From f180053694b43d5714bf56cb95499a3c32ff155c Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Mon, 2 Mar 2009 11:00:57 +0100 Subject: x86, mm: dont use non-temporal stores in pagecache accesses Impact: standardize IO on cached ops On modern CPUs it is almost always a bad idea to use non-temporal stores, as the regression in this commit has shown it: 30d697f: x86: fix performance regression in write() syscall The kernel simply has no good information about whether using non-temporal stores is a good idea or not - and trying to add heuristics only increases complexity and inserts fragility. The regression on cached write()s took very long to be found - over two years. So dont take any chances and let the hardware decide how it makes use of its caches. The only exception is drivers/gpu/drm/i915/i915_gem.c: there were we are absolutely sure that another entity (the GPU) will pick up the dirty data immediately and that the CPU will not touch that data before the GPU will. Also, keep the _nocache() primitives to make it easier for people to experiment with these details. There may be more clear-cut cases where non-cached copies can be used, outside of filemap.c. Cc: Salman Qazi Cc: Nick Piggin Cc: Linus Torvalds Signed-off-by: Ingo Molnar --- mm/filemap.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-) (limited to 'mm/filemap.c') diff --git a/mm/filemap.c b/mm/filemap.c index 60fd56772cc..126d3973b3d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1816,14 +1816,14 @@ EXPORT_SYMBOL(file_remove_suid); static size_t __iovec_copy_from_user_inatomic(char *vaddr, const struct iovec *iov, size_t base, size_t bytes) { - size_t copied = 0, left = 0, total = bytes; + size_t copied = 0, left = 0; while (bytes) { char __user *buf = iov->iov_base + base; int copy = min(bytes, iov->iov_len - base); base = 0; - left = __copy_from_user_inatomic_nocache(vaddr, buf, copy, total); + left = __copy_from_user_inatomic(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; @@ -1851,9 +1851,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - - left = __copy_from_user_inatomic_nocache(kaddr + offset, - buf, bytes, bytes); + left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, @@ -1881,8 +1879,7 @@ size_t iov_iter_copy_from_user(struct page *page, if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; - - left = __copy_from_user_nocache(kaddr + offset, buf, bytes, bytes); + left = __copy_from_user(kaddr + offset, buf, bytes); copied = bytes - left; } else { copied = __iovec_copy_from_user_inatomic(kaddr + offset, -- cgit v1.2.3