- ale_entries : Specifies No of entries ALE can hold
- host_port_reg_ofs : Specifies host port register offset
- hw_stats_reg_ofs : Specifies hardware statistics register offset
+- cpts_reg_ofs : Specifies the offset of the CPTS registers
- bd_ram_ofs : Specifies internal desciptor RAM offset
- bd_ram_size : Specifies internal descriptor RAM size
- rx_descs : Specifies number of Rx descriptors
- mac_control : Specifies Default MAC control register content
for the specific platform
- slaves : Specifies number for slaves
+- cpts_active_slave : Specifies the slave to use for time stamping
+- cpts_clock_mult : Numerator to convert input clock ticks into nanoseconds
+- cpts_clock_shift : Denominator to convert input clock ticks into nanoseconds
- slave_reg_ofs : Specifies slave register offset
- sliver_reg_ofs : Specifies slave sliver register offset
- phy_id : Specifies slave phy id
ale_entries = <1024>;
host_port_reg_ofs = <0x108>;
hw_stats_reg_ofs = <0x900>;
+ cpts_reg_ofs = <0xc00>;
bd_ram_ofs = <0x2000>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
+ cpts_active_slave = <0>;
+ cpts_clock_mult = <0x80000000>;
+ cpts_clock_shift = <29>;
cpsw_emac0: slave@0 {
- slave_reg_ofs = <0x208>;
+ slave_reg_ofs = <0x200>;
sliver_reg_ofs = <0xd80>;
phy_id = "davinci_mdio.16:00";
/* Filled in by U-Boot */
mac-address = [ 00 00 00 00 00 00 ];
};
cpsw_emac1: slave@1 {
- slave_reg_ofs = <0x308>;
+ slave_reg_ofs = <0x300>;
sliver_reg_ofs = <0xdc0>;
phy_id = "davinci_mdio.16:01";
/* Filled in by U-Boot */
ale_entries = <1024>;
host_port_reg_ofs = <0x108>;
hw_stats_reg_ofs = <0x900>;
+ cpts_reg_ofs = <0xc00>;
bd_ram_ofs = <0x2000>;
bd_ram_size = <0x2000>;
no_bd_ram = <0>;
rx_descs = <64>;
mac_control = <0x20>;
slaves = <2>;
+ cpts_active_slave = <0>;
+ cpts_clock_mult = <0x80000000>;
+ cpts_clock_shift = <29>;
cpsw_emac0: slave@0 {
- slave_reg_ofs = <0x208>;
+ slave_reg_ofs = <0x200>;
sliver_reg_ofs = <0xd80>;
phy_id = "davinci_mdio.16:00";
/* Filled in by U-Boot */
mac-address = [ 00 00 00 00 00 00 ];
};
cpsw_emac1: slave@1 {
- slave_reg_ofs = <0x308>;
+ slave_reg_ofs = <0x300>;
sliver_reg_ofs = <0xdc0>;
phy_id = "davinci_mdio.16:01";
/* Filled in by U-Boot */
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
66 0x1b0b0 /* MX6Q_PAD_RGMII_RD2__ENET_RGMII_RD2 */
70 0x1b0b0 /* MX6Q_PAD_RGMII_RD3__ENET_RGMII_RD3 */
48 0x1b0b0 /* MX6Q_PAD_RGMII_RX_CTL__RGMII_RX_CTL */
+ 1033 0x4001b0a8 /* MX6Q_PAD_GPIO_16__ENET_ANATOP_ETHERNET_REF_OUT*/
>;
};
compatible = "fsl,imx6q-fec";
reg = <0x02188000 0x4000>;
interrupts = <0 118 0x04 0 119 0x04>;
- clocks = <&clks 117>, <&clks 117>;
- clock-names = "ipg", "ahb";
+ clocks = <&clks 117>, <&clks 117>, <&clks 177>;
+ clock-names = "ipg", "ahb", "ptp";
status = "disabled";
};
imx6q_sabrelite_cko1_setup();
}
+static void __init imx6q_1588_init(void)
+{
+ struct regmap *gpr;
+
+ gpr = syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
+ if (!IS_ERR(gpr))
+ regmap_update_bits(gpr, 0x4, 1 << 21, 1 << 21);
+ else
+ pr_err("failed to find fsl,imx6q-iomux-gpr regmap\n");
+
+}
static void __init imx6q_usb_init(void)
{
struct regmap *anatop;
imx6q_pm_init();
imx6q_usb_init();
+ imx6q_1588_init();
}
static struct cpuidle_driver imx6q_cpuidle_driver = {
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 0x401a
#define SO_DETACH_FILTER 0x401b
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_ACCEPTCONN 0x401c
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
#define SO_ATTACH_FILTER 0x001a
#define SO_DETACH_FILTER 0x001b
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 0x001c
#define SO_TIMESTAMP 0x001d
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
config BFIN_MAC_USE_HWSTAMP
bool "Use IEEE 1588 hwstamp"
- depends on BFIN_MAC && BF518
+ depends on BFIN_MAC && BF518 && PTP_1588_CLOCK && !(BFIN_MAC=y && PTP_1588_CLOCK=m)
default y
---help---
To support the IEEE 1588 Precision Time Protocol (PTP), select y here
return 0;
}
+#ifdef CONFIG_BFIN_MAC_USE_HWSTAMP
static int bfin_mac_ethtool_get_ts_info(struct net_device *dev,
struct ethtool_ts_info *info)
{
+ struct bfin_mac_local *lp = netdev_priv(dev);
+
info->so_timestamping =
SOF_TIMESTAMPING_TX_HARDWARE |
SOF_TIMESTAMPING_RX_HARDWARE |
- SOF_TIMESTAMPING_SYS_HARDWARE;
- info->phc_index = -1;
+ SOF_TIMESTAMPING_RAW_HARDWARE;
+ info->phc_index = lp->phc_index;
info->tx_types =
(1 << HWTSTAMP_TX_OFF) |
(1 << HWTSTAMP_TX_ON);
(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT);
return 0;
}
+#endif
static const struct ethtool_ops bfin_mac_ethtool_ops = {
.get_settings = bfin_mac_ethtool_getsettings,
.get_drvinfo = bfin_mac_ethtool_getdrvinfo,
.get_wol = bfin_mac_ethtool_getwol,
.set_wol = bfin_mac_ethtool_setwol,
+#ifdef CONFIG_BFIN_MAC_USE_HWSTAMP
.get_ts_info = bfin_mac_ethtool_get_ts_info,
+#endif
};
/**************************************************************************/
#ifdef CONFIG_BFIN_MAC_USE_HWSTAMP
#define bfin_mac_hwtstamp_is_none(cfg) ((cfg) == HWTSTAMP_FILTER_NONE)
+static u32 bfin_select_phc_clock(u32 input_clk, unsigned int *shift_result)
+{
+ u32 ipn = 1000000000UL / input_clk;
+ u32 ppn = 1;
+ unsigned int shift = 0;
+
+ while (ppn <= ipn) {
+ ppn <<= 1;
+ shift++;
+ }
+ *shift_result = shift;
+ return 1000000000UL / ppn;
+}
+
static int bfin_mac_hwtstamp_ioctl(struct net_device *netdev,
struct ifreq *ifr, int cmd)
{
bfin_read_EMAC_PTP_TXSNAPLO();
bfin_read_EMAC_PTP_TXSNAPHI();
- /*
- * Set registers so that rollover occurs soon to test this.
- */
- bfin_write_EMAC_PTP_TIMELO(0x00000000);
- bfin_write_EMAC_PTP_TIMEHI(0xFF800000);
-
SSYNC();
-
- lp->compare.last_update = 0;
- timecounter_init(&lp->clock,
- &lp->cycles,
- ktime_to_ns(ktime_get_real()));
- timecompare_update(&lp->compare, 0);
}
lp->stamp_cfg = config;
-EFAULT : 0;
}
-static void bfin_dump_hwtamp(char *s, ktime_t *hw, ktime_t *ts, struct timecompare *cmp)
-{
- ktime_t sys = ktime_get_real();
-
- pr_debug("%s %s hardware:%d,%d transform system:%d,%d system:%d,%d, cmp:%lld, %lld\n",
- __func__, s, hw->tv.sec, hw->tv.nsec, ts->tv.sec, ts->tv.nsec, sys.tv.sec,
- sys.tv.nsec, cmp->offset, cmp->skew);
-}
-
static void bfin_tx_hwtstamp(struct net_device *netdev, struct sk_buff *skb)
{
struct bfin_mac_local *lp = netdev_priv(netdev);
regval = bfin_read_EMAC_PTP_TXSNAPLO();
regval |= (u64)bfin_read_EMAC_PTP_TXSNAPHI() << 32;
memset(&shhwtstamps, 0, sizeof(shhwtstamps));
- ns = timecounter_cyc2time(&lp->clock,
- regval);
- timecompare_update(&lp->compare, ns);
+ ns = regval << lp->shift;
shhwtstamps.hwtstamp = ns_to_ktime(ns);
- shhwtstamps.syststamp =
- timecompare_transform(&lp->compare, ns);
skb_tstamp_tx(skb, &shhwtstamps);
-
- bfin_dump_hwtamp("TX", &shhwtstamps.hwtstamp, &shhwtstamps.syststamp, &lp->compare);
}
}
}
regval = bfin_read_EMAC_PTP_RXSNAPLO();
regval |= (u64)bfin_read_EMAC_PTP_RXSNAPHI() << 32;
- ns = timecounter_cyc2time(&lp->clock, regval);
- timecompare_update(&lp->compare, ns);
+ ns = regval << lp->shift;
memset(shhwtstamps, 0, sizeof(*shhwtstamps));
shhwtstamps->hwtstamp = ns_to_ktime(ns);
- shhwtstamps->syststamp = timecompare_transform(&lp->compare, ns);
+}
+
+static void bfin_mac_hwtstamp_init(struct net_device *netdev)
+{
+ struct bfin_mac_local *lp = netdev_priv(netdev);
+ u64 addend, ppb;
+ u32 input_clk, phc_clk;
+
+ /* Initialize hardware timer */
+ input_clk = get_sclk();
+ phc_clk = bfin_select_phc_clock(input_clk, &lp->shift);
+ addend = phc_clk * (1ULL << 32);
+ do_div(addend, input_clk);
+ bfin_write_EMAC_PTP_ADDEND((u32)addend);
+
+ lp->addend = addend;
+ ppb = 1000000000ULL * input_clk;
+ do_div(ppb, phc_clk);
+ lp->max_ppb = ppb - 1000000000ULL - 1ULL;
- bfin_dump_hwtamp("RX", &shhwtstamps->hwtstamp, &shhwtstamps->syststamp, &lp->compare);
+ /* Initialize hwstamp config */
+ lp->stamp_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
+ lp->stamp_cfg.tx_type = HWTSTAMP_TX_OFF;
}
-/*
- * bfin_read_clock - read raw cycle counter (to be used by time counter)
- */
-static cycle_t bfin_read_clock(const struct cyclecounter *tc)
+static u64 bfin_ptp_time_read(struct bfin_mac_local *lp)
{
- u64 stamp;
+ u64 ns;
+ u32 lo, hi;
+
+ lo = bfin_read_EMAC_PTP_TIMELO();
+ hi = bfin_read_EMAC_PTP_TIMEHI();
- stamp = bfin_read_EMAC_PTP_TIMELO();
- stamp |= (u64)bfin_read_EMAC_PTP_TIMEHI() << 32ULL;
+ ns = ((u64) hi) << 32;
+ ns |= lo;
+ ns <<= lp->shift;
- return stamp;
+ return ns;
}
-#define PTP_CLK 25000000
+static void bfin_ptp_time_write(struct bfin_mac_local *lp, u64 ns)
+{
+ u32 hi, lo;
-static void bfin_mac_hwtstamp_init(struct net_device *netdev)
+ ns >>= lp->shift;
+ hi = ns >> 32;
+ lo = ns & 0xffffffff;
+
+ bfin_write_EMAC_PTP_TIMELO(lo);
+ bfin_write_EMAC_PTP_TIMEHI(hi);
+}
+
+/* PTP Hardware Clock operations */
+
+static int bfin_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+ u64 adj;
+ u32 diff, addend;
+ int neg_adj = 0;
+ struct bfin_mac_local *lp =
+ container_of(ptp, struct bfin_mac_local, caps);
+
+ if (ppb < 0) {
+ neg_adj = 1;
+ ppb = -ppb;
+ }
+ addend = lp->addend;
+ adj = addend;
+ adj *= ppb;
+ diff = div_u64(adj, 1000000000ULL);
+
+ addend = neg_adj ? addend - diff : addend + diff;
+
+ bfin_write_EMAC_PTP_ADDEND(addend);
+
+ return 0;
+}
+
+static int bfin_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ s64 now;
+ unsigned long flags;
+ struct bfin_mac_local *lp =
+ container_of(ptp, struct bfin_mac_local, caps);
+
+ spin_lock_irqsave(&lp->phc_lock, flags);
+
+ now = bfin_ptp_time_read(lp);
+ now += delta;
+ bfin_ptp_time_write(lp, now);
+
+ spin_unlock_irqrestore(&lp->phc_lock, flags);
+
+ return 0;
+}
+
+static int bfin_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+ u64 ns;
+ u32 remainder;
+ unsigned long flags;
+ struct bfin_mac_local *lp =
+ container_of(ptp, struct bfin_mac_local, caps);
+
+ spin_lock_irqsave(&lp->phc_lock, flags);
+
+ ns = bfin_ptp_time_read(lp);
+
+ spin_unlock_irqrestore(&lp->phc_lock, flags);
+
+ ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
+ ts->tv_nsec = remainder;
+ return 0;
+}
+
+static int bfin_ptp_settime(struct ptp_clock_info *ptp,
+ const struct timespec *ts)
+{
+ u64 ns;
+ unsigned long flags;
+ struct bfin_mac_local *lp =
+ container_of(ptp, struct bfin_mac_local, caps);
+
+ ns = ts->tv_sec * 1000000000ULL;
+ ns += ts->tv_nsec;
+
+ spin_lock_irqsave(&lp->phc_lock, flags);
+
+ bfin_ptp_time_write(lp, ns);
+
+ spin_unlock_irqrestore(&lp->phc_lock, flags);
+
+ return 0;
+}
+
+static int bfin_ptp_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info bfin_ptp_caps = {
+ .owner = THIS_MODULE,
+ .name = "BF518 clock",
+ .max_adj = 0,
+ .n_alarm = 0,
+ .n_ext_ts = 0,
+ .n_per_out = 0,
+ .pps = 0,
+ .adjfreq = bfin_ptp_adjfreq,
+ .adjtime = bfin_ptp_adjtime,
+ .gettime = bfin_ptp_gettime,
+ .settime = bfin_ptp_settime,
+ .enable = bfin_ptp_enable,
+};
+
+static int bfin_phc_init(struct net_device *netdev, struct device *dev)
{
struct bfin_mac_local *lp = netdev_priv(netdev);
- u64 append;
- /* Initialize hardware timer */
- append = PTP_CLK * (1ULL << 32);
- do_div(append, get_sclk());
- bfin_write_EMAC_PTP_ADDEND((u32)append);
-
- memset(&lp->cycles, 0, sizeof(lp->cycles));
- lp->cycles.read = bfin_read_clock;
- lp->cycles.mask = CLOCKSOURCE_MASK(64);
- lp->cycles.mult = 1000000000 / PTP_CLK;
- lp->cycles.shift = 0;
-
- /* Synchronize our NIC clock against system wall clock */
- memset(&lp->compare, 0, sizeof(lp->compare));
- lp->compare.source = &lp->clock;
- lp->compare.target = ktime_get_real;
- lp->compare.num_samples = 10;
+ lp->caps = bfin_ptp_caps;
+ lp->caps.max_adj = lp->max_ppb;
+ lp->clock = ptp_clock_register(&lp->caps, dev);
+ if (IS_ERR(lp->clock))
+ return PTR_ERR(lp->clock);
- /* Initialize hwstamp config */
- lp->stamp_cfg.rx_filter = HWTSTAMP_FILTER_NONE;
- lp->stamp_cfg.tx_type = HWTSTAMP_TX_OFF;
+ lp->phc_index = ptp_clock_index(lp->clock);
+ spin_lock_init(&lp->phc_lock);
+
+ return 0;
+}
+
+static void bfin_phc_release(struct bfin_mac_local *lp)
+{
+ ptp_clock_unregister(lp->clock);
}
#else
# define bfin_mac_hwtstamp_ioctl(dev, ifr, cmd) (-EOPNOTSUPP)
# define bfin_rx_hwtstamp(dev, skb)
# define bfin_tx_hwtstamp(dev, skb)
+# define bfin_phc_init(netdev, dev) 0
+# define bfin_phc_release(lp)
#endif
static inline void _tx_reclaim_skb(void)
}
bfin_mac_hwtstamp_init(ndev);
+ if (bfin_phc_init(ndev, &pdev->dev)) {
+ dev_err(&pdev->dev, "Cannot register PHC device!\n");
+ goto out_err_phc;
+ }
/* now, print out the card info, in a short format.. */
netdev_info(ndev, "%s, Version %s\n", DRV_DESC, DRV_VERSION);
return 0;
+out_err_phc:
out_err_reg_ndev:
free_irq(IRQ_MAC_RX, ndev);
out_err_request_irq:
struct net_device *ndev = platform_get_drvdata(pdev);
struct bfin_mac_local *lp = netdev_priv(ndev);
+ bfin_phc_release(lp);
+
platform_set_drvdata(pdev, NULL);
lp->mii_bus->priv = NULL;
#define _BFIN_MAC_H_
#include <linux/net_tstamp.h>
-#include <linux/clocksource.h>
-#include <linux/timecompare.h>
+#include <linux/ptp_clock_kernel.h>
#include <linux/timer.h>
#include <linux/etherdevice.h>
#include <linux/bfin_mac.h>
struct mii_bus *mii_bus;
#if defined(CONFIG_BFIN_MAC_USE_HWSTAMP)
- struct cyclecounter cycles;
- struct timecounter clock;
- struct timecompare compare;
+ u32 addend;
+ unsigned int shift;
+ s32 max_ppb;
struct hwtstamp_config stamp_cfg;
+ struct ptp_clock_info caps;
+ struct ptp_clock *clock;
+ int phc_index;
+ spinlock_t phc_lock; /* protects time lo/hi registers */
#endif
};
int i;
lp->rx_ring = dma_alloc_coherent(&lp->pdev->dev,
- MAX_RX_DESCR * sizeof(struct dma_desc),
+ MAX_RX_DESCR * sizeof(struct macb_dma_desc),
&lp->rx_ring_dma, GFP_KERNEL);
if (!lp->rx_ring) {
netdev_err(lp->dev, "unable to alloc rx ring DMA buffer\n");
netdev_err(lp->dev, "unable to alloc rx data DMA buffer\n");
dma_free_coherent(&lp->pdev->dev,
- MAX_RX_DESCR * sizeof(struct dma_desc),
+ MAX_RX_DESCR * sizeof(struct macb_dma_desc),
lp->rx_ring, lp->rx_ring_dma);
lp->rx_ring = NULL;
return -ENOMEM;
netif_stop_queue(dev);
dma_free_coherent(&lp->pdev->dev,
- MAX_RX_DESCR * sizeof(struct dma_desc),
+ MAX_RX_DESCR * sizeof(struct macb_dma_desc),
lp->rx_ring, lp->rx_ring_dma);
lp->rx_ring = NULL;
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_net.h>
+#include <linux/pinctrl/consumer.h>
#include "macb.h"
#define RX_BUFFER_SIZE 128
-#define RX_RING_SIZE 512
-#define RX_RING_BYTES (sizeof(struct dma_desc) * RX_RING_SIZE)
+#define RX_RING_SIZE 512 /* must be power of 2 */
+#define RX_RING_BYTES (sizeof(struct macb_dma_desc) * RX_RING_SIZE)
-/* Make the IP header word-aligned (the ethernet header is 14 bytes) */
-#define RX_OFFSET 2
-
-#define TX_RING_SIZE 128
-#define DEF_TX_RING_PENDING (TX_RING_SIZE - 1)
-#define TX_RING_BYTES (sizeof(struct dma_desc) * TX_RING_SIZE)
-
-#define TX_RING_GAP(bp) \
- (TX_RING_SIZE - (bp)->tx_pending)
-#define TX_BUFFS_AVAIL(bp) \
- (((bp)->tx_tail <= (bp)->tx_head) ? \
- (bp)->tx_tail + (bp)->tx_pending - (bp)->tx_head : \
- (bp)->tx_tail - (bp)->tx_head - TX_RING_GAP(bp))
-#define NEXT_TX(n) (((n) + 1) & (TX_RING_SIZE - 1))
-
-#define NEXT_RX(n) (((n) + 1) & (RX_RING_SIZE - 1))
+#define TX_RING_SIZE 128 /* must be power of 2 */
+#define TX_RING_BYTES (sizeof(struct macb_dma_desc) * TX_RING_SIZE)
/* minimum number of free TX descriptors before waking up TX process */
#define MACB_TX_WAKEUP_THRESH (TX_RING_SIZE / 4)
#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \
| MACB_BIT(ISR_ROVR))
+#define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \
+ | MACB_BIT(ISR_RLE) \
+ | MACB_BIT(TXERR))
+#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP))
+
+/*
+ * Graceful stop timeouts in us. We should allow up to
+ * 1 frame time (10 Mbits/s, full-duplex, ignoring collisions)
+ */
+#define MACB_HALT_TIMEOUT 1230
+
+/* Ring buffer accessors */
+static unsigned int macb_tx_ring_wrap(unsigned int index)
+{
+ return index & (TX_RING_SIZE - 1);
+}
+
+static unsigned int macb_tx_ring_avail(struct macb *bp)
+{
+ return (bp->tx_tail - bp->tx_head) & (TX_RING_SIZE - 1);
+}
+
+static struct macb_dma_desc *macb_tx_desc(struct macb *bp, unsigned int index)
+{
+ return &bp->tx_ring[macb_tx_ring_wrap(index)];
+}
+
+static struct macb_tx_skb *macb_tx_skb(struct macb *bp, unsigned int index)
+{
+ return &bp->tx_skb[macb_tx_ring_wrap(index)];
+}
+
+static dma_addr_t macb_tx_dma(struct macb *bp, unsigned int index)
+{
+ dma_addr_t offset;
+
+ offset = macb_tx_ring_wrap(index) * sizeof(struct macb_dma_desc);
+
+ return bp->tx_ring_dma + offset;
+}
+
+static unsigned int macb_rx_ring_wrap(unsigned int index)
+{
+ return index & (RX_RING_SIZE - 1);
+}
+
+static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
+{
+ return &bp->rx_ring[macb_rx_ring_wrap(index)];
+}
+
+static void *macb_rx_buffer(struct macb *bp, unsigned int index)
+{
+ return bp->rx_buffers + RX_BUFFER_SIZE * macb_rx_ring_wrap(index);
+}
static void __macb_set_hwaddr(struct macb *bp)
{
reg = macb_readl(bp, NCFGR);
reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
+ if (macb_is_gem(bp))
+ reg &= ~GEM_BIT(GBE);
if (phydev->duplex)
reg |= MACB_BIT(FD);
if (phydev->speed == SPEED_100)
reg |= MACB_BIT(SPD);
+ if (phydev->speed == SPEED_1000)
+ reg |= GEM_BIT(GBE);
- macb_writel(bp, NCFGR, reg);
+ macb_or_gem_writel(bp, NCFGR, reg);
bp->speed = phydev->speed;
bp->duplex = phydev->duplex;
}
/* mask with MAC supported features */
- phydev->supported &= PHY_BASIC_FEATURES;
+ if (macb_is_gem(bp))
+ phydev->supported &= PHY_GBIT_FEATURES;
+ else
+ phydev->supported &= PHY_BASIC_FEATURES;
phydev->advertising = phydev->supported;
*p += __raw_readl(reg);
}
-static void macb_tx(struct macb *bp)
+static int macb_halt_tx(struct macb *bp)
{
- unsigned int tail;
- unsigned int head;
- u32 status;
+ unsigned long halt_time, timeout;
+ u32 status;
- status = macb_readl(bp, TSR);
- macb_writel(bp, TSR, status);
+ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(THALT));
- netdev_dbg(bp->dev, "macb_tx status = %02lx\n", (unsigned long)status);
+ timeout = jiffies + usecs_to_jiffies(MACB_HALT_TIMEOUT);
+ do {
+ halt_time = jiffies;
+ status = macb_readl(bp, TSR);
+ if (!(status & MACB_BIT(TGO)))
+ return 0;
- if (status & (MACB_BIT(UND) | MACB_BIT(TSR_RLE))) {
- int i;
- netdev_err(bp->dev, "TX %s, resetting buffers\n",
- status & MACB_BIT(UND) ?
- "underrun" : "retry limit exceeded");
+ usleep_range(10, 250);
+ } while (time_before(halt_time, timeout));
- /* Transfer ongoing, disable transmitter, to avoid confusion */
- if (status & MACB_BIT(TGO))
- macb_writel(bp, NCR, macb_readl(bp, NCR) & ~MACB_BIT(TE));
+ return -ETIMEDOUT;
+}
- head = bp->tx_head;
+static void macb_tx_error_task(struct work_struct *work)
+{
+ struct macb *bp = container_of(work, struct macb, tx_error_task);
+ struct macb_tx_skb *tx_skb;
+ struct sk_buff *skb;
+ unsigned int tail;
- /*Mark all the buffer as used to avoid sending a lost buffer*/
- for (i = 0; i < TX_RING_SIZE; i++)
- bp->tx_ring[i].ctrl = MACB_BIT(TX_USED);
+ netdev_vdbg(bp->dev, "macb_tx_error_task: t = %u, h = %u\n",
+ bp->tx_tail, bp->tx_head);
- /* Add wrap bit */
- bp->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
+ /* Make sure nobody is trying to queue up new packets */
+ netif_stop_queue(bp->dev);
- /* free transmit buffer in upper layer*/
- for (tail = bp->tx_tail; tail != head; tail = NEXT_TX(tail)) {
- struct ring_info *rp = &bp->tx_skb[tail];
- struct sk_buff *skb = rp->skb;
+ /*
+ * Stop transmission now
+ * (in case we have just queued new packets)
+ */
+ if (macb_halt_tx(bp))
+ /* Just complain for now, reinitializing TX path can be good */
+ netdev_err(bp->dev, "BUG: halt tx timed out\n");
- BUG_ON(skb == NULL);
+ /* No need for the lock here as nobody will interrupt us anymore */
- rmb();
+ /*
+ * Treat frames in TX queue including the ones that caused the error.
+ * Free transmit buffers in upper layer.
+ */
+ for (tail = bp->tx_tail; tail != bp->tx_head; tail++) {
+ struct macb_dma_desc *desc;
+ u32 ctrl;
+
+ desc = macb_tx_desc(bp, tail);
+ ctrl = desc->ctrl;
+ tx_skb = macb_tx_skb(bp, tail);
+ skb = tx_skb->skb;
+
+ if (ctrl & MACB_BIT(TX_USED)) {
+ netdev_vdbg(bp->dev, "txerr skb %u (data %p) TX complete\n",
+ macb_tx_ring_wrap(tail), skb->data);
+ bp->stats.tx_packets++;
+ bp->stats.tx_bytes += skb->len;
+ } else {
+ /*
+ * "Buffers exhausted mid-frame" errors may only happen
+ * if the driver is buggy, so complain loudly about those.
+ * Statistics are updated by hardware.
+ */
+ if (ctrl & MACB_BIT(TX_BUF_EXHAUSTED))
+ netdev_err(bp->dev,
+ "BUG: TX buffers exhausted mid-frame\n");
- dma_unmap_single(&bp->pdev->dev, rp->mapping, skb->len,
- DMA_TO_DEVICE);
- rp->skb = NULL;
- dev_kfree_skb_irq(skb);
+ desc->ctrl = ctrl | MACB_BIT(TX_USED);
}
- bp->tx_head = bp->tx_tail = 0;
-
- /* Enable the transmitter again */
- if (status & MACB_BIT(TGO))
- macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TE));
+ dma_unmap_single(&bp->pdev->dev, tx_skb->mapping, skb->len,
+ DMA_TO_DEVICE);
+ tx_skb->skb = NULL;
+ dev_kfree_skb(skb);
}
- if (!(status & MACB_BIT(COMP)))
- /*
- * This may happen when a buffer becomes complete
- * between reading the ISR and scanning the
- * descriptors. Nothing to worry about.
- */
- return;
+ /* Make descriptor updates visible to hardware */
+ wmb();
+
+ /* Reinitialize the TX desc queue */
+ macb_writel(bp, TBQP, bp->tx_ring_dma);
+ /* Make TX ring reflect state of hardware */
+ bp->tx_head = bp->tx_tail = 0;
+
+ /* Now we are ready to start transmission again */
+ netif_wake_queue(bp->dev);
+
+ /* Housework before enabling TX IRQ */
+ macb_writel(bp, TSR, macb_readl(bp, TSR));
+ macb_writel(bp, IER, MACB_TX_INT_FLAGS);
+}
+
+static void macb_tx_interrupt(struct macb *bp)
+{
+ unsigned int tail;
+ unsigned int head;
+ u32 status;
+
+ status = macb_readl(bp, TSR);
+ macb_writel(bp, TSR, status);
+
+ netdev_vdbg(bp->dev, "macb_tx_interrupt status = 0x%03lx\n",
+ (unsigned long)status);
head = bp->tx_head;
- for (tail = bp->tx_tail; tail != head; tail = NEXT_TX(tail)) {
- struct ring_info *rp = &bp->tx_skb[tail];
- struct sk_buff *skb = rp->skb;
- u32 bufstat;
+ for (tail = bp->tx_tail; tail != head; tail++) {
+ struct macb_tx_skb *tx_skb;
+ struct sk_buff *skb;
+ struct macb_dma_desc *desc;
+ u32 ctrl;
- BUG_ON(skb == NULL);
+ desc = macb_tx_desc(bp, tail);
+ /* Make hw descriptor updates visible to CPU */
rmb();
- bufstat = bp->tx_ring[tail].ctrl;
- if (!(bufstat & MACB_BIT(TX_USED)))
+ ctrl = desc->ctrl;
+
+ if (!(ctrl & MACB_BIT(TX_USED)))
break;
- netdev_dbg(bp->dev, "skb %u (data %p) TX complete\n",
- tail, skb->data);
- dma_unmap_single(&bp->pdev->dev, rp->mapping, skb->len,
+ tx_skb = macb_tx_skb(bp, tail);
+ skb = tx_skb->skb;
+
+ netdev_vdbg(bp->dev, "skb %u (data %p) TX complete\n",
+ macb_tx_ring_wrap(tail), skb->data);
+ dma_unmap_single(&bp->pdev->dev, tx_skb->mapping, skb->len,
DMA_TO_DEVICE);
bp->stats.tx_packets++;
bp->stats.tx_bytes += skb->len;
- rp->skb = NULL;
+ tx_skb->skb = NULL;
dev_kfree_skb_irq(skb);
}
bp->tx_tail = tail;
- if (netif_queue_stopped(bp->dev) &&
- TX_BUFFS_AVAIL(bp) > MACB_TX_WAKEUP_THRESH)
+ if (netif_queue_stopped(bp->dev)
+ && macb_tx_ring_avail(bp) > MACB_TX_WAKEUP_THRESH)
netif_wake_queue(bp->dev);
}
{
unsigned int len;
unsigned int frag;
- unsigned int offset = 0;
+ unsigned int offset;
struct sk_buff *skb;
+ struct macb_dma_desc *desc;
- len = MACB_BFEXT(RX_FRMLEN, bp->rx_ring[last_frag].ctrl);
+ desc = macb_rx_desc(bp, last_frag);
+ len = MACB_BFEXT(RX_FRMLEN, desc->ctrl);
- netdev_dbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
- first_frag, last_frag, len);
+ netdev_vdbg(bp->dev, "macb_rx_frame frags %u - %u (len %u)\n",
+ macb_rx_ring_wrap(first_frag),
+ macb_rx_ring_wrap(last_frag), len);
- skb = netdev_alloc_skb(bp->dev, len + RX_OFFSET);
+ /*
+ * The ethernet header starts NET_IP_ALIGN bytes into the
+ * first buffer. Since the header is 14 bytes, this makes the
+ * payload word-aligned.
+ *
+ * Instead of calling skb_reserve(NET_IP_ALIGN), we just copy
+ * the two padding bytes into the skb so that we avoid hitting
+ * the slowpath in memcpy(), and pull them off afterwards.
+ */
+ skb = netdev_alloc_skb(bp->dev, len + NET_IP_ALIGN);
if (!skb) {
bp->stats.rx_dropped++;
- for (frag = first_frag; ; frag = NEXT_RX(frag)) {
- bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
+ for (frag = first_frag; ; frag++) {
+ desc = macb_rx_desc(bp, frag);
+ desc->addr &= ~MACB_BIT(RX_USED);
if (frag == last_frag)
break;
}
+
+ /* Make descriptor updates visible to hardware */
wmb();
+
return 1;
}
- skb_reserve(skb, RX_OFFSET);
+ offset = 0;
+ len += NET_IP_ALIGN;
skb_checksum_none_assert(skb);
skb_put(skb, len);
- for (frag = first_frag; ; frag = NEXT_RX(frag)) {
+ for (frag = first_frag; ; frag++) {
unsigned int frag_len = RX_BUFFER_SIZE;
if (offset + frag_len > len) {
frag_len = len - offset;
}
skb_copy_to_linear_data_offset(skb, offset,
- (bp->rx_buffers +
- (RX_BUFFER_SIZE * frag)),
- frag_len);
+ macb_rx_buffer(bp, frag), frag_len);
offset += RX_BUFFER_SIZE;
- bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
- wmb();
+ desc = macb_rx_desc(bp, frag);
+ desc->addr &= ~MACB_BIT(RX_USED);
if (frag == last_frag)
break;
}
+ /* Make descriptor updates visible to hardware */
+ wmb();
+
+ __skb_pull(skb, NET_IP_ALIGN);
skb->protocol = eth_type_trans(skb, bp->dev);
bp->stats.rx_packets++;
- bp->stats.rx_bytes += len;
- netdev_dbg(bp->dev, "received skb of length %u, csum: %08x\n",
+ bp->stats.rx_bytes += skb->len;
+ netdev_vdbg(bp->dev, "received skb of length %u, csum: %08x\n",
skb->len, skb->csum);
netif_receive_skb(skb);
{
unsigned int frag;
- for (frag = begin; frag != end; frag = NEXT_RX(frag))
- bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
+ for (frag = begin; frag != end; frag++) {
+ struct macb_dma_desc *desc = macb_rx_desc(bp, frag);
+ desc->addr &= ~MACB_BIT(RX_USED);
+ }
+
+ /* Make descriptor updates visible to hardware */
wmb();
/*
static int macb_rx(struct macb *bp, int budget)
{
int received = 0;
- unsigned int tail = bp->rx_tail;
+ unsigned int tail;
int first_frag = -1;
- for (; budget > 0; tail = NEXT_RX(tail)) {
+ for (tail = bp->rx_tail; budget > 0; tail++) {
+ struct macb_dma_desc *desc = macb_rx_desc(bp, tail);
u32 addr, ctrl;
+ /* Make hw descriptor updates visible to CPU */
rmb();
- addr = bp->rx_ring[tail].addr;
- ctrl = bp->rx_ring[tail].ctrl;
+
+ addr = desc->addr;
+ ctrl = desc->ctrl;
if (!(addr & MACB_BIT(RX_USED)))
break;
work_done = 0;
- netdev_dbg(bp->dev, "poll: status = %08lx, budget = %d\n",
+ netdev_vdbg(bp->dev, "poll: status = %08lx, budget = %d\n",
(unsigned long)status, budget);
work_done = macb_rx(bp, budget);
break;
}
+ netdev_vdbg(bp->dev, "isr = 0x%08lx\n", (unsigned long)status);
+
if (status & MACB_RX_INT_FLAGS) {
/*
* There's no point taking any more interrupts
macb_writel(bp, IDR, MACB_RX_INT_FLAGS);
if (napi_schedule_prep(&bp->napi)) {
- netdev_dbg(bp->dev, "scheduling RX softirq\n");
+ netdev_vdbg(bp->dev, "scheduling RX softirq\n");
__napi_schedule(&bp->napi);
}
}
- if (status & (MACB_BIT(TCOMP) | MACB_BIT(ISR_TUND) |
- MACB_BIT(ISR_RLE)))
- macb_tx(bp);
+ if (unlikely(status & (MACB_TX_ERR_FLAGS))) {
+ macb_writel(bp, IDR, MACB_TX_INT_FLAGS);
+ schedule_work(&bp->tx_error_task);
+ break;
+ }
+
+ if (status & MACB_BIT(TCOMP))
+ macb_tx_interrupt(bp);
/*
* Link change detection isn't possible with RMII, so we'll
struct macb *bp = netdev_priv(dev);
dma_addr_t mapping;
unsigned int len, entry;
+ struct macb_dma_desc *desc;
+ struct macb_tx_skb *tx_skb;
u32 ctrl;
unsigned long flags;
-#ifdef DEBUG
- netdev_dbg(bp->dev,
+#if defined(DEBUG) && defined(VERBOSE_DEBUG)
+ netdev_vdbg(bp->dev,
"start_xmit: len %u head %p data %p tail %p end %p\n",
skb->len, skb->head, skb->data,
skb_tail_pointer(skb), skb_end_pointer(skb));
spin_lock_irqsave(&bp->lock, flags);
/* This is a hard error, log it. */
- if (TX_BUFFS_AVAIL(bp) < 1) {
+ if (macb_tx_ring_avail(bp) < 1) {
netif_stop_queue(dev);
spin_unlock_irqrestore(&bp->lock, flags);
netdev_err(bp->dev, "BUG! Tx Ring full when queue awake!\n");
return NETDEV_TX_BUSY;
}
- entry = bp->tx_head;
- netdev_dbg(bp->dev, "Allocated ring entry %u\n", entry);
+ entry = macb_tx_ring_wrap(bp->tx_head);
+ bp->tx_head++;
+ netdev_vdbg(bp->dev, "Allocated ring entry %u\n", entry);
mapping = dma_map_single(&bp->pdev->dev, skb->data,
len, DMA_TO_DEVICE);
- bp->tx_skb[entry].skb = skb;
- bp->tx_skb[entry].mapping = mapping;
- netdev_dbg(bp->dev, "Mapped skb data %p to DMA addr %08lx\n",
+
+ tx_skb = &bp->tx_skb[entry];
+ tx_skb->skb = skb;
+ tx_skb->mapping = mapping;
+ netdev_vdbg(bp->dev, "Mapped skb data %p to DMA addr %08lx\n",
skb->data, (unsigned long)mapping);
ctrl = MACB_BF(TX_FRMLEN, len);
if (entry == (TX_RING_SIZE - 1))
ctrl |= MACB_BIT(TX_WRAP);
- bp->tx_ring[entry].addr = mapping;
- bp->tx_ring[entry].ctrl = ctrl;
- wmb();
+ desc = &bp->tx_ring[entry];
+ desc->addr = mapping;
+ desc->ctrl = ctrl;
- entry = NEXT_TX(entry);
- bp->tx_head = entry;
+ /* Make newly initialized descriptor visible to hardware */
+ wmb();
skb_tx_timestamp(skb);
macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
- if (TX_BUFFS_AVAIL(bp) < 1)
+ if (macb_tx_ring_avail(bp) < 1)
netif_stop_queue(dev);
spin_unlock_irqrestore(&bp->lock, flags);
{
int size;
- size = TX_RING_SIZE * sizeof(struct ring_info);
+ size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
bp->tx_skb = kmalloc(size, GFP_KERNEL);
if (!bp->tx_skb)
goto out_err;
static void macb_reset_hw(struct macb *bp)
{
- /* Make sure we have the write buffer for ourselves */
- wmb();
-
/*
* Disable RX and TX (XXX: Should we halt the transmission
* more gracefully?)
__macb_set_hwaddr(bp);
config = macb_mdc_clk_div(bp);
+ config |= MACB_BF(RBOF, NET_IP_ALIGN); /* Make eth data aligned */
config |= MACB_BIT(PAE); /* PAuse Enable */
config |= MACB_BIT(DRFCS); /* Discard Rx FCS */
config |= MACB_BIT(BIG); /* Receive oversized frames */
macb_writel(bp, NCR, MACB_BIT(RE) | MACB_BIT(TE) | MACB_BIT(MPE));
/* Enable interrupts */
- macb_writel(bp, IER, (MACB_BIT(RCOMP)
- | MACB_BIT(RXUBR)
- | MACB_BIT(ISR_TUND)
- | MACB_BIT(ISR_RLE)
- | MACB_BIT(TXERR)
- | MACB_BIT(TCOMP)
- | MACB_BIT(ISR_ROVR)
+ macb_writel(bp, IER, (MACB_RX_INT_FLAGS
+ | MACB_TX_INT_FLAGS
| MACB_BIT(HRESP)));
}
return phy_ethtool_sset(phydev, cmd);
}
-static void macb_get_drvinfo(struct net_device *dev,
- struct ethtool_drvinfo *info)
+static int macb_get_regs_len(struct net_device *netdev)
+{
+ return MACB_GREGS_NBR * sizeof(u32);
+}
+
+static void macb_get_regs(struct net_device *dev, struct ethtool_regs *regs,
+ void *p)
{
struct macb *bp = netdev_priv(dev);
+ unsigned int tail, head;
+ u32 *regs_buff = p;
+
+ regs->version = (macb_readl(bp, MID) & ((1 << MACB_REV_SIZE) - 1))
+ | MACB_GREGS_VERSION;
+
+ tail = macb_tx_ring_wrap(bp->tx_tail);
+ head = macb_tx_ring_wrap(bp->tx_head);
+
+ regs_buff[0] = macb_readl(bp, NCR);
+ regs_buff[1] = macb_or_gem_readl(bp, NCFGR);
+ regs_buff[2] = macb_readl(bp, NSR);
+ regs_buff[3] = macb_readl(bp, TSR);
+ regs_buff[4] = macb_readl(bp, RBQP);
+ regs_buff[5] = macb_readl(bp, TBQP);
+ regs_buff[6] = macb_readl(bp, RSR);
+ regs_buff[7] = macb_readl(bp, IMR);
+
+ regs_buff[8] = tail;
+ regs_buff[9] = head;
+ regs_buff[10] = macb_tx_dma(bp, tail);
+ regs_buff[11] = macb_tx_dma(bp, head);
- strcpy(info->driver, bp->pdev->dev.driver->name);
- strcpy(info->version, "$Revision: 1.14 $");
- strcpy(info->bus_info, dev_name(&bp->pdev->dev));
+ if (macb_is_gem(bp)) {
+ regs_buff[12] = gem_readl(bp, USRIO);
+ regs_buff[13] = gem_readl(bp, DMACFG);
+ }
}
const struct ethtool_ops macb_ethtool_ops = {
.get_settings = macb_get_settings,
.set_settings = macb_set_settings,
- .get_drvinfo = macb_get_drvinfo,
+ .get_regs_len = macb_get_regs_len,
+ .get_regs = macb_get_regs,
.get_link = ethtool_op_get_link,
.get_ts_info = ethtool_op_get_ts_info,
};
struct phy_device *phydev;
u32 config;
int err = -ENXIO;
+ struct pinctrl *pinctrl;
regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!regs) {
goto err_out;
}
+ pinctrl = devm_pinctrl_get_select_default(&pdev->dev);
+ if (IS_ERR(pinctrl)) {
+ err = PTR_ERR(pinctrl);
+ if (err == -EPROBE_DEFER)
+ goto err_out;
+
+ dev_warn(&pdev->dev, "No pinctrl provided\n");
+ }
+
err = -ENOMEM;
dev = alloc_etherdev(sizeof(*bp));
if (!dev)
bp->dev = dev;
spin_lock_init(&bp->lock);
+ INIT_WORK(&bp->tx_error_task, macb_tx_error_task);
bp->pclk = clk_get(&pdev->dev, "pclk");
if (IS_ERR(bp->pclk)) {
bp->phy_interface = err;
}
- if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
+ if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII)
+ macb_or_gem_writel(bp, USRIO, GEM_BIT(RGMII));
+ else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
#if defined(CONFIG_ARCH_AT91)
macb_or_gem_writel(bp, USRIO, (MACB_BIT(RMII) |
MACB_BIT(CLKEN)));
macb_or_gem_writel(bp, USRIO, MACB_BIT(MII));
#endif
- bp->tx_pending = DEF_TX_RING_PENDING;
-
err = register_netdev(dev);
if (err) {
dev_err(&pdev->dev, "Cannot register net device, aborting.\n");
#ifndef _MACB_H
#define _MACB_H
+#define MACB_GREGS_NBR 16
+#define MACB_GREGS_VERSION 1
+
/* MACB register offsets */
#define MACB_NCR 0x0000
#define MACB_NCFGR 0x0004
#define MACB_IRXFCS_SIZE 1
/* GEM specific NCFGR bitfields. */
+#define GEM_GBE_OFFSET 10
+#define GEM_GBE_SIZE 1
#define GEM_CLK_OFFSET 18
#define GEM_CLK_SIZE 3
#define GEM_DBW_OFFSET 21
/* Bitfields in USRIO (AT91) */
#define MACB_RMII_OFFSET 0
#define MACB_RMII_SIZE 1
+#define GEM_RGMII_OFFSET 0 /* GEM gigabit mode */
+#define GEM_RGMII_SIZE 1
#define MACB_CLKEN_OFFSET 1
#define MACB_CLKEN_SIZE 1
__v; \
})
-struct dma_desc {
+/**
+ * struct macb_dma_desc - Hardware DMA descriptor
+ * @addr: DMA address of data buffer
+ * @ctrl: Control and status bits
+ */
+struct macb_dma_desc {
u32 addr;
u32 ctrl;
};
#define MACB_TX_USED_OFFSET 31
#define MACB_TX_USED_SIZE 1
-struct ring_info {
+/**
+ * struct macb_tx_skb - data about an skb which is being transmitted
+ * @skb: skb currently being transmitted
+ * @mapping: DMA address of the skb's data buffer
+ */
+struct macb_tx_skb {
struct sk_buff *skb;
dma_addr_t mapping;
};
void __iomem *regs;
unsigned int rx_tail;
- struct dma_desc *rx_ring;
+ struct macb_dma_desc *rx_ring;
void *rx_buffers;
unsigned int tx_head, tx_tail;
- struct dma_desc *tx_ring;
- struct ring_info *tx_skb;
+ struct macb_dma_desc *tx_ring;
+ struct macb_tx_skb *tx_skb;
spinlock_t lock;
struct platform_device *pdev;
struct clk *hclk;
struct net_device *dev;
struct napi_struct napi;
+ struct work_struct tx_error_task;
struct net_device_stats stats;
union {
struct macb_stats macb;
dma_addr_t tx_ring_dma;
dma_addr_t rx_buffers_dma;
- unsigned int rx_pending, tx_pending;
-
struct mii_bus *mii_bus;
struct phy_device *phy_dev;
unsigned int link;
This driver supports the Gigabit TSEC on the MPC83xx, MPC85xx,
and MPC86xx family of chips, and the FEC on the 8540.
+config FEC_PTP
+ bool "PTP Hardware Clock (PHC)"
+ depends on FEC
+ select PPS
+ select PTP_1588_CLOCK
+ --help---
+ Say Y here if you want to use PTP Hardware Clock (PHC) in the
+ driver. Only the basic clock operations have been implemented.
+
endif # NET_VENDOR_FREESCALE
#
obj-$(CONFIG_FEC) += fec.o
+obj-$(CONFIG_FEC_PTP) += fec_ptp.o
obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx.o
ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y)
obj-$(CONFIG_FEC_MPC52xx) += fec_mpc52xx_phy.o
#endif
#endif /* CONFIG_M5272 */
-/* The number of Tx and Rx buffers. These are allocated from the page
- * pool. The code may assume these are power of two, so it it best
- * to keep them that size.
- * We don't need to allocate pages for the transmitter. We just use
- * the skbuffer directly.
- */
-#define FEC_ENET_RX_PAGES 8
-#define FEC_ENET_RX_FRSIZE 2048
-#define FEC_ENET_RX_FRPPG (PAGE_SIZE / FEC_ENET_RX_FRSIZE)
-#define RX_RING_SIZE (FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
-#define FEC_ENET_TX_FRSIZE 2048
-#define FEC_ENET_TX_FRPPG (PAGE_SIZE / FEC_ENET_TX_FRSIZE)
-#define TX_RING_SIZE 16 /* Must be power of two */
-#define TX_RING_MOD_MASK 15 /* for this to work */
-
#if (((RX_RING_SIZE + TX_RING_SIZE) * 8) > PAGE_SIZE)
#error "FEC: descriptor ring size constants too large"
#endif
#define PKT_MINBUF_SIZE 64
#define PKT_MAXBLR_SIZE 1520
-/* This device has up to three irqs on some platforms */
-#define FEC_IRQ_NUM 3
-
/*
* 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
#define OPT_FRAME_SIZE 0
#endif
-/* The FEC buffer descriptors track the ring buffers. The rx_bd_base and
- * tx_bd_base always point to the base of the buffer descriptors. The
- * cur_rx and cur_tx point to the currently available buffer.
- * The dirty_tx tracks the current buffer that is being sent by the
- * controller. The cur_tx and dirty_tx are equal under both completely
- * empty and completely full conditions. The empty/ready indicator in
- * the buffer descriptor determines the actual condition.
- */
-struct fec_enet_private {
- /* Hardware registers of the FEC device */
- void __iomem *hwp;
-
- struct net_device *netdev;
-
- struct clk *clk_ipg;
- struct clk *clk_ahb;
-
- /* The saved address of a sent-in-place packet/buffer, for skfree(). */
- unsigned char *tx_bounce[TX_RING_SIZE];
- struct sk_buff* tx_skbuff[TX_RING_SIZE];
- struct sk_buff* rx_skbuff[RX_RING_SIZE];
- ushort skb_cur;
- ushort skb_dirty;
-
- /* CPM dual port RAM relative addresses */
- dma_addr_t bd_dma;
- /* Address of Rx and Tx buffers */
- struct bufdesc *rx_bd_base;
- struct bufdesc *tx_bd_base;
- /* The next free ring entry */
- struct bufdesc *cur_rx, *cur_tx;
- /* The ring entries to be free()ed */
- struct bufdesc *dirty_tx;
-
- uint tx_full;
- /* hold while accessing the HW like ringbuffer for tx/rx but not MAC */
- spinlock_t hw_lock;
-
- struct platform_device *pdev;
-
- int opened;
- int dev_id;
-
- /* Phylib and MDIO interface */
- struct mii_bus *mii_bus;
- struct phy_device *phy_dev;
- int mii_timeout;
- uint phy_speed;
- phy_interface_t phy_interface;
- int link;
- int full_duplex;
- struct completion mdio_done;
- int irq[FEC_IRQ_NUM];
-};
-
/* FEC MII MMFR bits definition */
#define FEC_MMFR_ST (1 << 30)
#define FEC_MMFR_OP_READ (2 << 28)
| BD_ENET_TX_LAST | BD_ENET_TX_TC);
bdp->cbd_sc = status;
+#ifdef CONFIG_FEC_PTP
+ bdp->cbd_bdu = 0;
+ if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP &&
+ fep->hwts_tx_en)) {
+ bdp->cbd_esc = (BD_ENET_TX_TS | BD_ENET_TX_INT);
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+ } else {
+
+ bdp->cbd_esc = BD_ENET_TX_INT;
+ }
+#endif
/* Trigger transmission start */
writel(0, fep->hwp + FEC_X_DES_ACTIVE);
writel(1 << 8, fep->hwp + FEC_X_WMRK);
}
+#ifdef CONFIG_FEC_PTP
+ ecntl |= (1 << 4);
+#endif
+
/* And last, enable the transmit and receive processing */
writel(ecntl, fep->hwp + FEC_ECNTRL);
writel(0, fep->hwp + FEC_R_DES_ACTIVE);
+#ifdef CONFIG_FEC_PTP
+ fec_ptp_start_cyclecounter(ndev);
+#endif
/* Enable interrupts we wish to service */
writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
}
ndev->stats.tx_packets++;
}
+#ifdef CONFIG_FEC_PTP
+ if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS)) {
+ struct skb_shared_hwtstamps shhwtstamps;
+ unsigned long flags;
+
+ memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+ shhwtstamps.hwtstamp = ns_to_ktime(
+ timecounter_cyc2time(&fep->tc, bdp->ts));
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+ skb_tstamp_tx(skb, &shhwtstamps);
+ }
+#endif
if (status & BD_ENET_TX_READY)
printk("HEY! Enet xmit interrupt and TX_READY.\n");
skb_put(skb, pkt_len - 4); /* Make room */
skb_copy_to_linear_data(skb, data, pkt_len - 4);
skb->protocol = eth_type_trans(skb, ndev);
+#ifdef CONFIG_FEC_PTP
+ /* Get receive timestamp from the skb */
+ if (fep->hwts_rx_en) {
+ struct skb_shared_hwtstamps *shhwtstamps =
+ skb_hwtstamps(skb);
+ unsigned long flags;
+
+ memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+ shhwtstamps->hwtstamp = ns_to_ktime(
+ timecounter_cyc2time(&fep->tc, bdp->ts));
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+ }
+#endif
if (!skb_defer_rx_timestamp(skb))
netif_rx(skb);
}
status |= BD_ENET_RX_EMPTY;
bdp->cbd_sc = status;
+#ifdef CONFIG_FEC_PTP
+ bdp->cbd_esc = BD_ENET_RX_INT;
+ bdp->cbd_prot = 0;
+ bdp->cbd_bdu = 0;
+#endif
+
/* Update BD pointer to next entry */
if (status & BD_ENET_RX_WRAP)
bdp = fep->rx_bd_base;
if (!phydev)
return -ENODEV;
+#ifdef CONFIG_FEC_PTP
+ if (cmd == SIOCSHWTSTAMP)
+ return fec_ptp_ioctl(ndev, rq, cmd);
+#endif
return phy_mii_ioctl(phydev, rq, cmd);
}
bdp->cbd_bufaddr = dma_map_single(&fep->pdev->dev, skb->data,
FEC_ENET_RX_FRSIZE, DMA_FROM_DEVICE);
bdp->cbd_sc = BD_ENET_RX_EMPTY;
+#ifdef CONFIG_FEC_PTP
+ bdp->cbd_esc = BD_ENET_RX_INT;
+#endif
bdp++;
}
bdp->cbd_sc = 0;
bdp->cbd_bufaddr = 0;
+
+#ifdef CONFIG_FEC_PTP
+ bdp->cbd_esc = BD_ENET_RX_INT;
+#endif
bdp++;
}
goto failed_clk;
}
+#ifdef CONFIG_FEC_PTP
+ fep->clk_ptp = devm_clk_get(&pdev->dev, "ptp");
+ if (IS_ERR(fep->clk_ptp)) {
+ ret = PTR_ERR(fep->clk_ptp);
+ goto failed_clk;
+ }
+#endif
+
clk_prepare_enable(fep->clk_ahb);
clk_prepare_enable(fep->clk_ipg);
-
+#ifdef CONFIG_FEC_PTP
+ clk_prepare_enable(fep->clk_ptp);
+#endif
reg_phy = devm_regulator_get(&pdev->dev, "phy");
if (!IS_ERR(reg_phy)) {
ret = regulator_enable(reg_phy);
if (ret)
goto failed_register;
+#ifdef CONFIG_FEC_PTP
+ fec_ptp_init(ndev, pdev);
+#endif
+
return 0;
failed_register:
failed_regulator:
clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
+#ifdef CONFIG_FEC_PTP
+ clk_disable_unprepare(fep->clk_ptp);
+#endif
failed_pin:
failed_clk:
for (i = 0; i < FEC_IRQ_NUM; i++) {
if (irq > 0)
free_irq(irq, ndev);
}
+#ifdef CONFIG_FEC_PTP
+ del_timer_sync(&fep->time_keep);
+ clk_disable_unprepare(fep->clk_ptp);
+ if (fep->ptp_clock)
+ ptp_clock_unregister(fep->ptp_clock);
+#endif
clk_disable_unprepare(fep->clk_ahb);
clk_disable_unprepare(fep->clk_ipg);
iounmap(fep->hwp);
#define FEC_H
/****************************************************************************/
+#ifdef CONFIG_FEC_PTP
+#include <linux/clocksource.h>
+#include <linux/net_tstamp.h>
+#include <linux/ptp_clock_kernel.h>
+#endif
+
#if defined(CONFIG_M523x) || defined(CONFIG_M527x) || defined(CONFIG_M528x) || \
defined(CONFIG_M520x) || defined(CONFIG_M532x) || \
defined(CONFIG_ARCH_MXC) || defined(CONFIG_SOC_IMX28)
unsigned short cbd_datlen; /* Data length */
unsigned short cbd_sc; /* Control and status info */
unsigned long cbd_bufaddr; /* Buffer address */
+#ifdef CONFIG_FEC_PTP
+ unsigned long cbd_esc;
+ unsigned long cbd_prot;
+ unsigned long cbd_bdu;
+ unsigned long ts;
+ unsigned short res0[4];
+#endif
};
#else
struct bufdesc {
#define BD_ENET_TX_CSL ((ushort)0x0001)
#define BD_ENET_TX_STATS ((ushort)0x03ff) /* All status bits */
+/*enhanced buffer desciptor control/status used by Ethernet transmit*/
+#define BD_ENET_TX_INT 0x40000000
+#define BD_ENET_TX_TS 0x20000000
+
+
+/* This device has up to three irqs on some platforms */
+#define FEC_IRQ_NUM 3
+
+/* The number of Tx and Rx buffers. These are allocated from the page
+ * pool. The code may assume these are power of two, so it it best
+ * to keep them that size.
+ * We don't need to allocate pages for the transmitter. We just use
+ * the skbuffer directly.
+ */
+
+#define FEC_ENET_RX_PAGES 8
+#define FEC_ENET_RX_FRSIZE 2048
+#define FEC_ENET_RX_FRPPG (PAGE_SIZE / FEC_ENET_RX_FRSIZE)
+#define RX_RING_SIZE (FEC_ENET_RX_FRPPG * FEC_ENET_RX_PAGES)
+#define FEC_ENET_TX_FRSIZE 2048
+#define FEC_ENET_TX_FRPPG (PAGE_SIZE / FEC_ENET_TX_FRSIZE)
+#define TX_RING_SIZE 16 /* Must be power of two */
+#define TX_RING_MOD_MASK 15 /* for this to work */
+
+#define BD_ENET_RX_INT 0x00800000
+#define BD_ENET_RX_PTP ((ushort)0x0400)
+
+/* The FEC buffer descriptors track the ring buffers. The rx_bd_base and
+ * tx_bd_base always point to the base of the buffer descriptors. The
+ * cur_rx and cur_tx point to the currently available buffer.
+ * The dirty_tx tracks the current buffer that is being sent by the
+ * controller. The cur_tx and dirty_tx are equal under both completely
+ * empty and completely full conditions. The empty/ready indicator in
+ * the buffer descriptor determines the actual condition.
+ */
+struct fec_enet_private {
+ /* Hardware registers of the FEC device */
+ void __iomem *hwp;
+
+ struct net_device *netdev;
+
+ struct clk *clk_ipg;
+ struct clk *clk_ahb;
+#ifdef CONFIG_FEC_PTP
+ struct clk *clk_ptp;
+#endif
+
+ /* The saved address of a sent-in-place packet/buffer, for skfree(). */
+ unsigned char *tx_bounce[TX_RING_SIZE];
+ struct sk_buff *tx_skbuff[TX_RING_SIZE];
+ struct sk_buff *rx_skbuff[RX_RING_SIZE];
+ ushort skb_cur;
+ ushort skb_dirty;
+
+ /* CPM dual port RAM relative addresses */
+ dma_addr_t bd_dma;
+ /* Address of Rx and Tx buffers */
+ struct bufdesc *rx_bd_base;
+ struct bufdesc *tx_bd_base;
+ /* The next free ring entry */
+ struct bufdesc *cur_rx, *cur_tx;
+ /* The ring entries to be free()ed */
+ struct bufdesc *dirty_tx;
+
+ uint tx_full;
+ /* hold while accessing the HW like ringbuffer for tx/rx but not MAC */
+ spinlock_t hw_lock;
+
+ struct platform_device *pdev;
+
+ int opened;
+ int dev_id;
+
+ /* Phylib and MDIO interface */
+ struct mii_bus *mii_bus;
+ struct phy_device *phy_dev;
+ int mii_timeout;
+ uint phy_speed;
+ phy_interface_t phy_interface;
+ int link;
+ int full_duplex;
+ struct completion mdio_done;
+ int irq[FEC_IRQ_NUM];
+
+#ifdef CONFIG_FEC_PTP
+ struct ptp_clock *ptp_clock;
+ struct ptp_clock_info ptp_caps;
+ unsigned long last_overflow_check;
+ spinlock_t tmreg_lock;
+ struct cyclecounter cc;
+ struct timecounter tc;
+ int rx_hwtstamp_filter;
+ u32 base_incval;
+ u32 cycle_speed;
+ int hwts_rx_en;
+ int hwts_tx_en;
+ struct timer_list time_keep;
+#endif
+
+};
+
+#ifdef CONFIG_FEC_PTP
+void fec_ptp_init(struct net_device *ndev, struct platform_device *pdev);
+void fec_ptp_start_cyclecounter(struct net_device *ndev);
+int fec_ptp_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd);
+#endif
/****************************************************************************/
#endif /* FEC_H */
--- /dev/null
+/*
+ * Fast Ethernet Controller (ENET) PTP driver for MX6x.
+ *
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/ptrace.h>
+#include <linux/errno.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.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/phy.h>
+#include <linux/fec.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/of_net.h>
+
+#include "fec.h"
+
+/* FEC 1588 register bits */
+#define FEC_T_CTRL_SLAVE 0x00002000
+#define FEC_T_CTRL_CAPTURE 0x00000800
+#define FEC_T_CTRL_RESTART 0x00000200
+#define FEC_T_CTRL_PERIOD_RST 0x00000030
+#define FEC_T_CTRL_PERIOD_EN 0x00000010
+#define FEC_T_CTRL_ENABLE 0x00000001
+
+#define FEC_T_INC_MASK 0x0000007f
+#define FEC_T_INC_OFFSET 0
+#define FEC_T_INC_CORR_MASK 0x00007f00
+#define FEC_T_INC_CORR_OFFSET 8
+
+#define FEC_ATIME_CTRL 0x400
+#define FEC_ATIME 0x404
+#define FEC_ATIME_EVT_OFFSET 0x408
+#define FEC_ATIME_EVT_PERIOD 0x40c
+#define FEC_ATIME_CORR 0x410
+#define FEC_ATIME_INC 0x414
+#define FEC_TS_TIMESTAMP 0x418
+
+#define FEC_CC_MULT (1 << 31)
+/**
+ * fec_ptp_read - read raw cycle counter (to be used by time counter)
+ * @cc: the cyclecounter structure
+ *
+ * this function reads the cyclecounter registers and is called by the
+ * cyclecounter structure used to construct a ns counter from the
+ * arbitrary fixed point registers
+ */
+static cycle_t fec_ptp_read(const struct cyclecounter *cc)
+{
+ struct fec_enet_private *fep =
+ container_of(cc, struct fec_enet_private, cc);
+ u32 tempval;
+
+ tempval = readl(fep->hwp + FEC_ATIME_CTRL);
+ tempval |= FEC_T_CTRL_CAPTURE;
+ writel(tempval, fep->hwp + FEC_ATIME_CTRL);
+
+ return readl(fep->hwp + FEC_ATIME);
+}
+
+/**
+ * fec_ptp_start_cyclecounter - create the cycle counter from hw
+ * @ndev: network device
+ *
+ * this function initializes the timecounter and cyclecounter
+ * structures for use in generated a ns counter from the arbitrary
+ * fixed point cycles registers in the hardware.
+ */
+void fec_ptp_start_cyclecounter(struct net_device *ndev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+ unsigned long flags;
+ int inc;
+
+ inc = 1000000000 / clk_get_rate(fep->clk_ptp);
+
+ /* grab the ptp lock */
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+
+ /* 1ns counter */
+ writel(inc << FEC_T_INC_OFFSET, fep->hwp + FEC_ATIME_INC);
+
+ /* use free running count */
+ writel(0, fep->hwp + FEC_ATIME_EVT_PERIOD);
+
+ writel(FEC_T_CTRL_ENABLE, fep->hwp + FEC_ATIME_CTRL);
+
+ memset(&fep->cc, 0, sizeof(fep->cc));
+ fep->cc.read = fec_ptp_read;
+ fep->cc.mask = CLOCKSOURCE_MASK(32);
+ fep->cc.shift = 31;
+ fep->cc.mult = FEC_CC_MULT;
+
+ /* reset the ns time counter */
+ timecounter_init(&fep->tc, &fep->cc, ktime_to_ns(ktime_get_real()));
+
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+}
+
+/**
+ * fec_ptp_adjfreq - adjust ptp cycle frequency
+ * @ptp: the ptp clock structure
+ * @ppb: parts per billion adjustment from base
+ *
+ * Adjust the frequency of the ptp cycle counter by the
+ * indicated ppb from the base frequency.
+ *
+ * Because ENET hardware frequency adjust is complex,
+ * using software method to do that.
+ */
+static int fec_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+ u64 diff;
+ unsigned long flags;
+ int neg_adj = 0;
+
+ struct fec_enet_private *fep =
+ container_of(ptp, struct fec_enet_private, ptp_caps);
+
+ if (ppb < 0) {
+ ppb = -ppb;
+ neg_adj = 1;
+ }
+
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+ /*
+ * dummy read to set cycle_last in tc to now.
+ * So use adjusted mult to calculate when next call
+ * timercounter_read.
+ */
+ timecounter_read(&fep->tc);
+ fep->cc.mult = FEC_CC_MULT;
+ diff = fep->cc.mult;
+ diff *= ppb;
+ diff = div_u64(diff, 1000000000ULL);
+
+ if (neg_adj)
+ fep->cc.mult -= diff;
+ else
+ fep->cc.mult += diff;
+
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+
+ return 0;
+}
+
+/**
+ * fec_ptp_adjtime
+ * @ptp: the ptp clock structure
+ * @delta: offset to adjust the cycle counter by
+ *
+ * adjust the timer by resetting the timecounter structure.
+ */
+static int fec_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ struct fec_enet_private *fep =
+ container_of(ptp, struct fec_enet_private, ptp_caps);
+ unsigned long flags;
+ u64 now;
+
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+
+ now = timecounter_read(&fep->tc);
+ now += delta;
+
+ /* reset the timecounter */
+ timecounter_init(&fep->tc, &fep->cc, now);
+
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+
+ return 0;
+}
+
+/**
+ * fec_ptp_gettime
+ * @ptp: the ptp clock structure
+ * @ts: timespec structure to hold the current time value
+ *
+ * read the timecounter and return the correct value on ns,
+ * after converting it into a struct timespec.
+ */
+static int fec_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+ struct fec_enet_private *adapter =
+ container_of(ptp, struct fec_enet_private, ptp_caps);
+ u64 ns;
+ u32 remainder;
+ unsigned long flags;
+
+ spin_lock_irqsave(&adapter->tmreg_lock, flags);
+ ns = timecounter_read(&adapter->tc);
+ spin_unlock_irqrestore(&adapter->tmreg_lock, flags);
+
+ ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder);
+ ts->tv_nsec = remainder;
+
+ return 0;
+}
+
+/**
+ * fec_ptp_settime
+ * @ptp: the ptp clock structure
+ * @ts: the timespec containing the new time for the cycle counter
+ *
+ * reset the timecounter to use a new base value instead of the kernel
+ * wall timer value.
+ */
+static int fec_ptp_settime(struct ptp_clock_info *ptp,
+ const struct timespec *ts)
+{
+ struct fec_enet_private *fep =
+ container_of(ptp, struct fec_enet_private, ptp_caps);
+
+ u64 ns;
+ unsigned long flags;
+
+ ns = ts->tv_sec * 1000000000ULL;
+ ns += ts->tv_nsec;
+
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+ timecounter_init(&fep->tc, &fep->cc, ns);
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+ return 0;
+}
+
+/**
+ * fec_ptp_enable
+ * @ptp: the ptp clock structure
+ * @rq: the requested feature to change
+ * @on: whether to enable or disable the feature
+ *
+ */
+static int fec_ptp_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+/**
+ * fec_ptp_hwtstamp_ioctl - control hardware time stamping
+ * @ndev: pointer to net_device
+ * @ifreq: ioctl data
+ * @cmd: particular ioctl requested
+ */
+int fec_ptp_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ struct hwtstamp_config config;
+
+ if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ /* reserved for future extensions */
+ if (config.flags)
+ return -EINVAL;
+
+ switch (config.tx_type) {
+ case HWTSTAMP_TX_OFF:
+ fep->hwts_tx_en = 0;
+ break;
+ case HWTSTAMP_TX_ON:
+ fep->hwts_tx_en = 1;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ switch (config.rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ if (fep->hwts_rx_en)
+ fep->hwts_rx_en = 0;
+ config.rx_filter = HWTSTAMP_FILTER_NONE;
+ break;
+
+ default:
+ /*
+ * register RXMTRL must be set in order to do V1 packets,
+ * therefore it is not possible to time stamp both V1 Sync and
+ * Delay_Req messages and hardware does not support
+ * timestamping all packets => return error
+ */
+ fep->hwts_rx_en = 1;
+ config.rx_filter = HWTSTAMP_FILTER_ALL;
+ break;
+ }
+
+ return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ?
+ -EFAULT : 0;
+}
+
+/**
+ * fec_time_keep - call timecounter_read every second to avoid timer overrun
+ * because ENET just support 32bit counter, will timeout in 4s
+ */
+static void fec_time_keep(unsigned long _data)
+{
+ struct fec_enet_private *fep = (struct fec_enet_private *)_data;
+ u64 ns;
+ unsigned long flags;
+
+ spin_lock_irqsave(&fep->tmreg_lock, flags);
+ ns = timecounter_read(&fep->tc);
+ spin_unlock_irqrestore(&fep->tmreg_lock, flags);
+
+ mod_timer(&fep->time_keep, jiffies + HZ);
+}
+
+/**
+ * fec_ptp_init
+ * @ndev: The FEC network adapter
+ *
+ * This function performs the required steps for enabling ptp
+ * support. If ptp support has already been loaded it simply calls the
+ * cyclecounter init routine and exits.
+ */
+
+void fec_ptp_init(struct net_device *ndev, struct platform_device *pdev)
+{
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
+ fep->ptp_caps.owner = THIS_MODULE;
+ snprintf(fep->ptp_caps.name, 16, "fec ptp");
+
+ fep->ptp_caps.max_adj = 250000000;
+ fep->ptp_caps.n_alarm = 0;
+ fep->ptp_caps.n_ext_ts = 0;
+ fep->ptp_caps.n_per_out = 0;
+ fep->ptp_caps.pps = 0;
+ fep->ptp_caps.adjfreq = fec_ptp_adjfreq;
+ fep->ptp_caps.adjtime = fec_ptp_adjtime;
+ fep->ptp_caps.gettime = fec_ptp_gettime;
+ fep->ptp_caps.settime = fec_ptp_settime;
+ fep->ptp_caps.enable = fec_ptp_enable;
+
+ spin_lock_init(&fep->tmreg_lock);
+
+ fec_ptp_start_cyclecounter(ndev);
+
+ init_timer(&fep->time_keep);
+ fep->time_keep.data = (unsigned long)fep;
+ fep->time_keep.function = fec_time_keep;
+ fep->time_keep.expires = jiffies + HZ;
+ add_timer(&fep->time_keep);
+
+ fep->ptp_clock = ptp_clock_register(&fep->ptp_caps, &pdev->dev);
+ if (IS_ERR(fep->ptp_clock)) {
+ fep->ptp_clock = NULL;
+ pr_err("ptp_clock_register failed\n");
+ } else {
+ pr_info("registered PHC device on %s\n", ndev->name);
+ }
+}
config IGB
tristate "Intel(R) 82575/82576 PCI-Express Gigabit Ethernet support"
depends on PCI
+ select PTP_1588_CLOCK
---help---
This driver supports Intel(R) 82575/82576 gigabit ethernet family of
adapters. For more information on how to identify your adapter, go
driver. DCA is a method for warming the CPU cache before data
is used, with the intent of lessening the impact of cache misses.
-config IGB_PTP
- bool "PTP Hardware Clock (PHC)"
- default n
- depends on IGB && EXPERIMENTAL
- select PPS
- select PTP_1588_CLOCK
- ---help---
- Say Y here if you want to use PTP Hardware Clock (PHC) in the
- driver. Only the basic clock operations have been implemented.
-
- Every timestamp and clock read operations must consult the
- overflow counter to form a correct time value.
-
config IGBVF
tristate "Intel(R) 82576 Virtual Function Ethernet support"
depends on PCI
tristate "Intel(R) 10GbE PCI Express adapters support"
depends on PCI && INET
select MDIO
+ select PTP_1588_CLOCK
---help---
This driver supports Intel(R) 10GbE PCI Express family of
adapters. For more information on how to identify your adapter, go
If unsure, say N.
-config IXGBE_PTP
- bool "PTP Clock Support"
- default n
- depends on IXGBE && EXPERIMENTAL
- select PPS
- select PTP_1588_CLOCK
- ---help---
- Say Y here if you want support for 1588 Timestamping with a
- PHC device, using the PTP 1588 Clock support. This is
- required to enable timestamping support for the device.
-
- If unsure, say N.
-
config IXGBEVF
tristate "Intel(R) 82599 Virtual Function Ethernet support"
depends on PCI_MSI
igb-objs := igb_main.o igb_ethtool.o e1000_82575.o \
e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \
- e1000_i210.o
-
-igb-$(CONFIG_IGB_PTP) += igb_ptp.o
+ e1000_i210.o igb_ptp.o
#include "e1000_mac.h"
#include "e1000_82575.h"
-#ifdef CONFIG_IGB_PTP
#include <linux/clocksource.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
-#endif /* CONFIG_IGB_PTP */
#include <linux/bitops.h>
#include <linux/if_vlan.h>
u32 wvbr;
u32 *shadow_vfta;
-#ifdef CONFIG_IGB_PTP
struct ptp_clock *ptp_clock;
struct ptp_clock_info ptp_caps;
struct delayed_work ptp_overflow_work;
spinlock_t tmreg_lock;
struct cyclecounter cc;
struct timecounter tc;
-#endif /* CONFIG_IGB_PTP */
char fw_version[32];
};
extern void igb_set_ethtool_ops(struct net_device *);
extern void igb_power_up_link(struct igb_adapter *);
extern void igb_set_fw_version(struct igb_adapter *);
-#ifdef CONFIG_IGB_PTP
extern void igb_ptp_init(struct igb_adapter *adapter);
extern void igb_ptp_stop(struct igb_adapter *adapter);
extern void igb_ptp_reset(struct igb_adapter *adapter);
extern int igb_ptp_hwtstamp_ioctl(struct net_device *netdev,
struct ifreq *ifr, int cmd);
-#endif /* CONFIG_IGB_PTP */
static inline s32 igb_reset_phy(struct e1000_hw *hw)
{
struct igb_adapter *adapter = netdev_priv(dev);
switch (adapter->hw.mac.type) {
-#ifdef CONFIG_IGB_PTP
case e1000_82576:
case e1000_82580:
case e1000_i350:
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
return 0;
-#endif /* CONFIG_IGB_PTP */
default:
return -EOPNOTSUPP;
}
/* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */
wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE);
-#ifdef CONFIG_IGB_PTP
/* Re-enable PTP, where applicable. */
igb_ptp_reset(adapter);
-#endif /* CONFIG_IGB_PTP */
igb_get_phy_info(hw);
}
#endif
-#ifdef CONFIG_IGB_PTP
/* do hw tstamp init after resetting */
igb_ptp_init(adapter);
-#endif /* CONFIG_IGB_PTP */
dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n");
/* print bus type/speed/width info */
struct e1000_hw *hw = &adapter->hw;
pm_runtime_get_noresume(&pdev->dev);
-#ifdef CONFIG_IGB_PTP
igb_ptp_stop(adapter);
-#endif /* CONFIG_IGB_PTP */
/*
* The watchdog timer may be rescheduled, so explicitly
srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT;
srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT;
srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF;
-#ifdef CONFIG_IGB_PTP
if (hw->mac.type >= e1000_82580)
srrctl |= E1000_SRRCTL_TIMESTAMP;
-#endif /* CONFIG_IGB_PTP */
/* Only set Drop Enable if we are supporting multiple queues */
if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1)
srrctl |= E1000_SRRCTL_DROP_EN;
if (tx_flags & IGB_TX_FLAGS_VLAN)
cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE);
-#ifdef CONFIG_IGB_PTP
/* set timestamp bit if present */
if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP))
cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP);
-#endif /* CONFIG_IGB_PTP */
/* set segmentation bits for TSO */
if (tx_flags & IGB_TX_FLAGS_TSO)
netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
struct igb_ring *tx_ring)
{
-#ifdef CONFIG_IGB_PTP
struct igb_adapter *adapter = netdev_priv(tx_ring->netdev);
-#endif /* CONFIG_IGB_PTP */
struct igb_tx_buffer *first;
int tso;
u32 tx_flags = 0;
first->bytecount = skb->len;
first->gso_segs = 1;
-#ifdef CONFIG_IGB_PTP
if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
!(adapter->ptp_tx_skb))) {
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
if (adapter->hw.mac.type == e1000_82576)
schedule_work(&adapter->ptp_tx_work);
}
-#endif /* CONFIG_IGB_PTP */
if (vlan_tx_tag_present(skb)) {
tx_flags |= IGB_TX_FLAGS_VLAN;
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
-#ifdef CONFIG_IGB_PTP
if (icr & E1000_ICR_TS) {
u32 tsicr = rd32(E1000_TSICR);
schedule_work(&adapter->ptp_tx_work);
}
}
-#endif /* CONFIG_IGB_PTP */
wr32(E1000_EIMS, adapter->eims_other);
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
-#ifdef CONFIG_IGB_PTP
if (icr & E1000_ICR_TS) {
u32 tsicr = rd32(E1000_TSICR);
schedule_work(&adapter->ptp_tx_work);
}
}
-#endif /* CONFIG_IGB_PTP */
napi_schedule(&q_vector->napi);
mod_timer(&adapter->watchdog_timer, jiffies + 1);
}
-#ifdef CONFIG_IGB_PTP
if (icr & E1000_ICR_TS) {
u32 tsicr = rd32(E1000_TSICR);
schedule_work(&adapter->ptp_tx_work);
}
}
-#endif /* CONFIG_IGB_PTP */
napi_schedule(&q_vector->napi);
if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) {
unsigned char *va = page_address(page) + rx_buffer->page_offset;
-#ifdef CONFIG_IGB_PTP
if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
va += IGB_TS_HDR_LEN;
size -= IGB_TS_HDR_LEN;
}
-#endif
memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
/* we can reuse buffer as-is, just make sure it is local */
*/
va = skb_frag_address(frag);
-#ifdef CONFIG_IGB_PTP
if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
/* retrieve timestamp from buffer */
igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb);
va += IGB_TS_HDR_LEN;
}
-#endif
/*
* we need the header to contain the greater of either ETH_HLEN or
* 60 bytes if the skb->len is less than 60 for skb_pad.
igb_rx_checksum(rx_ring, rx_desc, skb);
-#ifdef CONFIG_IGB_PTP
igb_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
-#endif /* CONFIG_IGB_PTP */
if ((dev->features & NETIF_F_HW_VLAN_RX) &&
igb_test_staterr(rx_desc, E1000_RXD_STAT_VP)) {
case SIOCGMIIREG:
case SIOCSMIIREG:
return igb_mii_ioctl(netdev, ifr, cmd);
-#ifdef CONFIG_IGB_PTP
case SIOCSHWTSTAMP:
return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd);
-#endif /* CONFIG_IGB_PTP */
default:
return -EOPNOTSUPP;
}
ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o ixgbe_debugfs.o\
ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \
- ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o
+ ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe_ptp.o
ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \
ixgbe_dcb_82599.o ixgbe_dcb_nl.o
-ixgbe-$(CONFIG_IXGBE_PTP) += ixgbe_ptp.o
ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o
ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o
#include <linux/aer.h>
#include <linux/if_vlan.h>
-#ifdef CONFIG_IXGBE_PTP
#include <linux/clocksource.h>
#include <linux/net_tstamp.h>
#include <linux/ptp_clock_kernel.h>
-#endif /* CONFIG_IXGBE_PTP */
#include "ixgbe_type.h"
#include "ixgbe_common.h"
u32 interrupt_event;
u32 led_reg;
-#ifdef CONFIG_IXGBE_PTP
struct ptp_clock *ptp_clock;
struct ptp_clock_info ptp_caps;
unsigned long last_overflow_check;
struct timecounter tc;
int rx_hwtstamp_filter;
u32 base_incval;
-#endif /* CONFIG_IXGBE_PTP */
/* SR-IOV */
DECLARE_BITMAP(active_vfs, IXGBE_MAX_VF_FUNCTIONS);
return netdev_get_tx_queue(ring->netdev, ring->queue_index);
}
-#ifdef CONFIG_IXGBE_PTP
extern void ixgbe_ptp_init(struct ixgbe_adapter *adapter);
extern void ixgbe_ptp_stop(struct ixgbe_adapter *adapter);
extern void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter);
extern void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter);
extern void ixgbe_ptp_reset(struct ixgbe_adapter *adapter);
extern void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr);
-#endif /* CONFIG_IXGBE_PTP */
#endif /* _IXGBE_H_ */
struct ixgbe_adapter *adapter = netdev_priv(dev);
switch (adapter->hw.mac.type) {
-#ifdef CONFIG_IXGBE_PTP
case ixgbe_mac_X540:
case ixgbe_mac_82599EB:
info->so_timestamping =
(1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
(1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
break;
-#endif /* CONFIG_IXGBE_PTP */
default:
return ethtool_op_get_ts_info(dev, info);
break;
total_bytes += tx_buffer->bytecount;
total_packets += tx_buffer->gso_segs;
-#ifdef CONFIG_IXGBE_PTP
if (unlikely(tx_buffer->tx_flags & IXGBE_TX_FLAGS_TSTAMP))
ixgbe_ptp_tx_hwtstamp(q_vector, tx_buffer->skb);
-#endif
/* free the skb */
dev_kfree_skb_any(tx_buffer->skb);
ixgbe_rx_checksum(rx_ring, rx_desc, skb);
-#ifdef CONFIG_IXGBE_PTP
ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, rx_desc, skb);
-#endif
if ((dev->features & NETIF_F_HW_VLAN_RX) &&
ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) {
break;
}
-#ifdef CONFIG_IXGBE_PTP
if (adapter->hw.mac.type == ixgbe_mac_X540)
mask |= IXGBE_EIMS_TIMESYNC;
-#endif
if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) &&
!(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT))
ixgbe_check_fan_failure(adapter, eicr);
-#ifdef CONFIG_IXGBE_PTP
if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
ixgbe_ptp_check_pps_event(adapter, eicr);
-#endif
/* re-enable the original interrupt state, no lsc, no queues */
if (!test_bit(__IXGBE_DOWN, &adapter->state))
}
ixgbe_check_fan_failure(adapter, eicr);
-#ifdef CONFIG_IXGBE_PTP
if (unlikely(eicr & IXGBE_EICR_TIMESYNC))
ixgbe_ptp_check_pps_event(adapter, eicr);
-#endif
/* would disable interrupts here but EIAM disabled it */
napi_schedule(&q_vector->napi);
if (hw->mac.san_mac_rar_index)
hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0));
-#ifdef CONFIG_IXGBE_PTP
if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED)
ixgbe_ptp_reset(adapter);
-#endif
}
/**
if (err)
goto err_set_queues;
-#ifdef CONFIG_IXGBE_PTP
ixgbe_ptp_init(adapter);
-#endif /* CONFIG_IXGBE_PTP*/
ixgbe_up_complete(adapter);
{
struct ixgbe_adapter *adapter = netdev_priv(netdev);
-#ifdef CONFIG_IXGBE_PTP
ixgbe_ptp_stop(adapter);
-#endif
ixgbe_down(adapter);
ixgbe_free_irq(adapter);
break;
}
-#ifdef CONFIG_IXGBE_PTP
if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED)
ixgbe_ptp_start_cyclecounter(adapter);
-#endif
e_info(drv, "NIC Link is Up %s, Flow Control: %s\n",
(link_speed == IXGBE_LINK_SPEED_10GB_FULL ?
if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB)
adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP;
-#ifdef CONFIG_IXGBE_PTP
if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED)
ixgbe_ptp_start_cyclecounter(adapter);
-#endif
e_info(drv, "NIC Link is Down\n");
netif_carrier_off(netdev);
ixgbe_watchdog_subtask(adapter);
ixgbe_fdir_reinit_subtask(adapter);
ixgbe_check_hang_subtask(adapter);
-#ifdef CONFIG_IXGBE_PTP
ixgbe_ptp_overflow_check(adapter);
-#endif
ixgbe_service_event_complete(adapter);
}
if (tx_flags & IXGBE_TX_FLAGS_HW_VLAN)
cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE);
-#ifdef CONFIG_IXGBE_PTP
if (tx_flags & IXGBE_TX_FLAGS_TSTAMP)
cmd_type |= cpu_to_le32(IXGBE_ADVTXD_MAC_TSTAMP);
-#endif
/* set segmentation enable bits for TSO/FSO */
#ifdef IXGBE_FCOE
skb_tx_timestamp(skb);
-#ifdef CONFIG_IXGBE_PTP
if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
tx_flags |= IXGBE_TX_FLAGS_TSTAMP;
}
-#endif
#ifdef CONFIG_PCI_IOV
/*
struct ixgbe_adapter *adapter = netdev_priv(netdev);
switch (cmd) {
-#ifdef CONFIG_IXGBE_PTP
case SIOCSHWTSTAMP:
return ixgbe_ptp_hwtstamp_ioctl(adapter, req, cmd);
-#endif
default:
return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd);
}
purpose use.
ML7223/ML7831 is companion chip for Intel Atom E6xx series.
ML7223/ML7831 is completely compatible for Intel EG20T PCH.
-
-if PCH_GBE
-
-config PCH_PTP
- bool "PCH PTP clock support"
- default n
- depends on EXPERIMENTAL
- select PPS
- select PTP_1588_CLOCK
- select PTP_1588_CLOCK_PCH
- ---help---
- Say Y here if you want to use Precision Time Protocol (PTP) in the
- driver. PTP is a method to precisely synchronize distributed clocks
- over Ethernet networks.
-
-endif # PCH_GBE
extern void pch_gbe_free_rx_resources(struct pch_gbe_adapter *adapter,
struct pch_gbe_rx_ring *rx_ring);
extern void pch_gbe_update_stats(struct pch_gbe_adapter *adapter);
-#ifdef CONFIG_PCH_PTP
extern u32 pch_ch_control_read(struct pci_dev *pdev);
extern void pch_ch_control_write(struct pci_dev *pdev, u32 val);
extern u32 pch_ch_event_read(struct pci_dev *pdev);
extern u64 pch_rx_snap_read(struct pci_dev *pdev);
extern u64 pch_tx_snap_read(struct pci_dev *pdev);
extern int pch_set_station_address(u8 *addr, struct pci_dev *pdev);
-#endif
/* pch_gbe_param.c */
extern void pch_gbe_check_options(struct pch_gbe_adapter *adapter);
#include "pch_gbe.h"
#include "pch_gbe_api.h"
#include <linux/module.h>
-#ifdef CONFIG_PCH_PTP
#include <linux/net_tstamp.h>
#include <linux/ptp_classify.h>
-#endif
#define DRV_VERSION "1.01"
const char pch_driver_version[] = DRV_VERSION;
#define PCH_GBE_INT_DISABLE_ALL 0
-#ifdef CONFIG_PCH_PTP
/* Macros for ieee1588 */
/* 0x40 Time Synchronization Channel Control Register Bits */
#define MASTER_MODE (1<<0)
#define PTP_L4_MULTICAST_SA "01:00:5e:00:01:81"
#define PTP_L2_MULTICAST_SA "01:1b:19:00:00:00"
-#endif
static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT;
int data);
static void pch_gbe_set_multi(struct net_device *netdev);
-#ifdef CONFIG_PCH_PTP
static struct sock_filter ptp_filter[] = {
PTP_FILTER
};
return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
}
-#endif
inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw)
{
(int)sizeof(struct pch_gbe_tx_desc) * ring_num,
&hw->reg->TX_DSC_SW_P);
-#ifdef CONFIG_PCH_PTP
pch_tx_timestamp(adapter, skb);
-#endif
dev_kfree_skb_any(skb);
}
/* Write meta date of skb */
skb_put(skb, length);
-#ifdef CONFIG_PCH_PTP
pch_rx_timestamp(adapter, skb);
-#endif
skb->protocol = eth_type_trans(skb, netdev);
if (tcp_ip_status & PCH_GBE_RXD_ACC_STAT_TCPIPOK)
pr_debug("cmd : 0x%04x\n", cmd);
-#ifdef CONFIG_PCH_PTP
if (cmd == SIOCSHWTSTAMP)
return hwtstamp_ioctl(netdev, ifr, cmd);
-#endif
return generic_mii_ioctl(&adapter->mii, if_mii(ifr), cmd, NULL);
}
goto err_free_netdev;
}
-#ifdef CONFIG_PCH_PTP
adapter->ptp_pdev = pci_get_bus_and_slot(adapter->pdev->bus->number,
PCI_DEVFN(12, 4));
if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
pr_err("Bad ptp filter\n");
return -EINVAL;
}
-#endif
netdev->netdev_ops = &pch_gbe_netdev_ops;
netdev->watchdog_timeo = PCH_GBE_WATCHDOG_PERIOD;
This enables support for the SFC9000 I/O Virtualization
features, allowing accelerated network performance in
virtualized environments.
-config SFC_PTP
- bool "Solarflare SFC9000-family PTP support"
- depends on SFC && PTP_1588_CLOCK && !(SFC=y && PTP_1588_CLOCK=m)
- default y
- ---help---
- This enables support for the Precision Time Protocol (PTP)
- on SFC9000-family NICs
falcon_xmac.o mcdi_mac.o \
selftest.o ethtool.o qt202x_phy.o mdio_10g.o \
tenxpress.o txc43128_phy.o falcon_boards.o \
- mcdi.o mcdi_phy.o mcdi_mon.o
+ mcdi.o mcdi_phy.o mcdi_mon.o ptp.o
sfc-$(CONFIG_SFC_MTD) += mtd.o
sfc-$(CONFIG_SFC_SRIOV) += siena_sriov.o
-sfc-$(CONFIG_SFC_PTP) += ptp.o
obj-$(CONFIG_SFC) += sfc.o
struct work_struct peer_work;
#endif
-#ifdef CONFIG_SFC_PTP
struct efx_ptp_data *ptp_data;
-#endif
/* The following fields may be written more often */
bool spoofchk);
struct ethtool_ts_info;
-#ifdef CONFIG_SFC_PTP
extern void efx_ptp_probe(struct efx_nic *efx);
extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd);
extern int efx_ptp_get_ts_info(struct net_device *net_dev,
extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
-#else
-static inline void efx_ptp_probe(struct efx_nic *efx) {}
-static inline int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd)
-{
- return -EOPNOTSUPP;
-}
-static inline int efx_ptp_get_ts_info(struct net_device *net_dev,
- struct ethtool_ts_info *ts_info)
-{
- ts_info->so_timestamping = (SOF_TIMESTAMPING_SOFTWARE |
- SOF_TIMESTAMPING_RX_SOFTWARE);
- ts_info->phc_index = -1;
-
- return 0;
-}
-static inline bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
-{
- return false;
-}
-static inline int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
-{
- return NETDEV_TX_OK;
-}
-static inline void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) {}
-#endif
extern const struct efx_nic_type falcon_a1_nic_type;
extern const struct efx_nic_type falcon_b0_nic_type;
To compile this driver as a module, choose M here: the module
will be called cpsw.
+config TI_CPTS
+ boolean "TI Common Platform Time Sync (CPTS) Support"
+ depends on TI_CPSW && PTP_1588_CLOCK && !(TI_CPSW=y && PTP_1588_CLOCK=m)
+ ---help---
+ This driver supports the Common Platform Time Sync unit of
+ the CPSW Ethernet Switch. The unit can time stamp PTP UDP/IPv4
+ and Layer 2 packets, and the driver offers a PTP Hardware Clock.
+
config TLAN
tristate "TI ThunderLAN support"
depends on (PCI || EISA)
obj-$(CONFIG_TI_DAVINCI_MDIO) += davinci_mdio.o
obj-$(CONFIG_TI_DAVINCI_CPDMA) += davinci_cpdma.o
obj-$(CONFIG_TI_CPSW) += ti_cpsw.o
-ti_cpsw-y := cpsw_ale.o cpsw.o
+ti_cpsw-y := cpsw_ale.o cpsw.o cpts.o
#include <linux/if_ether.h>
#include <linux/etherdevice.h>
#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
#include <linux/phy.h>
#include <linux/workqueue.h>
#include <linux/delay.h>
#include <linux/platform_data/cpsw.h>
#include "cpsw_ale.h"
+#include "cpts.h"
#include "davinci_cpdma.h"
#define CPSW_DEBUG (NETIF_MSG_HW | NETIF_MSG_WOL | \
dev_notice(priv->dev, format, ## __VA_ARGS__); \
} while (0)
+#define ALE_ALL_PORTS 0x7
+
#define CPSW_MAJOR_VERSION(reg) (reg >> 8 & 0x7)
#define CPSW_MINOR_VERSION(reg) (reg & 0xff)
#define CPSW_RTL_VERSION(reg) ((reg >> 11) & 0x1f)
+#define CPSW_VERSION_1 0x19010a
+#define CPSW_VERSION_2 0x19010c
#define CPDMA_RXTHRESH 0x0c0
#define CPDMA_RXFREE 0x0e0
#define CPDMA_TXHDP 0x00
module_param(rx_packet_max, int, 0);
MODULE_PARM_DESC(rx_packet_max, "maximum receive packet size (bytes)");
-struct cpsw_ss_regs {
+struct cpsw_wr_regs {
u32 id_ver;
u32 soft_reset;
u32 control;
u32 misc_en;
};
-struct cpsw_regs {
+struct cpsw_ss_regs {
u32 id_ver;
u32 control;
u32 soft_reset;
u32 stat_port_en;
u32 ptype;
+ u32 soft_idle;
+ u32 thru_rate;
+ u32 gap_thresh;
+ u32 tx_start_wds;
+ u32 flow_control;
+ u32 vlan_ltype;
+ u32 ts_ltype;
+ u32 dlr_ltype;
};
-struct cpsw_slave_regs {
- u32 max_blks;
- u32 blk_cnt;
- u32 flow_thresh;
- u32 port_vlan;
- u32 tx_pri_map;
- u32 ts_ctl;
- u32 ts_seq_ltype;
- u32 ts_vlan;
- u32 sa_lo;
- u32 sa_hi;
-};
+/* CPSW_PORT_V1 */
+#define CPSW1_MAX_BLKS 0x00 /* Maximum FIFO Blocks */
+#define CPSW1_BLK_CNT 0x04 /* FIFO Block Usage Count (Read Only) */
+#define CPSW1_TX_IN_CTL 0x08 /* Transmit FIFO Control */
+#define CPSW1_PORT_VLAN 0x0c /* VLAN Register */
+#define CPSW1_TX_PRI_MAP 0x10 /* Tx Header Priority to Switch Pri Mapping */
+#define CPSW1_TS_CTL 0x14 /* Time Sync Control */
+#define CPSW1_TS_SEQ_LTYPE 0x18 /* Time Sync Sequence ID Offset and Msg Type */
+#define CPSW1_TS_VLAN 0x1c /* Time Sync VLAN1 and VLAN2 */
+
+/* CPSW_PORT_V2 */
+#define CPSW2_CONTROL 0x00 /* Control Register */
+#define CPSW2_MAX_BLKS 0x08 /* Maximum FIFO Blocks */
+#define CPSW2_BLK_CNT 0x0c /* FIFO Block Usage Count (Read Only) */
+#define CPSW2_TX_IN_CTL 0x10 /* Transmit FIFO Control */
+#define CPSW2_PORT_VLAN 0x14 /* VLAN Register */
+#define CPSW2_TX_PRI_MAP 0x18 /* Tx Header Priority to Switch Pri Mapping */
+#define CPSW2_TS_SEQ_MTYPE 0x1c /* Time Sync Sequence ID Offset and Msg Type */
+
+/* CPSW_PORT_V1 and V2 */
+#define SA_LO 0x20 /* CPGMAC_SL Source Address Low */
+#define SA_HI 0x24 /* CPGMAC_SL Source Address High */
+#define SEND_PERCENT 0x28 /* Transmit Queue Send Percentages */
+
+/* CPSW_PORT_V2 only */
+#define RX_DSCP_PRI_MAP0 0x30 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP1 0x34 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP2 0x38 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP3 0x3c /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP4 0x40 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP5 0x44 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP6 0x48 /* Rx DSCP Priority to Rx Packet Mapping */
+#define RX_DSCP_PRI_MAP7 0x4c /* Rx DSCP Priority to Rx Packet Mapping */
+
+/* Bit definitions for the CPSW2_CONTROL register */
+#define PASS_PRI_TAGGED (1<<24) /* Pass Priority Tagged */
+#define VLAN_LTYPE2_EN (1<<21) /* VLAN LTYPE 2 enable */
+#define VLAN_LTYPE1_EN (1<<20) /* VLAN LTYPE 1 enable */
+#define DSCP_PRI_EN (1<<16) /* DSCP Priority Enable */
+#define TS_320 (1<<14) /* Time Sync Dest Port 320 enable */
+#define TS_319 (1<<13) /* Time Sync Dest Port 319 enable */
+#define TS_132 (1<<12) /* Time Sync Dest IP Addr 132 enable */
+#define TS_131 (1<<11) /* Time Sync Dest IP Addr 131 enable */
+#define TS_130 (1<<10) /* Time Sync Dest IP Addr 130 enable */
+#define TS_129 (1<<9) /* Time Sync Dest IP Addr 129 enable */
+#define TS_BIT8 (1<<8) /* ts_ttl_nonzero? */
+#define TS_ANNEX_D_EN (1<<4) /* Time Sync Annex D enable */
+#define TS_LTYPE2_EN (1<<3) /* Time Sync LTYPE 2 enable */
+#define TS_LTYPE1_EN (1<<2) /* Time Sync LTYPE 1 enable */
+#define TS_TX_EN (1<<1) /* Time Sync Transmit Enable */
+#define TS_RX_EN (1<<0) /* Time Sync Receive Enable */
+
+#define CTRL_TS_BITS \
+ (TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 | TS_BIT8 | \
+ TS_ANNEX_D_EN | TS_LTYPE1_EN)
+
+#define CTRL_ALL_TS_MASK (CTRL_TS_BITS | TS_TX_EN | TS_RX_EN)
+#define CTRL_TX_TS_BITS (CTRL_TS_BITS | TS_TX_EN)
+#define CTRL_RX_TS_BITS (CTRL_TS_BITS | TS_RX_EN)
+
+/* Bit definitions for the CPSW2_TS_SEQ_MTYPE register */
+#define TS_SEQ_ID_OFFSET_SHIFT (16) /* Time Sync Sequence ID Offset */
+#define TS_SEQ_ID_OFFSET_MASK (0x3f)
+#define TS_MSG_TYPE_EN_SHIFT (0) /* Time Sync Message Type Enable */
+#define TS_MSG_TYPE_EN_MASK (0xffff)
+
+/* The PTP event messages - Sync, Delay_Req, Pdelay_Req, and Pdelay_Resp. */
+#define EVENT_MSG_BITS ((1<<0) | (1<<1) | (1<<2) | (1<<3))
+
+/* Bit definitions for the CPSW1_TS_CTL register */
+#define CPSW_V1_TS_RX_EN BIT(0)
+#define CPSW_V1_TS_TX_EN BIT(4)
+#define CPSW_V1_MSG_TYPE_OFS 16
+
+/* Bit definitions for the CPSW1_TS_SEQ_LTYPE register */
+#define CPSW_V1_SEQ_ID_OFS_SHIFT 16
struct cpsw_host_regs {
u32 max_blks;
};
struct cpsw_slave {
- struct cpsw_slave_regs __iomem *regs;
+ void __iomem *regs;
struct cpsw_sliver_regs __iomem *sliver;
int slave_num;
u32 mac_control;
struct phy_device *phy;
};
+static inline u32 slave_read(struct cpsw_slave *slave, u32 offset)
+{
+ return __raw_readl(slave->regs + offset);
+}
+
+static inline void slave_write(struct cpsw_slave *slave, u32 val, u32 offset)
+{
+ __raw_writel(val, slave->regs + offset);
+}
+
struct cpsw_priv {
spinlock_t lock;
struct platform_device *pdev;
struct napi_struct napi;
struct device *dev;
struct cpsw_platform_data data;
- struct cpsw_regs __iomem *regs;
- struct cpsw_ss_regs __iomem *ss_regs;
+ struct cpsw_ss_regs __iomem *regs;
+ struct cpsw_wr_regs __iomem *wr_regs;
struct cpsw_host_regs __iomem *host_port_regs;
u32 msg_enable;
+ u32 version;
struct net_device_stats stats;
int rx_packet_max;
int host_port;
/* snapshot of IRQ numbers */
u32 irqs_table[4];
u32 num_irqs;
+ struct cpts cpts;
};
#define napi_to_priv(napi) container_of(napi, struct cpsw_priv, napi)
(func)((priv)->slaves + idx, ##arg); \
} while (0)
+static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+
+ if (ndev->flags & IFF_PROMISC) {
+ /* Enable promiscuous mode */
+ dev_err(priv->dev, "Ignoring Promiscuous mode\n");
+ return;
+ }
+
+ /* Clear all mcast from ALE */
+ cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port);
+
+ if (!netdev_mc_empty(ndev)) {
+ struct netdev_hw_addr *ha;
+
+ /* program multicast address list into ALE register */
+ netdev_for_each_mc_addr(ha, ndev) {
+ cpsw_ale_add_mcast(priv->ale, (u8 *)ha->addr,
+ ALE_ALL_PORTS << priv->host_port, 0, 0);
+ }
+ }
+}
+
static void cpsw_intr_enable(struct cpsw_priv *priv)
{
- __raw_writel(0xFF, &priv->ss_regs->tx_en);
- __raw_writel(0xFF, &priv->ss_regs->rx_en);
+ __raw_writel(0xFF, &priv->wr_regs->tx_en);
+ __raw_writel(0xFF, &priv->wr_regs->rx_en);
cpdma_ctlr_int_ctrl(priv->dma, true);
return;
static void cpsw_intr_disable(struct cpsw_priv *priv)
{
- __raw_writel(0, &priv->ss_regs->tx_en);
- __raw_writel(0, &priv->ss_regs->rx_en);
+ __raw_writel(0, &priv->wr_regs->tx_en);
+ __raw_writel(0, &priv->wr_regs->rx_en);
cpdma_ctlr_int_ctrl(priv->dma, false);
return;
if (unlikely(netif_queue_stopped(ndev)))
netif_start_queue(ndev);
+ cpts_tx_timestamp(&priv->cpts, skb);
priv->stats.tx_packets++;
priv->stats.tx_bytes += len;
dev_kfree_skb_any(skb);
}
if (likely(status >= 0)) {
skb_put(skb, len);
+ cpts_rx_timestamp(&priv->cpts, skb);
skb->protocol = eth_type_trans(skb, ndev);
netif_receive_skb(skb);
priv->stats.rx_bytes += len;
static void cpsw_set_slave_mac(struct cpsw_slave *slave,
struct cpsw_priv *priv)
{
- __raw_writel(mac_hi(priv->mac_addr), &slave->regs->sa_hi);
- __raw_writel(mac_lo(priv->mac_addr), &slave->regs->sa_lo);
+ slave_write(slave, mac_hi(priv->mac_addr), SA_HI);
+ slave_write(slave, mac_lo(priv->mac_addr), SA_LO);
}
static void _cpsw_adjust_link(struct cpsw_slave *slave,
/* setup priority mapping */
__raw_writel(RX_PRIORITY_MAPPING, &slave->sliver->rx_pri_map);
- __raw_writel(TX_PRIORITY_MAPPING, &slave->regs->tx_pri_map);
+
+ switch (priv->version) {
+ case CPSW_VERSION_1:
+ slave_write(slave, TX_PRIORITY_MAPPING, CPSW1_TX_PRI_MAP);
+ break;
+ case CPSW_VERSION_2:
+ slave_write(slave, TX_PRIORITY_MAPPING, CPSW2_TX_PRI_MAP);
+ break;
+ }
/* setup max packet size, and mac address */
__raw_writel(priv->rx_packet_max, &slave->sliver->rx_maxlen);
pm_runtime_get_sync(&priv->pdev->dev);
reg = __raw_readl(&priv->regs->id_ver);
+ priv->version = reg;
dev_info(priv->dev, "initializing cpsw version %d.%d (%d)\n",
CPSW_MAJOR_VERSION(reg), CPSW_MINOR_VERSION(reg),
return NETDEV_TX_OK;
}
+ if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && priv->cpts.tx_enable)
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+ skb_tx_timestamp(skb);
+
ret = cpdma_chan_submit(priv->txch, skb, skb->data,
skb->len, GFP_KERNEL);
if (unlikely(ret != 0)) {
dev_err(&ndev->dev, "multicast traffic cannot be filtered!\n");
}
+#ifdef CONFIG_TI_CPTS
+
+static void cpsw_hwtstamp_v1(struct cpsw_priv *priv)
+{
+ struct cpsw_slave *slave = &priv->slaves[priv->data.cpts_active_slave];
+ u32 ts_en, seq_id;
+
+ if (!priv->cpts.tx_enable && !priv->cpts.rx_enable) {
+ slave_write(slave, 0, CPSW1_TS_CTL);
+ return;
+ }
+
+ seq_id = (30 << CPSW_V1_SEQ_ID_OFS_SHIFT) | ETH_P_1588;
+ ts_en = EVENT_MSG_BITS << CPSW_V1_MSG_TYPE_OFS;
+
+ if (priv->cpts.tx_enable)
+ ts_en |= CPSW_V1_TS_TX_EN;
+
+ if (priv->cpts.rx_enable)
+ ts_en |= CPSW_V1_TS_RX_EN;
+
+ slave_write(slave, ts_en, CPSW1_TS_CTL);
+ slave_write(slave, seq_id, CPSW1_TS_SEQ_LTYPE);
+}
+
+static void cpsw_hwtstamp_v2(struct cpsw_priv *priv)
+{
+ struct cpsw_slave *slave = &priv->slaves[priv->data.cpts_active_slave];
+ u32 ctrl, mtype;
+
+ ctrl = slave_read(slave, CPSW2_CONTROL);
+ ctrl &= ~CTRL_ALL_TS_MASK;
+
+ if (priv->cpts.tx_enable)
+ ctrl |= CTRL_TX_TS_BITS;
+
+ if (priv->cpts.rx_enable)
+ ctrl |= CTRL_RX_TS_BITS;
+
+ mtype = (30 << TS_SEQ_ID_OFFSET_SHIFT) | EVENT_MSG_BITS;
+
+ slave_write(slave, mtype, CPSW2_TS_SEQ_MTYPE);
+ slave_write(slave, ctrl, CPSW2_CONTROL);
+ __raw_writel(ETH_P_1588, &priv->regs->ts_ltype);
+}
+
+static int cpsw_hwtstamp_ioctl(struct cpsw_priv *priv, struct ifreq *ifr)
+{
+ struct cpts *cpts = &priv->cpts;
+ struct hwtstamp_config cfg;
+
+ if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+ return -EFAULT;
+
+ /* reserved for future extensions */
+ if (cfg.flags)
+ return -EINVAL;
+
+ switch (cfg.tx_type) {
+ case HWTSTAMP_TX_OFF:
+ cpts->tx_enable = 0;
+ break;
+ case HWTSTAMP_TX_ON:
+ cpts->tx_enable = 1;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ switch (cfg.rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ cpts->rx_enable = 0;
+ break;
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ return -ERANGE;
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ cpts->rx_enable = 1;
+ cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+ break;
+ default:
+ return -ERANGE;
+ }
+
+ switch (priv->version) {
+ case CPSW_VERSION_1:
+ cpsw_hwtstamp_v1(priv);
+ break;
+ case CPSW_VERSION_2:
+ cpsw_hwtstamp_v2(priv);
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+
+ return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0;
+}
+
+#endif /*CONFIG_TI_CPTS*/
+
+static int cpsw_ndo_ioctl(struct net_device *dev, struct ifreq *req, int cmd)
+{
+ struct cpsw_priv *priv = netdev_priv(dev);
+
+ if (!netif_running(dev))
+ return -EINVAL;
+
+#ifdef CONFIG_TI_CPTS
+ if (cmd == SIOCSHWTSTAMP)
+ return cpsw_hwtstamp_ioctl(priv, req);
+#endif
+ return -ENOTSUPP;
+}
+
static void cpsw_ndo_tx_timeout(struct net_device *ndev)
{
struct cpsw_priv *priv = netdev_priv(ndev);
.ndo_stop = cpsw_ndo_stop,
.ndo_start_xmit = cpsw_ndo_start_xmit,
.ndo_change_rx_flags = cpsw_ndo_change_rx_flags,
+ .ndo_do_ioctl = cpsw_ndo_ioctl,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = eth_change_mtu,
.ndo_tx_timeout = cpsw_ndo_tx_timeout,
.ndo_get_stats = cpsw_ndo_get_stats,
+ .ndo_set_rx_mode = cpsw_ndo_set_rx_mode,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = cpsw_ndo_poll_controller,
#endif
priv->msg_enable = value;
}
+static int cpsw_get_ts_info(struct net_device *ndev,
+ struct ethtool_ts_info *info)
+{
+#ifdef CONFIG_TI_CPTS
+ struct cpsw_priv *priv = netdev_priv(ndev);
+
+ info->so_timestamping =
+ SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE |
+ SOF_TIMESTAMPING_RAW_HARDWARE;
+ info->phc_index = priv->cpts.phc_index;
+ info->tx_types =
+ (1 << HWTSTAMP_TX_OFF) |
+ (1 << HWTSTAMP_TX_ON);
+ info->rx_filters =
+ (1 << HWTSTAMP_FILTER_NONE) |
+ (1 << HWTSTAMP_FILTER_PTP_V2_EVENT);
+#else
+ info->so_timestamping =
+ SOF_TIMESTAMPING_TX_SOFTWARE |
+ SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE;
+ info->phc_index = -1;
+ info->tx_types = 0;
+ info->rx_filters = 0;
+#endif
+ return 0;
+}
+
static const struct ethtool_ops cpsw_ethtool_ops = {
.get_drvinfo = cpsw_get_drvinfo,
.get_msglevel = cpsw_get_msglevel,
.set_msglevel = cpsw_set_msglevel,
.get_link = ethtool_op_get_link,
+ .get_ts_info = cpsw_get_ts_info,
};
static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv)
}
data->slaves = prop;
+ if (of_property_read_u32(node, "cpts_active_slave", &prop)) {
+ pr_err("Missing cpts_active_slave property in the DT.\n");
+ ret = -EINVAL;
+ goto error_ret;
+ }
+ data->cpts_active_slave = prop;
+
+ if (of_property_read_u32(node, "cpts_clock_mult", &prop)) {
+ pr_err("Missing cpts_clock_mult property in the DT.\n");
+ ret = -EINVAL;
+ goto error_ret;
+ }
+ data->cpts_clock_mult = prop;
+
+ if (of_property_read_u32(node, "cpts_clock_shift", &prop)) {
+ pr_err("Missing cpts_clock_shift property in the DT.\n");
+ ret = -EINVAL;
+ goto error_ret;
+ }
+ data->cpts_clock_shift = prop;
+
data->slave_data = kzalloc(sizeof(struct cpsw_slave_data) *
data->slaves, GFP_KERNEL);
if (!data->slave_data) {
}
data->hw_stats_reg_ofs = prop;
+ if (of_property_read_u32(node, "cpts_reg_ofs", &prop)) {
+ pr_err("Missing cpts_reg_ofs property in the DT.\n");
+ ret = -EINVAL;
+ goto error_ret;
+ }
+ data->cpts_reg_ofs = prop;
+
if (of_property_read_u32(node, "bd_ram_ofs", &prop)) {
pr_err("Missing bd_ram_ofs property in the DT.\n");
ret = -EINVAL;
priv->regs = regs;
priv->host_port = data->host_port_num;
priv->host_port_regs = regs + data->host_port_reg_ofs;
+ priv->cpts.reg = regs + data->cpts_reg_ofs;
priv->cpsw_ss_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
if (!priv->cpsw_ss_res) {
dev_err(priv->dev, "unable to map i/o region\n");
goto clean_cpsw_ss_iores_ret;
}
- priv->ss_regs = regs;
+ priv->wr_regs = regs;
for_each_slave(priv, cpsw_slave_init, priv);
goto clean_irq_ret;
}
+ if (cpts_register(&pdev->dev, &priv->cpts,
+ data->cpts_clock_mult, data->cpts_clock_shift))
+ dev_err(priv->dev, "error registering cpts device\n");
+
cpsw_notice(priv, probe, "initialized device (regs %x, irq %d)\n",
priv->cpsw_res->start, ndev->irq);
pr_info("removing device");
platform_set_drvdata(pdev, NULL);
+ cpts_unregister(&priv->cpts);
free_irq(ndev->irq, priv);
cpsw_ale_destroy(priv->ale);
cpdma_chan_destroy(priv->txch);
#include <linux/io.h>
#include <linux/stat.h>
#include <linux/sysfs.h>
+#include <linux/etherdevice.h>
#include "cpsw_ale.h"
mask &= ~port_mask;
/* free if only remaining port is host port */
- if (mask == BIT(ale->params.ale_ports))
- cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
- else
+ if (mask)
cpsw_ale_set_port_mask(ale_entry, mask);
+ else
+ cpsw_ale_set_entry_type(ale_entry, ALE_TYPE_FREE);
+}
+
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask)
+{
+ u32 ale_entry[ALE_ENTRY_WORDS];
+ int ret, idx;
+
+ for (idx = 0; idx < ale->params.ale_entries; idx++) {
+ cpsw_ale_read(ale, idx, ale_entry);
+ ret = cpsw_ale_get_entry_type(ale_entry);
+ if (ret != ALE_TYPE_ADDR && ret != ALE_TYPE_VLAN_ADDR)
+ continue;
+
+ if (cpsw_ale_get_mcast(ale_entry)) {
+ u8 addr[6];
+
+ cpsw_ale_get_addr(ale_entry, addr);
+ if (!is_broadcast_ether_addr(addr))
+ cpsw_ale_flush_mcast(ale, ale_entry, port_mask);
+ }
+
+ cpsw_ale_write(ale, idx, ale_entry);
+ }
+ return 0;
}
static void cpsw_ale_flush_ucast(struct cpsw_ale *ale, u32 *ale_entry,
int cpsw_ale_set_ageout(struct cpsw_ale *ale, int ageout);
int cpsw_ale_flush(struct cpsw_ale *ale, int port_mask);
+int cpsw_ale_flush_multicast(struct cpsw_ale *ale, int port_mask);
int cpsw_ale_add_ucast(struct cpsw_ale *ale, u8 *addr, int port, int flags);
int cpsw_ale_del_ucast(struct cpsw_ale *ale, u8 *addr, int port);
int cpsw_ale_add_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask,
--- /dev/null
+/*
+ * TI Common Platform Time Sync
+ *
+ * Copyright (C) 2012 Richard Cochran <richardcochran@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#include <linux/err.h>
+#include <linux/if.h>
+#include <linux/hrtimer.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/ptp_classify.h>
+#include <linux/time.h>
+#include <linux/uaccess.h>
+#include <linux/workqueue.h>
+
+#include <plat/clock.h>
+
+#include "cpts.h"
+
+#ifdef CONFIG_TI_CPTS
+
+static struct sock_filter ptp_filter[] = {
+ PTP_FILTER
+};
+
+#define cpts_read32(c, r) __raw_readl(&c->reg->r)
+#define cpts_write32(c, v, r) __raw_writel(v, &c->reg->r)
+
+static int event_expired(struct cpts_event *event)
+{
+ return time_after(jiffies, event->tmo);
+}
+
+static int event_type(struct cpts_event *event)
+{
+ return (event->high >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK;
+}
+
+static int cpts_fifo_pop(struct cpts *cpts, u32 *high, u32 *low)
+{
+ u32 r = cpts_read32(cpts, intstat_raw);
+
+ if (r & TS_PEND_RAW) {
+ *high = cpts_read32(cpts, event_high);
+ *low = cpts_read32(cpts, event_low);
+ cpts_write32(cpts, EVENT_POP, event_pop);
+ return 0;
+ }
+ return -1;
+}
+
+/*
+ * Returns zero if matching event type was found.
+ */
+static int cpts_fifo_read(struct cpts *cpts, int match)
+{
+ int i, type = -1;
+ u32 hi, lo;
+ struct cpts_event *event;
+
+ for (i = 0; i < CPTS_FIFO_DEPTH; i++) {
+ if (cpts_fifo_pop(cpts, &hi, &lo))
+ break;
+ if (list_empty(&cpts->pool)) {
+ pr_err("cpts: event pool is empty\n");
+ return -1;
+ }
+ event = list_first_entry(&cpts->pool, struct cpts_event, list);
+ event->tmo = jiffies + 2;
+ event->high = hi;
+ event->low = lo;
+ type = event_type(event);
+ switch (type) {
+ case CPTS_EV_PUSH:
+ case CPTS_EV_RX:
+ case CPTS_EV_TX:
+ list_del_init(&event->list);
+ list_add_tail(&event->list, &cpts->events);
+ break;
+ case CPTS_EV_ROLL:
+ case CPTS_EV_HALF:
+ case CPTS_EV_HW:
+ break;
+ default:
+ pr_err("cpts: unkown event type\n");
+ break;
+ }
+ if (type == match)
+ break;
+ }
+ return type == match ? 0 : -1;
+}
+
+static cycle_t cpts_systim_read(const struct cyclecounter *cc)
+{
+ u64 val = 0;
+ struct cpts_event *event;
+ struct list_head *this, *next;
+ struct cpts *cpts = container_of(cc, struct cpts, cc);
+
+ cpts_write32(cpts, TS_PUSH, ts_push);
+ if (cpts_fifo_read(cpts, CPTS_EV_PUSH))
+ pr_err("cpts: unable to obtain a time stamp\n");
+
+ list_for_each_safe(this, next, &cpts->events) {
+ event = list_entry(this, struct cpts_event, list);
+ if (event_type(event) == CPTS_EV_PUSH) {
+ list_del_init(&event->list);
+ list_add(&event->list, &cpts->pool);
+ val = event->low;
+ break;
+ }
+ }
+
+ return val;
+}
+
+/* PTP clock operations */
+
+static int cpts_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb)
+{
+ u64 adj;
+ u32 diff, mult;
+ int neg_adj = 0;
+ unsigned long flags;
+ struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+ if (ppb < 0) {
+ neg_adj = 1;
+ ppb = -ppb;
+ }
+ mult = cpts->cc_mult;
+ adj = mult;
+ adj *= ppb;
+ diff = div_u64(adj, 1000000000ULL);
+
+ spin_lock_irqsave(&cpts->lock, flags);
+
+ timecounter_read(&cpts->tc);
+
+ cpts->cc.mult = neg_adj ? mult - diff : mult + diff;
+
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ return 0;
+}
+
+static int cpts_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ s64 now;
+ unsigned long flags;
+ struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+ spin_lock_irqsave(&cpts->lock, flags);
+ now = timecounter_read(&cpts->tc);
+ now += delta;
+ timecounter_init(&cpts->tc, &cpts->cc, now);
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ return 0;
+}
+
+static int cpts_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+ u64 ns;
+ u32 remainder;
+ unsigned long flags;
+ struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+ spin_lock_irqsave(&cpts->lock, flags);
+ ns = timecounter_read(&cpts->tc);
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder);
+ ts->tv_nsec = remainder;
+
+ return 0;
+}
+
+static int cpts_ptp_settime(struct ptp_clock_info *ptp,
+ const struct timespec *ts)
+{
+ u64 ns;
+ unsigned long flags;
+ struct cpts *cpts = container_of(ptp, struct cpts, info);
+
+ ns = ts->tv_sec * 1000000000ULL;
+ ns += ts->tv_nsec;
+
+ spin_lock_irqsave(&cpts->lock, flags);
+ timecounter_init(&cpts->tc, &cpts->cc, ns);
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ return 0;
+}
+
+static int cpts_ptp_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *rq, int on)
+{
+ return -EOPNOTSUPP;
+}
+
+static struct ptp_clock_info cpts_info = {
+ .owner = THIS_MODULE,
+ .name = "CTPS timer",
+ .max_adj = 1000000,
+ .n_ext_ts = 0,
+ .pps = 0,
+ .adjfreq = cpts_ptp_adjfreq,
+ .adjtime = cpts_ptp_adjtime,
+ .gettime = cpts_ptp_gettime,
+ .settime = cpts_ptp_settime,
+ .enable = cpts_ptp_enable,
+};
+
+static void cpts_overflow_check(struct work_struct *work)
+{
+ struct timespec ts;
+ struct cpts *cpts = container_of(work, struct cpts, overflow_work.work);
+
+ cpts_write32(cpts, CPTS_EN, control);
+ cpts_write32(cpts, TS_PEND_EN, int_enable);
+ cpts_ptp_gettime(&cpts->info, &ts);
+ pr_debug("cpts overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec);
+ schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD);
+}
+
+#define CPTS_REF_CLOCK_NAME "cpsw_cpts_rft_clk"
+
+static void cpts_clk_init(struct cpts *cpts)
+{
+ cpts->refclk = clk_get(NULL, CPTS_REF_CLOCK_NAME);
+ if (IS_ERR(cpts->refclk)) {
+ pr_err("Failed to clk_get %s\n", CPTS_REF_CLOCK_NAME);
+ cpts->refclk = NULL;
+ return;
+ }
+ clk_enable(cpts->refclk);
+ cpts->freq = cpts->refclk->recalc(cpts->refclk);
+}
+
+static void cpts_clk_release(struct cpts *cpts)
+{
+ clk_disable(cpts->refclk);
+ clk_put(cpts->refclk);
+}
+
+static int cpts_match(struct sk_buff *skb, unsigned int ptp_class,
+ u16 ts_seqid, u8 ts_msgtype)
+{
+ u16 *seqid;
+ unsigned int offset;
+ u8 *msgtype, *data = skb->data;
+
+ switch (ptp_class) {
+ case PTP_CLASS_V1_IPV4:
+ case PTP_CLASS_V2_IPV4:
+ offset = ETH_HLEN + IPV4_HLEN(data) + UDP_HLEN;
+ break;
+ case PTP_CLASS_V1_IPV6:
+ case PTP_CLASS_V2_IPV6:
+ offset = OFF_PTP6;
+ break;
+ case PTP_CLASS_V2_L2:
+ offset = ETH_HLEN;
+ break;
+ case PTP_CLASS_V2_VLAN:
+ offset = ETH_HLEN + VLAN_HLEN;
+ break;
+ default:
+ return 0;
+ }
+
+ if (skb->len + ETH_HLEN < offset + OFF_PTP_SEQUENCE_ID + sizeof(*seqid))
+ return 0;
+
+ if (unlikely(ptp_class & PTP_CLASS_V1))
+ msgtype = data + offset + OFF_PTP_CONTROL;
+ else
+ msgtype = data + offset;
+
+ seqid = (u16 *)(data + offset + OFF_PTP_SEQUENCE_ID);
+
+ return (ts_msgtype == (*msgtype & 0xf) && ts_seqid == ntohs(*seqid));
+}
+
+static u64 cpts_find_ts(struct cpts *cpts, struct sk_buff *skb, int ev_type)
+{
+ u64 ns = 0;
+ struct cpts_event *event;
+ struct list_head *this, *next;
+ unsigned int class = sk_run_filter(skb, ptp_filter);
+ unsigned long flags;
+ u16 seqid;
+ u8 mtype;
+
+ if (class == PTP_CLASS_NONE)
+ return 0;
+
+ spin_lock_irqsave(&cpts->lock, flags);
+ cpts_fifo_read(cpts, CPTS_EV_PUSH);
+ list_for_each_safe(this, next, &cpts->events) {
+ event = list_entry(this, struct cpts_event, list);
+ if (event_expired(event)) {
+ list_del_init(&event->list);
+ list_add(&event->list, &cpts->pool);
+ continue;
+ }
+ mtype = (event->high >> MESSAGE_TYPE_SHIFT) & MESSAGE_TYPE_MASK;
+ seqid = (event->high >> SEQUENCE_ID_SHIFT) & SEQUENCE_ID_MASK;
+ if (ev_type == event_type(event) &&
+ cpts_match(skb, class, seqid, mtype)) {
+ ns = timecounter_cyc2time(&cpts->tc, event->low);
+ list_del_init(&event->list);
+ list_add(&event->list, &cpts->pool);
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ return ns;
+}
+
+void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
+{
+ u64 ns;
+ struct skb_shared_hwtstamps *ssh;
+
+ if (!cpts->rx_enable)
+ return;
+ ns = cpts_find_ts(cpts, skb, CPTS_EV_RX);
+ if (!ns)
+ return;
+ ssh = skb_hwtstamps(skb);
+ memset(ssh, 0, sizeof(*ssh));
+ ssh->hwtstamp = ns_to_ktime(ns);
+}
+
+void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
+{
+ u64 ns;
+ struct skb_shared_hwtstamps ssh;
+
+ if (!(skb_shinfo(skb)->tx_flags & SKBTX_IN_PROGRESS))
+ return;
+ ns = cpts_find_ts(cpts, skb, CPTS_EV_TX);
+ if (!ns)
+ return;
+ memset(&ssh, 0, sizeof(ssh));
+ ssh.hwtstamp = ns_to_ktime(ns);
+ skb_tstamp_tx(skb, &ssh);
+}
+
+#endif /*CONFIG_TI_CPTS*/
+
+int cpts_register(struct device *dev, struct cpts *cpts,
+ u32 mult, u32 shift)
+{
+#ifdef CONFIG_TI_CPTS
+ int err, i;
+ unsigned long flags;
+
+ if (ptp_filter_init(ptp_filter, ARRAY_SIZE(ptp_filter))) {
+ pr_err("cpts: bad ptp filter\n");
+ return -EINVAL;
+ }
+ cpts->info = cpts_info;
+ cpts->clock = ptp_clock_register(&cpts->info, dev);
+ if (IS_ERR(cpts->clock)) {
+ err = PTR_ERR(cpts->clock);
+ cpts->clock = NULL;
+ return err;
+ }
+ spin_lock_init(&cpts->lock);
+
+ cpts->cc.read = cpts_systim_read;
+ cpts->cc.mask = CLOCKSOURCE_MASK(32);
+ cpts->cc_mult = mult;
+ cpts->cc.mult = mult;
+ cpts->cc.shift = shift;
+
+ INIT_LIST_HEAD(&cpts->events);
+ INIT_LIST_HEAD(&cpts->pool);
+ for (i = 0; i < CPTS_MAX_EVENTS; i++)
+ list_add(&cpts->pool_data[i].list, &cpts->pool);
+
+ cpts_clk_init(cpts);
+ cpts_write32(cpts, CPTS_EN, control);
+ cpts_write32(cpts, TS_PEND_EN, int_enable);
+
+ spin_lock_irqsave(&cpts->lock, flags);
+ timecounter_init(&cpts->tc, &cpts->cc, ktime_to_ns(ktime_get_real()));
+ spin_unlock_irqrestore(&cpts->lock, flags);
+
+ INIT_DELAYED_WORK(&cpts->overflow_work, cpts_overflow_check);
+ schedule_delayed_work(&cpts->overflow_work, CPTS_OVERFLOW_PERIOD);
+
+ cpts->phc_index = ptp_clock_index(cpts->clock);
+#endif
+ return 0;
+}
+
+void cpts_unregister(struct cpts *cpts)
+{
+#ifdef CONFIG_TI_CPTS
+ if (cpts->clock) {
+ ptp_clock_unregister(cpts->clock);
+ cancel_delayed_work_sync(&cpts->overflow_work);
+ }
+ if (cpts->refclk)
+ cpts_clk_release(cpts);
+#endif
+}
--- /dev/null
+/*
+ * TI Common Platform Time Sync
+ *
+ * Copyright (C) 2012 Richard Cochran <richardcochran@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+#ifndef _TI_CPTS_H_
+#define _TI_CPTS_H_
+
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clocksource.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/ptp_clock_kernel.h>
+#include <linux/skbuff.h>
+
+struct cpsw_cpts {
+ u32 idver; /* Identification and version */
+ u32 control; /* Time sync control */
+ u32 res1;
+ u32 ts_push; /* Time stamp event push */
+ u32 ts_load_val; /* Time stamp load value */
+ u32 ts_load_en; /* Time stamp load enable */
+ u32 res2[2];
+ u32 intstat_raw; /* Time sync interrupt status raw */
+ u32 intstat_masked; /* Time sync interrupt status masked */
+ u32 int_enable; /* Time sync interrupt enable */
+ u32 res3;
+ u32 event_pop; /* Event interrupt pop */
+ u32 event_low; /* 32 Bit Event Time Stamp */
+ u32 event_high; /* Event Type Fields */
+};
+
+/* Bit definitions for the IDVER register */
+#define TX_IDENT_SHIFT (16) /* TX Identification Value */
+#define TX_IDENT_MASK (0xffff)
+#define RTL_VER_SHIFT (11) /* RTL Version Value */
+#define RTL_VER_MASK (0x1f)
+#define MAJOR_VER_SHIFT (8) /* Major Version Value */
+#define MAJOR_VER_MASK (0x7)
+#define MINOR_VER_SHIFT (0) /* Minor Version Value */
+#define MINOR_VER_MASK (0xff)
+
+/* Bit definitions for the CONTROL register */
+#define HW4_TS_PUSH_EN (1<<11) /* Hardware push 4 enable */
+#define HW3_TS_PUSH_EN (1<<10) /* Hardware push 3 enable */
+#define HW2_TS_PUSH_EN (1<<9) /* Hardware push 2 enable */
+#define HW1_TS_PUSH_EN (1<<8) /* Hardware push 1 enable */
+#define INT_TEST (1<<1) /* Interrupt Test */
+#define CPTS_EN (1<<0) /* Time Sync Enable */
+
+/*
+ * Definitions for the single bit resisters:
+ * TS_PUSH TS_LOAD_EN INTSTAT_RAW INTSTAT_MASKED INT_ENABLE EVENT_POP
+ */
+#define TS_PUSH (1<<0) /* Time stamp event push */
+#define TS_LOAD_EN (1<<0) /* Time Stamp Load */
+#define TS_PEND_RAW (1<<0) /* int read (before enable) */
+#define TS_PEND (1<<0) /* masked interrupt read (after enable) */
+#define TS_PEND_EN (1<<0) /* masked interrupt enable */
+#define EVENT_POP (1<<0) /* writing discards one event */
+
+/* Bit definitions for the EVENT_HIGH register */
+#define PORT_NUMBER_SHIFT (24) /* Indicates Ethernet port or HW pin */
+#define PORT_NUMBER_MASK (0x1f)
+#define EVENT_TYPE_SHIFT (20) /* Time sync event type */
+#define EVENT_TYPE_MASK (0xf)
+#define MESSAGE_TYPE_SHIFT (16) /* PTP message type */
+#define MESSAGE_TYPE_MASK (0xf)
+#define SEQUENCE_ID_SHIFT (0) /* PTP message sequence ID */
+#define SEQUENCE_ID_MASK (0xffff)
+
+enum {
+ CPTS_EV_PUSH, /* Time Stamp Push Event */
+ CPTS_EV_ROLL, /* Time Stamp Rollover Event */
+ CPTS_EV_HALF, /* Time Stamp Half Rollover Event */
+ CPTS_EV_HW, /* Hardware Time Stamp Push Event */
+ CPTS_EV_RX, /* Ethernet Receive Event */
+ CPTS_EV_TX, /* Ethernet Transmit Event */
+};
+
+/* This covers any input clock up to about 500 MHz. */
+#define CPTS_OVERFLOW_PERIOD (HZ * 8)
+
+#define CPTS_FIFO_DEPTH 16
+#define CPTS_MAX_EVENTS 32
+
+struct cpts_event {
+ struct list_head list;
+ unsigned long tmo;
+ u32 high;
+ u32 low;
+};
+
+struct cpts {
+ struct cpsw_cpts __iomem *reg;
+ int tx_enable;
+ int rx_enable;
+#ifdef CONFIG_TI_CPTS
+ struct ptp_clock_info info;
+ struct ptp_clock *clock;
+ spinlock_t lock; /* protects time registers */
+ u32 cc_mult; /* for the nominal frequency */
+ struct cyclecounter cc;
+ struct timecounter tc;
+ struct delayed_work overflow_work;
+ int phc_index;
+ struct clk *refclk;
+ unsigned long freq;
+ struct list_head events;
+ struct list_head pool;
+ struct cpts_event pool_data[CPTS_MAX_EVENTS];
+#endif
+};
+
+#ifdef CONFIG_TI_CPTS
+extern void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb);
+extern void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb);
+#else
+static inline void cpts_rx_timestamp(struct cpts *cpts, struct sk_buff *skb)
+{
+}
+static inline void cpts_tx_timestamp(struct cpts *cpts, struct sk_buff *skb)
+{
+}
+#endif
+
+extern int cpts_register(struct device *dev, struct cpts *cpts,
+ u32 mult, u32 shift);
+extern void cpts_unregister(struct cpts *cpts);
+
+#endif
return err;
}
-struct rtnl_link_stats64*
+static struct rtnl_link_stats64*
ppp_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats64)
{
struct ppp *ppp = netdev_priv(dev);
unsigned char addr[FLT_EXACT_COUNT][ETH_ALEN];
};
+/* 1024 is probably a high enough limit: modern hypervisors seem to support on
+ * the order of 100-200 CPUs so this leaves us some breathing space if we want
+ * to match a queue per guest CPU.
+ */
+#define MAX_TAP_QUEUES 1024
+
+#define TUN_FLOW_EXPIRE (3 * HZ)
+
+/* A tun_file connects an open character device to a tuntap netdevice. It
+ * also contains all socket related strctures (except sock_fprog and tap_filter)
+ * to serve as one transmit queue for tuntap device. The sock_fprog and
+ * tap_filter were kept in tun_struct since they were used for filtering for the
+ * netdevice not for a specific queue (at least I didn't see the reqirement for
+ * this).
+ *
+ * RCU usage:
+ * The tun_file and tun_struct are loosely coupled, the pointer from on to the
+ * other can only be read while rcu_read_lock or rtnl_lock is held.
+ */
struct tun_file {
- atomic_t count;
- struct tun_struct *tun;
+ struct sock sk;
+ struct socket socket;
+ struct socket_wq wq;
+ struct tun_struct __rcu *tun;
struct net *net;
+ struct fasync_struct *fasync;
+ /* only used for fasnyc */
+ unsigned int flags;
+ u16 queue_index;
+};
+
+struct tun_flow_entry {
+ struct hlist_node hash_link;
+ struct rcu_head rcu;
+ struct tun_struct *tun;
+
+ u32 rxhash;
+ int queue_index;
+ unsigned long updated;
};
-struct tun_sock;
+#define TUN_NUM_FLOW_ENTRIES 1024
+/* Since the socket were moved to tun_file, to preserve the behavior of persist
+ * device, socket fileter, sndbuf and vnet header size were restore when the
+ * file were attached to a persist device.
+ */
struct tun_struct {
- struct tun_file *tfile;
+ struct tun_file __rcu *tfiles[MAX_TAP_QUEUES];
+ unsigned int numqueues;
unsigned int flags;
kuid_t owner;
kgid_t group;
netdev_features_t set_features;
#define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
NETIF_F_TSO6|NETIF_F_UFO)
- struct fasync_struct *fasync;
-
- struct tap_filter txflt;
- struct socket socket;
- struct socket_wq wq;
int vnet_hdr_sz;
-
+ int sndbuf;
+ struct tap_filter txflt;
+ struct sock_fprog fprog;
+ /* protected by rtnl lock */
+ bool filter_attached;
#ifdef TUN_DEBUG
int debug;
#endif
+ spinlock_t lock;
+ struct kmem_cache *flow_cache;
+ struct hlist_head flows[TUN_NUM_FLOW_ENTRIES];
+ struct timer_list flow_gc_timer;
+ unsigned long ageing_time;
};
-struct tun_sock {
- struct sock sk;
- struct tun_struct *tun;
-};
+static inline u32 tun_hashfn(u32 rxhash)
+{
+ return rxhash & 0x3ff;
+}
-static inline struct tun_sock *tun_sk(struct sock *sk)
+static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash)
{
- return container_of(sk, struct tun_sock, sk);
+ struct tun_flow_entry *e;
+ struct hlist_node *n;
+
+ hlist_for_each_entry_rcu(e, n, head, hash_link) {
+ if (e->rxhash == rxhash)
+ return e;
+ }
+ return NULL;
}
-static int tun_attach(struct tun_struct *tun, struct file *file)
+static struct tun_flow_entry *tun_flow_create(struct tun_struct *tun,
+ struct hlist_head *head,
+ u32 rxhash, u16 queue_index)
{
- struct tun_file *tfile = file->private_data;
- int err;
+ struct tun_flow_entry *e = kmem_cache_alloc(tun->flow_cache,
+ GFP_ATOMIC);
+ if (e) {
+ tun_debug(KERN_INFO, tun, "create flow: hash %u index %u\n",
+ rxhash, queue_index);
+ e->updated = jiffies;
+ e->rxhash = rxhash;
+ e->queue_index = queue_index;
+ e->tun = tun;
+ hlist_add_head_rcu(&e->hash_link, head);
+ }
+ return e;
+}
- ASSERT_RTNL();
+static void tun_flow_free(struct rcu_head *head)
+{
+ struct tun_flow_entry *e
+ = container_of(head, struct tun_flow_entry, rcu);
+ kmem_cache_free(e->tun->flow_cache, e);
+}
- netif_tx_lock_bh(tun->dev);
+static void tun_flow_delete(struct tun_struct *tun, struct tun_flow_entry *e)
+{
+ tun_debug(KERN_INFO, tun, "delete flow: hash %u index %u\n",
+ e->rxhash, e->queue_index);
+ hlist_del_rcu(&e->hash_link);
+ call_rcu(&e->rcu, tun_flow_free);
+}
- err = -EINVAL;
- if (tfile->tun)
- goto out;
+static void tun_flow_flush(struct tun_struct *tun)
+{
+ int i;
- err = -EBUSY;
- if (tun->tfile)
- goto out;
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
- err = 0;
- tfile->tun = tun;
- tun->tfile = tfile;
- tun->socket.file = file;
- netif_carrier_on(tun->dev);
- dev_hold(tun->dev);
- sock_hold(tun->socket.sk);
- atomic_inc(&tfile->count);
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link)
+ tun_flow_delete(tun, e);
+ }
+ spin_unlock_bh(&tun->lock);
+}
-out:
- netif_tx_unlock_bh(tun->dev);
- return err;
+static void tun_flow_delete_by_queue(struct tun_struct *tun, u16 queue_index)
+{
+ int i;
+
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
+
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) {
+ if (e->queue_index == queue_index)
+ tun_flow_delete(tun, e);
+ }
+ }
+ spin_unlock_bh(&tun->lock);
}
-static void __tun_detach(struct tun_struct *tun)
+static void tun_flow_cleanup(unsigned long data)
{
- /* Detach from net device */
- netif_tx_lock_bh(tun->dev);
- netif_carrier_off(tun->dev);
- tun->tfile = NULL;
- netif_tx_unlock_bh(tun->dev);
+ struct tun_struct *tun = (struct tun_struct *)data;
+ unsigned long delay = tun->ageing_time;
+ unsigned long next_timer = jiffies + delay;
+ unsigned long count = 0;
+ int i;
- /* Drop read queue */
- skb_queue_purge(&tun->socket.sk->sk_receive_queue);
+ tun_debug(KERN_INFO, tun, "tun_flow_cleanup\n");
+
+ spin_lock_bh(&tun->lock);
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++) {
+ struct tun_flow_entry *e;
+ struct hlist_node *h, *n;
+
+ hlist_for_each_entry_safe(e, h, n, &tun->flows[i], hash_link) {
+ unsigned long this_timer;
+ count++;
+ this_timer = e->updated + delay;
+ if (time_before_eq(this_timer, jiffies))
+ tun_flow_delete(tun, e);
+ else if (time_before(this_timer, next_timer))
+ next_timer = this_timer;
+ }
+ }
- /* Drop the extra count on the net device */
- dev_put(tun->dev);
+ if (count)
+ mod_timer(&tun->flow_gc_timer, round_jiffies_up(next_timer));
+ spin_unlock_bh(&tun->lock);
}
-static void tun_detach(struct tun_struct *tun)
+static void tun_flow_update(struct tun_struct *tun, struct sk_buff *skb,
+ u16 queue_index)
+{
+ struct hlist_head *head;
+ struct tun_flow_entry *e;
+ unsigned long delay = tun->ageing_time;
+ u32 rxhash = skb_get_rxhash(skb);
+
+ if (!rxhash)
+ return;
+ else
+ head = &tun->flows[tun_hashfn(rxhash)];
+
+ rcu_read_lock();
+
+ if (tun->numqueues == 1)
+ goto unlock;
+
+ e = tun_flow_find(head, rxhash);
+ if (likely(e)) {
+ /* TODO: keep queueing to old queue until it's empty? */
+ e->queue_index = queue_index;
+ e->updated = jiffies;
+ } else {
+ spin_lock_bh(&tun->lock);
+ if (!tun_flow_find(head, rxhash))
+ tun_flow_create(tun, head, rxhash, queue_index);
+
+ if (!timer_pending(&tun->flow_gc_timer))
+ mod_timer(&tun->flow_gc_timer,
+ round_jiffies_up(jiffies + delay));
+ spin_unlock_bh(&tun->lock);
+ }
+
+unlock:
+ rcu_read_unlock();
+}
+
+/* We try to identify a flow through its rxhash first. The reason that
+ * we do not check rxq no. is becuase some cards(e.g 82599), chooses
+ * the rxq based on the txq where the last packet of the flow comes. As
+ * the userspace application move between processors, we may get a
+ * different rxq no. here. If we could not get rxhash, then we would
+ * hope the rxq no. may help here.
+ */
+static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ struct tun_flow_entry *e;
+ u32 txq = 0;
+ u32 numqueues = 0;
+
+ rcu_read_lock();
+ numqueues = tun->numqueues;
+
+ txq = skb_get_rxhash(skb);
+ if (txq) {
+ e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
+ if (e)
+ txq = e->queue_index;
+ else
+ /* use multiply and shift instead of expensive divide */
+ txq = ((u64)txq * numqueues) >> 32;
+ } else if (likely(skb_rx_queue_recorded(skb))) {
+ txq = skb_get_rx_queue(skb);
+ while (unlikely(txq >= numqueues))
+ txq -= numqueues;
+ }
+
+ rcu_read_unlock();
+ return txq;
+}
+
+static inline bool tun_not_capable(struct tun_struct *tun)
+{
+ const struct cred *cred = current_cred();
+
+ return ((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
+ (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
+ !capable(CAP_NET_ADMIN);
+}
+
+static void tun_set_real_num_queues(struct tun_struct *tun)
+{
+ netif_set_real_num_tx_queues(tun->dev, tun->numqueues);
+ netif_set_real_num_rx_queues(tun->dev, tun->numqueues);
+}
+
+static void __tun_detach(struct tun_file *tfile, bool clean)
+{
+ struct tun_file *ntfile;
+ struct tun_struct *tun;
+ struct net_device *dev;
+
+ tun = rcu_dereference_protected(tfile->tun,
+ lockdep_rtnl_is_held());
+ if (tun) {
+ u16 index = tfile->queue_index;
+ BUG_ON(index >= tun->numqueues);
+ dev = tun->dev;
+
+ rcu_assign_pointer(tun->tfiles[index],
+ tun->tfiles[tun->numqueues - 1]);
+ rcu_assign_pointer(tfile->tun, NULL);
+ ntfile = rcu_dereference_protected(tun->tfiles[index],
+ lockdep_rtnl_is_held());
+ ntfile->queue_index = index;
+
+ --tun->numqueues;
+ sock_put(&tfile->sk);
+
+ synchronize_net();
+ tun_flow_delete_by_queue(tun, tun->numqueues + 1);
+ /* Drop read queue */
+ skb_queue_purge(&tfile->sk.sk_receive_queue);
+ tun_set_real_num_queues(tun);
+
+ if (tun->numqueues == 0 && !(tun->flags & TUN_PERSIST))
+ if (dev->reg_state == NETREG_REGISTERED)
+ unregister_netdevice(dev);
+ }
+
+ if (clean) {
+ BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED,
+ &tfile->socket.flags));
+ sk_release_kernel(&tfile->sk);
+ }
+}
+
+static void tun_detach(struct tun_file *tfile, bool clean)
{
rtnl_lock();
- __tun_detach(tun);
+ __tun_detach(tfile, clean);
rtnl_unlock();
}
+static void tun_detach_all(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+ struct tun_file *tfile;
+ int i, n = tun->numqueues;
+
+ for (i = 0; i < n; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_rtnl_is_held());
+ BUG_ON(!tfile);
+ wake_up_all(&tfile->wq.wait);
+ rcu_assign_pointer(tfile->tun, NULL);
+ --tun->numqueues;
+ }
+ BUG_ON(tun->numqueues != 0);
+
+ synchronize_net();
+ for (i = 0; i < n; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_rtnl_is_held());
+ /* Drop read queue */
+ skb_queue_purge(&tfile->sk.sk_receive_queue);
+ sock_put(&tfile->sk);
+ }
+}
+
+static int tun_attach(struct tun_struct *tun, struct file *file)
+{
+ struct tun_file *tfile = file->private_data;
+ int err;
+
+ err = -EINVAL;
+ if (rcu_dereference_protected(tfile->tun, lockdep_rtnl_is_held()))
+ goto out;
+
+ err = -EBUSY;
+ if (!(tun->flags & TUN_TAP_MQ) && tun->numqueues == 1)
+ goto out;
+
+ err = -E2BIG;
+ if (tun->numqueues == MAX_TAP_QUEUES)
+ goto out;
+
+ err = 0;
+
+ /* Re-attach the filter to presist device */
+ if (tun->filter_attached == true) {
+ err = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+ if (!err)
+ goto out;
+ }
+ tfile->queue_index = tun->numqueues;
+ rcu_assign_pointer(tfile->tun, tun);
+ rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile);
+ sock_hold(&tfile->sk);
+ tun->numqueues++;
+
+ tun_set_real_num_queues(tun);
+
+ if (tun->numqueues == 1)
+ netif_carrier_on(tun->dev);
+
+ /* device is allowed to go away first, so no need to hold extra
+ * refcnt.
+ */
+
+out:
+ return err;
+}
+
static struct tun_struct *__tun_get(struct tun_file *tfile)
{
- struct tun_struct *tun = NULL;
+ struct tun_struct *tun;
- if (atomic_inc_not_zero(&tfile->count))
- tun = tfile->tun;
+ rcu_read_lock();
+ tun = rcu_dereference(tfile->tun);
+ if (tun)
+ dev_hold(tun->dev);
+ rcu_read_unlock();
return tun;
}
static void tun_put(struct tun_struct *tun)
{
- struct tun_file *tfile = tun->tfile;
-
- if (atomic_dec_and_test(&tfile->count))
- tun_detach(tfile->tun);
+ dev_put(tun->dev);
}
/* TAP filtering */
/* Net device detach from fd. */
static void tun_net_uninit(struct net_device *dev)
{
- struct tun_struct *tun = netdev_priv(dev);
- struct tun_file *tfile = tun->tfile;
-
- /* Inform the methods they need to stop using the dev.
- */
- if (tfile) {
- wake_up_all(&tun->wq.wait);
- if (atomic_dec_and_test(&tfile->count))
- __tun_detach(tun);
- }
-}
-
-static void tun_free_netdev(struct net_device *dev)
-{
- struct tun_struct *tun = netdev_priv(dev);
-
- BUG_ON(!test_bit(SOCK_EXTERNALLY_ALLOCATED, &tun->socket.flags));
-
- sk_release_kernel(tun->socket.sk);
+ tun_detach_all(dev);
}
/* Net device open. */
static int tun_net_open(struct net_device *dev)
{
- netif_start_queue(dev);
+ netif_tx_start_all_queues(dev);
return 0;
}
/* Net device close. */
static int tun_net_close(struct net_device *dev)
{
- netif_stop_queue(dev);
+ netif_tx_stop_all_queues(dev);
return 0;
}
static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
+ int txq = skb->queue_mapping;
+ struct tun_file *tfile;
- tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
+ rcu_read_lock();
+ tfile = rcu_dereference(tun->tfiles[txq]);
/* Drop packet if interface is not attached */
- if (!tun->tfile)
+ if (txq >= tun->numqueues)
goto drop;
+ tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);
+
+ BUG_ON(!tfile);
+
/* Drop if the filter does not like it.
* This is a noop if the filter is disabled.
* Filter can be enabled only for the TAP devices. */
if (!check_filter(&tun->txflt, skb))
goto drop;
- if (tun->socket.sk->sk_filter &&
- sk_filter(tun->socket.sk, skb))
+ if (tfile->socket.sk->sk_filter &&
+ sk_filter(tfile->socket.sk, skb))
goto drop;
- if (skb_queue_len(&tun->socket.sk->sk_receive_queue) >= dev->tx_queue_len) {
+ /* Limit the number of packets queued by divining txq length with the
+ * number of queues.
+ */
+ if (skb_queue_len(&tfile->socket.sk->sk_receive_queue)
+ >= dev->tx_queue_len / tun->numqueues){
if (!(tun->flags & TUN_ONE_QUEUE)) {
/* Normal queueing mode. */
/* Packet scheduler handles dropping of further packets. */
- netif_stop_queue(dev);
+ netif_stop_subqueue(dev, txq);
/* We won't see all dropped packets individually, so overrun
* error is more appropriate. */
skb_orphan(skb);
/* Enqueue packet */
- skb_queue_tail(&tun->socket.sk->sk_receive_queue, skb);
+ skb_queue_tail(&tfile->socket.sk->sk_receive_queue, skb);
/* Notify and wake up reader process */
- if (tun->flags & TUN_FASYNC)
- kill_fasync(&tun->fasync, SIGIO, POLL_IN);
- wake_up_interruptible_poll(&tun->wq.wait, POLLIN |
+ if (tfile->flags & TUN_FASYNC)
+ kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
+ wake_up_interruptible_poll(&tfile->wq.wait, POLLIN |
POLLRDNORM | POLLRDBAND);
+
+ rcu_read_unlock();
return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
kfree_skb(skb);
+ rcu_read_unlock();
return NETDEV_TX_OK;
}
.ndo_start_xmit = tun_net_xmit,
.ndo_change_mtu = tun_net_change_mtu,
.ndo_fix_features = tun_net_fix_features,
+ .ndo_select_queue = tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = tun_poll_controller,
#endif
.ndo_set_rx_mode = tun_net_mclist,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
+ .ndo_select_queue = tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = tun_poll_controller,
#endif
};
+static int tun_flow_init(struct tun_struct *tun)
+{
+ int i;
+
+ tun->flow_cache = kmem_cache_create("tun_flow_cache",
+ sizeof(struct tun_flow_entry), 0, 0,
+ NULL);
+ if (!tun->flow_cache)
+ return -ENOMEM;
+
+ for (i = 0; i < TUN_NUM_FLOW_ENTRIES; i++)
+ INIT_HLIST_HEAD(&tun->flows[i]);
+
+ tun->ageing_time = TUN_FLOW_EXPIRE;
+ setup_timer(&tun->flow_gc_timer, tun_flow_cleanup, (unsigned long)tun);
+ mod_timer(&tun->flow_gc_timer,
+ round_jiffies_up(jiffies + tun->ageing_time));
+
+ return 0;
+}
+
+static void tun_flow_uninit(struct tun_struct *tun)
+{
+ del_timer_sync(&tun->flow_gc_timer);
+ tun_flow_flush(tun);
+
+ /* Wait for completion of call_rcu()'s */
+ rcu_barrier();
+ kmem_cache_destroy(tun->flow_cache);
+}
+
/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
/* Character device part */
/* Poll */
-static unsigned int tun_chr_poll(struct file *file, poll_table * wait)
+static unsigned int tun_chr_poll(struct file *file, poll_table *wait)
{
struct tun_file *tfile = file->private_data;
struct tun_struct *tun = __tun_get(tfile);
if (!tun)
return POLLERR;
- sk = tun->socket.sk;
+ sk = tfile->socket.sk;
tun_debug(KERN_INFO, tun, "tun_chr_poll\n");
- poll_wait(file, &tun->wq.wait, wait);
+ poll_wait(file, &tfile->wq.wait, wait);
if (!skb_queue_empty(&sk->sk_receive_queue))
mask |= POLLIN | POLLRDNORM;
/* prepad is the amount to reserve at front. len is length after that.
* linear is a hint as to how much to copy (usually headers). */
-static struct sk_buff *tun_alloc_skb(struct tun_struct *tun,
+static struct sk_buff *tun_alloc_skb(struct tun_file *tfile,
size_t prepad, size_t len,
size_t linear, int noblock)
{
- struct sock *sk = tun->socket.sk;
+ struct sock *sk = tfile->socket.sk;
struct sk_buff *skb;
int err;
}
/* Get packet from user space buffer */
-static ssize_t tun_get_user(struct tun_struct *tun, void *msg_control,
- const struct iovec *iv, size_t total_len,
- size_t count, int noblock)
+static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
+ void *msg_control, const struct iovec *iv,
+ size_t total_len, size_t count, int noblock)
{
struct tun_pi pi = { 0, cpu_to_be16(ETH_P_IP) };
struct sk_buff *skb;
} else
copylen = len;
- skb = tun_alloc_skb(tun, align, copylen, gso.hdr_len, noblock);
+ skb = tun_alloc_skb(tfile, align, copylen, gso.hdr_len, noblock);
if (IS_ERR(skb)) {
if (PTR_ERR(skb) != -EAGAIN)
tun->dev->stats.rx_dropped++;
tun->dev->stats.rx_packets++;
tun->dev->stats.rx_bytes += len;
+ tun_flow_update(tun, skb, tfile->queue_index);
return total_len;
}
{
struct file *file = iocb->ki_filp;
struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
ssize_t result;
if (!tun)
tun_debug(KERN_INFO, tun, "tun_chr_write %ld\n", count);
- result = tun_get_user(tun, NULL, iv, iov_length(iv, count), count,
- file->f_flags & O_NONBLOCK);
+ result = tun_get_user(tun, tfile, NULL, iv, iov_length(iv, count),
+ count, file->f_flags & O_NONBLOCK);
tun_put(tun);
return result;
/* Put packet to the user space buffer */
static ssize_t tun_put_user(struct tun_struct *tun,
+ struct tun_file *tfile,
struct sk_buff *skb,
const struct iovec *iv, int len)
{
return total;
}
-static ssize_t tun_do_read(struct tun_struct *tun,
+static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
struct kiocb *iocb, const struct iovec *iv,
ssize_t len, int noblock)
{
tun_debug(KERN_INFO, tun, "tun_chr_read\n");
if (unlikely(!noblock))
- add_wait_queue(&tun->wq.wait, &wait);
+ add_wait_queue(&tfile->wq.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
- if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
+ if (!(skb = skb_dequeue(&tfile->socket.sk->sk_receive_queue))) {
if (noblock) {
ret = -EAGAIN;
break;
schedule();
continue;
}
- netif_wake_queue(tun->dev);
+ netif_wake_subqueue(tun->dev, tfile->queue_index);
- ret = tun_put_user(tun, skb, iv, len);
+ ret = tun_put_user(tun, tfile, skb, iv, len);
kfree_skb(skb);
break;
}
current->state = TASK_RUNNING;
if (unlikely(!noblock))
- remove_wait_queue(&tun->wq.wait, &wait);
+ remove_wait_queue(&tfile->wq.wait, &wait);
return ret;
}
goto out;
}
- ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = tun_do_read(tun, tfile, iocb, iv, len,
+ file->f_flags & O_NONBLOCK);
ret = min_t(ssize_t, ret, len);
out:
tun_put(tun);
return ret;
}
+static void tun_free_netdev(struct net_device *dev)
+{
+ struct tun_struct *tun = netdev_priv(dev);
+
+ tun_flow_uninit(tun);
+ free_netdev(dev);
+}
+
static void tun_setup(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
static void tun_sock_write_space(struct sock *sk)
{
- struct tun_struct *tun;
+ struct tun_file *tfile;
wait_queue_head_t *wqueue;
if (!sock_writeable(sk))
wake_up_interruptible_sync_poll(wqueue, POLLOUT |
POLLWRNORM | POLLWRBAND);
- tun = tun_sk(sk)->tun;
- kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
-}
-
-static void tun_sock_destruct(struct sock *sk)
-{
- free_netdev(tun_sk(sk)->tun->dev);
+ tfile = container_of(sk, struct tun_file, sk);
+ kill_fasync(&tfile->fasync, SIGIO, POLL_OUT);
}
static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
- return tun_get_user(tun, m->msg_control, m->msg_iov, total_len,
- m->msg_iovlen, m->msg_flags & MSG_DONTWAIT);
+ int ret;
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+ struct tun_struct *tun = __tun_get(tfile);
+
+ if (!tun)
+ return -EBADFD;
+ ret = tun_get_user(tun, tfile, m->msg_control, m->msg_iov, total_len,
+ m->msg_iovlen, m->msg_flags & MSG_DONTWAIT);
+ tun_put(tun);
+ return ret;
}
+
static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *m, size_t total_len,
int flags)
{
- struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ struct tun_file *tfile = container_of(sock, struct tun_file, socket);
+ struct tun_struct *tun = __tun_get(tfile);
int ret;
+
+ if (!tun)
+ return -EBADFD;
+
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
return -EINVAL;
- ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+ ret = tun_do_read(tun, tfile, iocb, m->msg_iov, total_len,
flags & MSG_DONTWAIT);
if (ret > total_len) {
m->msg_flags |= MSG_TRUNC;
ret = flags & MSG_TRUNC ? ret : total_len;
}
+ tun_put(tun);
return ret;
}
static struct proto tun_proto = {
.name = "tun",
.owner = THIS_MODULE,
- .obj_size = sizeof(struct tun_sock),
+ .obj_size = sizeof(struct tun_file),
};
static int tun_flags(struct tun_struct *tun)
if (tun->flags & TUN_VNET_HDR)
flags |= IFF_VNET_HDR;
+ if (tun->flags & TUN_TAP_MQ)
+ flags |= IFF_MULTI_QUEUE;
+
return flags;
}
static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
{
- struct sock *sk;
struct tun_struct *tun;
+ struct tun_file *tfile = file->private_data;
struct net_device *dev;
int err;
dev = __dev_get_by_name(net, ifr->ifr_name);
if (dev) {
- const struct cred *cred = current_cred();
-
if (ifr->ifr_flags & IFF_TUN_EXCL)
return -EBUSY;
if ((ifr->ifr_flags & IFF_TUN) && dev->netdev_ops == &tun_netdev_ops)
else
return -EINVAL;
- if (((uid_valid(tun->owner) && !uid_eq(cred->euid, tun->owner)) ||
- (gid_valid(tun->group) && !in_egroup_p(tun->group))) &&
- !capable(CAP_NET_ADMIN))
+ if (tun_not_capable(tun))
return -EPERM;
- err = security_tun_dev_attach(tun->socket.sk);
+ err = security_tun_dev_attach(tfile->socket.sk);
if (err < 0)
return err;
if (*ifr->ifr_name)
name = ifr->ifr_name;
- dev = alloc_netdev(sizeof(struct tun_struct), name,
- tun_setup);
+ dev = alloc_netdev_mqs(sizeof(struct tun_struct), name,
+ tun_setup,
+ MAX_TAP_QUEUES, MAX_TAP_QUEUES);
if (!dev)
return -ENOMEM;
tun->flags = flags;
tun->txflt.count = 0;
tun->vnet_hdr_sz = sizeof(struct virtio_net_hdr);
- set_bit(SOCK_EXTERNALLY_ALLOCATED, &tun->socket.flags);
-
- err = -ENOMEM;
- sk = sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL, &tun_proto);
- if (!sk)
- goto err_free_dev;
- sk_change_net(sk, net);
- tun->socket.wq = &tun->wq;
- init_waitqueue_head(&tun->wq.wait);
- tun->socket.ops = &tun_socket_ops;
- sock_init_data(&tun->socket, sk);
- sk->sk_write_space = tun_sock_write_space;
- sk->sk_sndbuf = INT_MAX;
- sock_set_flag(sk, SOCK_ZEROCOPY);
+ tun->filter_attached = false;
+ tun->sndbuf = tfile->socket.sk->sk_sndbuf;
- tun_sk(sk)->tun = tun;
+ spin_lock_init(&tun->lock);
- security_tun_dev_post_create(sk);
+ security_tun_dev_post_create(&tfile->sk);
tun_net_init(dev);
+ if (tun_flow_init(tun))
+ goto err_free_dev;
+
dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST |
TUN_USER_FEATURES;
dev->features = dev->hw_features;
err = register_netdevice(tun->dev);
if (err < 0)
- goto err_free_sk;
+ goto err_free_dev;
if (device_create_file(&tun->dev->dev, &dev_attr_tun_flags) ||
device_create_file(&tun->dev->dev, &dev_attr_owner) ||
device_create_file(&tun->dev->dev, &dev_attr_group))
pr_err("Failed to create tun sysfs files\n");
- sk->sk_destruct = tun_sock_destruct;
-
err = tun_attach(tun, file);
if (err < 0)
- goto failed;
+ goto err_free_dev;
}
tun_debug(KERN_INFO, tun, "tun_set_iff\n");
else
tun->flags &= ~TUN_VNET_HDR;
+ if (ifr->ifr_flags & IFF_MULTI_QUEUE)
+ tun->flags |= TUN_TAP_MQ;
+ else
+ tun->flags &= ~TUN_TAP_MQ;
+
/* Make sure persistent devices do not get stuck in
* xoff state.
*/
if (netif_running(tun->dev))
- netif_wake_queue(tun->dev);
+ netif_tx_wake_all_queues(tun->dev);
strcpy(ifr->ifr_name, tun->dev->name);
return 0;
- err_free_sk:
- tun_free_netdev(dev);
err_free_dev:
free_netdev(dev);
- failed:
return err;
}
return 0;
}
+static void tun_detach_filter(struct tun_struct *tun, int n)
+{
+ int i;
+ struct tun_file *tfile;
+
+ for (i = 0; i < n; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_rtnl_is_held());
+ sk_detach_filter(tfile->socket.sk);
+ }
+
+ tun->filter_attached = false;
+}
+
+static int tun_attach_filter(struct tun_struct *tun)
+{
+ int i, ret = 0;
+ struct tun_file *tfile;
+
+ for (i = 0; i < tun->numqueues; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_rtnl_is_held());
+ ret = sk_attach_filter(&tun->fprog, tfile->socket.sk);
+ if (ret) {
+ tun_detach_filter(tun, i);
+ return ret;
+ }
+ }
+
+ tun->filter_attached = true;
+ return ret;
+}
+
+static void tun_set_sndbuf(struct tun_struct *tun)
+{
+ struct tun_file *tfile;
+ int i;
+
+ for (i = 0; i < tun->numqueues; i++) {
+ tfile = rcu_dereference_protected(tun->tfiles[i],
+ lockdep_rtnl_is_held());
+ tfile->socket.sk->sk_sndbuf = tun->sndbuf;
+ }
+}
+
+static int tun_set_queue(struct file *file, struct ifreq *ifr)
+{
+ struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun;
+ struct net_device *dev;
+ int ret = 0;
+
+ rtnl_lock();
+
+ if (ifr->ifr_flags & IFF_ATTACH_QUEUE) {
+ dev = __dev_get_by_name(tfile->net, ifr->ifr_name);
+ if (!dev) {
+ ret = -EINVAL;
+ goto unlock;
+ }
+
+ tun = netdev_priv(dev);
+ if (dev->netdev_ops != &tap_netdev_ops &&
+ dev->netdev_ops != &tun_netdev_ops)
+ ret = -EINVAL;
+ else if (tun_not_capable(tun))
+ ret = -EPERM;
+ else
+ ret = tun_attach(tun, file);
+ } else if (ifr->ifr_flags & IFF_DETACH_QUEUE)
+ __tun_detach(tfile, false);
+ else
+ ret = -EINVAL;
+
+unlock:
+ rtnl_unlock();
+ return ret;
+}
+
static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
unsigned long arg, int ifreq_len)
{
struct tun_file *tfile = file->private_data;
struct tun_struct *tun;
void __user* argp = (void __user*)arg;
- struct sock_fprog fprog;
struct ifreq ifr;
kuid_t owner;
kgid_t group;
int vnet_hdr_sz;
int ret;
- if (cmd == TUNSETIFF || _IOC_TYPE(cmd) == 0x89) {
+ if (cmd == TUNSETIFF || cmd == TUNSETQUEUE || _IOC_TYPE(cmd) == 0x89) {
if (copy_from_user(&ifr, argp, ifreq_len))
return -EFAULT;
} else {
* This is needed because we never checked for invalid flags on
* TUNSETIFF. */
return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE |
- IFF_VNET_HDR,
+ IFF_VNET_HDR | IFF_MULTI_QUEUE,
(unsigned int __user*)argp);
- }
+ } else if (cmd == TUNSETQUEUE)
+ return tun_set_queue(file, &ifr);
+ ret = 0;
rtnl_lock();
tun = __tun_get(tfile);
if (!tun)
goto unlock;
- tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %d\n", cmd);
+ tun_debug(KERN_INFO, tun, "tun_chr_ioctl cmd %u\n", cmd);
ret = 0;
switch (cmd) {
break;
case TUNSETPERSIST:
- /* Disable/Enable persist mode */
- if (arg)
+ /* Disable/Enable persist mode. Keep an extra reference to the
+ * module to prevent the module being unprobed.
+ */
+ if (arg) {
tun->flags |= TUN_PERSIST;
- else
+ __module_get(THIS_MODULE);
+ } else {
tun->flags &= ~TUN_PERSIST;
+ module_put(THIS_MODULE);
+ }
tun_debug(KERN_INFO, tun, "persist %s\n",
arg ? "enabled" : "disabled");
break;
}
tun->owner = owner;
- tun_debug(KERN_INFO, tun, "owner set to %d\n",
+ tun_debug(KERN_INFO, tun, "owner set to %u\n",
from_kuid(&init_user_ns, tun->owner));
break;
break;
}
tun->group = group;
- tun_debug(KERN_INFO, tun, "group set to %d\n",
+ tun_debug(KERN_INFO, tun, "group set to %u\n",
from_kgid(&init_user_ns, tun->group));
break;
break;
case TUNGETSNDBUF:
- sndbuf = tun->socket.sk->sk_sndbuf;
+ sndbuf = tfile->socket.sk->sk_sndbuf;
if (copy_to_user(argp, &sndbuf, sizeof(sndbuf)))
ret = -EFAULT;
break;
break;
}
- tun->socket.sk->sk_sndbuf = sndbuf;
+ tun->sndbuf = sndbuf;
+ tun_set_sndbuf(tun);
break;
case TUNGETVNETHDRSZ:
if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
ret = -EFAULT;
- if (copy_from_user(&fprog, argp, sizeof(fprog)))
+ if (copy_from_user(&tun->fprog, argp, sizeof(tun->fprog)))
break;
- ret = sk_attach_filter(&fprog, tun->socket.sk);
+ ret = tun_attach_filter(tun);
break;
case TUNDETACHFILTER:
ret = -EINVAL;
if ((tun->flags & TUN_TYPE_MASK) != TUN_TAP_DEV)
break;
- ret = sk_detach_filter(tun->socket.sk);
+ ret = 0;
+ tun_detach_filter(tun, tun->numqueues);
break;
default:
static int tun_chr_fasync(int fd, struct file *file, int on)
{
- struct tun_struct *tun = tun_get(file);
+ struct tun_file *tfile = file->private_data;
int ret;
- if (!tun)
- return -EBADFD;
-
- tun_debug(KERN_INFO, tun, "tun_chr_fasync %d\n", on);
-
- if ((ret = fasync_helper(fd, file, on, &tun->fasync)) < 0)
+ if ((ret = fasync_helper(fd, file, on, &tfile->fasync)) < 0)
goto out;
if (on) {
ret = __f_setown(file, task_pid(current), PIDTYPE_PID, 0);
if (ret)
goto out;
- tun->flags |= TUN_FASYNC;
+ tfile->flags |= TUN_FASYNC;
} else
- tun->flags &= ~TUN_FASYNC;
+ tfile->flags &= ~TUN_FASYNC;
ret = 0;
out:
- tun_put(tun);
return ret;
}
DBG1(KERN_INFO, "tunX: tun_chr_open\n");
- tfile = kmalloc(sizeof(*tfile), GFP_KERNEL);
+ tfile = (struct tun_file *)sk_alloc(&init_net, AF_UNSPEC, GFP_KERNEL,
+ &tun_proto);
if (!tfile)
return -ENOMEM;
- atomic_set(&tfile->count, 0);
- tfile->tun = NULL;
+ rcu_assign_pointer(tfile->tun, NULL);
tfile->net = get_net(current->nsproxy->net_ns);
+ tfile->flags = 0;
+
+ rcu_assign_pointer(tfile->socket.wq, &tfile->wq);
+ init_waitqueue_head(&tfile->wq.wait);
+
+ tfile->socket.file = file;
+ tfile->socket.ops = &tun_socket_ops;
+
+ sock_init_data(&tfile->socket, &tfile->sk);
+ sk_change_net(&tfile->sk, tfile->net);
+
+ tfile->sk.sk_write_space = tun_sock_write_space;
+ tfile->sk.sk_sndbuf = INT_MAX;
+
file->private_data = tfile;
+ set_bit(SOCK_EXTERNALLY_ALLOCATED, &tfile->socket.flags);
+
return 0;
}
static int tun_chr_close(struct inode *inode, struct file *file)
{
struct tun_file *tfile = file->private_data;
- struct tun_struct *tun;
+ struct net *net = tfile->net;
- tun = __tun_get(tfile);
- if (tun) {
- struct net_device *dev = tun->dev;
-
- tun_debug(KERN_INFO, tun, "tun_chr_close\n");
-
- __tun_detach(tun);
-
- /* If desirable, unregister the netdevice. */
- if (!(tun->flags & TUN_PERSIST)) {
- rtnl_lock();
- if (dev->reg_state == NETREG_REGISTERED)
- unregister_netdevice(dev);
- rtnl_unlock();
- }
- }
-
- tun = tfile->tun;
- if (tun)
- sock_put(tun->socket.sk);
-
- put_net(tfile->net);
- kfree(tfile);
+ tun_detach(tfile, true);
+ put_net(net);
return 0;
}
* holding a reference to the file for as long as the socket is in use. */
struct socket *tun_get_socket(struct file *file)
{
- struct tun_struct *tun;
+ struct tun_file *tfile;
if (file->f_op != &tun_fops)
return ERR_PTR(-EINVAL);
- tun = tun_get(file);
- if (!tun)
+ tfile = file->private_data;
+ if (!tfile)
return ERR_PTR(-EBADFD);
- tun_put(tun);
- return &tun->socket;
+ return &tfile->socket;
}
EXPORT_SYMBOL_GPL(tun_get_socket);
ether_setup(dev);
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
dev->netdev_ops = &veth_netdev_ops;
dev->ethtool_ops = &veth_ethtool_ops;
config PPS
tristate "PPS support"
- depends on EXPERIMENTAL
---help---
PPS (Pulse Per Second) is a special pulse provided by some GPS
antennae. Userland can use it to get a high-precision time
menu "PTP clock support"
-comment "Enable Device Drivers -> PPS to see the PTP clock options."
- depends on PPS=n
-
config PTP_1588_CLOCK
tristate "PTP clock support"
- depends on EXPERIMENTAL
- depends on PPS
+ select PPS
help
The IEEE 1588 standard defines a method to precisely
synchronize distributed clocks over Ethernet networks. The
config PTP_1588_CLOCK_GIANFAR
tristate "Freescale eTSEC as PTP clock"
- depends on PTP_1588_CLOCK
depends on GIANFAR
+ select PTP_1588_CLOCK
+ default y
help
This driver adds support for using the eTSEC as a PTP
clock. This clock is only useful if your PTP programs are
config PTP_1588_CLOCK_IXP46X
tristate "Intel IXP46x as PTP clock"
- depends on PTP_1588_CLOCK
depends on IXP4XX_ETH
+ select PTP_1588_CLOCK
+ default y
help
This driver adds support for using the IXP46X as a PTP
clock. This clock is only useful if your PTP programs are
will be called ptp_ixp46x.
comment "Enable PHYLIB and NETWORK_PHY_TIMESTAMPING to see the additional clocks."
- depends on PTP_1588_CLOCK && (PHYLIB=n || NETWORK_PHY_TIMESTAMPING=n)
+ depends on PHYLIB=n || NETWORK_PHY_TIMESTAMPING=n
config DP83640_PHY
tristate "Driver for the National Semiconductor DP83640 PHYTER"
- depends on PTP_1588_CLOCK
depends on NETWORK_PHY_TIMESTAMPING
depends on PHYLIB
+ select PTP_1588_CLOCK
---help---
Supports the DP83640 PHYTER with IEEE 1588 features.
config PTP_1588_CLOCK_PCH
tristate "Intel PCH EG20T as PTP clock"
- depends on PTP_1588_CLOCK
depends on PCH_GBE
+ select PTP_1588_CLOCK
+ default y
help
This driver adds support for using the PCH EG20T as a PTP
clock. The hardware supports time stamping of PTP packets
{
struct ptp_clock_caps caps;
struct ptp_clock_request req;
+ struct ptp_sys_offset sysoff;
struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
struct ptp_clock_info *ops = ptp->info;
+ struct ptp_clock_time *pct;
+ struct timespec ts;
int enable, err = 0;
+ unsigned int i;
switch (cmd) {
err = ops->enable(ops, &req, enable);
break;
+ case PTP_SYS_OFFSET:
+ if (copy_from_user(&sysoff, (void __user *)arg,
+ sizeof(sysoff))) {
+ err = -EFAULT;
+ break;
+ }
+ if (sysoff.n_samples > PTP_MAX_SAMPLES) {
+ err = -EINVAL;
+ break;
+ }
+ pct = &sysoff.ts[0];
+ for (i = 0; i < sysoff.n_samples; i++) {
+ getnstimeofday(&ts);
+ pct->sec = ts.tv_sec;
+ pct->nsec = ts.tv_nsec;
+ pct++;
+ ptp->info->gettime(ptp->info, &ts);
+ pct->sec = ts.tv_sec;
+ pct->nsec = ts.tv_nsec;
+ pct++;
+ }
+ getnstimeofday(&ts);
+ pct->sec = ts.tv_sec;
+ pct->nsec = ts.tv_nsec;
+ if (copy_to_user((void __user *)arg, &sysoff, sizeof(sysoff)))
+ err = -EFAULT;
+ break;
+
default:
err = -ENOTTY;
break;
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, unsigned int flen);
+extern int sk_get_filter(struct sock *sk, struct sock_filter __user *filter, unsigned len);
#ifdef CONFIG_BPF_JIT
extern void bpf_jit_compile(struct sk_filter *fp);
u32 slaves; /* number of slave cpgmac ports */
struct cpsw_slave_data *slave_data;
+ u32 cpts_active_slave; /* time stamping slave */
+ u32 cpts_clock_mult; /* convert input clock ticks to nanoseconds */
+ u32 cpts_clock_shift; /* convert input clock ticks to nanoseconds */
u32 ale_reg_ofs; /* address lookup engine reg offset */
u32 ale_entries; /* ale table size */
u32 host_port_num; /* The port number for the host port */
u32 hw_stats_reg_ofs; /* cpsw hardware statistics counters */
+ u32 cpts_reg_ofs; /* cpts registers */
u32 bd_ram_ofs; /* embedded buffer descriptor RAM offset*/
u32 bd_ram_size; /*buffer descriptor ram size */
+++ /dev/null
-/*
- * Utility code which helps transforming between two different time
- * bases, called "source" and "target" time in this code.
- *
- * Source time has to be provided via the timecounter API while target
- * time is accessed via a function callback whose prototype
- * intentionally matches ktime_get() and ktime_get_real(). These
- * interfaces where chosen like this so that the code serves its
- * initial purpose without additional glue code.
- *
- * This purpose is synchronizing a hardware clock in a NIC with system
- * time, in order to implement the Precision Time Protocol (PTP,
- * IEEE1588) with more accurate hardware assisted time stamping. In
- * that context only synchronization against system time (=
- * ktime_get_real()) is currently needed. But this utility code might
- * become useful in other situations, which is why it was written as
- * general purpose utility code.
- *
- * The source timecounter is assumed to return monotonically
- * increasing time (but this code does its best to compensate if that
- * is not the case) whereas target time may jump.
- *
- * The target time corresponding to a source time is determined by
- * reading target time, reading source time, reading target time
- * again, then assuming that average target time corresponds to source
- * time. In other words, the assumption is that reading the source
- * time is slow and involves equal time for sending the request and
- * receiving the reply, whereas reading target time is assumed to be
- * fast.
- *
- * Copyright (C) 2009 Intel Corporation.
- * Author: Patrick Ohly <patrick.ohly@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
- */
-#ifndef _LINUX_TIMECOMPARE_H
-#define _LINUX_TIMECOMPARE_H
-
-#include <linux/clocksource.h>
-#include <linux/ktime.h>
-
-/**
- * struct timecompare - stores state and configuration for the two clocks
- *
- * Initialize to zero, then set source/target/num_samples.
- *
- * Transformation between source time and target time is done with:
- * target_time = source_time + offset +
- * (source_time - last_update) * skew /
- * TIMECOMPARE_SKEW_RESOLUTION
- *
- * @source: used to get source time stamps via timecounter_read()
- * @target: function returning target time (for example, ktime_get
- * for monotonic time, or ktime_get_real for wall clock)
- * @num_samples: number of times that source time and target time are to
- * be compared when determining their offset
- * @offset: (target time - source time) at the time of the last update
- * @skew: average (target time - source time) / delta source time *
- * TIMECOMPARE_SKEW_RESOLUTION
- * @last_update: last source time stamp when time offset was measured
- */
-struct timecompare {
- struct timecounter *source;
- ktime_t (*target)(void);
- int num_samples;
-
- s64 offset;
- s64 skew;
- u64 last_update;
-};
-
-/**
- * timecompare_transform - transform source time stamp into target time base
- * @sync: context for time sync
- * @source_tstamp: the result of timecounter_read() or
- * timecounter_cyc2time()
- */
-extern ktime_t timecompare_transform(struct timecompare *sync,
- u64 source_tstamp);
-
-/**
- * timecompare_offset - measure current (target time - source time) offset
- * @sync: context for time sync
- * @offset: average offset during sample period returned here
- * @source_tstamp: average source time during sample period returned here
- *
- * Returns number of samples used. Might be zero (= no result) in the
- * unlikely case that target time was monotonically decreasing for all
- * samples (= broken).
- */
-extern int timecompare_offset(struct timecompare *sync,
- s64 *offset,
- u64 *source_tstamp);
-
-extern void __timecompare_update(struct timecompare *sync,
- u64 source_tstamp);
-
-/**
- * timecompare_update - update offset and skew by measuring current offset
- * @sync: context for time sync
- * @source_tstamp: the result of timecounter_read() or
- * timecounter_cyc2time(), pass zero to force update
- *
- * Updates are only done at most once per second.
- */
-static inline void timecompare_update(struct timecompare *sync,
- u64 source_tstamp)
-{
- if (!source_tstamp ||
- (s64)(source_tstamp - sync->last_update) >= NSEC_PER_SEC)
- __timecompare_update(sync, source_tstamp);
-}
-
-#endif /* _LINUX_TIMECOMPARE_H */
/* Socket filtering */
#define SO_ATTACH_FILTER 26
#define SO_DETACH_FILTER 27
+#define SO_GET_FILTER SO_ATTACH_FILTER
#define SO_PEERNAME 28
#define SO_TIMESTAMP 29
#define TUN_ONE_QUEUE 0x0080
#define TUN_PERSIST 0x0100
#define TUN_VNET_HDR 0x0200
+#define TUN_TAP_MQ 0x0400
/* Ioctl defines */
#define TUNSETNOCSUM _IOW('T', 200, int)
#define TUNDETACHFILTER _IOW('T', 214, struct sock_fprog)
#define TUNGETVNETHDRSZ _IOR('T', 215, int)
#define TUNSETVNETHDRSZ _IOW('T', 216, int)
+#define TUNSETQUEUE _IOW('T', 217, int)
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
#define IFF_ONE_QUEUE 0x2000
#define IFF_VNET_HDR 0x4000
#define IFF_TUN_EXCL 0x8000
+#define IFF_MULTI_QUEUE 0x0100
+#define IFF_ATTACH_QUEUE 0x0200
+#define IFF_DETACH_QUEUE 0x0400
/* Features for GSO (TUNSETOFFLOAD). */
#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */
NETCONFA_UNSPEC,
NETCONFA_IFINDEX,
NETCONFA_FORWARDING,
+ NETCONFA_RP_FILTER,
__NETCONFA_MAX
};
#define NETCONFA_MAX (__NETCONFA_MAX - 1)
unsigned int rsv[4]; /* Reserved for future use. */
};
+#define PTP_MAX_SAMPLES 25 /* Maximum allowed offset measurement samples. */
+
+struct ptp_sys_offset {
+ unsigned int n_samples; /* Desired number of measurements. */
+ unsigned int rsv[3]; /* Reserved for future use. */
+ /*
+ * Array of interleaved system/phc time stamps. The kernel
+ * will provide 2*n_samples + 1 time stamps, with the last
+ * one as a system time stamp.
+ */
+ struct ptp_clock_time ts[2 * PTP_MAX_SAMPLES + 1];
+};
+
#define PTP_CLK_MAGIC '='
#define PTP_CLOCK_GETCAPS _IOR(PTP_CLK_MAGIC, 1, struct ptp_clock_caps)
#define PTP_EXTTS_REQUEST _IOW(PTP_CLK_MAGIC, 2, struct ptp_extts_request)
#define PTP_PEROUT_REQUEST _IOW(PTP_CLK_MAGIC, 3, struct ptp_perout_request)
#define PTP_ENABLE_PPS _IOW(PTP_CLK_MAGIC, 4, int)
+#define PTP_SYS_OFFSET _IOW(PTP_CLK_MAGIC, 5, struct ptp_sys_offset)
struct ptp_extts_event {
struct ptp_clock_time t; /* Time event occured. */
-obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o timecompare.o
+obj-y += timekeeping.o ntp.o clocksource.o jiffies.o timer_list.o
obj-y += timeconv.o posix-clock.o alarmtimer.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
+++ /dev/null
-/*
- * Copyright (C) 2009 Intel Corporation.
- * Author: Patrick Ohly <patrick.ohly@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/timecompare.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/math64.h>
-#include <linux/kernel.h>
-
-/*
- * fixed point arithmetic scale factor for skew
- *
- * Usually one would measure skew in ppb (parts per billion, 1e9), but
- * using a factor of 2 simplifies the math.
- */
-#define TIMECOMPARE_SKEW_RESOLUTION (((s64)1)<<30)
-
-ktime_t timecompare_transform(struct timecompare *sync,
- u64 source_tstamp)
-{
- u64 nsec;
-
- nsec = source_tstamp + sync->offset;
- nsec += (s64)(source_tstamp - sync->last_update) * sync->skew /
- TIMECOMPARE_SKEW_RESOLUTION;
-
- return ns_to_ktime(nsec);
-}
-EXPORT_SYMBOL_GPL(timecompare_transform);
-
-int timecompare_offset(struct timecompare *sync,
- s64 *offset,
- u64 *source_tstamp)
-{
- u64 start_source = 0, end_source = 0;
- struct {
- s64 offset;
- s64 duration_target;
- } buffer[10], sample, *samples;
- int counter = 0, i;
- int used;
- int index;
- int num_samples = sync->num_samples;
-
- if (num_samples > ARRAY_SIZE(buffer)) {
- samples = kmalloc(sizeof(*samples) * num_samples, GFP_ATOMIC);
- if (!samples) {
- samples = buffer;
- num_samples = ARRAY_SIZE(buffer);
- }
- } else {
- samples = buffer;
- }
-
- /* run until we have enough valid samples, but do not try forever */
- i = 0;
- counter = 0;
- while (1) {
- u64 ts;
- ktime_t start, end;
-
- start = sync->target();
- ts = timecounter_read(sync->source);
- end = sync->target();
-
- if (!i)
- start_source = ts;
-
- /* ignore negative durations */
- sample.duration_target = ktime_to_ns(ktime_sub(end, start));
- if (sample.duration_target >= 0) {
- /*
- * assume symetric delay to and from source:
- * average target time corresponds to measured
- * source time
- */
- sample.offset =
- (ktime_to_ns(end) + ktime_to_ns(start)) / 2 -
- ts;
-
- /* simple insertion sort based on duration */
- index = counter - 1;
- while (index >= 0) {
- if (samples[index].duration_target <
- sample.duration_target)
- break;
- samples[index + 1] = samples[index];
- index--;
- }
- samples[index + 1] = sample;
- counter++;
- }
-
- i++;
- if (counter >= num_samples || i >= 100000) {
- end_source = ts;
- break;
- }
- }
-
- *source_tstamp = (end_source + start_source) / 2;
-
- /* remove outliers by only using 75% of the samples */
- used = counter * 3 / 4;
- if (!used)
- used = counter;
- if (used) {
- /* calculate average */
- s64 off = 0;
- for (index = 0; index < used; index++)
- off += samples[index].offset;
- *offset = div_s64(off, used);
- }
-
- if (samples && samples != buffer)
- kfree(samples);
-
- return used;
-}
-EXPORT_SYMBOL_GPL(timecompare_offset);
-
-void __timecompare_update(struct timecompare *sync,
- u64 source_tstamp)
-{
- s64 offset;
- u64 average_time;
-
- if (!timecompare_offset(sync, &offset, &average_time))
- return;
-
- if (!sync->last_update) {
- sync->last_update = average_time;
- sync->offset = offset;
- sync->skew = 0;
- } else {
- s64 delta_nsec = average_time - sync->last_update;
-
- /* avoid division by negative or small deltas */
- if (delta_nsec >= 10000) {
- s64 delta_offset_nsec = offset - sync->offset;
- s64 skew; /* delta_offset_nsec *
- TIMECOMPARE_SKEW_RESOLUTION /
- delta_nsec */
- u64 divisor;
-
- /* div_s64() is limited to 32 bit divisor */
- skew = delta_offset_nsec * TIMECOMPARE_SKEW_RESOLUTION;
- divisor = delta_nsec;
- while (unlikely(divisor >= ((s64)1) << 32)) {
- /* divide both by 2; beware, right shift
- of negative value has undefined
- behavior and can only be used for
- the positive divisor */
- skew = div_s64(skew, 2);
- divisor >>= 1;
- }
- skew = div_s64(skew, divisor);
-
- /*
- * Calculate new overall skew as 4/16 the
- * old value and 12/16 the new one. This is
- * a rather arbitrary tradeoff between
- * only using the latest measurement (0/16 and
- * 16/16) and even more weight on past measurements.
- */
-#define TIMECOMPARE_NEW_SKEW_PER_16 12
- sync->skew =
- div_s64((16 - TIMECOMPARE_NEW_SKEW_PER_16) *
- sync->skew +
- TIMECOMPARE_NEW_SKEW_PER_16 * skew,
- 16);
- sync->last_update = average_time;
- sync->offset = offset;
- }
- }
-}
-EXPORT_SYMBOL_GPL(__timecompare_update);
else
vlandev->hard_header_len = dev->hard_header_len + VLAN_HLEN;
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
vlandev->fcoe_ddp_xid = dev->fcoe_ddp_xid;
#endif
return err;
}
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
static int vlan_dev_fcoe_ddp_setup(struct net_device *dev, u16 xid,
struct scatterlist *sgl, unsigned int sgc)
{
if (is_zero_ether_addr(dev->broadcast))
memcpy(dev->broadcast, real_dev->broadcast, dev->addr_len);
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
dev->fcoe_ddp_xid = real_dev->fcoe_ddp_xid;
#endif
.ndo_do_ioctl = vlan_dev_ioctl,
.ndo_neigh_setup = vlan_dev_neigh_setup,
.ndo_get_stats64 = vlan_dev_get_stats64,
-#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE)
+#if IS_ENABLED(CONFIG_FCOE)
.ndo_fcoe_ddp_setup = vlan_dev_fcoe_ddp_setup,
.ndo_fcoe_ddp_done = vlan_dev_fcoe_ddp_done,
.ndo_fcoe_enable = vlan_dev_fcoe_enable,
return ret;
}
EXPORT_SYMBOL_GPL(sk_detach_filter);
+
+static void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to)
+{
+ static const u16 decodes[] = {
+ [BPF_S_ALU_ADD_K] = BPF_ALU|BPF_ADD|BPF_K,
+ [BPF_S_ALU_ADD_X] = BPF_ALU|BPF_ADD|BPF_X,
+ [BPF_S_ALU_SUB_K] = BPF_ALU|BPF_SUB|BPF_K,
+ [BPF_S_ALU_SUB_X] = BPF_ALU|BPF_SUB|BPF_X,
+ [BPF_S_ALU_MUL_K] = BPF_ALU|BPF_MUL|BPF_K,
+ [BPF_S_ALU_MUL_X] = BPF_ALU|BPF_MUL|BPF_X,
+ [BPF_S_ALU_DIV_X] = BPF_ALU|BPF_DIV|BPF_X,
+ [BPF_S_ALU_MOD_K] = BPF_ALU|BPF_MOD|BPF_K,
+ [BPF_S_ALU_MOD_X] = BPF_ALU|BPF_MOD|BPF_X,
+ [BPF_S_ALU_AND_K] = BPF_ALU|BPF_AND|BPF_K,
+ [BPF_S_ALU_AND_X] = BPF_ALU|BPF_AND|BPF_X,
+ [BPF_S_ALU_OR_K] = BPF_ALU|BPF_OR|BPF_K,
+ [BPF_S_ALU_OR_X] = BPF_ALU|BPF_OR|BPF_X,
+ [BPF_S_ALU_XOR_K] = BPF_ALU|BPF_XOR|BPF_K,
+ [BPF_S_ALU_XOR_X] = BPF_ALU|BPF_XOR|BPF_X,
+ [BPF_S_ALU_LSH_K] = BPF_ALU|BPF_LSH|BPF_K,
+ [BPF_S_ALU_LSH_X] = BPF_ALU|BPF_LSH|BPF_X,
+ [BPF_S_ALU_RSH_K] = BPF_ALU|BPF_RSH|BPF_K,
+ [BPF_S_ALU_RSH_X] = BPF_ALU|BPF_RSH|BPF_X,
+ [BPF_S_ALU_NEG] = BPF_ALU|BPF_NEG,
+ [BPF_S_LD_W_ABS] = BPF_LD|BPF_W|BPF_ABS,
+ [BPF_S_LD_H_ABS] = BPF_LD|BPF_H|BPF_ABS,
+ [BPF_S_LD_B_ABS] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_PROTOCOL] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_PKTTYPE] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_IFINDEX] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_NLATTR] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_NLATTR_NEST] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_MARK] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_QUEUE] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_HATYPE] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS,
+ [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN,
+ [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND,
+ [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND,
+ [BPF_S_LD_B_IND] = BPF_LD|BPF_B|BPF_IND,
+ [BPF_S_LD_IMM] = BPF_LD|BPF_IMM,
+ [BPF_S_LDX_W_LEN] = BPF_LDX|BPF_W|BPF_LEN,
+ [BPF_S_LDX_B_MSH] = BPF_LDX|BPF_B|BPF_MSH,
+ [BPF_S_LDX_IMM] = BPF_LDX|BPF_IMM,
+ [BPF_S_MISC_TAX] = BPF_MISC|BPF_TAX,
+ [BPF_S_MISC_TXA] = BPF_MISC|BPF_TXA,
+ [BPF_S_RET_K] = BPF_RET|BPF_K,
+ [BPF_S_RET_A] = BPF_RET|BPF_A,
+ [BPF_S_ALU_DIV_K] = BPF_ALU|BPF_DIV|BPF_K,
+ [BPF_S_LD_MEM] = BPF_LD|BPF_MEM,
+ [BPF_S_LDX_MEM] = BPF_LDX|BPF_MEM,
+ [BPF_S_ST] = BPF_ST,
+ [BPF_S_STX] = BPF_STX,
+ [BPF_S_JMP_JA] = BPF_JMP|BPF_JA,
+ [BPF_S_JMP_JEQ_K] = BPF_JMP|BPF_JEQ|BPF_K,
+ [BPF_S_JMP_JEQ_X] = BPF_JMP|BPF_JEQ|BPF_X,
+ [BPF_S_JMP_JGE_K] = BPF_JMP|BPF_JGE|BPF_K,
+ [BPF_S_JMP_JGE_X] = BPF_JMP|BPF_JGE|BPF_X,
+ [BPF_S_JMP_JGT_K] = BPF_JMP|BPF_JGT|BPF_K,
+ [BPF_S_JMP_JGT_X] = BPF_JMP|BPF_JGT|BPF_X,
+ [BPF_S_JMP_JSET_K] = BPF_JMP|BPF_JSET|BPF_K,
+ [BPF_S_JMP_JSET_X] = BPF_JMP|BPF_JSET|BPF_X,
+ };
+ u16 code;
+
+ code = filt->code;
+
+ to->code = decodes[code];
+ to->jt = filt->jt;
+ to->jf = filt->jf;
+
+ if (code == BPF_S_ALU_DIV_K) {
+ /*
+ * When loaded this rule user gave us X, which was
+ * translated into R = r(X). Now we calculate the
+ * RR = r(R) and report it back. If next time this
+ * value is loaded and RRR = r(RR) is calculated
+ * then the R == RRR will be true.
+ *
+ * One exception. X == 1 translates into R == 0 and
+ * we can't calculate RR out of it with r().
+ */
+
+ if (filt->k == 0)
+ to->k = 1;
+ else
+ to->k = reciprocal_value(filt->k);
+
+ BUG_ON(reciprocal_value(to->k) != filt->k);
+ } else
+ to->k = filt->k;
+}
+
+int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, unsigned int len)
+{
+ struct sk_filter *filter;
+ int i, ret;
+
+ lock_sock(sk);
+ filter = rcu_dereference_protected(sk->sk_filter,
+ sock_owned_by_user(sk));
+ ret = 0;
+ if (!filter)
+ goto out;
+ ret = filter->len;
+ if (!len)
+ goto out;
+ ret = -EINVAL;
+ if (len < filter->len)
+ goto out;
+
+ ret = -EFAULT;
+ for (i = 0; i < filter->len; i++) {
+ struct sock_filter fb;
+
+ sk_decode_filter(&filter->insns[i], &fb);
+ if (copy_to_user(&ubuf[i], &fb, sizeof(fb)))
+ goto out;
+ }
+
+ ret = filter->len;
+out:
+ release_sock(sk);
+ return ret;
+}
case SO_BINDTODEVICE:
v.val = sk->sk_bound_dev_if;
break;
+ case SO_GET_FILTER:
+ len = sk_get_filter(sk, (struct sock_filter __user *)optval, len);
+ if (len < 0)
+ return len;
+
+ goto lenout;
default:
return -ENOPROTOOPT;
}
/* type -1 is used for ALL */
if (type == -1 || type == NETCONFA_FORWARDING)
size += nla_total_size(4);
+ if (type == -1 || type == NETCONFA_RP_FILTER)
+ size += nla_total_size(4);
return size;
}
nla_put_s32(skb, NETCONFA_FORWARDING,
IPV4_DEVCONF(*devconf, FORWARDING)) < 0)
goto nla_put_failure;
+ if ((type == -1 || type == NETCONFA_RP_FILTER) &&
+ nla_put_s32(skb, NETCONFA_RP_FILTER,
+ IPV4_DEVCONF(*devconf, RP_FILTER)) < 0)
+ goto nla_put_failure;
return nlmsg_end(skb, nlh);
static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = {
[NETCONFA_IFINDEX] = { .len = sizeof(int) },
[NETCONFA_FORWARDING] = { .len = sizeof(int) },
+ [NETCONFA_RP_FILTER] = { .len = sizeof(int) },
};
static int inet_netconf_get_devconf(struct sk_buff *in_skb,
i == IPV4_DEVCONF_ROUTE_LOCALNET - 1)
if ((new_value == 0) && (old_value != 0))
rt_cache_flush(net);
+ if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
+ new_value != old_value) {
+ int ifindex;
+
+ if (cnf == net->ipv4.devconf_dflt)
+ ifindex = NETCONFA_IFINDEX_DEFAULT;
+ else if (cnf == net->ipv4.devconf_all)
+ ifindex = NETCONFA_IFINDEX_ALL;
+ else {
+ struct in_device *idev =
+ container_of(cnf, struct in_device,
+ cnf);
+ ifindex = idev->dev->ifindex;
+ }
+ inet_netconf_notify_devconf(net, NETCONFA_RP_FILTER,
+ ifindex, cnf);
+ }
}
return ret;
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
ndev->cnf.accept_dad = -1;
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) {
pr_info("%s: Disabled Multicast RS\n", dev->name);
ndev->cnf.rtr_solicits = 0;
This thing is done here expecting that the whole
class of non-broadcast devices need not cloning.
*/
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT))
cfg.fc_flags |= RTF_NONEXTHOP;
#endif
ip6_route_add(&cfg);
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void sit_route_add(struct net_device *dev)
{
struct fib6_config cfg = {
if (dev == NULL)
goto err_exit;
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
if (dev->type == ARPHRD_SIT) {
const struct net_device_ops *ops = dev->netdev_ops;
struct ifreq ifr;
}
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void sit_add_v4_addrs(struct inet6_dev *idev)
{
struct in6_addr addr;
addrconf_add_linklocal(idev, &addr);
}
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
static void addrconf_sit_config(struct net_device *dev)
{
struct inet6_dev *idev;
}
#endif
-#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE)
+#if IS_ENABLED(CONFIG_NET_IPGRE)
static void addrconf_gre_config(struct net_device *dev)
{
struct inet6_dev *idev;
}
switch (dev->type) {
-#if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_SIT)
case ARPHRD_SIT:
addrconf_sit_config(dev);
break;
#endif
-#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE)
+#if IS_ENABLED(CONFIG_NET_IPGRE)
case ARPHRD_IPGRE:
addrconf_gre_config(dev);
break;
}
#endif /* CONFIG_PROC_FS */
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
/* Check if address is a home address configured on any interface. */
int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr)
{
#define IPV6HDR_BASELEN 8
struct tmp_ext {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
struct in6_addr saddr;
#endif
struct in6_addr daddr;
return false;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
/**
* ipv6_rearrange_destopt - rearrange IPv6 destination options header
* @iph: IPv6 header
memcpy(top_iph, iph_base, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(&top_iph->saddr, iph_ext, extlen);
#else
memcpy(&top_iph->daddr, iph_ext, extlen);
memcpy(iph_base, top_iph, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(iph_ext, &top_iph->saddr, extlen);
#else
memcpy(iph_ext, &top_iph->daddr, extlen);
memcpy(top_iph, iph_base, IPV6HDR_BASELEN);
if (extlen) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
memcpy(&top_iph->saddr, iph_ext, extlen);
#else
memcpy(&top_iph->daddr, iph_ext, extlen);
rthdr = (struct ipv6_rt_hdr *)CMSG_DATA(cmsg);
switch (rthdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1) {
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/xfrm.h>
#endif
Destination options header.
*****************************/
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
static bool ipv6_dest_hao(struct sk_buff *skb, int optoff)
{
struct ipv6_destopt_hao *hao;
#endif
static const struct tlvtype_proc tlvprocdestopt_lst[] = {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
{
.type = IPV6_TLV_HAO,
.func = ipv6_dest_hao,
static int ipv6_destopt_rcv(struct sk_buff *skb)
{
struct inet6_skb_parm *opt = IP6CB(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
__u16 dstbuf;
#endif
struct dst_entry *dst = skb_dst(skb);
}
opt->lastopt = opt->dst1 = skb_network_header_len(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
dstbuf = opt->dst1;
#endif
if (ip6_parse_tlv(tlvprocdestopt_lst, skb)) {
skb->transport_header += (skb_transport_header(skb)[1] + 1) << 3;
opt = IP6CB(skb);
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
opt->nhoff = dstbuf;
#else
opt->nhoff = opt->dst1;
looped_back:
if (hdr->segments_left == 0) {
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
/* Silently discard type 2 header unless it was
* processed by own
}
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (accept_source_route < 0)
goto unknown_rh;
addr += i - 1;
switch (hdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (xfrm6_input_addr(skb, (xfrm_address_t *)addr,
(xfrm_address_t *)&ipv6_hdr(skb)->saddr,
return 0;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
static void mip6_addr_swap(struct sk_buff *skb)
{
struct ipv6hdr *iph = ipv6_hdr(skb);
to->tc_index = from->tc_index;
#endif
nf_copy(to, from);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
to->nf_trace = from->nf_trace;
#endif
skb_copy_secmark(to, from);
found_rhdr = 1;
break;
case NEXTHDR_DEST:
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
if (ipv6_find_tlv(skb, offset, IPV6_TLV_HAO) >= 0)
break;
#endif
if (optname == IPV6_RTHDR && opt && opt->srcrt) {
struct ipv6_rt_hdr *rthdr = opt->srcrt;
switch (rthdr->type) {
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPV6_SRCRT_TYPE_2:
if (rthdr->hdrlen != 2 ||
rthdr->segments_left != 1)
return ip6t_get_target((struct ip6t_entry *)e);
}
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* This cries for unification! */
static const char *const hooknames[] = {
[NF_INET_PRE_ROUTING] = "PREROUTING",
t = ip6t_get_target_c(e);
IP_NF_ASSERT(t->u.kernel.target);
-#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
- defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
+#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE)
/* The packet is traced: log it */
if (unlikely(skb->nf_trace))
trace_packet(skb, hook, in, out,
},
};
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
.invert_tuple = ipv6_invert_tuple,
.print_tuple = ipv6_print_tuple,
.get_l4proto = ipv6_get_l4proto,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = ipv6_tuple_to_nlattr,
.nlattr_tuple_size = ipv6_nlattr_tuple_size,
.nlattr_to_tuple = ipv6_nlattr_to_tuple,
return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
}
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_conntrack.h>
.get_timeouts = icmpv6_get_timeouts,
.new = icmpv6_new,
.error = icmpv6_error,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.tuple_to_nlattr = icmpv6_tuple_to_nlattr,
.nlattr_tuple_size = icmpv6_nlattr_tuple_size,
.nlattr_to_tuple = icmpv6_nlattr_to_tuple,
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
#include <net/netfilter/nf_conntrack_l4proto.h>
{
u16 zone = NF_CT_DEFAULT_ZONE;
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
if (skb->nfct)
zone = nf_ct_zone((struct nf_conn *)skb->nfct);
#endif
{
struct sk_buff *reasm;
-#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
/* Previously seen (loopback)? */
if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
return NF_ACCEPT;
.manip_pkt = icmpv6_manip_pkt,
.in_range = icmpv6_in_range,
.unique_tuple = icmpv6_unique_tuple,
-#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
.nlattr_to_range = nf_nat_l4proto_nlattr_to_range,
#endif
};
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/tcp_states.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
#include <linux/mroute6.h>
return 1;
}
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb);
static mh_filter_t __rcu *mh_filter __read_mostly;
filtered = icmpv6_filter(sk, skb);
break;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
{
/* XXX: To validate MH only once for each packet,
#include <net/ip.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
#include <net/mip6.h>
#endif
fl6->flowi6_proto = nexthdr;
return;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case IPPROTO_MH:
if (!onlyproto && pskb_may_pull(skb, nh + offset + 3 - skb->data)) {
struct ip6_mh *mh;
return 1;
else
return 3;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case XFRM_MODE_ROUTEOPTIMIZATION:
case XFRM_MODE_IN_TRIGGER:
return 2;
switch (v->mode) {
case XFRM_MODE_TRANSPORT:
return 1;
-#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
+#if IS_ENABLED(CONFIG_IPV6_MIP6)
case XFRM_MODE_ROUTEOPTIMIZATION:
case XFRM_MODE_IN_TRIGGER:
return 2;
projects / firefly-linux-kernel-4.4.55.git / commitdiff