netdev - [PATCH net-next 2/2] net: kfree_skb_list use kmem_cache_free

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 05 Jan 2023 16:42:47 +0100
From:   Jesper Dangaard Brouer <brouer@...hat.com>
To:     netdev@...r.kernel.org
Cc:     Jesper Dangaard Brouer <brouer@...hat.com>,
        Jakub Kicinski <kuba@...nel.org>,
        "David S. Miller" <davem@...emloft.net>, edumazet@...gle.com,
        pabeni@...hat.com
Subject: [PATCH net-next 2/2] net: kfree_skb_list use kmem_cache_free_bulk

The kfree_skb_list function walks SKB (via skb->next) and frees them
individually to the SLUB/SLAB allocator (kmem_cache). It is more
efficient to bulk free them via the kmem_cache_free_bulk API.

This patches create a stack local array with SKBs to bulk free while
walking the list. Bulk array size is limited to 16 SKBs to trade off
stack usage and efficiency. The SLUB kmem_cache "skbuff_head_cache"
uses objsize 256 bytes usually in an order-1 page 8192 bytes that is
32 objects per slab (can vary on archs and due to SLUB sharing). Thus,
for SLUB the optimal bulk free case is 32 objects belonging to same
slab, but runtime this isn't likely to occur.

Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
 net/core/skbuff.c |   39 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 38 insertions(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 007a5fbe284b..e6fa667174d5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -964,16 +964,53 @@ kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason)
 }
 EXPORT_SYMBOL(kfree_skb_reason);
 
+#define KFREE_SKB_BULK_SIZE	16
+
+struct skb_free_array {
+	unsigned int skb_count;
+	void *skb_array[KFREE_SKB_BULK_SIZE];
+};
+
+static void kfree_skb_defer_local(struct sk_buff *skb,
+				  struct skb_free_array *sa,
+				  enum skb_drop_reason reason)
+{
+	/* if SKB is a clone, don't handle this case */
+	if (unlikely(skb->fclone != SKB_FCLONE_UNAVAILABLE)) {
+		__kfree_skb(skb);
+		return;
+	}
+
+	skb_release_all(skb, reason);
+	sa->skb_array[sa->skb_count++] = skb;
+
+	if (unlikely(sa->skb_count == KFREE_SKB_BULK_SIZE)) {
+		kmem_cache_free_bulk(skbuff_head_cache, KFREE_SKB_BULK_SIZE,
+				     sa->skb_array);
+		sa->skb_count = 0;
+	}
+}
+
 void __fix_address
 kfree_skb_list_reason(struct sk_buff *segs, enum skb_drop_reason reason)
 {
+	struct skb_free_array sa;
+	sa.skb_count = 0;
+
 	while (segs) {
 		struct sk_buff *next = segs->next;
 
+		skb_mark_not_on_list(segs);
+
 		if (__kfree_skb_reason(segs, reason))
-			__kfree_skb(segs);
+			kfree_skb_defer_local(segs, &sa, reason);
+
 		segs = next;
 	}
+
+	if (sa.skb_count)
+		kmem_cache_free_bulk(skbuff_head_cache, sa.skb_count,
+				     sa.skb_array);
 }
 EXPORT_SYMBOL(kfree_skb_list_reason);