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 The following changes since commit 4cc10cae64c51e17844dc4358481c393d7bf1ed4: Merge remote-tracking branch 'remotes/bonzini-gitlab/tags/for-upstream' into staging (2021-05-06 18:56:17 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210510 for you to fetch changes up to 8f96812baa53005f32aece3e30b140826c20aa19: hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 (2021-05-10 13:24:09 +0100) ---------------------------------------------------------------- target-arm queue: * docs: fix link in sbsa description * linux-user/aarch64: Enable hwcap for RND, BTI, and MTE * target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() * target/arm: Split neon and vfp translation to their own compilation units * target/arm: Make WFI a NOP for userspace emulators * hw/sd/omap_mmc: Use device_cold_reset() instead of device_legacy_reset() * include: More fixes for 'extern "C"' block use * hw/arm/imx25_pdk: Fix error message for invalid RAM size * hw/arm/mps2-tz: Implement AN524 memory remapping via machine property * hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 ---------------------------------------------------------------- Alex Bennée (1): docs: fix link in sbsa description Guenter Roeck (1): hw/arm/xlnx: Fix PHY address for xilinx-zynq-a9 Peter Maydell (22): target/arm: Fix tlbbits calculation in tlbi_aa64_vae2is_write() target/arm: Move constant expanders to translate.h target/arm: Share unallocated_encoding() and gen_exception_insn() target/arm: Make functions used by m-nocp global target/arm: Split m-nocp trans functions into their own file target/arm: Move gen_aa32 functions to translate-a32.h target/arm: Move vfp_{load, store}_reg{32, 64} to translate-vfp.c.inc target/arm: Make functions used by translate-vfp global target/arm: Make translate-vfp.c.inc its own compilation unit target/arm: Move vfp_reg_ptr() to translate-neon.c.inc target/arm: Delete unused typedef target/arm: Move NeonGenThreeOpEnvFn typedef to translate.h target/arm: Make functions used by translate-neon global target/arm: Make translate-neon.c.inc its own compilation unit target/arm: Make WFI a NOP for userspace emulators hw/sd/omap_mmc: Use device_cold_reset() instead of device_legacy_reset() osdep: Make os-win32.h and os-posix.h handle 'extern "C"' themselves include/qemu/bswap.h: Handle being included outside extern "C" block include/disas/dis-asm.h: Handle being included outside 'extern "C"' hw/misc/mps2-scc: Add "QEMU interface" comment hw/misc/mps2-scc: Support using CFG0 bit 0 for remapping hw/arm/mps2-tz: Implement AN524 memory remapping via machine property Philippe Mathieu-Daudé (1): hw/arm/imx25_pdk: Fix error message for invalid RAM size Richard Henderson (1): linux-user/aarch64: Enable hwcap for RND, BTI, and MTE docs/system/arm/mps2.rst | 10 + docs/system/arm/sbsa.rst | 2 +- include/disas/dis-asm.h | 12 +- include/hw/misc/mps2-scc.h | 21 ++ include/qemu/bswap.h | 26 ++- include/qemu/osdep.h | 8 +- include/sysemu/os-posix.h | 8 + include/sysemu/os-win32.h | 8 + target/arm/translate-a32.h | 144 +++++++++++++ target/arm/translate-a64.h | 2 - target/arm/translate.h | 29 +++ hw/arm/imx25_pdk.c | 5 +- hw/arm/mps2-tz.c | 108 +++++++++- hw/arm/xilinx_zynq.c | 2 +- hw/misc/mps2-scc.c | 13 +- hw/sd/omap_mmc.c | 2 +- linux-user/elfload.c | 13 ++ target/arm/helper.c | 2 +- target/arm/op_helper.c | 12 ++ target/arm/translate-a64.c | 15 -- target/arm/translate-m-nocp.c | 221 ++++++++++++++++++++ .../arm/{translate-neon.c.inc => translate-neon.c} | 19 +- .../arm/{translate-vfp.c.inc => translate-vfp.c} | 230 +++------------------ target/arm/translate.c | 200 ++++-------------- disas/arm-a64.cc | 2 - disas/nanomips.cpp | 2 - target/arm/meson.build | 15 +- 27 files changed, 718 insertions(+), 413 deletions(-) create mode 100644 target/arm/translate-a32.h create mode 100644 target/arm/translate-m-nocp.c rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (94%) From: Alex Bennée <alex.bennee@linaro.org> A trailing _ makes all the difference to the rendered link. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20210428131316.31390-1-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/sbsa.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/sbsa.rst +++ b/docs/system/arm/sbsa.rst @@ -XXX,XX +XXX,XX @@ Arm Server Base System Architecture Reference board (``sbsa-ref``) While the `virt` board is a generic board platform that doesn't match any real hardware the `sbsa-ref` board intends to look like real hardware. The `Server Base System Architecture -<https://developer.arm.com/documentation/den0029/latest>` defines a +<https://developer.arm.com/documentation/den0029/latest>`_ defines a minimum base line of hardware support and importantly how the firmware reports that to any operating system. It is a static system that reports a very minimal DT to the firmware for non-discoverable -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These three features are already enabled by TCG, but are missing their hwcap bits. Update HWCAP2 from linux v5.12. Cc: qemu-stable@nongnu.org (for 6.0.1) Buglink: https://bugs.launchpad.net/bugs/1926044 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210427214108.88503-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_A64_SVESM4 = 1 << 6, ARM_HWCAP2_A64_FLAGM2 = 1 << 7, ARM_HWCAP2_A64_FRINT = 1 << 8, + ARM_HWCAP2_A64_SVEI8MM = 1 << 9, + ARM_HWCAP2_A64_SVEF32MM = 1 << 10, + ARM_HWCAP2_A64_SVEF64MM = 1 << 11, + ARM_HWCAP2_A64_SVEBF16 = 1 << 12, + ARM_HWCAP2_A64_I8MM = 1 << 13, + ARM_HWCAP2_A64_BF16 = 1 << 14, + ARM_HWCAP2_A64_DGH = 1 << 15, + ARM_HWCAP2_A64_RNG = 1 << 16, + ARM_HWCAP2_A64_BTI = 1 << 17, + ARM_HWCAP2_A64_MTE = 1 << 18, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_dcpodp, ARM_HWCAP2_A64_DCPODP); GET_FEATURE_ID(aa64_condm_5, ARM_HWCAP2_A64_FLAGM2); GET_FEATURE_ID(aa64_frint, ARM_HWCAP2_A64_FRINT); + GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); + GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); + GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); return hwcaps; } -- 2.20.1 In tlbi_aa64_vae2is_write() the calculation bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, pageaddr) has the two arms of the ?: expression reversed. Fix the bug. Fixes: b6ad6062f1e5 Reported-by: Rebecca Cran <rebecca@nuviainc.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Rémi Denis-Courmont <remi.denis.courmont@huawei.com> Reviewed-by: Rebecca Cran <rebecca@nuviainc.com> Message-id: 20210420123106.10861-1-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 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 tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t pageaddr = sextract64(value << 12, 0, 56); bool secure = arm_is_secure_below_el3(env); int mask = secure ? ARMMMUIdxBit_SE2 : ARMMMUIdxBit_E2; - int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_E2 : ARMMMUIdx_SE2, + int bits = tlbbits_for_regime(env, secure ? ARMMMUIdx_SE2 : ARMMMUIdx_E2, pageaddr); tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); -- 2.20.1 Some of the constant expanders defined in translate.c are generically useful and will be used by the separate C files for VFP and Neon once they are created; move the expander definitions to translate.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-2-peter.maydell@linaro.org --- target/arm/translate.h | 24 ++++++++++++++++++++++++ target/arm/translate.c | 24 ------------------------ 2 files changed, 24 insertions(+), 24 deletions(-) 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 @@ extern TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF; extern TCGv_i64 cpu_exclusive_addr; extern TCGv_i64 cpu_exclusive_val; +/* + * Constant expanders for the decoders. + */ + +static inline int negate(DisasContext *s, int x) +{ + return -x; +} + +static inline int plus_2(DisasContext *s, int x) +{ + return x + 2; +} + +static inline int times_2(DisasContext *s, int x) +{ + return x * 2; +} + +static inline int times_4(DisasContext *s, int x) +{ + return x * 4; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 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 void arm_gen_condlabel(DisasContext *s) } } -/* - * Constant expanders for the decoders. - */ - -static int negate(DisasContext *s, int x) -{ - return -x; -} - -static int plus_2(DisasContext *s, int x) -{ - return x + 2; -} - -static int times_2(DisasContext *s, int x) -{ - return x * 2; -} - -static int times_4(DisasContext *s, int x) -{ - return x * 4; -} - /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ -- 2.20.1 The unallocated_encoding() function is the same in both translate-a64.c and translate.c; make the translate.c function global and drop the translate-a64.c version. To do this we need to also share gen_exception_insn(), which currently exists in two slightly different versions for A32 and A64: merge those into a single function that can work for both. This will be useful for splitting up translate.c, which will require unallocated_encoding() to no longer be file-local. It's also hopefully less confusing to have only one version of the function rather than two. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-3-peter.maydell@linaro.org --- target/arm/translate-a64.h | 2 -- target/arm/translate.h | 3 +++ target/arm/translate-a64.c | 15 --------------- target/arm/translate.c | 14 +++++++++----- 4 files changed, 12 insertions(+), 22 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_TRANSLATE_A64_H #define TARGET_ARM_TRANSLATE_A64_H -void unallocated_encoding(DisasContext *s); - #define unsupported_encoding(s, insn) \ do { \ qemu_log_mask(LOG_UNIMP, \ 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 @@ void arm_free_cc(DisasCompare *cmp); void arm_jump_cc(DisasCompare *cmp, TCGLabel *label); void arm_gen_test_cc(int cc, TCGLabel *label); MemOp pow2_align(unsigned i); +void unallocated_encoding(DisasContext *s); +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, + uint32_t syn, uint32_t target_el); /* Return state of Alternate Half-precision flag, caller frees result */ static inline TCGv_i32 get_ahp_flag(void) 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_exception_internal_insn(DisasContext *s, uint64_t pc, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, - uint32_t syndrome, uint32_t target_el) -{ - gen_a64_set_pc_im(pc); - gen_exception(excp, syndrome, target_el); - s->base.is_jmp = DISAS_NORETURN; -} - static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syndrome) { TCGv_i32 tcg_syn; @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) } } -void unallocated_encoding(DisasContext *s) -{ - /* Unallocated and reserved encodings are uncategorized */ - gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), - default_exception_el(s)); -} - static void init_tmp_a64_array(DisasContext *s) { #ifdef CONFIG_DEBUG_TCG 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 void gen_exception_internal_insn(DisasContext *s, uint32_t pc, int excp) s->base.is_jmp = DISAS_NORETURN; } -static void gen_exception_insn(DisasContext *s, uint32_t pc, int excp, - int syn, uint32_t target_el) +void gen_exception_insn(DisasContext *s, uint64_t pc, int excp, + uint32_t syn, uint32_t target_el) { - gen_set_condexec(s); - gen_set_pc_im(s, pc); + if (s->aarch64) { + gen_a64_set_pc_im(pc); + } else { + gen_set_condexec(s); + gen_set_pc_im(s, pc); + } gen_exception(excp, syn, target_el); s->base.is_jmp = DISAS_NORETURN; } @@ -XXX,XX +XXX,XX @@ static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syn) s->base.is_jmp = DISAS_NORETURN; } -static void unallocated_encoding(DisasContext *s) +void unallocated_encoding(DisasContext *s) { /* Unallocated and reserved encodings are uncategorized */ gen_exception_insn(s, s->pc_curr, EXCP_UDEF, syn_uncategorized(), -- 2.20.1 We want to split out the .c.inc files which are currently included into translate.c so they are separate compilation units. To do this we need to make some functions which are currently file-local to translate.c have global scope; create a translate-a32.h paralleling the existing translate-a64.h as a place for these declarations to live, so that code moved into the new compilation units can call them. The functions made global here are those required by the m-nocp.decode functions, except that I have converted the whole family of {read,write}_neon_element* and also both the load_cpu and store_cpu functions for consistency, even though m-nocp only wants a few functions from each. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-4-peter.maydell@linaro.org --- target/arm/translate-a32.h | 57 ++++++++++++++++++++++++++++++++++ target/arm/translate.c | 39 +++++------------------ target/arm/translate-vfp.c.inc | 2 +- 3 files changed, 65 insertions(+), 33 deletions(-) create mode 100644 target/arm/translate-a32.h diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ +/* + * AArch32 translation, common definitions. + * + * Copyright (c) 2021 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef TARGET_ARM_TRANSLATE_A64_H +#define TARGET_ARM_TRANSLATE_A64_H + +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); +void arm_gen_condlabel(DisasContext *s); +bool vfp_access_check(DisasContext *s); +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); +void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); + +static inline TCGv_i32 load_cpu_offset(int offset) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_ld_i32(tmp, cpu_env, offset); + return tmp; +} + +#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) + +static inline void store_cpu_offset(TCGv_i32 var, int offset) +{ + tcg_gen_st_i32(var, cpu_env, offset); + tcg_temp_free_i32(var); +} + +#define store_cpu_field(var, name) \ + store_cpu_offset(var, offsetof(CPUARMState, name)) + +/* Create a new temporary and set it to the value of a CPU register. */ +static inline TCGv_i32 load_reg(DisasContext *s, int reg) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + load_reg_var(s, tmp, reg); + return tmp; +} + +#endif 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 @@ #define ENABLE_ARCH_8 arm_dc_feature(s, ARM_FEATURE_V8) #include "translate.h" +#include "translate-a32.h" #if defined(CONFIG_USER_ONLY) #define IS_USER(s) 1 @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) } /* Generate a label used for skipping this instruction */ -static void arm_gen_condlabel(DisasContext *s) +void arm_gen_condlabel(DisasContext *s) { if (!s->condjmp) { s->condlabel = gen_new_label(); @@ -XXX,XX +XXX,XX @@ static inline int get_a32_user_mem_index(DisasContext *s) } } -static inline TCGv_i32 load_cpu_offset(int offset) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, offset); - return tmp; -} - -#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) - -static inline void store_cpu_offset(TCGv_i32 var, int offset) -{ - tcg_gen_st_i32(var, cpu_env, offset); - tcg_temp_free_i32(var); -} - -#define store_cpu_field(var, name) \ - store_cpu_offset(var, offsetof(CPUARMState, name)) - /* The architectural value of PC. */ static uint32_t read_pc(DisasContext *s) { @@ -XXX,XX +XXX,XX @@ static uint32_t read_pc(DisasContext *s) } /* Set a variable to the value of a CPU register. */ -static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) +void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) { if (reg == 15) { tcg_gen_movi_i32(var, read_pc(s)); @@ -XXX,XX +XXX,XX @@ static void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) } } -/* Create a new temporary and set it to the value of a CPU register. */ -static inline TCGv_i32 load_reg(DisasContext *s, int reg) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - load_reg_var(s, tmp, reg); - return tmp; -} - /* * Create a new temp, REG + OFS, except PC is ALIGN(PC, 4). * This is used for load/store for which use of PC implies (literal), @@ -XXX,XX +XXX,XX @@ static inline void vfp_store_reg32(TCGv_i32 var, int reg) tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); } -static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) +void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) } } -static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) +void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop) } } -static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) +void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); @@ -XXX,XX +XXX,XX @@ static void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop) } } -static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) +void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) * The most usual kind of VFP access check, for everything except * FMXR/FMRX to the always-available special registers. */ -static bool vfp_access_check(DisasContext *s) +bool vfp_access_check(DisasContext *s) { return full_vfp_access_check(s, false); } -- 2.20.1 Currently the trans functions for m-nocp.decode all live in translate-vfp.inc.c; move them out into their own translation unit, translate-m-nocp.c. The trans_* functions here are pure code motion with no changes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-5-peter.maydell@linaro.org --- target/arm/translate-a32.h | 3 + target/arm/translate-m-nocp.c | 221 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 1 - target/arm/translate-vfp.c.inc | 196 ----------------------------- target/arm/meson.build | 3 +- 5 files changed, 226 insertions(+), 198 deletions(-) create mode 100644 target/arm/translate-m-nocp.c diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_TRANSLATE_A64_H #define TARGET_ARM_TRANSLATE_A64_H +/* Prototypes for autogenerated disassembler functions */ +bool disas_m_nocp(DisasContext *dc, uint32_t insn); + void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); bool vfp_access_check(DisasContext *s); diff --git a/target/arm/translate-m-nocp.c b/target/arm/translate-m-nocp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-m-nocp.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM translation: M-profile NOCP special-case instructions + * + * Copyright (c) 2020 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "translate.h" +#include "translate-a32.h" + +#include "decode-m-nocp.c.inc" + +/* + * Decode VLLDM and VLSTM are nonstandard because: + * * if there is no FPU then these insns must NOP in + * Secure state and UNDEF in Nonsecure state + * * if there is an FPU then these insns do not have + * the usual behaviour that vfp_access_check() provides of + * being controlled by CPACR/NSACR enable bits or the + * lazy-stacking logic. + */ +static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) +{ + TCGv_i32 fptr; + + if (!arm_dc_feature(s, ARM_FEATURE_M) || + !arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + if (a->op) { + /* + * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not + * to take the IMPDEF option to make memory accesses to the stack + * slots that correspond to the D16-D31 registers (discarding + * read data and writing UNKNOWN values), so for us the T2 + * encoding behaves identically to the T1 encoding. + */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + } else { + /* + * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. + * This is currently architecturally impossible, but we add the + * check to stay in line with the pseudocode. Note that we must + * emit code for the UNDEF so it takes precedence over the NOCP. + */ + if (dc_isar_feature(aa32_simd_r32, s)) { + unallocated_encoding(s); + return true; + } + } + + /* + * If not secure, UNDEF. We must emit code for this + * rather than returning false so that this takes + * precedence over the m-nocp.decode NOCP fallback. + */ + if (!s->v8m_secure) { + unallocated_encoding(s); + return true; + } + /* If no fpu, NOP. */ + if (!dc_isar_feature(aa32_vfp, s)) { + return true; + } + + fptr = load_reg(s, a->rn); + if (a->l) { + gen_helper_v7m_vlldm(cpu_env, fptr); + } else { + gen_helper_v7m_vlstm(cpu_env, fptr); + } + tcg_temp_free_i32(fptr); + + /* End the TB, because we have updated FP control bits */ + s->base.is_jmp = DISAS_UPDATE_EXIT; + return true; +} + +static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) +{ + int btmreg, topreg; + TCGv_i64 zero; + TCGv_i32 aspen, sfpa; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + /* Before v8.1M, fall through in decode to NOCP check */ + return false; + } + + /* Explicitly UNDEF because this takes precedence over NOCP */ + if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { + unallocated_encoding(s); + return true; + } + + if (!dc_isar_feature(aa32_vfp_simd, s)) { + /* NOP if we have neither FP nor MVE */ + return true; + } + + /* + * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no + * active floating point context so we must NOP (without doing + * any lazy state preservation or the NOCP check). + */ + aspen = load_cpu_field(v7m.fpccr[M_REG_S]); + sfpa = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_or_i32(sfpa, sfpa, aspen); + arm_gen_condlabel(s); + tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + topreg = a->vd + a->imm - 1; + btmreg = a->vd; + + /* Convert to Sreg numbers if the insn specified in Dregs */ + if (a->size == 3) { + topreg = topreg * 2 + 1; + btmreg *= 2; + } + + if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { + /* UNPREDICTABLE: we choose to undef */ + unallocated_encoding(s); + return true; + } + + /* Silently ignore requests to clear D16-D31 if they don't exist */ + if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { + topreg = 31; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Zero the Sregs from btmreg to topreg inclusive. */ + zero = tcg_const_i64(0); + if (btmreg & 1) { + write_neon_element64(zero, btmreg >> 1, 1, MO_32); + btmreg++; + } + for (; btmreg + 1 <= topreg; btmreg += 2) { + write_neon_element64(zero, btmreg >> 1, 0, MO_64); + } + if (btmreg == topreg) { + write_neon_element64(zero, btmreg >> 1, 0, MO_32); + btmreg++; + } + assert(btmreg == topreg + 1); + /* TODO: when MVE is implemented, zero VPR here */ + return true; +} + +static bool trans_NOCP(DisasContext *s, arg_nocp *a) +{ + /* + * Handle M-profile early check for disabled coprocessor: + * all we need to do here is emit the NOCP exception if + * the coprocessor is disabled. Otherwise we return false + * and the real VFP/etc decode will handle the insn. + */ + assert(arm_dc_feature(s, ARM_FEATURE_M)); + + if (a->cp == 11) { + a->cp = 10; + } + if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && + (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { + /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ + a->cp = 10; + } + + if (a->cp != 10) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), default_exception_el(s)); + return true; + } + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + return false; +} + +static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) +{ + /* This range needs a coprocessor check for v8.1M and later only */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + return trans_NOCP(s, a); +} 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 TCGv_ptr vfp_reg_ptr(bool dp, int reg) #define ARM_CP_RW_BIT (1 << 20) /* Include the VFP and Neon decoders */ -#include "decode-m-nocp.c.inc" #include "translate-vfp.c.inc" #include "translate-neon.c.inc" diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) return true; } -/* - * Decode VLLDM and VLSTM are nonstandard because: - * * if there is no FPU then these insns must NOP in - * Secure state and UNDEF in Nonsecure state - * * if there is an FPU then these insns do not have - * the usual behaviour that vfp_access_check() provides of - * being controlled by CPACR/NSACR enable bits or the - * lazy-stacking logic. - */ -static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) -{ - TCGv_i32 fptr; - - if (!arm_dc_feature(s, ARM_FEATURE_M) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return false; - } - - if (a->op) { - /* - * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not - * to take the IMPDEF option to make memory accesses to the stack - * slots that correspond to the D16-D31 registers (discarding - * read data and writing UNKNOWN values), so for us the T2 - * encoding behaves identically to the T1 encoding. - */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; - } - } else { - /* - * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. - * This is currently architecturally impossible, but we add the - * check to stay in line with the pseudocode. Note that we must - * emit code for the UNDEF so it takes precedence over the NOCP. - */ - if (dc_isar_feature(aa32_simd_r32, s)) { - unallocated_encoding(s); - return true; - } - } - - /* - * If not secure, UNDEF. We must emit code for this - * rather than returning false so that this takes - * precedence over the m-nocp.decode NOCP fallback. - */ - if (!s->v8m_secure) { - unallocated_encoding(s); - return true; - } - /* If no fpu, NOP. */ - if (!dc_isar_feature(aa32_vfp, s)) { - return true; - } - - fptr = load_reg(s, a->rn); - if (a->l) { - gen_helper_v7m_vlldm(cpu_env, fptr); - } else { - gen_helper_v7m_vlstm(cpu_env, fptr); - } - tcg_temp_free_i32(fptr); - - /* End the TB, because we have updated FP control bits */ - s->base.is_jmp = DISAS_UPDATE_EXIT; - return true; -} - -static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) -{ - int btmreg, topreg; - TCGv_i64 zero; - TCGv_i32 aspen, sfpa; - - if (!dc_isar_feature(aa32_m_sec_state, s)) { - /* Before v8.1M, fall through in decode to NOCP check */ - return false; - } - - /* Explicitly UNDEF because this takes precedence over NOCP */ - if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { - unallocated_encoding(s); - return true; - } - - if (!dc_isar_feature(aa32_vfp_simd, s)) { - /* NOP if we have neither FP nor MVE */ - return true; - } - - /* - * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no - * active floating point context so we must NOP (without doing - * any lazy state preservation or the NOCP check). - */ - aspen = load_cpu_field(v7m.fpccr[M_REG_S]); - sfpa = load_cpu_field(v7m.control[M_REG_S]); - tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); - tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); - tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); - tcg_gen_or_i32(sfpa, sfpa, aspen); - arm_gen_condlabel(s); - tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); - - if (s->fp_excp_el != 0) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), s->fp_excp_el); - return true; - } - - topreg = a->vd + a->imm - 1; - btmreg = a->vd; - - /* Convert to Sreg numbers if the insn specified in Dregs */ - if (a->size == 3) { - topreg = topreg * 2 + 1; - btmreg *= 2; - } - - if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { - /* UNPREDICTABLE: we choose to undef */ - unallocated_encoding(s); - return true; - } - - /* Silently ignore requests to clear D16-D31 if they don't exist */ - if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { - topreg = 31; - } - - if (!vfp_access_check(s)) { - return true; - } - - /* Zero the Sregs from btmreg to topreg inclusive. */ - zero = tcg_const_i64(0); - if (btmreg & 1) { - write_neon_element64(zero, btmreg >> 1, 1, MO_32); - btmreg++; - } - for (; btmreg + 1 <= topreg; btmreg += 2) { - write_neon_element64(zero, btmreg >> 1, 0, MO_64); - } - if (btmreg == topreg) { - write_neon_element64(zero, btmreg >> 1, 0, MO_32); - btmreg++; - } - assert(btmreg == topreg + 1); - /* TODO: when MVE is implemented, zero VPR here */ - return true; -} - -static bool trans_NOCP(DisasContext *s, arg_nocp *a) -{ - /* - * Handle M-profile early check for disabled coprocessor: - * all we need to do here is emit the NOCP exception if - * the coprocessor is disabled. Otherwise we return false - * and the real VFP/etc decode will handle the insn. - */ - assert(arm_dc_feature(s, ARM_FEATURE_M)); - - if (a->cp == 11) { - a->cp = 10; - } - if (arm_dc_feature(s, ARM_FEATURE_V8_1M) && - (a->cp == 8 || a->cp == 9 || a->cp == 14 || a->cp == 15)) { - /* in v8.1M cp 8, 9, 14, 15 also are governed by the cp10 enable */ - a->cp = 10; - } - - if (a->cp != 10) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), default_exception_el(s)); - return true; - } - - if (s->fp_excp_el != 0) { - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), s->fp_excp_el); - return true; - } - - return false; -} - -static bool trans_NOCP_8_1(DisasContext *s, arg_nocp *a) -{ - /* This range needs a coprocessor check for v8.1M and later only */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { - return false; - } - return trans_NOCP(s, a); -} - static bool trans_VINS(DisasContext *s, arg_VINS *a) { TCGv_i32 rd, rm; diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), - decodetree.process('m-nocp.decode', extra_args: '--static-decode=disas_m_nocp'), + decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), decodetree.process('t32.decode', extra_args: '--static-decode=disas_t32'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'op_helper.c', 'tlb_helper.c', 'translate.c', + 'translate-m-nocp.c', 'vec_helper.c', 'vfp_helper.c', 'cpu_tcg.c', -- 2.20.1 Move the various gen_aa32* functions and macros out of translate.c and into translate-a32.h. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-6-peter.maydell@linaro.org --- target/arm/translate-a32.h | 53 ++++++++++++++++++++++++++++++++++++++ target/arm/translate.c | 51 ++++++++++++------------------------ 2 files changed, 69 insertions(+), 35 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) return tmp; } +void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc); +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc); +void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc); + +#define DO_GEN_LD(SUFF, OPC) \ + static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ + TCGv_i32 a32, int index) \ + { \ + gen_aa32_ld_i32(s, val, a32, index, OPC); \ + } + +#define DO_GEN_ST(SUFF, OPC) \ + static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \ + TCGv_i32 a32, int index) \ + { \ + gen_aa32_st_i32(s, val, a32, index, OPC); \ + } + +static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index) +{ + gen_aa32_ld_i64(s, val, a32, index, MO_Q); +} + +static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index) +{ + gen_aa32_st_i64(s, val, a32, index, MO_Q); +} + +DO_GEN_LD(8u, MO_UB) +DO_GEN_LD(16u, MO_UW) +DO_GEN_LD(32u, MO_UL) +DO_GEN_ST(8, MO_UB) +DO_GEN_ST(16, MO_UW) +DO_GEN_ST(32, MO_UL) + +#undef DO_GEN_LD +#undef DO_GEN_ST + #endif 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 TCGv gen_aa32_addr(DisasContext *s, TCGv_i32 a32, MemOp op) * Internal routines are used for NEON cases where the endianness * and/or alignment has already been taken into account and manipulated. */ -static void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, - TCGv_i32 a32, int index, MemOp opc) +void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc) { TCGv addr = gen_aa32_addr(s, a32, opc); tcg_gen_qemu_ld_i32(val, addr, index, opc); tcg_temp_free(addr); } -static void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, - TCGv_i32 a32, int index, MemOp opc) +void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, + TCGv_i32 a32, int index, MemOp opc) { TCGv addr = gen_aa32_addr(s, a32, opc); tcg_gen_qemu_st_i32(val, addr, index, opc); tcg_temp_free(addr); } -static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index, MemOp opc) +void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc) { TCGv addr = gen_aa32_addr(s, a32, opc); @@ -XXX,XX +XXX,XX @@ static void gen_aa32_ld_internal_i64(DisasContext *s, TCGv_i64 val, tcg_temp_free(addr); } -static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index, MemOp opc) +void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, + TCGv_i32 a32, int index, MemOp opc) { TCGv addr = gen_aa32_addr(s, a32, opc); @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_internal_i64(DisasContext *s, TCGv_i64 val, tcg_temp_free(addr); } -static void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, - int index, MemOp opc) +void gen_aa32_ld_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc) { gen_aa32_ld_internal_i32(s, val, a32, index, finalize_memop(s, opc)); } -static void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, - int index, MemOp opc) +void gen_aa32_st_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, + int index, MemOp opc) { gen_aa32_st_internal_i32(s, val, a32, index, finalize_memop(s, opc)); } -static void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, - int index, MemOp opc) +void gen_aa32_ld_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc) { gen_aa32_ld_internal_i64(s, val, a32, index, finalize_memop(s, opc)); } -static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, - int index, MemOp opc) +void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, + int index, MemOp opc) { gen_aa32_st_internal_i64(s, val, a32, index, finalize_memop(s, opc)); } @@ -XXX,XX +XXX,XX @@ static void gen_aa32_st_i64(DisasContext *s, TCGv_i64 val, TCGv_i32 a32, gen_aa32_st_i32(s, val, a32, index, OPC); \ } -static inline void gen_aa32_ld64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index) -{ - gen_aa32_ld_i64(s, val, a32, index, MO_Q); -} - -static inline void gen_aa32_st64(DisasContext *s, TCGv_i64 val, - TCGv_i32 a32, int index) -{ - gen_aa32_st_i64(s, val, a32, index, MO_Q); -} - -DO_GEN_LD(8u, MO_UB) -DO_GEN_LD(16u, MO_UW) -DO_GEN_LD(32u, MO_UL) -DO_GEN_ST(8, MO_UB) -DO_GEN_ST(16, MO_UW) -DO_GEN_ST(32, MO_UL) - static inline void gen_hvc(DisasContext *s, int imm16) { /* The pre HVC helper handles cases when HVC gets trapped -- 2.20.1 The functions vfp_load_reg32(), vfp_load_reg64(), vfp_store_reg32() and vfp_store_reg64() are used only in translate-vfp.c.inc. Move them to that file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-7-peter.maydell@linaro.org --- target/arm/translate.c | 20 -------------------- target/arm/translate-vfp.c.inc | 20 ++++++++++++++++++++ 2 files changed, 20 insertions(+), 20 deletions(-) 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 long vfp_reg_offset(bool dp, unsigned reg) } } -static inline void vfp_load_reg64(TCGv_i64 var, int reg) -{ - tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); -} - -static inline void vfp_store_reg64(TCGv_i64 var, int reg) -{ - tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); -} - -static inline void vfp_load_reg32(TCGv_i32 var, int reg) -{ - tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); -} - -static inline void vfp_store_reg32(TCGv_i32 var, int reg) -{ - tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); -} - void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop) { long off = neon_element_offset(reg, ele, memop); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ #include "decode-vfp.c.inc" #include "decode-vfp-uncond.c.inc" +static inline void vfp_load_reg64(TCGv_i64 var, int reg) +{ + tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(true, reg)); +} + +static inline void vfp_store_reg64(TCGv_i64 var, int reg) +{ + tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(true, reg)); +} + +static inline void vfp_load_reg32(TCGv_i32 var, int reg) +{ + tcg_gen_ld_i32(var, cpu_env, vfp_reg_offset(false, reg)); +} + +static inline void vfp_store_reg32(TCGv_i32 var, int reg) +{ + tcg_gen_st_i32(var, cpu_env, vfp_reg_offset(false, reg)); +} + /* * The imm8 encodes the sign bit, enough bits to represent an exponent in * the range 01....1xx to 10....0xx, and the most significant 4 bits of -- 2.20.1 Make the remaining functions which are needed by translate-vfp.c.inc global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-8-peter.maydell@linaro.org --- target/arm/translate-a32.h | 18 ++++++++++++++++++ target/arm/translate.c | 25 ++++++++----------------- 2 files changed, 26 insertions(+), 17 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void read_neon_element32(TCGv_i32 dest, int reg, int ele, MemOp memop); void read_neon_element64(TCGv_i64 dest, int reg, int ele, MemOp memop); void write_neon_element32(TCGv_i32 src, int reg, int ele, MemOp memop); void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop); +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs); +void gen_set_cpsr(TCGv_i32 var, uint32_t mask); +void gen_set_condexec(DisasContext *s); +void gen_set_pc_im(DisasContext *s, target_ulong val); +void gen_lookup_tb(DisasContext *s); +long vfp_reg_offset(bool dp, unsigned reg); +long neon_full_reg_offset(unsigned reg); static inline TCGv_i32 load_cpu_offset(int offset) { @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_reg(DisasContext *s, int reg) return tmp; } +void store_reg(DisasContext *s, int reg, TCGv_i32 var); + void gen_aa32_ld_internal_i32(DisasContext *s, TCGv_i32 val, TCGv_i32 a32, int index, MemOp opc); void gen_aa32_st_internal_i32(DisasContext *s, TCGv_i32 val, @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) #undef DO_GEN_LD #undef DO_GEN_ST +#if defined(CONFIG_USER_ONLY) +#define IS_USER(s) 1 +#else +#define IS_USER(s) (s->user) +#endif + +/* Set NZCV flags from the high 4 bits of var. */ +#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) + #endif 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 @@ #include "translate.h" #include "translate-a32.h" -#if defined(CONFIG_USER_ONLY) -#define IS_USER(s) 1 -#else -#define IS_USER(s) (s->user) -#endif - /* These are TCG temporaries used only by the legacy iwMMXt decoder */ static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; /* These are TCG globals which alias CPUARMState fields */ @@ -XXX,XX +XXX,XX @@ void load_reg_var(DisasContext *s, TCGv_i32 var, int reg) * This is used for load/store for which use of PC implies (literal), * or ADD that implies ADR. */ -static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) +TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static TCGv_i32 add_reg_for_lit(DisasContext *s, int reg, int ofs) /* Set a CPU register. The source must be a temporary and will be marked as dead. */ -static void store_reg(DisasContext *s, int reg, TCGv_i32 var) +void store_reg(DisasContext *s, int reg, TCGv_i32 var) { if (reg == 15) { /* In Thumb mode, we must ignore bit 0. @@ -XXX,XX +XXX,XX @@ static void store_sp_checked(DisasContext *s, TCGv_i32 var) #define gen_sxtb16(var) gen_helper_sxtb16(var, var) #define gen_uxtb16(var) gen_helper_uxtb16(var, var) - -static inline void gen_set_cpsr(TCGv_i32 var, uint32_t mask) +void gen_set_cpsr(TCGv_i32 var, uint32_t mask) { TCGv_i32 tmp_mask = tcg_const_i32(mask); gen_helper_cpsr_write(cpu_env, var, tmp_mask); tcg_temp_free_i32(tmp_mask); } -/* Set NZCV flags from the high 4 bits of var. */ -#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) static void gen_exception_internal(int excp) { @@ -XXX,XX +XXX,XX @@ void arm_gen_test_cc(int cc, TCGLabel *label) arm_free_cc(&cmp); } -static inline void gen_set_condexec(DisasContext *s) +void gen_set_condexec(DisasContext *s) { if (s->condexec_mask) { uint32_t val = (s->condexec_cond << 4) | (s->condexec_mask >> 1); @@ -XXX,XX +XXX,XX @@ static inline void gen_set_condexec(DisasContext *s) } } -static inline void gen_set_pc_im(DisasContext *s, target_ulong val) +void gen_set_pc_im(DisasContext *s, target_ulong val) { tcg_gen_movi_i32(cpu_R[15], val); } @@ -XXX,XX +XXX,XX @@ static void gen_exception_el(DisasContext *s, int excp, uint32_t syn, } /* Force a TB lookup after an instruction that changes the CPU state. */ -static inline void gen_lookup_tb(DisasContext *s) +void gen_lookup_tb(DisasContext *s) { tcg_gen_movi_i32(cpu_R[15], s->base.pc_next); s->base.is_jmp = DISAS_EXIT; @@ -XXX,XX +XXX,XX @@ static inline void gen_hlt(DisasContext *s, int imm) /* * Return the offset of a "full" NEON Dreg. */ -static long neon_full_reg_offset(unsigned reg) +long neon_full_reg_offset(unsigned reg) { return offsetof(CPUARMState, vfp.zregs[reg >> 1].d[reg & 1]); } @@ -XXX,XX +XXX,XX @@ static long neon_element_offset(int reg, int element, MemOp memop) } /* Return the offset of a VFP Dreg (dp = true) or VFP Sreg (dp = false). */ -static long vfp_reg_offset(bool dp, unsigned reg) +long vfp_reg_offset(bool dp, unsigned reg) { if (dp) { return neon_element_offset(reg, 0, MO_64); -- 2.20.1 Switch translate-vfp.c.inc from being #included into translate.c to being its own compilation unit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-9-peter.maydell@linaro.org --- target/arm/translate-a32.h | 2 ++ target/arm/{translate-vfp.c.inc => translate-vfp.c} | 12 +++++++----- target/arm/translate.c | 3 +-- target/arm/meson.build | 5 +++-- 4 files changed, 13 insertions(+), 9 deletions(-) rename target/arm/{translate-vfp.c.inc => translate-vfp.c} (99%) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ /* Prototypes for autogenerated disassembler functions */ bool disas_m_nocp(DisasContext *dc, uint32_t insn); +bool disas_vfp(DisasContext *s, uint32_t insn); +bool disas_vfp_uncond(DisasContext *s, uint32_t insn); void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c similarity index 99% rename from target/arm/translate-vfp.c.inc rename to target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -/* - * This file is intended to be included from translate.c; it uses - * some macros and definitions provided by that file. - * It might be possible to convert it to a standalone .c file eventually. - */ +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "exec/exec-all.h" +#include "exec/gen-icount.h" +#include "translate.h" +#include "translate-a32.h" /* Include the generated VFP decoder */ #include "decode-vfp.c.inc" 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 TCGv_ptr vfp_reg_ptr(bool dp, int reg) #define ARM_CP_RW_BIT (1 << 20) -/* Include the VFP and Neon decoders */ -#include "translate-vfp.c.inc" +/* Include the Neon decoder */ #include "translate-neon.c.inc" static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), - decodetree.process('vfp.decode', extra_args: '--static-decode=disas_vfp'), - decodetree.process('vfp-uncond.decode', extra_args: '--static-decode=disas_vfp_uncond'), + decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), + decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), decodetree.process('a32.decode', extra_args: '--static-decode=disas_a32'), decodetree.process('a32-uncond.decode', extra_args: '--static-decode=disas_a32_uncond'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'tlb_helper.c', 'translate.c', 'translate-m-nocp.c', + 'translate-vfp.c', 'vec_helper.c', 'vfp_helper.c', 'cpu_tcg.c', -- 2.20.1 The function vfp_reg_ptr() is used only in translate-neon.c.inc; move it there. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-10-peter.maydell@linaro.org --- target/arm/translate.c | 7 ------- target/arm/translate-neon.c.inc | 7 +++++++ 2 files changed, 7 insertions(+), 7 deletions(-) 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 @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) } } -static TCGv_ptr vfp_reg_ptr(bool dp, int reg) -{ - TCGv_ptr ret = tcg_temp_new_ptr(); - tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); - return ret; -} - #define ARM_CP_RW_BIT (1 << 20) /* Include the Neon decoder */ diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static inline int neon_3same_fp_size(DisasContext *s, int x) #include "decode-neon-ls.c.inc" #include "decode-neon-shared.c.inc" +static TCGv_ptr vfp_reg_ptr(bool dp, int reg) +{ + TCGv_ptr ret = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ret, cpu_env, vfp_reg_offset(dp, reg)); + return ret; +} + static void neon_load_element(TCGv_i32 var, int reg, int ele, MemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); -- 2.20.1 The VFPGenFixPointFn typedef is unused; delete it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210430132740.10391-11-peter.maydell@linaro.org --- target/arm/translate.c | 2 -- 1 file changed, 2 deletions(-) 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 const char * const regnames[] = /* Function prototypes for gen_ functions calling Neon helpers. */ typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, TCGv_i32, TCGv_i32); -/* Function prototypes for gen_ functions for fix point conversions */ -typedef void VFPGenFixPointFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); /* initialize TCG globals. */ void arm_translate_init(void) -- 2.20.1 Move the NeonGenThreeOpEnvFn typedef to translate.h together with the other similar typedefs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210430132740.10391-12-peter.maydell@linaro.org --- target/arm/translate.h | 2 ++ target/arm/translate.c | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) 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 @@ typedef void NeonGenOneOpFn(TCGv_i32, TCGv_i32); typedef void NeonGenOneOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32); typedef void NeonGenTwoOpFn(TCGv_i32, TCGv_i32, TCGv_i32); typedef void NeonGenTwoOpEnvFn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, + TCGv_i32, TCGv_i32); typedef void NeonGenTwo64OpFn(TCGv_i64, TCGv_i64, TCGv_i64); typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); 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 const char * const regnames[] = { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; -/* Function prototypes for gen_ functions calling Neon helpers. */ -typedef void NeonGenThreeOpEnvFn(TCGv_i32, TCGv_env, TCGv_i32, - TCGv_i32, TCGv_i32); /* initialize TCG globals. */ void arm_translate_init(void) -- 2.20.1 Make the remaining functions needed by the translate-neon code global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-13-peter.maydell@linaro.org --- target/arm/translate-a32.h | 8 ++++++++ target/arm/translate.c | 10 ++-------- 2 files changed, 10 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_set_pc_im(DisasContext *s, target_ulong val); void gen_lookup_tb(DisasContext *s); long vfp_reg_offset(bool dp, unsigned reg); long neon_full_reg_offset(unsigned reg); +long neon_element_offset(int reg, int element, MemOp memop); +void gen_rev16(TCGv_i32 dest, TCGv_i32 var); static inline TCGv_i32 load_cpu_offset(int offset) { @@ -XXX,XX +XXX,XX @@ DO_GEN_ST(32, MO_UL) /* Set NZCV flags from the high 4 bits of var. */ #define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV) +/* Swap low and high halfwords. */ +static inline void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) +{ + tcg_gen_rotri_i32(dest, var, 16); +} + #endif 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 void gen_smul_dual(TCGv_i32 a, TCGv_i32 b) } /* Byteswap each halfword. */ -static void gen_rev16(TCGv_i32 dest, TCGv_i32 var) +void gen_rev16(TCGv_i32 dest, TCGv_i32 var) { TCGv_i32 tmp = tcg_temp_new_i32(); TCGv_i32 mask = tcg_const_i32(0x00ff00ff); @@ -XXX,XX +XXX,XX @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var) tcg_gen_ext16s_i32(dest, var); } -/* Swap low and high halfwords. */ -static void gen_swap_half(TCGv_i32 dest, TCGv_i32 var) -{ - tcg_gen_rotri_i32(dest, var, 16); -} - /* Dual 16-bit add. Result placed in t0 and t1 is marked as dead. tmp = (t0 ^ t1) & 0x8000; t0 &= ~0x8000; @@ -XXX,XX +XXX,XX @@ long neon_full_reg_offset(unsigned reg) * Return the offset of a 2**SIZE piece of a NEON register, at index ELE, * where 0 is the least significant end of the register. */ -static long neon_element_offset(int reg, int element, MemOp memop) +long neon_element_offset(int reg, int element, MemOp memop) { int element_size = 1 << (memop & MO_SIZE); int ofs = element * element_size; -- 2.20.1 Switch translate-neon.c.inc from being #included into translate.c to being its own compilation unit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430132740.10391-14-peter.maydell@linaro.org --- target/arm/translate-a32.h | 3 +++ .../arm/{translate-neon.c.inc => translate-neon.c} | 12 +++++++----- target/arm/translate.c | 3 --- target/arm/meson.build | 7 ++++--- 4 files changed, 14 insertions(+), 11 deletions(-) rename target/arm/{translate-neon.c.inc => translate-neon.c} (99%) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ bool disas_m_nocp(DisasContext *dc, uint32_t insn); bool disas_vfp(DisasContext *s, uint32_t insn); bool disas_vfp_uncond(DisasContext *s, uint32_t insn); +bool disas_neon_dp(DisasContext *s, uint32_t insn); +bool disas_neon_ls(DisasContext *s, uint32_t insn); +bool disas_neon_shared(DisasContext *s, uint32_t insn); void load_reg_var(DisasContext *s, TCGv_i32 var, int reg); void arm_gen_condlabel(DisasContext *s); diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c similarity index 99% rename from target/arm/translate-neon.c.inc rename to target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -/* - * This file is intended to be included from translate.c; it uses - * some macros and definitions provided by that file. - * It might be possible to convert it to a standalone .c file eventually. - */ +#include "qemu/osdep.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "exec/exec-all.h" +#include "exec/gen-icount.h" +#include "translate.h" +#include "translate-a32.h" static inline int plus1(DisasContext *s, int x) { 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 @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) #define ARM_CP_RW_BIT (1 << 20) -/* Include the Neon decoder */ -#include "translate-neon.c.inc" - static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, offsetof(CPUARMState, iwmmxt.regs[reg])); diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), - decodetree.process('neon-shared.decode', extra_args: '--static-decode=disas_neon_shared'), - decodetree.process('neon-dp.decode', extra_args: '--static-decode=disas_neon_dp'), - decodetree.process('neon-ls.decode', extra_args: '--static-decode=disas_neon_ls'), + decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), + decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), + decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), decodetree.process('vfp.decode', extra_args: '--decode=disas_vfp'), decodetree.process('vfp-uncond.decode', extra_args: '--decode=disas_vfp_uncond'), decodetree.process('m-nocp.decode', extra_args: '--decode=disas_m_nocp'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'tlb_helper.c', 'translate.c', 'translate-m-nocp.c', + 'translate-neon.c', 'translate-vfp.c', 'vec_helper.c', 'vfp_helper.c', -- 2.20.1 The WFI insn is not system-mode only, though it doesn't usually make a huge amount of sense for userspace code to execute it. Currently if you try it in qemu-arm then the helper function will raise an EXCP_HLT exception, which is not covered by the switch in cpu_loop() and results in an abort: qemu: unhandled CPU exception 0x10001 - aborting R00=00000001 R01=408003e4 R02=408003ec R03=000102ec R04=00010a28 R05=00010158 R06=00087460 R07=00010158 R08=00000000 R09=00000000 R10=00085b7c R11=408002a4 R12=408002b8 R13=408002a0 R14=0001057c R15=000102f8 PSR=60000010 -ZC- A usr32 qemu:handle_cpu_signal received signal outside vCPU context @ pc=0x7fcbfa4f0a12 Make the WFI helper function return immediately in the usermode emulator. This turns WFI into a NOP, which is OK because: * architecturally "WFI is a NOP" is a permitted implementation * aarch64 Linux kernels use the SCTLR_EL1.nTWI bit to trap userspace WFI and NOP it (though aarch32 kernels currently just let WFI do whatever it would do) We could in theory make the translate.c code special case user-mode emulation and NOP the insn entirely rather than making the helper do nothing, but because no real world code will be trying to execute WFI we don't care about efficiency and the helper provides a single place where we can make the change rather than having to touch multiple places in translate.c and translate-a64.c. Fixes: https://bugs.launchpad.net/qemu/+bug/1926759 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210430162212.825-1-peter.maydell@linaro.org --- target/arm/op_helper.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ static inline int check_wfx_trap(CPUARMState *env, bool is_wfe) void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) { +#ifdef CONFIG_USER_ONLY + /* + * WFI in the user-mode emulator is technically permitted but not + * something any real-world code would do. AArch64 Linux kernels + * trap it via SCTRL_EL1.nTWI and make it an (expensive) NOP; + * AArch32 kernels don't trap it so it will delay a bit. + * For QEMU, make it NOP here, because trying to raise EXCP_HLT + * would trigger an abort. + */ + return; +#else CPUState *cs = env_cpu(env); int target_el = check_wfx_trap(env, false); @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) cs->exception_index = EXCP_HLT; cs->halted = 1; cpu_loop_exit(cs); +#endif } void HELPER(wfe)(CPUARMState *env) -- 2.20.1 The omap_mmc_reset() function resets its SD card via device_legacy_reset(). We know that the SD card does not have a qbus of its own, so the new device_cold_reset() function (which resets both the device and its child buses) is equivalent here to device_legacy_reset() and we can just switch to the new API. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210430222348.8514-1-peter.maydell@linaro.org --- hw/sd/omap_mmc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ void omap_mmc_reset(struct omap_mmc_s *host) * into any bus, and we must reset it manually. When omap_mmc is * QOMified this must move into the QOM reset function. */ - device_legacy_reset(DEVICE(host->card)); + device_cold_reset(DEVICE(host->card)); } static uint64_t omap_mmc_read(void *opaque, hwaddr offset, -- 2.20.1 Both os-win32.h and os-posix.h include system header files. Instead of having osdep.h include them inside its 'extern "C"' block, make these headers handle that themselves, so that we don't include the system headers inside 'extern "C"'. This doesn't fix any current problems, but it's conceptually the right way to handle system headers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/qemu/osdep.h | 8 ++++---- include/sysemu/os-posix.h | 8 ++++++++ include/sysemu/os-win32.h | 8 ++++++++ 3 files changed, 20 insertions(+), 4 deletions(-) diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -XXX,XX +XXX,XX @@ QEMU_EXTERN_C int daemon(int, int); */ #include "glib-compat.h" -#ifdef __cplusplus -extern "C" { -#endif - #ifdef _WIN32 #include "sysemu/os-win32.h" #endif @@ -XXX,XX +XXX,XX @@ extern "C" { #include "sysemu/os-posix.h" #endif +#ifdef __cplusplus +extern "C" { +#endif + #include "qemu/typedefs.h" /* diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/os-posix.h +++ b/include/sysemu/os-posix.h @@ -XXX,XX +XXX,XX @@ #include <sys/sysmacros.h> #endif +#ifdef __cplusplus +extern "C" { +#endif + void os_set_line_buffering(void); void os_set_proc_name(const char *s); void os_setup_signal_handling(void); @@ -XXX,XX +XXX,XX @@ static inline void qemu_funlockfile(FILE *f) funlockfile(f); } +#ifdef __cplusplus +} +#endif + #endif diff --git a/include/sysemu/os-win32.h b/include/sysemu/os-win32.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/os-win32.h +++ b/include/sysemu/os-win32.h @@ -XXX,XX +XXX,XX @@ #include <windows.h> #include <ws2tcpip.h> +#ifdef __cplusplus +extern "C" { +#endif + #if defined(_WIN64) /* On w64, setjmp is implemented by _setjmp which needs a second parameter. * If this parameter is NULL, longjump does no stack unwinding. @@ -XXX,XX +XXX,XX @@ ssize_t qemu_recv_wrap(int sockfd, void *buf, size_t len, int flags); ssize_t qemu_recvfrom_wrap(int sockfd, void *buf, size_t len, int flags, struct sockaddr *addr, socklen_t *addrlen); +#ifdef __cplusplus +} +#endif + #endif -- 2.20.1 Make bswap.h handle being included outside an 'extern "C"' block: all system headers are included first, then all declarations are put inside an 'extern "C"' block. This requires a little rearrangement as currently we have an ifdef ladder that has some system includes and some local declarations or definitions, and we need to separate those out. We want to do this because dis-asm.h includes bswap.h, dis-asm.h may need to be included from C++ files, and system headers should not be included within 'extern "C"' blocks. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/qemu/bswap.h | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/include/qemu/bswap.h b/include/qemu/bswap.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/bswap.h +++ b/include/qemu/bswap.h @@ -XXX,XX +XXX,XX @@ #ifndef BSWAP_H #define BSWAP_H -#include "fpu/softfloat-types.h" - #ifdef CONFIG_MACHINE_BSWAP_H # include <sys/endian.h> # include <machine/bswap.h> @@ -XXX,XX +XXX,XX @@ # include <endian.h> #elif defined(CONFIG_BYTESWAP_H) # include <byteswap.h> +#define BSWAP_FROM_BYTESWAP +# else +#define BSWAP_FROM_FALLBACKS +#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#ifdef __cplusplus +extern "C" { +#endif + +#include "fpu/softfloat-types.h" + +#ifdef BSWAP_FROM_BYTESWAP static inline uint16_t bswap16(uint16_t x) { return bswap_16(x); @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) { return bswap_64(x); } -# else +#endif + +#ifdef BSWAP_FROM_FALLBACKS static inline uint16_t bswap16(uint16_t x) { return (((x & 0x00ff) << 8) | @@ -XXX,XX +XXX,XX @@ static inline uint64_t bswap64(uint64_t x) ((x & 0x00ff000000000000ULL) >> 40) | ((x & 0xff00000000000000ULL) >> 56)); } -#endif /* ! CONFIG_MACHINE_BSWAP_H */ +#endif + +#undef BSWAP_FROM_BYTESWAP +#undef BSWAP_FROM_FALLBACKS static inline void bswap16s(uint16_t *s) { @@ -XXX,XX +XXX,XX @@ DO_STN_LDN_P(be) #undef le_bswaps #undef be_bswaps +#ifdef __cplusplus +} +#endif + #endif /* BSWAP_H */ -- 2.20.1 Make dis-asm.h handle being included outside an 'extern "C"' block; this allows us to remove the 'extern "C"' blocks that our two C++ files that include it are using. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/disas/dis-asm.h | 12 ++++++++++-- disas/arm-a64.cc | 2 -- disas/nanomips.cpp | 2 -- 3 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/disas/dis-asm.h b/include/disas/dis-asm.h index XXXXXXX..XXXXXXX 100644 --- a/include/disas/dis-asm.h +++ b/include/disas/dis-asm.h @@ -XXX,XX +XXX,XX @@ #ifndef DISAS_DIS_ASM_H #define DISAS_DIS_ASM_H +#include "qemu/bswap.h" + +#ifdef __cplusplus +extern "C" { +#endif + typedef void *PTR; typedef uint64_t bfd_vma; typedef int64_t bfd_signed_vma; @@ -XXX,XX +XXX,XX @@ bool cap_disas_plugin(disassemble_info *info, uint64_t pc, size_t size); /* from libbfd */ -#include "qemu/bswap.h" - static inline bfd_vma bfd_getl64(const bfd_byte *addr) { return ldq_le_p(addr); @@ -XXX,XX +XXX,XX @@ static inline bfd_vma bfd_getb16(const bfd_byte *addr) typedef bool bfd_boolean; +#ifdef __cplusplus +} +#endif + #endif /* DISAS_DIS_ASM_H */ diff --git a/disas/arm-a64.cc b/disas/arm-a64.cc index XXXXXXX..XXXXXXX 100644 --- a/disas/arm-a64.cc +++ b/disas/arm-a64.cc @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include "vixl/a64/disasm-a64.h" diff --git a/disas/nanomips.cpp b/disas/nanomips.cpp index XXXXXXX..XXXXXXX 100644 --- a/disas/nanomips.cpp +++ b/disas/nanomips.cpp @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" -extern "C" { #include "disas/dis-asm.h" -} #include <cstring> #include <stdexcept> -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The i.MX25 PDK board has 2 banks for SDRAM, each can address up to 256 MiB. So the total RAM usable for this board is 512M. When we ask for more we get a misleading error message: $ qemu-system-arm -M imx25-pdk -m 513M qemu-system-arm: Invalid RAM size, should be 128 MiB Update the error message to better match the reality: $ qemu-system-arm -M imx25-pdk -m 513M qemu-system-arm: RAM size more than 512 MiB is not supported Fixes: bf350daae02 ("arm/imx25_pdk: drop RAM size fixup") Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20210407225608.1882855-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/imx25_pdk.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info imx25_pdk_binfo; static void imx25_pdk_init(MachineState *machine) { - MachineClass *mc = MACHINE_GET_CLASS(machine); IMX25PDK *s = g_new0(IMX25PDK, 1); unsigned int ram_size; unsigned int alias_offset; @@ -XXX,XX +XXX,XX @@ static void imx25_pdk_init(MachineState *machine) /* We need to initialize our memory */ if (machine->ram_size > (FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE)) { - char *sz = size_to_str(mc->default_ram_size); - error_report("Invalid RAM size, should be %s", sz); + char *sz = size_to_str(FSL_IMX25_SDRAM0_SIZE + FSL_IMX25_SDRAM1_SIZE); + error_report("RAM size more than %s is not supported", sz); g_free(sz); exit(EXIT_FAILURE); } -- 2.20.1 The MPS2 SCC device doesn't have any documentation of its properties; add a "QEMU interface" format comment describing them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210504120912.23094-2-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ * (at your option) any later version. */ +/* + * This is a model of the Serial Communication Controller (SCC) + * block found in most MPS FPGA images. + * + * QEMU interface: + * + sysbus MMIO region 0: the register bank + * + QOM property "scc-cfg4": value of the read-only CFG4 register + * + QOM property "scc-aid": value of the read-only SCC_AID register + * + QOM property "scc-id": value of the read-only SCC_ID register + * + QOM property array "oscclk": reset values of the OSCCLK registers + * (which are accessed via the SYS_CFG channel provided by this device) + */ #ifndef MPS2_SCC_H #define MPS2_SCC_H -- 2.20.1 On some boards, SCC config register CFG0 bit 0 controls whether parts of the board memory map are remapped. Support this with: * a device property scc-cfg0 so the board can specify the initial value of the CFG0 register * an outbound GPIO line which tracks bit 0 and which the board can wire up to provide the remapping Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210504120912.23094-3-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 9 +++++++++ hw/misc/mps2-scc.c | 13 ++++++++++--- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ * + QOM property "scc-cfg4": value of the read-only CFG4 register * + QOM property "scc-aid": value of the read-only SCC_AID register * + QOM property "scc-id": value of the read-only SCC_ID register + * + QOM property "scc-cfg0": reset value of the CFG0 register * + QOM property array "oscclk": reset values of the OSCCLK registers * (which are accessed via the SYS_CFG channel provided by this device) + * + named GPIO output "remap": this tracks the value of CFG0 register + * bit 0. Boards where this bit controls memory remapping should + * connect this GPIO line to a function performing that mapping. + * Boards where bit 0 has no special function should leave the GPIO + * output disconnected. */ #ifndef MPS2_SCC_H #define MPS2_SCC_H @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t num_oscclk; uint32_t *oscclk; uint32_t *oscclk_reset; + uint32_t cfg0_reset; + + qemu_irq remap; }; #endif diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ #include "qemu/bitops.h" #include "trace.h" #include "hw/sysbus.h" +#include "hw/irq.h" #include "migration/vmstate.h" #include "hw/registerfields.h" #include "hw/misc/mps2-scc.h" @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, switch (offset) { case A_CFG0: /* - * TODO on some boards bit 0 controls RAM remapping; - * on others bit 1 is CPU_WAIT. + * On some boards bit 0 controls board-specific remapping; + * we always reflect bit 0 in the 'remap' GPIO output line, + * and let the board wire it up or not as it chooses. + * TODO on some boards bit 1 is CPU_WAIT. */ s->cfg0 = value; + qemu_set_irq(s->remap, s->cfg0 & 1); break; case A_CFG1: s->cfg1 = value; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) int i; trace_mps2_scc_reset(); - s->cfg0 = 0; + s->cfg0 = s->cfg0_reset; s->cfg1 = 0; s->cfg2 = 0; s->cfg5 = 0; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_init(Object *obj) memory_region_init_io(&s->iomem, obj, &mps2_scc_ops, s, "mps2-scc", 0x1000); sysbus_init_mmio(sbd, &s->iomem); + qdev_init_gpio_out_named(DEVICE(obj), &s->remap, "remap", 1); } static void mps2_scc_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static Property mps2_scc_properties[] = { DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), + /* Reset value for CFG0 register */ + DEFINE_PROP_UINT32("scc-cfg0", MPS2SCC, cfg0_reset, 0), /* * These are the initial settings for the source clocks on the board. * In hardware they can be configured via a config file read by the -- 2.20.1 The AN524 FPGA image supports two memory maps, which differ in where the QSPI and BRAM are. In the default map, the BRAM is at 0x0000_0000, and the QSPI at 0x2800_0000. In the second map, they are the other way around. In hardware, the initial mapping can be selected by the user by writing either "REMAP: BRAM" (the default) or "REMAP: QSPI" in the board configuration file. The board config file is acted on by the "Motherboard Configuration Controller", which is an entirely separate microcontroller on the dev board but outside the FPGA. The guest can also dynamically change the mapping via the SCC CFG_REG0 register. Implement this functionality for QEMU, using a machine property "remap" with valid values "BRAM" and "QSPI" to allow the user to set the initial mapping, in the same way they can on the FPGA, and wiring up the bit from the SCC register to also switch the mapping. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210504120912.23094-4-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 10 ++++ hw/arm/mps2-tz.c | 108 ++++++++++++++++++++++++++++++++++++++- 2 files changed, 117 insertions(+), 1 deletion(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ Differences between QEMU and real hardware: flash, but only as simple ROM, so attempting to rewrite the flash from the guest will fail - QEMU does not model the USB controller in MPS3 boards + +Machine-specific options +"""""""""""""""""""""""" + +The following machine-specific options are supported: + +remap + Supported for ``mps3-an524`` only. + Set ``BRAM``/``QSPI`` to select the initial memory mapping. The + default is ``BRAM``. diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "exec/address-spaces.h" #include "sysemu/sysemu.h" +#include "sysemu/reset.h" #include "hw/misc/unimp.h" #include "hw/char/cmsdk-apb-uart.h" #include "hw/timer/cmsdk-apb-timer.h" @@ -XXX,XX +XXX,XX @@ #include "hw/core/split-irq.h" #include "hw/qdev-clock.h" #include "qom/object.h" +#include "hw/irq.h" #define MPS2TZ_NUMIRQ_MAX 96 #define MPS2TZ_RAM_MAX 5 @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; Clock *sysclk; Clock *s32kclk; + + bool remap; + qemu_irq remap_irq; }; #define TYPE_MPS2TZ_MACHINE "mps2tz" @@ -XXX,XX +XXX,XX @@ static const RAMInfo an505_raminfo[] = { { }, }; +/* + * Note that the addresses and MPC numbering here should match up + * with those used in remap_memory(), which can swap the BRAM and QSPI. + */ static const RAMInfo an524_raminfo[] = { { .name = "bram", .base = 0x00000000, @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); sccdev = DEVICE(scc); + qdev_prop_set_uint32(sccdev, "scc-cfg0", mms->remap ? 1 : 0); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } +static hwaddr boot_mem_base(MPS2TZMachineState *mms) +{ + /* + * Return the canonical address of the block which will be mapped + * at address 0x0 (i.e. where the vector table is). + * This is usually 0, but if the AN524 alternate memory map is + * enabled it will be the base address of the QSPI block. + */ + return mms->remap ? 0x28000000 : 0; +} + +static void remap_memory(MPS2TZMachineState *mms, int map) +{ + /* + * Remap the memory for the AN524. 'map' is the value of + * SCC CFG_REG0 bit 0, i.e. 0 for the default map and 1 + * for the "option 1" mapping where QSPI is at address 0. + * + * Effectively we need to swap around the "upstream" ends of + * MPC 0 and MPC 1. + */ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + int i; + + if (mmc->fpga_type != FPGA_AN524) { + return; + } + + memory_region_transaction_begin(); + for (i = 0; i < 2; i++) { + TZMPC *mpc = &mms->mpc[i]; + MemoryRegion *upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); + hwaddr addr = (i ^ map) ? 0x28000000 : 0; + + memory_region_set_address(upstream, addr); + } + memory_region_transaction_commit(); +} + +static void remap_irq_fn(void *opaque, int n, int level) +{ + MPS2TZMachineState *mms = opaque; + + remap_memory(mms, level); +} + static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) @@ -XXX,XX +XXX,XX @@ static uint32_t boot_ram_size(MPS2TZMachineState *mms) MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); for (p = mmc->raminfo; p->name; p++) { - if (p->base == 0) { + if (p->base == boot_mem_base(mms)) { return p->size; } } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_non_mpc_ram(mms); + if (mmc->fpga_type == FPGA_AN524) { + /* + * Connect the line from the SCC so that we can remap when the + * guest updates that register. + */ + mms->remap_irq = qemu_allocate_irq(remap_irq_fn, mms, 0); + qdev_connect_gpio_out_named(DEVICE(&mms->scc), "remap", 0, + mms->remap_irq); + } + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, boot_ram_size(mms)); } @@ -XXX,XX +XXX,XX @@ static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, *iregion = region; } +static char *mps2_get_remap(Object *obj, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + const char *val = mms->remap ? "QSPI" : "BRAM"; + return g_strdup(val); +} + +static void mps2_set_remap(Object *obj, const char *value, Error **errp) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(obj); + + if (!strcmp(value, "BRAM")) { + mms->remap = false; + } else if (!strcmp(value, "QSPI")) { + mms->remap = true; + } else { + error_setg(errp, "Invalid remap value"); + error_append_hint(errp, "Valid values are BRAM and QSPI.\n"); + } +} + +static void mps2_machine_reset(MachineState *machine) +{ + MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); + + /* + * Set the initial memory mapping before triggering the reset of + * the rest of the system, so that the guest image loader and CPU + * reset see the correct mapping. + */ + remap_memory(mms, mms->remap); + qemu_devices_reset(); +} + static void mps2tz_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); IDAUInterfaceClass *iic = IDAU_INTERFACE_CLASS(oc); mc->init = mps2tz_common_init; + mc->reset = mps2_machine_reset; iic->check = mps2_tz_idau_check; } @@ -XXX,XX +XXX,XX @@ static void mps3tz_an524_class_init(ObjectClass *oc, void *data) mmc->raminfo = an524_raminfo; mmc->armsse_type = TYPE_SSE200; mps2tz_set_default_ram_info(mmc); + + object_class_property_add_str(oc, "remap", mps2_get_remap, mps2_set_remap); + object_class_property_set_description(oc, "remap", + "Set memory mapping. Valid values " + "are BRAM (default) and QSPI."); } static void mps3tz_an547_class_init(ObjectClass *oc, void *data) -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Commit dfc388797cc4 ("hw/arm: xlnx: Set all boards' GEM 'phy-addr' property value to 23") configured the PHY address for xilinx-zynq-a9 to 23. When trying to boot xilinx-zynq-a9 with zynq-zc702.dtb or zynq-zc706.dtb, this results in the following error message when trying to use the Ethernet interface. macb e000b000.ethernet eth0: Could not attach PHY (-19) The devicetree files for ZC702 and ZC706 configure PHY address 7. The documentation for the ZC702 and ZC706 evaluation boards suggest that the PHY address is 7, not 23. Other boards use PHY address 0, 1, 3, or 7. I was unable to find a documentation or a devicetree file suggesting or using PHY address 23. The Ethernet interface starts working with zynq-zc702.dtb and zynq-zc706.dtb when setting the PHY address to 7, so let's use it. Cc: Bin Meng <bin.meng@windriver.com> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Bin Meng <bmeng.cn@gmail.com> Acked-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20210504124140.1100346-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void gem_init(NICInfo *nd, uint32_t base, qemu_irq irq) qemu_check_nic_model(nd, TYPE_CADENCE_GEM); qdev_set_nic_properties(dev, nd); } - object_property_set_int(OBJECT(dev), "phy-addr", 23, &error_abort); + object_property_set_int(OBJECT(dev), "phy-addr", 7, &error_abort); s = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, base); -- 2.20.1