diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 16:38:14 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-06 16:38:14 (GMT) |
commit | ae045e2455429c418a418a3376301a9e5753a0a8 (patch) | |
tree | b445bdeecd3f38aa0d0a29c9585cee49e4ccb0f1 /lib | |
parent | f4f142ed4ef835709c7e6d12eaca10d190bcebed (diff) | |
parent | d247b6ab3ce6dd43665780865ec5fa145d9ab6bd (diff) | |
download | linux-ae045e2455429c418a418a3376301a9e5753a0a8.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
1) Steady transitioning of the BPF instructure to a generic spot so
all kernel subsystems can make use of it, from Alexei Starovoitov.
2) SFC driver supports busy polling, from Alexandre Rames.
3) Take advantage of hash table in UDP multicast delivery, from David
Held.
4) Lighten locking, in particular by getting rid of the LRU lists, in
inet frag handling. From Florian Westphal.
5) Add support for various RFC6458 control messages in SCTP, from
Geir Ola Vaagland.
6) Allow to filter bridge forwarding database dumps by device, from
Jamal Hadi Salim.
7) virtio-net also now supports busy polling, from Jason Wang.
8) Some low level optimization tweaks in pktgen from Jesper Dangaard
Brouer.
9) Add support for ipv6 address generation modes, so that userland
can have some input into the process. From Jiri Pirko.
10) Consolidate common TCP connection request code in ipv4 and ipv6,
from Octavian Purdila.
11) New ARP packet logger in netfilter, from Pablo Neira Ayuso.
12) Generic resizable RCU hash table, with intial users in netlink and
nftables. From Thomas Graf.
13) Maintain a name assignment type so that userspace can see where a
network device name came from (enumerated by kernel, assigned
explicitly by userspace, etc.) From Tom Gundersen.
14) Automatic flow label generation on transmit in ipv6, from Tom
Herbert.
15) New packet timestamping facilities from Willem de Bruijn, meant to
assist in measuring latencies going into/out-of the packet
scheduler, latency from TCP data transmission to ACK, etc"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1536 commits)
cxgb4 : Disable recursive mailbox commands when enabling vi
net: reduce USB network driver config options.
tg3: Modify tg3_tso_bug() to handle multiple TX rings
amd-xgbe: Perform phy connect/disconnect at dev open/stop
amd-xgbe: Use dma_set_mask_and_coherent to set DMA mask
net: sun4i-emac: fix memory leak on bad packet
sctp: fix possible seqlock seadlock in sctp_packet_transmit()
Revert "net: phy: Set the driver when registering an MDIO bus device"
cxgb4vf: Turn off SGE RX/TX Callback Timers and interrupts in PCI shutdown routine
team: Simplify return path of team_newlink
bridge: Update outdated comment on promiscuous mode
net-timestamp: ACK timestamp for bytestreams
net-timestamp: TCP timestamping
net-timestamp: SCHED timestamp on entering packet scheduler
net-timestamp: add key to disambiguate concurrent datagrams
net-timestamp: move timestamp flags out of sk_flags
net-timestamp: extend SCM_TIMESTAMPING ancillary data struct
cxgb4i : Move stray CPL definitions to cxgb4 driver
tcp: reduce spurious retransmits due to transient SACK reneging
qlcnic: Initialize dcbnl_ops before register_netdev
...
Diffstat (limited to 'lib')
-rw-r--r-- | lib/Kconfig.debug | 8 | ||||
-rw-r--r-- | lib/Makefile | 2 | ||||
-rw-r--r-- | lib/crc32.c | 153 | ||||
-rw-r--r-- | lib/dynamic_debug.c | 8 | ||||
-rw-r--r-- | lib/iovec.c | 4 | ||||
-rw-r--r-- | lib/net_utils.c | 10 | ||||
-rw-r--r-- | lib/random32.c | 49 | ||||
-rw-r--r-- | lib/rhashtable.c | 797 | ||||
-rw-r--r-- | lib/test_bpf.c | 28 |
9 files changed, 935 insertions, 124 deletions
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 1f630ad..cfe7df8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1536,6 +1536,14 @@ config TEST_STRING_HELPERS config TEST_KSTRTOX tristate "Test kstrto*() family of functions at runtime" +config TEST_RHASHTABLE + bool "Perform selftest on resizable hash table" + default n + help + Enable this option to test the rhashtable functions at boot. + + If unsure, say N. + endmenu # runtime tests config PROVIDE_OHCI1394_DMA_INIT diff --git a/lib/Makefile b/lib/Makefile index 230b4b1..8427df9 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -26,7 +26,7 @@ obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \ bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \ gcd.o lcm.o list_sort.o uuid.o flex_array.o iovec.o clz_ctz.o \ bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o kfifo.o \ - percpu-refcount.o percpu_ida.o hash.o + percpu-refcount.o percpu_ida.o hash.o rhashtable.o obj-y += string_helpers.o obj-$(CONFIG_TEST_STRING_HELPERS) += test-string_helpers.o obj-y += kstrtox.o diff --git a/lib/crc32.c b/lib/crc32.c index 21a7b2135..9a907d4 100644 --- a/lib/crc32.c +++ b/lib/crc32.c @@ -50,34 +50,10 @@ MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>"); MODULE_DESCRIPTION("Various CRC32 calculations"); MODULE_LICENSE("GPL"); -#define GF2_DIM 32 - -static u32 gf2_matrix_times(u32 *mat, u32 vec) -{ - u32 sum = 0; - - while (vec) { - if (vec & 1) - sum ^= *mat; - vec >>= 1; - mat++; - } - - return sum; -} - -static void gf2_matrix_square(u32 *square, u32 *mat) -{ - int i; - - for (i = 0; i < GF2_DIM; i++) - square[i] = gf2_matrix_times(mat, mat[i]); -} - #if CRC_LE_BITS > 8 || CRC_BE_BITS > 8 /* implements slicing-by-4 or slicing-by-8 algorithm */ -static inline u32 +static inline u32 __pure crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) { # ifdef __LITTLE_ENDIAN @@ -155,51 +131,6 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256]) } #endif -/* For conditions of distribution and use, see copyright notice in zlib.h */ -static u32 crc32_generic_combine(u32 crc1, u32 crc2, size_t len2, - u32 polynomial) -{ - u32 even[GF2_DIM]; /* Even-power-of-two zeros operator */ - u32 odd[GF2_DIM]; /* Odd-power-of-two zeros operator */ - u32 row; - int i; - - if (len2 <= 0) - return crc1; - - /* Put operator for one zero bit in odd */ - odd[0] = polynomial; - row = 1; - for (i = 1; i < GF2_DIM; i++) { - odd[i] = row; - row <<= 1; - } - - gf2_matrix_square(even, odd); /* Put operator for two zero bits in even */ - gf2_matrix_square(odd, even); /* Put operator for four zero bits in odd */ - - /* Apply len2 zeros to crc1 (first square will put the operator for one - * zero byte, eight zero bits, in even). - */ - do { - /* Apply zeros operator for this bit of len2 */ - gf2_matrix_square(even, odd); - if (len2 & 1) - crc1 = gf2_matrix_times(even, crc1); - len2 >>= 1; - /* If no more bits set, then done */ - if (len2 == 0) - break; - /* Another iteration of the loop with odd and even swapped */ - gf2_matrix_square(odd, even); - if (len2 & 1) - crc1 = gf2_matrix_times(odd, crc1); - len2 >>= 1; - } while (len2 != 0); - - crc1 ^= crc2; - return crc1; -} /** * crc32_le_generic() - Calculate bitwise little-endian Ethernet AUTODIN II @@ -271,19 +202,81 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len) (const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE); } #endif -u32 __pure crc32_le_combine(u32 crc1, u32 crc2, size_t len2) +EXPORT_SYMBOL(crc32_le); +EXPORT_SYMBOL(__crc32c_le); + +/* + * This multiplies the polynomials x and y modulo the given modulus. + * This follows the "little-endian" CRC convention that the lsbit + * represents the highest power of x, and the msbit represents x^0. + */ +static u32 __attribute_const__ gf2_multiply(u32 x, u32 y, u32 modulus) { - return crc32_generic_combine(crc1, crc2, len2, CRCPOLY_LE); + u32 product = x & 1 ? y : 0; + int i; + + for (i = 0; i < 31; i++) { + product = (product >> 1) ^ (product & 1 ? modulus : 0); + x >>= 1; + product ^= x & 1 ? y : 0; + } + + return product; } -u32 __pure __crc32c_le_combine(u32 crc1, u32 crc2, size_t len2) +/** + * crc32_generic_shift - Append len 0 bytes to crc, in logarithmic time + * @crc: The original little-endian CRC (i.e. lsbit is x^31 coefficient) + * @len: The number of bytes. @crc is multiplied by x^(8*@len) + * @polynomial: The modulus used to reduce the result to 32 bits. + * + * It's possible to parallelize CRC computations by computing a CRC + * over separate ranges of a buffer, then summing them. + * This shifts the given CRC by 8*len bits (i.e. produces the same effect + * as appending len bytes of zero to the data), in time proportional + * to log(len). + */ +static u32 __attribute_const__ crc32_generic_shift(u32 crc, size_t len, + u32 polynomial) { - return crc32_generic_combine(crc1, crc2, len2, CRC32C_POLY_LE); + u32 power = polynomial; /* CRC of x^32 */ + int i; + + /* Shift up to 32 bits in the simple linear way */ + for (i = 0; i < 8 * (int)(len & 3); i++) + crc = (crc >> 1) ^ (crc & 1 ? polynomial : 0); + + len >>= 2; + if (!len) + return crc; + + for (;;) { + /* "power" is x^(2^i), modulo the polynomial */ + if (len & 1) + crc = gf2_multiply(crc, power, polynomial); + + len >>= 1; + if (!len) + break; + + /* Square power, advancing to x^(2^(i+1)) */ + power = gf2_multiply(power, power, polynomial); + } + + return crc; } -EXPORT_SYMBOL(crc32_le); -EXPORT_SYMBOL(crc32_le_combine); -EXPORT_SYMBOL(__crc32c_le); -EXPORT_SYMBOL(__crc32c_le_combine); + +u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len) +{ + return crc32_generic_shift(crc, len, CRCPOLY_LE); +} + +u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len) +{ + return crc32_generic_shift(crc, len, CRC32C_POLY_LE); +} +EXPORT_SYMBOL(crc32_le_shift); +EXPORT_SYMBOL(__crc32c_le_shift); /** * crc32_be_generic() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32 @@ -351,7 +344,7 @@ EXPORT_SYMBOL(crc32_be); #ifdef CONFIG_CRC32_SELFTEST /* 4096 random bytes */ -static u8 __attribute__((__aligned__(8))) test_buf[] = +static u8 const __aligned(8) test_buf[] __initconst = { 0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30, 0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4, @@ -875,7 +868,7 @@ static struct crc_test { u32 crc_le; /* expected crc32_le result */ u32 crc_be; /* expected crc32_be result */ u32 crc32c_le; /* expected crc32c_le result */ -} test[] = +} const test[] __initconst = { {0x674bf11d, 0x00000038, 0x00000542, 0x0af6d466, 0xd8b6e4c1, 0xf6e93d6c}, {0x35c672c6, 0x0000003a, 0x000001aa, 0xc6d3dfba, 0x28aaf3ad, 0x0fe92aca}, diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c index 7288e38..c9afbe2 100644 --- a/lib/dynamic_debug.c +++ b/lib/dynamic_debug.c @@ -614,13 +614,15 @@ int __dynamic_netdev_dbg(struct _ddebug *descriptor, char buf[PREFIX_SIZE]; res = dev_printk_emit(7, dev->dev.parent, - "%s%s %s %s: %pV", + "%s%s %s %s%s: %pV", dynamic_emit_prefix(descriptor, buf), dev_driver_string(dev->dev.parent), dev_name(dev->dev.parent), - netdev_name(dev), &vaf); + netdev_name(dev), netdev_reg_state(dev), + &vaf); } else if (dev) { - res = printk(KERN_DEBUG "%s: %pV", netdev_name(dev), &vaf); + res = printk(KERN_DEBUG "%s%s: %pV", netdev_name(dev), + netdev_reg_state(dev), &vaf); } else { res = printk(KERN_DEBUG "(NULL net_device): %pV", &vaf); } diff --git a/lib/iovec.c b/lib/iovec.c index 7a7c2da..df3abd1 100644 --- a/lib/iovec.c +++ b/lib/iovec.c @@ -85,6 +85,10 @@ EXPORT_SYMBOL(memcpy_toiovecend); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len) { + /* No data? Done! */ + if (len == 0) + return 0; + /* Skip over the finished iovecs */ while (offset >= iov->iov_len) { offset -= iov->iov_len; diff --git a/lib/net_utils.c b/lib/net_utils.c index 2e3c52c..148fc6e 100644 --- a/lib/net_utils.c +++ b/lib/net_utils.c @@ -3,24 +3,24 @@ #include <linux/ctype.h> #include <linux/kernel.h> -int mac_pton(const char *s, u8 *mac) +bool mac_pton(const char *s, u8 *mac) { int i; /* XX:XX:XX:XX:XX:XX */ if (strlen(s) < 3 * ETH_ALEN - 1) - return 0; + return false; /* Don't dirty result unless string is valid MAC. */ for (i = 0; i < ETH_ALEN; i++) { if (!isxdigit(s[i * 3]) || !isxdigit(s[i * 3 + 1])) - return 0; + return false; if (i != ETH_ALEN - 1 && s[i * 3 + 2] != ':') - return 0; + return false; } for (i = 0; i < ETH_ALEN; i++) { mac[i] = (hex_to_bin(s[i * 3]) << 4) | hex_to_bin(s[i * 3 + 1]); } - return 1; + return true; } EXPORT_SYMBOL(mac_pton); diff --git a/lib/random32.c b/lib/random32.c index fa5da61..c9b6bf3 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -40,6 +40,10 @@ #ifdef CONFIG_RANDOM32_SELFTEST static void __init prandom_state_selftest(void); +#else +static inline void prandom_state_selftest(void) +{ +} #endif static DEFINE_PER_CPU(struct rnd_state, net_rand_state); @@ -53,8 +57,7 @@ static DEFINE_PER_CPU(struct rnd_state, net_rand_state); */ u32 prandom_u32_state(struct rnd_state *state) { -#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b) - +#define TAUSWORTHE(s, a, b, c, d) ((s & c) << d) ^ (((s << a) ^ s) >> b) state->s1 = TAUSWORTHE(state->s1, 6U, 13U, 4294967294U, 18U); state->s2 = TAUSWORTHE(state->s2, 2U, 27U, 4294967288U, 2U); state->s3 = TAUSWORTHE(state->s3, 13U, 21U, 4294967280U, 7U); @@ -147,21 +150,25 @@ static void prandom_warmup(struct rnd_state *state) prandom_u32_state(state); } -static void prandom_seed_very_weak(struct rnd_state *state, u32 seed) +static u32 __extract_hwseed(void) { - /* Note: This sort of seeding is ONLY used in test cases and - * during boot at the time from core_initcall until late_initcall - * as we don't have a stronger entropy source available yet. - * After late_initcall, we reseed entire state, we have to (!), - * otherwise an attacker just needs to search 32 bit space to - * probe for our internal 128 bit state if he knows a couple - * of prandom32 outputs! - */ -#define LCG(x) ((x) * 69069U) /* super-duper LCG */ - state->s1 = __seed(LCG(seed), 2U); - state->s2 = __seed(LCG(state->s1), 8U); - state->s3 = __seed(LCG(state->s2), 16U); - state->s4 = __seed(LCG(state->s3), 128U); + u32 val = 0; + + (void)(arch_get_random_seed_int(&val) || + arch_get_random_int(&val)); + + return val; +} + +static void prandom_seed_early(struct rnd_state *state, u32 seed, + bool mix_with_hwseed) +{ +#define LCG(x) ((x) * 69069U) /* super-duper LCG */ +#define HWSEED() (mix_with_hwseed ? __extract_hwseed() : 0) + state->s1 = __seed(HWSEED() ^ LCG(seed), 2U); + state->s2 = __seed(HWSEED() ^ LCG(state->s1), 8U); + state->s3 = __seed(HWSEED() ^ LCG(state->s2), 16U); + state->s4 = __seed(HWSEED() ^ LCG(state->s3), 128U); } /** @@ -194,14 +201,13 @@ static int __init prandom_init(void) { int i; -#ifdef CONFIG_RANDOM32_SELFTEST prandom_state_selftest(); -#endif for_each_possible_cpu(i) { struct rnd_state *state = &per_cpu(net_rand_state,i); + u32 weak_seed = (i + jiffies) ^ random_get_entropy(); - prandom_seed_very_weak(state, (i + jiffies) ^ random_get_entropy()); + prandom_seed_early(state, weak_seed, true); prandom_warmup(state); } @@ -210,6 +216,7 @@ static int __init prandom_init(void) core_initcall(prandom_init); static void __prandom_timer(unsigned long dontcare); + static DEFINE_TIMER(seed_timer, __prandom_timer, 0, 0); static void __prandom_timer(unsigned long dontcare) @@ -419,7 +426,7 @@ static void __init prandom_state_selftest(void) for (i = 0; i < ARRAY_SIZE(test1); i++) { struct rnd_state state; - prandom_seed_very_weak(&state, test1[i].seed); + prandom_seed_early(&state, test1[i].seed, false); prandom_warmup(&state); if (test1[i].result != prandom_u32_state(&state)) @@ -434,7 +441,7 @@ static void __init prandom_state_selftest(void) for (i = 0; i < ARRAY_SIZE(test2); i++) { struct rnd_state state; - prandom_seed_very_weak(&state, test2[i].seed); + prandom_seed_early(&state, test2[i].seed, false); prandom_warmup(&state); for (j = 0; j < test2[i].iteration - 1; j++) diff --git a/lib/rhashtable.c b/lib/rhashtable.c new file mode 100644 index 0000000..e6940cf --- /dev/null +++ b/lib/rhashtable.c @@ -0,0 +1,797 @@ +/* + * Resizable, Scalable, Concurrent Hash Table + * + * Copyright (c) 2014 Thomas Graf <tgraf@suug.ch> + * Copyright (c) 2008-2014 Patrick McHardy <kaber@trash.net> + * + * Based on the following paper: + * https://www.usenix.org/legacy/event/atc11/tech/final_files/Triplett.pdf + * + * Code partially derived from nft_hash + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/log2.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/mm.h> +#include <linux/hash.h> +#include <linux/random.h> +#include <linux/rhashtable.h> +#include <linux/log2.h> + +#define HASH_DEFAULT_SIZE 64UL +#define HASH_MIN_SIZE 4UL + +#define ASSERT_RHT_MUTEX(HT) BUG_ON(!lockdep_rht_mutex_is_held(HT)) + +#ifdef CONFIG_PROVE_LOCKING +int lockdep_rht_mutex_is_held(const struct rhashtable *ht) +{ + return ht->p.mutex_is_held(); +} +EXPORT_SYMBOL_GPL(lockdep_rht_mutex_is_held); +#endif + +/** + * rht_obj - cast hash head to outer object + * @ht: hash table + * @he: hashed node + */ +void *rht_obj(const struct rhashtable *ht, const struct rhash_head *he) +{ + return (void *) he - ht->p.head_offset; +} +EXPORT_SYMBOL_GPL(rht_obj); + +static u32 __hashfn(const struct rhashtable *ht, const void *key, + u32 len, u32 hsize) +{ + u32 h; + + h = ht->p.hashfn(key, len, ht->p.hash_rnd); + + return h & (hsize - 1); +} + +/** + * rhashtable_hashfn - compute hash for key of given length + * @ht: hash table to compuate for + * @key: pointer to key + * @len: length of key + * + * Computes the hash value using the hash function provided in the 'hashfn' + * of struct rhashtable_params. The returned value is guaranteed to be + * smaller than the number of buckets in the hash table. + */ +u32 rhashtable_hashfn(const struct rhashtable *ht, const void *key, u32 len) +{ + struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + + return __hashfn(ht, key, len, tbl->size); +} +EXPORT_SYMBOL_GPL(rhashtable_hashfn); + +static u32 obj_hashfn(const struct rhashtable *ht, const void *ptr, u32 hsize) +{ + if (unlikely(!ht->p.key_len)) { + u32 h; + + h = ht->p.obj_hashfn(ptr, ht->p.hash_rnd); + + return h & (hsize - 1); + } + + return __hashfn(ht, ptr + ht->p.key_offset, ht->p.key_len, hsize); +} + +/** + * rhashtable_obj_hashfn - compute hash for hashed object + * @ht: hash table to compuate for + * @ptr: pointer to hashed object + * + * Computes the hash value using the hash function `hashfn` respectively + * 'obj_hashfn' depending on whether the hash table is set up to work with + * a fixed length key. The returned value is guaranteed to be smaller than + * the number of buckets in the hash table. + */ +u32 rhashtable_obj_hashfn(const struct rhashtable *ht, void *ptr) +{ + struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + + return obj_hashfn(ht, ptr, tbl->size); +} +EXPORT_SYMBOL_GPL(rhashtable_obj_hashfn); + +static u32 head_hashfn(const struct rhashtable *ht, + const struct rhash_head *he, u32 hsize) +{ + return obj_hashfn(ht, rht_obj(ht, he), hsize); +} + +static struct bucket_table *bucket_table_alloc(size_t nbuckets, gfp_t flags) +{ + struct bucket_table *tbl; + size_t size; + + size = sizeof(*tbl) + nbuckets * sizeof(tbl->buckets[0]); + tbl = kzalloc(size, flags); + if (tbl == NULL) + tbl = vzalloc(size); + + if (tbl == NULL) + return NULL; + + tbl->size = nbuckets; + + return tbl; +} + +static void bucket_table_free(const struct bucket_table *tbl) +{ + kvfree(tbl); +} + +/** + * rht_grow_above_75 - returns true if nelems > 0.75 * table-size + * @ht: hash table + * @new_size: new table size + */ +bool rht_grow_above_75(const struct rhashtable *ht, size_t new_size) +{ + /* Expand table when exceeding 75% load */ + return ht->nelems > (new_size / 4 * 3); +} +EXPORT_SYMBOL_GPL(rht_grow_above_75); + +/** + * rht_shrink_below_30 - returns true if nelems < 0.3 * table-size + * @ht: hash table + * @new_size: new table size + */ +bool rht_shrink_below_30(const struct rhashtable *ht, size_t new_size) +{ + /* Shrink table beneath 30% load */ + return ht->nelems < (new_size * 3 / 10); +} +EXPORT_SYMBOL_GPL(rht_shrink_below_30); + +static void hashtable_chain_unzip(const struct rhashtable *ht, + const struct bucket_table *new_tbl, + struct bucket_table *old_tbl, size_t n) +{ + struct rhash_head *he, *p, *next; + unsigned int h; + + /* Old bucket empty, no work needed. */ + p = rht_dereference(old_tbl->buckets[n], ht); + if (!p) + return; + + /* Advance the old bucket pointer one or more times until it + * reaches a node that doesn't hash to the same bucket as the + * previous node p. Call the previous node p; + */ + h = head_hashfn(ht, p, new_tbl->size); + rht_for_each(he, p->next, ht) { + if (head_hashfn(ht, he, new_tbl->size) != h) + break; + p = he; + } + RCU_INIT_POINTER(old_tbl->buckets[n], p->next); + + /* Find the subsequent node which does hash to the same + * bucket as node P, or NULL if no such node exists. + */ + next = NULL; + if (he) { + rht_for_each(he, he->next, ht) { + if (head_hashfn(ht, he, new_tbl->size) == h) { + next = he; + break; + } + } + } + + /* Set p's next pointer to that subsequent node pointer, + * bypassing the nodes which do not hash to p's bucket + */ + RCU_INIT_POINTER(p->next, next); +} + +/** + * rhashtable_expand - Expand hash table while allowing concurrent lookups + * @ht: the hash table to expand + * @flags: allocation flags + * + * A secondary bucket array is allocated and the hash entries are migrated + * while keeping them on both lists until the end of the RCU grace period. + * + * This function may only be called in a context where it is safe to call + * synchronize_rcu(), e.g. not within a rcu_read_lock() section. + * + * The caller must ensure that no concurrent table mutations take place. + * It is however valid to have concurrent lookups if they are RCU protected. + */ +int rhashtable_expand(struct rhashtable *ht, gfp_t flags) +{ + struct bucket_table *new_tbl, *old_tbl = rht_dereference(ht->tbl, ht); + struct rhash_head *he; + unsigned int i, h; + bool complete; + + ASSERT_RHT_MUTEX(ht); + + if (ht->p.max_shift && ht->shift >= ht->p.max_shift) + return 0; + + new_tbl = bucket_table_alloc(old_tbl->size * 2, flags); + if (new_tbl == NULL) + return -ENOMEM; + + ht->shift++; + + /* For each new bucket, search the corresponding old bucket + * for the first entry that hashes to the new bucket, and + * link the new bucket to that entry. Since all the entries + * which will end up in the new bucket appear in the same + * old bucket, this constructs an entirely valid new hash + * table, but with multiple buckets "zipped" together into a + * single imprecise chain. + */ + for (i = 0; i < new_tbl->size; i++) { + h = i & (old_tbl->size - 1); + rht_for_each(he, old_tbl->buckets[h], ht) { + if (head_hashfn(ht, he, new_tbl->size) == i) { + RCU_INIT_POINTER(new_tbl->buckets[i], he); + break; + } + } + } + + /* Publish the new table pointer. Lookups may now traverse + * the new table, but they will not benefit from any + * additional efficiency until later steps unzip the buckets. + */ + rcu_assign_pointer(ht->tbl, new_tbl); + + /* Unzip interleaved hash chains */ + do { + /* Wait for readers. All new readers will see the new + * table, and thus no references to the old table will + * remain. + */ + synchronize_rcu(); + + /* For each bucket in the old table (each of which + * contains items from multiple buckets of the new + * table): ... + */ + complete = true; + for (i = 0; i < old_tbl->size; i++) { + hashtable_chain_unzip(ht, new_tbl, old_tbl, i); + if (old_tbl->buckets[i] != NULL) + complete = false; + } + } while (!complete); + + bucket_table_free(old_tbl); + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_expand); + +/** + * rhashtable_shrink - Shrink hash table while allowing concurrent lookups + * @ht: the hash table to shrink + * @flags: allocation flags + * + * This function may only be called in a context where it is safe to call + * synchronize_rcu(), e.g. not within a rcu_read_lock() section. + * + * The caller must ensure that no concurrent table mutations take place. + * It is however valid to have concurrent lookups if they are RCU protected. + */ +int rhashtable_shrink(struct rhashtable *ht, gfp_t flags) +{ + struct bucket_table *ntbl, *tbl = rht_dereference(ht->tbl, ht); + struct rhash_head __rcu **pprev; + unsigned int i; + + ASSERT_RHT_MUTEX(ht); + + if (tbl->size <= HASH_MIN_SIZE) + return 0; + + ntbl = bucket_table_alloc(tbl->size / 2, flags); + if (ntbl == NULL) + return -ENOMEM; + + ht->shift--; + + /* Link each bucket in the new table to the first bucket + * in the old table that contains entries which will hash + * to the new bucket. + */ + for (i = 0; i < ntbl->size; i++) { + ntbl->buckets[i] = tbl->buckets[i]; + + /* Link each bucket in the new table to the first bucket + * in the old table that contains entries which will hash + * to the new bucket. + */ + for (pprev = &ntbl->buckets[i]; *pprev != NULL; + pprev = &rht_dereference(*pprev, ht)->next) + ; + RCU_INIT_POINTER(*pprev, tbl->buckets[i + ntbl->size]); + } + + /* Publish the new, valid hash table */ + rcu_assign_pointer(ht->tbl, ntbl); + + /* Wait for readers. No new readers will have references to the + * old hash table. + */ + synchronize_rcu(); + + bucket_table_free(tbl); + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_shrink); + +/** + * rhashtable_insert - insert object into hash hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @flags: allocation flags (table expansion) + * + * Will automatically grow the table via rhashtable_expand() if the the + * grow_decision function specified at rhashtable_init() returns true. + * + * The caller must ensure that no concurrent table mutations occur. It is + * however valid to have concurrent lookups if they are RCU protected. + */ +void rhashtable_insert(struct rhashtable *ht, struct rhash_head *obj, + gfp_t flags) +{ + struct bucket_table *tbl = rht_dereference(ht->tbl, ht); + u32 hash; + + ASSERT_RHT_MUTEX(ht); + + hash = head_hashfn(ht, obj, tbl->size); + RCU_INIT_POINTER(obj->next, tbl->buckets[hash]); + rcu_assign_pointer(tbl->buckets[hash], obj); + ht->nelems++; + + if (ht->p.grow_decision && ht->p.grow_decision(ht, tbl->size)) + rhashtable_expand(ht, flags); +} +EXPORT_SYMBOL_GPL(rhashtable_insert); + +/** + * rhashtable_remove_pprev - remove object from hash table given previous element + * @ht: hash table + * @obj: pointer to hash head inside object + * @pprev: pointer to previous element + * @flags: allocation flags (table expansion) + * + * Identical to rhashtable_remove() but caller is alreayd aware of the element + * in front of the element to be deleted. This is in particular useful for + * deletion when combined with walking or lookup. + */ +void rhashtable_remove_pprev(struct rhashtable *ht, struct rhash_head *obj, + struct rhash_head **pprev, gfp_t flags) +{ + struct bucket_table *tbl = rht_dereference(ht->tbl, ht); + + ASSERT_RHT_MUTEX(ht); + + RCU_INIT_POINTER(*pprev, obj->next); + ht->nelems--; + + if (ht->p.shrink_decision && + ht->p.shrink_decision(ht, tbl->size)) + rhashtable_shrink(ht, flags); +} +EXPORT_SYMBOL_GPL(rhashtable_remove_pprev); + +/** + * rhashtable_remove - remove object from hash table + * @ht: hash table + * @obj: pointer to hash head inside object + * @flags: allocation flags (table expansion) + * + * Since the hash chain is single linked, the removal operation needs to + * walk the bucket chain upon removal. The removal operation is thus + * considerable slow if the hash table is not correctly sized. + * + * Will automatically shrink the table via rhashtable_expand() if the the + * shrink_decision function specified at rhashtable_init() returns true. + * + * The caller must ensure that no concurrent table mutations occur. It is + * however valid to have concurrent lookups if they are RCU protected. + */ +bool rhashtable_remove(struct rhashtable *ht, struct rhash_head *obj, + gfp_t flags) +{ + struct bucket_table *tbl = rht_dereference(ht->tbl, ht); + struct rhash_head __rcu **pprev; + struct rhash_head *he; + u32 h; + + ASSERT_RHT_MUTEX(ht); + + h = head_hashfn(ht, obj, tbl->size); + + pprev = &tbl->buckets[h]; + rht_for_each(he, tbl->buckets[h], ht) { + if (he != obj) { + pprev = &he->next; + continue; + } + + rhashtable_remove_pprev(ht, he, pprev, flags); + return true; + } + + return false; +} +EXPORT_SYMBOL_GPL(rhashtable_remove); + +/** + * rhashtable_lookup - lookup key in hash table + * @ht: hash table + * @key: pointer to key + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * This lookup function may only be used for fixed key hash table (key_len + * paramter set). It will BUG() if used inappropriately. + * + * Lookups may occur in parallel with hash mutations as long as the lookup is + * guarded by rcu_read_lock(). The caller must take care of this. + */ +void *rhashtable_lookup(const struct rhashtable *ht, const void *key) +{ + const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + struct rhash_head *he; + u32 h; + + BUG_ON(!ht->p.key_len); + + h = __hashfn(ht, key, ht->p.key_len, tbl->size); + rht_for_each_rcu(he, tbl->buckets[h], ht) { + if (memcmp(rht_obj(ht, he) + ht->p.key_offset, key, + ht->p.key_len)) + continue; + return (void *) he - ht->p.head_offset; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(rhashtable_lookup); + +/** + * rhashtable_lookup_compare - search hash table with compare function + * @ht: hash table + * @hash: hash value of desired entry + * @compare: compare function, must return true on match + * @arg: argument passed on to compare function + * + * Traverses the bucket chain behind the provided hash value and calls the + * specified compare function for each entry. + * + * Lookups may occur in parallel with hash mutations as long as the lookup is + * guarded by rcu_read_lock(). The caller must take care of this. + * + * Returns the first entry on which the compare function returned true. + */ +void *rhashtable_lookup_compare(const struct rhashtable *ht, u32 hash, + bool (*compare)(void *, void *), void *arg) +{ + const struct bucket_table *tbl = rht_dereference_rcu(ht->tbl, ht); + struct rhash_head *he; + + if (unlikely(hash >= tbl->size)) + return NULL; + + rht_for_each_rcu(he, tbl->buckets[hash], ht) { + if (!compare(rht_obj(ht, he), arg)) + continue; + return (void *) he - ht->p.head_offset; + } + + return NULL; +} +EXPORT_SYMBOL_GPL(rhashtable_lookup_compare); + +static size_t rounded_hashtable_size(unsigned int nelem) +{ + return max(roundup_pow_of_two(nelem * 4 / 3), HASH_MIN_SIZE); +} + +/** + * rhashtable_init - initialize a new hash table + * @ht: hash table to be initialized + * @params: configuration parameters + * + * Initializes a new hash table based on the provided configuration + * parameters. A table can be configured either with a variable or + * fixed length key: + * + * Configuration Example 1: Fixed length keys + * struct test_obj { + * int key; + * void * my_member; + * struct rhash_head node; + * }; + * + * struct rhashtable_params params = { + * .head_offset = offsetof(struct test_obj, node), + * .key_offset = offsetof(struct test_obj, key), + * .key_len = sizeof(int), + * .hashfn = arch_fast_hash, + * .mutex_is_held = &my_mutex_is_held, + * }; + * + * Configuration Example 2: Variable length keys + * struct test_obj { + * [...] + * struct rhash_head node; + * }; + * + * u32 my_hash_fn(const void *data, u32 seed) + * { + * struct test_obj *obj = data; + * + * return [... hash ...]; + * } + * + * struct rhashtable_params params = { + * .head_offset = offsetof(struct test_obj, node), + * .hashfn = arch_fast_hash, + * .obj_hashfn = my_hash_fn, + * .mutex_is_held = &my_mutex_is_held, + * }; + */ +int rhashtable_init(struct rhashtable *ht, struct rhashtable_params *params) +{ + struct bucket_table *tbl; + size_t size; + + size = HASH_DEFAULT_SIZE; + + if ((params->key_len && !params->hashfn) || + (!params->key_len && !params->obj_hashfn)) + return -EINVAL; + + if (params->nelem_hint) + size = rounded_hashtable_size(params->nelem_hint); + + tbl = bucket_table_alloc(size, GFP_KERNEL); + if (tbl == NULL) + return -ENOMEM; + + memset(ht, 0, sizeof(*ht)); + ht->shift = ilog2(tbl->size); + memcpy(&ht->p, params, sizeof(*params)); + RCU_INIT_POINTER(ht->tbl, tbl); + + if (!ht->p.hash_rnd) + get_random_bytes(&ht->p.hash_rnd, sizeof(ht->p.hash_rnd)); + + return 0; +} +EXPORT_SYMBOL_GPL(rhashtable_init); + +/** + * rhashtable_destroy - destroy hash table + * @ht: the hash table to destroy + * + * Frees the bucket array. + */ +void rhashtable_destroy(const struct rhashtable *ht) +{ + const struct bucket_table *tbl = rht_dereference(ht->tbl, ht); + + bucket_table_free(tbl); +} +EXPORT_SYMBOL_GPL(rhashtable_destroy); + +/************************************************************************** + * Self Test + **************************************************************************/ + +#ifdef CONFIG_TEST_RHASHTABLE + +#define TEST_HT_SIZE 8 +#define TEST_ENTRIES 2048 +#define TEST_PTR ((void *) 0xdeadbeef) +#define TEST_NEXPANDS 4 + +static int test_mutex_is_held(void) +{ + return 1; +} + +struct test_obj { + void *ptr; + int value; + struct rhash_head node; +}; + +static int __init test_rht_lookup(struct rhashtable *ht) +{ + unsigned int i; + + for (i = 0; i < TEST_ENTRIES * 2; i++) { + struct test_obj *obj; + bool expected = !(i % 2); + u32 key = i; + + obj = rhashtable_lookup(ht, &key); + + if (expected && !obj) { + pr_warn("Test failed: Could not find key %u\n", key); + return -ENOENT; + } else if (!expected && obj) { + pr_warn("Test failed: Unexpected entry found for key %u\n", + key); + return -EEXIST; + } else if (expected && obj) { + if (obj->ptr != TEST_PTR || obj->value != i) { + pr_warn("Test failed: Lookup value mismatch %p!=%p, %u!=%u\n", + obj->ptr, TEST_PTR, obj->value, i); + return -EINVAL; + } + } + } + + return 0; +} + +static void test_bucket_stats(struct rhashtable *ht, + struct bucket_table *tbl, + bool quiet) +{ + unsigned int cnt, i, total = 0; + struct test_obj *obj; + + for (i = 0; i < tbl->size; i++) { + cnt = 0; + + if (!quiet) + pr_info(" [%#4x/%zu]", i, tbl->size); + + rht_for_each_entry_rcu(obj, tbl->buckets[i], node) { + cnt++; + total++; + if (!quiet) + pr_cont(" [%p],", obj); + } + + if (!quiet) + pr_cont("\n [%#x] first element: %p, chain length: %u\n", + i, tbl->buckets[i], cnt); + } + + pr_info(" Traversal complete: counted=%u, nelems=%zu, entries=%d\n", + total, ht->nelems, TEST_ENTRIES); +} + +static int __init test_rhashtable(struct rhashtable *ht) +{ + struct bucket_table *tbl; + struct test_obj *obj, *next; + int err; + unsigned int i; + + /* + * Insertion Test: + * Insert TEST_ENTRIES into table with all keys even numbers + */ + pr_info(" Adding %d keys\n", TEST_ENTRIES); + for (i = 0; i < TEST_ENTRIES; i++) { + struct test_obj *obj; + + obj = kzalloc(sizeof(*obj), GFP_KERNEL); + if (!obj) { + err = -ENOMEM; + goto error; + } + + obj->ptr = TEST_PTR; + obj->value = i * 2; + + rhashtable_insert(ht, &obj->node, GFP_KERNEL); + } + + rcu_read_lock(); + tbl = rht_dereference_rcu(ht->tbl, ht); + test_bucket_stats(ht, tbl, true); + test_rht_lookup(ht); + rcu_read_unlock(); + + for (i = 0; i < TEST_NEXPANDS; i++) { + pr_info(" Table expansion iteration %u...\n", i); + rhashtable_expand(ht, GFP_KERNEL); + + rcu_read_lock(); + pr_info(" Verifying lookups...\n"); + test_rht_lookup(ht); + rcu_read_unlock(); + } + + for (i = 0; i < TEST_NEXPANDS; i++) { + pr_info(" Table shrinkage iteration %u...\n", i); + rhashtable_shrink(ht, GFP_KERNEL); + + rcu_read_lock(); + pr_info(" Verifying lookups...\n"); + test_rht_lookup(ht); + rcu_read_unlock(); + } + + pr_info(" Deleting %d keys\n", TEST_ENTRIES); + for (i = 0; i < TEST_ENTRIES; i++) { + u32 key = i * 2; + + obj = rhashtable_lookup(ht, &key); + BUG_ON(!obj); + + rhashtable_remove(ht, &obj->node, GFP_KERNEL); + kfree(obj); + } + + return 0; + +error: + tbl = rht_dereference_rcu(ht->tbl, ht); + for (i = 0; i < tbl->size; i++) + rht_for_each_entry_safe(obj, next, tbl->buckets[i], ht, node) + kfree(obj); + + return err; +} + +static int __init test_rht_init(void) +{ + struct rhashtable ht; + struct rhashtable_params params = { + .nelem_hint = TEST_HT_SIZE, + .head_offset = offsetof(struct test_obj, node), + .key_offset = offsetof(struct test_obj, value), + .key_len = sizeof(int), + .hashfn = arch_fast_hash, + .mutex_is_held = &test_mutex_is_held, + .grow_decision = rht_grow_above_75, + .shrink_decision = rht_shrink_below_30, + }; + int err; + + pr_info("Running resizable hashtable tests...\n"); + + err = rhashtable_init(&ht, ¶ms); + if (err < 0) { + pr_warn("Test failed: Unable to initialize hashtable: %d\n", + err); + return err; + } + + err = test_rhashtable(&ht); + + rhashtable_destroy(&ht); + + return err; +} + +subsys_initcall(test_rht_init); + +#endif /* CONFIG_TEST_RHASHTABLE */ diff --git a/lib/test_bpf.c b/lib/test_bpf.c index c579e0f..89e0345 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -66,7 +66,7 @@ struct bpf_test { const char *descr; union { struct sock_filter insns[MAX_INSNS]; - struct sock_filter_int insns_int[MAX_INSNS]; + struct bpf_insn insns_int[MAX_INSNS]; } u; __u8 aux; __u8 data[MAX_DATA]; @@ -1761,9 +1761,9 @@ static int probe_filter_length(struct sock_filter *fp) return len + 1; } -static struct sk_filter *generate_filter(int which, int *err) +static struct bpf_prog *generate_filter(int which, int *err) { - struct sk_filter *fp; + struct bpf_prog *fp; struct sock_fprog_kern fprog; unsigned int flen = probe_filter_length(tests[which].u.insns); __u8 test_type = tests[which].aux & TEST_TYPE_MASK; @@ -1773,7 +1773,7 @@ static struct sk_filter *generate_filter(int which, int *err) fprog.filter = tests[which].u.insns; fprog.len = flen; - *err = sk_unattached_filter_create(&fp, &fprog); + *err = bpf_prog_create(&fp, &fprog); if (tests[which].aux & FLAG_EXPECTED_FAIL) { if (*err == -EINVAL) { pr_cont("PASS\n"); @@ -1798,7 +1798,7 @@ static struct sk_filter *generate_filter(int which, int *err) break; case INTERNAL: - fp = kzalloc(sk_filter_size(flen), GFP_KERNEL); + fp = kzalloc(bpf_prog_size(flen), GFP_KERNEL); if (fp == NULL) { pr_cont("UNEXPECTED_FAIL no memory left\n"); *err = -ENOMEM; @@ -1807,9 +1807,9 @@ static struct sk_filter *generate_filter(int which, int *err) fp->len = flen; memcpy(fp->insnsi, tests[which].u.insns_int, - fp->len * sizeof(struct sock_filter_int)); + fp->len * sizeof(struct bpf_insn)); - sk_filter_select_runtime(fp); + bpf_prog_select_runtime(fp); break; } @@ -1817,21 +1817,21 @@ static struct sk_filter *generate_filter(int which, int *err) return fp; } -static void release_filter(struct sk_filter *fp, int which) +static void release_filter(struct bpf_prog *fp, int which) { __u8 test_type = tests[which].aux & TEST_TYPE_MASK; switch (test_type) { case CLASSIC: - sk_unattached_filter_destroy(fp); + bpf_prog_destroy(fp); break; case INTERNAL: - sk_filter_free(fp); + bpf_prog_free(fp); break; } } -static int __run_one(const struct sk_filter *fp, const void *data, +static int __run_one(const struct bpf_prog *fp, const void *data, int runs, u64 *duration) { u64 start, finish; @@ -1840,7 +1840,7 @@ static int __run_one(const struct sk_filter *fp, const void *data, start = ktime_to_us(ktime_get()); for (i = 0; i < runs; i++) - ret = SK_RUN_FILTER(fp, data); + ret = BPF_PROG_RUN(fp, data); finish = ktime_to_us(ktime_get()); @@ -1850,7 +1850,7 @@ static int __run_one(const struct sk_filter *fp, const void *data, return ret; } -static int run_one(const struct sk_filter *fp, struct bpf_test *test) +static int run_one(const struct bpf_prog *fp, struct bpf_test *test) { int err_cnt = 0, i, runs = MAX_TESTRUNS; @@ -1884,7 +1884,7 @@ static __init int test_bpf(void) int i, err_cnt = 0, pass_cnt = 0; for (i = 0; i < ARRAY_SIZE(tests); i++) { - struct sk_filter *fp; + struct bpf_prog *fp; int err; pr_info("#%d %s ", i, tests[i].descr); |