linux/drivers/net/ethernet/freescale/fec_main.c

3617 lines
92 KiB
C
Raw Normal View History

/*
* Fast Ethernet Controller (FEC) driver for Motorola MPC8xx.
* Copyright (c) 1997 Dan Malek (dmalek@jlc.net)
*
* Right now, I am very wasteful with the buffers. I allocate memory
* pages and then divide them into 2K frame buffers. This way I know I
* have buffers large enough to hold one frame within one buffer descriptor.
* Once I get this working, I will use 64 or 128 byte CPM buffers, which
* will be much more memory efficient and will easily handle lots of
* small packets.
*
* Much better multiple PHY support by Magnus Damm.
* Copyright (c) 2000 Ericsson Radio Systems AB.
*
* Support for FEC controller of ColdFire processors.
* Copyright (c) 2001-2005 Greg Ungerer (gerg@snapgear.com)
*
* Bug fixes and cleanup by Philippe De Muyter (phdm@macqel.be)
* Copyright (c) 2004-2006 Macq Electronique SA.
*
* Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/pm_runtime.h>
#include <linux/ptrace.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <net/ip.h>
#include <net/tso.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/icmp.h>
#include <linux/spinlock.h>
#include <linux/workqueue.h>
#include <linux/bitops.h>
#include <linux/io.h>
#include <linux/irq.h>
#include <linux/clk.h>
#include <linux/platform_device.h>
#include <linux/mdio.h>
#include <linux/phy.h>
#include <linux/fec.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_gpio.h>
#include <linux/of_mdio.h>
#include <linux/of_net.h>
#include <linux/regulator/consumer.h>
#include <linux/if_vlan.h>
#include <linux/pinctrl/consumer.h>
#include <linux/prefetch.h>
#include <asm/cacheflush.h>
#include "fec.h"
static void set_multicast_list(struct net_device *ndev);
static void fec_enet_itr_coal_init(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
#define FEC_ENET_RSFL_V 16
#define FEC_ENET_RAEM_V 0x8
#define FEC_ENET_RAFL_V 0x8
#define FEC_ENET_OPD_V 0xFFF0
#define FEC_MDIO_PM_TIMEOUT 100 /* ms */
static struct platform_device_id fec_devtype[] = {
{
/* keep it for coldfire */
.name = DRIVER_NAME,
.driver_data = 0,
}, {
.name = "imx25-fec",
.driver_data = FEC_QUIRK_USE_GASKET | FEC_QUIRK_HAS_RACC,
}, {
.name = "imx27-fec",
.driver_data = FEC_QUIRK_HAS_RACC,
}, {
.name = "imx28-fec",
net: fec: fix MDIO bus assignement for dual fec SoC's On i.MX28, the MDIO bus is shared between the two FEC instances. The driver makes sure that the second FEC uses the MDIO bus of the first FEC. This is done conditionally if FEC_QUIRK_ENET_MAC is set. However, in newer designs, such as Vybrid or i.MX6SX, each FEC MAC has its own MDIO bus. Simply removing the quirk FEC_QUIRK_ENET_MAC is not an option since other logic, triggered by this quirk, is still needed. Furthermore, there are board designs which use the same MDIO bus for both PHY's even though the second bus would be available on the SoC side. Such layout are popular since it saves pins on SoC side. Due to the above quirk, those boards currently do work fine. The boards in the mainline tree with such a layout are: - Freescale Vybrid Tower with TWR-SER2 (vf610-twr.dts) - Freescale i.MX6 SoloX SDB Board (imx6sx-sdb.dts) This patch adds a new quirk FEC_QUIRK_SINGLE_MDIO for i.MX28, which makes sure that the MDIO bus of the first FEC is used in any case. However, the boards above do have a SoC with a MDIO bus for each FEC instance. But the PHY's are not connected in a 1:1 configuration. A proper device tree description is needed to allow the driver to figure out where to find its PHY. This patch fixes that shortcoming by adding a MDIO bus child node to the first FEC instance, along with the two PHY's on that bus, and making use of the phy-handle property to add a reference to the PHY's. Acked-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Stefan Agner <stefan@agner.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-14 07:20:21 +08:00
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_SWAP_FRAME |
FEC_QUIRK_SINGLE_MDIO | FEC_QUIRK_HAS_RACC,
}, {
.name = "imx6q-fec",
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_ERR006358 |
FEC_QUIRK_HAS_RACC,
}, {
.name = "mvf600-fec",
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_RACC,
}, {
.name = "imx6sx-fec",
.driver_data = FEC_QUIRK_ENET_MAC | FEC_QUIRK_HAS_GBIT |
FEC_QUIRK_HAS_BUFDESC_EX | FEC_QUIRK_HAS_CSUM |
FEC_QUIRK_HAS_VLAN | FEC_QUIRK_HAS_AVB |
FEC_QUIRK_ERR007885 | FEC_QUIRK_BUG_CAPTURE |
FEC_QUIRK_HAS_RACC,
}, {
/* sentinel */
}
};
MODULE_DEVICE_TABLE(platform, fec_devtype);
enum imx_fec_type {
IMX25_FEC = 1, /* runs on i.mx25/50/53 */
IMX27_FEC, /* runs on i.mx27/35/51 */
IMX28_FEC,
IMX6Q_FEC,
MVF600_FEC,
IMX6SX_FEC,
};
static const struct of_device_id fec_dt_ids[] = {
{ .compatible = "fsl,imx25-fec", .data = &fec_devtype[IMX25_FEC], },
{ .compatible = "fsl,imx27-fec", .data = &fec_devtype[IMX27_FEC], },
{ .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);
static unsigned char macaddr[ETH_ALEN];
module_param_array(macaddr, byte, NULL, 0);
MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address");
#if defined(CONFIG_M5272)
/*
* Some hardware gets it MAC address out of local flash memory.
* if this is non-zero then assume it is the address to get MAC from.
*/
#if defined(CONFIG_NETtel)
#define FEC_FLASHMAC 0xf0006006
#elif defined(CONFIG_GILBARCONAP) || defined(CONFIG_SCALES)
#define FEC_FLASHMAC 0xf0006000
#elif defined(CONFIG_CANCam)
#define FEC_FLASHMAC 0xf0020000
#elif defined (CONFIG_M5272C3)
#define FEC_FLASHMAC (0xffe04000 + 4)
#elif defined(CONFIG_MOD5272)
#define FEC_FLASHMAC 0xffc0406b
#else
#define FEC_FLASHMAC 0
#endif
#endif /* CONFIG_M5272 */
/* The FEC stores dest/src/type/vlan, data, and checksum for receive packets.
*/
#define PKT_MAXBUF_SIZE 1522
#define PKT_MINBUF_SIZE 64
#define PKT_MAXBLR_SIZE 1536
/* FEC receive acceleration */
#define FEC_RACC_IPDIS (1 << 1)
#define FEC_RACC_PRODIS (1 << 2)
#define FEC_RACC_OPTIONS (FEC_RACC_IPDIS | FEC_RACC_PRODIS)
/*
* The 5270/5271/5280/5282/532x RX control register also contains maximum frame
* size bits. Other FEC hardware does not, so we need to take that into
* account when setting it.
*/
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM)
#define OPT_FRAME_SIZE (PKT_MAXBUF_SIZE << 16)
#else
#define OPT_FRAME_SIZE 0
#endif
/* FEC MII MMFR bits definition */
#define FEC_MMFR_ST (1 << 30)
#define FEC_MMFR_OP_READ (2 << 28)
#define FEC_MMFR_OP_WRITE (1 << 28)
#define FEC_MMFR_PA(v) ((v & 0x1f) << 23)
#define FEC_MMFR_RA(v) ((v & 0x1f) << 18)
#define FEC_MMFR_TA (2 << 16)
#define FEC_MMFR_DATA(v) (v & 0xffff)
/* FEC ECR bits definition */
#define FEC_ECR_MAGICEN (1 << 2)
#define FEC_ECR_SLEEP (1 << 3)
#define FEC_MII_TIMEOUT 30000 /* us */
/* Transmitter timeout */
#define TX_TIMEOUT (2 * HZ)
#define FEC_PAUSE_FLAG_AUTONEG 0x1
#define FEC_PAUSE_FLAG_ENABLE 0x2
#define FEC_WOL_HAS_MAGIC_PACKET (0x1 << 0)
#define FEC_WOL_FLAG_ENABLE (0x1 << 1)
#define FEC_WOL_FLAG_SLEEP_ON (0x1 << 2)
#define COPYBREAK_DEFAULT 256
#define TSO_HEADER_SIZE 128
/* Max number of allowed TCP segments for software TSO */
#define FEC_MAX_TSO_SEGS 100
#define FEC_MAX_SKB_DESCS (FEC_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
#define IS_TSO_HEADER(txq, addr) \
((addr >= txq->tso_hdrs_dma) && \
(addr < txq->tso_hdrs_dma + txq->bd.ring_size * TSO_HEADER_SIZE))
static int mii_cnt;
static struct bufdesc *fec_enet_get_nextdesc(struct bufdesc *bdp,
struct bufdesc_prop *bd)
{
return (bdp >= bd->last) ? bd->base
: (struct bufdesc *)(((unsigned)bdp) + bd->dsize);
}
static struct bufdesc *fec_enet_get_prevdesc(struct bufdesc *bdp,
struct bufdesc_prop *bd)
{
return (bdp <= bd->base) ? bd->last
: (struct bufdesc *)(((unsigned)bdp) - bd->dsize);
}
static int fec_enet_get_bd_index(struct bufdesc *bdp,
struct bufdesc_prop *bd)
{
return ((const char *)bdp - (const char *)bd->base) >> bd->dsize_log2;
}
static int fec_enet_get_free_txdesc_num(struct fec_enet_priv_tx_q *txq)
{
int entries;
entries = (((const char *)txq->dirty_tx -
(const char *)txq->bd.cur) >> txq->bd.dsize_log2) - 1;
return entries >= 0 ? entries : entries + txq->bd.ring_size;
}
static void swap_buffer(void *bufaddr, int len)
{
int i;
unsigned int *buf = bufaddr;
for (i = 0; i < len; i += 4, buf++)
swab32s(buf);
}
static void swap_buffer2(void *dst_buf, void *src_buf, int len)
{
int i;
unsigned int *src = src_buf;
unsigned int *dst = dst_buf;
for (i = 0; i < len; i += 4, src++, dst++)
*dst = swab32p(src);
}
static void fec_dump(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
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->bd.base;
do {
pr_info("%3u %c%c 0x%04x 0x%08x %4u %p\n",
index,
bdp == txq->bd.cur ? 'S' : ' ',
bdp == txq->dirty_tx ? 'H' : ' ',
fec16_to_cpu(bdp->cbd_sc),
fec32_to_cpu(bdp->cbd_bufaddr),
fec16_to_cpu(bdp->cbd_datlen),
txq->tx_skbuff[index]);
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
index++;
} while (bdp != txq->bd.base);
}
static inline bool is_ipv4_pkt(struct sk_buff *skb)
{
return skb->protocol == htons(ETH_P_IP) && ip_hdr(skb)->version == 4;
}
static int
fec_enet_clear_csum(struct sk_buff *skb, struct net_device *ndev)
{
/* Only run for packets requiring a checksum. */
if (skb->ip_summed != CHECKSUM_PARTIAL)
return 0;
if (unlikely(skb_cow_head(skb, 0)))
return -1;
if (is_ipv4_pkt(skb))
ip_hdr(skb)->check = 0;
*(__sum16 *)(skb->head + skb->csum_start + skb->csum_offset) = 0;
return 0;
}
static struct bufdesc *
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);
struct bufdesc *bdp = txq->bd.cur;
struct bufdesc_ex *ebdp;
int nr_frags = skb_shinfo(skb)->nr_frags;
int frag, frag_len;
unsigned short status;
unsigned int estatus = 0;
skb_frag_t *this_frag;
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
unsigned int index;
void *bufaddr;
dma_addr_t addr;
int i;
for (frag = 0; frag < nr_frags; frag++) {
this_frag = &skb_shinfo(skb)->frags[frag];
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
ebdp = (struct bufdesc_ex *)bdp;
status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
frag_len = skb_shinfo(skb)->frags[frag].size;
/* Handle the last BD specially */
if (frag == nr_frags - 1) {
status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
if (fep->bufdesc_ex) {
estatus |= BD_ENET_TX_INT;
if (unlikely(skb_shinfo(skb)->tx_flags &
SKBTX_HW_TSTAMP && fep->hwts_tx_en))
estatus |= BD_ENET_TX_TS;
}
}
if (fep->bufdesc_ex) {
if (fep->quirks & FEC_QUIRK_HAS_AVB)
estatus |= FEC_TX_BD_FTYPE(txq->bd.qid);
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
ebdp->cbd_esc = cpu_to_fec32(estatus);
}
bufaddr = page_address(this_frag->page.p) + this_frag->page_offset;
index = fec_enet_get_bd_index(bdp, &txq->bd);
if (((unsigned long) bufaddr) & fep->tx_align ||
fep->quirks & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], bufaddr, frag_len);
bufaddr = txq->tx_bounce[index];
if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, frag_len);
}
addr = dma_map_single(&fep->pdev->dev, bufaddr, frag_len,
DMA_TO_DEVICE);
if (dma_mapping_error(&fep->pdev->dev, addr)) {
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
goto dma_mapping_error;
}
bdp->cbd_bufaddr = cpu_to_fec32(addr);
bdp->cbd_datlen = cpu_to_fec16(frag_len);
/* Make sure the updates to rest of the descriptor are
* performed before transferring ownership.
*/
wmb();
bdp->cbd_sc = cpu_to_fec16(status);
}
return bdp;
dma_mapping_error:
bdp = txq->bd.cur;
for (i = 0; i < frag; i++) {
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
dma_unmap_single(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr),
fec16_to_cpu(bdp->cbd_datlen), DMA_TO_DEVICE);
}
return ERR_PTR(-ENOMEM);
}
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);
int nr_frags = skb_shinfo(skb)->nr_frags;
struct bufdesc *bdp, *last_bdp;
void *bufaddr;
dma_addr_t addr;
unsigned short status;
unsigned short buflen;
unsigned int estatus = 0;
unsigned int index;
int entries_free;
entries_free = fec_enet_get_free_txdesc_num(txq);
if (entries_free < MAX_SKB_FRAGS + 1) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "NOT enough BD for SG!\n");
return NETDEV_TX_OK;
}
/* Protocol checksum off-load for TCP and UDP. */
if (fec_enet_clear_csum(skb, ndev)) {
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
/* Fill in a Tx ring entry */
bdp = txq->bd.cur;
last_bdp = bdp;
status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
/* Set buffer length and buffer pointer */
bufaddr = skb->data;
buflen = skb_headlen(skb);
index = fec_enet_get_bd_index(bdp, &txq->bd);
if (((unsigned long) bufaddr) & fep->tx_align ||
fep->quirks & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], skb->data, buflen);
bufaddr = txq->tx_bounce[index];
if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, buflen);
}
/* Push the data cache so the CPM does not get stale memory data. */
addr = dma_map_single(&fep->pdev->dev, bufaddr, buflen, DMA_TO_DEVICE);
if (dma_mapping_error(&fep->pdev->dev, addr)) {
net:fec: fix WARNING caused by lack of calls to dma_mapping_error() The driver fails to check the results of DMA mapping and results in the following warning: (with kernel config "CONFIG_DMA_API_DEBUG" enable) ------------[ cut here ]------------ WARNING: at lib/dma-debug.c:937 check_unmap+0x43c/0x7d8() fec 2188000.ethernet: DMA-API: device driver failed to check map error[device address=0x00000000383a8040] [size=2048 bytes] [mapped as single] Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.10.17-16827-g9cdb0ba-dirty #188 [<80013c4c>] (unwind_backtrace+0x0/0xf8) from [<80011704>] (show_stack+0x10/0x14) [<80011704>] (show_stack+0x10/0x14) from [<80025614>] (warn_slowpath_common+0x4c/0x6c) [<80025614>] (warn_slowpath_common+0x4c/0x6c) from [<800256c8>] (warn_slowpath_fmt+0x30/0x40) [<800256c8>] (warn_slowpath_fmt+0x30/0x40) from [<8026bfdc>] (check_unmap+0x43c/0x7d8) [<8026bfdc>] (check_unmap+0x43c/0x7d8) from [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) from [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) from [<804dc8c0>] (net_rx_action+0x94/0x160) [<804dc8c0>] (net_rx_action+0x94/0x160) from [<8002c758>] (__do_softirq+0xe8/0x1d0) [<8002c758>] (__do_softirq+0xe8/0x1d0) from [<8002c8e8>] (do_softirq+0x4c/0x58) [<8002c8e8>] (do_softirq+0x4c/0x58) from [<8002cb50>] (irq_exit+0x90/0xc8) [<8002cb50>] (irq_exit+0x90/0xc8) from [<8000ea88>] (handle_IRQ+0x3c/0x94) [<8000ea88>] (handle_IRQ+0x3c/0x94) from [<8000855c>] (gic_handle_irq+0x28/0x5c) [<8000855c>] (gic_handle_irq+0x28/0x5c) from [<8000de00>] (__irq_svc+0x40/0x50) Exception stack(0x815a5f38 to 0x815a5f80) 5f20: 815a5f80 3b9aca00 5f40: 0fe52383 00000002 0dd8950e 00000002 81e7b080 00000000 00000000 815ac4d8 5f60: 806032ec 00000000 00000017 815a5f80 80059028 8041fc4c 60000013 ffffffff [<8000de00>] (__irq_svc+0x40/0x50) from [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) from [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) from [<8000edac>] (arch_cpu_idle+0x10/0x4c) [<8000edac>] (arch_cpu_idle+0x10/0x4c) from [<800582f8>] (cpu_startup_entry+0x60/0x130) [<800582f8>] (cpu_startup_entry+0x60/0x130) from [<80bc7a48>] (start_kernel+0x2d0/0x328) [<80bc7a48>] (start_kernel+0x2d0/0x328) from [<10008074>] (0x10008074) ---[ end trace c6edec32436e0042 ]--- Because dma-debug add new interfaces to debug dma mapping errors, pls refer to: http://lwn.net/Articles/516640/ After dma mapping, it must call dma_mapping_error() to check mapping error, otherwise the map_err_type alway is MAP_ERR_NOT_CHECKED, check_unmap() define the mapping is not checked and dump the error msg. So,add dma_mapping_error() checking to fix the WARNING And RX DMA buffers are used repeatedly and the driver copies it into an skb, fec_enet_rx() should not map or unmap, use dma_sync_single_for_cpu()/dma_sync_single_for_device() instead of dma_map_single()/dma_unmap_single(). There have another potential issue: fec_enet_rx() passes the DMA address to __va(). Physical and DMA addresses are *not* the same thing. They may differ if the device is behind an IOMMU or bounce buffering was required, or just because there is a fixed offset between the device and host physical addresses. Also fix it in this patch. ============================================= V2: add net_ratelimit() to limit map err message. use dma_sync_single_for_cpu() instead of dma_map_single(). fix the issue that pass DMA addresses to __va() to get virture address. V1: initial send ============================================= Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-14 09:57:10 +08:00
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
return NETDEV_TX_OK;
}
if (nr_frags) {
last_bdp = fec_enet_txq_submit_frag_skb(txq, skb, ndev);
if (IS_ERR(last_bdp)) {
dma_unmap_single(&fep->pdev->dev, addr,
buflen, DMA_TO_DEVICE);
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
} else {
status |= (BD_ENET_TX_INTR | BD_ENET_TX_LAST);
if (fep->bufdesc_ex) {
estatus = BD_ENET_TX_INT;
if (unlikely(skb_shinfo(skb)->tx_flags &
SKBTX_HW_TSTAMP && fep->hwts_tx_en))
estatus |= BD_ENET_TX_TS;
}
}
bdp->cbd_bufaddr = cpu_to_fec32(addr);
bdp->cbd_datlen = cpu_to_fec16(buflen);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
fep->hwts_tx_en))
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
if (fep->quirks & FEC_QUIRK_HAS_AVB)
estatus |= FEC_TX_BD_FTYPE(txq->bd.qid);
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
ebdp->cbd_esc = cpu_to_fec32(estatus);
}
2013-07-25 14:05:53 +08:00
index = fec_enet_get_bd_index(last_bdp, &txq->bd);
/* Save skb pointer */
txq->tx_skbuff[index] = skb;
/* Make sure the updates to rest of the descriptor are performed before
* transferring ownership.
*/
wmb();
/* Send it on its way. Tell FEC it's ready, interrupt when done,
* it's the last BD of the frame, and to put the CRC on the end.
*/
status |= (BD_ENET_TX_READY | BD_ENET_TX_TC);
bdp->cbd_sc = cpu_to_fec16(status);
/* If this was the last BD in the ring, start at the beginning again. */
bdp = fec_enet_get_nextdesc(last_bdp, &txq->bd);
skb_tx_timestamp(skb);
/* Make sure the update to bdp and tx_skbuff are performed before
* txq->bd.cur.
*/
wmb();
txq->bd.cur = bdp;
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
/* Trigger transmission start */
writel(0, txq->bd.reg_desc_active);
return 0;
}
static int
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);
struct bufdesc_ex *ebdp = container_of(bdp, struct bufdesc_ex, desc);
unsigned short status;
unsigned int estatus = 0;
dma_addr_t addr;
status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
if (((unsigned long) data) & fep->tx_align ||
fep->quirks & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], data, size);
data = txq->tx_bounce[index];
if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
swap_buffer(data, size);
}
addr = dma_map_single(&fep->pdev->dev, data, size, DMA_TO_DEVICE);
if (dma_mapping_error(&fep->pdev->dev, addr)) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
return NETDEV_TX_BUSY;
}
bdp->cbd_datlen = cpu_to_fec16(size);
bdp->cbd_bufaddr = cpu_to_fec32(addr);
if (fep->bufdesc_ex) {
if (fep->quirks & FEC_QUIRK_HAS_AVB)
estatus |= FEC_TX_BD_FTYPE(txq->bd.qid);
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
ebdp->cbd_esc = cpu_to_fec32(estatus);
}
/* Handle the last BD specially */
if (last_tcp)
status |= (BD_ENET_TX_LAST | BD_ENET_TX_TC);
if (is_last) {
status |= BD_ENET_TX_INTR;
if (fep->bufdesc_ex)
ebdp->cbd_esc |= cpu_to_fec32(BD_ENET_TX_INT);
}
bdp->cbd_sc = cpu_to_fec16(status);
return 0;
}
static int
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);
int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
struct bufdesc_ex *ebdp = container_of(bdp, struct bufdesc_ex, desc);
void *bufaddr;
unsigned long dmabuf;
unsigned short status;
unsigned int estatus = 0;
status = fec16_to_cpu(bdp->cbd_sc);
status &= ~BD_ENET_TX_STATS;
status |= (BD_ENET_TX_TC | BD_ENET_TX_READY);
bufaddr = txq->tso_hdrs + index * TSO_HEADER_SIZE;
dmabuf = txq->tso_hdrs_dma + index * TSO_HEADER_SIZE;
if (((unsigned long)bufaddr) & fep->tx_align ||
fep->quirks & FEC_QUIRK_SWAP_FRAME) {
memcpy(txq->tx_bounce[index], skb->data, hdr_len);
bufaddr = txq->tx_bounce[index];
if (fep->quirks & FEC_QUIRK_SWAP_FRAME)
swap_buffer(bufaddr, hdr_len);
dmabuf = dma_map_single(&fep->pdev->dev, bufaddr,
hdr_len, DMA_TO_DEVICE);
if (dma_mapping_error(&fep->pdev->dev, dmabuf)) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "Tx DMA memory map failed\n");
return NETDEV_TX_BUSY;
}
}
bdp->cbd_bufaddr = cpu_to_fec32(dmabuf);
bdp->cbd_datlen = cpu_to_fec16(hdr_len);
if (fep->bufdesc_ex) {
if (fep->quirks & FEC_QUIRK_HAS_AVB)
estatus |= FEC_TX_BD_FTYPE(txq->bd.qid);
if (skb->ip_summed == CHECKSUM_PARTIAL)
estatus |= BD_ENET_TX_PINS | BD_ENET_TX_IINS;
ebdp->cbd_bdu = 0;
ebdp->cbd_esc = cpu_to_fec32(estatus);
}
bdp->cbd_sc = cpu_to_fec16(status);
return 0;
}
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 = txq->bd.cur;
struct tso_t tso;
unsigned int index = 0;
int ret;
if (tso_count_descs(skb) >= fec_enet_get_free_txdesc_num(txq)) {
dev_kfree_skb_any(skb);
if (net_ratelimit())
netdev_err(ndev, "NOT enough BD for TSO!\n");
return NETDEV_TX_OK;
}
/* Protocol checksum off-load for TCP and UDP. */
if (fec_enet_clear_csum(skb, ndev)) {
dev_kfree_skb_any(skb);
return NETDEV_TX_OK;
}
/* Initialize the TSO handler, and prepare the first payload */
tso_start(skb, &tso);
total_len = skb->len - hdr_len;
while (total_len > 0) {
char *hdr;
index = fec_enet_get_bd_index(bdp, &txq->bd);
data_left = min_t(int, skb_shinfo(skb)->gso_size, total_len);
total_len -= data_left;
/* prepare packet headers: MAC + IP + TCP */
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(txq, skb, ndev, bdp, index);
if (ret)
goto err_release;
while (data_left > 0) {
int size;
size = min_t(int, tso.size, data_left);
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
index = fec_enet_get_bd_index(bdp, &txq->bd);
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;
data_left -= size;
tso_build_data(skb, &tso, size);
}
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
}
/* Save skb pointer */
txq->tx_skbuff[index] = skb;
skb_tx_timestamp(skb);
txq->bd.cur = bdp;
/* Trigger transmission start */
if (!(fep->quirks & FEC_QUIRK_ERR007885) ||
!readl(txq->bd.reg_desc_active) ||
!readl(txq->bd.reg_desc_active) ||
!readl(txq->bd.reg_desc_active) ||
!readl(txq->bd.reg_desc_active))
writel(0, txq->bd.reg_desc_active);
return 0;
err_release:
/* TODO: Release all used data descriptors for TSO */
return ret;
}
static netdev_tx_t
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(txq, skb, ndev);
else
ret = fec_enet_txq_submit_skb(txq, skb, ndev);
if (ret)
return ret;
entries_free = fec_enet_get_free_txdesc_num(txq);
if (entries_free <= txq->tx_stop_threshold)
netif_tx_stop_queue(nq);
return NETDEV_TX_OK;
}
/* Init RX & TX buffer descriptors
*/
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;
unsigned int q;
for (q = 0; q < fep->num_rx_queues; q++) {
/* Initialize the receive buffer descriptors. */
rxq = fep->rx_queue[q];
bdp = rxq->bd.base;
for (i = 0; i < rxq->bd.ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
if (bdp->cbd_bufaddr)
bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY);
else
bdp->cbd_sc = cpu_to_fec16(0);
bdp = fec_enet_get_nextdesc(bdp, &rxq->bd);
}
/* Set the last buffer to wrap */
bdp = fec_enet_get_prevdesc(bdp, &rxq->bd);
bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
rxq->bd.cur = rxq->bd.base;
}
for (q = 0; q < fep->num_tx_queues; q++) {
/* ...and the same for transmit */
txq = fep->tx_queue[q];
bdp = txq->bd.base;
txq->bd.cur = bdp;
for (i = 0; i < txq->bd.ring_size; i++) {
/* Initialize the BD for every fragment in the page. */
bdp->cbd_sc = cpu_to_fec16(0);
if (txq->tx_skbuff[i]) {
dev_kfree_skb_any(txq->tx_skbuff[i]);
txq->tx_skbuff[i] = NULL;
}
bdp->cbd_bufaddr = cpu_to_fec32(0);
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
}
/* Set the last buffer to wrap */
bdp = fec_enet_get_prevdesc(bdp, &txq->bd);
bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
txq->dirty_tx = bdp;
}
}
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->rx_queue[i]->bd.reg_desc_active);
}
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;
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));
writel(PKT_MAXBLR_SIZE, fep->hwp + FEC_R_BUFF_SIZE(i));
/* enable DMA1/2 */
if (i)
writel(RCMR_MATCHEN | RCMR_CMP(i),
fep->hwp + FEC_RCMR(i));
}
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));
}
}
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->bd.ring_size; j++) {
if (txq->tx_skbuff[j]) {
dev_kfree_skb_any(txq->tx_skbuff[j]);
txq->tx_skbuff[j] = NULL;
}
}
}
}
/*
* This function is called to start or restart the FEC during a link
* change, transmit timeout, or to reconfigure the FEC. The network
* packet processing for this device must be stopped before this call.
*/
static void
fec_restart(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
u32 val;
u32 temp_mac[2];
u32 rcntl = OPT_FRAME_SIZE | 0x04;
u32 ecntl = 0x2; /* ETHEREN */
/* Whack a reset. We should wait for this.
* For i.MX6SX SOC, enet use AXI bus, we use disable MAC
* instead of reset MAC itself.
*/
if (fep->quirks & FEC_QUIRK_HAS_AVB) {
writel(0, fep->hwp + FEC_ECNTRL);
} else {
writel(1, fep->hwp + FEC_ECNTRL);
udelay(10);
}
/*
* enet-mac reset will reset mac address registers too,
* so need to reconfigure it.
*/
if (fep->quirks & FEC_QUIRK_ENET_MAC) {
memcpy(&temp_mac, ndev->dev_addr, ETH_ALEN);
writel((__force u32)cpu_to_be32(temp_mac[0]),
fep->hwp + FEC_ADDR_LOW);
writel((__force u32)cpu_to_be32(temp_mac[1]),
fep->hwp + FEC_ADDR_HIGH);
}
/* Clear any outstanding interrupt. */
writel(0xffffffff, fep->hwp + FEC_IEVENT);
fec_enet_bd_init(ndev);
fec_enet_enable_ring(ndev);
/* Reset tx SKB buffers. */
fec_enet_reset_skb(ndev);
/* Enable MII mode */
if (fep->full_duplex == DUPLEX_FULL) {
/* FD enable */
writel(0x04, fep->hwp + FEC_X_CNTRL);
} else {
/* No Rcv on Xmit */
rcntl |= 0x02;
writel(0x0, fep->hwp + FEC_X_CNTRL);
}
/* Set MII speed */
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
#if !defined(CONFIG_M5272)
if (fep->quirks & FEC_QUIRK_HAS_RACC) {
/* set RX checksum */
val = readl(fep->hwp + FEC_RACC);
if (fep->csum_flags & FLAG_RX_CSUM_ENABLED)
val |= FEC_RACC_OPTIONS;
else
val &= ~FEC_RACC_OPTIONS;
writel(val, fep->hwp + FEC_RACC);
writel(PKT_MAXBUF_SIZE, fep->hwp + FEC_FTRL);
}
#endif
/*
* The phy interface and speed need to get configured
* differently on enet-mac.
*/
if (fep->quirks & FEC_QUIRK_ENET_MAC) {
/* Enable flow control and length check */
rcntl |= 0x40000000 | 0x00000020;
/* RGMII, RMII or MII */
if (fep->phy_interface == PHY_INTERFACE_MODE_RGMII ||
fep->phy_interface == PHY_INTERFACE_MODE_RGMII_ID ||
fep->phy_interface == PHY_INTERFACE_MODE_RGMII_RXID ||
fep->phy_interface == PHY_INTERFACE_MODE_RGMII_TXID)
rcntl |= (1 << 6);
else if (fep->phy_interface == PHY_INTERFACE_MODE_RMII)
rcntl |= (1 << 8);
else
rcntl &= ~(1 << 8);
/* 1G, 100M or 10M */
if (fep->phy_dev) {
if (fep->phy_dev->speed == SPEED_1000)
ecntl |= (1 << 5);
else if (fep->phy_dev->speed == SPEED_100)
rcntl &= ~(1 << 9);
else
rcntl |= (1 << 9);
}
} else {
#ifdef FEC_MIIGSK_ENR
if (fep->quirks & FEC_QUIRK_USE_GASKET) {
u32 cfgr;
/* disable the gasket and wait */
writel(0, fep->hwp + FEC_MIIGSK_ENR);
while (readl(fep->hwp + FEC_MIIGSK_ENR) & 4)
udelay(1);
/*
* configure the gasket:
* RMII, 50 MHz, no loopback, no echo
* MII, 25 MHz, no loopback, no echo
*/
cfgr = (fep->phy_interface == PHY_INTERFACE_MODE_RMII)
? BM_MIIGSK_CFGR_RMII : BM_MIIGSK_CFGR_MII;
if (fep->phy_dev && fep->phy_dev->speed == SPEED_10)
cfgr |= BM_MIIGSK_CFGR_FRCONT_10M;
writel(cfgr, fep->hwp + FEC_MIIGSK_CFGR);
/* re-enable the gasket */
writel(2, fep->hwp + FEC_MIIGSK_ENR);
}
#endif
}
#if !defined(CONFIG_M5272)
/* enable pause frame*/
if ((fep->pause_flag & FEC_PAUSE_FLAG_ENABLE) ||
((fep->pause_flag & FEC_PAUSE_FLAG_AUTONEG) &&
fep->phy_dev && fep->phy_dev->pause)) {
rcntl |= FEC_ENET_FCE;
/* set FIFO threshold parameter to reduce overrun */
writel(FEC_ENET_RSEM_V, fep->hwp + FEC_R_FIFO_RSEM);
writel(FEC_ENET_RSFL_V, fep->hwp + FEC_R_FIFO_RSFL);
writel(FEC_ENET_RAEM_V, fep->hwp + FEC_R_FIFO_RAEM);
writel(FEC_ENET_RAFL_V, fep->hwp + FEC_R_FIFO_RAFL);
/* OPD */
writel(FEC_ENET_OPD_V, fep->hwp + FEC_OPD);
} else {
rcntl &= ~FEC_ENET_FCE;
}
#endif /* !defined(CONFIG_M5272) */
writel(rcntl, fep->hwp + FEC_R_CNTRL);
/* Setup multicast filter. */
set_multicast_list(ndev);
#ifndef CONFIG_M5272
writel(0, fep->hwp + FEC_HASH_TABLE_HIGH);
writel(0, fep->hwp + FEC_HASH_TABLE_LOW);
#endif
if (fep->quirks & FEC_QUIRK_ENET_MAC) {
/* enable ENET endian swap */
ecntl |= (1 << 8);
/* enable ENET store and forward mode */
writel(1 << 8, fep->hwp + FEC_X_WMRK);
}
if (fep->bufdesc_ex)
ecntl |= (1 << 4);
#ifndef CONFIG_M5272
/* Enable the MIB statistic event counters */
writel(0 << 31, fep->hwp + FEC_MIB_CTRLSTAT);
#endif
/* And last, enable the transmit and receive processing */
writel(ecntl, fep->hwp + FEC_ECNTRL);
fec_enet_active_rxring(ndev);
if (fep->bufdesc_ex)
fec_ptp_start_cyclecounter(ndev);
/* Enable interrupts we wish to service */
if (fep->link)
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
else
writel(FEC_ENET_MII, fep->hwp + FEC_IMASK);
/* Init the interrupt coalescing */
fec_enet_itr_coal_init(ndev);
}
static void
fec_stop(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
u32 rmii_mode = readl(fep->hwp + FEC_R_CNTRL) & (1 << 8);
u32 val;
/* We cannot expect a graceful transmit stop without link !!! */
if (fep->link) {
writel(1, fep->hwp + FEC_X_CNTRL); /* Graceful transmit stop */
udelay(10);
if (!(readl(fep->hwp + FEC_IEVENT) & FEC_ENET_GRA))
netdev_err(ndev, "Graceful transmit stop did not complete!\n");
}
/* Whack a reset. We should wait for this.
* For i.MX6SX SOC, enet use AXI bus, we use disable MAC
* instead of reset MAC itself.
*/
if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
if (fep->quirks & FEC_QUIRK_HAS_AVB) {
writel(0, fep->hwp + FEC_ECNTRL);
} else {
writel(1, fep->hwp + FEC_ECNTRL);
udelay(10);
}
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
} else {
writel(FEC_DEFAULT_IMASK | FEC_ENET_WAKEUP, fep->hwp + FEC_IMASK);
val = readl(fep->hwp + FEC_ECNTRL);
val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
writel(val, fep->hwp + FEC_ECNTRL);
if (pdata && pdata->sleep_mode_enable)
pdata->sleep_mode_enable(true);
}
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
/* We have to keep ENET enabled to have MII interrupt stay working */
if (fep->quirks & FEC_QUIRK_ENET_MAC &&
!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
writel(2, fep->hwp + FEC_ECNTRL);
writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
}
}
static void
fec_timeout(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
fec_dump(ndev);
ndev->stats.tx_errors++;
schedule_work(&fep->tx_timeout_work);
}
static void fec_enet_timeout_work(struct work_struct *work)
{
struct fec_enet_private *fep =
container_of(work, struct fec_enet_private, tx_timeout_work);
struct net_device *ndev = fep->netdev;
rtnl_lock();
if (netif_device_present(ndev) || netif_running(ndev)) {
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
netif_wake_queue(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
rtnl_unlock();
}
static void
fec_enet_hwtstamp(struct fec_enet_private *fep, unsigned ts,
struct skb_shared_hwtstamps *hwtstamps)
{
unsigned long flags;
u64 ns;
spin_lock_irqsave(&fep->tmreg_lock, flags);
ns = timecounter_cyc2time(&fep->tc, ts);
spin_unlock_irqrestore(&fep->tmreg_lock, flags);
memset(hwtstamps, 0, sizeof(*hwtstamps));
hwtstamps->hwtstamp = ns_to_ktime(ns);
}
static void
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;
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
int index = 0;
int entries_free;
fep = netdev_priv(ndev);
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;
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
/* get next bdp of dirty_tx */
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
while (bdp != READ_ONCE(txq->bd.cur)) {
/* Order the load of bd.cur and cbd_sc */
rmb();
status = fec16_to_cpu(READ_ONCE(bdp->cbd_sc));
if (status & BD_ENET_TX_READY)
break;
index = fec_enet_get_bd_index(bdp, &txq->bd);
net: fec: fix the warning found by dma debug Enable kernel config "CONFIG_HAVE_DMA_API_DEBUG", FEC have kernel warning: [ 6.650444] fec 2188000.ethernet: DMA-API: device driver tries to free DMA memory it has not allocated [ 6.664289] Modules linked in: [ 6.667378] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 3.19.0-rc4-00688-g8834016-dirty #150 [ 6.675841] Hardware name: Freescale i.MX6 SoloX (Device Tree) [ 6.681698] Backtrace: [ 6.684189] [<80011e3c>] (dump_backtrace) from [<80011fdc>] (show_stack+0x18/0x1c) [ 6.691789] r6:80890154 r5:00000000 r4:00000000 r3:00000000 [ 6.697533] [<80011fc4>] (show_stack) from [<806d2d88>] (dump_stack+0x80/0x9c) [ 6.704799] [<806d2d08>] (dump_stack) from [<8002a4e4>] (warn_slowpath_common+0x7c/0xb4) [ 6.712917] r5:00000445 r4:00000000 [ 6.716544] [<8002a468>] (warn_slowpath_common) from [<8002a5c0>] (warn_slowpath_fmt+0x38/0x40) [ 6.725265] r8:809a2ee8 r7:00000000 r6:00000000 r5:00000000 r4:00000042 [ 6.732087] [<8002a58c>] (warn_slowpath_fmt) from [<802d6268>] (check_unmap+0x86c/0x98c) [ 6.740202] r3:808c79bc r2:8089060c [ 6.743826] [<802d59fc>] (check_unmap) from [<802d65e4>] (debug_dma_unmap_page+0x80/0x88) [ 6.752029] r10:00000000 r9:00000000 r8:00000000 r7:00000001 r6:be12a410 r5:00000000 [ 6.759967] r4:00000042 [ 6.762538] [<802d6564>] (debug_dma_unmap_page) from [<80440248>] (fec_enet_rx_napi+0x7ec/0xb9c) [ 6.771345] r7:00000400 r6:be3e4000 r5:bf08fa20 r4:be036000 [ 6.777094] [<8043fa5c>] (fec_enet_rx_napi) from [<8056ae24>] (net_rx_action+0x134/0x324) [ 6.785297] r10:be089e60 r9:80998180 r8:ffff8d68 r7:0000012c r6:00000040 r5:00000001 [ 6.793239] r4:be036718 [ 6.795801] [<8056acf0>] (net_rx_action) from [<8002db24>] (__do_softirq+0x138/0x2d0) [ 6.803655] r10:00000003 r9:00000003 r8:80996378 r7:8099c080 r6:00000100 r5:8099c08c [ 6.811593] r4:00000000 [ 6.814157] [<8002d9ec>] (__do_softirq) from [<8002dd00>] (run_ksoftirqd+0x44/0x5c) [ 6.821836] r10:00000000 r9:00000000 r8:809b133c r7:00000000 r6:00000001 r5:00000000 [ 6.829775] r4:be027e80 [ 6.832346] [<8002dcbc>] (run_ksoftirqd) from [<80048290>] (smpboot_thread_fn+0x154/0x1c4) [ 6.840649] [<8004813c>] (smpboot_thread_fn) from [<80044780>] (kthread+0xdc/0xf8) [ 6.848224] r10:00000000 r8:00000000 r7:8004813c r6:be027e80 r5:be027ec0 r4:00000000 [ 6.856179] [<800446a4>] (kthread) from [<8000ebc8>] (ret_from_fork+0x14/0x2c) [ 6.863425] r7:00000000 r6:00000000 r5:800446a4 r4:be027ec0 [ 6.869156] ---[ end trace 861cf914d2461a8b ]--- There have one bug in .fec_enet_tx_queue() function to unmap the DMA memory: For SG or TSO, get one buffer descriptor and then unmap the related DMA memory, and then get the next buffer descriptor, loop to while() to check "TX_READY". If "TX_READY" bit still __IS__ existed in the BD (The next fraglist or next TSO packet is not transmited complitely), exit the current clean work. When the next work is triggered, it still repeat above step with the same BD. The potential issue is that unmap the same DMA memory for multiple times. The patch fix the clean work for SG and TSO packet. Reported-by: Anand Moon <moon.linux@yahoo.com> Reported-by: Christian Gmeiner <christian.gmeiner@gmail.com> Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-20 14:10:35 +08:00
skb = txq->tx_skbuff[index];
net: fec: fix the warning found by dma debug Enable kernel config "CONFIG_HAVE_DMA_API_DEBUG", FEC have kernel warning: [ 6.650444] fec 2188000.ethernet: DMA-API: device driver tries to free DMA memory it has not allocated [ 6.664289] Modules linked in: [ 6.667378] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 3.19.0-rc4-00688-g8834016-dirty #150 [ 6.675841] Hardware name: Freescale i.MX6 SoloX (Device Tree) [ 6.681698] Backtrace: [ 6.684189] [<80011e3c>] (dump_backtrace) from [<80011fdc>] (show_stack+0x18/0x1c) [ 6.691789] r6:80890154 r5:00000000 r4:00000000 r3:00000000 [ 6.697533] [<80011fc4>] (show_stack) from [<806d2d88>] (dump_stack+0x80/0x9c) [ 6.704799] [<806d2d08>] (dump_stack) from [<8002a4e4>] (warn_slowpath_common+0x7c/0xb4) [ 6.712917] r5:00000445 r4:00000000 [ 6.716544] [<8002a468>] (warn_slowpath_common) from [<8002a5c0>] (warn_slowpath_fmt+0x38/0x40) [ 6.725265] r8:809a2ee8 r7:00000000 r6:00000000 r5:00000000 r4:00000042 [ 6.732087] [<8002a58c>] (warn_slowpath_fmt) from [<802d6268>] (check_unmap+0x86c/0x98c) [ 6.740202] r3:808c79bc r2:8089060c [ 6.743826] [<802d59fc>] (check_unmap) from [<802d65e4>] (debug_dma_unmap_page+0x80/0x88) [ 6.752029] r10:00000000 r9:00000000 r8:00000000 r7:00000001 r6:be12a410 r5:00000000 [ 6.759967] r4:00000042 [ 6.762538] [<802d6564>] (debug_dma_unmap_page) from [<80440248>] (fec_enet_rx_napi+0x7ec/0xb9c) [ 6.771345] r7:00000400 r6:be3e4000 r5:bf08fa20 r4:be036000 [ 6.777094] [<8043fa5c>] (fec_enet_rx_napi) from [<8056ae24>] (net_rx_action+0x134/0x324) [ 6.785297] r10:be089e60 r9:80998180 r8:ffff8d68 r7:0000012c r6:00000040 r5:00000001 [ 6.793239] r4:be036718 [ 6.795801] [<8056acf0>] (net_rx_action) from [<8002db24>] (__do_softirq+0x138/0x2d0) [ 6.803655] r10:00000003 r9:00000003 r8:80996378 r7:8099c080 r6:00000100 r5:8099c08c [ 6.811593] r4:00000000 [ 6.814157] [<8002d9ec>] (__do_softirq) from [<8002dd00>] (run_ksoftirqd+0x44/0x5c) [ 6.821836] r10:00000000 r9:00000000 r8:809b133c r7:00000000 r6:00000001 r5:00000000 [ 6.829775] r4:be027e80 [ 6.832346] [<8002dcbc>] (run_ksoftirqd) from [<80048290>] (smpboot_thread_fn+0x154/0x1c4) [ 6.840649] [<8004813c>] (smpboot_thread_fn) from [<80044780>] (kthread+0xdc/0xf8) [ 6.848224] r10:00000000 r8:00000000 r7:8004813c r6:be027e80 r5:be027ec0 r4:00000000 [ 6.856179] [<800446a4>] (kthread) from [<8000ebc8>] (ret_from_fork+0x14/0x2c) [ 6.863425] r7:00000000 r6:00000000 r5:800446a4 r4:be027ec0 [ 6.869156] ---[ end trace 861cf914d2461a8b ]--- There have one bug in .fec_enet_tx_queue() function to unmap the DMA memory: For SG or TSO, get one buffer descriptor and then unmap the related DMA memory, and then get the next buffer descriptor, loop to while() to check "TX_READY". If "TX_READY" bit still __IS__ existed in the BD (The next fraglist or next TSO packet is not transmited complitely), exit the current clean work. When the next work is triggered, it still repeat above step with the same BD. The potential issue is that unmap the same DMA memory for multiple times. The patch fix the clean work for SG and TSO packet. Reported-by: Anand Moon <moon.linux@yahoo.com> Reported-by: Christian Gmeiner <christian.gmeiner@gmail.com> Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-20 14:10:35 +08:00
txq->tx_skbuff[index] = NULL;
if (!IS_TSO_HEADER(txq, fec32_to_cpu(bdp->cbd_bufaddr)))
dma_unmap_single(&fep->pdev->dev,
fec32_to_cpu(bdp->cbd_bufaddr),
fec16_to_cpu(bdp->cbd_datlen),
DMA_TO_DEVICE);
bdp->cbd_bufaddr = cpu_to_fec32(0);
if (!skb) {
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
continue;
}
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
/* Check for errors. */
if (status & (BD_ENET_TX_HB | BD_ENET_TX_LC |
BD_ENET_TX_RL | BD_ENET_TX_UN |
BD_ENET_TX_CSL)) {
ndev->stats.tx_errors++;
if (status & BD_ENET_TX_HB) /* No heartbeat */
ndev->stats.tx_heartbeat_errors++;
if (status & BD_ENET_TX_LC) /* Late collision */
ndev->stats.tx_window_errors++;
if (status & BD_ENET_TX_RL) /* Retrans limit */
ndev->stats.tx_aborted_errors++;
if (status & BD_ENET_TX_UN) /* Underrun */
ndev->stats.tx_fifo_errors++;
if (status & BD_ENET_TX_CSL) /* Carrier lost */
ndev->stats.tx_carrier_errors++;
} else {
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += skb->len;
}
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS) &&
fep->bufdesc_ex) {
struct skb_shared_hwtstamps shhwtstamps;
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts), &shhwtstamps);
skb_tstamp_tx(skb, &shhwtstamps);
}
/* Deferred means some collisions occurred during transmit,
* but we eventually sent the packet OK.
*/
if (status & BD_ENET_TX_DEF)
ndev->stats.collisions++;
/* Free the sk buffer associated with this last transmit */
dev_kfree_skb_any(skb);
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
/* Make sure the update to bdp and tx_skbuff are performed
* before dirty_tx
*/
wmb();
txq->dirty_tx = bdp;
/* Update pointer to next buffer descriptor to be transmitted */
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
/* 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(txq);
if (entries_free >= txq->tx_wake_threshold)
netif_tx_wake_queue(nq);
}
}
/* ERR006538: Keep the transmitter going */
if (bdp != txq->bd.cur &&
readl(txq->bd.reg_desc_active) == 0)
writel(0, txq->bd.reg_desc_active);
}
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;
}
static int
fec_enet_new_rxbdp(struct net_device *ndev, struct bufdesc *bdp, struct sk_buff *skb)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int off;
off = ((unsigned long)skb->data) & fep->rx_align;
if (off)
skb_reserve(skb, fep->rx_align + 1 - off);
bdp->cbd_bufaddr = cpu_to_fec32(dma_map_single(&fep->pdev->dev, skb->data, FEC_ENET_RX_FRSIZE - fep->rx_align, DMA_FROM_DEVICE));
if (dma_mapping_error(&fep->pdev->dev, fec32_to_cpu(bdp->cbd_bufaddr))) {
if (net_ratelimit())
netdev_err(ndev, "Rx DMA memory map failed\n");
return -ENOMEM;
}
return 0;
}
static bool fec_enet_copybreak(struct net_device *ndev, struct sk_buff **skb,
struct bufdesc *bdp, u32 length, bool swap)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct sk_buff *new_skb;
if (length > fep->rx_copybreak)
return false;
new_skb = netdev_alloc_skb(ndev, length);
if (!new_skb)
return false;
dma_sync_single_for_cpu(&fep->pdev->dev,
fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
if (!swap)
memcpy(new_skb->data, (*skb)->data, length);
else
swap_buffer2(new_skb->data, (*skb)->data, length);
*skb = new_skb;
return true;
}
/* During a receive, the bd_rx.cur points to the current incoming buffer.
* When we update through the ring, if the next incoming buffer has
* not been given to the system, we just set the empty indicator,
* effectively tossing the packet.
*/
static int
fec_enet_rx_queue(struct net_device *ndev, int budget, u16 queue_id)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct fec_enet_priv_rx_q *rxq;
struct bufdesc *bdp;
unsigned short status;
struct sk_buff *skb_new = NULL;
struct sk_buff *skb;
ushort pkt_len;
__u8 *data;
int pkt_received = 0;
struct bufdesc_ex *ebdp = NULL;
bool vlan_packet_rcvd = false;
u16 vlan_tag;
net:fec: fix WARNING caused by lack of calls to dma_mapping_error() The driver fails to check the results of DMA mapping and results in the following warning: (with kernel config "CONFIG_DMA_API_DEBUG" enable) ------------[ cut here ]------------ WARNING: at lib/dma-debug.c:937 check_unmap+0x43c/0x7d8() fec 2188000.ethernet: DMA-API: device driver failed to check map error[device address=0x00000000383a8040] [size=2048 bytes] [mapped as single] Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.10.17-16827-g9cdb0ba-dirty #188 [<80013c4c>] (unwind_backtrace+0x0/0xf8) from [<80011704>] (show_stack+0x10/0x14) [<80011704>] (show_stack+0x10/0x14) from [<80025614>] (warn_slowpath_common+0x4c/0x6c) [<80025614>] (warn_slowpath_common+0x4c/0x6c) from [<800256c8>] (warn_slowpath_fmt+0x30/0x40) [<800256c8>] (warn_slowpath_fmt+0x30/0x40) from [<8026bfdc>] (check_unmap+0x43c/0x7d8) [<8026bfdc>] (check_unmap+0x43c/0x7d8) from [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) from [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) from [<804dc8c0>] (net_rx_action+0x94/0x160) [<804dc8c0>] (net_rx_action+0x94/0x160) from [<8002c758>] (__do_softirq+0xe8/0x1d0) [<8002c758>] (__do_softirq+0xe8/0x1d0) from [<8002c8e8>] (do_softirq+0x4c/0x58) [<8002c8e8>] (do_softirq+0x4c/0x58) from [<8002cb50>] (irq_exit+0x90/0xc8) [<8002cb50>] (irq_exit+0x90/0xc8) from [<8000ea88>] (handle_IRQ+0x3c/0x94) [<8000ea88>] (handle_IRQ+0x3c/0x94) from [<8000855c>] (gic_handle_irq+0x28/0x5c) [<8000855c>] (gic_handle_irq+0x28/0x5c) from [<8000de00>] (__irq_svc+0x40/0x50) Exception stack(0x815a5f38 to 0x815a5f80) 5f20: 815a5f80 3b9aca00 5f40: 0fe52383 00000002 0dd8950e 00000002 81e7b080 00000000 00000000 815ac4d8 5f60: 806032ec 00000000 00000017 815a5f80 80059028 8041fc4c 60000013 ffffffff [<8000de00>] (__irq_svc+0x40/0x50) from [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) from [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) from [<8000edac>] (arch_cpu_idle+0x10/0x4c) [<8000edac>] (arch_cpu_idle+0x10/0x4c) from [<800582f8>] (cpu_startup_entry+0x60/0x130) [<800582f8>] (cpu_startup_entry+0x60/0x130) from [<80bc7a48>] (start_kernel+0x2d0/0x328) [<80bc7a48>] (start_kernel+0x2d0/0x328) from [<10008074>] (0x10008074) ---[ end trace c6edec32436e0042 ]--- Because dma-debug add new interfaces to debug dma mapping errors, pls refer to: http://lwn.net/Articles/516640/ After dma mapping, it must call dma_mapping_error() to check mapping error, otherwise the map_err_type alway is MAP_ERR_NOT_CHECKED, check_unmap() define the mapping is not checked and dump the error msg. So,add dma_mapping_error() checking to fix the WARNING And RX DMA buffers are used repeatedly and the driver copies it into an skb, fec_enet_rx() should not map or unmap, use dma_sync_single_for_cpu()/dma_sync_single_for_device() instead of dma_map_single()/dma_unmap_single(). There have another potential issue: fec_enet_rx() passes the DMA address to __va(). Physical and DMA addresses are *not* the same thing. They may differ if the device is behind an IOMMU or bounce buffering was required, or just because there is a fixed offset between the device and host physical addresses. Also fix it in this patch. ============================================= V2: add net_ratelimit() to limit map err message. use dma_sync_single_for_cpu() instead of dma_map_single(). fix the issue that pass DMA addresses to __va() to get virture address. V1: initial send ============================================= Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-14 09:57:10 +08:00
int index = 0;
bool is_copybreak;
bool need_swap = fep->quirks & FEC_QUIRK_SWAP_FRAME;
#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 = rxq->bd.cur;
while (!((status = fec16_to_cpu(bdp->cbd_sc)) & BD_ENET_RX_EMPTY)) {
if (pkt_received >= budget)
break;
pkt_received++;
writel(FEC_ENET_RXF, fep->hwp + FEC_IEVENT);
/* Check for errors. */
status ^= BD_ENET_RX_LAST;
if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH | BD_ENET_RX_NO |
BD_ENET_RX_CR | BD_ENET_RX_OV | BD_ENET_RX_LAST |
BD_ENET_RX_CL)) {
ndev->stats.rx_errors++;
if (status & BD_ENET_RX_OV) {
/* FIFO overrun */
ndev->stats.rx_fifo_errors++;
goto rx_processing_done;
}
if (status & (BD_ENET_RX_LG | BD_ENET_RX_SH
| BD_ENET_RX_LAST)) {
/* Frame too long or too short. */
ndev->stats.rx_length_errors++;
if (status & BD_ENET_RX_LAST)
netdev_err(ndev, "rcv is not +last\n");
}
if (status & BD_ENET_RX_CR) /* CRC Error */
ndev->stats.rx_crc_errors++;
/* Report late collisions as a frame error. */
if (status & (BD_ENET_RX_NO | BD_ENET_RX_CL))
ndev->stats.rx_frame_errors++;
goto rx_processing_done;
}
/* Process the incoming frame. */
ndev->stats.rx_packets++;
pkt_len = fec16_to_cpu(bdp->cbd_datlen);
ndev->stats.rx_bytes += pkt_len;
index = fec_enet_get_bd_index(bdp, &rxq->bd);
skb = rxq->rx_skbuff[index];
/* The packet length includes FCS, but we don't want to
* include that when passing upstream as it messes up
* bridging applications.
*/
is_copybreak = fec_enet_copybreak(ndev, &skb, bdp, pkt_len - 4,
need_swap);
if (!is_copybreak) {
skb_new = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
if (unlikely(!skb_new)) {
ndev->stats.rx_dropped++;
goto rx_processing_done;
}
dma_unmap_single(&fep->pdev->dev,
fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
}
prefetch(skb->data - NET_IP_ALIGN);
skb_put(skb, pkt_len - 4);
data = skb->data;
if (!is_copybreak && need_swap)
swap_buffer(data, pkt_len);
/* Extract the enhanced buffer descriptor */
ebdp = NULL;
if (fep->bufdesc_ex)
ebdp = (struct bufdesc_ex *)bdp;
/* 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 & cpu_to_fec32(BD_ENET_RX_VLAN))) {
/* Push and remove the vlan tag */
struct vlan_hdr *vlan_header =
(struct vlan_hdr *) (data + ETH_HLEN);
vlan_tag = ntohs(vlan_header->h_vlan_TCI);
vlan_packet_rcvd = true;
memmove(skb->data + VLAN_HLEN, data, ETH_ALEN * 2);
skb_pull(skb, VLAN_HLEN);
}
skb->protocol = eth_type_trans(skb, ndev);
/* Get receive timestamp from the skb */
if (fep->hwts_rx_en && fep->bufdesc_ex)
fec_enet_hwtstamp(fep, fec32_to_cpu(ebdp->ts),
skb_hwtstamps(skb));
if (fep->bufdesc_ex &&
(fep->csum_flags & FLAG_RX_CSUM_ENABLED)) {
if (!(ebdp->cbd_esc & cpu_to_fec32(FLAG_RX_CSUM_ERROR))) {
/* don't check it */
skb->ip_summed = CHECKSUM_UNNECESSARY;
} else {
skb_checksum_none_assert(skb);
}
}
/* Handle received VLAN packets */
if (vlan_packet_rcvd)
__vlan_hwaccel_put_tag(skb,
htons(ETH_P_8021Q),
vlan_tag);
napi_gro_receive(&fep->napi, skb);
if (is_copybreak) {
dma_sync_single_for_device(&fep->pdev->dev,
fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
} else {
rxq->rx_skbuff[index] = skb_new;
fec_enet_new_rxbdp(ndev, bdp, skb_new);
}
rx_processing_done:
/* Clear the status flags for this buffer */
status &= ~BD_ENET_RX_STATS;
/* Mark the buffer empty */
status |= BD_ENET_RX_EMPTY;
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT);
ebdp->cbd_prot = 0;
ebdp->cbd_bdu = 0;
}
/* Make sure the updates to rest of the descriptor are
* performed before transferring ownership.
*/
wmb();
bdp->cbd_sc = cpu_to_fec16(status);
/* Update BD pointer to next entry */
bdp = fec_enet_get_nextdesc(bdp, &rxq->bd);
/* 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, rxq->bd.reg_desc_active);
}
rxq->bd.cur = 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_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;
}
static irqreturn_t
fec_enet_interrupt(int irq, void *dev_id)
{
struct net_device *ndev = dev_id;
struct fec_enet_private *fep = netdev_priv(ndev);
uint int_events;
irqreturn_t ret = IRQ_NONE;
net: fec: fix interrupt handling races While running: while :; do iperf -c <HOST> -P 4; done, transmit timeouts are regularly reported. With the tx ring dumping in place, we can see that all entries are in use, and the hardware has finished transmitting these packets. However, the driver has not reclaimed these ring entries. This can occur if the interrupt handler is invoked at the wrong moment - eg: CPU0 CPU1 fec_enet_tx() interrupt, IEVENT = FEC_ENET_TXF FEC_ENET_TXF cleared napi_schedule_prep() napi_complete() The result is that we clear the transmit interrupt, but we don't trigger any cleaning of the transmit ring. Instead, use a different strategy: - When receiving a transmit or receive interrupt, disable both tx and rx interrupts, but do not acknowledge them. Schedule a napi poll. Don't loop. - When we are polled, read IEVENT, acknowledging the pending transmit and receive interrupts, before then going on to process the appropriate rings. This allows us to avoid the race, and has a number of other advantages: - we cut down on the number of transmit interrupts we have to process. - we only look at the rings which have pending events. - we gain additional throughput: the iperf total bandwidth increases from about 180Mbps to 240Mbps: [ 3] 0.0-10.0 sec 68.1 MBytes 57.0 Mbits/sec [ 5] 0.0-10.0 sec 72.4 MBytes 60.5 Mbits/sec [ 4] 0.0-10.1 sec 76.1 MBytes 63.5 Mbits/sec [ 6] 0.0-10.1 sec 71.9 MBytes 59.9 Mbits/sec [SUM] 0.0-10.1 sec 288 MBytes 241 Mbits/sec Acked-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-08 07:22:44 +08:00
int_events = readl(fep->hwp + FEC_IEVENT);
net: fec: Fix NAPI race Do camera capture test on i.MX6q sabresd board, and save the capture data to nfs rootfs. The command is: gst-launch-1.0 -e imxv4l2src device=/dev/video1 num-buffers=2592000 ! tee name=t ! queue ! imxv4l2sink sync=false t. ! queue ! vpuenc ! queue ! mux. pulsesrc num-buffers=3720937 blocksize=4096 ! 'audio/x-raw, rate=44100, channels=2' ! queue ! imxmp3enc ! mpegaudioparse ! queue ! mux. qtmux name=mux ! filesink location=video_recording_long.mov After about 10 hours running, there have net watchdog timeout kernel dump: ... WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x2b4/0x2d8() NETDEV WATCHDOG: eth0 (fec): transmit queue 0 timed out CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.14.24-01051-gdb840b7 #440 [<80014e6c>] (unwind_backtrace) from [<800118ac>] (show_stack+0x10/0x14) [<800118ac>] (show_stack) from [<806ae3f0>] (dump_stack+0x78/0xc0) [<806ae3f0>] (dump_stack) from [<8002b504>] (warn_slowpath_common+0x68/0x8c) [<8002b504>] (warn_slowpath_common) from [<8002b558>] (warn_slowpath_fmt+0x30/0x40) [<8002b558>] (warn_slowpath_fmt) from [<8055e0d4>] (dev_watchdog+0x2b4/0x2d8) [<8055e0d4>] (dev_watchdog) from [<800352d8>] (call_timer_fn.isra.33+0x24/0x8c) [<800352d8>] (call_timer_fn.isra.33) from [<800354c4>] (run_timer_softirq+0x184/0x220) [<800354c4>] (run_timer_softirq) from [<8002f420>] (__do_softirq+0xc0/0x22c) [<8002f420>] (__do_softirq) from [<8002f804>] (irq_exit+0xa8/0xf4) [<8002f804>] (irq_exit) from [<8000ee5c>] (handle_IRQ+0x54/0xb4) [<8000ee5c>] (handle_IRQ) from [<80008598>] (gic_handle_irq+0x28/0x5c) [<80008598>] (gic_handle_irq) from [<800123c0>] (__irq_svc+0x40/0x74) Exception stack(0x80d27f18 to 0x80d27f60) 7f00: 80d27f60 0000014c 7f20: 8858c60e 0000004d 884e4540 0000004d ab7250d0 80d34348 00000000 00000000 7f40: 00000001 00000000 00000017 80d27f60 800702a4 80476e6c 600f0013 ffffffff [<800123c0>] (__irq_svc) from [<80476e6c>] (cpuidle_enter_state+0x50/0xe0) [<80476e6c>] (cpuidle_enter_state) from [<80476fa8>] (cpuidle_idle_call+0xac/0x154) [<80476fa8>] (cpuidle_idle_call) from [<8000f174>] (arch_cpu_idle+0x8/0x44) [<8000f174>] (arch_cpu_idle) from [<80064c54>] (cpu_startup_entry+0x100/0x158) [<80064c54>] (cpu_startup_entry) from [<80cd8a9c>] (start_kernel+0x304/0x368) ---[ end trace 09ebd32fb032f86d ]--- ... There might have a race in napi_schedule(), leaving interrupts disabled forever. After these patch, the case still work more than 40 hours running. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-16 18:25:58 +08:00
writel(int_events, fep->hwp + FEC_IEVENT);
fec_enet_collect_events(fep, int_events);
net: fec: fix rcv is not last issue when do suspend/resume test When do suspend/resume stress test, some log shows "rcv is not +last". The issue is that enet suspend will disable phy clock, phy link down, after resume back, enet MAC redo initial and ready to tx/rx packet, but phy still is not ready which is doing auto-negotiation. When phy link is not up, don't schdule napi soft irq. [Peter] It has fixed kernel panic after long time suspend/resume test with nfs rootfs. [ 8864.429458] fec 2188000.ethernet eth0: rcv is not +last [ 8864.434799] fec 2188000.ethernet eth0: rcv is not +last [ 8864.440088] fec 2188000.ethernet eth0: rcv is not +last [ 8864.445424] fec 2188000.ethernet eth0: rcv is not +last [ 8864.450782] fec 2188000.ethernet eth0: rcv is not +last [ 8864.456111] Unable to handle kernel NULL pointer dereference at virtual address 00000000 [ 8864.464225] pgd = 80004000 [ 8864.466997] [00000000] *pgd=00000000 [ 8864.470627] Internal error: Oops: 17 [#1] SMP ARM [ 8864.475353] Modules linked in: evbug [ 8864.479006] CPU: 0 PID: 3 Comm: ksoftirqd/0 Not tainted 4.0.0-rc1-00044-g7a2a1d2 #234 [ 8864.486854] Hardware name: Freescale i.MX6 SoloX (Device Tree) [ 8864.492709] task: be069380 ti: be07a000 task.ti: be07a000 [ 8864.498137] PC is at memcpy+0x80/0x330 [ 8864.501919] LR is at gro_pull_from_frag0+0x34/0xa8 [ 8864.506735] pc : [<802bb080>] lr : [<8057c204>] psr: 00000113 [ 8864.506735] sp : be07bbd4 ip : 00000010 fp : be07bc0c [ 8864.518235] r10: 0000000e r9 : 00000000 r8 : 809c7754 [ 8864.523479] r7 : 809c7754 r6 : bb43c040 r5 : bd280cc0 r4 : 00000012 [ 8864.530025] r3 : 00000804 r2 : fffffff2 r1 : 00000000 r0 : bb43b83c [ 8864.536575] Flags: nzcv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel [ 8864.543904] Control: 10c5387d Table: bd14c04a DAC: 00000015 [ 8864.549669] Process ksoftirqd/0 (pid: 3, stack limit = 0xbe07a210) [ 8864.555869] Stack: (0xbe07bbd4 to 0xbe07c000) [ 8864.560250] bbc0: bd280cc0 bb43c040 809c7754 [ 8864.568455] bbe0: 809c7754 bb43b83c 00000012 8057c204 00000000 bd280cc0 bd8a0718 00000003 [ 8864.576658] bc00: be07bc5c be07bc10 8057ebf0 8057c1dc 00000000 00000000 8057ecc4 bef59760 [ 8864.584863] bc20: 00000002 bd8a0000 be07bc64 809c7754 00000000 bd8a0718 bd280cc0 bd8a0000 [ 8864.593066] bc40: 00000000 0000001c 00000000 bd8a0000 be07bc74 be07bc60 8057f148 8057eb90 [ 8864.601268] bc60: bf0810a0 00000000 be07bcf4 be07bc78 8044e7b4 8057f12c 00000000 8007df6c [ 8864.609470] bc80: bd8a0718 00000040 00000000 bd280a80 00000002 00000019 bd8a0600 bd8a1214 [ 8864.617672] bca0: bd8a0690 bf0810a0 00000000 00000000 bd8a1000 00000000 00000027 bd280cc0 [ 8864.625874] bcc0: 80062708 800625cc 000943db bd8a0718 00000001 000d1166 00000040 be7c1ec0 [ 8864.634077] bce0: 0000012c be07bd00 be07bd3c be07bcf8 8057fc98 8044e3ac 809c2ec0 3ddff000 [ 8864.642280] bd00: be07bd00 be07bd00 be07bd08 be07bd08 00000000 00000020 809c608c 00000003 [ 8864.650481] bd20: 809c6080 40000001 809c6088 00200100 be07bd84 be07bd40 8002e690 8057fac8 [ 8864.658684] bd40: be07bd64 be07bd50 00000001 04208040 000d1165 0000000a be07bd84 809c0d7c [ 8864.666885] bd60: 00000000 809c6af8 00000000 00000001 be008000 00000000 be07bd9c be07bd88 [ 8864.675087] bd80: 8002eb64 8002e564 00000125 809c0d7c be07bdc4 be07bda0 8006f100 8002eaac [ 8864.683291] bda0: c080e10c be07bde8 809c6c6c c080e100 00000002 00000000 be07bde4 be07bdc8 [ 8864.691492] bdc0: 800087a0 8006f098 806f2934 20000013 ffffffff be07be1c be07be44 be07bde8 [ 8864.699695] bde0: 800133a4 80008784 00000001 00000001 00000000 00000000 be7c1680 00000000 [ 8864.707896] be00: be0cfe00 bd93eb40 00000002 00000000 00000000 be07be44 be07be00 be07be30 [ 8864.716098] be20: 8006278c 806f2934 20000013 ffffffff be069380 be7c1680 be07be7c be07be48 [ 8864.724300] be40: 80049cfc 806f2910 00000001 00000000 80049cb4 00000000 be07be7c be7c1680 [ 8864.732502] be60: be3289c0 be069380 bd23b600 be0cfe00 be07bebc be07be80 806ed614 80049c68 [ 8864.740706] be80: be07a000 0000020a 809c608c 00000003 00000001 8002e858 be07a000 be035740 [ 8864.748907] bea0: 00000000 00000001 809d4598 00000000 be07bed4 be07bec0 806edd0c 806ed440 [ 8864.757110] bec0: be07a000 be07a000 be07bee4 be07bed8 806edd68 806edcf0 be07bef4 be07bee8 [ 8864.765311] bee0: 8002e860 806edd34 be07bf24 be07bef8 800494b0 8002e828 be069380 00000000 [ 8864.773512] bf00: be035780 be035740 8004938c 00000000 00000000 00000000 be07bfac be07bf28 [ 8864.781715] bf20: 80045928 80049398 be07bf44 00000001 00000000 be035740 00000000 00030003 [ 8864.789917] bf40: dead4ead ffffffff ffffffff 80a2716c 80b59b00 00000000 8088c954 be07bf5c [ 8864.798120] bf60: be07bf5c 00000000 00000000 dead4ead ffffffff ffffffff 80a2716c 00000000 [ 8864.806320] bf80: 00000000 8088c954 be07bf88 be07bf88 be035780 8004584c 00000000 00000000 [ 8864.814523] bfa0: 00000000 be07bfb0 8000ed10 80045858 00000000 00000000 00000000 00000000 [ 8864.822723] bfc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 [ 8864.830925] bfe0: 00000000 00000000 00000000 00000000 00000013 00000000 5ffbb5f7 f9fcf5e7 [ 8864.839115] Backtrace: [ 8864.841631] [<8057c1d0>] (gro_pull_from_frag0) from [<8057ebf0>] (dev_gro_receive+0x6c/0x3f8) [ 8864.850173] r6:00000003 r5:bd8a0718 r4:bd280cc0 r3:00000000 [ 8864.855958] [<8057eb84>] (dev_gro_receive) from [<8057f148>] (napi_gro_receive+0x28/0xac) [ 8864.864152] r10:bd8a0000 r9:00000000 r8:0000001c r7:00000000 r6:bd8a0000 r5:bd280cc0 [ 8864.872115] r4:bd8a0718 [ 8864.874713] [<8057f120>] (napi_gro_receive) from [<8044e7b4>] (fec_enet_rx_napi+0x414/0xc74) [ 8864.883167] r5:00000000 r4:bf0810a0 [ 8864.886823] [<8044e3a0>] (fec_enet_rx_napi) from [<8057fc98>] (net_rx_action+0x1dc/0x2ec) [ 8864.895016] r10:be07bd00 r9:0000012c r8:be7c1ec0 r7:00000040 r6:000d1166 r5:00000001 [ 8864.902982] r4:bd8a0718 [ 8864.905570] [<8057fabc>] (net_rx_action) from [<8002e690>] (__do_softirq+0x138/0x2c4) [ 8864.913417] r10:00200100 r9:809c6088 r8:40000001 r7:809c6080 r6:00000003 r5:809c608c [ 8864.921382] r4:00000020 [ 8864.923966] [<8002e558>] (__do_softirq) from [<8002eb64>] (irq_exit+0xc4/0x138) [ 8864.931289] r10:00000000 r9:be008000 r8:00000001 r7:00000000 r6:809c6af8 r5:00000000 [ 8864.939252] r4:809c0d7c [ 8864.941841] [<8002eaa0>] (irq_exit) from [<8006f100>] (__handle_domain_irq+0x74/0xe8) [ 8864.949688] r4:809c0d7c r3:00000125 [ 8864.953342] [<8006f08c>] (__handle_domain_irq) from [<800087a0>] (gic_handle_irq+0x28/0x68) [ 8864.961707] r9:00000000 r8:00000002 r7:c080e100 r6:809c6c6c r5:be07bde8 r4:c080e10c [ 8864.969597] [<80008778>] (gic_handle_irq) from [<800133a4>] (__irq_svc+0x44/0x5c) [ 8864.977097] Exception stack(0xbe07bde8 to 0xbe07be30) [ 8864.982173] bde0: 00000001 00000001 00000000 00000000 be7c1680 00000000 [ 8864.990377] be00: be0cfe00 bd93eb40 00000002 00000000 00000000 be07be44 be07be00 be07be30 [ 8864.998573] be20: 8006278c 806f2934 20000013 ffffffff [ 8865.003638] r7:be07be1c r6:ffffffff r5:20000013 r4:806f2934 [ 8865.009447] [<806f2904>] (_raw_spin_unlock_irq) from [<80049cfc>] (finish_task_switch+0xa0/0x160) [ 8865.018334] r4:be7c1680 r3:be069380 [ 8865.021993] [<80049c5c>] (finish_task_switch) from [<806ed614>] (__schedule+0x1e0/0x5dc) [ 8865.030098] r8:be0cfe00 r7:bd23b600 r6:be069380 r5:be3289c0 r4:be7c1680 [ 8865.036942] [<806ed434>] (__schedule) from [<806edd0c>] (preempt_schedule_common+0x28/0x44) [ 8865.045307] r9:00000000 r8:809d4598 r7:00000001 r6:00000000 r5:be035740 r4:be07a000 [ 8865.053197] [<806edce4>] (preempt_schedule_common) from [<806edd68>] (_cond_resched+0x40/0x48) [ 8865.061822] r4:be07a000 r3:be07a000 [ 8865.065472] [<806edd28>] (_cond_resched) from [<8002e860>] (run_ksoftirqd+0x44/0x64) [ 8865.073252] [<8002e81c>] (run_ksoftirqd) from [<800494b0>] (smpboot_thread_fn+0x124/0x190) [ 8865.081550] [<8004938c>] (smpboot_thread_fn) from [<80045928>] (kthread+0xdc/0xf8) [ 8865.089133] r10:00000000 r9:00000000 r8:00000000 r7:8004938c r6:be035740 r5:be035780 [ 8865.097097] r4:00000000 r3:be069380 [ 8865.100752] [<8004584c>] (kthread) from [<8000ed10>] (ret_from_fork+0x14/0x24) [ 8865.107990] r7:00000000 r6:00000000 r5:8004584c r4:be035780 [ 8865.113767] Code: e320f000 e4913004 e4914004 e4915004 (e4916004) [ 8865.120006] ---[ end trace b0a4c6bd499288ca ]--- [ 8865.124697] Kernel panic - not syncing: Fatal exception in interrupt [ 8865.131084] ---[ end Kernel panic - not syncing: Fatal exception in interrupt Cc: [v3.19+] stable@vger.kernel.org Tested-by: Peter Chen <peter.chen@freescale.com> Signed-off-by: Peter Chen <peter.chen@freescale.com> Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-04 07:52:11 +08:00
if ((fep->work_tx || fep->work_rx) && fep->link) {
net: fec: fix interrupt handling races While running: while :; do iperf -c <HOST> -P 4; done, transmit timeouts are regularly reported. With the tx ring dumping in place, we can see that all entries are in use, and the hardware has finished transmitting these packets. However, the driver has not reclaimed these ring entries. This can occur if the interrupt handler is invoked at the wrong moment - eg: CPU0 CPU1 fec_enet_tx() interrupt, IEVENT = FEC_ENET_TXF FEC_ENET_TXF cleared napi_schedule_prep() napi_complete() The result is that we clear the transmit interrupt, but we don't trigger any cleaning of the transmit ring. Instead, use a different strategy: - When receiving a transmit or receive interrupt, disable both tx and rx interrupts, but do not acknowledge them. Schedule a napi poll. Don't loop. - When we are polled, read IEVENT, acknowledging the pending transmit and receive interrupts, before then going on to process the appropriate rings. This allows us to avoid the race, and has a number of other advantages: - we cut down on the number of transmit interrupts we have to process. - we only look at the rings which have pending events. - we gain additional throughput: the iperf total bandwidth increases from about 180Mbps to 240Mbps: [ 3] 0.0-10.0 sec 68.1 MBytes 57.0 Mbits/sec [ 5] 0.0-10.0 sec 72.4 MBytes 60.5 Mbits/sec [ 4] 0.0-10.1 sec 76.1 MBytes 63.5 Mbits/sec [ 6] 0.0-10.1 sec 71.9 MBytes 59.9 Mbits/sec [SUM] 0.0-10.1 sec 288 MBytes 241 Mbits/sec Acked-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-08 07:22:44 +08:00
ret = IRQ_HANDLED;
net: fec: Fix NAPI race Do camera capture test on i.MX6q sabresd board, and save the capture data to nfs rootfs. The command is: gst-launch-1.0 -e imxv4l2src device=/dev/video1 num-buffers=2592000 ! tee name=t ! queue ! imxv4l2sink sync=false t. ! queue ! vpuenc ! queue ! mux. pulsesrc num-buffers=3720937 blocksize=4096 ! 'audio/x-raw, rate=44100, channels=2' ! queue ! imxmp3enc ! mpegaudioparse ! queue ! mux. qtmux name=mux ! filesink location=video_recording_long.mov After about 10 hours running, there have net watchdog timeout kernel dump: ... WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x2b4/0x2d8() NETDEV WATCHDOG: eth0 (fec): transmit queue 0 timed out CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.14.24-01051-gdb840b7 #440 [<80014e6c>] (unwind_backtrace) from [<800118ac>] (show_stack+0x10/0x14) [<800118ac>] (show_stack) from [<806ae3f0>] (dump_stack+0x78/0xc0) [<806ae3f0>] (dump_stack) from [<8002b504>] (warn_slowpath_common+0x68/0x8c) [<8002b504>] (warn_slowpath_common) from [<8002b558>] (warn_slowpath_fmt+0x30/0x40) [<8002b558>] (warn_slowpath_fmt) from [<8055e0d4>] (dev_watchdog+0x2b4/0x2d8) [<8055e0d4>] (dev_watchdog) from [<800352d8>] (call_timer_fn.isra.33+0x24/0x8c) [<800352d8>] (call_timer_fn.isra.33) from [<800354c4>] (run_timer_softirq+0x184/0x220) [<800354c4>] (run_timer_softirq) from [<8002f420>] (__do_softirq+0xc0/0x22c) [<8002f420>] (__do_softirq) from [<8002f804>] (irq_exit+0xa8/0xf4) [<8002f804>] (irq_exit) from [<8000ee5c>] (handle_IRQ+0x54/0xb4) [<8000ee5c>] (handle_IRQ) from [<80008598>] (gic_handle_irq+0x28/0x5c) [<80008598>] (gic_handle_irq) from [<800123c0>] (__irq_svc+0x40/0x74) Exception stack(0x80d27f18 to 0x80d27f60) 7f00: 80d27f60 0000014c 7f20: 8858c60e 0000004d 884e4540 0000004d ab7250d0 80d34348 00000000 00000000 7f40: 00000001 00000000 00000017 80d27f60 800702a4 80476e6c 600f0013 ffffffff [<800123c0>] (__irq_svc) from [<80476e6c>] (cpuidle_enter_state+0x50/0xe0) [<80476e6c>] (cpuidle_enter_state) from [<80476fa8>] (cpuidle_idle_call+0xac/0x154) [<80476fa8>] (cpuidle_idle_call) from [<8000f174>] (arch_cpu_idle+0x8/0x44) [<8000f174>] (arch_cpu_idle) from [<80064c54>] (cpu_startup_entry+0x100/0x158) [<80064c54>] (cpu_startup_entry) from [<80cd8a9c>] (start_kernel+0x304/0x368) ---[ end trace 09ebd32fb032f86d ]--- ... There might have a race in napi_schedule(), leaving interrupts disabled forever. After these patch, the case still work more than 40 hours running. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-16 18:25:58 +08:00
if (napi_schedule_prep(&fep->napi)) {
/* Disable the NAPI interrupts */
writel(FEC_NAPI_IMASK, fep->hwp + FEC_IMASK);
net: fec: Fix NAPI race Do camera capture test on i.MX6q sabresd board, and save the capture data to nfs rootfs. The command is: gst-launch-1.0 -e imxv4l2src device=/dev/video1 num-buffers=2592000 ! tee name=t ! queue ! imxv4l2sink sync=false t. ! queue ! vpuenc ! queue ! mux. pulsesrc num-buffers=3720937 blocksize=4096 ! 'audio/x-raw, rate=44100, channels=2' ! queue ! imxmp3enc ! mpegaudioparse ! queue ! mux. qtmux name=mux ! filesink location=video_recording_long.mov After about 10 hours running, there have net watchdog timeout kernel dump: ... WARNING: CPU: 0 PID: 0 at net/sched/sch_generic.c:264 dev_watchdog+0x2b4/0x2d8() NETDEV WATCHDOG: eth0 (fec): transmit queue 0 timed out CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.14.24-01051-gdb840b7 #440 [<80014e6c>] (unwind_backtrace) from [<800118ac>] (show_stack+0x10/0x14) [<800118ac>] (show_stack) from [<806ae3f0>] (dump_stack+0x78/0xc0) [<806ae3f0>] (dump_stack) from [<8002b504>] (warn_slowpath_common+0x68/0x8c) [<8002b504>] (warn_slowpath_common) from [<8002b558>] (warn_slowpath_fmt+0x30/0x40) [<8002b558>] (warn_slowpath_fmt) from [<8055e0d4>] (dev_watchdog+0x2b4/0x2d8) [<8055e0d4>] (dev_watchdog) from [<800352d8>] (call_timer_fn.isra.33+0x24/0x8c) [<800352d8>] (call_timer_fn.isra.33) from [<800354c4>] (run_timer_softirq+0x184/0x220) [<800354c4>] (run_timer_softirq) from [<8002f420>] (__do_softirq+0xc0/0x22c) [<8002f420>] (__do_softirq) from [<8002f804>] (irq_exit+0xa8/0xf4) [<8002f804>] (irq_exit) from [<8000ee5c>] (handle_IRQ+0x54/0xb4) [<8000ee5c>] (handle_IRQ) from [<80008598>] (gic_handle_irq+0x28/0x5c) [<80008598>] (gic_handle_irq) from [<800123c0>] (__irq_svc+0x40/0x74) Exception stack(0x80d27f18 to 0x80d27f60) 7f00: 80d27f60 0000014c 7f20: 8858c60e 0000004d 884e4540 0000004d ab7250d0 80d34348 00000000 00000000 7f40: 00000001 00000000 00000017 80d27f60 800702a4 80476e6c 600f0013 ffffffff [<800123c0>] (__irq_svc) from [<80476e6c>] (cpuidle_enter_state+0x50/0xe0) [<80476e6c>] (cpuidle_enter_state) from [<80476fa8>] (cpuidle_idle_call+0xac/0x154) [<80476fa8>] (cpuidle_idle_call) from [<8000f174>] (arch_cpu_idle+0x8/0x44) [<8000f174>] (arch_cpu_idle) from [<80064c54>] (cpu_startup_entry+0x100/0x158) [<80064c54>] (cpu_startup_entry) from [<80cd8a9c>] (start_kernel+0x304/0x368) ---[ end trace 09ebd32fb032f86d ]--- ... There might have a race in napi_schedule(), leaving interrupts disabled forever. After these patch, the case still work more than 40 hours running. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-16 18:25:58 +08:00
__napi_schedule(&fep->napi);
}
net: fec: fix interrupt handling races While running: while :; do iperf -c <HOST> -P 4; done, transmit timeouts are regularly reported. With the tx ring dumping in place, we can see that all entries are in use, and the hardware has finished transmitting these packets. However, the driver has not reclaimed these ring entries. This can occur if the interrupt handler is invoked at the wrong moment - eg: CPU0 CPU1 fec_enet_tx() interrupt, IEVENT = FEC_ENET_TXF FEC_ENET_TXF cleared napi_schedule_prep() napi_complete() The result is that we clear the transmit interrupt, but we don't trigger any cleaning of the transmit ring. Instead, use a different strategy: - When receiving a transmit or receive interrupt, disable both tx and rx interrupts, but do not acknowledge them. Schedule a napi poll. Don't loop. - When we are polled, read IEVENT, acknowledging the pending transmit and receive interrupts, before then going on to process the appropriate rings. This allows us to avoid the race, and has a number of other advantages: - we cut down on the number of transmit interrupts we have to process. - we only look at the rings which have pending events. - we gain additional throughput: the iperf total bandwidth increases from about 180Mbps to 240Mbps: [ 3] 0.0-10.0 sec 68.1 MBytes 57.0 Mbits/sec [ 5] 0.0-10.0 sec 72.4 MBytes 60.5 Mbits/sec [ 4] 0.0-10.1 sec 76.1 MBytes 63.5 Mbits/sec [ 6] 0.0-10.1 sec 71.9 MBytes 59.9 Mbits/sec [SUM] 0.0-10.1 sec 288 MBytes 241 Mbits/sec Acked-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-08 07:22:44 +08:00
}
net: fec: fix interrupt handling races While running: while :; do iperf -c <HOST> -P 4; done, transmit timeouts are regularly reported. With the tx ring dumping in place, we can see that all entries are in use, and the hardware has finished transmitting these packets. However, the driver has not reclaimed these ring entries. This can occur if the interrupt handler is invoked at the wrong moment - eg: CPU0 CPU1 fec_enet_tx() interrupt, IEVENT = FEC_ENET_TXF FEC_ENET_TXF cleared napi_schedule_prep() napi_complete() The result is that we clear the transmit interrupt, but we don't trigger any cleaning of the transmit ring. Instead, use a different strategy: - When receiving a transmit or receive interrupt, disable both tx and rx interrupts, but do not acknowledge them. Schedule a napi poll. Don't loop. - When we are polled, read IEVENT, acknowledging the pending transmit and receive interrupts, before then going on to process the appropriate rings. This allows us to avoid the race, and has a number of other advantages: - we cut down on the number of transmit interrupts we have to process. - we only look at the rings which have pending events. - we gain additional throughput: the iperf total bandwidth increases from about 180Mbps to 240Mbps: [ 3] 0.0-10.0 sec 68.1 MBytes 57.0 Mbits/sec [ 5] 0.0-10.0 sec 72.4 MBytes 60.5 Mbits/sec [ 4] 0.0-10.1 sec 76.1 MBytes 63.5 Mbits/sec [ 6] 0.0-10.1 sec 71.9 MBytes 59.9 Mbits/sec [SUM] 0.0-10.1 sec 288 MBytes 241 Mbits/sec Acked-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-08 07:22:44 +08:00
if (int_events & FEC_ENET_MII) {
ret = IRQ_HANDLED;
complete(&fep->mdio_done);
}
if (fep->ptp_clock)
fec_ptp_check_pps_event(fep);
return ret;
}
static int fec_enet_rx_napi(struct napi_struct *napi, int budget)
{
struct net_device *ndev = napi->dev;
struct fec_enet_private *fep = netdev_priv(ndev);
net: fec: fix interrupt handling races While running: while :; do iperf -c <HOST> -P 4; done, transmit timeouts are regularly reported. With the tx ring dumping in place, we can see that all entries are in use, and the hardware has finished transmitting these packets. However, the driver has not reclaimed these ring entries. This can occur if the interrupt handler is invoked at the wrong moment - eg: CPU0 CPU1 fec_enet_tx() interrupt, IEVENT = FEC_ENET_TXF FEC_ENET_TXF cleared napi_schedule_prep() napi_complete() The result is that we clear the transmit interrupt, but we don't trigger any cleaning of the transmit ring. Instead, use a different strategy: - When receiving a transmit or receive interrupt, disable both tx and rx interrupts, but do not acknowledge them. Schedule a napi poll. Don't loop. - When we are polled, read IEVENT, acknowledging the pending transmit and receive interrupts, before then going on to process the appropriate rings. This allows us to avoid the race, and has a number of other advantages: - we cut down on the number of transmit interrupts we have to process. - we only look at the rings which have pending events. - we gain additional throughput: the iperf total bandwidth increases from about 180Mbps to 240Mbps: [ 3] 0.0-10.0 sec 68.1 MBytes 57.0 Mbits/sec [ 5] 0.0-10.0 sec 72.4 MBytes 60.5 Mbits/sec [ 4] 0.0-10.1 sec 76.1 MBytes 63.5 Mbits/sec [ 6] 0.0-10.1 sec 71.9 MBytes 59.9 Mbits/sec [SUM] 0.0-10.1 sec 288 MBytes 241 Mbits/sec Acked-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-07-08 07:22:44 +08:00
int pkts;
pkts = fec_enet_rx(ndev, budget);
net: fec: put tx to napi poll function to fix dead lock up stack ndo_start_xmit already hold lock. fec_enet_start_xmit needn't spin lock. stat_xmit just update fep->cur_tx fec_enet_tx just update fep->dirty_tx Reserve a empty bdb to check full or empty cur_tx == dirty_tx means full cur_tx == dirty_tx +1 means empty So needn't is_full variable. Fix spin lock deadlock ================================= [ INFO: inconsistent lock state ] 3.8.0-rc5+ #107 Not tainted --------------------------------- inconsistent {HARDIRQ-ON-W} -> {IN-HARDIRQ-W} usage. ptp4l/615 [HC1[1]:SC0[0]:HE0:SE1] takes: (&(&list->lock)->rlock#3){?.-...}, at: [<8042c3c4>] skb_queue_tail+0x20/0x50 {HARDIRQ-ON-W} state was registered at: [<80067250>] mark_lock+0x154/0x4e8 [<800676f4>] mark_irqflags+0x110/0x1a4 [<80069208>] __lock_acquire+0x494/0x9c0 [<80069ce8>] lock_acquire+0x90/0xa4 [<80527ad0>] _raw_spin_lock_bh+0x44/0x54 [<804877e0>] first_packet_length+0x38/0x1f0 [<804879e4>] udp_poll+0x4c/0x5c [<804231f8>] sock_poll+0x24/0x28 [<800d27f0>] do_poll.isra.10+0x120/0x254 [<800d36e4>] do_sys_poll+0x15c/0x1e8 [<800d3828>] sys_poll+0x60/0xc8 [<8000e780>] ret_fast_syscall+0x0/0x3c *** DEADLOCK *** 1 lock held by ptp4l/615: #0: (&(&fep->hw_lock)->rlock){-.-...}, at: [<80355f9c>] fec_enet_tx+0x24/0x268 stack backtrace: Backtrace: [<800121e0>] (dump_backtrace+0x0/0x10c) from [<80516210>] (dump_stack+0x18/0x1c) r6:8063b1fc r5:bf38b2f8 r4:bf38b000 r3:bf38b000 [<805161f8>] (dump_stack+0x0/0x1c) from [<805189d0>] (print_usage_bug.part.34+0x164/0x1a4) [<8051886c>] (print_usage_bug.part.34+0x0/0x1a4) from [<80518a88>] (print_usage_bug+0x78/0x88) r8:80065664 r7:bf38b2f8 r6:00000002 r5:00000000 r4:bf38b000 [<80518a10>] (print_usage_bug+0x0/0x88) from [<80518b58>] (mark_lock_irq+0xc0/0x270) r7:bf38b000 r6:00000002 r5:bf38b2f8 r4:00000000 [<80518a98>] (mark_lock_irq+0x0/0x270) from [<80067270>] (mark_lock+0x174/0x4e8) [<800670fc>] (mark_lock+0x0/0x4e8) from [<80067744>] (mark_irqflags+0x160/0x1a4) [<800675e4>] (mark_irqflags+0x0/0x1a4) from [<80069208>] (__lock_acquire+0x494/0x9c0) r5:00000002 r4:bf38b2f8 [<80068d74>] (__lock_acquire+0x0/0x9c0) from [<80069ce8>] (lock_acquire+0x90/0xa4) [<80069c58>] (lock_acquire+0x0/0xa4) from [<805278d8>] (_raw_spin_lock_irqsave+0x4c/0x60) [<8052788c>] (_raw_spin_lock_irqsave+0x0/0x60) from [<8042c3c4>] (skb_queue_tail+0x20/0x50) r6:bfbb2180 r5:bf1d0190 r4:bf1d0184 [<8042c3a4>] (skb_queue_tail+0x0/0x50) from [<8042c4cc>] (sock_queue_err_skb+0xd8/0x188) r6:00000056 r5:bfbb2180 r4:bf1d0000 r3:00000000 [<8042c3f4>] (sock_queue_err_skb+0x0/0x188) from [<8042d15c>] (skb_tstamp_tx+0x70/0xa0) r6:bf0dddb0 r5:bf1d0000 r4:bfbb2180 r3:00000004 [<8042d0ec>] (skb_tstamp_tx+0x0/0xa0) from [<803561d0>] (fec_enet_tx+0x258/0x268) r6:c089d260 r5:00001c00 r4:bfbd0000 [<80355f78>] (fec_enet_tx+0x0/0x268) from [<803562cc>] (fec_enet_interrupt+0xec/0xf8) [<803561e0>] (fec_enet_interrupt+0x0/0xf8) from [<8007d5b0>] (handle_irq_event_percpu+0x54/0x1a0) [<8007d55c>] (handle_irq_event_percpu+0x0/0x1a0) from [<8007d740>] (handle_irq_event+0x44/0x64) [<8007d6fc>] (handle_irq_event+0x0/0x64) from [<80080690>] (handle_fasteoi_irq+0xc4/0x15c) r6:bf0dc000 r5:bf811290 r4:bf811240 r3:00000000 [<800805cc>] (handle_fasteoi_irq+0x0/0x15c) from [<8007ceec>] (generic_handle_irq+0x28/0x38) r5:807130c8 r4:00000096 [<8007cec4>] (generic_handle_irq+0x0/0x38) from [<8000f16c>] (handle_IRQ+0x54/0xb4) r4:8071d280 r3:00000180 [<8000f118>] (handle_IRQ+0x0/0xb4) from [<80008544>] (gic_handle_irq+0x30/0x64) r8:8000e924 r7:f4000100 r6:bf0ddef8 r5:8071c974 r4:f400010c r3:00000000 [<80008514>] (gic_handle_irq+0x0/0x64) from [<8000e2e4>] (__irq_svc+0x44/0x5c) Exception stack(0xbf0ddef8 to 0xbf0ddf40) Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-04 01:34:25 +08:00
fec_enet_tx(ndev);
if (pkts < budget) {
napi_complete(napi);
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
}
return pkts;
}
/* ------------------------------------------------------------------------- */
static void fec_get_mac(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct fec_platform_data *pdata = dev_get_platdata(&fep->pdev->dev);
unsigned char *iap, tmpaddr[ETH_ALEN];
/*
* try to get mac address in following order:
*
* 1) module parameter via kernel command line in form
* fec.macaddr=0x00,0x04,0x9f,0x01,0x30,0xe0
*/
iap = macaddr;
/*
* 2) from device tree data
*/
if (!is_valid_ether_addr(iap)) {
struct device_node *np = fep->pdev->dev.of_node;
if (np) {
const char *mac = of_get_mac_address(np);
if (mac)
iap = (unsigned char *) mac;
}
}
/*
* 3) from flash or fuse (via platform data)
*/
if (!is_valid_ether_addr(iap)) {
#ifdef CONFIG_M5272
if (FEC_FLASHMAC)
iap = (unsigned char *)FEC_FLASHMAC;
#else
if (pdata)
iap = (unsigned char *)&pdata->mac;
#endif
}
/*
* 4) FEC mac registers set by bootloader
*/
if (!is_valid_ether_addr(iap)) {
*((__be32 *) &tmpaddr[0]) =
cpu_to_be32(readl(fep->hwp + FEC_ADDR_LOW));
*((__be16 *) &tmpaddr[4]) =
cpu_to_be16(readl(fep->hwp + FEC_ADDR_HIGH) >> 16);
iap = &tmpaddr[0];
}
/*
* 5) random mac address
*/
if (!is_valid_ether_addr(iap)) {
/* Report it and use a random ethernet address instead */
netdev_err(ndev, "Invalid MAC address: %pM\n", iap);
eth_hw_addr_random(ndev);
netdev_info(ndev, "Using random MAC address: %pM\n",
ndev->dev_addr);
return;
}
memcpy(ndev->dev_addr, iap, ETH_ALEN);
/* Adjust MAC if using macaddr */
if (iap == macaddr)
ndev->dev_addr[ETH_ALEN-1] = macaddr[ETH_ALEN-1] + fep->dev_id;
}
/* ------------------------------------------------------------------------- */
/*
* Phy section
*/
static void fec_enet_adjust_link(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct phy_device *phy_dev = fep->phy_dev;
int status_change = 0;
/* Prevent a state halted on mii error */
if (fep->mii_timeout && phy_dev->state == PHY_HALTED) {
phy_dev->state = PHY_RESUMING;
return;
}
/*
* If the netdev is down, or is going down, we're not interested
* in link state events, so just mark our idea of the link as down
* and ignore the event.
*/
if (!netif_running(ndev) || !netif_device_present(ndev)) {
fep->link = 0;
} else if (phy_dev->link) {
if (!fep->link) {
fep->link = phy_dev->link;
status_change = 1;
}
if (fep->full_duplex != phy_dev->duplex) {
fep->full_duplex = phy_dev->duplex;
status_change = 1;
}
if (phy_dev->speed != fep->speed) {
fep->speed = phy_dev->speed;
status_change = 1;
}
/* if any of the above changed restart the FEC */
if (status_change) {
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
netif_wake_queue(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
} else {
if (fep->link) {
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_stop(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
fep->link = phy_dev->link;
status_change = 1;
}
}
if (status_change)
phy_print_status(phy_dev);
}
static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
{
struct fec_enet_private *fep = bus->priv;
struct device *dev = &fep->pdev->dev;
unsigned long time_left;
int ret = 0;
ret = pm_runtime_get_sync(dev);
if (ret < 0)
return ret;
fep->mii_timeout = 0;
reinit_completion(&fep->mdio_done);
/* start a read op */
writel(FEC_MMFR_ST | FEC_MMFR_OP_READ |
FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(regnum) |
FEC_MMFR_TA, fep->hwp + FEC_MII_DATA);
/* wait for end of transfer */
time_left = wait_for_completion_timeout(&fep->mdio_done,
usecs_to_jiffies(FEC_MII_TIMEOUT));
if (time_left == 0) {
fep->mii_timeout = 1;
netdev_err(fep->netdev, "MDIO read timeout\n");
ret = -ETIMEDOUT;
goto out;
}
ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
out:
pm_runtime_mark_last_busy(dev);
pm_runtime_put_autosuspend(dev);
return ret;
}
static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
u16 value)
{
struct fec_enet_private *fep = bus->priv;
struct device *dev = &fep->pdev->dev;
unsigned long time_left;
int ret;
ret = pm_runtime_get_sync(dev);
if (ret < 0)
return ret;
else
ret = 0;
fep->mii_timeout = 0;
reinit_completion(&fep->mdio_done);
/* start a write op */
writel(FEC_MMFR_ST | FEC_MMFR_OP_WRITE |
FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(regnum) |
FEC_MMFR_TA | FEC_MMFR_DATA(value),
fep->hwp + FEC_MII_DATA);
/* wait for end of transfer */
time_left = wait_for_completion_timeout(&fep->mdio_done,
usecs_to_jiffies(FEC_MII_TIMEOUT));
if (time_left == 0) {
fep->mii_timeout = 1;
netdev_err(fep->netdev, "MDIO write timeout\n");
ret = -ETIMEDOUT;
}
pm_runtime_mark_last_busy(dev);
pm_runtime_put_autosuspend(dev);
return ret;
}
static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int ret;
if (enable) {
ret = clk_prepare_enable(fep->clk_ahb);
if (ret)
return ret;
if (fep->clk_enet_out) {
ret = clk_prepare_enable(fep->clk_enet_out);
if (ret)
goto failed_clk_enet_out;
}
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
ret = clk_prepare_enable(fep->clk_ptp);
if (ret) {
mutex_unlock(&fep->ptp_clk_mutex);
goto failed_clk_ptp;
} else {
fep->ptp_clk_on = true;
}
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);
if (fep->clk_enet_out)
clk_disable_unprepare(fep->clk_enet_out);
if (fep->clk_ptp) {
mutex_lock(&fep->ptp_clk_mutex);
clk_disable_unprepare(fep->clk_ptp);
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);
failed_clk_enet_out:
clk_disable_unprepare(fep->clk_ahb);
return ret;
}
static int fec_enet_mii_probe(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct phy_device *phy_dev = NULL;
char mdio_bus_id[MII_BUS_ID_SIZE];
char phy_name[MII_BUS_ID_SIZE + 3];
int phy_id;
int dev_id = fep->dev_id;
fep->phy_dev = NULL;
if (fep->phy_node) {
phy_dev = of_phy_connect(ndev, fep->phy_node,
&fec_enet_adjust_link, 0,
fep->phy_interface);
net: fec: avoid kernal crash by NULL pointer when no phy connection On i.MX6SX sabreauto board, when there have no phy daughter board connection, there have kernel crash by NULL pointer: fec 2188000.ethernet eth0: could not attach to PHY Unable to handle kernel NULL pointer dereference at virtual address 00000220 pgd = 80004000 [00000220] *pgd=00000000 Internal error: Oops: 5 [#1] PREEMPT SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.14.24-01042-g27eaeea-dirty #405 task: d8078000 ti: d8076000 task.ti: d8076000 PC is at mutex_lock+0x10/0x54 LR is at phy_start+0x14/0x68 pc : [<806ad4e4>] lr : [<803b0f90>] psr: 60000113 sp : d8077d80 ip : 00000000 fp : d83cc000 r10: 0000100c r9 : d83cc800 r8 : 00000000 r7 : d83bcd0c r6 : 00000200 r5 : 00000220 r4 : 00000220 r3 : 00000000 r2 : 00000000 r1 : d83bcd90 r0 : 00000220 Flags: nZCv IRQs on FIQs on Mode SVC_32 ISA ARM Segment kernel Control: 10c5387d Table: 8000404a DAC: 00000015 Process swapper/0 (pid: 1, stack limit = 0xd8076240) Stack: (0xd8077d80 to 0xd8078000) 7d80: 00000000 803b0f90 00000001 00000000 d83bc800 803be034 00000007 805c3fb4 7da0: 00000003 80d4e0bc 805efcb8 fffffff1 fffffff0 00000000 00000000 d8077dfc 7dc0: 0000000d 80d6ce80 80d126b0 800499c8 d83bc800 d83bc800 806f0f40 d83bc82c 7de0: 00000000 00000000 80d6ce80 80d126b0 0000016b 80540250 d8076008 d83bc800 7e00: 0000016b d83bc800 00001003 00000001 00001002 805404d4 d83bc800 00000120 7e20: 00001002 00001002 00000000 805405d4 d83bc800 00000001 80d126c0 00001002 7e40: 80dbc5dc 80d02024 00000000 806ae360 00000002 d6128420 d6127198 12400000 7e60: 00000000 00000000 00000002 d61271e8 00000000 12400000 d801674c 800e49f0 7e80: d6127198 d6124e58 00000000 80238848 d61271c4 00000000 00000001 d8016700 7ea0: 80dd2e00 80d752c0 80d752c0 80cfdaec 0000010c 80239430 806c2e90 d800f080 7ec0: d800f380 804e46b4 ffffffbc 80d15cb0 00000007 80d752c0 80d752c0 80d01e94 7ee0: 0000010c d8076030 00000000 800088cc 80dbaba4 80bd411c d80a6f00 806b1e04 7f00: 00000000 00000000 00000000 80125b84 00000000 80d2c56c 60000113 00000001 7f20: ef7ff9df 806c80cc 0000010c 80043f5c 80c95eb8 00000007 ef7ffa1d 00000007 7f40: 80d2c55c 80d15cb0 00000007 80d752c0 80d752c0 80ccc50c 0000010c 80d0a114 7f60: 80d0a10c 80cccc04 00000007 00000007 80ccc50c 806ae410 00000000 8004cb84 7f80: 80d17bc0 00000000 806a4bd4 00000000 00000000 00000000 00000000 00000000 7fa0: 00000000 806a4bdc 00000000 8000e5f8 00000000 00000000 00000000 00000000 7fc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000 7fe0: 00000000 00000000 00000000 00000000 00000013 00000000 1e79a7bb e5337f77 [<806ad4e4>] (mutex_lock) from [<803b0f90>] (phy_start+0x14/0x68) [<803b0f90>] (phy_start) from [<803be034>] (fec_enet_open+0x448/0x5dc) [<803be034>] (fec_enet_open) from [<80540250>] (__dev_open+0xa8/0x110) [<80540250>] (__dev_open) from [<805404d4>] (__dev_change_flags+0x88/0x170) [<805404d4>] (__dev_change_flags) from [<805405d4>] (dev_change_flags+0x18/0x48) [<805405d4>] (dev_change_flags) from [<80d02024>] (ip_auto_config+0x190/0xf94) [<80d02024>] (ip_auto_config) from [<800088cc>] (do_one_initcall+0xe8/0x144) [<800088cc>] (do_one_initcall) from [<80cccc04>] (kernel_init_freeable+0x104/0x1c8) [<80cccc04>] (kernel_init_freeable) from [<806a4bdc>] (kernel_init+0x8/0xec) [<806a4bdc>] (kernel_init) from [<8000e5f8>] (ret_from_fork+0x14/0x3c) Code: e92d4010 e3a03000 e1a04000 ee073fba (e1903f9f) Add phydev check to fix the issue. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-09 18:46:56 +08:00
if (!phy_dev)
return -ENODEV;
} else {
/* check for attached phy */
for (phy_id = 0; (phy_id < PHY_MAX_ADDR); phy_id++) {
if (!mdiobus_is_registered_device(fep->mii_bus, phy_id))
continue;
if (dev_id--)
continue;
strlcpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE);
break;
}
if (phy_id >= PHY_MAX_ADDR) {
netdev_info(ndev, "no PHY, assuming direct connection to switch\n");
strlcpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE);
phy_id = 0;
}
snprintf(phy_name, sizeof(phy_name),
PHY_ID_FMT, mdio_bus_id, phy_id);
phy_dev = phy_connect(ndev, phy_name, &fec_enet_adjust_link,
fep->phy_interface);
}
if (IS_ERR(phy_dev)) {
netdev_err(ndev, "could not attach to PHY\n");
return PTR_ERR(phy_dev);
}
/* mask with MAC supported features */
if (fep->quirks & FEC_QUIRK_HAS_GBIT) {
phy_dev->supported &= PHY_GBIT_FEATURES;
phy_dev->supported &= ~SUPPORTED_1000baseT_Half;
#if !defined(CONFIG_M5272)
phy_dev->supported |= SUPPORTED_Pause;
#endif
}
else
phy_dev->supported &= PHY_BASIC_FEATURES;
phy_dev->advertising = phy_dev->supported;
fep->phy_dev = phy_dev;
fep->link = 0;
fep->full_duplex = 0;
phy_attached_info(phy_dev);
return 0;
}
static int fec_enet_mii_init(struct platform_device *pdev)
{
static struct mii_bus *fec0_mii_bus;
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
struct device_node *node;
int err = -ENXIO;
u32 mii_speed, holdtime;
/*
net: fec: fix MDIO bus assignement for dual fec SoC's On i.MX28, the MDIO bus is shared between the two FEC instances. The driver makes sure that the second FEC uses the MDIO bus of the first FEC. This is done conditionally if FEC_QUIRK_ENET_MAC is set. However, in newer designs, such as Vybrid or i.MX6SX, each FEC MAC has its own MDIO bus. Simply removing the quirk FEC_QUIRK_ENET_MAC is not an option since other logic, triggered by this quirk, is still needed. Furthermore, there are board designs which use the same MDIO bus for both PHY's even though the second bus would be available on the SoC side. Such layout are popular since it saves pins on SoC side. Due to the above quirk, those boards currently do work fine. The boards in the mainline tree with such a layout are: - Freescale Vybrid Tower with TWR-SER2 (vf610-twr.dts) - Freescale i.MX6 SoloX SDB Board (imx6sx-sdb.dts) This patch adds a new quirk FEC_QUIRK_SINGLE_MDIO for i.MX28, which makes sure that the MDIO bus of the first FEC is used in any case. However, the boards above do have a SoC with a MDIO bus for each FEC instance. But the PHY's are not connected in a 1:1 configuration. A proper device tree description is needed to allow the driver to figure out where to find its PHY. This patch fixes that shortcoming by adding a MDIO bus child node to the first FEC instance, along with the two PHY's on that bus, and making use of the phy-handle property to add a reference to the PHY's. Acked-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Stefan Agner <stefan@agner.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-14 07:20:21 +08:00
* The i.MX28 dual fec interfaces are not equal.
* Here are the differences:
*
* - fec0 supports MII & RMII modes while fec1 only supports RMII
* - fec0 acts as the 1588 time master while fec1 is slave
* - external phys can only be configured by fec0
*
* That is to say fec1 can not work independently. It only works
* when fec0 is working. The reason behind this design is that the
* second interface is added primarily for Switch mode.
*
* Because of the last point above, both phys are attached on fec0
* mdio interface in board design, and need to be configured by
* fec0 mii_bus.
*/
net: fec: fix MDIO bus assignement for dual fec SoC's On i.MX28, the MDIO bus is shared between the two FEC instances. The driver makes sure that the second FEC uses the MDIO bus of the first FEC. This is done conditionally if FEC_QUIRK_ENET_MAC is set. However, in newer designs, such as Vybrid or i.MX6SX, each FEC MAC has its own MDIO bus. Simply removing the quirk FEC_QUIRK_ENET_MAC is not an option since other logic, triggered by this quirk, is still needed. Furthermore, there are board designs which use the same MDIO bus for both PHY's even though the second bus would be available on the SoC side. Such layout are popular since it saves pins on SoC side. Due to the above quirk, those boards currently do work fine. The boards in the mainline tree with such a layout are: - Freescale Vybrid Tower with TWR-SER2 (vf610-twr.dts) - Freescale i.MX6 SoloX SDB Board (imx6sx-sdb.dts) This patch adds a new quirk FEC_QUIRK_SINGLE_MDIO for i.MX28, which makes sure that the MDIO bus of the first FEC is used in any case. However, the boards above do have a SoC with a MDIO bus for each FEC instance. But the PHY's are not connected in a 1:1 configuration. A proper device tree description is needed to allow the driver to figure out where to find its PHY. This patch fixes that shortcoming by adding a MDIO bus child node to the first FEC instance, along with the two PHY's on that bus, and making use of the phy-handle property to add a reference to the PHY's. Acked-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Stefan Agner <stefan@agner.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-14 07:20:21 +08:00
if ((fep->quirks & FEC_QUIRK_SINGLE_MDIO) && fep->dev_id > 0) {
/* fec1 uses fec0 mii_bus */
if (mii_cnt && fec0_mii_bus) {
fep->mii_bus = fec0_mii_bus;
mii_cnt++;
return 0;
}
return -ENOENT;
}
fep->mii_timeout = 0;
/*
* Set MII speed to 2.5 MHz (= clk_get_rate() / 2 * phy_speed)
*
* The formula for FEC MDC is 'ref_freq / (MII_SPEED x 2)' while
* for ENET-MAC is 'ref_freq / ((MII_SPEED + 1) x 2)'. The i.MX28
* Reference Manual has an error on this, and gets fixed on i.MX6Q
* document.
*/
mii_speed = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 5000000);
if (fep->quirks & FEC_QUIRK_ENET_MAC)
mii_speed--;
if (mii_speed > 63) {
dev_err(&pdev->dev,
"fec clock (%lu) to fast to get right mii speed\n",
clk_get_rate(fep->clk_ipg));
err = -EINVAL;
goto err_out;
}
/*
* The i.MX28 and i.MX6 types have another filed in the MSCR (aka
* MII_SPEED) register that defines the MDIO output hold time. Earlier
* versions are RAZ there, so just ignore the difference and write the
* register always.
* The minimal hold time according to IEE802.3 (clause 22) is 10 ns.
* HOLDTIME + 1 is the number of clk cycles the fec is holding the
* output.
* The HOLDTIME bitfield takes values between 0 and 7 (inclusive).
* Given that ceil(clkrate / 5000000) <= 64, the calculation for
* holdtime cannot result in a value greater than 3.
*/
holdtime = DIV_ROUND_UP(clk_get_rate(fep->clk_ipg), 100000000) - 1;
fep->phy_speed = mii_speed << 1 | holdtime << 8;
writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
fep->mii_bus = mdiobus_alloc();
if (fep->mii_bus == NULL) {
err = -ENOMEM;
goto err_out;
}
fep->mii_bus->name = "fec_enet_mii_bus";
fep->mii_bus->read = fec_enet_mdio_read;
fep->mii_bus->write = fec_enet_mdio_write;
snprintf(fep->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x",
pdev->name, fep->dev_id + 1);
fep->mii_bus->priv = fep;
fep->mii_bus->parent = &pdev->dev;
node = of_get_child_by_name(pdev->dev.of_node, "mdio");
if (node) {
err = of_mdiobus_register(fep->mii_bus, node);
of_node_put(node);
} else {
err = mdiobus_register(fep->mii_bus);
}
if (err)
goto err_out_free_mdiobus;
mii_cnt++;
/* save fec0 mii_bus */
net: fec: fix MDIO bus assignement for dual fec SoC's On i.MX28, the MDIO bus is shared between the two FEC instances. The driver makes sure that the second FEC uses the MDIO bus of the first FEC. This is done conditionally if FEC_QUIRK_ENET_MAC is set. However, in newer designs, such as Vybrid or i.MX6SX, each FEC MAC has its own MDIO bus. Simply removing the quirk FEC_QUIRK_ENET_MAC is not an option since other logic, triggered by this quirk, is still needed. Furthermore, there are board designs which use the same MDIO bus for both PHY's even though the second bus would be available on the SoC side. Such layout are popular since it saves pins on SoC side. Due to the above quirk, those boards currently do work fine. The boards in the mainline tree with such a layout are: - Freescale Vybrid Tower with TWR-SER2 (vf610-twr.dts) - Freescale i.MX6 SoloX SDB Board (imx6sx-sdb.dts) This patch adds a new quirk FEC_QUIRK_SINGLE_MDIO for i.MX28, which makes sure that the MDIO bus of the first FEC is used in any case. However, the boards above do have a SoC with a MDIO bus for each FEC instance. But the PHY's are not connected in a 1:1 configuration. A proper device tree description is needed to allow the driver to figure out where to find its PHY. This patch fixes that shortcoming by adding a MDIO bus child node to the first FEC instance, along with the two PHY's on that bus, and making use of the phy-handle property to add a reference to the PHY's. Acked-by: Sascha Hauer <s.hauer@pengutronix.de> Signed-off-by: Stefan Agner <stefan@agner.ch> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-01-14 07:20:21 +08:00
if (fep->quirks & FEC_QUIRK_SINGLE_MDIO)
fec0_mii_bus = fep->mii_bus;
return 0;
err_out_free_mdiobus:
mdiobus_free(fep->mii_bus);
err_out:
return err;
}
static void fec_enet_mii_remove(struct fec_enet_private *fep)
{
if (--mii_cnt == 0) {
mdiobus_unregister(fep->mii_bus);
mdiobus_free(fep->mii_bus);
}
}
static int fec_enet_get_settings(struct net_device *ndev,
struct ethtool_cmd *cmd)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct phy_device *phydev = fep->phy_dev;
if (!phydev)
return -ENODEV;
return phy_ethtool_gset(phydev, cmd);
}
static int fec_enet_set_settings(struct net_device *ndev,
struct ethtool_cmd *cmd)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct phy_device *phydev = fep->phy_dev;
if (!phydev)
return -ENODEV;
return phy_ethtool_sset(phydev, cmd);
}
static void fec_enet_get_drvinfo(struct net_device *ndev,
struct ethtool_drvinfo *info)
{
struct fec_enet_private *fep = netdev_priv(ndev);
strlcpy(info->driver, fep->pdev->dev.driver->name,
sizeof(info->driver));
strlcpy(info->version, "Revision: 1.0", sizeof(info->version));
strlcpy(info->bus_info, dev_name(&ndev->dev), sizeof(info->bus_info));
}
static int fec_enet_get_regs_len(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct resource *r;
int s = 0;
r = platform_get_resource(fep->pdev, IORESOURCE_MEM, 0);
if (r)
s = resource_size(r);
return s;
}
/* List of registers that can be safety be read to dump them with ethtool */
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || defined(CONFIG_ARM)
static u32 fec_enet_register_offset[] = {
FEC_IEVENT, FEC_IMASK, FEC_R_DES_ACTIVE_0, FEC_X_DES_ACTIVE_0,
FEC_ECNTRL, FEC_MII_DATA, FEC_MII_SPEED, FEC_MIB_CTRLSTAT, FEC_R_CNTRL,
FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH, FEC_OPD, FEC_TXIC0, FEC_TXIC1,
FEC_TXIC2, FEC_RXIC0, FEC_RXIC1, FEC_RXIC2, FEC_HASH_TABLE_HIGH,
FEC_HASH_TABLE_LOW, FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW,
FEC_X_WMRK, FEC_R_BOUND, FEC_R_FSTART, FEC_R_DES_START_1,
FEC_X_DES_START_1, FEC_R_BUFF_SIZE_1, FEC_R_DES_START_2,
FEC_X_DES_START_2, FEC_R_BUFF_SIZE_2, FEC_R_DES_START_0,
FEC_X_DES_START_0, FEC_R_BUFF_SIZE_0, FEC_R_FIFO_RSFL, FEC_R_FIFO_RSEM,
FEC_R_FIFO_RAEM, FEC_R_FIFO_RAFL, FEC_RACC, FEC_RCMR_1, FEC_RCMR_2,
FEC_DMA_CFG_1, FEC_DMA_CFG_2, FEC_R_DES_ACTIVE_1, FEC_X_DES_ACTIVE_1,
FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_2, FEC_QOS_SCHEME,
RMON_T_DROP, RMON_T_PACKETS, RMON_T_BC_PKT, RMON_T_MC_PKT,
RMON_T_CRC_ALIGN, RMON_T_UNDERSIZE, RMON_T_OVERSIZE, RMON_T_FRAG,
RMON_T_JAB, RMON_T_COL, RMON_T_P64, RMON_T_P65TO127, RMON_T_P128TO255,
RMON_T_P256TO511, RMON_T_P512TO1023, RMON_T_P1024TO2047,
RMON_T_P_GTE2048, RMON_T_OCTETS,
IEEE_T_DROP, IEEE_T_FRAME_OK, IEEE_T_1COL, IEEE_T_MCOL, IEEE_T_DEF,
IEEE_T_LCOL, IEEE_T_EXCOL, IEEE_T_MACERR, IEEE_T_CSERR, IEEE_T_SQE,
IEEE_T_FDXFC, IEEE_T_OCTETS_OK,
RMON_R_PACKETS, RMON_R_BC_PKT, RMON_R_MC_PKT, RMON_R_CRC_ALIGN,
RMON_R_UNDERSIZE, RMON_R_OVERSIZE, RMON_R_FRAG, RMON_R_JAB,
RMON_R_RESVD_O, RMON_R_P64, RMON_R_P65TO127, RMON_R_P128TO255,
RMON_R_P256TO511, RMON_R_P512TO1023, RMON_R_P1024TO2047,
RMON_R_P_GTE2048, RMON_R_OCTETS,
IEEE_R_DROP, IEEE_R_FRAME_OK, IEEE_R_CRC, IEEE_R_ALIGN, IEEE_R_MACERR,
IEEE_R_FDXFC, IEEE_R_OCTETS_OK
};
#else
static u32 fec_enet_register_offset[] = {
FEC_ECNTRL, FEC_IEVENT, FEC_IMASK, FEC_IVEC, FEC_R_DES_ACTIVE_0,
FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2, FEC_X_DES_ACTIVE_0,
FEC_X_DES_ACTIVE_1, FEC_X_DES_ACTIVE_2, FEC_MII_DATA, FEC_MII_SPEED,
FEC_R_BOUND, FEC_R_FSTART, FEC_X_WMRK, FEC_X_FSTART, FEC_R_CNTRL,
FEC_MAX_FRM_LEN, FEC_X_CNTRL, FEC_ADDR_LOW, FEC_ADDR_HIGH,
FEC_GRP_HASH_TABLE_HIGH, FEC_GRP_HASH_TABLE_LOW, FEC_R_DES_START_0,
FEC_R_DES_START_1, FEC_R_DES_START_2, FEC_X_DES_START_0,
FEC_X_DES_START_1, FEC_X_DES_START_2, FEC_R_BUFF_SIZE_0,
FEC_R_BUFF_SIZE_1, FEC_R_BUFF_SIZE_2
};
#endif
static void fec_enet_get_regs(struct net_device *ndev,
struct ethtool_regs *regs, void *regbuf)
{
struct fec_enet_private *fep = netdev_priv(ndev);
u32 __iomem *theregs = (u32 __iomem *)fep->hwp;
u32 *buf = (u32 *)regbuf;
u32 i, off;
memset(buf, 0, regs->len);
for (i = 0; i < ARRAY_SIZE(fec_enet_register_offset); i++) {
off = fec_enet_register_offset[i] / 4;
buf[off] = readl(&theregs[off]);
}
}
static int fec_enet_get_ts_info(struct net_device *ndev,
struct ethtool_ts_info *info)
{
struct fec_enet_private *fep = netdev_priv(ndev);
if (fep->bufdesc_ex) {
info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
SOF_TIMESTAMPING_RX_SOFTWARE |
SOF_TIMESTAMPING_SOFTWARE |
SOF_TIMESTAMPING_TX_HARDWARE |
SOF_TIMESTAMPING_RX_HARDWARE |
SOF_TIMESTAMPING_RAW_HARDWARE;
if (fep->ptp_clock)
info->phc_index = ptp_clock_index(fep->ptp_clock);
else
info->phc_index = -1;
info->tx_types = (1 << HWTSTAMP_TX_OFF) |
(1 << HWTSTAMP_TX_ON);
info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
(1 << HWTSTAMP_FILTER_ALL);
return 0;
} else {
return ethtool_op_get_ts_info(ndev, info);
}
}
#if !defined(CONFIG_M5272)
static void fec_enet_get_pauseparam(struct net_device *ndev,
struct ethtool_pauseparam *pause)
{
struct fec_enet_private *fep = netdev_priv(ndev);
pause->autoneg = (fep->pause_flag & FEC_PAUSE_FLAG_AUTONEG) != 0;
pause->tx_pause = (fep->pause_flag & FEC_PAUSE_FLAG_ENABLE) != 0;
pause->rx_pause = pause->tx_pause;
}
static int fec_enet_set_pauseparam(struct net_device *ndev,
struct ethtool_pauseparam *pause)
{
struct fec_enet_private *fep = netdev_priv(ndev);
if (!fep->phy_dev)
return -ENODEV;
if (pause->tx_pause != pause->rx_pause) {
netdev_info(ndev,
"hardware only support enable/disable both tx and rx");
return -EINVAL;
}
fep->pause_flag = 0;
/* tx pause must be same as rx pause */
fep->pause_flag |= pause->rx_pause ? FEC_PAUSE_FLAG_ENABLE : 0;
fep->pause_flag |= pause->autoneg ? FEC_PAUSE_FLAG_AUTONEG : 0;
if (pause->rx_pause || pause->autoneg) {
fep->phy_dev->supported |= ADVERTISED_Pause;
fep->phy_dev->advertising |= ADVERTISED_Pause;
} else {
fep->phy_dev->supported &= ~ADVERTISED_Pause;
fep->phy_dev->advertising &= ~ADVERTISED_Pause;
}
if (pause->autoneg) {
if (netif_running(ndev))
fec_stop(ndev);
phy_start_aneg(fep->phy_dev);
}
if (netif_running(ndev)) {
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
fec_restart(ndev);
netif_wake_queue(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
}
return 0;
}
static const struct fec_stat {
char name[ETH_GSTRING_LEN];
u16 offset;
} fec_stats[] = {
/* RMON TX */
{ "tx_dropped", RMON_T_DROP },
{ "tx_packets", RMON_T_PACKETS },
{ "tx_broadcast", RMON_T_BC_PKT },
{ "tx_multicast", RMON_T_MC_PKT },
{ "tx_crc_errors", RMON_T_CRC_ALIGN },
{ "tx_undersize", RMON_T_UNDERSIZE },
{ "tx_oversize", RMON_T_OVERSIZE },
{ "tx_fragment", RMON_T_FRAG },
{ "tx_jabber", RMON_T_JAB },
{ "tx_collision", RMON_T_COL },
{ "tx_64byte", RMON_T_P64 },
{ "tx_65to127byte", RMON_T_P65TO127 },
{ "tx_128to255byte", RMON_T_P128TO255 },
{ "tx_256to511byte", RMON_T_P256TO511 },
{ "tx_512to1023byte", RMON_T_P512TO1023 },
{ "tx_1024to2047byte", RMON_T_P1024TO2047 },
{ "tx_GTE2048byte", RMON_T_P_GTE2048 },
{ "tx_octets", RMON_T_OCTETS },
/* IEEE TX */
{ "IEEE_tx_drop", IEEE_T_DROP },
{ "IEEE_tx_frame_ok", IEEE_T_FRAME_OK },
{ "IEEE_tx_1col", IEEE_T_1COL },
{ "IEEE_tx_mcol", IEEE_T_MCOL },
{ "IEEE_tx_def", IEEE_T_DEF },
{ "IEEE_tx_lcol", IEEE_T_LCOL },
{ "IEEE_tx_excol", IEEE_T_EXCOL },
{ "IEEE_tx_macerr", IEEE_T_MACERR },
{ "IEEE_tx_cserr", IEEE_T_CSERR },
{ "IEEE_tx_sqe", IEEE_T_SQE },
{ "IEEE_tx_fdxfc", IEEE_T_FDXFC },
{ "IEEE_tx_octets_ok", IEEE_T_OCTETS_OK },
/* RMON RX */
{ "rx_packets", RMON_R_PACKETS },
{ "rx_broadcast", RMON_R_BC_PKT },
{ "rx_multicast", RMON_R_MC_PKT },
{ "rx_crc_errors", RMON_R_CRC_ALIGN },
{ "rx_undersize", RMON_R_UNDERSIZE },
{ "rx_oversize", RMON_R_OVERSIZE },
{ "rx_fragment", RMON_R_FRAG },
{ "rx_jabber", RMON_R_JAB },
{ "rx_64byte", RMON_R_P64 },
{ "rx_65to127byte", RMON_R_P65TO127 },
{ "rx_128to255byte", RMON_R_P128TO255 },
{ "rx_256to511byte", RMON_R_P256TO511 },
{ "rx_512to1023byte", RMON_R_P512TO1023 },
{ "rx_1024to2047byte", RMON_R_P1024TO2047 },
{ "rx_GTE2048byte", RMON_R_P_GTE2048 },
{ "rx_octets", RMON_R_OCTETS },
/* IEEE RX */
{ "IEEE_rx_drop", IEEE_R_DROP },
{ "IEEE_rx_frame_ok", IEEE_R_FRAME_OK },
{ "IEEE_rx_crc", IEEE_R_CRC },
{ "IEEE_rx_align", IEEE_R_ALIGN },
{ "IEEE_rx_macerr", IEEE_R_MACERR },
{ "IEEE_rx_fdxfc", IEEE_R_FDXFC },
{ "IEEE_rx_octets_ok", IEEE_R_OCTETS_OK },
};
static void fec_enet_get_ethtool_stats(struct net_device *dev,
struct ethtool_stats *stats, u64 *data)
{
struct fec_enet_private *fep = netdev_priv(dev);
int i;
for (i = 0; i < ARRAY_SIZE(fec_stats); i++)
data[i] = readl(fep->hwp + fec_stats[i].offset);
}
static void fec_enet_get_strings(struct net_device *netdev,
u32 stringset, u8 *data)
{
int i;
switch (stringset) {
case ETH_SS_STATS:
for (i = 0; i < ARRAY_SIZE(fec_stats); i++)
memcpy(data + i * ETH_GSTRING_LEN,
fec_stats[i].name, ETH_GSTRING_LEN);
break;
}
}
static int fec_enet_get_sset_count(struct net_device *dev, int sset)
{
switch (sset) {
case ETH_SS_STATS:
return ARRAY_SIZE(fec_stats);
default:
return -EOPNOTSUPP;
}
}
#endif /* !defined(CONFIG_M5272) */
static int fec_enet_nway_reset(struct net_device *dev)
{
struct fec_enet_private *fep = netdev_priv(dev);
struct phy_device *phydev = fep->phy_dev;
if (!phydev)
return -ENODEV;
return genphy_restart_aneg(phydev);
}
/* ITR clock source is enet system clock (clk_ahb).
* TCTT unit is cycle_ns * 64 cycle
* So, the ICTT value = X us / (cycle_ns * 64)
*/
static int fec_enet_us_to_itr_clock(struct net_device *ndev, int us)
{
struct fec_enet_private *fep = netdev_priv(ndev);
return us * (fep->itr_clk_rate / 64000) / 1000;
}
/* Set threshold for interrupt coalescing */
static void fec_enet_itr_coal_set(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int rx_itr, tx_itr;
if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
return;
/* Must be greater than zero to avoid unpredictable behavior */
if (!fep->rx_time_itr || !fep->rx_pkts_itr ||
!fep->tx_time_itr || !fep->tx_pkts_itr)
return;
/* Select enet system clock as Interrupt Coalescing
* timer Clock Source
*/
rx_itr = FEC_ITR_CLK_SEL;
tx_itr = FEC_ITR_CLK_SEL;
/* set ICFT and ICTT */
rx_itr |= FEC_ITR_ICFT(fep->rx_pkts_itr);
rx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr));
tx_itr |= FEC_ITR_ICFT(fep->tx_pkts_itr);
tx_itr |= FEC_ITR_ICTT(fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr));
rx_itr |= FEC_ITR_EN;
tx_itr |= FEC_ITR_EN;
writel(tx_itr, fep->hwp + FEC_TXIC0);
writel(rx_itr, fep->hwp + FEC_RXIC0);
writel(tx_itr, fep->hwp + FEC_TXIC1);
writel(rx_itr, fep->hwp + FEC_RXIC1);
writel(tx_itr, fep->hwp + FEC_TXIC2);
writel(rx_itr, fep->hwp + FEC_RXIC2);
}
static int
fec_enet_get_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
{
struct fec_enet_private *fep = netdev_priv(ndev);
if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
return -EOPNOTSUPP;
ec->rx_coalesce_usecs = fep->rx_time_itr;
ec->rx_max_coalesced_frames = fep->rx_pkts_itr;
ec->tx_coalesce_usecs = fep->tx_time_itr;
ec->tx_max_coalesced_frames = fep->tx_pkts_itr;
return 0;
}
static int
fec_enet_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *ec)
{
struct fec_enet_private *fep = netdev_priv(ndev);
unsigned int cycle;
if (!(fep->quirks & FEC_QUIRK_HAS_AVB))
return -EOPNOTSUPP;
if (ec->rx_max_coalesced_frames > 255) {
pr_err("Rx coalesced frames exceed hardware limiation");
return -EINVAL;
}
if (ec->tx_max_coalesced_frames > 255) {
pr_err("Tx coalesced frame exceed hardware limiation");
return -EINVAL;
}
cycle = fec_enet_us_to_itr_clock(ndev, fep->rx_time_itr);
if (cycle > 0xFFFF) {
pr_err("Rx coalesed usec exceeed hardware limiation");
return -EINVAL;
}
cycle = fec_enet_us_to_itr_clock(ndev, fep->tx_time_itr);
if (cycle > 0xFFFF) {
pr_err("Rx coalesed usec exceeed hardware limiation");
return -EINVAL;
}
fep->rx_time_itr = ec->rx_coalesce_usecs;
fep->rx_pkts_itr = ec->rx_max_coalesced_frames;
fep->tx_time_itr = ec->tx_coalesce_usecs;
fep->tx_pkts_itr = ec->tx_max_coalesced_frames;
fec_enet_itr_coal_set(ndev);
return 0;
}
static void fec_enet_itr_coal_init(struct net_device *ndev)
{
struct ethtool_coalesce ec;
ec.rx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
ec.rx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
ec.tx_coalesce_usecs = FEC_ITR_ICTT_DEFAULT;
ec.tx_max_coalesced_frames = FEC_ITR_ICFT_DEFAULT;
fec_enet_set_coalesce(ndev, &ec);
}
static int fec_enet_get_tunable(struct net_device *netdev,
const struct ethtool_tunable *tuna,
void *data)
{
struct fec_enet_private *fep = netdev_priv(netdev);
int ret = 0;
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
*(u32 *)data = fep->rx_copybreak;
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
static int fec_enet_set_tunable(struct net_device *netdev,
const struct ethtool_tunable *tuna,
const void *data)
{
struct fec_enet_private *fep = netdev_priv(netdev);
int ret = 0;
switch (tuna->id) {
case ETHTOOL_RX_COPYBREAK:
fep->rx_copybreak = *(u32 *)data;
break;
default:
ret = -EINVAL;
break;
}
return ret;
}
static void
fec_enet_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
{
struct fec_enet_private *fep = netdev_priv(ndev);
if (fep->wol_flag & FEC_WOL_HAS_MAGIC_PACKET) {
wol->supported = WAKE_MAGIC;
wol->wolopts = fep->wol_flag & FEC_WOL_FLAG_ENABLE ? WAKE_MAGIC : 0;
} else {
wol->supported = wol->wolopts = 0;
}
}
static int
fec_enet_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol)
{
struct fec_enet_private *fep = netdev_priv(ndev);
if (!(fep->wol_flag & FEC_WOL_HAS_MAGIC_PACKET))
return -EINVAL;
if (wol->wolopts & ~WAKE_MAGIC)
return -EINVAL;
device_set_wakeup_enable(&ndev->dev, wol->wolopts & WAKE_MAGIC);
if (device_may_wakeup(&ndev->dev)) {
fep->wol_flag |= FEC_WOL_FLAG_ENABLE;
if (fep->irq[0] > 0)
enable_irq_wake(fep->irq[0]);
} else {
fep->wol_flag &= (~FEC_WOL_FLAG_ENABLE);
if (fep->irq[0] > 0)
disable_irq_wake(fep->irq[0]);
}
return 0;
}
static const struct ethtool_ops fec_enet_ethtool_ops = {
.get_settings = fec_enet_get_settings,
.set_settings = fec_enet_set_settings,
.get_drvinfo = fec_enet_get_drvinfo,
.get_regs_len = fec_enet_get_regs_len,
.get_regs = fec_enet_get_regs,
.nway_reset = fec_enet_nway_reset,
.get_link = ethtool_op_get_link,
.get_coalesce = fec_enet_get_coalesce,
.set_coalesce = fec_enet_set_coalesce,
#ifndef CONFIG_M5272
.get_pauseparam = fec_enet_get_pauseparam,
.set_pauseparam = fec_enet_set_pauseparam,
.get_strings = fec_enet_get_strings,
.get_ethtool_stats = fec_enet_get_ethtool_stats,
.get_sset_count = fec_enet_get_sset_count,
#endif
.get_ts_info = fec_enet_get_ts_info,
.get_tunable = fec_enet_get_tunable,
.set_tunable = fec_enet_set_tunable,
.get_wol = fec_enet_get_wol,
.set_wol = fec_enet_set_wol,
};
static int fec_enet_ioctl(struct net_device *ndev, struct ifreq *rq, int cmd)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct phy_device *phydev = fep->phy_dev;
if (!netif_running(ndev))
return -EINVAL;
if (!phydev)
return -ENODEV;
if (fep->bufdesc_ex) {
if (cmd == SIOCSHWTSTAMP)
return fec_ptp_set(ndev, rq);
if (cmd == SIOCGHWTSTAMP)
return fec_ptp_get(ndev, rq);
}
return phy_mii_ioctl(phydev, rq, cmd);
}
static void fec_enet_free_buffers(struct net_device *ndev)
{
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;
unsigned int q;
for (q = 0; q < fep->num_rx_queues; q++) {
rxq = fep->rx_queue[q];
bdp = rxq->bd.base;
for (i = 0; i < rxq->bd.ring_size; i++) {
skb = rxq->rx_skbuff[i];
rxq->rx_skbuff[i] = NULL;
if (skb) {
dma_unmap_single(&fep->pdev->dev,
fec32_to_cpu(bdp->cbd_bufaddr),
FEC_ENET_RX_FRSIZE - fep->rx_align,
DMA_FROM_DEVICE);
dev_kfree_skb(skb);
}
bdp = fec_enet_get_nextdesc(bdp, &rxq->bd);
}
}
for (q = 0; q < fep->num_tx_queues; q++) {
txq = fep->tx_queue[q];
bdp = txq->bd.base;
for (i = 0; i < txq->bd.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->bd.ring_size * TSO_HEADER_SIZE,
txq->tso_hdrs,
txq->tso_hdrs_dma);
}
for (i = 0; i < fep->num_rx_queues; i++)
kfree(fep->rx_queue[i]);
for (i = 0; i < fep->num_tx_queues; 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->bd.ring_size = TX_RING_SIZE;
fep->total_tx_ring_size += fep->tx_queue[i]->bd.ring_size;
txq->tx_stop_threshold = FEC_MAX_SKB_DESCS;
txq->tx_wake_threshold =
(txq->bd.ring_size - txq->tx_stop_threshold) / 2;
txq->tso_hdrs = dma_alloc_coherent(NULL,
txq->bd.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]->bd.ring_size = RX_RING_SIZE;
fep->total_rx_ring_size += fep->rx_queue[i]->bd.ring_size;
}
return ret;
alloc_failed:
fec_enet_free_queue(ndev);
return ret;
}
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_rx_q *rxq;
rxq = fep->rx_queue[queue];
bdp = rxq->bd.base;
for (i = 0; i < rxq->bd.ring_size; i++) {
skb = netdev_alloc_skb(ndev, FEC_ENET_RX_FRSIZE);
if (!skb)
goto err_alloc;
if (fec_enet_new_rxbdp(ndev, bdp, skb)) {
dev_kfree_skb(skb);
goto err_alloc;
net:fec: fix WARNING caused by lack of calls to dma_mapping_error() The driver fails to check the results of DMA mapping and results in the following warning: (with kernel config "CONFIG_DMA_API_DEBUG" enable) ------------[ cut here ]------------ WARNING: at lib/dma-debug.c:937 check_unmap+0x43c/0x7d8() fec 2188000.ethernet: DMA-API: device driver failed to check map error[device address=0x00000000383a8040] [size=2048 bytes] [mapped as single] Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.10.17-16827-g9cdb0ba-dirty #188 [<80013c4c>] (unwind_backtrace+0x0/0xf8) from [<80011704>] (show_stack+0x10/0x14) [<80011704>] (show_stack+0x10/0x14) from [<80025614>] (warn_slowpath_common+0x4c/0x6c) [<80025614>] (warn_slowpath_common+0x4c/0x6c) from [<800256c8>] (warn_slowpath_fmt+0x30/0x40) [<800256c8>] (warn_slowpath_fmt+0x30/0x40) from [<8026bfdc>] (check_unmap+0x43c/0x7d8) [<8026bfdc>] (check_unmap+0x43c/0x7d8) from [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) [<8026c584>] (debug_dma_unmap_page+0x6c/0x78) from [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) [<8038049c>] (fec_enet_rx_napi+0x254/0x8a8) from [<804dc8c0>] (net_rx_action+0x94/0x160) [<804dc8c0>] (net_rx_action+0x94/0x160) from [<8002c758>] (__do_softirq+0xe8/0x1d0) [<8002c758>] (__do_softirq+0xe8/0x1d0) from [<8002c8e8>] (do_softirq+0x4c/0x58) [<8002c8e8>] (do_softirq+0x4c/0x58) from [<8002cb50>] (irq_exit+0x90/0xc8) [<8002cb50>] (irq_exit+0x90/0xc8) from [<8000ea88>] (handle_IRQ+0x3c/0x94) [<8000ea88>] (handle_IRQ+0x3c/0x94) from [<8000855c>] (gic_handle_irq+0x28/0x5c) [<8000855c>] (gic_handle_irq+0x28/0x5c) from [<8000de00>] (__irq_svc+0x40/0x50) Exception stack(0x815a5f38 to 0x815a5f80) 5f20: 815a5f80 3b9aca00 5f40: 0fe52383 00000002 0dd8950e 00000002 81e7b080 00000000 00000000 815ac4d8 5f60: 806032ec 00000000 00000017 815a5f80 80059028 8041fc4c 60000013 ffffffff [<8000de00>] (__irq_svc+0x40/0x50) from [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) [<8041fc4c>] (cpuidle_enter_state+0x50/0xf0) from [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) [<8041fd94>] (cpuidle_idle_call+0xa8/0x14c) from [<8000edac>] (arch_cpu_idle+0x10/0x4c) [<8000edac>] (arch_cpu_idle+0x10/0x4c) from [<800582f8>] (cpu_startup_entry+0x60/0x130) [<800582f8>] (cpu_startup_entry+0x60/0x130) from [<80bc7a48>] (start_kernel+0x2d0/0x328) [<80bc7a48>] (start_kernel+0x2d0/0x328) from [<10008074>] (0x10008074) ---[ end trace c6edec32436e0042 ]--- Because dma-debug add new interfaces to debug dma mapping errors, pls refer to: http://lwn.net/Articles/516640/ After dma mapping, it must call dma_mapping_error() to check mapping error, otherwise the map_err_type alway is MAP_ERR_NOT_CHECKED, check_unmap() define the mapping is not checked and dump the error msg. So,add dma_mapping_error() checking to fix the WARNING And RX DMA buffers are used repeatedly and the driver copies it into an skb, fec_enet_rx() should not map or unmap, use dma_sync_single_for_cpu()/dma_sync_single_for_device() instead of dma_map_single()/dma_unmap_single(). There have another potential issue: fec_enet_rx() passes the DMA address to __va(). Physical and DMA addresses are *not* the same thing. They may differ if the device is behind an IOMMU or bounce buffering was required, or just because there is a fixed offset between the device and host physical addresses. Also fix it in this patch. ============================================= V2: add net_ratelimit() to limit map err message. use dma_sync_single_for_cpu() instead of dma_map_single(). fix the issue that pass DMA addresses to __va() to get virture address. V1: initial send ============================================= Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-14 09:57:10 +08:00
}
rxq->rx_skbuff[i] = skb;
bdp->cbd_sc = cpu_to_fec16(BD_ENET_RX_EMPTY);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
ebdp->cbd_esc = cpu_to_fec32(BD_ENET_RX_INT);
}
bdp = fec_enet_get_nextdesc(bdp, &rxq->bd);
}
/* Set the last buffer to wrap. */
bdp = fec_enet_get_prevdesc(bdp, &rxq->bd);
bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
return 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->bd.base;
for (i = 0; i < txq->bd.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 = cpu_to_fec16(0);
bdp->cbd_bufaddr = cpu_to_fec32(0);
if (fep->bufdesc_ex) {
struct bufdesc_ex *ebdp = (struct bufdesc_ex *)bdp;
ebdp->cbd_esc = cpu_to_fec32(BD_ENET_TX_INT);
}
bdp = fec_enet_get_nextdesc(bdp, &txq->bd);
}
/* Set the last buffer to wrap. */
bdp = fec_enet_get_prevdesc(bdp, &txq->bd);
bdp->cbd_sc |= cpu_to_fec16(BD_SC_WRAP);
return 0;
err_alloc:
fec_enet_free_buffers(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)
{
struct fec_enet_private *fep = netdev_priv(ndev);
int ret;
ret = pm_runtime_get_sync(&fep->pdev->dev);
if (ret < 0)
return ret;
pinctrl_pm_select_default_state(&fep->pdev->dev);
ret = fec_enet_clk_enable(ndev, true);
if (ret)
goto clk_enable;
/* I should reset the ring buffers here, but I don't yet know
* a simple way to do that.
*/
ret = fec_enet_alloc_buffers(ndev);
if (ret)
goto err_enet_alloc;
/* Init MAC prior to mii bus probe */
fec_restart(ndev);
/* Probe and connect to PHY when open the interface */
ret = fec_enet_mii_probe(ndev);
if (ret)
goto err_enet_mii_probe;
napi_enable(&fep->napi);
phy_start(fep->phy_dev);
netif_tx_start_all_queues(ndev);
device_set_wakeup_enable(&ndev->dev, fep->wol_flag &
FEC_WOL_FLAG_ENABLE);
return 0;
err_enet_mii_probe:
fec_enet_free_buffers(ndev);
err_enet_alloc:
fec_enet_clk_enable(ndev, false);
clk_enable:
pm_runtime_mark_last_busy(&fep->pdev->dev);
pm_runtime_put_autosuspend(&fep->pdev->dev);
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
return ret;
}
static int
fec_enet_close(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
phy_stop(fep->phy_dev);
if (netif_device_present(ndev)) {
napi_disable(&fep->napi);
netif_tx_disable(ndev);
fec_stop(ndev);
}
phy_disconnect(fep->phy_dev);
fep->phy_dev = NULL;
fec_enet_clk_enable(ndev, false);
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
pm_runtime_mark_last_busy(&fep->pdev->dev);
pm_runtime_put_autosuspend(&fep->pdev->dev);
fec_enet_free_buffers(ndev);
return 0;
}
/* Set or clear the multicast filter for this adaptor.
* Skeleton taken from sunlance driver.
* The CPM Ethernet implementation allows Multicast as well as individual
* MAC address filtering. Some of the drivers check to make sure it is
* a group multicast address, and discard those that are not. I guess I
* will do the same for now, but just remove the test if you want
* individual filtering as well (do the upper net layers want or support
* this kind of feature?).
*/
#define HASH_BITS 6 /* #bits in hash */
#define CRC32_POLY 0xEDB88320
static void set_multicast_list(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct netdev_hw_addr *ha;
unsigned int i, bit, data, crc, tmp;
unsigned char hash;
if (ndev->flags & IFF_PROMISC) {
tmp = readl(fep->hwp + FEC_R_CNTRL);
tmp |= 0x8;
writel(tmp, fep->hwp + FEC_R_CNTRL);
return;
}
tmp = readl(fep->hwp + FEC_R_CNTRL);
tmp &= ~0x8;
writel(tmp, fep->hwp + FEC_R_CNTRL);
if (ndev->flags & IFF_ALLMULTI) {
/* Catch all multicast addresses, so set the
* filter to all 1's
*/
writel(0xffffffff, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
writel(0xffffffff, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
return;
}
/* Clear filter and add the addresses in hash register
*/
writel(0, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
writel(0, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
netdev_for_each_mc_addr(ha, ndev) {
/* calculate crc32 value of mac address */
crc = 0xffffffff;
for (i = 0; i < ndev->addr_len; i++) {
data = ha->addr[i];
for (bit = 0; bit < 8; bit++, data >>= 1) {
crc = (crc >> 1) ^
(((crc ^ data) & 1) ? CRC32_POLY : 0);
}
}
/* only upper 6 bits (HASH_BITS) are used
* which point to specific bit in he hash registers
*/
hash = (crc >> (32 - HASH_BITS)) & 0x3f;
if (hash > 31) {
tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
tmp |= 1 << (hash - 32);
writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_HIGH);
} else {
tmp = readl(fep->hwp + FEC_GRP_HASH_TABLE_LOW);
tmp |= 1 << hash;
writel(tmp, fep->hwp + FEC_GRP_HASH_TABLE_LOW);
}
}
}
/* Set a MAC change in hardware. */
static int
fec_set_mac_address(struct net_device *ndev, void *p)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct sockaddr *addr = p;
if (addr) {
if (!is_valid_ether_addr(addr->sa_data))
return -EADDRNOTAVAIL;
memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len);
}
/* Add netif status check here to avoid system hang in below case:
* ifconfig ethx down; ifconfig ethx hw ether xx:xx:xx:xx:xx:xx;
* After ethx down, fec all clocks are gated off and then register
* access causes system hang.
*/
if (!netif_running(ndev))
return 0;
writel(ndev->dev_addr[3] | (ndev->dev_addr[2] << 8) |
(ndev->dev_addr[1] << 16) | (ndev->dev_addr[0] << 24),
fep->hwp + FEC_ADDR_LOW);
writel((ndev->dev_addr[5] << 16) | (ndev->dev_addr[4] << 24),
fep->hwp + FEC_ADDR_HIGH);
return 0;
}
#ifdef CONFIG_NET_POLL_CONTROLLER
/**
* fec_poll_controller - FEC Poll controller function
* @dev: The FEC network adapter
*
* Polled functionality used by netconsole and others in non interrupt mode
*
*/
static void fec_poll_controller(struct net_device *dev)
{
int i;
struct fec_enet_private *fep = netdev_priv(dev);
for (i = 0; i < FEC_IRQ_NUM; i++) {
if (fep->irq[i] > 0) {
disable_irq(fep->irq[i]);
fec_enet_interrupt(fep->irq[i], dev);
enable_irq(fep->irq[i]);
}
}
}
#endif
static inline void fec_enet_set_netdev_features(struct net_device *netdev,
netdev_features_t features)
{
struct fec_enet_private *fep = netdev_priv(netdev);
netdev_features_t changed = features ^ netdev->features;
netdev->features = features;
/* Receive checksum has been changed */
if (changed & NETIF_F_RXCSUM) {
if (features & NETIF_F_RXCSUM)
fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
else
fep->csum_flags &= ~FLAG_RX_CSUM_ENABLED;
}
}
static int fec_set_features(struct net_device *netdev,
netdev_features_t features)
{
struct fec_enet_private *fep = netdev_priv(netdev);
netdev_features_t changed = features ^ netdev->features;
if (netif_running(netdev) && changed & NETIF_F_RXCSUM) {
napi_disable(&fep->napi);
netif_tx_lock_bh(netdev);
fec_stop(netdev);
fec_enet_set_netdev_features(netdev, features);
fec_restart(netdev);
netif_tx_wake_all_queues(netdev);
netif_tx_unlock_bh(netdev);
napi_enable(&fep->napi);
} else {
fec_enet_set_netdev_features(netdev, features);
}
return 0;
}
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_set_rx_mode = set_multicast_list,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_tx_timeout = fec_timeout,
.ndo_set_mac_address = fec_set_mac_address,
.ndo_do_ioctl = fec_enet_ioctl,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = fec_poll_controller,
#endif
.ndo_set_features = fec_set_features,
};
static const unsigned short offset_des_active_rxq[] = {
FEC_R_DES_ACTIVE_0, FEC_R_DES_ACTIVE_1, FEC_R_DES_ACTIVE_2
};
static const unsigned short offset_des_active_txq[] = {
FEC_X_DES_ACTIVE_0, FEC_X_DES_ACTIVE_1, FEC_X_DES_ACTIVE_2
};
/*
* XXX: We need to clean up on failure exits here.
*
*/
static int fec_enet_init(struct net_device *ndev)
{
struct fec_enet_private *fep = netdev_priv(ndev);
struct bufdesc *cbd_base;
dma_addr_t bd_dma;
int bd_size;
unsigned int i;
unsigned dsize = fep->bufdesc_ex ? sizeof(struct bufdesc_ex) :
sizeof(struct bufdesc);
unsigned dsize_log2 = __fls(dsize);
WARN_ON(dsize != (1 << dsize_log2));
#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);
bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize;
/* Allocate memory for buffer descriptors. */
cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
GFP_KERNEL);
if (!cbd_base) {
return -ENOMEM;
}
memset(cbd_base, 0, bd_size);
/* Get the Ethernet address */
fec_get_mac(ndev);
/* make sure MAC we just acquired is programmed into the hw */
fec_set_mac_address(ndev, NULL);
/* Set receive and transmit descriptor base. */
for (i = 0; i < fep->num_rx_queues; i++) {
struct fec_enet_priv_rx_q *rxq = fep->rx_queue[i];
unsigned size = dsize * rxq->bd.ring_size;
rxq->bd.qid = i;
rxq->bd.base = cbd_base;
rxq->bd.cur = cbd_base;
rxq->bd.dma = bd_dma;
rxq->bd.dsize = dsize;
rxq->bd.dsize_log2 = dsize_log2;
rxq->bd.reg_desc_active = fep->hwp + offset_des_active_rxq[i];
bd_dma += size;
cbd_base = (struct bufdesc *)(((void *)cbd_base) + size);
rxq->bd.last = (struct bufdesc *)(((void *)cbd_base) - dsize);
}
for (i = 0; i < fep->num_tx_queues; i++) {
struct fec_enet_priv_tx_q *txq = fep->tx_queue[i];
unsigned size = dsize * txq->bd.ring_size;
txq->bd.qid = i;
txq->bd.base = cbd_base;
txq->bd.cur = cbd_base;
txq->bd.dma = bd_dma;
txq->bd.dsize = dsize;
txq->bd.dsize_log2 = dsize_log2;
txq->bd.reg_desc_active = fep->hwp + offset_des_active_txq[i];
bd_dma += size;
cbd_base = (struct bufdesc *)(((void *)cbd_base) + size);
txq->bd.last = (struct bufdesc *)(((void *)cbd_base) - dsize);
}
/* The FEC Ethernet specific entries in the device structure */
ndev->watchdog_timeo = TX_TIMEOUT;
ndev->netdev_ops = &fec_netdev_ops;
ndev->ethtool_ops = &fec_enet_ethtool_ops;
writel(FEC_RX_DISABLED_IMASK, fep->hwp + FEC_IMASK);
netif_napi_add(ndev, &fep->napi, fec_enet_rx_napi, NAPI_POLL_WEIGHT);
if (fep->quirks & FEC_QUIRK_HAS_VLAN)
/* enable hw VLAN support */
ndev->features |= NETIF_F_HW_VLAN_CTAG_RX;
if (fep->quirks & FEC_QUIRK_HAS_CSUM) {
ndev->gso_max_segs = FEC_MAX_TSO_SEGS;
/* enable hw accelerator */
ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM
| NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO);
fep->csum_flags |= FLAG_RX_CSUM_ENABLED;
}
if (fep->quirks & FEC_QUIRK_HAS_AVB) {
fep->tx_align = 0;
fep->rx_align = 0x3f;
}
ndev->hw_features = ndev->features;
fec_restart(ndev);
return 0;
}
#ifdef CONFIG_OF
static void fec_reset_phy(struct platform_device *pdev)
{
int err, phy_reset;
bool active_high = false;
int msec = 1;
struct device_node *np = pdev->dev.of_node;
if (!np)
return;
of_property_read_u32(np, "phy-reset-duration", &msec);
/* A sane reset duration should not be longer than 1s */
if (msec > 1000)
msec = 1;
phy_reset = of_get_named_gpio(np, "phy-reset-gpios", 0);
if (!gpio_is_valid(phy_reset))
return;
active_high = of_property_read_bool(np, "phy-reset-active-high");
err = devm_gpio_request_one(&pdev->dev, phy_reset,
active_high ? GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW,
"phy-reset");
if (err) {
dev_err(&pdev->dev, "failed to get phy-reset-gpios: %d\n", err);
return;
}
msleep(msec);
gpio_set_value_cansleep(phy_reset, !active_high);
}
#else /* CONFIG_OF */
static void fec_reset_phy(struct platform_device *pdev)
{
/*
* In case of platform probe, the reset has been done
* by machine code.
*/
}
#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;
*num_tx = *num_rx = 1;
if (!np || !of_device_is_available(np))
return;
/* parse the num of tx and rx queues */
of_property_read_u32(np, "fsl,num-tx-queues", num_tx);
of_property_read_u32(np, "fsl,num-rx-queues", num_rx);
if (*num_tx < 1 || *num_tx > FEC_ENET_MAX_TX_QS) {
dev_warn(&pdev->dev, "Invalid num_tx(=%d), fall back to 1\n",
*num_tx);
*num_tx = 1;
return;
}
if (*num_rx < 1 || *num_rx > FEC_ENET_MAX_RX_QS) {
dev_warn(&pdev->dev, "Invalid num_rx(=%d), fall back to 1\n",
*num_rx);
*num_rx = 1;
return;
}
}
static int
fec_probe(struct platform_device *pdev)
{
struct fec_enet_private *fep;
struct fec_platform_data *pdata;
struct net_device *ndev;
int i, irq, ret = 0;
struct resource *r;
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;
int num_rx_qs;
fec_enet_get_queue_num(pdev, &num_tx_qs, &num_rx_qs);
/* Init network device */
ndev = alloc_etherdev_mqs(sizeof(struct fec_enet_private),
num_tx_qs, num_rx_qs);
if (!ndev)
return -ENOMEM;
SET_NETDEV_DEV(ndev, &pdev->dev);
/* setup board info structure */
fep = netdev_priv(ndev);
of_id = of_match_device(fec_dt_ids, &pdev->dev);
if (of_id)
pdev->id_entry = of_id->data;
fep->quirks = pdev->id_entry->driver_data;
fep->netdev = 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 (fep->quirks & FEC_QUIRK_HAS_GBIT)
fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG;
#endif
/* Select default pin state */
pinctrl_pm_select_default_state(&pdev->dev);
r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
fep->hwp = devm_ioremap_resource(&pdev->dev, r);
if (IS_ERR(fep->hwp)) {
ret = PTR_ERR(fep->hwp);
goto failed_ioremap;
}
fep->pdev = pdev;
fep->dev_id = dev_id++;
platform_set_drvdata(pdev, ndev);
if (of_get_property(np, "fsl,magic-packet", NULL))
fep->wol_flag |= FEC_WOL_HAS_MAGIC_PACKET;
phy_node = of_parse_phandle(np, "phy-handle", 0);
if (!phy_node && of_phy_is_fixed_link(np)) {
ret = of_phy_register_fixed_link(np);
if (ret < 0) {
dev_err(&pdev->dev,
"broken fixed-link specification\n");
goto failed_phy;
}
phy_node = of_node_get(np);
}
fep->phy_node = phy_node;
ret = of_get_phy_mode(pdev->dev.of_node);
if (ret < 0) {
pdata = dev_get_platdata(&pdev->dev);
if (pdata)
fep->phy_interface = pdata->phy;
else
fep->phy_interface = PHY_INTERFACE_MODE_MII;
} else {
fep->phy_interface = ret;
}
fep->clk_ipg = devm_clk_get(&pdev->dev, "ipg");
if (IS_ERR(fep->clk_ipg)) {
ret = PTR_ERR(fep->clk_ipg);
goto failed_clk;
}
fep->clk_ahb = devm_clk_get(&pdev->dev, "ahb");
if (IS_ERR(fep->clk_ahb)) {
ret = PTR_ERR(fep->clk_ahb);
goto failed_clk;
}
fep->itr_clk_rate = clk_get_rate(fep->clk_ahb);
/* enet_out is optional, depends on board */
fep->clk_enet_out = devm_clk_get(&pdev->dev, "enet_out");
if (IS_ERR(fep->clk_enet_out))
fep->clk_enet_out = NULL;
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->bufdesc_ex = fep->quirks & FEC_QUIRK_HAS_BUFDESC_EX;
fep->clk_ptp = devm_clk_get(&pdev->dev, "ptp");
if (IS_ERR(fep->clk_ptp)) {
fep->clk_ptp = NULL;
fep->bufdesc_ex = false;
}
ret = fec_enet_clk_enable(ndev, true);
if (ret)
goto failed_clk;
ret = clk_prepare_enable(fep->clk_ipg);
if (ret)
goto failed_clk_ipg;
fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
if (!IS_ERR(fep->reg_phy)) {
ret = regulator_enable(fep->reg_phy);
if (ret) {
dev_err(&pdev->dev,
"Failed to enable phy regulator: %d\n", ret);
goto failed_regulator;
}
} else {
fep->reg_phy = NULL;
}
pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
pm_runtime_use_autosuspend(&pdev->dev);
pm_runtime_get_noresume(&pdev->dev);
pm_runtime_set_active(&pdev->dev);
pm_runtime_enable(&pdev->dev);
fec_reset_phy(pdev);
if (fep->bufdesc_ex)
fec_ptp_init(pdev);
ret = fec_enet_init(ndev);
if (ret)
goto failed_init;
for (i = 0; i < FEC_IRQ_NUM; i++) {
irq = platform_get_irq(pdev, i);
if (irq < 0) {
if (i)
break;
ret = irq;
goto failed_irq;
}
ret = devm_request_irq(&pdev->dev, irq, fec_enet_interrupt,
0, pdev->name, ndev);
if (ret)
goto failed_irq;
fep->irq[i] = irq;
}
net: fec: init complete variable in early to avoid kernel dump Software clear the MDIO interrupt before MDIO bus access, but MAC still generate MDIO interrupt. The issue only happen on imx6slx chip. CPU: 0 PID: 1 Comm: swapper/0 Not tainted 3.17.0-rc1-00399-g0bcad17 #315 Backtrace: [<800121fc>] (dump_backtrace) from [<800124e0>] (show_stack+0x18/0x1c) r6:8096e534 r5:8096e534 r4:00000000 r3:00000000 [<800124c8>] (show_stack) from [<806a4c60>] (dump_stack+0x8c/0xa4) [<806a4bd4>] (dump_stack) from [<80060ab8>] (__lock_acquire+0x1814/0x1c40) r6:be078000 r5:be074000 r4:be03f6e4 r3:be078000 [<8005f2a4>] (__lock_acquire) from [<800616e0>] (lock_acquire+0x70/0x84) r10:809ada33 r9:be010600 r8:00000096 r7:00000001 r6:be074000 r5:00000000 r4:60000193 [<80061670>] (lock_acquire) from [<806abb20>] (_raw_spin_lock_irqsave+0x40/0x54) r7:00000000 r6:8005a3f8 r5:00000193 r4:be03f6d4 [<806abae0>] (_raw_spin_lock_irqsave) from [<8005a3f8>] (complete+0x1c/0x4c) r6:80950904 r5:be03f6d0 r4:be03f6d4 [<8005a3dc>] (complete) from [<8041b4c0>] (fec_enet_interrupt+0x128/0x164) r6:80950904 r5:00800000 r4:be03f000 r3:00000000 [<8041b398>] (fec_enet_interrupt) from [<8006aeac>] (handle_irq_event_percpu+0x38/0x13c) r6:00000000 r5:be01065c r4:be399e00 r3:8041b398 [<8006ae74>] (handle_irq_event_percpu) from [<8006aff4>] (handle_irq_event+0x44/0x64) r10:be03f000 r9:80989fe0 r8:00000000 r7:00000096 r6:be399e00 r5:be01065c r4:be010600 [<8006afb0>] (handle_irq_event) from [<8006e3e8>] (handle_fasteoi_irq+0xc8/0x1bc) r6:8096e764 r5:be01065c r4:be010600 r3:00000000 [<8006e320>] (handle_fasteoi_irq) from [<8006a63c>] (generic_handle_irq+0x30/0x44) r6:be074010 r5:80945e4c r4:00000096 r3:8006e320 [<8006a60c>] (generic_handle_irq) from [<8000f218>] (handle_IRQ+0x54/0xbc) r4:80950d74 r3:00000180 [<8000f1c4>] (handle_IRQ) from [<800086cc>] (gic_handle_irq+0x30/0x68) r8:be3ab478 r7:c080e100 r6:be075bd8 r5:80950eec r4:c080e10c r3:000000a0 [<8000869c>] (gic_handle_irq) from [<80013064>] (__irq_svc+0x44/0x5c) Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: Frank Li <Frank.Li@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-09-13 05:00:55 +08:00
init_completion(&fep->mdio_done);
ret = fec_enet_mii_init(pdev);
if (ret)
goto failed_mii_init;
/* Carrier starts down, phylib will bring it up */
netif_carrier_off(ndev);
fec_enet_clk_enable(ndev, false);
pinctrl_pm_select_sleep_state(&pdev->dev);
ret = register_netdev(ndev);
if (ret)
goto failed_register;
device_init_wakeup(&ndev->dev, fep->wol_flag &
FEC_WOL_HAS_MAGIC_PACKET);
if (fep->bufdesc_ex && fep->ptp_clock)
netdev_info(ndev, "registered PHC device %d\n", fep->dev_id);
fep->rx_copybreak = COPYBREAK_DEFAULT;
INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
pm_runtime_mark_last_busy(&pdev->dev);
pm_runtime_put_autosuspend(&pdev->dev);
return 0;
failed_register:
fec_enet_mii_remove(fep);
failed_mii_init:
failed_irq:
failed_init:
fec_ptp_stop(pdev);
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
failed_regulator:
clk_disable_unprepare(fep->clk_ipg);
failed_clk_ipg:
fec_enet_clk_enable(ndev, false);
failed_clk:
failed_phy:
of_node_put(phy_node);
failed_ioremap:
free_netdev(ndev);
return ret;
}
static int
fec_drv_remove(struct platform_device *pdev)
{
struct net_device *ndev = platform_get_drvdata(pdev);
struct fec_enet_private *fep = netdev_priv(ndev);
cancel_work_sync(&fep->tx_timeout_work);
fec_ptp_stop(pdev);
unregister_netdev(ndev);
fec_enet_mii_remove(fep);
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
of_node_put(fep->phy_node);
free_netdev(ndev);
return 0;
}
static int __maybe_unused fec_suspend(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
rtnl_lock();
if (netif_running(ndev)) {
if (fep->wol_flag & FEC_WOL_FLAG_ENABLE)
fep->wol_flag |= FEC_WOL_FLAG_SLEEP_ON;
phy_stop(fep->phy_dev);
napi_disable(&fep->napi);
netif_tx_lock_bh(ndev);
netif_device_detach(ndev);
netif_tx_unlock_bh(ndev);
fec_stop(ndev);
net: fec: fix suspend broken on multiple MACs sillicons On i.MX6SX sdb platform, there has two same enet MACs, after system up, just eth0 is up, and then do suspend/resume test: [ 50.437967] PM: Syncing filesystems ... done. [ 50.476924] Freezing user space processes ... (elapsed 0.005 seconds) done. [ 50.490093] Freezing remaining freezable tasks ... (elapsed 0.004 seconds) done. [ 50.559771] ------------[ cut here ]------------ [ 50.564453] WARNING: CPU: 0 PID: 575 at drivers/clk/clk.c:851 __clk_disable+0x60/0x6c() [ 50.572475] Modules linked in: [ 50.575578] CPU: 0 PID: 575 Comm: sh Not tainted 3.18.0-rc2-next-20141031-00007-gf61135b #21 [ 50.584031] Backtrace: [ 50.586550] [<80011ecc>] (dump_backtrace) from [<8001206c>] (show_stack+0x18/0x1c) [ 50.594136] r6:808a7a54 r5:00000000 r4:00000000 r3:00000000 [ 50.599920] [<80012054>] (show_stack) from [<806ab3c0>] (dump_stack+0x80/0x9c) [ 50.607187] [<806ab340>] (dump_stack) from [<8002a3e8>] (warn_slowpath_common+0x6c/0x8c) [ 50.615294] r5:00000353 r4:00000000 [ 50.618940] [<8002a37c>] (warn_slowpath_common) from [<8002a42c>] (warn_slowpath_null+0x24/0x2c) [ 50.627738] r8:00000000 r7:be144c44 r6:be015600 r5:80070013 r4:be015600 [ 50.634573] [<8002a408>] (warn_slowpath_null) from [<804f8d4c>] (__clk_disable+0x60/0x6c) [ 50.642777] [<804f8cec>] (__clk_disable) from [<804f8e5c>] (clk_disable+0x2c/0x38) [ 50.650359] r4:be015600 r3:00000000 [ 50.654006] [<804f8e30>] (clk_disable) from [<80420ab4>] (fec_enet_clk_enable+0xc4/0x258) [ 50.662196] r5:be3cb620 r4:be3cb000 [ 50.665838] [<804209f0>] (fec_enet_clk_enable) from [<80421178>] (fec_suspend+0x30/0x180) [ 50.674026] r7:be144c44 r6:be144c10 r5:8037f5a4 r4:be3cb000 [ 50.679802] [<80421148>] (fec_suspend) from [<8037f5d8>] (platform_pm_suspend+0x34/0x64) [ 50.687906] r10:00000000 r9:00000000 r8:00000000 r7:be144c44 r6:be144c10 r5:8037f5a4 [ 50.695852] r4:be144c10 r3:80421148 [ 50.699511] [<8037f5a4>] (platform_pm_suspend) from [<8038784c>] (dpm_run_callback.isra.14+0x34/0x6c) [ 50.708764] [<80387818>] (dpm_run_callback.isra.14) from [<80387f00>] (__device_suspend+0x12c/0x2a4) [ 50.717909] r9:8098ec8c r8:80973bec r6:00000002 r5:811c7038 r4:be144c10 [ 50.724746] [<80387dd4>] (__device_suspend) from [<803894fc>] (dpm_suspend+0x64/0x224) [ 50.732675] r8:80973bec r7:be144c10 r6:8098ec24 r5:811c7038 r4:be144cc4 [ 50.739509] [<80389498>] (dpm_suspend) from [<8038999c>] (dpm_suspend_start+0x60/0x68) [ 50.747438] r10:8082fa24 r9:00000000 r8:00000004 r7:00000003 r6:00000000 r5:8116ec80 [ 50.755386] r4:00000002 [ 50.757969] [<8038993c>] (dpm_suspend_start) from [<800679d8>] (suspend_devices_and_enter+0x90/0x3ec) [ 50.767202] r4:00000003 r3:8116eca0 [ 50.770843] [<80067948>] (suspend_devices_and_enter) from [<80067f40>] (pm_suspend+0x20c/0x2a4) [ 50.779553] r8:00000004 r7:00000003 r6:00000000 r5:8116ec8c r4:00000003 [ 50.786394] [<80067d34>] (pm_suspend) from [<80066858>] (state_store+0x70/0xc0) [ 50.793718] r6:8116ec90 r5:00000003 r4:bd88a800 r3:0000006d [ 50.799496] [<800667e8>] (state_store) from [<802b0384>] (kobj_attr_store+0x1c/0x28) [ 50.807251] r10:bd399f78 r8:00000000 r7:bd88a800 r6:bd88a800 r5:00000004 r4:bd085680 [ 50.815219] [<802b0368>] (kobj_attr_store) from [<80153090>] (sysfs_kf_write+0x54/0x58) [ 50.823252] [<8015303c>] (sysfs_kf_write) from [<80151fd8>] (kernfs_fop_write+0xd0/0x194) [ 50.831441] r6:00000004 r5:bd08568c r4:bd085680 r3:8015303c [ 50.837220] [<80151f08>] (kernfs_fop_write) from [<800eddb4>] (vfs_write+0xb8/0x1a8) [ 50.844975] r10:00000000 r9:00000000 r8:00000000 r7:bd399f78 r6:01336408 r5:00000004 [ 50.852924] r4:bc584dc0 [ 50.855505] [<800edcfc>] (vfs_write) from [<800ee0b8>] (SyS_write+0x48/0x88) [ 50.862567] r10:00000000 r8:00000000 r7:01336408 r6:00000004 r5:bc584dc0 r4:bc584dc0 [ 50.870537] [<800ee070>] (SyS_write) from [<8000eb00>] (ret_fast_syscall+0x0/0x48) [ 50.878120] r9:bd398000 r8:8000ecc4 r7:00000004 r6:76f42b48 r5:01336408 r4:00000004 [ 50.885983] ---[ end trace 7545115d752a316a ]--- [ 50.890765] ------------[ cut here ]------------ The root cause is that eth1 is not opened and clock is not enabled, and .suspend() still call .fec_enet_clk_enable() to disable clock. To avoid the broken, let it check network device up status by calling .netif_running() before disable/enable clocks. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-03 13:26:50 +08:00
fec_enet_clk_enable(ndev, false);
if (!(fep->wol_flag & FEC_WOL_FLAG_ENABLE))
pinctrl_pm_select_sleep_state(&fep->pdev->dev);
}
rtnl_unlock();
if (fep->reg_phy && !(fep->wol_flag & FEC_WOL_FLAG_ENABLE))
regulator_disable(fep->reg_phy);
/* SOC supply clock to phy, when clock is disabled, phy link down
* SOC control phy regulator, when regulator is disabled, phy link down
*/
if (fep->clk_enet_out || fep->reg_phy)
fep->link = 0;
return 0;
}
static int __maybe_unused fec_resume(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
struct fec_platform_data *pdata = fep->pdev->dev.platform_data;
int ret;
int val;
if (fep->reg_phy && !(fep->wol_flag & FEC_WOL_FLAG_ENABLE)) {
ret = regulator_enable(fep->reg_phy);
if (ret)
return ret;
}
rtnl_lock();
if (netif_running(ndev)) {
net: fec: fix suspend broken on multiple MACs sillicons On i.MX6SX sdb platform, there has two same enet MACs, after system up, just eth0 is up, and then do suspend/resume test: [ 50.437967] PM: Syncing filesystems ... done. [ 50.476924] Freezing user space processes ... (elapsed 0.005 seconds) done. [ 50.490093] Freezing remaining freezable tasks ... (elapsed 0.004 seconds) done. [ 50.559771] ------------[ cut here ]------------ [ 50.564453] WARNING: CPU: 0 PID: 575 at drivers/clk/clk.c:851 __clk_disable+0x60/0x6c() [ 50.572475] Modules linked in: [ 50.575578] CPU: 0 PID: 575 Comm: sh Not tainted 3.18.0-rc2-next-20141031-00007-gf61135b #21 [ 50.584031] Backtrace: [ 50.586550] [<80011ecc>] (dump_backtrace) from [<8001206c>] (show_stack+0x18/0x1c) [ 50.594136] r6:808a7a54 r5:00000000 r4:00000000 r3:00000000 [ 50.599920] [<80012054>] (show_stack) from [<806ab3c0>] (dump_stack+0x80/0x9c) [ 50.607187] [<806ab340>] (dump_stack) from [<8002a3e8>] (warn_slowpath_common+0x6c/0x8c) [ 50.615294] r5:00000353 r4:00000000 [ 50.618940] [<8002a37c>] (warn_slowpath_common) from [<8002a42c>] (warn_slowpath_null+0x24/0x2c) [ 50.627738] r8:00000000 r7:be144c44 r6:be015600 r5:80070013 r4:be015600 [ 50.634573] [<8002a408>] (warn_slowpath_null) from [<804f8d4c>] (__clk_disable+0x60/0x6c) [ 50.642777] [<804f8cec>] (__clk_disable) from [<804f8e5c>] (clk_disable+0x2c/0x38) [ 50.650359] r4:be015600 r3:00000000 [ 50.654006] [<804f8e30>] (clk_disable) from [<80420ab4>] (fec_enet_clk_enable+0xc4/0x258) [ 50.662196] r5:be3cb620 r4:be3cb000 [ 50.665838] [<804209f0>] (fec_enet_clk_enable) from [<80421178>] (fec_suspend+0x30/0x180) [ 50.674026] r7:be144c44 r6:be144c10 r5:8037f5a4 r4:be3cb000 [ 50.679802] [<80421148>] (fec_suspend) from [<8037f5d8>] (platform_pm_suspend+0x34/0x64) [ 50.687906] r10:00000000 r9:00000000 r8:00000000 r7:be144c44 r6:be144c10 r5:8037f5a4 [ 50.695852] r4:be144c10 r3:80421148 [ 50.699511] [<8037f5a4>] (platform_pm_suspend) from [<8038784c>] (dpm_run_callback.isra.14+0x34/0x6c) [ 50.708764] [<80387818>] (dpm_run_callback.isra.14) from [<80387f00>] (__device_suspend+0x12c/0x2a4) [ 50.717909] r9:8098ec8c r8:80973bec r6:00000002 r5:811c7038 r4:be144c10 [ 50.724746] [<80387dd4>] (__device_suspend) from [<803894fc>] (dpm_suspend+0x64/0x224) [ 50.732675] r8:80973bec r7:be144c10 r6:8098ec24 r5:811c7038 r4:be144cc4 [ 50.739509] [<80389498>] (dpm_suspend) from [<8038999c>] (dpm_suspend_start+0x60/0x68) [ 50.747438] r10:8082fa24 r9:00000000 r8:00000004 r7:00000003 r6:00000000 r5:8116ec80 [ 50.755386] r4:00000002 [ 50.757969] [<8038993c>] (dpm_suspend_start) from [<800679d8>] (suspend_devices_and_enter+0x90/0x3ec) [ 50.767202] r4:00000003 r3:8116eca0 [ 50.770843] [<80067948>] (suspend_devices_and_enter) from [<80067f40>] (pm_suspend+0x20c/0x2a4) [ 50.779553] r8:00000004 r7:00000003 r6:00000000 r5:8116ec8c r4:00000003 [ 50.786394] [<80067d34>] (pm_suspend) from [<80066858>] (state_store+0x70/0xc0) [ 50.793718] r6:8116ec90 r5:00000003 r4:bd88a800 r3:0000006d [ 50.799496] [<800667e8>] (state_store) from [<802b0384>] (kobj_attr_store+0x1c/0x28) [ 50.807251] r10:bd399f78 r8:00000000 r7:bd88a800 r6:bd88a800 r5:00000004 r4:bd085680 [ 50.815219] [<802b0368>] (kobj_attr_store) from [<80153090>] (sysfs_kf_write+0x54/0x58) [ 50.823252] [<8015303c>] (sysfs_kf_write) from [<80151fd8>] (kernfs_fop_write+0xd0/0x194) [ 50.831441] r6:00000004 r5:bd08568c r4:bd085680 r3:8015303c [ 50.837220] [<80151f08>] (kernfs_fop_write) from [<800eddb4>] (vfs_write+0xb8/0x1a8) [ 50.844975] r10:00000000 r9:00000000 r8:00000000 r7:bd399f78 r6:01336408 r5:00000004 [ 50.852924] r4:bc584dc0 [ 50.855505] [<800edcfc>] (vfs_write) from [<800ee0b8>] (SyS_write+0x48/0x88) [ 50.862567] r10:00000000 r8:00000000 r7:01336408 r6:00000004 r5:bc584dc0 r4:bc584dc0 [ 50.870537] [<800ee070>] (SyS_write) from [<8000eb00>] (ret_fast_syscall+0x0/0x48) [ 50.878120] r9:bd398000 r8:8000ecc4 r7:00000004 r6:76f42b48 r5:01336408 r4:00000004 [ 50.885983] ---[ end trace 7545115d752a316a ]--- [ 50.890765] ------------[ cut here ]------------ The root cause is that eth1 is not opened and clock is not enabled, and .suspend() still call .fec_enet_clk_enable() to disable clock. To avoid the broken, let it check network device up status by calling .netif_running() before disable/enable clocks. Signed-off-by: Fugang Duan <B38611@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-03 13:26:50 +08:00
ret = fec_enet_clk_enable(ndev, true);
if (ret) {
rtnl_unlock();
goto failed_clk;
}
if (fep->wol_flag & FEC_WOL_FLAG_ENABLE) {
if (pdata && pdata->sleep_mode_enable)
pdata->sleep_mode_enable(false);
val = readl(fep->hwp + FEC_ECNTRL);
val &= ~(FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
writel(val, fep->hwp + FEC_ECNTRL);
fep->wol_flag &= ~FEC_WOL_FLAG_SLEEP_ON;
} else {
pinctrl_pm_select_default_state(&fep->pdev->dev);
}
fec_restart(ndev);
netif_tx_lock_bh(ndev);
netif_device_attach(ndev);
netif_tx_unlock_bh(ndev);
napi_enable(&fep->napi);
phy_start(fep->phy_dev);
}
rtnl_unlock();
return 0;
failed_clk:
if (fep->reg_phy)
regulator_disable(fep->reg_phy);
return ret;
}
static int __maybe_unused fec_runtime_suspend(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
clk_disable_unprepare(fep->clk_ipg);
return 0;
}
static int __maybe_unused fec_runtime_resume(struct device *dev)
{
struct net_device *ndev = dev_get_drvdata(dev);
struct fec_enet_private *fep = netdev_priv(ndev);
return clk_prepare_enable(fep->clk_ipg);
}
static const struct dev_pm_ops fec_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
};
static struct platform_driver fec_driver = {
.driver = {
.name = DRIVER_NAME,
.pm = &fec_pm_ops,
.of_match_table = fec_dt_ids,
},
.id_table = fec_devtype,
.probe = fec_probe,
.remove = fec_drv_remove,
};
module_platform_driver(fec_driver);
MODULE_ALIAS("platform:"DRIVER_NAME);
MODULE_LICENSE("GPL");