* [PATCH 05/13] stmmac: add GMAC4 DMA/CORE Header File
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
In-Reply-To: <1458897260-14104-1-git-send-email-alexandre.torgue@st.com>
This is the main header file to define all the
macro used for GMAC4 DMA and CORE parts.
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
new file mode 100644
index 0000000..c12f15c
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -0,0 +1,224 @@
+/*
+ * DWMAC4 Header file.
+ *
+ * Copyright (C) 2015 STMicroelectronics Ltd
+ *
+ * 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.
+ *
+ * Author: Alexandre Torgue <alexandre.torgue@st.com>
+ */
+
+#ifndef __DWMAC4_H__
+#define __DWMAC4_H__
+
+#include "common.h"
+
+/* MAC registers */
+#define GMAC_CONFIG 0x00000000
+#define GMAC_PACKET_FILTER 0x00000008
+#define GMAC_HASH_TAB_0_31 0x00000010
+#define GMAC_HASH_TAB_32_63 0x00000014
+#define GMAC_RX_FLOW_CTRL 0x00000090
+#define GMAC_QX_TX_FLOW_CTRL(x) (0x70 + x * 4)
+#define GMAC_INT_STATUS 0x000000b0
+#define GMAC_INT_EN 0x000000b4
+#define GMAC_AN_CTRL 0x000000e0
+#define GMAC_AN_STATUS 0x000000e4
+#define GMAC_AN_ADV 0x000000e8
+#define GMAC_AN_LPA 0x000000ec
+#define GMAC_PMT 0x000000c0
+#define GMAC_VERSION 0x00000110
+#define GMAC_DEBUG 0x00000114
+#define GMAC_HW_FEATURE0 0x0000011c
+#define GMAC_HW_FEATURE1 0x00000120
+#define GMAC_HW_FEATURE2 0x00000124
+#define GMAC_MDIO_ADDR 0x00000200
+#define GMAC_MDIO_DATA 0x00000204
+#define GMAC_ADDR_HIGH(reg) (0x300 + reg * 8)
+#define GMAC_ADDR_LOW(reg) (0x304 + reg * 8)
+
+/* MAC Packet Filtering */
+#define GMAC_PACKET_FILTER_PR BIT(0)
+#define GMAC_PACKET_FILTER_HMC BIT(2)
+#define GMAC_PACKET_FILTER_PM BIT(4)
+
+#define GMAC_MAX_PERFECT_ADDRESSES 128
+
+/* MAC Flow Control RX */
+#define GMAC_RX_FLOW_CTRL_RFE BIT(0)
+
+/* MAC Flow Control TX */
+#define GMAC_TX_FLOW_CTRL_TFE BIT(1)
+#define GMAC_TX_FLOW_CTRL_PT_SHIFT 16
+
+/* MAC Interrupt bitmap*/
+#define GMAC_INT_PMT_EN BIT(4)
+#define GMAC_INT_LPI_EN BIT(5)
+
+enum dwmac4_irq_status {
+ time_stamp_irq = 0x00001000,
+ mmc_rx_csum_offload_irq = 0x00000800,
+ mmc_tx_irq = 0x00000400,
+ mmc_rx_irq = 0x00000200,
+ mmc_irq = 0x00000100,
+ pmt_irq = 0x00000010,
+ pcs_ane_irq = 0x00000004,
+ pcs_link_irq = 0x00000002,
+};
+
+/* MAC Auto-Neg bitmap*/
+#define GMAC_AN_CTRL_RAN BIT(9)
+#define GMAC_AN_CTRL_ANE BIT(12)
+#define GMAC_AN_CTRL_ELE BIT(14)
+#define GMAC_AN_FD BIT(5)
+#define GMAC_AN_HD BIT(6)
+#define GMAC_AN_PSE_MASK GENMASK(8, 7)
+#define GMAC_AN_PSE_SHIFT 7
+
+/* MAC PMT bitmap */
+enum power_event {
+ pointer_reset = 0x80000000,
+ global_unicast = 0x00000200,
+ wake_up_rx_frame = 0x00000040,
+ magic_frame = 0x00000020,
+ wake_up_frame_en = 0x00000004,
+ magic_pkt_en = 0x00000002,
+ power_down = 0x00000001,
+};
+
+/* MAC Debug bitmap */
+#define GMAC_DEBUG_TFCSTS_MASK GENMASK(18, 17)
+#define GMAC_DEBUG_TFCSTS_SHIFT 17
+#define GMAC_DEBUG_TFCSTS_IDLE 0
+#define GMAC_DEBUG_TFCSTS_WAIT 1
+#define GMAC_DEBUG_TFCSTS_GEN_PAUSE 2
+#define GMAC_DEBUG_TFCSTS_XFER 3
+#define GMAC_DEBUG_TPESTS BIT(16)
+#define GMAC_DEBUG_RFCFCSTS_MASK GENMASK(2, 1)
+#define GMAC_DEBUG_RFCFCSTS_SHIFT 1
+#define GMAC_DEBUG_RPESTS BIT(0)
+
+/* MAC config */
+#define GMAC_CONFIG_IPC BIT(27)
+#define GMAC_CONFIG_2K BIT(22)
+#define GMAC_CONFIG_ACS BIT(20)
+#define GMAC_CONFIG_BE BIT(18)
+#define GMAC_CONFIG_JD BIT(17)
+#define GMAC_CONFIG_JE BIT(16)
+#define GMAC_CONFIG_PS BIT(15)
+#define GMAC_CONFIG_FES BIT(14)
+#define GMAC_CONFIG_DM BIT(13)
+#define GMAC_CONFIG_DCRS BIT(9)
+#define GMAC_CONFIG_TE BIT(1)
+#define GMAC_CONFIG_RE BIT(0)
+
+/* MAC HW features0 bitmap */
+#define GMAC_HW_FEAT_ADDMAC BIT(18)
+#define GMAC_HW_FEAT_RXCOESEL BIT(16)
+#define GMAC_HW_FEAT_TXCOSEL BIT(14)
+#define GMAC_HW_FEAT_EEESEL BIT(13)
+#define GMAC_HW_FEAT_TSSEL BIT(12)
+#define GMAC_HW_FEAT_MMCSEL BIT(8)
+#define GMAC_HW_FEAT_MGKSEL BIT(7)
+#define GMAC_HW_FEAT_RWKSEL BIT(6)
+#define GMAC_HW_FEAT_SMASEL BIT(5)
+#define GMAC_HW_FEAT_VLHASH BIT(4)
+#define GMAC_HW_FEAT_PCSSEL BIT(3)
+#define GMAC_HW_FEAT_HDSEL BIT(2)
+#define GMAC_HW_FEAT_GMIISEL BIT(1)
+#define GMAC_HW_FEAT_MIISEL BIT(0)
+
+/* MAC HW features1 bitmap */
+#define GMAC_HW_FEAT_AVSEL BIT(20)
+#define GMAC_HW_TSOEN BIT(18)
+
+/* MAC HW features2 bitmap */
+#define GMAC_HW_FEAT_TXCHCNT GENMASK(21, 18)
+#define GMAC_HW_FEAT_RXCHCNT GENMASK(15, 12)
+
+/* MAC HW ADDR regs */
+#define GMAC_HI_DCS GENMASK(18, 16)
+#define GMAC_HI_DCS_SHIFT 16
+#define GMAC_HI_REG_AE BIT(31)
+
+/* MTL registers */
+#define MTL_INT_STATUS 0x00000c20
+#define MTL_INT_Q0 BIT(0)
+
+#define MTL_CHAN_BASE_ADDR 0x00000d00
+#define MTL_CHAN_BASE_OFFSET 0x40
+#define MTL_CHANX_BASE_ADDR(x) (MTL_CHAN_BASE_ADDR + \
+ (x * MTL_CHAN_BASE_OFFSET))
+
+#define MTL_CHAN_TX_OP_MODE(x) MTL_CHANX_BASE_ADDR(x)
+#define MTL_CHAN_TX_DEBUG(x) (MTL_CHANX_BASE_ADDR(x) + 0x8)
+#define MTL_CHAN_INT_CTRL(x) (MTL_CHANX_BASE_ADDR(x) + 0x2c)
+#define MTL_CHAN_RX_OP_MODE(x) (MTL_CHANX_BASE_ADDR(x) + 0x30)
+#define MTL_CHAN_RX_DEBUG(x) (MTL_CHANX_BASE_ADDR(x) + 0x38)
+
+#define MTL_OP_MODE_RSF BIT(5)
+#define MTL_OP_MODE_TSF BIT(1)
+
+#define MTL_OP_MODE_TTC_MASK 0x70
+#define MTL_OP_MODE_TTC_SHIFT 4
+
+#define MTL_OP_MODE_TTC_32 0
+#define MTL_OP_MODE_TTC_64 (1 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_96 (2 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_128 (3 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_192 (4 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_256 (5 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_384 (6 << MTL_OP_MODE_TTC_SHIFT)
+#define MTL_OP_MODE_TTC_512 (7 << MTL_OP_MODE_TTC_SHIFT)
+
+#define MTL_OP_MODE_RTC_MASK 0x18
+#define MTL_OP_MODE_RTC_SHIFT 3
+
+#define MTL_OP_MODE_RTC_32 (1 << MTL_OP_MODE_RTC_SHIFT)
+#define MTL_OP_MODE_RTC_64 0
+#define MTL_OP_MODE_RTC_96 (2 << MTL_OP_MODE_RTC_SHIFT)
+#define MTL_OP_MODE_RTC_128 (3 << MTL_OP_MODE_RTC_SHIFT)
+
+/* MTL debug */
+#define MTL_DEBUG_TXSTSFSTS BIT(5)
+#define MTL_DEBUG_TXFSTS BIT(4)
+#define MTL_DEBUG_TWCSTS BIT(3)
+
+/* MTL debug: Tx FIFO Read Controller Status */
+#define MTL_DEBUG_TRCSTS_MASK GENMASK(2, 1)
+#define MTL_DEBUG_TRCSTS_SHIFT 1
+#define MTL_DEBUG_TRCSTS_IDLE 0
+#define MTL_DEBUG_TRCSTS_READ 1
+#define MTL_DEBUG_TRCSTS_TXW 2
+#define MTL_DEBUG_TRCSTS_WRITE 3
+#define MTL_DEBUG_TXPAUSED BIT(0)
+
+/* MAC debug: GMII or MII Transmit Protocol Engine Status */
+#define MTL_DEBUG_RXFSTS_MASK GENMASK(5, 4)
+#define MTL_DEBUG_RXFSTS_SHIFT 4
+#define MTL_DEBUG_RXFSTS_EMPTY 0
+#define MTL_DEBUG_RXFSTS_BT 1
+#define MTL_DEBUG_RXFSTS_AT 2
+#define MTL_DEBUG_RXFSTS_FULL 3
+#define MTL_DEBUG_RRCSTS_MASK GENMASK(2, 1)
+#define MTL_DEBUG_RRCSTS_SHIFT 1
+#define MTL_DEBUG_RRCSTS_IDLE 0
+#define MTL_DEBUG_RRCSTS_RDATA 1
+#define MTL_DEBUG_RRCSTS_RSTAT 2
+#define MTL_DEBUG_RRCSTS_FLUSH 3
+#define MTL_DEBUG_RWCSTS BIT(0)
+
+/* MTL interrupt */
+#define MTL_RX_OVERFLOW_INT_EN BIT(24)
+#define MTL_RX_OVERFLOW_INT BIT(16)
+
+/* Default operating mode of the MAC */
+#define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | GMAC_CONFIG_ACS | \
+ GMAC_CONFIG_BE | GMAC_CONFIG_DCRS)
+
+/* To dump the core regs excluding the Address Registers */
+#define GMAC_REG_NUM 132
+
+#endif /* __DWMAC4_H__ */
--
1.9.1
^ permalink raw reply related
* [PATCH 04/13] stmmac: add descriptors function for GMAC 4.xx
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
In-Reply-To: <1458897260-14104-1-git-send-email-alexandre.torgue@st.com>
One of main changes of GMAC 4.xx IP is descriptors management.
-descriptors are only used in ring mode.
-A descriptor is composed of 4 32bits registers (no more extended
descriptors)
-descriptor mechanism (Tx for example, but it is exactly the same for RX):
-useful registers:
-DMA_CH#_TxDesc_Ring_Len: length of transmit descriptor
ring
-DMA_CH#_TxDesc_List_Address: start address of the ring
-DMA_CH#_TxDesc_Tail_Pointer: address of the last
descriptor to send + 1.
-DMA_CH#_TxDesc_Current_App_TxDesc: address of the current
descriptor
-The descriptor Tail Pointer register contains the pointer to the
descriptor address (N). The base address and the current
descriptor decide the address of the current descriptor that the
DMA can process. The descriptors up to one location less than the
one indicated by the descriptor tail pointer (N-1) are owned by
the DMA. The DMA continues to process the descriptors until the
following condition occurs:
"current descriptor pointer == Descriptor Tail pointer"
Then the DMA goes into suspend mode. The application must perform
a write to descriptor tail pointer register and update the tail
pointer to have the following condition and to start a new
transfer:
"current descriptor pointer < Descriptor tail pointer"
The DMA automatically wraps around the base address when the end
of ring is reached.
-New features are available on IP:
-TSO (TCP Segmentation Offload) for TX only
-Split header: to have header and payload in 2 different buffers
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index b390161..fa000fd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -2,7 +2,8 @@ obj-$(CONFIG_STMMAC_ETH) += stmmac.o
stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \
chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \
dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \
- mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o $(stmmac-y)
+ mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o \
+ $(stmmac-y)
# Ordering matters. Generic driver must be last.
obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 66e132f..ea7eb0d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -243,6 +243,7 @@ enum rx_frame_status {
csum_none = 0x2,
llc_snap = 0x4,
dma_own = 0x8,
+ rx_not_ls = 0x10,
};
/* Tx status */
@@ -348,6 +349,10 @@ struct stmmac_desc_ops {
void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len,
bool csum_flag, int mode, bool tx_own,
bool ls);
+ void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1,
+ int len2, bool tx_own, bool ls,
+ unsigned int tcphdrlen,
+ unsigned int tcppayloadlen);
/* Set/get the owner of the descriptor */
void (*set_tx_owner) (struct dma_desc *p);
int (*get_tx_owner) (struct dma_desc *p);
@@ -382,6 +387,8 @@ struct stmmac_desc_ops {
int (*get_rx_timestamp_status) (void *desc, u32 ats);
/* Display ring */
void (*display_ring)(void *head, unsigned int size, bool rx);
+ /* set MSS via context descriptor */
+ void (*set_mss)(struct dma_desc *p, unsigned int mss);
};
extern const struct stmmac_desc_ops enh_desc_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
new file mode 100644
index 0000000..33cbec3
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
@@ -0,0 +1,396 @@
+/*
+ * This contains the functions to handle the descriptors for DesignWare databook
+ * 4.xx.
+ *
+ * Copyright (C) 2015 STMicroelectronics Ltd
+ *
+ * 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.
+ *
+ * Author: Alexandre Torgue <alexandre.torgue@st.com>
+ */
+
+#include <linux/stmmac.h>
+#include "common.h"
+#include "dwmac4_descs.h"
+
+static int dwmac4_wrback_get_tx_status(void *data, struct stmmac_extra_stats *x,
+ struct dma_desc *p,
+ void __iomem *ioaddr)
+{
+ struct net_device_stats *stats = (struct net_device_stats *)data;
+ unsigned int tdes3;
+ int ret = tx_done;
+
+ tdes3 = p->des3;
+
+ /* Get tx owner first */
+ if (unlikely(tdes3 & TDES3_OWN))
+ return tx_dma_own;
+
+ /* Verify tx error by looking at the last segment. */
+ if (likely(!(tdes3 & TDES3_LAST_DESCRIPTOR)))
+ return tx_not_ls;
+
+ if (unlikely(tdes3 & TDES3_ERROR_SUMMARY)) {
+ if (unlikely(tdes3 & TDES3_JABBER_TIMEOUT))
+ x->tx_jabber++;
+ if (unlikely(tdes3 & TDES3_PACKET_FLUSHED))
+ x->tx_frame_flushed++;
+ if (unlikely(tdes3 & TDES3_LOSS_CARRIER)) {
+ x->tx_losscarrier++;
+ stats->tx_carrier_errors++;
+ }
+ if (unlikely(tdes3 & TDES3_NO_CARRIER)) {
+ x->tx_carrier++;
+ stats->tx_carrier_errors++;
+ }
+ if (unlikely((tdes3 & TDES3_LATE_COLLISION) ||
+ (tdes3 & TDES3_EXCESSIVE_COLLISION)))
+ stats->collisions +=
+ (tdes3 & TDES3_COLLISION_COUNT_MASK)
+ >> TDES3_COLLISION_COUNT_SHIFT;
+
+ if (unlikely(tdes3 & TDES3_EXCESSIVE_DEFERRAL))
+ x->tx_deferred++;
+
+ if (unlikely(tdes3 & TDES3_UNDERFLOW_ERROR))
+ x->tx_underflow++;
+
+ if (unlikely(tdes3 & TDES3_IP_HDR_ERROR))
+ x->tx_ip_header_error++;
+
+ if (unlikely(tdes3 & TDES3_PAYLOAD_ERROR))
+ x->tx_payload_error++;
+
+ ret = tx_err;
+ }
+
+ if (unlikely(tdes3 & TDES3_DEFERRED))
+ x->tx_deferred++;
+
+ return ret;
+}
+
+static int dwmac4_wrback_get_rx_status(void *data, struct stmmac_extra_stats *x,
+ struct dma_desc *p)
+{
+ struct net_device_stats *stats = (struct net_device_stats *)data;
+ unsigned int rdes1 = p->des1;
+ unsigned int rdes2 = p->des2;
+ unsigned int rdes3 = p->des3;
+ int message_type;
+ int ret = good_frame;
+
+ if (unlikely(rdes3 & RDES3_OWN))
+ return dma_own;
+
+ /* Verify rx error by looking at the last segment. */
+ if (likely(!(rdes3 & RDES3_LAST_DESCRIPTOR)))
+ return discard_frame;
+
+ if (unlikely(rdes3 & RDES3_ERROR_SUMMARY)) {
+ if (unlikely(rdes3 & RDES3_GIANT_PACKET))
+ stats->rx_length_errors++;
+ if (unlikely(rdes3 & RDES3_OVERFLOW_ERROR))
+ x->rx_gmac_overflow++;
+
+ if (unlikely(rdes3 & RDES3_RECEIVE_WATCHDOG))
+ x->rx_watchdog++;
+
+ if (unlikely(rdes3 & RDES3_RECEIVE_ERROR))
+ x->rx_mii++;
+
+ if (unlikely(rdes3 & RDES3_CRC_ERROR)) {
+ x->rx_crc++;
+ stats->rx_crc_errors++;
+ }
+
+ if (unlikely(rdes3 & RDES3_DRIBBLE_ERROR))
+ x->dribbling_bit++;
+
+ ret = discard_frame;
+ }
+
+ message_type = (rdes1 & ERDES4_MSG_TYPE_MASK) >> 8;
+
+ if (rdes1 & RDES1_IP_HDR_ERROR)
+ x->ip_hdr_err++;
+ if (rdes1 & RDES1_IP_CSUM_BYPASSED)
+ x->ip_csum_bypassed++;
+ if (rdes1 & RDES1_IPV4_HEADER)
+ x->ipv4_pkt_rcvd++;
+ if (rdes1 & RDES1_IPV6_HEADER)
+ x->ipv6_pkt_rcvd++;
+ if (message_type == RDES_EXT_SYNC)
+ x->rx_msg_type_sync++;
+ else if (message_type == RDES_EXT_FOLLOW_UP)
+ x->rx_msg_type_follow_up++;
+ else if (message_type == RDES_EXT_DELAY_REQ)
+ x->rx_msg_type_delay_req++;
+ else if (message_type == RDES_EXT_DELAY_RESP)
+ x->rx_msg_type_delay_resp++;
+ else if (message_type == RDES_EXT_PDELAY_REQ)
+ x->rx_msg_type_pdelay_req++;
+ else if (message_type == RDES_EXT_PDELAY_RESP)
+ x->rx_msg_type_pdelay_resp++;
+ else if (message_type == RDES_EXT_PDELAY_FOLLOW_UP)
+ x->rx_msg_type_pdelay_follow_up++;
+ else
+ x->rx_msg_type_ext_no_ptp++;
+
+ if (rdes1 & RDES1_PTP_PACKET_TYPE)
+ x->ptp_frame_type++;
+ if (rdes1 & RDES1_PTP_VER)
+ x->ptp_ver++;
+ if (rdes1 & RDES1_TIMESTAMP_DROPPED)
+ x->timestamp_dropped++;
+
+ if (unlikely(rdes2 & RDES2_SA_FILTER_FAIL)) {
+ x->sa_rx_filter_fail++;
+ ret = discard_frame;
+ }
+ if (unlikely(rdes2 & RDES2_DA_FILTER_FAIL)) {
+ x->da_rx_filter_fail++;
+ ret = discard_frame;
+ }
+
+ if (rdes2 & RDES2_L3_FILTER_MATCH)
+ x->l3_filter_match++;
+ if (rdes2 & RDES2_L4_FILTER_MATCH)
+ x->l4_filter_match++;
+ if ((rdes2 & RDES2_L3_L4_FILT_NB_MATCH_MASK)
+ >> RDES2_L3_L4_FILT_NB_MATCH_SHIFT)
+ x->l3_l4_filter_no_match++;
+
+ return ret;
+}
+
+static int dwmac4_rd_get_tx_len(struct dma_desc *p)
+{
+ return (p->des2 & TDES2_BUFFER1_SIZE_MASK);
+}
+
+static int dwmac4_get_tx_owner(struct dma_desc *p)
+{
+ return (p->des3 & TDES3_OWN) >> TDES3_OWN_SHIFT;
+}
+
+static void dwmac4_set_tx_owner(struct dma_desc *p)
+{
+ p->des3 |= TDES3_OWN;
+}
+
+static void dwmac4_set_rx_owner(struct dma_desc *p)
+{
+ p->des3 |= RDES3_OWN;
+}
+
+static int dwmac4_get_tx_ls(struct dma_desc *p)
+{
+ return (p->des3 & TDES3_LAST_DESCRIPTOR) >> TDES3_LAST_DESCRIPTOR_SHIFT;
+}
+
+static int dwmac4_wrback_get_rx_frame_len(struct dma_desc *p, int rx_coe)
+{
+ return (p->des3 & RDES3_PACKET_SIZE_MASK);
+}
+
+static void dwmac4_rd_enable_tx_timestamp(struct dma_desc *p)
+{
+ p->des2 |= TDES2_TIMESTAMP_ENABLE;
+}
+
+static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p)
+{
+ return (p->des3 & TDES3_TIMESTAMP_STATUS)
+ >> TDES3_TIMESTAMP_STATUS_SHIFT;
+}
+
+/* NOTE: For RX CTX bit has to be checked before
+ * HAVE a specific function for TX and another one for RX
+ */
+static u64 dwmac4_wrback_get_timestamp(void *desc, u32 ats)
+{
+ struct dma_desc *p = (struct dma_desc *)desc;
+ u64 ns;
+
+ ns = p->des0;
+ /* convert high/sec time stamp value to nanosecond */
+ ns += p->des1 * 1000000000ULL;
+
+ return ns;
+}
+
+static int dwmac4_context_get_rx_timestamp_status(void *desc, u32 ats)
+{
+ struct dma_desc *p = (struct dma_desc *)desc;
+
+ return (p->des1 & RDES1_TIMESTAMP_AVAILABLE)
+ >> RDES1_TIMESTAMP_AVAILABLE_SHIFT;
+}
+
+static void dwmac4_rd_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
+ int mode, int end)
+{
+ p->des3 = RDES3_OWN | RDES3_BUFFER1_VALID_ADDR;
+
+ if (!disable_rx_ic)
+ p->des3 |= RDES3_INT_ON_COMPLETION_EN;
+}
+
+static void dwmac4_rd_init_tx_desc(struct dma_desc *p, int mode, int end)
+{
+ p->des0 = 0;
+ p->des1 = 0;
+ p->des2 = 0;
+ p->des3 = 0;
+}
+
+static void dwmac4_rd_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
+ bool csum_flag, int mode, bool tx_own,
+ bool ls)
+{
+ unsigned int tdes3 = p->des3;
+
+ if (unlikely(len > BUF_SIZE_16KiB)) {
+ p->des2 |= (((len - BUF_SIZE_16KiB) <<
+ TDES2_BUFFER2_SIZE_MASK_SHIFT)
+ & TDES2_BUFFER2_SIZE_MASK)
+ | (BUF_SIZE_16KiB & TDES2_BUFFER1_SIZE_MASK);
+ } else {
+ p->des2 |= (len & TDES2_BUFFER1_SIZE_MASK);
+ }
+
+ if (is_fs)
+ tdes3 |= TDES3_FIRST_DESCRIPTOR;
+ else
+ tdes3 &= ~TDES3_FIRST_DESCRIPTOR;
+
+ if (likely(csum_flag))
+ tdes3 |= (TX_CIC_FULL << TDES3_CHECKSUM_INSERTION_SHIFT);
+ else
+ tdes3 &= ~(TX_CIC_FULL << TDES3_CHECKSUM_INSERTION_SHIFT);
+
+ if (ls)
+ tdes3 |= TDES3_LAST_DESCRIPTOR;
+ else
+ tdes3 &= ~TDES3_LAST_DESCRIPTOR;
+
+ /* Finally set the OWN bit. Later the DMA will start! */
+ if (tx_own)
+ tdes3 |= TDES3_OWN;
+
+ if (is_fs & tx_own)
+ /* When the own bit, for the first frame, has to be set, all
+ * descriptors for the same frame has to be set before, to
+ * avoid race condition.
+ */
+ wmb();
+
+ p->des3 = tdes3;
+}
+
+static void dwmac4_rd_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
+ int len1, int len2, bool tx_own,
+ bool ls, unsigned int tcphdrlen,
+ unsigned int tcppayloadlen)
+{
+ unsigned int tdes3 = p->des3;
+
+ if (len1)
+ p->des2 |= (len1 & TDES2_BUFFER1_SIZE_MASK);
+
+ if (len2)
+ p->des2 |= (len2 << TDES2_BUFFER2_SIZE_MASK_SHIFT)
+ & TDES2_BUFFER2_SIZE_MASK;
+
+ if (is_fs) {
+ tdes3 |= TDES3_FIRST_DESCRIPTOR |
+ TDES3_TCP_SEGMENTATION_ENABLE |
+ ((tcphdrlen << TDES3_HDR_LEN_SHIFT) &
+ TDES3_SLOT_NUMBER_MASK) |
+ ((tcppayloadlen & TDES3_TCP_PKT_PAYLOAD_MASK));
+ } else {
+ tdes3 &= ~TDES3_FIRST_DESCRIPTOR;
+ }
+
+ if (ls)
+ tdes3 |= TDES3_LAST_DESCRIPTOR;
+ else
+ tdes3 &= ~TDES3_LAST_DESCRIPTOR;
+
+ /* Finally set the OWN bit. Later the DMA will start! */
+ if (tx_own)
+ tdes3 |= TDES3_OWN;
+
+ if (is_fs & tx_own)
+ /* When the own bit, for the first frame, has to be set, all
+ * descriptors for the same frame has to be set before, to
+ * avoid race condition.
+ */
+ wmb();
+
+ p->des3 = tdes3;
+}
+
+static void dwmac4_release_tx_desc(struct dma_desc *p, int mode)
+{
+ p->des2 = 0;
+ p->des3 = 0;
+}
+
+static void dwmac4_rd_set_tx_ic(struct dma_desc *p)
+{
+ p->des2 |= TDES2_INTERRUPT_ON_COMPLETION;
+}
+
+static void dwmac4_display_ring(void *head, unsigned size, bool rx)
+{
+ struct dma_desc *p = (struct dma_desc *)head;
+ int i;
+
+ pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
+
+ for (i = 0; i < size; i++) {
+ if (p->des0)
+ pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, (unsigned int)virt_to_phys(p),
+ p->des0, p->des1, p->des2, p->des3);
+ p++;
+ }
+}
+
+static void dwmac4_set_mss_ctxt(struct dma_desc *p, unsigned int mss)
+{
+ p->des0 = 0;
+ p->des1 = 0;
+ p->des2 = mss;
+ p->des3 = TDES3_CONTEXT_TYPE | TDES3_CTXT_TCMSSV;
+}
+
+const struct stmmac_desc_ops dwmac4_desc_ops = {
+ .tx_status = dwmac4_wrback_get_tx_status,
+ .rx_status = dwmac4_wrback_get_rx_status,
+ .get_tx_len = dwmac4_rd_get_tx_len,
+ .get_tx_owner = dwmac4_get_tx_owner,
+ .set_tx_owner = dwmac4_set_tx_owner,
+ .set_rx_owner = dwmac4_set_rx_owner,
+ .get_tx_ls = dwmac4_get_tx_ls,
+ .get_rx_frame_len = dwmac4_wrback_get_rx_frame_len,
+ .enable_tx_timestamp = dwmac4_rd_enable_tx_timestamp,
+ .get_tx_timestamp_status = dwmac4_wrback_get_tx_timestamp_status,
+ .get_timestamp = dwmac4_wrback_get_timestamp,
+ .get_rx_timestamp_status = dwmac4_context_get_rx_timestamp_status,
+ .set_tx_ic = dwmac4_rd_set_tx_ic,
+ .prepare_tx_desc = dwmac4_rd_prepare_tx_desc,
+ .prepare_tso_tx_desc = dwmac4_rd_prepare_tso_tx_desc,
+ .release_tx_desc = dwmac4_release_tx_desc,
+ .init_rx_desc = dwmac4_rd_init_rx_desc,
+ .init_tx_desc = dwmac4_rd_init_tx_desc,
+ .display_ring = dwmac4_display_ring,
+ .set_mss = dwmac4_set_mss_ctxt,
+};
+
+const struct stmmac_mode_ops dwmac4_ring_mode_ops = { };
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
new file mode 100644
index 0000000..0902a2e
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
@@ -0,0 +1,129 @@
+/*
+ * Header File to describe the DMA descriptors and related definitions specific
+ * for DesignWare databook 4.xx.
+ *
+ * Copyright (C) 2015 STMicroelectronics Ltd
+ *
+ * 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.
+ *
+ * Author: Alexandre Torgue <alexandre.torgue@st.com>
+ */
+
+#ifndef __DWMAC4_DESCS_H__
+#define __DWMAC4_DESCS_H__
+
+#include <linux/bitops.h>
+
+/* Normal transmit descriptor defines (without split feature) */
+
+/* TDES2 (read format) */
+#define TDES2_BUFFER1_SIZE_MASK GENMASK(13, 0)
+#define TDES2_VLAN_TAG_MASK GENMASK(15, 14)
+#define TDES2_BUFFER2_SIZE_MASK GENMASK(29, 16)
+#define TDES2_BUFFER2_SIZE_MASK_SHIFT 16
+#define TDES2_TIMESTAMP_ENABLE BIT(30)
+#define TDES2_INTERRUPT_ON_COMPLETION BIT(31)
+
+/* TDES3 (read format) */
+#define TDES3_PACKET_SIZE_MASK GENMASK(14, 0)
+#define TDES3_CHECKSUM_INSERTION_MASK GENMASK(17, 16)
+#define TDES3_CHECKSUM_INSERTION_SHIFT 16
+#define TDES3_TCP_PKT_PAYLOAD_MASK GENMASK(17, 0)
+#define TDES3_TCP_SEGMENTATION_ENABLE BIT(18)
+#define TDES3_HDR_LEN_SHIFT 19
+#define TDES3_SLOT_NUMBER_MASK GENMASK(22, 19)
+#define TDES3_SA_INSERT_CTRL_MASK GENMASK(25, 23)
+#define TDES3_CRC_PAD_CTRL_MASK GENMASK(27, 26)
+
+/* TDES3 (write back format) */
+#define TDES3_IP_HDR_ERROR BIT(0)
+#define TDES3_DEFERRED BIT(1)
+#define TDES3_UNDERFLOW_ERROR BIT(2)
+#define TDES3_EXCESSIVE_DEFERRAL BIT(3)
+#define TDES3_COLLISION_COUNT_MASK GENMASK(7, 4)
+#define TDES3_COLLISION_COUNT_SHIFT 4
+#define TDES3_EXCESSIVE_COLLISION BIT(8)
+#define TDES3_LATE_COLLISION BIT(9)
+#define TDES3_NO_CARRIER BIT(10)
+#define TDES3_LOSS_CARRIER BIT(11)
+#define TDES3_PAYLOAD_ERROR BIT(12)
+#define TDES3_PACKET_FLUSHED BIT(13)
+#define TDES3_JABBER_TIMEOUT BIT(14)
+#define TDES3_ERROR_SUMMARY BIT(15)
+#define TDES3_TIMESTAMP_STATUS BIT(17)
+#define TDES3_TIMESTAMP_STATUS_SHIFT 17
+
+/* TDES3 context */
+#define TDES3_CTXT_TCMSSV BIT(26)
+
+/* TDES3 Common */
+#define TDES3_LAST_DESCRIPTOR BIT(28)
+#define TDES3_LAST_DESCRIPTOR_SHIFT 28
+#define TDES3_FIRST_DESCRIPTOR BIT(29)
+#define TDES3_CONTEXT_TYPE BIT(30)
+
+/* TDS3 use for both format (read and write back) */
+#define TDES3_OWN BIT(31)
+#define TDES3_OWN_SHIFT 31
+
+/* Normal receive descriptor defines (without split feature) */
+
+/* RDES0 (write back format) */
+#define RDES0_VLAN_TAG_MASK GENMASK(15, 0)
+
+/* RDES1 (write back format) */
+#define RDES1_IP_PAYLOAD_TYPE_MASK GENMASK(2, 0)
+#define RDES1_IP_HDR_ERROR BIT(3)
+#define RDES1_IPV4_HEADER BIT(4)
+#define RDES1_IPV6_HEADER BIT(5)
+#define RDES1_IP_CSUM_BYPASSED BIT(6)
+#define RDES1_IP_CSUM_ERROR BIT(7)
+#define RDES1_PTP_MSG_TYPE_MASK GENMASK(11, 8)
+#define RDES1_PTP_PACKET_TYPE BIT(12)
+#define RDES1_PTP_VER BIT(13)
+#define RDES1_TIMESTAMP_AVAILABLE BIT(14)
+#define RDES1_TIMESTAMP_AVAILABLE_SHIFT 14
+#define RDES1_TIMESTAMP_DROPPED BIT(15)
+#define RDES1_IP_TYPE1_CSUM_MASK GENMASK(31, 16)
+
+/* RDES2 (write back format) */
+#define RDES2_L3_L4_HEADER_SIZE_MASK GENMASK(9, 0)
+#define RDES2_VLAN_FILTER_STATUS BIT(15)
+#define RDES2_SA_FILTER_FAIL BIT(16)
+#define RDES2_DA_FILTER_FAIL BIT(17)
+#define RDES2_HASH_FILTER_STATUS BIT(18)
+#define RDES2_MAC_ADDR_MATCH_MASK GENMASK(26, 19)
+#define RDES2_HASH_VALUE_MATCH_MASK GENMASK(26, 19)
+#define RDES2_L3_FILTER_MATCH BIT(27)
+#define RDES2_L4_FILTER_MATCH BIT(28)
+#define RDES2_L3_L4_FILT_NB_MATCH_MASK GENMASK(27, 26)
+#define RDES2_L3_L4_FILT_NB_MATCH_SHIFT 26
+
+/* RDES3 (write back format) */
+#define RDES3_PACKET_SIZE_MASK GENMASK(14, 0)
+#define RDES3_ERROR_SUMMARY BIT(15)
+#define RDES3_PACKET_LEN_TYPE_MASK GENMASK(18, 16)
+#define RDES3_DRIBBLE_ERROR BIT(19)
+#define RDES3_RECEIVE_ERROR BIT(20)
+#define RDES3_OVERFLOW_ERROR BIT(21)
+#define RDES3_RECEIVE_WATCHDOG BIT(22)
+#define RDES3_GIANT_PACKET BIT(23)
+#define RDES3_CRC_ERROR BIT(24)
+#define RDES3_RDES0_VALID BIT(25)
+#define RDES3_RDES1_VALID BIT(26)
+#define RDES3_RDES2_VALID BIT(27)
+#define RDES3_LAST_DESCRIPTOR BIT(28)
+#define RDES3_FIRST_DESCRIPTOR BIT(29)
+#define RDES3_CONTEXT_DESCRIPTOR BIT(30)
+
+/* RDES3 (read format) */
+#define RDES3_BUFFER1_VALID_ADDR BIT(24)
+#define RDES3_BUFFER2_VALID_ADDR BIT(25)
+#define RDES3_INT_ON_COMPLETION_EN BIT(30)
+
+/* TDS3 use for both format (read and write back) */
+#define RDES3_OWN BIT(31)
+
+#endif /* __DWMAC4_DESCS_H__ */
--
1.9.1
^ permalink raw reply related
* [PATCH 03/13] stmmac: rework synopsys id read, moved to dwmac setup
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
In-Reply-To: <1458897260-14104-1-git-send-email-alexandre.torgue@st.com>
synopsys_uid is only used once after setup, to get synopsys_id
by using shitf/mask operation. It's no longer used then.
So, remove this temporary variable and directly compute
synopsys_id from setup routine.
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Signed-off-by: Fabrice Gasnier <fabrice.gasnier@st.com>
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 6cea61b..66e132f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -498,7 +498,6 @@ struct mac_device_info {
const struct stmmac_hwtimestamp *ptp;
struct mii_regs mii; /* MII register Addresses */
struct mac_link link;
- unsigned int synopsys_uid;
void __iomem *pcsr; /* vpointer to device CSRs */
int multicast_filter_bins;
int unicast_filter_entries;
@@ -507,8 +506,10 @@ struct mac_device_info {
};
struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
- int perfect_uc_entries);
-struct mac_device_info *dwmac100_setup(void __iomem *ioaddr);
+ int perfect_uc_entries,
+ int *synopsys_id);
+struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id);
+
void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6],
unsigned int high, unsigned int low);
@@ -521,4 +522,24 @@ void dwmac_dma_flush_tx_fifo(void __iomem *ioaddr);
extern const struct stmmac_mode_ops ring_mode_ops;
extern const struct stmmac_mode_ops chain_mode_ops;
+/**
+ * stmmac_get_synopsys_id - return the SYINID.
+ * @priv: driver private structure
+ * Description: this simple function is to decode and return the SYINID
+ * starting from the HW core register.
+ */
+static inline u32 stmmac_get_synopsys_id(u32 hwid)
+{
+ /* Check Synopsys Id (not available on old chips) */
+ if (likely(hwid)) {
+ u32 uid = ((hwid & 0x0000ff00) >> 8);
+ u32 synid = (hwid & 0x000000ff);
+
+ pr_info("stmmac - user ID: 0x%x, Synopsys ID: 0x%x\n",
+ uid, synid);
+
+ return synid;
+ }
+ return 0;
+}
#endif /* __COMMON_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index c294117..fb1eb57 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -491,7 +491,8 @@ static const struct stmmac_ops dwmac1000_ops = {
};
struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
- int perfect_uc_entries)
+ int perfect_uc_entries,
+ int *synopsys_id)
{
struct mac_device_info *mac;
u32 hwid = readl(ioaddr + GMAC_VERSION);
@@ -516,7 +517,9 @@ struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins,
mac->link.speed = GMAC_CONTROL_FES;
mac->mii.addr = GMAC_MII_ADDR;
mac->mii.data = GMAC_MII_DATA;
- mac->synopsys_uid = hwid;
+
+ /* Get and dump the chip ID */
+ *synopsys_id = stmmac_get_synopsys_id(hwid);
return mac;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index f8dd773..6418b2e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -173,7 +173,7 @@ static const struct stmmac_ops dwmac100_ops = {
.get_umac_addr = dwmac100_get_umac_addr,
};
-struct mac_device_info *dwmac100_setup(void __iomem *ioaddr)
+struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id)
{
struct mac_device_info *mac;
@@ -192,7 +192,8 @@ struct mac_device_info *dwmac100_setup(void __iomem *ioaddr)
mac->link.speed = 0;
mac->mii.addr = MAC_MII_ADDR;
mac->mii.data = MAC_MII_DATA;
- mac->synopsys_uid = 0;
+ /* Synopsys Id is not available on old chips */
+ *synopsys_id = 0;
return mac;
}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 8103527..2ebee81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1468,29 +1468,6 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv)
}
/**
- * stmmac_get_synopsys_id - return the SYINID.
- * @priv: driver private structure
- * Description: this simple function is to decode and return the SYINID
- * starting from the HW core register.
- */
-static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv)
-{
- u32 hwid = priv->hw->synopsys_uid;
-
- /* Check Synopsys Id (not available on old chips) */
- if (likely(hwid)) {
- u32 uid = ((hwid & 0x0000ff00) >> 8);
- u32 synid = (hwid & 0x000000ff);
-
- pr_info("stmmac - user ID: 0x%x, Synopsys ID: 0x%x\n",
- uid, synid);
-
- return synid;
- }
- return 0;
-}
-
-/**
* stmmac_selec_desc_mode - to select among: normal/alternate/extend descriptors
* @priv: driver private structure
* Description: select the Enhanced/Alternate or Normal descriptors.
@@ -2763,18 +2740,16 @@ static int stmmac_hw_init(struct stmmac_priv *priv)
priv->dev->priv_flags |= IFF_UNICAST_FLT;
mac = dwmac1000_setup(priv->ioaddr,
priv->plat->multicast_filter_bins,
- priv->plat->unicast_filter_entries);
+ priv->plat->unicast_filter_entries,
+ &priv->synopsys_id);
} else {
- mac = dwmac100_setup(priv->ioaddr);
+ mac = dwmac100_setup(priv->ioaddr, &priv->synopsys_id);
}
if (!mac)
return -ENOMEM;
priv->hw = mac;
- /* Get and dump the chip ID */
- priv->synopsys_id = stmmac_get_synopsys_id(priv);
-
/* To use the chained or ring mode */
if (chain_mode) {
priv->hw->mode = &chain_mode_ops;
--
1.9.1
^ permalink raw reply related
* [PATCH 02/13] stmmac: rework the routines to show the ring status
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
In-Reply-To: <1458897260-14104-1-git-send-email-alexandre.torgue@st.com>
To avoid lot of check in stmmac_main for display ring management
and support the GMAC4 chip, the display_ring function is moved
into dedicated descriptor file.
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 797a913..6cea61b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -380,6 +380,8 @@ struct stmmac_desc_ops {
u64(*get_timestamp) (void *desc, u32 ats);
/* get rx timestamp status */
int (*get_rx_timestamp_status) (void *desc, u32 ats);
+ /* Display ring */
+ void (*display_ring)(void *head, unsigned int size, bool rx);
};
extern const struct stmmac_desc_ops enh_desc_ops;
diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
index cfb018c..3e1b249 100644
--- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c
@@ -411,6 +411,26 @@ static int enh_desc_get_rx_timestamp_status(void *desc, u32 ats)
}
}
+static void enh_desc_display_ring(void *head, unsigned size, bool rx)
+{
+ struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
+ int i;
+
+ pr_info("Extended %s descriptor ring:\n", rx ? "RX" : "TX");
+
+ for (i = 0; i < size; i++) {
+ u64 x;
+
+ x = *(u64 *)ep;
+ pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
+ i, (unsigned int)virt_to_phys(ep),
+ (unsigned int)x, (unsigned int)(x >> 32),
+ ep->basic.des2, ep->basic.des3);
+ ep++;
+ }
+ pr_info("\n");
+}
+
const struct stmmac_desc_ops enh_desc_ops = {
.tx_status = enh_desc_get_tx_status,
.rx_status = enh_desc_get_rx_status,
@@ -430,4 +450,5 @@ const struct stmmac_desc_ops enh_desc_ops = {
.get_tx_timestamp_status = enh_desc_get_tx_timestamp_status,
.get_timestamp = enh_desc_get_timestamp,
.get_rx_timestamp_status = enh_desc_get_rx_timestamp_status,
+ .display_ring = enh_desc_display_ring,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
index e13228f..d93323d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c
@@ -279,6 +279,26 @@ static int ndesc_get_rx_timestamp_status(void *desc, u32 ats)
return 1;
}
+static void ndesc_display_ring(void *head, unsigned size, bool rx)
+{
+ struct dma_desc *p = (struct dma_desc *)head;
+ int i;
+
+ pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");
+
+ for (i = 0; i < size; i++) {
+ u64 x;
+
+ x = *(u64 *)p;
+ pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
+ i, (unsigned int)virt_to_phys(p),
+ (unsigned int)x, (unsigned int)(x >> 32),
+ p->des2, p->des3);
+ p++;
+ }
+ pr_info("\n");
+}
+
const struct stmmac_desc_ops ndesc_ops = {
.tx_status = ndesc_get_tx_status,
.rx_status = ndesc_get_rx_status,
@@ -297,4 +317,5 @@ const struct stmmac_desc_ops ndesc_ops = {
.get_tx_timestamp_status = ndesc_get_tx_timestamp_status,
.get_timestamp = ndesc_get_timestamp,
.get_rx_timestamp_status = ndesc_get_rx_timestamp_status,
+ .display_ring = ndesc_display_ring,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3ebfea..8103527 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -883,53 +883,22 @@ static int stmmac_init_phy(struct net_device *dev)
return 0;
}
-/**
- * stmmac_display_ring - display ring
- * @head: pointer to the head of the ring passed.
- * @size: size of the ring.
- * @extend_desc: to verify if extended descriptors are used.
- * Description: display the control/status and buffer descriptors.
- */
-static void stmmac_display_ring(void *head, int size, int extend_desc)
-{
- int i;
- struct dma_extended_desc *ep = (struct dma_extended_desc *)head;
- struct dma_desc *p = (struct dma_desc *)head;
-
- for (i = 0; i < size; i++) {
- u64 x;
- if (extend_desc) {
- x = *(u64 *) ep;
- pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n",
- i, (unsigned int)virt_to_phys(ep),
- (unsigned int)x, (unsigned int)(x >> 32),
- ep->basic.des2, ep->basic.des3);
- ep++;
- } else {
- x = *(u64 *) p;
- pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x",
- i, (unsigned int)virt_to_phys(p),
- (unsigned int)x, (unsigned int)(x >> 32),
- p->des2, p->des3);
- p++;
- }
- pr_info("\n");
- }
-}
-
static void stmmac_display_rings(struct stmmac_priv *priv)
{
+ void *head_rx, *head_tx;
+
if (priv->extend_desc) {
- pr_info("Extended RX descriptor ring:\n");
- stmmac_display_ring((void *)priv->dma_erx, DMA_RX_SIZE, 1);
- pr_info("Extended TX descriptor ring:\n");
- stmmac_display_ring((void *)priv->dma_etx, DMA_TX_SIZE, 1);
+ head_rx = (void *)priv->dma_erx;
+ head_tx = (void *)priv->dma_etx;
} else {
- pr_info("RX descriptor ring:\n");
- stmmac_display_ring((void *)priv->dma_rx, DMA_RX_SIZE, 0);
- pr_info("TX descriptor ring:\n");
- stmmac_display_ring((void *)priv->dma_tx, DMA_TX_SIZE, 0);
+ head_rx = (void *)priv->dma_rx;
+ head_tx = (void *)priv->dma_tx;
}
+
+ /* Display Rx ring */
+ priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true);
+ /* Display Tx ring */
+ priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false);
}
static int stmmac_set_bfsize(int mtu, int bufsize)
@@ -1996,16 +1965,18 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
priv->cur_tx = entry;
if (netif_msg_pktdata(priv)) {
+ void *tx_head;
+
pr_debug("%s: curr=%d dirty=%d f=%d, e=%d, first=%p, nfrags=%d",
__func__, priv->cur_tx, priv->dirty_tx, first_entry,
entry, first, nfrags);
if (priv->extend_desc)
- stmmac_display_ring((void *)priv->dma_etx,
- DMA_TX_SIZE, 1);
+ tx_head = (void *)priv->dma_etx;
else
- stmmac_display_ring((void *)priv->dma_tx,
- DMA_TX_SIZE, 0);
+ tx_head = (void *)priv->dma_tx;
+
+ priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false);
pr_debug(">>> frame to be transmitted: ");
print_pkt(skb->data, skb->len);
@@ -2190,13 +2161,15 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit)
int coe = priv->hw->rx_csum;
if (netif_msg_rx_status(priv)) {
+ void *rx_head;
+
pr_debug("%s: descriptor ring:\n", __func__);
if (priv->extend_desc)
- stmmac_display_ring((void *)priv->dma_erx,
- DMA_RX_SIZE, 1);
+ rx_head = (void *)priv->dma_erx;
else
- stmmac_display_ring((void *)priv->dma_rx,
- DMA_RX_SIZE, 0);
+ rx_head = (void *)priv->dma_rx;
+
+ priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true);
}
while (count < limit) {
int status;
--
1.9.1
^ permalink raw reply related
* [PATCH 01/13] stmmac: rework get_hw_feature function
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
In-Reply-To: <1458897260-14104-1-git-send-email-alexandre.torgue@st.com>
On next GMAC IP generation (4.xx), the way to get hw feature
is not the same than on previous 3.xx. As it is hardware
dependent, the way to get hw capabilities should be defined in dma ops of
each MAC IP. It will avoid also a huge computation of hw capabilities in
stmmac_main.
Signed-off-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index f96d257..797a913 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -412,7 +412,8 @@ struct stmmac_dma_ops {
int (*dma_interrupt) (void __iomem *ioaddr,
struct stmmac_extra_stats *x);
/* If supported then get the optional core features */
- unsigned int (*get_hw_feature) (void __iomem *ioaddr);
+ void (*get_hw_feature)(void __iomem *ioaddr,
+ struct dma_features *dma_cap);
/* Program the HW RX Watchdog */
void (*rx_watchdog) (void __iomem *ioaddr, u32 riwt);
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
index da32d60..99074695 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_dma.c
@@ -215,9 +215,40 @@ static void dwmac1000_dump_dma_regs(void __iomem *ioaddr)
}
}
-static unsigned int dwmac1000_get_hw_feature(void __iomem *ioaddr)
+static void dwmac1000_get_hw_feature(void __iomem *ioaddr,
+ struct dma_features *dma_cap)
{
- return readl(ioaddr + DMA_HW_FEATURE);
+ u32 hw_cap = readl(ioaddr + DMA_HW_FEATURE);
+
+ dma_cap->mbps_10_100 = (hw_cap & DMA_HW_FEAT_MIISEL);
+ dma_cap->mbps_1000 = (hw_cap & DMA_HW_FEAT_GMIISEL) >> 1;
+ dma_cap->half_duplex = (hw_cap & DMA_HW_FEAT_HDSEL) >> 2;
+ dma_cap->hash_filter = (hw_cap & DMA_HW_FEAT_HASHSEL) >> 4;
+ dma_cap->multi_addr = (hw_cap & DMA_HW_FEAT_ADDMAC) >> 5;
+ dma_cap->pcs = (hw_cap & DMA_HW_FEAT_PCSSEL) >> 6;
+ dma_cap->sma_mdio = (hw_cap & DMA_HW_FEAT_SMASEL) >> 8;
+ dma_cap->pmt_remote_wake_up = (hw_cap & DMA_HW_FEAT_RWKSEL) >> 9;
+ dma_cap->pmt_magic_frame = (hw_cap & DMA_HW_FEAT_MGKSEL) >> 10;
+ /* MMC */
+ dma_cap->rmon = (hw_cap & DMA_HW_FEAT_MMCSEL) >> 11;
+ /* IEEE 1588-2002 */
+ dma_cap->time_stamp =
+ (hw_cap & DMA_HW_FEAT_TSVER1SEL) >> 12;
+ /* IEEE 1588-2008 */
+ dma_cap->atime_stamp = (hw_cap & DMA_HW_FEAT_TSVER2SEL) >> 13;
+ /* 802.3az - Energy-Efficient Ethernet (EEE) */
+ dma_cap->eee = (hw_cap & DMA_HW_FEAT_EEESEL) >> 14;
+ dma_cap->av = (hw_cap & DMA_HW_FEAT_AVSEL) >> 15;
+ /* TX and RX csum */
+ dma_cap->tx_coe = (hw_cap & DMA_HW_FEAT_TXCOESEL) >> 16;
+ dma_cap->rx_coe_type1 = (hw_cap & DMA_HW_FEAT_RXTYP1COE) >> 17;
+ dma_cap->rx_coe_type2 = (hw_cap & DMA_HW_FEAT_RXTYP2COE) >> 18;
+ dma_cap->rxfifo_over_2048 = (hw_cap & DMA_HW_FEAT_RXFIFOSIZE) >> 19;
+ /* TX and RX number of channels */
+ dma_cap->number_rx_channel = (hw_cap & DMA_HW_FEAT_RXCHCNT) >> 20;
+ dma_cap->number_tx_channel = (hw_cap & DMA_HW_FEAT_TXCHCNT) >> 22;
+ /* Alternate (enhanced) DESC mode */
+ dma_cap->enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
}
static void dwmac1000_rx_watchdog(void __iomem *ioaddr, u32 riwt)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 4c5ce98..d3ebfea 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1558,51 +1558,15 @@ static void stmmac_selec_desc_mode(struct stmmac_priv *priv)
*/
static int stmmac_get_hw_features(struct stmmac_priv *priv)
{
- u32 hw_cap = 0;
+ u32 ret = 0;
if (priv->hw->dma->get_hw_feature) {
- hw_cap = priv->hw->dma->get_hw_feature(priv->ioaddr);
-
- priv->dma_cap.mbps_10_100 = (hw_cap & DMA_HW_FEAT_MIISEL);
- priv->dma_cap.mbps_1000 = (hw_cap & DMA_HW_FEAT_GMIISEL) >> 1;
- priv->dma_cap.half_duplex = (hw_cap & DMA_HW_FEAT_HDSEL) >> 2;
- priv->dma_cap.hash_filter = (hw_cap & DMA_HW_FEAT_HASHSEL) >> 4;
- priv->dma_cap.multi_addr = (hw_cap & DMA_HW_FEAT_ADDMAC) >> 5;
- priv->dma_cap.pcs = (hw_cap & DMA_HW_FEAT_PCSSEL) >> 6;
- priv->dma_cap.sma_mdio = (hw_cap & DMA_HW_FEAT_SMASEL) >> 8;
- priv->dma_cap.pmt_remote_wake_up =
- (hw_cap & DMA_HW_FEAT_RWKSEL) >> 9;
- priv->dma_cap.pmt_magic_frame =
- (hw_cap & DMA_HW_FEAT_MGKSEL) >> 10;
- /* MMC */
- priv->dma_cap.rmon = (hw_cap & DMA_HW_FEAT_MMCSEL) >> 11;
- /* IEEE 1588-2002 */
- priv->dma_cap.time_stamp =
- (hw_cap & DMA_HW_FEAT_TSVER1SEL) >> 12;
- /* IEEE 1588-2008 */
- priv->dma_cap.atime_stamp =
- (hw_cap & DMA_HW_FEAT_TSVER2SEL) >> 13;
- /* 802.3az - Energy-Efficient Ethernet (EEE) */
- priv->dma_cap.eee = (hw_cap & DMA_HW_FEAT_EEESEL) >> 14;
- priv->dma_cap.av = (hw_cap & DMA_HW_FEAT_AVSEL) >> 15;
- /* TX and RX csum */
- priv->dma_cap.tx_coe = (hw_cap & DMA_HW_FEAT_TXCOESEL) >> 16;
- priv->dma_cap.rx_coe_type1 =
- (hw_cap & DMA_HW_FEAT_RXTYP1COE) >> 17;
- priv->dma_cap.rx_coe_type2 =
- (hw_cap & DMA_HW_FEAT_RXTYP2COE) >> 18;
- priv->dma_cap.rxfifo_over_2048 =
- (hw_cap & DMA_HW_FEAT_RXFIFOSIZE) >> 19;
- /* TX and RX number of channels */
- priv->dma_cap.number_rx_channel =
- (hw_cap & DMA_HW_FEAT_RXCHCNT) >> 20;
- priv->dma_cap.number_tx_channel =
- (hw_cap & DMA_HW_FEAT_TXCHCNT) >> 22;
- /* Alternate (enhanced) DESC mode */
- priv->dma_cap.enh_desc = (hw_cap & DMA_HW_FEAT_ENHDESSEL) >> 24;
- }
-
- return hw_cap;
+ priv->hw->dma->get_hw_feature(priv->ioaddr,
+ &priv->dma_cap);
+ ret = 1;
+ }
+
+ return ret;
}
/**
--
1.9.1
^ permalink raw reply related
* [PATCH 00/13] Enhance stmmac driver to support GMAC4.x IP
From: Alexandre TORGUE @ 2016-03-25 9:14 UTC (permalink / raw)
To: netdev, peppe.cavallaro; +Cc: Lars Persson
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=UTF-8, Size: 4976 bytes --]
This is a subset of patch to enhance current stmmac driver to support
new GMAC4.x chips. New set of callbacks is defined to support this new
family: descriptors, dma, core.
One of main changes of GMAC 4.xx IP is descriptors management.
-descriptors are only used in ring mode.
-A descriptor is composed of 4 32bits registers (no more extended
descriptors)
-descriptor mechanism (Tx for example, but it is exactly the same for RX):
-useful registers:
-DMA_CH#_TxDesc_Ring_Len: length of transmit descriptor ring
-DMA_CH#_TxDesc_List_Address: start address of the ring
-DMA_CH#_TxDesc_Tail_Pointer: address of the last descriptor to send + 1.
-DMA_CH#_TxDesc_Current_App_TxDesc: address of the current descriptor
-The descriptor Tail Pointer register contains the pointer to the
descriptor address (N). The base address and the current
descriptor decide the address of the current descriptor that the
DMA can process. The descriptors up to one location less than the
one indicated by the descriptor tail pointer (N-1) are owned by
the DMA. The DMA continues to process the descriptors until the
following condition occurs:
"current descriptor pointer == Descriptor Tail pointer"
Then the DMA goes into suspend mode. The application must perform
a write to descriptor tail pointer register and update the tail
pointer to have the following condition and to start a new transfer:
"current descriptor pointer < Descriptor tail pointer"
The DMA automatically wraps around the base address when the end
of ring is reached.
New features are available on IP:
-TSO (TCP Segmentation Offload) for TX only
-Split header: to have header and payload in 2 different buffers (not yet implemented)
Below some throughput figures obtained on some boxes:
iperf (mbps)
--------------------------------------
tcp udp
tx rx tx rx
-----------------
GMAC4.x 935 930 750 800
Note: There is a change in 4.10a databook on bitfield mapping of DMA_CHANx_INTR_ENA register.
This requires to have é diffrent set of callbacks between IP 4.00a and 4.10a.
Best regards
Alex
Alexandre TORGUE (13):
stmmac: rework get_hw_feature function
stmmac: rework the routines to show the ring status
stmmac: rework synopsys id read, moved to dwmac setup
stmmac: add descriptors function for GMAC 4.xx
stmmac: add GMAC4 DMA/CORE Header File
stmmac: add DMA support for GMAC 4.xx
stmmac: add GMAC4 core support
stmmac: enhance mmc counter management
stmmac: add new DT platform entries for GMAC4
stmmac: support new GMAC4
Documentation: networking: update stmmac
stmmac: update version to Jan_2016
stmmac: update MAINTAINERS
Documentation/devicetree/bindings/net/stmmac.txt | 2 +
Documentation/networking/stmmac.txt | 44 +-
MAINTAINERS | 1 +
drivers/net/ethernet/stmicro/stmmac/Makefile | 3 +-
drivers/net/ethernet/stmicro/stmmac/common.h | 64 +-
.../net/ethernet/stmicro/stmmac/dwmac1000_core.c | 7 +-
.../net/ethernet/stmicro/stmmac/dwmac1000_dma.c | 35 +-
.../net/ethernet/stmicro/stmmac/dwmac100_core.c | 5 +-
drivers/net/ethernet/stmicro/stmmac/dwmac4.h | 255 ++++++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 407 +++++++++++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c | 396 +++++++++++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h | 129 +++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c | 354 ++++++++++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h | 202 +++++++
drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c | 225 +++++++
drivers/net/ethernet/stmicro/stmmac/enh_desc.c | 21 +
drivers/net/ethernet/stmicro/stmmac/mmc.h | 4 +
drivers/net/ethernet/stmicro/stmmac/mmc_core.c | 349 +++++------
drivers/net/ethernet/stmicro/stmmac/norm_desc.c | 21 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 7 +-
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 7 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 643 +++++++++++++++------
.../net/ethernet/stmicro/stmmac/stmmac_platform.c | 7 +
include/linux/stmmac.h | 2 +
24 files changed, 2821 insertions(+), 369 deletions(-)
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4.h
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.h
create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac4_lib.c
--
1.9.1
^ permalink raw reply
* Re: [PATCH net] net: ipv4: Multipath needs to handle unreachable nexthops
From: Julian Anastasov @ 2016-03-25 9:05 UTC (permalink / raw)
To: David Ahern; +Cc: netdev
In-Reply-To: <56F49CD3.1060406@cumulusnetworks.com>
Hello,
On Thu, 24 Mar 2016, David Ahern wrote:
> On 3/24/16 4:33 PM, Julian Anastasov wrote:
> > But for multipath routes we can also consider the
> > nexthops as "alternatives", so it depends on how one uses
> > the multipath mechanism. The ability to fallback to
> > another nexthop assumes one connection is allowed to
> > move from one ISP to another. What if the second ISP
> > decides to reject the connection? What we have is a
> > broken connection just because the retransmits
> > were diverted to wrong place in the hurry. So, the
> > nexthops can be compatible or incompatible. For your
> > setup they are, for others they are not.
>
> I am not sure I completely understand your point. Are you saying that within a
> single multipath route some connections to nexthops are allowed and others are
> not?
>
> So to put that paragraph into an example
>
> 15.0.0.0/16
> nexthop via 12.0.0.2 dev swp1 weight 1
> nexthop via 12.0.0.3 dev swp1 weight 1
>
> Hosts from 15.0/16 could have TCP connections use 12.0.0.2, but not 12.0.0.3
> because 12.0.0.3 could be a different ISP and not allow TCP connections from
> this address space?
Yes. Two cases are possible:
1. ISP2 filters saddr, traffic with saddr from ISP1 is dropped.
2. ISP2 allows any saddr. But how the responses from
world with daddr=IP_from_ISP1 will come from ISP2 link?
If the nexthops are for different ISP the connection
can survive only if sticks to its ISP. An ISP will
not work as a backup link for another ISP.
The hash-based algorithm does not move connections
from one nexthop to another. If you rearrange the nexthops
on failure, the binding is lost and connections can break.
A fallback from fragile wifi link can upset users and any
redirects will lead to bad experience with broken conns.
So only CONNMARK can help to stick connection to some path.
If this path has multiple simultaneous alternatives you can
again use multipath route reached from 'ip rule from PUBIP2 table ISP2'
but then we again are restricted from the hash-based alg
which is suitable only for default routes hit by saddr=0.0.0.0
lookups. In the common case when connection is created
there are two lookups:
1. TCP selects nexthop with a saddr=0.0.0.0 lookup.
ISP is selected based on the mp alg.
2. If one is lucky to reach ip_route_me_harder the
hash-based lookup is defeated because now lookup
uses saddr=iph->saddr, so it selects different nexthop.
It works while all packets for the connection reach
ip_route_me_harder.
> > So, if the kernel used a random selection
> > your fallback algorithm should help. But it is fragile
> > for the simple setup with single default multipath route.
> > May be what we miss is the ability to choose between
> > random and hash-based selection. Then your patch may be
> > useful but only for setup 2 (multipath route hit only by
> > first packet). So, your patch may come with a sysctl var
> > that explains your current patch logic: "avoid failed nexthops,
> > never probe them, wait their failed entry to be expired by
> > neigh_periodic_work and just then we can use the nexthop
> > by creating new entry to probe the GW". Who will trigger
> > probes often enough to maintain fresh state?
>
> First packet out does the probe -- neigh lookup fails, kernel has no knowledge
> so can't reject the nexthop based on neighbor information.
>
> After that if it has information that says that a nexthop is dead, why would
> it continue to try to probe? Any traffic that selects that nh is dead. That to
If entry becomes FAILED this state is preserved
if we do not direct traffic to this entry. If there was a
single connection that was rejected after 3 failed probes
the next connection (with your patch) will fallback to
another neigh and the first entry will remain in FAILED
state until expiration. If one wants to refresh the state
often, a script/tool that pings all GWs is needed, so that
you can notice the available or failed paths faster.
> me defies the basis of having multiple paths.
We do not know how long is the outage. Long living
connections may prefer to survive with retransmits.
Say you are using SSH via wifi link doing important work.
Do you want your connection to break just because link was
down for a while?
Fallback to other ISP can be unwanted. If we do not
know if multipath route is used per-packet ot per-connection
we can not just apply a fallback to other nexthops.
We can do it only if user can configure the different
usages per multipath route:
1. hash-based or random
2. allow fallback or not. This config is not a MUST if users
can select random mode, it can imply that fallback is allowed.
Regards
^ permalink raw reply
* Re: [PATCH 1/1] net: Add SO_REUSEPORT_LISTEN_OFF socket option as drain mode
From: Willy Tarreau @ 2016-03-25 8:53 UTC (permalink / raw)
To: Eric Dumazet
Cc: Tom Herbert, Yann Ylavic, Linux Kernel Network Developers,
Tolga Ceylan, Craig Gallek, Josh Snyder, Aaron Conole,
David S. Miller, Daniel Borkmann
In-Reply-To: <1458888581.6473.30.camel@edumazet-glaptop3.roam.corp.google.com>
Hi Eric,
On Thu, Mar 24, 2016 at 11:49:41PM -0700, Eric Dumazet wrote:
> Everything is possible, but do not complain because BPF went in the
> kernel before your changes.
Don't get me wrong, I'm not complaining, I'm more asking for help to
try to elaborate the alternate solution. I understood well what my
proposal did because it was pretty straightforward, and the new one
I'll have to do is of an immense complexity for me by now, since it
will require learning a new language and finding doc on how all this
works together. But as I said I'm totally sold to the benefits it can
provide for large scale deployments and I'm well aware of the ugly
socket scan there was in the previous one.
> Just rework your patch.
>
> Supporting multiple SO_REUSEPORT groups on the same port should not be
> too hard really. Making sure BPF still work for them is feasible.
>
> But the semantic of the socket option would be really different.
I don't care much about the socket options themselves as long as I can
continue to support seamless reloads. I could even get rid of SO_REUSEPORT
on Linux to use something else instead if I have a reliable way to detect
that the alternative will work.
> You need to not control an individual listener, but a group of listener.
>
> Your dying haproxy would issue a single system call to tell the kernel :
> My SO_REUSEPORT group should not accept new SYN packets, so that the new
> haproxy can setup a working new SO_REUSEPORT group.
Normally it's the other way around :-) The new process first grabs the
socket, there's a tiny window where both are attached, and only then the
old process leaves. That's the only way to ensure there's no loss nor
added latency in the processing.
If you could share a pointer to some good starter documentation for this,
I would appreciate it. I really have no idea where to start from and the
only elements I found on the net didn't give a single hint regarding all
this :-/
Thanks,
Willy
^ permalink raw reply
* Re: [PATCH] stmmac: Fix phy without MDIO subnode
From: Giuseppe CAVALLARO @ 2016-03-25 8:42 UTC (permalink / raw)
To: John Keeping; +Cc: Gabriel Fernandez, netdev, linux-kernel
In-Reply-To: <20160324170119.28d54ed5.john@metanate.com>
On 3/24/2016 6:01 PM, John Keeping wrote:
> On Thu, 24 Mar 2016 13:56:02 +0100, Giuseppe CAVALLARO wrote:
>
>> This should be fixed by some work done some days
>> ago and not yet committed.
>>
>> Pls see "stmmac: MDIO fixes" patch-set and let me know
>> if ok on your side.
>
> Yes, that works for me.
thx John for having tested it on your side.
peppe
>
>
> Thanks,
> John
>
>> On 3/24/2016 11:56 AM, John Keeping wrote:
>>> Since commit 88f8b1bb41c6 ("stmmac: Fix 'eth0: No PHY found'
>>> regression") we no longer allocate mdio_bus_data unless there is a MDIO
>>> subnode. This breaks the ethernet on the Radxa Rock2 (using
>>> rk3288-rock2-square.dts) which does not have an MDIO subnode.
>>>
>>> That commit was correct that the phy_bus_name test is unhelpful since we
>>> allocate "plat" in the same function and never set phy_bus_name so let's
>>> just drop the test which restores the previous behaviour.
>>>
>>> Fixes: 88f8b1bb41c6 ("stmmac: Fix 'eth0: No PHY found' regression")
>>> Signed-off-by: John Keeping <john@metanate.com>
>>> ---
>>> drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +-
>>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>>> index dcbd2a1..e0fa060 100644
>>> --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>>> +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
>>> @@ -189,7 +189,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
>>> if (of_property_read_u32(np, "snps,phy-addr", &plat->phy_addr) == 0)
>>> dev_warn(&pdev->dev, "snps,phy-addr property is deprecated\n");
>>>
>>> - if ((plat->phy_node && !of_phy_is_fixed_link(np)) || !plat->mdio_node)
>>> + if ((plat->phy_node && !of_phy_is_fixed_link(np)))
>>> plat->mdio_bus_data = NULL;
>>> else
>>> plat->mdio_bus_data =
>>>
>>
>
>
^ permalink raw reply
* Re: [PATCH 1/1] net: Add SO_REUSEPORT_LISTEN_OFF socket option as drain mode
From: Eric Dumazet @ 2016-03-25 6:49 UTC (permalink / raw)
To: Willy Tarreau
Cc: Tom Herbert, Yann Ylavic, Linux Kernel Network Developers,
Tolga Ceylan, Craig Gallek, Josh Snyder, Aaron Conole,
David S. Miller, Daniel Borkmann
In-Reply-To: <20160325052819.GA8548@1wt.eu>
On Fri, 2016-03-25 at 06:28 +0100, Willy Tarreau wrote:
> On Thu, Mar 24, 2016 at 04:54:03PM -0700, Tom Herbert wrote:
> > On Thu, Mar 24, 2016 at 4:40 PM, Yann Ylavic <ylavic.dev@gmail.com> wrote:
> > > I'll learn how to do this to get the best performances from the
> > > server, but having to do so to work around what looks like a defect
> > > (for simple/default SMP configurations at least, no NUMA or clever
> > > CPU-affinity or queuing policy involved) seems odd in the first place.
> > >
> > I disagree with your assessment that there is a defect. SO_REUSEPORT
> > is designed to spread packets amongst _equivalent_ connections. In the
> > server draining case sockets are no longer equivalent, but that is a
> > special case.
>
> I partially disagree with you here Tom. Initially SO_REUSEPORT was not
> used to spread packets but to allow soft restart in some applications.
> I've been using it since 2001 in haproxy on *BSD and linux 2.2. It was
> removed during 2.3 and I used to keep a patch to reimplement it in 2.4
> (basically 2 or 3 lines, the infrastructure was still present), but the
> patch was not accepted. The same patch worked for 2.6 and 3.x, allowing
> me to continue to perform soft-restarts on Linux just like I used to do
> on *BSD. When SO_REUSEPORT was reimplemented in 3.9 with load balancing,
> I was happy because it at last allowed me to drop my patch and I got
> the extra benefit of better load balancing of incoming connections.
>
> But the main use we have for it (at least historically) is for soft
> restarts, where one process replaces another one. Very few people use
> more than one process in our case.
>
> However given the benefits of the load spreading for extreme loads,
> I'm willing to find how to achieve the same with BPF, but it's pretty
> clear that at this point I have no idea where to start from and that
> for a single process replacing a single one, it looks quite complicated.
>
> For me quite frankly the special case is the load balancing which is
> a side benefit (and a nice one, don't get me wrong).
>
> That's why I would have found it nice to "fix" the process replacement
> to avoid dropping incoming connections, though I don't want it to become
> a problem for future improvements on BPF. I don't think the two lines I
> proposed could become an issue but I'll live without them (or continue
> to apply this patch).
>
> BTW, I have no problem with having to write a little bit of assembly for
> fast interfaces if it remains untouched for years, we do already have a
> bit in haproxy. It's just a longterm investment.
Everything is possible, but do not complain because BPF went in the
kernel before your changes.
Just rework your patch.
Supporting multiple SO_REUSEPORT groups on the same port should not be
too hard really. Making sure BPF still work for them is feasible.
But the semantic of the socket option would be really different.
You need to not control an individual listener, but a group of listener.
Your dying haproxy would issue a single system call to tell the kernel :
My SO_REUSEPORT group should not accept new SYN packets, so that the new
haproxy can setup a working new SO_REUSEPORT group.
^ permalink raw reply
* RE: [v6, 2/5] soc: fsl: add GUTS driver for QorIQ platforms
From: Yangbo Lu @ 2016-03-25 6:44 UTC (permalink / raw)
To: Scott Wood, devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
linux-clk-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-i2c-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-mmc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, Zhao Qiang,
Russell King, Bhupesh Sharma, Santosh Shilimkar, Jochen Friedrich,
Yang-Leo Li, Rob Herring, Claudiu Manoil, Kumar Gala, Xiaobo Xie
In-Reply-To: <DB5PR0401MB1928302BB0DDE8D9B47E4361918C0-GXldUsIPo7Z/SeJcUcAJq43W/0Ik+aLCnBOFsp37pqbUKgpGm//BTAC/G2K4zDHf@public.gmane.org>
> -----Original Message-----
> From: Scott Wood
> Sent: Saturday, March 19, 2016 6:55 AM
> To: Yangbo Lu; devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-arm-
> kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org; linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linuxppc-
> dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org; linux-clk-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-
> i2c-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org;
> netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-mmc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> Cc: Rob Herring; Russell King; Jochen Friedrich; Joerg Roedel; Claudiu
> Manoil; ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org; Bhupesh Sharma; Zhao Qiang; Kumar Gala;
> Santosh Shilimkar; Yang-Leo Li; Xiaobo Xie
> Subject: Re: [v6, 2/5] soc: fsl: add GUTS driver for QorIQ platforms
>
> On 03/09/2016 04:18 AM, Yangbo Lu wrote:
> > +#ifdef CONFIG_FSL_GUTS
> > +u32 fsl_guts_get_svr(void);
> > +int fsl_guts_init(void);
> > +#endif
>
> Don't ifdef prototypes (when not providing a stub alternative).
>
> -Scott
[Lu Yangbo-B47093] Ok, will remove the ifdef.
Thank you very much.
^ permalink raw reply
* RE: [v6, 5/5] mmc: sdhci-of-esdhc: fix host version for T4240-R1.0-R2.0
From: Yangbo Lu @ 2016-03-25 6:43 UTC (permalink / raw)
To: Scott Wood, Arnd Bergmann, Rob Herring
Cc: linuxppc-dev@lists.ozlabs.org, devicetree@vger.kernel.org,
ulf.hansson@linaro.org, Zhao Qiang, Russell King, Bhupesh Sharma,
netdev@vger.kernel.org, Joerg Roedel, Kumar Gala,
linux-mmc@vger.kernel.org, linux-kernel@vger.kernel.org,
Yang-Leo Li, iommu@lists.linux-foundation.org,
linux-i2c@vger.kernel.org, Claudiu Manoil, Santosh Shilimkar,
Xiaobo Xie, linux-clk@vger.kernel.org
In-Reply-To: <DB5PR0401MB1928DA88B03970E1EACFB1FF918C0@DB5PR0401MB1928.eurprd04.prod.outlook.com>
> -----Original Message-----
> From: Scott Wood
> Sent: Saturday, March 19, 2016 2:28 AM
> To: Arnd Bergmann; Rob Herring
> Cc: Yangbo Lu; linuxppc-dev@lists.ozlabs.org; devicetree@vger.kernel.org;
> ulf.hansson@linaro.org; Zhao Qiang; Russell King; Bhupesh Sharma;
> netdev@vger.kernel.org; Joerg Roedel; Kumar Gala; linux-
> mmc@vger.kernel.org; linux-kernel@vger.kernel.org; Yang-Leo Li;
> iommu@lists.linux-foundation.org; linux-i2c@vger.kernel.org; Claudiu
> Manoil; Santosh Shilimkar; Xiaobo Xie; linux-clk@vger.kernel.org; linux-
> arm-kernel@lists.infradead.org
> Subject: Re: [v6, 5/5] mmc: sdhci-of-esdhc: fix host version for T4240-
> R1.0-R2.0
>
> On 03/17/2016 12:06 PM, Arnd Bergmann wrote:
> > On Thursday 17 March 2016 12:01:01 Rob Herring wrote:
> >> On Mon, Mar 14, 2016 at 05:45:43PM +0000, Scott Wood wrote:
> >
> >>>>> This makes the driver non-portable. Better identify the specific
> >>>>> workarounds based on the compatible string for this device, or add
> >>>>> a boolean DT property for the quirk.
> >>>>>
> >>>>> Arnd
> >>>>
> >>>> [Lu Yangbo-B47093] Hi Arnd, we did have a discussion about using DTS
> in v1 before.
> >>>> https://patchwork.kernel.org/patch/6834221/
> >>>>
> >>>> We don't have a separate DTS file for each revision of an SOC and if
> we did, we'd constantly have people using the wrong one.
> >>>> In addition, the device tree is stable ABI and errata are often
> discovered after device tree are deployed.
> >>>> See the link for details.
> >>>>
> >>>> So we decide to read SVR from the device-config/guts MMIO block
> other than using DTS.
> >>>> Thanks.
> >>>
> >>> Also note that this driver is already only for fsl-specific
> >>> hardware, and it will still work even if fsl_guts doesn't find
> >>> anything to bind to
> >>> -- it just wouldn't be able to detect errata based on SVR in that
> case.
> >>
> >> IIRC, it is the same IP block as i.MX and Arnd's point is this won't
> >> even compile on !PPC. It is things like this that prevent sharing the
> >> driver.
>
> The whole point of using the MMIO SVR instead of the PPC SPR is so that
> it will work on ARM... The guts driver should build on any platform as
> long as OF is enabled, and if it doesn't find a node to bind to it will
> return 0 for SVR, and the eSDHC driver will continue (after printing an
> error that should be removed) without the ability to test for errata
> based on SVR.
>
> > I think the first four patches take care of building for ARM, but the
> > problem remains if you want to enable COMPILE_TEST as we need for
> > certain automated checking.
>
> What specific problem is there with COMPILE_TEST?
>
> >> Dealing with Si revs is a common problem. We should have a common
> >> solution. There is soc_device for this purpose.
> >
> > Exactly. The last time this came up, I think we agreed to implement a
> > helper using glob_match() on the soc_device strings. Unfortunately
> > this hasn't happened then, but I'd still prefer that over yet another
> > vendor-specific way of dealing with the generic issue.
>
> soc_device would require encoding the SVR as a string and then decoding
> the string, which is more complicated and error prone than having
> platform-specific code test a platform-specific number. And when would
> it get registered on arm64, which doesn't have platform code?
>
> -Scott
[Lu Yangbo-B47093] Hi Arnd, could you answer Scott's questions?
If you don't oppose this patch, I'd like to rework a new version for merging.
Thanks.
:)
^ permalink raw reply
* RE: [v6, 3/5] dt: move guts devicetree doc out of powerpc directory
From: Yangbo Lu @ 2016-03-25 6:38 UTC (permalink / raw)
To: Scott Wood, Rob Herring
Cc: devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org, Zhao Qiang,
Russell King, Bhupesh Sharma,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Santosh Shilimkar,
linux-mmc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
Jochen Friedrich, Xiaobo Xie,
iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org,
linux-i2c-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Claudiu Manoil,
Kumar Gala, Yang-Leo Li,
linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
linux-clk-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <HE1PR0401MB1931444381E249E41C45C748918C0-B0v07Ae2tarQP5LCsfKN8o3W/0Ik+aLCnBOFsp37pqbUKgpGm//BTAC/G2K4zDHf@public.gmane.org>
> -----Original Message-----
> From: Scott Wood
> Sent: Saturday, March 19, 2016 2:16 AM
> To: Rob Herring; Yangbo Lu
> Cc: devicetree-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org;
> linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org; linux-
> clk-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-i2c-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; iommu-cunTk1MwBs/ROKNJybVBZg@public.gmane.org
> foundation.org; netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org; linux-mmc-u79uwXL29TY76Z2rM5mHXA@public.gmane.org;
> Russell King; Jochen Friedrich; Joerg Roedel; Claudiu Manoil;
> ulf.hansson-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org; Bhupesh Sharma; Zhao Qiang; Kumar Gala; Santosh
> Shilimkar; Yang-Leo Li; Xiaobo Xie
> Subject: Re: [v6, 3/5] dt: move guts devicetree doc out of powerpc
> directory
>
> On 03/17/2016 12:06 PM, Rob Herring wrote:
> > On Wed, Mar 09, 2016 at 06:08:49PM +0800, Yangbo Lu wrote:
> >> Move guts devicetree doc to
> >> Documentation/devicetree/bindings/soc/fsl/
> >> since it's used by not only PowerPC but also ARM. And add a
> >> specification for 'little-endian' property.
> >>
> >> Signed-off-by: Yangbo Lu <yangbo.lu-3arQi8VN3Tc@public.gmane.org>
> >> ---
> >> Changes for v2:
> >> - None
> >> Changes for v3:
> >> - None
> >> Changes for v4:
> >> - Added this patch
> >> Changes for v5:
> >> - Modified the description for little-endian property Changes for
> >> v6:
> >> - None
> >> ---
> >> Documentation/devicetree/bindings/{powerpc => soc}/fsl/guts.txt | 3
> >> +++
> >> 1 file changed, 3 insertions(+)
> >> rename Documentation/devicetree/bindings/{powerpc =>
> >> soc}/fsl/guts.txt (91%)
> >>
> >> diff --git a/Documentation/devicetree/bindings/powerpc/fsl/guts.txt
> >> b/Documentation/devicetree/bindings/soc/fsl/guts.txt
> >> similarity index 91%
> >> rename from Documentation/devicetree/bindings/powerpc/fsl/guts.txt
> >> rename to Documentation/devicetree/bindings/soc/fsl/guts.txt
> >> index b71b203..07adca9 100644
> >> --- a/Documentation/devicetree/bindings/powerpc/fsl/guts.txt
> >> +++ b/Documentation/devicetree/bindings/soc/fsl/guts.txt
> >> @@ -25,6 +25,9 @@ Recommended properties:
> >> - fsl,liodn-bits : Indicates the number of defined bits in the LIODN
> >> registers, for those SOCs that have a PAMU device.
> >>
> >> + - little-endian : Indicates that the global utilities block is
> little
> >> + endian. The default is big endian.
> >
> > The default is "the native endianness of the system". So absence on an
> > ARM system would be LE.
>
> No. For this binding, the default is big-endian, because that's what
> existed for this device before an endian property was added.
>
> "endianness of the system" is not a well-defined concept.
>
> > This property is valid for any simple-bus device,
>
> Since when does simple-bus mean anything more than that the nodes
> underneath it can be used without bus-specific knowledge?
>
> > so it isn't really required to document per device. You can, but your
> > description had better match the documented behaviour.
>
> Documented where?
>
> In fact, Documentation/devicetree/bindings/common-properties.txt
> explicitly says of the endian properties, "If a binding supports these
> properties, then the binding should also specify the default behavior if
> none of these properties are present."
>
> -Scott
[Lu Yangbo-B47093] So, Rob, could you accept this patch after so much discussion?
:)
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Cong Wang @ 2016-03-25 5:33 UTC (permalink / raw)
To: Ben Greear; +Cc: Vijay Pandurangan, netdev, Evan Jones, Cong Wang
In-Reply-To: <56F4C8FD.7030907@candelatech.com>
On Thu, Mar 24, 2016 at 10:13 PM, Ben Greear <greearb@candelatech.com> wrote:
>
>
> On 03/24/2016 10:06 PM, Cong Wang wrote:
>>
>> On Thu, Mar 24, 2016 at 9:34 PM, Ben Greear <greearb@candelatech.com>
>> wrote:
>>>
>>>
>>>
>>> On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
>>>>
>>>>
>>>> Oops, I think my last email didn't go through due to an inadvertent
>>>> html attachment from my phone mail client.
>>>>
>>>> Can you send us a copy of a packet you're sending and/or confirm that
>>>> the IP and UDP4 checksums are set correctly in the packet?
>>>>
>>>> If those are set right, I think we need to read through the networking
>>>> code again to see why this is broken...
>>>
>>>
>>>
>>> Wireshark decodes the packet as having no checksum errors.
>>>
>>> I think the contents of the packet is correct, but the 'ip_summed'
>>> field is set incorrectly to 'NONE' when transmitting on a raw packet
>>> socket.
>>
>>
>> Yeah, these bugs are all due to the different interpretations of
>> ip_summed on TX path and RX path. I think the following patch
>> should work, if the comments don't mislead me. Could you give
>> it a try?
>>
>> For the long term, we need to unify the meaning of ip_summed
>> on TX path and RX path, or at least translate it in skb_scrub_packet().
>
>
> I can test this tomorrow, but I think it will not work. I'm not sending raw
> IP frames, I'm sending full ethernet frames. Socket is PF_PACKET, SOCK_RAW.
>
> Your patch may still be useful for others though?
Here we go:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 1ecfa71..ab66080 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1925,6 +1925,7 @@ static int packet_sendmsg_spkt(struct socket
*sock, struct msghdr *msg,
goto out_unlock;
}
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
@@ -2496,6 +2497,7 @@ static int tpacket_fill_skb(struct packet_sock
*po, struct sk_buff *skb,
ph.raw = frame;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->protocol = proto;
skb->dev = dev;
skb->priority = po->sk.sk_priority;
@@ -2805,6 +2807,7 @@ static struct sk_buff *packet_alloc_skb(struct
sock *sk, size_t prepad,
skb_put(skb, linear);
skb->data_len = len - linear;
skb->len += len - linear;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
return skb;
}
Thanks for testing!
^ permalink raw reply related
* Re: [PATCH 1/1] net: Add SO_REUSEPORT_LISTEN_OFF socket option as drain mode
From: Willy Tarreau @ 2016-03-25 5:28 UTC (permalink / raw)
To: Tom Herbert
Cc: Yann Ylavic, Eric Dumazet, Linux Kernel Network Developers,
Tolga Ceylan, Craig Gallek, Josh Snyder, Aaron Conole,
David S. Miller, Daniel Borkmann
In-Reply-To: <CALx6S37uZah89sNgH9wuD1J+_WEhd34Z5zmrnG8Qp-AQ7Ew=Jg@mail.gmail.com>
On Thu, Mar 24, 2016 at 04:54:03PM -0700, Tom Herbert wrote:
> On Thu, Mar 24, 2016 at 4:40 PM, Yann Ylavic <ylavic.dev@gmail.com> wrote:
> > I'll learn how to do this to get the best performances from the
> > server, but having to do so to work around what looks like a defect
> > (for simple/default SMP configurations at least, no NUMA or clever
> > CPU-affinity or queuing policy involved) seems odd in the first place.
> >
> I disagree with your assessment that there is a defect. SO_REUSEPORT
> is designed to spread packets amongst _equivalent_ connections. In the
> server draining case sockets are no longer equivalent, but that is a
> special case.
I partially disagree with you here Tom. Initially SO_REUSEPORT was not
used to spread packets but to allow soft restart in some applications.
I've been using it since 2001 in haproxy on *BSD and linux 2.2. It was
removed during 2.3 and I used to keep a patch to reimplement it in 2.4
(basically 2 or 3 lines, the infrastructure was still present), but the
patch was not accepted. The same patch worked for 2.6 and 3.x, allowing
me to continue to perform soft-restarts on Linux just like I used to do
on *BSD. When SO_REUSEPORT was reimplemented in 3.9 with load balancing,
I was happy because it at last allowed me to drop my patch and I got
the extra benefit of better load balancing of incoming connections.
But the main use we have for it (at least historically) is for soft
restarts, where one process replaces another one. Very few people use
more than one process in our case.
However given the benefits of the load spreading for extreme loads,
I'm willing to find how to achieve the same with BPF, but it's pretty
clear that at this point I have no idea where to start from and that
for a single process replacing a single one, it looks quite complicated.
For me quite frankly the special case is the load balancing which is
a side benefit (and a nice one, don't get me wrong).
That's why I would have found it nice to "fix" the process replacement
to avoid dropping incoming connections, though I don't want it to become
a problem for future improvements on BPF. I don't think the two lines I
proposed could become an issue but I'll live without them (or continue
to apply this patch).
BTW, I have no problem with having to write a little bit of assembly for
fast interfaces if it remains untouched for years, we do already have a
bit in haproxy. It's just a longterm investment.
Best regards,
Willy
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Vijay Pandurangan @ 2016-03-25 5:24 UTC (permalink / raw)
To: Ben Greear; +Cc: Cong Wang, netdev, Evan Jones, Cong Wang
In-Reply-To: <56F4C77E.1010608@candelatech.com>
On Fri, Mar 25, 2016 at 1:07 AM, Ben Greear <greearb@candelatech.com> wrote:
> On 03/24/2016 09:45 PM, Vijay Pandurangan wrote:
>>
>> Actually, maybe they should be set to CHECKSUM_PARTIAL if we want veth
>> to drop the packets if they have bad checksums before they hit the
>> application level.
>
>
> VETH is pretty special in that when you transmit a frame on one
> device, it's pair receives it, and unless there is RAM corruption
> or bugs in the kernel, then it cannot be corrupted.
Yeah, you're right that that's an optimization. However, I think that
we should first ensure that
a->veth->b
operates exactly like:
a->physical eth 1 -> physical eth 2->b
in all cases. Once we have that working everywhere we could think
about optimizations.
If we're willing to refactor, we could implement the optimization by
allowing veth devices to know whether their immediate peer is. If a
veth knows it's talking to another veth, it could under some
circumstances elide checksum calculation and verification. I'm not
sure what abstractions that would break, though. What do you guys
think?
>
> But, if you are routing frames from the network to veth
> devices, then the original packet could be corrupted, as
> described in your patch.
>
> Probably the right behaviour is to keep the old logic for packets
> originating from sockets, at least. I am not sure of a good way
> to implement that.
>
> As for testing, I am not sure. Probably you have to make a good
> effort and then just deal with fallout like what I found. I would guess
> that any of us who have ever written an interesting patch have also written
> an interesting bug!
>
>
> Thanks,
> Ben
>
> --
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Ben Greear @ 2016-03-25 5:13 UTC (permalink / raw)
To: Cong Wang; +Cc: Vijay Pandurangan, netdev, Evan Jones, Cong Wang
In-Reply-To: <CAM_iQpUaBD-HmHVAcEBCRw38PbecjYk2to+DO9TNkLY93u2_NA@mail.gmail.com>
On 03/24/2016 10:06 PM, Cong Wang wrote:
> On Thu, Mar 24, 2016 at 9:34 PM, Ben Greear <greearb@candelatech.com> wrote:
>>
>>
>> On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
>>>
>>> Oops, I think my last email didn't go through due to an inadvertent
>>> html attachment from my phone mail client.
>>>
>>> Can you send us a copy of a packet you're sending and/or confirm that
>>> the IP and UDP4 checksums are set correctly in the packet?
>>>
>>> If those are set right, I think we need to read through the networking
>>> code again to see why this is broken...
>>
>>
>> Wireshark decodes the packet as having no checksum errors.
>>
>> I think the contents of the packet is correct, but the 'ip_summed'
>> field is set incorrectly to 'NONE' when transmitting on a raw packet
>> socket.
>
> Yeah, these bugs are all due to the different interpretations of
> ip_summed on TX path and RX path. I think the following patch
> should work, if the comments don't mislead me. Could you give
> it a try?
>
> For the long term, we need to unify the meaning of ip_summed
> on TX path and RX path, or at least translate it in skb_scrub_packet().
I can test this tomorrow, but I think it will not work. I'm not sending raw
IP frames, I'm sending full ethernet frames. Socket is PF_PACKET, SOCK_RAW.
Your patch may still be useful for others though?
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Ben Greear @ 2016-03-25 5:07 UTC (permalink / raw)
To: Vijay Pandurangan; +Cc: Cong Wang, netdev, Evan Jones, Cong Wang
In-Reply-To: <CAKUBDd8vwvN4z5gP63ukVjRsgbjKQBZvVHv+bJdQRQgcxD5HGA@mail.gmail.com>
On 03/24/2016 09:45 PM, Vijay Pandurangan wrote:
> Actually, maybe they should be set to CHECKSUM_PARTIAL if we want veth
> to drop the packets if they have bad checksums before they hit the
> application level.
VETH is pretty special in that when you transmit a frame on one
device, it's pair receives it, and unless there is RAM corruption
or bugs in the kernel, then it cannot be corrupted.
But, if you are routing frames from the network to veth
devices, then the original packet could be corrupted, as
described in your patch.
Probably the right behaviour is to keep the old logic for packets
originating from sockets, at least. I am not sure of a good way
to implement that.
As for testing, I am not sure. Probably you have to make a good
effort and then just deal with fallout like what I found. I would guess
that any of us who have ever written an interesting patch have also written
an interesting bug!
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Cong Wang @ 2016-03-25 5:06 UTC (permalink / raw)
To: Ben Greear; +Cc: Vijay Pandurangan, netdev, Evan Jones, Cong Wang
In-Reply-To: <56F4BFF1.8010806@candelatech.com>
On Thu, Mar 24, 2016 at 9:34 PM, Ben Greear <greearb@candelatech.com> wrote:
>
>
> On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
>>
>> Oops, I think my last email didn't go through due to an inadvertent
>> html attachment from my phone mail client.
>>
>> Can you send us a copy of a packet you're sending and/or confirm that
>> the IP and UDP4 checksums are set correctly in the packet?
>>
>> If those are set right, I think we need to read through the networking
>> code again to see why this is broken...
>
>
> Wireshark decodes the packet as having no checksum errors.
>
> I think the contents of the packet is correct, but the 'ip_summed'
> field is set incorrectly to 'NONE' when transmitting on a raw packet
> socket.
Yeah, these bugs are all due to the different interpretations of
ip_summed on TX path and RX path. I think the following patch
should work, if the comments don't mislead me. Could you give
it a try?
For the long term, we need to unify the meaning of ip_summed
on TX path and RX path, or at least translate it in skb_scrub_packet().
Thanks.
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 8d22de7..726457e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -377,7 +377,7 @@ static int raw_send_hdrinc(struct sock *sk, struct
flowi4 *fl4,
iph = ip_hdr(skb);
skb_put(skb, length);
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 4319e65..e6b3e31 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -646,7 +646,7 @@ static int rawv6_send_hdrinc(struct sock *sk,
struct msghdr *msg, int length,
skb_reset_network_header(skb);
iph = ipv6_hdr(skb);
- skb->ip_summed = CHECKSUM_NONE;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
skb->transport_header = skb->network_header;
err = memcpy_from_msg(iph, msg, length);
^ permalink raw reply related
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Vijay Pandurangan @ 2016-03-25 4:45 UTC (permalink / raw)
To: Ben Greear; +Cc: Cong Wang, netdev, Evan Jones, Cong Wang
In-Reply-To: <CAKUBDd8ojaAYHZ6L_8HBetqL1P6v9iy9W9ThZwnnzf3-npt-Vg@mail.gmail.com>
Actually, maybe they should be set to CHECKSUM_PARTIAL if we want veth
to drop the packets if they have bad checksums before they hit the
application level.
On Fri, Mar 25, 2016 at 12:41 AM, Vijay Pandurangan <vijayp@vijayp.ca> wrote:
> agreed. It should maybe be set to CHECKSUM_UNNECESSARY. The comment
> seems to imply that it's treated the same as CHECKSUM_NONE but that's
> evidently not true. I think that would fix the checksumming issue but
> I'm fearful it may break something else:
> http://lxr.free-electrons.com/source/include/linux/skbuff.h#L177
>
> I'm really worried there are other equally subtle bugs hidden in this
> code. Do we have any kind of regression test, or any automated way to
> test all possible values on an skb to determine side effects to any
> change here? (I'm new to the kernel so sorry if there's an answer in
> an FAQ somewhere).
>
> If not,
> 1. how should we ensure that our change doesn't break something else?
> 2. Should we audit / simplify the checksum code or come up with a list
> of test cases that covers all uses?
>
>
> On Fri, Mar 25, 2016 at 12:34 AM, Ben Greear <greearb@candelatech.com> wrote:
>>
>>
>> On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
>>>
>>> Oops, I think my last email didn't go through due to an inadvertent
>>> html attachment from my phone mail client.
>>>
>>> Can you send us a copy of a packet you're sending and/or confirm that
>>> the IP and UDP4 checksums are set correctly in the packet?
>>>
>>> If those are set right, I think we need to read through the networking
>>> code again to see why this is broken...
>>
>>
>> Wireshark decodes the packet as having no checksum errors.
>>
>> I think the contents of the packet is correct, but the 'ip_summed'
>> field is set incorrectly to 'NONE' when transmitting on a raw packet
>> socket.
>>
>>
>> Thanks,
>> Ben
>>
>> --
>> Ben Greear <greearb@candelatech.com>
>> Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Vijay Pandurangan @ 2016-03-25 4:41 UTC (permalink / raw)
To: Ben Greear; +Cc: Cong Wang, netdev, Evan Jones, Cong Wang
In-Reply-To: <56F4BFF1.8010806@candelatech.com>
agreed. It should maybe be set to CHECKSUM_UNNECESSARY. The comment
seems to imply that it's treated the same as CHECKSUM_NONE but that's
evidently not true. I think that would fix the checksumming issue but
I'm fearful it may break something else:
http://lxr.free-electrons.com/source/include/linux/skbuff.h#L177
I'm really worried there are other equally subtle bugs hidden in this
code. Do we have any kind of regression test, or any automated way to
test all possible values on an skb to determine side effects to any
change here? (I'm new to the kernel so sorry if there's an answer in
an FAQ somewhere).
If not,
1. how should we ensure that our change doesn't break something else?
2. Should we audit / simplify the checksum code or come up with a list
of test cases that covers all uses?
On Fri, Mar 25, 2016 at 12:34 AM, Ben Greear <greearb@candelatech.com> wrote:
>
>
> On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
>>
>> Oops, I think my last email didn't go through due to an inadvertent
>> html attachment from my phone mail client.
>>
>> Can you send us a copy of a packet you're sending and/or confirm that
>> the IP and UDP4 checksums are set correctly in the packet?
>>
>> If those are set right, I think we need to read through the networking
>> code again to see why this is broken...
>
>
> Wireshark decodes the packet as having no checksum errors.
>
> I think the contents of the packet is correct, but the 'ip_summed'
> field is set incorrectly to 'NONE' when transmitting on a raw packet
> socket.
>
>
> Thanks,
> Ben
>
> --
> Ben Greear <greearb@candelatech.com>
> Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* Re: veth regression with "don’t modify ip_summed; doing so treats packets with bad checksums as good."
From: Ben Greear @ 2016-03-25 4:34 UTC (permalink / raw)
To: Vijay Pandurangan; +Cc: Cong Wang, netdev, Evan Jones, Cong Wang
In-Reply-To: <CAKUBDd9TjFTvXSEL=+J02PVndNG-gcrMOpRo_MFp4J-oOnLrvQ@mail.gmail.com>
On 03/24/2016 06:44 PM, Vijay Pandurangan wrote:
> Oops, I think my last email didn't go through due to an inadvertent
> html attachment from my phone mail client.
>
> Can you send us a copy of a packet you're sending and/or confirm that
> the IP and UDP4 checksums are set correctly in the packet?
>
> If those are set right, I think we need to read through the networking
> code again to see why this is broken...
Wireshark decodes the packet as having no checksum errors.
I think the contents of the packet is correct, but the 'ip_summed'
field is set incorrectly to 'NONE' when transmitting on a raw packet
socket.
Thanks,
Ben
--
Ben Greear <greearb@candelatech.com>
Candela Technologies Inc http://www.candelatech.com
^ permalink raw reply
* [PATCH] net: phy: bcm7xxx: Add entries for Broadcom BCM7346 and BCM7362
From: Jaedon Shin @ 2016-03-25 3:46 UTC (permalink / raw)
To: netdev; +Cc: Florian Fainelli, David S . Miller, Jaedon Shin
Add PHY entries for the Broadcom BCM7346 and BCM7362 chips, these are
40nm generation Ethernet PHY.
Fixes: 815717d1473e ("net: phy: bcm7xxx: Remove wildcard entries")
Signed-off-by: Jaedon Shin <jaedon.shin@gmail.com>
---
drivers/net/phy/bcm7xxx.c | 4 ++++
include/linux/brcmphy.h | 2 ++
2 files changed, 6 insertions(+)
diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index b881a7b1e4f6..9636da0b6efc 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -339,6 +339,8 @@ static struct phy_driver bcm7xxx_driver[] = {
BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"),
BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"),
+ BCM7XXX_40NM_EPHY(PHY_ID_BCM7346, "Broadcom BCM7346"),
+ BCM7XXX_40NM_EPHY(PHY_ID_BCM7362, "Broadcom BCM7362"),
BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"),
BCM7XXX_40NM_EPHY(PHY_ID_BCM7429, "Broadcom BCM7429"),
BCM7XXX_40NM_EPHY(PHY_ID_BCM7435, "Broadcom BCM7435"),
@@ -348,6 +350,8 @@ static struct mdio_device_id __maybe_unused bcm7xxx_tbl[] = {
{ PHY_ID_BCM7250, 0xfffffff0, },
{ PHY_ID_BCM7364, 0xfffffff0, },
{ PHY_ID_BCM7366, 0xfffffff0, },
+ { PHY_ID_BCM7346, 0xfffffff0, },
+ { PHY_ID_BCM7362, 0xfffffff0, },
{ PHY_ID_BCM7425, 0xfffffff0, },
{ PHY_ID_BCM7429, 0xfffffff0, },
{ PHY_ID_BCM7439, 0xfffffff0, },
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index f0ba9c2ec639..e3354b74286c 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -24,6 +24,8 @@
#define PHY_ID_BCM7250 0xae025280
#define PHY_ID_BCM7364 0xae025260
#define PHY_ID_BCM7366 0x600d8490
+#define PHY_ID_BCM7346 0x600d8650
+#define PHY_ID_BCM7362 0x600d84b0
#define PHY_ID_BCM7425 0x600d86b0
#define PHY_ID_BCM7429 0x600d8730
#define PHY_ID_BCM7435 0x600d8750
--
2.7.4
^ permalink raw reply related
* [PATCH v2] netpoll: Fix extra refcount release in netpoll_cleanup()
From: Bjorn Helgaas @ 2016-03-25 2:56 UTC (permalink / raw)
To: David S. Miller
Cc: Nikolay Aleksandrov, netdev, Neil Horman, Alexander Duyck,
linux-kernel
netpoll_setup() does a dev_hold() on np->dev, the netpoll device. If it
fails, it correctly does a dev_put() but leaves np->dev set. If we call
netpoll_cleanup() after the failure, np->dev is still set so we do another
dev_put(), which decrements the refcount an extra time.
It's questionable to call netpoll_cleanup() after netpoll_setup() fails,
but it can be difficult to find the problem, and we can easily avoid it in
this case. The extra decrements can lead to hangs like this:
unregister_netdevice: waiting for bond0 to become free. Usage count = -3
Set and clear np->dev at the points where we dev_hold() and dev_put() the
device.
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
net/core/netpoll.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 94acfc8..a57bd17 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -603,7 +603,6 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
const struct net_device_ops *ops;
int err;
- np->dev = ndev;
strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
@@ -670,6 +669,7 @@ int netpoll_setup(struct netpoll *np)
goto unlock;
}
dev_hold(ndev);
+ np->dev = ndev;
if (netdev_master_upper_dev_get(ndev)) {
np_err(np, "%s is a slave device, aborting\n", np->dev_name);
@@ -770,6 +770,7 @@ int netpoll_setup(struct netpoll *np)
return 0;
put:
+ np->dev = NULL;
dev_put(ndev);
unlock:
rtnl_unlock();
^ permalink raw reply related
* [PATCH net-next] phy: keep the BCMR_LOOPBACK bit while setup forced mode
From: Weidong Wang @ 2016-03-25 2:47 UTC (permalink / raw)
To: f.fainelli; +Cc: netdev, linux-kernel
When tested the PHY SGMII Loopback,:
1.set the LOOPBACK bit,
2.set the autoneg to AUTONEG_DISABLE, it calls the
genphy_setup_forced which will clear the bit.
So just keep the LOOPBACK bit while setup forced mode.
Signed-off-by: Weidong Wang <wangweidong1@huawei.com>
---
drivers/net/phy/phy_device.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index e551f3a..8da4b80 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1124,7 +1124,9 @@ static int genphy_config_advert(struct phy_device *phydev)
int genphy_setup_forced(struct phy_device *phydev)
{
int ctl = 0;
+ int val = phy_read(phydev, MII_BMCR);
+ ctl |= val & BMCR_LOOPBACK;
phydev->pause = 0;
phydev->asym_pause = 0;
--
2.7.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox