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 target-arm queue: mostly smallish stuff. I expect to send out another pullreq at the end of this week, but since this is up to 32 patches already I'd rather send it out now than accumulate a monster sized patchset. thanks -- PMM The following changes since commit 0ab4c574a55448a37b9f616259b82950742c9427: Merge remote-tracking branch 'remotes/kraxel/tags/ui-20180626-pull-request' into staging (2018-06-26 16:44:57 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180626 for you to fetch changes up to 9b945a9ee36a34eaeca412ef9ef35fbfe33c2c85: aspeed/timer: use the APB frequency from the SCU (2018-06-26 17:50:42 +0100) ---------------------------------------------------------------- target-arm queue: * aspeed: set APB clocks correctly (fixes slowdown on palmetto) * smmuv3: cache config data and TLB entries * v7m/v8m: support read/write from MPU regions smaller than 1K * various: clean up logging/debug messages * xilinx_spips: Make dma transactions as per dma_burst_size ---------------------------------------------------------------- Cédric Le Goater (6): aspeed/smc: fix dummy cycles count when in dual IO mode aspeed/smc: fix HW strapping aspeed/smc: rename aspeed_smc_flash_send_addr() to aspeed_smc_flash_setup() aspeed/scu: introduce clock frequencies aspeed: initialize the SCU controller first aspeed/timer: use the APB frequency from the SCU Eric Auger (3): hw/arm/smmuv3: Cache/invalidate config data hw/arm/smmuv3: IOTLB emulation hw/arm/smmuv3: Add notifications on invalidation Jia He (1): hw/arm/smmuv3: Fix translate error handling Joel Stanley (1): MAINTAINERS: Add ASPEED BMCs Peter Maydell (3): tcg: Support MMU protection regions smaller than TARGET_PAGE_SIZE target/arm: Set page (region) size in get_phys_addr_pmsav7() target/arm: Handle small regions in get_phys_addr_pmsav8() Philippe Mathieu-Daudé (17): MAINTAINERS: Adopt the Gumstix computers-on-module machines hw/input/pckbd: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/input/tsc2005: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/dma/omap_dma: Use qemu_log_mask(UNIMP) instead of printf hw/dma/omap_dma: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/ssi/omap_spi: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/sd/omap_mmc: Use qemu_log_mask(UNIMP) instead of printf hw/i2c/omap_i2c: Use qemu_log_mask(UNIMP) instead of fprintf hw/arm/omap1: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/arm/omap: Use qemu_log_mask(GUEST_ERROR) instead of fprintf hw/arm/stellaris: Use qemu_log_mask(UNIMP) instead of fprintf hw/net/stellaris_enet: Fix a typo hw/net/stellaris_enet: Use qemu_log_mask(GUEST_ERROR) instead of hw_error hw/net/smc91c111: Use qemu_log_mask(GUEST_ERROR) instead of hw_error hw/net/smc91c111: Use qemu_log_mask(UNIMP) instead of fprintf hw/arm/stellaris: Fix gptm_write() error message hw/arm/stellaris: Use HWADDR_PRIx to display register address Sai Pavan Boddu (1): xilinx_spips: Make dma transactions as per dma_burst_size accel/tcg/softmmu_template.h | 24 ++- hw/arm/smmuv3-internal.h | 12 +- include/exec/cpu-all.h | 5 +- include/hw/arm/omap.h | 30 +-- include/hw/arm/smmu-common.h | 24 +++ include/hw/arm/smmuv3.h | 1 + include/hw/misc/aspeed_scu.h | 70 ++++++- include/hw/ssi/xilinx_spips.h | 5 +- include/hw/timer/aspeed_timer.h | 4 + accel/tcg/cputlb.c | 131 +++++++++++-- hw/arm/aspeed_soc.c | 42 ++-- hw/arm/omap1.c | 18 +- hw/arm/smmu-common.c | 118 ++++++++++- hw/arm/smmuv3.c | 420 ++++++++++++++++++++++++++++++++++++---- hw/arm/stellaris.c | 8 +- hw/dma/omap_dma.c | 70 ++++--- hw/i2c/omap_i2c.c | 20 +- hw/input/pckbd.c | 4 +- hw/input/tsc2005.c | 13 +- hw/misc/aspeed_scu.c | 106 ++++++++++ hw/net/smc91c111.c | 21 +- hw/net/stellaris_enet.c | 11 +- hw/sd/omap_mmc.c | 13 +- hw/ssi/aspeed_smc.c | 48 ++--- hw/ssi/omap_spi.c | 15 +- hw/ssi/xilinx_spips.c | 23 ++- hw/timer/aspeed_timer.c | 19 +- target/arm/helper.c | 115 +++++++---- MAINTAINERS | 14 +- hw/arm/trace-events | 27 ++- 30 files changed, 1176 insertions(+), 255 deletions(-) From: Cédric Le Goater <clg@kaod.org> When configured in dual I/O mode, address and data are sent in dual mode, including the dummy byte cycles in between. Adapt the count to the IO setting. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180612065716.10587-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/aspeed_smc.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ /* CEx Control Register */ #define R_CTRL0 (0x10 / 4) +#define CTRL_IO_DUAL_DATA (1 << 29) +#define CTRL_IO_DUAL_ADDR_DATA (1 << 28) /* Includes dummies */ #define CTRL_CMD_SHIFT 16 #define CTRL_CMD_MASK 0xff #define CTRL_DUMMY_HIGH_SHIFT 14 @@ -XXX,XX +XXX,XX @@ static int aspeed_smc_flash_dummies(const AspeedSMCFlash *fl) uint32_t r_ctrl0 = s->regs[s->r_ctrl0 + fl->id]; uint32_t dummy_high = (r_ctrl0 >> CTRL_DUMMY_HIGH_SHIFT) & 0x1; uint32_t dummy_low = (r_ctrl0 >> CTRL_DUMMY_LOW_SHIFT) & 0x3; + uint32_t dummies = ((dummy_high << 2) | dummy_low) * 8; - return ((dummy_high << 2) | dummy_low) * 8; + if (r_ctrl0 & CTRL_IO_DUAL_ADDR_DATA) { + dummies /= 2; + } + + return dummies; } static void aspeed_smc_flash_send_addr(AspeedSMCFlash *fl, uint32_t addr) -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> Only the flash type is strapped by HW. The 4BYTE mode is set by firmware when the flash device is detected. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180612065716.10587-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/aspeed_smc.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_reset(DeviceState *d) aspeed_smc_segment_to_reg(&s->ctrl->segments[i]); } - /* HW strapping for AST2500 FMC controllers */ + /* HW strapping flash type for FMC controllers */ if (s->ctrl->segments == aspeed_segments_ast2500_fmc) { /* flash type is fixed to SPI for CE0 and CE1 */ s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE0); s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE1); - - /* 4BYTE mode is autodetected for CE0. Let's force it to 1 for - * now */ - s->regs[s->r_ce_ctrl] |= (1 << (CTRL_EXTENDED0)); } /* HW strapping for AST2400 FMC controllers (SCU70). Let's use the * configuration of the palmetto-bmc machine */ if (s->ctrl->segments == aspeed_segments_fmc) { s->regs[s->r_conf] |= (CONF_FLASH_TYPE_SPI << CONF_FLASH_TYPE0); - - s->regs[s->r_ce_ctrl] |= (1 << (CTRL_EXTENDED0)); } } -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> Also handle the fake transfers for dummy bytes in this setup routine. It will be useful when we activate MMIO execution. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180612065716.10587-4-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/aspeed_smc.c | 31 ++++++++++++++++--------------- 1 file changed, 16 insertions(+), 15 deletions(-) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ static int aspeed_smc_flash_dummies(const AspeedSMCFlash *fl) return dummies; } -static void aspeed_smc_flash_send_addr(AspeedSMCFlash *fl, uint32_t addr) +static void aspeed_smc_flash_setup(AspeedSMCFlash *fl, uint32_t addr) { const AspeedSMCState *s = fl->controller; uint8_t cmd = aspeed_smc_flash_cmd(fl); + int i; /* Flash access can not exceed CS segment */ addr = aspeed_smc_check_segment_addr(fl, addr); @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_send_addr(AspeedSMCFlash *fl, uint32_t addr) ssi_transfer(s->spi, (addr >> 16) & 0xff); ssi_transfer(s->spi, (addr >> 8) & 0xff); ssi_transfer(s->spi, (addr & 0xff)); + + /* + * Use fake transfers to model dummy bytes. The value should + * be configured to some non-zero value in fast read mode and + * zero in read mode. But, as the HW allows inconsistent + * settings, let's check for fast read mode. + */ + if (aspeed_smc_flash_mode(fl) == CTRL_FREADMODE) { + for (i = 0; i < aspeed_smc_flash_dummies(fl); i++) { + ssi_transfer(fl->controller->spi, 0xFF); + } + } } static uint64_t aspeed_smc_flash_read(void *opaque, hwaddr addr, unsigned size) @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_smc_flash_read(void *opaque, hwaddr addr, unsigned size) case CTRL_READMODE: case CTRL_FREADMODE: aspeed_smc_flash_select(fl); - aspeed_smc_flash_send_addr(fl, addr); - - /* - * Use fake transfers to model dummy bytes. The value should - * be configured to some non-zero value in fast read mode and - * zero in read mode. But, as the HW allows inconsistent - * settings, let's check for fast read mode. - */ - if (aspeed_smc_flash_mode(fl) == CTRL_FREADMODE) { - for (i = 0; i < aspeed_smc_flash_dummies(fl); i++) { - ssi_transfer(fl->controller->spi, 0xFF); - } - } + aspeed_smc_flash_setup(fl, addr); for (i = 0; i < size; i++) { ret |= ssi_transfer(s->spi, 0x0) << (8 * i); @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_write(void *opaque, hwaddr addr, uint64_t data, break; case CTRL_WRITEMODE: aspeed_smc_flash_select(fl); - aspeed_smc_flash_send_addr(fl, addr); + aspeed_smc_flash_setup(fl, addr); for (i = 0; i < size; i++) { ssi_transfer(s->spi, (data >> (8 * i)) & 0xff); -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> These COMs are hard to find, and the companie dropped the support few years ago. Per the "Gumstix Product Changes, Known Issues, and EOL" pdf: - Phasing out: PXA270-based Verdex product line September 2012 - Phasing out: PXA255-based Basix & Connex September 2009 However there are still booting SD card image availables, very convenient to stress test the QEMU SD card implementation. Therefore I volunteer to keep an eye on this file, while it is useful for testing. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180606144706.29732-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/arm/digic.h F: hw/*/digic* Gumstix +M: Philippe Mathieu-Daudé <f4bug@amsat.org> L: qemu-devel@nongnu.org L: qemu-arm@nongnu.org -S: Orphan +S: Odd Fixes F: hw/arm/gumstix.c i.MX31 -- 2.17.1 From: Sai Pavan Boddu <saipava@xilinx.com> Qspi dma has a burst length of 64 bytes, So limit the transactions w.r.t dma-burst-size property. Signed-off-by: Sai Pavan Boddu <saipava@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1529660880-30376-1-git-send-email-sai.pavan.boddu@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/ssi/xilinx_spips.h | 5 ++++- hw/ssi/xilinx_spips.c | 23 ++++++++++++++++++++--- 2 files changed, 24 insertions(+), 4 deletions(-) diff --git a/include/hw/ssi/xilinx_spips.h b/include/hw/ssi/xilinx_spips.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/ssi/xilinx_spips.h +++ b/include/hw/ssi/xilinx_spips.h @@ -XXX,XX +XXX,XX @@ typedef struct XilinxSPIPS XilinxSPIPS; /* Bite off 4k chunks at a time */ #define LQSPI_CACHE_SIZE 1024 +#define QSPI_DMA_MAX_BURST_SIZE 2048 + typedef enum { READ = 0x3, READ_4 = 0x13, FAST_READ = 0xb, FAST_READ_4 = 0x0c, @@ -XXX,XX +XXX,XX @@ typedef struct { XilinxQSPIPS parent_obj; StreamSlave *dma; - uint8_t dma_buf[4]; int gqspi_irqline; uint32_t regs[XLNX_ZYNQMP_SPIPS_R_MAX]; @@ -XXX,XX +XXX,XX @@ typedef struct { uint8_t rx_fifo_g_align; uint8_t tx_fifo_g_align; bool man_start_com_g; + uint32_t dma_burst_size; + uint8_t dma_buf[QSPI_DMA_MAX_BURST_SIZE]; } XlnxZynqMPQSPIPS; typedef struct XilinxSPIPSClass { diff --git a/hw/ssi/xilinx_spips.c b/hw/ssi/xilinx_spips.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/xilinx_spips.c +++ b/hw/ssi/xilinx_spips.c @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_qspips_notify(void *opaque) { size_t ret; uint32_t num; - const void *rxd = pop_buf(recv_fifo, 4, &num); + const void *rxd; + int len; + + len = recv_fifo->num >= rq->dma_burst_size ? rq->dma_burst_size : + recv_fifo->num; + rxd = pop_buf(recv_fifo, len, &num); memcpy(rq->dma_buf, rxd, num); - ret = stream_push(rq->dma, rq->dma_buf, 4); - assert(ret == 4); + ret = stream_push(rq->dma, rq->dma_buf, num); + assert(ret == num); xlnx_zynqmp_qspips_check_flush(rq); } } @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_qspips_realize(DeviceState *dev, Error **errp) XlnxZynqMPQSPIPS *s = XLNX_ZYNQMP_QSPIPS(dev); XilinxSPIPSClass *xsc = XILINX_SPIPS_GET_CLASS(s); + if (s->dma_burst_size > QSPI_DMA_MAX_BURST_SIZE) { + error_setg(errp, + "qspi dma burst size %u exceeds maximum limit %d", + s->dma_burst_size, QSPI_DMA_MAX_BURST_SIZE); + return; + } xilinx_qspips_realize(dev, errp); fifo8_create(&s->rx_fifo_g, xsc->rx_fifo_size); fifo8_create(&s->tx_fifo_g, xsc->tx_fifo_size); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_xlnx_zynqmp_qspips = { } }; +static Property xilinx_zynqmp_qspips_properties[] = { + DEFINE_PROP_UINT32("dma-burst-size", XlnxZynqMPQSPIPS, dma_burst_size, 64), + DEFINE_PROP_END_OF_LIST(), +}; + static Property xilinx_qspips_properties[] = { /* We had to turn this off for 2.10 as it is not compatible with migration. * It can be enabled but will prevent the device to be migrated. @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_qspips_class_init(ObjectClass *klass, void * data) dc->realize = xlnx_zynqmp_qspips_realize; dc->reset = xlnx_zynqmp_qspips_reset; dc->vmsd = &vmstate_xlnx_zynqmp_qspips; + dc->props = xilinx_zynqmp_qspips_properties; xsc->reg_ops = &xlnx_zynqmp_qspips_ops; xsc->rx_fifo_size = RXFF_A_Q; xsc->tx_fifo_size = TXFF_A_Q; -- 2.17.1 From: Joel Stanley <joel@jms.id.au> This adds Cedric as the maintainer, with Andrew and I as reviewers, for the ASPEED boards and the peripherals we have developed. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Acked-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Joel Stanley <joel@jms.id.au> Message-id: 20180625140055.32223-1-joel@jms.id.au Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Subbaraya Sundeep <sundeep.lkml@gmail.com> S: Maintained F: hw/arm/msf2-som.c +ASPEED BMCs +M: Cédric Le Goater <clg@kaod.org> +R: Andrew Jeffery <andrew@aj.id.au> +R: Joel Stanley <joel@jms.id.au> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/*/*aspeed* +F: include/hw/*/*aspeed* +F: hw/net/ftgmac100.c +F: include/hw/net/ftgmac100.h + CRIS Machines ------------- Axis Dev88 -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/input/pckbd.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/input/pckbd.c b/hw/input/pckbd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/pckbd.c +++ b/hw/input/pckbd.c @@ -XXX,XX +XXX,XX @@ * THE SOFTWARE. */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/hw.h" #include "hw/isa/isa.h" #include "hw/i386/pc.h" @@ -XXX,XX +XXX,XX @@ static void kbd_write_command(void *opaque, hwaddr addr, /* ignore that */ break; default: - fprintf(stderr, "qemu: unsupported keyboard cmd=0x%02x\n", (int)val); + qemu_log_mask(LOG_GUEST_ERROR, + "unsupported keyboard cmd=0x%02" PRIx64 "\n", val); break; } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/input/tsc2005.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/hw/input/tsc2005.c b/hw/input/tsc2005.c index XXXXXXX..XXXXXXX 100644 --- a/hw/input/tsc2005.c +++ b/hw/input/tsc2005.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/hw.h" #include "qemu/timer.h" #include "ui/console.h" @@ -XXX,XX +XXX,XX @@ static void tsc2005_write(TSC2005State *s, int reg, uint16_t data) } s->nextprecision = (data >> 13) & 1; s->timing[0] = data & 0x1fff; - if ((s->timing[0] >> 11) == 3) - fprintf(stderr, "%s: illegal conversion clock setting\n", - __func__); + if ((s->timing[0] >> 11) == 3) { + qemu_log_mask(LOG_GUEST_ERROR, + "tsc2005_write: illegal conversion clock setting\n"); + } break; case 0xd: /* CFR1 */ s->timing[1] = data & 0xf07; @@ -XXX,XX +XXX,XX @@ static void tsc2005_write(TSC2005State *s, int reg, uint16_t data) break; default: - fprintf(stderr, "%s: write into read-only register %x\n", - __func__, reg); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write into read-only register 0x%x\n", + __func__, reg); } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/omap_dma.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "qemu-common.h" #include "qemu/timer.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static int omap_dma_sys_read(struct omap_dma_s *s, int offset, case 0x480: /* DMA_PCh0_SR */ case 0x482: /* DMA_PCh1_SR */ case 0x4c0: /* DMA_PChD_SR_0 */ - printf("%s: Physical Channel Status Registers not implemented.\n", - __func__); + qemu_log_mask(LOG_UNIMP, + "%s: Physical Channel Status Registers not implemented\n", + __func__); *ret = 0xff; break; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-5-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/dma/omap_dma.c | 64 +++++++++++++++++++++++++++++------------------ 1 file changed, 40 insertions(+), 24 deletions(-) diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ static int omap_dma_ch_reg_write(struct omap_dma_s *s, ch->burst[0] = (value & 0x0180) >> 7; ch->pack[0] = (value & 0x0040) >> 6; ch->port[0] = (enum omap_dma_port) ((value & 0x003c) >> 2); - if (ch->port[0] >= __omap_dma_port_last) - printf("%s: invalid DMA port %i\n", __func__, - ch->port[0]); - if (ch->port[1] >= __omap_dma_port_last) - printf("%s: invalid DMA port %i\n", __func__, - ch->port[1]); + if (ch->port[0] >= __omap_dma_port_last) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid DMA port %i\n", + __func__, ch->port[0]); + } + if (ch->port[1] >= __omap_dma_port_last) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid DMA port %i\n", + __func__, ch->port[1]); + } ch->data_type = 1 << (value & 3); if ((value & 3) == 3) { - printf("%s: bad data_type for DMA channel\n", __func__); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad data_type for DMA channel\n", __func__); ch->data_type >>= 1; } break; @@ -XXX,XX +XXX,XX @@ static void omap_dma4_write(void *opaque, hwaddr addr, if (value & 2) /* SOFTRESET */ omap_dma_reset(s->dma); s->ocp = value & 0x3321; - if (((s->ocp >> 12) & 3) == 3) /* MIDLEMODE */ - fprintf(stderr, "%s: invalid DMA power mode\n", __func__); + if (((s->ocp >> 12) & 3) == 3) { /* MIDLEMODE */ + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid DMA power mode\n", + __func__); + } return; case 0x78: /* DMA4_GCR */ s->gcr = value & 0x00ff00ff; - if ((value & 0xff) == 0x00) /* MAX_CHANNEL_FIFO_DEPTH */ - fprintf(stderr, "%s: wrong FIFO depth in GCR\n", __func__); + if ((value & 0xff) == 0x00) { /* MAX_CHANNEL_FIFO_DEPTH */ + qemu_log_mask(LOG_GUEST_ERROR, "%s: wrong FIFO depth in GCR\n", + __func__); + } return; case 0x80 ... 0xfff: @@ -XXX,XX +XXX,XX @@ static void omap_dma4_write(void *opaque, hwaddr addr, case 0x00: /* DMA4_CCR */ ch->buf_disable = (value >> 25) & 1; ch->src_sync = (value >> 24) & 1; /* XXX For CamDMA must be 1 */ - if (ch->buf_disable && !ch->src_sync) - fprintf(stderr, "%s: Buffering disable is not allowed in " - "destination synchronised mode\n", __func__); + if (ch->buf_disable && !ch->src_sync) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Buffering disable is not allowed in " + "destination synchronised mode\n", __func__); + } ch->prefetch = (value >> 23) & 1; ch->bs = (value >> 18) & 1; ch->transparent_copy = (value >> 17) & 1; @@ -XXX,XX +XXX,XX @@ static void omap_dma4_write(void *opaque, hwaddr addr, ch->suspend = (value & 0x0100) >> 8; ch->priority = (value & 0x0040) >> 6; ch->fs = (value & 0x0020) >> 5; - if (ch->fs && ch->bs && ch->mode[0] && ch->mode[1]) - fprintf(stderr, "%s: For a packet transfer at least one port " - "must be constant-addressed\n", __func__); + if (ch->fs && ch->bs && ch->mode[0] && ch->mode[1]) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: For a packet transfer at least one port " + "must be constant-addressed\n", __func__); + } ch->sync = (value & 0x001f) | ((value >> 14) & 0x0060); /* XXX must be 0x01 for CamDMA */ @@ -XXX,XX +XXX,XX @@ static void omap_dma4_write(void *opaque, hwaddr addr, ch->endian_lock[0] =(value >> 20) & 1; ch->endian[1] =(value >> 19) & 1; ch->endian_lock[1] =(value >> 18) & 1; - if (ch->endian[0] != ch->endian[1]) - fprintf(stderr, "%s: DMA endianness conversion enable attempt\n", - __func__); + if (ch->endian[0] != ch->endian[1]) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: DMA endianness conversion enable attempt\n", + __func__); + } ch->write_mode = (value >> 16) & 3; ch->burst[1] = (value & 0xc000) >> 14; ch->pack[1] = (value & 0x2000) >> 13; @@ -XXX,XX +XXX,XX @@ static void omap_dma4_write(void *opaque, hwaddr addr, ch->burst[0] = (value & 0x0180) >> 7; ch->pack[0] = (value & 0x0040) >> 6; ch->translate[0] = (value & 0x003c) >> 2; - if (ch->translate[0] | ch->translate[1]) - fprintf(stderr, "%s: bad MReqAddressTranslate sideband signal\n", - __func__); + if (ch->translate[0] | ch->translate[1]) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad MReqAddressTranslate sideband signal\n", + __func__); + } ch->data_type = 1 << (value & 3); if ((value & 3) == 3) { - printf("%s: bad data_type for DMA channel\n", __func__); + qemu_log_mask(LOG_GUEST_ERROR, + "%s: bad data_type for DMA channel\n", __func__); ch->data_type >>= 1; } break; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20180624040609.17572-6-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/omap_spi.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/hw/ssi/omap_spi.c b/hw/ssi/omap_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/omap_spi.c +++ b/hw/ssi/omap_spi.c @@ -XXX,XX +XXX,XX @@ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/hw.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static void omap_mcspi_write(void *opaque, hwaddr addr, case 0x2c: /* MCSPI_CHCONF */ if ((value ^ s->ch[ch].config) & (3 << 14)) /* DMAR | DMAW */ omap_mcspi_dmarequest_update(s->ch + ch); - if (((value >> 12) & 3) == 3) /* TRM */ - fprintf(stderr, "%s: invalid TRM value (3)\n", __func__); - if (((value >> 7) & 0x1f) < 3) /* WL */ - fprintf(stderr, "%s: invalid WL value (%" PRIx64 ")\n", - __func__, (value >> 7) & 0x1f); + if (((value >> 12) & 3) == 3) { /* TRM */ + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid TRM value (3)\n", + __func__); + } + if (((value >> 7) & 0x1f) < 3) { /* WL */ + qemu_log_mask(LOG_GUEST_ERROR, + "%s: invalid WL value (%" PRIx64 ")\n", + __func__, (value >> 7) & 0x1f); + } s->ch[ch].config = value & 0x7fffff; break; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-7-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/omap_mmc.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) 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 @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/hw.h" #include "hw/arm/omap.h" #include "hw/sd/sd.h" @@ -XXX,XX +XXX,XX @@ static void omap_mmc_write(void *opaque, hwaddr offset, s->enable = (value >> 11) & 1; s->be = (value >> 10) & 1; s->clkdiv = (value >> 0) & (s->rev >= 2 ? 0x3ff : 0xff); - if (s->mode != 0) - printf("SD mode %i unimplemented!\n", s->mode); - if (s->be != 0) - printf("SD FIFO byte sex unimplemented!\n"); + if (s->mode != 0) { + qemu_log_mask(LOG_UNIMP, + "omap_mmc_wr: mode #%i unimplemented\n", s->mode); + } + if (s->be != 0) { + qemu_log_mask(LOG_UNIMP, + "omap_mmc_wr: Big Endian not implemented\n"); + } if (s->dw != 0 && s->lines < 4) printf("4-bit SD bus enabled\n"); if (!s->enable) -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-8-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/omap_i2c.c | 20 ++++++++++++-------- 1 file changed, 12 insertions(+), 8 deletions(-) diff --git a/hw/i2c/omap_i2c.c b/hw/i2c/omap_i2c.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/omap_i2c.c +++ b/hw/i2c/omap_i2c.c @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "hw/hw.h" #include "hw/i2c/i2c.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static void omap_i2c_write(void *opaque, hwaddr addr, } break; } - if ((value & (1 << 15)) && !(value & (1 << 10))) { /* MST */ - fprintf(stderr, "%s: I^2C slave mode not supported\n", - __func__); + if ((value & (1 << 15)) && !(value & (1 << 10))) { /* MST */ + qemu_log_mask(LOG_UNIMP, "%s: I^2C slave mode not supported\n", + __func__); break; } - if ((value & (1 << 15)) && value & (1 << 8)) { /* XA */ - fprintf(stderr, "%s: 10-bit addressing mode not supported\n", - __func__); + if ((value & (1 << 15)) && value & (1 << 8)) { /* XA */ + qemu_log_mask(LOG_UNIMP, + "%s: 10-bit addressing mode not supported\n", + __func__); break; } if ((value & (1 << 15)) && value & (1 << 0)) { /* STT */ @@ -XXX,XX +XXX,XX @@ static void omap_i2c_write(void *opaque, hwaddr addr, s->stat |= 0x3f; omap_i2c_interrupts_update(s); } - if (value & (1 << 15)) /* ST_EN */ - fprintf(stderr, "%s: System Test not supported\n", __func__); + if (value & (1 << 15)) { /* ST_EN */ + qemu_log_mask(LOG_UNIMP, + "%s: System Test not supported\n", __func__); + } break; default: -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> TCMI_VERBOSE is no more used, drop the OMAP_8/16/32B_REG macros. Suggested-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-9-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 18 ------------------ hw/arm/omap1.c | 18 ++++++++++++------ 2 files changed, 12 insertions(+), 24 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ enum { #define OMAP_GPIOSW_INVERTED 0x0001 #define OMAP_GPIOSW_OUTPUT 0x0002 -# define TCMI_VERBOSE 1 - -# ifdef TCMI_VERBOSE -# define OMAP_8B_REG(paddr) \ - fprintf(stderr, "%s: 8-bit register " OMAP_FMT_plx "\n", \ - __func__, paddr) -# define OMAP_16B_REG(paddr) \ - fprintf(stderr, "%s: 16-bit register " OMAP_FMT_plx "\n", \ - __func__, paddr) -# define OMAP_32B_REG(paddr) \ - fprintf(stderr, "%s: 32-bit register " OMAP_FMT_plx "\n", \ - __func__, paddr) -# else -# define OMAP_8B_REG(paddr) -# define OMAP_16B_REG(paddr) -# define OMAP_32B_REG(paddr) -# endif - # define OMAP_MPUI_REG_MASK 0x000007ff #endif /* hw_omap_h */ diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap1.c +++ b/hw/arm/omap1.c @@ -XXX,XX +XXX,XX @@ #include "qemu/cutils.h" #include "qemu/bcd.h" +static inline void omap_log_badwidth(const char *funcname, hwaddr addr, int sz) +{ + qemu_log_mask(LOG_GUEST_ERROR, "%s: %d-bit register %#08" HWADDR_PRIx "\n", + funcname, 8 * sz, addr); +} + /* Should signal the TCMI/GPMC */ uint32_t omap_badwidth_read8(void *opaque, hwaddr addr) { uint8_t ret; - OMAP_8B_REG(addr); + omap_log_badwidth(__func__, addr, 1); cpu_physical_memory_read(addr, &ret, 1); return ret; } @@ -XXX,XX +XXX,XX @@ void omap_badwidth_write8(void *opaque, hwaddr addr, { uint8_t val8 = value; - OMAP_8B_REG(addr); + omap_log_badwidth(__func__, addr, 1); cpu_physical_memory_write(addr, &val8, 1); } @@ -XXX,XX +XXX,XX @@ uint32_t omap_badwidth_read16(void *opaque, hwaddr addr) { uint16_t ret; - OMAP_16B_REG(addr); + omap_log_badwidth(__func__, addr, 2); cpu_physical_memory_read(addr, &ret, 2); return ret; } @@ -XXX,XX +XXX,XX @@ void omap_badwidth_write16(void *opaque, hwaddr addr, { uint16_t val16 = value; - OMAP_16B_REG(addr); + omap_log_badwidth(__func__, addr, 2); cpu_physical_memory_write(addr, &val16, 2); } @@ -XXX,XX +XXX,XX @@ uint32_t omap_badwidth_read32(void *opaque, hwaddr addr) { uint32_t ret; - OMAP_32B_REG(addr); + omap_log_badwidth(__func__, addr, 4); cpu_physical_memory_read(addr, &ret, 4); return ret; } @@ -XXX,XX +XXX,XX @@ uint32_t omap_badwidth_read32(void *opaque, hwaddr addr) void omap_badwidth_write32(void *opaque, hwaddr addr, uint32_t value) { - OMAP_32B_REG(addr); + omap_log_badwidth(__func__, addr, 4); cpu_physical_memory_write(addr, &value, 4); } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-10-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ # define hw_omap_h "omap.h" #include "hw/irq.h" #include "target/arm/cpu-qom.h" +#include "qemu/log.h" # define OMAP_EMIFS_BASE 0x00000000 # define OMAP2_Q0_BASE 0x00000000 @@ -XXX,XX +XXX,XX @@ struct omap_mpu_state_s *omap2420_mpu_init(MemoryRegion *sysmem, unsigned long sdram_size, const char *core); -#define OMAP_FMT_plx "%#08" HWADDR_PRIx - uint32_t omap_badwidth_read8(void *opaque, hwaddr addr); void omap_badwidth_write8(void *opaque, hwaddr addr, uint32_t value); @@ -XXX,XX +XXX,XX @@ void omap_badwidth_write32(void *opaque, hwaddr addr, void omap_mpu_wakeup(void *opaque, int irq, int req); # define OMAP_BAD_REG(paddr) \ - fprintf(stderr, "%s: Bad register " OMAP_FMT_plx "\n", \ - __func__, paddr) + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad register %#08"HWADDR_PRIx"\n", \ + __func__, paddr) # define OMAP_RO_REG(paddr) \ - fprintf(stderr, "%s: Read-only register " OMAP_FMT_plx "\n", \ - __func__, paddr) + qemu_log_mask(LOG_GUEST_ERROR, "%s: Read-only register %#08" \ + HWADDR_PRIx "\n", \ + __func__, paddr) /* OMAP-specific Linux bootloader tags for the ATAG_BOARD area (Board-specifc tags are not here) */ -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-11-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void ssys_write(void *opaque, hwaddr offset, case 0x040: /* SRCR0 */ case 0x044: /* SRCR1 */ case 0x048: /* SRCR2 */ - fprintf(stderr, "Peripheral reset not implemented\n"); + qemu_log_mask(LOG_UNIMP, "Peripheral reset not implemented\n"); break; case 0x054: /* IMC */ s->int_mask = value & 0x7f; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Suggested-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180624040609.17572-12-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/stellaris_enet.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/stellaris_enet.c b/hw/net/stellaris_enet.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/stellaris_enet.c +++ b/hw/net/stellaris_enet.c @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_enet_read(void *opaque, hwaddr offset, return s->np; case 0x38: /* TR */ return 0; - case 0x3c: /* Undocuented: Timestamp? */ + case 0x3c: /* Undocumented: Timestamp? */ return 0; default: hw_error("stellaris_enet_read: Bad offset %x\n", (int)offset); -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> hw_error() finally calls abort(), but there is no need to abort here. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180624040609.17572-13-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/stellaris_enet.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/hw/net/stellaris_enet.c b/hw/net/stellaris_enet.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/stellaris_enet.c +++ b/hw/net/stellaris_enet.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "hw/sysbus.h" #include "net/net.h" +#include "qemu/log.h" #include <zlib.h> //#define DEBUG_STELLARIS_ENET 1 @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_enet_read(void *opaque, hwaddr offset, case 0x3c: /* Undocumented: Timestamp? */ return 0; default: - hw_error("stellaris_enet_read: Bad offset %x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "stellaris_enet_rd%d: Illegal register" + " 0x02%" HWADDR_PRIx "\n", + size * 8, offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void stellaris_enet_write(void *opaque, hwaddr offset, /* Ignored. */ break; default: - hw_error("stellaris_enet_write: Bad offset %x\n", (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "stellaris_enet_wr%d: Illegal register " + "0x02%" HWADDR_PRIx " = 0x%" PRIx64 "\n", + size * 8, offset, value); } } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> hw_error() finally calls abort(), but there is no need to abort here. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-14-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/smc91c111.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/smc91c111.c +++ b/hw/net/smc91c111.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "net/net.h" #include "hw/devices.h" +#include "qemu/log.h" /* For crc32 */ #include <zlib.h> @@ -XXX,XX +XXX,XX @@ static void smc91c111_writeb(void *opaque, hwaddr offset, } break; } - hw_error("smc91c111_write: Bad reg %d:%x\n", s->bank, (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "smc91c111_write(bank:%d) Illegal register" + " 0x%" HWADDR_PRIx " = 0x%x\n", + s->bank, offset, value); } static uint32_t smc91c111_readb(void *opaque, hwaddr offset) @@ -XXX,XX +XXX,XX @@ static uint32_t smc91c111_readb(void *opaque, hwaddr offset) } break; } - hw_error("smc91c111_read: Bad reg %d:%x\n", s->bank, (int)offset); + qemu_log_mask(LOG_GUEST_ERROR, "smc91c111_read(bank:%d) Illegal register" + " 0x%" HWADDR_PRIx "\n", + s->bank, offset); return 0; } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20180624040609.17572-15-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/smc91c111.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/hw/net/smc91c111.c b/hw/net/smc91c111.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/smc91c111.c +++ b/hw/net/smc91c111.c @@ -XXX,XX +XXX,XX @@ static void smc91c111_writeb(void *opaque, hwaddr offset, SET_HIGH(gpr, value); return; case 12: /* Control */ - if (value & 1) - fprintf(stderr, "smc91c111:EEPROM store not implemented\n"); - if (value & 2) - fprintf(stderr, "smc91c111:EEPROM reload not implemented\n"); + if (value & 1) { + qemu_log_mask(LOG_UNIMP, + "smc91c111: EEPROM store not implemented\n"); + } + if (value & 2) { + qemu_log_mask(LOG_UNIMP, + "smc91c111: EEPROM reload not implemented\n"); + } value &= ~3; SET_LOW(ctr, value); return; -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Missed in df3692e04b2. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180624040609.17572-16-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void gptm_write(void *opaque, hwaddr offset, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: read at bad offset 0x%x\n", (int)offset); + "GPTM: write at bad offset 0x%x\n", (int)offset); } gptm_update_irq(s); } -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Suggested-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180624040609.17572-17-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static uint64_t gptm_read(void *opaque, hwaddr offset, return 0; default: qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: read at bad offset 0x%x\n", (int)offset); + "GPTM: read at bad offset 0x02%" HWADDR_PRIx "\n", + offset); return 0; } } @@ -XXX,XX +XXX,XX @@ static void gptm_write(void *opaque, hwaddr offset, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: write at bad offset 0x%x\n", (int)offset); + "GPTM: write at bad offset 0x02%" HWADDR_PRIx "\n", + offset); } gptm_update_irq(s); } -- 2.17.1 Add support for MMU protection regions that are smaller than TARGET_PAGE_SIZE. We do this by marking the TLB entry for those pages with a flag TLB_RECHECK. This flag causes us to always take the slow-path for accesses. In the slow path we can then special case them to always call tlb_fill() again, so we have the correct information for the exact address being accessed. This change allows us to handle reading and writing from small regions; we cannot deal with execution from the small region. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180620130619.11362-2-peter.maydell@linaro.org --- accel/tcg/softmmu_template.h | 24 ++++--- include/exec/cpu-all.h | 5 +- accel/tcg/cputlb.c | 131 +++++++++++++++++++++++++++++------ 3 files changed, 130 insertions(+), 30 deletions(-) diff --git a/accel/tcg/softmmu_template.h b/accel/tcg/softmmu_template.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/softmmu_template.h +++ b/accel/tcg/softmmu_template.h @@ -XXX,XX +XXX,XX @@ static inline DATA_TYPE glue(io_read, SUFFIX)(CPUArchState *env, size_t mmu_idx, size_t index, target_ulong addr, - uintptr_t retaddr) + uintptr_t retaddr, + bool recheck) { CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index]; - return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, DATA_SIZE); + return io_readx(env, iotlbentry, mmu_idx, addr, retaddr, recheck, + DATA_SIZE); } #endif @@ -XXX,XX +XXX,XX @@ WORD_TYPE helper_le_ld_name(CPUArchState *env, target_ulong addr, /* ??? Note that the io helpers always read data in the target byte ordering. We should push the LE/BE request down into io. */ - res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr); + res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr, + tlb_addr & TLB_RECHECK); res = TGT_LE(res); return res; } @@ -XXX,XX +XXX,XX @@ WORD_TYPE helper_be_ld_name(CPUArchState *env, target_ulong addr, /* ??? Note that the io helpers always read data in the target byte ordering. We should push the LE/BE request down into io. */ - res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr); + res = glue(io_read, SUFFIX)(env, mmu_idx, index, addr, retaddr, + tlb_addr & TLB_RECHECK); res = TGT_BE(res); return res; } @@ -XXX,XX +XXX,XX @@ static inline void glue(io_write, SUFFIX)(CPUArchState *env, size_t mmu_idx, size_t index, DATA_TYPE val, target_ulong addr, - uintptr_t retaddr) + uintptr_t retaddr, + bool recheck) { CPUIOTLBEntry *iotlbentry = &env->iotlb[mmu_idx][index]; - return io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr, DATA_SIZE); + return io_writex(env, iotlbentry, mmu_idx, val, addr, retaddr, + recheck, DATA_SIZE); } void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val, @@ -XXX,XX +XXX,XX @@ void helper_le_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val, /* ??? Note that the io helpers always read data in the target byte ordering. We should push the LE/BE request down into io. */ val = TGT_LE(val); - glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr); + glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, + retaddr, tlb_addr & TLB_RECHECK); return; } @@ -XXX,XX +XXX,XX @@ void helper_be_st_name(CPUArchState *env, target_ulong addr, DATA_TYPE val, /* ??? Note that the io helpers always read data in the target byte ordering. We should push the LE/BE request down into io. */ val = TGT_BE(val); - glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr); + glue(io_write, SUFFIX)(env, mmu_idx, index, val, addr, retaddr, + tlb_addr & TLB_RECHECK); return; } diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ CPUArchState *cpu_copy(CPUArchState *env); #define TLB_NOTDIRTY (1 << (TARGET_PAGE_BITS - 2)) /* Set if TLB entry is an IO callback. */ #define TLB_MMIO (1 << (TARGET_PAGE_BITS - 3)) +/* Set if TLB entry must have MMU lookup repeated for every access */ +#define TLB_RECHECK (1 << (TARGET_PAGE_BITS - 4)) /* Use this mask to check interception with an alignment mask * in a TCG backend. */ -#define TLB_FLAGS_MASK (TLB_INVALID_MASK | TLB_NOTDIRTY | TLB_MMIO) +#define TLB_FLAGS_MASK (TLB_INVALID_MASK | TLB_NOTDIRTY | TLB_MMIO \ + | TLB_RECHECK) void dump_exec_info(FILE *f, fprintf_function cpu_fprintf); void dump_opcount_info(FILE *f, fprintf_function cpu_fprintf); diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, target_ulong code_address; uintptr_t addend; CPUTLBEntry *te, *tv, tn; - hwaddr iotlb, xlat, sz; + hwaddr iotlb, xlat, sz, paddr_page; + target_ulong vaddr_page; unsigned vidx = env->vtlb_index++ % CPU_VTLB_SIZE; int asidx = cpu_asidx_from_attrs(cpu, attrs); assert_cpu_is_self(cpu); - assert(size >= TARGET_PAGE_SIZE); - if (size != TARGET_PAGE_SIZE) { - tlb_add_large_page(env, vaddr, size); - } - sz = size; - section = address_space_translate_for_iotlb(cpu, asidx, paddr, &xlat, &sz, - attrs, &prot); + if (size < TARGET_PAGE_SIZE) { + sz = TARGET_PAGE_SIZE; + } else { + if (size > TARGET_PAGE_SIZE) { + tlb_add_large_page(env, vaddr, size); + } + sz = size; + } + vaddr_page = vaddr & TARGET_PAGE_MASK; + paddr_page = paddr & TARGET_PAGE_MASK; + + section = address_space_translate_for_iotlb(cpu, asidx, paddr_page, + &xlat, &sz, attrs, &prot); assert(sz >= TARGET_PAGE_SIZE); tlb_debug("vaddr=" TARGET_FMT_lx " paddr=0x" TARGET_FMT_plx " prot=%x idx=%d\n", vaddr, paddr, prot, mmu_idx); - address = vaddr; - if (!memory_region_is_ram(section->mr) && !memory_region_is_romd(section->mr)) { + address = vaddr_page; + if (size < TARGET_PAGE_SIZE) { + /* + * Slow-path the TLB entries; we will repeat the MMU check and TLB + * fill on every access. + */ + address |= TLB_RECHECK; + } + if (!memory_region_is_ram(section->mr) && + !memory_region_is_romd(section->mr)) { /* IO memory case */ address |= TLB_MMIO; addend = 0; @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, } code_address = address; - iotlb = memory_region_section_get_iotlb(cpu, section, vaddr, paddr, xlat, - prot, &address); + iotlb = memory_region_section_get_iotlb(cpu, section, vaddr_page, + paddr_page, xlat, prot, &address); - index = (vaddr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); + index = (vaddr_page >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); te = &env->tlb_table[mmu_idx][index]; /* do not discard the translation in te, evict it into a victim tlb */ tv = &env->tlb_v_table[mmu_idx][vidx]; @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, * TARGET_PAGE_BITS, and either * + the ram_addr_t of the page base of the target RAM (if NOTDIRTY or ROM) * + the offset within section->mr of the page base (otherwise) - * We subtract the vaddr (which is page aligned and thus won't + * We subtract the vaddr_page (which is page aligned and thus won't * disturb the low bits) to give an offset which can be added to the * (non-page-aligned) vaddr of the eventual memory access to get * the MemoryRegion offset for the access. Note that the vaddr we * subtract here is that of the page base, and not the same as the * vaddr we add back in io_readx()/io_writex()/get_page_addr_code(). */ - env->iotlb[mmu_idx][index].addr = iotlb - vaddr; + env->iotlb[mmu_idx][index].addr = iotlb - vaddr_page; env->iotlb[mmu_idx][index].attrs = attrs; /* Now calculate the new entry */ - tn.addend = addend - vaddr; + tn.addend = addend - vaddr_page; if (prot & PAGE_READ) { tn.addr_read = address; } else { @@ -XXX,XX +XXX,XX @@ void tlb_set_page_with_attrs(CPUState *cpu, target_ulong vaddr, tn.addr_write = address | TLB_MMIO; } else if (memory_region_is_ram(section->mr) && cpu_physical_memory_is_clean( - memory_region_get_ram_addr(section->mr) + xlat)) { + memory_region_get_ram_addr(section->mr) + xlat)) { tn.addr_write = address | TLB_NOTDIRTY; } else { tn.addr_write = address; @@ -XXX,XX +XXX,XX @@ static inline ram_addr_t qemu_ram_addr_from_host_nofail(void *ptr) static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, int mmu_idx, - target_ulong addr, uintptr_t retaddr, int size) + target_ulong addr, uintptr_t retaddr, + bool recheck, int size) { CPUState *cpu = ENV_GET_CPU(env); hwaddr mr_offset; @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; + if (recheck) { + /* + * This is a TLB_RECHECK access, where the MMU protection + * covers a smaller range than a target page, and we must + * repeat the MMU check here. This tlb_fill() call might + * longjump out if this access should cause a guest exception. + */ + int index; + target_ulong tlb_addr; + + tlb_fill(cpu, addr, size, MMU_DATA_LOAD, mmu_idx, retaddr); + + index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); + tlb_addr = env->tlb_table[mmu_idx][index].addr_read; + if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) { + /* RAM access */ + uintptr_t haddr = addr + env->tlb_table[mmu_idx][index].addend; + + return ldn_p((void *)haddr, size); + } + /* Fall through for handling IO accesses */ + } + section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); mr = section->mr; mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; @@ -XXX,XX +XXX,XX @@ static uint64_t io_readx(CPUArchState *env, CPUIOTLBEntry *iotlbentry, static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, int mmu_idx, uint64_t val, target_ulong addr, - uintptr_t retaddr, int size) + uintptr_t retaddr, bool recheck, int size) { CPUState *cpu = ENV_GET_CPU(env); hwaddr mr_offset; @@ -XXX,XX +XXX,XX @@ static void io_writex(CPUArchState *env, CPUIOTLBEntry *iotlbentry, bool locked = false; MemTxResult r; + if (recheck) { + /* + * This is a TLB_RECHECK access, where the MMU protection + * covers a smaller range than a target page, and we must + * repeat the MMU check here. This tlb_fill() call might + * longjump out if this access should cause a guest exception. + */ + int index; + target_ulong tlb_addr; + + tlb_fill(cpu, addr, size, MMU_DATA_STORE, mmu_idx, retaddr); + + index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); + tlb_addr = env->tlb_table[mmu_idx][index].addr_write; + if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) { + /* RAM access */ + uintptr_t haddr = addr + env->tlb_table[mmu_idx][index].addend; + + stn_p((void *)haddr, size, val); + return; + } + /* Fall through for handling IO accesses */ + } + section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); mr = section->mr; mr_offset = (iotlbentry->addr & TARGET_PAGE_MASK) + addr; @@ -XXX,XX +XXX,XX @@ tb_page_addr_t get_page_addr_code(CPUArchState *env, target_ulong addr) tlb_fill(ENV_GET_CPU(env), addr, 0, MMU_INST_FETCH, mmu_idx, 0); } } + + if (unlikely(env->tlb_table[mmu_idx][index].addr_code & TLB_RECHECK)) { + /* + * This is a TLB_RECHECK access, where the MMU protection + * covers a smaller range than a target page, and we must + * repeat the MMU check here. This tlb_fill() call might + * longjump out if this access should cause a guest exception. + */ + int index; + target_ulong tlb_addr; + + tlb_fill(cpu, addr, 0, MMU_INST_FETCH, mmu_idx, 0); + + index = (addr >> TARGET_PAGE_BITS) & (CPU_TLB_SIZE - 1); + tlb_addr = env->tlb_table[mmu_idx][index].addr_code; + if (!(tlb_addr & ~(TARGET_PAGE_MASK | TLB_RECHECK))) { + /* RAM access. We can't handle this, so for now just stop */ + cpu_abort(cpu, "Unable to handle guest executing from RAM within " + "a small MPU region at 0x" TARGET_FMT_lx, addr); + } + /* + * Fall through to handle IO accesses (which will almost certainly + * also result in failure) + */ + } + iotlbentry = &env->iotlb[mmu_idx][index]; section = iotlb_to_section(cpu, iotlbentry->addr, iotlbentry->attrs); mr = section->mr; @@ -XXX,XX +XXX,XX @@ static void *atomic_mmu_lookup(CPUArchState *env, target_ulong addr, tlb_addr = tlbe->addr_write & ~TLB_INVALID_MASK; } - /* Notice an IO access */ - if (unlikely(tlb_addr & TLB_MMIO)) { + /* Notice an IO access or a needs-MMU-lookup access */ + if (unlikely(tlb_addr & (TLB_MMIO | TLB_RECHECK))) { /* There's really nothing that can be done to support this apart from stop-the-world. */ goto stop_the_world; -- 2.17.1 We want to handle small MPU region sizes for ARMv7M. To do this, make get_phys_addr_pmsav7() set the page size to the region size if it is less that TARGET_PAGE_SIZE, rather than working only in TARGET_PAGE_SIZE chunks. Since the core TCG code con't handle execution from small MPU regions, we strip the exec permission from them so that any execution attempts will cause an MPU exception, rather than allowing it to end up with a cpu_abort() in get_page_addr_code(). (The previous code's intention was to make any small page be treated as having no permissions, but unfortunately errors in the implementation meant that it didn't behave that way. It's possible that some binaries using small regions were accidentally working with our old behaviour and won't now.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180620130619.11362-3-peter.maydell@linaro.org --- target/arm/helper.c | 37 ++++++++++++++++++++++++++----------- 1 file changed, 26 insertions(+), 11 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline bool m_is_system_region(CPUARMState *env, uint32_t address) static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, int *prot, + target_ulong *page_size, ARMMMUFaultInfo *fi) { ARMCPU *cpu = arm_env_get_cpu(env); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, bool is_user = regime_is_user(env, mmu_idx); *phys_ptr = address; + *page_size = TARGET_PAGE_SIZE; *prot = 0; if (regime_translation_disabled(env, mmu_idx) || @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, rsize++; } } - if (rsize < TARGET_PAGE_BITS) { - qemu_log_mask(LOG_UNIMP, - "DRSR[%d]: No support for MPU (sub)region size of" - " %" PRIu32 " bytes. Minimum is %d.\n", - n, (1 << rsize), TARGET_PAGE_SIZE); - continue; - } if (srdis) { continue; } + if (rsize < TARGET_PAGE_BITS) { + *page_size = 1 << rsize; + } break; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav7(CPUARMState *env, uint32_t address, fi->type = ARMFault_Permission; fi->level = 1; + /* + * Core QEMU code can't handle execution from small pages yet, so + * don't try it. This way we'll get an MPU exception, rather than + * eventually causing QEMU to exit in get_page_addr_code(). + */ + if (*page_size < TARGET_PAGE_SIZE && (*prot & PAGE_EXEC)) { + qemu_log_mask(LOG_UNIMP, + "MPU: No support for execution from regions " + "smaller than 1K\n"); + *prot &= ~PAGE_EXEC; + } return !(*prot & (1 << access_type)); } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, } else if (arm_feature(env, ARM_FEATURE_V7)) { /* PMSAv7 */ ret = get_phys_addr_pmsav7(env, address, access_type, mmu_idx, - phys_ptr, prot, fi); + phys_ptr, prot, page_size, fi); } else { /* Pre-v7 MPU */ ret = get_phys_addr_pmsav5(env, address, access_type, mmu_idx, @@ -XXX,XX +XXX,XX @@ bool arm_tlb_fill(CPUState *cs, vaddr address, core_to_arm_mmu_idx(env, mmu_idx), &phys_addr, &attrs, &prot, &page_size, fi, NULL); if (!ret) { - /* Map a single [sub]page. */ - phys_addr &= TARGET_PAGE_MASK; - address &= TARGET_PAGE_MASK; + /* + * Map a single [sub]page. Regions smaller than our declared + * target page size are handled specially, so for those we + * pass in the exact addresses. + */ + if (page_size >= TARGET_PAGE_SIZE) { + phys_addr &= TARGET_PAGE_MASK; + address &= TARGET_PAGE_MASK; + } tlb_set_page_with_attrs(cs, address, phys_addr, attrs, prot, mmu_idx, page_size); return 0; -- 2.17.1 Allow ARMv8M to handle small MPU and SAU region sizes, by making get_phys_add_pmsav8() set the page size to the 1 if the MPU or SAU region covers less than a TARGET_PAGE_SIZE. We choose to use a size of 1 because it makes no difference to the core code, and avoids having to track both the base and limit for SAU and MPU and then convert into an artificially restricted "page size" that the core code will then ignore. Since the core TCG code can't handle execution from small MPU regions, we strip the exec permission from them so that any execution attempts will cause an MPU exception, rather than allowing it to end up with a cpu_abort() in get_page_addr_code(). (The previous code's intention was to make any small page be treated as having no permissions, but unfortunately errors in the implementation meant that it didn't behave that way. It's possible that some binaries using small regions were accidentally working with our old behaviour and won't now.) We also retain an existing bug, where we ignored the possibility that the SAU region might not cover the entire page, in the case of executable regions. This is necessary because some currently-working guest code images rely on being able to execute from addresses which are covered by a page-sized MPU region but a smaller SAU region. We can remove this workaround if we ever support execution from small regions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180620130619.11362-4-peter.maydell@linaro.org --- target/arm/helper.c | 78 ++++++++++++++++++++++++++++++++------------- 1 file changed, 55 insertions(+), 23 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, /* Security attributes for an address, as returned by v8m_security_lookup. */ typedef struct V8M_SAttributes { + bool subpage; /* true if these attrs don't cover the whole TARGET_PAGE */ bool ns; bool nsc; uint8_t sregion; @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, int r; bool idau_exempt = false, idau_ns = true, idau_nsc = true; int idau_region = IREGION_NOTVALID; + uint32_t addr_page_base = address & TARGET_PAGE_MASK; + uint32_t addr_page_limit = addr_page_base + (TARGET_PAGE_SIZE - 1); if (cpu->idau) { IDAUInterfaceClass *iic = IDAU_INTERFACE_GET_CLASS(cpu->idau); @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, uint32_t limit = env->sau.rlar[r] | 0x1f; if (base <= address && limit >= address) { + if (base > addr_page_base || limit < addr_page_limit) { + sattrs->subpage = true; + } if (sattrs->srvalid) { /* If we hit in more than one region then we must report * as Secure, not NS-Callable, with no valid region @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, MemTxAttrs *txattrs, - int *prot, ARMMMUFaultInfo *fi, uint32_t *mregion) + int *prot, bool *is_subpage, + ARMMMUFaultInfo *fi, uint32_t *mregion) { /* Perform a PMSAv8 MPU lookup (without also doing the SAU check * that a full phys-to-virt translation does). * mregion is (if not NULL) set to the region number which matched, * or -1 if no region number is returned (MPU off, address did not * hit a region, address hit in multiple regions). + * We set is_subpage to true if the region hit doesn't cover the + * entire TARGET_PAGE the address is within. */ ARMCPU *cpu = arm_env_get_cpu(env); bool is_user = regime_is_user(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, int n; int matchregion = -1; bool hit = false; + uint32_t addr_page_base = address & TARGET_PAGE_MASK; + uint32_t addr_page_limit = addr_page_base + (TARGET_PAGE_SIZE - 1); + *is_subpage = false; *phys_ptr = address; *prot = 0; if (mregion) { @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, continue; } + if (base > addr_page_base || limit < addr_page_limit) { + *is_subpage = true; + } + if (hit) { /* Multiple regions match -- always a failure (unlike * PMSAv7 where highest-numbered-region wins) @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, matchregion = n; hit = true; - - if (base & ~TARGET_PAGE_MASK) { - qemu_log_mask(LOG_UNIMP, - "MPU_RBAR[%d]: No support for MPU region base" - "address of 0x%" PRIx32 ". Minimum alignment is " - "%d\n", - n, base, TARGET_PAGE_BITS); - continue; - } - if ((limit + 1) & ~TARGET_PAGE_MASK) { - qemu_log_mask(LOG_UNIMP, - "MPU_RBAR[%d]: No support for MPU region limit" - "address of 0x%" PRIx32 ". Minimum alignment is " - "%d\n", - n, limit, TARGET_PAGE_BITS); - continue; - } } } @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, fi->type = ARMFault_Permission; fi->level = 1; + /* + * Core QEMU code can't handle execution from small pages yet, so + * don't try it. This means any attempted execution will generate + * an MPU exception, rather than eventually causing QEMU to exit in + * get_page_addr_code(). + */ + if (*is_subpage && (*prot & PAGE_EXEC)) { + qemu_log_mask(LOG_UNIMP, + "MPU: No support for execution from regions " + "smaller than 1K\n"); + *prot &= ~PAGE_EXEC; + } return !(*prot & (1 << access_type)); } @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, MemTxAttrs *txattrs, - int *prot, ARMMMUFaultInfo *fi) + int *prot, target_ulong *page_size, + ARMMMUFaultInfo *fi) { uint32_t secure = regime_is_secure(env, mmu_idx); V8M_SAttributes sattrs = {}; + bool ret; + bool mpu_is_subpage; if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { v8m_security_lookup(env, address, access_type, mmu_idx, &sattrs); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address, } else { fi->type = ARMFault_QEMU_SFault; } + *page_size = sattrs.subpage ? 1 : TARGET_PAGE_SIZE; *phys_ptr = address; *prot = 0; return true; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address, * for M_FAKE_FSR_SFAULT in arm_v7m_cpu_do_interrupt(). */ fi->type = ARMFault_QEMU_SFault; + *page_size = sattrs.subpage ? 1 : TARGET_PAGE_SIZE; *phys_ptr = address; *prot = 0; return true; @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_pmsav8(CPUARMState *env, uint32_t address, } } - return pmsav8_mpu_lookup(env, address, access_type, mmu_idx, phys_ptr, - txattrs, prot, fi, NULL); + ret = pmsav8_mpu_lookup(env, address, access_type, mmu_idx, phys_ptr, + txattrs, prot, &mpu_is_subpage, fi, NULL); + /* + * TODO: this is a temporary hack to ignore the fact that the SAU region + * is smaller than a page if this is an executable region. We never + * supported small MPU regions, but we did (accidentally) allow small + * SAU regions, and if we now made small SAU regions not be executable + * then this would break previously working guest code. We can't + * remove this until/unless we implement support for execution from + * small regions. + */ + if (*prot & PAGE_EXEC) { + sattrs.subpage = false; + } + *page_size = sattrs.subpage || mpu_is_subpage ? 1 : TARGET_PAGE_SIZE; + return ret; } static bool get_phys_addr_pmsav5(CPUARMState *env, uint32_t address, @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, if (arm_feature(env, ARM_FEATURE_V8)) { /* PMSAv8 */ ret = get_phys_addr_pmsav8(env, address, access_type, mmu_idx, - phys_ptr, attrs, prot, fi); + phys_ptr, attrs, prot, page_size, fi); } else if (arm_feature(env, ARM_FEATURE_V7)) { /* PMSAv7 */ ret = get_phys_addr_pmsav7(env, address, access_type, mmu_idx, @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) uint32_t mregion; bool targetpriv; bool targetsec = env->v7m.secure; + bool is_subpage; /* Work out what the security state and privilege level we're * interested in is... @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) if (arm_current_el(env) != 0 || alt) { /* We can ignore the return value as prot is always set */ pmsav8_mpu_lookup(env, addr, MMU_DATA_LOAD, mmu_idx, - &phys_addr, &attrs, &prot, &fi, &mregion); + &phys_addr, &attrs, &prot, &is_subpage, + &fi, &mregion); if (mregion == -1) { mrvalid = false; mregion = 0; -- 2.17.1 From: Jia He <hejianet@gmail.com> In case the STE's config is "Bypass" we currently don't set the IOMMUTLBEntry perm flags and the access does not succeed. Also if the config is 0b0xx (Aborted/Reserved), decode_ste and smmuv3_decode_config currently returns -EINVAL and we don't enter the expected code path: we record an event whereas we should not. This patch fixes those bugs and simplifies the error handling. decode_ste and smmuv3_decode_config now return 0 if aborted or bypassed config was found. Only bad config info produces negative error values. In smmuv3_translate we more clearly differentiate errors, bypass/smmu disabled, aborted and success cases. Also trace points are differentiated. Fixes: 9bde7f0674fe ("hw/arm/smmuv3: Implement translate callback") Reported-by: jia.he@hxt-semitech.com Signed-off-by: jia.he@hxt-semitech.com Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1529653501-15358-2-git-send-email-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3-internal.h | 12 ++++- hw/arm/smmuv3.c | 96 +++++++++++++++++++++++++++------------- hw/arm/trace-events | 7 +-- 3 files changed, 80 insertions(+), 35 deletions(-) diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3-internal.h +++ b/hw/arm/smmuv3-internal.h @@ -XXX,XX +XXX,XX @@ #include "hw/arm/smmu-common.h" +typedef enum SMMUTranslationStatus { + SMMU_TRANS_DISABLE, + SMMU_TRANS_ABORT, + SMMU_TRANS_BYPASS, + SMMU_TRANS_ERROR, + SMMU_TRANS_SUCCESS, +} SMMUTranslationStatus; + /* MMIO Registers */ REG32(IDR0, 0x0) @@ -XXX,XX +XXX,XX @@ enum { /* Command completion notification */ /* Events */ typedef enum SMMUEventType { - SMMU_EVT_OK = 0x00, + SMMU_EVT_NONE = 0x00, SMMU_EVT_F_UUT , SMMU_EVT_C_BAD_STREAMID , SMMU_EVT_F_STE_FETCH , @@ -XXX,XX +XXX,XX @@ typedef enum SMMUEventType { } SMMUEventType; static const char *event_stringify[] = { - [SMMU_EVT_OK] = "SMMU_EVT_OK", + [SMMU_EVT_NONE] = "no recorded event", [SMMU_EVT_F_UUT] = "SMMU_EVT_F_UUT", [SMMU_EVT_C_BAD_STREAMID] = "SMMU_EVT_C_BAD_STREAMID", [SMMU_EVT_F_STE_FETCH] = "SMMU_EVT_F_STE_FETCH", diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-core.h" #include "hw/pci/pci.h" #include "exec/address-spaces.h" +#include "cpu.h" #include "trace.h" #include "qemu/log.h" #include "qemu/error-report.h" @@ -XXX,XX +XXX,XX @@ void smmuv3_record_event(SMMUv3State *s, SMMUEventInfo *info) EVT_SET_SID(&evt, info->sid); switch (info->type) { - case SMMU_EVT_OK: + case SMMU_EVT_NONE: return; case SMMU_EVT_F_UUT: EVT_SET_SSID(&evt, info->u.f_uut.ssid); @@ -XXX,XX +XXX,XX @@ static int smmu_get_cd(SMMUv3State *s, STE *ste, uint32_t ssid, return 0; } -/* Returns <0 if the caller has no need to continue the translation */ +/* Returns < 0 in case of invalid STE, 0 otherwise */ static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg, STE *ste, SMMUEventInfo *event) { uint32_t config; - int ret = -EINVAL; if (!STE_VALID(ste)) { goto bad_ste; @@ -XXX,XX +XXX,XX @@ static int decode_ste(SMMUv3State *s, SMMUTransCfg *cfg, config = STE_CONFIG(ste); if (STE_CFG_ABORT(config)) { - cfg->aborted = true; /* abort but don't record any event */ - return ret; + cfg->aborted = true; + return 0; } if (STE_CFG_BYPASS(config)) { cfg->bypassed = true; - return ret; + return 0; } if (STE_CFG_S2_ENABLED(config)) { @@ -XXX,XX +XXX,XX @@ bad_cd: * the different configuration decoding steps * @event: must be zero'ed by the caller * - * return < 0 if the translation needs to be aborted (@event is filled + * return < 0 in case of config decoding error (@event is filled * accordingly). Return 0 otherwise. */ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg, @@ -XXX,XX +XXX,XX @@ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg, SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); uint32_t sid = smmu_get_sid(sdev); SMMUv3State *s = sdev->smmu; - int ret = -EINVAL; + int ret; STE ste; CD cd; - if (smmu_find_ste(s, sid, &ste, event)) { + ret = smmu_find_ste(s, sid, &ste, event); + if (ret) { return ret; } - if (decode_ste(s, cfg, &ste, event)) { + ret = decode_ste(s, cfg, &ste, event); + if (ret) { return ret; } - if (smmu_get_cd(s, &ste, 0 /* ssid */, &cd, event)) { + if (cfg->aborted || cfg->bypassed) { + return 0; + } + + ret = smmu_get_cd(s, &ste, 0 /* ssid */, &cd, event); + if (ret) { return ret; } @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); SMMUv3State *s = sdev->smmu; uint32_t sid = smmu_get_sid(sdev); - SMMUEventInfo event = {.type = SMMU_EVT_OK, .sid = sid}; + SMMUEventInfo event = {.type = SMMU_EVT_NONE, .sid = sid}; SMMUPTWEventInfo ptw_info = {}; + SMMUTranslationStatus status; SMMUTransCfg cfg = {}; IOMMUTLBEntry entry = { .target_as = &address_space_memory, @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, .addr_mask = ~(hwaddr)0, .perm = IOMMU_NONE, }; - int ret = 0; if (!smmu_enabled(s)) { - goto out; + status = SMMU_TRANS_DISABLE; + goto epilogue; } - ret = smmuv3_decode_config(mr, &cfg, &event); - if (ret) { - goto out; + if (smmuv3_decode_config(mr, &cfg, &event)) { + status = SMMU_TRANS_ERROR; + goto epilogue; } if (cfg.aborted) { - goto out; + status = SMMU_TRANS_ABORT; + goto epilogue; } - ret = smmu_ptw(&cfg, addr, flag, &entry, &ptw_info); - if (ret) { + if (cfg.bypassed) { + status = SMMU_TRANS_BYPASS; + goto epilogue; + } + + if (smmu_ptw(&cfg, addr, flag, &entry, &ptw_info)) { switch (ptw_info.type) { case SMMU_PTW_ERR_WALK_EABT: event.type = SMMU_EVT_F_WALK_EABT; @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, default: g_assert_not_reached(); } + status = SMMU_TRANS_ERROR; + } else { + status = SMMU_TRANS_SUCCESS; } -out: - if (ret) { - qemu_log_mask(LOG_GUEST_ERROR, - "%s translation failed for iova=0x%"PRIx64"(%d)\n", - mr->parent_obj.name, addr, ret); - entry.perm = IOMMU_NONE; - smmuv3_record_event(s, &event); - } else if (!cfg.aborted) { + +epilogue: + switch (status) { + case SMMU_TRANS_SUCCESS: entry.perm = flag; - trace_smmuv3_translate(mr->parent_obj.name, sid, addr, - entry.translated_addr, entry.perm); + trace_smmuv3_translate_success(mr->parent_obj.name, sid, addr, + entry.translated_addr, entry.perm); + break; + case SMMU_TRANS_DISABLE: + entry.perm = flag; + entry.addr_mask = ~TARGET_PAGE_MASK; + trace_smmuv3_translate_disable(mr->parent_obj.name, sid, addr, + entry.perm); + break; + case SMMU_TRANS_BYPASS: + entry.perm = flag; + entry.addr_mask = ~TARGET_PAGE_MASK; + trace_smmuv3_translate_bypass(mr->parent_obj.name, sid, addr, + entry.perm); + break; + case SMMU_TRANS_ABORT: + /* no event is recorded on abort */ + trace_smmuv3_translate_abort(mr->parent_obj.name, sid, addr, + entry.perm); + break; + case SMMU_TRANS_ERROR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s translation failed for iova=0x%"PRIx64"(%s)\n", + mr->parent_obj.name, addr, smmu_event_string(event.type)); + smmuv3_record_event(s, &event); + break; } return entry; diff --git a/hw/arm/trace-events b/hw/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -XXX,XX +XXX,XX @@ smmuv3_record_event(const char *type, uint32_t sid) "%s sid=%d" smmuv3_find_ste(uint16_t sid, uint32_t features, uint16_t sid_split) "SID:0x%x features:0x%x, sid_split:0x%x" smmuv3_find_ste_2lvl(uint64_t strtab_base, uint64_t l1ptr, int l1_ste_offset, uint64_t l2ptr, int l2_ste_offset, int max_l2_ste) "strtab_base:0x%"PRIx64" l1ptr:0x%"PRIx64" l1_off:0x%x, l2ptr:0x%"PRIx64" l2_off:0x%x max_l2_ste:%d" smmuv3_get_ste(uint64_t addr) "STE addr: 0x%"PRIx64 -smmuv3_translate_bypass(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d bypass iova:0x%"PRIx64" is_write=%d" -smmuv3_translate_in(uint16_t sid, int pci_bus_num, uint64_t strtab_base) "SID:0x%x bus:%d strtab_base:0x%"PRIx64 +smmuv3_translate_disable(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d bypass (smmu disabled) iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_bypass(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d STE bypass iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_abort(const char *n, uint16_t sid, uint64_t addr, bool is_write) "%s sid=%d abort on iova:0x%"PRIx64" is_write=%d" +smmuv3_translate_success(const char *n, uint16_t sid, uint64_t iova, uint64_t translated, int perm) "%s sid=%d iova=0x%"PRIx64" translated=0x%"PRIx64" perm=0x%x" smmuv3_get_cd(uint64_t addr) "CD addr: 0x%"PRIx64 -smmuv3_translate(const char *n, uint16_t sid, uint64_t iova, uint64_t translated, int perm) "%s sid=%d iova=0x%"PRIx64" translated=0x%"PRIx64" perm=0x%x" smmuv3_decode_cd(uint32_t oas) "oas=%d" smmuv3_decode_cd_tt(int i, uint32_t tsz, uint64_t ttb, uint32_t granule_sz) "TT[%d]:tsz:%d ttb:0x%"PRIx64" granule_sz:%d" -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> Let's cache config data to avoid fetching and parsing STE/CD structures on each translation. We invalidate them on data structure invalidation commands. We put in place a per-smmu mutex to protect the config cache. This will be useful too to protect the IOTLB cache. The caches can be accessed without BQL, ie. in IO dataplane. The same kind of mutex was put in place in the intel viommu. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1529653501-15358-3-git-send-email-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/smmu-common.h | 5 ++ include/hw/arm/smmuv3.h | 1 + hw/arm/smmu-common.c | 24 ++++++- hw/arm/smmuv3.c | 135 +++++++++++++++++++++++++++++++++-- hw/arm/trace-events | 6 ++ 5 files changed, 164 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -XXX,XX +XXX,XX @@ typedef struct SMMUDevice { int devfn; IOMMUMemoryRegion iommu; AddressSpace as; + uint32_t cfg_cache_hits; + uint32_t cfg_cache_misses; } SMMUDevice; typedef struct SMMUNotifierNode { @@ -XXX,XX +XXX,XX @@ int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm, */ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova); +/* Return the iommu mr associated to @sid, or NULL if none */ +IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid); + #endif /* HW_ARM_SMMU_COMMON */ diff --git a/include/hw/arm/smmuv3.h b/include/hw/arm/smmuv3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/smmuv3.h +++ b/include/hw/arm/smmuv3.h @@ -XXX,XX +XXX,XX @@ typedef struct SMMUv3State { SMMUQueue eventq, cmdq; qemu_irq irq[4]; + QemuMutex mutex; } SMMUv3State; typedef enum { diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ static AddressSpace *smmu_find_add_as(PCIBus *bus, void *opaque, int devfn) return &sdev->as; } +IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid) +{ + uint8_t bus_n, devfn; + SMMUPciBus *smmu_bus; + SMMUDevice *smmu; + + bus_n = PCI_BUS_NUM(sid); + smmu_bus = smmu_find_smmu_pcibus(s, bus_n); + if (smmu_bus) { + devfn = sid & 0x7; + smmu = smmu_bus->pbdev[devfn]; + if (smmu) { + return &smmu->iommu; + } + } + return NULL; +} + static void smmu_base_realize(DeviceState *dev, Error **errp) { SMMUState *s = ARM_SMMU(dev); @@ -XXX,XX +XXX,XX @@ static void smmu_base_realize(DeviceState *dev, Error **errp) error_propagate(errp, local_err); return; } - + s->configs = g_hash_table_new_full(NULL, NULL, NULL, g_free); s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL); if (s->primary_bus) { @@ -XXX,XX +XXX,XX @@ static void smmu_base_realize(DeviceState *dev, Error **errp) static void smmu_base_reset(DeviceState *dev) { - /* will be filled later on */ + SMMUState *s = ARM_SMMU(dev); + + g_hash_table_remove_all(s->configs); } static Property smmu_dev_properties[] = { diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static int smmuv3_decode_config(IOMMUMemoryRegion *mr, SMMUTransCfg *cfg, return decode_cd(cfg, &cd, event); } +/** + * smmuv3_get_config - Look up for a cached copy of configuration data for + * @sdev and on cache miss performs a configuration structure decoding from + * guest RAM. + * + * @sdev: SMMUDevice handle + * @event: output event info + * + * The configuration cache contains data resulting from both STE and CD + * decoding under the form of an SMMUTransCfg struct. The hash table is indexed + * by the SMMUDevice handle. + */ +static SMMUTransCfg *smmuv3_get_config(SMMUDevice *sdev, SMMUEventInfo *event) +{ + SMMUv3State *s = sdev->smmu; + SMMUState *bc = &s->smmu_state; + SMMUTransCfg *cfg; + + cfg = g_hash_table_lookup(bc->configs, sdev); + if (cfg) { + sdev->cfg_cache_hits++; + trace_smmuv3_config_cache_hit(smmu_get_sid(sdev), + sdev->cfg_cache_hits, sdev->cfg_cache_misses, + 100 * sdev->cfg_cache_hits / + (sdev->cfg_cache_hits + sdev->cfg_cache_misses)); + } else { + sdev->cfg_cache_misses++; + trace_smmuv3_config_cache_miss(smmu_get_sid(sdev), + sdev->cfg_cache_hits, sdev->cfg_cache_misses, + 100 * sdev->cfg_cache_hits / + (sdev->cfg_cache_hits + sdev->cfg_cache_misses)); + cfg = g_new0(SMMUTransCfg, 1); + + if (!smmuv3_decode_config(&sdev->iommu, cfg, event)) { + g_hash_table_insert(bc->configs, sdev, cfg); + } else { + g_free(cfg); + cfg = NULL; + } + } + return cfg; +} + +static void smmuv3_flush_config(SMMUDevice *sdev) +{ + SMMUv3State *s = sdev->smmu; + SMMUState *bc = &s->smmu_state; + + trace_smmuv3_config_cache_inv(smmu_get_sid(sdev)); + g_hash_table_remove(bc->configs, sdev); +} + static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, IOMMUAccessFlags flag, int iommu_idx) { @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, SMMUEventInfo event = {.type = SMMU_EVT_NONE, .sid = sid}; SMMUPTWEventInfo ptw_info = {}; SMMUTranslationStatus status; - SMMUTransCfg cfg = {}; + SMMUTransCfg *cfg = NULL; IOMMUTLBEntry entry = { .target_as = &address_space_memory, .iova = addr, @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, .perm = IOMMU_NONE, }; + qemu_mutex_lock(&s->mutex); + if (!smmu_enabled(s)) { status = SMMU_TRANS_DISABLE; goto epilogue; } - if (smmuv3_decode_config(mr, &cfg, &event)) { + cfg = smmuv3_get_config(sdev, &event); + if (!cfg) { status = SMMU_TRANS_ERROR; goto epilogue; } - if (cfg.aborted) { + if (cfg->aborted) { status = SMMU_TRANS_ABORT; goto epilogue; } - if (cfg.bypassed) { + if (cfg->bypassed) { status = SMMU_TRANS_BYPASS; goto epilogue; } - if (smmu_ptw(&cfg, addr, flag, &entry, &ptw_info)) { + if (smmu_ptw(cfg, addr, flag, &entry, &ptw_info)) { switch (ptw_info.type) { case SMMU_PTW_ERR_WALK_EABT: event.type = SMMU_EVT_F_WALK_EABT; @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, } epilogue: + qemu_mutex_unlock(&s->mutex); switch (status) { case SMMU_TRANS_SUCCESS: entry.perm = flag; @@ -XXX,XX +XXX,XX @@ epilogue: static int smmuv3_cmdq_consume(SMMUv3State *s) { + SMMUState *bs = ARM_SMMU(s); SMMUCmdError cmd_error = SMMU_CERROR_NONE; SMMUQueue *q = &s->cmdq; SMMUCommandType type = 0; @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) trace_smmuv3_cmdq_opcode(smmu_cmd_string(type)); + qemu_mutex_lock(&s->mutex); switch (type) { case SMMU_CMD_SYNC: if (CMD_SYNC_CS(&cmd) & CMD_SYNC_SIG_IRQ) { @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) break; case SMMU_CMD_PREFETCH_CONFIG: case SMMU_CMD_PREFETCH_ADDR: + break; case SMMU_CMD_CFGI_STE: + { + uint32_t sid = CMD_SID(&cmd); + IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, sid); + SMMUDevice *sdev; + + if (CMD_SSEC(&cmd)) { + cmd_error = SMMU_CERROR_ILL; + break; + } + + if (!mr) { + break; + } + + trace_smmuv3_cmdq_cfgi_ste(sid); + sdev = container_of(mr, SMMUDevice, iommu); + smmuv3_flush_config(sdev); + + break; + } case SMMU_CMD_CFGI_STE_RANGE: /* same as SMMU_CMD_CFGI_ALL */ + { + uint32_t start = CMD_SID(&cmd), end, i; + uint8_t range = CMD_STE_RANGE(&cmd); + + if (CMD_SSEC(&cmd)) { + cmd_error = SMMU_CERROR_ILL; + break; + } + + end = start + (1 << (range + 1)) - 1; + trace_smmuv3_cmdq_cfgi_ste_range(start, end); + + for (i = start; i <= end; i++) { + IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, i); + SMMUDevice *sdev; + + if (!mr) { + continue; + } + sdev = container_of(mr, SMMUDevice, iommu); + smmuv3_flush_config(sdev); + } + break; + } case SMMU_CMD_CFGI_CD: case SMMU_CMD_CFGI_CD_ALL: + { + uint32_t sid = CMD_SID(&cmd); + IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, sid); + SMMUDevice *sdev; + + if (CMD_SSEC(&cmd)) { + cmd_error = SMMU_CERROR_ILL; + break; + } + + if (!mr) { + break; + } + + trace_smmuv3_cmdq_cfgi_cd(sid); + sdev = container_of(mr, SMMUDevice, iommu); + smmuv3_flush_config(sdev); + break; + } case SMMU_CMD_TLBI_NH_ALL: case SMMU_CMD_TLBI_NH_ASID: case SMMU_CMD_TLBI_NH_VA: @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) "Illegal command type: %d\n", CMD_TYPE(&cmd)); break; } + qemu_mutex_unlock(&s->mutex); if (cmd_error) { break; } @@ -XXX,XX +XXX,XX @@ static void smmu_realize(DeviceState *d, Error **errp) return; } + qemu_mutex_init(&s->mutex); + memory_region_init_io(&sys->iomem, OBJECT(s), &smmu_mem_ops, sys, TYPE_ARM_SMMUV3, 0x20000); diff --git a/hw/arm/trace-events b/hw/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -XXX,XX +XXX,XX @@ smmuv3_translate_success(const char *n, uint16_t sid, uint64_t iova, uint64_t tr smmuv3_get_cd(uint64_t addr) "CD addr: 0x%"PRIx64 smmuv3_decode_cd(uint32_t oas) "oas=%d" smmuv3_decode_cd_tt(int i, uint32_t tsz, uint64_t ttb, uint32_t granule_sz) "TT[%d]:tsz:%d ttb:0x%"PRIx64" granule_sz:%d" +smmuv3_cmdq_cfgi_ste(int streamid) "streamid =%d" +smmuv3_cmdq_cfgi_ste_range(int start, int end) "start=0x%d - end=0x%d" +smmuv3_cmdq_cfgi_cd(uint32_t sid) "streamid = %d" +smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid %d (hits=%d, misses=%d, hit rate=%d)" +smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid %d (hits=%d, misses=%d, hit rate=%d)" +smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid %d" -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> We emulate a TLB cache of size SMMU_IOTLB_MAX_SIZE=256. It is implemented as a hash table whose key is a combination of the 16b asid and 48b IOVA (Jenkins hash). Entries are invalidated on TLB invalidation commands, either globally, or per asid, or per asid/iova. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 1529653501-15358-4-git-send-email-eric.auger@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/smmu-common.h | 13 +++++ hw/arm/smmu-common.c | 60 ++++++++++++++++++++++ hw/arm/smmuv3.c | 98 ++++++++++++++++++++++++++++++++++-- hw/arm/trace-events | 9 ++++ 4 files changed, 176 insertions(+), 4 deletions(-) diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -XXX,XX +XXX,XX @@ typedef struct SMMUTransCfg { uint8_t tbi; /* Top Byte Ignore */ uint16_t asid; SMMUTransTableInfo tt[2]; + uint32_t iotlb_hits; /* counts IOTLB hits for this asid */ + uint32_t iotlb_misses; /* counts IOTLB misses for this asid */ } SMMUTransCfg; typedef struct SMMUDevice { @@ -XXX,XX +XXX,XX @@ typedef struct SMMUPciBus { SMMUDevice *pbdev[0]; /* Parent array is sparse, so dynamically alloc */ } SMMUPciBus; +typedef struct SMMUIOTLBKey { + uint64_t iova; + uint16_t asid; +} SMMUIOTLBKey; + typedef struct SMMUState { /* <private> */ SysBusDevice dev; @@ -XXX,XX +XXX,XX @@ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova); /* Return the iommu mr associated to @sid, or NULL if none */ IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid); +#define SMMU_IOTLB_MAX_SIZE 256 + +void smmu_iotlb_inv_all(SMMUState *s); +void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid); +void smmu_iotlb_inv_iova(SMMUState *s, uint16_t asid, dma_addr_t iova); + #endif /* HW_ARM_SMMU_COMMON */ diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ #include "qom/cpu.h" #include "hw/qdev-properties.h" #include "qapi/error.h" +#include "qemu/jhash.h" #include "qemu/error-report.h" #include "hw/arm/smmu-common.h" #include "smmu-internal.h" +/* IOTLB Management */ + +inline void smmu_iotlb_inv_all(SMMUState *s) +{ + trace_smmu_iotlb_inv_all(); + g_hash_table_remove_all(s->iotlb); +} + +static gboolean smmu_hash_remove_by_asid(gpointer key, gpointer value, + gpointer user_data) +{ + uint16_t asid = *(uint16_t *)user_data; + SMMUIOTLBKey *iotlb_key = (SMMUIOTLBKey *)key; + + return iotlb_key->asid == asid; +} + +inline void smmu_iotlb_inv_iova(SMMUState *s, uint16_t asid, dma_addr_t iova) +{ + SMMUIOTLBKey key = {.asid = asid, .iova = iova}; + + trace_smmu_iotlb_inv_iova(asid, iova); + g_hash_table_remove(s->iotlb, &key); +} + +inline void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid) +{ + trace_smmu_iotlb_inv_asid(asid); + g_hash_table_foreach_remove(s->iotlb, smmu_hash_remove_by_asid, &asid); +} + /* VMSAv8-64 Translation */ /** @@ -XXX,XX +XXX,XX @@ IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid) return NULL; } +static guint smmu_iotlb_key_hash(gconstpointer v) +{ + SMMUIOTLBKey *key = (SMMUIOTLBKey *)v; + uint32_t a, b, c; + + /* Jenkins hash */ + a = b = c = JHASH_INITVAL + sizeof(*key); + a += key->asid; + b += extract64(key->iova, 0, 32); + c += extract64(key->iova, 32, 32); + + __jhash_mix(a, b, c); + __jhash_final(a, b, c); + + return c; +} + +static gboolean smmu_iotlb_key_equal(gconstpointer v1, gconstpointer v2) +{ + const SMMUIOTLBKey *k1 = v1; + const SMMUIOTLBKey *k2 = v2; + + return (k1->asid == k2->asid) && (k1->iova == k2->iova); +} + static void smmu_base_realize(DeviceState *dev, Error **errp) { SMMUState *s = ARM_SMMU(dev); @@ -XXX,XX +XXX,XX @@ static void smmu_base_realize(DeviceState *dev, Error **errp) return; } s->configs = g_hash_table_new_full(NULL, NULL, NULL, g_free); + s->iotlb = g_hash_table_new_full(smmu_iotlb_key_hash, smmu_iotlb_key_equal, + g_free, g_free); s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL); if (s->primary_bus) { @@ -XXX,XX +XXX,XX @@ static void smmu_base_reset(DeviceState *dev) SMMUState *s = ARM_SMMU(dev); g_hash_table_remove_all(s->configs); + g_hash_table_remove_all(s->iotlb); } static Property smmu_dev_properties[] = { diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, SMMUEventInfo event = {.type = SMMU_EVT_NONE, .sid = sid}; SMMUPTWEventInfo ptw_info = {}; SMMUTranslationStatus status; + SMMUState *bs = ARM_SMMU(s); + uint64_t page_mask, aligned_addr; + IOMMUTLBEntry *cached_entry = NULL; + SMMUTransTableInfo *tt; SMMUTransCfg *cfg = NULL; IOMMUTLBEntry entry = { .target_as = &address_space_memory, @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, .addr_mask = ~(hwaddr)0, .perm = IOMMU_NONE, }; + SMMUIOTLBKey key, *new_key; qemu_mutex_lock(&s->mutex); @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, goto epilogue; } - if (smmu_ptw(cfg, addr, flag, &entry, &ptw_info)) { + tt = select_tt(cfg, addr); + if (!tt) { + if (event.record_trans_faults) { + event.type = SMMU_EVT_F_TRANSLATION; + event.u.f_translation.addr = addr; + event.u.f_translation.rnw = flag & 0x1; + } + status = SMMU_TRANS_ERROR; + goto epilogue; + } + + page_mask = (1ULL << (tt->granule_sz)) - 1; + aligned_addr = addr & ~page_mask; + + key.asid = cfg->asid; + key.iova = aligned_addr; + + cached_entry = g_hash_table_lookup(bs->iotlb, &key); + if (cached_entry) { + cfg->iotlb_hits++; + trace_smmu_iotlb_cache_hit(cfg->asid, aligned_addr, + cfg->iotlb_hits, cfg->iotlb_misses, + 100 * cfg->iotlb_hits / + (cfg->iotlb_hits + cfg->iotlb_misses)); + if ((flag & IOMMU_WO) && !(cached_entry->perm & IOMMU_WO)) { + status = SMMU_TRANS_ERROR; + if (event.record_trans_faults) { + event.type = SMMU_EVT_F_PERMISSION; + event.u.f_permission.addr = addr; + event.u.f_permission.rnw = flag & 0x1; + } + } else { + status = SMMU_TRANS_SUCCESS; + } + goto epilogue; + } + + cfg->iotlb_misses++; + trace_smmu_iotlb_cache_miss(cfg->asid, addr & ~page_mask, + cfg->iotlb_hits, cfg->iotlb_misses, + 100 * cfg->iotlb_hits / + (cfg->iotlb_hits + cfg->iotlb_misses)); + + if (g_hash_table_size(bs->iotlb) >= SMMU_IOTLB_MAX_SIZE) { + smmu_iotlb_inv_all(bs); + } + + cached_entry = g_new0(IOMMUTLBEntry, 1); + + if (smmu_ptw(cfg, aligned_addr, flag, cached_entry, &ptw_info)) { + g_free(cached_entry); switch (ptw_info.type) { case SMMU_PTW_ERR_WALK_EABT: event.type = SMMU_EVT_F_WALK_EABT; @@ -XXX,XX +XXX,XX @@ static IOMMUTLBEntry smmuv3_translate(IOMMUMemoryRegion *mr, hwaddr addr, } status = SMMU_TRANS_ERROR; } else { + new_key = g_new0(SMMUIOTLBKey, 1); + new_key->asid = cfg->asid; + new_key->iova = aligned_addr; + g_hash_table_insert(bs->iotlb, new_key, cached_entry); status = SMMU_TRANS_SUCCESS; } @@ -XXX,XX +XXX,XX @@ epilogue: switch (status) { case SMMU_TRANS_SUCCESS: entry.perm = flag; + entry.translated_addr = cached_entry->translated_addr + + (addr & page_mask); + entry.addr_mask = cached_entry->addr_mask; trace_smmuv3_translate_success(mr->parent_obj.name, sid, addr, entry.translated_addr, entry.perm); break; @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) smmuv3_flush_config(sdev); break; } - case SMMU_CMD_TLBI_NH_ALL: case SMMU_CMD_TLBI_NH_ASID: - case SMMU_CMD_TLBI_NH_VA: + { + uint16_t asid = CMD_ASID(&cmd); + + trace_smmuv3_cmdq_tlbi_nh_asid(asid); + smmu_iotlb_inv_asid(bs, asid); + break; + } + case SMMU_CMD_TLBI_NH_ALL: + case SMMU_CMD_TLBI_NSNH_ALL: + trace_smmuv3_cmdq_tlbi_nh(); + smmu_iotlb_inv_all(bs); + break; case SMMU_CMD_TLBI_NH_VAA: + { + dma_addr_t addr = CMD_ADDR(&cmd); + uint16_t vmid = CMD_VMID(&cmd); + + trace_smmuv3_cmdq_tlbi_nh_vaa(vmid, addr); + smmu_iotlb_inv_all(bs); + break; + } + case SMMU_CMD_TLBI_NH_VA: + { + uint16_t asid = CMD_ASID(&cmd); + uint16_t vmid = CMD_VMID(&cmd); + dma_addr_t addr = CMD_ADDR(&cmd); + bool leaf = CMD_LEAF(&cmd); + + trace_smmuv3_cmdq_tlbi_nh_va(vmid, asid, addr, leaf); + smmu_iotlb_inv_iova(bs, asid, addr); + break; + } case SMMU_CMD_TLBI_EL3_ALL: case SMMU_CMD_TLBI_EL3_VA: case SMMU_CMD_TLBI_EL2_ALL: @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) case SMMU_CMD_TLBI_EL2_VAA: case SMMU_CMD_TLBI_S12_VMALL: case SMMU_CMD_TLBI_S2_IPA: - case SMMU_CMD_TLBI_NSNH_ALL: case SMMU_CMD_ATC_INV: case SMMU_CMD_PRI_RESP: case SMMU_CMD_RESUME: diff --git a/hw/arm/trace-events b/hw/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -XXX,XX +XXX,XX @@ smmu_ptw_invalid_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, smmu_ptw_page_pte(int stage, int level, uint64_t iova, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t address) "stage=%d level=%d iova=0x%"PRIx64" base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" page address = 0x%"PRIx64 smmu_ptw_block_pte(int stage, int level, uint64_t baseaddr, uint64_t pteaddr, uint64_t pte, uint64_t iova, uint64_t gpa, int bsize_mb) "stage=%d level=%d base@=0x%"PRIx64" pte@=0x%"PRIx64" pte=0x%"PRIx64" iova=0x%"PRIx64" block address = 0x%"PRIx64" block size = %d MiB" smmu_get_pte(uint64_t baseaddr, int index, uint64_t pteaddr, uint64_t pte) "baseaddr=0x%"PRIx64" index=0x%x, pteaddr=0x%"PRIx64", pte=0x%"PRIx64 +smmu_iotlb_cache_hit(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache HIT asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d" +smmu_iotlb_cache_miss(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, uint32_t p) "IOTLB cache MISS asid=%d addr=0x%"PRIx64" hit=%d miss=%d hit rate=%d" +smmu_iotlb_inv_all(void) "IOTLB invalidate all" +smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d" +smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64 #hw/arm/smmuv3.c smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" @@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_cfgi_ste_range(int start, int end) "start=0x%d - end=0x%d" smmuv3_cmdq_cfgi_cd(uint32_t sid) "streamid = %d" smmuv3_config_cache_hit(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache HIT for sid %d (hits=%d, misses=%d, hit rate=%d)" smmuv3_config_cache_miss(uint32_t sid, uint32_t hits, uint32_t misses, uint32_t perc) "Config cache MISS for sid %d (hits=%d, misses=%d, hit rate=%d)" +smmuv3_cmdq_tlbi_nh_va(int vmid, int asid, uint64_t addr, bool leaf) "vmid =%d asid =%d addr=0x%"PRIx64" leaf=%d" +smmuv3_cmdq_tlbi_nh_vaa(int vmid, uint64_t addr) "vmid =%d addr=0x%"PRIx64 +smmuv3_cmdq_tlbi_nh(void) "" +smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d" smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid %d" -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> On TLB invalidation commands, let's call registered IOMMU notifiers. Those can only be UNMAP notifiers. SMMUv3 does not support notification on MAP (VFIO). This patch allows vhost use case where IOTLB API is notified on each guest IOTLB invalidation. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1529653501-15358-5-git-send-email-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/smmu-common.h | 6 +++ hw/arm/smmu-common.c | 34 +++++++++++++ hw/arm/smmuv3.c | 99 +++++++++++++++++++++++++++++++++++- hw/arm/trace-events | 5 ++ 4 files changed, 142 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -XXX,XX +XXX,XX @@ void smmu_iotlb_inv_all(SMMUState *s); void smmu_iotlb_inv_asid(SMMUState *s, uint16_t asid); void smmu_iotlb_inv_iova(SMMUState *s, uint16_t asid, dma_addr_t iova); +/* Unmap the range of all the notifiers registered to any IOMMU mr */ +void smmu_inv_notifiers_all(SMMUState *s); + +/* Unmap the range of all the notifiers registered to @mr */ +void smmu_inv_notifiers_mr(IOMMUMemoryRegion *mr); + #endif /* HW_ARM_SMMU_COMMON */ diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ static gboolean smmu_iotlb_key_equal(gconstpointer v1, gconstpointer v2) return (k1->asid == k2->asid) && (k1->iova == k2->iova); } +/* Unmap the whole notifier's range */ +static void smmu_unmap_notifier_range(IOMMUNotifier *n) +{ + IOMMUTLBEntry entry; + + entry.target_as = &address_space_memory; + entry.iova = n->start; + entry.perm = IOMMU_NONE; + entry.addr_mask = n->end - n->start; + + memory_region_notify_one(n, &entry); +} + +/* Unmap all notifiers attached to @mr */ +inline void smmu_inv_notifiers_mr(IOMMUMemoryRegion *mr) +{ + IOMMUNotifier *n; + + trace_smmu_inv_notifiers_mr(mr->parent_obj.name); + IOMMU_NOTIFIER_FOREACH(n, mr) { + smmu_unmap_notifier_range(n); + } +} + +/* Unmap all notifiers of all mr's */ +void smmu_inv_notifiers_all(SMMUState *s) +{ + SMMUNotifierNode *node; + + QLIST_FOREACH(node, &s->notifiers_list, next) { + smmu_inv_notifiers_mr(&node->sdev->iommu); + } +} + static void smmu_base_realize(DeviceState *dev, Error **errp) { SMMUState *s = ARM_SMMU(dev); diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ epilogue: return entry; } +/** + * smmuv3_notify_iova - call the notifier @n for a given + * @asid and @iova tuple. + * + * @mr: IOMMU mr region handle + * @n: notifier to be called + * @asid: address space ID or negative value if we don't care + * @iova: iova + */ +static void smmuv3_notify_iova(IOMMUMemoryRegion *mr, + IOMMUNotifier *n, + int asid, + dma_addr_t iova) +{ + SMMUDevice *sdev = container_of(mr, SMMUDevice, iommu); + SMMUEventInfo event = {}; + SMMUTransTableInfo *tt; + SMMUTransCfg *cfg; + IOMMUTLBEntry entry; + + cfg = smmuv3_get_config(sdev, &event); + if (!cfg) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s error decoding the configuration for iommu mr=%s\n", + __func__, mr->parent_obj.name); + return; + } + + if (asid >= 0 && cfg->asid != asid) { + return; + } + + tt = select_tt(cfg, iova); + if (!tt) { + return; + } + + entry.target_as = &address_space_memory; + entry.iova = iova; + entry.addr_mask = (1 << tt->granule_sz) - 1; + entry.perm = IOMMU_NONE; + + memory_region_notify_one(n, &entry); +} + +/* invalidate an asid/iova tuple in all mr's */ +static void smmuv3_inv_notifiers_iova(SMMUState *s, int asid, dma_addr_t iova) +{ + SMMUNotifierNode *node; + + QLIST_FOREACH(node, &s->notifiers_list, next) { + IOMMUMemoryRegion *mr = &node->sdev->iommu; + IOMMUNotifier *n; + + trace_smmuv3_inv_notifiers_iova(mr->parent_obj.name, asid, iova); + + IOMMU_NOTIFIER_FOREACH(n, mr) { + smmuv3_notify_iova(mr, n, asid, iova); + } + } +} + static int smmuv3_cmdq_consume(SMMUv3State *s) { SMMUState *bs = ARM_SMMU(s); @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) uint16_t asid = CMD_ASID(&cmd); trace_smmuv3_cmdq_tlbi_nh_asid(asid); + smmu_inv_notifiers_all(&s->smmu_state); smmu_iotlb_inv_asid(bs, asid); break; } case SMMU_CMD_TLBI_NH_ALL: case SMMU_CMD_TLBI_NSNH_ALL: trace_smmuv3_cmdq_tlbi_nh(); + smmu_inv_notifiers_all(&s->smmu_state); smmu_iotlb_inv_all(bs); break; case SMMU_CMD_TLBI_NH_VAA: @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) uint16_t vmid = CMD_VMID(&cmd); trace_smmuv3_cmdq_tlbi_nh_vaa(vmid, addr); + smmuv3_inv_notifiers_iova(bs, -1, addr); smmu_iotlb_inv_all(bs); break; } @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) bool leaf = CMD_LEAF(&cmd); trace_smmuv3_cmdq_tlbi_nh_va(vmid, asid, addr, leaf); + smmuv3_inv_notifiers_iova(bs, asid, addr); smmu_iotlb_inv_iova(bs, asid, addr); break; } @@ -XXX,XX +XXX,XX @@ static void smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu, IOMMUNotifierFlag old, IOMMUNotifierFlag new) { + SMMUDevice *sdev = container_of(iommu, SMMUDevice, iommu); + SMMUv3State *s3 = sdev->smmu; + SMMUState *s = &(s3->smmu_state); + SMMUNotifierNode *node = NULL; + SMMUNotifierNode *next_node = NULL; + + if (new & IOMMU_NOTIFIER_MAP) { + int bus_num = pci_bus_num(sdev->bus); + PCIDevice *pcidev = pci_find_device(sdev->bus, bus_num, sdev->devfn); + + warn_report("SMMUv3 does not support notification on MAP: " + "device %s will not function properly", pcidev->name); + } + if (old == IOMMU_NOTIFIER_NONE) { - warn_report("SMMUV3 does not support vhost/vfio integration yet: " - "devices of those types will not function properly"); + trace_smmuv3_notify_flag_add(iommu->parent_obj.name); + node = g_malloc0(sizeof(*node)); + node->sdev = sdev; + QLIST_INSERT_HEAD(&s->notifiers_list, node, next); + return; + } + + /* update notifier node with new flags */ + QLIST_FOREACH_SAFE(node, &s->notifiers_list, next, next_node) { + if (node->sdev == sdev) { + if (new == IOMMU_NOTIFIER_NONE) { + trace_smmuv3_notify_flag_del(iommu->parent_obj.name); + QLIST_REMOVE(node, next); + g_free(node); + } + return; + } } } diff --git a/hw/arm/trace-events b/hw/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/trace-events +++ b/hw/arm/trace-events @@ -XXX,XX +XXX,XX @@ smmu_iotlb_cache_miss(uint16_t asid, uint64_t addr, uint32_t hit, uint32_t miss, smmu_iotlb_inv_all(void) "IOTLB invalidate all" smmu_iotlb_inv_asid(uint16_t asid) "IOTLB invalidate asid=%d" smmu_iotlb_inv_iova(uint16_t asid, uint64_t addr) "IOTLB invalidate asid=%d addr=0x%"PRIx64 +smmu_inv_notifiers_mr(const char *name) "iommu mr=%s" #hw/arm/smmuv3.c smmuv3_read_mmio(uint64_t addr, uint64_t val, unsigned size, uint32_t r) "addr: 0x%"PRIx64" val:0x%"PRIx64" size: 0x%x(%d)" @@ -XXX,XX +XXX,XX @@ smmuv3_cmdq_tlbi_nh_vaa(int vmid, uint64_t addr) "vmid =%d addr=0x%"PRIx64 smmuv3_cmdq_tlbi_nh(void) "" smmuv3_cmdq_tlbi_nh_asid(uint16_t asid) "asid=%d" smmuv3_config_cache_inv(uint32_t sid) "Config cache INV for sid %d" +smmuv3_notify_flag_add(const char *iommu) "ADD SMMUNotifier node for iommu mr=%s" +smmuv3_notify_flag_del(const char *iommu) "DEL SMMUNotifier node for iommu mr=%s" +smmuv3_inv_notifiers_iova(const char *name, uint16_t asid, uint64_t iova) "iommu mr=%s asid=%d iova=0x%"PRIx64 + -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> All Aspeed SoC clocks are driven by an input source clock which can have different frequencies : 24MHz or 25MHz, and also, on the Aspeed AST2400 SoC, 48MHz. The H-PLL (CPU) clock is defined from a calculation using parameters in the H-PLL Parameter register or from a predefined set of frequencies if the setting is strapped by hardware (Aspeed AST2400 SoC). The other clocks of the SoC are then defined from the H-PLL using dividers. We introduce first the APB clock because it should be used to drive the Aspeed timer model. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180622075700.5923-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/aspeed_scu.h | 70 +++++++++++++++++++++-- hw/misc/aspeed_scu.c | 106 +++++++++++++++++++++++++++++++++++ 2 files changed, 172 insertions(+), 4 deletions(-) diff --git a/include/hw/misc/aspeed_scu.h b/include/hw/misc/aspeed_scu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/aspeed_scu.h +++ b/include/hw/misc/aspeed_scu.h @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSCUState { uint32_t hw_strap1; uint32_t hw_strap2; uint32_t hw_prot_key; + + uint32_t clkin; + uint32_t hpll; + uint32_t apb_freq; } AspeedSCUState; #define AST2400_A0_SILICON_REV 0x02000303U @@ -XXX,XX +XXX,XX @@ extern bool is_supported_silicon_rev(uint32_t silicon_rev); * 1. 2012/12/29 Ryan Chen Create */ -/* Hardware Strapping Register definition (for Aspeed AST2400 SOC) +/* SCU08 Clock Selection Register + * + * 31 Enable Video Engine clock dynamic slow down + * 30:28 Video Engine clock slow down setting + * 27 2D Engine GCLK clock source selection + * 26 2D Engine GCLK clock throttling enable + * 25:23 APB PCLK divider selection + * 22:20 LPC Host LHCLK divider selection + * 19 LPC Host LHCLK clock generation/output enable control + * 18:16 MAC AHB bus clock divider selection + * 15 SD/SDIO clock running enable + * 14:12 SD/SDIO divider selection + * 11 Reserved + * 10:8 Video port output clock delay control bit + * 7 ARM CPU/AHB clock slow down enable + * 6:4 ARM CPU/AHB clock slow down setting + * 3:2 ECLK clock source selection + * 1 CPU/AHB clock slow down idle timer + * 0 CPU/AHB clock dynamic slow down enable (defined in bit[6:4]) + */ +#define SCU_CLK_GET_PCLK_DIV(x) (((x) >> 23) & 0x7) + +/* SCU24 H-PLL Parameter Register (for Aspeed AST2400 SOC) + * + * 18 H-PLL parameter selection + * 0: Select H-PLL by strapping resistors + * 1: Select H-PLL by the programmed registers (SCU24[17:0]) + * 17 Enable H-PLL bypass mode + * 16 Turn off H-PLL + * 10:5 H-PLL Numerator + * 4 H-PLL Output Divider + * 3:0 H-PLL Denumerator + * + * (Output frequency) = 24MHz * (2-OD) * [(Numerator+2) / (Denumerator+1)] + */ + +#define SCU_AST2400_H_PLL_PROGRAMMED (0x1 << 18) +#define SCU_AST2400_H_PLL_BYPASS_EN (0x1 << 17) +#define SCU_AST2400_H_PLL_OFF (0x1 << 16) + +/* SCU24 H-PLL Parameter Register (for Aspeed AST2500 SOC) + * + * 21 Enable H-PLL reset + * 20 Enable H-PLL bypass mode + * 19 Turn off H-PLL + * 18:13 H-PLL Post Divider + * 12:5 H-PLL Numerator (M) + * 4:0 H-PLL Denumerator (N) + * + * (Output frequency) = CLKIN(24MHz) * [(M+1) / (N+1)] / (P+1) + * + * The default frequency is 792Mhz when CLKIN = 24MHz + */ + +#define SCU_H_PLL_BYPASS_EN (0x1 << 20) +#define SCU_H_PLL_OFF (0x1 << 19) + +/* SCU70 Hardware Strapping Register definition (for Aspeed AST2400 SOC) * * 31:29 Software defined strapping registers * 28:27 DRAM size setting (for VGA driver use) @@ -XXX,XX +XXX,XX @@ extern bool is_supported_silicon_rev(uint32_t silicon_rev); #define SCU_AST2400_HW_STRAP_GET_CLK_SOURCE(x) (((((x) >> 23) & 0x1) << 1) \ | (((x) >> 18) & 0x1)) #define SCU_AST2400_HW_STRAP_CLK_SOURCE_MASK ((0x1 << 23) | (0x1 << 18)) -#define AST2400_CLK_25M_IN (0x1 << 23) +#define SCU_HW_STRAP_CLK_25M_IN (0x1 << 23) #define AST2400_CLK_24M_IN 0 #define AST2400_CLK_48M_IN 1 #define AST2400_CLK_25M_IN_24M_USB_CKI 2 #define AST2400_CLK_25M_IN_48M_USB_CKI 3 +#define SCU_HW_STRAP_CLK_48M_IN (0x1 << 18) #define SCU_HW_STRAP_2ND_BOOT_WDT (0x1 << 17) #define SCU_HW_STRAP_SUPER_IO_CONFIG (0x1 << 16) #define SCU_HW_STRAP_VGA_CLASS_CODE (0x1 << 15) @@ -XXX,XX +XXX,XX @@ extern bool is_supported_silicon_rev(uint32_t silicon_rev); #define AST2400_DIS_BOOT 3 /* - * Hardware strapping register definition (for Aspeed AST2500 SoC and - * higher) + * SCU70 Hardware strapping register definition (for Aspeed AST2500 + * SoC and higher) * * 31 Enable SPI Flash Strap Auto Fetch Mode * 30 Enable GPIO Strap Mode diff --git a/hw/misc/aspeed_scu.c b/hw/misc/aspeed_scu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/aspeed_scu.c +++ b/hw/misc/aspeed_scu.c @@ -XXX,XX +XXX,XX @@ static uint32_t aspeed_scu_get_random(void) return num; } +static void aspeed_scu_set_apb_freq(AspeedSCUState *s) +{ + uint32_t apb_divider; + + switch (s->silicon_rev) { + case AST2400_A0_SILICON_REV: + case AST2400_A1_SILICON_REV: + apb_divider = 2; + break; + case AST2500_A0_SILICON_REV: + case AST2500_A1_SILICON_REV: + apb_divider = 4; + break; + default: + g_assert_not_reached(); + } + + s->apb_freq = s->hpll / (SCU_CLK_GET_PCLK_DIV(s->regs[CLK_SEL]) + 1) + / apb_divider; +} + static uint64_t aspeed_scu_read(void *opaque, hwaddr offset, unsigned size) { AspeedSCUState *s = ASPEED_SCU(opaque); @@ -XXX,XX +XXX,XX @@ static void aspeed_scu_write(void *opaque, hwaddr offset, uint64_t data, case PROT_KEY: s->regs[reg] = (data == ASPEED_SCU_PROT_KEY) ? 1 : 0; return; + case CLK_SEL: + s->regs[reg] = data; + aspeed_scu_set_apb_freq(s); + break; case FREQ_CNTR_EVAL: case VGA_SCRATCH1 ... VGA_SCRATCH8: @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps aspeed_scu_ops = { .valid.unaligned = false, }; +static uint32_t aspeed_scu_get_clkin(AspeedSCUState *s) +{ + if (s->hw_strap1 & SCU_HW_STRAP_CLK_25M_IN) { + return 25000000; + } else if (s->hw_strap1 & SCU_HW_STRAP_CLK_48M_IN) { + return 48000000; + } else { + return 24000000; + } +} + +/* + * Strapped frequencies for the AST2400 in MHz. They depend on the + * clkin frequency. + */ +static const uint32_t hpll_ast2400_freqs[][4] = { + { 384, 360, 336, 408 }, /* 24MHz or 48MHz */ + { 400, 375, 350, 425 }, /* 25MHz */ +}; + +static uint32_t aspeed_scu_calc_hpll_ast2400(AspeedSCUState *s) +{ + uint32_t hpll_reg = s->regs[HPLL_PARAM]; + uint8_t freq_select; + bool clk_25m_in; + + if (hpll_reg & SCU_AST2400_H_PLL_OFF) { + return 0; + } + + if (hpll_reg & SCU_AST2400_H_PLL_PROGRAMMED) { + uint32_t multiplier = 1; + + if (!(hpll_reg & SCU_AST2400_H_PLL_BYPASS_EN)) { + uint32_t n = (hpll_reg >> 5) & 0x3f; + uint32_t od = (hpll_reg >> 4) & 0x1; + uint32_t d = hpll_reg & 0xf; + + multiplier = (2 - od) * ((n + 2) / (d + 1)); + } + + return s->clkin * multiplier; + } + + /* HW strapping */ + clk_25m_in = !!(s->hw_strap1 & SCU_HW_STRAP_CLK_25M_IN); + freq_select = SCU_AST2400_HW_STRAP_GET_H_PLL_CLK(s->hw_strap1); + + return hpll_ast2400_freqs[clk_25m_in][freq_select] * 1000000; +} + +static uint32_t aspeed_scu_calc_hpll_ast2500(AspeedSCUState *s) +{ + uint32_t hpll_reg = s->regs[HPLL_PARAM]; + uint32_t multiplier = 1; + + if (hpll_reg & SCU_H_PLL_OFF) { + return 0; + } + + if (!(hpll_reg & SCU_H_PLL_BYPASS_EN)) { + uint32_t p = (hpll_reg >> 13) & 0x3f; + uint32_t m = (hpll_reg >> 5) & 0xff; + uint32_t n = hpll_reg & 0x1f; + + multiplier = ((m + 1) / (n + 1)) / (p + 1); + } + + return s->clkin * multiplier; +} + static void aspeed_scu_reset(DeviceState *dev) { AspeedSCUState *s = ASPEED_SCU(dev); const uint32_t *reset; + uint32_t (*calc_hpll)(AspeedSCUState *s); switch (s->silicon_rev) { case AST2400_A0_SILICON_REV: case AST2400_A1_SILICON_REV: reset = ast2400_a0_resets; + calc_hpll = aspeed_scu_calc_hpll_ast2400; break; case AST2500_A0_SILICON_REV: case AST2500_A1_SILICON_REV: reset = ast2500_a1_resets; + calc_hpll = aspeed_scu_calc_hpll_ast2500; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static void aspeed_scu_reset(DeviceState *dev) s->regs[HW_STRAP1] = s->hw_strap1; s->regs[HW_STRAP2] = s->hw_strap2; s->regs[PROT_KEY] = s->hw_prot_key; + + /* + * All registers are set. Now compute the frequencies of the main clocks + */ + s->clkin = aspeed_scu_get_clkin(s); + s->hpll = calc_hpll(s); + aspeed_scu_set_apb_freq(s); } static uint32_t aspeed_silicon_revs[] = { -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The System Control Unit should be initialized first as it drives all the configuration of the SoC and other device models. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Acked-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180622075700.5923-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed_soc.c | 40 ++++++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 20 deletions(-) diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) object_initialize(&s->cpu, sizeof(s->cpu), sc->info->cpu_type); object_property_add_child(obj, "cpu", OBJECT(&s->cpu), NULL); - object_initialize(&s->vic, sizeof(s->vic), TYPE_ASPEED_VIC); - object_property_add_child(obj, "vic", OBJECT(&s->vic), NULL); - qdev_set_parent_bus(DEVICE(&s->vic), sysbus_get_default()); - - object_initialize(&s->timerctrl, sizeof(s->timerctrl), TYPE_ASPEED_TIMER); - object_property_add_child(obj, "timerctrl", OBJECT(&s->timerctrl), NULL); - qdev_set_parent_bus(DEVICE(&s->timerctrl), sysbus_get_default()); - - object_initialize(&s->i2c, sizeof(s->i2c), TYPE_ASPEED_I2C); - object_property_add_child(obj, "i2c", OBJECT(&s->i2c), NULL); - qdev_set_parent_bus(DEVICE(&s->i2c), sysbus_get_default()); - object_initialize(&s->scu, sizeof(s->scu), TYPE_ASPEED_SCU); object_property_add_child(obj, "scu", OBJECT(&s->scu), NULL); qdev_set_parent_bus(DEVICE(&s->scu), sysbus_get_default()); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) object_property_add_alias(obj, "hw-prot-key", OBJECT(&s->scu), "hw-prot-key", &error_abort); + object_initialize(&s->vic, sizeof(s->vic), TYPE_ASPEED_VIC); + object_property_add_child(obj, "vic", OBJECT(&s->vic), NULL); + qdev_set_parent_bus(DEVICE(&s->vic), sysbus_get_default()); + + object_initialize(&s->timerctrl, sizeof(s->timerctrl), TYPE_ASPEED_TIMER); + object_property_add_child(obj, "timerctrl", OBJECT(&s->timerctrl), NULL); + qdev_set_parent_bus(DEVICE(&s->timerctrl), sysbus_get_default()); + + object_initialize(&s->i2c, sizeof(s->i2c), TYPE_ASPEED_I2C); + object_property_add_child(obj, "i2c", OBJECT(&s->i2c), NULL); + qdev_set_parent_bus(DEVICE(&s->i2c), sysbus_get_default()); + object_initialize(&s->fmc, sizeof(s->fmc), sc->info->fmc_typename); object_property_add_child(obj, "fmc", OBJECT(&s->fmc), NULL); qdev_set_parent_bus(DEVICE(&s->fmc), sysbus_get_default()); @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), ASPEED_SOC_SRAM_BASE, &s->sram); + /* SCU */ + object_property_set_bool(OBJECT(&s->scu), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->scu), 0, ASPEED_SOC_SCU_BASE); + /* VIC */ object_property_set_bool(OBJECT(&s->vic), true, "realized", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->timerctrl), i, irq); } - /* SCU */ - object_property_set_bool(OBJECT(&s->scu), true, "realized", &err); - if (err) { - error_propagate(errp, err); - return; - } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->scu), 0, ASPEED_SOC_SCU_BASE); - /* UART - attach an 8250 to the IO space as our UART5 */ if (serial_hd(0)) { qemu_irq uart5 = qdev_get_gpio_in(DEVICE(&s->vic), uart_irqs[4]); -- 2.17.1 From: Cédric Le Goater <clg@kaod.org> The timer controller can be driven by either an external 1MHz clock or by the APB clock. Today, the model makes the assumption that the APB frequency is always set to 24MHz but this is incorrect. The AST2400 SoC on the palmetto machines uses a 48MHz input clock source and the APB can be set to 48MHz. The consequence is a general system slowdown. The QEMU machines using the AST2500 SoC do not seem impacted today because the APB frequency is still set to 24MHz. We fix the timer frequency for all SoCs by linking the Timer model to the SCU model. The APB frequency driving the timers is now the one configured for the SoC. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20180622075700.5923-4-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/timer/aspeed_timer.h | 4 ++++ hw/arm/aspeed_soc.c | 2 ++ hw/timer/aspeed_timer.c | 19 +++++++++++++++---- 3 files changed, 21 insertions(+), 4 deletions(-) diff --git a/include/hw/timer/aspeed_timer.h b/include/hw/timer/aspeed_timer.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/aspeed_timer.h +++ b/include/hw/timer/aspeed_timer.h @@ -XXX,XX +XXX,XX @@ #include "qemu/timer.h" +typedef struct AspeedSCUState AspeedSCUState; + #define ASPEED_TIMER(obj) \ OBJECT_CHECK(AspeedTimerCtrlState, (obj), TYPE_ASPEED_TIMER); #define TYPE_ASPEED_TIMER "aspeed.timer" @@ -XXX,XX +XXX,XX @@ typedef struct AspeedTimerCtrlState { uint32_t ctrl; uint32_t ctrl2; AspeedTimer timers[ASPEED_TIMER_NR_TIMERS]; + + AspeedSCUState *scu; } AspeedTimerCtrlState; #endif /* ASPEED_TIMER_H */ diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) object_initialize(&s->timerctrl, sizeof(s->timerctrl), TYPE_ASPEED_TIMER); object_property_add_child(obj, "timerctrl", OBJECT(&s->timerctrl), NULL); + object_property_add_const_link(OBJECT(&s->timerctrl), "scu", + OBJECT(&s->scu), &error_abort); qdev_set_parent_bus(DEVICE(&s->timerctrl), sysbus_get_default()); object_initialize(&s->i2c, sizeof(s->i2c), TYPE_ASPEED_I2C); diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qapi/error.h" #include "hw/sysbus.h" #include "hw/timer/aspeed_timer.h" +#include "hw/misc/aspeed_scu.h" #include "qemu-common.h" #include "qemu/bitops.h" #include "qemu/timer.h" @@ -XXX,XX +XXX,XX @@ #define TIMER_CLOCK_USE_EXT true #define TIMER_CLOCK_EXT_HZ 1000000 #define TIMER_CLOCK_USE_APB false -#define TIMER_CLOCK_APB_HZ 24000000 #define TIMER_REG_STATUS 0 #define TIMER_REG_RELOAD 1 @@ -XXX,XX +XXX,XX @@ static inline bool timer_external_clock(AspeedTimer *t) return timer_ctrl_status(t, op_external_clock); } -static uint32_t clock_rates[] = { TIMER_CLOCK_APB_HZ, TIMER_CLOCK_EXT_HZ }; - static inline uint32_t calculate_rate(struct AspeedTimer *t) { - return clock_rates[timer_external_clock(t)]; + AspeedTimerCtrlState *s = timer_to_ctrl(t); + + return timer_external_clock(t) ? TIMER_CLOCK_EXT_HZ : s->scu->apb_freq; } static inline uint32_t calculate_ticks(struct AspeedTimer *t, uint64_t now_ns) @@ -XXX,XX +XXX,XX @@ static void aspeed_timer_realize(DeviceState *dev, Error **errp) int i; SysBusDevice *sbd = SYS_BUS_DEVICE(dev); AspeedTimerCtrlState *s = ASPEED_TIMER(dev); + Object *obj; + Error *err = NULL; + + obj = object_property_get_link(OBJECT(dev), "scu", &err); + if (!obj) { + error_propagate(errp, err); + error_prepend(errp, "required link 'scu' not found: "); + return; + } + s->scu = ASPEED_SCU(obj); for (i = 0; i < ASPEED_TIMER_NR_TIMERS; i++) { aspeed_init_one_timer(s, i); -- 2.17.1