Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit b753c5a7 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'r8152-RX-improve' 



Hayes says:

====================
v2:
For patch #2, replace list_for_each_safe with list_for_each_entry_safe.
Remove unlikely in WARN_ON. Adjust the coding style.

For patch #4, replace list_for_each_safe with list_for_each_entry_safe.
Remove "else" after "continue".

For patch #5. replace sysfs with ethtool to modify rx_copybreak and
rx_pending.

v1:
The different chips use different rx buffer size.

Use skb_add_rx_frag() to reduce memory copy for RX.
====================

Signed-off-by: default avatarJakub Kicinski <jakub.kicinski@netronome.com>
parents e070ca37 e4a5017a

drivers/net/usb/r8152.c

+304 −70
Original line number Diff line number Diff line
@@ -22,10 +22,11 @@ 
#include <linux/mdio.h>

#include <linux/usb/cdc.h>

#include <linux/suspend.h>

#include <linux/atomic.h>

#include <linux/acpi.h>



/* Information for net-next */

#define NETNEXT_VERSION		"09"

#define NETNEXT_VERSION		"10"



/* Information for net */

#define NET_VERSION		"10"
@@ -583,6 +584,9 @@ enum rtl_register_content { 
#define TX_ALIGN		4

#define RX_ALIGN		8



#define RTL8152_RX_MAX_PENDING	4096

#define RTL8152_RXFG_HEADSZ	256



#define INTR_LINK		0x0004



#define RTL8152_REQT_READ	0xc0
@@ -694,11 +698,11 @@ struct tx_desc { 
struct r8152;



struct rx_agg {

	struct list_head list;

	struct list_head list, info_list;

	struct urb *urb;

	struct r8152 *context;

	struct page *page;

	void *buffer;

	void *head;

};



struct tx_agg {
@@ -719,7 +723,7 @@ struct r8152 { 
	struct net_device *netdev;

	struct urb *intr_urb;

	struct tx_agg tx_info[RTL8152_MAX_TX];

	struct rx_agg rx_info[RTL8152_MAX_RX];

	struct list_head rx_info, rx_used;

	struct list_head rx_done, tx_free;

	struct sk_buff_head tx_queue, rx_queue;

	spinlock_t rx_lock, tx_lock;
@@ -744,11 +748,17 @@ struct r8152 { 
		void (*autosuspend_en)(struct r8152 *tp, bool enable);

	} rtl_ops;



	atomic_t rx_count;



	int intr_interval;

	u32 saved_wolopts;

	u32 msg_enable;

	u32 tx_qlen;

	u32 coalesce;

	u32 rx_buf_sz;

	u32 rx_copybreak;

	u32 rx_pending;



	u16 ocp_base;

	u16 speed;

	u8 *intr_buff;
@@ -1467,18 +1477,72 @@ static inline void *tx_agg_align(void *data) 
	return (void *)ALIGN((uintptr_t)data, TX_ALIGN);

}



static void free_rx_agg(struct r8152 *tp, struct rx_agg *agg)

{

	list_del(&agg->info_list);



	usb_free_urb(agg->urb);

	put_page(agg->page);

	kfree(agg);



	atomic_dec(&tp->rx_count);

}



static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags)

{

	struct net_device *netdev = tp->netdev;

	int node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1;

	unsigned int order = get_order(tp->rx_buf_sz);

	struct rx_agg *rx_agg;

	unsigned long flags;



	rx_agg = kmalloc_node(sizeof(*rx_agg), mflags, node);

	if (!rx_agg)

		return NULL;



	rx_agg->page = alloc_pages(mflags | __GFP_COMP, order);

	if (!rx_agg->page)

		goto free_rx;



	rx_agg->buffer = page_address(rx_agg->page);



	rx_agg->urb = usb_alloc_urb(0, mflags);

	if (!rx_agg->urb)

		goto free_buf;



	rx_agg->context = tp;



	INIT_LIST_HEAD(&rx_agg->list);

	INIT_LIST_HEAD(&rx_agg->info_list);

	spin_lock_irqsave(&tp->rx_lock, flags);

	list_add_tail(&rx_agg->info_list, &tp->rx_info);

	spin_unlock_irqrestore(&tp->rx_lock, flags);



	atomic_inc(&tp->rx_count);



	return rx_agg;



free_buf:

	__free_pages(rx_agg->page, order);

free_rx:

	kfree(rx_agg);

	return NULL;

}



static void free_all_mem(struct r8152 *tp)

{

	struct rx_agg *agg, *agg_next;

	unsigned long flags;

	int i;



	for (i = 0; i < RTL8152_MAX_RX; i++) {

		usb_free_urb(tp->rx_info[i].urb);

		tp->rx_info[i].urb = NULL;

	spin_lock_irqsave(&tp->rx_lock, flags);



		kfree(tp->rx_info[i].buffer);

		tp->rx_info[i].buffer = NULL;

		tp->rx_info[i].head = NULL;

	}

	list_for_each_entry_safe(agg, agg_next, &tp->rx_info, info_list)

		free_rx_agg(tp, agg);



	spin_unlock_irqrestore(&tp->rx_lock, flags);



	WARN_ON(atomic_read(&tp->rx_count));



	for (i = 0; i < RTL8152_MAX_TX; i++) {

		usb_free_urb(tp->tx_info[i].urb);
@@ -1502,46 +1566,28 @@ static int alloc_all_mem(struct r8152 *tp) 
	struct usb_interface *intf = tp->intf;

	struct usb_host_interface *alt = intf->cur_altsetting;

	struct usb_host_endpoint *ep_intr = alt->endpoint + 2;

	struct urb *urb;

	int node, i;

	u8 *buf;



	node = netdev->dev.parent ? dev_to_node(netdev->dev.parent) : -1;



	spin_lock_init(&tp->rx_lock);

	spin_lock_init(&tp->tx_lock);

	INIT_LIST_HEAD(&tp->rx_info);

	INIT_LIST_HEAD(&tp->tx_free);

	INIT_LIST_HEAD(&tp->rx_done);

	skb_queue_head_init(&tp->tx_queue);

	skb_queue_head_init(&tp->rx_queue);

	atomic_set(&tp->rx_count, 0);



	for (i = 0; i < RTL8152_MAX_RX; i++) {

		buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node);

		if (!buf)

			goto err1;



		if (buf != rx_agg_align(buf)) {

			kfree(buf);

			buf = kmalloc_node(agg_buf_sz + RX_ALIGN, GFP_KERNEL,

					   node);

			if (!buf)

		if (!alloc_rx_agg(tp, GFP_KERNEL))

			goto err1;

	}



		urb = usb_alloc_urb(0, GFP_KERNEL);

		if (!urb) {

			kfree(buf);

			goto err1;

		}



		INIT_LIST_HEAD(&tp->rx_info[i].list);

		tp->rx_info[i].context = tp;

		tp->rx_info[i].urb = urb;

		tp->rx_info[i].buffer = buf;

		tp->rx_info[i].head = rx_agg_align(buf);

	}



	for (i = 0; i < RTL8152_MAX_TX; i++) {

		struct urb *urb;

		u8 *buf;



		buf = kmalloc_node(agg_buf_sz, GFP_KERNEL, node);

		if (!buf)

			goto err1;
@@ -1907,6 +1953,46 @@ static u8 r8152_rx_csum(struct r8152 *tp, struct rx_desc *rx_desc) 
	return checksum;

}



static inline bool rx_count_exceed(struct r8152 *tp)

{

	return atomic_read(&tp->rx_count) > RTL8152_MAX_RX;

}



static inline int agg_offset(struct rx_agg *agg, void *addr)

{

	return (int)(addr - agg->buffer);

}



static struct rx_agg *rtl_get_free_rx(struct r8152 *tp, gfp_t mflags)

{

	struct rx_agg *agg, *agg_next, *agg_free = NULL;

	unsigned long flags;



	spin_lock_irqsave(&tp->rx_lock, flags);



	list_for_each_entry_safe(agg, agg_next, &tp->rx_used, list) {

		if (page_count(agg->page) == 1) {

			if (!agg_free) {

				list_del_init(&agg->list);

				agg_free = agg;

				continue;

			}

			if (rx_count_exceed(tp)) {

				list_del_init(&agg->list);

				free_rx_agg(tp, agg);

			}

			break;

		}

	}



	spin_unlock_irqrestore(&tp->rx_lock, flags);



	if (!agg_free && atomic_read(&tp->rx_count) < tp->rx_pending)

		agg_free = alloc_rx_agg(tp, mflags);



	return agg_free;

}



static int rx_bottom(struct r8152 *tp, int budget)

{

	unsigned long flags;
@@ -1942,7 +2028,7 @@ static int rx_bottom(struct r8152 *tp, int budget) 


	list_for_each_safe(cursor, next, &rx_queue) {

		struct rx_desc *rx_desc;

		struct rx_agg *agg;

		struct rx_agg *agg, *agg_free;

		int len_used = 0;

		struct urb *urb;

		u8 *rx_data;
@@ -1954,14 +2040,16 @@ static int rx_bottom(struct r8152 *tp, int budget) 
		if (urb->actual_length < ETH_ZLEN)

			goto submit;



		rx_desc = agg->head;

		rx_data = agg->head;

		agg_free = rtl_get_free_rx(tp, GFP_ATOMIC);



		rx_desc = agg->buffer;

		rx_data = agg->buffer;

		len_used += sizeof(struct rx_desc);



		while (urb->actual_length > len_used) {

			struct net_device *netdev = tp->netdev;

			struct net_device_stats *stats = &netdev->stats;

			unsigned int pkt_len;

			unsigned int pkt_len, rx_frag_head_sz;

			struct sk_buff *skb;



			/* limite the skb numbers for rx_queue */
@@ -1979,22 +2067,37 @@ static int rx_bottom(struct r8152 *tp, int budget) 
			pkt_len -= ETH_FCS_LEN;

			rx_data += sizeof(struct rx_desc);



			skb = napi_alloc_skb(napi, pkt_len);

			if (!agg_free || tp->rx_copybreak > pkt_len)

				rx_frag_head_sz = pkt_len;

			else

				rx_frag_head_sz = tp->rx_copybreak;



			skb = napi_alloc_skb(napi, rx_frag_head_sz);

			if (!skb) {

				stats->rx_dropped++;

				goto find_next_rx;

			}



			skb->ip_summed = r8152_rx_csum(tp, rx_desc);

			memcpy(skb->data, rx_data, pkt_len);

			skb_put(skb, pkt_len);

			memcpy(skb->data, rx_data, rx_frag_head_sz);

			skb_put(skb, rx_frag_head_sz);

			pkt_len -= rx_frag_head_sz;

			rx_data += rx_frag_head_sz;

			if (pkt_len) {

				skb_add_rx_frag(skb, 0, agg->page,

						agg_offset(agg, rx_data),

						pkt_len,

						SKB_DATA_ALIGN(pkt_len));

				get_page(agg->page);

			}



			skb->protocol = eth_type_trans(skb, netdev);

			rtl_rx_vlan_tag(rx_desc, skb);

			if (work_done < budget) {

				napi_gro_receive(napi, skb);

				work_done++;

				stats->rx_packets++;

				stats->rx_bytes += pkt_len;

				stats->rx_bytes += skb->len;

			} else {

				__skb_queue_tail(&tp->rx_queue, skb);

			}
@@ -2002,10 +2105,24 @@ static int rx_bottom(struct r8152 *tp, int budget) 
find_next_rx:

			rx_data = rx_agg_align(rx_data + pkt_len + ETH_FCS_LEN);

			rx_desc = (struct rx_desc *)rx_data;

			len_used = (int)(rx_data - (u8 *)agg->head);

			len_used = agg_offset(agg, rx_data);

			len_used += sizeof(struct rx_desc);

		}



		WARN_ON(!agg_free && page_count(agg->page) > 1);



		if (agg_free) {

			spin_lock_irqsave(&tp->rx_lock, flags);

			if (page_count(agg->page) == 1) {

				list_add(&agg_free->list, &tp->rx_used);

			} else {

				list_add_tail(&agg->list, &tp->rx_used);

				agg = agg_free;

				urb = agg->urb;

			}

			spin_unlock_irqrestore(&tp->rx_lock, flags);

		}



submit:

		if (!ret) {

			ret = r8152_submit_rx(tp, agg, GFP_ATOMIC);
@@ -2113,7 +2230,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) 
		return 0;



	usb_fill_bulk_urb(agg->urb, tp->udev, usb_rcvbulkpipe(tp->udev, 1),

			  agg->head, agg_buf_sz,

			  agg->buffer, tp->rx_buf_sz,

			  (usb_complete_t)read_bulk_callback, agg);



	ret = usb_submit_urb(agg->urb, mem_flags);
@@ -2330,44 +2447,80 @@ static void rxdy_gated_en(struct r8152 *tp, bool enable) 


static int rtl_start_rx(struct r8152 *tp)

{

	int i, ret = 0;

	struct rx_agg *agg, *agg_next;

	struct list_head tmp_list;

	unsigned long flags;

	int ret = 0, i = 0;



	INIT_LIST_HEAD(&tp->rx_done);

	for (i = 0; i < RTL8152_MAX_RX; i++) {

		INIT_LIST_HEAD(&tp->rx_info[i].list);

		ret = r8152_submit_rx(tp, &tp->rx_info[i], GFP_KERNEL);

		if (ret)

			break;

	}

	INIT_LIST_HEAD(&tmp_list);



	if (ret && ++i < RTL8152_MAX_RX) {

		struct list_head rx_queue;

		unsigned long flags;

	spin_lock_irqsave(&tp->rx_lock, flags);



		INIT_LIST_HEAD(&rx_queue);

	INIT_LIST_HEAD(&tp->rx_done);

	INIT_LIST_HEAD(&tp->rx_used);



		do {

			struct rx_agg *agg = &tp->rx_info[i++];

			struct urb *urb = agg->urb;

	list_splice_init(&tp->rx_info, &tmp_list);



			urb->actual_length = 0;

			list_add_tail(&agg->list, &rx_queue);

		} while (i < RTL8152_MAX_RX);

	spin_unlock_irqrestore(&tp->rx_lock, flags);



	list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) {

		INIT_LIST_HEAD(&agg->list);



		/* Only RTL8152_MAX_RX rx_agg need to be submitted. */

		if (++i > RTL8152_MAX_RX) {

			spin_lock_irqsave(&tp->rx_lock, flags);

		list_splice_tail(&rx_queue, &tp->rx_done);

			list_add_tail(&agg->list, &tp->rx_used);

			spin_unlock_irqrestore(&tp->rx_lock, flags);

		} else if (unlikely(ret < 0)) {

			spin_lock_irqsave(&tp->rx_lock, flags);

			list_add_tail(&agg->list, &tp->rx_done);

			spin_unlock_irqrestore(&tp->rx_lock, flags);

		} else {

			ret = r8152_submit_rx(tp, agg, GFP_KERNEL);

		}

	}



	spin_lock_irqsave(&tp->rx_lock, flags);

	WARN_ON(!list_empty(&tp->rx_info));

	list_splice(&tmp_list, &tp->rx_info);

	spin_unlock_irqrestore(&tp->rx_lock, flags);



	return ret;

}



static int rtl_stop_rx(struct r8152 *tp)

{

	int i;

	struct rx_agg *agg, *agg_next;

	struct list_head tmp_list;

	unsigned long flags;



	INIT_LIST_HEAD(&tmp_list);



	/* The usb_kill_urb() couldn't be used in atomic.

	 * Therefore, move the list of rx_info to a tmp one.

	 * Then, list_for_each_entry_safe could be used without

	 * spin lock.

	 */



	for (i = 0; i < RTL8152_MAX_RX; i++)

		usb_kill_urb(tp->rx_info[i].urb);

	spin_lock_irqsave(&tp->rx_lock, flags);

	list_splice_init(&tp->rx_info, &tmp_list);

	spin_unlock_irqrestore(&tp->rx_lock, flags);



	list_for_each_entry_safe(agg, agg_next, &tmp_list, info_list) {

		/* At least RTL8152_MAX_RX rx_agg have the page_count being

		 * equal to 1, so the other ones could be freed safely.

		 */

		if (page_count(agg->page) > 1)

			free_rx_agg(tp, agg);

		else

			usb_kill_urb(agg->urb);

	}



	/* Move back the list of temp to the rx_info */

	spin_lock_irqsave(&tp->rx_lock, flags);

	WARN_ON(!list_empty(&tp->rx_info));

	list_splice(&tmp_list, &tp->rx_info);

	spin_unlock_irqrestore(&tp->rx_lock, flags);



	while (!skb_queue_empty(&tp->rx_queue))

		dev_kfree_skb(__skb_dequeue(&tp->rx_queue));
@@ -2447,7 +2600,7 @@ static void r8153_set_rx_early_timeout(struct r8152 *tp) 


static void r8153_set_rx_early_size(struct r8152 *tp)

{

	u32 ocp_data = agg_buf_sz - rx_reserved_size(tp->netdev->mtu);

	u32 ocp_data = tp->rx_buf_sz - rx_reserved_size(tp->netdev->mtu);



	switch (tp->version) {

	case RTL_VER_03:
@@ -4954,6 +5107,77 @@ static int rtl8152_set_coalesce(struct net_device *netdev, 
	return ret;

}



static int rtl8152_get_tunable(struct net_device *netdev,

			       const struct ethtool_tunable *tunable, void *d)

{

	struct r8152 *tp = netdev_priv(netdev);



	switch (tunable->id) {

	case ETHTOOL_RX_COPYBREAK:

		*(u32 *)d = tp->rx_copybreak;

		break;

	default:

		return -EOPNOTSUPP;

	}



	return 0;

}



static int rtl8152_set_tunable(struct net_device *netdev,

			       const struct ethtool_tunable *tunable,

			       const void *d)

{

	struct r8152 *tp = netdev_priv(netdev);

	u32 val;



	switch (tunable->id) {

	case ETHTOOL_RX_COPYBREAK:

		val = *(u32 *)d;

		if (val < ETH_ZLEN) {

			netif_err(tp, rx_err, netdev,

				  "Invalid rx copy break value\n");

			return -EINVAL;

		}



		if (tp->rx_copybreak != val) {

			napi_disable(&tp->napi);

			tp->rx_copybreak = val;

			napi_enable(&tp->napi);

		}

		break;

	default:

		return -EOPNOTSUPP;

	}



	return 0;

}



static void rtl8152_get_ringparam(struct net_device *netdev,

				  struct ethtool_ringparam *ring)

{

	struct r8152 *tp = netdev_priv(netdev);



	ring->rx_max_pending = RTL8152_RX_MAX_PENDING;

	ring->rx_pending = tp->rx_pending;

}



static int rtl8152_set_ringparam(struct net_device *netdev,

				 struct ethtool_ringparam *ring)

{

	struct r8152 *tp = netdev_priv(netdev);



	if (ring->rx_pending < (RTL8152_MAX_RX * 2))

		return -EINVAL;



	if (tp->rx_pending != ring->rx_pending) {

		napi_disable(&tp->napi);

		tp->rx_pending = ring->rx_pending;

		napi_enable(&tp->napi);

	}



	return 0;

}



static const struct ethtool_ops ops = {

	.get_drvinfo = rtl8152_get_drvinfo,

	.get_link = ethtool_op_get_link,
@@ -4971,6 +5195,10 @@ static const struct ethtool_ops ops = { 
	.set_eee = rtl_ethtool_set_eee,

	.get_link_ksettings = rtl8152_get_link_ksettings,

	.set_link_ksettings = rtl8152_set_link_ksettings,

	.get_tunable = rtl8152_get_tunable,

	.set_tunable = rtl8152_set_tunable,

	.get_ringparam = rtl8152_get_ringparam,

	.set_ringparam = rtl8152_set_ringparam,

};



static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd)
@@ -5115,6 +5343,7 @@ static int rtl_ops_init(struct r8152 *tp) 
		ops->in_nway		= rtl8152_in_nway;

		ops->hw_phy_cfg		= r8152b_hw_phy_cfg;

		ops->autosuspend_en	= rtl_runtime_suspend_enable;

		tp->rx_buf_sz		= 16 * 1024;

		break;



	case RTL_VER_03:
@@ -5132,6 +5361,7 @@ static int rtl_ops_init(struct r8152 *tp) 
		ops->in_nway		= rtl8153_in_nway;

		ops->hw_phy_cfg		= r8153_hw_phy_cfg;

		ops->autosuspend_en	= rtl8153_runtime_enable;

		tp->rx_buf_sz		= 32 * 1024;

		break;



	case RTL_VER_08:
@@ -5147,6 +5377,7 @@ static int rtl_ops_init(struct r8152 *tp) 
		ops->in_nway		= rtl8153_in_nway;

		ops->hw_phy_cfg		= r8153b_hw_phy_cfg;

		ops->autosuspend_en	= rtl8153b_runtime_enable;

		tp->rx_buf_sz		= 32 * 1024;

		break;



	default:
@@ -5321,6 +5552,9 @@ static int rtl8152_probe(struct usb_interface *intf, 
	tp->speed = tp->mii.supports_gmii ? SPEED_1000 : SPEED_100;

	tp->duplex = DUPLEX_FULL;



	tp->rx_copybreak = RTL8152_RXFG_HEADSZ;

	tp->rx_pending = 10 * RTL8152_MAX_RX;



	intf->needs_remote_wakeup = 1;



	tp->rtl_ops.init(tp);