page_pool: devmem support

Convert netmem to be a union of struct page and struct netmem. Overload
the LSB of struct netmem* to indicate that it's a net_iov, otherwise
it's a page.

Currently these entries in struct page are rented by the page_pool and
used exclusively by the net stack:

struct {
	unsigned long pp_magic;
	struct page_pool *pp;
	unsigned long _pp_mapping_pad;
	unsigned long dma_addr;
	atomic_long_t pp_ref_count;
};

Mirror these (and only these) entries into struct net_iov and implement
netmem helpers that can access these common fields regardless of
whether the underlying type is page or net_iov.

Implement checks for net_iov in netmem helpers which delegate to mm
APIs, to ensure net_iov are never passed to the mm stack.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-6-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 13 insertions, 12 deletions

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 2abe6e919224..52659db2d765 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -24,8 +24,11 @@
 
 #include <trace/events/page_pool.h>
 
+#include "netmem_priv.h"
 #include "page_pool_priv.h"
 
+DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);
+
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
 
@@ -358,7 +361,7 @@ static noinline netmem_ref page_pool_refill_alloc_cache(struct page_pool *pool)
 		if (unlikely(!netmem))
 			break;
 
-		if (likely(page_to_nid(netmem_to_page(netmem)) == pref_nid)) {
+		if (likely(netmem_is_pref_nid(netmem, pref_nid))) {
 			pool->alloc.cache[pool->alloc.count++] = netmem;
 		} else {
 			/* NUMA mismatch;
@@ -454,10 +457,8 @@ unmap_failed:
 
 static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	page->pp = pool;
-	page->pp_magic |= PP_SIGNATURE;
+	netmem_set_pp(netmem, pool);
+	netmem_or_pp_magic(netmem, PP_SIGNATURE);
 
 	/* Ensuring all pages have been split into one fragment initially:
 	 * page_pool_set_pp_info() is only called once for every page when it
@@ -472,10 +473,8 @@ static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
 
 static void page_pool_clear_pp_info(netmem_ref netmem)
 {
-	struct page *page = netmem_to_page(netmem);
-
-	page->pp_magic = 0;
-	page->pp = NULL;
+	netmem_clear_pp_magic(netmem);
+	netmem_set_pp(netmem, NULL);
 }
 
 static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
@@ -692,8 +691,9 @@ static bool page_pool_recycle_in_cache(netmem_ref netmem,
 
 static bool __page_pool_page_can_be_recycled(netmem_ref netmem)
 {
-	return page_ref_count(netmem_to_page(netmem)) == 1 &&
-	       !page_is_pfmemalloc(netmem_to_page(netmem));
+	return netmem_is_net_iov(netmem) ||
+	       (page_ref_count(netmem_to_page(netmem)) == 1 &&
+		!page_is_pfmemalloc(netmem_to_page(netmem)));
 }
 
 /* If the page refcnt == 1, this will try to recycle the page.
@@ -728,6 +728,7 @@ __page_pool_put_page(struct page_pool *pool, netmem_ref netmem,
 		/* Page found as candidate for recycling */
 		return netmem;
 	}
+
 	/* Fallback/non-XDP mode: API user have elevated refcnt.
 	 *
 	 * Many drivers split up the page into fragments, and some
@@ -949,7 +950,7 @@ static void page_pool_empty_ring(struct page_pool *pool)
 	/* Empty recycle ring */
 	while ((netmem = (__force netmem_ref)ptr_ring_consume_bh(&pool->ring))) {
 		/* Verify the refcnt invariant of cached pages */
-		if (!(page_ref_count(netmem_to_page(netmem)) == 1))
+		if (!(netmem_ref_count(netmem) == 1))
 			pr_crit("%s() page_pool refcnt %d violation\n",
 				__func__, netmem_ref_count(netmem));