[PATCH net-next 04/12] mm: Make the page_frag_cache allocator use multipage folios
David Howells
dhowells at redhat.com
Wed May 24 08:33:03 PDT 2023
Change the page_frag_cache allocator to use multipage folios rather than
groups of pages. This reduces page_frag_free to just a folio_put() or
put_page().
Signed-off-by: David Howells <dhowells at redhat.com>
cc: "David S. Miller" <davem at davemloft.net>
cc: Eric Dumazet <edumazet at google.com>
cc: Jakub Kicinski <kuba at kernel.org>
cc: Paolo Abeni <pabeni at redhat.com>
cc: Jens Axboe <axboe at kernel.dk>
cc: Jeroen de Borst <jeroendb at google.com>
cc: Catherine Sullivan <csully at google.com>
cc: Shailend Chand <shailend at google.com>
cc: Felix Fietkau <nbd at nbd.name>
cc: John Crispin <john at phrozen.org>
cc: Sean Wang <sean.wang at mediatek.com>
cc: Mark Lee <Mark-MC.Lee at mediatek.com>
cc: Lorenzo Bianconi <lorenzo at kernel.org>
cc: Matthias Brugger <matthias.bgg at gmail.com>
cc: AngeloGioacchino Del Regno <angelogioacchino.delregno at collabora.com>
cc: Keith Busch <kbusch at kernel.org>
cc: Jens Axboe <axboe at fb.com>
cc: Christoph Hellwig <hch at lst.de>
cc: Sagi Grimberg <sagi at grimberg.me>
cc: Chaitanya Kulkarni <kch at nvidia.com>
cc: Andrew Morton <akpm at linux-foundation.org>
cc: Matthew Wilcox <willy at infradead.org>
cc: netdev at vger.kernel.org
cc: linux-arm-kernel at lists.infradead.org
cc: linux-mediatek at lists.infradead.org
cc: linux-nvme at lists.infradead.org
cc: linux-mm at kvack.org
---
include/linux/mm_types.h | 13 ++----
mm/page_frag_alloc.c | 99 +++++++++++++++++++---------------------
2 files changed, 52 insertions(+), 60 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..d7c52a5979cc 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -420,18 +420,13 @@ static inline void *folio_get_private(struct folio *folio)
}
struct page_frag_cache {
- void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
- __u16 offset;
- __u16 size;
-#else
- __u32 offset;
-#endif
+ struct folio *folio;
+ unsigned int offset;
/* we maintain a pagecount bias, so that we dont dirty cache line
* containing page->_refcount every time we allocate a fragment.
*/
- unsigned int pagecnt_bias;
- bool pfmemalloc;
+ unsigned int pagecnt_bias;
+ bool pfmemalloc;
};
typedef unsigned long vm_flags_t;
diff --git a/mm/page_frag_alloc.c b/mm/page_frag_alloc.c
index 9d3f6fbd9a07..ffd68bfb677d 100644
--- a/mm/page_frag_alloc.c
+++ b/mm/page_frag_alloc.c
@@ -16,33 +16,34 @@
#include <linux/init.h>
#include <linux/mm.h>
-static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
- gfp_t gfp_mask)
+/*
+ * Allocate a new folio for the frag cache.
+ */
+static struct folio *page_frag_cache_refill(struct page_frag_cache *nc,
+ gfp_t gfp_mask)
{
- struct page *page = NULL;
+ struct folio *folio = NULL;
gfp_t gfp = gfp_mask;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
- gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY |
- __GFP_NOMEMALLOC;
- page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
- PAGE_FRAG_CACHE_MAX_ORDER);
- nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
+ gfp_mask |= __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
+ folio = folio_alloc(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER);
#endif
- if (unlikely(!page))
- page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+ if (unlikely(!folio))
+ folio = folio_alloc(gfp, 0);
- nc->va = page ? page_address(page) : NULL;
-
- return page;
+ if (folio)
+ nc->folio = folio;
+ return folio;
}
void __page_frag_cache_drain(struct page *page, unsigned int count)
{
- VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+ struct folio *folio = page_folio(page);
+
+ VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
- if (page_ref_sub_and_test(page, count - 1))
- __free_pages(page, compound_order(page));
+ folio_put_refs(folio, count);
}
EXPORT_SYMBOL(__page_frag_cache_drain);
@@ -54,11 +55,12 @@ EXPORT_SYMBOL(__page_frag_cache_drain);
*/
void page_frag_cache_clear(struct page_frag_cache *nc)
{
- if (nc->va) {
- struct page *page = virt_to_head_page(nc->va);
+ struct folio *folio = nc->folio;
- __page_frag_cache_drain(page, nc->pagecnt_bias);
- nc->va = NULL;
+ if (folio) {
+ VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
+ folio_put_refs(folio, nc->pagecnt_bias);
+ nc->folio = NULL;
}
}
EXPORT_SYMBOL(page_frag_cache_clear);
@@ -67,56 +69,51 @@ void *page_frag_alloc_align(struct page_frag_cache *nc,
unsigned int fragsz, gfp_t gfp_mask,
unsigned int align)
{
- unsigned int size = PAGE_SIZE;
- struct page *page;
- int offset;
+ struct folio *folio = nc->folio;
+ size_t offset;
WARN_ON_ONCE(!is_power_of_2(align));
- if (unlikely(!nc->va)) {
+ if (unlikely(!folio)) {
refill:
- page = __page_frag_cache_refill(nc, gfp_mask);
- if (!page)
+ folio = page_frag_cache_refill(nc, gfp_mask);
+ if (!folio)
return NULL;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
- /* if size can vary use size else just use PAGE_SIZE */
- size = nc->size;
-#endif
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
- page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
+ folio_ref_add(folio, PAGE_FRAG_CACHE_MAX_SIZE);
/* reset page count bias and offset to start of new frag */
- nc->pfmemalloc = page_is_pfmemalloc(page);
+ nc->pfmemalloc = folio_is_pfmemalloc(folio);
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
- nc->offset = size;
+ nc->offset = folio_size(folio);
}
- offset = nc->offset - fragsz;
- if (unlikely(offset < 0)) {
- page = virt_to_page(nc->va);
-
- if (page_ref_count(page) != nc->pagecnt_bias)
+ offset = nc->offset;
+ if (unlikely(fragsz > offset)) {
+ /* Reuse the folio if everyone we gave it to has finished with
+ * it.
+ */
+ if (!folio_ref_sub_and_test(folio, nc->pagecnt_bias)) {
+ nc->folio = NULL;
goto refill;
+ }
+
if (unlikely(nc->pfmemalloc)) {
- page_ref_sub(page, nc->pagecnt_bias - 1);
- __free_pages(page, compound_order(page));
+ __folio_put(folio);
+ nc->folio = NULL;
goto refill;
}
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
- /* if size can vary use size else just use PAGE_SIZE */
- size = nc->size;
-#endif
/* OK, page count is 0, we can safely set it */
- set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+ folio_set_count(folio, PAGE_FRAG_CACHE_MAX_SIZE + 1);
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
- offset = size - fragsz;
- if (unlikely(offset < 0)) {
+ offset = folio_size(folio);
+ if (unlikely(fragsz > offset)) {
/*
* The caller is trying to allocate a fragment
* with fragsz > PAGE_SIZE but the cache isn't big
@@ -126,15 +123,17 @@ void *page_frag_alloc_align(struct page_frag_cache *nc,
* it could make memory pressure worse
* so we simply return NULL here.
*/
+ nc->offset = offset;
return NULL;
}
}
nc->pagecnt_bias--;
+ offset -= fragsz;
offset &= ~(align - 1);
nc->offset = offset;
- return nc->va + offset;
+ return folio_address(folio) + offset;
}
EXPORT_SYMBOL(page_frag_alloc_align);
@@ -143,8 +142,6 @@ EXPORT_SYMBOL(page_frag_alloc_align);
*/
void page_frag_free(void *addr)
{
- struct page *page = virt_to_head_page(addr);
-
- __free_pages(page, compound_order(page));
+ folio_put(virt_to_folio(addr));
}
EXPORT_SYMBOL(page_frag_free);
More information about the Linux-nvme
mailing list