From patchwork Mon Dec 19 15:35:33 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Zijlstra X-Patchwork-Id: 13076873 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by smtp.lore.kernel.org (Postfix) with ESMTP id 49C03C4332F for ; Mon, 19 Dec 2022 16:53:48 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id C5F028E0003; Mon, 19 Dec 2022 11:53:47 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id C0F298E0001; Mon, 19 Dec 2022 11:53:47 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id AB1498E0003; Mon, 19 Dec 2022 11:53:47 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id 9A8048E0001 for ; Mon, 19 Dec 2022 11:53:47 -0500 (EST) Received: from smtpin22.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay02.hostedemail.com (Postfix) with ESMTP id 60DA31203B0 for ; Mon, 19 Dec 2022 16:53:47 +0000 (UTC) X-FDA: 80259652494.22.69B73CF Received: from desiato.infradead.org (desiato.infradead.org [90.155.92.199]) by imf01.hostedemail.com (Postfix) with ESMTP id 9D1E740009 for ; Mon, 19 Dec 2022 16:53:43 +0000 (UTC) Authentication-Results: imf01.hostedemail.com; dkim=pass header.d=infradead.org header.s=desiato.20200630 header.b=H4AjUmHw; spf=none (imf01.hostedemail.com: domain of peterz@infradead.org has no SPF policy when checking 90.155.92.199) smtp.mailfrom=peterz@infradead.org; dmarc=none ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1671468825; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:content-transfer-encoding:in-reply-to: references:references:dkim-signature; bh=gkcjStIUQsvZMzBnRMKIS/S8C1S2HdQdTZCEH219uhc=; b=yj8b1Xb957/vq/2bFhkCCTz2Jh8NwzrJVlWdSXL9t6iv4h++Q+qEp124Kyu2tZeCRsYw3N fK2a8N7+q3Gt9psTOGR16QEaJpTu6IuwSJn6QxTkcC4iXKodEp3kKMddB4ZoDYs7cxgJf/ LL3RLd7tp5ah8/fdWgY5w5KAvi/x9xM= ARC-Authentication-Results: i=1; imf01.hostedemail.com; dkim=pass header.d=infradead.org header.s=desiato.20200630 header.b=H4AjUmHw; spf=none (imf01.hostedemail.com: domain of peterz@infradead.org has no SPF policy when checking 90.155.92.199) smtp.mailfrom=peterz@infradead.org; dmarc=none ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1671468825; a=rsa-sha256; cv=none; b=k3kVmTpbJA+RBCre8SFlPnVE3P1CMH5IpU/pnkj7jGVMa6C0rxxK68TIP3bChGzo4XCqJ2 YLnqDUhgS/yVxSPLfJ6fYYEuGC8pvVS3JymuOYse0xgJSGD40BFTHfXhfw+k2C1jZafF2+ +0itJLi9L6Q+SK910VafQikPszs66cg= 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=gkcjStIUQsvZMzBnRMKIS/S8C1S2HdQdTZCEH219uhc=; b=H4AjUmHwWCRzxq87XM6dpIVmhp a6K9WMWqe+zvKBxZT3MnWCIIOoYI+xLcYdnMcJtUyBQ537agojcGqjlVwUHqfZ8U+DwCSlb/u9KU1 a9t3thKS+ZDlG1xqzGNzzZa48TCVaH1NcBD5Az/De/G46fj5MSt/nmPBonJHKh8hNu9qACt/gtfvp STxqJIgeYtBhW19qvGf/EppiN+gRv9z++90g+9r9t5rp2CxhjZeNcDiUYzRO10sDir1IBJqPb3ok/ xDzrfmrgdazGWSgN0dy03Y8gM38cdg75QYDKcSDFiiZOXRZBaXpEIx9k4lY2E1hX7XWVYP22eha5G 9ZUUr+Fg==; Received: from j130084.upc-j.chello.nl ([24.132.130.84] helo=noisy.programming.kicks-ass.net) by desiato.infradead.org with esmtpsa (Exim 4.96 #2 (Red Hat Linux)) id 1p7III-00CeDp-35; Mon, 19 Dec 2022 15:43:11 +0000 Received: from hirez.programming.kicks-ass.net (hirez.programming.kicks-ass.net [192.168.1.225]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits)) (Client did not present a certificate) by noisy.programming.kicks-ass.net (Postfix) with ESMTPS id 0DD4F30330E; Mon, 19 Dec 2022 16:43:10 +0100 (CET) Received: by hirez.programming.kicks-ass.net (Postfix, from userid 0) id 8F28420B0F89B; Mon, 19 Dec 2022 16:43:06 +0100 (CET) Message-ID: <20221219154119.352918965@infradead.org> User-Agent: quilt/0.66 Date: Mon, 19 Dec 2022 16:35:33 +0100 From: Peter Zijlstra To: torvalds@linux-foundation.org Cc: corbet@lwn.net, will@kernel.org, peterz@infradead.org, boqun.feng@gmail.com, mark.rutland@arm.com, catalin.marinas@arm.com, dennis@kernel.org, tj@kernel.org, cl@linux.com, hca@linux.ibm.com, gor@linux.ibm.com, agordeev@linux.ibm.com, borntraeger@linux.ibm.com, svens@linux.ibm.com, Herbert Xu , davem@davemloft.net, tglx@linutronix.de, mingo@redhat.com, bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org, hpa@zytor.com, joro@8bytes.org, suravee.suthikulpanit@amd.com, robin.murphy@arm.com, dwmw2@infradead.org, baolu.lu@linux.intel.com, Arnd Bergmann , penberg@kernel.org, rientjes@google.com, iamjoonsoo.kim@lge.com, Andrew Morton , vbabka@suse.cz, roman.gushchin@linux.dev, 42.hyeyoo@gmail.com, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-s390@vger.kernel.org, linux-crypto@vger.kernel.org, iommu@lists.linux.dev, linux-arch@vger.kernel.org Subject: [RFC][PATCH 08/12] s390: Replace cmpxchg_double() with cmpxchg128() References: <20221219153525.632521981@infradead.org> MIME-Version: 1.0 X-Rspamd-Server: rspam07 X-Rspamd-Queue-Id: 9D1E740009 X-Rspam-User: X-Stat-Signature: 5j5iykfksw898j5u4t4gwba56ensmbjd X-HE-Tag: 1671468823-429339 X-HE-Meta: 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 fSSRjr9J wH9o7txDGRulg4SxUclieGx1UgucyP3BTp6aErxFp8iPJqvY= X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: In order to depricate cmpxchg_double(), replace all its usage with cmpxchg128(). Signed-off-by: Peter Zijlstra (Intel) Reported-by: Alexander Gordeev Acked-by: Alexander Gordeev Acked-by: Hendrik Brueckner Signed-off-by: Heiko Carstens --- arch/s390/include/asm/cpu_mf.h | 29 ++++++++++++----- arch/s390/kernel/perf_cpum_sf.c | 65 +++++++++++++++++++++++++--------------- 2 files changed, 63 insertions(+), 31 deletions(-) --- a/arch/s390/include/asm/cpu_mf.h +++ b/arch/s390/include/asm/cpu_mf.h @@ -131,19 +131,32 @@ struct hws_combined_entry { struct hws_diag_entry diag; /* Diagnostic-sampling data entry */ } __packed; +union hws_flags_and_overflow { + struct { + unsigned long flags; + unsigned long overflow; + }; + u128 full; +}; + struct hws_trailer_entry { union { struct { - unsigned int f:1; /* 0 - Block Full Indicator */ - unsigned int a:1; /* 1 - Alert request control */ - unsigned int t:1; /* 2 - Timestamp format */ - unsigned int :29; /* 3 - 31: Reserved */ - unsigned int bsdes:16; /* 32-47: size of basic SDE */ - unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + union { + struct { + unsigned int f:1; /* 0 - Block Full Indicator */ + unsigned int a:1; /* 1 - Alert request control */ + unsigned int t:1; /* 2 - Timestamp format */ + unsigned int :29; /* 3 - 31: Reserved */ + unsigned int bsdes:16; /* 32-47: size of basic SDE */ + unsigned int dsdes:16; /* 48-63: size of diagnostic SDE */ + }; + unsigned long long flags; /* 0 - 63: All indicators */ + }; + unsigned long long overflow; /* 64 - sample Overflow count */ }; - unsigned long long flags; /* 0 - 63: All indicators */ + union hws_flags_and_overflow flags_and_overflow; }; - unsigned long long overflow; /* 64 - sample Overflow count */ unsigned char timestamp[16]; /* 16 - 31 timestamp */ unsigned long long reserved1; /* 32 -Reserved */ unsigned long long reserved2; /* */ --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1227,6 +1227,8 @@ static void hw_collect_samples(struct pe } } +typedef union hws_flags_and_overflow fao_t; + /* hw_perf_event_update() - Process sampling buffer * @event: The perf event * @flush_all: Flag to also flush partially filled sample-data-blocks @@ -1243,10 +1245,11 @@ static void hw_collect_samples(struct pe */ static void hw_perf_event_update(struct perf_event *event, int flush_all) { + unsigned long long event_overflow, sampl_overflow, num_sdb; struct hw_perf_event *hwc = &event->hw; struct hws_trailer_entry *te; + fao_t old_fao, new_fao; unsigned long *sdbt; - unsigned long long event_overflow, sampl_overflow, num_sdb, te_flags; int done; /* @@ -1294,12 +1297,16 @@ static void hw_perf_event_update(struct num_sdb++; /* Reset trailer (using compare-double-and-swap) */ + old_fao = te->flags_and_overflow; do { - te_flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te_flags |= SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - te->flags, te->overflow, - te_flags, 0ULL)); + new_fao = (fao_t){ + .flags = old_fao.flags, + .overflow = 0, + }; + new_fao.flags &= ~SDB_TE_BUFFER_FULL_MASK; + new_fao.flags |= SDB_TE_ALERT_REQ_MASK; + } while (!try_cmpxchg128(&te->flags_and_overflow.full, + &old_fao.full, new_fao.full)); /* Advance to next sample-data-block */ sdbt++; @@ -1475,14 +1482,19 @@ static int aux_output_begin(struct perf_ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; struct hws_trailer_entry *te; + fao_t old_fao, new_fao; te = aux_sdb_trailer(aux, alert_index); + + old_fao = te->flags_and_overflow; do { - orig_flags = te->flags; - *overflow = orig_overflow = te->overflow; - if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { + new_fao = (fao_t){ + .flags = old_fao.flags, + .overflow = 0, + }; + *overflow = old_fao.overflow; + if (new_fao.flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. * Abort and try to set somewhere @@ -1490,10 +1502,11 @@ static bool aux_set_alert(struct aux_buf */ return false; } - new_flags = orig_flags | SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new_fao.flags |= SDB_TE_ALERT_REQ_MASK; + + } while (!try_cmpxchg128(&te->flags_and_overflow.full, + &old_fao.full, new_fao.full)); + return true; } @@ -1522,9 +1535,10 @@ static bool aux_set_alert(struct aux_buf static bool aux_reset_buffer(struct aux_buffer *aux, unsigned long range, unsigned long long *overflow) { - unsigned long long orig_overflow, orig_flags, new_flags; unsigned long i, range_scan, idx, idx_old; + unsigned long long orig_overflow; struct hws_trailer_entry *te; + fao_t old_fao, new_fao; debug_sprintf_event(sfdbg, 6, "%s: range %ld head %ld alert %ld " "empty %ld\n", __func__, range, aux->head, @@ -1554,17 +1568,22 @@ static bool aux_reset_buffer(struct aux_ idx_old = idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); + + old_fao = te->flags_and_overflow; do { - orig_flags = te->flags; - orig_overflow = te->overflow; - new_flags = orig_flags & ~SDB_TE_BUFFER_FULL_MASK; + new_fao = (fao_t){ + .flags = old_fao.flags, + .overflow = 0, + }; + orig_overflow = old_fao.overflow; + new_fao.flags &= ~SDB_TE_BUFFER_FULL_MASK; if (idx == aux->alert_mark) - new_flags |= SDB_TE_ALERT_REQ_MASK; + new_fao.flags |= SDB_TE_ALERT_REQ_MASK; else - new_flags &= ~SDB_TE_ALERT_REQ_MASK; - } while (!cmpxchg_double(&te->flags, &te->overflow, - orig_flags, orig_overflow, - new_flags, 0ULL)); + new_fao.flags &= ~SDB_TE_ALERT_REQ_MASK; + } while (!try_cmpxchg128(&te->flags_and_overflow.full, + &old_fao.full, new_fao.full)); + *overflow += orig_overflow; }