diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-11 05:07:44 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-08-11 05:07:44 +0300 |
commit | 97d052ea3fa853b9aabcc4baca1a605cb1188611 (patch) | |
tree | 48901cbccafdc5870c7dad9cce98e9338065f8a3 /net | |
parent | 086ba2ec163b638abd2a90ef3e8bab0238d02e56 (diff) | |
parent | 0cd39f4600ed4de859383018eb10f0f724900e1b (diff) | |
download | linux-97d052ea3fa853b9aabcc4baca1a605cb1188611.tar.xz |
Merge tag 'locking-urgent-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Thomas Gleixner:
"A set of locking fixes and updates:
- Untangle the header spaghetti which causes build failures in
various situations caused by the lockdep additions to seqcount to
validate that the write side critical sections are non-preemptible.
- The seqcount associated lock debug addons which were blocked by the
above fallout.
seqcount writers contrary to seqlock writers must be externally
serialized, which usually happens via locking - except for strict
per CPU seqcounts. As the lock is not part of the seqcount, lockdep
cannot validate that the lock is held.
This new debug mechanism adds the concept of associated locks.
sequence count has now lock type variants and corresponding
initializers which take a pointer to the associated lock used for
writer serialization. If lockdep is enabled the pointer is stored
and write_seqcount_begin() has a lockdep assertion to validate that
the lock is held.
Aside of the type and the initializer no other code changes are
required at the seqcount usage sites. The rest of the seqcount API
is unchanged and determines the type at compile time with the help
of _Generic which is possible now that the minimal GCC version has
been moved up.
Adding this lockdep coverage unearthed a handful of seqcount bugs
which have been addressed already independent of this.
While generally useful this comes with a Trojan Horse twist: On RT
kernels the write side critical section can become preemtible if
the writers are serialized by an associated lock, which leads to
the well known reader preempts writer livelock. RT prevents this by
storing the associated lock pointer independent of lockdep in the
seqcount and changing the reader side to block on the lock when a
reader detects that a writer is in the write side critical section.
- Conversion of seqcount usage sites to associated types and
initializers"
* tag 'locking-urgent-2020-08-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
locking/seqlock, headers: Untangle the spaghetti monster
locking, arch/ia64: Reduce <asm/smp.h> header dependencies by moving XTP bits into the new <asm/xtp.h> header
x86/headers: Remove APIC headers from <asm/smp.h>
seqcount: More consistent seqprop names
seqcount: Compress SEQCNT_LOCKNAME_ZERO()
seqlock: Fold seqcount_LOCKNAME_init() definition
seqlock: Fold seqcount_LOCKNAME_t definition
seqlock: s/__SEQ_LOCKDEP/__SEQ_LOCK/g
hrtimer: Use sequence counter with associated raw spinlock
kvm/eventfd: Use sequence counter with associated spinlock
userfaultfd: Use sequence counter with associated spinlock
NFSv4: Use sequence counter with associated spinlock
iocost: Use sequence counter with associated spinlock
raid5: Use sequence counter with associated spinlock
vfs: Use sequence counter with associated spinlock
timekeeping: Use sequence counter with associated raw spinlock
xfrm: policy: Use sequence counters with associated lock
netfilter: nft_set_rbtree: Use sequence counter with associated rwlock
netfilter: conntrack: Use sequence counter with associated spinlock
sched: tasks: Use sequence counter with associated spinlock
...
Diffstat (limited to 'net')
-rw-r--r-- | net/netfilter/nf_conntrack_core.c | 5 | ||||
-rw-r--r-- | net/netfilter/nft_set_rbtree.c | 4 | ||||
-rw-r--r-- | net/xfrm/xfrm_policy.c | 10 |
3 files changed, 10 insertions, 9 deletions
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e38b60fc183e..5b97d233f89b 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -180,7 +180,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_max); -seqcount_t nf_conntrack_generation __read_mostly; +seqcount_spinlock_t nf_conntrack_generation __read_mostly; static unsigned int nf_conntrack_hash_rnd __read_mostly; static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple, @@ -2588,7 +2588,8 @@ int nf_conntrack_init_start(void) /* struct nf_ct_ext uses u8 to store offsets/size */ BUILD_BUG_ON(total_extension_size() > 255u); - seqcount_init(&nf_conntrack_generation); + seqcount_spinlock_init(&nf_conntrack_generation, + &nf_conntrack_locks_all_lock); for (i = 0; i < CONNTRACK_LOCKS; i++) spin_lock_init(&nf_conntrack_locks[i]); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index b6aad3fc46c3..4b2834fd17b2 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -18,7 +18,7 @@ struct nft_rbtree { struct rb_root root; rwlock_t lock; - seqcount_t count; + seqcount_rwlock_t count; struct delayed_work gc_work; }; @@ -523,7 +523,7 @@ static int nft_rbtree_init(const struct nft_set *set, struct nft_rbtree *priv = nft_set_priv(set); rwlock_init(&priv->lock); - seqcount_init(&priv->count); + seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 042ea9b40c7b..d5280fd6f9c1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -122,7 +122,7 @@ struct xfrm_pol_inexact_bin { /* list containing '*:*' policies */ struct hlist_head hhead; - seqcount_t count; + seqcount_spinlock_t count; /* tree sorted by daddr/prefix */ struct rb_root root_d; @@ -155,7 +155,7 @@ static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; -static __read_mostly seqcount_t xfrm_policy_hash_generation; +static __read_mostly seqcount_mutex_t xfrm_policy_hash_generation; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; @@ -719,7 +719,7 @@ xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir) INIT_HLIST_HEAD(&bin->hhead); bin->root_d = RB_ROOT; bin->root_s = RB_ROOT; - seqcount_init(&bin->count); + seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock); prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table, &bin->k, &bin->head, @@ -1899,7 +1899,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol, static struct xfrm_pol_inexact_node * xfrm_policy_lookup_inexact_addr(const struct rb_root *r, - seqcount_t *count, + seqcount_spinlock_t *count, const xfrm_address_t *addr, u16 family) { const struct rb_node *parent; @@ -4157,7 +4157,7 @@ void __init xfrm_init(void) { register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); - seqcount_init(&xfrm_policy_hash_generation); + seqcount_mutex_init(&xfrm_policy_hash_generation, &hash_resize_mutex); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP |