summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2009-03-02 11:00:57 +0100
committerIngo Molnar <mingo@elte.hu>2009-03-02 11:06:49 +0100
commitf180053694b43d5714bf56cb95499a3c32ff155c (patch)
tree00286fcc88d2842629b039da4009a1332b3a1719
parent34754b69a6f87aa6aa2860525a82f12532f83afd (diff)
downloadop-kernel-dev-f180053694b43d5714bf56cb95499a3c32ff155c.zip
op-kernel-dev-f180053694b43d5714bf56cb95499a3c32ff155c.tar.gz
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 <sqazi@google.com> Cc: Nick Piggin <npiggin@suse.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
-rw-r--r--arch/x86/include/asm/uaccess_32.h4
-rw-r--r--arch/x86/include/asm/uaccess_64.h25
-rw-r--r--drivers/gpu/drm/i915/i915_gem.c2
-rw-r--r--include/linux/uaccess.h4
-rw-r--r--mm/filemap.c11
-rw-r--r--mm/filemap_xip.c2
6 files changed, 17 insertions, 31 deletions
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index a0ba613..5e06259 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -157,7 +157,7 @@ __copy_from_user(void *to, const void __user *from, unsigned long n)
}
static __always_inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n, unsigned long total)
+ const void __user *from, unsigned long n)
{
might_fault();
if (__builtin_constant_p(n)) {
@@ -180,7 +180,7 @@ static __always_inline unsigned long __copy_from_user_nocache(void *to,
static __always_inline unsigned long
__copy_from_user_inatomic_nocache(void *to, const void __user *from,
- unsigned long n, unsigned long total)
+ unsigned long n)
{
return __copy_from_user_ll_nocache_nozero(to, from, n);
}
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index dcaa0404..8cc6873 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -188,29 +188,18 @@ __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
extern long __copy_user_nocache(void *dst, const void __user *src,
unsigned size, int zerorest);
-static inline int __copy_from_user_nocache(void *dst, const void __user *src,
- unsigned size, unsigned long total)
+static inline int
+__copy_from_user_nocache(void *dst, const void __user *src, unsigned size)
{
might_sleep();
- /*
- * In practice this limit means that large file write()s
- * which get chunked to 4K copies get handled via
- * non-temporal stores here. Smaller writes get handled
- * via regular __copy_from_user():
- */
- if (likely(total >= PAGE_SIZE))
- return __copy_user_nocache(dst, src, size, 1);
- else
- return __copy_from_user(dst, src, size);
+ return __copy_user_nocache(dst, src, size, 1);
}
-static inline int __copy_from_user_inatomic_nocache(void *dst,
- const void __user *src, unsigned size, unsigned total)
+static inline int
+__copy_from_user_inatomic_nocache(void *dst, const void __user *src,
+ unsigned size)
{
- if (likely(total >= PAGE_SIZE))
- return __copy_user_nocache(dst, src, size, 0);
- else
- return __copy_from_user_inatomic(dst, src, size);
+ return __copy_user_nocache(dst, src, size, 0);
}
unsigned long
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 6b209db..8185766 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -215,7 +215,7 @@ fast_user_write(struct io_mapping *mapping,
vaddr_atomic = io_mapping_map_atomic_wc(mapping, page_base);
unwritten = __copy_from_user_inatomic_nocache(vaddr_atomic + page_offset,
- user_data, length, length);
+ user_data, length);
io_mapping_unmap_atomic(vaddr_atomic);
if (unwritten)
return -EFAULT;
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 6f3c603..6b58367 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -41,13 +41,13 @@ static inline void pagefault_enable(void)
#ifndef ARCH_HAS_NOCACHE_UACCESS
static inline unsigned long __copy_from_user_inatomic_nocache(void *to,
- const void __user *from, unsigned long n, unsigned long total)
+ const void __user *from, unsigned long n)
{
return __copy_from_user_inatomic(to, from, n);
}
static inline unsigned long __copy_from_user_nocache(void *to,
- const void __user *from, unsigned long n, unsigned long total)
+ const void __user *from, unsigned long n)
{
return __copy_from_user(to, from, n);
}
diff --git a/mm/filemap.c b/mm/filemap.c
index 60fd567..126d397 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,
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index bf54f8a..0c04615 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -354,7 +354,7 @@ __xip_file_write(struct file *filp, const char __user *buf,
break;
copied = bytes -
- __copy_from_user_nocache(xip_mem + offset, buf, bytes, bytes);
+ __copy_from_user_nocache(xip_mem + offset, buf, bytes);
if (likely(copied > 0)) {
status = copied;
OpenPOWER on IntegriCloud