From patchwork Tue Apr 16 09:16:51 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Asias He X-Patchwork-Id: 2448461 Return-Path: X-Original-To: patchwork-kvm@patchwork.kernel.org Delivered-To: patchwork-process-083081@patchwork2.kernel.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by patchwork2.kernel.org (Postfix) with ESMTP id 518C1DF230 for ; Tue, 16 Apr 2013 09:17:33 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751403Ab3DPJR3 (ORCPT ); Tue, 16 Apr 2013 05:17:29 -0400 Received: from mx1.redhat.com ([209.132.183.28]:26690 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756303Ab3DPJR1 (ORCPT ); Tue, 16 Apr 2013 05:17:27 -0400 Received: from int-mx11.intmail.prod.int.phx2.redhat.com (int-mx11.intmail.prod.int.phx2.redhat.com [10.5.11.24]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id r3G9HOoe019948 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Tue, 16 Apr 2013 05:17:24 -0400 Received: from hj.localdomain.com ([10.66.4.126]) by int-mx11.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id r3G9H4WF012163; Tue, 16 Apr 2013 05:17:17 -0400 From: Asias He To: Nicholas Bellinger Cc: Paolo Bonzini , Stefan Hajnoczi , "Michael S. Tsirkin" , Rusty Russell , kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, target-devel@vger.kernel.org, Asias He Subject: [PATCH v5 2/2] tcm_vhost: Wait for pending requests in vhost_scsi_flush() Date: Tue, 16 Apr 2013 17:16:51 +0800 Message-Id: <1366103811-21887-3-git-send-email-asias@redhat.com> In-Reply-To: <1366103811-21887-1-git-send-email-asias@redhat.com> References: <1366103811-21887-1-git-send-email-asias@redhat.com> In-Reply-To: <1365823754-27730-1-git-send-email-asias@redhat.com> References: <1365823754-27730-1-git-send-email-asias@redhat.com> X-Scanned-By: MIMEDefang 2.68 on 10.5.11.24 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org This patch makes vhost_scsi_flush() wait for all the pending requests issued before the flush operation to be finished. Changes in v5: - Use kref and completion - Fail req if vs->vs_inflight is NULL - Rename tcm_vhost_alloc_inflight to tcm_vhost_set_inflight Changes in v4: - Introduce vhost_scsi_inflight - Drop array to track flush - Use RCU to protect vs_inflight explicitly Changes in v3: - Rebase - Drop 'tcm_vhost: Wait for pending requests in vhost_scsi_clear_endpoint()' in this series, we already did that in 'tcm_vhost: Use vq->private_data to indicate if the endpoint is setup' Changes in v2: - Increase/Decrease inflight requests in vhost_scsi_{allocate,free}_cmd and tcm_vhost_{allocate,free}_evt Signed-off-by: Asias He --- drivers/vhost/tcm_vhost.c | 101 +++++++++++++++++++++++++++++++++++++++++++--- drivers/vhost/tcm_vhost.h | 5 +++ 2 files changed, 101 insertions(+), 5 deletions(-) diff --git a/drivers/vhost/tcm_vhost.c b/drivers/vhost/tcm_vhost.c index 4ae6725..ef40a8f 100644 --- a/drivers/vhost/tcm_vhost.c +++ b/drivers/vhost/tcm_vhost.c @@ -74,6 +74,11 @@ enum { #define VHOST_SCSI_MAX_VQ 128 #define VHOST_SCSI_MAX_EVENT 128 +struct vhost_scsi_inflight { + struct completion comp; /* Wait for the flush operation to finish */ + struct kref kref; /* Refcount for the inflight reqs */ +}; + struct vhost_scsi { /* Protected by vhost_scsi->dev.mutex */ struct tcm_vhost_tpg **vs_tpg; @@ -91,6 +96,8 @@ struct vhost_scsi { struct mutex vs_events_lock; /* protect vs_events_dropped,events_nr */ bool vs_events_dropped; /* any missed events */ int vs_events_nr; /* num of pending events */ + + struct vhost_scsi_inflight __rcu *vs_inflight; /* track inflight reqs */ }; /* Local pointer to allocated TCM configfs fabric module */ @@ -108,6 +115,51 @@ static int iov_num_pages(struct iovec *iov) ((unsigned long)iov->iov_base & PAGE_MASK)) >> PAGE_SHIFT; } +static int tcm_vhost_set_inflight(struct vhost_scsi *vs) +{ + struct vhost_scsi_inflight *inflight; + int ret = -ENOMEM; + + inflight = kzalloc(sizeof(*inflight), GFP_KERNEL); + if (inflight) { + kref_init(&inflight->kref); + init_completion(&inflight->comp); + ret = 0; + } + rcu_assign_pointer(vs->vs_inflight, inflight); + synchronize_rcu(); + + return ret; +} + +static struct vhost_scsi_inflight * +tcm_vhost_inc_inflight(struct vhost_scsi *vs) +{ + struct vhost_scsi_inflight *inflight; + + rcu_read_lock(); + inflight = rcu_dereference(vs->vs_inflight); + if (inflight) + kref_get(&inflight->kref); + rcu_read_unlock(); + + return inflight; +} + +void tcm_vhost_done_inflight(struct kref *kref) +{ + struct vhost_scsi_inflight *inflight; + + inflight = container_of(kref, struct vhost_scsi_inflight, kref); + complete(&inflight->comp); +} + +static void tcm_vhost_dec_inflight(struct vhost_scsi_inflight *inflight) +{ + if (inflight) + kref_put(&inflight->kref, tcm_vhost_done_inflight); +} + static bool tcm_vhost_check_feature(struct vhost_scsi *vs, int feature) { bool ret = false; @@ -402,6 +454,7 @@ static int tcm_vhost_queue_tm_rsp(struct se_cmd *se_cmd) static void tcm_vhost_free_evt(struct vhost_scsi *vs, struct tcm_vhost_evt *evt) { mutex_lock(&vs->vs_events_lock); + tcm_vhost_dec_inflight(evt->inflight); vs->vs_events_nr--; kfree(evt); mutex_unlock(&vs->vs_events_lock); @@ -413,21 +466,27 @@ static struct tcm_vhost_evt *tcm_vhost_allocate_evt(struct vhost_scsi *vs, struct tcm_vhost_evt *evt; mutex_lock(&vs->vs_events_lock); - if (vs->vs_events_nr > VHOST_SCSI_MAX_EVENT) { - vs->vs_events_dropped = true; - mutex_unlock(&vs->vs_events_lock); - return NULL; - } + if (vs->vs_events_nr > VHOST_SCSI_MAX_EVENT) + goto out; evt = kzalloc(sizeof(*evt), GFP_KERNEL); if (evt) { evt->event.event = event; evt->event.reason = reason; + evt->inflight = tcm_vhost_inc_inflight(vs); + if (!evt->inflight) { + kfree(evt); + goto out; + } vs->vs_events_nr++; } mutex_unlock(&vs->vs_events_lock); return evt; +out: + vs->vs_events_dropped = true; + mutex_unlock(&vs->vs_events_lock); + return NULL; } static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *tv_cmd) @@ -445,6 +504,8 @@ static void vhost_scsi_free_cmd(struct tcm_vhost_cmd *tv_cmd) kfree(tv_cmd->tvc_sgl); } + tcm_vhost_dec_inflight(tv_cmd->inflight); + kfree(tv_cmd); } @@ -595,6 +656,9 @@ static struct tcm_vhost_cmd *vhost_scsi_allocate_cmd( tv_cmd->tvc_data_direction = data_direction; tv_cmd->tvc_nexus = tv_nexus; tv_cmd->tvc_vhost = vs; + tv_cmd->inflight = tcm_vhost_inc_inflight(vs); + if (!tv_cmd->inflight) + return ERR_PTR(-ENOMEM); return tv_cmd; } @@ -982,12 +1046,35 @@ static void vhost_scsi_flush_vq(struct vhost_scsi *vs, int index) static void vhost_scsi_flush(struct vhost_scsi *vs) { + struct vhost_scsi_inflight *inflight; int i; + /* inflight points to the old inflight */ + inflight = rcu_dereference_protected(vs->vs_inflight, + lockdep_is_held(&vs->dev.mutex)); + + /* Allocate a new inflight and make vs->vs_inflight points to it */ + if (tcm_vhost_set_inflight(vs) < 0) + pr_warn("vhost_scsi_flush failed to allocate inflight\n"); + + /* + * The inflight->kref was initialized to 1. We decrement it here to + * indicate the start of the flush operation so that it will reach 0 + * when all the reqs are finished. + */ + kref_put(&inflight->kref, tcm_vhost_done_inflight); + + /* Flush both the vhost poll and vhost work */ for (i = 0; i < VHOST_SCSI_MAX_VQ; i++) vhost_scsi_flush_vq(vs, i); vhost_work_flush(&vs->dev, &vs->vs_completion_work); vhost_work_flush(&vs->dev, &vs->vs_event_work); + + /* Wait for all reqs issued before the flush to be finished */ + if (inflight) { + wait_for_completion(&inflight->comp); + kfree(inflight); + } } /* @@ -1196,6 +1283,9 @@ static int vhost_scsi_open(struct inode *inode, struct file *f) s->vs_events_dropped = false; mutex_init(&s->vs_events_lock); + if (tcm_vhost_set_inflight(s) < 0) + return -ENOMEM; + s->vqs[VHOST_SCSI_VQ_CTL].handle_kick = vhost_scsi_ctl_handle_kick; s->vqs[VHOST_SCSI_VQ_EVT].handle_kick = vhost_scsi_evt_handle_kick; for (i = VHOST_SCSI_VQ_IO; i < VHOST_SCSI_MAX_VQ; i++) @@ -1221,6 +1311,7 @@ static int vhost_scsi_release(struct inode *inode, struct file *f) vhost_scsi_clear_endpoint(s, &t); vhost_dev_stop(&s->dev); vhost_dev_cleanup(&s->dev, false); + kfree(s->vs_inflight); kfree(s); return 0; } diff --git a/drivers/vhost/tcm_vhost.h b/drivers/vhost/tcm_vhost.h index 94e9ee53..7567767 100644 --- a/drivers/vhost/tcm_vhost.h +++ b/drivers/vhost/tcm_vhost.h @@ -2,6 +2,7 @@ #define TCM_VHOST_NAMELEN 256 #define TCM_VHOST_MAX_CDB_SIZE 32 +struct vhost_scsi_inflight; struct tcm_vhost_cmd { /* Descriptor from vhost_get_vq_desc() for virt_queue segment */ int tvc_vq_desc; @@ -37,6 +38,8 @@ struct tcm_vhost_cmd { unsigned char tvc_sense_buf[TRANSPORT_SENSE_BUFFER]; /* Completed commands list, serviced from vhost worker thread */ struct llist_node tvc_completion_list; + /* Used to track inflight req */ + struct vhost_scsi_inflight *inflight; }; struct tcm_vhost_nexus { @@ -91,6 +94,8 @@ struct tcm_vhost_evt { struct virtio_scsi_event event; /* virtio_scsi event list, serviced from vhost worker thread */ struct llist_node list; + /* Used to track inflight req */ + struct vhost_scsi_inflight *inflight; }; /*