diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 15:04:25 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-15 15:04:25 -0700 |
commit | 9a76aba02a37718242d7cdc294f0a3901928aa57 (patch) | |
tree | 2040d038f85d2120f21af83b0793efd5af1864e3 /lib/rhashtable.c | |
parent | 0a957467c5fd46142bc9c52758ffc552d4c5e2f7 (diff) | |
parent | 26a1ccc6c117be8e33e0410fce8c5298b0015b99 (diff) | |
download | linux-9a76aba02a37718242d7cdc294f0a3901928aa57.tar.bz2 |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Highlights:
- Gustavo A. R. Silva keeps working on the implicit switch fallthru
changes.
- Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
Luca Coelho.
- Re-enable ASPM in r8169, from Kai-Heng Feng.
- Add virtual XFRM interfaces, which avoids all of the limitations of
existing IPSEC tunnels. From Steffen Klassert.
- Convert GRO over to use a hash table, so that when we have many
flows active we don't traverse a long list during accumluation.
- Many new self tests for routing, TC, tunnels, etc. Too many
contributors to mention them all, but I'm really happy to keep
seeing this stuff.
- Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.
- Lots of cleanups and fixes in L2TP code from Guillaume Nault.
- Add IPSEC offload support to netdevsim, from Shannon Nelson.
- Add support for slotting with non-uniform distribution to netem
packet scheduler, from Yousuk Seung.
- Add UDP GSO support to mlx5e, from Boris Pismenny.
- Support offloading of Team LAG in NFP, from John Hurley.
- Allow to configure TX queue selection based upon RX queue, from
Amritha Nambiar.
- Support ethtool ring size configuration in aquantia, from Anton
Mikaev.
- Support DSCP and flowlabel per-transport in SCTP, from Xin Long.
- Support list based batching and stack traversal of SKBs, this is
very exciting work. From Edward Cree.
- Busyloop optimizations in vhost_net, from Toshiaki Makita.
- Introduce the ETF qdisc, which allows time based transmissions. IGB
can offload this in hardware. From Vinicius Costa Gomes.
- Add parameter support to devlink, from Moshe Shemesh.
- Several multiplication and division optimizations for BPF JIT in
nfp driver, from Jiong Wang.
- Lots of prepatory work to make more of the packet scheduler layer
lockless, when possible, from Vlad Buslov.
- Add ACK filter and NAT awareness to sch_cake packet scheduler, from
Toke Høiland-Jørgensen.
- Support regions and region snapshots in devlink, from Alex Vesker.
- Allow to attach XDP programs to both HW and SW at the same time on
a given device, with initial support in nfp. From Jakub Kicinski.
- Add TLS RX offload and support in mlx5, from Ilya Lesokhin.
- Use PHYLIB in r8169 driver, from Heiner Kallweit.
- All sorts of changes to support Spectrum 2 in mlxsw driver, from
Ido Schimmel.
- PTP support in mv88e6xxx DSA driver, from Andrew Lunn.
- Make TCP_USER_TIMEOUT socket option more accurate, from Jon
Maxwell.
- Support for templates in packet scheduler classifier, from Jiri
Pirko.
- IPV6 support in RDS, from Ka-Cheong Poon.
- Native tproxy support in nf_tables, from Máté Eckl.
- Maintain IP fragment queue in an rbtree, but optimize properly for
in-order frags. From Peter Oskolkov.
- Improvde handling of ACKs on hole repairs, from Yuchung Cheng"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
hv/netvsc: Fix NULL dereference at single queue mode fallback
net: filter: mark expected switch fall-through
xen-netfront: fix warn message as irq device name has '/'
cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
net: dsa: mv88e6xxx: missing unlock on error path
rds: fix building with IPV6=m
inet/connection_sock: prefer _THIS_IP_ to current_text_addr
net: dsa: mv88e6xxx: bitwise vs logical bug
net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
ieee802154: hwsim: using right kind of iteration
net: hns3: Add vlan filter setting by ethtool command -K
net: hns3: Set tx ring' tc info when netdev is up
net: hns3: Remove tx ring BD len register in hns3_enet
net: hns3: Fix desc num set to default when setting channel
net: hns3: Fix for phy link issue when using marvell phy driver
net: hns3: Fix for information of phydev lost problem when down/up
net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
net: hns3: Add support for serdes loopback selftest
bnxt_en: take coredump_record structure off stack
...
Diffstat (limited to 'lib/rhashtable.c')
-rw-r--r-- | lib/rhashtable.c | 58 |
1 files changed, 17 insertions, 41 deletions
diff --git a/lib/rhashtable.c b/lib/rhashtable.c index e5c8586cf717..ae4223e0f5bc 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -28,6 +28,7 @@ #include <linux/rhashtable.h> #include <linux/err.h> #include <linux/export.h> +#include <linux/rhashtable.h> #define HASH_DEFAULT_SIZE 64UL #define HASH_MIN_SIZE 4U @@ -115,8 +116,7 @@ static void bucket_table_free_rcu(struct rcu_head *head) static union nested_table *nested_table_alloc(struct rhashtable *ht, union nested_table __rcu **prev, - unsigned int shifted, - unsigned int nhash) + bool leaf) { union nested_table *ntbl; int i; @@ -127,10 +127,9 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht, ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC); - if (ntbl && shifted) { - for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++) - INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht, - (i << shifted) | nhash); + if (ntbl && leaf) { + for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++) + INIT_RHT_NULLS_HEAD(ntbl[i].bucket); } rcu_assign_pointer(*prev, ntbl); @@ -156,7 +155,7 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht, return NULL; if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets, - 0, 0)) { + false)) { kfree(tbl); return NULL; } @@ -206,7 +205,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht, tbl->hash_rnd = get_random_u32(); for (i = 0; i < nbuckets; i++) - INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i); + INIT_RHT_NULLS_HEAD(tbl->buckets[i]); return tbl; } @@ -227,8 +226,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht, static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash) { struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht); - struct bucket_table *new_tbl = rhashtable_last_table(ht, - rht_dereference_rcu(old_tbl->future_tbl, ht)); + struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl); struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash); int err = -EAGAIN; struct rhash_head *head, *next, *entry; @@ -298,21 +296,14 @@ static int rhashtable_rehash_attach(struct rhashtable *ht, struct bucket_table *old_tbl, struct bucket_table *new_tbl) { - /* Protect future_tbl using the first bucket lock. */ - spin_lock_bh(old_tbl->locks); - - /* Did somebody beat us to it? */ - if (rcu_access_pointer(old_tbl->future_tbl)) { - spin_unlock_bh(old_tbl->locks); - return -EEXIST; - } - /* Make insertions go into the new, empty table right away. Deletions * and lookups will be attempted in both tables until we synchronize. + * As cmpxchg() provides strong barriers, we do not need + * rcu_assign_pointer(). */ - rcu_assign_pointer(old_tbl->future_tbl, new_tbl); - spin_unlock_bh(old_tbl->locks); + if (cmpxchg(&old_tbl->future_tbl, NULL, new_tbl) != NULL) + return -EEXIST; return 0; } @@ -475,7 +466,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht, fail: /* Do not fail the insert if someone else did a rehash. */ - if (likely(rcu_dereference_raw(tbl->future_tbl))) + if (likely(rcu_access_pointer(tbl->future_tbl))) return 0; /* Schedule async rehash to retry allocation in process context. */ @@ -548,7 +539,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht, if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT) return ERR_CAST(data); - new_tbl = rcu_dereference(tbl->future_tbl); + new_tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (new_tbl) return new_tbl; @@ -607,7 +598,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key, break; spin_unlock_bh(lock); - tbl = rcu_dereference(tbl->future_tbl); + tbl = rht_dereference_rcu(tbl->future_tbl, ht); } data = rhashtable_lookup_one(ht, tbl, hash, key, obj); @@ -1002,7 +993,6 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed) * .key_offset = offsetof(struct test_obj, key), * .key_len = sizeof(int), * .hashfn = jhash, - * .nulls_base = (1U << RHT_BASE_SHIFT), * }; * * Configuration Example 2: Variable length keys @@ -1034,9 +1024,6 @@ int rhashtable_init(struct rhashtable *ht, (params->obj_hashfn && !params->obj_cmpfn)) return -EINVAL; - if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT)) - return -EINVAL; - memset(ht, 0, sizeof(*ht)); mutex_init(&ht->mutex); spin_lock_init(&ht->lock); @@ -1100,10 +1087,6 @@ int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params) { int err; - /* No rhlist NULLs marking for now. */ - if (params->nulls_base) - return -EINVAL; - err = rhashtable_init(&hlt->ht, params); hlt->ht.rhlist = true; return err; @@ -1227,25 +1210,18 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht, unsigned int index = hash & ((1 << tbl->nest) - 1); unsigned int size = tbl->size >> tbl->nest; union nested_table *ntbl; - unsigned int shifted; - unsigned int nhash; ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]); hash >>= tbl->nest; - nhash = index; - shifted = tbl->nest; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, nhash); + size <= (1 << shift)); while (ntbl && size > (1 << shift)) { index = hash & ((1 << shift) - 1); size >>= shift; hash >>= shift; - nhash |= index << shifted; - shifted += shift; ntbl = nested_table_alloc(ht, &ntbl[index].table, - size <= (1 << shift) ? shifted : 0, - nhash); + size <= (1 << shift)); } if (!ntbl) |