On 08/03/18 16:06, Jan Beulich wrote: >>>> On 02.03.18 at 09:14, <jgr...@suse.com> wrote: >> @@ -123,22 +142,14 @@ unsigned int flush_area_local(const void *va, unsigned >> int flags) >> u32 t = pre_flush(); >> >> if ( !cpu_has_invpcid ) >> - { >> - unsigned long cr4 = read_cr4(); >> - >> - write_cr4(cr4 & ~X86_CR4_PGE); >> - barrier(); >> - write_cr4(cr4); >> - } >> + do_flush_tlb(0); >> else >> - { >> /* >> * Using invpcid to flush all mappings works >> * regardless of whether PCID is enabled or not. >> * It is faster than read-modify-write CR4. >> */ >> invpcid_flush_all(); >> - } > > Btw, this is correct for FLUSH_TLB_GLOBAL, but goes too far for > FLUSH_TLB.
You are aware that my patches didn't change anything in this regard? Juergen _______________________________________________ Xen-devel mailing list Xen-devel@lists.xenproject.org https://lists.xenproject.org/mailman/listinfo/xen-devel