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.
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.
-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
|