Re: [PATCH v2] x86, uaccess: introduce copy_from_iter_wt for pmem / writethrough operations

On Fri, Apr 28, 2017 at 12:39:12PM -0700, Dan Williams wrote: > The pmem driver has a need to transfer data with a persistent memory > destination and be able to rely on the fact that the destination writes > are not cached. It is sufficient for the writes to be flushed to a > cpu-store-buffer (non-temporal / "movnt" in x86 terms), as we expect > userspace to call fsync() to ensure data-writes have reached a > power-fail-safe zone in the platform. The fsync() triggers a REQ_FUA or > REQ_FLUSH to the pmem driver which will turn around and fence previous > writes with an "sfence". > > Implement a __copy_from_user_inatomic_wt, memcpy_page_wt, and memcpy_wt, > that guarantee that the destination buffer is not dirty in the cpu cache > on completion. The new copy_from_iter_wt and sub-routines will be used > to replace the "pmem api" (include/linux/pmem.h + > arch/x86/include/asm/pmem.h). The availability of copy_from_iter_wt() > and memcpy_wt() are gated by the CONFIG_ARCH_HAS_UACCESS_WT config > symbol, and fallback to copy_from_iter_nocache() and plain memcpy() > otherwise. > > This is meant to satisfy the concern from Linus that if a driver wants > to do something beyond the normal nocache semantics it should be > something private to that driver [1], and Al's concern that anything > uaccess related belongs with the rest of the uaccess code [2]. > > [1]: https://lists.01.org/pipermail/linux-nvdimm/2017-January/008364.html > [2]: https://lists.01.org/pipermail/linux-nvdimm/2017-April/009942.html > > Cc: <x86(a)kernel.org&gt; > Cc: Jan Kara <jack(a)suse.cz&gt; > Cc: Jeff Moyer <jmoyer(a)redhat.com&gt; > Cc: Ingo Molnar <mingo(a)redhat.com&gt; > Cc: Christoph Hellwig <hch(a)lst.de&gt; > Cc: "H. Peter Anvin" <hpa(a)zytor.com&gt; > Cc: Al Viro <viro(a)zeniv.linux.org.uk&gt; > Cc: Thomas Gleixner <tglx(a)linutronix.de&gt; > Cc: Matthew Wilcox <mawilcox(a)microsoft.com&gt; > Cc: Ross Zwisler <ross.zwisler(a)linux.intel.com&gt; > Signed-off-by: Dan Williams <dan.j.williams(a)intel.com&gt;

I took a pretty hard look at the changes in arch/x86/lib/usercopy_64.c, and they look correct to me. The inline assembly for non-temporal copies mixed with C for loop control is IMHO much easier to follow than the pure assembly of __copy_user_nocache(). Reviewed-by: Ross Zwisler <ross.zwisler(a)linux.intel.com&gt;