From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=95.215.58.159 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1795205124; b=ujIURw4euDfj7wOIOmKXf+iOiHDuJ+TxiiXOl3av9G6zFjJt78qSFkmrxzeQTmvcJe8l sbi+owTJU+g3g7vWDTTAKoqorWUErmNh322ii20D57OU1tc/LavU3luA6gJTu+UXW7rR2 w709X7uZSrTfzzj90nTgoZvi7CXRLPjuZu/QxwKIpU8JCnk/HzDyUszCMfCJelT1Pio70 +toxxoqbSWEfCuouYQWhsYhBE3lKkvJV30Fj6Zjo69HNpmmKNvzWOC42Z+SzrT7WERzY2 opbIhHrJ+yxjH8ms18yXrASUeFYxhNIHvXS0pS9JVLxEabqfi4vtkFiDnccoV9rgkwA== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1795205124; h=DMARC-Filter:X-Envelope-To:DKIM-Signature:X-Envelope-To:Received: X-Mizu-Trace-ID:X-Migadu-Flow:Message-ID:Date:MIME-Version:User-Agent: Subject:To:Cc:References:Content-Language:From:In-Reply-To: Content-Type:Content-Transfer-Encoding; bh=Lp04bo2sgP06USHAChXdOuNrd2K1DM1CxyrrPNLoIDc=; b=PCkOTksyxMq+hmfBK1oj4RuHuI4MtqeP3s5CUFWRiUWzCxcWoz3KB7E/N4bwkuzg3Wxu 9IvNffNtXyr8XN6L6eJ8LmcxxplSCvBKuAns7WglKPjQyPRrDL303AwM9PEcEG9WxNy0p r2dEK5zjFvXLMuf6PLN4mUQ3rUFTCGBtysUL64u+Aiq5jAUpbvzV/U0V31oj8SiQMoiAe Xt9OpuO4xlDKsZKhp8nNGueoAf5qN2IgddiIEMMSoMlu4r9ab7n9LlUwf6lQd7sqgmdEw HpSEdsiulDufqmK1mGiRSfyeDbFhCHSzQtyhzvHJJNxT56r1vEZIfFPRFNnHbnX+evA== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b="p/71m9Bl"; arc=none smtp.remote-ip=95.215.58.159 Received: from mta1.migadu.com (out-159.mta1.migadu.com [95.215.58.159]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3ACA8606A33B for ; Fri, 20 Nov 2026 20:05:19 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 3ACA8606A33B Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key, unprotected) header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=p/71m9Bl X-Envelope-To: linux-perf-users@vger.kernel.org DKIM-Signature: a=rsa-sha256; bh=6iXX93MlfIOuC/eK1roCbWuvGCrP8yxENT5m24PLFpg=; c=simple/simple; d=linux.dev; h=from:to:subject:date:message-id:mime-version:content-type; s=key1; t=1795205118; v=1; x=1795809918; b=p/71m9BlbwFJb0TdRnG4u3KnNBiLxaf0sq42iV6OQu6Z9SYyEPr3dD9dQR00EYbiBBwgM1zr rTHfO/Z5O+ESBgZ8OIdrYGOa6vLxfQSYW6pp/Ww+9tbKEfsJVpmsion1KPjrHlSOlpoXrCHMsVh wbpVt5WtceZQd1fsViRm65TQ= X-Envelope-To: linux-perf-users@vger.kernel.org Received: by smtp.migadu.com with ESMTPS id 4ca826ec631b7483; Fri, 20 Nov 2026 20:05:17 +0000 X-Mizu-Trace-ID: 4ca826ec631b7483 X-Migadu-Flow: FLOW_OUT Message-ID: <7f9c12cf-b2a6-4238-b768-17d66b84b2a9@linux.dev> Date: Fri, 20 Nov 2026 20:05:12 +0000 X-Mailing-List: linux-perf-users@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH 3/3] perf/core: Don't zero perf_sample_data in do_perf_sw_event() To: Peter Zijlstra Cc: mingo@redhat.com, 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, james.clark@linaro.org, linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, rkeilty@meta.com, atish.patra@linux.dev, dgreid@meta.com, riel@surriel.com, shakeel.butt@linux.dev, kernel-team@meta.com References: <20261119211235.99805-1-usama.arif@linux.dev> <20261119211235.99805-4-usama.arif@linux.dev> <20261120091150.GN2668564@noisy.programming.kicks-ass.net> <20261120091258.GH2669272@noisy.programming.kicks-ass.net> Content-Language: en-US From: Usama Arif In-Reply-To: <20261120091258.GH2669272@noisy.programming.kicks-ass.net> Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit On 20/11/2026 01:12, Peter Zijlstra wrote: > On Fri, Nov 20, 2026 at 10:11:51AM +0100, Peter Zijlstra wrote: >> On Thu, Nov 19, 2026 at 01:10:46PM -0800, Usama Arif wrote: >> >>> kernel/events/core.c | 2 +- >>> 1 file changed, 1 insertion(+), 1 deletion(-) >>> >>> diff --git a/kernel/events/core.c b/kernel/events/core.c >>> index 57ea7e3c01a025..fa10ad7cfd99af 100644 >>> --- a/kernel/events/core.c >>> +++ b/kernel/events/core.c >>> @@ -11212,7 +11212,7 @@ static void do_perf_sw_event(enum perf_type_id type, u32 event_id, >>> u64 nr, struct pt_regs *regs, u64 addr) >>> { >>> struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable); >>> - struct perf_sample_data data; >>> + struct perf_sample_data data __uninitialized; >>> struct perf_event *event; >>> struct hlist_head *head; >>> >> >> I like this one, didn't know about the __uninitialized thing. But I >> think we wants to be more consistent with this. >> >> A little git-grep seems to suggest we ought to do the same elsewhere. >> Shall I fold the little something below in this patch? >> > > And this should be a separate patch again I think. Agreed, but IBS is not safe yet. For PERF_SAMPLE_WEIGHT_STRUCT, perf_ibs_parse_ld_st_data() writes only var1_dw and var2_w but sets PERF_SAMPLE_WEIGHT_TYPE, so perf_output_sample() copies var3_w from whatever is on the stack. INIT_STACK_ALL_ZERO hides that today, and INIT_STACK_NONE kernels have leaked those 2 bytes since 6b2ae4952ef8. With __uninitialized in perf_ibs_handle_irq() every kernel would. We need the below: commit e662f8539ca00096db3ee4d570efe97767427fbe Author: Usama Arif Date: Fri Nov 20 09:04:13 2026 -0800 perf/x86/amd/ibs: Don't leak stack contents through PERF_SAMPLE_WEIGHT_STRUCT For a load that missed the data cache, perf_ibs_parse_ld_st_data() reports the miss latency as the sample weight and marks PERF_SAMPLE_WEIGHT_TYPE as done, so perf_prepare_sample() leaves the field alone. With PERF_SAMPLE_WEIGHT_STRUCT it writes only var1_dw and var2_w, but perf_output_sample() copies all 8 bytes of the union into the ring buffer. var3_w therefore carries whatever was left in the on-stack struct perf_sample_data in perf_ibs_handle_irq(). CONFIG_INIT_STACK_ALL_ZERO hides this by clearing the struct on entry. Without it, every such sample hands 2 bytes of kernel stack to user space. "perf mem record" asks for PERF_SAMPLE_WEIGHT_STRUCT on x86, and since v6.14 swfilt lets an unprivileged user sample their own tasks with IBS. Write var3_w as well. Fixes: 6b2ae4952ef8 ("perf/x86/amd: Support PERF_SAMPLE_{WEIGHT|WEIGHT_STRUCT}") Cc: stable@vger.kernel.org Signed-off-by: Usama Arif diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 66e67e27224f18..9aa47751b37f6c 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -1376,6 +1376,7 @@ static void perf_ibs_parse_ld_st_data(__u64 sample_type, if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) { data->weight.var1_dw = op_data3.dc_miss_lat; data->weight.var2_w = op_data.tag_to_ret_ctr; + data->weight.var3_w = 0; } else if (sample_type & PERF_SAMPLE_WEIGHT) { data->weight.full = op_data3.dc_miss_lat; } The other sites look fine to me, including arch-PEBS: the drain skips records whose first fragment has no basic group, so var3_w is always written there. > > --- > diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c > index 49b6b8fce566..db6c87552594 100644 > --- a/arch/x86/events/amd/core.c > +++ b/arch/x86/events/amd/core.c > @@ -958,7 +958,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) > struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); > static atomic64_t status_warned = ATOMIC64_INIT(0); > u64 reserved, status, mask, new_bits, prev_bits; > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct hw_perf_event *hwc; > struct perf_event *event; > int handled = 0, idx; > diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c > index 96c96369480a..cf0eafd67430 100644 > --- a/arch/x86/events/amd/ibs.c > +++ b/arch/x86/events/amd/ibs.c > @@ -1483,7 +1483,7 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs) > struct cpu_perf_ibs *pcpu = this_cpu_ptr(perf_ibs->pcpu); > struct perf_event *event = pcpu->event; > struct hw_perf_event *hwc; > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct perf_raw_record raw; > struct pt_regs regs; > struct perf_ibs_data ibs_data; > diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c > index 4e344fb1ae3e..5f8bfc65b256 100644 > --- a/arch/x86/events/core.c > +++ b/arch/x86/events/core.c > @@ -2157,7 +2157,7 @@ void x86_pmu_update_perf_regs(struct perf_event *event, > > int x86_pmu_handle_irq(struct pt_regs *regs) > { > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct cpu_hw_events *cpuc; > struct perf_event *event; > int idx, handled = 0; > diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c > index 0a34d674df59..5d84c18096a9 100644 > --- a/arch/x86/events/intel/core.c > +++ b/arch/x86/events/intel/core.c > @@ -3819,7 +3819,7 @@ static int x86_pmu_handle_guest_pebs(struct pt_regs *regs, > > static int handle_pmi_common(struct pt_regs *regs, u64 status) > { > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); > int bit; > int handled = 0; > diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c > index 8444670cee4a..73f6fd66856f 100644 > --- a/arch/x86/events/intel/ds.c > +++ b/arch/x86/events/intel/ds.c > @@ -1184,7 +1184,7 @@ int intel_pmu_drain_bts_buffer(void) > struct bts_record *at, *base, *top; > struct perf_output_handle handle; > struct perf_event_header header; > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > unsigned long skip = 0; > struct pt_regs regs; > > @@ -1265,7 +1265,7 @@ int intel_pmu_drain_bts_buffer(void) > void intel_pmu_drain_pebs_buffer(void) > { > struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > > WARN_ON_ONCE(cpuc->enabled); > > diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c > index e887adc108ac..aa38b0ac3c7b 100644 > --- a/arch/x86/events/intel/knc.c > +++ b/arch/x86/events/intel/knc.c > @@ -213,7 +213,7 @@ static inline void knc_pmu_ack_status(u64 ack) > > static int knc_pmu_handle_irq(struct pt_regs *regs) > { > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct cpu_hw_events *cpuc; > int handled = 0; > int bit, loops; > diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c > index 5368dc31787c..4ac429e55935 100644 > --- a/arch/x86/events/intel/p4.c > +++ b/arch/x86/events/intel/p4.c > @@ -1033,7 +1033,7 @@ static int p4_pmu_set_period(struct perf_event *event) > > static int p4_pmu_handle_irq(struct pt_regs *regs) > { > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct cpu_hw_events *cpuc; > struct perf_event *event; > struct hw_perf_event *hwc; > diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c > index e506f677db57..fc98a7fdd3bc 100644 > --- a/arch/x86/events/zhaoxin/core.c > +++ b/arch/x86/events/zhaoxin/core.c > @@ -355,7 +355,7 @@ static void zhaoxin_pmu_enable_event(struct perf_event *event) > */ > static int zhaoxin_pmu_handle_irq(struct pt_regs *regs) > { > - struct perf_sample_data data; > + struct perf_sample_data data __uninitialized; > struct cpu_hw_events *cpuc; > int handled = 0; > u64 status; > diff --git a/arch/x86/include/asm/stop_machine.h b/arch/x86/include/asm/stop_machine.h > deleted file mode 100644 > index e69de29bb2d1..000000000000