nft_set_pipapo: Prepare for single ranged field usage

A few adjustments in nft_pipapo_init() are needed to allow usage of
this set back-end for a single, ranged field.

Provide a convenient NFT_PIPAPO_MIN_FIELDS definition that currently
makes sure that the rbtree back-end is selected instead, for sets
with a single field.

This finally allows a fair comparison with rbtree sets, by defining
NFT_PIPAPO_MIN_FIELDS as 0 and skipping rbtree back-end initialisation:

 ---------------.--------------------------.-------------------------.
 AMD Epyc 7402  |      baselines, Mpps     |   Mpps, % over rbtree   |
  1 thread      |__________________________|_________________________|
  3.35GHz       |        |        |        |            |            |
  768KiB L1D$   | netdev |  hash  | rbtree |            |   pipapo   |
 ---------------|  hook  |   no   | single |   pipapo   |single field|
 type   entries |  drop  | ranges | field  |single field|    AVX2    |
 ---------------|--------|--------|--------|------------|------------|
 net,port       |        |        |        |            |            |
          1000  |   19.0 |   10.4 |    3.8 | 6.0   +58% | 9.6  +153% |
 ---------------|--------|--------|--------|------------|------------|
 port,net       |        |        |        |            |            |
           100  |   18.8 |   10.3 |    5.8 | 9.1   +57% |11.6  +100% |
 ---------------|--------|--------|--------|------------|------------|
 net6,port      |        |        |        |            |            |
          1000  |   16.4 |    7.6 |    1.8 | 2.8   +55% | 6.5  +261% |
 ---------------|--------|--------|--------|------------|------------|
 port,proto     |        |        |        |     [1]    |    [1]     |
         30000  |   19.6 |   11.6 |    3.9 | 0.9   -77% | 2.7   -31% |
 ---------------|--------|--------|--------|------------|------------|
 port,proto     |        |        |        |            |            |
         10000  |   19.6 |   11.6 |    4.4 | 2.1   -52% | 5.6   +27% |
 ---------------|--------|--------|--------|------------|------------|
 port,proto     |        |        |        |            |            |
 4 threads 10000|   77.9 |   45.1 |   17.4 | 8.3   -52% |22.4   +29% |
 ---------------|--------|--------|--------|------------|------------|
 net6,port,mac  |        |        |        |            |            |
            10  |   16.5 |    5.4 |    4.3 | 4.5    +5% | 8.2   +91% |
 ---------------|--------|--------|--------|------------|------------|
 net6,port,mac, |        |        |        |            |            |
 proto    1000  |   16.5 |    5.7 |    1.9 | 2.8   +47% | 6.6  +247% |
 ---------------|--------|--------|--------|------------|------------|
 net,mac        |        |        |        |            |            |
          1000  |   19.0 |    8.4 |    3.9 | 6.0   +54% | 9.9  +154% |
 ---------------'--------'--------'--------'------------'------------'
 [1] Causes switch of lookup table buckets for 'port' to 4-bit groups

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 1e8dd5d..c1afb6c 100644 (file)
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -1983,7 +1983,8 @@ static u64 nft_pipapo_privsize(const struct nlattr * const nla[],
 static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features,
                                struct nft_set_estimate *est)
 {
-       if (!(features & NFT_SET_INTERVAL) || desc->field_count <= 1)
+       if (!(features & NFT_SET_INTERVAL) ||
+           desc->field_count < NFT_PIPAPO_MIN_FIELDS)
                return false;
 
        est->size = pipapo_estimate_size(desc);
@@ -2016,17 +2017,19 @@ static int nft_pipapo_init(const struct nft_set *set,
        struct nft_pipapo *priv = nft_set_priv(set);
        struct nft_pipapo_match *m;
        struct nft_pipapo_field *f;
-       int err, i;
+       int err, i, field_count;
 
-       if (desc->field_count > NFT_PIPAPO_MAX_FIELDS)
+       field_count = desc->field_count ? : 1;
+
+       if (field_count > NFT_PIPAPO_MAX_FIELDS)
                return -EINVAL;
 
-       m = kmalloc(sizeof(*priv->match) + sizeof(*f) * desc->field_count,
+       m = kmalloc(sizeof(*priv->match) + sizeof(*f) * field_count,
                    GFP_KERNEL);
        if (!m)
                return -ENOMEM;
 
-       m->field_count = desc->field_count;
+       m->field_count = field_count;
        m->bsize_max = 0;
 
        m->scratch = alloc_percpu(unsigned long *);
@@ -2050,10 +2053,12 @@ static int nft_pipapo_init(const struct nft_set *set,
        rcu_head_init(&m->rcu);
 
        nft_pipapo_for_each_field(f, i, m) {
+               int len = desc->field_len[i] ? : set->klen;
+
                f->bb = NFT_PIPAPO_GROUP_BITS_INIT;
-               f->groups = desc->field_len[i] * NFT_PIPAPO_GROUPS_PER_BYTE(f);
+               f->groups = len * NFT_PIPAPO_GROUPS_PER_BYTE(f);
 
-               priv->width += round_up(desc->field_len[i], sizeof(u32));
+               priv->width += round_up(len, sizeof(u32));
 
                f->bsize = 0;
                f->rules = 0;

diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
index 3cfc0a3..25a7559 100644 (file)
--- a/net/netfilter/nft_set_pipapo.h
+++ b/net/netfilter/nft_set_pipapo.h
@@ -8,6 +8,9 @@
 /* Count of concatenated fields depends on count of 32-bit nftables registers */
 #define NFT_PIPAPO_MAX_FIELDS          NFT_REG32_COUNT
 
+/* Restrict usage to multiple fields, make sure rbtree is used otherwise */
+#define NFT_PIPAPO_MIN_FIELDS          2
+
 /* Largest supported field size */
 #define NFT_PIPAPO_MAX_BYTES           (sizeof(struct in6_addr))
 #define NFT_PIPAPO_MAX_BITS            (NFT_PIPAPO_MAX_BYTES * BITS_PER_BYTE)

diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
index f6e2015..d65ae0e 100644 (file)
--- a/net/netfilter/nft_set_pipapo_avx2.c
+++ b/net/netfilter/nft_set_pipapo_avx2.c
@@ -1087,7 +1087,8 @@ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill,
 bool nft_pipapo_avx2_estimate(const struct nft_set_desc *desc, u32 features,
                              struct nft_set_estimate *est)
 {
-       if (!(features & NFT_SET_INTERVAL) || desc->field_count <= 1)
+       if (!(features & NFT_SET_INTERVAL) ||
+           desc->field_count < NFT_PIPAPO_MIN_FIELDS)
                return false;
 
        if (!boot_cpu_has(X86_FEATURE_AVX2) || !boot_cpu_has(X86_FEATURE_AVX))