From: Laurent Vivier <lvivier@redhat.com>
To: passt-dev@passt.top
Cc: Laurent Vivier <lvivier@redhat.com>
Subject: [PATCH 21/24] vhost-user: use guest buffer directly in vu_handle_tx()
Date: Fri, 2 Feb 2024 15:11:48 +0100 [thread overview]
Message-ID: <20240202141151.3762941-22-lvivier@redhat.com> (raw)
In-Reply-To: <20240202141151.3762941-1-lvivier@redhat.com>
Check the buffer address is correctly in the mmap'ed memory.
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
---
packet.c | 6 +++++
packet.h | 2 ++
tap.c | 39 +++++++++++++++++++++++++++----
tap.h | 1 +
vhost_user.c | 66 ++++++++++++++++++++++++++++++++--------------------
5 files changed, 84 insertions(+), 30 deletions(-)
diff --git a/packet.c b/packet.c
index af2a539a1794..3c5fc39df6d7 100644
--- a/packet.c
+++ b/packet.c
@@ -25,6 +25,12 @@
static int packet_check_range(const struct pool *p, size_t offset, size_t len,
const char *start, const char *func, int line)
{
+ ASSERT(p->buf);
+
+ if (p->buf_size == 0)
+ return vu_packet_check_range((void *)p->buf, offset, len, start,
+ func, line);
+
if (start < p->buf) {
if (func) {
trace("add packet start %p before buffer start %p, "
diff --git a/packet.h b/packet.h
index 8377dcf678bb..0aec6d9410aa 100644
--- a/packet.h
+++ b/packet.h
@@ -22,6 +22,8 @@ struct pool {
struct iovec pkt[1];
};
+int vu_packet_check_range(void *buf, size_t offset, size_t len,
+ const char *start, const char *func, int line);
void packet_add_do(struct pool *p, size_t len, const char *start,
const char *func, int line);
void *packet_get_do(const struct pool *p, const size_t idx,
diff --git a/tap.c b/tap.c
index c2a917bc00ca..930e48689497 100644
--- a/tap.c
+++ b/tap.c
@@ -626,7 +626,7 @@ resume:
if (!eh)
continue;
if (ntohs(eh->h_proto) == ETH_P_ARP) {
- PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));
+ PACKET_POOL_P(pkt, 1, in->buf, in->buf_size);
packet_add(pkt, l2_len, (char *)eh);
arp(c, pkt);
@@ -656,7 +656,7 @@ resume:
continue;
if (iph->protocol == IPPROTO_ICMP) {
- PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));
+ PACKET_POOL_P(pkt, 1, in->buf, in->buf_size);
if (c->no_icmp)
continue;
@@ -675,7 +675,7 @@ resume:
continue;
if (iph->protocol == IPPROTO_UDP) {
- PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));
+ PACKET_POOL_P(pkt, 1, in->buf, in->buf_size);
packet_add(pkt, l2_len, (char *)eh);
if (dhcp(c, pkt))
@@ -815,7 +815,7 @@ resume:
}
if (proto == IPPROTO_ICMPV6) {
- PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));
+ PACKET_POOL_P(pkt, 1, in->buf, in->buf_size);
if (c->no_icmp)
continue;
@@ -839,7 +839,7 @@ resume:
uh = (struct udphdr *)l4h;
if (proto == IPPROTO_UDP) {
- PACKET_POOL_P(pkt, 1, in->buf, sizeof(pkt_buf));
+ PACKET_POOL_P(pkt, 1, in->buf, in->buf_size);
packet_add(pkt, l4_len, l4h);
@@ -1291,6 +1291,23 @@ static void tap_sock_tun_init(struct ctx *c)
epoll_ctl(c->epollfd, EPOLL_CTL_ADD, c->fd_tap, &ev);
}
+void tap_sock_update_buf(void *base, size_t size)
+{
+ int i;
+
+ pool_tap4_storage.buf = base;
+ pool_tap4_storage.buf_size = size;
+ pool_tap6_storage.buf = base;
+ pool_tap6_storage.buf_size = size;
+
+ for (i = 0; i < TAP_SEQS; i++) {
+ tap4_l4[i].p.buf = base;
+ tap4_l4[i].p.buf_size = size;
+ tap6_l4[i].p.buf = base;
+ tap6_l4[i].p.buf_size = size;
+ }
+}
+
/**
* tap_sock_init() - Create and set up AF_UNIX socket or tuntap file descriptor
* @c: Execution context
@@ -1302,10 +1319,22 @@ void tap_sock_init(struct ctx *c)
pool_tap4_storage = PACKET_INIT(pool_tap4, TAP_MSGS, pkt_buf, sz);
pool_tap6_storage = PACKET_INIT(pool_tap6, TAP_MSGS, pkt_buf, sz);
+ if (c->mode == MODE_VU) {
+ pool_tap4_storage.buf = NULL;
+ pool_tap4_storage.buf_size = 0;
+ pool_tap6_storage.buf = NULL;
+ pool_tap6_storage.buf_size = 0;
+ }
for (i = 0; i < TAP_SEQS; i++) {
tap4_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz);
tap6_l4[i].p = PACKET_INIT(pool_l4, UIO_MAXIOV, pkt_buf, sz);
+ if (c->mode == MODE_VU) {
+ tap4_l4[i].p.buf = NULL;
+ tap4_l4[i].p.buf_size = 0;
+ tap6_l4[i].p.buf = NULL;
+ tap6_l4[i].p.buf_size = 0;
+ }
}
if (c->fd_tap != -1) { /* Passed as --fd */
diff --git a/tap.h b/tap.h
index ee839d4f09dc..6823c9b32313 100644
--- a/tap.h
+++ b/tap.h
@@ -82,6 +82,7 @@ void tap_handler_pasta(struct ctx *c, uint32_t events,
void tap_handler_passt(struct ctx *c, uint32_t events,
const struct timespec *now);
void tap_sock_reset(struct ctx *c);
+void tap_sock_update_buf(void *base, size_t size);
void tap_sock_init(struct ctx *c);
void pool_flush_all(void);
void tap_handler_all(struct ctx *c, const struct timespec *now);
diff --git a/vhost_user.c b/vhost_user.c
index 2acd72398e3a..9cc07c8312c0 100644
--- a/vhost_user.c
+++ b/vhost_user.c
@@ -334,6 +334,25 @@ static bool map_ring(VuDev *vdev, VuVirtq *vq)
return !(vq->vring.desc && vq->vring.used && vq->vring.avail);
}
+int vu_packet_check_range(void *buf, size_t offset, size_t len, const char *start,
+ const char *func, int line)
+{
+ VuDevRegion *dev_region;
+
+ for (dev_region = buf; dev_region->mmap_addr; dev_region++) {
+ if ((char *)dev_region->mmap_addr <= start &&
+ start + offset + len < (char *)dev_region->mmap_addr +
+ dev_region->mmap_offset +
+ dev_region->size)
+ return 0;
+ }
+ if (func) {
+ trace("cannot find region, %s:%i", func, line);
+ }
+
+ return -1;
+}
+
/*
* #syscalls:passt mmap munmap
*/
@@ -400,6 +419,12 @@ static bool vu_set_mem_table_exec(VuDev *vdev,
}
}
+ /* XXX */
+ ASSERT(vdev->nregions < VHOST_USER_MAX_RAM_SLOTS - 1);
+ vdev->regions[vdev->nregions].mmap_addr = 0; /* mark EOF for vu_packet_check_range() */
+
+ tap_sock_update_buf(vdev->regions, 0);
+
return false;
}
@@ -650,8 +675,8 @@ static void vu_handle_tx(VuDev *vdev, int index)
VuVirtq *vq = &vdev->vq[index];
int hdrlen = vdev->hdrlen;
struct timespec now;
- char *p;
- size_t n;
+ unsigned int indexes[VIRTQUEUE_MAX_SIZE];
+ int count;
if (index % 2 != VHOST_USER_TX_QUEUE) {
debug("index %d is not an TX queue", index);
@@ -660,14 +685,11 @@ static void vu_handle_tx(VuDev *vdev, int index)
clock_gettime(CLOCK_MONOTONIC, &now);
- p = pkt_buf;
-
pool_flush_all();
+ count = 0;
while (1) {
VuVirtqElement *elem;
- unsigned int out_num;
- struct iovec sg[VIRTQUEUE_MAX_SIZE], *out_sg;
ASSERT(index == VHOST_USER_TX_QUEUE);
elem = vu_queue_pop(vdev, vq, sizeof(VuVirtqElement), buffer[index]);
@@ -675,32 +697,26 @@ static void vu_handle_tx(VuDev *vdev, int index)
break;
}
- out_num = elem->out_num;
- out_sg = elem->out_sg;
- if (out_num < 1) {
+ if (elem->out_num < 1) {
debug("virtio-net header not in first element");
break;
}
+ ASSERT(elem->out_num == 1);
- if (hdrlen) {
- unsigned sg_num;
-
- sg_num = iov_copy(sg, ARRAY_SIZE(sg), out_sg, out_num,
- hdrlen, -1);
- out_num = sg_num;
- out_sg = sg;
- }
-
- n = iov_to_buf(out_sg, out_num, 0, p, TAP_BUF_FILL);
-
- packet_add_all(c, n, p);
-
- p += n;
+ packet_add_all(c, elem->out_sg[0].iov_len - hdrlen,
+ (char *)elem->out_sg[0].iov_base + hdrlen);
+ indexes[count] = elem->index;
+ count++;
+ }
+ tap_handler_all(c, &now);
- vu_queue_push(vdev, vq, elem, 0);
+ if (count) {
+ int i;
+ for (i = 0; i < count; i++)
+ vu_queue_fill_by_index(vdev, vq, indexes[i], 0, i);
+ vu_queue_flush(vdev, vq, count);
vu_queue_notify(vdev, vq);
}
- tap_handler_all(c, &now);
}
void vu_kick_cb(struct ctx *c, union epoll_ref ref)
--
@@ -334,6 +334,25 @@ static bool map_ring(VuDev *vdev, VuVirtq *vq)
return !(vq->vring.desc && vq->vring.used && vq->vring.avail);
}
+int vu_packet_check_range(void *buf, size_t offset, size_t len, const char *start,
+ const char *func, int line)
+{
+ VuDevRegion *dev_region;
+
+ for (dev_region = buf; dev_region->mmap_addr; dev_region++) {
+ if ((char *)dev_region->mmap_addr <= start &&
+ start + offset + len < (char *)dev_region->mmap_addr +
+ dev_region->mmap_offset +
+ dev_region->size)
+ return 0;
+ }
+ if (func) {
+ trace("cannot find region, %s:%i", func, line);
+ }
+
+ return -1;
+}
+
/*
* #syscalls:passt mmap munmap
*/
@@ -400,6 +419,12 @@ static bool vu_set_mem_table_exec(VuDev *vdev,
}
}
+ /* XXX */
+ ASSERT(vdev->nregions < VHOST_USER_MAX_RAM_SLOTS - 1);
+ vdev->regions[vdev->nregions].mmap_addr = 0; /* mark EOF for vu_packet_check_range() */
+
+ tap_sock_update_buf(vdev->regions, 0);
+
return false;
}
@@ -650,8 +675,8 @@ static void vu_handle_tx(VuDev *vdev, int index)
VuVirtq *vq = &vdev->vq[index];
int hdrlen = vdev->hdrlen;
struct timespec now;
- char *p;
- size_t n;
+ unsigned int indexes[VIRTQUEUE_MAX_SIZE];
+ int count;
if (index % 2 != VHOST_USER_TX_QUEUE) {
debug("index %d is not an TX queue", index);
@@ -660,14 +685,11 @@ static void vu_handle_tx(VuDev *vdev, int index)
clock_gettime(CLOCK_MONOTONIC, &now);
- p = pkt_buf;
-
pool_flush_all();
+ count = 0;
while (1) {
VuVirtqElement *elem;
- unsigned int out_num;
- struct iovec sg[VIRTQUEUE_MAX_SIZE], *out_sg;
ASSERT(index == VHOST_USER_TX_QUEUE);
elem = vu_queue_pop(vdev, vq, sizeof(VuVirtqElement), buffer[index]);
@@ -675,32 +697,26 @@ static void vu_handle_tx(VuDev *vdev, int index)
break;
}
- out_num = elem->out_num;
- out_sg = elem->out_sg;
- if (out_num < 1) {
+ if (elem->out_num < 1) {
debug("virtio-net header not in first element");
break;
}
+ ASSERT(elem->out_num == 1);
- if (hdrlen) {
- unsigned sg_num;
-
- sg_num = iov_copy(sg, ARRAY_SIZE(sg), out_sg, out_num,
- hdrlen, -1);
- out_num = sg_num;
- out_sg = sg;
- }
-
- n = iov_to_buf(out_sg, out_num, 0, p, TAP_BUF_FILL);
-
- packet_add_all(c, n, p);
-
- p += n;
+ packet_add_all(c, elem->out_sg[0].iov_len - hdrlen,
+ (char *)elem->out_sg[0].iov_base + hdrlen);
+ indexes[count] = elem->index;
+ count++;
+ }
+ tap_handler_all(c, &now);
- vu_queue_push(vdev, vq, elem, 0);
+ if (count) {
+ int i;
+ for (i = 0; i < count; i++)
+ vu_queue_fill_by_index(vdev, vq, indexes[i], 0, i);
+ vu_queue_flush(vdev, vq, count);
vu_queue_notify(vdev, vq);
}
- tap_handler_all(c, &now);
}
void vu_kick_cb(struct ctx *c, union epoll_ref ref)
--
2.42.0
next prev parent reply other threads:[~2024-02-02 14:11 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-02-02 14:11 [PATCH 00/24] Add vhost-user support to passt Laurent Vivier
2024-02-02 14:11 ` [PATCH 01/24] iov: add some functions to manage iovec Laurent Vivier
2024-02-05 5:57 ` David Gibson
2024-02-06 14:28 ` Laurent Vivier
2024-02-07 1:01 ` David Gibson
2024-02-07 10:00 ` Laurent Vivier
2024-02-06 16:10 ` Stefano Brivio
2024-02-07 14:02 ` Laurent Vivier
2024-02-07 14:57 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 02/24] pcap: add pcap_iov() Laurent Vivier
2024-02-05 6:25 ` David Gibson
2024-02-06 16:10 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 03/24] checksum: align buffers Laurent Vivier
2024-02-05 6:02 ` David Gibson
2024-02-07 9:01 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 04/24] checksum: add csum_iov() Laurent Vivier
2024-02-05 6:07 ` David Gibson
2024-02-07 9:02 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 05/24] util: move IP stuff from util.[ch] to ip.[ch] Laurent Vivier
2024-02-05 6:13 ` David Gibson
2024-02-07 9:03 ` Stefano Brivio
2024-02-08 0:04 ` David Gibson
2024-02-02 14:11 ` [PATCH 06/24] ip: move duplicate IPv4 checksum function to ip.h Laurent Vivier
2024-02-05 6:16 ` David Gibson
2024-02-07 10:40 ` Stefano Brivio
2024-02-07 23:43 ` David Gibson
2024-02-02 14:11 ` [PATCH 07/24] ip: introduce functions to compute the header part checksum for TCP/UDP Laurent Vivier
2024-02-05 6:20 ` David Gibson
2024-02-07 10:41 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 08/24] tcp: extract buffer management from tcp_send_flag() Laurent Vivier
2024-02-06 0:24 ` David Gibson
2024-02-08 16:57 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 09/24] tcp: extract buffer management from tcp_conn_tap_mss() Laurent Vivier
2024-02-06 0:47 ` David Gibson
2024-02-08 16:59 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 10/24] tcp: rename functions that manage buffers Laurent Vivier
2024-02-06 1:48 ` David Gibson
2024-02-08 17:10 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 11/24] tcp: move buffers management functions to their own file Laurent Vivier
2024-02-02 14:11 ` [PATCH 12/24] tap: make tap_update_mac() generic Laurent Vivier
2024-02-06 1:49 ` David Gibson
2024-02-08 17:10 ` Stefano Brivio
2024-02-09 5:02 ` David Gibson
2024-02-02 14:11 ` [PATCH 13/24] tap: export pool_flush()/tapX_handler()/packet_add() Laurent Vivier
2024-02-02 14:29 ` Laurent Vivier
2024-02-06 1:52 ` David Gibson
2024-02-11 23:15 ` Stefano Brivio
2024-02-12 2:22 ` David Gibson
2024-02-02 14:11 ` [PATCH 14/24] udp: move udpX_l2_buf_t and udpX_l2_mh_sock out of udp_update_hdrX() Laurent Vivier
2024-02-06 1:59 ` David Gibson
2024-02-11 23:16 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 15/24] udp: rename udp_sock_handler() to udp_buf_sock_handler() Laurent Vivier
2024-02-06 2:14 ` David Gibson
2024-02-11 23:17 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 16/24] packet: replace struct desc by struct iovec Laurent Vivier
2024-02-06 2:25 ` David Gibson
2024-02-11 23:18 ` Stefano Brivio
2024-02-02 14:11 ` [PATCH 17/24] vhost-user: compare mode MODE_PASTA and not MODE_PASST Laurent Vivier
2024-02-06 2:29 ` David Gibson
2024-02-02 14:11 ` [PATCH 18/24] vhost-user: introduce virtio API Laurent Vivier
2024-02-06 3:51 ` David Gibson
2024-02-11 23:18 ` Stefano Brivio
2024-02-12 2:26 ` David Gibson
2024-02-02 14:11 ` [PATCH 19/24] vhost-user: introduce vhost-user API Laurent Vivier
2024-02-07 2:13 ` David Gibson
2024-02-02 14:11 ` [PATCH 20/24] vhost-user: add vhost-user Laurent Vivier
2024-02-07 2:40 ` David Gibson
2024-02-11 23:19 ` Stefano Brivio
2024-02-12 2:47 ` David Gibson
2024-02-13 15:22 ` Stefano Brivio
2024-02-14 2:05 ` David Gibson
2024-02-11 23:19 ` Stefano Brivio
2024-02-12 2:49 ` David Gibson
2024-02-12 10:02 ` Laurent Vivier
2024-02-12 16:56 ` Stefano Brivio
2024-02-02 14:11 ` Laurent Vivier [this message]
2024-02-09 4:26 ` [PATCH 21/24] vhost-user: use guest buffer directly in vu_handle_tx() David Gibson
2024-02-02 14:11 ` [PATCH 22/24] tcp: vhost-user RX nocopy Laurent Vivier
2024-02-09 4:57 ` David Gibson
2024-02-02 14:11 ` [PATCH 23/24] udp: " Laurent Vivier
2024-02-09 5:00 ` David Gibson
2024-02-02 14:11 ` [PATCH 24/24] vhost-user: remove tap_send_frames_vu() Laurent Vivier
2024-02-09 5:01 ` David Gibson
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=20240202141151.3762941-22-lvivier@redhat.com \
--to=lvivier@redhat.com \
--cc=passt-dev@passt.top \
/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.
Code repositories for project(s) associated with this public inbox
https://passt.top/passt
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 IMAP folder(s).