x86/cpufeatures: Enumerate #DB for bus lock detection
mainline inclusion from mainline-v5.12-rc4 commit f21d4d3b category: feature bugzilla: https://gitee.com/openeuler/intel-kernel/issues/I5G10C CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/ commit/?id=f21d4d3b Intel-SIG: commit f21d4d3b x86/cpufeatures: Enumerate #DB for bus lock detection -------------------------------- A bus lock is acquired through either a split locked access to writeback (WB) memory or any locked access to non-WB memory. This is typically >1000 cycles slower than an atomic operation within a cache line. It also disrupts performance on other cores. Some CPUs have the ability to notify the kernel by a #DB trap after a user instruction acquires a bus lock and is executed. This allows the kernel to enforce user application throttling or mitigation. Both breakpoint and bus lock can trigger the #DB trap in the same instruction and the ordering of handling them is the kernel #DB handler's choice. The CPU feature flag to be shown in /proc/cpuinfo will be "bus_lock_detect". Signed-off-by: NFenghua Yu <fenghua.yu@intel.com> Signed-off-by: NThomas Gleixner <tglx@linutronix.de> Reviewed-by: NTony Luck <tony.luck@intel.com> Link: https://lore.kernel.org/r/20210322135325.682257-2-fenghua.yu@intel.com (cherry picked from commit f21d4d3b) Signed-off-by: NEthan Zhao <haifeng.zhao@linux.intel.com>
Showing
想要评论请 注册 或 登录