From nobody Mon Feb 9 21:19:19 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 97D2922AE71 for ; Wed, 5 Feb 2025 10:25:35 +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=1738751137; cv=none; b=qIeaQ5cP3xJy3/djMsKEfPM6Thls/TuS4ZTHwSiMnfqB6lt6o8PhrO7HulvK2YMM1kYGrkPfpPR6KkfNBwVBowBTRLocazlpudmKTb1DckDnJayeTUTPhN3jRndSiAoji8M7XZF9qpcvAVYDsnub4RkdEZpYL53fUntEI2lL6MM= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1738751137; c=relaxed/simple; bh=lYXRXPP6HLwg/Bp8nCAcHAAa3/kzpOc+P0uFm2dk0qY=; h=Message-ID:Date:From:To:Cc:Subject:References:MIME-Version: Content-Type; b=rV1mjIjnbxU7lsTmdAHd/p+8Exz09vzZFapDS3z3pyVBYmQe2G006uDNu9EC8n0befL20q7fHoincTSfwJLM28uMQLPgagxjy4cgzGGpkZSXaIHKBFd/1//It8m6LpDZKmf/ngE/BOxBBxb8Qc3OjqD4YeINB96Ow0KOJ8KxTZ0= 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=Sm8UQ8fQ; 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="Sm8UQ8fQ" 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=WAF72F0vl5OegJiTt7utxhY0fac2CVe/BE2y5cW/mMs=; b=Sm8UQ8fQ/WuHYbGLDVWldUILRR iX46Hm0IIvmdJb1HydK3ojcaZNuvazjyoFMGV4XM7RVepjF6oaw4Cw7P3ww43BYxZCUKi4IPmLO5a vS1w5BjeXEDrHJEL39m707GDY1AaW12KLdiPsddReCq+uquitbjqsof61dgYmqZxt8RCpu2e38gn0 0qh/YpvCg0n81JRT6BtDGulK40wT8L9/yb5Znymmuw80SeUaUSxTbDyjGn49byZuZbanpjBlf9fB2 lNjhijLaG/9weTj+M1WgwgM1RyFsoBFA2MnaaI2QzFm8WI1TNreDQb6j3pMP3zaz7BHqE525tkdqc IPDuWiug==; Received: from 77-249-17-89.cable.dynamic.v4.ziggo.nl ([77.249.17.89] helo=noisy.programming.kicks-ass.net) by desiato.infradead.org with esmtpsa (Exim 4.98 #2 (Red Hat Linux)) id 1tfcb3-0000000GbmD-2SoP; Wed, 05 Feb 2025 10:25:32 +0000 Received: by noisy.programming.kicks-ass.net (Postfix, from userid 0) id CFD153061E4; Wed, 5 Feb 2025 11:25:27 +0100 (CET) Message-ID: <20250205102449.230417308@infradead.org> User-Agent: quilt/0.66 Date: Wed, 05 Feb 2025 11:21:29 +0100 From: Peter Zijlstra To: mingo@kernel.org, ravi.bangoria@amd.com, 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 v2 09/24] perf: Simplify perf_event_alloc() error path References: <20250205102120.531585416@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, 75 insertions(+), 75 deletions(-) --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -673,13 +673,15 @@ 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 @@ -5245,6 +5245,8 @@ static int exclusive_event_init(struct p return -EBUSY; } =20 + event->attach_state |=3D PERF_ATTACH_EXCLUSIVE; + return 0; } =20 @@ -5252,14 +5254,13 @@ 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) @@ -5318,40 +5319,20 @@ 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 @@ -5362,22 +5343,58 @@ 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. @@ -12390,7 +12407,7 @@ 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; @@ -12398,7 +12415,7 @@ 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 /* @@ -12408,25 +12425,25 @@ 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) || event->attr.aux_pause || event->attr.aux_resume)) { err =3D -EOPNOTSUPP; - goto err_pmu; + goto err; } =20 if (event->attr.aux_pause && event->attr.aux_resume) { err =3D -EINVAL; - goto err_pmu; + goto err; } =20 if (event->attr.aux_start_paused) { if (!(pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE)) { err =3D -EOPNOTSUPP; - goto err_pmu; + goto err; } event->hw.aux_paused =3D 1; } @@ -12434,12 +12451,12 @@ perf_event_alloc(struct perf_event_attr 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, @@ -12447,7 +12464,7 @@ perf_event_alloc(struct perf_event_attr GFP_KERNEL); if (!event->addr_filter_ranges) { err =3D -ENOMEM; - goto err_per_task; + goto err; } =20 /* @@ -12472,41 +12489,22 @@ 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); }