Skip to content

Commit

Permalink
nft_set_pipapo: Prepare for vectorised implementation: helpers
Browse files Browse the repository at this point in the history 
Move most macros and helpers to a header file, so that they can be
conveniently used by related implementations.

No functional changes are intended here.

Signed-off-by: Stefano Brivio <[email protected]>
Signed-off-by: Pablo Neira Ayuso <[email protected]>
  • Loading branch information
@sbrivio-rh @ummakynes
sbrivio-rh authored and ummakynes committed Mar 15, 2020
1 parent bf3e583 commit 8683f4b
Show file tree
Hide file tree
Showing 2 changed files with 285 additions and 261 deletions.
269 changes: 8 additions & 261 deletions net/netfilter/nft_set_pipapo.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -330,188 +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)

/* Bits to be grouped together in table buckets depending on set size */
#define NFT_PIPAPO_GROUP_BITS_INIT NFT_PIPAPO_GROUP_BITS_SMALL_SET
#define NFT_PIPAPO_GROUP_BITS_SMALL_SET 8
#define NFT_PIPAPO_GROUP_BITS_LARGE_SET 4
#define NFT_PIPAPO_GROUP_BITS_ARE_8_OR_4 \
BUILD_BUG_ON((NFT_PIPAPO_GROUP_BITS_SMALL_SET != 8) || \
(NFT_PIPAPO_GROUP_BITS_LARGE_SET != 4))
#define NFT_PIPAPO_GROUPS_PER_BYTE(f) (BITS_PER_BYTE / (f)->bb)

/* If a lookup table gets bigger than NFT_PIPAPO_LT_SIZE_HIGH, switch to the
* small group width, and switch to the big group width if the table gets
* smaller than NFT_PIPAPO_LT_SIZE_LOW.
*
* Picking 2MiB as threshold (for a single table) avoids as much as possible
* crossing page boundaries on most architectures (x86-64 and MIPS huge pages,
* ARMv7 supersections, POWER "large" pages, SPARC Level 1 regions, etc.), which
* keeps performance nice in case kvmalloc() gives us non-contiguous areas.
*/
#define NFT_PIPAPO_LT_SIZE_THRESHOLD (1 << 21)
#define NFT_PIPAPO_LT_SIZE_HYSTERESIS (1 << 16)
#define NFT_PIPAPO_LT_SIZE_HIGH NFT_PIPAPO_LT_SIZE_THRESHOLD
#define NFT_PIPAPO_LT_SIZE_LOW NFT_PIPAPO_LT_SIZE_THRESHOLD - \
NFT_PIPAPO_LT_SIZE_HYSTERESIS

/* Fields are padded to 32 bits in input registers */
#define NFT_PIPAPO_GROUPS_PADDED_SIZE(f) \
(round_up((f)->groups / NFT_PIPAPO_GROUPS_PER_BYTE(f), sizeof(u32)))
#define NFT_PIPAPO_GROUPS_PADDING(f) \
(NFT_PIPAPO_GROUPS_PADDED_SIZE(f) - (f)->groups / \
NFT_PIPAPO_GROUPS_PER_BYTE(f))

/* Number of buckets given by 2 ^ n, with n bucket bits */
#define NFT_PIPAPO_BUCKETS(bb) (1 << (bb))

/* 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 bit groups
* @rules: Number of inserted rules
* @bsize: Size of each bucket in lookup table, in longs
* @bb: Number of bits grouped together in lookup table buckets
* @lt: Lookup table: 'groups' rows of 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;
int bb;
#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[];
};
#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
* @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
*/
struct nft_pipapo {
struct nft_pipapo_match __rcu *match;
struct nft_pipapo_match *clone;
int width;
bool dirty;
unsigned long last_gc;
};

struct nft_pipapo_elem;

/**
* struct nft_pipapo_elem - API-facing representation of single set element
* @ext: nftables API extensions
*/
struct nft_pipapo_elem {
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
Expand All @@ -529,9 +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;
Expand Down Expand Up @@ -565,54 +396,6 @@ static int pipapo_refill(unsigned long *map, int len, int rules,
return ret;
}

/**
* pipapo_and_field_buckets_4bit() - Intersect buckets for 4-bit groups
* @f: Field including lookup table
* @dst: Area to store result
* @data: Input data selecting table buckets
*/
static void pipapo_and_field_buckets_4bit(struct nft_pipapo_field *f,
unsigned long *dst,
const u8 *data)
{
unsigned long *lt = f->lt;
int group;

for (group = 0; group < f->groups; group += BITS_PER_BYTE / 4, data++) {
u8 v;

v = *data >> 4;
__bitmap_and(dst, dst, lt + v * f->bsize,
f->bsize * BITS_PER_LONG);
lt += f->bsize * NFT_PIPAPO_BUCKETS(4);

v = *data & 0x0f;
__bitmap_and(dst, dst, lt + v * f->bsize,
f->bsize * BITS_PER_LONG);
lt += f->bsize * NFT_PIPAPO_BUCKETS(4);
}
}

/**
* pipapo_and_field_buckets_8bit() - Intersect buckets for 8-bit groups
* @f: Field including lookup table
* @dst: Area to store result
* @data: Input data selecting table buckets
*/
static void pipapo_and_field_buckets_8bit(struct nft_pipapo_field *f,
unsigned long *dst,
const u8 *data)
{
unsigned long *lt = f->lt;
int group;

for (group = 0; group < f->groups; group++, data++) {
__bitmap_and(dst, dst, lt + *data * f->bsize,
f->bsize * BITS_PER_LONG);
lt += f->bsize * NFT_PIPAPO_BUCKETS(8);
}
}

/**
* nft_pipapo_lookup() - Lookup function
* @net: Network namespace
Expand Down Expand Up @@ -753,7 +536,6 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net,
memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));

nft_pipapo_for_each_field(f, i, m) {
unsigned long *lt = NFT_PIPAPO_LT_ALIGN(f->lt);
bool last = i == m->field_count - 1;
int b;

Expand Down Expand Up @@ -2190,58 +1972,23 @@ static u64 nft_pipapo_privsize(const struct nlattr * const nla[],
}

/**
* nft_pipapo_estimate() - Estimate set size, space and lookup complexity
* @desc: Set description, element count and field description used here
* nft_pipapo_estimate() - Set size, space and lookup complexity
* @desc: Set description, element count and field description used
* @features: Flags: NFT_SET_INTERVAL 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 general, for a non-ranged entry or a single composing netmask, we need
* one bit in each of the sixteen 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 only for compatible range concatenations
* Return: true if set description is compatible, false otherwise
*/
static bool nft_pipapo_estimate(const struct nft_set_desc *desc, u32 features,
struct nft_set_estimate *est)
{
unsigned long entry_size;
int i;

if (!(features & NFT_SET_INTERVAL) || desc->field_count <= 1)
return false;

for (i = 0, entry_size = 0; i < desc->field_count; i++) {
unsigned long rules;

if (desc->field_len[i] > NFT_PIPAPO_MAX_BYTES)
return false;

/* Worst-case ranges for each concatenated field: each n-bit
* field can expand to up to n * 2 rules in each bucket, and
* each rule also needs a mapping bucket.
*/
rules = ilog2(desc->field_len[i] * BITS_PER_BYTE) * 2;
entry_size += rules *
NFT_PIPAPO_BUCKETS(NFT_PIPAPO_GROUP_BITS_INIT) /
BITS_PER_BYTE;
entry_size += rules * sizeof(union nft_pipapo_map_bucket);
}

/* Rules in lookup and mapping tables are needed for each entry */
est->size = desc->size * entry_size;
if (est->size && div_u64(est->size, desc->size) != entry_size)
est->size = pipapo_estimate_size(desc);
if (!est->size)
return false;

est->size += sizeof(struct nft_pipapo) +
sizeof(struct nft_pipapo_match) * 2;

est->size += sizeof(struct nft_pipapo_field) * desc->field_count;

est->lookup = NFT_SET_CLASS_O_LOG_N;

est->space = NFT_SET_CLASS_O_N;
Expand Down
Loading

0 comments on commit 8683f4b

Please sign in to comment.