5 files changed, 319 insertions, 0 deletions
diff --git a/results/classifier/118/TCG-x86/1147 b/results/classifier/118/TCG-x86/1147
new file mode 100644
index 000000000..108952809
--- /dev/null
+++ b/results/classifier/118/TCG-x86/1147
@@ -0,0 +1,69 @@
+x86: 0.933
+graphic: 0.900
+TCG: 0.840
+architecture: 0.777
+kernel: 0.703
+device: 0.693
+semantic: 0.499
+performance: 0.412
+vnc: 0.406
+ppc: 0.406
+arm: 0.332
+risc-v: 0.299
+user-level: 0.282
+PID: 0.280
+register: 0.277
+socket: 0.259
+files: 0.242
+mistranslation: 0.234
+permissions: 0.232
+boot: 0.189
+debug: 0.165
+VMM: 0.144
+virtual: 0.097
+network: 0.074
+peripherals: 0.073
+assembly: 0.069
+hypervisor: 0.057
+i386: 0.020
+KVM: 0.003
+--------------------
+x86: 0.986
+kernel: 0.889
+TCG: 0.448
+hypervisor: 0.176
+debug: 0.109
+virtual: 0.027
+files: 0.026
+user-level: 0.018
+architecture: 0.016
+register: 0.016
+performance: 0.015
+PID: 0.015
+device: 0.011
+arm: 0.006
+VMM: 0.006
+boot: 0.005
+KVM: 0.004
+assembly: 0.002
+semantic: 0.002
+socket: 0.002
+network: 0.002
+ppc: 0.001
+peripherals: 0.001
+graphic: 0.001
+permissions: 0.001
+vnc: 0.000
+risc-v: 0.000
+mistranslation: 0.000
+i386: 0.000
+
+x86_64 emu on aarch64 host: cpu_exec: assertion failed: (cpu == current_cpu)
+Description of problem:
+Execution of some binaries crashes with `Bail out! ERROR:../qemu-7.0.0/accel/tcg/cpu-exec.c:933:cpu_exec: assertion failed: (cpu == current_cpu)`. Looking at the code, that code is wrapped in a gcc/clang ifdef. Recompiling with clang produces this crash instead: `... include/qemu/rcu.h:102: void rcu_read_unlock(void): Assertion 'p_rcu_reader->depth != 0' failed.`
+
+No easier steps to reproduce (yet) than `systemd-nspawn`ing into an x86_64 Ubuntu container invoking qemu-x86_64-static through binfmt. Commands such as `ls` work fine, while `apt-get` will immediately crash with the error listed above.
+
+Note that this happens running Asahi Linux on the bare metal of an M1-based Macbook Pro. This same issue does *not* occur running the *same* binaries with the *same* x86_64 Ubuntu image on an Arch or Ubuntu VM under macOS on the same machine - regardless of if the QEMU binaries were built in a VM or in Asahi.
+
+These are big.LITTLE chips. Using taskset/affinity to limit the target process to a single specific core does not help. The Asahi kernel has a 16K page-size, which is known to cause trouble for some programs. qemu-arm(-static) however works without any issues (the M1 cannot run 32-bit ARM code natively, only 64-bit).
diff --git a/results/classifier/118/TCG-x86/1351 b/results/classifier/118/TCG-x86/1351
new file mode 100644
index 000000000..0359131f5
--- /dev/null
+++ b/results/classifier/118/TCG-x86/1351
@@ -0,0 +1,65 @@
+x86: 0.998
+i386: 0.997
+TCG: 0.879
+graphic: 0.867
+device: 0.822
+semantic: 0.643
+network: 0.632
+mistranslation: 0.612
+vnc: 0.594
+architecture: 0.533
+performance: 0.506
+PID: 0.375
+peripherals: 0.353
+debug: 0.333
+ppc: 0.313
+socket: 0.294
+user-level: 0.289
+register: 0.275
+hypervisor: 0.270
+files: 0.223
+arm: 0.223
+VMM: 0.211
+risc-v: 0.184
+assembly: 0.132
+virtual: 0.126
+boot: 0.118
+permissions: 0.105
+kernel: 0.104
+KVM: 0.003
+--------------------
+x86: 0.991
+virtual: 0.908
+TCG: 0.672
+hypervisor: 0.536
+debug: 0.290
+i386: 0.076
+files: 0.050
+assembly: 0.050
+user-level: 0.046
+kernel: 0.026
+performance: 0.025
+register: 0.024
+PID: 0.022
+semantic: 0.020
+mistranslation: 0.018
+device: 0.017
+boot: 0.011
+graphic: 0.009
+VMM: 0.005
+architecture: 0.004
+network: 0.004
+socket: 0.003
+risc-v: 0.003
+peripherals: 0.002
+KVM: 0.002
+permissions: 0.001
+vnc: 0.001
+ppc: 0.000
+arm: 0.000
+
+qemu-system-x86_64  run win7 qcow2 got an exception
+Description of problem:
+when qemu-system-X86-64 run the win7 qcow2,  qemu got an exception
+
+\*\* ERROR:../target/i386/tcg/sysemu/excp_helper.c:517:raise_stage2: code should not be reached Aborted (核心已转储)
diff --git a/results/classifier/118/TCG-x86/164 b/results/classifier/118/TCG-x86/164
new file mode 100644
index 000000000..132dfd387
--- /dev/null
+++ b/results/classifier/118/TCG-x86/164
@@ -0,0 +1,61 @@
+TCG: 0.938
+x86: 0.933
+architecture: 0.924
+device: 0.877
+network: 0.612
+arm: 0.603
+peripherals: 0.536
+mistranslation: 0.459
+graphic: 0.424
+performance: 0.383
+semantic: 0.347
+permissions: 0.339
+kernel: 0.311
+hypervisor: 0.292
+user-level: 0.272
+socket: 0.235
+i386: 0.223
+register: 0.206
+risc-v: 0.205
+files: 0.200
+boot: 0.186
+debug: 0.179
+virtual: 0.166
+vnc: 0.153
+ppc: 0.136
+VMM: 0.094
+PID: 0.094
+assembly: 0.081
+KVM: 0.010
+--------------------
+x86: 0.998
+virtual: 0.980
+TCG: 0.956
+i386: 0.935
+hypervisor: 0.931
+architecture: 0.424
+semantic: 0.045
+user-level: 0.040
+performance: 0.030
+device: 0.025
+files: 0.016
+assembly: 0.015
+KVM: 0.015
+debug: 0.008
+boot: 0.007
+register: 0.006
+kernel: 0.006
+VMM: 0.004
+PID: 0.002
+network: 0.002
+graphic: 0.002
+peripherals: 0.002
+socket: 0.001
+risc-v: 0.001
+permissions: 0.001
+mistranslation: 0.001
+vnc: 0.000
+ppc: 0.000
+arm: 0.000
+
+qemu x86 TCG doesn't support AVX insns
diff --git a/results/classifier/118/TCG-x86/2096 b/results/classifier/118/TCG-x86/2096
new file mode 100644
index 000000000..59bb72c1b
--- /dev/null
+++ b/results/classifier/118/TCG-x86/2096
@@ -0,0 +1,61 @@
+x86: 0.975
+TCG: 0.973
+device: 0.854
+performance: 0.700
+network: 0.581
+arm: 0.504
+architecture: 0.421
+graphic: 0.415
+i386: 0.389
+boot: 0.263
+semantic: 0.227
+kernel: 0.189
+peripherals: 0.174
+permissions: 0.173
+register: 0.171
+ppc: 0.164
+mistranslation: 0.159
+hypervisor: 0.139
+vnc: 0.129
+PID: 0.109
+files: 0.103
+debug: 0.097
+socket: 0.084
+user-level: 0.077
+VMM: 0.076
+virtual: 0.059
+assembly: 0.051
+risc-v: 0.035
+KVM: 0.028
+--------------------
+x86: 0.998
+TCG: 0.926
+i386: 0.912
+architecture: 0.828
+PID: 0.302
+debug: 0.117
+kernel: 0.083
+user-level: 0.043
+virtual: 0.028
+files: 0.025
+semantic: 0.020
+register: 0.016
+performance: 0.015
+device: 0.012
+assembly: 0.011
+boot: 0.003
+socket: 0.002
+peripherals: 0.002
+hypervisor: 0.002
+graphic: 0.002
+permissions: 0.001
+VMM: 0.001
+KVM: 0.001
+risc-v: 0.001
+mistranslation: 0.001
+network: 0.000
+vnc: 0.000
+ppc: 0.000
+arm: 0.000
+
+test-x86-cpuid-compat qtest produces warnings on TCG
diff --git a/results/classifier/118/TCG-x86/2381 b/results/classifier/118/TCG-x86/2381
new file mode 100644
index 000000000..4027b7a46
--- /dev/null
+++ b/results/classifier/118/TCG-x86/2381
@@ -0,0 +1,63 @@
+x86: 0.993
+TCG: 0.979
+device: 0.876
+graphic: 0.776
+architecture: 0.594
+arm: 0.506
+semantic: 0.505
+boot: 0.481
+network: 0.474
+register: 0.447
+mistranslation: 0.416
+socket: 0.389
+performance: 0.353
+risc-v: 0.323
+permissions: 0.315
+ppc: 0.264
+kernel: 0.250
+vnc: 0.233
+PID: 0.225
+debug: 0.205
+hypervisor: 0.148
+assembly: 0.138
+peripherals: 0.103
+files: 0.101
+VMM: 0.100
+virtual: 0.090
+user-level: 0.087
+KVM: 0.028
+i386: 0.003
+--------------------
+x86: 0.998
+TCG: 0.933
+kernel: 0.701
+i386: 0.343
+assembly: 0.285
+performance: 0.270
+device: 0.027
+files: 0.023
+virtual: 0.020
+register: 0.019
+user-level: 0.019
+debug: 0.016
+architecture: 0.016
+boot: 0.014
+semantic: 0.012
+hypervisor: 0.007
+VMM: 0.005
+peripherals: 0.005
+permissions: 0.004
+KVM: 0.003
+network: 0.002
+risc-v: 0.002
+graphic: 0.002
+vnc: 0.001
+socket: 0.001
+PID: 0.001
+ppc: 0.000
+mistranslation: 0.000
+arm: 0.000
+
+Modern x86 TSC features under TCG
+Additional information:
+I may be able to find a volunteer to implement this. If this feature does not appear to be a good first task, please let me know.