}
}
-/**
- * i40e_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int i40e_rx_offset(struct i40e_ring *rx_ring)
-{
- return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0;
-}
-
/**
* i40e_setup_rx_descriptors - Allocate Rx descriptors
* @rx_ring: Rx descriptor ring (for a specific queue) to setup
rx_ring->next_to_alloc = 0;
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
- rx_ring->rx_offset = i40e_rx_offset(rx_ring);
/* XDP RX-queue info only needed for RX rings exposed to XDP */
if (rx_ring->vsi->type == I40E_VSI_MAIN) {
}
/**
- * i40e_create_tx_ctx Build the Tx context descriptor
+ * i40e_create_tx_ctx - Build the Tx context descriptor
* @tx_ring: ring to create the descriptor on
* @cd_type_cmd_tso_mss: Quad Word 1
* @cd_tunneling: Quad Word 0 - bits 0-31
* @frames: array of XDP buffer pointers
* @flags: XDP extra info
*
- * Returns number of frames successfully sent. Frames that fail are
- * free'ed via XDP return API.
+ * Returns number of frames successfully sent. Failed frames
+ * will be free'ed by XDP core.
*
* For error cases, a negative errno code is returned and no-frames
* are transmitted (caller must handle freeing frames).
struct i40e_vsi *vsi = np->vsi;
struct i40e_pf *pf = vsi->back;
struct i40e_ring *xdp_ring;
- int drops = 0;
+ int nxmit = 0;
int i;
if (test_bit(__I40E_VSI_DOWN, vsi->state))
int err;
err = i40e_xmit_xdp_ring(xdpf, xdp_ring);
- if (err != I40E_XDP_TX) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- }
+ if (err != I40E_XDP_TX)
+ break;
+ nxmit++;
}
if (unlikely(flags & XDP_XMIT_FLUSH))
i40e_xdp_ring_update_tail(xdp_ring);
- return n - drops;
+ return nxmit;
}
}
}
-/**
- * ice_rx_offset - Return expected offset into page to access data
- * @rx_ring: Ring we are requesting offset of
- *
- * Returns the offset value for ring into the data buffer.
- */
-static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
-{
- if (ice_ring_uses_build_skb(rx_ring))
- return ICE_SKB_PAD;
- else if (ice_is_xdp_ena_vsi(rx_ring->vsi))
- return XDP_PACKET_HEADROOM;
-
- return 0;
-}
-
/**
* ice_setup_rx_ring - Allocate the Rx descriptors
* @rx_ring: the Rx ring to set up
rx_ring->next_to_use = 0;
rx_ring->next_to_clean = 0;
- rx_ring->rx_offset = ice_rx_offset(rx_ring);
if (ice_is_xdp_ena_vsi(rx_ring->vsi))
WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog);
* @frames: XDP frames to be transmitted
* @flags: transmit flags
*
- * Returns number of frames successfully sent. Frames that fail are
- * free'ed via XDP return API.
+ * Returns number of frames successfully sent. Failed frames
+ * will be free'ed by XDP core.
* For error cases, a negative errno code is returned and no-frames
* are transmitted (caller must handle freeing frames).
*/
unsigned int queue_index = smp_processor_id();
struct ice_vsi *vsi = np->vsi;
struct ice_ring *xdp_ring;
- int drops = 0, i;
+ int nxmit = 0, i;
if (test_bit(__ICE_DOWN, vsi->state))
return -ENETDOWN;
int err;
err = ice_xmit_xdp_ring(xdpf->data, xdpf->len, xdp_ring);
- if (err != ICE_XDP_TX) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- }
+ if (err != ICE_XDP_TX)
+ break;
+ nxmit++;
}
if (unlikely(flags & XDP_XMIT_FLUSH))
ice_xdp_ring_update_tail(xdp_ring);
- return n - drops;
+ return nxmit;
}
/**
dma_rmb();
if (rx_desc->wb.rxdid == FDIR_DESC_RXDID || !rx_ring->netdev) {
+ struct ice_vsi *ctrl_vsi = rx_ring->vsi;
+
+ if (rx_desc->wb.rxdid == FDIR_DESC_RXDID &&
+ ctrl_vsi->vf_id != ICE_INVAL_VFID)
+ ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc);
ice_put_rx_buf(rx_ring, NULL, 0);
cleaned_count++;
continue;
}
/**
- * Detect and switch function for Media Auto Sense
+ * igb_check_swap_media - Detect and switch function for Media Auto Sense
* @adapter: address of the board private structure
**/
static void igb_check_swap_media(struct igb_adapter *adapter)
int cpu = smp_processor_id();
struct igb_ring *tx_ring;
struct netdev_queue *nq;
- int drops = 0;
+ int nxmit = 0;
int i;
if (unlikely(test_bit(__IGB_DOWN, &adapter->state)))
int err;
err = igb_xmit_xdp_ring(adapter, tx_ring, xdpf);
- if (err != IGB_XDP_TX) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- }
+ if (err != IGB_XDP_TX)
+ break;
+ nxmit++;
}
__netif_tx_unlock(nq);
if (unlikely(flags & XDP_XMIT_FLUSH))
igb_xdp_ring_update_tail(tx_ring);
- return n - drops;
+ return nxmit;
}
static const struct net_device_ops igb_netdev_ops = {
return 0;
/* Initialize the i2c bus which is controlled by the registers.
- * This bus will use the i2c_algo_bit structue that implements
+ * This bus will use the i2c_algo_bit structure that implements
* the protocol through toggling of the 4 bits in the register.
*/
adapter->i2c_adap.owner = THIS_MODULE;
}
/**
- * igb_open - Called when a network interface is made active
+ * __igb_open - Called when a network interface is made active
* @netdev: network interface device structure
* @resuming: indicates whether we are in a resume call
*
}
/**
- * igb_close - Disables a network interface
+ * __igb_close - Disables a network interface
* @netdev: network interface device structure
* @suspending: indicates we are in a suspend call
*
*/
if (tx_ring->launchtime_enable) {
ts = ktime_to_timespec64(first->skb->tstamp);
- first->skb->tstamp = ktime_set(0, 0);
+ skb_txtime_consumed(first->skb);
context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
} else {
context_desc->seqnum_seed = 0;
new_buff->pagecnt_bias = old_buff->pagecnt_bias;
}
-static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer)
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
+ int rx_buf_pgcnt)
{
unsigned int pagecnt_bias = rx_buffer->pagecnt_bias;
struct page *page = rx_buffer->page;
#if (PAGE_SIZE < 8192)
/* if we are only owner of page we can reuse it */
- if (unlikely((page_ref_count(page) - pagecnt_bias) > 1))
+ if (unlikely((rx_buf_pgcnt - pagecnt_bias) > 1))
return false;
#else
#define IGB_LAST_OFFSET \
return NULL;
if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) {
- igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb);
- xdp->data += IGB_TS_HDR_LEN;
- size -= IGB_TS_HDR_LEN;
+ if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, xdp->data, skb)) {
+ xdp->data += IGB_TS_HDR_LEN;
+ size -= IGB_TS_HDR_LEN;
+ }
}
/* Determine available headroom for copy */
/* pull timestamp out of packet data */
if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
- igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
- __skb_pull(skb, IGB_TS_HDR_LEN);
+ if (!igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb))
+ __skb_pull(skb, IGB_TS_HDR_LEN);
}
/* update buffer offset */
}
static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring,
- const unsigned int size)
+ const unsigned int size, int *rx_buf_pgcnt)
{
struct igb_rx_buffer *rx_buffer;
rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+ *rx_buf_pgcnt =
+#if (PAGE_SIZE < 8192)
+ page_count(rx_buffer->page);
+#else
+ 0;
+#endif
prefetchw(rx_buffer->page);
/* we are reusing so sync this buffer for CPU use */
}
static void igb_put_rx_buffer(struct igb_ring *rx_ring,
- struct igb_rx_buffer *rx_buffer)
+ struct igb_rx_buffer *rx_buffer, int rx_buf_pgcnt)
{
- if (igb_can_reuse_rx_page(rx_buffer)) {
+ if (igb_can_reuse_rx_page(rx_buffer, rx_buf_pgcnt)) {
/* hand second half of page back to the ring */
igb_reuse_rx_page(rx_ring, rx_buffer);
} else {
unsigned int xdp_xmit = 0;
struct xdp_buff xdp;
u32 frame_sz = 0;
+ int rx_buf_pgcnt;
/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
#if (PAGE_SIZE < 8192)
*/
dma_rmb();
- rx_buffer = igb_get_rx_buffer(rx_ring, size);
+ rx_buffer = igb_get_rx_buffer(rx_ring, size, &rx_buf_pgcnt);
/* retrieve a buffer from the ring */
if (!skb) {
break;
}
- igb_put_rx_buffer(rx_ring, rx_buffer);
+ igb_put_rx_buffer(rx_ring, rx_buffer, rx_buf_pgcnt);
cleaned_count++;
/* fetch next buffer in frame if non-eop */
}
/**
- * ixgbe_check_from_parent - Determine whether PCIe info should come from parent
+ * ixgbe_pcie_from_parent - Determine whether PCIe info should come from parent
* @hw: hw specific details
*
* This function is used by probe to determine whether a device's PCI-Express
#endif
}
+ ring->rx_offset = ixgbe_rx_offset(ring);
+
if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) {
u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool);
}
/**
- * ixgbe_eee_capable - helper function to determine EEE support on X550
+ * ixgbe_set_eee_capable - helper function to determine EEE support on X550
* @adapter: board private structure
*/
static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter)
rx_ring->next_to_clean = 0;
rx_ring->next_to_use = 0;
- rx_ring->rx_offset = ixgbe_rx_offset(rx_ring);
/* XDP RX-queue info */
if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev,
{
struct ixgbe_adapter *adapter = netdev_priv(dev);
struct ixgbe_ring *ring;
- int drops = 0;
+ int nxmit = 0;
int i;
if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state)))
int err;
err = ixgbe_xmit_xdp_ring(adapter, xdpf);
- if (err != IXGBE_XDP_TX) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- }
+ if (err != IXGBE_XDP_TX)
+ break;
+ nxmit++;
}
if (unlikely(flags & XDP_XMIT_FLUSH))
ixgbe_xdp_ring_update_tail(ring);
- return n - drops;
+ return nxmit;
}
static const struct net_device_ops ixgbe_netdev_ops = {
goto err1;
/* set phy power down */
- data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR) |
- BMCR_PDOWN;
- netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+ data = netsec_phy_read(priv->mii_bus, priv->phy_addr, MII_BMCR);
+ netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR,
+ data | BMCR_PDOWN);
ret = netsec_reset_hardware(priv, true);
if (ret)
goto err2;
+ /* Restore phy power state */
+ netsec_phy_write(priv->mii_bus, priv->phy_addr, MII_BMCR, data);
+
spin_lock_init(&priv->desc_ring[NETSEC_RING_TX].lock);
spin_lock_init(&priv->desc_ring[NETSEC_RING_RX].lock);
{
struct netsec_priv *priv = netdev_priv(ndev);
struct netsec_desc_ring *tx_ring = &priv->desc_ring[NETSEC_RING_TX];
- int drops = 0;
- int i;
+ int i, nxmit = 0;
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
return -EINVAL;
int err;
err = netsec_xdp_queue_one(priv, xdpf, true);
- if (err != NETSEC_XDP_TX) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- } else {
- tx_ring->xdp_xmit++;
- }
+ if (err != NETSEC_XDP_TX)
+ break;
+
+ tx_ring->xdp_xmit++;
+ nxmit++;
}
spin_unlock(&tx_ring->lock);
tx_ring->xdp_xmit = 0;
}
- return n - drops;
+ return nxmit;
}
static int netsec_xdp_setup(struct netsec_priv *priv, struct bpf_prog *prog,
if (rxq < rcv->real_num_rx_queues) {
rq = &rcv_priv->rq[rxq];
rcv_xdp = rcu_access_pointer(rq->xdp_prog);
- if (rcv_xdp)
- skb_record_rx_queue(skb, rxq);
+ skb_record_rx_queue(skb, rxq);
}
skb_tx_timestamp(skb);
u32 flags, bool ndo_xmit)
{
struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
- int i, ret = -ENXIO, drops = 0;
+ int i, ret = -ENXIO, nxmit = 0;
struct net_device *rcv;
unsigned int max_len;
struct veth_rq *rq;
void *ptr = veth_xdp_to_ptr(frame);
if (unlikely(frame->len > max_len ||
- __ptr_ring_produce(&rq->xdp_ring, ptr))) {
- xdp_return_frame_rx_napi(frame);
- drops++;
- }
+ __ptr_ring_produce(&rq->xdp_ring, ptr)))
+ break;
+ nxmit++;
}
spin_unlock(&rq->xdp_ring.producer_lock);
if (flags & XDP_XMIT_FLUSH)
__veth_xdp_flush(rq);
- ret = n - drops;
+ ret = nxmit;
if (ndo_xmit) {
u64_stats_update_begin(&rq->stats.syncp);
- rq->stats.vs.peer_tq_xdp_xmit += n - drops;
- rq->stats.vs.peer_tq_xdp_xmit_err += drops;
+ rq->stats.vs.peer_tq_xdp_xmit += nxmit;
+ rq->stats.vs.peer_tq_xdp_xmit_err += n - nxmit;
u64_stats_update_end(&rq->stats.syncp);
}
static void veth_xdp_flush_bq(struct veth_rq *rq, struct veth_xdp_tx_bq *bq)
{
- int sent, i, err = 0;
+ int sent, i, err = 0, drops;
sent = veth_xdp_xmit(rq->dev, bq->count, bq->q, 0, false);
if (sent < 0) {
err = sent;
sent = 0;
- for (i = 0; i < bq->count; i++)
- xdp_return_frame(bq->q[i]);
}
- trace_xdp_bulk_tx(rq->dev, sent, bq->count - sent, err);
+
+ for (i = sent; unlikely(i < bq->count); i++)
+ xdp_return_frame(bq->q[i]);
+
+ drops = bq->count - sent;
+ trace_xdp_bulk_tx(rq->dev, sent, drops, err);
u64_stats_update_begin(&rq->stats.syncp);
rq->stats.vs.xdp_tx += sent;
- rq->stats.vs.xdp_tx_err += bq->count - sent;
+ rq->stats.vs.xdp_tx_err += drops;
u64_stats_update_end(&rq->stats.syncp);
bq->count = 0;
/* # of XDP queue pairs currently used by the driver */
u16 xdp_queue_pairs;
+ /* xdp_queue_pairs may be 0, when xdp is already loaded. So add this. */
+ bool xdp_enabled;
+
/* I like... big packets and I cannot lie! */
bool big_packets;
return 0;
}
-static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi)
-{
- unsigned int qp;
-
- qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
- return &vi->sq[qp];
+/* when vi->curr_queue_pairs > nr_cpu_ids, the txq/sq is only used for xdp tx on
+ * the current cpu, so it does not need to be locked.
+ *
+ * Here we use marco instead of inline functions because we have to deal with
+ * three issues at the same time: 1. the choice of sq. 2. judge and execute the
+ * lock/unlock of txq 3. make sparse happy. It is difficult for two inline
+ * functions to perfectly solve these three problems at the same time.
+ */
+#define virtnet_xdp_get_sq(vi) ({ \
+ struct netdev_queue *txq; \
+ typeof(vi) v = (vi); \
+ unsigned int qp; \
+ \
+ if (v->curr_queue_pairs > nr_cpu_ids) { \
+ qp = v->curr_queue_pairs - v->xdp_queue_pairs; \
+ qp += smp_processor_id(); \
+ txq = netdev_get_tx_queue(v->dev, qp); \
+ __netif_tx_acquire(txq); \
+ } else { \
+ qp = smp_processor_id() % v->curr_queue_pairs; \
+ txq = netdev_get_tx_queue(v->dev, qp); \
+ __netif_tx_lock(txq, raw_smp_processor_id()); \
+ } \
+ v->sq + qp; \
+})
+
+#define virtnet_xdp_put_sq(vi, q) { \
+ struct netdev_queue *txq; \
+ typeof(vi) v = (vi); \
+ \
+ txq = netdev_get_tx_queue(v->dev, (q) - v->sq); \
+ if (v->curr_queue_pairs > nr_cpu_ids) \
+ __netif_tx_release(txq); \
+ else \
+ __netif_tx_unlock(txq); \
}
static int virtnet_xdp_xmit(struct net_device *dev,
unsigned int len;
int packets = 0;
int bytes = 0;
- int drops = 0;
+ int nxmit = 0;
int kicks = 0;
- int ret, err;
void *ptr;
+ int ret;
int i;
/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
if (!xdp_prog)
return -ENXIO;
- sq = virtnet_xdp_sq(vi);
+ sq = virtnet_xdp_get_sq(vi);
if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
ret = -EINVAL;
- drops = n;
goto out;
}
for (i = 0; i < n; i++) {
struct xdp_frame *xdpf = frames[i];
- err = __virtnet_xdp_xmit_one(vi, sq, xdpf);
- if (err) {
- xdp_return_frame_rx_napi(xdpf);
- drops++;
- }
+ if (__virtnet_xdp_xmit_one(vi, sq, xdpf))
+ break;
+ nxmit++;
}
- ret = n - drops;
+ ret = nxmit;
if (flags & XDP_XMIT_FLUSH) {
if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
sq->stats.bytes += bytes;
sq->stats.packets += packets;
sq->stats.xdp_tx += n;
- sq->stats.xdp_tx_drops += drops;
+ sq->stats.xdp_tx_drops += n - nxmit;
sq->stats.kicks += kicks;
u64_stats_update_end(&sq->stats.syncp);
+ virtnet_xdp_put_sq(vi, sq);
return ret;
}
static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
{
- return vi->xdp_queue_pairs ? VIRTIO_XDP_HEADROOM : 0;
+ return vi->xdp_enabled ? VIRTIO_XDP_HEADROOM : 0;
}
/* We copy the packet for XDP in the following cases:
if (unlikely(!xdpf))
goto err_xdp;
err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
- if (unlikely(err < 0)) {
+ if (unlikely(!err)) {
+ xdp_return_frame_rx_napi(xdpf);
+ } else if (unlikely(err < 0)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
goto err_xdp;
}
if (unlikely(!xdpf))
goto err_xdp;
err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
- if (unlikely(err < 0)) {
+ if (unlikely(!err)) {
+ xdp_return_frame_rx_napi(xdpf);
+ } else if (unlikely(err < 0)) {
trace_xdp_exception(vi->dev, xdp_prog, act);
if (unlikely(xdp_page != page))
put_page(xdp_page);
xdp_do_flush();
if (xdp_xmit & VIRTIO_XDP_TX) {
- sq = virtnet_xdp_sq(vi);
+ sq = virtnet_xdp_get_sq(vi);
if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
u64_stats_update_begin(&sq->stats.syncp);
sq->stats.kicks++;
u64_stats_update_end(&sq->stats.syncp);
}
+ virtnet_xdp_put_sq(vi, sq);
}
return received;
}
virtqueue_set_affinity(vi->rq[i].vq, mask);
virtqueue_set_affinity(vi->sq[i].vq, mask);
- __netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, false);
+ __netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, XPS_CPUS);
cpumask_clear(mask);
}
static void virtnet_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
struct virtnet_info *vi = netdev_priv(dev);
- char *p = (char *)data;
unsigned int i, j;
+ u8 *p = data;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < vi->curr_queue_pairs; i++) {
- for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) {
- snprintf(p, ETH_GSTRING_LEN, "rx_queue_%u_%s",
- i, virtnet_rq_stats_desc[j].desc);
- p += ETH_GSTRING_LEN;
- }
+ for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++)
+ ethtool_sprintf(&p, "rx_queue_%u_%s", i,
+ virtnet_rq_stats_desc[j].desc);
}
for (i = 0; i < vi->curr_queue_pairs; i++) {
- for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++) {
- snprintf(p, ETH_GSTRING_LEN, "tx_queue_%u_%s",
- i, virtnet_sq_stats_desc[j].desc);
- p += ETH_GSTRING_LEN;
- }
+ for (j = 0; j < VIRTNET_SQ_STATS_LEN; j++)
+ ethtool_sprintf(&p, "tx_queue_%u_%s", i,
+ virtnet_sq_stats_desc[j].desc);
}
break;
}
/* XDP requires extra queues for XDP_TX */
if (curr_qp + xdp_qp > vi->max_queue_pairs) {
- NL_SET_ERR_MSG_MOD(extack, "Too few free TX rings available");
- netdev_warn(dev, "request %i queues but max is %i\n",
+ netdev_warn(dev, "XDP request %i queues but max is %i. XDP_TX and XDP_REDIRECT will operate in a slower locked tx mode.\n",
curr_qp + xdp_qp, vi->max_queue_pairs);
- return -ENOMEM;
+ xdp_qp = 0;
}
old_prog = rtnl_dereference(vi->rq[0].xdp_prog);
vi->xdp_queue_pairs = xdp_qp;
if (prog) {
+ vi->xdp_enabled = true;
for (i = 0; i < vi->max_queue_pairs; i++) {
rcu_assign_pointer(vi->rq[i].xdp_prog, prog);
if (i == 0 && !old_prog)
virtnet_clear_guest_offloads(vi);
}
+ } else {
+ vi->xdp_enabled = false;
}
for (i = 0; i < vi->max_queue_pairs; i++) {
int err;
if ((dev->features ^ features) & NETIF_F_LRO) {
- if (vi->xdp_queue_pairs)
+ if (vi->xdp_enabled)
return -EBUSY;
if (features & NETIF_F_LRO)
{
bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
(opcode == BPF_SUB && !off_is_neg);
- u32 off;
+ u32 off, max;
switch (ptr_reg->type) {
case PTR_TO_STACK:
+ /* Offset 0 is out-of-bounds, but acceptable start for the
+ * left direction, see BPF_REG_FP.
+ */
+ max = MAX_BPF_STACK + mask_to_left;
/* Indirect variable offset stack access is prohibited in
* unprivileged mode so it's not handled here.
*/
if (mask_to_left)
*ptr_limit = MAX_BPF_STACK + off;
else
- *ptr_limit = -off;
- return 0;
+ *ptr_limit = -off - 1;
+ return *ptr_limit >= max ? -ERANGE : 0;
case PTR_TO_MAP_KEY:
/* Currently, this code is not exercised as the only use
* is bpf_for_each_map_elem() helper which requires
}
return 0;
case PTR_TO_MAP_VALUE:
+ max = ptr_reg->map_ptr->value_size;
if (mask_to_left) {
*ptr_limit = ptr_reg->umax_value + ptr_reg->off;
} else {
off = ptr_reg->smin_value + ptr_reg->off;
- *ptr_limit = ptr_reg->map_ptr->value_size - off;
+ *ptr_limit = ptr_reg->map_ptr->value_size - off - 1;
}
- return 0;
+ return *ptr_limit >= max ? -ERANGE : 0;
default:
return -EINVAL;
}
u32 alu_state, alu_limit;
struct bpf_reg_state tmp;
bool ret;
+ int err;
if (can_skip_alu_sanitation(env, insn))
return 0;
alu_state |= ptr_is_dst_reg ?
BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
- if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
- return 0;
- if (update_alu_sanitation_state(aux, alu_state, alu_limit))
- return -EACCES;
+ err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+ if (err < 0)
+ return err;
+
+ err = update_alu_sanitation_state(aux, alu_state, alu_limit);
+ if (err < 0)
+ return err;
do_sim:
/* Simulate and find potential out-of-bounds access under
* speculative execution from truncation as a result of
case BPF_ADD:
ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
if (ret < 0) {
- verbose(env, "R%d tried to add from different maps or paths\n", dst);
+ verbose(env, "R%d tried to add from different maps, paths, or prohibited types\n", dst);
return ret;
}
/* We can take a fixed offset as long as it doesn't overflow
case BPF_SUB:
ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
if (ret < 0) {
- verbose(env, "R%d tried to sub from different maps or paths\n", dst);
+ verbose(env, "R%d tried to sub from different maps, paths, or prohibited types\n", dst);
return ret;
}
if (dst_reg == off_reg) {
btf = btf_get_by_fd(attr->prog_btf_fd);
if (IS_ERR(btf))
return PTR_ERR(btf);
+ if (btf_is_kernel(btf)) {
+ btf_put(btf);
+ return -EACCES;
+ }
env->prog->aux->btf = btf;
err = check_btf_func(env, attr, uattr);
insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
- struct bpf_insn insn_buf[16];
struct bpf_insn *patch = &insn_buf[0];
bool issrc, isneg;
u32 off_reg;
off_reg = issrc ? insn->src_reg : insn->dst_reg;
if (isneg)
*patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
- *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+ *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit);
*patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
*patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
sk->sk_prot->keepalive(sk, valbool);
sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
break;
+ case SO_REUSEPORT:
+ sk->sk_reuseport = valbool;
+ break;
default:
ret = -EINVAL;
}
case SO_BINDTOIFINDEX:
*((int *)optval) = sk->sk_bound_dev_if;
break;
+ case SO_REUSEPORT:
+ *((int *)optval) = sk->sk_reuseport;
+ break;
default:
goto err_clear;
}
if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
return -EINVAL;
- if (unlikely(flags & BPF_MTU_CHK_SEGS && len_diff))
+ if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
return -EINVAL;
dev = __dev_via_ifindex(dev, ifindex);
mtu = READ_ONCE(dev->mtu);
dev_len = mtu + dev->hard_header_len;
- skb_len = skb->len + len_diff; /* minus result pass check */
+
+ /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+ skb_len = *mtu_len ? *mtu_len + dev->hard_header_len : skb->len;
+
+ skb_len += len_diff; /* minus result pass check */
if (skb_len <= dev_len) {
ret = BPF_MTU_CHK_RET_SUCCESS;
goto out;
/* Add L2-header as dev MTU is L3 size */
dev_len = mtu + dev->hard_header_len;
+ /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+ if (*mtu_len)
+ xdp_len = *mtu_len + dev->hard_header_len;
+
xdp_len += len_diff; /* minus result pass check */
if (xdp_len > dev_len)
ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
if [ ! -d '$(DESTDIR_SQ)$2' ]; then \
$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2'; \
fi; \
- $(INSTALL) $1 $(if $3,-m $3,) '$(DESTDIR_SQ)$2'
+ $(INSTALL) $(if $3,-m $3,) $1 '$(DESTDIR_SQ)$2'
endef
install_lib: all_cmd
$(call do_install,bpf.h,$(prefix)/include/bpf,644); \
$(call do_install,libbpf.h,$(prefix)/include/bpf,644); \
$(call do_install,btf.h,$(prefix)/include/bpf,644); \
- $(call do_install,libbpf_util.h,$(prefix)/include/bpf,644); \
$(call do_install,libbpf_common.h,$(prefix)/include/bpf,644); \
$(call do_install,xsk.h,$(prefix)/include/bpf,644); \
$(call do_install,bpf_helpers.h,$(prefix)/include/bpf,644); \
if (last_id <= d->last_id)
return 0;
- if (btf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
- sizeof(*d->type_states), last_id + 1))
+ if (libbpf_ensure_mem((void **)&d->type_states, &d->type_states_cap,
+ sizeof(*d->type_states), last_id + 1))
return -ENOMEM;
- if (btf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
- sizeof(*d->cached_names), last_id + 1))
+ if (libbpf_ensure_mem((void **)&d->cached_names, &d->cached_names_cap,
+ sizeof(*d->cached_names), last_id + 1))
return -ENOMEM;
if (d->last_id == 0) {
return err;
case BTF_KIND_ARRAY:
- return btf_dump_order_type(d, btf_array(t)->type, through_ptr);
+ return btf_dump_order_type(d, btf_array(t)->type, false);
case BTF_KIND_STRUCT:
case BTF_KIND_UNION: {
#include "libbpf_internal.h"
#include "hashmap.h"
- #ifndef EM_BPF
- #define EM_BPF 247
- #endif
-
#ifndef BPF_FS_MAGIC
#define BPF_FS_MAGIC 0xcafe4a11
#endif
obj->efile.obj_buf_sz = 0;
}
- /* if libelf is old and doesn't support mmap(), fall back to read() */
- #ifndef ELF_C_READ_MMAP
- #define ELF_C_READ_MMAP ELF_C_READ
- #endif
-
static int bpf_object__elf_init(struct bpf_object *obj)
{
int err = 0;
if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
pr_warn("elf: failed to get section names strings from %s: %s\n",
obj->path, elf_errmsg(-1));
- return -LIBBPF_ERRNO__FORMAT;
+ err = -LIBBPF_ERRNO__FORMAT;
+ goto errout;
}
/* Old LLVM set e_machine to EM_NONE */
return true;
/* ignore .llvm_addrsig section as well */
- if (hdr->sh_type == 0x6FFF4C03 /* SHT_LLVM_ADDRSIG */)
+ if (hdr->sh_type == SHT_LLVM_ADDRSIG)
return true;
/* no subprograms will lead to an empty .text section, ignore it */
goto err_out;
}
- err = btf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
- sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
+ err = libbpf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap,
+ sizeof(*obj->btf_modules), obj->btf_module_cnt + 1);
if (err)
goto err_out;