From: David Howells <dhowells@redhat.com>
To: netdev@vger.kernel.org
Cc: David Howells <dhowells@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
Willem de Bruijn <willemdebruijn.kernel@gmail.com>,
David Ahern <dsahern@kernel.org>,
Matthew Wilcox <willy@infradead.org>,
Jens Axboe <axboe@kernel.dk>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org,
Jeroen de Borst <jeroendb@google.com>,
Catherine Sullivan <csully@google.com>,
Shailend Chand <shailend@google.com>,
Felix Fietkau <nbd@nbd.name>, John Crispin <john@phrozen.org>,
Sean Wang <sean.wang@mediatek.com>,
Mark Lee <Mark-MC.Lee@mediatek.com>,
Lorenzo Bianconi <lorenzo@kernel.org>,
Matthias Brugger <matthias.bgg@gmail.com>,
AngeloGioacchino Del Regno
<angelogioacchino.delregno@collabora.com>,
Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@fb.com>,
Christoph Hellwig <hch@lst.de>, Sagi Grimberg <sagi@grimberg.me>,
Chaitanya Kulkarni <kch@nvidia.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-arm-kernel@lists.infradead.org,
linux-mediatek@lists.infradead.org,
linux-nvme@lists.infradead.org
Subject: [PATCH net-next 04/12] mm: Make the page_frag_cache allocator use multipage folios
Date: Wed, 24 May 2023 16:33:03 +0100 [thread overview]
Message-ID: <20230524153311.3625329-5-dhowells@redhat.com> (raw)
In-Reply-To: <20230524153311.3625329-1-dhowells@redhat.com>
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@redhat.com>
cc: "David S. Miller" <davem@davemloft.net>
cc: Eric Dumazet <edumazet@google.com>
cc: Jakub Kicinski <kuba@kernel.org>
cc: Paolo Abeni <pabeni@redhat.com>
cc: Jens Axboe <axboe@kernel.dk>
cc: Jeroen de Borst <jeroendb@google.com>
cc: Catherine Sullivan <csully@google.com>
cc: Shailend Chand <shailend@google.com>
cc: Felix Fietkau <nbd@nbd.name>
cc: John Crispin <john@phrozen.org>
cc: Sean Wang <sean.wang@mediatek.com>
cc: Mark Lee <Mark-MC.Lee@mediatek.com>
cc: Lorenzo Bianconi <lorenzo@kernel.org>
cc: Matthias Brugger <matthias.bgg@gmail.com>
cc: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
cc: Keith Busch <kbusch@kernel.org>
cc: Jens Axboe <axboe@fb.com>
cc: Christoph Hellwig <hch@lst.de>
cc: Sagi Grimberg <sagi@grimberg.me>
cc: Chaitanya Kulkarni <kch@nvidia.com>
cc: Andrew Morton <akpm@linux-foundation.org>
cc: Matthew Wilcox <willy@infradead.org>
cc: netdev@vger.kernel.org
cc: linux-arm-kernel@lists.infradead.org
cc: linux-mediatek@lists.infradead.org
cc: linux-nvme@lists.infradead.org
cc: linux-mm@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);
next prev parent reply other threads:[~2023-05-24 15:33 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-24 15:32 [PATCH net-next 00/12] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES), part 3 David Howells
2023-05-24 15:33 ` [PATCH net-next 01/12] mm: Move the page fragment allocator from page_alloc.c into its own file David Howells
2023-05-24 15:33 ` [PATCH net-next 02/12] mm: Provide a page_frag_cache allocator cleanup function David Howells
2023-05-24 15:33 ` [PATCH net-next 03/12] mm: Make the page_frag_cache allocator alignment param a pow-of-2 David Howells
2023-05-27 15:54 ` Alexander H Duyck
2023-11-30 9:00 ` Yunsheng Lin
2023-06-16 15:28 ` David Howells
2023-06-16 16:06 ` Alexander Duyck
2023-05-24 15:33 ` David Howells [this message]
2023-05-26 11:56 ` [PATCH net-next 04/12] mm: Make the page_frag_cache allocator use multipage folios Yunsheng Lin
2023-05-27 15:47 ` Alexander H Duyck
2023-05-26 12:47 ` David Howells
2023-05-26 14:06 ` Mika Penttilä
2023-05-27 0:50 ` Jakub Kicinski
2023-05-24 15:33 ` [PATCH net-next 05/12] mm: Make the page_frag_cache allocator handle __GFP_ZERO itself David Howells
2023-05-27 0:57 ` Jakub Kicinski
2023-05-27 15:54 ` Alexander Duyck
2023-05-24 15:33 ` [PATCH net-next 06/12] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-05-27 1:02 ` Jakub Kicinski
2023-05-24 15:33 ` [PATCH net-next 07/12] net: Clean up users of netdev_alloc_cache and napi_frag_cache David Howells
2023-05-24 15:33 ` [PATCH net-next 08/12] net: Copy slab data for sendmsg(MSG_SPLICE_PAGES) David Howells
2023-05-24 15:33 ` [PATCH net-next 09/12] tls/sw: Support MSG_SPLICE_PAGES David Howells
2023-05-27 1:08 ` Jakub Kicinski
2023-05-30 22:26 ` Bug in short splice to socket? David Howells
2023-05-31 0:32 ` Jakub Kicinski
2023-05-24 15:33 ` [PATCH net-next 10/12] tls/sw: Convert tls_sw_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-05-27 1:13 ` Jakub Kicinski
2023-05-24 15:33 ` [PATCH net-next 11/12] tls/device: Support MSG_SPLICE_PAGES David Howells
2023-05-24 15:33 ` [PATCH net-next 12/12] tls/device: Convert tls_device_sendpage() to use MSG_SPLICE_PAGES David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230524153311.3625329-5-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=Mark-MC.Lee@mediatek.com \
--cc=akpm@linux-foundation.org \
--cc=angelogioacchino.delregno@collabora.com \
--cc=axboe@fb.com \
--cc=axboe@kernel.dk \
--cc=csully@google.com \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=edumazet@google.com \
--cc=hch@lst.de \
--cc=jeroendb@google.com \
--cc=john@phrozen.org \
--cc=kbusch@kernel.org \
--cc=kch@nvidia.com \
--cc=kuba@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mediatek@lists.infradead.org \
--cc=linux-mm@kvack.org \
--cc=linux-nvme@lists.infradead.org \
--cc=lorenzo@kernel.org \
--cc=matthias.bgg@gmail.com \
--cc=nbd@nbd.name \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sagi@grimberg.me \
--cc=sean.wang@mediatek.com \
--cc=shailend@google.com \
--cc=willemdebruijn.kernel@gmail.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).