[nf-next,v2,7/8] nft_set_pipapo: Prepare for vectorised implementation: helpers

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index 92a0e3dc6f79..5076325b8093 100644
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -330,173 +330,20 @@ 
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-#include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/netlink.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <uapi/linux/netfilter/nf_tables.h>
-#include <net/ipv6.h>			/* For the maximum length of a field */
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 
-/* Count of concatenated fields depends on count of 32-bit nftables registers */
-#define NFT_PIPAPO_MAX_FIELDS		NFT_REG32_COUNT
-
-/* 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)
-
-/* Number of bits to be grouped together in lookup table buckets, arbitrary */
-#define NFT_PIPAPO_GROUP_BITS		4
-#define NFT_PIPAPO_GROUPS_PER_BYTE	(BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS)
-
-/* Fields are padded to 32 bits in input registers */
-#define NFT_PIPAPO_GROUPS_PADDED_SIZE(x)				\
-	(round_up((x) / NFT_PIPAPO_GROUPS_PER_BYTE, sizeof(u32)))
-#define NFT_PIPAPO_GROUPS_PADDING(x)					\
-	(NFT_PIPAPO_GROUPS_PADDED_SIZE((x)) - (x) / NFT_PIPAPO_GROUPS_PER_BYTE)
-
-/* Number of buckets, given by 2 ^ n, with n grouped bits */
-#define NFT_PIPAPO_BUCKETS		(1 << NFT_PIPAPO_GROUP_BITS)
-
-/* Each n-bit range maps to up to n * 2 rules */
-#define NFT_PIPAPO_MAP_NBITS		(const_ilog2(NFT_PIPAPO_MAX_BITS * 2))
-
-/* Use the rest of mapping table buckets for rule indices, but it makes no sense
- * to exceed 32 bits
- */
-#if BITS_PER_LONG == 64
-#define NFT_PIPAPO_MAP_TOBITS		32
-#else
-#define NFT_PIPAPO_MAP_TOBITS		(BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS)
-#endif
-
-/* ...which gives us the highest allowed index for a rule */
-#define NFT_PIPAPO_RULE0_MAX		((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \
-					- (1UL << NFT_PIPAPO_MAP_NBITS))
-
-/* Definitions for vectorised implementations */
-#ifdef NFT_PIPAPO_ALIGN
-#define NFT_PIPAPO_ALIGN_HEADROOM					\
-	(NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN)
-#define NFT_PIPAPO_LT_ALIGN(lt)		(PTR_ALIGN((lt), NFT_PIPAPO_ALIGN))
-#define NFT_PIPAPO_LT_ASSIGN(field, x)					\
-	do {								\
-		(field)->lt_aligned = NFT_PIPAPO_LT_ALIGN(x);		\
-		(field)->lt = (x);					\
-	} while (0)
-#else
-#define NFT_PIPAPO_ALIGN_HEADROOM	0
-#define NFT_PIPAPO_LT_ALIGN(lt)		(lt)
-#define NFT_PIPAPO_LT_ASSIGN(field, x)	((field)->lt = (x))
-#endif /* NFT_PIPAPO_ALIGN */
-
-#define nft_pipapo_for_each_field(field, index, match)		\
-	for ((field) = (match)->f, (index) = 0;			\
-	     (index) < (match)->field_count;			\
-	     (index)++, (field)++)
-
-/**
- * union nft_pipapo_map_bucket - Bucket of mapping table
- * @to:		First rule number (in next field) this rule maps to
- * @n:		Number of rules (in next field) this rule maps to
- * @e:		If there's no next field, pointer to element this rule maps to
- */
-union nft_pipapo_map_bucket {
-	struct {
-#if BITS_PER_LONG == 64
-		static_assert(NFT_PIPAPO_MAP_TOBITS <= 32);
-		u32 to;
-
-		static_assert(NFT_PIPAPO_MAP_NBITS <= 32);
-		u32 n;
-#else
-		unsigned long to:NFT_PIPAPO_MAP_TOBITS;
-		unsigned long  n:NFT_PIPAPO_MAP_NBITS;
-#endif
-	};
-	struct nft_pipapo_elem *e;
-};
-
-/**
- * struct nft_pipapo_field - Lookup, mapping tables and related data for a field
- * @groups:	Amount of 4-bit groups
- * @rules:	Number of inserted rules
- * @bsize:	Size of each bucket in lookup table, in longs
- * @lt:		Lookup table: 'groups' rows of NFT_PIPAPO_BUCKETS buckets
- * @lt_aligned:	Version of @lt aligned to NFT_PIPAPO_ALIGN bytes
- * @mt:		Mapping table: one bucket per rule
- */
-struct nft_pipapo_field {
-	int groups;
-	unsigned long rules;
-	size_t bsize;
-#ifdef NFT_PIPAPO_ALIGN
-	unsigned long *lt_aligned;
-#endif
-	unsigned long *lt;
-	union nft_pipapo_map_bucket *mt;
-};
-
-/**
- * struct nft_pipapo_match - Data used for lookup and matching
- * @field_count		Amount of fields in set
- * @scratch:		Preallocated per-CPU maps for partial matching results
- * @scratch_aligned:	Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
- * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
- * @rcu			Matching data is swapped on commits
- * @f:			Fields, with lookup and mapping tables
- */
-struct nft_pipapo_match {
-	int field_count;
-#ifdef NFT_PIPAPO_ALIGN
-	unsigned long * __percpu *scratch_aligned;
-#endif
-	unsigned long * __percpu *scratch;
-	size_t bsize_max;
-	struct rcu_head rcu;
-	struct nft_pipapo_field f[0];
-};
+#include "nft_set_pipapo.h"
 
 /* Current working bitmap index, toggled between field matches */
 static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index);
 
-/**
- * struct nft_pipapo - Representation of a set
- * @match:	Currently in-use matching data
- * @clone:	Copy where pending insertions and deletions are kept
- * @groups:	Total amount of 4-bit groups for fields in this set
- * @width:	Total bytes to be matched for one packet, including padding
- * @dirty:	Working copy has pending insertions or deletions
- * @last_gc:	Timestamp of last garbage collection run, jiffies
- * @start_data:	Key data of start element for insertion
- * @start_elem:	Start element for insertion
- */
-struct nft_pipapo {
-	struct nft_pipapo_match __rcu *match;
-	struct nft_pipapo_match *clone;
-	int groups;
-	int width;
-	bool dirty;
-	unsigned long last_gc;
-	u8 start_data[NFT_DATA_VALUE_MAXLEN * sizeof(u32)];
-	struct nft_pipapo_elem *start_elem;
-};
-
-struct nft_pipapo_elem;
-
-/**
- * struct nft_pipapo_elem - API-facing representation of single set element
- * @start:	Pointer to element that represents start of interval
- * @ext:	nftables API extensions
- */
-struct nft_pipapo_elem {
-	struct nft_pipapo_elem *start;
-	struct nft_set_ext ext;
-};
-
 /**
  * pipapo_refill() - For each set bit, set bits from selected mapping table item
  * @map:	Bitmap to be scanned for set bits
@@ -514,9 +361,8 @@  struct nft_pipapo_elem {
  *
  * Return: -1 on no match, bit position on 'match_only', 0 otherwise.
  */
-static int pipapo_refill(unsigned long *map, int len, int rules,
-			 unsigned long *dst, union nft_pipapo_map_bucket *mt,
-			 bool match_only)
+int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst,
+		  union nft_pipapo_map_bucket *mt, bool match_only)
 {
 	unsigned long bitset;
 	int k, ret = -1;
@@ -635,7 +481,7 @@  static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 	nft_pipapo_for_each_field(f, i, m) {
 		bool last = i == m->field_count - 1;
 		unsigned long *lt = f->lt;
-		int b, group, j;
+		int b, j;
 
 		/* For each 4-bit group: select lookup table bucket depending on
 		 * packet bytes value, then AND bucket value. Unroll loops for
@@ -653,21 +499,8 @@  static bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
 		} else if (f->groups == 32) {
 			NFT_PIPAPO_MATCH_32(res_map, lt, f->bsize, rp, j);
 		} else {
-			for (group = 0; group < f->groups; group++) {
-				u8 v;
-
-				if (group % 2) {
-					v = *rp & 0x0f;
-					rp++;
-				} else {
-					v = *rp >> 4;
-				}
-				__bitmap_and(res_map, res_map,
-					     lt + v * f->bsize,
-					     f->bsize * BITS_PER_LONG);
-
-				lt += f->bsize * NFT_PIPAPO_BUCKETS;
-			}
+			pipapo_and_field_buckets(f, res_map, rp);
+			rp += f->groups / NFT_PIPAPO_GROUPS_PER_BYTE;
 		}
 
 		/* Now populate the bitmap for the next field, unless this is
@@ -2077,21 +1910,11 @@  static u64 nft_pipapo_privsize(const struct nlattr * const nla[],
 }
 
 /**
- * nft_pipapo_estimate() - Estimate set size, space and lookup complexity
+ * nft_pipapo_estimate() - Set size, space and lookup complexity
  * @desc:	Set description, initial element count used here
  * @features:	Flags: NFT_SET_SUBKEY needs to be there
  * @est:	Storage for estimation data
  *
- * The size for this set type can vary dramatically, as it depends on the number
- * of rules (composing netmasks) the entries expand to. We compute the worst
- * case here, in order to ensure that other types are used if concatenation of
- * ranges is not needed.
- *
- * In general, for a non-ranged entry or a single composing netmask, we need
- * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that
- * is, each input bit needs four bits of matching data), plus a bucket in the
- * mapping table for each field.
- *
  * Return: true
  */
 static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features,
@@ -2100,26 +1923,7 @@  static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features,
 	if (!(features & NFT_SET_SUBKEY))
 		return false;
 
-	est->size = sizeof(struct nft_pipapo) + sizeof(struct nft_pipapo_match);
-
-	/* Worst-case with current amount of 32-bit VM registers (16 of them):
-	 * - 2 IPv6 addresses	8 registers
-	 * - 2 interface names	8 registers
-	 * that is, four 128-bit fields:
-	 */
-	est->size += sizeof(struct nft_pipapo_field) * 4;
-
-	/* expanding to worst-case ranges, 128 * 2 rules each, resulting in:
-	 * - 128 4-bit groups
-	 * - each set entry taking 256 bits in each bucket
-	 */
-	est->size += desc->size * NFT_PIPAPO_MAX_BITS / NFT_PIPAPO_GROUP_BITS *
-		     NFT_PIPAPO_BUCKETS * NFT_PIPAPO_MAX_BITS * 2 /
-		     BITS_PER_BYTE;
-
-	/* and we need mapping buckets, too */
-	est->size += desc->size * NFT_PIPAPO_MAP_NBITS *
-		     sizeof(union nft_pipapo_map_bucket);
+	est->size = pipapo_estimate_size(desc->size);
 
 	est->lookup = NFT_SET_CLASS_O_LOG_N;
 
diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
new file mode 100644
index 000000000000..0261f72b804f
--- /dev/null
+++ b/net/netfilter/nft_set_pipapo.h
@@ -0,0 +1,236 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+
+#ifndef _NFT_SET_PIPAPO_H
+
+#include <linux/log2.h>
+#include <net/ipv6.h>			/* For the maximum length of a field */
+
+/* Count of concatenated fields depends on count of 32-bit nftables registers */
+#define NFT_PIPAPO_MAX_FIELDS		NFT_REG32_COUNT
+
+/* 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)
+
+/* Number of bits to be grouped together in lookup table buckets, arbitrary */
+#define NFT_PIPAPO_GROUP_BITS		4
+#define NFT_PIPAPO_GROUPS_PER_BYTE	(BITS_PER_BYTE / NFT_PIPAPO_GROUP_BITS)
+
+/* Fields are padded to 32 bits in input registers */
+#define NFT_PIPAPO_GROUPS_PADDED_SIZE(x)				\
+	(round_up((x) / NFT_PIPAPO_GROUPS_PER_BYTE, sizeof(u32)))
+#define NFT_PIPAPO_GROUPS_PADDING(x)					\
+	(NFT_PIPAPO_GROUPS_PADDED_SIZE((x)) - (x) / NFT_PIPAPO_GROUPS_PER_BYTE)
+
+/* Number of buckets, given by 2 ^ n, with n grouped bits */
+#define NFT_PIPAPO_BUCKETS		(1 << NFT_PIPAPO_GROUP_BITS)
+
+/* Each n-bit range maps to up to n * 2 rules */
+#define NFT_PIPAPO_MAP_NBITS		(const_ilog2(NFT_PIPAPO_MAX_BITS * 2))
+
+/* Use the rest of mapping table buckets for rule indices, but it makes no sense
+ * to exceed 32 bits
+ */
+#if BITS_PER_LONG == 64
+#define NFT_PIPAPO_MAP_TOBITS		32
+#else
+#define NFT_PIPAPO_MAP_TOBITS		(BITS_PER_LONG - NFT_PIPAPO_MAP_NBITS)
+#endif
+
+/* ...which gives us the highest allowed index for a rule */
+#define NFT_PIPAPO_RULE0_MAX		((1UL << (NFT_PIPAPO_MAP_TOBITS - 1)) \
+					- (1UL << NFT_PIPAPO_MAP_NBITS))
+
+/* Definitions for vectorised implementations */
+#ifdef NFT_PIPAPO_ALIGN
+#define NFT_PIPAPO_ALIGN_HEADROOM					\
+	(NFT_PIPAPO_ALIGN - ARCH_KMALLOC_MINALIGN)
+#define NFT_PIPAPO_LT_ALIGN(lt)		(PTR_ALIGN((lt), NFT_PIPAPO_ALIGN))
+#define NFT_PIPAPO_LT_ASSIGN(field, x)					\
+	do {								\
+		(field)->lt_aligned = NFT_PIPAPO_LT_ALIGN(x);		\
+		(field)->lt = (x);					\
+	} while (0);
+#else
+#define NFT_PIPAPO_ALIGN_HEADROOM	0
+#define NFT_PIPAPO_LT_ALIGN(lt)		(lt)
+#define NFT_PIPAPO_LT_ASSIGN(field, x)					\
+	do {								\
+		(field)->lt = (x);					\
+	} while (0);
+#endif /* NFT_PIPAPO_ALIGN */
+
+#define nft_pipapo_for_each_field(field, index, match)		\
+	for ((field) = (match)->f, (index) = 0;			\
+	     (index) < (match)->field_count;			\
+	     (index)++, (field)++)
+
+/**
+ * union nft_pipapo_map_bucket - Bucket of mapping table
+ * @to:		First rule number (in next field) this rule maps to
+ * @n:		Number of rules (in next field) this rule maps to
+ * @e:		If there's no next field, pointer to element this rule maps to
+ */
+union nft_pipapo_map_bucket {
+	struct {
+#if BITS_PER_LONG == 64
+		static_assert(NFT_PIPAPO_MAP_TOBITS <= 32);
+		u32 to;
+
+		static_assert(NFT_PIPAPO_MAP_NBITS <= 32);
+		u32 n;
+#else
+		unsigned long to:NFT_PIPAPO_MAP_TOBITS;
+		unsigned long  n:NFT_PIPAPO_MAP_NBITS;
+#endif
+	};
+	struct nft_pipapo_elem *e;
+};
+
+/**
+ * struct nft_pipapo_field - Lookup, mapping tables and related data for a field
+ * @groups:	Amount of 4-bit groups
+ * @rules:	Number of inserted rules
+ * @bsize:	Size of each bucket in lookup table, in longs
+ * @lt:		Lookup table: 'groups' rows of NFT_PIPAPO_BUCKETS buckets
+ * @lt_aligned:	Version of @lt aligned to NFT_PIPAPO_ALIGN bytes
+ * @mt:		Mapping table: one bucket per rule
+ */
+struct nft_pipapo_field {
+	int groups;
+	unsigned long rules;
+	size_t bsize;
+	unsigned long *lt;
+#ifdef NFT_PIPAPO_ALIGN
+	unsigned long *lt_aligned;
+#endif
+	union nft_pipapo_map_bucket *mt;
+};
+
+/**
+ * struct nft_pipapo_match - Data used for lookup and matching
+ * @field_count		Amount of fields in set
+ * @scratch:		Preallocated per-CPU maps for partial matching results
+ * @scratch_aligned:	Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes
+ * @bsize_max:		Maximum lookup table bucket size of all fields, in longs
+ * @rcu			Matching data is swapped on commits
+ * @f:			Fields, with lookup and mapping tables
+ */
+struct nft_pipapo_match {
+	int field_count;
+#ifdef NFT_PIPAPO_ALIGN
+	unsigned long * __percpu *scratch_aligned;
+#endif
+	unsigned long * __percpu *scratch;
+	size_t bsize_max;
+	struct rcu_head rcu;
+	struct nft_pipapo_field f[0];
+};
+
+/**
+ * struct nft_pipapo - Representation of a set
+ * @match:	Currently in-use matching data
+ * @clone:	Copy where pending insertions and deletions are kept
+ * @groups:	Total amount of 4-bit groups for fields in this set
+ * @width:	Total bytes to be matched for one packet, including padding
+ * @dirty:	Working copy has pending insertions or deletions
+ * @last_gc:	Timestamp of last garbage collection run, jiffies
+ * @start_data:	Key data of start element for insertion
+ * @start_elem:	Start element for insertion
+ */
+struct nft_pipapo {
+	struct nft_pipapo_match __rcu *match;
+	struct nft_pipapo_match *clone;
+	int groups;
+	int width;
+	bool dirty;
+	unsigned long last_gc;
+	u8 start_data[NFT_DATA_VALUE_MAXLEN * sizeof(u32)];
+	struct nft_pipapo_elem *start_elem;
+};
+
+struct nft_pipapo_elem;
+
+/**
+ * struct nft_pipapo_elem - API-facing representation of single set element
+ * @start:	Pointer to element that represents start of interval
+ * @ext:	nftables API extensions
+ */
+struct nft_pipapo_elem {
+	struct nft_pipapo_elem *start;
+	struct nft_set_ext ext;
+};
+
+int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst,
+		  union nft_pipapo_map_bucket *mt, bool match_only);
+
+/**
+ * pipapo_and_field_buckets() - Select buckets from packet data and intersect
+ * @f:		Field including lookup table
+ * @dst:	Scratch map for partial matching result
+ * @rp:		Packet data register pointer
+ */
+static inline void pipapo_and_field_buckets(struct nft_pipapo_field *f,
+					    unsigned long *dst, const u8 *rp)
+{
+	unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt);
+	int group;
+
+	for (group = 0; group < f->groups; group++) {
+		u8 v;
+
+		if (group % 2) {
+			v = *rp & 0x0f;
+			rp++;
+		} else {
+			v = *rp >> 4;
+		}
+		__bitmap_and(dst, dst, lt + v * f->bsize,
+			     f->bsize * BITS_PER_LONG);
+
+		lt += f->bsize * NFT_PIPAPO_BUCKETS;
+	}
+}
+
+/**
+ * pipapo_estimate_size() - Estimate worst-case for set size
+ * @elem_count:		Count of initial set elements
+ *
+ * The size for this set type can vary dramatically, as it depends on the number
+ * of rules (composing netmasks) the entries expand to. We compute the worst
+ * case here, in order to ensure that other types are used if concatenation of
+ * ranges is not needed.
+ *
+ * In general, for a non-ranged entry or a single composing netmask, we need
+ * one bit in each of the sixteen NFT_PIPAPO_BUCKETS, for each 4-bit group (that
+ * is, each input bit needs four bits of matching data), plus a bucket in the
+ * mapping table for each field.
+ *
+ * Return: estimated worst-case set size, in bytes.
+ */
+static int pipapo_estimate_size(int elem_count)
+{
+	int size = sizeof(struct nft_pipapo) + sizeof(struct nft_pipapo_match);
+
+	/* Worst-case with current amount of 32-bit VM registers (16 of them):
+	 * - 2 IPv6 addresses	8 registers
+	 * - 2 interface names	8 registers
+	 * that is, four 128-bit fields:
+	 */
+	size += sizeof(struct nft_pipapo_field) * 4;
+
+	/* expanding to worst-case ranges, 128 * 2 rules each, resulting in:
+	 * - 128 4-bit groups
+	 * - each set entry taking 256 bits in each bucket
+	 */
+	size += elem_count * NFT_PIPAPO_MAX_BITS / NFT_PIPAPO_GROUP_BITS *
+		NFT_PIPAPO_BUCKETS * NFT_PIPAPO_MAX_BITS * 2 / BITS_PER_BYTE;
+
+	/* and we need mapping buckets, too */
+	size += elem_count * NFT_PIPAPO_MAP_NBITS *
+		sizeof(union nft_pipapo_map_bucket);
+
+	return size;
+}
+
+#endif /* _NFT_SET_PIPAPO_H */