From: "Wang, Xiao W" <xiao.w.wang@intel.com>
To: "Burakov, Anatoly" <anatoly.burakov@intel.com>,
"Yigit, Ferruh" <ferruh.yigit@intel.com>
Cc: "dev@dpdk.org" <dev@dpdk.org>,
"maxime.coquelin@redhat.com" <maxime.coquelin@redhat.com>,
"Wang, Zhihong" <zhihong.wang@intel.com>,
"Bie, Tiwei" <tiwei.bie@intel.com>,
"Tan, Jianfeng" <jianfeng.tan@intel.com>,
"Liang, Cunming" <cunming.liang@intel.com>,
"Daly, Dan" <dan.daly@intel.com>,
"thomas@monjalon.net" <thomas@monjalon.net>,
"Chen, Junjie J" <junjie.j.chen@intel.com>
Subject: Re: [dpdk-dev] [PATCH v7 1/5] vfio: extend data structure for multi container
Date: Mon, 16 Apr 2018 12:22:24 +0000 [thread overview]
Message-ID: <B7F2E978279D1D49A3034B7786DACF406F8997CE@SHSMSX101.ccr.corp.intel.com> (raw)
In-Reply-To: <9f41b581-ea27-51fb-dfbe-affd64d7996c@intel.com>
Hi Anatoly,
> -----Original Message-----
> From: Burakov, Anatoly
> Sent: Monday, April 16, 2018 6:03 PM
> To: Wang, Xiao W <xiao.w.wang@intel.com>; Yigit, Ferruh
> <ferruh.yigit@intel.com>
> Cc: dev@dpdk.org; maxime.coquelin@redhat.com; Wang, Zhihong
> <zhihong.wang@intel.com>; Bie, Tiwei <tiwei.bie@intel.com>; Tan, Jianfeng
> <jianfeng.tan@intel.com>; Liang, Cunming <cunming.liang@intel.com>; Daly,
> Dan <dan.daly@intel.com>; thomas@monjalon.net; Chen, Junjie J
> <junjie.j.chen@intel.com>
> Subject: Re: [PATCH v7 1/5] vfio: extend data structure for multi container
>
> On 15-Apr-18 4:33 PM, Xiao Wang wrote:
> > Currently eal vfio framework binds vfio group fd to the default
> > container fd during rte_vfio_setup_device, while in some cases,
> > e.g. vDPA (vhost data path acceleration), we want to put vfio group
> > to a separate container and program IOMMU via this container.
> >
> > This patch extends the vfio_config structure to contain per-container
> > user_mem_maps and defines an array of vfio_config. The next patch will
> > base on this to add container API.
> >
> > Signed-off-by: Junjie Chen <junjie.j.chen@intel.com>
> > Signed-off-by: Xiao Wang <xiao.w.wang@intel.com>
> > Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
> > Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
> > ---
> > config/common_base | 1 +
> > lib/librte_eal/linuxapp/eal/eal_vfio.c | 407 ++++++++++++++++++++++-------
> ----
> > lib/librte_eal/linuxapp/eal/eal_vfio.h | 19 +-
> > 3 files changed, 275 insertions(+), 152 deletions(-)
> >
> > diff --git a/config/common_base b/config/common_base
> > index c4236fd1f..4a76d2f14 100644
> > --- a/config/common_base
> > +++ b/config/common_base
> > @@ -87,6 +87,7 @@ CONFIG_RTE_EAL_ALWAYS_PANIC_ON_ERROR=n
> > CONFIG_RTE_EAL_IGB_UIO=n
> > CONFIG_RTE_EAL_VFIO=n
> > CONFIG_RTE_MAX_VFIO_GROUPS=64
> > +CONFIG_RTE_MAX_VFIO_CONTAINERS=64
> > CONFIG_RTE_MALLOC_DEBUG=n
> > CONFIG_RTE_EAL_NUMA_AWARE_HUGEPAGES=n
> > CONFIG_RTE_USE_LIBBSD=n
> > diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c
> b/lib/librte_eal/linuxapp/eal/eal_vfio.c
> > index 589d7d478..46fba2d8d 100644
> > --- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
> > +++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
> > @@ -22,8 +22,46 @@
> >
> > #define VFIO_MEM_EVENT_CLB_NAME "vfio_mem_event_clb"
> >
> > +/*
> > + * we don't need to store device fd's anywhere since they can be obtained
> from
> > + * the group fd via an ioctl() call.
> > + */
> > +struct vfio_group {
> > + int group_no;
> > + int fd;
> > + int devices;
> > +};
>
> What is the purpose of moving this into .c file? Seems like an
> unnecessary change.
Yes, we can let vfio_group stay at .h, and move vfio_config into .c
>
> > +
> > +/* hot plug/unplug of VFIO groups may cause all DMA maps to be dropped.
> we can
> > + * recreate the mappings for DPDK segments, but we cannot do so for
> memory that
> > + * was registered by the user themselves, so we need to store the user
> mappings
> > + * somewhere, to recreate them later.
> > + */
> > +#define VFIO_MAX_USER_MEM_MAPS 256
> > +struct user_mem_map {
> > + uint64_t addr;
> > + uint64_t iova;
> > + uint64_t len;
> > +};
> > +
>
> <...>
>
> > +static struct vfio_config *
> > +get_vfio_cfg_by_group_no(int iommu_group_no)
> > +{
> > + struct vfio_config *vfio_cfg;
> > + int i, j;
> > +
> > + for (i = 0; i < VFIO_MAX_CONTAINERS; i++) {
> > + vfio_cfg = &vfio_cfgs[i];
> > + for (j = 0; j < VFIO_MAX_GROUPS; j++) {
> > + if (vfio_cfg->vfio_groups[j].group_no ==
> > + iommu_group_no)
> > + return vfio_cfg;
> > + }
> > + }
> > +
> > + return default_vfio_cfg;
>
> Here and in other places: i'm not sure returning default vfio config if
> group not found is such a good idea. It would be better if calling code
> explicitly handled case of group not existing yet.
Agree. It would be explicit.
>
> > +}
> > +
> > +static struct vfio_config *
> > +get_vfio_cfg_by_group_fd(int vfio_group_fd)
> > +{
> > + struct vfio_config *vfio_cfg;
> > + int i, j;
> > +
> > + for (i = 0; i < VFIO_MAX_CONTAINERS; i++) {
> > + vfio_cfg = &vfio_cfgs[i];
> > + for (j = 0; j < VFIO_MAX_GROUPS; j++)
> > + if (vfio_cfg->vfio_groups[j].fd == vfio_group_fd)
> > + return vfio_cfg;
> > + }
> >
>
> <...>
>
> > - for (i = 0; i < VFIO_MAX_GROUPS; i++) {
> > - vfio_cfg.vfio_groups[i].fd = -1;
> > - vfio_cfg.vfio_groups[i].group_no = -1;
> > - vfio_cfg.vfio_groups[i].devices = 0;
> > + rte_spinlock_recursive_t lock =
> RTE_SPINLOCK_RECURSIVE_INITIALIZER;
> > +
> > + for (i = 0; i < VFIO_MAX_CONTAINERS; i++) {
> > + vfio_cfgs[i].vfio_container_fd = -1;
> > + vfio_cfgs[i].vfio_active_groups = 0;
> > + vfio_cfgs[i].vfio_iommu_type = NULL;
> > + vfio_cfgs[i].mem_maps.lock = lock;
>
> Nitpick - why copy, instead of straight up initializing with
> RTE_SPINLOCK_RECURSIVE_INITIALIZER?
I tried but compiler doesn't allow this assignment.
RTE_SPINLOCK_RECURSIVE_INITIALIZER could only be used for initialization.
Thanks for the comments,
Xiao
next prev parent reply other threads:[~2018-04-16 12:22 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-09 23:08 [dpdk-dev] [PATCH 0/3] add ifcvf driver Xiao Wang
2018-03-09 23:08 ` [dpdk-dev] [PATCH 1/3] eal/vfio: add support for multiple container Xiao Wang
2018-03-14 12:08 ` Burakov, Anatoly
2018-03-15 16:49 ` Wang, Xiao W
2018-03-09 23:08 ` [dpdk-dev] [PATCH 2/3] bus/pci: expose sysfs parsing API Xiao Wang
2018-03-14 11:19 ` Burakov, Anatoly
2018-03-14 13:30 ` Gaëtan Rivet
2018-03-15 16:49 ` Wang, Xiao W
2018-03-15 17:19 ` Gaëtan Rivet
2018-03-19 1:31 ` Wang, Xiao W
2018-03-21 13:21 ` [dpdk-dev] [PATCH v2 0/3] add ifcvf driver Xiao Wang
2018-03-21 13:21 ` [dpdk-dev] [PATCH v2 1/3] eal/vfio: add support for multiple container Xiao Wang
2018-03-21 20:32 ` Thomas Monjalon
2018-03-21 21:37 ` Gaëtan Rivet
2018-03-22 3:00 ` Wang, Xiao W
2018-03-21 13:21 ` [dpdk-dev] [PATCH v2 2/3] bus/pci: expose sysfs parsing API Xiao Wang
2018-03-21 20:44 ` Thomas Monjalon
2018-03-22 2:46 ` Wang, Xiao W
2018-03-21 13:21 ` [dpdk-dev] [PATCH v2 3/3] net/ifcvf: add ifcvf driver Xiao Wang
2018-03-21 20:52 ` Thomas Monjalon
2018-03-23 10:39 ` Wang, Xiao W
2018-03-21 20:57 ` Maxime Coquelin
2018-03-23 10:37 ` Wang, Xiao W
2018-03-22 8:51 ` Ferruh Yigit
2018-03-22 17:23 ` Wang, Xiao W
2018-03-31 2:29 ` [dpdk-dev] [PATCH v3 0/3] add ifcvf vdpa driver Xiao Wang
2018-03-31 2:29 ` [dpdk-dev] [PATCH v3 1/4] eal/vfio: add support for multiple container Xiao Wang
2018-03-31 11:06 ` Maxime Coquelin
2018-03-31 2:29 ` [dpdk-dev] [PATCH v3 2/4] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-03-31 11:13 ` Maxime Coquelin
2018-03-31 13:16 ` Thomas Monjalon
2018-04-02 4:08 ` Wang, Xiao W
2018-03-31 2:29 ` [dpdk-dev] [PATCH v3 3/4] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-03-31 11:26 ` Maxime Coquelin
2018-04-03 9:38 ` Wang, Xiao W
2018-04-04 14:40 ` [dpdk-dev] [PATCH v4 0/4] " Xiao Wang
2018-04-04 14:40 ` [dpdk-dev] [PATCH v4 1/4] eal/vfio: add multiple container support Xiao Wang
2018-04-05 18:06 ` [dpdk-dev] [PATCH v5 0/4] add ifcvf vdpa driver Xiao Wang
2018-04-05 18:06 ` [dpdk-dev] [PATCH v5 1/4] eal/vfio: add multiple container support Xiao Wang
2018-04-05 18:06 ` [dpdk-dev] [PATCH v5 2/4] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-11 18:58 ` Ferruh Yigit
2018-04-05 18:07 ` [dpdk-dev] [PATCH v5 3/4] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-11 18:58 ` Ferruh Yigit
2018-04-12 7:19 ` [dpdk-dev] [PATCH v6 0/4] " Xiao Wang
2018-04-12 7:19 ` [dpdk-dev] [PATCH v6 1/4] eal/vfio: add multiple container support Xiao Wang
2018-04-12 14:03 ` Burakov, Anatoly
2018-04-12 16:07 ` Wang, Xiao W
2018-04-12 16:24 ` Burakov, Anatoly
2018-04-13 9:18 ` Wang, Xiao W
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 0/5] add ifcvf vdpa driver Xiao Wang
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 1/5] vfio: extend data structure for multi container Xiao Wang
2018-04-16 10:02 ` Burakov, Anatoly
2018-04-16 12:22 ` Wang, Xiao W [this message]
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 0/5] add ifcvf vdpa driver Xiao Wang
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 1/5] vfio: extend data structure for multi container Xiao Wang
2018-04-16 15:56 ` Burakov, Anatoly
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 2/5] vfio: add multi container support Xiao Wang
2018-04-16 15:58 ` Burakov, Anatoly
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 0/5] add ifcvf vdpa driver Xiao Wang
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 1/5] vfio: extend data structure for multi container Xiao Wang
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 2/5] vfio: add multi container support Xiao Wang
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 3/5] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 4/5] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-17 7:06 ` [dpdk-dev] [PATCH v9 5/5] doc: add ifcvf driver document and release note Xiao Wang
2018-04-17 11:13 ` [dpdk-dev] [PATCH v9 0/5] add ifcvf vdpa driver Ferruh Yigit
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 3/5] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 4/5] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-16 15:34 ` [dpdk-dev] [PATCH v8 5/5] doc: add ifcvf driver document and release note Xiao Wang
2018-04-16 16:36 ` [dpdk-dev] [PATCH v8 0/5] add ifcvf vdpa driver Ferruh Yigit
2018-04-16 18:07 ` Thomas Monjalon
2018-04-17 5:36 ` Wang, Xiao W
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 2/5] vfio: add multi container support Xiao Wang
2018-04-16 10:03 ` Burakov, Anatoly
2018-04-16 12:44 ` Wang, Xiao W
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 3/5] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 4/5] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-15 15:33 ` [dpdk-dev] [PATCH v7 5/5] doc: add ifcvf driver document and release note Xiao Wang
2018-04-12 7:19 ` [dpdk-dev] [PATCH v6 2/4] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-12 7:19 ` [dpdk-dev] [PATCH v6 3/4] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-12 7:19 ` [dpdk-dev] [PATCH v6 4/4] doc: add ifcvf driver document and release note Xiao Wang
2018-04-05 18:07 ` [dpdk-dev] [PATCH v5 " Xiao Wang
2018-04-11 18:59 ` [dpdk-dev] [PATCH v5 0/4] add ifcvf vdpa driver Ferruh Yigit
2018-04-12 5:47 ` Wang, Xiao W
2018-04-04 14:40 ` [dpdk-dev] [PATCH v4 2/4] net/virtio: skip device probe in vdpa mode Xiao Wang
2018-04-04 14:40 ` [dpdk-dev] [PATCH v4 3/4] net/ifcvf: add ifcvf vdpa driver Xiao Wang
2018-04-04 14:40 ` [dpdk-dev] [PATCH v4 4/4] doc: add ifcvf driver document and release note Xiao Wang
2018-03-31 2:29 ` [dpdk-dev] [PATCH v3 4/4] net/ifcvf: add " Xiao Wang
2018-03-31 11:28 ` Maxime Coquelin
2018-03-09 23:08 ` [dpdk-dev] [PATCH 3/3] net/ifcvf: add ifcvf driver Xiao Wang
2018-03-10 18:23 ` [dpdk-dev] [PATCH 0/3] " Maxime Coquelin
2018-03-15 16:49 ` Wang, Xiao W
2018-03-21 20:47 ` Maxime Coquelin
2018-03-23 10:27 ` Wang, Xiao W
2018-03-25 9:51 ` Maxime Coquelin
2018-03-26 9:05 ` Wang, Xiao W
2018-03-26 13:29 ` Maxime Coquelin
2018-03-27 4:40 ` Wang, Xiao W
2018-03-27 5:09 ` Maxime Coquelin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=B7F2E978279D1D49A3034B7786DACF406F8997CE@SHSMSX101.ccr.corp.intel.com \
--to=xiao.w.wang@intel.com \
--cc=anatoly.burakov@intel.com \
--cc=cunming.liang@intel.com \
--cc=dan.daly@intel.com \
--cc=dev@dpdk.org \
--cc=ferruh.yigit@intel.com \
--cc=jianfeng.tan@intel.com \
--cc=junjie.j.chen@intel.com \
--cc=maxime.coquelin@redhat.com \
--cc=thomas@monjalon.net \
--cc=tiwei.bie@intel.com \
--cc=zhihong.wang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).