From: David Howells <dhowells@redhat.com>
To: Matthew Wilcox <willy@infradead.org>,
"David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: David Howells <dhowells@redhat.com>,
Al Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>,
Jens Axboe <axboe@kernel.dk>, Jeff Layton <jlayton@kernel.org>,
Christian Brauner <brauner@kernel.org>,
Chuck Lever III <chuck.lever@oracle.com>,
Linus Torvalds <torvalds@linux-foundation.org>,
netdev@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Bernard Metzler <bmt@zurich.ibm.com>, Tom Talpey <tom@talpey.com>,
linux-rdma@vger.kernel.org
Subject: [RFC PATCH v2 05/48] mm: Move the page fragment allocator from page_alloc.c into its own file
Date: Wed, 29 Mar 2023 15:13:11 +0100 [thread overview]
Message-ID: <20230329141354.516864-6-dhowells@redhat.com> (raw)
In-Reply-To: <20230329141354.516864-1-dhowells@redhat.com>
Move the page fragment allocator from page_alloc.c into its own file
preparatory to changing it.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Bernard Metzler <bmt@zurich.ibm.com>
cc: Tom Talpey <tom@talpey.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: Matthew Wilcox <willy@infradead.org>
cc: linux-rdma@vger.kernel.org
cc: netdev@vger.kernel.org
---
mm/Makefile | 2 +-
mm/page_alloc.c | 126 -----------------------------------------
mm/page_frag_alloc.c | 131 +++++++++++++++++++++++++++++++++++++++++++
3 files changed, 132 insertions(+), 127 deletions(-)
create mode 100644 mm/page_frag_alloc.c
diff --git a/mm/Makefile b/mm/Makefile
index 8e105e5b3e29..4e6dc12b4cbd 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -52,7 +52,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
util.o mmzone.o vmstat.o backing-dev.o \
mm_init.o percpu.o slab_common.o \
- compaction.o \
+ compaction.o page_frag_alloc.o \
interval_tree.o list_lru.o workingset.o \
debug.o gup.o mmap_lock.o $(mmu-y)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ac1fc986af44..c08847308907 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5694,132 +5694,6 @@ void free_pages(unsigned long addr, unsigned int order)
EXPORT_SYMBOL(free_pages);
-/*
- * Page Fragment:
- * An arbitrary-length arbitrary-offset area of memory which resides
- * within a 0 or higher order page. Multiple fragments within that page
- * are individually refcounted, in the page's reference counter.
- *
- * The page_frag functions below provide a simple allocation framework for
- * page fragments. This is used by the network stack and network device
- * drivers to provide a backing region of memory for use as either an
- * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
- */
-static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
- gfp_t gfp_mask)
-{
- struct page *page = 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;
-#endif
- if (unlikely(!page))
- page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
-
- nc->va = page ? page_address(page) : NULL;
-
- return page;
-}
-
-void __page_frag_cache_drain(struct page *page, unsigned int count)
-{
- VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
-
- if (page_ref_sub_and_test(page, count))
- free_the_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(__page_frag_cache_drain);
-
-void *page_frag_alloc_align(struct page_frag_cache *nc,
- unsigned int fragsz, gfp_t gfp_mask,
- unsigned int align_mask)
-{
- unsigned int size = PAGE_SIZE;
- struct page *page;
- int offset;
-
- if (unlikely(!nc->va)) {
-refill:
- page = __page_frag_cache_refill(nc, gfp_mask);
- if (!page)
- 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);
-
- /* reset page count bias and offset to start of new frag */
- nc->pfmemalloc = page_is_pfmemalloc(page);
- nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
- nc->offset = size;
- }
-
- offset = nc->offset - fragsz;
- if (unlikely(offset < 0)) {
- page = virt_to_page(nc->va);
-
- if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
- goto refill;
-
- if (unlikely(nc->pfmemalloc)) {
- free_the_page(page, compound_order(page));
- 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);
-
- /* 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)) {
- /*
- * The caller is trying to allocate a fragment
- * with fragsz > PAGE_SIZE but the cache isn't big
- * enough to satisfy the request, this may
- * happen in low memory conditions.
- * We don't release the cache page because
- * it could make memory pressure worse
- * so we simply return NULL here.
- */
- return NULL;
- }
- }
-
- nc->pagecnt_bias--;
- offset &= align_mask;
- nc->offset = offset;
-
- return nc->va + offset;
-}
-EXPORT_SYMBOL(page_frag_alloc_align);
-
-/*
- * Frees a page fragment allocated out of either a compound or order 0 page.
- */
-void page_frag_free(void *addr)
-{
- struct page *page = virt_to_head_page(addr);
-
- if (unlikely(put_page_testzero(page)))
- free_the_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(page_frag_free);
-
static void *make_alloc_exact(unsigned long addr, unsigned int order,
size_t size)
{
diff --git a/mm/page_frag_alloc.c b/mm/page_frag_alloc.c
new file mode 100644
index 000000000000..bee95824ef8f
--- /dev/null
+++ b/mm/page_frag_alloc.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Page fragment allocator
+ *
+ * Page Fragment:
+ * An arbitrary-length arbitrary-offset area of memory which resides within a
+ * 0 or higher order page. Multiple fragments within that page are
+ * individually refcounted, in the page's reference counter.
+ *
+ * The page_frag functions provide a simple allocation framework for page
+ * fragments. This is used by the network stack and network device drivers to
+ * provide a backing region of memory for use as either an sk_buff->head, or to
+ * be used in the "frags" portion of skb_shared_info.
+ */
+
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+
+static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
+ gfp_t gfp_mask)
+{
+ struct page *page = 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;
+#endif
+ if (unlikely(!page))
+ page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+ nc->va = page ? page_address(page) : NULL;
+
+ return page;
+}
+
+void __page_frag_cache_drain(struct page *page, unsigned int count)
+{
+ VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+
+ if (page_ref_sub_and_test(page, count - 1))
+ __free_pages(page, compound_order(page));
+}
+EXPORT_SYMBOL(__page_frag_cache_drain);
+
+void *page_frag_alloc_align(struct page_frag_cache *nc,
+ unsigned int fragsz, gfp_t gfp_mask,
+ unsigned int align_mask)
+{
+ unsigned int size = PAGE_SIZE;
+ struct page *page;
+ int offset;
+
+ if (unlikely(!nc->va)) {
+refill:
+ page = __page_frag_cache_refill(nc, gfp_mask);
+ if (!page)
+ 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);
+
+ /* reset page count bias and offset to start of new frag */
+ nc->pfmemalloc = page_is_pfmemalloc(page);
+ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+ nc->offset = size;
+ }
+
+ offset = nc->offset - fragsz;
+ if (unlikely(offset < 0)) {
+ page = virt_to_page(nc->va);
+
+ if (page_ref_count(page) != nc->pagecnt_bias)
+ goto refill;
+ if (unlikely(nc->pfmemalloc)) {
+ page_ref_sub(page, nc->pagecnt_bias - 1);
+ __free_pages(page, compound_order(page));
+ 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);
+
+ /* 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)) {
+ /*
+ * The caller is trying to allocate a fragment
+ * with fragsz > PAGE_SIZE but the cache isn't big
+ * enough to satisfy the request, this may
+ * happen in low memory conditions.
+ * We don't release the cache page because
+ * it could make memory pressure worse
+ * so we simply return NULL here.
+ */
+ return NULL;
+ }
+ }
+
+ nc->pagecnt_bias--;
+ offset &= align_mask;
+ nc->offset = offset;
+
+ return nc->va + offset;
+}
+EXPORT_SYMBOL(page_frag_alloc_align);
+
+/*
+ * Frees a page fragment allocated out of either a compound or order 0 page.
+ */
+void page_frag_free(void *addr)
+{
+ struct page *page = virt_to_head_page(addr);
+
+ __free_pages(page, compound_order(page));
+}
+EXPORT_SYMBOL(page_frag_free);
next prev parent reply other threads:[~2023-03-29 14:17 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-29 14:13 [RFC PATCH v2 00/48] splice, net: Replace sendpage with sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 01/48] netfs: Fix netfs_extract_iter_to_sg() for ITER_UBUF/IOVEC David Howells
2023-03-29 14:13 ` [RFC PATCH v2 02/48] iov_iter: Remove last_offset member David Howells
2023-03-29 14:13 ` [RFC PATCH v2 03/48] iov_iter: Add an iterator-of-iterators David Howells
2023-03-29 14:13 ` [RFC PATCH v2 04/48] net: Declare MSG_SPLICE_PAGES internal sendmsg() flag David Howells
2023-03-30 14:28 ` Willem de Bruijn
2023-03-30 15:07 ` David Howells
2023-03-30 17:51 ` Willem de Bruijn
2023-03-29 14:13 ` David Howells [this message]
2023-03-29 14:13 ` [RFC PATCH v2 06/48] mm: Make the page_frag_cache allocator use multipage folios David Howells
2023-03-29 14:13 ` [RFC PATCH v2 07/48] mm: Make the page_frag_cache allocator use per-cpu David Howells
2023-03-29 14:13 ` [RFC PATCH v2 08/48] tcp: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 09/48] tcp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 10/48] tcp: Convert do_tcp_sendpages() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 11/48] tcp_bpf: Inline do_tcp_sendpages as it's now a wrapper around tcp_sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 12/48] espintcp: Inline do_tcp_sendpages() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 13/48] tls: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 14/48] siw: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 15/48] tcp: Fold do_tcp_sendpages() into tcp_sendpage_locked() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 16/48] ip, udp: Support MSG_SPLICE_PAGES David Howells
2023-03-30 14:20 ` Willem de Bruijn
2023-03-30 14:39 ` David Howells
2023-03-30 17:46 ` Willem de Bruijn
2023-03-30 15:11 ` David Howells
2023-03-30 17:55 ` Willem de Bruijn
2023-03-30 19:49 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 17/48] ip, udp: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 18/48] udp: Convert udp_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 19/48] af_unix: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 20/48] af_unix: Make sendmsg(MSG_SPLICE_PAGES) copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 21/48] crypto: af_alg: Pin pages rather than ref'ing if appropriate David Howells
2023-03-29 14:13 ` [RFC PATCH v2 22/48] crypto: af_alg: Use netfs_extract_iter_to_sg() to create scatterlists David Howells
2023-03-29 14:13 ` [RFC PATCH v2 23/48] crypto: af_alg: Indent the loop in af_alg_sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 24/48] crypto: af_alg: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 25/48] crypto: af_alg: Convert af_alg_sendpage() to use MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 26/48] crypto: af_alg/hash: Support MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 27/48] splice, net: Use sendmsg(MSG_SPLICE_PAGES) rather than ->sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 28/48] splice: Reimplement splice_to_socket() to pass multiple bufs to sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 29/48] Remove file->f_op->sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 30/48] siw: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage to transmit David Howells
2023-03-29 15:18 ` Bernard Metzler
2023-03-29 15:32 ` David Howells
2023-03-29 14:13 ` [RFC PATCH v2 31/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 32/48] iscsi: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 33/48] iscsi: Assume "sendpage" is okay in iscsi_tcp_segment_map() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 34/48] tcp_bpf: Make tcp_bpf_sendpage() go through tcp_bpf_sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:13 ` [RFC PATCH v2 35/48] net: Use sendmsg(MSG_SPLICE_PAGES) not sendpage in skb_send_sock() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 36/48] algif: Remove hash_sendpage*() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 37/48] ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-30 1:45 ` Xiubo Li
2023-03-30 6:48 ` David Howells
2023-03-31 13:05 ` Xiubo Li
2023-04-03 3:27 ` Xiubo Li
2023-04-03 8:32 ` David Howells
2023-04-10 0:38 ` Xiubo Li
2023-03-29 14:13 ` [RFC PATCH v2 38/48] rds: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 39/48] dlm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 40/48] sunrpc: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 15:28 ` Chuck Lever III
2023-03-29 19:58 ` David Howells
2023-03-30 9:29 ` David Howells
2023-03-30 9:41 ` David Howells
2023-03-30 13:16 ` Chuck Lever III
2023-03-30 13:01 ` David Howells
2023-03-30 13:16 ` David Howells
2023-03-30 13:27 ` Chuck Lever III
2023-03-30 14:26 ` David Howells
2023-03-30 16:36 ` Chuck Lever III
2023-04-14 14:41 ` Daire Byrne
2023-03-29 14:13 ` [RFC PATCH v2 41/48] sunrpc: Rely on TCP sendmsg + MSG_SPLICE_PAGES to copy unspliceable data David Howells
2023-03-29 14:13 ` [RFC PATCH v2 42/48] nvme: Use sendmsg(MSG_SPLICE_PAGES) rather then sendpage David Howells
2023-03-29 14:13 ` [RFC PATCH v2 43/48] kcm: " David Howells
2023-03-29 14:13 ` [RFC PATCH v2 44/48] smc: Drop smc_sendpage() in favour of smc_sendmsg() + MSG_SPLICE_PAGES David Howells
2023-03-29 14:13 ` [RFC PATCH v2 45/48] ocfs2: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 46/48] drbd: Use sendmsg(MSG_SPLICE_PAGES) rather than sendmsg() David Howells
2023-03-29 14:13 ` [RFC PATCH v2 47/48] drdb: Send an entire bio in a single sendmsg David Howells
2023-03-29 14:13 ` [RFC PATCH v2 48/48] sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) David Howells
2023-03-29 14:23 ` Hannes Reinecke
2023-03-29 14:39 ` 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=20230329141354.516864-6-dhowells@redhat.com \
--to=dhowells@redhat.com \
--cc=axboe@kernel.dk \
--cc=bmt@zurich.ibm.com \
--cc=brauner@kernel.org \
--cc=chuck.lever@oracle.com \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=hch@infradead.org \
--cc=jlayton@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=tom@talpey.com \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
--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).