* Re: [PATCH net-next v3 af-packet 1/2] Enhance af-packet to provide (near zero)lossless packet capture functionality.
From: Eric Dumazet @ 2011-07-18 6:38 UTC (permalink / raw)
To: Chetan Loke; +Cc: davem, netdev
In-Reply-To: <1310959610-1688-2-git-send-email-loke.chetan@gmail.com>
Le dimanche 17 juillet 2011 à 23:26 -0400, Chetan Loke a écrit :
> Signed-off-by: Chetan Loke <loke.chetan@gmail.com>
> ---
> include/linux/if_packet.h | 125 +++++++++++++++++++++++++++++++++++++++++++++
> 1 files changed, 125 insertions(+), 0 deletions(-)
>
> +struct tpacket3_hdr {
> + __u32 tp_status;
> + __u32 tp_next_offset;
> + __u32 tp_len;
> + __u32 tp_snaplen;
> + __u16 tp_mac;
> + __u16 tp_net;
> + __u32 tp_sec;
> + __u32 tp_nsec;
> + __u32 tp_rxhash;
> + __u16 tp_vlan_tci;
> + __u16 tp_padding;
> + __u32 tp_next_offset;
> +};
Srange, I see tp_next_offset twice in tpacket3_hdr ?
^ permalink raw reply
* linux-next: manual merge of the net tree with Linus' tree
From: Stephen Rothwell @ 2011-07-18 4:41 UTC (permalink / raw)
To: David Miller, netdev
Cc: linux-next, linux-kernel, Ilia Kolomisnky, Gustavo F. Padovan,
Luiz Augusto von Dentz
Hi all,
Today's linux-next merge of the net tree got a conflict in
net/bluetooth/l2cap_core.c between commit 9191e6ad897a ("Bluetooth: Fix
regression in L2CAP connection procedure") from Linus' tree and commit
e2fd318e3a92 ("Bluetooth: Fixes l2cap "command reject" reply according to
spec") from the net tree.
I fixed it up (see below) and can carry the fix as necessary.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
diff --cc net/bluetooth/l2cap_core.c
index 7705e26,f7f8e2c..0000000
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@@ -620,11 -763,10 +763,11 @@@ static void l2cap_conn_start(struct l2c
struct sock *parent = bt_sk(sk)->parent;
rsp.result = cpu_to_le16(L2CAP_CR_PEND);
rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND);
- parent->sk_data_ready(parent, 0);
+ if (parent)
+ parent->sk_data_ready(parent, 0);
} else {
- sk->sk_state = BT_CONFIG;
+ l2cap_state_change(chan, BT_CONFIG);
rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS);
rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO);
}
@@@ -2324,10 -2523,14 +2524,13 @@@ static inline int l2cap_config_req(stru
sk = chan->sk;
- if (sk->sk_state != BT_CONFIG && sk->sk_state != BT_CONNECT2) {
- struct l2cap_cmd_rej rej;
- if ((bt_sk(sk)->defer_setup && chan->state != BT_CONNECT2) ||
- (!bt_sk(sk)->defer_setup && chan->state != BT_CONFIG)) {
++ if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) {
+ struct l2cap_cmd_rej_cid rej;
+
+ rej.reason = cpu_to_le16(L2CAP_REJ_INVALID_CID);
+ rej.scid = cpu_to_le16(chan->scid);
+ rej.dcid = cpu_to_le16(chan->dcid);
- rej.reason = cpu_to_le16(0x0002);
l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ,
sizeof(rej), &rej);
goto unlock;
@@@ -4010,10 -4150,9 +4150,10 @@@ static int l2cap_security_cfm(struct hc
struct sock *parent = bt_sk(sk)->parent;
res = L2CAP_CR_PEND;
stat = L2CAP_CS_AUTHOR_PEND;
- parent->sk_data_ready(parent, 0);
+ if (parent)
+ parent->sk_data_ready(parent, 0);
} else {
- sk->sk_state = BT_CONFIG;
+ l2cap_state_change(chan, BT_CONFIG);
res = L2CAP_CR_SUCCESS;
stat = L2CAP_CS_NO_INFO;
}
^ permalink raw reply
* Re: [PATCH] Fix panic in virtnet_remove
From: Krishna Kumar @ 2011-07-18 3:57 UTC (permalink / raw)
To: mst; +Cc: netdev, shemminger, davem, Krishna Kumar
"Michael S. Tsirkin" <mst@redhat.com> wrote on 07/17/2011 03:42:15 PM:
> > modprobe -r virtio_net panics in free_netdev() as the
> > dev is already freed in the newly introduced virtnet_free
> > (commit 3fa2a1df9094).
>
> Good catch, thanks!
>
> > Since virtnet_remove doesn't require
> > dev after unregister,
>
> I'm not sure that true: vi used just above the line you remove
> is I think the struct virtnet_info that is allocated
> as part of that structure.
You are right, the dev cannot be freed in the destructor.
> > I am removing the free_netdev call
> > in virtnet_remove instead of in virtnet_free (which seems
> > to be the right place to free the dev). Confirmed that
> > the panic is fixed with this patch.
>
> This might be just because the memory isn't reused.
> Try enabling slab poisoning, I think you'll observe some problems.
>
> Do we absolutely have to have a destructor?
> Can't we move the per cpu counter free from
> virtnet_free to virtnet_remove, and get rid of
> virtnet_free completely?
I see some other drivers doing that, e.g. xennet_remove:
...
free_percpu(info->stats);
free_netdev(info->netdev);
...
How about this patch (compile tested only)?
Signed-off-by: Krishna Kumar <krkumar2@in.ibm.com>
---
drivers/net/virtio_net.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
diff -ruNp org/drivers/net/virtio_net.c new/drivers/net/virtio_net.c
--- org/drivers/net/virtio_net.c 2011-07-18 09:14:02.000000000 +0530
+++ new/drivers/net/virtio_net.c 2011-07-18 09:16:35.000000000 +0530
@@ -705,14 +705,6 @@ static void virtnet_netpoll(struct net_d
}
#endif
-static void virtnet_free(struct net_device *dev)
-{
- struct virtnet_info *vi = netdev_priv(dev);
-
- free_percpu(vi->stats);
- free_netdev(dev);
-}
-
static int virtnet_open(struct net_device *dev)
{
struct virtnet_info *vi = netdev_priv(dev);
@@ -959,7 +951,6 @@ static int virtnet_probe(struct virtio_d
/* Set up network device as normal. */
dev->netdev_ops = &virtnet_netdev;
dev->features = NETIF_F_HIGHDMA;
- dev->destructor = virtnet_free;
SET_ETHTOOL_OPS(dev, &virtnet_ethtool_ops);
SET_NETDEV_DEV(dev, &vdev->dev);
@@ -1122,6 +1113,7 @@ static void __devexit virtnet_remove(str
while (vi->pages)
__free_pages(get_a_page(vi, GFP_KERNEL), 0);
+ free_percpu(vi->stats);
free_netdev(vi->dev);
}
^ permalink raw reply
* Re: [PATCH net-next v3 af-packet 2/2] Enhance af-packet to provide (near zero)lossless packet capture functionality.
From: Joe Perches @ 2011-07-18 3:46 UTC (permalink / raw)
To: Chetan Loke; +Cc: davem, netdev
In-Reply-To: <1310959610-1688-3-git-send-email-loke.chetan@gmail.com>
On Sun, 2011-07-17 at 23:26 -0400, Chetan Loke wrote:
> diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
[]
> +#define V3_ALIGNMENT (8)
> +#define ALIGN_V3(x) (((x)+V3_ALIGNMENT-1)&~(V3_ALIGNMENT-1))
Maybe just use the kernel.h macro ALIGN()?
> +#define BLK_HDR_LEN (ALIGN_V3(sizeof(struct block_desc)))
So this becomes:
#define BLK_HDR_LEN ALIGN(sizeof(struct block_desc), V3_ALIGNMENT)
^ permalink raw reply
* [PATCH net-next v3 af-packet 2/2] Enhance af-packet to provide (near zero)lossless packet capture functionality.
From: Chetan Loke @ 2011-07-18 3:26 UTC (permalink / raw)
To: davem, netdev; +Cc: Chetan Loke
In-Reply-To: <1310959610-1688-1-git-send-email-loke.chetan@gmail.com>
1) Blocks can now be configured with non-static frame format.
Non-static frame format provides following benefits:
1.1) Increases packet density by a factor of 2x.
1.2) Ability to capture entire packet.
1.3) Captures 99% 64-byte traffic as seen by the kernel.
2) Read/poll is now at a block-level rather than at packet level.
3) Added user-configurable timeout knob for timing out blocks on slow/bursty links.
4) Block level processing now allows monitoring multiple links as a single
logical pipe.
Changes:
C1) tpacket_rcv()
C1.1) packet_current_frame() is replaced by packet_current_rx_frame()
The bulk of the processing is then moved in the following chain:
packet_current_rx_frame()
__packet_lookup_frame_in_block
fill_curr_block()
or
retire_current_block
dispatch_next_block
or
return NULL(queue is plugged/paused)
Signed-off-by: Chetan Loke <loke.chetan@gmail.com>
---
net/packet/af_packet.c | 920 +++++++++++++++++++++++++++++++++++++++++++++---
1 files changed, 874 insertions(+), 46 deletions(-)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c698cec..a6df380 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -40,6 +40,10 @@
* byte arrays at the end of sockaddr_ll
* and packet_mreq.
* Johann Baudy : Added TX RING.
+ * Chetan Loke : Implemented TPACKET_V3 block abstraction
+ * layer.
+ * Copyright (C) 2011, <lokec@ccs.neu.edu>
+ *
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
@@ -161,9 +165,62 @@ struct packet_mreq_max {
unsigned char mr_address[MAX_ADDR_LEN];
};
-static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
+static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
int closing, int tx_ring);
+
+#define V3_ALIGNMENT (8)
+#define ALIGN_V3(x) (((x)+V3_ALIGNMENT-1)&~(V3_ALIGNMENT-1))
+
+#define BLK_HDR_LEN (ALIGN_V3(sizeof(struct block_desc)))
+
+#define BLK_PLUS_PRIV(sz_of_priv) \
+ (BLK_HDR_LEN + ALIGN_V3((sz_of_priv)))
+
+struct kbdq_ft_ops {
+ int num_ops;
+ int (*fn_ptrs[1])(void *, void *);
+};
+
+/* kbdq - kernel block descriptor queue */
+struct kbdq_core {
+ struct pgv *pkbdq;
+ unsigned int hdrlen;
+ unsigned char reset_pending_on_curr_blk;
+ unsigned char delete_blk_timer;
+ unsigned short kactive_blk_num;
+ unsigned short blk_sizeof_priv;
+
+ /* last_kactive_blk_num:
+ * trick to see if user-space has caught up
+ * in order to avoid refreshing timer when every single pkt arrives.
+ */
+ unsigned short last_kactive_blk_num;
+
+ char *pkblk_start;
+ char *pkblk_end;
+ int kblk_size;
+ unsigned int knum_blocks;
+ uint64_t knxt_seq_num;
+ char *prev;
+ char *nxt_offset;
+ struct sk_buff *skb;
+ struct kbdq_ft_ops kfops;
+
+ atomic_t blk_fill_in_prog;
+
+ /* Default is set to 8ms */
+#define DEFAULT_PRB_RETIRE_TOV (8)
+
+ unsigned short retire_blk_tov;
+ unsigned short version;
+ unsigned long tov_in_jiffies;
+
+ /* timer to retire an outstanding block */
+ struct timer_list retire_blk_timer;
+};
+
+#define PGV_FROM_VMALLOC 1
struct pgv {
char *buffer;
};
@@ -179,12 +236,31 @@ struct packet_ring_buffer {
unsigned int pg_vec_pages;
unsigned int pg_vec_len;
+ struct kbdq_core prb_bdqc;
atomic_t pending;
};
struct packet_sock;
static int tpacket_snd(struct packet_sock *po, struct msghdr *msg);
+static void *packet_previous_frame(struct packet_sock *po,
+ struct packet_ring_buffer *rb,
+ int status);
+static void packet_increment_head(struct packet_ring_buffer *buff);
+static int prb_curr_blk_in_use(struct kbdq_core *,
+ struct block_desc *);
+static void *prb_dispatch_next_block(struct kbdq_core *,
+ struct packet_sock *);
+static void prb_retire_current_block(struct kbdq_core *,
+ struct packet_sock *, unsigned int status);
+static int prb_queue_frozen(struct kbdq_core *);
+static void prb_open_block(struct kbdq_core *, struct block_desc *);
+static void prb_retire_rx_blk_timer_expired(unsigned long);
+static void _prb_refresh_rx_retire_blk_timer(struct kbdq_core *);
+static void prb_init_blk_timer(struct packet_sock *, struct kbdq_core *,
+ void (*func) (unsigned long));
+static void prb_fill_rxhash(struct kbdq_core *,
+ struct tpacket3_hdr *);
static void packet_flush_mclist(struct sock *sk);
struct packet_fanout;
@@ -193,6 +269,7 @@ struct packet_sock {
struct sock sk;
struct packet_fanout *fanout;
struct tpacket_stats stats;
+ union tpacket_stats_u stats_u;
struct packet_ring_buffer rx_ring;
struct packet_ring_buffer tx_ring;
int copy_thresh;
@@ -242,6 +319,15 @@ struct packet_skb_cb {
#define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb))
+#define GET_PBDQC_FROM_RB(x) ((struct kbdq_core *)(&(x)->prb_bdqc))
+#define GET_PBLOCK_DESC(x, bid) \
+ ((struct block_desc *)((x)->pkbdq[(bid)].buffer))
+#define GET_CURR_PBLOCK_DESC_FROM_CORE(x) \
+ ((struct block_desc *)((x)->pkbdq[(x)->kactive_blk_num].buffer))
+#define GET_NEXT_PRB_BLK_NUM(x) \
+ (((x)->kactive_blk_num < ((x)->knum_blocks-1)) ? \
+ ((x)->kactive_blk_num+1) : 0)
+
static inline struct packet_sock *pkt_sk(struct sock *sk)
{
return (struct packet_sock *)sk;
@@ -325,8 +411,9 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status)
h.h2->tp_status = status;
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
break;
+ case TPACKET_V3:
default:
- pr_err("TPACKET version not supported\n");
+ WARN(1, "TPACKET version not supported.\n");
BUG();
}
@@ -351,8 +438,9 @@ static int __packet_get_status(struct packet_sock *po, void *frame)
case TPACKET_V2:
flush_dcache_page(pgv_to_page(&h.h2->tp_status));
return h.h2->tp_status;
+ case TPACKET_V3:
default:
- pr_err("TPACKET version not supported\n");
+ WARN(1, "TPACKET version not supported.\n");
BUG();
return 0;
}
@@ -389,6 +477,644 @@ static inline void *packet_current_frame(struct packet_sock *po,
return packet_lookup_frame(po, rb, rb->head, status);
}
+static void prb_del_retire_blk_timer(struct kbdq_core *pkc)
+{
+ del_timer_sync(&pkc->retire_blk_timer);
+}
+
+static void prb_shutdown_retire_blk_timer(struct packet_sock *po,
+ int tx_ring,
+ struct sk_buff_head *rb_queue)
+{
+ struct kbdq_core *pkc;
+
+ pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+
+ spin_lock(&rb_queue->lock);
+ pkc->delete_blk_timer = 1;
+ spin_unlock(&rb_queue->lock);
+
+ prb_del_retire_blk_timer(pkc);
+}
+
+static void prb_init_blk_timer(struct packet_sock *po,
+ struct kbdq_core *pkc,
+ void (*func) (unsigned long))
+{
+ init_timer(&pkc->retire_blk_timer);
+ pkc->retire_blk_timer.data = (long)po;
+ pkc->retire_blk_timer.function = func;
+ pkc->retire_blk_timer.expires = jiffies;
+}
+
+static void prb_setup_retire_blk_timer(struct packet_sock *po, int tx_ring)
+{
+ struct kbdq_core *pkc;
+
+ if (tx_ring)
+ BUG();
+
+ pkc = tx_ring ? &po->tx_ring.prb_bdqc : &po->rx_ring.prb_bdqc;
+ prb_init_blk_timer(po, pkc, prb_retire_rx_blk_timer_expired);
+}
+
+static int prb_calc_retire_blk_tmo(struct packet_sock *po,
+ int blk_size_in_bytes)
+{
+ struct net_device *dev;
+ unsigned int mbits = 0, msec = 0, div = 0, tmo = 0;
+
+ dev = dev_get_by_index(sock_net(&po->sk), po->ifindex);
+ if (unlikely(dev == NULL))
+ return DEFAULT_PRB_RETIRE_TOV;
+
+ if (dev->ethtool_ops && dev->ethtool_ops->get_settings) {
+ struct ethtool_cmd ecmd = { .cmd = ETHTOOL_GSET, };
+
+ if (!dev->ethtool_ops->get_settings(dev, &ecmd)) {
+ switch (ecmd.speed) {
+ case SPEED_10000:
+ msec = 1;
+ div = 10000/1000;
+ break;
+ case SPEED_1000:
+ msec = 1;
+ div = 1000/1000;
+ break;
+ /*
+ * If the link speed is so slow you don't really
+ * need to worry about perf anyways
+ */
+ case SPEED_100:
+ case SPEED_10:
+ default:
+ return DEFAULT_PRB_RETIRE_TOV;
+ }
+ }
+ }
+
+ mbits = (blk_size_in_bytes * 8) / (1024 * 1024);
+
+ if (div)
+ mbits /= div;
+
+ tmo = mbits * msec;
+
+ if (div)
+ return tmo+1;
+ return tmo;
+}
+
+static void init_prb_bdqc(struct packet_sock *po,
+ struct packet_ring_buffer *rb,
+ struct pgv *pg_vec,
+ union tpacket_req_u *req_u, int tx_ring)
+{
+ struct kbdq_core *p1 = &rb->prb_bdqc;
+ struct block_desc *pbd;
+
+ memset(p1, 0x0, sizeof(*p1));
+
+ if (req_u->req3.tp_feature_req_word) {
+ if (req_u->req3.tp_feature_req_word & TP_FT_REQ_FILL_RXHASH) {
+ p1->kfops.fn_ptrs[p1->kfops.num_ops] = prb_fill_rxhash;
+ p1->kfops.num_ops += 1;
+ }
+ }
+
+ p1->knxt_seq_num = 1;
+ p1->pkbdq = pg_vec;
+ pbd = (struct block_desc *)pg_vec[0].buffer;
+ p1->pkblk_start = (char *)pg_vec[0].buffer;
+ p1->kblk_size = req_u->req3.tp_block_size;
+ p1->knum_blocks = req_u->req3.tp_block_nr;
+ p1->hdrlen = po->tp_hdrlen;
+ p1->version = po->tp_version;
+ p1->last_kactive_blk_num = 0;
+ po->stats_u.stats3.tp_freeze_q_cnt = 0;
+ if (req_u->req3.tp_retire_blk_tov)
+ p1->retire_blk_tov = req_u->req3.tp_retire_blk_tov;
+ else
+ p1->retire_blk_tov = prb_calc_retire_blk_tmo(po,
+ req_u->req3.tp_block_size);
+ p1->tov_in_jiffies = msecs_to_jiffies(p1->retire_blk_tov);
+ p1->blk_sizeof_priv = req_u->req3.tp_sizeof_priv;
+ prb_setup_retire_blk_timer(po, tx_ring);
+ prb_open_block(p1, pbd);
+}
+
+/* Do NOT update the last_blk_num first.
+ * Assumes sk_buff_head lock is held.
+ */
+static void _prb_refresh_rx_retire_blk_timer(struct kbdq_core *pkc)
+{
+ mod_timer(&pkc->retire_blk_timer,
+ jiffies + pkc->tov_in_jiffies);
+ pkc->last_kactive_blk_num = pkc->kactive_blk_num;
+}
+
+/*
+ * Timer logic:
+ * 1) We refresh the timer only when we open a block.
+ * By doing this we don't waste cycles refreshing the timer
+ * on packet-by-packet basis.
+ *
+ * With a 1MB block-size, on a 1Gbps line, it will take
+ * i) ~8 ms to fill a block + ii) memcpy etc.
+ * In this cut we are not accounting for the memcpy time.
+ *
+ * So, if the user sets the 'tmo' to 10ms then the timer
+ * will never fire while the block is still getting filled
+ * (which is what we want). However, the user could choose
+ * to close a block early and that's fine.
+ *
+ * But when the timer does fire, we check whether or not to refresh it.
+ * Since the tmo granularity is in msecs, it is not too expensive
+ * to refresh the timer, lets say every '8' msecs.
+ * Either the user can set the 'tmo' or we can derive it based on
+ * a) line-speed and b) block-size.
+ * prb_calc_retire_blk_tmo() calculates the tmo.
+ *
+ */
+static void prb_retire_rx_blk_timer_expired(unsigned long data)
+{
+ struct packet_sock *po = (struct packet_sock *)data;
+ struct kbdq_core *pkc = &po->rx_ring.prb_bdqc;
+ unsigned int frozen;
+ struct block_desc *pbd;
+
+ spin_lock(&po->sk.sk_receive_queue.lock);
+
+ frozen = prb_queue_frozen(pkc);
+ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
+
+ if (unlikely(pkc->delete_blk_timer))
+ goto out;
+
+ /* We only need to plug the race when the block is partially filled.
+ * tpacket_rcv:
+ * lock(); increment BLOCK_NUM_PKTS; unlock()
+ * copy_bits() is in progress ...
+ * timer fires on other cpu:
+ * we can't retire the current block because copy_bits
+ * is in progress.
+ *
+ */
+ if (BLOCK_NUM_PKTS(pbd)) {
+ while (atomic_read(&pkc->blk_fill_in_prog)) {
+ /* Waiting for skb_copy_bits to finish... */
+ cpu_relax();
+ }
+ }
+
+ if (pkc->last_kactive_blk_num == pkc->kactive_blk_num) {
+ if (!frozen) {
+ prb_retire_current_block(pkc, po, TP_STATUS_BLK_TMO);
+ if (!prb_dispatch_next_block(pkc, po))
+ goto refresh_timer;
+ else
+ goto out;
+ } else {
+ /* Case 1. Queue was frozen because user-space was
+ * lagging behind.
+ */
+ if (prb_curr_blk_in_use(pkc, pbd)) {
+ /*
+ * Ok, user-space is still behind.
+ * So just refresh the timer.
+ */
+ goto refresh_timer;
+ } else {
+ /* Case 2. queue was frozen,user-space caught up,
+ * now the link went idle && the timer fired.
+ * We don't have a block to close.So we open this
+ * block and restart the timer.
+ * opening a block thaws the queue,restarts timer
+ * Thawing/timer-refresh is a side effect.
+ */
+ prb_open_block(pkc, pbd);
+ goto out;
+ }
+ }
+ }
+
+refresh_timer:
+ _prb_refresh_rx_retire_blk_timer(pkc);
+
+out:
+ spin_unlock(&po->sk.sk_receive_queue.lock);
+}
+
+static inline void prb_flush_block(struct kbdq_core *pkc1,
+ struct block_desc *pbd1, __u32 status)
+{
+ /* Flush everything minus the block header */
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
+ u8 *start, *end;
+
+ start = (u8 *)pbd1;
+
+ /* Skip the block header(we know header WILL fit in 4K) */
+ start += PAGE_SIZE;
+
+ end = (u8 *)PAGE_ALIGN((unsigned long)pkc1->pkblk_end);
+ for (; start < end; start += PAGE_SIZE)
+ flush_dcache_page(pgv_to_page(start));
+
+ smp_wmb();
+#endif
+
+ /* Now update the block status. */
+
+ BLOCK_STATUS(pbd1) = status;
+
+ /* Flush the block header */
+
+#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
+ start = (u8 *)pbd1;
+ flush_dcache_page(pgv_to_page(start));
+
+ smp_wmb();
+#endif
+}
+
+/*
+ * Side effect:
+ *
+ * 1) flush the block
+ * 2) Increment active_blk_num
+ *
+ * Note:We DONT refresh the timer on purpose.
+ * Because almost always the next block will be opened.
+ */
+static void prb_close_block(struct kbdq_core *pkc1, struct block_desc *pbd1,
+ struct packet_sock *po, unsigned int stat)
+{
+ __u32 status = TP_STATUS_USER | stat;
+
+ struct tpacket3_hdr *last_pkt;
+ struct hdr_v1 *h1 = &pbd1->hdr.h1;
+
+ if (po->stats.tp_drops)
+ status |= TP_STATUS_LOSING;
+
+ last_pkt = (struct tpacket3_hdr *)pkc1->prev;
+ last_pkt->tp_next_offset = 0;
+
+ /* Get the ts of the last pkt */
+ if (BLOCK_NUM_PKTS(pbd1)) {
+ h1->ts_last_pkt.ts_sec = last_pkt->tp_sec;
+ h1->ts_last_pkt.ts_nsec = last_pkt->tp_nsec;
+ } else {
+ /* Ok, we tmo'd - so get the current time */
+ struct timespec ts;
+ getnstimeofday(&ts);
+ h1->ts_last_pkt.ts_sec = ts.tv_sec;
+ h1->ts_last_pkt.ts_nsec = ts.tv_nsec;
+ }
+
+ smp_wmb();
+
+ /* Flush the block */
+ prb_flush_block(pkc1, pbd1, status);
+
+ pkc1->kactive_blk_num = GET_NEXT_PRB_BLK_NUM(pkc1);
+}
+
+static inline void prb_thaw_queue(struct kbdq_core *pkc)
+{
+ pkc->reset_pending_on_curr_blk = 0;
+}
+
+/*
+ * Side effect of opening a block:
+ *
+ * 1) prb_queue is thawed.
+ * 2) retire_blk_timer is refreshed.
+ *
+ */
+static void prb_open_block(struct kbdq_core *pkc1, struct block_desc *pbd1)
+{
+ struct timespec ts;
+ struct hdr_v1 *h1 = &pbd1->hdr.h1;
+
+ smp_rmb();
+
+ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd1))) {
+
+ /* We could have just memset this but we will lose the
+ * flexibility of making the priv area sticky
+ */
+ BLOCK_SNUM(pbd1) = pkc1->knxt_seq_num++;
+ BLOCK_NUM_PKTS(pbd1) = 0;
+ BLOCK_LEN(pbd1) = BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
+ getnstimeofday(&ts);
+ h1->ts_first_pkt.ts_sec = ts.tv_sec;
+ h1->ts_first_pkt.ts_nsec = ts.tv_nsec;
+ pkc1->pkblk_start = (char *)pbd1;
+ pkc1->nxt_offset = (char *)(pkc1->pkblk_start +
+ BLK_PLUS_PRIV(pkc1->blk_sizeof_priv));
+ BLOCK_O2FP(pbd1) = (__u32)BLK_PLUS_PRIV(pkc1->blk_sizeof_priv);
+ BLOCK_O2PRIV(pbd1) = (__u16)BLK_HDR_LEN;
+ pbd1->version = pkc1->version;
+ pkc1->prev = pkc1->nxt_offset;
+ pkc1->pkblk_end = pkc1->pkblk_start + pkc1->kblk_size;
+ prb_thaw_queue(pkc1);
+ _prb_refresh_rx_retire_blk_timer(pkc1);
+
+ smp_wmb();
+
+ return;
+ }
+
+ WARN(1, "ERROR block:%p is NOT FREE status:%d kactive_blk_num:%d\n",
+ pbd1, BLOCK_STATUS(pbd1), pkc1->kactive_blk_num);
+ dump_stack();
+ BUG();
+}
+
+/*
+ * Queue freeze logic:
+ * 1) Assume tp_block_nr = 8 blocks.
+ * 2) At time 't0', user opens Rx ring.
+ * 3) Some time past 't0', kernel starts filling blocks starting from 0 .. 7
+ * 4) user-space is either sleeping or processing block '0'.
+ * 5) tpacket_rcv is currently filling block '7', since there is no space left,
+ * it will close block-7,loop around and try to fill block '0'.
+ * call-flow:
+ * __packet_lookup_frame_in_block
+ * prb_retire_current_block()
+ * prb_dispatch_next_block()
+ * |->(BLOCK_STATUS == USER) evaluates to true
+ * 5.1) Since block-0 is currently in-use, we just freeze the queue.
+ * 6) Now there are two cases:
+ * 6.1) Link goes idle right after the queue is frozen.
+ * But remember, the last open_block() refreshed the timer.
+ * When this timer expires,it will refresh itself so that we can
+ * re-open block-0 in near future.
+ * 6.2) Link is busy and keeps on receiving packets. This is a simple
+ * case and __packet_lookup_frame_in_block will check if block-0
+ * is free and can now be re-used.
+ */
+static inline void prb_freeze_queue(struct kbdq_core *pkc,
+ struct packet_sock *po)
+{
+ pkc->reset_pending_on_curr_blk = 1;
+ po->stats_u.stats3.tp_freeze_q_cnt++;
+}
+
+#define TOTAL_PKT_LEN_INCL_ALIGN(length) (ALIGN_V3((length)))
+
+/*
+ * If the next block is free then we will dispatch it
+ * and return a good offset.
+ * Else, we will freeze the queue.
+ * So, caller must check the return value.
+ */
+static void *prb_dispatch_next_block(struct kbdq_core *pkc,
+ struct packet_sock *po)
+{
+ struct block_desc *pbd;
+
+ smp_rmb();
+
+ /* 1. Get current block num */
+ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
+
+ /* 2. If this block is currently in_use then freeze the queue */
+ if (TP_STATUS_USER & BLOCK_STATUS(pbd)) {
+ prb_freeze_queue(pkc, po);
+ return NULL;
+ }
+
+ /*
+ * 3.
+ * open this block and return the offset where the first packet
+ * needs to get stored.
+ */
+ prb_open_block(pkc, pbd);
+ return (void *)pkc->nxt_offset;
+}
+
+static void prb_retire_current_block(struct kbdq_core *pkc,
+ struct packet_sock *po, unsigned int status)
+{
+ struct block_desc *pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
+
+ /* retire/close the current block */
+ if (likely(TP_STATUS_KERNEL == BLOCK_STATUS(pbd))) {
+ /*
+ * Plug the case where copy_bits() is in progress on
+ * cpu-0 and tpacket_rcv() got invoked on cpu-1, didn't
+ * have space to copy the pkt in the current block and
+ * called prb_retire_current_block()
+ *
+ * We don't need to worry about the TMO case because
+ * the timer-handler already handled this case.
+ */
+ if (!(status & TP_STATUS_BLK_TMO)) {
+ while (atomic_read(&pkc->blk_fill_in_prog)) {
+ /* Waiting for skb_copy_bits to finish... */
+ cpu_relax();
+ }
+ }
+ prb_close_block(pkc, pbd, po, status);
+ return;
+ }
+
+ WARN(1, "ERROR-pbd[%d]:%p\n", pkc->kactive_blk_num, pbd);
+ dump_stack();
+ BUG();
+}
+
+static inline int prb_curr_blk_in_use(struct kbdq_core *pkc,
+ struct block_desc *pbd)
+{
+ return TP_STATUS_USER & BLOCK_STATUS(pbd);
+}
+
+static inline int prb_queue_frozen(struct kbdq_core *pkc)
+{
+ return pkc->reset_pending_on_curr_blk;
+}
+
+static inline void prb_clear_blk_fill_status(struct packet_ring_buffer *rb)
+{
+ struct kbdq_core *pkc = GET_PBDQC_FROM_RB(rb);
+ atomic_dec(&pkc->blk_fill_in_prog);
+}
+
+static void prb_fill_rxhash(struct kbdq_core *pkc,
+ struct tpacket3_hdr *ppd)
+{
+ ppd->tp_rxhash = skb_get_rxhash(pkc->skb);
+}
+
+static void prb_run_all_ft_ops(struct kbdq_core *pkc,
+ struct tpacket3_hdr *ppd)
+{
+ int ops;
+ for (ops = 0; ops < pkc->kfops.num_ops; ops++)
+ pkc->kfops.fn_ptrs[ops](pkc, ppd);
+}
+
+static inline void prb_fill_curr_block(char *curr, struct kbdq_core *pkc,
+ struct block_desc *pbd,
+ unsigned int len)
+{
+ struct tpacket3_hdr *ppd;
+
+ ppd = (struct tpacket3_hdr *)curr;
+ ppd->tp_next_offset = TOTAL_PKT_LEN_INCL_ALIGN(len);
+ pkc->prev = curr;
+ pkc->nxt_offset += TOTAL_PKT_LEN_INCL_ALIGN(len);
+ BLOCK_LEN(pbd) += TOTAL_PKT_LEN_INCL_ALIGN(len);
+ BLOCK_NUM_PKTS(pbd) += 1;
+ atomic_inc(&pkc->blk_fill_in_prog);
+ prb_run_all_ft_ops(pkc, ppd);
+}
+
+/* Assumes caller has the sk->rx_queue.lock */
+static void *__packet_lookup_frame_in_block(struct packet_sock *po,
+ struct sk_buff *skb,
+ int status,
+ unsigned int len
+ )
+{
+ struct kbdq_core *pkc;
+ struct block_desc *pbd;
+ char *curr, *end;
+
+ pkc = GET_PBDQC_FROM_RB(((struct packet_ring_buffer *)&po->rx_ring));
+ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
+ pkc->skb = skb;
+
+ /* Queue is frozen when user space is lagging behind */
+ if (prb_queue_frozen(pkc)) {
+ /*
+ * Check if that last block which caused the queue to freeze,
+ * is still in_use by user-space.
+ */
+ if (prb_curr_blk_in_use(pkc, pbd)) {
+ /* Can't record this packet */
+ return NULL;
+ } else {
+ /*
+ * Ok, the block was released by user-space.
+ * Now let's open that block.
+ * opening a block also thaws the queue.
+ * Thawing is a side effect.
+ */
+ prb_open_block(pkc, pbd);
+ }
+ }
+
+ smp_mb();
+ curr = pkc->nxt_offset;
+ end = (char *) ((char *)pbd + pkc->kblk_size);
+
+ /* first try the current block */
+ if (curr+TOTAL_PKT_LEN_INCL_ALIGN(len) < end) {
+ prb_fill_curr_block(curr, pkc, pbd, len);
+ return (void *)curr;
+ }
+
+ /* Ok, close the current block */
+ prb_retire_current_block(pkc, po, 0);
+
+ /* Now, try to dispatch the next block */
+ curr = (char *)prb_dispatch_next_block(pkc, po);
+ if (curr) {
+ pbd = GET_CURR_PBLOCK_DESC_FROM_CORE(pkc);
+ prb_fill_curr_block(curr, pkc, pbd, len);
+ return (void *)curr;
+ }
+
+ /*
+ * No free blocks are available.user_space hasn't caught up yet.
+ * Queue was just frozen and now this packet will get dropped.
+ */
+ return NULL;
+}
+
+static inline void *packet_current_rx_frame(struct packet_sock *po,
+ struct sk_buff *skb,
+ int status, unsigned int len)
+{
+ char *curr = NULL;
+ switch (po->tp_version) {
+ case TPACKET_V1:
+ case TPACKET_V2:
+ curr = packet_lookup_frame(po, &po->rx_ring,
+ po->rx_ring.head, status);
+ return curr;
+ case TPACKET_V3:
+ return __packet_lookup_frame_in_block(po, skb, status, len);
+ default:
+ WARN(1, "TPACKET version not supported\n");
+ BUG();
+ return 0;
+ }
+}
+
+static inline void *prb_lookup_block(struct packet_sock *po,
+ struct packet_ring_buffer *rb,
+ unsigned int previous,
+ int status)
+{
+ struct kbdq_core *pkc = GET_PBDQC_FROM_RB(rb);
+ struct block_desc *pbd = GET_PBLOCK_DESC(pkc, previous);
+
+ if (status != BLOCK_STATUS(pbd))
+ return NULL;
+ return pbd;
+}
+
+static inline int prb_previous_blk_num(struct packet_ring_buffer *rb)
+{
+ unsigned int prev;
+ if (rb->prb_bdqc.kactive_blk_num)
+ prev = rb->prb_bdqc.kactive_blk_num-1;
+ else
+ prev = rb->prb_bdqc.knum_blocks-1;
+ return prev;
+}
+
+/* Assumes caller has held the rx_queue.lock */
+static inline void *__prb_previous_block(struct packet_sock *po,
+ struct packet_ring_buffer *rb,
+ int status)
+{
+ unsigned int previous = prb_previous_blk_num(rb);
+ return prb_lookup_block(po, rb, previous, status);
+}
+
+static inline void *packet_previous_rx_frame(struct packet_sock *po,
+ struct packet_ring_buffer *rb,
+ int status)
+{
+ if (po->tp_version <= TPACKET_V2)
+ return packet_previous_frame(po, rb, status);
+
+ return __prb_previous_block(po, rb, status);
+}
+
+static inline void packet_increment_rx_head(struct packet_sock *po,
+ struct packet_ring_buffer *rb)
+{
+ switch (po->tp_version) {
+ case TPACKET_V1:
+ case TPACKET_V2:
+ return packet_increment_head(rb);
+ case TPACKET_V3:
+ default:
+ WARN(1, "TPACKET version not supported.\n");
+ BUG();
+ return;
+ }
+}
+
static inline void *packet_previous_frame(struct packet_sock *po,
struct packet_ring_buffer *rb,
int status)
@@ -982,12 +1708,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
union {
struct tpacket_hdr *h1;
struct tpacket2_hdr *h2;
+ struct tpacket3_hdr *h3;
void *raw;
} h;
u8 *skb_head = skb->data;
int skb_len = skb->len;
unsigned int snaplen, res;
- unsigned long status = TP_STATUS_LOSING|TP_STATUS_USER;
+ unsigned long status = TP_STATUS_USER;
unsigned short macoff, netoff, hdrlen;
struct sk_buff *copy_skb = NULL;
struct timeval tv;
@@ -1033,37 +1760,46 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
po->tp_reserve;
macoff = netoff - maclen;
}
-
- if (macoff + snaplen > po->rx_ring.frame_size) {
- if (po->copy_thresh &&
- atomic_read(&sk->sk_rmem_alloc) + skb->truesize <
- (unsigned)sk->sk_rcvbuf) {
- if (skb_shared(skb)) {
- copy_skb = skb_clone(skb, GFP_ATOMIC);
- } else {
- copy_skb = skb_get(skb);
- skb_head = skb->data;
+ if (po->tp_version <= TPACKET_V2) {
+ if (macoff + snaplen > po->rx_ring.frame_size) {
+ if (po->copy_thresh &&
+ atomic_read(&sk->sk_rmem_alloc) + skb->truesize
+ < (unsigned)sk->sk_rcvbuf) {
+ if (skb_shared(skb)) {
+ copy_skb = skb_clone(skb, GFP_ATOMIC);
+ } else {
+ copy_skb = skb_get(skb);
+ skb_head = skb->data;
+ }
+ if (copy_skb)
+ skb_set_owner_r(copy_skb, sk);
}
- if (copy_skb)
- skb_set_owner_r(copy_skb, sk);
+ snaplen = po->rx_ring.frame_size - macoff;
+ if ((int)snaplen < 0)
+ snaplen = 0;
}
- snaplen = po->rx_ring.frame_size - macoff;
- if ((int)snaplen < 0)
- snaplen = 0;
}
-
spin_lock(&sk->sk_receive_queue.lock);
- h.raw = packet_current_frame(po, &po->rx_ring, TP_STATUS_KERNEL);
+ h.raw = packet_current_rx_frame(po, skb,
+ TP_STATUS_KERNEL, (macoff+snaplen));
if (!h.raw)
goto ring_is_full;
- packet_increment_head(&po->rx_ring);
+ if (po->tp_version <= TPACKET_V2) {
+ packet_increment_rx_head(po, &po->rx_ring);
+ /*
+ * LOSING will be reported till you read the stats,
+ * because it's COR - Clear On Read.
+ * Anyways, moving it for V1/V2 only as V3 doesn't need this
+ * at packet level.
+ */
+ if (po->stats.tp_drops)
+ status |= TP_STATUS_LOSING;
+ }
po->stats.tp_packets++;
if (copy_skb) {
status |= TP_STATUS_COPY;
__skb_queue_tail(&sk->sk_receive_queue, copy_skb);
}
- if (!po->stats.tp_drops)
- status &= ~TP_STATUS_LOSING;
spin_unlock(&sk->sk_receive_queue.lock);
skb_copy_bits(skb, 0, h.raw + macoff, snaplen);
@@ -1114,6 +1850,36 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
h.h2->tp_padding = 0;
hdrlen = sizeof(*h.h2);
break;
+ case TPACKET_V3:
+ /* tp_nxt_offset is already populated above.
+ * So DONT clear those fields here
+ */
+ h.h3->tp_status = status;
+ h.h3->tp_len = skb->len;
+ h.h3->tp_snaplen = snaplen;
+ h.h3->tp_mac = macoff;
+ h.h3->tp_net = netoff;
+ if ((po->tp_tstamp & SOF_TIMESTAMPING_SYS_HARDWARE)
+ && shhwtstamps->syststamp.tv64)
+ ts = ktime_to_timespec(shhwtstamps->syststamp);
+ else if ((po->tp_tstamp & SOF_TIMESTAMPING_RAW_HARDWARE)
+ && shhwtstamps->hwtstamp.tv64)
+ ts = ktime_to_timespec(shhwtstamps->hwtstamp);
+ else if (skb->tstamp.tv64)
+ ts = ktime_to_timespec(skb->tstamp);
+ else
+ getnstimeofday(&ts);
+ h.h3->tp_sec = ts.tv_sec;
+ h.h3->tp_nsec = ts.tv_nsec;
+ if (vlan_tx_tag_present(skb)) {
+ h.h3->tp_vlan_tci = vlan_tx_tag_get(skb);
+ h.h3->tp_status |= TP_STATUS_VLAN_VALID;
+ } else {
+ h.h3->tp_vlan_tci = 0;
+ }
+ h.h3->tp_padding = 0;
+ hdrlen = sizeof(*h.h3);
+ break;
default:
BUG();
}
@@ -1134,13 +1900,19 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
{
u8 *start, *end;
- end = (u8 *)PAGE_ALIGN((unsigned long)h.raw + macoff + snaplen);
- for (start = h.raw; start < end; start += PAGE_SIZE)
- flush_dcache_page(pgv_to_page(start));
+ if (po->tp_version <= TPACKET_V2) {
+ end = (u8 *)PAGE_ALIGN((unsigned long)h.raw
+ + macoff + snaplen);
+ for (start = h.raw; start < end; start += PAGE_SIZE)
+ flush_dcache_page(pgv_to_page(start));
+ }
smp_wmb();
}
#endif
- __packet_set_status(po, h.raw, status);
+ if (po->tp_version <= TPACKET_V2)
+ __packet_set_status(po, h.raw, status);
+ else
+ prb_clear_blk_fill_status(&po->rx_ring);
sk->sk_data_ready(sk, 0);
@@ -1631,7 +2403,7 @@ static int packet_release(struct socket *sock)
struct sock *sk = sock->sk;
struct packet_sock *po;
struct net *net;
- struct tpacket_req req;
+ union tpacket_req_u req_u;
if (!sk)
return 0;
@@ -1654,13 +2426,13 @@ static int packet_release(struct socket *sock)
packet_flush_mclist(sk);
- memset(&req, 0, sizeof(req));
+ memset(&req_u, 0, sizeof(req_u));
if (po->rx_ring.pg_vec)
- packet_set_ring(sk, &req, 1, 0);
+ packet_set_ring(sk, &req_u, 1, 0);
if (po->tx_ring.pg_vec)
- packet_set_ring(sk, &req, 1, 1);
+ packet_set_ring(sk, &req_u, 1, 1);
fanout_release(sk);
@@ -2280,15 +3052,27 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
case PACKET_RX_RING:
case PACKET_TX_RING:
{
- struct tpacket_req req;
+ union tpacket_req_u req_u;
+ int len;
- if (optlen < sizeof(req))
+ switch (po->tp_version) {
+ case TPACKET_V1:
+ case TPACKET_V2:
+ len = sizeof(req_u.req);
+ break;
+ case TPACKET_V3:
+ default:
+ len = sizeof(req_u.req3);
+ break;
+ }
+ if (optlen < len)
return -EINVAL;
if (pkt_sk(sk)->has_vnet_hdr)
return -EINVAL;
- if (copy_from_user(&req, optval, sizeof(req)))
+ if (copy_from_user(&req_u.req, optval, len))
return -EFAULT;
- return packet_set_ring(sk, &req, 0, optname == PACKET_TX_RING);
+ return packet_set_ring(sk, &req_u, 0,
+ optname == PACKET_TX_RING);
}
case PACKET_COPY_THRESH:
{
@@ -2315,6 +3099,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv
switch (val) {
case TPACKET_V1:
case TPACKET_V2:
+ case TPACKET_V3:
po->tp_version = val;
return 0;
default:
@@ -2424,6 +3209,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
struct packet_sock *po = pkt_sk(sk);
void *data;
struct tpacket_stats st;
+ union tpacket_stats_u st_u;
if (level != SOL_PACKET)
return -ENOPROTOOPT;
@@ -2436,15 +3222,27 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
switch (optname) {
case PACKET_STATISTICS:
- if (len > sizeof(struct tpacket_stats))
- len = sizeof(struct tpacket_stats);
+ if (po->tp_version == TPACKET_V3) {
+ len = sizeof(struct tpacket_stats_v3);
+ } else {
+ if (len > sizeof(struct tpacket_stats))
+ len = sizeof(struct tpacket_stats);
+ }
spin_lock_bh(&sk->sk_receive_queue.lock);
- st = po->stats;
+ if (po->tp_version == TPACKET_V3) {
+ memcpy(&st_u.stats3, &po->stats,
+ sizeof(struct tpacket_stats));
+ st_u.stats3.tp_freeze_q_cnt =
+ po->stats_u.stats3.tp_freeze_q_cnt;
+ st_u.stats3.tp_packets += po->stats.tp_drops;
+ data = &st_u.stats3;
+ } else {
+ st = po->stats;
+ st.tp_packets += st.tp_drops;
+ data = &st;
+ }
memset(&po->stats, 0, sizeof(st));
spin_unlock_bh(&sk->sk_receive_queue.lock);
- st.tp_packets += st.tp_drops;
-
- data = &st;
break;
case PACKET_AUXDATA:
if (len > sizeof(int))
@@ -2485,6 +3283,9 @@ static int packet_getsockopt(struct socket *sock, int level, int optname,
case TPACKET_V2:
val = sizeof(struct tpacket2_hdr);
break;
+ case TPACKET_V3:
+ val = sizeof(struct tpacket3_hdr);
+ break;
default:
return -EINVAL;
}
@@ -2641,7 +3442,8 @@ static unsigned int packet_poll(struct file *file, struct socket *sock,
spin_lock_bh(&sk->sk_receive_queue.lock);
if (po->rx_ring.pg_vec) {
- if (!packet_previous_frame(po, &po->rx_ring, TP_STATUS_KERNEL))
+ if (!packet_previous_rx_frame(po, &po->rx_ring,
+ TP_STATUS_KERNEL))
mask |= POLLIN | POLLRDNORM;
}
spin_unlock_bh(&sk->sk_receive_queue.lock);
@@ -2760,7 +3562,7 @@ out_free_pgvec:
goto out;
}
-static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
+static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
int closing, int tx_ring)
{
struct pgv *pg_vec = NULL;
@@ -2769,7 +3571,15 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
struct packet_ring_buffer *rb;
struct sk_buff_head *rb_queue;
__be16 num;
- int err;
+ int err = -EINVAL;
+ /* Added to avoid minimal code churn */
+ struct tpacket_req *req = &req_u->req;
+
+ /* Opening a Tx-ring is NOT supported in TPACKET_V3 */
+ if (!closing && tx_ring && (po->tp_version > TPACKET_V2)) {
+ WARN(1, "Tx-ring is not supported.\n");
+ goto out;
+ }
rb = tx_ring ? &po->tx_ring : &po->rx_ring;
rb_queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
@@ -2795,6 +3605,9 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
case TPACKET_V2:
po->tp_hdrlen = TPACKET2_HDRLEN;
break;
+ case TPACKET_V3:
+ po->tp_hdrlen = TPACKET3_HDRLEN;
+ break;
}
err = -EINVAL;
@@ -2820,6 +3633,17 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
pg_vec = alloc_pg_vec(req, order);
if (unlikely(!pg_vec))
goto out;
+ switch (po->tp_version) {
+ case TPACKET_V3:
+ /* Transmit path is not supported. We checked
+ * it above but just being paranoid
+ */
+ if (!tx_ring)
+ init_prb_bdqc(po, rb, pg_vec, req_u, tx_ring);
+ break;
+ default:
+ break;
+ }
}
/* Done */
else {
@@ -2872,7 +3696,11 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req,
register_prot_hook(sk);
}
spin_unlock(&po->bind_lock);
-
+ if (closing && (po->tp_version > TPACKET_V2)) {
+ /* Because we don't support block-based V3 on tx-ring */
+ if (!tx_ring)
+ prb_shutdown_retire_blk_timer(po, tx_ring, rb_queue);
+ }
release_sock(sk);
if (pg_vec)
--
1.7.5.2
^ permalink raw reply related
* [PATCH net-next v3 af-packet 1/2] Enhance af-packet to provide (near zero)lossless packet capture functionality.
From: Chetan Loke @ 2011-07-18 3:26 UTC (permalink / raw)
To: davem, netdev; +Cc: Chetan Loke
In-Reply-To: <1310959610-1688-1-git-send-email-loke.chetan@gmail.com>
Signed-off-by: Chetan Loke <loke.chetan@gmail.com>
---
include/linux/if_packet.h | 125 +++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 125 insertions(+), 0 deletions(-)
diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
index c148606..19427d7 100644
--- a/include/linux/if_packet.h
+++ b/include/linux/if_packet.h
@@ -61,6 +61,17 @@ struct tpacket_stats {
unsigned int tp_drops;
};
+struct tpacket_stats_v3 {
+ unsigned int tp_packets;
+ unsigned int tp_drops;
+ unsigned int tp_freeze_q_cnt;
+};
+
+union tpacket_stats_u {
+ struct tpacket_stats stats1;
+ struct tpacket_stats_v3 stats3;
+};
+
struct tpacket_auxdata {
__u32 tp_status;
__u32 tp_len;
@@ -78,6 +89,7 @@ struct tpacket_auxdata {
#define TP_STATUS_LOSING 0x4
#define TP_STATUS_CSUMNOTREADY 0x8
#define TP_STATUS_VLAN_VALID 0x10 /* auxdata has valid tp_vlan_tci */
+#define TP_STATUS_BLK_TMO 0x20
/* Tx ring - header status */
#define TP_STATUS_AVAILABLE 0x0
@@ -85,6 +97,9 @@ struct tpacket_auxdata {
#define TP_STATUS_SENDING 0x2
#define TP_STATUS_WRONG_FORMAT 0x4
+/* Rx ring - feature request bits */
+#define TP_FT_REQ_FILL_RXHASH 0x1
+
struct tpacket_hdr {
unsigned long tp_status;
unsigned int tp_len;
@@ -111,11 +126,106 @@ struct tpacket2_hdr {
__u16 tp_padding;
};
+struct tpacket3_hdr {
+ __u32 tp_status;
+ __u32 tp_next_offset;
+ __u32 tp_len;
+ __u32 tp_snaplen;
+ __u16 tp_mac;
+ __u16 tp_net;
+ __u32 tp_sec;
+ __u32 tp_nsec;
+ __u32 tp_rxhash;
+ __u16 tp_vlan_tci;
+ __u16 tp_padding;
+ __u32 tp_next_offset;
+};
+
+struct bd_ts {
+ unsigned int ts_sec;
+ union {
+ unsigned int ts_usec;
+ unsigned int ts_nsec;
+ };
+};
+
+struct hdr_v1 {
+ __u32 block_status;
+ __u32 num_pkts;
+ __u32 offset_to_first_pkt;
+
+ /* Number of valid bytes (including padding)
+ * blk_len <= tp_block_size
+ */
+ __u32 blk_len;
+
+ /*
+ * Quite a few uses of sequence number:
+ * 1. Make sure cache flush etc worked.
+ * Well, one can argue - why not use the increasing ts below?
+ * But look at 2. below first.
+ * 2. When you pass around blocks to other user space decoders,
+ * you can see which blk[s] is[are] outstanding etc.
+ * 3. Validate kernel code.
+ */
+ aligned_u64 seq_num;
+
+ /*
+ * ts_last_pkt:
+ *
+ * Case 1. Block has 'N'(N >=1) packets and TMO'd(timed out)
+ * ts_last_pkt == 'time-stamp of last packet' and NOT the
+ * time when the timer fired and the block was closed.
+ * By providing the ts of the last packet we can absolutely
+ * guarantee that time-stamp wise, the first packet in the next
+ * block will never precede the last packet of the previous
+ * block.
+ * Case 2. Block has zero packets and TMO'd
+ * ts_last_pkt = time when the timer fired and the block
+ * was closed.
+ * Case 3. Block has 'N' packets and NO TMO.
+ * ts_last_pkt = time-stamp of the last pkt in the block.
+ *
+ * ts_first_pkt:
+ * Is always the time-stamp when the block was opened.
+ * Case a) ZERO packets
+ * No packets to deal with but atleast you know the
+ * time-interval of this block.
+ * Case b) Non-zero packets
+ * Use the ts of the first packet in the block.
+ *
+ */
+ struct bd_ts ts_first_pkt, ts_last_pkt;
+};
+
+union bd_header_u {
+ struct hdr_v1 h1;
+};
+
+struct block_desc {
+ __u16 version;
+ __u16 offset_to_priv;
+ __u32 rsvd1;
+ union bd_header_u hdr;
+};
+
+
+
#define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll))
+#define TPACKET3_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket3_hdr)) + sizeof(struct sockaddr_ll))
+
+#define BLOCK_STATUS(x) ((x)->hdr.h1.block_status)
+#define BLOCK_NUM_PKTS(x) ((x)->hdr.h1.num_pkts)
+#define BLOCK_O2FP(x) ((x)->hdr.h1.offset_to_first_pkt)
+#define BLOCK_LEN(x) ((x)->hdr.h1.blk_len)
+#define BLOCK_SNUM(x) ((x)->hdr.h1.seq_num)
+#define BLOCK_O2PRIV(x) ((x)->offset_to_priv)
+#define BLOCK_PRIV(x) ((void *)((char *)(x) + BLOCK_O2PRIV(x)))
enum tpacket_versions {
TPACKET_V1,
TPACKET_V2,
+ TPACKET_V3,
};
/*
@@ -138,6 +248,21 @@ struct tpacket_req {
unsigned int tp_frame_nr; /* Total number of frames */
};
+struct tpacket_req3 {
+ unsigned int tp_block_size; /* Minimal size of contiguous block */
+ unsigned int tp_block_nr; /* Number of blocks */
+ unsigned int tp_frame_size; /* Size of frame */
+ unsigned int tp_frame_nr; /* Total number of frames */
+ unsigned int tp_retire_blk_tov; /* timeout in msecs */
+ unsigned int tp_sizeof_priv; /* offset to private data area */
+ unsigned int tp_feature_req_word;
+};
+
+union tpacket_req_u {
+ struct tpacket_req req;
+ struct tpacket_req3 req3;
+};
+
struct packet_mreq {
int mr_ifindex;
unsigned short mr_type;
--
1.7.5.2
^ permalink raw reply related
* [PATCH net-next v3 af-packet 0/2] Enhance af-packet to provide (near zero)lossless packet capture functionality.
From: Chetan Loke @ 2011-07-18 3:26 UTC (permalink / raw)
To: davem, netdev; +Cc: Chetan Loke
Changes in v3:
1) Stripped __packed__ attribute. (Dave Miller)
Replaced with aligned_u64 and padding.
2) Added 'feature_request_word'.
3) Added rx_hash field to the v3-header. (Chetan L)
Changes in v2:
1) Aligned bdqc members, pr_err to WARN, sob email (Joe Perches)
2) Added tp_padding (Eric Dumazet)
3) Nuked useless ;) white space (Stephen H)
4) Use __u types in headers (Ben Hutchings)
5) Added field for creating private area (Chetan Loke)
This patch attempts to:
1)Improve network capture visibility by increasing packet density
2)Assist in analyzing multiple(aggregated) capture ports.
Benefits:
B1) ~15-20% reduction in cpu-usage.
B2) ~20% increase in packet capture rate.
B3) ~2x increase in packet density.
B4) Port aggregation analysis.
B5) Non static frame size to capture entire packet payload.
With the current af_packet->rx::mmap based approach, the element size
in the block needs to be statically configured. Nothing wrong with this
config/implementation. But the traffic profile cannot be known in advance.
And so it would be nice if that configuration wasn't static. Normally,
one would configure the element-size to be '2048' so that you can atleast
capture the entire 'MTU-size'.But if the traffic profile varies then we
would end up either i)wasting memory or ii) end up getting a sliced frame.
In other words the packet density will be much less in the first case.
Detailed description of the test-setup etc can be viewed at:
http://thread.gmane.org/gmane.linux.kernel/1158216
Chetan Loke (2):
include/linux/if_packet.h | 125 ++++++
net/packet/af_packet.c | 920 ++++++++++++++++++++++++++++++++++++++++++---
2 files changed, 999 insertions(+), 46 deletions(-)
--
1.7.5.2
^ permalink raw reply
* Confirm Your $0.00 Copy Of "Winning In The Online Home Business Arena" ($39.97 Value
From: nick @ 2011-07-17 23:48 UTC (permalink / raw)
To: netdev
Inside Of Your Free 8 Part DVD \\\"Winning
In The Online Home Business Arena\\\"
($39.97 Value)
Go here now:
==> https://daegansmith.infusionsoft.com/go/freedvdbootcamp/a12144
You\\\'ll Discover . . .
What\\\'s Working Now! \\\"How To Get Up To 37
Checks Per Month, Earn Upwards Of
$4,954.55 While You Sleep At Night, And
Recruit WITHOUT Ever Having To Pick Up The Phone\\\"
Here\\\'s where to go:
==> https://daegansmith.infusionsoft.com/go/freedvdbootcamp/a12144
To the top,
Nick
Pick up now while it still costs zilch,
before I start charing for it again.
Make haste - Go here Now:
==> https://daegansmith.infusionsoft.com/go/freedvdbootcamp/a12144
^ permalink raw reply
* Re: [PATCH 0/2] ath6kl: more neatening
From: Kalle Valo @ 2011-07-17 21:49 UTC (permalink / raw)
To: Joe Perches; +Cc: devel, gregkh, error27, linux-kernel, linux-wireless, netdev
In-Reply-To: <cover.1310938421.git.joe@perches.com>
On 07/18/2011 12:38 AM, Joe Perches wrote:
>> Great, thanks. I have now applied your patches to ath6kl-cleanup tree
>> and they will be included in patchset v3.
>
> Here's a couple of more.
>
> Joe Perches (2):
> ath6kl: Remove __func__ uses from ath6kl_dbg
> ath6kl: Remove trailing unpaired close paren from ath6kl_err uses
Thanks again.
I just sent v3. But if I need to create v4 (I hope not) I'll include
your patches. If v3 is ok, I can resend your patches to wireless-testing
so that you don't need to followup.
Kalle
^ permalink raw reply
* [PATCH 1/2] ath6kl: Remove __func__ uses from ath6kl_dbg
From: Joe Perches @ 2011-07-17 21:38 UTC (permalink / raw)
To: Kalle Valo, linux-kernel
Cc: devel, gregkh, error27, linux-wireless, netdev, John W. Linville
In-Reply-To: <cover.1310938421.git.joe@perches.com>
Make the ath6kl_dbg uses consistly _not_ use __func__.
Add __func__ to #define ath6kl_dbg.
Remove __func__ from single ath6kl_err.
Signed-off-by: Joe Perches <joe@perches.com>
---
drivers/net/wireless/ath/ath6kl/bmi.c | 4 +-
drivers/net/wireless/ath/ath6kl/cfg80211.c | 101 ++++++++++++---------------
drivers/net/wireless/ath/ath6kl/debug.c | 20 +++---
drivers/net/wireless/ath/ath6kl/debug.h | 27 ++++----
drivers/net/wireless/ath/ath6kl/htc.c | 11 ++--
drivers/net/wireless/ath/ath6kl/init.c | 8 +-
drivers/net/wireless/ath/ath6kl/main.c | 13 ++--
drivers/net/wireless/ath/ath6kl/sdio.c | 8 +-
drivers/net/wireless/ath/ath6kl/txrx.c | 30 ++++-----
drivers/net/wireless/ath/ath6kl/wmi.c | 8 +--
10 files changed, 105 insertions(+), 125 deletions(-)
diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index 8467669..22dd247 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -407,7 +407,7 @@ int ath6kl_bmi_execute(struct ath6kl *ar, u32 addr, u32 *param)
}
memset(ar->bmi.cmd_buf, 0, size);
- ath6kl_dbg(ATH6KL_DBG_BMI, "bmi execute: addr: 0x%x, param: %d)\n",
+ ath6kl_dbg(ATH6KL_DBG_BMI, "bmi execute: addr: 0x%x, param: %d\n",
addr, *param);
offset = 0;
@@ -575,7 +575,7 @@ int ath6kl_bmi_lz_data(struct ath6kl *ar, u8 *buf, u32 len)
}
memset(ar->bmi.cmd_buf, 0, size);
- ath6kl_dbg(ATH6KL_DBG_BMI, "bmi send LZ data: len: %d)\n",
+ ath6kl_dbg(ATH6KL_DBG_BMI, "bmi send LZ data: len: %d\n",
len);
len_remain = len;
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 71515bb..6c7970f 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -118,7 +118,7 @@ static struct ieee80211_supported_band ath6kl_band_5ghz = {
static int ath6kl_set_wpa_version(struct ath6kl *ar,
enum nl80211_wpa_versions wpa_version)
{
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: %u\n", __func__, wpa_version);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "wpa version: %u\n", wpa_version);
if (!wpa_version) {
ar->auth_mode = NONE_AUTH;
@@ -127,7 +127,7 @@ static int ath6kl_set_wpa_version(struct ath6kl *ar,
} else if (wpa_version & NL80211_WPA_VERSION_2) {
ar->auth_mode = WPA2_AUTH;
} else {
- ath6kl_err("%s: %u not supported\n", __func__, wpa_version);
+ ath6kl_err("wpa version %u not supported\n", wpa_version);
return -ENOTSUPP;
}
@@ -138,7 +138,7 @@ static int ath6kl_set_auth_type(struct ath6kl *ar,
enum nl80211_auth_type auth_type)
{
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: 0x%x\n", __func__, auth_type);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "auth type: 0x%x\n", auth_type);
switch (auth_type) {
case NL80211_AUTHTYPE_OPEN_SYSTEM:
@@ -158,7 +158,7 @@ static int ath6kl_set_auth_type(struct ath6kl *ar,
default:
ar->dot11_auth_mode = OPEN_AUTH;
- ath6kl_err("%s: 0x%x not spported\n", __func__, auth_type);
+ ath6kl_err("auth type 0x%x not supported\n", auth_type);
return -ENOTSUPP;
}
@@ -170,8 +170,8 @@ static int ath6kl_set_cipher(struct ath6kl *ar, u32 cipher, bool ucast)
u8 *ar_cipher = ucast ? &ar->prwise_crypto : &ar->grp_crypto;
u8 *ar_cipher_len = ucast ? &ar->prwise_crypto_len : &ar->grp_crpto_len;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: cipher 0x%x, ucast %u\n",
- __func__, cipher, ucast);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "cipher 0x%x, ucast %u\n",
+ cipher, ucast);
switch (cipher) {
case 0:
@@ -205,7 +205,7 @@ static int ath6kl_set_cipher(struct ath6kl *ar, u32 cipher, bool ucast)
static void ath6kl_set_key_mgmt(struct ath6kl *ar, u32 key_mgmt)
{
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: 0x%x\n", __func__, key_mgmt);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "set key: 0x%x\n", key_mgmt);
if (key_mgmt == WLAN_AKM_SUITE_PSK) {
if (ar->auth_mode == WPA_AUTH)
@@ -365,10 +365,9 @@ static int ath6kl_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev,
ar->nw_type = ar->next_mode;
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: connect called with authmode %d dot11 auth %d"
+ "connect called with authmode %d dot11 auth %d"
" PW crypto %d PW crypto len %d GRP crypto %d"
" GRP crypto len %d channel hint %u\n",
- __func__,
ar->auth_mode, ar->dot11_auth_mode, ar->prwise_crypto,
ar->prwise_crypto_len, ar->grp_crypto,
ar->grp_crpto_len, ar->ch_hint);
@@ -447,7 +446,7 @@ void ath6kl_cfg80211_connect_event(struct ath6kl *ar, u16 channel,
if (nw_type & ADHOC_NETWORK) {
if (ar->wdev->iftype != NL80211_IFTYPE_ADHOC) {
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: ath6k not in ibss mode\n", __func__);
+ "ath6k not in ibss mode\n");
return;
}
}
@@ -455,7 +454,7 @@ void ath6kl_cfg80211_connect_event(struct ath6kl *ar, u16 channel,
if (nw_type & INFRA_NETWORK) {
if (ar->wdev->iftype != NL80211_IFTYPE_STATION) {
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: ath6k not in station mode\n", __func__);
+ "ath6k not in station mode\n");
return;
}
}
@@ -545,9 +544,8 @@ void ath6kl_cfg80211_connect_event(struct ath6kl *ar, u16 channel,
ibss_ch = ieee80211_get_channel(ar->wdev->wiphy, (int)channel);
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: inform bss with bssid %pM channel %d beacon_intvl %d capability 0x%x\n",
- __func__, mgmt->bssid, ibss_ch->hw_value,
- beacon_intvl, capability);
+ "inform bss with bssid %pM channel %d beacon_intvl %d capability 0x%x\n",
+ mgmt->bssid, ibss_ch->hw_value, beacon_intvl, capability);
bss = cfg80211_inform_bss_frame(ar->wdev->wiphy,
ibss_ch, mgmt,
@@ -580,8 +578,7 @@ static int ath6kl_cfg80211_disconnect(struct wiphy *wiphy,
{
struct ath6kl *ar = (struct ath6kl *)ath6kl_priv(dev);
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: reason=%u\n", __func__,
- reason_code);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "disconnect reason=%u\n", reason_code);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
@@ -624,7 +621,7 @@ void ath6kl_cfg80211_disconnect_event(struct ath6kl *ar, u8 reason,
if (ar->nw_type & ADHOC_NETWORK) {
if (ar->wdev->iftype != NL80211_IFTYPE_ADHOC) {
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: ath6k not in ibss mode\n", __func__);
+ "ath6k not in ibss mode\n");
return;
}
memset(bssid, 0, ETH_ALEN);
@@ -635,7 +632,7 @@ void ath6kl_cfg80211_disconnect_event(struct ath6kl *ar, u8 reason,
if (ar->nw_type & INFRA_NETWORK) {
if (ar->wdev->iftype != NL80211_IFTYPE_STATION) {
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: ath6k not in station mode\n", __func__);
+ "ath6k not in station mode\n");
return;
}
}
@@ -767,7 +764,7 @@ static void ath6kl_cfg80211_scan_node(void *arg, struct bss *ni)
signal = ni->ni_snr * 100;
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: bssid %pM ch %d freq %d size %d\n", __func__,
+ "bssid %pM ch %d freq %d size %d\n",
mgmt->bssid, channel->hw_value, freq, size);
cfg80211_inform_bss_frame(wiphy, channel, mgmt,
size, signal, GFP_KERNEL);
@@ -825,7 +822,7 @@ static int ath6kl_cfg80211_scan(struct wiphy *wiphy, struct net_device *ndev,
void ath6kl_cfg80211_scan_complete_event(struct ath6kl *ar, int status)
{
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: status %d\n", __func__, status);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "scan complete status %d\n", status);
if (ar->scan_req) {
/* Translate data to cfg80211 mgmt format */
@@ -864,8 +861,7 @@ static int ath6kl_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev,
return -EIO;
if (key_index < WMI_MIN_KEY_INDEX || key_index > WMI_MAX_KEY_INDEX) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: key index %d out of bounds\n", __func__,
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d out of bounds\n",
key_index);
return -ENOENT;
}
@@ -914,9 +910,8 @@ static int ath6kl_cfg80211_add_key(struct wiphy *wiphy, struct net_device *ndev,
del_timer(&ar->disconnect_timer);
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: index %d, key_len %d, key_type 0x%x, key_usage 0x%x, seq_len %d\n",
- __func__, key_index, key->key_len, key_type,
- key_usage, key->seq_len);
+ "index %d, key_len %d, key_type 0x%x, key_usage 0x%x, seq_len %d\n",
+ key_index, key->key_len, key_type, key_usage, key->seq_len);
ar->def_txkey_index = key_index;
status = ath6kl_wmi_addkey_cmd(ar->wmi, ar->def_txkey_index,
@@ -936,21 +931,20 @@ static int ath6kl_cfg80211_del_key(struct wiphy *wiphy, struct net_device *ndev,
{
struct ath6kl *ar = (struct ath6kl *)ath6kl_priv(ndev);
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "del key index %d\n", key_index);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
if (key_index < WMI_MIN_KEY_INDEX || key_index > WMI_MAX_KEY_INDEX) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: key index %d out of bounds\n", __func__,
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d out of bounds\n",
key_index);
return -ENOENT;
}
if (!ar->keys[key_index].key_len) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: index %d is empty\n", __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d is empty\n",
+ key_index);
return 0;
}
@@ -969,14 +963,13 @@ static int ath6kl_cfg80211_get_key(struct wiphy *wiphy, struct net_device *ndev,
struct ath6kl_key *key = NULL;
struct key_params params;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d\n", key_index);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
if (key_index < WMI_MIN_KEY_INDEX || key_index > WMI_MAX_KEY_INDEX) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: key index %d out of bounds\n", __func__,
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d out of bounds\n",
key_index);
return -ENOENT;
}
@@ -1004,21 +997,20 @@ static int ath6kl_cfg80211_set_default_key(struct wiphy *wiphy,
int status = 0;
u8 key_usage;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "default key index %d\n", key_index);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
if (key_index < WMI_MIN_KEY_INDEX || key_index > WMI_MAX_KEY_INDEX) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: key index %d out of bounds\n",
- __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "key index %d out of bounds\n",
+ key_index);
return -ENOENT;
}
if (!ar->keys[key_index].key_len) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: invalid key index %d\n",
- __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "invalid key index %d\n",
+ key_index);
return -EINVAL;
}
@@ -1045,20 +1037,20 @@ static int ath6kl_cfg80211_set_default_mgmt_key(struct wiphy *wiphy,
{
struct ath6kl *ar = (struct ath6kl *)ath6kl_priv(ndev);
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: index %d\n", __func__, key_index);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "mgmt index %d\n", key_index);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: not supported\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "mgnt index not supported\n");
return -ENOTSUPP;
}
void ath6kl_cfg80211_tkip_micerr_event(struct ath6kl *ar, u8 keyid,
bool ismcast)
{
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: keyid %d, ismcast %d\n", __func__, keyid, ismcast);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "keyid %d, ismcast %d\n",
+ keyid, ismcast);
cfg80211_michael_mic_failure(ar->net_dev, ar->bssid,
(ismcast ? NL80211_KEYTYPE_GROUP :
@@ -1071,8 +1063,7 @@ static int ath6kl_cfg80211_set_wiphy_params(struct wiphy *wiphy, u32 changed)
struct ath6kl *ar = (struct ath6kl *)wiphy_priv(wiphy);
int ret;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: changed 0x%x\n", __func__,
- changed);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "wiphy changed 0x%x\n", changed);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
@@ -1099,8 +1090,7 @@ static int ath6kl_cfg80211_set_txpower(struct wiphy *wiphy,
struct ath6kl *ar = (struct ath6kl *)wiphy_priv(wiphy);
u8 ath6kl_dbm;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: type 0x%x, dbm %d\n", __func__,
- type, dbm);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "type 0x%x, dbm %d\n", type, dbm);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
@@ -1112,8 +1102,8 @@ static int ath6kl_cfg80211_set_txpower(struct wiphy *wiphy,
ar->tx_pwr = ath6kl_dbm = dbm;
break;
default:
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: type 0x%x not supported\n",
- __func__, type);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "type 0x%x not supported\n",
+ type);
return -EOPNOTSUPP;
}
@@ -1157,17 +1147,17 @@ static int ath6kl_cfg80211_set_power_mgmt(struct wiphy *wiphy,
struct ath6kl *ar = ath6kl_priv(dev);
struct wmi_power_mode_cmd mode;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: pmgmt %d, timeout %d\n",
- __func__, pmgmt, timeout);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "pmgmt %d, timeout %d\n",
+ pmgmt, timeout);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
if (pmgmt) {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: max perf\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "max perf\n");
mode.pwr_mode = REC_POWER;
} else {
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: rec power\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "rec power\n");
mode.pwr_mode = MAX_PERF_POWER;
}
@@ -1187,7 +1177,7 @@ static int ath6kl_cfg80211_change_iface(struct wiphy *wiphy,
struct ath6kl *ar = ath6kl_priv(ndev);
struct wireless_dev *wdev = ar->wdev;
- ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "%s: type %u\n", __func__, type);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_CFG, "iface type %u\n", type);
if (!ath6kl_cfg80211_ready(ar))
return -EIO;
@@ -1258,10 +1248,9 @@ static int ath6kl_cfg80211_join_ibss(struct wiphy *wiphy,
ar->nw_type = ar->next_mode;
ath6kl_dbg(ATH6KL_DBG_WLAN_CFG,
- "%s: connect called with authmode %d dot11 auth %d"
+ "connect called with authmode %d dot11 auth %d"
" PW crypto %d PW crypto len %d GRP crypto %d"
" GRP crypto len %d channel hint %u\n",
- __func__,
ar->auth_mode, ar->dot11_auth_mode, ar->prwise_crypto,
ar->prwise_crypto_len, ar->grp_crypto,
ar->grp_crpto_len, ar->ch_hint);
diff --git a/drivers/net/wireless/ath/ath6kl/debug.c b/drivers/net/wireless/ath/ath6kl/debug.c
index 316136c..b30d583 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.c
+++ b/drivers/net/wireless/ath/ath6kl/debug.c
@@ -41,33 +41,33 @@ void ath6kl_dump_registers(struct ath6kl_device *dev,
struct ath6kl_irq_enable_reg *irq_enable_reg)
{
- ath6kl_dbg(ATH6KL_DBG_ANY, ("<------- Register Table -------->\n"));
+ ath6kl_dbg(ATH6KL_DBG_ANY, "<------- Register Table -------->\n");
if (irq_proc_reg != NULL) {
ath6kl_dbg(ATH6KL_DBG_ANY,
- "Host Int status: 0x%x\n",
- irq_proc_reg->host_int_status);
+ "Host Int status: 0x%x\n",
+ irq_proc_reg->host_int_status);
ath6kl_dbg(ATH6KL_DBG_ANY,
"CPU Int status: 0x%x\n",
- irq_proc_reg->cpu_int_status);
+ irq_proc_reg->cpu_int_status);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Error Int status: 0x%x\n",
- irq_proc_reg->error_int_status);
+ irq_proc_reg->error_int_status);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Counter Int status: 0x%x\n",
- irq_proc_reg->counter_int_status);
+ irq_proc_reg->counter_int_status);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Mbox Frame: 0x%x\n",
- irq_proc_reg->mbox_frame);
+ irq_proc_reg->mbox_frame);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Rx Lookahead Valid: 0x%x\n",
- irq_proc_reg->rx_lkahd_valid);
+ irq_proc_reg->rx_lkahd_valid);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Rx Lookahead 0: 0x%x\n",
- irq_proc_reg->rx_lkahd[0]);
+ irq_proc_reg->rx_lkahd[0]);
ath6kl_dbg(ATH6KL_DBG_ANY,
"Rx Lookahead 1: 0x%x\n",
- irq_proc_reg->rx_lkahd[1]);
+ irq_proc_reg->rx_lkahd[1]);
if (dev->ar->mbox_info.gmbox_addr != 0) {
/*
diff --git a/drivers/net/wireless/ath/ath6kl/debug.h b/drivers/net/wireless/ath/ath6kl/debug.h
index 2e60588..ece20c9 100644
--- a/drivers/net/wireless/ath/ath6kl/debug.h
+++ b/drivers/net/wireless/ath/ath6kl/debug.h
@@ -42,7 +42,7 @@ extern unsigned int debug_mask;
extern int ath6kl_printk(const char *level, const char *fmt, ...)
__attribute__ ((format (printf, 2, 3)));
-#define ath6kl_info(fmt, ...) \
+#define ath6kl_info(fmt, ...) \
ath6kl_printk(KERN_INFO, fmt, ##__VA_ARGS__)
#define ath6kl_err(fmt, ...) \
ath6kl_printk(KERN_ERR, fmt, ##__VA_ARGS__)
@@ -52,16 +52,17 @@ extern int ath6kl_printk(const char *level, const char *fmt, ...)
#define AR_DBG_LVL_CHECK(mask) (debug_mask & mask)
#ifdef CONFIG_ATH6KL_DEBUG
-#define ath6kl_dbg(mask, fmt, ...) \
- ({ \
- int rtn; \
- if (debug_mask & mask) \
- rtn = ath6kl_printk(KERN_DEBUG, fmt, ##__VA_ARGS__); \
- else \
- rtn = 0; \
- \
- rtn; \
- })
+#define ath6kl_dbg(mask, fmt, ...) \
+({ \
+ int rtn; \
+ if (debug_mask & mask) \
+ rtn = ath6kl_printk(KERN_DEBUG, "%s: " fmt, \
+ __func__, ##__VA_ARGS__); \
+ else \
+ rtn = 0; \
+ \
+ rtn; \
+})
static inline void ath6kl_dbg_dump(enum ATH6K_DEBUG_MASK mask,
const char *msg, const void *buf,
@@ -78,8 +79,8 @@ void ath6kl_dump_registers(struct ath6kl_device *dev,
struct ath6kl_irq_enable_reg *irq_en_reg);
void dump_cred_dist_stats(struct htc_target *target);
#else
-static inline int ath6kl_dbg(enum ATH6K_DEBUG_MASK dbg_mask,
- const char *fmt, ...)
+static inline __attribute__ ((format (printf, 2, 3)))
+int ath6kl_dbg(enum ATH6K_DEBUG_MASK dbg_mask, const char *fmt, ...)
{
return 0;
}
diff --git a/drivers/net/wireless/ath/ath6kl/htc.c b/drivers/net/wireless/ath/ath6kl/htc.c
index 95c47bb..ab651fb 100644
--- a/drivers/net/wireless/ath/ath6kl/htc.c
+++ b/drivers/net/wireless/ath/ath6kl/htc.c
@@ -175,16 +175,15 @@ static int htc_issue_send(struct htc_target *target, struct htc_packet *packet)
send_len = packet->act_len + HTC_HDR_LENGTH;
- ath6kl_dbg(ATH6KL_DBG_HTC_SEND, "%s: transmit len : %d (%s)\n",
- __func__, send_len, sync ? "sync" : "async");
+ ath6kl_dbg(ATH6KL_DBG_HTC_SEND, "transmit len : %d (%s)\n",
+ send_len, sync ? "sync" : "async");
padded_len = CALC_TXRX_PADDED_LEN(target->dev, send_len);
ath6kl_dbg(ATH6KL_DBG_HTC_SEND,
- "DevSendPacket, padded len: %d mbox:0x%X (mode:%s)\n",
- padded_len,
- target->dev->ar->mbox_info.htc_addr,
- sync ? "sync" : "async");
+ "DevSendPacket, padded len: %d mbox:0x%X (mode:%s)\n",
+ padded_len, target->dev->ar->mbox_info.htc_addr,
+ sync ? "sync" : "async");
if (sync) {
status = hif_read_write_sync(target->dev->ar,
diff --git a/drivers/net/wireless/ath/ath6kl/init.c b/drivers/net/wireless/ath/ath6kl/init.c
index fe61871..a8f4452 100644
--- a/drivers/net/wireless/ath/ath6kl/init.c
+++ b/drivers/net/wireless/ath/ath6kl/init.c
@@ -1060,7 +1060,7 @@ static int ath6kl_init(struct net_device *dev)
goto ath6kl_init_done;
}
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: got wmi @ 0x%p.\n", __func__, ar->wmi);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "got wmi @ 0x%p\n", ar->wmi);
/*
* The reason we have to wait for the target here is that the
@@ -1122,7 +1122,7 @@ static int ath6kl_init(struct net_device *dev)
goto err_htc_stop;
}
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: wmi is ready\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "wmi is ready\n");
/* communicate the wmi protocol verision to the target */
if ((ath6kl_set_host_app_area(ar)) != 0)
@@ -1208,8 +1208,8 @@ int ath6kl_core_init(struct ath6kl *ar)
set_bit(NETDEV_REGISTERED, &ar->flag);
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: name=%s dev=0x%p, ar=0x%p\n",
- __func__, ar->net_dev->name, ar->net_dev, ar);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "name=%s dev=0x%p, ar=0x%p\n",
+ ar->net_dev->name, ar->net_dev, ar);
return ret;
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index f325a23..6ef26a3 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -359,14 +359,12 @@ void ath6kl_stop_endpoint(struct net_device *dev, bool keep_profile,
ar->user_key_ctrl = 0;
} else {
- ath6kl_dbg(ATH6KL_DBG_TRC,
- "%s: wmi is not ready 0x%p 0x%p\n",
- __func__, ar, ar->wmi);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "wmi is not ready 0x%p 0x%p\n",
+ ar, ar->wmi);
/* Shut down WMI if we have started it */
if (test_bit(WMI_ENABLED, &ar->flag)) {
- ath6kl_dbg(ATH6KL_DBG_TRC,
- "%s: shut down wmi\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "shut down wmi\n");
ath6kl_wmi_shutdown(ar->wmi);
clear_bit(WMI_ENABLED, &ar->flag);
ar->wmi = NULL;
@@ -374,7 +372,7 @@ void ath6kl_stop_endpoint(struct net_device *dev, bool keep_profile,
}
if (ar->htc_target) {
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: shut down htc\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "shut down htc\n");
htc_stop(ar->htc_target);
}
@@ -801,8 +799,7 @@ void ath6kl_ready_event(void *devt, u8 *datap, u32 sw_ver, u32 abi_ver)
struct net_device *dev = ar->net_dev;
memcpy(dev->dev_addr, datap, ETH_ALEN);
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: mac addr = %pM\n",
- __func__, dev->dev_addr);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "mac addr = %pM\n", dev->dev_addr);
ar->version.wlan_ver = sw_ver;
ar->version.abi_ver = abi_ver;
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index b38732a..c58a107 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -145,7 +145,7 @@ static struct bus_request *ath6kl_sdio_alloc_busreq(struct ath6kl_sdio *ar_sdio)
list_del(&bus_req->list);
spin_unlock_irqrestore(&ar_sdio->lock, flag);
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: bus request 0x%p\n", __func__, bus_req);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "bus request 0x%p\n", bus_req);
return bus_req;
}
@@ -155,7 +155,7 @@ static void ath6kl_sdio_free_bus_req(struct ath6kl_sdio *ar_sdio,
{
unsigned long flag;
- ath6kl_dbg(ATH6KL_DBG_TRC, "%s: bus request 0x%p\n", __func__, bus_req);
+ ath6kl_dbg(ATH6KL_DBG_TRC, "bus request 0x%p\n", bus_req);
spin_lock_irqsave(&ar_sdio->lock, flag);
list_add_tail(&bus_req->list, &ar_sdio->bus_req_freeq);
@@ -683,8 +683,8 @@ static int ath6kl_sdio_probe(struct sdio_func *func,
int count;
ath6kl_dbg(ATH6KL_DBG_TRC,
- "%s: func: 0x%X, vendor id: 0x%X, dev id: 0x%X, block size: 0x%X/0x%X\n",
- __func__, func->num, func->vendor,
+ "func: 0x%X, vendor id: 0x%X, dev id: 0x%X, block size: 0x%X/0x%X\n",
+ func->num, func->vendor,
func->device, func->max_blksize, func->cur_blksize);
ar_sdio = kzalloc(sizeof(struct ath6kl_sdio), GFP_KERNEL);
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index 615b46d..e2e3673 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -184,8 +184,7 @@ int ath6kl_control_tx(void *devt, struct sk_buff *skb,
spin_lock_bh(&ar->lock);
- ath6kl_dbg(ATH6KL_DBG_WLAN_TX,
- "%s: skb=0x%p, len=0x%x eid =%d\n", __func__,
+ ath6kl_dbg(ATH6KL_DBG_WLAN_TX, "skb=0x%p, len=0x%x eid=%d\n",
skb, skb->len, eid);
if (test_bit(WMI_CTRL_EP_FULL, &ar->flag) && (eid == ar->ctrl_ep)) {
@@ -242,8 +241,7 @@ int ath6kl_data_tx(struct sk_buff *skb, struct net_device *dev)
struct wmi_tx_meta_v2 meta_v2;
int ret;
- ath6kl_dbg(ATH6KL_DBG_WLAN_TX,
- "%s: skb=0x%p, data=0x%p, len=0x%x\n", __func__,
+ ath6kl_dbg(ATH6KL_DBG_WLAN_TX, "skb=0x%p, data=0x%p, len=0x%x\n",
skb, skb->data, skb->len);
/* If target is not associated */
@@ -563,13 +561,13 @@ void ath6kl_tx_complete(void *context, struct list_head *packet_queue)
if (status != -ENOSPC)
ath6kl_err("tx error, status: 0x%x\n", status);
ath6kl_dbg(ATH6KL_DBG_WLAN_TX,
- "%s: skb=0x%p data=0x%p len=0x%x eid=%d %s\n",
- __func__, skb, packet->buf, packet->act_len,
+ "skb=0x%p data=0x%p len=0x%x eid=%d %s\n",
+ skb, packet->buf, packet->act_len,
eid, "error!");
} else {
ath6kl_dbg(ATH6KL_DBG_WLAN_TX,
- "%s: skb=0x%p data=0x%p len=0x%x eid=%d %s\n",
- __func__, skb, packet->buf, packet->act_len,
+ "skb=0x%p data=0x%p len=0x%x eid=%d %s\n",
+ skb, packet->buf, packet->act_len,
eid, "OK");
flushing = false;
@@ -680,8 +678,8 @@ void ath6kl_rx_refill(struct htc_target *target, enum htc_endpoint_id endpoint)
INIT_LIST_HEAD(&queue);
ath6kl_dbg(ATH6KL_DBG_WLAN_RX,
- "%s: providing htc with %d buffers at eid=%d\n",
- __func__, n_buf_refill, endpoint);
+ "providing htc with %d buffers at eid=%d\n",
+ n_buf_refill, endpoint);
for (rx_buf = 0; rx_buf < n_buf_refill; rx_buf++) {
skb = ath6kl_buf_alloc(ATH6KL_BUFFER_SIZE);
@@ -731,8 +729,7 @@ struct htc_packet *ath6kl_alloc_amsdu_rxbuf(struct htc_target *target,
struct list_head *pkt_pos;
int refill_cnt = 0, depth = 0;
- ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: eid=%d, len:%d\n",
- __func__, endpoint, len);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "eid=%d, len:%d\n", endpoint, len);
if ((len <= ATH6KL_BUFFER_SIZE) ||
(len > ATH6KL_AMSDU_BUFFER_SIZE))
@@ -1025,9 +1022,8 @@ void ath6kl_rx(struct htc_target *target, struct htc_packet *packet)
u8 tid;
ath6kl_dbg(ATH6KL_DBG_WLAN_RX,
- "%s: ar=0x%p eid=%d, skb=0x%p, data=0x%p, len=0x%x status:%d",
- __func__, ar, ept, skb, packet->buf,
- packet->act_len, status);
+ "ar=0x%p eid=%d, skb=0x%p, data=0x%p, len=0x%x status:%d\n",
+ ar, ept, skb, packet->buf, packet->act_len, status);
if (status || !(skb->data + HTC_HDR_LENGTH)) {
ar->net_stats.rx_errors++;
@@ -1324,8 +1320,8 @@ void aggr_recv_addba_req_evt(struct ath6kl *ar, u8 tid, u16 seq_no, u8 win_sz)
stats = &p_aggr->stat[tid];
if (win_sz < AGGR_WIN_SZ_MIN || win_sz > AGGR_WIN_SZ_MAX)
- ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: win_sz %d, tid %d\n",
- __func__, win_sz, tid);
+ ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "win_sz %d, tid %d\n",
+ win_sz, tid);
if (rxtid->aggr)
aggr_delete_tid_state(p_aggr, tid);
diff --git a/drivers/net/wireless/ath/ath6kl/wmi.c b/drivers/net/wireless/ath/ath6kl/wmi.c
index a52d7d2..29790e5 100644
--- a/drivers/net/wireless/ath/ath6kl/wmi.c
+++ b/drivers/net/wireless/ath/ath6kl/wmi.c
@@ -102,8 +102,7 @@ int ath6kl_wmi_dix_2_dot3(struct wmi *wmi, struct sk_buff *skb)
type = eth_hdr->h_proto;
if (!is_ethertype(be16_to_cpu(type))) {
- ath6kl_dbg(ATH6KL_DBG_WMI,
- "%s: pkt is already in 802.3 format\n", __func__);
+ ath6kl_dbg(ATH6KL_DBG_WMI, "pkt is already in 802.3 format\n");
return 0;
}
@@ -496,8 +495,7 @@ static int ath6kl_wmi_connect_event_rx(struct wmi *wmi, u8 *datap, int len)
ev = (struct wmi_connect_event *) datap;
- ath6kl_dbg(ATH6KL_DBG_WMI, "%s: freq %d bssid %pM\n",
- __func__, ev->ch, ev->bssid);
+ ath6kl_dbg(ATH6KL_DBG_WMI, "freq %d bssid %pM\n", ev->ch, ev->bssid);
memcpy(wmi->bssid, ev->bssid, ETH_ALEN);
@@ -2545,7 +2543,7 @@ int ath6kl_wmi_control_rx(struct wmi *wmi, struct sk_buff *skb)
datap = skb->data;
len = skb->len;
- ath6kl_dbg(ATH6KL_DBG_WMI, "%s: wmi id: %d\n", __func__, id);
+ ath6kl_dbg(ATH6KL_DBG_WMI, "wmi id: %d\n", id);
ath6kl_dbg_dump(ATH6KL_DBG_RAW_BYTES, "msg payload ", datap, len);
switch (id) {
--
1.7.6.131.g99019
^ permalink raw reply related
* [PATCH 2/2] ath6kl: Remove trailing unpaired close paren from ath6kl_err uses
From: Joe Perches @ 2011-07-17 21:38 UTC (permalink / raw)
To: Kalle Valo, linux-kernel-u79uwXL29TY76Z2rM5mHXA
Cc: devel-tBiZLqfeLfOHmIFyCCdPziST3g8Odh+X, gregkh-l3A5Bk7waGM,
error27-Re5JQEeQqe8AvxtiuMwx3w,
linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, John W. Linville
In-Reply-To: <cover.1310938421.git.joe-6d6DIl74uiNBDgjK7y7TUQ@public.gmane.org>
Unpaired parentheses are unsightly.
Signed-off-by: Joe Perches <joe-6d6DIl74uiNBDgjK7y7TUQ@public.gmane.org>
---
drivers/net/wireless/ath/ath6kl/sdio.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index c58a107..e399b17 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -511,7 +511,7 @@ static int ath6kl_sdio_power_on(struct ath6kl_sdio *ar_sdio)
ret = sdio_enable_func(func);
if (ret) {
- ath6kl_err("Unable to enable sdio func: %d)\n", ret);
+ ath6kl_err("Unable to enable sdio func: %d\n", ret);
sdio_release_host(func);
return ret;
}
@@ -760,7 +760,7 @@ static int ath6kl_sdio_probe(struct sdio_func *func,
ret = sdio_set_block_size(func, HIF_MBOX_BLOCK_SIZE);
if (ret) {
- ath6kl_err("Set sdio block size %d failed: %d)\n",
+ ath6kl_err("Set sdio block size %d failed: %d\n",
HIF_MBOX_BLOCK_SIZE, ret);
sdio_release_host(func);
goto err_off;
--
1.7.6.131.g99019
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 0/2] ath6kl: more neatening
From: Joe Perches @ 2011-07-17 21:38 UTC (permalink / raw)
To: Kalle Valo; +Cc: netdev, gregkh, linux-wireless, linux-kernel, devel
In-Reply-To: <4E2349D4.4000204@qca.qualcomm.com>
> Great, thanks. I have now applied your patches to ath6kl-cleanup tree
> and they will be included in patchset v3.
Here's a couple of more.
Joe Perches (2):
ath6kl: Remove __func__ uses from ath6kl_dbg
ath6kl: Remove trailing unpaired close paren from ath6kl_err uses
drivers/net/wireless/ath/ath6kl/bmi.c | 4 +-
drivers/net/wireless/ath/ath6kl/cfg80211.c | 101 ++++++++++++---------------
drivers/net/wireless/ath/ath6kl/debug.c | 20 +++---
drivers/net/wireless/ath/ath6kl/debug.h | 27 ++++----
drivers/net/wireless/ath/ath6kl/htc.c | 11 ++--
drivers/net/wireless/ath/ath6kl/init.c | 8 +-
drivers/net/wireless/ath/ath6kl/main.c | 13 ++--
drivers/net/wireless/ath/ath6kl/sdio.c | 12 ++--
drivers/net/wireless/ath/ath6kl/txrx.c | 30 ++++-----
drivers/net/wireless/ath/ath6kl/wmi.c | 8 +--
10 files changed, 107 insertions(+), 127 deletions(-)
--
1.7.6.131.g99019
^ permalink raw reply
* Re: iproute2: Add 802.1ad / QinQ support
From: David Lamparter @ 2011-07-17 21:11 UTC (permalink / raw)
To: David Lamparter; +Cc: netdev, Patrick McHardy
In-Reply-To: <1310936903-26251-1-git-send-email-equinox@diac24.net>
probably should've put "iproute2" in the subject line... sorry.
-David
On Sun, Jul 17, 2011 at 11:08:23PM +0200, David Lamparter wrote:
> + } else if (matches(*argv, "protocol") == 0) {
> + NEXT_ARG();
> + if (strcmp(*argv, "802.1Q") == 0)
> + proto = 0x8100;
> + else if (strcmp(*argv, "802.1ad") == 0)
> + proto = 0x88a8;
> + else if (strcmp(*argv, "9100") == 0)
> + proto = 0x9100;
> + else if (strcmp(*argv, "9200") == 0)
> + proto = 0x9200;
> + else if (strcmp(*argv, "9300") == 0)
> + proto = 0x9300;
> + else
> + invarg("protocol is invalid", *argv);
> + addattr_l(n, 1024, IFLA_VLAN_PROTOCOL, &proto, 2);
^ permalink raw reply
* [PATCH] Add 802.1ad / QinQ support
From: David Lamparter @ 2011-07-17 21:08 UTC (permalink / raw)
To: netdev; +Cc: Patrick McHardy, David Lamparter
In-Reply-To: <1310936105-3494206-1-git-send-email-equinox@diac24.net>
(work in progress, patch for testing)
---
include/linux/if_link.h | 1 +
ip/iplink_vlan.c | 22 ++++++++++++++++++++--
2 files changed, 21 insertions(+), 2 deletions(-)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 304c44f..0e6eeec 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -223,6 +223,7 @@ enum {
IFLA_VLAN_FLAGS,
IFLA_VLAN_EGRESS_QOS,
IFLA_VLAN_INGRESS_QOS,
+ IFLA_VLAN_PROTOCOL,
__IFLA_VLAN_MAX,
};
diff --git a/ip/iplink_vlan.c b/ip/iplink_vlan.c
index 223feb3..f5e5a5f 100644
--- a/ip/iplink_vlan.c
+++ b/ip/iplink_vlan.c
@@ -21,7 +21,7 @@
static void explain(void)
{
fprintf(stderr,
- "Usage: ... vlan id VLANID [ FLAG-LIST ]\n"
+ "Usage: ... vlan id VLANID [ protocol ENCAPSULATION ] [ FLAG-LIST ]\n"
" [ ingress-qos-map QOS-MAP ] [ egress-qos-map QOS-MAP ]\n"
"\n"
"VLANID := 0-4095\n"
@@ -30,6 +30,7 @@ static void explain(void)
" [ loose_binding { on | off } ]\n"
"QOS-MAP := [ QOS-MAP ] QOS-MAPPING\n"
"QOS-MAPPING := FROM:TO\n"
+ "ENCAPSULATION := 802.1Q | 802.1ad | 9100 | 9200 | 9300\n"
);
}
@@ -77,7 +78,7 @@ static int vlan_parse_opt(struct link_util *lu, int argc, char **argv,
struct nlmsghdr *n)
{
struct ifla_vlan_flags flags = { 0 };
- __u16 id;
+ __u16 id, proto;
while (argc > 0) {
if (matches(*argv, "id") == 0) {
@@ -85,6 +86,21 @@ static int vlan_parse_opt(struct link_util *lu, int argc, char **argv,
if (get_u16(&id, *argv, 0))
invarg("id is invalid", *argv);
addattr_l(n, 1024, IFLA_VLAN_ID, &id, 2);
+ } else if (matches(*argv, "protocol") == 0) {
+ NEXT_ARG();
+ if (strcmp(*argv, "802.1Q") == 0)
+ proto = 0x8100;
+ else if (strcmp(*argv, "802.1ad") == 0)
+ proto = 0x88a8;
+ else if (strcmp(*argv, "9100") == 0)
+ proto = 0x9100;
+ else if (strcmp(*argv, "9200") == 0)
+ proto = 0x9200;
+ else if (strcmp(*argv, "9300") == 0)
+ proto = 0x9300;
+ else
+ invarg("protocol is invalid", *argv);
+ addattr_l(n, 1024, IFLA_VLAN_PROTOCOL, &proto, 2);
} else if (matches(*argv, "reorder_hdr") == 0) {
NEXT_ARG();
flags.mask |= VLAN_FLAG_REORDER_HDR;
@@ -183,6 +199,8 @@ static void vlan_print_opt(struct link_util *lu, FILE *f, struct rtattr *tb[])
RTA_PAYLOAD(tb[IFLA_VLAN_ID]) < sizeof(__u16))
return;
+ if (tb[IFLA_VLAN_PROTOCOL])
+ fprintf(f, "protocol 0x%04x ", *(__u16 *)RTA_DATA(tb[IFLA_VLAN_PROTOCOL]));
fprintf(f, "id %u ", *(__u16 *)RTA_DATA(tb[IFLA_VLAN_ID]));
if (tb[IFLA_VLAN_FLAGS]) {
--
1.7.5.3
^ permalink raw reply related
* [PATCH RFC 2/2] r8169: jumbo fixes.
From: Francois Romieu @ 2011-07-17 20:53 UTC (permalink / raw)
To: netdev; +Cc: Hayes Wang
(Hayes, I'd welcome comments regarding the jumbo enable/disable stuff)
- fix features : jumbo frames and checksumming can not be used at the
same time.
- introduce hw_jumbo_{enable / disable} helpers. Their content has been
creatively extracted from Realtek's own drivers. As an illustration,
it would be nice to know how/if the MaxTxPacketSize register operates
when the device can work with a 9k jumbo frame as its documentation
(8168c) can not be applied beyond ~7k.
- rtl_tx_performance_tweak is moved forward. No change.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
---
drivers/net/r8169.c | 302 ++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 248 insertions(+), 54 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index ea8ee93..9451958 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -141,84 +141,104 @@ enum rtl_tx_desc_version {
RTL_TD_1 = 1,
};
-#define _R(NAME,TD,FW) \
- { .name = NAME, .txd_version = TD, .fw_name = FW }
+#define JUMBO_1K ETH_DATA_LEN
+#define JUMBO_4K (4*1024 - ETH_HLEN - 2)
+#define JUMBO_6K (6*1024 - ETH_HLEN - 2)
+#define JUMBO_7K (7*1024 - ETH_HLEN - 2)
+#define JUMBO_9K (9*1024 - ETH_HLEN - 2)
+
+#define _R(NAME,TD,FW,SZ,B) { \
+ .name = NAME, \
+ .txd_version = TD, \
+ .fw_name = FW, \
+ .jumbo_max = SZ, \
+ .jumbo_csum_ok = B \
+}
static const struct {
const char *name;
enum rtl_tx_desc_version txd_version;
const char *fw_name;
+ u16 jumbo_max;
+ bool jumbo_csum_ok;
} rtl_chip_infos[] = {
/* PCI devices. */
[RTL_GIGA_MAC_VER_01] =
- _R("RTL8169", RTL_TD_0, NULL),
+ _R("RTL8169", RTL_TD_0, NULL, JUMBO_7K, true),
[RTL_GIGA_MAC_VER_02] =
- _R("RTL8169s", RTL_TD_0, NULL),
+ _R("RTL8169s", RTL_TD_0, NULL, JUMBO_7K, true),
[RTL_GIGA_MAC_VER_03] =
- _R("RTL8110s", RTL_TD_0, NULL),
+ _R("RTL8110s", RTL_TD_0, NULL, JUMBO_7K, true),
[RTL_GIGA_MAC_VER_04] =
- _R("RTL8169sb/8110sb", RTL_TD_0, NULL),
+ _R("RTL8169sb/8110sb", RTL_TD_0, NULL, JUMBO_7K, true),
[RTL_GIGA_MAC_VER_05] =
- _R("RTL8169sc/8110sc", RTL_TD_0, NULL),
+ _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K, true),
[RTL_GIGA_MAC_VER_06] =
- _R("RTL8169sc/8110sc", RTL_TD_0, NULL),
+ _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K, true),
/* PCI-E devices. */
[RTL_GIGA_MAC_VER_07] =
- _R("RTL8102e", RTL_TD_1, NULL),
+ _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_08] =
- _R("RTL8102e", RTL_TD_1, NULL),
+ _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_09] =
- _R("RTL8102e", RTL_TD_1, NULL),
+ _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_10] =
- _R("RTL8101e", RTL_TD_0, NULL),
+ _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_11] =
- _R("RTL8168b/8111b", RTL_TD_0, NULL),
+ _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false),
[RTL_GIGA_MAC_VER_12] =
- _R("RTL8168b/8111b", RTL_TD_0, NULL),
+ _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false),
[RTL_GIGA_MAC_VER_13] =
- _R("RTL8101e", RTL_TD_0, NULL),
+ _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_14] =
- _R("RTL8100e", RTL_TD_0, NULL),
+ _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_15] =
- _R("RTL8100e", RTL_TD_0, NULL),
+ _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_16] =
- _R("RTL8101e", RTL_TD_0, NULL),
+ _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true),
[RTL_GIGA_MAC_VER_17] =
- _R("RTL8168b/8111b", RTL_TD_0, NULL),
+ _R("RTL8168b/8111b", RTL_TD_1, NULL, JUMBO_4K, false),
[RTL_GIGA_MAC_VER_18] =
- _R("RTL8168cp/8111cp", RTL_TD_1, NULL),
+ _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_19] =
- _R("RTL8168c/8111c", RTL_TD_1, NULL),
+ _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_20] =
- _R("RTL8168c/8111c", RTL_TD_1, NULL),
+ _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_21] =
- _R("RTL8168c/8111c", RTL_TD_1, NULL),
+ _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_22] =
- _R("RTL8168c/8111c", RTL_TD_1, NULL),
+ _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_23] =
- _R("RTL8168cp/8111cp", RTL_TD_1, NULL),
+ _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_24] =
- _R("RTL8168cp/8111cp", RTL_TD_1, NULL),
+ _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false),
[RTL_GIGA_MAC_VER_25] =
- _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_1),
+ _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_1,
+ JUMBO_9K, false),
[RTL_GIGA_MAC_VER_26] =
- _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_2),
+ _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_2,
+ JUMBO_9K, false),
[RTL_GIGA_MAC_VER_27] =
- _R("RTL8168dp/8111dp", RTL_TD_1, NULL),
+ _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false),
[RTL_GIGA_MAC_VER_28] =
- _R("RTL8168dp/8111dp", RTL_TD_1, NULL),
+ _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false),
[RTL_GIGA_MAC_VER_29] =
- _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1),
+ _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1,
+ JUMBO_1K, true),
[RTL_GIGA_MAC_VER_30] =
- _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1),
+ _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1,
+ JUMBO_1K, true),
[RTL_GIGA_MAC_VER_31] =
- _R("RTL8168dp/8111dp", RTL_TD_1, NULL),
+ _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false),
[RTL_GIGA_MAC_VER_32] =
- _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_1),
+ _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_1,
+ JUMBO_9K, false),
[RTL_GIGA_MAC_VER_33] =
- _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_2),
+ _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_2,
+ JUMBO_9K, false),
[RTL_GIGA_MAC_VER_34] =
- _R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3)
+ _R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3,
+ JUMBO_9K, false),
};
#undef _R
@@ -457,8 +477,12 @@ enum rtl_register_content {
/* Config3 register p.25 */
MagicPacket = (1 << 5), /* Wake up when receives a Magic Packet */
LinkUp = (1 << 4), /* Wake up when the cable connection is re-established */
+ Jumbo_En0 = (1 << 2), /* 8168 only. Reserved in the 8168b */
Beacon_en = (1 << 0), /* 8168 only. Reserved in the 8168b */
+ /* Config4 register */
+ Jumbo_En1 = (1 << 1), /* 8168 only. Reserved in the 8168b */
+
/* Config5 register p.27 */
BWF = (1 << 6), /* Accept Broadcast wakeup frame */
MWF = (1 << 5), /* Accept Multicast wakeup frame */
@@ -667,6 +691,11 @@ struct rtl8169_private {
void (*up)(struct rtl8169_private *);
} pll_power_ops;
+ struct jumbo_ops {
+ void (*enable)(struct rtl8169_private *);
+ void (*disable)(struct rtl8169_private *);
+ } jumbo_ops;
+
int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
int (*get_settings)(struct net_device *, struct ethtool_cmd *);
void (*phy_reset_enable)(struct rtl8169_private *tp);
@@ -727,6 +756,19 @@ static void rtl8169_down(struct net_device *dev);
static void rtl8169_rx_clear(struct rtl8169_private *tp);
static int rtl8169_poll(struct napi_struct *napi, int budget);
+static void rtl_tx_performance_tweak(struct pci_dev *pdev, u16 force)
+{
+ int cap = pci_pcie_cap(pdev);
+
+ if (cap) {
+ u16 ctl;
+
+ pci_read_config_word(pdev, cap + PCI_EXP_DEVCTL, &ctl);
+ ctl = (ctl & ~PCI_EXP_DEVCTL_READRQ) | force;
+ pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, ctl);
+ }
+}
+
static u32 ocp_read(struct rtl8169_private *tp, u8 mask, u16 reg)
{
void __iomem *ioaddr = tp->mmio_addr;
@@ -1467,9 +1509,15 @@ static int rtl8169_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
static u32 rtl8169_fix_features(struct net_device *dev, u32 features)
{
+ struct rtl8169_private *tp = netdev_priv(dev);
+
if (dev->mtu > TD_MSS_MAX)
features &= ~NETIF_F_ALL_TSO;
+ if (dev->mtu > JUMBO_1K &&
+ !rtl_chip_infos[tp->mac_version].jumbo_csum_ok)
+ features &= ~(NETIF_F_IP_CSUM | NETIF_F_RXCSUM);
+
return features;
}
@@ -3438,8 +3486,8 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
r8168_phy_power_up(tp);
}
-static void rtl_pll_power_op(struct rtl8169_private *tp,
- void (*op)(struct rtl8169_private *))
+static void rtl_generic_op(struct rtl8169_private *tp,
+ void (*op)(struct rtl8169_private *))
{
if (op)
op(tp);
@@ -3447,12 +3495,12 @@ static void rtl_pll_power_op(struct rtl8169_private *tp,
static void rtl_pll_power_down(struct rtl8169_private *tp)
{
- rtl_pll_power_op(tp, tp->pll_power_ops.down);
+ rtl_generic_op(tp, tp->pll_power_ops.down);
}
static void rtl_pll_power_up(struct rtl8169_private *tp)
{
- rtl_pll_power_op(tp, tp->pll_power_ops.up);
+ rtl_generic_op(tp, tp->pll_power_ops.up);
}
static void __devinit rtl_init_pll_power_ops(struct rtl8169_private *tp)
@@ -3541,6 +3589,150 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp)
tp->dirty_tx = tp->dirty_rx = tp->cur_tx = tp->cur_rx = 0;
}
+static void rtl_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ rtl_generic_op(tp, tp->jumbo_ops.enable);
+}
+
+static void rtl_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ rtl_generic_op(tp, tp->jumbo_ops.disable);
+}
+
+static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0);
+ RTL_W8(Config4, RTL_R8(Config4) | Jumbo_En1);
+ rtl_tx_performance_tweak(tp->pci_dev, 0x2 << MAX_READ_REQUEST_SHIFT);
+}
+
+static void r8168c_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0);
+ RTL_W8(Config4, RTL_R8(Config4) & ~Jumbo_En1);
+ rtl_tx_performance_tweak(tp->pci_dev, 0x5 << MAX_READ_REQUEST_SHIFT);
+}
+
+static void r8168dp_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0);
+}
+
+static void r8168dp_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0);
+}
+
+static void r8168e_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+ struct pci_dev *pdev = tp->pci_dev;
+
+ RTL_W8(MaxTxPacketSize, 0x3f);
+ RTL_W8(Config3, RTL_R8(Config3) | Jumbo_En0);
+ RTL_W8(Config4, RTL_R8(Config4) | 0x01);
+ pci_write_config_byte(pdev, 0x79, 0x20);
+}
+
+static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+ struct pci_dev *pdev = tp->pci_dev;
+
+ RTL_W8(MaxTxPacketSize, 0x0c);
+ RTL_W8(Config3, RTL_R8(Config3) & ~Jumbo_En0);
+ RTL_W8(Config4, RTL_R8(Config4) & ~0x01);
+ pci_write_config_byte(pdev, 0x79, 0x50);
+}
+
+static void r8168b_0_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ rtl_tx_performance_tweak(tp->pci_dev,
+ (0x2 << MAX_READ_REQUEST_SHIFT) | PCI_EXP_DEVCTL_NOSNOOP_EN);
+}
+
+static void r8168b_0_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ rtl_tx_performance_tweak(tp->pci_dev,
+ (0x5 << MAX_READ_REQUEST_SHIFT) | PCI_EXP_DEVCTL_NOSNOOP_EN);
+}
+
+static void r8168b_1_hw_jumbo_enable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ r8168b_0_hw_jumbo_enable(tp);
+
+ RTL_W8(Config4, RTL_R8(Config4) | (1 << 0));
+}
+
+static void r8168b_1_hw_jumbo_disable(struct rtl8169_private *tp)
+{
+ void __iomem *ioaddr = tp->mmio_addr;
+
+ r8168b_0_hw_jumbo_disable(tp);
+
+ RTL_W8(Config4, RTL_R8(Config4) & ~(1 << 0));
+}
+
+static void __devinit rtl_init_jumbo_ops(struct rtl8169_private *tp)
+{
+ struct jumbo_ops *ops = &tp->jumbo_ops;
+
+ switch (tp->mac_version) {
+ case RTL_GIGA_MAC_VER_11:
+ ops->disable = r8168b_0_hw_jumbo_disable;
+ ops->enable = r8168b_0_hw_jumbo_enable;
+ break;
+ case RTL_GIGA_MAC_VER_12:
+ case RTL_GIGA_MAC_VER_17:
+ ops->disable = r8168b_1_hw_jumbo_disable;
+ ops->enable = r8168b_1_hw_jumbo_enable;
+ break;
+ case RTL_GIGA_MAC_VER_18: /* Wild guess. Needs info from Realtek. */
+ case RTL_GIGA_MAC_VER_19:
+ case RTL_GIGA_MAC_VER_20:
+ case RTL_GIGA_MAC_VER_21: /* Wild guess. Needs info from Realtek. */
+ case RTL_GIGA_MAC_VER_22:
+ case RTL_GIGA_MAC_VER_23:
+ case RTL_GIGA_MAC_VER_24:
+ case RTL_GIGA_MAC_VER_25:
+ case RTL_GIGA_MAC_VER_26:
+ ops->disable = r8168c_hw_jumbo_disable;
+ ops->enable = r8168c_hw_jumbo_enable;
+ break;
+ case RTL_GIGA_MAC_VER_27:
+ case RTL_GIGA_MAC_VER_28:
+ ops->disable = r8168dp_hw_jumbo_disable;
+ ops->enable = r8168dp_hw_jumbo_enable;
+ break;
+ case RTL_GIGA_MAC_VER_31: /* Wild guess. Needs info from Realtek. */
+ case RTL_GIGA_MAC_VER_32:
+ case RTL_GIGA_MAC_VER_33:
+ case RTL_GIGA_MAC_VER_34:
+ ops->disable = r8168e_hw_jumbo_disable;
+ ops->enable = r8168e_hw_jumbo_enable;
+ break;
+
+ /*
+ * No action needed for jumbo frames with 8169.
+ * No jumbo for 810x at all.
+ */
+ default:
+ ops->disable = NULL;
+ ops->enable = NULL;
+ break;
+ }
+}
+
static void rtl_hw_reset(struct rtl8169_private *tp)
{
void __iomem *ioaddr = tp->mmio_addr;
@@ -3685,6 +3877,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
rtl_init_mdio_ops(tp);
rtl_init_pll_power_ops(tp);
+ rtl_init_jumbo_ops(tp);
rtl8169_print_mac_version(tp);
@@ -3766,6 +3959,12 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
netif_info(tp, probe, dev, "%s at 0x%lx, %pM, XID %08x IRQ %d\n",
rtl_chip_infos[chipset].name, dev->base_addr, dev->dev_addr,
(u32)(RTL_R32(TxConfig) & 0x9cf0f8ff), dev->irq);
+ if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) {
+ netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, "
+ "rx/tx checksumming: %s]\n",
+ rtl_chip_infos[chipset].jumbo_max,
+ rtl_chip_infos[chipset].jumbo_csum_ok ? "ok" : "ko");
+ }
if (tp->mac_version == RTL_GIGA_MAC_VER_27 ||
tp->mac_version == RTL_GIGA_MAC_VER_28 ||
@@ -4122,19 +4321,6 @@ static void rtl_hw_start_8169(struct net_device *dev)
RTL_W16(IntrMask, tp->intr_event);
}
-static void rtl_tx_performance_tweak(struct pci_dev *pdev, u16 force)
-{
- int cap = pci_pcie_cap(pdev);
-
- if (cap) {
- u16 ctl;
-
- pci_read_config_word(pdev, cap + PCI_EXP_DEVCTL, &ctl);
- ctl = (ctl & ~PCI_EXP_DEVCTL_READRQ) | force;
- pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, ctl);
- }
-}
-
static void rtl_csi_access_enable(void __iomem *ioaddr, u32 bits)
{
u32 csi;
@@ -4714,9 +4900,17 @@ static void rtl_hw_start_8101(struct net_device *dev)
static int rtl8169_change_mtu(struct net_device *dev, int new_mtu)
{
- if (new_mtu < ETH_ZLEN || new_mtu > SafeMtu)
+ struct rtl8169_private *tp = netdev_priv(dev);
+
+ if (new_mtu < ETH_ZLEN ||
+ new_mtu > rtl_chip_infos[tp->mac_version].jumbo_max)
return -EINVAL;
+ if (new_mtu > ETH_DATA_LEN)
+ rtl_hw_jumbo_enable(tp);
+ else
+ rtl_hw_jumbo_disable(tp);
+
dev->mtu = new_mtu;
netdev_update_features(dev);
--
1.7.4.4
^ permalink raw reply related
* Re: [patch net-next-2.6] vlan: introduce ndo_vlan_[enable/disable]
From: Michał Mirosław @ 2011-07-17 21:06 UTC (permalink / raw)
To: Jiri Pirko; +Cc: netdev, davem, shemminger, eric.dumazet, greearb
In-Reply-To: <20110717194421.GA2153@minipsycho>
W dniu 17 lipca 2011 21:44 użytkownik Jiri Pirko <jpirko@redhat.com> napisał:
> Sun, Jul 17, 2011 at 10:36:04AM CEST, mirqus@gmail.com wrote:
>>W dniu 17 lipca 2011 09:30 użytkownik Jiri Pirko <jpirko@redhat.com> napisał:
>>> Sat, Jul 16, 2011 at 04:14:36PM CEST, mirqus@gmail.com wrote:
>>>>2011/7/16 Jiri Pirko <jpirko@redhat.com>:
>>>>> Some devices are not able to enable/disable rx/tw vlan accel separately.
>>>>> they depend on ndo_vlan_rx_register to know if to enable of disable
>>>>> hw accel. And since ndo_vlan_rx_register is going to die soon,
>>>>> this must be resolved.
>>>>>
>>>>> One solution might be to enable accel on device start every time, even
>>>>> if there are no vlan up on. But this would change behaviour and might
>>>>> lead to possible regression (on older devices).
>>>>[...]
>>>>
>>>>Please describe the possible regression. As I see it, there won't be
>>>>any user visible change of behaviour - network code takes care of
>>>>reinserting VLAN tag when necessary. If you think that disabling tag
>>>>stripping is beneficial for cases where no VLANs are configured, it's
>>>>better to do that in netdev_fix_features() for devices which advertise
>>>>NETIF_F_HW_VLAN_RX in hw_features.
>>>
>>> Well I just wanted to preserve current behaviour which is that in many
>>> drivers vlan accel is enabled only if some vid is registered upon the
>>> device and it's disabled again when no vid is registered. I can see
>>> no way to do this with current code after removing ndo_vlan_rx_register.
>>>
>>> I expect unexpected
>>
>>:-D
>>
>>> ... problems on old cards when vlan accel would be
>>> enabled all the time, but maybe I'm wrong...
>>
>>Device has no way of knowing how the system uses VLAN tags, stripped
>>or not. Any problems would be driver problems and since you're making
>>it all use generic code, bugs will hit all drivers simultaneously or
>>(preferably) won't happen at all.
>>
>>> One idea is for device which do not support sepatate rx/tx vlan accel
>>> enabling/disabling they can probably use ndo_fix_features force to
>>> enable/disable rx/tx pair together. That would resolve the situation as
>>> well giving user possibility to turn off vlan accel in case of any issues.
>>
>>That is exactly the idea behind ndo_fix_features.
> In netdev_fix_features add check if either one of NETIF_F_HW_VLAN_TX or
> NETIF_F_HW_VLAN_RX is set and in that case set the other one. Of course
> this would be done only for devices what do not support separate rx/tx
> vlan on/off. But how to distinguish? NETIF_F_HW_VLAN_BOTH feature flag?
Not in netdev_fix_features(). This case you describe should be handled
in driver-specific
ndo_fix_features callback. Because if NETIF_F_HW_VLAN_TX is disabled,
the network core will insert the tag anyway, this would cover the
restriction:
if (!(features & NEITF_F_HW_VLAN_RX))
features &= ~NETIF_F_HW_VLAN_TX;
This works, because if HW_VLAN_TX is disabled, the driver never gets
packets which need tag insertion. Besides those already in the queue,
of course.
For netdev_fix_features() I thought that if no VLANs are configured, then it
could disable NETIF_F_HW_VLAN_RX (if set in hw_features). The
conditions for disabling it need some thought. For example, if the
device is not slave to some stacking device (bonding doesn't count, as
it passes VLAN registeration to its slaves) then packets with tags
would be either dropped or have tag reinserted (for network taps).
Best Regards,
Michał Mirosław
^ permalink raw reply
* [PATCH RFC 1/2] r8169: expand received packet length indication.
From: Francois Romieu @ 2011-07-17 20:51 UTC (permalink / raw)
To: netdev; +Cc: Hayes Wang
8168d and above allow jumbo frames beyond 8k. Bump the received
packet length check before enabling jumbo frames on these chipsets.
Frame length indication covers bits 0..13 of the first Rx descriptor
32 bits for the 8169 and 8168. I only have authoritative documentation
for the allowed use of the extra (13) bit with the 8169 and 8168c.
Realtek's drivers use the same mask for the 816x and the fast ethernet
only 810x.
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
---
drivers/net/r8169.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 3ddd339..ea8ee93 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -5311,7 +5311,7 @@ static int rtl8169_rx_interrupt(struct net_device *dev,
} else {
struct sk_buff *skb;
dma_addr_t addr = le64_to_cpu(desc->addr);
- int pkt_size = (status & 0x00001FFF) - 4;
+ int pkt_size = (status & 0x00003fff) - 4;
/*
* The driver does not support incoming fragmented
--
1.7.4.4
^ permalink raw reply related
* [RFC PATCH] net: vlan: 802.1ad S-VLAN support
From: David Lamparter @ 2011-07-17 20:55 UTC (permalink / raw)
To: netdev; +Cc: Patrick McHardy, David Lamparter
this adds support for 802.1ad S-VLANs, which basically are regular VLANs
with a different protocol field. also supported are the legacy QinQ
9100/9200/9300 ethertypes. as with the CFI bit for 802.1Q, the DEI bit
is blissfully ignored.
this patch modifies the 802.1Q code, but keeps the regular VLAN
acceleration architecture unchanged. the S-VLAN code does not use that;
I am not aware of any NIC implementing it for ethertypes other than
8100.
all in-kernel interfaces and definitions are kept compatible; 802.1Q
performance should not experience significant changes.
tested in a simple setup with kvm, including some random stackings of
S-VLANs and C-VLANs.
---
well, this isn't quite finished yet, but it's in a state where I need
some feedback... especially on:
- int vlan_pidx(u16 protocol)
do i do this with a table? that wastes a cacheline... as code it's
around 32 bytes on x86_64. it's not called for regular 802.1Q frames
from any hot paths btw, so maybe i shouldn't care?
- is_vlan_dev / IFF_802_1Q_VLAN
need to decide whether this should be set for S-VLAN devices, and
after it's decided need to look at the users from drivers/net and
drivers/scsi
- vlan_dev_vlan_id - same as above
- GRO & co. - basically i have no clue.
Any feedback very welcome,
David
include/linux/if_link.h | 1 +
include/linux/if_vlan.h | 43 +++++++----
net/8021q/vlan.c | 190 ++++++++++++++++++++++++++++++----------------
net/8021q/vlan.h | 9 ++-
net/8021q/vlan_core.c | 6 +-
net/8021q/vlan_dev.c | 15 +++-
net/8021q/vlan_gvrp.c | 6 ++
net/8021q/vlan_netlink.c | 21 +++++-
net/8021q/vlanproc.c | 9 ++-
net/core/dev.c | 2 +-
10 files changed, 207 insertions(+), 95 deletions(-)
diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 0ee969a..23653a7 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -225,6 +225,7 @@ enum {
IFLA_VLAN_FLAGS,
IFLA_VLAN_EGRESS_QOS,
IFLA_VLAN_INGRESS_QOS,
+ IFLA_VLAN_PROTOCOL,
__IFLA_VLAN_MAX,
};
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index bc03e40..cd0269e 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -45,7 +45,7 @@ struct vlan_hdr {
* struct vlan_ethhdr - vlan ethernet header (ethhdr + vlan_hdr)
* @h_dest: destination ethernet address
* @h_source: source ethernet address
- * @h_vlan_proto: ethernet protocol (always 0x8100)
+ * @h_vlan_proto: ethernet protocol (0x8100, 0x88a8, 0x9x00)
* @h_vlan_TCI: priority and VLAN ID
* @h_vlan_encapsulated_proto: packet type ID or len
*/
@@ -71,6 +71,16 @@ static inline struct vlan_ethhdr *vlan_eth_hdr(const struct sk_buff *skb)
#define VLAN_VID_MASK 0x0fff /* VLAN Identifier */
#define VLAN_N_VID 4096
+enum {
+ VLAN_PROTOIDX_8021Q = 0,
+ VLAN_PROTOIDX_8021AD,
+ VLAN_PROTOIDX_QINQ1,
+ VLAN_PROTOIDX_QINQ2,
+ VLAN_PROTOIDX_QINQ3,
+
+ VLAN_N_PROTOCOL
+};
+
/* found in socket.c */
extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
@@ -86,27 +96,31 @@ struct vlan_group {
* the vlan is attached to.
*/
unsigned int nr_vlans;
- struct hlist_node hlist; /* linked list */
- struct net_device **vlan_devices_arrays[VLAN_GROUP_ARRAY_SPLIT_PARTS];
+ struct net_device **vlan_devices_arrays[VLAN_N_PROTOCOL]
+ [VLAN_GROUP_ARRAY_SPLIT_PARTS];
struct rcu_head rcu;
};
-static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
- u16 vlan_id)
+#define vlan_group_get_device(vg, vlan_id) \
+ vlan_group_get_device_pidx(vg, VLAN_PROTOIDX_8021Q, vlan_id)
+static inline struct net_device *vlan_group_get_device_pidx(struct vlan_group *vg,
+ int proto_idx, u16 vlan_id)
{
struct net_device **array;
- array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
+ array = vg->vlan_devices_arrays[proto_idx][vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL;
}
-static inline void vlan_group_set_device(struct vlan_group *vg,
- u16 vlan_id,
- struct net_device *dev)
+#define vlan_group_set_device(vg, vlan_id, dev) \
+ vlan_group_set_device_pidx(vg, VLAN_PROTOIDX_8021Q, vlan_id, dev)
+static inline void vlan_group_set_device_pidx(struct vlan_group *vg,
+ int proto_idx, u16 vlan_id,
+ struct net_device *dev)
{
struct net_device **array;
if (!vg)
return;
- array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
+ array = vg->vlan_devices_arrays[proto_idx][vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev;
}
@@ -125,7 +139,7 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
u16 vlan_tci, int polling);
-extern bool vlan_do_receive(struct sk_buff **skb);
+extern bool vlan_do_receive(struct sk_buff **skb, int pidx, u16 protocol);
extern struct sk_buff *vlan_untag(struct sk_buff *skb);
extern gro_result_t
vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
@@ -226,7 +240,8 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb,
*
* Does not change skb->protocol so this function can be used during receive.
*/
-static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci)
+static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
+ u16 protocol, u16 vlan_tci)
{
struct vlan_ethhdr *veth;
@@ -241,7 +256,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci)
skb->mac_header -= VLAN_HLEN;
/* first, the ethernet type */
- veth->h_vlan_proto = htons(ETH_P_8021Q);
+ veth->h_vlan_proto = htons(protocol);
/* now, the TCI */
veth->h_vlan_TCI = htons(vlan_tci);
@@ -262,7 +277,7 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci)
*/
static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci)
{
- skb = vlan_insert_tag(skb, vlan_tci);
+ skb = vlan_insert_tag(skb, ETH_P_8021Q, vlan_tci);
if (skb)
skb->protocol = htons(ETH_P_8021Q);
return skb;
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index d24c464..2cdd886 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -46,17 +46,39 @@
int vlan_net_id __read_mostly;
-const char vlan_fullname[] = "802.1Q VLAN Support";
+const char vlan_fullname[] = "802.1Q/.1ad VLAN Support";
const char vlan_version[] = DRV_VERSION;
/* End of global variables definitions. */
+#if 0
+/* lookup table, use first byte */
+static const uint8_t vlan_protocol_idx[256] = {
+ [ETH_P_8021Q >> 8] = VLAN_PROTOIDX_8021Q,
+ [ETH_P_8021AD >> 8] = VLAN_PROTOIDX_8021AD,
+ [ETH_P_QINQ1 >> 8] = VLAN_PROTOIDX_QINQ1,
+ [ETH_P_QINQ2 >> 8] = VLAN_PROTOIDX_QINQ2,
+ [ETH_P_QINQ3 >> 8] = VLAN_PROTOIDX_QINQ3,
+};
+#define vlan_pidx(protocol) (vlan_protocol_idx[(protocol) >> 8])
+#else
+static inline int vlan_pidx(u16 protocol)
+{
+ if (likely(protocol == ETH_P_8021Q))
+ return VLAN_PROTOIDX_8021Q;
+ if (protocol == ETH_P_8021AD)
+ return VLAN_PROTOIDX_8021AD;
+ return ((protocol - ETH_P_QINQ1) >> 8) + VLAN_PROTOIDX_QINQ1;
+}
+#endif
+
static void vlan_group_free(struct vlan_group *grp)
{
- int i;
+ int i, j;
- for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
- kfree(grp->vlan_devices_arrays[i]);
+ for (j = 0; j < VLAN_N_PROTOCOL; j++)
+ for (i = 0; i < VLAN_GROUP_ARRAY_SPLIT_PARTS; i++)
+ kfree(grp->vlan_devices_arrays[j][i]);
kfree(grp);
}
@@ -72,14 +94,16 @@ static struct vlan_group *vlan_group_alloc(struct net_device *real_dev)
return grp;
}
-static int vlan_group_prealloc_vid(struct vlan_group *vg, u16 vlan_id)
+static int vlan_group_prealloc_vid(struct vlan_group *vg,
+ u16 protocol, u16 vlan_id)
{
struct net_device **array;
unsigned int size;
ASSERT_RTNL();
- array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
+ array = vg->vlan_devices_arrays[vlan_pidx(protocol)]
+ [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
if (array != NULL)
return 0;
@@ -88,7 +112,8 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg, u16 vlan_id)
if (array == NULL)
return -ENOBUFS;
- vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN] = array;
+ vg->vlan_devices_arrays[vlan_pidx(protocol)]
+ [vlan_id / VLAN_GROUP_ARRAY_PART_LEN] = array;
return 0;
}
@@ -103,6 +128,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
struct net_device *real_dev = vlan->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
struct vlan_group *grp;
+ u16 protocol = vlan->protocol;
u16 vlan_id = vlan->vlan_id;
ASSERT_RTNL();
@@ -114,7 +140,8 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
* HW accelerating devices or SW vlan input packet processing if
* VLAN is not 0 (leave it there for 802.1p).
*/
- if (vlan_id && (real_dev->features & NETIF_F_HW_VLAN_FILTER))
+ if (vlan_id && protocol == ETH_P_8021Q &&
+ (real_dev->features & NETIF_F_HW_VLAN_FILTER))
ops->ndo_vlan_rx_kill_vid(real_dev, vlan_id);
grp->nr_vlans--;
@@ -122,7 +149,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
if (vlan->flags & VLAN_FLAG_GVRP)
vlan_gvrp_request_leave(dev);
- vlan_group_set_device(grp, vlan_id, NULL);
+ vlan_group_set_device_pidx(grp, vlan_pidx(protocol), vlan_id, NULL);
/* Because unregister_netdevice_queue() makes sure at least one rcu
* grace period is respected before device freeing,
* we dont need to call synchronize_net() here.
@@ -145,7 +172,8 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
dev_put(real_dev);
}
-int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id)
+int vlan_check_real_dev(struct net_device *real_dev,
+ u16 protocol, u16 vlan_id)
{
const char *name = real_dev->name;
const struct net_device_ops *ops = real_dev->netdev_ops;
@@ -161,7 +189,7 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id)
return -EOPNOTSUPP;
}
- if (vlan_find_dev(real_dev, vlan_id) != NULL)
+ if (vlan_find_dev(real_dev, vlan_pidx(protocol), vlan_id) != NULL)
return -EEXIST;
return 0;
@@ -173,6 +201,7 @@ int register_vlan_dev(struct net_device *dev)
struct net_device *real_dev = vlan->real_dev;
const struct net_device_ops *ops = real_dev->netdev_ops;
u16 vlan_id = vlan->vlan_id;
+ u16 protocol = vlan->protocol;
struct vlan_group *grp, *ngrp = NULL;
int err;
@@ -186,7 +215,7 @@ int register_vlan_dev(struct net_device *dev)
goto out_free_group;
}
- err = vlan_group_prealloc_vid(grp, vlan_id);
+ err = vlan_group_prealloc_vid(grp, protocol, vlan_id);
if (err < 0)
goto out_uninit_applicant;
@@ -203,7 +232,7 @@ int register_vlan_dev(struct net_device *dev)
/* So, got the sucker initialized, now lets place
* it into our local structure.
*/
- vlan_group_set_device(grp, vlan_id, dev);
+ vlan_group_set_device_pidx(grp, vlan_pidx(protocol), vlan_id, dev);
grp->nr_vlans++;
if (ngrp) {
@@ -211,7 +240,7 @@ int register_vlan_dev(struct net_device *dev)
ops->ndo_vlan_rx_register(real_dev, ngrp);
rcu_assign_pointer(real_dev->vlgrp, ngrp);
}
- if (real_dev->features & NETIF_F_HW_VLAN_FILTER)
+ if (protocol == ETH_P_8021Q && real_dev->features & NETIF_F_HW_VLAN_FILTER)
ops->ndo_vlan_rx_add_vid(real_dev, vlan_id);
return 0;
@@ -230,18 +259,26 @@ out_free_group:
/* Attach a VLAN device to a mac address (ie Ethernet Card).
* Returns 0 if the device was created or a negative error code otherwise.
*/
-static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
+static int register_vlan_device(struct net_device *real_dev,
+ u16 protocol, u16 vlan_id)
{
struct net_device *new_dev;
struct net *net = dev_net(real_dev);
struct vlan_net *vn = net_generic(net, vlan_net_id);
char name[IFNAMSIZ];
+ static const char *protonames[VLAN_N_PROTOCOL] = {
+ [VLAN_PROTOIDX_8021Q] = "",
+ [VLAN_PROTOIDX_8021AD] = "1ad",
+ [VLAN_PROTOIDX_QINQ1] = "91-",
+ [VLAN_PROTOIDX_QINQ2] = "92-",
+ [VLAN_PROTOIDX_QINQ3] = "93-"
+ };
int err;
if (vlan_id >= VLAN_VID_MASK)
return -ERANGE;
- err = vlan_check_real_dev(real_dev, vlan_id);
+ err = vlan_check_real_dev(real_dev, protocol, vlan_id);
if (err < 0)
return err;
@@ -249,26 +286,30 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
switch (vn->name_type) {
case VLAN_NAME_TYPE_RAW_PLUS_VID:
/* name will look like: eth1.0005 */
- snprintf(name, IFNAMSIZ, "%s.%.4i", real_dev->name, vlan_id);
+ snprintf(name, IFNAMSIZ, "%s.%s%.4i", real_dev->name,
+ protonames[vlan_pidx(protocol)], vlan_id);
break;
case VLAN_NAME_TYPE_PLUS_VID_NO_PAD:
/* Put our vlan.VID in the name.
* Name will look like: vlan5
*/
- snprintf(name, IFNAMSIZ, "vlan%i", vlan_id);
+ snprintf(name, IFNAMSIZ, "vlan%s%i",
+ protonames[vlan_pidx(protocol)], vlan_id);
break;
case VLAN_NAME_TYPE_RAW_PLUS_VID_NO_PAD:
/* Put our vlan.VID in the name.
* Name will look like: eth0.5
*/
- snprintf(name, IFNAMSIZ, "%s.%i", real_dev->name, vlan_id);
+ snprintf(name, IFNAMSIZ, "%s.%s%i", real_dev->name,
+ protonames[vlan_pidx(protocol)], vlan_id);
break;
case VLAN_NAME_TYPE_PLUS_VID:
/* Put our vlan.VID in the name.
* Name will look like: vlan0005
*/
default:
- snprintf(name, IFNAMSIZ, "vlan%.4i", vlan_id);
+ snprintf(name, IFNAMSIZ, "vlan%s%.4i",
+ protonames[vlan_pidx(protocol)], vlan_id);
}
new_dev = alloc_netdev(sizeof(struct vlan_dev_info), name, vlan_setup);
@@ -282,6 +323,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
*/
new_dev->mtu = real_dev->mtu;
+ vlan_dev_info(new_dev)->protocol = protocol;
vlan_dev_info(new_dev)->vlan_id = vlan_id;
vlan_dev_info(new_dev)->real_dev = real_dev;
vlan_dev_info(new_dev)->dent = NULL;
@@ -359,6 +401,12 @@ static void __vlan_device_event(struct net_device *dev, unsigned long event)
}
}
+#define vlangrp_for_each_dev(i, grp, vlandev) \
+ for (i = 0; i < VLAN_N_VID * VLAN_N_PROTOCOL; i++) \
+ if ((vlandev = vlan_group_get_device_pidx(grp, \
+ i / VLAN_N_VID, i % VLAN_N_VID)))
+ /* { code here } */
+
static int vlan_device_event(struct notifier_block *unused, unsigned long event,
void *ptr)
{
@@ -391,22 +439,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
switch (event) {
case NETDEV_CHANGE:
/* Propagate real device state to vlan devices */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
netif_stacked_transfer_operstate(dev, vlandev);
}
break;
case NETDEV_CHANGEADDR:
/* Adjust unicast filters on underlying device */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
flgs = vlandev->flags;
if (!(flgs & IFF_UP))
continue;
@@ -416,11 +456,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
break;
case NETDEV_CHANGEMTU:
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
if (vlandev->mtu <= dev->mtu)
continue;
@@ -430,11 +466,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_FEAT_CHANGE:
/* Propagate device features to underlying device */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
vlan_transfer_features(dev, vlandev);
}
@@ -442,11 +474,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_DOWN:
/* Put all VLANs for this dev in the down state too. */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
flgs = vlandev->flags;
if (!(flgs & IFF_UP))
continue;
@@ -460,11 +488,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_UP:
/* Put all VLANs for this dev in the up state too. */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
flgs = vlandev->flags;
if (flgs & IFF_UP)
continue;
@@ -481,17 +505,14 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
if (dev->reg_state != NETREG_UNREGISTERING)
break;
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
- /* unregistration of last vlan destroys group, abort
- * afterwards */
- if (grp->nr_vlans == 1)
- i = VLAN_N_VID;
+ vlangrp_for_each_dev(i, grp, vlandev) {
+ unsigned int nr = grp->nr_vlans;
unregister_vlan_dev(vlandev, &list);
+
+ /* if it was the last VLAN, grp is now gone */
+ if (nr == 1)
+ break;
}
unregister_netdevice_many(&list);
break;
@@ -503,11 +524,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
case NETDEV_NOTIFY_PEERS:
case NETDEV_BONDING_FAILOVER:
/* Propagate to vlan devices */
- for (i = 0; i < VLAN_N_VID; i++) {
- vlandev = vlan_group_get_device(grp, i);
- if (!vlandev)
- continue;
-
+ vlangrp_for_each_dev(i, grp, vlandev) {
call_netdevice_notifiers(event, vlandev);
}
break;
@@ -608,7 +625,7 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg)
err = -EPERM;
if (!capable(CAP_NET_ADMIN))
break;
- err = register_vlan_device(dev, args.u.VID);
+ err = register_vlan_device(dev, ETH_P_8021Q, args.u.VID);
break;
case DEL_VLAN_CMD:
@@ -668,6 +685,39 @@ static struct pernet_operations vlan_net_ops = {
.size = sizeof(struct vlan_net),
};
+static int vlan_rcv(struct sk_buff *skb, struct net_device *dev,
+ struct packet_type *pt, struct net_device *orig_dev)
+{
+ u16 protocol = be16_to_cpu(pt->type);
+
+ skb = vlan_untag(skb);
+ if (unlikely(!skb))
+ return 0;
+ if (vlan_do_receive(&skb, vlan_pidx(protocol), protocol))
+ return netif_receive_skb(skb);
+
+ if (likely(skb))
+ kfree_skb(skb);
+ return 0;
+}
+
+static struct packet_type vlan_1ad_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_8021AD),
+ .func = vlan_rcv,
+};
+static struct packet_type vlan_qq1_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_QINQ1),
+ .func = vlan_rcv,
+};
+static struct packet_type vlan_qq2_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_QINQ2),
+ .func = vlan_rcv,
+};
+static struct packet_type vlan_qq3_type __read_mostly = {
+ .type = cpu_to_be16(ETH_P_QINQ3),
+ .func = vlan_rcv,
+};
+
static int __init vlan_proto_init(void)
{
int err;
@@ -691,6 +741,11 @@ static int __init vlan_proto_init(void)
goto err4;
vlan_ioctl_set(vlan_ioctl_handler);
+
+ dev_add_pack(&vlan_1ad_type);
+ dev_add_pack(&vlan_qq1_type);
+ dev_add_pack(&vlan_qq2_type);
+ dev_add_pack(&vlan_qq3_type);
return 0;
err4:
@@ -705,6 +760,11 @@ err0:
static void __exit vlan_cleanup_module(void)
{
+ dev_remove_pack(&vlan_1ad_type);
+ dev_remove_pack(&vlan_qq1_type);
+ dev_remove_pack(&vlan_qq2_type);
+ dev_remove_pack(&vlan_qq3_type);
+
vlan_ioctl_set(NULL);
vlan_netlink_fini();
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index b132f54..2043b06 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -46,6 +46,7 @@ struct vlan_pcpu_stats {
* @ingress_priority_map: ingress priority mappings
* @nr_egress_mappings: number of egress priority mappings
* @egress_priority_map: hash of egress priority mappings
+ * @protocol: encapsulation protocol value (8100, 88a8, 9x00)
* @vlan_id: VLAN identifier
* @flags: device flags
* @real_dev: underlying netdevice
@@ -59,6 +60,7 @@ struct vlan_dev_info {
unsigned int nr_egress_mappings;
struct vlan_priority_tci_mapping *egress_priority_map[16];
+ u16 protocol;
u16 vlan_id;
u16 flags;
@@ -76,12 +78,12 @@ static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev)
/* Must be invoked with rcu_read_lock or with RTNL. */
static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
- u16 vlan_id)
+ int pidx, u16 vlan_id)
{
struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp);
if (grp)
- return vlan_group_get_device(grp, vlan_id);
+ return vlan_group_get_device_pidx(grp, pidx, vlan_id);
return NULL;
}
@@ -94,7 +96,8 @@ int vlan_dev_set_egress_priority(const struct net_device *dev,
int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask);
void vlan_dev_get_realdev_name(const struct net_device *dev, char *result);
-int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id);
+int vlan_check_real_dev(struct net_device *real_dev,
+ u16 protocol, u16 vlan_id);
void vlan_setup(struct net_device *dev);
int register_vlan_dev(struct net_device *dev);
void unregister_vlan_dev(struct net_device *dev, struct list_head *head);
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index fcc6846..921e240 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -4,14 +4,14 @@
#include <linux/netpoll.h>
#include "vlan.h"
-bool vlan_do_receive(struct sk_buff **skbp)
+bool vlan_do_receive(struct sk_buff **skbp, int pidx, u16 protocol)
{
struct sk_buff *skb = *skbp;
u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
struct net_device *vlan_dev;
struct vlan_pcpu_stats *rx_stats;
- vlan_dev = vlan_find_dev(skb->dev, vlan_id);
+ vlan_dev = vlan_find_dev(skb->dev, pidx, vlan_id);
if (!vlan_dev) {
if (vlan_id)
skb->pkt_type = PACKET_OTHERHOST;
@@ -41,7 +41,7 @@ bool vlan_do_receive(struct sk_buff **skbp)
* original position later
*/
skb_push(skb, offset);
- skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci);
+ skb = *skbp = vlan_insert_tag(skb, protocol, skb->vlan_tci);
if (!skb)
return false;
skb_pull(skb, offset + VLAN_HLEN);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 49bb752..67c6a66 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -119,8 +119,8 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev,
else
vhdr->h_vlan_encapsulated_proto = htons(len);
- skb->protocol = htons(ETH_P_8021Q);
- type = ETH_P_8021Q;
+ type = vlan_dev_info(dev)->protocol;
+ skb->protocol = htons(type);
vhdrlen = VLAN_HLEN;
}
@@ -140,6 +140,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct vlan_ethhdr *veth = (struct vlan_ethhdr *)(skb->data);
+ u16 protocol = vlan_dev_info(dev)->protocol;
unsigned int len;
int ret;
@@ -148,12 +149,15 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
* NOTE: THIS ASSUMES DIX ETHERNET, SPECIFICALLY NOT SUPPORTING
* OTHER THINGS LIKE FDDI/TokenRing/802.3 SNAPs...
*/
- if (veth->h_vlan_proto != htons(ETH_P_8021Q) ||
+ if (veth->h_vlan_proto != htons(protocol) ||
vlan_dev_info(dev)->flags & VLAN_FLAG_REORDER_HDR) {
u16 vlan_tci;
vlan_tci = vlan_dev_info(dev)->vlan_id;
vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb);
- skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
+ if (protocol == ETH_P_8021Q)
+ skb = __vlan_hwaccel_put_tag(skb, vlan_tci);
+ else
+ skb = vlan_insert_tag(skb, protocol, vlan_tci);
}
skb_set_dev(skb, vlan_dev_info(dev)->real_dev);
@@ -547,7 +551,8 @@ static int vlan_dev_init(struct net_device *dev)
#endif
dev->needed_headroom = real_dev->needed_headroom;
- if (real_dev->features & NETIF_F_HW_VLAN_TX) {
+ if (vlan_dev_info(dev)->protocol == ETH_P_8021Q
+ && real_dev->features & NETIF_F_HW_VLAN_TX) {
dev->header_ops = real_dev->header_ops;
dev->hard_header_len = real_dev->hard_header_len;
} else {
diff --git a/net/8021q/vlan_gvrp.c b/net/8021q/vlan_gvrp.c
index 061cece..83c6728 100644
--- a/net/8021q/vlan_gvrp.c
+++ b/net/8021q/vlan_gvrp.c
@@ -32,6 +32,9 @@ int vlan_gvrp_request_join(const struct net_device *dev)
const struct vlan_dev_info *vlan = vlan_dev_info(dev);
__be16 vlan_id = htons(vlan->vlan_id);
+ if (vlan->protocol != ETH_P_8021Q)
+ return 0;
+
return garp_request_join(vlan->real_dev, &vlan_gvrp_app,
&vlan_id, sizeof(vlan_id), GVRP_ATTR_VID);
}
@@ -41,6 +44,9 @@ void vlan_gvrp_request_leave(const struct net_device *dev)
const struct vlan_dev_info *vlan = vlan_dev_info(dev);
__be16 vlan_id = htons(vlan->vlan_id);
+ if (vlan->protocol != ETH_P_8021Q)
+ return;
+
garp_request_leave(vlan->real_dev, &vlan_gvrp_app,
&vlan_id, sizeof(vlan_id), GVRP_ATTR_VID);
}
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index be9a5c1..418dc55 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -19,6 +19,7 @@
static const struct nla_policy vlan_policy[IFLA_VLAN_MAX + 1] = {
[IFLA_VLAN_ID] = { .type = NLA_U16 },
+ [IFLA_VLAN_PROTOCOL] = { .type = NLA_U16 },
[IFLA_VLAN_FLAGS] = { .len = sizeof(struct ifla_vlan_flags) },
[IFLA_VLAN_EGRESS_QOS] = { .type = NLA_NESTED },
[IFLA_VLAN_INGRESS_QOS] = { .type = NLA_NESTED },
@@ -57,6 +58,19 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[])
if (id >= VLAN_VID_MASK)
return -ERANGE;
}
+ if (data[IFLA_VLAN_PROTOCOL]) {
+ id = nla_get_u16(data[IFLA_VLAN_PROTOCOL]);
+ switch (id) {
+ case ETH_P_8021Q:
+ case ETH_P_8021AD:
+ case ETH_P_QINQ1:
+ case ETH_P_QINQ2:
+ case ETH_P_QINQ3:
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
if (data[IFLA_VLAN_FLAGS]) {
flags = nla_data(data[IFLA_VLAN_FLAGS]);
if ((flags->flags & flags->mask) &
@@ -118,10 +132,12 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev,
return -ENODEV;
vlan->vlan_id = nla_get_u16(data[IFLA_VLAN_ID]);
+ vlan->protocol = data[IFLA_VLAN_PROTOCOL]
+ ? nla_get_u16(data[IFLA_VLAN_PROTOCOL]) : ETH_P_8021Q;
vlan->real_dev = real_dev;
vlan->flags = VLAN_FLAG_REORDER_HDR;
- err = vlan_check_real_dev(real_dev, vlan->vlan_id);
+ err = vlan_check_real_dev(real_dev, vlan->protocol, vlan->vlan_id);
if (err < 0)
return err;
@@ -150,7 +166,7 @@ static size_t vlan_get_size(const struct net_device *dev)
{
struct vlan_dev_info *vlan = vlan_dev_info(dev);
- return nla_total_size(2) + /* IFLA_VLAN_ID */
+ return nla_total_size(4) + /* IFLA_VLAN_ID + _PROTOCOL */
sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
vlan_qos_map_size(vlan->nr_ingress_mappings) +
vlan_qos_map_size(vlan->nr_egress_mappings);
@@ -166,6 +182,7 @@ static int vlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
unsigned int i;
NLA_PUT_U16(skb, IFLA_VLAN_ID, vlan_dev_info(dev)->vlan_id);
+ NLA_PUT_U16(skb, IFLA_VLAN_PROTOCOL, vlan_dev_info(dev)->protocol);
if (vlan->flags) {
f.flags = vlan->flags;
f.mask = ~0;
diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c
index d34b6da..7e6464c 100644
--- a/net/8021q/vlanproc.c
+++ b/net/8021q/vlanproc.c
@@ -270,8 +270,11 @@ static int vlan_seq_show(struct seq_file *seq, void *v)
const struct net_device *vlandev = v;
const struct vlan_dev_info *dev_info = vlan_dev_info(vlandev);
- seq_printf(seq, "%-15s| %d | %s\n", vlandev->name,
- dev_info->vlan_id, dev_info->real_dev->name);
+ seq_printf(seq, "%-15s| ", vlandev->name);
+ if (dev_info->protocol != ETH_P_8021Q)
+ seq_printf(seq, "%04x:", dev_info->protocol);
+ seq_printf(seq, "%d | %s\n", dev_info->vlan_id,
+ dev_info->real_dev->name);
}
return 0;
}
@@ -301,6 +304,8 @@ static int vlandev_seq_show(struct seq_file *seq, void *offset)
seq_printf(seq, fmt64, "total frames transmitted", stats->tx_packets);
seq_printf(seq, fmt64, "total bytes transmitted", stats->tx_bytes);
seq_printf(seq, "Device: %s", dev_info->real_dev->name);
+ if (dev_info->protocol != ETH_P_8021Q)
+ seq_printf(seq, ", protocol 0x%04x", dev_info->protocol);
/* now show all PRIORITY mappings relating to this VLAN */
seq_printf(seq, "\nINGRESS priority mappings: "
"0:%u 1:%u 2:%u 3:%u 4:%u 5:%u 6:%u 7:%u\n",
diff --git a/net/core/dev.c b/net/core/dev.c
index 9444c5c..ece5fd3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3187,7 +3187,7 @@ ncls:
ret = deliver_skb(skb, pt_prev, orig_dev);
pt_prev = NULL;
}
- if (vlan_do_receive(&skb)) {
+ if (vlan_do_receive(&skb, VLAN_PROTOIDX_8021Q, ETH_P_8021Q)) {
ret = __netif_receive_skb(skb);
goto out;
} else if (unlikely(!skb))
--
1.7.5.3
^ permalink raw reply related
* Re: [PATCH 0/3] ath6kl: neatening
From: Kalle Valo @ 2011-07-17 20:45 UTC (permalink / raw)
To: Joe Perches; +Cc: devel, gregkh, error27, linux-kernel, linux-wireless, netdev
In-Reply-To: <1310932335.2286.8.camel@Joe-Laptop>
On 07/17/2011 10:52 PM, Joe Perches wrote:
> On Sun, 2011-07-17 at 21:56 +0300, Kalle Valo wrote:
>> On 07/17/2011 09:43 PM, Joe Perches wrote:
>>> Joe Perches (3):
>>> ath6kl: Add missing newlines and coalesce messages
>>> ath6kl: Remove __func__ uses from ath6kl_err
>>> ath6kl: cfg80211: Add and use ath6kl_cfg80211_ready helper
>> Nice, thanks a lot. I'm planning to send v3 of athk6kl patches later
>> today. Is it okay for you if I amend your three patches to that patchset?
>
> 'course.
Great, thanks. I have now applied your patches to ath6kl-cleanup tree
and they will be included in patchset v3.
Kalle
^ permalink raw reply
* Re: [PATCHv9] vhost: experimental tx zero-copy support
From: Jesper Juhl @ 2011-07-17 20:01 UTC (permalink / raw)
To: Michael S. Tsirkin; +Cc: kvm, virtualization, netdev, linux-kernel
In-Reply-To: <20110717193540.GA29392@redhat.com>
On Sun, 17 Jul 2011, Michael S. Tsirkin wrote:
> From: Shirley Ma <mashirle@us.ibm.com>
>
> This adds experimental zero copy support in vhost-net,
> disabled by default. To enable, set the zerocopytx
> module option to 1.
>
> This patch maintains the outstanding userspace buffers in the
> sequence it is delivered to vhost. The outstanding userspace buffers
> will be marked as done once the lower device buffers DMA has finished.
> This is monitored through last reference of kfree_skb callback. Two
> buffer indices are used for this purpose.
>
> The vhost-net device passes the userspace buffers info to lower device
> skb through message control. DMA done status check and guest
> notification are handled by handle_tx: in the worst case is all buffers
> in the vq are in pending/done status, so we need to notify guest to
> release DMA done buffers first before we get any new buffers from the
> vq.
>
> One known problem is that if the guest stops submitting
> buffers, buffers might never get used until some
> further action, e.g. device reset. This does not
> seem to affect linux guests.
>
> Signed-off-by: Shirley <xma@us.ibm.com>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> ---
>
> The below is what I came up with. We add the feature enabled
> by default for now as there are known issues,
You mean "disabled" - right?
> but some
> guests can benefit so there's value in putting this
> in tree, to help the code get wider testing.
>
> drivers/vhost/net.c | 73 +++++++++++++++++++++++++++++++++++++++++-
> drivers/vhost/vhost.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++
> drivers/vhost/vhost.h | 29 +++++++++++++++++
> 3 files changed, 186 insertions(+), 1 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index e224a92..226ca6b 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -12,6 +12,7 @@
> #include <linux/virtio_net.h>
> #include <linux/miscdevice.h>
> #include <linux/module.h>
> +#include <linux/moduleparam.h>
> #include <linux/mutex.h>
> #include <linux/workqueue.h>
> #include <linux/rcupdate.h>
> @@ -28,10 +29,18 @@
>
> #include "vhost.h"
>
> +static int zcopytx;
> +module_param(zcopytx, int, 0444);
Should everyone be able to read this? How about "0440" just to be
paranoid? or?
> +MODULE_PARM_DESC(lnksts, "Enable Zero Copy Transmit");
> +
> /* Max number of bytes transferred before requeueing the job.
> * Using this limit prevents one virtqueue from starving others. */
> #define VHOST_NET_WEIGHT 0x80000
>
> +/* MAX number of TX used buffers for outstanding zerocopy */
> +#define VHOST_MAX_PEND 128
> +#define VHOST_GOODCOPY_LEN 256
> +
> enum {
> VHOST_NET_VQ_RX = 0,
> VHOST_NET_VQ_TX = 1,
> @@ -54,6 +63,11 @@ struct vhost_net {
> enum vhost_net_poll_state tx_poll_state;
> };
>
> +static bool vhost_sock_zcopy(struct socket *sock)
> +{
> + return unlikely(zcopytx) && sock_flag(sock->sk, SOCK_ZEROCOPY);
> +}
> +
> /* Pop first len bytes from iovec. Return number of segments used. */
> static int move_iovec_hdr(struct iovec *from, struct iovec *to,
> size_t len, int iov_count)
> @@ -129,6 +143,8 @@ static void handle_tx(struct vhost_net *net)
> int err, wmem;
> size_t hdr_size;
> struct socket *sock;
> + struct vhost_ubuf_ref *uninitialized_var(ubufs);
> + bool zcopy;
>
> /* TODO: check that we are running from vhost_worker? */
> sock = rcu_dereference_check(vq->private_data, 1);
> @@ -149,8 +165,13 @@ static void handle_tx(struct vhost_net *net)
> if (wmem < sock->sk->sk_sndbuf / 2)
> tx_poll_stop(net);
> hdr_size = vq->vhost_hlen;
> + zcopy = vhost_sock_zcopy(sock);
>
> for (;;) {
> + /* Release DMAs done buffers first */
> + if (zcopy)
> + vhost_zerocopy_signal_used(vq);
> +
> head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
> ARRAY_SIZE(vq->iov),
> &out, &in,
> @@ -166,6 +187,12 @@ static void handle_tx(struct vhost_net *net)
> set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
> break;
> }
> + /* If more outstanding DMAs, queue the work */
> + if (vq->upend_idx - vq->done_idx > VHOST_MAX_PEND) {
> + tx_poll_start(net, sock);
> + set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
> + break;
> + }
> if (unlikely(vhost_enable_notify(&net->dev, vq))) {
> vhost_disable_notify(&net->dev, vq);
> continue;
> @@ -188,9 +215,39 @@ static void handle_tx(struct vhost_net *net)
> iov_length(vq->hdr, s), hdr_size);
> break;
> }
> + /* use msg_control to pass vhost zerocopy ubuf info to skb */
> + if (zcopy) {
> + vq->heads[vq->upend_idx].id = head;
> + if (len < VHOST_GOODCOPY_LEN) {
> + /* copy don't need to wait for DMA done */
> + vq->heads[vq->upend_idx].len =
> + VHOST_DMA_DONE_LEN;
> + msg.msg_control = NULL;
> + msg.msg_controllen = 0;
> + ubufs = NULL;
> + } else {
> + struct ubuf_info *ubuf = &vq->ubuf_info[head];
> +
> + vq->heads[vq->upend_idx].len = len;
> + ubuf->callback = vhost_zerocopy_callback;
> + ubuf->arg = vq->ubufs;
> + ubuf->desc = vq->upend_idx;
> + msg.msg_control = ubuf;
> + msg.msg_controllen = sizeof(ubuf);
> + ubufs = vq->ubufs;
> + kref_get(&ubufs->kref);
> + }
> + vq->upend_idx = (vq->upend_idx + 1) % UIO_MAXIOV;
> + }
> /* TODO: Check specific error and bomb out unless ENOBUFS? */
> err = sock->ops->sendmsg(NULL, sock, &msg, len);
> if (unlikely(err < 0)) {
> + if (zcopy) {
> + if (ubufs)
> + vhost_ubuf_put(ubufs);
> + vq->upend_idx = ((unsigned)vq->upend_idx - 1) %
> + UIO_MAXIOV;
> + }
> vhost_discard_vq_desc(vq, 1);
> tx_poll_start(net, sock);
> break;
> @@ -198,7 +255,8 @@ static void handle_tx(struct vhost_net *net)
> if (err != len)
> pr_debug("Truncated TX packet: "
> " len %d != %zd\n", err, len);
> - vhost_add_used_and_signal(&net->dev, vq, head, 0);
> + if (!zcopy)
> + vhost_add_used_and_signal(&net->dev, vq, head, 0);
> total_len += len;
> if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
> vhost_poll_queue(&vq->poll);
> @@ -603,6 +661,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
> {
> struct socket *sock, *oldsock;
> struct vhost_virtqueue *vq;
> + struct vhost_ubuf_ref *ubufs, *oldubufs = NULL;
> int r;
>
> mutex_lock(&n->dev.mutex);
> @@ -632,6 +691,13 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
> oldsock = rcu_dereference_protected(vq->private_data,
> lockdep_is_held(&vq->mutex));
> if (sock != oldsock) {
> + ubufs = vhost_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock));
> + if (IS_ERR(ubufs)) {
> + r = PTR_ERR(ubufs);
> + goto err_ubufs;
> + }
> + oldubufs = vq->ubufs;
> + vq->ubufs = ubufs;
> vhost_net_disable_vq(n, vq);
> rcu_assign_pointer(vq->private_data, sock);
> vhost_net_enable_vq(n, vq);
> @@ -639,6 +705,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
>
> mutex_unlock(&vq->mutex);
>
> + if (oldubufs)
> + vhost_ubuf_put_and_wait(oldubufs);
> +
> if (oldsock) {
> vhost_net_flush_vq(n, index);
> fput(oldsock->file);
> @@ -647,6 +716,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
> mutex_unlock(&n->dev.mutex);
> return 0;
>
> +err_ubufs:
> + fput(sock->file);
> err_vq:
> mutex_unlock(&vq->mutex);
> err:
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index ea966b3..2ebf6fc 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -179,6 +179,9 @@ static void vhost_vq_reset(struct vhost_dev *dev,
> vq->call_ctx = NULL;
> vq->call = NULL;
> vq->log_ctx = NULL;
> + vq->upend_idx = 0;
> + vq->done_idx = 0;
> + vq->ubufs = NULL;
> }
>
> static int vhost_worker(void *data)
> @@ -237,6 +240,8 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
> GFP_KERNEL);
> dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
> UIO_MAXIOV, GFP_KERNEL);
> + dev->vqs[i].ubuf_info = kmalloc(sizeof *dev->vqs[i].ubuf_info *
> + UIO_MAXIOV, GFP_KERNEL);
>
> if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
> !dev->vqs[i].heads)
> @@ -249,6 +254,7 @@ err_nomem:
> kfree(dev->vqs[i].indirect);
> kfree(dev->vqs[i].log);
> kfree(dev->vqs[i].heads);
> + kfree(dev->vqs[i].ubuf_info);
> }
> return -ENOMEM;
> }
> @@ -390,6 +396,29 @@ long vhost_dev_reset_owner(struct vhost_dev *dev)
> return 0;
> }
>
> +/* In case of DMA done not in order in lower device driver for some reason.
> + * upend_idx is used to track end of used idx, done_idx is used to track head
> + * of used idx. Once lower device DMA done contiguously, we will signal KVM
> + * guest used idx.
> + */
> +int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq)
> +{
> + int i, j = 0;
On two lines?
int i;
int j = 0;
as per CodingStyle..
> +
> + for (i = vq->done_idx; i != vq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
> + if ((vq->heads[i].len == VHOST_DMA_DONE_LEN)) {
> + vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
> + vhost_add_used_and_signal(vq->dev, vq,
> + vq->heads[i].id, 0);
> + ++j;
> + } else
> + break;
> + }
> + if (j)
> + vq->done_idx = i;
> + return j;
> +}
> +
> /* Caller should have device mutex */
> void vhost_dev_cleanup(struct vhost_dev *dev)
> {
> @@ -400,6 +429,13 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
> vhost_poll_stop(&dev->vqs[i].poll);
> vhost_poll_flush(&dev->vqs[i].poll);
> }
> + /* Wait for all lower device DMAs done. */
> + if (dev->vqs[i].ubufs)
> + vhost_ubuf_put_and_wait(dev->vqs[i].ubufs);
> +
> + /* Signal guest as appropriate. */
> + vhost_zerocopy_signal_used(&dev->vqs[i]);
> +
> if (dev->vqs[i].error_ctx)
> eventfd_ctx_put(dev->vqs[i].error_ctx);
> if (dev->vqs[i].error)
> @@ -1486,3 +1522,52 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
> &vq->used->flags, r);
> }
> }
> +
> +static void vhost_zerocopy_done_signal(struct kref *kref)
> +{
> + struct vhost_ubuf_ref *ubufs = container_of(kref, struct vhost_ubuf_ref,
> + kref);
> + wake_up(&ubufs->wait);
> +}
> +
> +struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *vq,
> + bool zcopy)
> +{
> + struct vhost_ubuf_ref *ubufs;
> + /* No zero copy backend? Nothing to count. */
> + if (!zcopy)
> + return NULL;
> + ubufs = kmalloc(sizeof *ubufs, GFP_KERNEL);
> + if (!ubufs)
> + return ERR_PTR(-ENOMEM);
> + kref_init(&ubufs->kref);
> + kref_get(&ubufs->kref);
> + init_waitqueue_head(&ubufs->wait);
> + ubufs->vq = vq;
> + return ubufs;
> +}
> +
> +void vhost_ubuf_put(struct vhost_ubuf_ref *ubufs)
> +{
> + kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
> +}
> +
> +void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
> +{
> + kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
> + wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
> + kfree(ubufs);
> +}
> +
> +void vhost_zerocopy_callback(void *arg)
> +{
> + struct ubuf_info *ubuf = (struct ubuf_info *)arg;
No need to explicitly cast a void*, just do:
struct ubuf_info *ubuf = arg;
> + struct vhost_ubuf_ref *ubufs;
> + struct vhost_virtqueue *vq;
> +
> + ubufs = ubuf->arg;
> + vq = ubufs->vq;
Why not shorten this a bit as:
struct vhost_ubuf_ref *ubufs = ubuf->arg;
struct vhost_virtqueue *vq = ubufs->vq;
?
> + /* set len = 1 to mark this desc buffers done DMA */
> + vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
> + kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
> +}
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 8e03379..e287145 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -13,6 +13,11 @@
> #include <linux/virtio_ring.h>
> #include <asm/atomic.h>
>
> +/* This is for zerocopy, used buffer len is set to 1 when lower device DMA
> + * done */
> +#define VHOST_DMA_DONE_LEN 1
> +#define VHOST_DMA_CLEAR_LEN 0
> +
> struct vhost_device;
>
> struct vhost_work;
> @@ -50,6 +55,18 @@ struct vhost_log {
> u64 len;
> };
>
> +struct vhost_virtqueue;
> +
> +struct vhost_ubuf_ref {
> + struct kref kref;
> + wait_queue_t wait;
> + struct vhost_virtqueue *vq;
> +};
> +
> +struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *, bool zcopy);
> +void vhost_ubuf_put(struct vhost_ubuf_ref *);
> +void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *);
> +
> /* The virtqueue structure describes a queue attached to a device. */
> struct vhost_virtqueue {
> struct vhost_dev *dev;
> @@ -114,6 +131,16 @@ struct vhost_virtqueue {
> /* Log write descriptors */
> void __user *log_base;
> struct vhost_log *log;
> + /* vhost zerocopy support fields below: */
> + /* last used idx for outstanding DMA zerocopy buffers */
> + int upend_idx;
> + /* first used idx for DMA done zerocopy buffers */
> + int done_idx;
> + /* an array of userspace buffers info */
> + struct ubuf_info *ubuf_info;
> + /* Reference counting for outstanding ubufs.
> + * Protected by vq mutex. Writers must also take device mutex. */
> + struct vhost_ubuf_ref *ubufs;
> };
>
> struct vhost_dev {
> @@ -160,6 +187,8 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
>
> int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
> unsigned int log_num, u64 len);
> +void vhost_zerocopy_callback(void *arg);
> +int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq);
>
> #define vq_err(vq, fmt, ...) do { \
> pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
>
--
Jesper Juhl <jj@chaosbits.net> http://www.chaosbits.net/
Don't top-post http://www.catb.org/jargon/html/T/top-post.html
Plain text mails only, please.
^ permalink raw reply
* Re: [PATCHv9] vhost: experimental tx zero-copy support
From: David Miller @ 2011-07-17 19:53 UTC (permalink / raw)
To: mst; +Cc: kvm, virtualization, netdev, linux-kernel
In-Reply-To: <20110717193540.GA29392@redhat.com>
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 17 Jul 2011 22:36:14 +0300
> The below is what I came up with. We add the feature enabled
> by default ...
s/enabled/disabled/ Well, at least you got it right in the
commit message where it counts :-)
^ permalink raw reply
* Re: [PATCH 0/3] ath6kl: neatening
From: Joe Perches @ 2011-07-17 19:52 UTC (permalink / raw)
To: Kalle Valo; +Cc: devel, gregkh, error27, linux-kernel, linux-wireless, netdev
In-Reply-To: <4E23307B.4060504@qca.qualcomm.com>
On Sun, 2011-07-17 at 21:56 +0300, Kalle Valo wrote:
> On 07/17/2011 09:43 PM, Joe Perches wrote:
> > Joe Perches (3):
> > ath6kl: Add missing newlines and coalesce messages
> > ath6kl: Remove __func__ uses from ath6kl_err
> > ath6kl: cfg80211: Add and use ath6kl_cfg80211_ready helper
> Nice, thanks a lot. I'm planning to send v3 of athk6kl patches later
> today. Is it okay for you if I amend your three patches to that patchset?
'course.
^ permalink raw reply
* Re: [patch net-next-2.6] vlan: introduce ndo_vlan_[enable/disable]
From: Jiri Pirko @ 2011-07-17 19:44 UTC (permalink / raw)
To: Michał Mirosław
Cc: netdev, davem, shemminger, eric.dumazet, greearb
In-Reply-To: <CAHXqBFL1s30DxxHk-1wEy1q48LvgbO+w4zXkOm0sAU61XONoVw@mail.gmail.com>
Sun, Jul 17, 2011 at 10:36:04AM CEST, mirqus@gmail.com wrote:
>W dniu 17 lipca 2011 09:30 użytkownik Jiri Pirko <jpirko@redhat.com> napisał:
>> Sat, Jul 16, 2011 at 04:14:36PM CEST, mirqus@gmail.com wrote:
>>>2011/7/16 Jiri Pirko <jpirko@redhat.com>:
>>>> Some devices are not able to enable/disable rx/tw vlan accel separately.
>>>> they depend on ndo_vlan_rx_register to know if to enable of disable
>>>> hw accel. And since ndo_vlan_rx_register is going to die soon,
>>>> this must be resolved.
>>>>
>>>> One solution might be to enable accel on device start every time, even
>>>> if there are no vlan up on. But this would change behaviour and might
>>>> lead to possible regression (on older devices).
>>>[...]
>>>
>>>Please describe the possible regression. As I see it, there won't be
>>>any user visible change of behaviour - network code takes care of
>>>reinserting VLAN tag when necessary. If you think that disabling tag
>>>stripping is beneficial for cases where no VLANs are configured, it's
>>>better to do that in netdev_fix_features() for devices which advertise
>>>NETIF_F_HW_VLAN_RX in hw_features.
>>
>> Well I just wanted to preserve current behaviour which is that in many
>> drivers vlan accel is enabled only if some vid is registered upon the
>> device and it's disabled again when no vid is registered. I can see
>> no way to do this with current code after removing ndo_vlan_rx_register.
>>
>> I expect unexpected
>
>:-D
>
>> ... problems on old cards when vlan accel would be
>> enabled all the time, but maybe I'm wrong...
>
>Device has no way of knowing how the system uses VLAN tags, stripped
>or not. Any problems would be driver problems and since you're making
>it all use generic code, bugs will hit all drivers simultaneously or
>(preferably) won't happen at all.
>
>> One idea is for device which do not support sepatate rx/tx vlan accel
>> enabling/disabling they can probably use ndo_fix_features force to
>> enable/disable rx/tx pair together. That would resolve the situation as
>> well giving user possibility to turn off vlan accel in case of any issues.
>
>That is exactly the idea behind ndo_fix_features.
In netdev_fix_features add check if either one of NETIF_F_HW_VLAN_TX or
NETIF_F_HW_VLAN_RX is set and in that case set the other one. Of course
this would be done only for devices what do not support separate rx/tx
vlan on/off. But how to distinguish? NETIF_F_HW_VLAN_BOTH feature flag?
Thanks.
Jirka
>
>Best Regards,
>Michał Mirosław
^ permalink raw reply
* Re: [PATCH] net: vlan, qlcnic: make vlan_find_dev private
From: David Miller @ 2011-07-17 19:33 UTC (permalink / raw)
To: equinox; +Cc: netdev, kaber, amit.salecha, anirban.chakraborty, linux-driver
In-Reply-To: <1310928792-3436326-1-git-send-email-equinox@diac24.net>
From: David Lamparter <equinox@diac24.net>
Date: Sun, 17 Jul 2011 20:53:12 +0200
> there is only one user of vlan_find_dev outside of the actual vlan code:
> qlcnic uses it to iterate over some VLANs it knows.
>
> let's just make vlan_find_dev private to the VLAN code and have the
> iteration in qlcnic be a bit more direct. (a few rcu dereferences less
> too)
>
> Signed-off-by: David Lamparter <equinox@diac24.net>
Applied.
^ permalink raw reply
* [PATCHv9] vhost: experimental tx zero-copy support
From: Michael S. Tsirkin @ 2011-07-17 19:36 UTC (permalink / raw)
To: kvm, virtualization, netdev, linux-kernel
From: Shirley Ma <mashirle@us.ibm.com>
This adds experimental zero copy support in vhost-net,
disabled by default. To enable, set the zerocopytx
module option to 1.
This patch maintains the outstanding userspace buffers in the
sequence it is delivered to vhost. The outstanding userspace buffers
will be marked as done once the lower device buffers DMA has finished.
This is monitored through last reference of kfree_skb callback. Two
buffer indices are used for this purpose.
The vhost-net device passes the userspace buffers info to lower device
skb through message control. DMA done status check and guest
notification are handled by handle_tx: in the worst case is all buffers
in the vq are in pending/done status, so we need to notify guest to
release DMA done buffers first before we get any new buffers from the
vq.
One known problem is that if the guest stops submitting
buffers, buffers might never get used until some
further action, e.g. device reset. This does not
seem to affect linux guests.
Signed-off-by: Shirley <xma@us.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
The below is what I came up with. We add the feature enabled
by default for now as there are known issues, but some
guests can benefit so there's value in putting this
in tree, to help the code get wider testing.
drivers/vhost/net.c | 73 +++++++++++++++++++++++++++++++++++++++++-
drivers/vhost/vhost.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++++
drivers/vhost/vhost.h | 29 +++++++++++++++++
3 files changed, 186 insertions(+), 1 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index e224a92..226ca6b 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -12,6 +12,7 @@
#include <linux/virtio_net.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
+#include <linux/moduleparam.h>
#include <linux/mutex.h>
#include <linux/workqueue.h>
#include <linux/rcupdate.h>
@@ -28,10 +29,18 @@
#include "vhost.h"
+static int zcopytx;
+module_param(zcopytx, int, 0444);
+MODULE_PARM_DESC(lnksts, "Enable Zero Copy Transmit");
+
/* Max number of bytes transferred before requeueing the job.
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000
+/* MAX number of TX used buffers for outstanding zerocopy */
+#define VHOST_MAX_PEND 128
+#define VHOST_GOODCOPY_LEN 256
+
enum {
VHOST_NET_VQ_RX = 0,
VHOST_NET_VQ_TX = 1,
@@ -54,6 +63,11 @@ struct vhost_net {
enum vhost_net_poll_state tx_poll_state;
};
+static bool vhost_sock_zcopy(struct socket *sock)
+{
+ return unlikely(zcopytx) && sock_flag(sock->sk, SOCK_ZEROCOPY);
+}
+
/* Pop first len bytes from iovec. Return number of segments used. */
static int move_iovec_hdr(struct iovec *from, struct iovec *to,
size_t len, int iov_count)
@@ -129,6 +143,8 @@ static void handle_tx(struct vhost_net *net)
int err, wmem;
size_t hdr_size;
struct socket *sock;
+ struct vhost_ubuf_ref *uninitialized_var(ubufs);
+ bool zcopy;
/* TODO: check that we are running from vhost_worker? */
sock = rcu_dereference_check(vq->private_data, 1);
@@ -149,8 +165,13 @@ static void handle_tx(struct vhost_net *net)
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
+ zcopy = vhost_sock_zcopy(sock);
for (;;) {
+ /* Release DMAs done buffers first */
+ if (zcopy)
+ vhost_zerocopy_signal_used(vq);
+
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
ARRAY_SIZE(vq->iov),
&out, &in,
@@ -166,6 +187,12 @@ static void handle_tx(struct vhost_net *net)
set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
break;
}
+ /* If more outstanding DMAs, queue the work */
+ if (vq->upend_idx - vq->done_idx > VHOST_MAX_PEND) {
+ tx_poll_start(net, sock);
+ set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+ break;
+ }
if (unlikely(vhost_enable_notify(&net->dev, vq))) {
vhost_disable_notify(&net->dev, vq);
continue;
@@ -188,9 +215,39 @@ static void handle_tx(struct vhost_net *net)
iov_length(vq->hdr, s), hdr_size);
break;
}
+ /* use msg_control to pass vhost zerocopy ubuf info to skb */
+ if (zcopy) {
+ vq->heads[vq->upend_idx].id = head;
+ if (len < VHOST_GOODCOPY_LEN) {
+ /* copy don't need to wait for DMA done */
+ vq->heads[vq->upend_idx].len =
+ VHOST_DMA_DONE_LEN;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ ubufs = NULL;
+ } else {
+ struct ubuf_info *ubuf = &vq->ubuf_info[head];
+
+ vq->heads[vq->upend_idx].len = len;
+ ubuf->callback = vhost_zerocopy_callback;
+ ubuf->arg = vq->ubufs;
+ ubuf->desc = vq->upend_idx;
+ msg.msg_control = ubuf;
+ msg.msg_controllen = sizeof(ubuf);
+ ubufs = vq->ubufs;
+ kref_get(&ubufs->kref);
+ }
+ vq->upend_idx = (vq->upend_idx + 1) % UIO_MAXIOV;
+ }
/* TODO: Check specific error and bomb out unless ENOBUFS? */
err = sock->ops->sendmsg(NULL, sock, &msg, len);
if (unlikely(err < 0)) {
+ if (zcopy) {
+ if (ubufs)
+ vhost_ubuf_put(ubufs);
+ vq->upend_idx = ((unsigned)vq->upend_idx - 1) %
+ UIO_MAXIOV;
+ }
vhost_discard_vq_desc(vq, 1);
tx_poll_start(net, sock);
break;
@@ -198,7 +255,8 @@ static void handle_tx(struct vhost_net *net)
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
- vhost_add_used_and_signal(&net->dev, vq, head, 0);
+ if (!zcopy)
+ vhost_add_used_and_signal(&net->dev, vq, head, 0);
total_len += len;
if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
vhost_poll_queue(&vq->poll);
@@ -603,6 +661,7 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
struct vhost_virtqueue *vq;
+ struct vhost_ubuf_ref *ubufs, *oldubufs = NULL;
int r;
mutex_lock(&n->dev.mutex);
@@ -632,6 +691,13 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
oldsock = rcu_dereference_protected(vq->private_data,
lockdep_is_held(&vq->mutex));
if (sock != oldsock) {
+ ubufs = vhost_ubuf_alloc(vq, sock && vhost_sock_zcopy(sock));
+ if (IS_ERR(ubufs)) {
+ r = PTR_ERR(ubufs);
+ goto err_ubufs;
+ }
+ oldubufs = vq->ubufs;
+ vq->ubufs = ubufs;
vhost_net_disable_vq(n, vq);
rcu_assign_pointer(vq->private_data, sock);
vhost_net_enable_vq(n, vq);
@@ -639,6 +705,9 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
mutex_unlock(&vq->mutex);
+ if (oldubufs)
+ vhost_ubuf_put_and_wait(oldubufs);
+
if (oldsock) {
vhost_net_flush_vq(n, index);
fput(oldsock->file);
@@ -647,6 +716,8 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
mutex_unlock(&n->dev.mutex);
return 0;
+err_ubufs:
+ fput(sock->file);
err_vq:
mutex_unlock(&vq->mutex);
err:
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index ea966b3..2ebf6fc 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -179,6 +179,9 @@ static void vhost_vq_reset(struct vhost_dev *dev,
vq->call_ctx = NULL;
vq->call = NULL;
vq->log_ctx = NULL;
+ vq->upend_idx = 0;
+ vq->done_idx = 0;
+ vq->ubufs = NULL;
}
static int vhost_worker(void *data)
@@ -237,6 +240,8 @@ static long vhost_dev_alloc_iovecs(struct vhost_dev *dev)
GFP_KERNEL);
dev->vqs[i].heads = kmalloc(sizeof *dev->vqs[i].heads *
UIO_MAXIOV, GFP_KERNEL);
+ dev->vqs[i].ubuf_info = kmalloc(sizeof *dev->vqs[i].ubuf_info *
+ UIO_MAXIOV, GFP_KERNEL);
if (!dev->vqs[i].indirect || !dev->vqs[i].log ||
!dev->vqs[i].heads)
@@ -249,6 +254,7 @@ err_nomem:
kfree(dev->vqs[i].indirect);
kfree(dev->vqs[i].log);
kfree(dev->vqs[i].heads);
+ kfree(dev->vqs[i].ubuf_info);
}
return -ENOMEM;
}
@@ -390,6 +396,29 @@ long vhost_dev_reset_owner(struct vhost_dev *dev)
return 0;
}
+/* In case of DMA done not in order in lower device driver for some reason.
+ * upend_idx is used to track end of used idx, done_idx is used to track head
+ * of used idx. Once lower device DMA done contiguously, we will signal KVM
+ * guest used idx.
+ */
+int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq)
+{
+ int i, j = 0;
+
+ for (i = vq->done_idx; i != vq->upend_idx; i = (i + 1) % UIO_MAXIOV) {
+ if ((vq->heads[i].len == VHOST_DMA_DONE_LEN)) {
+ vq->heads[i].len = VHOST_DMA_CLEAR_LEN;
+ vhost_add_used_and_signal(vq->dev, vq,
+ vq->heads[i].id, 0);
+ ++j;
+ } else
+ break;
+ }
+ if (j)
+ vq->done_idx = i;
+ return j;
+}
+
/* Caller should have device mutex */
void vhost_dev_cleanup(struct vhost_dev *dev)
{
@@ -400,6 +429,13 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
vhost_poll_stop(&dev->vqs[i].poll);
vhost_poll_flush(&dev->vqs[i].poll);
}
+ /* Wait for all lower device DMAs done. */
+ if (dev->vqs[i].ubufs)
+ vhost_ubuf_put_and_wait(dev->vqs[i].ubufs);
+
+ /* Signal guest as appropriate. */
+ vhost_zerocopy_signal_used(&dev->vqs[i]);
+
if (dev->vqs[i].error_ctx)
eventfd_ctx_put(dev->vqs[i].error_ctx);
if (dev->vqs[i].error)
@@ -1486,3 +1522,52 @@ void vhost_disable_notify(struct vhost_dev *dev, struct vhost_virtqueue *vq)
&vq->used->flags, r);
}
}
+
+static void vhost_zerocopy_done_signal(struct kref *kref)
+{
+ struct vhost_ubuf_ref *ubufs = container_of(kref, struct vhost_ubuf_ref,
+ kref);
+ wake_up(&ubufs->wait);
+}
+
+struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *vq,
+ bool zcopy)
+{
+ struct vhost_ubuf_ref *ubufs;
+ /* No zero copy backend? Nothing to count. */
+ if (!zcopy)
+ return NULL;
+ ubufs = kmalloc(sizeof *ubufs, GFP_KERNEL);
+ if (!ubufs)
+ return ERR_PTR(-ENOMEM);
+ kref_init(&ubufs->kref);
+ kref_get(&ubufs->kref);
+ init_waitqueue_head(&ubufs->wait);
+ ubufs->vq = vq;
+ return ubufs;
+}
+
+void vhost_ubuf_put(struct vhost_ubuf_ref *ubufs)
+{
+ kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
+}
+
+void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *ubufs)
+{
+ kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
+ wait_event(ubufs->wait, !atomic_read(&ubufs->kref.refcount));
+ kfree(ubufs);
+}
+
+void vhost_zerocopy_callback(void *arg)
+{
+ struct ubuf_info *ubuf = (struct ubuf_info *)arg;
+ struct vhost_ubuf_ref *ubufs;
+ struct vhost_virtqueue *vq;
+
+ ubufs = ubuf->arg;
+ vq = ubufs->vq;
+ /* set len = 1 to mark this desc buffers done DMA */
+ vq->heads[ubuf->desc].len = VHOST_DMA_DONE_LEN;
+ kref_put(&ubufs->kref, vhost_zerocopy_done_signal);
+}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 8e03379..e287145 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -13,6 +13,11 @@
#include <linux/virtio_ring.h>
#include <asm/atomic.h>
+/* This is for zerocopy, used buffer len is set to 1 when lower device DMA
+ * done */
+#define VHOST_DMA_DONE_LEN 1
+#define VHOST_DMA_CLEAR_LEN 0
+
struct vhost_device;
struct vhost_work;
@@ -50,6 +55,18 @@ struct vhost_log {
u64 len;
};
+struct vhost_virtqueue;
+
+struct vhost_ubuf_ref {
+ struct kref kref;
+ wait_queue_t wait;
+ struct vhost_virtqueue *vq;
+};
+
+struct vhost_ubuf_ref *vhost_ubuf_alloc(struct vhost_virtqueue *, bool zcopy);
+void vhost_ubuf_put(struct vhost_ubuf_ref *);
+void vhost_ubuf_put_and_wait(struct vhost_ubuf_ref *);
+
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
@@ -114,6 +131,16 @@ struct vhost_virtqueue {
/* Log write descriptors */
void __user *log_base;
struct vhost_log *log;
+ /* vhost zerocopy support fields below: */
+ /* last used idx for outstanding DMA zerocopy buffers */
+ int upend_idx;
+ /* first used idx for DMA done zerocopy buffers */
+ int done_idx;
+ /* an array of userspace buffers info */
+ struct ubuf_info *ubuf_info;
+ /* Reference counting for outstanding ubufs.
+ * Protected by vq mutex. Writers must also take device mutex. */
+ struct vhost_ubuf_ref *ubufs;
};
struct vhost_dev {
@@ -160,6 +187,8 @@ bool vhost_enable_notify(struct vhost_dev *, struct vhost_virtqueue *);
int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
unsigned int log_num, u64 len);
+void vhost_zerocopy_callback(void *arg);
+int vhost_zerocopy_signal_used(struct vhost_virtqueue *vq);
#define vq_err(vq, fmt, ...) do { \
pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
--
1.7.5.53.gc233e
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox