On Thu, Jun 14, 2012 at 2:20 AM, Tony Luck <tony.luck@xxxxxxxxx> wrote: > On Tue, Jun 12, 2012 at 8:51 AM, Kautuk Consul <consul.kautuk@xxxxxxxxx> wrote: >>> + mask = ((((isr >> IA64_ISR_X_BIT) & 1UL) << VM_EXEC_BIT) >>> + | (((isr >> IA64_ISR_W_BIT) & 1UL) << VM_WRITE_BIT)); > > You added these uses of VM_EXEC_BIT and VM_WRITE_BIT ... but > these macros are not defined until a few lines later in this file. I moved > them (and the VM_READ_BIT definition) up to just before the > start of ia64_do_page_fault() to fix the compilation errors. No need > to re-submit a fixed patch. > Thanks for the help, Tony ! Terribly sorry for my mistakes as I don't have an ia64 system. > Do you know if the test program mentioned in > d065bd810b6deb67d4897a14bfe21f8eb526ba99: > - microbenchmark: thread A mmaps a large file and does random read accesses > to the mmaped area - achieves about 55 iterations/s. Thread B does > mmap/munmap in a loop at a separate location - achieves 55 iterations/s > before, 15000 iterations/s after. > was posted? I'd like to make sure that ia64 is seeing the benefit. I couldn't find any test-case for that, but I tested in for ARM and MIPS where I was seeing hangs and livelocks. Maybe you can try my test-case at https://lkml.org/lkml/2012/3/31/90 ? > > -Tony -- To unsubscribe from this list: send the line "unsubscribe linux-ia64" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html