[RFC v11 11/14] mm: page_frag: introduce prepare/probe/commit API

[Yunsheng Lin <linyunsheng@huawei.com>]

There are many use cases that need minimum memory in order
for forward progress, but more performant if more memory is
available or need to probe the cache info to use any memory
available for frag caoleasing reason.

Currently skb_page_frag_refill() API is used to solve the
above use cases, but caller needs to know about the internal
detail and access the data field of 'struct page_frag' to
meet the requirement of the above use cases and 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 a
probe API to report the current available memory to caller
without doing cache refilling. The caller needs to either call
the commit API to report how much memory it actually uses, or
not do so if deciding to not use any memory.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h |  76 +++++++++++++++++++++
 mm/page_frag_cache.c            | 114 ++++++++++++++++++++++++++++++++
 2 files changed, 190 insertions(+)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 5aa45de7a9a5..1242bfb53ccc 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -7,6 +7,8 @@
 #include <linux/build_bug.h>
 #include <linux/log2.h>
 #include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/mmdebug.h>
 #include <linux/mm_types_task.h>
 #include <asm/page.h>
 
@@ -65,6 +67,9 @@ static inline unsigned int page_frag_cache_page_size(unsigned long encoded_va)
 
 void page_frag_cache_drain(struct page_frag_cache *nc);
 void __page_frag_cache_drain(struct page *page, unsigned int count);
+struct page *page_frag_alloc_pg(struct page_frag_cache *nc,
+				unsigned int *offset, unsigned int fragsz,
+				gfp_t gfp);
 void *__page_frag_alloc_va_align(struct page_frag_cache *nc,
 				 unsigned int fragsz, gfp_t gfp_mask,
 				 unsigned int align_mask);
@@ -77,12 +82,83 @@ 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 unsigned int page_frag_cache_page_offset(const struct page_frag_cache *nc)
+{
+	return page_frag_cache_page_size(nc->encoded_va) - nc->remaining;
+}
+
 static inline void *page_frag_alloc_va(struct page_frag_cache *nc,
 				       unsigned int fragsz, gfp_t gfp_mask)
 {
 	return __page_frag_alloc_va_align(nc, fragsz, gfp_mask, ~0u);
 }
 
+void *page_frag_alloc_va_prepare(struct page_frag_cache *nc, unsigned int *fragsz,
+				 gfp_t gfp);
+
+static inline void *page_frag_alloc_va_prepare_align(struct page_frag_cache *nc,
+						     unsigned int *fragsz,
+						     gfp_t gfp,
+						     unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	nc->remaining = nc->remaining & -align;
+	return page_frag_alloc_va_prepare(nc, fragsz, gfp);
+}
+
+struct page *page_frag_alloc_pg_prepare(struct page_frag_cache *nc,
+					unsigned int *offset,
+					unsigned int *fragsz, gfp_t gfp);
+
+struct page *page_frag_alloc_prepare(struct page_frag_cache *nc,
+				     unsigned int *offset,
+				     unsigned int *fragsz,
+				     void **va, gfp_t gfp);
+
+static inline struct page *page_frag_alloc_probe(struct page_frag_cache *nc,
+						 unsigned int *offset,
+						 unsigned int *fragsz,
+						 void **va)
+{
+	unsigned long encoded_va;
+	struct page *page;
+
+	VM_BUG_ON(!*fragsz);
+	if (unlikely(nc->remaining < *fragsz))
+		return NULL;
+
+	*fragsz = nc->remaining;
+	encoded_va = nc->encoded_va;
+	*va = encoded_page_address(encoded_va);
+	page = virt_to_page(*va);
+	*offset = page_frag_cache_page_size(encoded_va) - *fragsz;
+	*va += *offset;
+
+	return page;
+}
+
+static inline void page_frag_alloc_commit(struct page_frag_cache *nc,
+					  unsigned int fragsz)
+{
+	VM_BUG_ON(fragsz > nc->remaining || !nc->pagecnt_bias);
+	nc->pagecnt_bias--;
+	nc->remaining -= fragsz;
+}
+
+static inline void page_frag_alloc_commit_noref(struct page_frag_cache *nc,
+						unsigned int fragsz)
+{
+	VM_BUG_ON(fragsz > nc->remaining);
+	nc->remaining -= fragsz;
+}
+
+static inline void page_frag_alloc_abort(struct page_frag_cache *nc,
+					 unsigned int fragsz)
+{
+	nc->pagecnt_bias++;
+	nc->remaining += fragsz;
+}
+
 void page_frag_free_va(void *addr);
 
 #endif
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 3f162e9d23ba..74d2a13d12a8 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -88,6 +88,120 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	return page;
 }
 
+void *page_frag_alloc_va_prepare(struct page_frag_cache *nc,
+				 unsigned int *fragsz, gfp_t gfp)
+{
+	unsigned long encoded_va;
+	unsigned int remaining;
+
+	remaining = nc->remaining;
+	if (unlikely(*fragsz > remaining)) {
+		if (unlikely(!__page_frag_cache_refill(nc, gfp) ||
+			     *fragsz > PAGE_SIZE))
+			return NULL;
+
+		remaining = nc->remaining;
+	}
+
+	encoded_va = nc->encoded_va;
+	*fragsz = remaining;
+	return encoded_page_address(encoded_va) +
+			page_frag_cache_page_size(encoded_va) - remaining;
+}
+EXPORT_SYMBOL(page_frag_alloc_va_prepare);
+
+struct page *page_frag_alloc_pg_prepare(struct page_frag_cache *nc,
+					unsigned int *offset,
+					unsigned int *fragsz, gfp_t gfp)
+{
+	unsigned long encoded_va;
+	unsigned int remaining;
+	struct page *page;
+
+	remaining = nc->remaining;
+	if (unlikely(*fragsz > remaining)) {
+		if (unlikely(*fragsz > PAGE_SIZE)) {
+			*fragsz = 0;
+			return NULL;
+		}
+
+		page = __page_frag_cache_refill(nc, gfp);
+		remaining = nc->remaining;
+		encoded_va = nc->encoded_va;
+	} else {
+		encoded_va = nc->encoded_va;
+		page = virt_to_page((void *)encoded_va);
+	}
+
+	*offset = page_frag_cache_page_size(encoded_va) - remaining;
+	*fragsz = remaining;
+
+	return page;
+}
+EXPORT_SYMBOL(page_frag_alloc_pg_prepare);
+
+struct page *page_frag_alloc_prepare(struct page_frag_cache *nc,
+				     unsigned int *offset,
+				     unsigned int *fragsz,
+				     void **va, gfp_t gfp)
+{
+	unsigned long encoded_va;
+	unsigned int remaining;
+	struct page *page;
+
+	remaining = nc->remaining;
+	if (unlikely(*fragsz > remaining)) {
+		if (unlikely(*fragsz > PAGE_SIZE)) {
+			*fragsz = 0;
+			return NULL;
+		}
+
+		page = __page_frag_cache_refill(nc, gfp);
+		remaining = nc->remaining;
+		encoded_va = nc->encoded_va;
+	} else {
+		encoded_va = nc->encoded_va;
+		page = virt_to_page((void *)encoded_va);
+	}
+
+	*offset = page_frag_cache_page_size(encoded_va) - remaining;
+	*fragsz = remaining;
+	*va = encoded_page_address(encoded_va) + *offset;
+
+	return page;
+}
+EXPORT_SYMBOL(page_frag_alloc_prepare);
+
+struct page *page_frag_alloc_pg(struct page_frag_cache *nc,
+				unsigned int *offset, unsigned int fragsz,
+				gfp_t gfp)
+{
+	struct page *page;
+
+	if (unlikely(fragsz > nc->remaining)) {
+		if (unlikely(fragsz > PAGE_SIZE))
+			return NULL;
+
+		page = __page_frag_cache_refill(nc, gfp);
+		if (unlikely(!page))
+			return NULL;
+
+		*offset = 0;
+	} else {
+		unsigned long encoded_va = nc->encoded_va;
+
+		page = virt_to_page((void *)encoded_va);
+		*offset = page_frag_cache_page_size(encoded_va) -
+					nc->remaining;
+	}
+
+	nc->remaining -= fragsz;
+	nc->pagecnt_bias--;
+
+	return page;
+}
+EXPORT_SYMBOL(page_frag_alloc_pg);
+
 void page_frag_cache_drain(struct page_frag_cache *nc)
 {
 	if (!nc->encoded_va)
-- 
2.33.0