The avx2 lookup routines get the next map index to process passes as a function argument, but this isn't obvious because it's hidden in the lookup macro. Additionally, a recent LLM review pointed out following "bug": ------------------------------------------------------------- > b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); > if (last) > - return b; > + ret = b; > > if (unlikely(ret == -1)) > ret = b / XSAVE_YMM_SIZE; Does this change introduce a logic error when last=true and no match is found? [..] Should this be changed to an else-if structure instead? ------------------------------------------------------------- LLM sees a control-flow change, but there is none: All call sites invoke nft_pipapo_avx2_refill() only when at least one bit in the map is set, i.e. nft_pipapo_avx2_refill() never returns -1. Add a runtime debug check that fires if we'd return -1 as additional documentation and also make the suggested change, code might be easier to understand this way. In commit 17a20e09f086 ("netfilter: nft_set: remove one argument from lookup and update functions") I incorrectly moved the "ret" scope into the loop. This has no effect on the correctness, but it can (depending on map sizes) cause a redundant repeat of an earlier processing step. Restore the intended 'pass map index' instead of always-0. Note that I did not see any change in performance numbers, but Stefano correctly points out that the existing perf test likely lack a sparse intermediate bitmap (between fields) with a lot of leading zeroes. Reviewed-by: Stefano Brivio Signed-off-by: Florian Westphal --- net/netfilter/nft_set_pipapo_avx2.c | 35 ++++++++++++----------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index dad265807b8b..b3f105520a85 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -144,6 +144,7 @@ static void nft_pipapo_avx2_fill(unsigned long *data, int start, int len) * This is an alternative implementation of pipapo_refill() suitable for usage * with AVX2 lookup routines: we know there are four words to be scanned, at * a given offset inside the map, for each matching iteration. + * The caller must ensure at least one bit in the four words is set. * * This function doesn't actually use any AVX2 instruction. * @@ -179,6 +180,7 @@ static int nft_pipapo_avx2_refill(int offset, unsigned long *map, NFT_PIPAPO_AVX2_REFILL_ONE_WORD(3); #undef NFT_PIPAPO_AVX2_REFILL_ONE_WORD + DEBUG_NET_WARN_ON_ONCE(ret < 0); return ret; } @@ -243,8 +245,7 @@ static int nft_pipapo_avx2_lookup_4b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -320,8 +321,7 @@ static int nft_pipapo_avx2_lookup_4b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -415,8 +415,7 @@ static int nft_pipapo_avx2_lookup_4b_8(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -506,8 +505,7 @@ static int nft_pipapo_avx2_lookup_4b_12(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -642,8 +640,7 @@ static int nft_pipapo_avx2_lookup_4b_32(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -700,8 +697,7 @@ static int nft_pipapo_avx2_lookup_8b_1(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -765,8 +761,7 @@ static int nft_pipapo_avx2_lookup_8b_2(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -840,8 +835,7 @@ static int nft_pipapo_avx2_lookup_8b_4(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -926,8 +920,7 @@ static int nft_pipapo_avx2_lookup_8b_6(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -1020,8 +1013,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill, b = nft_pipapo_avx2_refill(i_ul, &map[i_ul], fill, f->mt, last); if (last) ret = b; - - if (unlikely(ret == -1)) + else if (unlikely(ret == -1)) ret = b / XSAVE_YMM_SIZE; continue; @@ -1143,6 +1135,7 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, const struct nft_pipapo_field *f; unsigned long *res, *fill, *map; bool map_index; + int ret = 0; int i; scratch = *raw_cpu_ptr(m->scratch); @@ -1167,8 +1160,8 @@ struct nft_pipapo_elem *pipapo_get_avx2(const struct nft_pipapo_match *m, nft_pipapo_for_each_field(f, i, m) { bool last = i == m->field_count - 1, first = !i; - int ret = 0; + /* NB: previous round @ret is passed to avx2 lookup fn */ #define NFT_SET_PIPAPO_AVX2_LOOKUP(b, n) \ (ret = nft_pipapo_avx2_lookup_##b##b_##n(res, fill, f, \ ret, data, \ -- 2.53.0