page_pool: make sure frag API fields don't span between cachelines

After commit 5027ec19 ("net: page_pool: split the page_pool_params
into fast and slow") that made &page_pool contain only "hot" params at
the start, cacheline boundary chops frag API fields group in the middle
again.
To not bother with this each time fast params get expanded or shrunk,
let's just align them to `4 * sizeof(long)`, the closest upper pow-2 to
their actual size (2 longs + 1 int). This ensures 16-byte alignment for
the 32-bit architectures and 32-byte alignment for the 64-bit ones,
excluding unnecessary false-sharing.
::page_state_hold_cnt is used quite intensively on hotpath no matter if
frag API is used, so move it to the newly created hole in the first
cacheline.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

include/net/page_pool/types.h

@@ -130,12 +130,22 @@ struct page_pool {
 	struct page_pool_params_fast p;
 
 	int cpuid;
+	u32 pages_state_hold_cnt;
 	bool has_init_callback;
 
+	/* The following block must stay within one cacheline. On 32-bit
+	 * systems, sizeof(long) == sizeof(int), so that the block size is
+	 * ``3 * sizeof(long)``. On 64-bit systems, the actual size is
+	 * ``2 * sizeof(long) + sizeof(int)``. The closest pow-2 to both of
+	 * them is ``4 * sizeof(long)``, so just use that one for simplicity.
+	 * Having it aligned to a cacheline boundary may be excessive and
+	 * doesn't bring any good.
+	 */
+	__cacheline_group_begin(frag) __aligned(4 * sizeof(long));
 	long frag_users;
 	struct page *frag_page;
 	unsigned int frag_offset;
-	u32 pages_state_hold_cnt;
+	__cacheline_group_end(frag);
 
 	struct delayed_work release_dw;
 	void (*disconnect)(void *pool);

net/core/page_pool.c

@@ -172,12 +172,22 @@ static void page_pool_producer_unlock(struct page_pool *pool,
 		spin_unlock_bh(&pool->ring.producer_lock);
 }
 
+static void page_pool_struct_check(void)
+{
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_users);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_page);
+	CACHELINE_ASSERT_GROUP_MEMBER(struct page_pool, frag, frag_offset);
+	CACHELINE_ASSERT_GROUP_SIZE(struct page_pool, frag, 4 * sizeof(long));
+}
+
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params,
 			  int cpuid)
 {
 	unsigned int ring_qsize = 1024; /* Default */
 
+	page_pool_struct_check();
+
 	memcpy(&pool->p, &params->fast, sizeof(pool->p));
 	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));