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 First arm pullreq of the 5.1 cycle; mostly bugfixes and some cleanup patches. The new clock modelling framework is the big thing here. -- PMM The following changes since commit 648db19685b7030aa558a4ddbd3a8e53d8c9a062: Merge remote-tracking branch 'remotes/armbru/tags/pull-misc-2020-04-29' into staging (2020-04-29 15:07:33 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200430 for you to fetch changes up to 1267437e593e85498f9105b3bdab796630d2e83f: hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes (2020-04-30 11:52:29 +0100) ---------------------------------------------------------------- target-arm queue: * xlnx-zdma: Fix endianness handling of descriptor loading * nrf51: Fix last GPIO CNF address * gicv3: Use gicr_typer in arm_gicv3_icc_reset * msf2: Add EMAC block to SmartFusion2 SoC * New clock modelling framework * hw/arm: versal: Setup the ADMA with 128bit bus-width * Cadence: gem: fix wraparound in 64bit descriptors * cadence_gem: clear RX control descriptor * target/arm: Vectorize integer comparison vs zero * hw/arm/virt: dt: add kaslr-seed property * hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes ---------------------------------------------------------------- Cameron Esfahani (1): nrf51: Fix last GPIO CNF address Damien Hedde (7): hw/core/clock-vmstate: define a vmstate entry for clock state qdev: add clock input&output support to devices. qdev-clock: introduce an init array to ease the device construction hw/misc/zynq_slcr: add clock generation for uarts hw/char/cadence_uart: add clock support hw/arm/xilinx_zynq: connect uart clocks to slcr qdev-monitor: print the device's clock with info qtree Edgar E. Iglesias (7): dma/xlnx-zdma: Fix descriptor loading (MEM) wrt endianness dma/xlnx-zdma: Fix descriptor loading (REG) wrt endianness hw/arm: versal: Setup the ADMA with 128bit bus-width device_tree: Allow name wildcards in qemu_fdt_node_path() device_tree: Constify compat in qemu_fdt_node_path() hw/arm: xlnx-zcu102: Move arm_boot_info into XlnxZCU102 hw/arm: xlnx-zcu102: Disable unsupported FDT firmware nodes Jerome Forissier (2): hw/arm/virt: dt: move creation of /secure-chosen to create_fdt() hw/arm/virt: dt: add kaslr-seed property Keqian Zhu (2): bugfix: Use gicr_typer in arm_gicv3_icc_reset Typo: Correct the name of CPU hotplug memory region Peter Maydell (2): hw/core/clock: introduce clock object docs/clocks: add device's clock documentation Philippe Mathieu-Daudé (3): target/arm: Restrict the Address Translate write operation to TCG accel target/arm/cpu: Use ARRAY_SIZE() to iterate over ARMCPUInfo[] target/arm/cpu: Update coding style to make checkpatch.pl happy Ramon Fried (2): Cadence: gem: fix wraparound in 64bit descriptors net: cadence_gem: clear RX control descriptor Richard Henderson (1): target/arm: Vectorize integer comparison vs zero Subbaraya Sundeep (3): hw/net: Add Smartfusion2 emac block msf2: Add EMAC block to SmartFusion2 SoC tests/boot_linux_console: Add ethernet test to SmartFusion2 Thomas Huth (1): target/arm: Make cpu_register() available for other files hw/core/Makefile.objs | 2 + hw/net/Makefile.objs | 1 + tests/Makefile.include | 1 + include/hw/arm/msf2-soc.h | 2 + include/hw/char/cadence_uart.h | 1 + include/hw/clock.h | 225 +++++++++++++ include/hw/gpio/nrf51_gpio.h | 2 +- include/hw/net/msf2-emac.h | 53 +++ include/hw/qdev-clock.h | 159 +++++++++ include/hw/qdev-core.h | 12 + include/sysemu/device_tree.h | 5 +- target/arm/cpu-qom.h | 9 +- target/arm/helper.h | 27 +- target/arm/translate.h | 5 + device_tree.c | 4 +- hw/acpi/cpu.c | 2 +- hw/arm/msf2-soc.c | 26 +- hw/arm/virt.c | 20 +- hw/arm/xilinx_zynq.c | 57 +++- hw/arm/xlnx-versal.c | 2 + hw/arm/xlnx-zcu102.c | 39 ++- hw/char/cadence_uart.c | 73 +++- hw/core/clock-vmstate.c | 25 ++ hw/core/clock.c | 130 ++++++++ hw/core/qdev-clock.c | 185 +++++++++++ hw/core/qdev.c | 12 + hw/dma/xlnx-zdma.c | 25 +- hw/intc/arm_gicv3_kvm.c | 4 +- hw/misc/zynq_slcr.c | 172 +++++++++- hw/net/cadence_gem.c | 16 +- hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++ qdev-monitor.c | 9 + target/arm/cpu.c | 25 +- target/arm/cpu64.c | 16 +- target/arm/helper.c | 17 + target/arm/neon_helper.c | 24 -- target/arm/translate-a64.c | 64 +--- target/arm/translate.c | 256 ++++++++++++-- target/arm/vec_helper.c | 25 ++ MAINTAINERS | 2 + docs/devel/clocks.rst | 391 ++++++++++++++++++++++ docs/devel/index.rst | 1 + hw/char/trace-events | 3 + hw/core/trace-events | 7 + tests/acceptance/boot_linux_console.py | 15 +- 45 files changed, 2538 insertions(+), 202 deletions(-) create mode 100644 include/hw/clock.h create mode 100644 include/hw/net/msf2-emac.h create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/clock-vmstate.c create mode 100644 hw/core/clock.c create mode 100644 hw/core/qdev-clock.c create mode 100644 hw/net/msf2-emac.c create mode 100644 docs/devel/clocks.rst From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from memory wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200404122718.25111-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 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 void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } -static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, void *buf) +static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, + XlnxZDMADescr *descr) { /* ZDMA descriptors must be aligned to their own size. */ if (addr % sizeof(XlnxZDMADescr)) { qemu_log_mask(LOG_GUEST_ERROR, "zdma: unaligned descriptor at %" PRIx64, addr); - memset(buf, 0x0, sizeof(XlnxZDMADescr)); + memset(descr, 0x0, sizeof(XlnxZDMADescr)); s->error = true; return false; } - address_space_read(s->dma_as, addr, s->attr, buf, sizeof(XlnxZDMADescr)); + descr->addr = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); + descr->size = address_space_ldl_le(s->dma_as, addr + 8, s->attr, NULL); + descr->attr = address_space_ldl_le(s->dma_as, addr + 12, s->attr, NULL); return true; } @@ -XXX,XX +XXX,XX @@ static void zdma_update_descr_addr(XlnxZDMA *s, bool type, } else { addr = zdma_get_regaddr64(s, basereg); addr += sizeof(s->dsc_dst); - address_space_read(s->dma_as, addr, s->attr, (void *) &next, 8); + next = address_space_ldq_le(s->dma_as, addr, s->attr, NULL); } zdma_put_regaddr64(s, basereg, next); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Fix descriptor loading from registers wrt host endianness. Reported-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20200404122718.25111-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/xlnx-zdma.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 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 void zdma_put_regaddr64(XlnxZDMA *s, unsigned int basereg, uint64_t addr) s->regs[basereg + 1] = addr >> 32; } +static void zdma_load_descriptor_reg(XlnxZDMA *s, unsigned int reg, + XlnxZDMADescr *descr) +{ + descr->addr = zdma_get_regaddr64(s, reg); + descr->size = s->regs[reg + 2]; + descr->attr = s->regs[reg + 3]; +} + static bool zdma_load_descriptor(XlnxZDMA *s, uint64_t addr, XlnxZDMADescr *descr) { @@ -XXX,XX +XXX,XX @@ static void zdma_load_src_descriptor(XlnxZDMA *s) unsigned int ptype = ARRAY_FIELD_EX32(s->regs, ZDMA_CH_CTRL0, POINT_TYPE); if (ptype == PT_REG) { - memcpy(&s->dsc_src, &s->regs[R_ZDMA_CH_SRC_DSCR_WORD0], - sizeof(s->dsc_src)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_SRC_DSCR_WORD0, &s->dsc_src); return; } @@ -XXX,XX +XXX,XX @@ static void zdma_load_dst_descriptor(XlnxZDMA *s) bool dst_type; if (ptype == PT_REG) { - memcpy(&s->dsc_dst, &s->regs[R_ZDMA_CH_DST_DSCR_WORD0], - sizeof(s->dsc_dst)); + zdma_load_descriptor_reg(s, R_ZDMA_CH_DST_DSCR_WORD0, &s->dsc_dst); return; } -- 2.20.1 From: Cameron Esfahani <dirty@apple.com> NRF51_GPIO_REG_CNF_END doesn't actually refer to the start of the last valid CNF register: it's referring to the last byte of the last valid CNF register. This hasn't been a problem up to now, as current implementation in memory.c turns an unaligned 4-byte read from 0x77f to a single byte read and the qtest only looks at the least-significant byte of the register. But when running with patches which fix unaligned accesses in memory.c, the qtest breaks. Considering NRF51 doesn't support unaligned accesses, the simplest fix is to actually set NRF51_GPIO_REG_CNF_END to the start of the last valid CNF register: 0x77c. Now, qtests work with or without the unaligned access patches. Reviewed-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Signed-off-by: Cameron Esfahani <dirty@apple.com> Message-id: 51b427f06838622da783d38ba56e3630d6d85c60.1586925392.git.dirty@apple.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/gpio/nrf51_gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/hw/gpio/nrf51_gpio.h b/include/hw/gpio/nrf51_gpio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/gpio/nrf51_gpio.h +++ b/include/hw/gpio/nrf51_gpio.h @@ -XXX,XX +XXX,XX @@ #define NRF51_GPIO_REG_DIRSET 0x518 #define NRF51_GPIO_REG_DIRCLR 0x51C #define NRF51_GPIO_REG_CNF_START 0x700 -#define NRF51_GPIO_REG_CNF_END 0x77F +#define NRF51_GPIO_REG_CNF_END 0x77C #define NRF51_GPIO_PULLDOWN 1 #define NRF51_GPIO_PULLUP 3 -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> The KVM_VGIC_ATTR macro expect the second parameter as gicr_typer, of which high 32bit is constructed by mp_affinity. For most case, the high 32bit of mp_affinity is zero, so it will always access the ICC_CTLR_EL1 of CPU0. Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-2-zhukeqian1@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 | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) 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_get(GICv3State *s) static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) { - ARMCPU *cpu; GICv3State *s; GICv3CPUState *c; c = (GICv3CPUState *)env->gicv3state; s = c->gic; - cpu = ARM_CPU(c->cpu); c->icc_pmr_el1 = 0; c->icc_bpr[GICV3_G0] = GIC_MIN_BPR; @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) /* Initialize to actual HW supported configuration */ kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, - KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity), + KVM_VGIC_ATTR(ICC_CTLR_EL1, c->gicr_typer), &c->icc_ctlr_el1[GICV3_NS], false, &error_abort); c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS]; -- 2.20.1 From: Keqian Zhu <zhukeqian1@huawei.com> Replace "acpi-mem-hotplug" with "acpi-cpu-hotplug" Signed-off-by: Keqian Zhu <zhukeqian1@huawei.com> Message-id: 20200413091552.62748-4-zhukeqian1@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/acpi/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -XXX,XX +XXX,XX @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, state->devs[i].arch_id = id_list->cpus[i].arch_id; } memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state, - "acpi-mem-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); + "acpi-cpu-hotplug", ACPI_CPU_HOTPLUG_REG_LEN); memory_region_add_subregion(as, base_addr, &state->ctrl_reg); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> Modelled Ethernet MAC of Smartfusion2 SoC. Micrel KSZ8051 PHY is present on Emcraft's SOM kit hence same PHY is emulated. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-2-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/Makefile.objs | 1 + include/hw/net/msf2-emac.h | 53 ++++ hw/net/msf2-emac.c | 589 +++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + 4 files changed, 645 insertions(+) create mode 100644 include/hw/net/msf2-emac.h create mode 100644 hw/net/msf2-emac.c diff --git a/hw/net/Makefile.objs b/hw/net/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Makefile.objs +++ b/hw/net/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ROCKER) += rocker/rocker.o rocker/rocker_fp.o \ obj-$(call lnot,$(CONFIG_ROCKER)) += rocker/qmp-norocker.o common-obj-$(CONFIG_CAN_BUS) += can/ +common-obj-$(CONFIG_MSF2) += msf2-emac.o diff --git a/include/hw/net/msf2-emac.h b/include/hw/net/msf2-emac.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/msf2-emac.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 Subbaraya Sundeep <sundeep.lkml@gmail.com>. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "hw/sysbus.h" +#include "exec/memory.h" +#include "net/net.h" +#include "net/eth.h" + +#define TYPE_MSS_EMAC "msf2-emac" +#define MSS_EMAC(obj) \ + OBJECT_CHECK(MSF2EmacState, (obj), TYPE_MSS_EMAC) + +#define R_MAX (0x1a0 / 4) +#define PHY_MAX_REGS 32 + +typedef struct MSF2EmacState { + SysBusDevice parent; + + MemoryRegion mmio; + MemoryRegion *dma_mr; + AddressSpace dma_as; + + qemu_irq irq; + NICState *nic; + NICConf conf; + + uint8_t mac_addr[ETH_ALEN]; + uint32_t rx_desc; + uint16_t phy_regs[PHY_MAX_REGS]; + + uint32_t regs[R_MAX]; +} MSF2EmacState; diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/msf2-emac.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Smartfusion2 Ethernet MAC. + * + * Copyright (c) 2020 Subbaraya Sundeep <sundeep.lkml@gmail.com>. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + * + * Refer to section Ethernet MAC in the document: + * UG0331: SmartFusion2 Microcontroller Subsystem User Guide + * Datasheet URL: + * https://www.microsemi.com/document-portal/cat_view/56661-internal-documents/ + * 56758-soc?lang=en&limit=20&limitstart=220 + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/log.h" +#include "qapi/error.h" +#include "exec/address-spaces.h" +#include "hw/registerfields.h" +#include "hw/net/msf2-emac.h" +#include "hw/net/mii.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "migration/vmstate.h" + +REG32(CFG1, 0x0) + FIELD(CFG1, RESET, 31, 1) + FIELD(CFG1, RX_EN, 2, 1) + FIELD(CFG1, TX_EN, 0, 1) + FIELD(CFG1, LB_EN, 8, 1) +REG32(CFG2, 0x4) +REG32(IFG, 0x8) +REG32(HALF_DUPLEX, 0xc) +REG32(MAX_FRAME_LENGTH, 0x10) +REG32(MII_CMD, 0x24) + FIELD(MII_CMD, READ, 0, 1) +REG32(MII_ADDR, 0x28) + FIELD(MII_ADDR, REGADDR, 0, 5) + FIELD(MII_ADDR, PHYADDR, 8, 5) +REG32(MII_CTL, 0x2c) +REG32(MII_STS, 0x30) +REG32(STA1, 0x40) +REG32(STA2, 0x44) +REG32(FIFO_CFG0, 0x48) +REG32(FIFO_CFG4, 0x58) + FIELD(FIFO_CFG4, BCAST, 9, 1) + FIELD(FIFO_CFG4, MCAST, 8, 1) +REG32(FIFO_CFG5, 0x5C) + FIELD(FIFO_CFG5, BCAST, 9, 1) + FIELD(FIFO_CFG5, MCAST, 8, 1) +REG32(DMA_TX_CTL, 0x180) + FIELD(DMA_TX_CTL, EN, 0, 1) +REG32(DMA_TX_DESC, 0x184) +REG32(DMA_TX_STATUS, 0x188) + FIELD(DMA_TX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_TX_STATUS, UNDERRUN, 1, 1) + FIELD(DMA_TX_STATUS, PKT_SENT, 0, 1) +REG32(DMA_RX_CTL, 0x18c) + FIELD(DMA_RX_CTL, EN, 0, 1) +REG32(DMA_RX_DESC, 0x190) +REG32(DMA_RX_STATUS, 0x194) + FIELD(DMA_RX_STATUS, PKTCNT, 16, 8) + FIELD(DMA_RX_STATUS, OVERFLOW, 2, 1) + FIELD(DMA_RX_STATUS, PKT_RCVD, 0, 1) +REG32(DMA_IRQ_MASK, 0x198) +REG32(DMA_IRQ, 0x19c) + +#define EMPTY_MASK (1 << 31) +#define PKT_SIZE 0x7FF +#define PHYADDR 0x1 +#define MAX_PKT_SIZE 2048 + +typedef struct { + uint32_t pktaddr; + uint32_t pktsize; + uint32_t next; +} EmacDesc; + +static uint32_t emac_get_isr(MSF2EmacState *s) +{ + uint32_t ier = s->regs[R_DMA_IRQ_MASK]; + uint32_t tx = s->regs[R_DMA_TX_STATUS] & 0xF; + uint32_t rx = s->regs[R_DMA_RX_STATUS] & 0xF; + uint32_t isr = (rx << 4) | tx; + + s->regs[R_DMA_IRQ] = ier & isr; + return s->regs[R_DMA_IRQ]; +} + +static void emac_update_irq(MSF2EmacState *s) +{ + bool intr = emac_get_isr(s); + + qemu_set_irq(s->irq, intr); +} + +static void emac_load_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + address_space_read(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); + /* Convert from LE into host endianness. */ + d->pktaddr = le32_to_cpu(d->pktaddr); + d->pktsize = le32_to_cpu(d->pktsize); + d->next = le32_to_cpu(d->next); +} + +static void emac_store_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +{ + /* Convert from host endianness into LE. */ + d->pktaddr = cpu_to_le32(d->pktaddr); + d->pktsize = cpu_to_le32(d->pktsize); + d->next = cpu_to_le32(d->next); + + address_space_write(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); +} + +static void msf2_dma_tx(MSF2EmacState *s) +{ + NetClientState *nc = qemu_get_queue(s->nic); + hwaddr desc = s->regs[R_DMA_TX_DESC]; + uint8_t buf[MAX_PKT_SIZE]; + EmacDesc d; + int size; + uint8_t pktcnt; + uint32_t status; + + if (!(s->regs[R_CFG1] & R_CFG1_TX_EN_MASK)) { + return; + } + + while (1) { + emac_load_desc(s, &d, desc); + if (d.pktsize & EMPTY_MASK) { + break; + } + size = d.pktsize & PKT_SIZE; + address_space_read(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size); + /* + * This is very basic way to send packets. Ideally there should be + * a FIFO and packets should be sent out from FIFO only when + * R_CFG1 bit 0 is set. + */ + if (s->regs[R_CFG1] & R_CFG1_LB_EN_MASK) { + nc->info->receive(nc, buf, size); + } else { + qemu_send_packet(nc, buf, size); + } + d.pktsize |= EMPTY_MASK; + emac_store_desc(s, &d, desc); + /* update sent packets count */ + status = s->regs[R_DMA_TX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_TX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_TX_STATUS] = FIELD_DP32(status, DMA_TX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_PKT_SENT_MASK; + desc = d.next; + } + s->regs[R_DMA_TX_STATUS] |= R_DMA_TX_STATUS_UNDERRUN_MASK; + s->regs[R_DMA_TX_CTL] &= ~R_DMA_TX_CTL_EN_MASK; +} + +static void msf2_phy_update_link(MSF2EmacState *s) +{ + /* Autonegotiation status mirrors link status. */ + if (qemu_get_queue(s->nic)->link_down) { + s->phy_regs[MII_BMSR] &= ~(MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } else { + s->phy_regs[MII_BMSR] |= (MII_BMSR_AN_COMP | + MII_BMSR_LINK_ST); + } +} + +static void msf2_phy_reset(MSF2EmacState *s) +{ + memset(&s->phy_regs[0], 0, sizeof(s->phy_regs)); + s->phy_regs[MII_BMCR] = 0x1140; + s->phy_regs[MII_BMSR] = 0x7968; + s->phy_regs[MII_PHYID1] = 0x0022; + s->phy_regs[MII_PHYID2] = 0x1550; + s->phy_regs[MII_ANAR] = 0x01E1; + s->phy_regs[MII_ANLPAR] = 0xCDE1; + + msf2_phy_update_link(s); +} + +static void write_to_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + uint16_t data = s->regs[R_MII_CTL] & 0xFFFF; + + if (phy_addr != PHYADDR) { + return; + } + + switch (reg_addr) { + case MII_BMCR: + if (data & MII_BMCR_RESET) { + /* Phy reset */ + msf2_phy_reset(s); + data &= ~MII_BMCR_RESET; + } + if (data & MII_BMCR_AUTOEN) { + /* Complete autonegotiation immediately */ + data &= ~MII_BMCR_AUTOEN; + s->phy_regs[MII_BMSR] |= MII_BMSR_AN_COMP; + } + break; + } + + s->phy_regs[reg_addr] = data; +} + +static uint16_t read_from_phy(MSF2EmacState *s) +{ + uint8_t reg_addr = s->regs[R_MII_ADDR] & R_MII_ADDR_REGADDR_MASK; + uint8_t phy_addr = (s->regs[R_MII_ADDR] >> R_MII_ADDR_PHYADDR_SHIFT) & + R_MII_ADDR_REGADDR_MASK; + + if (phy_addr == PHYADDR) { + return s->phy_regs[reg_addr]; + } else { + return 0xFFFF; + } +} + +static void msf2_emac_do_reset(MSF2EmacState *s) +{ + memset(&s->regs[0], 0, sizeof(s->regs)); + s->regs[R_CFG1] = 0x80000000; + s->regs[R_CFG2] = 0x00007000; + s->regs[R_IFG] = 0x40605060; + s->regs[R_HALF_DUPLEX] = 0x00A1F037; + s->regs[R_MAX_FRAME_LENGTH] = 0x00000600; + s->regs[R_FIFO_CFG5] = 0X3FFFF; + + msf2_phy_reset(s); +} + +static uint64_t emac_read(void *opaque, hwaddr addr, unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t r = 0; + + addr >>= 2; + + switch (addr) { + case R_DMA_IRQ: + r = emac_get_isr(s); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return r; + } + r = s->regs[addr]; + break; + } + return r; +} + +static void emac_write(void *opaque, hwaddr addr, uint64_t val64, + unsigned int size) +{ + MSF2EmacState *s = opaque; + uint32_t value = val64; + uint32_t enreqbits; + uint8_t pktcnt; + + addr >>= 2; + switch (addr) { + case R_DMA_TX_CTL: + s->regs[addr] = value; + if (value & R_DMA_TX_CTL_EN_MASK) { + msf2_dma_tx(s); + } + break; + case R_DMA_RX_CTL: + s->regs[addr] = value; + if (value & R_DMA_RX_CTL_EN_MASK) { + s->rx_desc = s->regs[R_DMA_RX_DESC]; + qemu_flush_queued_packets(qemu_get_queue(s->nic)); + } + break; + case R_CFG1: + s->regs[addr] = value; + if (value & R_CFG1_RESET_MASK) { + msf2_emac_do_reset(s); + } + break; + case R_FIFO_CFG0: + /* + * For our implementation, turning on modules is instantaneous, + * so the states requested via the *ENREQ bits appear in the + * *ENRPLY bits immediately. Also the reset bits to reset PE-MCXMAC + * module are not emulated here since it deals with start of frames, + * inter-packet gap and control frames. + */ + enreqbits = extract32(value, 8, 5); + s->regs[addr] = deposit32(value, 16, 5, enreqbits); + break; + case R_DMA_TX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Tx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_RX_DESC: + if (value & 0x3) { + qemu_log_mask(LOG_GUEST_ERROR, "Rx Descriptor address should be" + " 32 bit aligned\n"); + } + /* Ignore [1:0] bits */ + s->regs[addr] = value & ~3; + break; + case R_DMA_TX_STATUS: + if (value & R_DMA_TX_STATUS_UNDERRUN_MASK) { + s->regs[addr] &= ~R_DMA_TX_STATUS_UNDERRUN_MASK; + } + if (value & R_DMA_TX_STATUS_PKT_SENT_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_TX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_TX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_TX_STATUS_PKT_SENT_MASK; + } + } + break; + case R_DMA_RX_STATUS: + if (value & R_DMA_RX_STATUS_OVERFLOW_MASK) { + s->regs[addr] &= ~R_DMA_RX_STATUS_OVERFLOW_MASK; + } + if (value & R_DMA_RX_STATUS_PKT_RCVD_MASK) { + pktcnt = FIELD_EX32(s->regs[addr], DMA_RX_STATUS, PKTCNT); + pktcnt--; + s->regs[addr] = FIELD_DP32(s->regs[addr], DMA_RX_STATUS, + PKTCNT, pktcnt); + if (pktcnt == 0) { + s->regs[addr] &= ~R_DMA_RX_STATUS_PKT_RCVD_MASK; + } + } + break; + case R_DMA_IRQ: + break; + case R_MII_CMD: + if (value & R_MII_CMD_READ_MASK) { + s->regs[R_MII_STS] = read_from_phy(s); + } + break; + case R_MII_CTL: + s->regs[addr] = value; + write_to_phy(s); + break; + case R_STA1: + s->regs[addr] = value; + /* + * R_STA1 [31:24] : octet 1 of mac address + * R_STA1 [23:16] : octet 2 of mac address + * R_STA1 [15:8] : octet 3 of mac address + * R_STA1 [7:0] : octet 4 of mac address + */ + stl_be_p(s->mac_addr, value); + break; + case R_STA2: + s->regs[addr] = value; + /* + * R_STA2 [31:24] : octet 5 of mac address + * R_STA2 [23:16] : octet 6 of mac address + */ + stw_be_p(s->mac_addr + 4, value >> 16); + break; + default: + if (addr >= ARRAY_SIZE(s->regs)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, + addr * 4); + return; + } + s->regs[addr] = value; + break; + } + emac_update_irq(s); +} + +static const MemoryRegionOps emac_ops = { + .read = emac_read, + .write = emac_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4 + } +}; + +static bool emac_can_rx(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + return (s->regs[R_CFG1] & R_CFG1_RX_EN_MASK) && + (s->regs[R_DMA_RX_CTL] & R_DMA_RX_CTL_EN_MASK); +} + +static bool addr_filter_ok(MSF2EmacState *s, const uint8_t *buf) +{ + /* The broadcast MAC address: FF:FF:FF:FF:FF:FF */ + const uint8_t broadcast_addr[] = { 0xFF, 0xFF, 0xFF, 0xFF, + 0xFF, 0xFF }; + bool bcast_en = true; + bool mcast_en = true; + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_BCAST_MASK) { + bcast_en = true; /* Broadcast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_BCAST_MASK) { + bcast_en = false; + } + + if (s->regs[R_FIFO_CFG5] & R_FIFO_CFG5_MCAST_MASK) { + mcast_en = true; /* Multicast dont care for drop circuitry */ + } else if (s->regs[R_FIFO_CFG4] & R_FIFO_CFG4_MCAST_MASK) { + mcast_en = false; + } + + if (!memcmp(buf, broadcast_addr, sizeof(broadcast_addr))) { + return bcast_en; + } + + if (buf[0] & 1) { + return mcast_en; + } + + return !memcmp(buf, s->mac_addr, sizeof(s->mac_addr)); +} + +static ssize_t emac_rx(NetClientState *nc, const uint8_t *buf, size_t size) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + EmacDesc d; + uint8_t pktcnt; + uint32_t status; + + if (size > (s->regs[R_MAX_FRAME_LENGTH] & 0xFFFF)) { + return size; + } + if (!addr_filter_ok(s, buf)) { + return size; + } + + emac_load_desc(s, &d, s->rx_desc); + + if (d.pktsize & EMPTY_MASK) { + address_space_write(&s->dma_as, d.pktaddr, MEMTXATTRS_UNSPECIFIED, + buf, size & PKT_SIZE); + d.pktsize = size & PKT_SIZE; + emac_store_desc(s, &d, s->rx_desc); + /* update received packets count */ + status = s->regs[R_DMA_RX_STATUS]; + pktcnt = FIELD_EX32(status, DMA_RX_STATUS, PKTCNT); + pktcnt++; + s->regs[R_DMA_RX_STATUS] = FIELD_DP32(status, DMA_RX_STATUS, + PKTCNT, pktcnt); + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_PKT_RCVD_MASK; + s->rx_desc = d.next; + } else { + s->regs[R_DMA_RX_CTL] &= ~R_DMA_RX_CTL_EN_MASK; + s->regs[R_DMA_RX_STATUS] |= R_DMA_RX_STATUS_OVERFLOW_MASK; + } + emac_update_irq(s); + return size; +} + +static void msf2_emac_reset(DeviceState *dev) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + msf2_emac_do_reset(s); +} + +static void emac_set_link(NetClientState *nc) +{ + MSF2EmacState *s = qemu_get_nic_opaque(nc); + + msf2_phy_update_link(s); +} + +static NetClientInfo net_msf2_emac_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = emac_can_rx, + .receive = emac_rx, + .link_status_changed = emac_set_link, +}; + +static void msf2_emac_realize(DeviceState *dev, Error **errp) +{ + MSF2EmacState *s = MSS_EMAC(dev); + + if (!s->dma_mr) { + error_setg(errp, "MSS_EMAC 'ahb-bus' link not set"); + return; + } + + address_space_init(&s->dma_as, s->dma_mr, "emac-ahb"); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + s->nic = qemu_new_nic(&net_msf2_emac_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static void msf2_emac_init(Object *obj) +{ + MSF2EmacState *s = MSS_EMAC(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &emac_ops, s, + "msf2-emac", R_MAX * 4); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); +} + +static Property msf2_emac_properties[] = { + DEFINE_PROP_LINK("ahb-bus", MSF2EmacState, dma_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_NIC_PROPERTIES(MSF2EmacState, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static const VMStateDescription vmstate_msf2_emac = { + .name = TYPE_MSS_EMAC, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(mac_addr, MSF2EmacState, ETH_ALEN), + VMSTATE_UINT32(rx_desc, MSF2EmacState), + VMSTATE_UINT16_ARRAY(phy_regs, MSF2EmacState, PHY_MAX_REGS), + VMSTATE_UINT32_ARRAY(regs, MSF2EmacState, R_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static void msf2_emac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = msf2_emac_realize; + dc->reset = msf2_emac_reset; + dc->vmsd = &vmstate_msf2_emac; + device_class_set_props(dc, msf2_emac_properties); +} + +static const TypeInfo msf2_emac_info = { + .name = TYPE_MSS_EMAC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(MSF2EmacState), + .instance_init = msf2_emac_init, + .class_init = msf2_emac_class_init, +}; + +static void msf2_emac_register_types(void) +{ + type_register_static(&msf2_emac_info); +} + +type_init(msf2_emac_register_types) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/arm/msf2-soc.h F: include/hw/misc/msf2-sysreg.h F: include/hw/timer/mss-timer.h F: include/hw/ssi/mss-spi.h +F: hw/net/msf2-emac.c +F: include/hw/net/msf2-emac.h Emcraft M2S-FG484 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> With SmartFusion2 Ethernet MAC model in place this patch adds the same to SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-3-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/msf2-soc.h | 2 ++ hw/arm/msf2-soc.c | 26 ++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/mss-timer.h" #include "hw/misc/msf2-sysreg.h" #include "hw/ssi/mss-spi.h" +#include "hw/net/msf2-emac.h" #define TYPE_MSF2_SOC "msf2-soc" #define MSF2_SOC(obj) OBJECT_CHECK(MSF2State, (obj), TYPE_MSF2_SOC) @@ -XXX,XX +XXX,XX @@ typedef struct MSF2State { MSF2SysregState sysreg; MSSTimerState timer; MSSSpiState spi[MSF2_NUM_SPIS]; + MSF2EmacState emac; } MSF2State; #endif diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ /* * SmartFusion2 SoC emulation. * - * Copyright (c) 2017 Subbaraya Sundeep <sundeep.lkml@gmail.com> + * Copyright (c) 2017-2020 Subbaraya Sundeep <sundeep.lkml@gmail.com> * * Permission is hereby granted, free of charge, to any person obtaining a copy * of this software and associated documentation files (the "Software"), to deal @@ -XXX,XX +XXX,XX @@ #define MSF2_TIMER_BASE 0x40004000 #define MSF2_SYSREG_BASE 0x40038000 +#define MSF2_EMAC_BASE 0x40041000 #define ENVM_BASE_ADDRESS 0x60000000 #define SRAM_BASE_ADDRESS 0x20000000 +#define MSF2_EMAC_IRQ 12 + #define MSF2_ENVM_MAX_SIZE (512 * KiB) /* @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_initfn(Object *obj) sysbus_init_child_obj(obj, "spi[*]", &s->spi[i], sizeof(s->spi[i]), TYPE_MSS_SPI); } + + sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), + TYPE_MSS_EMAC); + if (nd_table[0].used) { + qemu_check_nic_model(&nd_table[0], TYPE_MSS_EMAC); + qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]); + } } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) g_free(bus_name); } + dev = DEVICE(&s->emac); + object_property_set_link(OBJECT(&s->emac), OBJECT(get_system_memory()), + "ahb-bus", &error_abort); + object_property_set_bool(OBJECT(&s->emac), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + busdev = SYS_BUS_DEVICE(dev); + sysbus_mmio_map(busdev, 0, MSF2_EMAC_BASE); + sysbus_connect_irq(busdev, 0, + qdev_get_gpio_in(armv7m, MSF2_EMAC_IRQ)); + /* Below devices are not modelled yet. */ create_unimplemented_device("i2c_0", 0x40002000, 0x1000); create_unimplemented_device("dma", 0x40003000, 0x1000); @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("can", 0x40015000, 0x1000); create_unimplemented_device("rtc", 0x40017000, 0x1000); create_unimplemented_device("apb_config", 0x40020000, 0x10000); - create_unimplemented_device("emac", 0x40041000, 0x1000); create_unimplemented_device("usb", 0x40043000, 0x1000); } -- 2.20.1 From: Subbaraya Sundeep <sundeep.lkml@gmail.com> In addition to simple serial test this patch uses ping to test the ethernet block modelled in SmartFusion2 SoC. Signed-off-by: Subbaraya Sundeep <sundeep.lkml@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 1587048891-30493-4-git-send-email-sundeep.lkml@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 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 @@ class BootLinuxConsole(Test): """ uboot_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/u-boot') - uboot_hash = 'abba5d9c24cdd2d49cdc2a8aa92976cf20737eff' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/u-boot') + uboot_hash = 'cbb8cbab970f594bf6523b9855be209c08374ae2' uboot_path = self.fetch_asset(uboot_url, asset_hash=uboot_hash) spi_url = ('https://raw.githubusercontent.com/' 'Subbaraya-Sundeep/qemu-test-binaries/' - 'fa030bd77a014a0b8e360d3b7011df89283a2f0b/spi.bin') - spi_hash = '85f698329d38de63aea6e884a86fbde70890a78a' + 'fe371d32e50ca682391e1e70ab98c2942aeffb01/spi.bin') + spi_hash = '65523a1835949b6f4553be96dec1b6a38fb05501' spi_path = self.fetch_asset(spi_url, asset_hash=spi_hash) self.vm.set_console() @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): '-drive', 'file=' + spi_path + ',if=mtd,format=raw', '-no-reboot') self.vm.launch() - self.wait_for_console_pattern('init started: BusyBox') + self.wait_for_console_pattern('Enter \'help\' for a list') + + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 10.0.2.15', + 'eth0: link becomes ready') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') def do_test_arm_raspi2(self, uart_id): """ -- 2.20.1 This object may be used to represent a clock inside a clock tree. A clock may be connected to another clock so that it receives update, through a callback, whenever the source/parent clock is updated. Although only the root clock of a clock tree controls the values (represented as periods) of all clocks in tree, each clock holds a local state containing the current value so that it can be fetched independently. It will allows us to fullfill migration requirements by migrating each clock independently of others. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-2-damien.hedde@greensocs.com [PMM: Use uint64_t rather than unsigned long long in trace events; the dtrace backend can't handle the latter] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 216 ++++++++++++++++++++++++++++++++++++++++++ hw/core/clock.c | 130 +++++++++++++++++++++++++ hw/core/trace-events | 7 ++ 4 files changed, 354 insertions(+) create mode 100644 include/hw/clock.h create mode 100644 hw/core/clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o +common-obj-y += clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/include/hw/clock.h b/include/hw/clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_HW_CLOCK_H +#define QEMU_HW_CLOCK_H + +#include "qom/object.h" +#include "qemu/queue.h" + +#define TYPE_CLOCK "clock" +#define CLOCK(obj) OBJECT_CHECK(Clock, (obj), TYPE_CLOCK) + +typedef void ClockCallback(void *opaque); + +/* + * clock store a value representing the clock's period in 2^-32ns unit. + * It can represent: + * + periods from 2^-32ns up to 4seconds + * + frequency from ~0.25Hz 2e10Ghz + * Resolution of frequency representation decreases with frequency: + * + at 100MHz, resolution is ~2mHz + * + at 1Ghz, resolution is ~0.2Hz + * + at 10Ghz, resolution is ~20Hz + */ +#define CLOCK_SECOND (1000000000llu << 32) + +/* + * macro helpers to convert to hertz / nanosecond + */ +#define CLOCK_PERIOD_FROM_NS(ns) ((ns) * (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_TO_NS(per) ((per) / (CLOCK_SECOND / 1000000000llu)) +#define CLOCK_PERIOD_FROM_HZ(hz) (((hz) != 0) ? CLOCK_SECOND / (hz) : 0u) +#define CLOCK_PERIOD_TO_HZ(per) (((per) != 0) ? CLOCK_SECOND / (per) : 0u) + +/** + * Clock: + * @parent_obj: parent class + * @period: unsigned integer representing the period of the clock + * @canonical_path: clock path string cache (used for trace purpose) + * @callback: called when clock changes + * @callback_opaque: argument for @callback + * @source: source (or parent in clock tree) of the clock + * @children: list of clocks connected to this one (it is their source) + * @sibling: structure used to form a clock list + */ + +typedef struct Clock Clock; + +struct Clock { + /*< private >*/ + Object parent_obj; + + /* all fields are private and should not be modified directly */ + + /* fields */ + uint64_t period; + char *canonical_path; + ClockCallback *callback; + void *callback_opaque; + + /* Clocks are organized in a clock tree */ + Clock *source; + QLIST_HEAD(, Clock) children; + QLIST_ENTRY(Clock) sibling; +}; + +/** + * clock_setup_canonical_path: + * @clk: clock + * + * compute the canonical path of the clock (used by log messages) + */ +void clock_setup_canonical_path(Clock *clk); + +/** + * clock_set_callback: + * @clk: the clock to register the callback into + * @cb: the callback function + * @opaque: the argument to the callback + * + * Register a callback called on every clock update. + */ +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque); + +/** + * clock_clear_callback: + * @clk: the clock to delete the callback from + * + * Unregister the callback registered with clock_set_callback. + */ +void clock_clear_callback(Clock *clk); + +/** + * clock_set_source: + * @clk: the clock. + * @src: the source clock + * + * Setup @src as the clock source of @clk. The current @src period + * value is also copied to @clk and its subtree but no callback is + * called. + * Further @src update will be propagated to @clk and its subtree. + */ +void clock_set_source(Clock *clk, Clock *src); + +/** + * clock_set: + * @clk: the clock to initialize. + * @value: the clock's value, 0 means unclocked + * + * Set the local cached period value of @clk to @value. + */ +void clock_set(Clock *clk, uint64_t value); + +static inline void clock_set_hz(Clock *clk, unsigned hz) +{ + clock_set(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_set_ns(Clock *clk, unsigned ns) +{ + clock_set(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_propagate: + * @clk: the clock + * + * Propagate the clock period that has been previously configured using + * @clock_set(). This will update recursively all connected clocks. + * It is an error to call this function on a clock which has a source. + * Note: this function must not be called during device inititialization + * or migration. + */ +void clock_propagate(Clock *clk); + +/** + * clock_update: + * @clk: the clock to update. + * @value: the new clock's value, 0 means unclocked + * + * Update the @clk to the new @value. All connected clocks will be informed + * of this update. This is equivalent to call @clock_set() then + * @clock_propagate(). + */ +static inline void clock_update(Clock *clk, uint64_t value) +{ + clock_set(clk, value); + clock_propagate(clk); +} + +static inline void clock_update_hz(Clock *clk, unsigned hz) +{ + clock_update(clk, CLOCK_PERIOD_FROM_HZ(hz)); +} + +static inline void clock_update_ns(Clock *clk, unsigned ns) +{ + clock_update(clk, CLOCK_PERIOD_FROM_NS(ns)); +} + +/** + * clock_get: + * @clk: the clk to fetch the clock + * + * @return: the current period. + */ +static inline uint64_t clock_get(const Clock *clk) +{ + return clk->period; +} + +static inline unsigned clock_get_hz(Clock *clk) +{ + return CLOCK_PERIOD_TO_HZ(clock_get(clk)); +} + +static inline unsigned clock_get_ns(Clock *clk) +{ + return CLOCK_PERIOD_TO_NS(clock_get(clk)); +} + +/** + * clock_is_enabled: + * @clk: a clock + * + * @return: true if the clock is running. + */ +static inline bool clock_is_enabled(const Clock *clk) +{ + return clock_get(clk) != 0; +} + +static inline void clock_init(Clock *clk, uint64_t value) +{ + clock_set(clk, value); +} +static inline void clock_init_hz(Clock *clk, uint64_t value) +{ + clock_set_hz(clk, value); +} +static inline void clock_init_ns(Clock *clk, uint64_t value) +{ + clock_set_ns(clk, value); +} + +#endif /* QEMU_HW_CLOCK_H */ diff --git a/hw/core/clock.c b/hw/core/clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Hardware Clocks + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/clock.h" +#include "trace.h" + +#define CLOCK_PATH(_clk) (_clk->canonical_path) + +void clock_setup_canonical_path(Clock *clk) +{ + g_free(clk->canonical_path); + clk->canonical_path = object_get_canonical_path(OBJECT(clk)); +} + +void clock_set_callback(Clock *clk, ClockCallback *cb, void *opaque) +{ + clk->callback = cb; + clk->callback_opaque = opaque; +} + +void clock_clear_callback(Clock *clk) +{ + clock_set_callback(clk, NULL, NULL); +} + +void clock_set(Clock *clk, uint64_t period) +{ + trace_clock_set(CLOCK_PATH(clk), CLOCK_PERIOD_TO_NS(clk->period), + CLOCK_PERIOD_TO_NS(period)); + clk->period = period; +} + +static void clock_propagate_period(Clock *clk, bool call_callbacks) +{ + Clock *child; + + QLIST_FOREACH(child, &clk->children, sibling) { + if (child->period != clk->period) { + child->period = clk->period; + trace_clock_update(CLOCK_PATH(child), CLOCK_PATH(clk), + CLOCK_PERIOD_TO_NS(clk->period), + call_callbacks); + if (call_callbacks && child->callback) { + child->callback(child->callback_opaque); + } + clock_propagate_period(child, call_callbacks); + } + } +} + +void clock_propagate(Clock *clk) +{ + assert(clk->source == NULL); + trace_clock_propagate(CLOCK_PATH(clk)); + clock_propagate_period(clk, true); +} + +void clock_set_source(Clock *clk, Clock *src) +{ + /* changing clock source is not supported */ + assert(!clk->source); + + trace_clock_set_source(CLOCK_PATH(clk), CLOCK_PATH(src)); + + clk->period = src->period; + QLIST_INSERT_HEAD(&src->children, clk, sibling); + clk->source = src; + clock_propagate_period(clk, false); +} + +static void clock_disconnect(Clock *clk) +{ + if (clk->source == NULL) { + return; + } + + trace_clock_disconnect(CLOCK_PATH(clk)); + + clk->source = NULL; + QLIST_REMOVE(clk, sibling); +} + +static void clock_initfn(Object *obj) +{ + Clock *clk = CLOCK(obj); + + QLIST_INIT(&clk->children); +} + +static void clock_finalizefn(Object *obj) +{ + Clock *clk = CLOCK(obj); + Clock *child, *next; + + /* clear our list of children */ + QLIST_FOREACH_SAFE(child, &clk->children, sibling, next) { + clock_disconnect(child); + } + + /* remove us from source's children list */ + clock_disconnect(clk); + + g_free(clk->canonical_path); +} + +static const TypeInfo clock_info = { + .name = TYPE_CLOCK, + .parent = TYPE_OBJECT, + .instance_size = sizeof(Clock), + .instance_init = clock_initfn, + .instance_finalize = clock_finalizefn, +}; + +static void clock_register_types(void) +{ + type_register_static(&clock_info); +} + +type_init(clock_register_types) diff --git a/hw/core/trace-events b/hw/core/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/core/trace-events +++ b/hw/core/trace-events @@ -XXX,XX +XXX,XX @@ resettable_phase_exit_begin(void *obj, const char *objtype, unsigned count, int resettable_phase_exit_exec(void *obj, const char *objtype, int has_method) "obj=%p(%s) method=%d" resettable_phase_exit_end(void *obj, const char *objtype, unsigned count) "obj=%p(%s) count=%d" resettable_transitional_function(void *obj, const char *objtype) "obj=%p(%s)" + +# clock.c +clock_set_source(const char *clk, const char *src) "'%s', src='%s'" +clock_disconnect(const char *clk) "'%s'" +clock_set(const char *clk, uint64_t old, uint64_t new) "'%s', ns=%"PRIu64"->%"PRIu64 +clock_propagate(const char *clk) "'%s'" +clock_update(const char *clk, const char *src, uint64_t val, int cb) "'%s', src='%s', ns=%"PRIu64", cb=%d" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-3-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 1 + include/hw/clock.h | 9 +++++++++ hw/core/clock-vmstate.c | 25 +++++++++++++++++++++++++ 3 files changed, 35 insertions(+) create mode 100644 hw/core/clock-vmstate.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SOFTMMU) += null-machine.o common-obj-$(CONFIG_SOFTMMU) += loader.o common-obj-$(CONFIG_SOFTMMU) += machine-hmp-cmds.o common-obj-$(CONFIG_SOFTMMU) += numa.o +common-obj-$(CONFIG_SOFTMMU) += clock-vmstate.o obj-$(CONFIG_SOFTMMU) += machine-qmp-cmds.o common-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o diff --git a/include/hw/clock.h b/include/hw/clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ struct Clock { QLIST_ENTRY(Clock) sibling; }; +/* + * vmstate description entry to be added in device vmsd. + */ +extern const VMStateDescription vmstate_clock; +#define VMSTATE_CLOCK(field, state) \ + VMSTATE_CLOCK_V(field, state, 0) +#define VMSTATE_CLOCK_V(field, state, version) \ + VMSTATE_STRUCT_POINTER_V(field, state, version, vmstate_clock, Clock) + /** * clock_setup_canonical_path: * @clk: clock diff --git a/hw/core/clock-vmstate.c b/hw/core/clock-vmstate.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/clock-vmstate.c @@ -XXX,XX +XXX,XX @@ +/* + * Clock migration structure + * + * Copyright GreenSocs 2019-2020 + * + * Authors: + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "migration/vmstate.h" +#include "hw/clock.h" + +const VMStateDescription vmstate_clock = { + .name = "clock", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT64(period, Clock), + VMSTATE_END_OF_LIST() + } +}; -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add functions to easily handle clocks with devices. Clock inputs and outputs should be used to handle clock propagation between devices. The API is very similar the GPIO API. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-4-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/core/Makefile.objs | 2 +- tests/Makefile.include | 1 + include/hw/qdev-clock.h | 104 +++++++++++++++++++++++++ include/hw/qdev-core.h | 12 +++ hw/core/qdev-clock.c | 168 ++++++++++++++++++++++++++++++++++++++++ hw/core/qdev.c | 12 +++ 6 files changed, 298 insertions(+), 1 deletion(-) create mode 100644 include/hw/qdev-clock.h create mode 100644 hw/core/qdev-clock.c diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += hotplug.o common-obj-y += vmstate-if.o # irq.o needed for qdev GPIO handling: common-obj-y += irq.o -common-obj-y += clock.o +common-obj-y += clock.o qdev-clock.o common-obj-$(CONFIG_SOFTMMU) += reset.o common-obj-$(CONFIG_SOFTMMU) += qdev-fw.o diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ tests/test-qdev-global-props$(EXESUF): tests/test-qdev-global-props.o \ hw/core/fw-path-provider.o \ hw/core/reset.o \ hw/core/vmstate-if.o \ + hw/core/clock.o hw/core/qdev-clock.o \ $(test-qapi-obj-y) tests/test-vmstate$(EXESUF): tests/test-vmstate.o \ migration/vmstate.o migration/vmstate-types.o migration/qemu-file.o \ diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef QDEV_CLOCK_H +#define QDEV_CLOCK_H + +#include "hw/clock.h" + +/** + * qdev_init_clock_in: + * @dev: the device to add an input clock to + * @name: the name of the clock (can't be NULL). + * @callback: optional callback to be called on update or NULL. + * @opaque: argument for the callback + * @returns: a pointer to the newly added clock + * + * Add an input clock to device @dev as a clock named @name. + * This adds a child<> property. + * The callback will be called with @opaque as opaque parameter. + */ +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque); + +/** + * qdev_init_clock_out: + * @dev: the device to add an output clock to + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the newly added clock + * + * Add an output clock to device @dev as a clock named @name. + * This adds a child<> property. + */ +Clock *qdev_init_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_in: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the input clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_in(DeviceState *dev, const char *name); + +/** + * qdev_get_clock_out: + * @dev: the device which has the clock + * @name: the name of the clock (can't be NULL). + * @returns: a pointer to the clock + * + * Get the output clock @name from @dev or NULL if does not exist. + */ +Clock *qdev_get_clock_out(DeviceState *dev, const char *name); + +/** + * qdev_connect_clock_in: + * @dev: a device + * @name: the name of an input clock in @dev + * @source: the source clock (an output clock of another device for example) + * + * Set the source clock of input clock @name of device @dev to @source. + * @source period update will be propagated to @name clock. + */ +static inline void qdev_connect_clock_in(DeviceState *dev, const char *name, + Clock *source) +{ + clock_set_source(qdev_get_clock_in(dev, name), source); +} + +/** + * qdev_alias_clock: + * @dev: the device which has the clock + * @name: the name of the clock in @dev (can't be NULL) + * @alias_dev: the device to add the clock + * @alias_name: the name of the clock in @container + * @returns: a pointer to the clock + * + * Add a clock @alias_name in @alias_dev which is an alias of the clock @name + * in @dev. The direction _in_ or _out_ will the same as the original. + * An alias clock must not be modified or used by @alias_dev and should + * typically be only only for device composition purpose. + */ +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name); + +/** + * qdev_finalize_clocklist: + * @dev: the device being finalized + * + * Clear the clocklist from @dev. Only used internally in qdev. + */ +void qdev_finalize_clocklist(DeviceState *dev); + +#endif /* QDEV_CLOCK_H */ diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-core.h +++ b/include/hw/qdev-core.h @@ -XXX,XX +XXX,XX @@ struct NamedGPIOList { QLIST_ENTRY(NamedGPIOList) node; }; +typedef struct Clock Clock; +typedef struct NamedClockList NamedClockList; + +struct NamedClockList { + char *name; + Clock *clock; + bool output; + bool alias; + QLIST_ENTRY(NamedClockList) node; +}; + /** * DeviceState: * @realized: Indicates whether the device has been fully constructed. @@ -XXX,XX +XXX,XX @@ struct DeviceState { bool allow_unplug_during_migration; BusState *parent_bus; QLIST_HEAD(, NamedGPIOList) gpios; + QLIST_HEAD(, NamedClockList) clocks; QLIST_HEAD(, BusState) child_bus; int num_child_bus; int instance_id_alias; diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ +/* + * Device's clock input and output + * + * Copyright GreenSocs 2016-2020 + * + * Authors: + * Frederic Konrad + * Damien Hedde + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-core.h" +#include "qapi/error.h" + +/* + * qdev_init_clocklist: + * Add a new clock in a device + */ +static NamedClockList *qdev_init_clocklist(DeviceState *dev, const char *name, + bool output, Clock *clk) +{ + NamedClockList *ncl; + + /* + * Clock must be added before realize() so that we can compute the + * clock's canonical path during device_realize(). + */ + assert(!dev->realized); + + /* + * The ncl structure is freed by qdev_finalize_clocklist() which will + * be called during @dev's device_finalize(). + */ + ncl = g_new0(NamedClockList, 1); + ncl->name = g_strdup(name); + ncl->output = output; + ncl->alias = (clk != NULL); + + /* + * Trying to create a clock whose name clashes with some other + * clock or property is a bug in the caller and we will abort(). + */ + if (clk == NULL) { + clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(dev), name, OBJECT(clk), &error_abort); + if (output) { + /* + * Remove object_new()'s initial reference. + * Note that for inputs, the reference created by object_new() + * will be deleted in qdev_finalize_clocklist(). + */ + object_unref(OBJECT(clk)); + } + } else { + object_property_add_link(OBJECT(dev), name, + object_get_typename(OBJECT(clk)), + (Object **) &ncl->clock, + NULL, OBJ_PROP_LINK_STRONG, &error_abort); + } + + ncl->clock = clk; + + QLIST_INSERT_HEAD(&dev->clocks, ncl, node); + return ncl; +} + +void qdev_finalize_clocklist(DeviceState *dev) +{ + /* called by @dev's device_finalize() */ + NamedClockList *ncl, *ncl_next; + + QLIST_FOREACH_SAFE(ncl, &dev->clocks, node, ncl_next) { + QLIST_REMOVE(ncl, node); + if (!ncl->output && !ncl->alias) { + /* + * We kept a reference on the input clock to ensure it lives up to + * this point so we can safely remove the callback. + * It avoids having a callback to a deleted object if ncl->clock + * is still referenced somewhere else (eg: by a clock output). + */ + clock_clear_callback(ncl->clock); + object_unref(OBJECT(ncl->clock)); + } + g_free(ncl->name); + g_free(ncl); + } +} + +Clock *qdev_init_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, true, NULL); + + return ncl->clock; +} + +Clock *qdev_init_clock_in(DeviceState *dev, const char *name, + ClockCallback *callback, void *opaque) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_init_clocklist(dev, name, false, NULL); + + if (callback) { + clock_set_callback(ncl->clock, callback, opaque); + } + return ncl->clock; +} + +static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (strcmp(name, ncl->name) == 0) { + return ncl; + } + } + + return NULL; +} + +Clock *qdev_get_clock_in(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(!ncl->output); + + return ncl->clock; +} + +Clock *qdev_get_clock_out(DeviceState *dev, const char *name) +{ + NamedClockList *ncl; + + assert(name); + + ncl = qdev_get_clocklist(dev, name); + assert(ncl->output); + + return ncl->clock; +} + +Clock *qdev_alias_clock(DeviceState *dev, const char *name, + DeviceState *alias_dev, const char *alias_name) +{ + NamedClockList *ncl; + + assert(name && alias_name); + + ncl = qdev_get_clocklist(dev, name); + + qdev_init_clocklist(alias_dev, alias_name, ncl->output, ncl->clock); + + return ncl->clock; +} diff --git a/hw/core/qdev.c b/hw/core/qdev.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "hw/boards.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "migration/vmstate.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) DeviceClass *dc = DEVICE_GET_CLASS(dev); HotplugHandler *hotplug_ctrl; BusState *bus; + NamedClockList *ncl; Error *local_err = NULL; bool unattached_parent = false; static int unattached_count; @@ -XXX,XX +XXX,XX @@ static void device_set_realized(Object *obj, bool value, Error **errp) */ g_free(dev->canonical_path); dev->canonical_path = object_get_canonical_path(OBJECT(dev)); + QLIST_FOREACH(ncl, &dev->clocks, node) { + if (ncl->alias) { + continue; + } else { + clock_setup_canonical_path(ncl->clock); + } + } if (qdev_get_vmsd(dev)) { if (vmstate_register_with_alias_id(VMSTATE_IF(dev), @@ -XXX,XX +XXX,XX @@ static void device_initfn(Object *obj) dev->allow_unplug_during_migration = false; QLIST_INIT(&dev->gpios); + QLIST_INIT(&dev->clocks); } static void device_post_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void device_finalize(Object *obj) */ } + qdev_finalize_clocklist(dev); + /* Only send event if the device had been completely realized */ if (dev->pending_deleted_event) { g_assert(dev->canonical_path); -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Introduce a function and macro helpers to setup several clocks in a device from a static array description. An element of the array describes the clock (name and direction) as well as the related callback and an optional offset to store the created object pointer in the device state structure. The array must be terminated by a special element QDEV_CLOCK_END. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-5-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/qdev-clock.h | 55 +++++++++++++++++++++++++++++++++++++++++ hw/core/qdev-clock.c | 17 +++++++++++++ 2 files changed, 72 insertions(+) diff --git a/include/hw/qdev-clock.h b/include/hw/qdev-clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/qdev-clock.h +++ b/include/hw/qdev-clock.h @@ -XXX,XX +XXX,XX @@ Clock *qdev_alias_clock(DeviceState *dev, const char *name, */ void qdev_finalize_clocklist(DeviceState *dev); +/** + * ClockPortInitElem: + * @name: name of the clock (can't be NULL) + * @output: indicates whether the clock is input or output + * @callback: for inputs, optional callback to be called on clock's update + * with device as opaque + * @offset: optional offset to store the ClockIn or ClockOut pointer in device + * state structure (0 means unused) + */ +struct ClockPortInitElem { + const char *name; + bool is_output; + ClockCallback *callback; + size_t offset; +}; + +#define clock_offset_value(devstate, field) \ + (offsetof(devstate, field) + \ + type_check(Clock *, typeof_field(devstate, field))) + +#define QDEV_CLOCK(out_not_in, devstate, field, cb) { \ + .name = (stringify(field)), \ + .is_output = out_not_in, \ + .callback = cb, \ + .offset = clock_offset_value(devstate, field), \ +} + +/** + * QDEV_CLOCK_(IN|OUT): + * @devstate: structure type. @dev argument of qdev_init_clocks below must be + * a pointer to that same type. + * @field: a field in @_devstate (must be Clock*) + * @callback: (for input only) callback (or NULL) to be called with the device + * state as argument + * + * The name of the clock will be derived from @field + */ +#define QDEV_CLOCK_IN(devstate, field, callback) \ + QDEV_CLOCK(false, devstate, field, callback) + +#define QDEV_CLOCK_OUT(devstate, field) \ + QDEV_CLOCK(true, devstate, field, NULL) + +#define QDEV_CLOCK_END { .name = NULL } + +typedef struct ClockPortInitElem ClockPortInitArray[]; + +/** + * qdev_init_clocks: + * @dev: the device to add clocks to + * @clocks: a QDEV_CLOCK_END-terminated array which contains the + * clocks information. + */ +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks); + #endif /* QDEV_CLOCK_H */ diff --git a/hw/core/qdev-clock.c b/hw/core/qdev-clock.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev-clock.c +++ b/hw/core/qdev-clock.c @@ -XXX,XX +XXX,XX @@ Clock *qdev_init_clock_in(DeviceState *dev, const char *name, return ncl->clock; } +void qdev_init_clocks(DeviceState *dev, const ClockPortInitArray clocks) +{ + const struct ClockPortInitElem *elem; + + for (elem = &clocks[0]; elem->name != NULL; elem++) { + Clock **clkp; + /* offset cannot be inside the DeviceState part */ + assert(elem->offset > sizeof(DeviceState)); + clkp = (Clock **)(((void *) dev) + elem->offset); + if (elem->is_output) { + *clkp = qdev_init_clock_out(dev, elem->name); + } else { + *clkp = qdev_init_clock_in(dev, elem->name, elem->callback, dev); + } + } +} + static NamedClockList *qdev_get_clocklist(DeviceState *dev, const char *name) { NamedClockList *ncl; -- 2.20.1 Add the documentation about the clock inputs and outputs in devices. This is based on the original work of Frederic Konrad. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-6-damien.hedde@greensocs.com [PMM: Editing pass for minor grammar, style and Sphinx formatting fixes] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/devel/clocks.rst | 391 ++++++++++++++++++++++++++++++++++++++++++ docs/devel/index.rst | 1 + 2 files changed, 392 insertions(+) create mode 100644 docs/devel/clocks.rst diff --git a/docs/devel/clocks.rst b/docs/devel/clocks.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/clocks.rst @@ -XXX,XX +XXX,XX @@ +Modelling a clock tree in QEMU +============================== + +What are clocks? +---------------- + +Clocks are QOM objects developed for the purpose of modelling the +distribution of clocks in QEMU. + +They allow us to model the clock distribution of a platform and detect +configuration errors in the clock tree such as badly configured PLL, clock +source selection or disabled clock. + +The object is *Clock* and its QOM name is ``clock`` (in C code, the macro +``TYPE_CLOCK``). + +Clocks are typically used with devices where they are used to model inputs +and outputs. They are created in a similar way to GPIOs. Inputs and outputs +of different devices can be connected together. + +In these cases a Clock object is a child of a Device object, but this +is not a requirement. Clocks can be independent of devices. For +example it is possible to create a clock outside of any device to +model the main clock source of a machine. + +Here is an example of clocks:: + + +---------+ +----------------------+ +--------------+ + | Clock 1 | | Device B | | Device C | + | | | +-------+ +-------+ | | +-------+ | + | |>>-+-->>|Clock 2| |Clock 3|>>--->>|Clock 6| | + +---------+ | | | (in) | | (out) | | | | (in) | | + | | +-------+ +-------+ | | +-------+ | + | | +-------+ | +--------------+ + | | |Clock 4|>> + | | | (out) | | +--------------+ + | | +-------+ | | Device D | + | | +-------+ | | +-------+ | + | | |Clock 5|>>--->>|Clock 7| | + | | | (out) | | | | (in) | | + | | +-------+ | | +-------+ | + | +----------------------+ | | + | | +-------+ | + +----------------------------->>|Clock 8| | + | | (in) | | + | +-------+ | + +--------------+ + +Clocks are defined in the ``include/hw/clock.h`` header and device +related functions are defined in the ``include/hw/qdev-clock.h`` +header. + +The clock state +--------------- + +The state of a clock is its period; it is stored as an integer +representing it in units of 2 :sup:`-32` ns. The special value of 0 is used to +represent the clock being inactive or gated. The clocks do not model +the signal itself (pin toggling) or other properties such as the duty +cycle. + +All clocks contain this state: outputs as well as inputs. This allows +the current period of a clock to be fetched at any time. When a clock +is updated, the value is immediately propagated to all connected +clocks in the tree. + +To ease interaction with clocks, helpers with a unit suffix are defined for +every clock state setter or getter. The suffixes are: + +- ``_ns`` for handling periods in nanoseconds +- ``_hz`` for handling frequencies in hertz + +The 0 period value is converted to 0 in hertz and vice versa. 0 always means +that the clock is disabled. + +Adding a new clock +------------------ + +Adding clocks to a device must be done during the init method of the Device +instance. + +To add an input clock to a device, the function ``qdev_init_clock_in()`` +must be used. It takes the name, a callback and an opaque parameter +for the callback (this will be explained in a following section). +Output is simpler; only the name is required. Typically:: + + qdev_init_clock_in(DEVICE(dev), "clk_in", clk_in_callback, dev); + qdev_init_clock_out(DEVICE(dev), "clk_out"); + +Both functions return the created Clock pointer, which should be saved in the +device's state structure for further use. + +These objects will be automatically deleted by the QOM reference mechanism. + +Note that it is possible to create a static array describing clock inputs and +outputs. The function ``qdev_init_clocks()`` must be called with the array as +parameter to initialize the clocks: it has the same behaviour as calling the +``qdev_init_clock_in/out()`` for each clock in the array. To ease the array +construction, some macros are defined in ``include/hw/qdev-clock.h``. +As an example, the following creates 2 clocks to a device: one input and one +output. + +.. code-block:: c + + /* device structure containing pointers to the clock objects */ + typedef struct MyDeviceState { + DeviceState parent_obj; + Clock *clk_in; + Clock *clk_out; + } MyDeviceState; + + /* + * callback for the input clock (see "Callback on input clock + * change" section below for more information). + */ + static void clk_in_callback(void *opaque); + + /* + * static array describing clocks: + * + a clock input named "clk_in", whose pointer is stored in + * the clk_in field of a MyDeviceState structure with callback + * clk_in_callback. + * + a clock output named "clk_out" whose pointer is stored in + * the clk_out field of a MyDeviceState structure. + */ + static const ClockPortInitArray mydev_clocks = { + QDEV_CLOCK_IN(MyDeviceState, clk_in, clk_in_callback), + QDEV_CLOCK_OUT(MyDeviceState, clk_out), + QDEV_CLOCK_END + }; + + /* device initialization function */ + static void mydev_init(Object *obj) + { + /* cast to MyDeviceState */ + MyDeviceState *mydev = MYDEVICE(obj); + /* create and fill the pointer fields in the MyDeviceState */ + qdev_init_clocks(mydev, mydev_clocks); + [...] + } + +An alternative way to create a clock is to simply call +``object_new(TYPE_CLOCK)``. In that case the clock will neither be an +input nor an output of a device. After the whole QOM hierarchy of the +clock has been set ``clock_setup_canonical_path()`` should be called. + +At creation, the period of the clock is 0: the clock is disabled. You can +change it using ``clock_set_ns()`` or ``clock_set_hz()``. + +Note that if you are creating a clock with a fixed period which will never +change (for example the main clock source of a board), then you'll have +nothing else to do. This value will be propagated to other clocks when +connecting the clocks together and devices will fetch the right value during +the first reset. + +Retrieving clocks from a device +------------------------------- + +``qdev_get_clock_in()`` and ``dev_get_clock_out()`` are available to +get the clock inputs or outputs of a device. For example: + +.. code-block:: c + + Clock *clk = qdev_get_clock_in(DEVICE(mydev), "clk_in"); + +or: + +.. code-block:: c + + Clock *clk = qdev_get_clock_out(DEVICE(mydev), "clk_out"); + +Connecting two clocks together +------------------------------ + +To connect two clocks together, use the ``clock_set_source()`` function. +Given two clocks ``clk1``, and ``clk2``, ``clock_set_source(clk2, clk1);`` +configures ``clk2`` to follow the ``clk1`` period changes. Every time ``clk1`` +is updated, ``clk2`` will be updated too. + +When connecting clock between devices, prefer using the +``qdev_connect_clock_in()`` function to set the source of an input +device clock. For example, to connect the input clock ``clk2`` of +``devB`` to the output clock ``clk1`` of ``devA``, do: + +.. code-block:: c + + qdev_connect_clock_in(devB, "clk2", qdev_get_clock_out(devA, "clk1")) + +We used ``qdev_get_clock_out()`` above, but any clock can drive an +input clock, even another input clock. The following diagram shows +some examples of connections. Note also that a clock can drive several +other clocks. + +:: + + +------------+ +--------------------------------------------------+ + | Device A | | Device B | + | | | +---------------------+ | + | | | | Device C | | + | +-------+ | | +-------+ | +-------+ +-------+ | +-------+ | + | |Clock 1|>>-->>|Clock 2|>>+-->>|Clock 3| |Clock 5|>>>>|Clock 6|>> + | | (out) | | | | (in) | | | | (in) | | (out) | | | (out) | | + | +-------+ | | +-------+ | | +-------+ +-------+ | +-------+ | + +------------+ | | +---------------------+ | + | | | + | | +--------------+ | + | | | Device D | | + | | | +-------+ | | + | +-->>|Clock 4| | | + | | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------------------------------+ + +In the above example, when *Clock 1* is updated by *Device A*, three +clocks get the new clock period value: *Clock 2*, *Clock 3* and *Clock 4*. + +It is not possible to disconnect a clock or to change the clock connection +after it is connected. + +Unconnected input clocks +------------------------ + +A newly created input clock is disabled (period of 0). This means the +clock will be considered as disabled until the period is updated. If +the clock remains unconnected it will always keep its initial value +of 0. If this is not the desired behaviour, ``clock_set()``, +``clock_set_ns()`` or ``clock_set_hz()`` should be called on the Clock +object during device instance init. For example: + +.. code-block:: c + + clk = qdev_init_clock_in(DEVICE(dev), "clk-in", clk_in_callback, + dev); + /* set initial value to 10ns / 100MHz */ + clock_set_ns(clk, 10); + +Fetching clock frequency/period +------------------------------- + +To get the current state of a clock, use the functions ``clock_get()``, +``clock_get_ns()`` or ``clock_get_hz()``. + +It is also possible to register a callback on clock frequency changes. +Here is an example: + +.. code-block:: c + + void clock_callback(void *opaque) { + MyDeviceState *s = (MyDeviceState *) opaque; + /* + * 'opaque' is the argument passed to qdev_init_clock_in(); + * usually this will be the device state pointer. + */ + + /* do something with the new period */ + fprintf(stdout, "device new period is %" PRIu64 "ns\n", + clock_get_ns(dev->my_clk_input)); + } + +Changing a clock period +----------------------- + +A device can change its outputs using the ``clock_update()``, +``clock_update_ns()`` or ``clock_update_hz()`` function. It will trigger +updates on every connected input. + +For example, let's say that we have an output clock *clkout* and we +have a pointer to it in the device state because we did the following +in init phase: + +.. code-block:: c + + dev->clkout = qdev_init_clock_out(DEVICE(dev), "clkout"); + +Then at any time (apart from the cases listed below), it is possible to +change the clock value by doing: + +.. code-block:: c + + clock_update_hz(dev->clkout, 1000 * 1000 * 1000); /* 1GHz */ + +Because updating a clock may trigger any side effects through +connected clocks and their callbacks, this operation must be done +while holding the qemu io lock. + +For the same reason, one can update clocks only when it is allowed to have +side effects on other objects. In consequence, it is forbidden: + +* during migration, +* and in the enter phase of reset. + +Note that calling ``clock_update[_ns|_hz]()`` is equivalent to calling +``clock_set[_ns|_hz]()`` (with the same arguments) then +``clock_propagate()`` on the clock. Thus, setting the clock value can +be separated from triggering the side-effects. This is often required +to factorize code to handle reset and migration in devices. + +Aliasing clocks +--------------- + +Sometimes, one needs to forward, or inherit, a clock from another +device. Typically, when doing device composition, a device might +expose a sub-device's clock without interfering with it. The function +``qdev_alias_clock()`` can be used to achieve this behaviour. Note +that it is possible to expose the clock under a different name. +``qdev_alias_clock()`` works for both input and output clocks. + +For example, if device B is a child of device A, +``device_a_instance_init()`` may do something like this: + +.. code-block:: c + + void device_a_instance_init(Object *obj) + { + AState *A = DEVICE_A(obj); + BState *B; + /* create object B as child of A */ + [...] + qdev_alias_clock(B, "clk", A, "b_clk"); + /* + * Now A has a clock "b_clk" which is an alias to + * the clock "clk" of its child B. + */ + } + +This function does not return any clock object. The new clock has the +same direction (input or output) as the original one. This function +only adds a link to the existing clock. In the above example, object B +remains the only object allowed to use the clock and device A must not +try to change the clock period or set a callback to the clock. This +diagram describes the example with an input clock:: + + +--------------------------+ + | Device A | + | +--------------+ | + | | Device B | | + | | +-------+ | | + >>"b_clk">>>| "clk" | | | + | (in) | | (in) | | | + | | +-------+ | | + | +--------------+ | + +--------------------------+ + +Migration +--------- + +Clock state is not migrated automatically. Every device must handle its +clock migration. Alias clocks must not be migrated. + +To ensure clock states are restored correctly during migration, there +are two solutions. + +Clock states can be migrated by adding an entry into the device +vmstate description. You should use the ``VMSTATE_CLOCK`` macro for this. +This is typically used to migrate an input clock state. For example: + +.. code-block:: c + + MyDeviceState { + DeviceState parent_obj; + [...] /* some fields */ + Clock *clk; + }; + + VMStateDescription my_device_vmstate = { + .name = "my_device", + .fields = (VMStateField[]) { + [...], /* other migrated fields */ + VMSTATE_CLOCK(clk, MyDeviceState), + VMSTATE_END_OF_LIST() + } + }; + +The second solution is to restore the clock state using information already +at our disposal. This can be used to restore output clock states using the +device state. The functions ``clock_set[_ns|_hz]()`` can be used during the +``post_load()`` migration callback. + +When adding clock support to an existing device, if you care about +migration compatibility you will need to be careful, as simply adding +a ``VMSTATE_CLOCK()`` line will break compatibility. Instead, you can +put the ``VMSTATE_CLOCK()`` line into a vmstate subsection with a +suitable ``needed`` function, and use ``clock_set()`` in a +``pre_load()`` function to set the default value that will be used if +the source virtual machine in the migration does not send the clock +state. + +Care should be taken not to use ``clock_update[_ns|_hz]()`` or +``clock_propagate()`` during the whole migration procedure because it +will trigger side effects to other devices in an unknown state. diff --git a/docs/devel/index.rst b/docs/devel/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -XXX,XX +XXX,XX @@ Contents: bitops reset s390-dasd-ipl + clocks -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add some clocks to zynq_slcr + the main input clock (ps_clk) + the reference clock outputs for each uart (uart0 & 1) This commit also transitional the slcr to multi-phase reset as it is required to initialize the clocks correctly. The clock frequencies are computed using the internal pll & uart configuration registers and the input ps_clk frequency. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Acked-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-7-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 172 ++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 168 insertions(+), 4 deletions(-) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "qemu/module.h" #include "hw/registerfields.h" +#include "hw/qdev-clock.h" #ifndef ZYNQ_SLCR_ERR_DEBUG #define ZYNQ_SLCR_ERR_DEBUG 0 @@ -XXX,XX +XXX,XX @@ REG32(LOCKSTA, 0x00c) REG32(ARM_PLL_CTRL, 0x100) REG32(DDR_PLL_CTRL, 0x104) REG32(IO_PLL_CTRL, 0x108) +/* fields for [ARM|DDR|IO]_PLL_CTRL registers */ + FIELD(xxx_PLL_CTRL, PLL_RESET, 0, 1) + FIELD(xxx_PLL_CTRL, PLL_PWRDWN, 1, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_QUAL, 3, 1) + FIELD(xxx_PLL_CTRL, PLL_BYPASS_FORCE, 4, 1) + FIELD(xxx_PLL_CTRL, PLL_FPDIV, 12, 7) REG32(PLL_STATUS, 0x10c) REG32(ARM_PLL_CFG, 0x110) REG32(DDR_PLL_CFG, 0x114) @@ -XXX,XX +XXX,XX @@ REG32(SMC_CLK_CTRL, 0x148) REG32(LQSPI_CLK_CTRL, 0x14c) REG32(SDIO_CLK_CTRL, 0x150) REG32(UART_CLK_CTRL, 0x154) + FIELD(UART_CLK_CTRL, CLKACT0, 0, 1) + FIELD(UART_CLK_CTRL, CLKACT1, 1, 1) + FIELD(UART_CLK_CTRL, SRCSEL, 4, 2) + FIELD(UART_CLK_CTRL, DIVISOR, 8, 6) REG32(SPI_CLK_CTRL, 0x158) REG32(CAN_CLK_CTRL, 0x15c) REG32(CAN_MIOCLK_CTRL, 0x160) @@ -XXX,XX +XXX,XX @@ typedef struct ZynqSLCRState { MemoryRegion iomem; uint32_t regs[ZYNQ_SLCR_NUM_REGS]; + + Clock *ps_clk; + Clock *uart0_ref_clk; + Clock *uart1_ref_clk; } ZynqSLCRState; -static void zynq_slcr_reset(DeviceState *d) +/* + * return the output frequency of ARM/DDR/IO pll + * using input frequency and PLL_CTRL register + */ +static uint64_t zynq_slcr_compute_pll(uint64_t input, uint32_t ctrl_reg) { - ZynqSLCRState *s = ZYNQ_SLCR(d); + uint32_t mult = ((ctrl_reg & R_xxx_PLL_CTRL_PLL_FPDIV_MASK) >> + R_xxx_PLL_CTRL_PLL_FPDIV_SHIFT); + + /* first, check if pll is bypassed */ + if (ctrl_reg & R_xxx_PLL_CTRL_PLL_BYPASS_FORCE_MASK) { + return input; + } + + /* is pll disabled ? */ + if (ctrl_reg & (R_xxx_PLL_CTRL_PLL_RESET_MASK | + R_xxx_PLL_CTRL_PLL_PWRDWN_MASK)) { + return 0; + } + + /* frequency multiplier -> period division */ + return input / mult; +} + +/* + * return the output period of a clock given: + * + the periods in an array corresponding to input mux selector + * + the register xxx_CLK_CTRL value + * + enable bit index in ctrl register + * + * This function makes the assumption that the ctrl_reg value is organized as + * follows: + * + bits[13:8] clock frequency divisor + * + bits[5:4] clock mux selector (index in array) + * + bits[index] clock enable + */ +static uint64_t zynq_slcr_compute_clock(const uint64_t periods[], + uint32_t ctrl_reg, + unsigned index) +{ + uint32_t srcsel = extract32(ctrl_reg, 4, 2); /* bits [5:4] */ + uint32_t divisor = extract32(ctrl_reg, 8, 6); /* bits [13:8] */ + + /* first, check if clock is disabled */ + if (((ctrl_reg >> index) & 1u) == 0) { + return 0; + } + + /* + * according to the Zynq technical ref. manual UG585 v1.12.2 in + * Clocks chapter, section 25.10.1 page 705: + * "The 6-bit divider provides a divide range of 1 to 63" + * We follow here what is implemented in linux kernel and consider + * the 0 value as a bypass (no division). + */ + /* frequency divisor -> period multiplication */ + return periods[srcsel] * (divisor ? divisor : 1u); +} + +/* + * macro helper around zynq_slcr_compute_clock to avoid repeating + * the register name. + */ +#define ZYNQ_COMPUTE_CLK(state, plls, reg, enable_field) \ + zynq_slcr_compute_clock((plls), (state)->regs[reg], \ + reg ## _ ## enable_field ## _SHIFT) + +/** + * Compute and set the ouputs clocks periods. + * But do not propagate them further. Connected clocks + * will not receive any updates (See zynq_slcr_compute_clocks()) + */ +static void zynq_slcr_compute_clocks(ZynqSLCRState *s) +{ + uint64_t ps_clk = clock_get(s->ps_clk); + + /* consider outputs clocks are disabled while in reset */ + if (device_is_in_reset(DEVICE(s))) { + ps_clk = 0; + } + + uint64_t io_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_IO_PLL_CTRL]); + uint64_t arm_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_ARM_PLL_CTRL]); + uint64_t ddr_pll = zynq_slcr_compute_pll(ps_clk, s->regs[R_DDR_PLL_CTRL]); + + uint64_t uart_mux[4] = {io_pll, io_pll, arm_pll, ddr_pll}; + + /* compute uartX reference clocks */ + clock_set(s->uart0_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT0)); + clock_set(s->uart1_ref_clk, + ZYNQ_COMPUTE_CLK(s, uart_mux, R_UART_CLK_CTRL, CLKACT1)); +} + +/** + * Propagate the outputs clocks. + * zynq_slcr_compute_clocks() should have been called before + * to configure them. + */ +static void zynq_slcr_propagate_clocks(ZynqSLCRState *s) +{ + clock_propagate(s->uart0_ref_clk); + clock_propagate(s->uart1_ref_clk); +} + +static void zynq_slcr_ps_clk_callback(void *opaque) +{ + ZynqSLCRState *s = (ZynqSLCRState *) opaque; + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_init(Object *obj, ResetType type) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); int i; DB_PRINT("RESET\n"); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset(DeviceState *d) s->regs[R_DDRIOB + 12] = 0x00000021; } +static void zynq_slcr_reset_hold(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will disable all output clocks */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} + +static void zynq_slcr_reset_exit(Object *obj) +{ + ZynqSLCRState *s = ZYNQ_SLCR(obj); + + /* will compute output clocks according to ps_clk and registers */ + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); +} static bool zynq_slcr_check_offset(hwaddr offset, bool rnw) { @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_write(void *opaque, hwaddr offset, qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); } break; + case R_IO_PLL_CTRL: + case R_ARM_PLL_CTRL: + case R_DDR_PLL_CTRL: + case R_UART_CLK_CTRL: + zynq_slcr_compute_clocks(s); + zynq_slcr_propagate_clocks(s); + break; } } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps slcr_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; +static const ClockPortInitArray zynq_slcr_clocks = { + QDEV_CLOCK_IN(ZynqSLCRState, ps_clk, zynq_slcr_ps_clk_callback), + QDEV_CLOCK_OUT(ZynqSLCRState, uart0_ref_clk), + QDEV_CLOCK_OUT(ZynqSLCRState, uart1_ref_clk), + QDEV_CLOCK_END +}; + static void zynq_slcr_init(Object *obj) { ZynqSLCRState *s = ZYNQ_SLCR(obj); @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_init(Object *obj) memory_region_init_io(&s->iomem, obj, &slcr_ops, s, "slcr", ZYNQ_SLCR_MMIO_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->iomem); + + qdev_init_clocks(DEVICE(obj), zynq_slcr_clocks); } static const VMStateDescription vmstate_zynq_slcr = { .name = "zynq_slcr", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(regs, ZynqSLCRState, ZYNQ_SLCR_NUM_REGS), + VMSTATE_CLOCK_V(ps_clk, ZynqSLCRState, 3), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_zynq_slcr = { static void zynq_slcr_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->vmsd = &vmstate_zynq_slcr; - dc->reset = zynq_slcr_reset; + rc->phases.enter = zynq_slcr_reset_init; + rc->phases.hold = zynq_slcr_reset_hold; + rc->phases.exit = zynq_slcr_reset_exit; } static const TypeInfo zynq_slcr_info = { -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Switch the cadence uart to multi-phase reset and add the reference clock input. The input clock frequency is added to the migration structure. The reference clock controls the baudrate generation. If it disabled, any input characters and events are ignored. If this clock remains unconnected, the uart behaves as before (it default to a 50MHz ref clock). Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200406135251.157596-8-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/cadence_uart.h | 1 + hw/char/cadence_uart.c | 73 +++++++++++++++++++++++++++++----- hw/char/trace-events | 3 ++ 3 files changed, 67 insertions(+), 10 deletions(-) diff --git a/include/hw/char/cadence_uart.h b/include/hw/char/cadence_uart.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/cadence_uart.h +++ b/include/hw/char/cadence_uart.h @@ -XXX,XX +XXX,XX @@ typedef struct { CharBackend chr; qemu_irq irq; QEMUTimer *fifo_trigger_handle; + Clock *refclk; } CadenceUARTState; static inline DeviceState *cadence_uart_create(hwaddr addr, diff --git a/hw/char/cadence_uart.c b/hw/char/cadence_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/cadence_uart.c +++ b/hw/char/cadence_uart.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "hw/char/cadence_uart.h" #include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "trace.h" #ifdef CADENCE_UART_ERR_DEBUG #define DB_PRINT(...) do { \ @@ -XXX,XX +XXX,XX @@ #define LOCAL_LOOPBACK (0x2 << UART_MR_CHMODE_SH) #define REMOTE_LOOPBACK (0x3 << UART_MR_CHMODE_SH) -#define UART_INPUT_CLK 50000000 +#define UART_DEFAULT_REF_CLK (50 * 1000 * 1000) #define R_CR (0x00/4) #define R_MR (0x04/4) @@ -XXX,XX +XXX,XX @@ static void uart_send_breaks(CadenceUARTState *s) static void uart_parameters_setup(CadenceUARTState *s) { QEMUSerialSetParams ssp; - unsigned int baud_rate, packet_size; + unsigned int baud_rate, packet_size, input_clk; + input_clk = clock_get_hz(s->refclk); - baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? - UART_INPUT_CLK / 8 : UART_INPUT_CLK; + baud_rate = (s->r[R_MR] & UART_MR_CLKS) ? input_clk / 8 : input_clk; + baud_rate /= (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); + trace_cadence_uart_baudrate(baud_rate); + + ssp.speed = baud_rate; - ssp.speed = baud_rate / (s->r[R_BRGR] * (s->r[R_BDIV] + 1)); packet_size = 1; switch (s->r[R_MR] & UART_MR_PAR) { @@ -XXX,XX +XXX,XX @@ static void uart_parameters_setup(CadenceUARTState *s) } packet_size += ssp.data_bits + ssp.stop_bits; + if (ssp.speed == 0) { + /* + * Avoid division-by-zero below. + * TODO: find something better + */ + ssp.speed = 1; + } s->char_tx_time = (NANOSECONDS_PER_SECOND / ssp.speed) * packet_size; qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_PARAMS, &ssp); } @@ -XXX,XX +XXX,XX @@ static void uart_receive(void *opaque, const uint8_t *buf, int size) CadenceUARTState *s = opaque; uint32_t ch_mode = s->r[R_MR] & UART_MR_CHMODE; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (ch_mode == NORMAL_MODE || ch_mode == ECHO_MODE) { uart_write_rx_fifo(opaque, buf, size); } @@ -XXX,XX +XXX,XX @@ static void uart_event(void *opaque, QEMUChrEvent event) CadenceUARTState *s = opaque; uint8_t buf = '\0'; + /* ignore characters when unclocked or in reset */ + if (!clock_is_enabled(s->refclk) || device_is_in_reset(DEVICE(s))) { + return; + } + if (event == CHR_EVENT_BREAK) { uart_write_rx_fifo(opaque, &buf, 1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps uart_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static void cadence_uart_reset(DeviceState *dev) +static void cadence_uart_reset_init(Object *obj, ResetType type) { - CadenceUARTState *s = CADENCE_UART(dev); + CadenceUARTState *s = CADENCE_UART(obj); s->r[R_CR] = 0x00000128; s->r[R_IMR] = 0; @@ -XXX,XX +XXX,XX @@ static void cadence_uart_reset(DeviceState *dev) s->r[R_BRGR] = 0x0000028B; s->r[R_BDIV] = 0x0000000F; s->r[R_TTRIG] = 0x00000020; +} + +static void cadence_uart_reset_hold(Object *obj) +{ + CadenceUARTState *s = CADENCE_UART(obj); uart_rx_reset(s); uart_tx_reset(s); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_realize(DeviceState *dev, Error **errp) uart_event, NULL, s, NULL, true); } +static void cadence_uart_refclk_update(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* recompute uart's speed on clock change */ + uart_parameters_setup(s); +} + static void cadence_uart_init(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); @@ -XXX,XX +XXX,XX @@ static void cadence_uart_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", + cadence_uart_refclk_update, s); + /* initialize the frequency in case the clock remains unconnected */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + s->char_tx_time = (NANOSECONDS_PER_SECOND / 9600) * 10; } +static int cadence_uart_pre_load(void *opaque) +{ + CadenceUARTState *s = opaque; + + /* the frequency will be overriden if the refclk field is present */ + clock_set_hz(s->refclk, UART_DEFAULT_REF_CLK); + return 0; +} + static int cadence_uart_post_load(void *opaque, int version_id) { CadenceUARTState *s = opaque; @@ -XXX,XX +XXX,XX @@ static int cadence_uart_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_cadence_uart = { .name = "cadence_uart", - .version_id = 2, + .version_id = 3, .minimum_version_id = 2, + .pre_load = cadence_uart_pre_load, .post_load = cadence_uart_post_load, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(r, CadenceUARTState, CADENCE_UART_R_MAX), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_cadence_uart = { VMSTATE_UINT32(tx_count, CadenceUARTState), VMSTATE_UINT32(rx_wpos, CadenceUARTState), VMSTATE_TIMER_PTR(fifo_trigger_handle, CadenceUARTState), + VMSTATE_CLOCK_V(refclk, CadenceUARTState, 3), VMSTATE_END_OF_LIST() - } + }, }; static Property cadence_uart_properties[] = { @@ -XXX,XX +XXX,XX @@ static Property cadence_uart_properties[] = { static void cadence_uart_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); dc->realize = cadence_uart_realize; dc->vmsd = &vmstate_cadence_uart; - dc->reset = cadence_uart_reset; + rc->phases.enter = cadence_uart_reset_init; + rc->phases.hold = cadence_uart_reset_hold; device_class_set_props(dc, cadence_uart_properties); } diff --git a/hw/char/trace-events b/hw/char/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/char/trace-events +++ b/hw/char/trace-events @@ -XXX,XX +XXX,XX @@ exynos_uart_wo_read(uint32_t channel, const char *name, uint32_t reg) "UART%d: T exynos_uart_rxsize(uint32_t channel, uint32_t size) "UART%d: Rx FIFO size: %d" exynos_uart_channel_error(uint32_t channel) "Wrong UART channel number: %d" exynos_uart_rx_timeout(uint32_t channel, uint32_t stat, uint32_t intsp) "UART%d: Rx timeout stat=0x%x intsp=0x%x" + +# hw/char/cadence_uart.c +cadence_uart_baudrate(unsigned baudrate) "baudrate %u" -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> Add the connection between the slcr's output clocks and the uarts inputs. Also add the main board clock 'ps_clk', which is hard-coded to 33.33MHz (the default frequency). This clock is used to feed the slcr's input clock. Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-9-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 57 +++++++++++++++++++++++++++++++++++++------- 1 file changed, 49 insertions(+), 8 deletions(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/cadence_uart.h" #include "hw/net/cadence_gem.h" #include "hw/cpu/a9mpcore.h" +#include "hw/qdev-clock.h" +#include "sysemu/reset.h" + +#define TYPE_ZYNQ_MACHINE MACHINE_TYPE_NAME("xilinx-zynq-a9") +#define ZYNQ_MACHINE(obj) \ + OBJECT_CHECK(ZynqMachineState, (obj), TYPE_ZYNQ_MACHINE) + +/* board base frequency: 33.333333 MHz */ +#define PS_CLK_FREQUENCY (100 * 1000 * 1000 / 3) #define NUM_SPI_FLASHES 4 #define NUM_QSPI_FLASHES 2 @@ -XXX,XX +XXX,XX @@ static const int dma_irqs[8] = { 0xe3401000 + ARMV7_IMM16(extract32((val), 16, 16)), /* movt r1 ... */ \ 0xe5801000 + (addr) +typedef struct ZynqMachineState { + MachineState parent; + Clock *ps_clk; +} ZynqMachineState; + static void zynq_write_board_setup(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static inline void zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, static void zynq_init(MachineState *machine) { + ZynqMachineState *zynq_machine = ZYNQ_MACHINE(machine); ARMCPU *cpu; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *ocm_ram = g_new(MemoryRegion, 1); - DeviceState *dev; + DeviceState *dev, *slcr; SysBusDevice *busdev; qemu_irq pic[64]; int n; @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) 1, 0x0066, 0x0022, 0x0000, 0x0000, 0x0555, 0x2aa, 0); - dev = qdev_create(NULL, "xilinx,zynq_slcr"); - qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0xF8000000); + /* Create slcr, keep a pointer to connect clocks */ + slcr = qdev_create(NULL, "xilinx,zynq_slcr"); + qdev_init_nofail(slcr); + sysbus_mmio_map(SYS_BUS_DEVICE(slcr), 0, 0xF8000000); + + /* Create the main clock source, and feed slcr with it */ + zynq_machine->ps_clk = CLOCK(object_new(TYPE_CLOCK)); + object_property_add_child(OBJECT(zynq_machine), "ps_clk", + OBJECT(zynq_machine->ps_clk), &error_abort); + object_unref(OBJECT(zynq_machine->ps_clk)); + clock_set_hz(zynq_machine->ps_clk, PS_CLK_FREQUENCY); + qdev_connect_clock_in(slcr, "ps_clk", zynq_machine->ps_clk); dev = qdev_create(NULL, TYPE_A9MPCORE_PRIV); qdev_prop_set_uint32(dev, "num-cpu", 1); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_create_simple(TYPE_CHIPIDEA, 0xE0002000, pic[53 - IRQ_OFFSET]); sysbus_create_simple(TYPE_CHIPIDEA, 0xE0003000, pic[76 - IRQ_OFFSET]); - cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); - cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + dev = cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart0_ref_clk")); + dev = cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); + qdev_connect_clock_in(dev, "refclk", + qdev_get_clock_out(slcr, "uart1_ref_clk")); sysbus_create_varargs("cadence_ttc", 0xF8001000, pic[42-IRQ_OFFSET], pic[43-IRQ_OFFSET], pic[44-IRQ_OFFSET], NULL); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) arm_load_kernel(ARM_CPU(first_cpu), machine, &zynq_binfo); } -static void zynq_machine_init(MachineClass *mc) +static void zynq_machine_class_init(ObjectClass *oc, void *data) { + MachineClass *mc = MACHINE_CLASS(oc); mc->desc = "Xilinx Zynq Platform Baseboard for Cortex-A9"; mc->init = zynq_init; mc->max_cpus = 1; @@ -XXX,XX +XXX,XX @@ static void zynq_machine_init(MachineClass *mc) mc->default_ram_id = "zynq.ext_ram"; } -DEFINE_MACHINE("xilinx-zynq-a9", zynq_machine_init) +static const TypeInfo zynq_machine_type = { + .name = TYPE_ZYNQ_MACHINE, + .parent = TYPE_MACHINE, + .class_init = zynq_machine_class_init, + .instance_size = sizeof(ZynqMachineState), +}; + +static void zynq_machine_register_types(void) +{ + type_register_static(&zynq_machine_type); +} + +type_init(zynq_machine_register_types) -- 2.20.1 From: Damien Hedde <damien.hedde@greensocs.com> This prints the clocks attached to a DeviceState when using "info qtree" monitor command. For every clock, it displays the direction, the name and if the clock is forwarded. For input clock, it displays also the frequency. This is based on the original work of Frederic Konrad. Here follows a sample of `info qtree` output on xilinx_zynq machine after linux boot with only one uart clocked: > bus: main-system-bus > type System > [...] > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=0.000000e+00 > chardev = "" > mmio 00000000e0001000/0000000000001000 > dev: cadence_uart, id "" > gpio-out "sysbus-irq" 1 > clock-in "refclk" freq_hz=1.375661e+07 > chardev = "serial0" > mmio 00000000e0000000/0000000000001000 > [...] > dev: xilinx,zynq_slcr, id "" > clock-out "uart1_ref_clk" freq_hz=0.000000e+00 > clock-out "uart0_ref_clk" freq_hz=1.375661e+07 > clock-in "ps_clk" freq_hz=3.333333e+07 > mmio 00000000f8000000/0000000000001000 Signed-off-by: Damien Hedde <damien.hedde@greensocs.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200406135251.157596-10-damien.hedde@greensocs.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qdev-monitor.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/qdev-monitor.c b/qdev-monitor.c index XXXXXXX..XXXXXXX 100644 --- a/qdev-monitor.c +++ b/qdev-monitor.c @@ -XXX,XX +XXX,XX @@ #include "migration/misc.h" #include "migration/migration.h" #include "qemu/cutils.h" +#include "hw/clock.h" /* * Aliases were a bad idea from the start. Let's keep them @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ObjectClass *class; BusState *child; NamedGPIOList *ngl; + NamedClockList *ncl; qdev_printf("dev: %s, id \"%s\"\n", object_get_typename(OBJECT(dev)), dev->id ? dev->id : ""); @@ -XXX,XX +XXX,XX @@ static void qdev_print(Monitor *mon, DeviceState *dev, int indent) ngl->num_out); } } + QLIST_FOREACH(ncl, &dev->clocks, node) { + qdev_printf("clock-%s%s \"%s\" freq_hz=%e\n", + ncl->output ? "out" : "in", + ncl->alias ? " (alias)" : "", + ncl->name, + CLOCK_PERIOD_TO_HZ(1.0 * clock_get(ncl->clock))); + } class = object_get_class(OBJECT(dev)); do { qdev_print_props(mon, dev, DEVICE_CLASS(class)->props_, indent); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Setup the ADMA with 128bit bus-width. This matters when FIXED BURST mode is used. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc.michel@greensocs.com> Message-id: 20200417153800.27399-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-versal.c | 2 ++ 1 file changed, 2 insertions(+) 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 @@ static void versal_create_admas(Versal *s, qemu_irq *pic) dev = qdev_create(NULL, "xlnx.zdma"); s->lpd.iou.adma[i] = SYS_BUS_DEVICE(dev); + object_property_set_int(OBJECT(s->lpd.iou.adma[i]), 128, "bus-width", + &error_abort); object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); qdev_init_nofail(dev); -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> Wraparound of TX descriptor cyclic buffer only updated the low 32 bits of the descriptor. Fix that by checking if we're working with 64bit descriptors. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200417171736.441607-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_transmit(CadenceGEMState *s) /* read next descriptor */ if (tx_desc_get_wrap(desc)) { tx_desc_set_last(desc); - packet_desc_addr = s->regs[GEM_TXQBASE]; + + if (s->regs[GEM_DMACFG] & GEM_DMACFG_ADDR_64B) { + packet_desc_addr = s->regs[GEM_TBQPH]; + packet_desc_addr <<= 32; + } else { + packet_desc_addr = 0; + } + packet_desc_addr |= s->regs[GEM_TXQBASE]; } else { packet_desc_addr += 4 * gem_get_desc_len(s, false); } -- 2.20.1 From: Ramon Fried <rfried.dev@gmail.com> The RX ring descriptors control field is used for setting SOF and EOF (start of frame and end of frame). The SOF and EOF weren't cleared from the previous descriptors, causing inconsistencies in ring buffer. Fix that by clearing the control field of every descriptors we're processing. Signed-off-by: Ramon Fried <rfried.dev@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200418085145.489726-1-rfried.dev@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static inline void rx_desc_set_sof(uint32_t *desc) desc[1] |= DESC_1_RX_SOF; } +static inline void rx_desc_clear_control(uint32_t *desc) +{ + desc[1] = 0; +} + static inline void rx_desc_set_eof(uint32_t *desc) { desc[1] |= DESC_1_RX_EOF; @@ -XXX,XX +XXX,XX @@ static ssize_t gem_receive(NetClientState *nc, const uint8_t *buf, size_t size) rxbuf_ptr += MIN(bytes_to_copy, rxbufsize); bytes_to_copy -= MIN(bytes_to_copy, rxbufsize); + rx_desc_clear_control(s->rx_desc[q]); + /* Update the descriptor. */ if (first_desc) { rx_desc_set_sof(s->rx_desc[q]); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These instructions are often used in glibc's string routines. They were the final uses of the 32-bit at a time neon helpers. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200418162808.4680-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 27 ++-- target/arm/translate.h | 5 + target/arm/neon_helper.c | 24 ---- target/arm/translate-a64.c | 64 +++------- target/arm/translate.c | 256 +++++++++++++++++++++++++++++++------ target/arm/vec_helper.c | 25 ++++ 6 files changed, 278 insertions(+), 123 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_hsub_u16, i32, i32, i32) DEF_HELPER_2(neon_hsub_s32, s32, s32, s32) DEF_HELPER_2(neon_hsub_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s8, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s16, i32, i32, i32) -DEF_HELPER_2(neon_cgt_u32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_s32, i32, i32, i32) -DEF_HELPER_2(neon_cge_u8, i32, i32, i32) -DEF_HELPER_2(neon_cge_s8, i32, i32, i32) -DEF_HELPER_2(neon_cge_u16, i32, i32, i32) -DEF_HELPER_2(neon_cge_s16, i32, i32, i32) -DEF_HELPER_2(neon_cge_u32, i32, i32, i32) -DEF_HELPER_2(neon_cge_s32, i32, i32, i32) - DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_mul_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u8, i32, i32, i32) DEF_HELPER_2(neon_tst_u16, i32, i32, i32) DEF_HELPER_2(neon_tst_u32, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u8, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u16, i32, i32, i32) -DEF_HELPER_2(neon_ceq_u32, i32, i32, i32) DEF_HELPER_1(neon_clz_u8, i32, i32) DEF_HELPER_1(neon_clz_u16, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_clt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_cge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_sshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_ushl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) uint64_t vfp_expand_imm(int size, uint8_t imm8); /* Vector operations shared between ARM and AArch64. */ +extern const GVecGen2 ceq0_op[4]; +extern const GVecGen2 clt0_op[4]; +extern const GVecGen2 cgt0_op[4]; +extern const GVecGen2 cle0_op[4]; +extern const GVecGen2 cge0_op[4]; extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(neon_hsub_u32)(uint32_t src1, uint32_t src2) return dest; } -#define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? ~0 : 0 -NEON_VOP(cgt_s8, neon_s8, 4) -NEON_VOP(cgt_u8, neon_u8, 4) -NEON_VOP(cgt_s16, neon_s16, 2) -NEON_VOP(cgt_u16, neon_u16, 2) -NEON_VOP(cgt_s32, neon_s32, 1) -NEON_VOP(cgt_u32, neon_u32, 1) -#undef NEON_FN - -#define NEON_FN(dest, src1, src2) dest = (src1 >= src2) ? ~0 : 0 -NEON_VOP(cge_s8, neon_s8, 4) -NEON_VOP(cge_u8, neon_u8, 4) -NEON_VOP(cge_s16, neon_s16, 2) -NEON_VOP(cge_u16, neon_u16, 2) -NEON_VOP(cge_s32, neon_s32, 1) -NEON_VOP(cge_u32, neon_u32, 1) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) @@ -XXX,XX +XXX,XX @@ NEON_VOP(tst_u16, neon_u16, 2) NEON_VOP(tst_u32, neon_u32, 1) #undef NEON_FN -#define NEON_FN(dest, src1, src2) dest = (src1 == src2) ? -1 : 0 -NEON_VOP(ceq_u8, neon_u8, 4) -NEON_VOP(ceq_u16, neon_u16, 2) -NEON_VOP(ceq_u32, neon_u32, 1) -#undef NEON_FN - /* Count Leading Sign/Zero Bits. */ static inline int do_clz8(uint8_t x) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } +/* Expand a 2-operand AdvSIMD vector operation using an op descriptor. */ +static void gen_gvec_op2(DisasContext *s, bool is_q, int rd, + int rn, const GVecGen2 *gvec_op) +{ + tcg_gen_gvec_2(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), + is_q ? 16 : 8, vec_full_reg_size(s), gvec_op); +} + /* Expand a 2-operand + immediate AdvSIMD vector operation using * an op descriptor. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; + case 0x8: /* CMGT, CMGE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cge0_op[size] : &cgt0_op[size]); + return; + case 0x9: /* CMEQ, CMLE */ + gen_gvec_op2(s, is_q, rd, rn, u ? &cle0_op[size] : &ceq0_op[size]); + return; + case 0xa: /* CMLT */ + gen_gvec_op2(s, is_q, rd, rn, &clt0_op[size]); + return; case 0xb: if (u) { /* ABS, NEG */ gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_neg, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) for (pass = 0; pass < (is_q ? 4 : 2); pass++) { TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); - TCGCond cond; read_vec_element_i32(s, tcg_op, rn, pass, MO_32); if (size == 2) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0xa: /* CMLT */ - /* 32 bit integer comparison against zero, result is - * test ? (2^32 - 1) : 0. We implement via setcond(test) - * and inverting. - */ - cond = TCG_COND_LT; - do_cmop: - tcg_gen_setcondi_i32(cond, tcg_res, tcg_op, 0); - tcg_gen_neg_i32(tcg_res, tcg_res); - break; - case 0x8: /* CMGT, CMGE */ - cond = u ? TCG_COND_GE : TCG_COND_GT; - goto do_cmop; - case 0x9: /* CMEQ, CMLE */ - cond = u ? TCG_COND_LE : TCG_COND_EQ; - goto do_cmop; case 0x4: /* CLS */ if (u) { tcg_gen_clzi_i32(tcg_res, tcg_op, 32); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) genfn(tcg_res, cpu_env, tcg_op); break; } - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_cgt_s8, gen_helper_neon_cgt_s16 }, - { gen_helper_neon_cge_s8, gen_helper_neon_cge_s16 }, - { gen_helper_neon_ceq_u8, gen_helper_neon_ceq_u16 }, - }; - NeonGenTwoOpFn *genfn; - int comp; - bool reverse; - TCGv_i32 tcg_zero = tcg_const_i32(0); - - /* comp = index into [CMGT, CMGE, CMEQ, CMLE, CMLT] */ - comp = (opcode - 0x8) * 2 + u; - /* ...but LE, LT are implemented as reverse GE, GT */ - reverse = (comp > 2); - if (reverse) { - comp = 4 - comp; - } - genfn = fns[comp][size]; - if (reverse) { - genfn(tcg_res, tcg_zero, tcg_op); - } else { - genfn(tcg_res, tcg_op, tcg_zero); - } - tcg_temp_free_i32(tcg_zero); - break; - } case 0x4: /* CLS, CLZ */ if (u) { if (size == 0) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } +static void gen_ceq0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_ceq0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_EQ, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_ceq0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_EQ, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +static const TCGOpcode vecop_list_cmp[] = { + INDEX_op_cmp_vec, 0 +}; + +const GVecGen2 ceq0_op[4] = { + { .fno = gen_helper_gvec_ceq0_b, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_ceq0_h, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_ceq0_i32, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_ceq0_i64, + .fniv = gen_ceq0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cle0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cle0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cle0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cle0_op[4] = { + { .fno = gen_helper_gvec_cle0_b, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cle0_h, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cle0_i32, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cle0_i64, + .fniv = gen_cle0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cge0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cge0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GE, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cge0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GE, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cge0_op[4] = { + { .fno = gen_helper_gvec_cge0_b, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cge0_h, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cge0_i32, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cge0_i64, + .fniv = gen_cge0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_clt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_clt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_LT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_clt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_LT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 clt0_op[4] = { + { .fno = gen_helper_gvec_clt0_b, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_clt0_h, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_clt0_i32, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_clt0_i64, + .fniv = gen_clt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + +static void gen_cgt0_i32(TCGv_i32 d, TCGv_i32 a) +{ + tcg_gen_setcondi_i32(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i32(d, d); +} + +static void gen_cgt0_i64(TCGv_i64 d, TCGv_i64 a) +{ + tcg_gen_setcondi_i64(TCG_COND_GT, d, a, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cgt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) +{ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); + tcg_gen_cmp_vec(TCG_COND_GT, vece, d, a, zero); + tcg_temp_free_vec(zero); +} + +const GVecGen2 cgt0_op[4] = { + { .fno = gen_helper_gvec_cgt0_b, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_8 }, + { .fno = gen_helper_gvec_cgt0_h, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_16 }, + { .fni4 = gen_cgt0_i32, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .vece = MO_32 }, + { .fni8 = gen_cgt0_i64, + .fniv = gen_cgt0_vec, + .opt_opc = vecop_list_cmp, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { tcg_gen_vec_sar8i_i64(a, a, shift); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_abs(size, rd_ofs, rm_ofs, vec_size, vec_size); break; + case NEON_2RM_VCEQ0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &ceq0_op[size]); + break; + case NEON_2RM_VCGT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cgt0_op[size]); + break; + case NEON_2RM_VCLE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cle0_op[size]); + break; + case NEON_2RM_VCGE0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &cge0_op[size]); + break; + case NEON_2RM_VCLT0: + tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, + vec_size, &clt0_op[size]); + break; + default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: abort(); } break; - case NEON_2RM_VCGT0: case NEON_2RM_VCLE0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cgt_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cgt_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cgt_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLE0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCGE0: case NEON_2RM_VCLT0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_cge_s8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_cge_s16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_cge_s32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - if (op == NEON_2RM_VCLT0) { - tcg_gen_not_i32(tmp, tmp); - } - break; - case NEON_2RM_VCEQ0: - tmp2 = tcg_const_i32(0); - switch(size) { - case 0: gen_helper_neon_ceq_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_ceq_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_ceq_u32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - break; case NEON_2RM_VCGT0_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_pmull_h)(void *vd, void *vn, void *vm, uint32_t desc) } } #endif + +#define DO_CMP0(NAME, TYPE, OP) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE nn = *(TYPE *)(vn + i); \ + *(TYPE *)(vd + i) = -(nn OP 0); \ + } \ + clear_tail(vd, opr_sz, simd_maxsz(desc)); \ +} + +DO_CMP0(gvec_ceq0_b, int8_t, ==) +DO_CMP0(gvec_clt0_b, int8_t, <) +DO_CMP0(gvec_cle0_b, int8_t, <=) +DO_CMP0(gvec_cgt0_b, int8_t, >) +DO_CMP0(gvec_cge0_b, int8_t, >=) + +DO_CMP0(gvec_ceq0_h, int16_t, ==) +DO_CMP0(gvec_clt0_h, int16_t, <) +DO_CMP0(gvec_cle0_h, int16_t, <=) +DO_CMP0(gvec_cgt0_h, int16_t, >) +DO_CMP0(gvec_cge0_h, int16_t, >=) + +#undef DO_CMP0 -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> The /secure-chosen node is currently used only by create_uart(), but this will change. Therefore move the creation of this node to create_fdt(). Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-2-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) 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 void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + if (vms->secure) { + qemu_fdt_add_subnode(fdt, "/secure-chosen"); + } + /* Clock node, for the benefit of the UART. The kernel device tree * binding documentation claims the PL011 node clock properties are * optional but in practice if you omit them the kernel refuses to @@ -XXX,XX +XXX,XX @@ static void create_uart(const VirtMachineState *vms, int uart, qemu_fdt_setprop_string(vms->fdt, nodename, "status", "disabled"); qemu_fdt_setprop_string(vms->fdt, nodename, "secure-status", "okay"); - qemu_fdt_add_subnode(vms->fdt, "/secure-chosen"); qemu_fdt_setprop_string(vms->fdt, "/secure-chosen", "stdout-path", nodename); } -- 2.20.1 From: Jerome Forissier <jerome@forissier.org> Generate random seeds to be used by the non-secure and/or secure OSes for ASLR. The seeds are 64-bit random values exported via the DT properties /chosen/kaslr-seed [1] and /secure-chosen/kaslr-seed, the latter being used by OP-TEE [2]. [1] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e5bc0c37c97e1 [2] https://github.com/OP-TEE/optee_os/commit/ef262691fe0e Signed-off-by: Jerome Forissier <jerome@forissier.org> Message-id: 20200420121807.8204-3-jerome@forissier.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) 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 @@ #include "hw/acpi/generic_event_device.h" #include "hw/virtio/virtio-iommu.h" #include "hw/char/pl011.h" +#include "qemu/guest-random.h" #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ @@ -XXX,XX +XXX,XX @@ static bool cpu_type_valid(const char *cpu) return false; } +static void create_kaslr_seed(VirtMachineState *vms, const char *node) +{ + Error *err = NULL; + uint64_t seed; + + if (qemu_guest_getrandom(&seed, sizeof(seed), &err)) { + error_free(err); + return; + } + qemu_fdt_setprop_u64(vms->fdt, node, "kaslr-seed", seed); +} + static void create_fdt(VirtMachineState *vms) { MachineState *ms = MACHINE(vms); @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); + create_kaslr_seed(vms, "/chosen"); if (vms->secure) { qemu_fdt_add_subnode(fdt, "/secure-chosen"); + create_kaslr_seed(vms, "/secure-chosen"); } /* Clock node, for the benefit of the UART. The kernel device tree -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Under KVM these registers are written by the hardware. Restrict the writefn handlers to TCG to avoid when building without TCG: LINK aarch64-softmmu/qemu-system-aarch64 target/arm/helper.o: In function `do_ats_write': target/arm/helper.c:3524: undefined reference to `raise_exception' Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-2-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri, return CP_ACCESS_OK; } +#ifdef CONFIG_TCG static uint64_t do_ats_write(CPUARMState *env, uint64_t value, MMUAccessType access_type, ARMMMUIdx mmu_idx) { @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, } return par64; } +#endif /* CONFIG_TCG */ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; ARMMMUIdx mmu_idx; @@ -XXX,XX +XXX,XX @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) par64 = do_ats_write(env, value, access_type, mmu_idx); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static void ats1h_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; uint64_t par64; par64 = do_ats_write(env, value, access_type, ARMMMUIdx_E2); A32_BANKED_CURRENT_REG_SET(env, par, par64); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static CPAccessResult at_s1e2_access(CPUARMState *env, const ARMCPRegInfo *ri, static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { +#ifdef CONFIG_TCG MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; ARMMMUIdx mmu_idx; int secure = arm_is_secure_below_el3(env); @@ -XXX,XX +XXX,XX @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, } env->cp15.par_el[1] = do_ats_write(env, value, access_type, mmu_idx); +#else + /* Handled by hardware accelerator. */ + g_assert_not_reached(); +#endif /* CONFIG_TCG */ } #endif -- 2.20.1 From: Thomas Huth <thuth@redhat.com> Make cpu_register() (renamed to arm_cpu_register()) available from internals.h so we can register CPUs also from other files in the future. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-3-philmd@redhat.com Message-ID: <20190921150420.30743-2-thuth@redhat.com> [PMD: Only take cpu_register() from Thomas's patch] Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu-qom.h | 9 ++++++++- target/arm/cpu.c | 10 ++-------- target/arm/cpu64.c | 8 +------- 3 files changed, 11 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu-qom.h b/target/arm/cpu-qom.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-qom.h +++ b/target/arm/cpu-qom.h @@ -XXX,XX +XXX,XX @@ struct arm_boot_info; #define TYPE_ARM_MAX_CPU "max-" TYPE_ARM_CPU -typedef struct ARMCPUInfo ARMCPUInfo; +typedef struct ARMCPUInfo { + const char *name; + void (*initfn)(Object *obj); + void (*class_init)(ObjectClass *oc, void *data); +} ARMCPUInfo; + +void arm_cpu_register(const ARMCPUInfo *info); +void aarch64_cpu_register(const ARMCPUInfo *info); /** * ARMCPUClass: diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) #endif /* !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) */ -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo arm_cpus[] = { #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) { .name = "arm926", .initfn = arm926_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void cpu_register(const ARMCPUInfo *info) +void arm_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_ARM_CPU, @@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void) type_register_static(&idau_interface_type_info); while (info->name) { - cpu_register(info); + arm_cpu_register(info); info++; } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu_max_set_sve_max_vq, NULL, NULL, &error_fatal); } -struct ARMCPUInfo { - const char *name; - void (*initfn)(Object *obj); - void (*class_init)(ObjectClass *oc, void *data); -}; - static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, @@ -XXX,XX +XXX,XX @@ static void cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; } -static void aarch64_cpu_register(const ARMCPUInfo *info) +void aarch64_cpu_register(const ARMCPUInfo *info) { TypeInfo type_info = { .parent = TYPE_AARCH64_CPU, -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-4-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 8 +++----- target/arm/cpu64.c | 8 +++----- 2 files changed, 6 insertions(+), 10 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = { { .name = "any", .initfn = arm_max_initfn }, #endif #endif - { .name = NULL } }; static Property arm_cpu_properties[] = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo idau_interface_type_info = { static void arm_cpu_register_types(void) { - const ARMCPUInfo *info = arm_cpus; + size_t i; type_register_static(&arm_cpu_type_info); type_register_static(&idau_interface_type_info); - while (info->name) { - arm_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(arm_cpus); ++i) { + arm_cpu_register(&arm_cpus[i]); } #ifdef CONFIG_KVM diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, - { .name = NULL } }; static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp) @@ -XXX,XX +XXX,XX @@ static const TypeInfo aarch64_cpu_type_info = { static void aarch64_cpu_register_types(void) { - const ARMCPUInfo *info = aarch64_cpus; + size_t i; type_register_static(&aarch64_cpu_type_info); - while (info->name) { - aarch64_cpu_register(info); - info++; + for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) { + aarch64_cpu_register(&aarch64_cpus[i]); } } -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> We will move this code in the next commit. Clean it up first to avoid checkpatch.pl errors. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200423073358.27155-5-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) CPUARMState *env = &cpu->env; bool ret = false; - /* ARMv7-M interrupt masking works differently than -A or -R. + /* + * ARMv7-M interrupt masking works differently than -A or -R. * There is no FIQ/IRQ distinction. Instead of I and F bits * masking FIQ and IRQ interrupts, an exception is taken only * if it is higher priority than the current execution priority @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) static void arm1136_r2_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); - /* What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an + /* + * What qemu calls "arm1136_r2" is actually the 1136 r0p2, ie an * older core than plain "arm1136". In particular this does not * have the v6K features. * These ID register values are correct for 1136 but may be wrong @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_cpus[] = { { .name = "arm926", .initfn = arm926_initfn }, { .name = "arm946", .initfn = arm946_initfn }, { .name = "arm1026", .initfn = arm1026_initfn }, - /* What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an + /* + * What QEMU calls "arm1136-r2" is actually the 1136 r0p2, i.e. an * older core than plain "arm1136". In particular this does not * have the v6K features. */ -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Allow name wildcards in qemu_fdt_node_path(). This is useful to find all nodes with a given compatibility string. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 3 +++ device_tree.c | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * NULL. If there is no error but no matching node was found, the * returned array contains a single element equal to NULL. If an error * was encountered when parsing the blob, the function returns NULL + * + * @name may be NULL to wildcard names and only match compatibility + * strings. */ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, Error **errp); diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, offset = len; break; } - if (!strcmp(iter_name, name)) { + if (!name || !strcmp(iter_name, name)) { char *path; path = g_malloc(path_len); -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Make compat in qemu_fdt_node_path() const char *. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-3-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 2 +- device_tree.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); * @name may be NULL to wildcard names and only match compatibility * strings. */ -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp); /** diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp) return path_array; } -char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, +char **qemu_fdt_node_path(void *fdt, const char *name, const char *compat, Error **errp) { int offset, len, ret; -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Move arm_boot_info into XlnxZCU102. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-4-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ typedef struct XlnxZCU102 { bool secure; bool virt; + + struct arm_boot_info binfo; } XlnxZCU102; #define TYPE_ZCU102_MACHINE MACHINE_TYPE_NAME("xlnx-zcu102") #define ZCU102_MACHINE(obj) \ OBJECT_CHECK(XlnxZCU102, (obj), TYPE_ZCU102_MACHINE) -static struct arm_boot_info xlnx_zcu102_binfo; static bool zcu102_get_secure(Object *obj, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) /* TODO create and connect IDE devices for ide_drive_get() */ - xlnx_zcu102_binfo.ram_size = ram_size; - xlnx_zcu102_binfo.loader_start = 0; - arm_load_kernel(s->soc.boot_cpu_ptr, machine, &xlnx_zcu102_binfo); + s->binfo.ram_size = ram_size; + s->binfo.loader_start = 0; + arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } static void xlnx_zcu102_machine_instance_init(Object *obj) -- 2.20.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Disable unsupported FDT firmware nodes if a user passes us a DTB with nodes enabled that the machine cannot support due to lack of EL3 or EL2 support. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20200423121114.4274-5-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xlnx-zcu102.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/log.h" #include "sysemu/qtest.h" +#include "sysemu/device_tree.h" typedef struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ static void zcu102_set_virt(Object *obj, bool value, Error **errp) s->virt = value; } +static void zcu102_modify_dtb(const struct arm_boot_info *binfo, void *fdt) +{ + XlnxZCU102 *s = container_of(binfo, XlnxZCU102, binfo); + bool method_is_hvc; + char **node_path; + const char *r; + int prop_len; + int i; + + /* If EL3 is enabled, we keep all firmware nodes active. */ + if (!s->secure) { + node_path = qemu_fdt_node_path(fdt, NULL, "xlnx,zynqmp-firmware", + &error_fatal); + + for (i = 0; node_path && node_path[i]; i++) { + r = qemu_fdt_getprop(fdt, node_path[i], "method", &prop_len, NULL); + method_is_hvc = r && !strcmp("hvc", r); + + /* Allow HVC based firmware if EL2 is enabled. */ + if (method_is_hvc && s->virt) { + continue; + } + qemu_fdt_setprop_string(fdt, node_path[i], "status", "disabled"); + } + g_strfreev(node_path); + } +} + static void xlnx_zcu102_init(MachineState *machine) { XlnxZCU102 *s = ZCU102_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) s->binfo.ram_size = ram_size; s->binfo.loader_start = 0; + s->binfo.modify_dtb = zcu102_modify_dtb; arm_load_kernel(s->soc.boot_cpu_ptr, machine, &s->binfo); } -- 2.20.1