diff mbox series

[net-next,v6,01/12] page_pool: make sure frag API fields don't span between cachelines

Message ID 20231207172010.1441468-2-aleksander.lobakin@intel.com
State Handled Elsewhere
Headers show
Series net: intel: start The Great Code Dedup + Page Pool for iavf | expand

Commit Message

Alexander Lobakin Dec. 7, 2023, 5:19 p.m. UTC 
After commit 5027ec19f104 ("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 + 2 ints). This ensures 16-byte alignment for
the 32-bit architectures and 32-byte alignment for the 64-bit ones,
excluding unnecessary false-sharing.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
 include/net/page_pool/types.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index ac286ea8ce2d..35ab82da7f2a 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -130,7 +130,16 @@  struct page_pool {
 
 	bool has_init_callback;
 
-	long frag_users;
+	/* The following block must stay within one cacheline. On 32-bit
+	 * systems, sizeof(long) == sizeof(int), so that the block size is
+	 * precisely ``4 * sizeof(long)``. On 64-bit systems, the actual size
+	 * is ``2 * sizeof(long) + 2 * sizeof(int)``, i.e. 24 bytes, but the
+	 * closest pow-2 to that is 32 bytes, which also equals to
+	 * ``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.
+	 */
+	long frag_users __aligned(4 * sizeof(long));
 	struct page *frag_page;
 	unsigned int frag_offset;
 	u32 pages_state_hold_cnt;