summaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
authorMichel Lespinasse <walken@google.com>2020-06-09 06:33:37 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2020-06-09 18:39:14 +0200
commit0cc55a0213a02b760ade1d4755fdccfbf7d3157e (patch)
tree4424662fc8a6ba6e4c2293fa60cbab1132269d8f /kernel/bpf
parentmmap locking API: convert nested write lock sites (diff)
downloadlinux-0cc55a0213a02b760ade1d4755fdccfbf7d3157e.tar.xz
linux-0cc55a0213a02b760ade1d4755fdccfbf7d3157e.zip
mmap locking API: add mmap_read_trylock_non_owner()
Add a couple APIs used by kernel/bpf/stackmap.c only: - mmap_read_trylock_non_owner() - mmap_read_unlock_non_owner() (may be called from a work queue). It's still not ideal that bpf/stackmap subverts the lock ownership in this way. Thanks to Peter Zijlstra for suggesting this API as the least-ugly way of addressing this in the short term. Signed-off-by: Michel Lespinasse <walken@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Daniel Jordan <daniel.m.jordan@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Davidlohr Bueso <dbueso@suse.de> Cc: David Rientjes <rientjes@google.com> Cc: Hugh Dickins <hughd@google.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jerome Glisse <jglisse@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam Howlett <Liam.Howlett@oracle.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ying Han <yinghan@google.com> Link: http://lkml.kernel.org/r/20200520052908.204642-8-walken@google.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/stackmap.c17
1 files changed, 5 insertions, 12 deletions
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index a13b7e28eaf8..599488f25e40 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -33,7 +33,7 @@ struct bpf_stack_map {
/* irq_work to run up_read() for build_id lookup in nmi context */
struct stack_map_irq_work {
struct irq_work irq_work;
- struct rw_semaphore *sem;
+ struct mm_struct *mm;
};
static void do_up_read(struct irq_work *entry)
@@ -44,8 +44,7 @@ static void do_up_read(struct irq_work *entry)
return;
work = container_of(entry, struct stack_map_irq_work, irq_work);
- up_read_non_owner(work->sem);
- work->sem = NULL;
+ mmap_read_unlock_non_owner(work->mm);
}
static DEFINE_PER_CPU(struct stack_map_irq_work, up_read_work);
@@ -317,7 +316,7 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
* with build_id.
*/
if (!user || !current || !current->mm || irq_work_busy ||
- mmap_read_trylock(current->mm) == 0) {
+ !mmap_read_trylock_non_owner(current->mm)) {
/* cannot access current->mm, fall back to ips */
for (i = 0; i < trace_nr; i++) {
id_offs[i].status = BPF_STACK_BUILD_ID_IP;
@@ -342,16 +341,10 @@ static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs,
}
if (!work) {
- mmap_read_unlock(current->mm);
+ mmap_read_unlock_non_owner(current->mm);
} else {
- work->sem = &current->mm->mmap_sem;
+ work->mm = current->mm;
irq_work_queue(&work->irq_work);
- /*
- * The irq_work will release the mmap_sem with
- * up_read_non_owner(). The rwsem_release() is called
- * here to release the lock from lockdep's perspective.
- */
- rwsem_release(&current->mm->mmap_sem.dep_map, _RET_IP_);
}
}