Commit c9b47cc1 authored by Magnus Karlsson's avatar Magnus Karlsson Committed by Daniel Borkmann

xsk: fix bug when trying to use both copy and zero-copy on one queue id

Previously, the xsk code did not record which umem was bound to a
specific queue id. This was not required if all drivers were zero-copy
enabled as this had to be recorded in the driver anyway. So if a user
tried to bind two umems to the same queue, the driver would say
no. But if copy-mode was first enabled and then zero-copy mode (or the
reverse order), we mistakenly enabled both of them on the same umem
leading to buggy behavior. The main culprit for this is that we did
not store the association of umem to queue id in the copy case and
only relied on the driver reporting this. As this relation was not
stored in the driver for copy mode (it does not rely on the AF_XDP
NDOs), this obviously could not work.

This patch fixes the problem by always recording the umem to queue id
relationship in the netdev_queue and netdev_rx_queue structs. This way
we always know what kind of umem has been bound to a queue id and can
act appropriately at bind time.
Signed-off-by: default avatarMagnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
parent 661b8d1b
...@@ -42,27 +42,47 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) ...@@ -42,27 +42,47 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
} }
} }
int xdp_umem_query(struct net_device *dev, u16 queue_id) /* The umem is stored both in the _rx struct and the _tx struct as we do
* not know if the device has more tx queues than rx, or the opposite.
* This might also change during run time.
*/
static void xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
u16 queue_id)
{ {
struct netdev_bpf bpf; if (queue_id < dev->real_num_rx_queues)
dev->_rx[queue_id].umem = umem;
if (queue_id < dev->real_num_tx_queues)
dev->_tx[queue_id].umem = umem;
}
ASSERT_RTNL(); static struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
u16 queue_id)
{
if (queue_id < dev->real_num_rx_queues)
return dev->_rx[queue_id].umem;
if (queue_id < dev->real_num_tx_queues)
return dev->_tx[queue_id].umem;
memset(&bpf, 0, sizeof(bpf)); return NULL;
bpf.command = XDP_QUERY_XSK_UMEM; }
bpf.xsk.queue_id = queue_id;
if (!dev->netdev_ops->ndo_bpf) static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
return 0; {
return dev->netdev_ops->ndo_bpf(dev, &bpf) ?: !!bpf.xsk.umem; /* Zero out the entry independent on how many queues are configured
* at this point in time, as it might be used in the future.
*/
if (queue_id < dev->num_rx_queues)
dev->_rx[queue_id].umem = NULL;
if (queue_id < dev->num_tx_queues)
dev->_tx[queue_id].umem = NULL;
} }
int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
u32 queue_id, u16 flags) u16 queue_id, u16 flags)
{ {
bool force_zc, force_copy; bool force_zc, force_copy;
struct netdev_bpf bpf; struct netdev_bpf bpf;
int err; int err = 0;
force_zc = flags & XDP_ZEROCOPY; force_zc = flags & XDP_ZEROCOPY;
force_copy = flags & XDP_COPY; force_copy = flags & XDP_COPY;
...@@ -70,17 +90,23 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, ...@@ -70,17 +90,23 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
if (force_zc && force_copy) if (force_zc && force_copy)
return -EINVAL; return -EINVAL;
if (force_copy) rtnl_lock();
return 0; if (xdp_get_umem_from_qid(dev, queue_id)) {
err = -EBUSY;
goto out_rtnl_unlock;
}
if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) xdp_reg_umem_at_qid(dev, umem, queue_id);
return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ umem->dev = dev;
umem->queue_id = queue_id;
if (force_copy)
/* For copy-mode, we are done. */
goto out_rtnl_unlock;
rtnl_lock(); if (!dev->netdev_ops->ndo_bpf ||
err = xdp_umem_query(dev, queue_id); !dev->netdev_ops->ndo_xsk_async_xmit) {
if (err) { err = -EOPNOTSUPP;
err = err < 0 ? -EOPNOTSUPP : -EBUSY; goto err_unreg_umem;
goto err_rtnl_unlock;
} }
bpf.command = XDP_SETUP_XSK_UMEM; bpf.command = XDP_SETUP_XSK_UMEM;
...@@ -89,18 +115,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, ...@@ -89,18 +115,20 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
err = dev->netdev_ops->ndo_bpf(dev, &bpf); err = dev->netdev_ops->ndo_bpf(dev, &bpf);
if (err) if (err)
goto err_rtnl_unlock; goto err_unreg_umem;
rtnl_unlock(); rtnl_unlock();
dev_hold(dev); dev_hold(dev);
umem->dev = dev;
umem->queue_id = queue_id;
umem->zc = true; umem->zc = true;
return 0; return 0;
err_rtnl_unlock: err_unreg_umem:
xdp_clear_umem_at_qid(dev, queue_id);
if (!force_zc)
err = 0; /* fallback to copy mode */
out_rtnl_unlock:
rtnl_unlock(); rtnl_unlock();
return force_zc ? err : 0; /* fail or fallback */ return err;
} }
static void xdp_umem_clear_dev(struct xdp_umem *umem) static void xdp_umem_clear_dev(struct xdp_umem *umem)
...@@ -108,7 +136,7 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem) ...@@ -108,7 +136,7 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem)
struct netdev_bpf bpf; struct netdev_bpf bpf;
int err; int err;
if (umem->dev) { if (umem->zc) {
bpf.command = XDP_SETUP_XSK_UMEM; bpf.command = XDP_SETUP_XSK_UMEM;
bpf.xsk.umem = NULL; bpf.xsk.umem = NULL;
bpf.xsk.queue_id = umem->queue_id; bpf.xsk.queue_id = umem->queue_id;
...@@ -119,9 +147,17 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem) ...@@ -119,9 +147,17 @@ static void xdp_umem_clear_dev(struct xdp_umem *umem)
if (err) if (err)
WARN(1, "failed to disable umem!\n"); WARN(1, "failed to disable umem!\n");
}
if (umem->dev) {
rtnl_lock();
xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
rtnl_unlock();
}
if (umem->zc) {
dev_put(umem->dev); dev_put(umem->dev);
umem->dev = NULL; umem->zc = false;
} }
} }
......
...@@ -9,7 +9,7 @@ ...@@ -9,7 +9,7 @@
#include <net/xdp_sock.h> #include <net/xdp_sock.h>
int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
u32 queue_id, u16 flags); u16 queue_id, u16 flags);
bool xdp_umem_validate_queues(struct xdp_umem *umem); bool xdp_umem_validate_queues(struct xdp_umem *umem);
void xdp_get_umem(struct xdp_umem *umem); void xdp_get_umem(struct xdp_umem *umem);
void xdp_put_umem(struct xdp_umem *umem); void xdp_put_umem(struct xdp_umem *umem);
......
...@@ -419,13 +419,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) ...@@ -419,13 +419,6 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
} }
qid = sxdp->sxdp_queue_id; qid = sxdp->sxdp_queue_id;
if ((xs->rx && qid >= dev->real_num_rx_queues) ||
(xs->tx && qid >= dev->real_num_tx_queues)) {
err = -EINVAL;
goto out_unlock;
}
flags = sxdp->sxdp_flags; flags = sxdp->sxdp_flags;
if (flags & XDP_SHARED_UMEM) { if (flags & XDP_SHARED_UMEM) {
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment