Message ID | 20230331154259.1447831-6-maxime.coquelin@redhat.com (mailing list archive) |
---|---|
State | Superseded, archived |
Delegated to: | Maxime Coquelin |
Headers |
Return-Path: <dev-bounces@dpdk.org> X-Original-To: patchwork@inbox.dpdk.org Delivered-To: patchwork@inbox.dpdk.org Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 20E3342887; Fri, 31 Mar 2023 17:43:53 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id A28BF42D69; Fri, 31 Mar 2023 17:43:26 +0200 (CEST) Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) by mails.dpdk.org (Postfix) with ESMTP id E60EB42D62 for <dev@dpdk.org>; Fri, 31 Mar 2023 17:43:23 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1680277403; 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=DzI2mzfZqWy/oUf+X58/CEpCAfnbfcJJtVS9mWXswDg=; b=hXdhlYaewLnQ3q/1I775nErLqoMX+q9c6y3ZXBPm4PBR7pE5vSN6kYuVsKoda3MixADV6D wEIqyw3LNgiyfdtvYwpvdB8NIaInpBzHzEaZ7zPRZIV7bTPZttEymxlc1ONSELkoP12omR PEHtU+I02nFEo10rm75Oh8I3aEdqa1Q= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-488-NLRI65qmPlOSiqIGlFJ7MA-1; Fri, 31 Mar 2023 11:43:19 -0400 X-MC-Unique: NLRI65qmPlOSiqIGlFJ7MA-1 Received: from smtp.corp.redhat.com (int-mx04.intmail.prod.int.rdu2.redhat.com [10.11.54.4]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id BDCDC85A588; Fri, 31 Mar 2023 15:43:18 +0000 (UTC) Received: from max-t490s.redhat.com (unknown [10.39.208.6]) by smtp.corp.redhat.com (Postfix) with ESMTP id 868242027040; Fri, 31 Mar 2023 15:43:16 +0000 (UTC) From: Maxime Coquelin <maxime.coquelin@redhat.com> To: dev@dpdk.org, david.marchand@redhat.com, chenbo.xia@intel.com, mkp@redhat.com, fbl@redhat.com, jasowang@redhat.com, cunming.liang@intel.com, xieyongji@bytedance.com, echaudro@redhat.com, eperezma@redhat.com, amorenoz@redhat.com Cc: Maxime Coquelin <maxime.coquelin@redhat.com> Subject: [RFC 05/27] vhost: add helper for IOTLB entries shared page check Date: Fri, 31 Mar 2023 17:42:37 +0200 Message-Id: <20230331154259.1447831-6-maxime.coquelin@redhat.com> In-Reply-To: <20230331154259.1447831-1-maxime.coquelin@redhat.com> References: <20230331154259.1447831-1-maxime.coquelin@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.1 on 10.11.54.4 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset="US-ASCII"; x-default=true X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions <dev.dpdk.org> List-Unsubscribe: <https://mails.dpdk.org/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://mails.dpdk.org/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <https://mails.dpdk.org/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> Errors-To: dev-bounces@dpdk.org |
Series |
Add VDUSE support to Vhost library
|
|
Commit Message
Maxime Coquelin
March 31, 2023, 3:42 p.m. UTC
This patch introduces a helper to check whether two IOTLB
entries share a page.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
---
lib/vhost/iotlb.c | 25 ++++++++++++++++++++-----
1 file changed, 20 insertions(+), 5 deletions(-)
Comments
Hi Maxime, On Fri, Mar 31, 2023 at 11:43 AM Maxime Coquelin <maxime.coquelin@redhat.com> wrote: > > This patch introduces a helper to check whether two IOTLB > entries share a page. > > Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> > --- > lib/vhost/iotlb.c | 25 ++++++++++++++++++++----- > 1 file changed, 20 insertions(+), 5 deletions(-) > > diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c > index e8f1cb661e..d919f74704 100644 > --- a/lib/vhost/iotlb.c > +++ b/lib/vhost/iotlb.c > @@ -23,6 +23,23 @@ struct vhost_iotlb_entry { > > #define IOTLB_CACHE_SIZE 2048 > > +static bool > +vhost_user_iotlb_share_page(struct vhost_iotlb_entry *a, struct vhost_iotlb_entry *b, > + uint64_t align) > +{ > + uint64_t a_end, b_start; > + > + if (a == NULL || b == NULL) > + return false; > + > + /* Assumes entry a lower than entry b */ > + RTE_ASSERT(a->uaddr < b->uaddr); > + a_end = RTE_ALIGN_CEIL(a->uaddr + a->size, align); > + b_start = RTE_ALIGN_FLOOR(b->uaddr, align); > + > + return a_end > b_start; This may be a very minor detail, but it might improve readability if the a_end calculation used addr + size - 1 and the return conditional used >=. Cheers, M > +} > + > static void > vhost_user_iotlb_set_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node) > { > @@ -37,16 +54,14 @@ static void > vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node, > struct vhost_iotlb_entry *prev, struct vhost_iotlb_entry *next) > { > - uint64_t align, mask; > + uint64_t align; > > align = hua_to_alignment(dev->mem, (void *)(uintptr_t)node->uaddr); > - mask = ~(align - 1); > > /* Don't disable coredump if the previous node is in the same page */ > - if (prev == NULL || (node->uaddr & mask) != ((prev->uaddr + prev->size - 1) & mask)) { > + if (!vhost_user_iotlb_share_page(prev, node, align)) { > /* Don't disable coredump if the next node is in the same page */ > - if (next == NULL || > - ((node->uaddr + node->size - 1) & mask) != (next->uaddr & mask)) > + if (!vhost_user_iotlb_share_page(node, next, align)) > mem_set_dump((void *)(uintptr_t)node->uaddr, node->size, false, align); > } > } > -- > 2.39.2 >
Hi Mike, On 4/17/23 21:39, Mike Pattrick wrote: > Hi Maxime, > > On Fri, Mar 31, 2023 at 11:43 AM Maxime Coquelin > <maxime.coquelin@redhat.com> wrote: >> >> This patch introduces a helper to check whether two IOTLB >> entries share a page. >> >> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> >> --- >> lib/vhost/iotlb.c | 25 ++++++++++++++++++++----- >> 1 file changed, 20 insertions(+), 5 deletions(-) >> >> diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c >> index e8f1cb661e..d919f74704 100644 >> --- a/lib/vhost/iotlb.c >> +++ b/lib/vhost/iotlb.c >> @@ -23,6 +23,23 @@ struct vhost_iotlb_entry { >> >> #define IOTLB_CACHE_SIZE 2048 >> >> +static bool >> +vhost_user_iotlb_share_page(struct vhost_iotlb_entry *a, struct vhost_iotlb_entry *b, >> + uint64_t align) >> +{ >> + uint64_t a_end, b_start; >> + >> + if (a == NULL || b == NULL) >> + return false; >> + >> + /* Assumes entry a lower than entry b */ >> + RTE_ASSERT(a->uaddr < b->uaddr); >> + a_end = RTE_ALIGN_CEIL(a->uaddr + a->size, align); >> + b_start = RTE_ALIGN_FLOOR(b->uaddr, align); >> + >> + return a_end > b_start; > > This may be a very minor detail, but it might improve readability if > the a_end calculation used addr + size - 1 and the return conditional > used >=. That's actually how I initially implemented it, but discussing with David we agreed it would be better that way for consistency with vhost_user_iotlb_clear_dump(). Regards, Maxime > > Cheers, > M > > >> +} >> + >> static void >> vhost_user_iotlb_set_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node) >> { >> @@ -37,16 +54,14 @@ static void >> vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node, >> struct vhost_iotlb_entry *prev, struct vhost_iotlb_entry *next) >> { >> - uint64_t align, mask; >> + uint64_t align; >> >> align = hua_to_alignment(dev->mem, (void *)(uintptr_t)node->uaddr); >> - mask = ~(align - 1); >> >> /* Don't disable coredump if the previous node is in the same page */ >> - if (prev == NULL || (node->uaddr & mask) != ((prev->uaddr + prev->size - 1) & mask)) { >> + if (!vhost_user_iotlb_share_page(prev, node, align)) { >> /* Don't disable coredump if the next node is in the same page */ >> - if (next == NULL || >> - ((node->uaddr + node->size - 1) & mask) != (next->uaddr & mask)) >> + if (!vhost_user_iotlb_share_page(node, next, align)) >> mem_set_dump((void *)(uintptr_t)node->uaddr, node->size, false, align); >> } >> } >> -- >> 2.39.2 >> >
On Wed, Apr 19, 2023 at 5:35 AM Maxime Coquelin <maxime.coquelin@redhat.com> wrote: > > Hi Mike, > > On 4/17/23 21:39, Mike Pattrick wrote: > > Hi Maxime, > > > > On Fri, Mar 31, 2023 at 11:43 AM Maxime Coquelin > > <maxime.coquelin@redhat.com> wrote: > >> > >> This patch introduces a helper to check whether two IOTLB > >> entries share a page. > >> > >> Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> > >> --- > >> lib/vhost/iotlb.c | 25 ++++++++++++++++++++----- > >> 1 file changed, 20 insertions(+), 5 deletions(-) > >> > >> diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c > >> index e8f1cb661e..d919f74704 100644 > >> --- a/lib/vhost/iotlb.c > >> +++ b/lib/vhost/iotlb.c > >> @@ -23,6 +23,23 @@ struct vhost_iotlb_entry { > >> > >> #define IOTLB_CACHE_SIZE 2048 > >> > >> +static bool > >> +vhost_user_iotlb_share_page(struct vhost_iotlb_entry *a, struct vhost_iotlb_entry *b, > >> + uint64_t align) > >> +{ > >> + uint64_t a_end, b_start; > >> + > >> + if (a == NULL || b == NULL) > >> + return false; > >> + > >> + /* Assumes entry a lower than entry b */ > >> + RTE_ASSERT(a->uaddr < b->uaddr); > >> + a_end = RTE_ALIGN_CEIL(a->uaddr + a->size, align); > >> + b_start = RTE_ALIGN_FLOOR(b->uaddr, align); > >> + > >> + return a_end > b_start; > > > > This may be a very minor detail, but it might improve readability if > > the a_end calculation used addr + size - 1 and the return conditional > > used >=. > > That's actually how I initially implemented it, but discussing with > David we agreed it would be better that way for consistency with > vhost_user_iotlb_clear_dump(). I can get behind consistency. Acked-by: Mike Pattrick <mkp@redhat.com> > > Regards, > Maxime > > > > > Cheers, > > M > > > > > >> +} > >> + > >> static void > >> vhost_user_iotlb_set_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node) > >> { > >> @@ -37,16 +54,14 @@ static void > >> vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node, > >> struct vhost_iotlb_entry *prev, struct vhost_iotlb_entry *next) > >> { > >> - uint64_t align, mask; > >> + uint64_t align; > >> > >> align = hua_to_alignment(dev->mem, (void *)(uintptr_t)node->uaddr); > >> - mask = ~(align - 1); > >> > >> /* Don't disable coredump if the previous node is in the same page */ > >> - if (prev == NULL || (node->uaddr & mask) != ((prev->uaddr + prev->size - 1) & mask)) { > >> + if (!vhost_user_iotlb_share_page(prev, node, align)) { > >> /* Don't disable coredump if the next node is in the same page */ > >> - if (next == NULL || > >> - ((node->uaddr + node->size - 1) & mask) != (next->uaddr & mask)) > >> + if (!vhost_user_iotlb_share_page(node, next, align)) > >> mem_set_dump((void *)(uintptr_t)node->uaddr, node->size, false, align); > >> } > >> } > >> -- > >> 2.39.2 > >> > > >
> -----Original Message----- > From: Maxime Coquelin <maxime.coquelin@redhat.com> > Sent: Friday, March 31, 2023 11:43 PM > To: dev@dpdk.org; david.marchand@redhat.com; Xia, Chenbo > <chenbo.xia@intel.com>; mkp@redhat.com; fbl@redhat.com; > jasowang@redhat.com; Liang, Cunming <cunming.liang@intel.com>; Xie, Yongji > <xieyongji@bytedance.com>; echaudro@redhat.com; eperezma@redhat.com; > amorenoz@redhat.com > Cc: Maxime Coquelin <maxime.coquelin@redhat.com> > Subject: [RFC 05/27] vhost: add helper for IOTLB entries shared page check > > This patch introduces a helper to check whether two IOTLB > entries share a page. > > Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com> > --- > lib/vhost/iotlb.c | 25 ++++++++++++++++++++----- > 1 file changed, 20 insertions(+), 5 deletions(-) > > diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c > index e8f1cb661e..d919f74704 100644 > --- a/lib/vhost/iotlb.c > +++ b/lib/vhost/iotlb.c > @@ -23,6 +23,23 @@ struct vhost_iotlb_entry { > > #define IOTLB_CACHE_SIZE 2048 > > +static bool > +vhost_user_iotlb_share_page(struct vhost_iotlb_entry *a, struct > vhost_iotlb_entry *b, > + uint64_t align) > +{ > + uint64_t a_end, b_start; > + > + if (a == NULL || b == NULL) > + return false; > + > + /* Assumes entry a lower than entry b */ > + RTE_ASSERT(a->uaddr < b->uaddr); > + a_end = RTE_ALIGN_CEIL(a->uaddr + a->size, align); > + b_start = RTE_ALIGN_FLOOR(b->uaddr, align); > + > + return a_end > b_start; > +} > + > static void > vhost_user_iotlb_set_dump(struct virtio_net *dev, struct > vhost_iotlb_entry *node) > { > @@ -37,16 +54,14 @@ static void > vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct > vhost_iotlb_entry *node, > struct vhost_iotlb_entry *prev, struct vhost_iotlb_entry *next) > { > - uint64_t align, mask; > + uint64_t align; > > align = hua_to_alignment(dev->mem, (void *)(uintptr_t)node->uaddr); > - mask = ~(align - 1); > > /* Don't disable coredump if the previous node is in the same page > */ > - if (prev == NULL || (node->uaddr & mask) != ((prev->uaddr + prev- > >size - 1) & mask)) { > + if (!vhost_user_iotlb_share_page(prev, node, align)) { > /* Don't disable coredump if the next node is in the same page > */ > - if (next == NULL || > - ((node->uaddr + node->size - 1) & mask) != (next- > >uaddr & mask)) > + if (!vhost_user_iotlb_share_page(node, next, align)) > mem_set_dump((void *)(uintptr_t)node->uaddr, node->size, > false, align); > } > } > -- > 2.39.2 Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
diff --git a/lib/vhost/iotlb.c b/lib/vhost/iotlb.c index e8f1cb661e..d919f74704 100644 --- a/lib/vhost/iotlb.c +++ b/lib/vhost/iotlb.c @@ -23,6 +23,23 @@ struct vhost_iotlb_entry { #define IOTLB_CACHE_SIZE 2048 +static bool +vhost_user_iotlb_share_page(struct vhost_iotlb_entry *a, struct vhost_iotlb_entry *b, + uint64_t align) +{ + uint64_t a_end, b_start; + + if (a == NULL || b == NULL) + return false; + + /* Assumes entry a lower than entry b */ + RTE_ASSERT(a->uaddr < b->uaddr); + a_end = RTE_ALIGN_CEIL(a->uaddr + a->size, align); + b_start = RTE_ALIGN_FLOOR(b->uaddr, align); + + return a_end > b_start; +} + static void vhost_user_iotlb_set_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node) { @@ -37,16 +54,14 @@ static void vhost_user_iotlb_clear_dump(struct virtio_net *dev, struct vhost_iotlb_entry *node, struct vhost_iotlb_entry *prev, struct vhost_iotlb_entry *next) { - uint64_t align, mask; + uint64_t align; align = hua_to_alignment(dev->mem, (void *)(uintptr_t)node->uaddr); - mask = ~(align - 1); /* Don't disable coredump if the previous node is in the same page */ - if (prev == NULL || (node->uaddr & mask) != ((prev->uaddr + prev->size - 1) & mask)) { + if (!vhost_user_iotlb_share_page(prev, node, align)) { /* Don't disable coredump if the next node is in the same page */ - if (next == NULL || - ((node->uaddr + node->size - 1) & mask) != (next->uaddr & mask)) + if (!vhost_user_iotlb_share_page(node, next, align)) mem_set_dump((void *)(uintptr_t)node->uaddr, node->size, false, align); } }