[PATCH 6/6] netfilter: nft_set_pipapo_avx2: add missing vzeroupper

[Eric Biggers <ebiggers@kernel.org>]

Since pipapo_get_avx2() uses YMM registers, execute vzeroupper before
returning from it.  This is needed to avoid degrading the performance of
any later SSE code that may happen to be executed.

Fixes: 7400b063969b ("nft_set_pipapo: Introduce AVX2-based lookup implementation")
Cc: stable@vger.kernel.org
Cc: Florian Westphal <fw@strlen.de>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 net/netfilter/nft_set_pipapo_avx2.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index b3f105520a85..21f5be68c703 100644
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1134,6 +1134,7 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m,
 	struct nft_pipapo_scratch *scratch;
 	const struct nft_pipapo_field *f;
 	unsigned long *res, *fill, *map;
+	struct nft_pipapo_elem *e;
 	bool map_index;
 	int ret = 0;
 	int i;
@@ -1207,14 +1208,11 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m,
 next_match:
 		if (ret < 0) {
 			scratch->map_index = map_index;
-			kernel_fpu_end();
-			__local_unlock_nested_bh(&scratch->bh_lock);
-			return NULL;
+			e = NULL;
+			goto out;
 		}
 
 		if (last) {
-			struct nft_pipapo_elem *e;
-
 			e = f->mt[ret].e;
 			if (unlikely(__nft_set_elem_expired(&e->ext, tstamp) ||
 				     !nft_set_elem_active(&e->ext, genmask))) {
@@ -1224,9 +1222,7 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m,
 			}
 
 			scratch->map_index = map_index;
-			kernel_fpu_end();
-			__local_unlock_nested_bh(&scratch->bh_lock);
-			return e;
+			goto out;
 		}
 
 		map_index = !map_index;
@@ -1234,9 +1230,12 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m,
 		data += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
 	}
 
+	e = NULL;
+out:
+	asm volatile("vzeroupper");
 	kernel_fpu_end();
 	__local_unlock_nested_bh(&scratch->bh_lock);
-	return NULL;
+	return e;
 }
 
 /**
-- 
2.55.0