linux-stable/include/linux/pagevec.h
Matthew Wilcox (Oracle) 9cecde80aa mm: increase folio batch size
On a 104 thread, 2 socket Skylake system, Intel report a 4.7% performance
reduction with will-it-scale page_fault2.  This was due to reducing the
size of the batch from 32 to 15.  Increasing the folio batch size from 15
to 31 gives a performance increase of 12.5% relative to the original, or
17.2% relative to the reduced performance commit.

The penalty of this commit is an additional 128 bytes of stack usage.  Six
folio_batches are also allocated from percpu memory in cpu_fbatches so
that will be an additional 768 bytes of percpu memory (per CPU).  Tim Chen
originally submitted a patch like this in 2020:
https://lore.kernel.org/linux-mm/d1cc9f12a8ad6c2a52cb600d93b06b064f2bbc57.1593205965.git.tim.c.chen@linux.intel.com/

Link: https://lkml.kernel.org/r/20240315140823.2478146-1-willy@infradead.org
Fixes: 99fbb6bfc1 ("mm: make folios_put() the basis of release_pages()")
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Tested-by: Yujie Liu <yujie.liu@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202403151058.7048f6a8-oliver.sang@intel.com
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-03-26 11:07:20 -07:00

105 lines
2.6 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* include/linux/pagevec.h
*
* In many places it is efficient to batch an operation up against multiple
* folios. A folio_batch is a container which is used for that.
*/
#ifndef _LINUX_PAGEVEC_H
#define _LINUX_PAGEVEC_H
#include <linux/types.h>
/* 31 pointers + header align the folio_batch structure to a power of two */
#define PAGEVEC_SIZE 31
struct folio;
/**
* struct folio_batch - A collection of folios.
*
* The folio_batch is used to amortise the cost of retrieving and
* operating on a set of folios. The order of folios in the batch may be
* significant (eg delete_from_page_cache_batch()). Some users of the
* folio_batch store "exceptional" entries in it which can be removed
* by calling folio_batch_remove_exceptionals().
*/
struct folio_batch {
unsigned char nr;
unsigned char i;
bool percpu_pvec_drained;
struct folio *folios[PAGEVEC_SIZE];
};
/**
* folio_batch_init() - Initialise a batch of folios
* @fbatch: The folio batch.
*
* A freshly initialised folio_batch contains zero folios.
*/
static inline void folio_batch_init(struct folio_batch *fbatch)
{
fbatch->nr = 0;
fbatch->i = 0;
fbatch->percpu_pvec_drained = false;
}
static inline void folio_batch_reinit(struct folio_batch *fbatch)
{
fbatch->nr = 0;
fbatch->i = 0;
}
static inline unsigned int folio_batch_count(struct folio_batch *fbatch)
{
return fbatch->nr;
}
static inline unsigned int folio_batch_space(struct folio_batch *fbatch)
{
return PAGEVEC_SIZE - fbatch->nr;
}
/**
* folio_batch_add() - Add a folio to a batch.
* @fbatch: The folio batch.
* @folio: The folio to add.
*
* The folio is added to the end of the batch.
* The batch must have previously been initialised using folio_batch_init().
*
* Return: The number of slots still available.
*/
static inline unsigned folio_batch_add(struct folio_batch *fbatch,
struct folio *folio)
{
fbatch->folios[fbatch->nr++] = folio;
return folio_batch_space(fbatch);
}
/**
* folio_batch_next - Return the next folio to process.
* @fbatch: The folio batch being processed.
*
* Use this function to implement a queue of folios.
*
* Return: The next folio in the queue, or NULL if the queue is empty.
*/
static inline struct folio *folio_batch_next(struct folio_batch *fbatch)
{
if (fbatch->i == fbatch->nr)
return NULL;
return fbatch->folios[fbatch->i++];
}
void __folio_batch_release(struct folio_batch *pvec);
static inline void folio_batch_release(struct folio_batch *fbatch)
{
if (folio_batch_count(fbatch))
__folio_batch_release(fbatch);
}
void folio_batch_remove_exceptionals(struct folio_batch *fbatch);
#endif /* _LINUX_PAGEVEC_H */