From: Jason Wang <jasowang@redhat.com>
To: mst@redhat.com, jasowang@redhat.com, kvm@vger.kernel.org,
virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Jintack Lim <jintack@cs.columbia.edu>
Subject: [PATCH net 4/4] vhost: log dirty page correctly
Date: Mon, 10 Dec 2018 17:44:54 +0800 [thread overview]
Message-ID: <20181210094454.21144-5-jasowang@redhat.com> (raw)
In-Reply-To: <20181210094454.21144-1-jasowang@redhat.com>
Vhost dirty page logging API is designed to sync through GPA. But we
try to log GIOVA when device IOTLB is enabled. This is wrong and may
lead to missing data after migration.
To solve this issue, when logging with device IOTLB enabled, we will:
1) reuse the device IOTLB translation result of GIOVA->HVA mapping to
get HVA, for writable descriptor, get HVA through iovec. For used
ring update, translate its GIOVA to HVA
2) traverse the GPA->HVA mapping to get the possible GPA and log
through GPA. Pay attention this reverse mapping is not guaranteed
to be unique, so we should log each possible GPA in this case.
This fix the failure of scp to guest during migration. In -next, we
will probably support passing GIOVA->GPA instead of GIOVA->HVA.
Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Reported-by: Jintack Lim <jintack@cs.columbia.edu>
Cc: Jintack Lim <jintack@cs.columbia.edu>
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 3 +-
drivers/vhost/vhost.c | 78 +++++++++++++++++++++++++++++++++++--------
drivers/vhost/vhost.h | 3 +-
3 files changed, 68 insertions(+), 16 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5f272ab4d5b4..754ca22efb43 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1196,7 +1196,8 @@ static void handle_rx(struct vhost_net *net)
if (nvq->done_idx > VHOST_NET_BATCH)
vhost_net_signal_used(nvq);
if (unlikely(vq_log))
- vhost_log_write(vq, vq_log, log, vhost_len);
+ vhost_log_write(vq, vq_log, log, vhost_len,
+ vq->iov, in);
total_len += vhost_len;
if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
vhost_poll_queue(&vq->poll);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 55e5aa662ad5..8ab279720a2b 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1733,11 +1733,66 @@ static int log_write(void __user *log_base,
return r;
}
+static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
+{
+ struct vhost_umem *umem = vq->umem;
+ struct vhost_umem_node *u;
+ u64 gpa;
+ int r;
+ bool hit = false;
+
+ list_for_each_entry(u, &umem->umem_list, link) {
+ if (u->userspace_addr < hva &&
+ u->userspace_addr + u->size >=
+ hva + len) {
+ gpa = u->start + hva - u->userspace_addr;
+ r = log_write(vq->log_base, gpa, len);
+ if (r < 0)
+ return r;
+ hit = true;
+ }
+ }
+
+ /* No reverse mapping, should be a bug */
+ WARN_ON(!hit);
+ return 0;
+}
+
+static void log_used(struct vhost_virtqueue *vq, u64 used_offset, u64 len)
+{
+ struct iovec iov[64];
+ int i, ret;
+
+ if (!vq->iotlb) {
+ log_write(vq->log_base, vq->log_addr + used_offset, len);
+ return;
+ }
+
+ ret = translate_desc(vq, (u64)vq->used + used_offset, len, iov, 64,
+ VHOST_ACCESS_WO);
+ WARN_ON(ret < 0);
+
+ for (i = 0; i < ret; i++) {
+ ret = log_write_hva(vq, (u64)iov[i].iov_base, iov[i].iov_len);
+ WARN_ON(ret);
+ }
+}
+
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
- unsigned int log_num, u64 len)
+ unsigned int log_num, u64 len, struct iovec *iov, int count)
{
int i, r;
+ if (vq->iotlb) {
+ for (i = 0; i < count; i++) {
+ r = log_write_hva(vq, (u64)iov[i].iov_base,
+ iov[i].iov_len);
+ if (r < 0)
+ return r;
+ }
+ return 0;
+ }
+
/* Make sure data written is seen before log. */
smp_wmb();
for (i = 0; i < log_num; ++i) {
@@ -1769,9 +1824,8 @@ static int vhost_update_used_flags(struct vhost_virtqueue *vq)
smp_wmb();
/* Log used flag write. */
used = &vq->used->flags;
- log_write(vq->log_base, vq->log_addr +
- (used - (void __user *)vq->used),
- sizeof vq->used->flags);
+ log_used(vq, (used - (void __user *)vq->used),
+ sizeof vq->used->flags);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
@@ -1789,9 +1843,8 @@ static int vhost_update_avail_event(struct vhost_virtqueue *vq, u16 avail_event)
smp_wmb();
/* Log avail event write */
used = vhost_avail_event(vq);
- log_write(vq->log_base, vq->log_addr +
- (used - (void __user *)vq->used),
- sizeof *vhost_avail_event(vq));
+ log_used(vq, (used - (void __user *)vq->used),
+ sizeof *vhost_avail_event(vq));
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
@@ -2191,10 +2244,8 @@ static int __vhost_add_used_n(struct vhost_virtqueue *vq,
/* Make sure data is seen before log. */
smp_wmb();
/* Log used ring entry write. */
- log_write(vq->log_base,
- vq->log_addr +
- ((void __user *)used - (void __user *)vq->used),
- count * sizeof *used);
+ log_used(vq, ((void __user *)used - (void __user *)vq->used),
+ count * sizeof *used);
}
old = vq->last_used_idx;
new = (vq->last_used_idx += count);
@@ -2236,9 +2287,8 @@ int vhost_add_used_n(struct vhost_virtqueue *vq, struct vring_used_elem *heads,
/* Make sure used idx is seen before log. */
smp_wmb();
/* Log used index update. */
- log_write(vq->log_base,
- vq->log_addr + offsetof(struct vring_used, idx),
- sizeof vq->used->idx);
+ log_used(vq, offsetof(struct vring_used, idx),
+ sizeof vq->used->idx);
if (vq->log_ctx)
eventfd_signal(vq->log_ctx, 1);
}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 466ef7542291..1b675dad5e05 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -205,7 +205,8 @@ bool vhost_vq_avail_empty(struct vhost_dev *, struct vhost_virtqueue *);
bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
- unsigned int log_num, u64 len);
+ unsigned int log_num, u64 len,
+ struct iovec *iov, int count);
int vq_iotlb_prefetch(struct vhost_virtqueue *vq);
struct vhost_msg_node *vhost_new_msg(struct vhost_virtqueue *vq, int type);
--
2.17.1
next prev parent reply other threads:[~2018-12-10 9:45 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-10 9:44 [PATCH net 0/4] Fix various issue of vhost Jason Wang
2018-12-10 9:44 ` [PATCH net 1/4] vhost: make sure used idx is seen before log in vhost_add_used_n() Jason Wang
2018-12-10 9:44 ` [PATCH net 2/4] vhost_net: rework on the lock ordering for busy polling Jason Wang
2018-12-11 1:34 ` Michael S. Tsirkin
2018-12-11 3:06 ` Jason Wang
2018-12-11 4:04 ` Michael S. Tsirkin
2018-12-12 3:03 ` Jason Wang
2018-12-12 3:40 ` Michael S. Tsirkin
2018-12-10 9:44 ` [PATCH net 3/4] Revert "net: vhost: lock the vqs one by one" Jason Wang
2018-12-10 9:44 ` Jason Wang [this message]
2018-12-10 15:14 ` [PATCH net 4/4] vhost: log dirty page correctly kbuild test robot
2018-12-11 1:30 ` Michael S. Tsirkin
2018-12-19 17:29 ` kbuild test robot
2018-12-10 19:47 ` [PATCH net 0/4] Fix various issue of vhost David Miller
2018-12-11 3:01 ` Jason Wang
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=20181210094454.21144-5-jasowang@redhat.com \
--to=jasowang@redhat.com \
--cc=jintack@cs.columbia.edu \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=virtualization@lists.linux-foundation.org \
/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).