Commit f1800536 authored by Ingo Molnar's avatar Ingo Molnar
Browse files

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:

  30d697fa: 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: default avatarIngo Molnar <mingo@elte.hu>
parent 34754b69

arch/x86/include/asm/uaccess_32.h

+2 −2
Original line number Diff line number Diff line
@@ -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);

}

arch/x86/include/asm/uaccess_64.h

+7 −18
Original line number Diff line number Diff line
@@ -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);

}



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);

}



unsigned long

drivers/gpu/drm/i915/i915_gem.c

+1 −1
Original line number Diff line number Diff line
@@ -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;

include/linux/uaccess.h

+2 −2
Original line number Diff line number Diff line
@@ -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);

}

mm/filemap.c

+4 −7
Original line number Diff line number Diff line
@@ -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,

CRA Git | Maintained and supported by SUSTech CRA and CCSE