lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZrdxPgcqLdzCXCAS@boxer>
Date: Sat, 10 Aug 2024 15:55:10 +0200
From: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
To: Tony Nguyen <anthony.l.nguyen@...el.com>
CC: <davem@...emloft.net>, <kuba@...nel.org>, <pabeni@...hat.com>,
	<edumazet@...gle.com>, <netdev@...r.kernel.org>, Sriram Yagnaraman
	<sriram.yagnaraman@....tech>, <magnus.karlsson@...el.com>, <ast@...nel.org>,
	<daniel@...earbox.net>, <hawk@...nel.org>, <john.fastabend@...il.com>,
	<bpf@...r.kernel.org>, <kurt@...utronix.de>,
	<sriram.yagnaraman@...csson.com>, <richardcochran@...il.com>,
	<benjamin.steinke@...s-audio.com>, <bigeasy@...utronix.de>, "Chandan Kumar
 Rout" <chandanx.rout@...el.com>
Subject: Re: [PATCH net-next 3/4] igb: add AF_XDP zero-copy Rx support

On Thu, Aug 08, 2024 at 11:35:53AM -0700, Tony Nguyen wrote:
> From: Sriram Yagnaraman <sriram.yagnaraman@....tech>
> 
> Add support for AF_XDP zero-copy receive path.
> 
> When AF_XDP zero-copy is enabled, the rx buffers are allocated from the
> xsk buff pool using igb_alloc_rx_buffers_zc.
> 
> Use xsk_pool_get_rx_frame_size to set SRRCTL rx buf size when zero-copy
> is enabled.
> 
> Signed-off-by: Sriram Yagnaraman <sriram.yagnaraman@....tech>
> [Kurt: Port to v6.10 and provide napi_id for xdp_rxq_info_reg()]
> Signed-off-by: Kurt Kanzenbach <kurt@...utronix.de>
> Tested-by: Chandan Kumar Rout <chandanx.rout@...el.com> (A Contingent Worker at Intel)
> Signed-off-by: Tony Nguyen <anthony.l.nguyen@...el.com>
> ---
>  drivers/net/ethernet/intel/igb/igb.h      |   4 +
>  drivers/net/ethernet/intel/igb/igb_main.c |  95 ++++++--
>  drivers/net/ethernet/intel/igb/igb_xsk.c  | 261 +++++++++++++++++++++-
>  3 files changed, 337 insertions(+), 23 deletions(-)
> 
> diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
> index 053130c01480..4983a6ec718e 100644
> --- a/drivers/net/ethernet/intel/igb/igb.h
> +++ b/drivers/net/ethernet/intel/igb/igb.h
> @@ -87,6 +87,7 @@ struct igb_adapter;
>  #define IGB_XDP_CONSUMED	BIT(0)
>  #define IGB_XDP_TX		BIT(1)
>  #define IGB_XDP_REDIR		BIT(2)
> +#define IGB_XDP_EXIT		BIT(3)
>  
>  struct vf_data_storage {
>  	unsigned char vf_mac_addresses[ETH_ALEN];
> @@ -832,6 +833,9 @@ struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter,
>  int igb_xsk_pool_setup(struct igb_adapter *adapter,
>  		       struct xsk_buff_pool *pool,
>  		       u16 qid);
> +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, u16 count);
> +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring);
> +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, const int budget);
>  int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags);
>  
>  #endif /* _IGB_H_ */
> diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
> index b6f23bbeff71..0b779b2ca9ea 100644
> --- a/drivers/net/ethernet/intel/igb/igb_main.c
> +++ b/drivers/net/ethernet/intel/igb/igb_main.c
> @@ -472,12 +472,17 @@ static void igb_dump(struct igb_adapter *adapter)
>  
>  		for (i = 0; i < rx_ring->count; i++) {
>  			const char *next_desc;
> -			struct igb_rx_buffer *buffer_info;
> -			buffer_info = &rx_ring->rx_buffer_info[i];
> +			dma_addr_t dma = (dma_addr_t)0;
> +			struct igb_rx_buffer *buffer_info = NULL;
>  			rx_desc = IGB_RX_DESC(rx_ring, i);
>  			u0 = (struct my_u0 *)rx_desc;
>  			staterr = le32_to_cpu(rx_desc->wb.upper.status_error);
>  
> +			if (!rx_ring->xsk_pool) {
> +				buffer_info = &rx_ring->rx_buffer_info[i];
> +				dma = buffer_info->dma;
> +			}
> +
>  			if (i == rx_ring->next_to_use)
>  				next_desc = " NTU";
>  			else if (i == rx_ring->next_to_clean)
> @@ -497,11 +502,11 @@ static void igb_dump(struct igb_adapter *adapter)
>  					"R  ", i,
>  					le64_to_cpu(u0->a),
>  					le64_to_cpu(u0->b),
> -					(u64)buffer_info->dma,
> +					(u64)dma,
>  					next_desc);
>  
>  				if (netif_msg_pktdata(adapter) &&
> -				    buffer_info->dma && buffer_info->page) {
> +				    buffer_info && dma && buffer_info->page) {
>  					print_hex_dump(KERN_INFO, "",
>  					  DUMP_PREFIX_ADDRESS,
>  					  16, 1,
> @@ -1983,7 +1988,10 @@ static void igb_configure(struct igb_adapter *adapter)
>  	 */
>  	for (i = 0; i < adapter->num_rx_queues; i++) {
>  		struct igb_ring *ring = adapter->rx_ring[i];
> -		igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
> +		if (ring->xsk_pool)
> +			igb_alloc_rx_buffers_zc(ring, igb_desc_unused(ring));
> +		else
> +			igb_alloc_rx_buffers(ring, igb_desc_unused(ring));
>  	}
>  }
>  
> @@ -3335,7 +3343,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
>  	netdev->priv_flags |= IFF_SUPP_NOFCS;
>  
>  	netdev->priv_flags |= IFF_UNICAST_FLT;
> -	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT;
> +	netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
> +			       NETDEV_XDP_ACT_XSK_ZEROCOPY;
>  
>  	/* MTU range: 68 - 9216 */
>  	netdev->min_mtu = ETH_MIN_MTU;
> @@ -4423,7 +4432,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring)
>  	if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
>  		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
>  	res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev,
> -			       rx_ring->queue_index, 0);
> +			       rx_ring->queue_index,
> +			       rx_ring->q_vector->napi.napi_id);
>  	if (res < 0) {
>  		dev_err(dev, "Failed to register xdp_rxq index %u\n",
>  			rx_ring->queue_index);
> @@ -4719,12 +4729,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring)
>  	struct e1000_hw *hw = &adapter->hw;
>  	int reg_idx = ring->reg_idx;
>  	u32 srrctl = 0;
> +	u32 buf_size;
>  
> -	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
> -	if (ring_uses_large_buffer(ring))
> -		srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
> +	if (ring->xsk_pool)
> +		buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool);
> +	else if (ring_uses_large_buffer(ring))
> +		buf_size = IGB_RXBUFFER_3072;
>  	else
> -		srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT;
> +		buf_size = IGB_RXBUFFER_2048;
> +
> +	srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
> +	srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT;
>  	srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
>  	if (hw->mac.type >= e1000_82580)
>  		srrctl |= E1000_SRRCTL_TIMESTAMP;
> @@ -4756,9 +4771,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
>  	u32 rxdctl = 0;
>  
>  	xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
> -	WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
> -					   MEM_TYPE_PAGE_SHARED, NULL));
>  	ring->xsk_pool = igb_xsk_pool(adapter, ring);
> +	if (ring->xsk_pool) {
> +		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
> +						   MEM_TYPE_XSK_BUFF_POOL,
> +						   NULL));
> +		xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
> +	} else {
> +		WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
> +						   MEM_TYPE_PAGE_SHARED,
> +						   NULL));
> +	}
>  
>  	/* disable the queue */
>  	wr32(E1000_RXDCTL(reg_idx), 0);
> @@ -4785,9 +4808,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
>  	rxdctl |= IGB_RX_HTHRESH << 8;
>  	rxdctl |= IGB_RX_WTHRESH << 16;
>  
> -	/* initialize rx_buffer_info */
> -	memset(ring->rx_buffer_info, 0,
> -	       sizeof(struct igb_rx_buffer) * ring->count);
> +	if (ring->xsk_pool)
> +		memset(ring->rx_buffer_info_zc, 0,
> +		       sizeof(*ring->rx_buffer_info_zc) * ring->count);
> +	else
> +		memset(ring->rx_buffer_info, 0,
> +		       sizeof(*ring->rx_buffer_info) * ring->count);

ah okay. comment from previous patch is addressed here, thanks.

>  
>  	/* initialize Rx descriptor 0 */
>  	rx_desc = IGB_RX_DESC(ring, 0);
> @@ -4974,8 +5000,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring)
>  
>  	rx_ring->xdp_prog = NULL;
>  	xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
> -	vfree(rx_ring->rx_buffer_info);
> -	rx_ring->rx_buffer_info = NULL;
> +	if (rx_ring->xsk_pool) {
> +		vfree(rx_ring->rx_buffer_info_zc);
> +		rx_ring->rx_buffer_info_zc = NULL;
> +	} else {
> +		vfree(rx_ring->rx_buffer_info);
> +		rx_ring->rx_buffer_info = NULL;
> +	}
>  
>  	/* if not set, then don't free */
>  	if (!rx_ring->desc)
> @@ -5013,6 +5044,11 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring)
>  	dev_kfree_skb(rx_ring->skb);
>  	rx_ring->skb = NULL;
>  
> +	if (rx_ring->xsk_pool) {
> +		igb_clean_rx_ring_zc(rx_ring);
> +		goto skip_for_xsk;
> +	}
> +
>  	/* Free all the Rx ring sk_buffs */
>  	while (i != rx_ring->next_to_alloc) {
>  		struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i];
> @@ -5040,6 +5076,7 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring)
>  			i = 0;
>  	}
>  
> +skip_for_xsk:
>  	rx_ring->next_to_alloc = 0;
>  	rx_ring->next_to_clean = 0;
>  	rx_ring->next_to_use = 0;
> @@ -8195,7 +8232,9 @@ static int igb_poll(struct napi_struct *napi, int budget)
>  		clean_complete = igb_clean_tx_irq(q_vector, budget);
>  
>  	if (q_vector->rx.ring) {
> -		int cleaned = igb_clean_rx_irq(q_vector, budget);
> +		int cleaned = q_vector->rx.ring->xsk_pool ?

best if you would READ_ONCE() here pool and use it for the rest of napi
lifetime...

> +			igb_clean_rx_irq_zc(q_vector, budget) :
> +			igb_clean_rx_irq(q_vector, budget);
>  
>  		work_done += cleaned;
>  		if (cleaned >= budget)
> @@ -8603,8 +8642,15 @@ struct sk_buff *igb_run_xdp(struct igb_adapter *adapter,
>  		break;
>  	case XDP_REDIRECT:
>  		err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog);

We were introducing a ZC variant of handling XDP verdict due to a fact
that mostly what happens is the redirect to user space. We observed a
reasonable perf improvement from likely()fying XDP_REDIRECT case.

> -		if (err)
> +		if (err) {
> +			if (rx_ring->xsk_pool &&
> +			    xsk_uses_need_wakeup(rx_ring->xsk_pool) &&
> +			    err == -ENOBUFS)
> +				result = IGB_XDP_EXIT;
> +			else
> +				result = IGB_XDP_CONSUMED;
>  			goto out_failure;
> +		}
>  		result = IGB_XDP_REDIR;
>  		break;
>  	default:
> @@ -8861,12 +8907,14 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
>  
>  static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
>  {
> +	unsigned int total_bytes = 0, total_packets = 0;
>  	struct igb_adapter *adapter = q_vector->adapter;
>  	struct igb_ring *rx_ring = q_vector->rx.ring;
> -	struct sk_buff *skb = rx_ring->skb;
> -	unsigned int total_bytes = 0, total_packets = 0;
>  	u16 cleaned_count = igb_desc_unused(rx_ring);
> +	struct sk_buff *skb = rx_ring->skb;
> +	int cpu = smp_processor_id();
>  	unsigned int xdp_xmit = 0;
> +	struct netdev_queue *nq;
>  	struct xdp_buff xdp;
>  	u32 frame_sz = 0;
>  	int rx_buf_pgcnt;
> @@ -8994,7 +9042,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
>  	if (xdp_xmit & IGB_XDP_TX) {
>  		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
>  
> +		nq = txring_txq(tx_ring);
> +		__netif_tx_lock(nq, cpu);

That belongs to a patch where you do:
"Always call igb_xdp_ring_update_tail under __netif_tx_lock"

>  		igb_xdp_ring_update_tail(tx_ring);
> +		__netif_tx_unlock(nq);
>  	}
>  
>  	u64_stats_update_begin(&rx_ring->rx_syncp);
> diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c
> index 925bf97f7caa..66cdc30e9b6e 100644
> --- a/drivers/net/ethernet/intel/igb/igb_xsk.c
> +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c
> @@ -66,7 +66,10 @@ static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid)
>  	 * at least 1 descriptor unused to make sure
>  	 * next_to_use != next_to_clean
>  	 */
> -	igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
> +	if (rx_ring->xsk_pool)
> +		igb_alloc_rx_buffers_zc(rx_ring, igb_desc_unused(rx_ring));
> +	else
> +		igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring));
>  
>  	/* Rx/Tx share the same napi context. */
>  	napi_enable(&rx_ring->q_vector->napi);
> @@ -172,6 +175,262 @@ int igb_xsk_pool_setup(struct igb_adapter *adapter,
>  		igb_xsk_pool_disable(adapter, qid);
>  }
>  
> +static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
> +			     union e1000_adv_rx_desc *rx_desc, u16 count)
> +{
> +	dma_addr_t dma;
> +	u16 buffs;
> +	int i;
> +
> +	/* nothing to do */
> +	if (!count)
> +		return 0;
> +
> +	buffs = xsk_buff_alloc_batch(pool, xdp, count);
> +	for (i = 0; i < buffs; i++) {
> +		dma = xsk_buff_xdp_get_dma(*xdp);
> +		rx_desc->read.pkt_addr = cpu_to_le64(dma);
> +		rx_desc->wb.upper.length = 0;
> +
> +		rx_desc++;
> +		xdp++;
> +	}
> +
> +	return buffs;
> +}
> +
> +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, u16 count)
> +{
> +	u32 nb_buffs_extra = 0, nb_buffs = 0;
> +	union e1000_adv_rx_desc *rx_desc;
> +	u16 ntu = rx_ring->next_to_use;
> +	u16 total_count = count;
> +	struct xdp_buff **xdp;
> +
> +	rx_desc = IGB_RX_DESC(rx_ring, ntu);
> +	xdp = &rx_ring->rx_buffer_info_zc[ntu];
> +
> +	if (ntu + count >= rx_ring->count) {
> +		nb_buffs_extra = igb_fill_rx_descs(rx_ring->xsk_pool, xdp,
> +						   rx_desc,
> +						   rx_ring->count - ntu);
> +		if (nb_buffs_extra != rx_ring->count - ntu) {
> +			ntu += nb_buffs_extra;
> +			goto exit;
> +		}
> +		rx_desc = IGB_RX_DESC(rx_ring, 0);
> +		xdp = rx_ring->rx_buffer_info_zc;
> +		ntu = 0;
> +		count -= nb_buffs_extra;
> +	}
> +
> +	nb_buffs = igb_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
> +	ntu += nb_buffs;
> +	if (ntu == rx_ring->count)
> +		ntu = 0;
> +
> +	/* clear the length for the next_to_use descriptor */
> +	rx_desc = IGB_RX_DESC(rx_ring, ntu);
> +	rx_desc->wb.upper.length = 0;
> +
> +exit:
> +	if (rx_ring->next_to_use != ntu) {
> +		rx_ring->next_to_use = ntu;
> +
> +		/* Force memory writes to complete before letting h/w
> +		 * know there are new descriptors to fetch.  (Only
> +		 * applicable for weak-ordered memory model archs,
> +		 * such as IA-64).
> +		 */
> +		wmb();
> +		writel(ntu, rx_ring->tail);
> +	}
> +
> +	return total_count == (nb_buffs + nb_buffs_extra);
> +}
> +
> +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring)
> +{
> +	u16 ntc = rx_ring->next_to_clean;
> +	u16 ntu = rx_ring->next_to_use;
> +
> +	while (ntc != ntu) {
> +		struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc];
> +
> +		xsk_buff_free(xdp);
> +		ntc++;
> +		if (ntc >= rx_ring->count)
> +			ntc = 0;
> +	}
> +}
> +
> +static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring,
> +					    struct xdp_buff *xdp,
> +					    ktime_t timestamp)
> +{
> +	unsigned int totalsize = xdp->data_end - xdp->data_meta;
> +	unsigned int metasize = xdp->data - xdp->data_meta;
> +	struct sk_buff *skb;
> +
> +	net_prefetch(xdp->data_meta);
> +
> +	/* allocate a skb to store the frags */
> +	skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize);
> +	if (unlikely(!skb))
> +		return NULL;
> +
> +	if (timestamp)
> +		skb_hwtstamps(skb)->hwtstamp = timestamp;
> +
> +	memcpy(__skb_put(skb, totalsize), xdp->data_meta,
> +	       ALIGN(totalsize, sizeof(long)));
> +
> +	if (metasize) {
> +		skb_metadata_set(skb, metasize);
> +		__skb_pull(skb, metasize);
> +	}
> +
> +	return skb;
> +}
> +
> +static void igb_update_ntc(struct igb_ring *rx_ring)
> +{
> +	u32 ntc = rx_ring->next_to_clean + 1;
> +
> +	/* fetch, update, and store next to clean */
> +	ntc = (ntc < rx_ring->count) ? ntc : 0;
> +	rx_ring->next_to_clean = ntc;

That is suboptimal. You don't have update the ring's member per each
procesed descriptor. What you can do is to work on a local ntc and update
it to ring at the end of napi's Rx side.

Even if you would insist on doing the current way then I would expect that
you would use this helper in igb_is_non_eop() as this is duplicated code.

> +
> +	prefetch(IGB_RX_DESC(rx_ring, ntc));
> +}
> +
> +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, const int budget)
> +{
> +	struct igb_adapter *adapter = q_vector->adapter;
> +	unsigned int total_bytes = 0, total_packets = 0;
> +	struct igb_ring *rx_ring = q_vector->rx.ring;
> +	int cpu = smp_processor_id();
> +	unsigned int xdp_xmit = 0;
> +	struct netdev_queue *nq;
> +	bool failure = false;
> +	u16 entries_to_alloc;
> +	struct sk_buff *skb;
> +
> +	while (likely(total_packets < budget)) {
> +		union e1000_adv_rx_desc *rx_desc;
> +		struct xdp_buff *xdp;
> +		ktime_t timestamp = 0;

minor: RCT

> +		unsigned int size;
> +
> +		rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean);
> +		size = le16_to_cpu(rx_desc->wb.upper.length);
> +		if (!size)
> +			break;
> +
> +		/* This memory barrier is needed to keep us from reading
> +		 * any other fields out of the rx_desc until we know the
> +		 * descriptor has been written back
> +		 */
> +		dma_rmb();
> +
> +		xdp = rx_ring->rx_buffer_info_zc[rx_ring->next_to_clean];
> +		xsk_buff_set_size(xdp, size);
> +		xsk_buff_dma_sync_for_cpu(xdp);
> +
> +		/* pull rx packet timestamp if available and valid */
> +		if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
> +			int ts_hdr_len;
> +
> +			ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector,
> +							 xdp->data,
> +							 &timestamp);
> +
> +			xdp->data += ts_hdr_len;
> +			xdp->data_meta += ts_hdr_len;
> +			size -= ts_hdr_len;
> +		}
> +
> +		skb = igb_run_xdp(adapter, rx_ring, xdp);
> +
> +		if (IS_ERR(skb)) {
> +			unsigned int xdp_res = -PTR_ERR(skb);
> +
> +			if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) {
> +				xdp_xmit |= xdp_res;
> +			} else if (xdp_res == IGB_XDP_EXIT) {
> +				failure = true;
> +				break;
> +			} else if (xdp_res == IGB_XDP_CONSUMED) {
> +				xsk_buff_free(xdp);
> +			}
> +
> +			total_packets++;
> +			total_bytes += size;
> +
> +			igb_update_ntc(rx_ring);
> +			continue;
> +		}
> +
> +		skb = igb_construct_skb_zc(rx_ring, xdp, timestamp);
> +
> +		/* exit if we failed to retrieve a buffer */
> +		if (!skb) {
> +			rx_ring->rx_stats.alloc_failed++;
> +			break;
> +		}
> +
> +		xsk_buff_free(xdp);
> +		igb_update_ntc(rx_ring);
> +
> +		if (eth_skb_pad(skb))
> +			continue;
> +
> +		/* probably a little skewed due to removing CRC */
> +		total_bytes += skb->len;
> +
> +		/* populate checksum, timestamp, VLAN, and protocol */
> +		igb_process_skb_fields(rx_ring, rx_desc, skb);
> +
> +		napi_gro_receive(&q_vector->napi, skb);
> +
> +		/* update budget accounting */
> +		total_packets++;
> +	}
> +
> +	if (xdp_xmit & IGB_XDP_REDIR)
> +		xdp_do_flush();
> +
> +	if (xdp_xmit & IGB_XDP_TX) {
> +		struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);

pull this out to common function and use this in igb_clean_rx_irq() ?

> +
> +		nq = txring_txq(tx_ring);
> +		__netif_tx_lock(nq, cpu);
> +		igb_xdp_ring_update_tail(tx_ring);
> +		__netif_tx_unlock(nq);
> +	}
> +
> +	u64_stats_update_begin(&rx_ring->rx_syncp);
> +	rx_ring->rx_stats.packets += total_packets;
> +	rx_ring->rx_stats.bytes += total_bytes;
> +	u64_stats_update_end(&rx_ring->rx_syncp);
> +	q_vector->rx.total_packets += total_packets;
> +	q_vector->rx.total_bytes += total_bytes;

... same here :)

> +
> +	entries_to_alloc = igb_desc_unused(rx_ring);
> +	if (entries_to_alloc >= IGB_RX_BUFFER_WRITE)
> +		failure |= !igb_alloc_rx_buffers_zc(rx_ring, entries_to_alloc);
> +
> +	if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) {
> +		if (failure || rx_ring->next_to_clean == rx_ring->next_to_use)
> +			xsk_set_rx_need_wakeup(rx_ring->xsk_pool);
> +		else
> +			xsk_clear_rx_need_wakeup(rx_ring->xsk_pool);
> +
> +		return (int)total_packets;
> +	}
> +	return failure ? budget : (int)total_packets;
> +}
> +
>  int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
>  {
>  	struct igb_adapter *adapter = netdev_priv(dev);
> -- 
> 2.42.0
> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ