On 4/24/24 11:52 PM, Andrii Nakryiko wrote: > objpool_push() and objpool_pop() are very performance-critical functions > and can be called very frequently in kretprobe triggering path. > > As such, it makes sense to allow compiler to inline them completely to > eliminate function calls overhead. Luckily, their logic is quite well > isolated and doesn't have any sprawling dependencies. > > This patch moves both objpool_push() and objpool_pop() into > include/linux/objpool.h and marks them as static inline functions, > enabling inlining. To avoid anyone using internal helpers > (objpool_try_get_slot, objpool_try_add_slot), rename them to use leading > underscores. > > We used kretprobe microbenchmark from BPF selftests (bench trig-kprobe > and trig-kprobe-multi benchmarks) running no-op BPF kretprobe/kretprobe.multi > programs in a tight loop to evaluate the effect. BPF own overhead in > this case is minimal and it mostly stresses the rest of in-kernel > kretprobe infrastructure overhead. Results are in millions of calls per > second. This is not super scientific, but shows the trend nevertheless. > > BEFORE > ====== > kretprobe : 9.794 ± 0.086M/s > kretprobe-multi: 10.219 ± 0.032M/s > > AFTER > ===== > kretprobe : 9.937 ± 0.174M/s (+1.5%) > kretprobe-multi: 10.440 ± 0.108M/s (+2.2%) > > Cc: Matt (Qiang) Wu <wuqiang.matt@xxxxxxxxxxxxx> > Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx> Hello, this question is not specific to your patch, but since it's a recent thread, I'll ask it here instead of digging up the original objpool patches. I'm trying to understand how objpool works and if it could be integrated into SLUB, for the LSF/MM discussion next week: https://lore.kernel.org/all/b929d5fb-8e88-4f23-8ec7-6bdaf61f84f9@xxxxxxx/ > +/* adding object to slot, abort if the slot was already full */ I don't see any actual abort in the code (not in this code nor in the deleted code - it's the same code, just moved for inlining purposes). > +static inline int > +__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) > +{ > + struct objpool_slot *slot = pool->cpu_slots[cpu]; > + uint32_t head, tail; > + > + /* loading tail and head as a local snapshot, tail first */ > + tail = READ_ONCE(slot->tail); > + > + do { > + head = READ_ONCE(slot->head); > + /* fault caught: something must be wrong */ > + WARN_ON_ONCE(tail - head > pool->nr_objs); So this will only WARN if we go over the capacity, but continue and overwrite a pointer that was already there, effectively leaking said object, no? > + } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); > + > + /* now the tail position is reserved for the given obj */ > + WRITE_ONCE(slot->entries[tail & slot->mask], obj); > + /* update sequence to make this obj available for pop() */ > + smp_store_release(&slot->last, tail + 1); > + > + return 0; > +} > > /** > * objpool_push() - reclaim the object and return back to objpool > @@ -134,7 +219,19 @@ void *objpool_pop(struct objpool_head *pool); > * return: 0 or error code (it fails only when user tries to push > * the same object multiple times or wrong "objects" into objpool) > */ > -int objpool_push(void *obj, struct objpool_head *pool); > +static inline int objpool_push(void *obj, struct objpool_head *pool) > +{ > + unsigned long flags; > + int rc; > + > + /* disable local irq to avoid preemption & interruption */ > + raw_local_irq_save(flags); > + rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id()); And IIUC, we could in theory objpool_pop() on one cpu, then later another cpu might do objpool_push() and cause the latter cpu's pool to go over capacity? Is there some implicit requirements of objpool users to take care of having matched cpu for pop and push? Are the current objpool users obeying this requirement? (I can see the selftests do, not sure about the actual users). Or am I missing something? Thanks. > + raw_local_irq_restore(flags); > + > + return rc; > +} > + > > /** > * objpool_drop() - discard the object and deref objpool > diff --git a/lib/objpool.c b/lib/objpool.c > index cfdc02420884..f696308fc026 100644 > --- a/lib/objpool.c > +++ b/lib/objpool.c > @@ -152,106 +152,6 @@ int objpool_init(struct objpool_head *pool, int nr_objs, int object_size, > } > EXPORT_SYMBOL_GPL(objpool_init); > > -/* adding object to slot, abort if the slot was already full */ > -static inline int > -objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu) > -{ > - struct objpool_slot *slot = pool->cpu_slots[cpu]; > - uint32_t head, tail; > - > - /* loading tail and head as a local snapshot, tail first */ > - tail = READ_ONCE(slot->tail); > - > - do { > - head = READ_ONCE(slot->head); > - /* fault caught: something must be wrong */ > - WARN_ON_ONCE(tail - head > pool->nr_objs); > - } while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1)); > - > - /* now the tail position is reserved for the given obj */ > - WRITE_ONCE(slot->entries[tail & slot->mask], obj); > - /* update sequence to make this obj available for pop() */ > - smp_store_release(&slot->last, tail + 1); > - > - return 0; > -} > - > -/* reclaim an object to object pool */ > -int objpool_push(void *obj, struct objpool_head *pool) > -{ > - unsigned long flags; > - int rc; > - > - /* disable local irq to avoid preemption & interruption */ > - raw_local_irq_save(flags); > - rc = objpool_try_add_slot(obj, pool, raw_smp_processor_id()); > - raw_local_irq_restore(flags); > - > - return rc; > -} > -EXPORT_SYMBOL_GPL(objpool_push); > - > -/* try to retrieve object from slot */ > -static inline void *objpool_try_get_slot(struct objpool_head *pool, int cpu) > -{ > - struct objpool_slot *slot = pool->cpu_slots[cpu]; > - /* load head snapshot, other cpus may change it */ > - uint32_t head = smp_load_acquire(&slot->head); > - > - while (head != READ_ONCE(slot->last)) { > - void *obj; > - > - /* > - * data visibility of 'last' and 'head' could be out of > - * order since memory updating of 'last' and 'head' are > - * performed in push() and pop() independently > - * > - * before any retrieving attempts, pop() must guarantee > - * 'last' is behind 'head', that is to say, there must > - * be available objects in slot, which could be ensured > - * by condition 'last != head && last - head <= nr_objs' > - * that is equivalent to 'last - head - 1 < nr_objs' as > - * 'last' and 'head' are both unsigned int32 > - */ > - if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) { > - head = READ_ONCE(slot->head); > - continue; > - } > - > - /* obj must be retrieved before moving forward head */ > - obj = READ_ONCE(slot->entries[head & slot->mask]); > - > - /* move head forward to mark it's consumption */ > - if (try_cmpxchg_release(&slot->head, &head, head + 1)) > - return obj; > - } > - > - return NULL; > -} > - > -/* allocate an object from object pool */ > -void *objpool_pop(struct objpool_head *pool) > -{ > - void *obj = NULL; > - unsigned long flags; > - int i, cpu; > - > - /* disable local irq to avoid preemption & interruption */ > - raw_local_irq_save(flags); > - > - cpu = raw_smp_processor_id(); > - for (i = 0; i < num_possible_cpus(); i++) { > - obj = objpool_try_get_slot(pool, cpu); > - if (obj) > - break; > - cpu = cpumask_next_wrap(cpu, cpu_possible_mask, -1, 1); > - } > - raw_local_irq_restore(flags); > - > - return obj; > -} > -EXPORT_SYMBOL_GPL(objpool_pop); > - > /* release whole objpool forcely */ > void objpool_free(struct objpool_head *pool) > {
