* [Patch v3 net-next 07/12] net: fec: add enet-avb IP support
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Frank Li,
Fugang Duan
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
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@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
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
^ permalink raw reply related
* [Patch v3 net-next 08/12] net:fec: Add fsl,imx6sx-fec compatible strings
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Fugang Duan,
Frank Li
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
From: Fugang Duan <B38611@freescale.com>
Add compatible string "fsl,imx6sx-fec" for i.MX6SX.
Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
drivers/net/ethernet/freescale/fec_main.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 658b0b3..0cc7313 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -157,6 +157,7 @@ enum imx_fec_type {
IMX28_FEC,
IMX6Q_FEC,
MVF600_FEC,
+ IMX6SX_FEC,
};
static const struct of_device_id fec_dt_ids[] = {
@@ -165,6 +166,7 @@ static const struct of_device_id fec_dt_ids[] = {
{ .compatible = "fsl,imx28-fec", .data = &fec_devtype[IMX28_FEC], },
{ .compatible = "fsl,imx6q-fec", .data = &fec_devtype[IMX6Q_FEC], },
{ .compatible = "fsl,mvf600-fec", .data = &fec_devtype[MVF600_FEC], },
+ { .compatible = "fsl,imx6sx-fec", .data = &fec_devtype[IMX6SX_FEC], },
{ /* sentinel */ }
};
MODULE_DEVICE_TABLE(of, fec_dt_ids);
--
1.9.1
^ permalink raw reply related
* [Patch v3 net-next 01/12] net:fec: add enet refrence clock for i.MX 6SX chip
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Fugang Duan,
Frank Li
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
From: Fugang Duan <B38611@freescale.com>
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@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
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
^ permalink raw reply related
* [Patch v3 net-next 09/12] net: fec: change FEC alignment according to i.mx6 sx requirement
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Fugang Duan,
Frank Li
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
From: Fugang Duan <B38611@freescale.com>
i.MX6 SX change FEC alignment requirement.
i.MX6 SX change internal bus from AHB to AXI.
It require RX buffer must be 64 bytes alignment.
And remove TX buffer alignment requirement.
Signed-off-by: Fugang Duan <B38611@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
drivers/net/ethernet/freescale/fec.h | 3 +++
drivers/net/ethernet/freescale/fec_main.c | 35 +++++++++++++++++++++----------
2 files changed, 27 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 5ec3828..7cc8382 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -443,6 +443,9 @@ struct fec_enet_private {
int hwts_tx_en;
struct delayed_work time_keep;
struct regulator *reg_phy;
+
+ unsigned tx_align;
+ unsigned rx_align;
};
void fec_ptp_init(struct platform_device *pdev);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 0cc7313..8043cd7 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -64,12 +64,6 @@
static void set_multicast_list(struct net_device *ndev);
-#if defined(CONFIG_ARM)
-#define FEC_ALIGNMENT 0xf
-#else
-#define FEC_ALIGNMENT 0x3
-#endif
-
#define DRIVER_NAME "fec"
#define FEC_ENET_GET_QUQUE(_x) ((_x == 0) ? 1 : ((_x == 1) ? 2 : 0))
@@ -434,7 +428,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq,
bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
- if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+ if (((unsigned long) bufaddr) & fep->tx_align ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], bufaddr, frag_len);
bufaddr = txq->tx_bounce[index];
@@ -514,7 +508,7 @@ static int fec_enet_txq_submit_skb(struct fec_enet_priv_tx_q *txq,
queue = skb_get_queue_mapping(skb);
index = fec_enet_get_bd_index(txq->tx_bd_base, bdp, fep);
- if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+ if (((unsigned long) bufaddr) & fep->tx_align ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], skb->data, buflen);
bufaddr = txq->tx_bounce[index];
@@ -607,7 +601,7 @@ fec_enet_txq_put_data_tso(struct fec_enet_priv_tx_q *txq, struct sk_buff *skb,
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
- if (((unsigned long) data) & FEC_ALIGNMENT ||
+ if (((unsigned long) data) & fep->tx_align ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], data, size);
data = txq->tx_bounce[index];
@@ -669,7 +663,7 @@ fec_enet_txq_put_hdr_tso(struct fec_enet_priv_tx_q *txq,
bufaddr = txq->tso_hdrs + index * TSO_HEADER_SIZE;
dmabuf = txq->tso_hdrs_dma + index * TSO_HEADER_SIZE;
- if (((unsigned long) bufaddr) & FEC_ALIGNMENT ||
+ if (((unsigned long)bufaddr) & fep->tx_align ||
id_entry->driver_data & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], skb->data, hdr_len);
bufaddr = txq->tx_bounce[index];
@@ -2399,6 +2393,7 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
struct sk_buff *skb;
struct bufdesc *bdp;
struct fec_enet_priv_rx_q *rxq;
+ unsigned off;
rxq = fep->rx_queue[queue];
bdp = rxq->rx_bd_base;
@@ -2409,8 +2404,13 @@ fec_enet_alloc_rxq_buffers(struct net_device *ndev, unsigned int queue)
if (!skb)
goto err_alloc;
+ off = ((unsigned long)skb->data) & fep->rx_align;
+ if (off)
+ skb_reserve(skb, fep->rx_align + 1 - off);
+
addr = dma_map_single(&fep->pdev->dev, skb->data,
- FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
+ FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE);
+
if (dma_mapping_error(&fep->pdev->dev, addr)) {
dev_kfree_skb(skb);
if (net_ratelimit())
@@ -2743,6 +2743,14 @@ static int fec_enet_init(struct net_device *ndev)
int bd_size;
unsigned int i;
+#if defined(CONFIG_ARM)
+ fep->rx_align = 0xf;
+ fep->tx_align = 0xf;
+#else
+ fep->rx_align = 0x3;
+ fep->tx_align = 0x3;
+#endif
+
fec_enet_alloc_queue(ndev);
if (fep->bufdesc_ex)
@@ -2819,6 +2827,11 @@ static int fec_enet_init(struct net_device *ndev)
fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
}
+ if (id_entry->driver_data & FEC_QUIRK_HAS_AVB) {
+ fep->tx_align = 0;
+ fep->rx_align = 0x3f;
+ }
+
ndev->hw_features = ndev->features;
fec_restart(ndev);
--
1.9.1
^ permalink raw reply related
* [Patch v3 net-next 00/12] net: fec: imx6sx multiqueue support
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Frank Li
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
^ permalink raw reply
* [Patch v3 net-next 04/12] net: fec: parser max queue number from dt file
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Fugang Duan,
Frank Li
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
From: Fugang Duan <B38611@freescale.com>
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@freescale.com>
Signed-off-by: Frank Li <Frank.Li@freescale.com>
---
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
^ permalink raw reply related
* [Patch v3 net-next 03/12] net: fec: change data structure to support multiqueue
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Fugang Duan,
Frank Li
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
From: Fugang Duan <B38611@freescale.com>
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@freescale.com>
Signed-off-by: Frank Li <frank.li@freescale.com>
---
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
^ permalink raw reply related
* Re: [Patch v3 net-next 00/12] net: fec: imx6sx multiqueue support
From: Zhi Li @ 2014-09-10 18:55 UTC (permalink / raw)
To: yes
Cc: Duan Fugang-B38611, David Miller, netdev@vger.kernel.org,
Shawn Guo, linux-arm-kernel@lists.infradead.org,
devicetree@vger.kernel.org, Russell King - ARM Linux, Frank Li
In-Reply-To: <54109e51.65d4440a.594b.6b4bSMTPIN_ADDED_BROKEN@mx.google.com>
On Wed, Sep 10, 2014 at 1:30 PM, <yes@shlinux1.ap.freescale.net> wrote:
>
>
Sorry again, use wrong sender email address.
^ permalink raw reply
* [PATCH v2 03/14] isdn: i4l: Remove ASYNC_CTS_FLOW
From: Peter Hurley @ 2014-09-10 19:06 UTC (permalink / raw)
To: Greg Kroah-Hartman
Cc: Jiri Slaby, One Thousand Gnomes, linux-kernel, linux-serial,
Peter Hurley, Karsten Keil, netdev
In-Reply-To: <1410375996-4693-1-git-send-email-peter@hurleysoftware.com>
ISDN4Linux always enables CTS flow control and does not use the
tty_port_cts_enabled() helper function; remove ASYNC_CTS_FLOW
state enable/disable.
cc: Karsten Keil <isdn@linux-pingi.de>
cc: <netdev@vger.kernel.org>
Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
---
drivers/isdn/i4l/isdn_tty.c | 5 -----
1 file changed, 5 deletions(-)
diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 3c5f249..bc91261 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -1043,11 +1043,6 @@ isdn_tty_change_speed(modem_info *info)
if (!(cflag & PARODD))
cval |= UART_LCR_EPAR;
- /* CTS flow control flag and modem status interrupts */
- if (cflag & CRTSCTS) {
- port->flags |= ASYNC_CTS_FLOW;
- } else
- port->flags &= ~ASYNC_CTS_FLOW;
if (cflag & CLOCAL)
port->flags &= ~ASYNC_CHECK_CD;
else {
--
2.1.0
^ permalink raw reply related
* [Patch v3 net-next 05/12] net: fec: init multi queue date structure
From: Frank Li @ 2014-09-10 18:30 UTC (permalink / raw)
To: b38611, davem, netdev, lznuaa
Cc: shawn.guo, linux-arm-kernel, devicetree, linux, Frank Li,
Duan Fugang
In-Reply-To: <1410373845-5801-1-git-send-email-Frank.Li@freescale.com>
initilized all queues according to queue number get from DT file.
Signed-off-by: Frank Li <Frank.Li@freescale.com>
Signed-off-by: Duan Fugang <B38611@freescale.com>
---
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
^ permalink raw reply related
* Re: [PATCH net-next 0/5] net: Convert pr_warning to pr_warn
From: David Miller @ 2014-09-10 19:43 UTC (permalink / raw)
To: joe
Cc: netdev, sage, ursula.braun, linux390, pablo, kaber, kadlec,
linux-kernel, ceph-devel, linux-s390, netfilter-devel, coreteam
In-Reply-To: <cover.1410322181.git.joe@perches.com>
From: Joe Perches <joe@perches.com>
Date: Tue, 9 Sep 2014 21:17:27 -0700
> Remove remaining uses of pr_warning in net/
>
> Joe Perches (5):
> atm: Convert pr_warning to pr_warn
> ceph: Convert pr_warning to pr_warn
> pktgen: Convert pr_warning to pr_warn
> iucv: Convert pr_warning to pr_warn
> netfilter: Convert pr_warning to pr_warn
All except the ceph patch which is going via another tree.
^ permalink raw reply
* Re: [PATCH 00/25] nf-next pull request
From: David Miller @ 2014-09-10 19:47 UTC (permalink / raw)
To: pablo; +Cc: netfilter-devel, netdev
In-Reply-To: <1410361842-4656-1-git-send-email-pablo@netfilter.org>
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Wed, 10 Sep 2014 17:10:17 +0200
> The following patchset contains Netfilter/IPVS updates for your
> net-next tree. Regarding nf_tables, most updates focus on consolidating
> the NAT infrastructure and adding support for masquerading.
Pulled, thanks Pablo.
^ permalink raw reply
* Re: [Patch net-next 0/5] ipv6: clean up locking in anycast and mcast
From: David Miller @ 2014-09-10 20:01 UTC (permalink / raw)
To: xiyou.wangcong; +Cc: netdev, hannes, yoshfuji
In-Reply-To: <1410306738-18036-1-git-send-email-xiyou.wangcong@gmail.com>
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Tue, 9 Sep 2014 16:52:13 -0700
> This patchset cleans up the locking in anycast.c and mcast.c.
>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Please update this based upon the feedback you've received.
Thanks!
^ permalink raw reply
* Re: [PATCH v1] net: ethernet: arc: Don't free Rockchip resources before disconnect from phy
From: David Miller @ 2014-09-10 20:03 UTC (permalink / raw)
To: romain.perier; +Cc: heiko, linux-rockchip, linux-arm-kernel, netdev
In-Reply-To: <1410335473-23573-1-git-send-email-romain.perier@gmail.com>
From: Romain Perier <romain.perier@gmail.com>
Date: Wed, 10 Sep 2014 07:51:13 +0000
> Free resources before being disconnected from phy and calling core driver is
> wrong and should not happen. It avoids a delay of 4-5s caused by the timeout of
> phy_disconnect().
>
> Signed-off-by: Romain Perier <romain.perier@gmail.com>
Applied, thanks.
^ permalink raw reply
* Re: 3.17-rc1 oops during network interface configuration
From: David Miller @ 2014-09-10 20:04 UTC (permalink / raw)
To: ogerlitz-VPRAkNaXOzVWk0Htik3J/w
Cc: chuck.lever-QHcLZuEGTsvQT0dZR+AlfA, _govind-KK0ffGbhmjU,
netdev-u79uwXL29TY76Z2rM5mHXA,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA, bvanassche-HInyCGIudOg,
saeedm-VPRAkNaXOzVWk0Htik3J/w, talal-VPRAkNaXOzVWk0Htik3J/w,
yevgenyp-VPRAkNaXOzVWk0Htik3J/w, roland-DgEjT+Ai2ygdnm+yROfE0A
In-Reply-To: <541000F1.5000805-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
From: Or Gerlitz <ogerlitz-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Date: Wed, 10 Sep 2014 10:42:41 +0300
> Hi Chuck, thanks for bisecting this out. Indeed, as of this kernel 3.2
> commit 936d7de "IPoIB: Stop lying about hard_header_len and use
> skb->cb to stash LL addresses" we are using the skb->cb field to
> enable proper work under GRO and avoid another historical quirk we had
> there... so I think we can definetly consider commit e0f31d849 to
> introduce a severe regression... Govindarajulu, Dave - what's your
> thinking here? any quick idea on how to fix?
Eric mentioned that we could reduce the amount of flow state stored
in the qdisc cb in order to handle this better.
Making skb->cb[] larger is basically out of the question as far as
I'm concerned.
> Also, I was thinking we have the mechanics in the kernel, e.g commit
> a0417fa3a18a ("net: Make qdisc_skb_cb upper size bound explicit.") to
> catch such over-flows?
Yes we should have added a build-time check so that we would discover
this issue more quickly.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" 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 V2 net] core: Don't attempt to load the "" driver.
From: David Miller @ 2014-09-10 20:06 UTC (permalink / raw)
To: David.Laight; +Cc: netdev
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D1748EC90@AcuExch.aculab.com>
From: David Laight <David.Laight@ACULAB.COM>
Date: Wed, 10 Sep 2014 08:50:50 +0000
> I actually wonder when the module load is useful - must be useful
> sometimes, otherwise it wouldn't have been added.
Just grep for things like MODULE_ALIAS_NETDEV(...) for the legacy cases
where this can still be used. Largely it's for tunneling devices.
^ permalink raw reply
* [PATCH net-next] mac80211: Check correct skb for shared states before freeing original
From: Alexander Duyck @ 2014-09-10 20:06 UTC (permalink / raw)
To: netdev-u79uwXL29TY76Z2rM5mHXA,
linux-wireless-u79uwXL29TY76Z2rM5mHXA
Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q, linville-2XuSBdqkA4R54TAoqtyWWQ
The code for cloning the skb for an acknowledgement was checking to see if
the cloned skb was shared and if it was it was then freeing the original
skb. Since a clone should never really be shared I suspect that the
intention was to avoid freeing the clone if the original was shared. As
such I am updating the code so that if the original is shared we free the
original and use the clone. This avoids unnecessary work in the next
section where we would be cloning the skb if the original is shared.
Signed-off-by: Alexander Duyck <alexander.h.duyck-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org>
---
net/mac80211/tx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 925c39f..e527cd3 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -2087,7 +2087,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
if (id >= 0) {
info_id = id;
info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
- } else if (skb_shared(skb)) {
+ } else if (skb_shared(orig_skb)) {
kfree_skb(orig_skb);
} else {
kfree_skb(skb);
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH net-next] ipv6: implement rt_genid_bump_ipv6 with fn_sernum and remove rt6i_genid
From: David Miller @ 2014-09-10 20:09 UTC (permalink / raw)
To: hannes; +Cc: netdev, eric.dumazet, nicolas.dichtel
In-Reply-To: <130f98f49b1b90a30908bfda8f01109c91edfe1c.1410341451.git.hannes@stressinduktion.org>
From: Hannes Frederic Sowa <hannes@stressinduktion.org>
Date: Wed, 10 Sep 2014 11:31:28 +0200
> In case we need to force the sockets to relookup the routes we now
> increase the fn_sernum on all fibnodes in the routing tree. This is a
> costly operation but should only happen if we have major routing/policy
> changes in the kernel (e.g. manual route adding/removal, xfrm policy
> changes).
Core routers can update thousands of route updates per second, and they
do this via what you refer to as "manual route adding/removal".
I don't think we want to put such a scalability problem into the tree.
There has to be a lightweight way to address this.
^ permalink raw reply
* Re: [PATCH v11 net-next 00/12] eBPF syscall, verifier, testsuite
From: Alexei Starovoitov @ 2014-09-10 20:21 UTC (permalink / raw)
To: Andy Lutomirski
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-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <CALCETrVBb_uQZpodv67XSTGVU40y6+9Ktw=3zAJgGV2mNJ=_0A-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
On Wed, Sep 10, 2014 at 11:22 AM, Andy Lutomirski <luto-kltTT9wpgjJwATOyAt5JVQ@public.gmane.org> wrote:
>>
>> 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?
you mean change attr to be 'void *' and type cast it to particular
struct type based on cmd ? Possible, but I tried to avoid all
typecasts as Dave doesn't like them.
>> 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 :(
enum is int on both 32 and 64-bit. What was the concern?
anonymous struct ?
I've checked that with gcc 4.2 - 4.9 and clang. All was fine
and it's part of C standard now.
>> 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.
would do you mean specifically?
const pointer is obviously 'in' argument.
'void *' is 'out'.
>> 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.)
if inner struct types had names they would need to
have field names as well, so the syscall wrapper above
would become much more verbose and uglier.
Also naming structs may give wrong ideas to some users,
since they might think it's ok to init struct only and type cast
it to pass into syscall. When inner structs don't have names,
the user space is forced to always use 'union bpf_attr' and
initialize relevant fields.
>> char bpf_log_buf[LOG_BUF_SIZE];
>
> What happens if the size isn't LOG_BUF_SIZE?
would do you mean?
LOG_BUF_SIZE is just a user defined macro.
Can be anything.
it's passed along with pointer:
.log_buf = bpf_log_buf,
.log_size = LOG_BUF_SIZE,
.log_level = 1,
>> enum bpf_prog_type {
>> BPF_PROG_TYPE_UNSPEC,
>> BPF_PROG_TYPE_SOCKET_FILTER,
>> BPF_PROG_TYPE_TRACING_FILTER,
>> };
>
> Why does the type matter?
type is way to tell eBPF infra what this type of programs
is allowed to do. Different kernel subsystems
configure different types.
Like patch 12 configures TYPE_UNSPEC for testing.
This type allows one dummy function call and
bpf_context of two u64 fields.
tracing subsystem will configure TYPE_TRACING
to do different set of helper functions and different
body of 'bpf_context'.
PROG_TYPE and MAP_TYPE are two main ways
to configure eBPF infra for different use cases.
> 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.
we discussed relocations before, right? ;)
I believe relocations are ugly. elf has no other way to deal
with it, since .text has valid cpu instructions and generic
loader has to adjust them without knowing hw encoding.
Here we have pseudo instructions that are much easier
to check/track in verifier than relocations.
As you remember in previous series I've tried relocation
style and it was ugly. Both as user interface and as extra
complexity for verifier.
Does commit log of patch 8 explain map_fd conversion
well enough or not?
If not, I'll add more info, but please read it first.
>> ENOENT For BPF_MAP_LOOKUP_ELEM or BPF_MAP_DELETE_ELEM, indicates that
>> element with given key was not found.
>
> What does it return? (The same question goes for a bunch of the map ops.)
...
> Shouldn't delete return different values depending on whether anything
> was deleted?
...
> Ah, here it is. Please document this with the ops.
I believe it's a standard manpage style to document
return values at the end in 'return value' section.
I can duplicate it with ops, but is it really necessary?
>> These commands may be used only by a privileged process (one having the
>> CAP_SYS_ADMIN capability).
>
> I hope this goes away :)
hehe.
I think folks obsessed with security will say it should stay
this way for looooong time :)
My immediate goal is tracing and there this restriction is
necessary anyway.
> 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.
'concept of objects'... sounds abstractly good :)
Something concrete you have in mind?
Theoretically I can see how we can add a 'stream' object
which user space can read and programs feed stuff to.
In other words an 'abstract' trace buffer, but imo it's
overdesign. When we need a trace buffer, we'll just
add a helper function that pushes stuff to it.
That will be the time when you see how handy pseudo
instructions are. In this patch the only '.imm thing', as you
say, is map_fd. I'm working on per-cpu local buffer via
the same pseudo stuff. Seem to work quite nicely.
Let's not get carried on with future cool stuff, basics first :)
Thanks for the feedback!
^ permalink raw reply
* Re: [PATCH net-next] mac80211: Check correct skb for shared states before freeing original
From: Johannes Berg @ 2014-09-10 20:33 UTC (permalink / raw)
To: Alexander Duyck; +Cc: netdev, linux-wireless, davem, linville
In-Reply-To: <20140910200442.15961.84466.stgit@ahduyck-bv4.jf.intel.com>
On Wed, 2014-09-10 at 16:06 -0400, Alexander Duyck wrote:
> The code for cloning the skb for an acknowledgement was checking to see if
> the cloned skb was shared and if it was it was then freeing the original
> skb. Since a clone should never really be shared I suspect that the
> intention was to avoid freeing the clone if the original was shared. As
> such I am updating the code so that if the original is shared we free the
> original and use the clone. This avoids unnecessary work in the next
> section where we would be cloning the skb if the original is shared.
Thanks, yeah, I admit that this is clearly fishy.
> @@ -2087,7 +2087,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
> if (id >= 0) {
> info_id = id;
> info_flags |= IEEE80211_TX_CTL_REQ_TX_STATUS;
Luckily, we practically always go into this path.
> - } else if (skb_shared(skb)) {
> + } else if (skb_shared(orig_skb)) {
> kfree_skb(orig_skb);
> } else {
> kfree_skb(skb);
We have a clone already so we could just remove the whole "else if" I
think, but I'm guessing my intent was to keep it accounted to the socket
where possible rather than freeing the original in all cases.
So yeah, I think this makes sense. Maybe we should add a comment to the
if though to explain this?
johannes
^ permalink raw reply
* [PATCH v2 0/2] net: arc_emac: fix tx issues
From: Beniamino Galvani @ 2014-09-10 20:50 UTC (permalink / raw)
To: David S. Miller
Cc: Romain Perier, Heiko Stübner, Arnd Bergmann, Tobias Klauser,
Jingoo Han, Max Schwarz, Florian Fainelli, netdev, linux-kernel,
Beniamino Galvani
Hi,
the patches below solve some issues found in the tx ring reclaim
strategy currently implemented in the arc_emac driver.
Without these patches a simple outgoing UDP flow blocks almost
immediately with the socket send buffer full, until some new rx
packets trigger a clean of the tx ring.
Everything seems to work fine on a Radxa Rock with this fix applied.
Changes since v1:
- reworded commit messages
Beniamino Galvani (2):
net: arc_emac: enable tx interrupts
net: arc_emac: prevent reuse of unreclaimed tx descriptors
drivers/net/ethernet/arc/emac_main.c | 53 +++++++++++++++++++++++++-----------
1 file changed, 37 insertions(+), 16 deletions(-)
--
1.9.1
^ permalink raw reply
* [PATCH v2 1/2] net: arc_emac: enable tx interrupts
From: Beniamino Galvani @ 2014-09-10 20:50 UTC (permalink / raw)
To: David S. Miller
Cc: Romain Perier, Heiko Stübner, Arnd Bergmann, Tobias Klauser,
Jingoo Han, Max Schwarz, Florian Fainelli, netdev, linux-kernel,
Beniamino Galvani
In-Reply-To: <1410382203-10395-1-git-send-email-b.galvani@gmail.com>
In the current implementation the cleaning of tx ring is done by the
NAPI poll handler, which is scheduled after rx interrupts. Thus, in
absence of received packets the reclaim of used tx buffers is never
executed, blocking further transmission.
This can be easily reproduced starting the transmission of a UDP flow
with iperf, which blocks almost immediately because skbs are not
returned to the stack and the socket send buffer becomes full.
The patch enables tx interrupts so that the tx reclaim is scheduled
after completed transmissions.
Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
---
drivers/net/ethernet/arc/emac_main.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index dbea847..1d08f63 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -300,7 +300,7 @@ static int arc_emac_poll(struct napi_struct *napi, int budget)
work_done = arc_emac_rx(ndev, budget);
if (work_done < budget) {
napi_complete(napi);
- arc_reg_or(priv, R_ENABLE, RXINT_MASK);
+ arc_reg_or(priv, R_ENABLE, RXINT_MASK | TXINT_MASK);
}
return work_done;
@@ -329,9 +329,9 @@ static irqreturn_t arc_emac_intr(int irq, void *dev_instance)
/* Reset all flags except "MDIO complete" */
arc_reg_set(priv, R_STATUS, status);
- if (status & RXINT_MASK) {
+ if (status & (RXINT_MASK | TXINT_MASK)) {
if (likely(napi_schedule_prep(&priv->napi))) {
- arc_reg_clr(priv, R_ENABLE, RXINT_MASK);
+ arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK);
__napi_schedule(&priv->napi);
}
}
@@ -442,7 +442,7 @@ static int arc_emac_open(struct net_device *ndev)
arc_reg_set(priv, R_TX_RING, (unsigned int)priv->txbd_dma);
/* Enable interrupts */
- arc_reg_set(priv, R_ENABLE, RXINT_MASK | ERR_MASK);
+ arc_reg_set(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK);
/* Set CONTROL */
arc_reg_set(priv, R_CTRL,
@@ -513,7 +513,7 @@ static int arc_emac_stop(struct net_device *ndev)
netif_stop_queue(ndev);
/* Disable interrupts */
- arc_reg_clr(priv, R_ENABLE, RXINT_MASK | ERR_MASK);
+ arc_reg_clr(priv, R_ENABLE, RXINT_MASK | TXINT_MASK | ERR_MASK);
/* Disable EMAC */
arc_reg_clr(priv, R_CTRL, EN_MASK);
--
1.9.1
^ permalink raw reply related
* [PATCH v2 2/2] net: arc_emac: prevent reuse of unreclaimed tx descriptors
From: Beniamino Galvani @ 2014-09-10 20:50 UTC (permalink / raw)
To: David S. Miller
Cc: Romain Perier, Heiko Stübner, Arnd Bergmann, Tobias Klauser,
Jingoo Han, Max Schwarz, Florian Fainelli, netdev, linux-kernel,
Beniamino Galvani
In-Reply-To: <1410382203-10395-1-git-send-email-b.galvani@gmail.com>
This patch changes the logic in tx path to ensure that tx descriptors
are reused for transmission only after they have been reclaimed by
arc_emac_tx_clean().
Signed-off-by: Beniamino Galvani <b.galvani@gmail.com>
---
drivers/net/ethernet/arc/emac_main.c | 43 +++++++++++++++++++++++++++---------
1 file changed, 32 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index 1d08f63..abe1eab 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -28,6 +28,17 @@
/**
+ * arc_emac_tx_avail - Return the number of available slots in the tx ring.
+ * @priv: Pointer to ARC EMAC private data structure.
+ *
+ * returns: the number of slots available for transmission in tx the ring.
+ */
+static inline int arc_emac_tx_avail(struct arc_emac_priv *priv)
+{
+ return (priv->txbd_dirty + TX_BD_NUM - priv->txbd_curr - 1) % TX_BD_NUM;
+}
+
+/**
* arc_emac_adjust_link - Adjust the PHY link duplex.
* @ndev: Pointer to the net_device structure.
*
@@ -182,10 +193,15 @@ static void arc_emac_tx_clean(struct net_device *ndev)
txbd->info = 0;
*txbd_dirty = (*txbd_dirty + 1) % TX_BD_NUM;
-
- if (netif_queue_stopped(ndev))
- netif_wake_queue(ndev);
}
+
+ /* Ensure that txbd_dirty is visible to tx() before checking
+ * for queue stopped.
+ */
+ smp_mb();
+
+ if (netif_queue_stopped(ndev) && arc_emac_tx_avail(priv))
+ netif_wake_queue(ndev);
}
/**
@@ -576,11 +592,9 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
len = max_t(unsigned int, ETH_ZLEN, skb->len);
- /* EMAC still holds this buffer in its possession.
- * CPU must not modify this buffer descriptor
- */
- if (unlikely((le32_to_cpu(*info) & OWN_MASK) == FOR_EMAC)) {
+ if (unlikely(!arc_emac_tx_avail(priv))) {
netif_stop_queue(ndev);
+ netdev_err(ndev, "BUG! Tx Ring full when queue awake!\n");
return NETDEV_TX_BUSY;
}
@@ -609,12 +623,19 @@ static int arc_emac_tx(struct sk_buff *skb, struct net_device *ndev)
/* Increment index to point to the next BD */
*txbd_curr = (*txbd_curr + 1) % TX_BD_NUM;
- /* Get "info" of the next BD */
- info = &priv->txbd[*txbd_curr].info;
+ /* Ensure that tx_clean() sees the new txbd_curr before
+ * checking the queue status. This prevents an unneeded wake
+ * of the queue in tx_clean().
+ */
+ smp_mb();
- /* Check if if Tx BD ring is full - next BD is still owned by EMAC */
- if (unlikely((le32_to_cpu(*info) & OWN_MASK) == FOR_EMAC))
+ if (!arc_emac_tx_avail(priv)) {
netif_stop_queue(ndev);
+ /* Refresh tx_dirty */
+ smp_mb();
+ if (arc_emac_tx_avail(priv))
+ netif_start_queue(ndev);
+ }
arc_reg_set(priv, R_STATUS, TXPL_MASK);
--
1.9.1
^ permalink raw reply related
* Re: [PATCH net] ipv6: clean up anycast when an interface is destroyed
From: David Miller @ 2014-09-10 20:58 UTC (permalink / raw)
To: cwang; +Cc: sd, netdev, hannes
In-Reply-To: <CAHA+R7ODewXP69ULsR0RD+c3BEfMa90zATRjHF3dC9Dkv7jgZw@mail.gmail.com>
From: Cong Wang <cwang@twopensource.com>
Date: Wed, 10 Sep 2014 10:15:01 -0700
> On Wed, Sep 10, 2014 at 3:27 AM, Sabrina Dubroca <sd@queasysnail.net> wrote:
>> diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
>> index ff2de7d9d8e6..a1bf80574bfe 100644
>> --- a/net/ipv6/anycast.c
>> +++ b/net/ipv6/anycast.c
>> @@ -351,6 +351,28 @@ static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
>> return __ipv6_dev_ac_dec(idev, addr);
>> }
>>
>> +/* Device is being destroyed: clean up */
>
> This comment is useless.
Agreed, please remove this and respin that patch.
Thanks.
^ permalink raw reply
* Re: [net PATCH v2 1/1] drivers: net: cpsw: dual_emac: fix reducing of rx descriptor during ifdown
From: David Miller @ 2014-09-10 20:59 UTC (permalink / raw)
To: mugunthanvnm; +Cc: netdev
In-Reply-To: <1410347289-3555-1-git-send-email-mugunthanvnm@ti.com>
From: Mugunthan V N <mugunthanvnm@ti.com>
Date: Wed, 10 Sep 2014 16:38:09 +0530
> In Dual EMAC, when both interface are up and while doing ifdown with heavy
> traffic then skbs already processed by DMA from that slave emac has to be
> requeued as still the other interface is up and running.
>
> Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
Applied.
^ 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