net: page_pool: report amount of memory held by page pools

Advanced deployments need the ability to check memory use
of various system components. It makes it possible to make informed
decisions about memory allocation and to find regressions and leaks.

Report memory use of page pools. Report both number of references
and bytes held.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Author: kuba-moo

Documentation/netlink/specs/netdev.yaml

@@ -114,6 +114,19 @@ attribute-sets:
         checks:
           min: 1
           max: u32-max
+      -
+        name: inflight
+        type: uint
+        doc: |
+          Number of outstanding references to this page pool (allocated
+          but yet to be freed pages). Allocated pages may be held in
+          socket receive queues, driver receive ring, page pool recycling
+          ring, the page pool cache, etc.
+      -
+        name: inflight-mem
+        type: uint
+        doc: |
+          Amount of memory held by inflight pages.
 
 operations:
   list:
@@ -163,6 +176,8 @@ operations:
             - id
             - ifindex
             - napi-id
+            - inflight
+            - inflight-mem
       dump:
         reply: *pp-reply
       config-cond: page-pool

include/uapi/linux/netdev.h

@@ -68,6 +68,8 @@ enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
 	NETDEV_A_PAGE_POOL_NAPI_ID,
+	NETDEV_A_PAGE_POOL_INFLIGHT,
+	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)

net/core/page_pool.c

@@ -529,16 +529,21 @@ EXPORT_SYMBOL(page_pool_alloc_pages);
  */
 #define _distance(a, b)	(s32)((a) - (b))
 
-static s32 page_pool_inflight(struct page_pool *pool)
+s32 page_pool_inflight(const struct page_pool *pool, bool strict)
 {
 	u32 release_cnt = atomic_read(&pool->pages_state_release_cnt);
 	u32 hold_cnt = READ_ONCE(pool->pages_state_hold_cnt);
 	s32 inflight;
 
 	inflight = _distance(hold_cnt, release_cnt);
 
-	trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
-	WARN(inflight < 0, "Negative(%d) inflight packet-pages", inflight);
+	if (strict) {
+		trace_page_pool_release(pool, inflight, hold_cnt, release_cnt);
+		WARN(inflight < 0, "Negative(%d) inflight packet-pages",
+		     inflight);
+	} else {
+		inflight = max(0, inflight);
+	}
 
 	return inflight;
 }
@@ -881,7 +886,7 @@ static int page_pool_release(struct page_pool *pool)
 	int inflight;
 
 	page_pool_scrub(pool);
-	inflight = page_pool_inflight(pool);
+	inflight = page_pool_inflight(pool, true);
 	if (!inflight)
 		__page_pool_destroy(pool);
 

net/core/page_pool_priv.h

@@ -3,6 +3,8 @@
 #ifndef __PAGE_POOL_PRIV_H
 #define __PAGE_POOL_PRIV_H
 
+s32 page_pool_inflight(const struct page_pool *pool, bool strict);
+
 int page_pool_list(struct page_pool *pool);
 void page_pool_unlist(struct page_pool *pool);
 

net/core/page_pool_user.c

@@ -110,6 +110,7 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
+	size_t inflight, refsz;
 	void *hdr;
 
 	hdr = genlmsg_iput(rsp, info);
@@ -127,6 +128,13 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, pool->user.napi_id))
 		goto err_cancel;
 
+	inflight = page_pool_inflight(pool, false);
+	refsz =	PAGE_SIZE << pool->p.order;
+	if (nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT, inflight) ||
+	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
+			 inflight * refsz))
+		goto err_cancel;
+
 	genlmsg_end(rsp, hdr);
 
 	return 0;