Messages in this thread | | | Date | Mon, 22 Apr 2024 16:09:33 +0800 | From | Yujie Liu <> | Subject | Re: [PATCH v4 1/5] x86/bugs: Only harden syscalls when needed |
| |
On Fri, Apr 19, 2024 at 02:09:47PM -0700, Josh Poimboeuf wrote: > Syscall hardening (converting the syscall indirect branch to a series of > direct branches) has shown some performance regressions: > > - Red Hat internal testing showed up to 12% slowdowns in database > benchmark testing on Sapphire Rapids when the DB was stressed with 80+ > users to cause contention. > > - The kernel test robot's will-it-scale benchmarks showed significant > regressions on Skylake with IBRS: > https://lkml.kernel.org/lkml/202404191333.178a0eed-yujie.liu@intel.com
To clarify, we reported a +1.4% improvement (not regression) of will-it-scale futex4 benchmark on Skylake. Meanwhile we did observe some regressions by running other benchmarks on Ice Lake, such as:
stress-ng.null.ops_per_sec -4.0% regression on Intel Xeon Gold 6346 (Ice Lake) unixbench.fsbuffer.throughput -1.4% regression on Intel Xeon Gold 6346 (Ice Lake)
> > To fix those slowdowns, only use the syscall direct branches when > indirect branches are considered to be "not OK": meaning Spectre v2+BHI > isn't mitigated by HW and the user hasn't disabled mitigations.
| |