2024-03-28 13:41:24

by Yunsheng Lin

[permalink] [raw]
Subject: [PATCH RFC 01/10] mm: Move the page fragment allocator from page_alloc into its own file

Inspired by [1], but use free_unref_page() to replace free_the_page()
instead of __free_pages(), use VM_BUG_ON() to catch that we can use
free_unref_page() directly, also add its own header file.

As the API is only used by the networking, it may make sense to
move it to the networking directory like the page_pool does in the
future if we can make the free_unref_page() callable outside of the
mm subsystem. And we can utilize that to decouple the 'struct page'
in the networking subsystem in the future.

1. https://lore.kernel.org/all/[email protected]/

CC: David Howells <[email protected]>
Signed-off-by: Yunsheng Lin <[email protected]>
---
include/linux/gfp.h | 22 -----
include/linux/mm_types.h | 18 ----
include/linux/page_frag_cache.h | 47 ++++++++++
include/linux/skbuff.h | 1 +
mm/Makefile | 1 +
mm/page_alloc.c | 136 -----------------------------
mm/page_frag_alloc.c | 149 ++++++++++++++++++++++++++++++++
7 files changed, 198 insertions(+), 176 deletions(-)
create mode 100644 include/linux/page_frag_cache.h
create mode 100644 mm/page_frag_alloc.c

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index c775ea3c6015..5afeab2b906f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -310,28 +310,6 @@ __meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __al
extern void __free_pages(struct page *page, unsigned int order);
extern void free_pages(unsigned long addr, unsigned int order);

-struct page_frag_cache;
-void page_frag_cache_drain(struct page_frag_cache *nc);
-extern void __page_frag_cache_drain(struct page *page, unsigned int count);
-void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
- gfp_t gfp_mask, unsigned int align_mask);
-
-static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
- unsigned int fragsz, gfp_t gfp_mask,
- unsigned int align)
-{
- WARN_ON_ONCE(!is_power_of_2(align));
- return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
-}
-
-static inline void *page_frag_alloc(struct page_frag_cache *nc,
- unsigned int fragsz, gfp_t gfp_mask)
-{
- return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
-}
-
-extern void page_frag_free(void *addr);
-
#define __free_page(page) __free_pages((page), 0)
#define free_page(addr) free_pages((addr), 0)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 5240bd7bca33..78a92b4475a7 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -504,9 +504,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
*/
#define STRUCT_PAGE_MAX_SHIFT (order_base_2(sizeof(struct page)))

-#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK)
-#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
-
/*
* page_private can be used on tail pages. However, PagePrivate is only
* checked by the VM on the head page. So page_private on the tail pages
@@ -525,21 +522,6 @@ static inline void *folio_get_private(struct folio *folio)
return folio->private;
}

-struct page_frag_cache {
- void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
- __u16 offset;
- __u16 size;
-#else
- __u32 offset;
-#endif
- /* 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;
-};
-
typedef unsigned long vm_flags_t;

/*
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
new file mode 100644
index 000000000000..04810d8d6a7d
--- /dev/null
+++ b/include/linux/page_frag_cache.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PAGE_FRAG_CACHE_H
+#define _LINUX_PAGE_FRAG_CACHE_H
+
+#include <linux/gfp.h>
+
+#define PAGE_FRAG_CACHE_MAX_SIZE __ALIGN_MASK(32768, ~PAGE_MASK)
+#define PAGE_FRAG_CACHE_MAX_ORDER get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+
+struct page_frag_cache {
+ void *va;
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+ __u16 offset;
+ __u16 size;
+#else
+ __u32 offset;
+#endif
+ /* 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;
+};
+
+void page_frag_cache_drain(struct page_frag_cache *nc);
+void __page_frag_cache_drain(struct page *page, unsigned int count);
+void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
+ gfp_t gfp_mask, unsigned int align_mask);
+
+static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
+ unsigned int fragsz, gfp_t gfp_mask,
+ unsigned int align)
+{
+ WARN_ON_ONCE(!is_power_of_2(align));
+ return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
+}
+
+static inline void *page_frag_alloc(struct page_frag_cache *nc,
+ unsigned int fragsz, gfp_t gfp_mask)
+{
+ return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
+}
+
+void page_frag_free(void *addr);
+
+#endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b945af8a6208..7f68199fee34 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -31,6 +31,7 @@
#include <linux/in6.h>
#include <linux/if_packet.h>
#include <linux/llist.h>
+#include <linux/page_frag_cache.h>
#include <net/flow.h>
#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <linux/netfilter/nf_conntrack_common.h>
diff --git a/mm/Makefile b/mm/Makefile
index e4b5b75aaec9..6083f3dd7cc3 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -60,6 +60,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o
memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o

obj-y += page-alloc.o
+obj-y += page_frag_alloc.o
obj-y += init-mm.o
obj-y += memblock.o
obj-y += $(memory-hotplug-y)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 14d39f34d336..2308360d78eb 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4675,142 +4675,6 @@ 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_mask & ~__GFP_DIRECT_RECLAIM) | __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_frag_cache *nc)
-{
- if (!nc->va)
- return;
-
- __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
- nc->va = NULL;
-}
-EXPORT_SYMBOL(page_frag_cache_drain);
-
-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..a0f90ba25200
--- /dev/null
+++ b/mm/page_frag_alloc.c
@@ -0,0 +1,149 @@
+// 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>
+#include <linux/page_frag_cache.h>
+#include "internal.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_mask & ~__GFP_DIRECT_RECLAIM) | __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_frag_cache *nc)
+{
+ if (!nc->va)
+ return;
+
+ __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
+ nc->va = NULL;
+}
+EXPORT_SYMBOL(page_frag_cache_drain);
+
+void __page_frag_cache_drain(struct page *page, unsigned int count)
+{
+ VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+
+ /* ensure we can call free_unref_page() directly as we are bypassing
+ * the pcp_allowed_order() checking.
+ */
+ VM_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_ALLOC_COSTLY_ORDER);
+
+ if (page_ref_sub_and_test(page, count))
+ free_unref_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_unref_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_unref_page(page, compound_order(page));
+}
+EXPORT_SYMBOL(page_frag_free);
--
2.33.0



2024-03-29 17:19:34

by Christophe Leroy

[permalink] [raw]
Subject: Re: [PATCH RFC 01/10] mm: Move the page fragment allocator from page_alloc into its own file



Le 28/03/2024 à 14:38, Yunsheng Lin a écrit :
> Inspired by [1], but use free_unref_page() to replace free_the_page()
> instead of __free_pages(), use VM_BUG_ON() to catch that we can use
> free_unref_page() directly, also add its own header file.
>
> As the API is only used by the networking, it may make sense to
> move it to the networking directory like the page_pool does in the
> future if we can make the free_unref_page() callable outside of the
> mm subsystem. And we can utilize that to decouple the 'struct page'
> in the networking subsystem in the future.

I'm wondering if this page fragment allocator could replace the page
fragment allocator used in powerpc to allocate fragment of pages for
page tables.

See arch/powerpc/mm/pgtable-frag.c

Christophe

2024-03-30 12:01:30

by Yunsheng Lin

[permalink] [raw]
Subject: Re: [PATCH RFC 01/10] mm: Move the page fragment allocator from page_alloc into its own file

On 2024/3/30 1:19, Christophe Leroy wrote:
>
>
> Le 28/03/2024 à 14:38, Yunsheng Lin a écrit :
>> Inspired by [1], but use free_unref_page() to replace free_the_page()
>> instead of __free_pages(), use VM_BUG_ON() to catch that we can use
>> free_unref_page() directly, also add its own header file.
>>
>> As the API is only used by the networking, it may make sense to
>> move it to the networking directory like the page_pool does in the
>> future if we can make the free_unref_page() callable outside of the
>> mm subsystem. And we can utilize that to decouple the 'struct page'
>> in the networking subsystem in the future.
>
> I'm wondering if this page fragment allocator could replace the page
> fragment allocator used in powerpc to allocate fragment of pages for
> page tables.

From a quick glance, it seems possible. If there are potential users
other than the networking for this API, we can keep it in mm subsystem
for now as this patch does and see how thing will evolve.

>
> See arch/powerpc/mm/pgtable-frag.c
>
> Christophe
>