aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/bpf/hashtab.c
diff options
context:
space:
mode:
authorSong Liu <song@kernel.org>2023-10-11 22:57:41 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2023-10-24 14:25:55 +0200
commitd35381aa73f7e1e8b25f3ed5283287a64d9ddff5 (patch)
tree2e3c4cd03ad2acc9f2c5b5b47b2383c69d9ec037 /kernel/bpf/hashtab.c
parentxsk: Avoid starving the xsk further down the list (diff)
downloadlinux-d35381aa73f7e1e8b25f3ed5283287a64d9ddff5.tar.xz
linux-d35381aa73f7e1e8b25f3ed5283287a64d9ddff5.zip
bpf: Fix unnecessary -EBUSY from htab_lock_bucket
htab_lock_bucket uses the following logic to avoid recursion: 1. preempt_disable(); 2. check percpu counter htab->map_locked[hash] for recursion; 2.1. if map_lock[hash] is already taken, return -BUSY; 3. raw_spin_lock_irqsave(); However, if an IRQ hits between 2 and 3, BPF programs attached to the IRQ logic will not able to access the same hash of the hashtab and get -EBUSY. This -EBUSY is not really necessary. Fix it by disabling IRQ before checking map_locked: 1. preempt_disable(); 2. local_irq_save(); 3. check percpu counter htab->map_locked[hash] for recursion; 3.1. if map_lock[hash] is already taken, return -BUSY; 4. raw_spin_lock(). Similarly, use raw_spin_unlock() and local_irq_restore() in htab_unlock_bucket(). Fixes: 20b6cc34ea74 ("bpf: Avoid hashtab deadlock with map_locked") Suggested-by: Tejun Heo <tj@kernel.org> Signed-off-by: Song Liu <song@kernel.org> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/7a9576222aa40b1c84ad3a9ba3e64011d1a04d41.camel@linux.ibm.com Link: https://lore.kernel.org/bpf/20231012055741.3375999-1-song@kernel.org
Diffstat (limited to 'kernel/bpf/hashtab.c')
-rw-r--r--kernel/bpf/hashtab.c7
1 files changed, 5 insertions, 2 deletions
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index a8c7e1c5abfa..fd8d4b0addfc 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -155,13 +155,15 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab,
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
preempt_disable();
+ local_irq_save(flags);
if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) {
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
return -EBUSY;
}
- raw_spin_lock_irqsave(&b->raw_lock, flags);
+ raw_spin_lock(&b->raw_lock);
*pflags = flags;
return 0;
@@ -172,8 +174,9 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab,
unsigned long flags)
{
hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1);
- raw_spin_unlock_irqrestore(&b->raw_lock, flags);
+ raw_spin_unlock(&b->raw_lock);
__this_cpu_dec(*(htab->map_locked[hash]));
+ local_irq_restore(flags);
preempt_enable();
}