Received: by 2002:a05:6a10:af89:0:0:0:0 with SMTP id iu9csp3354964pxb; Mon, 17 Jan 2022 18:25:37 -0800 (PST) X-Google-Smtp-Source: ABdhPJw1fccHAg93dFcVRQiFK+7Pypacf/5Rhk24aQG7SOdX2x8Jxnmmb4Gp593WUFrtCI95W4XF X-Received: by 2002:a17:903:1210:b0:149:8d21:3e43 with SMTP id l16-20020a170903121000b001498d213e43mr25372003plh.83.1642472737385; Mon, 17 Jan 2022 18:25:37 -0800 (PST) ARC-Seal: i=1; a=rsa-sha256; t=1642472737; cv=none; d=google.com; s=arc-20160816; b=llXLxGai2dS9ljUHlVP66TQAr4whdcl+ny3XeZ2YcAjuOqBggxcy06+E01/sTEBDw/ 6ppqQeet8a+zZO+WwyTtBrv9jGoqmwpawT7QM8CaPMlUwHAEUhoO29QnUDY0IRODNdRP 9hHCnc3gaTOGDyM+iTJtHiav1/kHp2dwVe5Hz2II3qrCXopN4Sd1m/HwIfPNoTvc2vDy P22x0QgtecNp8SuhUkglRfNY+NP1j6Wtvc0bX/opqRmLFlgA3I+BwFYj81aFIUojicuf SHsNAMj6/RqiPnOfL+/61FzuSNyWBCbq8tsqq1bdjHLKxsHic4E6HlIMf8z3uskQZHrD vfqQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :references:in-reply-to:message-id:date:subject:cc:to:from; bh=RepyTl6Ex7LH92WUrnySxq98h0B4JcPpu6+zEibdBTE=; b=iPIxleVlSRp9v05fayF8JvJ1lARvU58pzjn7iG2fMezb0xRfIFk+OE8ZCGtIL4fTFW 65T2k/GfVbLeT6f4djOxYR1u8yOeEEsRzLneB7CyyNCJ2KyotNz71HjaVbINzGfv2N4A vBYpt2Szs3InHeH30q1W0kp6okKsrqs14zSqqljF5RQ7eYXlCzuddShIxcXhtqj0mv9I c9sVs7jeiKTsqfckYw49kjqGoue4lpTT7zmb+FlX+V96aSwF7zDFFtNjIaEXqRm7iAWD 8NRrd73Y4SS+9Op9dKkP3mGuT8HW9vkz7yAqyLt3mgg3mcuGaxpGYf3Cx5rcAN1qbG1T U+yw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=arm.com Return-Path: Received: from vger.kernel.org (vger.kernel.org. [23.128.96.18]) by mx.google.com with ESMTP id q7si5793393pfs.65.2022.01.17.18.25.25; Mon, 17 Jan 2022 18:25:37 -0800 (PST) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18; Authentication-Results: mx.google.com; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=arm.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229873AbiAQMp2 (ORCPT + 99 others); Mon, 17 Jan 2022 07:45:28 -0500 Received: from foss.arm.com ([217.140.110.172]:57834 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231622AbiAQMpZ (ORCPT ); Mon, 17 Jan 2022 07:45:25 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 5F123101E; Mon, 17 Jan 2022 04:45:25 -0800 (PST) Received: from e127744.arm.com (unknown [10.57.36.133]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 20D453F73D; Mon, 17 Jan 2022 04:45:24 -0800 (PST) From: German Gomez To: linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, will@kernel.org, mark.rutland@arm.com, james.clark@arm.com, leo.yan@linaro.org Cc: German Gomez Subject: [RFC PATCH 1/2] perf: arm_spe: Fix consistency of PMSCR register bit CX Date: Mon, 17 Jan 2022 12:44:31 +0000 Message-Id: <20220117124432.3119132-2-german.gomez@arm.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20220117124432.3119132-1-german.gomez@arm.com> References: <20220117124432.3119132-1-german.gomez@arm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The arm_spe_pmu driver will enable the CX bit of the PMSCR register in order to add CONTEXT packets into the traces if the owner of the perf event runs with capabilities CAP_PERFMON or CAP_SYS_ADMIN. The value of the bit is computed in the arm_spe_event_to_pmscr function [1], and the check for capabilities happens in [2] in the pmu init callback. This suggests that the value of the CX bit should remain consistent for the duration of the perf session. However, the function arm_spe_event_to_pmscr may be called later during the start callback [3] when the "current" process is not the owner of the perf session, so the CX bit is currently not consistent. Consider the following example: 1. Run a process in the background with capability CAP_SYS_ADMIN in CPU0. $ taskset --cpu-list 0 sudo dd if=/dev/random of=/dev/null & [3] 3806 2. Begin a perf session _without_ capabilities (we shouldn't see CONTEXT packets). $ perf record -e arm_spe_0// -C0 -- sleep 1 $ perf report -D | grep CONTEXT . 0000000e: 65 df 0e 00 00 CONTEXT 0xedf el2 . 0000004e: 65 df 0e 00 00 CONTEXT 0xedf el2 . 0000008e: 65 df 0e 00 00 CONTEXT 0xedf el2 [...] As can be seen, the traces begin showing CONTEXT packets when the pid is 0xedf (3807). This happens because the pmu start callback is run when the current process is not the owner of the perf session, so the CX register bit is set. One way to fix this is by caching the value of the CX bit during the initialization of the PMU event, so that it remains consistent for the duration of the session. [1]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/perf/arm_spe_pmu.c?h=v5.16#n275 [2]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/perf/arm_spe_pmu.c?h=v5.16#n713 [3]: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/drivers/perf/arm_spe_pmu.c?h=v5.16#n751 Signed-off-by: German Gomez --- drivers/perf/arm_spe_pmu.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c index d44bcc29d..8515bf85c 100644 --- a/drivers/perf/arm_spe_pmu.c +++ b/drivers/perf/arm_spe_pmu.c @@ -57,6 +57,7 @@ struct arm_spe_pmu { u16 pmsver; u16 min_period; u16 counter_sz; + bool pmscr_cx; #define SPE_PMU_FEAT_FILT_EVT (1UL << 0) #define SPE_PMU_FEAT_FILT_TYP (1UL << 1) @@ -260,6 +261,7 @@ static const struct attribute_group *arm_spe_pmu_attr_groups[] = { static u64 arm_spe_event_to_pmscr(struct perf_event *event) { struct perf_event_attr *attr = &event->attr; + struct arm_spe_pmu *spe_pmu = to_spe_pmu(event->pmu); u64 reg = 0; reg |= ATTR_CFG_GET_FLD(attr, ts_enable) << SYS_PMSCR_EL1_TS_SHIFT; @@ -272,7 +274,7 @@ static u64 arm_spe_event_to_pmscr(struct perf_event *event) if (!attr->exclude_kernel) reg |= BIT(SYS_PMSCR_EL1_E1SPE_SHIFT); - if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && perfmon_capable()) + if (IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR) && spe_pmu->pmscr_cx) reg |= BIT(SYS_PMSCR_EL1_CX_SHIFT); return reg; @@ -709,10 +711,10 @@ static int arm_spe_pmu_event_init(struct perf_event *event) !(spe_pmu->features & SPE_PMU_FEAT_FILT_LAT)) return -EOPNOTSUPP; + spe_pmu->pmscr_cx = perfmon_capable(); reg = arm_spe_event_to_pmscr(event); if (!perfmon_capable() && (reg & (BIT(SYS_PMSCR_EL1_PA_SHIFT) | - BIT(SYS_PMSCR_EL1_CX_SHIFT) | BIT(SYS_PMSCR_EL1_PCT_SHIFT)))) return -EACCES; -- 2.25.1