A bus lock [1] is acquired either through split locked access to writeback (WB) memory or by using locks to uncacheable (UC) memory (e.g. direct device assignment). This is typically >1000 cycles slower than an atomic operation within a cache line. It also disrupts performance on other cores.
Although split lock can be detected by #AC trap, the trap is triggered before the instruction acquires bus lock. This makes it difficult to mitigate bus lock (e.g. throttle the user application). Some CPUs have ability to notify the kernel by an #DB trap after a user instruction acquires a bus lock and is executed. This allows the kernel to enforce user application throttling or mitigations. #DB for bus lock detect fixes issues in #AC for split lock detect: 1) It's architectural ... just need to look at one CPUID bit to know it exists 2) The IA32_DEBUGCTL MSR, which reports bus lock in #DB, is per-thread. So each process or guest can have different behavior. 3) It has support for VMM/guests (new VMEXIT codes, etc). Hardware only generates #DB for bus lock detect when CPL>0 to avoid nested #DB from multiple bus locks while the first #DB is being handled. Use the existing kernel command line option "split_lock_detect=" to handle #DB for bus lock: split_lock_detect= #AC for split lock #DB for bus lock off Do nothing Do nothing warn Kernel OOPs Warn once per task and Warn once per task and and continues to run. disable future checking When both features are supported, warn in #DB fatal Kernel OOPs Send SIGBUS to user Send SIGBUS to user When both features are supported, fatal in #AC. ratelimit:N Do nothing Limit bus lock rate to N per second in the current non root user. Default split_lock_detect is "warn". [1] Chapter 8 https://software.intel.com/sites/default/files/managed/c5/15/architecture-instruction-set-extensions-programming-reference.pdf Change Log: RFC v2: - Architecture changed based on feedback from Thomas and PeterZ. #DB is no longer generated for bus lock in ring0. - Split the one single patch into four patches. [RFC v1 can be found at: https://lore.kernel.org/lkml/1595021700-68460-1-git-send-email-fenghua...@intel.com/] Fenghua Yu (4): x86/cpufeatures: Enumerate #DB for bus lock detection x86/bus_lock: Handle warn and fatal in #DB for bus lock x86/bus_lock: Set rate limit for bus lock Documentation: Change doc for split_lock_detect parameter .../admin-guide/kernel-parameters.txt | 47 +++++- arch/x86/include/asm/cpu.h | 10 +- arch/x86/include/asm/cpufeatures.h | 1 + arch/x86/include/asm/msr-index.h | 1 + arch/x86/include/uapi/asm/debugreg.h | 3 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/cpu/intel.c | 145 +++++++++++++++--- arch/x86/kernel/traps.c | 7 + include/linux/sched/user.h | 4 +- kernel/user.c | 7 + 10 files changed, 193 insertions(+), 34 deletions(-) -- 2.29.0