From nobody Fri Nov 14 20:43:47 2025 Delivered-To: importer@patchew.org Authentication-Results: mx.zohomail.com; dkim=fail; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com ARC-Seal: i=1; a=rsa-sha256; t=1589908550; cv=none; d=zohomail.com; s=zohoarc; b=T1q4mKt0GwJEilPCb5vV5dGpIFHRSb6Yg1qqLsdWL4M8qf6cTLur28BCG1NGBqibvtimXJjlT9aappYgl+ro11POjJ6vSmWvOSHbfRqHWB6QycaWqtxaxB2mDyZAsFvkM6MbJKjIk9nDmmZDNMmFltm8IPQ91TkVogXsnglvlgU= ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=zohomail.com; s=zohoarc; t=1589908550; h=Content-Type:Content-Transfer-Encoding:Cc:Date:From:In-Reply-To:List-Subscribe:List-Post:List-Id:List-Archive:List-Help:List-Unsubscribe:MIME-Version:Message-ID:References:Sender:Subject:To; bh=gK+3NhfsKlN8RgvfVxbtX56OFKu6ouTjsvZ5gcQ+1uA=; b=VWm2vf7en50zU+9BqQJqrX+5WMIq9EDIUZMx0ud55/Qo5vEzgwEvR9UklpN+yQZiT41Vq3tCXq6JzwW8zHJnMWDdYGP5ykCOBumkp3T2aaUlUGYER2sdf8rOcp/knb4jkXGbqfOWo16H+Eooebe6CkFPVdDr8SBnxZ395wBCCzI= ARC-Authentication-Results: i=1; mx.zohomail.com; dkim=fail; spf=pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail header.from= (p=none dis=none) header.from= Return-Path: Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) by mx.zohomail.com with SMTPS id 1589908550015663.9325402858902; Tue, 19 May 2020 10:15:50 -0700 (PDT) Received: from localhost ([::1]:54726 helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1jb5qH-0000ga-6w for importer@patchew.org; Tue, 19 May 2020 13:15:49 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]:34304) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1jb5mc-00034K-RA for qemu-devel@nongnu.org; Tue, 19 May 2020 13:12:02 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:46398 helo=us-smtp-1.mimecast.com) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_CBC_SHA1:256) (Exim 4.90_1) (envelope-from ) id 1jb5mb-0002Zw-1v for qemu-devel@nongnu.org; Tue, 19 May 2020 13:12:02 -0400 Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-13-4pVnU1JIP6mM4idJJZc23Q-1; Tue, 19 May 2020 13:11:58 -0400 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.phx2.redhat.com [10.5.11.14]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 7E9FD464; Tue, 19 May 2020 17:11:57 +0000 (UTC) Received: from localhost (ovpn-114-215.ams2.redhat.com [10.36.114.215]) by smtp.corp.redhat.com (Postfix) with ESMTP id 329485D9C5; Tue, 19 May 2020 17:11:54 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1589908320; h=from:from: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:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=gK+3NhfsKlN8RgvfVxbtX56OFKu6ouTjsvZ5gcQ+1uA=; b=ZgEOj6hKwVADEuLTGdFcs8G7NbkgbkwLXr1OhagImape192yTnviagJ7IFdjZZlLWUdhN8 ymeAQ7jhTnGf/ThpJLPOU6Wrx0om2oHi8gVgFsLmLk08stYTJCBnwsGSfPsPicAbVKLaWm G2ppidhyPa/2O3VCQz3Qpa8E58a0uKM= X-MC-Unique: 4pVnU1JIP6mM4idJJZc23Q-1 From: Stefan Hajnoczi To: qemu-devel@nongnu.org Subject: [PATCH 4/7] block/nvme: switch to a NVMeRequest freelist Date: Tue, 19 May 2020 18:11:35 +0100 Message-Id: <20200519171138.201667-5-stefanha@redhat.com> In-Reply-To: <20200519171138.201667-1-stefanha@redhat.com> References: <20200519171138.201667-1-stefanha@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.14 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: quoted-printable Received-SPF: pass (zohomail.com: domain of gnu.org designates 209.51.188.17 as permitted sender) client-ip=209.51.188.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Received-SPF: pass client-ip=207.211.31.81; envelope-from=stefanha@redhat.com; helo=us-smtp-1.mimecast.com X-detected-operating-system: by eggs.gnu.org: First seen = 2020/05/19 00:34:39 X-ACL-Warn: Detected OS = Linux 2.2.x-3.x [generic] [fuzzy] X-Spam_score_int: -3 X-Spam_score: -0.4 X-Spam_bar: / X-Spam_report: (-0.4 / 5.0 requ) BAYES_00=-1.9, DKIMWL_WL_HIGH=0.001, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, MIME_BASE64_TEXT=1.741, RCVD_IN_DNSWL_NONE=-0.0001, RCVD_IN_MSPIKE_H4=0.001, RCVD_IN_MSPIKE_WL=0.001, SPF_PASS=-0.001 autolearn=_AUTOLEARN X-Spam_action: no action X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.23 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Kevin Wolf , Fam Zheng , qemu-block@nongnu.org, Max Reitz , Stefan Hajnoczi , =?UTF-8?q?Philippe=20Mathieu-Daud=C3=A9?= Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail-DKIM: fail (Header signature does not verify) Content-Type: text/plain; charset="utf-8" There are three issues with the current NVMeRequest->busy field: 1. The busy field is accidentally accessed outside q->lock when request submission fails. 2. Waiters on free_req_queue are not woken when a request is returned early due to submission failure. 2. Finding a free request involves scanning all requests. This makes request submission O(n^2). Switch to an O(1) freelist that is always accessed under the lock. Also differentiate between NVME_QUEUE_SIZE, the actual SQ/CQ size, and NVME_NUM_REQS, the number of usable requests. This makes the code simpler than using NVME_QUEUE_SIZE everywhere and having to keep in mind that one slot is reserved. Signed-off-by: Stefan Hajnoczi Reviewed-by: Sergio Lopez --- block/nvme.c | 81 ++++++++++++++++++++++++++++++++++------------------ 1 file changed, 54 insertions(+), 27 deletions(-) diff --git a/block/nvme.c b/block/nvme.c index 6bf58bc6aa..3ad4f27e1c 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -33,6 +33,12 @@ #define NVME_QUEUE_SIZE 128 #define NVME_BAR_SIZE 8192 =20 +/* + * We have to leave one slot empty as that is the full queue case where + * head =3D=3D tail + 1. + */ +#define NVME_NUM_REQS (NVME_QUEUE_SIZE - 1) + typedef struct { int32_t head, tail; uint8_t *queue; @@ -47,7 +53,7 @@ typedef struct { int cid; void *prp_list_page; uint64_t prp_list_iova; - bool busy; + int free_req_next; /* q->reqs[] index of next free req */ } NVMeRequest; =20 typedef struct { @@ -61,7 +67,8 @@ typedef struct { /* Fields protected by @lock */ NVMeQueue sq, cq; int cq_phase; - NVMeRequest reqs[NVME_QUEUE_SIZE]; + int free_req_head; + NVMeRequest reqs[NVME_NUM_REQS]; bool busy; int need_kick; int inflight; @@ -200,19 +207,23 @@ static NVMeQueuePair *nvme_create_queue_pair(BlockDri= verState *bs, qemu_mutex_init(&q->lock); q->index =3D idx; qemu_co_queue_init(&q->free_req_queue); - q->prp_list_pages =3D qemu_blockalign0(bs, s->page_size * NVME_QUEUE_S= IZE); + q->prp_list_pages =3D qemu_blockalign0(bs, s->page_size * NVME_NUM_REQ= S); r =3D qemu_vfio_dma_map(s->vfio, q->prp_list_pages, - s->page_size * NVME_QUEUE_SIZE, + s->page_size * NVME_NUM_REQS, false, &prp_list_iova); if (r) { goto fail; } - for (i =3D 0; i < NVME_QUEUE_SIZE; i++) { + q->free_req_head =3D -1; + for (i =3D 0; i < NVME_NUM_REQS; i++) { NVMeRequest *req =3D &q->reqs[i]; req->cid =3D i + 1; + req->free_req_next =3D q->free_req_head; + q->free_req_head =3D i; req->prp_list_page =3D q->prp_list_pages + i * s->page_size; req->prp_list_iova =3D prp_list_iova + i * s->page_size; } + nvme_init_queue(bs, &q->sq, size, NVME_SQ_ENTRY_BYTES, &local_err); if (local_err) { error_propagate(errp, local_err); @@ -254,13 +265,11 @@ static void nvme_kick(BDRVNVMeState *s, NVMeQueuePair= *q) */ static NVMeRequest *nvme_get_free_req(NVMeQueuePair *q) { - int i; - NVMeRequest *req =3D NULL; + NVMeRequest *req; =20 qemu_mutex_lock(&q->lock); - while (q->inflight + q->need_kick > NVME_QUEUE_SIZE - 2) { - /* We have to leave one slot empty as that is the full queue case = (head - * =3D=3D tail + 1). */ + + while (q->free_req_head =3D=3D -1) { if (qemu_in_coroutine()) { trace_nvme_free_req_queue_wait(q); qemu_co_queue_wait(&q->free_req_queue, &q->lock); @@ -269,20 +278,41 @@ static NVMeRequest *nvme_get_free_req(NVMeQueuePair *= q) return NULL; } } - for (i =3D 0; i < NVME_QUEUE_SIZE; i++) { - if (!q->reqs[i].busy) { - q->reqs[i].busy =3D true; - req =3D &q->reqs[i]; - break; - } - } - /* We have checked inflight and need_kick while holding q->lock, so one - * free req must be available. */ - assert(req); + + req =3D &q->reqs[q->free_req_head]; + q->free_req_head =3D req->free_req_next; + req->free_req_next =3D -1; + qemu_mutex_unlock(&q->lock); return req; } =20 +/* With q->lock */ +static void nvme_put_free_req_locked(NVMeQueuePair *q, NVMeRequest *req) +{ + req->free_req_next =3D q->free_req_head; + q->free_req_head =3D req - q->reqs; +} + +/* With q->lock */ +static void nvme_wake_free_req_locked(BDRVNVMeState *s, NVMeQueuePair *q) +{ + if (!qemu_co_queue_empty(&q->free_req_queue)) { + replay_bh_schedule_oneshot_event(s->aio_context, + nvme_free_req_queue_cb, q); + } +} + +/* Insert a request in the freelist and wake waiters */ +static void nvme_put_free_req_and_wake(BDRVNVMeState *s, NVMeQueuePair *q, + NVMeRequest *req) +{ + qemu_mutex_lock(&q->lock); + nvme_put_free_req_locked(q, req); + nvme_wake_free_req_locked(s, q); + qemu_mutex_unlock(&q->lock); +} + static inline int nvme_translate_error(const NvmeCqe *c) { uint16_t status =3D (le16_to_cpu(c->status) >> 1) & 0xFF; @@ -344,7 +374,7 @@ static bool nvme_process_completion(BDRVNVMeState *s, N= VMeQueuePair *q) req =3D *preq; assert(req.cid =3D=3D cid); assert(req.cb); - preq->busy =3D false; + nvme_put_free_req_locked(q, preq); preq->cb =3D preq->opaque =3D NULL; qemu_mutex_unlock(&q->lock); req.cb(req.opaque, ret); @@ -356,10 +386,7 @@ static bool nvme_process_completion(BDRVNVMeState *s, = NVMeQueuePair *q) /* Notify the device so it can post more completions. */ smp_mb_release(); *q->cq.doorbell =3D cpu_to_le32(q->cq.head); - if (!qemu_co_queue_empty(&q->free_req_queue)) { - replay_bh_schedule_oneshot_event(s->aio_context, - nvme_free_req_queue_cb, q); - } + nvme_wake_free_req_locked(s, q); } q->busy =3D false; return progress; @@ -1001,7 +1028,7 @@ static coroutine_fn int nvme_co_prw_aligned(BlockDriv= erState *bs, r =3D nvme_cmd_map_qiov(bs, &cmd, req, qiov); qemu_co_mutex_unlock(&s->dma_map_lock); if (r) { - req->busy =3D false; + nvme_put_free_req_and_wake(s, ioq, req); return r; } nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data); @@ -1218,7 +1245,7 @@ static int coroutine_fn nvme_co_pdiscard(BlockDriverS= tate *bs, qemu_co_mutex_unlock(&s->dma_map_lock); =20 if (ret) { - req->busy =3D false; + nvme_put_free_req_and_wake(s, ioq, req); goto out; } =20 --=20 2.25.3