* [Patch v3 net-next 07/12] net: fec: add enet-avb IP support
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Frank Li, Fugang Duan
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
i.MX6SX Enet-AVB support 3 tx queues, 3 rx queues.
For tx queues: ring 0 -> best effort
ring 1 -> Class A
ring 2 -> Class B
For rx queues:
ring 0 -> best effort
ring 1 -> receive VLAN packet with classification match
ring 2 -> receive VLAN packet with classification match
Add enet-avb IP multiqueue support for the driver.
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec.h | 33 ++++++++++++++++++++++++++++
drivers/net/ethernet/freescale/fec_main.c | 36 +++++++++++++++----------------
2 files changed, 51 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 72fb90f..5ec3828 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -38,6 +38,12 @@
#define FEC_ADDR_LOW 0x0e4 /* Low 32bits MAC address */
#define FEC_ADDR_HIGH 0x0e8 /* High 16bits MAC address */
#define FEC_OPD 0x0ec /* Opcode + Pause duration */
+#define FEC_TXIC0 0xF0 /* Tx Interrupt Coalescing for ring 0 */
+#define FEC_TXIC1 0xF4 /* Tx Interrupt Coalescing for ring 1 */
+#define FEC_TXIC2 0xF8 /* Tx Interrupt Coalescing for ring 2 */
+#define FEC_RXIC0 0x100 /* Rx Interrupt Coalescing for ring 0 */
+#define FEC_RXIC1 0x104 /* Rx Interrupt Coalescing for ring 1 */
+#define FEC_RXIC2 0x108 /* Rx Interrupt Coalescing for ring 2 */
#define FEC_HASH_TABLE_HIGH 0x118 /* High 32bits hash table */
#define FEC_HASH_TABLE_LOW 0x11c /* Low 32bits hash table */
#define FEC_GRP_HASH_TABLE_HIGH 0x120 /* High 32bits hash table */
@@ -65,6 +71,7 @@
#define FEC_X_DES_ACTIVE_1 0x1e4 /* Tx descriptor active for ring 1 */
#define FEC_R_DES_ACTIVE_2 0x1e8 /* Rx descriptor active for ring 2 */
#define FEC_X_DES_ACTIVE_2 0x1ec /* Tx descriptor active for ring 2 */
+#define FEC_QOS_SCHEME 0x1f0 /* Set multi queues Qos scheme */
#define FEC_MIIGSK_CFGR 0x300 /* MIIGSK Configuration reg */
#define FEC_MIIGSK_ENR 0x308 /* MIIGSK Enable reg */
@@ -305,6 +312,32 @@ struct bufdesc_ex {
#define FLAG_RX_CSUM_ENABLED (BD_ENET_RX_ICE | BD_ENET_RX_PCR)
#define FLAG_RX_CSUM_ERROR (BD_ENET_RX_ICE | BD_ENET_RX_PCR)
+/* Interrupt events/masks. */
+#define FEC_ENET_HBERR ((uint)0x80000000) /* Heartbeat error */
+#define FEC_ENET_BABR ((uint)0x40000000) /* Babbling receiver */
+#define FEC_ENET_BABT ((uint)0x20000000) /* Babbling transmitter */
+#define FEC_ENET_GRA ((uint)0x10000000) /* Graceful stop complete */
+#define FEC_ENET_TXF_0 ((uint)0x08000000) /* Full frame transmitted */
+#define FEC_ENET_TXF_1 ((uint)0x00000008) /* Full frame transmitted */
+#define FEC_ENET_TXF_2 ((uint)0x00000080) /* Full frame transmitted */
+#define FEC_ENET_TXB ((uint)0x04000000) /* A buffer was transmitted */
+#define FEC_ENET_RXF_0 ((uint)0x02000000) /* Full frame received */
+#define FEC_ENET_RXF_1 ((uint)0x00000002) /* Full frame received */
+#define FEC_ENET_RXF_2 ((uint)0x00000020) /* Full frame received */
+#define FEC_ENET_RXB ((uint)0x01000000) /* A buffer was received */
+#define FEC_ENET_MII ((uint)0x00800000) /* MII interrupt */
+#define FEC_ENET_EBERR ((uint)0x00400000) /* SDMA bus error */
+#define FEC_ENET_TXF (FEC_ENET_TXF_0 | FEC_ENET_TXF_1 | FEC_ENET_TXF_2)
+#define FEC_ENET_RXF (FEC_ENET_RXF_0 | FEC_ENET_RXF_1 | FEC_ENET_RXF_2)
+#define FEC_ENET_TS_AVAIL ((uint)0x00010000)
+#define FEC_ENET_TS_TIMER ((uint)0x00008000)
+
+#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII | FEC_ENET_TS_TIMER)
+#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
+
+#define FEC_VLAN_TAG_LEN 0x04
+#define FEC_ETHTYPE_LEN 0x02
+
struct fec_enet_priv_tx_q {
int index;
unsigned char *tx_bounce[TX_RING_SIZE];
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 5f8e997..658b0b3 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -193,21 +193,6 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
#endif
#endif /* CONFIG_M5272 */
-/* Interrupt events/masks. */
-#define FEC_ENET_HBERR ((uint)0x80000000) /* Heartbeat error */
-#define FEC_ENET_BABR ((uint)0x40000000) /* Babbling receiver */
-#define FEC_ENET_BABT ((uint)0x20000000) /* Babbling transmitter */
-#define FEC_ENET_GRA ((uint)0x10000000) /* Graceful stop complete */
-#define FEC_ENET_TXF ((uint)0x08000000) /* Full frame transmitted */
-#define FEC_ENET_TXB ((uint)0x04000000) /* A buffer was transmitted */
-#define FEC_ENET_RXF ((uint)0x02000000) /* Full frame received */
-#define FEC_ENET_RXB ((uint)0x01000000) /* A buffer was received */
-#define FEC_ENET_MII ((uint)0x00800000) /* MII interrupt */
-#define FEC_ENET_EBERR ((uint)0x00400000) /* SDMA bus error */
-
-#define FEC_DEFAULT_IMASK (FEC_ENET_TXF | FEC_ENET_RXF | FEC_ENET_MII)
-#define FEC_RX_DISABLED_IMASK (FEC_DEFAULT_IMASK & (~FEC_ENET_RXF))
-
/* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
*/
#define PKT_MAXBUF_SIZE 1522
@@ -882,6 +867,15 @@ static void fec_enet_bd_init(struct net_device *dev)
}
}
+static void fec_enet_active_rxring(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ int i;
+
+ for (i = 0; i < fep->num_rx_queues; i++)
+ writel(0, fep->hwp + FEC_R_DES_ACTIVE(i));
+}
+
static void fec_enet_enable_ring(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
@@ -939,7 +933,6 @@ fec_restart(struct net_device *ndev)
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
platform_get_device_id(fep->pdev);
- int i;
u32 val;
u32 temp_mac[2];
u32 rcntl = OPT_FRAME_SIZE | 0x04;
@@ -1099,8 +1092,7 @@ fec_restart(struct net_device *ndev)
/* And last, enable the transmit and receive processing */
writel(ecntl, fep->hwp + FEC_ECNTRL);
- for (i = 0; i < fep->num_rx_queues; i++)
- writel(0, fep->hwp + FEC_R_DES_ACTIVE(i));
+ fec_enet_active_rxring(ndev);
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
@@ -1511,9 +1503,17 @@ fec_enet_collect_events(struct fec_enet_private *fep, uint int_events)
if (int_events & FEC_ENET_RXF)
fep->work_rx |= (1 << 2);
+ if (int_events & FEC_ENET_RXF_1)
+ fep->work_rx |= (1 << 0);
+ if (int_events & FEC_ENET_RXF_2)
+ fep->work_rx |= (1 << 1);
if (int_events & FEC_ENET_TXF)
fep->work_tx |= (1 << 2);
+ if (int_events & FEC_ENET_TXF_1)
+ fep->work_tx |= (1 << 0);
+ if (int_events & FEC_ENET_TXF_2)
+ fep->work_tx |= (1 << 1);
return true;
}
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 06/12] net:fec: Disable enet-avb MAC instead of reset MAC
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Fugang Duan, Frank Li
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
For i.MX6SX enet use AXI bus, reset MAC will make system bus dead
if ENET-AXI bus has pending access (AHB bus should not have such issue).
So, disable enet with AVB MAC instead of reset MAC itself.
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec_main.c | 26 ++++++++++++++++++++------
1 file changed, 20 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 03972f7..5f8e997 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -945,9 +945,16 @@ fec_restart(struct net_device *ndev)
u32 rcntl = OPT_FRAME_SIZE | 0x04;
u32 ecntl = 0x2; /* ETHEREN */
- /* Whack a reset. We should wait for this. */
- writel(1, fep->hwp + FEC_ECNTRL);
- udelay(10);
+ /* Whack a reset. We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+ if (id_entry && id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+ writel(0, fep->hwp + FEC_ECNTRL);
+ } else {
+ writel(1, fep->hwp + FEC_ECNTRL);
+ udelay(10);
+ }
/*
* enet-mac reset will reset mac address registers too,
@@ -1118,9 +1125,16 @@ fec_stop(struct net_device *ndev)
netdev_err(ndev, "Graceful transmit stop did not complete!\n");
}
- /* Whack a reset. We should wait for this. */
- writel(1, fep->hwp + FEC_ECNTRL);
- udelay(10);
+ /* Whack a reset. We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+ if (id_entry && id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+ writel(0, fep->hwp + FEC_ECNTRL);
+ } else {
+ writel(1, fep->hwp + FEC_ECNTRL);
+ udelay(10);
+ }
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 05/12] net: fec: init multi queue date structure
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Frank Li, Duan Fugang
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
initilized all queues according to queue number get from DT file.
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Duan Fugang <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec_main.c | 365 +++++++++++++++++++++---------
1 file changed, 252 insertions(+), 113 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 2240df0..03972f7 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -834,47 +834,98 @@ static void fec_enet_bd_init(struct net_device *dev)
struct fec_enet_priv_rx_q *rxq;
struct bufdesc *bdp;
unsigned int i;
+ unsigned int q;
- /* Initialize the receive buffer descriptors. */
- rxq = fep->rx_queue[0];
- bdp = rxq->rx_bd_base;
+ for (q = 0; q < fep->num_rx_queues; q++) {
+ /* Initialize the receive buffer descriptors. */
+ rxq = fep->rx_queue[q];
+ bdp = rxq->rx_bd_base;
- for (i = 0; i < rxq->rx_ring_size; i++) {
+ for (i = 0; i < rxq->rx_ring_size; i++) {
- /* Initialize the BD for every fragment in the page. */
- if (bdp->cbd_bufaddr)
- bdp->cbd_sc = BD_ENET_RX_EMPTY;
- else
+ /* Initialize the BD for every fragment in the page. */
+ if (bdp->cbd_bufaddr)
+ bdp->cbd_sc = BD_ENET_RX_EMPTY;
+ else
+ bdp->cbd_sc = 0;
+ bdp = fec_enet_get_nextdesc(bdp, fep, q);
+ }
+
+ /* Set the last buffer to wrap */
+ bdp = fec_enet_get_prevdesc(bdp, fep, q);
+ bdp->cbd_sc |= BD_SC_WRAP;
+
+ rxq->cur_rx = rxq->rx_bd_base;
+ }
+
+ for (q = 0; q < fep->num_tx_queues; q++) {
+ /* ...and the same for transmit */
+ txq = fep->tx_queue[q];
+ bdp = txq->tx_bd_base;
+ txq->cur_tx = bdp;
+
+ for (i = 0; i < txq->tx_ring_size; i++) {
+ /* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep, 0);
+ if (txq->tx_skbuff[i]) {
+ dev_kfree_skb_any(txq->tx_skbuff[i]);
+ txq->tx_skbuff[i] = NULL;
+ }
+ bdp->cbd_bufaddr = 0;
+ bdp = fec_enet_get_nextdesc(bdp, fep, q);
+ }
+
+ /* Set the last buffer to wrap */
+ bdp = fec_enet_get_prevdesc(bdp, fep, q);
+ bdp->cbd_sc |= BD_SC_WRAP;
+ txq->dirty_tx = bdp;
}
+}
- /* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep, 0);
- bdp->cbd_sc |= BD_SC_WRAP;
+static void fec_enet_enable_ring(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
+ int i;
- rxq->cur_rx = rxq->rx_bd_base;
+ for (i = 0; i < fep->num_rx_queues; i++) {
+ rxq = fep->rx_queue[i];
+ writel(rxq->bd_dma, fep->hwp + FEC_R_DES_START(i));
- /* ...and the same for transmit */
- txq = fep->tx_queue[0];
- bdp = txq->tx_bd_base;
- txq->cur_tx = bdp;
+ /* enable DMA1/2 */
+ if (i)
+ writel(RCMR_MATCHEN | RCMR_CMP(i),
+ fep->hwp + FEC_RCMR(i));
+ }
- for (i = 0; i < txq->tx_ring_size; i++) {
- /* Initialize the BD for every fragment in the page. */
- bdp->cbd_sc = 0;
- if (txq->tx_skbuff[i]) {
- dev_kfree_skb_any(txq->tx_skbuff[i]);
- txq->tx_skbuff[i] = NULL;
- }
- bdp->cbd_bufaddr = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep, 0);
+ for (i = 0; i < fep->num_tx_queues; i++) {
+ txq = fep->tx_queue[i];
+ writel(txq->bd_dma, fep->hwp + FEC_X_DES_START(i));
+
+ /* enable DMA1/2 */
+ if (i)
+ writel(DMA_CLASS_EN | IDLE_SLOPE(i),
+ fep->hwp + FEC_DMA_CFG(i));
}
+}
- /* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep, 0);
- bdp->cbd_sc |= BD_SC_WRAP;
- txq->dirty_tx = bdp;
+static void fec_enet_reset_skb(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ struct fec_enet_priv_tx_q *txq;
+ int i, j;
+
+ for (i = 0; i < fep->num_tx_queues; i++) {
+ txq = fep->tx_queue[i];
+
+ for (j = 0; j < txq->tx_ring_size; j++) {
+ if (txq->tx_skbuff[j]) {
+ dev_kfree_skb_any(txq->tx_skbuff[j]);
+ txq->tx_skbuff[j] = NULL;
+ }
+ }
+ }
}
/*
@@ -893,8 +944,6 @@ fec_restart(struct net_device *ndev)
u32 temp_mac[2];
u32 rcntl = OPT_FRAME_SIZE | 0x04;
u32 ecntl = 0x2; /* ETHEREN */
- struct fec_enet_priv_tx_q *txq;
- struct fec_enet_priv_rx_q *rxq;
/* Whack a reset. We should wait for this. */
writel(1, fep->hwp + FEC_ECNTRL);
@@ -918,24 +967,10 @@ fec_restart(struct net_device *ndev)
fec_enet_bd_init(ndev);
- /* Set receive and transmit descriptor base. */
- rxq = fep->rx_queue[0];
- writel(rxq->bd_dma, fep->hwp + FEC_R_DES_START(0));
- if (fep->bufdesc_ex)
- writel((unsigned long)rxq->bd_dma + sizeof(struct bufdesc_ex)
- * rxq->rx_ring_size, fep->hwp + FEC_X_DES_START(0));
- else
- writel((unsigned long)rxq->bd_dma + sizeof(struct bufdesc)
- * rxq->rx_ring_size, fep->hwp + FEC_X_DES_START(0));
+ fec_enet_enable_ring(ndev);
-
- txq = fep->tx_queue[0];
- for (i = 0; i <= TX_RING_MOD_MASK; i++) {
- if (txq->tx_skbuff[i]) {
- dev_kfree_skb_any(txq->tx_skbuff[i]);
- txq->tx_skbuff[i] = NULL;
- }
- }
+ /* Reset tx SKB buffers. */
+ fec_enet_reset_skb(ndev);
/* Enable MII mode */
if (fep->full_duplex == DUPLEX_FULL) {
@@ -1057,7 +1092,8 @@ fec_restart(struct net_device *ndev)
/* And last, enable the transmit and receive processing */
writel(ecntl, fep->hwp + FEC_ECNTRL);
- writel(0, fep->hwp + FEC_R_DES_ACTIVE(0));
+ for (i = 0; i < fep->num_rx_queues; i++)
+ writel(0, fep->hwp + FEC_R_DES_ACTIVE(i));
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
@@ -2233,41 +2269,122 @@ static void fec_enet_free_buffers(struct net_device *ndev)
struct bufdesc *bdp;
struct fec_enet_priv_tx_q *txq;
struct fec_enet_priv_rx_q *rxq;
+ unsigned int q;
+
+ for (q = 0; q < fep->num_rx_queues; q++) {
+ rxq = fep->rx_queue[q];
+ bdp = rxq->rx_bd_base;
+ for (i = 0; i < rxq->rx_ring_size; i++) {
+ skb = rxq->rx_skbuff[i];
+ rxq->rx_skbuff[i] = NULL;
+ if (skb) {
+ dma_unmap_single(&fep->pdev->dev,
+ bdp->cbd_bufaddr,
+ FEC_ENET_RX_FRSIZE,
+ DMA_FROM_DEVICE);
+ dev_kfree_skb(skb);
+ }
+ bdp = fec_enet_get_nextdesc(bdp, fep, q);
+ }
+ }
- rxq = fep->rx_queue[0];
- bdp = rxq->rx_bd_base;
- for (i = 0; i < rxq->rx_ring_size; i++) {
- skb = rxq->rx_skbuff[i];
- rxq->rx_skbuff[i] = NULL;
- if (skb) {
- dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
- FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
+ for (q = 0; q < fep->num_tx_queues; q++) {
+ txq = fep->tx_queue[q];
+ bdp = txq->tx_bd_base;
+ for (i = 0; i < txq->tx_ring_size; i++) {
+ kfree(txq->tx_bounce[i]);
+ txq->tx_bounce[i] = NULL;
+ skb = txq->tx_skbuff[i];
+ txq->tx_skbuff[i] = NULL;
dev_kfree_skb(skb);
}
- bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
+}
- txq = fep->tx_queue[0];
- bdp = txq->tx_bd_base;
- for (i = 0; i < txq->tx_ring_size; i++) {
- kfree(txq->tx_bounce[i]);
- txq->tx_bounce[i] = NULL;
- skb = txq->tx_skbuff[i];
- txq->tx_skbuff[i] = NULL;
- dev_kfree_skb(skb);
+static void fec_enet_free_queue(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ int i;
+ struct fec_enet_priv_tx_q *txq;
+
+ for (i = 0; i < fep->num_tx_queues; i++)
+ if (fep->tx_queue[i] && fep->tx_queue[i]->tso_hdrs) {
+ txq = fep->tx_queue[i];
+ dma_free_coherent(NULL,
+ txq->tx_ring_size * TSO_HEADER_SIZE,
+ txq->tso_hdrs,
+ txq->tso_hdrs_dma);
+ }
+
+ for (i = 0; i < fep->num_rx_queues; i++)
+ if (fep->rx_queue[i])
+ kfree(fep->rx_queue[i]);
+
+ for (i = 0; i < fep->num_tx_queues; i++)
+ if (fep->tx_queue[i])
+ kfree(fep->tx_queue[i]);
+}
+
+static int fec_enet_alloc_queue(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ int i;
+ int ret = 0;
+ struct fec_enet_priv_tx_q *txq;
+
+ for (i = 0; i < fep->num_tx_queues; i++) {
+ txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+ if (!txq) {
+ ret = -ENOMEM;
+ goto alloc_failed;
+ }
+
+ fep->tx_queue[i] = txq;
+ txq->tx_ring_size = TX_RING_SIZE;
+ fep->total_tx_ring_size += fep->tx_queue[i]->tx_ring_size;
+
+ txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
+ txq->tx_wake_threshold =
+ (txq->tx_ring_size - txq->tx_stop_threshold) / 2;
+
+ txq->tso_hdrs = dma_alloc_coherent(NULL,
+ txq->tx_ring_size * TSO_HEADER_SIZE,
+ &txq->tso_hdrs_dma,
+ GFP_KERNEL);
+ if (!txq->tso_hdrs) {
+ ret = -ENOMEM;
+ goto alloc_failed;
+ }
}
+
+ for (i = 0; i < fep->num_rx_queues; i++) {
+ fep->rx_queue[i] = kzalloc(sizeof(*fep->rx_queue[i]),
+ GFP_KERNEL);
+ if (!fep->rx_queue[i]) {
+ ret = -ENOMEM;
+ goto alloc_failed;
+ }
+
+ fep->rx_queue[i]->rx_ring_size = RX_RING_SIZE;
+ fep->total_rx_ring_size += fep->rx_queue[i]->rx_ring_size;
+ }
+ return ret;
+
+alloc_failed:
+ fec_enet_free_queue(ndev);
+ return ret;
}
-static int fec_enet_alloc_buffers(struct net_device *ndev)
+static int
+fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
{
struct fec_enet_private *fep = netdev_priv(ndev);
unsigned int i;
struct sk_buff *skb;
struct bufdesc *bdp;
- struct fec_enet_priv_tx_q *txq;
struct fec_enet_priv_rx_q *rxq;
- rxq = fep->rx_queue[0];
+ rxq = fep->rx_queue[queue];
bdp = rxq->rx_bd_base;
for (i = 0; i < rxq->rx_ring_size; i++) {
dma_addr_t addr;
@@ -2294,14 +2411,28 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
ebdp->cbd_esc = BD_ENET_RX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep, 0);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep, 0);
+ bdp = fec_enet_get_prevdesc(bdp, fep, queue);
bdp->cbd_sc |= BD_SC_WRAP;
+ return 0;
- txq = fep->tx_queue[0];
+ err_alloc:
+ fec_enet_free_buffers(ndev);
+ return -ENOMEM;
+}
+
+static int
+fec_enet_alloc_txq_buffers(struct net_device *ndev, unsigned int queue)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ unsigned int i;
+ struct bufdesc *bdp;
+ struct fec_enet_priv_tx_q *txq;
+
+ txq = fep->tx_queue[queue];
bdp = txq->tx_bd_base;
for (i = 0; i < txq->tx_ring_size; i++) {
txq->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
@@ -2316,11 +2447,11 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
ebdp->cbd_esc = BD_ENET_TX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep, 0);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep, 0);
+ bdp = fec_enet_get_prevdesc(bdp, fep, queue);
bdp->cbd_sc |= BD_SC_WRAP;
return 0;
@@ -2330,6 +2461,21 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
return -ENOMEM;
}
+static int fec_enet_alloc_buffers(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ unsigned int i;
+
+ for (i = 0; i < fep->num_rx_queues; i++)
+ if (fec_enet_alloc_rxq_buffers(ndev, i))
+ return -ENOMEM;
+
+ for (i = 0; i < fep->num_tx_queues; i++)
+ if (fec_enet_alloc_txq_buffers(ndev, i))
+ return -ENOMEM;
+ return 0;
+}
+
static int
fec_enet_open(struct net_device *ndev)
{
@@ -2579,28 +2725,9 @@ static int fec_enet_init(struct net_device *ndev)
struct bufdesc *cbd_base;
dma_addr_t bd_dma;
int bd_size;
+ unsigned int i;
- txq = kzalloc(sizeof(*txq), GFP_KERNEL);
- if (!txq)
- return -ENOMEM;
- fep->tx_queue[0] = txq;
-
- rxq = kzalloc(sizeof(*rxq), GFP_KERNEL);
- if (!rxq) {
- kfree(txq);
- return -ENOMEM;
- }
-
- fep->rx_queue[0] = rxq;
-
-
- txq->tx_ring_size = TX_RING_SIZE;
- rxq->rx_ring_size = RX_RING_SIZE;
- fep->total_tx_ring_size = txq->tx_ring_size;
- fep->total_rx_ring_size = rxq->rx_ring_size;
-
- txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
- txq->tx_wake_threshold = (txq->tx_ring_size - txq->tx_stop_threshold) / 2;
+ fec_enet_alloc_queue(ndev);
if (fep->bufdesc_ex)
fep->bufdesc_size = sizeof(struct bufdesc_ex);
@@ -2613,17 +2740,6 @@ static int fec_enet_init(struct net_device *ndev)
cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
GFP_KERNEL);
if (!cbd_base) {
- kfree(rxq);
- kfree(txq);
- return -ENOMEM;
- }
-
- txq->tso_hdrs = dma_alloc_coherent(NULL, txq->tx_ring_size * TSO_HEADER_SIZE,
- &txq->tso_hdrs_dma, GFP_KERNEL);
- if (!txq->tso_hdrs) {
- kfree(rxq);
- kfree(txq);
- dma_free_coherent(NULL, bd_size, cbd_base, bd_dma);
return -ENOMEM;
}
@@ -2635,12 +2751,35 @@ static int fec_enet_init(struct net_device *ndev)
fec_set_mac_address(ndev, NULL);
/* Set receive and transmit descriptor base. */
- rxq->rx_bd_base = cbd_base;
- if (fep->bufdesc_ex)
- txq->tx_bd_base = (struct bufdesc *)
- (((struct bufdesc_ex *)cbd_base) + rxq->rx_ring_size);
- else
- txq->tx_bd_base = cbd_base + rxq->rx_ring_size;
+ for (i = 0; i < fep->num_rx_queues; i++) {
+ rxq = fep->rx_queue[i];
+ rxq->index = i;
+ rxq->rx_bd_base = (struct bufdesc *)cbd_base;
+ rxq->bd_dma = bd_dma;
+ if (fep->bufdesc_ex) {
+ bd_dma += sizeof(struct bufdesc_ex) * rxq->rx_ring_size;
+ cbd_base = (struct bufdesc *)
+ (((struct bufdesc_ex *)cbd_base) + rxq->rx_ring_size);
+ } else {
+ bd_dma += sizeof(struct bufdesc) * rxq->rx_ring_size;
+ cbd_base += rxq->rx_ring_size;
+ }
+ }
+
+ for (i = 0; i < fep->num_tx_queues; i++) {
+ txq = fep->tx_queue[i];
+ txq->index = i;
+ txq->tx_bd_base = (struct bufdesc *)cbd_base;
+ txq->bd_dma = bd_dma;
+ if (fep->bufdesc_ex) {
+ bd_dma += sizeof(struct bufdesc_ex) * txq->tx_ring_size;
+ cbd_base = (struct bufdesc *)
+ (((struct bufdesc_ex *)cbd_base) + txq->tx_ring_size);
+ } else {
+ bd_dma += sizeof(struct bufdesc) * txq->tx_ring_size;
+ cbd_base += txq->tx_ring_size;
+ }
+ }
/* The FEC Ethernet specific entries in the device structure */
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 04/12] net: fec: parser max queue number from dt file
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Fugang Duan, Frank Li
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
By default, the tx/rx queue number is 1, user can config the queue number
at DTS file like this:
fsl,num-tx-queues=<3>;
fsl,num-rx-queues=<3>
Since i.MX6SX enet-AVB IP support multi queues, so use multi queues
interface to allocate and set up an Ethernet device.
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec.h | 2 ++
drivers/net/ethernet/freescale/fec_main.c | 46 ++++++++++++++++++++++++++++++-
2 files changed, 47 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index b2b91f8..72fb90f 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -356,6 +356,8 @@ struct fec_enet_private {
bool ptp_clk_on;
struct mutex ptp_clk_mutex;
+ unsigned int num_tx_queues;
+ unsigned int num_rx_queues;
/* The saved address of a sent-in-place packet/buffer, for skfree(). */
struct fec_enet_priv_tx_q *tx_queue[FEC_ENET_MAX_TX_QS];
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 4c0d2ee..2240df0 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -2709,6 +2709,42 @@ static void fec_reset_phy(struct platform_device *pdev)
}
#endif /* CONFIG_OF */
+static void
+fec_enet_get_queue_num(struct platform_device *pdev, int *num_tx, int *num_rx)
+{
+ struct device_node *np = pdev->dev.of_node;
+ int err;
+
+ *num_tx = *num_rx = 1;
+
+ if (!np || !of_device_is_available(np))
+ return;
+
+ /* parse the num of tx and rx queues */
+ err = of_property_read_u32(np, "fsl,num-tx-queues", num_tx);
+ err |= of_property_read_u32(np, "fsl,num-rx-queues", num_rx);
+ if (err) {
+ *num_tx = 1;
+ *num_rx = 1;
+ return;
+ }
+
+ if (*num_tx < 1 || *num_tx > FEC_ENET_MAX_TX_QS) {
+ dev_err(&pdev->dev, "Invalidate num_tx(=%d), fail back to 1\n",
+ *num_tx);
+ *num_tx = 1;
+ return;
+ }
+
+ if (*num_rx < 1 || *num_rx > FEC_ENET_MAX_RX_QS) {
+ dev_err(&pdev->dev, "Invalidate num_rx(=%d), fail back to 1\n",
+ *num_rx);
+ *num_rx = 1;
+ return;
+ }
+
+}
+
static int
fec_probe(struct platform_device *pdev)
{
@@ -2720,13 +2756,18 @@ fec_probe(struct platform_device *pdev)
const struct of_device_id *of_id;
static int dev_id;
struct device_node *np = pdev->dev.of_node, *phy_node;
+ int num_tx_qs = 1;
+ int num_rx_qs = 1;
of_id = of_match_device(fec_dt_ids, &pdev->dev);
if (of_id)
pdev->id_entry = of_id->data;
+ fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs);
+
/* Init network device */
- ndev = alloc_etherdev(sizeof(struct fec_enet_private));
+ ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private),
+ num_tx_qs, num_rx_qs);
if (!ndev)
return -ENOMEM;
@@ -2735,6 +2776,9 @@ fec_probe(struct platform_device *pdev)
/* setup board info structure */
fep = netdev_priv(ndev);
+ fep->num_rx_queues = num_rx_qs;
+ fep->num_tx_queues = num_tx_qs;
+
#if !defined(CONFIG_M5272)
/* default enable pause frame auto negotiation */
if (pdev->id_entry &&
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 03/12] net: fec: change data structure to support multiqueue
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Fugang Duan, Frank Li
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
This patch just change data structure to support multi-queue.
Only 1 queue enabled.
Ethernet multiqueue mechanism can improve performance in SMP system.
For single hw queue, multiqueue can balance cpu loading.
For multi hw queues, multiple cores can process network packets in parallel,
and refer the article for the detail advantage for multiqueue:
http://vger.kernel.org/~davem/davem_nyc09.pdf
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <frank.li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec.h | 115 +++++--
drivers/net/ethernet/freescale/fec_main.c | 481 +++++++++++++++++++-----------
2 files changed, 400 insertions(+), 196 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 635772b..b2b91f8 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -27,8 +27,8 @@
*/
#define FEC_IEVENT 0x004 /* Interrupt event reg */
#define FEC_IMASK 0x008 /* Interrupt mask reg */
-#define FEC_R_DES_ACTIVE 0x010 /* Receive descriptor reg */
-#define FEC_X_DES_ACTIVE 0x014 /* Transmit descriptor reg */
+#define FEC_R_DES_ACTIVE_0 0x010 /* Receive descriptor reg */
+#define FEC_X_DES_ACTIVE_0 0x014 /* Transmit descriptor reg */
#define FEC_ECNTRL 0x024 /* Ethernet control reg */
#define FEC_MII_DATA 0x040 /* MII manage frame reg */
#define FEC_MII_SPEED 0x044 /* MII speed control reg */
@@ -45,14 +45,26 @@
#define FEC_X_WMRK 0x144 /* FIFO transmit water mark */
#define FEC_R_BOUND 0x14c /* FIFO receive bound reg */
#define FEC_R_FSTART 0x150 /* FIFO receive start reg */
-#define FEC_R_DES_START 0x180 /* Receive descriptor ring */
-#define FEC_X_DES_START 0x184 /* Transmit descriptor ring */
+#define FEC_R_DES_START_1 0x160 /* Receive descriptor ring 1 */
+#define FEC_X_DES_START_1 0x164 /* Transmit descriptor ring 1 */
+#define FEC_R_DES_START_2 0x16c /* Receive descriptor ring 2 */
+#define FEC_X_DES_START_2 0x170 /* Transmit descriptor ring 2 */
+#define FEC_R_DES_START_0 0x180 /* Receive descriptor ring */
+#define FEC_X_DES_START_0 0x184 /* Transmit descriptor ring */
#define FEC_R_BUFF_SIZE 0x188 /* Maximum receive buff size */
#define FEC_R_FIFO_RSFL 0x190 /* Receive FIFO section full threshold */
#define FEC_R_FIFO_RSEM 0x194 /* Receive FIFO section empty threshold */
#define FEC_R_FIFO_RAEM 0x198 /* Receive FIFO almost empty threshold */
#define FEC_R_FIFO_RAFL 0x19c /* Receive FIFO almost full threshold */
#define FEC_RACC 0x1C4 /* Receive Accelerator function */
+#define FEC_RCMR_1 0x1c8 /* Receive classification match ring 1 */
+#define FEC_RCMR_2 0x1cc /* Receive classification match ring 2 */
+#define FEC_DMA_CFG_1 0x1d8 /* DMA class configuration for ring 1 */
+#define FEC_DMA_CFG_2 0x1dc /* DMA class Configuration for ring 2 */
+#define FEC_R_DES_ACTIVE_1 0x1e0 /* Rx descriptor active for ring 1 */
+#define FEC_X_DES_ACTIVE_1 0x1e4 /* Tx descriptor active for ring 1 */
+#define FEC_R_DES_ACTIVE_2 0x1e8 /* Rx descriptor active for ring 2 */
+#define FEC_X_DES_ACTIVE_2 0x1ec /* Tx descriptor active for ring 2 */
#define FEC_MIIGSK_CFGR 0x300 /* MIIGSK Configuration reg */
#define FEC_MIIGSK_ENR 0x308 /* MIIGSK Enable reg */
@@ -233,6 +245,43 @@ struct bufdesc_ex {
/* This device has up to three irqs on some platforms */
#define FEC_IRQ_NUM 3
+/* Maximum number of queues supported
+ * ENET with AVB IP can support up to 3 independent tx queues and rx queues.
+ * User can point the queue number that is less than or equal to 3.
+ */
+#define FEC_ENET_MAX_TX_QS 3
+#define FEC_ENET_MAX_RX_QS 3
+
+#define FEC_R_DES_START(X) ((X == 1) ? FEC_R_DES_START_1 : \
+ ((X == 2) ? \
+ FEC_R_DES_START_2 : FEC_R_DES_START_0))
+#define FEC_X_DES_START(X) ((X == 1) ? FEC_X_DES_START_1 : \
+ ((X == 2) ? \
+ FEC_X_DES_START_2 : FEC_X_DES_START_0))
+#define FEC_R_DES_ACTIVE(X) ((X == 1) ? FEC_R_DES_ACTIVE_1 : \
+ ((X == 2) ? \
+ FEC_R_DES_ACTIVE_2 : FEC_R_DES_ACTIVE_0))
+#define FEC_X_DES_ACTIVE(X) ((X == 1) ? FEC_X_DES_ACTIVE_1 : \
+ ((X == 2) ? \
+ FEC_X_DES_ACTIVE_2 : FEC_X_DES_ACTIVE_0))
+
+#define FEC_DMA_CFG(X) ((X == 2) ? FEC_DMA_CFG_2 : FEC_DMA_CFG_1)
+
+#define DMA_CLASS_EN (1 << 16)
+#define FEC_RCMR(X) ((X == 2) ? FEC_RCMR_2 : FEC_RCMR_1)
+#define IDLE_SLOPE_MASK 0xFFFF
+#define IDLE_SLOPE_1 0x200 /* BW fraction: 0.5 */
+#define IDLE_SLOPE_2 0x200 /* BW fraction: 0.5 */
+#define IDLE_SLOPE(X) ((X == 1) ? (IDLE_SLOPE_1 & IDLE_SLOPE_MASK) : \
+ (IDLE_SLOPE_2 & IDLE_SLOPE_MASK))
+#define RCMR_MATCHEN (0x1 << 16)
+#define RCMR_CMP_CFG(v, n) ((v & 0x7) << (n << 2))
+#define RCMR_CMP_1 (RCMR_CMP_CFG(0, 0) | RCMR_CMP_CFG(1, 1) | \
+ RCMR_CMP_CFG(2, 2) | RCMR_CMP_CFG(3, 3))
+#define RCMR_CMP_2 (RCMR_CMP_CFG(4, 0) | RCMR_CMP_CFG(5, 1) | \
+ RCMR_CMP_CFG(6, 2) | RCMR_CMP_CFG(7, 3))
+#define RCMR_CMP(X) ((X == 1) ? RCMR_CMP_1 : RCMR_CMP_2)
+
/* The number of Tx and Rx buffers. These are allocated from the page
* pool. The code may assume these are power of two, so it it best
* to keep them that size.
@@ -256,6 +305,35 @@ struct bufdesc_ex {
#define FLAG_RX_CSUM_ENABLED (BD_ENET_RX_ICE | BD_ENET_RX_PCR)
#define FLAG_RX_CSUM_ERROR (BD_ENET_RX_ICE | BD_ENET_RX_PCR)
+struct fec_enet_priv_tx_q {
+ int index;
+ unsigned char *tx_bounce[TX_RING_SIZE];
+ struct sk_buff *tx_skbuff[TX_RING_SIZE];
+
+ dma_addr_t bd_dma;
+ struct bufdesc *tx_bd_base;
+ uint tx_ring_size;
+
+ unsigned short tx_stop_threshold;
+ unsigned short tx_wake_threshold;
+
+ struct bufdesc *cur_tx;
+ struct bufdesc *dirty_tx;
+ char *tso_hdrs;
+ dma_addr_t tso_hdrs_dma;
+};
+
+struct fec_enet_priv_rx_q {
+ int index;
+ struct sk_buff *rx_skbuff[RX_RING_SIZE];
+
+ dma_addr_t bd_dma;
+ struct bufdesc *rx_bd_base;
+ uint rx_ring_size;
+
+ struct bufdesc *cur_rx;
+};
+
/* The FEC buffer descriptors track the ring buffers. The rx_bd_base and
* tx_bd_base always point to the base of the buffer descriptors. The
* cur_rx and cur_tx point to the currently available buffer.
@@ -280,29 +358,18 @@ struct fec_enet_private {
struct mutex ptp_clk_mutex;
/* The saved address of a sent-in-place packet/buffer, for skfree(). */
- unsigned char *tx_bounce[TX_RING_SIZE];
- struct sk_buff *tx_skbuff[TX_RING_SIZE];
- struct sk_buff *rx_skbuff[RX_RING_SIZE];
+ struct fec_enet_priv_tx_q *tx_queue[FEC_ENET_MAX_TX_QS];
+ struct fec_enet_priv_rx_q *rx_queue[FEC_ENET_MAX_RX_QS];
- /* CPM dual port RAM relative addresses */
- dma_addr_t bd_dma;
- /* Address of Rx and Tx buffers */
- struct bufdesc *rx_bd_base;
- struct bufdesc *tx_bd_base;
- /* The next free ring entry */
- struct bufdesc *cur_rx, *cur_tx;
- /* The ring entries to be free()ed */
- struct bufdesc *dirty_tx;
+ unsigned int total_tx_ring_size;
+ unsigned int total_rx_ring_size;
- unsigned short bufdesc_size;
- unsigned short tx_ring_size;
- unsigned short rx_ring_size;
- unsigned short tx_stop_threshold;
- unsigned short tx_wake_threshold;
+ unsigned long work_tx;
+ unsigned long work_rx;
+ unsigned long work_ts;
+ unsigned long work_mdio;
- /* Software TSO */
- char *tso_hdrs;
- dma_addr_t tso_hdrs_dma;
+ unsigned short bufdesc_size;
struct platform_device *pdev;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index ee9f04f..4c0d2ee 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -72,6 +72,8 @@ static void set_multicast_list(struct net_device *ndev);
#define DRIVER_NAME "fec"
+#define FEC_ENET_GET_QUQUE(_x) ((_x == 0) ? 1 : ((_x == 1) ? 2 : 0))
+
/* Pause frame feild and FIFO threshold */
#define FEC_ENET_FCE (1 << 5)
#define FEC_ENET_RSEM_V 0x84
@@ -258,22 +260,26 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
static int mii_cnt;
static inline
-struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
+struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp,
+ struct fec_enet_private *fep,
+ int queue_id)
{
struct bufdesc *new_bd = bdp + 1;
struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp + 1;
+ struct fec_enet_priv_tx_q *txq = fep->tx_queue[queue_id];
+ struct fec_enet_priv_rx_q *rxq = fep->rx_queue[queue_id];
struct bufdesc_ex *ex_base;
struct bufdesc *base;
int ring_size;
- if (bdp >= fep->tx_bd_base) {
- base = fep->tx_bd_base;
- ring_size = fep->tx_ring_size;
- ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+ if (bdp >= txq->tx_bd_base) {
+ base = txq->tx_bd_base;
+ ring_size = txq->tx_ring_size;
+ ex_base = (struct bufdesc_ex *)txq->tx_bd_base;
} else {
- base = fep->rx_bd_base;
- ring_size = fep->rx_ring_size;
- ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+ base = rxq->rx_bd_base;
+ ring_size = rxq->rx_ring_size;
+ ex_base = (struct bufdesc_ex *)rxq->rx_bd_base;
}
if (fep->bufdesc_ex)
@@ -285,22 +291,26 @@ struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp, struct fec_enet_priva
}
static inline
-struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp, struct fec_enet_private *fep)
+struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp,
+ struct fec_enet_private *fep,
+ int queue_id)
{
struct bufdesc *new_bd = bdp - 1;
struct bufdesc_ex *ex_new_bd = (struct bufdesc_ex *)bdp - 1;
+ struct fec_enet_priv_tx_q *txq = fep->tx_queue[queue_id];
+ struct fec_enet_priv_rx_q *rxq = fep->rx_queue[queue_id];
struct bufdesc_ex *ex_base;
struct bufdesc *base;
int ring_size;
- if (bdp >= fep->tx_bd_base) {
- base = fep->tx_bd_base;
- ring_size = fep->tx_ring_size;
- ex_base = (struct bufdesc_ex *)fep->tx_bd_base;
+ if (bdp >= txq->tx_bd_base) {
+ base = txq->tx_bd_base;
+ ring_size = txq->tx_ring_size;
+ ex_base = (struct bufdesc_ex *)txq->tx_bd_base;
} else {
- base = fep->rx_bd_base;
- ring_size = fep->rx_ring_size;
- ex_base = (struct bufdesc_ex *)fep->rx_bd_base;
+ base = rxq->rx_bd_base;
+ ring_size = rxq->rx_ring_size;
+ ex_base = (struct bufdesc_ex *)rxq->rx_bd_base;
}
if (fep->bufdesc_ex)
@@ -316,14 +326,15 @@ static int fec_enet_get_bd_index(struct bufdesc *base, struct bufdesc *bdp,
return ((const char *)bdp - (const char *)base) / fep->bufdesc_size;
}
-static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep)
+static int fec_enet_get_free_txdesc_num(struct fec_enet_private *fep,
+ struct fec_enet_priv_tx_q *txq)
{
int entries;
- entries = ((const char *)fep->dirty_tx -
- (const char *)fep->cur_tx) / fep->bufdesc_size - 1;
+ entries = ((const char *)txq->dirty_tx -
+ (const char *)txq->cur_tx) / fep->bufdesc_size - 1;
- return entries > 0 ? entries : entries + fep->tx_ring_size;
+ return entries > 0 ? entries : entries + txq->tx_ring_size;
}
static void *swap_buffer(void *bufaddr, int len)
@@ -340,22 +351,26 @@ static void *swap_buffer(void *bufaddr, int len)
static void fec_dump(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
- struct bufdesc *bdp = fep->tx_bd_base;
- unsigned int index = 0;
+ struct bufdesc *bdp;
+ struct fec_enet_priv_tx_q *txq;
+ int index = 0;
netdev_info(ndev, "TX ring dump\n");
pr_info("Nr SC addr len SKB\n");
+ txq = fep->tx_queue[0];
+ bdp = txq->tx_bd_base;
+
do {
pr_info("%3u %c%c 0x%04x 0x%08lx %4u %p\n",
index,
- bdp == fep->cur_tx ? 'S' : ' ',
- bdp == fep->dirty_tx ? 'H' : ' ',
+ bdp == txq->cur_tx ? 'S' : ' ',
+ bdp == txq->dirty_tx ? 'H' : ' ',
bdp->cbd_sc, bdp->cbd_bufaddr, bdp->cbd_datlen,
- fep->tx_skbuff[index]);
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ txq->tx_skbuff[index]);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
index++;
- } while (bdp != fep->tx_bd_base);
+ } while (bdp != txq->tx_bd_base);
}
static inline bool is_ipv4_pkt(struct sk_buff *skb)
@@ -381,14 +396,17 @@ fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
}
static int
-fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
+fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq,
+ struct sk_buff *skb,
+ struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
platform_get_device_id(fep->pdev);
- struct bufdesc *bdp = fep->cur_tx;
+ struct bufdesc *bdp = txq->cur_tx;
struct bufdesc_ex *ebdp;
int nr_frags = skb_shinfo(skb)->nr_frags;
+ unsigned short queue = skb_get_queue_mapping(skb);
int frag, frag_len;
unsigned short status;
unsigned int estatus = 0;
@@ -400,7 +418,7 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
for (frag = 0; frag < nr_frags; frag++) {
this_frag = &skb_shinfo(skb)->frags[frag];
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
ebdp = (struct bufdesc_ex *)bdp;
status = bdp->cbd_sc;
@@ -428,11 +446,11 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
- index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+ index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
- memcpy(fep->tx_bounce[index], bufaddr, frag_len);
- bufaddr = fep->tx_bounce[index];
+ memcpy(txq->tx_bounce[index], bufaddr, frag_len);
+ bufaddr = txq->tx_bounce[index];
if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, frag_len);
@@ -452,21 +470,22 @@ fec_enet_txq_submit_frag_skb(struct sk_buff *skb, struct net_device *ndev)
bdp->cbd_sc = status;
}
- fep->cur_tx = bdp;
+ txq->cur_tx = bdp;
return 0;
dma_mapping_error:
- bdp = fep->cur_tx;
+ bdp = txq->cur_tx;
for (i = 0; i < frag; i++) {
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
bdp->cbd_datlen, DMA_TO_DEVICE);
}
return NETDEV_TX_OK;
}
-static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
+static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
+ struct sk_buff *skb, struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
@@ -477,12 +496,13 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
dma_addr_t addr;
unsigned short status;
unsigned short buflen;
+ unsigned short queue;
unsigned int estatus = 0;
unsigned int index;
int entries_free;
int ret;
- entries_free = fec_enet_get_free_txdesc_num(fep);
+ entries_free = fec_enet_get_free_txdesc_num(fep, txq);
if (entries_free < MAX_SKB_FRAGS + 1) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
@@ -497,7 +517,7 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
}
/* Fill in a Tx ring entry */
- bdp = fep->cur_tx;
+ bdp = txq->cur_tx;
status = bdp->cbd_sc;
status &= ~BD_ENET_TX_STATS;
@@ -505,11 +525,12 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
bufaddr = skb->data;
buflen = skb_headlen(skb);
- index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+ queue = skb_get_queue_mapping(skb);
+ index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
- memcpy(fep->tx_bounce[index], skb->data, buflen);
- bufaddr = fep->tx_bounce[index];
+ memcpy(txq->tx_bounce[index], skb->data, buflen);
+ bufaddr = txq->tx_bounce[index];
if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, buflen);
@@ -525,7 +546,7 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
}
if (nr_frags) {
- ret = fec_enet_txq_submit_frag_skb(skb, ndev);
+ ret = fec_enet_txq_submit_frag_skb(txq, skb, ndev);
if (ret)
return ret;
} else {
@@ -553,10 +574,10 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
ebdp->cbd_esc = estatus;
}
- last_bdp = fep->cur_tx;
- index = fec_enet_get_bd_index(fep->tx_bd_base, last_bdp, fep);
+ last_bdp = txq->cur_tx;
+ index = fec_enet_get_bd_index(txq->tx_bd_base, last_bdp, fep);
/* Save skb pointer */
- fep->tx_skbuff[index] = skb;
+ txq->tx_skbuff[index] = skb;
bdp->cbd_datlen = buflen;
bdp->cbd_bufaddr = addr;
@@ -568,22 +589,23 @@ static int fec_enet_txq_submit_skb(struct sk_buff *skb, struct net_device *ndev)
bdp->cbd_sc = status;
/* If this was the last BD in the ring, start at the beginning again. */
- bdp = fec_enet_get_nextdesc(last_bdp, fep);
+ bdp = fec_enet_get_nextdesc(last_bdp, fep, queue);
skb_tx_timestamp(skb);
- fep->cur_tx = bdp;
+ txq->cur_tx = bdp;
/* Trigger transmission start */
- writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+ writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
return 0;
}
static int
-fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
- struct bufdesc *bdp, int index, char *data,
- int size, bool last_tcp, bool is_last)
+fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb,
+ struct net_device *ndev,
+ struct bufdesc *bdp, int index, char *data,
+ int size, bool last_tcp, bool is_last)
{
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
@@ -600,8 +622,8 @@ fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
if (((unsigned long) data) & FEC_ALIGNMENT ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
- memcpy(fep->tx_bounce[index], data, size);
- data = fep->tx_bounce[index];
+ memcpy(txq->tx_bounce[index], data, size);
+ data = txq->tx_bounce[index];
if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
swap_buffer(data, size);
@@ -640,8 +662,9 @@ fec_enet_txq_put_data_tso(struct sk_buff *skb, struct net_device *ndev,
}
static int
-fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
- struct bufdesc *bdp, int index)
+fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq,
+ struct sk_buff *skb, struct net_device *ndev,
+ struct bufdesc *bdp, int index)
{
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
@@ -657,12 +680,12 @@ fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
- bufaddr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
- dmabuf = fep->tso_hdrs_dma + index * TSO_HEADER_SIZE;
+ bufaddr = txq->tso_hdrs + index * TSO_HEADER_SIZE;
+ dmabuf = txq->tso_hdrs_dma + index * TSO_HEADER_SIZE;
if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
- memcpy(fep->tx_bounce[index], skb->data, hdr_len);
- bufaddr = fep->tx_bounce[index];
+ memcpy(txq->tx_bounce[index], skb->data, hdr_len);
+ bufaddr = txq->tx_bounce[index];
if (id_entry->driver_data & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, hdr_len);
@@ -692,17 +715,20 @@ fec_enet_txq_put_hdr_tso(struct sk_buff *skb, struct net_device *ndev,
return 0;
}
-static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
+static int fec_enet_txq_submit_tso(struct fec_enet_priv_tx_q *txq,
+ struct sk_buff *skb,
+ struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
int total_len, data_left;
- struct bufdesc *bdp = fep->cur_tx;
+ struct bufdesc *bdp = txq->cur_tx;
+ unsigned short queue = skb_get_queue_mapping(skb);
struct tso_t tso;
unsigned int index = 0;
int ret;
- if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep)) {
+ if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(fep, txq)) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "NOT enough BD for TSO!\n");
@@ -722,14 +748,14 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
while (total_len > 0) {
char *hdr;
- index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+ index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
total_len -= data_left;
/* prepare packet headers: MAC + IP + TCP */
- hdr = fep->tso_hdrs + index * TSO_HEADER_SIZE;
+ hdr = txq->tso_hdrs + index * TSO_HEADER_SIZE;
tso_build_hdr(skb, hdr, &tso, data_left, total_len == 0);
- ret = fec_enet_txq_put_hdr_tso(skb, ndev, bdp, index);
+ ret = fec_enet_txq_put_hdr_tso(txq, skb, ndev, bdp, index);
if (ret)
goto err_release;
@@ -737,10 +763,13 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
int size;
size = min_t(int, tso.size, data_left);
- bdp = fec_enet_get_nextdesc(bdp, fep);
- index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
- ret = fec_enet_txq_put_data_tso(skb, ndev, bdp, index, tso.data,
- size, size == data_left,
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
+ index = fec_enet_get_bd_index(txq->tx_bd_base,
+ bdp, fep);
+ ret = fec_enet_txq_put_data_tso(txq, skb, ndev,
+ bdp, index,
+ tso.data, size,
+ size == data_left,
total_len == 0);
if (ret)
goto err_release;
@@ -749,17 +778,17 @@ static int fec_enet_txq_submit_tso(struct sk_buff *skb, struct net_device *ndev)
tso_build_data(skb, &tso, size);
}
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue);
}
/* Save skb pointer */
- fep->tx_skbuff[index] = skb;
+ txq->tx_skbuff[index] = skb;
skb_tx_timestamp(skb);
- fep->cur_tx = bdp;
+ txq->cur_tx = bdp;
/* Trigger transmission start */
- writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+ writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue));
return 0;
@@ -773,18 +802,25 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int entries_free;
+ unsigned short queue;
+ struct fec_enet_priv_tx_q *txq;
+ struct netdev_queue *nq;
int ret;
+ queue = skb_get_queue_mapping(skb);
+ txq = fep->tx_queue[queue];
+ nq = netdev_get_tx_queue(ndev, queue);
+
if (skb_is_gso(skb))
- ret = fec_enet_txq_submit_tso(skb, ndev);
+ ret = fec_enet_txq_submit_tso(txq, skb, ndev);
else
- ret = fec_enet_txq_submit_skb(skb, ndev);
+ ret = fec_enet_txq_submit_skb(txq, skb, ndev);
if (ret)
return ret;
- entries_free = fec_enet_get_free_txdesc_num(fep);
- if (entries_free <= fep->tx_stop_threshold)
- netif_stop_queue(ndev);
+ entries_free = fec_enet_get_free_txdesc_num(fep, txq);
+ if (entries_free <= txq->tx_stop_threshold)
+ netif_tx_stop_queue(nq);
return NETDEV_TX_OK;
}
@@ -794,46 +830,51 @@ fec_enet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
static void fec_enet_bd_init(struct net_device *dev)
{
struct fec_enet_private *fep = netdev_priv(dev);
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
struct bufdesc *bdp;
unsigned int i;
/* Initialize the receive buffer descriptors. */
- bdp = fep->rx_bd_base;
- for (i = 0; i < fep->rx_ring_size; i++) {
+ rxq = fep->rx_queue[0];
+ bdp = rxq->rx_bd_base;
+
+ for (i = 0; i < rxq->rx_ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
if (bdp->cbd_bufaddr)
bdp->cbd_sc = BD_ENET_RX_EMPTY;
else
bdp->cbd_sc = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
/* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep);
+ bdp = fec_enet_get_prevdesc(bdp, fep, 0);
bdp->cbd_sc |= BD_SC_WRAP;
- fep->cur_rx = fep->rx_bd_base;
+ rxq->cur_rx = rxq->rx_bd_base;
/* ...and the same for transmit */
- bdp = fep->tx_bd_base;
- fep->cur_tx = bdp;
- for (i = 0; i < fep->tx_ring_size; i++) {
+ txq = fep->tx_queue[0];
+ bdp = txq->tx_bd_base;
+ txq->cur_tx = bdp;
+ for (i = 0; i < txq->tx_ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = 0;
- if (fep->tx_skbuff[i]) {
- dev_kfree_skb_any(fep->tx_skbuff[i]);
- fep->tx_skbuff[i] = NULL;
+ if (txq->tx_skbuff[i]) {
+ dev_kfree_skb_any(txq->tx_skbuff[i]);
+ txq->tx_skbuff[i] = NULL;
}
bdp->cbd_bufaddr = 0;
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
/* Set the last buffer to wrap */
- bdp = fec_enet_get_prevdesc(bdp, fep);
+ bdp = fec_enet_get_prevdesc(bdp, fep, 0);
bdp->cbd_sc |= BD_SC_WRAP;
- fep->dirty_tx = bdp;
+ txq->dirty_tx = bdp;
}
/*
@@ -852,6 +893,8 @@ fec_restart(struct net_device *ndev)
u32 temp_mac[2];
u32 rcntl = OPT_FRAME_SIZE | 0x04;
u32 ecntl = 0x2; /* ETHEREN */
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
/* Whack a reset. We should wait for this. */
writel(1, fep->hwp + FEC_ECNTRL);
@@ -876,19 +919,21 @@ fec_restart(struct net_device *ndev)
fec_enet_bd_init(ndev);
/* Set receive and transmit descriptor base. */
- writel(fep->bd_dma, fep->hwp + FEC_R_DES_START);
+ rxq = fep->rx_queue[0];
+ writel(rxq->bd_dma, fep->hwp + FEC_R_DES_START(0));
if (fep->bufdesc_ex)
- writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc_ex)
- * fep->rx_ring_size, fep->hwp + FEC_X_DES_START);
+ writel((unsigned long)rxq->bd_dma + sizeof(struct bufdesc_ex)
+ * rxq->rx_ring_size, fep->hwp + FEC_X_DES_START(0));
else
- writel((unsigned long)fep->bd_dma + sizeof(struct bufdesc)
- * fep->rx_ring_size, fep->hwp + FEC_X_DES_START);
+ writel((unsigned long)rxq->bd_dma + sizeof(struct bufdesc)
+ * rxq->rx_ring_size, fep->hwp + FEC_X_DES_START(0));
+ txq = fep->tx_queue[0];
for (i = 0; i <= TX_RING_MOD_MASK; i++) {
- if (fep->tx_skbuff[i]) {
- dev_kfree_skb_any(fep->tx_skbuff[i]);
- fep->tx_skbuff[i] = NULL;
+ if (txq->tx_skbuff[i]) {
+ dev_kfree_skb_any(txq->tx_skbuff[i]);
+ txq->tx_skbuff[i] = NULL;
}
}
@@ -1012,7 +1057,7 @@ fec_restart(struct net_device *ndev)
/* And last, enable the transmit and receive processing */
writel(ecntl, fep->hwp + FEC_ECNTRL);
- writel(0, fep->hwp + FEC_R_DES_ACTIVE);
+ writel(0, fep->hwp + FEC_R_DES_ACTIVE(0));
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
@@ -1097,37 +1142,45 @@ fec_enet_hwtstamp(struct fec_enet_private *fep, unsigned ts,
}
static void
-fec_enet_tx(struct net_device *ndev)
+fec_enet_tx_queue(struct net_device *ndev, u16 queue_id)
{
struct fec_enet_private *fep;
struct bufdesc *bdp;
unsigned short status;
struct sk_buff *skb;
+ struct fec_enet_priv_tx_q *txq;
+ struct netdev_queue *nq;
int index = 0;
int entries_free;
fep = netdev_priv(ndev);
- bdp = fep->dirty_tx;
+
+ queue_id = FEC_ENET_GET_QUQUE(queue_id);
+
+ txq = fep->tx_queue[queue_id];
+ /* get next bdp of dirty_tx */
+ nq = netdev_get_tx_queue(ndev, queue_id);
+ bdp = txq->dirty_tx;
/* get next bdp of dirty_tx */
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
while (((status = bdp->cbd_sc) & BD_ENET_TX_READY) == 0) {
/* current queue is empty */
- if (bdp == fep->cur_tx)
+ if (bdp == txq->cur_tx)
break;
- index = fec_enet_get_bd_index(fep->tx_bd_base, bdp, fep);
+ index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
- skb = fep->tx_skbuff[index];
- fep->tx_skbuff[index] = NULL;
- if (!IS_TSO_HEADER(fep, bdp->cbd_bufaddr))
+ skb = txq->tx_skbuff[index];
+ txq->tx_skbuff[index] = NULL;
+ if (!IS_TSO_HEADER(txq, bdp->cbd_bufaddr))
dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
bdp->cbd_datlen, DMA_TO_DEVICE);
bdp->cbd_bufaddr = 0;
if (!skb) {
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
continue;
}
@@ -1169,23 +1222,37 @@ fec_enet_tx(struct net_device *ndev)
/* Free the sk buffer associated with this last transmit */
dev_kfree_skb_any(skb);
- fep->dirty_tx = bdp;
+ txq->dirty_tx = bdp;
/* Update pointer to next buffer descriptor to be transmitted */
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
/* Since we have freed up a buffer, the ring is no longer full
*/
if (netif_queue_stopped(ndev)) {
- entries_free = fec_enet_get_free_txdesc_num(fep);
- if (entries_free >= fep->tx_wake_threshold)
- netif_wake_queue(ndev);
+ entries_free = fec_enet_get_free_txdesc_num(fep, txq);
+ if (entries_free >= txq->tx_wake_threshold)
+ netif_tx_wake_queue(nq);
}
}
/* ERR006538: Keep the transmitter going */
- if (bdp != fep->cur_tx && readl(fep->hwp + FEC_X_DES_ACTIVE) == 0)
- writel(0, fep->hwp + FEC_X_DES_ACTIVE);
+ if (bdp != txq->cur_tx &&
+ readl(fep->hwp + FEC_X_DES_ACTIVE(queue_id)) == 0)
+ writel(0, fep->hwp + FEC_X_DES_ACTIVE(queue_id));
+}
+
+static void
+fec_enet_tx(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ u16 queue_id;
+ /* First process class A queue, then Class B and Best Effort queue */
+ for_each_set_bit(queue_id, &fep->work_tx, FEC_ENET_MAX_TX_QS) {
+ clear_bit(queue_id, &fep->work_tx);
+ fec_enet_tx_queue(ndev, queue_id);
+ }
+ return;
}
/* During a receive, the cur_rx points to the current incoming buffer.
@@ -1194,11 +1261,12 @@ fec_enet_tx(struct net_device *ndev)
* effectively tossing the packet.
*/
static int
-fec_enet_rx(struct net_device *ndev, int budget)
+fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
{
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
platform_get_device_id(fep->pdev);
+ struct fec_enet_priv_rx_q *rxq;
struct bufdesc *bdp;
unsigned short status;
struct sk_buff *skb;
@@ -1213,11 +1281,13 @@ fec_enet_rx(struct net_device *ndev, int budget)
#ifdef CONFIG_M532x
flush_cache_all();
#endif
+ queue_id = FEC_ENET_GET_QUQUE(queue_id);
+ rxq = fep->rx_queue[queue_id];
/* First, grab all of the stats for the incoming packet.
* These get messed up if we get called due to a busy condition.
*/
- bdp = fep->cur_rx;
+ bdp = rxq->cur_rx;
while (!((status = bdp->cbd_sc) & BD_ENET_RX_EMPTY)) {
@@ -1231,7 +1301,6 @@ fec_enet_rx(struct net_device *ndev, int budget)
if ((status & BD_ENET_RX_LAST) == 0)
netdev_err(ndev, "rcv is not +last\n");
- writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
/* Check for errors. */
if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
@@ -1264,8 +1333,8 @@ fec_enet_rx(struct net_device *ndev, int budget)
pkt_len = bdp->cbd_datlen;
ndev->stats.rx_bytes += pkt_len;
- index = fec_enet_get_bd_index(fep->rx_bd_base, bdp, fep);
- data = fep->rx_skbuff[index]->data;
+ index = fec_enet_get_bd_index(rxq->rx_bd_base, bdp, fep);
+ data = rxq->rx_skbuff[index]->data;
dma_sync_single_for_cpu(&fep->pdev->dev, bdp->cbd_bufaddr,
FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
@@ -1280,7 +1349,7 @@ fec_enet_rx(struct net_device *ndev, int budget)
/* If this is a VLAN packet remove the VLAN Tag */
vlan_packet_rcvd = false;
if ((ndev->features & NETIF_F_HW_VLAN_CTAG_RX) &&
- fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) {
+ fep->bufdesc_ex && (ebdp->cbd_esc & BD_ENET_RX_VLAN)) {
/* Push and remove the vlan tag */
struct vlan_hdr *vlan_header =
(struct vlan_hdr *) (data + ETH_HLEN);
@@ -1308,7 +1377,7 @@ fec_enet_rx(struct net_device *ndev, int budget)
skb_copy_to_linear_data(skb, data, (2 * ETH_ALEN));
if (vlan_packet_rcvd)
payload_offset = (2 * ETH_ALEN) + VLAN_HLEN;
- skb_copy_to_linear_data_offset(skb, (2 * ETH_ALEN),
+ skb_copy_to_linear_data_offset(skb, (2 * ETH_ALEN),
data + payload_offset,
pkt_len - 4 - (2 * ETH_ALEN));
@@ -1357,19 +1426,48 @@ rx_processing_done:
}
/* Update BD pointer to next entry */
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, queue_id);
/* Doing this here will keep the FEC running while we process
* incoming frames. On a heavily loaded network, we should be
* able to keep up at the expense of system resources.
*/
- writel(0, fep->hwp + FEC_R_DES_ACTIVE);
+ writel(0, fep->hwp + FEC_R_DES_ACTIVE(queue_id));
}
- fep->cur_rx = bdp;
+ rxq->cur_rx = bdp;
+ return pkt_received;
+}
+static int
+fec_enet_rx(struct net_device *ndev, int budget)
+{
+ int pkt_received = 0;
+ u16 queue_id;
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ for_each_set_bit(queue_id, &fep->work_rx, FEC_ENET_MAX_RX_QS) {
+ clear_bit(queue_id, &fep->work_rx);
+ pkt_received += fec_enet_rx_queue(ndev,
+ budget - pkt_received, queue_id);
+ }
return pkt_received;
}
+static bool
+fec_enet_collect_events(struct fec_enet_private *fep, uint int_events)
+{
+ if (int_events == 0)
+ return false;
+
+ if (int_events & FEC_ENET_RXF)
+ fep->work_rx |= (1 << 2);
+
+ if (int_events & FEC_ENET_TXF)
+ fep->work_tx |= (1 << 2);
+
+ return true;
+}
+
static irqreturn_t
fec_enet_interrupt(int irq, void *dev_id)
{
@@ -1381,6 +1479,7 @@ fec_enet_interrupt(int irq, void *dev_id)
int_events = readl(fep->hwp + FEC_IEVENT);
writel(int_events & ~napi_mask, fep->hwp + FEC_IEVENT);
+ fec_enet_collect_events(fep, int_events);
if (int_events & napi_mask) {
ret = IRQ_HANDLED;
@@ -2132,25 +2231,29 @@ static void fec_enet_free_buffers(struct net_device *ndev)
unsigned int i;
struct sk_buff *skb;
struct bufdesc *bdp;
-
- bdp = fep->rx_bd_base;
- for (i = 0; i < fep->rx_ring_size; i++) {
- skb = fep->rx_skbuff[i];
- fep->rx_skbuff[i] = NULL;
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
+
+ rxq = fep->rx_queue[0];
+ bdp = rxq->rx_bd_base;
+ for (i = 0; i < rxq->rx_ring_size; i++) {
+ skb = rxq->rx_skbuff[i];
+ rxq->rx_skbuff[i] = NULL;
if (skb) {
dma_unmap_single(&fep->pdev->dev, bdp->cbd_bufaddr,
FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
dev_kfree_skb(skb);
}
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
- bdp = fep->tx_bd_base;
- for (i = 0; i < fep->tx_ring_size; i++) {
- kfree(fep->tx_bounce[i]);
- fep->tx_bounce[i] = NULL;
- skb = fep->tx_skbuff[i];
- fep->tx_skbuff[i] = NULL;
+ txq = fep->tx_queue[0];
+ bdp = txq->tx_bd_base;
+ for (i = 0; i < txq->tx_ring_size; i++) {
+ kfree(txq->tx_bounce[i]);
+ txq->tx_bounce[i] = NULL;
+ skb = txq->tx_skbuff[i];
+ txq->tx_skbuff[i] = NULL;
dev_kfree_skb(skb);
}
}
@@ -2161,9 +2264,12 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
unsigned int i;
struct sk_buff *skb;
struct bufdesc *bdp;
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
- bdp = fep->rx_bd_base;
- for (i = 0; i < fep->rx_ring_size; i++) {
+ rxq = fep->rx_queue[0];
+ bdp = rxq->rx_bd_base;
+ for (i = 0; i < rxq->rx_ring_size; i++) {
dma_addr_t addr;
skb = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
@@ -2179,7 +2285,7 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
goto err_alloc;
}
- fep->rx_skbuff[i] = skb;
+ rxq->rx_skbuff[i] = skb;
bdp->cbd_bufaddr = addr;
bdp->cbd_sc = BD_ENET_RX_EMPTY;
@@ -2188,17 +2294,18 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
ebdp->cbd_esc = BD_ENET_RX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep);
+ bdp = fec_enet_get_prevdesc(bdp, fep, 0);
bdp->cbd_sc |= BD_SC_WRAP;
- bdp = fep->tx_bd_base;
- for (i = 0; i < fep->tx_ring_size; i++) {
- fep->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
- if (!fep->tx_bounce[i])
+ txq = fep->tx_queue[0];
+ bdp = txq->tx_bd_base;
+ for (i = 0; i < txq->tx_ring_size; i++) {
+ txq->tx_bounce[i] = kmalloc(FEC_ENET_TX_FRSIZE, GFP_KERNEL);
+ if (!txq->tx_bounce[i])
goto err_alloc;
bdp->cbd_sc = 0;
@@ -2209,11 +2316,11 @@ static int fec_enet_alloc_buffers(struct net_device *ndev)
ebdp->cbd_esc = BD_ENET_TX_INT;
}
- bdp = fec_enet_get_nextdesc(bdp, fep);
+ bdp = fec_enet_get_nextdesc(bdp, fep, 0);
}
/* Set the last buffer to wrap. */
- bdp = fec_enet_get_prevdesc(bdp, fep);
+ bdp = fec_enet_get_prevdesc(bdp, fep, 0);
bdp->cbd_sc |= BD_SC_WRAP;
return 0;
@@ -2252,7 +2359,8 @@ fec_enet_open(struct net_device *ndev)
fec_restart(ndev);
napi_enable(&fep->napi);
phy_start(fep->phy_dev);
- netif_start_queue(ndev);
+ netif_tx_start_all_queues(ndev);
+
return 0;
}
@@ -2426,7 +2534,7 @@ static int fec_set_features(struct net_device *netdev,
/* Resume the device after updates */
if (netif_running(netdev) && changed & FEATURES_NEED_QUIESCE) {
fec_restart(netdev);
- netif_wake_queue(netdev);
+ netif_tx_wake_all_queues(netdev);
netif_tx_unlock_bh(netdev);
napi_enable(&fep->napi);
}
@@ -2434,10 +2542,17 @@ static int fec_set_features(struct net_device *netdev,
return 0;
}
+u16 fec_enet_select_queue(struct net_device *ndev, struct sk_buff *skb,
+ void *accel_priv, select_queue_fallback_t fallback)
+{
+ return skb_tx_hash(ndev, skb);
+}
+
static const struct net_device_ops fec_netdev_ops = {
.ndo_open = fec_enet_open,
.ndo_stop = fec_enet_close,
.ndo_start_xmit = fec_enet_start_xmit,
+ .ndo_select_queue = fec_enet_select_queue,
.ndo_set_rx_mode = set_multicast_list,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
@@ -2459,39 +2574,60 @@ static int fec_enet_init(struct net_device *ndev)
struct fec_enet_private *fep = netdev_priv(ndev);
const struct platform_device_id *id_entry =
platform_get_device_id(fep->pdev);
+ struct fec_enet_priv_tx_q *txq;
+ struct fec_enet_priv_rx_q *rxq;
struct bufdesc *cbd_base;
+ dma_addr_t bd_dma;
int bd_size;
- /* init the tx & rx ring size */
- fep->tx_ring_size = TX_RING_SIZE;
- fep->rx_ring_size = RX_RING_SIZE;
+ txq = kzalloc(sizeof(*txq), GFP_KERNEL);
+ if (!txq)
+ return -ENOMEM;
+ fep->tx_queue[0] = txq;
+
+ rxq = kzalloc(sizeof(*rxq), GFP_KERNEL);
+ if (!rxq) {
+ kfree(txq);
+ return -ENOMEM;
+ }
+
+ fep->rx_queue[0] = rxq;
- fep->tx_stop_threshold = FEC_MAX_SKB_DESCS;
- fep->tx_wake_threshold = (fep->tx_ring_size - fep->tx_stop_threshold) / 2;
+
+ txq->tx_ring_size = TX_RING_SIZE;
+ rxq->rx_ring_size = RX_RING_SIZE;
+ fep->total_tx_ring_size = txq->tx_ring_size;
+ fep->total_rx_ring_size = rxq->rx_ring_size;
+
+ txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
+ txq->tx_wake_threshold = (txq->tx_ring_size - txq->tx_stop_threshold) / 2;
if (fep->bufdesc_ex)
fep->bufdesc_size = sizeof(struct bufdesc_ex);
else
fep->bufdesc_size = sizeof(struct bufdesc);
- bd_size = (fep->tx_ring_size + fep->rx_ring_size) *
+ bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) *
fep->bufdesc_size;
/* Allocate memory for buffer descriptors. */
- cbd_base = dma_alloc_coherent(NULL, bd_size, &fep->bd_dma,
+ cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
GFP_KERNEL);
- if (!cbd_base)
+ if (!cbd_base) {
+ kfree(rxq);
+ kfree(txq);
return -ENOMEM;
+ }
- fep->tso_hdrs = dma_alloc_coherent(NULL, fep->tx_ring_size * TSO_HEADER_SIZE,
- &fep->tso_hdrs_dma, GFP_KERNEL);
- if (!fep->tso_hdrs) {
- dma_free_coherent(NULL, bd_size, cbd_base, fep->bd_dma);
+ txq->tso_hdrs = dma_alloc_coherent(NULL, txq->tx_ring_size * TSO_HEADER_SIZE,
+ &txq->tso_hdrs_dma, GFP_KERNEL);
+ if (!txq->tso_hdrs) {
+ kfree(rxq);
+ kfree(txq);
+ dma_free_coherent(NULL, bd_size, cbd_base, bd_dma);
return -ENOMEM;
}
- memset(cbd_base, 0, PAGE_SIZE);
-
- fep->netdev = ndev;
+ memset(cbd_base, 0, bd_size);
/* Get the Ethernet address */
fec_get_mac(ndev);
@@ -2499,12 +2635,13 @@ static int fec_enet_init(struct net_device *ndev)
fec_set_mac_address(ndev, NULL);
/* Set receive and transmit descriptor base. */
- fep->rx_bd_base = cbd_base;
+ rxq->rx_bd_base = cbd_base;
if (fep->bufdesc_ex)
- fep->tx_bd_base = (struct bufdesc *)
- (((struct bufdesc_ex *)cbd_base) + fep->rx_ring_size);
+ txq->tx_bd_base = (struct bufdesc *)
+ (((struct bufdesc_ex *)cbd_base) + rxq->rx_ring_size);
else
- fep->tx_bd_base = cbd_base + fep->rx_ring_size;
+ txq->tx_bd_base = cbd_base + rxq->rx_ring_size;
+
/* The FEC Ethernet specific entries in the device structure */
ndev->watchdog_timeo = TX_TIMEOUT;
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 02/12] net:fec: add enet AVB feature macro define for imx6sx
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Fugang Duan, Frank Li
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Add enet AVB feature macro define for imx6sx.
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec_main.c | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c21ecff1..ee9f04f 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -104,6 +104,16 @@ static void set_multicast_list(struct net_device *ndev);
* ENET_TDAR[TDAR].
*/
#define FEC_QUIRK_ERR006358 (1 << 7)
+/* ENET IP hw AVB
+ *
+ * i.MX6SX ENET IP add Audio Video Bridging (AVB) feature support.
+ * - Two class indicators on receive with configurable priority
+ * - Two class indicators and line speed timer on transmit allowing
+ * implementation class credit based shapers externally
+ * - Additional DMA registers provisioned to allow managing up to 3
+ * independent rings
+ */
+#define FEC_QUIRK_HAS_AVB (1 << 8)
static struct platform_device_id fec_devtype[] = {
{
@@ -128,6 +138,12 @@ static struct platform_device_id fec_devtype[] = {
.name = "mvf600-fec",
.driver_data = FEC_QUIRK_ENET_MAC,
}, {
+ .name = "imx6sx-fec",
+ .driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
+ FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
+ FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
+ FEC_QUIRK_HAS_AVB,
+ }, {
/* sentinel */
}
};
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 01/12] net:fec: add enet refrence clock for i.MX 6SX chip
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Fugang Duan, Frank Li
In-Reply-To: <1410373813-5731-1-git-send-email-yes>
From: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
i.MX6sx enet has below clocks for user config:
clk_ipg: ipg_clk_s, ipg_clk_mac0_s, 66Mhz
clk_ahb: enet system clock, it is enet AXI clock for imx6sx.
For imx6sx, it alos is the clock source of interrupt coalescing.
The clock range: 200Mhz ~ 266Mhz.
clk_ref: refrence clock for tx and rx. For imx6sx enet RGMII mode,
the refrence clock is 125Mhz coming from internal PLL or external.
In i.MX6sx-arm2 board, the clock is from internal PLL.
clk_ref is optional, depends on board.
clk_enet_out: The clock can be output from internal PLL. It can supply 50Mhz
clock for phy. clk_enet_out is optional, depends on chip and board.
clk_ptp: 1588 ts clock. It is optional, depends on chip.
The patch add clk_ref to distiguish the different clocks.
Signed-off-by: Fugang Duan <B38611-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
Signed-off-by: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
---
drivers/net/ethernet/freescale/fec.h | 1 +
drivers/net/ethernet/freescale/fec_main.c | 17 +++++++++++++++++
2 files changed, 18 insertions(+)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index ee41d98..635772b 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -272,6 +272,7 @@ struct fec_enet_private {
struct clk *clk_ipg;
struct clk *clk_ahb;
+ struct clk *clk_ref;
struct clk *clk_enet_out;
struct clk *clk_ptp;
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 89355a7..c21ecff1 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1621,6 +1621,11 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
}
mutex_unlock(&fep->ptp_clk_mutex);
}
+ if (fep->clk_ref) {
+ ret = clk_prepare_enable(fep->clk_ref);
+ if (ret)
+ goto failed_clk_ref;
+ }
} else {
clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
@@ -1632,9 +1637,15 @@ static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
fep->ptp_clk_on = false;
mutex_unlock(&fep->ptp_clk_mutex);
}
+ if (fep->clk_ref)
+ clk_disable_unprepare(fep->clk_ref);
}
return 0;
+
+failed_clk_ref:
+ if (fep->clk_ref)
+ clk_disable_unprepare(fep->clk_ref);
failed_clk_ptp:
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
@@ -2637,6 +2648,12 @@ fec_probe(struct platform_device *pdev)
fep->ptp_clk_on = false;
mutex_init(&fep->ptp_clk_mutex);
+
+ /* clk_ref is optional, depends on board */
+ fep->clk_ref = devm_clk_get(&pdev->dev, "enet_clk_ref");
+ if (IS_ERR(fep->clk_ref))
+ fep->clk_ref = NULL;
+
fep->clk_ptp = devm_clk_get(&pdev->dev, "ptp");
fep->bufdesc_ex =
pdev->id_entry->driver_data & FEC_QUIRK_HAS_BUFDESC_EX;
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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 v3 net-next 00/12] net: fec: imx6sx multiqueue support
From: yes-KgLukfWpBlCctlrPMvKcciBecyulp+rMXqFh9Ls21Oc @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611-KZfg59tc24xl57MIdRCFDg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
netdev-u79uwXL29TY76Z2rM5mHXA, lznuaa-Re5JQEeQqe8AvxtiuMwx3w
Cc: shawn.guo-QSEj5FYQhm4dnm+yROfE0A,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
devicetree-u79uwXL29TY76Z2rM5mHXA, linux-lFZ/pmaqli7XmaaqVzeoHQ,
Frank Li
From: Frank Li <Frank.Li-KZfg59tc24xl57MIdRCFDg@public.gmane.org>
These patches enable i.MX6SX multi queue support.
i.MX6SX support 3 queue and AVB feature.
Change from v2 to v3
- fixed alignment requirement for ARM and NO-ARM platform
Change from v1 to v2.
- Change num_tx_queue to unsigned int
- Avoid block non-dt platform
- remove call netif_set_real_num_rx_queues
- seperate multi queue patch two part, one is tx and rx handle, with fixed queue 0
then other one is initilized multiqueue
- use two difference alignment for tx and rx path
Frank Li (4):
net: fec: init multi queue date structure
net: fec: add enet-avb IP support
ARM: Documentation: Update fec dts binding doc
ARM: dts: imx6sx: add multi-queue support enet
Fugang Duan (8):
net:fec: add enet refrence clock for i.MX 6SX chip
net:fec: add enet AVB feature macro define for imx6sx
net: fec: change data structure to support multiqueue
net: fec: parser max queue number from dt file
net:fec: Disable enet-avb MAC instead of reset MAC
net:fec: Add fsl,imx6sx-fec compatible strings
net: fec: change FEC alignment according to i.mx6 sx requirement
net: fec: init complete variable in early to avoid kernel dump
Documentation/devicetree/bindings/net/fsl-fec.txt | 6 +
arch/arm/boot/dts/imx6sx.dtsi | 2 +
drivers/net/ethernet/freescale/fec.h | 154 +++-
drivers/net/ethernet/freescale/fec_main.c | 853 ++++++++++++++++------
4 files changed, 756 insertions(+), 259 deletions(-)
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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
* Re: [PATCH v11 net-next 00/12] eBPF syscall, verifier, testsuite
From: Andy Lutomirski @ 2014-09-10 18:22 UTC (permalink / raw)
To: Alexei Starovoitov
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Steven Rostedt,
Daniel Borkmann, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development,
linux-kernel@vger.kernel.org
In-Reply-To: <1410325808-3657-1-git-send-email-ast@plumgrid.com>
On Tue, Sep 9, 2014 at 10:09 PM, Alexei Starovoitov <ast@plumgrid.com> wrote:
> Hi David,
>
> I've managed to reduce this set to 12:
> Patches 1-4 establish BPF syscall shell for maps and programs.
> Patches 5-10 add verifier step by step
> Patch 11 exposes existing instruction macros to user space
> Patch 12 adds test stubs and verifier testsuite from user space
>
> I don't know how to reduce it further. Drop verifier and
> have programs loaded without verification? Sounds wrong.
> If anyone has other ideas, I'll gladly reduce it further.
>
> Note that patches 1,3,4,7 add commands and attributes to the syscall
> while being backwards compatible from each other, which should demonstrate
> how other commands can be added in the future.
>
> Daniel,
> bpf_common.h patch (that we discussed earlier) I didn't include here
> to reduce the number of patches. It can come next.
>
> For those who have looked at the last set of 28 patches, the difference is:
> - moved attaching to tracing and sockets to future patches
> - moved hash table map type implementation to future
> - split verifier further and moved LD_ABS checks and state prunning to future
> - instead of running verifier testsuite on real tracing programs added
> test_stub.c with fake maps, context and helper functions to test verifier only
> - rebased
>
> Note, after this set the programs can be loaded for testing only. They cannot
> be attached to any events. This will come in the next set.
>
> As requested by Andy and others, here is the man page:
>
> BPF(2) Linux Programmer's Manual BPF(2)
>
>
>
> NAME
> bpf - perform a command on eBPF map or program
>
> SYNOPSIS
> #include <linux/bpf.h>
>
> int bpf(int cmd, union bpf_attr *attr, unsigned int size);
>
>
> DESCRIPTION
> bpf() syscall is a multiplexor for a range of different operations on
> eBPF which can be characterized as "universal in-kernel virtual
> machine". eBPF is similar to original Berkeley Packet Filter (or "clas-
> sic BPF") used to filter network packets. Both statically analyze the
> programs before loading them into the kernel to ensure that programs
> cannot harm the running system.
>
> eBPF extends classic BPF in multiple ways including ability to call in-
> kernel helper functions and access shared data structures like eBPF
> maps. The programs can be written in a restricted C that is compiled
> into eBPF bytecode and executed on the eBPF virtual machine or JITed
> into native instruction set.
>
> eBPF Design/Architecture
> eBPF maps is a generic storage of different types. User process can
> create multiple maps (with key/value being opaque bytes of data) and
> access them via file descriptor. In parallel eBPF programs can access
> maps from inside the kernel. It's up to user process and eBPF program
> to decide what they store inside maps.
>
> eBPF programs are similar to kernel modules. They are loaded by the
> user process and automatically unloaded when process exits. Each eBPF
> program is a safe run-to-completion set of instructions. eBPF verifier
> statically determines that the program terminates and is safe to exe-
> cute. During verification the program takes a hold of maps that it
> intends to use, so selected maps cannot be removed until the program is
> unloaded. The program can be attached to different events. These events
> can be packets, tracepoint events and other types in the future. A new
> event triggers execution of the program which may store information
> about the event in the maps. Beyond storing data the programs may call
> into in-kernel helper functions which may, for example, dump stack, do
> trace_printk or other forms of live kernel debugging. The same program
> can be attached to multiple events. Different programs can access the
> same map:
> tracepoint tracepoint tracepoint sk_buff sk_buff
> event A event B event C on eth0 on eth1
> | | | | |
> | | | | |
> --> tracing <-- tracing socket socket
> prog_1 prog_2 prog_3 prog_4
> | | | |
> |--- -----| |-------| map_3
> map_1 map_2
>
> Syscall Arguments
> bpf() syscall operation is determined by cmd which can be one of the
> following:
>
> BPF_MAP_CREATE
> Create a map with given type and attributes and return map FD
>
> BPF_MAP_LOOKUP_ELEM
> Lookup element by key in a given map and return its value
>
> BPF_MAP_UPDATE_ELEM
> Create or update element (key/value pair) in a given map
>
> BPF_MAP_DELETE_ELEM
> Lookup and delete element by key in a given map
>
> BPF_MAP_GET_NEXT_KEY
> Lookup element by key in a given map and return key of next ele-
> ment
>
> BPF_PROG_LOAD
> Verify and load eBPF program
>
> attr is a pointer to a union of type bpf_attr as defined below.
>
> size is the size of the union.
I find this strange. Why not just make attr be a pointer to the
relevant struct for the operation being invoked?
>
> union bpf_attr {
> struct { /* anonymous struct used by BPF_MAP_CREATE command */
> enum bpf_map_type map_type;
Does this reliably generate the same type on compat systems? C++11
has a fix for enum ABI compatibility, but this is plain C :(
> struct { /* anonymous struct used by BPF_PROG_LOAD command */
> enum bpf_prog_type prog_type;
> __u32 insn_cnt;
> const struct bpf_insn *insns;
> const char *license;
> __u32 log_level; /* verbosity level of eBPF verifier */
> __u32 log_size; /* size of user buffer */
> void *log_buf; /* user supplied buffer */
> };
> };
It might be a bit nicer to have separate in and out arguments.
>
> BPF_MAP_CREATE
> int bpf_create_map(enum bpf_map_type map_type, int key_size,
> int value_size, int max_entries)
> {
> union bpf_attr attr = {
> .map_type = map_type,
> .key_size = key_size,
> .value_size = value_size,
> .max_entries = max_entries
> };
I feel like this is asking for trouble, or at least bizarre namespace
collisions in the anonymous struct members. At least please give the
structs names. (Also, the first time I read this, I assumed that
those were union members, which would have made the code be nonsense.)
>
> BPF_MAP_DELETE_ELEM
> int bpf_delete_elem(int fd, void *key)
> {
> union bpf_attr attr = {
> .map_fd = fd,
> .key = key,
> };
>
> return bpf(BPF_MAP_DELETE_ELEM, &attr, sizeof(attr));
> }
> The call deletes an element in a map fd with given key.
What does it return? (The same question goes for a bunch of the map ops.)
>
> eBPF programs
> BPF_PROG_LOAD
> This cmd is used to load eBPF program into the kernel.
>
> char bpf_log_buf[LOG_BUF_SIZE];
What happens if the size isn't LOG_BUF_SIZE?
>
> int bpf_prog_load(enum bpf_prog_type prog_type,
> const struct bpf_insn *insns, int insn_cnt,
> const char *license)
> {
> union bpf_attr attr = {
> .prog_type = prog_type,
> .insns = insns,
> .insn_cnt = insn_cnt,
> .license = license,
> .log_buf = bpf_log_buf,
> .log_size = LOG_BUF_SIZE,
> .log_level = 1,
> };
>
> return bpf(BPF_PROG_LOAD, &attr, sizeof(attr));
> }
> prog_type one of the available program types:
> enum bpf_prog_type {
> BPF_PROG_TYPE_UNSPEC,
> BPF_PROG_TYPE_SOCKET_FILTER,
> BPF_PROG_TYPE_TRACING_FILTER,
> };
Why does the type matter?
> {
> static struct bpf_insn prog[] = {
> BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
> BPF_LD_ABS(BPF_B, 14 + 9 /* R0 = ip->proto */),
> BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
> BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
> BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
> BPF_LD_MAP_FD(BPF_REG_1, 0),
> BPF_CALL_FUNC(BPF_FUNC_map_lookup_elem),
> BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
> BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
> BPF_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
> BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */
> BPF_EXIT_INSN(),
> };
> int sock, map_fd, prog_fd, key;
> long long value = 0, tcp_cnt, udp_cnt;
>
> map_fd = bpf_create_map(BPF_MAP_TYPE_HASH, sizeof(key), sizeof(value), 2);
> if (map_fd < 0) {
> printf("failed to create map '%s'\n", strerror(errno));
> /* likely not run as root */
> return 1;
> }
>
> key = 6; /* tcp */
> assert(bpf_update_elem(map_fd, &key, &value) == 0);
>
> key = 17; /* udp */
> assert(bpf_update_elem(map_fd, &key, &value) == 0);
>
> prog[5].imm = map_fd;
This (the .imm thing) is sufficiently weird that I think it needs to
be mentioned in the main docs, not just in an example. It's
especially odd since AFAIK essentially every other object format in
the world uses a separate relocation table instead of inline magic
opcodes like this.
>
> All other commands
> Zero.
Shouldn't delete return different values depending on whether anything
was deleted?
>
> ENOENT For BPF_MAP_LOOKUP_ELEM or BPF_MAP_DELETE_ELEM, indicates that
> element with given key was not found.
Ah, here it is. Please document this with the ops.
>
> E2BIG program is too large.
>
> NOTES
> These commands may be used only by a privileged process (one having the
> CAP_SYS_ADMIN capability).
I hope this goes away :)
I can't shake the feeling that the whole syscall map API is wrong and
that, instead, there should be a more general concept of objects
provided by the eBPF runtime. Those objects could have methods that
are callable by the syscall and callable from eBPF code.
--Andy
^ permalink raw reply
* Re: [PATCH v11 net-next 11/12] net: filter: move eBPF instruction macros
From: Alexei Starovoitov @ 2014-09-10 18:16 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <54103506.1030501-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Wed, Sep 10, 2014 at 4:24 AM, Daniel Borkmann <dborkman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
> On 09/10/2014 07:10 AM, Alexei Starovoitov wrote:
>>
>> move instruction macros (like BPF_MOV64_REG or BPF_ALU32_IMM)
>> from linux/filter.h into uapi/linux/bpf.h
>> so that userspace programs can use them.
>>
>> verifier testsuite (in later patches) will be using them.
>>
>> Signed-off-by: Alexei Starovoitov <ast-uqk4Ao+rVK5Wk0Htik3J/w@public.gmane.org>
>
>
> I don't think we need this commit at all. These macros are not really
> part of the ABI and we should expose __as less as possible__, otherwise
> we won't be able to alter them anymore. Plus, based on your previous
> argumentation regarding the header file expose, we also won't be able
> to add any new macros anymore since you could run into name collisions.
>
> Anyway, I don't see a reason why a e.g. central user space eBPF library
> cannot live with, for example, a private copy of these helper macros or
> whatever it wants to define by itself.
>
> I know in classic BPF there's BPF_STMT() and BPF_JUMP() but it's much
> less complicated than eBPF and less likely to changes.
Interesting idea. Are you saying just copy paste these
226 lines into user libbpf.h for now to use them in testsuite
and examples ? Hmm.
Indeed the less lines we add to uapi the better. I'll do that.
^ permalink raw reply
* Re: [PATCH v11 net-next 12/12] bpf: mini eBPF library, test stubs and verifier testsuite
From: Alexei Starovoitov @ 2014-09-10 18:08 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <54103776.3080706-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Wed, Sep 10, 2014 at 4:35 AM, Daniel Borkmann <dborkman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>
> Since we already have an extensive BPF test suite, that is, lib/test_bpf.c,
> which currently also does sanity checks for the classic BPF verifier, is
> there a reason these verifier test cases cannot be extended/integrated there
> as well but have to go to kernel/bpf/test_stub.c resp.
> samples/bpf/test_verifier.c ?
> I don't like that we put testing code into kernel/bpf/ whereas we already
> have a BPF test infrastructure in the kernel elsewhere.
yes. there is a reason. Verifier needs to be tested from user space,
since it works on fds. Process local map_fd are part of the eBPF
programs. Therefore one is testing things from kernel and
another from userspace. We definitely need both.
Currently there is no use case to call verifier from inside
the kernel. I'm not sure there will be one. Verifier's main
purpose is to check user supplied programs and provide
humans an understandable error messages of what
is 'unsafe' in particular program.
Eventually we will integrate this verifier messages with
program compilation. Like, the user would write a program
in C then invoke a wrapper of compiler and verifier, which
will point to lines in C code which are doing something
wrong like loops or out of bounds access. Currently verifier
complains about particular 'unsafe' instruction, but
humans have hard time correlating asm to C.
^ permalink raw reply
* Re: rtt vs. rcv_rtt ?
From: Eric Dumazet @ 2014-09-10 18:06 UTC (permalink / raw)
To: Robert Engels; +Cc: netdev
In-Reply-To: <CA+q+rD1=ohtL5EkoXkSVS5A5ygop4ev3CoN=HOLNSrTPp7BtiA@mail.gmail.com>
On Wed, 2014-09-10 at 12:15 -0500, Robert Engels wrote:
> When using 'ss', both rtt, and rcv_rtt are reported.
>
> My understanding is that rcv_rtt is an estimate of the receivers rtt ?? Is
> this true? My assumption is that differences in rtt vs. rcv_rtt would be
> due to asymmetric networking connections ???
>
> Here is a sample 'ss' output:
>
> cubic wscale:2,9 rto:437 rtt:101.625/84 ato:40 cwnd:10 ssthresh:15 send
> 991.9Kbps rcv_rtt:18291 rcv_space:151142
>
> Can someone explain why the rcv_rtt would be so much higher than the rtt?
> Is it that the client is not reading the data fast enough? Other reasons?
>
> Thanks so much for your help.
rcv_rtt is not the rtt as you think it is ;)
rtt is the smooth rtt of delays between sent packets and received ACK.
But rcv_rtt is the time to receive one full window.
Its used by DRS (Dynamic Right-Sizing)
Check tcp_rcv_rtt_measure() & tcp_rcv_rtt_update() for details.
^ permalink raw reply
* Generic way to change net namespace for wireless device
From: Vadim Kochan @ 2014-09-10 18:01 UTC (permalink / raw)
To: netdev@vger.kernel.org
Hi All,
I see that setting of network namespace differs for wireless and for
other devices. To change netns for wireless device it is needed to use
nl80211 API. Seems wireless device must have some special way to
change netns, but what if to:
- add new netdev_ops->ndo_set_netns callback
- implement it in net/mac80211/iface.c
- delegate callback from net/mac80211 to net/wireless/core.c ->
cfg80211_switch_netns func.
- in net/core/rtnetlink.c ->do_setlink func check & call
dev->netdev_ops->ndo_set_netns or call
dev_change_net_namespace
Then it will be possible to change netns for wireless device via
RTM_SETLINK.
Regards,
^ permalink raw reply
* rtt vs. rcv_rtt
From: Robert Engels @ 2014-09-10 17:56 UTC (permalink / raw)
To: netdev
When using 'ss', both rtt, and rcv_rtt are reported.
My understanding is that rcv_rtt is an estimate of the receivers rtt
?? Is this true?
My assumption is that differences in rtt vs. rcv_rtt would be due to
asymmetric networking connections ???
Here is a sample 'ss' output:
cubic wscale:2,9 rto:437 rtt:101.625/84 ato:40 cwnd:10 ssthresh:15
send 991.9Kbps rcv_rtt:18291 rcv_space:151142
Can someone explain why the rcv_rtt would be so much higher than the rtt?
Is it that the client is not reading the data fast enough? Other reasons?
Thanks so much for your help.
Robert Engels
^ permalink raw reply
* Re: [PATCH net-next v2] net: bpf: only build bpf_jit_binary_{alloc,free}() when jit selected
From: Cong Wang @ 2014-09-10 17:48 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: David Miller, Fengguang Wu, Alexei Starovoitov, netdev
In-Reply-To: <1410354062-25337-1-git-send-email-dborkman@redhat.com>
On Wed, Sep 10, 2014 at 6:01 AM, Daniel Borkmann <dborkman@redhat.com> wrote:
> Since BPF JIT depends on the availability of module_alloc() and
> module_free() helpers (HAVE_BPF_JIT and MODULES), we better build
> that code only in case we have BPF_JIT in our config enabled, just
> like with other JIT code. Fixes builds for arm/marzen_defconfig
> and sh/rsk7269_defconfig.
It is quite useful to include the build failure in changelog:
kernel/built-in.o: In function `bpf_jit_binary_alloc':
/home/cwang/linux/kernel/bpf/core.c:144: undefined reference to `module_alloc'
kernel/built-in.o: In function `bpf_jit_binary_free':
/home/cwang/linux/kernel/bpf/core.c:164: undefined reference to `module_free'
make: *** [vmlinux] Error 1
^ permalink raw reply
* Re: [PATCH v11 net-next 00/12] eBPF syscall, verifier, testsuite
From: Alexei Starovoitov @ 2014-09-10 17:48 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <541017FD.1030308@redhat.com>
On Wed, Sep 10, 2014 at 2:21 AM, Daniel Borkmann <dborkman@redhat.com> wrote:
>
> When you pass in these structs with pointers in it to other user space
> buffers, how do you handle this with mixed 32/64 bit user/kernel space?
...
> Perhaps I'm missing something, but I think, that would currently break in
> your syscall handler, no?
yes. compat stuff is not part of this diff.
I was thinking to handle it similar to the way signalfd deals with it:
add compat syscall, compat struct and convert it before going into
main entry point.
^ permalink raw reply
* [BUG REPORT] Unencrypted packets after SNAT, allthough IPSEC-Policies are present
From: Konstantinos Kolelis @ 2014-09-10 17:26 UTC (permalink / raw)
To: netdev; +Cc: davem, kuznet, jmorris, yoshfuji, kaber, steffen.klassert,
herbert
Hi all,
i' ve observed a problem with xfrm lookups, SNAT, blackhole route and
missing SAs.
The problem occures with all Kernels above 3.6.x and might has to do
with the changes in
ip4_blackhole_route() function in net/route.c.
Let say you have two network interfaces:
eth0 with ip 172.16.0.10/24
and
eth1 with ip 192.168.0.1/24
and you have done the following configuration:
iptables -t nat -A POSTROUTING -s 192.168.0.0/24 -j SNAT --to-source
172.16.0.10
and
ip xfrm policy add dir out src 172.16.0.10 dst 0.0.0.0/0 tmpl proto esp
src 172.16.0.10 dst 172.31.0.10 mode tunnel
with the following routes:
default via 172.16.0.1 dev eth0 proto static
172.16.0.0/24 dev eth0 proto kernel scope link src 172.16.0.10
192.168.0.0/24 dev eth1 proto kernel scope link src 192.168.0.1
If for what ever reason IPSEC-SAs can not be established, maybe because
172.31.0.10 is down,
the traffic comming from 192.168.0.0/24 will leave unencrypted the
external (eth0) interface.
I can see that the traffic is source-Nated correctly and
xfrm_me_harder() is called.
Also i can see that a xfrm_bundle can not be created so
make_blackhole_route()
and ip4_blackhole_route() is called. But the callback for dst_output()
is never called afterwards.
The following Patch is workaround which restores the expected behavior.
It should work for Kernel 3.6.x and higher.
diff -rupN a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
--- a/net/ipv4/ip_output.c 2014-09-06 01:37:11.000000000 +0200
+++ b/net/ipv4/ip_output.c 2014-09-10 16:27:12.287893706 +0200
@@ -260,6 +260,9 @@ static int ip_finish_output(struct sk_bu
if (skb_dst(skb)->xfrm != NULL) {
IPCB(skb)->flags |= IPSKB_REROUTED;
return dst_output(skb);
+ } else if (skb_dst(skb)->error == -EINVAL) {
+ IPCB(skb)->flags |= IPSKB_REROUTED;
+ return dst_output(skb);
}
#endif
if (skb_is_gso(skb))
diff -rupN a/net/ipv4/route.c b/net/ipv4/route.c
--- a/net/ipv4/route.c 2014-09-06 01:37:11.000000000 +0200
+++ b/net/ipv4/route.c 2014-09-10 16:13:07.179847637 +0200
@@ -2231,6 +2231,7 @@ struct dst_entry *ipv4_blackhole_route(s
struct dst_entry *new = &rt->dst;
new->__use = 1;
+ new->error = -EINVAL;
new->input = dst_discard;
new->output = dst_discard_sk;
Please let me know if you need more details.
Best regards,
Kosta
^ permalink raw reply
* Re: linux-next: build failure after merge of the wireless-next tree
From: John W. Linville @ 2014-09-10 17:46 UTC (permalink / raw)
To: David Miller
Cc: sfr, netdev, linux-next, linux-kernel, herself, linux, geert,
broonie
In-Reply-To: <20140909.163733.1827908634029213952.davem@davemloft.net>
On Tue, Sep 09, 2014 at 04:37:33PM -0700, David Miller wrote:
> From: Stephen Rothwell <sfr@canb.auug.org.au>
> Date: Wed, 10 Sep 2014 09:28:19 +1000
>
> > Hi Dave,
> ...
> > This fix patch is now needed in the net-next tree ...
>
> Applied thanks Stephen.
Doh! Sorry I missed that one...
--
John W. Linville Someday the world will need a hero, and you
linville@tuxdriver.com might be all we have. Be ready.
^ permalink raw reply
* Re: [PATCH v2 4/8] net: pxa168_eth: fix Ethernet flow control status
From: Antoine Tenart @ 2014-09-10 17:44 UTC (permalink / raw)
To: Andrew Lunn
Cc: Antoine Tenart, sebastian.hesselbarth-Re5JQEeQqe8AvxtiuMwx3w,
thomas.petazzoni-wi1+55ScJUtKEb57/3fJTNBPR1lH4CV8,
zmxu-eYqpPyKDWXRBDgjK7y7TUQ, devicetree-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
alexandre.belloni-wi1+55ScJUtKEb57/3fJTNBPR1lH4CV8,
jszhang-eYqpPyKDWXRBDgjK7y7TUQ,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r
In-Reply-To: <20140910153902.GE13342-g2DYL2Zd6BY@public.gmane.org>
Andrew,
On Wed, Sep 10, 2014 at 05:39:02PM +0200, Andrew Lunn wrote:
> On Tue, Sep 09, 2014 at 04:44:04PM +0200, Antoine Tenart wrote:
> > IEEE 802.3x Ethernet flow control is disabled when bit (1 << 2) is set
> > in the port status register. Fix the flow control detection in the link
> > event handling function which was relying on the opposite assumption.
> >
> > Signed-off-by: Antoine Tenart <antoine.tenart-wi1+55ScJUtKEb57/3fJTNBPR1lH4CV8@public.gmane.org>
> > ---
> > drivers/net/ethernet/marvell/pxa168_eth.c | 4 ++--
> > 1 file changed, 2 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c
> > index 953112f87c5f..10422f2df6cc 100644
> > --- a/drivers/net/ethernet/marvell/pxa168_eth.c
> > +++ b/drivers/net/ethernet/marvell/pxa168_eth.c
> > @@ -163,7 +163,7 @@
> > /* Bit definitions for Port status */
> > #define PORT_SPEED_100 (1 << 0)
> > #define FULL_DUPLEX (1 << 1)
> > -#define FLOW_CONTROL_ENABLED (1 << 2)
> > +#define FLOW_CONTROL_DISABLED (1 << 2)
> > #define LINK_UP (1 << 3)
> >
> > /* Bit definitions for work to be done */
> > @@ -885,7 +885,7 @@ static void handle_link_event(struct pxa168_eth_private *pep)
> > speed = 10;
> >
> > duplex = (port_status & FULL_DUPLEX) ? 1 : 0;
> > - fc = (port_status & FLOW_CONTROL_ENABLED) ? 1 : 0;
> > + fc = (port_status & FLOW_CONTROL_DISABLED) ? 0 : 1;
> > netdev_info(dev, "link up, %d Mb/s, %s duplex, flow control %sabled\n",
> > speed, duplex ? "full" : "half", fc ? "en" : "dis");
> > if (!netif_carrier_ok(dev))
>
> Could this be a hardware bug which has been fixed in a newer version
> of the IP? It would be good to have this tested on an old platform
> using this driver.
This driver seems to be used by the pxa168 GuruPlug board, and according
to the pxa168 datasheet the flow control status is reported as above (I
checked before sending this patch). I used the software manual
referenced in Documentation/arm/Marvell/README.
This is also the case for the Ethernet controller of the Berlin SoCs.
I could only test on the Berlin BG2Q. I can't be sure this was not a
hardware bug, but at least this is consistent with the pxa168 platform
using the driver. All other registers controlling this flow control
capability also enable on 0.
Antoine
--
Antoine Ténart, Free Electrons
Embedded Linux, Kernel and Android engineering
http://free-electrons.com
--
To unsubscribe from this list: send the line "unsubscribe devicetree" 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
* Re: [PATCH v11 net-next 00/12] eBPF syscall, verifier, testsuite
From: Alexei Starovoitov @ 2014-09-10 17:32 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <541013CE.6020307-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Wed, Sep 10, 2014 at 2:03 AM, Daniel Borkmann <dborkman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> wrote:
>> struct { /* anonymous struct used by BPF_PROG_LOAD command */
>> enum bpf_prog_type prog_type;
>> __u32 insn_cnt;
>> const struct bpf_insn *insns;
>> const char *license;
>> __u32 log_level; /* verbosity level of
>> eBPF verifier */
>> __u32 log_size; /* size of user buffer */
>> void *log_buf; /* user supplied buffer
>> */
>
>
> What is log buffer? Would that mean the verifier will return an error
> string if the program will not pass it, or if not, what other data?
> I think the man page is missing how to examine the returned verifier
> log buffer data.
yes. it's an error log (as text string for humans) from verifier.
It is briefly explained in the man page:
EACCES For BPF_PROG_LOAD, though program has valid instructions, it was
rejected, since it was deemed unsafe (may access disallowed mem-
ory region or uninitialized stack/register or function con-
straints don't match actual types or misaligned access). In such
case it is recommended to call bpf() again with log_level = 1
and examine log_buf for specific reason provided by verifier.
and there is a whole section about it in
Documentation/networking/filter.txt
called "Understanding eBPF verifier messages".
^ permalink raw reply
* Re: [PATCH v11 net-next 00/12] eBPF syscall, verifier, testsuite
From: Alexei Starovoitov @ 2014-09-10 17:28 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <54100975.6030809@redhat.com>
On Wed, Sep 10, 2014 at 1:19 AM, Daniel Borkmann <dborkman@redhat.com> wrote:
>>
>> In the future maps can have different types: hash, array, bloom
>> filter,
>> radix-tree, but currently only hash type is supported:
>> enum bpf_map_type {
>> BPF_MAP_TYPE_UNSPEC,
>> BPF_MAP_TYPE_HASH,
>> };
>
>
> If we mention them here in the man page, users are going to request
> them, naturally. ;) So I'd just mention what we have, not what we do
> not yet have. But I'm wondering how much library boiler plate only
> for BPF we want to add in future, hopefully not most of what's in
> Corman ... ? ;)
:)
as cover letter says hash type was moved from this set to
later series, so it's implemented.
array and radix-tree are implemented as well, but not ready for
review yet. I have strong use cases for them.
Even two of the simplest examples for tracing (ex2 and ex3)
will benefit from 'array' type.
For bloomfiler type Chema had a strong use case as well.
I was assuming he will implement it sooner or later ;)
But, surely, I can drop future features from the manpage.
^ permalink raw reply
* Re: PTP_PEROUT_REQUEST and clock stepping
From: Richard Cochran @ 2014-09-10 17:26 UTC (permalink / raw)
To: Daniel Glöckner; +Cc: netdev
In-Reply-To: <54107965.6040007@emlix.com>
On Wed, Sep 10, 2014 at 06:16:37PM +0200, Daniel Glöckner wrote:
> Hi,
> I was wondering how periodic output is supposed to behave if the clock
> is stepped from a time after ptp_perout_request.start to a time before
> ptp_perout_request.start.
I would say the result is undefined.
User space should first stop the periodic output, then reprogram the
clock, then restart the periodic output. Anything else makes no sense
at all.
Thanks,
Richard
^ permalink raw reply
* Re: [PATCH] Documentation: filter: Add MIPS to architectures with BPF JIT
From: Alexei Starovoitov @ 2014-09-10 17:23 UTC (permalink / raw)
To: Markos Chandras
Cc: Network Development, Randy Dunlap, David S. Miller,
Daniel Borkmann, linux-doc, LKML
In-Reply-To: <1410357104-30490-1-git-send-email-markos.chandras@imgtec.com>
On Wed, Sep 10, 2014 at 6:51 AM, Markos Chandras
<markos.chandras@imgtec.com> wrote:
> MIPS supports BPF JIT since v3.16-rc1
>
> Cc: Randy Dunlap <rdunlap@infradead.org>
> Cc: "David S. Miller" <davem@davemloft.net>
> Cc: Daniel Borkmann <dborkman@redhat.com>
> Cc: Alexei Starovoitov <ast@plumgrid.com>
> Cc: linux-doc@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> Acked-by: Daniel Borkmann <dborkman@redhat.com>
> Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
^ permalink raw reply
* Re: [PATCH net-next v2] net: bpf: only build bpf_jit_binary_{alloc,free}() when jit selected
From: Alexei Starovoitov @ 2014-09-10 17:22 UTC (permalink / raw)
To: Daniel Borkmann; +Cc: David S. Miller, kbuild test robot, Network Development
In-Reply-To: <1410354062-25337-1-git-send-email-dborkman@redhat.com>
On Wed, Sep 10, 2014 at 6:01 AM, Daniel Borkmann <dborkman@redhat.com> wrote:
> Since BPF JIT depends on the availability of module_alloc() and
> module_free() helpers (HAVE_BPF_JIT and MODULES), we better build
> that code only in case we have BPF_JIT in our config enabled, just
> like with other JIT code. Fixes builds for arm/marzen_defconfig
> and sh/rsk7269_defconfig.
>
> Reported-by: Fengguang Wu <fengguang.wu@intel.com>
> Fixes: 738cbe72adc5 ("net: bpf: consolidate JIT binary allocator")
> Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
haven't tested it, but looks good to me, so
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
thank you for taking care of it so quickly.
^ permalink raw reply
* Re: [PATCH v11 net-next 04/12] bpf: expand BPF syscall with program load/unload
From: Alexei Starovoitov @ 2014-09-10 17:19 UTC (permalink / raw)
To: Daniel Borkmann
Cc: David S. Miller, Ingo Molnar, Linus Torvalds, Andy Lutomirski,
Steven Rostedt, Hannes Frederic Sowa, Chema Gonzalez,
Eric Dumazet, Peter Zijlstra, Pablo Neira Ayuso, H. Peter Anvin,
Andrew Morton, Kees Cook, Linux API, Network Development, LKML
In-Reply-To: <5410062A.4090003@redhat.com>
On Wed, Sep 10, 2014 at 1:04 AM, Daniel Borkmann <dborkman@redhat.com> wrote:
>> + bool has_info; /* whether 'info' is valid
>> u32 len; /* Number of filter blocks
>> - struct sock_fprog_kern *orig_prog; /* Original BPF program */
>> + union {
>> + struct sock_fprog_kern *orig_prog; /* Original BPF
>> program */
>> + struct bpf_prog_info *info;
>> + };
>
>
> All members of this bpf_prog_info should go into bpf_work_struct,
> as I have intended this to be a ancillary structure here. Since
> we already allocate this anyway, you can reduce complexity by doing
> the additional allocation plus remove the has_info member.
that's doable, but won't you be worried about extra 6 fields
in there that only used by native eBPF programs?
I kept them separate not to introduce any overhead
to classic programs.
>> struct bpf_work_struct *work; /* Deferred free work
>> struct */
Also we'd need to rename it, adjust the comment above
and move into linux/bpf.h, since it don't want to overload
linux/filter.h with native eBPF stuff. In my mind filter.h
is for classic and socket things, whereas bpf.h is net-less.
So I'm 50/50 on this one.
Dropping has_info flag is definitely a plus.
Rename 'struct bpf_work_struct' to 'struct bpf_prog_info' ?
bpf_prog_aux_data? bpf_prog_extra ?
Naming is hard.
> But seccomp already does refcounting on each BPF filter. Or, is the
> intention to remove this from seccomp?
seccomp refcounts its own wrapper struct on top of classic bpf.
It gets incremented when task is forked, so I suspect it will
be needed even when seccomp moves to native.
Note that 'struct sk_filter' has its own refcnt as well which
gets incremented when socket is cloned. It's independent from
eBPF program refcnt which is part of 'struct bpf_prog_info',
since the same eBPF program can be attached to multiple
sockets. So both are needed. Seccomp may want to attach
the same eBPF program to multiple tasks as well to save
some memory.
In classic BPF we may open multiple sockets and attach
the same classic BPF prog to all. prog is allocated multiple
times. JIT is called multiple times, but overhead is not huge.
For eBPF is not an option. In eBPF+tracing single program
may be attached to hundreds of events.
>> + BUG_ON(fp->has_info);
>
> Why BUG_ON() (also in so many other places)?
because struct bpf_prog can be created in many different
ways and I had a painful bug here while developing.
I think it can be dropped now.
^ permalink raw reply
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