_remove() we iterate over all the entries to find a potential range that overlaps it. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20210309102742.30442-6-eric.auger@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmu-common.c | 30 ++++++++++++++++++------------ hw/arm/smmuv3.c | 24 ++++++++++++++++++++---- 2 files changed, 38 insertions(+), 16 deletions(-) diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ inline void smmu_iotlb_inv_iova(SMMUState *s, int asid, dma_addr_t iova, uint8_t tg, uint64_t num_pages, uint8_t ttl) { + /* if tg is not set we use 4KB range invalidation */ + uint8_t granule = tg ? tg * 2 + 10 : 12; + if (ttl && (num_pages == 1) && (asid >= 0)) { SMMUIOTLBKey key = smmu_get_iotlb_key(asid, iova, tg, ttl); - g_hash_table_remove(s->iotlb, &key); - } else { - /* if tg is not set we use 4KB range invalidation */ - uint8_t granule = tg ? tg * 2 + 10 : 12; - - SMMUIOTLBPageInvInfo info = { - .asid = asid, .iova = iova, - .mask = (num_pages * 1 << granule) - 1}; - - g_hash_table_foreach_remove(s->iotlb, - smmu_hash_remove_by_asid_iova, - &info); + if (g_hash_table_remove(s->iotlb, &key)) { + return; + } + /* + * if the entry is not found, let's see if it does not + * belong to a larger IOTLB entry + */ } + + SMMUIOTLBPageInvInfo info = { + .asid = asid, .iova = iova, + .mask = (num_pages * 1 << granule) - 1}; + + g_hash_table_foreach_remove(s->iotlb, + smmu_hash_remove_by_asid_iova, + &info); } inline void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid) diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) uint16_t vmid = CMD_VMID(cmd); bool leaf = CMD_LEAF(cmd); uint8_t tg = CMD_TG(cmd); - hwaddr num_pages = 1; + uint64_t first_page = 0, last_page; + uint64_t num_pages = 1; int asid = -1; if (tg) { @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) if (type == SMMU_CMD_TLBI_NH_VA) { asid = CMD_ASID(cmd); } - trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, num_pages, ttl, leaf); - smmuv3_inv_notifiers_iova(s, asid, addr, tg, num_pages); - smmu_iotlb_inv_iova(s, asid, addr, tg, num_pages, ttl); + + /* Split invalidations into ^2 range invalidations */ + last_page = num_pages - 1; + while (num_pages) { + uint8_t granule = tg * 2 + 10; + uint64_t mask, count; + + mask = dma_aligned_pow2_mask(first_page, last_page, 64 - granule); + count = mask + 1; + + trace_smmuv3_s1_range_inval(vmid, asid, addr, tg, count, ttl, leaf); + smmuv3_inv_notifiers_iova(s, asid, addr, tg, count); + smmu_iotlb_inv_iova(s, asid, addr, tg, count, ttl); + + num_pages -= count; + first_page += count; + addr += count * BIT_ULL(granule); + } } static int smmuv3_cmdq_consume(SMMUv3State *s) -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> If the whole SID range (32b) is invalidated (SMMU_CMD_CFGI_ALL), @end overflows and we fail to handle the command properly. Once this gets fixed, the current code really is awkward in the sense it loops over the whole range instead of removing the currently cached configs through a hash table lookup. Fix both the overflow and the lookup. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210309102742.30442-7-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmu-internal.h | 5 +++++ hw/arm/smmuv3.c | 34 ++++++++++++++++++++-------------- 2 files changed, 25 insertions(+), 14 deletions(-) diff --git a/hw/arm/smmu-internal.h b/hw/arm/smmu-internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-internal.h +++ b/hw/arm/smmu-internal.h @@ -XXX,XX +XXX,XX @@ typedef struct SMMUIOTLBPageInvInfo { uint64_t mask; } SMMUIOTLBPageInvInfo; +typedef struct SMMUSIDRange { + uint32_t start; + uint32_t end; +} SMMUSIDRange; + #endif diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/smmuv3.h" #include "smmuv3-internal.h" +#include "smmu-internal.h" /** * smmuv3_trigger_irq - pulse @irq if enabled and update @@ -XXX,XX +XXX,XX @@ static void smmuv3_s1_range_inval(SMMUState *s, Cmd *cmd) } } +static gboolean +smmuv3_invalidate_ste(gpointer key, gpointer value, gpointer user_data) +{ + SMMUDevice *sdev = (SMMUDevice *)key; + uint32_t sid = smmu_get_sid(sdev); + SMMUSIDRange *sid_range = (SMMUSIDRange *)user_data; + + if (sid < sid_range->start || sid > sid_range->end) { + return false; + } + trace_smmuv3_config_cache_inv(sid); + return true; +} + static int smmuv3_cmdq_consume(SMMUv3State *s) { SMMUState *bs = ARM_SMMU(s); @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) } case SMMU_CMD_CFGI_STE_RANGE: /* same as SMMU_CMD_CFGI_ALL */ { - uint32_t start = CMD_SID(&cmd), end, i; + uint32_t start = CMD_SID(&cmd); uint8_t range = CMD_STE_RANGE(&cmd); + uint64_t end = start + (1ULL << (range + 1)) - 1; + SMMUSIDRange sid_range = {start, end}; if (CMD_SSEC(&cmd)) { cmd_error = SMMU_CERROR_ILL; break; } - - end = start + (1 << (range + 1)) - 1; trace_smmuv3_cmdq_cfgi_ste_range(start, end); - - for (i = start; i <= end; i++) { - IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, i); - SMMUDevice *sdev; - - if (!mr) { - continue; - } - sdev = container_of(mr, SMMUDevice, iommu); - smmuv3_flush_config(sdev); - } + g_hash_table_foreach_remove(bs->configs, smmuv3_invalidate_ste, + &sid_range); break; } case SMMU_CMD_CFGI_CD: -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Convert all sid printouts to sid=0x%x. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210309102742.30442-8-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/trace-events | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/hw/arm/trace-events b/hw/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_opcode(const char *opcode) "<--- %s" smmuv3_cmdq_consume_out(uint32_t prod, uint32_t cons, uint8_t prod_wrap, uint8_t cons_wrap) "prod:%d, cons:%d, prod_wrap:%d, cons_wrap:%d " smmuv3_cmdq_consume_error(const char *cmd_name, uint8_t cmd_error) "Error on %s command execution: %d" smmuv3_write_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" -smmuv3_record_event(const char *type, uint32_t sid) "%s sid=%d" -smmuv3_find_ste(uint16_t sid, uint32_t features, uint16_t sid_split) "SID:0x%x features:0x%x, sid_split:0x%x" +smmuv3_record_event(const char *type, uint32_t sid) "%s sid=0x%x" +smmuv3_find_ste(uint16_t sid, uint32_t features, uint16_t sid_split) "sid=0x%x features:0x%x, sid_split:0x%x" smmuv3_find_ste_2lvl(uint64_t strtab_base, uint64_t l1ptr, int l1_ste_offset, uint64_t l2ptr, int l2_ste_offset, int max_l2_ste) "strtab_base:0x%"PRIx64" l1ptr:0x%"PRIx64" l1_off:0x%x, l2ptr:0x%"PRIx64" l2_off:0x%x max_l2_ste:%d" smmuv3_get_ste(uint64_t addr) "STE addr: 0x%"PRIx64 -smmuv3_translate_disable(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d bypass (smmu disabled) iova:0x%"PRIx64" is_write=%d" -smmuv3_translate_bypass(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d STE bypass iova:0x%"PRIx64" is_write=%d" -smmuv3_translate_abort(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d abort on iova:0x%"PRIx64" is_write=%d" -smmuv3_translate_success(const char *n, uint16_t sid, uint64_t iova, uint64_t translated, int perm) "%s sid=%d iova=0x%"PRIx64" translated=0x%"PRIx64" perm=0x%x" +smmuv3_translate_disable(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=0x%x bypass (smmu disabled) iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_bypass(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=0x%x STE bypass iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_abort(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=0x%x abort on iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_success(const char *n, uint16_t sid, uint64_t iova, uint64_t translated, int perm) "%s sid=0x%x iova=0x%"PRIx64" translated=0x%"PRIx64" perm=0x%x" smmuv3_get_cd(uint64_t addr) "CD addr: 0x%"PRIx64 smmuv3_decode_cd(uint32_t oas) "oas=%d" smmuv3_decode_cd_tt(int i, uint32_t tsz, uint64_t ttb, uint32_t granule_sz, bool had) "TT[%d]:tsz:%d ttb:0x%"PRIx64" granule_sz:%d had:%d" -smmuv3_cmdq_cfgi_ste(int streamid) "streamid =%d" +smmuv3_cmdq_cfgi_ste(int streamid) "streamid= 0x%x" smmuv3_cmdq_cfgi_ste_range(int start, int end) "start=0x%x - end=0x%x" -smmuv3_cmdq_cfgi_cd(uint32_t sid) "streamid = %d" -smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid %d (hits=%d, misses=%d, hit rate=%d)" -smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid %d (hits=%d, misses=%d, hit rate=%d)" -smmuv3_s1_range_inval(int vmid, int asid, uint64_t addr, uint8_t tg, uint64_t num_pages, uint8_t ttl, bool leaf) "vmid =%d asid =%d addr=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64" ttl=%d leaf=%d" +smmuv3_cmdq_cfgi_cd(uint32_t sid) "sid=0x%x" +smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid=0x%x (hits=%d, misses=%d, hit rate=%d)" +smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid=0x%x (hits=%d, misses=%d, hit rate=%d)" +smmuv3_s1_range_inval(int vmid, int asid, uint64_t addr, uint8_t tg, uint64_t num_pages, uint8_t ttl, bool leaf) "vmid=%d asid=%d addr=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64" ttl=%d leaf=%d" smmuv3_cmdq_tlbi_nh(void) "" smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d" -smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid %d" +smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid=0x%x" smmuv3_notify_flag_add(const char *iommu) "ADD SMMUNotifier node for iommu mr=%s" smmuv3_notify_flag_del(const char *iommu) "DEL SMMUNotifier node for iommu mr=%s" smmuv3_inv_notifiers_iova(const char *name, uint16_t asid, uint64_t iova, uint8_t tg, uint64_t num_pages) "iommu mr=%s asid=%d iova=0x%"PRIx64" tg=%d num_pages=0x%"PRIx64 -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Missed out on compressing the second half of a predicate with length vl % 512 > 256. Adjust all of the x + (y << s) to x | (y << s) as a general style fix. Drop the extract64 because the input uint64_t are known to be already zero-extended from the current size of the predicate. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 30 +++++++++++++++++++++--------- 1 file changed, 21 insertions(+), 9 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 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) if (oprsz <= 8) { l = compress_bits(n[0] >> odd, esz); h = compress_bits(m[0] >> odd, esz); - d[0] = extract64(l + (h << (4 * oprsz)), 0, 8 * oprsz); + d[0] = l | (h << (4 * oprsz)); } else { ARMPredicateReg tmp_m; intptr_t oprsz_16 = oprsz / 16; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) h = n[2 * i + 1]; l = compress_bits(l >> odd, esz); h = compress_bits(h >> odd, esz); - d[i] = l + (h << 32); + d[i] = l | (h << 32); } - /* For VL which is not a power of 2, the results from M do not - align nicely with the uint64_t for D. Put the aligned results - from M into TMP_M and then copy it into place afterward. */ + /* + * For VL which is not a multiple of 512, the results from M do not + * align nicely with the uint64_t for D. Put the aligned results + * from M into TMP_M and then copy it into place afterward. + */ if (oprsz & 15) { - d[i] = compress_bits(n[2 * i] >> odd, esz); + int final_shift = (oprsz & 15) * 2; + + l = n[2 * i + 0]; + h = n[2 * i + 1]; + l = compress_bits(l >> odd, esz); + h = compress_bits(h >> odd, esz); + d[i] = l | (h << final_shift); for (i = 0; i < oprsz_16; i++) { l = m[2 * i + 0]; h = m[2 * i + 1]; l = compress_bits(l >> odd, esz); h = compress_bits(h >> odd, esz); - tmp_m.p[i] = l + (h << 32); + tmp_m.p[i] = l | (h << 32); } - tmp_m.p[i] = compress_bits(m[2 * i] >> odd, esz); + l = m[2 * i + 0]; + h = m[2 * i + 1]; + l = compress_bits(l >> odd, esz); + h = compress_bits(h >> odd, esz); + tmp_m.p[i] = l | (h << final_shift); swap_memmove(vd + oprsz / 2, &tmp_m, oprsz / 2); } else { @@ -XXX,XX +XXX,XX @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) h = m[2 * i + 1]; l = compress_bits(l >> odd, esz); h = compress_bits(h >> odd, esz); - d[oprsz_16 + i] = l + (h << 32); + d[oprsz_16 + i] = l | (h << 32); } } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Wrote too much with low-half zip (zip1) with vl % 512 != 0. Adjust all of the x + (y << s) to x | (y << s) as a style fix. We only ever have exact overlap between D, M, and N. Therefore we only need a single temporary, and we do not need to check for partial overlap. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 25 ++++++++++++++----------- 1 file changed, 14 insertions(+), 11 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 @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); int esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); intptr_t high = FIELD_EX32(pred_desc, PREDDESC, DATA); + int esize = 1 << esz; uint64_t *d = vd; intptr_t i; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) mm = extract64(mm, high * half, half); nn = expand_bits(nn, esz); mm = expand_bits(mm, esz); - d[0] = nn + (mm << (1 << esz)); + d[0] = nn | (mm << esize); } else { - ARMPredicateReg tmp_n, tmp_m; + ARMPredicateReg tmp; /* We produce output faster than we consume input. Therefore we must be mindful of possible overlap. */ - if ((vn - vd) < (uintptr_t)oprsz) { - vn = memcpy(&tmp_n, vn, oprsz); - } - if ((vm - vd) < (uintptr_t)oprsz) { - vm = memcpy(&tmp_m, vm, oprsz); + if (vd == vn) { + vn = memcpy(&tmp, vn, oprsz); + if (vd == vm) { + vm = vn; + } + } else if (vd == vm) { + vm = memcpy(&tmp, vm, oprsz); } if (high) { high = oprsz >> 1; } - if ((high & 3) == 0) { + if ((oprsz & 7) == 0) { uint32_t *n = vn, *m = vm; high >>= 2; - for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) { + for (i = 0; i < oprsz / 8; i++) { uint64_t nn = n[H4(high + i)]; uint64_t mm = m[H4(high + i)]; nn = expand_bits(nn, esz); mm = expand_bits(mm, esz); - d[i] = nn + (mm << (1 << esz)); + d[i] = nn | (mm << esize); } } else { uint8_t *n = vn, *m = vm; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc) nn = expand_bits(nn, esz); mm = expand_bits(mm, esz); - d16[H2(i)] = nn + (mm << (1 << esz)); + d16[H2(i)] = nn | (mm << esize); } } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Wrote too much with punpk1 with vl % 512 != 0. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 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 @@ void HELPER(sve_punpk_p)(void *vd, void *vn, uint32_t pred_desc) high = oprsz >> 1; } - if ((high & 3) == 0) { + if ((oprsz & 7) == 0) { uint32_t *n = vn; high >>= 2; - for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) { + for (i = 0; i < oprsz / 8; i++) { uint64_t nn = n[H4(high + i)]; d[i] = expand_bits(nn, 0); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Since b64ee454a4a0, all predicate operations should be using these field macros for predicates. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 6 +++--- target/arm/translate-sve.c | 7 +++---- 2 files changed, 6 insertions(+), 7 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 @@ void HELPER(sve_compact_d)(void *vd, void *vn, void *vg, uint32_t desc) */ int32_t HELPER(sve_last_active_element)(void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; - intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + intptr_t words = DIV_ROUND_UP(FIELD_EX32(pred_desc, PREDDESC, OPRSZ), 8); + intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); - return last_active_element(vg, DIV_ROUND_UP(oprsz, 8), esz); + return last_active_element(vg, words, esz); } void HELPER(sve_splice)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void find_last_active(DisasContext *s, TCGv_i32 ret, int esz, int pg) */ TCGv_ptr t_p = tcg_temp_new_ptr(); TCGv_i32 t_desc; - unsigned vsz = pred_full_reg_size(s); - unsigned desc; + unsigned desc = 0; - desc = vsz - 2; - desc = deposit32(desc, SIMD_DATA_SHIFT, 2, esz); + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, pred_full_reg_size(s)); + desc = FIELD_DP32(desc, PREDDESC, ESZ, esz); tcg_gen_addi_ptr(t_p, cpu_env, pred_full_reg_offset(s, pg)); t_desc = tcg_const_i32(desc); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Since b64ee454a4a0, all predicate operations should be using these field macros for predicates. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 30 ++++++++++++++---------------- target/arm/translate-sve.c | 4 ++-- 2 files changed, 16 insertions(+), 18 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 @@ static uint32_t do_zero(ARMPredicateReg *d, intptr_t oprsz) void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, true); } else { @@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpa)(void *vd, void *vn, void *vm, void *vg, uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, true); } else { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpas)(void *vd, void *vn, void *vm, void *vg, void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { compute_brk_z(vd, vm, vg, oprsz, false); } else { @@ -XXX,XX +XXX,XX @@ void HELPER(sve_brkpb)(void *vd, void *vn, void *vm, void *vg, uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { return compute_brks_z(vd, vm, vg, oprsz, false); } else { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_brkpbs)(void *vd, void *vn, void *vm, void *vg, void HELPER(sve_brka_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); compute_brk_z(vd, vn, vg, oprsz, true); } uint32_t HELPER(sve_brkas_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); return compute_brks_z(vd, vn, vg, oprsz, true); } void HELPER(sve_brkb_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); compute_brk_z(vd, vn, vg, oprsz, false); } uint32_t HELPER(sve_brkbs_z)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); return compute_brks_z(vd, vn, vg, oprsz, false); } void HELPER(sve_brka_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); compute_brk_m(vd, vn, vg, oprsz, true); } uint32_t HELPER(sve_brkas_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); return compute_brks_m(vd, vn, vg, oprsz, true); } void HELPER(sve_brkb_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); compute_brk_m(vd, vn, vg, oprsz, false); } uint32_t HELPER(sve_brkbs_m)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); return compute_brks_m(vd, vn, vg, oprsz, false); } void HELPER(sve_brkn)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; - + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (!last_active_pred(vn, vg, oprsz)) { do_zero(vd, oprsz); } @@ -XXX,XX +XXX,XX @@ static uint32_t predtest_ones(ARMPredicateReg *d, intptr_t oprsz, uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; - + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); if (last_active_pred(vn, vg, oprsz)) { return predtest_ones(vd, oprsz, -1); } else { diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_brk3(DisasContext *s, arg_rprr_s *a, TCGv_ptr n = tcg_temp_new_ptr(); TCGv_ptr m = tcg_temp_new_ptr(); TCGv_ptr g = tcg_temp_new_ptr(); - TCGv_i32 t = tcg_const_i32(vsz - 2); + TCGv_i32 t = tcg_const_i32(FIELD_DP32(0, PREDDESC, OPRSZ, vsz)); tcg_gen_addi_ptr(d, cpu_env, pred_full_reg_offset(s, a->rd)); tcg_gen_addi_ptr(n, cpu_env, pred_full_reg_offset(s, a->rn)); @@ -XXX,XX +XXX,XX @@ static bool do_brk2(DisasContext *s, arg_rpr_s *a, TCGv_ptr d = tcg_temp_new_ptr(); TCGv_ptr n = tcg_temp_new_ptr(); TCGv_ptr g = tcg_temp_new_ptr(); - TCGv_i32 t = tcg_const_i32(vsz - 2); + TCGv_i32 t = tcg_const_i32(FIELD_DP32(0, PREDDESC, OPRSZ, vsz)); tcg_gen_addi_ptr(d, cpu_env, pred_full_reg_offset(s, a->rd)); tcg_gen_addi_ptr(n, cpu_env, pred_full_reg_offset(s, a->rn)); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Since b64ee454a4a0, all predicate operations should be using these field macros for predicates. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 6 +++--- target/arm/translate-sve.c | 6 +++--- 2 files changed, 6 insertions(+), 6 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 @@ uint32_t HELPER(sve_brkns)(void *vd, void *vn, void *vg, uint32_t pred_desc) uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) { - intptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; - intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + intptr_t words = DIV_ROUND_UP(FIELD_EX32(pred_desc, PREDDESC, OPRSZ), 8); + intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); uint64_t *n = vn, *g = vg, sum = 0, mask = pred_esz_masks[esz]; intptr_t i; - for (i = 0; i < DIV_ROUND_UP(oprsz, 8); ++i) { + for (i = 0; i < words; ++i) { uint64_t t = n[i] & g[i] & mask; sum += ctpop64(t); } diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_cntp(DisasContext *s, TCGv_i64 val, int esz, int pn, int pg) } else { TCGv_ptr t_pn = tcg_temp_new_ptr(); TCGv_ptr t_pg = tcg_temp_new_ptr(); - unsigned desc; + unsigned desc = 0; TCGv_i32 t_desc; - desc = psz - 2; - desc = deposit32(desc, SIMD_DATA_SHIFT, 2, esz); + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, psz); + desc = FIELD_DP32(desc, PREDDESC, ESZ, esz); tcg_gen_addi_ptr(t_pn, cpu_env, pred_full_reg_offset(s, pn)); tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Since b64ee454a4a0, all predicate operations should be using these field macros for predicates. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 4 ++-- target/arm/translate-sve.c | 7 ++++--- 2 files changed, 6 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 @@ uint64_t HELPER(sve_cntp)(void *vn, void *vg, uint32_t pred_desc) uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) { - uintptr_t oprsz = extract32(pred_desc, 0, SIMD_OPRSZ_BITS) + 2; - intptr_t esz = extract32(pred_desc, SIMD_DATA_SHIFT, 2); + intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ); + intptr_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ); uint64_t esz_mask = pred_esz_masks[esz]; ARMPredicateReg *d = vd; uint32_t flags; diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) TCGv_i64 op0, op1, t0, t1, tmax; TCGv_i32 t2, t3; TCGv_ptr ptr; - unsigned desc, vsz = vec_full_reg_size(s); + unsigned vsz = vec_full_reg_size(s); + unsigned desc = 0; TCGCond cond; if (!sve_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a) /* Scale elements to bits. */ tcg_gen_shli_i32(t2, t2, a->esz); - desc = (vsz / 8) - 2; - desc = deposit32(desc, SIMD_DATA_SHIFT, 2, a->esz); + desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8); + desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz); t3 = tcg_const_i32(desc); ptr = tcg_temp_new_ptr(); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> With the reduction operations, we intentionally increase maxsz to the next power of 2, so as to fill out the reduction tree correctly. Since e2e7168a214b, oprsz must equal maxsz, with exceptions for small vectors, so this triggers an assertion for vector sizes > 32 that are not themselves a power of 2. Pass the power-of-two value in the simd_data field instead. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210309155305.11301-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 2 +- target/arm/translate-sve.c | 2 +- 2 files changed, 2 insertions(+), 2 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 @@ static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \ } \ uint64_t HELPER(NAME)(void *vn, void *vg, void *vs, uint32_t desc) \ { \ - uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_maxsz(desc); \ + uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ for (i = 0; i < oprsz; ) { \ uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_reduce(DisasContext *s, arg_rpr_esz *a, { unsigned vsz = vec_full_reg_size(s); unsigned p2vsz = pow2ceil(vsz); - TCGv_i32 t_desc = tcg_const_i32(simd_desc(vsz, p2vsz, 0)); + TCGv_i32 t_desc = tcg_const_i32(simd_desc(vsz, vsz, p2vsz)); TCGv_ptr t_zn, t_pg, status; TCGv_i64 temp; -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Currently the emulated EMAC for sun8i always traverses the transmit queue from the head when transferring packets. It searches for a list of consecutive descriptors whichs are flagged as ready for processing and transmits their payloads accordingly. The controller stops processing once it finds a descriptor that is not marked ready. While the above behaviour works in most situations, it is not the same as the actual EMAC in hardware. Actual hardware uses the TX_CUR_DESC register value to keep track of the last position in the transmit queue and continues processing from that position when software triggers the start of DMA processing. The currently emulated behaviour can lead to packet loss on transmit when software fills the transmit queue with ready descriptors that overlap the tail of the circular list. This commit modifies the emulated EMAC for sun8i such that it processes the transmit queue using the TX_CUR_DESC register in the same way as hardware. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210310195820.21950-2-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/allwinner-sun8i-emac.c | 62 +++++++++++++++++++---------------- 1 file changed, 34 insertions(+), 28 deletions(-) diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/allwinner-sun8i-emac.c +++ b/hw/net/allwinner-sun8i-emac.c @@ -XXX,XX +XXX,XX @@ static void allwinner_sun8i_emac_update_irq(AwSun8iEmacState *s) qemu_set_irq(s->irq, (s->int_sta & s->int_en) != 0); } -static uint32_t allwinner_sun8i_emac_next_desc(AwSun8iEmacState *s, - FrameDescriptor *desc, - size_t min_size) +static bool allwinner_sun8i_emac_desc_owned(FrameDescriptor *desc, + size_t min_buf_size) { - uint32_t paddr = desc->next; - - dma_memory_read(&s->dma_as, paddr, desc, sizeof(*desc)); - - if ((desc->status & DESC_STATUS_CTL) && - (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { - return paddr; - } else { - return 0; - } + return (desc->status & DESC_STATUS_CTL) && (min_buf_size == 0 || + (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_buf_size); } -static uint32_t allwinner_sun8i_emac_get_desc(AwSun8iEmacState *s, - FrameDescriptor *desc, - uint32_t start_addr, - size_t min_size) +static void allwinner_sun8i_emac_get_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + uint32_t phys_addr) +{ + dma_memory_read(&s->dma_as, phys_addr, desc, sizeof(*desc)); +} + +static uint32_t allwinner_sun8i_emac_next_desc(AwSun8iEmacState *s, + FrameDescriptor *desc) +{ + const uint32_t nxt = desc->next; + allwinner_sun8i_emac_get_desc(s, desc, nxt); + return nxt; +} + +static uint32_t allwinner_sun8i_emac_find_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + uint32_t start_addr, + size_t min_size) { uint32_t desc_addr = start_addr; /* Note that the list is a cycle. Last entry points back to the head. */ while (desc_addr != 0) { - dma_memory_read(&s->dma_as, desc_addr, desc, sizeof(*desc)); + allwinner_sun8i_emac_get_desc(s, desc, desc_addr); - if ((desc->status & DESC_STATUS_CTL) && - (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { + if (allwinner_sun8i_emac_desc_owned(desc, min_size)) { return desc_addr; } else if (desc->next == start_addr) { break; @@ -XXX,XX +XXX,XX @@ static uint32_t allwinner_sun8i_emac_rx_desc(AwSun8iEmacState *s, FrameDescriptor *desc, size_t min_size) { - return allwinner_sun8i_emac_get_desc(s, desc, s->rx_desc_curr, min_size); + return allwinner_sun8i_emac_find_desc(s, desc, s->rx_desc_curr, min_size); } static uint32_t allwinner_sun8i_emac_tx_desc(AwSun8iEmacState *s, - FrameDescriptor *desc, - size_t min_size) + FrameDescriptor *desc) { - return allwinner_sun8i_emac_get_desc(s, desc, s->tx_desc_head, min_size); + allwinner_sun8i_emac_get_desc(s, desc, s->tx_desc_curr); + return s->tx_desc_curr; } static void allwinner_sun8i_emac_flush_desc(AwSun8iEmacState *s, @@ -XXX,XX +XXX,XX @@ static ssize_t allwinner_sun8i_emac_receive(NetClientState *nc, bytes_left -= desc_bytes; /* Move to the next descriptor */ - s->rx_desc_curr = allwinner_sun8i_emac_next_desc(s, &desc, 64); + s->rx_desc_curr = allwinner_sun8i_emac_find_desc(s, &desc, desc.next, + AW_SUN8I_EMAC_MIN_PKT_SZ); if (!s->rx_desc_curr) { /* Not enough buffer space available */ s->int_sta |= INT_STA_RX_BUF_UA; @@ -XXX,XX +XXX,XX @@ static void allwinner_sun8i_emac_transmit(AwSun8iEmacState *s) size_t transmitted = 0; static uint8_t packet_buf[2048]; - s->tx_desc_curr = allwinner_sun8i_emac_tx_desc(s, &desc, 0); + s->tx_desc_curr = allwinner_sun8i_emac_tx_desc(s, &desc); /* Read all transmit descriptors */ - while (s->tx_desc_curr != 0) { + while (allwinner_sun8i_emac_desc_owned(&desc, 0)) { /* Read from physical memory into packet buffer */ bytes = desc.status2 & DESC_STATUS2_BUF_SIZE_MASK; @@ -XXX,XX +XXX,XX @@ static void allwinner_sun8i_emac_transmit(AwSun8iEmacState *s) packet_bytes = 0; transmitted++; } - s->tx_desc_curr = allwinner_sun8i_emac_next_desc(s, &desc, 0); + s->tx_desc_curr = allwinner_sun8i_emac_next_desc(s, &desc); } /* Raise transmit completed interrupt */ -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The image for Armbian 19.11.3 bionic has been removed from the armbian server. Without the image as input the test arm_orangepi_bionic_19_11 cannot run. This commit removes the test completely and merges the code of the generic function do_test_arm_orangepi_uboot_armbian back with the 20.08 test. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-id: 20210310195820.21950-3-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 72 ++++++++------------------ 1 file changed, 23 insertions(+), 49 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_sd(self): # Wait for VM to shut down gracefully self.vm.wait() - def do_test_arm_orangepi_uboot_armbian(self, image_path): + @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), + 'Test artifacts fetched from unreliable apt.armbian.com') + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_orangepi_bionic_20_08(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + :avocado: tags=device:sd + """ + + # This test download a 275 MiB compressed image and expand it + # to 1036 MiB, but the underlying filesystem is 1552 MiB... + # As we expand it to 2 GiB we are safe. + + image_url = ('https://dl.armbian.com/orangepipc/archive/' + 'Armbian_20.08.1_Orangepipc_bionic_current_5.8.5.img.xz') + image_hash = ('b4d6775f5673486329e45a0586bf06b6' + 'dbe792199fd182ac6b9c7bb6c7d3e6dd') + image_path_xz = self.fetch_asset(image_url, asset_hash=image_hash, + algorithm='sha256') + image_path = archive.extract(image_path_xz, 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', @@ -XXX,XX +XXX,XX @@ def do_test_arm_orangepi_uboot_armbian(self, image_path): 'to <orangepipc>') self.wait_for_console_pattern('Starting Load Kernel Modules...') - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') - @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') - @skipUnless(P7ZIP_AVAILABLE, '7z not installed') - def test_arm_orangepi_bionic_19_11(self): - """ - :avocado: tags=arch:arm - :avocado: tags=machine:orangepi-pc - :avocado: tags=device:sd - """ - - # This test download a 196MB compressed image and expand it to 1GB - image_url = ('https://dl.armbian.com/orangepipc/archive/' - 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.7z') - image_hash = '196a8ffb72b0123d92cea4a070894813d305c71e' - image_path_7z = self.fetch_asset(image_url, asset_hash=image_hash) - image_name = 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.img' - image_path = os.path.join(self.workdir, image_name) - process.run("7z e -o%s %s" % (self.workdir, image_path_7z)) - image_pow2ceil_expand(image_path) - - self.do_test_arm_orangepi_uboot_armbian(image_path) - - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') - @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') - def test_arm_orangepi_bionic_20_08(self): - """ - :avocado: tags=arch:arm - :avocado: tags=machine:orangepi-pc - :avocado: tags=device:sd - """ - - # This test download a 275 MiB compressed image and expand it - # to 1036 MiB, but the underlying filesystem is 1552 MiB... - # As we expand it to 2 GiB we are safe. - - image_url = ('https://dl.armbian.com/orangepipc/archive/' - 'Armbian_20.08.1_Orangepipc_bionic_current_5.8.5.img.xz') - image_hash = ('b4d6775f5673486329e45a0586bf06b6' - 'dbe792199fd182ac6b9c7bb6c7d3e6dd') - image_path_xz = self.fetch_asset(image_url, asset_hash=image_hash, - algorithm='sha256') - image_path = archive.extract(image_path_xz, self.workdir) - image_pow2ceil_expand(image_path) - - self.do_test_arm_orangepi_uboot_armbian(image_path) - @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') def test_arm_orangepi_uboot_netbsd9(self): """ -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Update the download URL of the Armbian 20.08 Bionic image for test_arm_orangepi_bionic_20_08 of the orangepi-pc machine. The archive.armbian.com URL contains more images and should keep stable for a longer period of time than dl.armbian.com. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-id: 20210310195820.21950-4-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_bionic_20_08(self): # to 1036 MiB, but the underlying filesystem is 1552 MiB... # As we expand it to 2 GiB we are safe. - image_url = ('https://dl.armbian.com/orangepipc/archive/' + image_url = ('https://archive.armbian.com/orangepipc/archive/' 'Armbian_20.08.1_Orangepipc_bionic_current_5.8.5.img.xz') image_hash = ('b4d6775f5673486329e45a0586bf06b6' 'dbe792199fd182ac6b9c7bb6c7d3e6dd') -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The linux kernel 4.20.7 binary for sunxi has been removed from apt.armbian.com: $ ARMBIAN_ARTIFACTS_CACHED=yes AVOCADO_ALLOW_LARGE_STORAGE=yes avocado --show=app,console run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py Fetching asset from tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_orangepi ... (1/6) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_orangepi: CANCEL: Missing asset https://apt.armbian.com/pool/main/l/linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb (0.55 s) This commit updates the sunxi kernel to 5.10.16 for the acceptance tests of the orangepi-pc and cubieboard machines. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-id: 20210310195820.21950-5-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 40 +++++++++++++------------- tests/acceptance/replay_kernel.py | 8 +++--- 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_initrd(self): :avocado: tags=machine:cubieboard """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_sata(self): :avocado: tags=machine:cubieboard """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) rootfs_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi(self): :avocado: tags=machine:orangepi-pc """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) self.vm.set_console() @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_initrd(self): :avocado: tags=machine:orangepi-pc """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_sd(self): :avocado: tags=device:sd """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun8i-h3-orangepi-pc.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' 'kci-2019.02/armel/base/rootfs.ext2.xz') diff --git a/tests/acceptance/replay_kernel.py b/tests/acceptance/replay_kernel.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/replay_kernel.py +++ b/tests/acceptance/replay_kernel.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_initrd(self): :avocado: tags=machine:cubieboard """ deb_url = ('https://apt.armbian.com/pool/main/l/' - 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') - deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + 'linux-5.10.16-sunxi/linux-image-current-sunxi_21.02.2_armhf.deb') + deb_hash = '9fa84beda245cabf0b4fa84cf6eaa7738ead1da0' deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) kernel_path = self.extract_from_deb(deb_path, - '/boot/vmlinuz-4.20.7-sunxi') - dtb_path = '/usr/lib/linux-image-dev-sunxi/sun4i-a10-cubieboard.dtb' + '/boot/vmlinuz-5.10.16-sunxi') + dtb_path = '/usr/lib/linux-image-current-sunxi/sun4i-a10-cubieboard.dtb' dtb_path = self.extract_from_deb(deb_path, dtb_path) initrd_url = ('https://github.com/groeck/linux-build-test/raw/' '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Previously the ARMBIAN_ARTIFACTS_CACHED pre-condition was added to allow running tests that have already existing armbian.com artifacts stored in the local avocado cache, but do not have working URLs to download a fresh copy. At this time of writing the URLs for artifacts on the armbian.com server are updated and working. Any future broken URLs will result in a skipped acceptance test, for example: (1/5) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_orangepi: CANCEL: Missing asset https://apt.armbian.com/pool/main/l/linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb (0.53 s) This commits removes the ARMBIAN_ARTIFACTS_CACHED pre-condition such that the acceptance tests for the orangepi-pc and cubieboard machines can run. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-id: 20210310195820.21950-6-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 12 ------------ tests/acceptance/replay_kernel.py | 2 -- 2 files changed, 14 deletions(-) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_exynos4210_initrd(self): self.wait_for_console_pattern('Boot successful.') # TODO user command, for now the uart is stuck - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_cubieboard_initrd(self): """ :avocado: tags=arch:arm @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_initrd(self): 'system-control@1c00000') # cubieboard's reboot is not functioning; omit reboot test. - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_cubieboard_sata(self): """ :avocado: tags=arch:arm @@ -XXX,XX +XXX,XX @@ def test_arm_quanta_gsj_initrd(self): self.wait_for_console_pattern( 'Give root password for system maintenance') - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_orangepi(self): """ :avocado: tags=arch:arm @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi(self): console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_orangepi_initrd(self): """ :avocado: tags=arch:arm @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_initrd(self): # Wait for VM to shut down gracefully self.vm.wait() - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_orangepi_sd(self): """ :avocado: tags=arch:arm @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_sd(self): # Wait for VM to shut down gracefully self.vm.wait() - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') def test_arm_orangepi_bionic_20_08(self): """ diff --git a/tests/acceptance/replay_kernel.py b/tests/acceptance/replay_kernel.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/replay_kernel.py +++ b/tests/acceptance/replay_kernel.py @@ -XXX,XX +XXX,XX @@ def test_arm_virt(self): self.run_rr(kernel_path, kernel_command_line, console_pattern, shift=1) @skipIf(os.getenv('GITLAB_CI'), 'Running on GitLab') - @skipUnless(os.getenv('ARMBIAN_ARTIFACTS_CACHED'), - 'Test artifacts fetched from unreliable apt.armbian.com') def test_arm_cubieboard_initrd(self): """ :avocado: tags=arch:arm -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> If the SSECounter link is absent, we set an error message in sse_timer_realize() but forgot to propagate this error. Add the missing 'return'. Fixes: CID 1450755 (Null pointer dereferences) Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210312001845.1562670-1-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/sse-timer.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/timer/sse-timer.c b/hw/timer/sse-timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/sse-timer.c +++ b/hw/timer/sse-timer.c @@ -XXX,XX +XXX,XX @@ static void sse_timer_realize(DeviceState *dev, Error **errp) if (!s->counter) { error_setg(errp, "counter property was not set"); + return; } s->counter_notifier.notify = sse_timer_counter_callback; -- 2.20.1 From: Andrew Jones <drjones@redhat.com> Prior to commit f2ce39b4f067 a MachineClass kvm_type method only needed to be registered to ensure it would be executed. With commit f2ce39b4f067 a kvm-type machine property must also be specified. hw/arm/virt relies on the kvm_type method to pass its selected IPA limit to KVM, but this is not exposed as a machine property. Restore the previous functionality of invoking kvm_type when it's present. Fixes: f2ce39b4f067 ("vl: make qemu_get_machine_opts static") Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 20210310135218.255205-2-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/boards.h | 1 + accel/kvm/kvm-all.c | 2 ++ 2 files changed, 3 insertions(+) diff --git a/include/hw/boards.h b/include/hw/boards.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -XXX,XX +XXX,XX @@ typedef struct { * @kvm_type: * Return the type of KVM corresponding to the kvm-type string option or * computed based on other criteria such as the host kernel capabilities. + * kvm-type may be NULL if it is not needed. * @numa_mem_supported: * true if '--numa node.mem' option is supported and false otherwise * @smp_parse: diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -XXX,XX +XXX,XX @@ static int kvm_init(MachineState *ms) "kvm-type", &error_abort); type = mc->kvm_type(ms, kvm_type); + } else if (mc->kvm_type) { + type = mc->kvm_type(ms, NULL); } do { -- 2.20.1 From: Andrew Jones <drjones@redhat.com> The virt machine already checks KVM_CAP_ARM_VM_IPA_SIZE to get the upper bound of the IPA size. If that bound is lower than the highest possible GPA for the machine, then QEMU will error out. However, the IPA is set to 40 when the highest GPA is less than or equal to 40, even when KVM may support an IPA limit as low as 32. This means KVM may fail the VM creation unnecessarily. Additionally, 40 is selected with the value 0, which means use the default, and that gets around a check in some versions of KVM, causing a difficult to debug fail. Always use the IPA size that corresponds to the highest possible GPA, unless it's lower than 32, in which case use 32. Also, we must still use 0 when KVM only supports the legacy fixed 40 bit IPA. Suggested-by: Marc Zyngier <maz@kernel.org> Signed-off-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Marc Zyngier <maz@kernel.org> Message-id: 20210310135218.255205-3-drjones@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 6 ++++-- hw/arm/virt.c | 23 ++++++++++++++++------- target/arm/kvm.c | 4 +++- 3 files changed, 23 insertions(+), 10 deletions(-) diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ bool kvm_arm_sve_supported(void); /** * kvm_arm_get_max_vm_ipa_size: * @ms: Machine state handle + * @fixed_ipa: True when the IPA limit is fixed at 40. This is the case + * for legacy KVM. * * Returns the number of bits in the IPA address space supported by KVM */ -int kvm_arm_get_max_vm_ipa_size(MachineState *ms); +int kvm_arm_get_max_vm_ipa_size(MachineState *ms, bool *fixed_ipa); /** * kvm_arm_sync_mpstate_to_kvm: @@ -XXX,XX +XXX,XX @@ static inline void kvm_arm_add_vcpu_properties(Object *obj) g_assert_not_reached(); } -static inline int kvm_arm_get_max_vm_ipa_size(MachineState *ms) +static inline int kvm_arm_get_max_vm_ipa_size(MachineState *ms, bool *fixed_ipa) { g_assert_not_reached(); } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static HotplugHandler *virt_machine_get_hotplug_handler(MachineState *machine, static int virt_kvm_type(MachineState *ms, const char *type_str) { VirtMachineState *vms = VIRT_MACHINE(ms); - int max_vm_pa_size = kvm_arm_get_max_vm_ipa_size(ms); - int requested_pa_size; + int max_vm_pa_size, requested_pa_size; + bool fixed_ipa; + + max_vm_pa_size = kvm_arm_get_max_vm_ipa_size(ms, &fixed_ipa); /* we freeze the memory map to compute the highest gpa */ virt_set_memmap(vms); requested_pa_size = 64 - clz64(vms->highest_gpa); + /* + * KVM requires the IPA size to be at least 32 bits. + */ + if (requested_pa_size < 32) { + requested_pa_size = 32; + } + if (requested_pa_size > max_vm_pa_size) { error_report("-m and ,maxmem option values " "require an IPA range (%d bits) larger than " "the one supported by the host (%d bits)", requested_pa_size, max_vm_pa_size); - exit(1); + exit(1); } /* - * By default we return 0 which corresponds to an implicit legacy - * 40b IPA setting. Otherwise we return the actual requested PA - * logsize + * We return the requested PA log size, unless KVM only supports + * the implicit legacy 40b IPA setting, in which case the kvm_type + * must be 0. */ - return requested_pa_size > 40 ? requested_pa_size : 0; + return fixed_ipa ? 0 : requested_pa_size; } static void virt_machine_class_init(ObjectClass *oc, void *data) 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 @@ bool kvm_arm_pmu_supported(void) return kvm_check_extension(kvm_state, KVM_CAP_ARM_PMU_V3); } -int kvm_arm_get_max_vm_ipa_size(MachineState *ms) +int kvm_arm_get_max_vm_ipa_size(MachineState *ms, bool *fixed_ipa) { KVMState *s = KVM_STATE(ms->accelerator); int ret; ret = kvm_check_extension(s, KVM_CAP_ARM_VM_IPA_SIZE); + *fixed_ipa = ret <= 0; + return ret > 0 ? ret : 40; } -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch adds GPIOs in NPCM7xx PWM module for its duty values. The purpose of this is to connect it to the MFT module to provide an input for measuring a PWM fan's RPM. Each PWM module has NPCM7XX_PWM_PER_MODULE of GPIOs, each one corresponds to one PWM instance and can connect to multiple fan instances in MFT. Reviewed-by: Doug Evans <dje@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210311180855.149764-2-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_pwm.h | 4 +++- hw/misc/npcm7xx_pwm.c | 4 ++++ 2 files changed, 7 insertions(+), 1 deletion(-) 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 @@ typedef struct NPCM7xxPWM { * @iomem: Memory region through which registers are accessed. * @clock: The PWM clock. * @pwm: The PWM channels owned by this module. + * @duty_gpio_out: The duty cycle of each PWM channels as a output GPIO. * @ppr: The prescaler register. * @csr: The clock selector register. * @pcr: The control register. @@ -XXX,XX +XXX,XX @@ struct NPCM7xxPWMState { MemoryRegion iomem; Clock *clock; - NPCM7xxPWM pwm[NPCM7XX_PWM_PER_MODULE]; + NPCM7xxPWM pwm[NPCM7XX_PWM_PER_MODULE]; + qemu_irq duty_gpio_out[NPCM7XX_PWM_PER_MODULE]; uint32_t ppr; uint32_t csr; diff --git a/hw/misc/npcm7xx_pwm.c b/hw/misc/npcm7xx_pwm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/npcm7xx_pwm.c +++ b/hw/misc/npcm7xx_pwm.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_pwm_update_duty(NPCM7xxPWM *p) trace_npcm7xx_pwm_update_duty(DEVICE(p->module)->canonical_path, p->index, p->duty, duty); p->duty = duty; + qemu_set_irq(p->module->duty_gpio_out[p->index], p->duty); } } @@ -XXX,XX +XXX,XX @@ static void npcm7xx_pwm_init(Object *obj) SysBusDevice *sbd = SYS_BUS_DEVICE(obj); int i; + QEMU_BUILD_BUG_ON(ARRAY_SIZE(s->pwm) != NPCM7XX_PWM_PER_MODULE); for (i = 0; i < NPCM7XX_PWM_PER_MODULE; i++) { NPCM7xxPWM *p = &s->pwm[i]; p->module = s; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_pwm_init(Object *obj) object_property_add_uint32_ptr(obj, "duty[*]", &s->pwm[i].duty, OBJ_PROP_FLAG_READ); } + qdev_init_gpio_out_named(DEVICE(s), s->duty_gpio_out, + "duty-gpio-out", NPCM7XX_PWM_PER_MODULE); } static const VMStateDescription vmstate_npcm7xx_pwm = { -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch implements Multi Function Timer (MFT) module for NPCM7XX. This module is mainly used to configure PWM fans. It has just enough functionality to make the PWM fan kernel module work. The module takes two input, the max_rpm of a fan (modifiable via QMP) and duty cycle (a GPIO from the PWM module.) The actual measured RPM is equal to max_rpm * duty_cycle / NPCM7XX_PWM_MAX_DUTY. The RPM is measured as a counter compared to a prescaled input clock. The kernel driver reads this counter and report to user space. Refs: https://github.com/torvalds/linux/blob/master/drivers/hwmon/npcm750-pwm-fan.c Reviewed-by: Doug Evans <dje@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210311180855.149764-3-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_mft.h | 70 +++++ hw/misc/npcm7xx_mft.c | 540 ++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + hw/misc/trace-events | 8 + 4 files changed, 619 insertions(+) create mode 100644 include/hw/misc/npcm7xx_mft.h create mode 100644 hw/misc/npcm7xx_mft.c diff --git a/include/hw/misc/npcm7xx_mft.h b/include/hw/misc/npcm7xx_mft.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/npcm7xx_mft.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx MFT Module + * + * Copyright 2021 Google LLC + * + * 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. + */ +#ifndef NPCM7XX_MFT_H +#define NPCM7XX_MFT_H + +#include "exec/memory.h" +#include "hw/clock.h" +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "qom/object.h" + +/* Max Fan input number. */ +#define NPCM7XX_MFT_MAX_FAN_INPUT 19 + +/* + * Number of registers in one MFT module. Don't change this without increasing + * the version_id in vmstate. + */ +#define NPCM7XX_MFT_NR_REGS (0x20 / sizeof(uint16_t)) + +/* + * The MFT can take up to 4 inputs: A0, B0, A1, B1. It can measure one A and one + * B simultaneously. NPCM7XX_MFT_INASEL and NPCM7XX_MFT_INBSEL are used to + * select which A or B input are used. + */ +#define NPCM7XX_MFT_FANIN_COUNT 4 + +/** + * struct NPCM7xxMFTState - Multi Functional Tachometer device state. + * @parent: System bus device. + * @iomem: Memory region through which registers are accessed. + * @clock_in: The input clock for MFT from CLK module. + * @clock_{1,2}: The counter clocks for NPCM7XX_MFT_CNT{1,2} + * @irq: The IRQ for this MFT state. + * @regs: The MMIO registers. + * @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 { + SysBusDevice parent; + + MemoryRegion iomem; + + Clock *clock_in; + Clock *clock_1, *clock_2; + qemu_irq irq; + uint16_t regs[NPCM7XX_MFT_NR_REGS]; + + 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) + +#endif /* NPCM7XX_MFT_H */ diff --git a/hw/misc/npcm7xx_mft.c b/hw/misc/npcm7xx_mft.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/npcm7xx_mft.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx MFT Module + * + * Copyright 2021 Google LLC + * + * 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. + */ + +#include "qemu/osdep.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/misc/npcm7xx_mft.h" +#include "hw/misc/npcm7xx_pwm.h" +#include "hw/registerfields.h" +#include "migration/vmstate.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qemu/units.h" +#include "trace.h" + +/* + * Some of the registers can only accessed via 16-bit ops and some can only + * be accessed via 8-bit ops. However we mark all of them using REG16 to + * simplify implementation. npcm7xx_mft_check_mem_op checks the access length + * of memory operations. + */ +REG16(NPCM7XX_MFT_CNT1, 0x00); +REG16(NPCM7XX_MFT_CRA, 0x02); +REG16(NPCM7XX_MFT_CRB, 0x04); +REG16(NPCM7XX_MFT_CNT2, 0x06); +REG16(NPCM7XX_MFT_PRSC, 0x08); +REG16(NPCM7XX_MFT_CKC, 0x0a); +REG16(NPCM7XX_MFT_MCTRL, 0x0c); +REG16(NPCM7XX_MFT_ICTRL, 0x0e); +REG16(NPCM7XX_MFT_ICLR, 0x10); +REG16(NPCM7XX_MFT_IEN, 0x12); +REG16(NPCM7XX_MFT_CPA, 0x14); +REG16(NPCM7XX_MFT_CPB, 0x16); +REG16(NPCM7XX_MFT_CPCFG, 0x18); +REG16(NPCM7XX_MFT_INASEL, 0x1a); +REG16(NPCM7XX_MFT_INBSEL, 0x1c); + +/* Register Fields */ +#define NPCM7XX_MFT_CKC_C2CSEL BIT(3) +#define NPCM7XX_MFT_CKC_C1CSEL BIT(0) + +#define NPCM7XX_MFT_MCTRL_TBEN BIT(6) +#define NPCM7XX_MFT_MCTRL_TAEN BIT(5) +#define NPCM7XX_MFT_MCTRL_TBEDG BIT(4) +#define NPCM7XX_MFT_MCTRL_TAEDG BIT(3) +#define NPCM7XX_MFT_MCTRL_MODE5 BIT(2) + +#define NPCM7XX_MFT_ICTRL_TFPND BIT(5) +#define NPCM7XX_MFT_ICTRL_TEPND BIT(4) +#define NPCM7XX_MFT_ICTRL_TDPND BIT(3) +#define NPCM7XX_MFT_ICTRL_TCPND BIT(2) +#define NPCM7XX_MFT_ICTRL_TBPND BIT(1) +#define NPCM7XX_MFT_ICTRL_TAPND BIT(0) + +#define NPCM7XX_MFT_ICLR_TFCLR BIT(5) +#define NPCM7XX_MFT_ICLR_TECLR BIT(4) +#define NPCM7XX_MFT_ICLR_TDCLR BIT(3) +#define NPCM7XX_MFT_ICLR_TCCLR BIT(2) +#define NPCM7XX_MFT_ICLR_TBCLR BIT(1) +#define NPCM7XX_MFT_ICLR_TACLR BIT(0) + +#define NPCM7XX_MFT_IEN_TFIEN BIT(5) +#define NPCM7XX_MFT_IEN_TEIEN BIT(4) +#define NPCM7XX_MFT_IEN_TDIEN BIT(3) +#define NPCM7XX_MFT_IEN_TCIEN BIT(2) +#define NPCM7XX_MFT_IEN_TBIEN BIT(1) +#define NPCM7XX_MFT_IEN_TAIEN BIT(0) + +#define NPCM7XX_MFT_CPCFG_GET_B(rv) extract8((rv), 4, 4) +#define NPCM7XX_MFT_CPCFG_GET_A(rv) extract8((rv), 0, 4) +#define NPCM7XX_MFT_CPCFG_HIEN BIT(3) +#define NPCM7XX_MFT_CPCFG_EQEN BIT(2) +#define NPCM7XX_MFT_CPCFG_LOEN BIT(1) +#define NPCM7XX_MFT_CPCFG_CPSEL BIT(0) + +#define NPCM7XX_MFT_INASEL_SELA BIT(0) +#define NPCM7XX_MFT_INBSEL_SELB BIT(0) + +/* Max CNT values of the module. The CNT value is a countdown from it. */ +#define NPCM7XX_MFT_MAX_CNT 0xFFFF + +/* Each fan revolution should generated 2 pulses */ +#define NPCM7XX_MFT_PULSE_PER_REVOLUTION 2 + +typedef enum NPCM7xxMFTCaptureState { + /* capture succeeded with a valid CNT value. */ + NPCM7XX_CAPTURE_SUCCEED, + /* capture stopped prematurely due to reaching CPCFG condition. */ + NPCM7XX_CAPTURE_COMPARE_HIT, + /* capture fails since it reaches underflow condition for CNT. */ + NPCM7XX_CAPTURE_UNDERFLOW, +} NPCM7xxMFTCaptureState; + +static void npcm7xx_mft_reset(NPCM7xxMFTState *s) +{ + int i; + + /* Only registers PRSC ~ INBSEL need to be reset. */ + for (i = R_NPCM7XX_MFT_PRSC; i <= R_NPCM7XX_MFT_INBSEL; ++i) { + s->regs[i] = 0; + } +} + +static void npcm7xx_mft_clear_interrupt(NPCM7xxMFTState *s, uint8_t iclr) +{ + /* + * Clear bits in ICTRL where corresponding bits in iclr is 1. + * Both iclr and ictrl are 8-bit regs. (See npcm7xx_mft_check_mem_op) + */ + s->regs[R_NPCM7XX_MFT_ICTRL] &= ~iclr; +} + +/* + * If the CPCFG's condition should be triggered during count down from + * NPCM7XX_MFT_MAX_CNT to src if compared to tgt, return the count when + * the condition is triggered. + * Otherwise return -1. + * Since tgt is uint16_t it must always <= NPCM7XX_MFT_MAX_CNT. + */ +static int npcm7xx_mft_compare(int32_t src, uint16_t tgt, uint8_t cpcfg) +{ + if (cpcfg & NPCM7XX_MFT_CPCFG_HIEN) { + return NPCM7XX_MFT_MAX_CNT; + } + if ((cpcfg & NPCM7XX_MFT_CPCFG_EQEN) && (src <= tgt)) { + return tgt; + } + if ((cpcfg & NPCM7XX_MFT_CPCFG_LOEN) && (tgt > 0) && (src < tgt)) { + return tgt - 1; + } + + return -1; +} + +/* Compute CNT according to corresponding fan's RPM. */ +static NPCM7xxMFTCaptureState npcm7xx_mft_compute_cnt( + Clock *clock, uint32_t max_rpm, uint32_t duty, uint16_t tgt, + uint8_t cpcfg, uint16_t *cnt) +{ + uint32_t rpm = (uint64_t)max_rpm * (uint64_t)duty / NPCM7XX_PWM_MAX_DUTY; + int32_t count; + int stopped; + NPCM7xxMFTCaptureState state; + + if (rpm == 0) { + /* + * If RPM = 0, capture won't happen. CNT will continue count down. + * So it's effective equivalent to have a cnt > NPCM7XX_MFT_MAX_CNT + */ + count = NPCM7XX_MFT_MAX_CNT + 1; + } else { + /* + * RPM = revolution/min. The time for one revlution (in ns) is + * MINUTE_TO_NANOSECOND / RPM. + */ + count = clock_ns_to_ticks(clock, (60 * NANOSECONDS_PER_SECOND) / + (rpm * NPCM7XX_MFT_PULSE_PER_REVOLUTION)); + } + + if (count > NPCM7XX_MFT_MAX_CNT) { + count = -1; + } else { + /* The CNT is a countdown value from NPCM7XX_MFT_MAX_CNT. */ + count = NPCM7XX_MFT_MAX_CNT - count; + } + stopped = npcm7xx_mft_compare(count, tgt, cpcfg); + if (stopped == -1) { + if (count == -1) { + /* Underflow */ + state = NPCM7XX_CAPTURE_UNDERFLOW; + } else { + state = NPCM7XX_CAPTURE_SUCCEED; + } + } else { + count = stopped; + state = NPCM7XX_CAPTURE_COMPARE_HIT; + } + + if (count != -1) { + *cnt = count; + } + trace_npcm7xx_mft_rpm(clock->canonical_path, clock_get_hz(clock), + state, count, rpm, duty); + return state; +} + +/* + * Capture Fan RPM and update CNT and CR registers accordingly. + * Raise IRQ if certain contidions are met in IEN. + */ +static void npcm7xx_mft_capture(NPCM7xxMFTState *s) +{ + int irq_level = 0; + NPCM7xxMFTCaptureState state; + int sel; + uint8_t cpcfg; + + /* + * If not mode 5, the behavior is undefined. We just do nothing in this + * case. + */ + if (!(s->regs[R_NPCM7XX_MFT_MCTRL] & NPCM7XX_MFT_MCTRL_MODE5)) { + return; + } + + /* Capture input A. */ + if (s->regs[R_NPCM7XX_MFT_MCTRL] & NPCM7XX_MFT_MCTRL_TAEN && + s->regs[R_NPCM7XX_MFT_CKC] & NPCM7XX_MFT_CKC_C1CSEL) { + sel = s->regs[R_NPCM7XX_MFT_INASEL] & NPCM7XX_MFT_INASEL_SELA; + cpcfg = NPCM7XX_MFT_CPCFG_GET_A(s->regs[R_NPCM7XX_MFT_CPCFG]); + state = npcm7xx_mft_compute_cnt(s->clock_1, + sel ? s->max_rpm[2] : s->max_rpm[0], + sel ? s->duty[2] : s->duty[0], + s->regs[R_NPCM7XX_MFT_CPA], + cpcfg, + &s->regs[R_NPCM7XX_MFT_CNT1]); + switch (state) { + case NPCM7XX_CAPTURE_SUCCEED: + /* Interrupt on input capture on TAn transition - TAPND */ + s->regs[R_NPCM7XX_MFT_CRA] = s->regs[R_NPCM7XX_MFT_CNT1]; + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TAPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TAIEN) { + irq_level = 1; + } + break; + + case NPCM7XX_CAPTURE_COMPARE_HIT: + /* Compare Hit - TEPND */ + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TEPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TEIEN) { + irq_level = 1; + } + break; + + case NPCM7XX_CAPTURE_UNDERFLOW: + /* Underflow - TCPND */ + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TCPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TCIEN) { + irq_level = 1; + } + break; + + default: + g_assert_not_reached(); + } + } + + /* Capture input B. */ + if (s->regs[R_NPCM7XX_MFT_MCTRL] & NPCM7XX_MFT_MCTRL_TBEN && + s->regs[R_NPCM7XX_MFT_CKC] & NPCM7XX_MFT_CKC_C2CSEL) { + sel = s->regs[R_NPCM7XX_MFT_INBSEL] & NPCM7XX_MFT_INBSEL_SELB; + cpcfg = NPCM7XX_MFT_CPCFG_GET_B(s->regs[R_NPCM7XX_MFT_CPCFG]); + state = npcm7xx_mft_compute_cnt(s->clock_2, + sel ? s->max_rpm[3] : s->max_rpm[1], + sel ? s->duty[3] : s->duty[1], + s->regs[R_NPCM7XX_MFT_CPB], + cpcfg, + &s->regs[R_NPCM7XX_MFT_CNT2]); + switch (state) { + case NPCM7XX_CAPTURE_SUCCEED: + /* Interrupt on input capture on TBn transition - TBPND */ + s->regs[R_NPCM7XX_MFT_CRB] = s->regs[R_NPCM7XX_MFT_CNT2]; + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TBPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TBIEN) { + irq_level = 1; + } + break; + + case NPCM7XX_CAPTURE_COMPARE_HIT: + /* Compare Hit - TFPND */ + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TFPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TFIEN) { + irq_level = 1; + } + break; + + case NPCM7XX_CAPTURE_UNDERFLOW: + /* Underflow - TDPND */ + s->regs[R_NPCM7XX_MFT_ICTRL] |= NPCM7XX_MFT_ICTRL_TDPND; + if (s->regs[R_NPCM7XX_MFT_IEN] & NPCM7XX_MFT_IEN_TDIEN) { + irq_level = 1; + } + break; + + default: + g_assert_not_reached(); + } + } + + trace_npcm7xx_mft_capture(DEVICE(s)->canonical_path, irq_level); + qemu_set_irq(s->irq, irq_level); +} + +/* Update clock for counters. */ +static void npcm7xx_mft_update_clock(void *opaque, ClockEvent event) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(opaque); + uint64_t prescaled_clock_period; + + prescaled_clock_period = clock_get(s->clock_in) * + (s->regs[R_NPCM7XX_MFT_PRSC] + 1ULL); + trace_npcm7xx_mft_update_clock(s->clock_in->canonical_path, + s->regs[R_NPCM7XX_MFT_CKC], + clock_get(s->clock_in), + prescaled_clock_period); + /* Update clock 1 */ + if (s->regs[R_NPCM7XX_MFT_CKC] & NPCM7XX_MFT_CKC_C1CSEL) { + /* Clock is prescaled. */ + clock_update(s->clock_1, prescaled_clock_period); + } else { + /* Clock stopped. */ + clock_update(s->clock_1, 0); + } + /* Update clock 2 */ + if (s->regs[R_NPCM7XX_MFT_CKC] & NPCM7XX_MFT_CKC_C2CSEL) { + /* Clock is prescaled. */ + clock_update(s->clock_2, prescaled_clock_period); + } else { + /* Clock stopped. */ + clock_update(s->clock_2, 0); + } + + npcm7xx_mft_capture(s); +} + +static uint64_t npcm7xx_mft_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(opaque); + uint16_t value = 0; + + switch (offset) { + case A_NPCM7XX_MFT_ICLR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: register @ 0x%04" HWADDR_PRIx " is write-only\n", + __func__, offset); + break; + + default: + value = s->regs[offset / 2]; + } + + trace_npcm7xx_mft_read(DEVICE(s)->canonical_path, offset, value); + return value; +} + +static void npcm7xx_mft_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(opaque); + + trace_npcm7xx_mft_write(DEVICE(s)->canonical_path, offset, v); + switch (offset) { + case A_NPCM7XX_MFT_ICLR: + npcm7xx_mft_clear_interrupt(s, v); + break; + + case A_NPCM7XX_MFT_CKC: + case A_NPCM7XX_MFT_PRSC: + s->regs[offset / 2] = v; + npcm7xx_mft_update_clock(s, ClockUpdate); + break; + + default: + s->regs[offset / 2] = v; + npcm7xx_mft_capture(s); + break; + } +} + +static bool npcm7xx_mft_check_mem_op(void *opaque, hwaddr offset, + unsigned size, bool is_write, + MemTxAttrs attrs) +{ + switch (offset) { + /* 16-bit registers. Must be accessed with 16-bit read/write.*/ + case A_NPCM7XX_MFT_CNT1: + case A_NPCM7XX_MFT_CRA: + case A_NPCM7XX_MFT_CRB: + case A_NPCM7XX_MFT_CNT2: + case A_NPCM7XX_MFT_CPA: + case A_NPCM7XX_MFT_CPB: + return size == 2; + + /* 8-bit registers. Must be accessed with 8-bit read/write.*/ + case A_NPCM7XX_MFT_PRSC: + case A_NPCM7XX_MFT_CKC: + case A_NPCM7XX_MFT_MCTRL: + case A_NPCM7XX_MFT_ICTRL: + case A_NPCM7XX_MFT_ICLR: + case A_NPCM7XX_MFT_IEN: + case A_NPCM7XX_MFT_CPCFG: + case A_NPCM7XX_MFT_INASEL: + case A_NPCM7XX_MFT_INBSEL: + return size == 1; + + default: + /* Invalid registers. */ + return false; + } +} + +static void npcm7xx_mft_get_max_rpm(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + visit_type_uint32(v, name, (uint32_t *)opaque, errp); +} + +static void npcm7xx_mft_set_max_rpm(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(obj); + uint32_t *max_rpm = opaque; + uint32_t value; + + if (!visit_type_uint32(v, name, &value, errp)) { + return; + } + + *max_rpm = value; + npcm7xx_mft_capture(s); +} + +static void npcm7xx_mft_duty_handler(void *opaque, int n, int value) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(opaque); + + trace_npcm7xx_mft_set_duty(DEVICE(s)->canonical_path, n, value); + s->duty[n] = value; + npcm7xx_mft_capture(s); +} + +static const struct MemoryRegionOps npcm7xx_mft_ops = { + .read = npcm7xx_mft_read, + .write = npcm7xx_mft_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 1, + .max_access_size = 2, + .unaligned = false, + .accepts = npcm7xx_mft_check_mem_op, + }, +}; + +static void npcm7xx_mft_enter_reset(Object *obj, ResetType type) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(obj); + + npcm7xx_mft_reset(s); +} + +static void npcm7xx_mft_hold_reset(Object *obj) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(obj); + + qemu_irq_lower(s->irq); +} + +static void npcm7xx_mft_init(Object *obj) +{ + NPCM7xxMFTState *s = NPCM7XX_MFT(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + DeviceState *dev = DEVICE(obj); + + memory_region_init_io(&s->iomem, obj, &npcm7xx_mft_ops, s, + TYPE_NPCM7XX_MFT, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(sbd, &s->irq); + s->clock_in = qdev_init_clock_in(dev, "clock-in", npcm7xx_mft_update_clock, + s, ClockUpdate); + s->clock_1 = qdev_init_clock_out(dev, "clock1"); + s->clock_2 = qdev_init_clock_out(dev, "clock2"); + + for (int i = 0; i < NPCM7XX_PWM_PER_MODULE; ++i) { + object_property_add(obj, "max_rpm[*]", "uint32", + npcm7xx_mft_get_max_rpm, + npcm7xx_mft_set_max_rpm, + NULL, &s->max_rpm[i]); + } + qdev_init_gpio_in_named(dev, npcm7xx_mft_duty_handler, "duty", + NPCM7XX_MFT_FANIN_COUNT); +} + +static const VMStateDescription vmstate_npcm7xx_mft = { + .name = "npcm7xx-mft-module", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_CLOCK(clock_in, NPCM7xxMFTState), + VMSTATE_CLOCK(clock_1, NPCM7xxMFTState), + VMSTATE_CLOCK(clock_2, NPCM7xxMFTState), + VMSTATE_UINT16_ARRAY(regs, NPCM7xxMFTState, NPCM7XX_MFT_NR_REGS), + VMSTATE_UINT32_ARRAY(max_rpm, NPCM7xxMFTState, NPCM7XX_MFT_FANIN_COUNT), + VMSTATE_UINT32_ARRAY(duty, NPCM7xxMFTState, NPCM7XX_MFT_FANIN_COUNT), + VMSTATE_END_OF_LIST(), + }, +}; + +static void npcm7xx_mft_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->desc = "NPCM7xx MFT Controller"; + dc->vmsd = &vmstate_npcm7xx_mft; + rc->phases.enter = npcm7xx_mft_enter_reset; + rc->phases.hold = npcm7xx_mft_hold_reset; +} + +static const TypeInfo npcm7xx_mft_info = { + .name = TYPE_NPCM7XX_MFT, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxMFTState), + .class_init = npcm7xx_mft_class_init, + .instance_init = npcm7xx_mft_init, +}; + +static void npcm7xx_mft_register_type(void) +{ + type_register_static(&npcm7xx_mft_info); +} +type_init(npcm7xx_mft_register_type); 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 @@ softmmu_ss.add(when: 'CONFIG_MAINSTONE', if_true: files('mst_fpga.c')) softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files( 'npcm7xx_clk.c', 'npcm7xx_gcr.c', + 'npcm7xx_mft.c', 'npcm7xx_pwm.c', 'npcm7xx_rng.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 @@ npcm7xx_clk_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " valu npcm7xx_gcr_read(uint64_t offset, uint32_t value) " offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 npcm7xx_gcr_write(uint64_t offset, uint32_t value) "offset: 0x%04" PRIx64 " value: 0x%08" PRIx32 +# npcm7xx_mft.c +npcm7xx_mft_read(const char *name, uint64_t offset, uint16_t value) "%s: offset: 0x%04" PRIx64 " value: 0x%04" PRIx16 +npcm7xx_mft_write(const char *name, uint64_t offset, uint16_t value) "%s: offset: 0x%04" PRIx64 " value: 0x%04" PRIx16 +npcm7xx_mft_rpm(const char *clock, uint32_t clock_hz, int state, int32_t cnt, uint32_t rpm, uint32_t duty) " fan clk: %s clock_hz: %" PRIu32 ", state: %d, cnt: %" PRIi32 ", rpm: %" PRIu32 ", duty: %" PRIu32 +npcm7xx_mft_capture(const char *name, int irq_level) "%s: level: %d" +npcm7xx_mft_update_clock(const char *name, uint16_t sel, uint64_t clock_period, uint64_t prescaled_clock_period) "%s: sel: 0x%02" PRIx16 ", period: %" PRIu64 ", prescaled: %" PRIu64 +npcm7xx_mft_set_duty(const char *name, int n, int value) "%s[%d]: %d" + # npcm7xx_rng.c npcm7xx_rng_read(uint64_t offset, uint64_t value, unsigned size) "offset: 0x%04" PRIx64 " value: 0x%02" PRIx64 " size: %u" npcm7xx_rng_write(uint64_t offset, uint64_t value, unsigned size) "offset: 0x%04" PRIx64 " value: 0x%02" PRIx64 " size: %u" -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch adds the recently implemented MFT device to the NPCM7XX SoC file. Reviewed-by: Doug Evans <dje@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210311180855.149764-4-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 2 +- include/hw/arm/npcm7xx.h | 2 ++ hw/arm/npcm7xx.c | 45 ++++++++++++++++++++++++++++++------- 3 files changed, 40 insertions(+), 9 deletions(-) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Supported devices * Pulse Width Modulation (PWM) * SMBus controller (SMBF) * Ethernet controller (EMC) + * Tachometer Missing devices --------------- @@ -XXX,XX +XXX,XX @@ Missing devices * Peripheral SPI controller (PSPI) * SD/MMC host * PECI interface - * Tachometer * PCI and PCIe root complex and bridges * VDM and MCTP support * Serial I/O expansion 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 @@ #include "hw/mem/npcm7xx_mc.h" #include "hw/misc/npcm7xx_clk.h" #include "hw/misc/npcm7xx_gcr.h" +#include "hw/misc/npcm7xx_mft.h" #include "hw/misc/npcm7xx_pwm.h" #include "hw/misc/npcm7xx_rng.h" #include "hw/net/npcm7xx_emc.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxTimerCtrlState tim[3]; NPCM7xxADCState adc; NPCM7xxPWMState pwm[2]; + NPCM7xxMFTState mft[8]; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; NPCM7xxMCState mc; diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_SMBUS15_IRQ, NPCM7XX_PWM0_IRQ = 93, /* PWM module 0 */ NPCM7XX_PWM1_IRQ, /* PWM module 1 */ + NPCM7XX_MFT0_IRQ = 96, /* MFT module 0 */ + NPCM7XX_MFT1_IRQ, /* MFT module 1 */ + NPCM7XX_MFT2_IRQ, /* MFT module 2 */ + NPCM7XX_MFT3_IRQ, /* MFT module 3 */ + NPCM7XX_MFT4_IRQ, /* MFT module 4 */ + NPCM7XX_MFT5_IRQ, /* MFT module 5 */ + NPCM7XX_MFT6_IRQ, /* MFT module 6 */ + NPCM7XX_MFT7_IRQ, /* MFT module 7 */ NPCM7XX_EMC2RX_IRQ = 114, NPCM7XX_EMC2TX_IRQ, NPCM7XX_GPIO0_IRQ = 116, @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_pwm_addr[] = { 0xf0104000, }; +/* Register base address for each MFT Module */ +static const hwaddr npcm7xx_mft_addr[] = { + 0xf0180000, + 0xf0181000, + 0xf0182000, + 0xf0183000, + 0xf0184000, + 0xf0185000, + 0xf0186000, + 0xf0187000, +}; + /* Direct memory-mapped access to each SMBus Module. */ static const hwaddr npcm7xx_smbus_addr[] = { 0xf0080000, @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) object_initialize_child(obj, "pwm[*]", &s->pwm[i], TYPE_NPCM7XX_PWM); } + for (i = 0; i < ARRAY_SIZE(s->mft); i++) { + object_initialize_child(obj, "mft[*]", &s->mft[i], TYPE_NPCM7XX_MFT); + } + for (i = 0; i < ARRAY_SIZE(s->emc); i++) { object_initialize_child(obj, "emc[*]", &s->emc[i], TYPE_NPCM7XX_EMC); } @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(sbd, i, npcm7xx_irq(s, NPCM7XX_PWM0_IRQ + i)); } + /* MFT Modules. Cannot fail. */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_mft_addr) != ARRAY_SIZE(s->mft)); + for (i = 0; i < ARRAY_SIZE(s->mft); i++) { + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->mft[i]); + + qdev_connect_clock_in(DEVICE(&s->mft[i]), "clock-in", + qdev_get_clock_out(DEVICE(&s->clk), + "apb4-clock")); + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_mft_addr[i]); + sysbus_connect_irq(sbd, 0, npcm7xx_irq(s, NPCM7XX_MFT0_IRQ + i)); + } + /* * EMC Modules. Cannot fail. * The mapping of the device to its netdev backend works as follows: @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) create_unimplemented_device("npcm7xx.peci", 0xf0100000, 4 * KiB); create_unimplemented_device("npcm7xx.siox[1]", 0xf0101000, 4 * KiB); create_unimplemented_device("npcm7xx.siox[2]", 0xf0102000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[0]", 0xf0180000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[1]", 0xf0181000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[2]", 0xf0182000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[3]", 0xf0183000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[4]", 0xf0184000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[5]", 0xf0185000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[6]", 0xf0186000, 4 * KiB); - create_unimplemented_device("npcm7xx.mft[7]", 0xf0187000, 4 * KiB); create_unimplemented_device("npcm7xx.pspi1", 0xf0200000, 4 * KiB); create_unimplemented_device("npcm7xx.pspi2", 0xf0201000, 4 * KiB); create_unimplemented_device("npcm7xx.ahbpci", 0xf0400000, 1 * MiB); -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch adds fan_splitters (split IRQs) in NPCM7XX boards. Each fan splitter corresponds to 1 PWM output and can connect to multiple fan inputs (MFT devices). In NPCM7XX boards(NPCM750 EVB and Quanta GSJ boards), we initializes these splitters and connect them to their corresponding modules according their specific device trees. Reviewed-by: Doug Evans <dje@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210311180855.149764-5-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/npcm7xx.h | 11 ++++- hw/arm/npcm7xx_boards.c | 99 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 109 insertions(+), 1 deletion(-) 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 @@ #include "hw/boards.h" #include "hw/adc/npcm7xx_adc.h" +#include "hw/core/split-irq.h" #include "hw/cpu/a9mpcore.h" #include "hw/gpio/npcm7xx_gpio.h" #include "hw/i2c/npcm7xx_smbus.h" @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_GIC_CPU_IF_ADDR (0xf03fe100) /* GIC within A9 */ #define NPCM7XX_BOARD_SETUP_ADDR (0xffff1000) /* Boot ROM */ +#define NPCM7XX_NR_PWM_MODULES 2 + typedef struct NPCM7xxMachine { MachineState parent; + /* + * PWM fan splitter. each splitter connects to one PWM output and + * multiple MFT inputs. + */ + SplitIRQ fan_splitter[NPCM7XX_NR_PWM_MODULES * + NPCM7XX_PWM_PER_MODULE]; } NPCM7xxMachine; #define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxCLKState clk; NPCM7xxTimerCtrlState tim[3]; NPCM7xxADCState adc; - NPCM7xxPWMState pwm[2]; + NPCM7xxPWMState pwm[NPCM7XX_NR_PWM_MODULES]; NPCM7xxMFTState mft[8]; NPCM7xxOTPState key_storage; NPCM7xxOTPState fuse_array; diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/cpu.h" #include "hw/i2c/smbus_eeprom.h" #include "hw/loader.h" +#include "hw/qdev-core.h" #include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu-common.h" @@ -XXX,XX +XXX,XX @@ static void at24c_eeprom_init(NPCM7xxState *soc, int bus, uint8_t addr, i2c_slave_realize_and_unref(i2c_dev, i2c_bus, &error_abort); } +static void npcm7xx_init_pwm_splitter(NPCM7xxMachine *machine, + NPCM7xxState *soc, const int *fan_counts) +{ + SplitIRQ *splitters = machine->fan_splitter; + + /* + * PWM 0~3 belong to module 0 output 0~3. + * PWM 4~7 belong to module 1 output 0~3. + */ + for (int i = 0; i < NPCM7XX_NR_PWM_MODULES; ++i) { + for (int j = 0; j < NPCM7XX_PWM_PER_MODULE; ++j) { + int splitter_no = i * NPCM7XX_PWM_PER_MODULE + j; + DeviceState *splitter; + + if (fan_counts[splitter_no] < 1) { + continue; + } + object_initialize_child(OBJECT(machine), "fan-splitter[*]", + &splitters[splitter_no], TYPE_SPLIT_IRQ); + splitter = DEVICE(&splitters[splitter_no]); + qdev_prop_set_uint16(splitter, "num-lines", + fan_counts[splitter_no]); + qdev_realize(splitter, NULL, &error_abort); + qdev_connect_gpio_out_named(DEVICE(&soc->pwm[i]), "duty-gpio-out", + j, qdev_get_gpio_in(splitter, 0)); + } + } +} + +static void npcm7xx_connect_pwm_fan(NPCM7xxState *soc, SplitIRQ *splitter, + int fan_no, int output_no) +{ + DeviceState *fan; + int fan_input; + qemu_irq fan_duty_gpio; + + g_assert(fan_no >= 0 && fan_no <= NPCM7XX_MFT_MAX_FAN_INPUT); + /* + * Fan 0~1 belong to module 0 input 0~1. + * Fan 2~3 belong to module 1 input 0~1. + * ... + * Fan 14~15 belong to module 7 input 0~1. + * Fan 16~17 belong to module 0 input 2~3. + * Fan 18~19 belong to module 1 input 2~3. + */ + if (fan_no < 16) { + fan = DEVICE(&soc->mft[fan_no / 2]); + fan_input = fan_no % 2; + } else { + fan = DEVICE(&soc->mft[(fan_no - 16) / 2]); + fan_input = fan_no % 2 + 2; + } + + /* Connect the Fan to PWM module */ + fan_duty_gpio = qdev_get_gpio_in_named(fan, "duty", fan_input); + qdev_connect_gpio_out(DEVICE(splitter), output_no, fan_duty_gpio); +} + static void npcm750_evb_i2c_init(NPCM7xxState *soc) { /* lm75 temperature sensor on SVB, tmp105 is compatible */ @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_i2c_init(NPCM7xxState *soc) i2c_slave_create_simple(npcm7xx_i2c_get_bus(soc, 6), "tmp105", 0x48); } +static void npcm750_evb_fan_init(NPCM7xxMachine *machine, NPCM7xxState *soc) +{ + SplitIRQ *splitter = machine->fan_splitter; + static const int fan_counts[] = {2, 2, 2, 2, 2, 2, 2, 2}; + + npcm7xx_init_pwm_splitter(machine, soc, fan_counts); + npcm7xx_connect_pwm_fan(soc, &splitter[0], 0x00, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[0], 0x01, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[1], 0x02, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[1], 0x03, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[2], 0x04, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[2], 0x05, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[3], 0x06, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[3], 0x07, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[4], 0x08, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[4], 0x09, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[5], 0x0a, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[5], 0x0b, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[6], 0x0c, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[6], 0x0d, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[7], 0x0e, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[7], 0x0f, 1); +} + static void quanta_gsj_i2c_init(NPCM7xxState *soc) { /* GSJ machine have 4 max31725 temperature sensors, tmp105 is compatible. */ @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_i2c_init(NPCM7xxState *soc) /* TODO: Add additional i2c devices. */ } +static void quanta_gsj_fan_init(NPCM7xxMachine *machine, NPCM7xxState *soc) +{ + SplitIRQ *splitter = machine->fan_splitter; + static const int fan_counts[] = {2, 2, 2, 0, 0, 0, 0, 0}; + + npcm7xx_init_pwm_splitter(machine, soc, fan_counts); + npcm7xx_connect_pwm_fan(soc, &splitter[0], 0x00, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[0], 0x01, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[1], 0x02, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[1], 0x03, 1); + npcm7xx_connect_pwm_fan(soc, &splitter[2], 0x04, 0); + npcm7xx_connect_pwm_fan(soc, &splitter[2], 0x05, 1); +} + static void npcm750_evb_init(MachineState *machine) { NPCM7xxState *soc; @@ -XXX,XX +XXX,XX @@ static void npcm750_evb_init(MachineState *machine) npcm7xx_load_bootrom(machine, soc); npcm7xx_connect_flash(&soc->fiu[0], 0, "w25q256", drive_get(IF_MTD, 0, 0)); npcm750_evb_i2c_init(soc); + npcm750_evb_fan_init(NPCM7XX_MACHINE(machine), soc); npcm7xx_load_kernel(machine, soc); } @@ -XXX,XX +XXX,XX @@ static void quanta_gsj_init(MachineState *machine) npcm7xx_connect_flash(&soc->fiu[0], 0, "mx25l25635e", drive_get(IF_MTD, 0, 0)); quanta_gsj_i2c_init(soc); + quanta_gsj_fan_init(NPCM7XX_MACHINE(machine), soc); npcm7xx_load_kernel(machine, soc); } -- 2.20.1 From: Hao Wu <wuhaotsh@google.com> This patch adds testing of PWM fan RPMs in the existing npcm7xx pwm test. It tests whether the MFT module can measure correct fan values for a PWM fan in NPCM7XX boards. Reviewed-by: Doug Evans <dje@google.com> Reviewed-by: Tyrone Ting <kfting@nuvoton.com> Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20210311180855.149764-6-wuhaotsh@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_pwm-test.c | 205 ++++++++++++++++++++++++++++++++- 1 file changed, 199 insertions(+), 6 deletions(-) diff --git a/tests/qtest/npcm7xx_pwm-test.c b/tests/qtest/npcm7xx_pwm-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/npcm7xx_pwm-test.c +++ b/tests/qtest/npcm7xx_pwm-test.c @@ -XXX,XX +XXX,XX @@ #define PLL_FBDV(rv) extract32((rv), 16, 12) #define PLL_OTDV1(rv) extract32((rv), 8, 3) #define PLL_OTDV2(rv) extract32((rv), 13, 3) +#define APB4CKDIV(rv) extract32((rv), 30, 2) #define APB3CKDIV(rv) extract32((rv), 28, 2) #define CLK2CKDIV(rv) extract32((rv), 0, 1) #define CLK4CKDIV(rv) extract32((rv), 26, 2) @@ -XXX,XX +XXX,XX @@ #define MAX_DUTY 1000000 +/* MFT (PWM fan) related */ +#define MFT_BA(n) (0xf0180000 + ((n) * 0x1000)) +#define MFT_IRQ(n) (96 + (n)) +#define MFT_CNT1 0x00 +#define MFT_CRA 0x02 +#define MFT_CRB 0x04 +#define MFT_CNT2 0x06 +#define MFT_PRSC 0x08 +#define MFT_CKC 0x0a +#define MFT_MCTRL 0x0c +#define MFT_ICTRL 0x0e +#define MFT_ICLR 0x10 +#define MFT_IEN 0x12 +#define MFT_CPA 0x14 +#define MFT_CPB 0x16 +#define MFT_CPCFG 0x18 +#define MFT_INASEL 0x1a +#define MFT_INBSEL 0x1c + +#define MFT_MCTRL_ALL 0x64 +#define MFT_ICLR_ALL 0x3f +#define MFT_IEN_ALL 0x3f +#define MFT_CPCFG_EQ_MODE 0x44 + +#define MFT_CKC_C2CSEL BIT(3) +#define MFT_CKC_C1CSEL BIT(0) + +#define MFT_ICTRL_TFPND BIT(5) +#define MFT_ICTRL_TEPND BIT(4) +#define MFT_ICTRL_TDPND BIT(3) +#define MFT_ICTRL_TCPND BIT(2) +#define MFT_ICTRL_TBPND BIT(1) +#define MFT_ICTRL_TAPND BIT(0) + +#define MFT_MAX_CNT 0xffff +#define MFT_TIMEOUT 0x5000 + +#define DEFAULT_RPM 19800 +#define DEFAULT_PRSC 255 +#define MFT_PULSE_PER_REVOLUTION 2 + +#define MAX_ERROR 1 + typedef struct PWMModule { int irq; uint64_t base_addr; @@ -XXX,XX +XXX,XX @@ static uint64_t pwm_get_duty(QTestState *qts, int module_index, int pwm_index) return pwm_qom_get(qts, path, name); } +static void mft_qom_set(QTestState *qts, int index, const char *name, + uint32_t value) +{ + QDict *response; + char *path = g_strdup_printf("/machine/soc/mft[%d]", index); + + g_test_message("Setting properties %s of mft[%d] with value %u", + name, index, value); + response = qtest_qmp(qts, "{ 'execute': 'qom-set'," + " 'arguments': { 'path': %s, " + " 'property': %s, 'value': %u}}", + path, name, value); + /* The qom set message returns successfully. */ + g_assert_true(qdict_haskey(response, "return")); +} + static uint32_t get_pll(uint32_t con) { return REF_HZ * PLL_FBDV(con) / (PLL_INDV(con) * PLL_OTDV1(con) * PLL_OTDV2(con)); } -static uint64_t read_pclk(QTestState *qts) +static uint64_t read_pclk(QTestState *qts, bool mft) { uint64_t freq = REF_HZ; uint32_t clksel = qtest_readl(qts, CLK_BA + CLKSEL); uint32_t pllcon; uint32_t clkdiv1 = qtest_readl(qts, CLK_BA + CLKDIV1); uint32_t clkdiv2 = qtest_readl(qts, CLK_BA + CLKDIV2); + uint32_t apbdiv = mft ? APB4CKDIV(clkdiv2) : APB3CKDIV(clkdiv2); switch (CPUCKSEL(clksel)) { case 0: @@ -XXX,XX +XXX,XX @@ static uint64_t read_pclk(QTestState *qts) g_assert_not_reached(); } - freq >>= (CLK2CKDIV(clkdiv1) + CLK4CKDIV(clkdiv1) + APB3CKDIV(clkdiv2)); + freq >>= (CLK2CKDIV(clkdiv1) + CLK4CKDIV(clkdiv1) + apbdiv); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t pwm_selector(uint32_t csr) static uint64_t pwm_compute_freq(QTestState *qts, uint32_t ppr, uint32_t csr, uint32_t cnr) { - return read_pclk(qts) / ((ppr + 1) * pwm_selector(csr) * (cnr + 1)); + return read_pclk(qts, false) / ((ppr + 1) * pwm_selector(csr) * (cnr + 1)); } static uint64_t pwm_compute_duty(uint32_t cnr, uint32_t cmr, bool inverted) @@ -XXX,XX +XXX,XX @@ static void pwm_write(QTestState *qts, const TestData *td, unsigned offset, qtest_writel(qts, td->module->base_addr + offset, value); } +static uint8_t mft_readb(QTestState *qts, int index, unsigned offset) +{ + return qtest_readb(qts, MFT_BA(index) + offset); +} + +static uint16_t mft_readw(QTestState *qts, int index, unsigned offset) +{ + return qtest_readw(qts, MFT_BA(index) + offset); +} + +static void mft_writeb(QTestState *qts, int index, unsigned offset, + uint8_t value) +{ + qtest_writeb(qts, MFT_BA(index) + offset, value); +} + +static void mft_writew(QTestState *qts, int index, unsigned offset, + uint16_t value) +{ + return qtest_writew(qts, MFT_BA(index) + offset, value); +} + static uint32_t pwm_read_ppr(QTestState *qts, const TestData *td) { return extract32(pwm_read(qts, td, PPR), ppr_base[pwm_index(td->pwm)], 8); @@ -XXX,XX +XXX,XX @@ static void pwm_write_cmr(QTestState *qts, const TestData *td, uint32_t value) pwm_write(qts, td, td->pwm->cmr_offset, value); } +static int mft_compute_index(const TestData *td) +{ + int index = pwm_module_index(td->module) * ARRAY_SIZE(pwm_list) + + pwm_index(td->pwm); + + g_assert_cmpint(index, <, + ARRAY_SIZE(pwm_module_list) * ARRAY_SIZE(pwm_list)); + + return index; +} + +static void mft_reset_counters(QTestState *qts, int index) +{ + mft_writew(qts, index, MFT_CNT1, MFT_MAX_CNT); + mft_writew(qts, index, MFT_CNT2, MFT_MAX_CNT); + mft_writew(qts, index, MFT_CRA, MFT_MAX_CNT); + mft_writew(qts, index, MFT_CRB, MFT_MAX_CNT); + mft_writew(qts, index, MFT_CPA, MFT_MAX_CNT - MFT_TIMEOUT); + mft_writew(qts, index, MFT_CPB, MFT_MAX_CNT - MFT_TIMEOUT); +} + +static void mft_init(QTestState *qts, const TestData *td) +{ + int index = mft_compute_index(td); + + /* Enable everything */ + mft_writeb(qts, index, MFT_CKC, 0); + mft_writeb(qts, index, MFT_ICLR, MFT_ICLR_ALL); + mft_writeb(qts, index, MFT_MCTRL, MFT_MCTRL_ALL); + mft_writeb(qts, index, MFT_IEN, MFT_IEN_ALL); + mft_writeb(qts, index, MFT_INASEL, 0); + mft_writeb(qts, index, MFT_INBSEL, 0); + + /* Set cpcfg to use EQ mode, same as kernel driver */ + mft_writeb(qts, index, MFT_CPCFG, MFT_CPCFG_EQ_MODE); + + /* Write default counters, timeout and prescaler */ + mft_reset_counters(qts, index); + mft_writeb(qts, index, MFT_PRSC, DEFAULT_PRSC); + + /* Write default max rpm via QMP */ + mft_qom_set(qts, index, "max_rpm[0]", DEFAULT_RPM); + mft_qom_set(qts, index, "max_rpm[1]", DEFAULT_RPM); +} + +static int32_t mft_compute_cnt(uint32_t rpm, uint64_t clk) +{ + uint64_t cnt; + + if (rpm == 0) { + return -1; + } + + cnt = clk * 60 / ((DEFAULT_PRSC + 1) * rpm * MFT_PULSE_PER_REVOLUTION); + if (cnt >= MFT_TIMEOUT) { + return -1; + } + return MFT_MAX_CNT - cnt; +} + +static void mft_verify_rpm(QTestState *qts, const TestData *td, uint64_t duty) +{ + int index = mft_compute_index(td); + uint16_t cnt, cr; + uint32_t rpm = DEFAULT_RPM * duty / MAX_DUTY; + uint64_t clk = read_pclk(qts, true); + int32_t expected_cnt = mft_compute_cnt(rpm, clk); + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + g_test_message( + "verifying rpm for mft[%d]: clk: %lu, duty: %lu, rpm: %u, cnt: %d", + index, clk, duty, rpm, expected_cnt); + + /* Verify rpm for fan A */ + /* Stop capture */ + mft_writeb(qts, index, MFT_CKC, 0); + mft_writeb(qts, index, MFT_ICLR, MFT_ICLR_ALL); + mft_reset_counters(qts, index); + g_assert_cmphex(mft_readw(qts, index, MFT_CNT1), ==, MFT_MAX_CNT); + g_assert_cmphex(mft_readw(qts, index, MFT_CRA), ==, MFT_MAX_CNT); + g_assert_cmphex(mft_readw(qts, index, MFT_CPA), ==, + MFT_MAX_CNT - MFT_TIMEOUT); + /* Start capture */ + mft_writeb(qts, index, MFT_CKC, MFT_CKC_C1CSEL); + g_assert_true(qtest_get_irq(qts, MFT_IRQ(index))); + if (expected_cnt == -1) { + g_assert_cmphex(mft_readb(qts, index, MFT_ICTRL), ==, MFT_ICTRL_TEPND); + } else { + g_assert_cmphex(mft_readb(qts, index, MFT_ICTRL), ==, MFT_ICTRL_TAPND); + cnt = mft_readw(qts, index, MFT_CNT1); + /* + * Due to error in clock measurement and rounding, we might have a small + * error in measuring RPM. + */ + g_assert_cmphex(cnt + MAX_ERROR, >=, expected_cnt); + g_assert_cmphex(cnt, <=, expected_cnt + MAX_ERROR); + cr = mft_readw(qts, index, MFT_CRA); + g_assert_cmphex(cnt, ==, cr); + } + + /* Verify rpm for fan B */ + + qtest_irq_intercept_out(qts, "/machine/soc/a9mpcore/gic"); +} + /* Check pwm registers can be reset to default value */ static void test_init(gconstpointer test_data) { const TestData *td = test_data; - QTestState *qts = qtest_init("-machine quanta-gsj"); + QTestState *qts = qtest_init("-machine npcm750-evb"); int module = pwm_module_index(td->module); int pwm = pwm_index(td->pwm); @@ -XXX,XX +XXX,XX @@ static void test_init(gconstpointer test_data) static void test_oneshot(gconstpointer test_data) { const TestData *td = test_data; - QTestState *qts = qtest_init("-machine quanta-gsj"); + QTestState *qts = qtest_init("-machine npcm750-evb"); int module = pwm_module_index(td->module); int pwm = pwm_index(td->pwm); uint32_t ppr, csr, pcr; @@ -XXX,XX +XXX,XX @@ static void test_oneshot(gconstpointer test_data) static void test_toggle(gconstpointer test_data) { const TestData *td = test_data; - QTestState *qts = qtest_init("-machine quanta-gsj"); + QTestState *qts = qtest_init("-machine npcm750-evb"); int module = pwm_module_index(td->module); int pwm = pwm_index(td->pwm); uint32_t ppr, csr, pcr, cnr, cmr; int i, j, k, l; uint64_t expected_freq, expected_duty; + mft_init(qts, td); + pcr = CH_EN | CH_MOD; for (i = 0; i < ARRAY_SIZE(ppr_list); ++i) { ppr = ppr_list[i]; @@ -XXX,XX +XXX,XX @@ static void test_toggle(gconstpointer test_data) ==, expected_freq); } + /* Test MFT's RPM is correct. */ + mft_verify_rpm(qts, td, expected_duty); + /* Test inverted mode */ expected_duty = pwm_compute_duty(cnr, cmr, true); pwm_write_pcr(qts, td, pcr | CH_INV); -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel. Remove the legacy dead code from the pl110 display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-2-peter.maydell@linaro.org --- hw/display/pl110.c | 53 +++++++--------------------------------------- 1 file changed, 8 insertions(+), 45 deletions(-) diff --git a/hw/display/pl110.c b/hw/display/pl110.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pl110.c +++ b/hw/display/pl110.c @@ -XXX,XX +XXX,XX @@ static const unsigned char *idregs[] = { pl111_id }; -#define BITS 8 -#include "pl110_template.h" -#define BITS 15 -#include "pl110_template.h" -#define BITS 16 -#include "pl110_template.h" -#define BITS 24 -#include "pl110_template.h" #define BITS 32 #include "pl110_template.h" @@ -XXX,XX +XXX,XX @@ static void pl110_update_display(void *opaque) PL110State *s = (PL110State *)opaque; SysBusDevice *sbd; DisplaySurface *surface = qemu_console_surface(s->con); - drawfn* fntable; drawfn fn; - int dest_width; int src_width; int bpp_offset; int first; @@ -XXX,XX +XXX,XX @@ static void pl110_update_display(void *opaque) sbd = SYS_BUS_DEVICE(s); - switch (surface_bits_per_pixel(surface)) { - case 0: - return; - case 8: - fntable = pl110_draw_fn_8; - dest_width = 1; - break; - case 15: - fntable = pl110_draw_fn_15; - dest_width = 2; - break; - case 16: - fntable = pl110_draw_fn_16; - dest_width = 2; - break; - case 24: - fntable = pl110_draw_fn_24; - dest_width = 3; - break; - case 32: - fntable = pl110_draw_fn_32; - dest_width = 4; - break; - default: - fprintf(stderr, "pl110: Bad color depth\n"); - exit(1); - } if (s->cr & PL110_CR_BGR) bpp_offset = 0; else @@ -XXX,XX +XXX,XX @@ static void pl110_update_display(void *opaque) } } - if (s->cr & PL110_CR_BEBO) - fn = fntable[s->bpp + 8 + bpp_offset]; - else if (s->cr & PL110_CR_BEPO) - fn = fntable[s->bpp + 16 + bpp_offset]; - else - fn = fntable[s->bpp + bpp_offset]; + if (s->cr & PL110_CR_BEBO) { + fn = pl110_draw_fn_32[s->bpp + 8 + bpp_offset]; + } else if (s->cr & PL110_CR_BEPO) { + fn = pl110_draw_fn_32[s->bpp + 16 + bpp_offset]; + } else { + fn = pl110_draw_fn_32[s->bpp + bpp_offset]; + } src_width = s->cols; switch (s->bpp) { @@ -XXX,XX +XXX,XX @@ static void pl110_update_display(void *opaque) src_width <<= 2; break; } - dest_width *= s->cols; first = 0; if (s->invalidate) { framebuffer_update_memory_section(&s->fbsection, @@ -XXX,XX +XXX,XX @@ static void pl110_update_display(void *opaque) framebuffer_update_display(surface, &s->fbsection, s->cols, s->rows, - src_width, dest_width, 0, + src_width, s->cols * 4, 0, s->invalidate, fn, s->palette, &first, &last); -- 2.20.1 The pl110_template.h header has a doubly-nested multiple-include pattern: * pl110.c includes it once for each host bit depth (now always 32) * every time it is included, it includes itself 6 times, to account for multiple guest device pixel and byte orders Now we only have to deal with 32-bit host bit depths, we can move the code corresponding to the outer layer of this double-nesting to be directly in pl110.c and reduce the template header to a single layer of nesting. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-3-peter.maydell@linaro.org --- hw/display/pl110_template.h | 100 +----------------------------------- hw/display/pl110.c | 79 ++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+), 99 deletions(-) diff --git a/hw/display/pl110_template.h b/hw/display/pl110_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pl110_template.h +++ b/hw/display/pl110_template.h @@ -XXX,XX +XXX,XX @@ */ #ifndef ORDER - -#if BITS == 8 -#define COPY_PIXEL(to, from) *(to++) = from -#elif BITS == 15 || BITS == 16 -#define COPY_PIXEL(to, from) do { *(uint16_t *)to = from; to += 2; } while (0) -#elif BITS == 24 -#define COPY_PIXEL(to, from) \ - do { \ - *(to++) = from; \ - *(to++) = (from) >> 8; \ - *(to++) = (from) >> 16; \ - } while (0) -#elif BITS == 32 -#define COPY_PIXEL(to, from) do { *(uint32_t *)to = from; to += 4; } while (0) -#else -#error unknown bit depth +#error "pl110_template.h is only for inclusion by pl110.c" #endif -#undef RGB -#define BORDER bgr -#define ORDER 0 -#include "pl110_template.h" -#define ORDER 1 -#include "pl110_template.h" -#define ORDER 2 -#include "pl110_template.h" -#undef BORDER -#define RGB -#define BORDER rgb -#define ORDER 0 -#include "pl110_template.h" -#define ORDER 1 -#include "pl110_template.h" -#define ORDER 2 -#include "pl110_template.h" -#undef BORDER - -static drawfn glue(pl110_draw_fn_,BITS)[48] = -{ - glue(pl110_draw_line1_lblp_bgr,BITS), - glue(pl110_draw_line2_lblp_bgr,BITS), - glue(pl110_draw_line4_lblp_bgr,BITS), - glue(pl110_draw_line8_lblp_bgr,BITS), - glue(pl110_draw_line16_555_lblp_bgr,BITS), - glue(pl110_draw_line32_lblp_bgr,BITS), - glue(pl110_draw_line16_lblp_bgr,BITS), - glue(pl110_draw_line12_lblp_bgr,BITS), - - glue(pl110_draw_line1_bbbp_bgr,BITS), - glue(pl110_draw_line2_bbbp_bgr,BITS), - glue(pl110_draw_line4_bbbp_bgr,BITS), - glue(pl110_draw_line8_bbbp_bgr,BITS), - glue(pl110_draw_line16_555_bbbp_bgr,BITS), - glue(pl110_draw_line32_bbbp_bgr,BITS), - glue(pl110_draw_line16_bbbp_bgr,BITS), - glue(pl110_draw_line12_bbbp_bgr,BITS), - - glue(pl110_draw_line1_lbbp_bgr,BITS), - glue(pl110_draw_line2_lbbp_bgr,BITS), - glue(pl110_draw_line4_lbbp_bgr,BITS), - glue(pl110_draw_line8_lbbp_bgr,BITS), - glue(pl110_draw_line16_555_lbbp_bgr,BITS), - glue(pl110_draw_line32_lbbp_bgr,BITS), - glue(pl110_draw_line16_lbbp_bgr,BITS), - glue(pl110_draw_line12_lbbp_bgr,BITS), - - glue(pl110_draw_line1_lblp_rgb,BITS), - glue(pl110_draw_line2_lblp_rgb,BITS), - glue(pl110_draw_line4_lblp_rgb,BITS), - glue(pl110_draw_line8_lblp_rgb,BITS), - glue(pl110_draw_line16_555_lblp_rgb,BITS), - glue(pl110_draw_line32_lblp_rgb,BITS), - glue(pl110_draw_line16_lblp_rgb,BITS), - glue(pl110_draw_line12_lblp_rgb,BITS), - - glue(pl110_draw_line1_bbbp_rgb,BITS), - glue(pl110_draw_line2_bbbp_rgb,BITS), - glue(pl110_draw_line4_bbbp_rgb,BITS), - glue(pl110_draw_line8_bbbp_rgb,BITS), - glue(pl110_draw_line16_555_bbbp_rgb,BITS), - glue(pl110_draw_line32_bbbp_rgb,BITS), - glue(pl110_draw_line16_bbbp_rgb,BITS), - glue(pl110_draw_line12_bbbp_rgb,BITS), - - glue(pl110_draw_line1_lbbp_rgb,BITS), - glue(pl110_draw_line2_lbbp_rgb,BITS), - glue(pl110_draw_line4_lbbp_rgb,BITS), - glue(pl110_draw_line8_lbbp_rgb,BITS), - glue(pl110_draw_line16_555_lbbp_rgb,BITS), - glue(pl110_draw_line32_lbbp_rgb,BITS), - glue(pl110_draw_line16_lbbp_rgb,BITS), - glue(pl110_draw_line12_lbbp_rgb,BITS), -}; - -#undef BITS -#undef COPY_PIXEL - -#else - #if ORDER == 0 #define NAME glue(glue(lblp_, BORDER), BITS) #ifdef HOST_WORDS_BIGENDIAN @@ -XXX,XX +XXX,XX @@ static void glue(pl110_draw_line12_,NAME)(void *opaque, uint8_t *d, const uint8_ #undef NAME #undef SWAP_WORDS #undef ORDER - -#endif diff --git a/hw/display/pl110.c b/hw/display/pl110.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pl110.c +++ b/hw/display/pl110.c @@ -XXX,XX +XXX,XX @@ static const unsigned char *idregs[] = { }; #define BITS 32 +#define COPY_PIXEL(to, from) do { *(uint32_t *)to = from; to += 4; } while (0) + +#undef RGB +#define BORDER bgr +#define ORDER 0 #include "pl110_template.h" +#define ORDER 1 +#include "pl110_template.h" +#define ORDER 2 +#include "pl110_template.h" +#undef BORDER +#define RGB +#define BORDER rgb +#define ORDER 0 +#include "pl110_template.h" +#define ORDER 1 +#include "pl110_template.h" +#define ORDER 2 +#include "pl110_template.h" +#undef BORDER + +static drawfn pl110_draw_fn_32[48] = { + pl110_draw_line1_lblp_bgr32, + pl110_draw_line2_lblp_bgr32, + pl110_draw_line4_lblp_bgr32, + pl110_draw_line8_lblp_bgr32, + pl110_draw_line16_555_lblp_bgr32, + pl110_draw_line32_lblp_bgr32, + pl110_draw_line16_lblp_bgr32, + pl110_draw_line12_lblp_bgr32, + + pl110_draw_line1_bbbp_bgr32, + pl110_draw_line2_bbbp_bgr32, + pl110_draw_line4_bbbp_bgr32, + pl110_draw_line8_bbbp_bgr32, + pl110_draw_line16_555_bbbp_bgr32, + pl110_draw_line32_bbbp_bgr32, + pl110_draw_line16_bbbp_bgr32, + pl110_draw_line12_bbbp_bgr32, + + pl110_draw_line1_lbbp_bgr32, + pl110_draw_line2_lbbp_bgr32, + pl110_draw_line4_lbbp_bgr32, + pl110_draw_line8_lbbp_bgr32, + pl110_draw_line16_555_lbbp_bgr32, + pl110_draw_line32_lbbp_bgr32, + pl110_draw_line16_lbbp_bgr32, + pl110_draw_line12_lbbp_bgr32, + + pl110_draw_line1_lblp_rgb32, + pl110_draw_line2_lblp_rgb32, + pl110_draw_line4_lblp_rgb32, + pl110_draw_line8_lblp_rgb32, + pl110_draw_line16_555_lblp_rgb32, + pl110_draw_line32_lblp_rgb32, + pl110_draw_line16_lblp_rgb32, + pl110_draw_line12_lblp_rgb32, + + pl110_draw_line1_bbbp_rgb32, + pl110_draw_line2_bbbp_rgb32, + pl110_draw_line4_bbbp_rgb32, + pl110_draw_line8_bbbp_rgb32, + pl110_draw_line16_555_bbbp_rgb32, + pl110_draw_line32_bbbp_rgb32, + pl110_draw_line16_bbbp_rgb32, + pl110_draw_line12_bbbp_rgb32, + + pl110_draw_line1_lbbp_rgb32, + pl110_draw_line2_lbbp_rgb32, + pl110_draw_line4_lbbp_rgb32, + pl110_draw_line8_lbbp_rgb32, + pl110_draw_line16_555_lbbp_rgb32, + pl110_draw_line32_lbbp_rgb32, + pl110_draw_line16_lbbp_rgb32, + pl110_draw_line12_lbbp_rgb32, +}; + +#undef BITS +#undef COPY_PIXEL + static int pl110_enabled(PL110State *s) { -- 2.20.1 BITS is always 32, so remove all uses of it from the template header, by dropping the trailing '32' from the draw function names and not constructing the name of rgb_to_pixel32() via the glue() macro. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-4-peter.maydell@linaro.org --- hw/display/pl110_template.h | 20 +++---- hw/display/pl110.c | 113 ++++++++++++++++++------------------ 2 files changed, 65 insertions(+), 68 deletions(-) diff --git a/hw/display/pl110_template.h b/hw/display/pl110_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pl110_template.h +++ b/hw/display/pl110_template.h @@ -XXX,XX +XXX,XX @@ #endif #if ORDER == 0 -#define NAME glue(glue(lblp_, BORDER), BITS) +#define NAME glue(lblp_, BORDER) #ifdef HOST_WORDS_BIGENDIAN #define SWAP_WORDS 1 #endif #elif ORDER == 1 -#define NAME glue(glue(bbbp_, BORDER), BITS) +#define NAME glue(bbbp_, BORDER) #ifndef HOST_WORDS_BIGENDIAN #define SWAP_WORDS 1 #endif #else #define SWAP_PIXELS 1 -#define NAME glue(glue(lbbp_, BORDER), BITS) +#define NAME glue(lbbp_, BORDER) #ifdef HOST_WORDS_BIGENDIAN #define SWAP_WORDS 1 #endif @@ -XXX,XX +XXX,XX @@ static void glue(pl110_draw_line16_,NAME)(void *opaque, uint8_t *d, const uint8_ MSB = (data & 0x1f) << 3; data >>= 5; #endif - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); LSB = (data & 0x1f) << 3; data >>= 5; g = (data & 0x3f) << 2; data >>= 6; MSB = (data & 0x1f) << 3; data >>= 5; - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); #undef MSB #undef LSB width -= 2; @@ -XXX,XX +XXX,XX @@ static void glue(pl110_draw_line32_,NAME)(void *opaque, uint8_t *d, const uint8_ g = (data >> 16) & 0xff; MSB = (data >> 8) & 0xff; #endif - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); #undef MSB #undef LSB width--; @@ -XXX,XX +XXX,XX @@ static void glue(pl110_draw_line16_555_,NAME)(void *opaque, uint8_t *d, const ui data >>= 5; MSB = (data & 0x1f) << 3; data >>= 5; - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); LSB = (data & 0x1f) << 3; data >>= 5; g = (data & 0x1f) << 3; data >>= 5; MSB = (data & 0x1f) << 3; data >>= 6; - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); #undef MSB #undef LSB width -= 2; @@ -XXX,XX +XXX,XX @@ static void glue(pl110_draw_line12_,NAME)(void *opaque, uint8_t *d, const uint8_ data >>= 4; MSB = (data & 0xf) << 4; data >>= 8; - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); LSB = (data & 0xf) << 4; data >>= 4; g = (data & 0xf) << 4; data >>= 4; MSB = (data & 0xf) << 4; data >>= 8; - COPY_PIXEL(d, glue(rgb_to_pixel,BITS)(r, g, b)); + COPY_PIXEL(d, rgb_to_pixel32(r, g, b)); #undef MSB #undef LSB width -= 2; diff --git a/hw/display/pl110.c b/hw/display/pl110.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pl110.c +++ b/hw/display/pl110.c @@ -XXX,XX +XXX,XX @@ static const unsigned char *idregs[] = { pl111_id }; -#define BITS 32 #define COPY_PIXEL(to, from) do { *(uint32_t *)to = from; to += 4; } while (0) #undef RGB @@ -XXX,XX +XXX,XX @@ static const unsigned char *idregs[] = { #include "pl110_template.h" #undef BORDER -static drawfn pl110_draw_fn_32[48] = { - pl110_draw_line1_lblp_bgr32, - pl110_draw_line2_lblp_bgr32, - pl110_draw_line4_lblp_bgr32, - pl110_draw_line8_lblp_bgr32, - pl110_draw_line16_555_lblp_bgr32, - pl110_draw_line32_lblp_bgr32, - pl110_draw_line16_lblp_bgr32, - pl110_draw_line12_lblp_bgr32, - - pl110_draw_line1_bbbp_bgr32, - pl110_draw_line2_bbbp_bgr32, - pl110_draw_line4_bbbp_bgr32, - pl110_draw_line8_bbbp_bgr32, - pl110_draw_line16_555_bbbp_bgr32, - pl110_draw_line32_bbbp_bgr32, - pl110_draw_line16_bbbp_bgr32, - pl110_draw_line12_bbbp_bgr32, - - pl110_draw_line1_lbbp_bgr32, - pl110_draw_line2_lbbp_bgr32, - pl110_draw_line4_lbbp_bgr32, - pl110_draw_line8_lbbp_bgr32, - pl110_draw_line16_555_lbbp_bgr32, - pl110_draw_line32_lbbp_bgr32, - pl110_draw_line16_lbbp_bgr32, - pl110_draw_line12_lbbp_bgr32, - - pl110_draw_line1_lblp_rgb32, - pl110_draw_line2_lblp_rgb32, - pl110_draw_line4_lblp_rgb32, - pl110_draw_line8_lblp_rgb32, - pl110_draw_line16_555_lblp_rgb32, - pl110_draw_line32_lblp_rgb32, - pl110_draw_line16_lblp_rgb32, - pl110_draw_line12_lblp_rgb32, - - pl110_draw_line1_bbbp_rgb32, - pl110_draw_line2_bbbp_rgb32, - pl110_draw_line4_bbbp_rgb32, - pl110_draw_line8_bbbp_rgb32, - pl110_draw_line16_555_bbbp_rgb32, - pl110_draw_line32_bbbp_rgb32, - pl110_draw_line16_bbbp_rgb32, - pl110_draw_line12_bbbp_rgb32, - - pl110_draw_line1_lbbp_rgb32, - pl110_draw_line2_lbbp_rgb32, - pl110_draw_line4_lbbp_rgb32, - pl110_draw_line8_lbbp_rgb32, - pl110_draw_line16_555_lbbp_rgb32, - pl110_draw_line32_lbbp_rgb32, - pl110_draw_line16_lbbp_rgb32, - pl110_draw_line12_lbbp_rgb32, -}; - -#undef BITS #undef COPY_PIXEL +static drawfn pl110_draw_fn_32[48] = { + pl110_draw_line1_lblp_bgr, + pl110_draw_line2_lblp_bgr, + pl110_draw_line4_lblp_bgr, + pl110_draw_line8_lblp_bgr, + pl110_draw_line16_555_lblp_bgr, + pl110_draw_line32_lblp_bgr, + pl110_draw_line16_lblp_bgr, + pl110_draw_line12_lblp_bgr, + + pl110_draw_line1_bbbp_bgr, + pl110_draw_line2_bbbp_bgr, + pl110_draw_line4_bbbp_bgr, + pl110_draw_line8_bbbp_bgr, + pl110_draw_line16_555_bbbp_bgr, + pl110_draw_line32_bbbp_bgr, + pl110_draw_line16_bbbp_bgr, + pl110_draw_line12_bbbp_bgr, + + pl110_draw_line1_lbbp_bgr, + pl110_draw_line2_lbbp_bgr, + pl110_draw_line4_lbbp_bgr, + pl110_draw_line8_lbbp_bgr, + pl110_draw_line16_555_lbbp_bgr, + pl110_draw_line32_lbbp_bgr, + pl110_draw_line16_lbbp_bgr, + pl110_draw_line12_lbbp_bgr, + + pl110_draw_line1_lblp_rgb, + pl110_draw_line2_lblp_rgb, + pl110_draw_line4_lblp_rgb, + pl110_draw_line8_lblp_rgb, + pl110_draw_line16_555_lblp_rgb, + pl110_draw_line32_lblp_rgb, + pl110_draw_line16_lblp_rgb, + pl110_draw_line12_lblp_rgb, + + pl110_draw_line1_bbbp_rgb, + pl110_draw_line2_bbbp_rgb, + pl110_draw_line4_bbbp_rgb, + pl110_draw_line8_bbbp_rgb, + pl110_draw_line16_555_bbbp_rgb, + pl110_draw_line32_bbbp_rgb, + pl110_draw_line16_bbbp_rgb, + pl110_draw_line12_bbbp_rgb, + + pl110_draw_line1_lbbp_rgb, + pl110_draw_line2_lbbp_rgb, + pl110_draw_line4_lbbp_rgb, + pl110_draw_line8_lbbp_rgb, + pl110_draw_line16_555_lbbp_rgb, + pl110_draw_line32_lbbp_rgb, + pl110_draw_line16_lbbp_rgb, + pl110_draw_line12_lbbp_rgb, +}; static int pl110_enabled(PL110State *s) { -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel. Remove the legacy dead code from the pxa2xx_lcd display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-5-peter.maydell@linaro.org --- hw/display/pxa2xx_lcd.c | 79 +++++++++-------------------------------- 1 file changed, 17 insertions(+), 62 deletions(-) diff --git a/hw/display/pxa2xx_lcd.c b/hw/display/pxa2xx_lcd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_lcd.c +++ b/hw/display/pxa2xx_lcd.c @@ -XXX,XX +XXX,XX @@ struct PXA2xxLCDState { int invalidated; QemuConsole *con; - drawfn *line_fn[2]; int dest_width; int xres, yres; int pal_for; @@ -XXX,XX +XXX,XX @@ typedef struct QEMU_PACKED { #define LDCMD_SOFINT (1 << 22) #define LDCMD_PAL (1 << 26) +#define BITS 32 +#include "pxa2xx_template.h" + /* Route internal interrupt lines to the global IC */ static void pxa2xx_lcdc_int_update(PXA2xxLCDState *s) { @@ -XXX,XX +XXX,XX @@ static void pxa2xx_palette_parse(PXA2xxLCDState *s, int ch, int bpp) } } +static inline drawfn pxa2xx_drawfn(PXA2xxLCDState *s) +{ + if (s->transp) { + return pxa2xx_draw_fn_32t[s->bpp]; + } else { + return pxa2xx_draw_fn_32[s->bpp]; + } +} + static void pxa2xx_lcdc_dma0_redraw_rot0(PXA2xxLCDState *s, hwaddr addr, int *miny, int *maxy) { DisplaySurface *surface = qemu_console_surface(s->con); int src_width, dest_width; - drawfn fn = NULL; - if (s->dest_width) - fn = s->line_fn[s->transp][s->bpp]; + drawfn fn = pxa2xx_drawfn(s); if (!fn) return; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot90(PXA2xxLCDState *s, { DisplaySurface *surface = qemu_console_surface(s->con); int src_width, dest_width; - drawfn fn = NULL; - if (s->dest_width) - fn = s->line_fn[s->transp][s->bpp]; + drawfn fn = pxa2xx_drawfn(s); if (!fn) return; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot180(PXA2xxLCDState *s, { DisplaySurface *surface = qemu_console_surface(s->con); int src_width, dest_width; - drawfn fn = NULL; - if (s->dest_width) { - fn = s->line_fn[s->transp][s->bpp]; - } + drawfn fn = pxa2xx_drawfn(s); if (!fn) { return; } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot270(PXA2xxLCDState *s, { DisplaySurface *surface = qemu_console_surface(s->con); int src_width, dest_width; - drawfn fn = NULL; - if (s->dest_width) { - fn = s->line_fn[s->transp][s->bpp]; - } + drawfn fn = pxa2xx_drawfn(s); if (!fn) { return; } @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_pxa2xx_lcdc = { } }; -#define BITS 8 -#include "pxa2xx_template.h" -#define BITS 15 -#include "pxa2xx_template.h" -#define BITS 16 -#include "pxa2xx_template.h" -#define BITS 24 -#include "pxa2xx_template.h" -#define BITS 32 -#include "pxa2xx_template.h" - static const GraphicHwOps pxa2xx_ops = { .invalidate = pxa2xx_invalidate_display, .gfx_update = pxa2xx_update_display, @@ -XXX,XX +XXX,XX @@ PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, hwaddr base, qemu_irq irq) { PXA2xxLCDState *s; - DisplaySurface *surface; s = (PXA2xxLCDState *) g_malloc0(sizeof(PXA2xxLCDState)); s->invalidated = 1; @@ -XXX,XX +XXX,XX @@ PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, memory_region_add_subregion(sysmem, base, &s->iomem); s->con = graphic_console_init(NULL, 0, &pxa2xx_ops, s); - surface = qemu_console_surface(s->con); - - switch (surface_bits_per_pixel(surface)) { - case 0: - s->dest_width = 0; - break; - case 8: - s->line_fn[0] = pxa2xx_draw_fn_8; - s->line_fn[1] = pxa2xx_draw_fn_8t; - s->dest_width = 1; - break; - case 15: - s->line_fn[0] = pxa2xx_draw_fn_15; - s->line_fn[1] = pxa2xx_draw_fn_15t; - s->dest_width = 2; - break; - case 16: - s->line_fn[0] = pxa2xx_draw_fn_16; - s->line_fn[1] = pxa2xx_draw_fn_16t; - s->dest_width = 2; - break; - case 24: - s->line_fn[0] = pxa2xx_draw_fn_24; - s->line_fn[1] = pxa2xx_draw_fn_24t; - s->dest_width = 3; - break; - case 32: - s->line_fn[0] = pxa2xx_draw_fn_32; - s->line_fn[1] = pxa2xx_draw_fn_32t; - s->dest_width = 4; - break; - default: - fprintf(stderr, "%s: Bad color depth\n", __func__); - exit(1); - } + s->dest_width = 4; vmstate_register(NULL, 0, &vmstate_pxa2xx_lcdc, s); -- 2.20.1 Since the dest_width is now always 4 because the output surface is 32bpp, we can replace the dest_width state field with a constant. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-6-peter.maydell@linaro.org --- hw/display/pxa2xx_lcd.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/hw/display/pxa2xx_lcd.c b/hw/display/pxa2xx_lcd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_lcd.c +++ b/hw/display/pxa2xx_lcd.c @@ -XXX,XX +XXX,XX @@ typedef struct QEMU_PACKED { #define LDCMD_SOFINT (1 << 22) #define LDCMD_PAL (1 << 26) +/* Size of a pixel in the QEMU UI output surface, in bytes */ +#define DEST_PIXEL_WIDTH 4 + #define BITS 32 #include "pxa2xx_template.h" @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot0(PXA2xxLCDState *s, else if (s->bpp > pxa_lcdc_8bpp) src_width *= 2; - dest_width = s->xres * s->dest_width; + dest_width = s->xres * DEST_PIXEL_WIDTH; *miny = 0; if (s->invalidated) { framebuffer_update_memory_section(&s->fbsection, s->sysmem, addr, s->yres, src_width); } framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, dest_width, s->dest_width, + src_width, dest_width, DEST_PIXEL_WIDTH, s->invalidated, fn, s->dma_ch[0].palette, miny, maxy); } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot90(PXA2xxLCDState *s, else if (s->bpp > pxa_lcdc_8bpp) src_width *= 2; - dest_width = s->yres * s->dest_width; + dest_width = s->yres * DEST_PIXEL_WIDTH; *miny = 0; if (s->invalidated) { framebuffer_update_memory_section(&s->fbsection, s->sysmem, addr, s->yres, src_width); } framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, s->dest_width, -dest_width, + src_width, DEST_PIXEL_WIDTH, -dest_width, s->invalidated, fn, s->dma_ch[0].palette, miny, maxy); @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot180(PXA2xxLCDState *s, src_width *= 2; } - dest_width = s->xres * s->dest_width; + dest_width = s->xres * DEST_PIXEL_WIDTH; *miny = 0; if (s->invalidated) { framebuffer_update_memory_section(&s->fbsection, s->sysmem, addr, s->yres, src_width); } framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, -dest_width, -s->dest_width, + src_width, -dest_width, -DEST_PIXEL_WIDTH, s->invalidated, fn, s->dma_ch[0].palette, miny, maxy); } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_lcdc_dma0_redraw_rot270(PXA2xxLCDState *s, src_width *= 2; } - dest_width = s->yres * s->dest_width; + dest_width = s->yres * DEST_PIXEL_WIDTH; *miny = 0; if (s->invalidated) { framebuffer_update_memory_section(&s->fbsection, s->sysmem, addr, s->yres, src_width); } framebuffer_update_display(surface, &s->fbsection, s->xres, s->yres, - src_width, -s->dest_width, dest_width, + src_width, -DEST_PIXEL_WIDTH, dest_width, s->invalidated, fn, s->dma_ch[0].palette, miny, maxy); @@ -XXX,XX +XXX,XX @@ PXA2xxLCDState *pxa2xx_lcdc_init(MemoryRegion *sysmem, memory_region_add_subregion(sysmem, base, &s->iomem); s->con = graphic_console_init(NULL, 0, &pxa2xx_ops, s); - s->dest_width = 4; vmstate_register(NULL, 0, &vmstate_pxa2xx_lcdc, s); -- 2.20.1 Now that BITS is always 32, expand out all its uses in the template header, including removing now-useless uses of the glue() macro. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-7-peter.maydell@linaro.org --- hw/display/pxa2xx_template.h | 110 ++++++++++++++--------------------- 1 file changed, 45 insertions(+), 65 deletions(-) diff --git a/hw/display/pxa2xx_template.h b/hw/display/pxa2xx_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_template.h +++ b/hw/display/pxa2xx_template.h @@ -XXX,XX +XXX,XX @@ */ # define SKIP_PIXEL(to) to += deststep -#if BITS == 8 -# define COPY_PIXEL(to, from) do { *to = from; SKIP_PIXEL(to); } while (0) -#elif BITS == 15 || BITS == 16 -# define COPY_PIXEL(to, from) \ - do { \ - *(uint16_t *) to = from; \ - SKIP_PIXEL(to); \ - } while (0) -#elif BITS == 24 -# define COPY_PIXEL(to, from) \ - do { \ - *(uint16_t *) to = from; \ - *(to + 2) = (from) >> 16; \ - SKIP_PIXEL(to); \ - } while (0) -#elif BITS == 32 # define COPY_PIXEL(to, from) \ do { \ *(uint32_t *) to = from; \ SKIP_PIXEL(to); \ } while (0) -#else -# error unknown bit depth -#endif #ifdef HOST_WORDS_BIGENDIAN # define SWAP_WORDS 1 @@ -XXX,XX +XXX,XX @@ #define FN_2(x) FN(x + 1) FN(x) #define FN_4(x) FN_2(x + 2) FN_2(x) -static void glue(pxa2xx_draw_line2_, BITS)(void *opaque, +static void pxa2xx_draw_line2(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t *palette = opaque; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line2_, BITS)(void *opaque, } } -static void glue(pxa2xx_draw_line4_, BITS)(void *opaque, +static void pxa2xx_draw_line4(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t *palette = opaque; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line4_, BITS)(void *opaque, } } -static void glue(pxa2xx_draw_line8_, BITS)(void *opaque, +static void pxa2xx_draw_line8(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t *palette = opaque; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line8_, BITS)(void *opaque, } } -static void glue(pxa2xx_draw_line16_, BITS)(void *opaque, +static void pxa2xx_draw_line16(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line16_, BITS)(void *opaque, data >>= 6; r = (data & 0x1f) << 3; data >>= 5; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); b = (data & 0x1f) << 3; data >>= 5; g = (data & 0x3f) << 2; data >>= 6; r = (data & 0x1f) << 3; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 2; src += 4; } } -static void glue(pxa2xx_draw_line16t_, BITS)(void *opaque, +static void pxa2xx_draw_line16t(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line16t_, BITS)(void *opaque, if (data & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); data >>= 1; b = (data & 0x1f) << 3; data >>= 5; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line16t_, BITS)(void *opaque, if (data & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 2; src += 4; } } -static void glue(pxa2xx_draw_line18_, BITS)(void *opaque, +static void pxa2xx_draw_line18(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line18_, BITS)(void *opaque, g = (data & 0x3f) << 2; data >>= 6; r = (data & 0x3f) << 2; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 1; src += 4; } } /* The wicked packed format */ -static void glue(pxa2xx_draw_line18p_, BITS)(void *opaque, +static void pxa2xx_draw_line18p(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data[3]; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line18p_, BITS)(void *opaque, data[0] >>= 6; r = (data[0] & 0x3f) << 2; data[0] >>= 12; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); b = (data[0] & 0x3f) << 2; data[0] >>= 6; g = ((data[1] & 0xf) << 4) | (data[0] << 2); data[1] >>= 4; r = (data[1] & 0x3f) << 2; data[1] >>= 12; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); b = (data[1] & 0x3f) << 2; data[1] >>= 6; g = (data[1] & 0x3f) << 2; data[1] >>= 6; r = ((data[2] & 0x3) << 6) | (data[1] << 2); data[2] >>= 8; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); b = (data[2] & 0x3f) << 2; data[2] >>= 6; g = (data[2] & 0x3f) << 2; data[2] >>= 6; r = data[2] << 2; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 4; } } -static void glue(pxa2xx_draw_line19_, BITS)(void *opaque, +static void pxa2xx_draw_line19(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line19_, BITS)(void *opaque, if (data & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 1; src += 4; } } /* The wicked packed format */ -static void glue(pxa2xx_draw_line19p_, BITS)(void *opaque, +static void pxa2xx_draw_line19p(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data[3]; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line19p_, BITS)(void *opaque, if (data[0] & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); data[0] >>= 6; b = (data[0] & 0x3f) << 2; data[0] >>= 6; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line19p_, BITS)(void *opaque, if (data[1] & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); data[1] >>= 6; b = (data[1] & 0x3f) << 2; data[1] >>= 6; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line19p_, BITS)(void *opaque, if (data[2] & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); data[2] >>= 6; b = (data[2] & 0x3f) << 2; data[2] >>= 6; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line19p_, BITS)(void *opaque, if (data[2] & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 4; } } -static void glue(pxa2xx_draw_line24_, BITS)(void *opaque, +static void pxa2xx_draw_line24(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line24_, BITS)(void *opaque, g = data & 0xff; data >>= 8; r = data & 0xff; - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 1; src += 4; } } -static void glue(pxa2xx_draw_line24t_, BITS)(void *opaque, +static void pxa2xx_draw_line24t(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line24t_, BITS)(void *opaque, if (data & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 1; src += 4; } } -static void glue(pxa2xx_draw_line25_, BITS)(void *opaque, +static void pxa2xx_draw_line25(void *opaque, uint8_t *dest, const uint8_t *src, int width, int deststep) { uint32_t data; @@ -XXX,XX +XXX,XX @@ static void glue(pxa2xx_draw_line25_, BITS)(void *opaque, if (data & 1) SKIP_PIXEL(dest); else - COPY_PIXEL(dest, glue(rgb_to_pixel, BITS)(r, g, b)); + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); width -= 1; src += 4; } } /* Overlay planes disabled, no transparency */ -static drawfn glue(pxa2xx_draw_fn_, BITS)[16] = +static drawfn pxa2xx_draw_fn_32[16] = { [0 ... 0xf] = NULL, - [pxa_lcdc_2bpp] = glue(pxa2xx_draw_line2_, BITS), - [pxa_lcdc_4bpp] = glue(pxa2xx_draw_line4_, BITS), - [pxa_lcdc_8bpp] = glue(pxa2xx_draw_line8_, BITS), - [pxa_lcdc_16bpp] = glue(pxa2xx_draw_line16_, BITS), - [pxa_lcdc_18bpp] = glue(pxa2xx_draw_line18_, BITS), - [pxa_lcdc_18pbpp] = glue(pxa2xx_draw_line18p_, BITS), - [pxa_lcdc_24bpp] = glue(pxa2xx_draw_line24_, BITS), + [pxa_lcdc_2bpp] = pxa2xx_draw_line2, + [pxa_lcdc_4bpp] = pxa2xx_draw_line4, + [pxa_lcdc_8bpp] = pxa2xx_draw_line8, + [pxa_lcdc_16bpp] = pxa2xx_draw_line16, + [pxa_lcdc_18bpp] = pxa2xx_draw_line18, + [pxa_lcdc_18pbpp] = pxa2xx_draw_line18p, + [pxa_lcdc_24bpp] = pxa2xx_draw_line24, }; /* Overlay planes enabled, transparency used */ -static drawfn glue(glue(pxa2xx_draw_fn_, BITS), t)[16] = +static drawfn pxa2xx_draw_fn_32t[16] = { [0 ... 0xf] = NULL, - [pxa_lcdc_4bpp] = glue(pxa2xx_draw_line4_, BITS), - [pxa_lcdc_8bpp] = glue(pxa2xx_draw_line8_, BITS), - [pxa_lcdc_16bpp] = glue(pxa2xx_draw_line16t_, BITS), - [pxa_lcdc_19bpp] = glue(pxa2xx_draw_line19_, BITS), - [pxa_lcdc_19pbpp] = glue(pxa2xx_draw_line19p_, BITS), - [pxa_lcdc_24bpp] = glue(pxa2xx_draw_line24t_, BITS), - [pxa_lcdc_25bpp] = glue(pxa2xx_draw_line25_, BITS), + [pxa_lcdc_4bpp] = pxa2xx_draw_line4, + [pxa_lcdc_8bpp] = pxa2xx_draw_line8, + [pxa_lcdc_16bpp] = pxa2xx_draw_line16t, + [pxa_lcdc_19bpp] = pxa2xx_draw_line19, + [pxa_lcdc_19pbpp] = pxa2xx_draw_line19p, + [pxa_lcdc_24bpp] = pxa2xx_draw_line24t, + [pxa_lcdc_25bpp] = pxa2xx_draw_line25, }; -#undef BITS #undef COPY_PIXEL #undef SKIP_PIXEL -- 2.20.1 We're about to move code from the template header into pxa2xx_lcd.c. Before doing that, make coding style fixes so checkpatch doesn't complain about the patch which moves the code. This commit fixes missing braces in the SKIP_PIXEL() macro definition and in if() statements. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-8-peter.maydell@linaro.org --- hw/display/pxa2xx_template.h | 47 +++++++++++++++++++++--------------- 1 file changed, 28 insertions(+), 19 deletions(-) diff --git a/hw/display/pxa2xx_template.h b/hw/display/pxa2xx_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_template.h +++ b/hw/display/pxa2xx_template.h @@ -XXX,XX +XXX,XX @@ * Framebuffer format conversion routines. */ -# define SKIP_PIXEL(to) to += deststep +# define SKIP_PIXEL(to) do { to += deststep; } while (0) # define COPY_PIXEL(to, from) \ do { \ *(uint32_t *) to = from; \ @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line16t(void *opaque, data >>= 5; r = (data & 0x1f) << 3; data >>= 5; - if (data & 1) + if (data & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } data >>= 1; b = (data & 0x1f) << 3; data >>= 5; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line16t(void *opaque, data >>= 5; r = (data & 0x1f) << 3; data >>= 5; - if (data & 1) + if (data & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } width -= 2; src += 4; } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19(void *opaque, data >>= 6; r = (data & 0x3f) << 2; data >>= 6; - if (data & 1) + if (data & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } width -= 1; src += 4; } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19p(void *opaque, data[0] >>= 6; r = (data[0] & 0x3f) << 2; data[0] >>= 6; - if (data[0] & 1) + if (data[0] & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } data[0] >>= 6; b = (data[0] & 0x3f) << 2; data[0] >>= 6; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19p(void *opaque, data[1] >>= 4; r = (data[1] & 0x3f) << 2; data[1] >>= 6; - if (data[1] & 1) + if (data[1] & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } data[1] >>= 6; b = (data[1] & 0x3f) << 2; data[1] >>= 6; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19p(void *opaque, data[1] >>= 6; r = ((data[2] & 0x3) << 6) | (data[1] << 2); data[2] >>= 2; - if (data[2] & 1) + if (data[2] & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } data[2] >>= 6; b = (data[2] & 0x3f) << 2; data[2] >>= 6; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19p(void *opaque, data[2] >>= 6; r = data[2] << 2; data[2] >>= 6; - if (data[2] & 1) + if (data[2] & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } width -= 4; } } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line24t(void *opaque, data >>= 8; r = data & 0xff; data >>= 8; - if (data & 1) + if (data & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } width -= 1; src += 4; } @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line25(void *opaque, data >>= 8; r = data & 0xff; data >>= 8; - if (data & 1) + if (data & 1) { SKIP_PIXEL(dest); - else + } else { COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } width -= 1; src += 4; } -- 2.20.1 We're about to move code from the template header into pxa2xx_lcd.c. Before doing that, make coding style fixes so checkpatch doesn't complain about the patch which moves the code. This commit is whitespace changes only: * avoid hard-coded tabs * fix ident on function prototypes * no newline before open brace on array definitions Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-9-peter.maydell@linaro.org --- hw/display/pxa2xx_template.h | 66 +++++++++++++++++------------------- 1 file changed, 32 insertions(+), 34 deletions(-) diff --git a/hw/display/pxa2xx_template.h b/hw/display/pxa2xx_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_template.h +++ b/hw/display/pxa2xx_template.h @@ -XXX,XX +XXX,XX @@ } while (0) #ifdef HOST_WORDS_BIGENDIAN -# define SWAP_WORDS 1 +# define SWAP_WORDS 1 #endif -#define FN_2(x) FN(x + 1) FN(x) -#define FN_4(x) FN_2(x + 2) FN_2(x) +#define FN_2(x) FN(x + 1) FN(x) +#define FN_4(x) FN_2(x + 2) FN_2(x) -static void pxa2xx_draw_line2(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line2(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t *palette = opaque; uint32_t data; while (width > 0) { data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 2)) & 3]); +#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 2)) & 3]); #ifdef SWAP_WORDS FN_4(12) FN_4(8) @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line2(void *opaque, } } -static void pxa2xx_draw_line4(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line4(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t *palette = opaque; uint32_t data; while (width > 0) { data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 4)) & 0xf]); +#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 4)) & 0xf]); #ifdef SWAP_WORDS FN_2(6) FN_2(4) @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line4(void *opaque, } } -static void pxa2xx_draw_line8(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line8(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t *palette = opaque; uint32_t data; while (width > 0) { data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> (x)) & 0xff]); +#define FN(x) COPY_PIXEL(dest, palette[(data >> (x)) & 0xff]); #ifdef SWAP_WORDS FN(24) FN(16) @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line8(void *opaque, } } -static void pxa2xx_draw_line16(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line16(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line16(void *opaque, } } -static void pxa2xx_draw_line16t(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line16t(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line16t(void *opaque, } } -static void pxa2xx_draw_line18(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line18(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line18(void *opaque, } /* The wicked packed format */ -static void pxa2xx_draw_line18p(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line18p(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data[3]; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line18p(void *opaque, } } -static void pxa2xx_draw_line19(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line19(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19(void *opaque, } /* The wicked packed format */ -static void pxa2xx_draw_line19p(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line19p(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data[3]; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line19p(void *opaque, } } -static void pxa2xx_draw_line24(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line24(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line24(void *opaque, } } -static void pxa2xx_draw_line24t(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line24t(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line24t(void *opaque, } } -static void pxa2xx_draw_line25(void *opaque, - uint8_t *dest, const uint8_t *src, int width, int deststep) +static void pxa2xx_draw_line25(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) { uint32_t data; unsigned int r, g, b; @@ -XXX,XX +XXX,XX @@ static void pxa2xx_draw_line25(void *opaque, } /* Overlay planes disabled, no transparency */ -static drawfn pxa2xx_draw_fn_32[16] = -{ +static drawfn pxa2xx_draw_fn_32[16] = { [0 ... 0xf] = NULL, [pxa_lcdc_2bpp] = pxa2xx_draw_line2, [pxa_lcdc_4bpp] = pxa2xx_draw_line4, @@ -XXX,XX +XXX,XX @@ static drawfn pxa2xx_draw_fn_32[16] = }; /* Overlay planes enabled, transparency used */ -static drawfn pxa2xx_draw_fn_32t[16] = -{ +static drawfn pxa2xx_draw_fn_32t[16] = { [0 ... 0xf] = NULL, [pxa_lcdc_4bpp] = pxa2xx_draw_line4, [pxa_lcdc_8bpp] = pxa2xx_draw_line8, -- 2.20.1 The template header is now included only once; just inline its contents in hw/display/pxa2xx_lcd.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20210211141515.8755-10-peter.maydell@linaro.org --- hw/display/pxa2xx_template.h | 434 ----------------------------------- hw/display/pxa2xx_lcd.c | 427 +++++++++++++++++++++++++++++++++- 2 files changed, 425 insertions(+), 436 deletions(-) delete mode 100644 hw/display/pxa2xx_template.h diff --git a/hw/display/pxa2xx_template.h b/hw/display/pxa2xx_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/pxa2xx_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Intel XScale PXA255/270 LCDC emulation. - * - * Copyright (c) 2006 Openedhand Ltd. - * Written by Andrzej Zaborowski <balrog@zabor.org> - * - * This code is licensed under the GPLv2. - * - * Framebuffer format conversion routines. - */ - -# define SKIP_PIXEL(to) do { to += deststep; } while (0) -# define COPY_PIXEL(to, from) \ - do { \ - *(uint32_t *) to = from; \ - SKIP_PIXEL(to); \ - } while (0) - -#ifdef HOST_WORDS_BIGENDIAN -# define SWAP_WORDS 1 -#endif - -#define FN_2(x) FN(x + 1) FN(x) -#define FN_4(x) FN_2(x + 2) FN_2(x) - -static void pxa2xx_draw_line2(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 2)) & 3]); -#ifdef SWAP_WORDS - FN_4(12) - FN_4(8) - FN_4(4) - FN_4(0) -#else - FN_4(0) - FN_4(4) - FN_4(8) - FN_4(12) -#endif -#undef FN - width -= 16; - src += 4; - } -} - -static void pxa2xx_draw_line4(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 4)) & 0xf]); -#ifdef SWAP_WORDS - FN_2(6) - FN_2(4) - FN_2(2) - FN_2(0) -#else - FN_2(0) - FN_2(2) - FN_2(4) - FN_2(6) -#endif -#undef FN - width -= 8; - src += 4; - } -} - -static void pxa2xx_draw_line8(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t *palette = opaque; - uint32_t data; - while (width > 0) { - data = *(uint32_t *) src; -#define FN(x) COPY_PIXEL(dest, palette[(data >> (x)) & 0xff]); -#ifdef SWAP_WORDS - FN(24) - FN(16) - FN(8) - FN(0) -#else - FN(0) - FN(8) - FN(16) - FN(24) -#endif -#undef FN - width -= 4; - src += 4; - } -} - -static void pxa2xx_draw_line16(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x1f) << 3; - data >>= 5; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x1f) << 3; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 2; - src += 4; - } -} - -static void pxa2xx_draw_line16t(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x1f) << 3; - data >>= 5; - r = (data & 0x1f) << 3; - data >>= 5; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data >>= 1; - b = (data & 0x1f) << 3; - data >>= 5; - g = (data & 0x1f) << 3; - data >>= 5; - r = (data & 0x1f) << 3; - data >>= 5; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 2; - src += 4; - } -} - -static void pxa2xx_draw_line18(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x3f) << 2; - data >>= 6; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x3f) << 2; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 1; - src += 4; - } -} - -/* The wicked packed format */ -static void pxa2xx_draw_line18p(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data[3]; - unsigned int r, g, b; - while (width > 0) { - data[0] = *(uint32_t *) src; - src += 4; - data[1] = *(uint32_t *) src; - src += 4; - data[2] = *(uint32_t *) src; - src += 4; -#ifdef SWAP_WORDS - data[0] = bswap32(data[0]); - data[1] = bswap32(data[1]); - data[2] = bswap32(data[2]); -#endif - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = (data[0] & 0x3f) << 2; - data[0] >>= 6; - r = (data[0] & 0x3f) << 2; - data[0] >>= 12; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = ((data[1] & 0xf) << 4) | (data[0] << 2); - data[1] >>= 4; - r = (data[1] & 0x3f) << 2; - data[1] >>= 12; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[1] & 0x3f) << 2; - data[1] >>= 6; - g = (data[1] & 0x3f) << 2; - data[1] >>= 6; - r = ((data[2] & 0x3) << 6) | (data[1] << 2); - data[2] >>= 8; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - b = (data[2] & 0x3f) << 2; - data[2] >>= 6; - g = (data[2] & 0x3f) << 2; - data[2] >>= 6; - r = data[2] << 2; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 4; - } -} - -static void pxa2xx_draw_line19(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x3f) << 2; - data >>= 6; - g = (data & 0x3f) << 2; - data >>= 6; - r = (data & 0x3f) << 2; - data >>= 6; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -/* The wicked packed format */ -static void pxa2xx_draw_line19p(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data[3]; - unsigned int r, g, b; - while (width > 0) { - data[0] = *(uint32_t *) src; - src += 4; - data[1] = *(uint32_t *) src; - src += 4; - data[2] = *(uint32_t *) src; - src += 4; -# ifdef SWAP_WORDS - data[0] = bswap32(data[0]); - data[1] = bswap32(data[1]); - data[2] = bswap32(data[2]); -# endif - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = (data[0] & 0x3f) << 2; - data[0] >>= 6; - r = (data[0] & 0x3f) << 2; - data[0] >>= 6; - if (data[0] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[0] >>= 6; - b = (data[0] & 0x3f) << 2; - data[0] >>= 6; - g = ((data[1] & 0xf) << 4) | (data[0] << 2); - data[1] >>= 4; - r = (data[1] & 0x3f) << 2; - data[1] >>= 6; - if (data[1] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[1] >>= 6; - b = (data[1] & 0x3f) << 2; - data[1] >>= 6; - g = (data[1] & 0x3f) << 2; - data[1] >>= 6; - r = ((data[2] & 0x3) << 6) | (data[1] << 2); - data[2] >>= 2; - if (data[2] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - data[2] >>= 6; - b = (data[2] & 0x3f) << 2; - data[2] >>= 6; - g = (data[2] & 0x3f) << 2; - data[2] >>= 6; - r = data[2] << 2; - data[2] >>= 6; - if (data[2] & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 4; - } -} - -static void pxa2xx_draw_line24(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = data & 0xff; - data >>= 8; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - width -= 1; - src += 4; - } -} - -static void pxa2xx_draw_line24t(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = (data & 0x7f) << 1; - data >>= 7; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - data >>= 8; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -static void pxa2xx_draw_line25(void *opaque, uint8_t *dest, const uint8_t *src, - int width, int deststep) -{ - uint32_t data; - unsigned int r, g, b; - while (width > 0) { - data = *(uint32_t *) src; -#ifdef SWAP_WORDS - data = bswap32(data); -#endif - b = data & 0xff; - data >>= 8; - g = data & 0xff; - data >>= 8; - r = data & 0xff; - data >>= 8; - if (data & 1) { - SKIP_PIXEL(dest); - } else { - COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); - } - width -= 1; - src += 4; - } -} - -/* Overlay planes disabled, no transparency */ -static drawfn pxa2xx_draw_fn_32[16] = { - [0 ... 0xf] = NULL, - [pxa_lcdc_2bpp] = pxa2xx_draw_line2, - [pxa_lcdc_4bpp] = pxa2xx_draw_line4, - [pxa_lcdc_8bpp] = pxa2xx_draw_line8, - [pxa_lcdc_16bpp] = pxa2xx_draw_line16, - [pxa_lcdc_18bpp] = pxa2xx_draw_line18, - [pxa_lcdc_18pbpp] = pxa2xx_draw_line18p, - [pxa_lcdc_24bpp] = pxa2xx_draw_line24, -}; - -/* Overlay planes enabled, transparency used */ -static drawfn pxa2xx_draw_fn_32t[16] = { - [0 ... 0xf] = NULL, - [pxa_lcdc_4bpp] = pxa2xx_draw_line4, - [pxa_lcdc_8bpp] = pxa2xx_draw_line8, - [pxa_lcdc_16bpp] = pxa2xx_draw_line16t, - [pxa_lcdc_19bpp] = pxa2xx_draw_line19, - [pxa_lcdc_19pbpp] = pxa2xx_draw_line19p, - [pxa_lcdc_24bpp] = pxa2xx_draw_line24t, - [pxa_lcdc_25bpp] = pxa2xx_draw_line25, -}; - -#undef COPY_PIXEL -#undef SKIP_PIXEL - -#ifdef SWAP_WORDS -# undef SWAP_WORDS -#endif diff --git a/hw/display/pxa2xx_lcd.c b/hw/display/pxa2xx_lcd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/pxa2xx_lcd.c +++ b/hw/display/pxa2xx_lcd.c @@ -XXX,XX +XXX,XX @@ typedef struct QEMU_PACKED { /* Size of a pixel in the QEMU UI output surface, in bytes */ #define DEST_PIXEL_WIDTH 4 -#define BITS 32 -#include "pxa2xx_template.h" +/* Line drawing code to handle the various possible guest pixel formats */ + +# define SKIP_PIXEL(to) do { to += deststep; } while (0) +# define COPY_PIXEL(to, from) \ + do { \ + *(uint32_t *) to = from; \ + SKIP_PIXEL(to); \ + } while (0) + +#ifdef HOST_WORDS_BIGENDIAN +# define SWAP_WORDS 1 +#endif + +#define FN_2(x) FN(x + 1) FN(x) +#define FN_4(x) FN_2(x + 2) FN_2(x) + +static void pxa2xx_draw_line2(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t *palette = opaque; + uint32_t data; + while (width > 0) { + data = *(uint32_t *) src; +#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 2)) & 3]); +#ifdef SWAP_WORDS + FN_4(12) + FN_4(8) + FN_4(4) + FN_4(0) +#else + FN_4(0) + FN_4(4) + FN_4(8) + FN_4(12) +#endif +#undef FN + width -= 16; + src += 4; + } +} + +static void pxa2xx_draw_line4(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t *palette = opaque; + uint32_t data; + while (width > 0) { + data = *(uint32_t *) src; +#define FN(x) COPY_PIXEL(dest, palette[(data >> ((x) * 4)) & 0xf]); +#ifdef SWAP_WORDS + FN_2(6) + FN_2(4) + FN_2(2) + FN_2(0) +#else + FN_2(0) + FN_2(2) + FN_2(4) + FN_2(6) +#endif +#undef FN + width -= 8; + src += 4; + } +} + +static void pxa2xx_draw_line8(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t *palette = opaque; + uint32_t data; + while (width > 0) { + data = *(uint32_t *) src; +#define FN(x) COPY_PIXEL(dest, palette[(data >> (x)) & 0xff]); +#ifdef SWAP_WORDS + FN(24) + FN(16) + FN(8) + FN(0) +#else + FN(0) + FN(8) + FN(16) + FN(24) +#endif +#undef FN + width -= 4; + src += 4; + } +} + +static void pxa2xx_draw_line16(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = (data & 0x1f) << 3; + data >>= 5; + g = (data & 0x3f) << 2; + data >>= 6; + r = (data & 0x1f) << 3; + data >>= 5; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + b = (data & 0x1f) << 3; + data >>= 5; + g = (data & 0x3f) << 2; + data >>= 6; + r = (data & 0x1f) << 3; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + width -= 2; + src += 4; + } +} + +static void pxa2xx_draw_line16t(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = (data & 0x1f) << 3; + data >>= 5; + g = (data & 0x1f) << 3; + data >>= 5; + r = (data & 0x1f) << 3; + data >>= 5; + if (data & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + data >>= 1; + b = (data & 0x1f) << 3; + data >>= 5; + g = (data & 0x1f) << 3; + data >>= 5; + r = (data & 0x1f) << 3; + data >>= 5; + if (data & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + width -= 2; + src += 4; + } +} + +static void pxa2xx_draw_line18(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = (data & 0x3f) << 2; + data >>= 6; + g = (data & 0x3f) << 2; + data >>= 6; + r = (data & 0x3f) << 2; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + width -= 1; + src += 4; + } +} + +/* The wicked packed format */ +static void pxa2xx_draw_line18p(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data[3]; + unsigned int r, g, b; + while (width > 0) { + data[0] = *(uint32_t *) src; + src += 4; + data[1] = *(uint32_t *) src; + src += 4; + data[2] = *(uint32_t *) src; + src += 4; +#ifdef SWAP_WORDS + data[0] = bswap32(data[0]); + data[1] = bswap32(data[1]); + data[2] = bswap32(data[2]); +#endif + b = (data[0] & 0x3f) << 2; + data[0] >>= 6; + g = (data[0] & 0x3f) << 2; + data[0] >>= 6; + r = (data[0] & 0x3f) << 2; + data[0] >>= 12; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + b = (data[0] & 0x3f) << 2; + data[0] >>= 6; + g = ((data[1] & 0xf) << 4) | (data[0] << 2); + data[1] >>= 4; + r = (data[1] & 0x3f) << 2; + data[1] >>= 12; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + b = (data[1] & 0x3f) << 2; + data[1] >>= 6; + g = (data[1] & 0x3f) << 2; + data[1] >>= 6; + r = ((data[2] & 0x3) << 6) | (data[1] << 2); + data[2] >>= 8; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + b = (data[2] & 0x3f) << 2; + data[2] >>= 6; + g = (data[2] & 0x3f) << 2; + data[2] >>= 6; + r = data[2] << 2; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + width -= 4; + } +} + +static void pxa2xx_draw_line19(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = (data & 0x3f) << 2; + data >>= 6; + g = (data & 0x3f) << 2; + data >>= 6; + r = (data & 0x3f) << 2; + data >>= 6; + if (data & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + width -= 1; + src += 4; + } +} + +/* The wicked packed format */ +static void pxa2xx_draw_line19p(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data[3]; + unsigned int r, g, b; + while (width > 0) { + data[0] = *(uint32_t *) src; + src += 4; + data[1] = *(uint32_t *) src; + src += 4; + data[2] = *(uint32_t *) src; + src += 4; +# ifdef SWAP_WORDS + data[0] = bswap32(data[0]); + data[1] = bswap32(data[1]); + data[2] = bswap32(data[2]); +# endif + b = (data[0] & 0x3f) << 2; + data[0] >>= 6; + g = (data[0] & 0x3f) << 2; + data[0] >>= 6; + r = (data[0] & 0x3f) << 2; + data[0] >>= 6; + if (data[0] & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + data[0] >>= 6; + b = (data[0] & 0x3f) << 2; + data[0] >>= 6; + g = ((data[1] & 0xf) << 4) | (data[0] << 2); + data[1] >>= 4; + r = (data[1] & 0x3f) << 2; + data[1] >>= 6; + if (data[1] & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + data[1] >>= 6; + b = (data[1] & 0x3f) << 2; + data[1] >>= 6; + g = (data[1] & 0x3f) << 2; + data[1] >>= 6; + r = ((data[2] & 0x3) << 6) | (data[1] << 2); + data[2] >>= 2; + if (data[2] & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + data[2] >>= 6; + b = (data[2] & 0x3f) << 2; + data[2] >>= 6; + g = (data[2] & 0x3f) << 2; + data[2] >>= 6; + r = data[2] << 2; + data[2] >>= 6; + if (data[2] & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + width -= 4; + } +} + +static void pxa2xx_draw_line24(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = data & 0xff; + data >>= 8; + g = data & 0xff; + data >>= 8; + r = data & 0xff; + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + width -= 1; + src += 4; + } +} + +static void pxa2xx_draw_line24t(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = (data & 0x7f) << 1; + data >>= 7; + g = data & 0xff; + data >>= 8; + r = data & 0xff; + data >>= 8; + if (data & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + width -= 1; + src += 4; + } +} + +static void pxa2xx_draw_line25(void *opaque, uint8_t *dest, const uint8_t *src, + int width, int deststep) +{ + uint32_t data; + unsigned int r, g, b; + while (width > 0) { + data = *(uint32_t *) src; +#ifdef SWAP_WORDS + data = bswap32(data); +#endif + b = data & 0xff; + data >>= 8; + g = data & 0xff; + data >>= 8; + r = data & 0xff; + data >>= 8; + if (data & 1) { + SKIP_PIXEL(dest); + } else { + COPY_PIXEL(dest, rgb_to_pixel32(r, g, b)); + } + width -= 1; + src += 4; + } +} + +/* Overlay planes disabled, no transparency */ +static drawfn pxa2xx_draw_fn_32[16] = { + [0 ... 0xf] = NULL, + [pxa_lcdc_2bpp] = pxa2xx_draw_line2, + [pxa_lcdc_4bpp] = pxa2xx_draw_line4, + [pxa_lcdc_8bpp] = pxa2xx_draw_line8, + [pxa_lcdc_16bpp] = pxa2xx_draw_line16, + [pxa_lcdc_18bpp] = pxa2xx_draw_line18, + [pxa_lcdc_18pbpp] = pxa2xx_draw_line18p, + [pxa_lcdc_24bpp] = pxa2xx_draw_line24, +}; + +/* Overlay planes enabled, transparency used */ +static drawfn pxa2xx_draw_fn_32t[16] = { + [0 ... 0xf] = NULL, + [pxa_lcdc_4bpp] = pxa2xx_draw_line4, + [pxa_lcdc_8bpp] = pxa2xx_draw_line8, + [pxa_lcdc_16bpp] = pxa2xx_draw_line16t, + [pxa_lcdc_19bpp] = pxa2xx_draw_line19, + [pxa_lcdc_19pbpp] = pxa2xx_draw_line19p, + [pxa_lcdc_24bpp] = pxa2xx_draw_line24t, + [pxa_lcdc_25bpp] = pxa2xx_draw_line25, +}; + +#undef COPY_PIXEL +#undef SKIP_PIXEL + +#ifdef SWAP_WORDS +# undef SWAP_WORDS +#endif /* Route internal interrupt lines to the global IC */ static void pxa2xx_lcdc_int_update(PXA2xxLCDState *s) -- 2.20.1