From nobody Tue Feb 10 04:12:30 2026 Received: from desiato.infradead.org (desiato.infradead.org [90.155.92.199]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8AFDA83CD3 for ; Mon, 4 Nov 2024 13:56:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=90.155.92.199 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730728613; cv=none; b=F1i+oFXbVGOza0Mp2SDtV5rExD65fMLrcGCFi0ot2yEZJEjCr/DVx68gFy/GiLxIWNPiAQn8IEbJ0od/rJFGxOvZASeaqrN+AZk7QqpNgiqT16YnwLPXh4lFcp1QqacLGC2j/W3ERGDGluVAWqT4xucM3ozbk1OLejU2GTNHURQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730728613; c=relaxed/simple; bh=ekxfE5Wf64sxcJSq3U+5kwvEHPVYIZ7WQLWtqSBqYAk=; h=Message-Id:Date:From:To:Cc:Subject:References:MIME-Version: Content-Type; b=c990xjS6X2DsPcO10f2SAZwOGUVOr8n6IkchaLwwJk1AewDoB2cta7jDDN8JZE9+6QXahFMYRhzETROqopHSI/oyM/KC6H5SwXMIQ6NgZ47YwZfVBglq4poDiRxXgxlZlKATPgk8gliGLx3NCiQW0bz22+5teFsJLg1W6ednHMo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=infradead.org; spf=none smtp.mailfrom=infradead.org; dkim=pass (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b=lRzbJ4Tx; arc=none smtp.client-ip=90.155.92.199 Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=infradead.org Authentication-Results: smtp.subspace.kernel.org; spf=none smtp.mailfrom=infradead.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=infradead.org header.i=@infradead.org header.b="lRzbJ4Tx" DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=infradead.org; s=desiato.20200630; h=Content-Type:MIME-Version:References: Subject:Cc:To:From:Date:Message-Id:Sender:Reply-To:Content-Transfer-Encoding: Content-ID:Content-Description:In-Reply-To; bh=0FAeUrh26MQMtKZAZg5j/4wlBo016TKLb6lLfEuS0hU=; b=lRzbJ4Tx68yaH/oaLk0ccCjNy9 Ab1ANt+SUxRdxFdp2p6b82UpYZoBoglEE1eWzCpRDsL3dpYp/PSV4rTfyednRzU3VsiMA0MvGnFbA ldOMnPXie4RLLD8KJVz5pZTnGALDvEPejzGo6j9osbCrb+1pRWhrPuCo3AnJAhkMvqbmBiiz0L+Qh TSWgnBSDrg0ClJioDBG4uR0/Gq+T3d6lcQ8NOXJVVEwPtWek8ii2KMb4GPsRcj/jLnpAJbv0+NZXw 90JLepM3ee6/MqDq2gbCrzPPLT/taT7qCBQ0+QmRA8ylYTHFZ0fp7LsKPDHcF9SPO0n+hDD9AlicV LJcWSq2Q==; Received: from j130084.upc-j.chello.nl ([24.132.130.84] helo=noisy.programming.kicks-ass.net) by desiato.infradead.org with esmtpsa (Exim 4.98 #2 (Red Hat Linux)) id 1t7xZX-0000000BL7z-1Ozz; Mon, 04 Nov 2024 13:56:47 +0000 Received: by noisy.programming.kicks-ass.net (Postfix, from userid 0) id 5F27A302179; Mon, 4 Nov 2024 14:56:46 +0100 (CET) Message-Id: <20241104135517.967889521@infradead.org> User-Agent: quilt/0.65 Date: Mon, 04 Nov 2024 14:39:13 +0100 From: Peter Zijlstra To: mingo@kernel.org, lucas.demarchi@intel.com Cc: linux-kernel@vger.kernel.org, peterz@infradead.org, willy@infradead.org, acme@kernel.org, namhyung@kernel.org, mark.rutland@arm.com, alexander.shishkin@linux.intel.com, jolsa@kernel.org, irogers@google.com, adrian.hunter@intel.com, kan.liang@linux.intel.com Subject: [PATCH 04/19] perf: Simplify perf_event_alloc() error path References: <20241104133909.669111662@infradead.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" The error cleanup sequence in perf_event_alloc() is a subset of the existing _free_event() function (it must of course be). Split this out into __free_event() and simplify the error path. Signed-off-by: Peter Zijlstra (Intel) --- include/linux/perf_event.h | 16 +++-- kernel/events/core.c | 134 ++++++++++++++++++++++------------------= ----- 2 files changed, 76 insertions(+), 74 deletions(-) --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -652,13 +652,15 @@ struct swevent_hlist { struct rcu_head rcu_head; }; =20 -#define PERF_ATTACH_CONTEXT 0x01 -#define PERF_ATTACH_GROUP 0x02 -#define PERF_ATTACH_TASK 0x04 -#define PERF_ATTACH_TASK_DATA 0x08 -#define PERF_ATTACH_ITRACE 0x10 -#define PERF_ATTACH_SCHED_CB 0x20 -#define PERF_ATTACH_CHILD 0x40 +#define PERF_ATTACH_CONTEXT 0x0001 +#define PERF_ATTACH_GROUP 0x0002 +#define PERF_ATTACH_TASK 0x0004 +#define PERF_ATTACH_TASK_DATA 0x0008 +#define PERF_ATTACH_ITRACE 0x0010 +#define PERF_ATTACH_SCHED_CB 0x0020 +#define PERF_ATTACH_CHILD 0x0040 +#define PERF_ATTACH_EXCLUSIVE 0x0080 +#define PERF_ATTACH_CALLCHAIN 0x0100 =20 struct bpf_prog; struct perf_cgroup; --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -5246,6 +5246,8 @@ static int exclusive_event_init(struct p return -EBUSY; } =20 + event->attach_state |=3D PERF_ATTACH_EXCLUSIVE; + return 0; } =20 @@ -5253,14 +5255,13 @@ static void exclusive_event_destroy(stru { struct pmu *pmu =3D event->pmu; =20 - if (!is_exclusive_pmu(pmu)) - return; - /* see comment in exclusive_event_init() */ if (event->attach_state & PERF_ATTACH_TASK) atomic_dec(&pmu->exclusive_cnt); else atomic_inc(&pmu->exclusive_cnt); + + event->attach_state &=3D ~PERF_ATTACH_EXCLUSIVE; } =20 static bool exclusive_event_match(struct perf_event *e1, struct perf_event= *e2) @@ -5319,40 +5320,20 @@ static void perf_pending_task_sync(struc rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_= UNINTERRUPTIBLE); } =20 -static void _free_event(struct perf_event *event) +/* vs perf_event_alloc() error */ +static void __free_event(struct perf_event *event) { - irq_work_sync(&event->pending_irq); - irq_work_sync(&event->pending_disable_irq); - perf_pending_task_sync(event); - - unaccount_event(event); + if (event->attach_state & PERF_ATTACH_CALLCHAIN) + put_callchain_buffers(); =20 - security_perf_event_free(event); + kfree(event->addr_filter_ranges); =20 - if (event->rb) { - /* - * Can happen when we close an event with re-directed output. - * - * Since we have a 0 refcount, perf_mmap_close() will skip - * over us; possibly making our ring_buffer_put() the last. - */ - mutex_lock(&event->mmap_mutex); - ring_buffer_attach(event, NULL); - mutex_unlock(&event->mmap_mutex); - } + if (event->attach_state & PERF_ATTACH_EXCLUSIVE) + exclusive_event_destroy(event); =20 if (is_cgroup_event(event)) perf_detach_cgroup(event); =20 - if (!event->parent) { - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - put_callchain_buffers(); - } - - perf_event_free_bpf_prog(event); - perf_addr_filters_splice(event, NULL); - kfree(event->addr_filter_ranges); - if (event->destroy) event->destroy(event); =20 @@ -5363,22 +5344,58 @@ static void _free_event(struct perf_even if (event->hw.target) put_task_struct(event->hw.target); =20 - if (event->pmu_ctx) + if (event->pmu_ctx) { + /* + * put_pmu_ctx() needs an event->ctx reference, because of + * epc->ctx. + */ + WARN_ON_ONCE(!event->ctx); + WARN_ON_ONCE(event->pmu_ctx->ctx !=3D event->ctx); put_pmu_ctx(event->pmu_ctx); + } =20 /* - * perf_event_free_task() relies on put_ctx() being 'last', in particular - * all task references must be cleaned up. + * perf_event_free_task() relies on put_ctx() being 'last', in + * particular all task references must be cleaned up. */ if (event->ctx) put_ctx(event->ctx); =20 - exclusive_event_destroy(event); - module_put(event->pmu->module); + if (event->pmu) + module_put(event->pmu->module); =20 call_rcu(&event->rcu_head, free_event_rcu); } =20 +/* vs perf_event_alloc() success */ +static void _free_event(struct perf_event *event) +{ + irq_work_sync(&event->pending_irq); + irq_work_sync(&event->pending_disable_irq); + perf_pending_task_sync(event); + + unaccount_event(event); + + security_perf_event_free(event); + + if (event->rb) { + /* + * Can happen when we close an event with re-directed output. + * + * Since we have a 0 refcount, perf_mmap_close() will skip + * over us; possibly making our ring_buffer_put() the last. + */ + mutex_lock(&event->mmap_mutex); + ring_buffer_attach(event, NULL); + mutex_unlock(&event->mmap_mutex); + } + + perf_event_free_bpf_prog(event); + perf_addr_filters_splice(event, NULL); + + __free_event(event); +} + /* * Used to free events which have a known refcount of 1, such as in error = paths * where the event isn't exposed yet and inherited events. @@ -11922,8 +11939,10 @@ static int perf_try_init_event(struct pm event->destroy(event); } =20 - if (ret) + if (ret) { + event->pmu =3D NULL; module_put(pmu->module); + } =20 return ret; } @@ -12251,7 +12270,7 @@ perf_event_alloc(struct perf_event_attr * See perf_output_read(). */ if (has_inherit_and_sample_read(attr) && !(attr->sample_type & PERF_SAMPL= E_TID)) - goto err_ns; + goto err; =20 if (!has_branch_stack(event)) event->attr.branch_sample_type =3D 0; @@ -12259,7 +12278,7 @@ perf_event_alloc(struct perf_event_attr pmu =3D perf_init_event(event); if (IS_ERR(pmu)) { err =3D PTR_ERR(pmu); - goto err_ns; + goto err; } =20 /* @@ -12269,24 +12288,24 @@ perf_event_alloc(struct perf_event_attr */ if (pmu->task_ctx_nr =3D=3D perf_invalid_context && (task || cgroup_fd != =3D -1)) { err =3D -EINVAL; - goto err_pmu; + goto err; } =20 if (event->attr.aux_output && !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { err =3D -EOPNOTSUPP; - goto err_pmu; + goto err; } =20 if (cgroup_fd !=3D -1) { err =3D perf_cgroup_connect(cgroup_fd, event, attr, group_leader); if (err) - goto err_pmu; + goto err; } =20 err =3D exclusive_event_init(event); if (err) - goto err_pmu; + goto err; =20 if (has_addr_filter(event)) { event->addr_filter_ranges =3D kcalloc(pmu->nr_addr_filters, @@ -12294,7 +12313,7 @@ perf_event_alloc(struct perf_event_attr GFP_KERNEL); if (!event->addr_filter_ranges) { err =3D -ENOMEM; - goto err_per_task; + goto err; } =20 /* @@ -12319,41 +12338,22 @@ perf_event_alloc(struct perf_event_attr if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) { err =3D get_callchain_buffers(attr->sample_max_stack); if (err) - goto err_addr_filters; + goto err; + event->attach_state |=3D PERF_ATTACH_CALLCHAIN; } } =20 err =3D security_perf_event_alloc(event); if (err) - goto err_callchain_buffer; + goto err; =20 /* symmetric to unaccount_event() in _free_event() */ account_event(event); =20 return event; =20 -err_callchain_buffer: - if (!event->parent) { - if (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) - put_callchain_buffers(); - } -err_addr_filters: - kfree(event->addr_filter_ranges); - -err_per_task: - exclusive_event_destroy(event); - -err_pmu: - if (is_cgroup_event(event)) - perf_detach_cgroup(event); - if (event->destroy) - event->destroy(event); - module_put(pmu->module); -err_ns: - if (event->hw.target) - put_task_struct(event->hw.target); - call_rcu(&event->rcu_head, free_event_rcu); - +err: + __free_event(event); return ERR_PTR(err); }