From 39ec58f3fea47c242724109cc1da999f74810bbc Mon Sep 17 00:00:00 2001 From: Lennert Buytenhek Date: Mon, 9 Mar 2009 14:30:09 -0400 Subject: [ARM] alternative copy_to_user/clear_user implementation This implements {copy_to,clear}_user() by faulting in the userland pages and then using the regular kernel mem{cpy,set}() to copy the data (while holding the page table lock). This is a win if the regular mem{cpy,set}() implementations are faster than the user copy functions, which is the case e.g. on Feroceon, where 8-word STMs (which memcpy() uses under the right conditions) give significantly higher memory write throughput than a sequence of individual 32bit stores. Here are numbers for page sized buffers on some Feroceon cores: - copy_to_user on Orion5x goes from 51 MB/s to 83 MB/s - clear_user on Orion5x goes from 89MB/s to 314MB/s - copy_to_user on Kirkwood goes from 240 MB/s to 356 MB/s - clear_user on Kirkwood goes from 367 MB/s to 1108 MB/s - copy_to_user on Disco-Duo goes from 248 MB/s to 398 MB/s - clear_user on Disco-Duo goes from 328 MB/s to 1741 MB/s Because the setup cost is non negligible, this is worthwhile only if the amount of data to copy is large enough. The operation falls back to the standard implementation when the amount of data is below a certain threshold. This threshold was determined empirically, however some targets could benefit from a lower runtime determined value for optimal results eventually. In the copy_from_user() case, this technique does not provide any worthwhile performance gain due to the fact that any kind of read access allocates the cache and subsequent 32bit loads are just as fast as the equivalent 8-word LDM. Signed-off-by: Lennert Buytenhek Signed-off-by: Nicolas Pitre Tested-by: Martin Michlmayr --- arch/arm/Kconfig | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'arch/arm/Kconfig') diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 9d02cdb15b23..c63e65d436a3 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -1085,6 +1085,22 @@ config ALIGNMENT_TRAP correct operation of some network protocols. With an IP-only configuration it is safe to say N, otherwise say Y. +config UACCESS_WITH_MEMCPY + bool "Use kernel mem{cpy,set}() for {copy_to,clear}_user() (EXPERIMENTAL)" + depends on MMU && EXPERIMENTAL + default y if CPU_FEROCEON + help + Implement faster copy_to_user and clear_user methods for CPU + cores where a 8-word STM instruction give significantly higher + memory write throughput than a sequence of individual 32bit stores. + + A possible side effect is a slight increase in scheduling latency + between threads sharing the same address space if they invoke + such copy operations with large buffers. + + However, if the CPU data cache is using a write-allocate mode, + this option is unlikely to provide any performance gain. + endmenu menu "Boot options" -- cgit v1.2.3