rr (http://rr-project.org/), a userspace record-and-replay reverse- execution debugger, would like to trap and emulate the CPUID instruction. This would allow us to a) mask away certain hardware features that rr does not support (e.g. RDRAND) and b) enable trace portability across machines by providing constant results. Newer Intel CPUs (Ivy Bridge and later) can fault when CPUID is executed at CPL > 0. Expose this capability to userspace as a new pair of arch_prctls, ARCH_GET_CPUID and ARCH_SET_CPUID, with two values, ARCH_CPUID_ENABLE and ARCH_CPUID_SIGSEGV. The following changes have been made since v3: Patch 1 was split into patches 1-4, patches 2 and 3 became patches 5 and 6, respectively. Patch 1: - Use SYSCALL_DEFINE in UML. Patch 2: - More descriptive commit message. Patch 3: - More decriptive commit message. - Name the common arch_prctl function do_arch_prctl instead of do_arch_prctl_common Patch 4: - Move the 32-bit syscall entry point to process_32.c, place the compat entry point in process_64.c Patch 5 (previously Patch 2): - More descriptive commit message. - Prefix the #define for the cpuid faulting bit with PLATINFO - supports_cpuid_faulting returns bool - Rearrange supports_cpuid_faulting to avoid linebreaks Patch 6 (previously Patch 3): - ARCH_GET_CPUID now takes 0 for the second argument, and returns the result directly. - arch_post_exec is now a #define, called from setup_new_exec - The test now uses errx - The test now checks that ARCH_GET_CPUID returns ARCH_CPUID_SIGSEGV after fork() -- To unsubscribe from this list: send the line "unsubscribe linux-kselftest" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
