[PATCH net-next v1 01/12] mm: Move the page fragment allocator from page_alloc into its own file

[PATCH net-next v1 01/12] mm: Move the page fragment allocator from page_alloc into its own file

[Yunsheng Lin]

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/20230411160902.4134381-3-dhowells@redhat.com/

CC: David Howells <dhowells@redhat.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 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_cache.c            | 149 ++++++++++++++++++++++++++++++++
 7 files changed, 198 insertions(+), 176 deletions(-)
 create mode 100644 include/linux/page_frag_cache.h
 create mode 100644 mm/page_frag_cache.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 7dfb906d92f7..76c5be5b1a8c 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 4abb40b911ec..146c481c006f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -59,6 +59,7 @@ 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_cache.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_cache.c b/mm/page_frag_cache.c
new file mode 100644
index 000000000000..a0f90ba25200
--- /dev/null
+++ b/mm/page_frag_cache.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

[PATCH net-next v1 02/12] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Yunsheng Lin]

We are above to use page_frag_alloc_*() API to not just
allocate memory for skb->data, but also use them to do
the memory allocation for skb frag too. Currently the
implementation of page_frag in mm subsystem is running
the offset as a countdown rather than count-up value,
there may have several advantages to that as mentioned
in [1], but it may have some disadvantages, for example,
it may disable skb frag coaleasing and more correct cache
prefetching

We have a trade-off to make in order to have a unified
implementation and API for page_frag, so use a initial zero
offset in this patch, and the following patch will try to
make some optimization to aovid the disadvantages as much
as possible.

1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 mm/page_frag_cache.c | 31 ++++++++++++++-----------------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index a0f90ba25200..3e3e88d9af90 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -67,9 +67,8 @@ 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;
+	unsigned int size, offset;
 	struct page *page;
-	int offset;
 
 	if (unlikely(!nc->va)) {
 refill:
@@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 		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.
 		 */
@@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 		/* 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;
+		nc->offset = 0;
 	}
 
-	offset = nc->offset - fragsz;
-	if (unlikely(offset < 0)) {
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	/* if size can vary use size else just use PAGE_SIZE */
+	size = nc->size;
+#else
+	size = PAGE_SIZE;
+#endif
+
+	offset = ALIGN(nc->offset, -align_mask);
+	if (unlikely(offset + fragsz > size)) {
 		page = virt_to_page(nc->va);
 
 		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
@@ -104,17 +106,13 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			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)) {
+		offset = 0;
+		if (unlikely(fragsz > size)) {
 			/*
 			 * The caller is trying to allocate a fragment
 			 * with fragsz > PAGE_SIZE but the cache isn't big
@@ -129,8 +127,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 	}
 
 	nc->pagecnt_bias--;
-	offset &= align_mask;
-	nc->offset = offset;
+	nc->offset = offset + fragsz;
 
 	return nc->va + offset;
 }
-- 
2.33.0

[PATCH net-next v1 03/12] mm: page_frag: change page_frag_alloc_* API to accept align param

[Yunsheng Lin]

When page_frag_alloc_* API doesn't need data alignment, the
ALIGN() operation is unnecessary, so change page_frag_alloc_*
API to accept align param instead of align_mask param, and do
the ALIGN()'ing in the inline helper when needed.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 20 ++++++++++++--------
 include/linux/skbuff.h          | 12 ++++++------
 mm/page_frag_cache.c            |  9 ++++-----
 net/core/skbuff.c               | 12 +++++-------
 net/rxrpc/txbuf.c               |  5 +++--
 5 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 04810d8d6a7d..cc0ede0912f3 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -25,21 +25,25 @@ struct page_frag_cache {
 
 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);
+void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz,
+		      gfp_t gfp_mask);
+
+static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
+					    unsigned int fragsz, gfp_t gfp_mask,
+					    unsigned int align)
+{
+	nc->offset = ALIGN(nc->offset, align);
+
+	return page_frag_alloc(nc, fragsz, gfp_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);
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, align);
 }
 
 void page_frag_free(void *addr);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 76c5be5b1a8c..2ef14dde5bbc 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3268,7 +3268,7 @@ static inline void skb_queue_purge(struct sk_buff_head *list)
 unsigned int skb_rbtree_purge(struct rb_root *root);
 void skb_errqueue_purge(struct sk_buff_head *list);
 
-void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
+void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align);
 
 /**
  * netdev_alloc_frag - allocate a page fragment
@@ -3279,14 +3279,14 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
  */
 static inline void *netdev_alloc_frag(unsigned int fragsz)
 {
-	return __netdev_alloc_frag_align(fragsz, ~0u);
+	return __netdev_alloc_frag_align(fragsz, 1u);
 }
 
 static inline void *netdev_alloc_frag_align(unsigned int fragsz,
 					    unsigned int align)
 {
 	WARN_ON_ONCE(!is_power_of_2(align));
-	return __netdev_alloc_frag_align(fragsz, -align);
+	return __netdev_alloc_frag_align(fragsz, align);
 }
 
 struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length,
@@ -3346,18 +3346,18 @@ static inline void skb_free_frag(void *addr)
 	page_frag_free(addr);
 }
 
-void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask);
+void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align);
 
 static inline void *napi_alloc_frag(unsigned int fragsz)
 {
-	return __napi_alloc_frag_align(fragsz, ~0u);
+	return __napi_alloc_frag_align(fragsz, 1u);
 }
 
 static inline void *napi_alloc_frag_align(unsigned int fragsz,
 					  unsigned int align)
 {
 	WARN_ON_ONCE(!is_power_of_2(align));
-	return __napi_alloc_frag_align(fragsz, -align);
+	return __napi_alloc_frag_align(fragsz, align);
 }
 
 struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int length);
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 3e3e88d9af90..39c744c892ed 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -63,9 +63,8 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 }
 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)
+void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz,
+		      gfp_t gfp_mask)
 {
 	unsigned int size, offset;
 	struct page *page;
@@ -94,7 +93,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 	size = PAGE_SIZE;
 #endif
 
-	offset = ALIGN(nc->offset, -align_mask);
+	offset = nc->offset;
 	if (unlikely(offset + fragsz > size)) {
 		page = virt_to_page(nc->va);
 
@@ -131,7 +130,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 
 	return nc->va + offset;
 }
-EXPORT_SYMBOL(__page_frag_alloc_align);
+EXPORT_SYMBOL(page_frag_alloc);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2a5ce6667bbb..e5196c284b33 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -305,18 +305,17 @@ void napi_get_frags_check(struct napi_struct *napi)
 	local_bh_enable();
 }
 
-void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
+void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
-				       align_mask);
+	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align);
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
-void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
+void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align)
 {
 	void *data;
 
@@ -324,15 +323,14 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 	if (in_hardirq() || irqs_disabled()) {
 		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
 
-		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC,
-					       align_mask);
+		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align);
 	} else {
 		struct napi_alloc_cache *nc;
 
 		local_bh_disable();
 		nc = this_cpu_ptr(&napi_alloc_cache);
 		data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
-					       align_mask);
+					       align);
 		local_bh_enable();
 	}
 	return data;
diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c
index e0679658d9de..eb640875bf07 100644
--- a/net/rxrpc/txbuf.c
+++ b/net/rxrpc/txbuf.c
@@ -32,9 +32,10 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_
 		hoff = round_up(sizeof(*whdr), data_align) - sizeof(*whdr);
 	total = hoff + sizeof(*whdr) + data_size;
 
+	data_align = max_t(size_t, data_align, L1_CACHE_BYTES);
 	mutex_lock(&call->conn->tx_data_alloc_lock);
-	buf = __page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
-				      ~(data_align - 1) & ~(L1_CACHE_BYTES - 1));
+	buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
+				    data_align);
 	mutex_unlock(&call->conn->tx_data_alloc_lock);
 	if (!buf) {
 		kfree(txb);
-- 
2.33.0

[PATCH net-next v1 04/12] mm: page_frag: add '_va' suffix to page_frag API

[Yunsheng Lin]

Currently most of the API for page_frag API is returning
'virtual address' as output or expecting 'virtual address'
as input, in order to differentiate the API handling between
'virtual address' and 'struct page', add '_va' suffix to the
corresponding API mirroring the page_pool_alloc_va() API of
the page_pool.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 drivers/net/ethernet/google/gve/gve_rx.c      |  4 ++--
 drivers/net/ethernet/intel/ice/ice_txrx.c     |  2 +-
 drivers/net/ethernet/intel/ice/ice_txrx.h     |  2 +-
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c |  2 +-
 .../net/ethernet/intel/ixgbevf/ixgbevf_main.c |  4 ++--
 .../marvell/octeontx2/nic/otx2_common.c       |  2 +-
 drivers/net/ethernet/mediatek/mtk_wed_wo.c    |  4 ++--
 drivers/nvme/host/tcp.c                       |  8 +++----
 drivers/nvme/target/tcp.c                     | 22 ++++++++---------
 drivers/vhost/net.c                           |  6 ++---
 include/linux/page_frag_cache.h               | 24 ++++++++++---------
 include/linux/skbuff.h                        |  2 +-
 kernel/bpf/cpumap.c                           |  2 +-
 mm/page_frag_cache.c                          | 10 ++++----
 net/core/skbuff.c                             | 15 ++++++------
 net/core/xdp.c                                |  2 +-
 net/rxrpc/txbuf.c                             | 15 ++++++------
 net/sunrpc/svcsock.c                          |  4 ++--
 18 files changed, 67 insertions(+), 63 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index cd727e55ae0f..820874c1c570 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -687,7 +687,7 @@ static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx,
 
 	total_len = headroom + SKB_DATA_ALIGN(len) +
 		SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
-	frame = page_frag_alloc(&rx->page_cache, total_len, GFP_ATOMIC);
+	frame = page_frag_alloc_va(&rx->page_cache, total_len, GFP_ATOMIC);
 	if (!frame) {
 		u64_stats_update_begin(&rx->statss);
 		rx->xdp_alloc_fails++;
@@ -700,7 +700,7 @@ static int gve_xdp_redirect(struct net_device *dev, struct gve_rx_ring *rx,
 
 	err = xdp_do_redirect(dev, &new, xdp_prog);
 	if (err)
-		page_frag_free(frame);
+		page_frag_free_va(frame);
 
 	return err;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8bb743f78fcb..399b317c509d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -126,7 +126,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf)
 		dev_kfree_skb_any(tx_buf->skb);
 		break;
 	case ICE_TX_BUF_XDP_TX:
-		page_frag_free(tx_buf->raw_buf);
+		page_frag_free_va(tx_buf->raw_buf);
 		break;
 	case ICE_TX_BUF_XDP_XMIT:
 		xdp_return_frame(tx_buf->xdpf);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index feba314a3fe4..6379f57d8228 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -148,7 +148,7 @@ static inline int ice_skb_pad(void)
  * @ICE_TX_BUF_DUMMY: dummy Flow Director packet, unmap and kfree()
  * @ICE_TX_BUF_FRAG: mapped skb OR &xdp_buff frag, only unmap DMA
  * @ICE_TX_BUF_SKB: &sk_buff, unmap and consume_skb(), update stats
- * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free(), stats
+ * @ICE_TX_BUF_XDP_TX: &xdp_buff, unmap and page_frag_free_va(), stats
  * @ICE_TX_BUF_XDP_XMIT: &xdp_frame, unmap and xdp_return_frame(), stats
  * @ICE_TX_BUF_XSK_TX: &xdp_buff on XSk queue, xsk_buff_free(), stats
  */
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index df072ce767b1..c34cc02ad578 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -288,7 +288,7 @@ ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf,
 
 	switch (tx_buf->type) {
 	case ICE_TX_BUF_XDP_TX:
-		page_frag_free(tx_buf->raw_buf);
+		page_frag_free_va(tx_buf->raw_buf);
 		break;
 	case ICE_TX_BUF_XDP_XMIT:
 		xdp_return_frame_bulk(tx_buf->xdpf, bq);
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 3161a13079fe..c35b8f675b48 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -303,7 +303,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
 
 		/* free the skb */
 		if (ring_is_xdp(tx_ring))
-			page_frag_free(tx_buffer->data);
+			page_frag_free_va(tx_buffer->data);
 		else
 			napi_consume_skb(tx_buffer->skb, napi_budget);
 
@@ -2413,7 +2413,7 @@ static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring)
 
 		/* Free all the Tx ring sk_buffs */
 		if (ring_is_xdp(tx_ring))
-			page_frag_free(tx_buffer->data);
+			page_frag_free_va(tx_buffer->data);
 		else
 			dev_kfree_skb_any(tx_buffer->skb);
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index a85ac039d779..8eb5820b8a70 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -553,7 +553,7 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 	*dma = dma_map_single_attrs(pfvf->dev, buf, pool->rbsize,
 				    DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
 	if (unlikely(dma_mapping_error(pfvf->dev, *dma))) {
-		page_frag_free(buf);
+		page_frag_free_va(buf);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
index 7063c78bd35f..c4228719f8a4 100644
--- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c
+++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c
@@ -142,8 +142,8 @@ mtk_wed_wo_queue_refill(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q,
 		dma_addr_t addr;
 		void *buf;
 
-		buf = page_frag_alloc(&q->cache, q->buf_size,
-				      GFP_ATOMIC | GFP_DMA32);
+		buf = page_frag_alloc_va(&q->cache, q->buf_size,
+					 GFP_ATOMIC | GFP_DMA32);
 		if (!buf)
 			break;
 
diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index fdbcdcedcee9..79eddd74bfbb 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -500,7 +500,7 @@ static void nvme_tcp_exit_request(struct blk_mq_tag_set *set,
 {
 	struct nvme_tcp_request *req = blk_mq_rq_to_pdu(rq);
 
-	page_frag_free(req->pdu);
+	page_frag_free_va(req->pdu);
 }
 
 static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
@@ -514,7 +514,7 @@ static int nvme_tcp_init_request(struct blk_mq_tag_set *set,
 	struct nvme_tcp_queue *queue = &ctrl->queues[queue_idx];
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 
-	req->pdu = page_frag_alloc(&queue->pf_cache,
+	req->pdu = page_frag_alloc_va(&queue->pf_cache,
 		sizeof(struct nvme_tcp_cmd_pdu) + hdgst,
 		GFP_KERNEL | __GFP_ZERO);
 	if (!req->pdu)
@@ -1331,7 +1331,7 @@ static void nvme_tcp_free_async_req(struct nvme_tcp_ctrl *ctrl)
 {
 	struct nvme_tcp_request *async = &ctrl->async_req;
 
-	page_frag_free(async->pdu);
+	page_frag_free_va(async->pdu);
 }
 
 static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl)
@@ -1340,7 +1340,7 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl)
 	struct nvme_tcp_request *async = &ctrl->async_req;
 	u8 hdgst = nvme_tcp_hdgst_len(queue);
 
-	async->pdu = page_frag_alloc(&queue->pf_cache,
+	async->pdu = page_frag_alloc_va(&queue->pf_cache,
 		sizeof(struct nvme_tcp_cmd_pdu) + hdgst,
 		GFP_KERNEL | __GFP_ZERO);
 	if (!async->pdu)
diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index a5422e2c979a..ea356ce22672 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -1462,24 +1462,24 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
 	c->queue = queue;
 	c->req.port = queue->port->nport;
 
-	c->cmd_pdu = page_frag_alloc(&queue->pf_cache,
+	c->cmd_pdu = page_frag_alloc_va(&queue->pf_cache,
 			sizeof(*c->cmd_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
 	if (!c->cmd_pdu)
 		return -ENOMEM;
 	c->req.cmd = &c->cmd_pdu->cmd;
 
-	c->rsp_pdu = page_frag_alloc(&queue->pf_cache,
+	c->rsp_pdu = page_frag_alloc_va(&queue->pf_cache,
 			sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
 	if (!c->rsp_pdu)
 		goto out_free_cmd;
 	c->req.cqe = &c->rsp_pdu->cqe;
 
-	c->data_pdu = page_frag_alloc(&queue->pf_cache,
+	c->data_pdu = page_frag_alloc_va(&queue->pf_cache,
 			sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
 	if (!c->data_pdu)
 		goto out_free_rsp;
 
-	c->r2t_pdu = page_frag_alloc(&queue->pf_cache,
+	c->r2t_pdu = page_frag_alloc_va(&queue->pf_cache,
 			sizeof(*c->r2t_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO);
 	if (!c->r2t_pdu)
 		goto out_free_data;
@@ -1494,20 +1494,20 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue,
 
 	return 0;
 out_free_data:
-	page_frag_free(c->data_pdu);
+	page_frag_free_va(c->data_pdu);
 out_free_rsp:
-	page_frag_free(c->rsp_pdu);
+	page_frag_free_va(c->rsp_pdu);
 out_free_cmd:
-	page_frag_free(c->cmd_pdu);
+	page_frag_free_va(c->cmd_pdu);
 	return -ENOMEM;
 }
 
 static void nvmet_tcp_free_cmd(struct nvmet_tcp_cmd *c)
 {
-	page_frag_free(c->r2t_pdu);
-	page_frag_free(c->data_pdu);
-	page_frag_free(c->rsp_pdu);
-	page_frag_free(c->cmd_pdu);
+	page_frag_free_va(c->r2t_pdu);
+	page_frag_free_va(c->data_pdu);
+	page_frag_free_va(c->rsp_pdu);
+	page_frag_free_va(c->cmd_pdu);
 }
 
 static int nvmet_tcp_alloc_cmds(struct nvmet_tcp_queue *queue)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index c64ded183f8d..96d5ca299552 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -682,8 +682,8 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 		return -ENOSPC;
 
 	buflen += SKB_DATA_ALIGN(len + pad);
-	buf = page_frag_alloc_align(&net->pf_cache, buflen, GFP_KERNEL,
-				    SMP_CACHE_BYTES);
+	buf = page_frag_alloc_va_align(&net->pf_cache, buflen, GFP_KERNEL,
+				       SMP_CACHE_BYTES);
 	if (unlikely(!buf))
 		return -ENOMEM;
 
@@ -730,7 +730,7 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	return 0;
 
 err:
-	page_frag_free(buf);
+	page_frag_free_va(buf);
 	return ret;
 }
 
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index cc0ede0912f3..9d5d86b2d3ab 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -25,27 +25,29 @@ struct page_frag_cache {
 
 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(struct page_frag_cache *nc, unsigned int fragsz,
-		      gfp_t gfp_mask);
+void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
+			 gfp_t gfp_mask);
 
-static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
-					    unsigned int fragsz, gfp_t gfp_mask,
-					    unsigned int align)
+static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
+					       unsigned int fragsz,
+					       gfp_t gfp_mask,
+					       unsigned int align)
 {
 	nc->offset = ALIGN(nc->offset, align);
 
-	return page_frag_alloc(nc, fragsz, gfp_mask);
+	return page_frag_alloc_va(nc, fragsz, gfp_mask);
 }
 
-static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
-					  unsigned int fragsz, gfp_t gfp_mask,
-					  unsigned int align)
+static inline void *page_frag_alloc_va_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);
+	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
 }
 
-void page_frag_free(void *addr);
+void page_frag_free_va(void *addr);
 
 #endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2ef14dde5bbc..ccd0244f0f39 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3343,7 +3343,7 @@ static inline struct sk_buff *netdev_alloc_skb_ip_align(struct net_device *dev,
 
 static inline void skb_free_frag(void *addr)
 {
-	page_frag_free(addr);
+	page_frag_free_va(addr);
 }
 
 void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index a8e34416e960..3a6a237e7dd3 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -322,7 +322,7 @@ static int cpu_map_kthread_run(void *data)
 
 			/* Bring struct page memory area to curr CPU. Read by
 			 * build_skb_around via page_is_pfmemalloc(), and when
-			 * freed written by page_frag_free call.
+			 * freed written by page_frag_free_va call.
 			 */
 			prefetchw(page);
 		}
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 39c744c892ed..7f639af4e518 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -63,8 +63,8 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
-void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz,
-		      gfp_t gfp_mask)
+void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
+			 gfp_t gfp_mask)
 {
 	unsigned int size, offset;
 	struct page *page;
@@ -130,16 +130,16 @@ void *page_frag_alloc(struct page_frag_cache *nc, unsigned int fragsz,
 
 	return nc->va + offset;
 }
-EXPORT_SYMBOL(page_frag_alloc);
+EXPORT_SYMBOL(page_frag_alloc_va);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
  */
-void page_frag_free(void *addr)
+void page_frag_free_va(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);
+EXPORT_SYMBOL(page_frag_free_va);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e5196c284b33..2c10ebd133ac 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -311,7 +311,7 @@ void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align)
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align);
+	return __page_frag_alloc_va_align(&nc->page, fragsz, GFP_ATOMIC, align);
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
@@ -323,14 +323,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align)
 	if (in_hardirq() || irqs_disabled()) {
 		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
 
-		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align);
+		data = __page_frag_alloc_va_align(nc, fragsz, GFP_ATOMIC,
+						  align);
 	} else {
 		struct napi_alloc_cache *nc;
 
 		local_bh_disable();
 		nc = this_cpu_ptr(&napi_alloc_cache);
-		data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
-					       align);
+		data = __page_frag_alloc_va_align(&nc->page, fragsz, GFP_ATOMIC,
+						  align);
 		local_bh_enable();
 	}
 	return data;
@@ -740,12 +741,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 
 	if (in_hardirq() || irqs_disabled()) {
 		nc = this_cpu_ptr(&netdev_alloc_cache);
-		data = page_frag_alloc(nc, len, gfp_mask);
+		data = page_frag_alloc_va(nc, len, gfp_mask);
 		pfmemalloc = nc->pfmemalloc;
 	} else {
 		local_bh_disable();
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
-		data = page_frag_alloc(nc, len, gfp_mask);
+		data = page_frag_alloc_va(nc, len, gfp_mask);
 		pfmemalloc = nc->pfmemalloc;
 		local_bh_enable();
 	}
@@ -833,7 +834,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 	} else {
 		len = SKB_HEAD_ALIGN(len);
 
-		data = page_frag_alloc(&nc->page, len, gfp_mask);
+		data = page_frag_alloc_va(&nc->page, len, gfp_mask);
 		pfmemalloc = nc->page.pfmemalloc;
 	}
 
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 41693154e426..245a2d011aeb 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -391,7 +391,7 @@ void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		page_pool_put_full_page(page->pp, page, napi_direct);
 		break;
 	case MEM_TYPE_PAGE_SHARED:
-		page_frag_free(data);
+		page_frag_free_va(data);
 		break;
 	case MEM_TYPE_PAGE_ORDER0:
 		page = virt_to_page(data); /* Assumes order0 page*/
diff --git a/net/rxrpc/txbuf.c b/net/rxrpc/txbuf.c
index eb640875bf07..f2fa98360789 100644
--- a/net/rxrpc/txbuf.c
+++ b/net/rxrpc/txbuf.c
@@ -34,8 +34,8 @@ struct rxrpc_txbuf *rxrpc_alloc_data_txbuf(struct rxrpc_call *call, size_t data_
 
 	data_align = max_t(size_t, data_align, L1_CACHE_BYTES);
 	mutex_lock(&call->conn->tx_data_alloc_lock);
-	buf = page_frag_alloc_align(&call->conn->tx_data_alloc, total, gfp,
-				    data_align);
+	buf = page_frag_alloc_va_align(&call->conn->tx_data_alloc, total, gfp,
+				       data_align);
 	mutex_unlock(&call->conn->tx_data_alloc_lock);
 	if (!buf) {
 		kfree(txb);
@@ -97,17 +97,18 @@ struct rxrpc_txbuf *rxrpc_alloc_ack_txbuf(struct rxrpc_call *call, size_t sack_s
 	if (!txb)
 		return NULL;
 
-	buf = page_frag_alloc(&call->local->tx_alloc,
-			      sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp);
+	buf = page_frag_alloc_va(&call->local->tx_alloc,
+				 sizeof(*whdr) + sizeof(*ack) + 1 + 3 + sizeof(*trailer), gfp);
 	if (!buf) {
 		kfree(txb);
 		return NULL;
 	}
 
 	if (sack_size) {
-		buf2 = page_frag_alloc(&call->local->tx_alloc, sack_size, gfp);
+		buf2 = page_frag_alloc_va(&call->local->tx_alloc, sack_size,
+					  gfp);
 		if (!buf2) {
-			page_frag_free(buf);
+			page_frag_free_va(buf);
 			kfree(txb);
 			return NULL;
 		}
@@ -181,7 +182,7 @@ static void rxrpc_free_txbuf(struct rxrpc_txbuf *txb)
 			  rxrpc_txbuf_free);
 	for (i = 0; i < txb->nr_kvec; i++)
 		if (txb->kvec[i].iov_base)
-			page_frag_free(txb->kvec[i].iov_base);
+			page_frag_free_va(txb->kvec[i].iov_base);
 	kfree(txb);
 	atomic_dec(&rxrpc_nr_txbuf);
 }
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 545017a3daa4..055ed38cef97 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1231,8 +1231,8 @@ static int svc_tcp_sendmsg(struct svc_sock *svsk, struct svc_rqst *rqstp,
 	/* The stream record marker is copied into a temporary page
 	 * fragment buffer so that it can be included in rq_bvec.
 	 */
-	buf = page_frag_alloc(&svsk->sk_frag_cache, sizeof(marker),
-			      GFP_KERNEL);
+	buf = page_frag_alloc_va(&svsk->sk_frag_cache, sizeof(marker),
+				 GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 	memcpy(buf, &marker, sizeof(marker));
-- 
2.33.0

[PATCH net-next v1 05/12] mm: page_frag: add two inline helper for page_frag API

[Yunsheng Lin]

Add two inline helpers for page_frag API to avoid calling
accessing the field of 'struct page_frag_cache'.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 10 ++++++++++
 net/core/skbuff.c               |  4 ++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 9d5d86b2d3ab..fe5faa80b6c3 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -23,6 +23,16 @@ struct page_frag_cache {
 	bool pfmemalloc;
 };
 
+static inline void page_frag_cache_init(struct page_frag_cache *nc)
+{
+	nc->va = NULL;
+}
+
+static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
+{
+	return !!nc->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_va(struct page_frag_cache *nc, unsigned int fragsz,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2c10ebd133ac..4ad4db7403ba 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -742,12 +742,12 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 	if (in_hardirq() || irqs_disabled()) {
 		nc = this_cpu_ptr(&netdev_alloc_cache);
 		data = page_frag_alloc_va(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 	} else {
 		local_bh_disable();
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
 		data = page_frag_alloc_va(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 		local_bh_enable();
 	}
 
-- 
2.33.0

[PATCH net-next v1 06/12] mm: page_frag: reuse MSB of 'size' field for pfmemalloc

[Yunsheng Lin]

The '(PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)' case is for the
system with page size less than 32KB, which is 0x8000 bytes
requiring 16 bits space, change 'size' to 'size_mask' to avoid
using the MSB, and change 'pfmemalloc' field to reuse the that
MSB, so that we remove the orginal space needed by 'pfmemalloc'.

For another case, the MSB of 'offset' is reused for 'pfmemalloc'.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 13 ++++++++-----
 mm/page_frag_cache.c            |  5 +++--
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index fe5faa80b6c3..40a7d6da9ef0 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -12,15 +12,16 @@ struct page_frag_cache {
 	void *va;
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 	__u16 offset;
-	__u16 size;
+	__u16 size_mask:15;
+	__u16 pfmemalloc:1;
 #else
-	__u32 offset;
+	__u32 offset:31;
+	__u32 pfmemalloc:1;
 #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;
 };
 
 static inline void page_frag_cache_init(struct page_frag_cache *nc)
@@ -43,7 +44,9 @@ static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
 					       gfp_t gfp_mask,
 					       unsigned int align)
 {
-	nc->offset = ALIGN(nc->offset, align);
+	unsigned int offset = nc->offset;
+
+	nc->offset = ALIGN(offset, align);
 
 	return page_frag_alloc_va(nc, fragsz, gfp_mask);
 }
@@ -53,7 +56,7 @@ static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
 					     gfp_t gfp_mask,
 					     unsigned int align)
 {
-	WARN_ON_ONCE(!is_power_of_2(align));
+	WARN_ON_ONCE(!is_power_of_2(align) || align >= PAGE_SIZE);
 
 	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
 }
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 7f639af4e518..a02e57a439f0 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -29,7 +29,8 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 		   __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;
+	nc->size_mask = page ? PAGE_FRAG_CACHE_MAX_SIZE - 1 : PAGE_SIZE - 1;
+	VM_BUG_ON(page && nc->size_mask != PAGE_FRAG_CACHE_MAX_SIZE - 1);
 #endif
 	if (unlikely(!page))
 		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
@@ -88,7 +89,7 @@ void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 	/* if size can vary use size else just use PAGE_SIZE */
-	size = nc->size;
+	size = nc->size_mask + 1;
 #else
 	size = PAGE_SIZE;
 #endif
-- 
2.33.0

[PATCH net-next v1 07/12] mm: page_frag: reuse existing bit field of 'va' for pagecnt_bias

[Yunsheng Lin]

As alignment of 'va' is always aligned with the order of the
page allocated, we can reuse the LSB bits for the pagecount
bias, and remove the orginal space needed by 'pagecnt_bias'.
Also limit the 'fragsz' to be at least the size of
'usigned int' to match the limited pagecnt_bias.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 20 +++++++----
 mm/page_frag_cache.c            | 63 +++++++++++++++++++--------------
 2 files changed, 50 insertions(+), 33 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 40a7d6da9ef0..a97a1ac017d6 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -9,7 +9,18 @@
 #define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
 
 struct page_frag_cache {
-	void *va;
+	union {
+		void *va;
+		/* we maintain a pagecount bias, so that we dont dirty cache
+		 * line containing page->_refcount every time we allocate a
+		 * fragment. As 'va' is always aligned with the order of the
+		 * page allocated, we can reuse the LSB bits for the pagecount
+		 * bias, and its bit width happens to be indicated by the
+		 * 'size_mask' below.
+		 */
+		unsigned long pagecnt_bias;
+
+	};
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 	__u16 offset;
 	__u16 size_mask:15;
@@ -18,10 +29,6 @@ struct page_frag_cache {
 	__u32 offset:31;
 	__u32 pfmemalloc:1;
 #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;
 };
 
 static inline void page_frag_cache_init(struct page_frag_cache *nc)
@@ -56,7 +63,8 @@ static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
 					     gfp_t gfp_mask,
 					     unsigned int align)
 {
-	WARN_ON_ONCE(!is_power_of_2(align) || align >= PAGE_SIZE);
+	WARN_ON_ONCE(!is_power_of_2(align) || align >= PAGE_SIZE ||
+		     fragsz < sizeof(unsigned int));
 
 	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
 }
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index a02e57a439f0..ae1393d0619a 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -18,8 +18,8 @@
 #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)
+static bool __page_frag_cache_refill(struct page_frag_cache *nc,
+				     gfp_t gfp_mask)
 {
 	struct page *page = NULL;
 	gfp_t gfp = gfp_mask;
@@ -35,9 +35,26 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	if (unlikely(!page))
 		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
 
-	nc->va = page ? page_address(page) : NULL;
+	if (unlikely(!page)) {
+		nc->va = NULL;
+		return false;
+	}
+
+	nc->va = page_address(page);
 
-	return page;
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	VM_BUG_ON(nc->pagecnt_bias & nc->size_mask);
+	page_ref_add(page, nc->size_mask - 1);
+	nc->pagecnt_bias |= nc->size_mask;
+#else
+	VM_BUG_ON(nc->pagecnt_bias & (PAGE_SIZE - 1));
+	page_ref_add(page, PAGE_SIZE - 2);
+	nc->pagecnt_bias |= (PAGE_SIZE - 1);
+#endif
+
+	nc->pfmemalloc = page_is_pfmemalloc(page);
+	nc->offset = 0;
+	return true;
 }
 
 void page_frag_cache_drain(struct page_frag_cache *nc)
@@ -67,38 +84,31 @@ EXPORT_SYMBOL(__page_frag_cache_drain);
 void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 			 gfp_t gfp_mask)
 {
-	unsigned int size, offset;
+	unsigned long size_mask;
+	unsigned int offset;
 	struct page *page;
+	void *va;
 
 	if (unlikely(!nc->va)) {
 refill:
-		page = __page_frag_cache_refill(nc, gfp_mask);
-		if (!page)
+		if (!__page_frag_cache_refill(nc, gfp_mask))
 			return NULL;
-
-		/* 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 = 0;
 	}
 
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 	/* if size can vary use size else just use PAGE_SIZE */
-	size = nc->size_mask + 1;
+	size_mask = nc->size_mask;
 #else
-	size = PAGE_SIZE;
+	size_mask = PAGE_SIZE - 1;
 #endif
 
+	va = (void *)((unsigned long)nc->va & ~size_mask);
 	offset = nc->offset;
-	if (unlikely(offset + fragsz > size)) {
-		page = virt_to_page(nc->va);
 
-		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
+	if (unlikely(offset + fragsz > (size_mask + 1))) {
+		page = virt_to_page(va);
+
+		if (!page_ref_sub_and_test(page, nc->pagecnt_bias & size_mask))
 			goto refill;
 
 		if (unlikely(nc->pfmemalloc)) {
@@ -107,12 +117,11 @@ void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 		}
 
 		/* OK, page count is 0, we can safely set it */
-		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+		set_page_count(page, size_mask);
+		nc->pagecnt_bias |= size_mask;
 
-		/* reset page count bias and offset to start of new frag */
-		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
 		offset = 0;
-		if (unlikely(fragsz > size)) {
+		if (unlikely(fragsz > (size_mask + 1))) {
 			/*
 			 * The caller is trying to allocate a fragment
 			 * with fragsz > PAGE_SIZE but the cache isn't big
@@ -129,7 +138,7 @@ void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 	nc->pagecnt_bias--;
 	nc->offset = offset + fragsz;
 
-	return nc->va + offset;
+	return va + offset;
 }
 EXPORT_SYMBOL(page_frag_alloc_va);
 
-- 
2.33.0

[PATCH net-next v1 09/12] mm: page_frag: introduce prepare/commit API for page_frag

[Yunsheng Lin]

There are many use cases that need minimum memory in order
for forward progressing, but can do better if there is more
memory available.

Currently skb_page_frag_refill() API is used to solve the
above usecases, as mentioned in [1], its implementation is
similar to the one in mm subsystem.

To unify those two page_frag implementations, introduce a
prepare API to ensure minimum memory is satisfied and return
how much the actual memory is available to the caller.

And the caller can decide how much memory to use by calling
commit API, or not calling the commit API if deciding to not
use any memory.

Note it seems hard to decide which header files for caling
virt_to_page() in the inline helper, so macro is used instead
of inline helper to avoid dealing with that.

1. https://lore.kernel.org/all/20240228093013.8263-1-linyunsheng@huawei.com/

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 141 +++++++++++++++++++++++++++++++-
 mm/page_frag_cache.c            |  13 ++-
 2 files changed, 144 insertions(+), 10 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index a97a1ac017d6..28185969cd2c 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -43,8 +43,25 @@ static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 
 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_va(struct page_frag_cache *nc, unsigned int fragsz,
-			 gfp_t gfp_mask);
+void *page_frag_cache_refill(struct page_frag_cache *nc, unsigned int fragsz,
+			     gfp_t gfp_mask);
+
+static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
+				       unsigned int fragsz, gfp_t gfp_mask)
+{
+	unsigned int offset;
+	void *va;
+
+	va = page_frag_cache_refill(nc, fragsz, gfp_mask);
+	if (unlikely(!va))
+		return NULL;
+
+	offset = nc->offset;
+	nc->pagecnt_bias--;
+	nc->offset = offset + fragsz;
+
+	return va + offset;
+}
 
 static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
 					       unsigned int fragsz,
@@ -69,6 +86,126 @@ static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
 	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
 }
 
+static inline void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
+					       unsigned int *offset,
+					       unsigned int *size,
+					       gfp_t gfp_mask)
+{
+	void *va;
+
+	va = page_frag_cache_refill(nc, *size, gfp_mask);
+	if (unlikely(!va))
+		return NULL;
+
+	*offset = nc->offset;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	*size = nc->size_mask - *offset + 1;
+#else
+	*size = PAGE_SIZE - *offset;
+#endif
+
+	return va + *offset;
+}
+
+static inline void *page_frag_alloc_va_prepare_align(struct page_frag_cache *nc,
+						     unsigned int *offset,
+						     unsigned int *size,
+						     unsigned int align,
+						     gfp_t gfp_mask)
+{
+	WARN_ON_ONCE(!is_power_of_2(align) || align >= PAGE_SIZE ||
+		     *size < sizeof(unsigned int));
+
+	*offset = nc->offset;
+	nc->offset = ALIGN(*offset, align);
+	return page_frag_alloc_va_prepare(nc, offset, size, gfp_mask);
+}
+
+static inline void *__page_frag_alloc_pg_prepare(struct page_frag_cache *nc,
+						 unsigned int *offset,
+						 unsigned int *size,
+						 gfp_t gfp_mask)
+{
+	void *va;
+
+	va = page_frag_cache_refill(nc, *size, gfp_mask);
+	if (unlikely(!va))
+		return NULL;
+
+	*offset = nc->offset;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	*size = nc->size_mask - *offset + 1;
+#else
+	*size = PAGE_SIZE - *offset;
+#endif
+
+	return va;
+}
+
+#define page_frag_alloc_pg_prepare(nc, offset, size, gfp)		\
+({									\
+	struct page *__page = NULL;					\
+	void *__va;							\
+									\
+	__va = __page_frag_alloc_pg_prepare(nc, offset, size, gfp);	\
+	if (likely(__va))						\
+		__page = virt_to_page(__va);				\
+									\
+	__page;								\
+})
+
+static inline void *__page_frag_alloc_prepare(struct page_frag_cache *nc,
+					      unsigned int *offset,
+					      unsigned int *size,
+					      void **va, gfp_t gfp_mask)
+{
+	void *nc_va;
+
+	nc_va = page_frag_cache_refill(nc, *size, gfp_mask);
+	if (unlikely(!nc_va))
+		return NULL;
+
+	*offset = nc->offset;
+	*va = nc_va + *offset;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	*size = nc->size_mask - *offset + 1;
+#else
+	*size = PAGE_SIZE - *offset;
+#endif
+
+	return nc_va;
+}
+
+#define page_frag_alloc_prepare(nc, offset, size, va, gfp)		\
+({									\
+	struct page *__page = NULL;					\
+	void *__va;							\
+									\
+	__va = __page_frag_alloc_prepare(nc, offset, size, va, gfp);	\
+	if (likely(__va))						\
+		__page = virt_to_page(__va);				\
+									\
+	__page;								\
+})
+
+static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
+					  unsigned int offset,
+					  unsigned int size)
+{
+	nc->pagecnt_bias--;
+	nc->offset = offset + size;
+}
+
+static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
+						unsigned int offset,
+						unsigned int size)
+{
+	nc->offset = offset + size;
+}
+
 void page_frag_free_va(void *addr);
 
 #endif
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index ae1393d0619a..cbd0ed82a596 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -81,8 +81,8 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
-void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
-			 gfp_t gfp_mask)
+void *page_frag_cache_refill(struct page_frag_cache *nc, unsigned int fragsz,
+			     gfp_t gfp_mask)
 {
 	unsigned long size_mask;
 	unsigned int offset;
@@ -120,7 +120,7 @@ void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 		set_page_count(page, size_mask);
 		nc->pagecnt_bias |= size_mask;
 
-		offset = 0;
+		nc->offset = 0;
 		if (unlikely(fragsz > (size_mask + 1))) {
 			/*
 			 * The caller is trying to allocate a fragment
@@ -135,12 +135,9 @@ void *page_frag_alloc_va(struct page_frag_cache *nc, unsigned int fragsz,
 		}
 	}
 
-	nc->pagecnt_bias--;
-	nc->offset = offset + fragsz;
-
-	return va + offset;
+	return va;
 }
-EXPORT_SYMBOL(page_frag_alloc_va);
+EXPORT_SYMBOL(page_frag_cache_refill);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
-- 
2.33.0

[PATCH net-next v1 11/12] mm: page_frag: add a test module for page_frag

[Yunsheng Lin]

Basing on the lib/objpool.c, change it to something like a
ptrpool, so that we can utilize that to test the correctness
and performance of the page_frag.

The testing is done by ensuring that the fragments allocated
from a frag_frag_cache instance is pushed into a ptrpool
instance in a kthread binded to the first cpu, and a kthread
binded to the current node will pop the fragmemt from the
ptrpool and call page_frag_alloc_va() to free the fragmemt.

We may refactor out the common part between objpool and ptrpool
if this ptrpool thing turns out to be helpful for other place.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 mm/Kconfig.debug    |   8 +
 mm/Makefile         |   1 +
 mm/page_frag_test.c | 366 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 375 insertions(+)
 create mode 100644 mm/page_frag_test.c

diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index afc72fde0f03..1ebcd45f47d4 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -142,6 +142,14 @@ config DEBUG_PAGE_REF
 	  kernel code.  However the runtime performance overhead is virtually
 	  nil until the tracepoints are actually enabled.
 
+config DEBUG_PAGE_FRAG_TEST
+	tristate "Test module for page_frag"
+	default n
+	depends on m && DEBUG_KERNEL
+	help
+	  This builds the "page_frag_test" module that is used to test the
+	  correctness and performance of page_frag's implementation.
+
 config DEBUG_RODATA_TEST
     bool "Testcase for the marking rodata read-only"
     depends on STRICT_KERNEL_RWX
diff --git a/mm/Makefile b/mm/Makefile
index 146c481c006f..8b62f5de48a7 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -102,6 +102,7 @@ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
 obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
 obj-$(CONFIG_DEBUG_RODATA_TEST) += rodata_test.o
+obj-$(CONFIG_DEBUG_PAGE_FRAG_TEST) += page_frag_test.o
 obj-$(CONFIG_DEBUG_VM_PGTABLE) += debug_vm_pgtable.o
 obj-$(CONFIG_PAGE_OWNER) += page_owner.o
 obj-$(CONFIG_MEMORY_ISOLATION) += page_isolation.o
diff --git a/mm/page_frag_test.c b/mm/page_frag_test.c
new file mode 100644
index 000000000000..e311c2e7ff49
--- /dev/null
+++ b/mm/page_frag_test.c
@@ -0,0 +1,366 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test module for page_frag cache
+ *
+ * Copyright: linyunsheng@huawei.com
+ */
+
+#include <linux/module.h>
+#include <linux/page_frag_cache.h>
+#include <linux/version.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/atomic.h>
+#include <linux/irqflags.h>
+#include <linux/cpumask.h>
+#include <linux/log2.h>
+#include <linux/completion.h>
+#include <linux/kthread.h>
+
+#define OBJPOOL_NR_OBJECT_MAX	BIT(24)
+
+struct objpool_slot {
+	u32 head;
+	u32 tail;
+	u32 last;
+	u32 mask;
+	void *entries[];
+} __packed;
+
+struct objpool_head {
+	int nr_cpus;
+	int capacity;
+	struct objpool_slot **cpu_slots;
+};
+
+/* initialize percpu objpool_slot */
+static void objpool_init_percpu_slot(struct objpool_head *pool,
+				     struct objpool_slot *slot)
+{
+	/* initialize elements of percpu objpool_slot */
+	slot->mask = pool->capacity - 1;
+}
+
+/* allocate and initialize percpu slots */
+static int objpool_init_percpu_slots(struct objpool_head *pool,
+				     int nr_objs, gfp_t gfp)
+{
+	int i;
+
+	for (i = 0; i < pool->nr_cpus; i++) {
+		struct objpool_slot *slot;
+		int size;
+
+		/* skip the cpu node which could never be present */
+		if (!cpu_possible(i))
+			continue;
+
+		size = struct_size(slot, entries, pool->capacity);
+
+		/*
+		 * here we allocate percpu-slot & objs together in a single
+		 * allocation to make it more compact, taking advantage of
+		 * warm caches and TLB hits. in default vmalloc is used to
+		 * reduce the pressure of kernel slab system. as we know,
+		 * mimimal size of vmalloc is one page since vmalloc would
+		 * always align the requested size to page size
+		 */
+		if (gfp & GFP_ATOMIC)
+			slot = kmalloc_node(size, gfp, cpu_to_node(i));
+		else
+			slot = __vmalloc_node(size, sizeof(void *), gfp,
+					      cpu_to_node(i),
+					      __builtin_return_address(0));
+		if (!slot)
+			return -ENOMEM;
+
+		memset(slot, 0, size);
+		pool->cpu_slots[i] = slot;
+
+		objpool_init_percpu_slot(pool, slot);
+	}
+
+	return 0;
+}
+
+/* cleanup all percpu slots of the object pool */
+static void objpool_fini_percpu_slots(struct objpool_head *pool)
+{
+	int i;
+
+	if (!pool->cpu_slots)
+		return;
+
+	for (i = 0; i < pool->nr_cpus; i++)
+		kvfree(pool->cpu_slots[i]);
+	kfree(pool->cpu_slots);
+}
+
+/* initialize object pool and pre-allocate objects */
+static int objpool_init(struct objpool_head *pool, int nr_objs, gfp_t gfp)
+{
+	int rc, capacity, slot_size;
+
+	/* check input parameters */
+	if (nr_objs <= 0 || nr_objs > OBJPOOL_NR_OBJECT_MAX)
+		return -EINVAL;
+
+	/* calculate capacity of percpu objpool_slot */
+	capacity = roundup_pow_of_two(nr_objs);
+	if (!capacity)
+		return -EINVAL;
+
+	gfp = gfp & ~__GFP_ZERO;
+
+	/* initialize objpool pool */
+	memset(pool, 0, sizeof(struct objpool_head));
+	pool->nr_cpus = nr_cpu_ids;
+	pool->capacity = capacity;
+	slot_size = pool->nr_cpus * sizeof(struct objpool_slot *);
+	pool->cpu_slots = kzalloc(slot_size, gfp);
+	if (!pool->cpu_slots)
+		return -ENOMEM;
+
+	/* initialize per-cpu slots */
+	rc = objpool_init_percpu_slots(pool, nr_objs, gfp);
+	if (rc)
+		objpool_fini_percpu_slots(pool);
+
+	return rc;
+}
+
+/* adding object to slot, abort if the slot was already full */
+static int objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	u32 head, tail;
+
+	/* loading tail and head as a local snapshot, tail first */
+	tail = READ_ONCE(slot->tail);
+
+	do {
+		head = READ_ONCE(slot->head);
+		/* slot is full */
+		if (unlikely(tail - head >= pool->capacity))
+			return -ENOSPC;
+	} while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1));
+
+	/* now the tail position is reserved for the given obj */
+	WRITE_ONCE(slot->entries[tail & slot->mask], obj);
+	/* update sequence to make this obj available for pop() */
+	smp_store_release(&slot->last, tail + 1);
+
+	return 0;
+}
+
+/* reclaim an object to object pool */
+static int objpool_push(void *obj, struct objpool_head *pool)
+{
+	unsigned long flags;
+	int rc;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+	rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id());
+	raw_local_irq_restore(flags);
+
+	return rc;
+}
+
+/* try to retrieve object from slot */
+static void *objpool_try_get_slot(struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	/* load head snapshot, other cpus may change it */
+	u32 head = smp_load_acquire(&slot->head);
+
+	while (head != READ_ONCE(slot->last)) {
+		void *obj;
+
+		/*
+		 * data visibility of 'last' and 'head' could be out of
+		 * order since memory updating of 'last' and 'head' are
+		 * performed in push() and pop() independently
+		 *
+		 * before any retrieving attempts, pop() must guarantee
+		 * 'last' is behind 'head', that is to say, there must
+		 * be available objects in slot, which could be ensured
+		 * by condition 'last != head && last - head <= nr_objs'
+		 * that is equivalent to 'last - head - 1 < nr_objs' as
+		 * 'last' and 'head' are both unsigned int32
+		 */
+		if (READ_ONCE(slot->last) - head - 1 >= pool->capacity) {
+			head = READ_ONCE(slot->head);
+			continue;
+		}
+
+		/* obj must be retrieved before moving forward head */
+		obj = READ_ONCE(slot->entries[head & slot->mask]);
+
+		/* move head forward to mark it's consumption */
+		if (try_cmpxchg_release(&slot->head, &head, head + 1))
+			return obj;
+	}
+
+	return NULL;
+}
+
+/* allocate an object from object pool */
+static void *objpool_pop(struct objpool_head *pool)
+{
+	void *obj = NULL;
+	unsigned long flags;
+	int i, cpu;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+
+	cpu = raw_smp_processor_id();
+	for (i = 0; i < num_possible_cpus(); i++) {
+		obj = objpool_try_get_slot(pool, cpu);
+		if (obj)
+			break;
+		cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1);
+	}
+	raw_local_irq_restore(flags);
+
+	return obj;
+}
+
+/* release whole objpool forcely */
+static void objpool_free(struct objpool_head *pool)
+{
+	if (!pool->cpu_slots)
+		return;
+
+	/* release percpu slots */
+	objpool_fini_percpu_slots(pool);
+}
+
+static struct objpool_head ptr_pool;
+static int nr_objs = 512;
+static int nr_test = 5120000;
+static atomic_t nthreads;
+static struct completion wait;
+struct page_frag_cache test_frag;
+
+module_param(nr_test, int, 0600);
+MODULE_PARM_DESC(nr_test, "number of iterations to test");
+
+static int page_frag_pop_thread(void *arg)
+{
+	struct objpool_head *pool = arg;
+	int nr = nr_test;
+
+	pr_info("page_frag pop test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (nr > 0) {
+		void *obj = objpool_pop(pool);
+
+		if (obj) {
+			nr--;
+			page_frag_free_va(obj);
+		} else {
+			cond_resched();
+		}
+	}
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	pr_info("page_frag pop test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	return 0;
+}
+
+static int page_frag_push_thread(void *arg)
+{
+	struct objpool_head *pool = arg;
+	int nr = nr_test;
+
+	pr_info("page_frag push test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (nr > 0) {
+		unsigned int size = get_random_u32();
+		void *va;
+		int ret;
+
+		size = clamp(size, sizeof(unsigned int), PAGE_SIZE);
+		va = page_frag_alloc_va(&test_frag, size, GFP_KERNEL);
+		if (!va)
+			continue;
+
+		ret = objpool_push(va, pool);
+		if (ret) {
+			page_frag_free_va(va);
+			cond_resched();
+		} else {
+			nr--;
+		}
+	}
+
+	pr_info("page_frag push test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	return 0;
+}
+
+static int __init page_frag_test_init(void)
+{
+	struct task_struct *tsk_push, *tsk_pop;
+	ktime_t start;
+	u64 duration;
+	int ret;
+
+	page_frag_cache_init(&test_frag);
+	atomic_set(&nthreads, 2);
+	init_completion(&wait);
+
+	ret = objpool_init(&ptr_pool, nr_objs, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_pool,
+					 cpumask_first(cpu_online_mask),
+					 "page_frag_push");
+	if (IS_ERR(tsk_push))
+		return PTR_ERR(tsk_push);
+
+	tsk_pop = kthread_create(page_frag_pop_thread, &ptr_pool,
+				 "page_frag_pop");
+	if (IS_ERR(tsk_pop)) {
+		kthread_stop(tsk_push);
+		return PTR_ERR(tsk_pop);
+	}
+
+	start = ktime_get();
+	wake_up_process(tsk_push);
+	wake_up_process(tsk_pop);
+
+	pr_info("waiting for test to complete\n");
+	wait_for_completion(&wait);
+
+	duration = (u64)ktime_us_delta(ktime_get(), start);
+	pr_info("%d of iterations took: %lluus\n", nr_test, duration);
+
+	objpool_free(&ptr_pool);
+	page_frag_cache_drain(&test_frag);
+
+	return -EAGAIN;
+}
+
+static void __exit page_frag_test_exit(void)
+{
+}
+
+module_init(page_frag_test_init);
+module_exit(page_frag_test_exit);
+
+MODULE_LICENSE("GPL");
-- 
2.33.0

[PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Yunsheng Lin]

Update documentation about design, implementation and API usages
for page_frag.

Also update MAINTAINERS for page_frag. Alexander seems to be the
orginal author for page_frag, we can add him to the MAINTAINERS
later if we have an ack from him.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 Documentation/mm/page_frags.rst | 115 ++++++++++++++++++----------
 MAINTAINERS                     |  10 +++
 include/linux/page_frag_cache.h | 128 ++++++++++++++++++++++++++++++++
 mm/page_frag_cache.c            |  51 ++++++++++---
 4 files changed, 256 insertions(+), 48 deletions(-)

diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 503ca6cdb804..77256dfb58bf 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -1,43 +1,80 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==============
 Page fragments
 ==============
 
-A page fragment is an arbitrary-length arbitrary-offset area of memory
-which resides within a 0 or higher order compound page.  Multiple
-fragments within that page are individually refcounted, in the page's
-reference counter.
-
-The page_frag functions, page_frag_alloc and page_frag_free, 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.
-
-In order to make use of the page fragment APIs a backing page fragment
-cache is needed.  This provides a central point for the fragment allocation
-and tracks allows multiple calls to make use of a cached page.  The
-advantage to doing this is that multiple calls to get_page can be avoided
-which can be expensive at allocation time.  However due to the nature of
-this caching it is required that any calls to the cache be protected by
-either a per-cpu limitation, or a per-cpu limitation and forcing interrupts
-to be disabled when executing the fragment allocation.
-
-The network stack uses two separate caches per CPU to handle fragment
-allocation.  The netdev_alloc_cache is used by callers making use of the
-netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
-used by callers of the __napi_alloc_frag and napi_alloc_skb calls.  The
-main difference between these two calls is the context in which they may be
-called.  The "netdev" prefixed functions are usable in any context as these
-functions will disable interrupts, while the "napi" prefixed functions are
-only usable within the softirq context.
-
-Many network device drivers use a similar methodology for allocating page
-fragments, but the page fragments are cached at the ring or descriptor
-level.  In order to enable these cases it is necessary to provide a generic
-way of tearing down a page cache.  For this reason __page_frag_cache_drain
-was implemented.  It allows for freeing multiple references from a single
-page via a single call.  The advantage to doing this is that it allows for
-cleaning up the multiple references that were added to a page in order to
-avoid calling get_page per allocation.
-
-Alexander Duyck, Nov 29, 2016.
+.. kernel-doc:: mm/page_frag_cache.c
+   :doc: page_frag allocator
+
+Architecture overview
+=====================
+
+.. code-block:: none
+
+    +----------------------+
+    | page_frag API caller |
+    +----------------------+
+            ^
+            |
+            |
+            |
+            v
+    +----------------------------------------------+
+    |          request page fragment               |
+    +----------------------------------------------+
+        ^                                        ^
+        |                                        |
+        | Cache empty or not enough              |
+        |                                        |
+        v                                        |
+    +--------------------------------+           |
+    | refill cache with order 3 page |           |
+    +--------------------------------+           |
+     ^                  ^                        |
+     |                  |                        |
+     |                  | Refill failed          |
+     |                  |                        | Cache is enough
+     |                  |                        |
+     |                  v                        |
+     |    +----------------------------------+   |
+     |    |  refill cache with order 0 page  |   |
+     |    +----------------------------------+   |
+     |                       ^                   |
+     | Refill succeed        |                   |
+     |                       | Refill succeed    |
+     |                       |                   |
+     v                       v                   v
+    +----------------------------------------------+
+    |       allocate fragment from cache           |
+    +----------------------------------------------+
+
+API interface
+=============
+As the design and implementation of page_frag API, the allocation side does not
+allow concurrent calling, it is assumed that the caller must ensure there is not
+concurrent alloc calling to the same page_frag_cache instance by using it's own
+lock or rely on some lockless guarantee like NAPI softirq.
+
+Depending on different use cases, callers expecting to deal with va, page or
+both va and page for them may call page_frag_alloc_va(), page_frag_alloc_pg(),
+or page_frag_alloc() accordingly.
+
+There is also a use case that need minimum memory in order for forward
+progressing, but can do better if there is more memory available. Introduce
+page_frag_alloc_prepare() and page_frag_alloc_commit() related API, the caller
+requests the minimum memory it need and the prepare API will return the maximum
+size of the fragment returned, caller need to report back to the page_frag core
+how much memory it actually use by calling commit API, or not calling the commit
+API if deciding to not use any memory.
+
+.. kernel-doc:: include/linux/page_frag_cache.h
+   :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
+                 page_frag_alloc_va __page_frag_alloc_va_align
+                 page_frag_alloc_va_align page_frag_alloc_va_prepare
+                 page_frag_alloc_va_prepare_align page_frag_alloc_pg_prepare
+                 page_frag_alloc_prepare page_frag_alloc_commit
+                 page_frag_alloc_commit_noref page_frag_free_va
+
+.. kernel-doc:: mm/page_frag_cache.c
+   :identifiers: page_frag_cache_drain
diff --git a/MAINTAINERS b/MAINTAINERS
index 4745ea94d463..2f84aba59428 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16683,6 +16683,16 @@ F:	mm/page-writeback.c
 F:	mm/readahead.c
 F:	mm/truncate.c
 
+PAGE FRAG
+M:	Yunsheng Lin <linyunsheng@huawei.com>
+L:	linux-mm@kvack.org
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/mm/page_frags.rst
+F:	include/linux/page_frag_cache.h
+F:	mm/page_frag_cache.c
+F:	mm/page_frag_test.c
+
 PAGE POOL
 M:	Jesper Dangaard Brouer <hawk@kernel.org>
 M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 28185969cd2c..d8edbecdd179 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -31,11 +31,23 @@ struct page_frag_cache {
 #endif
 };
 
+/**
+ * page_frag_cache_init() - Init page_frag cache.
+ * @nc: page_frag cache from which to init
+ *
+ * Inline helper to init the page_frag cache.
+ */
 static inline void page_frag_cache_init(struct page_frag_cache *nc)
 {
 	nc->va = NULL;
 }
 
+/**
+ * page_frag_cache_is_pfmemalloc() - Check for pfmemalloc.
+ * @nc: page_frag cache from which to check
+ *
+ * Used to check if the current page in page_frag cache is pfmemalloc'ed.
+ */
 static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 {
 	return !!nc->pfmemalloc;
@@ -46,6 +58,17 @@ void __page_frag_cache_drain(struct page *page, unsigned int count);
 void *page_frag_cache_refill(struct page_frag_cache *nc, unsigned int fragsz,
 			     gfp_t gfp_mask);
 
+/**
+ * page_frag_alloc_va() - Alloc a page fragment.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Get a page fragment from page_frag cache.
+ *
+ * Return:
+ * Return va of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
 				       unsigned int fragsz, gfp_t gfp_mask)
 {
@@ -63,6 +86,19 @@ static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
 	return va + offset;
 }
 
+/**
+ * __page_frag_alloc_va_align() - Alloc a page fragment with aligning
+ * requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align: the requested aligning requirement
+ *
+ * Get a page fragment from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * Return va of the page fragment, otherwise return NULL.
+ */
 static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
 					       unsigned int fragsz,
 					       gfp_t gfp_mask,
@@ -75,6 +111,19 @@ static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
 	return page_frag_alloc_va(nc, fragsz, gfp_mask);
 }
 
+/**
+ * page_frag_alloc_va_align() - Alloc a page fragment with aligning requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align: the requested aligning requirement
+ *
+ * WARN_ON_ONCE() checking for align and fragsz before getting a page fragment
+ * from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * Return va of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
 					     unsigned int fragsz,
 					     gfp_t gfp_mask,
@@ -86,6 +135,19 @@ static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
 	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
 }
 
+/**
+ * page_frag_alloc_va_prepare() - Prepare allocing a page fragment.
+ * @nc: page_frag cache from which to prepare
+ * @offset: out as the offset of the page fragment
+ * @size: in as the requested size, out as the available size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
+ * report the maximum size of the page fragment the caller can use.
+ *
+ * Return:
+ * Return va of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
 					       unsigned int *offset,
 					       unsigned int *size,
@@ -108,6 +170,21 @@ static inline void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
 	return va + *offset;
 }
 
+/**
+ * page_frag_alloc_va_prepare_align() - Prepare allocing a page fragment with
+ * aligning requirement.
+ * @nc: page_frag cache from which to prepare
+ * @offset: out as the offset of the page fragment
+ * @size: in as the requested size, out as the available size
+ * @align: the requested aligning requirement
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare an aligned page fragment with minimum size of ‘size’, 'size' is also
+ * used to report the maximum size of the page fragment the caller can use.
+ *
+ * Return:
+ * Return va of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_va_prepare_align(struct page_frag_cache *nc,
 						     unsigned int *offset,
 						     unsigned int *size,
@@ -144,6 +221,19 @@ static inline void *__page_frag_alloc_pg_prepare(struct page_frag_cache *nc,
 	return va;
 }
 
+/**
+ * page_frag_alloc_pg_prepare - Prepare allocing a page fragment.
+ * @nc: page_frag cache from which to prepare
+ * @offset: out as the offset of the page fragment
+ * @size: in as the requested size, out as the available size
+ * @gfp: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
+ * report the maximum size of the page fragment the caller can use.
+ *
+ * Return:
+ * Return the page fragment, otherwise return NULL.
+ */
 #define page_frag_alloc_pg_prepare(nc, offset, size, gfp)		\
 ({									\
 	struct page *__page = NULL;					\
@@ -179,6 +269,21 @@ static inline void *__page_frag_alloc_prepare(struct page_frag_cache *nc,
 	return nc_va;
 }
 
+/**
+ * page_frag_alloc_prepare - Prepare allocing a page fragment.
+ * @nc: page_frag cache from which to prepare
+ * @offset: out as the offset of the page fragment
+ * @size: in as the requested size, out as the available size
+ * @va: out as the va of the returned page fragment
+ * @gfp: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
+ * report the maximum size of the page fragment. Return both 'page' and 'va' of
+ * the fragment to the caller.
+ *
+ * Return:
+ * Return the page fragment, otherwise return NULL.
+ */
 #define page_frag_alloc_prepare(nc, offset, size, va, gfp)		\
 ({									\
 	struct page *__page = NULL;					\
@@ -191,6 +296,14 @@ static inline void *__page_frag_alloc_prepare(struct page_frag_cache *nc,
 	__page;								\
 })
 
+/**
+ * page_frag_alloc_commit - Commit allocing a page fragment.
+ * @nc: page_frag cache from which to commit
+ * @offset: offset of the page fragment
+ * @size: size of the page fragment has been used
+ *
+ * Commit the alloc preparing by passing offset and the actual used size.
+ */
 static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
 					  unsigned int offset,
 					  unsigned int size)
@@ -199,6 +312,17 @@ static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
 	nc->offset = offset + size;
 }
 
+/**
+ * page_frag_alloc_commit_noref - Commit allocing a page fragment without taking
+ * page refcount.
+ * @nc: page_frag cache from which to commit
+ * @offset: offset of the page fragment
+ * @size: size of the page fragment has been used
+ *
+ * Commit the alloc preparing by passing offset and the actual used size, but
+ * not taking page refcount. Mostly used for fragmemt coaleasing case when the
+ * current fragmemt can share the same refcount with previous fragmemt.
+ */
 static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
 						unsigned int offset,
 						unsigned int size)
@@ -206,6 +330,10 @@ static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
 	nc->offset = offset + size;
 }
 
+/**
+ * page_frag_free_va - Free a page fragment by va.
+ * @addr: va of page fragment to be freed
+ */
 void page_frag_free_va(void *addr);
 
 #endif
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index cbd0ed82a596..0c76ec006c22 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -1,15 +1,44 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/* Page fragment allocator
+
+/**
+ * DOC: page_frag allocator
+ *
+ * A page fragment is an arbitrary-length arbitrary-offset area of memory which
+ * resides within a 0 or higher order compound page.  Multiple fragments within
+ * that page are individually refcounted, in the page's reference counter.
+ *
+ * The page_frag functions, page_frag_alloc* and page_frag_free*, 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.
  *
- * 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.
+ * In order to make use of the page fragment APIs a backing page fragment cache
+ * is needed.  This provides a central point for the fragment allocation and
+ * tracks allows multiple calls to make use of a cached page.  The advantage to
+ * doing this is that multiple calls to get_page can be avoided which can be
+ * expensive at allocation time.  However due to the nature of this caching it
+ * is required that any calls to the cache be protected by either a per-cpu
+ * limitation, or a per-cpu limitation and forcing interrupts to be disabled
+ * when executing the fragment allocation.
  *
- * 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.
+ * The network stack uses two separate caches per CPU to handle fragment
+ * allocation.  The netdev_alloc_cache is used by callers making use of the
+ * netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
+ * used by callers of the __napi_alloc_frag and napi_alloc_skb calls.  The
+ * main difference between these two calls is the context in which they may be
+ * called.  The "netdev" prefixed functions are usable in any context as these
+ * functions will disable interrupts, while the "napi" prefixed functions are
+ * only usable within the softirq context.
+ *
+ * Many network device drivers use a similar methodology for allocating page
+ * fragments, but the page fragments are cached at the ring or descriptor
+ * level.  In order to enable these cases it is necessary to provide a generic
+ * way of tearing down a page cache.  For this reason __page_frag_cache_drain
+ * was implemented.  It allows for freeing multiple references from a single
+ * page via a single call.  The advantage to doing this is that it allows for
+ * cleaning up the multiple references that were added to a page in order to
+ * avoid calling get_page per allocation.
  */
 
 #include <linux/export.h>
@@ -57,6 +86,10 @@ static bool __page_frag_cache_refill(struct page_frag_cache *nc,
 	return true;
 }
 
+/**
+ * page_frag_cache_drain - Drain the current page from page_frag cache.
+ * @nc: page_frag cache from which to drain
+ */
 void page_frag_cache_drain(struct page_frag_cache *nc)
 {
 	if (!nc->va)
-- 
2.33.0

Re: [PATCH net-next v1 01/12] mm: Move the page fragment allocator from page_alloc into its own file

[Alexander H Duyck]

On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> 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.

Instead of doing this all as one patch it would be better to split this
into 2. Make the refactor first, and then move the code. Don't do it
all in one patch.

Adding a refactor that changes out functions called in addition to
moving the functions makes it very difficult to provide useful feedback
and review.

One of the big things with free_unref_page vx free_the_page is a check
to see how costly it is to free the page. Right now the page frags are
on the verge of crossing that threshold with defaulting to order 3
pages.

> 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/20230411160902.4134381-3-dhowells@redhat.com/

The problem with moving this out to networking is the fact that this is
memory allocation. In my opinion it would better for it to live there.

> CC: David Howells <dhowells@redhat.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>  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_cache.c            | 149 ++++++++++++++++++++++++++++++++
>  7 files changed, 198 insertions(+), 176 deletions(-)
>  create mode 100644 include/linux/page_frag_cache.h
>  create mode 100644 mm/page_frag_cache.c

I would add comments inline below about the changes you made but it is
hard to keep them in any sort of context since what is contained in the
"-" block is well spaced out from the "+" block.

Re: [PATCH net-next v1 02/12] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Alexander H Duyck]

On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> We are above to use page_frag_alloc_*() API to not just
> allocate memory for skb->data, but also use them to do
> the memory allocation for skb frag too. Currently the
> implementation of page_frag in mm subsystem is running
> the offset as a countdown rather than count-up value,
> there may have several advantages to that as mentioned
> in [1], but it may have some disadvantages, for example,
> it may disable skb frag coaleasing and more correct cache
> prefetching
> 
> We have a trade-off to make in order to have a unified
> implementation and API for page_frag, so use a initial zero
> offset in this patch, and the following patch will try to
> make some optimization to aovid the disadvantages as much
> as possible.
> 
> 1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/
> 
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>  mm/page_frag_cache.c | 31 ++++++++++++++-----------------
>  1 file changed, 14 insertions(+), 17 deletions(-)
> 
> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> index a0f90ba25200..3e3e88d9af90 100644
> --- a/mm/page_frag_cache.c
> +++ b/mm/page_frag_cache.c
> @@ -67,9 +67,8 @@ 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;
> +	unsigned int size, offset;
>  	struct page *page;
> -	int offset;
>  
>  	if (unlikely(!nc->va)) {
>  refill:
> @@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>  		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.
>  		 */
> @@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>  		/* 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;
> +		nc->offset = 0;
>  	}
>  
> -	offset = nc->offset - fragsz;
> -	if (unlikely(offset < 0)) {
> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> +	/* if size can vary use size else just use PAGE_SIZE */
> +	size = nc->size;
> +#else
> +	size = PAGE_SIZE;
> +#endif
> +
> +	offset = ALIGN(nc->offset, -align_mask);
> +	if (unlikely(offset + fragsz > size)) {

Rather than using "ALIGN" with a negative value it would probably make
more sense to use __ALIGN_KERNEL_MASK with ~align_mask. I am not sure
how well the compiler sorts out the use of negatives to flip values
that are then converted to masks with the "(a) - 1".

>  		page = virt_to_page(nc->va);
>  
>  		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
> @@ -104,17 +106,13 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>  			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)) {
> +		offset = 0;
> +		if (unlikely(fragsz > size)) {
>  			/*
>  			 * The caller is trying to allocate a fragment
>  			 * with fragsz > PAGE_SIZE but the cache isn't big
> @@ -129,8 +127,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>  	}
>  
>  	nc->pagecnt_bias--;
> -	offset &= align_mask;
> -	nc->offset = offset;
> +	nc->offset = offset + fragsz;
>  
>  	return nc->va + offset;
>  }

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Alexander H Duyck]

On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> Update documentation about design, implementation and API usages
> for page_frag.
> 
> Also update MAINTAINERS for page_frag. Alexander seems to be the
> orginal author for page_frag, we can add him to the MAINTAINERS
> later if we have an ack from him.
> 
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>

Again, this seems more like 2 different pathches at least. One for the
Documentation and MAINTAINERS changes, and one for the function
documentation.

> ---
>  Documentation/mm/page_frags.rst | 115 ++++++++++++++++++----------
>  MAINTAINERS                     |  10 +++
>  include/linux/page_frag_cache.h | 128 ++++++++++++++++++++++++++++++++
>  mm/page_frag_cache.c            |  51 ++++++++++---
>  4 files changed, 256 insertions(+), 48 deletions(-)
> 
> diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
> index 503ca6cdb804..77256dfb58bf 100644
> --- a/Documentation/mm/page_frags.rst
> +++ b/Documentation/mm/page_frags.rst
> @@ -1,43 +1,80 @@
> +.. SPDX-License-Identifier: GPL-2.0
> +
>  ==============
>  Page fragments
>  ==============
>  
> -A page fragment is an arbitrary-length arbitrary-offset area of memory
> -which resides within a 0 or higher order compound page.  Multiple
> -fragments within that page are individually refcounted, in the page's
> -reference counter.
> -
> -The page_frag functions, page_frag_alloc and page_frag_free, 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.
> -
> -In order to make use of the page fragment APIs a backing page fragment
> -cache is needed.  This provides a central point for the fragment allocation
> -and tracks allows multiple calls to make use of a cached page.  The
> -advantage to doing this is that multiple calls to get_page can be avoided
> -which can be expensive at allocation time.  However due to the nature of
> -this caching it is required that any calls to the cache be protected by
> -either a per-cpu limitation, or a per-cpu limitation and forcing interrupts
> -to be disabled when executing the fragment allocation.
> -
> -The network stack uses two separate caches per CPU to handle fragment
> -allocation.  The netdev_alloc_cache is used by callers making use of the
> -netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
> -used by callers of the __napi_alloc_frag and napi_alloc_skb calls.  The
> -main difference between these two calls is the context in which they may be
> -called.  The "netdev" prefixed functions are usable in any context as these
> -functions will disable interrupts, while the "napi" prefixed functions are
> -only usable within the softirq context.
> -
> -Many network device drivers use a similar methodology for allocating page
> -fragments, but the page fragments are cached at the ring or descriptor
> -level.  In order to enable these cases it is necessary to provide a generic
> -way of tearing down a page cache.  For this reason __page_frag_cache_drain
> -was implemented.  It allows for freeing multiple references from a single
> -page via a single call.  The advantage to doing this is that it allows for
> -cleaning up the multiple references that were added to a page in order to
> -avoid calling get_page per allocation.
> -
> -Alexander Duyck, Nov 29, 2016.

What is the point of removing this just to add it to a C file further
down in the diff? Honestly I am not a fan of all the noise this is
adding to these diffs. Can we do a little less moving of lines for the
sake of moving them? All it does is pollute the git blame if you try to
figure out the origin of the lines.

> +.. kernel-doc:: mm/page_frag_cache.c
> +   :doc: page_frag allocator
> +
> +Architecture overview
> +=====================
> +
> +.. code-block:: none
> +
> +    +----------------------+
> +    | page_frag API caller |
> +    +----------------------+
> +            ^
> +            |
> +            |
> +            |
> +            v
> +    +----------------------------------------------+
> +    |          request page fragment               |
> +    +----------------------------------------------+
> +        ^                                        ^
> +        |                                        |
> +        | Cache empty or not enough              |
> +        |                                        |
> +        v                                        |
> +    +--------------------------------+           |
> +    | refill cache with order 3 page |           |
> +    +--------------------------------+           |
> +     ^                  ^                        |
> +     |                  |                        |
> +     |                  | Refill failed          |
> +     |                  |                        | Cache is enough
> +     |                  |                        |
> +     |                  v                        |
> +     |    +----------------------------------+   |
> +     |    |  refill cache with order 0 page  |   |
> +     |    +----------------------------------+   |
> +     |                       ^                   |
> +     | Refill succeed        |                   |
> +     |                       | Refill succeed    |
> +     |                       |                   |
> +     v                       v                   v
> +    +----------------------------------------------+
> +    |       allocate fragment from cache           |
> +    +----------------------------------------------+
> +

+1 for the simple visualization of how this works.

> +API interface
> +=============
> +As the design and implementation of page_frag API, the allocation side does not
> +allow concurrent calling, it is assumed that the caller must ensure there is not
> +concurrent alloc calling to the same page_frag_cache instance by using it's own
> +lock or rely on some lockless guarantee like NAPI softirq.
> +
> +Depending on different use cases, callers expecting to deal with va, page or
> +both va and page for them may call page_frag_alloc_va(), page_frag_alloc_pg(),
> +or page_frag_alloc() accordingly.
> +

So the new documentation is good up to here.

> +There is also a use case that need minimum memory in order for forward
> +progressing, but can do better if there is more memory available. Introduce
> +page_frag_alloc_prepare() and page_frag_alloc_commit() related API, the caller
> +requests the minimum memory it need and the prepare API will return the maximum
> +size of the fragment returned, caller need to report back to the page_frag core
> +how much memory it actually use by calling commit API, or not calling the commit
> +API if deciding to not use any memory.
> +

This part is as clear as mud to me. It sounds like kind of a convoluted
setup where you are having the caller have to know a fair bit about the
internal structure of the cache and it is essentially checking the
state and then performing a commit. Not a huge fan. I would almost
prefer to see something more like what we used to do with msix where
you just had a range you could request and if it can't give you at
least the minimum it fails.

I assume the patch is somewhere here in the set. Will take a look at it
later.

> +.. kernel-doc:: include/linux/page_frag_cache.h
> +   :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
> +                 page_frag_alloc_va __page_frag_alloc_va_align
> +                 page_frag_alloc_va_align page_frag_alloc_va_prepare
> +                 page_frag_alloc_va_prepare_align page_frag_alloc_pg_prepare
> +                 page_frag_alloc_prepare page_frag_alloc_commit
> +                 page_frag_alloc_commit_noref page_frag_free_va
> +
> +.. kernel-doc:: mm/page_frag_cache.c
> +   :identifiers: page_frag_cache_drain
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 4745ea94d463..2f84aba59428 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -16683,6 +16683,16 @@ F:	mm/page-writeback.c
>  F:	mm/readahead.c
>  F:	mm/truncate.c
>  
> +PAGE FRAG
> +M:	Yunsheng Lin <linyunsheng@huawei.com>
> +L:	linux-mm@kvack.org
> +L:	netdev@vger.kernel.org
> +S:	Supported
> +F:	Documentation/mm/page_frags.rst
> +F:	include/linux/page_frag_cache.h
> +F:	mm/page_frag_cache.c
> +F:	mm/page_frag_test.c
> +

I would appreciate it if you could add me as I usually am having to
deal with issues people have with this anyway. You can probably just go
with:
Alexander Duyck <alexander.duyck@gmail.com>

>  PAGE POOL
>  M:	Jesper Dangaard Brouer <hawk@kernel.org>
>  M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
> index 28185969cd2c..d8edbecdd179 100644
> --- a/include/linux/page_frag_cache.h
> +++ b/include/linux/page_frag_cache.h
> @@ -31,11 +31,23 @@ struct page_frag_cache {
>  #endif
>  };
>  
> +/**
> + * page_frag_cache_init() - Init page_frag cache.
> + * @nc: page_frag cache from which to init
> + *
> + * Inline helper to init the page_frag cache.
> + */
>  static inline void page_frag_cache_init(struct page_frag_cache *nc)
>  {
>  	nc->va = NULL;
>  }
>  
> +/**
> + * page_frag_cache_is_pfmemalloc() - Check for pfmemalloc.
> + * @nc: page_frag cache from which to check
> + *
> + * Used to check if the current page in page_frag cache is pfmemalloc'ed.
> + */
>  static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
>  {
>  	return !!nc->pfmemalloc;
> @@ -46,6 +58,17 @@ void __page_frag_cache_drain(struct page *page, unsigned int count);
>  void *page_frag_cache_refill(struct page_frag_cache *nc, unsigned int fragsz,
>  			     gfp_t gfp_mask);
>  
> +/**
> + * page_frag_alloc_va() - Alloc a page fragment.
> + * @nc: page_frag cache from which to allocate
> + * @fragsz: the requested fragment size
> + * @gfp_mask: the allocation gfp to use when cache need to be refilled
> + *
> + * Get a page fragment from page_frag cache.
> + *
> + * Return:
> + * Return va of the page fragment, otherwise return NULL.
> + */
>  static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
>  				       unsigned int fragsz, gfp_t gfp_mask)
>  {
> @@ -63,6 +86,19 @@ static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
>  	return va + offset;
>  }
>  
> +/**
> + * __page_frag_alloc_va_align() - Alloc a page fragment with aligning
> + * requirement.
> + * @nc: page_frag cache from which to allocate
> + * @fragsz: the requested fragment size
> + * @gfp_mask: the allocation gfp to use when cache need to be refilled
> + * @align: the requested aligning requirement
> + *
> + * Get a page fragment from page_frag cache with aligning requirement.
> + *
> + * Return:
> + * Return va of the page fragment, otherwise return NULL.
> + */
>  static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
>  					       unsigned int fragsz,
>  					       gfp_t gfp_mask,
> @@ -75,6 +111,19 @@ static inline void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
>  	return page_frag_alloc_va(nc, fragsz, gfp_mask);
>  }
>  
> +/**
> + * page_frag_alloc_va_align() - Alloc a page fragment with aligning requirement.
> + * @nc: page_frag cache from which to allocate
> + * @fragsz: the requested fragment size
> + * @gfp_mask: the allocation gfp to use when cache need to be refilled
> + * @align: the requested aligning requirement
> + *
> + * WARN_ON_ONCE() checking for align and fragsz before getting a page fragment
> + * from page_frag cache with aligning requirement.
> + *
> + * Return:
> + * Return va of the page fragment, otherwise return NULL.
> + */
>  static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
>  					     unsigned int fragsz,
>  					     gfp_t gfp_mask,
> @@ -86,6 +135,19 @@ static inline void *page_frag_alloc_va_align(struct page_frag_cache *nc,
>  	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, align);
>  }
>  
> +/**
> + * page_frag_alloc_va_prepare() - Prepare allocing a page fragment.
> + * @nc: page_frag cache from which to prepare
> + * @offset: out as the offset of the page fragment
> + * @size: in as the requested size, out as the available size
> + * @gfp_mask: the allocation gfp to use when cache need to be refilled
> + *
> + * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
> + * report the maximum size of the page fragment the caller can use.
> + *
> + * Return:
> + * Return va of the page fragment, otherwise return NULL.
> + */
>  static inline void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
>  					       unsigned int *offset,
>  					       unsigned int *size,
> @@ -108,6 +170,21 @@ static inline void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
>  	return va + *offset;
>  }
>  
> +/**
> + * page_frag_alloc_va_prepare_align() - Prepare allocing a page fragment with
> + * aligning requirement.
> + * @nc: page_frag cache from which to prepare
> + * @offset: out as the offset of the page fragment
> + * @size: in as the requested size, out as the available size
> + * @align: the requested aligning requirement
> + * @gfp_mask: the allocation gfp to use when cache need to be refilled
> + *
> + * Prepare an aligned page fragment with minimum size of ‘size’, 'size' is also
> + * used to report the maximum size of the page fragment the caller can use.
> + *
> + * Return:
> + * Return va of the page fragment, otherwise return NULL.
> + */
>  static inline void *page_frag_alloc_va_prepare_align(struct page_frag_cache *nc,
>  						     unsigned int *offset,
>  						     unsigned int *size,
> @@ -144,6 +221,19 @@ static inline void *__page_frag_alloc_pg_prepare(struct page_frag_cache *nc,
>  	return va;
>  }
>  
> +/**
> + * page_frag_alloc_pg_prepare - Prepare allocing a page fragment.
> + * @nc: page_frag cache from which to prepare
> + * @offset: out as the offset of the page fragment
> + * @size: in as the requested size, out as the available size
> + * @gfp: the allocation gfp to use when cache need to be refilled
> + *
> + * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
> + * report the maximum size of the page fragment the caller can use.
> + *
> + * Return:
> + * Return the page fragment, otherwise return NULL.
> + */
>  #define page_frag_alloc_pg_prepare(nc, offset, size, gfp)		\
>  ({									\
>  	struct page *__page = NULL;					\
> @@ -179,6 +269,21 @@ static inline void *__page_frag_alloc_prepare(struct page_frag_cache *nc,
>  	return nc_va;
>  }
>  
> +/**
> + * page_frag_alloc_prepare - Prepare allocing a page fragment.
> + * @nc: page_frag cache from which to prepare
> + * @offset: out as the offset of the page fragment
> + * @size: in as the requested size, out as the available size
> + * @va: out as the va of the returned page fragment
> + * @gfp: the allocation gfp to use when cache need to be refilled
> + *
> + * Prepare a page fragment with minimum size of ‘size’, 'size' is also used to
> + * report the maximum size of the page fragment. Return both 'page' and 'va' of
> + * the fragment to the caller.
> + *
> + * Return:
> + * Return the page fragment, otherwise return NULL.
> + */
>  #define page_frag_alloc_prepare(nc, offset, size, va, gfp)		\
>  ({									\
>  	struct page *__page = NULL;					\
> @@ -191,6 +296,14 @@ static inline void *__page_frag_alloc_prepare(struct page_frag_cache *nc,
>  	__page;								\
>  })
>  
> +/**
> + * page_frag_alloc_commit - Commit allocing a page fragment.
> + * @nc: page_frag cache from which to commit
> + * @offset: offset of the page fragment
> + * @size: size of the page fragment has been used
> + *
> + * Commit the alloc preparing by passing offset and the actual used size.
> + */
>  static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
>  					  unsigned int offset,
>  					  unsigned int size)
> @@ -199,6 +312,17 @@ static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
>  	nc->offset = offset + size;
>  }
>  
> +/**
> + * page_frag_alloc_commit_noref - Commit allocing a page fragment without taking
> + * page refcount.
> + * @nc: page_frag cache from which to commit
> + * @offset: offset of the page fragment
> + * @size: size of the page fragment has been used
> + *
> + * Commit the alloc preparing by passing offset and the actual used size, but
> + * not taking page refcount. Mostly used for fragmemt coaleasing case when the
> + * current fragmemt can share the same refcount with previous fragmemt.
> + */
>  static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
>  						unsigned int offset,
>  						unsigned int size)
> @@ -206,6 +330,10 @@ static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
>  	nc->offset = offset + size;
>  }
>  
> +/**
> + * page_frag_free_va - Free a page fragment by va.
> + * @addr: va of page fragment to be freed
> + */
>  void page_frag_free_va(void *addr);
>  
>  #endif
> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> index cbd0ed82a596..0c76ec006c22 100644
> --- a/mm/page_frag_cache.c
> +++ b/mm/page_frag_cache.c
> @@ -1,15 +1,44 @@
>  // SPDX-License-Identifier: GPL-2.0-only
> -/* Page fragment allocator
> +
> +/**
> + * DOC: page_frag allocator
> + *
> + * A page fragment is an arbitrary-length arbitrary-offset area of memory which
> + * resides within a 0 or higher order compound page.  Multiple fragments within
> + * that page are individually refcounted, in the page's reference counter.
> + *
> + * The page_frag functions, page_frag_alloc* and page_frag_free*, 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.
>   *
> - * 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.
> + * In order to make use of the page fragment APIs a backing page fragment cache
> + * is needed.  This provides a central point for the fragment allocation and
> + * tracks allows multiple calls to make use of a cached page.  The advantage to
> + * doing this is that multiple calls to get_page can be avoided which can be
> + * expensive at allocation time.  However due to the nature of this caching it
> + * is required that any calls to the cache be protected by either a per-cpu
> + * limitation, or a per-cpu limitation and forcing interrupts to be disabled
> + * when executing the fragment allocation.
>   *
> - * 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.
> + * The network stack uses two separate caches per CPU to handle fragment
> + * allocation.  The netdev_alloc_cache is used by callers making use of the
> + * netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
> + * used by callers of the __napi_alloc_frag and napi_alloc_skb calls.  The
> + * main difference between these two calls is the context in which they may be
> + * called.  The "netdev" prefixed functions are usable in any context as these
> + * functions will disable interrupts, while the "napi" prefixed functions are
> + * only usable within the softirq context.
> + *
> + * Many network device drivers use a similar methodology for allocating page
> + * fragments, but the page fragments are cached at the ring or descriptor
> + * level.  In order to enable these cases it is necessary to provide a generic
> + * way of tearing down a page cache.  For this reason __page_frag_cache_drain
> + * was implemented.  It allows for freeing multiple references from a single
> + * page via a single call.  The advantage to doing this is that it allows for
> + * cleaning up the multiple references that were added to a page in order to
> + * avoid calling get_page per allocation.
>   */
>  

Again, not a huge fan of moving this. It would be better to just leave
it where it was and add your documentation onto it.

>  #include <linux/export.h>
> @@ -57,6 +86,10 @@ static bool __page_frag_cache_refill(struct page_frag_cache *nc,
>  	return true;
>  }
>  
> +/**
> + * page_frag_cache_drain - Drain the current page from page_frag cache.
> + * @nc: page_frag cache from which to drain
> + */
>  void page_frag_cache_drain(struct page_frag_cache *nc)
>  {
>  	if (!nc->va)

Re: [PATCH net-next v1 01/12] mm: Move the page fragment allocator from page_alloc into its own file

[Yunsheng Lin]

On 2024/4/8 1:42, Alexander H Duyck wrote:
> On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
>> 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.
> 
> Instead of doing this all as one patch it would be better to split this
> into 2. Make the refactor first, and then move the code. Don't do it
> all in one patch.

Sure, will split this into 2 patches, thanks.

Re: [PATCH net-next v1 02/12] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Yunsheng Lin]

On 2024/4/8 1:52, Alexander H Duyck wrote:
> On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
>> We are above to use page_frag_alloc_*() API to not just
>> allocate memory for skb->data, but also use them to do
>> the memory allocation for skb frag too. Currently the
>> implementation of page_frag in mm subsystem is running
>> the offset as a countdown rather than count-up value,
>> there may have several advantages to that as mentioned
>> in [1], but it may have some disadvantages, for example,
>> it may disable skb frag coaleasing and more correct cache
>> prefetching
>>
>> We have a trade-off to make in order to have a unified
>> implementation and API for page_frag, so use a initial zero
>> offset in this patch, and the following patch will try to
>> make some optimization to aovid the disadvantages as much
>> as possible.
>>
>> 1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/
>>
>> CC: Alexander Duyck <alexander.duyck@gmail.com>
>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>> ---
>>  mm/page_frag_cache.c | 31 ++++++++++++++-----------------
>>  1 file changed, 14 insertions(+), 17 deletions(-)
>>
>> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
>> index a0f90ba25200..3e3e88d9af90 100644
>> --- a/mm/page_frag_cache.c
>> +++ b/mm/page_frag_cache.c
>> @@ -67,9 +67,8 @@ 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;
>> +	unsigned int size, offset;
>>  	struct page *page;
>> -	int offset;
>>  
>>  	if (unlikely(!nc->va)) {
>>  refill:
>> @@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>>  		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.
>>  		 */
>> @@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>>  		/* 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;
>> +		nc->offset = 0;
>>  	}
>>  
>> -	offset = nc->offset - fragsz;
>> -	if (unlikely(offset < 0)) {
>> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
>> +	/* if size can vary use size else just use PAGE_SIZE */
>> +	size = nc->size;
>> +#else
>> +	size = PAGE_SIZE;
>> +#endif
>> +
>> +	offset = ALIGN(nc->offset, -align_mask);
>> +	if (unlikely(offset + fragsz > size)) {
> 
> Rather than using "ALIGN" with a negative value it would probably make
> more sense to use __ALIGN_KERNEL_MASK with ~align_mask. I am not sure
> how well the compiler sorts out the use of negatives to flip values
> that are then converted to masks with the "(a) - 1".

The next patch will remove the '-' in '-align_mask' as the 'ALIGN' operation
is done in the inline helper. I am not sure that matter much to use
__ALIGN_KERNEL_MASK with ~align_mask?

>

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Yunsheng Lin]

On 2024/4/8 2:13, Alexander H Duyck wrote:
> On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
>> Update documentation about design, implementation and API usages
>> for page_frag.
>>
>> Also update MAINTAINERS for page_frag. Alexander seems to be the
>> orginal author for page_frag, we can add him to the MAINTAINERS
>> later if we have an ack from him.
>>
>> CC: Alexander Duyck <alexander.duyck@gmail.com>
>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> 
> Again, this seems more like 2 different pathches at least. One for the
> Documentation and MAINTAINERS changes, and one for the function
> documentation.

Sure.

> 
>> ---
>>  Documentation/mm/page_frags.rst | 115 ++++++++++++++++++----------
>>  MAINTAINERS                     |  10 +++
>>  include/linux/page_frag_cache.h | 128 ++++++++++++++++++++++++++++++++
>>  mm/page_frag_cache.c            |  51 ++++++++++---
>>  4 files changed, 256 insertions(+), 48 deletions(-)
>>
>> diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
>> index 503ca6cdb804..77256dfb58bf 100644
>> --- a/Documentation/mm/page_frags.rst
>> +++ b/Documentation/mm/page_frags.rst
>> @@ -1,43 +1,80 @@
>> +.. SPDX-License-Identifier: GPL-2.0
>> +
>>  ==============
>>  Page fragments
>>  ==============
>>  
>> -A page fragment is an arbitrary-length arbitrary-offset area of memory
>> -which resides within a 0 or higher order compound page.  Multiple
>> -fragments within that page are individually refcounted, in the page's
>> -reference counter.
>> -
>> -The page_frag functions, page_frag_alloc and page_frag_free, 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.
>> -
>> -In order to make use of the page fragment APIs a backing page fragment
>> -cache is needed.  This provides a central point for the fragment allocation
>> -and tracks allows multiple calls to make use of a cached page.  The
>> -advantage to doing this is that multiple calls to get_page can be avoided
>> -which can be expensive at allocation time.  However due to the nature of
>> -this caching it is required that any calls to the cache be protected by
>> -either a per-cpu limitation, or a per-cpu limitation and forcing interrupts
>> -to be disabled when executing the fragment allocation.
>> -
>> -The network stack uses two separate caches per CPU to handle fragment
>> -allocation.  The netdev_alloc_cache is used by callers making use of the
>> -netdev_alloc_frag and __netdev_alloc_skb calls.  The napi_alloc_cache is
>> -used by callers of the __napi_alloc_frag and napi_alloc_skb calls.  The
>> -main difference between these two calls is the context in which they may be
>> -called.  The "netdev" prefixed functions are usable in any context as these
>> -functions will disable interrupts, while the "napi" prefixed functions are
>> -only usable within the softirq context.
>> -
>> -Many network device drivers use a similar methodology for allocating page
>> -fragments, but the page fragments are cached at the ring or descriptor
>> -level.  In order to enable these cases it is necessary to provide a generic
>> -way of tearing down a page cache.  For this reason __page_frag_cache_drain
>> -was implemented.  It allows for freeing multiple references from a single
>> -page via a single call.  The advantage to doing this is that it allows for
>> -cleaning up the multiple references that were added to a page in order to
>> -avoid calling get_page per allocation.
>> -
>> -Alexander Duyck, Nov 29, 2016.
> 
> What is the point of removing this just to add it to a C file further
> down in the diff? Honestly I am not a fan of all the noise this is
> adding to these diffs. Can we do a little less moving of lines for the
> sake of moving them? All it does is pollute the git blame if you try to
> figure out the origin of the lines.

I was thinking about move the doc related code to file where code is related,
so that author will remember to update the doc when changing the code.
Maybe above does not matter that much?

> 
>> +.. kernel-doc:: mm/page_frag_cache.c
>> +   :doc: page_frag allocator
>> +
>> +Architecture overview
>> +=====================
>> +
>> +.. code-block:: none
>> +
>> +    +----------------------+
>> +    | page_frag API caller |
>> +    +----------------------+
>> +            ^
>> +            |
>> +            |
>> +            |
>> +            v
>> +    +----------------------------------------------+
>> +    |          request page fragment               |
>> +    +----------------------------------------------+
>> +        ^                                        ^
>> +        |                                        |
>> +        | Cache empty or not enough              |
>> +        |                                        |
>> +        v                                        |
>> +    +--------------------------------+           |
>> +    | refill cache with order 3 page |           |
>> +    +--------------------------------+           |
>> +     ^                  ^                        |
>> +     |                  |                        |
>> +     |                  | Refill failed          |
>> +     |                  |                        | Cache is enough
>> +     |                  |                        |
>> +     |                  v                        |
>> +     |    +----------------------------------+   |
>> +     |    |  refill cache with order 0 page  |   |
>> +     |    +----------------------------------+   |
>> +     |                       ^                   |
>> +     | Refill succeed        |                   |
>> +     |                       | Refill succeed    |
>> +     |                       |                   |
>> +     v                       v                   v
>> +    +----------------------------------------------+
>> +    |       allocate fragment from cache           |
>> +    +----------------------------------------------+
>> +
> 
> +1 for the simple visualization of how this works.
> 
>> +API interface
>> +=============
>> +As the design and implementation of page_frag API, the allocation side does not
>> +allow concurrent calling, it is assumed that the caller must ensure there is not
>> +concurrent alloc calling to the same page_frag_cache instance by using it's own
>> +lock or rely on some lockless guarantee like NAPI softirq.
>> +
>> +Depending on different use cases, callers expecting to deal with va, page or
>> +both va and page for them may call page_frag_alloc_va(), page_frag_alloc_pg(),
>> +or page_frag_alloc() accordingly.
>> +
> 
> So the new documentation is good up to here.
> 
>> +There is also a use case that need minimum memory in order for forward
>> +progressing, but can do better if there is more memory available. Introduce
>> +page_frag_alloc_prepare() and page_frag_alloc_commit() related API, the caller
>> +requests the minimum memory it need and the prepare API will return the maximum
>> +size of the fragment returned, caller need to report back to the page_frag core
>> +how much memory it actually use by calling commit API, or not calling the commit
>> +API if deciding to not use any memory.
>> +
> 
> This part is as clear as mud to me. It sounds like kind of a convoluted
> setup where you are having the caller have to know a fair bit about the
> internal structure of the cache and it is essentially checking the
> state and then performing a commit. Not a huge fan. I would almost
> prefer to see something more like what we used to do with msix where
> you just had a range you could request and if it can't give you at
> least the minimum it fails.>
> I assume the patch is somewhere here in the set. Will take a look at it
> later.

Yes, the API is introduced in patch 9 and used in patch 10.

> 
>> +.. kernel-doc:: include/linux/page_frag_cache.h
>> +   :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
>> +                 page_frag_alloc_va __page_frag_alloc_va_align
>> +                 page_frag_alloc_va_align page_frag_alloc_va_prepare
>> +                 page_frag_alloc_va_prepare_align page_frag_alloc_pg_prepare
>> +                 page_frag_alloc_prepare page_frag_alloc_commit
>> +                 page_frag_alloc_commit_noref page_frag_free_va
>> +
>> +.. kernel-doc:: mm/page_frag_cache.c
>> +   :identifiers: page_frag_cache_drain
>> diff --git a/MAINTAINERS b/MAINTAINERS
>> index 4745ea94d463..2f84aba59428 100644
>> --- a/MAINTAINERS
>> +++ b/MAINTAINERS
>> @@ -16683,6 +16683,16 @@ F:	mm/page-writeback.c
>>  F:	mm/readahead.c
>>  F:	mm/truncate.c
>>  
>> +PAGE FRAG
>> +M:	Yunsheng Lin <linyunsheng@huawei.com>
>> +L:	linux-mm@kvack.org
>> +L:	netdev@vger.kernel.org
>> +S:	Supported
>> +F:	Documentation/mm/page_frags.rst
>> +F:	include/linux/page_frag_cache.h
>> +F:	mm/page_frag_cache.c
>> +F:	mm/page_frag_test.c
>> +
> 
> I would appreciate it if you could add me as I usually am having to
> deal with issues people have with this anyway. You can probably just go
> with:
> Alexander Duyck <alexander.duyck@gmail.com>

Sure, good to your ack here.

> 
>>  PAGE POOL
>>  M:	Jesper Dangaard Brouer <hawk@kernel.org>
>>  M:	Ilias Apalodimas <ilias.apalodimas@linaro.org>
>> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
>> index 28185969cd2c..d8edbecdd179 100644

Re: [PATCH net-next v1 02/12] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Alexander Duyck]

On Mon, Apr 8, 2024 at 6:39 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> On 2024/4/8 1:52, Alexander H Duyck wrote:
> > On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> >> We are above to use page_frag_alloc_*() API to not just
> >> allocate memory for skb->data, but also use them to do
> >> the memory allocation for skb frag too. Currently the
> >> implementation of page_frag in mm subsystem is running
> >> the offset as a countdown rather than count-up value,
> >> there may have several advantages to that as mentioned
> >> in [1], but it may have some disadvantages, for example,
> >> it may disable skb frag coaleasing and more correct cache
> >> prefetching
> >>
> >> We have a trade-off to make in order to have a unified
> >> implementation and API for page_frag, so use a initial zero
> >> offset in this patch, and the following patch will try to
> >> make some optimization to aovid the disadvantages as much
> >> as possible.
> >>
> >> 1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/
> >>
> >> CC: Alexander Duyck <alexander.duyck@gmail.com>
> >> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> >> ---
> >>  mm/page_frag_cache.c | 31 ++++++++++++++-----------------
> >>  1 file changed, 14 insertions(+), 17 deletions(-)
> >>
> >> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> >> index a0f90ba25200..3e3e88d9af90 100644
> >> --- a/mm/page_frag_cache.c
> >> +++ b/mm/page_frag_cache.c
> >> @@ -67,9 +67,8 @@ 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;
> >> +    unsigned int size, offset;
> >>      struct page *page;
> >> -    int offset;
> >>
> >>      if (unlikely(!nc->va)) {
> >>  refill:
> >> @@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
> >>              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.
> >>               */
> >> @@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
> >>              /* 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;
> >> +            nc->offset = 0;
> >>      }
> >>
> >> -    offset = nc->offset - fragsz;
> >> -    if (unlikely(offset < 0)) {
> >> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> >> +    /* if size can vary use size else just use PAGE_SIZE */
> >> +    size = nc->size;
> >> +#else
> >> +    size = PAGE_SIZE;
> >> +#endif
> >> +
> >> +    offset = ALIGN(nc->offset, -align_mask);
> >> +    if (unlikely(offset + fragsz > size)) {
> >
> > Rather than using "ALIGN" with a negative value it would probably make
> > more sense to use __ALIGN_KERNEL_MASK with ~align_mask. I am not sure
> > how well the compiler sorts out the use of negatives to flip values
> > that are then converted to masks with the "(a) - 1".
>
> The next patch will remove the '-' in '-align_mask' as the 'ALIGN' operation
> is done in the inline helper. I am not sure that matter much to use
> __ALIGN_KERNEL_MASK with ~align_mask?

It is a matter of making the negations more obvious. Basically you
could achieve the same alignment by doing:
  (offset + (~align_mask)) & ~(~align_mask)
rather than:
  (offset + ((-align_mask) - 1)) & ~((-align_mask) - 1)

I'm not sure the compiler will pick up on the fact that the two are
identical and can save a number of operations. Also my suggested
approach is closer to how it used to work. Technically the one you are
using only works if align_mask is a negative power of 2.

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Alexander Duyck]

On Mon, Apr 8, 2024 at 6:39 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>
> On 2024/4/8 2:13, Alexander H Duyck wrote:
> > On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
> >> Update documentation about design, implementation and API usages
> >> for page_frag.
> >>
> >> Also update MAINTAINERS for page_frag. Alexander seems to be the
> >> orginal author for page_frag, we can add him to the MAINTAINERS
> >> later if we have an ack from him.
> >>
> >> CC: Alexander Duyck <alexander.duyck@gmail.com>
> >> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> >
> > Again, this seems more like 2 different pathches at least. One for the
> > Documentation and MAINTAINERS changes, and one for the function
> > documentation.
>
> Sure.
>

[...]

> >> --- a/MAINTAINERS
> >> +++ b/MAINTAINERS
> >> @@ -16683,6 +16683,16 @@ F:  mm/page-writeback.c
> >>  F:  mm/readahead.c
> >>  F:  mm/truncate.c
> >>
> >> +PAGE FRAG
> >> +M:  Yunsheng Lin <linyunsheng@huawei.com>
> >> +L:  linux-mm@kvack.org
> >> +L:  netdev@vger.kernel.org
> >> +S:  Supported
> >> +F:  Documentation/mm/page_frags.rst
> >> +F:  include/linux/page_frag_cache.h
> >> +F:  mm/page_frag_cache.c
> >> +F:  mm/page_frag_test.c
> >> +
> >
> > I would appreciate it if you could add me as I usually am having to
> > deal with issues people have with this anyway. You can probably just go
> > with:
> > Alexander Duyck <alexander.duyck@gmail.com>
>
> Sure, good to your ack here.

Just to be clear this isn't an Ack, but if you are going to list
maintainers for this my name should be on the list so this is the
preferred format. There are still some things to be cleaned up in this
patch.

Re: [PATCH net-next v1 02/12] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Yunsheng Lin]

On 2024/4/9 0:11, Alexander Duyck wrote:
> On Mon, Apr 8, 2024 at 6:39 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>
>> On 2024/4/8 1:52, Alexander H Duyck wrote:
>>> On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
>>>> We are above to use page_frag_alloc_*() API to not just
>>>> allocate memory for skb->data, but also use them to do
>>>> the memory allocation for skb frag too. Currently the
>>>> implementation of page_frag in mm subsystem is running
>>>> the offset as a countdown rather than count-up value,
>>>> there may have several advantages to that as mentioned
>>>> in [1], but it may have some disadvantages, for example,
>>>> it may disable skb frag coaleasing and more correct cache
>>>> prefetching
>>>>
>>>> We have a trade-off to make in order to have a unified
>>>> implementation and API for page_frag, so use a initial zero
>>>> offset in this patch, and the following patch will try to
>>>> make some optimization to aovid the disadvantages as much
>>>> as possible.
>>>>
>>>> 1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/
>>>>
>>>> CC: Alexander Duyck <alexander.duyck@gmail.com>
>>>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>>>> ---
>>>>  mm/page_frag_cache.c | 31 ++++++++++++++-----------------
>>>>  1 file changed, 14 insertions(+), 17 deletions(-)
>>>>
>>>> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
>>>> index a0f90ba25200..3e3e88d9af90 100644
>>>> --- a/mm/page_frag_cache.c
>>>> +++ b/mm/page_frag_cache.c
>>>> @@ -67,9 +67,8 @@ 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;
>>>> +    unsigned int size, offset;
>>>>      struct page *page;
>>>> -    int offset;
>>>>
>>>>      if (unlikely(!nc->va)) {
>>>>  refill:
>>>> @@ -77,10 +76,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>>>>              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.
>>>>               */
>>>> @@ -89,11 +84,18 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
>>>>              /* 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;
>>>> +            nc->offset = 0;
>>>>      }
>>>>
>>>> -    offset = nc->offset - fragsz;
>>>> -    if (unlikely(offset < 0)) {
>>>> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
>>>> +    /* if size can vary use size else just use PAGE_SIZE */
>>>> +    size = nc->size;
>>>> +#else
>>>> +    size = PAGE_SIZE;
>>>> +#endif
>>>> +
>>>> +    offset = ALIGN(nc->offset, -align_mask);
>>>> +    if (unlikely(offset + fragsz > size)) {
>>>
>>> Rather than using "ALIGN" with a negative value it would probably make
>>> more sense to use __ALIGN_KERNEL_MASK with ~align_mask. I am not sure
>>> how well the compiler sorts out the use of negatives to flip values
>>> that are then converted to masks with the "(a) - 1".
>>
>> The next patch will remove the '-' in '-align_mask' as the 'ALIGN' operation
>> is done in the inline helper. I am not sure that matter much to use
>> __ALIGN_KERNEL_MASK with ~align_mask?
> 
> It is a matter of making the negations more obvious. Basically you
> could achieve the same alignment by doing:
>   (offset + (~align_mask)) & ~(~align_mask)
> rather than:
>   (offset + ((-align_mask) - 1)) & ~((-align_mask) - 1)
> 
> I'm not sure the compiler will pick up on the fact that the two are
> identical and can save a number of operations. Also my suggested
> approach is closer to how it used to work. Technically the one you are
> using only works if align_mask is a negative power of 2.

In patch 3, we have below, so the above trick is not really needed after
patch 3:


@@ -94,7 +93,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 	size = PAGE_SIZE;
 #endif

-	offset = ALIGN(nc->offset, -align_mask);
+	offset = nc->offset;
 	if (unlikely(offset + fragsz > size)) {
 		page = virt_to_page(nc->va);

@@ -131,7 +130,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,

 	return nc->va + offset;
 }
-EXPORT_SYMBOL(__page_frag_alloc_align);
+EXPORT_SYMBOL(page_frag_alloc);

...

+static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
+					    unsigned int fragsz, gfp_t gfp_mask,
+					    unsigned int align)
+{
+	nc->offset = ALIGN(nc->offset, align);
+
+	return page_frag_alloc(nc, fragsz, gfp_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);
-}



> .
> 

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Yunsheng Lin]

On 2024/4/9 0:13, Alexander Duyck wrote:
> On Mon, Apr 8, 2024 at 6:39 AM Yunsheng Lin <linyunsheng@huawei.com> wrote:
>>
>> On 2024/4/8 2:13, Alexander H Duyck wrote:
>>> On Sun, 2024-04-07 at 21:08 +0800, Yunsheng Lin wrote:
>>>> Update documentation about design, implementation and API usages
>>>> for page_frag.
>>>>
>>>> Also update MAINTAINERS for page_frag. Alexander seems to be the
>>>> orginal author for page_frag, we can add him to the MAINTAINERS
>>>> later if we have an ack from him.
>>>>
>>>> CC: Alexander Duyck <alexander.duyck@gmail.com>
>>>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>>>
>>> Again, this seems more like 2 different pathches at least. One for the
>>> Documentation and MAINTAINERS changes, and one for the function
>>> documentation.
>>
>> Sure.
>>
> 
> [...]
> 
>>>> --- a/MAINTAINERS
>>>> +++ b/MAINTAINERS
>>>> @@ -16683,6 +16683,16 @@ F:  mm/page-writeback.c
>>>>  F:  mm/readahead.c
>>>>  F:  mm/truncate.c
>>>>
>>>> +PAGE FRAG
>>>> +M:  Yunsheng Lin <linyunsheng@huawei.com>
>>>> +L:  linux-mm@kvack.org
>>>> +L:  netdev@vger.kernel.org
>>>> +S:  Supported
>>>> +F:  Documentation/mm/page_frags.rst
>>>> +F:  include/linux/page_frag_cache.h
>>>> +F:  mm/page_frag_cache.c
>>>> +F:  mm/page_frag_test.c
>>>> +
>>>
>>> I would appreciate it if you could add me as I usually am having to
>>> deal with issues people have with this anyway. You can probably just go
>>> with:
>>> Alexander Duyck <alexander.duyck@gmail.com>
>>
>> Sure, good to your ack here.
> 
> Just to be clear this isn't an Ack, but if you are going to list
> maintainers for this my name should be on the list so this is the
> preferred format. There are still some things to be cleaned up in this
> patch.

Sure, I was talking about "Alexander seems to be the orginal author for
page_frag, we can add him to the MAINTAINERS later if we have an ack from
him." in the commit log.

> .
> 

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Jakub Kicinski]

On Tue, 9 Apr 2024 15:59:58 +0800 Yunsheng Lin wrote:
> > Just to be clear this isn't an Ack, but if you are going to list
> > maintainers for this my name should be on the list so this is the
> > preferred format. There are still some things to be cleaned up in this
> > patch.  
> 
> Sure, I was talking about "Alexander seems to be the orginal author for
> page_frag, we can add him to the MAINTAINERS later if we have an ack from
> him." in the commit log.

Do we have to have a MAINTAINERS entry for every 1000 lines of code?
It really feels forced :/

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Alexander Duyck]

On Tue, Apr 9, 2024 at 6:25 AM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Tue, 9 Apr 2024 15:59:58 +0800 Yunsheng Lin wrote:
> > > Just to be clear this isn't an Ack, but if you are going to list
> > > maintainers for this my name should be on the list so this is the
> > > preferred format. There are still some things to be cleaned up in this
> > > patch.
> >
> > Sure, I was talking about "Alexander seems to be the orginal author for
> > page_frag, we can add him to the MAINTAINERS later if we have an ack from
> > him." in the commit log.
>
> Do we have to have a MAINTAINERS entry for every 1000 lines of code?
> It really feels forced :/

I don't disagree. However, if nothing else I think it gets used as a
part of get_maintainers.pl that tells you who to email about changes
doesn't it? It might make sense in my case since I am still
maintaining it using my gmail account, but I think the commits for
that were mostly from my Intel account weren't they? So if nothing
else it might be a way to provide a trail of breadcrumbs on how to
find a maintainer who changed employers..

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Yunsheng Lin]

On 2024/4/9 23:11, Alexander Duyck wrote:
> On Tue, Apr 9, 2024 at 6:25 AM Jakub Kicinski <kuba@kernel.org> wrote:
>>
>> On Tue, 9 Apr 2024 15:59:58 +0800 Yunsheng Lin wrote:
>>>> Just to be clear this isn't an Ack, but if you are going to list
>>>> maintainers for this my name should be on the list so this is the
>>>> preferred format. There are still some things to be cleaned up in this
>>>> patch.
>>>
>>> Sure, I was talking about "Alexander seems to be the orginal author for
>>> page_frag, we can add him to the MAINTAINERS later if we have an ack from
>>> him." in the commit log.
>>
>> Do we have to have a MAINTAINERS entry for every 1000 lines of code?

Do we have something like rule or guidance against that?
Looking at the entry in MAINTAINERS, it seems quite normal to me,
I thouht it is generally encourage someone with willing and ability
to be a maintainer/reviewer.

Considering you have refused adding me as the reviewer of page_pool
despite the support from two maintainers of page_pool, for the season
of something like below:
'page pool is increasingly central to the whole networking stack.
The bar for "ownership" is getting higher and higher..'

I think I might need a second opinion here.

>> It really feels forced :/

I am not a native english speaker here, I would rather not comment
on the 'forced' part here and focus more on the technical disscusion.

> 
> I don't disagree. However, if nothing else I think it gets used as a
> part of get_maintainers.pl that tells you who to email about changes
> doesn't it? It might make sense in my case since I am still
> maintaining it using my gmail account, but I think the commits for
> that were mostly from my Intel account weren't they? So if nothing
> else it might be a way to provide a trail of breadcrumbs on how to
> find a maintainer who changed employers..

+1.
I generally pay more attention to the patch that is to'ed or cc'ed
to my email when I am overloaded with other work.

> .
> 

Re: [PATCH net-next v1 12/12] mm: page_frag: update documentation and maintainer for page_frag

[Alexander Duyck]

On Wed, Apr 10, 2024 at 9:06 AM David Hildenbrand <david@redhat.com> wrote:
>
> On 09.04.24 17:11, Alexander Duyck wrote:
> > On Tue, Apr 9, 2024 at 6:25 AM Jakub Kicinski <kuba@kernel.org> wrote:
> >>
> >> On Tue, 9 Apr 2024 15:59:58 +0800 Yunsheng Lin wrote:
> >>>> Just to be clear this isn't an Ack, but if you are going to list
> >>>> maintainers for this my name should be on the list so this is the
> >>>> preferred format. There are still some things to be cleaned up in this
> >>>> patch.
> >>>
> >>> Sure, I was talking about "Alexander seems to be the orginal author for
> >>> page_frag, we can add him to the MAINTAINERS later if we have an ack from
> >>> him." in the commit log.
> >>
> >> Do we have to have a MAINTAINERS entry for every 1000 lines of code?
> >> It really feels forced :/
> >
> > I don't disagree. However, if nothing else I think it gets used as a
> > part of get_maintainers.pl that tells you who to email about changes
> > doesn't it? It might make sense in my case since I am still
> > maintaining it using my gmail account, but I think the commits for
> > that were mostly from my Intel account weren't they? So if nothing
> > else it might be a way to provide a trail of breadcrumbs on how to
> > find a maintainer who changed employers..
>
> Would a .mailmap entry also help for your case, such that the mail
> address might get mapped to the new one? (note, I never edited .mailmap
> myself)

Not sure. My concern is that it might undo the existing tracking for
contributions by employer as I know they use the emails for the most
basic setup for that. I suppose that is one downside of being a job
hopper.. :-P

I'd rather not make more work for someone like Jon Corbet or Jakub who
I know maintain statistics based on the emails used and such.

Re: [PATCH net-next v1 11/12] mm: page_frag: add a test module for page_frag

[Simon Horman]

On Sun, Apr 07, 2024 at 09:08:48PM +0800, Yunsheng Lin wrote:
> Basing on the lib/objpool.c, change it to something like a
> ptrpool, so that we can utilize that to test the correctness
> and performance of the page_frag.
> 
> The testing is done by ensuring that the fragments allocated
> from a frag_frag_cache instance is pushed into a ptrpool
> instance in a kthread binded to the first cpu, and a kthread
> binded to the current node will pop the fragmemt from the
> ptrpool and call page_frag_alloc_va() to free the fragmemt.
> 
> We may refactor out the common part between objpool and ptrpool
> if this ptrpool thing turns out to be helpful for other place.
> 
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>

...

> diff --git a/mm/page_frag_test.c b/mm/page_frag_test.c

...

> +/* allocate and initialize percpu slots */
> +static int objpool_init_percpu_slots(struct objpool_head *pool,
> +				     int nr_objs, gfp_t gfp)
> +{
> +	int i;
> +
> +	for (i = 0; i < pool->nr_cpus; i++) {
> +		struct objpool_slot *slot;
> +		int size;
> +
> +		/* skip the cpu node which could never be present */
> +		if (!cpu_possible(i))
> +			continue;
> +
> +		size = struct_size(slot, entries, pool->capacity);
> +
> +		/*
> +		 * here we allocate percpu-slot & objs together in a single
> +		 * allocation to make it more compact, taking advantage of
> +		 * warm caches and TLB hits. in default vmalloc is used to
> +		 * reduce the pressure of kernel slab system. as we know,
> +		 * mimimal size of vmalloc is one page since vmalloc would

nit: minimal

> +		 * always align the requested size to page size
> +		 */
> +		if (gfp & GFP_ATOMIC)
> +			slot = kmalloc_node(size, gfp, cpu_to_node(i));
> +		else
> +			slot = __vmalloc_node(size, sizeof(void *), gfp,
> +					      cpu_to_node(i),
> +					      __builtin_return_address(0));
> +		if (!slot)
> +			return -ENOMEM;
> +
> +		memset(slot, 0, size);
> +		pool->cpu_slots[i] = slot;
> +
> +		objpool_init_percpu_slot(pool, slot);
> +	}
> +
> +	return 0;
> +}

...

> +static struct objpool_head ptr_pool;
> +static int nr_objs = 512;
> +static int nr_test = 5120000;
> +static atomic_t nthreads;
> +static struct completion wait;
> +struct page_frag_cache test_frag;

nit: Is test_frag used outside of this file?
     If not, should it be static?

...