aboutsummaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/sfc
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/sfc')
-rw-r--r--drivers/net/ethernet/sfc/Kconfig33
-rw-r--r--drivers/net/ethernet/sfc/Makefile8
-rw-r--r--drivers/net/ethernet/sfc/bitfield.h52
-rw-r--r--drivers/net/ethernet/sfc/ef10.c3699
-rw-r--r--drivers/net/ethernet/sfc/ef10_regs.h355
-rw-r--r--drivers/net/ethernet/sfc/efx.c2039
-rw-r--r--drivers/net/ethernet/sfc/efx.h254
-rw-r--r--drivers/net/ethernet/sfc/enum.h42
-rw-r--r--drivers/net/ethernet/sfc/ethtool.c537
-rw-r--r--drivers/net/ethernet/sfc/falcon.c1317
-rw-r--r--drivers/net/ethernet/sfc/falcon_boards.c31
-rw-r--r--drivers/net/ethernet/sfc/falcon_xmac.c369
-rw-r--r--drivers/net/ethernet/sfc/farch.c2959
-rw-r--r--drivers/net/ethernet/sfc/farch_regs.h (renamed from drivers/net/ethernet/sfc/regs.h)292
-rw-r--r--drivers/net/ethernet/sfc/filter.c961
-rw-r--r--drivers/net/ethernet/sfc/filter.h252
-rw-r--r--drivers/net/ethernet/sfc/io.h105
-rw-r--r--drivers/net/ethernet/sfc/mac.h21
-rw-r--r--drivers/net/ethernet/sfc/mcdi.c1664
-rw-r--r--drivers/net/ethernet/sfc/mcdi.h399
-rw-r--r--drivers/net/ethernet/sfc/mcdi_mac.c145
-rw-r--r--drivers/net/ethernet/sfc/mcdi_mon.c534
-rw-r--r--drivers/net/ethernet/sfc/mcdi_pcol.h9010
-rw-r--r--drivers/net/ethernet/sfc/mcdi_port.c (renamed from drivers/net/ethernet/sfc/mcdi_phy.c)492
-rw-r--r--drivers/net/ethernet/sfc/mdio_10g.c4
-rw-r--r--drivers/net/ethernet/sfc/mdio_10g.h28
-rw-r--r--drivers/net/ethernet/sfc/mtd.c640
-rw-r--r--drivers/net/ethernet/sfc/net_driver.h903
-rw-r--r--drivers/net/ethernet/sfc/nic.c1834
-rw-r--r--drivers/net/ethernet/sfc/nic.h750
-rw-r--r--drivers/net/ethernet/sfc/phy.h27
-rw-r--r--drivers/net/ethernet/sfc/ptp.c1939
-rw-r--r--drivers/net/ethernet/sfc/qt202x_phy.c43
-rw-r--r--drivers/net/ethernet/sfc/rx.c1056
-rw-r--r--drivers/net/ethernet/sfc/selftest.c310
-rw-r--r--drivers/net/ethernet/sfc/selftest.h18
-rw-r--r--drivers/net/ethernet/sfc/siena.c878
-rw-r--r--drivers/net/ethernet/sfc/siena_sriov.c1645
-rw-r--r--drivers/net/ethernet/sfc/spi.h99
-rw-r--r--drivers/net/ethernet/sfc/tenxpress.c4
-rw-r--r--drivers/net/ethernet/sfc/tx.c1131
-rw-r--r--drivers/net/ethernet/sfc/txc43128_phy.c4
-rw-r--r--drivers/net/ethernet/sfc/vfdi.h255
-rw-r--r--drivers/net/ethernet/sfc/workarounds.h22
44 files changed, 27744 insertions, 9416 deletions
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 5d18841f0f3..08892129444 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -1,21 +1,38 @@
config SFC
- tristate "Solarflare SFC4000/SFC9000-family support"
- depends on PCI && INET
+ tristate "Solarflare SFC4000/SFC9000/SFC9100-family support"
+ depends on PCI
select MDIO
select CRC32
select I2C
select I2C_ALGOBIT
+ select PTP_1588_CLOCK
---help---
- This driver supports 10-gigabit Ethernet cards based on
- the Solarflare SFC4000 and SFC9000-family controllers.
+ This driver supports 10/40-gigabit Ethernet cards based on
+ the Solarflare SFC4000, SFC9000-family and SFC9100-family
+ controllers.
To compile this driver as a module, choose M here. The module
will be called sfc.
config SFC_MTD
- bool "Solarflare SFC4000/SFC9000-family MTD support"
+ bool "Solarflare SFC4000/SFC9000/SFC9100-family MTD support"
depends on SFC && MTD && !(SFC=y && MTD=m)
default y
---help---
- This exposes the on-board flash memory as MTD devices (e.g.
- /dev/mtd1). This makes it possible to upload new firmware
- to the NIC.
+ This exposes the on-board flash and/or EEPROM as MTD devices
+ (e.g. /dev/mtd1). This is required to update the firmware or
+ the boot configuration under Linux.
+config SFC_MCDI_MON
+ bool "Solarflare SFC9000/SFC9100-family hwmon support"
+ depends on SFC && HWMON && !(SFC=y && HWMON=m)
+ default y
+ ---help---
+ This exposes the on-board firmware-managed sensors as a
+ hardware monitor device.
+config SFC_SRIOV
+ bool "Solarflare SFC9000-family SR-IOV support"
+ depends on SFC && PCI_IOV
+ default y
+ ---help---
+ This enables support for the SFC9000 I/O Virtualization
+ features, allowing accelerated network performance in
+ virtualized environments.
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index ab31c7124db..3a83c0dca8e 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -1,8 +1,8 @@
-sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \
- falcon_xmac.o mcdi_mac.o \
- selftest.o ethtool.o qt202x_phy.o mdio_10g.o \
+sfc-y += efx.o nic.o farch.o falcon.o siena.o ef10.o tx.o \
+ rx.o selftest.o ethtool.o qt202x_phy.o mdio_10g.o \
tenxpress.o txc43128_phy.o falcon_boards.o \
- mcdi.o mcdi_phy.o
+ mcdi.o mcdi_port.o mcdi_mon.o ptp.o
sfc-$(CONFIG_SFC_MTD) += mtd.o
+sfc-$(CONFIG_SFC_SRIOV) += siena_sriov.o
obj-$(CONFIG_SFC) += sfc.o
diff --git a/drivers/net/ethernet/sfc/bitfield.h b/drivers/net/ethernet/sfc/bitfield.h
index 098ac2ad757..17d83f37fbf 100644
--- a/drivers/net/ethernet/sfc/bitfield.h
+++ b/drivers/net/ethernet/sfc/bitfield.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2009 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -29,6 +29,10 @@
/* Lowest bit numbers and widths */
#define EFX_DUMMY_FIELD_LBN 0
#define EFX_DUMMY_FIELD_WIDTH 0
+#define EFX_WORD_0_LBN 0
+#define EFX_WORD_0_WIDTH 16
+#define EFX_WORD_1_LBN 16
+#define EFX_WORD_1_WIDTH 16
#define EFX_DWORD_0_LBN 0
#define EFX_DWORD_0_WIDTH 32
#define EFX_DWORD_1_LBN 32
@@ -120,10 +124,10 @@ typedef union efx_oword {
* [0,high-low), with garbage in bits [high-low+1,...).
*/
#define EFX_EXTRACT_NATIVE(native_element, min, max, low, high) \
- (((low > max) || (high < min)) ? 0 : \
- ((low > min) ? \
- ((native_element) >> (low - min)) : \
- ((native_element) << (min - low))))
+ ((low) > (max) || (high) < (min) ? 0 : \
+ (low) > (min) ? \
+ (native_element) >> ((low) - (min)) : \
+ (native_element) << ((min) - (low)))
/*
* Extract bit field portion [low,high) from the 64-bit little-endian
@@ -142,27 +146,27 @@ typedef union efx_oword {
#define EFX_EXTRACT_OWORD64(oword, low, high) \
((EFX_EXTRACT64((oword).u64[0], 0, 63, low, high) | \
EFX_EXTRACT64((oword).u64[1], 64, 127, low, high)) & \
- EFX_MASK64(high + 1 - low))
+ EFX_MASK64((high) + 1 - (low)))
#define EFX_EXTRACT_QWORD64(qword, low, high) \
(EFX_EXTRACT64((qword).u64[0], 0, 63, low, high) & \
- EFX_MASK64(high + 1 - low))
+ EFX_MASK64((high) + 1 - (low)))
#define EFX_EXTRACT_OWORD32(oword, low, high) \
((EFX_EXTRACT32((oword).u32[0], 0, 31, low, high) | \
EFX_EXTRACT32((oword).u32[1], 32, 63, low, high) | \
EFX_EXTRACT32((oword).u32[2], 64, 95, low, high) | \
EFX_EXTRACT32((oword).u32[3], 96, 127, low, high)) & \
- EFX_MASK32(high + 1 - low))
+ EFX_MASK32((high) + 1 - (low)))
#define EFX_EXTRACT_QWORD32(qword, low, high) \
((EFX_EXTRACT32((qword).u32[0], 0, 31, low, high) | \
EFX_EXTRACT32((qword).u32[1], 32, 63, low, high)) & \
- EFX_MASK32(high + 1 - low))
+ EFX_MASK32((high) + 1 - (low)))
#define EFX_EXTRACT_DWORD(dword, low, high) \
(EFX_EXTRACT32((dword).u32[0], 0, 31, low, high) & \
- EFX_MASK32(high + 1 - low))
+ EFX_MASK32((high) + 1 - (low)))
#define EFX_OWORD_FIELD64(oword, field) \
EFX_EXTRACT_OWORD64(oword, EFX_LOW_BIT(field), \
@@ -442,46 +446,46 @@ typedef union efx_oword {
cpu_to_le32(EFX_INSERT_NATIVE(min, max, low, high, value))
#define EFX_INPLACE_MASK64(min, max, low, high) \
- EFX_INSERT64(min, max, low, high, EFX_MASK64(high + 1 - low))
+ EFX_INSERT64(min, max, low, high, EFX_MASK64((high) + 1 - (low)))
#define EFX_INPLACE_MASK32(min, max, low, high) \
- EFX_INSERT32(min, max, low, high, EFX_MASK32(high + 1 - low))
+ EFX_INSERT32(min, max, low, high, EFX_MASK32((high) + 1 - (low)))
#define EFX_SET_OWORD64(oword, low, high, value) do { \
- (oword).u64[0] = (((oword).u64[0] \
+ (oword).u64[0] = (((oword).u64[0] \
& ~EFX_INPLACE_MASK64(0, 63, low, high)) \
| EFX_INSERT64(0, 63, low, high, value)); \
- (oword).u64[1] = (((oword).u64[1] \
+ (oword).u64[1] = (((oword).u64[1] \
& ~EFX_INPLACE_MASK64(64, 127, low, high)) \
| EFX_INSERT64(64, 127, low, high, value)); \
} while (0)
#define EFX_SET_QWORD64(qword, low, high, value) do { \
- (qword).u64[0] = (((qword).u64[0] \
+ (qword).u64[0] = (((qword).u64[0] \
& ~EFX_INPLACE_MASK64(0, 63, low, high)) \
| EFX_INSERT64(0, 63, low, high, value)); \
} while (0)
#define EFX_SET_OWORD32(oword, low, high, value) do { \
- (oword).u32[0] = (((oword).u32[0] \
+ (oword).u32[0] = (((oword).u32[0] \
& ~EFX_INPLACE_MASK32(0, 31, low, high)) \
| EFX_INSERT32(0, 31, low, high, value)); \
- (oword).u32[1] = (((oword).u32[1] \
+ (oword).u32[1] = (((oword).u32[1] \
& ~EFX_INPLACE_MASK32(32, 63, low, high)) \
| EFX_INSERT32(32, 63, low, high, value)); \
- (oword).u32[2] = (((oword).u32[2] \
+ (oword).u32[2] = (((oword).u32[2] \
& ~EFX_INPLACE_MASK32(64, 95, low, high)) \
| EFX_INSERT32(64, 95, low, high, value)); \
- (oword).u32[3] = (((oword).u32[3] \
+ (oword).u32[3] = (((oword).u32[3] \
& ~EFX_INPLACE_MASK32(96, 127, low, high)) \
| EFX_INSERT32(96, 127, low, high, value)); \
} while (0)
#define EFX_SET_QWORD32(qword, low, high, value) do { \
- (qword).u32[0] = (((qword).u32[0] \
+ (qword).u32[0] = (((qword).u32[0] \
& ~EFX_INPLACE_MASK32(0, 31, low, high)) \
| EFX_INSERT32(0, 31, low, high, value)); \
- (qword).u32[1] = (((qword).u32[1] \
+ (qword).u32[1] = (((qword).u32[1] \
& ~EFX_INPLACE_MASK32(32, 63, low, high)) \
| EFX_INSERT32(32, 63, low, high, value)); \
} while (0)
@@ -531,8 +535,8 @@ typedef union efx_oword {
/* Static initialiser */
-#define EFX_OWORD32(a, b, c, d) \
- { .u32 = { cpu_to_le32(a), cpu_to_le32(b), \
+#define EFX_OWORD32(a, b, c, d) \
+ { .u32 = { cpu_to_le32(a), cpu_to_le32(b), \
cpu_to_le32(c), cpu_to_le32(d) } }
#endif /* EFX_BITFIELD_H */
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
new file mode 100644
index 00000000000..b5ed30a3914
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -0,0 +1,3699 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2012-2013 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include "net_driver.h"
+#include "ef10_regs.h"
+#include "io.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+#include "nic.h"
+#include "workarounds.h"
+#include "selftest.h"
+#include <linux/in.h>
+#include <linux/jhash.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+
+/* Hardware control for EF10 architecture including 'Huntington'. */
+
+#define EFX_EF10_DRVGEN_EV 7
+enum {
+ EFX_EF10_TEST = 1,
+ EFX_EF10_REFILL,
+};
+
+/* The reserved RSS context value */
+#define EFX_EF10_RSS_CONTEXT_INVALID 0xffffffff
+
+/* The filter table(s) are managed by firmware and we have write-only
+ * access. When removing filters we must identify them to the
+ * firmware by a 64-bit handle, but this is too wide for Linux kernel
+ * interfaces (32-bit for RX NFC, 16-bit for RFS). Also, we need to
+ * be able to tell in advance whether a requested insertion will
+ * replace an existing filter. Therefore we maintain a software hash
+ * table, which should be at least as large as the hardware hash
+ * table.
+ *
+ * Huntington has a single 8K filter table shared between all filter
+ * types and both ports.
+ */
+#define HUNT_FILTER_TBL_ROWS 8192
+
+struct efx_ef10_filter_table {
+/* The RX match field masks supported by this fw & hw, in order of priority */
+ enum efx_filter_match_flags rx_match_flags[
+ MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM];
+ unsigned int rx_match_count;
+
+ struct {
+ unsigned long spec; /* pointer to spec plus flag bits */
+/* BUSY flag indicates that an update is in progress. AUTO_OLD is
+ * used to mark and sweep MAC filters for the device address lists.
+ */
+#define EFX_EF10_FILTER_FLAG_BUSY 1UL
+#define EFX_EF10_FILTER_FLAG_AUTO_OLD 2UL
+#define EFX_EF10_FILTER_FLAGS 3UL
+ u64 handle; /* firmware handle */
+ } *entry;
+ wait_queue_head_t waitq;
+/* Shadow of net_device address lists, guarded by mac_lock */
+#define EFX_EF10_FILTER_DEV_UC_MAX 32
+#define EFX_EF10_FILTER_DEV_MC_MAX 256
+ struct {
+ u8 addr[ETH_ALEN];
+ u16 id;
+ } dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX],
+ dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX];
+ int dev_uc_count; /* negative for PROMISC */
+ int dev_mc_count; /* negative for PROMISC/ALLMULTI */
+};
+
+/* An arbitrary search limit for the software hash table */
+#define EFX_EF10_FILTER_SEARCH_LIMIT 200
+
+static void efx_ef10_rx_push_rss_config(struct efx_nic *efx);
+static void efx_ef10_rx_free_indir_table(struct efx_nic *efx);
+static void efx_ef10_filter_table_remove(struct efx_nic *efx);
+
+static int efx_ef10_get_warm_boot_count(struct efx_nic *efx)
+{
+ efx_dword_t reg;
+
+ efx_readd(efx, &reg, ER_DZ_BIU_MC_SFT_STATUS);
+ return EFX_DWORD_FIELD(reg, EFX_WORD_1) == 0xb007 ?
+ EFX_DWORD_FIELD(reg, EFX_WORD_0) : -EIO;
+}
+
+static unsigned int efx_ef10_mem_map_size(struct efx_nic *efx)
+{
+ return resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]);
+}
+
+static int efx_ef10_init_datapath_caps(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_OUT_LEN);
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ size_t outlen;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < sizeof(outbuf)) {
+ netif_err(efx, drv, efx->net_dev,
+ "unable to read datapath firmware capabilities\n");
+ return -EIO;
+ }
+
+ nic_data->datapath_caps =
+ MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1);
+
+ if (!(nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))) {
+ netif_err(efx, drv, efx->net_dev,
+ "current firmware does not support TSO\n");
+ return -ENODEV;
+ }
+
+ if (!(nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_LBN))) {
+ netif_err(efx, probe, efx->net_dev,
+ "current firmware does not support an RX prefix\n");
+ return -ENODEV;
+ }
+
+ return 0;
+}
+
+static int efx_ef10_get_sysclk_freq(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CLOCK_OUT_LEN);
+ int rc;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_CLOCK, NULL, 0,
+ outbuf, sizeof(outbuf), NULL);
+ if (rc)
+ return rc;
+ rc = MCDI_DWORD(outbuf, GET_CLOCK_OUT_SYS_FREQ);
+ return rc > 0 ? rc : -ERANGE;
+}
+
+static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_MAC_ADDRESSES_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_MAC_ADDRESSES_IN_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_MAC_ADDRESSES, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN)
+ return -EIO;
+
+ ether_addr_copy(mac_address,
+ MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE));
+ return 0;
+}
+
+static int efx_ef10_probe(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data;
+ int i, rc;
+
+ /* We can have one VI for each 8K region. However, until we
+ * use TX option descriptors we need two TX queues per channel.
+ */
+ efx->max_channels =
+ min_t(unsigned int,
+ EFX_MAX_CHANNELS,
+ resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]) /
+ (EFX_VI_PAGE_SIZE * EFX_TXQ_TYPES));
+ BUG_ON(efx->max_channels == 0);
+
+ nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL);
+ if (!nic_data)
+ return -ENOMEM;
+ efx->nic_data = nic_data;
+
+ rc = efx_nic_alloc_buffer(efx, &nic_data->mcdi_buf,
+ 8 + MCDI_CTL_SDU_LEN_MAX_V2, GFP_KERNEL);
+ if (rc)
+ goto fail1;
+
+ /* Get the MC's warm boot count. In case it's rebooting right
+ * now, be prepared to retry.
+ */
+ i = 0;
+ for (;;) {
+ rc = efx_ef10_get_warm_boot_count(efx);
+ if (rc >= 0)
+ break;
+ if (++i == 5)
+ goto fail2;
+ ssleep(1);
+ }
+ nic_data->warm_boot_count = rc;
+
+ nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
+
+ /* In case we're recovering from a crash (kexec), we want to
+ * cancel any outstanding request by the previous user of this
+ * function. We send a special message using the least
+ * significant bits of the 'high' (doorbell) register.
+ */
+ _efx_writed(efx, cpu_to_le32(1), ER_DZ_MC_DB_HWRD);
+
+ rc = efx_mcdi_init(efx);
+ if (rc)
+ goto fail2;
+
+ /* Reset (most) configuration for this function */
+ rc = efx_mcdi_reset(efx, RESET_TYPE_ALL);
+ if (rc)
+ goto fail3;
+
+ /* Enable event logging */
+ rc = efx_mcdi_log_ctrl(efx, true, false, 0);
+ if (rc)
+ goto fail3;
+
+ rc = efx_ef10_init_datapath_caps(efx);
+ if (rc < 0)
+ goto fail3;
+
+ efx->rx_packet_len_offset =
+ ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE;
+
+ rc = efx_mcdi_port_get_number(efx);
+ if (rc < 0)
+ goto fail3;
+ efx->port_num = rc;
+
+ rc = efx_ef10_get_mac_address(efx, efx->net_dev->perm_addr);
+ if (rc)
+ goto fail3;
+
+ rc = efx_ef10_get_sysclk_freq(efx);
+ if (rc < 0)
+ goto fail3;
+ efx->timer_quantum_ns = 1536000 / rc; /* 1536 cycles */
+
+ /* Check whether firmware supports bug 35388 workaround */
+ rc = efx_mcdi_set_workaround(efx, MC_CMD_WORKAROUND_BUG35388, true);
+ if (rc == 0)
+ nic_data->workaround_35388 = true;
+ else if (rc != -ENOSYS && rc != -ENOENT)
+ goto fail3;
+ netif_dbg(efx, probe, efx->net_dev,
+ "workaround for bug 35388 is %sabled\n",
+ nic_data->workaround_35388 ? "en" : "dis");
+
+ rc = efx_mcdi_mon_probe(efx);
+ if (rc)
+ goto fail3;
+
+ efx_ptp_probe(efx, NULL);
+
+ return 0;
+
+fail3:
+ efx_mcdi_fini(efx);
+fail2:
+ efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
+fail1:
+ kfree(nic_data);
+ efx->nic_data = NULL;
+ return rc;
+}
+
+static int efx_ef10_free_vis(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+ size_t outlen;
+ int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+
+ /* -EALREADY means nothing to free, so ignore */
+ if (rc == -EALREADY)
+ rc = 0;
+ if (rc)
+ efx_mcdi_display_error(efx, MC_CMD_FREE_VIS, 0, outbuf, outlen,
+ rc);
+ return rc;
+}
+
+#ifdef EFX_USE_PIO
+
+static void efx_ef10_free_piobufs(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FREE_PIOBUF_IN_LEN);
+ unsigned int i;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_FREE_PIOBUF_OUT_LEN != 0);
+
+ for (i = 0; i < nic_data->n_piobufs; i++) {
+ MCDI_SET_DWORD(inbuf, FREE_PIOBUF_IN_PIOBUF_HANDLE,
+ nic_data->piobuf_handle[i]);
+ rc = efx_mcdi_rpc(efx, MC_CMD_FREE_PIOBUF, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ WARN_ON(rc);
+ }
+
+ nic_data->n_piobufs = 0;
+}
+
+static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_PIOBUF_OUT_LEN);
+ unsigned int i;
+ size_t outlen;
+ int rc = 0;
+
+ BUILD_BUG_ON(MC_CMD_ALLOC_PIOBUF_IN_LEN != 0);
+
+ for (i = 0; i < n; i++) {
+ rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ break;
+ if (outlen < MC_CMD_ALLOC_PIOBUF_OUT_LEN) {
+ rc = -EIO;
+ break;
+ }
+ nic_data->piobuf_handle[i] =
+ MCDI_DWORD(outbuf, ALLOC_PIOBUF_OUT_PIOBUF_HANDLE);
+ netif_dbg(efx, probe, efx->net_dev,
+ "allocated PIO buffer %u handle %x\n", i,
+ nic_data->piobuf_handle[i]);
+ }
+
+ nic_data->n_piobufs = i;
+ if (rc)
+ efx_ef10_free_piobufs(efx);
+ return rc;
+}
+
+static int efx_ef10_link_piobufs(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ MCDI_DECLARE_BUF(inbuf,
+ max(MC_CMD_LINK_PIOBUF_IN_LEN,
+ MC_CMD_UNLINK_PIOBUF_IN_LEN));
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+ unsigned int offset, index;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0);
+ BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0);
+
+ /* Link a buffer to each VI in the write-combining mapping */
+ for (index = 0; index < nic_data->n_piobufs; ++index) {
+ MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE,
+ nic_data->piobuf_handle[index]);
+ MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_TXQ_INSTANCE,
+ nic_data->pio_write_vi_base + index);
+ rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
+ inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
+ NULL, 0, NULL);
+ if (rc) {
+ netif_err(efx, drv, efx->net_dev,
+ "failed to link VI %u to PIO buffer %u (%d)\n",
+ nic_data->pio_write_vi_base + index, index,
+ rc);
+ goto fail;
+ }
+ netif_dbg(efx, probe, efx->net_dev,
+ "linked VI %u to PIO buffer %u\n",
+ nic_data->pio_write_vi_base + index, index);
+ }
+
+ /* Link a buffer to each TX queue */
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ /* We assign the PIO buffers to queues in
+ * reverse order to allow for the following
+ * special case.
+ */
+ offset = ((efx->tx_channel_offset + efx->n_tx_channels -
+ tx_queue->channel->channel - 1) *
+ efx_piobuf_size);
+ index = offset / ER_DZ_TX_PIOBUF_SIZE;
+ offset = offset % ER_DZ_TX_PIOBUF_SIZE;
+
+ /* When the host page size is 4K, the first
+ * host page in the WC mapping may be within
+ * the same VI page as the last TX queue. We
+ * can only link one buffer to each VI.
+ */
+ if (tx_queue->queue == nic_data->pio_write_vi_base) {
+ BUG_ON(index != 0);
+ rc = 0;
+ } else {
+ MCDI_SET_DWORD(inbuf,
+ LINK_PIOBUF_IN_PIOBUF_HANDLE,
+ nic_data->piobuf_handle[index]);
+ MCDI_SET_DWORD(inbuf,
+ LINK_PIOBUF_IN_TXQ_INSTANCE,
+ tx_queue->queue);
+ rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF,
+ inbuf, MC_CMD_LINK_PIOBUF_IN_LEN,
+ NULL, 0, NULL);
+ }
+
+ if (rc) {
+ /* This is non-fatal; the TX path just
+ * won't use PIO for this queue
+ */
+ netif_err(efx, drv, efx->net_dev,
+ "failed to link VI %u to PIO buffer %u (%d)\n",
+ tx_queue->queue, index, rc);
+ tx_queue->piobuf = NULL;
+ } else {
+ tx_queue->piobuf =
+ nic_data->pio_write_base +
+ index * EFX_VI_PAGE_SIZE + offset;
+ tx_queue->piobuf_offset = offset;
+ netif_dbg(efx, probe, efx->net_dev,
+ "linked VI %u to PIO buffer %u offset %x addr %p\n",
+ tx_queue->queue, index,
+ tx_queue->piobuf_offset,
+ tx_queue->piobuf);
+ }
+ }
+ }
+
+ return 0;
+
+fail:
+ while (index--) {
+ MCDI_SET_DWORD(inbuf, UNLINK_PIOBUF_IN_TXQ_INSTANCE,
+ nic_data->pio_write_vi_base + index);
+ efx_mcdi_rpc(efx, MC_CMD_UNLINK_PIOBUF,
+ inbuf, MC_CMD_UNLINK_PIOBUF_IN_LEN,
+ NULL, 0, NULL);
+ }
+ return rc;
+}
+
+#else /* !EFX_USE_PIO */
+
+static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n)
+{
+ return n == 0 ? 0 : -ENOBUFS;
+}
+
+static int efx_ef10_link_piobufs(struct efx_nic *efx)
+{
+ return 0;
+}
+
+static void efx_ef10_free_piobufs(struct efx_nic *efx)
+{
+}
+
+#endif /* EFX_USE_PIO */
+
+static void efx_ef10_remove(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ efx_ptp_remove(efx);
+
+ efx_mcdi_mon_remove(efx);
+
+ efx_ef10_rx_free_indir_table(efx);
+
+ if (nic_data->wc_membase)
+ iounmap(nic_data->wc_membase);
+
+ rc = efx_ef10_free_vis(efx);
+ WARN_ON(rc != 0);
+
+ if (!nic_data->must_restore_piobufs)
+ efx_ef10_free_piobufs(efx);
+
+ efx_mcdi_fini(efx);
+ efx_nic_free_buffer(efx, &nic_data->mcdi_buf);
+ kfree(nic_data);
+}
+
+static int efx_ef10_alloc_vis(struct efx_nic *efx,
+ unsigned int min_vis, unsigned int max_vis)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_ALLOC_VIS_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_VIS_OUT_LEN);
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MIN_VI_COUNT, min_vis);
+ MCDI_SET_DWORD(inbuf, ALLOC_VIS_IN_MAX_VI_COUNT, max_vis);
+ rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_VIS, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc != 0)
+ return rc;
+
+ if (outlen < MC_CMD_ALLOC_VIS_OUT_LEN)
+ return -EIO;
+
+ netif_dbg(efx, drv, efx->net_dev, "base VI is A0x%03x\n",
+ MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE));
+
+ nic_data->vi_base = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_BASE);
+ nic_data->n_allocated_vis = MCDI_DWORD(outbuf, ALLOC_VIS_OUT_VI_COUNT);
+ return 0;
+}
+
+/* Note that the failure path of this function does not free
+ * resources, as this will be done by efx_ef10_remove().
+ */
+static int efx_ef10_dimension_resources(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ unsigned int uc_mem_map_size, wc_mem_map_size;
+ unsigned int min_vis, pio_write_vi_base, max_vis;
+ void __iomem *membase;
+ int rc;
+
+ min_vis = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES);
+
+#ifdef EFX_USE_PIO
+ /* Try to allocate PIO buffers if wanted and if the full
+ * number of PIO buffers would be sufficient to allocate one
+ * copy-buffer per TX channel. Failure is non-fatal, as there
+ * are only a small number of PIO buffers shared between all
+ * functions of the controller.
+ */
+ if (efx_piobuf_size != 0 &&
+ ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size * EF10_TX_PIOBUF_COUNT >=
+ efx->n_tx_channels) {
+ unsigned int n_piobufs =
+ DIV_ROUND_UP(efx->n_tx_channels,
+ ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size);
+
+ rc = efx_ef10_alloc_piobufs(efx, n_piobufs);
+ if (rc)
+ netif_err(efx, probe, efx->net_dev,
+ "failed to allocate PIO buffers (%d)\n", rc);
+ else
+ netif_dbg(efx, probe, efx->net_dev,
+ "allocated %u PIO buffers\n", n_piobufs);
+ }
+#else
+ nic_data->n_piobufs = 0;
+#endif
+
+ /* PIO buffers should be mapped with write-combining enabled,
+ * and we want to make single UC and WC mappings rather than
+ * several of each (in fact that's the only option if host
+ * page size is >4K). So we may allocate some extra VIs just
+ * for writing PIO buffers through.
+ *
+ * The UC mapping contains (min_vis - 1) complete VIs and the
+ * first half of the next VI. Then the WC mapping begins with
+ * the second half of this last VI.
+ */
+ uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE +
+ ER_DZ_TX_PIOBUF);
+ if (nic_data->n_piobufs) {
+ /* pio_write_vi_base rounds down to give the number of complete
+ * VIs inside the UC mapping.
+ */
+ pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE;
+ wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base +
+ nic_data->n_piobufs) *
+ EFX_VI_PAGE_SIZE) -
+ uc_mem_map_size);
+ max_vis = pio_write_vi_base + nic_data->n_piobufs;
+ } else {
+ pio_write_vi_base = 0;
+ wc_mem_map_size = 0;
+ max_vis = min_vis;
+ }
+
+ /* In case the last attached driver failed to free VIs, do it now */
+ rc = efx_ef10_free_vis(efx);
+ if (rc != 0)
+ return rc;
+
+ rc = efx_ef10_alloc_vis(efx, min_vis, max_vis);
+ if (rc != 0)
+ return rc;
+
+ /* If we didn't get enough VIs to map all the PIO buffers, free the
+ * PIO buffers
+ */
+ if (nic_data->n_piobufs &&
+ nic_data->n_allocated_vis <
+ pio_write_vi_base + nic_data->n_piobufs) {
+ netif_dbg(efx, probe, efx->net_dev,
+ "%u VIs are not sufficient to map %u PIO buffers\n",
+ nic_data->n_allocated_vis, nic_data->n_piobufs);
+ efx_ef10_free_piobufs(efx);
+ }
+
+ /* Shrink the original UC mapping of the memory BAR */
+ membase = ioremap_nocache(efx->membase_phys, uc_mem_map_size);
+ if (!membase) {
+ netif_err(efx, probe, efx->net_dev,
+ "could not shrink memory BAR to %x\n",
+ uc_mem_map_size);
+ return -ENOMEM;
+ }
+ iounmap(efx->membase);
+ efx->membase = membase;
+
+ /* Set up the WC mapping if needed */
+ if (wc_mem_map_size) {
+ nic_data->wc_membase = ioremap_wc(efx->membase_phys +
+ uc_mem_map_size,
+ wc_mem_map_size);
+ if (!nic_data->wc_membase) {
+ netif_err(efx, probe, efx->net_dev,
+ "could not allocate WC mapping of size %x\n",
+ wc_mem_map_size);
+ return -ENOMEM;
+ }
+ nic_data->pio_write_vi_base = pio_write_vi_base;
+ nic_data->pio_write_base =
+ nic_data->wc_membase +
+ (pio_write_vi_base * EFX_VI_PAGE_SIZE + ER_DZ_TX_PIOBUF -
+ uc_mem_map_size);
+
+ rc = efx_ef10_link_piobufs(efx);
+ if (rc)
+ efx_ef10_free_piobufs(efx);
+ }
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "memory BAR at %pa (virtual %p+%x UC, %p+%x WC)\n",
+ &efx->membase_phys, efx->membase, uc_mem_map_size,
+ nic_data->wc_membase, wc_mem_map_size);
+
+ return 0;
+}
+
+static int efx_ef10_init_nic(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ if (nic_data->must_check_datapath_caps) {
+ rc = efx_ef10_init_datapath_caps(efx);
+ if (rc)
+ return rc;
+ nic_data->must_check_datapath_caps = false;
+ }
+
+ if (nic_data->must_realloc_vis) {
+ /* We cannot let the number of VIs change now */
+ rc = efx_ef10_alloc_vis(efx, nic_data->n_allocated_vis,
+ nic_data->n_allocated_vis);
+ if (rc)
+ return rc;
+ nic_data->must_realloc_vis = false;
+ }
+
+ if (nic_data->must_restore_piobufs && nic_data->n_piobufs) {
+ rc = efx_ef10_alloc_piobufs(efx, nic_data->n_piobufs);
+ if (rc == 0) {
+ rc = efx_ef10_link_piobufs(efx);
+ if (rc)
+ efx_ef10_free_piobufs(efx);
+ }
+
+ /* Log an error on failure, but this is non-fatal */
+ if (rc)
+ netif_err(efx, drv, efx->net_dev,
+ "failed to restore PIO buffers (%d)\n", rc);
+ nic_data->must_restore_piobufs = false;
+ }
+
+ efx_ef10_rx_push_rss_config(efx);
+ return 0;
+}
+
+static void efx_ef10_reset_mc_allocations(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+ /* All our allocations have been reset */
+ nic_data->must_realloc_vis = true;
+ nic_data->must_restore_filters = true;
+ nic_data->must_restore_piobufs = true;
+ nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
+}
+
+static int efx_ef10_map_reset_flags(u32 *flags)
+{
+ enum {
+ EF10_RESET_PORT = ((ETH_RESET_MAC | ETH_RESET_PHY) <<
+ ETH_RESET_SHARED_SHIFT),
+ EF10_RESET_MC = ((ETH_RESET_DMA | ETH_RESET_FILTER |
+ ETH_RESET_OFFLOAD | ETH_RESET_MAC |
+ ETH_RESET_PHY | ETH_RESET_MGMT) <<
+ ETH_RESET_SHARED_SHIFT)
+ };
+
+ /* We assume for now that our PCI function is permitted to
+ * reset everything.
+ */
+
+ if ((*flags & EF10_RESET_MC) == EF10_RESET_MC) {
+ *flags &= ~EF10_RESET_MC;
+ return RESET_TYPE_WORLD;
+ }
+
+ if ((*flags & EF10_RESET_PORT) == EF10_RESET_PORT) {
+ *flags &= ~EF10_RESET_PORT;
+ return RESET_TYPE_ALL;
+ }
+
+ /* no invisible reset implemented */
+
+ return -EINVAL;
+}
+
+static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type)
+{
+ int rc = efx_mcdi_reset(efx, reset_type);
+
+ /* If it was a port reset, trigger reallocation of MC resources.
+ * Note that on an MC reset nothing needs to be done now because we'll
+ * detect the MC reset later and handle it then.
+ * For an FLR, we never get an MC reset event, but the MC has reset all
+ * resources assigned to us, so we have to trigger reallocation now.
+ */
+ if ((reset_type == RESET_TYPE_ALL ||
+ reset_type == RESET_TYPE_MCDI_TIMEOUT) && !rc)
+ efx_ef10_reset_mc_allocations(efx);
+ return rc;
+}
+
+#define EF10_DMA_STAT(ext_name, mcdi_name) \
+ [EF10_STAT_ ## ext_name] = \
+ { #ext_name, 64, 8 * MC_CMD_MAC_ ## mcdi_name }
+#define EF10_DMA_INVIS_STAT(int_name, mcdi_name) \
+ [EF10_STAT_ ## int_name] = \
+ { NULL, 64, 8 * MC_CMD_MAC_ ## mcdi_name }
+#define EF10_OTHER_STAT(ext_name) \
+ [EF10_STAT_ ## ext_name] = { #ext_name, 0, 0 }
+
+static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = {
+ EF10_DMA_STAT(tx_bytes, TX_BYTES),
+ EF10_DMA_STAT(tx_packets, TX_PKTS),
+ EF10_DMA_STAT(tx_pause, TX_PAUSE_PKTS),
+ EF10_DMA_STAT(tx_control, TX_CONTROL_PKTS),
+ EF10_DMA_STAT(tx_unicast, TX_UNICAST_PKTS),
+ EF10_DMA_STAT(tx_multicast, TX_MULTICAST_PKTS),
+ EF10_DMA_STAT(tx_broadcast, TX_BROADCAST_PKTS),
+ EF10_DMA_STAT(tx_lt64, TX_LT64_PKTS),
+ EF10_DMA_STAT(tx_64, TX_64_PKTS),
+ EF10_DMA_STAT(tx_65_to_127, TX_65_TO_127_PKTS),
+ EF10_DMA_STAT(tx_128_to_255, TX_128_TO_255_PKTS),
+ EF10_DMA_STAT(tx_256_to_511, TX_256_TO_511_PKTS),
+ EF10_DMA_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS),
+ EF10_DMA_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
+ EF10_DMA_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
+ EF10_DMA_STAT(rx_bytes, RX_BYTES),
+ EF10_DMA_INVIS_STAT(rx_bytes_minus_good_bytes, RX_BAD_BYTES),
+ EF10_OTHER_STAT(rx_good_bytes),
+ EF10_OTHER_STAT(rx_bad_bytes),
+ EF10_DMA_STAT(rx_packets, RX_PKTS),
+ EF10_DMA_STAT(rx_good, RX_GOOD_PKTS),
+ EF10_DMA_STAT(rx_bad, RX_BAD_FCS_PKTS),
+ EF10_DMA_STAT(rx_pause, RX_PAUSE_PKTS),
+ EF10_DMA_STAT(rx_control, RX_CONTROL_PKTS),
+ EF10_DMA_STAT(rx_unicast, RX_UNICAST_PKTS),
+ EF10_DMA_STAT(rx_multicast, RX_MULTICAST_PKTS),
+ EF10_DMA_STAT(rx_broadcast, RX_BROADCAST_PKTS),
+ EF10_DMA_STAT(rx_lt64, RX_UNDERSIZE_PKTS),
+ EF10_DMA_STAT(rx_64, RX_64_PKTS),
+ EF10_DMA_STAT(rx_65_to_127, RX_65_TO_127_PKTS),
+ EF10_DMA_STAT(rx_128_to_255, RX_128_TO_255_PKTS),
+ EF10_DMA_STAT(rx_256_to_511, RX_256_TO_511_PKTS),
+ EF10_DMA_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS),
+ EF10_DMA_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
+ EF10_DMA_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
+ EF10_DMA_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS),
+ EF10_DMA_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS),
+ EF10_DMA_STAT(rx_overflow, RX_OVERFLOW_PKTS),
+ EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS),
+ EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS),
+ EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS),
+ EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW),
+ EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW),
+ EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL),
+ EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL),
+ EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB),
+ EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB),
+ EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING),
+ EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS),
+ EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS),
+ EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS),
+ EF10_DMA_STAT(rx_dp_hlb_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS),
+ EF10_DMA_STAT(rx_dp_hlb_wait, RXDP_EMERGENCY_WAIT_CONDITIONS),
+};
+
+#define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) | \
+ (1ULL << EF10_STAT_tx_packets) | \
+ (1ULL << EF10_STAT_tx_pause) | \
+ (1ULL << EF10_STAT_tx_unicast) | \
+ (1ULL << EF10_STAT_tx_multicast) | \
+ (1ULL << EF10_STAT_tx_broadcast) | \
+ (1ULL << EF10_STAT_rx_bytes) | \
+ (1ULL << EF10_STAT_rx_bytes_minus_good_bytes) | \
+ (1ULL << EF10_STAT_rx_good_bytes) | \
+ (1ULL << EF10_STAT_rx_bad_bytes) | \
+ (1ULL << EF10_STAT_rx_packets) | \
+ (1ULL << EF10_STAT_rx_good) | \
+ (1ULL << EF10_STAT_rx_bad) | \
+ (1ULL << EF10_STAT_rx_pause) | \
+ (1ULL << EF10_STAT_rx_control) | \
+ (1ULL << EF10_STAT_rx_unicast) | \
+ (1ULL << EF10_STAT_rx_multicast) | \
+ (1ULL << EF10_STAT_rx_broadcast) | \
+ (1ULL << EF10_STAT_rx_lt64) | \
+ (1ULL << EF10_STAT_rx_64) | \
+ (1ULL << EF10_STAT_rx_65_to_127) | \
+ (1ULL << EF10_STAT_rx_128_to_255) | \
+ (1ULL << EF10_STAT_rx_256_to_511) | \
+ (1ULL << EF10_STAT_rx_512_to_1023) | \
+ (1ULL << EF10_STAT_rx_1024_to_15xx) | \
+ (1ULL << EF10_STAT_rx_15xx_to_jumbo) | \
+ (1ULL << EF10_STAT_rx_gtjumbo) | \
+ (1ULL << EF10_STAT_rx_bad_gtjumbo) | \
+ (1ULL << EF10_STAT_rx_overflow) | \
+ (1ULL << EF10_STAT_rx_nodesc_drops))
+
+/* These statistics are only provided by the 10G MAC. For a 10G/40G
+ * switchable port we do not expose these because they might not
+ * include all the packets they should.
+ */
+#define HUNT_10G_ONLY_STAT_MASK ((1ULL << EF10_STAT_tx_control) | \
+ (1ULL << EF10_STAT_tx_lt64) | \
+ (1ULL << EF10_STAT_tx_64) | \
+ (1ULL << EF10_STAT_tx_65_to_127) | \
+ (1ULL << EF10_STAT_tx_128_to_255) | \
+ (1ULL << EF10_STAT_tx_256_to_511) | \
+ (1ULL << EF10_STAT_tx_512_to_1023) | \
+ (1ULL << EF10_STAT_tx_1024_to_15xx) | \
+ (1ULL << EF10_STAT_tx_15xx_to_jumbo))
+
+/* These statistics are only provided by the 40G MAC. For a 10G/40G
+ * switchable port we do expose these because the errors will otherwise
+ * be silent.
+ */
+#define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) | \
+ (1ULL << EF10_STAT_rx_length_error))
+
+/* These statistics are only provided if the firmware supports the
+ * capability PM_AND_RXDP_COUNTERS.
+ */
+#define HUNT_PM_AND_RXDP_STAT_MASK ( \
+ (1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) | \
+ (1ULL << EF10_STAT_rx_pm_discard_bb_overflow) | \
+ (1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) | \
+ (1ULL << EF10_STAT_rx_pm_discard_vfifo_full) | \
+ (1ULL << EF10_STAT_rx_pm_trunc_qbb) | \
+ (1ULL << EF10_STAT_rx_pm_discard_qbb) | \
+ (1ULL << EF10_STAT_rx_pm_discard_mapping) | \
+ (1ULL << EF10_STAT_rx_dp_q_disabled_packets) | \
+ (1ULL << EF10_STAT_rx_dp_di_dropped_packets) | \
+ (1ULL << EF10_STAT_rx_dp_streaming_packets) | \
+ (1ULL << EF10_STAT_rx_dp_hlb_fetch) | \
+ (1ULL << EF10_STAT_rx_dp_hlb_wait))
+
+static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx)
+{
+ u64 raw_mask = HUNT_COMMON_STAT_MASK;
+ u32 port_caps = efx_mcdi_phy_get_caps(efx);
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+ if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN))
+ raw_mask |= HUNT_40G_EXTRA_STAT_MASK;
+ else
+ raw_mask |= HUNT_10G_ONLY_STAT_MASK;
+
+ if (nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN))
+ raw_mask |= HUNT_PM_AND_RXDP_STAT_MASK;
+
+ return raw_mask;
+}
+
+static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask)
+{
+ u64 raw_mask = efx_ef10_raw_stat_mask(efx);
+
+#if BITS_PER_LONG == 64
+ mask[0] = raw_mask;
+#else
+ mask[0] = raw_mask & 0xffffffff;
+ mask[1] = raw_mask >> 32;
+#endif
+}
+
+static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names)
+{
+ DECLARE_BITMAP(mask, EF10_STAT_COUNT);
+
+ efx_ef10_get_stat_mask(efx, mask);
+ return efx_nic_describe_stats(efx_ef10_stat_desc, EF10_STAT_COUNT,
+ mask, names);
+}
+
+static int efx_ef10_try_update_nic_stats(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ DECLARE_BITMAP(mask, EF10_STAT_COUNT);
+ __le64 generation_start, generation_end;
+ u64 *stats = nic_data->stats;
+ __le64 *dma_stats;
+
+ efx_ef10_get_stat_mask(efx, mask);
+
+ dma_stats = efx->stats_buffer.addr;
+ nic_data = efx->nic_data;
+
+ generation_end = dma_stats[MC_CMD_MAC_GENERATION_END];
+ if (generation_end == EFX_MC_STATS_GENERATION_INVALID)
+ return 0;
+ rmb();
+ efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask,
+ stats, efx->stats_buffer.addr, false);
+ rmb();
+ generation_start = dma_stats[MC_CMD_MAC_GENERATION_START];
+ if (generation_end != generation_start)
+ return -EAGAIN;
+
+ /* Update derived statistics */
+ efx_nic_fix_nodesc_drop_stat(efx, &stats[EF10_STAT_rx_nodesc_drops]);
+ stats[EF10_STAT_rx_good_bytes] =
+ stats[EF10_STAT_rx_bytes] -
+ stats[EF10_STAT_rx_bytes_minus_good_bytes];
+ efx_update_diff_stat(&stats[EF10_STAT_rx_bad_bytes],
+ stats[EF10_STAT_rx_bytes_minus_good_bytes]);
+
+ return 0;
+}
+
+
+static size_t efx_ef10_update_stats(struct efx_nic *efx, u64 *full_stats,
+ struct rtnl_link_stats64 *core_stats)
+{
+ DECLARE_BITMAP(mask, EF10_STAT_COUNT);
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ u64 *stats = nic_data->stats;
+ size_t stats_count = 0, index;
+ int retry;
+
+ efx_ef10_get_stat_mask(efx, mask);
+
+ /* If we're unlucky enough to read statistics during the DMA, wait
+ * up to 10ms for it to finish (typically takes <500us)
+ */
+ for (retry = 0; retry < 100; ++retry) {
+ if (efx_ef10_try_update_nic_stats(efx) == 0)
+ break;
+ udelay(100);
+ }
+
+ if (full_stats) {
+ for_each_set_bit(index, mask, EF10_STAT_COUNT) {
+ if (efx_ef10_stat_desc[index].name) {
+ *full_stats++ = stats[index];
+ ++stats_count;
+ }
+ }
+ }
+
+ if (core_stats) {
+ core_stats->rx_packets = stats[EF10_STAT_rx_packets];
+ core_stats->tx_packets = stats[EF10_STAT_tx_packets];
+ core_stats->rx_bytes = stats[EF10_STAT_rx_bytes];
+ core_stats->tx_bytes = stats[EF10_STAT_tx_bytes];
+ core_stats->rx_dropped = stats[EF10_STAT_rx_nodesc_drops];
+ core_stats->multicast = stats[EF10_STAT_rx_multicast];
+ core_stats->rx_length_errors =
+ stats[EF10_STAT_rx_gtjumbo] +
+ stats[EF10_STAT_rx_length_error];
+ core_stats->rx_crc_errors = stats[EF10_STAT_rx_bad];
+ core_stats->rx_frame_errors = stats[EF10_STAT_rx_align_error];
+ core_stats->rx_fifo_errors = stats[EF10_STAT_rx_overflow];
+ core_stats->rx_errors = (core_stats->rx_length_errors +
+ core_stats->rx_crc_errors +
+ core_stats->rx_frame_errors);
+ }
+
+ return stats_count;
+}
+
+static void efx_ef10_push_irq_moderation(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+ unsigned int mode, value;
+ efx_dword_t timer_cmd;
+
+ if (channel->irq_moderation) {
+ mode = 3;
+ value = channel->irq_moderation - 1;
+ } else {
+ mode = 0;
+ value = 0;
+ }
+
+ if (EFX_EF10_WORKAROUND_35388(efx)) {
+ EFX_POPULATE_DWORD_3(timer_cmd, ERF_DD_EVQ_IND_TIMER_FLAGS,
+ EFE_DD_EVQ_IND_TIMER_FLAGS,
+ ERF_DD_EVQ_IND_TIMER_MODE, mode,
+ ERF_DD_EVQ_IND_TIMER_VAL, value);
+ efx_writed_page(efx, &timer_cmd, ER_DD_EVQ_INDIRECT,
+ channel->channel);
+ } else {
+ EFX_POPULATE_DWORD_2(timer_cmd, ERF_DZ_TC_TIMER_MODE, mode,
+ ERF_DZ_TC_TIMER_VAL, value);
+ efx_writed_page(efx, &timer_cmd, ER_DZ_EVQ_TMR,
+ channel->channel);
+ }
+}
+
+static void efx_ef10_get_wol(struct efx_nic *efx, struct ethtool_wolinfo *wol)
+{
+ wol->supported = 0;
+ wol->wolopts = 0;
+ memset(&wol->sopass, 0, sizeof(wol->sopass));
+}
+
+static int efx_ef10_set_wol(struct efx_nic *efx, u32 type)
+{
+ if (type != 0)
+ return -EINVAL;
+ return 0;
+}
+
+static void efx_ef10_mcdi_request(struct efx_nic *efx,
+ const efx_dword_t *hdr, size_t hdr_len,
+ const efx_dword_t *sdu, size_t sdu_len)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ u8 *pdu = nic_data->mcdi_buf.addr;
+
+ memcpy(pdu, hdr, hdr_len);
+ memcpy(pdu + hdr_len, sdu, sdu_len);
+ wmb();
+
+ /* The hardware provides 'low' and 'high' (doorbell) registers
+ * for passing the 64-bit address of an MCDI request to
+ * firmware. However the dwords are swapped by firmware. The
+ * least significant bits of the doorbell are then 0 for all
+ * MCDI requests due to alignment.
+ */
+ _efx_writed(efx, cpu_to_le32((u64)nic_data->mcdi_buf.dma_addr >> 32),
+ ER_DZ_MC_DB_LWRD);
+ _efx_writed(efx, cpu_to_le32((u32)nic_data->mcdi_buf.dma_addr),
+ ER_DZ_MC_DB_HWRD);
+}
+
+static bool efx_ef10_mcdi_poll_response(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ const efx_dword_t hdr = *(const efx_dword_t *)nic_data->mcdi_buf.addr;
+
+ rmb();
+ return EFX_DWORD_FIELD(hdr, MCDI_HEADER_RESPONSE);
+}
+
+static void
+efx_ef10_mcdi_read_response(struct efx_nic *efx, efx_dword_t *outbuf,
+ size_t offset, size_t outlen)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ const u8 *pdu = nic_data->mcdi_buf.addr;
+
+ memcpy(outbuf, pdu + offset, outlen);
+}
+
+static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ rc = efx_ef10_get_warm_boot_count(efx);
+ if (rc < 0) {
+ /* The firmware is presumably in the process of
+ * rebooting. However, we are supposed to report each
+ * reboot just once, so we must only do that once we
+ * can read and store the updated warm boot count.
+ */
+ return 0;
+ }
+
+ if (rc == nic_data->warm_boot_count)
+ return 0;
+
+ nic_data->warm_boot_count = rc;
+
+ /* All our allocations have been reset */
+ efx_ef10_reset_mc_allocations(efx);
+
+ /* The datapath firmware might have been changed */
+ nic_data->must_check_datapath_caps = true;
+
+ /* MAC statistics have been cleared on the NIC; clear the local
+ * statistic that we update with efx_update_diff_stat().
+ */
+ nic_data->stats[EF10_STAT_rx_bad_bytes] = 0;
+
+ return -EIO;
+}
+
+/* Handle an MSI interrupt
+ *
+ * Handle an MSI hardware interrupt. This routine schedules event
+ * queue processing. No interrupt acknowledgement cycle is necessary.
+ * Also, we never need to check that the interrupt is for us, since
+ * MSI interrupts cannot be shared.
+ */
+static irqreturn_t efx_ef10_msi_interrupt(int irq, void *dev_id)
+{
+ struct efx_msi_context *context = dev_id;
+ struct efx_nic *efx = context->efx;
+
+ netif_vdbg(efx, intr, efx->net_dev,
+ "IRQ %d on CPU %d\n", irq, raw_smp_processor_id());
+
+ if (likely(ACCESS_ONCE(efx->irq_soft_enabled))) {
+ /* Note test interrupts */
+ if (context->index == efx->irq_level)
+ efx->last_irq_cpu = raw_smp_processor_id();
+
+ /* Schedule processing of the channel */
+ efx_schedule_channel_irq(efx->channel[context->index]);
+ }
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t efx_ef10_legacy_interrupt(int irq, void *dev_id)
+{
+ struct efx_nic *efx = dev_id;
+ bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled);
+ struct efx_channel *channel;
+ efx_dword_t reg;
+ u32 queues;
+
+ /* Read the ISR which also ACKs the interrupts */
+ efx_readd(efx, &reg, ER_DZ_BIU_INT_ISR);
+ queues = EFX_DWORD_FIELD(reg, ERF_DZ_ISR_REG);
+
+ if (queues == 0)
+ return IRQ_NONE;
+
+ if (likely(soft_enabled)) {
+ /* Note test interrupts */
+ if (queues & (1U << efx->irq_level))
+ efx->last_irq_cpu = raw_smp_processor_id();
+
+ efx_for_each_channel(channel, efx) {
+ if (queues & 1)
+ efx_schedule_channel_irq(channel);
+ queues >>= 1;
+ }
+ }
+
+ netif_vdbg(efx, intr, efx->net_dev,
+ "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n",
+ irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg));
+
+ return IRQ_HANDLED;
+}
+
+static void efx_ef10_irq_test_generate(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_TRIGGER_INTERRUPT_IN_LEN);
+
+ BUILD_BUG_ON(MC_CMD_TRIGGER_INTERRUPT_OUT_LEN != 0);
+
+ MCDI_SET_DWORD(inbuf, TRIGGER_INTERRUPT_IN_INTR_LEVEL, efx->irq_level);
+ (void) efx_mcdi_rpc(efx, MC_CMD_TRIGGER_INTERRUPT,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
+}
+
+static int efx_ef10_tx_probe(struct efx_tx_queue *tx_queue)
+{
+ return efx_nic_alloc_buffer(tx_queue->efx, &tx_queue->txd.buf,
+ (tx_queue->ptr_mask + 1) *
+ sizeof(efx_qword_t),
+ GFP_KERNEL);
+}
+
+/* This writes to the TX_DESC_WPTR and also pushes data */
+static inline void efx_ef10_push_tx_desc(struct efx_tx_queue *tx_queue,
+ const efx_qword_t *txd)
+{
+ unsigned int write_ptr;
+ efx_oword_t reg;
+
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ EFX_POPULATE_OWORD_1(reg, ERF_DZ_TX_DESC_WPTR, write_ptr);
+ reg.qword[0] = *txd;
+ efx_writeo_page(tx_queue->efx, &reg,
+ ER_DZ_TX_DESC_UPD, tx_queue->queue);
+}
+
+static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_INIT_TXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_TXQ_OUT_LEN);
+ bool csum_offload = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
+ size_t entries = tx_queue->txd.buf.len / EFX_BUF_SIZE;
+ struct efx_channel *channel = tx_queue->channel;
+ struct efx_nic *efx = tx_queue->efx;
+ size_t inlen, outlen;
+ dma_addr_t dma_addr;
+ efx_qword_t *txd;
+ int rc;
+ int i;
+
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_SIZE, tx_queue->ptr_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_TARGET_EVQ, channel->channel);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_LABEL, tx_queue->queue);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_INSTANCE, tx_queue->queue);
+ MCDI_POPULATE_DWORD_2(inbuf, INIT_TXQ_IN_FLAGS,
+ INIT_TXQ_IN_FLAG_IP_CSUM_DIS, !csum_offload,
+ INIT_TXQ_IN_FLAG_TCP_CSUM_DIS, !csum_offload);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_OWNER_ID, 0);
+ MCDI_SET_DWORD(inbuf, INIT_TXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+
+ dma_addr = tx_queue->txd.buf.dma_addr;
+
+ netif_dbg(efx, hw, efx->net_dev, "pushing TXQ %d. %zu entries (%llx)\n",
+ tx_queue->queue, entries, (u64)dma_addr);
+
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_TXQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_TXQ_IN_LEN(entries);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_INIT_TXQ, inbuf, inlen,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ goto fail;
+
+ /* A previous user of this TX queue might have set us up the
+ * bomb by writing a descriptor to the TX push collector but
+ * not the doorbell. (Each collector belongs to a port, not a
+ * queue or function, so cannot easily be reset.) We must
+ * attempt to push a no-op descriptor in its place.
+ */
+ tx_queue->buffer[0].flags = EFX_TX_BUF_OPTION;
+ tx_queue->insert_count = 1;
+ txd = efx_tx_desc(tx_queue, 0);
+ EFX_POPULATE_QWORD_4(*txd,
+ ESF_DZ_TX_DESC_IS_OPT, true,
+ ESF_DZ_TX_OPTION_TYPE,
+ ESE_DZ_TX_OPTION_DESC_CRC_CSUM,
+ ESF_DZ_TX_OPTION_UDP_TCP_CSUM, csum_offload,
+ ESF_DZ_TX_OPTION_IP_CSUM, csum_offload);
+ tx_queue->write_count = 1;
+ wmb();
+ efx_ef10_push_tx_desc(tx_queue, txd);
+
+ return;
+
+fail:
+ netdev_WARN(efx->net_dev, "failed to initialise TXQ %d\n",
+ tx_queue->queue);
+}
+
+static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_TXQ_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_TXQ_OUT_LEN);
+ struct efx_nic *efx = tx_queue->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_TXQ_IN_INSTANCE,
+ tx_queue->queue);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_TXQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_TXQ, MC_CMD_FINI_TXQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+static void efx_ef10_tx_remove(struct efx_tx_queue *tx_queue)
+{
+ efx_nic_free_buffer(tx_queue->efx, &tx_queue->txd.buf);
+}
+
+/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */
+static inline void efx_ef10_notify_tx_desc(struct efx_tx_queue *tx_queue)
+{
+ unsigned int write_ptr;
+ efx_dword_t reg;
+
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ EFX_POPULATE_DWORD_1(reg, ERF_DZ_TX_DESC_WPTR_DWORD, write_ptr);
+ efx_writed_page(tx_queue->efx, &reg,
+ ER_DZ_TX_DESC_UPD_DWORD, tx_queue->queue);
+}
+
+static void efx_ef10_tx_write(struct efx_tx_queue *tx_queue)
+{
+ unsigned int old_write_count = tx_queue->write_count;
+ struct efx_tx_buffer *buffer;
+ unsigned int write_ptr;
+ efx_qword_t *txd;
+
+ BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+
+ do {
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ buffer = &tx_queue->buffer[write_ptr];
+ txd = efx_tx_desc(tx_queue, write_ptr);
+ ++tx_queue->write_count;
+
+ /* Create TX descriptor ring entry */
+ if (buffer->flags & EFX_TX_BUF_OPTION) {
+ *txd = buffer->option;
+ } else {
+ BUILD_BUG_ON(EFX_TX_BUF_CONT != 1);
+ EFX_POPULATE_QWORD_3(
+ *txd,
+ ESF_DZ_TX_KER_CONT,
+ buffer->flags & EFX_TX_BUF_CONT,
+ ESF_DZ_TX_KER_BYTE_CNT, buffer->len,
+ ESF_DZ_TX_KER_BUF_ADDR, buffer->dma_addr);
+ }
+ } while (tx_queue->write_count != tx_queue->insert_count);
+
+ wmb(); /* Ensure descriptors are written before they are fetched */
+
+ if (efx_nic_may_push_tx_desc(tx_queue, old_write_count)) {
+ txd = efx_tx_desc(tx_queue,
+ old_write_count & tx_queue->ptr_mask);
+ efx_ef10_push_tx_desc(tx_queue, txd);
+ ++tx_queue->pushes;
+ } else {
+ efx_ef10_notify_tx_desc(tx_queue);
+ }
+}
+
+static int efx_ef10_alloc_rss_context(struct efx_nic *efx, u32 *context)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_ALLOC_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN);
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID,
+ EVB_PORT_ID_ASSIGNED);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_TYPE,
+ MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_EXCLUSIVE);
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_ALLOC_IN_NUM_QUEUES,
+ EFX_MAX_CHANNELS);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_ALLOC, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc != 0)
+ return rc;
+
+ if (outlen < MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN)
+ return -EIO;
+
+ *context = MCDI_DWORD(outbuf, RSS_CONTEXT_ALLOC_OUT_RSS_CONTEXT_ID);
+
+ return 0;
+}
+
+static void efx_ef10_free_rss_context(struct efx_nic *efx, u32 context)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_RSS_CONTEXT_FREE_IN_LEN);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, RSS_CONTEXT_FREE_IN_RSS_CONTEXT_ID,
+ context);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_FREE, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ WARN_ON(rc != 0);
+}
+
+static int efx_ef10_populate_rss_table(struct efx_nic *efx, u32 context)
+{
+ MCDI_DECLARE_BUF(tablebuf, MC_CMD_RSS_CONTEXT_SET_TABLE_IN_LEN);
+ MCDI_DECLARE_BUF(keybuf, MC_CMD_RSS_CONTEXT_SET_KEY_IN_LEN);
+ int i, rc;
+
+ MCDI_SET_DWORD(tablebuf, RSS_CONTEXT_SET_TABLE_IN_RSS_CONTEXT_ID,
+ context);
+ BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) !=
+ MC_CMD_RSS_CONTEXT_SET_TABLE_IN_INDIRECTION_TABLE_LEN);
+
+ for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); ++i)
+ MCDI_PTR(tablebuf,
+ RSS_CONTEXT_SET_TABLE_IN_INDIRECTION_TABLE)[i] =
+ (u8) efx->rx_indir_table[i];
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_TABLE, tablebuf,
+ sizeof(tablebuf), NULL, 0, NULL);
+ if (rc != 0)
+ return rc;
+
+ MCDI_SET_DWORD(keybuf, RSS_CONTEXT_SET_KEY_IN_RSS_CONTEXT_ID,
+ context);
+ BUILD_BUG_ON(ARRAY_SIZE(efx->rx_hash_key) !=
+ MC_CMD_RSS_CONTEXT_SET_KEY_IN_TOEPLITZ_KEY_LEN);
+ for (i = 0; i < ARRAY_SIZE(efx->rx_hash_key); ++i)
+ MCDI_PTR(keybuf, RSS_CONTEXT_SET_KEY_IN_TOEPLITZ_KEY)[i] =
+ efx->rx_hash_key[i];
+
+ return efx_mcdi_rpc(efx, MC_CMD_RSS_CONTEXT_SET_KEY, keybuf,
+ sizeof(keybuf), NULL, 0, NULL);
+}
+
+static void efx_ef10_rx_free_indir_table(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+ if (nic_data->rx_rss_context != EFX_EF10_RSS_CONTEXT_INVALID)
+ efx_ef10_free_rss_context(efx, nic_data->rx_rss_context);
+ nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID;
+}
+
+static void efx_ef10_rx_push_rss_config(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ netif_dbg(efx, drv, efx->net_dev, "pushing RSS config\n");
+
+ if (nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID) {
+ rc = efx_ef10_alloc_rss_context(efx, &nic_data->rx_rss_context);
+ if (rc != 0)
+ goto fail;
+ }
+
+ rc = efx_ef10_populate_rss_table(efx, nic_data->rx_rss_context);
+ if (rc != 0)
+ goto fail;
+
+ return;
+
+fail:
+ netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+}
+
+static int efx_ef10_rx_probe(struct efx_rx_queue *rx_queue)
+{
+ return efx_nic_alloc_buffer(rx_queue->efx, &rx_queue->rxd.buf,
+ (rx_queue->ptr_mask + 1) *
+ sizeof(efx_qword_t),
+ GFP_KERNEL);
+}
+
+static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_INIT_RXQ_IN_LEN(EFX_MAX_DMAQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_RXQ_OUT_LEN);
+ struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
+ size_t entries = rx_queue->rxd.buf.len / EFX_BUF_SIZE;
+ struct efx_nic *efx = rx_queue->efx;
+ size_t inlen, outlen;
+ dma_addr_t dma_addr;
+ int rc;
+ int i;
+
+ rx_queue->scatter_n = 0;
+ rx_queue->scatter_len = 0;
+
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_SIZE, rx_queue->ptr_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_TARGET_EVQ, channel->channel);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_LABEL, efx_rx_queue_index(rx_queue));
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_INSTANCE,
+ efx_rx_queue_index(rx_queue));
+ MCDI_POPULATE_DWORD_2(inbuf, INIT_RXQ_IN_FLAGS,
+ INIT_RXQ_IN_FLAG_PREFIX, 1,
+ INIT_RXQ_IN_FLAG_TIMESTAMP, 1);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0);
+ MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+
+ dma_addr = rx_queue->rxd.buf.dma_addr;
+
+ netif_dbg(efx, hw, efx->net_dev, "pushing RXQ %d. %zu entries (%llx)\n",
+ efx_rx_queue_index(rx_queue), entries, (u64)dma_addr);
+
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_RXQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_RXQ_IN_LEN(entries);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_INIT_RXQ, inbuf, inlen,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ netdev_WARN(efx->net_dev, "failed to initialise RXQ %d\n",
+ efx_rx_queue_index(rx_queue));
+}
+
+static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_RXQ_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_RXQ_OUT_LEN);
+ struct efx_nic *efx = rx_queue->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_RXQ_IN_INSTANCE,
+ efx_rx_queue_index(rx_queue));
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_RXQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_RXQ, MC_CMD_FINI_RXQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+static void efx_ef10_rx_remove(struct efx_rx_queue *rx_queue)
+{
+ efx_nic_free_buffer(rx_queue->efx, &rx_queue->rxd.buf);
+}
+
+/* This creates an entry in the RX descriptor queue */
+static inline void
+efx_ef10_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
+{
+ struct efx_rx_buffer *rx_buf;
+ efx_qword_t *rxd;
+
+ rxd = efx_rx_desc(rx_queue, index);
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ EFX_POPULATE_QWORD_2(*rxd,
+ ESF_DZ_RX_KER_BYTE_CNT, rx_buf->len,
+ ESF_DZ_RX_KER_BUF_ADDR, rx_buf->dma_addr);
+}
+
+static void efx_ef10_rx_write(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned int write_count;
+ efx_dword_t reg;
+
+ /* Firmware requires that RX_DESC_WPTR be a multiple of 8 */
+ write_count = rx_queue->added_count & ~7;
+ if (rx_queue->notified_count == write_count)
+ return;
+
+ do
+ efx_ef10_build_rx_desc(
+ rx_queue,
+ rx_queue->notified_count & rx_queue->ptr_mask);
+ while (++rx_queue->notified_count != write_count);
+
+ wmb();
+ EFX_POPULATE_DWORD_1(reg, ERF_DZ_RX_DESC_WPTR,
+ write_count & rx_queue->ptr_mask);
+ efx_writed_page(efx, &reg, ER_DZ_RX_DESC_UPD,
+ efx_rx_queue_index(rx_queue));
+}
+
+static efx_mcdi_async_completer efx_ef10_rx_defer_refill_complete;
+
+static void efx_ef10_rx_defer_refill(struct efx_rx_queue *rx_queue)
+{
+ struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_DRIVER_EVENT_IN_LEN);
+ efx_qword_t event;
+
+ EFX_POPULATE_QWORD_2(event,
+ ESF_DZ_EV_CODE, EFX_EF10_DRVGEN_EV,
+ ESF_DZ_EV_DATA, EFX_EF10_REFILL);
+
+ MCDI_SET_DWORD(inbuf, DRIVER_EVENT_IN_EVQ, channel->channel);
+
+ /* MCDI_SET_QWORD is not appropriate here since EFX_POPULATE_* has
+ * already swapped the data to little-endian order.
+ */
+ memcpy(MCDI_PTR(inbuf, DRIVER_EVENT_IN_DATA), &event.u64[0],
+ sizeof(efx_qword_t));
+
+ efx_mcdi_rpc_async(channel->efx, MC_CMD_DRIVER_EVENT,
+ inbuf, sizeof(inbuf), 0,
+ efx_ef10_rx_defer_refill_complete, 0);
+}
+
+static void
+efx_ef10_rx_defer_refill_complete(struct efx_nic *efx, unsigned long cookie,
+ int rc, efx_dword_t *outbuf,
+ size_t outlen_actual)
+{
+ /* nothing to do */
+}
+
+static int efx_ef10_ev_probe(struct efx_channel *channel)
+{
+ return efx_nic_alloc_buffer(channel->efx, &channel->eventq.buf,
+ (channel->eventq_mask + 1) *
+ sizeof(efx_qword_t),
+ GFP_KERNEL);
+}
+
+static int efx_ef10_ev_init(struct efx_channel *channel)
+{
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_INIT_EVQ_IN_LEN(EFX_MAX_EVQ_SIZE * 8 /
+ EFX_BUF_SIZE));
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_INIT_EVQ_OUT_LEN);
+ size_t entries = channel->eventq.buf.len / EFX_BUF_SIZE;
+ struct efx_nic *efx = channel->efx;
+ struct efx_ef10_nic_data *nic_data;
+ bool supports_rx_merge;
+ size_t inlen, outlen;
+ dma_addr_t dma_addr;
+ int rc;
+ int i;
+
+ nic_data = efx->nic_data;
+ supports_rx_merge =
+ !!(nic_data->datapath_caps &
+ 1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN);
+
+ /* Fill event queue with all ones (i.e. empty events) */
+ memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
+
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_SIZE, channel->eventq_mask + 1);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_INSTANCE, channel->channel);
+ /* INIT_EVQ expects index in vector table, not absolute */
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_IRQ_NUM, channel->channel);
+ MCDI_POPULATE_DWORD_4(inbuf, INIT_EVQ_IN_FLAGS,
+ INIT_EVQ_IN_FLAG_INTERRUPTING, 1,
+ INIT_EVQ_IN_FLAG_RX_MERGE, 1,
+ INIT_EVQ_IN_FLAG_TX_MERGE, 1,
+ INIT_EVQ_IN_FLAG_CUT_THRU, !supports_rx_merge);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_MODE,
+ MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_LOAD, 0);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_TMR_RELOAD, 0);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_MODE,
+ MC_CMD_INIT_EVQ_IN_COUNT_MODE_DIS);
+ MCDI_SET_DWORD(inbuf, INIT_EVQ_IN_COUNT_THRSHLD, 0);
+
+ dma_addr = channel->eventq.buf.dma_addr;
+ for (i = 0; i < entries; ++i) {
+ MCDI_SET_ARRAY_QWORD(inbuf, INIT_EVQ_IN_DMA_ADDR, i, dma_addr);
+ dma_addr += EFX_BUF_SIZE;
+ }
+
+ inlen = MC_CMD_INIT_EVQ_IN_LEN(entries);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen,
+ outbuf, sizeof(outbuf), &outlen);
+ /* IRQ return is ignored */
+ return rc;
+}
+
+static void efx_ef10_ev_fini(struct efx_channel *channel)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FINI_EVQ_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_FINI_EVQ_OUT_LEN);
+ struct efx_nic *efx = channel->efx;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+
+ if (rc && rc != -EALREADY)
+ goto fail;
+
+ return;
+
+fail:
+ efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN,
+ outbuf, outlen, rc);
+}
+
+static void efx_ef10_ev_remove(struct efx_channel *channel)
+{
+ efx_nic_free_buffer(channel->efx, &channel->eventq.buf);
+}
+
+static void efx_ef10_handle_rx_wrong_queue(struct efx_rx_queue *rx_queue,
+ unsigned int rx_queue_label)
+{
+ struct efx_nic *efx = rx_queue->efx;
+
+ netif_info(efx, hw, efx->net_dev,
+ "rx event arrived on queue %d labeled as queue %u\n",
+ efx_rx_queue_index(rx_queue), rx_queue_label);
+
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+}
+
+static void
+efx_ef10_handle_rx_bad_lbits(struct efx_rx_queue *rx_queue,
+ unsigned int actual, unsigned int expected)
+{
+ unsigned int dropped = (actual - expected) & rx_queue->ptr_mask;
+ struct efx_nic *efx = rx_queue->efx;
+
+ netif_info(efx, hw, efx->net_dev,
+ "dropped %d events (index=%d expected=%d)\n",
+ dropped, actual, expected);
+
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+}
+
+/* partially received RX was aborted. clean up. */
+static void efx_ef10_handle_rx_abort(struct efx_rx_queue *rx_queue)
+{
+ unsigned int rx_desc_ptr;
+
+ netif_dbg(rx_queue->efx, hw, rx_queue->efx->net_dev,
+ "scattered RX aborted (dropping %u buffers)\n",
+ rx_queue->scatter_n);
+
+ rx_desc_ptr = rx_queue->removed_count & rx_queue->ptr_mask;
+
+ efx_rx_packet(rx_queue, rx_desc_ptr, rx_queue->scatter_n,
+ 0, EFX_RX_PKT_DISCARD);
+
+ rx_queue->removed_count += rx_queue->scatter_n;
+ rx_queue->scatter_n = 0;
+ rx_queue->scatter_len = 0;
+ ++efx_rx_queue_channel(rx_queue)->n_rx_nodesc_trunc;
+}
+
+static int efx_ef10_handle_rx_event(struct efx_channel *channel,
+ const efx_qword_t *event)
+{
+ unsigned int rx_bytes, next_ptr_lbits, rx_queue_label, rx_l4_class;
+ unsigned int n_descs, n_packets, i;
+ struct efx_nic *efx = channel->efx;
+ struct efx_rx_queue *rx_queue;
+ bool rx_cont;
+ u16 flags = 0;
+
+ if (unlikely(ACCESS_ONCE(efx->reset_pending)))
+ return 0;
+
+ /* Basic packet information */
+ rx_bytes = EFX_QWORD_FIELD(*event, ESF_DZ_RX_BYTES);
+ next_ptr_lbits = EFX_QWORD_FIELD(*event, ESF_DZ_RX_DSC_PTR_LBITS);
+ rx_queue_label = EFX_QWORD_FIELD(*event, ESF_DZ_RX_QLABEL);
+ rx_l4_class = EFX_QWORD_FIELD(*event, ESF_DZ_RX_L4_CLASS);
+ rx_cont = EFX_QWORD_FIELD(*event, ESF_DZ_RX_CONT);
+
+ if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_DROP_EVENT))
+ netdev_WARN(efx->net_dev, "saw RX_DROP_EVENT: event="
+ EFX_QWORD_FMT "\n",
+ EFX_QWORD_VAL(*event));
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+
+ if (unlikely(rx_queue_label != efx_rx_queue_index(rx_queue)))
+ efx_ef10_handle_rx_wrong_queue(rx_queue, rx_queue_label);
+
+ n_descs = ((next_ptr_lbits - rx_queue->removed_count) &
+ ((1 << ESF_DZ_RX_DSC_PTR_LBITS_WIDTH) - 1));
+
+ if (n_descs != rx_queue->scatter_n + 1) {
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+ /* detect rx abort */
+ if (unlikely(n_descs == rx_queue->scatter_n)) {
+ if (rx_queue->scatter_n == 0 || rx_bytes != 0)
+ netdev_WARN(efx->net_dev,
+ "invalid RX abort: scatter_n=%u event="
+ EFX_QWORD_FMT "\n",
+ rx_queue->scatter_n,
+ EFX_QWORD_VAL(*event));
+ efx_ef10_handle_rx_abort(rx_queue);
+ return 0;
+ }
+
+ /* Check that RX completion merging is valid, i.e.
+ * the current firmware supports it and this is a
+ * non-scattered packet.
+ */
+ if (!(nic_data->datapath_caps &
+ (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN)) ||
+ rx_queue->scatter_n != 0 || rx_cont) {
+ efx_ef10_handle_rx_bad_lbits(
+ rx_queue, next_ptr_lbits,
+ (rx_queue->removed_count +
+ rx_queue->scatter_n + 1) &
+ ((1 << ESF_DZ_RX_DSC_PTR_LBITS_WIDTH) - 1));
+ return 0;
+ }
+
+ /* Merged completion for multiple non-scattered packets */
+ rx_queue->scatter_n = 1;
+ rx_queue->scatter_len = 0;
+ n_packets = n_descs;
+ ++channel->n_rx_merge_events;
+ channel->n_rx_merge_packets += n_packets;
+ flags |= EFX_RX_PKT_PREFIX_LEN;
+ } else {
+ ++rx_queue->scatter_n;
+ rx_queue->scatter_len += rx_bytes;
+ if (rx_cont)
+ return 0;
+ n_packets = 1;
+ }
+
+ if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_RX_ECRC_ERR)))
+ flags |= EFX_RX_PKT_DISCARD;
+
+ if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_RX_IPCKSUM_ERR))) {
+ channel->n_rx_ip_hdr_chksum_err += n_packets;
+ } else if (unlikely(EFX_QWORD_FIELD(*event,
+ ESF_DZ_RX_TCPUDP_CKSUM_ERR))) {
+ channel->n_rx_tcp_udp_chksum_err += n_packets;
+ } else if (rx_l4_class == ESE_DZ_L4_CLASS_TCP ||
+ rx_l4_class == ESE_DZ_L4_CLASS_UDP) {
+ flags |= EFX_RX_PKT_CSUMMED;
+ }
+
+ if (rx_l4_class == ESE_DZ_L4_CLASS_TCP)
+ flags |= EFX_RX_PKT_TCP;
+
+ channel->irq_mod_score += 2 * n_packets;
+
+ /* Handle received packet(s) */
+ for (i = 0; i < n_packets; i++) {
+ efx_rx_packet(rx_queue,
+ rx_queue->removed_count & rx_queue->ptr_mask,
+ rx_queue->scatter_n, rx_queue->scatter_len,
+ flags);
+ rx_queue->removed_count += rx_queue->scatter_n;
+ }
+
+ rx_queue->scatter_n = 0;
+ rx_queue->scatter_len = 0;
+
+ return n_packets;
+}
+
+static int
+efx_ef10_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ struct efx_tx_queue *tx_queue;
+ unsigned int tx_ev_desc_ptr;
+ unsigned int tx_ev_q_label;
+ int tx_descs = 0;
+
+ if (unlikely(ACCESS_ONCE(efx->reset_pending)))
+ return 0;
+
+ if (unlikely(EFX_QWORD_FIELD(*event, ESF_DZ_TX_DROP_EVENT)))
+ return 0;
+
+ /* Transmit completion */
+ tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, ESF_DZ_TX_DESCR_INDX);
+ tx_ev_q_label = EFX_QWORD_FIELD(*event, ESF_DZ_TX_QLABEL);
+ tx_queue = efx_channel_get_tx_queue(channel,
+ tx_ev_q_label % EFX_TXQ_TYPES);
+ tx_descs = ((tx_ev_desc_ptr + 1 - tx_queue->read_count) &
+ tx_queue->ptr_mask);
+ efx_xmit_done(tx_queue, tx_ev_desc_ptr & tx_queue->ptr_mask);
+
+ return tx_descs;
+}
+
+static void
+efx_ef10_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ int subcode;
+
+ subcode = EFX_QWORD_FIELD(*event, ESF_DZ_DRV_SUB_CODE);
+
+ switch (subcode) {
+ case ESE_DZ_DRV_TIMER_EV:
+ case ESE_DZ_DRV_WAKE_UP_EV:
+ break;
+ case ESE_DZ_DRV_START_UP_EV:
+ /* event queue init complete. ok. */
+ break;
+ default:
+ netif_err(efx, hw, efx->net_dev,
+ "channel %d unknown driver event type %d"
+ " (data " EFX_QWORD_FMT ")\n",
+ channel->channel, subcode,
+ EFX_QWORD_VAL(*event));
+
+ }
+}
+
+static void efx_ef10_handle_driver_generated_event(struct efx_channel *channel,
+ efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ u32 subcode;
+
+ subcode = EFX_QWORD_FIELD(*event, EFX_DWORD_0);
+
+ switch (subcode) {
+ case EFX_EF10_TEST:
+ channel->event_test_cpu = raw_smp_processor_id();
+ break;
+ case EFX_EF10_REFILL:
+ /* The queue must be empty, so we won't receive any rx
+ * events, so efx_process_channel() won't refill the
+ * queue. Refill it here
+ */
+ efx_fast_push_rx_descriptors(&channel->rx_queue, true);
+ break;
+ default:
+ netif_err(efx, hw, efx->net_dev,
+ "channel %d unknown driver event type %u"
+ " (data " EFX_QWORD_FMT ")\n",
+ channel->channel, (unsigned) subcode,
+ EFX_QWORD_VAL(*event));
+ }
+}
+
+static int efx_ef10_ev_process(struct efx_channel *channel, int quota)
+{
+ struct efx_nic *efx = channel->efx;
+ efx_qword_t event, *p_event;
+ unsigned int read_ptr;
+ int ev_code;
+ int tx_descs = 0;
+ int spent = 0;
+
+ if (quota <= 0)
+ return spent;
+
+ read_ptr = channel->eventq_read_ptr;
+
+ for (;;) {
+ p_event = efx_event(channel, read_ptr);
+ event = *p_event;
+
+ if (!efx_event_present(&event))
+ break;
+
+ EFX_SET_QWORD(*p_event);
+
+ ++read_ptr;
+
+ ev_code = EFX_QWORD_FIELD(event, ESF_DZ_EV_CODE);
+
+ netif_vdbg(efx, drv, efx->net_dev,
+ "processing event on %d " EFX_QWORD_FMT "\n",
+ channel->channel, EFX_QWORD_VAL(event));
+
+ switch (ev_code) {
+ case ESE_DZ_EV_CODE_MCDI_EV:
+ efx_mcdi_process_event(channel, &event);
+ break;
+ case ESE_DZ_EV_CODE_RX_EV:
+ spent += efx_ef10_handle_rx_event(channel, &event);
+ if (spent >= quota) {
+ /* XXX can we split a merged event to
+ * avoid going over-quota?
+ */
+ spent = quota;
+ goto out;
+ }
+ break;
+ case ESE_DZ_EV_CODE_TX_EV:
+ tx_descs += efx_ef10_handle_tx_event(channel, &event);
+ if (tx_descs > efx->txq_entries) {
+ spent = quota;
+ goto out;
+ } else if (++spent == quota) {
+ goto out;
+ }
+ break;
+ case ESE_DZ_EV_CODE_DRIVER_EV:
+ efx_ef10_handle_driver_event(channel, &event);
+ if (++spent == quota)
+ goto out;
+ break;
+ case EFX_EF10_DRVGEN_EV:
+ efx_ef10_handle_driver_generated_event(channel, &event);
+ break;
+ default:
+ netif_err(efx, hw, efx->net_dev,
+ "channel %d unknown event type %d"
+ " (data " EFX_QWORD_FMT ")\n",
+ channel->channel, ev_code,
+ EFX_QWORD_VAL(event));
+ }
+ }
+
+out:
+ channel->eventq_read_ptr = read_ptr;
+ return spent;
+}
+
+static void efx_ef10_ev_read_ack(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+ efx_dword_t rptr;
+
+ if (EFX_EF10_WORKAROUND_35388(efx)) {
+ BUILD_BUG_ON(EFX_MIN_EVQ_SIZE <
+ (1 << ERF_DD_EVQ_IND_RPTR_WIDTH));
+ BUILD_BUG_ON(EFX_MAX_EVQ_SIZE >
+ (1 << 2 * ERF_DD_EVQ_IND_RPTR_WIDTH));
+
+ EFX_POPULATE_DWORD_2(rptr, ERF_DD_EVQ_IND_RPTR_FLAGS,
+ EFE_DD_EVQ_IND_RPTR_FLAGS_HIGH,
+ ERF_DD_EVQ_IND_RPTR,
+ (channel->eventq_read_ptr &
+ channel->eventq_mask) >>
+ ERF_DD_EVQ_IND_RPTR_WIDTH);
+ efx_writed_page(efx, &rptr, ER_DD_EVQ_INDIRECT,
+ channel->channel);
+ EFX_POPULATE_DWORD_2(rptr, ERF_DD_EVQ_IND_RPTR_FLAGS,
+ EFE_DD_EVQ_IND_RPTR_FLAGS_LOW,
+ ERF_DD_EVQ_IND_RPTR,
+ channel->eventq_read_ptr &
+ ((1 << ERF_DD_EVQ_IND_RPTR_WIDTH) - 1));
+ efx_writed_page(efx, &rptr, ER_DD_EVQ_INDIRECT,
+ channel->channel);
+ } else {
+ EFX_POPULATE_DWORD_1(rptr, ERF_DZ_EVQ_RPTR,
+ channel->eventq_read_ptr &
+ channel->eventq_mask);
+ efx_writed_page(efx, &rptr, ER_DZ_EVQ_RPTR, channel->channel);
+ }
+}
+
+static void efx_ef10_ev_test_generate(struct efx_channel *channel)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_DRIVER_EVENT_IN_LEN);
+ struct efx_nic *efx = channel->efx;
+ efx_qword_t event;
+ int rc;
+
+ EFX_POPULATE_QWORD_2(event,
+ ESF_DZ_EV_CODE, EFX_EF10_DRVGEN_EV,
+ ESF_DZ_EV_DATA, EFX_EF10_TEST);
+
+ MCDI_SET_DWORD(inbuf, DRIVER_EVENT_IN_EVQ, channel->channel);
+
+ /* MCDI_SET_QWORD is not appropriate here since EFX_POPULATE_* has
+ * already swapped the data to little-endian order.
+ */
+ memcpy(MCDI_PTR(inbuf, DRIVER_EVENT_IN_DATA), &event.u64[0],
+ sizeof(efx_qword_t));
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_DRIVER_EVENT, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ if (rc != 0)
+ goto fail;
+
+ return;
+
+fail:
+ WARN_ON(true);
+ netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+}
+
+void efx_ef10_handle_drain_event(struct efx_nic *efx)
+{
+ if (atomic_dec_and_test(&efx->active_queues))
+ wake_up(&efx->flush_wq);
+
+ WARN_ON(atomic_read(&efx->active_queues) < 0);
+}
+
+static int efx_ef10_fini_dmaq(struct efx_nic *efx)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ int pending;
+
+ /* If the MC has just rebooted, the TX/RX queues will have already been
+ * torn down, but efx->active_queues needs to be set to zero.
+ */
+ if (nic_data->must_realloc_vis) {
+ atomic_set(&efx->active_queues, 0);
+ return 0;
+ }
+
+ /* Do not attempt to write to the NIC during EEH recovery */
+ if (efx->state != STATE_RECOVERY) {
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ efx_ef10_rx_fini(rx_queue);
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ efx_ef10_tx_fini(tx_queue);
+ }
+
+ wait_event_timeout(efx->flush_wq,
+ atomic_read(&efx->active_queues) == 0,
+ msecs_to_jiffies(EFX_MAX_FLUSH_TIME));
+ pending = atomic_read(&efx->active_queues);
+ if (pending) {
+ netif_err(efx, hw, efx->net_dev, "failed to flush %d queues\n",
+ pending);
+ return -ETIMEDOUT;
+ }
+ }
+
+ return 0;
+}
+
+static void efx_ef10_prepare_flr(struct efx_nic *efx)
+{
+ atomic_set(&efx->active_queues, 0);
+}
+
+static bool efx_ef10_filter_equal(const struct efx_filter_spec *left,
+ const struct efx_filter_spec *right)
+{
+ if ((left->match_flags ^ right->match_flags) |
+ ((left->flags ^ right->flags) &
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)))
+ return false;
+
+ return memcmp(&left->outer_vid, &right->outer_vid,
+ sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) == 0;
+}
+
+static unsigned int efx_ef10_filter_hash(const struct efx_filter_spec *spec)
+{
+ BUILD_BUG_ON(offsetof(struct efx_filter_spec, outer_vid) & 3);
+ return jhash2((const u32 *)&spec->outer_vid,
+ (sizeof(struct efx_filter_spec) -
+ offsetof(struct efx_filter_spec, outer_vid)) / 4,
+ 0);
+ /* XXX should we randomise the initval? */
+}
+
+/* Decide whether a filter should be exclusive or else should allow
+ * delivery to additional recipients. Currently we decide that
+ * filters for specific local unicast MAC and IP addresses are
+ * exclusive.
+ */
+static bool efx_ef10_filter_is_exclusive(const struct efx_filter_spec *spec)
+{
+ if (spec->match_flags & EFX_FILTER_MATCH_LOC_MAC &&
+ !is_multicast_ether_addr(spec->loc_mac))
+ return true;
+
+ if ((spec->match_flags &
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) ==
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) {
+ if (spec->ether_type == htons(ETH_P_IP) &&
+ !ipv4_is_multicast(spec->loc_host[0]))
+ return true;
+ if (spec->ether_type == htons(ETH_P_IPV6) &&
+ ((const u8 *)spec->loc_host)[0] != 0xff)
+ return true;
+ }
+
+ return false;
+}
+
+static struct efx_filter_spec *
+efx_ef10_filter_entry_spec(const struct efx_ef10_filter_table *table,
+ unsigned int filter_idx)
+{
+ return (struct efx_filter_spec *)(table->entry[filter_idx].spec &
+ ~EFX_EF10_FILTER_FLAGS);
+}
+
+static unsigned int
+efx_ef10_filter_entry_flags(const struct efx_ef10_filter_table *table,
+ unsigned int filter_idx)
+{
+ return table->entry[filter_idx].spec & EFX_EF10_FILTER_FLAGS;
+}
+
+static void
+efx_ef10_filter_set_entry(struct efx_ef10_filter_table *table,
+ unsigned int filter_idx,
+ const struct efx_filter_spec *spec,
+ unsigned int flags)
+{
+ table->entry[filter_idx].spec = (unsigned long)spec | flags;
+}
+
+static void efx_ef10_filter_push_prep(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ efx_dword_t *inbuf, u64 handle,
+ bool replacing)
+{
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+
+ memset(inbuf, 0, MC_CMD_FILTER_OP_IN_LEN);
+
+ if (replacing) {
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ MC_CMD_FILTER_OP_IN_OP_REPLACE);
+ MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE, handle);
+ } else {
+ u32 match_fields = 0;
+
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ efx_ef10_filter_is_exclusive(spec) ?
+ MC_CMD_FILTER_OP_IN_OP_INSERT :
+ MC_CMD_FILTER_OP_IN_OP_SUBSCRIBE);
+
+ /* Convert match flags and values. Unlike almost
+ * everything else in MCDI, these fields are in
+ * network byte order.
+ */
+ if (spec->match_flags & EFX_FILTER_MATCH_LOC_MAC_IG)
+ match_fields |=
+ is_multicast_ether_addr(spec->loc_mac) ?
+ 1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_MCAST_DST_LBN :
+ 1 << MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_UCAST_DST_LBN;
+#define COPY_FIELD(gen_flag, gen_field, mcdi_field) \
+ if (spec->match_flags & EFX_FILTER_MATCH_ ## gen_flag) { \
+ match_fields |= \
+ 1 << MC_CMD_FILTER_OP_IN_MATCH_ ## \
+ mcdi_field ## _LBN; \
+ BUILD_BUG_ON( \
+ MC_CMD_FILTER_OP_IN_ ## mcdi_field ## _LEN < \
+ sizeof(spec->gen_field)); \
+ memcpy(MCDI_PTR(inbuf, FILTER_OP_IN_ ## mcdi_field), \
+ &spec->gen_field, sizeof(spec->gen_field)); \
+ }
+ COPY_FIELD(REM_HOST, rem_host, SRC_IP);
+ COPY_FIELD(LOC_HOST, loc_host, DST_IP);
+ COPY_FIELD(REM_MAC, rem_mac, SRC_MAC);
+ COPY_FIELD(REM_PORT, rem_port, SRC_PORT);
+ COPY_FIELD(LOC_MAC, loc_mac, DST_MAC);
+ COPY_FIELD(LOC_PORT, loc_port, DST_PORT);
+ COPY_FIELD(ETHER_TYPE, ether_type, ETHER_TYPE);
+ COPY_FIELD(INNER_VID, inner_vid, INNER_VLAN);
+ COPY_FIELD(OUTER_VID, outer_vid, OUTER_VLAN);
+ COPY_FIELD(IP_PROTO, ip_proto, IP_PROTO);
+#undef COPY_FIELD
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_MATCH_FIELDS,
+ match_fields);
+ }
+
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_PORT_ID, EVB_PORT_ID_ASSIGNED);
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_DEST,
+ spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ?
+ MC_CMD_FILTER_OP_IN_RX_DEST_DROP :
+ MC_CMD_FILTER_OP_IN_RX_DEST_HOST);
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_TX_DEST,
+ MC_CMD_FILTER_OP_IN_TX_DEST_DEFAULT);
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_QUEUE,
+ spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ?
+ 0 : spec->dmaq_id);
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_MODE,
+ (spec->flags & EFX_FILTER_FLAG_RX_RSS) ?
+ MC_CMD_FILTER_OP_IN_RX_MODE_RSS :
+ MC_CMD_FILTER_OP_IN_RX_MODE_SIMPLE);
+ if (spec->flags & EFX_FILTER_FLAG_RX_RSS)
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_CONTEXT,
+ spec->rss_context !=
+ EFX_FILTER_RSS_CONTEXT_DEFAULT ?
+ spec->rss_context : nic_data->rx_rss_context);
+}
+
+static int efx_ef10_filter_push(struct efx_nic *efx,
+ const struct efx_filter_spec *spec,
+ u64 *handle, bool replacing)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_FILTER_OP_OUT_LEN);
+ int rc;
+
+ efx_ef10_filter_push_prep(efx, spec, inbuf, *handle, replacing);
+ rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ if (rc == 0)
+ *handle = MCDI_QWORD(outbuf, FILTER_OP_OUT_HANDLE);
+ if (rc == -ENOSPC)
+ rc = -EBUSY; /* to match efx_farch_filter_insert() */
+ return rc;
+}
+
+static int efx_ef10_filter_rx_match_pri(struct efx_ef10_filter_table *table,
+ enum efx_filter_match_flags match_flags)
+{
+ unsigned int match_pri;
+
+ for (match_pri = 0;
+ match_pri < table->rx_match_count;
+ match_pri++)
+ if (table->rx_match_flags[match_pri] == match_flags)
+ return match_pri;
+
+ return -EPROTONOSUPPORT;
+}
+
+static s32 efx_ef10_filter_insert(struct efx_nic *efx,
+ struct efx_filter_spec *spec,
+ bool replace_equal)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ DECLARE_BITMAP(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
+ struct efx_filter_spec *saved_spec;
+ unsigned int match_pri, hash;
+ unsigned int priv_flags;
+ bool replacing = false;
+ int ins_index = -1;
+ DEFINE_WAIT(wait);
+ bool is_mc_recip;
+ s32 rc;
+
+ /* For now, only support RX filters */
+ if ((spec->flags & (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_TX)) !=
+ EFX_FILTER_FLAG_RX)
+ return -EINVAL;
+
+ rc = efx_ef10_filter_rx_match_pri(table, spec->match_flags);
+ if (rc < 0)
+ return rc;
+ match_pri = rc;
+
+ hash = efx_ef10_filter_hash(spec);
+ is_mc_recip = efx_filter_is_mc_recipient(spec);
+ if (is_mc_recip)
+ bitmap_zero(mc_rem_map, EFX_EF10_FILTER_SEARCH_LIMIT);
+
+ /* Find any existing filters with the same match tuple or
+ * else a free slot to insert at. If any of them are busy,
+ * we have to wait and retry.
+ */
+ for (;;) {
+ unsigned int depth = 1;
+ unsigned int i;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (;;) {
+ i = (hash + depth) & (HUNT_FILTER_TBL_ROWS - 1);
+ saved_spec = efx_ef10_filter_entry_spec(table, i);
+
+ if (!saved_spec) {
+ if (ins_index < 0)
+ ins_index = i;
+ } else if (efx_ef10_filter_equal(spec, saved_spec)) {
+ if (table->entry[i].spec &
+ EFX_EF10_FILTER_FLAG_BUSY)
+ break;
+ if (spec->priority < saved_spec->priority &&
+ spec->priority != EFX_FILTER_PRI_AUTO) {
+ rc = -EPERM;
+ goto out_unlock;
+ }
+ if (!is_mc_recip) {
+ /* This is the only one */
+ if (spec->priority ==
+ saved_spec->priority &&
+ !replace_equal) {
+ rc = -EEXIST;
+ goto out_unlock;
+ }
+ ins_index = i;
+ goto found;
+ } else if (spec->priority >
+ saved_spec->priority ||
+ (spec->priority ==
+ saved_spec->priority &&
+ replace_equal)) {
+ if (ins_index < 0)
+ ins_index = i;
+ else
+ __set_bit(depth, mc_rem_map);
+ }
+ }
+
+ /* Once we reach the maximum search depth, use
+ * the first suitable slot or return -EBUSY if
+ * there was none
+ */
+ if (depth == EFX_EF10_FILTER_SEARCH_LIMIT) {
+ if (ins_index < 0) {
+ rc = -EBUSY;
+ goto out_unlock;
+ }
+ goto found;
+ }
+
+ ++depth;
+ }
+
+ prepare_to_wait(&table->waitq, &wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock_bh(&efx->filter_lock);
+ schedule();
+ }
+
+found:
+ /* Create a software table entry if necessary, and mark it
+ * busy. We might yet fail to insert, but any attempt to
+ * insert a conflicting filter while we're waiting for the
+ * firmware must find the busy entry.
+ */
+ saved_spec = efx_ef10_filter_entry_spec(table, ins_index);
+ if (saved_spec) {
+ if (spec->priority == EFX_FILTER_PRI_AUTO &&
+ saved_spec->priority >= EFX_FILTER_PRI_AUTO) {
+ /* Just make sure it won't be removed */
+ if (saved_spec->priority > EFX_FILTER_PRI_AUTO)
+ saved_spec->flags |= EFX_FILTER_FLAG_RX_OVER_AUTO;
+ table->entry[ins_index].spec &=
+ ~EFX_EF10_FILTER_FLAG_AUTO_OLD;
+ rc = ins_index;
+ goto out_unlock;
+ }
+ replacing = true;
+ priv_flags = efx_ef10_filter_entry_flags(table, ins_index);
+ } else {
+ saved_spec = kmalloc(sizeof(*spec), GFP_ATOMIC);
+ if (!saved_spec) {
+ rc = -ENOMEM;
+ goto out_unlock;
+ }
+ *saved_spec = *spec;
+ priv_flags = 0;
+ }
+ efx_ef10_filter_set_entry(table, ins_index, saved_spec,
+ priv_flags | EFX_EF10_FILTER_FLAG_BUSY);
+
+ /* Mark lower-priority multicast recipients busy prior to removal */
+ if (is_mc_recip) {
+ unsigned int depth, i;
+
+ for (depth = 0; depth < EFX_EF10_FILTER_SEARCH_LIMIT; depth++) {
+ i = (hash + depth) & (HUNT_FILTER_TBL_ROWS - 1);
+ if (test_bit(depth, mc_rem_map))
+ table->entry[i].spec |=
+ EFX_EF10_FILTER_FLAG_BUSY;
+ }
+ }
+
+ spin_unlock_bh(&efx->filter_lock);
+
+ rc = efx_ef10_filter_push(efx, spec, &table->entry[ins_index].handle,
+ replacing);
+
+ /* Finalise the software table entry */
+ spin_lock_bh(&efx->filter_lock);
+ if (rc == 0) {
+ if (replacing) {
+ /* Update the fields that may differ */
+ if (saved_spec->priority == EFX_FILTER_PRI_AUTO)
+ saved_spec->flags |=
+ EFX_FILTER_FLAG_RX_OVER_AUTO;
+ saved_spec->priority = spec->priority;
+ saved_spec->flags &= EFX_FILTER_FLAG_RX_OVER_AUTO;
+ saved_spec->flags |= spec->flags;
+ saved_spec->rss_context = spec->rss_context;
+ saved_spec->dmaq_id = spec->dmaq_id;
+ }
+ } else if (!replacing) {
+ kfree(saved_spec);
+ saved_spec = NULL;
+ }
+ efx_ef10_filter_set_entry(table, ins_index, saved_spec, priv_flags);
+
+ /* Remove and finalise entries for lower-priority multicast
+ * recipients
+ */
+ if (is_mc_recip) {
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+ unsigned int depth, i;
+
+ memset(inbuf, 0, sizeof(inbuf));
+
+ for (depth = 0; depth < EFX_EF10_FILTER_SEARCH_LIMIT; depth++) {
+ if (!test_bit(depth, mc_rem_map))
+ continue;
+
+ i = (hash + depth) & (HUNT_FILTER_TBL_ROWS - 1);
+ saved_spec = efx_ef10_filter_entry_spec(table, i);
+ priv_flags = efx_ef10_filter_entry_flags(table, i);
+
+ if (rc == 0) {
+ spin_unlock_bh(&efx->filter_lock);
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE);
+ MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE,
+ table->entry[i].handle);
+ rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP,
+ inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ spin_lock_bh(&efx->filter_lock);
+ }
+
+ if (rc == 0) {
+ kfree(saved_spec);
+ saved_spec = NULL;
+ priv_flags = 0;
+ } else {
+ priv_flags &= ~EFX_EF10_FILTER_FLAG_BUSY;
+ }
+ efx_ef10_filter_set_entry(table, i, saved_spec,
+ priv_flags);
+ }
+ }
+
+ /* If successful, return the inserted filter ID */
+ if (rc == 0)
+ rc = match_pri * HUNT_FILTER_TBL_ROWS + ins_index;
+
+ wake_up_all(&table->waitq);
+out_unlock:
+ spin_unlock_bh(&efx->filter_lock);
+ finish_wait(&table->waitq, &wait);
+ return rc;
+}
+
+static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx)
+{
+ /* no need to do anything here on EF10 */
+}
+
+/* Remove a filter.
+ * If !by_index, remove by ID
+ * If by_index, remove by index
+ * Filter ID may come from userland and must be range-checked.
+ */
+static int efx_ef10_filter_remove_internal(struct efx_nic *efx,
+ unsigned int priority_mask,
+ u32 filter_id, bool by_index)
+{
+ unsigned int filter_idx = filter_id % HUNT_FILTER_TBL_ROWS;
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_FILTER_OP_IN_HANDLE_OFST +
+ MC_CMD_FILTER_OP_IN_HANDLE_LEN);
+ struct efx_filter_spec *spec;
+ DEFINE_WAIT(wait);
+ int rc;
+
+ /* Find the software table entry and mark it busy. Don't
+ * remove it yet; any attempt to update while we're waiting
+ * for the firmware must find the busy entry.
+ */
+ for (;;) {
+ spin_lock_bh(&efx->filter_lock);
+ if (!(table->entry[filter_idx].spec &
+ EFX_EF10_FILTER_FLAG_BUSY))
+ break;
+ prepare_to_wait(&table->waitq, &wait, TASK_UNINTERRUPTIBLE);
+ spin_unlock_bh(&efx->filter_lock);
+ schedule();
+ }
+
+ spec = efx_ef10_filter_entry_spec(table, filter_idx);
+ if (!spec ||
+ (!by_index &&
+ efx_ef10_filter_rx_match_pri(table, spec->match_flags) !=
+ filter_id / HUNT_FILTER_TBL_ROWS)) {
+ rc = -ENOENT;
+ goto out_unlock;
+ }
+
+ if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO &&
+ priority_mask == (1U << EFX_FILTER_PRI_AUTO)) {
+ /* Just remove flags */
+ spec->flags &= ~EFX_FILTER_FLAG_RX_OVER_AUTO;
+ table->entry[filter_idx].spec &= ~EFX_EF10_FILTER_FLAG_AUTO_OLD;
+ rc = 0;
+ goto out_unlock;
+ }
+
+ if (!(priority_mask & (1U << spec->priority))) {
+ rc = -ENOENT;
+ goto out_unlock;
+ }
+
+ table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_BUSY;
+ spin_unlock_bh(&efx->filter_lock);
+
+ if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) {
+ /* Reset to an automatic filter */
+
+ struct efx_filter_spec new_spec = *spec;
+
+ new_spec.priority = EFX_FILTER_PRI_AUTO;
+ new_spec.flags = (EFX_FILTER_FLAG_RX |
+ EFX_FILTER_FLAG_RX_RSS);
+ new_spec.dmaq_id = 0;
+ new_spec.rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT;
+ rc = efx_ef10_filter_push(efx, &new_spec,
+ &table->entry[filter_idx].handle,
+ true);
+
+ spin_lock_bh(&efx->filter_lock);
+ if (rc == 0)
+ *spec = new_spec;
+ } else {
+ /* Really remove the filter */
+
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ efx_ef10_filter_is_exclusive(spec) ?
+ MC_CMD_FILTER_OP_IN_OP_REMOVE :
+ MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE);
+ MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE,
+ table->entry[filter_idx].handle);
+ rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
+
+ spin_lock_bh(&efx->filter_lock);
+ if (rc == 0) {
+ kfree(spec);
+ efx_ef10_filter_set_entry(table, filter_idx, NULL, 0);
+ }
+ }
+
+ table->entry[filter_idx].spec &= ~EFX_EF10_FILTER_FLAG_BUSY;
+ wake_up_all(&table->waitq);
+out_unlock:
+ spin_unlock_bh(&efx->filter_lock);
+ finish_wait(&table->waitq, &wait);
+ return rc;
+}
+
+static int efx_ef10_filter_remove_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id)
+{
+ return efx_ef10_filter_remove_internal(efx, 1U << priority,
+ filter_id, false);
+}
+
+static int efx_ef10_filter_get_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *spec)
+{
+ unsigned int filter_idx = filter_id % HUNT_FILTER_TBL_ROWS;
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ const struct efx_filter_spec *saved_spec;
+ int rc;
+
+ spin_lock_bh(&efx->filter_lock);
+ saved_spec = efx_ef10_filter_entry_spec(table, filter_idx);
+ if (saved_spec && saved_spec->priority == priority &&
+ efx_ef10_filter_rx_match_pri(table, saved_spec->match_flags) ==
+ filter_id / HUNT_FILTER_TBL_ROWS) {
+ *spec = *saved_spec;
+ rc = 0;
+ } else {
+ rc = -ENOENT;
+ }
+ spin_unlock_bh(&efx->filter_lock);
+ return rc;
+}
+
+static int efx_ef10_filter_clear_rx(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ unsigned int priority_mask;
+ unsigned int i;
+ int rc;
+
+ priority_mask = (((1U << (priority + 1)) - 1) &
+ ~(1U << EFX_FILTER_PRI_AUTO));
+
+ for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) {
+ rc = efx_ef10_filter_remove_internal(efx, priority_mask,
+ i, true);
+ if (rc && rc != -ENOENT)
+ return rc;
+ }
+
+ return 0;
+}
+
+static u32 efx_ef10_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ unsigned int filter_idx;
+ s32 count = 0;
+
+ spin_lock_bh(&efx->filter_lock);
+ for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
+ if (table->entry[filter_idx].spec &&
+ efx_ef10_filter_entry_spec(table, filter_idx)->priority ==
+ priority)
+ ++count;
+ }
+ spin_unlock_bh(&efx->filter_lock);
+ return count;
+}
+
+static u32 efx_ef10_filter_get_rx_id_limit(struct efx_nic *efx)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+
+ return table->rx_match_count * HUNT_FILTER_TBL_ROWS;
+}
+
+static s32 efx_ef10_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ struct efx_filter_spec *spec;
+ unsigned int filter_idx;
+ s32 count = 0;
+
+ spin_lock_bh(&efx->filter_lock);
+ for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
+ spec = efx_ef10_filter_entry_spec(table, filter_idx);
+ if (spec && spec->priority == priority) {
+ if (count == size) {
+ count = -EMSGSIZE;
+ break;
+ }
+ buf[count++] = (efx_ef10_filter_rx_match_pri(
+ table, spec->match_flags) *
+ HUNT_FILTER_TBL_ROWS +
+ filter_idx);
+ }
+ }
+ spin_unlock_bh(&efx->filter_lock);
+ return count;
+}
+
+#ifdef CONFIG_RFS_ACCEL
+
+static efx_mcdi_async_completer efx_ef10_filter_rfs_insert_complete;
+
+static s32 efx_ef10_filter_rfs_insert(struct efx_nic *efx,
+ struct efx_filter_spec *spec)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+ struct efx_filter_spec *saved_spec;
+ unsigned int hash, i, depth = 1;
+ bool replacing = false;
+ int ins_index = -1;
+ u64 cookie;
+ s32 rc;
+
+ /* Must be an RX filter without RSS and not for a multicast
+ * destination address (RFS only works for connected sockets).
+ * These restrictions allow us to pass only a tiny amount of
+ * data through to the completion function.
+ */
+ EFX_WARN_ON_PARANOID(spec->flags !=
+ (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_SCATTER));
+ EFX_WARN_ON_PARANOID(spec->priority != EFX_FILTER_PRI_HINT);
+ EFX_WARN_ON_PARANOID(efx_filter_is_mc_recipient(spec));
+
+ hash = efx_ef10_filter_hash(spec);
+
+ spin_lock_bh(&efx->filter_lock);
+
+ /* Find any existing filter with the same match tuple or else
+ * a free slot to insert at. If an existing filter is busy,
+ * we have to give up.
+ */
+ for (;;) {
+ i = (hash + depth) & (HUNT_FILTER_TBL_ROWS - 1);
+ saved_spec = efx_ef10_filter_entry_spec(table, i);
+
+ if (!saved_spec) {
+ if (ins_index < 0)
+ ins_index = i;
+ } else if (efx_ef10_filter_equal(spec, saved_spec)) {
+ if (table->entry[i].spec & EFX_EF10_FILTER_FLAG_BUSY) {
+ rc = -EBUSY;
+ goto fail_unlock;
+ }
+ if (spec->priority < saved_spec->priority) {
+ rc = -EPERM;
+ goto fail_unlock;
+ }
+ ins_index = i;
+ break;
+ }
+
+ /* Once we reach the maximum search depth, use the
+ * first suitable slot or return -EBUSY if there was
+ * none
+ */
+ if (depth == EFX_EF10_FILTER_SEARCH_LIMIT) {
+ if (ins_index < 0) {
+ rc = -EBUSY;
+ goto fail_unlock;
+ }
+ break;
+ }
+
+ ++depth;
+ }
+
+ /* Create a software table entry if necessary, and mark it
+ * busy. We might yet fail to insert, but any attempt to
+ * insert a conflicting filter while we're waiting for the
+ * firmware must find the busy entry.
+ */
+ saved_spec = efx_ef10_filter_entry_spec(table, ins_index);
+ if (saved_spec) {
+ replacing = true;
+ } else {
+ saved_spec = kmalloc(sizeof(*spec), GFP_ATOMIC);
+ if (!saved_spec) {
+ rc = -ENOMEM;
+ goto fail_unlock;
+ }
+ *saved_spec = *spec;
+ }
+ efx_ef10_filter_set_entry(table, ins_index, saved_spec,
+ EFX_EF10_FILTER_FLAG_BUSY);
+
+ spin_unlock_bh(&efx->filter_lock);
+
+ /* Pack up the variables needed on completion */
+ cookie = replacing << 31 | ins_index << 16 | spec->dmaq_id;
+
+ efx_ef10_filter_push_prep(efx, spec, inbuf,
+ table->entry[ins_index].handle, replacing);
+ efx_mcdi_rpc_async(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf),
+ MC_CMD_FILTER_OP_OUT_LEN,
+ efx_ef10_filter_rfs_insert_complete, cookie);
+
+ return ins_index;
+
+fail_unlock:
+ spin_unlock_bh(&efx->filter_lock);
+ return rc;
+}
+
+static void
+efx_ef10_filter_rfs_insert_complete(struct efx_nic *efx, unsigned long cookie,
+ int rc, efx_dword_t *outbuf,
+ size_t outlen_actual)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ unsigned int ins_index, dmaq_id;
+ struct efx_filter_spec *spec;
+ bool replacing;
+
+ /* Unpack the cookie */
+ replacing = cookie >> 31;
+ ins_index = (cookie >> 16) & (HUNT_FILTER_TBL_ROWS - 1);
+ dmaq_id = cookie & 0xffff;
+
+ spin_lock_bh(&efx->filter_lock);
+ spec = efx_ef10_filter_entry_spec(table, ins_index);
+ if (rc == 0) {
+ table->entry[ins_index].handle =
+ MCDI_QWORD(outbuf, FILTER_OP_OUT_HANDLE);
+ if (replacing)
+ spec->dmaq_id = dmaq_id;
+ } else if (!replacing) {
+ kfree(spec);
+ spec = NULL;
+ }
+ efx_ef10_filter_set_entry(table, ins_index, spec, 0);
+ spin_unlock_bh(&efx->filter_lock);
+
+ wake_up_all(&table->waitq);
+}
+
+static void
+efx_ef10_filter_rfs_expire_complete(struct efx_nic *efx,
+ unsigned long filter_idx,
+ int rc, efx_dword_t *outbuf,
+ size_t outlen_actual);
+
+static bool efx_ef10_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
+ unsigned int filter_idx)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ struct efx_filter_spec *spec =
+ efx_ef10_filter_entry_spec(table, filter_idx);
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_FILTER_OP_IN_HANDLE_OFST +
+ MC_CMD_FILTER_OP_IN_HANDLE_LEN);
+
+ if (!spec ||
+ (table->entry[filter_idx].spec & EFX_EF10_FILTER_FLAG_BUSY) ||
+ spec->priority != EFX_FILTER_PRI_HINT ||
+ !rps_may_expire_flow(efx->net_dev, spec->dmaq_id,
+ flow_id, filter_idx))
+ return false;
+
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ MC_CMD_FILTER_OP_IN_OP_REMOVE);
+ MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE,
+ table->entry[filter_idx].handle);
+ if (efx_mcdi_rpc_async(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf), 0,
+ efx_ef10_filter_rfs_expire_complete, filter_idx))
+ return false;
+
+ table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_BUSY;
+ return true;
+}
+
+static void
+efx_ef10_filter_rfs_expire_complete(struct efx_nic *efx,
+ unsigned long filter_idx,
+ int rc, efx_dword_t *outbuf,
+ size_t outlen_actual)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ struct efx_filter_spec *spec =
+ efx_ef10_filter_entry_spec(table, filter_idx);
+
+ spin_lock_bh(&efx->filter_lock);
+ if (rc == 0) {
+ kfree(spec);
+ efx_ef10_filter_set_entry(table, filter_idx, NULL, 0);
+ }
+ table->entry[filter_idx].spec &= ~EFX_EF10_FILTER_FLAG_BUSY;
+ wake_up_all(&table->waitq);
+ spin_unlock_bh(&efx->filter_lock);
+}
+
+#endif /* CONFIG_RFS_ACCEL */
+
+static int efx_ef10_filter_match_flags_from_mcdi(u32 mcdi_flags)
+{
+ int match_flags = 0;
+
+#define MAP_FLAG(gen_flag, mcdi_field) { \
+ u32 old_mcdi_flags = mcdi_flags; \
+ mcdi_flags &= ~(1 << MC_CMD_FILTER_OP_IN_MATCH_ ## \
+ mcdi_field ## _LBN); \
+ if (mcdi_flags != old_mcdi_flags) \
+ match_flags |= EFX_FILTER_MATCH_ ## gen_flag; \
+ }
+ MAP_FLAG(LOC_MAC_IG, UNKNOWN_UCAST_DST);
+ MAP_FLAG(LOC_MAC_IG, UNKNOWN_MCAST_DST);
+ MAP_FLAG(REM_HOST, SRC_IP);
+ MAP_FLAG(LOC_HOST, DST_IP);
+ MAP_FLAG(REM_MAC, SRC_MAC);
+ MAP_FLAG(REM_PORT, SRC_PORT);
+ MAP_FLAG(LOC_MAC, DST_MAC);
+ MAP_FLAG(LOC_PORT, DST_PORT);
+ MAP_FLAG(ETHER_TYPE, ETHER_TYPE);
+ MAP_FLAG(INNER_VID, INNER_VLAN);
+ MAP_FLAG(OUTER_VID, OUTER_VLAN);
+ MAP_FLAG(IP_PROTO, IP_PROTO);
+#undef MAP_FLAG
+
+ /* Did we map them all? */
+ if (mcdi_flags)
+ return -EINVAL;
+
+ return match_flags;
+}
+
+static int efx_ef10_filter_table_probe(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PARSER_DISP_INFO_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMAX);
+ unsigned int pd_match_pri, pd_match_count;
+ struct efx_ef10_filter_table *table;
+ size_t outlen;
+ int rc;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return -ENOMEM;
+
+ /* Find out which RX filter types are supported, and their priorities */
+ MCDI_SET_DWORD(inbuf, GET_PARSER_DISP_INFO_IN_OP,
+ MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_RX_MATCHES);
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PARSER_DISP_INFO,
+ inbuf, sizeof(inbuf), outbuf, sizeof(outbuf),
+ &outlen);
+ if (rc)
+ goto fail;
+ pd_match_count = MCDI_VAR_ARRAY_LEN(
+ outlen, GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES);
+ table->rx_match_count = 0;
+
+ for (pd_match_pri = 0; pd_match_pri < pd_match_count; pd_match_pri++) {
+ u32 mcdi_flags =
+ MCDI_ARRAY_DWORD(
+ outbuf,
+ GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES,
+ pd_match_pri);
+ rc = efx_ef10_filter_match_flags_from_mcdi(mcdi_flags);
+ if (rc < 0) {
+ netif_dbg(efx, probe, efx->net_dev,
+ "%s: fw flags %#x pri %u not supported in driver\n",
+ __func__, mcdi_flags, pd_match_pri);
+ } else {
+ netif_dbg(efx, probe, efx->net_dev,
+ "%s: fw flags %#x pri %u supported as driver flags %#x pri %u\n",
+ __func__, mcdi_flags, pd_match_pri,
+ rc, table->rx_match_count);
+ table->rx_match_flags[table->rx_match_count++] = rc;
+ }
+ }
+
+ table->entry = vzalloc(HUNT_FILTER_TBL_ROWS * sizeof(*table->entry));
+ if (!table->entry) {
+ rc = -ENOMEM;
+ goto fail;
+ }
+
+ efx->filter_state = table;
+ init_waitqueue_head(&table->waitq);
+ return 0;
+
+fail:
+ kfree(table);
+ return rc;
+}
+
+static void efx_ef10_filter_table_restore(struct efx_nic *efx)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ struct efx_ef10_nic_data *nic_data = efx->nic_data;
+ struct efx_filter_spec *spec;
+ unsigned int filter_idx;
+ bool failed = false;
+ int rc;
+
+ if (!nic_data->must_restore_filters)
+ return;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
+ spec = efx_ef10_filter_entry_spec(table, filter_idx);
+ if (!spec)
+ continue;
+
+ table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_BUSY;
+ spin_unlock_bh(&efx->filter_lock);
+
+ rc = efx_ef10_filter_push(efx, spec,
+ &table->entry[filter_idx].handle,
+ false);
+ if (rc)
+ failed = true;
+
+ spin_lock_bh(&efx->filter_lock);
+ if (rc) {
+ kfree(spec);
+ efx_ef10_filter_set_entry(table, filter_idx, NULL, 0);
+ } else {
+ table->entry[filter_idx].spec &=
+ ~EFX_EF10_FILTER_FLAG_BUSY;
+ }
+ }
+
+ spin_unlock_bh(&efx->filter_lock);
+
+ if (failed)
+ netif_err(efx, hw, efx->net_dev,
+ "unable to restore all filters\n");
+ else
+ nic_data->must_restore_filters = false;
+}
+
+static void efx_ef10_filter_table_remove(struct efx_nic *efx)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FILTER_OP_IN_LEN);
+ struct efx_filter_spec *spec;
+ unsigned int filter_idx;
+ int rc;
+
+ for (filter_idx = 0; filter_idx < HUNT_FILTER_TBL_ROWS; filter_idx++) {
+ spec = efx_ef10_filter_entry_spec(table, filter_idx);
+ if (!spec)
+ continue;
+
+ MCDI_SET_DWORD(inbuf, FILTER_OP_IN_OP,
+ efx_ef10_filter_is_exclusive(spec) ?
+ MC_CMD_FILTER_OP_IN_OP_REMOVE :
+ MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE);
+ MCDI_SET_QWORD(inbuf, FILTER_OP_IN_HANDLE,
+ table->entry[filter_idx].handle);
+ rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ if (rc)
+ netdev_WARN(efx->net_dev,
+ "filter_idx=%#x handle=%#llx\n",
+ filter_idx,
+ table->entry[filter_idx].handle);
+ kfree(spec);
+ }
+
+ vfree(table->entry);
+ kfree(table);
+}
+
+static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx)
+{
+ struct efx_ef10_filter_table *table = efx->filter_state;
+ struct net_device *net_dev = efx->net_dev;
+ struct efx_filter_spec spec;
+ bool remove_failed = false;
+ struct netdev_hw_addr *uc;
+ struct netdev_hw_addr *mc;
+ unsigned int filter_idx;
+ int i, n, rc;
+
+ if (!efx_dev_registered(efx))
+ return;
+
+ /* Mark old filters that may need to be removed */
+ spin_lock_bh(&efx->filter_lock);
+ n = table->dev_uc_count < 0 ? 1 : table->dev_uc_count;
+ for (i = 0; i < n; i++) {
+ filter_idx = table->dev_uc_list[i].id % HUNT_FILTER_TBL_ROWS;
+ table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;
+ }
+ n = table->dev_mc_count < 0 ? 1 : table->dev_mc_count;
+ for (i = 0; i < n; i++) {
+ filter_idx = table->dev_mc_list[i].id % HUNT_FILTER_TBL_ROWS;
+ table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD;
+ }
+ spin_unlock_bh(&efx->filter_lock);
+
+ /* Copy/convert the address lists; add the primary station
+ * address and broadcast address
+ */
+ netif_addr_lock_bh(net_dev);
+ if (net_dev->flags & IFF_PROMISC ||
+ netdev_uc_count(net_dev) >= EFX_EF10_FILTER_DEV_UC_MAX) {
+ table->dev_uc_count = -1;
+ } else {
+ table->dev_uc_count = 1 + netdev_uc_count(net_dev);
+ ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr);
+ i = 1;
+ netdev_for_each_uc_addr(uc, net_dev) {
+ ether_addr_copy(table->dev_uc_list[i].addr, uc->addr);
+ i++;
+ }
+ }
+ if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI) ||
+ netdev_mc_count(net_dev) >= EFX_EF10_FILTER_DEV_MC_MAX) {
+ table->dev_mc_count = -1;
+ } else {
+ table->dev_mc_count = 1 + netdev_mc_count(net_dev);
+ eth_broadcast_addr(table->dev_mc_list[0].addr);
+ i = 1;
+ netdev_for_each_mc_addr(mc, net_dev) {
+ ether_addr_copy(table->dev_mc_list[i].addr, mc->addr);
+ i++;
+ }
+ }
+ netif_addr_unlock_bh(net_dev);
+
+ /* Insert/renew unicast filters */
+ if (table->dev_uc_count >= 0) {
+ for (i = 0; i < table->dev_uc_count; i++) {
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
+ EFX_FILTER_FLAG_RX_RSS,
+ 0);
+ efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
+ table->dev_uc_list[i].addr);
+ rc = efx_ef10_filter_insert(efx, &spec, true);
+ if (rc < 0) {
+ /* Fall back to unicast-promisc */
+ while (i--)
+ efx_ef10_filter_remove_safe(
+ efx, EFX_FILTER_PRI_AUTO,
+ table->dev_uc_list[i].id);
+ table->dev_uc_count = -1;
+ break;
+ }
+ table->dev_uc_list[i].id = rc;
+ }
+ }
+ if (table->dev_uc_count < 0) {
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
+ EFX_FILTER_FLAG_RX_RSS,
+ 0);
+ efx_filter_set_uc_def(&spec);
+ rc = efx_ef10_filter_insert(efx, &spec, true);
+ if (rc < 0) {
+ WARN_ON(1);
+ table->dev_uc_count = 0;
+ } else {
+ table->dev_uc_list[0].id = rc;
+ }
+ }
+
+ /* Insert/renew multicast filters */
+ if (table->dev_mc_count >= 0) {
+ for (i = 0; i < table->dev_mc_count; i++) {
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
+ EFX_FILTER_FLAG_RX_RSS,
+ 0);
+ efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC,
+ table->dev_mc_list[i].addr);
+ rc = efx_ef10_filter_insert(efx, &spec, true);
+ if (rc < 0) {
+ /* Fall back to multicast-promisc */
+ while (i--)
+ efx_ef10_filter_remove_safe(
+ efx, EFX_FILTER_PRI_AUTO,
+ table->dev_mc_list[i].id);
+ table->dev_mc_count = -1;
+ break;
+ }
+ table->dev_mc_list[i].id = rc;
+ }
+ }
+ if (table->dev_mc_count < 0) {
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO,
+ EFX_FILTER_FLAG_RX_RSS,
+ 0);
+ efx_filter_set_mc_def(&spec);
+ rc = efx_ef10_filter_insert(efx, &spec, true);
+ if (rc < 0) {
+ WARN_ON(1);
+ table->dev_mc_count = 0;
+ } else {
+ table->dev_mc_list[0].id = rc;
+ }
+ }
+
+ /* Remove filters that weren't renewed. Since nothing else
+ * changes the AUTO_OLD flag or removes these filters, we
+ * don't need to hold the filter_lock while scanning for
+ * these filters.
+ */
+ for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) {
+ if (ACCESS_ONCE(table->entry[i].spec) &
+ EFX_EF10_FILTER_FLAG_AUTO_OLD) {
+ if (efx_ef10_filter_remove_internal(
+ efx, 1U << EFX_FILTER_PRI_AUTO,
+ i, true) < 0)
+ remove_failed = true;
+ }
+ }
+ WARN_ON(remove_failed);
+}
+
+static int efx_ef10_mac_reconfigure(struct efx_nic *efx)
+{
+ efx_ef10_filter_sync_rx_mode(efx);
+
+ return efx_mcdi_set_mac(efx);
+}
+
+static int efx_ef10_start_bist(struct efx_nic *efx, u32 bist_type)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN);
+
+ MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_type);
+ return efx_mcdi_rpc(efx, MC_CMD_START_BIST, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+}
+
+/* MC BISTs follow a different poll mechanism to phy BISTs.
+ * The BIST is done in the poll handler on the MC, and the MCDI command
+ * will block until the BIST is done.
+ */
+static int efx_ef10_poll_bist(struct efx_nic *efx)
+{
+ int rc;
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_LEN);
+ size_t outlen;
+ u32 result;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc != 0)
+ return rc;
+
+ if (outlen < MC_CMD_POLL_BIST_OUT_LEN)
+ return -EIO;
+
+ result = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT);
+ switch (result) {
+ case MC_CMD_POLL_BIST_PASSED:
+ netif_dbg(efx, hw, efx->net_dev, "BIST passed.\n");
+ return 0;
+ case MC_CMD_POLL_BIST_TIMEOUT:
+ netif_err(efx, hw, efx->net_dev, "BIST timed out\n");
+ return -EIO;
+ case MC_CMD_POLL_BIST_FAILED:
+ netif_err(efx, hw, efx->net_dev, "BIST failed.\n");
+ return -EIO;
+ default:
+ netif_err(efx, hw, efx->net_dev,
+ "BIST returned unknown result %u", result);
+ return -EIO;
+ }
+}
+
+static int efx_ef10_run_bist(struct efx_nic *efx, u32 bist_type)
+{
+ int rc;
+
+ netif_dbg(efx, drv, efx->net_dev, "starting BIST type %u\n", bist_type);
+
+ rc = efx_ef10_start_bist(efx, bist_type);
+ if (rc != 0)
+ return rc;
+
+ return efx_ef10_poll_bist(efx);
+}
+
+static int
+efx_ef10_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
+{
+ int rc, rc2;
+
+ efx_reset_down(efx, RESET_TYPE_WORLD);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_ENABLE_OFFLINE_BIST,
+ NULL, 0, NULL, 0, NULL);
+ if (rc != 0)
+ goto out;
+
+ tests->memory = efx_ef10_run_bist(efx, MC_CMD_MC_MEM_BIST) ? -1 : 1;
+ tests->registers = efx_ef10_run_bist(efx, MC_CMD_REG_BIST) ? -1 : 1;
+
+ rc = efx_mcdi_reset(efx, RESET_TYPE_WORLD);
+
+out:
+ rc2 = efx_reset_up(efx, RESET_TYPE_WORLD, rc == 0);
+ return rc ? rc : rc2;
+}
+
+#ifdef CONFIG_SFC_MTD
+
+struct efx_ef10_nvram_type_info {
+ u16 type, type_mask;
+ u8 port;
+ const char *name;
+};
+
+static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = {
+ { NVRAM_PARTITION_TYPE_MC_FIRMWARE, 0, 0, "sfc_mcfw" },
+ { NVRAM_PARTITION_TYPE_MC_FIRMWARE_BACKUP, 0, 0, "sfc_mcfw_backup" },
+ { NVRAM_PARTITION_TYPE_EXPANSION_ROM, 0, 0, "sfc_exp_rom" },
+ { NVRAM_PARTITION_TYPE_STATIC_CONFIG, 0, 0, "sfc_static_cfg" },
+ { NVRAM_PARTITION_TYPE_DYNAMIC_CONFIG, 0, 0, "sfc_dynamic_cfg" },
+ { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT0, 0, 0, "sfc_exp_rom_cfg" },
+ { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1, 0, 1, "sfc_exp_rom_cfg" },
+ { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT2, 0, 2, "sfc_exp_rom_cfg" },
+ { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0, 3, "sfc_exp_rom_cfg" },
+ { NVRAM_PARTITION_TYPE_LICENSE, 0, 0, "sfc_license" },
+ { NVRAM_PARTITION_TYPE_PHY_MIN, 0xff, 0, "sfc_phy_fw" },
+};
+
+static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
+ struct efx_mcdi_mtd_partition *part,
+ unsigned int type)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
+ const struct efx_ef10_nvram_type_info *info;
+ size_t size, erase_size, outlen;
+ bool protected;
+ int rc;
+
+ for (info = efx_ef10_nvram_types; ; info++) {
+ if (info ==
+ efx_ef10_nvram_types + ARRAY_SIZE(efx_ef10_nvram_types))
+ return -ENODEV;
+ if ((type & ~info->type_mask) == info->type)
+ break;
+ }
+ if (info->port != efx_port_num(efx))
+ return -ENODEV;
+
+ rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
+ if (rc)
+ return rc;
+ if (protected)
+ return -ENODEV; /* hide it */
+
+ part->nvram_type = type;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_METADATA_IN_TYPE, type);
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_METADATA, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_NVRAM_METADATA_OUT_LENMIN)
+ return -EIO;
+ if (MCDI_DWORD(outbuf, NVRAM_METADATA_OUT_FLAGS) &
+ (1 << MC_CMD_NVRAM_METADATA_OUT_SUBTYPE_VALID_LBN))
+ part->fw_subtype = MCDI_DWORD(outbuf,
+ NVRAM_METADATA_OUT_SUBTYPE);
+
+ part->common.dev_type_name = "EF10 NVRAM manager";
+ part->common.type_name = info->name;
+
+ part->common.mtd.type = MTD_NORFLASH;
+ part->common.mtd.flags = MTD_CAP_NORFLASH;
+ part->common.mtd.size = size;
+ part->common.mtd.erasesize = erase_size;
+
+ return 0;
+}
+
+static int efx_ef10_mtd_probe(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX);
+ struct efx_mcdi_mtd_partition *parts;
+ size_t outlen, n_parts_total, i, n_parts;
+ unsigned int type;
+ int rc;
+
+ ASSERT_RTNL();
+
+ BUILD_BUG_ON(MC_CMD_NVRAM_PARTITIONS_IN_LEN != 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_PARTITIONS, NULL, 0,
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_NVRAM_PARTITIONS_OUT_LENMIN)
+ return -EIO;
+
+ n_parts_total = MCDI_DWORD(outbuf, NVRAM_PARTITIONS_OUT_NUM_PARTITIONS);
+ if (n_parts_total >
+ MCDI_VAR_ARRAY_LEN(outlen, NVRAM_PARTITIONS_OUT_TYPE_ID))
+ return -EIO;
+
+ parts = kcalloc(n_parts_total, sizeof(*parts), GFP_KERNEL);
+ if (!parts)
+ return -ENOMEM;
+
+ n_parts = 0;
+ for (i = 0; i < n_parts_total; i++) {
+ type = MCDI_ARRAY_DWORD(outbuf, NVRAM_PARTITIONS_OUT_TYPE_ID,
+ i);
+ rc = efx_ef10_mtd_probe_partition(efx, &parts[n_parts], type);
+ if (rc == 0)
+ n_parts++;
+ else if (rc != -ENODEV)
+ goto fail;
+ }
+
+ rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
+fail:
+ if (rc)
+ kfree(parts);
+ return rc;
+}
+
+#endif /* CONFIG_SFC_MTD */
+
+static void efx_ef10_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
+{
+ _efx_writed(efx, cpu_to_le32(host_time), ER_DZ_MC_DB_LWRD);
+}
+
+static int efx_ef10_rx_enable_timestamping(struct efx_channel *channel,
+ bool temp)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN);
+ int rc;
+
+ if (channel->sync_events_state == SYNC_EVENTS_REQUESTED ||
+ channel->sync_events_state == SYNC_EVENTS_VALID ||
+ (temp && channel->sync_events_state == SYNC_EVENTS_DISABLED))
+ return 0;
+ channel->sync_events_state = SYNC_EVENTS_REQUESTED;
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE,
+ channel->channel);
+
+ rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
+
+ if (rc != 0)
+ channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
+ SYNC_EVENTS_DISABLED;
+
+ return rc;
+}
+
+static int efx_ef10_rx_disable_timestamping(struct efx_channel *channel,
+ bool temp)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN);
+ int rc;
+
+ if (channel->sync_events_state == SYNC_EVENTS_DISABLED ||
+ (temp && channel->sync_events_state == SYNC_EVENTS_QUIESCENT))
+ return 0;
+ if (channel->sync_events_state == SYNC_EVENTS_QUIESCENT) {
+ channel->sync_events_state = SYNC_EVENTS_DISABLED;
+ return 0;
+ }
+ channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT :
+ SYNC_EVENTS_DISABLED;
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL,
+ MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE);
+ MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE,
+ channel->channel);
+
+ rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
+
+ return rc;
+}
+
+static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en,
+ bool temp)
+{
+ int (*set)(struct efx_channel *channel, bool temp);
+ struct efx_channel *channel;
+
+ set = en ?
+ efx_ef10_rx_enable_timestamping :
+ efx_ef10_rx_disable_timestamping;
+
+ efx_for_each_channel(channel, efx) {
+ int rc = set(channel, temp);
+ if (en && rc != 0) {
+ efx_ef10_ptp_set_ts_sync_events(efx, false, temp);
+ return rc;
+ }
+ }
+
+ return 0;
+}
+
+static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx,
+ struct hwtstamp_config *init)
+{
+ int rc;
+
+ switch (init->rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ efx_ef10_ptp_set_ts_sync_events(efx, false, false);
+ /* if TX timestamping is still requested then leave PTP on */
+ return efx_ptp_change_mode(efx,
+ init->tx_type != HWTSTAMP_TX_OFF, 0);
+ case HWTSTAMP_FILTER_ALL:
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+ case HWTSTAMP_FILTER_PTP_V2_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+ init->rx_filter = HWTSTAMP_FILTER_ALL;
+ rc = efx_ptp_change_mode(efx, true, 0);
+ if (!rc)
+ rc = efx_ef10_ptp_set_ts_sync_events(efx, true, false);
+ if (rc)
+ efx_ptp_change_mode(efx, false, 0);
+ return rc;
+ default:
+ return -ERANGE;
+ }
+}
+
+const struct efx_nic_type efx_hunt_a0_nic_type = {
+ .mem_map_size = efx_ef10_mem_map_size,
+ .probe = efx_ef10_probe,
+ .remove = efx_ef10_remove,
+ .dimension_resources = efx_ef10_dimension_resources,
+ .init = efx_ef10_init_nic,
+ .fini = efx_port_dummy_op_void,
+ .map_reset_reason = efx_mcdi_map_reset_reason,
+ .map_reset_flags = efx_ef10_map_reset_flags,
+ .reset = efx_ef10_reset,
+ .probe_port = efx_mcdi_port_probe,
+ .remove_port = efx_mcdi_port_remove,
+ .fini_dmaq = efx_ef10_fini_dmaq,
+ .prepare_flr = efx_ef10_prepare_flr,
+ .finish_flr = efx_port_dummy_op_void,
+ .describe_stats = efx_ef10_describe_stats,
+ .update_stats = efx_ef10_update_stats,
+ .start_stats = efx_mcdi_mac_start_stats,
+ .pull_stats = efx_mcdi_mac_pull_stats,
+ .stop_stats = efx_mcdi_mac_stop_stats,
+ .set_id_led = efx_mcdi_set_id_led,
+ .push_irq_moderation = efx_ef10_push_irq_moderation,
+ .reconfigure_mac = efx_ef10_mac_reconfigure,
+ .check_mac_fault = efx_mcdi_mac_check_fault,
+ .reconfigure_port = efx_mcdi_port_reconfigure,
+ .get_wol = efx_ef10_get_wol,
+ .set_wol = efx_ef10_set_wol,
+ .resume_wol = efx_port_dummy_op_void,
+ .test_chip = efx_ef10_test_chip,
+ .test_nvram = efx_mcdi_nvram_test_all,
+ .mcdi_request = efx_ef10_mcdi_request,
+ .mcdi_poll_response = efx_ef10_mcdi_poll_response,
+ .mcdi_read_response = efx_ef10_mcdi_read_response,
+ .mcdi_poll_reboot = efx_ef10_mcdi_poll_reboot,
+ .irq_enable_master = efx_port_dummy_op_void,
+ .irq_test_generate = efx_ef10_irq_test_generate,
+ .irq_disable_non_ev = efx_port_dummy_op_void,
+ .irq_handle_msi = efx_ef10_msi_interrupt,
+ .irq_handle_legacy = efx_ef10_legacy_interrupt,
+ .tx_probe = efx_ef10_tx_probe,
+ .tx_init = efx_ef10_tx_init,
+ .tx_remove = efx_ef10_tx_remove,
+ .tx_write = efx_ef10_tx_write,
+ .rx_push_rss_config = efx_ef10_rx_push_rss_config,
+ .rx_probe = efx_ef10_rx_probe,
+ .rx_init = efx_ef10_rx_init,
+ .rx_remove = efx_ef10_rx_remove,
+ .rx_write = efx_ef10_rx_write,
+ .rx_defer_refill = efx_ef10_rx_defer_refill,
+ .ev_probe = efx_ef10_ev_probe,
+ .ev_init = efx_ef10_ev_init,
+ .ev_fini = efx_ef10_ev_fini,
+ .ev_remove = efx_ef10_ev_remove,
+ .ev_process = efx_ef10_ev_process,
+ .ev_read_ack = efx_ef10_ev_read_ack,
+ .ev_test_generate = efx_ef10_ev_test_generate,
+ .filter_table_probe = efx_ef10_filter_table_probe,
+ .filter_table_restore = efx_ef10_filter_table_restore,
+ .filter_table_remove = efx_ef10_filter_table_remove,
+ .filter_update_rx_scatter = efx_ef10_filter_update_rx_scatter,
+ .filter_insert = efx_ef10_filter_insert,
+ .filter_remove_safe = efx_ef10_filter_remove_safe,
+ .filter_get_safe = efx_ef10_filter_get_safe,
+ .filter_clear_rx = efx_ef10_filter_clear_rx,
+ .filter_count_rx_used = efx_ef10_filter_count_rx_used,
+ .filter_get_rx_id_limit = efx_ef10_filter_get_rx_id_limit,
+ .filter_get_rx_ids = efx_ef10_filter_get_rx_ids,
+#ifdef CONFIG_RFS_ACCEL
+ .filter_rfs_insert = efx_ef10_filter_rfs_insert,
+ .filter_rfs_expire_one = efx_ef10_filter_rfs_expire_one,
+#endif
+#ifdef CONFIG_SFC_MTD
+ .mtd_probe = efx_ef10_mtd_probe,
+ .mtd_rename = efx_mcdi_mtd_rename,
+ .mtd_read = efx_mcdi_mtd_read,
+ .mtd_erase = efx_mcdi_mtd_erase,
+ .mtd_write = efx_mcdi_mtd_write,
+ .mtd_sync = efx_mcdi_mtd_sync,
+#endif
+ .ptp_write_host_time = efx_ef10_ptp_write_host_time,
+ .ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events,
+ .ptp_set_ts_config = efx_ef10_ptp_set_ts_config,
+
+ .revision = EFX_REV_HUNT_A0,
+ .max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH),
+ .rx_prefix_size = ES_DZ_RX_PREFIX_SIZE,
+ .rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST,
+ .rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST,
+ .can_rx_scatter = true,
+ .always_rx_scatter = true,
+ .max_interrupt_mode = EFX_INT_MODE_MSIX,
+ .timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
+ .offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_RXHASH | NETIF_F_NTUPLE),
+ .mcdi_max_ver = 2,
+ .max_rx_ip_filters = HUNT_FILTER_TBL_ROWS,
+ .hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE |
+ 1 << HWTSTAMP_FILTER_ALL,
+};
diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h
new file mode 100644
index 00000000000..62a55dde61d
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ef10_regs.h
@@ -0,0 +1,355 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2012-2013 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef EFX_EF10_REGS_H
+#define EFX_EF10_REGS_H
+
+/* EF10 hardware architecture definitions have a name prefix following
+ * the format:
+ *
+ * E<type>_<min-rev><max-rev>_
+ *
+ * The following <type> strings are used:
+ *
+ * MMIO register Host memory structure
+ * -------------------------------------------------------------
+ * Address R
+ * Bitfield RF SF
+ * Enumerator FE SE
+ *
+ * <min-rev> is the first revision to which the definition applies:
+ *
+ * D: Huntington A0
+ *
+ * If the definition has been changed or removed in later revisions
+ * then <max-rev> is the last revision to which the definition applies;
+ * otherwise it is "Z".
+ */
+
+/**************************************************************************
+ *
+ * EF10 registers and descriptors
+ *
+ **************************************************************************
+ */
+
+/* BIU_HW_REV_ID_REG: */
+#define ER_DZ_BIU_HW_REV_ID 0x00000000
+#define ERF_DZ_HW_REV_ID_LBN 0
+#define ERF_DZ_HW_REV_ID_WIDTH 32
+
+/* BIU_MC_SFT_STATUS_REG: */
+#define ER_DZ_BIU_MC_SFT_STATUS 0x00000010
+#define ER_DZ_BIU_MC_SFT_STATUS_STEP 4
+#define ER_DZ_BIU_MC_SFT_STATUS_ROWS 8
+#define ERF_DZ_MC_SFT_STATUS_LBN 0
+#define ERF_DZ_MC_SFT_STATUS_WIDTH 32
+
+/* BIU_INT_ISR_REG: */
+#define ER_DZ_BIU_INT_ISR 0x00000090
+#define ERF_DZ_ISR_REG_LBN 0
+#define ERF_DZ_ISR_REG_WIDTH 32
+
+/* MC_DB_LWRD_REG: */
+#define ER_DZ_MC_DB_LWRD 0x00000200
+#define ERF_DZ_MC_DOORBELL_L_LBN 0
+#define ERF_DZ_MC_DOORBELL_L_WIDTH 32
+
+/* MC_DB_HWRD_REG: */
+#define ER_DZ_MC_DB_HWRD 0x00000204
+#define ERF_DZ_MC_DOORBELL_H_LBN 0
+#define ERF_DZ_MC_DOORBELL_H_WIDTH 32
+
+/* EVQ_RPTR_REG: */
+#define ER_DZ_EVQ_RPTR 0x00000400
+#define ER_DZ_EVQ_RPTR_STEP 8192
+#define ER_DZ_EVQ_RPTR_ROWS 2048
+#define ERF_DZ_EVQ_RPTR_VLD_LBN 15
+#define ERF_DZ_EVQ_RPTR_VLD_WIDTH 1
+#define ERF_DZ_EVQ_RPTR_LBN 0
+#define ERF_DZ_EVQ_RPTR_WIDTH 15
+
+/* EVQ_TMR_REG: */
+#define ER_DZ_EVQ_TMR 0x00000420
+#define ER_DZ_EVQ_TMR_STEP 8192
+#define ER_DZ_EVQ_TMR_ROWS 2048
+#define ERF_DZ_TC_TIMER_MODE_LBN 14
+#define ERF_DZ_TC_TIMER_MODE_WIDTH 2
+#define ERF_DZ_TC_TIMER_VAL_LBN 0
+#define ERF_DZ_TC_TIMER_VAL_WIDTH 14
+
+/* RX_DESC_UPD_REG: */
+#define ER_DZ_RX_DESC_UPD 0x00000830
+#define ER_DZ_RX_DESC_UPD_STEP 8192
+#define ER_DZ_RX_DESC_UPD_ROWS 2048
+#define ERF_DZ_RX_DESC_WPTR_LBN 0
+#define ERF_DZ_RX_DESC_WPTR_WIDTH 12
+
+/* TX_DESC_UPD_REG: */
+#define ER_DZ_TX_DESC_UPD 0x00000a10
+#define ER_DZ_TX_DESC_UPD_STEP 8192
+#define ER_DZ_TX_DESC_UPD_ROWS 2048
+#define ERF_DZ_RSVD_LBN 76
+#define ERF_DZ_RSVD_WIDTH 20
+#define ERF_DZ_TX_DESC_WPTR_LBN 64
+#define ERF_DZ_TX_DESC_WPTR_WIDTH 12
+#define ERF_DZ_TX_DESC_HWORD_LBN 32
+#define ERF_DZ_TX_DESC_HWORD_WIDTH 32
+#define ERF_DZ_TX_DESC_LWORD_LBN 0
+#define ERF_DZ_TX_DESC_LWORD_WIDTH 32
+
+/* DRIVER_EV */
+#define ESF_DZ_DRV_CODE_LBN 60
+#define ESF_DZ_DRV_CODE_WIDTH 4
+#define ESF_DZ_DRV_SUB_CODE_LBN 56
+#define ESF_DZ_DRV_SUB_CODE_WIDTH 4
+#define ESE_DZ_DRV_TIMER_EV 3
+#define ESE_DZ_DRV_START_UP_EV 2
+#define ESE_DZ_DRV_WAKE_UP_EV 1
+#define ESF_DZ_DRV_SUB_DATA_LBN 0
+#define ESF_DZ_DRV_SUB_DATA_WIDTH 56
+#define ESF_DZ_DRV_EVQ_ID_LBN 0
+#define ESF_DZ_DRV_EVQ_ID_WIDTH 14
+#define ESF_DZ_DRV_TMR_ID_LBN 0
+#define ESF_DZ_DRV_TMR_ID_WIDTH 14
+
+/* EVENT_ENTRY */
+#define ESF_DZ_EV_CODE_LBN 60
+#define ESF_DZ_EV_CODE_WIDTH 4
+#define ESE_DZ_EV_CODE_MCDI_EV 12
+#define ESE_DZ_EV_CODE_DRIVER_EV 5
+#define ESE_DZ_EV_CODE_TX_EV 2
+#define ESE_DZ_EV_CODE_RX_EV 0
+#define ESE_DZ_OTHER other
+#define ESF_DZ_EV_DATA_LBN 0
+#define ESF_DZ_EV_DATA_WIDTH 60
+
+/* MC_EVENT */
+#define ESF_DZ_MC_CODE_LBN 60
+#define ESF_DZ_MC_CODE_WIDTH 4
+#define ESF_DZ_MC_OVERRIDE_HOLDOFF_LBN 59
+#define ESF_DZ_MC_OVERRIDE_HOLDOFF_WIDTH 1
+#define ESF_DZ_MC_DROP_EVENT_LBN 58
+#define ESF_DZ_MC_DROP_EVENT_WIDTH 1
+#define ESF_DZ_MC_SOFT_LBN 0
+#define ESF_DZ_MC_SOFT_WIDTH 58
+
+/* RX_EVENT */
+#define ESF_DZ_RX_CODE_LBN 60
+#define ESF_DZ_RX_CODE_WIDTH 4
+#define ESF_DZ_RX_OVERRIDE_HOLDOFF_LBN 59
+#define ESF_DZ_RX_OVERRIDE_HOLDOFF_WIDTH 1
+#define ESF_DZ_RX_DROP_EVENT_LBN 58
+#define ESF_DZ_RX_DROP_EVENT_WIDTH 1
+#define ESF_DZ_RX_EV_RSVD2_LBN 54
+#define ESF_DZ_RX_EV_RSVD2_WIDTH 4
+#define ESF_DZ_RX_EV_SOFT2_LBN 52
+#define ESF_DZ_RX_EV_SOFT2_WIDTH 2
+#define ESF_DZ_RX_DSC_PTR_LBITS_LBN 48
+#define ESF_DZ_RX_DSC_PTR_LBITS_WIDTH 4
+#define ESF_DZ_RX_L4_CLASS_LBN 45
+#define ESF_DZ_RX_L4_CLASS_WIDTH 3
+#define ESE_DZ_L4_CLASS_RSVD7 7
+#define ESE_DZ_L4_CLASS_RSVD6 6
+#define ESE_DZ_L4_CLASS_RSVD5 5
+#define ESE_DZ_L4_CLASS_RSVD4 4
+#define ESE_DZ_L4_CLASS_RSVD3 3
+#define ESE_DZ_L4_CLASS_UDP 2
+#define ESE_DZ_L4_CLASS_TCP 1
+#define ESE_DZ_L4_CLASS_UNKNOWN 0
+#define ESF_DZ_RX_L3_CLASS_LBN 42
+#define ESF_DZ_RX_L3_CLASS_WIDTH 3
+#define ESE_DZ_L3_CLASS_RSVD7 7
+#define ESE_DZ_L3_CLASS_IP6_FRAG 6
+#define ESE_DZ_L3_CLASS_ARP 5
+#define ESE_DZ_L3_CLASS_IP4_FRAG 4
+#define ESE_DZ_L3_CLASS_FCOE 3
+#define ESE_DZ_L3_CLASS_IP6 2
+#define ESE_DZ_L3_CLASS_IP4 1
+#define ESE_DZ_L3_CLASS_UNKNOWN 0
+#define ESF_DZ_RX_ETH_TAG_CLASS_LBN 39
+#define ESF_DZ_RX_ETH_TAG_CLASS_WIDTH 3
+#define ESE_DZ_ETH_TAG_CLASS_RSVD7 7
+#define ESE_DZ_ETH_TAG_CLASS_RSVD6 6
+#define ESE_DZ_ETH_TAG_CLASS_RSVD5 5
+#define ESE_DZ_ETH_TAG_CLASS_RSVD4 4
+#define ESE_DZ_ETH_TAG_CLASS_RSVD3 3
+#define ESE_DZ_ETH_TAG_CLASS_VLAN2 2
+#define ESE_DZ_ETH_TAG_CLASS_VLAN1 1
+#define ESE_DZ_ETH_TAG_CLASS_NONE 0
+#define ESF_DZ_RX_ETH_BASE_CLASS_LBN 36
+#define ESF_DZ_RX_ETH_BASE_CLASS_WIDTH 3
+#define ESE_DZ_ETH_BASE_CLASS_LLC_SNAP 2
+#define ESE_DZ_ETH_BASE_CLASS_LLC 1
+#define ESE_DZ_ETH_BASE_CLASS_ETH2 0
+#define ESF_DZ_RX_MAC_CLASS_LBN 35
+#define ESF_DZ_RX_MAC_CLASS_WIDTH 1
+#define ESE_DZ_MAC_CLASS_MCAST 1
+#define ESE_DZ_MAC_CLASS_UCAST 0
+#define ESF_DZ_RX_EV_SOFT1_LBN 32
+#define ESF_DZ_RX_EV_SOFT1_WIDTH 3
+#define ESF_DZ_RX_EV_RSVD1_LBN 31
+#define ESF_DZ_RX_EV_RSVD1_WIDTH 1
+#define ESF_DZ_RX_ABORT_LBN 30
+#define ESF_DZ_RX_ABORT_WIDTH 1
+#define ESF_DZ_RX_ECC_ERR_LBN 29
+#define ESF_DZ_RX_ECC_ERR_WIDTH 1
+#define ESF_DZ_RX_CRC1_ERR_LBN 28
+#define ESF_DZ_RX_CRC1_ERR_WIDTH 1
+#define ESF_DZ_RX_CRC0_ERR_LBN 27
+#define ESF_DZ_RX_CRC0_ERR_WIDTH 1
+#define ESF_DZ_RX_TCPUDP_CKSUM_ERR_LBN 26
+#define ESF_DZ_RX_TCPUDP_CKSUM_ERR_WIDTH 1
+#define ESF_DZ_RX_IPCKSUM_ERR_LBN 25
+#define ESF_DZ_RX_IPCKSUM_ERR_WIDTH 1
+#define ESF_DZ_RX_ECRC_ERR_LBN 24
+#define ESF_DZ_RX_ECRC_ERR_WIDTH 1
+#define ESF_DZ_RX_QLABEL_LBN 16
+#define ESF_DZ_RX_QLABEL_WIDTH 5
+#define ESF_DZ_RX_PARSE_INCOMPLETE_LBN 15
+#define ESF_DZ_RX_PARSE_INCOMPLETE_WIDTH 1
+#define ESF_DZ_RX_CONT_LBN 14
+#define ESF_DZ_RX_CONT_WIDTH 1
+#define ESF_DZ_RX_BYTES_LBN 0
+#define ESF_DZ_RX_BYTES_WIDTH 14
+
+/* RX_KER_DESC */
+#define ESF_DZ_RX_KER_RESERVED_LBN 62
+#define ESF_DZ_RX_KER_RESERVED_WIDTH 2
+#define ESF_DZ_RX_KER_BYTE_CNT_LBN 48
+#define ESF_DZ_RX_KER_BYTE_CNT_WIDTH 14
+#define ESF_DZ_RX_KER_BUF_ADDR_LBN 0
+#define ESF_DZ_RX_KER_BUF_ADDR_WIDTH 48
+
+/* TX_CSUM_TSTAMP_DESC */
+#define ESF_DZ_TX_DESC_IS_OPT_LBN 63
+#define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1
+#define ESF_DZ_TX_OPTION_TYPE_LBN 60
+#define ESF_DZ_TX_OPTION_TYPE_WIDTH 3
+#define ESE_DZ_TX_OPTION_DESC_TSO 7
+#define ESE_DZ_TX_OPTION_DESC_VLAN 6
+#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_TIMESTAMP_LBN 5
+#define ESF_DZ_TX_TIMESTAMP_WIDTH 1
+#define ESF_DZ_TX_OPTION_CRC_MODE_LBN 2
+#define ESF_DZ_TX_OPTION_CRC_MODE_WIDTH 3
+#define ESE_DZ_TX_OPTION_CRC_FCOIP_MPA 5
+#define ESE_DZ_TX_OPTION_CRC_FCOIP_FCOE 4
+#define ESE_DZ_TX_OPTION_CRC_ISCSI_HDR_AND_PYLD 3
+#define ESE_DZ_TX_OPTION_CRC_ISCSI_HDR 2
+#define ESE_DZ_TX_OPTION_CRC_FCOE 1
+#define ESE_DZ_TX_OPTION_CRC_OFF 0
+#define ESF_DZ_TX_OPTION_UDP_TCP_CSUM_LBN 1
+#define ESF_DZ_TX_OPTION_UDP_TCP_CSUM_WIDTH 1
+#define ESF_DZ_TX_OPTION_IP_CSUM_LBN 0
+#define ESF_DZ_TX_OPTION_IP_CSUM_WIDTH 1
+
+/* TX_EVENT */
+#define ESF_DZ_TX_CODE_LBN 60
+#define ESF_DZ_TX_CODE_WIDTH 4
+#define ESF_DZ_TX_OVERRIDE_HOLDOFF_LBN 59
+#define ESF_DZ_TX_OVERRIDE_HOLDOFF_WIDTH 1
+#define ESF_DZ_TX_DROP_EVENT_LBN 58
+#define ESF_DZ_TX_DROP_EVENT_WIDTH 1
+#define ESF_DZ_TX_EV_RSVD_LBN 48
+#define ESF_DZ_TX_EV_RSVD_WIDTH 10
+#define ESF_DZ_TX_SOFT2_LBN 32
+#define ESF_DZ_TX_SOFT2_WIDTH 16
+#define ESF_DZ_TX_CAN_MERGE_LBN 31
+#define ESF_DZ_TX_CAN_MERGE_WIDTH 1
+#define ESF_DZ_TX_SOFT1_LBN 24
+#define ESF_DZ_TX_SOFT1_WIDTH 7
+#define ESF_DZ_TX_QLABEL_LBN 16
+#define ESF_DZ_TX_QLABEL_WIDTH 5
+#define ESF_DZ_TX_DESCR_INDX_LBN 0
+#define ESF_DZ_TX_DESCR_INDX_WIDTH 16
+
+/* TX_KER_DESC */
+#define ESF_DZ_TX_KER_TYPE_LBN 63
+#define ESF_DZ_TX_KER_TYPE_WIDTH 1
+#define ESF_DZ_TX_KER_CONT_LBN 62
+#define ESF_DZ_TX_KER_CONT_WIDTH 1
+#define ESF_DZ_TX_KER_BYTE_CNT_LBN 48
+#define ESF_DZ_TX_KER_BYTE_CNT_WIDTH 14
+#define ESF_DZ_TX_KER_BUF_ADDR_LBN 0
+#define ESF_DZ_TX_KER_BUF_ADDR_WIDTH 48
+
+/* TX_PIO_DESC */
+#define ESF_DZ_TX_PIO_TYPE_LBN 63
+#define ESF_DZ_TX_PIO_TYPE_WIDTH 1
+#define ESF_DZ_TX_PIO_OPT_LBN 60
+#define ESF_DZ_TX_PIO_OPT_WIDTH 3
+#define ESE_DZ_TX_OPTION_DESC_PIO 1
+#define ESF_DZ_TX_PIO_CONT_LBN 59
+#define ESF_DZ_TX_PIO_CONT_WIDTH 1
+#define ESF_DZ_TX_PIO_BYTE_CNT_LBN 32
+#define ESF_DZ_TX_PIO_BYTE_CNT_WIDTH 12
+#define ESF_DZ_TX_PIO_BUF_ADDR_LBN 0
+#define ESF_DZ_TX_PIO_BUF_ADDR_WIDTH 12
+
+/* TX_TSO_DESC */
+#define ESF_DZ_TX_DESC_IS_OPT_LBN 63
+#define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1
+#define ESF_DZ_TX_OPTION_TYPE_LBN 60
+#define ESF_DZ_TX_OPTION_TYPE_WIDTH 3
+#define ESE_DZ_TX_OPTION_DESC_TSO 7
+#define ESE_DZ_TX_OPTION_DESC_VLAN 6
+#define ESE_DZ_TX_OPTION_DESC_CRC_CSUM 0
+#define ESF_DZ_TX_TSO_TCP_FLAGS_LBN 48
+#define ESF_DZ_TX_TSO_TCP_FLAGS_WIDTH 8
+#define ESF_DZ_TX_TSO_IP_ID_LBN 32
+#define ESF_DZ_TX_TSO_IP_ID_WIDTH 16
+#define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0
+#define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32
+
+/*************************************************************************/
+
+/* TX_DESC_UPD_REG: Transmit descriptor update register.
+ * We may write just one dword of these registers.
+ */
+#define ER_DZ_TX_DESC_UPD_DWORD (ER_DZ_TX_DESC_UPD + 2 * 4)
+#define ERF_DZ_TX_DESC_WPTR_DWORD_LBN (ERF_DZ_TX_DESC_WPTR_LBN - 2 * 32)
+#define ERF_DZ_TX_DESC_WPTR_DWORD_WIDTH ERF_DZ_TX_DESC_WPTR_WIDTH
+
+/* The workaround for bug 35388 requires multiplexing writes through
+ * the TX_DESC_UPD_DWORD address.
+ * TX_DESC_UPD: 0ppppppppppp (bit 11 lost)
+ * EVQ_RPTR: 1000hhhhhhhh, 1001llllllll (split into high and low bits)
+ * EVQ_TMR: 11mmvvvvvvvv (bits 8:13 of value lost)
+ */
+#define ER_DD_EVQ_INDIRECT ER_DZ_TX_DESC_UPD_DWORD
+#define ERF_DD_EVQ_IND_RPTR_FLAGS_LBN 8
+#define ERF_DD_EVQ_IND_RPTR_FLAGS_WIDTH 4
+#define EFE_DD_EVQ_IND_RPTR_FLAGS_HIGH 8
+#define EFE_DD_EVQ_IND_RPTR_FLAGS_LOW 9
+#define ERF_DD_EVQ_IND_RPTR_LBN 0
+#define ERF_DD_EVQ_IND_RPTR_WIDTH 8
+#define ERF_DD_EVQ_IND_TIMER_FLAGS_LBN 10
+#define ERF_DD_EVQ_IND_TIMER_FLAGS_WIDTH 2
+#define EFE_DD_EVQ_IND_TIMER_FLAGS 3
+#define ERF_DD_EVQ_IND_TIMER_MODE_LBN 8
+#define ERF_DD_EVQ_IND_TIMER_MODE_WIDTH 2
+#define ERF_DD_EVQ_IND_TIMER_VAL_LBN 0
+#define ERF_DD_EVQ_IND_TIMER_VAL_WIDTH 8
+
+/* TX_PIOBUF
+ * PIO buffer aperture (paged)
+ */
+#define ER_DZ_TX_PIOBUF 4096
+#define ER_DZ_TX_PIOBUF_SIZE 2048
+
+/* RX packet prefix */
+#define ES_DZ_RX_PREFIX_HASH_OFST 0
+#define ES_DZ_RX_PREFIX_VLAN1_OFST 4
+#define ES_DZ_RX_PREFIX_VLAN2_OFST 6
+#define ES_DZ_RX_PREFIX_PKTLEN_OFST 8
+#define ES_DZ_RX_PREFIX_TSTAMP_OFST 10
+#define ES_DZ_RX_PREFIX_SIZE 14
+
+#endif /* EFX_EF10_REGS_H */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index e43702f33b6..1e274045970 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2005-2011 Solarflare Communications Inc.
+ * Copyright 2005-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -17,14 +17,15 @@
#include <linux/ip.h>
#include <linux/tcp.h>
#include <linux/in.h>
-#include <linux/crc32.h>
#include <linux/ethtool.h>
#include <linux/topology.h>
#include <linux/gfp.h>
-#include <linux/cpu_rmap.h>
+#include <linux/aer.h>
+#include <linux/interrupt.h>
#include "net_driver.h"
#include "efx.h"
#include "nic.h"
+#include "selftest.h"
#include "mcdi.h"
#include "workarounds.h"
@@ -38,15 +39,15 @@
/* Loopback mode names (see LOOPBACK_MODE()) */
const unsigned int efx_loopback_mode_max = LOOPBACK_MAX;
-const char *efx_loopback_mode_names[] = {
+const char *const efx_loopback_mode_names[] = {
[LOOPBACK_NONE] = "NONE",
[LOOPBACK_DATA] = "DATAPATH",
[LOOPBACK_GMAC] = "GMAC",
[LOOPBACK_XGMII] = "XGMII",
[LOOPBACK_XGXS] = "XGXS",
- [LOOPBACK_XAUI] = "XAUI",
- [LOOPBACK_GMII] = "GMII",
- [LOOPBACK_SGMII] = "SGMII",
+ [LOOPBACK_XAUI] = "XAUI",
+ [LOOPBACK_GMII] = "GMII",
+ [LOOPBACK_SGMII] = "SGMII",
[LOOPBACK_XGBR] = "XGBR",
[LOOPBACK_XFI] = "XFI",
[LOOPBACK_XAUI_FAR] = "XAUI_FAR",
@@ -55,42 +56,49 @@ const char *efx_loopback_mode_names[] = {
[LOOPBACK_XFI_FAR] = "XFI_FAR",
[LOOPBACK_GPHY] = "GPHY",
[LOOPBACK_PHYXS] = "PHYXS",
- [LOOPBACK_PCS] = "PCS",
- [LOOPBACK_PMAPMD] = "PMA/PMD",
+ [LOOPBACK_PCS] = "PCS",
+ [LOOPBACK_PMAPMD] = "PMA/PMD",
[LOOPBACK_XPORT] = "XPORT",
[LOOPBACK_XGMII_WS] = "XGMII_WS",
- [LOOPBACK_XAUI_WS] = "XAUI_WS",
+ [LOOPBACK_XAUI_WS] = "XAUI_WS",
[LOOPBACK_XAUI_WS_FAR] = "XAUI_WS_FAR",
[LOOPBACK_XAUI_WS_NEAR] = "XAUI_WS_NEAR",
- [LOOPBACK_GMII_WS] = "GMII_WS",
+ [LOOPBACK_GMII_WS] = "GMII_WS",
[LOOPBACK_XFI_WS] = "XFI_WS",
[LOOPBACK_XFI_WS_FAR] = "XFI_WS_FAR",
- [LOOPBACK_PHYXS_WS] = "PHYXS_WS",
+ [LOOPBACK_PHYXS_WS] = "PHYXS_WS",
};
const unsigned int efx_reset_type_max = RESET_TYPE_MAX;
-const char *efx_reset_type_names[] = {
- [RESET_TYPE_INVISIBLE] = "INVISIBLE",
- [RESET_TYPE_ALL] = "ALL",
- [RESET_TYPE_WORLD] = "WORLD",
- [RESET_TYPE_DISABLE] = "DISABLE",
- [RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG",
- [RESET_TYPE_INT_ERROR] = "INT_ERROR",
- [RESET_TYPE_RX_RECOVERY] = "RX_RECOVERY",
- [RESET_TYPE_RX_DESC_FETCH] = "RX_DESC_FETCH",
- [RESET_TYPE_TX_DESC_FETCH] = "TX_DESC_FETCH",
- [RESET_TYPE_TX_SKIP] = "TX_SKIP",
- [RESET_TYPE_MC_FAILURE] = "MC_FAILURE",
+const char *const efx_reset_type_names[] = {
+ [RESET_TYPE_INVISIBLE] = "INVISIBLE",
+ [RESET_TYPE_ALL] = "ALL",
+ [RESET_TYPE_RECOVER_OR_ALL] = "RECOVER_OR_ALL",
+ [RESET_TYPE_WORLD] = "WORLD",
+ [RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE",
+ [RESET_TYPE_MC_BIST] = "MC_BIST",
+ [RESET_TYPE_DISABLE] = "DISABLE",
+ [RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG",
+ [RESET_TYPE_INT_ERROR] = "INT_ERROR",
+ [RESET_TYPE_RX_RECOVERY] = "RX_RECOVERY",
+ [RESET_TYPE_DMA_ERROR] = "DMA_ERROR",
+ [RESET_TYPE_TX_SKIP] = "TX_SKIP",
+ [RESET_TYPE_MC_FAILURE] = "MC_FAILURE",
+ [RESET_TYPE_MCDI_TIMEOUT] = "MCDI_TIMEOUT (FLR)",
};
-#define EFX_MAX_MTU (9 * 1024)
-
/* Reset workqueue. If any NIC has a hardware failure then a reset will be
* queued onto this work queue. This is not a per-nic work queue, because
* efx_reset_work() acquires the rtnl lock, so resets are naturally serialised.
*/
static struct workqueue_struct *reset_workqueue;
+/* How often and how many times to poll for a reset while waiting for a
+ * BIST that another function started to complete.
+ */
+#define BIST_WAIT_DELAY_MS 100
+#define BIST_WAIT_DELAY_COUNT 100
+
/**************************************************************************
*
* Configurable values
@@ -105,8 +113,8 @@ static struct workqueue_struct *reset_workqueue;
*
* This is only used in MSI-X interrupt mode
*/
-static unsigned int separate_tx_channels;
-module_param(separate_tx_channels, uint, 0444);
+static bool separate_tx_channels;
+module_param(separate_tx_channels, bool, 0444);
MODULE_PARM_DESC(separate_tx_channels,
"Use separate channels for TX and RX");
@@ -116,21 +124,15 @@ MODULE_PARM_DESC(separate_tx_channels,
static int napi_weight = 64;
/* This is the time (in jiffies) between invocations of the hardware
- * monitor. On Falcon-based NICs, this will:
+ * monitor.
+ * On Falcon-based NICs, this will:
* - Check the on-board hardware monitor;
* - Poll the link state and reconfigure the hardware as necessary.
+ * On Siena-based NICs for power systems with EEH support, this will give EEH a
+ * chance to start.
*/
static unsigned int efx_monitor_interval = 1 * HZ;
-/* This controls whether or not the driver will initialise devices
- * with invalid MAC addresses stored in the EEPROM or flash. If true,
- * such devices will be initialised with a random locally-generated
- * MAC address. This allows for loading the sfc_mtd driver to
- * reprogram the flash, even if the flash contents (including the MAC
- * address) have previously been erased.
- */
-static unsigned int allow_bad_hwaddr;
-
/* Initial interrupt moderation settings. They can be modified after
* module load with ethtool.
*
@@ -162,22 +164,22 @@ static unsigned int interrupt_mode;
* interrupt handling.
*
* Cards without MSI-X will only target one CPU via legacy or MSI interrupt.
- * The default (0) means to assign an interrupt to each package (level II cache)
+ * The default (0) means to assign an interrupt to each core.
*/
static unsigned int rss_cpus;
module_param(rss_cpus, uint, 0444);
MODULE_PARM_DESC(rss_cpus, "Number of CPUs to use for Receive-Side Scaling");
-static int phy_flash_cfg;
-module_param(phy_flash_cfg, int, 0644);
+static bool phy_flash_cfg;
+module_param(phy_flash_cfg, bool, 0644);
MODULE_PARM_DESC(phy_flash_cfg, "Set PHYs into reflash mode initially");
-static unsigned irq_adapt_low_thresh = 10000;
+static unsigned irq_adapt_low_thresh = 8000;
module_param(irq_adapt_low_thresh, uint, 0644);
MODULE_PARM_DESC(irq_adapt_low_thresh,
"Threshold score for reducing IRQ moderation");
-static unsigned irq_adapt_high_thresh = 20000;
+static unsigned irq_adapt_high_thresh = 16000;
module_param(irq_adapt_high_thresh, uint, 0644);
MODULE_PARM_DESC(irq_adapt_high_thresh,
"Threshold score for increasing IRQ moderation");
@@ -195,9 +197,13 @@ MODULE_PARM_DESC(debug, "Bitmapped debugging message enable value");
*
*************************************************************************/
+static int efx_soft_enable_interrupts(struct efx_nic *efx);
+static void efx_soft_disable_interrupts(struct efx_nic *efx);
+static void efx_remove_channel(struct efx_channel *channel);
static void efx_remove_channels(struct efx_nic *efx);
+static const struct efx_channel_type efx_default_channel_type;
static void efx_remove_port(struct efx_nic *efx);
-static void efx_init_napi(struct efx_nic *efx);
+static void efx_init_napi_channel(struct efx_channel *channel);
static void efx_fini_napi(struct efx_nic *efx);
static void efx_fini_napi_channel(struct efx_channel *channel);
static void efx_fini_struct(struct efx_nic *efx);
@@ -206,11 +212,22 @@ static void efx_stop_all(struct efx_nic *efx);
#define EFX_ASSERT_RESET_SERIALISED(efx) \
do { \
- if ((efx->state == STATE_RUNNING) || \
+ if ((efx->state == STATE_READY) || \
+ (efx->state == STATE_RECOVERY) || \
(efx->state == STATE_DISABLED)) \
ASSERT_RTNL(); \
} while (0)
+static int efx_check_disabled(struct efx_nic *efx)
+{
+ if (efx->state == STATE_DISABLED || efx->state == STATE_RECOVERY) {
+ netif_err(efx, drv, efx->net_dev,
+ "device is disabled due to earlier errors\n");
+ return -EIO;
+ }
+ return 0;
+}
+
/**************************************************************************
*
* Event queue processing
@@ -226,47 +243,23 @@ static void efx_stop_all(struct efx_nic *efx);
*/
static int efx_process_channel(struct efx_channel *channel, int budget)
{
- struct efx_nic *efx = channel->efx;
int spent;
- if (unlikely(efx->reset_pending || !channel->enabled))
+ if (unlikely(!channel->enabled))
return 0;
spent = efx_nic_process_eventq(channel, budget);
- if (spent == 0)
- return 0;
+ if (spent && efx_channel_has_rx_queue(channel)) {
+ struct efx_rx_queue *rx_queue =
+ efx_channel_get_rx_queue(channel);
- /* Deliver last RX packet. */
- if (channel->rx_pkt) {
- __efx_rx_packet(channel, channel->rx_pkt,
- channel->rx_pkt_csummed);
- channel->rx_pkt = NULL;
+ efx_rx_flush_packet(channel);
+ efx_fast_push_rx_descriptors(rx_queue, true);
}
- efx_rx_strategy(channel);
-
- efx_fast_push_rx_descriptors(efx_channel_get_rx_queue(channel));
-
return spent;
}
-/* Mark channel as finished processing
- *
- * Note that since we will not receive further interrupts for this
- * channel before we finish processing and call the eventq_read_ack()
- * method, there is no need to use the interrupt hold-off timers.
- */
-static inline void efx_channel_processed(struct efx_channel *channel)
-{
- /* The interrupt handler for this channel may set work_pending
- * as soon as we acknowledge the events we've seen. Make sure
- * it's cleared before then. */
- channel->work_pending = false;
- smp_wmb();
-
- efx_nic_eventq_read_ack(channel);
-}
-
/* NAPI poll handler
*
* NAPI guarantees serialisation of polls of the same device, which
@@ -286,7 +279,7 @@ static int efx_poll(struct napi_struct *napi, int budget)
spent = efx_process_channel(channel, budget);
if (spent < budget) {
- if (channel->channel < efx->n_rx_channels &&
+ if (efx_channel_has_rx_queue(channel) &&
efx->irq_rx_adaptive &&
unlikely(++channel->irq_count == 1000)) {
if (unlikely(channel->irq_mod_score <
@@ -311,58 +304,16 @@ static int efx_poll(struct napi_struct *napi, int budget)
/* There is no race here; although napi_disable() will
* only wait for napi_complete(), this isn't a problem
- * since efx_channel_processed() will have no effect if
+ * since efx_nic_eventq_read_ack() will have no effect if
* interrupts have already been disabled.
*/
napi_complete(napi);
- efx_channel_processed(channel);
+ efx_nic_eventq_read_ack(channel);
}
return spent;
}
-/* Process the eventq of the specified channel immediately on this CPU
- *
- * Disable hardware generated interrupts, wait for any existing
- * processing to finish, then directly poll (and ack ) the eventq.
- * Finally reenable NAPI and interrupts.
- *
- * This is for use only during a loopback self-test. It must not
- * deliver any packets up the stack as this can result in deadlock.
- */
-void efx_process_channel_now(struct efx_channel *channel)
-{
- struct efx_nic *efx = channel->efx;
-
- BUG_ON(channel->channel >= efx->n_channels);
- BUG_ON(!channel->enabled);
- BUG_ON(!efx->loopback_selftest);
-
- /* Disable interrupts and wait for ISRs to complete */
- efx_nic_disable_interrupts(efx);
- if (efx->legacy_irq) {
- synchronize_irq(efx->legacy_irq);
- efx->legacy_irq_enabled = false;
- }
- if (channel->irq)
- synchronize_irq(channel->irq);
-
- /* Wait for any NAPI processing to complete */
- napi_disable(&channel->napi_str);
-
- /* Poll the channel */
- efx_process_channel(channel, channel->eventq_mask + 1);
-
- /* Ack the eventq. This may cause an interrupt to be generated
- * when they are reenabled */
- efx_channel_processed(channel);
-
- napi_enable(&channel->napi_str);
- if (efx->legacy_irq)
- efx->legacy_irq_enabled = true;
- efx_nic_enable_interrupts(efx);
-}
-
/* Create event queue
* Event queue memory allocations are done only once. If the channel
* is reset, the memory buffer will be reused; this guards against
@@ -373,7 +324,7 @@ static int efx_probe_eventq(struct efx_channel *channel)
struct efx_nic *efx = channel->efx;
unsigned long entries;
- netif_dbg(channel->efx, probe, channel->efx->net_dev,
+ netif_dbg(efx, probe, efx->net_dev,
"chan %d create event queue\n", channel->channel);
/* Build an event queue with room for one event per tx and rx buffer,
@@ -386,22 +337,59 @@ static int efx_probe_eventq(struct efx_channel *channel)
}
/* Prepare channel's event queue */
-static void efx_init_eventq(struct efx_channel *channel)
+static int efx_init_eventq(struct efx_channel *channel)
{
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
+ struct efx_nic *efx = channel->efx;
+ int rc;
+
+ EFX_WARN_ON_PARANOID(channel->eventq_init);
+
+ netif_dbg(efx, drv, efx->net_dev,
"chan %d init event queue\n", channel->channel);
- channel->eventq_read_ptr = 0;
+ rc = efx_nic_init_eventq(channel);
+ if (rc == 0) {
+ efx->type->push_irq_moderation(channel);
+ channel->eventq_read_ptr = 0;
+ channel->eventq_init = true;
+ }
+ return rc;
+}
+
+/* Enable event queue processing and NAPI */
+static void efx_start_eventq(struct efx_channel *channel)
+{
+ netif_dbg(channel->efx, ifup, channel->efx->net_dev,
+ "chan %d start event queue\n", channel->channel);
+
+ /* Make sure the NAPI handler sees the enabled flag set */
+ channel->enabled = true;
+ smp_wmb();
+
+ napi_enable(&channel->napi_str);
+ efx_nic_eventq_read_ack(channel);
+}
+
+/* Disable event queue processing and NAPI */
+static void efx_stop_eventq(struct efx_channel *channel)
+{
+ if (!channel->enabled)
+ return;
- efx_nic_init_eventq(channel);
+ napi_disable(&channel->napi_str);
+ channel->enabled = false;
}
static void efx_fini_eventq(struct efx_channel *channel)
{
+ if (!channel->eventq_init)
+ return;
+
netif_dbg(channel->efx, drv, channel->efx->net_dev,
"chan %d fini event queue\n", channel->channel);
efx_nic_fini_eventq(channel);
+ channel->eventq_init = false;
}
static void efx_remove_eventq(struct efx_channel *channel)
@@ -418,8 +406,7 @@ static void efx_remove_eventq(struct efx_channel *channel)
*
*************************************************************************/
-/* Allocate and initialise a channel structure, optionally copying
- * parameters (but not resources) from an old channel structure. */
+/* Allocate and initialise a channel structure. */
static struct efx_channel *
efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
{
@@ -428,45 +415,60 @@ efx_alloc_channel(struct efx_nic *efx, int i, struct efx_channel *old_channel)
struct efx_tx_queue *tx_queue;
int j;
- if (old_channel) {
- channel = kmalloc(sizeof(*channel), GFP_KERNEL);
- if (!channel)
- return NULL;
+ channel = kzalloc(sizeof(*channel), GFP_KERNEL);
+ if (!channel)
+ return NULL;
+
+ channel->efx = efx;
+ channel->channel = i;
+ channel->type = &efx_default_channel_type;
+
+ for (j = 0; j < EFX_TXQ_TYPES; j++) {
+ tx_queue = &channel->tx_queue[j];
+ tx_queue->efx = efx;
+ tx_queue->queue = i * EFX_TXQ_TYPES + j;
+ tx_queue->channel = channel;
+ }
+
+ rx_queue = &channel->rx_queue;
+ rx_queue->efx = efx;
+ setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
+ (unsigned long)rx_queue);
- *channel = *old_channel;
+ return channel;
+}
- channel->napi_dev = NULL;
- memset(&channel->eventq, 0, sizeof(channel->eventq));
+/* Allocate and initialise a channel structure, copying parameters
+ * (but not resources) from an old channel structure.
+ */
+static struct efx_channel *
+efx_copy_channel(const struct efx_channel *old_channel)
+{
+ struct efx_channel *channel;
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+ int j;
- rx_queue = &channel->rx_queue;
- rx_queue->buffer = NULL;
- memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
+ channel = kmalloc(sizeof(*channel), GFP_KERNEL);
+ if (!channel)
+ return NULL;
- for (j = 0; j < EFX_TXQ_TYPES; j++) {
- tx_queue = &channel->tx_queue[j];
- if (tx_queue->channel)
- tx_queue->channel = channel;
- tx_queue->buffer = NULL;
- memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
- }
- } else {
- channel = kzalloc(sizeof(*channel), GFP_KERNEL);
- if (!channel)
- return NULL;
+ *channel = *old_channel;
- channel->efx = efx;
- channel->channel = i;
+ channel->napi_dev = NULL;
+ memset(&channel->eventq, 0, sizeof(channel->eventq));
- for (j = 0; j < EFX_TXQ_TYPES; j++) {
- tx_queue = &channel->tx_queue[j];
- tx_queue->efx = efx;
- tx_queue->queue = i * EFX_TXQ_TYPES + j;
+ for (j = 0; j < EFX_TXQ_TYPES; j++) {
+ tx_queue = &channel->tx_queue[j];
+ if (tx_queue->channel)
tx_queue->channel = channel;
- }
+ tx_queue->buffer = NULL;
+ memset(&tx_queue->txd, 0, sizeof(tx_queue->txd));
}
rx_queue = &channel->rx_queue;
- rx_queue->efx = efx;
+ rx_queue->buffer = NULL;
+ memset(&rx_queue->rxd, 0, sizeof(rx_queue->rxd));
setup_timer(&rx_queue->slow_fill, efx_rx_slow_fill,
(unsigned long)rx_queue);
@@ -482,57 +484,60 @@ static int efx_probe_channel(struct efx_channel *channel)
netif_dbg(channel->efx, probe, channel->efx->net_dev,
"creating channel %d\n", channel->channel);
+ rc = channel->type->pre_probe(channel);
+ if (rc)
+ goto fail;
+
rc = efx_probe_eventq(channel);
if (rc)
- goto fail1;
+ goto fail;
efx_for_each_channel_tx_queue(tx_queue, channel) {
rc = efx_probe_tx_queue(tx_queue);
if (rc)
- goto fail2;
+ goto fail;
}
efx_for_each_channel_rx_queue(rx_queue, channel) {
rc = efx_probe_rx_queue(rx_queue);
if (rc)
- goto fail3;
+ goto fail;
}
- channel->n_rx_frm_trunc = 0;
-
return 0;
- fail3:
- efx_for_each_channel_rx_queue(rx_queue, channel)
- efx_remove_rx_queue(rx_queue);
- fail2:
- efx_for_each_channel_tx_queue(tx_queue, channel)
- efx_remove_tx_queue(tx_queue);
- fail1:
+fail:
+ efx_remove_channel(channel);
return rc;
}
+static void
+efx_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
+{
+ struct efx_nic *efx = channel->efx;
+ const char *type;
+ int number;
+
+ number = channel->channel;
+ if (efx->tx_channel_offset == 0) {
+ type = "";
+ } else if (channel->channel < efx->tx_channel_offset) {
+ type = "-rx";
+ } else {
+ type = "-tx";
+ number -= efx->tx_channel_offset;
+ }
+ snprintf(buf, len, "%s%s-%d", efx->name, type, number);
+}
static void efx_set_channel_names(struct efx_nic *efx)
{
struct efx_channel *channel;
- const char *type = "";
- int number;
- efx_for_each_channel(channel, efx) {
- number = channel->channel;
- if (efx->n_channels > efx->n_rx_channels) {
- if (channel->channel < efx->n_rx_channels) {
- type = "-rx";
- } else {
- type = "-tx";
- number -= efx->n_rx_channels;
- }
- }
- snprintf(efx->channel_name[channel->channel],
- sizeof(efx->channel_name[0]),
- "%s%s-%d", efx->name, type, number);
- }
+ efx_for_each_channel(channel, efx)
+ channel->type->get_name(channel,
+ efx->msi_context[channel->channel].name,
+ sizeof(efx->msi_context[0].name));
}
static int efx_probe_channels(struct efx_nic *efx)
@@ -543,7 +548,12 @@ static int efx_probe_channels(struct efx_nic *efx)
/* Restart special buffer allocation */
efx->next_buffer_table = 0;
- efx_for_each_channel(channel, efx) {
+ /* Probe channels in reverse, so that any 'extra' channels
+ * use the start of the buffer table. This allows the traffic
+ * channels to be resized without moving them or wasting the
+ * entries before them.
+ */
+ efx_for_each_channel_rev(channel, efx) {
rc = efx_probe_channel(channel);
if (rc) {
netif_err(efx, probe, efx->net_dev,
@@ -565,87 +575,91 @@ fail:
* to propagate configuration changes (mtu, checksum offload), or
* to clear hardware error conditions
*/
-static void efx_init_channels(struct efx_nic *efx)
+static void efx_start_datapath(struct efx_nic *efx)
{
+ bool old_rx_scatter = efx->rx_scatter;
struct efx_tx_queue *tx_queue;
struct efx_rx_queue *rx_queue;
struct efx_channel *channel;
+ size_t rx_buf_len;
/* Calculate the rx buffer allocation parameters required to
* support the current MTU, including padding for header
* alignment and overruns.
*/
- efx->rx_buffer_len = (max(EFX_PAGE_IP_ALIGN, NET_IP_ALIGN) +
- EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
- efx->type->rx_buffer_hash_size +
- efx->type->rx_buffer_padding);
- efx->rx_buffer_order = get_order(efx->rx_buffer_len +
- sizeof(struct efx_rx_page_state));
+ efx->rx_dma_len = (efx->rx_prefix_size +
+ EFX_MAX_FRAME_LEN(efx->net_dev->mtu) +
+ efx->type->rx_buffer_padding);
+ rx_buf_len = (sizeof(struct efx_rx_page_state) +
+ efx->rx_ip_align + efx->rx_dma_len);
+ if (rx_buf_len <= PAGE_SIZE) {
+ efx->rx_scatter = efx->type->always_rx_scatter;
+ efx->rx_buffer_order = 0;
+ } else if (efx->type->can_rx_scatter) {
+ BUILD_BUG_ON(EFX_RX_USR_BUF_SIZE % L1_CACHE_BYTES);
+ BUILD_BUG_ON(sizeof(struct efx_rx_page_state) +
+ 2 * ALIGN(NET_IP_ALIGN + EFX_RX_USR_BUF_SIZE,
+ EFX_RX_BUF_ALIGNMENT) >
+ PAGE_SIZE);
+ efx->rx_scatter = true;
+ efx->rx_dma_len = EFX_RX_USR_BUF_SIZE;
+ efx->rx_buffer_order = 0;
+ } else {
+ efx->rx_scatter = false;
+ efx->rx_buffer_order = get_order(rx_buf_len);
+ }
+
+ efx_rx_config_page_split(efx);
+ if (efx->rx_buffer_order)
+ netif_dbg(efx, drv, efx->net_dev,
+ "RX buf len=%u; page order=%u batch=%u\n",
+ efx->rx_dma_len, efx->rx_buffer_order,
+ efx->rx_pages_per_batch);
+ else
+ netif_dbg(efx, drv, efx->net_dev,
+ "RX buf len=%u step=%u bpp=%u; page batch=%u\n",
+ efx->rx_dma_len, efx->rx_page_buf_step,
+ efx->rx_bufs_per_page, efx->rx_pages_per_batch);
+
+ /* RX filters may also have scatter-enabled flags */
+ if (efx->rx_scatter != old_rx_scatter)
+ efx->type->filter_update_rx_scatter(efx);
+
+ /* We must keep at least one descriptor in a TX ring empty.
+ * We could avoid this when the queue size does not exactly
+ * match the hardware ring size, but it's not that important.
+ * Therefore we stop the queue when one more skb might fill
+ * the ring completely. We wake it when half way back to
+ * empty.
+ */
+ efx->txq_stop_thresh = efx->txq_entries - efx_tx_max_skb_descs(efx);
+ efx->txq_wake_thresh = efx->txq_stop_thresh / 2;
/* Initialise the channels */
efx_for_each_channel(channel, efx) {
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
- "init chan %d\n", channel->channel);
-
- efx_init_eventq(channel);
-
- efx_for_each_channel_tx_queue(tx_queue, channel)
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
efx_init_tx_queue(tx_queue);
+ atomic_inc(&efx->active_queues);
+ }
- /* The rx buffer allocation strategy is MTU dependent */
- efx_rx_strategy(channel);
-
- efx_for_each_channel_rx_queue(rx_queue, channel)
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
efx_init_rx_queue(rx_queue);
+ atomic_inc(&efx->active_queues);
+ efx_stop_eventq(channel);
+ efx_fast_push_rx_descriptors(rx_queue, false);
+ efx_start_eventq(channel);
+ }
- WARN_ON(channel->rx_pkt != NULL);
- efx_rx_strategy(channel);
+ WARN_ON(channel->rx_pkt_n_frags);
}
-}
-/* This enables event queue processing and packet transmission.
- *
- * Note that this function is not allowed to fail, since that would
- * introduce too much complexity into the suspend/resume path.
- */
-static void efx_start_channel(struct efx_channel *channel)
-{
- struct efx_rx_queue *rx_queue;
-
- netif_dbg(channel->efx, ifup, channel->efx->net_dev,
- "starting chan %d\n", channel->channel);
+ efx_ptp_start_datapath(efx);
- /* The interrupt handler for this channel may set work_pending
- * as soon as we enable it. Make sure it's cleared before
- * then. Similarly, make sure it sees the enabled flag set. */
- channel->work_pending = false;
- channel->enabled = true;
- smp_wmb();
-
- /* Fill the queues before enabling NAPI */
- efx_for_each_channel_rx_queue(rx_queue, channel)
- efx_fast_push_rx_descriptors(rx_queue);
-
- napi_enable(&channel->napi_str);
-}
-
-/* This disables event queue processing and packet transmission.
- * This function does not guarantee that all queue processing
- * (e.g. RX refill) is complete.
- */
-static void efx_stop_channel(struct efx_channel *channel)
-{
- if (!channel->enabled)
- return;
-
- netif_dbg(channel->efx, ifdown, channel->efx->net_dev,
- "stop chan %d\n", channel->channel);
-
- channel->enabled = false;
- napi_disable(&channel->napi_str);
+ if (netif_device_present(efx->net_dev))
+ netif_tx_wake_all_queues(efx->net_dev);
}
-static void efx_fini_channels(struct efx_nic *efx)
+static void efx_stop_datapath(struct efx_nic *efx)
{
struct efx_channel *channel;
struct efx_tx_queue *tx_queue;
@@ -655,12 +669,34 @@ static void efx_fini_channels(struct efx_nic *efx)
EFX_ASSERT_RESET_SERIALISED(efx);
BUG_ON(efx->port_enabled);
- rc = efx_nic_flush_queues(efx);
+ efx_ptp_stop_datapath(efx);
+
+ /* Stop RX refill */
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ rx_queue->refill_enabled = false;
+ }
+
+ efx_for_each_channel(channel, efx) {
+ /* RX packet processing is pipelined, so wait for the
+ * NAPI handler to complete. At least event queue 0
+ * might be kept active by non-data events, so don't
+ * use napi_synchronize() but actually disable NAPI
+ * temporarily.
+ */
+ if (efx_channel_has_rx_queue(channel)) {
+ efx_stop_eventq(channel);
+ efx_start_eventq(channel);
+ }
+ }
+
+ rc = efx->type->fini_dmaq(efx);
if (rc && EFX_WORKAROUND_7803(efx)) {
/* Schedule a reset to recover from the flush failure. The
* descriptor caches reference memory we're about to free,
* but falcon_reconfigure_mac_wrapper() won't reconnect
- * the MACs because of the pending reset. */
+ * the MACs because of the pending reset.
+ */
netif_err(efx, drv, efx->net_dev,
"Resetting to recover from flush failure\n");
efx_schedule_reset(efx, RESET_TYPE_ALL);
@@ -672,14 +708,10 @@ static void efx_fini_channels(struct efx_nic *efx)
}
efx_for_each_channel(channel, efx) {
- netif_dbg(channel->efx, drv, channel->efx->net_dev,
- "shut down chan %d\n", channel->channel);
-
efx_for_each_channel_rx_queue(rx_queue, channel)
efx_fini_rx_queue(rx_queue);
efx_for_each_possible_channel_tx_queue(tx_queue, channel)
efx_fini_tx_queue(tx_queue);
- efx_fini_eventq(channel);
}
}
@@ -696,6 +728,7 @@ static void efx_remove_channel(struct efx_channel *channel)
efx_for_each_possible_channel_tx_queue(tx_queue, channel)
efx_remove_tx_queue(tx_queue);
efx_remove_eventq(channel);
+ channel->type->post_remove(channel);
}
static void efx_remove_channels(struct efx_nic *efx)
@@ -711,16 +744,45 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
{
struct efx_channel *other_channel[EFX_MAX_CHANNELS], *channel;
u32 old_rxq_entries, old_txq_entries;
- unsigned i;
- int rc;
+ unsigned i, next_buffer_table = 0;
+ int rc, rc2;
+
+ rc = efx_check_disabled(efx);
+ if (rc)
+ return rc;
+ /* Not all channels should be reallocated. We must avoid
+ * reallocating their buffer table entries.
+ */
+ efx_for_each_channel(channel, efx) {
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+
+ if (channel->type->copy)
+ continue;
+ next_buffer_table = max(next_buffer_table,
+ channel->eventq.index +
+ channel->eventq.entries);
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ next_buffer_table = max(next_buffer_table,
+ rx_queue->rxd.index +
+ rx_queue->rxd.entries);
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ next_buffer_table = max(next_buffer_table,
+ tx_queue->txd.index +
+ tx_queue->txd.entries);
+ }
+
+ efx_device_detach_sync(efx);
efx_stop_all(efx);
- efx_fini_channels(efx);
+ efx_soft_disable_interrupts(efx);
- /* Clone channels */
+ /* Clone channels (where possible) */
memset(other_channel, 0, sizeof(other_channel));
for (i = 0; i < efx->n_channels; i++) {
- channel = efx_alloc_channel(efx, i, efx->channel[i]);
+ channel = efx->channel[i];
+ if (channel->type->copy)
+ channel = channel->type->copy(channel);
if (!channel) {
rc = -ENOMEM;
goto out;
@@ -739,24 +801,40 @@ efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries)
other_channel[i] = channel;
}
- rc = efx_probe_channels(efx);
- if (rc)
- goto rollback;
-
- efx_init_napi(efx);
+ /* Restart buffer table allocation */
+ efx->next_buffer_table = next_buffer_table;
- /* Destroy old channels */
for (i = 0; i < efx->n_channels; i++) {
- efx_fini_napi_channel(other_channel[i]);
- efx_remove_channel(other_channel[i]);
+ channel = efx->channel[i];
+ if (!channel->type->copy)
+ continue;
+ rc = efx_probe_channel(channel);
+ if (rc)
+ goto rollback;
+ efx_init_napi_channel(efx->channel[i]);
}
+
out:
- /* Free unused channel structures */
- for (i = 0; i < efx->n_channels; i++)
- kfree(other_channel[i]);
+ /* Destroy unused channel structures */
+ for (i = 0; i < efx->n_channels; i++) {
+ channel = other_channel[i];
+ if (channel && channel->type->copy) {
+ efx_fini_napi_channel(channel);
+ efx_remove_channel(channel);
+ kfree(channel);
+ }
+ }
- efx_init_channels(efx);
- efx_start_all(efx);
+ rc2 = efx_soft_enable_interrupts(efx);
+ if (rc2) {
+ rc = rc ? rc : rc2;
+ netif_err(efx, drv, efx->net_dev,
+ "unable to restart interrupts on channel reallocation\n");
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+ } else {
+ efx_start_all(efx);
+ netif_device_attach(efx->net_dev);
+ }
return rc;
rollback:
@@ -776,6 +854,23 @@ void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue)
mod_timer(&rx_queue->slow_fill, jiffies + msecs_to_jiffies(100));
}
+static const struct efx_channel_type efx_default_channel_type = {
+ .pre_probe = efx_channel_dummy_op_int,
+ .post_remove = efx_channel_dummy_op_void,
+ .get_name = efx_get_channel_name,
+ .copy = efx_copy_channel,
+ .keep_eventq = false,
+};
+
+int efx_channel_dummy_op_int(struct efx_channel *channel)
+{
+ return 0;
+}
+
+void efx_channel_dummy_op_void(struct efx_channel *channel)
+{
+}
+
/**************************************************************************
*
* Port handling
@@ -807,16 +902,13 @@ void efx_link_status_changed(struct efx_nic *efx)
}
/* Status message for kernel log */
- if (link_state->up) {
+ if (link_state->up)
netif_info(efx, link, efx->net_dev,
- "link up at %uMbps %s-duplex (MTU %d)%s\n",
+ "link up at %uMbps %s-duplex (MTU %d)\n",
link_state->speed, link_state->fd ? "full" : "half",
- efx->net_dev->mtu,
- (efx->promiscuous ? " [PROMISC]" : ""));
- } else {
+ efx->net_dev->mtu);
+ else
netif_info(efx, link, efx->net_dev, "link down\n");
- }
-
}
void efx_link_set_advertising(struct efx_nic *efx, u32 advertising)
@@ -863,12 +955,6 @@ int __efx_reconfigure_port(struct efx_nic *efx)
WARN_ON(!mutex_is_locked(&efx->mac_lock));
- /* Serialise the promiscuous flag with efx_set_multicast_list. */
- if (efx_dev_registered(efx)) {
- netif_addr_lock_bh(efx->net_dev);
- netif_addr_unlock_bh(efx->net_dev);
- }
-
/* Disable PHY transmit in mac level loopbacks */
phy_mode = efx->phy_mode;
if (LOOPBACK_INTERNAL(efx))
@@ -907,16 +993,13 @@ static void efx_mac_work(struct work_struct *data)
struct efx_nic *efx = container_of(data, struct efx_nic, mac_work);
mutex_lock(&efx->mac_lock);
- if (efx->port_enabled) {
- efx->type->push_multicast_hash(efx);
- efx->mac_op->reconfigure(efx);
- }
+ if (efx->port_enabled)
+ efx->type->reconfigure_mac(efx);
mutex_unlock(&efx->mac_lock);
}
static int efx_probe_port(struct efx_nic *efx)
{
- unsigned char *perm_addr;
int rc;
netif_dbg(efx, probe, efx->net_dev, "create port\n");
@@ -929,28 +1012,10 @@ static int efx_probe_port(struct efx_nic *efx)
if (rc)
return rc;
- /* Sanity check MAC address */
- perm_addr = efx->net_dev->perm_addr;
- if (is_valid_ether_addr(perm_addr)) {
- memcpy(efx->net_dev->dev_addr, perm_addr, ETH_ALEN);
- } else {
- netif_err(efx, probe, efx->net_dev, "invalid MAC address %pM\n",
- perm_addr);
- if (!allow_bad_hwaddr) {
- rc = -EINVAL;
- goto err;
- }
- random_ether_addr(efx->net_dev->dev_addr);
- netif_info(efx, probe, efx->net_dev,
- "using locally-generated MAC %pM\n",
- efx->net_dev->dev_addr);
- }
+ /* Initialise MAC address to permanent address */
+ ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr);
return 0;
-
- err:
- efx->type->remove_port(efx);
- return rc;
}
static int efx_init_port(struct efx_nic *efx)
@@ -969,7 +1034,7 @@ static int efx_init_port(struct efx_nic *efx)
/* Reconfigure the MAC before creating dma queues (required for
* Falcon/A1 where RX_INGR_EN/TX_DRAIN_EN isn't supported) */
- efx->mac_op->reconfigure(efx);
+ efx->type->reconfigure_mac(efx);
/* Ensure the PHY advertises the correct flow control settings */
rc = efx->phy_op->reconfigure(efx);
@@ -994,28 +1059,34 @@ static void efx_start_port(struct efx_nic *efx)
mutex_lock(&efx->mac_lock);
efx->port_enabled = true;
- /* efx_mac_work() might have been scheduled after efx_stop_port(),
- * and then cancelled by efx_flush_all() */
- efx->type->push_multicast_hash(efx);
- efx->mac_op->reconfigure(efx);
+ /* Ensure MAC ingress/egress is enabled */
+ efx->type->reconfigure_mac(efx);
mutex_unlock(&efx->mac_lock);
}
-/* Prevent efx_mac_work() and efx_monitor() from working */
+/* Cancel work for MAC reconfiguration, periodic hardware monitoring
+ * and the async self-test, wait for them to finish and prevent them
+ * being scheduled again. This doesn't cover online resets, which
+ * should only be cancelled when removing the device.
+ */
static void efx_stop_port(struct efx_nic *efx)
{
netif_dbg(efx, ifdown, efx->net_dev, "stop port\n");
+ EFX_ASSERT_RESET_SERIALISED(efx);
+
mutex_lock(&efx->mac_lock);
efx->port_enabled = false;
mutex_unlock(&efx->mac_lock);
/* Serialise against efx_set_multicast_list() */
- if (efx_dev_registered(efx)) {
- netif_addr_lock_bh(efx->net_dev);
- netif_addr_unlock_bh(efx->net_dev);
- }
+ netif_addr_lock_bh(efx->net_dev);
+ netif_addr_unlock_bh(efx->net_dev);
+
+ cancel_delayed_work_sync(&efx->monitor_work);
+ efx_selftest_async_cancel(efx);
+ cancel_work_sync(&efx->mac_work);
}
static void efx_fini_port(struct efx_nic *efx)
@@ -1045,11 +1116,83 @@ static void efx_remove_port(struct efx_nic *efx)
*
**************************************************************************/
+static LIST_HEAD(efx_primary_list);
+static LIST_HEAD(efx_unassociated_list);
+
+static bool efx_same_controller(struct efx_nic *left, struct efx_nic *right)
+{
+ return left->type == right->type &&
+ left->vpd_sn && right->vpd_sn &&
+ !strcmp(left->vpd_sn, right->vpd_sn);
+}
+
+static void efx_associate(struct efx_nic *efx)
+{
+ struct efx_nic *other, *next;
+
+ if (efx->primary == efx) {
+ /* Adding primary function; look for secondaries */
+
+ netif_dbg(efx, probe, efx->net_dev, "adding to primary list\n");
+ list_add_tail(&efx->node, &efx_primary_list);
+
+ list_for_each_entry_safe(other, next, &efx_unassociated_list,
+ node) {
+ if (efx_same_controller(efx, other)) {
+ list_del(&other->node);
+ netif_dbg(other, probe, other->net_dev,
+ "moving to secondary list of %s %s\n",
+ pci_name(efx->pci_dev),
+ efx->net_dev->name);
+ list_add_tail(&other->node,
+ &efx->secondary_list);
+ other->primary = efx;
+ }
+ }
+ } else {
+ /* Adding secondary function; look for primary */
+
+ list_for_each_entry(other, &efx_primary_list, node) {
+ if (efx_same_controller(efx, other)) {
+ netif_dbg(efx, probe, efx->net_dev,
+ "adding to secondary list of %s %s\n",
+ pci_name(other->pci_dev),
+ other->net_dev->name);
+ list_add_tail(&efx->node,
+ &other->secondary_list);
+ efx->primary = other;
+ return;
+ }
+ }
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "adding to unassociated list\n");
+ list_add_tail(&efx->node, &efx_unassociated_list);
+ }
+}
+
+static void efx_dissociate(struct efx_nic *efx)
+{
+ struct efx_nic *other, *next;
+
+ list_del(&efx->node);
+ efx->primary = NULL;
+
+ list_for_each_entry_safe(other, next, &efx->secondary_list, node) {
+ list_del(&other->node);
+ netif_dbg(other, probe, other->net_dev,
+ "moving to unassociated list\n");
+ list_add_tail(&other->node, &efx_unassociated_list);
+ other->primary = NULL;
+ }
+}
+
/* This configures the PCI device to enable I/O and DMA. */
static int efx_init_io(struct efx_nic *efx)
{
struct pci_dev *pci_dev = efx->pci_dev;
dma_addr_t dma_mask = efx->type->max_dma_mask;
+ unsigned int mem_map_size = efx->type->mem_map_size(efx);
int rc;
netif_dbg(efx, probe, efx->net_dev, "initialising I/O\n");
@@ -1069,9 +1212,11 @@ static int efx_init_io(struct efx_nic *efx)
* masks event though they reject 46 bit masks.
*/
while (dma_mask > 0x7fffffffUL) {
- if (pci_dma_supported(pci_dev, dma_mask) &&
- ((rc = pci_set_dma_mask(pci_dev, dma_mask)) == 0))
- break;
+ if (dma_supported(&pci_dev->dev, dma_mask)) {
+ rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask);
+ if (rc == 0)
+ break;
+ }
dma_mask >>= 1;
}
if (rc) {
@@ -1081,16 +1226,6 @@ static int efx_init_io(struct efx_nic *efx)
}
netif_dbg(efx, probe, efx->net_dev,
"using DMA mask %llx\n", (unsigned long long) dma_mask);
- rc = pci_set_consistent_dma_mask(pci_dev, dma_mask);
- if (rc) {
- /* pci_set_consistent_dma_mask() is not *allowed* to
- * fail with a mask that pci_set_dma_mask() accepted,
- * but just in case...
- */
- netif_err(efx, probe, efx->net_dev,
- "failed to set consistent DMA mask\n");
- goto fail2;
- }
efx->membase_phys = pci_resource_start(efx->pci_dev, EFX_MEM_BAR);
rc = pci_request_region(pci_dev, EFX_MEM_BAR, "sfc");
@@ -1100,20 +1235,18 @@ static int efx_init_io(struct efx_nic *efx)
rc = -EIO;
goto fail3;
}
- efx->membase = ioremap_nocache(efx->membase_phys,
- efx->type->mem_map_size);
+ efx->membase = ioremap_nocache(efx->membase_phys, mem_map_size);
if (!efx->membase) {
netif_err(efx, probe, efx->net_dev,
"could not map memory BAR at %llx+%x\n",
- (unsigned long long)efx->membase_phys,
- efx->type->mem_map_size);
+ (unsigned long long)efx->membase_phys, mem_map_size);
rc = -ENOMEM;
goto fail4;
}
netif_dbg(efx, probe, efx->net_dev,
"memory BAR at %llx+%x (virtual %p)\n",
- (unsigned long long)efx->membase_phys,
- efx->type->mem_map_size, efx->membase);
+ (unsigned long long)efx->membase_phys, mem_map_size,
+ efx->membase);
return 0;
@@ -1144,116 +1277,106 @@ static void efx_fini_io(struct efx_nic *efx)
pci_disable_device(efx->pci_dev);
}
-/* Get number of channels wanted. Each channel will have its own IRQ,
- * 1 RX queue and/or 2 TX queues. */
-static int efx_wanted_channels(void)
+static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
{
- cpumask_var_t core_mask;
- int count;
+ cpumask_var_t thread_mask;
+ unsigned int count;
int cpu;
- if (rss_cpus)
- return rss_cpus;
+ if (rss_cpus) {
+ count = rss_cpus;
+ } else {
+ if (unlikely(!zalloc_cpumask_var(&thread_mask, GFP_KERNEL))) {
+ netif_warn(efx, probe, efx->net_dev,
+ "RSS disabled due to allocation failure\n");
+ return 1;
+ }
- if (unlikely(!zalloc_cpumask_var(&core_mask, GFP_KERNEL))) {
- printk(KERN_WARNING
- "sfc: RSS disabled due to allocation failure\n");
- return 1;
+ count = 0;
+ for_each_online_cpu(cpu) {
+ if (!cpumask_test_cpu(cpu, thread_mask)) {
+ ++count;
+ cpumask_or(thread_mask, thread_mask,
+ topology_thread_cpumask(cpu));
+ }
+ }
+
+ free_cpumask_var(thread_mask);
}
- count = 0;
- for_each_online_cpu(cpu) {
- if (!cpumask_test_cpu(cpu, core_mask)) {
- ++count;
- cpumask_or(core_mask, core_mask,
- topology_core_cpumask(cpu));
- }
+ /* If RSS is requested for the PF *and* VFs then we can't write RSS
+ * table entries that are inaccessible to VFs
+ */
+ if (efx_sriov_wanted(efx) && efx_vf_size(efx) > 1 &&
+ count > efx_vf_size(efx)) {
+ netif_warn(efx, probe, efx->net_dev,
+ "Reducing number of RSS channels from %u to %u for "
+ "VF support. Increase vf-msix-limit to use more "
+ "channels on the PF.\n",
+ count, efx_vf_size(efx));
+ count = efx_vf_size(efx);
}
- free_cpumask_var(core_mask);
return count;
}
-static int
-efx_init_rx_cpu_rmap(struct efx_nic *efx, struct msix_entry *xentries)
-{
-#ifdef CONFIG_RFS_ACCEL
- int i, rc;
-
- efx->net_dev->rx_cpu_rmap = alloc_irq_cpu_rmap(efx->n_rx_channels);
- if (!efx->net_dev->rx_cpu_rmap)
- return -ENOMEM;
- for (i = 0; i < efx->n_rx_channels; i++) {
- rc = irq_cpu_rmap_add(efx->net_dev->rx_cpu_rmap,
- xentries[i].vector);
- if (rc) {
- free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
- efx->net_dev->rx_cpu_rmap = NULL;
- return rc;
- }
- }
-#endif
- return 0;
-}
-
/* Probe the number and type of interrupts we are able to obtain, and
* the resulting numbers of channels and RX queues.
*/
static int efx_probe_interrupts(struct efx_nic *efx)
{
- int max_channels =
- min_t(int, efx->type->phys_addr_channels, EFX_MAX_CHANNELS);
- int rc, i;
+ unsigned int extra_channels = 0;
+ unsigned int i, j;
+ int rc;
+
+ for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++)
+ if (efx->extra_channel_type[i])
+ ++extra_channels;
if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
struct msix_entry xentries[EFX_MAX_CHANNELS];
- int n_channels;
+ unsigned int n_channels;
- n_channels = efx_wanted_channels();
+ n_channels = efx_wanted_parallelism(efx);
if (separate_tx_channels)
n_channels *= 2;
- n_channels = min(n_channels, max_channels);
+ n_channels += extra_channels;
+ n_channels = min(n_channels, efx->max_channels);
for (i = 0; i < n_channels; i++)
xentries[i].entry = i;
- rc = pci_enable_msix(efx->pci_dev, xentries, n_channels);
- if (rc > 0) {
+ rc = pci_enable_msix_range(efx->pci_dev,
+ xentries, 1, n_channels);
+ if (rc < 0) {
+ /* Fall back to single channel MSI */
+ efx->interrupt_mode = EFX_INT_MODE_MSI;
+ netif_err(efx, drv, efx->net_dev,
+ "could not enable MSI-X\n");
+ } else if (rc < n_channels) {
netif_err(efx, drv, efx->net_dev,
"WARNING: Insufficient MSI-X vectors"
- " available (%d < %d).\n", rc, n_channels);
+ " available (%d < %u).\n", rc, n_channels);
netif_err(efx, drv, efx->net_dev,
"WARNING: Performance may be reduced.\n");
- EFX_BUG_ON_PARANOID(rc >= n_channels);
n_channels = rc;
- rc = pci_enable_msix(efx->pci_dev, xentries,
- n_channels);
}
- if (rc == 0) {
+ if (rc > 0) {
efx->n_channels = n_channels;
+ if (n_channels > extra_channels)
+ n_channels -= extra_channels;
if (separate_tx_channels) {
- efx->n_tx_channels =
- max(efx->n_channels / 2, 1U);
- efx->n_rx_channels =
- max(efx->n_channels -
- efx->n_tx_channels, 1U);
+ efx->n_tx_channels = max(n_channels / 2, 1U);
+ efx->n_rx_channels = max(n_channels -
+ efx->n_tx_channels,
+ 1U);
} else {
- efx->n_tx_channels = efx->n_channels;
- efx->n_rx_channels = efx->n_channels;
- }
- rc = efx_init_rx_cpu_rmap(efx, xentries);
- if (rc) {
- pci_disable_msix(efx->pci_dev);
- return rc;
+ efx->n_tx_channels = n_channels;
+ efx->n_rx_channels = n_channels;
}
- for (i = 0; i < n_channels; i++)
+ for (i = 0; i < efx->n_channels; i++)
efx_get_channel(efx, i)->irq =
xentries[i].vector;
- } else {
- /* Fall back to single channel MSI */
- efx->interrupt_mode = EFX_INT_MODE_MSI;
- netif_err(efx, drv, efx->net_dev,
- "could not enable MSI-X\n");
}
}
@@ -1280,7 +1403,145 @@ static int efx_probe_interrupts(struct efx_nic *efx)
efx->legacy_irq = efx->pci_dev->irq;
}
+ /* Assign extra channels if possible */
+ j = efx->n_channels;
+ for (i = 0; i < EFX_MAX_EXTRA_CHANNELS; i++) {
+ if (!efx->extra_channel_type[i])
+ continue;
+ if (efx->interrupt_mode != EFX_INT_MODE_MSIX ||
+ efx->n_channels <= extra_channels) {
+ efx->extra_channel_type[i]->handle_no_channel(efx);
+ } else {
+ --j;
+ efx_get_channel(efx, j)->type =
+ efx->extra_channel_type[i];
+ }
+ }
+
+ /* RSS might be usable on VFs even if it is disabled on the PF */
+ efx->rss_spread = ((efx->n_rx_channels > 1 || !efx_sriov_wanted(efx)) ?
+ efx->n_rx_channels : efx_vf_size(efx));
+
+ return 0;
+}
+
+static int efx_soft_enable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel, *end_channel;
+ int rc;
+
+ BUG_ON(efx->state == STATE_DISABLED);
+
+ efx->irq_soft_enabled = true;
+ smp_wmb();
+
+ efx_for_each_channel(channel, efx) {
+ if (!channel->type->keep_eventq) {
+ rc = efx_init_eventq(channel);
+ if (rc)
+ goto fail;
+ }
+ efx_start_eventq(channel);
+ }
+
+ efx_mcdi_mode_event(efx);
+
return 0;
+fail:
+ end_channel = channel;
+ efx_for_each_channel(channel, efx) {
+ if (channel == end_channel)
+ break;
+ efx_stop_eventq(channel);
+ if (!channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ return rc;
+}
+
+static void efx_soft_disable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ if (efx->state == STATE_DISABLED)
+ return;
+
+ efx_mcdi_mode_poll(efx);
+
+ efx->irq_soft_enabled = false;
+ smp_wmb();
+
+ if (efx->legacy_irq)
+ synchronize_irq(efx->legacy_irq);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->irq)
+ synchronize_irq(channel->irq);
+
+ efx_stop_eventq(channel);
+ if (!channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ /* Flush the asynchronous MCDI request queue */
+ efx_mcdi_flush_async(efx);
+}
+
+static int efx_enable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel, *end_channel;
+ int rc;
+
+ BUG_ON(efx->state == STATE_DISABLED);
+
+ if (efx->eeh_disabled_legacy_irq) {
+ enable_irq(efx->legacy_irq);
+ efx->eeh_disabled_legacy_irq = false;
+ }
+
+ efx->type->irq_enable_master(efx);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->type->keep_eventq) {
+ rc = efx_init_eventq(channel);
+ if (rc)
+ goto fail;
+ }
+ }
+
+ rc = efx_soft_enable_interrupts(efx);
+ if (rc)
+ goto fail;
+
+ return 0;
+
+fail:
+ end_channel = channel;
+ efx_for_each_channel(channel, efx) {
+ if (channel == end_channel)
+ break;
+ if (channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ efx->type->irq_disable_non_ev(efx);
+
+ return rc;
+}
+
+static void efx_disable_interrupts(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_soft_disable_interrupts(efx);
+
+ efx_for_each_channel(channel, efx) {
+ if (channel->type->keep_eventq)
+ efx_fini_eventq(channel);
+ }
+
+ efx->type->irq_disable_non_ev(efx);
}
static void efx_remove_interrupts(struct efx_nic *efx)
@@ -1305,10 +1566,16 @@ static void efx_set_channels(struct efx_nic *efx)
efx->tx_channel_offset =
separate_tx_channels ? efx->n_channels - efx->n_tx_channels : 0;
- /* We need to adjust the TX queue numbers if we have separate
+ /* We need to mark which channels really have RX and TX
+ * queues, and adjust the TX queue numbers if we have separate
* RX-only and TX-only channels.
*/
efx_for_each_channel(channel, efx) {
+ if (channel->channel < efx->n_rx_channels)
+ channel->rx_queue.core_index = channel->channel;
+ else
+ channel->rx_queue.core_index = -1;
+
efx_for_each_channel_tx_queue(tx_queue, channel)
tx_queue->queue -= (efx->tx_channel_offset *
EFX_TXQ_TYPES);
@@ -1331,15 +1598,20 @@ static int efx_probe_nic(struct efx_nic *efx)
* in MSI-X interrupts. */
rc = efx_probe_interrupts(efx);
if (rc)
- goto fail;
+ goto fail1;
+
+ efx_set_channels(efx);
+
+ rc = efx->type->dimension_resources(efx);
+ if (rc)
+ goto fail2;
if (efx->n_channels > 1)
get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
for (i = 0; i < ARRAY_SIZE(efx->rx_indir_table); i++)
efx->rx_indir_table[i] =
- ethtool_rxfh_indir_default(i, efx->n_rx_channels);
+ ethtool_rxfh_indir_default(i, efx->rss_spread);
- efx_set_channels(efx);
netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels);
netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels);
@@ -1349,7 +1621,9 @@ static int efx_probe_nic(struct efx_nic *efx)
return 0;
-fail:
+fail2:
+ efx_remove_interrupts(efx);
+fail1:
efx->type->remove(efx);
return rc;
}
@@ -1362,6 +1636,44 @@ static void efx_remove_nic(struct efx_nic *efx)
efx->type->remove(efx);
}
+static int efx_probe_filters(struct efx_nic *efx)
+{
+ int rc;
+
+ spin_lock_init(&efx->filter_lock);
+
+ rc = efx->type->filter_table_probe(efx);
+ if (rc)
+ return rc;
+
+#ifdef CONFIG_RFS_ACCEL
+ if (efx->type->offload_features & NETIF_F_NTUPLE) {
+ efx->rps_flow_id = kcalloc(efx->type->max_rx_ip_filters,
+ sizeof(*efx->rps_flow_id),
+ GFP_KERNEL);
+ if (!efx->rps_flow_id) {
+ efx->type->filter_table_remove(efx);
+ return -ENOMEM;
+ }
+ }
+#endif
+
+ return 0;
+}
+
+static void efx_remove_filters(struct efx_nic *efx)
+{
+#ifdef CONFIG_RFS_ACCEL
+ kfree(efx->rps_flow_id);
+#endif
+ efx->type->filter_table_remove(efx);
+}
+
+static void efx_restore_filters(struct efx_nic *efx)
+{
+ efx->type->filter_table_restore(efx);
+}
+
/**************************************************************************
*
* NIC startup/shutdown
@@ -1384,22 +1696,28 @@ static int efx_probe_all(struct efx_nic *efx)
goto fail2;
}
- efx->rxq_entries = efx->txq_entries = EFX_DEFAULT_DMAQ_SIZE;
- rc = efx_probe_channels(efx);
- if (rc)
+ BUILD_BUG_ON(EFX_DEFAULT_DMAQ_SIZE < EFX_RXQ_MIN_ENT);
+ if (WARN_ON(EFX_DEFAULT_DMAQ_SIZE < EFX_TXQ_MIN_ENT(efx))) {
+ rc = -EINVAL;
goto fail3;
+ }
+ efx->rxq_entries = efx->txq_entries = EFX_DEFAULT_DMAQ_SIZE;
rc = efx_probe_filters(efx);
if (rc) {
netif_err(efx, probe, efx->net_dev,
"failed to create filter tables\n");
- goto fail4;
+ goto fail3;
}
+ rc = efx_probe_channels(efx);
+ if (rc)
+ goto fail4;
+
return 0;
fail4:
- efx_remove_channels(efx);
+ efx_remove_filters(efx);
fail3:
efx_remove_port(efx);
fail2:
@@ -1408,56 +1726,36 @@ static int efx_probe_all(struct efx_nic *efx)
return rc;
}
-/* Called after previous invocation(s) of efx_stop_all, restarts the
- * port, kernel transmit queue, NAPI processing and hardware interrupts,
- * and ensures that the port is scheduled to be reconfigured.
- * This function is safe to call multiple times when the NIC is in any
- * state. */
+/* If the interface is supposed to be running but is not, start
+ * the hardware and software data path, regular activity for the port
+ * (MAC statistics, link polling, etc.) and schedule the port to be
+ * reconfigured. Interrupts must already be enabled. This function
+ * is safe to call multiple times, so long as the NIC is not disabled.
+ * Requires the RTNL lock.
+ */
static void efx_start_all(struct efx_nic *efx)
{
- struct efx_channel *channel;
-
EFX_ASSERT_RESET_SERIALISED(efx);
+ BUG_ON(efx->state == STATE_DISABLED);
/* Check that it is appropriate to restart the interface. All
* of these flags are safe to read under just the rtnl lock */
- if (efx->port_enabled)
- return;
- if ((efx->state != STATE_RUNNING) && (efx->state != STATE_INIT))
- return;
- if (efx_dev_registered(efx) && !netif_running(efx->net_dev))
+ if (efx->port_enabled || !netif_running(efx->net_dev) ||
+ efx->reset_pending)
return;
- /* Mark the port as enabled so port reconfigurations can start, then
- * restart the transmit interface early so the watchdog timer stops */
efx_start_port(efx);
+ efx_start_datapath(efx);
- if (efx_dev_registered(efx) && netif_device_present(efx->net_dev))
- netif_tx_wake_all_queues(efx->net_dev);
-
- efx_for_each_channel(channel, efx)
- efx_start_channel(channel);
-
- if (efx->legacy_irq)
- efx->legacy_irq_enabled = true;
- efx_nic_enable_interrupts(efx);
-
- /* Switch to event based MCDI completions after enabling interrupts.
- * If a reset has been scheduled, then we need to stay in polled mode.
- * Rather than serialising efx_mcdi_mode_event() [which sleeps] and
- * reset_pending [modified from an atomic context], we instead guarantee
- * that efx_mcdi_mode_poll() isn't reverted erroneously */
- efx_mcdi_mode_event(efx);
- if (efx->reset_pending)
- efx_mcdi_mode_poll(efx);
-
- /* Start the hardware monitor if there is one. Otherwise (we're link
- * event driven), we have to poll the PHY because after an event queue
- * flush, we could have a missed a link state change */
- if (efx->type->monitor != NULL) {
+ /* Start the hardware monitor if there is one */
+ if (efx->type->monitor != NULL)
queue_delayed_work(efx->workqueue, &efx->monitor_work,
efx_monitor_interval);
- } else {
+
+ /* If link state detection is normally event-driven, we have
+ * to poll now because we could have missed a change
+ */
+ if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) {
mutex_lock(&efx->mac_lock);
if (efx->phy_op->poll(efx))
efx_link_status_changed(efx);
@@ -1465,75 +1763,50 @@ static void efx_start_all(struct efx_nic *efx)
}
efx->type->start_stats(efx);
+ efx->type->pull_stats(efx);
+ spin_lock_bh(&efx->stats_lock);
+ efx->type->update_stats(efx, NULL, NULL);
+ spin_unlock_bh(&efx->stats_lock);
}
-/* Flush all delayed work. Should only be called when no more delayed work
- * will be scheduled. This doesn't flush pending online resets (efx_reset),
- * since we're holding the rtnl_lock at this point. */
-static void efx_flush_all(struct efx_nic *efx)
-{
- /* Make sure the hardware monitor is stopped */
- cancel_delayed_work_sync(&efx->monitor_work);
- /* Stop scheduled port reconfigurations */
- cancel_work_sync(&efx->mac_work);
-}
-
-/* Quiesce hardware and software without bringing the link down.
- * Safe to call multiple times, when the nic and interface is in any
- * state. The caller is guaranteed to subsequently be in a position
- * to modify any hardware and software state they see fit without
- * taking locks. */
+/* Quiesce the hardware and software data path, and regular activity
+ * for the port without bringing the link down. Safe to call multiple
+ * times with the NIC in almost any state, but interrupts should be
+ * enabled. Requires the RTNL lock.
+ */
static void efx_stop_all(struct efx_nic *efx)
{
- struct efx_channel *channel;
-
EFX_ASSERT_RESET_SERIALISED(efx);
/* port_enabled can be read safely under the rtnl lock */
if (!efx->port_enabled)
return;
+ /* update stats before we go down so we can accurately count
+ * rx_nodesc_drops
+ */
+ efx->type->pull_stats(efx);
+ spin_lock_bh(&efx->stats_lock);
+ efx->type->update_stats(efx, NULL, NULL);
+ spin_unlock_bh(&efx->stats_lock);
efx->type->stop_stats(efx);
-
- /* Switch to MCDI polling on Siena before disabling interrupts */
- efx_mcdi_mode_poll(efx);
-
- /* Disable interrupts and wait for ISR to complete */
- efx_nic_disable_interrupts(efx);
- if (efx->legacy_irq) {
- synchronize_irq(efx->legacy_irq);
- efx->legacy_irq_enabled = false;
- }
- efx_for_each_channel(channel, efx) {
- if (channel->irq)
- synchronize_irq(channel->irq);
- }
-
- /* Stop all NAPI processing and synchronous rx refills */
- efx_for_each_channel(channel, efx)
- efx_stop_channel(channel);
-
- /* Stop all asynchronous port reconfigurations. Since all
- * event processing has already been stopped, there is no
- * window to loose phy events */
efx_stop_port(efx);
- /* Flush efx_mac_work(), refill_workqueue, monitor_work */
- efx_flush_all(efx);
+ /* Stop the kernel transmit interface. This is only valid if
+ * the device is stopped or detached; otherwise the watchdog
+ * may fire immediately.
+ */
+ WARN_ON(netif_running(efx->net_dev) &&
+ netif_device_present(efx->net_dev));
+ netif_tx_disable(efx->net_dev);
- /* Stop the kernel transmit interface late, so the watchdog
- * timer isn't ticking over the flush */
- if (efx_dev_registered(efx)) {
- netif_tx_stop_all_queues(efx->net_dev);
- netif_tx_lock_bh(efx->net_dev);
- netif_tx_unlock_bh(efx->net_dev);
- }
+ efx_stop_datapath(efx);
}
static void efx_remove_all(struct efx_nic *efx)
{
- efx_remove_filters(efx);
efx_remove_channels(efx);
+ efx_remove_filters(efx);
efx_remove_port(efx);
efx_remove_nic(efx);
}
@@ -1544,13 +1817,13 @@ static void efx_remove_all(struct efx_nic *efx)
*
**************************************************************************/
-static unsigned int irq_mod_ticks(unsigned int usecs, unsigned int resolution)
+static unsigned int irq_mod_ticks(unsigned int usecs, unsigned int quantum_ns)
{
if (usecs == 0)
return 0;
- if (usecs < resolution)
+ if (usecs * 1000 < quantum_ns)
return 1; /* never round down to 0 */
- return usecs / resolution;
+ return usecs * 1000 / quantum_ns;
}
/* Set interrupt moderation parameters */
@@ -1559,14 +1832,20 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
bool rx_may_override_tx)
{
struct efx_channel *channel;
- unsigned tx_ticks = irq_mod_ticks(tx_usecs, EFX_IRQ_MOD_RESOLUTION);
- unsigned rx_ticks = irq_mod_ticks(rx_usecs, EFX_IRQ_MOD_RESOLUTION);
+ unsigned int irq_mod_max = DIV_ROUND_UP(efx->type->timer_period_max *
+ efx->timer_quantum_ns,
+ 1000);
+ unsigned int tx_ticks;
+ unsigned int rx_ticks;
EFX_ASSERT_RESET_SERIALISED(efx);
- if (tx_ticks > EFX_IRQ_MOD_MAX || rx_ticks > EFX_IRQ_MOD_MAX)
+ if (tx_usecs > irq_mod_max || rx_usecs > irq_mod_max)
return -EINVAL;
+ tx_ticks = irq_mod_ticks(tx_usecs, efx->timer_quantum_ns);
+ rx_ticks = irq_mod_ticks(rx_usecs, efx->timer_quantum_ns);
+
if (tx_ticks != rx_ticks && efx->tx_channel_offset == 0 &&
!rx_may_override_tx) {
netif_err(efx, drv, efx->net_dev, "Channels are shared. "
@@ -1589,8 +1868,14 @@ int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
unsigned int *rx_usecs, bool *rx_adaptive)
{
+ /* We must round up when converting ticks to microseconds
+ * because we round down when converting the other way.
+ */
+
*rx_adaptive = efx->irq_rx_adaptive;
- *rx_usecs = efx->irq_rx_moderation * EFX_IRQ_MOD_RESOLUTION;
+ *rx_usecs = DIV_ROUND_UP(efx->irq_rx_moderation *
+ efx->timer_quantum_ns,
+ 1000);
/* If channels are shared between RX and TX, so is IRQ
* moderation. Otherwise, IRQ moderation is the same for all
@@ -1599,9 +1884,10 @@ void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
if (efx->tx_channel_offset == 0)
*tx_usecs = *rx_usecs;
else
- *tx_usecs =
+ *tx_usecs = DIV_ROUND_UP(
efx->channel[efx->tx_channel_offset]->irq_moderation *
- EFX_IRQ_MOD_RESOLUTION;
+ efx->timer_quantum_ns,
+ 1000);
}
/**************************************************************************
@@ -1648,7 +1934,10 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
struct efx_nic *efx = netdev_priv(net_dev);
struct mii_ioctl_data *data = if_mii(ifr);
- EFX_ASSERT_RESET_SERIALISED(efx);
+ if (cmd == SIOCSHWTSTAMP)
+ return efx_ptp_set_ts_config(efx, ifr);
+ if (cmd == SIOCGHWTSTAMP)
+ return efx_ptp_get_ts_config(efx, ifr);
/* Convert phy_id from older PRTAD/DEVAD format */
if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
@@ -1664,15 +1953,21 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
*
**************************************************************************/
+static void efx_init_napi_channel(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+
+ channel->napi_dev = efx->net_dev;
+ netif_napi_add(channel->napi_dev, &channel->napi_str,
+ efx_poll, napi_weight);
+}
+
static void efx_init_napi(struct efx_nic *efx)
{
struct efx_channel *channel;
- efx_for_each_channel(channel, efx) {
- channel->napi_dev = efx->net_dev;
- netif_napi_add(channel->napi_dev, &channel->napi_str,
- efx_poll, napi_weight);
- }
+ efx_for_each_channel(channel, efx)
+ efx_init_napi_channel(channel);
}
static void efx_fini_napi_channel(struct efx_channel *channel)
@@ -1723,13 +2018,14 @@ static void efx_netpoll(struct net_device *net_dev)
static int efx_net_open(struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
- EFX_ASSERT_RESET_SERIALISED(efx);
+ int rc;
netif_dbg(efx, ifup, efx->net_dev, "opening device on CPU %d\n",
raw_smp_processor_id());
- if (efx->state == STATE_DISABLED)
- return -EIO;
+ rc = efx_check_disabled(efx);
+ if (rc)
+ return rc;
if (efx->phy_mode & PHY_MODE_SPECIAL)
return -EBUSY;
if (efx_mcdi_poll_reboot(efx) && efx_reset(efx, RESET_TYPE_ALL))
@@ -1740,6 +2036,7 @@ static int efx_net_open(struct net_device *net_dev)
efx_link_status_changed(efx);
efx_start_all(efx);
+ efx_selftest_async_start(efx);
return 0;
}
@@ -1754,48 +2051,22 @@ static int efx_net_stop(struct net_device *net_dev)
netif_dbg(efx, ifdown, efx->net_dev, "closing on CPU %d\n",
raw_smp_processor_id());
- if (efx->state != STATE_DISABLED) {
- /* Stop the device and flush all the channels */
- efx_stop_all(efx);
- efx_fini_channels(efx);
- efx_init_channels(efx);
- }
+ /* Stop the device and flush all the channels */
+ efx_stop_all(efx);
return 0;
}
/* Context: process, dev_base_lock or RTNL held, non-blocking. */
-static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev, struct rtnl_link_stats64 *stats)
+static struct rtnl_link_stats64 *efx_net_stats(struct net_device *net_dev,
+ struct rtnl_link_stats64 *stats)
{
struct efx_nic *efx = netdev_priv(net_dev);
- struct efx_mac_stats *mac_stats = &efx->mac_stats;
spin_lock_bh(&efx->stats_lock);
- efx->type->update_stats(efx);
+ efx->type->update_stats(efx, NULL, stats);
spin_unlock_bh(&efx->stats_lock);
- stats->rx_packets = mac_stats->rx_packets;
- stats->tx_packets = mac_stats->tx_packets;
- stats->rx_bytes = mac_stats->rx_bytes;
- stats->tx_bytes = mac_stats->tx_bytes;
- stats->rx_dropped = efx->n_rx_nodesc_drop_cnt;
- stats->multicast = mac_stats->rx_multicast;
- stats->collisions = mac_stats->tx_collision;
- stats->rx_length_errors = (mac_stats->rx_gtjumbo +
- mac_stats->rx_length_error);
- stats->rx_crc_errors = mac_stats->rx_bad;
- stats->rx_frame_errors = mac_stats->rx_align_error;
- stats->rx_fifo_errors = mac_stats->rx_overflow;
- stats->rx_missed_errors = mac_stats->rx_missed;
- stats->tx_window_errors = mac_stats->tx_late_collision;
-
- stats->rx_errors = (stats->rx_length_errors +
- stats->rx_crc_errors +
- stats->rx_frame_errors +
- mac_stats->rx_symbol_error);
- stats->tx_errors = (stats->tx_window_errors +
- mac_stats->tx_bad);
-
return stats;
}
@@ -1816,85 +2087,57 @@ static void efx_watchdog(struct net_device *net_dev)
static int efx_change_mtu(struct net_device *net_dev, int new_mtu)
{
struct efx_nic *efx = netdev_priv(net_dev);
- int rc = 0;
-
- EFX_ASSERT_RESET_SERIALISED(efx);
+ int rc;
+ rc = efx_check_disabled(efx);
+ if (rc)
+ return rc;
if (new_mtu > EFX_MAX_MTU)
return -EINVAL;
- efx_stop_all(efx);
-
netif_dbg(efx, drv, efx->net_dev, "changing MTU to %d\n", new_mtu);
- efx_fini_channels(efx);
+ efx_device_detach_sync(efx);
+ efx_stop_all(efx);
mutex_lock(&efx->mac_lock);
- /* Reconfigure the MAC before enabling the dma queues so that
- * the RX buffers don't overflow */
net_dev->mtu = new_mtu;
- efx->mac_op->reconfigure(efx);
+ efx->type->reconfigure_mac(efx);
mutex_unlock(&efx->mac_lock);
- efx_init_channels(efx);
-
efx_start_all(efx);
- return rc;
+ netif_device_attach(efx->net_dev);
+ return 0;
}
static int efx_set_mac_address(struct net_device *net_dev, void *data)
{
struct efx_nic *efx = netdev_priv(net_dev);
struct sockaddr *addr = data;
- char *new_addr = addr->sa_data;
-
- EFX_ASSERT_RESET_SERIALISED(efx);
+ u8 *new_addr = addr->sa_data;
if (!is_valid_ether_addr(new_addr)) {
netif_err(efx, drv, efx->net_dev,
"invalid ethernet MAC address requested: %pM\n",
new_addr);
- return -EINVAL;
+ return -EADDRNOTAVAIL;
}
- memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len);
+ ether_addr_copy(net_dev->dev_addr, new_addr);
+ efx_sriov_mac_address_changed(efx);
/* Reconfigure the MAC */
mutex_lock(&efx->mac_lock);
- efx->mac_op->reconfigure(efx);
+ efx->type->reconfigure_mac(efx);
mutex_unlock(&efx->mac_lock);
return 0;
}
/* Context: netif_addr_lock held, BHs disabled. */
-static void efx_set_multicast_list(struct net_device *net_dev)
+static void efx_set_rx_mode(struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
- struct netdev_hw_addr *ha;
- union efx_multicast_hash *mc_hash = &efx->multicast_hash;
- u32 crc;
- int bit;
-
- efx->promiscuous = !!(net_dev->flags & IFF_PROMISC);
-
- /* Build multicast hash table */
- if (efx->promiscuous || (net_dev->flags & IFF_ALLMULTI)) {
- memset(mc_hash, 0xff, sizeof(*mc_hash));
- } else {
- memset(mc_hash, 0x00, sizeof(*mc_hash));
- netdev_for_each_mc_addr(ha, net_dev) {
- crc = ether_crc_le(ETH_ALEN, ha->addr);
- bit = crc & (EFX_MCAST_HASH_ENTRIES - 1);
- set_bit_le(bit, mc_hash->byte);
- }
-
- /* Broadcast packets go through the multicast hash filter.
- * ether_crc_le() of the broadcast address is 0xbe2612ff
- * so we always add bit 0xff to the mask.
- */
- set_bit_le(0xff, mc_hash->byte);
- }
if (efx->port_enabled)
queue_work(efx->workqueue, &efx->mac_work);
@@ -1907,12 +2150,12 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data)
/* If disabling RX n-tuple filtering, clear existing filters */
if (net_dev->features & ~data & NETIF_F_NTUPLE)
- efx_filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
+ return efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL);
return 0;
}
-static const struct net_device_ops efx_netdev_ops = {
+static const struct net_device_ops efx_farch_netdev_ops = {
.ndo_open = efx_net_open,
.ndo_stop = efx_net_stop,
.ndo_get_stats64 = efx_net_stats,
@@ -1922,8 +2165,14 @@ static const struct net_device_ops efx_netdev_ops = {
.ndo_do_ioctl = efx_ioctl,
.ndo_change_mtu = efx_change_mtu,
.ndo_set_mac_address = efx_set_mac_address,
- .ndo_set_rx_mode = efx_set_multicast_list,
+ .ndo_set_rx_mode = efx_set_rx_mode,
.ndo_set_features = efx_set_features,
+#ifdef CONFIG_SFC_SRIOV
+ .ndo_set_vf_mac = efx_sriov_set_vf_mac,
+ .ndo_set_vf_vlan = efx_sriov_set_vf_vlan,
+ .ndo_set_vf_spoofchk = efx_sriov_set_vf_spoofchk,
+ .ndo_get_vf_config = efx_sriov_get_vf_config,
+#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = efx_netpoll,
#endif
@@ -1933,6 +2182,26 @@ static const struct net_device_ops efx_netdev_ops = {
#endif
};
+static const struct net_device_ops efx_ef10_netdev_ops = {
+ .ndo_open = efx_net_open,
+ .ndo_stop = efx_net_stop,
+ .ndo_get_stats64 = efx_net_stats,
+ .ndo_tx_timeout = efx_watchdog,
+ .ndo_start_xmit = efx_hard_start_xmit,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_do_ioctl = efx_ioctl,
+ .ndo_change_mtu = efx_change_mtu,
+ .ndo_set_mac_address = efx_set_mac_address,
+ .ndo_set_rx_mode = efx_set_rx_mode,
+ .ndo_set_features = efx_set_features,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+ .ndo_poll_controller = efx_netpoll,
+#endif
+#ifdef CONFIG_RFS_ACCEL
+ .ndo_rx_flow_steer = efx_filter_rfs,
+#endif
+};
+
static void efx_update_name(struct efx_nic *efx)
{
strcpy(efx->name, efx->net_dev->name);
@@ -1943,9 +2212,10 @@ static void efx_update_name(struct efx_nic *efx)
static int efx_netdev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
- struct net_device *net_dev = ptr;
+ struct net_device *net_dev = netdev_notifier_info_to_dev(ptr);
- if (net_dev->netdev_ops == &efx_netdev_ops &&
+ if ((net_dev->netdev_ops == &efx_farch_netdev_ops ||
+ net_dev->netdev_ops == &efx_ef10_netdev_ops) &&
event == NETDEV_CHANGENAME)
efx_update_name(netdev_priv(net_dev));
@@ -1962,7 +2232,7 @@ show_phy_type(struct device *dev, struct device_attribute *attr, char *buf)
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
return sprintf(buf, "%d\n", efx->phy_type);
}
-static DEVICE_ATTR(phy_type, 0644, show_phy_type, NULL);
+static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL);
static int efx_register_netdev(struct efx_nic *efx)
{
@@ -1972,20 +2242,38 @@ static int efx_register_netdev(struct efx_nic *efx)
net_dev->watchdog_timeo = 5 * HZ;
net_dev->irq = efx->pci_dev->irq;
- net_dev->netdev_ops = &efx_netdev_ops;
- SET_ETHTOOL_OPS(net_dev, &efx_ethtool_ops);
-
- /* Clear MAC statistics */
- efx->mac_op->update_stats(efx);
- memset(&efx->mac_stats, 0, sizeof(efx->mac_stats));
+ if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
+ net_dev->netdev_ops = &efx_ef10_netdev_ops;
+ net_dev->priv_flags |= IFF_UNICAST_FLT;
+ } else {
+ net_dev->netdev_ops = &efx_farch_netdev_ops;
+ }
+ net_dev->ethtool_ops = &efx_ethtool_ops;
+ net_dev->gso_max_segs = EFX_TSO_MAX_SEGS;
rtnl_lock();
+ /* Enable resets to be scheduled and check whether any were
+ * already requested. If so, the NIC is probably hosed so we
+ * abort.
+ */
+ efx->state = STATE_READY;
+ smp_mb(); /* ensure we change state before checking reset_pending */
+ if (efx->reset_pending) {
+ netif_err(efx, probe, efx->net_dev,
+ "aborting probe due to scheduled reset\n");
+ rc = -EIO;
+ goto fail_locked;
+ }
+
rc = dev_alloc_name(net_dev, net_dev->name);
if (rc < 0)
goto fail_locked;
efx_update_name(efx);
+ /* Always start with carrier off; PHY events will detect the link */
+ netif_carrier_off(net_dev);
+
rc = register_netdevice(net_dev);
if (rc)
goto fail_locked;
@@ -1996,8 +2284,7 @@ static int efx_register_netdev(struct efx_nic *efx)
efx_init_tx_queue_core_txq(tx_queue);
}
- /* Always start with carrier off; PHY events will detect the link */
- netif_carrier_off(efx->net_dev);
+ efx_associate(efx);
rtnl_unlock();
@@ -2010,39 +2297,31 @@ static int efx_register_netdev(struct efx_nic *efx)
return 0;
+fail_registered:
+ rtnl_lock();
+ efx_dissociate(efx);
+ unregister_netdevice(net_dev);
fail_locked:
+ efx->state = STATE_UNINIT;
rtnl_unlock();
netif_err(efx, drv, efx->net_dev, "could not register net dev\n");
return rc;
-
-fail_registered:
- unregister_netdev(net_dev);
- return rc;
}
static void efx_unregister_netdev(struct efx_nic *efx)
{
- struct efx_channel *channel;
- struct efx_tx_queue *tx_queue;
-
if (!efx->net_dev)
return;
BUG_ON(netdev_priv(efx->net_dev) != efx);
- /* Free up any skbs still remaining. This has to happen before
- * we try to unregister the netdev as running their destructors
- * may be needed to get the device ref. count to 0. */
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_tx_queue(tx_queue, channel)
- efx_release_tx_buffers(tx_queue);
- }
+ strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
+ device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
- if (efx_dev_registered(efx)) {
- strlcpy(efx->name, pci_name(efx->pci_dev), sizeof(efx->name));
- device_remove_file(&efx->pci_dev->dev, &dev_attr_phy_type);
- unregister_netdev(efx->net_dev);
- }
+ rtnl_lock();
+ unregister_netdevice(efx->net_dev);
+ efx->state = STATE_UNINIT;
+ rtnl_unlock();
}
/**************************************************************************
@@ -2057,10 +2336,13 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method)
{
EFX_ASSERT_RESET_SERIALISED(efx);
+ if (method == RESET_TYPE_MCDI_TIMEOUT)
+ efx->type->prepare_flr(efx);
+
efx_stop_all(efx);
- mutex_lock(&efx->mac_lock);
+ efx_disable_interrupts(efx);
- efx_fini_channels(efx);
+ mutex_lock(&efx->mac_lock);
if (efx->port_initialized && method != RESET_TYPE_INVISIBLE)
efx->phy_op->fini(efx);
efx->type->fini(efx);
@@ -2077,6 +2359,10 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
EFX_ASSERT_RESET_SERIALISED(efx);
+ if (method == RESET_TYPE_MCDI_TIMEOUT)
+ efx->type->finish_flr(efx);
+
+ /* Ensure that SRAM is initialised even if we're disabling the device */
rc = efx->type->init(efx);
if (rc) {
netif_err(efx, drv, efx->net_dev, "failed to initialise NIC\n");
@@ -2095,10 +2381,11 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
"could not restore PHY settings\n");
}
- efx->mac_op->reconfigure(efx);
-
- efx_init_channels(efx);
+ rc = efx_enable_interrupts(efx);
+ if (rc)
+ goto fail;
efx_restore_filters(efx);
+ efx_sriov_reset(efx);
mutex_unlock(&efx->mac_lock);
@@ -2127,7 +2414,7 @@ int efx_reset(struct efx_nic *efx, enum reset_type method)
netif_info(efx, drv, efx->net_dev, "resetting (%s)\n",
RESET_TYPE(method));
- netif_device_detach(efx->net_dev);
+ efx_device_detach_sync(efx);
efx_reset_down(efx, method);
rc = efx->type->reset(efx, method);
@@ -2139,7 +2426,10 @@ int efx_reset(struct efx_nic *efx, enum reset_type method)
/* Clear flags for the scopes we covered. We assume the NIC and
* driver are now quiescent so that there is no race here.
*/
- efx->reset_pending &= -(1 << (method + 1));
+ if (method < RESET_TYPE_MAX_METHOD)
+ efx->reset_pending &= -(1 << (method + 1));
+ else /* it doesn't fit into the well-ordered scope hierarchy */
+ __clear_bit(method, &efx->reset_pending);
/* Reinitialise bus-mastering, which may have been turned off before
* the reset was scheduled. This is still appropriate, even in the
@@ -2149,7 +2439,9 @@ int efx_reset(struct efx_nic *efx, enum reset_type method)
out:
/* Leave device stopped if necessary */
- disabled = rc || method == RESET_TYPE_DISABLE;
+ disabled = rc ||
+ method == RESET_TYPE_DISABLE ||
+ method == RESET_TYPE_RECOVER_OR_DISABLE;
rc2 = efx_reset_up(efx, method, !disabled);
if (rc2) {
disabled = true;
@@ -2168,27 +2460,82 @@ out:
return rc;
}
+/* Try recovery mechanisms.
+ * For now only EEH is supported.
+ * Returns 0 if the recovery mechanisms are unsuccessful.
+ * Returns a non-zero value otherwise.
+ */
+int efx_try_recovery(struct efx_nic *efx)
+{
+#ifdef CONFIG_EEH
+ /* A PCI error can occur and not be seen by EEH because nothing
+ * happens on the PCI bus. In this case the driver may fail and
+ * schedule a 'recover or reset', leading to this recovery handler.
+ * Manually call the eeh failure check function.
+ */
+ struct eeh_dev *eehdev =
+ of_node_to_eeh_dev(pci_device_to_OF_node(efx->pci_dev));
+
+ if (eeh_dev_check_failure(eehdev)) {
+ /* The EEH mechanisms will handle the error and reset the
+ * device if necessary.
+ */
+ return 1;
+ }
+#endif
+ return 0;
+}
+
+static void efx_wait_for_bist_end(struct efx_nic *efx)
+{
+ int i;
+
+ for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) {
+ if (efx_mcdi_poll_reboot(efx))
+ goto out;
+ msleep(BIST_WAIT_DELAY_MS);
+ }
+
+ netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n");
+out:
+ /* Either way unset the BIST flag. If we found no reboot we probably
+ * won't recover, but we should try.
+ */
+ efx->mc_bist_for_other_fn = false;
+}
+
/* The worker thread exists so that code that cannot sleep can
* schedule a reset for later.
*/
static void efx_reset_work(struct work_struct *data)
{
struct efx_nic *efx = container_of(data, struct efx_nic, reset_work);
- unsigned long pending = ACCESS_ONCE(efx->reset_pending);
+ unsigned long pending;
+ enum reset_type method;
- if (!pending)
+ pending = ACCESS_ONCE(efx->reset_pending);
+ method = fls(pending) - 1;
+
+ if (method == RESET_TYPE_MC_BIST)
+ efx_wait_for_bist_end(efx);
+
+ if ((method == RESET_TYPE_RECOVER_OR_DISABLE ||
+ method == RESET_TYPE_RECOVER_OR_ALL) &&
+ efx_try_recovery(efx))
return;
- /* If we're not RUNNING then don't reset. Leave the reset_pending
- * flags set so that efx_pci_probe_main will be retried */
- if (efx->state != STATE_RUNNING) {
- netif_info(efx, drv, efx->net_dev,
- "scheduled reset quenched. NIC not RUNNING\n");
+ if (!pending)
return;
- }
rtnl_lock();
- (void)efx_reset(efx, fls(pending) - 1);
+
+ /* We checked the state in efx_schedule_reset() but it may
+ * have changed by now. Now that we have the RTNL lock,
+ * it cannot change again.
+ */
+ if (efx->state == STATE_READY)
+ (void)efx_reset(efx, method);
+
rtnl_unlock();
}
@@ -2196,11 +2543,22 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
{
enum reset_type method;
+ if (efx->state == STATE_RECOVERY) {
+ netif_dbg(efx, drv, efx->net_dev,
+ "recovering: skip scheduling %s reset\n",
+ RESET_TYPE(type));
+ return;
+ }
+
switch (type) {
case RESET_TYPE_INVISIBLE:
case RESET_TYPE_ALL:
+ case RESET_TYPE_RECOVER_OR_ALL:
case RESET_TYPE_WORLD:
case RESET_TYPE_DISABLE:
+ case RESET_TYPE_RECOVER_OR_DISABLE:
+ case RESET_TYPE_MC_BIST:
+ case RESET_TYPE_MCDI_TIMEOUT:
method = type;
netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n",
RESET_TYPE(method));
@@ -2214,6 +2572,13 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type)
}
set_bit(method, &efx->reset_pending);
+ smp_mb(); /* ensure we change reset_pending before checking state */
+
+ /* If we're not READY then just leave the flags set as the cue
+ * to abort probing or reschedule the reset later.
+ */
+ if (ACCESS_ONCE(efx->state) != STATE_READY)
+ return;
/* efx_process_channel() will no longer read events once a
* reset is scheduled. So switch back to poll'd MCDI completions. */
@@ -2240,6 +2605,8 @@ static DEFINE_PCI_DEVICE_TABLE(efx_pci_table) = {
.driver_data = (unsigned long) &siena_a0_nic_type},
{PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0813), /* SFL9021 */
.driver_data = (unsigned long) &siena_a0_nic_type},
+ {PCI_DEVICE(PCI_VENDOR_ID_SOLARFLARE, 0x0903), /* SFC9120 PF */
+ .driver_data = (unsigned long) &efx_hunt_a0_nic_type},
{0} /* end of list */
};
@@ -2279,42 +2646,49 @@ static const struct efx_phy_operations efx_dummy_phy_operations = {
/* This zeroes out and then fills in the invariants in a struct
* efx_nic (including all sub-structures).
*/
-static int efx_init_struct(struct efx_nic *efx, const struct efx_nic_type *type,
+static int efx_init_struct(struct efx_nic *efx,
struct pci_dev *pci_dev, struct net_device *net_dev)
{
int i;
/* Initialise common structures */
- memset(efx, 0, sizeof(*efx));
+ INIT_LIST_HEAD(&efx->node);
+ INIT_LIST_HEAD(&efx->secondary_list);
spin_lock_init(&efx->biu_lock);
#ifdef CONFIG_SFC_MTD
INIT_LIST_HEAD(&efx->mtd_list);
#endif
INIT_WORK(&efx->reset_work, efx_reset_work);
INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor);
+ INIT_DELAYED_WORK(&efx->selftest_work, efx_selftest_async_work);
efx->pci_dev = pci_dev;
efx->msg_enable = debug;
- efx->state = STATE_INIT;
+ efx->state = STATE_UNINIT;
strlcpy(efx->name, pci_name(pci_dev), sizeof(efx->name));
efx->net_dev = net_dev;
+ efx->rx_prefix_size = efx->type->rx_prefix_size;
+ efx->rx_ip_align =
+ NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0;
+ efx->rx_packet_hash_offset =
+ efx->type->rx_hash_offset - efx->type->rx_prefix_size;
+ efx->rx_packet_ts_offset =
+ efx->type->rx_ts_offset - efx->type->rx_prefix_size;
spin_lock_init(&efx->stats_lock);
mutex_init(&efx->mac_lock);
- efx->mac_op = type->default_mac_ops;
efx->phy_op = &efx_dummy_phy_operations;
efx->mdio.dev = net_dev;
INIT_WORK(&efx->mac_work, efx_mac_work);
+ init_waitqueue_head(&efx->flush_wq);
for (i = 0; i < EFX_MAX_CHANNELS; i++) {
efx->channel[i] = efx_alloc_channel(efx, i, NULL);
if (!efx->channel[i])
goto fail;
+ efx->msi_context[i].efx = efx;
+ efx->msi_context[i].index = i;
}
- efx->type = type;
-
- EFX_BUG_ON_PARANOID(efx->type->phys_addr_channels > EFX_MAX_CHANNELS);
-
/* Higher numbered interrupt modes are less capable! */
efx->interrupt_mode = max(efx->type->max_interrupt_mode,
interrupt_mode);
@@ -2340,6 +2714,8 @@ static void efx_fini_struct(struct efx_nic *efx)
for (i = 0; i < EFX_MAX_CHANNELS; i++)
kfree(efx->channel[i]);
+ kfree(efx->vpd_sn);
+
if (efx->workqueue) {
destroy_workqueue(efx->workqueue);
efx->workqueue = NULL;
@@ -2357,12 +2733,14 @@ static void efx_fini_struct(struct efx_nic *efx)
*/
static void efx_pci_remove_main(struct efx_nic *efx)
{
-#ifdef CONFIG_RFS_ACCEL
- free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
- efx->net_dev->rx_cpu_rmap = NULL;
-#endif
+ /* Flush reset_work. It can no longer be scheduled since we
+ * are not READY.
+ */
+ BUG_ON(efx->state == STATE_READY);
+ cancel_work_sync(&efx->reset_work);
+
+ efx_disable_interrupts(efx);
efx_nic_fini_interrupt(efx);
- efx_fini_channels(efx);
efx_fini_port(efx);
efx->type->fini(efx);
efx_fini_napi(efx);
@@ -2382,32 +2760,100 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
/* Mark the NIC as fini, then stop the interface */
rtnl_lock();
- efx->state = STATE_FINI;
+ efx_dissociate(efx);
dev_close(efx->net_dev);
-
- /* Allow any queued efx_resets() to complete */
+ efx_disable_interrupts(efx);
rtnl_unlock();
+ efx_sriov_fini(efx);
efx_unregister_netdev(efx);
efx_mtd_remove(efx);
- /* Wait for any scheduled resets to complete. No more will be
- * scheduled from this point because efx_stop_all() has been
- * called, we are no longer registered with driverlink, and
- * the net_device's have been removed. */
- cancel_work_sync(&efx->reset_work);
-
efx_pci_remove_main(efx);
efx_fini_io(efx);
netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n");
- pci_set_drvdata(pci_dev, NULL);
efx_fini_struct(efx);
free_netdev(efx->net_dev);
+
+ pci_disable_pcie_error_reporting(pci_dev);
};
+/* NIC VPD information
+ * Called during probe to display the part number of the
+ * installed NIC. VPD is potentially very large but this should
+ * always appear within the first 512 bytes.
+ */
+#define SFC_VPD_LEN 512
+static void efx_probe_vpd_strings(struct efx_nic *efx)
+{
+ struct pci_dev *dev = efx->pci_dev;
+ char vpd_data[SFC_VPD_LEN];
+ ssize_t vpd_size;
+ int ro_start, ro_size, i, j;
+
+ /* Get the vpd data from the device */
+ vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data);
+ if (vpd_size <= 0) {
+ netif_err(efx, drv, efx->net_dev, "Unable to read VPD\n");
+ return;
+ }
+
+ /* Get the Read only section */
+ ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA);
+ if (ro_start < 0) {
+ netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n");
+ return;
+ }
+
+ ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]);
+ j = ro_size;
+ i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+ if (i + j > vpd_size)
+ j = vpd_size - i;
+
+ /* Get the Part number */
+ i = pci_vpd_find_info_keyword(vpd_data, i, j, "PN");
+ if (i < 0) {
+ netif_err(efx, drv, efx->net_dev, "Part number not found\n");
+ return;
+ }
+
+ j = pci_vpd_info_field_size(&vpd_data[i]);
+ i += PCI_VPD_INFO_FLD_HDR_SIZE;
+ if (i + j > vpd_size) {
+ netif_err(efx, drv, efx->net_dev, "Incomplete part number\n");
+ return;
+ }
+
+ netif_info(efx, drv, efx->net_dev,
+ "Part Number : %.*s\n", j, &vpd_data[i]);
+
+ i = ro_start + PCI_VPD_LRDT_TAG_SIZE;
+ j = ro_size;
+ i = pci_vpd_find_info_keyword(vpd_data, i, j, "SN");
+ if (i < 0) {
+ netif_err(efx, drv, efx->net_dev, "Serial number not found\n");
+ return;
+ }
+
+ j = pci_vpd_info_field_size(&vpd_data[i]);
+ i += PCI_VPD_INFO_FLD_HDR_SIZE;
+ if (i + j > vpd_size) {
+ netif_err(efx, drv, efx->net_dev, "Incomplete serial number\n");
+ return;
+ }
+
+ efx->vpd_sn = kmalloc(j + 1, GFP_KERNEL);
+ if (!efx->vpd_sn)
+ return;
+
+ snprintf(efx->vpd_sn, j + 1, "%s", &vpd_data[i]);
+}
+
+
/* Main body of NIC initialisation
* This is called at module load (or hotplug insertion, theoretically).
*/
@@ -2436,16 +2882,18 @@ static int efx_pci_probe_main(struct efx_nic *efx)
goto fail4;
}
- efx_init_channels(efx);
-
rc = efx_nic_init_interrupt(efx);
if (rc)
goto fail5;
+ rc = efx_enable_interrupts(efx);
+ if (rc)
+ goto fail6;
return 0;
+ fail6:
+ efx_nic_fini_interrupt(efx);
fail5:
- efx_fini_channels(efx);
efx_fini_port(efx);
fail4:
efx->type->fini(efx);
@@ -2459,29 +2907,30 @@ static int efx_pci_probe_main(struct efx_nic *efx)
/* NIC initialisation
*
* This is called at module load (or hotplug insertion,
- * theoretically). It sets up PCI mappings, tests and resets the NIC,
+ * theoretically). It sets up PCI mappings, resets the NIC,
* sets up and registers the network devices with the kernel and hooks
* the interrupt service routine. It does not prepare the device for
* transmission; this is left to the first time one of the network
* interfaces is brought up (i.e. efx_net_open).
*/
-static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
- const struct pci_device_id *entry)
+static int efx_pci_probe(struct pci_dev *pci_dev,
+ const struct pci_device_id *entry)
{
- const struct efx_nic_type *type = (const struct efx_nic_type *) entry->driver_data;
struct net_device *net_dev;
struct efx_nic *efx;
- int i, rc;
+ int rc;
/* Allocate and initialise a struct net_device and struct efx_nic */
net_dev = alloc_etherdev_mqs(sizeof(*efx), EFX_MAX_CORE_TX_QUEUES,
EFX_MAX_RX_QUEUES);
if (!net_dev)
return -ENOMEM;
- net_dev->features |= (type->offload_features | NETIF_F_SG |
+ efx = netdev_priv(net_dev);
+ efx->type = (const struct efx_nic_type *) entry->driver_data;
+ net_dev->features |= (efx->type->offload_features | NETIF_F_SG |
NETIF_F_HIGHDMA | NETIF_F_TSO |
NETIF_F_RXCSUM);
- if (type->offload_features & NETIF_F_V6_CSUM)
+ if (efx->type->offload_features & NETIF_F_V6_CSUM)
net_dev->features |= NETIF_F_TSO6;
/* Mask for features that also apply to VLAN devices */
net_dev->vlan_features |= (NETIF_F_ALL_CSUM | NETIF_F_SG |
@@ -2489,75 +2938,54 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
NETIF_F_RXCSUM);
/* All offloads can be toggled */
net_dev->hw_features = net_dev->features & ~NETIF_F_HIGHDMA;
- efx = netdev_priv(net_dev);
pci_set_drvdata(pci_dev, efx);
SET_NETDEV_DEV(net_dev, &pci_dev->dev);
- rc = efx_init_struct(efx, type, pci_dev, net_dev);
+ rc = efx_init_struct(efx, pci_dev, net_dev);
if (rc)
goto fail1;
netif_info(efx, probe, efx->net_dev,
"Solarflare NIC detected\n");
+ efx_probe_vpd_strings(efx);
+
/* Set up basic I/O (BAR mappings etc) */
rc = efx_init_io(efx);
if (rc)
goto fail2;
- /* No serialisation is required with the reset path because
- * we're in STATE_INIT. */
- for (i = 0; i < 5; i++) {
- rc = efx_pci_probe_main(efx);
-
- /* Serialise against efx_reset(). No more resets will be
- * scheduled since efx_stop_all() has been called, and we
- * have not and never have been registered with either
- * the rtnetlink or driverlink layers. */
- cancel_work_sync(&efx->reset_work);
-
- if (rc == 0) {
- if (efx->reset_pending) {
- /* If there was a scheduled reset during
- * probe, the NIC is probably hosed anyway */
- efx_pci_remove_main(efx);
- rc = -EIO;
- } else {
- break;
- }
- }
-
- /* Retry if a recoverably reset event has been scheduled */
- if (efx->reset_pending &
- ~(1 << RESET_TYPE_INVISIBLE | 1 << RESET_TYPE_ALL) ||
- !efx->reset_pending)
- goto fail3;
-
- efx->reset_pending = 0;
- }
+ rc = efx_pci_probe_main(efx);
+ if (rc)
+ goto fail3;
- if (rc) {
- netif_err(efx, probe, efx->net_dev, "Could not reset NIC\n");
+ rc = efx_register_netdev(efx);
+ if (rc)
goto fail4;
- }
- /* Switch to the running state before we expose the device to the OS,
- * so that dev_open()|efx_start_all() will actually start the device */
- efx->state = STATE_RUNNING;
-
- rc = efx_register_netdev(efx);
+ rc = efx_sriov_init(efx);
if (rc)
- goto fail5;
+ netif_err(efx, probe, efx->net_dev,
+ "SR-IOV can't be enabled rc %d\n", rc);
netif_dbg(efx, probe, efx->net_dev, "initialisation successful\n");
+ /* Try to create MTDs, but allow this to fail */
rtnl_lock();
- efx_mtd_probe(efx); /* allowed to fail */
+ rc = efx_mtd_probe(efx);
rtnl_unlock();
+ if (rc)
+ netif_warn(efx, probe, efx->net_dev,
+ "failed to create MTDs (%d)\n", rc);
+
+ rc = pci_enable_pcie_error_reporting(pci_dev);
+ if (rc && rc != -EINVAL)
+ netif_warn(efx, probe, efx->net_dev,
+ "pci_enable_pcie_error_reporting failed (%d)\n", rc);
+
return 0;
- fail5:
- efx_pci_remove_main(efx);
fail4:
+ efx_pci_remove_main(efx);
fail3:
efx_fini_io(efx);
fail2:
@@ -2573,40 +3001,58 @@ static int efx_pm_freeze(struct device *dev)
{
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
- efx->state = STATE_FINI;
+ rtnl_lock();
+
+ if (efx->state != STATE_DISABLED) {
+ efx->state = STATE_UNINIT;
- netif_device_detach(efx->net_dev);
+ efx_device_detach_sync(efx);
- efx_stop_all(efx);
- efx_fini_channels(efx);
+ efx_stop_all(efx);
+ efx_disable_interrupts(efx);
+ }
+
+ rtnl_unlock();
return 0;
}
static int efx_pm_thaw(struct device *dev)
{
+ int rc;
struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev));
- efx->state = STATE_INIT;
+ rtnl_lock();
+
+ if (efx->state != STATE_DISABLED) {
+ rc = efx_enable_interrupts(efx);
+ if (rc)
+ goto fail;
- efx_init_channels(efx);
+ mutex_lock(&efx->mac_lock);
+ efx->phy_op->reconfigure(efx);
+ mutex_unlock(&efx->mac_lock);
- mutex_lock(&efx->mac_lock);
- efx->phy_op->reconfigure(efx);
- mutex_unlock(&efx->mac_lock);
+ efx_start_all(efx);
- efx_start_all(efx);
+ netif_device_attach(efx->net_dev);
- netif_device_attach(efx->net_dev);
+ efx->state = STATE_READY;
- efx->state = STATE_RUNNING;
+ efx->type->resume_wol(efx);
+ }
- efx->type->resume_wol(efx);
+ rtnl_unlock();
/* Reschedule any quenched resets scheduled during efx_pm_freeze() */
queue_work(reset_workqueue, &efx->reset_work);
return 0;
+
+fail:
+ rtnl_unlock();
+
+ return rc;
}
static int efx_pm_poweroff(struct device *dev)
@@ -2643,8 +3089,8 @@ static int efx_pm_resume(struct device *dev)
rc = efx->type->init(efx);
if (rc)
return rc;
- efx_pm_thaw(dev);
- return 0;
+ rc = efx_pm_thaw(dev);
+ return rc;
}
static int efx_pm_suspend(struct device *dev)
@@ -2658,7 +3104,7 @@ static int efx_pm_suspend(struct device *dev)
return rc;
}
-static struct dev_pm_ops efx_pm_ops = {
+static const struct dev_pm_ops efx_pm_ops = {
.suspend = efx_pm_suspend,
.resume = efx_pm_resume,
.freeze = efx_pm_freeze,
@@ -2667,12 +3113,112 @@ static struct dev_pm_ops efx_pm_ops = {
.restore = efx_pm_resume,
};
+/* A PCI error affecting this device was detected.
+ * At this point MMIO and DMA may be disabled.
+ * Stop the software path and request a slot reset.
+ */
+static pci_ers_result_t efx_io_error_detected(struct pci_dev *pdev,
+ enum pci_channel_state state)
+{
+ pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+ struct efx_nic *efx = pci_get_drvdata(pdev);
+
+ if (state == pci_channel_io_perm_failure)
+ return PCI_ERS_RESULT_DISCONNECT;
+
+ rtnl_lock();
+
+ if (efx->state != STATE_DISABLED) {
+ efx->state = STATE_RECOVERY;
+ efx->reset_pending = 0;
+
+ efx_device_detach_sync(efx);
+
+ efx_stop_all(efx);
+ efx_disable_interrupts(efx);
+
+ status = PCI_ERS_RESULT_NEED_RESET;
+ } else {
+ /* If the interface is disabled we don't want to do anything
+ * with it.
+ */
+ status = PCI_ERS_RESULT_RECOVERED;
+ }
+
+ rtnl_unlock();
+
+ pci_disable_device(pdev);
+
+ return status;
+}
+
+/* Fake a successfull reset, which will be performed later in efx_io_resume. */
+static pci_ers_result_t efx_io_slot_reset(struct pci_dev *pdev)
+{
+ struct efx_nic *efx = pci_get_drvdata(pdev);
+ pci_ers_result_t status = PCI_ERS_RESULT_RECOVERED;
+ int rc;
+
+ if (pci_enable_device(pdev)) {
+ netif_err(efx, hw, efx->net_dev,
+ "Cannot re-enable PCI device after reset.\n");
+ status = PCI_ERS_RESULT_DISCONNECT;
+ }
+
+ rc = pci_cleanup_aer_uncorrect_error_status(pdev);
+ if (rc) {
+ netif_err(efx, hw, efx->net_dev,
+ "pci_cleanup_aer_uncorrect_error_status failed (%d)\n", rc);
+ /* Non-fatal error. Continue. */
+ }
+
+ return status;
+}
+
+/* Perform the actual reset and resume I/O operations. */
+static void efx_io_resume(struct pci_dev *pdev)
+{
+ struct efx_nic *efx = pci_get_drvdata(pdev);
+ int rc;
+
+ rtnl_lock();
+
+ if (efx->state == STATE_DISABLED)
+ goto out;
+
+ rc = efx_reset(efx, RESET_TYPE_ALL);
+ if (rc) {
+ netif_err(efx, hw, efx->net_dev,
+ "efx_reset failed after PCI error (%d)\n", rc);
+ } else {
+ efx->state = STATE_READY;
+ netif_dbg(efx, hw, efx->net_dev,
+ "Done resetting and resuming IO after PCI error.\n");
+ }
+
+out:
+ rtnl_unlock();
+}
+
+/* For simplicity and reliability, we always require a slot reset and try to
+ * reset the hardware when a pci error affecting the device is detected.
+ * We leave both the link_reset and mmio_enabled callback unimplemented:
+ * with our request for slot reset the mmio_enabled callback will never be
+ * called, and the link_reset callback is not used by AER or EEH mechanisms.
+ */
+static struct pci_error_handlers efx_err_handlers = {
+ .error_detected = efx_io_error_detected,
+ .slot_reset = efx_io_slot_reset,
+ .resume = efx_io_resume,
+};
+
static struct pci_driver efx_pci_driver = {
.name = KBUILD_MODNAME,
.id_table = efx_pci_table,
.probe = efx_pci_probe,
.remove = efx_pci_remove,
.driver.pm = &efx_pm_ops,
+ .err_handler = &efx_err_handlers,
};
/**************************************************************************
@@ -2695,6 +3241,10 @@ static int __init efx_init_module(void)
if (rc)
goto err_notifier;
+ rc = efx_init_sriov();
+ if (rc)
+ goto err_sriov;
+
reset_workqueue = create_singlethread_workqueue("sfc_reset");
if (!reset_workqueue) {
rc = -ENOMEM;
@@ -2710,6 +3260,8 @@ static int __init efx_init_module(void)
err_pci:
destroy_workqueue(reset_workqueue);
err_reset:
+ efx_fini_sriov();
+ err_sriov:
unregister_netdevice_notifier(&efx_netdev_notifier);
err_notifier:
return rc;
@@ -2721,6 +3273,7 @@ static void __exit efx_exit_module(void)
pci_unregister_driver(&efx_pci_driver);
destroy_workqueue(reset_workqueue);
+ efx_fini_sriov();
unregister_netdevice_notifier(&efx_netdev_notifier);
}
@@ -2730,6 +3283,6 @@ module_exit(efx_exit_module);
MODULE_AUTHOR("Solarflare Communications and "
"Michael Brown <mbrown@fensystems.co.uk>");
-MODULE_DESCRIPTION("Solarflare Communications network driver");
+MODULE_DESCRIPTION("Solarflare network driver");
MODULE_LICENSE("GPL");
MODULE_DEVICE_TABLE(pci, efx_pci_table);
diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h
index a3541ac6ea0..99032581336 100644
--- a/drivers/net/ethernet/sfc/efx.h
+++ b/drivers/net/ethernet/sfc/efx.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -14,36 +14,40 @@
#include "net_driver.h"
#include "filter.h"
-/* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
+/* All controllers use BAR 0 for I/O space and BAR 2(&3) for memory */
#define EFX_MEM_BAR 2
/* TX */
-extern int efx_probe_tx_queue(struct efx_tx_queue *tx_queue);
-extern void efx_remove_tx_queue(struct efx_tx_queue *tx_queue);
-extern void efx_init_tx_queue(struct efx_tx_queue *tx_queue);
-extern void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue);
-extern void efx_fini_tx_queue(struct efx_tx_queue *tx_queue);
-extern void efx_release_tx_buffers(struct efx_tx_queue *tx_queue);
-extern netdev_tx_t
-efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev);
-extern netdev_tx_t
-efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb);
-extern void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
-extern int efx_setup_tc(struct net_device *net_dev, u8 num_tc);
+int efx_probe_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_remove_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_init_tx_queue(struct efx_tx_queue *tx_queue);
+void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue);
+void efx_fini_tx_queue(struct efx_tx_queue *tx_queue);
+netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
+ struct net_device *net_dev);
+netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb);
+void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index);
+int efx_setup_tc(struct net_device *net_dev, u8 num_tc);
+unsigned int efx_tx_max_skb_descs(struct efx_nic *efx);
+extern unsigned int efx_piobuf_size;
/* RX */
-extern int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
-extern void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
-extern void efx_init_rx_queue(struct efx_rx_queue *rx_queue);
-extern void efx_fini_rx_queue(struct efx_rx_queue *rx_queue);
-extern void efx_rx_strategy(struct efx_channel *channel);
-extern void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue);
-extern void efx_rx_slow_fill(unsigned long context);
-extern void __efx_rx_packet(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf, bool checksummed);
-extern void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
- unsigned int len, bool checksummed, bool discard);
-extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
+void efx_rx_config_page_split(struct efx_nic *efx);
+int efx_probe_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_remove_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_init_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_fini_rx_queue(struct efx_rx_queue *rx_queue);
+void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic);
+void efx_rx_slow_fill(unsigned long context);
+void __efx_rx_packet(struct efx_channel *channel);
+void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
+ unsigned int n_frags, unsigned int len, u16 flags);
+static inline void efx_rx_flush_packet(struct efx_channel *channel)
+{
+ if (channel->rx_pkt_n_frags)
+ __efx_rx_packet(channel);
+}
+void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
#define EFX_MAX_DMAQ_SIZE 4096UL
#define EFX_DEFAULT_DMAQ_SIZE 1024UL
@@ -52,36 +56,106 @@ extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue);
#define EFX_MAX_EVQ_SIZE 16384UL
#define EFX_MIN_EVQ_SIZE 512UL
-/* The smallest [rt]xq_entries that the driver supports. Callers of
- * efx_wake_queue() assume that they can subsequently send at least one
- * skb. Falcon/A1 may require up to three descriptors per skb_frag. */
-#define EFX_MIN_RING_SIZE (roundup_pow_of_two(2 * 3 * MAX_SKB_FRAGS))
+/* Maximum number of TCP segments we support for soft-TSO */
+#define EFX_TSO_MAX_SEGS 100
+
+/* The smallest [rt]xq_entries that the driver supports. RX minimum
+ * is a bit arbitrary. For TX, we must have space for at least 2
+ * TSO skbs.
+ */
+#define EFX_RXQ_MIN_ENT 128U
+#define EFX_TXQ_MIN_ENT(efx) (2 * efx_tx_max_skb_descs(efx))
+
+#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \
+ EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE)
/* Filters */
-extern int efx_probe_filters(struct efx_nic *efx);
-extern void efx_restore_filters(struct efx_nic *efx);
-extern void efx_remove_filters(struct efx_nic *efx);
-extern s32 efx_filter_insert_filter(struct efx_nic *efx,
- struct efx_filter_spec *spec,
- bool replace);
-extern int efx_filter_remove_id_safe(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 filter_id);
-extern int efx_filter_get_filter_safe(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 filter_id, struct efx_filter_spec *);
-extern void efx_filter_clear_rx(struct efx_nic *efx,
- enum efx_filter_priority priority);
-extern u32 efx_filter_count_rx_used(struct efx_nic *efx,
- enum efx_filter_priority priority);
-extern u32 efx_filter_get_rx_id_limit(struct efx_nic *efx);
-extern s32 efx_filter_get_rx_ids(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 *buf, u32 size);
+
+/**
+ * efx_filter_insert_filter - add or replace a filter
+ * @efx: NIC in which to insert the filter
+ * @spec: Specification for the filter
+ * @replace_equal: Flag for whether the specified filter may replace an
+ * existing filter with equal priority
+ *
+ * On success, return the filter ID.
+ * On failure, return a negative error code.
+ *
+ * If existing filters have equal match values to the new filter spec,
+ * then the new filter might replace them or the function might fail,
+ * as follows.
+ *
+ * 1. If the existing filters have lower priority, or @replace_equal
+ * is set and they have equal priority, replace them.
+ *
+ * 2. If the existing filters have higher priority, return -%EPERM.
+ *
+ * 3. If !efx_filter_is_mc_recipient(@spec), or the NIC does not
+ * support delivery to multiple recipients, return -%EEXIST.
+ *
+ * This implies that filters for multiple multicast recipients must
+ * all be inserted with the same priority and @replace_equal = %false.
+ */
+static inline s32 efx_filter_insert_filter(struct efx_nic *efx,
+ struct efx_filter_spec *spec,
+ bool replace_equal)
+{
+ return efx->type->filter_insert(efx, spec, replace_equal);
+}
+
+/**
+ * efx_filter_remove_id_safe - remove a filter by ID, carefully
+ * @efx: NIC from which to remove the filter
+ * @priority: Priority of filter, as passed to @efx_filter_insert_filter
+ * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
+ *
+ * This function will range-check @filter_id, so it is safe to call
+ * with a value passed from userland.
+ */
+static inline int efx_filter_remove_id_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id)
+{
+ return efx->type->filter_remove_safe(efx, priority, filter_id);
+}
+
+/**
+ * efx_filter_get_filter_safe - retrieve a filter by ID, carefully
+ * @efx: NIC from which to remove the filter
+ * @priority: Priority of filter, as passed to @efx_filter_insert_filter
+ * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
+ * @spec: Buffer in which to store filter specification
+ *
+ * This function will range-check @filter_id, so it is safe to call
+ * with a value passed from userland.
+ */
+static inline int
+efx_filter_get_filter_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *spec)
+{
+ return efx->type->filter_get_safe(efx, priority, filter_id, spec);
+}
+
+static inline u32 efx_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ return efx->type->filter_count_rx_used(efx, priority);
+}
+static inline u32 efx_filter_get_rx_id_limit(struct efx_nic *efx)
+{
+ return efx->type->filter_get_rx_id_limit(efx);
+}
+static inline s32 efx_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size)
+{
+ return efx->type->filter_get_rx_ids(efx, priority, buf, size);
+}
#ifdef CONFIG_RFS_ACCEL
-extern int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
- u16 rxq_index, u32 flow_id);
-extern bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota);
+int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+ u16 rxq_index, u32 flow_id);
+bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota);
static inline void efx_filter_rfs_expire(struct efx_channel *channel)
{
if (channel->rfs_filters_added >= 60 &&
@@ -93,42 +167,48 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel)
static inline void efx_filter_rfs_expire(struct efx_channel *channel) {}
#define efx_filter_rfs_enabled() 0
#endif
+bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec);
/* Channels */
-extern void efx_process_channel_now(struct efx_channel *channel);
-extern int
-efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
+int efx_channel_dummy_op_int(struct efx_channel *channel);
+void efx_channel_dummy_op_void(struct efx_channel *channel);
+int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries);
/* Ports */
-extern int efx_reconfigure_port(struct efx_nic *efx);
-extern int __efx_reconfigure_port(struct efx_nic *efx);
+int efx_reconfigure_port(struct efx_nic *efx);
+int __efx_reconfigure_port(struct efx_nic *efx);
/* Ethtool support */
extern const struct ethtool_ops efx_ethtool_ops;
/* Reset handling */
-extern int efx_reset(struct efx_nic *efx, enum reset_type method);
-extern void efx_reset_down(struct efx_nic *efx, enum reset_type method);
-extern int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok);
+int efx_reset(struct efx_nic *efx, enum reset_type method);
+void efx_reset_down(struct efx_nic *efx, enum reset_type method);
+int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok);
+int efx_try_recovery(struct efx_nic *efx);
/* Global */
-extern void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
-extern int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
- unsigned int rx_usecs, bool rx_adaptive,
- bool rx_may_override_tx);
-extern void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
- unsigned int *rx_usecs, bool *rx_adaptive);
+void efx_schedule_reset(struct efx_nic *efx, enum reset_type type);
+int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs,
+ unsigned int rx_usecs, bool rx_adaptive,
+ bool rx_may_override_tx);
+void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
+ unsigned int *rx_usecs, bool *rx_adaptive);
/* Dummy PHY ops for PHY drivers */
-extern int efx_port_dummy_op_int(struct efx_nic *efx);
-extern void efx_port_dummy_op_void(struct efx_nic *efx);
-
+int efx_port_dummy_op_int(struct efx_nic *efx);
+void efx_port_dummy_op_void(struct efx_nic *efx);
/* MTD */
#ifdef CONFIG_SFC_MTD
-extern int efx_mtd_probe(struct efx_nic *efx);
-extern void efx_mtd_rename(struct efx_nic *efx);
-extern void efx_mtd_remove(struct efx_nic *efx);
+int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts,
+ size_t n_parts, size_t sizeof_part);
+static inline int efx_mtd_probe(struct efx_nic *efx)
+{
+ return efx->type->mtd_probe(efx);
+}
+void efx_mtd_rename(struct efx_nic *efx);
+void efx_mtd_remove(struct efx_nic *efx);
#else
static inline int efx_mtd_probe(struct efx_nic *efx) { return 0; }
static inline void efx_mtd_rename(struct efx_nic *efx) {}
@@ -140,13 +220,31 @@ static inline void efx_schedule_channel(struct efx_channel *channel)
netif_vdbg(channel->efx, intr, channel->efx->net_dev,
"channel %d scheduling NAPI poll on CPU%d\n",
channel->channel, raw_smp_processor_id());
- channel->work_pending = true;
napi_schedule(&channel->napi_str);
}
-extern void efx_link_status_changed(struct efx_nic *efx);
-extern void efx_link_set_advertising(struct efx_nic *efx, u32);
-extern void efx_link_set_wanted_fc(struct efx_nic *efx, u8);
+static inline void efx_schedule_channel_irq(struct efx_channel *channel)
+{
+ channel->event_test_cpu = raw_smp_processor_id();
+ efx_schedule_channel(channel);
+}
+
+void efx_link_status_changed(struct efx_nic *efx);
+void efx_link_set_advertising(struct efx_nic *efx, u32);
+void efx_link_set_wanted_fc(struct efx_nic *efx, u8);
+
+static inline void efx_device_detach_sync(struct efx_nic *efx)
+{
+ struct net_device *dev = efx->net_dev;
+
+ /* Lock/freeze all TX queues so that we can be sure the
+ * TX scheduler is stopped when we're done and before
+ * netif_device_present() becomes false.
+ */
+ netif_tx_lock_bh(dev);
+ netif_device_detach(dev);
+ netif_tx_unlock_bh(dev);
+}
#endif /* EFX_EFX_H */
diff --git a/drivers/net/ethernet/sfc/enum.h b/drivers/net/ethernet/sfc/enum.h
index d725a8fbe1a..d1dbb5fb31b 100644
--- a/drivers/net/ethernet/sfc/enum.h
+++ b/drivers/net/ethernet/sfc/enum.h
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007-2009 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2007-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -136,31 +136,45 @@ enum efx_loopback_mode {
*
* Reset methods are numbered in order of increasing scope.
*
- * @RESET_TYPE_INVISIBLE: don't reset the PHYs or interrupts
- * @RESET_TYPE_ALL: reset everything but PCI core blocks
- * @RESET_TYPE_WORLD: reset everything, save & restore PCI config
- * @RESET_TYPE_DISABLE: disable NIC
+ * @RESET_TYPE_INVISIBLE: Reset datapath and MAC (Falcon only)
+ * @RESET_TYPE_RECOVER_OR_ALL: Try to recover. Apply RESET_TYPE_ALL
+ * if unsuccessful.
+ * @RESET_TYPE_ALL: Reset datapath, MAC and PHY
+ * @RESET_TYPE_WORLD: Reset as much as possible
+ * @RESET_TYPE_RECOVER_OR_DISABLE: Try to recover. Apply RESET_TYPE_DISABLE if
+ * unsuccessful.
+ * @RESET_TYPE_MC_BIST: MC entering BIST mode.
+ * @RESET_TYPE_DISABLE: Reset datapath, MAC and PHY; leave NIC disabled
* @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog
* @RESET_TYPE_INT_ERROR: reset due to internal error
* @RESET_TYPE_RX_RECOVERY: reset to recover from RX datapath errors
- * @RESET_TYPE_RX_DESC_FETCH: pcie error during rx descriptor fetch
- * @RESET_TYPE_TX_DESC_FETCH: pcie error during tx descriptor fetch
+ * @RESET_TYPE_DMA_ERROR: DMA error
* @RESET_TYPE_TX_SKIP: hardware completed empty tx descriptors
* @RESET_TYPE_MC_FAILURE: MC reboot/assertion
+ * @RESET_TYPE_MCDI_TIMEOUT: MCDI timeout.
*/
enum reset_type {
- RESET_TYPE_INVISIBLE = 0,
- RESET_TYPE_ALL = 1,
- RESET_TYPE_WORLD = 2,
- RESET_TYPE_DISABLE = 3,
+ RESET_TYPE_INVISIBLE,
+ RESET_TYPE_RECOVER_OR_ALL,
+ RESET_TYPE_ALL,
+ RESET_TYPE_WORLD,
+ RESET_TYPE_RECOVER_OR_DISABLE,
+ RESET_TYPE_MC_BIST,
+ RESET_TYPE_DISABLE,
RESET_TYPE_MAX_METHOD,
RESET_TYPE_TX_WATCHDOG,
RESET_TYPE_INT_ERROR,
RESET_TYPE_RX_RECOVERY,
- RESET_TYPE_RX_DESC_FETCH,
- RESET_TYPE_TX_DESC_FETCH,
+ RESET_TYPE_DMA_ERROR,
RESET_TYPE_TX_SKIP,
RESET_TYPE_MC_FAILURE,
+ /* RESET_TYPE_MCDI_TIMEOUT is actually a method, not just a reason, but
+ * it doesn't fit the scope hierarchy (not well-ordered by inclusion).
+ * We encode this by having its enum value be greater than
+ * RESET_TYPE_MAX_METHOD. This also prevents issuing it with
+ * efx_ioctl_reset.
+ */
+ RESET_TYPE_MCDI_TIMEOUT,
RESET_TYPE_MAX,
};
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 29b2ebfef19..74739c4b999 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -19,14 +19,9 @@
#include "filter.h"
#include "nic.h"
-struct ethtool_string {
- char name[ETH_GSTRING_LEN];
-};
-
-struct efx_ethtool_stat {
+struct efx_sw_stat_desc {
const char *name;
enum {
- EFX_ETHTOOL_STAT_SOURCE_mac_stats,
EFX_ETHTOOL_STAT_SOURCE_nic,
EFX_ETHTOOL_STAT_SOURCE_channel,
EFX_ETHTOOL_STAT_SOURCE_tx_queue
@@ -35,7 +30,7 @@ struct efx_ethtool_stat {
u64(*get_stat) (void *field); /* Reader function */
};
-/* Initialiser for a struct #efx_ethtool_stat with type-checking */
+/* Initialiser for a struct efx_sw_stat_desc with type-checking */
#define EFX_ETHTOOL_STAT(stat_name, source_name, field, field_type, \
get_stat_function) { \
.name = #stat_name, \
@@ -52,33 +47,11 @@ static u64 efx_get_uint_stat(void *field)
return *(unsigned int *)field;
}
-static u64 efx_get_ulong_stat(void *field)
-{
- return *(unsigned long *)field;
-}
-
-static u64 efx_get_u64_stat(void *field)
-{
- return *(u64 *) field;
-}
-
static u64 efx_get_atomic_stat(void *field)
{
return atomic_read((atomic_t *) field);
}
-#define EFX_ETHTOOL_ULONG_MAC_STAT(field) \
- EFX_ETHTOOL_STAT(field, mac_stats, field, \
- unsigned long, efx_get_ulong_stat)
-
-#define EFX_ETHTOOL_U64_MAC_STAT(field) \
- EFX_ETHTOOL_STAT(field, mac_stats, field, \
- u64, efx_get_u64_stat)
-
-#define EFX_ETHTOOL_UINT_NIC_STAT(name) \
- EFX_ETHTOOL_STAT(name, nic, n_##name, \
- unsigned int, efx_get_uint_stat)
-
#define EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(field) \
EFX_ETHTOOL_STAT(field, nic, field, \
atomic_t, efx_get_atomic_stat)
@@ -91,82 +64,25 @@ static u64 efx_get_atomic_stat(void *field)
EFX_ETHTOOL_STAT(tx_##field, tx_queue, field, \
unsigned int, efx_get_uint_stat)
-static struct efx_ethtool_stat efx_ethtool_stats[] = {
- EFX_ETHTOOL_U64_MAC_STAT(tx_bytes),
- EFX_ETHTOOL_U64_MAC_STAT(tx_good_bytes),
- EFX_ETHTOOL_U64_MAC_STAT(tx_bad_bytes),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_packets),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_bad),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_pause),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_control),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_unicast),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_multicast),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_broadcast),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_lt64),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_64),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_65_to_127),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_128_to_255),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_256_to_511),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_512_to_1023),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_1024_to_15xx),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_15xx_to_jumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_gtjumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_collision),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_single_collision),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_multiple_collision),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_excessive_collision),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_deferred),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_late_collision),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_excessive_deferred),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_non_tcpudp),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_mac_src_error),
- EFX_ETHTOOL_ULONG_MAC_STAT(tx_ip_src_error),
+static const struct efx_sw_stat_desc efx_sw_stat_desc[] = {
+ EFX_ETHTOOL_UINT_TXQ_STAT(merge_events),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_bursts),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers),
EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets),
EFX_ETHTOOL_UINT_TXQ_STAT(pushes),
- EFX_ETHTOOL_U64_MAC_STAT(rx_bytes),
- EFX_ETHTOOL_U64_MAC_STAT(rx_good_bytes),
- EFX_ETHTOOL_U64_MAC_STAT(rx_bad_bytes),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_packets),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_good),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_bad),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_pause),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_control),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_unicast),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_multicast),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_broadcast),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_lt64),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_64),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_65_to_127),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_128_to_255),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_256_to_511),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_512_to_1023),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_1024_to_15xx),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_15xx_to_jumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_gtjumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_bad_lt64),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_bad_64_to_15xx),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_bad_15xx_to_jumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_bad_gtjumbo),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_overflow),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_missed),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_false_carrier),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_symbol_error),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_align_error),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_length_error),
- EFX_ETHTOOL_ULONG_MAC_STAT(rx_internal_error),
- EFX_ETHTOOL_UINT_NIC_STAT(rx_nodesc_drop_cnt),
+ EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets),
EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tcp_udp_chksum_err),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_mcast_mismatch),
EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_frm_trunc),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_nodesc_trunc),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_events),
+ EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_merge_packets),
};
-/* Number of ethtool statistics */
-#define EFX_ETHTOOL_NUM_STATS ARRAY_SIZE(efx_ethtool_stats)
+#define EFX_ETHTOOL_SW_STAT_COUNT ARRAY_SIZE(efx_sw_stat_desc)
#define EFX_ETHTOOL_EEPROM_MAGIC 0xEFAB
@@ -213,8 +129,6 @@ static int efx_ethtool_get_settings(struct net_device *net_dev,
efx->phy_op->get_settings(efx, ecmd);
mutex_unlock(&efx->mac_lock);
- /* GMAC does not support 1000Mbps HD */
- ecmd->supported &= ~SUPPORTED_1000baseT_Half;
/* Both MACs support pause frames (bidirectional and respond-only) */
ecmd->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
@@ -299,12 +213,11 @@ static void efx_ethtool_set_msglevel(struct net_device *net_dev, u32 msg_enable)
*
* Fill in an individual self-test entry.
*/
-static void efx_fill_test(unsigned int test_index,
- struct ethtool_string *strings, u64 *data,
+static void efx_fill_test(unsigned int test_index, u8 *strings, u64 *data,
int *test, const char *unit_format, int unit_id,
const char *test_format, const char *test_id)
{
- struct ethtool_string unit_str, test_str;
+ char unit_str[ETH_GSTRING_LEN], test_str[ETH_GSTRING_LEN];
/* Fill data value, if applicable */
if (data)
@@ -313,15 +226,14 @@ static void efx_fill_test(unsigned int test_index,
/* Fill string, if applicable */
if (strings) {
if (strchr(unit_format, '%'))
- snprintf(unit_str.name, sizeof(unit_str.name),
+ snprintf(unit_str, sizeof(unit_str),
unit_format, unit_id);
else
- strcpy(unit_str.name, unit_format);
- snprintf(test_str.name, sizeof(test_str.name),
- test_format, test_id);
- snprintf(strings[test_index].name,
- sizeof(strings[test_index].name),
- "%-6s %-24s", unit_str.name, test_str.name);
+ strcpy(unit_str, unit_format);
+ snprintf(test_str, sizeof(test_str), test_format, test_id);
+ snprintf(strings + test_index * ETH_GSTRING_LEN,
+ ETH_GSTRING_LEN,
+ "%-6s %-24s", unit_str, test_str);
}
}
@@ -339,14 +251,18 @@ static void efx_fill_test(unsigned int test_index,
* @test_index: Starting index of the test
* @strings: Ethtool strings, or %NULL
* @data: Ethtool test results, or %NULL
+ *
+ * Fill in a block of loopback self-test entries. Return new test
+ * index.
*/
static int efx_fill_loopback_test(struct efx_nic *efx,
struct efx_loopback_self_tests *lb_tests,
enum efx_loopback_mode mode,
unsigned int test_index,
- struct ethtool_string *strings, u64 *data)
+ u8 *strings, u64 *data)
{
- struct efx_channel *channel = efx_get_channel(efx, 0);
+ struct efx_channel *channel =
+ efx_get_channel(efx, efx->tx_channel_offset);
struct efx_tx_queue *tx_queue;
efx_for_each_channel_tx_queue(tx_queue, channel) {
@@ -377,11 +293,16 @@ static int efx_fill_loopback_test(struct efx_nic *efx,
* @tests: Efx self-test results structure, or %NULL
* @strings: Ethtool strings, or %NULL
* @data: Ethtool test results, or %NULL
+ *
+ * Get self-test number of strings, strings, and/or test results.
+ * Return number of strings (== number of test results).
+ *
+ * The reason for merging these three functions is to make sure that
+ * they can never be inconsistent.
*/
static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
struct efx_self_tests *tests,
- struct ethtool_string *strings,
- u64 *data)
+ u8 *strings, u64 *data)
{
struct efx_channel *channel;
unsigned int n = 0, i;
@@ -404,12 +325,10 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
&tests->eventq_int[channel->channel],
EFX_CHANNEL_NAME(channel),
"eventq.int", NULL);
- efx_fill_test(n++, strings, data,
- &tests->eventq_poll[channel->channel],
- EFX_CHANNEL_NAME(channel),
- "eventq.poll", NULL);
}
+ efx_fill_test(n++, strings, data, &tests->memory,
+ "core", 0, "memory", NULL);
efx_fill_test(n++, strings, data, &tests->registers,
"core", 0, "registers", NULL);
@@ -444,12 +363,15 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx,
static int efx_ethtool_get_sset_count(struct net_device *net_dev,
int string_set)
{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
switch (string_set) {
case ETH_SS_STATS:
- return EFX_ETHTOOL_NUM_STATS;
+ return efx->type->describe_stats(efx, NULL) +
+ EFX_ETHTOOL_SW_STAT_COUNT +
+ efx_ptp_describe_stats(efx, NULL);
case ETH_SS_TEST:
- return efx_ethtool_fill_self_tests(netdev_priv(net_dev),
- NULL, NULL, NULL);
+ return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL);
default:
return -EINVAL;
}
@@ -459,20 +381,20 @@ static void efx_ethtool_get_strings(struct net_device *net_dev,
u32 string_set, u8 *strings)
{
struct efx_nic *efx = netdev_priv(net_dev);
- struct ethtool_string *ethtool_strings =
- (struct ethtool_string *)strings;
int i;
switch (string_set) {
case ETH_SS_STATS:
- for (i = 0; i < EFX_ETHTOOL_NUM_STATS; i++)
- strncpy(ethtool_strings[i].name,
- efx_ethtool_stats[i].name,
- sizeof(ethtool_strings[i].name));
+ strings += (efx->type->describe_stats(efx, strings) *
+ ETH_GSTRING_LEN);
+ for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++)
+ strlcpy(strings + i * ETH_GSTRING_LEN,
+ efx_sw_stat_desc[i].name, ETH_GSTRING_LEN);
+ strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN;
+ efx_ptp_describe_stats(efx, strings);
break;
case ETH_SS_TEST:
- efx_ethtool_fill_self_tests(efx, NULL,
- ethtool_strings, NULL);
+ efx_ethtool_fill_self_tests(efx, NULL, strings, NULL);
break;
default:
/* No other string sets */
@@ -485,26 +407,20 @@ static void efx_ethtool_get_stats(struct net_device *net_dev,
u64 *data)
{
struct efx_nic *efx = netdev_priv(net_dev);
- struct efx_mac_stats *mac_stats = &efx->mac_stats;
- struct efx_ethtool_stat *stat;
+ const struct efx_sw_stat_desc *stat;
struct efx_channel *channel;
struct efx_tx_queue *tx_queue;
- struct rtnl_link_stats64 temp;
int i;
- EFX_BUG_ON_PARANOID(stats->n_stats != EFX_ETHTOOL_NUM_STATS);
+ spin_lock_bh(&efx->stats_lock);
- /* Update MAC and NIC statistics */
- dev_get_stats(net_dev, &temp);
+ /* Get NIC statistics */
+ data += efx->type->update_stats(efx, data, NULL);
- /* Fill detailed statistics buffer */
- for (i = 0; i < EFX_ETHTOOL_NUM_STATS; i++) {
- stat = &efx_ethtool_stats[i];
+ /* Get software statistics */
+ for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) {
+ stat = &efx_sw_stat_desc[i];
switch (stat->source) {
- case EFX_ETHTOOL_STAT_SOURCE_mac_stats:
- data[i] = stat->get_stat((void *)mac_stats +
- stat->offset);
- break;
case EFX_ETHTOOL_STAT_SOURCE_nic:
data[i] = stat->get_stat((void *)efx + stat->offset);
break;
@@ -525,6 +441,11 @@ static void efx_ethtool_get_stats(struct net_device *net_dev,
break;
}
}
+ data += EFX_ETHTOOL_SW_STAT_COUNT;
+
+ spin_unlock_bh(&efx->stats_lock);
+
+ efx_ptp_update_stats(efx, data);
}
static void efx_ethtool_self_test(struct net_device *net_dev,
@@ -532,18 +453,16 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_self_tests *efx_tests;
- int already_up;
+ bool already_up;
int rc = -ENOMEM;
efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL);
if (!efx_tests)
goto fail;
-
- ASSERT_RTNL();
- if (efx->state != STATE_RUNNING) {
- rc = -EIO;
- goto fail1;
+ if (efx->state != STATE_READY) {
+ rc = -EBUSY;
+ goto out;
}
netif_info(efx, drv, efx->net_dev, "starting %sline testing\n",
@@ -556,7 +475,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
if (rc) {
netif_err(efx, drv, efx->net_dev,
"failed opening device.\n");
- goto fail1;
+ goto out;
}
}
@@ -569,8 +488,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev,
rc == 0 ? "passed" : "failed",
(test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on");
-fail1:
- /* Fill ethtool results structures */
+out:
efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data);
kfree(efx_tests);
fail:
@@ -681,7 +599,7 @@ static void efx_ethtool_get_ringparam(struct net_device *net_dev,
struct efx_nic *efx = netdev_priv(net_dev);
ring->rx_max_pending = EFX_MAX_DMAQ_SIZE;
- ring->tx_max_pending = EFX_MAX_DMAQ_SIZE;
+ ring->tx_max_pending = EFX_TXQ_MAX_ENT(efx);
ring->rx_pending = efx->rxq_entries;
ring->tx_pending = efx->txq_entries;
}
@@ -690,21 +608,27 @@ static int efx_ethtool_set_ringparam(struct net_device *net_dev,
struct ethtool_ringparam *ring)
{
struct efx_nic *efx = netdev_priv(net_dev);
+ u32 txq_entries;
if (ring->rx_mini_pending || ring->rx_jumbo_pending ||
ring->rx_pending > EFX_MAX_DMAQ_SIZE ||
- ring->tx_pending > EFX_MAX_DMAQ_SIZE)
+ ring->tx_pending > EFX_TXQ_MAX_ENT(efx))
return -EINVAL;
- if (ring->rx_pending < EFX_MIN_RING_SIZE ||
- ring->tx_pending < EFX_MIN_RING_SIZE) {
+ if (ring->rx_pending < EFX_RXQ_MIN_ENT) {
netif_err(efx, drv, efx->net_dev,
- "TX and RX queues cannot be smaller than %ld\n",
- EFX_MIN_RING_SIZE);
+ "RX queues cannot be smaller than %u\n",
+ EFX_RXQ_MIN_ENT);
return -EINVAL;
}
- return efx_realloc_channels(efx, ring->rx_pending, ring->tx_pending);
+ txq_entries = max(ring->tx_pending, EFX_TXQ_MIN_ENT(efx));
+ if (txq_entries != ring->tx_pending)
+ netif_warn(efx, drv, efx->net_dev,
+ "increasing TX queue size to minimum of %u\n",
+ txq_entries);
+
+ return efx_realloc_channels(efx, ring->rx_pending, txq_entries);
}
static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
@@ -713,7 +637,6 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
struct efx_nic *efx = netdev_priv(net_dev);
u8 wanted_fc, old_fc;
u32 old_adv;
- bool reset;
int rc = 0;
mutex_lock(&efx->mac_lock);
@@ -736,24 +659,10 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
goto out;
}
- /* TX flow control may automatically turn itself off if the
- * link partner (intermittently) stops responding to pause
- * frames. There isn't any indication that this has happened,
- * so the best we do is leave it up to the user to spot this
- * and fix it be cycling transmit flow control on this end. */
- reset = (wanted_fc & EFX_FC_TX) && !(efx->wanted_fc & EFX_FC_TX);
- if (EFX_WORKAROUND_11482(efx) && reset) {
- if (efx_nic_rev(efx) == EFX_REV_FALCON_B0) {
- /* Recover by resetting the EM block */
- falcon_stop_nic_stats(efx);
- falcon_drain_tx_fifo(efx);
- efx->mac_op->reconfigure(efx);
- falcon_start_nic_stats(efx);
- } else {
- /* Schedule a reset to recover */
- efx_schedule_reset(efx, RESET_TYPE_INVISIBLE);
- }
- }
+ /* Hook for Falcon bug 11482 workaround */
+ if (efx->type->prepare_enable_fc_tx &&
+ (wanted_fc & EFX_FC_TX) && !(efx->wanted_fc & EFX_FC_TX))
+ efx->type->prepare_enable_fc_tx(efx);
old_adv = efx->link_advertising;
old_fc = efx->wanted_fc;
@@ -772,7 +681,7 @@ static int efx_ethtool_set_pauseparam(struct net_device *net_dev,
/* Reconfigure the MAC. The PHY *may* generate a link state change event
* if the user just changed the advertised capabilities, but there's no
* harm doing this twice */
- efx->mac_op->reconfigure(efx);
+ efx->type->reconfigure_mac(efx);
out:
mutex_unlock(&efx->mac_lock);
@@ -790,7 +699,6 @@ static void efx_ethtool_get_pauseparam(struct net_device *net_dev,
pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO);
}
-
static void efx_ethtool_get_wol(struct net_device *net_dev,
struct ethtool_wolinfo *wol)
{
@@ -818,14 +726,21 @@ static int efx_ethtool_reset(struct net_device *net_dev, u32 *flags)
return efx_reset(efx, rc);
}
+/* MAC address mask including only I/G bit */
+static const u8 mac_addr_ig_mask[ETH_ALEN] __aligned(2) = {0x01, 0, 0, 0, 0, 0};
+
+#define IP4_ADDR_FULL_MASK ((__force __be32)~0)
+#define PORT_FULL_MASK ((__force __be16)~0)
+#define ETHER_TYPE_FULL_MASK ((__force __be16)~0)
+
static int efx_ethtool_get_class_rule(struct efx_nic *efx,
struct ethtool_rx_flow_spec *rule)
{
struct ethtool_tcpip4_spec *ip_entry = &rule->h_u.tcp_ip4_spec;
struct ethtool_tcpip4_spec *ip_mask = &rule->m_u.tcp_ip4_spec;
+ struct ethhdr *mac_entry = &rule->h_u.ether_spec;
+ struct ethhdr *mac_mask = &rule->m_u.ether_spec;
struct efx_filter_spec spec;
- u16 vid;
- u8 proto;
int rc;
rc = efx_filter_get_filter_safe(efx, EFX_FILTER_PRI_MANUAL,
@@ -833,37 +748,72 @@ static int efx_ethtool_get_class_rule(struct efx_nic *efx,
if (rc)
return rc;
- if (spec.dmaq_id == 0xfff)
+ if (spec.dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP)
rule->ring_cookie = RX_CLS_FLOW_DISC;
else
rule->ring_cookie = spec.dmaq_id;
- rc = efx_filter_get_eth_local(&spec, &vid,
- rule->h_u.ether_spec.h_dest);
- if (rc == 0) {
+ if ((spec.match_flags & EFX_FILTER_MATCH_ETHER_TYPE) &&
+ spec.ether_type == htons(ETH_P_IP) &&
+ (spec.match_flags & EFX_FILTER_MATCH_IP_PROTO) &&
+ (spec.ip_proto == IPPROTO_TCP || spec.ip_proto == IPPROTO_UDP) &&
+ !(spec.match_flags &
+ ~(EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_OUTER_VID |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_REM_HOST |
+ EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_PORT | EFX_FILTER_MATCH_REM_PORT))) {
+ rule->flow_type = ((spec.ip_proto == IPPROTO_TCP) ?
+ TCP_V4_FLOW : UDP_V4_FLOW);
+ if (spec.match_flags & EFX_FILTER_MATCH_LOC_HOST) {
+ ip_entry->ip4dst = spec.loc_host[0];
+ ip_mask->ip4dst = IP4_ADDR_FULL_MASK;
+ }
+ if (spec.match_flags & EFX_FILTER_MATCH_REM_HOST) {
+ ip_entry->ip4src = spec.rem_host[0];
+ ip_mask->ip4src = IP4_ADDR_FULL_MASK;
+ }
+ if (spec.match_flags & EFX_FILTER_MATCH_LOC_PORT) {
+ ip_entry->pdst = spec.loc_port;
+ ip_mask->pdst = PORT_FULL_MASK;
+ }
+ if (spec.match_flags & EFX_FILTER_MATCH_REM_PORT) {
+ ip_entry->psrc = spec.rem_port;
+ ip_mask->psrc = PORT_FULL_MASK;
+ }
+ } else if (!(spec.match_flags &
+ ~(EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG |
+ EFX_FILTER_MATCH_REM_MAC | EFX_FILTER_MATCH_ETHER_TYPE |
+ EFX_FILTER_MATCH_OUTER_VID))) {
rule->flow_type = ETHER_FLOW;
- memset(rule->m_u.ether_spec.h_dest, ~0, ETH_ALEN);
- if (vid != EFX_FILTER_VID_UNSPEC) {
- rule->flow_type |= FLOW_EXT;
- rule->h_ext.vlan_tci = htons(vid);
- rule->m_ext.vlan_tci = htons(0xfff);
+ if (spec.match_flags &
+ (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG)) {
+ ether_addr_copy(mac_entry->h_dest, spec.loc_mac);
+ if (spec.match_flags & EFX_FILTER_MATCH_LOC_MAC)
+ eth_broadcast_addr(mac_mask->h_dest);
+ else
+ ether_addr_copy(mac_mask->h_dest,
+ mac_addr_ig_mask);
}
- return 0;
+ if (spec.match_flags & EFX_FILTER_MATCH_REM_MAC) {
+ ether_addr_copy(mac_entry->h_source, spec.rem_mac);
+ eth_broadcast_addr(mac_mask->h_source);
+ }
+ if (spec.match_flags & EFX_FILTER_MATCH_ETHER_TYPE) {
+ mac_entry->h_proto = spec.ether_type;
+ mac_mask->h_proto = ETHER_TYPE_FULL_MASK;
+ }
+ } else {
+ /* The above should handle all filters that we insert */
+ WARN_ON(1);
+ return -EINVAL;
}
- rc = efx_filter_get_ipv4_local(&spec, &proto,
- &ip_entry->ip4dst, &ip_entry->pdst);
- if (rc != 0) {
- rc = efx_filter_get_ipv4_full(
- &spec, &proto, &ip_entry->ip4src, &ip_entry->psrc,
- &ip_entry->ip4dst, &ip_entry->pdst);
- EFX_WARN_ON_PARANOID(rc);
- ip_mask->ip4src = ~0;
- ip_mask->psrc = ~0;
+ if (spec.match_flags & EFX_FILTER_MATCH_OUTER_VID) {
+ rule->flow_type |= FLOW_EXT;
+ rule->h_ext.vlan_tci = spec.outer_vid;
+ rule->m_ext.vlan_tci = htons(0xfff);
}
- rule->flow_type = (proto == IPPROTO_TCP) ? TCP_V4_FLOW : UDP_V4_FLOW;
- ip_mask->ip4dst = ~0;
- ip_mask->pdst = ~0;
+
return rc;
}
@@ -954,9 +904,7 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
int rc;
/* Check that user wants us to choose the location */
- if (rule->location != RX_CLS_LOC_ANY &&
- rule->location != RX_CLS_LOC_FIRST &&
- rule->location != RX_CLS_LOC_LAST)
+ if (rule->location != RX_CLS_LOC_ANY)
return -EINVAL;
/* Range-check ring_cookie */
@@ -966,77 +914,87 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx,
/* Check for unsupported extensions */
if ((rule->flow_type & FLOW_EXT) &&
- (rule->m_ext.vlan_etype | rule->m_ext.data[0] |
+ (rule->m_ext.vlan_etype || rule->m_ext.data[0] ||
rule->m_ext.data[1]))
return -EINVAL;
efx_filter_init_rx(&spec, EFX_FILTER_PRI_MANUAL,
- (rule->location == RX_CLS_LOC_FIRST) ?
- EFX_FILTER_FLAG_RX_OVERRIDE_IP : 0,
+ efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
(rule->ring_cookie == RX_CLS_FLOW_DISC) ?
- 0xfff : rule->ring_cookie);
+ EFX_FILTER_RX_DMAQ_ID_DROP : rule->ring_cookie);
- switch (rule->flow_type) {
+ switch (rule->flow_type & ~FLOW_EXT) {
case TCP_V4_FLOW:
- case UDP_V4_FLOW: {
- u8 proto = (rule->flow_type == TCP_V4_FLOW ?
- IPPROTO_TCP : IPPROTO_UDP);
-
- /* Must match all of destination, */
- if ((__force u32)~ip_mask->ip4dst |
- (__force u16)~ip_mask->pdst)
- return -EINVAL;
- /* all or none of source, */
- if ((ip_mask->ip4src | ip_mask->psrc) &&
- ((__force u32)~ip_mask->ip4src |
- (__force u16)~ip_mask->psrc))
- return -EINVAL;
- /* and nothing else */
- if (ip_mask->tos | rule->m_ext.vlan_tci)
+ case UDP_V4_FLOW:
+ spec.match_flags = (EFX_FILTER_MATCH_ETHER_TYPE |
+ EFX_FILTER_MATCH_IP_PROTO);
+ spec.ether_type = htons(ETH_P_IP);
+ spec.ip_proto = ((rule->flow_type & ~FLOW_EXT) == TCP_V4_FLOW ?
+ IPPROTO_TCP : IPPROTO_UDP);
+ if (ip_mask->ip4dst) {
+ if (ip_mask->ip4dst != IP4_ADDR_FULL_MASK)
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_LOC_HOST;
+ spec.loc_host[0] = ip_entry->ip4dst;
+ }
+ if (ip_mask->ip4src) {
+ if (ip_mask->ip4src != IP4_ADDR_FULL_MASK)
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_REM_HOST;
+ spec.rem_host[0] = ip_entry->ip4src;
+ }
+ if (ip_mask->pdst) {
+ if (ip_mask->pdst != PORT_FULL_MASK)
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_LOC_PORT;
+ spec.loc_port = ip_entry->pdst;
+ }
+ if (ip_mask->psrc) {
+ if (ip_mask->psrc != PORT_FULL_MASK)
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_REM_PORT;
+ spec.rem_port = ip_entry->psrc;
+ }
+ if (ip_mask->tos)
return -EINVAL;
-
- if (ip_mask->ip4src)
- rc = efx_filter_set_ipv4_full(&spec, proto,
- ip_entry->ip4dst,
- ip_entry->pdst,
- ip_entry->ip4src,
- ip_entry->psrc);
- else
- rc = efx_filter_set_ipv4_local(&spec, proto,
- ip_entry->ip4dst,
- ip_entry->pdst);
- if (rc)
- return rc;
break;
- }
- case ETHER_FLOW | FLOW_EXT:
- /* Must match all or none of VID */
- if (rule->m_ext.vlan_tci != htons(0xfff) &&
- rule->m_ext.vlan_tci != 0)
- return -EINVAL;
case ETHER_FLOW:
- /* Must match all of destination */
- if (!is_broadcast_ether_addr(mac_mask->h_dest))
- return -EINVAL;
- /* and nothing else */
- if (!is_zero_ether_addr(mac_mask->h_source) ||
- mac_mask->h_proto)
- return -EINVAL;
-
- rc = efx_filter_set_eth_local(
- &spec,
- (rule->flow_type & FLOW_EXT && rule->m_ext.vlan_tci) ?
- ntohs(rule->h_ext.vlan_tci) : EFX_FILTER_VID_UNSPEC,
- mac_entry->h_dest);
- if (rc)
- return rc;
+ if (!is_zero_ether_addr(mac_mask->h_dest)) {
+ if (ether_addr_equal(mac_mask->h_dest,
+ mac_addr_ig_mask))
+ spec.match_flags |= EFX_FILTER_MATCH_LOC_MAC_IG;
+ else if (is_broadcast_ether_addr(mac_mask->h_dest))
+ spec.match_flags |= EFX_FILTER_MATCH_LOC_MAC;
+ else
+ return -EINVAL;
+ ether_addr_copy(spec.loc_mac, mac_entry->h_dest);
+ }
+ if (!is_zero_ether_addr(mac_mask->h_source)) {
+ if (!is_broadcast_ether_addr(mac_mask->h_source))
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_REM_MAC;
+ ether_addr_copy(spec.rem_mac, mac_entry->h_source);
+ }
+ if (mac_mask->h_proto) {
+ if (mac_mask->h_proto != ETHER_TYPE_FULL_MASK)
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_ETHER_TYPE;
+ spec.ether_type = mac_entry->h_proto;
+ }
break;
default:
return -EINVAL;
}
+ if ((rule->flow_type & FLOW_EXT) && rule->m_ext.vlan_tci) {
+ if (rule->m_ext.vlan_tci != htons(0xfff))
+ return -EINVAL;
+ spec.match_flags |= EFX_FILTER_MATCH_OUTER_VID;
+ spec.outer_vid = rule->h_ext.vlan_tci;
+ }
+
rc = efx_filter_insert_filter(efx, &spec, true);
if (rc < 0)
return rc;
@@ -1070,11 +1028,12 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
- return (efx_nic_rev(efx) < EFX_REV_FALCON_B0 ?
+ return ((efx_nic_rev(efx) < EFX_REV_FALCON_B0 ||
+ efx->n_rx_channels == 1) ?
0 : ARRAY_SIZE(efx->rx_indir_table));
}
-static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
+static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key)
{
struct efx_nic *efx = netdev_priv(net_dev);
@@ -1082,16 +1041,63 @@ static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir)
return 0;
}
-static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev,
- const u32 *indir)
+static int efx_ethtool_set_rxfh(struct net_device *net_dev,
+ const u32 *indir, const u8 *key)
{
struct efx_nic *efx = netdev_priv(net_dev);
memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table));
- efx_nic_push_rx_indir_table(efx);
+ efx->type->rx_push_rss_config(efx);
+ return 0;
+}
+
+static int efx_ethtool_get_ts_info(struct net_device *net_dev,
+ struct ethtool_ts_info *ts_info)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+
+ /* Software capabilities */
+ ts_info->so_timestamping = (SOF_TIMESTAMPING_RX_SOFTWARE |
+ SOF_TIMESTAMPING_SOFTWARE);
+ ts_info->phc_index = -1;
+
+ efx_ptp_get_ts_info(efx, ts_info);
return 0;
}
+static int efx_ethtool_get_module_eeprom(struct net_device *net_dev,
+ struct ethtool_eeprom *ee,
+ u8 *data)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ int ret;
+
+ if (!efx->phy_op || !efx->phy_op->get_module_eeprom)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&efx->mac_lock);
+ ret = efx->phy_op->get_module_eeprom(efx, ee, data);
+ mutex_unlock(&efx->mac_lock);
+
+ return ret;
+}
+
+static int efx_ethtool_get_module_info(struct net_device *net_dev,
+ struct ethtool_modinfo *modinfo)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ int ret;
+
+ if (!efx->phy_op || !efx->phy_op->get_module_info)
+ return -EOPNOTSUPP;
+
+ mutex_lock(&efx->mac_lock);
+ ret = efx->phy_op->get_module_info(efx, modinfo);
+ mutex_unlock(&efx->mac_lock);
+
+ return ret;
+}
+
const struct ethtool_ops efx_ethtool_ops = {
.get_settings = efx_ethtool_get_settings,
.set_settings = efx_ethtool_set_settings,
@@ -1119,6 +1125,9 @@ const struct ethtool_ops efx_ethtool_ops = {
.get_rxnfc = efx_ethtool_get_rxnfc,
.set_rxnfc = efx_ethtool_set_rxnfc,
.get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size,
- .get_rxfh_indir = efx_ethtool_get_rxfh_indir,
- .set_rxfh_indir = efx_ethtool_set_rxfh_indir,
+ .get_rxfh = efx_ethtool_get_rxfh,
+ .set_rxfh = efx_ethtool_set_rxfh,
+ .get_ts_info = efx_ethtool_get_ts_info,
+ .get_module_info = efx_ethtool_get_module_info,
+ .get_module_eeprom = efx_ethtool_get_module_eeprom,
};
diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c
index 8ae1ebd3539..fae25a41864 100644
--- a/drivers/net/ethernet/sfc/falcon.c
+++ b/drivers/net/ethernet/sfc/falcon.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -19,16 +19,285 @@
#include "net_driver.h"
#include "bitfield.h"
#include "efx.h"
-#include "mac.h"
-#include "spi.h"
#include "nic.h"
-#include "regs.h"
+#include "farch_regs.h"
#include "io.h"
#include "phy.h"
#include "workarounds.h"
+#include "selftest.h"
+#include "mdio_10g.h"
/* Hardware control for SFC4000 (aka Falcon). */
+/**************************************************************************
+ *
+ * NIC stats
+ *
+ **************************************************************************
+ */
+
+#define FALCON_MAC_STATS_SIZE 0x100
+
+#define XgRxOctets_offset 0x0
+#define XgRxOctets_WIDTH 48
+#define XgRxOctetsOK_offset 0x8
+#define XgRxOctetsOK_WIDTH 48
+#define XgRxPkts_offset 0x10
+#define XgRxPkts_WIDTH 32
+#define XgRxPktsOK_offset 0x14
+#define XgRxPktsOK_WIDTH 32
+#define XgRxBroadcastPkts_offset 0x18
+#define XgRxBroadcastPkts_WIDTH 32
+#define XgRxMulticastPkts_offset 0x1C
+#define XgRxMulticastPkts_WIDTH 32
+#define XgRxUnicastPkts_offset 0x20
+#define XgRxUnicastPkts_WIDTH 32
+#define XgRxUndersizePkts_offset 0x24
+#define XgRxUndersizePkts_WIDTH 32
+#define XgRxOversizePkts_offset 0x28
+#define XgRxOversizePkts_WIDTH 32
+#define XgRxJabberPkts_offset 0x2C
+#define XgRxJabberPkts_WIDTH 32
+#define XgRxUndersizeFCSerrorPkts_offset 0x30
+#define XgRxUndersizeFCSerrorPkts_WIDTH 32
+#define XgRxDropEvents_offset 0x34
+#define XgRxDropEvents_WIDTH 32
+#define XgRxFCSerrorPkts_offset 0x38
+#define XgRxFCSerrorPkts_WIDTH 32
+#define XgRxAlignError_offset 0x3C
+#define XgRxAlignError_WIDTH 32
+#define XgRxSymbolError_offset 0x40
+#define XgRxSymbolError_WIDTH 32
+#define XgRxInternalMACError_offset 0x44
+#define XgRxInternalMACError_WIDTH 32
+#define XgRxControlPkts_offset 0x48
+#define XgRxControlPkts_WIDTH 32
+#define XgRxPausePkts_offset 0x4C
+#define XgRxPausePkts_WIDTH 32
+#define XgRxPkts64Octets_offset 0x50
+#define XgRxPkts64Octets_WIDTH 32
+#define XgRxPkts65to127Octets_offset 0x54
+#define XgRxPkts65to127Octets_WIDTH 32
+#define XgRxPkts128to255Octets_offset 0x58
+#define XgRxPkts128to255Octets_WIDTH 32
+#define XgRxPkts256to511Octets_offset 0x5C
+#define XgRxPkts256to511Octets_WIDTH 32
+#define XgRxPkts512to1023Octets_offset 0x60
+#define XgRxPkts512to1023Octets_WIDTH 32
+#define XgRxPkts1024to15xxOctets_offset 0x64
+#define XgRxPkts1024to15xxOctets_WIDTH 32
+#define XgRxPkts15xxtoMaxOctets_offset 0x68
+#define XgRxPkts15xxtoMaxOctets_WIDTH 32
+#define XgRxLengthError_offset 0x6C
+#define XgRxLengthError_WIDTH 32
+#define XgTxPkts_offset 0x80
+#define XgTxPkts_WIDTH 32
+#define XgTxOctets_offset 0x88
+#define XgTxOctets_WIDTH 48
+#define XgTxMulticastPkts_offset 0x90
+#define XgTxMulticastPkts_WIDTH 32
+#define XgTxBroadcastPkts_offset 0x94
+#define XgTxBroadcastPkts_WIDTH 32
+#define XgTxUnicastPkts_offset 0x98
+#define XgTxUnicastPkts_WIDTH 32
+#define XgTxControlPkts_offset 0x9C
+#define XgTxControlPkts_WIDTH 32
+#define XgTxPausePkts_offset 0xA0
+#define XgTxPausePkts_WIDTH 32
+#define XgTxPkts64Octets_offset 0xA4
+#define XgTxPkts64Octets_WIDTH 32
+#define XgTxPkts65to127Octets_offset 0xA8
+#define XgTxPkts65to127Octets_WIDTH 32
+#define XgTxPkts128to255Octets_offset 0xAC
+#define XgTxPkts128to255Octets_WIDTH 32
+#define XgTxPkts256to511Octets_offset 0xB0
+#define XgTxPkts256to511Octets_WIDTH 32
+#define XgTxPkts512to1023Octets_offset 0xB4
+#define XgTxPkts512to1023Octets_WIDTH 32
+#define XgTxPkts1024to15xxOctets_offset 0xB8
+#define XgTxPkts1024to15xxOctets_WIDTH 32
+#define XgTxPkts1519toMaxOctets_offset 0xBC
+#define XgTxPkts1519toMaxOctets_WIDTH 32
+#define XgTxUndersizePkts_offset 0xC0
+#define XgTxUndersizePkts_WIDTH 32
+#define XgTxOversizePkts_offset 0xC4
+#define XgTxOversizePkts_WIDTH 32
+#define XgTxNonTcpUdpPkt_offset 0xC8
+#define XgTxNonTcpUdpPkt_WIDTH 16
+#define XgTxMacSrcErrPkt_offset 0xCC
+#define XgTxMacSrcErrPkt_WIDTH 16
+#define XgTxIpSrcErrPkt_offset 0xD0
+#define XgTxIpSrcErrPkt_WIDTH 16
+#define XgDmaDone_offset 0xD4
+#define XgDmaDone_WIDTH 32
+
+#define FALCON_XMAC_STATS_DMA_FLAG(efx) \
+ (*(u32 *)((efx)->stats_buffer.addr + XgDmaDone_offset))
+
+#define FALCON_DMA_STAT(ext_name, hw_name) \
+ [FALCON_STAT_ ## ext_name] = \
+ { #ext_name, \
+ /* 48-bit stats are zero-padded to 64 on DMA */ \
+ hw_name ## _ ## WIDTH == 48 ? 64 : hw_name ## _ ## WIDTH, \
+ hw_name ## _ ## offset }
+#define FALCON_OTHER_STAT(ext_name) \
+ [FALCON_STAT_ ## ext_name] = { #ext_name, 0, 0 }
+
+static const struct efx_hw_stat_desc falcon_stat_desc[FALCON_STAT_COUNT] = {
+ FALCON_DMA_STAT(tx_bytes, XgTxOctets),
+ FALCON_DMA_STAT(tx_packets, XgTxPkts),
+ FALCON_DMA_STAT(tx_pause, XgTxPausePkts),
+ FALCON_DMA_STAT(tx_control, XgTxControlPkts),
+ FALCON_DMA_STAT(tx_unicast, XgTxUnicastPkts),
+ FALCON_DMA_STAT(tx_multicast, XgTxMulticastPkts),
+ FALCON_DMA_STAT(tx_broadcast, XgTxBroadcastPkts),
+ FALCON_DMA_STAT(tx_lt64, XgTxUndersizePkts),
+ FALCON_DMA_STAT(tx_64, XgTxPkts64Octets),
+ FALCON_DMA_STAT(tx_65_to_127, XgTxPkts65to127Octets),
+ FALCON_DMA_STAT(tx_128_to_255, XgTxPkts128to255Octets),
+ FALCON_DMA_STAT(tx_256_to_511, XgTxPkts256to511Octets),
+ FALCON_DMA_STAT(tx_512_to_1023, XgTxPkts512to1023Octets),
+ FALCON_DMA_STAT(tx_1024_to_15xx, XgTxPkts1024to15xxOctets),
+ FALCON_DMA_STAT(tx_15xx_to_jumbo, XgTxPkts1519toMaxOctets),
+ FALCON_DMA_STAT(tx_gtjumbo, XgTxOversizePkts),
+ FALCON_DMA_STAT(tx_non_tcpudp, XgTxNonTcpUdpPkt),
+ FALCON_DMA_STAT(tx_mac_src_error, XgTxMacSrcErrPkt),
+ FALCON_DMA_STAT(tx_ip_src_error, XgTxIpSrcErrPkt),
+ FALCON_DMA_STAT(rx_bytes, XgRxOctets),
+ FALCON_DMA_STAT(rx_good_bytes, XgRxOctetsOK),
+ FALCON_OTHER_STAT(rx_bad_bytes),
+ FALCON_DMA_STAT(rx_packets, XgRxPkts),
+ FALCON_DMA_STAT(rx_good, XgRxPktsOK),
+ FALCON_DMA_STAT(rx_bad, XgRxFCSerrorPkts),
+ FALCON_DMA_STAT(rx_pause, XgRxPausePkts),
+ FALCON_DMA_STAT(rx_control, XgRxControlPkts),
+ FALCON_DMA_STAT(rx_unicast, XgRxUnicastPkts),
+ FALCON_DMA_STAT(rx_multicast, XgRxMulticastPkts),
+ FALCON_DMA_STAT(rx_broadcast, XgRxBroadcastPkts),
+ FALCON_DMA_STAT(rx_lt64, XgRxUndersizePkts),
+ FALCON_DMA_STAT(rx_64, XgRxPkts64Octets),
+ FALCON_DMA_STAT(rx_65_to_127, XgRxPkts65to127Octets),
+ FALCON_DMA_STAT(rx_128_to_255, XgRxPkts128to255Octets),
+ FALCON_DMA_STAT(rx_256_to_511, XgRxPkts256to511Octets),
+ FALCON_DMA_STAT(rx_512_to_1023, XgRxPkts512to1023Octets),
+ FALCON_DMA_STAT(rx_1024_to_15xx, XgRxPkts1024to15xxOctets),
+ FALCON_DMA_STAT(rx_15xx_to_jumbo, XgRxPkts15xxtoMaxOctets),
+ FALCON_DMA_STAT(rx_gtjumbo, XgRxOversizePkts),
+ FALCON_DMA_STAT(rx_bad_lt64, XgRxUndersizeFCSerrorPkts),
+ FALCON_DMA_STAT(rx_bad_gtjumbo, XgRxJabberPkts),
+ FALCON_DMA_STAT(rx_overflow, XgRxDropEvents),
+ FALCON_DMA_STAT(rx_symbol_error, XgRxSymbolError),
+ FALCON_DMA_STAT(rx_align_error, XgRxAlignError),
+ FALCON_DMA_STAT(rx_length_error, XgRxLengthError),
+ FALCON_DMA_STAT(rx_internal_error, XgRxInternalMACError),
+ FALCON_OTHER_STAT(rx_nodesc_drop_cnt),
+};
+static const unsigned long falcon_stat_mask[] = {
+ [0 ... BITS_TO_LONGS(FALCON_STAT_COUNT) - 1] = ~0UL,
+};
+
+/**************************************************************************
+ *
+ * Basic SPI command set and bit definitions
+ *
+ *************************************************************************/
+
+#define SPI_WRSR 0x01 /* Write status register */
+#define SPI_WRITE 0x02 /* Write data to memory array */
+#define SPI_READ 0x03 /* Read data from memory array */
+#define SPI_WRDI 0x04 /* Reset write enable latch */
+#define SPI_RDSR 0x05 /* Read status register */
+#define SPI_WREN 0x06 /* Set write enable latch */
+#define SPI_SST_EWSR 0x50 /* SST: Enable write to status register */
+
+#define SPI_STATUS_WPEN 0x80 /* Write-protect pin enabled */
+#define SPI_STATUS_BP2 0x10 /* Block protection bit 2 */
+#define SPI_STATUS_BP1 0x08 /* Block protection bit 1 */
+#define SPI_STATUS_BP0 0x04 /* Block protection bit 0 */
+#define SPI_STATUS_WEN 0x02 /* State of the write enable latch */
+#define SPI_STATUS_NRDY 0x01 /* Device busy flag */
+
+/**************************************************************************
+ *
+ * Non-volatile memory layout
+ *
+ **************************************************************************
+ */
+
+/* SFC4000 flash is partitioned into:
+ * 0-0x400 chip and board config (see struct falcon_nvconfig)
+ * 0x400-0x8000 unused (or may contain VPD if EEPROM not present)
+ * 0x8000-end boot code (mapped to PCI expansion ROM)
+ * SFC4000 small EEPROM (size < 0x400) is used for VPD only.
+ * SFC4000 large EEPROM (size >= 0x400) is partitioned into:
+ * 0-0x400 chip and board config
+ * configurable VPD
+ * 0x800-0x1800 boot config
+ * Aside from the chip and board config, all of these are optional and may
+ * be absent or truncated depending on the devices used.
+ */
+#define FALCON_NVCONFIG_END 0x400U
+#define FALCON_FLASH_BOOTCODE_START 0x8000U
+#define FALCON_EEPROM_BOOTCONFIG_START 0x800U
+#define FALCON_EEPROM_BOOTCONFIG_END 0x1800U
+
+/* Board configuration v2 (v1 is obsolete; later versions are compatible) */
+struct falcon_nvconfig_board_v2 {
+ __le16 nports;
+ u8 port0_phy_addr;
+ u8 port0_phy_type;
+ u8 port1_phy_addr;
+ u8 port1_phy_type;
+ __le16 asic_sub_revision;
+ __le16 board_revision;
+} __packed;
+
+/* Board configuration v3 extra information */
+struct falcon_nvconfig_board_v3 {
+ __le32 spi_device_type[2];
+} __packed;
+
+/* Bit numbers for spi_device_type */
+#define SPI_DEV_TYPE_SIZE_LBN 0
+#define SPI_DEV_TYPE_SIZE_WIDTH 5
+#define SPI_DEV_TYPE_ADDR_LEN_LBN 6
+#define SPI_DEV_TYPE_ADDR_LEN_WIDTH 2
+#define SPI_DEV_TYPE_ERASE_CMD_LBN 8
+#define SPI_DEV_TYPE_ERASE_CMD_WIDTH 8
+#define SPI_DEV_TYPE_ERASE_SIZE_LBN 16
+#define SPI_DEV_TYPE_ERASE_SIZE_WIDTH 5
+#define SPI_DEV_TYPE_BLOCK_SIZE_LBN 24
+#define SPI_DEV_TYPE_BLOCK_SIZE_WIDTH 5
+#define SPI_DEV_TYPE_FIELD(type, field) \
+ (((type) >> EFX_LOW_BIT(field)) & EFX_MASK32(EFX_WIDTH(field)))
+
+#define FALCON_NVCONFIG_OFFSET 0x300
+
+#define FALCON_NVCONFIG_BOARD_MAGIC_NUM 0xFA1C
+struct falcon_nvconfig {
+ efx_oword_t ee_vpd_cfg_reg; /* 0x300 */
+ u8 mac_address[2][8]; /* 0x310 */
+ efx_oword_t pcie_sd_ctl0123_reg; /* 0x320 */
+ efx_oword_t pcie_sd_ctl45_reg; /* 0x330 */
+ efx_oword_t pcie_pcs_ctl_stat_reg; /* 0x340 */
+ efx_oword_t hw_init_reg; /* 0x350 */
+ efx_oword_t nic_stat_reg; /* 0x360 */
+ efx_oword_t glb_ctl_reg; /* 0x370 */
+ efx_oword_t srm_cfg_reg; /* 0x380 */
+ efx_oword_t spare_reg; /* 0x390 */
+ __le16 board_magic_num; /* 0x3A0 */
+ __le16 board_struct_ver;
+ __le16 board_checksum;
+ struct falcon_nvconfig_board_v2 board_v2;
+ efx_oword_t ee_base_page_reg; /* 0x3B0 */
+ struct falcon_nvconfig_board_v3 board_v3; /* 0x3C0 */
+} __packed;
+
+/*************************************************************************/
+
+static int falcon_reset_hw(struct efx_nic *efx, enum reset_type method);
+static void falcon_reconfigure_mac_wrapper(struct efx_nic *efx);
+
static const unsigned int
/* "Large" EEPROM device: Atmel AT25640 or similar
* 8 KB, 16-bit address, 32 B write block */
@@ -89,7 +358,7 @@ static int falcon_getscl(void *data)
return EFX_OWORD_FIELD(reg, FRF_AB_GPIO0_IN);
}
-static struct i2c_algo_bit_data falcon_i2c_bit_operations = {
+static const struct i2c_algo_bit_data falcon_i2c_bit_operations = {
.setsda = falcon_setsda,
.setscl = falcon_setscl,
.getsda = falcon_getsda,
@@ -104,8 +373,6 @@ static void falcon_push_irq_moderation(struct efx_channel *channel)
efx_dword_t timer_cmd;
struct efx_nic *efx = channel->efx;
- BUILD_BUG_ON(EFX_IRQ_MOD_MAX > (1 << FRF_AB_TC_TIMER_VAL_WIDTH));
-
/* Set timer register */
if (channel->irq_moderation) {
EFX_POPULATE_DWORD_2(timer_cmd,
@@ -146,7 +413,7 @@ static void falcon_prepare_flush(struct efx_nic *efx)
*
* NB most hardware supports MSI interrupts
*/
-inline void falcon_irq_ack_a1(struct efx_nic *efx)
+static inline void falcon_irq_ack_a1(struct efx_nic *efx)
{
efx_dword_t reg;
@@ -155,8 +422,7 @@ inline void falcon_irq_ack_a1(struct efx_nic *efx)
efx_readd(efx, &reg, FR_AA_WORK_AROUND_BROKEN_PCI_READS);
}
-
-irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
+static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
{
struct efx_nic *efx = dev_id;
efx_oword_t *int_ker = efx->irq_status.addr;
@@ -177,29 +443,48 @@ irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id)
"IRQ %d on CPU %d status " EFX_OWORD_FMT "\n",
irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
+ if (!likely(ACCESS_ONCE(efx->irq_soft_enabled)))
+ return IRQ_HANDLED;
+
+ /* Check to see if we have a serious error condition */
+ syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+ if (unlikely(syserr))
+ return efx_farch_fatal_interrupt(efx);
+
/* Determine interrupting queues, clear interrupt status
* register and acknowledge the device interrupt.
*/
BUILD_BUG_ON(FSF_AZ_NET_IVEC_INT_Q_WIDTH > EFX_MAX_CHANNELS);
queues = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_INT_Q);
-
- /* Check to see if we have a serious error condition */
- if (queues & (1U << efx->fatal_irq_level)) {
- syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
- if (unlikely(syserr))
- return efx_nic_fatal_interrupt(efx);
- }
-
EFX_ZERO_OWORD(*int_ker);
wmb(); /* Ensure the vector is cleared before interrupt ack */
falcon_irq_ack_a1(efx);
if (queues & 1)
- efx_schedule_channel(efx_get_channel(efx, 0));
+ efx_schedule_channel_irq(efx_get_channel(efx, 0));
if (queues & 2)
- efx_schedule_channel(efx_get_channel(efx, 1));
+ efx_schedule_channel_irq(efx_get_channel(efx, 1));
return IRQ_HANDLED;
}
+
+/**************************************************************************
+ *
+ * RSS
+ *
+ **************************************************************************
+ */
+
+static void falcon_b0_rx_push_rss_config(struct efx_nic *efx)
+{
+ efx_oword_t temp;
+
+ /* Set hash key for IPv4 */
+ memcpy(&temp, efx->rx_hash_key, sizeof(temp));
+ efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
+
+ efx_farch_rx_push_indir_table(efx);
+}
+
/**************************************************************************
*
* EEPROM/flash
@@ -244,9 +529,10 @@ static int falcon_spi_wait(struct efx_nic *efx)
}
}
-int falcon_spi_cmd(struct efx_nic *efx, const struct efx_spi_device *spi,
- unsigned int command, int address,
- const void *in, void *out, size_t len)
+static int
+falcon_spi_cmd(struct efx_nic *efx, const struct falcon_spi_device *spi,
+ unsigned int command, int address,
+ const void *in, void *out, size_t len)
{
bool addressed = (address >= 0);
bool reading = (out != NULL);
@@ -300,48 +586,16 @@ int falcon_spi_cmd(struct efx_nic *efx, const struct efx_spi_device *spi,
return 0;
}
-static size_t
-falcon_spi_write_limit(const struct efx_spi_device *spi, size_t start)
-{
- return min(FALCON_SPI_MAX_LEN,
- (spi->block_size - (start & (spi->block_size - 1))));
-}
-
static inline u8
-efx_spi_munge_command(const struct efx_spi_device *spi,
- const u8 command, const unsigned int address)
+falcon_spi_munge_command(const struct falcon_spi_device *spi,
+ const u8 command, const unsigned int address)
{
return command | (((address >> 8) & spi->munge_address) << 3);
}
-/* Wait up to 10 ms for buffered write completion */
-int
-falcon_spi_wait_write(struct efx_nic *efx, const struct efx_spi_device *spi)
-{
- unsigned long timeout = jiffies + 1 + DIV_ROUND_UP(HZ, 100);
- u8 status;
- int rc;
-
- for (;;) {
- rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
- &status, sizeof(status));
- if (rc)
- return rc;
- if (!(status & SPI_STATUS_NRDY))
- return 0;
- if (time_after_eq(jiffies, timeout)) {
- netif_err(efx, hw, efx->net_dev,
- "SPI write timeout on device %d"
- " last status=0x%02x\n",
- spi->device_id, status);
- return -ETIMEDOUT;
- }
- schedule_timeout_uninterruptible(1);
- }
-}
-
-int falcon_spi_read(struct efx_nic *efx, const struct efx_spi_device *spi,
- loff_t start, size_t len, size_t *retlen, u8 *buffer)
+static int
+falcon_spi_read(struct efx_nic *efx, const struct falcon_spi_device *spi,
+ loff_t start, size_t len, size_t *retlen, u8 *buffer)
{
size_t block_len, pos = 0;
unsigned int command;
@@ -350,7 +604,7 @@ int falcon_spi_read(struct efx_nic *efx, const struct efx_spi_device *spi,
while (pos < len) {
block_len = min(len - pos, FALCON_SPI_MAX_LEN);
- command = efx_spi_munge_command(spi, SPI_READ, start + pos);
+ command = falcon_spi_munge_command(spi, SPI_READ, start + pos);
rc = falcon_spi_cmd(efx, spi, command, start + pos, NULL,
buffer + pos, block_len);
if (rc)
@@ -370,8 +624,52 @@ int falcon_spi_read(struct efx_nic *efx, const struct efx_spi_device *spi,
return rc;
}
-int
-falcon_spi_write(struct efx_nic *efx, const struct efx_spi_device *spi,
+#ifdef CONFIG_SFC_MTD
+
+struct falcon_mtd_partition {
+ struct efx_mtd_partition common;
+ const struct falcon_spi_device *spi;
+ size_t offset;
+};
+
+#define to_falcon_mtd_partition(mtd) \
+ container_of(mtd, struct falcon_mtd_partition, common.mtd)
+
+static size_t
+falcon_spi_write_limit(const struct falcon_spi_device *spi, size_t start)
+{
+ return min(FALCON_SPI_MAX_LEN,
+ (spi->block_size - (start & (spi->block_size - 1))));
+}
+
+/* Wait up to 10 ms for buffered write completion */
+static int
+falcon_spi_wait_write(struct efx_nic *efx, const struct falcon_spi_device *spi)
+{
+ unsigned long timeout = jiffies + 1 + DIV_ROUND_UP(HZ, 100);
+ u8 status;
+ int rc;
+
+ for (;;) {
+ rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
+ &status, sizeof(status));
+ if (rc)
+ return rc;
+ if (!(status & SPI_STATUS_NRDY))
+ return 0;
+ if (time_after_eq(jiffies, timeout)) {
+ netif_err(efx, hw, efx->net_dev,
+ "SPI write timeout on device %d"
+ " last status=0x%02x\n",
+ spi->device_id, status);
+ return -ETIMEDOUT;
+ }
+ schedule_timeout_uninterruptible(1);
+ }
+}
+
+static int
+falcon_spi_write(struct efx_nic *efx, const struct falcon_spi_device *spi,
loff_t start, size_t len, size_t *retlen, const u8 *buffer)
{
u8 verify_buffer[FALCON_SPI_MAX_LEN];
@@ -386,7 +684,7 @@ falcon_spi_write(struct efx_nic *efx, const struct efx_spi_device *spi,
block_len = min(len - pos,
falcon_spi_write_limit(spi, start + pos));
- command = efx_spi_munge_command(spi, SPI_WRITE, start + pos);
+ command = falcon_spi_munge_command(spi, SPI_WRITE, start + pos);
rc = falcon_spi_cmd(efx, spi, command, start + pos,
buffer + pos, NULL, block_len);
if (rc)
@@ -396,7 +694,7 @@ falcon_spi_write(struct efx_nic *efx, const struct efx_spi_device *spi,
if (rc)
break;
- command = efx_spi_munge_command(spi, SPI_READ, start + pos);
+ command = falcon_spi_munge_command(spi, SPI_READ, start + pos);
rc = falcon_spi_cmd(efx, spi, command, start + pos,
NULL, verify_buffer, block_len);
if (memcmp(verify_buffer, buffer + pos, block_len)) {
@@ -419,6 +717,520 @@ falcon_spi_write(struct efx_nic *efx, const struct efx_spi_device *spi,
return rc;
}
+static int
+falcon_spi_slow_wait(struct falcon_mtd_partition *part, bool uninterruptible)
+{
+ const struct falcon_spi_device *spi = part->spi;
+ struct efx_nic *efx = part->common.mtd.priv;
+ u8 status;
+ int rc, i;
+
+ /* Wait up to 4s for flash/EEPROM to finish a slow operation. */
+ for (i = 0; i < 40; i++) {
+ __set_current_state(uninterruptible ?
+ TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE);
+ schedule_timeout(HZ / 10);
+ rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
+ &status, sizeof(status));
+ if (rc)
+ return rc;
+ if (!(status & SPI_STATUS_NRDY))
+ return 0;
+ if (signal_pending(current))
+ return -EINTR;
+ }
+ pr_err("%s: timed out waiting for %s\n",
+ part->common.name, part->common.dev_type_name);
+ return -ETIMEDOUT;
+}
+
+static int
+falcon_spi_unlock(struct efx_nic *efx, const struct falcon_spi_device *spi)
+{
+ const u8 unlock_mask = (SPI_STATUS_BP2 | SPI_STATUS_BP1 |
+ SPI_STATUS_BP0);
+ u8 status;
+ int rc;
+
+ rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
+ &status, sizeof(status));
+ if (rc)
+ return rc;
+
+ if (!(status & unlock_mask))
+ return 0; /* already unlocked */
+
+ rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0);
+ if (rc)
+ return rc;
+ rc = falcon_spi_cmd(efx, spi, SPI_SST_EWSR, -1, NULL, NULL, 0);
+ if (rc)
+ return rc;
+
+ status &= ~unlock_mask;
+ rc = falcon_spi_cmd(efx, spi, SPI_WRSR, -1, &status,
+ NULL, sizeof(status));
+ if (rc)
+ return rc;
+ rc = falcon_spi_wait_write(efx, spi);
+ if (rc)
+ return rc;
+
+ return 0;
+}
+
+#define FALCON_SPI_VERIFY_BUF_LEN 16
+
+static int
+falcon_spi_erase(struct falcon_mtd_partition *part, loff_t start, size_t len)
+{
+ const struct falcon_spi_device *spi = part->spi;
+ struct efx_nic *efx = part->common.mtd.priv;
+ unsigned pos, block_len;
+ u8 empty[FALCON_SPI_VERIFY_BUF_LEN];
+ u8 buffer[FALCON_SPI_VERIFY_BUF_LEN];
+ int rc;
+
+ if (len != spi->erase_size)
+ return -EINVAL;
+
+ if (spi->erase_command == 0)
+ return -EOPNOTSUPP;
+
+ rc = falcon_spi_unlock(efx, spi);
+ if (rc)
+ return rc;
+ rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0);
+ if (rc)
+ return rc;
+ rc = falcon_spi_cmd(efx, spi, spi->erase_command, start, NULL,
+ NULL, 0);
+ if (rc)
+ return rc;
+ rc = falcon_spi_slow_wait(part, false);
+
+ /* Verify the entire region has been wiped */
+ memset(empty, 0xff, sizeof(empty));
+ for (pos = 0; pos < len; pos += block_len) {
+ block_len = min(len - pos, sizeof(buffer));
+ rc = falcon_spi_read(efx, spi, start + pos, block_len,
+ NULL, buffer);
+ if (rc)
+ return rc;
+ if (memcmp(empty, buffer, block_len))
+ return -EIO;
+
+ /* Avoid locking up the system */
+ cond_resched();
+ if (signal_pending(current))
+ return -EINTR;
+ }
+
+ return rc;
+}
+
+static void falcon_mtd_rename(struct efx_mtd_partition *part)
+{
+ struct efx_nic *efx = part->mtd.priv;
+
+ snprintf(part->name, sizeof(part->name), "%s %s",
+ efx->name, part->type_name);
+}
+
+static int falcon_mtd_read(struct mtd_info *mtd, loff_t start,
+ size_t len, size_t *retlen, u8 *buffer)
+{
+ struct falcon_mtd_partition *part = to_falcon_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ rc = mutex_lock_interruptible(&nic_data->spi_lock);
+ if (rc)
+ return rc;
+ rc = falcon_spi_read(efx, part->spi, part->offset + start,
+ len, retlen, buffer);
+ mutex_unlock(&nic_data->spi_lock);
+ return rc;
+}
+
+static int falcon_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len)
+{
+ struct falcon_mtd_partition *part = to_falcon_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ rc = mutex_lock_interruptible(&nic_data->spi_lock);
+ if (rc)
+ return rc;
+ rc = falcon_spi_erase(part, part->offset + start, len);
+ mutex_unlock(&nic_data->spi_lock);
+ return rc;
+}
+
+static int falcon_mtd_write(struct mtd_info *mtd, loff_t start,
+ size_t len, size_t *retlen, const u8 *buffer)
+{
+ struct falcon_mtd_partition *part = to_falcon_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ rc = mutex_lock_interruptible(&nic_data->spi_lock);
+ if (rc)
+ return rc;
+ rc = falcon_spi_write(efx, part->spi, part->offset + start,
+ len, retlen, buffer);
+ mutex_unlock(&nic_data->spi_lock);
+ return rc;
+}
+
+static int falcon_mtd_sync(struct mtd_info *mtd)
+{
+ struct falcon_mtd_partition *part = to_falcon_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ int rc;
+
+ mutex_lock(&nic_data->spi_lock);
+ rc = falcon_spi_slow_wait(part, true);
+ mutex_unlock(&nic_data->spi_lock);
+ return rc;
+}
+
+static int falcon_mtd_probe(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ struct falcon_mtd_partition *parts;
+ struct falcon_spi_device *spi;
+ size_t n_parts;
+ int rc = -ENODEV;
+
+ ASSERT_RTNL();
+
+ /* Allocate space for maximum number of partitions */
+ parts = kcalloc(2, sizeof(*parts), GFP_KERNEL);
+ if (!parts)
+ return -ENOMEM;
+ n_parts = 0;
+
+ spi = &nic_data->spi_flash;
+ if (falcon_spi_present(spi) && spi->size > FALCON_FLASH_BOOTCODE_START) {
+ parts[n_parts].spi = spi;
+ parts[n_parts].offset = FALCON_FLASH_BOOTCODE_START;
+ parts[n_parts].common.dev_type_name = "flash";
+ parts[n_parts].common.type_name = "sfc_flash_bootrom";
+ parts[n_parts].common.mtd.type = MTD_NORFLASH;
+ parts[n_parts].common.mtd.flags = MTD_CAP_NORFLASH;
+ parts[n_parts].common.mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START;
+ parts[n_parts].common.mtd.erasesize = spi->erase_size;
+ n_parts++;
+ }
+
+ spi = &nic_data->spi_eeprom;
+ if (falcon_spi_present(spi) && spi->size > FALCON_EEPROM_BOOTCONFIG_START) {
+ parts[n_parts].spi = spi;
+ parts[n_parts].offset = FALCON_EEPROM_BOOTCONFIG_START;
+ parts[n_parts].common.dev_type_name = "EEPROM";
+ parts[n_parts].common.type_name = "sfc_bootconfig";
+ parts[n_parts].common.mtd.type = MTD_RAM;
+ parts[n_parts].common.mtd.flags = MTD_CAP_RAM;
+ parts[n_parts].common.mtd.size =
+ min(spi->size, FALCON_EEPROM_BOOTCONFIG_END) -
+ FALCON_EEPROM_BOOTCONFIG_START;
+ parts[n_parts].common.mtd.erasesize = spi->erase_size;
+ n_parts++;
+ }
+
+ rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
+ if (rc)
+ kfree(parts);
+ return rc;
+}
+
+#endif /* CONFIG_SFC_MTD */
+
+/**************************************************************************
+ *
+ * XMAC operations
+ *
+ **************************************************************************
+ */
+
+/* Configure the XAUI driver that is an output from Falcon */
+static void falcon_setup_xaui(struct efx_nic *efx)
+{
+ efx_oword_t sdctl, txdrv;
+
+ /* Move the XAUI into low power, unless there is no PHY, in
+ * which case the XAUI will have to drive a cable. */
+ if (efx->phy_type == PHY_TYPE_NONE)
+ return;
+
+ efx_reado(efx, &sdctl, FR_AB_XX_SD_CTL);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVD, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVD, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVC, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVC, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVB, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVB, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVA, FFE_AB_XX_SD_CTL_DRV_DEF);
+ EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVA, FFE_AB_XX_SD_CTL_DRV_DEF);
+ efx_writeo(efx, &sdctl, FR_AB_XX_SD_CTL);
+
+ EFX_POPULATE_OWORD_8(txdrv,
+ FRF_AB_XX_DEQD, FFE_AB_XX_TXDRV_DEQ_DEF,
+ FRF_AB_XX_DEQC, FFE_AB_XX_TXDRV_DEQ_DEF,
+ FRF_AB_XX_DEQB, FFE_AB_XX_TXDRV_DEQ_DEF,
+ FRF_AB_XX_DEQA, FFE_AB_XX_TXDRV_DEQ_DEF,
+ FRF_AB_XX_DTXD, FFE_AB_XX_TXDRV_DTX_DEF,
+ FRF_AB_XX_DTXC, FFE_AB_XX_TXDRV_DTX_DEF,
+ FRF_AB_XX_DTXB, FFE_AB_XX_TXDRV_DTX_DEF,
+ FRF_AB_XX_DTXA, FFE_AB_XX_TXDRV_DTX_DEF);
+ efx_writeo(efx, &txdrv, FR_AB_XX_TXDRV_CTL);
+}
+
+int falcon_reset_xaui(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ efx_oword_t reg;
+ int count;
+
+ /* Don't fetch MAC statistics over an XMAC reset */
+ WARN_ON(nic_data->stats_disable_count == 0);
+
+ /* Start reset sequence */
+ EFX_POPULATE_OWORD_1(reg, FRF_AB_XX_RST_XX_EN, 1);
+ efx_writeo(efx, &reg, FR_AB_XX_PWR_RST);
+
+ /* Wait up to 10 ms for completion, then reinitialise */
+ for (count = 0; count < 1000; count++) {
+ efx_reado(efx, &reg, FR_AB_XX_PWR_RST);
+ if (EFX_OWORD_FIELD(reg, FRF_AB_XX_RST_XX_EN) == 0 &&
+ EFX_OWORD_FIELD(reg, FRF_AB_XX_SD_RST_ACT) == 0) {
+ falcon_setup_xaui(efx);
+ return 0;
+ }
+ udelay(10);
+ }
+ netif_err(efx, hw, efx->net_dev,
+ "timed out waiting for XAUI/XGXS reset\n");
+ return -ETIMEDOUT;
+}
+
+static void falcon_ack_status_intr(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ efx_oword_t reg;
+
+ if ((efx_nic_rev(efx) != EFX_REV_FALCON_B0) || LOOPBACK_INTERNAL(efx))
+ return;
+
+ /* We expect xgmii faults if the wireside link is down */
+ if (!efx->link_state.up)
+ return;
+
+ /* We can only use this interrupt to signal the negative edge of
+ * xaui_align [we have to poll the positive edge]. */
+ if (nic_data->xmac_poll_required)
+ return;
+
+ efx_reado(efx, &reg, FR_AB_XM_MGT_INT_MSK);
+}
+
+static bool falcon_xgxs_link_ok(struct efx_nic *efx)
+{
+ efx_oword_t reg;
+ bool align_done, link_ok = false;
+ int sync_status;
+
+ /* Read link status */
+ efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
+
+ align_done = EFX_OWORD_FIELD(reg, FRF_AB_XX_ALIGN_DONE);
+ sync_status = EFX_OWORD_FIELD(reg, FRF_AB_XX_SYNC_STAT);
+ if (align_done && (sync_status == FFE_AB_XX_STAT_ALL_LANES))
+ link_ok = true;
+
+ /* Clear link status ready for next read */
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_COMMA_DET, FFE_AB_XX_STAT_ALL_LANES);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_CHAR_ERR, FFE_AB_XX_STAT_ALL_LANES);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_DISPERR, FFE_AB_XX_STAT_ALL_LANES);
+ efx_writeo(efx, &reg, FR_AB_XX_CORE_STAT);
+
+ return link_ok;
+}
+
+static bool falcon_xmac_link_ok(struct efx_nic *efx)
+{
+ /*
+ * Check MAC's XGXS link status except when using XGMII loopback
+ * which bypasses the XGXS block.
+ * If possible, check PHY's XGXS link status except when using
+ * MAC loopback.
+ */
+ return (efx->loopback_mode == LOOPBACK_XGMII ||
+ falcon_xgxs_link_ok(efx)) &&
+ (!(efx->mdio.mmds & (1 << MDIO_MMD_PHYXS)) ||
+ LOOPBACK_INTERNAL(efx) ||
+ efx_mdio_phyxgxs_lane_sync(efx));
+}
+
+static void falcon_reconfigure_xmac_core(struct efx_nic *efx)
+{
+ unsigned int max_frame_len;
+ efx_oword_t reg;
+ bool rx_fc = !!(efx->link_state.fc & EFX_FC_RX);
+ bool tx_fc = !!(efx->link_state.fc & EFX_FC_TX);
+
+ /* Configure MAC - cut-thru mode is hard wired on */
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_AB_XM_RX_JUMBO_MODE, 1,
+ FRF_AB_XM_TX_STAT_EN, 1,
+ FRF_AB_XM_RX_STAT_EN, 1);
+ efx_writeo(efx, &reg, FR_AB_XM_GLB_CFG);
+
+ /* Configure TX */
+ EFX_POPULATE_OWORD_6(reg,
+ FRF_AB_XM_TXEN, 1,
+ FRF_AB_XM_TX_PRMBL, 1,
+ FRF_AB_XM_AUTO_PAD, 1,
+ FRF_AB_XM_TXCRC, 1,
+ FRF_AB_XM_FCNTL, tx_fc,
+ FRF_AB_XM_IPG, 0x3);
+ efx_writeo(efx, &reg, FR_AB_XM_TX_CFG);
+
+ /* Configure RX */
+ EFX_POPULATE_OWORD_5(reg,
+ FRF_AB_XM_RXEN, 1,
+ FRF_AB_XM_AUTO_DEPAD, 0,
+ FRF_AB_XM_ACPT_ALL_MCAST, 1,
+ FRF_AB_XM_ACPT_ALL_UCAST, !efx->unicast_filter,
+ FRF_AB_XM_PASS_CRC_ERR, 1);
+ efx_writeo(efx, &reg, FR_AB_XM_RX_CFG);
+
+ /* Set frame length */
+ max_frame_len = EFX_MAX_FRAME_LEN(efx->net_dev->mtu);
+ EFX_POPULATE_OWORD_1(reg, FRF_AB_XM_MAX_RX_FRM_SIZE, max_frame_len);
+ efx_writeo(efx, &reg, FR_AB_XM_RX_PARAM);
+ EFX_POPULATE_OWORD_2(reg,
+ FRF_AB_XM_MAX_TX_FRM_SIZE, max_frame_len,
+ FRF_AB_XM_TX_JUMBO_MODE, 1);
+ efx_writeo(efx, &reg, FR_AB_XM_TX_PARAM);
+
+ EFX_POPULATE_OWORD_2(reg,
+ FRF_AB_XM_PAUSE_TIME, 0xfffe, /* MAX PAUSE TIME */
+ FRF_AB_XM_DIS_FCNTL, !rx_fc);
+ efx_writeo(efx, &reg, FR_AB_XM_FC);
+
+ /* Set MAC address */
+ memcpy(&reg, &efx->net_dev->dev_addr[0], 4);
+ efx_writeo(efx, &reg, FR_AB_XM_ADR_LO);
+ memcpy(&reg, &efx->net_dev->dev_addr[4], 2);
+ efx_writeo(efx, &reg, FR_AB_XM_ADR_HI);
+}
+
+static void falcon_reconfigure_xgxs_core(struct efx_nic *efx)
+{
+ efx_oword_t reg;
+ bool xgxs_loopback = (efx->loopback_mode == LOOPBACK_XGXS);
+ bool xaui_loopback = (efx->loopback_mode == LOOPBACK_XAUI);
+ bool xgmii_loopback = (efx->loopback_mode == LOOPBACK_XGMII);
+ bool old_xgmii_loopback, old_xgxs_loopback, old_xaui_loopback;
+
+ /* XGXS block is flaky and will need to be reset if moving
+ * into our out of XGMII, XGXS or XAUI loopbacks. */
+ efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
+ old_xgxs_loopback = EFX_OWORD_FIELD(reg, FRF_AB_XX_XGXS_LB_EN);
+ old_xgmii_loopback = EFX_OWORD_FIELD(reg, FRF_AB_XX_XGMII_LB_EN);
+
+ efx_reado(efx, &reg, FR_AB_XX_SD_CTL);
+ old_xaui_loopback = EFX_OWORD_FIELD(reg, FRF_AB_XX_LPBKA);
+
+ /* The PHY driver may have turned XAUI off */
+ if ((xgxs_loopback != old_xgxs_loopback) ||
+ (xaui_loopback != old_xaui_loopback) ||
+ (xgmii_loopback != old_xgmii_loopback))
+ falcon_reset_xaui(efx);
+
+ efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_FORCE_SIG,
+ (xgxs_loopback || xaui_loopback) ?
+ FFE_AB_XX_FORCE_SIG_ALL_LANES : 0);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_XGXS_LB_EN, xgxs_loopback);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_XGMII_LB_EN, xgmii_loopback);
+ efx_writeo(efx, &reg, FR_AB_XX_CORE_STAT);
+
+ efx_reado(efx, &reg, FR_AB_XX_SD_CTL);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKD, xaui_loopback);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKC, xaui_loopback);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKB, xaui_loopback);
+ EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKA, xaui_loopback);
+ efx_writeo(efx, &reg, FR_AB_XX_SD_CTL);
+}
+
+
+/* Try to bring up the Falcon side of the Falcon-Phy XAUI link */
+static bool falcon_xmac_link_ok_retry(struct efx_nic *efx, int tries)
+{
+ bool mac_up = falcon_xmac_link_ok(efx);
+
+ if (LOOPBACK_MASK(efx) & LOOPBACKS_EXTERNAL(efx) & LOOPBACKS_WS ||
+ efx_phy_mode_disabled(efx->phy_mode))
+ /* XAUI link is expected to be down */
+ return mac_up;
+
+ falcon_stop_nic_stats(efx);
+
+ while (!mac_up && tries) {
+ netif_dbg(efx, hw, efx->net_dev, "bashing xaui\n");
+ falcon_reset_xaui(efx);
+ udelay(200);
+
+ mac_up = falcon_xmac_link_ok(efx);
+ --tries;
+ }
+
+ falcon_start_nic_stats(efx);
+
+ return mac_up;
+}
+
+static bool falcon_xmac_check_fault(struct efx_nic *efx)
+{
+ return !falcon_xmac_link_ok_retry(efx, 5);
+}
+
+static int falcon_reconfigure_xmac(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+
+ efx_farch_filter_sync_rx_mode(efx);
+
+ falcon_reconfigure_xgxs_core(efx);
+ falcon_reconfigure_xmac_core(efx);
+
+ falcon_reconfigure_mac_wrapper(efx);
+
+ nic_data->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 5);
+ falcon_ack_status_intr(efx);
+
+ return 0;
+}
+
+static void falcon_poll_xmac(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+
+ /* We expect xgmii faults if the wireside link is down */
+ if (!efx->link_state.up || !nic_data->xmac_poll_required)
+ return;
+
+ nic_data->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 1);
+ falcon_ack_status_intr(efx);
+}
+
/**************************************************************************
*
* MAC wrapper
@@ -500,7 +1312,7 @@ static void falcon_reset_macs(struct efx_nic *efx)
falcon_setup_xaui(efx);
}
-void falcon_drain_tx_fifo(struct efx_nic *efx)
+static void falcon_drain_tx_fifo(struct efx_nic *efx)
{
efx_oword_t reg;
@@ -532,7 +1344,7 @@ static void falcon_deconfigure_mac_wrapper(struct efx_nic *efx)
falcon_drain_tx_fifo(efx);
}
-void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
+static void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
{
struct efx_link_state *link_state = &efx->link_state;
efx_oword_t reg;
@@ -546,6 +1358,7 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
case 100: link_speed = 1; break;
default: link_speed = 0; break;
}
+
/* MAC_LINK_STATUS controls MAC backpressure but doesn't work
* as advertised. Disable to ensure packets are not
* indefinitely held and TX queue can be flushed at any point
@@ -553,7 +1366,7 @@ void falcon_reconfigure_mac_wrapper(struct efx_nic *efx)
EFX_POPULATE_OWORD_5(reg,
FRF_AB_MAC_XOFF_VAL, 0xffff /* max pause time */,
FRF_AB_MAC_BCAD_ACPT, 1,
- FRF_AB_MAC_UC_PROM, efx->promiscuous,
+ FRF_AB_MAC_UC_PROM, !efx->unicast_filter,
FRF_AB_MAC_LINK_STATUS, 1, /* always set */
FRF_AB_MAC_SPEED, link_speed);
/* On B0, MAC backpressure can be disabled and packets get
@@ -586,10 +1399,7 @@ static void falcon_stats_request(struct efx_nic *efx)
WARN_ON(nic_data->stats_pending);
WARN_ON(nic_data->stats_disable_count);
- if (nic_data->stats_dma_done == NULL)
- return; /* no mac selected */
-
- *nic_data->stats_dma_done = FALCON_STATS_NOT_DONE;
+ FALCON_XMAC_STATS_DMA_FLAG(efx) = 0;
nic_data->stats_pending = true;
wmb(); /* ensure done flag is clear */
@@ -611,9 +1421,11 @@ static void falcon_stats_complete(struct efx_nic *efx)
return;
nic_data->stats_pending = false;
- if (*nic_data->stats_dma_done == FALCON_STATS_DONE) {
+ if (FALCON_XMAC_STATS_DMA_FLAG(efx)) {
rmb(); /* read the done flag before the stats */
- efx->mac_op->update_stats(efx);
+ efx_nic_update_stats(falcon_stat_desc, FALCON_STAT_COUNT,
+ falcon_stat_mask, nic_data->stats,
+ efx->stats_buffer.addr, true);
} else {
netif_err(efx, hw, efx->net_dev,
"timed out waiting for statistics\n");
@@ -670,7 +1482,7 @@ static int falcon_reconfigure_port(struct efx_nic *efx)
falcon_reset_macs(efx);
efx->phy_op->reconfigure(efx);
- rc = efx->mac_op->reconfigure(efx);
+ rc = falcon_reconfigure_xmac(efx);
BUG_ON(rc);
falcon_start_nic_stats(efx);
@@ -681,6 +1493,28 @@ static int falcon_reconfigure_port(struct efx_nic *efx)
return 0;
}
+/* TX flow control may automatically turn itself off if the link
+ * partner (intermittently) stops responding to pause frames. There
+ * isn't any indication that this has happened, so the best we do is
+ * leave it up to the user to spot this and fix it by cycling transmit
+ * flow control on this end.
+ */
+
+static void falcon_a1_prepare_enable_fc_tx(struct efx_nic *efx)
+{
+ /* Schedule a reset to recover */
+ efx_schedule_reset(efx, RESET_TYPE_INVISIBLE);
+}
+
+static void falcon_b0_prepare_enable_fc_tx(struct efx_nic *efx)
+{
+ /* Recover by resetting the EM block */
+ falcon_stop_nic_stats(efx);
+ falcon_drain_tx_fifo(efx);
+ falcon_reconfigure_xmac(efx);
+ falcon_start_nic_stats(efx);
+}
+
/**************************************************************************
*
* PHY access via GMII
@@ -864,7 +1698,7 @@ static int falcon_probe_port(struct efx_nic *efx)
/* Allocate buffer for stats */
rc = efx_nic_alloc_buffer(efx, &efx->stats_buffer,
- FALCON_MAC_STATS_SIZE);
+ FALCON_MAC_STATS_SIZE, GFP_KERNEL);
if (rc)
return rc;
netif_dbg(efx, probe, efx->net_dev,
@@ -872,7 +1706,6 @@ static int falcon_probe_port(struct efx_nic *efx)
(u64)efx->stats_buffer.dma_addr,
efx->stats_buffer.addr,
(u64)virt_to_phys(efx->stats_buffer.addr));
- nic_data->stats_dma_done = efx->stats_buffer.addr + XgDmaDone_offset;
return 0;
}
@@ -929,15 +1762,15 @@ falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out)
{
struct falcon_nic_data *nic_data = efx->nic_data;
struct falcon_nvconfig *nvconfig;
- struct efx_spi_device *spi;
+ struct falcon_spi_device *spi;
void *region;
int rc, magic_num, struct_ver;
__le16 *word, *limit;
u32 csum;
- if (efx_spi_present(&nic_data->spi_flash))
+ if (falcon_spi_present(&nic_data->spi_flash))
spi = &nic_data->spi_flash;
- else if (efx_spi_present(&nic_data->spi_eeprom))
+ else if (falcon_spi_present(&nic_data->spi_eeprom))
spi = &nic_data->spi_eeprom;
else
return -EINVAL;
@@ -952,7 +1785,7 @@ falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out)
mutex_unlock(&nic_data->spi_lock);
if (rc) {
netif_err(efx, hw, efx->net_dev, "Failed to read %s\n",
- efx_spi_present(&nic_data->spi_flash) ?
+ falcon_spi_present(&nic_data->spi_flash) ?
"flash" : "EEPROM");
rc = -EIO;
goto out;
@@ -1001,7 +1834,7 @@ static int falcon_test_nvram(struct efx_nic *efx)
return falcon_read_nvram(efx, NULL);
}
-static const struct efx_nic_register_test falcon_b0_register_tests[] = {
+static const struct efx_farch_register_test falcon_b0_register_tests[] = {
{ FR_AZ_ADR_REGION,
EFX_OWORD32(0x0003FFFF, 0x0003FFFF, 0x0003FFFF, 0x0003FFFF) },
{ FR_AZ_RX_CFG,
@@ -1040,10 +1873,34 @@ static const struct efx_nic_register_test falcon_b0_register_tests[] = {
EFX_OWORD32(0x0003FF0F, 0x00000000, 0x00000000, 0x00000000) },
};
-static int falcon_b0_test_registers(struct efx_nic *efx)
+static int
+falcon_b0_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
{
- return efx_nic_test_registers(efx, falcon_b0_register_tests,
- ARRAY_SIZE(falcon_b0_register_tests));
+ enum reset_type reset_method = RESET_TYPE_INVISIBLE;
+ int rc, rc2;
+
+ mutex_lock(&efx->mac_lock);
+ if (efx->loopback_modes) {
+ /* We need the 312 clock from the PHY to test the XMAC
+ * registers, so move into XGMII loopback if available */
+ if (efx->loopback_modes & (1 << LOOPBACK_XGMII))
+ efx->loopback_mode = LOOPBACK_XGMII;
+ else
+ efx->loopback_mode = __ffs(efx->loopback_modes);
+ }
+ __efx_reconfigure_port(efx);
+ mutex_unlock(&efx->mac_lock);
+
+ efx_reset_down(efx, reset_method);
+
+ tests->registers =
+ efx_farch_test_registers(efx, falcon_b0_register_tests,
+ ARRAY_SIZE(falcon_b0_register_tests))
+ ? -1 : 1;
+
+ rc = falcon_reset_hw(efx, reset_method);
+ rc2 = efx_reset_up(efx, reset_method, rc == 0);
+ return rc ? rc : rc2;
}
/**************************************************************************
@@ -1057,8 +1914,7 @@ static enum reset_type falcon_map_reset_reason(enum reset_type reason)
{
switch (reason) {
case RESET_TYPE_RX_RECOVERY:
- case RESET_TYPE_RX_DESC_FETCH:
- case RESET_TYPE_TX_DESC_FETCH:
+ case RESET_TYPE_DMA_ERROR:
case RESET_TYPE_TX_SKIP:
/* These can occasionally occur due to hardware bugs.
* We try to reset without disrupting the link.
@@ -1218,7 +2074,7 @@ static void falcon_monitor(struct efx_nic *efx)
falcon_deconfigure_mac_wrapper(efx);
falcon_reset_macs(efx);
- rc = efx->mac_op->reconfigure(efx);
+ rc = falcon_reconfigure_xmac(efx);
BUG_ON(rc);
falcon_start_nic_stats(efx);
@@ -1273,7 +2129,7 @@ static int falcon_reset_sram(struct efx_nic *efx)
}
static void falcon_spi_device_init(struct efx_nic *efx,
- struct efx_spi_device *spi_device,
+ struct falcon_spi_device *spi_device,
unsigned int device_id, u32 device_type)
{
if (device_type != 0) {
@@ -1327,7 +2183,7 @@ static int falcon_probe_nvconfig(struct efx_nic *efx)
}
/* Read the MAC addresses */
- memcpy(efx->net_dev->perm_addr, nvconfig->mac_address[0], ETH_ALEN);
+ ether_addr_copy(efx->net_dev->perm_addr, nvconfig->mac_address[0]);
netif_dbg(efx, probe, efx->net_dev, "PHY is %d phy_id %d\n",
efx->phy_type, efx->mdio.prtad);
@@ -1339,6 +2195,13 @@ out:
return rc;
}
+static int falcon_dimension_resources(struct efx_nic *efx)
+{
+ efx->rx_dc_base = 0x20000;
+ efx->tx_dc_base = 0x26000;
+ return 0;
+}
+
/* Probe all SPI devices on the NIC */
static void falcon_probe_spi_devices(struct efx_nic *efx)
{
@@ -1383,12 +2246,28 @@ static void falcon_probe_spi_devices(struct efx_nic *efx)
large_eeprom_type);
}
+static unsigned int falcon_a1_mem_map_size(struct efx_nic *efx)
+{
+ return 0x20000;
+}
+
+static unsigned int falcon_b0_mem_map_size(struct efx_nic *efx)
+{
+ /* Map everything up to and including the RSS indirection table.
+ * The PCI core takes care of mapping the MSI-X tables.
+ */
+ return FR_BZ_RX_INDIRECTION_TBL +
+ FR_BZ_RX_INDIRECTION_TBL_STEP * FR_BZ_RX_INDIRECTION_TBL_ROWS;
+}
+
static int falcon_probe_nic(struct efx_nic *efx)
{
struct falcon_nic_data *nic_data;
struct falcon_board *board;
int rc;
+ efx->primary = efx; /* only one usable function per controller */
+
/* Allocate storage for hardware specific data */
nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL);
if (!nic_data)
@@ -1397,7 +2276,7 @@ static int falcon_probe_nic(struct efx_nic *efx)
rc = -ENODEV;
- if (efx_nic_fpga_ver(efx) != 0) {
+ if (efx_farch_fpga_ver(efx) != 0) {
netif_err(efx, probe, efx->net_dev,
"Falcon FPGA not supported\n");
goto fail1;
@@ -1451,7 +2330,8 @@ static int falcon_probe_nic(struct efx_nic *efx)
}
/* Allocate memory for INT_KER */
- rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t));
+ rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t),
+ GFP_KERNEL);
if (rc)
goto fail4;
BUG_ON(efx->irq_status.dma_addr & 0x0f);
@@ -1472,6 +2352,10 @@ static int falcon_probe_nic(struct efx_nic *efx)
goto fail5;
}
+ efx->max_channels = (efx_nic_rev(efx) <= EFX_REV_FALCON_A1 ? 4 :
+ EFX_MAX_CHANNELS);
+ efx->timer_quantum_ns = 4968; /* 621 cycles */
+
/* Initialise I2C adapter */
board = falcon_board(efx);
board->i2c_adap.owner = THIS_MODULE;
@@ -1499,7 +2383,7 @@ static int falcon_probe_nic(struct efx_nic *efx)
return 0;
fail6:
- BUG_ON(i2c_del_adapter(&board->i2c_adap));
+ i2c_del_adapter(&board->i2c_adap);
memset(&board->i2c_adap, 0, sizeof(board->i2c_adap));
fail5:
efx_nic_free_buffer(efx, &efx->irq_status);
@@ -1517,10 +2401,6 @@ static int falcon_probe_nic(struct efx_nic *efx)
static void falcon_init_rx_cfg(struct efx_nic *efx)
{
- /* Prior to Siena the RX DMA engine will split each frame at
- * intervals of RX_USR_BUF_SIZE (32-byte units). We set it to
- * be so large that that never happens. */
- const unsigned huge_buf_size = (3 * 4096) >> 5;
/* RX control FIFO thresholds (32 entries) */
const unsigned ctrl_xon_thr = 20;
const unsigned ctrl_xoff_thr = 25;
@@ -1528,10 +2408,15 @@ static void falcon_init_rx_cfg(struct efx_nic *efx)
efx_reado(efx, &reg, FR_AZ_RX_CFG);
if (efx_nic_rev(efx) <= EFX_REV_FALCON_A1) {
- /* Data FIFO size is 5.5K */
+ /* Data FIFO size is 5.5K. The RX DMA engine only
+ * supports scattering for user-mode queues, but will
+ * split DMA writes at intervals of RX_USR_BUF_SIZE
+ * (32-byte units) even for kernel-mode queues. We
+ * set it to be so large that that never happens.
+ */
EFX_SET_OWORD_FIELD(reg, FRF_AA_RX_DESC_PUSH_EN, 0);
EFX_SET_OWORD_FIELD(reg, FRF_AA_RX_USR_BUF_SIZE,
- huge_buf_size);
+ (3 * 4096) >> 5);
EFX_SET_OWORD_FIELD(reg, FRF_AA_RX_XON_MAC_TH, 512 >> 8);
EFX_SET_OWORD_FIELD(reg, FRF_AA_RX_XOFF_MAC_TH, 2048 >> 8);
EFX_SET_OWORD_FIELD(reg, FRF_AA_RX_XON_TX_TH, ctrl_xon_thr);
@@ -1540,7 +2425,7 @@ static void falcon_init_rx_cfg(struct efx_nic *efx)
/* Data FIFO size is 80K; register fields moved */
EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_DESC_PUSH_EN, 0);
EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_USR_BUF_SIZE,
- huge_buf_size);
+ EFX_RX_USR_BUF_SIZE >> 5);
/* Send XON and XOFF at ~3 * max MTU away from empty/full */
EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_XON_MAC_TH, 27648 >> 8);
EFX_SET_OWORD_FIELD(reg, FRF_BZ_RX_XOFF_MAC_TH, 54272 >> 8);
@@ -1618,16 +2503,14 @@ static int falcon_init_nic(struct efx_nic *efx)
falcon_init_rx_cfg(efx);
if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
- /* Set hash key for IPv4 */
- memcpy(&temp, efx->rx_hash_key, sizeof(temp));
- efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
+ falcon_b0_rx_push_rss_config(efx);
/* Set destination of both TX and RX Flush events */
EFX_POPULATE_OWORD_1(temp, FRF_BZ_FLS_EVQ_ID, 0);
efx_writeo(efx, &temp, FR_BZ_DP_CTRL);
}
- efx_nic_init_common(efx);
+ efx_farch_init_common(efx);
return 0;
}
@@ -1636,13 +2519,11 @@ static void falcon_remove_nic(struct efx_nic *efx)
{
struct falcon_nic_data *nic_data = efx->nic_data;
struct falcon_board *board = falcon_board(efx);
- int rc;
board->type->fini(efx);
/* Remove I2C adapter and clear it in preparation for a retry */
- rc = i2c_del_adapter(&board->i2c_adap);
- BUG_ON(rc);
+ i2c_del_adapter(&board->i2c_adap);
memset(&board->i2c_adap, 0, sizeof(board->i2c_adap));
efx_nic_free_buffer(efx, &efx->irq_status);
@@ -1660,24 +2541,65 @@ static void falcon_remove_nic(struct efx_nic *efx)
efx->nic_data = NULL;
}
-static void falcon_update_nic_stats(struct efx_nic *efx)
+static size_t falcon_describe_nic_stats(struct efx_nic *efx, u8 *names)
+{
+ return efx_nic_describe_stats(falcon_stat_desc, FALCON_STAT_COUNT,
+ falcon_stat_mask, names);
+}
+
+static size_t falcon_update_nic_stats(struct efx_nic *efx, u64 *full_stats,
+ struct rtnl_link_stats64 *core_stats)
{
struct falcon_nic_data *nic_data = efx->nic_data;
+ u64 *stats = nic_data->stats;
efx_oword_t cnt;
- if (nic_data->stats_disable_count)
- return;
+ if (!nic_data->stats_disable_count) {
+ efx_reado(efx, &cnt, FR_AZ_RX_NODESC_DROP);
+ stats[FALCON_STAT_rx_nodesc_drop_cnt] +=
+ EFX_OWORD_FIELD(cnt, FRF_AB_RX_NODESC_DROP_CNT);
+
+ if (nic_data->stats_pending &&
+ FALCON_XMAC_STATS_DMA_FLAG(efx)) {
+ nic_data->stats_pending = false;
+ rmb(); /* read the done flag before the stats */
+ efx_nic_update_stats(
+ falcon_stat_desc, FALCON_STAT_COUNT,
+ falcon_stat_mask,
+ stats, efx->stats_buffer.addr, true);
+ }
- efx_reado(efx, &cnt, FR_AZ_RX_NODESC_DROP);
- efx->n_rx_nodesc_drop_cnt +=
- EFX_OWORD_FIELD(cnt, FRF_AB_RX_NODESC_DROP_CNT);
+ /* Update derived statistic */
+ efx_update_diff_stat(&stats[FALCON_STAT_rx_bad_bytes],
+ stats[FALCON_STAT_rx_bytes] -
+ stats[FALCON_STAT_rx_good_bytes] -
+ stats[FALCON_STAT_rx_control] * 64);
+ }
- if (nic_data->stats_pending &&
- *nic_data->stats_dma_done == FALCON_STATS_DONE) {
- nic_data->stats_pending = false;
- rmb(); /* read the done flag before the stats */
- efx->mac_op->update_stats(efx);
+ if (full_stats)
+ memcpy(full_stats, stats, sizeof(u64) * FALCON_STAT_COUNT);
+
+ if (core_stats) {
+ core_stats->rx_packets = stats[FALCON_STAT_rx_packets];
+ core_stats->tx_packets = stats[FALCON_STAT_tx_packets];
+ core_stats->rx_bytes = stats[FALCON_STAT_rx_bytes];
+ core_stats->tx_bytes = stats[FALCON_STAT_tx_bytes];
+ core_stats->rx_dropped = stats[FALCON_STAT_rx_nodesc_drop_cnt];
+ core_stats->multicast = stats[FALCON_STAT_rx_multicast];
+ core_stats->rx_length_errors =
+ stats[FALCON_STAT_rx_gtjumbo] +
+ stats[FALCON_STAT_rx_length_error];
+ core_stats->rx_crc_errors = stats[FALCON_STAT_rx_bad];
+ core_stats->rx_frame_errors = stats[FALCON_STAT_rx_align_error];
+ core_stats->rx_fifo_errors = stats[FALCON_STAT_rx_overflow];
+
+ core_stats->rx_errors = (core_stats->rx_length_errors +
+ core_stats->rx_crc_errors +
+ core_stats->rx_frame_errors +
+ stats[FALCON_STAT_rx_symbol_error]);
}
+
+ return FALCON_STAT_COUNT;
}
void falcon_start_nic_stats(struct efx_nic *efx)
@@ -1690,6 +2612,14 @@ void falcon_start_nic_stats(struct efx_nic *efx)
spin_unlock_bh(&efx->stats_lock);
}
+/* We don't acutally pull stats on falcon. Wait 10ms so that
+ * they arrive when we call this just after start_stats
+ */
+static void falcon_pull_nic_stats(struct efx_nic *efx)
+{
+ msleep(10);
+}
+
void falcon_stop_nic_stats(struct efx_nic *efx)
{
struct falcon_nic_data *nic_data = efx->nic_data;
@@ -1706,7 +2636,7 @@ void falcon_stop_nic_stats(struct efx_nic *efx)
/* Wait enough time for the most recent transfer to
* complete. */
for (i = 0; i < 4 && nic_data->stats_pending; i++) {
- if (*nic_data->stats_dma_done == FALCON_STATS_DONE)
+ if (FALCON_XMAC_STATS_DMA_FLAG(efx))
break;
msleep(1);
}
@@ -1750,10 +2680,12 @@ static int falcon_set_wol(struct efx_nic *efx, u32 type)
*/
const struct efx_nic_type falcon_a1_nic_type = {
+ .mem_map_size = falcon_a1_mem_map_size,
.probe = falcon_probe_nic,
.remove = falcon_remove_nic,
.init = falcon_init_nic,
- .fini = efx_port_dummy_op_void,
+ .dimension_resources = falcon_dimension_resources,
+ .fini = falcon_irq_ack_a1,
.monitor = falcon_monitor,
.map_reset_reason = falcon_map_reset_reason,
.map_reset_flags = falcon_map_reset_flags,
@@ -1761,22 +2693,74 @@ const struct efx_nic_type falcon_a1_nic_type = {
.probe_port = falcon_probe_port,
.remove_port = falcon_remove_port,
.handle_global_event = falcon_handle_global_event,
+ .fini_dmaq = efx_farch_fini_dmaq,
.prepare_flush = falcon_prepare_flush,
+ .finish_flush = efx_port_dummy_op_void,
+ .prepare_flr = efx_port_dummy_op_void,
+ .finish_flr = efx_farch_finish_flr,
+ .describe_stats = falcon_describe_nic_stats,
.update_stats = falcon_update_nic_stats,
.start_stats = falcon_start_nic_stats,
+ .pull_stats = falcon_pull_nic_stats,
.stop_stats = falcon_stop_nic_stats,
.set_id_led = falcon_set_id_led,
.push_irq_moderation = falcon_push_irq_moderation,
- .push_multicast_hash = falcon_push_multicast_hash,
.reconfigure_port = falcon_reconfigure_port,
+ .prepare_enable_fc_tx = falcon_a1_prepare_enable_fc_tx,
+ .reconfigure_mac = falcon_reconfigure_xmac,
+ .check_mac_fault = falcon_xmac_check_fault,
.get_wol = falcon_get_wol,
.set_wol = falcon_set_wol,
.resume_wol = efx_port_dummy_op_void,
.test_nvram = falcon_test_nvram,
- .default_mac_ops = &falcon_xmac_operations,
+ .irq_enable_master = efx_farch_irq_enable_master,
+ .irq_test_generate = efx_farch_irq_test_generate,
+ .irq_disable_non_ev = efx_farch_irq_disable_master,
+ .irq_handle_msi = efx_farch_msi_interrupt,
+ .irq_handle_legacy = falcon_legacy_interrupt_a1,
+ .tx_probe = efx_farch_tx_probe,
+ .tx_init = efx_farch_tx_init,
+ .tx_remove = efx_farch_tx_remove,
+ .tx_write = efx_farch_tx_write,
+ .rx_push_rss_config = efx_port_dummy_op_void,
+ .rx_probe = efx_farch_rx_probe,
+ .rx_init = efx_farch_rx_init,
+ .rx_remove = efx_farch_rx_remove,
+ .rx_write = efx_farch_rx_write,
+ .rx_defer_refill = efx_farch_rx_defer_refill,
+ .ev_probe = efx_farch_ev_probe,
+ .ev_init = efx_farch_ev_init,
+ .ev_fini = efx_farch_ev_fini,
+ .ev_remove = efx_farch_ev_remove,
+ .ev_process = efx_farch_ev_process,
+ .ev_read_ack = efx_farch_ev_read_ack,
+ .ev_test_generate = efx_farch_ev_test_generate,
+
+ /* We don't expose the filter table on Falcon A1 as it is not
+ * mapped into function 0, but these implementations still
+ * work with a degenerate case of all tables set to size 0.
+ */
+ .filter_table_probe = efx_farch_filter_table_probe,
+ .filter_table_restore = efx_farch_filter_table_restore,
+ .filter_table_remove = efx_farch_filter_table_remove,
+ .filter_insert = efx_farch_filter_insert,
+ .filter_remove_safe = efx_farch_filter_remove_safe,
+ .filter_get_safe = efx_farch_filter_get_safe,
+ .filter_clear_rx = efx_farch_filter_clear_rx,
+ .filter_count_rx_used = efx_farch_filter_count_rx_used,
+ .filter_get_rx_id_limit = efx_farch_filter_get_rx_id_limit,
+ .filter_get_rx_ids = efx_farch_filter_get_rx_ids,
+
+#ifdef CONFIG_SFC_MTD
+ .mtd_probe = falcon_mtd_probe,
+ .mtd_rename = falcon_mtd_rename,
+ .mtd_read = falcon_mtd_read,
+ .mtd_erase = falcon_mtd_erase,
+ .mtd_write = falcon_mtd_write,
+ .mtd_sync = falcon_mtd_sync,
+#endif
.revision = EFX_REV_FALCON_A1,
- .mem_map_size = 0x20000,
.txd_ptr_tbl_base = FR_AA_TX_DESC_PTR_TBL_KER,
.rxd_ptr_tbl_base = FR_AA_RX_DESC_PTR_TBL_KER,
.buf_tbl_base = FR_AA_BUF_FULL_TBL_KER,
@@ -1784,17 +2768,19 @@ const struct efx_nic_type falcon_a1_nic_type = {
.evq_rptr_tbl_base = FR_AA_EVQ_RPTR_KER,
.max_dma_mask = DMA_BIT_MASK(FSF_AZ_TX_KER_BUF_ADDR_WIDTH),
.rx_buffer_padding = 0x24,
+ .can_rx_scatter = false,
.max_interrupt_mode = EFX_INT_MODE_MSI,
- .phys_addr_channels = 4,
- .tx_dc_base = 0x130000,
- .rx_dc_base = 0x100000,
+ .timer_period_max = 1 << FRF_AB_TC_TIMER_VAL_WIDTH,
.offload_features = NETIF_F_IP_CSUM,
+ .mcdi_max_ver = -1,
};
const struct efx_nic_type falcon_b0_nic_type = {
+ .mem_map_size = falcon_b0_mem_map_size,
.probe = falcon_probe_nic,
.remove = falcon_remove_nic,
.init = falcon_init_nic,
+ .dimension_resources = falcon_dimension_resources,
.fini = efx_port_dummy_op_void,
.monitor = falcon_monitor,
.map_reset_reason = falcon_map_reset_reason,
@@ -1803,42 +2789,87 @@ const struct efx_nic_type falcon_b0_nic_type = {
.probe_port = falcon_probe_port,
.remove_port = falcon_remove_port,
.handle_global_event = falcon_handle_global_event,
+ .fini_dmaq = efx_farch_fini_dmaq,
.prepare_flush = falcon_prepare_flush,
+ .finish_flush = efx_port_dummy_op_void,
+ .prepare_flr = efx_port_dummy_op_void,
+ .finish_flr = efx_farch_finish_flr,
+ .describe_stats = falcon_describe_nic_stats,
.update_stats = falcon_update_nic_stats,
.start_stats = falcon_start_nic_stats,
+ .pull_stats = falcon_pull_nic_stats,
.stop_stats = falcon_stop_nic_stats,
.set_id_led = falcon_set_id_led,
.push_irq_moderation = falcon_push_irq_moderation,
- .push_multicast_hash = falcon_push_multicast_hash,
.reconfigure_port = falcon_reconfigure_port,
+ .prepare_enable_fc_tx = falcon_b0_prepare_enable_fc_tx,
+ .reconfigure_mac = falcon_reconfigure_xmac,
+ .check_mac_fault = falcon_xmac_check_fault,
.get_wol = falcon_get_wol,
.set_wol = falcon_set_wol,
.resume_wol = efx_port_dummy_op_void,
- .test_registers = falcon_b0_test_registers,
+ .test_chip = falcon_b0_test_chip,
.test_nvram = falcon_test_nvram,
- .default_mac_ops = &falcon_xmac_operations,
+ .irq_enable_master = efx_farch_irq_enable_master,
+ .irq_test_generate = efx_farch_irq_test_generate,
+ .irq_disable_non_ev = efx_farch_irq_disable_master,
+ .irq_handle_msi = efx_farch_msi_interrupt,
+ .irq_handle_legacy = efx_farch_legacy_interrupt,
+ .tx_probe = efx_farch_tx_probe,
+ .tx_init = efx_farch_tx_init,
+ .tx_remove = efx_farch_tx_remove,
+ .tx_write = efx_farch_tx_write,
+ .rx_push_rss_config = falcon_b0_rx_push_rss_config,
+ .rx_probe = efx_farch_rx_probe,
+ .rx_init = efx_farch_rx_init,
+ .rx_remove = efx_farch_rx_remove,
+ .rx_write = efx_farch_rx_write,
+ .rx_defer_refill = efx_farch_rx_defer_refill,
+ .ev_probe = efx_farch_ev_probe,
+ .ev_init = efx_farch_ev_init,
+ .ev_fini = efx_farch_ev_fini,
+ .ev_remove = efx_farch_ev_remove,
+ .ev_process = efx_farch_ev_process,
+ .ev_read_ack = efx_farch_ev_read_ack,
+ .ev_test_generate = efx_farch_ev_test_generate,
+ .filter_table_probe = efx_farch_filter_table_probe,
+ .filter_table_restore = efx_farch_filter_table_restore,
+ .filter_table_remove = efx_farch_filter_table_remove,
+ .filter_update_rx_scatter = efx_farch_filter_update_rx_scatter,
+ .filter_insert = efx_farch_filter_insert,
+ .filter_remove_safe = efx_farch_filter_remove_safe,
+ .filter_get_safe = efx_farch_filter_get_safe,
+ .filter_clear_rx = efx_farch_filter_clear_rx,
+ .filter_count_rx_used = efx_farch_filter_count_rx_used,
+ .filter_get_rx_id_limit = efx_farch_filter_get_rx_id_limit,
+ .filter_get_rx_ids = efx_farch_filter_get_rx_ids,
+#ifdef CONFIG_RFS_ACCEL
+ .filter_rfs_insert = efx_farch_filter_rfs_insert,
+ .filter_rfs_expire_one = efx_farch_filter_rfs_expire_one,
+#endif
+#ifdef CONFIG_SFC_MTD
+ .mtd_probe = falcon_mtd_probe,
+ .mtd_rename = falcon_mtd_rename,
+ .mtd_read = falcon_mtd_read,
+ .mtd_erase = falcon_mtd_erase,
+ .mtd_write = falcon_mtd_write,
+ .mtd_sync = falcon_mtd_sync,
+#endif
.revision = EFX_REV_FALCON_B0,
- /* Map everything up to and including the RSS indirection
- * table. Don't map MSI-X table, MSI-X PBA since Linux
- * requires that they not be mapped. */
- .mem_map_size = (FR_BZ_RX_INDIRECTION_TBL +
- FR_BZ_RX_INDIRECTION_TBL_STEP *
- FR_BZ_RX_INDIRECTION_TBL_ROWS),
.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
.rxd_ptr_tbl_base = FR_BZ_RX_DESC_PTR_TBL,
.buf_tbl_base = FR_BZ_BUF_FULL_TBL,
.evq_ptr_tbl_base = FR_BZ_EVQ_PTR_TBL,
.evq_rptr_tbl_base = FR_BZ_EVQ_RPTR,
.max_dma_mask = DMA_BIT_MASK(FSF_AZ_TX_KER_BUF_ADDR_WIDTH),
- .rx_buffer_hash_size = 0x10,
+ .rx_prefix_size = FS_BZ_RX_PREFIX_SIZE,
+ .rx_hash_offset = FS_BZ_RX_PREFIX_HASH_OFST,
.rx_buffer_padding = 0,
+ .can_rx_scatter = true,
.max_interrupt_mode = EFX_INT_MODE_MSIX,
- .phys_addr_channels = 32, /* Hardware limit is 64, but the legacy
- * interrupt handler only supports 32
- * channels */
- .tx_dc_base = 0x130000,
- .rx_dc_base = 0x100000,
+ .timer_period_max = 1 << FRF_AB_TC_TIMER_VAL_WIDTH,
.offload_features = NETIF_F_IP_CSUM | NETIF_F_RXHASH | NETIF_F_NTUPLE,
+ .mcdi_max_ver = -1,
+ .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
};
-
diff --git a/drivers/net/ethernet/sfc/falcon_boards.c b/drivers/net/ethernet/sfc/falcon_boards.c
index 6cc16b8cc6f..1736f4b806a 100644
--- a/drivers/net/ethernet/sfc/falcon_boards.c
+++ b/drivers/net/ethernet/sfc/falcon_boards.c
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2007-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2007-2012 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -87,7 +87,7 @@ static const u8 falcon_lm87_common_regs[] = {
0
};
-static int efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info,
+static int efx_init_lm87(struct efx_nic *efx, const struct i2c_board_info *info,
const u8 *reg_values)
{
struct falcon_board *board = falcon_board(efx);
@@ -179,7 +179,7 @@ static int efx_check_lm87(struct efx_nic *efx, unsigned mask)
#else /* !CONFIG_SENSORS_LM87 */
static inline int
-efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info,
+efx_init_lm87(struct efx_nic *efx, const struct i2c_board_info *info,
const u8 *reg_values)
{
return 0;
@@ -380,7 +380,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev,
new_mode = PHY_MODE_SPECIAL;
if (!((old_mode ^ new_mode) & PHY_MODE_SPECIAL)) {
err = 0;
- } else if (efx->state != STATE_RUNNING || netif_running(efx->net_dev)) {
+ } else if (efx->state != STATE_READY || netif_running(efx->net_dev)) {
err = -EBUSY;
} else {
/* Reset the PHY, reconfigure the MAC and enable/disable
@@ -442,7 +442,7 @@ static int sfe4001_check_hw(struct efx_nic *efx)
return (status < 0) ? -EIO : -ERANGE;
}
-static struct i2c_board_info sfe4001_hwmon_info = {
+static const struct i2c_board_info sfe4001_hwmon_info = {
I2C_BOARD_INFO("max6647", 0x4e),
};
@@ -522,7 +522,7 @@ static const u8 sfe4002_lm87_regs[] = {
0
};
-static struct i2c_board_info sfe4002_hwmon_info = {
+static const struct i2c_board_info sfe4002_hwmon_info = {
I2C_BOARD_INFO("lm87", 0x2e),
.platform_data = &sfe4002_lm87_channel,
};
@@ -591,7 +591,7 @@ static const u8 sfn4112f_lm87_regs[] = {
0
};
-static struct i2c_board_info sfn4112f_hwmon_info = {
+static const struct i2c_board_info sfn4112f_hwmon_info = {
I2C_BOARD_INFO("lm87", 0x2e),
.platform_data = &sfn4112f_lm87_channel,
};
@@ -653,7 +653,7 @@ static const u8 sfe4003_lm87_regs[] = {
0
};
-static struct i2c_board_info sfe4003_hwmon_info = {
+static const struct i2c_board_info sfe4003_hwmon_info = {
I2C_BOARD_INFO("lm87", 0x2e),
.platform_data = &sfe4003_lm87_channel,
};
@@ -709,8 +709,6 @@ static int sfe4003_init(struct efx_nic *efx)
static const struct falcon_board_type board_types[] = {
{
.id = FALCON_BOARD_SFE4001,
- .ref_model = "SFE4001",
- .gen_type = "10GBASE-T adapter",
.init = sfe4001_init,
.init_phy = efx_port_dummy_op_void,
.fini = sfe4001_fini,
@@ -719,8 +717,6 @@ static const struct falcon_board_type board_types[] = {
},
{
.id = FALCON_BOARD_SFE4002,
- .ref_model = "SFE4002",
- .gen_type = "XFP adapter",
.init = sfe4002_init,
.init_phy = sfe4002_init_phy,
.fini = efx_fini_lm87,
@@ -729,8 +725,6 @@ static const struct falcon_board_type board_types[] = {
},
{
.id = FALCON_BOARD_SFE4003,
- .ref_model = "SFE4003",
- .gen_type = "10GBASE-CX4 adapter",
.init = sfe4003_init,
.init_phy = sfe4003_init_phy,
.fini = efx_fini_lm87,
@@ -739,8 +733,6 @@ static const struct falcon_board_type board_types[] = {
},
{
.id = FALCON_BOARD_SFN4112F,
- .ref_model = "SFN4112F",
- .gen_type = "SFP+ adapter",
.init = sfn4112f_init,
.init_phy = sfn4112f_init_phy,
.fini = efx_fini_lm87,
@@ -763,11 +755,6 @@ int falcon_probe_board(struct efx_nic *efx, u16 revision_info)
board->type = &board_types[i];
if (board->type) {
- netif_info(efx, probe, efx->net_dev, "board is %s rev %c%d\n",
- (efx->pci_dev->subsystem_vendor ==
- PCI_VENDOR_ID_SOLARFLARE)
- ? board->type->ref_model : board->type->gen_type,
- 'A' + board->major, board->minor);
return 0;
} else {
netif_err(efx, probe, efx->net_dev, "unknown board type %d\n",
diff --git a/drivers/net/ethernet/sfc/falcon_xmac.c b/drivers/net/ethernet/sfc/falcon_xmac.c
deleted file mode 100644
index 9516452c079..00000000000
--- a/drivers/net/ethernet/sfc/falcon_xmac.c
+++ /dev/null
@@ -1,369 +0,0 @@
-/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
- */
-
-#include <linux/delay.h>
-#include "net_driver.h"
-#include "efx.h"
-#include "nic.h"
-#include "regs.h"
-#include "io.h"
-#include "mac.h"
-#include "mdio_10g.h"
-#include "workarounds.h"
-
-/**************************************************************************
- *
- * MAC operations
- *
- *************************************************************************/
-
-/* Configure the XAUI driver that is an output from Falcon */
-void falcon_setup_xaui(struct efx_nic *efx)
-{
- efx_oword_t sdctl, txdrv;
-
- /* Move the XAUI into low power, unless there is no PHY, in
- * which case the XAUI will have to drive a cable. */
- if (efx->phy_type == PHY_TYPE_NONE)
- return;
-
- efx_reado(efx, &sdctl, FR_AB_XX_SD_CTL);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVD, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVD, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVC, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVC, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVB, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVB, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_HIDRVA, FFE_AB_XX_SD_CTL_DRV_DEF);
- EFX_SET_OWORD_FIELD(sdctl, FRF_AB_XX_LODRVA, FFE_AB_XX_SD_CTL_DRV_DEF);
- efx_writeo(efx, &sdctl, FR_AB_XX_SD_CTL);
-
- EFX_POPULATE_OWORD_8(txdrv,
- FRF_AB_XX_DEQD, FFE_AB_XX_TXDRV_DEQ_DEF,
- FRF_AB_XX_DEQC, FFE_AB_XX_TXDRV_DEQ_DEF,
- FRF_AB_XX_DEQB, FFE_AB_XX_TXDRV_DEQ_DEF,
- FRF_AB_XX_DEQA, FFE_AB_XX_TXDRV_DEQ_DEF,
- FRF_AB_XX_DTXD, FFE_AB_XX_TXDRV_DTX_DEF,
- FRF_AB_XX_DTXC, FFE_AB_XX_TXDRV_DTX_DEF,
- FRF_AB_XX_DTXB, FFE_AB_XX_TXDRV_DTX_DEF,
- FRF_AB_XX_DTXA, FFE_AB_XX_TXDRV_DTX_DEF);
- efx_writeo(efx, &txdrv, FR_AB_XX_TXDRV_CTL);
-}
-
-int falcon_reset_xaui(struct efx_nic *efx)
-{
- struct falcon_nic_data *nic_data = efx->nic_data;
- efx_oword_t reg;
- int count;
-
- /* Don't fetch MAC statistics over an XMAC reset */
- WARN_ON(nic_data->stats_disable_count == 0);
-
- /* Start reset sequence */
- EFX_POPULATE_OWORD_1(reg, FRF_AB_XX_RST_XX_EN, 1);
- efx_writeo(efx, &reg, FR_AB_XX_PWR_RST);
-
- /* Wait up to 10 ms for completion, then reinitialise */
- for (count = 0; count < 1000; count++) {
- efx_reado(efx, &reg, FR_AB_XX_PWR_RST);
- if (EFX_OWORD_FIELD(reg, FRF_AB_XX_RST_XX_EN) == 0 &&
- EFX_OWORD_FIELD(reg, FRF_AB_XX_SD_RST_ACT) == 0) {
- falcon_setup_xaui(efx);
- return 0;
- }
- udelay(10);
- }
- netif_err(efx, hw, efx->net_dev,
- "timed out waiting for XAUI/XGXS reset\n");
- return -ETIMEDOUT;
-}
-
-static void falcon_ack_status_intr(struct efx_nic *efx)
-{
- struct falcon_nic_data *nic_data = efx->nic_data;
- efx_oword_t reg;
-
- if ((efx_nic_rev(efx) != EFX_REV_FALCON_B0) || LOOPBACK_INTERNAL(efx))
- return;
-
- /* We expect xgmii faults if the wireside link is down */
- if (!EFX_WORKAROUND_5147(efx) || !efx->link_state.up)
- return;
-
- /* We can only use this interrupt to signal the negative edge of
- * xaui_align [we have to poll the positive edge]. */
- if (nic_data->xmac_poll_required)
- return;
-
- efx_reado(efx, &reg, FR_AB_XM_MGT_INT_MSK);
-}
-
-static bool falcon_xgxs_link_ok(struct efx_nic *efx)
-{
- efx_oword_t reg;
- bool align_done, link_ok = false;
- int sync_status;
-
- /* Read link status */
- efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
-
- align_done = EFX_OWORD_FIELD(reg, FRF_AB_XX_ALIGN_DONE);
- sync_status = EFX_OWORD_FIELD(reg, FRF_AB_XX_SYNC_STAT);
- if (align_done && (sync_status == FFE_AB_XX_STAT_ALL_LANES))
- link_ok = true;
-
- /* Clear link status ready for next read */
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_COMMA_DET, FFE_AB_XX_STAT_ALL_LANES);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_CHAR_ERR, FFE_AB_XX_STAT_ALL_LANES);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_DISPERR, FFE_AB_XX_STAT_ALL_LANES);
- efx_writeo(efx, &reg, FR_AB_XX_CORE_STAT);
-
- return link_ok;
-}
-
-static bool falcon_xmac_link_ok(struct efx_nic *efx)
-{
- /*
- * Check MAC's XGXS link status except when using XGMII loopback
- * which bypasses the XGXS block.
- * If possible, check PHY's XGXS link status except when using
- * MAC loopback.
- */
- return (efx->loopback_mode == LOOPBACK_XGMII ||
- falcon_xgxs_link_ok(efx)) &&
- (!(efx->mdio.mmds & (1 << MDIO_MMD_PHYXS)) ||
- LOOPBACK_INTERNAL(efx) ||
- efx_mdio_phyxgxs_lane_sync(efx));
-}
-
-static void falcon_reconfigure_xmac_core(struct efx_nic *efx)
-{
- unsigned int max_frame_len;
- efx_oword_t reg;
- bool rx_fc = !!(efx->link_state.fc & EFX_FC_RX);
- bool tx_fc = !!(efx->link_state.fc & EFX_FC_TX);
-
- /* Configure MAC - cut-thru mode is hard wired on */
- EFX_POPULATE_OWORD_3(reg,
- FRF_AB_XM_RX_JUMBO_MODE, 1,
- FRF_AB_XM_TX_STAT_EN, 1,
- FRF_AB_XM_RX_STAT_EN, 1);
- efx_writeo(efx, &reg, FR_AB_XM_GLB_CFG);
-
- /* Configure TX */
- EFX_POPULATE_OWORD_6(reg,
- FRF_AB_XM_TXEN, 1,
- FRF_AB_XM_TX_PRMBL, 1,
- FRF_AB_XM_AUTO_PAD, 1,
- FRF_AB_XM_TXCRC, 1,
- FRF_AB_XM_FCNTL, tx_fc,
- FRF_AB_XM_IPG, 0x3);
- efx_writeo(efx, &reg, FR_AB_XM_TX_CFG);
-
- /* Configure RX */
- EFX_POPULATE_OWORD_5(reg,
- FRF_AB_XM_RXEN, 1,
- FRF_AB_XM_AUTO_DEPAD, 0,
- FRF_AB_XM_ACPT_ALL_MCAST, 1,
- FRF_AB_XM_ACPT_ALL_UCAST, efx->promiscuous,
- FRF_AB_XM_PASS_CRC_ERR, 1);
- efx_writeo(efx, &reg, FR_AB_XM_RX_CFG);
-
- /* Set frame length */
- max_frame_len = EFX_MAX_FRAME_LEN(efx->net_dev->mtu);
- EFX_POPULATE_OWORD_1(reg, FRF_AB_XM_MAX_RX_FRM_SIZE, max_frame_len);
- efx_writeo(efx, &reg, FR_AB_XM_RX_PARAM);
- EFX_POPULATE_OWORD_2(reg,
- FRF_AB_XM_MAX_TX_FRM_SIZE, max_frame_len,
- FRF_AB_XM_TX_JUMBO_MODE, 1);
- efx_writeo(efx, &reg, FR_AB_XM_TX_PARAM);
-
- EFX_POPULATE_OWORD_2(reg,
- FRF_AB_XM_PAUSE_TIME, 0xfffe, /* MAX PAUSE TIME */
- FRF_AB_XM_DIS_FCNTL, !rx_fc);
- efx_writeo(efx, &reg, FR_AB_XM_FC);
-
- /* Set MAC address */
- memcpy(&reg, &efx->net_dev->dev_addr[0], 4);
- efx_writeo(efx, &reg, FR_AB_XM_ADR_LO);
- memcpy(&reg, &efx->net_dev->dev_addr[4], 2);
- efx_writeo(efx, &reg, FR_AB_XM_ADR_HI);
-}
-
-static void falcon_reconfigure_xgxs_core(struct efx_nic *efx)
-{
- efx_oword_t reg;
- bool xgxs_loopback = (efx->loopback_mode == LOOPBACK_XGXS);
- bool xaui_loopback = (efx->loopback_mode == LOOPBACK_XAUI);
- bool xgmii_loopback = (efx->loopback_mode == LOOPBACK_XGMII);
-
- /* XGXS block is flaky and will need to be reset if moving
- * into our out of XGMII, XGXS or XAUI loopbacks. */
- if (EFX_WORKAROUND_5147(efx)) {
- bool old_xgmii_loopback, old_xgxs_loopback, old_xaui_loopback;
- bool reset_xgxs;
-
- efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
- old_xgxs_loopback = EFX_OWORD_FIELD(reg, FRF_AB_XX_XGXS_LB_EN);
- old_xgmii_loopback =
- EFX_OWORD_FIELD(reg, FRF_AB_XX_XGMII_LB_EN);
-
- efx_reado(efx, &reg, FR_AB_XX_SD_CTL);
- old_xaui_loopback = EFX_OWORD_FIELD(reg, FRF_AB_XX_LPBKA);
-
- /* The PHY driver may have turned XAUI off */
- reset_xgxs = ((xgxs_loopback != old_xgxs_loopback) ||
- (xaui_loopback != old_xaui_loopback) ||
- (xgmii_loopback != old_xgmii_loopback));
-
- if (reset_xgxs)
- falcon_reset_xaui(efx);
- }
-
- efx_reado(efx, &reg, FR_AB_XX_CORE_STAT);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_FORCE_SIG,
- (xgxs_loopback || xaui_loopback) ?
- FFE_AB_XX_FORCE_SIG_ALL_LANES : 0);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_XGXS_LB_EN, xgxs_loopback);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_XGMII_LB_EN, xgmii_loopback);
- efx_writeo(efx, &reg, FR_AB_XX_CORE_STAT);
-
- efx_reado(efx, &reg, FR_AB_XX_SD_CTL);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKD, xaui_loopback);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKC, xaui_loopback);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKB, xaui_loopback);
- EFX_SET_OWORD_FIELD(reg, FRF_AB_XX_LPBKA, xaui_loopback);
- efx_writeo(efx, &reg, FR_AB_XX_SD_CTL);
-}
-
-
-/* Try to bring up the Falcon side of the Falcon-Phy XAUI link */
-static bool falcon_xmac_link_ok_retry(struct efx_nic *efx, int tries)
-{
- bool mac_up = falcon_xmac_link_ok(efx);
-
- if (LOOPBACK_MASK(efx) & LOOPBACKS_EXTERNAL(efx) & LOOPBACKS_WS ||
- efx_phy_mode_disabled(efx->phy_mode))
- /* XAUI link is expected to be down */
- return mac_up;
-
- falcon_stop_nic_stats(efx);
-
- while (!mac_up && tries) {
- netif_dbg(efx, hw, efx->net_dev, "bashing xaui\n");
- falcon_reset_xaui(efx);
- udelay(200);
-
- mac_up = falcon_xmac_link_ok(efx);
- --tries;
- }
-
- falcon_start_nic_stats(efx);
-
- return mac_up;
-}
-
-static bool falcon_xmac_check_fault(struct efx_nic *efx)
-{
- return !falcon_xmac_link_ok_retry(efx, 5);
-}
-
-static int falcon_reconfigure_xmac(struct efx_nic *efx)
-{
- struct falcon_nic_data *nic_data = efx->nic_data;
-
- falcon_reconfigure_xgxs_core(efx);
- falcon_reconfigure_xmac_core(efx);
-
- falcon_reconfigure_mac_wrapper(efx);
-
- nic_data->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 5);
- falcon_ack_status_intr(efx);
-
- return 0;
-}
-
-static void falcon_update_stats_xmac(struct efx_nic *efx)
-{
- struct efx_mac_stats *mac_stats = &efx->mac_stats;
-
- /* Update MAC stats from DMAed values */
- FALCON_STAT(efx, XgRxOctets, rx_bytes);
- FALCON_STAT(efx, XgRxOctetsOK, rx_good_bytes);
- FALCON_STAT(efx, XgRxPkts, rx_packets);
- FALCON_STAT(efx, XgRxPktsOK, rx_good);
- FALCON_STAT(efx, XgRxBroadcastPkts, rx_broadcast);
- FALCON_STAT(efx, XgRxMulticastPkts, rx_multicast);
- FALCON_STAT(efx, XgRxUnicastPkts, rx_unicast);
- FALCON_STAT(efx, XgRxUndersizePkts, rx_lt64);
- FALCON_STAT(efx, XgRxOversizePkts, rx_gtjumbo);
- FALCON_STAT(efx, XgRxJabberPkts, rx_bad_gtjumbo);
- FALCON_STAT(efx, XgRxUndersizeFCSerrorPkts, rx_bad_lt64);
- FALCON_STAT(efx, XgRxDropEvents, rx_overflow);
- FALCON_STAT(efx, XgRxFCSerrorPkts, rx_bad);
- FALCON_STAT(efx, XgRxAlignError, rx_align_error);
- FALCON_STAT(efx, XgRxSymbolError, rx_symbol_error);
- FALCON_STAT(efx, XgRxInternalMACError, rx_internal_error);
- FALCON_STAT(efx, XgRxControlPkts, rx_control);
- FALCON_STAT(efx, XgRxPausePkts, rx_pause);
- FALCON_STAT(efx, XgRxPkts64Octets, rx_64);
- FALCON_STAT(efx, XgRxPkts65to127Octets, rx_65_to_127);
- FALCON_STAT(efx, XgRxPkts128to255Octets, rx_128_to_255);
- FALCON_STAT(efx, XgRxPkts256to511Octets, rx_256_to_511);
- FALCON_STAT(efx, XgRxPkts512to1023Octets, rx_512_to_1023);
- FALCON_STAT(efx, XgRxPkts1024to15xxOctets, rx_1024_to_15xx);
- FALCON_STAT(efx, XgRxPkts15xxtoMaxOctets, rx_15xx_to_jumbo);
- FALCON_STAT(efx, XgRxLengthError, rx_length_error);
- FALCON_STAT(efx, XgTxPkts, tx_packets);
- FALCON_STAT(efx, XgTxOctets, tx_bytes);
- FALCON_STAT(efx, XgTxMulticastPkts, tx_multicast);
- FALCON_STAT(efx, XgTxBroadcastPkts, tx_broadcast);
- FALCON_STAT(efx, XgTxUnicastPkts, tx_unicast);
- FALCON_STAT(efx, XgTxControlPkts, tx_control);
- FALCON_STAT(efx, XgTxPausePkts, tx_pause);
- FALCON_STAT(efx, XgTxPkts64Octets, tx_64);
- FALCON_STAT(efx, XgTxPkts65to127Octets, tx_65_to_127);
- FALCON_STAT(efx, XgTxPkts128to255Octets, tx_128_to_255);
- FALCON_STAT(efx, XgTxPkts256to511Octets, tx_256_to_511);
- FALCON_STAT(efx, XgTxPkts512to1023Octets, tx_512_to_1023);
- FALCON_STAT(efx, XgTxPkts1024to15xxOctets, tx_1024_to_15xx);
- FALCON_STAT(efx, XgTxPkts1519toMaxOctets, tx_15xx_to_jumbo);
- FALCON_STAT(efx, XgTxUndersizePkts, tx_lt64);
- FALCON_STAT(efx, XgTxOversizePkts, tx_gtjumbo);
- FALCON_STAT(efx, XgTxNonTcpUdpPkt, tx_non_tcpudp);
- FALCON_STAT(efx, XgTxMacSrcErrPkt, tx_mac_src_error);
- FALCON_STAT(efx, XgTxIpSrcErrPkt, tx_ip_src_error);
-
- /* Update derived statistics */
- mac_stats->tx_good_bytes =
- (mac_stats->tx_bytes - mac_stats->tx_bad_bytes -
- mac_stats->tx_control * 64);
- mac_stats->rx_bad_bytes =
- (mac_stats->rx_bytes - mac_stats->rx_good_bytes -
- mac_stats->rx_control * 64);
-}
-
-void falcon_poll_xmac(struct efx_nic *efx)
-{
- struct falcon_nic_data *nic_data = efx->nic_data;
-
- if (!EFX_WORKAROUND_5147(efx) || !efx->link_state.up ||
- !nic_data->xmac_poll_required)
- return;
-
- nic_data->xmac_poll_required = !falcon_xmac_link_ok_retry(efx, 1);
- falcon_ack_status_intr(efx);
-}
-
-const struct efx_mac_operations falcon_xmac_operations = {
- .reconfigure = falcon_reconfigure_xmac,
- .update_stats = falcon_update_stats_xmac,
- .check_fault = falcon_xmac_check_fault,
-};
diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c
new file mode 100644
index 00000000000..0537381cd2f
--- /dev/null
+++ b/drivers/net/ethernet/sfc/farch.c
@@ -0,0 +1,2959 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2006-2013 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/bitops.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/crc32.h>
+#include "net_driver.h"
+#include "bitfield.h"
+#include "efx.h"
+#include "nic.h"
+#include "farch_regs.h"
+#include "io.h"
+#include "workarounds.h"
+
+/* Falcon-architecture (SFC4000 and SFC9000-family) support */
+
+/**************************************************************************
+ *
+ * Configurable values
+ *
+ **************************************************************************
+ */
+
+/* This is set to 16 for a good reason. In summary, if larger than
+ * 16, the descriptor cache holds more than a default socket
+ * buffer's worth of packets (for UDP we can only have at most one
+ * socket buffer's worth outstanding). This combined with the fact
+ * that we only get 1 TX event per descriptor cache means the NIC
+ * goes idle.
+ */
+#define TX_DC_ENTRIES 16
+#define TX_DC_ENTRIES_ORDER 1
+
+#define RX_DC_ENTRIES 64
+#define RX_DC_ENTRIES_ORDER 3
+
+/* If EFX_MAX_INT_ERRORS internal errors occur within
+ * EFX_INT_ERROR_EXPIRE seconds, we consider the NIC broken and
+ * disable it.
+ */
+#define EFX_INT_ERROR_EXPIRE 3600
+#define EFX_MAX_INT_ERRORS 5
+
+/* Depth of RX flush request fifo */
+#define EFX_RX_FLUSH_COUNT 4
+
+/* Driver generated events */
+#define _EFX_CHANNEL_MAGIC_TEST 0x000101
+#define _EFX_CHANNEL_MAGIC_FILL 0x000102
+#define _EFX_CHANNEL_MAGIC_RX_DRAIN 0x000103
+#define _EFX_CHANNEL_MAGIC_TX_DRAIN 0x000104
+
+#define _EFX_CHANNEL_MAGIC(_code, _data) ((_code) << 8 | (_data))
+#define _EFX_CHANNEL_MAGIC_CODE(_magic) ((_magic) >> 8)
+
+#define EFX_CHANNEL_MAGIC_TEST(_channel) \
+ _EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_TEST, (_channel)->channel)
+#define EFX_CHANNEL_MAGIC_FILL(_rx_queue) \
+ _EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_FILL, \
+ efx_rx_queue_index(_rx_queue))
+#define EFX_CHANNEL_MAGIC_RX_DRAIN(_rx_queue) \
+ _EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_RX_DRAIN, \
+ efx_rx_queue_index(_rx_queue))
+#define EFX_CHANNEL_MAGIC_TX_DRAIN(_tx_queue) \
+ _EFX_CHANNEL_MAGIC(_EFX_CHANNEL_MAGIC_TX_DRAIN, \
+ (_tx_queue)->queue)
+
+static void efx_farch_magic_event(struct efx_channel *channel, u32 magic);
+
+/**************************************************************************
+ *
+ * Hardware access
+ *
+ **************************************************************************/
+
+static inline void efx_write_buf_tbl(struct efx_nic *efx, efx_qword_t *value,
+ unsigned int index)
+{
+ efx_sram_writeq(efx, efx->membase + efx->type->buf_tbl_base,
+ value, index);
+}
+
+static bool efx_masked_compare_oword(const efx_oword_t *a, const efx_oword_t *b,
+ const efx_oword_t *mask)
+{
+ return ((a->u64[0] ^ b->u64[0]) & mask->u64[0]) ||
+ ((a->u64[1] ^ b->u64[1]) & mask->u64[1]);
+}
+
+int efx_farch_test_registers(struct efx_nic *efx,
+ const struct efx_farch_register_test *regs,
+ size_t n_regs)
+{
+ unsigned address = 0, i, j;
+ efx_oword_t mask, imask, original, reg, buf;
+
+ for (i = 0; i < n_regs; ++i) {
+ address = regs[i].address;
+ mask = imask = regs[i].mask;
+ EFX_INVERT_OWORD(imask);
+
+ efx_reado(efx, &original, address);
+
+ /* bit sweep on and off */
+ for (j = 0; j < 128; j++) {
+ if (!EFX_EXTRACT_OWORD32(mask, j, j))
+ continue;
+
+ /* Test this testable bit can be set in isolation */
+ EFX_AND_OWORD(reg, original, mask);
+ EFX_SET_OWORD32(reg, j, j, 1);
+
+ efx_writeo(efx, &reg, address);
+ efx_reado(efx, &buf, address);
+
+ if (efx_masked_compare_oword(&reg, &buf, &mask))
+ goto fail;
+
+ /* Test this testable bit can be cleared in isolation */
+ EFX_OR_OWORD(reg, original, mask);
+ EFX_SET_OWORD32(reg, j, j, 0);
+
+ efx_writeo(efx, &reg, address);
+ efx_reado(efx, &buf, address);
+
+ if (efx_masked_compare_oword(&reg, &buf, &mask))
+ goto fail;
+ }
+
+ efx_writeo(efx, &original, address);
+ }
+
+ return 0;
+
+fail:
+ netif_err(efx, hw, efx->net_dev,
+ "wrote "EFX_OWORD_FMT" read "EFX_OWORD_FMT
+ " at address 0x%x mask "EFX_OWORD_FMT"\n", EFX_OWORD_VAL(reg),
+ EFX_OWORD_VAL(buf), address, EFX_OWORD_VAL(mask));
+ return -EIO;
+}
+
+/**************************************************************************
+ *
+ * Special buffer handling
+ * Special buffers are used for event queues and the TX and RX
+ * descriptor rings.
+ *
+ *************************************************************************/
+
+/*
+ * Initialise a special buffer
+ *
+ * This will define a buffer (previously allocated via
+ * efx_alloc_special_buffer()) in the buffer table, allowing
+ * it to be used for event queues, descriptor rings etc.
+ */
+static void
+efx_init_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
+{
+ efx_qword_t buf_desc;
+ unsigned int index;
+ dma_addr_t dma_addr;
+ int i;
+
+ EFX_BUG_ON_PARANOID(!buffer->buf.addr);
+
+ /* Write buffer descriptors to NIC */
+ for (i = 0; i < buffer->entries; i++) {
+ index = buffer->index + i;
+ dma_addr = buffer->buf.dma_addr + (i * EFX_BUF_SIZE);
+ netif_dbg(efx, probe, efx->net_dev,
+ "mapping special buffer %d at %llx\n",
+ index, (unsigned long long)dma_addr);
+ EFX_POPULATE_QWORD_3(buf_desc,
+ FRF_AZ_BUF_ADR_REGION, 0,
+ FRF_AZ_BUF_ADR_FBUF, dma_addr >> 12,
+ FRF_AZ_BUF_OWNER_ID_FBUF, 0);
+ efx_write_buf_tbl(efx, &buf_desc, index);
+ }
+}
+
+/* Unmaps a buffer and clears the buffer table entries */
+static void
+efx_fini_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
+{
+ efx_oword_t buf_tbl_upd;
+ unsigned int start = buffer->index;
+ unsigned int end = (buffer->index + buffer->entries - 1);
+
+ if (!buffer->entries)
+ return;
+
+ netif_dbg(efx, hw, efx->net_dev, "unmapping special buffers %d-%d\n",
+ buffer->index, buffer->index + buffer->entries - 1);
+
+ EFX_POPULATE_OWORD_4(buf_tbl_upd,
+ FRF_AZ_BUF_UPD_CMD, 0,
+ FRF_AZ_BUF_CLR_CMD, 1,
+ FRF_AZ_BUF_CLR_END_ID, end,
+ FRF_AZ_BUF_CLR_START_ID, start);
+ efx_writeo(efx, &buf_tbl_upd, FR_AZ_BUF_TBL_UPD);
+}
+
+/*
+ * Allocate a new special buffer
+ *
+ * This allocates memory for a new buffer, clears it and allocates a
+ * new buffer ID range. It does not write into the buffer table.
+ *
+ * This call will allocate 4KB buffers, since 8KB buffers can't be
+ * used for event queues and descriptor rings.
+ */
+static int efx_alloc_special_buffer(struct efx_nic *efx,
+ struct efx_special_buffer *buffer,
+ unsigned int len)
+{
+ len = ALIGN(len, EFX_BUF_SIZE);
+
+ if (efx_nic_alloc_buffer(efx, &buffer->buf, len, GFP_KERNEL))
+ return -ENOMEM;
+ buffer->entries = len / EFX_BUF_SIZE;
+ BUG_ON(buffer->buf.dma_addr & (EFX_BUF_SIZE - 1));
+
+ /* Select new buffer ID */
+ buffer->index = efx->next_buffer_table;
+ efx->next_buffer_table += buffer->entries;
+#ifdef CONFIG_SFC_SRIOV
+ BUG_ON(efx_sriov_enabled(efx) &&
+ efx->vf_buftbl_base < efx->next_buffer_table);
+#endif
+
+ netif_dbg(efx, probe, efx->net_dev,
+ "allocating special buffers %d-%d at %llx+%x "
+ "(virt %p phys %llx)\n", buffer->index,
+ buffer->index + buffer->entries - 1,
+ (u64)buffer->buf.dma_addr, len,
+ buffer->buf.addr, (u64)virt_to_phys(buffer->buf.addr));
+
+ return 0;
+}
+
+static void
+efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
+{
+ if (!buffer->buf.addr)
+ return;
+
+ netif_dbg(efx, hw, efx->net_dev,
+ "deallocating special buffers %d-%d at %llx+%x "
+ "(virt %p phys %llx)\n", buffer->index,
+ buffer->index + buffer->entries - 1,
+ (u64)buffer->buf.dma_addr, buffer->buf.len,
+ buffer->buf.addr, (u64)virt_to_phys(buffer->buf.addr));
+
+ efx_nic_free_buffer(efx, &buffer->buf);
+ buffer->entries = 0;
+}
+
+/**************************************************************************
+ *
+ * TX path
+ *
+ **************************************************************************/
+
+/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */
+static inline void efx_farch_notify_tx_desc(struct efx_tx_queue *tx_queue)
+{
+ unsigned write_ptr;
+ efx_dword_t reg;
+
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ EFX_POPULATE_DWORD_1(reg, FRF_AZ_TX_DESC_WPTR_DWORD, write_ptr);
+ efx_writed_page(tx_queue->efx, &reg,
+ FR_AZ_TX_DESC_UPD_DWORD_P0, tx_queue->queue);
+}
+
+/* Write pointer and first descriptor for TX descriptor ring */
+static inline void efx_farch_push_tx_desc(struct efx_tx_queue *tx_queue,
+ const efx_qword_t *txd)
+{
+ unsigned write_ptr;
+ efx_oword_t reg;
+
+ BUILD_BUG_ON(FRF_AZ_TX_DESC_LBN != 0);
+ BUILD_BUG_ON(FR_AA_TX_DESC_UPD_KER != FR_BZ_TX_DESC_UPD_P0);
+
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ EFX_POPULATE_OWORD_2(reg, FRF_AZ_TX_DESC_PUSH_CMD, true,
+ FRF_AZ_TX_DESC_WPTR, write_ptr);
+ reg.qword[0] = *txd;
+ efx_writeo_page(tx_queue->efx, &reg,
+ FR_BZ_TX_DESC_UPD_P0, tx_queue->queue);
+}
+
+
+/* For each entry inserted into the software descriptor ring, create a
+ * descriptor in the hardware TX descriptor ring (in host memory), and
+ * write a doorbell.
+ */
+void efx_farch_tx_write(struct efx_tx_queue *tx_queue)
+{
+ struct efx_tx_buffer *buffer;
+ efx_qword_t *txd;
+ unsigned write_ptr;
+ unsigned old_write_count = tx_queue->write_count;
+
+ BUG_ON(tx_queue->write_count == tx_queue->insert_count);
+
+ do {
+ write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
+ buffer = &tx_queue->buffer[write_ptr];
+ txd = efx_tx_desc(tx_queue, write_ptr);
+ ++tx_queue->write_count;
+
+ EFX_BUG_ON_PARANOID(buffer->flags & EFX_TX_BUF_OPTION);
+
+ /* Create TX descriptor ring entry */
+ BUILD_BUG_ON(EFX_TX_BUF_CONT != 1);
+ EFX_POPULATE_QWORD_4(*txd,
+ FSF_AZ_TX_KER_CONT,
+ buffer->flags & EFX_TX_BUF_CONT,
+ FSF_AZ_TX_KER_BYTE_COUNT, buffer->len,
+ FSF_AZ_TX_KER_BUF_REGION, 0,
+ FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr);
+ } while (tx_queue->write_count != tx_queue->insert_count);
+
+ wmb(); /* Ensure descriptors are written before they are fetched */
+
+ if (efx_nic_may_push_tx_desc(tx_queue, old_write_count)) {
+ txd = efx_tx_desc(tx_queue,
+ old_write_count & tx_queue->ptr_mask);
+ efx_farch_push_tx_desc(tx_queue, txd);
+ ++tx_queue->pushes;
+ } else {
+ efx_farch_notify_tx_desc(tx_queue);
+ }
+}
+
+/* Allocate hardware resources for a TX queue */
+int efx_farch_tx_probe(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ unsigned entries;
+
+ entries = tx_queue->ptr_mask + 1;
+ return efx_alloc_special_buffer(efx, &tx_queue->txd,
+ entries * sizeof(efx_qword_t));
+}
+
+void efx_farch_tx_init(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ efx_oword_t reg;
+
+ /* Pin TX descriptor ring */
+ efx_init_special_buffer(efx, &tx_queue->txd);
+
+ /* Push TX descriptor ring to card */
+ EFX_POPULATE_OWORD_10(reg,
+ FRF_AZ_TX_DESCQ_EN, 1,
+ FRF_AZ_TX_ISCSI_DDIG_EN, 0,
+ FRF_AZ_TX_ISCSI_HDIG_EN, 0,
+ FRF_AZ_TX_DESCQ_BUF_BASE_ID, tx_queue->txd.index,
+ FRF_AZ_TX_DESCQ_EVQ_ID,
+ tx_queue->channel->channel,
+ FRF_AZ_TX_DESCQ_OWNER_ID, 0,
+ FRF_AZ_TX_DESCQ_LABEL, tx_queue->queue,
+ FRF_AZ_TX_DESCQ_SIZE,
+ __ffs(tx_queue->txd.entries),
+ FRF_AZ_TX_DESCQ_TYPE, 0,
+ FRF_BZ_TX_NON_IP_DROP_DIS, 1);
+
+ if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
+ int csum = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
+ EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_IP_CHKSM_DIS, !csum);
+ EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_TCP_CHKSM_DIS,
+ !csum);
+ }
+
+ efx_writeo_table(efx, &reg, efx->type->txd_ptr_tbl_base,
+ tx_queue->queue);
+
+ if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) {
+ /* Only 128 bits in this register */
+ BUILD_BUG_ON(EFX_MAX_TX_QUEUES > 128);
+
+ efx_reado(efx, &reg, FR_AA_TX_CHKSM_CFG);
+ if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
+ __clear_bit_le(tx_queue->queue, &reg);
+ else
+ __set_bit_le(tx_queue->queue, &reg);
+ efx_writeo(efx, &reg, FR_AA_TX_CHKSM_CFG);
+ }
+
+ if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
+ EFX_POPULATE_OWORD_1(reg,
+ FRF_BZ_TX_PACE,
+ (tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI) ?
+ FFE_BZ_TX_PACE_OFF :
+ FFE_BZ_TX_PACE_RESERVED);
+ efx_writeo_table(efx, &reg, FR_BZ_TX_PACE_TBL,
+ tx_queue->queue);
+ }
+}
+
+static void efx_farch_flush_tx_queue(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ efx_oword_t tx_flush_descq;
+
+ WARN_ON(atomic_read(&tx_queue->flush_outstanding));
+ atomic_set(&tx_queue->flush_outstanding, 1);
+
+ EFX_POPULATE_OWORD_2(tx_flush_descq,
+ FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
+ FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue);
+ efx_writeo(efx, &tx_flush_descq, FR_AZ_TX_FLUSH_DESCQ);
+}
+
+void efx_farch_tx_fini(struct efx_tx_queue *tx_queue)
+{
+ struct efx_nic *efx = tx_queue->efx;
+ efx_oword_t tx_desc_ptr;
+
+ /* Remove TX descriptor ring from card */
+ EFX_ZERO_OWORD(tx_desc_ptr);
+ efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base,
+ tx_queue->queue);
+
+ /* Unpin TX descriptor ring */
+ efx_fini_special_buffer(efx, &tx_queue->txd);
+}
+
+/* Free buffers backing TX queue */
+void efx_farch_tx_remove(struct efx_tx_queue *tx_queue)
+{
+ efx_free_special_buffer(tx_queue->efx, &tx_queue->txd);
+}
+
+/**************************************************************************
+ *
+ * RX path
+ *
+ **************************************************************************/
+
+/* This creates an entry in the RX descriptor queue */
+static inline void
+efx_farch_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned index)
+{
+ struct efx_rx_buffer *rx_buf;
+ efx_qword_t *rxd;
+
+ rxd = efx_rx_desc(rx_queue, index);
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ EFX_POPULATE_QWORD_3(*rxd,
+ FSF_AZ_RX_KER_BUF_SIZE,
+ rx_buf->len -
+ rx_queue->efx->type->rx_buffer_padding,
+ FSF_AZ_RX_KER_BUF_REGION, 0,
+ FSF_AZ_RX_KER_BUF_ADDR, rx_buf->dma_addr);
+}
+
+/* This writes to the RX_DESC_WPTR register for the specified receive
+ * descriptor ring.
+ */
+void efx_farch_rx_write(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ efx_dword_t reg;
+ unsigned write_ptr;
+
+ while (rx_queue->notified_count != rx_queue->added_count) {
+ efx_farch_build_rx_desc(
+ rx_queue,
+ rx_queue->notified_count & rx_queue->ptr_mask);
+ ++rx_queue->notified_count;
+ }
+
+ wmb();
+ write_ptr = rx_queue->added_count & rx_queue->ptr_mask;
+ EFX_POPULATE_DWORD_1(reg, FRF_AZ_RX_DESC_WPTR_DWORD, write_ptr);
+ efx_writed_page(efx, &reg, FR_AZ_RX_DESC_UPD_DWORD_P0,
+ efx_rx_queue_index(rx_queue));
+}
+
+int efx_farch_rx_probe(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned entries;
+
+ entries = rx_queue->ptr_mask + 1;
+ return efx_alloc_special_buffer(efx, &rx_queue->rxd,
+ entries * sizeof(efx_qword_t));
+}
+
+void efx_farch_rx_init(struct efx_rx_queue *rx_queue)
+{
+ efx_oword_t rx_desc_ptr;
+ struct efx_nic *efx = rx_queue->efx;
+ bool is_b0 = efx_nic_rev(efx) >= EFX_REV_FALCON_B0;
+ bool iscsi_digest_en = is_b0;
+ bool jumbo_en;
+
+ /* For kernel-mode queues in Falcon A1, the JUMBO flag enables
+ * DMA to continue after a PCIe page boundary (and scattering
+ * is not possible). In Falcon B0 and Siena, it enables
+ * scatter.
+ */
+ jumbo_en = !is_b0 || efx->rx_scatter;
+
+ netif_dbg(efx, hw, efx->net_dev,
+ "RX queue %d ring in special buffers %d-%d\n",
+ efx_rx_queue_index(rx_queue), rx_queue->rxd.index,
+ rx_queue->rxd.index + rx_queue->rxd.entries - 1);
+
+ rx_queue->scatter_n = 0;
+
+ /* Pin RX descriptor ring */
+ efx_init_special_buffer(efx, &rx_queue->rxd);
+
+ /* Push RX descriptor ring to card */
+ EFX_POPULATE_OWORD_10(rx_desc_ptr,
+ FRF_AZ_RX_ISCSI_DDIG_EN, iscsi_digest_en,
+ FRF_AZ_RX_ISCSI_HDIG_EN, iscsi_digest_en,
+ FRF_AZ_RX_DESCQ_BUF_BASE_ID, rx_queue->rxd.index,
+ FRF_AZ_RX_DESCQ_EVQ_ID,
+ efx_rx_queue_channel(rx_queue)->channel,
+ FRF_AZ_RX_DESCQ_OWNER_ID, 0,
+ FRF_AZ_RX_DESCQ_LABEL,
+ efx_rx_queue_index(rx_queue),
+ FRF_AZ_RX_DESCQ_SIZE,
+ __ffs(rx_queue->rxd.entries),
+ FRF_AZ_RX_DESCQ_TYPE, 0 /* kernel queue */ ,
+ FRF_AZ_RX_DESCQ_JUMBO, jumbo_en,
+ FRF_AZ_RX_DESCQ_EN, 1);
+ efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
+ efx_rx_queue_index(rx_queue));
+}
+
+static void efx_farch_flush_rx_queue(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ efx_oword_t rx_flush_descq;
+
+ EFX_POPULATE_OWORD_2(rx_flush_descq,
+ FRF_AZ_RX_FLUSH_DESCQ_CMD, 1,
+ FRF_AZ_RX_FLUSH_DESCQ,
+ efx_rx_queue_index(rx_queue));
+ efx_writeo(efx, &rx_flush_descq, FR_AZ_RX_FLUSH_DESCQ);
+}
+
+void efx_farch_rx_fini(struct efx_rx_queue *rx_queue)
+{
+ efx_oword_t rx_desc_ptr;
+ struct efx_nic *efx = rx_queue->efx;
+
+ /* Remove RX descriptor ring from card */
+ EFX_ZERO_OWORD(rx_desc_ptr);
+ efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
+ efx_rx_queue_index(rx_queue));
+
+ /* Unpin RX descriptor ring */
+ efx_fini_special_buffer(efx, &rx_queue->rxd);
+}
+
+/* Free buffers backing RX queue */
+void efx_farch_rx_remove(struct efx_rx_queue *rx_queue)
+{
+ efx_free_special_buffer(rx_queue->efx, &rx_queue->rxd);
+}
+
+/**************************************************************************
+ *
+ * Flush handling
+ *
+ **************************************************************************/
+
+/* efx_farch_flush_queues() must be woken up when all flushes are completed,
+ * or more RX flushes can be kicked off.
+ */
+static bool efx_farch_flush_wake(struct efx_nic *efx)
+{
+ /* Ensure that all updates are visible to efx_farch_flush_queues() */
+ smp_mb();
+
+ return (atomic_read(&efx->active_queues) == 0 ||
+ (atomic_read(&efx->rxq_flush_outstanding) < EFX_RX_FLUSH_COUNT
+ && atomic_read(&efx->rxq_flush_pending) > 0));
+}
+
+static bool efx_check_tx_flush_complete(struct efx_nic *efx)
+{
+ bool i = true;
+ efx_oword_t txd_ptr_tbl;
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ efx_reado_table(efx, &txd_ptr_tbl,
+ FR_BZ_TX_DESC_PTR_TBL, tx_queue->queue);
+ if (EFX_OWORD_FIELD(txd_ptr_tbl,
+ FRF_AZ_TX_DESCQ_FLUSH) ||
+ EFX_OWORD_FIELD(txd_ptr_tbl,
+ FRF_AZ_TX_DESCQ_EN)) {
+ netif_dbg(efx, hw, efx->net_dev,
+ "flush did not complete on TXQ %d\n",
+ tx_queue->queue);
+ i = false;
+ } else if (atomic_cmpxchg(&tx_queue->flush_outstanding,
+ 1, 0)) {
+ /* The flush is complete, but we didn't
+ * receive a flush completion event
+ */
+ netif_dbg(efx, hw, efx->net_dev,
+ "flush complete on TXQ %d, so drain "
+ "the queue\n", tx_queue->queue);
+ /* Don't need to increment active_queues as it
+ * has already been incremented for the queues
+ * which did not drain
+ */
+ efx_farch_magic_event(channel,
+ EFX_CHANNEL_MAGIC_TX_DRAIN(
+ tx_queue));
+ }
+ }
+ }
+
+ return i;
+}
+
+/* Flush all the transmit queues, and continue flushing receive queues until
+ * they're all flushed. Wait for the DRAIN events to be recieved so that there
+ * are no more RX and TX events left on any channel. */
+static int efx_farch_do_flush(struct efx_nic *efx)
+{
+ unsigned timeout = msecs_to_jiffies(5000); /* 5s for all flushes and drains */
+ struct efx_channel *channel;
+ struct efx_rx_queue *rx_queue;
+ struct efx_tx_queue *tx_queue;
+ int rc = 0;
+
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_tx_queue(tx_queue, channel) {
+ efx_farch_flush_tx_queue(tx_queue);
+ }
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ rx_queue->flush_pending = true;
+ atomic_inc(&efx->rxq_flush_pending);
+ }
+ }
+
+ while (timeout && atomic_read(&efx->active_queues) > 0) {
+ /* If SRIOV is enabled, then offload receive queue flushing to
+ * the firmware (though we will still have to poll for
+ * completion). If that fails, fall back to the old scheme.
+ */
+ if (efx_sriov_enabled(efx)) {
+ rc = efx_mcdi_flush_rxqs(efx);
+ if (!rc)
+ goto wait;
+ }
+
+ /* The hardware supports four concurrent rx flushes, each of
+ * which may need to be retried if there is an outstanding
+ * descriptor fetch
+ */
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ if (atomic_read(&efx->rxq_flush_outstanding) >=
+ EFX_RX_FLUSH_COUNT)
+ break;
+
+ if (rx_queue->flush_pending) {
+ rx_queue->flush_pending = false;
+ atomic_dec(&efx->rxq_flush_pending);
+ atomic_inc(&efx->rxq_flush_outstanding);
+ efx_farch_flush_rx_queue(rx_queue);
+ }
+ }
+ }
+
+ wait:
+ timeout = wait_event_timeout(efx->flush_wq,
+ efx_farch_flush_wake(efx),
+ timeout);
+ }
+
+ if (atomic_read(&efx->active_queues) &&
+ !efx_check_tx_flush_complete(efx)) {
+ netif_err(efx, hw, efx->net_dev, "failed to flush %d queues "
+ "(rx %d+%d)\n", atomic_read(&efx->active_queues),
+ atomic_read(&efx->rxq_flush_outstanding),
+ atomic_read(&efx->rxq_flush_pending));
+ rc = -ETIMEDOUT;
+
+ atomic_set(&efx->active_queues, 0);
+ atomic_set(&efx->rxq_flush_pending, 0);
+ atomic_set(&efx->rxq_flush_outstanding, 0);
+ }
+
+ return rc;
+}
+
+int efx_farch_fini_dmaq(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ struct efx_tx_queue *tx_queue;
+ struct efx_rx_queue *rx_queue;
+ int rc = 0;
+
+ /* Do not attempt to write to the NIC during EEH recovery */
+ if (efx->state != STATE_RECOVERY) {
+ /* Only perform flush if DMA is enabled */
+ if (efx->pci_dev->is_busmaster) {
+ efx->type->prepare_flush(efx);
+ rc = efx_farch_do_flush(efx);
+ efx->type->finish_flush(efx);
+ }
+
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel)
+ efx_farch_rx_fini(rx_queue);
+ efx_for_each_channel_tx_queue(tx_queue, channel)
+ efx_farch_tx_fini(tx_queue);
+ }
+ }
+
+ return rc;
+}
+
+/* Reset queue and flush accounting after FLR
+ *
+ * One possible cause of FLR recovery is that DMA may be failing (eg. if bus
+ * mastering was disabled), in which case we don't receive (RXQ) flush
+ * completion events. This means that efx->rxq_flush_outstanding remained at 4
+ * after the FLR; also, efx->active_queues was non-zero (as no flush completion
+ * events were received, and we didn't go through efx_check_tx_flush_complete())
+ * If we don't fix this up, on the next call to efx_realloc_channels() we won't
+ * flush any RX queues because efx->rxq_flush_outstanding is at the limit of 4
+ * for batched flush requests; and the efx->active_queues gets messed up because
+ * we keep incrementing for the newly initialised queues, but it never went to
+ * zero previously. Then we get a timeout every time we try to restart the
+ * queues, as it doesn't go back to zero when we should be flushing the queues.
+ */
+void efx_farch_finish_flr(struct efx_nic *efx)
+{
+ atomic_set(&efx->rxq_flush_pending, 0);
+ atomic_set(&efx->rxq_flush_outstanding, 0);
+ atomic_set(&efx->active_queues, 0);
+}
+
+
+/**************************************************************************
+ *
+ * Event queue processing
+ * Event queues are processed by per-channel tasklets.
+ *
+ **************************************************************************/
+
+/* Update a channel's event queue's read pointer (RPTR) register
+ *
+ * This writes the EVQ_RPTR_REG register for the specified channel's
+ * event queue.
+ */
+void efx_farch_ev_read_ack(struct efx_channel *channel)
+{
+ efx_dword_t reg;
+ struct efx_nic *efx = channel->efx;
+
+ EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR,
+ channel->eventq_read_ptr & channel->eventq_mask);
+
+ /* For Falcon A1, EVQ_RPTR_KER is documented as having a step size
+ * of 4 bytes, but it is really 16 bytes just like later revisions.
+ */
+ efx_writed(efx, &reg,
+ efx->type->evq_rptr_tbl_base +
+ FR_BZ_EVQ_RPTR_STEP * channel->channel);
+}
+
+/* Use HW to insert a SW defined event */
+void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq,
+ efx_qword_t *event)
+{
+ efx_oword_t drv_ev_reg;
+
+ BUILD_BUG_ON(FRF_AZ_DRV_EV_DATA_LBN != 0 ||
+ FRF_AZ_DRV_EV_DATA_WIDTH != 64);
+ drv_ev_reg.u32[0] = event->u32[0];
+ drv_ev_reg.u32[1] = event->u32[1];
+ drv_ev_reg.u32[2] = 0;
+ drv_ev_reg.u32[3] = 0;
+ EFX_SET_OWORD_FIELD(drv_ev_reg, FRF_AZ_DRV_EV_QID, evq);
+ efx_writeo(efx, &drv_ev_reg, FR_AZ_DRV_EV);
+}
+
+static void efx_farch_magic_event(struct efx_channel *channel, u32 magic)
+{
+ efx_qword_t event;
+
+ EFX_POPULATE_QWORD_2(event, FSF_AZ_EV_CODE,
+ FSE_AZ_EV_CODE_DRV_GEN_EV,
+ FSF_AZ_DRV_GEN_EV_MAGIC, magic);
+ efx_farch_generate_event(channel->efx, channel->channel, &event);
+}
+
+/* Handle a transmit completion event
+ *
+ * The NIC batches TX completion events; the message we receive is of
+ * the form "complete all TX events up to this index".
+ */
+static int
+efx_farch_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
+{
+ unsigned int tx_ev_desc_ptr;
+ unsigned int tx_ev_q_label;
+ struct efx_tx_queue *tx_queue;
+ struct efx_nic *efx = channel->efx;
+ int tx_packets = 0;
+
+ if (unlikely(ACCESS_ONCE(efx->reset_pending)))
+ return 0;
+
+ if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) {
+ /* Transmit completion */
+ tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR);
+ tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
+ tx_queue = efx_channel_get_tx_queue(
+ channel, tx_ev_q_label % EFX_TXQ_TYPES);
+ tx_packets = ((tx_ev_desc_ptr - tx_queue->read_count) &
+ tx_queue->ptr_mask);
+ efx_xmit_done(tx_queue, tx_ev_desc_ptr);
+ } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) {
+ /* Rewrite the FIFO write pointer */
+ tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
+ tx_queue = efx_channel_get_tx_queue(
+ channel, tx_ev_q_label % EFX_TXQ_TYPES);
+
+ netif_tx_lock(efx->net_dev);
+ efx_farch_notify_tx_desc(tx_queue);
+ netif_tx_unlock(efx->net_dev);
+ } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_PKT_ERR)) {
+ efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
+ } else {
+ netif_err(efx, tx_err, efx->net_dev,
+ "channel %d unexpected TX event "
+ EFX_QWORD_FMT"\n", channel->channel,
+ EFX_QWORD_VAL(*event));
+ }
+
+ return tx_packets;
+}
+
+/* Detect errors included in the rx_evt_pkt_ok bit. */
+static u16 efx_farch_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
+ const efx_qword_t *event)
+{
+ struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
+ struct efx_nic *efx = rx_queue->efx;
+ bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err;
+ bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err;
+ bool rx_ev_frm_trunc, rx_ev_drib_nib, rx_ev_tobe_disc;
+ bool rx_ev_other_err, rx_ev_pause_frm;
+ bool rx_ev_hdr_type, rx_ev_mcast_pkt;
+ unsigned rx_ev_pkt_type;
+
+ rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
+ rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
+ rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC);
+ rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE);
+ rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event,
+ FSF_AZ_RX_EV_BUF_OWNER_ID_ERR);
+ rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event,
+ FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR);
+ rx_ev_tcp_udp_chksum_err = EFX_QWORD_FIELD(*event,
+ FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR);
+ rx_ev_eth_crc_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_ETH_CRC_ERR);
+ rx_ev_frm_trunc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_FRM_TRUNC);
+ rx_ev_drib_nib = ((efx_nic_rev(efx) >= EFX_REV_FALCON_B0) ?
+ 0 : EFX_QWORD_FIELD(*event, FSF_AA_RX_EV_DRIB_NIB));
+ rx_ev_pause_frm = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR);
+
+ /* Every error apart from tobe_disc and pause_frm */
+ rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err |
+ rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
+ rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);
+
+ /* Count errors that are not in MAC stats. Ignore expected
+ * checksum errors during self-test. */
+ if (rx_ev_frm_trunc)
+ ++channel->n_rx_frm_trunc;
+ else if (rx_ev_tobe_disc)
+ ++channel->n_rx_tobe_disc;
+ else if (!efx->loopback_selftest) {
+ if (rx_ev_ip_hdr_chksum_err)
+ ++channel->n_rx_ip_hdr_chksum_err;
+ else if (rx_ev_tcp_udp_chksum_err)
+ ++channel->n_rx_tcp_udp_chksum_err;
+ }
+
+ /* TOBE_DISC is expected on unicast mismatches; don't print out an
+ * error message. FRM_TRUNC indicates RXDP dropped the packet due
+ * to a FIFO overflow.
+ */
+#ifdef DEBUG
+ if (rx_ev_other_err && net_ratelimit()) {
+ netif_dbg(efx, rx_err, efx->net_dev,
+ " RX queue %d unexpected RX event "
+ EFX_QWORD_FMT "%s%s%s%s%s%s%s%s\n",
+ efx_rx_queue_index(rx_queue), EFX_QWORD_VAL(*event),
+ rx_ev_buf_owner_id_err ? " [OWNER_ID_ERR]" : "",
+ rx_ev_ip_hdr_chksum_err ?
+ " [IP_HDR_CHKSUM_ERR]" : "",
+ rx_ev_tcp_udp_chksum_err ?
+ " [TCP_UDP_CHKSUM_ERR]" : "",
+ rx_ev_eth_crc_err ? " [ETH_CRC_ERR]" : "",
+ rx_ev_frm_trunc ? " [FRM_TRUNC]" : "",
+ rx_ev_drib_nib ? " [DRIB_NIB]" : "",
+ rx_ev_tobe_disc ? " [TOBE_DISC]" : "",
+ rx_ev_pause_frm ? " [PAUSE]" : "");
+ }
+#endif
+
+ /* The frame must be discarded if any of these are true. */
+ return (rx_ev_eth_crc_err | rx_ev_frm_trunc | rx_ev_drib_nib |
+ rx_ev_tobe_disc | rx_ev_pause_frm) ?
+ EFX_RX_PKT_DISCARD : 0;
+}
+
+/* Handle receive events that are not in-order. Return true if this
+ * can be handled as a partial packet discard, false if it's more
+ * serious.
+ */
+static bool
+efx_farch_handle_rx_bad_index(struct efx_rx_queue *rx_queue, unsigned index)
+{
+ struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned expected, dropped;
+
+ if (rx_queue->scatter_n &&
+ index == ((rx_queue->removed_count + rx_queue->scatter_n - 1) &
+ rx_queue->ptr_mask)) {
+ ++channel->n_rx_nodesc_trunc;
+ return true;
+ }
+
+ expected = rx_queue->removed_count & rx_queue->ptr_mask;
+ dropped = (index - expected) & rx_queue->ptr_mask;
+ netif_info(efx, rx_err, efx->net_dev,
+ "dropped %d events (index=%d expected=%d)\n",
+ dropped, index, expected);
+
+ efx_schedule_reset(efx, EFX_WORKAROUND_5676(efx) ?
+ RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE);
+ return false;
+}
+
+/* Handle a packet received event
+ *
+ * The NIC gives a "discard" flag if it's a unicast packet with the
+ * wrong destination address
+ * Also "is multicast" and "matches multicast filter" flags can be used to
+ * discard non-matching multicast packets.
+ */
+static void
+efx_farch_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
+{
+ unsigned int rx_ev_desc_ptr, rx_ev_byte_cnt;
+ unsigned int rx_ev_hdr_type, rx_ev_mcast_pkt;
+ unsigned expected_ptr;
+ bool rx_ev_pkt_ok, rx_ev_sop, rx_ev_cont;
+ u16 flags;
+ struct efx_rx_queue *rx_queue;
+ struct efx_nic *efx = channel->efx;
+
+ if (unlikely(ACCESS_ONCE(efx->reset_pending)))
+ return;
+
+ rx_ev_cont = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT);
+ rx_ev_sop = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_SOP);
+ WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_Q_LABEL) !=
+ channel->channel);
+
+ rx_queue = efx_channel_get_rx_queue(channel);
+
+ rx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_DESC_PTR);
+ expected_ptr = ((rx_queue->removed_count + rx_queue->scatter_n) &
+ rx_queue->ptr_mask);
+
+ /* Check for partial drops and other errors */
+ if (unlikely(rx_ev_desc_ptr != expected_ptr) ||
+ unlikely(rx_ev_sop != (rx_queue->scatter_n == 0))) {
+ if (rx_ev_desc_ptr != expected_ptr &&
+ !efx_farch_handle_rx_bad_index(rx_queue, rx_ev_desc_ptr))
+ return;
+
+ /* Discard all pending fragments */
+ if (rx_queue->scatter_n) {
+ efx_rx_packet(
+ rx_queue,
+ rx_queue->removed_count & rx_queue->ptr_mask,
+ rx_queue->scatter_n, 0, EFX_RX_PKT_DISCARD);
+ rx_queue->removed_count += rx_queue->scatter_n;
+ rx_queue->scatter_n = 0;
+ }
+
+ /* Return if there is no new fragment */
+ if (rx_ev_desc_ptr != expected_ptr)
+ return;
+
+ /* Discard new fragment if not SOP */
+ if (!rx_ev_sop) {
+ efx_rx_packet(
+ rx_queue,
+ rx_queue->removed_count & rx_queue->ptr_mask,
+ 1, 0, EFX_RX_PKT_DISCARD);
+ ++rx_queue->removed_count;
+ return;
+ }
+ }
+
+ ++rx_queue->scatter_n;
+ if (rx_ev_cont)
+ return;
+
+ rx_ev_byte_cnt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BYTE_CNT);
+ rx_ev_pkt_ok = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_OK);
+ rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
+
+ if (likely(rx_ev_pkt_ok)) {
+ /* If packet is marked as OK then we can rely on the
+ * hardware checksum and classification.
+ */
+ flags = 0;
+ switch (rx_ev_hdr_type) {
+ case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP:
+ flags |= EFX_RX_PKT_TCP;
+ /* fall through */
+ case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP:
+ flags |= EFX_RX_PKT_CSUMMED;
+ /* fall through */
+ case FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_OTHER:
+ case FSE_AZ_RX_EV_HDR_TYPE_OTHER:
+ break;
+ }
+ } else {
+ flags = efx_farch_handle_rx_not_ok(rx_queue, event);
+ }
+
+ /* Detect multicast packets that didn't match the filter */
+ rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
+ if (rx_ev_mcast_pkt) {
+ unsigned int rx_ev_mcast_hash_match =
+ EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_HASH_MATCH);
+
+ if (unlikely(!rx_ev_mcast_hash_match)) {
+ ++channel->n_rx_mcast_mismatch;
+ flags |= EFX_RX_PKT_DISCARD;
+ }
+ }
+
+ channel->irq_mod_score += 2;
+
+ /* Handle received packet */
+ efx_rx_packet(rx_queue,
+ rx_queue->removed_count & rx_queue->ptr_mask,
+ rx_queue->scatter_n, rx_ev_byte_cnt, flags);
+ rx_queue->removed_count += rx_queue->scatter_n;
+ rx_queue->scatter_n = 0;
+}
+
+/* If this flush done event corresponds to a &struct efx_tx_queue, then
+ * send an %EFX_CHANNEL_MAGIC_TX_DRAIN event to drain the event queue
+ * of all transmit completions.
+ */
+static void
+efx_farch_handle_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
+{
+ struct efx_tx_queue *tx_queue;
+ int qid;
+
+ qid = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);
+ if (qid < EFX_TXQ_TYPES * efx->n_tx_channels) {
+ tx_queue = efx_get_tx_queue(efx, qid / EFX_TXQ_TYPES,
+ qid % EFX_TXQ_TYPES);
+ if (atomic_cmpxchg(&tx_queue->flush_outstanding, 1, 0)) {
+ efx_farch_magic_event(tx_queue->channel,
+ EFX_CHANNEL_MAGIC_TX_DRAIN(tx_queue));
+ }
+ }
+}
+
+/* If this flush done event corresponds to a &struct efx_rx_queue: If the flush
+ * was succesful then send an %EFX_CHANNEL_MAGIC_RX_DRAIN, otherwise add
+ * the RX queue back to the mask of RX queues in need of flushing.
+ */
+static void
+efx_farch_handle_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
+{
+ struct efx_channel *channel;
+ struct efx_rx_queue *rx_queue;
+ int qid;
+ bool failed;
+
+ qid = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
+ failed = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
+ if (qid >= efx->n_channels)
+ return;
+ channel = efx_get_channel(efx, qid);
+ if (!efx_channel_has_rx_queue(channel))
+ return;
+ rx_queue = efx_channel_get_rx_queue(channel);
+
+ if (failed) {
+ netif_info(efx, hw, efx->net_dev,
+ "RXQ %d flush retry\n", qid);
+ rx_queue->flush_pending = true;
+ atomic_inc(&efx->rxq_flush_pending);
+ } else {
+ efx_farch_magic_event(efx_rx_queue_channel(rx_queue),
+ EFX_CHANNEL_MAGIC_RX_DRAIN(rx_queue));
+ }
+ atomic_dec(&efx->rxq_flush_outstanding);
+ if (efx_farch_flush_wake(efx))
+ wake_up(&efx->flush_wq);
+}
+
+static void
+efx_farch_handle_drain_event(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+
+ WARN_ON(atomic_read(&efx->active_queues) == 0);
+ atomic_dec(&efx->active_queues);
+ if (efx_farch_flush_wake(efx))
+ wake_up(&efx->flush_wq);
+}
+
+static void efx_farch_handle_generated_event(struct efx_channel *channel,
+ efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ struct efx_rx_queue *rx_queue =
+ efx_channel_has_rx_queue(channel) ?
+ efx_channel_get_rx_queue(channel) : NULL;
+ unsigned magic, code;
+
+ magic = EFX_QWORD_FIELD(*event, FSF_AZ_DRV_GEN_EV_MAGIC);
+ code = _EFX_CHANNEL_MAGIC_CODE(magic);
+
+ if (magic == EFX_CHANNEL_MAGIC_TEST(channel)) {
+ channel->event_test_cpu = raw_smp_processor_id();
+ } else if (rx_queue && magic == EFX_CHANNEL_MAGIC_FILL(rx_queue)) {
+ /* The queue must be empty, so we won't receive any rx
+ * events, so efx_process_channel() won't refill the
+ * queue. Refill it here */
+ efx_fast_push_rx_descriptors(rx_queue, true);
+ } else if (rx_queue && magic == EFX_CHANNEL_MAGIC_RX_DRAIN(rx_queue)) {
+ efx_farch_handle_drain_event(channel);
+ } else if (code == _EFX_CHANNEL_MAGIC_TX_DRAIN) {
+ efx_farch_handle_drain_event(channel);
+ } else {
+ netif_dbg(efx, hw, efx->net_dev, "channel %d received "
+ "generated event "EFX_QWORD_FMT"\n",
+ channel->channel, EFX_QWORD_VAL(*event));
+ }
+}
+
+static void
+efx_farch_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ unsigned int ev_sub_code;
+ unsigned int ev_sub_data;
+
+ ev_sub_code = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBCODE);
+ ev_sub_data = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);
+
+ switch (ev_sub_code) {
+ case FSE_AZ_TX_DESCQ_FLS_DONE_EV:
+ netif_vdbg(efx, hw, efx->net_dev, "channel %d TXQ %d flushed\n",
+ channel->channel, ev_sub_data);
+ efx_farch_handle_tx_flush_done(efx, event);
+ efx_sriov_tx_flush_done(efx, event);
+ break;
+ case FSE_AZ_RX_DESCQ_FLS_DONE_EV:
+ netif_vdbg(efx, hw, efx->net_dev, "channel %d RXQ %d flushed\n",
+ channel->channel, ev_sub_data);
+ efx_farch_handle_rx_flush_done(efx, event);
+ efx_sriov_rx_flush_done(efx, event);
+ break;
+ case FSE_AZ_EVQ_INIT_DONE_EV:
+ netif_dbg(efx, hw, efx->net_dev,
+ "channel %d EVQ %d initialised\n",
+ channel->channel, ev_sub_data);
+ break;
+ case FSE_AZ_SRM_UPD_DONE_EV:
+ netif_vdbg(efx, hw, efx->net_dev,
+ "channel %d SRAM update done\n", channel->channel);
+ break;
+ case FSE_AZ_WAKE_UP_EV:
+ netif_vdbg(efx, hw, efx->net_dev,
+ "channel %d RXQ %d wakeup event\n",
+ channel->channel, ev_sub_data);
+ break;
+ case FSE_AZ_TIMER_EV:
+ netif_vdbg(efx, hw, efx->net_dev,
+ "channel %d RX queue %d timer expired\n",
+ channel->channel, ev_sub_data);
+ break;
+ case FSE_AA_RX_RECOVER_EV:
+ netif_err(efx, rx_err, efx->net_dev,
+ "channel %d seen DRIVER RX_RESET event. "
+ "Resetting.\n", channel->channel);
+ atomic_inc(&efx->rx_reset);
+ efx_schedule_reset(efx,
+ EFX_WORKAROUND_6555(efx) ?
+ RESET_TYPE_RX_RECOVERY :
+ RESET_TYPE_DISABLE);
+ break;
+ case FSE_BZ_RX_DSC_ERROR_EV:
+ if (ev_sub_data < EFX_VI_BASE) {
+ netif_err(efx, rx_err, efx->net_dev,
+ "RX DMA Q %d reports descriptor fetch error."
+ " RX Q %d is disabled.\n", ev_sub_data,
+ ev_sub_data);
+ efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
+ } else
+ efx_sriov_desc_fetch_err(efx, ev_sub_data);
+ break;
+ case FSE_BZ_TX_DSC_ERROR_EV:
+ if (ev_sub_data < EFX_VI_BASE) {
+ netif_err(efx, tx_err, efx->net_dev,
+ "TX DMA Q %d reports descriptor fetch error."
+ " TX Q %d is disabled.\n", ev_sub_data,
+ ev_sub_data);
+ efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
+ } else
+ efx_sriov_desc_fetch_err(efx, ev_sub_data);
+ break;
+ default:
+ netif_vdbg(efx, hw, efx->net_dev,
+ "channel %d unknown driver event code %d "
+ "data %04x\n", channel->channel, ev_sub_code,
+ ev_sub_data);
+ break;
+ }
+}
+
+int efx_farch_ev_process(struct efx_channel *channel, int budget)
+{
+ struct efx_nic *efx = channel->efx;
+ unsigned int read_ptr;
+ efx_qword_t event, *p_event;
+ int ev_code;
+ int tx_packets = 0;
+ int spent = 0;
+
+ if (budget <= 0)
+ return spent;
+
+ read_ptr = channel->eventq_read_ptr;
+
+ for (;;) {
+ p_event = efx_event(channel, read_ptr);
+ event = *p_event;
+
+ if (!efx_event_present(&event))
+ /* End of events */
+ break;
+
+ netif_vdbg(channel->efx, intr, channel->efx->net_dev,
+ "channel %d event is "EFX_QWORD_FMT"\n",
+ channel->channel, EFX_QWORD_VAL(event));
+
+ /* Clear this event by marking it all ones */
+ EFX_SET_QWORD(*p_event);
+
+ ++read_ptr;
+
+ ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE);
+
+ switch (ev_code) {
+ case FSE_AZ_EV_CODE_RX_EV:
+ efx_farch_handle_rx_event(channel, &event);
+ if (++spent == budget)
+ goto out;
+ break;
+ case FSE_AZ_EV_CODE_TX_EV:
+ tx_packets += efx_farch_handle_tx_event(channel,
+ &event);
+ if (tx_packets > efx->txq_entries) {
+ spent = budget;
+ goto out;
+ }
+ break;
+ case FSE_AZ_EV_CODE_DRV_GEN_EV:
+ efx_farch_handle_generated_event(channel, &event);
+ break;
+ case FSE_AZ_EV_CODE_DRIVER_EV:
+ efx_farch_handle_driver_event(channel, &event);
+ break;
+ case FSE_CZ_EV_CODE_USER_EV:
+ efx_sriov_event(channel, &event);
+ break;
+ case FSE_CZ_EV_CODE_MCDI_EV:
+ efx_mcdi_process_event(channel, &event);
+ break;
+ case FSE_AZ_EV_CODE_GLOBAL_EV:
+ if (efx->type->handle_global_event &&
+ efx->type->handle_global_event(channel, &event))
+ break;
+ /* else fall through */
+ default:
+ netif_err(channel->efx, hw, channel->efx->net_dev,
+ "channel %d unknown event type %d (data "
+ EFX_QWORD_FMT ")\n", channel->channel,
+ ev_code, EFX_QWORD_VAL(event));
+ }
+ }
+
+out:
+ channel->eventq_read_ptr = read_ptr;
+ return spent;
+}
+
+/* Allocate buffer table entries for event queue */
+int efx_farch_ev_probe(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+ unsigned entries;
+
+ entries = channel->eventq_mask + 1;
+ return efx_alloc_special_buffer(efx, &channel->eventq,
+ entries * sizeof(efx_qword_t));
+}
+
+int efx_farch_ev_init(struct efx_channel *channel)
+{
+ efx_oword_t reg;
+ struct efx_nic *efx = channel->efx;
+
+ netif_dbg(efx, hw, efx->net_dev,
+ "channel %d event queue in special buffers %d-%d\n",
+ channel->channel, channel->eventq.index,
+ channel->eventq.index + channel->eventq.entries - 1);
+
+ if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) {
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_CZ_TIMER_Q_EN, 1,
+ FRF_CZ_HOST_NOTIFY_MODE, 0,
+ FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
+ efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);
+ }
+
+ /* Pin event queue buffer */
+ efx_init_special_buffer(efx, &channel->eventq);
+
+ /* Fill event queue with all ones (i.e. empty events) */
+ memset(channel->eventq.buf.addr, 0xff, channel->eventq.buf.len);
+
+ /* Push event queue to card */
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_AZ_EVQ_EN, 1,
+ FRF_AZ_EVQ_SIZE, __ffs(channel->eventq.entries),
+ FRF_AZ_EVQ_BUF_BASE_ID, channel->eventq.index);
+ efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
+ channel->channel);
+
+ return 0;
+}
+
+void efx_farch_ev_fini(struct efx_channel *channel)
+{
+ efx_oword_t reg;
+ struct efx_nic *efx = channel->efx;
+
+ /* Remove event queue from card */
+ EFX_ZERO_OWORD(reg);
+ efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
+ channel->channel);
+ if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
+ efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);
+
+ /* Unpin event queue */
+ efx_fini_special_buffer(efx, &channel->eventq);
+}
+
+/* Free buffers backing event queue */
+void efx_farch_ev_remove(struct efx_channel *channel)
+{
+ efx_free_special_buffer(channel->efx, &channel->eventq);
+}
+
+
+void efx_farch_ev_test_generate(struct efx_channel *channel)
+{
+ efx_farch_magic_event(channel, EFX_CHANNEL_MAGIC_TEST(channel));
+}
+
+void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue)
+{
+ efx_farch_magic_event(efx_rx_queue_channel(rx_queue),
+ EFX_CHANNEL_MAGIC_FILL(rx_queue));
+}
+
+/**************************************************************************
+ *
+ * Hardware interrupts
+ * The hardware interrupt handler does very little work; all the event
+ * queue processing is carried out by per-channel tasklets.
+ *
+ **************************************************************************/
+
+/* Enable/disable/generate interrupts */
+static inline void efx_farch_interrupts(struct efx_nic *efx,
+ bool enabled, bool force)
+{
+ efx_oword_t int_en_reg_ker;
+
+ EFX_POPULATE_OWORD_3(int_en_reg_ker,
+ FRF_AZ_KER_INT_LEVE_SEL, efx->irq_level,
+ FRF_AZ_KER_INT_KER, force,
+ FRF_AZ_DRV_INT_EN_KER, enabled);
+ efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER);
+}
+
+void efx_farch_irq_enable_master(struct efx_nic *efx)
+{
+ EFX_ZERO_OWORD(*((efx_oword_t *) efx->irq_status.addr));
+ wmb(); /* Ensure interrupt vector is clear before interrupts enabled */
+
+ efx_farch_interrupts(efx, true, false);
+}
+
+void efx_farch_irq_disable_master(struct efx_nic *efx)
+{
+ /* Disable interrupts */
+ efx_farch_interrupts(efx, false, false);
+}
+
+/* Generate a test interrupt
+ * Interrupt must already have been enabled, otherwise nasty things
+ * may happen.
+ */
+void efx_farch_irq_test_generate(struct efx_nic *efx)
+{
+ efx_farch_interrupts(efx, true, true);
+}
+
+/* Process a fatal interrupt
+ * Disable bus mastering ASAP and schedule a reset
+ */
+irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx)
+{
+ struct falcon_nic_data *nic_data = efx->nic_data;
+ efx_oword_t *int_ker = efx->irq_status.addr;
+ efx_oword_t fatal_intr;
+ int error, mem_perr;
+
+ efx_reado(efx, &fatal_intr, FR_AZ_FATAL_INTR_KER);
+ error = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_FATAL_INTR);
+
+ netif_err(efx, hw, efx->net_dev, "SYSTEM ERROR "EFX_OWORD_FMT" status "
+ EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker),
+ EFX_OWORD_VAL(fatal_intr),
+ error ? "disabling bus mastering" : "no recognised error");
+
+ /* If this is a memory parity error dump which blocks are offending */
+ mem_perr = (EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER) ||
+ EFX_OWORD_FIELD(fatal_intr, FRF_AZ_SRM_PERR_INT_KER));
+ if (mem_perr) {
+ efx_oword_t reg;
+ efx_reado(efx, &reg, FR_AZ_MEM_STAT);
+ netif_err(efx, hw, efx->net_dev,
+ "SYSTEM ERROR: memory parity error "EFX_OWORD_FMT"\n",
+ EFX_OWORD_VAL(reg));
+ }
+
+ /* Disable both devices */
+ pci_clear_master(efx->pci_dev);
+ if (efx_nic_is_dual_func(efx))
+ pci_clear_master(nic_data->pci_dev2);
+ efx_farch_irq_disable_master(efx);
+
+ /* Count errors and reset or disable the NIC accordingly */
+ if (efx->int_error_count == 0 ||
+ time_after(jiffies, efx->int_error_expire)) {
+ efx->int_error_count = 0;
+ efx->int_error_expire =
+ jiffies + EFX_INT_ERROR_EXPIRE * HZ;
+ }
+ if (++efx->int_error_count < EFX_MAX_INT_ERRORS) {
+ netif_err(efx, hw, efx->net_dev,
+ "SYSTEM ERROR - reset scheduled\n");
+ efx_schedule_reset(efx, RESET_TYPE_INT_ERROR);
+ } else {
+ netif_err(efx, hw, efx->net_dev,
+ "SYSTEM ERROR - max number of errors seen."
+ "NIC will be disabled\n");
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+ }
+
+ return IRQ_HANDLED;
+}
+
+/* Handle a legacy interrupt
+ * Acknowledges the interrupt and schedule event queue processing.
+ */
+irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id)
+{
+ struct efx_nic *efx = dev_id;
+ bool soft_enabled = ACCESS_ONCE(efx->irq_soft_enabled);
+ efx_oword_t *int_ker = efx->irq_status.addr;
+ irqreturn_t result = IRQ_NONE;
+ struct efx_channel *channel;
+ efx_dword_t reg;
+ u32 queues;
+ int syserr;
+
+ /* Read the ISR which also ACKs the interrupts */
+ efx_readd(efx, &reg, FR_BZ_INT_ISR0);
+ queues = EFX_EXTRACT_DWORD(reg, 0, 31);
+
+ /* Legacy interrupts are disabled too late by the EEH kernel
+ * code. Disable them earlier.
+ * If an EEH error occurred, the read will have returned all ones.
+ */
+ if (EFX_DWORD_IS_ALL_ONES(reg) && efx_try_recovery(efx) &&
+ !efx->eeh_disabled_legacy_irq) {
+ disable_irq_nosync(efx->legacy_irq);
+ efx->eeh_disabled_legacy_irq = true;
+ }
+
+ /* Handle non-event-queue sources */
+ if (queues & (1U << efx->irq_level) && soft_enabled) {
+ syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+ if (unlikely(syserr))
+ return efx_farch_fatal_interrupt(efx);
+ efx->last_irq_cpu = raw_smp_processor_id();
+ }
+
+ if (queues != 0) {
+ efx->irq_zero_count = 0;
+
+ /* Schedule processing of any interrupting queues */
+ if (likely(soft_enabled)) {
+ efx_for_each_channel(channel, efx) {
+ if (queues & 1)
+ efx_schedule_channel_irq(channel);
+ queues >>= 1;
+ }
+ }
+ result = IRQ_HANDLED;
+
+ } else {
+ efx_qword_t *event;
+
+ /* Legacy ISR read can return zero once (SF bug 15783) */
+
+ /* We can't return IRQ_HANDLED more than once on seeing ISR=0
+ * because this might be a shared interrupt. */
+ if (efx->irq_zero_count++ == 0)
+ result = IRQ_HANDLED;
+
+ /* Ensure we schedule or rearm all event queues */
+ if (likely(soft_enabled)) {
+ efx_for_each_channel(channel, efx) {
+ event = efx_event(channel,
+ channel->eventq_read_ptr);
+ if (efx_event_present(event))
+ efx_schedule_channel_irq(channel);
+ else
+ efx_farch_ev_read_ack(channel);
+ }
+ }
+ }
+
+ if (result == IRQ_HANDLED)
+ netif_vdbg(efx, intr, efx->net_dev,
+ "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n",
+ irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg));
+
+ return result;
+}
+
+/* Handle an MSI interrupt
+ *
+ * Handle an MSI hardware interrupt. This routine schedules event
+ * queue processing. No interrupt acknowledgement cycle is necessary.
+ * Also, we never need to check that the interrupt is for us, since
+ * MSI interrupts cannot be shared.
+ */
+irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id)
+{
+ struct efx_msi_context *context = dev_id;
+ struct efx_nic *efx = context->efx;
+ efx_oword_t *int_ker = efx->irq_status.addr;
+ int syserr;
+
+ netif_vdbg(efx, intr, efx->net_dev,
+ "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n",
+ irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
+
+ if (!likely(ACCESS_ONCE(efx->irq_soft_enabled)))
+ return IRQ_HANDLED;
+
+ /* Handle non-event-queue sources */
+ if (context->index == efx->irq_level) {
+ syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
+ if (unlikely(syserr))
+ return efx_farch_fatal_interrupt(efx);
+ efx->last_irq_cpu = raw_smp_processor_id();
+ }
+
+ /* Schedule processing of the channel */
+ efx_schedule_channel_irq(efx->channel[context->index]);
+
+ return IRQ_HANDLED;
+}
+
+/* Setup RSS indirection table.
+ * This maps from the hash value of the packet to RXQ
+ */
+void efx_farch_rx_push_indir_table(struct efx_nic *efx)
+{
+ size_t i = 0;
+ efx_dword_t dword;
+
+ BUG_ON(efx_nic_rev(efx) < EFX_REV_FALCON_B0);
+
+ BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) !=
+ FR_BZ_RX_INDIRECTION_TBL_ROWS);
+
+ for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
+ EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
+ efx->rx_indir_table[i]);
+ efx_writed(efx, &dword,
+ FR_BZ_RX_INDIRECTION_TBL +
+ FR_BZ_RX_INDIRECTION_TBL_STEP * i);
+ }
+}
+
+/* Looks at available SRAM resources and works out how many queues we
+ * can support, and where things like descriptor caches should live.
+ *
+ * SRAM is split up as follows:
+ * 0 buftbl entries for channels
+ * efx->vf_buftbl_base buftbl entries for SR-IOV
+ * efx->rx_dc_base RX descriptor caches
+ * efx->tx_dc_base TX descriptor caches
+ */
+void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
+{
+ unsigned vi_count, buftbl_min;
+
+ /* Account for the buffer table entries backing the datapath channels
+ * and the descriptor caches for those channels.
+ */
+ buftbl_min = ((efx->n_rx_channels * EFX_MAX_DMAQ_SIZE +
+ efx->n_tx_channels * EFX_TXQ_TYPES * EFX_MAX_DMAQ_SIZE +
+ efx->n_channels * EFX_MAX_EVQ_SIZE)
+ * sizeof(efx_qword_t) / EFX_BUF_SIZE);
+ vi_count = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES);
+
+#ifdef CONFIG_SFC_SRIOV
+ if (efx_sriov_wanted(efx)) {
+ unsigned vi_dc_entries, buftbl_free, entries_per_vf, vf_limit;
+
+ efx->vf_buftbl_base = buftbl_min;
+
+ vi_dc_entries = RX_DC_ENTRIES + TX_DC_ENTRIES;
+ vi_count = max(vi_count, EFX_VI_BASE);
+ buftbl_free = (sram_lim_qw - buftbl_min -
+ vi_count * vi_dc_entries);
+
+ entries_per_vf = ((vi_dc_entries + EFX_VF_BUFTBL_PER_VI) *
+ efx_vf_size(efx));
+ vf_limit = min(buftbl_free / entries_per_vf,
+ (1024U - EFX_VI_BASE) >> efx->vi_scale);
+
+ if (efx->vf_count > vf_limit) {
+ netif_err(efx, probe, efx->net_dev,
+ "Reducing VF count from from %d to %d\n",
+ efx->vf_count, vf_limit);
+ efx->vf_count = vf_limit;
+ }
+ vi_count += efx->vf_count * efx_vf_size(efx);
+ }
+#endif
+
+ efx->tx_dc_base = sram_lim_qw - vi_count * TX_DC_ENTRIES;
+ efx->rx_dc_base = efx->tx_dc_base - vi_count * RX_DC_ENTRIES;
+}
+
+u32 efx_farch_fpga_ver(struct efx_nic *efx)
+{
+ efx_oword_t altera_build;
+ efx_reado(efx, &altera_build, FR_AZ_ALTERA_BUILD);
+ return EFX_OWORD_FIELD(altera_build, FRF_AZ_ALTERA_BUILD_VER);
+}
+
+void efx_farch_init_common(struct efx_nic *efx)
+{
+ efx_oword_t temp;
+
+ /* Set positions of descriptor caches in SRAM. */
+ EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_TX_DC_BASE_ADR, efx->tx_dc_base);
+ efx_writeo(efx, &temp, FR_AZ_SRM_TX_DC_CFG);
+ EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_RX_DC_BASE_ADR, efx->rx_dc_base);
+ efx_writeo(efx, &temp, FR_AZ_SRM_RX_DC_CFG);
+
+ /* Set TX descriptor cache size. */
+ BUILD_BUG_ON(TX_DC_ENTRIES != (8 << TX_DC_ENTRIES_ORDER));
+ EFX_POPULATE_OWORD_1(temp, FRF_AZ_TX_DC_SIZE, TX_DC_ENTRIES_ORDER);
+ efx_writeo(efx, &temp, FR_AZ_TX_DC_CFG);
+
+ /* Set RX descriptor cache size. Set low watermark to size-8, as
+ * this allows most efficient prefetching.
+ */
+ BUILD_BUG_ON(RX_DC_ENTRIES != (8 << RX_DC_ENTRIES_ORDER));
+ EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_SIZE, RX_DC_ENTRIES_ORDER);
+ efx_writeo(efx, &temp, FR_AZ_RX_DC_CFG);
+ EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_PF_LWM, RX_DC_ENTRIES - 8);
+ efx_writeo(efx, &temp, FR_AZ_RX_DC_PF_WM);
+
+ /* Program INT_KER address */
+ EFX_POPULATE_OWORD_2(temp,
+ FRF_AZ_NORM_INT_VEC_DIS_KER,
+ EFX_INT_MODE_USE_MSI(efx),
+ FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr);
+ efx_writeo(efx, &temp, FR_AZ_INT_ADR_KER);
+
+ if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx))
+ /* Use an interrupt level unused by event queues */
+ efx->irq_level = 0x1f;
+ else
+ /* Use a valid MSI-X vector */
+ efx->irq_level = 0;
+
+ /* Enable all the genuinely fatal interrupts. (They are still
+ * masked by the overall interrupt mask, controlled by
+ * falcon_interrupts()).
+ *
+ * Note: All other fatal interrupts are enabled
+ */
+ EFX_POPULATE_OWORD_3(temp,
+ FRF_AZ_ILL_ADR_INT_KER_EN, 1,
+ FRF_AZ_RBUF_OWN_INT_KER_EN, 1,
+ FRF_AZ_TBUF_OWN_INT_KER_EN, 1);
+ if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
+ EFX_SET_OWORD_FIELD(temp, FRF_CZ_SRAM_PERR_INT_P_KER_EN, 1);
+ EFX_INVERT_OWORD(temp);
+ efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER);
+
+ /* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be
+ * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q.
+ */
+ efx_reado(efx, &temp, FR_AZ_TX_RESERVED);
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER, 0xfe);
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER_EN, 1);
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_ONE_PKT_PER_Q, 1);
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PUSH_EN, 1);
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_DIS_NON_IP_EV, 1);
+ /* Enable SW_EV to inherit in char driver - assume harmless here */
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_SOFT_EVT_EN, 1);
+ /* Prefetch threshold 2 => fetch when descriptor cache half empty */
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_THRESHOLD, 2);
+ /* Disable hardware watchdog which can misfire */
+ EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_WD_TMR, 0x3fffff);
+ /* Squash TX of packets of 16 bytes or less */
+ if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)
+ EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1);
+ efx_writeo(efx, &temp, FR_AZ_TX_RESERVED);
+
+ if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
+ EFX_POPULATE_OWORD_4(temp,
+ /* Default values */
+ FRF_BZ_TX_PACE_SB_NOT_AF, 0x15,
+ FRF_BZ_TX_PACE_SB_AF, 0xb,
+ FRF_BZ_TX_PACE_FB_BASE, 0,
+ /* Allow large pace values in the
+ * fast bin. */
+ FRF_BZ_TX_PACE_BIN_TH,
+ FFE_BZ_TX_PACE_RESERVED);
+ efx_writeo(efx, &temp, FR_BZ_TX_PACE);
+ }
+}
+
+/**************************************************************************
+ *
+ * Filter tables
+ *
+ **************************************************************************
+ */
+
+/* "Fudge factors" - difference between programmed value and actual depth.
+ * Due to pipelined implementation we need to program H/W with a value that
+ * is larger than the hop limit we want.
+ */
+#define EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD 3
+#define EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL 1
+
+/* Hard maximum search limit. Hardware will time-out beyond 200-something.
+ * We also need to avoid infinite loops in efx_farch_filter_search() when the
+ * table is full.
+ */
+#define EFX_FARCH_FILTER_CTL_SRCH_MAX 200
+
+/* Don't try very hard to find space for performance hints, as this is
+ * counter-productive. */
+#define EFX_FARCH_FILTER_CTL_SRCH_HINT_MAX 5
+
+enum efx_farch_filter_type {
+ EFX_FARCH_FILTER_TCP_FULL = 0,
+ EFX_FARCH_FILTER_TCP_WILD,
+ EFX_FARCH_FILTER_UDP_FULL,
+ EFX_FARCH_FILTER_UDP_WILD,
+ EFX_FARCH_FILTER_MAC_FULL = 4,
+ EFX_FARCH_FILTER_MAC_WILD,
+ EFX_FARCH_FILTER_UC_DEF = 8,
+ EFX_FARCH_FILTER_MC_DEF,
+ EFX_FARCH_FILTER_TYPE_COUNT, /* number of specific types */
+};
+
+enum efx_farch_filter_table_id {
+ EFX_FARCH_FILTER_TABLE_RX_IP = 0,
+ EFX_FARCH_FILTER_TABLE_RX_MAC,
+ EFX_FARCH_FILTER_TABLE_RX_DEF,
+ EFX_FARCH_FILTER_TABLE_TX_MAC,
+ EFX_FARCH_FILTER_TABLE_COUNT,
+};
+
+enum efx_farch_filter_index {
+ EFX_FARCH_FILTER_INDEX_UC_DEF,
+ EFX_FARCH_FILTER_INDEX_MC_DEF,
+ EFX_FARCH_FILTER_SIZE_RX_DEF,
+};
+
+struct efx_farch_filter_spec {
+ u8 type:4;
+ u8 priority:4;
+ u8 flags;
+ u16 dmaq_id;
+ u32 data[3];
+};
+
+struct efx_farch_filter_table {
+ enum efx_farch_filter_table_id id;
+ u32 offset; /* address of table relative to BAR */
+ unsigned size; /* number of entries */
+ unsigned step; /* step between entries */
+ unsigned used; /* number currently used */
+ unsigned long *used_bitmap;
+ struct efx_farch_filter_spec *spec;
+ unsigned search_limit[EFX_FARCH_FILTER_TYPE_COUNT];
+};
+
+struct efx_farch_filter_state {
+ struct efx_farch_filter_table table[EFX_FARCH_FILTER_TABLE_COUNT];
+};
+
+static void
+efx_farch_filter_table_clear_entry(struct efx_nic *efx,
+ struct efx_farch_filter_table *table,
+ unsigned int filter_idx);
+
+/* The filter hash function is LFSR polynomial x^16 + x^3 + 1 of a 32-bit
+ * key derived from the n-tuple. The initial LFSR state is 0xffff. */
+static u16 efx_farch_filter_hash(u32 key)
+{
+ u16 tmp;
+
+ /* First 16 rounds */
+ tmp = 0x1fff ^ key >> 16;
+ tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
+ tmp = tmp ^ tmp >> 9;
+ /* Last 16 rounds */
+ tmp = tmp ^ tmp << 13 ^ key;
+ tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
+ return tmp ^ tmp >> 9;
+}
+
+/* To allow for hash collisions, filter search continues at these
+ * increments from the first possible entry selected by the hash. */
+static u16 efx_farch_filter_increment(u32 key)
+{
+ return key * 2 - 1;
+}
+
+static enum efx_farch_filter_table_id
+efx_farch_filter_spec_table_id(const struct efx_farch_filter_spec *spec)
+{
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
+ (EFX_FARCH_FILTER_TCP_FULL >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
+ (EFX_FARCH_FILTER_TCP_WILD >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
+ (EFX_FARCH_FILTER_UDP_FULL >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_IP !=
+ (EFX_FARCH_FILTER_UDP_WILD >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_MAC !=
+ (EFX_FARCH_FILTER_MAC_FULL >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_RX_MAC !=
+ (EFX_FARCH_FILTER_MAC_WILD >> 2));
+ BUILD_BUG_ON(EFX_FARCH_FILTER_TABLE_TX_MAC !=
+ EFX_FARCH_FILTER_TABLE_RX_MAC + 2);
+ return (spec->type >> 2) + ((spec->flags & EFX_FILTER_FLAG_TX) ? 2 : 0);
+}
+
+static void efx_farch_filter_push_rx_config(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ struct efx_farch_filter_table *table;
+ efx_oword_t filter_ctl;
+
+ efx_reado(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
+ EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_FULL_SRCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_TCP_FULL] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
+ EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_WILD_SRCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_TCP_WILD] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
+ EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_FULL_SRCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_UDP_FULL] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
+ EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_WILD_SRCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_UDP_WILD] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_MAC];
+ if (table->size) {
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_MAC_FULL] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT,
+ table->search_limit[EFX_FARCH_FILTER_MAC_WILD] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
+ }
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
+ if (table->size) {
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_UNICAST_NOMATCH_Q_ID,
+ table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].dmaq_id);
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_UNICAST_NOMATCH_RSS_ENABLED,
+ !!(table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].flags &
+ EFX_FILTER_FLAG_RX_RSS));
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_MULTICAST_NOMATCH_Q_ID,
+ table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].dmaq_id);
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_CZ_MULTICAST_NOMATCH_RSS_ENABLED,
+ !!(table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].flags &
+ EFX_FILTER_FLAG_RX_RSS));
+
+ /* There is a single bit to enable RX scatter for all
+ * unmatched packets. Only set it if scatter is
+ * enabled in both filter specs.
+ */
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_BZ_SCATTER_ENBL_NO_MATCH_Q,
+ !!(table->spec[EFX_FARCH_FILTER_INDEX_UC_DEF].flags &
+ table->spec[EFX_FARCH_FILTER_INDEX_MC_DEF].flags &
+ EFX_FILTER_FLAG_RX_SCATTER));
+ } else if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
+ /* We don't expose 'default' filters because unmatched
+ * packets always go to the queue number found in the
+ * RSS table. But we still need to set the RX scatter
+ * bit here.
+ */
+ EFX_SET_OWORD_FIELD(
+ filter_ctl, FRF_BZ_SCATTER_ENBL_NO_MATCH_Q,
+ efx->rx_scatter);
+ }
+
+ efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
+}
+
+static void efx_farch_filter_push_tx_limits(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ struct efx_farch_filter_table *table;
+ efx_oword_t tx_cfg;
+
+ efx_reado(efx, &tx_cfg, FR_AZ_TX_CFG);
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_TX_MAC];
+ if (table->size) {
+ EFX_SET_OWORD_FIELD(
+ tx_cfg, FRF_CZ_TX_ETH_FILTER_FULL_SEARCH_RANGE,
+ table->search_limit[EFX_FARCH_FILTER_MAC_FULL] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_FULL);
+ EFX_SET_OWORD_FIELD(
+ tx_cfg, FRF_CZ_TX_ETH_FILTER_WILD_SEARCH_RANGE,
+ table->search_limit[EFX_FARCH_FILTER_MAC_WILD] +
+ EFX_FARCH_FILTER_CTL_SRCH_FUDGE_WILD);
+ }
+
+ efx_writeo(efx, &tx_cfg, FR_AZ_TX_CFG);
+}
+
+static int
+efx_farch_filter_from_gen_spec(struct efx_farch_filter_spec *spec,
+ const struct efx_filter_spec *gen_spec)
+{
+ bool is_full = false;
+
+ if ((gen_spec->flags & EFX_FILTER_FLAG_RX_RSS) &&
+ gen_spec->rss_context != EFX_FILTER_RSS_CONTEXT_DEFAULT)
+ return -EINVAL;
+
+ spec->priority = gen_spec->priority;
+ spec->flags = gen_spec->flags;
+ spec->dmaq_id = gen_spec->dmaq_id;
+
+ switch (gen_spec->match_flags) {
+ case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
+ EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT):
+ is_full = true;
+ /* fall through */
+ case (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT): {
+ __be32 rhost, host1, host2;
+ __be16 rport, port1, port2;
+
+ EFX_BUG_ON_PARANOID(!(gen_spec->flags & EFX_FILTER_FLAG_RX));
+
+ if (gen_spec->ether_type != htons(ETH_P_IP))
+ return -EPROTONOSUPPORT;
+ if (gen_spec->loc_port == 0 ||
+ (is_full && gen_spec->rem_port == 0))
+ return -EADDRNOTAVAIL;
+ switch (gen_spec->ip_proto) {
+ case IPPROTO_TCP:
+ spec->type = (is_full ? EFX_FARCH_FILTER_TCP_FULL :
+ EFX_FARCH_FILTER_TCP_WILD);
+ break;
+ case IPPROTO_UDP:
+ spec->type = (is_full ? EFX_FARCH_FILTER_UDP_FULL :
+ EFX_FARCH_FILTER_UDP_WILD);
+ break;
+ default:
+ return -EPROTONOSUPPORT;
+ }
+
+ /* Filter is constructed in terms of source and destination,
+ * with the odd wrinkle that the ports are swapped in a UDP
+ * wildcard filter. We need to convert from local and remote
+ * (= zero for wildcard) addresses.
+ */
+ rhost = is_full ? gen_spec->rem_host[0] : 0;
+ rport = is_full ? gen_spec->rem_port : 0;
+ host1 = rhost;
+ host2 = gen_spec->loc_host[0];
+ if (!is_full && gen_spec->ip_proto == IPPROTO_UDP) {
+ port1 = gen_spec->loc_port;
+ port2 = rport;
+ } else {
+ port1 = rport;
+ port2 = gen_spec->loc_port;
+ }
+ spec->data[0] = ntohl(host1) << 16 | ntohs(port1);
+ spec->data[1] = ntohs(port2) << 16 | ntohl(host1) >> 16;
+ spec->data[2] = ntohl(host2);
+
+ break;
+ }
+
+ case EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_OUTER_VID:
+ is_full = true;
+ /* fall through */
+ case EFX_FILTER_MATCH_LOC_MAC:
+ spec->type = (is_full ? EFX_FARCH_FILTER_MAC_FULL :
+ EFX_FARCH_FILTER_MAC_WILD);
+ spec->data[0] = is_full ? ntohs(gen_spec->outer_vid) : 0;
+ spec->data[1] = (gen_spec->loc_mac[2] << 24 |
+ gen_spec->loc_mac[3] << 16 |
+ gen_spec->loc_mac[4] << 8 |
+ gen_spec->loc_mac[5]);
+ spec->data[2] = (gen_spec->loc_mac[0] << 8 |
+ gen_spec->loc_mac[1]);
+ break;
+
+ case EFX_FILTER_MATCH_LOC_MAC_IG:
+ spec->type = (is_multicast_ether_addr(gen_spec->loc_mac) ?
+ EFX_FARCH_FILTER_MC_DEF :
+ EFX_FARCH_FILTER_UC_DEF);
+ memset(spec->data, 0, sizeof(spec->data)); /* ensure equality */
+ break;
+
+ default:
+ return -EPROTONOSUPPORT;
+ }
+
+ return 0;
+}
+
+static void
+efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec,
+ const struct efx_farch_filter_spec *spec)
+{
+ bool is_full = false;
+
+ /* *gen_spec should be completely initialised, to be consistent
+ * with efx_filter_init_{rx,tx}() and in case we want to copy
+ * it back to userland.
+ */
+ memset(gen_spec, 0, sizeof(*gen_spec));
+
+ gen_spec->priority = spec->priority;
+ gen_spec->flags = spec->flags;
+ gen_spec->dmaq_id = spec->dmaq_id;
+
+ switch (spec->type) {
+ case EFX_FARCH_FILTER_TCP_FULL:
+ case EFX_FARCH_FILTER_UDP_FULL:
+ is_full = true;
+ /* fall through */
+ case EFX_FARCH_FILTER_TCP_WILD:
+ case EFX_FARCH_FILTER_UDP_WILD: {
+ __be32 host1, host2;
+ __be16 port1, port2;
+
+ gen_spec->match_flags =
+ EFX_FILTER_MATCH_ETHER_TYPE |
+ EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT;
+ if (is_full)
+ gen_spec->match_flags |= (EFX_FILTER_MATCH_REM_HOST |
+ EFX_FILTER_MATCH_REM_PORT);
+ gen_spec->ether_type = htons(ETH_P_IP);
+ gen_spec->ip_proto =
+ (spec->type == EFX_FARCH_FILTER_TCP_FULL ||
+ spec->type == EFX_FARCH_FILTER_TCP_WILD) ?
+ IPPROTO_TCP : IPPROTO_UDP;
+
+ host1 = htonl(spec->data[0] >> 16 | spec->data[1] << 16);
+ port1 = htons(spec->data[0]);
+ host2 = htonl(spec->data[2]);
+ port2 = htons(spec->data[1] >> 16);
+ if (spec->flags & EFX_FILTER_FLAG_TX) {
+ gen_spec->loc_host[0] = host1;
+ gen_spec->rem_host[0] = host2;
+ } else {
+ gen_spec->loc_host[0] = host2;
+ gen_spec->rem_host[0] = host1;
+ }
+ if (!!(gen_spec->flags & EFX_FILTER_FLAG_TX) ^
+ (!is_full && gen_spec->ip_proto == IPPROTO_UDP)) {
+ gen_spec->loc_port = port1;
+ gen_spec->rem_port = port2;
+ } else {
+ gen_spec->loc_port = port2;
+ gen_spec->rem_port = port1;
+ }
+
+ break;
+ }
+
+ case EFX_FARCH_FILTER_MAC_FULL:
+ is_full = true;
+ /* fall through */
+ case EFX_FARCH_FILTER_MAC_WILD:
+ gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC;
+ if (is_full)
+ gen_spec->match_flags |= EFX_FILTER_MATCH_OUTER_VID;
+ gen_spec->loc_mac[0] = spec->data[2] >> 8;
+ gen_spec->loc_mac[1] = spec->data[2];
+ gen_spec->loc_mac[2] = spec->data[1] >> 24;
+ gen_spec->loc_mac[3] = spec->data[1] >> 16;
+ gen_spec->loc_mac[4] = spec->data[1] >> 8;
+ gen_spec->loc_mac[5] = spec->data[1];
+ gen_spec->outer_vid = htons(spec->data[0]);
+ break;
+
+ case EFX_FARCH_FILTER_UC_DEF:
+ case EFX_FARCH_FILTER_MC_DEF:
+ gen_spec->match_flags = EFX_FILTER_MATCH_LOC_MAC_IG;
+ gen_spec->loc_mac[0] = spec->type == EFX_FARCH_FILTER_MC_DEF;
+ break;
+
+ default:
+ WARN_ON(1);
+ break;
+ }
+}
+
+static void
+efx_farch_filter_init_rx_auto(struct efx_nic *efx,
+ struct efx_farch_filter_spec *spec)
+{
+ /* If there's only one channel then disable RSS for non VF
+ * traffic, thereby allowing VFs to use RSS when the PF can't.
+ */
+ spec->priority = EFX_FILTER_PRI_AUTO;
+ spec->flags = (EFX_FILTER_FLAG_RX |
+ (efx->n_rx_channels > 1 ? EFX_FILTER_FLAG_RX_RSS : 0) |
+ (efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0));
+ spec->dmaq_id = 0;
+}
+
+/* Build a filter entry and return its n-tuple key. */
+static u32 efx_farch_filter_build(efx_oword_t *filter,
+ struct efx_farch_filter_spec *spec)
+{
+ u32 data3;
+
+ switch (efx_farch_filter_spec_table_id(spec)) {
+ case EFX_FARCH_FILTER_TABLE_RX_IP: {
+ bool is_udp = (spec->type == EFX_FARCH_FILTER_UDP_FULL ||
+ spec->type == EFX_FARCH_FILTER_UDP_WILD);
+ EFX_POPULATE_OWORD_7(
+ *filter,
+ FRF_BZ_RSS_EN,
+ !!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
+ FRF_BZ_SCATTER_EN,
+ !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
+ FRF_BZ_TCP_UDP, is_udp,
+ FRF_BZ_RXQ_ID, spec->dmaq_id,
+ EFX_DWORD_2, spec->data[2],
+ EFX_DWORD_1, spec->data[1],
+ EFX_DWORD_0, spec->data[0]);
+ data3 = is_udp;
+ break;
+ }
+
+ case EFX_FARCH_FILTER_TABLE_RX_MAC: {
+ bool is_wild = spec->type == EFX_FARCH_FILTER_MAC_WILD;
+ EFX_POPULATE_OWORD_7(
+ *filter,
+ FRF_CZ_RMFT_RSS_EN,
+ !!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
+ FRF_CZ_RMFT_SCATTER_EN,
+ !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
+ FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id,
+ FRF_CZ_RMFT_WILDCARD_MATCH, is_wild,
+ FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2],
+ FRF_CZ_RMFT_DEST_MAC_LO, spec->data[1],
+ FRF_CZ_RMFT_VLAN_ID, spec->data[0]);
+ data3 = is_wild;
+ break;
+ }
+
+ case EFX_FARCH_FILTER_TABLE_TX_MAC: {
+ bool is_wild = spec->type == EFX_FARCH_FILTER_MAC_WILD;
+ EFX_POPULATE_OWORD_5(*filter,
+ FRF_CZ_TMFT_TXQ_ID, spec->dmaq_id,
+ FRF_CZ_TMFT_WILDCARD_MATCH, is_wild,
+ FRF_CZ_TMFT_SRC_MAC_HI, spec->data[2],
+ FRF_CZ_TMFT_SRC_MAC_LO, spec->data[1],
+ FRF_CZ_TMFT_VLAN_ID, spec->data[0]);
+ data3 = is_wild | spec->dmaq_id << 1;
+ break;
+ }
+
+ default:
+ BUG();
+ }
+
+ return spec->data[0] ^ spec->data[1] ^ spec->data[2] ^ data3;
+}
+
+static bool efx_farch_filter_equal(const struct efx_farch_filter_spec *left,
+ const struct efx_farch_filter_spec *right)
+{
+ if (left->type != right->type ||
+ memcmp(left->data, right->data, sizeof(left->data)))
+ return false;
+
+ if (left->flags & EFX_FILTER_FLAG_TX &&
+ left->dmaq_id != right->dmaq_id)
+ return false;
+
+ return true;
+}
+
+/*
+ * Construct/deconstruct external filter IDs. At least the RX filter
+ * IDs must be ordered by matching priority, for RX NFC semantics.
+ *
+ * Deconstruction needs to be robust against invalid IDs so that
+ * efx_filter_remove_id_safe() and efx_filter_get_filter_safe() can
+ * accept user-provided IDs.
+ */
+
+#define EFX_FARCH_FILTER_MATCH_PRI_COUNT 5
+
+static const u8 efx_farch_filter_type_match_pri[EFX_FARCH_FILTER_TYPE_COUNT] = {
+ [EFX_FARCH_FILTER_TCP_FULL] = 0,
+ [EFX_FARCH_FILTER_UDP_FULL] = 0,
+ [EFX_FARCH_FILTER_TCP_WILD] = 1,
+ [EFX_FARCH_FILTER_UDP_WILD] = 1,
+ [EFX_FARCH_FILTER_MAC_FULL] = 2,
+ [EFX_FARCH_FILTER_MAC_WILD] = 3,
+ [EFX_FARCH_FILTER_UC_DEF] = 4,
+ [EFX_FARCH_FILTER_MC_DEF] = 4,
+};
+
+static const enum efx_farch_filter_table_id efx_farch_filter_range_table[] = {
+ EFX_FARCH_FILTER_TABLE_RX_IP, /* RX match pri 0 */
+ EFX_FARCH_FILTER_TABLE_RX_IP,
+ EFX_FARCH_FILTER_TABLE_RX_MAC,
+ EFX_FARCH_FILTER_TABLE_RX_MAC,
+ EFX_FARCH_FILTER_TABLE_RX_DEF, /* RX match pri 4 */
+ EFX_FARCH_FILTER_TABLE_TX_MAC, /* TX match pri 0 */
+ EFX_FARCH_FILTER_TABLE_TX_MAC, /* TX match pri 1 */
+};
+
+#define EFX_FARCH_FILTER_INDEX_WIDTH 13
+#define EFX_FARCH_FILTER_INDEX_MASK ((1 << EFX_FARCH_FILTER_INDEX_WIDTH) - 1)
+
+static inline u32
+efx_farch_filter_make_id(const struct efx_farch_filter_spec *spec,
+ unsigned int index)
+{
+ unsigned int range;
+
+ range = efx_farch_filter_type_match_pri[spec->type];
+ if (!(spec->flags & EFX_FILTER_FLAG_RX))
+ range += EFX_FARCH_FILTER_MATCH_PRI_COUNT;
+
+ return range << EFX_FARCH_FILTER_INDEX_WIDTH | index;
+}
+
+static inline enum efx_farch_filter_table_id
+efx_farch_filter_id_table_id(u32 id)
+{
+ unsigned int range = id >> EFX_FARCH_FILTER_INDEX_WIDTH;
+
+ if (range < ARRAY_SIZE(efx_farch_filter_range_table))
+ return efx_farch_filter_range_table[range];
+ else
+ return EFX_FARCH_FILTER_TABLE_COUNT; /* invalid */
+}
+
+static inline unsigned int efx_farch_filter_id_index(u32 id)
+{
+ return id & EFX_FARCH_FILTER_INDEX_MASK;
+}
+
+u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ unsigned int range = EFX_FARCH_FILTER_MATCH_PRI_COUNT - 1;
+ enum efx_farch_filter_table_id table_id;
+
+ do {
+ table_id = efx_farch_filter_range_table[range];
+ if (state->table[table_id].size != 0)
+ return range << EFX_FARCH_FILTER_INDEX_WIDTH |
+ state->table[table_id].size;
+ } while (range--);
+
+ return 0;
+}
+
+s32 efx_farch_filter_insert(struct efx_nic *efx,
+ struct efx_filter_spec *gen_spec,
+ bool replace_equal)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ struct efx_farch_filter_table *table;
+ struct efx_farch_filter_spec spec;
+ efx_oword_t filter;
+ int rep_index, ins_index;
+ unsigned int depth = 0;
+ int rc;
+
+ rc = efx_farch_filter_from_gen_spec(&spec, gen_spec);
+ if (rc)
+ return rc;
+
+ table = &state->table[efx_farch_filter_spec_table_id(&spec)];
+ if (table->size == 0)
+ return -EINVAL;
+
+ netif_vdbg(efx, hw, efx->net_dev,
+ "%s: type %d search_limit=%d", __func__, spec.type,
+ table->search_limit[spec.type]);
+
+ if (table->id == EFX_FARCH_FILTER_TABLE_RX_DEF) {
+ /* One filter spec per type */
+ BUILD_BUG_ON(EFX_FARCH_FILTER_INDEX_UC_DEF != 0);
+ BUILD_BUG_ON(EFX_FARCH_FILTER_INDEX_MC_DEF !=
+ EFX_FARCH_FILTER_MC_DEF - EFX_FARCH_FILTER_UC_DEF);
+ rep_index = spec.type - EFX_FARCH_FILTER_UC_DEF;
+ ins_index = rep_index;
+
+ spin_lock_bh(&efx->filter_lock);
+ } else {
+ /* Search concurrently for
+ * (1) a filter to be replaced (rep_index): any filter
+ * with the same match values, up to the current
+ * search depth for this type, and
+ * (2) the insertion point (ins_index): (1) or any
+ * free slot before it or up to the maximum search
+ * depth for this priority
+ * We fail if we cannot find (2).
+ *
+ * We can stop once either
+ * (a) we find (1), in which case we have definitely
+ * found (2) as well; or
+ * (b) we have searched exhaustively for (1), and have
+ * either found (2) or searched exhaustively for it
+ */
+ u32 key = efx_farch_filter_build(&filter, &spec);
+ unsigned int hash = efx_farch_filter_hash(key);
+ unsigned int incr = efx_farch_filter_increment(key);
+ unsigned int max_rep_depth = table->search_limit[spec.type];
+ unsigned int max_ins_depth =
+ spec.priority <= EFX_FILTER_PRI_HINT ?
+ EFX_FARCH_FILTER_CTL_SRCH_HINT_MAX :
+ EFX_FARCH_FILTER_CTL_SRCH_MAX;
+ unsigned int i = hash & (table->size - 1);
+
+ ins_index = -1;
+ depth = 1;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (;;) {
+ if (!test_bit(i, table->used_bitmap)) {
+ if (ins_index < 0)
+ ins_index = i;
+ } else if (efx_farch_filter_equal(&spec,
+ &table->spec[i])) {
+ /* Case (a) */
+ if (ins_index < 0)
+ ins_index = i;
+ rep_index = i;
+ break;
+ }
+
+ if (depth >= max_rep_depth &&
+ (ins_index >= 0 || depth >= max_ins_depth)) {
+ /* Case (b) */
+ if (ins_index < 0) {
+ rc = -EBUSY;
+ goto out;
+ }
+ rep_index = -1;
+ break;
+ }
+
+ i = (i + incr) & (table->size - 1);
+ ++depth;
+ }
+ }
+
+ /* If we found a filter to be replaced, check whether we
+ * should do so
+ */
+ if (rep_index >= 0) {
+ struct efx_farch_filter_spec *saved_spec =
+ &table->spec[rep_index];
+
+ if (spec.priority == saved_spec->priority && !replace_equal) {
+ rc = -EEXIST;
+ goto out;
+ }
+ if (spec.priority < saved_spec->priority) {
+ rc = -EPERM;
+ goto out;
+ }
+ if (saved_spec->priority == EFX_FILTER_PRI_AUTO ||
+ saved_spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO)
+ spec.flags |= EFX_FILTER_FLAG_RX_OVER_AUTO;
+ }
+
+ /* Insert the filter */
+ if (ins_index != rep_index) {
+ __set_bit(ins_index, table->used_bitmap);
+ ++table->used;
+ }
+ table->spec[ins_index] = spec;
+
+ if (table->id == EFX_FARCH_FILTER_TABLE_RX_DEF) {
+ efx_farch_filter_push_rx_config(efx);
+ } else {
+ if (table->search_limit[spec.type] < depth) {
+ table->search_limit[spec.type] = depth;
+ if (spec.flags & EFX_FILTER_FLAG_TX)
+ efx_farch_filter_push_tx_limits(efx);
+ else
+ efx_farch_filter_push_rx_config(efx);
+ }
+
+ efx_writeo(efx, &filter,
+ table->offset + table->step * ins_index);
+
+ /* If we were able to replace a filter by inserting
+ * at a lower depth, clear the replaced filter
+ */
+ if (ins_index != rep_index && rep_index >= 0)
+ efx_farch_filter_table_clear_entry(efx, table,
+ rep_index);
+ }
+
+ netif_vdbg(efx, hw, efx->net_dev,
+ "%s: filter type %d index %d rxq %u set",
+ __func__, spec.type, ins_index, spec.dmaq_id);
+ rc = efx_farch_filter_make_id(&spec, ins_index);
+
+out:
+ spin_unlock_bh(&efx->filter_lock);
+ return rc;
+}
+
+static void
+efx_farch_filter_table_clear_entry(struct efx_nic *efx,
+ struct efx_farch_filter_table *table,
+ unsigned int filter_idx)
+{
+ static efx_oword_t filter;
+
+ EFX_WARN_ON_PARANOID(!test_bit(filter_idx, table->used_bitmap));
+ BUG_ON(table->offset == 0); /* can't clear MAC default filters */
+
+ __clear_bit(filter_idx, table->used_bitmap);
+ --table->used;
+ memset(&table->spec[filter_idx], 0, sizeof(table->spec[0]));
+
+ efx_writeo(efx, &filter, table->offset + table->step * filter_idx);
+
+ /* If this filter required a greater search depth than
+ * any other, the search limit for its type can now be
+ * decreased. However, it is hard to determine that
+ * unless the table has become completely empty - in
+ * which case, all its search limits can be set to 0.
+ */
+ if (unlikely(table->used == 0)) {
+ memset(table->search_limit, 0, sizeof(table->search_limit));
+ if (table->id == EFX_FARCH_FILTER_TABLE_TX_MAC)
+ efx_farch_filter_push_tx_limits(efx);
+ else
+ efx_farch_filter_push_rx_config(efx);
+ }
+}
+
+static int efx_farch_filter_remove(struct efx_nic *efx,
+ struct efx_farch_filter_table *table,
+ unsigned int filter_idx,
+ enum efx_filter_priority priority)
+{
+ struct efx_farch_filter_spec *spec = &table->spec[filter_idx];
+
+ if (!test_bit(filter_idx, table->used_bitmap) ||
+ spec->priority != priority)
+ return -ENOENT;
+
+ if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) {
+ efx_farch_filter_init_rx_auto(efx, spec);
+ efx_farch_filter_push_rx_config(efx);
+ } else {
+ efx_farch_filter_table_clear_entry(efx, table, filter_idx);
+ }
+
+ return 0;
+}
+
+int efx_farch_filter_remove_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ unsigned int filter_idx;
+ struct efx_farch_filter_spec *spec;
+ int rc;
+
+ table_id = efx_farch_filter_id_table_id(filter_id);
+ if ((unsigned int)table_id >= EFX_FARCH_FILTER_TABLE_COUNT)
+ return -ENOENT;
+ table = &state->table[table_id];
+
+ filter_idx = efx_farch_filter_id_index(filter_id);
+ if (filter_idx >= table->size)
+ return -ENOENT;
+ spec = &table->spec[filter_idx];
+
+ spin_lock_bh(&efx->filter_lock);
+ rc = efx_farch_filter_remove(efx, table, filter_idx, priority);
+ spin_unlock_bh(&efx->filter_lock);
+
+ return rc;
+}
+
+int efx_farch_filter_get_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *spec_buf)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ struct efx_farch_filter_spec *spec;
+ unsigned int filter_idx;
+ int rc;
+
+ table_id = efx_farch_filter_id_table_id(filter_id);
+ if ((unsigned int)table_id >= EFX_FARCH_FILTER_TABLE_COUNT)
+ return -ENOENT;
+ table = &state->table[table_id];
+
+ filter_idx = efx_farch_filter_id_index(filter_id);
+ if (filter_idx >= table->size)
+ return -ENOENT;
+ spec = &table->spec[filter_idx];
+
+ spin_lock_bh(&efx->filter_lock);
+
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ spec->priority == priority) {
+ efx_farch_filter_to_gen_spec(spec_buf, spec);
+ rc = 0;
+ } else {
+ rc = -ENOENT;
+ }
+
+ spin_unlock_bh(&efx->filter_lock);
+
+ return rc;
+}
+
+static void
+efx_farch_filter_table_clear(struct efx_nic *efx,
+ enum efx_farch_filter_table_id table_id,
+ enum efx_filter_priority priority)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ struct efx_farch_filter_table *table = &state->table[table_id];
+ unsigned int filter_idx;
+
+ spin_lock_bh(&efx->filter_lock);
+ for (filter_idx = 0; filter_idx < table->size; ++filter_idx) {
+ if (table->spec[filter_idx].priority != EFX_FILTER_PRI_AUTO)
+ efx_farch_filter_remove(efx, table,
+ filter_idx, priority);
+ }
+ spin_unlock_bh(&efx->filter_lock);
+}
+
+int efx_farch_filter_clear_rx(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_IP,
+ priority);
+ efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_MAC,
+ priority);
+ efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_DEF,
+ priority);
+ return 0;
+}
+
+u32 efx_farch_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ unsigned int filter_idx;
+ u32 count = 0;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
+ table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
+ table_id++) {
+ table = &state->table[table_id];
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ table->spec[filter_idx].priority == priority)
+ ++count;
+ }
+ }
+
+ spin_unlock_bh(&efx->filter_lock);
+
+ return count;
+}
+
+s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ unsigned int filter_idx;
+ s32 count = 0;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
+ table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
+ table_id++) {
+ table = &state->table[table_id];
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (test_bit(filter_idx, table->used_bitmap) &&
+ table->spec[filter_idx].priority == priority) {
+ if (count == size) {
+ count = -EMSGSIZE;
+ goto out;
+ }
+ buf[count++] = efx_farch_filter_make_id(
+ &table->spec[filter_idx], filter_idx);
+ }
+ }
+ }
+out:
+ spin_unlock_bh(&efx->filter_lock);
+
+ return count;
+}
+
+/* Restore filter stater after reset */
+void efx_farch_filter_table_restore(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ efx_oword_t filter;
+ unsigned int filter_idx;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
+ table = &state->table[table_id];
+
+ /* Check whether this is a regular register table */
+ if (table->step == 0)
+ continue;
+
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (!test_bit(filter_idx, table->used_bitmap))
+ continue;
+ efx_farch_filter_build(&filter, &table->spec[filter_idx]);
+ efx_writeo(efx, &filter,
+ table->offset + table->step * filter_idx);
+ }
+ }
+
+ efx_farch_filter_push_rx_config(efx);
+ efx_farch_filter_push_tx_limits(efx);
+
+ spin_unlock_bh(&efx->filter_lock);
+}
+
+void efx_farch_filter_table_remove(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+
+ for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
+ kfree(state->table[table_id].used_bitmap);
+ vfree(state->table[table_id].spec);
+ }
+ kfree(state);
+}
+
+int efx_farch_filter_table_probe(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state;
+ struct efx_farch_filter_table *table;
+ unsigned table_id;
+
+ state = kzalloc(sizeof(struct efx_farch_filter_state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+ efx->filter_state = state;
+
+ if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
+ table->id = EFX_FARCH_FILTER_TABLE_RX_IP;
+ table->offset = FR_BZ_RX_FILTER_TBL0;
+ table->size = FR_BZ_RX_FILTER_TBL0_ROWS;
+ table->step = FR_BZ_RX_FILTER_TBL0_STEP;
+ }
+
+ if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) {
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_MAC];
+ table->id = EFX_FARCH_FILTER_TABLE_RX_MAC;
+ table->offset = FR_CZ_RX_MAC_FILTER_TBL0;
+ table->size = FR_CZ_RX_MAC_FILTER_TBL0_ROWS;
+ table->step = FR_CZ_RX_MAC_FILTER_TBL0_STEP;
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
+ table->id = EFX_FARCH_FILTER_TABLE_RX_DEF;
+ table->size = EFX_FARCH_FILTER_SIZE_RX_DEF;
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_TX_MAC];
+ table->id = EFX_FARCH_FILTER_TABLE_TX_MAC;
+ table->offset = FR_CZ_TX_MAC_FILTER_TBL0;
+ table->size = FR_CZ_TX_MAC_FILTER_TBL0_ROWS;
+ table->step = FR_CZ_TX_MAC_FILTER_TBL0_STEP;
+ }
+
+ for (table_id = 0; table_id < EFX_FARCH_FILTER_TABLE_COUNT; table_id++) {
+ table = &state->table[table_id];
+ if (table->size == 0)
+ continue;
+ table->used_bitmap = kcalloc(BITS_TO_LONGS(table->size),
+ sizeof(unsigned long),
+ GFP_KERNEL);
+ if (!table->used_bitmap)
+ goto fail;
+ table->spec = vzalloc(table->size * sizeof(*table->spec));
+ if (!table->spec)
+ goto fail;
+ }
+
+ table = &state->table[EFX_FARCH_FILTER_TABLE_RX_DEF];
+ if (table->size) {
+ /* RX default filters must always exist */
+ struct efx_farch_filter_spec *spec;
+ unsigned i;
+
+ for (i = 0; i < EFX_FARCH_FILTER_SIZE_RX_DEF; i++) {
+ spec = &table->spec[i];
+ spec->type = EFX_FARCH_FILTER_UC_DEF + i;
+ efx_farch_filter_init_rx_auto(efx, spec);
+ __set_bit(i, table->used_bitmap);
+ }
+ }
+
+ efx_farch_filter_push_rx_config(efx);
+
+ return 0;
+
+fail:
+ efx_farch_filter_table_remove(efx);
+ return -ENOMEM;
+}
+
+/* Update scatter enable flags for filters pointing to our own RX queues */
+void efx_farch_filter_update_rx_scatter(struct efx_nic *efx)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ enum efx_farch_filter_table_id table_id;
+ struct efx_farch_filter_table *table;
+ efx_oword_t filter;
+ unsigned int filter_idx;
+
+ spin_lock_bh(&efx->filter_lock);
+
+ for (table_id = EFX_FARCH_FILTER_TABLE_RX_IP;
+ table_id <= EFX_FARCH_FILTER_TABLE_RX_DEF;
+ table_id++) {
+ table = &state->table[table_id];
+
+ for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
+ if (!test_bit(filter_idx, table->used_bitmap) ||
+ table->spec[filter_idx].dmaq_id >=
+ efx->n_rx_channels)
+ continue;
+
+ if (efx->rx_scatter)
+ table->spec[filter_idx].flags |=
+ EFX_FILTER_FLAG_RX_SCATTER;
+ else
+ table->spec[filter_idx].flags &=
+ ~EFX_FILTER_FLAG_RX_SCATTER;
+
+ if (table_id == EFX_FARCH_FILTER_TABLE_RX_DEF)
+ /* Pushed by efx_farch_filter_push_rx_config() */
+ continue;
+
+ efx_farch_filter_build(&filter, &table->spec[filter_idx]);
+ efx_writeo(efx, &filter,
+ table->offset + table->step * filter_idx);
+ }
+ }
+
+ efx_farch_filter_push_rx_config(efx);
+
+ spin_unlock_bh(&efx->filter_lock);
+}
+
+#ifdef CONFIG_RFS_ACCEL
+
+s32 efx_farch_filter_rfs_insert(struct efx_nic *efx,
+ struct efx_filter_spec *gen_spec)
+{
+ return efx_farch_filter_insert(efx, gen_spec, true);
+}
+
+bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
+ unsigned int index)
+{
+ struct efx_farch_filter_state *state = efx->filter_state;
+ struct efx_farch_filter_table *table =
+ &state->table[EFX_FARCH_FILTER_TABLE_RX_IP];
+
+ if (test_bit(index, table->used_bitmap) &&
+ table->spec[index].priority == EFX_FILTER_PRI_HINT &&
+ rps_may_expire_flow(efx->net_dev, table->spec[index].dmaq_id,
+ flow_id, index)) {
+ efx_farch_filter_table_clear_entry(efx, table, index);
+ return true;
+ }
+
+ return false;
+}
+
+#endif /* CONFIG_RFS_ACCEL */
+
+void efx_farch_filter_sync_rx_mode(struct efx_nic *efx)
+{
+ struct net_device *net_dev = efx->net_dev;
+ struct netdev_hw_addr *ha;
+ union efx_multicast_hash *mc_hash = &efx->multicast_hash;
+ u32 crc;
+ int bit;
+
+ netif_addr_lock_bh(net_dev);
+
+ efx->unicast_filter = !(net_dev->flags & IFF_PROMISC);
+
+ /* Build multicast hash table */
+ if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI)) {
+ memset(mc_hash, 0xff, sizeof(*mc_hash));
+ } else {
+ memset(mc_hash, 0x00, sizeof(*mc_hash));
+ netdev_for_each_mc_addr(ha, net_dev) {
+ crc = ether_crc_le(ETH_ALEN, ha->addr);
+ bit = crc & (EFX_MCAST_HASH_ENTRIES - 1);
+ __set_bit_le(bit, mc_hash);
+ }
+
+ /* Broadcast packets go through the multicast hash filter.
+ * ether_crc_le() of the broadcast address is 0xbe2612ff
+ * so we always add bit 0xff to the mask.
+ */
+ __set_bit_le(0xff, mc_hash);
+ }
+
+ netif_addr_unlock_bh(net_dev);
+}
diff --git a/drivers/net/ethernet/sfc/regs.h b/drivers/net/ethernet/sfc/farch_regs.h
index cc2c86b76a7..7019a712e79 100644
--- a/drivers/net/ethernet/sfc/regs.h
+++ b/drivers/net/ethernet/sfc/farch_regs.h
@@ -1,15 +1,15 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2012 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation, incorporated herein by reference.
*/
-#ifndef EFX_REGS_H
-#define EFX_REGS_H
+#ifndef EFX_FARCH_REGS_H
+#define EFX_FARCH_REGS_H
/*
* Falcon hardware architecture definitions have a name prefix following
@@ -2446,8 +2446,8 @@
#define FRF_CZ_RMFT_RXQ_ID_WIDTH 12
#define FRF_CZ_RMFT_WILDCARD_MATCH_LBN 60
#define FRF_CZ_RMFT_WILDCARD_MATCH_WIDTH 1
-#define FRF_CZ_RMFT_DEST_MAC_LBN 16
-#define FRF_CZ_RMFT_DEST_MAC_WIDTH 44
+#define FRF_CZ_RMFT_DEST_MAC_LBN 12
+#define FRF_CZ_RMFT_DEST_MAC_WIDTH 48
#define FRF_CZ_RMFT_VLAN_ID_LBN 0
#define FRF_CZ_RMFT_VLAN_ID_WIDTH 12
@@ -2523,8 +2523,8 @@
#define FRF_CZ_TMFT_TXQ_ID_WIDTH 12
#define FRF_CZ_TMFT_WILDCARD_MATCH_LBN 60
#define FRF_CZ_TMFT_WILDCARD_MATCH_WIDTH 1
-#define FRF_CZ_TMFT_SRC_MAC_LBN 16
-#define FRF_CZ_TMFT_SRC_MAC_WIDTH 44
+#define FRF_CZ_TMFT_SRC_MAC_LBN 12
+#define FRF_CZ_TMFT_SRC_MAC_WIDTH 48
#define FRF_CZ_TMFT_VLAN_ID_LBN 0
#define FRF_CZ_TMFT_VLAN_ID_WIDTH 12
@@ -2895,17 +2895,17 @@
/* RX_MAC_FILTER_TBL0 */
/* RMFT_DEST_MAC is wider than 32 bits */
-#define FRF_CZ_RMFT_DEST_MAC_LO_LBN 12
+#define FRF_CZ_RMFT_DEST_MAC_LO_LBN FRF_CZ_RMFT_DEST_MAC_LBN
#define FRF_CZ_RMFT_DEST_MAC_LO_WIDTH 32
-#define FRF_CZ_RMFT_DEST_MAC_HI_LBN 44
-#define FRF_CZ_RMFT_DEST_MAC_HI_WIDTH 16
+#define FRF_CZ_RMFT_DEST_MAC_HI_LBN (FRF_CZ_RMFT_DEST_MAC_LBN + 32)
+#define FRF_CZ_RMFT_DEST_MAC_HI_WIDTH (FRF_CZ_RMFT_DEST_MAC_WIDTH - 32)
/* TX_MAC_FILTER_TBL0 */
/* TMFT_SRC_MAC is wider than 32 bits */
-#define FRF_CZ_TMFT_SRC_MAC_LO_LBN 12
+#define FRF_CZ_TMFT_SRC_MAC_LO_LBN FRF_CZ_TMFT_SRC_MAC_LBN
#define FRF_CZ_TMFT_SRC_MAC_LO_WIDTH 32
-#define FRF_CZ_TMFT_SRC_MAC_HI_LBN 44
-#define FRF_CZ_TMFT_SRC_MAC_HI_WIDTH 16
+#define FRF_CZ_TMFT_SRC_MAC_HI_LBN (FRF_CZ_TMFT_SRC_MAC_LBN + 32)
+#define FRF_CZ_TMFT_SRC_MAC_HI_WIDTH (FRF_CZ_TMFT_SRC_MAC_WIDTH - 32)
/* TX_PACE_TBL */
/* Values >20 are documented as reserved, but will result in a queue going
@@ -2925,264 +2925,8 @@
#define FSF_AZ_DRV_GEN_EV_MAGIC_LBN 0
#define FSF_AZ_DRV_GEN_EV_MAGIC_WIDTH 32
-/**************************************************************************
- *
- * Falcon MAC stats
- *
- **************************************************************************
- *
- */
-
-#define GRxGoodOct_offset 0x0
-#define GRxGoodOct_WIDTH 48
-#define GRxBadOct_offset 0x8
-#define GRxBadOct_WIDTH 48
-#define GRxMissPkt_offset 0x10
-#define GRxMissPkt_WIDTH 32
-#define GRxFalseCRS_offset 0x14
-#define GRxFalseCRS_WIDTH 32
-#define GRxPausePkt_offset 0x18
-#define GRxPausePkt_WIDTH 32
-#define GRxBadPkt_offset 0x1C
-#define GRxBadPkt_WIDTH 32
-#define GRxUcastPkt_offset 0x20
-#define GRxUcastPkt_WIDTH 32
-#define GRxMcastPkt_offset 0x24
-#define GRxMcastPkt_WIDTH 32
-#define GRxBcastPkt_offset 0x28
-#define GRxBcastPkt_WIDTH 32
-#define GRxGoodLt64Pkt_offset 0x2C
-#define GRxGoodLt64Pkt_WIDTH 32
-#define GRxBadLt64Pkt_offset 0x30
-#define GRxBadLt64Pkt_WIDTH 32
-#define GRx64Pkt_offset 0x34
-#define GRx64Pkt_WIDTH 32
-#define GRx65to127Pkt_offset 0x38
-#define GRx65to127Pkt_WIDTH 32
-#define GRx128to255Pkt_offset 0x3C
-#define GRx128to255Pkt_WIDTH 32
-#define GRx256to511Pkt_offset 0x40
-#define GRx256to511Pkt_WIDTH 32
-#define GRx512to1023Pkt_offset 0x44
-#define GRx512to1023Pkt_WIDTH 32
-#define GRx1024to15xxPkt_offset 0x48
-#define GRx1024to15xxPkt_WIDTH 32
-#define GRx15xxtoJumboPkt_offset 0x4C
-#define GRx15xxtoJumboPkt_WIDTH 32
-#define GRxGtJumboPkt_offset 0x50
-#define GRxGtJumboPkt_WIDTH 32
-#define GRxFcsErr64to15xxPkt_offset 0x54
-#define GRxFcsErr64to15xxPkt_WIDTH 32
-#define GRxFcsErr15xxtoJumboPkt_offset 0x58
-#define GRxFcsErr15xxtoJumboPkt_WIDTH 32
-#define GRxFcsErrGtJumboPkt_offset 0x5C
-#define GRxFcsErrGtJumboPkt_WIDTH 32
-#define GTxGoodBadOct_offset 0x80
-#define GTxGoodBadOct_WIDTH 48
-#define GTxGoodOct_offset 0x88
-#define GTxGoodOct_WIDTH 48
-#define GTxSglColPkt_offset 0x90
-#define GTxSglColPkt_WIDTH 32
-#define GTxMultColPkt_offset 0x94
-#define GTxMultColPkt_WIDTH 32
-#define GTxExColPkt_offset 0x98
-#define GTxExColPkt_WIDTH 32
-#define GTxDefPkt_offset 0x9C
-#define GTxDefPkt_WIDTH 32
-#define GTxLateCol_offset 0xA0
-#define GTxLateCol_WIDTH 32
-#define GTxExDefPkt_offset 0xA4
-#define GTxExDefPkt_WIDTH 32
-#define GTxPausePkt_offset 0xA8
-#define GTxPausePkt_WIDTH 32
-#define GTxBadPkt_offset 0xAC
-#define GTxBadPkt_WIDTH 32
-#define GTxUcastPkt_offset 0xB0
-#define GTxUcastPkt_WIDTH 32
-#define GTxMcastPkt_offset 0xB4
-#define GTxMcastPkt_WIDTH 32
-#define GTxBcastPkt_offset 0xB8
-#define GTxBcastPkt_WIDTH 32
-#define GTxLt64Pkt_offset 0xBC
-#define GTxLt64Pkt_WIDTH 32
-#define GTx64Pkt_offset 0xC0
-#define GTx64Pkt_WIDTH 32
-#define GTx65to127Pkt_offset 0xC4
-#define GTx65to127Pkt_WIDTH 32
-#define GTx128to255Pkt_offset 0xC8
-#define GTx128to255Pkt_WIDTH 32
-#define GTx256to511Pkt_offset 0xCC
-#define GTx256to511Pkt_WIDTH 32
-#define GTx512to1023Pkt_offset 0xD0
-#define GTx512to1023Pkt_WIDTH 32
-#define GTx1024to15xxPkt_offset 0xD4
-#define GTx1024to15xxPkt_WIDTH 32
-#define GTx15xxtoJumboPkt_offset 0xD8
-#define GTx15xxtoJumboPkt_WIDTH 32
-#define GTxGtJumboPkt_offset 0xDC
-#define GTxGtJumboPkt_WIDTH 32
-#define GTxNonTcpUdpPkt_offset 0xE0
-#define GTxNonTcpUdpPkt_WIDTH 16
-#define GTxMacSrcErrPkt_offset 0xE4
-#define GTxMacSrcErrPkt_WIDTH 16
-#define GTxIpSrcErrPkt_offset 0xE8
-#define GTxIpSrcErrPkt_WIDTH 16
-#define GDmaDone_offset 0xEC
-#define GDmaDone_WIDTH 32
-
-#define XgRxOctets_offset 0x0
-#define XgRxOctets_WIDTH 48
-#define XgRxOctetsOK_offset 0x8
-#define XgRxOctetsOK_WIDTH 48
-#define XgRxPkts_offset 0x10
-#define XgRxPkts_WIDTH 32
-#define XgRxPktsOK_offset 0x14
-#define XgRxPktsOK_WIDTH 32
-#define XgRxBroadcastPkts_offset 0x18
-#define XgRxBroadcastPkts_WIDTH 32
-#define XgRxMulticastPkts_offset 0x1C
-#define XgRxMulticastPkts_WIDTH 32
-#define XgRxUnicastPkts_offset 0x20
-#define XgRxUnicastPkts_WIDTH 32
-#define XgRxUndersizePkts_offset 0x24
-#define XgRxUndersizePkts_WIDTH 32
-#define XgRxOversizePkts_offset 0x28
-#define XgRxOversizePkts_WIDTH 32
-#define XgRxJabberPkts_offset 0x2C
-#define XgRxJabberPkts_WIDTH 32
-#define XgRxUndersizeFCSerrorPkts_offset 0x30
-#define XgRxUndersizeFCSerrorPkts_WIDTH 32
-#define XgRxDropEvents_offset 0x34
-#define XgRxDropEvents_WIDTH 32
-#define XgRxFCSerrorPkts_offset 0x38
-#define XgRxFCSerrorPkts_WIDTH 32
-#define XgRxAlignError_offset 0x3C
-#define XgRxAlignError_WIDTH 32
-#define XgRxSymbolError_offset 0x40
-#define XgRxSymbolError_WIDTH 32
-#define XgRxInternalMACError_offset 0x44
-#define XgRxInternalMACError_WIDTH 32
-#define XgRxControlPkts_offset 0x48
-#define XgRxControlPkts_WIDTH 32
-#define XgRxPausePkts_offset 0x4C
-#define XgRxPausePkts_WIDTH 32
-#define XgRxPkts64Octets_offset 0x50
-#define XgRxPkts64Octets_WIDTH 32
-#define XgRxPkts65to127Octets_offset 0x54
-#define XgRxPkts65to127Octets_WIDTH 32
-#define XgRxPkts128to255Octets_offset 0x58
-#define XgRxPkts128to255Octets_WIDTH 32
-#define XgRxPkts256to511Octets_offset 0x5C
-#define XgRxPkts256to511Octets_WIDTH 32
-#define XgRxPkts512to1023Octets_offset 0x60
-#define XgRxPkts512to1023Octets_WIDTH 32
-#define XgRxPkts1024to15xxOctets_offset 0x64
-#define XgRxPkts1024to15xxOctets_WIDTH 32
-#define XgRxPkts15xxtoMaxOctets_offset 0x68
-#define XgRxPkts15xxtoMaxOctets_WIDTH 32
-#define XgRxLengthError_offset 0x6C
-#define XgRxLengthError_WIDTH 32
-#define XgTxPkts_offset 0x80
-#define XgTxPkts_WIDTH 32
-#define XgTxOctets_offset 0x88
-#define XgTxOctets_WIDTH 48
-#define XgTxMulticastPkts_offset 0x90
-#define XgTxMulticastPkts_WIDTH 32
-#define XgTxBroadcastPkts_offset 0x94
-#define XgTxBroadcastPkts_WIDTH 32
-#define XgTxUnicastPkts_offset 0x98
-#define XgTxUnicastPkts_WIDTH 32
-#define XgTxControlPkts_offset 0x9C
-#define XgTxControlPkts_WIDTH 32
-#define XgTxPausePkts_offset 0xA0
-#define XgTxPausePkts_WIDTH 32
-#define XgTxPkts64Octets_offset 0xA4
-#define XgTxPkts64Octets_WIDTH 32
-#define XgTxPkts65to127Octets_offset 0xA8
-#define XgTxPkts65to127Octets_WIDTH 32
-#define XgTxPkts128to255Octets_offset 0xAC
-#define XgTxPkts128to255Octets_WIDTH 32
-#define XgTxPkts256to511Octets_offset 0xB0
-#define XgTxPkts256to511Octets_WIDTH 32
-#define XgTxPkts512to1023Octets_offset 0xB4
-#define XgTxPkts512to1023Octets_WIDTH 32
-#define XgTxPkts1024to15xxOctets_offset 0xB8
-#define XgTxPkts1024to15xxOctets_WIDTH 32
-#define XgTxPkts1519toMaxOctets_offset 0xBC
-#define XgTxPkts1519toMaxOctets_WIDTH 32
-#define XgTxUndersizePkts_offset 0xC0
-#define XgTxUndersizePkts_WIDTH 32
-#define XgTxOversizePkts_offset 0xC4
-#define XgTxOversizePkts_WIDTH 32
-#define XgTxNonTcpUdpPkt_offset 0xC8
-#define XgTxNonTcpUdpPkt_WIDTH 16
-#define XgTxMacSrcErrPkt_offset 0xCC
-#define XgTxMacSrcErrPkt_WIDTH 16
-#define XgTxIpSrcErrPkt_offset 0xD0
-#define XgTxIpSrcErrPkt_WIDTH 16
-#define XgDmaDone_offset 0xD4
-#define XgDmaDone_WIDTH 32
-
-#define FALCON_STATS_NOT_DONE 0x00000000
-#define FALCON_STATS_DONE 0xffffffff
-
-/**************************************************************************
- *
- * Falcon non-volatile configuration
- *
- **************************************************************************
- */
+/* RX packet prefix */
+#define FS_BZ_RX_PREFIX_HASH_OFST 12
+#define FS_BZ_RX_PREFIX_SIZE 16
-/* Board configuration v2 (v1 is obsolete; later versions are compatible) */
-struct falcon_nvconfig_board_v2 {
- __le16 nports;
- u8 port0_phy_addr;
- u8 port0_phy_type;
- u8 port1_phy_addr;
- u8 port1_phy_type;
- __le16 asic_sub_revision;
- __le16 board_revision;
-} __packed;
-
-/* Board configuration v3 extra information */
-struct falcon_nvconfig_board_v3 {
- __le32 spi_device_type[2];
-} __packed;
-
-/* Bit numbers for spi_device_type */
-#define SPI_DEV_TYPE_SIZE_LBN 0
-#define SPI_DEV_TYPE_SIZE_WIDTH 5
-#define SPI_DEV_TYPE_ADDR_LEN_LBN 6
-#define SPI_DEV_TYPE_ADDR_LEN_WIDTH 2
-#define SPI_DEV_TYPE_ERASE_CMD_LBN 8
-#define SPI_DEV_TYPE_ERASE_CMD_WIDTH 8
-#define SPI_DEV_TYPE_ERASE_SIZE_LBN 16
-#define SPI_DEV_TYPE_ERASE_SIZE_WIDTH 5
-#define SPI_DEV_TYPE_BLOCK_SIZE_LBN 24
-#define SPI_DEV_TYPE_BLOCK_SIZE_WIDTH 5
-#define SPI_DEV_TYPE_FIELD(type, field) \
- (((type) >> EFX_LOW_BIT(field)) & EFX_MASK32(EFX_WIDTH(field)))
-
-#define FALCON_NVCONFIG_OFFSET 0x300
-
-#define FALCON_NVCONFIG_BOARD_MAGIC_NUM 0xFA1C
-struct falcon_nvconfig {
- efx_oword_t ee_vpd_cfg_reg; /* 0x300 */
- u8 mac_address[2][8]; /* 0x310 */
- efx_oword_t pcie_sd_ctl0123_reg; /* 0x320 */
- efx_oword_t pcie_sd_ctl45_reg; /* 0x330 */
- efx_oword_t pcie_pcs_ctl_stat_reg; /* 0x340 */
- efx_oword_t hw_init_reg; /* 0x350 */
- efx_oword_t nic_stat_reg; /* 0x360 */
- efx_oword_t glb_ctl_reg; /* 0x370 */
- efx_oword_t srm_cfg_reg; /* 0x380 */
- efx_oword_t spare_reg; /* 0x390 */
- __le16 board_magic_num; /* 0x3A0 */
- __le16 board_struct_ver;
- __le16 board_checksum;
- struct falcon_nvconfig_board_v2 board_v2;
- efx_oword_t ee_base_page_reg; /* 0x3B0 */
- struct falcon_nvconfig_board_v3 board_v3; /* 0x3C0 */
-} __packed;
-
-#endif /* EFX_REGS_H */
+#endif /* EFX_FARCH_REGS_H */
diff --git a/drivers/net/ethernet/sfc/filter.c b/drivers/net/ethernet/sfc/filter.c
deleted file mode 100644
index 1fbbbee7b1a..00000000000
--- a/drivers/net/ethernet/sfc/filter.c
+++ /dev/null
@@ -1,961 +0,0 @@
-/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2005-2010 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
- */
-
-#include <linux/in.h>
-#include <net/ip.h>
-#include "efx.h"
-#include "filter.h"
-#include "io.h"
-#include "nic.h"
-#include "regs.h"
-
-/* "Fudge factors" - difference between programmed value and actual depth.
- * Due to pipelined implementation we need to program H/W with a value that
- * is larger than the hop limit we want.
- */
-#define FILTER_CTL_SRCH_FUDGE_WILD 3
-#define FILTER_CTL_SRCH_FUDGE_FULL 1
-
-/* Hard maximum hop limit. Hardware will time-out beyond 200-something.
- * We also need to avoid infinite loops in efx_filter_search() when the
- * table is full.
- */
-#define FILTER_CTL_SRCH_MAX 200
-
-/* Don't try very hard to find space for performance hints, as this is
- * counter-productive. */
-#define FILTER_CTL_SRCH_HINT_MAX 5
-
-enum efx_filter_table_id {
- EFX_FILTER_TABLE_RX_IP = 0,
- EFX_FILTER_TABLE_RX_MAC,
- EFX_FILTER_TABLE_COUNT,
-};
-
-struct efx_filter_table {
- enum efx_filter_table_id id;
- u32 offset; /* address of table relative to BAR */
- unsigned size; /* number of entries */
- unsigned step; /* step between entries */
- unsigned used; /* number currently used */
- unsigned long *used_bitmap;
- struct efx_filter_spec *spec;
- unsigned search_depth[EFX_FILTER_TYPE_COUNT];
-};
-
-struct efx_filter_state {
- spinlock_t lock;
- struct efx_filter_table table[EFX_FILTER_TABLE_COUNT];
-#ifdef CONFIG_RFS_ACCEL
- u32 *rps_flow_id;
- unsigned rps_expire_index;
-#endif
-};
-
-/* The filter hash function is LFSR polynomial x^16 + x^3 + 1 of a 32-bit
- * key derived from the n-tuple. The initial LFSR state is 0xffff. */
-static u16 efx_filter_hash(u32 key)
-{
- u16 tmp;
-
- /* First 16 rounds */
- tmp = 0x1fff ^ key >> 16;
- tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
- tmp = tmp ^ tmp >> 9;
- /* Last 16 rounds */
- tmp = tmp ^ tmp << 13 ^ key;
- tmp = tmp ^ tmp >> 3 ^ tmp >> 6;
- return tmp ^ tmp >> 9;
-}
-
-/* To allow for hash collisions, filter search continues at these
- * increments from the first possible entry selected by the hash. */
-static u16 efx_filter_increment(u32 key)
-{
- return key * 2 - 1;
-}
-
-static enum efx_filter_table_id
-efx_filter_spec_table_id(const struct efx_filter_spec *spec)
-{
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_TCP_FULL >> 2));
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_TCP_WILD >> 2));
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_UDP_FULL >> 2));
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_IP != (EFX_FILTER_UDP_WILD >> 2));
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_MAC != (EFX_FILTER_MAC_FULL >> 2));
- BUILD_BUG_ON(EFX_FILTER_TABLE_RX_MAC != (EFX_FILTER_MAC_WILD >> 2));
- EFX_BUG_ON_PARANOID(spec->type == EFX_FILTER_UNSPEC);
- return spec->type >> 2;
-}
-
-static struct efx_filter_table *
-efx_filter_spec_table(struct efx_filter_state *state,
- const struct efx_filter_spec *spec)
-{
- if (spec->type == EFX_FILTER_UNSPEC)
- return NULL;
- else
- return &state->table[efx_filter_spec_table_id(spec)];
-}
-
-static void efx_filter_table_reset_search_depth(struct efx_filter_table *table)
-{
- memset(table->search_depth, 0, sizeof(table->search_depth));
-}
-
-static void efx_filter_push_rx_limits(struct efx_nic *efx)
-{
- struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_table *table;
- efx_oword_t filter_ctl;
-
- efx_reado(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
-
- table = &state->table[EFX_FILTER_TABLE_RX_IP];
- EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_FULL_SRCH_LIMIT,
- table->search_depth[EFX_FILTER_TCP_FULL] +
- FILTER_CTL_SRCH_FUDGE_FULL);
- EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_TCP_WILD_SRCH_LIMIT,
- table->search_depth[EFX_FILTER_TCP_WILD] +
- FILTER_CTL_SRCH_FUDGE_WILD);
- EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_FULL_SRCH_LIMIT,
- table->search_depth[EFX_FILTER_UDP_FULL] +
- FILTER_CTL_SRCH_FUDGE_FULL);
- EFX_SET_OWORD_FIELD(filter_ctl, FRF_BZ_UDP_WILD_SRCH_LIMIT,
- table->search_depth[EFX_FILTER_UDP_WILD] +
- FILTER_CTL_SRCH_FUDGE_WILD);
-
- table = &state->table[EFX_FILTER_TABLE_RX_MAC];
- if (table->size) {
- EFX_SET_OWORD_FIELD(
- filter_ctl, FRF_CZ_ETHERNET_FULL_SEARCH_LIMIT,
- table->search_depth[EFX_FILTER_MAC_FULL] +
- FILTER_CTL_SRCH_FUDGE_FULL);
- EFX_SET_OWORD_FIELD(
- filter_ctl, FRF_CZ_ETHERNET_WILDCARD_SEARCH_LIMIT,
- table->search_depth[EFX_FILTER_MAC_WILD] +
- FILTER_CTL_SRCH_FUDGE_WILD);
- }
-
- efx_writeo(efx, &filter_ctl, FR_BZ_RX_FILTER_CTL);
-}
-
-static inline void __efx_filter_set_ipv4(struct efx_filter_spec *spec,
- __be32 host1, __be16 port1,
- __be32 host2, __be16 port2)
-{
- spec->data[0] = ntohl(host1) << 16 | ntohs(port1);
- spec->data[1] = ntohs(port2) << 16 | ntohl(host1) >> 16;
- spec->data[2] = ntohl(host2);
-}
-
-static inline void __efx_filter_get_ipv4(const struct efx_filter_spec *spec,
- __be32 *host1, __be16 *port1,
- __be32 *host2, __be16 *port2)
-{
- *host1 = htonl(spec->data[0] >> 16 | spec->data[1] << 16);
- *port1 = htons(spec->data[0]);
- *host2 = htonl(spec->data[2]);
- *port2 = htons(spec->data[1] >> 16);
-}
-
-/**
- * efx_filter_set_ipv4_local - specify IPv4 host, transport protocol and port
- * @spec: Specification to initialise
- * @proto: Transport layer protocol number
- * @host: Local host address (network byte order)
- * @port: Local port (network byte order)
- */
-int efx_filter_set_ipv4_local(struct efx_filter_spec *spec, u8 proto,
- __be32 host, __be16 port)
-{
- __be32 host1;
- __be16 port1;
-
- EFX_BUG_ON_PARANOID(!(spec->flags & EFX_FILTER_FLAG_RX));
-
- /* This cannot currently be combined with other filtering */
- if (spec->type != EFX_FILTER_UNSPEC)
- return -EPROTONOSUPPORT;
-
- if (port == 0)
- return -EINVAL;
-
- switch (proto) {
- case IPPROTO_TCP:
- spec->type = EFX_FILTER_TCP_WILD;
- break;
- case IPPROTO_UDP:
- spec->type = EFX_FILTER_UDP_WILD;
- break;
- default:
- return -EPROTONOSUPPORT;
- }
-
- /* Filter is constructed in terms of source and destination,
- * with the odd wrinkle that the ports are swapped in a UDP
- * wildcard filter. We need to convert from local and remote
- * (= zero for wildcard) addresses.
- */
- host1 = 0;
- if (proto != IPPROTO_UDP) {
- port1 = 0;
- } else {
- port1 = port;
- port = 0;
- }
-
- __efx_filter_set_ipv4(spec, host1, port1, host, port);
- return 0;
-}
-
-int efx_filter_get_ipv4_local(const struct efx_filter_spec *spec,
- u8 *proto, __be32 *host, __be16 *port)
-{
- __be32 host1;
- __be16 port1;
-
- switch (spec->type) {
- case EFX_FILTER_TCP_WILD:
- *proto = IPPROTO_TCP;
- __efx_filter_get_ipv4(spec, &host1, &port1, host, port);
- return 0;
- case EFX_FILTER_UDP_WILD:
- *proto = IPPROTO_UDP;
- __efx_filter_get_ipv4(spec, &host1, port, host, &port1);
- return 0;
- default:
- return -EINVAL;
- }
-}
-
-/**
- * efx_filter_set_ipv4_full - specify IPv4 hosts, transport protocol and ports
- * @spec: Specification to initialise
- * @proto: Transport layer protocol number
- * @host: Local host address (network byte order)
- * @port: Local port (network byte order)
- * @rhost: Remote host address (network byte order)
- * @rport: Remote port (network byte order)
- */
-int efx_filter_set_ipv4_full(struct efx_filter_spec *spec, u8 proto,
- __be32 host, __be16 port,
- __be32 rhost, __be16 rport)
-{
- EFX_BUG_ON_PARANOID(!(spec->flags & EFX_FILTER_FLAG_RX));
-
- /* This cannot currently be combined with other filtering */
- if (spec->type != EFX_FILTER_UNSPEC)
- return -EPROTONOSUPPORT;
-
- if (port == 0 || rport == 0)
- return -EINVAL;
-
- switch (proto) {
- case IPPROTO_TCP:
- spec->type = EFX_FILTER_TCP_FULL;
- break;
- case IPPROTO_UDP:
- spec->type = EFX_FILTER_UDP_FULL;
- break;
- default:
- return -EPROTONOSUPPORT;
- }
-
- __efx_filter_set_ipv4(spec, rhost, rport, host, port);
- return 0;
-}
-
-int efx_filter_get_ipv4_full(const struct efx_filter_spec *spec,
- u8 *proto, __be32 *host, __be16 *port,
- __be32 *rhost, __be16 *rport)
-{
- switch (spec->type) {
- case EFX_FILTER_TCP_FULL:
- *proto = IPPROTO_TCP;
- break;
- case EFX_FILTER_UDP_FULL:
- *proto = IPPROTO_UDP;
- break;
- default:
- return -EINVAL;
- }
-
- __efx_filter_get_ipv4(spec, rhost, rport, host, port);
- return 0;
-}
-
-/**
- * efx_filter_set_eth_local - specify local Ethernet address and optional VID
- * @spec: Specification to initialise
- * @vid: VLAN ID to match, or %EFX_FILTER_VID_UNSPEC
- * @addr: Local Ethernet MAC address
- */
-int efx_filter_set_eth_local(struct efx_filter_spec *spec,
- u16 vid, const u8 *addr)
-{
- EFX_BUG_ON_PARANOID(!(spec->flags & EFX_FILTER_FLAG_RX));
-
- /* This cannot currently be combined with other filtering */
- if (spec->type != EFX_FILTER_UNSPEC)
- return -EPROTONOSUPPORT;
-
- if (vid == EFX_FILTER_VID_UNSPEC) {
- spec->type = EFX_FILTER_MAC_WILD;
- spec->data[0] = 0;
- } else {
- spec->type = EFX_FILTER_MAC_FULL;
- spec->data[0] = vid;
- }
-
- spec->data[1] = addr[2] << 24 | addr[3] << 16 | addr[4] << 8 | addr[5];
- spec->data[2] = addr[0] << 8 | addr[1];
- return 0;
-}
-
-int efx_filter_get_eth_local(const struct efx_filter_spec *spec,
- u16 *vid, u8 *addr)
-{
- switch (spec->type) {
- case EFX_FILTER_MAC_WILD:
- *vid = EFX_FILTER_VID_UNSPEC;
- break;
- case EFX_FILTER_MAC_FULL:
- *vid = spec->data[0];
- break;
- default:
- return -EINVAL;
- }
-
- addr[0] = spec->data[2] >> 8;
- addr[1] = spec->data[2];
- addr[2] = spec->data[1] >> 24;
- addr[3] = spec->data[1] >> 16;
- addr[4] = spec->data[1] >> 8;
- addr[5] = spec->data[1];
- return 0;
-}
-
-/* Build a filter entry and return its n-tuple key. */
-static u32 efx_filter_build(efx_oword_t *filter, struct efx_filter_spec *spec)
-{
- u32 data3;
-
- switch (efx_filter_spec_table_id(spec)) {
- case EFX_FILTER_TABLE_RX_IP: {
- bool is_udp = (spec->type == EFX_FILTER_UDP_FULL ||
- spec->type == EFX_FILTER_UDP_WILD);
- EFX_POPULATE_OWORD_7(
- *filter,
- FRF_BZ_RSS_EN,
- !!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
- FRF_BZ_SCATTER_EN,
- !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
- FRF_BZ_TCP_UDP, is_udp,
- FRF_BZ_RXQ_ID, spec->dmaq_id,
- EFX_DWORD_2, spec->data[2],
- EFX_DWORD_1, spec->data[1],
- EFX_DWORD_0, spec->data[0]);
- data3 = is_udp;
- break;
- }
-
- case EFX_FILTER_TABLE_RX_MAC: {
- bool is_wild = spec->type == EFX_FILTER_MAC_WILD;
- EFX_POPULATE_OWORD_8(
- *filter,
- FRF_CZ_RMFT_RSS_EN,
- !!(spec->flags & EFX_FILTER_FLAG_RX_RSS),
- FRF_CZ_RMFT_SCATTER_EN,
- !!(spec->flags & EFX_FILTER_FLAG_RX_SCATTER),
- FRF_CZ_RMFT_IP_OVERRIDE,
- !!(spec->flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP),
- FRF_CZ_RMFT_RXQ_ID, spec->dmaq_id,
- FRF_CZ_RMFT_WILDCARD_MATCH, is_wild,
- FRF_CZ_RMFT_DEST_MAC_HI, spec->data[2],
- FRF_CZ_RMFT_DEST_MAC_LO, spec->data[1],
- FRF_CZ_RMFT_VLAN_ID, spec->data[0]);
- data3 = is_wild;
- break;
- }
-
- default:
- BUG();
- }
-
- return spec->data[0] ^ spec->data[1] ^ spec->data[2] ^ data3;
-}
-
-static bool efx_filter_equal(const struct efx_filter_spec *left,
- const struct efx_filter_spec *right)
-{
- if (left->type != right->type ||
- memcmp(left->data, right->data, sizeof(left->data)))
- return false;
-
- return true;
-}
-
-static int efx_filter_search(struct efx_filter_table *table,
- struct efx_filter_spec *spec, u32 key,
- bool for_insert, unsigned int *depth_required)
-{
- unsigned hash, incr, filter_idx, depth, depth_max;
-
- hash = efx_filter_hash(key);
- incr = efx_filter_increment(key);
-
- filter_idx = hash & (table->size - 1);
- depth = 1;
- depth_max = (for_insert ?
- (spec->priority <= EFX_FILTER_PRI_HINT ?
- FILTER_CTL_SRCH_HINT_MAX : FILTER_CTL_SRCH_MAX) :
- table->search_depth[spec->type]);
-
- for (;;) {
- /* Return success if entry is used and matches this spec
- * or entry is unused and we are trying to insert.
- */
- if (test_bit(filter_idx, table->used_bitmap) ?
- efx_filter_equal(spec, &table->spec[filter_idx]) :
- for_insert) {
- *depth_required = depth;
- return filter_idx;
- }
-
- /* Return failure if we reached the maximum search depth */
- if (depth == depth_max)
- return for_insert ? -EBUSY : -ENOENT;
-
- filter_idx = (filter_idx + incr) & (table->size - 1);
- ++depth;
- }
-}
-
-/*
- * Construct/deconstruct external filter IDs. These must be ordered
- * by matching priority, for RX NFC semantics.
- *
- * Each RX MAC filter entry has a flag for whether it can override an
- * RX IP filter that also matches. So we assign locations for MAC
- * filters with overriding behaviour, then for IP filters, then for
- * MAC filters without overriding behaviour.
- */
-
-#define EFX_FILTER_INDEX_WIDTH 13
-#define EFX_FILTER_INDEX_MASK ((1 << EFX_FILTER_INDEX_WIDTH) - 1)
-
-static inline u32 efx_filter_make_id(enum efx_filter_table_id table_id,
- unsigned int index, u8 flags)
-{
- return (table_id == EFX_FILTER_TABLE_RX_MAC &&
- flags & EFX_FILTER_FLAG_RX_OVERRIDE_IP) ?
- index :
- (table_id + 1) << EFX_FILTER_INDEX_WIDTH | index;
-}
-
-static inline enum efx_filter_table_id efx_filter_id_table_id(u32 id)
-{
- return (id <= EFX_FILTER_INDEX_MASK) ?
- EFX_FILTER_TABLE_RX_MAC :
- (id >> EFX_FILTER_INDEX_WIDTH) - 1;
-}
-
-static inline unsigned int efx_filter_id_index(u32 id)
-{
- return id & EFX_FILTER_INDEX_MASK;
-}
-
-static inline u8 efx_filter_id_flags(u32 id)
-{
- return (id <= EFX_FILTER_INDEX_MASK) ?
- EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_OVERRIDE_IP :
- EFX_FILTER_FLAG_RX;
-}
-
-u32 efx_filter_get_rx_id_limit(struct efx_nic *efx)
-{
- struct efx_filter_state *state = efx->filter_state;
-
- if (state->table[EFX_FILTER_TABLE_RX_MAC].size != 0)
- return ((EFX_FILTER_TABLE_RX_MAC + 1) << EFX_FILTER_INDEX_WIDTH)
- + state->table[EFX_FILTER_TABLE_RX_MAC].size;
- else if (state->table[EFX_FILTER_TABLE_RX_IP].size != 0)
- return ((EFX_FILTER_TABLE_RX_IP + 1) << EFX_FILTER_INDEX_WIDTH)
- + state->table[EFX_FILTER_TABLE_RX_IP].size;
- else
- return 0;
-}
-
-/**
- * efx_filter_insert_filter - add or replace a filter
- * @efx: NIC in which to insert the filter
- * @spec: Specification for the filter
- * @replace: Flag for whether the specified filter may replace a filter
- * with an identical match expression and equal or lower priority
- *
- * On success, return the filter ID.
- * On failure, return a negative error code.
- */
-s32 efx_filter_insert_filter(struct efx_nic *efx, struct efx_filter_spec *spec,
- bool replace)
-{
- struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_table *table = efx_filter_spec_table(state, spec);
- struct efx_filter_spec *saved_spec;
- efx_oword_t filter;
- unsigned int filter_idx, depth;
- u32 key;
- int rc;
-
- if (!table || table->size == 0)
- return -EINVAL;
-
- key = efx_filter_build(&filter, spec);
-
- netif_vdbg(efx, hw, efx->net_dev,
- "%s: type %d search_depth=%d", __func__, spec->type,
- table->search_depth[spec->type]);
-
- spin_lock_bh(&state->lock);
-
- rc = efx_filter_search(table, spec, key, true, &depth);
- if (rc < 0)
- goto out;
- filter_idx = rc;
- BUG_ON(filter_idx >= table->size);
- saved_spec = &table->spec[filter_idx];
-
- if (test_bit(filter_idx, table->used_bitmap)) {
- /* Should we replace the existing filter? */
- if (!replace) {
- rc = -EEXIST;
- goto out;
- }
- if (spec->priority < saved_spec->priority) {
- rc = -EPERM;
- goto out;
- }
- } else {
- __set_bit(filter_idx, table->used_bitmap);
- ++table->used;
- }
- *saved_spec = *spec;
-
- if (table->search_depth[spec->type] < depth) {
- table->search_depth[spec->type] = depth;
- efx_filter_push_rx_limits(efx);
- }
-
- efx_writeo(efx, &filter, table->offset + table->step * filter_idx);
-
- netif_vdbg(efx, hw, efx->net_dev,
- "%s: filter type %d index %d rxq %u set",
- __func__, spec->type, filter_idx, spec->dmaq_id);
- rc = efx_filter_make_id(table->id, filter_idx, spec->flags);
-
-out:
- spin_unlock_bh(&state->lock);
- return rc;
-}
-
-static void efx_filter_table_clear_entry(struct efx_nic *efx,
- struct efx_filter_table *table,
- unsigned int filter_idx)
-{
- static efx_oword_t filter;
-
- if (test_bit(filter_idx, table->used_bitmap)) {
- __clear_bit(filter_idx, table->used_bitmap);
- --table->used;
- memset(&table->spec[filter_idx], 0, sizeof(table->spec[0]));
-
- efx_writeo(efx, &filter,
- table->offset + table->step * filter_idx);
- }
-}
-
-/**
- * efx_filter_remove_id_safe - remove a filter by ID, carefully
- * @efx: NIC from which to remove the filter
- * @priority: Priority of filter, as passed to @efx_filter_insert_filter
- * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
- *
- * This function will range-check @filter_id, so it is safe to call
- * with a value passed from userland.
- */
-int efx_filter_remove_id_safe(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 filter_id)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
- struct efx_filter_table *table;
- unsigned int filter_idx;
- struct efx_filter_spec *spec;
- u8 filter_flags;
- int rc;
-
- table_id = efx_filter_id_table_id(filter_id);
- if ((unsigned int)table_id >= EFX_FILTER_TABLE_COUNT)
- return -ENOENT;
- table = &state->table[table_id];
-
- filter_idx = efx_filter_id_index(filter_id);
- if (filter_idx >= table->size)
- return -ENOENT;
- spec = &table->spec[filter_idx];
-
- filter_flags = efx_filter_id_flags(filter_id);
-
- spin_lock_bh(&state->lock);
-
- if (test_bit(filter_idx, table->used_bitmap) &&
- spec->priority == priority && spec->flags == filter_flags) {
- efx_filter_table_clear_entry(efx, table, filter_idx);
- if (table->used == 0)
- efx_filter_table_reset_search_depth(table);
- rc = 0;
- } else {
- rc = -ENOENT;
- }
-
- spin_unlock_bh(&state->lock);
-
- return rc;
-}
-
-/**
- * efx_filter_get_filter_safe - retrieve a filter by ID, carefully
- * @efx: NIC from which to remove the filter
- * @priority: Priority of filter, as passed to @efx_filter_insert_filter
- * @filter_id: ID of filter, as returned by @efx_filter_insert_filter
- * @spec: Buffer in which to store filter specification
- *
- * This function will range-check @filter_id, so it is safe to call
- * with a value passed from userland.
- */
-int efx_filter_get_filter_safe(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 filter_id, struct efx_filter_spec *spec_buf)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
- struct efx_filter_table *table;
- struct efx_filter_spec *spec;
- unsigned int filter_idx;
- u8 filter_flags;
- int rc;
-
- table_id = efx_filter_id_table_id(filter_id);
- if ((unsigned int)table_id >= EFX_FILTER_TABLE_COUNT)
- return -ENOENT;
- table = &state->table[table_id];
-
- filter_idx = efx_filter_id_index(filter_id);
- if (filter_idx >= table->size)
- return -ENOENT;
- spec = &table->spec[filter_idx];
-
- filter_flags = efx_filter_id_flags(filter_id);
-
- spin_lock_bh(&state->lock);
-
- if (test_bit(filter_idx, table->used_bitmap) &&
- spec->priority == priority && spec->flags == filter_flags) {
- *spec_buf = *spec;
- rc = 0;
- } else {
- rc = -ENOENT;
- }
-
- spin_unlock_bh(&state->lock);
-
- return rc;
-}
-
-static void efx_filter_table_clear(struct efx_nic *efx,
- enum efx_filter_table_id table_id,
- enum efx_filter_priority priority)
-{
- struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_table *table = &state->table[table_id];
- unsigned int filter_idx;
-
- spin_lock_bh(&state->lock);
-
- for (filter_idx = 0; filter_idx < table->size; ++filter_idx)
- if (table->spec[filter_idx].priority <= priority)
- efx_filter_table_clear_entry(efx, table, filter_idx);
- if (table->used == 0)
- efx_filter_table_reset_search_depth(table);
-
- spin_unlock_bh(&state->lock);
-}
-
-/**
- * efx_filter_clear_rx - remove RX filters by priority
- * @efx: NIC from which to remove the filters
- * @priority: Maximum priority to remove
- */
-void efx_filter_clear_rx(struct efx_nic *efx, enum efx_filter_priority priority)
-{
- efx_filter_table_clear(efx, EFX_FILTER_TABLE_RX_IP, priority);
- efx_filter_table_clear(efx, EFX_FILTER_TABLE_RX_MAC, priority);
-}
-
-u32 efx_filter_count_rx_used(struct efx_nic *efx,
- enum efx_filter_priority priority)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
- struct efx_filter_table *table;
- unsigned int filter_idx;
- u32 count = 0;
-
- spin_lock_bh(&state->lock);
-
- for (table_id = EFX_FILTER_TABLE_RX_IP;
- table_id <= EFX_FILTER_TABLE_RX_MAC;
- table_id++) {
- table = &state->table[table_id];
- for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
- if (test_bit(filter_idx, table->used_bitmap) &&
- table->spec[filter_idx].priority == priority)
- ++count;
- }
- }
-
- spin_unlock_bh(&state->lock);
-
- return count;
-}
-
-s32 efx_filter_get_rx_ids(struct efx_nic *efx,
- enum efx_filter_priority priority,
- u32 *buf, u32 size)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
- struct efx_filter_table *table;
- unsigned int filter_idx;
- s32 count = 0;
-
- spin_lock_bh(&state->lock);
-
- for (table_id = EFX_FILTER_TABLE_RX_IP;
- table_id <= EFX_FILTER_TABLE_RX_MAC;
- table_id++) {
- table = &state->table[table_id];
- for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
- if (test_bit(filter_idx, table->used_bitmap) &&
- table->spec[filter_idx].priority == priority) {
- if (count == size) {
- count = -EMSGSIZE;
- goto out;
- }
- buf[count++] = efx_filter_make_id(
- table_id, filter_idx,
- table->spec[filter_idx].flags);
- }
- }
- }
-out:
- spin_unlock_bh(&state->lock);
-
- return count;
-}
-
-/* Restore filter stater after reset */
-void efx_restore_filters(struct efx_nic *efx)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
- struct efx_filter_table *table;
- efx_oword_t filter;
- unsigned int filter_idx;
-
- spin_lock_bh(&state->lock);
-
- for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) {
- table = &state->table[table_id];
- for (filter_idx = 0; filter_idx < table->size; filter_idx++) {
- if (!test_bit(filter_idx, table->used_bitmap))
- continue;
- efx_filter_build(&filter, &table->spec[filter_idx]);
- efx_writeo(efx, &filter,
- table->offset + table->step * filter_idx);
- }
- }
-
- efx_filter_push_rx_limits(efx);
-
- spin_unlock_bh(&state->lock);
-}
-
-int efx_probe_filters(struct efx_nic *efx)
-{
- struct efx_filter_state *state;
- struct efx_filter_table *table;
- unsigned table_id;
-
- state = kzalloc(sizeof(*efx->filter_state), GFP_KERNEL);
- if (!state)
- return -ENOMEM;
- efx->filter_state = state;
-
- spin_lock_init(&state->lock);
-
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
-#ifdef CONFIG_RFS_ACCEL
- state->rps_flow_id = kcalloc(FR_BZ_RX_FILTER_TBL0_ROWS,
- sizeof(*state->rps_flow_id),
- GFP_KERNEL);
- if (!state->rps_flow_id)
- goto fail;
-#endif
- table = &state->table[EFX_FILTER_TABLE_RX_IP];
- table->id = EFX_FILTER_TABLE_RX_IP;
- table->offset = FR_BZ_RX_FILTER_TBL0;
- table->size = FR_BZ_RX_FILTER_TBL0_ROWS;
- table->step = FR_BZ_RX_FILTER_TBL0_STEP;
- }
-
- if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) {
- table = &state->table[EFX_FILTER_TABLE_RX_MAC];
- table->id = EFX_FILTER_TABLE_RX_MAC;
- table->offset = FR_CZ_RX_MAC_FILTER_TBL0;
- table->size = FR_CZ_RX_MAC_FILTER_TBL0_ROWS;
- table->step = FR_CZ_RX_MAC_FILTER_TBL0_STEP;
- }
-
- for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) {
- table = &state->table[table_id];
- if (table->size == 0)
- continue;
- table->used_bitmap = kcalloc(BITS_TO_LONGS(table->size),
- sizeof(unsigned long),
- GFP_KERNEL);
- if (!table->used_bitmap)
- goto fail;
- table->spec = vzalloc(table->size * sizeof(*table->spec));
- if (!table->spec)
- goto fail;
- }
-
- return 0;
-
-fail:
- efx_remove_filters(efx);
- return -ENOMEM;
-}
-
-void efx_remove_filters(struct efx_nic *efx)
-{
- struct efx_filter_state *state = efx->filter_state;
- enum efx_filter_table_id table_id;
-
- for (table_id = 0; table_id < EFX_FILTER_TABLE_COUNT; table_id++) {
- kfree(state->table[table_id].used_bitmap);
- vfree(state->table[table_id].spec);
- }
-#ifdef CONFIG_RFS_ACCEL
- kfree(state->rps_flow_id);
-#endif
- kfree(state);
-}
-
-#ifdef CONFIG_RFS_ACCEL
-
-int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
- u16 rxq_index, u32 flow_id)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- struct efx_channel *channel;
- struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_spec spec;
- const struct iphdr *ip;
- const __be16 *ports;
- int nhoff;
- int rc;
-
- nhoff = skb_network_offset(skb);
-
- if (skb->protocol != htons(ETH_P_IP))
- return -EPROTONOSUPPORT;
-
- /* RFS must validate the IP header length before calling us */
- EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));
- ip = (const struct iphdr *)(skb->data + nhoff);
- if (ip_is_fragment(ip))
- return -EPROTONOSUPPORT;
- EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
- ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
-
- efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT, 0, rxq_index);
- rc = efx_filter_set_ipv4_full(&spec, ip->protocol,
- ip->daddr, ports[1], ip->saddr, ports[0]);
- if (rc)
- return rc;
-
- rc = efx_filter_insert_filter(efx, &spec, true);
- if (rc < 0)
- return rc;
-
- /* Remember this so we can check whether to expire the filter later */
- state->rps_flow_id[rc] = flow_id;
- channel = efx_get_channel(efx, skb_get_rx_queue(skb));
- ++channel->rfs_filters_added;
-
- netif_info(efx, rx_status, efx->net_dev,
- "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
- (ip->protocol == IPPROTO_TCP) ? "TCP" : "UDP",
- &ip->saddr, ntohs(ports[0]), &ip->daddr, ntohs(ports[1]),
- rxq_index, flow_id, rc);
-
- return rc;
-}
-
-bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota)
-{
- struct efx_filter_state *state = efx->filter_state;
- struct efx_filter_table *table = &state->table[EFX_FILTER_TABLE_RX_IP];
- unsigned mask = table->size - 1;
- unsigned index;
- unsigned stop;
-
- if (!spin_trylock_bh(&state->lock))
- return false;
-
- index = state->rps_expire_index;
- stop = (index + quota) & mask;
-
- while (index != stop) {
- if (test_bit(index, table->used_bitmap) &&
- table->spec[index].priority == EFX_FILTER_PRI_HINT &&
- rps_may_expire_flow(efx->net_dev,
- table->spec[index].dmaq_id,
- state->rps_flow_id[index], index)) {
- netif_info(efx, rx_status, efx->net_dev,
- "expiring filter %d [flow %u]\n",
- index, state->rps_flow_id[index]);
- efx_filter_table_clear_entry(efx, table, index);
- }
- index = (index + 1) & mask;
- }
-
- state->rps_expire_index = stop;
- if (table->used == 0)
- efx_filter_table_reset_search_depth(table);
-
- spin_unlock_bh(&state->lock);
- return true;
-}
-
-#endif /* CONFIG_RFS_ACCEL */
diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h
index 3d4108cd90c..d0ed7f71ea7 100644
--- a/drivers/net/ethernet/sfc/filter.h
+++ b/drivers/net/ethernet/sfc/filter.h
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2005-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2005-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -11,38 +11,64 @@
#define EFX_FILTER_H
#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <asm/byteorder.h>
/**
- * enum efx_filter_type - type of hardware filter
- * @EFX_FILTER_TCP_FULL: Matching TCP/IPv4 4-tuple
- * @EFX_FILTER_TCP_WILD: Matching TCP/IPv4 destination (host, port)
- * @EFX_FILTER_UDP_FULL: Matching UDP/IPv4 4-tuple
- * @EFX_FILTER_UDP_WILD: Matching UDP/IPv4 destination (host, port)
- * @EFX_FILTER_MAC_FULL: Matching Ethernet destination MAC address, VID
- * @EFX_FILTER_MAC_WILD: Matching Ethernet destination MAC address
- * @EFX_FILTER_UNSPEC: Match type is unspecified
+ * enum efx_filter_match_flags - Flags for hardware filter match type
+ * @EFX_FILTER_MATCH_REM_HOST: Match by remote IP host address
+ * @EFX_FILTER_MATCH_LOC_HOST: Match by local IP host address
+ * @EFX_FILTER_MATCH_REM_MAC: Match by remote MAC address
+ * @EFX_FILTER_MATCH_REM_PORT: Match by remote TCP/UDP port
+ * @EFX_FILTER_MATCH_LOC_MAC: Match by local MAC address
+ * @EFX_FILTER_MATCH_LOC_PORT: Match by local TCP/UDP port
+ * @EFX_FILTER_MATCH_ETHER_TYPE: Match by Ether-type
+ * @EFX_FILTER_MATCH_INNER_VID: Match by inner VLAN ID
+ * @EFX_FILTER_MATCH_OUTER_VID: Match by outer VLAN ID
+ * @EFX_FILTER_MATCH_IP_PROTO: Match by IP transport protocol
+ * @EFX_FILTER_MATCH_LOC_MAC_IG: Match by local MAC address I/G bit.
+ * Used for RX default unicast and multicast/broadcast filters.
*
- * Falcon NICs only support the TCP/IPv4 and UDP/IPv4 filter types.
+ * Only some combinations are supported, depending on NIC type:
+ *
+ * - Falcon supports RX filters matching by {TCP,UDP}/IPv4 4-tuple or
+ * local 2-tuple (only implemented for Falcon B0)
+ *
+ * - Siena supports RX and TX filters matching by {TCP,UDP}/IPv4 4-tuple
+ * or local 2-tuple, or local MAC with or without outer VID, and RX
+ * default filters
+ *
+ * - Huntington supports filter matching controlled by firmware, potentially
+ * using {TCP,UDP}/IPv{4,6} 4-tuple or local 2-tuple, local MAC or I/G bit,
+ * with or without outer and inner VID
*/
-enum efx_filter_type {
- EFX_FILTER_TCP_FULL = 0,
- EFX_FILTER_TCP_WILD,
- EFX_FILTER_UDP_FULL,
- EFX_FILTER_UDP_WILD,
- EFX_FILTER_MAC_FULL = 4,
- EFX_FILTER_MAC_WILD,
- EFX_FILTER_TYPE_COUNT, /* number of specific types */
- EFX_FILTER_UNSPEC = 0xf,
+enum efx_filter_match_flags {
+ EFX_FILTER_MATCH_REM_HOST = 0x0001,
+ EFX_FILTER_MATCH_LOC_HOST = 0x0002,
+ EFX_FILTER_MATCH_REM_MAC = 0x0004,
+ EFX_FILTER_MATCH_REM_PORT = 0x0008,
+ EFX_FILTER_MATCH_LOC_MAC = 0x0010,
+ EFX_FILTER_MATCH_LOC_PORT = 0x0020,
+ EFX_FILTER_MATCH_ETHER_TYPE = 0x0040,
+ EFX_FILTER_MATCH_INNER_VID = 0x0080,
+ EFX_FILTER_MATCH_OUTER_VID = 0x0100,
+ EFX_FILTER_MATCH_IP_PROTO = 0x0200,
+ EFX_FILTER_MATCH_LOC_MAC_IG = 0x0400,
};
/**
* enum efx_filter_priority - priority of a hardware filter specification
* @EFX_FILTER_PRI_HINT: Performance hint
+ * @EFX_FILTER_PRI_AUTO: Automatic filter based on device address list
+ * or hardware requirements. This may only be used by the filter
+ * implementation for each NIC type.
* @EFX_FILTER_PRI_MANUAL: Manually configured filter
- * @EFX_FILTER_PRI_REQUIRED: Required for correct behaviour
+ * @EFX_FILTER_PRI_REQUIRED: Required for correct behaviour (user-level
+ * networking and SR-IOV)
*/
enum efx_filter_priority {
EFX_FILTER_PRI_HINT = 0,
+ EFX_FILTER_PRI_AUTO,
EFX_FILTER_PRI_MANUAL,
EFX_FILTER_PRI_REQUIRED,
};
@@ -56,40 +82,74 @@ enum efx_filter_priority {
* according to the indirection table.
* @EFX_FILTER_FLAG_RX_SCATTER: Enable DMA scatter on the receiving
* queue.
- * @EFX_FILTER_FLAG_RX_OVERRIDE_IP: Enables a MAC filter to override
- * any IP filter that matches the same packet. By default, IP
- * filters take precedence.
+ * @EFX_FILTER_FLAG_RX_OVER_AUTO: Indicates a filter that is
+ * overriding an automatic filter (priority
+ * %EFX_FILTER_PRI_AUTO). This may only be set by the filter
+ * implementation for each type. A removal request will restore
+ * the automatic filter in its place.
* @EFX_FILTER_FLAG_RX: Filter is for RX
+ * @EFX_FILTER_FLAG_TX: Filter is for TX
*/
enum efx_filter_flags {
EFX_FILTER_FLAG_RX_RSS = 0x01,
EFX_FILTER_FLAG_RX_SCATTER = 0x02,
- EFX_FILTER_FLAG_RX_OVERRIDE_IP = 0x04,
+ EFX_FILTER_FLAG_RX_OVER_AUTO = 0x04,
EFX_FILTER_FLAG_RX = 0x08,
+ EFX_FILTER_FLAG_TX = 0x10,
};
/**
* struct efx_filter_spec - specification for a hardware filter
- * @type: Type of match to be performed, from &enum efx_filter_type
+ * @match_flags: Match type flags, from &enum efx_filter_match_flags
* @priority: Priority of the filter, from &enum efx_filter_priority
* @flags: Miscellaneous flags, from &enum efx_filter_flags
- * @dmaq_id: Source/target queue index
- * @data: Match data (type-dependent)
+ * @rss_context: RSS context to use, if %EFX_FILTER_FLAG_RX_RSS is set
+ * @dmaq_id: Source/target queue index, or %EFX_FILTER_RX_DMAQ_ID_DROP for
+ * an RX drop filter
+ * @outer_vid: Outer VLAN ID to match, if %EFX_FILTER_MATCH_OUTER_VID is set
+ * @inner_vid: Inner VLAN ID to match, if %EFX_FILTER_MATCH_INNER_VID is set
+ * @loc_mac: Local MAC address to match, if %EFX_FILTER_MATCH_LOC_MAC or
+ * %EFX_FILTER_MATCH_LOC_MAC_IG is set
+ * @rem_mac: Remote MAC address to match, if %EFX_FILTER_MATCH_REM_MAC is set
+ * @ether_type: Ether-type to match, if %EFX_FILTER_MATCH_ETHER_TYPE is set
+ * @ip_proto: IP transport protocol to match, if %EFX_FILTER_MATCH_IP_PROTO
+ * is set
+ * @loc_host: Local IP host to match, if %EFX_FILTER_MATCH_LOC_HOST is set
+ * @rem_host: Remote IP host to match, if %EFX_FILTER_MATCH_REM_HOST is set
+ * @loc_port: Local TCP/UDP port to match, if %EFX_FILTER_MATCH_LOC_PORT is set
+ * @rem_port: Remote TCP/UDP port to match, if %EFX_FILTER_MATCH_REM_PORT is set
*
- * Use the efx_filter_set_*() functions to initialise the @type and
- * @data fields.
+ * The efx_filter_init_rx() or efx_filter_init_tx() function *must* be
+ * used to initialise the structure. The efx_filter_set_*() functions
+ * may then be used to set @rss_context, @match_flags and related
+ * fields.
*
* The @priority field is used by software to determine whether a new
* filter may replace an old one. The hardware priority of a filter
- * depends on the filter type and %EFX_FILTER_FLAG_RX_OVERRIDE_IP
- * flag.
+ * depends on which fields are matched.
*/
struct efx_filter_spec {
- u8 type:4;
- u8 priority:4;
- u8 flags;
- u16 dmaq_id;
- u32 data[3];
+ u32 match_flags:12;
+ u32 priority:2;
+ u32 flags:6;
+ u32 dmaq_id:12;
+ u32 rss_context;
+ __be16 outer_vid __aligned(4); /* allow jhash2() of match values */
+ __be16 inner_vid;
+ u8 loc_mac[ETH_ALEN];
+ u8 rem_mac[ETH_ALEN];
+ __be16 ether_type;
+ u8 ip_proto;
+ __be32 loc_host[4];
+ __be32 rem_host[4];
+ __be16 loc_port;
+ __be16 rem_port;
+ /* total 64 bytes */
+};
+
+enum {
+ EFX_FILTER_RSS_CONTEXT_DEFAULT = 0xffffffff,
+ EFX_FILTER_RX_DMAQ_ID_DROP = 0xfff
};
static inline void efx_filter_init_rx(struct efx_filter_spec *spec,
@@ -97,28 +157,116 @@ static inline void efx_filter_init_rx(struct efx_filter_spec *spec,
enum efx_filter_flags flags,
unsigned rxq_id)
{
- spec->type = EFX_FILTER_UNSPEC;
+ memset(spec, 0, sizeof(*spec));
spec->priority = priority;
spec->flags = EFX_FILTER_FLAG_RX | flags;
+ spec->rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT;
spec->dmaq_id = rxq_id;
}
-extern int efx_filter_set_ipv4_local(struct efx_filter_spec *spec, u8 proto,
- __be32 host, __be16 port);
-extern int efx_filter_get_ipv4_local(const struct efx_filter_spec *spec,
- u8 *proto, __be32 *host, __be16 *port);
-extern int efx_filter_set_ipv4_full(struct efx_filter_spec *spec, u8 proto,
- __be32 host, __be16 port,
- __be32 rhost, __be16 rport);
-extern int efx_filter_get_ipv4_full(const struct efx_filter_spec *spec,
- u8 *proto, __be32 *host, __be16 *port,
- __be32 *rhost, __be16 *rport);
-extern int efx_filter_set_eth_local(struct efx_filter_spec *spec,
- u16 vid, const u8 *addr);
-extern int efx_filter_get_eth_local(const struct efx_filter_spec *spec,
- u16 *vid, u8 *addr);
+static inline void efx_filter_init_tx(struct efx_filter_spec *spec,
+ unsigned txq_id)
+{
+ memset(spec, 0, sizeof(*spec));
+ spec->priority = EFX_FILTER_PRI_REQUIRED;
+ spec->flags = EFX_FILTER_FLAG_TX;
+ spec->dmaq_id = txq_id;
+}
+
+/**
+ * efx_filter_set_ipv4_local - specify IPv4 host, transport protocol and port
+ * @spec: Specification to initialise
+ * @proto: Transport layer protocol number
+ * @host: Local host address (network byte order)
+ * @port: Local port (network byte order)
+ */
+static inline int
+efx_filter_set_ipv4_local(struct efx_filter_spec *spec, u8 proto,
+ __be32 host, __be16 port)
+{
+ spec->match_flags |=
+ EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT;
+ spec->ether_type = htons(ETH_P_IP);
+ spec->ip_proto = proto;
+ spec->loc_host[0] = host;
+ spec->loc_port = port;
+ return 0;
+}
+
+/**
+ * efx_filter_set_ipv4_full - specify IPv4 hosts, transport protocol and ports
+ * @spec: Specification to initialise
+ * @proto: Transport layer protocol number
+ * @lhost: Local host address (network byte order)
+ * @lport: Local port (network byte order)
+ * @rhost: Remote host address (network byte order)
+ * @rport: Remote port (network byte order)
+ */
+static inline int
+efx_filter_set_ipv4_full(struct efx_filter_spec *spec, u8 proto,
+ __be32 lhost, __be16 lport,
+ __be32 rhost, __be16 rport)
+{
+ spec->match_flags |=
+ EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
+ EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT;
+ spec->ether_type = htons(ETH_P_IP);
+ spec->ip_proto = proto;
+ spec->loc_host[0] = lhost;
+ spec->loc_port = lport;
+ spec->rem_host[0] = rhost;
+ spec->rem_port = rport;
+ return 0;
+}
+
enum {
EFX_FILTER_VID_UNSPEC = 0xffff,
};
+/**
+ * efx_filter_set_eth_local - specify local Ethernet address and/or VID
+ * @spec: Specification to initialise
+ * @vid: Outer VLAN ID to match, or %EFX_FILTER_VID_UNSPEC
+ * @addr: Local Ethernet MAC address, or %NULL
+ */
+static inline int efx_filter_set_eth_local(struct efx_filter_spec *spec,
+ u16 vid, const u8 *addr)
+{
+ if (vid == EFX_FILTER_VID_UNSPEC && addr == NULL)
+ return -EINVAL;
+
+ if (vid != EFX_FILTER_VID_UNSPEC) {
+ spec->match_flags |= EFX_FILTER_MATCH_OUTER_VID;
+ spec->outer_vid = htons(vid);
+ }
+ if (addr != NULL) {
+ spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC;
+ ether_addr_copy(spec->loc_mac, addr);
+ }
+ return 0;
+}
+
+/**
+ * efx_filter_set_uc_def - specify matching otherwise-unmatched unicast
+ * @spec: Specification to initialise
+ */
+static inline int efx_filter_set_uc_def(struct efx_filter_spec *spec)
+{
+ spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC_IG;
+ return 0;
+}
+
+/**
+ * efx_filter_set_mc_def - specify matching otherwise-unmatched multicast
+ * @spec: Specification to initialise
+ */
+static inline int efx_filter_set_mc_def(struct efx_filter_spec *spec)
+{
+ spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC_IG;
+ spec->loc_mac[0] = 1;
+ return 0;
+}
+
#endif /* EFX_FILTER_H */
diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h
index 751d1ec112c..afb94aa2c15 100644
--- a/drivers/net/ethernet/sfc/io.h
+++ b/drivers/net/ethernet/sfc/io.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -20,24 +20,23 @@
*
**************************************************************************
*
- * Notes on locking strategy:
+ * Notes on locking strategy for the Falcon architecture:
*
- * Most CSRs are 128-bit (oword) and therefore cannot be read or
- * written atomically. Access from the host is buffered by the Bus
- * Interface Unit (BIU). Whenever the host reads from the lowest
- * address of such a register, or from the address of a different such
- * register, the BIU latches the register's value. Subsequent reads
- * from higher addresses of the same register will read the latched
- * value. Whenever the host writes part of such a register, the BIU
- * collects the written value and does not write to the underlying
- * register until all 4 dwords have been written. A similar buffering
- * scheme applies to host access to the NIC's 64-bit SRAM.
+ * Many CSRs are very wide and cannot be read or written atomically.
+ * Writes from the host are buffered by the Bus Interface Unit (BIU)
+ * up to 128 bits. Whenever the host writes part of such a register,
+ * the BIU collects the written value and does not write to the
+ * underlying register until all 4 dwords have been written. A
+ * similar buffering scheme applies to host access to the NIC's 64-bit
+ * SRAM.
*
- * Access to different CSRs and 64-bit SRAM words must be serialised,
- * since interleaved access can result in lost writes or lost
- * information from read-to-clear fields. We use efx_nic::biu_lock
- * for this. (We could use separate locks for read and write, but
- * this is not normally a performance bottleneck.)
+ * Writes to different CSRs and 64-bit SRAM words must be serialised,
+ * since interleaved access can result in lost writes. We use
+ * efx_nic::biu_lock for this.
+ *
+ * We also serialise reads from 128-bit CSRs and SRAM with the same
+ * spinlock. This may not be necessary, but it doesn't really matter
+ * as there are no such reads on the fast path.
*
* The DMA descriptor pointers (RX_DESC_UPD and TX_DESC_UPD) are
* 128-bit but are special-cased in the BIU to avoid the need for
@@ -55,12 +54,30 @@
* register while the collector already holds values for some other
* register, the write is discarded and the collector maintains its
* current state.
+ *
+ * The EF10 architecture exposes very few registers to the host and
+ * most of them are only 32 bits wide. The only exceptions are the MC
+ * doorbell register pair, which has its own latching, and
+ * TX_DESC_UPD, which works in a similar way to the Falcon
+ * architecture.
*/
#if BITS_PER_LONG == 64
#define EFX_USE_QWORD_IO 1
#endif
+/* Hardware issue requires that only 64-bit naturally aligned writes
+ * are seen by hardware. Its not strictly necessary to restrict to
+ * x86_64 arch, but done for safety since unusual write combining behaviour
+ * can break PIO.
+ */
+#ifdef CONFIG_X86_64
+/* PIO is a win only if write-combining is possible */
+#ifdef ARCH_HAS_IOREMAP_WC
+#define EFX_USE_PIO 1
+#endif
+#endif
+
#ifdef EFX_USE_QWORD_IO
static inline void _efx_writeq(struct efx_nic *efx, __le64 value,
unsigned int reg)
@@ -84,7 +101,7 @@ static inline __le32 _efx_readd(struct efx_nic *efx, unsigned int reg)
}
/* Write a normal 128-bit CSR, locking as appropriate. */
-static inline void efx_writeo(struct efx_nic *efx, efx_oword_t *value,
+static inline void efx_writeo(struct efx_nic *efx, const efx_oword_t *value,
unsigned int reg)
{
unsigned long flags __attribute__ ((unused));
@@ -109,7 +126,7 @@ static inline void efx_writeo(struct efx_nic *efx, efx_oword_t *value,
/* Write 64-bit SRAM through the supplied mapping, locking as appropriate. */
static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
- efx_qword_t *value, unsigned int index)
+ const efx_qword_t *value, unsigned int index)
{
unsigned int addr = index * sizeof(*value);
unsigned long flags __attribute__ ((unused));
@@ -130,7 +147,7 @@ static inline void efx_sram_writeq(struct efx_nic *efx, void __iomem *membase,
}
/* Write a 32-bit CSR or the last dword of a special 128-bit CSR */
-static inline void efx_writed(struct efx_nic *efx, efx_dword_t *value,
+static inline void efx_writed(struct efx_nic *efx, const efx_dword_t *value,
unsigned int reg)
{
netif_vdbg(efx, hw, efx->net_dev,
@@ -191,8 +208,9 @@ static inline void efx_readd(struct efx_nic *efx, efx_dword_t *value,
}
/* Write a 128-bit CSR forming part of a table */
-static inline void efx_writeo_table(struct efx_nic *efx, efx_oword_t *value,
- unsigned int reg, unsigned int index)
+static inline void
+efx_writeo_table(struct efx_nic *efx, const efx_oword_t *value,
+ unsigned int reg, unsigned int index)
{
efx_writeo(efx, value, reg + index * sizeof(efx_oword_t));
}
@@ -204,26 +222,12 @@ static inline void efx_reado_table(struct efx_nic *efx, efx_oword_t *value,
efx_reado(efx, value, reg + index * sizeof(efx_oword_t));
}
-/* Write a 32-bit CSR forming part of a table, or 32-bit SRAM */
-static inline void efx_writed_table(struct efx_nic *efx, efx_dword_t *value,
- unsigned int reg, unsigned int index)
-{
- efx_writed(efx, value, reg + index * sizeof(efx_oword_t));
-}
-
-/* Read a 32-bit CSR forming part of a table, or 32-bit SRAM */
-static inline void efx_readd_table(struct efx_nic *efx, efx_dword_t *value,
- unsigned int reg, unsigned int index)
-{
- efx_readd(efx, value, reg + index * sizeof(efx_dword_t));
-}
-
-/* Page-mapped register block size */
-#define EFX_PAGE_BLOCK_SIZE 0x2000
+/* Page size used as step between per-VI registers */
+#define EFX_VI_PAGE_SIZE 0x2000
-/* Calculate offset to page-mapped register block */
+/* Calculate offset to page-mapped register */
#define EFX_PAGED_REG(page, reg) \
- ((page) * EFX_PAGE_BLOCK_SIZE + (reg))
+ ((page) * EFX_VI_PAGE_SIZE + (reg))
/* Write the whole of RX_DESC_UPD or TX_DESC_UPD */
static inline void _efx_writeo_page(struct efx_nic *efx, efx_oword_t *value,
@@ -251,19 +255,24 @@ static inline void _efx_writeo_page(struct efx_nic *efx, efx_oword_t *value,
BUILD_BUG_ON_ZERO((reg) != 0x830 && (reg) != 0xa10), \
page)
-/* Write a page-mapped 32-bit CSR (EVQ_RPTR or the high bits of
- * RX_DESC_UPD or TX_DESC_UPD)
+/* Write a page-mapped 32-bit CSR (EVQ_RPTR, EVQ_TMR (EF10), or the
+ * high bits of RX_DESC_UPD or TX_DESC_UPD)
*/
-static inline void _efx_writed_page(struct efx_nic *efx, efx_dword_t *value,
- unsigned int reg, unsigned int page)
+static inline void
+_efx_writed_page(struct efx_nic *efx, const efx_dword_t *value,
+ unsigned int reg, unsigned int page)
{
efx_writed(efx, value, EFX_PAGED_REG(page, reg));
}
#define efx_writed_page(efx, value, reg, page) \
_efx_writed_page(efx, value, \
reg + \
- BUILD_BUG_ON_ZERO((reg) != 0x400 && (reg) != 0x83c \
- && (reg) != 0xa1c), \
+ BUILD_BUG_ON_ZERO((reg) != 0x400 && \
+ (reg) != 0x420 && \
+ (reg) != 0x830 && \
+ (reg) != 0x83c && \
+ (reg) != 0xa18 && \
+ (reg) != 0xa1c), \
page)
/* Write TIMER_COMMAND. This is a page-mapped 32-bit CSR, but a bug
@@ -271,7 +280,7 @@ static inline void _efx_writed_page(struct efx_nic *efx, efx_dword_t *value,
* collector register.
*/
static inline void _efx_writed_page_locked(struct efx_nic *efx,
- efx_dword_t *value,
+ const efx_dword_t *value,
unsigned int reg,
unsigned int page)
{
diff --git a/drivers/net/ethernet/sfc/mac.h b/drivers/net/ethernet/sfc/mac.h
deleted file mode 100644
index d6a255d0856..00000000000
--- a/drivers/net/ethernet/sfc/mac.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2009 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
- */
-
-#ifndef EFX_MAC_H
-#define EFX_MAC_H
-
-#include "net_driver.h"
-
-extern const struct efx_mac_operations falcon_xmac_operations;
-extern const struct efx_mac_operations efx_mcdi_mac_operations;
-extern int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr,
- u32 dma_len, int enable, int clear);
-
-#endif
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 81a42539746..5239cf9bdc5 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2008-2011 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2008-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -8,10 +8,11 @@
*/
#include <linux/delay.h>
+#include <asm/cmpxchg.h>
#include "net_driver.h"
#include "nic.h"
#include "io.h"
-#include "regs.h"
+#include "farch_regs.h"
#include "mcdi_pcol.h"
#include "phy.h"
@@ -22,121 +23,262 @@
**************************************************************************
*/
-/* Software-defined structure to the shared-memory */
-#define CMD_NOTIFY_PORT0 0
-#define CMD_NOTIFY_PORT1 4
-#define CMD_PDU_PORT0 0x008
-#define CMD_PDU_PORT1 0x108
-#define REBOOT_FLAG_PORT0 0x3f8
-#define REBOOT_FLAG_PORT1 0x3fc
+#define MCDI_RPC_TIMEOUT (10 * HZ)
-#define MCDI_RPC_TIMEOUT 10 /*seconds */
-
-#define MCDI_PDU(efx) \
- (efx_port_num(efx) ? CMD_PDU_PORT1 : CMD_PDU_PORT0)
-#define MCDI_DOORBELL(efx) \
- (efx_port_num(efx) ? CMD_NOTIFY_PORT1 : CMD_NOTIFY_PORT0)
-#define MCDI_REBOOT_FLAG(efx) \
- (efx_port_num(efx) ? REBOOT_FLAG_PORT1 : REBOOT_FLAG_PORT0)
+/* A reboot/assertion causes the MCDI status word to be set after the
+ * command word is set or a REBOOT event is sent. If we notice a reboot
+ * via these mechanisms then wait 250ms for the status word to be set.
+ */
+#define MCDI_STATUS_DELAY_US 100
+#define MCDI_STATUS_DELAY_COUNT 2500
+#define MCDI_STATUS_SLEEP_MS \
+ (MCDI_STATUS_DELAY_US * MCDI_STATUS_DELAY_COUNT / 1000)
#define SEQ_MASK \
EFX_MASK32(EFX_WIDTH(MCDI_HEADER_SEQ))
-static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx)
-{
- struct siena_nic_data *nic_data;
- EFX_BUG_ON_PARANOID(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
- nic_data = efx->nic_data;
- return &nic_data->mcdi;
-}
+struct efx_mcdi_async_param {
+ struct list_head list;
+ unsigned int cmd;
+ size_t inlen;
+ size_t outlen;
+ bool quiet;
+ efx_mcdi_async_completer *complete;
+ unsigned long cookie;
+ /* followed by request/response buffer */
+};
+
+static void efx_mcdi_timeout_async(unsigned long context);
+static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
+ bool *was_attached_out);
+static bool efx_mcdi_poll_once(struct efx_nic *efx);
+static void efx_mcdi_abandon(struct efx_nic *efx);
-void efx_mcdi_init(struct efx_nic *efx)
+int efx_mcdi_init(struct efx_nic *efx)
{
struct efx_mcdi_iface *mcdi;
+ bool already_attached;
+ int rc;
- if (efx_nic_rev(efx) < EFX_REV_SIENA_A0)
- return;
+ efx->mcdi = kzalloc(sizeof(*efx->mcdi), GFP_KERNEL);
+ if (!efx->mcdi)
+ return -ENOMEM;
mcdi = efx_mcdi(efx);
+ mcdi->efx = efx;
init_waitqueue_head(&mcdi->wq);
spin_lock_init(&mcdi->iface_lock);
- atomic_set(&mcdi->state, MCDI_STATE_QUIESCENT);
+ mcdi->state = MCDI_STATE_QUIESCENT;
mcdi->mode = MCDI_MODE_POLL;
+ spin_lock_init(&mcdi->async_lock);
+ INIT_LIST_HEAD(&mcdi->async_list);
+ setup_timer(&mcdi->async_timer, efx_mcdi_timeout_async,
+ (unsigned long)mcdi);
(void) efx_mcdi_poll_reboot(efx);
+ mcdi->new_epoch = true;
+
+ /* Recover from a failed assertion before probing */
+ rc = efx_mcdi_handle_assertion(efx);
+ if (rc)
+ return rc;
+
+ /* Let the MC (and BMC, if this is a LOM) know that the driver
+ * is loaded. We should do this before we reset the NIC.
+ */
+ rc = efx_mcdi_drv_attach(efx, true, &already_attached);
+ if (rc) {
+ netif_err(efx, probe, efx->net_dev,
+ "Unable to register driver with MCPU\n");
+ return rc;
+ }
+ if (already_attached)
+ /* Not a fatal error */
+ netif_err(efx, probe, efx->net_dev,
+ "Host already registered with MCPU\n");
+
+ if (efx->mcdi->fn_flags &
+ (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY))
+ efx->primary = efx;
+
+ return 0;
}
-static void efx_mcdi_copyin(struct efx_nic *efx, unsigned cmd,
- const u8 *inbuf, size_t inlen)
+void efx_mcdi_fini(struct efx_nic *efx)
+{
+ if (!efx->mcdi)
+ return;
+
+ BUG_ON(efx->mcdi->iface.state != MCDI_STATE_QUIESCENT);
+
+ /* Relinquish the device (back to the BMC, if this is a LOM) */
+ efx_mcdi_drv_attach(efx, false, NULL);
+
+ kfree(efx->mcdi);
+}
+
+static void efx_mcdi_send_request(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen)
{
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- unsigned pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
- unsigned doorbell = FR_CZ_MC_TREG_SMEM + MCDI_DOORBELL(efx);
- unsigned int i;
- efx_dword_t hdr;
+ efx_dword_t hdr[2];
+ size_t hdr_len;
u32 xflags, seqno;
- BUG_ON(atomic_read(&mcdi->state) == MCDI_STATE_QUIESCENT);
- BUG_ON(inlen & 3 || inlen >= 0x100);
+ BUG_ON(mcdi->state == MCDI_STATE_QUIESCENT);
+
+ /* Serialise with efx_mcdi_ev_cpl() and efx_mcdi_ev_death() */
+ spin_lock_bh(&mcdi->iface_lock);
+ ++mcdi->seqno;
+ spin_unlock_bh(&mcdi->iface_lock);
seqno = mcdi->seqno & SEQ_MASK;
xflags = 0;
if (mcdi->mode == MCDI_MODE_EVENTS)
xflags |= MCDI_HEADER_XFLAGS_EVREQ;
- EFX_POPULATE_DWORD_6(hdr,
- MCDI_HEADER_RESPONSE, 0,
- MCDI_HEADER_RESYNC, 1,
- MCDI_HEADER_CODE, cmd,
- MCDI_HEADER_DATALEN, inlen,
- MCDI_HEADER_SEQ, seqno,
- MCDI_HEADER_XFLAGS, xflags);
+ if (efx->type->mcdi_max_ver == 1) {
+ /* MCDI v1 */
+ EFX_POPULATE_DWORD_7(hdr[0],
+ MCDI_HEADER_RESPONSE, 0,
+ MCDI_HEADER_RESYNC, 1,
+ MCDI_HEADER_CODE, cmd,
+ MCDI_HEADER_DATALEN, inlen,
+ MCDI_HEADER_SEQ, seqno,
+ MCDI_HEADER_XFLAGS, xflags,
+ MCDI_HEADER_NOT_EPOCH, !mcdi->new_epoch);
+ hdr_len = 4;
+ } else {
+ /* MCDI v2 */
+ BUG_ON(inlen > MCDI_CTL_SDU_LEN_MAX_V2);
+ EFX_POPULATE_DWORD_7(hdr[0],
+ MCDI_HEADER_RESPONSE, 0,
+ MCDI_HEADER_RESYNC, 1,
+ MCDI_HEADER_CODE, MC_CMD_V2_EXTN,
+ MCDI_HEADER_DATALEN, 0,
+ MCDI_HEADER_SEQ, seqno,
+ MCDI_HEADER_XFLAGS, xflags,
+ MCDI_HEADER_NOT_EPOCH, !mcdi->new_epoch);
+ EFX_POPULATE_DWORD_2(hdr[1],
+ MC_CMD_V2_EXTN_IN_EXTENDED_CMD, cmd,
+ MC_CMD_V2_EXTN_IN_ACTUAL_LEN, inlen);
+ hdr_len = 8;
+ }
+
+ efx->type->mcdi_request(efx, hdr, hdr_len, inbuf, inlen);
+
+ mcdi->new_epoch = false;
+}
+
+static int efx_mcdi_errno(unsigned int mcdi_err)
+{
+ switch (mcdi_err) {
+ case 0:
+ return 0;
+#define TRANSLATE_ERROR(name) \
+ case MC_CMD_ERR_ ## name: \
+ return -name;
+ TRANSLATE_ERROR(EPERM);
+ TRANSLATE_ERROR(ENOENT);
+ TRANSLATE_ERROR(EINTR);
+ TRANSLATE_ERROR(EAGAIN);
+ TRANSLATE_ERROR(EACCES);
+ TRANSLATE_ERROR(EBUSY);
+ TRANSLATE_ERROR(EINVAL);
+ TRANSLATE_ERROR(EDEADLK);
+ TRANSLATE_ERROR(ENOSYS);
+ TRANSLATE_ERROR(ETIME);
+ TRANSLATE_ERROR(EALREADY);
+ TRANSLATE_ERROR(ENOSPC);
+#undef TRANSLATE_ERROR
+ case MC_CMD_ERR_ENOTSUP:
+ return -EOPNOTSUPP;
+ case MC_CMD_ERR_ALLOC_FAIL:
+ return -ENOBUFS;
+ case MC_CMD_ERR_MAC_EXIST:
+ return -EADDRINUSE;
+ default:
+ return -EPROTO;
+ }
+}
- efx_writed(efx, &hdr, pdu);
+static void efx_mcdi_read_response_header(struct efx_nic *efx)
+{
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ unsigned int respseq, respcmd, error;
+ efx_dword_t hdr;
- for (i = 0; i < inlen; i += 4)
- _efx_writed(efx, *((__le32 *)(inbuf + i)), pdu + 4 + i);
+ efx->type->mcdi_read_response(efx, &hdr, 0, 4);
+ respseq = EFX_DWORD_FIELD(hdr, MCDI_HEADER_SEQ);
+ respcmd = EFX_DWORD_FIELD(hdr, MCDI_HEADER_CODE);
+ error = EFX_DWORD_FIELD(hdr, MCDI_HEADER_ERROR);
- /* Ensure the payload is written out before the header */
- wmb();
+ if (respcmd != MC_CMD_V2_EXTN) {
+ mcdi->resp_hdr_len = 4;
+ mcdi->resp_data_len = EFX_DWORD_FIELD(hdr, MCDI_HEADER_DATALEN);
+ } else {
+ efx->type->mcdi_read_response(efx, &hdr, 4, 4);
+ mcdi->resp_hdr_len = 8;
+ mcdi->resp_data_len =
+ EFX_DWORD_FIELD(hdr, MC_CMD_V2_EXTN_IN_ACTUAL_LEN);
+ }
- /* ring the doorbell with a distinctive value */
- _efx_writed(efx, (__force __le32) 0x45789abc, doorbell);
+ if (error && mcdi->resp_data_len == 0) {
+ netif_err(efx, hw, efx->net_dev, "MC rebooted\n");
+ mcdi->resprc = -EIO;
+ } else if ((respseq ^ mcdi->seqno) & SEQ_MASK) {
+ netif_err(efx, hw, efx->net_dev,
+ "MC response mismatch tx seq 0x%x rx seq 0x%x\n",
+ respseq, mcdi->seqno);
+ mcdi->resprc = -EIO;
+ } else if (error) {
+ efx->type->mcdi_read_response(efx, &hdr, mcdi->resp_hdr_len, 4);
+ mcdi->resprc =
+ efx_mcdi_errno(EFX_DWORD_FIELD(hdr, EFX_DWORD_0));
+ } else {
+ mcdi->resprc = 0;
+ }
}
-static void efx_mcdi_copyout(struct efx_nic *efx, u8 *outbuf, size_t outlen)
+static bool efx_mcdi_poll_once(struct efx_nic *efx)
{
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
- int i;
- BUG_ON(atomic_read(&mcdi->state) == MCDI_STATE_QUIESCENT);
- BUG_ON(outlen & 3 || outlen >= 0x100);
+ rmb();
+ if (!efx->type->mcdi_poll_response(efx))
+ return false;
+
+ spin_lock_bh(&mcdi->iface_lock);
+ efx_mcdi_read_response_header(efx);
+ spin_unlock_bh(&mcdi->iface_lock);
- for (i = 0; i < outlen; i += 4)
- *((__le32 *)(outbuf + i)) = _efx_readd(efx, pdu + 4 + i);
+ return true;
}
static int efx_mcdi_poll(struct efx_nic *efx)
{
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- unsigned int time, finish;
- unsigned int respseq, respcmd, error;
- unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
- unsigned int rc, spins;
- efx_dword_t reg;
+ unsigned long time, finish;
+ unsigned int spins;
+ int rc;
/* Check for a reboot atomically with respect to efx_mcdi_copyout() */
- rc = -efx_mcdi_poll_reboot(efx);
- if (rc)
- goto out;
+ rc = efx_mcdi_poll_reboot(efx);
+ if (rc) {
+ spin_lock_bh(&mcdi->iface_lock);
+ mcdi->resprc = rc;
+ mcdi->resp_hdr_len = 0;
+ mcdi->resp_data_len = 0;
+ spin_unlock_bh(&mcdi->iface_lock);
+ return 0;
+ }
/* Poll for completion. Poll quickly (once a us) for the 1st jiffy,
* because generally mcdi responses are fast. After that, back off
* and poll once a jiffy (approximately)
*/
spins = TICK_USEC;
- finish = get_seconds() + MCDI_RPC_TIMEOUT;
+ finish = jiffies + MCDI_RPC_TIMEOUT;
while (1) {
if (spins != 0) {
@@ -146,111 +288,54 @@ static int efx_mcdi_poll(struct efx_nic *efx)
schedule_timeout_uninterruptible(1);
}
- time = get_seconds();
+ time = jiffies;
- rmb();
- efx_readd(efx, &reg, pdu);
-
- /* All 1's indicates that shared memory is in reset (and is
- * not a valid header). Wait for it to come out reset before
- * completing the command */
- if (EFX_DWORD_FIELD(reg, EFX_DWORD_0) != 0xffffffff &&
- EFX_DWORD_FIELD(reg, MCDI_HEADER_RESPONSE))
+ if (efx_mcdi_poll_once(efx))
break;
- if (time >= finish)
+ if (time_after(time, finish))
return -ETIMEDOUT;
}
- mcdi->resplen = EFX_DWORD_FIELD(reg, MCDI_HEADER_DATALEN);
- respseq = EFX_DWORD_FIELD(reg, MCDI_HEADER_SEQ);
- respcmd = EFX_DWORD_FIELD(reg, MCDI_HEADER_CODE);
- error = EFX_DWORD_FIELD(reg, MCDI_HEADER_ERROR);
-
- if (error && mcdi->resplen == 0) {
- netif_err(efx, hw, efx->net_dev, "MC rebooted\n");
- rc = EIO;
- } else if ((respseq ^ mcdi->seqno) & SEQ_MASK) {
- netif_err(efx, hw, efx->net_dev,
- "MC response mismatch tx seq 0x%x rx seq 0x%x\n",
- respseq, mcdi->seqno);
- rc = EIO;
- } else if (error) {
- efx_readd(efx, &reg, pdu + 4);
- switch (EFX_DWORD_FIELD(reg, EFX_DWORD_0)) {
-#define TRANSLATE_ERROR(name) \
- case MC_CMD_ERR_ ## name: \
- rc = name; \
- break
- TRANSLATE_ERROR(ENOENT);
- TRANSLATE_ERROR(EINTR);
- TRANSLATE_ERROR(EACCES);
- TRANSLATE_ERROR(EBUSY);
- TRANSLATE_ERROR(EINVAL);
- TRANSLATE_ERROR(EDEADLK);
- TRANSLATE_ERROR(ENOSYS);
- TRANSLATE_ERROR(ETIME);
-#undef TRANSLATE_ERROR
- default:
- rc = EIO;
- break;
- }
- } else
- rc = 0;
-
-out:
- mcdi->resprc = rc;
- if (rc)
- mcdi->resplen = 0;
-
/* Return rc=0 like wait_event_timeout() */
return 0;
}
-/* Test and clear MC-rebooted flag for this port/function */
+/* Test and clear MC-rebooted flag for this port/function; reset
+ * software state as necessary.
+ */
int efx_mcdi_poll_reboot(struct efx_nic *efx)
{
- unsigned int addr = FR_CZ_MC_TREG_SMEM + MCDI_REBOOT_FLAG(efx);
- efx_dword_t reg;
- uint32_t value;
-
- if (efx_nic_rev(efx) < EFX_REV_SIENA_A0)
- return false;
-
- efx_readd(efx, &reg, addr);
- value = EFX_DWORD_FIELD(reg, EFX_DWORD_0);
-
- if (value == 0)
+ if (!efx->mcdi)
return 0;
- EFX_ZERO_DWORD(reg);
- efx_writed(efx, &reg, addr);
+ return efx->type->mcdi_poll_reboot(efx);
+}
- if (value == MC_STATUS_DWORD_ASSERT)
- return -EINTR;
- else
- return -EIO;
+static bool efx_mcdi_acquire_async(struct efx_mcdi_iface *mcdi)
+{
+ return cmpxchg(&mcdi->state,
+ MCDI_STATE_QUIESCENT, MCDI_STATE_RUNNING_ASYNC) ==
+ MCDI_STATE_QUIESCENT;
}
-static void efx_mcdi_acquire(struct efx_mcdi_iface *mcdi)
+static void efx_mcdi_acquire_sync(struct efx_mcdi_iface *mcdi)
{
/* Wait until the interface becomes QUIESCENT and we win the race
- * to mark it RUNNING. */
+ * to mark it RUNNING_SYNC.
+ */
wait_event(mcdi->wq,
- atomic_cmpxchg(&mcdi->state,
- MCDI_STATE_QUIESCENT,
- MCDI_STATE_RUNNING)
- == MCDI_STATE_QUIESCENT);
+ cmpxchg(&mcdi->state,
+ MCDI_STATE_QUIESCENT, MCDI_STATE_RUNNING_SYNC) ==
+ MCDI_STATE_QUIESCENT);
}
static int efx_mcdi_await_completion(struct efx_nic *efx)
{
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- if (wait_event_timeout(
- mcdi->wq,
- atomic_read(&mcdi->state) == MCDI_STATE_COMPLETED,
- msecs_to_jiffies(MCDI_RPC_TIMEOUT * 1000)) == 0)
+ if (wait_event_timeout(mcdi->wq, mcdi->state == MCDI_STATE_COMPLETED,
+ MCDI_RPC_TIMEOUT) == 0)
return -ETIMEDOUT;
/* Check if efx_mcdi_set_mode() switched us back to polled completions.
@@ -267,17 +352,14 @@ static int efx_mcdi_await_completion(struct efx_nic *efx)
return 0;
}
-static bool efx_mcdi_complete(struct efx_mcdi_iface *mcdi)
+/* If the interface is RUNNING_SYNC, switch to COMPLETED and wake the
+ * requester. Return whether this was done. Does not take any locks.
+ */
+static bool efx_mcdi_complete_sync(struct efx_mcdi_iface *mcdi)
{
- /* If the interface is RUNNING, then move to COMPLETED and wake any
- * waiters. If the interface isn't in RUNNING then we've received a
- * duplicate completion after we've already transitioned back to
- * QUIESCENT. [A subsequent invocation would increment seqno, so would
- * have failed the seqno check].
- */
- if (atomic_cmpxchg(&mcdi->state,
- MCDI_STATE_RUNNING,
- MCDI_STATE_COMPLETED) == MCDI_STATE_RUNNING) {
+ if (cmpxchg(&mcdi->state,
+ MCDI_STATE_RUNNING_SYNC, MCDI_STATE_COMPLETED) ==
+ MCDI_STATE_RUNNING_SYNC) {
wake_up(&mcdi->wq);
return true;
}
@@ -287,12 +369,101 @@ static bool efx_mcdi_complete(struct efx_mcdi_iface *mcdi)
static void efx_mcdi_release(struct efx_mcdi_iface *mcdi)
{
- atomic_set(&mcdi->state, MCDI_STATE_QUIESCENT);
+ if (mcdi->mode == MCDI_MODE_EVENTS) {
+ struct efx_mcdi_async_param *async;
+ struct efx_nic *efx = mcdi->efx;
+
+ /* Process the asynchronous request queue */
+ spin_lock_bh(&mcdi->async_lock);
+ async = list_first_entry_or_null(
+ &mcdi->async_list, struct efx_mcdi_async_param, list);
+ if (async) {
+ mcdi->state = MCDI_STATE_RUNNING_ASYNC;
+ efx_mcdi_send_request(efx, async->cmd,
+ (const efx_dword_t *)(async + 1),
+ async->inlen);
+ mod_timer(&mcdi->async_timer,
+ jiffies + MCDI_RPC_TIMEOUT);
+ }
+ spin_unlock_bh(&mcdi->async_lock);
+
+ if (async)
+ return;
+ }
+
+ mcdi->state = MCDI_STATE_QUIESCENT;
wake_up(&mcdi->wq);
}
+/* If the interface is RUNNING_ASYNC, switch to COMPLETED, call the
+ * asynchronous completion function, and release the interface.
+ * Return whether this was done. Must be called in bh-disabled
+ * context. Will take iface_lock and async_lock.
+ */
+static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout)
+{
+ struct efx_nic *efx = mcdi->efx;
+ struct efx_mcdi_async_param *async;
+ size_t hdr_len, data_len, err_len;
+ efx_dword_t *outbuf;
+ MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+ int rc;
+
+ if (cmpxchg(&mcdi->state,
+ MCDI_STATE_RUNNING_ASYNC, MCDI_STATE_COMPLETED) !=
+ MCDI_STATE_RUNNING_ASYNC)
+ return false;
+
+ spin_lock(&mcdi->iface_lock);
+ if (timeout) {
+ /* Ensure that if the completion event arrives later,
+ * the seqno check in efx_mcdi_ev_cpl() will fail
+ */
+ ++mcdi->seqno;
+ ++mcdi->credits;
+ rc = -ETIMEDOUT;
+ hdr_len = 0;
+ data_len = 0;
+ } else {
+ rc = mcdi->resprc;
+ hdr_len = mcdi->resp_hdr_len;
+ data_len = mcdi->resp_data_len;
+ }
+ spin_unlock(&mcdi->iface_lock);
+
+ /* Stop the timer. In case the timer function is running, we
+ * must wait for it to return so that there is no possibility
+ * of it aborting the next request.
+ */
+ if (!timeout)
+ del_timer_sync(&mcdi->async_timer);
+
+ spin_lock(&mcdi->async_lock);
+ async = list_first_entry(&mcdi->async_list,
+ struct efx_mcdi_async_param, list);
+ list_del(&async->list);
+ spin_unlock(&mcdi->async_lock);
+
+ outbuf = (efx_dword_t *)(async + 1);
+ efx->type->mcdi_read_response(efx, outbuf, hdr_len,
+ min(async->outlen, data_len));
+ if (!timeout && rc && !async->quiet) {
+ err_len = min(sizeof(errbuf), data_len);
+ efx->type->mcdi_read_response(efx, errbuf, hdr_len,
+ sizeof(errbuf));
+ efx_mcdi_display_error(efx, async->cmd, async->inlen, errbuf,
+ err_len, rc);
+ }
+ async->complete(efx, async->cookie, rc, outbuf, data_len);
+ kfree(async);
+
+ efx_mcdi_release(mcdi);
+
+ return true;
+}
+
static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
- unsigned int datalen, unsigned int errno)
+ unsigned int datalen, unsigned int mcdi_err)
{
struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
bool wake = false;
@@ -308,36 +479,63 @@ static void efx_mcdi_ev_cpl(struct efx_nic *efx, unsigned int seqno,
"MC response mismatch tx seq 0x%x rx "
"seq 0x%x\n", seqno, mcdi->seqno);
} else {
- mcdi->resprc = errno;
- mcdi->resplen = datalen;
+ if (efx->type->mcdi_max_ver >= 2) {
+ /* MCDI v2 responses don't fit in an event */
+ efx_mcdi_read_response_header(efx);
+ } else {
+ mcdi->resprc = efx_mcdi_errno(mcdi_err);
+ mcdi->resp_hdr_len = 4;
+ mcdi->resp_data_len = datalen;
+ }
wake = true;
}
spin_unlock(&mcdi->iface_lock);
- if (wake)
- efx_mcdi_complete(mcdi);
+ if (wake) {
+ if (!efx_mcdi_complete_async(mcdi, false))
+ (void) efx_mcdi_complete_sync(mcdi);
+
+ /* If the interface isn't RUNNING_ASYNC or
+ * RUNNING_SYNC then we've received a duplicate
+ * completion after we've already transitioned back to
+ * QUIESCENT. [A subsequent invocation would increment
+ * seqno, so would have failed the seqno check].
+ */
+ }
}
-/* Issue the given command by writing the data into the shared memory PDU,
- * ring the doorbell and wait for completion. Copyout the result. */
-int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
- const u8 *inbuf, size_t inlen, u8 *outbuf, size_t outlen,
- size_t *outlen_actual)
+static void efx_mcdi_timeout_async(unsigned long context)
{
- struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- int rc;
- BUG_ON(efx_nic_rev(efx) < EFX_REV_SIENA_A0);
+ struct efx_mcdi_iface *mcdi = (struct efx_mcdi_iface *)context;
- efx_mcdi_acquire(mcdi);
+ efx_mcdi_complete_async(mcdi, true);
+}
- /* Serialise with efx_mcdi_ev_cpl() and efx_mcdi_ev_death() */
- spin_lock_bh(&mcdi->iface_lock);
- ++mcdi->seqno;
- spin_unlock_bh(&mcdi->iface_lock);
+static int
+efx_mcdi_check_supported(struct efx_nic *efx, unsigned int cmd, size_t inlen)
+{
+ if (efx->type->mcdi_max_ver < 0 ||
+ (efx->type->mcdi_max_ver < 2 &&
+ cmd > MC_CMD_CMD_SPACE_ESCAPE_7))
+ return -EINVAL;
+
+ if (inlen > MCDI_CTL_SDU_LEN_MAX_V2 ||
+ (efx->type->mcdi_max_ver < 2 &&
+ inlen > MCDI_CTL_SDU_LEN_MAX_V1))
+ return -EMSGSIZE;
- efx_mcdi_copyin(efx, cmd, inbuf, inlen);
+ return 0;
+}
+
+static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual, bool quiet)
+{
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0);
+ int rc;
if (mcdi->mode == MCDI_MODE_POLL)
rc = efx_mcdi_poll(efx);
@@ -345,6 +543,18 @@ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
rc = efx_mcdi_await_completion(efx);
if (rc != 0) {
+ netif_err(efx, hw, efx->net_dev,
+ "MC command 0x%x inlen %d mode %d timed out\n",
+ cmd, (int)inlen, mcdi->mode);
+
+ if (mcdi->mode == MCDI_MODE_EVENTS && efx_mcdi_poll_once(efx)) {
+ netif_err(efx, hw, efx->net_dev,
+ "MCDI request was completed without an event\n");
+ rc = 0;
+ }
+
+ efx_mcdi_abandon(efx);
+
/* Close the race with efx_mcdi_ev_cpl() executing just too late
* and completing a request we've just cancelled, by ensuring
* that the seqno check therein fails.
@@ -353,52 +563,260 @@ int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
++mcdi->seqno;
++mcdi->credits;
spin_unlock_bh(&mcdi->iface_lock);
+ }
- netif_err(efx, hw, efx->net_dev,
- "MC command 0x%x inlen %d mode %d timed out\n",
- cmd, (int)inlen, mcdi->mode);
+ if (rc != 0) {
+ if (outlen_actual)
+ *outlen_actual = 0;
} else {
- size_t resplen;
+ size_t hdr_len, data_len, err_len;
/* At the very least we need a memory barrier here to ensure
* we pick up changes from efx_mcdi_ev_cpl(). Protect against
* a spurious efx_mcdi_ev_cpl() running concurrently by
* acquiring the iface_lock. */
spin_lock_bh(&mcdi->iface_lock);
- rc = -mcdi->resprc;
- resplen = mcdi->resplen;
+ rc = mcdi->resprc;
+ hdr_len = mcdi->resp_hdr_len;
+ data_len = mcdi->resp_data_len;
+ err_len = min(sizeof(errbuf), data_len);
spin_unlock_bh(&mcdi->iface_lock);
- if (rc == 0) {
- efx_mcdi_copyout(efx, outbuf,
- min(outlen, mcdi->resplen + 3) & ~0x3);
- if (outlen_actual != NULL)
- *outlen_actual = resplen;
- } else if (cmd == MC_CMD_REBOOT && rc == -EIO)
- ; /* Don't reset if MC_CMD_REBOOT returns EIO */
- else if (rc == -EIO || rc == -EINTR) {
+ BUG_ON(rc > 0);
+
+ efx->type->mcdi_read_response(efx, outbuf, hdr_len,
+ min(outlen, data_len));
+ if (outlen_actual)
+ *outlen_actual = data_len;
+
+ efx->type->mcdi_read_response(efx, errbuf, hdr_len, err_len);
+
+ if (cmd == MC_CMD_REBOOT && rc == -EIO) {
+ /* Don't reset if MC_CMD_REBOOT returns EIO */
+ } else if (rc == -EIO || rc == -EINTR) {
netif_err(efx, hw, efx->net_dev, "MC fatal error %d\n",
-rc);
efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE);
- } else
- netif_dbg(efx, hw, efx->net_dev,
- "MC command 0x%x inlen %d failed rc=%d\n",
- cmd, (int)inlen, -rc);
+ } else if (rc && !quiet) {
+ efx_mcdi_display_error(efx, cmd, inlen, errbuf, err_len,
+ rc);
+ }
+
+ if (rc == -EIO || rc == -EINTR) {
+ msleep(MCDI_STATUS_SLEEP_MS);
+ efx_mcdi_poll_reboot(efx);
+ mcdi->new_epoch = true;
+ }
}
efx_mcdi_release(mcdi);
return rc;
}
+static int _efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual, bool quiet)
+{
+ int rc;
+
+ rc = efx_mcdi_rpc_start(efx, cmd, inbuf, inlen);
+ if (rc) {
+ if (outlen_actual)
+ *outlen_actual = 0;
+ return rc;
+ }
+ return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen,
+ outlen_actual, quiet);
+}
+
+int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual)
+{
+ return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen,
+ outlen_actual, false);
+}
+
+/* Normally, on receiving an error code in the MCDI response,
+ * efx_mcdi_rpc will log an error message containing (among other
+ * things) the raw error code, by means of efx_mcdi_display_error.
+ * This _quiet version suppresses that; if the caller wishes to log
+ * the error conditionally on the return code, it should call this
+ * function and is then responsible for calling efx_mcdi_display_error
+ * as needed.
+ */
+int efx_mcdi_rpc_quiet(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual)
+{
+ return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen,
+ outlen_actual, true);
+}
+
+int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen)
+{
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ int rc;
+
+ rc = efx_mcdi_check_supported(efx, cmd, inlen);
+ if (rc)
+ return rc;
+
+ if (efx->mc_bist_for_other_fn)
+ return -ENETDOWN;
+
+ if (mcdi->mode == MCDI_MODE_FAIL)
+ return -ENETDOWN;
+
+ efx_mcdi_acquire_sync(mcdi);
+ efx_mcdi_send_request(efx, cmd, inbuf, inlen);
+ return 0;
+}
+
+static int _efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ size_t outlen,
+ efx_mcdi_async_completer *complete,
+ unsigned long cookie, bool quiet)
+{
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ struct efx_mcdi_async_param *async;
+ int rc;
+
+ rc = efx_mcdi_check_supported(efx, cmd, inlen);
+ if (rc)
+ return rc;
+
+ if (efx->mc_bist_for_other_fn)
+ return -ENETDOWN;
+
+ async = kmalloc(sizeof(*async) + ALIGN(max(inlen, outlen), 4),
+ GFP_ATOMIC);
+ if (!async)
+ return -ENOMEM;
+
+ async->cmd = cmd;
+ async->inlen = inlen;
+ async->outlen = outlen;
+ async->quiet = quiet;
+ async->complete = complete;
+ async->cookie = cookie;
+ memcpy(async + 1, inbuf, inlen);
+
+ spin_lock_bh(&mcdi->async_lock);
+
+ if (mcdi->mode == MCDI_MODE_EVENTS) {
+ list_add_tail(&async->list, &mcdi->async_list);
+
+ /* If this is at the front of the queue, try to start it
+ * immediately
+ */
+ if (mcdi->async_list.next == &async->list &&
+ efx_mcdi_acquire_async(mcdi)) {
+ efx_mcdi_send_request(efx, cmd, inbuf, inlen);
+ mod_timer(&mcdi->async_timer,
+ jiffies + MCDI_RPC_TIMEOUT);
+ }
+ } else {
+ kfree(async);
+ rc = -ENETDOWN;
+ }
+
+ spin_unlock_bh(&mcdi->async_lock);
+
+ return rc;
+}
+
+/**
+ * efx_mcdi_rpc_async - Schedule an MCDI command to run asynchronously
+ * @efx: NIC through which to issue the command
+ * @cmd: Command type number
+ * @inbuf: Command parameters
+ * @inlen: Length of command parameters, in bytes
+ * @outlen: Length to allocate for response buffer, in bytes
+ * @complete: Function to be called on completion or cancellation.
+ * @cookie: Arbitrary value to be passed to @complete.
+ *
+ * This function does not sleep and therefore may be called in atomic
+ * context. It will fail if event queues are disabled or if MCDI
+ * event completions have been disabled due to an error.
+ *
+ * If it succeeds, the @complete function will be called exactly once
+ * in atomic context, when one of the following occurs:
+ * (a) the completion event is received (in NAPI context)
+ * (b) event queues are disabled (in the process that disables them)
+ * (c) the request times-out (in timer context)
+ */
+int
+efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd,
+ const efx_dword_t *inbuf, size_t inlen, size_t outlen,
+ efx_mcdi_async_completer *complete, unsigned long cookie)
+{
+ return _efx_mcdi_rpc_async(efx, cmd, inbuf, inlen, outlen, complete,
+ cookie, false);
+}
+
+int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ size_t outlen, efx_mcdi_async_completer *complete,
+ unsigned long cookie)
+{
+ return _efx_mcdi_rpc_async(efx, cmd, inbuf, inlen, outlen, complete,
+ cookie, true);
+}
+
+int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual)
+{
+ return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen,
+ outlen_actual, false);
+}
+
+int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual)
+{
+ return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen,
+ outlen_actual, true);
+}
+
+void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd,
+ size_t inlen, efx_dword_t *outbuf,
+ size_t outlen, int rc)
+{
+ int code = 0, err_arg = 0;
+
+ if (outlen >= MC_CMD_ERR_CODE_OFST + 4)
+ code = MCDI_DWORD(outbuf, ERR_CODE);
+ if (outlen >= MC_CMD_ERR_ARG_OFST + 4)
+ err_arg = MCDI_DWORD(outbuf, ERR_ARG);
+ netif_err(efx, hw, efx->net_dev,
+ "MC command 0x%x inlen %d failed rc=%d (raw=%d) arg=%d\n",
+ cmd, (int)inlen, rc, code, err_arg);
+}
+
+/* Switch to polled MCDI completions. This can be called in various
+ * error conditions with various locks held, so it must be lockless.
+ * Caller is responsible for flushing asynchronous requests later.
+ */
void efx_mcdi_mode_poll(struct efx_nic *efx)
{
struct efx_mcdi_iface *mcdi;
- if (efx_nic_rev(efx) < EFX_REV_SIENA_A0)
+ if (!efx->mcdi)
return;
mcdi = efx_mcdi(efx);
- if (mcdi->mode == MCDI_MODE_POLL)
+ /* If already in polling mode, nothing to do.
+ * If in fail-fast state, don't switch to polled completion.
+ * FLR recovery will do that later.
+ */
+ if (mcdi->mode == MCDI_MODE_POLL || mcdi->mode == MCDI_MODE_FAIL)
return;
/* We can switch from event completion to polled completion, because
@@ -407,23 +825,65 @@ void efx_mcdi_mode_poll(struct efx_nic *efx)
* efx_mcdi_await_completion() will then call efx_mcdi_poll().
*
* We need an smp_wmb() to synchronise with efx_mcdi_await_completion(),
- * which efx_mcdi_complete() provides for us.
+ * which efx_mcdi_complete_sync() provides for us.
*/
mcdi->mode = MCDI_MODE_POLL;
- efx_mcdi_complete(mcdi);
+ efx_mcdi_complete_sync(mcdi);
}
-void efx_mcdi_mode_event(struct efx_nic *efx)
+/* Flush any running or queued asynchronous requests, after event processing
+ * is stopped
+ */
+void efx_mcdi_flush_async(struct efx_nic *efx)
{
+ struct efx_mcdi_async_param *async, *next;
struct efx_mcdi_iface *mcdi;
- if (efx_nic_rev(efx) < EFX_REV_SIENA_A0)
+ if (!efx->mcdi)
return;
mcdi = efx_mcdi(efx);
- if (mcdi->mode == MCDI_MODE_EVENTS)
+ /* We must be in poll or fail mode so no more requests can be queued */
+ BUG_ON(mcdi->mode == MCDI_MODE_EVENTS);
+
+ del_timer_sync(&mcdi->async_timer);
+
+ /* If a request is still running, make sure we give the MC
+ * time to complete it so that the response won't overwrite our
+ * next request.
+ */
+ if (mcdi->state == MCDI_STATE_RUNNING_ASYNC) {
+ efx_mcdi_poll(efx);
+ mcdi->state = MCDI_STATE_QUIESCENT;
+ }
+
+ /* Nothing else will access the async list now, so it is safe
+ * to walk it without holding async_lock. If we hold it while
+ * calling a completer then lockdep may warn that we have
+ * acquired locks in the wrong order.
+ */
+ list_for_each_entry_safe(async, next, &mcdi->async_list, list) {
+ async->complete(efx, async->cookie, -ENETDOWN, NULL, 0);
+ list_del(&async->list);
+ kfree(async);
+ }
+}
+
+void efx_mcdi_mode_event(struct efx_nic *efx)
+{
+ struct efx_mcdi_iface *mcdi;
+
+ if (!efx->mcdi)
+ return;
+
+ mcdi = efx_mcdi(efx);
+ /* If already in event completion mode, nothing to do.
+ * If in fail-fast state, don't switch to event completion. FLR
+ * recovery will do that later.
+ */
+ if (mcdi->mode == MCDI_MODE_EVENTS || mcdi->mode == MCDI_MODE_FAIL)
return;
/* We can't switch from polled to event completion in the middle of a
@@ -433,7 +893,7 @@ void efx_mcdi_mode_event(struct efx_nic *efx)
* write memory barrier ensure that efx_mcdi_rpc() sees it, which
* efx_mcdi_acquire() provides.
*/
- efx_mcdi_acquire(mcdi);
+ efx_mcdi_acquire_sync(mcdi);
mcdi->mode = MCDI_MODE_EVENTS;
efx_mcdi_release(mcdi);
}
@@ -450,99 +910,80 @@ static void efx_mcdi_ev_death(struct efx_nic *efx, int rc)
* are sent to the same queue, we can't be racing with
* efx_mcdi_ev_cpl()]
*
- * There's a race here with efx_mcdi_rpc(), because we might receive
- * a REBOOT event *before* the request has been copied out. In polled
- * mode (during startup) this is irrelevant, because efx_mcdi_complete()
- * is ignored. In event mode, this condition is just an edge-case of
- * receiving a REBOOT event after posting the MCDI request. Did the mc
- * reboot before or after the copyout? The best we can do always is
- * just return failure.
+ * If there is an outstanding asynchronous request, we can't
+ * complete it now (efx_mcdi_complete() would deadlock). The
+ * reset process will take care of this.
+ *
+ * There's a race here with efx_mcdi_send_request(), because
+ * we might receive a REBOOT event *before* the request has
+ * been copied out. In polled mode (during startup) this is
+ * irrelevant, because efx_mcdi_complete_sync() is ignored. In
+ * event mode, this condition is just an edge-case of
+ * receiving a REBOOT event after posting the MCDI
+ * request. Did the mc reboot before or after the copyout? The
+ * best we can do always is just return failure.
*/
spin_lock(&mcdi->iface_lock);
- if (efx_mcdi_complete(mcdi)) {
+ if (efx_mcdi_complete_sync(mcdi)) {
if (mcdi->mode == MCDI_MODE_EVENTS) {
mcdi->resprc = rc;
- mcdi->resplen = 0;
+ mcdi->resp_hdr_len = 0;
+ mcdi->resp_data_len = 0;
++mcdi->credits;
}
- } else
+ } else {
+ int count;
+
+ /* Consume the status word since efx_mcdi_rpc_finish() won't */
+ for (count = 0; count < MCDI_STATUS_DELAY_COUNT; ++count) {
+ if (efx_mcdi_poll_reboot(efx))
+ break;
+ udelay(MCDI_STATUS_DELAY_US);
+ }
+ mcdi->new_epoch = true;
+
/* Nobody was waiting for an MCDI request, so trigger a reset */
efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE);
+ }
spin_unlock(&mcdi->iface_lock);
}
-static unsigned int efx_mcdi_event_link_speed[] = {
- [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100,
- [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000,
- [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000,
-};
-
-
-static void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev)
+/* The MC is going down in to BIST mode. set the BIST flag to block
+ * new MCDI, cancel any outstanding MCDI and and schedule a BIST-type reset
+ * (which doesn't actually execute a reset, it waits for the controlling
+ * function to reset it).
+ */
+static void efx_mcdi_ev_bist(struct efx_nic *efx)
{
- u32 flags, fcntl, speed, lpa;
-
- speed = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_SPEED);
- EFX_BUG_ON_PARANOID(speed >= ARRAY_SIZE(efx_mcdi_event_link_speed));
- speed = efx_mcdi_event_link_speed[speed];
-
- flags = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LINK_FLAGS);
- fcntl = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_FCNTL);
- lpa = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LP_CAP);
-
- /* efx->link_state is only modified by efx_mcdi_phy_get_link(),
- * which is only run after flushing the event queues. Therefore, it
- * is safe to modify the link state outside of the mac_lock here.
- */
- efx_mcdi_phy_decode_link(efx, &efx->link_state, speed, flags, fcntl);
-
- efx_mcdi_phy_check_fcntl(efx, lpa);
-
- efx_link_status_changed(efx);
-}
-
-static const char *sensor_names[] = {
- [MC_CMD_SENSOR_CONTROLLER_TEMP] = "Controller temp. sensor",
- [MC_CMD_SENSOR_PHY_COMMON_TEMP] = "PHY shared temp. sensor",
- [MC_CMD_SENSOR_CONTROLLER_COOLING] = "Controller cooling",
- [MC_CMD_SENSOR_PHY0_TEMP] = "PHY 0 temp. sensor",
- [MC_CMD_SENSOR_PHY0_COOLING] = "PHY 0 cooling",
- [MC_CMD_SENSOR_PHY1_TEMP] = "PHY 1 temp. sensor",
- [MC_CMD_SENSOR_PHY1_COOLING] = "PHY 1 cooling",
- [MC_CMD_SENSOR_IN_1V0] = "1.0V supply sensor",
- [MC_CMD_SENSOR_IN_1V2] = "1.2V supply sensor",
- [MC_CMD_SENSOR_IN_1V8] = "1.8V supply sensor",
- [MC_CMD_SENSOR_IN_2V5] = "2.5V supply sensor",
- [MC_CMD_SENSOR_IN_3V3] = "3.3V supply sensor",
- [MC_CMD_SENSOR_IN_12V0] = "12V supply sensor"
-};
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
-static const char *sensor_status_names[] = {
- [MC_CMD_SENSOR_STATE_OK] = "OK",
- [MC_CMD_SENSOR_STATE_WARNING] = "Warning",
- [MC_CMD_SENSOR_STATE_FATAL] = "Fatal",
- [MC_CMD_SENSOR_STATE_BROKEN] = "Device failure",
-};
+ spin_lock(&mcdi->iface_lock);
+ efx->mc_bist_for_other_fn = true;
+ if (efx_mcdi_complete_sync(mcdi)) {
+ if (mcdi->mode == MCDI_MODE_EVENTS) {
+ mcdi->resprc = -EIO;
+ mcdi->resp_hdr_len = 0;
+ mcdi->resp_data_len = 0;
+ ++mcdi->credits;
+ }
+ }
+ mcdi->new_epoch = true;
+ efx_schedule_reset(efx, RESET_TYPE_MC_BIST);
+ spin_unlock(&mcdi->iface_lock);
+}
-static void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev)
-{
- unsigned int monitor, state, value;
- const char *name, *state_txt;
- monitor = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_MONITOR);
- state = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_STATE);
- value = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_VALUE);
- /* Deal gracefully with the board having more drivers than we
- * know about, but do not expect new sensor states. */
- name = (monitor >= ARRAY_SIZE(sensor_names))
- ? "No sensor name available" :
- sensor_names[monitor];
- EFX_BUG_ON_PARANOID(state >= ARRAY_SIZE(sensor_status_names));
- state_txt = sensor_status_names[state];
+/* MCDI timeouts seen, so make all MCDI calls fail-fast and issue an FLR to try
+ * to recover.
+ */
+static void efx_mcdi_abandon(struct efx_nic *efx)
+{
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
- netif_err(efx, hw, efx->net_dev,
- "Sensor %d (%s) reports condition '%s' for raw value %d\n",
- monitor, name, state_txt, value);
+ if (xchg(&mcdi->mode, MCDI_MODE_FAIL) == MCDI_MODE_FAIL)
+ return; /* it had already been done */
+ netif_dbg(efx, hw, efx->net_dev, "MCDI is timing out; trying to recover\n");
+ efx_schedule_reset(efx, RESET_TYPE_MCDI_TIMEOUT);
}
/* Called from falcon_process_eventq for MCDI events */
@@ -557,7 +998,7 @@ void efx_mcdi_process_event(struct efx_channel *channel,
case MCDI_EVENT_CODE_BADSSERT:
netif_err(efx, hw, efx->net_dev,
"MC watchdog or assertion failure at 0x%x\n", data);
- efx_mcdi_ev_death(efx, EINTR);
+ efx_mcdi_ev_death(efx, -EINTR);
break;
case MCDI_EVENT_CODE_PMNOTICE:
@@ -578,17 +1019,53 @@ void efx_mcdi_process_event(struct efx_channel *channel,
efx_mcdi_sensor_event(efx, event);
break;
case MCDI_EVENT_CODE_SCHEDERR:
- netif_info(efx, hw, efx->net_dev,
- "MC Scheduler error address=0x%x\n", data);
+ netif_dbg(efx, hw, efx->net_dev,
+ "MC Scheduler alert (0x%x)\n", data);
break;
case MCDI_EVENT_CODE_REBOOT:
+ case MCDI_EVENT_CODE_MC_REBOOT:
netif_info(efx, hw, efx->net_dev, "MC Reboot\n");
- efx_mcdi_ev_death(efx, EIO);
+ efx_mcdi_ev_death(efx, -EIO);
+ break;
+ case MCDI_EVENT_CODE_MC_BIST:
+ netif_info(efx, hw, efx->net_dev, "MC entered BIST mode\n");
+ efx_mcdi_ev_bist(efx);
break;
case MCDI_EVENT_CODE_MAC_STATS_DMA:
/* MAC stats are gather lazily. We can ignore this. */
break;
-
+ case MCDI_EVENT_CODE_FLR:
+ efx_sriov_flr(efx, MCDI_EVENT_FIELD(*event, FLR_VF));
+ break;
+ case MCDI_EVENT_CODE_PTP_RX:
+ case MCDI_EVENT_CODE_PTP_FAULT:
+ case MCDI_EVENT_CODE_PTP_PPS:
+ efx_ptp_event(efx, event);
+ break;
+ case MCDI_EVENT_CODE_PTP_TIME:
+ efx_time_sync_event(channel, event);
+ break;
+ case MCDI_EVENT_CODE_TX_FLUSH:
+ case MCDI_EVENT_CODE_RX_FLUSH:
+ /* Two flush events will be sent: one to the same event
+ * queue as completions, and one to event queue 0.
+ * In the latter case the {RX,TX}_FLUSH_TO_DRIVER
+ * flag will be set, and we should ignore the event
+ * because we want to wait for all completions.
+ */
+ BUILD_BUG_ON(MCDI_EVENT_TX_FLUSH_TO_DRIVER_LBN !=
+ MCDI_EVENT_RX_FLUSH_TO_DRIVER_LBN);
+ if (!MCDI_EVENT_FIELD(*event, TX_FLUSH_TO_DRIVER))
+ efx_ef10_handle_drain_event(efx);
+ break;
+ case MCDI_EVENT_CODE_TX_ERR:
+ case MCDI_EVENT_CODE_RX_ERR:
+ netif_err(efx, hw, efx->net_dev,
+ "%s DMA error (event: "EFX_QWORD_FMT")\n",
+ code == MCDI_EVENT_CODE_TX_ERR ? "TX" : "RX",
+ EFX_QWORD_VAL(*event));
+ efx_schedule_reset(efx, RESET_TYPE_DMA_ERROR);
+ break;
default:
netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n",
code);
@@ -604,27 +1081,55 @@ void efx_mcdi_process_event(struct efx_channel *channel,
void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len)
{
- u8 outbuf[ALIGN(MC_CMD_GET_VERSION_V1_OUT_LEN, 4)];
+ MCDI_DECLARE_BUF(outbuf,
+ max(MC_CMD_GET_VERSION_OUT_LEN,
+ MC_CMD_GET_CAPABILITIES_OUT_LEN));
size_t outlength;
const __le16 *ver_words;
+ size_t offset;
int rc;
BUILD_BUG_ON(MC_CMD_GET_VERSION_IN_LEN != 0);
-
rc = efx_mcdi_rpc(efx, MC_CMD_GET_VERSION, NULL, 0,
outbuf, sizeof(outbuf), &outlength);
if (rc)
goto fail;
-
- if (outlength < MC_CMD_GET_VERSION_V1_OUT_LEN) {
+ if (outlength < MC_CMD_GET_VERSION_OUT_LEN) {
rc = -EIO;
goto fail;
}
ver_words = (__le16 *)MCDI_PTR(outbuf, GET_VERSION_OUT_VERSION);
- snprintf(buf, len, "%u.%u.%u.%u",
- le16_to_cpu(ver_words[0]), le16_to_cpu(ver_words[1]),
- le16_to_cpu(ver_words[2]), le16_to_cpu(ver_words[3]));
+ offset = snprintf(buf, len, "%u.%u.%u.%u",
+ le16_to_cpu(ver_words[0]), le16_to_cpu(ver_words[1]),
+ le16_to_cpu(ver_words[2]), le16_to_cpu(ver_words[3]));
+
+ /* EF10 may have multiple datapath firmware variants within a
+ * single version. Report which variants are running.
+ */
+ if (efx_nic_rev(efx) >= EFX_REV_HUNT_A0) {
+ BUILD_BUG_ON(MC_CMD_GET_CAPABILITIES_IN_LEN != 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_CAPABILITIES, NULL, 0,
+ outbuf, sizeof(outbuf), &outlength);
+ if (rc || outlength < MC_CMD_GET_CAPABILITIES_OUT_LEN)
+ offset += snprintf(
+ buf + offset, len - offset, " rx? tx?");
+ else
+ offset += snprintf(
+ buf + offset, len - offset, " rx%x tx%x",
+ MCDI_WORD(outbuf,
+ GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID),
+ MCDI_WORD(outbuf,
+ GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID));
+
+ /* It's theoretically possible for the string to exceed 31
+ * characters, though in practice the first three version
+ * components are short enough that this doesn't happen.
+ */
+ if (WARN_ON(offset >= len))
+ buf[0] = 0;
+ }
+
return;
fail:
@@ -632,17 +1137,18 @@ fail:
buf[0] = 0;
}
-int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
- bool *was_attached)
+static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
+ bool *was_attached)
{
- u8 inbuf[MC_CMD_DRV_ATTACH_IN_LEN];
- u8 outbuf[MC_CMD_DRV_ATTACH_OUT_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_DRV_ATTACH_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_DRV_ATTACH_EXT_OUT_LEN);
size_t outlen;
int rc;
MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_NEW_STATE,
driver_operating ? 1 : 0);
MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_UPDATE, 1);
+ MCDI_SET_DWORD(inbuf, DRV_ATTACH_IN_FIRMWARE_ID, MC_CMD_FW_LOW_LATENCY);
rc = efx_mcdi_rpc(efx, MC_CMD_DRV_ATTACH, inbuf, sizeof(inbuf),
outbuf, sizeof(outbuf), &outlen);
@@ -653,6 +1159,36 @@ int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
goto fail;
}
+ if (driver_operating) {
+ if (outlen >= MC_CMD_DRV_ATTACH_EXT_OUT_LEN) {
+ efx->mcdi->fn_flags =
+ MCDI_DWORD(outbuf,
+ DRV_ATTACH_EXT_OUT_FUNC_FLAGS);
+ } else {
+ /* Synthesise flags for Siena */
+ efx->mcdi->fn_flags =
+ 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
+ 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED |
+ (efx_port_num(efx) == 0) <<
+ MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY;
+ }
+ }
+
+ /* We currently assume we have control of the external link
+ * and are completely trusted by firmware. Abort probing
+ * if that's not true for this function.
+ */
+ if (driver_operating &&
+ (efx->mcdi->fn_flags &
+ (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
+ 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) !=
+ (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL |
+ 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) {
+ netif_err(efx, probe, efx->net_dev,
+ "This driver version only supports one function per port\n");
+ return -ENODEV;
+ }
+
if (was_attached != NULL)
*was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE);
return 0;
@@ -663,35 +1199,51 @@ fail:
}
int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
- u16 *fw_subtype_list)
+ u16 *fw_subtype_list, u32 *capabilities)
{
- uint8_t outbuf[MC_CMD_GET_BOARD_CFG_OUT_LEN];
- size_t outlen;
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_BOARD_CFG_OUT_LENMAX);
+ size_t outlen, i;
int port_num = efx_port_num(efx);
- int offset;
int rc;
BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0);
+ /* we need __aligned(2) for ether_addr_copy */
+ BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST & 1);
+ BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST & 1);
rc = efx_mcdi_rpc(efx, MC_CMD_GET_BOARD_CFG, NULL, 0,
outbuf, sizeof(outbuf), &outlen);
if (rc)
goto fail;
- if (outlen < MC_CMD_GET_BOARD_CFG_OUT_LEN) {
+ if (outlen < MC_CMD_GET_BOARD_CFG_OUT_LENMIN) {
rc = -EIO;
goto fail;
}
- offset = (port_num)
- ? MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST
- : MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST;
if (mac_address)
- memcpy(mac_address, outbuf + offset, ETH_ALEN);
- if (fw_subtype_list)
- memcpy(fw_subtype_list,
- outbuf + MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST,
- MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN);
+ ether_addr_copy(mac_address,
+ port_num ?
+ MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) :
+ MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0));
+ if (fw_subtype_list) {
+ for (i = 0;
+ i < MCDI_VAR_ARRAY_LEN(outlen,
+ GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST);
+ i++)
+ fw_subtype_list[i] = MCDI_ARRAY_WORD(
+ outbuf, GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST, i);
+ for (; i < MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM; i++)
+ fw_subtype_list[i] = 0;
+ }
+ if (capabilities) {
+ if (port_num)
+ *capabilities = MCDI_DWORD(outbuf,
+ GET_BOARD_CFG_OUT_CAPABILITIES_PORT1);
+ else
+ *capabilities = MCDI_DWORD(outbuf,
+ GET_BOARD_CFG_OUT_CAPABILITIES_PORT0);
+ }
return 0;
@@ -704,7 +1256,7 @@ fail:
int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq)
{
- u8 inbuf[MC_CMD_LOG_CTRL_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_LOG_CTRL_IN_LEN);
u32 dest = 0;
int rc;
@@ -720,19 +1272,12 @@ int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq)
rc = efx_mcdi_rpc(efx, MC_CMD_LOG_CTRL, inbuf, sizeof(inbuf),
NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
return rc;
}
int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out)
{
- u8 outbuf[MC_CMD_NVRAM_TYPES_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_TYPES_OUT_LEN);
size_t outlen;
int rc;
@@ -760,8 +1305,8 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
size_t *size_out, size_t *erase_size_out,
bool *protected_out)
{
- u8 inbuf[MC_CMD_NVRAM_INFO_IN_LEN];
- u8 outbuf[MC_CMD_NVRAM_INFO_OUT_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_INFO_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_INFO_OUT_LEN);
size_t outlen;
int rc;
@@ -779,124 +1324,7 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
*size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_SIZE);
*erase_size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_ERASESIZE);
*protected_out = !!(MCDI_DWORD(outbuf, NVRAM_INFO_OUT_FLAGS) &
- (1 << MC_CMD_NVRAM_PROTECTED_LBN));
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
-{
- u8 inbuf[MC_CMD_NVRAM_UPDATE_START_IN_LEN];
- int rc;
-
- MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_START_IN_TYPE, type);
-
- BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_START_OUT_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
- loff_t offset, u8 *buffer, size_t length)
-{
- u8 inbuf[MC_CMD_NVRAM_READ_IN_LEN];
- u8 outbuf[MC_CMD_NVRAM_READ_OUT_LEN(EFX_MCDI_NVRAM_LEN_MAX)];
- size_t outlen;
- int rc;
-
- MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_TYPE, type);
- MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_OFFSET, offset);
- MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_LENGTH, length);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf),
- outbuf, sizeof(outbuf), &outlen);
- if (rc)
- goto fail;
-
- memcpy(buffer, MCDI_PTR(outbuf, NVRAM_READ_OUT_READ_BUFFER), length);
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
- loff_t offset, const u8 *buffer, size_t length)
-{
- u8 inbuf[MC_CMD_NVRAM_WRITE_IN_LEN(EFX_MCDI_NVRAM_LEN_MAX)];
- int rc;
-
- MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_TYPE, type);
- MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_OFFSET, offset);
- MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_LENGTH, length);
- memcpy(MCDI_PTR(inbuf, NVRAM_WRITE_IN_WRITE_BUFFER), buffer, length);
-
- BUILD_BUG_ON(MC_CMD_NVRAM_WRITE_OUT_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf,
- ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4),
- NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
- loff_t offset, size_t length)
-{
- u8 inbuf[MC_CMD_NVRAM_ERASE_IN_LEN];
- int rc;
-
- MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_TYPE, type);
- MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_OFFSET, offset);
- MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_LENGTH, length);
-
- BUILD_BUG_ON(MC_CMD_NVRAM_ERASE_OUT_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_ERASE, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
-}
-
-int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
-{
- u8 inbuf[MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN];
- int rc;
-
- MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
-
- BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
- if (rc)
- goto fail;
-
+ (1 << MC_CMD_NVRAM_INFO_OUT_PROTECTED_LBN));
return 0;
fail:
@@ -906,8 +1334,8 @@ fail:
static int efx_mcdi_nvram_test(struct efx_nic *efx, unsigned int type)
{
- u8 inbuf[MC_CMD_NVRAM_TEST_IN_LEN];
- u8 outbuf[MC_CMD_NVRAM_TEST_OUT_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_TEST_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_TEST_OUT_LEN);
int rc;
MCDI_SET_DWORD(inbuf, NVRAM_TEST_IN_TYPE, type);
@@ -959,9 +1387,9 @@ fail1:
static int efx_mcdi_read_assertion(struct efx_nic *efx)
{
- u8 inbuf[MC_CMD_GET_ASSERTS_IN_LEN];
- u8 outbuf[MC_CMD_GET_ASSERTS_OUT_LEN];
- unsigned int flags, index, ofst;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_ASSERTS_IN_LEN);
+ MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN);
+ unsigned int flags, index;
const char *reason;
size_t outlen;
int retry;
@@ -975,13 +1403,17 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
retry = 2;
do {
MCDI_SET_DWORD(inbuf, GET_ASSERTS_IN_CLEAR, 1);
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_ASSERTS,
- inbuf, MC_CMD_GET_ASSERTS_IN_LEN,
- outbuf, sizeof(outbuf), &outlen);
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_ASSERTS,
+ inbuf, MC_CMD_GET_ASSERTS_IN_LEN,
+ outbuf, sizeof(outbuf), &outlen);
} while ((rc == -EINTR || rc == -EIO) && retry-- > 0);
- if (rc)
+ if (rc) {
+ efx_mcdi_display_error(efx, MC_CMD_GET_ASSERTS,
+ MC_CMD_GET_ASSERTS_IN_LEN, outbuf,
+ outlen, rc);
return rc;
+ }
if (outlen < MC_CMD_GET_ASSERTS_OUT_LEN)
return -EIO;
@@ -1003,26 +1435,32 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx)
MCDI_DWORD(outbuf, GET_ASSERTS_OUT_THREAD_OFFS));
/* Print out the registers */
- ofst = MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST;
- for (index = 1; index < 32; index++) {
- netif_err(efx, hw, efx->net_dev, "R%.2d (?): 0x%.8x\n", index,
- MCDI_DWORD2(outbuf, ofst));
- ofst += sizeof(efx_dword_t);
- }
+ for (index = 0;
+ index < MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_NUM;
+ index++)
+ netif_err(efx, hw, efx->net_dev, "R%.2d (?): 0x%.8x\n",
+ 1 + index,
+ MCDI_ARRAY_DWORD(outbuf, GET_ASSERTS_OUT_GP_REGS_OFFS,
+ index));
return 0;
}
static void efx_mcdi_exit_assertion(struct efx_nic *efx)
{
- u8 inbuf[MC_CMD_REBOOT_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_REBOOT_IN_LEN);
- /* Atomically reboot the mcfw out of the assertion handler */
+ /* If the MC is running debug firmware, it might now be
+ * waiting for a debugger to attach, but we just want it to
+ * reboot. We set a flag that makes the command a no-op if it
+ * has already done so. We don't know what return code to
+ * expect (0 or -EIO), so ignore it.
+ */
BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0);
MCDI_SET_DWORD(inbuf, REBOOT_IN_FLAGS,
MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION);
- efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
- NULL, 0, NULL);
+ (void) efx_mcdi_rpc(efx, MC_CMD_REBOOT, inbuf, MC_CMD_REBOOT_IN_LEN,
+ NULL, 0, NULL);
}
int efx_mcdi_handle_assertion(struct efx_nic *efx)
@@ -1040,7 +1478,7 @@ int efx_mcdi_handle_assertion(struct efx_nic *efx)
void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode)
{
- u8 inbuf[MC_CMD_SET_ID_LED_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_ID_LED_IN_LEN);
int rc;
BUILD_BUG_ON(EFX_LED_OFF != MC_CMD_LED_OFF);
@@ -1053,23 +1491,24 @@ void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode)
rc = efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf),
NULL, 0, NULL);
- if (rc)
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n",
- __func__, rc);
}
-int efx_mcdi_reset_port(struct efx_nic *efx)
+static int efx_mcdi_reset_func(struct efx_nic *efx)
{
- int rc = efx_mcdi_rpc(efx, MC_CMD_PORT_RESET, NULL, 0, NULL, 0, NULL);
- if (rc)
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n",
- __func__, rc);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_ENTITY_RESET_IN_LEN);
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_ENTITY_RESET_OUT_LEN != 0);
+ MCDI_POPULATE_DWORD_1(inbuf, ENTITY_RESET_IN_FLAG,
+ ENTITY_RESET_IN_FUNCTION_RESOURCE_RESET, 1);
+ rc = efx_mcdi_rpc(efx, MC_CMD_ENTITY_RESET, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
return rc;
}
-int efx_mcdi_reset_mc(struct efx_nic *efx)
+static int efx_mcdi_reset_mc(struct efx_nic *efx)
{
- u8 inbuf[MC_CMD_REBOOT_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_REBOOT_IN_LEN);
int rc;
BUILD_BUG_ON(MC_CMD_REBOOT_OUT_LEN != 0);
@@ -1081,22 +1520,54 @@ int efx_mcdi_reset_mc(struct efx_nic *efx)
return 0;
if (rc == 0)
rc = -EIO;
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
return rc;
}
+enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason)
+{
+ return RESET_TYPE_RECOVER_OR_ALL;
+}
+
+int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method)
+{
+ int rc;
+
+ /* If MCDI is down, we can't handle_assertion */
+ if (method == RESET_TYPE_MCDI_TIMEOUT) {
+ rc = pci_reset_function(efx->pci_dev);
+ if (rc)
+ return rc;
+ /* Re-enable polled MCDI completion */
+ if (efx->mcdi) {
+ struct efx_mcdi_iface *mcdi = efx_mcdi(efx);
+ mcdi->mode = MCDI_MODE_POLL;
+ }
+ return 0;
+ }
+
+ /* Recover from a failed assertion pre-reset */
+ rc = efx_mcdi_handle_assertion(efx);
+ if (rc)
+ return rc;
+
+ if (method == RESET_TYPE_WORLD)
+ return efx_mcdi_reset_mc(efx);
+ else
+ return efx_mcdi_reset_func(efx);
+}
+
static int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type,
const u8 *mac, int *id_out)
{
- u8 inbuf[MC_CMD_WOL_FILTER_SET_IN_LEN];
- u8 outbuf[MC_CMD_WOL_FILTER_SET_OUT_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_WOL_FILTER_SET_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_WOL_FILTER_SET_OUT_LEN);
size_t outlen;
int rc;
MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_WOL_TYPE, type);
MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_FILTER_MODE,
MC_CMD_FILTER_MODE_SIMPLE);
- memcpy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac, ETH_ALEN);
+ ether_addr_copy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac);
rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_SET, inbuf, sizeof(inbuf),
outbuf, sizeof(outbuf), &outlen);
@@ -1129,7 +1600,7 @@ efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, int *id_out)
int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out)
{
- u8 outbuf[MC_CMD_WOL_FILTER_GET_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_WOL_FILTER_GET_OUT_LEN);
size_t outlen;
int rc;
@@ -1156,36 +1627,265 @@ fail:
int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id)
{
- u8 inbuf[MC_CMD_WOL_FILTER_REMOVE_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_WOL_FILTER_REMOVE_IN_LEN);
int rc;
MCDI_SET_DWORD(inbuf, WOL_FILTER_REMOVE_IN_FILTER_ID, (u32)id);
rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_REMOVE, inbuf, sizeof(inbuf),
NULL, 0, NULL);
- if (rc)
- goto fail;
+ return rc;
+}
- return 0;
+int efx_mcdi_flush_rxqs(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ struct efx_rx_queue *rx_queue;
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_FLUSH_RX_QUEUES_IN_LEN(EFX_MAX_CHANNELS));
+ int rc, count;
+
+ BUILD_BUG_ON(EFX_MAX_CHANNELS >
+ MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
+
+ count = 0;
+ efx_for_each_channel(channel, efx) {
+ efx_for_each_channel_rx_queue(rx_queue, channel) {
+ if (rx_queue->flush_pending) {
+ rx_queue->flush_pending = false;
+ atomic_dec(&efx->rxq_flush_pending);
+ MCDI_SET_ARRAY_DWORD(
+ inbuf, FLUSH_RX_QUEUES_IN_QID_OFST,
+ count, efx_rx_queue_index(rx_queue));
+ count++;
+ }
+ }
+ }
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, inbuf,
+ MC_CMD_FLUSH_RX_QUEUES_IN_LEN(count), NULL, 0, NULL);
+ WARN_ON(rc < 0);
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
return rc;
}
-
int efx_mcdi_wol_filter_reset(struct efx_nic *efx)
{
int rc;
rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_RESET, NULL, 0, NULL, 0, NULL);
+ return rc;
+}
+
+int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_WORKAROUND_IN_LEN);
+
+ BUILD_BUG_ON(MC_CMD_WORKAROUND_OUT_LEN != 0);
+ MCDI_SET_DWORD(inbuf, WORKAROUND_IN_TYPE, type);
+ MCDI_SET_DWORD(inbuf, WORKAROUND_IN_ENABLED, enabled);
+ return efx_mcdi_rpc(efx, MC_CMD_WORKAROUND, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+}
+
+#ifdef CONFIG_SFC_MTD
+
+#define EFX_MCDI_NVRAM_LEN_MAX 128
+
+static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_IN_LEN);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_START_IN_TYPE, type);
+
+ BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_START_OUT_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ return rc;
+}
+
+static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
+ loff_t offset, u8 *buffer, size_t length)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_READ_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf,
+ MC_CMD_NVRAM_READ_OUT_LEN(EFX_MCDI_NVRAM_LEN_MAX));
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_TYPE, type);
+ MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_OFFSET, offset);
+ MCDI_SET_DWORD(inbuf, NVRAM_READ_IN_LENGTH, length);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
if (rc)
- goto fail;
+ return rc;
+ memcpy(buffer, MCDI_PTR(outbuf, NVRAM_READ_OUT_READ_BUFFER), length);
return 0;
+}
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
+static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
+ loff_t offset, const u8 *buffer, size_t length)
+{
+ MCDI_DECLARE_BUF(inbuf,
+ MC_CMD_NVRAM_WRITE_IN_LEN(EFX_MCDI_NVRAM_LEN_MAX));
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_TYPE, type);
+ MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_OFFSET, offset);
+ MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_LENGTH, length);
+ memcpy(MCDI_PTR(inbuf, NVRAM_WRITE_IN_WRITE_BUFFER), buffer, length);
+
+ BUILD_BUG_ON(MC_CMD_NVRAM_WRITE_OUT_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf,
+ ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4),
+ NULL, 0, NULL);
+ return rc;
+}
+
+static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
+ loff_t offset, size_t length)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_ERASE_IN_LEN);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_TYPE, type);
+ MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_OFFSET, offset);
+ MCDI_SET_DWORD(inbuf, NVRAM_ERASE_IN_LENGTH, length);
+
+ BUILD_BUG_ON(MC_CMD_NVRAM_ERASE_OUT_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_ERASE, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
return rc;
}
+static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
+
+ BUILD_BUG_ON(MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ return rc;
+}
+
+int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start,
+ size_t len, size_t *retlen, u8 *buffer)
+{
+ struct efx_mcdi_mtd_partition *part = to_efx_mcdi_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ loff_t offset = start;
+ loff_t end = min_t(loff_t, start + len, mtd->size);
+ size_t chunk;
+ int rc = 0;
+
+ while (offset < end) {
+ chunk = min_t(size_t, end - offset, EFX_MCDI_NVRAM_LEN_MAX);
+ rc = efx_mcdi_nvram_read(efx, part->nvram_type, offset,
+ buffer, chunk);
+ if (rc)
+ goto out;
+ offset += chunk;
+ buffer += chunk;
+ }
+out:
+ *retlen = offset - start;
+ return rc;
+}
+
+int efx_mcdi_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len)
+{
+ struct efx_mcdi_mtd_partition *part = to_efx_mcdi_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ loff_t offset = start & ~((loff_t)(mtd->erasesize - 1));
+ loff_t end = min_t(loff_t, start + len, mtd->size);
+ size_t chunk = part->common.mtd.erasesize;
+ int rc = 0;
+
+ if (!part->updating) {
+ rc = efx_mcdi_nvram_update_start(efx, part->nvram_type);
+ if (rc)
+ goto out;
+ part->updating = true;
+ }
+
+ /* The MCDI interface can in fact do multiple erase blocks at once;
+ * but erasing may be slow, so we make multiple calls here to avoid
+ * tripping the MCDI RPC timeout. */
+ while (offset < end) {
+ rc = efx_mcdi_nvram_erase(efx, part->nvram_type, offset,
+ chunk);
+ if (rc)
+ goto out;
+ offset += chunk;
+ }
+out:
+ return rc;
+}
+
+int efx_mcdi_mtd_write(struct mtd_info *mtd, loff_t start,
+ size_t len, size_t *retlen, const u8 *buffer)
+{
+ struct efx_mcdi_mtd_partition *part = to_efx_mcdi_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ loff_t offset = start;
+ loff_t end = min_t(loff_t, start + len, mtd->size);
+ size_t chunk;
+ int rc = 0;
+
+ if (!part->updating) {
+ rc = efx_mcdi_nvram_update_start(efx, part->nvram_type);
+ if (rc)
+ goto out;
+ part->updating = true;
+ }
+
+ while (offset < end) {
+ chunk = min_t(size_t, end - offset, EFX_MCDI_NVRAM_LEN_MAX);
+ rc = efx_mcdi_nvram_write(efx, part->nvram_type, offset,
+ buffer, chunk);
+ if (rc)
+ goto out;
+ offset += chunk;
+ buffer += chunk;
+ }
+out:
+ *retlen = offset - start;
+ return rc;
+}
+
+int efx_mcdi_mtd_sync(struct mtd_info *mtd)
+{
+ struct efx_mcdi_mtd_partition *part = to_efx_mcdi_mtd_partition(mtd);
+ struct efx_nic *efx = mtd->priv;
+ int rc = 0;
+
+ if (part->updating) {
+ part->updating = false;
+ rc = efx_mcdi_nvram_update_finish(efx, part->nvram_type);
+ }
+
+ return rc;
+}
+
+void efx_mcdi_mtd_rename(struct efx_mtd_partition *part)
+{
+ struct efx_mcdi_mtd_partition *mcdi_part =
+ container_of(part, struct efx_mcdi_mtd_partition, common);
+ struct efx_nic *efx = part->mtd.priv;
+
+ snprintf(part->name, sizeof(part->name), "%s %s:%02x",
+ efx->name, part->type_name, mcdi_part->fw_subtype);
+}
+
+#endif /* CONFIG_SFC_MTD */
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index aced2a7856f..56465f7465a 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2008-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2008-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -11,120 +11,351 @@
#define EFX_MCDI_H
/**
- * enum efx_mcdi_state
+ * enum efx_mcdi_state - MCDI request handling state
* @MCDI_STATE_QUIESCENT: No pending MCDI requests. If the caller holds the
- * mcdi_lock then they are able to move to MCDI_STATE_RUNNING
- * @MCDI_STATE_RUNNING: There is an MCDI request pending. Only the thread that
- * moved into this state is allowed to move out of it.
+ * mcdi @iface_lock then they are able to move to %MCDI_STATE_RUNNING
+ * @MCDI_STATE_RUNNING_SYNC: There is a synchronous MCDI request pending.
+ * Only the thread that moved into this state is allowed to move out of it.
+ * @MCDI_STATE_RUNNING_ASYNC: There is an asynchronous MCDI request pending.
* @MCDI_STATE_COMPLETED: An MCDI request has completed, but the owning thread
* has not yet consumed the result. For all other threads, equivalent to
- * MCDI_STATE_RUNNING.
+ * %MCDI_STATE_RUNNING.
*/
enum efx_mcdi_state {
MCDI_STATE_QUIESCENT,
- MCDI_STATE_RUNNING,
+ MCDI_STATE_RUNNING_SYNC,
+ MCDI_STATE_RUNNING_ASYNC,
MCDI_STATE_COMPLETED,
};
+/**
+ * enum efx_mcdi_mode - MCDI transaction mode
+ * @MCDI_MODE_POLL: poll for MCDI completion, until timeout
+ * @MCDI_MODE_EVENTS: wait for an mcdi_event. On timeout, poll once
+ * @MCDI_MODE_FAIL: we think MCDI is dead, so fail-fast all calls
+ */
enum efx_mcdi_mode {
MCDI_MODE_POLL,
MCDI_MODE_EVENTS,
+ MCDI_MODE_FAIL,
};
/**
- * struct efx_mcdi_iface
- * @state: Interface state. Waited for by mcdi_wq.
- * @wq: Wait queue for threads waiting for state != STATE_RUNNING
- * @iface_lock: Protects @credits, @seqno, @resprc, @resplen
+ * struct efx_mcdi_iface - MCDI protocol context
+ * @efx: The associated NIC.
+ * @state: Request handling state. Waited for by @wq.
* @mode: Poll for mcdi completion, or wait for an mcdi_event.
- * Serialised by @lock
+ * @wq: Wait queue for threads waiting for @state != %MCDI_STATE_RUNNING
+ * @new_epoch: Indicates start of day or start of MC reboot recovery
+ * @iface_lock: Serialises access to @seqno, @credits and response metadata
* @seqno: The next sequence number to use for mcdi requests.
- * Serialised by @lock
* @credits: Number of spurious MCDI completion events allowed before we
- * trigger a fatal error. Protected by @lock
- * @resprc: Returned MCDI completion
- * @resplen: Returned payload length
+ * trigger a fatal error
+ * @resprc: Response error/success code (Linux numbering)
+ * @resp_hdr_len: Response header length
+ * @resp_data_len: Response data (SDU or error) length
+ * @async_lock: Serialises access to @async_list while event processing is
+ * enabled
+ * @async_list: Queue of asynchronous requests
+ * @async_timer: Timer for asynchronous request timeout
*/
struct efx_mcdi_iface {
- atomic_t state;
+ struct efx_nic *efx;
+ enum efx_mcdi_state state;
+ enum efx_mcdi_mode mode;
wait_queue_head_t wq;
spinlock_t iface_lock;
- enum efx_mcdi_mode mode;
+ bool new_epoch;
unsigned int credits;
unsigned int seqno;
- unsigned int resprc;
- size_t resplen;
+ int resprc;
+ size_t resp_hdr_len;
+ size_t resp_data_len;
+ spinlock_t async_lock;
+ struct list_head async_list;
+ struct timer_list async_timer;
+};
+
+struct efx_mcdi_mon {
+ struct efx_buffer dma_buf;
+ struct mutex update_lock;
+ unsigned long last_update;
+ struct device *device;
+ struct efx_mcdi_mon_attribute *attrs;
+ struct attribute_group group;
+ const struct attribute_group *groups[2];
+ unsigned int n_attrs;
+};
+
+struct efx_mcdi_mtd_partition {
+ struct efx_mtd_partition common;
+ bool updating;
+ u16 nvram_type;
+ u16 fw_subtype;
+};
+
+#define to_efx_mcdi_mtd_partition(mtd) \
+ container_of(mtd, struct efx_mcdi_mtd_partition, common.mtd)
+
+/**
+ * struct efx_mcdi_data - extra state for NICs that implement MCDI
+ * @iface: Interface/protocol state
+ * @hwmon: Hardware monitor state
+ * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH.
+ */
+struct efx_mcdi_data {
+ struct efx_mcdi_iface iface;
+#ifdef CONFIG_SFC_MCDI_MON
+ struct efx_mcdi_mon hwmon;
+#endif
+ u32 fn_flags;
};
-extern void efx_mcdi_init(struct efx_nic *efx);
+static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx)
+{
+ EFX_BUG_ON_PARANOID(!efx->mcdi);
+ return &efx->mcdi->iface;
+}
-extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const u8 *inbuf,
- size_t inlen, u8 *outbuf, size_t outlen,
+#ifdef CONFIG_SFC_MCDI_MON
+static inline struct efx_mcdi_mon *efx_mcdi_mon(struct efx_nic *efx)
+{
+ EFX_BUG_ON_PARANOID(!efx->mcdi);
+ return &efx->mcdi->hwmon;
+}
+#endif
+
+int efx_mcdi_init(struct efx_nic *efx);
+void efx_mcdi_fini(struct efx_nic *efx);
+
+int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const efx_dword_t *inbuf,
+ size_t inlen, efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual);
+int efx_mcdi_rpc_quiet(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
+ size_t *outlen_actual);
+
+int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd,
+ const efx_dword_t *inbuf, size_t inlen);
+int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen,
+ efx_dword_t *outbuf, size_t outlen,
size_t *outlen_actual);
+int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd,
+ size_t inlen, efx_dword_t *outbuf,
+ size_t outlen, size_t *outlen_actual);
+
+typedef void efx_mcdi_async_completer(struct efx_nic *efx,
+ unsigned long cookie, int rc,
+ efx_dword_t *outbuf,
+ size_t outlen_actual);
+int efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd,
+ const efx_dword_t *inbuf, size_t inlen, size_t outlen,
+ efx_mcdi_async_completer *complete,
+ unsigned long cookie);
+int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd,
+ const efx_dword_t *inbuf, size_t inlen,
+ size_t outlen,
+ efx_mcdi_async_completer *complete,
+ unsigned long cookie);
+
+void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd,
+ size_t inlen, efx_dword_t *outbuf,
+ size_t outlen, int rc);
+
+int efx_mcdi_poll_reboot(struct efx_nic *efx);
+void efx_mcdi_mode_poll(struct efx_nic *efx);
+void efx_mcdi_mode_event(struct efx_nic *efx);
+void efx_mcdi_flush_async(struct efx_nic *efx);
-extern int efx_mcdi_poll_reboot(struct efx_nic *efx);
-extern void efx_mcdi_mode_poll(struct efx_nic *efx);
-extern void efx_mcdi_mode_event(struct efx_nic *efx);
-
-extern void efx_mcdi_process_event(struct efx_channel *channel,
- efx_qword_t *event);
-
-#define MCDI_PTR2(_buf, _ofst) \
- (((u8 *)_buf) + _ofst)
-#define MCDI_SET_DWORD2(_buf, _ofst, _value) \
- EFX_POPULATE_DWORD_1(*((efx_dword_t *)MCDI_PTR2(_buf, _ofst)), \
- EFX_DWORD_0, _value)
-#define MCDI_DWORD2(_buf, _ofst) \
- EFX_DWORD_FIELD(*((efx_dword_t *)MCDI_PTR2(_buf, _ofst)), \
- EFX_DWORD_0)
-#define MCDI_QWORD2(_buf, _ofst) \
- EFX_QWORD_FIELD64(*((efx_qword_t *)MCDI_PTR2(_buf, _ofst)), \
- EFX_QWORD_0)
-
-#define MCDI_PTR(_buf, _ofst) \
- MCDI_PTR2(_buf, MC_CMD_ ## _ofst ## _OFST)
-#define MCDI_SET_DWORD(_buf, _ofst, _value) \
- MCDI_SET_DWORD2(_buf, MC_CMD_ ## _ofst ## _OFST, _value)
-#define MCDI_DWORD(_buf, _ofst) \
- MCDI_DWORD2(_buf, MC_CMD_ ## _ofst ## _OFST)
-#define MCDI_QWORD(_buf, _ofst) \
- MCDI_QWORD2(_buf, MC_CMD_ ## _ofst ## _OFST)
+void efx_mcdi_process_event(struct efx_channel *channel, efx_qword_t *event);
+void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev);
+
+/* We expect that 16- and 32-bit fields in MCDI requests and responses
+ * are appropriately aligned, but 64-bit fields are only
+ * 32-bit-aligned. Also, on Siena we must copy to the MC shared
+ * memory strictly 32 bits at a time, so add any necessary padding.
+ */
+#define MCDI_DECLARE_BUF(_name, _len) \
+ efx_dword_t _name[DIV_ROUND_UP(_len, 4)]
+#define MCDI_DECLARE_BUF_OUT_OR_ERR(_name, _len) \
+ MCDI_DECLARE_BUF(_name, max_t(size_t, _len, 8))
+#define _MCDI_PTR(_buf, _offset) \
+ ((u8 *)(_buf) + (_offset))
+#define MCDI_PTR(_buf, _field) \
+ _MCDI_PTR(_buf, MC_CMD_ ## _field ## _OFST)
+#define _MCDI_CHECK_ALIGN(_ofst, _align) \
+ ((_ofst) + BUILD_BUG_ON_ZERO((_ofst) & (_align - 1)))
+#define _MCDI_DWORD(_buf, _field) \
+ ((_buf) + (_MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _OFST, 4) >> 2))
+
+#define MCDI_WORD(_buf, _field) \
+ ((u16)BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2) + \
+ le16_to_cpu(*(__force const __le16 *)MCDI_PTR(_buf, _field)))
+#define MCDI_SET_DWORD(_buf, _field, _value) \
+ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0, _value)
+#define MCDI_DWORD(_buf, _field) \
+ EFX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), EFX_DWORD_0)
+#define MCDI_POPULATE_DWORD_1(_buf, _field, _name1, _value1) \
+ EFX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1)
+#define MCDI_POPULATE_DWORD_2(_buf, _field, _name1, _value1, \
+ _name2, _value2) \
+ EFX_POPULATE_DWORD_2(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2)
+#define MCDI_POPULATE_DWORD_3(_buf, _field, _name1, _value1, \
+ _name2, _value2, _name3, _value3) \
+ EFX_POPULATE_DWORD_3(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2, \
+ MC_CMD_ ## _name3, _value3)
+#define MCDI_POPULATE_DWORD_4(_buf, _field, _name1, _value1, \
+ _name2, _value2, _name3, _value3, \
+ _name4, _value4) \
+ EFX_POPULATE_DWORD_4(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2, \
+ MC_CMD_ ## _name3, _value3, \
+ MC_CMD_ ## _name4, _value4)
+#define MCDI_POPULATE_DWORD_5(_buf, _field, _name1, _value1, \
+ _name2, _value2, _name3, _value3, \
+ _name4, _value4, _name5, _value5) \
+ EFX_POPULATE_DWORD_5(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2, \
+ MC_CMD_ ## _name3, _value3, \
+ MC_CMD_ ## _name4, _value4, \
+ MC_CMD_ ## _name5, _value5)
+#define MCDI_POPULATE_DWORD_6(_buf, _field, _name1, _value1, \
+ _name2, _value2, _name3, _value3, \
+ _name4, _value4, _name5, _value5, \
+ _name6, _value6) \
+ EFX_POPULATE_DWORD_6(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2, \
+ MC_CMD_ ## _name3, _value3, \
+ MC_CMD_ ## _name4, _value4, \
+ MC_CMD_ ## _name5, _value5, \
+ MC_CMD_ ## _name6, _value6)
+#define MCDI_POPULATE_DWORD_7(_buf, _field, _name1, _value1, \
+ _name2, _value2, _name3, _value3, \
+ _name4, _value4, _name5, _value5, \
+ _name6, _value6, _name7, _value7) \
+ EFX_POPULATE_DWORD_7(*_MCDI_DWORD(_buf, _field), \
+ MC_CMD_ ## _name1, _value1, \
+ MC_CMD_ ## _name2, _value2, \
+ MC_CMD_ ## _name3, _value3, \
+ MC_CMD_ ## _name4, _value4, \
+ MC_CMD_ ## _name5, _value5, \
+ MC_CMD_ ## _name6, _value6, \
+ MC_CMD_ ## _name7, _value7)
+#define MCDI_SET_QWORD(_buf, _field, _value) \
+ do { \
+ EFX_POPULATE_DWORD_1(_MCDI_DWORD(_buf, _field)[0], \
+ EFX_DWORD_0, (u32)(_value)); \
+ EFX_POPULATE_DWORD_1(_MCDI_DWORD(_buf, _field)[1], \
+ EFX_DWORD_0, (u64)(_value) >> 32); \
+ } while (0)
+#define MCDI_QWORD(_buf, _field) \
+ (EFX_DWORD_FIELD(_MCDI_DWORD(_buf, _field)[0], EFX_DWORD_0) | \
+ (u64)EFX_DWORD_FIELD(_MCDI_DWORD(_buf, _field)[1], EFX_DWORD_0) << 32)
+#define MCDI_FIELD(_ptr, _type, _field) \
+ EFX_EXTRACT_DWORD( \
+ *(efx_dword_t *) \
+ _MCDI_PTR(_ptr, MC_CMD_ ## _type ## _ ## _field ## _OFST & ~3),\
+ MC_CMD_ ## _type ## _ ## _field ## _LBN & 0x1f, \
+ (MC_CMD_ ## _type ## _ ## _field ## _LBN & 0x1f) + \
+ MC_CMD_ ## _type ## _ ## _field ## _WIDTH - 1)
+
+#define _MCDI_ARRAY_PTR(_buf, _field, _index, _align) \
+ (_MCDI_PTR(_buf, _MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _OFST, _align))\
+ + (_index) * _MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _LEN, _align))
+#define MCDI_DECLARE_STRUCT_PTR(_name) \
+ efx_dword_t *_name
+#define MCDI_ARRAY_STRUCT_PTR(_buf, _field, _index) \
+ ((efx_dword_t *)_MCDI_ARRAY_PTR(_buf, _field, _index, 4))
+#define MCDI_VAR_ARRAY_LEN(_len, _field) \
+ min_t(size_t, MC_CMD_ ## _field ## _MAXNUM, \
+ ((_len) - MC_CMD_ ## _field ## _OFST) / MC_CMD_ ## _field ## _LEN)
+#define MCDI_ARRAY_WORD(_buf, _field, _index) \
+ (BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 2) + \
+ le16_to_cpu(*(__force const __le16 *) \
+ _MCDI_ARRAY_PTR(_buf, _field, _index, 2)))
+#define _MCDI_ARRAY_DWORD(_buf, _field, _index) \
+ (BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 4) + \
+ (efx_dword_t *)_MCDI_ARRAY_PTR(_buf, _field, _index, 4))
+#define MCDI_SET_ARRAY_DWORD(_buf, _field, _index, _value) \
+ EFX_SET_DWORD_FIELD(*_MCDI_ARRAY_DWORD(_buf, _field, _index), \
+ EFX_DWORD_0, _value)
+#define MCDI_ARRAY_DWORD(_buf, _field, _index) \
+ EFX_DWORD_FIELD(*_MCDI_ARRAY_DWORD(_buf, _field, _index), EFX_DWORD_0)
+#define _MCDI_ARRAY_QWORD(_buf, _field, _index) \
+ (BUILD_BUG_ON_ZERO(MC_CMD_ ## _field ## _LEN != 8) + \
+ (efx_dword_t *)_MCDI_ARRAY_PTR(_buf, _field, _index, 4))
+#define MCDI_SET_ARRAY_QWORD(_buf, _field, _index, _value) \
+ do { \
+ EFX_SET_DWORD_FIELD(_MCDI_ARRAY_QWORD(_buf, _field, _index)[0],\
+ EFX_DWORD_0, (u32)(_value)); \
+ EFX_SET_DWORD_FIELD(_MCDI_ARRAY_QWORD(_buf, _field, _index)[1],\
+ EFX_DWORD_0, (u64)(_value) >> 32); \
+ } while (0)
+#define MCDI_ARRAY_FIELD(_buf, _field1, _type, _index, _field2) \
+ MCDI_FIELD(MCDI_ARRAY_STRUCT_PTR(_buf, _field1, _index), \
+ _type ## _TYPEDEF, _field2)
#define MCDI_EVENT_FIELD(_ev, _field) \
EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field)
-extern void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len);
-extern int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating,
- bool *was_attached_out);
-extern int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
- u16 *fw_subtype_list);
-extern int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart,
- u32 dest_evq);
-extern int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out);
-extern int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
- size_t *size_out, size_t *erase_size_out,
- bool *protected_out);
-extern int efx_mcdi_nvram_update_start(struct efx_nic *efx,
- unsigned int type);
-extern int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
- loff_t offset, u8 *buffer, size_t length);
-extern int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
- loff_t offset, const u8 *buffer,
- size_t length);
-#define EFX_MCDI_NVRAM_LEN_MAX 128
-extern int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
- loff_t offset, size_t length);
-extern int efx_mcdi_nvram_update_finish(struct efx_nic *efx,
- unsigned int type);
-extern int efx_mcdi_nvram_test_all(struct efx_nic *efx);
-extern int efx_mcdi_handle_assertion(struct efx_nic *efx);
-extern void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode);
-extern int efx_mcdi_reset_port(struct efx_nic *efx);
-extern int efx_mcdi_reset_mc(struct efx_nic *efx);
-extern int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx,
- const u8 *mac, int *id_out);
-extern int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out);
-extern int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id);
-extern int efx_mcdi_wol_filter_reset(struct efx_nic *efx);
+void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len);
+int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address,
+ u16 *fw_subtype_list, u32 *capabilities);
+int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq);
+int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out);
+int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
+ size_t *size_out, size_t *erase_size_out,
+ bool *protected_out);
+int efx_mcdi_nvram_test_all(struct efx_nic *efx);
+int efx_mcdi_handle_assertion(struct efx_nic *efx);
+void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode);
+int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac,
+ int *id_out);
+int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out);
+int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id);
+int efx_mcdi_wol_filter_reset(struct efx_nic *efx);
+int efx_mcdi_flush_rxqs(struct efx_nic *efx);
+int efx_mcdi_port_probe(struct efx_nic *efx);
+void efx_mcdi_port_remove(struct efx_nic *efx);
+int efx_mcdi_port_reconfigure(struct efx_nic *efx);
+int efx_mcdi_port_get_number(struct efx_nic *efx);
+u32 efx_mcdi_phy_get_caps(struct efx_nic *efx);
+void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev);
+int efx_mcdi_set_mac(struct efx_nic *efx);
+#define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1))
+void efx_mcdi_mac_start_stats(struct efx_nic *efx);
+void efx_mcdi_mac_stop_stats(struct efx_nic *efx);
+void efx_mcdi_mac_pull_stats(struct efx_nic *efx);
+bool efx_mcdi_mac_check_fault(struct efx_nic *efx);
+enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason);
+int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method);
+int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled);
+
+#ifdef CONFIG_SFC_MCDI_MON
+int efx_mcdi_mon_probe(struct efx_nic *efx);
+void efx_mcdi_mon_remove(struct efx_nic *efx);
+#else
+static inline int efx_mcdi_mon_probe(struct efx_nic *efx) { return 0; }
+static inline void efx_mcdi_mon_remove(struct efx_nic *efx) {}
+#endif
+
+#ifdef CONFIG_SFC_MTD
+int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start, size_t len,
+ size_t *retlen, u8 *buffer);
+int efx_mcdi_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len);
+int efx_mcdi_mtd_write(struct mtd_info *mtd, loff_t start, size_t len,
+ size_t *retlen, const u8 *buffer);
+int efx_mcdi_mtd_sync(struct mtd_info *mtd);
+void efx_mcdi_mtd_rename(struct efx_mtd_partition *part);
+#endif
#endif /* EFX_MCDI_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_mac.c b/drivers/net/ethernet/sfc/mcdi_mac.c
deleted file mode 100644
index 50c20777a56..00000000000
--- a/drivers/net/ethernet/sfc/mcdi_mac.c
+++ /dev/null
@@ -1,145 +0,0 @@
-/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2009-2010 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
- */
-
-#include "net_driver.h"
-#include "efx.h"
-#include "mac.h"
-#include "mcdi.h"
-#include "mcdi_pcol.h"
-
-static int efx_mcdi_set_mac(struct efx_nic *efx)
-{
- u32 reject, fcntl;
- u8 cmdbytes[MC_CMD_SET_MAC_IN_LEN];
-
- memcpy(cmdbytes + MC_CMD_SET_MAC_IN_ADDR_OFST,
- efx->net_dev->dev_addr, ETH_ALEN);
-
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU,
- EFX_MAX_FRAME_LEN(efx->net_dev->mtu));
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0);
-
- /* The MCDI command provides for controlling accept/reject
- * of broadcast packets too, but the driver doesn't currently
- * expose this. */
- reject = (efx->promiscuous) ? 0 :
- (1 << MC_CMD_SET_MAC_IN_REJECT_UNCST_LBN);
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_REJECT, reject);
-
- switch (efx->wanted_fc) {
- case EFX_FC_RX | EFX_FC_TX:
- fcntl = MC_CMD_FCNTL_BIDIR;
- break;
- case EFX_FC_RX:
- fcntl = MC_CMD_FCNTL_RESPOND;
- break;
- default:
- fcntl = MC_CMD_FCNTL_OFF;
- break;
- }
- if (efx->wanted_fc & EFX_FC_AUTO)
- fcntl = MC_CMD_FCNTL_AUTO;
-
- MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_FCNTL, fcntl);
-
- return efx_mcdi_rpc(efx, MC_CMD_SET_MAC, cmdbytes, sizeof(cmdbytes),
- NULL, 0, NULL);
-}
-
-static int efx_mcdi_get_mac_faults(struct efx_nic *efx, u32 *faults)
-{
- u8 outbuf[MC_CMD_GET_LINK_OUT_LEN];
- size_t outlength;
- int rc;
-
- BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
- outbuf, sizeof(outbuf), &outlength);
- if (rc)
- goto fail;
-
- *faults = MCDI_DWORD(outbuf, GET_LINK_OUT_MAC_FAULT);
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n",
- __func__, rc);
- return rc;
-}
-
-int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr,
- u32 dma_len, int enable, int clear)
-{
- u8 inbuf[MC_CMD_MAC_STATS_IN_LEN];
- int rc;
- efx_dword_t *cmd_ptr;
- int period = enable ? 1000 : 0;
- u32 addr_hi;
- u32 addr_lo;
-
- BUILD_BUG_ON(MC_CMD_MAC_STATS_OUT_LEN != 0);
-
- addr_lo = ((u64)dma_addr) >> 0;
- addr_hi = ((u64)dma_addr) >> 32;
-
- MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_LO, addr_lo);
- MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_ADDR_HI, addr_hi);
- cmd_ptr = (efx_dword_t *)MCDI_PTR(inbuf, MAC_STATS_IN_CMD);
- EFX_POPULATE_DWORD_7(*cmd_ptr,
- MC_CMD_MAC_STATS_CMD_DMA, !!enable,
- MC_CMD_MAC_STATS_CMD_CLEAR, clear,
- MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE, 1,
- MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE, !!enable,
- MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR, 0,
- MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT, 1,
- MC_CMD_MAC_STATS_CMD_PERIOD_MS, period);
- MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
-
- rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
- NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: %s failed rc=%d\n",
- __func__, enable ? "enable" : "disable", rc);
- return rc;
-}
-
-static int efx_mcdi_mac_reconfigure(struct efx_nic *efx)
-{
- int rc;
-
- rc = efx_mcdi_set_mac(efx);
- if (rc != 0)
- return rc;
-
- /* Restore the multicast hash registers. */
- efx->type->push_multicast_hash(efx);
-
- return 0;
-}
-
-
-static bool efx_mcdi_mac_check_fault(struct efx_nic *efx)
-{
- u32 faults;
- int rc = efx_mcdi_get_mac_faults(efx, &faults);
- return (rc != 0) || (faults != 0);
-}
-
-
-const struct efx_mac_operations efx_mcdi_mac_operations = {
- .reconfigure = efx_mcdi_mac_reconfigure,
- .update_stats = efx_port_dummy_op_void,
- .check_fault = efx_mcdi_mac_check_fault,
-};
diff --git a/drivers/net/ethernet/sfc/mcdi_mon.c b/drivers/net/ethernet/sfc/mcdi_mon.c
new file mode 100644
index 00000000000..bc27d5b580f
--- /dev/null
+++ b/drivers/net/ethernet/sfc/mcdi_mon.c
@@ -0,0 +1,534 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2011-2013 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/hwmon.h>
+#include <linux/stat.h>
+
+#include "net_driver.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+#include "nic.h"
+
+enum efx_hwmon_type {
+ EFX_HWMON_UNKNOWN,
+ EFX_HWMON_TEMP, /* temperature */
+ EFX_HWMON_COOL, /* cooling device, probably a heatsink */
+ EFX_HWMON_IN, /* voltage */
+ EFX_HWMON_CURR, /* current */
+ EFX_HWMON_POWER, /* power */
+ EFX_HWMON_TYPES_COUNT
+};
+
+static const char *const efx_hwmon_unit[EFX_HWMON_TYPES_COUNT] = {
+ [EFX_HWMON_TEMP] = " degC",
+ [EFX_HWMON_COOL] = " rpm", /* though nonsense for a heatsink */
+ [EFX_HWMON_IN] = " mV",
+ [EFX_HWMON_CURR] = " mA",
+ [EFX_HWMON_POWER] = " W",
+};
+
+static const struct {
+ const char *label;
+ enum efx_hwmon_type hwmon_type;
+ int port;
+} efx_mcdi_sensor_type[] = {
+#define SENSOR(name, label, hwmon_type, port) \
+ [MC_CMD_SENSOR_##name] = { label, EFX_HWMON_ ## hwmon_type, port }
+ SENSOR(CONTROLLER_TEMP, "Controller board temp.", TEMP, -1),
+ SENSOR(PHY_COMMON_TEMP, "PHY temp.", TEMP, -1),
+ SENSOR(CONTROLLER_COOLING, "Controller heat sink", COOL, -1),
+ SENSOR(PHY0_TEMP, "PHY temp.", TEMP, 0),
+ SENSOR(PHY0_COOLING, "PHY heat sink", COOL, 0),
+ SENSOR(PHY1_TEMP, "PHY temp.", TEMP, 1),
+ SENSOR(PHY1_COOLING, "PHY heat sink", COOL, 1),
+ SENSOR(IN_1V0, "1.0V supply", IN, -1),
+ SENSOR(IN_1V2, "1.2V supply", IN, -1),
+ SENSOR(IN_1V8, "1.8V supply", IN, -1),
+ SENSOR(IN_2V5, "2.5V supply", IN, -1),
+ SENSOR(IN_3V3, "3.3V supply", IN, -1),
+ SENSOR(IN_12V0, "12.0V supply", IN, -1),
+ SENSOR(IN_1V2A, "1.2V analogue supply", IN, -1),
+ SENSOR(IN_VREF, "Ref. voltage", IN, -1),
+ SENSOR(OUT_VAOE, "AOE FPGA supply", IN, -1),
+ SENSOR(AOE_TEMP, "AOE FPGA temp.", TEMP, -1),
+ SENSOR(PSU_AOE_TEMP, "AOE regulator temp.", TEMP, -1),
+ SENSOR(PSU_TEMP, "Controller regulator temp.",
+ TEMP, -1),
+ SENSOR(FAN_0, "Fan 0", COOL, -1),
+ SENSOR(FAN_1, "Fan 1", COOL, -1),
+ SENSOR(FAN_2, "Fan 2", COOL, -1),
+ SENSOR(FAN_3, "Fan 3", COOL, -1),
+ SENSOR(FAN_4, "Fan 4", COOL, -1),
+ SENSOR(IN_VAOE, "AOE input supply", IN, -1),
+ SENSOR(OUT_IAOE, "AOE output current", CURR, -1),
+ SENSOR(IN_IAOE, "AOE input current", CURR, -1),
+ SENSOR(NIC_POWER, "Board power use", POWER, -1),
+ SENSOR(IN_0V9, "0.9V supply", IN, -1),
+ SENSOR(IN_I0V9, "0.9V supply current", CURR, -1),
+ SENSOR(IN_I1V2, "1.2V supply current", CURR, -1),
+ SENSOR(IN_0V9_ADC, "0.9V supply (ext. ADC)", IN, -1),
+ SENSOR(CONTROLLER_2_TEMP, "Controller board temp. 2", TEMP, -1),
+ SENSOR(VREG_INTERNAL_TEMP, "Regulator die temp.", TEMP, -1),
+ SENSOR(VREG_0V9_TEMP, "0.9V regulator temp.", TEMP, -1),
+ SENSOR(VREG_1V2_TEMP, "1.2V regulator temp.", TEMP, -1),
+ SENSOR(CONTROLLER_VPTAT,
+ "Controller PTAT voltage (int. ADC)", IN, -1),
+ SENSOR(CONTROLLER_INTERNAL_TEMP,
+ "Controller die temp. (int. ADC)", TEMP, -1),
+ SENSOR(CONTROLLER_VPTAT_EXTADC,
+ "Controller PTAT voltage (ext. ADC)", IN, -1),
+ SENSOR(CONTROLLER_INTERNAL_TEMP_EXTADC,
+ "Controller die temp. (ext. ADC)", TEMP, -1),
+ SENSOR(AMBIENT_TEMP, "Ambient temp.", TEMP, -1),
+ SENSOR(AIRFLOW, "Air flow raw", IN, -1),
+ SENSOR(VDD08D_VSS08D_CSR, "0.9V die (int. ADC)", IN, -1),
+ SENSOR(VDD08D_VSS08D_CSR_EXTADC, "0.9V die (ext. ADC)", IN, -1),
+ SENSOR(HOTPOINT_TEMP, "Controller board temp. (hotpoint)", TEMP, -1),
+#undef SENSOR
+};
+
+static const char *const sensor_status_names[] = {
+ [MC_CMD_SENSOR_STATE_OK] = "OK",
+ [MC_CMD_SENSOR_STATE_WARNING] = "Warning",
+ [MC_CMD_SENSOR_STATE_FATAL] = "Fatal",
+ [MC_CMD_SENSOR_STATE_BROKEN] = "Device failure",
+ [MC_CMD_SENSOR_STATE_NO_READING] = "No reading",
+};
+
+void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev)
+{
+ unsigned int type, state, value;
+ enum efx_hwmon_type hwmon_type = EFX_HWMON_UNKNOWN;
+ const char *name = NULL, *state_txt, *unit;
+
+ type = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_MONITOR);
+ state = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_STATE);
+ value = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_VALUE);
+
+ /* Deal gracefully with the board having more drivers than we
+ * know about, but do not expect new sensor states. */
+ if (type < ARRAY_SIZE(efx_mcdi_sensor_type)) {
+ name = efx_mcdi_sensor_type[type].label;
+ hwmon_type = efx_mcdi_sensor_type[type].hwmon_type;
+ }
+ if (!name)
+ name = "No sensor name available";
+ EFX_BUG_ON_PARANOID(state >= ARRAY_SIZE(sensor_status_names));
+ state_txt = sensor_status_names[state];
+ EFX_BUG_ON_PARANOID(hwmon_type >= EFX_HWMON_TYPES_COUNT);
+ unit = efx_hwmon_unit[hwmon_type];
+ if (!unit)
+ unit = "";
+
+ netif_err(efx, hw, efx->net_dev,
+ "Sensor %d (%s) reports condition '%s' for value %d%s\n",
+ type, name, state_txt, value, unit);
+}
+
+#ifdef CONFIG_SFC_MCDI_MON
+
+struct efx_mcdi_mon_attribute {
+ struct device_attribute dev_attr;
+ unsigned int index;
+ unsigned int type;
+ enum efx_hwmon_type hwmon_type;
+ unsigned int limit_value;
+ char name[12];
+};
+
+static int efx_mcdi_mon_update(struct efx_nic *efx)
+{
+ struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_READ_SENSORS_EXT_IN_LEN);
+ int rc;
+
+ MCDI_SET_QWORD(inbuf, READ_SENSORS_EXT_IN_DMA_ADDR,
+ hwmon->dma_buf.dma_addr);
+ MCDI_SET_DWORD(inbuf, READ_SENSORS_EXT_IN_LENGTH, hwmon->dma_buf.len);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_READ_SENSORS,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
+ if (rc == 0)
+ hwmon->last_update = jiffies;
+ return rc;
+}
+
+static int efx_mcdi_mon_get_entry(struct device *dev, unsigned int index,
+ efx_dword_t *entry)
+{
+ struct efx_nic *efx = dev_get_drvdata(dev->parent);
+ struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx);
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_READ_SENSORS_OUT_LEN != 0);
+
+ mutex_lock(&hwmon->update_lock);
+
+ /* Use cached value if last update was < 1 s ago */
+ if (time_before(jiffies, hwmon->last_update + HZ))
+ rc = 0;
+ else
+ rc = efx_mcdi_mon_update(efx);
+
+ /* Copy out the requested entry */
+ *entry = ((efx_dword_t *)hwmon->dma_buf.addr)[index];
+
+ mutex_unlock(&hwmon->update_lock);
+
+ return rc;
+}
+
+static ssize_t efx_mcdi_mon_show_value(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct efx_mcdi_mon_attribute *mon_attr =
+ container_of(attr, struct efx_mcdi_mon_attribute, dev_attr);
+ efx_dword_t entry;
+ unsigned int value, state;
+ int rc;
+
+ rc = efx_mcdi_mon_get_entry(dev, mon_attr->index, &entry);
+ if (rc)
+ return rc;
+
+ state = EFX_DWORD_FIELD(entry, MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE);
+ if (state == MC_CMD_SENSOR_STATE_NO_READING)
+ return -EBUSY;
+
+ value = EFX_DWORD_FIELD(entry, MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_VALUE);
+
+ switch (mon_attr->hwmon_type) {
+ case EFX_HWMON_TEMP:
+ /* Convert temperature from degrees to milli-degrees Celsius */
+ value *= 1000;
+ break;
+ case EFX_HWMON_POWER:
+ /* Convert power from watts to microwatts */
+ value *= 1000000;
+ break;
+ default:
+ /* No conversion needed */
+ break;
+ }
+
+ return sprintf(buf, "%u\n", value);
+}
+
+static ssize_t efx_mcdi_mon_show_limit(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct efx_mcdi_mon_attribute *mon_attr =
+ container_of(attr, struct efx_mcdi_mon_attribute, dev_attr);
+ unsigned int value;
+
+ value = mon_attr->limit_value;
+
+ switch (mon_attr->hwmon_type) {
+ case EFX_HWMON_TEMP:
+ /* Convert temperature from degrees to milli-degrees Celsius */
+ value *= 1000;
+ break;
+ case EFX_HWMON_POWER:
+ /* Convert power from watts to microwatts */
+ value *= 1000000;
+ break;
+ default:
+ /* No conversion needed */
+ break;
+ }
+
+ return sprintf(buf, "%u\n", value);
+}
+
+static ssize_t efx_mcdi_mon_show_alarm(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct efx_mcdi_mon_attribute *mon_attr =
+ container_of(attr, struct efx_mcdi_mon_attribute, dev_attr);
+ efx_dword_t entry;
+ int state;
+ int rc;
+
+ rc = efx_mcdi_mon_get_entry(dev, mon_attr->index, &entry);
+ if (rc)
+ return rc;
+
+ state = EFX_DWORD_FIELD(entry, MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE);
+ return sprintf(buf, "%d\n", state != MC_CMD_SENSOR_STATE_OK);
+}
+
+static ssize_t efx_mcdi_mon_show_label(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct efx_mcdi_mon_attribute *mon_attr =
+ container_of(attr, struct efx_mcdi_mon_attribute, dev_attr);
+ return sprintf(buf, "%s\n",
+ efx_mcdi_sensor_type[mon_attr->type].label);
+}
+
+static void
+efx_mcdi_mon_add_attr(struct efx_nic *efx, const char *name,
+ ssize_t (*reader)(struct device *,
+ struct device_attribute *, char *),
+ unsigned int index, unsigned int type,
+ unsigned int limit_value)
+{
+ struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx);
+ struct efx_mcdi_mon_attribute *attr = &hwmon->attrs[hwmon->n_attrs];
+
+ strlcpy(attr->name, name, sizeof(attr->name));
+ attr->index = index;
+ attr->type = type;
+ if (type < ARRAY_SIZE(efx_mcdi_sensor_type))
+ attr->hwmon_type = efx_mcdi_sensor_type[type].hwmon_type;
+ else
+ attr->hwmon_type = EFX_HWMON_UNKNOWN;
+ attr->limit_value = limit_value;
+ sysfs_attr_init(&attr->dev_attr.attr);
+ attr->dev_attr.attr.name = attr->name;
+ attr->dev_attr.attr.mode = S_IRUGO;
+ attr->dev_attr.show = reader;
+ hwmon->group.attrs[hwmon->n_attrs++] = &attr->dev_attr.attr;
+}
+
+int efx_mcdi_mon_probe(struct efx_nic *efx)
+{
+ unsigned int n_temp = 0, n_cool = 0, n_in = 0, n_curr = 0, n_power = 0;
+ struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SENSOR_INFO_EXT_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_SENSOR_INFO_OUT_LENMAX);
+ unsigned int n_pages, n_sensors, n_attrs, page;
+ size_t outlen;
+ char name[12];
+ u32 mask;
+ int rc, i, j, type;
+
+ /* Find out how many sensors are present */
+ n_sensors = 0;
+ page = 0;
+ do {
+ MCDI_SET_DWORD(inbuf, SENSOR_INFO_EXT_IN_PAGE, page);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_SENSOR_INFO, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_SENSOR_INFO_OUT_LENMIN)
+ return -EIO;
+
+ mask = MCDI_DWORD(outbuf, SENSOR_INFO_OUT_MASK);
+ n_sensors += hweight32(mask & ~(1 << MC_CMD_SENSOR_PAGE0_NEXT));
+ ++page;
+ } while (mask & (1 << MC_CMD_SENSOR_PAGE0_NEXT));
+ n_pages = page;
+
+ /* Don't create a device if there are none */
+ if (n_sensors == 0)
+ return 0;
+
+ rc = efx_nic_alloc_buffer(
+ efx, &hwmon->dma_buf,
+ n_sensors * MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_LEN,
+ GFP_KERNEL);
+ if (rc)
+ return rc;
+
+ mutex_init(&hwmon->update_lock);
+ efx_mcdi_mon_update(efx);
+
+ /* Allocate space for the maximum possible number of
+ * attributes for this set of sensors:
+ * value, min, max, crit, alarm and label for each sensor.
+ */
+ n_attrs = 6 * n_sensors;
+ hwmon->attrs = kcalloc(n_attrs, sizeof(*hwmon->attrs), GFP_KERNEL);
+ if (!hwmon->attrs) {
+ rc = -ENOMEM;
+ goto fail;
+ }
+ hwmon->group.attrs = kcalloc(n_attrs + 1, sizeof(struct attribute *),
+ GFP_KERNEL);
+ if (!hwmon->group.attrs) {
+ rc = -ENOMEM;
+ goto fail;
+ }
+
+ for (i = 0, j = -1, type = -1; ; i++) {
+ enum efx_hwmon_type hwmon_type;
+ const char *hwmon_prefix;
+ unsigned hwmon_index;
+ u16 min1, max1, min2, max2;
+
+ /* Find next sensor type or exit if there is none */
+ do {
+ type++;
+
+ if ((type % 32) == 0) {
+ page = type / 32;
+ j = -1;
+ if (page == n_pages)
+ goto hwmon_register;
+
+ MCDI_SET_DWORD(inbuf, SENSOR_INFO_EXT_IN_PAGE,
+ page);
+ rc = efx_mcdi_rpc(efx, MC_CMD_SENSOR_INFO,
+ inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf),
+ &outlen);
+ if (rc)
+ goto fail;
+ if (outlen < MC_CMD_SENSOR_INFO_OUT_LENMIN) {
+ rc = -EIO;
+ goto fail;
+ }
+
+ mask = (MCDI_DWORD(outbuf,
+ SENSOR_INFO_OUT_MASK) &
+ ~(1 << MC_CMD_SENSOR_PAGE0_NEXT));
+
+ /* Check again for short response */
+ if (outlen <
+ MC_CMD_SENSOR_INFO_OUT_LEN(hweight32(mask))) {
+ rc = -EIO;
+ goto fail;
+ }
+ }
+ } while (!(mask & (1 << type % 32)));
+ j++;
+
+ if (type < ARRAY_SIZE(efx_mcdi_sensor_type)) {
+ hwmon_type = efx_mcdi_sensor_type[type].hwmon_type;
+
+ /* Skip sensors specific to a different port */
+ if (hwmon_type != EFX_HWMON_UNKNOWN &&
+ efx_mcdi_sensor_type[type].port >= 0 &&
+ efx_mcdi_sensor_type[type].port !=
+ efx_port_num(efx))
+ continue;
+ } else {
+ hwmon_type = EFX_HWMON_UNKNOWN;
+ }
+
+ switch (hwmon_type) {
+ case EFX_HWMON_TEMP:
+ hwmon_prefix = "temp";
+ hwmon_index = ++n_temp; /* 1-based */
+ break;
+ case EFX_HWMON_COOL:
+ /* This is likely to be a heatsink, but there
+ * is no convention for representing cooling
+ * devices other than fans.
+ */
+ hwmon_prefix = "fan";
+ hwmon_index = ++n_cool; /* 1-based */
+ break;
+ default:
+ hwmon_prefix = "in";
+ hwmon_index = n_in++; /* 0-based */
+ break;
+ case EFX_HWMON_CURR:
+ hwmon_prefix = "curr";
+ hwmon_index = ++n_curr; /* 1-based */
+ break;
+ case EFX_HWMON_POWER:
+ hwmon_prefix = "power";
+ hwmon_index = ++n_power; /* 1-based */
+ break;
+ }
+
+ min1 = MCDI_ARRAY_FIELD(outbuf, SENSOR_ENTRY,
+ SENSOR_INFO_ENTRY, j, MIN1);
+ max1 = MCDI_ARRAY_FIELD(outbuf, SENSOR_ENTRY,
+ SENSOR_INFO_ENTRY, j, MAX1);
+ min2 = MCDI_ARRAY_FIELD(outbuf, SENSOR_ENTRY,
+ SENSOR_INFO_ENTRY, j, MIN2);
+ max2 = MCDI_ARRAY_FIELD(outbuf, SENSOR_ENTRY,
+ SENSOR_INFO_ENTRY, j, MAX2);
+
+ if (min1 != max1) {
+ snprintf(name, sizeof(name), "%s%u_input",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_value, i, type, 0);
+
+ if (hwmon_type != EFX_HWMON_POWER) {
+ snprintf(name, sizeof(name), "%s%u_min",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_limit,
+ i, type, min1);
+ }
+
+ snprintf(name, sizeof(name), "%s%u_max",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_limit,
+ i, type, max1);
+
+ if (min2 != max2) {
+ /* Assume max2 is critical value.
+ * But we have no good way to expose min2.
+ */
+ snprintf(name, sizeof(name), "%s%u_crit",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_limit,
+ i, type, max2);
+ }
+ }
+
+ snprintf(name, sizeof(name), "%s%u_alarm",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_alarm, i, type, 0);
+
+ if (type < ARRAY_SIZE(efx_mcdi_sensor_type) &&
+ efx_mcdi_sensor_type[type].label) {
+ snprintf(name, sizeof(name), "%s%u_label",
+ hwmon_prefix, hwmon_index);
+ efx_mcdi_mon_add_attr(
+ efx, name, efx_mcdi_mon_show_label, i, type, 0);
+ }
+ }
+
+hwmon_register:
+ hwmon->groups[0] = &hwmon->group;
+ hwmon->device = hwmon_device_register_with_groups(&efx->pci_dev->dev,
+ KBUILD_MODNAME, NULL,
+ hwmon->groups);
+ if (IS_ERR(hwmon->device)) {
+ rc = PTR_ERR(hwmon->device);
+ goto fail;
+ }
+
+ return 0;
+
+fail:
+ efx_mcdi_mon_remove(efx);
+ return rc;
+}
+
+void efx_mcdi_mon_remove(struct efx_nic *efx)
+{
+ struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx);
+
+ if (hwmon->device)
+ hwmon_device_unregister(hwmon->device);
+ kfree(hwmon->attrs);
+ kfree(hwmon->group.attrs);
+ efx_nic_free_buffer(efx, &hwmon->dma_buf);
+}
+
+#endif /* CONFIG_SFC_MCDI_MON */
diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index 41fe06fa060..a707fb5ef14 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2009-2011 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2009-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -21,23 +21,46 @@
#define MC_FW_STATE_BOOTING (4)
/* The Scheduler has started. */
#define MC_FW_STATE_SCHED (8)
+/* If this is set in MC_RESET_STATE_REG then it should be
+ * possible to jump into IMEM without loading code from flash.
+ * Unlike a warm boot, assume DMEM has been reloaded, so that
+ * the MC persistent data must be reinitialised. */
+#define MC_FW_TEPID_BOOT_OK (16)
+/* BIST state has been initialized */
+#define MC_FW_BIST_INIT_OK (128)
+
+/* Siena MC shared memmory offsets */
+/* The 'doorbell' addresses are hard-wired to alert the MC when written */
+#define MC_SMEM_P0_DOORBELL_OFST 0x000
+#define MC_SMEM_P1_DOORBELL_OFST 0x004
+/* The rest of these are firmware-defined */
+#define MC_SMEM_P0_PDU_OFST 0x008
+#define MC_SMEM_P1_PDU_OFST 0x108
+#define MC_SMEM_PDU_LEN 0x100
+#define MC_SMEM_P0_PTP_TIME_OFST 0x7f0
+#define MC_SMEM_P0_STATUS_OFST 0x7f8
+#define MC_SMEM_P1_STATUS_OFST 0x7fc
/* Values to be written to the per-port status dword in shared
* memory on reboot and assert */
#define MC_STATUS_DWORD_REBOOT (0xb007b007)
#define MC_STATUS_DWORD_ASSERT (0xdeaddead)
+/* Check whether an mcfw version (in host order) belongs to a bootloader */
+#define MC_FW_VERSION_IS_BOOTLOADER(_v) (((_v) >> 16) == 0xb007)
+
/* The current version of the MCDI protocol.
*
* Note that the ROM burnt into the card only talks V0, so at the very
* least every driver must support version 0 and MCDI_PCOL_VERSION
*/
-#define MCDI_PCOL_VERSION 1
+#define MCDI_PCOL_VERSION 2
+
+/* Unused commands: 0x23, 0x27, 0x30, 0x31 */
-/**
- * MCDI version 1
+/* MCDI version 1
*
- * Each MCDI request starts with an MCDI_HEADER, which is a 32byte
+ * Each MCDI request starts with an MCDI_HEADER, which is a 32bit
* structure, filled in by the client.
*
* 0 7 8 16 20 22 23 24 31
@@ -74,9 +97,11 @@
#define MCDI_HEADER_DATALEN_LBN 8
#define MCDI_HEADER_DATALEN_WIDTH 8
#define MCDI_HEADER_SEQ_LBN 16
-#define MCDI_HEADER_RSVD_LBN 20
-#define MCDI_HEADER_RSVD_WIDTH 2
#define MCDI_HEADER_SEQ_WIDTH 4
+#define MCDI_HEADER_RSVD_LBN 20
+#define MCDI_HEADER_RSVD_WIDTH 1
+#define MCDI_HEADER_NOT_EPOCH_LBN 21
+#define MCDI_HEADER_NOT_EPOCH_WIDTH 1
#define MCDI_HEADER_ERROR_LBN 22
#define MCDI_HEADER_ERROR_WIDTH 1
#define MCDI_HEADER_RESPONSE_LBN 23
@@ -87,7 +112,11 @@
#define MCDI_HEADER_XFLAGS_EVREQ 0x01
/* Maximum number of payload bytes */
-#define MCDI_CTL_SDU_LEN_MAX 0xfc
+#define MCDI_CTL_SDU_LEN_MAX_V1 0xfc
+#define MCDI_CTL_SDU_LEN_MAX_V2 0x400
+
+#define MCDI_CTL_SDU_LEN_MAX MCDI_CTL_SDU_LEN_MAX_V2
+
/* The MC can generate events for two reasons:
* - To complete a shared memory request if XFLAGS_EVREQ was set
@@ -131,188 +160,95 @@
*/
#define FSE_AZ_EV_CODE_MCDI_EVRESPONSE 0xc
-#define MCDI_EVENT_DATA_LBN 0
-#define MCDI_EVENT_DATA_WIDTH 32
-#define MCDI_EVENT_CONT_LBN 32
-#define MCDI_EVENT_CONT_WIDTH 1
-#define MCDI_EVENT_LEVEL_LBN 33
-#define MCDI_EVENT_LEVEL_WIDTH 3
-#define MCDI_EVENT_LEVEL_INFO (0)
-#define MCDI_EVENT_LEVEL_WARN (1)
-#define MCDI_EVENT_LEVEL_ERR (2)
-#define MCDI_EVENT_LEVEL_FATAL (3)
-#define MCDI_EVENT_SRC_LBN 36
-#define MCDI_EVENT_SRC_WIDTH 8
-#define MCDI_EVENT_CODE_LBN 44
-#define MCDI_EVENT_CODE_WIDTH 8
-#define MCDI_EVENT_CODE_BADSSERT (1)
-#define MCDI_EVENT_CODE_PMNOTICE (2)
-#define MCDI_EVENT_CODE_CMDDONE (3)
-#define MCDI_EVENT_CMDDONE_SEQ_LBN 0
-#define MCDI_EVENT_CMDDONE_SEQ_WIDTH 8
-#define MCDI_EVENT_CMDDONE_DATALEN_LBN 8
-#define MCDI_EVENT_CMDDONE_DATALEN_WIDTH 8
-#define MCDI_EVENT_CMDDONE_ERRNO_LBN 16
-#define MCDI_EVENT_CMDDONE_ERRNO_WIDTH 8
-#define MCDI_EVENT_CODE_LINKCHANGE (4)
-#define MCDI_EVENT_LINKCHANGE_LP_CAP_LBN 0
-#define MCDI_EVENT_LINKCHANGE_LP_CAP_WIDTH 16
-#define MCDI_EVENT_LINKCHANGE_SPEED_LBN 16
-#define MCDI_EVENT_LINKCHANGE_SPEED_WIDTH 4
-#define MCDI_EVENT_LINKCHANGE_SPEED_100M 1
-#define MCDI_EVENT_LINKCHANGE_SPEED_1G 2
-#define MCDI_EVENT_LINKCHANGE_SPEED_10G 3
-#define MCDI_EVENT_LINKCHANGE_FCNTL_LBN 20
-#define MCDI_EVENT_LINKCHANGE_FCNTL_WIDTH 4
-#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_LBN 24
-#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_WIDTH 8
-#define MCDI_EVENT_CODE_SENSOREVT (5)
-#define MCDI_EVENT_SENSOREVT_MONITOR_LBN 0
-#define MCDI_EVENT_SENSOREVT_MONITOR_WIDTH 8
-#define MCDI_EVENT_SENSOREVT_STATE_LBN 8
-#define MCDI_EVENT_SENSOREVT_STATE_WIDTH 8
-#define MCDI_EVENT_SENSOREVT_VALUE_LBN 16
-#define MCDI_EVENT_SENSOREVT_VALUE_WIDTH 16
-#define MCDI_EVENT_CODE_SCHEDERR (6)
-#define MCDI_EVENT_CODE_REBOOT (7)
-#define MCDI_EVENT_CODE_MAC_STATS_DMA (8)
-#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_LBN 0
-#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_WIDTH 32
+/* Operation not permitted. */
+#define MC_CMD_ERR_EPERM 1
/* Non-existent command target */
#define MC_CMD_ERR_ENOENT 2
/* assert() has killed the MC */
#define MC_CMD_ERR_EINTR 4
+/* I/O failure */
+#define MC_CMD_ERR_EIO 5
+/* Try again */
+#define MC_CMD_ERR_EAGAIN 11
+/* Out of memory */
+#define MC_CMD_ERR_ENOMEM 12
/* Caller does not hold required locks */
#define MC_CMD_ERR_EACCES 13
/* Resource is currently unavailable (e.g. lock contention) */
#define MC_CMD_ERR_EBUSY 16
+/* No such device */
+#define MC_CMD_ERR_ENODEV 19
/* Invalid argument to target */
#define MC_CMD_ERR_EINVAL 22
+/* Out of range */
+#define MC_CMD_ERR_ERANGE 34
/* Non-recursive resource is already acquired */
#define MC_CMD_ERR_EDEADLK 35
/* Operation not implemented */
#define MC_CMD_ERR_ENOSYS 38
/* Operation timed out */
#define MC_CMD_ERR_ETIME 62
+/* Link has been severed */
+#define MC_CMD_ERR_ENOLINK 67
+/* Protocol error */
+#define MC_CMD_ERR_EPROTO 71
+/* Operation not supported */
+#define MC_CMD_ERR_ENOTSUP 95
+/* Address not available */
+#define MC_CMD_ERR_EADDRNOTAVAIL 99
+/* Not connected */
+#define MC_CMD_ERR_ENOTCONN 107
+/* Operation already in progress */
+#define MC_CMD_ERR_EALREADY 114
+
+/* Resource allocation failed. */
+#define MC_CMD_ERR_ALLOC_FAIL 0x1000
+/* V-adaptor not found. */
+#define MC_CMD_ERR_NO_VADAPTOR 0x1001
+/* EVB port not found. */
+#define MC_CMD_ERR_NO_EVB_PORT 0x1002
+/* V-switch not found. */
+#define MC_CMD_ERR_NO_VSWITCH 0x1003
+/* Too many VLAN tags. */
+#define MC_CMD_ERR_VLAN_LIMIT 0x1004
+/* Bad PCI function number. */
+#define MC_CMD_ERR_BAD_PCI_FUNC 0x1005
+/* Invalid VLAN mode. */
+#define MC_CMD_ERR_BAD_VLAN_MODE 0x1006
+/* Invalid v-switch type. */
+#define MC_CMD_ERR_BAD_VSWITCH_TYPE 0x1007
+/* Invalid v-port type. */
+#define MC_CMD_ERR_BAD_VPORT_TYPE 0x1008
+/* MAC address exists. */
+#define MC_CMD_ERR_MAC_EXIST 0x1009
+/* Slave core not present */
+#define MC_CMD_ERR_SLAVE_NOT_PRESENT 0x100a
+/* The datapath is disabled. */
+#define MC_CMD_ERR_DATAPATH_DISABLED 0x100b
#define MC_CMD_ERR_CODE_OFST 0
+/* We define 8 "escape" commands to allow
+ for command number space extension */
-/* MC_CMD_READ32: (debug, variadic out)
- * Read multiple 32byte words from MC memory
- */
-#define MC_CMD_READ32 0x01
-#define MC_CMD_READ32_IN_LEN 8
-#define MC_CMD_READ32_IN_ADDR_OFST 0
-#define MC_CMD_READ32_IN_NUMWORDS_OFST 4
-#define MC_CMD_READ32_OUT_LEN(_numwords) \
- (4 * (_numwords))
-#define MC_CMD_READ32_OUT_BUFFER_OFST 0
-
-/* MC_CMD_WRITE32: (debug, variadic in)
- * Write multiple 32byte words to MC memory
- */
-#define MC_CMD_WRITE32 0x02
-#define MC_CMD_WRITE32_IN_LEN(_numwords) (((_numwords) * 4) + 4)
-#define MC_CMD_WRITE32_IN_ADDR_OFST 0
-#define MC_CMD_WRITE32_IN_BUFFER_OFST 4
-#define MC_CMD_WRITE32_OUT_LEN 0
-
-/* MC_CMD_COPYCODE: (debug)
- * Copy MC code between two locations and jump
- */
-#define MC_CMD_COPYCODE 0x03
-#define MC_CMD_COPYCODE_IN_LEN 16
-#define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0
-#define MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4
-#define MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8
-#define MC_CMD_COPYCODE_IN_JUMP_OFST 12
-/* Control should return to the caller rather than jumping */
-#define MC_CMD_COPYCODE_JUMP_NONE 1
-#define MC_CMD_COPYCODE_OUT_LEN 0
-
-/* MC_CMD_SET_FUNC: (debug)
- * Select function for function-specific commands.
- */
-#define MC_CMD_SET_FUNC 0x04
-#define MC_CMD_SET_FUNC_IN_LEN 4
-#define MC_CMD_SET_FUNC_IN_FUNC_OFST 0
-#define MC_CMD_SET_FUNC_OUT_LEN 0
+#define MC_CMD_CMD_SPACE_ESCAPE_0 0x78
+#define MC_CMD_CMD_SPACE_ESCAPE_1 0x79
+#define MC_CMD_CMD_SPACE_ESCAPE_2 0x7A
+#define MC_CMD_CMD_SPACE_ESCAPE_3 0x7B
+#define MC_CMD_CMD_SPACE_ESCAPE_4 0x7C
+#define MC_CMD_CMD_SPACE_ESCAPE_5 0x7D
+#define MC_CMD_CMD_SPACE_ESCAPE_6 0x7E
+#define MC_CMD_CMD_SPACE_ESCAPE_7 0x7F
+
+/* Vectors in the boot ROM */
+/* Point to the copycode entry point. */
+#define SIENA_MC_BOOTROM_COPYCODE_VEC (0x800 - 3 * 0x4)
+#define HUNT_MC_BOOTROM_COPYCODE_VEC (0x8000 - 3 * 0x4)
+/* Points to the recovery mode entry point. */
+#define SIENA_MC_BOOTROM_NOFLASH_VEC (0x800 - 2 * 0x4)
+#define HUNT_MC_BOOTROM_NOFLASH_VEC (0x8000 - 2 * 0x4)
-/* MC_CMD_GET_BOOT_STATUS:
- * Get the instruction address from which the MC booted.
- */
-#define MC_CMD_GET_BOOT_STATUS 0x05
-#define MC_CMD_GET_BOOT_STATUS_IN_LEN 0
-#define MC_CMD_GET_BOOT_STATUS_OUT_LEN 8
-#define MC_CMD_GET_BOOT_STATUS_OUT_BOOT_OFFSET_OFST 0
-#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_OFST 4
-/* Reboot caused by watchdog */
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_WATCHDOG_LBN (0)
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_WATCHDOG_WIDTH (1)
-/* MC booted from primary flash partition */
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_PRIMARY_LBN (1)
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_PRIMARY_WIDTH (1)
-/* MC booted from backup flash partition */
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_BACKUP_LBN (2)
-#define MC_CMD_GET_BOOT_STATUS_FLAGS_BACKUP_WIDTH (1)
-
-/* MC_CMD_GET_ASSERTS: (debug, variadic out)
- * Get (and optionally clear) the current assertion status.
- *
- * Only OUT.GLOBAL_FLAGS is guaranteed to exist in the completion
- * payload. The other fields will only be present if
- * OUT.GLOBAL_FLAGS != NO_FAILS
- */
-#define MC_CMD_GET_ASSERTS 0x06
-#define MC_CMD_GET_ASSERTS_IN_LEN 4
-#define MC_CMD_GET_ASSERTS_IN_CLEAR_OFST 0
-#define MC_CMD_GET_ASSERTS_OUT_LEN 140
-/* Assertion status flag */
-#define MC_CMD_GET_ASSERTS_OUT_GLOBAL_FLAGS_OFST 0
-/*! No assertions have failed. */
-#define MC_CMD_GET_ASSERTS_FLAGS_NO_FAILS 1
-/*! A system-level assertion has failed. */
-#define MC_CMD_GET_ASSERTS_FLAGS_SYS_FAIL 2
-/*! A thread-level assertion has failed. */
-#define MC_CMD_GET_ASSERTS_FLAGS_THR_FAIL 3
-/*! The system was reset by the watchdog. */
-#define MC_CMD_GET_ASSERTS_FLAGS_WDOG_FIRED 4
-/* Failing PC value */
-#define MC_CMD_GET_ASSERTS_OUT_SAVED_PC_OFFS_OFST 4
-/* Saved GP regs */
-#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST 8
-#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_LEN 124
-/* Failing thread address */
-#define MC_CMD_GET_ASSERTS_OUT_THREAD_OFFS_OFST 132
-
-/* MC_CMD_LOG_CTRL:
- * Determine the output stream for various events and messages
- */
-#define MC_CMD_LOG_CTRL 0x07
-#define MC_CMD_LOG_CTRL_IN_LEN 8
-#define MC_CMD_LOG_CTRL_IN_LOG_DEST_OFST 0
-#define MC_CMD_LOG_CTRL_IN_LOG_DEST_UART (1)
-#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ (2)
-#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ_OFST 4
-#define MC_CMD_LOG_CTRL_OUT_LEN 0
-
-/* MC_CMD_GET_VERSION:
- * Get version information about the MC firmware
- */
-#define MC_CMD_GET_VERSION 0x08
-#define MC_CMD_GET_VERSION_IN_LEN 0
-#define MC_CMD_GET_VERSION_V0_OUT_LEN 4
-#define MC_CMD_GET_VERSION_V1_OUT_LEN 32
-#define MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0
-/* Reserved version number to indicate "any" version. */
-#define MC_CMD_GET_VERSION_OUT_FIRMWARE_ANY 0xffffffff
-/* The version response of a boot ROM awaiting rescue */
-#define MC_CMD_GET_VERSION_OUT_FIRMWARE_BOOTROM 0xb0070000
-#define MC_CMD_GET_VERSION_V1_OUT_PCOL_OFST 4
-/* 128bit mask of functions supported by the current firmware */
-#define MC_CMD_GET_VERSION_V1_OUT_SUPPORTED_FUNCS_OFST 8
/* The command set exported by the boot ROM (MCDI v0) */
#define MC_CMD_GET_VERSION_V0_SUPPORTED_FUNCS { \
(1 << MC_CMD_READ32) | \
@@ -320,1456 +256,7652 @@
(1 << MC_CMD_COPYCODE) | \
(1 << MC_CMD_GET_VERSION), \
0, 0, 0 }
-#define MC_CMD_GET_VERSION_OUT_VERSION_OFST 24
-/* Vectors in the boot ROM */
-/* Point to the copycode entry point. */
-#define MC_BOOTROM_COPYCODE_VEC (0x7f4)
-/* Points to the recovery mode entry point. */
-#define MC_BOOTROM_NOFLASH_VEC (0x7f8)
+#define MC_CMD_SENSOR_INFO_OUT_OFFSET_OFST(_x) \
+ (MC_CMD_SENSOR_ENTRY_OFST + (_x))
-/* Test execution limits */
-#define MC_TESTEXEC_VARIANT_COUNT 16
-#define MC_TESTEXEC_RESULT_COUNT 7
+#define MC_CMD_DBI_WRITE_IN_ADDRESS_OFST(n) \
+ (MC_CMD_DBI_WRITE_IN_DBIWROP_OFST + \
+ MC_CMD_DBIWROP_TYPEDEF_ADDRESS_OFST + \
+ (n) * MC_CMD_DBIWROP_TYPEDEF_LEN)
-/* MC_CMD_SET_TESTVARS: (debug, variadic in)
- * Write variant words for test.
- *
- * The user supplies a bitmap of the variants they wish to set.
- * They must ensure that IN.LEN >= 4 + 4 * ffs(BITMAP)
- */
-#define MC_CMD_SET_TESTVARS 0x09
-#define MC_CMD_SET_TESTVARS_IN_LEN(_numwords) \
- (4 + 4*(_numwords))
-#define MC_CMD_SET_TESTVARS_IN_ARGS_BITMAP_OFST 0
-/* Up to MC_TESTEXEC_VARIANT_COUNT of 32byte words start here */
-#define MC_CMD_SET_TESTVARS_IN_ARGS_BUFFER_OFST 4
-#define MC_CMD_SET_TESTVARS_OUT_LEN 0
-
-/* MC_CMD_GET_TESTRCS: (debug, variadic out)
- * Return result words from test.
- */
-#define MC_CMD_GET_TESTRCS 0x0a
-#define MC_CMD_GET_TESTRCS_IN_LEN 4
-#define MC_CMD_GET_TESTRCS_IN_NUMWORDS_OFST 0
-#define MC_CMD_GET_TESTRCS_OUT_LEN(_numwords) \
- (4 * (_numwords))
-#define MC_CMD_GET_TESTRCS_OUT_BUFFER_OFST 0
-
-/* MC_CMD_RUN_TEST: (debug)
- * Run the test exported by this firmware image
- */
-#define MC_CMD_RUN_TEST 0x0b
-#define MC_CMD_RUN_TEST_IN_LEN 0
-#define MC_CMD_RUN_TEST_OUT_LEN 0
-
-/* MC_CMD_CSR_READ32: (debug, variadic out)
- * Read 32bit words from the indirect memory map
- */
-#define MC_CMD_CSR_READ32 0x0c
-#define MC_CMD_CSR_READ32_IN_LEN 12
-#define MC_CMD_CSR_READ32_IN_ADDR_OFST 0
-#define MC_CMD_CSR_READ32_IN_STEP_OFST 4
-#define MC_CMD_CSR_READ32_IN_NUMWORDS_OFST 8
-#define MC_CMD_CSR_READ32_OUT_LEN(_numwords) \
- (((_numwords) * 4) + 4)
-/* IN.NUMWORDS of 32bit words start here */
-#define MC_CMD_CSR_READ32_OUT_BUFFER_OFST 0
-#define MC_CMD_CSR_READ32_OUT_IREG_STATUS_OFST(_numwords) \
- ((_numwords) * 4)
-
-/* MC_CMD_CSR_WRITE32: (debug, variadic in)
- * Write 32bit dwords to the indirect memory map
- */
-#define MC_CMD_CSR_WRITE32 0x0d
-#define MC_CMD_CSR_WRITE32_IN_LEN(_numwords) \
- (((_numwords) * 4) + 8)
-#define MC_CMD_CSR_WRITE32_IN_ADDR_OFST 0
-#define MC_CMD_CSR_WRITE32_IN_STEP_OFST 4
-/* Multiple 32bit words of data to write start here */
-#define MC_CMD_CSR_WRITE32_IN_BUFFER_OFST 8
-#define MC_CMD_CSR_WRITE32_OUT_LEN 4
-#define MC_CMD_CSR_WRITE32_OUT_STATUS_OFST 0
-
-/* MC_CMD_JTAG_WORK: (debug, fpga only)
- * Process JTAG work buffer for RBF acceleration.
- *
- * Host: bit count, (up to) 32 words of data to clock out to JTAG
- * (bits 1,0=TMS,TDO for first bit; bits 3,2=TMS,TDO for second bit, etc.)
- * MC: bit count, (up to) 32 words of data clocked in from JTAG
- * (bit 0=TDI for first bit, bit 1=TDI for second bit, etc.; [31:16] unused)
+#define MC_CMD_DBI_WRITE_IN_BYTE_MASK_OFST(n) \
+ (MC_CMD_DBI_WRITE_IN_DBIWROP_OFST + \
+ MC_CMD_DBIWROP_TYPEDEF_BYTE_MASK_OFST + \
+ (n) * MC_CMD_DBIWROP_TYPEDEF_LEN)
+
+#define MC_CMD_DBI_WRITE_IN_VALUE_OFST(n) \
+ (MC_CMD_DBI_WRITE_IN_DBIWROP_OFST + \
+ MC_CMD_DBIWROP_TYPEDEF_VALUE_OFST + \
+ (n) * MC_CMD_DBIWROP_TYPEDEF_LEN)
+
+
+/* Version 2 adds an optional argument to error returns: the errno value
+ * may be followed by the (0-based) number of the first argument that
+ * could not be processed.
+ */
+#define MC_CMD_ERR_ARG_OFST 4
+
+/* No space */
+#define MC_CMD_ERR_ENOSPC 28
+
+/* MCDI_EVENT structuredef */
+#define MCDI_EVENT_LEN 8
+#define MCDI_EVENT_CONT_LBN 32
+#define MCDI_EVENT_CONT_WIDTH 1
+#define MCDI_EVENT_LEVEL_LBN 33
+#define MCDI_EVENT_LEVEL_WIDTH 3
+/* enum: Info. */
+#define MCDI_EVENT_LEVEL_INFO 0x0
+/* enum: Warning. */
+#define MCDI_EVENT_LEVEL_WARN 0x1
+/* enum: Error. */
+#define MCDI_EVENT_LEVEL_ERR 0x2
+/* enum: Fatal. */
+#define MCDI_EVENT_LEVEL_FATAL 0x3
+#define MCDI_EVENT_DATA_OFST 0
+#define MCDI_EVENT_CMDDONE_SEQ_LBN 0
+#define MCDI_EVENT_CMDDONE_SEQ_WIDTH 8
+#define MCDI_EVENT_CMDDONE_DATALEN_LBN 8
+#define MCDI_EVENT_CMDDONE_DATALEN_WIDTH 8
+#define MCDI_EVENT_CMDDONE_ERRNO_LBN 16
+#define MCDI_EVENT_CMDDONE_ERRNO_WIDTH 8
+#define MCDI_EVENT_LINKCHANGE_LP_CAP_LBN 0
+#define MCDI_EVENT_LINKCHANGE_LP_CAP_WIDTH 16
+#define MCDI_EVENT_LINKCHANGE_SPEED_LBN 16
+#define MCDI_EVENT_LINKCHANGE_SPEED_WIDTH 4
+/* enum: 100Mbs */
+#define MCDI_EVENT_LINKCHANGE_SPEED_100M 0x1
+/* enum: 1Gbs */
+#define MCDI_EVENT_LINKCHANGE_SPEED_1G 0x2
+/* enum: 10Gbs */
+#define MCDI_EVENT_LINKCHANGE_SPEED_10G 0x3
+/* enum: 40Gbs */
+#define MCDI_EVENT_LINKCHANGE_SPEED_40G 0x4
+#define MCDI_EVENT_LINKCHANGE_FCNTL_LBN 20
+#define MCDI_EVENT_LINKCHANGE_FCNTL_WIDTH 4
+#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_LBN 24
+#define MCDI_EVENT_LINKCHANGE_LINK_FLAGS_WIDTH 8
+#define MCDI_EVENT_SENSOREVT_MONITOR_LBN 0
+#define MCDI_EVENT_SENSOREVT_MONITOR_WIDTH 8
+#define MCDI_EVENT_SENSOREVT_STATE_LBN 8
+#define MCDI_EVENT_SENSOREVT_STATE_WIDTH 8
+#define MCDI_EVENT_SENSOREVT_VALUE_LBN 16
+#define MCDI_EVENT_SENSOREVT_VALUE_WIDTH 16
+#define MCDI_EVENT_FWALERT_DATA_LBN 8
+#define MCDI_EVENT_FWALERT_DATA_WIDTH 24
+#define MCDI_EVENT_FWALERT_REASON_LBN 0
+#define MCDI_EVENT_FWALERT_REASON_WIDTH 8
+/* enum: SRAM Access. */
+#define MCDI_EVENT_FWALERT_REASON_SRAM_ACCESS 0x1
+#define MCDI_EVENT_FLR_VF_LBN 0
+#define MCDI_EVENT_FLR_VF_WIDTH 8
+#define MCDI_EVENT_TX_ERR_TXQ_LBN 0
+#define MCDI_EVENT_TX_ERR_TXQ_WIDTH 12
+#define MCDI_EVENT_TX_ERR_TYPE_LBN 12
+#define MCDI_EVENT_TX_ERR_TYPE_WIDTH 4
+/* enum: Descriptor loader reported failure */
+#define MCDI_EVENT_TX_ERR_DL_FAIL 0x1
+/* enum: Descriptor ring empty and no EOP seen for packet */
+#define MCDI_EVENT_TX_ERR_NO_EOP 0x2
+/* enum: Overlength packet */
+#define MCDI_EVENT_TX_ERR_2BIG 0x3
+/* enum: Malformed option descriptor */
+#define MCDI_EVENT_TX_BAD_OPTDESC 0x5
+/* enum: Option descriptor part way through a packet */
+#define MCDI_EVENT_TX_OPT_IN_PKT 0x8
+/* enum: DMA or PIO data access error */
+#define MCDI_EVENT_TX_ERR_BAD_DMA_OR_PIO 0x9
+#define MCDI_EVENT_TX_ERR_INFO_LBN 16
+#define MCDI_EVENT_TX_ERR_INFO_WIDTH 16
+#define MCDI_EVENT_TX_FLUSH_TO_DRIVER_LBN 12
+#define MCDI_EVENT_TX_FLUSH_TO_DRIVER_WIDTH 1
+#define MCDI_EVENT_TX_FLUSH_TXQ_LBN 0
+#define MCDI_EVENT_TX_FLUSH_TXQ_WIDTH 12
+#define MCDI_EVENT_PTP_ERR_TYPE_LBN 0
+#define MCDI_EVENT_PTP_ERR_TYPE_WIDTH 8
+/* enum: PLL lost lock */
+#define MCDI_EVENT_PTP_ERR_PLL_LOST 0x1
+/* enum: Filter overflow (PDMA) */
+#define MCDI_EVENT_PTP_ERR_FILTER 0x2
+/* enum: FIFO overflow (FPGA) */
+#define MCDI_EVENT_PTP_ERR_FIFO 0x3
+/* enum: Merge queue overflow */
+#define MCDI_EVENT_PTP_ERR_QUEUE 0x4
+#define MCDI_EVENT_AOE_ERR_TYPE_LBN 0
+#define MCDI_EVENT_AOE_ERR_TYPE_WIDTH 8
+/* enum: AOE failed to load - no valid image? */
+#define MCDI_EVENT_AOE_NO_LOAD 0x1
+/* enum: AOE FC reported an exception */
+#define MCDI_EVENT_AOE_FC_ASSERT 0x2
+/* enum: AOE FC watchdogged */
+#define MCDI_EVENT_AOE_FC_WATCHDOG 0x3
+/* enum: AOE FC failed to start */
+#define MCDI_EVENT_AOE_FC_NO_START 0x4
+/* enum: Generic AOE fault - likely to have been reported via other means too
+ * but intended for use by aoex driver.
+ */
+#define MCDI_EVENT_AOE_FAULT 0x5
+/* enum: Results of reprogramming the CPLD (status in AOE_ERR_DATA) */
+#define MCDI_EVENT_AOE_CPLD_REPROGRAMMED 0x6
+/* enum: AOE loaded successfully */
+#define MCDI_EVENT_AOE_LOAD 0x7
+/* enum: AOE DMA operation completed (LSB of HOST_HANDLE in AOE_ERR_DATA) */
+#define MCDI_EVENT_AOE_DMA 0x8
+/* enum: AOE byteblaster connected/disconnected (Connection status in
+ * AOE_ERR_DATA)
+ */
+#define MCDI_EVENT_AOE_BYTEBLASTER 0x9
+/* enum: DDR ECC status update */
+#define MCDI_EVENT_AOE_DDR_ECC_STATUS 0xa
+#define MCDI_EVENT_AOE_ERR_DATA_LBN 8
+#define MCDI_EVENT_AOE_ERR_DATA_WIDTH 8
+#define MCDI_EVENT_RX_ERR_RXQ_LBN 0
+#define MCDI_EVENT_RX_ERR_RXQ_WIDTH 12
+#define MCDI_EVENT_RX_ERR_TYPE_LBN 12
+#define MCDI_EVENT_RX_ERR_TYPE_WIDTH 4
+#define MCDI_EVENT_RX_ERR_INFO_LBN 16
+#define MCDI_EVENT_RX_ERR_INFO_WIDTH 16
+#define MCDI_EVENT_RX_FLUSH_TO_DRIVER_LBN 12
+#define MCDI_EVENT_RX_FLUSH_TO_DRIVER_WIDTH 1
+#define MCDI_EVENT_RX_FLUSH_RXQ_LBN 0
+#define MCDI_EVENT_RX_FLUSH_RXQ_WIDTH 12
+#define MCDI_EVENT_MC_REBOOT_COUNT_LBN 0
+#define MCDI_EVENT_MC_REBOOT_COUNT_WIDTH 16
+#define MCDI_EVENT_DATA_LBN 0
+#define MCDI_EVENT_DATA_WIDTH 32
+#define MCDI_EVENT_SRC_LBN 36
+#define MCDI_EVENT_SRC_WIDTH 8
+#define MCDI_EVENT_EV_CODE_LBN 60
+#define MCDI_EVENT_EV_CODE_WIDTH 4
+#define MCDI_EVENT_CODE_LBN 44
+#define MCDI_EVENT_CODE_WIDTH 8
+/* enum: Bad assert. */
+#define MCDI_EVENT_CODE_BADSSERT 0x1
+/* enum: PM Notice. */
+#define MCDI_EVENT_CODE_PMNOTICE 0x2
+/* enum: Command done. */
+#define MCDI_EVENT_CODE_CMDDONE 0x3
+/* enum: Link change. */
+#define MCDI_EVENT_CODE_LINKCHANGE 0x4
+/* enum: Sensor Event. */
+#define MCDI_EVENT_CODE_SENSOREVT 0x5
+/* enum: Schedule error. */
+#define MCDI_EVENT_CODE_SCHEDERR 0x6
+/* enum: Reboot. */
+#define MCDI_EVENT_CODE_REBOOT 0x7
+/* enum: Mac stats DMA. */
+#define MCDI_EVENT_CODE_MAC_STATS_DMA 0x8
+/* enum: Firmware alert. */
+#define MCDI_EVENT_CODE_FWALERT 0x9
+/* enum: Function level reset. */
+#define MCDI_EVENT_CODE_FLR 0xa
+/* enum: Transmit error */
+#define MCDI_EVENT_CODE_TX_ERR 0xb
+/* enum: Tx flush has completed */
+#define MCDI_EVENT_CODE_TX_FLUSH 0xc
+/* enum: PTP packet received timestamp */
+#define MCDI_EVENT_CODE_PTP_RX 0xd
+/* enum: PTP NIC failure */
+#define MCDI_EVENT_CODE_PTP_FAULT 0xe
+/* enum: PTP PPS event */
+#define MCDI_EVENT_CODE_PTP_PPS 0xf
+/* enum: Rx flush has completed */
+#define MCDI_EVENT_CODE_RX_FLUSH 0x10
+/* enum: Receive error */
+#define MCDI_EVENT_CODE_RX_ERR 0x11
+/* enum: AOE fault */
+#define MCDI_EVENT_CODE_AOE 0x12
+/* enum: Network port calibration failed (VCAL). */
+#define MCDI_EVENT_CODE_VCAL_FAIL 0x13
+/* enum: HW PPS event */
+#define MCDI_EVENT_CODE_HW_PPS 0x14
+/* enum: The MC has rebooted (huntington and later, siena uses CODE_REBOOT and
+ * a different format)
+ */
+#define MCDI_EVENT_CODE_MC_REBOOT 0x15
+/* enum: the MC has detected a parity error */
+#define MCDI_EVENT_CODE_PAR_ERR 0x16
+/* enum: the MC has detected a correctable error */
+#define MCDI_EVENT_CODE_ECC_CORR_ERR 0x17
+/* enum: the MC has detected an uncorrectable error */
+#define MCDI_EVENT_CODE_ECC_FATAL_ERR 0x18
+/* enum: The MC has entered offline BIST mode */
+#define MCDI_EVENT_CODE_MC_BIST 0x19
+/* enum: PTP tick event providing current NIC time */
+#define MCDI_EVENT_CODE_PTP_TIME 0x1a
+/* enum: Artificial event generated by host and posted via MC for test
+ * purposes.
+ */
+#define MCDI_EVENT_CODE_TESTGEN 0xfa
+#define MCDI_EVENT_CMDDONE_DATA_OFST 0
+#define MCDI_EVENT_CMDDONE_DATA_LBN 0
+#define MCDI_EVENT_CMDDONE_DATA_WIDTH 32
+#define MCDI_EVENT_LINKCHANGE_DATA_OFST 0
+#define MCDI_EVENT_LINKCHANGE_DATA_LBN 0
+#define MCDI_EVENT_LINKCHANGE_DATA_WIDTH 32
+#define MCDI_EVENT_SENSOREVT_DATA_OFST 0
+#define MCDI_EVENT_SENSOREVT_DATA_LBN 0
+#define MCDI_EVENT_SENSOREVT_DATA_WIDTH 32
+#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_OFST 0
+#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_LBN 0
+#define MCDI_EVENT_MAC_STATS_DMA_GENERATION_WIDTH 32
+#define MCDI_EVENT_TX_ERR_DATA_OFST 0
+#define MCDI_EVENT_TX_ERR_DATA_LBN 0
+#define MCDI_EVENT_TX_ERR_DATA_WIDTH 32
+/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the seconds field of
+ * timestamp
+ */
+#define MCDI_EVENT_PTP_SECONDS_OFST 0
+#define MCDI_EVENT_PTP_SECONDS_LBN 0
+#define MCDI_EVENT_PTP_SECONDS_WIDTH 32
+/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the major field of
+ * timestamp
*/
-#define MC_CMD_JTAG_WORK 0x0e
+#define MCDI_EVENT_PTP_MAJOR_OFST 0
+#define MCDI_EVENT_PTP_MAJOR_LBN 0
+#define MCDI_EVENT_PTP_MAJOR_WIDTH 32
+/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the nanoseconds field
+ * of timestamp
+ */
+#define MCDI_EVENT_PTP_NANOSECONDS_OFST 0
+#define MCDI_EVENT_PTP_NANOSECONDS_LBN 0
+#define MCDI_EVENT_PTP_NANOSECONDS_WIDTH 32
+/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the minor field of
+ * timestamp
+ */
+#define MCDI_EVENT_PTP_MINOR_OFST 0
+#define MCDI_EVENT_PTP_MINOR_LBN 0
+#define MCDI_EVENT_PTP_MINOR_WIDTH 32
+/* For CODE_PTP_RX events, the lowest four bytes of sourceUUID from PTP packet
+ */
+#define MCDI_EVENT_PTP_UUID_OFST 0
+#define MCDI_EVENT_PTP_UUID_LBN 0
+#define MCDI_EVENT_PTP_UUID_WIDTH 32
+#define MCDI_EVENT_RX_ERR_DATA_OFST 0
+#define MCDI_EVENT_RX_ERR_DATA_LBN 0
+#define MCDI_EVENT_RX_ERR_DATA_WIDTH 32
+#define MCDI_EVENT_PAR_ERR_DATA_OFST 0
+#define MCDI_EVENT_PAR_ERR_DATA_LBN 0
+#define MCDI_EVENT_PAR_ERR_DATA_WIDTH 32
+#define MCDI_EVENT_ECC_CORR_ERR_DATA_OFST 0
+#define MCDI_EVENT_ECC_CORR_ERR_DATA_LBN 0
+#define MCDI_EVENT_ECC_CORR_ERR_DATA_WIDTH 32
+#define MCDI_EVENT_ECC_FATAL_ERR_DATA_OFST 0
+#define MCDI_EVENT_ECC_FATAL_ERR_DATA_LBN 0
+#define MCDI_EVENT_ECC_FATAL_ERR_DATA_WIDTH 32
+/* For CODE_PTP_TIME events, the major value of the PTP clock */
+#define MCDI_EVENT_PTP_TIME_MAJOR_OFST 0
+#define MCDI_EVENT_PTP_TIME_MAJOR_LBN 0
+#define MCDI_EVENT_PTP_TIME_MAJOR_WIDTH 32
+/* For CODE_PTP_TIME events, bits 19-26 of the minor value of the PTP clock */
+#define MCDI_EVENT_PTP_TIME_MINOR_26_19_LBN 36
+#define MCDI_EVENT_PTP_TIME_MINOR_26_19_WIDTH 8
+
+/* FCDI_EVENT structuredef */
+#define FCDI_EVENT_LEN 8
+#define FCDI_EVENT_CONT_LBN 32
+#define FCDI_EVENT_CONT_WIDTH 1
+#define FCDI_EVENT_LEVEL_LBN 33
+#define FCDI_EVENT_LEVEL_WIDTH 3
+/* enum: Info. */
+#define FCDI_EVENT_LEVEL_INFO 0x0
+/* enum: Warning. */
+#define FCDI_EVENT_LEVEL_WARN 0x1
+/* enum: Error. */
+#define FCDI_EVENT_LEVEL_ERR 0x2
+/* enum: Fatal. */
+#define FCDI_EVENT_LEVEL_FATAL 0x3
+#define FCDI_EVENT_DATA_OFST 0
+#define FCDI_EVENT_LINK_STATE_STATUS_LBN 0
+#define FCDI_EVENT_LINK_STATE_STATUS_WIDTH 1
+#define FCDI_EVENT_LINK_DOWN 0x0 /* enum */
+#define FCDI_EVENT_LINK_UP 0x1 /* enum */
+#define FCDI_EVENT_DATA_LBN 0
+#define FCDI_EVENT_DATA_WIDTH 32
+#define FCDI_EVENT_SRC_LBN 36
+#define FCDI_EVENT_SRC_WIDTH 8
+#define FCDI_EVENT_EV_CODE_LBN 60
+#define FCDI_EVENT_EV_CODE_WIDTH 4
+#define FCDI_EVENT_CODE_LBN 44
+#define FCDI_EVENT_CODE_WIDTH 8
+/* enum: The FC was rebooted. */
+#define FCDI_EVENT_CODE_REBOOT 0x1
+/* enum: Bad assert. */
+#define FCDI_EVENT_CODE_ASSERT 0x2
+/* enum: DDR3 test result. */
+#define FCDI_EVENT_CODE_DDR_TEST_RESULT 0x3
+/* enum: Link status. */
+#define FCDI_EVENT_CODE_LINK_STATE 0x4
+/* enum: A timed read is ready to be serviced. */
+#define FCDI_EVENT_CODE_TIMED_READ 0x5
+/* enum: One or more PPS IN events */
+#define FCDI_EVENT_CODE_PPS_IN 0x6
+/* enum: Tick event from PTP clock */
+#define FCDI_EVENT_CODE_PTP_TICK 0x7
+/* enum: ECC error counters */
+#define FCDI_EVENT_CODE_DDR_ECC_STATUS 0x8
+#define FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0
+#define FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0
+#define FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32
+#define FCDI_EVENT_ASSERT_TYPE_LBN 36
+#define FCDI_EVENT_ASSERT_TYPE_WIDTH 8
+#define FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_LBN 36
+#define FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_WIDTH 8
+#define FCDI_EVENT_DDR_TEST_RESULT_RESULT_OFST 0
+#define FCDI_EVENT_DDR_TEST_RESULT_RESULT_LBN 0
+#define FCDI_EVENT_DDR_TEST_RESULT_RESULT_WIDTH 32
+#define FCDI_EVENT_LINK_STATE_DATA_OFST 0
+#define FCDI_EVENT_LINK_STATE_DATA_LBN 0
+#define FCDI_EVENT_LINK_STATE_DATA_WIDTH 32
+#define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_LBN 36
+#define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_WIDTH 8
+#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_OFST 0
+#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_LBN 0
+#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_WIDTH 32
+
+/* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events
+ * to the MC. Note that this structure | is overlayed over a normal FCDI event
+ * such that bits 32-63 containing | event code, level, source etc remain the
+ * same. In this case the data | field of the header is defined to be the
+ * number of timestamps
+ */
+#define FCDI_EXTENDED_EVENT_PPS_LENMIN 16
+#define FCDI_EXTENDED_EVENT_PPS_LENMAX 248
+#define FCDI_EXTENDED_EVENT_PPS_LEN(num) (8+8*(num))
+/* Number of timestamps following */
+#define FCDI_EXTENDED_EVENT_PPS_COUNT_OFST 0
+#define FCDI_EXTENDED_EVENT_PPS_COUNT_LBN 0
+#define FCDI_EXTENDED_EVENT_PPS_COUNT_WIDTH 32
+/* Seconds field of a timestamp record */
+#define FCDI_EXTENDED_EVENT_PPS_SECONDS_OFST 8
+#define FCDI_EXTENDED_EVENT_PPS_SECONDS_LBN 64
+#define FCDI_EXTENDED_EVENT_PPS_SECONDS_WIDTH 32
+/* Nanoseconds field of a timestamp record */
+#define FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_OFST 12
+#define FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LBN 96
+#define FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_WIDTH 32
+/* Timestamp records comprising the event */
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_OFST 8
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LEN 8
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_OFST 8
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_OFST 12
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MINNUM 1
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM 30
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LBN 64
+#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_WIDTH 64
+
+
+/***********************************/
+/* MC_CMD_READ32
+ * Read multiple 32byte words from MC memory.
+ */
+#define MC_CMD_READ32 0x1
+
+/* MC_CMD_READ32_IN msgrequest */
+#define MC_CMD_READ32_IN_LEN 8
+#define MC_CMD_READ32_IN_ADDR_OFST 0
+#define MC_CMD_READ32_IN_NUMWORDS_OFST 4
+
+/* MC_CMD_READ32_OUT msgresponse */
+#define MC_CMD_READ32_OUT_LENMIN 4
+#define MC_CMD_READ32_OUT_LENMAX 252
+#define MC_CMD_READ32_OUT_LEN(num) (0+4*(num))
+#define MC_CMD_READ32_OUT_BUFFER_OFST 0
+#define MC_CMD_READ32_OUT_BUFFER_LEN 4
+#define MC_CMD_READ32_OUT_BUFFER_MINNUM 1
+#define MC_CMD_READ32_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_WRITE32
+ * Write multiple 32byte words to MC memory.
+ */
+#define MC_CMD_WRITE32 0x2
-/* MC_CMD_STACKINFO: (debug, variadic out)
- * Get stack information
- *
- * Host: nothing
- * MC: (thread ptr, stack size, free space) for each thread in system
+/* MC_CMD_WRITE32_IN msgrequest */
+#define MC_CMD_WRITE32_IN_LENMIN 8
+#define MC_CMD_WRITE32_IN_LENMAX 252
+#define MC_CMD_WRITE32_IN_LEN(num) (4+4*(num))
+#define MC_CMD_WRITE32_IN_ADDR_OFST 0
+#define MC_CMD_WRITE32_IN_BUFFER_OFST 4
+#define MC_CMD_WRITE32_IN_BUFFER_LEN 4
+#define MC_CMD_WRITE32_IN_BUFFER_MINNUM 1
+#define MC_CMD_WRITE32_IN_BUFFER_MAXNUM 62
+
+/* MC_CMD_WRITE32_OUT msgresponse */
+#define MC_CMD_WRITE32_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_COPYCODE
+ * Copy MC code between two locations and jump.
+ */
+#define MC_CMD_COPYCODE 0x3
+
+/* MC_CMD_COPYCODE_IN msgrequest */
+#define MC_CMD_COPYCODE_IN_LEN 16
+/* Source address */
+#define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0
+/* enum: The main image should be entered via a copy of a single word from and
+ * to this address when none of the other magic behaviours are required.
*/
-#define MC_CMD_STACKINFO 0x0f
+#define MC_CMD_COPYCODE_HUNT_NO_MAGIC_ADDR 0x10000
+/* enum: Entering the main image via a copy of a single word from and to this
+ * address indicates that it should not attempt to start the datapath CPUs.
+ * This is useful for certain soft rebooting scenarios. (Huntington only)
+ */
+#define MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR 0x1d0d0
+/* enum: Entering the main image via a copy of a single word from and to this
+ * address indicates that it should not attempt to parse any configuration from
+ * flash. (In addition, the datapath CPUs will not be started, as for
+ * MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR above.) This is useful for
+ * certain soft rebooting scenarios. (Huntington only)
+ */
+#define MC_CMD_COPYCODE_HUNT_IGNORE_CONFIG_MAGIC_ADDR 0x1badc
+/* Destination address */
+#define MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4
+#define MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8
+/* Address of where to jump after copy. */
+#define MC_CMD_COPYCODE_IN_JUMP_OFST 12
+/* enum: Control should return to the caller rather than jumping */
+#define MC_CMD_COPYCODE_JUMP_NONE 0x1
+
+/* MC_CMD_COPYCODE_OUT msgresponse */
+#define MC_CMD_COPYCODE_OUT_LEN 0
-/* MC_CMD_MDIO_READ:
- * MDIO register read
+
+/***********************************/
+/* MC_CMD_SET_FUNC
+ * Select function for function-specific commands.
*/
-#define MC_CMD_MDIO_READ 0x10
-#define MC_CMD_MDIO_READ_IN_LEN 16
-#define MC_CMD_MDIO_READ_IN_BUS_OFST 0
-#define MC_CMD_MDIO_READ_IN_PRTAD_OFST 4
-#define MC_CMD_MDIO_READ_IN_DEVAD_OFST 8
-#define MC_CMD_MDIO_READ_IN_ADDR_OFST 12
-#define MC_CMD_MDIO_READ_OUT_LEN 8
-#define MC_CMD_MDIO_READ_OUT_VALUE_OFST 0
-#define MC_CMD_MDIO_READ_OUT_STATUS_OFST 4
-
-/* MC_CMD_MDIO_WRITE:
- * MDIO register write
+#define MC_CMD_SET_FUNC 0x4
+
+/* MC_CMD_SET_FUNC_IN msgrequest */
+#define MC_CMD_SET_FUNC_IN_LEN 4
+/* Set function */
+#define MC_CMD_SET_FUNC_IN_FUNC_OFST 0
+
+/* MC_CMD_SET_FUNC_OUT msgresponse */
+#define MC_CMD_SET_FUNC_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_BOOT_STATUS
+ * Get the instruction address from which the MC booted.
*/
-#define MC_CMD_MDIO_WRITE 0x11
-#define MC_CMD_MDIO_WRITE_IN_LEN 20
-#define MC_CMD_MDIO_WRITE_IN_BUS_OFST 0
-#define MC_CMD_MDIO_WRITE_IN_PRTAD_OFST 4
-#define MC_CMD_MDIO_WRITE_IN_DEVAD_OFST 8
-#define MC_CMD_MDIO_WRITE_IN_ADDR_OFST 12
-#define MC_CMD_MDIO_WRITE_IN_VALUE_OFST 16
-#define MC_CMD_MDIO_WRITE_OUT_LEN 4
-#define MC_CMD_MDIO_WRITE_OUT_STATUS_OFST 0
+#define MC_CMD_GET_BOOT_STATUS 0x5
+
+/* MC_CMD_GET_BOOT_STATUS_IN msgrequest */
+#define MC_CMD_GET_BOOT_STATUS_IN_LEN 0
+
+/* MC_CMD_GET_BOOT_STATUS_OUT msgresponse */
+#define MC_CMD_GET_BOOT_STATUS_OUT_LEN 8
+/* ?? */
+#define MC_CMD_GET_BOOT_STATUS_OUT_BOOT_OFFSET_OFST 0
+/* enum: indicates that the MC wasn't flash booted */
+#define MC_CMD_GET_BOOT_STATUS_OUT_BOOT_OFFSET_NULL 0xdeadbeef
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_OFST 4
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_WATCHDOG_LBN 0
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_WATCHDOG_WIDTH 1
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_PRIMARY_LBN 1
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_PRIMARY_WIDTH 1
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_BACKUP_LBN 2
+#define MC_CMD_GET_BOOT_STATUS_OUT_FLAGS_BACKUP_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_GET_ASSERTS
+ * Get (and optionally clear) the current assertion status. Only
+ * OUT.GLOBAL_FLAGS is guaranteed to exist in the completion payload. The other
+ * fields will only be present if OUT.GLOBAL_FLAGS != NO_FAILS
+ */
+#define MC_CMD_GET_ASSERTS 0x6
+
+/* MC_CMD_GET_ASSERTS_IN msgrequest */
+#define MC_CMD_GET_ASSERTS_IN_LEN 4
+/* Set to clear assertion */
+#define MC_CMD_GET_ASSERTS_IN_CLEAR_OFST 0
+
+/* MC_CMD_GET_ASSERTS_OUT msgresponse */
+#define MC_CMD_GET_ASSERTS_OUT_LEN 140
+/* Assertion status flag. */
+#define MC_CMD_GET_ASSERTS_OUT_GLOBAL_FLAGS_OFST 0
+/* enum: No assertions have failed. */
+#define MC_CMD_GET_ASSERTS_FLAGS_NO_FAILS 0x1
+/* enum: A system-level assertion has failed. */
+#define MC_CMD_GET_ASSERTS_FLAGS_SYS_FAIL 0x2
+/* enum: A thread-level assertion has failed. */
+#define MC_CMD_GET_ASSERTS_FLAGS_THR_FAIL 0x3
+/* enum: The system was reset by the watchdog. */
+#define MC_CMD_GET_ASSERTS_FLAGS_WDOG_FIRED 0x4
+/* enum: An illegal address trap stopped the system (huntington and later) */
+#define MC_CMD_GET_ASSERTS_FLAGS_ADDR_TRAP 0x5
+/* Failing PC value */
+#define MC_CMD_GET_ASSERTS_OUT_SAVED_PC_OFFS_OFST 4
+/* Saved GP regs */
+#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_OFST 8
+#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_LEN 4
+#define MC_CMD_GET_ASSERTS_OUT_GP_REGS_OFFS_NUM 31
+/* Failing thread address */
+#define MC_CMD_GET_ASSERTS_OUT_THREAD_OFFS_OFST 132
+#define MC_CMD_GET_ASSERTS_OUT_RESERVED_OFST 136
+
+
+/***********************************/
+/* MC_CMD_LOG_CTRL
+ * Configure the output stream for various events and messages.
+ */
+#define MC_CMD_LOG_CTRL 0x7
+
+/* MC_CMD_LOG_CTRL_IN msgrequest */
+#define MC_CMD_LOG_CTRL_IN_LEN 8
+/* Log destination */
+#define MC_CMD_LOG_CTRL_IN_LOG_DEST_OFST 0
+/* enum: UART. */
+#define MC_CMD_LOG_CTRL_IN_LOG_DEST_UART 0x1
+/* enum: Event queue. */
+#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ 0x2
+#define MC_CMD_LOG_CTRL_IN_LOG_DEST_EVQ_OFST 4
+
+/* MC_CMD_LOG_CTRL_OUT msgresponse */
+#define MC_CMD_LOG_CTRL_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_VERSION
+ * Get version information about the MC firmware.
+ */
+#define MC_CMD_GET_VERSION 0x8
+
+/* MC_CMD_GET_VERSION_IN msgrequest */
+#define MC_CMD_GET_VERSION_IN_LEN 0
+
+/* MC_CMD_GET_VERSION_EXT_IN msgrequest: Asks for the extended version */
+#define MC_CMD_GET_VERSION_EXT_IN_LEN 4
+/* placeholder, set to 0 */
+#define MC_CMD_GET_VERSION_EXT_IN_EXT_FLAGS_OFST 0
+
+/* MC_CMD_GET_VERSION_V0_OUT msgresponse: deprecated version format */
+#define MC_CMD_GET_VERSION_V0_OUT_LEN 4
+#define MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0
+/* enum: Reserved version number to indicate "any" version. */
+#define MC_CMD_GET_VERSION_OUT_FIRMWARE_ANY 0xffffffff
+/* enum: Bootrom version value for Siena. */
+#define MC_CMD_GET_VERSION_OUT_FIRMWARE_SIENA_BOOTROM 0xb0070000
+/* enum: Bootrom version value for Huntington. */
+#define MC_CMD_GET_VERSION_OUT_FIRMWARE_HUNT_BOOTROM 0xb0070001
+
+/* MC_CMD_GET_VERSION_OUT msgresponse */
+#define MC_CMD_GET_VERSION_OUT_LEN 32
+/* MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
+/* Enum values, see field(s): */
+/* MC_CMD_GET_VERSION_V0_OUT/MC_CMD_GET_VERSION_OUT_FIRMWARE */
+#define MC_CMD_GET_VERSION_OUT_PCOL_OFST 4
+/* 128bit mask of functions supported by the current firmware */
+#define MC_CMD_GET_VERSION_OUT_SUPPORTED_FUNCS_OFST 8
+#define MC_CMD_GET_VERSION_OUT_SUPPORTED_FUNCS_LEN 16
+#define MC_CMD_GET_VERSION_OUT_VERSION_OFST 24
+#define MC_CMD_GET_VERSION_OUT_VERSION_LEN 8
+#define MC_CMD_GET_VERSION_OUT_VERSION_LO_OFST 24
+#define MC_CMD_GET_VERSION_OUT_VERSION_HI_OFST 28
+
+/* MC_CMD_GET_VERSION_EXT_OUT msgresponse */
+#define MC_CMD_GET_VERSION_EXT_OUT_LEN 48
+/* MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
+/* Enum values, see field(s): */
+/* MC_CMD_GET_VERSION_V0_OUT/MC_CMD_GET_VERSION_OUT_FIRMWARE */
+#define MC_CMD_GET_VERSION_EXT_OUT_PCOL_OFST 4
+/* 128bit mask of functions supported by the current firmware */
+#define MC_CMD_GET_VERSION_EXT_OUT_SUPPORTED_FUNCS_OFST 8
+#define MC_CMD_GET_VERSION_EXT_OUT_SUPPORTED_FUNCS_LEN 16
+#define MC_CMD_GET_VERSION_EXT_OUT_VERSION_OFST 24
+#define MC_CMD_GET_VERSION_EXT_OUT_VERSION_LEN 8
+#define MC_CMD_GET_VERSION_EXT_OUT_VERSION_LO_OFST 24
+#define MC_CMD_GET_VERSION_EXT_OUT_VERSION_HI_OFST 28
+/* extra info */
+#define MC_CMD_GET_VERSION_EXT_OUT_EXTRA_OFST 32
+#define MC_CMD_GET_VERSION_EXT_OUT_EXTRA_LEN 16
+
+
+/***********************************/
+/* MC_CMD_PTP
+ * Perform PTP operation
+ */
+#define MC_CMD_PTP 0xb
+
+/* MC_CMD_PTP_IN msgrequest */
+#define MC_CMD_PTP_IN_LEN 1
+/* PTP operation code */
+#define MC_CMD_PTP_IN_OP_OFST 0
+#define MC_CMD_PTP_IN_OP_LEN 1
+/* enum: Enable PTP packet timestamping operation. */
+#define MC_CMD_PTP_OP_ENABLE 0x1
+/* enum: Disable PTP packet timestamping operation. */
+#define MC_CMD_PTP_OP_DISABLE 0x2
+/* enum: Send a PTP packet. */
+#define MC_CMD_PTP_OP_TRANSMIT 0x3
+/* enum: Read the current NIC time. */
+#define MC_CMD_PTP_OP_READ_NIC_TIME 0x4
+/* enum: Get the current PTP status. */
+#define MC_CMD_PTP_OP_STATUS 0x5
+/* enum: Adjust the PTP NIC's time. */
+#define MC_CMD_PTP_OP_ADJUST 0x6
+/* enum: Synchronize host and NIC time. */
+#define MC_CMD_PTP_OP_SYNCHRONIZE 0x7
+/* enum: Basic manufacturing tests. */
+#define MC_CMD_PTP_OP_MANFTEST_BASIC 0x8
+/* enum: Packet based manufacturing tests. */
+#define MC_CMD_PTP_OP_MANFTEST_PACKET 0x9
+/* enum: Reset some of the PTP related statistics */
+#define MC_CMD_PTP_OP_RESET_STATS 0xa
+/* enum: Debug operations to MC. */
+#define MC_CMD_PTP_OP_DEBUG 0xb
+/* enum: Read an FPGA register */
+#define MC_CMD_PTP_OP_FPGAREAD 0xc
+/* enum: Write an FPGA register */
+#define MC_CMD_PTP_OP_FPGAWRITE 0xd
+/* enum: Apply an offset to the NIC clock */
+#define MC_CMD_PTP_OP_CLOCK_OFFSET_ADJUST 0xe
+/* enum: Change Apply an offset to the NIC clock */
+#define MC_CMD_PTP_OP_CLOCK_FREQ_ADJUST 0xf
+/* enum: Set the MC packet filter VLAN tags for received PTP packets */
+#define MC_CMD_PTP_OP_RX_SET_VLAN_FILTER 0x10
+/* enum: Set the MC packet filter UUID for received PTP packets */
+#define MC_CMD_PTP_OP_RX_SET_UUID_FILTER 0x11
+/* enum: Set the MC packet filter Domain for received PTP packets */
+#define MC_CMD_PTP_OP_RX_SET_DOMAIN_FILTER 0x12
+/* enum: Set the clock source */
+#define MC_CMD_PTP_OP_SET_CLK_SRC 0x13
+/* enum: Reset value of Timer Reg. */
+#define MC_CMD_PTP_OP_RST_CLK 0x14
+/* enum: Enable the forwarding of PPS events to the host */
+#define MC_CMD_PTP_OP_PPS_ENABLE 0x15
+/* enum: Get the time format used by this NIC for PTP operations */
+#define MC_CMD_PTP_OP_GET_TIME_FORMAT 0x16
+/* enum: Get the clock attributes. NOTE- extended version of
+ * MC_CMD_PTP_OP_GET_TIME_FORMAT
+ */
+#define MC_CMD_PTP_OP_GET_ATTRIBUTES 0x16
+/* enum: Get corrections that should be applied to the various different
+ * timestamps
+ */
+#define MC_CMD_PTP_OP_GET_TIMESTAMP_CORRECTIONS 0x17
+/* enum: Subscribe to receive periodic time events indicating the current NIC
+ * time
+ */
+#define MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE 0x18
+/* enum: Unsubscribe to stop receiving time events */
+#define MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE 0x19
+/* enum: PPS based manfacturing tests. Requires PPS output to be looped to PPS
+ * input on the same NIC.
+ */
+#define MC_CMD_PTP_OP_MANFTEST_PPS 0x1a
+/* enum: Above this for future use. */
+#define MC_CMD_PTP_OP_MAX 0x1b
+
+/* MC_CMD_PTP_IN_ENABLE msgrequest */
+#define MC_CMD_PTP_IN_ENABLE_LEN 16
+#define MC_CMD_PTP_IN_CMD_OFST 0
+#define MC_CMD_PTP_IN_PERIPH_ID_OFST 4
+/* Event queue for PTP events */
+#define MC_CMD_PTP_IN_ENABLE_QUEUE_OFST 8
+/* PTP timestamping mode */
+#define MC_CMD_PTP_IN_ENABLE_MODE_OFST 12
+/* enum: PTP, version 1 */
+#define MC_CMD_PTP_MODE_V1 0x0
+/* enum: PTP, version 1, with VLAN headers - deprecated */
+#define MC_CMD_PTP_MODE_V1_VLAN 0x1
+/* enum: PTP, version 2 */
+#define MC_CMD_PTP_MODE_V2 0x2
+/* enum: PTP, version 2, with VLAN headers - deprecated */
+#define MC_CMD_PTP_MODE_V2_VLAN 0x3
+/* enum: PTP, version 2, with improved UUID filtering */
+#define MC_CMD_PTP_MODE_V2_ENHANCED 0x4
+/* enum: FCoE (seconds and microseconds) */
+#define MC_CMD_PTP_MODE_FCOE 0x5
+
+/* MC_CMD_PTP_IN_DISABLE msgrequest */
+#define MC_CMD_PTP_IN_DISABLE_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_TRANSMIT msgrequest */
+#define MC_CMD_PTP_IN_TRANSMIT_LENMIN 13
+#define MC_CMD_PTP_IN_TRANSMIT_LENMAX 252
+#define MC_CMD_PTP_IN_TRANSMIT_LEN(num) (12+1*(num))
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Transmit packet length */
+#define MC_CMD_PTP_IN_TRANSMIT_LENGTH_OFST 8
+/* Transmit packet data */
+#define MC_CMD_PTP_IN_TRANSMIT_PACKET_OFST 12
+#define MC_CMD_PTP_IN_TRANSMIT_PACKET_LEN 1
+#define MC_CMD_PTP_IN_TRANSMIT_PACKET_MINNUM 1
+#define MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM 240
+
+/* MC_CMD_PTP_IN_READ_NIC_TIME msgrequest */
+#define MC_CMD_PTP_IN_READ_NIC_TIME_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_STATUS msgrequest */
+#define MC_CMD_PTP_IN_STATUS_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_ADJUST msgrequest */
+#define MC_CMD_PTP_IN_ADJUST_LEN 24
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Frequency adjustment 40 bit fixed point ns */
+#define MC_CMD_PTP_IN_ADJUST_FREQ_OFST 8
+#define MC_CMD_PTP_IN_ADJUST_FREQ_LEN 8
+#define MC_CMD_PTP_IN_ADJUST_FREQ_LO_OFST 8
+#define MC_CMD_PTP_IN_ADJUST_FREQ_HI_OFST 12
+/* enum: Number of fractional bits in frequency adjustment */
+#define MC_CMD_PTP_IN_ADJUST_BITS 0x28
+/* Time adjustment in seconds */
+#define MC_CMD_PTP_IN_ADJUST_SECONDS_OFST 16
+/* Time adjustment major value */
+#define MC_CMD_PTP_IN_ADJUST_MAJOR_OFST 16
+/* Time adjustment in nanoseconds */
+#define MC_CMD_PTP_IN_ADJUST_NANOSECONDS_OFST 20
+/* Time adjustment minor value */
+#define MC_CMD_PTP_IN_ADJUST_MINOR_OFST 20
+
+/* MC_CMD_PTP_IN_SYNCHRONIZE msgrequest */
+#define MC_CMD_PTP_IN_SYNCHRONIZE_LEN 20
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Number of time readings to capture */
+#define MC_CMD_PTP_IN_SYNCHRONIZE_NUMTIMESETS_OFST 8
+/* Host address in which to write "synchronization started" indication (64
+ * bits)
+ */
+#define MC_CMD_PTP_IN_SYNCHRONIZE_START_ADDR_OFST 12
+#define MC_CMD_PTP_IN_SYNCHRONIZE_START_ADDR_LEN 8
+#define MC_CMD_PTP_IN_SYNCHRONIZE_START_ADDR_LO_OFST 12
+#define MC_CMD_PTP_IN_SYNCHRONIZE_START_ADDR_HI_OFST 16
+
+/* MC_CMD_PTP_IN_MANFTEST_BASIC msgrequest */
+#define MC_CMD_PTP_IN_MANFTEST_BASIC_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_MANFTEST_PACKET msgrequest */
+#define MC_CMD_PTP_IN_MANFTEST_PACKET_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Enable or disable packet testing */
+#define MC_CMD_PTP_IN_MANFTEST_PACKET_TEST_ENABLE_OFST 8
+
+/* MC_CMD_PTP_IN_RESET_STATS msgrequest */
+#define MC_CMD_PTP_IN_RESET_STATS_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* Reset PTP statistics */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_DEBUG msgrequest */
+#define MC_CMD_PTP_IN_DEBUG_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Debug operations */
+#define MC_CMD_PTP_IN_DEBUG_DEBUG_PARAM_OFST 8
+
+/* MC_CMD_PTP_IN_FPGAREAD msgrequest */
+#define MC_CMD_PTP_IN_FPGAREAD_LEN 16
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+#define MC_CMD_PTP_IN_FPGAREAD_ADDR_OFST 8
+#define MC_CMD_PTP_IN_FPGAREAD_NUMBYTES_OFST 12
+
+/* MC_CMD_PTP_IN_FPGAWRITE msgrequest */
+#define MC_CMD_PTP_IN_FPGAWRITE_LENMIN 13
+#define MC_CMD_PTP_IN_FPGAWRITE_LENMAX 252
+#define MC_CMD_PTP_IN_FPGAWRITE_LEN(num) (12+1*(num))
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+#define MC_CMD_PTP_IN_FPGAWRITE_ADDR_OFST 8
+#define MC_CMD_PTP_IN_FPGAWRITE_BUFFER_OFST 12
+#define MC_CMD_PTP_IN_FPGAWRITE_BUFFER_LEN 1
+#define MC_CMD_PTP_IN_FPGAWRITE_BUFFER_MINNUM 1
+#define MC_CMD_PTP_IN_FPGAWRITE_BUFFER_MAXNUM 240
+
+/* MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST msgrequest */
+#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_LEN 16
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Time adjustment in seconds */
+#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_SECONDS_OFST 8
+/* Time adjustment major value */
+#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_MAJOR_OFST 8
+/* Time adjustment in nanoseconds */
+#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_NANOSECONDS_OFST 12
+/* Time adjustment minor value */
+#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_MINOR_OFST 12
+
+/* MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST msgrequest */
+#define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_LEN 16
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Frequency adjustment 40 bit fixed point ns */
+#define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_FREQ_OFST 8
+#define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_FREQ_LEN 8
+#define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_FREQ_LO_OFST 8
+#define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_FREQ_HI_OFST 12
+/* enum: Number of fractional bits in frequency adjustment */
+/* MC_CMD_PTP_IN_ADJUST_BITS 0x28 */
+
+/* MC_CMD_PTP_IN_RX_SET_VLAN_FILTER msgrequest */
+#define MC_CMD_PTP_IN_RX_SET_VLAN_FILTER_LEN 24
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Number of VLAN tags, 0 if not VLAN */
+#define MC_CMD_PTP_IN_RX_SET_VLAN_FILTER_NUM_VLAN_TAGS_OFST 8
+/* Set of VLAN tags to filter against */
+#define MC_CMD_PTP_IN_RX_SET_VLAN_FILTER_VLAN_TAG_OFST 12
+#define MC_CMD_PTP_IN_RX_SET_VLAN_FILTER_VLAN_TAG_LEN 4
+#define MC_CMD_PTP_IN_RX_SET_VLAN_FILTER_VLAN_TAG_NUM 3
+
+/* MC_CMD_PTP_IN_RX_SET_UUID_FILTER msgrequest */
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_LEN 20
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* 1 to enable UUID filtering, 0 to disable */
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_ENABLE_OFST 8
+/* UUID to filter against */
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_UUID_OFST 12
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_UUID_LEN 8
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_UUID_LO_OFST 12
+#define MC_CMD_PTP_IN_RX_SET_UUID_FILTER_UUID_HI_OFST 16
+
+/* MC_CMD_PTP_IN_RX_SET_DOMAIN_FILTER msgrequest */
+#define MC_CMD_PTP_IN_RX_SET_DOMAIN_FILTER_LEN 16
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* 1 to enable Domain filtering, 0 to disable */
+#define MC_CMD_PTP_IN_RX_SET_DOMAIN_FILTER_ENABLE_OFST 8
+/* Domain number to filter against */
+#define MC_CMD_PTP_IN_RX_SET_DOMAIN_FILTER_DOMAIN_OFST 12
+
+/* MC_CMD_PTP_IN_SET_CLK_SRC msgrequest */
+#define MC_CMD_PTP_IN_SET_CLK_SRC_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Set the clock source. */
+#define MC_CMD_PTP_IN_SET_CLK_SRC_CLK_OFST 8
+/* enum: Internal. */
+#define MC_CMD_PTP_CLK_SRC_INTERNAL 0x0
+/* enum: External. */
+#define MC_CMD_PTP_CLK_SRC_EXTERNAL 0x1
+
+/* MC_CMD_PTP_IN_RST_CLK msgrequest */
+#define MC_CMD_PTP_IN_RST_CLK_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* Reset value of Timer Reg. */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_PPS_ENABLE msgrequest */
+#define MC_CMD_PTP_IN_PPS_ENABLE_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* Enable or disable */
+#define MC_CMD_PTP_IN_PPS_ENABLE_OP_OFST 4
+/* enum: Enable */
+#define MC_CMD_PTP_ENABLE_PPS 0x0
+/* enum: Disable */
+#define MC_CMD_PTP_DISABLE_PPS 0x1
+/* Queue id to send events back */
+#define MC_CMD_PTP_IN_PPS_ENABLE_QUEUE_ID_OFST 8
+
+/* MC_CMD_PTP_IN_GET_TIME_FORMAT msgrequest */
+#define MC_CMD_PTP_IN_GET_TIME_FORMAT_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_GET_ATTRIBUTES msgrequest */
+#define MC_CMD_PTP_IN_GET_ATTRIBUTES_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS msgrequest */
+#define MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS_LEN 8
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+
+/* MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE msgrequest */
+#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Event queue to send PTP time events to */
+#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE_OFST 8
+
+/* MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE msgrequest */
+#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN 16
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* Unsubscribe options */
+#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL_OFST 8
+/* enum: Unsubscribe a single queue */
+#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE 0x0
+/* enum: Unsubscribe all queues */
+#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_ALL 0x1
+/* Event queue ID */
+#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_OFST 12
+
+/* MC_CMD_PTP_IN_MANFTEST_PPS msgrequest */
+#define MC_CMD_PTP_IN_MANFTEST_PPS_LEN 12
+/* MC_CMD_PTP_IN_CMD_OFST 0 */
+/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/* 1 to enable PPS test mode, 0 to disable and return result. */
+#define MC_CMD_PTP_IN_MANFTEST_PPS_TEST_ENABLE_OFST 8
+
+/* MC_CMD_PTP_OUT msgresponse */
+#define MC_CMD_PTP_OUT_LEN 0
+
+/* MC_CMD_PTP_OUT_TRANSMIT msgresponse */
+#define MC_CMD_PTP_OUT_TRANSMIT_LEN 8
+/* Value of seconds timestamp */
+#define MC_CMD_PTP_OUT_TRANSMIT_SECONDS_OFST 0
+/* Timestamp major value */
+#define MC_CMD_PTP_OUT_TRANSMIT_MAJOR_OFST 0
+/* Value of nanoseconds timestamp */
+#define MC_CMD_PTP_OUT_TRANSMIT_NANOSECONDS_OFST 4
+/* Timestamp minor value */
+#define MC_CMD_PTP_OUT_TRANSMIT_MINOR_OFST 4
+
+/* MC_CMD_PTP_OUT_TIME_EVENT_SUBSCRIBE msgresponse */
+#define MC_CMD_PTP_OUT_TIME_EVENT_SUBSCRIBE_LEN 0
+
+/* MC_CMD_PTP_OUT_TIME_EVENT_UNSUBSCRIBE msgresponse */
+#define MC_CMD_PTP_OUT_TIME_EVENT_UNSUBSCRIBE_LEN 0
+
+/* MC_CMD_PTP_OUT_READ_NIC_TIME msgresponse */
+#define MC_CMD_PTP_OUT_READ_NIC_TIME_LEN 8
+/* Value of seconds timestamp */
+#define MC_CMD_PTP_OUT_READ_NIC_TIME_SECONDS_OFST 0
+/* Timestamp major value */
+#define MC_CMD_PTP_OUT_READ_NIC_TIME_MAJOR_OFST 0
+/* Value of nanoseconds timestamp */
+#define MC_CMD_PTP_OUT_READ_NIC_TIME_NANOSECONDS_OFST 4
+/* Timestamp minor value */
+#define MC_CMD_PTP_OUT_READ_NIC_TIME_MINOR_OFST 4
+
+/* MC_CMD_PTP_OUT_STATUS msgresponse */
+#define MC_CMD_PTP_OUT_STATUS_LEN 64
+/* Frequency of NIC's hardware clock */
+#define MC_CMD_PTP_OUT_STATUS_CLOCK_FREQ_OFST 0
+/* Number of packets transmitted and timestamped */
+#define MC_CMD_PTP_OUT_STATUS_STATS_TX_OFST 4
+/* Number of packets received and timestamped */
+#define MC_CMD_PTP_OUT_STATUS_STATS_RX_OFST 8
+/* Number of packets timestamped by the FPGA */
+#define MC_CMD_PTP_OUT_STATUS_STATS_TS_OFST 12
+/* Number of packets filter matched */
+#define MC_CMD_PTP_OUT_STATUS_STATS_FM_OFST 16
+/* Number of packets not filter matched */
+#define MC_CMD_PTP_OUT_STATUS_STATS_NFM_OFST 20
+/* Number of PPS overflows (noise on input?) */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFLOW_OFST 24
+/* Number of PPS bad periods */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_BAD_OFST 28
+/* Minimum period of PPS pulse in nanoseconds */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MIN_OFST 32
+/* Maximum period of PPS pulse in nanoseconds */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MAX_OFST 36
+/* Last period of PPS pulse in nanoseconds */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_LAST_OFST 40
+/* Mean period of PPS pulse in nanoseconds */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MEAN_OFST 44
+/* Minimum offset of PPS pulse in nanoseconds (signed) */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MIN_OFST 48
+/* Maximum offset of PPS pulse in nanoseconds (signed) */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MAX_OFST 52
+/* Last offset of PPS pulse in nanoseconds (signed) */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_LAST_OFST 56
+/* Mean offset of PPS pulse in nanoseconds (signed) */
+#define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MEAN_OFST 60
+
+/* MC_CMD_PTP_OUT_SYNCHRONIZE msgresponse */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_LENMIN 20
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX 240
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_LEN(num) (0+20*(num))
+/* A set of host and NIC times */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_OFST 0
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_LEN 20
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MINNUM 1
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM 12
+/* Host time immediately before NIC's hardware clock read */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_HOSTSTART_OFST 0
+/* Value of seconds timestamp */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_SECONDS_OFST 4
+/* Timestamp major value */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_MAJOR_OFST 4
+/* Value of nanoseconds timestamp */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_NANOSECONDS_OFST 8
+/* Timestamp minor value */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_MINOR_OFST 8
+/* Host time immediately after NIC's hardware clock read */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_HOSTEND_OFST 12
+/* Number of nanoseconds waited after reading NIC's hardware clock */
+#define MC_CMD_PTP_OUT_SYNCHRONIZE_WAITNS_OFST 16
+
+/* MC_CMD_PTP_OUT_MANFTEST_BASIC msgresponse */
+#define MC_CMD_PTP_OUT_MANFTEST_BASIC_LEN 8
+/* Results of testing */
+#define MC_CMD_PTP_OUT_MANFTEST_BASIC_TEST_RESULT_OFST 0
+/* enum: Successful test */
+#define MC_CMD_PTP_MANF_SUCCESS 0x0
+/* enum: FPGA load failed */
+#define MC_CMD_PTP_MANF_FPGA_LOAD 0x1
+/* enum: FPGA version invalid */
+#define MC_CMD_PTP_MANF_FPGA_VERSION 0x2
+/* enum: FPGA registers incorrect */
+#define MC_CMD_PTP_MANF_FPGA_REGISTERS 0x3
+/* enum: Oscillator possibly not working? */
+#define MC_CMD_PTP_MANF_OSCILLATOR 0x4
+/* enum: Timestamps not increasing */
+#define MC_CMD_PTP_MANF_TIMESTAMPS 0x5
+/* enum: Mismatched packet count */
+#define MC_CMD_PTP_MANF_PACKET_COUNT 0x6
+/* enum: Mismatched packet count (Siena filter and FPGA) */
+#define MC_CMD_PTP_MANF_FILTER_COUNT 0x7
+/* enum: Not enough packets to perform timestamp check */
+#define MC_CMD_PTP_MANF_PACKET_ENOUGH 0x8
+/* enum: Timestamp trigger GPIO not working */
+#define MC_CMD_PTP_MANF_GPIO_TRIGGER 0x9
+/* enum: Insufficient PPS events to perform checks */
+#define MC_CMD_PTP_MANF_PPS_ENOUGH 0xa
+/* enum: PPS time event period not sufficiently close to 1s. */
+#define MC_CMD_PTP_MANF_PPS_PERIOD 0xb
+/* enum: PPS time event nS reading not sufficiently close to zero. */
+#define MC_CMD_PTP_MANF_PPS_NS 0xc
+/* enum: PTP peripheral registers incorrect */
+#define MC_CMD_PTP_MANF_REGISTERS 0xd
+/* enum: Failed to read time from PTP peripheral */
+#define MC_CMD_PTP_MANF_CLOCK_READ 0xe
+/* Presence of external oscillator */
+#define MC_CMD_PTP_OUT_MANFTEST_BASIC_TEST_EXTOSC_OFST 4
+
+/* MC_CMD_PTP_OUT_MANFTEST_PACKET msgresponse */
+#define MC_CMD_PTP_OUT_MANFTEST_PACKET_LEN 12
+/* Results of testing */
+#define MC_CMD_PTP_OUT_MANFTEST_PACKET_TEST_RESULT_OFST 0
+/* Number of packets received by FPGA */
+#define MC_CMD_PTP_OUT_MANFTEST_PACKET_TEST_FPGACOUNT_OFST 4
+/* Number of packets received by Siena filters */
+#define MC_CMD_PTP_OUT_MANFTEST_PACKET_TEST_FILTERCOUNT_OFST 8
+
+/* MC_CMD_PTP_OUT_FPGAREAD msgresponse */
+#define MC_CMD_PTP_OUT_FPGAREAD_LENMIN 1
+#define MC_CMD_PTP_OUT_FPGAREAD_LENMAX 252
+#define MC_CMD_PTP_OUT_FPGAREAD_LEN(num) (0+1*(num))
+#define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_OFST 0
+#define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_LEN 1
+#define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_MINNUM 1
+#define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_MAXNUM 252
+
+/* MC_CMD_PTP_OUT_GET_TIME_FORMAT msgresponse */
+#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_LEN 4
+/* Time format required/used by for this NIC. Applies to all PTP MCDI
+ * operations that pass times between the host and firmware. If this operation
+ * is not supported (older firmware) a format of seconds and nanoseconds should
+ * be assumed.
+ */
+#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_FORMAT_OFST 0
+/* enum: Times are in seconds and nanoseconds */
+#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_SECONDS_NANOSECONDS 0x0
+/* enum: Major register has units of 16 second per tick, minor 8 ns per tick */
+#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_16SECONDS_8NANOSECONDS 0x1
+/* enum: Major register has units of seconds, minor 2^-27s per tick */
+#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_SECONDS_27FRACTION 0x2
+
+/* MC_CMD_PTP_OUT_GET_ATTRIBUTES msgresponse */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN 8
+/* Time format required/used by for this NIC. Applies to all PTP MCDI
+ * operations that pass times between the host and firmware. If this operation
+ * is not supported (older firmware) a format of seconds and nanoseconds should
+ * be assumed.
+ */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_TIME_FORMAT_OFST 0
+/* enum: Times are in seconds and nanoseconds */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS 0x0
+/* enum: Major register has units of 16 second per tick, minor 8 ns per tick */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_16SECONDS_8NANOSECONDS 0x1
+/* enum: Major register has units of seconds, minor 2^-27s per tick */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION 0x2
+/* Minimum acceptable value for a corrected synchronization timeset. When
+ * comparing host and NIC clock times, the MC returns a set of samples that
+ * contain the host start and end time, the MC time when the host start was
+ * detected and the time the MC waited between reading the time and detecting
+ * the host end. The corrected sync window is the difference between the host
+ * end and start times minus the time that the MC waited for host end.
+ */
+#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN_OFST 4
+
+/* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS msgresponse */
+#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN 16
+/* Uncorrected error on transmit timestamps in NIC clock format */
+#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT_OFST 0
+/* Uncorrected error on receive timestamps in NIC clock format */
+#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE_OFST 4
+/* Uncorrected error on PPS output in NIC clock format */
+#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT_OFST 8
+/* Uncorrected error on PPS input in NIC clock format */
+#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN_OFST 12
+
+/* MC_CMD_PTP_OUT_MANFTEST_PPS msgresponse */
+#define MC_CMD_PTP_OUT_MANFTEST_PPS_LEN 4
+/* Results of testing */
+#define MC_CMD_PTP_OUT_MANFTEST_PPS_TEST_RESULT_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_PTP_OUT_MANFTEST_BASIC/TEST_RESULT */
+
+
+/***********************************/
+/* MC_CMD_CSR_READ32
+ * Read 32bit words from the indirect memory map.
+ */
+#define MC_CMD_CSR_READ32 0xc
+
+/* MC_CMD_CSR_READ32_IN msgrequest */
+#define MC_CMD_CSR_READ32_IN_LEN 12
+/* Address */
+#define MC_CMD_CSR_READ32_IN_ADDR_OFST 0
+#define MC_CMD_CSR_READ32_IN_STEP_OFST 4
+#define MC_CMD_CSR_READ32_IN_NUMWORDS_OFST 8
+
+/* MC_CMD_CSR_READ32_OUT msgresponse */
+#define MC_CMD_CSR_READ32_OUT_LENMIN 4
+#define MC_CMD_CSR_READ32_OUT_LENMAX 252
+#define MC_CMD_CSR_READ32_OUT_LEN(num) (0+4*(num))
+/* The last dword is the status, not a value read */
+#define MC_CMD_CSR_READ32_OUT_BUFFER_OFST 0
+#define MC_CMD_CSR_READ32_OUT_BUFFER_LEN 4
+#define MC_CMD_CSR_READ32_OUT_BUFFER_MINNUM 1
+#define MC_CMD_CSR_READ32_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_CSR_WRITE32
+ * Write 32bit dwords to the indirect memory map.
+ */
+#define MC_CMD_CSR_WRITE32 0xd
+
+/* MC_CMD_CSR_WRITE32_IN msgrequest */
+#define MC_CMD_CSR_WRITE32_IN_LENMIN 12
+#define MC_CMD_CSR_WRITE32_IN_LENMAX 252
+#define MC_CMD_CSR_WRITE32_IN_LEN(num) (8+4*(num))
+/* Address */
+#define MC_CMD_CSR_WRITE32_IN_ADDR_OFST 0
+#define MC_CMD_CSR_WRITE32_IN_STEP_OFST 4
+#define MC_CMD_CSR_WRITE32_IN_BUFFER_OFST 8
+#define MC_CMD_CSR_WRITE32_IN_BUFFER_LEN 4
+#define MC_CMD_CSR_WRITE32_IN_BUFFER_MINNUM 1
+#define MC_CMD_CSR_WRITE32_IN_BUFFER_MAXNUM 61
+
+/* MC_CMD_CSR_WRITE32_OUT msgresponse */
+#define MC_CMD_CSR_WRITE32_OUT_LEN 4
+#define MC_CMD_CSR_WRITE32_OUT_STATUS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_HP
+ * These commands are used for HP related features. They are grouped under one
+ * MCDI command to avoid creating too many MCDI commands.
+ */
+#define MC_CMD_HP 0x54
+
+/* MC_CMD_HP_IN msgrequest */
+#define MC_CMD_HP_IN_LEN 16
+/* HP OCSD sub-command. When address is not NULL, request activation of OCSD at
+ * the specified address with the specified interval.When address is NULL,
+ * INTERVAL is interpreted as a command: 0: stop OCSD / 1: Report OCSD current
+ * state / 2: (debug) Show temperature reported by one of the supported
+ * sensors.
+ */
+#define MC_CMD_HP_IN_SUBCMD_OFST 0
+/* enum: OCSD (Option Card Sensor Data) sub-command. */
+#define MC_CMD_HP_IN_OCSD_SUBCMD 0x0
+/* enum: Last known valid HP sub-command. */
+#define MC_CMD_HP_IN_LAST_SUBCMD 0x0
+/* The address to the array of sensor fields. (Or NULL to use a sub-command.)
+ */
+#define MC_CMD_HP_IN_OCSD_ADDR_OFST 4
+#define MC_CMD_HP_IN_OCSD_ADDR_LEN 8
+#define MC_CMD_HP_IN_OCSD_ADDR_LO_OFST 4
+#define MC_CMD_HP_IN_OCSD_ADDR_HI_OFST 8
+/* The requested update interval, in seconds. (Or the sub-command if ADDR is
+ * NULL.)
+ */
+#define MC_CMD_HP_IN_OCSD_INTERVAL_OFST 12
+
+/* MC_CMD_HP_OUT msgresponse */
+#define MC_CMD_HP_OUT_LEN 4
+#define MC_CMD_HP_OUT_OCSD_STATUS_OFST 0
+/* enum: OCSD stopped for this card. */
+#define MC_CMD_HP_OUT_OCSD_STOPPED 0x1
+/* enum: OCSD was successfully started with the address provided. */
+#define MC_CMD_HP_OUT_OCSD_STARTED 0x2
+/* enum: OCSD was already started for this card. */
+#define MC_CMD_HP_OUT_OCSD_ALREADY_STARTED 0x3
+
+
+/***********************************/
+/* MC_CMD_STACKINFO
+ * Get stack information.
+ */
+#define MC_CMD_STACKINFO 0xf
+
+/* MC_CMD_STACKINFO_IN msgrequest */
+#define MC_CMD_STACKINFO_IN_LEN 0
+
+/* MC_CMD_STACKINFO_OUT msgresponse */
+#define MC_CMD_STACKINFO_OUT_LENMIN 12
+#define MC_CMD_STACKINFO_OUT_LENMAX 252
+#define MC_CMD_STACKINFO_OUT_LEN(num) (0+12*(num))
+/* (thread ptr, stack size, free space) for each thread in system */
+#define MC_CMD_STACKINFO_OUT_THREAD_INFO_OFST 0
+#define MC_CMD_STACKINFO_OUT_THREAD_INFO_LEN 12
+#define MC_CMD_STACKINFO_OUT_THREAD_INFO_MINNUM 1
+#define MC_CMD_STACKINFO_OUT_THREAD_INFO_MAXNUM 21
+
-/* By default all the MCDI MDIO operations perform clause45 mode.
- * If you want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
+/***********************************/
+/* MC_CMD_MDIO_READ
+ * MDIO register read.
*/
-#define MC_CMD_MDIO_CLAUSE22 32
+#define MC_CMD_MDIO_READ 0x10
+
+/* MC_CMD_MDIO_READ_IN msgrequest */
+#define MC_CMD_MDIO_READ_IN_LEN 16
+/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
+ * external devices.
+ */
+#define MC_CMD_MDIO_READ_IN_BUS_OFST 0
+/* enum: Internal. */
+#define MC_CMD_MDIO_BUS_INTERNAL 0x0
+/* enum: External. */
+#define MC_CMD_MDIO_BUS_EXTERNAL 0x1
+/* Port address */
+#define MC_CMD_MDIO_READ_IN_PRTAD_OFST 4
+/* Device Address or clause 22. */
+#define MC_CMD_MDIO_READ_IN_DEVAD_OFST 8
+/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
+ * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
+ */
+#define MC_CMD_MDIO_CLAUSE22 0x20
+/* Address */
+#define MC_CMD_MDIO_READ_IN_ADDR_OFST 12
+
+/* MC_CMD_MDIO_READ_OUT msgresponse */
+#define MC_CMD_MDIO_READ_OUT_LEN 8
+/* Value */
+#define MC_CMD_MDIO_READ_OUT_VALUE_OFST 0
+/* Status the MDIO commands return the raw status bits from the MDIO block. A
+ * "good" transaction should have the DONE bit set and all other bits clear.
+ */
+#define MC_CMD_MDIO_READ_OUT_STATUS_OFST 4
+/* enum: Good. */
+#define MC_CMD_MDIO_STATUS_GOOD 0x8
+
-/* There are two MDIO buses: one for the internal PHY, and one for external
- * devices.
+/***********************************/
+/* MC_CMD_MDIO_WRITE
+ * MDIO register write.
*/
-#define MC_CMD_MDIO_BUS_INTERNAL 0
-#define MC_CMD_MDIO_BUS_EXTERNAL 1
+#define MC_CMD_MDIO_WRITE 0x11
-/* The MDIO commands return the raw status bits from the MDIO block. A "good"
- * transaction should have the DONE bit set and all other bits clear.
+/* MC_CMD_MDIO_WRITE_IN msgrequest */
+#define MC_CMD_MDIO_WRITE_IN_LEN 20
+/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
+ * external devices.
+ */
+#define MC_CMD_MDIO_WRITE_IN_BUS_OFST 0
+/* enum: Internal. */
+/* MC_CMD_MDIO_BUS_INTERNAL 0x0 */
+/* enum: External. */
+/* MC_CMD_MDIO_BUS_EXTERNAL 0x1 */
+/* Port address */
+#define MC_CMD_MDIO_WRITE_IN_PRTAD_OFST 4
+/* Device Address or clause 22. */
+#define MC_CMD_MDIO_WRITE_IN_DEVAD_OFST 8
+/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
+ * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
+ */
+/* MC_CMD_MDIO_CLAUSE22 0x20 */
+/* Address */
+#define MC_CMD_MDIO_WRITE_IN_ADDR_OFST 12
+/* Value */
+#define MC_CMD_MDIO_WRITE_IN_VALUE_OFST 16
+
+/* MC_CMD_MDIO_WRITE_OUT msgresponse */
+#define MC_CMD_MDIO_WRITE_OUT_LEN 4
+/* Status; the MDIO commands return the raw status bits from the MDIO block. A
+ * "good" transaction should have the DONE bit set and all other bits clear.
*/
-#define MC_CMD_MDIO_STATUS_GOOD 0x08
+#define MC_CMD_MDIO_WRITE_OUT_STATUS_OFST 0
+/* enum: Good. */
+/* MC_CMD_MDIO_STATUS_GOOD 0x8 */
-/* MC_CMD_DBI_WRITE: (debug)
- * Write DBI register(s)
- *
- * Host: address, byte-enables (and VF selection, and cs2 flag),
- * value [,address ...]
- * MC: nothing
+/***********************************/
+/* MC_CMD_DBI_WRITE
+ * Write DBI register(s).
*/
#define MC_CMD_DBI_WRITE 0x12
-#define MC_CMD_DBI_WRITE_IN_LEN(_numwords) \
- (12 * (_numwords))
-#define MC_CMD_DBI_WRITE_IN_ADDRESS_OFST(_word) \
- (((_word) * 12) + 0)
-#define MC_CMD_DBI_WRITE_IN_BYTE_MASK_OFST(_word) \
- (((_word) * 12) + 4)
-#define MC_CMD_DBI_WRITE_IN_VALUE_OFST(_word) \
- (((_word) * 12) + 8)
-#define MC_CMD_DBI_WRITE_OUT_LEN 0
-
-/* MC_CMD_DBI_READ: (debug)
- * Read DBI register(s)
- *
- * Host: address, [,address ...]
- * MC: value [,value ...]
- * (note: this does not support reading from VFs, but is retained for backwards
- * compatibility; see MC_CMD_DBI_READX below)
- */
-#define MC_CMD_DBI_READ 0x13
-#define MC_CMD_DBI_READ_IN_LEN(_numwords) \
- (4 * (_numwords))
-#define MC_CMD_DBI_READ_OUT_LEN(_numwords) \
- (4 * (_numwords))
-
-/* MC_CMD_PORT_READ32: (debug)
- * Read a 32-bit register from the indirect port register map.
- *
- * The port to access is implied by the Shared memory channel used.
+
+/* MC_CMD_DBI_WRITE_IN msgrequest */
+#define MC_CMD_DBI_WRITE_IN_LENMIN 12
+#define MC_CMD_DBI_WRITE_IN_LENMAX 252
+#define MC_CMD_DBI_WRITE_IN_LEN(num) (0+12*(num))
+/* Each write op consists of an address (offset 0), byte enable/VF/CS2 (offset
+ * 32) and value (offset 64). See MC_CMD_DBIWROP_TYPEDEF.
+ */
+#define MC_CMD_DBI_WRITE_IN_DBIWROP_OFST 0
+#define MC_CMD_DBI_WRITE_IN_DBIWROP_LEN 12
+#define MC_CMD_DBI_WRITE_IN_DBIWROP_MINNUM 1
+#define MC_CMD_DBI_WRITE_IN_DBIWROP_MAXNUM 21
+
+/* MC_CMD_DBI_WRITE_OUT msgresponse */
+#define MC_CMD_DBI_WRITE_OUT_LEN 0
+
+/* MC_CMD_DBIWROP_TYPEDEF structuredef */
+#define MC_CMD_DBIWROP_TYPEDEF_LEN 12
+#define MC_CMD_DBIWROP_TYPEDEF_ADDRESS_OFST 0
+#define MC_CMD_DBIWROP_TYPEDEF_ADDRESS_LBN 0
+#define MC_CMD_DBIWROP_TYPEDEF_ADDRESS_WIDTH 32
+#define MC_CMD_DBIWROP_TYPEDEF_PARMS_OFST 4
+#define MC_CMD_DBIWROP_TYPEDEF_VF_NUM_LBN 16
+#define MC_CMD_DBIWROP_TYPEDEF_VF_NUM_WIDTH 16
+#define MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_LBN 15
+#define MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_WIDTH 1
+#define MC_CMD_DBIWROP_TYPEDEF_CS2_LBN 14
+#define MC_CMD_DBIWROP_TYPEDEF_CS2_WIDTH 1
+#define MC_CMD_DBIWROP_TYPEDEF_PARMS_LBN 32
+#define MC_CMD_DBIWROP_TYPEDEF_PARMS_WIDTH 32
+#define MC_CMD_DBIWROP_TYPEDEF_VALUE_OFST 8
+#define MC_CMD_DBIWROP_TYPEDEF_VALUE_LBN 64
+#define MC_CMD_DBIWROP_TYPEDEF_VALUE_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_PORT_READ32
+ * Read a 32-bit register from the indirect port register map. The port to
+ * access is implied by the Shared memory channel used.
*/
#define MC_CMD_PORT_READ32 0x14
-#define MC_CMD_PORT_READ32_IN_LEN 4
-#define MC_CMD_PORT_READ32_IN_ADDR_OFST 0
-#define MC_CMD_PORT_READ32_OUT_LEN 8
-#define MC_CMD_PORT_READ32_OUT_VALUE_OFST 0
-#define MC_CMD_PORT_READ32_OUT_STATUS_OFST 4
-
-/* MC_CMD_PORT_WRITE32: (debug)
- * Write a 32-bit register to the indirect port register map.
- *
- * The port to access is implied by the Shared memory channel used.
+
+/* MC_CMD_PORT_READ32_IN msgrequest */
+#define MC_CMD_PORT_READ32_IN_LEN 4
+/* Address */
+#define MC_CMD_PORT_READ32_IN_ADDR_OFST 0
+
+/* MC_CMD_PORT_READ32_OUT msgresponse */
+#define MC_CMD_PORT_READ32_OUT_LEN 8
+/* Value */
+#define MC_CMD_PORT_READ32_OUT_VALUE_OFST 0
+/* Status */
+#define MC_CMD_PORT_READ32_OUT_STATUS_OFST 4
+
+
+/***********************************/
+/* MC_CMD_PORT_WRITE32
+ * Write a 32-bit register to the indirect port register map. The port to
+ * access is implied by the Shared memory channel used.
*/
#define MC_CMD_PORT_WRITE32 0x15
-#define MC_CMD_PORT_WRITE32_IN_LEN 8
-#define MC_CMD_PORT_WRITE32_IN_ADDR_OFST 0
-#define MC_CMD_PORT_WRITE32_IN_VALUE_OFST 4
-#define MC_CMD_PORT_WRITE32_OUT_LEN 4
-#define MC_CMD_PORT_WRITE32_OUT_STATUS_OFST 0
-
-/* MC_CMD_PORT_READ128: (debug)
- * Read a 128-bit register from indirect port register map
- *
- * The port to access is implied by the Shared memory channel used.
+
+/* MC_CMD_PORT_WRITE32_IN msgrequest */
+#define MC_CMD_PORT_WRITE32_IN_LEN 8
+/* Address */
+#define MC_CMD_PORT_WRITE32_IN_ADDR_OFST 0
+/* Value */
+#define MC_CMD_PORT_WRITE32_IN_VALUE_OFST 4
+
+/* MC_CMD_PORT_WRITE32_OUT msgresponse */
+#define MC_CMD_PORT_WRITE32_OUT_LEN 4
+/* Status */
+#define MC_CMD_PORT_WRITE32_OUT_STATUS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_PORT_READ128
+ * Read a 128-bit register from the indirect port register map. The port to
+ * access is implied by the Shared memory channel used.
*/
#define MC_CMD_PORT_READ128 0x16
-#define MC_CMD_PORT_READ128_IN_LEN 4
-#define MC_CMD_PORT_READ128_IN_ADDR_OFST 0
-#define MC_CMD_PORT_READ128_OUT_LEN 20
-#define MC_CMD_PORT_READ128_OUT_VALUE_OFST 0
-#define MC_CMD_PORT_READ128_OUT_STATUS_OFST 16
-
-/* MC_CMD_PORT_WRITE128: (debug)
- * Write a 128-bit register to indirect port register map.
- *
- * The port to access is implied by the Shared memory channel used.
+
+/* MC_CMD_PORT_READ128_IN msgrequest */
+#define MC_CMD_PORT_READ128_IN_LEN 4
+/* Address */
+#define MC_CMD_PORT_READ128_IN_ADDR_OFST 0
+
+/* MC_CMD_PORT_READ128_OUT msgresponse */
+#define MC_CMD_PORT_READ128_OUT_LEN 20
+/* Value */
+#define MC_CMD_PORT_READ128_OUT_VALUE_OFST 0
+#define MC_CMD_PORT_READ128_OUT_VALUE_LEN 16
+/* Status */
+#define MC_CMD_PORT_READ128_OUT_STATUS_OFST 16
+
+
+/***********************************/
+/* MC_CMD_PORT_WRITE128
+ * Write a 128-bit register to the indirect port register map. The port to
+ * access is implied by the Shared memory channel used.
*/
#define MC_CMD_PORT_WRITE128 0x17
-#define MC_CMD_PORT_WRITE128_IN_LEN 20
-#define MC_CMD_PORT_WRITE128_IN_ADDR_OFST 0
-#define MC_CMD_PORT_WRITE128_IN_VALUE_OFST 4
-#define MC_CMD_PORT_WRITE128_OUT_LEN 4
-#define MC_CMD_PORT_WRITE128_OUT_STATUS_OFST 0
-
-/* MC_CMD_GET_BOARD_CFG:
- * Returns the MC firmware configuration structure
- *
- * The FW_SUBTYPE_LIST contains a 16-bit value for each of the 12 types of
- * NVRAM area. The values are defined in the firmware/mc/platform/<xxx>.c file
- * for a specific board type, but otherwise have no meaning to the MC; they
- * are used by the driver to manage selection of appropriate firmware updates.
+
+/* MC_CMD_PORT_WRITE128_IN msgrequest */
+#define MC_CMD_PORT_WRITE128_IN_LEN 20
+/* Address */
+#define MC_CMD_PORT_WRITE128_IN_ADDR_OFST 0
+/* Value */
+#define MC_CMD_PORT_WRITE128_IN_VALUE_OFST 4
+#define MC_CMD_PORT_WRITE128_IN_VALUE_LEN 16
+
+/* MC_CMD_PORT_WRITE128_OUT msgresponse */
+#define MC_CMD_PORT_WRITE128_OUT_LEN 4
+/* Status */
+#define MC_CMD_PORT_WRITE128_OUT_STATUS_OFST 0
+
+/* MC_CMD_CAPABILITIES structuredef */
+#define MC_CMD_CAPABILITIES_LEN 4
+/* Small buf table. */
+#define MC_CMD_CAPABILITIES_SMALL_BUF_TBL_LBN 0
+#define MC_CMD_CAPABILITIES_SMALL_BUF_TBL_WIDTH 1
+/* Turbo mode (for Maranello). */
+#define MC_CMD_CAPABILITIES_TURBO_LBN 1
+#define MC_CMD_CAPABILITIES_TURBO_WIDTH 1
+/* Turbo mode active (for Maranello). */
+#define MC_CMD_CAPABILITIES_TURBO_ACTIVE_LBN 2
+#define MC_CMD_CAPABILITIES_TURBO_ACTIVE_WIDTH 1
+/* PTP offload. */
+#define MC_CMD_CAPABILITIES_PTP_LBN 3
+#define MC_CMD_CAPABILITIES_PTP_WIDTH 1
+/* AOE mode. */
+#define MC_CMD_CAPABILITIES_AOE_LBN 4
+#define MC_CMD_CAPABILITIES_AOE_WIDTH 1
+/* AOE mode active. */
+#define MC_CMD_CAPABILITIES_AOE_ACTIVE_LBN 5
+#define MC_CMD_CAPABILITIES_AOE_ACTIVE_WIDTH 1
+/* AOE mode active. */
+#define MC_CMD_CAPABILITIES_FC_ACTIVE_LBN 6
+#define MC_CMD_CAPABILITIES_FC_ACTIVE_WIDTH 1
+#define MC_CMD_CAPABILITIES_RESERVED_LBN 7
+#define MC_CMD_CAPABILITIES_RESERVED_WIDTH 25
+
+
+/***********************************/
+/* MC_CMD_GET_BOARD_CFG
+ * Returns the MC firmware configuration structure.
*/
#define MC_CMD_GET_BOARD_CFG 0x18
-#define MC_CMD_GET_BOARD_CFG_IN_LEN 0
-#define MC_CMD_GET_BOARD_CFG_OUT_LEN 96
-#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_TYPE_OFST 0
-#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_OFST 4
-#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_LEN 32
-#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT0_OFST 36
-#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT1_OFST 40
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST 44
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_LEN 6
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST 50
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_LEN 6
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT0_OFST 56
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT1_OFST 60
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT0_OFST 64
-#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT1_OFST 68
-#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST 72
-#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN 24
-
-/* MC_CMD_DBI_READX: (debug)
+
+/* MC_CMD_GET_BOARD_CFG_IN msgrequest */
+#define MC_CMD_GET_BOARD_CFG_IN_LEN 0
+
+/* MC_CMD_GET_BOARD_CFG_OUT msgresponse */
+#define MC_CMD_GET_BOARD_CFG_OUT_LENMIN 96
+#define MC_CMD_GET_BOARD_CFG_OUT_LENMAX 136
+#define MC_CMD_GET_BOARD_CFG_OUT_LEN(num) (72+2*(num))
+#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_TYPE_OFST 0
+#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_OFST 4
+#define MC_CMD_GET_BOARD_CFG_OUT_BOARD_NAME_LEN 32
+/* See MC_CMD_CAPABILITIES */
+#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT0_OFST 36
+/* See MC_CMD_CAPABILITIES */
+#define MC_CMD_GET_BOARD_CFG_OUT_CAPABILITIES_PORT1_OFST 40
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST 44
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_LEN 6
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST 50
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_LEN 6
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT0_OFST 56
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_COUNT_PORT1_OFST 60
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT0_OFST 64
+#define MC_CMD_GET_BOARD_CFG_OUT_MAC_STRIDE_PORT1_OFST 68
+/* This field contains a 16-bit value for each of the types of NVRAM area. The
+ * values are defined in the firmware/mc/platform/.c file for a specific board
+ * type, but otherwise have no meaning to the MC; they are used by the driver
+ * to manage selection of appropriate firmware updates.
+ */
+#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_OFST 72
+#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN 2
+#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MINNUM 12
+#define MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM 32
+
+
+/***********************************/
+/* MC_CMD_DBI_READX
* Read DBI register(s) -- extended functionality
- *
- * Host: vf selection, address, [,vf selection ...]
- * MC: value [,value ...]
*/
#define MC_CMD_DBI_READX 0x19
-#define MC_CMD_DBI_READX_IN_LEN(_numwords) \
- (8*(_numwords))
-#define MC_CMD_DBI_READX_OUT_LEN(_numwords) \
- (4*(_numwords))
-/* MC_CMD_SET_RAND_SEED:
- * Set the 16byte seed for the MC pseudo-random generator
+/* MC_CMD_DBI_READX_IN msgrequest */
+#define MC_CMD_DBI_READX_IN_LENMIN 8
+#define MC_CMD_DBI_READX_IN_LENMAX 248
+#define MC_CMD_DBI_READX_IN_LEN(num) (0+8*(num))
+/* Each Read op consists of an address (offset 0), VF/CS2) */
+#define MC_CMD_DBI_READX_IN_DBIRDOP_OFST 0
+#define MC_CMD_DBI_READX_IN_DBIRDOP_LEN 8
+#define MC_CMD_DBI_READX_IN_DBIRDOP_LO_OFST 0
+#define MC_CMD_DBI_READX_IN_DBIRDOP_HI_OFST 4
+#define MC_CMD_DBI_READX_IN_DBIRDOP_MINNUM 1
+#define MC_CMD_DBI_READX_IN_DBIRDOP_MAXNUM 31
+
+/* MC_CMD_DBI_READX_OUT msgresponse */
+#define MC_CMD_DBI_READX_OUT_LENMIN 4
+#define MC_CMD_DBI_READX_OUT_LENMAX 252
+#define MC_CMD_DBI_READX_OUT_LEN(num) (0+4*(num))
+/* Value */
+#define MC_CMD_DBI_READX_OUT_VALUE_OFST 0
+#define MC_CMD_DBI_READX_OUT_VALUE_LEN 4
+#define MC_CMD_DBI_READX_OUT_VALUE_MINNUM 1
+#define MC_CMD_DBI_READX_OUT_VALUE_MAXNUM 63
+
+/* MC_CMD_DBIRDOP_TYPEDEF structuredef */
+#define MC_CMD_DBIRDOP_TYPEDEF_LEN 8
+#define MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_OFST 0
+#define MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_LBN 0
+#define MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_WIDTH 32
+#define MC_CMD_DBIRDOP_TYPEDEF_PARMS_OFST 4
+#define MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_LBN 16
+#define MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_WIDTH 16
+#define MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_LBN 15
+#define MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_WIDTH 1
+#define MC_CMD_DBIRDOP_TYPEDEF_CS2_LBN 14
+#define MC_CMD_DBIRDOP_TYPEDEF_CS2_WIDTH 1
+#define MC_CMD_DBIRDOP_TYPEDEF_PARMS_LBN 32
+#define MC_CMD_DBIRDOP_TYPEDEF_PARMS_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_SET_RAND_SEED
+ * Set the 16byte seed for the MC pseudo-random generator.
*/
#define MC_CMD_SET_RAND_SEED 0x1a
-#define MC_CMD_SET_RAND_SEED_IN_LEN 16
-#define MC_CMD_SET_RAND_SEED_IN_SEED_OFST 0
-#define MC_CMD_SET_RAND_SEED_OUT_LEN 0
-/* MC_CMD_LTSSM_HIST: (debug)
+/* MC_CMD_SET_RAND_SEED_IN msgrequest */
+#define MC_CMD_SET_RAND_SEED_IN_LEN 16
+/* Seed value. */
+#define MC_CMD_SET_RAND_SEED_IN_SEED_OFST 0
+#define MC_CMD_SET_RAND_SEED_IN_SEED_LEN 16
+
+/* MC_CMD_SET_RAND_SEED_OUT msgresponse */
+#define MC_CMD_SET_RAND_SEED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_LTSSM_HIST
* Retrieve the history of the LTSSM, if the build supports it.
- *
- * Host: nothing
- * MC: variable number of LTSSM values, as bytes
- * The history is read-to-clear.
*/
#define MC_CMD_LTSSM_HIST 0x1b
-/* MC_CMD_DRV_ATTACH:
- * Inform MCPU that this port is managed on the host (i.e. driver active)
+/* MC_CMD_LTSSM_HIST_IN msgrequest */
+#define MC_CMD_LTSSM_HIST_IN_LEN 0
+
+/* MC_CMD_LTSSM_HIST_OUT msgresponse */
+#define MC_CMD_LTSSM_HIST_OUT_LENMIN 0
+#define MC_CMD_LTSSM_HIST_OUT_LENMAX 252
+#define MC_CMD_LTSSM_HIST_OUT_LEN(num) (0+4*(num))
+/* variable number of LTSSM values, as bytes. The history is read-to-clear. */
+#define MC_CMD_LTSSM_HIST_OUT_DATA_OFST 0
+#define MC_CMD_LTSSM_HIST_OUT_DATA_LEN 4
+#define MC_CMD_LTSSM_HIST_OUT_DATA_MINNUM 0
+#define MC_CMD_LTSSM_HIST_OUT_DATA_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_DRV_ATTACH
+ * Inform MCPU that this port is managed on the host (i.e. driver active). For
+ * Huntington, also request the preferred datapath firmware to use if possible
+ * (it may not be possible for this request to be fulfilled; the driver must
+ * issue a subsequent MC_CMD_GET_CAPABILITIES command to determine which
+ * features are actually available). The FIRMWARE_ID field is ignored by older
+ * platforms.
*/
#define MC_CMD_DRV_ATTACH 0x1c
-#define MC_CMD_DRV_ATTACH_IN_LEN 8
-#define MC_CMD_DRV_ATTACH_IN_NEW_STATE_OFST 0
-#define MC_CMD_DRV_ATTACH_IN_UPDATE_OFST 4
-#define MC_CMD_DRV_ATTACH_OUT_LEN 4
-#define MC_CMD_DRV_ATTACH_OUT_OLD_STATE_OFST 0
-
-/* MC_CMD_NCSI_PROD: (debug)
- * Trigger an NC-SI event (and possibly an AEN in response)
- */
-#define MC_CMD_NCSI_PROD 0x1d
-#define MC_CMD_NCSI_PROD_IN_LEN 4
-#define MC_CMD_NCSI_PROD_IN_EVENTS_OFST 0
-#define MC_CMD_NCSI_PROD_LINKCHANGE_LBN 0
-#define MC_CMD_NCSI_PROD_LINKCHANGE_WIDTH 1
-#define MC_CMD_NCSI_PROD_RESET_LBN 1
-#define MC_CMD_NCSI_PROD_RESET_WIDTH 1
-#define MC_CMD_NCSI_PROD_DRVATTACH_LBN 2
-#define MC_CMD_NCSI_PROD_DRVATTACH_WIDTH 1
-#define MC_CMD_NCSI_PROD_OUT_LEN 0
-
-/* Enumeration */
-#define MC_CMD_NCSI_PROD_LINKCHANGE 0
-#define MC_CMD_NCSI_PROD_RESET 1
-#define MC_CMD_NCSI_PROD_DRVATTACH 2
-
-/* MC_CMD_DEVEL: (debug)
- * Reserved for development
- */
-#define MC_CMD_DEVEL 0x1e
-
-/* MC_CMD_SHMUART: (debug)
+
+/* MC_CMD_DRV_ATTACH_IN msgrequest */
+#define MC_CMD_DRV_ATTACH_IN_LEN 12
+/* new state (0=detached, 1=attached) to set if UPDATE=1 */
+#define MC_CMD_DRV_ATTACH_IN_NEW_STATE_OFST 0
+/* 1 to set new state, or 0 to just report the existing state */
+#define MC_CMD_DRV_ATTACH_IN_UPDATE_OFST 4
+/* preferred datapath firmware (for Huntington; ignored for Siena) */
+#define MC_CMD_DRV_ATTACH_IN_FIRMWARE_ID_OFST 8
+/* enum: Prefer to use full featured firmware */
+#define MC_CMD_FW_FULL_FEATURED 0x0
+/* enum: Prefer to use firmware with fewer features but lower latency */
+#define MC_CMD_FW_LOW_LATENCY 0x1
+
+/* MC_CMD_DRV_ATTACH_OUT msgresponse */
+#define MC_CMD_DRV_ATTACH_OUT_LEN 4
+/* previous or existing state (0=detached, 1=attached) */
+#define MC_CMD_DRV_ATTACH_OUT_OLD_STATE_OFST 0
+
+/* MC_CMD_DRV_ATTACH_EXT_OUT msgresponse */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_LEN 8
+/* previous or existing state (0=detached, 1=attached) */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_OLD_STATE_OFST 0
+/* Flags associated with this function */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_OFST 4
+/* enum: Labels the lowest-numbered function visible to the OS */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY 0x0
+/* enum: The function can control the link state of the physical port it is
+ * bound to.
+ */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL 0x1
+/* enum: The function can perform privileged operations */
+#define MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED 0x2
+
+
+/***********************************/
+/* MC_CMD_SHMUART
* Route UART output to circular buffer in shared memory instead.
*/
#define MC_CMD_SHMUART 0x1f
-#define MC_CMD_SHMUART_IN_FLAG_OFST 0
-#define MC_CMD_SHMUART_IN_LEN 4
-#define MC_CMD_SHMUART_OUT_LEN 0
-/* MC_CMD_PORT_RESET:
- * Generic per-port reset. There is no equivalent for per-board reset.
- *
- * Locks required: None
- * Return code: 0, ETIME
+/* MC_CMD_SHMUART_IN msgrequest */
+#define MC_CMD_SHMUART_IN_LEN 4
+/* ??? */
+#define MC_CMD_SHMUART_IN_FLAG_OFST 0
+
+/* MC_CMD_SHMUART_OUT msgresponse */
+#define MC_CMD_SHMUART_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PORT_RESET
+ * Generic per-port reset. There is no equivalent for per-board reset. Locks
+ * required: None; Return code: 0, ETIME. NOTE: This command is deprecated -
+ * use MC_CMD_ENTITY_RESET instead.
*/
#define MC_CMD_PORT_RESET 0x20
-#define MC_CMD_PORT_RESET_IN_LEN 0
-#define MC_CMD_PORT_RESET_OUT_LEN 0
-/* MC_CMD_RESOURCE_LOCK:
- * Generic resource lock/unlock interface.
- *
- * Locks required: None
- * Return code: 0,
- * EBUSY (if trylock is contended by other port),
- * EDEADLK (if trylock is already acquired by this port)
- * EINVAL (if unlock doesn't own the lock)
- */
-#define MC_CMD_RESOURCE_LOCK 0x21
-#define MC_CMD_RESOURCE_LOCK_IN_LEN 8
-#define MC_CMD_RESOURCE_LOCK_IN_ACTION_OFST 0
-#define MC_CMD_RESOURCE_LOCK_ACTION_TRYLOCK 1
-#define MC_CMD_RESOURCE_LOCK_ACTION_UNLOCK 0
-#define MC_CMD_RESOURCE_LOCK_IN_RESOURCE_OFST 4
-#define MC_CMD_RESOURCE_LOCK_I2C 2
-#define MC_CMD_RESOURCE_LOCK_PHY 3
-#define MC_CMD_RESOURCE_LOCK_OUT_LEN 0
-
-/* MC_CMD_SPI_COMMAND: (variadic in, variadic out)
- * Read/Write to/from the SPI device.
- *
- * Locks required: SPI_LOCK
- * Return code: 0, ETIME, EINVAL, EACCES (if SPI_LOCK is not held)
- */
-#define MC_CMD_SPI_COMMAND 0x22
-#define MC_CMD_SPI_COMMAND_IN_LEN(_write_bytes) (12 + (_write_bytes))
-#define MC_CMD_SPI_COMMAND_IN_ARGS_OFST 0
-#define MC_CMD_SPI_COMMAND_IN_ARGS_ADDRESS_OFST 0
-#define MC_CMD_SPI_COMMAND_IN_ARGS_READ_BYTES_OFST 4
-#define MC_CMD_SPI_COMMAND_IN_ARGS_CHIP_SELECT_OFST 8
-/* Data to write here */
-#define MC_CMD_SPI_COMMAND_IN_WRITE_BUFFER_OFST 12
-#define MC_CMD_SPI_COMMAND_OUT_LEN(_read_bytes) (_read_bytes)
-/* Data read here */
-#define MC_CMD_SPI_COMMAND_OUT_READ_BUFFER_OFST 0
-
-/* MC_CMD_I2C_READ_WRITE: (variadic in, variadic out)
- * Read/Write to/from the I2C bus.
- *
- * Locks required: I2C_LOCK
- * Return code: 0, ETIME, EINVAL, EACCES (if I2C_LOCK is not held)
- */
-#define MC_CMD_I2C_RW 0x23
-#define MC_CMD_I2C_RW_IN_LEN(_write_bytes) (8 + (_write_bytes))
-#define MC_CMD_I2C_RW_IN_ARGS_OFST 0
-#define MC_CMD_I2C_RW_IN_ARGS_ADDR_OFST 0
-#define MC_CMD_I2C_RW_IN_ARGS_READ_BYTES_OFST 4
-/* Data to write here */
-#define MC_CMD_I2C_RW_IN_WRITE_BUFFER_OFSET 8
-#define MC_CMD_I2C_RW_OUT_LEN(_read_bytes) (_read_bytes)
-/* Data read here */
-#define MC_CMD_I2C_RW_OUT_READ_BUFFER_OFST 0
-
-/* Generic phy capability bitmask */
-#define MC_CMD_PHY_CAP_10HDX_LBN 1
-#define MC_CMD_PHY_CAP_10HDX_WIDTH 1
-#define MC_CMD_PHY_CAP_10FDX_LBN 2
-#define MC_CMD_PHY_CAP_10FDX_WIDTH 1
-#define MC_CMD_PHY_CAP_100HDX_LBN 3
-#define MC_CMD_PHY_CAP_100HDX_WIDTH 1
-#define MC_CMD_PHY_CAP_100FDX_LBN 4
-#define MC_CMD_PHY_CAP_100FDX_WIDTH 1
-#define MC_CMD_PHY_CAP_1000HDX_LBN 5
-#define MC_CMD_PHY_CAP_1000HDX_WIDTH 1
-#define MC_CMD_PHY_CAP_1000FDX_LBN 6
-#define MC_CMD_PHY_CAP_1000FDX_WIDTH 1
-#define MC_CMD_PHY_CAP_10000FDX_LBN 7
-#define MC_CMD_PHY_CAP_10000FDX_WIDTH 1
-#define MC_CMD_PHY_CAP_PAUSE_LBN 8
-#define MC_CMD_PHY_CAP_PAUSE_WIDTH 1
-#define MC_CMD_PHY_CAP_ASYM_LBN 9
-#define MC_CMD_PHY_CAP_ASYM_WIDTH 1
-#define MC_CMD_PHY_CAP_AN_LBN 10
-#define MC_CMD_PHY_CAP_AN_WIDTH 1
-
-/* Generic loopback enumeration */
-#define MC_CMD_LOOPBACK_NONE 0
-#define MC_CMD_LOOPBACK_DATA 1
-#define MC_CMD_LOOPBACK_GMAC 2
-#define MC_CMD_LOOPBACK_XGMII 3
-#define MC_CMD_LOOPBACK_XGXS 4
-#define MC_CMD_LOOPBACK_XAUI 5
-#define MC_CMD_LOOPBACK_GMII 6
-#define MC_CMD_LOOPBACK_SGMII 7
-#define MC_CMD_LOOPBACK_XGBR 8
-#define MC_CMD_LOOPBACK_XFI 9
-#define MC_CMD_LOOPBACK_XAUI_FAR 10
-#define MC_CMD_LOOPBACK_GMII_FAR 11
-#define MC_CMD_LOOPBACK_SGMII_FAR 12
-#define MC_CMD_LOOPBACK_XFI_FAR 13
-#define MC_CMD_LOOPBACK_GPHY 14
-#define MC_CMD_LOOPBACK_PHYXS 15
-#define MC_CMD_LOOPBACK_PCS 16
-#define MC_CMD_LOOPBACK_PMAPMD 17
-#define MC_CMD_LOOPBACK_XPORT 18
-#define MC_CMD_LOOPBACK_XGMII_WS 19
-#define MC_CMD_LOOPBACK_XAUI_WS 20
-#define MC_CMD_LOOPBACK_XAUI_WS_FAR 21
-#define MC_CMD_LOOPBACK_XAUI_WS_NEAR 22
-#define MC_CMD_LOOPBACK_GMII_WS 23
-#define MC_CMD_LOOPBACK_XFI_WS 24
-#define MC_CMD_LOOPBACK_XFI_WS_FAR 25
-#define MC_CMD_LOOPBACK_PHYXS_WS 26
-
-/* Generic PHY statistics enumeration */
-#define MC_CMD_OUI 0
-#define MC_CMD_PMA_PMD_LINK_UP 1
-#define MC_CMD_PMA_PMD_RX_FAULT 2
-#define MC_CMD_PMA_PMD_TX_FAULT 3
-#define MC_CMD_PMA_PMD_SIGNAL 4
-#define MC_CMD_PMA_PMD_SNR_A 5
-#define MC_CMD_PMA_PMD_SNR_B 6
-#define MC_CMD_PMA_PMD_SNR_C 7
-#define MC_CMD_PMA_PMD_SNR_D 8
-#define MC_CMD_PCS_LINK_UP 9
-#define MC_CMD_PCS_RX_FAULT 10
-#define MC_CMD_PCS_TX_FAULT 11
-#define MC_CMD_PCS_BER 12
-#define MC_CMD_PCS_BLOCK_ERRORS 13
-#define MC_CMD_PHYXS_LINK_UP 14
-#define MC_CMD_PHYXS_RX_FAULT 15
-#define MC_CMD_PHYXS_TX_FAULT 16
-#define MC_CMD_PHYXS_ALIGN 17
-#define MC_CMD_PHYXS_SYNC 18
-#define MC_CMD_AN_LINK_UP 19
-#define MC_CMD_AN_COMPLETE 20
-#define MC_CMD_AN_10GBT_STATUS 21
-#define MC_CMD_CL22_LINK_UP 22
-#define MC_CMD_PHY_NSTATS 23
-
-/* MC_CMD_GET_PHY_CFG:
- * Report PHY configuration. This guarantees to succeed even if the PHY is in
- * a "zombie" state.
- *
- * Locks required: None
- * Return code: 0
+/* MC_CMD_PORT_RESET_IN msgrequest */
+#define MC_CMD_PORT_RESET_IN_LEN 0
+
+/* MC_CMD_PORT_RESET_OUT msgresponse */
+#define MC_CMD_PORT_RESET_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_ENTITY_RESET
+ * Generic per-resource reset. There is no equivalent for per-board reset.
+ * Locks required: None; Return code: 0, ETIME. NOTE: This command is an
+ * extended version of the deprecated MC_CMD_PORT_RESET with added fields.
+ */
+#define MC_CMD_ENTITY_RESET 0x20
+
+/* MC_CMD_ENTITY_RESET_IN msgrequest */
+#define MC_CMD_ENTITY_RESET_IN_LEN 4
+/* Optional flags field. Omitting this will perform a "legacy" reset action
+ * (TBD).
+ */
+#define MC_CMD_ENTITY_RESET_IN_FLAG_OFST 0
+#define MC_CMD_ENTITY_RESET_IN_FUNCTION_RESOURCE_RESET_LBN 0
+#define MC_CMD_ENTITY_RESET_IN_FUNCTION_RESOURCE_RESET_WIDTH 1
+
+/* MC_CMD_ENTITY_RESET_OUT msgresponse */
+#define MC_CMD_ENTITY_RESET_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PCIE_CREDITS
+ * Read instantaneous and minimum flow control thresholds.
+ */
+#define MC_CMD_PCIE_CREDITS 0x21
+
+/* MC_CMD_PCIE_CREDITS_IN msgrequest */
+#define MC_CMD_PCIE_CREDITS_IN_LEN 8
+/* poll period. 0 is disabled */
+#define MC_CMD_PCIE_CREDITS_IN_POLL_PERIOD_OFST 0
+/* wipe statistics */
+#define MC_CMD_PCIE_CREDITS_IN_WIPE_OFST 4
+
+/* MC_CMD_PCIE_CREDITS_OUT msgresponse */
+#define MC_CMD_PCIE_CREDITS_OUT_LEN 16
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_OFST 0
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_OFST 2
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_OFST 4
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_OFST 6
+#define MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_OFST 8
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_OFST 10
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_OFST 12
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_LEN 2
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_OFST 14
+#define MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_LEN 2
+
+
+/***********************************/
+/* MC_CMD_RXD_MONITOR
+ * Get histogram of RX queue fill level.
+ */
+#define MC_CMD_RXD_MONITOR 0x22
+
+/* MC_CMD_RXD_MONITOR_IN msgrequest */
+#define MC_CMD_RXD_MONITOR_IN_LEN 12
+#define MC_CMD_RXD_MONITOR_IN_QID_OFST 0
+#define MC_CMD_RXD_MONITOR_IN_POLL_PERIOD_OFST 4
+#define MC_CMD_RXD_MONITOR_IN_WIPE_OFST 8
+
+/* MC_CMD_RXD_MONITOR_OUT msgresponse */
+#define MC_CMD_RXD_MONITOR_OUT_LEN 80
+#define MC_CMD_RXD_MONITOR_OUT_QID_OFST 0
+#define MC_CMD_RXD_MONITOR_OUT_RING_FILL_OFST 4
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_FILL_OFST 8
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_1_OFST 12
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_2_OFST 16
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_4_OFST 20
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_8_OFST 24
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_16_OFST 28
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_32_OFST 32
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_64_OFST 36
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_128_OFST 40
+#define MC_CMD_RXD_MONITOR_OUT_RING_LT_256_OFST 44
+#define MC_CMD_RXD_MONITOR_OUT_RING_GE_256_OFST 48
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_1_OFST 52
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_2_OFST 56
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_4_OFST 60
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_8_OFST 64
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_16_OFST 68
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_LT_32_OFST 72
+#define MC_CMD_RXD_MONITOR_OUT_CACHE_GE_32_OFST 76
+
+
+/***********************************/
+/* MC_CMD_PUTS
+ * Copy the given ASCII string out onto UART and/or out of the network port.
+ */
+#define MC_CMD_PUTS 0x23
+
+/* MC_CMD_PUTS_IN msgrequest */
+#define MC_CMD_PUTS_IN_LENMIN 13
+#define MC_CMD_PUTS_IN_LENMAX 252
+#define MC_CMD_PUTS_IN_LEN(num) (12+1*(num))
+#define MC_CMD_PUTS_IN_DEST_OFST 0
+#define MC_CMD_PUTS_IN_UART_LBN 0
+#define MC_CMD_PUTS_IN_UART_WIDTH 1
+#define MC_CMD_PUTS_IN_PORT_LBN 1
+#define MC_CMD_PUTS_IN_PORT_WIDTH 1
+#define MC_CMD_PUTS_IN_DHOST_OFST 4
+#define MC_CMD_PUTS_IN_DHOST_LEN 6
+#define MC_CMD_PUTS_IN_STRING_OFST 12
+#define MC_CMD_PUTS_IN_STRING_LEN 1
+#define MC_CMD_PUTS_IN_STRING_MINNUM 1
+#define MC_CMD_PUTS_IN_STRING_MAXNUM 240
+
+/* MC_CMD_PUTS_OUT msgresponse */
+#define MC_CMD_PUTS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_PHY_CFG
+ * Report PHY configuration. This guarantees to succeed even if the PHY is in a
+ * 'zombie' state. Locks required: None
*/
#define MC_CMD_GET_PHY_CFG 0x24
-#define MC_CMD_GET_PHY_CFG_IN_LEN 0
-#define MC_CMD_GET_PHY_CFG_OUT_LEN 72
-
-#define MC_CMD_GET_PHY_CFG_OUT_FLAGS_OFST 0
-#define MC_CMD_GET_PHY_CFG_PRESENT_LBN 0
-#define MC_CMD_GET_PHY_CFG_PRESENT_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_LBN 1
-#define MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN 2
-#define MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_LOWPOWER_LBN 3
-#define MC_CMD_GET_PHY_CFG_LOWPOWER_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_POWEROFF_LBN 4
-#define MC_CMD_GET_PHY_CFG_POWEROFF_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_TXDIS_LBN 5
-#define MC_CMD_GET_PHY_CFG_TXDIS_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_BIST_LBN 6
-#define MC_CMD_GET_PHY_CFG_BIST_WIDTH 1
-#define MC_CMD_GET_PHY_CFG_OUT_TYPE_OFST 4
+/* MC_CMD_GET_PHY_CFG_IN msgrequest */
+#define MC_CMD_GET_PHY_CFG_IN_LEN 0
+
+/* MC_CMD_GET_PHY_CFG_OUT msgresponse */
+#define MC_CMD_GET_PHY_CFG_OUT_LEN 72
+/* flags */
+#define MC_CMD_GET_PHY_CFG_OUT_FLAGS_OFST 0
+#define MC_CMD_GET_PHY_CFG_OUT_PRESENT_LBN 0
+#define MC_CMD_GET_PHY_CFG_OUT_PRESENT_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN 1
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN 2
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_LOWPOWER_LBN 3
+#define MC_CMD_GET_PHY_CFG_OUT_LOWPOWER_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_POWEROFF_LBN 4
+#define MC_CMD_GET_PHY_CFG_OUT_POWEROFF_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_TXDIS_LBN 5
+#define MC_CMD_GET_PHY_CFG_OUT_TXDIS_WIDTH 1
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_LBN 6
+#define MC_CMD_GET_PHY_CFG_OUT_BIST_WIDTH 1
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_TYPE_OFST 4
/* Bitmask of supported capabilities */
-#define MC_CMD_GET_PHY_CFG_OUT_SUPPORTED_CAP_OFST 8
-#define MC_CMD_GET_PHY_CFG_OUT_CHANNEL_OFST 12
-#define MC_CMD_GET_PHY_CFG_OUT_PRT_OFST 16
-/* PHY statistics bitmap */
-#define MC_CMD_GET_PHY_CFG_OUT_STATS_MASK_OFST 20
-/* PHY type/name string */
-#define MC_CMD_GET_PHY_CFG_OUT_NAME_OFST 24
-#define MC_CMD_GET_PHY_CFG_OUT_NAME_LEN 20
-#define MC_CMD_GET_PHY_CFG_OUT_MEDIA_TYPE_OFST 44
-#define MC_CMD_MEDIA_XAUI 1
-#define MC_CMD_MEDIA_CX4 2
-#define MC_CMD_MEDIA_KX4 3
-#define MC_CMD_MEDIA_XFP 4
-#define MC_CMD_MEDIA_SFP_PLUS 5
-#define MC_CMD_MEDIA_BASE_T 6
-/* MDIO "MMDS" supported */
-#define MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48
-/* Native clause 22 */
-#define MC_CMD_MMD_CLAUSE22 0
-#define MC_CMD_MMD_CLAUSE45_PMAPMD 1
-#define MC_CMD_MMD_CLAUSE45_WIS 2
-#define MC_CMD_MMD_CLAUSE45_PCS 3
-#define MC_CMD_MMD_CLAUSE45_PHYXS 4
-#define MC_CMD_MMD_CLAUSE45_DTEXS 5
-#define MC_CMD_MMD_CLAUSE45_TC 6
-#define MC_CMD_MMD_CLAUSE45_AN 7
-/* Clause22 proxied over clause45 by PHY */
-#define MC_CMD_MMD_CLAUSE45_C22EXT 29
-#define MC_CMD_MMD_CLAUSE45_VEND1 30
-#define MC_CMD_MMD_CLAUSE45_VEND2 31
-/* PHY stepping version */
-#define MC_CMD_GET_PHY_CFG_OUT_REVISION_OFST 52
-#define MC_CMD_GET_PHY_CFG_OUT_REVISION_LEN 20
-
-/* MC_CMD_START_BIST:
- * Start a BIST test on the PHY.
- *
- * Locks required: PHY_LOCK if doing a PHY BIST
+#define MC_CMD_GET_PHY_CFG_OUT_SUPPORTED_CAP_OFST 8
+#define MC_CMD_PHY_CAP_10HDX_LBN 1
+#define MC_CMD_PHY_CAP_10HDX_WIDTH 1
+#define MC_CMD_PHY_CAP_10FDX_LBN 2
+#define MC_CMD_PHY_CAP_10FDX_WIDTH 1
+#define MC_CMD_PHY_CAP_100HDX_LBN 3
+#define MC_CMD_PHY_CAP_100HDX_WIDTH 1
+#define MC_CMD_PHY_CAP_100FDX_LBN 4
+#define MC_CMD_PHY_CAP_100FDX_WIDTH 1
+#define MC_CMD_PHY_CAP_1000HDX_LBN 5
+#define MC_CMD_PHY_CAP_1000HDX_WIDTH 1
+#define MC_CMD_PHY_CAP_1000FDX_LBN 6
+#define MC_CMD_PHY_CAP_1000FDX_WIDTH 1
+#define MC_CMD_PHY_CAP_10000FDX_LBN 7
+#define MC_CMD_PHY_CAP_10000FDX_WIDTH 1
+#define MC_CMD_PHY_CAP_PAUSE_LBN 8
+#define MC_CMD_PHY_CAP_PAUSE_WIDTH 1
+#define MC_CMD_PHY_CAP_ASYM_LBN 9
+#define MC_CMD_PHY_CAP_ASYM_WIDTH 1
+#define MC_CMD_PHY_CAP_AN_LBN 10
+#define MC_CMD_PHY_CAP_AN_WIDTH 1
+#define MC_CMD_PHY_CAP_40000FDX_LBN 11
+#define MC_CMD_PHY_CAP_40000FDX_WIDTH 1
+#define MC_CMD_PHY_CAP_DDM_LBN 12
+#define MC_CMD_PHY_CAP_DDM_WIDTH 1
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_CHANNEL_OFST 12
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_PRT_OFST 16
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_STATS_MASK_OFST 20
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_NAME_OFST 24
+#define MC_CMD_GET_PHY_CFG_OUT_NAME_LEN 20
+/* ?? */
+#define MC_CMD_GET_PHY_CFG_OUT_MEDIA_TYPE_OFST 44
+/* enum: Xaui. */
+#define MC_CMD_MEDIA_XAUI 0x1
+/* enum: CX4. */
+#define MC_CMD_MEDIA_CX4 0x2
+/* enum: KX4. */
+#define MC_CMD_MEDIA_KX4 0x3
+/* enum: XFP Far. */
+#define MC_CMD_MEDIA_XFP 0x4
+/* enum: SFP+. */
+#define MC_CMD_MEDIA_SFP_PLUS 0x5
+/* enum: 10GBaseT. */
+#define MC_CMD_MEDIA_BASE_T 0x6
+/* enum: QSFP+. */
+#define MC_CMD_MEDIA_QSFP_PLUS 0x7
+#define MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48
+/* enum: Native clause 22 */
+#define MC_CMD_MMD_CLAUSE22 0x0
+#define MC_CMD_MMD_CLAUSE45_PMAPMD 0x1 /* enum */
+#define MC_CMD_MMD_CLAUSE45_WIS 0x2 /* enum */
+#define MC_CMD_MMD_CLAUSE45_PCS 0x3 /* enum */
+#define MC_CMD_MMD_CLAUSE45_PHYXS 0x4 /* enum */
+#define MC_CMD_MMD_CLAUSE45_DTEXS 0x5 /* enum */
+#define MC_CMD_MMD_CLAUSE45_TC 0x6 /* enum */
+#define MC_CMD_MMD_CLAUSE45_AN 0x7 /* enum */
+/* enum: Clause22 proxied over clause45 by PHY. */
+#define MC_CMD_MMD_CLAUSE45_C22EXT 0x1d
+#define MC_CMD_MMD_CLAUSE45_VEND1 0x1e /* enum */
+#define MC_CMD_MMD_CLAUSE45_VEND2 0x1f /* enum */
+#define MC_CMD_GET_PHY_CFG_OUT_REVISION_OFST 52
+#define MC_CMD_GET_PHY_CFG_OUT_REVISION_LEN 20
+
+
+/***********************************/
+/* MC_CMD_START_BIST
+ * Start a BIST test on the PHY. Locks required: PHY_LOCK if doing a PHY BIST
* Return code: 0, EINVAL, EACCES (if PHY_LOCK is not held)
*/
#define MC_CMD_START_BIST 0x25
-#define MC_CMD_START_BIST_IN_LEN 4
-#define MC_CMD_START_BIST_IN_TYPE_OFST 0
-#define MC_CMD_START_BIST_OUT_LEN 0
-
-/* Run the PHY's short cable BIST */
-#define MC_CMD_PHY_BIST_CABLE_SHORT 1
-/* Run the PHY's long cable BIST */
-#define MC_CMD_PHY_BIST_CABLE_LONG 2
-/* Run BIST on the currently selected BPX Serdes (XAUI or XFI) */
-#define MC_CMD_BPX_SERDES_BIST 3
-/* Run the MC loopback tests */
-#define MC_CMD_MC_LOOPBACK_BIST 4
-/* Run the PHY's standard BIST */
-#define MC_CMD_PHY_BIST 5
-
-/* MC_CMD_POLL_PHY_BIST: (variadic output)
- * Poll for BIST completion
- *
- * Returns a single status code, and optionally some PHY specific
- * bist output. The driver should only consume the BIST output
- * after validating OUTLEN and PHY_CFG.PHY_TYPE.
- *
- * If a driver can't successfully parse the BIST output, it should
- * still respect the pass/Fail in OUT.RESULT
- *
- * Locks required: PHY_LOCK if doing a PHY BIST
- * Return code: 0, EACCES (if PHY_LOCK is not held)
+
+/* MC_CMD_START_BIST_IN msgrequest */
+#define MC_CMD_START_BIST_IN_LEN 4
+/* Type of test. */
+#define MC_CMD_START_BIST_IN_TYPE_OFST 0
+/* enum: Run the PHY's short cable BIST. */
+#define MC_CMD_PHY_BIST_CABLE_SHORT 0x1
+/* enum: Run the PHY's long cable BIST. */
+#define MC_CMD_PHY_BIST_CABLE_LONG 0x2
+/* enum: Run BIST on the currently selected BPX Serdes (XAUI or XFI) . */
+#define MC_CMD_BPX_SERDES_BIST 0x3
+/* enum: Run the MC loopback tests. */
+#define MC_CMD_MC_LOOPBACK_BIST 0x4
+/* enum: Run the PHY's standard BIST. */
+#define MC_CMD_PHY_BIST 0x5
+/* enum: Run MC RAM test. */
+#define MC_CMD_MC_MEM_BIST 0x6
+/* enum: Run Port RAM test. */
+#define MC_CMD_PORT_MEM_BIST 0x7
+/* enum: Run register test. */
+#define MC_CMD_REG_BIST 0x8
+
+/* MC_CMD_START_BIST_OUT msgresponse */
+#define MC_CMD_START_BIST_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_POLL_BIST
+ * Poll for BIST completion. Returns a single status code, and optionally some
+ * PHY specific bist output. The driver should only consume the BIST output
+ * after validating OUTLEN and MC_CMD_GET_PHY_CFG.TYPE. If a driver can't
+ * successfully parse the BIST output, it should still respect the pass/Fail in
+ * OUT.RESULT. Locks required: PHY_LOCK if doing a PHY BIST. Return code: 0,
+ * EACCES (if PHY_LOCK is not held).
*/
#define MC_CMD_POLL_BIST 0x26
-#define MC_CMD_POLL_BIST_IN_LEN 0
-#define MC_CMD_POLL_BIST_OUT_LEN UNKNOWN
-#define MC_CMD_POLL_BIST_OUT_SFT9001_LEN 36
-#define MC_CMD_POLL_BIST_OUT_MRSFP_LEN 8
-#define MC_CMD_POLL_BIST_OUT_RESULT_OFST 0
-#define MC_CMD_POLL_BIST_RUNNING 1
-#define MC_CMD_POLL_BIST_PASSED 2
-#define MC_CMD_POLL_BIST_FAILED 3
-#define MC_CMD_POLL_BIST_TIMEOUT 4
-/* Generic: */
-#define MC_CMD_POLL_BIST_OUT_PRIVATE_OFST 4
-/* SFT9001-specific: */
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A_OFST 4
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_B_OFST 8
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_C_OFST 12
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_D_OFST 16
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_A_OFST 20
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_B_OFST 24
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_C_OFST 28
-#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_D_OFST 32
-#define MC_CMD_POLL_BIST_SFT9001_PAIR_OK 1
-#define MC_CMD_POLL_BIST_SFT9001_PAIR_OPEN 2
-#define MC_CMD_POLL_BIST_SFT9001_INTRA_PAIR_SHORT 3
-#define MC_CMD_POLL_BIST_SFT9001_INTER_PAIR_SHORT 4
-#define MC_CMD_POLL_BIST_SFT9001_PAIR_BUSY 9
-/* mrsfp "PHY" driver: */
-#define MC_CMD_POLL_BIST_OUT_MRSFP_TEST_OFST 4
-#define MC_CMD_POLL_BIST_MRSFP_TEST_COMPLETE 0
-#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_WRITE 1
-#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_NO_ACCESS_IO_EXP 2
-#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_NO_ACCESS_MODULE 3
-#define MC_CMD_POLL_BIST_MRSFP_TEST_IO_EXP_I2C_CONFIGURE 4
-#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_I2C_NO_CROSSTALK 5
-#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_PRESENCE 6
-#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_ID_I2C_ACCESS 7
-#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_ID_SANE_VALUE 8
-
-/* MC_CMD_PHY_SPI: (variadic in, variadic out)
- * Read/Write/Erase the PHY SPI device
- *
- * Locks required: PHY_LOCK
- * Return code: 0, ETIME, EINVAL, EACCES (if PHY_LOCK is not held)
- */
-#define MC_CMD_PHY_SPI 0x27
-#define MC_CMD_PHY_SPI_IN_LEN(_write_bytes) (12 + (_write_bytes))
-#define MC_CMD_PHY_SPI_IN_ARGS_OFST 0
-#define MC_CMD_PHY_SPI_IN_ARGS_ADDR_OFST 0
-#define MC_CMD_PHY_SPI_IN_ARGS_READ_BYTES_OFST 4
-#define MC_CMD_PHY_SPI_IN_ARGS_ERASE_ALL_OFST 8
-/* Data to write here */
-#define MC_CMD_PHY_SPI_IN_WRITE_BUFFER_OFSET 12
-#define MC_CMD_PHY_SPI_OUT_LEN(_read_bytes) (_read_bytes)
-/* Data read here */
-#define MC_CMD_PHY_SPI_OUT_READ_BUFFER_OFST 0
-
-
-/* MC_CMD_GET_LOOPBACK_MODES:
- * Returns a bitmask of loopback modes evailable at each speed.
+
+/* MC_CMD_POLL_BIST_IN msgrequest */
+#define MC_CMD_POLL_BIST_IN_LEN 0
+
+/* MC_CMD_POLL_BIST_OUT msgresponse */
+#define MC_CMD_POLL_BIST_OUT_LEN 8
+/* result */
+#define MC_CMD_POLL_BIST_OUT_RESULT_OFST 0
+/* enum: Running. */
+#define MC_CMD_POLL_BIST_RUNNING 0x1
+/* enum: Passed. */
+#define MC_CMD_POLL_BIST_PASSED 0x2
+/* enum: Failed. */
+#define MC_CMD_POLL_BIST_FAILED 0x3
+/* enum: Timed-out. */
+#define MC_CMD_POLL_BIST_TIMEOUT 0x4
+#define MC_CMD_POLL_BIST_OUT_PRIVATE_OFST 4
+
+/* MC_CMD_POLL_BIST_OUT_SFT9001 msgresponse */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_LEN 36
+/* result */
+/* MC_CMD_POLL_BIST_OUT_RESULT_OFST 0 */
+/* Enum values, see field(s): */
+/* MC_CMD_POLL_BIST_OUT/MC_CMD_POLL_BIST_OUT_RESULT */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A_OFST 4
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_B_OFST 8
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_C_OFST 12
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_LENGTH_D_OFST 16
+/* Status of each channel A */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_A_OFST 20
+/* enum: Ok. */
+#define MC_CMD_POLL_BIST_SFT9001_PAIR_OK 0x1
+/* enum: Open. */
+#define MC_CMD_POLL_BIST_SFT9001_PAIR_OPEN 0x2
+/* enum: Intra-pair short. */
+#define MC_CMD_POLL_BIST_SFT9001_INTRA_PAIR_SHORT 0x3
+/* enum: Inter-pair short. */
+#define MC_CMD_POLL_BIST_SFT9001_INTER_PAIR_SHORT 0x4
+/* enum: Busy. */
+#define MC_CMD_POLL_BIST_SFT9001_PAIR_BUSY 0x9
+/* Status of each channel B */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_B_OFST 24
+/* Enum values, see field(s): */
+/* CABLE_STATUS_A */
+/* Status of each channel C */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_C_OFST 28
+/* Enum values, see field(s): */
+/* CABLE_STATUS_A */
+/* Status of each channel D */
+#define MC_CMD_POLL_BIST_OUT_SFT9001_CABLE_STATUS_D_OFST 32
+/* Enum values, see field(s): */
+/* CABLE_STATUS_A */
+
+/* MC_CMD_POLL_BIST_OUT_MRSFP msgresponse */
+#define MC_CMD_POLL_BIST_OUT_MRSFP_LEN 8
+/* result */
+/* MC_CMD_POLL_BIST_OUT_RESULT_OFST 0 */
+/* Enum values, see field(s): */
+/* MC_CMD_POLL_BIST_OUT/MC_CMD_POLL_BIST_OUT_RESULT */
+#define MC_CMD_POLL_BIST_OUT_MRSFP_TEST_OFST 4
+/* enum: Complete. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_COMPLETE 0x0
+/* enum: Bus switch off I2C write. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_WRITE 0x1
+/* enum: Bus switch off I2C no access IO exp. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_NO_ACCESS_IO_EXP 0x2
+/* enum: Bus switch off I2C no access module. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_OFF_I2C_NO_ACCESS_MODULE 0x3
+/* enum: IO exp I2C configure. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_IO_EXP_I2C_CONFIGURE 0x4
+/* enum: Bus switch I2C no cross talk. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_BUS_SWITCH_I2C_NO_CROSSTALK 0x5
+/* enum: Module presence. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_PRESENCE 0x6
+/* enum: Module ID I2C access. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_ID_I2C_ACCESS 0x7
+/* enum: Module ID sane value. */
+#define MC_CMD_POLL_BIST_MRSFP_TEST_MODULE_ID_SANE_VALUE 0x8
+
+/* MC_CMD_POLL_BIST_OUT_MEM msgresponse */
+#define MC_CMD_POLL_BIST_OUT_MEM_LEN 36
+/* result */
+/* MC_CMD_POLL_BIST_OUT_RESULT_OFST 0 */
+/* Enum values, see field(s): */
+/* MC_CMD_POLL_BIST_OUT/MC_CMD_POLL_BIST_OUT_RESULT */
+#define MC_CMD_POLL_BIST_OUT_MEM_TEST_OFST 4
+/* enum: Test has completed. */
+#define MC_CMD_POLL_BIST_MEM_COMPLETE 0x0
+/* enum: RAM test - walk ones. */
+#define MC_CMD_POLL_BIST_MEM_MEM_WALK_ONES 0x1
+/* enum: RAM test - walk zeros. */
+#define MC_CMD_POLL_BIST_MEM_MEM_WALK_ZEROS 0x2
+/* enum: RAM test - walking inversions zeros/ones. */
+#define MC_CMD_POLL_BIST_MEM_MEM_INV_ZERO_ONE 0x3
+/* enum: RAM test - walking inversions checkerboard. */
+#define MC_CMD_POLL_BIST_MEM_MEM_INV_CHKBOARD 0x4
+/* enum: Register test - set / clear individual bits. */
+#define MC_CMD_POLL_BIST_MEM_REG 0x5
+/* enum: ECC error detected. */
+#define MC_CMD_POLL_BIST_MEM_ECC 0x6
+/* Failure address, only valid if result is POLL_BIST_FAILED */
+#define MC_CMD_POLL_BIST_OUT_MEM_ADDR_OFST 8
+/* Bus or address space to which the failure address corresponds */
+#define MC_CMD_POLL_BIST_OUT_MEM_BUS_OFST 12
+/* enum: MC MIPS bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_MC 0x0
+/* enum: CSR IREG bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_CSR 0x1
+/* enum: RX DPCPU bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_DPCPU_RX 0x2
+/* enum: TX0 DPCPU bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_DPCPU_TX0 0x3
+/* enum: TX1 DPCPU bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_DPCPU_TX1 0x4
+/* enum: RX DICPU bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_DICPU_RX 0x5
+/* enum: TX DICPU bus. */
+#define MC_CMD_POLL_BIST_MEM_BUS_DICPU_TX 0x6
+/* Pattern written to RAM / register */
+#define MC_CMD_POLL_BIST_OUT_MEM_EXPECT_OFST 16
+/* Actual value read from RAM / register */
+#define MC_CMD_POLL_BIST_OUT_MEM_ACTUAL_OFST 20
+/* ECC error mask */
+#define MC_CMD_POLL_BIST_OUT_MEM_ECC_OFST 24
+/* ECC parity error mask */
+#define MC_CMD_POLL_BIST_OUT_MEM_ECC_PARITY_OFST 28
+/* ECC fatal error mask */
+#define MC_CMD_POLL_BIST_OUT_MEM_ECC_FATAL_OFST 32
+
+
+/***********************************/
+/* MC_CMD_FLUSH_RX_QUEUES
+ * Flush receive queue(s). If SRIOV is enabled (via MC_CMD_SRIOV), then RXQ
+ * flushes should be initiated via this MCDI operation, rather than via
+ * directly writing FLUSH_CMD.
*
- * Locks required: None
- * Return code: 0
+ * The flush is completed (either done/fail) asynchronously (after this command
+ * returns). The driver must still wait for flush done/failure events as usual.
+ */
+#define MC_CMD_FLUSH_RX_QUEUES 0x27
+
+/* MC_CMD_FLUSH_RX_QUEUES_IN msgrequest */
+#define MC_CMD_FLUSH_RX_QUEUES_IN_LENMIN 4
+#define MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX 252
+#define MC_CMD_FLUSH_RX_QUEUES_IN_LEN(num) (0+4*(num))
+#define MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_OFST 0
+#define MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_LEN 4
+#define MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MINNUM 1
+#define MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM 63
+
+/* MC_CMD_FLUSH_RX_QUEUES_OUT msgresponse */
+#define MC_CMD_FLUSH_RX_QUEUES_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_LOOPBACK_MODES
+ * Returns a bitmask of loopback modes available at each speed.
*/
#define MC_CMD_GET_LOOPBACK_MODES 0x28
-#define MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0
-#define MC_CMD_GET_LOOPBACK_MODES_OUT_LEN 32
-#define MC_CMD_GET_LOOPBACK_MODES_100M_OFST 0
-#define MC_CMD_GET_LOOPBACK_MODES_1G_OFST 8
-#define MC_CMD_GET_LOOPBACK_MODES_10G_OFST 16
-#define MC_CMD_GET_LOOPBACK_MODES_SUGGESTED_OFST 24
-
-/* Flow control enumeration */
-#define MC_CMD_FCNTL_OFF 0
-#define MC_CMD_FCNTL_RESPOND 1
-#define MC_CMD_FCNTL_BIDIR 2
-/* Auto - Use what the link has autonegotiated
- * - The driver should modify the advertised capabilities via SET_LINK.CAP
- * to control the negotiated flow control mode.
- * - Can only be set if the PHY supports PAUSE+ASYM capabilities
- * - Never returned by GET_LINK as the value programmed into the MAC
- */
-#define MC_CMD_FCNTL_AUTO 3
-
-/* Generic mac fault bitmask */
-#define MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0
-#define MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1
-#define MC_CMD_MAC_FAULT_XGMII_REMOTE_LBN 1
-#define MC_CMD_MAC_FAULT_XGMII_REMOTE_WIDTH 1
-#define MC_CMD_MAC_FAULT_SGMII_REMOTE_LBN 2
-#define MC_CMD_MAC_FAULT_SGMII_REMOTE_WIDTH 1
-
-/* MC_CMD_GET_LINK:
- * Read the unified MAC/PHY link state
- *
- * Locks required: None
- * Return code: 0, ETIME
+
+/* MC_CMD_GET_LOOPBACK_MODES_IN msgrequest */
+#define MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0
+
+/* MC_CMD_GET_LOOPBACK_MODES_OUT msgresponse */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_LEN 40
+/* Supported loopbacks. */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_100M_OFST 0
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_100M_LEN 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_100M_LO_OFST 0
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_OFST 4
+/* enum: None. */
+#define MC_CMD_LOOPBACK_NONE 0x0
+/* enum: Data. */
+#define MC_CMD_LOOPBACK_DATA 0x1
+/* enum: GMAC. */
+#define MC_CMD_LOOPBACK_GMAC 0x2
+/* enum: XGMII. */
+#define MC_CMD_LOOPBACK_XGMII 0x3
+/* enum: XGXS. */
+#define MC_CMD_LOOPBACK_XGXS 0x4
+/* enum: XAUI. */
+#define MC_CMD_LOOPBACK_XAUI 0x5
+/* enum: GMII. */
+#define MC_CMD_LOOPBACK_GMII 0x6
+/* enum: SGMII. */
+#define MC_CMD_LOOPBACK_SGMII 0x7
+/* enum: XGBR. */
+#define MC_CMD_LOOPBACK_XGBR 0x8
+/* enum: XFI. */
+#define MC_CMD_LOOPBACK_XFI 0x9
+/* enum: XAUI Far. */
+#define MC_CMD_LOOPBACK_XAUI_FAR 0xa
+/* enum: GMII Far. */
+#define MC_CMD_LOOPBACK_GMII_FAR 0xb
+/* enum: SGMII Far. */
+#define MC_CMD_LOOPBACK_SGMII_FAR 0xc
+/* enum: XFI Far. */
+#define MC_CMD_LOOPBACK_XFI_FAR 0xd
+/* enum: GPhy. */
+#define MC_CMD_LOOPBACK_GPHY 0xe
+/* enum: PhyXS. */
+#define MC_CMD_LOOPBACK_PHYXS 0xf
+/* enum: PCS. */
+#define MC_CMD_LOOPBACK_PCS 0x10
+/* enum: PMA-PMD. */
+#define MC_CMD_LOOPBACK_PMAPMD 0x11
+/* enum: Cross-Port. */
+#define MC_CMD_LOOPBACK_XPORT 0x12
+/* enum: XGMII-Wireside. */
+#define MC_CMD_LOOPBACK_XGMII_WS 0x13
+/* enum: XAUI Wireside. */
+#define MC_CMD_LOOPBACK_XAUI_WS 0x14
+/* enum: XAUI Wireside Far. */
+#define MC_CMD_LOOPBACK_XAUI_WS_FAR 0x15
+/* enum: XAUI Wireside near. */
+#define MC_CMD_LOOPBACK_XAUI_WS_NEAR 0x16
+/* enum: GMII Wireside. */
+#define MC_CMD_LOOPBACK_GMII_WS 0x17
+/* enum: XFI Wireside. */
+#define MC_CMD_LOOPBACK_XFI_WS 0x18
+/* enum: XFI Wireside Far. */
+#define MC_CMD_LOOPBACK_XFI_WS_FAR 0x19
+/* enum: PhyXS Wireside. */
+#define MC_CMD_LOOPBACK_PHYXS_WS 0x1a
+/* enum: PMA lanes MAC-Serdes. */
+#define MC_CMD_LOOPBACK_PMA_INT 0x1b
+/* enum: KR Serdes Parallel (Encoder). */
+#define MC_CMD_LOOPBACK_SD_NEAR 0x1c
+/* enum: KR Serdes Serial. */
+#define MC_CMD_LOOPBACK_SD_FAR 0x1d
+/* enum: PMA lanes MAC-Serdes Wireside. */
+#define MC_CMD_LOOPBACK_PMA_INT_WS 0x1e
+/* enum: KR Serdes Parallel Wireside (Full PCS). */
+#define MC_CMD_LOOPBACK_SD_FEP2_WS 0x1f
+/* enum: KR Serdes Parallel Wireside (Sym Aligner to TX). */
+#define MC_CMD_LOOPBACK_SD_FEP1_5_WS 0x20
+/* enum: KR Serdes Parallel Wireside (Deserializer to Serializer). */
+#define MC_CMD_LOOPBACK_SD_FEP_WS 0x21
+/* enum: KR Serdes Serial Wireside. */
+#define MC_CMD_LOOPBACK_SD_FES_WS 0x22
+/* enum: Near side of AOE Siena side port */
+#define MC_CMD_LOOPBACK_AOE_INT_NEAR 0x23
+/* Supported loopbacks. */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_OFST 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_LEN 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_LO_OFST 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_OFST 12
+/* Enum values, see field(s): */
+/* 100M */
+/* Supported loopbacks. */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_10G_OFST 16
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_10G_LEN 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_10G_LO_OFST 16
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_OFST 20
+/* Enum values, see field(s): */
+/* 100M */
+/* Supported loopbacks. */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_OFST 24
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_LEN 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_LO_OFST 24
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_OFST 28
+/* Enum values, see field(s): */
+/* 100M */
+/* Supported loopbacks. */
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_40G_OFST 32
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_40G_LEN 8
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_40G_LO_OFST 32
+#define MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_OFST 36
+/* Enum values, see field(s): */
+/* 100M */
+
+
+/***********************************/
+/* MC_CMD_GET_LINK
+ * Read the unified MAC/PHY link state. Locks required: None Return code: 0,
+ * ETIME.
*/
#define MC_CMD_GET_LINK 0x29
-#define MC_CMD_GET_LINK_IN_LEN 0
-#define MC_CMD_GET_LINK_OUT_LEN 28
-/* near-side and link-partner advertised capabilities */
-#define MC_CMD_GET_LINK_OUT_CAP_OFST 0
-#define MC_CMD_GET_LINK_OUT_LP_CAP_OFST 4
-/* Autonegotiated speed in mbit/s. The link may still be down
- * even if this reads non-zero */
-#define MC_CMD_GET_LINK_OUT_LINK_SPEED_OFST 8
-#define MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_OFST 12
-#define MC_CMD_GET_LINK_OUT_FLAGS_OFST 16
-/* Whether we have overall link up */
-#define MC_CMD_GET_LINK_LINK_UP_LBN 0
-#define MC_CMD_GET_LINK_LINK_UP_WIDTH 1
-#define MC_CMD_GET_LINK_FULL_DUPLEX_LBN 1
-#define MC_CMD_GET_LINK_FULL_DUPLEX_WIDTH 1
-/* Whether we have link at the layers provided by the BPX */
-#define MC_CMD_GET_LINK_BPX_LINK_LBN 2
-#define MC_CMD_GET_LINK_BPX_LINK_WIDTH 1
-/* Whether the PHY has external link */
-#define MC_CMD_GET_LINK_PHY_LINK_LBN 3
-#define MC_CMD_GET_LINK_PHY_LINK_WIDTH 1
-#define MC_CMD_GET_LINK_OUT_FCNTL_OFST 20
-#define MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24
-
-/* MC_CMD_SET_LINK:
- * Write the unified MAC/PHY link configuration
- *
- * A loopback speed of "0" is supported, and means
- * (choose any available speed)
- *
- * Locks required: None
- * Return code: 0, EINVAL, ETIME
+
+/* MC_CMD_GET_LINK_IN msgrequest */
+#define MC_CMD_GET_LINK_IN_LEN 0
+
+/* MC_CMD_GET_LINK_OUT msgresponse */
+#define MC_CMD_GET_LINK_OUT_LEN 28
+/* near-side advertised capabilities */
+#define MC_CMD_GET_LINK_OUT_CAP_OFST 0
+/* link-partner advertised capabilities */
+#define MC_CMD_GET_LINK_OUT_LP_CAP_OFST 4
+/* Autonegotiated speed in mbit/s. The link may still be down even if this
+ * reads non-zero.
+ */
+#define MC_CMD_GET_LINK_OUT_LINK_SPEED_OFST 8
+/* Current loopback setting. */
+#define MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_OFST 12
+/* Enum values, see field(s): */
+/* MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
+#define MC_CMD_GET_LINK_OUT_FLAGS_OFST 16
+#define MC_CMD_GET_LINK_OUT_LINK_UP_LBN 0
+#define MC_CMD_GET_LINK_OUT_LINK_UP_WIDTH 1
+#define MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN 1
+#define MC_CMD_GET_LINK_OUT_FULL_DUPLEX_WIDTH 1
+#define MC_CMD_GET_LINK_OUT_BPX_LINK_LBN 2
+#define MC_CMD_GET_LINK_OUT_BPX_LINK_WIDTH 1
+#define MC_CMD_GET_LINK_OUT_PHY_LINK_LBN 3
+#define MC_CMD_GET_LINK_OUT_PHY_LINK_WIDTH 1
+#define MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_LBN 6
+#define MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_WIDTH 1
+#define MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_LBN 7
+#define MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_WIDTH 1
+/* This returns the negotiated flow control value. */
+#define MC_CMD_GET_LINK_OUT_FCNTL_OFST 20
+/* enum: Flow control is off. */
+#define MC_CMD_FCNTL_OFF 0x0
+/* enum: Respond to flow control. */
+#define MC_CMD_FCNTL_RESPOND 0x1
+/* enum: Respond to and Issue flow control. */
+#define MC_CMD_FCNTL_BIDIR 0x2
+#define MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24
+#define MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0
+#define MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1
+#define MC_CMD_MAC_FAULT_XGMII_REMOTE_LBN 1
+#define MC_CMD_MAC_FAULT_XGMII_REMOTE_WIDTH 1
+#define MC_CMD_MAC_FAULT_SGMII_REMOTE_LBN 2
+#define MC_CMD_MAC_FAULT_SGMII_REMOTE_WIDTH 1
+#define MC_CMD_MAC_FAULT_PENDING_RECONFIG_LBN 3
+#define MC_CMD_MAC_FAULT_PENDING_RECONFIG_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_SET_LINK
+ * Write the unified MAC/PHY link configuration. Locks required: None. Return
+ * code: 0, EINVAL, ETIME
*/
#define MC_CMD_SET_LINK 0x2a
-#define MC_CMD_SET_LINK_IN_LEN 16
-#define MC_CMD_SET_LINK_IN_CAP_OFST 0
-#define MC_CMD_SET_LINK_IN_FLAGS_OFST 4
-#define MC_CMD_SET_LINK_LOWPOWER_LBN 0
-#define MC_CMD_SET_LINK_LOWPOWER_WIDTH 1
-#define MC_CMD_SET_LINK_POWEROFF_LBN 1
-#define MC_CMD_SET_LINK_POWEROFF_WIDTH 1
-#define MC_CMD_SET_LINK_TXDIS_LBN 2
-#define MC_CMD_SET_LINK_TXDIS_WIDTH 1
-#define MC_CMD_SET_LINK_IN_LOOPBACK_MODE_OFST 8
-#define MC_CMD_SET_LINK_IN_LOOPBACK_SPEED_OFST 12
-#define MC_CMD_SET_LINK_OUT_LEN 0
-
-/* MC_CMD_SET_ID_LED:
- * Set indentification LED state
- *
- * Locks required: None
- * Return code: 0, EINVAL
+
+/* MC_CMD_SET_LINK_IN msgrequest */
+#define MC_CMD_SET_LINK_IN_LEN 16
+/* ??? */
+#define MC_CMD_SET_LINK_IN_CAP_OFST 0
+/* Flags */
+#define MC_CMD_SET_LINK_IN_FLAGS_OFST 4
+#define MC_CMD_SET_LINK_IN_LOWPOWER_LBN 0
+#define MC_CMD_SET_LINK_IN_LOWPOWER_WIDTH 1
+#define MC_CMD_SET_LINK_IN_POWEROFF_LBN 1
+#define MC_CMD_SET_LINK_IN_POWEROFF_WIDTH 1
+#define MC_CMD_SET_LINK_IN_TXDIS_LBN 2
+#define MC_CMD_SET_LINK_IN_TXDIS_WIDTH 1
+/* Loopback mode. */
+#define MC_CMD_SET_LINK_IN_LOOPBACK_MODE_OFST 8
+/* Enum values, see field(s): */
+/* MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
+/* A loopback speed of "0" is supported, and means (choose any available
+ * speed).
+ */
+#define MC_CMD_SET_LINK_IN_LOOPBACK_SPEED_OFST 12
+
+/* MC_CMD_SET_LINK_OUT msgresponse */
+#define MC_CMD_SET_LINK_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SET_ID_LED
+ * Set identification LED state. Locks required: None. Return code: 0, EINVAL
*/
#define MC_CMD_SET_ID_LED 0x2b
-#define MC_CMD_SET_ID_LED_IN_LEN 4
-#define MC_CMD_SET_ID_LED_IN_STATE_OFST 0
-#define MC_CMD_LED_OFF 0
-#define MC_CMD_LED_ON 1
-#define MC_CMD_LED_DEFAULT 2
-#define MC_CMD_SET_ID_LED_OUT_LEN 0
-
-/* MC_CMD_SET_MAC:
- * Set MAC configuration
- *
- * The MTU is the MTU programmed directly into the XMAC/GMAC
- * (inclusive of EtherII, VLAN, bug16011 padding)
- *
- * Locks required: None
- * Return code: 0, EINVAL
+
+/* MC_CMD_SET_ID_LED_IN msgrequest */
+#define MC_CMD_SET_ID_LED_IN_LEN 4
+/* Set LED state. */
+#define MC_CMD_SET_ID_LED_IN_STATE_OFST 0
+#define MC_CMD_LED_OFF 0x0 /* enum */
+#define MC_CMD_LED_ON 0x1 /* enum */
+#define MC_CMD_LED_DEFAULT 0x2 /* enum */
+
+/* MC_CMD_SET_ID_LED_OUT msgresponse */
+#define MC_CMD_SET_ID_LED_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SET_MAC
+ * Set MAC configuration. Locks required: None. Return code: 0, EINVAL
*/
#define MC_CMD_SET_MAC 0x2c
-#define MC_CMD_SET_MAC_IN_LEN 24
-#define MC_CMD_SET_MAC_IN_MTU_OFST 0
-#define MC_CMD_SET_MAC_IN_DRAIN_OFST 4
-#define MC_CMD_SET_MAC_IN_ADDR_OFST 8
-#define MC_CMD_SET_MAC_IN_REJECT_OFST 16
-#define MC_CMD_SET_MAC_IN_REJECT_UNCST_LBN 0
-#define MC_CMD_SET_MAC_IN_REJECT_UNCST_WIDTH 1
-#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_LBN 1
-#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_WIDTH 1
-#define MC_CMD_SET_MAC_IN_FCNTL_OFST 20
-#define MC_CMD_SET_MAC_OUT_LEN 0
-
-/* MC_CMD_PHY_STATS:
- * Get generic PHY statistics
- *
- * This call returns the statistics for a generic PHY in a sparse
- * array (indexed by the enumerate). Each value is represented by
- * a 32bit number.
- *
- * If the DMA_ADDR is 0, then no DMA is performed, and the statistics
- * may be read directly out of shared memory. If DMA_ADDR != 0, then
- * the statistics are dmad to that (page-aligned location)
- *
- * Locks required: None
+
+/* MC_CMD_SET_MAC_IN msgrequest */
+#define MC_CMD_SET_MAC_IN_LEN 24
+/* The MTU is the MTU programmed directly into the XMAC/GMAC (inclusive of
+ * EtherII, VLAN, bug16011 padding).
+ */
+#define MC_CMD_SET_MAC_IN_MTU_OFST 0
+#define MC_CMD_SET_MAC_IN_DRAIN_OFST 4
+#define MC_CMD_SET_MAC_IN_ADDR_OFST 8
+#define MC_CMD_SET_MAC_IN_ADDR_LEN 8
+#define MC_CMD_SET_MAC_IN_ADDR_LO_OFST 8
+#define MC_CMD_SET_MAC_IN_ADDR_HI_OFST 12
+#define MC_CMD_SET_MAC_IN_REJECT_OFST 16
+#define MC_CMD_SET_MAC_IN_REJECT_UNCST_LBN 0
+#define MC_CMD_SET_MAC_IN_REJECT_UNCST_WIDTH 1
+#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_LBN 1
+#define MC_CMD_SET_MAC_IN_REJECT_BRDCST_WIDTH 1
+#define MC_CMD_SET_MAC_IN_FCNTL_OFST 20
+/* enum: Flow control is off. */
+/* MC_CMD_FCNTL_OFF 0x0 */
+/* enum: Respond to flow control. */
+/* MC_CMD_FCNTL_RESPOND 0x1 */
+/* enum: Respond to and Issue flow control. */
+/* MC_CMD_FCNTL_BIDIR 0x2 */
+/* enum: Auto neg flow control. */
+#define MC_CMD_FCNTL_AUTO 0x3
+
+/* MC_CMD_SET_MAC_OUT msgresponse */
+#define MC_CMD_SET_MAC_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PHY_STATS
+ * Get generic PHY statistics. This call returns the statistics for a generic
+ * PHY in a sparse array (indexed by the enumerate). Each value is represented
+ * by a 32bit number. If the DMA_ADDR is 0, then no DMA is performed, and the
+ * statistics may be read from the message response. If DMA_ADDR != 0, then the
+ * statistics are dmad to that (page-aligned location). Locks required: None.
* Returns: 0, ETIME
- * Response methods: shared memory, event
*/
#define MC_CMD_PHY_STATS 0x2d
-#define MC_CMD_PHY_STATS_IN_LEN 8
-#define MC_CMD_PHY_STATS_IN_DMA_ADDR_LO_OFST 0
-#define MC_CMD_PHY_STATS_IN_DMA_ADDR_HI_OFST 4
-#define MC_CMD_PHY_STATS_OUT_DMA_LEN 0
-#define MC_CMD_PHY_STATS_OUT_NO_DMA_LEN (MC_CMD_PHY_NSTATS * 4)
-
-/* Unified MAC statistics enumeration */
-#define MC_CMD_MAC_GENERATION_START 0
-#define MC_CMD_MAC_TX_PKTS 1
-#define MC_CMD_MAC_TX_PAUSE_PKTS 2
-#define MC_CMD_MAC_TX_CONTROL_PKTS 3
-#define MC_CMD_MAC_TX_UNICAST_PKTS 4
-#define MC_CMD_MAC_TX_MULTICAST_PKTS 5
-#define MC_CMD_MAC_TX_BROADCAST_PKTS 6
-#define MC_CMD_MAC_TX_BYTES 7
-#define MC_CMD_MAC_TX_BAD_BYTES 8
-#define MC_CMD_MAC_TX_LT64_PKTS 9
-#define MC_CMD_MAC_TX_64_PKTS 10
-#define MC_CMD_MAC_TX_65_TO_127_PKTS 11
-#define MC_CMD_MAC_TX_128_TO_255_PKTS 12
-#define MC_CMD_MAC_TX_256_TO_511_PKTS 13
-#define MC_CMD_MAC_TX_512_TO_1023_PKTS 14
-#define MC_CMD_MAC_TX_1024_TO_15XX_PKTS 15
-#define MC_CMD_MAC_TX_15XX_TO_JUMBO_PKTS 16
-#define MC_CMD_MAC_TX_GTJUMBO_PKTS 17
-#define MC_CMD_MAC_TX_BAD_FCS_PKTS 18
-#define MC_CMD_MAC_TX_SINGLE_COLLISION_PKTS 19
-#define MC_CMD_MAC_TX_MULTIPLE_COLLISION_PKTS 20
-#define MC_CMD_MAC_TX_EXCESSIVE_COLLISION_PKTS 21
-#define MC_CMD_MAC_TX_LATE_COLLISION_PKTS 22
-#define MC_CMD_MAC_TX_DEFERRED_PKTS 23
-#define MC_CMD_MAC_TX_EXCESSIVE_DEFERRED_PKTS 24
-#define MC_CMD_MAC_TX_NON_TCPUDP_PKTS 25
-#define MC_CMD_MAC_TX_MAC_SRC_ERR_PKTS 26
-#define MC_CMD_MAC_TX_IP_SRC_ERR_PKTS 27
-#define MC_CMD_MAC_RX_PKTS 28
-#define MC_CMD_MAC_RX_PAUSE_PKTS 29
-#define MC_CMD_MAC_RX_GOOD_PKTS 30
-#define MC_CMD_MAC_RX_CONTROL_PKTS 31
-#define MC_CMD_MAC_RX_UNICAST_PKTS 32
-#define MC_CMD_MAC_RX_MULTICAST_PKTS 33
-#define MC_CMD_MAC_RX_BROADCAST_PKTS 34
-#define MC_CMD_MAC_RX_BYTES 35
-#define MC_CMD_MAC_RX_BAD_BYTES 36
-#define MC_CMD_MAC_RX_64_PKTS 37
-#define MC_CMD_MAC_RX_65_TO_127_PKTS 38
-#define MC_CMD_MAC_RX_128_TO_255_PKTS 39
-#define MC_CMD_MAC_RX_256_TO_511_PKTS 40
-#define MC_CMD_MAC_RX_512_TO_1023_PKTS 41
-#define MC_CMD_MAC_RX_1024_TO_15XX_PKTS 42
-#define MC_CMD_MAC_RX_15XX_TO_JUMBO_PKTS 43
-#define MC_CMD_MAC_RX_GTJUMBO_PKTS 44
-#define MC_CMD_MAC_RX_UNDERSIZE_PKTS 45
-#define MC_CMD_MAC_RX_BAD_FCS_PKTS 46
-#define MC_CMD_MAC_RX_OVERFLOW_PKTS 47
-#define MC_CMD_MAC_RX_FALSE_CARRIER_PKTS 48
-#define MC_CMD_MAC_RX_SYMBOL_ERROR_PKTS 49
-#define MC_CMD_MAC_RX_ALIGN_ERROR_PKTS 50
-#define MC_CMD_MAC_RX_LENGTH_ERROR_PKTS 51
-#define MC_CMD_MAC_RX_INTERNAL_ERROR_PKTS 52
-#define MC_CMD_MAC_RX_JABBER_PKTS 53
-#define MC_CMD_MAC_RX_NODESC_DROPS 54
-#define MC_CMD_MAC_RX_LANES01_CHAR_ERR 55
-#define MC_CMD_MAC_RX_LANES23_CHAR_ERR 56
-#define MC_CMD_MAC_RX_LANES01_DISP_ERR 57
-#define MC_CMD_MAC_RX_LANES23_DISP_ERR 58
-#define MC_CMD_MAC_RX_MATCH_FAULT 59
-#define MC_CMD_GMAC_DMABUF_START 64
-#define MC_CMD_GMAC_DMABUF_END 95
-/* Insert new members here. */
-#define MC_CMD_MAC_GENERATION_END 96
-#define MC_CMD_MAC_NSTATS (MC_CMD_MAC_GENERATION_END+1)
-
-/* MC_CMD_MAC_STATS:
- * Get unified GMAC/XMAC statistics
- *
- * This call returns unified statistics maintained by the MC as it
- * switches between the GMAC and XMAC. The MC will write out all
- * supported stats. The driver should zero initialise the buffer to
- * guarantee consistent results.
- *
- * Locks required: None
- * Returns: 0
- * Response methods: shared memory, event
+
+/* MC_CMD_PHY_STATS_IN msgrequest */
+#define MC_CMD_PHY_STATS_IN_LEN 8
+/* ??? */
+#define MC_CMD_PHY_STATS_IN_DMA_ADDR_OFST 0
+#define MC_CMD_PHY_STATS_IN_DMA_ADDR_LEN 8
+#define MC_CMD_PHY_STATS_IN_DMA_ADDR_LO_OFST 0
+#define MC_CMD_PHY_STATS_IN_DMA_ADDR_HI_OFST 4
+
+/* MC_CMD_PHY_STATS_OUT_DMA msgresponse */
+#define MC_CMD_PHY_STATS_OUT_DMA_LEN 0
+
+/* MC_CMD_PHY_STATS_OUT_NO_DMA msgresponse */
+#define MC_CMD_PHY_STATS_OUT_NO_DMA_LEN (((MC_CMD_PHY_NSTATS*32))>>3)
+#define MC_CMD_PHY_STATS_OUT_NO_DMA_STATISTICS_OFST 0
+#define MC_CMD_PHY_STATS_OUT_NO_DMA_STATISTICS_LEN 4
+#define MC_CMD_PHY_STATS_OUT_NO_DMA_STATISTICS_NUM MC_CMD_PHY_NSTATS
+/* enum: OUI. */
+#define MC_CMD_OUI 0x0
+/* enum: PMA-PMD Link Up. */
+#define MC_CMD_PMA_PMD_LINK_UP 0x1
+/* enum: PMA-PMD RX Fault. */
+#define MC_CMD_PMA_PMD_RX_FAULT 0x2
+/* enum: PMA-PMD TX Fault. */
+#define MC_CMD_PMA_PMD_TX_FAULT 0x3
+/* enum: PMA-PMD Signal */
+#define MC_CMD_PMA_PMD_SIGNAL 0x4
+/* enum: PMA-PMD SNR A. */
+#define MC_CMD_PMA_PMD_SNR_A 0x5
+/* enum: PMA-PMD SNR B. */
+#define MC_CMD_PMA_PMD_SNR_B 0x6
+/* enum: PMA-PMD SNR C. */
+#define MC_CMD_PMA_PMD_SNR_C 0x7
+/* enum: PMA-PMD SNR D. */
+#define MC_CMD_PMA_PMD_SNR_D 0x8
+/* enum: PCS Link Up. */
+#define MC_CMD_PCS_LINK_UP 0x9
+/* enum: PCS RX Fault. */
+#define MC_CMD_PCS_RX_FAULT 0xa
+/* enum: PCS TX Fault. */
+#define MC_CMD_PCS_TX_FAULT 0xb
+/* enum: PCS BER. */
+#define MC_CMD_PCS_BER 0xc
+/* enum: PCS Block Errors. */
+#define MC_CMD_PCS_BLOCK_ERRORS 0xd
+/* enum: PhyXS Link Up. */
+#define MC_CMD_PHYXS_LINK_UP 0xe
+/* enum: PhyXS RX Fault. */
+#define MC_CMD_PHYXS_RX_FAULT 0xf
+/* enum: PhyXS TX Fault. */
+#define MC_CMD_PHYXS_TX_FAULT 0x10
+/* enum: PhyXS Align. */
+#define MC_CMD_PHYXS_ALIGN 0x11
+/* enum: PhyXS Sync. */
+#define MC_CMD_PHYXS_SYNC 0x12
+/* enum: AN link-up. */
+#define MC_CMD_AN_LINK_UP 0x13
+/* enum: AN Complete. */
+#define MC_CMD_AN_COMPLETE 0x14
+/* enum: AN 10GBaseT Status. */
+#define MC_CMD_AN_10GBT_STATUS 0x15
+/* enum: Clause 22 Link-Up. */
+#define MC_CMD_CL22_LINK_UP 0x16
+/* enum: (Last entry) */
+#define MC_CMD_PHY_NSTATS 0x17
+
+
+/***********************************/
+/* MC_CMD_MAC_STATS
+ * Get generic MAC statistics. This call returns unified statistics maintained
+ * by the MC as it switches between the GMAC and XMAC. The MC will write out
+ * all supported stats. The driver should zero initialise the buffer to
+ * guarantee consistent results. If the DMA_ADDR is 0, then no DMA is
+ * performed, and the statistics may be read from the message response. If
+ * DMA_ADDR != 0, then the statistics are dmad to that (page-aligned location).
+ * Locks required: None. Returns: 0, ETIME
*/
#define MC_CMD_MAC_STATS 0x2e
-#define MC_CMD_MAC_STATS_IN_LEN 16
-#define MC_CMD_MAC_STATS_IN_DMA_ADDR_LO_OFST 0
-#define MC_CMD_MAC_STATS_IN_DMA_ADDR_HI_OFST 4
-#define MC_CMD_MAC_STATS_IN_CMD_OFST 8
-#define MC_CMD_MAC_STATS_CMD_DMA_LBN 0
-#define MC_CMD_MAC_STATS_CMD_DMA_WIDTH 1
-#define MC_CMD_MAC_STATS_CMD_CLEAR_LBN 1
-#define MC_CMD_MAC_STATS_CMD_CLEAR_WIDTH 1
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_LBN 2
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_CHANGE_WIDTH 1
-/* Remaining PERIOD* fields only relevant when PERIODIC_CHANGE is set */
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_LBN 3
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_ENABLE_WIDTH 1
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_LBN 4
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_CLEAR_WIDTH 1
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT_LBN 5
-#define MC_CMD_MAC_STATS_CMD_PERIODIC_NOEVENT_WIDTH 1
-#define MC_CMD_MAC_STATS_CMD_PERIOD_MS_LBN 16
-#define MC_CMD_MAC_STATS_CMD_PERIOD_MS_WIDTH 16
-#define MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12
-
-#define MC_CMD_MAC_STATS_OUT_LEN 0
-
-/* Callisto flags */
-#define MC_CMD_SFT9001_ROBUST_LBN 0
-#define MC_CMD_SFT9001_ROBUST_WIDTH 1
-#define MC_CMD_SFT9001_SHORT_REACH_LBN 1
-#define MC_CMD_SFT9001_SHORT_REACH_WIDTH 1
-
-/* MC_CMD_SFT9001_GET:
- * Read current callisto specific setting
- *
- * Locks required: None
- * Returns: 0, ETIME
- */
-#define MC_CMD_SFT9001_GET 0x30
-#define MC_CMD_SFT9001_GET_IN_LEN 0
-#define MC_CMD_SFT9001_GET_OUT_LEN 4
-#define MC_CMD_SFT9001_GET_OUT_FLAGS_OFST 0
-/* MC_CMD_SFT9001_SET:
- * Write current callisto specific setting
+/* MC_CMD_MAC_STATS_IN msgrequest */
+#define MC_CMD_MAC_STATS_IN_LEN 16
+/* ??? */
+#define MC_CMD_MAC_STATS_IN_DMA_ADDR_OFST 0
+#define MC_CMD_MAC_STATS_IN_DMA_ADDR_LEN 8
+#define MC_CMD_MAC_STATS_IN_DMA_ADDR_LO_OFST 0
+#define MC_CMD_MAC_STATS_IN_DMA_ADDR_HI_OFST 4
+#define MC_CMD_MAC_STATS_IN_CMD_OFST 8
+#define MC_CMD_MAC_STATS_IN_DMA_LBN 0
+#define MC_CMD_MAC_STATS_IN_DMA_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_CLEAR_LBN 1
+#define MC_CMD_MAC_STATS_IN_CLEAR_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_PERIODIC_CHANGE_LBN 2
+#define MC_CMD_MAC_STATS_IN_PERIODIC_CHANGE_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_PERIODIC_ENABLE_LBN 3
+#define MC_CMD_MAC_STATS_IN_PERIODIC_ENABLE_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_PERIODIC_CLEAR_LBN 4
+#define MC_CMD_MAC_STATS_IN_PERIODIC_CLEAR_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_PERIODIC_NOEVENT_LBN 5
+#define MC_CMD_MAC_STATS_IN_PERIODIC_NOEVENT_WIDTH 1
+#define MC_CMD_MAC_STATS_IN_PERIOD_MS_LBN 16
+#define MC_CMD_MAC_STATS_IN_PERIOD_MS_WIDTH 16
+#define MC_CMD_MAC_STATS_IN_DMA_LEN_OFST 12
+
+/* MC_CMD_MAC_STATS_OUT_DMA msgresponse */
+#define MC_CMD_MAC_STATS_OUT_DMA_LEN 0
+
+/* MC_CMD_MAC_STATS_OUT_NO_DMA msgresponse */
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_LEN (((MC_CMD_MAC_NSTATS*64))>>3)
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_OFST 0
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_LEN 8
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_LO_OFST 0
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_OFST 4
+#define MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS
+#define MC_CMD_MAC_GENERATION_START 0x0 /* enum */
+#define MC_CMD_MAC_TX_PKTS 0x1 /* enum */
+#define MC_CMD_MAC_TX_PAUSE_PKTS 0x2 /* enum */
+#define MC_CMD_MAC_TX_CONTROL_PKTS 0x3 /* enum */
+#define MC_CMD_MAC_TX_UNICAST_PKTS 0x4 /* enum */
+#define MC_CMD_MAC_TX_MULTICAST_PKTS 0x5 /* enum */
+#define MC_CMD_MAC_TX_BROADCAST_PKTS 0x6 /* enum */
+#define MC_CMD_MAC_TX_BYTES 0x7 /* enum */
+#define MC_CMD_MAC_TX_BAD_BYTES 0x8 /* enum */
+#define MC_CMD_MAC_TX_LT64_PKTS 0x9 /* enum */
+#define MC_CMD_MAC_TX_64_PKTS 0xa /* enum */
+#define MC_CMD_MAC_TX_65_TO_127_PKTS 0xb /* enum */
+#define MC_CMD_MAC_TX_128_TO_255_PKTS 0xc /* enum */
+#define MC_CMD_MAC_TX_256_TO_511_PKTS 0xd /* enum */
+#define MC_CMD_MAC_TX_512_TO_1023_PKTS 0xe /* enum */
+#define MC_CMD_MAC_TX_1024_TO_15XX_PKTS 0xf /* enum */
+#define MC_CMD_MAC_TX_15XX_TO_JUMBO_PKTS 0x10 /* enum */
+#define MC_CMD_MAC_TX_GTJUMBO_PKTS 0x11 /* enum */
+#define MC_CMD_MAC_TX_BAD_FCS_PKTS 0x12 /* enum */
+#define MC_CMD_MAC_TX_SINGLE_COLLISION_PKTS 0x13 /* enum */
+#define MC_CMD_MAC_TX_MULTIPLE_COLLISION_PKTS 0x14 /* enum */
+#define MC_CMD_MAC_TX_EXCESSIVE_COLLISION_PKTS 0x15 /* enum */
+#define MC_CMD_MAC_TX_LATE_COLLISION_PKTS 0x16 /* enum */
+#define MC_CMD_MAC_TX_DEFERRED_PKTS 0x17 /* enum */
+#define MC_CMD_MAC_TX_EXCESSIVE_DEFERRED_PKTS 0x18 /* enum */
+#define MC_CMD_MAC_TX_NON_TCPUDP_PKTS 0x19 /* enum */
+#define MC_CMD_MAC_TX_MAC_SRC_ERR_PKTS 0x1a /* enum */
+#define MC_CMD_MAC_TX_IP_SRC_ERR_PKTS 0x1b /* enum */
+#define MC_CMD_MAC_RX_PKTS 0x1c /* enum */
+#define MC_CMD_MAC_RX_PAUSE_PKTS 0x1d /* enum */
+#define MC_CMD_MAC_RX_GOOD_PKTS 0x1e /* enum */
+#define MC_CMD_MAC_RX_CONTROL_PKTS 0x1f /* enum */
+#define MC_CMD_MAC_RX_UNICAST_PKTS 0x20 /* enum */
+#define MC_CMD_MAC_RX_MULTICAST_PKTS 0x21 /* enum */
+#define MC_CMD_MAC_RX_BROADCAST_PKTS 0x22 /* enum */
+#define MC_CMD_MAC_RX_BYTES 0x23 /* enum */
+#define MC_CMD_MAC_RX_BAD_BYTES 0x24 /* enum */
+#define MC_CMD_MAC_RX_64_PKTS 0x25 /* enum */
+#define MC_CMD_MAC_RX_65_TO_127_PKTS 0x26 /* enum */
+#define MC_CMD_MAC_RX_128_TO_255_PKTS 0x27 /* enum */
+#define MC_CMD_MAC_RX_256_TO_511_PKTS 0x28 /* enum */
+#define MC_CMD_MAC_RX_512_TO_1023_PKTS 0x29 /* enum */
+#define MC_CMD_MAC_RX_1024_TO_15XX_PKTS 0x2a /* enum */
+#define MC_CMD_MAC_RX_15XX_TO_JUMBO_PKTS 0x2b /* enum */
+#define MC_CMD_MAC_RX_GTJUMBO_PKTS 0x2c /* enum */
+#define MC_CMD_MAC_RX_UNDERSIZE_PKTS 0x2d /* enum */
+#define MC_CMD_MAC_RX_BAD_FCS_PKTS 0x2e /* enum */
+#define MC_CMD_MAC_RX_OVERFLOW_PKTS 0x2f /* enum */
+#define MC_CMD_MAC_RX_FALSE_CARRIER_PKTS 0x30 /* enum */
+#define MC_CMD_MAC_RX_SYMBOL_ERROR_PKTS 0x31 /* enum */
+#define MC_CMD_MAC_RX_ALIGN_ERROR_PKTS 0x32 /* enum */
+#define MC_CMD_MAC_RX_LENGTH_ERROR_PKTS 0x33 /* enum */
+#define MC_CMD_MAC_RX_INTERNAL_ERROR_PKTS 0x34 /* enum */
+#define MC_CMD_MAC_RX_JABBER_PKTS 0x35 /* enum */
+#define MC_CMD_MAC_RX_NODESC_DROPS 0x36 /* enum */
+#define MC_CMD_MAC_RX_LANES01_CHAR_ERR 0x37 /* enum */
+#define MC_CMD_MAC_RX_LANES23_CHAR_ERR 0x38 /* enum */
+#define MC_CMD_MAC_RX_LANES01_DISP_ERR 0x39 /* enum */
+#define MC_CMD_MAC_RX_LANES23_DISP_ERR 0x3a /* enum */
+#define MC_CMD_MAC_RX_MATCH_FAULT 0x3b /* enum */
+/* enum: PM trunc_bb_overflow counter. Valid for EF10 with PM_AND_RXDP_COUNTERS
+ * capability only.
+ */
+#define MC_CMD_MAC_PM_TRUNC_BB_OVERFLOW 0x3c
+/* enum: PM discard_bb_overflow counter. Valid for EF10 with
+ * PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_PM_DISCARD_BB_OVERFLOW 0x3d
+/* enum: PM trunc_vfifo_full counter. Valid for EF10 with PM_AND_RXDP_COUNTERS
+ * capability only.
+ */
+#define MC_CMD_MAC_PM_TRUNC_VFIFO_FULL 0x3e
+/* enum: PM discard_vfifo_full counter. Valid for EF10 with
+ * PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_PM_DISCARD_VFIFO_FULL 0x3f
+/* enum: PM trunc_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS
+ * capability only.
+ */
+#define MC_CMD_MAC_PM_TRUNC_QBB 0x40
+/* enum: PM discard_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS
+ * capability only.
+ */
+#define MC_CMD_MAC_PM_DISCARD_QBB 0x41
+/* enum: PM discard_mapping counter. Valid for EF10 with PM_AND_RXDP_COUNTERS
+ * capability only.
+ */
+#define MC_CMD_MAC_PM_DISCARD_MAPPING 0x42
+/* enum: RXDP counter: Number of packets dropped due to the queue being
+ * disabled. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_RXDP_Q_DISABLED_PKTS 0x43
+/* enum: RXDP counter: Number of packets dropped by the DICPU. Valid for EF10
+ * with PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_RXDP_DI_DROPPED_PKTS 0x45
+/* enum: RXDP counter: Number of non-host packets. Valid for EF10 with
+ * PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_RXDP_STREAMING_PKTS 0x46
+/* enum: RXDP counter: Number of times an emergency descriptor fetch was
+ * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_RXDP_EMERGENCY_FETCH_CONDITIONS 0x47
+/* enum: RXDP counter: Number of times the DPCPU waited for an existing
+ * descriptor fetch. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only.
+ */
+#define MC_CMD_MAC_RXDP_EMERGENCY_WAIT_CONDITIONS 0x48
+/* enum: Start of GMAC stats buffer space, for Siena only. */
+#define MC_CMD_GMAC_DMABUF_START 0x40
+/* enum: End of GMAC stats buffer space, for Siena only. */
+#define MC_CMD_GMAC_DMABUF_END 0x5f
+#define MC_CMD_MAC_GENERATION_END 0x60 /* enum */
+#define MC_CMD_MAC_NSTATS 0x61 /* enum */
+
+
+/***********************************/
+/* MC_CMD_SRIOV
+ * to be documented
+ */
+#define MC_CMD_SRIOV 0x30
+
+/* MC_CMD_SRIOV_IN msgrequest */
+#define MC_CMD_SRIOV_IN_LEN 12
+#define MC_CMD_SRIOV_IN_ENABLE_OFST 0
+#define MC_CMD_SRIOV_IN_VI_BASE_OFST 4
+#define MC_CMD_SRIOV_IN_VF_COUNT_OFST 8
+
+/* MC_CMD_SRIOV_OUT msgresponse */
+#define MC_CMD_SRIOV_OUT_LEN 8
+#define MC_CMD_SRIOV_OUT_VI_SCALE_OFST 0
+#define MC_CMD_SRIOV_OUT_VF_TOTAL_OFST 4
+
+/* MC_CMD_MEMCPY_RECORD_TYPEDEF structuredef */
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_LEN 32
+/* this is only used for the first record */
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_OFST 0
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_LBN 0
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_WIDTH 32
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_OFST 4
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_LBN 32
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_WIDTH 32
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_OFST 8
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LEN 8
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_OFST 8
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_OFST 12
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LBN 64
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_WIDTH 64
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_OFST 16
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE 0x100 /* enum */
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_LBN 128
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_WIDTH 32
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_OFST 20
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LEN 8
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_OFST 20
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_OFST 24
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LBN 160
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_WIDTH 64
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_OFST 28
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_LBN 224
+#define MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_MEMCPY
+ * DMA write data into (Rid,Addr), either by dma reading (Rid,Addr), or by data
+ * embedded directly in the command.
+ *
+ * A common pattern is for a client to use generation counts to signal a dma
+ * update of a datastructure. To facilitate this, this MCDI operation can
+ * contain multiple requests which are executed in strict order. Requests take
+ * the form of duplicating the entire MCDI request continuously (including the
+ * requests record, which is ignored in all but the first structure)
*
- * Locks required: None
- * Returns: 0, ETIME, EINVAL
+ * The source data can either come from a DMA from the host, or it can be
+ * embedded within the request directly, thereby eliminating a DMA read. To
+ * indicate this, the client sets FROM_RID=%RID_INLINE, ADDR_HI=0, and
+ * ADDR_LO=offset, and inserts the data at %offset from the start of the
+ * payload. It's the callers responsibility to ensure that the embedded data
+ * doesn't overlap the records.
+ *
+ * Returns: 0, EINVAL (invalid RID)
*/
-#define MC_CMD_SFT9001_SET 0x31
-#define MC_CMD_SFT9001_SET_IN_LEN 4
-#define MC_CMD_SFT9001_SET_IN_FLAGS_OFST 0
-#define MC_CMD_SFT9001_SET_OUT_LEN 0
+#define MC_CMD_MEMCPY 0x31
+/* MC_CMD_MEMCPY_IN msgrequest */
+#define MC_CMD_MEMCPY_IN_LENMIN 32
+#define MC_CMD_MEMCPY_IN_LENMAX 224
+#define MC_CMD_MEMCPY_IN_LEN(num) (0+32*(num))
+/* see MC_CMD_MEMCPY_RECORD_TYPEDEF */
+#define MC_CMD_MEMCPY_IN_RECORD_OFST 0
+#define MC_CMD_MEMCPY_IN_RECORD_LEN 32
+#define MC_CMD_MEMCPY_IN_RECORD_MINNUM 1
+#define MC_CMD_MEMCPY_IN_RECORD_MAXNUM 7
-/* MC_CMD_WOL_FILTER_SET:
- * Set a WoL filter
- *
- * Locks required: None
- * Returns: 0, EBUSY, EINVAL, ENOSYS
+/* MC_CMD_MEMCPY_OUT msgresponse */
+#define MC_CMD_MEMCPY_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_WOL_FILTER_SET
+ * Set a WoL filter.
*/
#define MC_CMD_WOL_FILTER_SET 0x32
-#define MC_CMD_WOL_FILTER_SET_IN_LEN 192 /* 190 rounded up to a word */
-#define MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0
-#define MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4
-
-/* There is a union at offset 8, following defines overlap due to
- * this */
-#define MC_CMD_WOL_FILTER_SET_IN_DATA_OFST 8
-
-#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_OFST \
- MC_CMD_WOL_FILTER_SET_IN_DATA_OFST
-
-#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_IP_OFST \
- MC_CMD_WOL_FILTER_SET_IN_DATA_OFST
-#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_IP_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 4)
-#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_PORT_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 8)
-#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_PORT_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 10)
-
-#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_IP_OFST \
- MC_CMD_WOL_FILTER_SET_IN_DATA_OFST
-#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_IP_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 16)
-#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_PORT_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 32)
-#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_PORT_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 34)
-
-#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_MASK_OFST \
- MC_CMD_WOL_FILTER_SET_IN_DATA_OFST
-#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 48)
-#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LEN_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 176)
-#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER3_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 177)
-#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER4_OFST \
- (MC_CMD_WOL_FILTER_SET_IN_DATA_OFST + 178)
-
-#define MC_CMD_WOL_FILTER_SET_IN_LINK_MASK_OFST \
- MC_CMD_WOL_FILTER_SET_IN_DATA_OFST
-#define MC_CMD_WOL_FILTER_SET_IN_LINK_UP_LBN 0
-#define MC_CMD_WOL_FILTER_SET_IN_LINK_UP_WIDTH 1
-#define MC_CMD_WOL_FILTER_SET_IN_LINK_DOWN_LBN 1
-#define MC_CMD_WOL_FILTER_SET_IN_LINK_DOWN_WIDTH 1
-
-#define MC_CMD_WOL_FILTER_SET_OUT_LEN 4
-#define MC_CMD_WOL_FILTER_SET_OUT_FILTER_ID_OFST 0
-
-/* WOL Filter types enumeration */
-#define MC_CMD_WOL_TYPE_MAGIC 0x0
- /* unused 0x1 */
-#define MC_CMD_WOL_TYPE_WIN_MAGIC 0x2
-#define MC_CMD_WOL_TYPE_IPV4_SYN 0x3
-#define MC_CMD_WOL_TYPE_IPV6_SYN 0x4
-#define MC_CMD_WOL_TYPE_BITMAP 0x5
-#define MC_CMD_WOL_TYPE_LINK 0x6
-#define MC_CMD_WOL_TYPE_MAX 0x7
-
-#define MC_CMD_FILTER_MODE_SIMPLE 0x0
-#define MC_CMD_FILTER_MODE_STRUCTURED 0xffffffff
-
-/* MC_CMD_WOL_FILTER_REMOVE:
- * Remove a WoL filter
- *
- * Locks required: None
- * Returns: 0, EINVAL, ENOSYS
+
+/* MC_CMD_WOL_FILTER_SET_IN msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_LEN 192
+#define MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0
+#define MC_CMD_FILTER_MODE_SIMPLE 0x0 /* enum */
+#define MC_CMD_FILTER_MODE_STRUCTURED 0xffffffff /* enum */
+/* A type value of 1 is unused. */
+#define MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4
+/* enum: Magic */
+#define MC_CMD_WOL_TYPE_MAGIC 0x0
+/* enum: MS Windows Magic */
+#define MC_CMD_WOL_TYPE_WIN_MAGIC 0x2
+/* enum: IPv4 Syn */
+#define MC_CMD_WOL_TYPE_IPV4_SYN 0x3
+/* enum: IPv6 Syn */
+#define MC_CMD_WOL_TYPE_IPV6_SYN 0x4
+/* enum: Bitmap */
+#define MC_CMD_WOL_TYPE_BITMAP 0x5
+/* enum: Link */
+#define MC_CMD_WOL_TYPE_LINK 0x6
+/* enum: (Above this for future use) */
+#define MC_CMD_WOL_TYPE_MAX 0x7
+#define MC_CMD_WOL_FILTER_SET_IN_DATA_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_DATA_LEN 4
+#define MC_CMD_WOL_FILTER_SET_IN_DATA_NUM 46
+
+/* MC_CMD_WOL_FILTER_SET_IN_MAGIC msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_LEN 16
+/* MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 */
+/* MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 */
+#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_LEN 8
+#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_LO_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_MAGIC_MAC_HI_OFST 12
+
+/* MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_LEN 20
+/* MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 */
+/* MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 */
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_IP_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_IP_OFST 12
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_PORT_OFST 16
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_SRC_PORT_LEN 2
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_PORT_OFST 18
+#define MC_CMD_WOL_FILTER_SET_IN_IPV4_SYN_DST_PORT_LEN 2
+
+/* MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_LEN 44
+/* MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 */
+/* MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 */
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_IP_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_IP_LEN 16
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_IP_OFST 24
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_IP_LEN 16
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_PORT_OFST 40
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_SRC_PORT_LEN 2
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_PORT_OFST 42
+#define MC_CMD_WOL_FILTER_SET_IN_IPV6_SYN_DST_PORT_LEN 2
+
+/* MC_CMD_WOL_FILTER_SET_IN_BITMAP msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LEN 187
+/* MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 */
+/* MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 */
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_MASK_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_MASK_LEN 48
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_BITMAP_OFST 56
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_BITMAP_LEN 128
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LEN_OFST 184
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LEN_LEN 1
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER3_OFST 185
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER3_LEN 1
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER4_OFST 186
+#define MC_CMD_WOL_FILTER_SET_IN_BITMAP_LAYER4_LEN 1
+
+/* MC_CMD_WOL_FILTER_SET_IN_LINK msgrequest */
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_LEN 12
+/* MC_CMD_WOL_FILTER_SET_IN_FILTER_MODE_OFST 0 */
+/* MC_CMD_WOL_FILTER_SET_IN_WOL_TYPE_OFST 4 */
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_MASK_OFST 8
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_UP_LBN 0
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_UP_WIDTH 1
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_DOWN_LBN 1
+#define MC_CMD_WOL_FILTER_SET_IN_LINK_DOWN_WIDTH 1
+
+/* MC_CMD_WOL_FILTER_SET_OUT msgresponse */
+#define MC_CMD_WOL_FILTER_SET_OUT_LEN 4
+#define MC_CMD_WOL_FILTER_SET_OUT_FILTER_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_WOL_FILTER_REMOVE
+ * Remove a WoL filter. Locks required: None. Returns: 0, EINVAL, ENOSYS
*/
#define MC_CMD_WOL_FILTER_REMOVE 0x33
-#define MC_CMD_WOL_FILTER_REMOVE_IN_LEN 4
-#define MC_CMD_WOL_FILTER_REMOVE_IN_FILTER_ID_OFST 0
-#define MC_CMD_WOL_FILTER_REMOVE_OUT_LEN 0
+/* MC_CMD_WOL_FILTER_REMOVE_IN msgrequest */
+#define MC_CMD_WOL_FILTER_REMOVE_IN_LEN 4
+#define MC_CMD_WOL_FILTER_REMOVE_IN_FILTER_ID_OFST 0
-/* MC_CMD_WOL_FILTER_RESET:
- * Reset (i.e. remove all) WoL filters
- *
- * Locks required: None
- * Returns: 0, ENOSYS
+/* MC_CMD_WOL_FILTER_REMOVE_OUT msgresponse */
+#define MC_CMD_WOL_FILTER_REMOVE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_WOL_FILTER_RESET
+ * Reset (i.e. remove all) WoL filters. Locks required: None. Returns: 0,
+ * ENOSYS
*/
#define MC_CMD_WOL_FILTER_RESET 0x34
-#define MC_CMD_WOL_FILTER_RESET_IN_LEN 0
-#define MC_CMD_WOL_FILTER_RESET_OUT_LEN 0
-/* MC_CMD_SET_MCAST_HASH:
- * Set the MCASH hash value without otherwise
- * reconfiguring the MAC
+/* MC_CMD_WOL_FILTER_RESET_IN msgrequest */
+#define MC_CMD_WOL_FILTER_RESET_IN_LEN 4
+#define MC_CMD_WOL_FILTER_RESET_IN_MASK_OFST 0
+#define MC_CMD_WOL_FILTER_RESET_IN_WAKE_FILTERS 0x1 /* enum */
+#define MC_CMD_WOL_FILTER_RESET_IN_LIGHTSOUT_OFFLOADS 0x2 /* enum */
+
+/* MC_CMD_WOL_FILTER_RESET_OUT msgresponse */
+#define MC_CMD_WOL_FILTER_RESET_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SET_MCAST_HASH
+ * Set the MCAST hash value without otherwise reconfiguring the MAC
*/
#define MC_CMD_SET_MCAST_HASH 0x35
-#define MC_CMD_SET_MCAST_HASH_IN_LEN 32
-#define MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST 0
-#define MC_CMD_SET_MCAST_HASH_IN_HASH1_OFST 16
-#define MC_CMD_SET_MCAST_HASH_OUT_LEN 0
-/* MC_CMD_NVRAM_TYPES:
- * Return bitfield indicating available types of virtual NVRAM partitions
- *
- * Locks required: none
- * Returns: 0
+/* MC_CMD_SET_MCAST_HASH_IN msgrequest */
+#define MC_CMD_SET_MCAST_HASH_IN_LEN 32
+#define MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST 0
+#define MC_CMD_SET_MCAST_HASH_IN_HASH0_LEN 16
+#define MC_CMD_SET_MCAST_HASH_IN_HASH1_OFST 16
+#define MC_CMD_SET_MCAST_HASH_IN_HASH1_LEN 16
+
+/* MC_CMD_SET_MCAST_HASH_OUT msgresponse */
+#define MC_CMD_SET_MCAST_HASH_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_NVRAM_TYPES
+ * Return bitfield indicating available types of virtual NVRAM partitions.
+ * Locks required: none. Returns: 0
*/
#define MC_CMD_NVRAM_TYPES 0x36
-#define MC_CMD_NVRAM_TYPES_IN_LEN 0
-#define MC_CMD_NVRAM_TYPES_OUT_LEN 4
-#define MC_CMD_NVRAM_TYPES_OUT_TYPES_OFST 0
-
-/* Supported NVRAM types */
-#define MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO 0
-#define MC_CMD_NVRAM_TYPE_MC_FW 1
-#define MC_CMD_NVRAM_TYPE_MC_FW_BACKUP 2
-#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0 3
-#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1 4
-#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0 5
-#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1 6
-#define MC_CMD_NVRAM_TYPE_EXP_ROM 7
-#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0 8
-#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1 9
-#define MC_CMD_NVRAM_TYPE_PHY_PORT0 10
-#define MC_CMD_NVRAM_TYPE_PHY_PORT1 11
-#define MC_CMD_NVRAM_TYPE_LOG 12
-
-/* MC_CMD_NVRAM_INFO:
- * Read info about a virtual NVRAM partition
- *
- * Locks required: none
- * Returns: 0, EINVAL (bad type)
+
+/* MC_CMD_NVRAM_TYPES_IN msgrequest */
+#define MC_CMD_NVRAM_TYPES_IN_LEN 0
+
+/* MC_CMD_NVRAM_TYPES_OUT msgresponse */
+#define MC_CMD_NVRAM_TYPES_OUT_LEN 4
+/* Bit mask of supported types. */
+#define MC_CMD_NVRAM_TYPES_OUT_TYPES_OFST 0
+/* enum: Disabled callisto. */
+#define MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO 0x0
+/* enum: MC firmware. */
+#define MC_CMD_NVRAM_TYPE_MC_FW 0x1
+/* enum: MC backup firmware. */
+#define MC_CMD_NVRAM_TYPE_MC_FW_BACKUP 0x2
+/* enum: Static configuration Port0. */
+#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0 0x3
+/* enum: Static configuration Port1. */
+#define MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1 0x4
+/* enum: Dynamic configuration Port0. */
+#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0 0x5
+/* enum: Dynamic configuration Port1. */
+#define MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1 0x6
+/* enum: Expansion Rom. */
+#define MC_CMD_NVRAM_TYPE_EXP_ROM 0x7
+/* enum: Expansion Rom Configuration Port0. */
+#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0 0x8
+/* enum: Expansion Rom Configuration Port1. */
+#define MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1 0x9
+/* enum: Phy Configuration Port0. */
+#define MC_CMD_NVRAM_TYPE_PHY_PORT0 0xa
+/* enum: Phy Configuration Port1. */
+#define MC_CMD_NVRAM_TYPE_PHY_PORT1 0xb
+/* enum: Log. */
+#define MC_CMD_NVRAM_TYPE_LOG 0xc
+/* enum: FPGA image. */
+#define MC_CMD_NVRAM_TYPE_FPGA 0xd
+/* enum: FPGA backup image */
+#define MC_CMD_NVRAM_TYPE_FPGA_BACKUP 0xe
+/* enum: FC firmware. */
+#define MC_CMD_NVRAM_TYPE_FC_FW 0xf
+/* enum: FC backup firmware. */
+#define MC_CMD_NVRAM_TYPE_FC_FW_BACKUP 0x10
+/* enum: CPLD image. */
+#define MC_CMD_NVRAM_TYPE_CPLD 0x11
+/* enum: Licensing information. */
+#define MC_CMD_NVRAM_TYPE_LICENSE 0x12
+/* enum: FC Log. */
+#define MC_CMD_NVRAM_TYPE_FC_LOG 0x13
+
+
+/***********************************/
+/* MC_CMD_NVRAM_INFO
+ * Read info about a virtual NVRAM partition. Locks required: none. Returns: 0,
+ * EINVAL (bad type).
*/
#define MC_CMD_NVRAM_INFO 0x37
-#define MC_CMD_NVRAM_INFO_IN_LEN 4
-#define MC_CMD_NVRAM_INFO_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_INFO_OUT_LEN 24
-#define MC_CMD_NVRAM_INFO_OUT_TYPE_OFST 0
-#define MC_CMD_NVRAM_INFO_OUT_SIZE_OFST 4
-#define MC_CMD_NVRAM_INFO_OUT_ERASESIZE_OFST 8
-#define MC_CMD_NVRAM_INFO_OUT_FLAGS_OFST 12
-#define MC_CMD_NVRAM_PROTECTED_LBN 0
-#define MC_CMD_NVRAM_PROTECTED_WIDTH 1
-#define MC_CMD_NVRAM_INFO_OUT_PHYSDEV_OFST 16
-#define MC_CMD_NVRAM_INFO_OUT_PHYSADDR_OFST 20
-
-/* MC_CMD_NVRAM_UPDATE_START:
- * Start a group of update operations on a virtual NVRAM partition
- *
- * Locks required: PHY_LOCK if type==*PHY*
- * Returns: 0, EINVAL (bad type), EACCES (if PHY_LOCK required and not held)
+
+/* MC_CMD_NVRAM_INFO_IN msgrequest */
+#define MC_CMD_NVRAM_INFO_IN_LEN 4
+#define MC_CMD_NVRAM_INFO_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+
+/* MC_CMD_NVRAM_INFO_OUT msgresponse */
+#define MC_CMD_NVRAM_INFO_OUT_LEN 24
+#define MC_CMD_NVRAM_INFO_OUT_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_INFO_OUT_SIZE_OFST 4
+#define MC_CMD_NVRAM_INFO_OUT_ERASESIZE_OFST 8
+#define MC_CMD_NVRAM_INFO_OUT_FLAGS_OFST 12
+#define MC_CMD_NVRAM_INFO_OUT_PROTECTED_LBN 0
+#define MC_CMD_NVRAM_INFO_OUT_PROTECTED_WIDTH 1
+#define MC_CMD_NVRAM_INFO_OUT_TLV_LBN 1
+#define MC_CMD_NVRAM_INFO_OUT_TLV_WIDTH 1
+#define MC_CMD_NVRAM_INFO_OUT_A_B_LBN 7
+#define MC_CMD_NVRAM_INFO_OUT_A_B_WIDTH 1
+#define MC_CMD_NVRAM_INFO_OUT_PHYSDEV_OFST 16
+#define MC_CMD_NVRAM_INFO_OUT_PHYSADDR_OFST 20
+
+
+/***********************************/
+/* MC_CMD_NVRAM_UPDATE_START
+ * Start a group of update operations on a virtual NVRAM partition. Locks
+ * required: PHY_LOCK if type==*PHY*. Returns: 0, EINVAL (bad type), EACCES (if
+ * PHY_LOCK required and not held).
*/
#define MC_CMD_NVRAM_UPDATE_START 0x38
-#define MC_CMD_NVRAM_UPDATE_START_IN_LEN 4
-#define MC_CMD_NVRAM_UPDATE_START_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_UPDATE_START_OUT_LEN 0
-/* MC_CMD_NVRAM_READ:
- * Read data from a virtual NVRAM partition
- *
- * Locks required: PHY_LOCK if type==*PHY*
- * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held)
+/* MC_CMD_NVRAM_UPDATE_START_IN msgrequest */
+#define MC_CMD_NVRAM_UPDATE_START_IN_LEN 4
+#define MC_CMD_NVRAM_UPDATE_START_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+
+/* MC_CMD_NVRAM_UPDATE_START_OUT msgresponse */
+#define MC_CMD_NVRAM_UPDATE_START_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_NVRAM_READ
+ * Read data from a virtual NVRAM partition. Locks required: PHY_LOCK if
+ * type==*PHY*. Returns: 0, EINVAL (bad type/offset/length), EACCES (if
+ * PHY_LOCK required and not held)
*/
#define MC_CMD_NVRAM_READ 0x39
-#define MC_CMD_NVRAM_READ_IN_LEN 12
-#define MC_CMD_NVRAM_READ_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_READ_IN_OFFSET_OFST 4
-#define MC_CMD_NVRAM_READ_IN_LENGTH_OFST 8
-#define MC_CMD_NVRAM_READ_OUT_LEN(_read_bytes) (_read_bytes)
-#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0
-
-/* MC_CMD_NVRAM_WRITE:
- * Write data to a virtual NVRAM partition
- *
- * Locks required: PHY_LOCK if type==*PHY*
- * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held)
+
+/* MC_CMD_NVRAM_READ_IN msgrequest */
+#define MC_CMD_NVRAM_READ_IN_LEN 12
+#define MC_CMD_NVRAM_READ_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_READ_IN_OFFSET_OFST 4
+/* amount to read in bytes */
+#define MC_CMD_NVRAM_READ_IN_LENGTH_OFST 8
+
+/* MC_CMD_NVRAM_READ_OUT msgresponse */
+#define MC_CMD_NVRAM_READ_OUT_LENMIN 1
+#define MC_CMD_NVRAM_READ_OUT_LENMAX 252
+#define MC_CMD_NVRAM_READ_OUT_LEN(num) (0+1*(num))
+#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_OFST 0
+#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_LEN 1
+#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MINNUM 1
+#define MC_CMD_NVRAM_READ_OUT_READ_BUFFER_MAXNUM 252
+
+
+/***********************************/
+/* MC_CMD_NVRAM_WRITE
+ * Write data to a virtual NVRAM partition. Locks required: PHY_LOCK if
+ * type==*PHY*. Returns: 0, EINVAL (bad type/offset/length), EACCES (if
+ * PHY_LOCK required and not held)
*/
#define MC_CMD_NVRAM_WRITE 0x3a
-#define MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_WRITE_IN_OFFSET_OFST 4
-#define MC_CMD_NVRAM_WRITE_IN_LENGTH_OFST 8
-#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12
-#define MC_CMD_NVRAM_WRITE_IN_LEN(_write_bytes) (12 + _write_bytes)
-#define MC_CMD_NVRAM_WRITE_OUT_LEN 0
-
-/* MC_CMD_NVRAM_ERASE:
- * Erase sector(s) from a virtual NVRAM partition
- *
- * Locks required: PHY_LOCK if type==*PHY*
- * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held)
+
+/* MC_CMD_NVRAM_WRITE_IN msgrequest */
+#define MC_CMD_NVRAM_WRITE_IN_LENMIN 13
+#define MC_CMD_NVRAM_WRITE_IN_LENMAX 252
+#define MC_CMD_NVRAM_WRITE_IN_LEN(num) (12+1*(num))
+#define MC_CMD_NVRAM_WRITE_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_WRITE_IN_OFFSET_OFST 4
+#define MC_CMD_NVRAM_WRITE_IN_LENGTH_OFST 8
+#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_OFST 12
+#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN 1
+#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MINNUM 1
+#define MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM 240
+
+/* MC_CMD_NVRAM_WRITE_OUT msgresponse */
+#define MC_CMD_NVRAM_WRITE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_NVRAM_ERASE
+ * Erase sector(s) from a virtual NVRAM partition. Locks required: PHY_LOCK if
+ * type==*PHY*. Returns: 0, EINVAL (bad type/offset/length), EACCES (if
+ * PHY_LOCK required and not held)
*/
#define MC_CMD_NVRAM_ERASE 0x3b
-#define MC_CMD_NVRAM_ERASE_IN_LEN 12
-#define MC_CMD_NVRAM_ERASE_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_ERASE_IN_OFFSET_OFST 4
-#define MC_CMD_NVRAM_ERASE_IN_LENGTH_OFST 8
-#define MC_CMD_NVRAM_ERASE_OUT_LEN 0
-
-/* MC_CMD_NVRAM_UPDATE_FINISH:
- * Finish a group of update operations on a virtual NVRAM partition
- *
- * Locks required: PHY_LOCK if type==*PHY*
- * Returns: 0, EINVAL (bad type/offset/length), EACCES (if PHY_LOCK required and not held)
+
+/* MC_CMD_NVRAM_ERASE_IN msgrequest */
+#define MC_CMD_NVRAM_ERASE_IN_LEN 12
+#define MC_CMD_NVRAM_ERASE_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_ERASE_IN_OFFSET_OFST 4
+#define MC_CMD_NVRAM_ERASE_IN_LENGTH_OFST 8
+
+/* MC_CMD_NVRAM_ERASE_OUT msgresponse */
+#define MC_CMD_NVRAM_ERASE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_NVRAM_UPDATE_FINISH
+ * Finish a group of update operations on a virtual NVRAM partition. Locks
+ * required: PHY_LOCK if type==*PHY*. Returns: 0, EINVAL (bad
+ * type/offset/length), EACCES (if PHY_LOCK required and not held)
*/
#define MC_CMD_NVRAM_UPDATE_FINISH 0x3c
-#define MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN 8
-#define MC_CMD_NVRAM_UPDATE_FINISH_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_UPDATE_FINISH_IN_REBOOT_OFST 4
-#define MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN 0
-/* MC_CMD_REBOOT:
+/* MC_CMD_NVRAM_UPDATE_FINISH_IN msgrequest */
+#define MC_CMD_NVRAM_UPDATE_FINISH_IN_LEN 8
+#define MC_CMD_NVRAM_UPDATE_FINISH_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+#define MC_CMD_NVRAM_UPDATE_FINISH_IN_REBOOT_OFST 4
+
+/* MC_CMD_NVRAM_UPDATE_FINISH_OUT msgresponse */
+#define MC_CMD_NVRAM_UPDATE_FINISH_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_REBOOT
* Reboot the MC.
*
- * The AFTER_ASSERTION flag is intended to be used when the driver notices
- * an assertion failure (at which point it is expected to perform a complete
- * tear down and reinitialise), to allow both ports to reset the MC once
- * in an atomic fashion.
+ * The AFTER_ASSERTION flag is intended to be used when the driver notices an
+ * assertion failure (at which point it is expected to perform a complete tear
+ * down and reinitialise), to allow both ports to reset the MC once in an
+ * atomic fashion.
*
* Production mc firmwares are generally compiled with REBOOT_ON_ASSERT=1,
* which means that they will automatically reboot out of the assertion
* handler, so this is in practise an optional operation. It is still
- * recommended that drivers execute this to support custom firmwares
- * with REBOOT_ON_ASSERT=0.
+ * recommended that drivers execute this to support custom firmwares with
+ * REBOOT_ON_ASSERT=0.
*
- * Locks required: NONE
- * Returns: Nothing. You get back a response with ERR=1, DATALEN=0
+ * Locks required: NONE Returns: Nothing. You get back a response with ERR=1,
+ * DATALEN=0
*/
#define MC_CMD_REBOOT 0x3d
-#define MC_CMD_REBOOT_IN_LEN 4
-#define MC_CMD_REBOOT_IN_FLAGS_OFST 0
-#define MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION 1
-#define MC_CMD_REBOOT_OUT_LEN 0
-/* MC_CMD_SCHEDINFO:
- * Request scheduler info. from the MC.
- *
- * Locks required: NONE
- * Returns: An array of (timeslice,maximum overrun), one for each thread,
- * in ascending order of thread address.s
+/* MC_CMD_REBOOT_IN msgrequest */
+#define MC_CMD_REBOOT_IN_LEN 4
+#define MC_CMD_REBOOT_IN_FLAGS_OFST 0
+#define MC_CMD_REBOOT_FLAGS_AFTER_ASSERTION 0x1 /* enum */
+
+/* MC_CMD_REBOOT_OUT msgresponse */
+#define MC_CMD_REBOOT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SCHEDINFO
+ * Request scheduler info. Locks required: NONE. Returns: An array of
+ * (timeslice,maximum overrun), one for each thread, in ascending order of
+ * thread address.
*/
#define MC_CMD_SCHEDINFO 0x3e
-#define MC_CMD_SCHEDINFO_IN_LEN 0
+/* MC_CMD_SCHEDINFO_IN msgrequest */
+#define MC_CMD_SCHEDINFO_IN_LEN 0
-/* MC_CMD_SET_REBOOT_MODE: (debug)
- * Set the mode for the next MC reboot.
- *
- * Locks required: NONE
- *
- * Sets the reboot mode to the specified value. Returns the old mode.
+/* MC_CMD_SCHEDINFO_OUT msgresponse */
+#define MC_CMD_SCHEDINFO_OUT_LENMIN 4
+#define MC_CMD_SCHEDINFO_OUT_LENMAX 252
+#define MC_CMD_SCHEDINFO_OUT_LEN(num) (0+4*(num))
+#define MC_CMD_SCHEDINFO_OUT_DATA_OFST 0
+#define MC_CMD_SCHEDINFO_OUT_DATA_LEN 4
+#define MC_CMD_SCHEDINFO_OUT_DATA_MINNUM 1
+#define MC_CMD_SCHEDINFO_OUT_DATA_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_REBOOT_MODE
+ * Set the mode for the next MC reboot. Locks required: NONE. Sets the reboot
+ * mode to the specified value. Returns the old mode.
*/
#define MC_CMD_REBOOT_MODE 0x3f
-#define MC_CMD_REBOOT_MODE_IN_LEN 4
-#define MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0
-#define MC_CMD_REBOOT_MODE_OUT_LEN 4
-#define MC_CMD_REBOOT_MODE_OUT_VALUE_OFST 0
-#define MC_CMD_REBOOT_MODE_NORMAL 0
-#define MC_CMD_REBOOT_MODE_SNAPPER 3
-
-/* MC_CMD_DEBUG_LOG:
- * Null request/response command (debug)
- * - sequence number is always zero
- * - only supported on the UART interface
- * (the same set of bytes is delivered as an
- * event over PCI)
- */
-#define MC_CMD_DEBUG_LOG 0x40
-#define MC_CMD_DEBUG_LOG_IN_LEN 0
-#define MC_CMD_DEBUG_LOG_OUT_LEN 0
-
-/* Generic sensor enumeration. Note that a dual port NIC
- * will EITHER expose PHY_COMMON_TEMP OR PHY0_TEMP and
- * PHY1_TEMP depending on whether there is a single sensor
- * in the vicinity of the two port, or one per port.
- */
-#define MC_CMD_SENSOR_CONTROLLER_TEMP 0 /* degC */
-#define MC_CMD_SENSOR_PHY_COMMON_TEMP 1 /* degC */
-#define MC_CMD_SENSOR_CONTROLLER_COOLING 2 /* bool */
-#define MC_CMD_SENSOR_PHY0_TEMP 3 /* degC */
-#define MC_CMD_SENSOR_PHY0_COOLING 4 /* bool */
-#define MC_CMD_SENSOR_PHY1_TEMP 5 /* degC */
-#define MC_CMD_SENSOR_PHY1_COOLING 6 /* bool */
-#define MC_CMD_SENSOR_IN_1V0 7 /* mV */
-#define MC_CMD_SENSOR_IN_1V2 8 /* mV */
-#define MC_CMD_SENSOR_IN_1V8 9 /* mV */
-#define MC_CMD_SENSOR_IN_2V5 10 /* mV */
-#define MC_CMD_SENSOR_IN_3V3 11 /* mV */
-#define MC_CMD_SENSOR_IN_12V0 12 /* mV */
-
-
-/* Sensor state */
-#define MC_CMD_SENSOR_STATE_OK 0
-#define MC_CMD_SENSOR_STATE_WARNING 1
-#define MC_CMD_SENSOR_STATE_FATAL 2
-#define MC_CMD_SENSOR_STATE_BROKEN 3
-
-/* MC_CMD_SENSOR_INFO:
+
+/* MC_CMD_REBOOT_MODE_IN msgrequest */
+#define MC_CMD_REBOOT_MODE_IN_LEN 4
+#define MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0
+/* enum: Normal. */
+#define MC_CMD_REBOOT_MODE_NORMAL 0x0
+/* enum: Power-on Reset. */
+#define MC_CMD_REBOOT_MODE_POR 0x2
+/* enum: Snapper. */
+#define MC_CMD_REBOOT_MODE_SNAPPER 0x3
+/* enum: snapper fake POR */
+#define MC_CMD_REBOOT_MODE_SNAPPER_POR 0x4
+#define MC_CMD_REBOOT_MODE_IN_FAKE_LBN 7
+#define MC_CMD_REBOOT_MODE_IN_FAKE_WIDTH 1
+
+/* MC_CMD_REBOOT_MODE_OUT msgresponse */
+#define MC_CMD_REBOOT_MODE_OUT_LEN 4
+#define MC_CMD_REBOOT_MODE_OUT_VALUE_OFST 0
+
+
+/***********************************/
+/* MC_CMD_SENSOR_INFO
* Returns information about every available sensor.
*
- * Each sensor has a single (16bit) value, and a corresponding state.
- * The mapping between value and sensor is nominally determined by the
- * MC, but in practise is implemented as zero (BROKEN), one (TEMPERATURE),
- * or two (VOLTAGE) ranges per sensor per state.
+ * Each sensor has a single (16bit) value, and a corresponding state. The
+ * mapping between value and state is nominally determined by the MC, but may
+ * be implemented using up to 2 ranges per sensor.
+ *
+ * This call returns a mask (32bit) of the sensors that are supported by this
+ * platform, then an array of sensor information structures, in order of sensor
+ * type (but without gaps for unimplemented sensors). Each structure defines
+ * the ranges for the corresponding sensor. An unused range is indicated by
+ * equal limit values. If one range is used, a value outside that range results
+ * in STATE_FATAL. If two ranges are used, a value outside the second range
+ * results in STATE_FATAL while a value outside the first and inside the second
+ * range results in STATE_WARNING.
+ *
+ * Sensor masks and sensor information arrays are organised into pages. For
+ * backward compatibility, older host software can only use sensors in page 0.
+ * Bit 32 in the sensor mask was previously unused, and is no reserved for use
+ * as the next page flag.
*
- * This call returns a mask (32bit) of the sensors that are supported
- * by this platform, then an array (indexed by MC_CMD_SENSOR) of byte
- * offsets to the per-sensor arrays. Each sensor array has four 16bit
- * numbers, min1, max1, min2, max2.
+ * If the request does not contain a PAGE value then firmware will only return
+ * page 0 of sensor information, with bit 31 in the sensor mask cleared.
*
- * Locks required: None
- * Returns: 0
+ * If the request contains a PAGE value then firmware responds with the sensor
+ * mask and sensor information array for that page of sensors. In this case bit
+ * 31 in the mask is set if another page exists.
+ *
+ * Locks required: None Returns: 0
*/
#define MC_CMD_SENSOR_INFO 0x41
-#define MC_CMD_SENSOR_INFO_IN_LEN 0
-#define MC_CMD_SENSOR_INFO_OUT_MASK_OFST 0
-#define MC_CMD_SENSOR_INFO_OUT_OFFSET_OFST(_x) \
- (4 + (_x))
-#define MC_CMD_SENSOR_INFO_OUT_MIN1_OFST(_ofst) \
- ((_ofst) + 0)
-#define MC_CMD_SENSOR_INFO_OUT_MAX1_OFST(_ofst) \
- ((_ofst) + 2)
-#define MC_CMD_SENSOR_INFO_OUT_MIN2_OFST(_ofst) \
- ((_ofst) + 4)
-#define MC_CMD_SENSOR_INFO_OUT_MAX2_OFST(_ofst) \
- ((_ofst) + 6)
+/* MC_CMD_SENSOR_INFO_IN msgrequest */
+#define MC_CMD_SENSOR_INFO_IN_LEN 0
+
+/* MC_CMD_SENSOR_INFO_EXT_IN msgrequest */
+#define MC_CMD_SENSOR_INFO_EXT_IN_LEN 4
+/* Which page of sensors to report.
+ *
+ * Page 0 contains sensors 0 to 30 (sensor 31 is the next page bit).
+ *
+ * Page 1 contains sensors 32 to 62 (sensor 63 is the next page bit). etc.
+ */
+#define MC_CMD_SENSOR_INFO_EXT_IN_PAGE_OFST 0
+
+/* MC_CMD_SENSOR_INFO_OUT msgresponse */
+#define MC_CMD_SENSOR_INFO_OUT_LENMIN 4
+#define MC_CMD_SENSOR_INFO_OUT_LENMAX 252
+#define MC_CMD_SENSOR_INFO_OUT_LEN(num) (4+8*(num))
+#define MC_CMD_SENSOR_INFO_OUT_MASK_OFST 0
+/* enum: Controller temperature: degC */
+#define MC_CMD_SENSOR_CONTROLLER_TEMP 0x0
+/* enum: Phy common temperature: degC */
+#define MC_CMD_SENSOR_PHY_COMMON_TEMP 0x1
+/* enum: Controller cooling: bool */
+#define MC_CMD_SENSOR_CONTROLLER_COOLING 0x2
+/* enum: Phy 0 temperature: degC */
+#define MC_CMD_SENSOR_PHY0_TEMP 0x3
+/* enum: Phy 0 cooling: bool */
+#define MC_CMD_SENSOR_PHY0_COOLING 0x4
+/* enum: Phy 1 temperature: degC */
+#define MC_CMD_SENSOR_PHY1_TEMP 0x5
+/* enum: Phy 1 cooling: bool */
+#define MC_CMD_SENSOR_PHY1_COOLING 0x6
+/* enum: 1.0v power: mV */
+#define MC_CMD_SENSOR_IN_1V0 0x7
+/* enum: 1.2v power: mV */
+#define MC_CMD_SENSOR_IN_1V2 0x8
+/* enum: 1.8v power: mV */
+#define MC_CMD_SENSOR_IN_1V8 0x9
+/* enum: 2.5v power: mV */
+#define MC_CMD_SENSOR_IN_2V5 0xa
+/* enum: 3.3v power: mV */
+#define MC_CMD_SENSOR_IN_3V3 0xb
+/* enum: 12v power: mV */
+#define MC_CMD_SENSOR_IN_12V0 0xc
+/* enum: 1.2v analogue power: mV */
+#define MC_CMD_SENSOR_IN_1V2A 0xd
+/* enum: reference voltage: mV */
+#define MC_CMD_SENSOR_IN_VREF 0xe
+/* enum: AOE FPGA power: mV */
+#define MC_CMD_SENSOR_OUT_VAOE 0xf
+/* enum: AOE FPGA temperature: degC */
+#define MC_CMD_SENSOR_AOE_TEMP 0x10
+/* enum: AOE FPGA PSU temperature: degC */
+#define MC_CMD_SENSOR_PSU_AOE_TEMP 0x11
+/* enum: AOE PSU temperature: degC */
+#define MC_CMD_SENSOR_PSU_TEMP 0x12
+/* enum: Fan 0 speed: RPM */
+#define MC_CMD_SENSOR_FAN_0 0x13
+/* enum: Fan 1 speed: RPM */
+#define MC_CMD_SENSOR_FAN_1 0x14
+/* enum: Fan 2 speed: RPM */
+#define MC_CMD_SENSOR_FAN_2 0x15
+/* enum: Fan 3 speed: RPM */
+#define MC_CMD_SENSOR_FAN_3 0x16
+/* enum: Fan 4 speed: RPM */
+#define MC_CMD_SENSOR_FAN_4 0x17
+/* enum: AOE FPGA input power: mV */
+#define MC_CMD_SENSOR_IN_VAOE 0x18
+/* enum: AOE FPGA current: mA */
+#define MC_CMD_SENSOR_OUT_IAOE 0x19
+/* enum: AOE FPGA input current: mA */
+#define MC_CMD_SENSOR_IN_IAOE 0x1a
+/* enum: NIC power consumption: W */
+#define MC_CMD_SENSOR_NIC_POWER 0x1b
+/* enum: 0.9v power voltage: mV */
+#define MC_CMD_SENSOR_IN_0V9 0x1c
+/* enum: 0.9v power current: mA */
+#define MC_CMD_SENSOR_IN_I0V9 0x1d
+/* enum: 1.2v power current: mA */
+#define MC_CMD_SENSOR_IN_I1V2 0x1e
+/* enum: Not a sensor: reserved for the next page flag */
+#define MC_CMD_SENSOR_PAGE0_NEXT 0x1f
+/* enum: 0.9v power voltage (at ADC): mV */
+#define MC_CMD_SENSOR_IN_0V9_ADC 0x20
+/* enum: Controller temperature 2: degC */
+#define MC_CMD_SENSOR_CONTROLLER_2_TEMP 0x21
+/* enum: Voltage regulator internal temperature: degC */
+#define MC_CMD_SENSOR_VREG_INTERNAL_TEMP 0x22
+/* enum: 0.9V voltage regulator temperature: degC */
+#define MC_CMD_SENSOR_VREG_0V9_TEMP 0x23
+/* enum: 1.2V voltage regulator temperature: degC */
+#define MC_CMD_SENSOR_VREG_1V2_TEMP 0x24
+/* enum: controller internal temperature sensor voltage (internal ADC): mV */
+#define MC_CMD_SENSOR_CONTROLLER_VPTAT 0x25
+/* enum: controller internal temperature (internal ADC): degC */
+#define MC_CMD_SENSOR_CONTROLLER_INTERNAL_TEMP 0x26
+/* enum: controller internal temperature sensor voltage (external ADC): mV */
+#define MC_CMD_SENSOR_CONTROLLER_VPTAT_EXTADC 0x27
+/* enum: controller internal temperature (external ADC): degC */
+#define MC_CMD_SENSOR_CONTROLLER_INTERNAL_TEMP_EXTADC 0x28
+/* enum: ambient temperature: degC */
+#define MC_CMD_SENSOR_AMBIENT_TEMP 0x29
+/* enum: air flow: bool */
+#define MC_CMD_SENSOR_AIRFLOW 0x2a
+/* enum: voltage between VSS08D and VSS08D at CSR: mV */
+#define MC_CMD_SENSOR_VDD08D_VSS08D_CSR 0x2b
+/* enum: voltage between VSS08D and VSS08D at CSR (external ADC): mV */
+#define MC_CMD_SENSOR_VDD08D_VSS08D_CSR_EXTADC 0x2c
+/* enum: Hotpoint temperature: degC */
+#define MC_CMD_SENSOR_HOTPOINT_TEMP 0x2d
+/* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */
+#define MC_CMD_SENSOR_ENTRY_OFST 4
+#define MC_CMD_SENSOR_ENTRY_LEN 8
+#define MC_CMD_SENSOR_ENTRY_LO_OFST 4
+#define MC_CMD_SENSOR_ENTRY_HI_OFST 8
+#define MC_CMD_SENSOR_ENTRY_MINNUM 0
+#define MC_CMD_SENSOR_ENTRY_MAXNUM 31
+
+/* MC_CMD_SENSOR_INFO_EXT_OUT msgresponse */
+#define MC_CMD_SENSOR_INFO_EXT_OUT_LENMIN 4
+#define MC_CMD_SENSOR_INFO_EXT_OUT_LENMAX 252
+#define MC_CMD_SENSOR_INFO_EXT_OUT_LEN(num) (4+8*(num))
+#define MC_CMD_SENSOR_INFO_EXT_OUT_MASK_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_SENSOR_INFO_OUT */
+#define MC_CMD_SENSOR_INFO_EXT_OUT_NEXT_PAGE_LBN 31
+#define MC_CMD_SENSOR_INFO_EXT_OUT_NEXT_PAGE_WIDTH 1
+/* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */
+/* MC_CMD_SENSOR_ENTRY_OFST 4 */
+/* MC_CMD_SENSOR_ENTRY_LEN 8 */
+/* MC_CMD_SENSOR_ENTRY_LO_OFST 4 */
+/* MC_CMD_SENSOR_ENTRY_HI_OFST 8 */
+/* MC_CMD_SENSOR_ENTRY_MINNUM 0 */
+/* MC_CMD_SENSOR_ENTRY_MAXNUM 31 */
+
+/* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF structuredef */
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_LEN 8
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN1_OFST 0
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN1_LEN 2
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN1_LBN 0
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN1_WIDTH 16
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX1_OFST 2
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX1_LEN 2
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX1_LBN 16
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX1_WIDTH 16
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN2_OFST 4
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN2_LEN 2
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN2_LBN 32
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MIN2_WIDTH 16
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX2_OFST 6
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX2_LEN 2
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX2_LBN 48
+#define MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF_MAX2_WIDTH 16
+
+
+/***********************************/
/* MC_CMD_READ_SENSORS
- * Returns the current reading from each sensor
+ * Returns the current reading from each sensor. DMAs an array of sensor
+ * readings, in order of sensor type (but without gaps for unimplemented
+ * sensors), into host memory. Each array element is a
+ * MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF dword.
*
- * Returns a sparse array of sensor readings (indexed by the sensor
- * type) into host memory. Each array element is a dword.
+ * If the request does not contain the LENGTH field then only sensors 0 to 30
+ * are reported, to avoid DMA buffer overflow in older host software. If the
+ * sensor reading require more space than the LENGTH allows, then return
+ * EINVAL.
*
* The MC will send a SENSOREVT event every time any sensor changes state. The
- * driver is responsible for ensuring that it doesn't miss any events. The board
- * will function normally if all sensors are in STATE_OK or state_WARNING.
- * Otherwise the board should not be expected to function.
+ * driver is responsible for ensuring that it doesn't miss any events. The
+ * board will function normally if all sensors are in STATE_OK or
+ * STATE_WARNING. Otherwise the board should not be expected to function.
*/
#define MC_CMD_READ_SENSORS 0x42
-#define MC_CMD_READ_SENSORS_IN_LEN 8
-#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_LO_OFST 0
-#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_HI_OFST 4
-#define MC_CMD_READ_SENSORS_OUT_LEN 0
-/* Sensor reading fields */
-#define MC_CMD_READ_SENSOR_VALUE_LBN 0
-#define MC_CMD_READ_SENSOR_VALUE_WIDTH 16
-#define MC_CMD_READ_SENSOR_STATE_LBN 16
-#define MC_CMD_READ_SENSOR_STATE_WIDTH 8
-
-
-/* MC_CMD_GET_PHY_STATE:
- * Report current state of PHY. A "zombie" PHY is a PHY that has failed to
- * boot (e.g. due to missing or corrupted firmware).
- *
- * Locks required: None
- * Return code: 0
+/* MC_CMD_READ_SENSORS_IN msgrequest */
+#define MC_CMD_READ_SENSORS_IN_LEN 8
+/* DMA address of host buffer for sensor readings (must be 4Kbyte aligned). */
+#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_OFST 0
+#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_LEN 8
+#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_LO_OFST 0
+#define MC_CMD_READ_SENSORS_IN_DMA_ADDR_HI_OFST 4
+
+/* MC_CMD_READ_SENSORS_EXT_IN msgrequest */
+#define MC_CMD_READ_SENSORS_EXT_IN_LEN 12
+/* DMA address of host buffer for sensor readings */
+#define MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_OFST 0
+#define MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LEN 8
+#define MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_LO_OFST 0
+#define MC_CMD_READ_SENSORS_EXT_IN_DMA_ADDR_HI_OFST 4
+/* Size in bytes of host buffer. */
+#define MC_CMD_READ_SENSORS_EXT_IN_LENGTH_OFST 8
+
+/* MC_CMD_READ_SENSORS_OUT msgresponse */
+#define MC_CMD_READ_SENSORS_OUT_LEN 0
+
+/* MC_CMD_READ_SENSORS_EXT_OUT msgresponse */
+#define MC_CMD_READ_SENSORS_EXT_OUT_LEN 0
+
+/* MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF structuredef */
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_LEN 4
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_VALUE_OFST 0
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_VALUE_LEN 2
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_VALUE_LBN 0
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_VALUE_WIDTH 16
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_OFST 2
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_LEN 1
+/* enum: Ok. */
+#define MC_CMD_SENSOR_STATE_OK 0x0
+/* enum: Breached warning threshold. */
+#define MC_CMD_SENSOR_STATE_WARNING 0x1
+/* enum: Breached fatal threshold. */
+#define MC_CMD_SENSOR_STATE_FATAL 0x2
+/* enum: Fault with sensor. */
+#define MC_CMD_SENSOR_STATE_BROKEN 0x3
+/* enum: Sensor is working but does not currently have a reading. */
+#define MC_CMD_SENSOR_STATE_NO_READING 0x4
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_LBN 16
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_STATE_WIDTH 8
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_TYPE_OFST 3
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_TYPE_LEN 1
+/* Enum values, see field(s): */
+/* MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_TYPE_LBN 24
+#define MC_CMD_SENSOR_VALUE_ENTRY_TYPEDEF_TYPE_WIDTH 8
+
+
+/***********************************/
+/* MC_CMD_GET_PHY_STATE
+ * Report current state of PHY. A 'zombie' PHY is a PHY that has failed to boot
+ * (e.g. due to missing or corrupted firmware). Locks required: None. Return
+ * code: 0
*/
#define MC_CMD_GET_PHY_STATE 0x43
-#define MC_CMD_GET_PHY_STATE_IN_LEN 0
-#define MC_CMD_GET_PHY_STATE_OUT_LEN 4
-#define MC_CMD_GET_PHY_STATE_STATE_OFST 0
-/* PHY state enumeration: */
-#define MC_CMD_PHY_STATE_OK 1
-#define MC_CMD_PHY_STATE_ZOMBIE 2
+/* MC_CMD_GET_PHY_STATE_IN msgrequest */
+#define MC_CMD_GET_PHY_STATE_IN_LEN 0
+/* MC_CMD_GET_PHY_STATE_OUT msgresponse */
+#define MC_CMD_GET_PHY_STATE_OUT_LEN 4
+#define MC_CMD_GET_PHY_STATE_OUT_STATE_OFST 0
+/* enum: Ok. */
+#define MC_CMD_PHY_STATE_OK 0x1
+/* enum: Faulty. */
+#define MC_CMD_PHY_STATE_ZOMBIE 0x2
-/* 802.1Qbb control. 8 Tx queues that map to priorities 0 - 7. Use all 1s to
- * disable 802.Qbb for a given priority. */
+
+/***********************************/
+/* MC_CMD_SETUP_8021QBB
+ * 802.1Qbb control. 8 Tx queues that map to priorities 0 - 7. Use all 1s to
+ * disable 802.Qbb for a given priority.
+ */
#define MC_CMD_SETUP_8021QBB 0x44
-#define MC_CMD_SETUP_8021QBB_IN_LEN 32
-#define MC_CMD_SETUP_8021QBB_OUT_LEN 0
-#define MC_CMD_SETUP_8021QBB_IN_TXQS_OFFST 0
+/* MC_CMD_SETUP_8021QBB_IN msgrequest */
+#define MC_CMD_SETUP_8021QBB_IN_LEN 32
+#define MC_CMD_SETUP_8021QBB_IN_TXQS_OFST 0
+#define MC_CMD_SETUP_8021QBB_IN_TXQS_LEN 32
-/* MC_CMD_WOL_FILTER_GET:
- * Retrieve ID of any WoL filters
- *
- * Locks required: None
- * Returns: 0, ENOSYS
- */
-#define MC_CMD_WOL_FILTER_GET 0x45
-#define MC_CMD_WOL_FILTER_GET_IN_LEN 0
-#define MC_CMD_WOL_FILTER_GET_OUT_LEN 4
-#define MC_CMD_WOL_FILTER_GET_OUT_FILTER_ID_OFST 0
+/* MC_CMD_SETUP_8021QBB_OUT msgresponse */
+#define MC_CMD_SETUP_8021QBB_OUT_LEN 0
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD:
- * Offload a protocol to NIC for lights-out state
- *
- * Locks required: None
- * Returns: 0, ENOSYS
+/***********************************/
+/* MC_CMD_WOL_FILTER_GET
+ * Retrieve ID of any WoL filters. Locks required: None. Returns: 0, ENOSYS
*/
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46
-
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LEN 16
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
+#define MC_CMD_WOL_FILTER_GET 0x45
-/* There is a union at offset 4, following defines overlap due to
- * this */
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_OFST 4
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARPMAC_OFST 4
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARPIP_OFST 10
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSMAC_OFST 4
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSSNIPV6_OFST 10
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NSIPV6_OFST 26
+/* MC_CMD_WOL_FILTER_GET_IN msgrequest */
+#define MC_CMD_WOL_FILTER_GET_IN_LEN 0
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_LEN 4
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_OFST 0
+/* MC_CMD_WOL_FILTER_GET_OUT msgresponse */
+#define MC_CMD_WOL_FILTER_GET_OUT_LEN 4
+#define MC_CMD_WOL_FILTER_GET_OUT_FILTER_ID_OFST 0
-/* MC_CMD_REMOVE_LIGHTSOUT_PROTOCOL_OFFLOAD:
- * Offload a protocol to NIC for lights-out state
- *
- * Locks required: None
+/***********************************/
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD
+ * Add a protocol offload to NIC for lights-out state. Locks required: None.
* Returns: 0, ENOSYS
*/
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46
+
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN msgrequest */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMIN 8
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX 252
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LEN(num) (4+4*(num))
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
+#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_ARP 0x1 /* enum */
+#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_NS 0x2 /* enum */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_OFST 4
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_LEN 4
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MINNUM 1
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MAXNUM 62
+
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP msgrequest */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_LEN 14
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_OFST 4
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_LEN 6
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_IP_OFST 10
+
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS msgrequest */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_LEN 42
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_OFST 4
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_LEN 6
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_OFST 10
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_LEN 16
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_OFST 26
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_LEN 16
+
+/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT msgresponse */
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_LEN 4
+#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD
+ * Remove a protocol offload from NIC for lights-out state. Locks required:
+ * None. Returns: 0, ENOSYS
+ */
#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD 0x47
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT_LEN 0
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_OFST 4
+/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN msgrequest */
+#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8
+#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
+#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_OFST 4
-/* Lights-out offload protocols enumeration */
-#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_ARP 0x1
-#define MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_NS 0x2
+/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT msgresponse */
+#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT_LEN 0
-/* MC_CMD_MAC_RESET_RESTORE:
- * Restore MAC after block reset
- *
- * Locks required: None
- * Returns: 0
+/***********************************/
+/* MC_CMD_MAC_RESET_RESTORE
+ * Restore MAC after block reset. Locks required: None. Returns: 0.
*/
-
#define MC_CMD_MAC_RESET_RESTORE 0x48
-#define MC_CMD_MAC_RESET_RESTORE_IN_LEN 0
-#define MC_CMD_MAC_RESET_RESTORE_OUT_LEN 0
+/* MC_CMD_MAC_RESET_RESTORE_IN msgrequest */
+#define MC_CMD_MAC_RESET_RESTORE_IN_LEN 0
-/* MC_CMD_TEST_ASSERT:
+/* MC_CMD_MAC_RESET_RESTORE_OUT msgresponse */
+#define MC_CMD_MAC_RESET_RESTORE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_TESTASSERT
* Deliberately trigger an assert-detonation in the firmware for testing
- * purposes (i.e. to allow tests that the driver copes gracefully).
- *
- * Locks required: None
- * Returns: 0
+ * purposes (i.e. to allow tests that the driver copes gracefully). Locks
+ * required: None Returns: 0
*/
-
#define MC_CMD_TESTASSERT 0x49
-#define MC_CMD_TESTASSERT_IN_LEN 0
-#define MC_CMD_TESTASSERT_OUT_LEN 0
-/* MC_CMD_WORKAROUND 0x4a
- *
- * Enable/Disable a given workaround. The mcfw will return EINVAL if it
- * doesn't understand the given workaround number - which should not
- * be treated as a hard error by client code.
- *
- * This op does not imply any semantics about each workaround, that's between
- * the driver and the mcfw on a per-workaround basis.
- *
- * Locks required: None
- * Returns: 0, EINVAL
+/* MC_CMD_TESTASSERT_IN msgrequest */
+#define MC_CMD_TESTASSERT_IN_LEN 0
+
+/* MC_CMD_TESTASSERT_OUT msgresponse */
+#define MC_CMD_TESTASSERT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_WORKAROUND
+ * Enable/Disable a given workaround. The mcfw will return EINVAL if it doesn't
+ * understand the given workaround number - which should not be treated as a
+ * hard error by client code. This op does not imply any semantics about each
+ * workaround, that's between the driver and the mcfw on a per-workaround
+ * basis. Locks required: None. Returns: 0, EINVAL .
*/
#define MC_CMD_WORKAROUND 0x4a
-#define MC_CMD_WORKAROUND_IN_LEN 8
-#define MC_CMD_WORKAROUND_IN_TYPE_OFST 0
-#define MC_CMD_WORKAROUND_BUG17230 1
-#define MC_CMD_WORKAROUND_IN_ENABLED_OFST 4
-#define MC_CMD_WORKAROUND_OUT_LEN 0
-/* MC_CMD_GET_PHY_MEDIA_INFO:
+/* MC_CMD_WORKAROUND_IN msgrequest */
+#define MC_CMD_WORKAROUND_IN_LEN 8
+#define MC_CMD_WORKAROUND_IN_TYPE_OFST 0
+/* enum: Bug 17230 work around. */
+#define MC_CMD_WORKAROUND_BUG17230 0x1
+/* enum: Bug 35388 work around (unsafe EVQ writes). */
+#define MC_CMD_WORKAROUND_BUG35388 0x2
+/* enum: Bug35017 workaround (A64 tables must be identity map) */
+#define MC_CMD_WORKAROUND_BUG35017 0x3
+#define MC_CMD_WORKAROUND_IN_ENABLED_OFST 4
+
+/* MC_CMD_WORKAROUND_OUT msgresponse */
+#define MC_CMD_WORKAROUND_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_PHY_MEDIA_INFO
* Read media-specific data from PHY (e.g. SFP/SFP+ module ID information for
- * SFP+ PHYs).
- *
- * The "media type" can be found via GET_PHY_CFG (GET_PHY_CFG_OUT_MEDIA_TYPE);
- * the valid "page number" input values, and the output data, are interpreted
- * on a per-type basis.
- *
- * For SFP+: PAGE=0 or 1 returns a 128-byte block read from module I2C address
- * 0xA0 offset 0 or 0x80.
- * Anything else: currently undefined.
- *
- * Locks required: None
- * Return code: 0
+ * SFP+ PHYs). The 'media type' can be found via GET_PHY_CFG
+ * (GET_PHY_CFG_OUT_MEDIA_TYPE); the valid 'page number' input values, and the
+ * output data, are interpreted on a per-type basis. For SFP+: PAGE=0 or 1
+ * returns a 128-byte block read from module I2C address 0xA0 offset 0 or 0x80.
+ * Anything else: currently undefined. Locks required: None. Return code: 0.
*/
#define MC_CMD_GET_PHY_MEDIA_INFO 0x4b
-#define MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN 4
-#define MC_CMD_GET_PHY_MEDIA_INFO_IN_PAGE_OFST 0
-#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LEN(_num_bytes) (4 + (_num_bytes))
-#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATALEN_OFST 0
-#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST 4
-
-/* MC_CMD_NVRAM_TEST:
- * Test a particular NVRAM partition for valid contents (where "valid"
- * depends on the type of partition).
- *
- * Locks required: None
- * Return code: 0
+
+/* MC_CMD_GET_PHY_MEDIA_INFO_IN msgrequest */
+#define MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN 4
+#define MC_CMD_GET_PHY_MEDIA_INFO_IN_PAGE_OFST 0
+
+/* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_LEN(num) (4+1*(num))
+/* in bytes */
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATALEN_OFST 0
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST 4
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_LEN 1
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MINNUM 1
+#define MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_MAXNUM 248
+
+
+/***********************************/
+/* MC_CMD_NVRAM_TEST
+ * Test a particular NVRAM partition for valid contents (where "valid" depends
+ * on the type of partition).
*/
#define MC_CMD_NVRAM_TEST 0x4c
-#define MC_CMD_NVRAM_TEST_IN_LEN 4
-#define MC_CMD_NVRAM_TEST_IN_TYPE_OFST 0
-#define MC_CMD_NVRAM_TEST_OUT_LEN 4
-#define MC_CMD_NVRAM_TEST_OUT_RESULT_OFST 0
-#define MC_CMD_NVRAM_TEST_PASS 0
-#define MC_CMD_NVRAM_TEST_FAIL 1
-#define MC_CMD_NVRAM_TEST_NOTSUPP 2
-
-/* MC_CMD_MRSFP_TWEAK: (debug)
- * Read status and/or set parameters for the "mrsfp" driver in mr_rusty builds.
+
+/* MC_CMD_NVRAM_TEST_IN msgrequest */
+#define MC_CMD_NVRAM_TEST_IN_LEN 4
+#define MC_CMD_NVRAM_TEST_IN_TYPE_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_NVRAM_TYPES/MC_CMD_NVRAM_TYPES_OUT/TYPES */
+
+/* MC_CMD_NVRAM_TEST_OUT msgresponse */
+#define MC_CMD_NVRAM_TEST_OUT_LEN 4
+#define MC_CMD_NVRAM_TEST_OUT_RESULT_OFST 0
+/* enum: Passed. */
+#define MC_CMD_NVRAM_TEST_PASS 0x0
+/* enum: Failed. */
+#define MC_CMD_NVRAM_TEST_FAIL 0x1
+/* enum: Not supported. */
+#define MC_CMD_NVRAM_TEST_NOTSUPP 0x2
+
+
+/***********************************/
+/* MC_CMD_MRSFP_TWEAK
+ * Read status and/or set parameters for the 'mrsfp' driver in mr_rusty builds.
* I2C I/O expander bits are always read; if equaliser parameters are supplied,
- * they are configured first.
- *
- * Locks required: None
- * Return code: 0, EINVAL
+ * they are configured first. Locks required: None. Return code: 0, EINVAL.
*/
#define MC_CMD_MRSFP_TWEAK 0x4d
-#define MC_CMD_MRSFP_TWEAK_IN_LEN_READ_ONLY 0
-#define MC_CMD_MRSFP_TWEAK_IN_LEN_EQ_CONFIG 16
-#define MC_CMD_MRSFP_TWEAK_IN_TXEQ_LEVEL_OFST 0 /* 0-6 low->high de-emph. */
-#define MC_CMD_MRSFP_TWEAK_IN_TXEQ_DT_CFG_OFST 4 /* 0-8 low->high ref.V */
-#define MC_CMD_MRSFP_TWEAK_IN_RXEQ_BOOST_OFST 8 /* 0-8 low->high boost */
-#define MC_CMD_MRSFP_TWEAK_IN_RXEQ_DT_CFG_OFST 12 /* 0-8 low->high ref.V */
-#define MC_CMD_MRSFP_TWEAK_OUT_LEN 12
-#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_OFST 0 /* input bits */
-#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_OFST 4 /* output bits */
-#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OFST 8 /* dirs: 0=out, 1=in */
-
-/* MC_CMD_TEST_HACK: (debug (unsurprisingly))
- * Change bits of network port state for test purposes in ways that would never be
- * useful in normal operation and so need a special command to change. */
-#define MC_CMD_TEST_HACK 0x2f
-#define MC_CMD_TEST_HACK_IN_LEN 8
-#define MC_CMD_TEST_HACK_IN_TXPAD_OFST 0
-#define MC_CMD_TEST_HACK_IN_TXPAD_AUTO 0 /* Let the MC manage things */
-#define MC_CMD_TEST_HACK_IN_TXPAD_ON 1 /* Force on */
-#define MC_CMD_TEST_HACK_IN_TXPAD_OFF 2 /* Force on */
-#define MC_CMD_TEST_HACK_IN_IPG_OFST 4 /* Takes a value in bits */
-#define MC_CMD_TEST_HACK_IN_IPG_AUTO 0 /* The MC picks the value */
-#define MC_CMD_TEST_HACK_OUT_LEN 0
-
-/* MC_CMD_SENSOR_SET_LIMS: (debug) (mostly) adjust the sensor limits. This
- * is a warranty-voiding operation.
- *
- * IN: sensor identifier (one of the enumeration starting with MC_CMD_SENSOR_CONTROLLER_TEMP
- * followed by 4 32-bit values: min(warning) max(warning), min(fatal), max(fatal). Which
- * of these limits are meaningful and what their interpretation is is sensor-specific.
+
+/* MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG msgrequest */
+#define MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_LEN 16
+/* 0-6 low->high de-emph. */
+#define MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_LEVEL_OFST 0
+/* 0-8 low->high ref.V */
+#define MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_DT_CFG_OFST 4
+/* 0-8 0-8 low->high boost */
+#define MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_BOOST_OFST 8
+/* 0-8 low->high ref.V */
+#define MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_DT_CFG_OFST 12
+
+/* MC_CMD_MRSFP_TWEAK_IN_READ_ONLY msgrequest */
+#define MC_CMD_MRSFP_TWEAK_IN_READ_ONLY_LEN 0
+
+/* MC_CMD_MRSFP_TWEAK_OUT msgresponse */
+#define MC_CMD_MRSFP_TWEAK_OUT_LEN 12
+/* input bits */
+#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_OFST 0
+/* output bits */
+#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_OFST 4
+/* direction */
+#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OFST 8
+/* enum: Out. */
+#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OUT 0x0
+/* enum: In. */
+#define MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_IN 0x1
+
+
+/***********************************/
+/* MC_CMD_SENSOR_SET_LIMS
+ * Adjusts the sensor limits. This is a warranty-voiding operation. Returns:
+ * ENOENT if the sensor specified does not exist, EINVAL if the limits are out
+ * of range.
+ */
+#define MC_CMD_SENSOR_SET_LIMS 0x4e
+
+/* MC_CMD_SENSOR_SET_LIMS_IN msgrequest */
+#define MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
+#define MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
+/* interpretation is is sensor-specific. */
+#define MC_CMD_SENSOR_SET_LIMS_IN_LOW0_OFST 4
+/* interpretation is is sensor-specific. */
+#define MC_CMD_SENSOR_SET_LIMS_IN_HI0_OFST 8
+/* interpretation is is sensor-specific. */
+#define MC_CMD_SENSOR_SET_LIMS_IN_LOW1_OFST 12
+/* interpretation is is sensor-specific. */
+#define MC_CMD_SENSOR_SET_LIMS_IN_HI1_OFST 16
+
+/* MC_CMD_SENSOR_SET_LIMS_OUT msgresponse */
+#define MC_CMD_SENSOR_SET_LIMS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_RESOURCE_LIMITS
+ */
+#define MC_CMD_GET_RESOURCE_LIMITS 0x4f
+
+/* MC_CMD_GET_RESOURCE_LIMITS_IN msgrequest */
+#define MC_CMD_GET_RESOURCE_LIMITS_IN_LEN 0
+
+/* MC_CMD_GET_RESOURCE_LIMITS_OUT msgresponse */
+#define MC_CMD_GET_RESOURCE_LIMITS_OUT_LEN 16
+#define MC_CMD_GET_RESOURCE_LIMITS_OUT_BUFTBL_OFST 0
+#define MC_CMD_GET_RESOURCE_LIMITS_OUT_EVQ_OFST 4
+#define MC_CMD_GET_RESOURCE_LIMITS_OUT_RXQ_OFST 8
+#define MC_CMD_GET_RESOURCE_LIMITS_OUT_TXQ_OFST 12
+
+
+/***********************************/
+/* MC_CMD_NVRAM_PARTITIONS
+ * Reads the list of available virtual NVRAM partition types. Locks required:
+ * none. Returns: 0, EINVAL (bad type).
+ */
+#define MC_CMD_NVRAM_PARTITIONS 0x51
+
+/* MC_CMD_NVRAM_PARTITIONS_IN msgrequest */
+#define MC_CMD_NVRAM_PARTITIONS_IN_LEN 0
+
+/* MC_CMD_NVRAM_PARTITIONS_OUT msgresponse */
+#define MC_CMD_NVRAM_PARTITIONS_OUT_LENMIN 4
+#define MC_CMD_NVRAM_PARTITIONS_OUT_LENMAX 252
+#define MC_CMD_NVRAM_PARTITIONS_OUT_LEN(num) (4+4*(num))
+/* total number of partitions */
+#define MC_CMD_NVRAM_PARTITIONS_OUT_NUM_PARTITIONS_OFST 0
+/* type ID code for each of NUM_PARTITIONS partitions */
+#define MC_CMD_NVRAM_PARTITIONS_OUT_TYPE_ID_OFST 4
+#define MC_CMD_NVRAM_PARTITIONS_OUT_TYPE_ID_LEN 4
+#define MC_CMD_NVRAM_PARTITIONS_OUT_TYPE_ID_MINNUM 0
+#define MC_CMD_NVRAM_PARTITIONS_OUT_TYPE_ID_MAXNUM 62
+
+
+/***********************************/
+/* MC_CMD_NVRAM_METADATA
+ * Reads soft metadata for a virtual NVRAM partition type. Locks required:
+ * none. Returns: 0, EINVAL (bad type).
+ */
+#define MC_CMD_NVRAM_METADATA 0x52
+
+/* MC_CMD_NVRAM_METADATA_IN msgrequest */
+#define MC_CMD_NVRAM_METADATA_IN_LEN 4
+/* Partition type ID code */
+#define MC_CMD_NVRAM_METADATA_IN_TYPE_OFST 0
+
+/* MC_CMD_NVRAM_METADATA_OUT msgresponse */
+#define MC_CMD_NVRAM_METADATA_OUT_LENMIN 20
+#define MC_CMD_NVRAM_METADATA_OUT_LENMAX 252
+#define MC_CMD_NVRAM_METADATA_OUT_LEN(num) (20+1*(num))
+/* Partition type ID code */
+#define MC_CMD_NVRAM_METADATA_OUT_TYPE_OFST 0
+#define MC_CMD_NVRAM_METADATA_OUT_FLAGS_OFST 4
+#define MC_CMD_NVRAM_METADATA_OUT_SUBTYPE_VALID_LBN 0
+#define MC_CMD_NVRAM_METADATA_OUT_SUBTYPE_VALID_WIDTH 1
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_VALID_LBN 1
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_VALID_WIDTH 1
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_VALID_LBN 2
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_VALID_WIDTH 1
+/* Subtype ID code for content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_SUBTYPE_OFST 8
+/* 1st component of W.X.Y.Z version number for content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_W_OFST 12
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_W_LEN 2
+/* 2nd component of W.X.Y.Z version number for content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_X_OFST 14
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_X_LEN 2
+/* 3rd component of W.X.Y.Z version number for content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_Y_OFST 16
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_Y_LEN 2
+/* 4th component of W.X.Y.Z version number for content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_Z_OFST 18
+#define MC_CMD_NVRAM_METADATA_OUT_VERSION_Z_LEN 2
+/* Zero-terminated string describing the content of this partition */
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_OFST 20
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_LEN 1
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_MINNUM 0
+#define MC_CMD_NVRAM_METADATA_OUT_DESCRIPTION_MAXNUM 232
+
+
+/***********************************/
+/* MC_CMD_GET_MAC_ADDRESSES
+ * Returns the base MAC, count and stride for the requestiong function
+ */
+#define MC_CMD_GET_MAC_ADDRESSES 0x55
+
+/* MC_CMD_GET_MAC_ADDRESSES_IN msgrequest */
+#define MC_CMD_GET_MAC_ADDRESSES_IN_LEN 0
+
+/* MC_CMD_GET_MAC_ADDRESSES_OUT msgresponse */
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_LEN 16
+/* Base MAC address */
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE_OFST 0
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE_LEN 6
+/* Padding */
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_RESERVED_OFST 6
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_RESERVED_LEN 2
+/* Number of allocated MAC addresses */
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_COUNT_OFST 8
+/* Spacing of allocated MAC addresses */
+#define MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_OFST 12
+
+/* MC_CMD_RESOURCE_SPECIFIER enum */
+/* enum: Any */
+#define MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff
+/* enum: None */
+#define MC_CMD_RESOURCE_INSTANCE_NONE 0xfffffffe
+
+/* EVB_PORT_ID structuredef */
+#define EVB_PORT_ID_LEN 4
+#define EVB_PORT_ID_PORT_ID_OFST 0
+/* enum: An invalid port handle. */
+#define EVB_PORT_ID_NULL 0x0
+/* enum: The port assigned to this function.. */
+#define EVB_PORT_ID_ASSIGNED 0x1000000
+/* enum: External network port 0 */
+#define EVB_PORT_ID_MAC0 0x2000000
+/* enum: External network port 1 */
+#define EVB_PORT_ID_MAC1 0x2000001
+/* enum: External network port 2 */
+#define EVB_PORT_ID_MAC2 0x2000002
+/* enum: External network port 3 */
+#define EVB_PORT_ID_MAC3 0x2000003
+#define EVB_PORT_ID_PORT_ID_LBN 0
+#define EVB_PORT_ID_PORT_ID_WIDTH 32
+
+/* EVB_VLAN_TAG structuredef */
+#define EVB_VLAN_TAG_LEN 2
+/* The VLAN tag value */
+#define EVB_VLAN_TAG_VLAN_ID_LBN 0
+#define EVB_VLAN_TAG_VLAN_ID_WIDTH 12
+#define EVB_VLAN_TAG_MODE_LBN 12
+#define EVB_VLAN_TAG_MODE_WIDTH 4
+/* enum: Insert the VLAN. */
+#define EVB_VLAN_TAG_INSERT 0x0
+/* enum: Replace the VLAN if already present. */
+#define EVB_VLAN_TAG_REPLACE 0x1
+
+/* BUFTBL_ENTRY structuredef */
+#define BUFTBL_ENTRY_LEN 12
+/* the owner ID */
+#define BUFTBL_ENTRY_OID_OFST 0
+#define BUFTBL_ENTRY_OID_LEN 2
+#define BUFTBL_ENTRY_OID_LBN 0
+#define BUFTBL_ENTRY_OID_WIDTH 16
+/* the page parameter as one of ESE_DZ_SMC_PAGE_SIZE_ */
+#define BUFTBL_ENTRY_PGSZ_OFST 2
+#define BUFTBL_ENTRY_PGSZ_LEN 2
+#define BUFTBL_ENTRY_PGSZ_LBN 16
+#define BUFTBL_ENTRY_PGSZ_WIDTH 16
+/* the raw 64-bit address field from the SMC, not adjusted for page size */
+#define BUFTBL_ENTRY_RAWADDR_OFST 4
+#define BUFTBL_ENTRY_RAWADDR_LEN 8
+#define BUFTBL_ENTRY_RAWADDR_LO_OFST 4
+#define BUFTBL_ENTRY_RAWADDR_HI_OFST 8
+#define BUFTBL_ENTRY_RAWADDR_LBN 32
+#define BUFTBL_ENTRY_RAWADDR_WIDTH 64
+
+/* NVRAM_PARTITION_TYPE structuredef */
+#define NVRAM_PARTITION_TYPE_LEN 2
+#define NVRAM_PARTITION_TYPE_ID_OFST 0
+#define NVRAM_PARTITION_TYPE_ID_LEN 2
+/* enum: Primary MC firmware partition */
+#define NVRAM_PARTITION_TYPE_MC_FIRMWARE 0x100
+/* enum: Secondary MC firmware partition */
+#define NVRAM_PARTITION_TYPE_MC_FIRMWARE_BACKUP 0x200
+/* enum: Expansion ROM partition */
+#define NVRAM_PARTITION_TYPE_EXPANSION_ROM 0x300
+/* enum: Static configuration TLV partition */
+#define NVRAM_PARTITION_TYPE_STATIC_CONFIG 0x400
+/* enum: Dynamic configuration TLV partition */
+#define NVRAM_PARTITION_TYPE_DYNAMIC_CONFIG 0x500
+/* enum: Expansion ROM configuration data for port 0 */
+#define NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT0 0x600
+/* enum: Expansion ROM configuration data for port 1 */
+#define NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1 0x601
+/* enum: Expansion ROM configuration data for port 2 */
+#define NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT2 0x602
+/* enum: Expansion ROM configuration data for port 3 */
+#define NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3 0x603
+/* enum: Non-volatile log output partition */
+#define NVRAM_PARTITION_TYPE_LOG 0x700
+/* enum: Device state dump output partition */
+#define NVRAM_PARTITION_TYPE_DUMP 0x800
+/* enum: Application license key storage partition */
+#define NVRAM_PARTITION_TYPE_LICENSE 0x900
+/* enum: Start of range used for PHY partitions (low 8 bits are the PHY ID) */
+#define NVRAM_PARTITION_TYPE_PHY_MIN 0xa00
+/* enum: End of range used for PHY partitions (low 8 bits are the PHY ID) */
+#define NVRAM_PARTITION_TYPE_PHY_MAX 0xaff
+/* enum: Start of reserved value range (firmware may use for any purpose) */
+#define NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00
+/* enum: End of reserved value range (firmware may use for any purpose) */
+#define NVRAM_PARTITION_TYPE_RESERVED_VALUES_MAX 0xfffd
+/* enum: Recovery partition map (provided if real map is missing or corrupt) */
+#define NVRAM_PARTITION_TYPE_RECOVERY_MAP 0xfffe
+/* enum: Partition map (real map as stored in flash) */
+#define NVRAM_PARTITION_TYPE_PARTITION_MAP 0xffff
+#define NVRAM_PARTITION_TYPE_ID_LBN 0
+#define NVRAM_PARTITION_TYPE_ID_WIDTH 16
+
+/* LICENSED_APP_ID structuredef */
+#define LICENSED_APP_ID_LEN 4
+#define LICENSED_APP_ID_ID_OFST 0
+/* enum: OpenOnload */
+#define LICENSED_APP_ID_ONLOAD 0x1
+/* enum: PTP timestamping */
+#define LICENSED_APP_ID_PTP 0x2
+/* enum: SolarCapture Pro */
+#define LICENSED_APP_ID_SOLARCAPTURE_PRO 0x4
+#define LICENSED_APP_ID_ID_LBN 0
+#define LICENSED_APP_ID_ID_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_READ_REGS
+ * Get a dump of the MCPU registers
+ */
+#define MC_CMD_READ_REGS 0x50
+
+/* MC_CMD_READ_REGS_IN msgrequest */
+#define MC_CMD_READ_REGS_IN_LEN 0
+
+/* MC_CMD_READ_REGS_OUT msgresponse */
+#define MC_CMD_READ_REGS_OUT_LEN 308
+/* Whether the corresponding register entry contains a valid value */
+#define MC_CMD_READ_REGS_OUT_MASK_OFST 0
+#define MC_CMD_READ_REGS_OUT_MASK_LEN 16
+/* Same order as MIPS GDB (r0-r31, sr, lo, hi, bad, cause, 32 x float, fsr,
+ * fir, fp)
+ */
+#define MC_CMD_READ_REGS_OUT_REGS_OFST 16
+#define MC_CMD_READ_REGS_OUT_REGS_LEN 4
+#define MC_CMD_READ_REGS_OUT_REGS_NUM 73
+
+
+/***********************************/
+/* MC_CMD_INIT_EVQ
+ * Set up an event queue according to the supplied parameters. The IN arguments
+ * end with an address for each 4k of host memory required to back the EVQ.
+ */
+#define MC_CMD_INIT_EVQ 0x80
+
+/* MC_CMD_INIT_EVQ_IN msgrequest */
+#define MC_CMD_INIT_EVQ_IN_LENMIN 44
+#define MC_CMD_INIT_EVQ_IN_LENMAX 548
+#define MC_CMD_INIT_EVQ_IN_LEN(num) (36+8*(num))
+/* Size, in entries */
+#define MC_CMD_INIT_EVQ_IN_SIZE_OFST 0
+/* Desired instance. Must be set to a specific instance, which is a function
+ * local queue index.
+ */
+#define MC_CMD_INIT_EVQ_IN_INSTANCE_OFST 4
+/* The initial timer value. The load value is ignored if the timer mode is DIS.
+ */
+#define MC_CMD_INIT_EVQ_IN_TMR_LOAD_OFST 8
+/* The reload value is ignored in one-shot modes */
+#define MC_CMD_INIT_EVQ_IN_TMR_RELOAD_OFST 12
+/* tbd */
+#define MC_CMD_INIT_EVQ_IN_FLAGS_OFST 16
+#define MC_CMD_INIT_EVQ_IN_FLAG_INTERRUPTING_LBN 0
+#define MC_CMD_INIT_EVQ_IN_FLAG_INTERRUPTING_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_RPTR_DOS_LBN 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_RPTR_DOS_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_INT_ARMD_LBN 2
+#define MC_CMD_INIT_EVQ_IN_FLAG_INT_ARMD_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_CUT_THRU_LBN 3
+#define MC_CMD_INIT_EVQ_IN_FLAG_CUT_THRU_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_RX_MERGE_LBN 4
+#define MC_CMD_INIT_EVQ_IN_FLAG_RX_MERGE_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_LBN 5
+#define MC_CMD_INIT_EVQ_IN_FLAG_TX_MERGE_WIDTH 1
+#define MC_CMD_INIT_EVQ_IN_TMR_MODE_OFST 20
+/* enum: Disabled */
+#define MC_CMD_INIT_EVQ_IN_TMR_MODE_DIS 0x0
+/* enum: Immediate */
+#define MC_CMD_INIT_EVQ_IN_TMR_IMMED_START 0x1
+/* enum: Triggered */
+#define MC_CMD_INIT_EVQ_IN_TMR_TRIG_START 0x2
+/* enum: Hold-off */
+#define MC_CMD_INIT_EVQ_IN_TMR_INT_HLDOFF 0x3
+/* Target EVQ for wakeups if in wakeup mode. */
+#define MC_CMD_INIT_EVQ_IN_TARGET_EVQ_OFST 24
+/* Target interrupt if in interrupting mode (note union with target EVQ). Use
+ * MC_CMD_RESOURCE_INSTANCE_ANY unless a specific one required for test
+ * purposes.
+ */
+#define MC_CMD_INIT_EVQ_IN_IRQ_NUM_OFST 24
+/* Event Counter Mode. */
+#define MC_CMD_INIT_EVQ_IN_COUNT_MODE_OFST 28
+/* enum: Disabled */
+#define MC_CMD_INIT_EVQ_IN_COUNT_MODE_DIS 0x0
+/* enum: Disabled */
+#define MC_CMD_INIT_EVQ_IN_COUNT_MODE_RX 0x1
+/* enum: Disabled */
+#define MC_CMD_INIT_EVQ_IN_COUNT_MODE_TX 0x2
+/* enum: Disabled */
+#define MC_CMD_INIT_EVQ_IN_COUNT_MODE_RXTX 0x3
+/* Event queue packet count threshold. */
+#define MC_CMD_INIT_EVQ_IN_COUNT_THRSHLD_OFST 32
+/* 64-bit address of 4k of 4k-aligned host memory buffer */
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_OFST 36
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_LEN 8
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_LO_OFST 36
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_HI_OFST 40
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_MINNUM 1
+#define MC_CMD_INIT_EVQ_IN_DMA_ADDR_MAXNUM 64
+
+/* MC_CMD_INIT_EVQ_OUT msgresponse */
+#define MC_CMD_INIT_EVQ_OUT_LEN 4
+/* Only valid if INTRFLAG was true */
+#define MC_CMD_INIT_EVQ_OUT_IRQ_OFST 0
+
+/* QUEUE_CRC_MODE structuredef */
+#define QUEUE_CRC_MODE_LEN 1
+#define QUEUE_CRC_MODE_MODE_LBN 0
+#define QUEUE_CRC_MODE_MODE_WIDTH 4
+/* enum: No CRC. */
+#define QUEUE_CRC_MODE_NONE 0x0
+/* enum: CRC Fiber channel over ethernet. */
+#define QUEUE_CRC_MODE_FCOE 0x1
+/* enum: CRC (digest) iSCSI header only. */
+#define QUEUE_CRC_MODE_ISCSI_HDR 0x2
+/* enum: CRC (digest) iSCSI header and payload. */
+#define QUEUE_CRC_MODE_ISCSI 0x3
+/* enum: CRC Fiber channel over IP over ethernet. */
+#define QUEUE_CRC_MODE_FCOIPOE 0x4
+/* enum: CRC MPA. */
+#define QUEUE_CRC_MODE_MPA 0x5
+#define QUEUE_CRC_MODE_SPARE_LBN 4
+#define QUEUE_CRC_MODE_SPARE_WIDTH 4
+
+
+/***********************************/
+/* MC_CMD_INIT_RXQ
+ * set up a receive queue according to the supplied parameters. The IN
+ * arguments end with an address for each 4k of host memory required to back
+ * the RXQ.
+ */
+#define MC_CMD_INIT_RXQ 0x81
+
+/* MC_CMD_INIT_RXQ_IN msgrequest */
+#define MC_CMD_INIT_RXQ_IN_LENMIN 36
+#define MC_CMD_INIT_RXQ_IN_LENMAX 252
+#define MC_CMD_INIT_RXQ_IN_LEN(num) (28+8*(num))
+/* Size, in entries */
+#define MC_CMD_INIT_RXQ_IN_SIZE_OFST 0
+/* The EVQ to send events to. This is an index originally specified to INIT_EVQ
+ */
+#define MC_CMD_INIT_RXQ_IN_TARGET_EVQ_OFST 4
+/* The value to put in the event data. Check hardware spec. for valid range. */
+#define MC_CMD_INIT_RXQ_IN_LABEL_OFST 8
+/* Desired instance. Must be set to a specific instance, which is a function
+ * local queue index.
+ */
+#define MC_CMD_INIT_RXQ_IN_INSTANCE_OFST 12
+/* There will be more flags here. */
+#define MC_CMD_INIT_RXQ_IN_FLAGS_OFST 16
+#define MC_CMD_INIT_RXQ_IN_FLAG_BUFF_MODE_LBN 0
+#define MC_CMD_INIT_RXQ_IN_FLAG_BUFF_MODE_WIDTH 1
+#define MC_CMD_INIT_RXQ_IN_FLAG_HDR_SPLIT_LBN 1
+#define MC_CMD_INIT_RXQ_IN_FLAG_HDR_SPLIT_WIDTH 1
+#define MC_CMD_INIT_RXQ_IN_FLAG_TIMESTAMP_LBN 2
+#define MC_CMD_INIT_RXQ_IN_FLAG_TIMESTAMP_WIDTH 1
+#define MC_CMD_INIT_RXQ_IN_CRC_MODE_LBN 3
+#define MC_CMD_INIT_RXQ_IN_CRC_MODE_WIDTH 4
+#define MC_CMD_INIT_RXQ_IN_FLAG_CHAIN_LBN 7
+#define MC_CMD_INIT_RXQ_IN_FLAG_CHAIN_WIDTH 1
+#define MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_LBN 8
+#define MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_WIDTH 1
+#define MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_LBN 9
+#define MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_WIDTH 1
+/* Owner ID to use if in buffer mode (zero if physical) */
+#define MC_CMD_INIT_RXQ_IN_OWNER_ID_OFST 20
+/* The port ID associated with the v-adaptor which should contain this DMAQ. */
+#define MC_CMD_INIT_RXQ_IN_PORT_ID_OFST 24
+/* 64-bit address of 4k of 4k-aligned host memory buffer */
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_OFST 28
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_LEN 8
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_LO_OFST 28
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_HI_OFST 32
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_MINNUM 1
+#define MC_CMD_INIT_RXQ_IN_DMA_ADDR_MAXNUM 28
+
+/* MC_CMD_INIT_RXQ_OUT msgresponse */
+#define MC_CMD_INIT_RXQ_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_INIT_TXQ
+ */
+#define MC_CMD_INIT_TXQ 0x82
+
+/* MC_CMD_INIT_TXQ_IN msgrequest */
+#define MC_CMD_INIT_TXQ_IN_LENMIN 36
+#define MC_CMD_INIT_TXQ_IN_LENMAX 252
+#define MC_CMD_INIT_TXQ_IN_LEN(num) (28+8*(num))
+/* Size, in entries */
+#define MC_CMD_INIT_TXQ_IN_SIZE_OFST 0
+/* The EVQ to send events to. This is an index originally specified to
+ * INIT_EVQ.
+ */
+#define MC_CMD_INIT_TXQ_IN_TARGET_EVQ_OFST 4
+/* The value to put in the event data. Check hardware spec. for valid range. */
+#define MC_CMD_INIT_TXQ_IN_LABEL_OFST 8
+/* Desired instance. Must be set to a specific instance, which is a function
+ * local queue index.
+ */
+#define MC_CMD_INIT_TXQ_IN_INSTANCE_OFST 12
+/* There will be more flags here. */
+#define MC_CMD_INIT_TXQ_IN_FLAGS_OFST 16
+#define MC_CMD_INIT_TXQ_IN_FLAG_BUFF_MODE_LBN 0
+#define MC_CMD_INIT_TXQ_IN_FLAG_BUFF_MODE_WIDTH 1
+#define MC_CMD_INIT_TXQ_IN_FLAG_IP_CSUM_DIS_LBN 1
+#define MC_CMD_INIT_TXQ_IN_FLAG_IP_CSUM_DIS_WIDTH 1
+#define MC_CMD_INIT_TXQ_IN_FLAG_TCP_CSUM_DIS_LBN 2
+#define MC_CMD_INIT_TXQ_IN_FLAG_TCP_CSUM_DIS_WIDTH 1
+#define MC_CMD_INIT_TXQ_IN_FLAG_TCP_UDP_ONLY_LBN 3
+#define MC_CMD_INIT_TXQ_IN_FLAG_TCP_UDP_ONLY_WIDTH 1
+#define MC_CMD_INIT_TXQ_IN_CRC_MODE_LBN 4
+#define MC_CMD_INIT_TXQ_IN_CRC_MODE_WIDTH 4
+#define MC_CMD_INIT_TXQ_IN_FLAG_TIMESTAMP_LBN 8
+#define MC_CMD_INIT_TXQ_IN_FLAG_TIMESTAMP_WIDTH 1
+#define MC_CMD_INIT_TXQ_IN_FLAG_PACER_BYPASS_LBN 9
+#define MC_CMD_INIT_TXQ_IN_FLAG_PACER_BYPASS_WIDTH 1
+/* Owner ID to use if in buffer mode (zero if physical) */
+#define MC_CMD_INIT_TXQ_IN_OWNER_ID_OFST 20
+/* The port ID associated with the v-adaptor which should contain this DMAQ. */
+#define MC_CMD_INIT_TXQ_IN_PORT_ID_OFST 24
+/* 64-bit address of 4k of 4k-aligned host memory buffer */
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_OFST 28
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_LEN 8
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_LO_OFST 28
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_HI_OFST 32
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_MINNUM 1
+#define MC_CMD_INIT_TXQ_IN_DMA_ADDR_MAXNUM 28
+
+/* MC_CMD_INIT_TXQ_OUT msgresponse */
+#define MC_CMD_INIT_TXQ_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_FINI_EVQ
+ * Teardown an EVQ.
+ *
+ * All DMAQs or EVQs that point to the EVQ to tear down must be torn down first
+ * or the operation will fail with EBUSY
+ */
+#define MC_CMD_FINI_EVQ 0x83
+
+/* MC_CMD_FINI_EVQ_IN msgrequest */
+#define MC_CMD_FINI_EVQ_IN_LEN 4
+/* Instance of EVQ to destroy. Should be the same instance as that previously
+ * passed to INIT_EVQ
+ */
+#define MC_CMD_FINI_EVQ_IN_INSTANCE_OFST 0
+
+/* MC_CMD_FINI_EVQ_OUT msgresponse */
+#define MC_CMD_FINI_EVQ_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_FINI_RXQ
+ * Teardown a RXQ.
+ */
+#define MC_CMD_FINI_RXQ 0x84
+
+/* MC_CMD_FINI_RXQ_IN msgrequest */
+#define MC_CMD_FINI_RXQ_IN_LEN 4
+/* Instance of RXQ to destroy */
+#define MC_CMD_FINI_RXQ_IN_INSTANCE_OFST 0
+
+/* MC_CMD_FINI_RXQ_OUT msgresponse */
+#define MC_CMD_FINI_RXQ_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_FINI_TXQ
+ * Teardown a TXQ.
+ */
+#define MC_CMD_FINI_TXQ 0x85
+
+/* MC_CMD_FINI_TXQ_IN msgrequest */
+#define MC_CMD_FINI_TXQ_IN_LEN 4
+/* Instance of TXQ to destroy */
+#define MC_CMD_FINI_TXQ_IN_INSTANCE_OFST 0
+
+/* MC_CMD_FINI_TXQ_OUT msgresponse */
+#define MC_CMD_FINI_TXQ_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_DRIVER_EVENT
+ * Generate an event on an EVQ belonging to the function issuing the command.
+ */
+#define MC_CMD_DRIVER_EVENT 0x86
+
+/* MC_CMD_DRIVER_EVENT_IN msgrequest */
+#define MC_CMD_DRIVER_EVENT_IN_LEN 12
+/* Handle of target EVQ */
+#define MC_CMD_DRIVER_EVENT_IN_EVQ_OFST 0
+/* Bits 0 - 63 of event */
+#define MC_CMD_DRIVER_EVENT_IN_DATA_OFST 4
+#define MC_CMD_DRIVER_EVENT_IN_DATA_LEN 8
+#define MC_CMD_DRIVER_EVENT_IN_DATA_LO_OFST 4
+#define MC_CMD_DRIVER_EVENT_IN_DATA_HI_OFST 8
+
+/* MC_CMD_DRIVER_EVENT_OUT msgresponse */
+#define MC_CMD_DRIVER_EVENT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_PROXY_CMD
+ * Execute an arbitrary MCDI command on behalf of a different function, subject
+ * to security restrictions. The command to be proxied follows immediately
+ * afterward in the host buffer (or on the UART). This command supercedes
+ * MC_CMD_SET_FUNC, which remains available for Siena but now deprecated.
+ */
+#define MC_CMD_PROXY_CMD 0x5b
+
+/* MC_CMD_PROXY_CMD_IN msgrequest */
+#define MC_CMD_PROXY_CMD_IN_LEN 4
+/* The handle of the target function. */
+#define MC_CMD_PROXY_CMD_IN_TARGET_OFST 0
+#define MC_CMD_PROXY_CMD_IN_TARGET_PF_LBN 0
+#define MC_CMD_PROXY_CMD_IN_TARGET_PF_WIDTH 16
+#define MC_CMD_PROXY_CMD_IN_TARGET_VF_LBN 16
+#define MC_CMD_PROXY_CMD_IN_TARGET_VF_WIDTH 16
+#define MC_CMD_PROXY_CMD_IN_VF_NULL 0xffff /* enum */
+
+/* MC_CMD_PROXY_CMD_OUT msgresponse */
+#define MC_CMD_PROXY_CMD_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_ALLOC_BUFTBL_CHUNK
+ * Allocate a set of buffer table entries using the specified owner ID. This
+ * operation allocates the required buffer table entries (and fails if it
+ * cannot do so). The buffer table entries will initially be zeroed.
+ */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK 0x87
+
+/* MC_CMD_ALLOC_BUFTBL_CHUNK_IN msgrequest */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_IN_LEN 8
+/* Owner ID to use */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_IN_OWNER_OFST 0
+/* Size of buffer table pages to use, in bytes (note that only a few values are
+ * legal on any specific hardware).
+ */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_IN_PAGE_SIZE_OFST 4
+
+/* MC_CMD_ALLOC_BUFTBL_CHUNK_OUT msgresponse */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_LEN 12
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_HANDLE_OFST 0
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_NUMENTRIES_OFST 4
+/* Buffer table IDs for use in DMA descriptors. */
+#define MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_ID_OFST 8
+
+
+/***********************************/
+/* MC_CMD_PROGRAM_BUFTBL_ENTRIES
+ * Reprogram a set of buffer table entries in the specified chunk.
+ */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES 0x88
+
+/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN msgrequest */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMIN 20
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 268
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LEN(num) (12+8*(num))
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_OFST 0
+/* ID */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_FIRSTID_OFST 4
+/* Num entries */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 8
+/* Buffer table entry address */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_OFST 12
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LEN 8
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_OFST 12
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_OFST 16
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MINNUM 1
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM 32
+
+/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT msgresponse */
+#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_FREE_BUFTBL_CHUNK
+ */
+#define MC_CMD_FREE_BUFTBL_CHUNK 0x89
+
+/* MC_CMD_FREE_BUFTBL_CHUNK_IN msgrequest */
+#define MC_CMD_FREE_BUFTBL_CHUNK_IN_LEN 4
+#define MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_OFST 0
+
+/* MC_CMD_FREE_BUFTBL_CHUNK_OUT msgresponse */
+#define MC_CMD_FREE_BUFTBL_CHUNK_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_FILTER_OP
+ * Multiplexed MCDI call for filter operations
+ */
+#define MC_CMD_FILTER_OP 0x8a
+
+/* MC_CMD_FILTER_OP_IN msgrequest */
+#define MC_CMD_FILTER_OP_IN_LEN 108
+/* identifies the type of operation requested */
+#define MC_CMD_FILTER_OP_IN_OP_OFST 0
+/* enum: single-recipient filter insert */
+#define MC_CMD_FILTER_OP_IN_OP_INSERT 0x0
+/* enum: single-recipient filter remove */
+#define MC_CMD_FILTER_OP_IN_OP_REMOVE 0x1
+/* enum: multi-recipient filter subscribe */
+#define MC_CMD_FILTER_OP_IN_OP_SUBSCRIBE 0x2
+/* enum: multi-recipient filter unsubscribe */
+#define MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE 0x3
+/* enum: replace one recipient with another (warning - the filter handle may
+ * change)
+ */
+#define MC_CMD_FILTER_OP_IN_OP_REPLACE 0x4
+/* filter handle (for remove / unsubscribe operations) */
+#define MC_CMD_FILTER_OP_IN_HANDLE_OFST 4
+#define MC_CMD_FILTER_OP_IN_HANDLE_LEN 8
+#define MC_CMD_FILTER_OP_IN_HANDLE_LO_OFST 4
+#define MC_CMD_FILTER_OP_IN_HANDLE_HI_OFST 8
+/* The port ID associated with the v-adaptor which should contain this filter.
+ */
+#define MC_CMD_FILTER_OP_IN_PORT_ID_OFST 12
+/* fields to include in match criteria */
+#define MC_CMD_FILTER_OP_IN_MATCH_FIELDS_OFST 16
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_IP_LBN 0
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_IP_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_IP_LBN 1
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_IP_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_MAC_LBN 2
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_MAC_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_PORT_LBN 3
+#define MC_CMD_FILTER_OP_IN_MATCH_SRC_PORT_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_MAC_LBN 4
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_MAC_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_PORT_LBN 5
+#define MC_CMD_FILTER_OP_IN_MATCH_DST_PORT_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_ETHER_TYPE_LBN 6
+#define MC_CMD_FILTER_OP_IN_MATCH_ETHER_TYPE_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_INNER_VLAN_LBN 7
+#define MC_CMD_FILTER_OP_IN_MATCH_INNER_VLAN_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_OUTER_VLAN_LBN 8
+#define MC_CMD_FILTER_OP_IN_MATCH_OUTER_VLAN_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_IP_PROTO_LBN 9
+#define MC_CMD_FILTER_OP_IN_MATCH_IP_PROTO_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_FWDEF0_LBN 10
+#define MC_CMD_FILTER_OP_IN_MATCH_FWDEF0_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_FWDEF1_LBN 11
+#define MC_CMD_FILTER_OP_IN_MATCH_FWDEF1_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_MCAST_DST_LBN 30
+#define MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_MCAST_DST_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_UCAST_DST_LBN 31
+#define MC_CMD_FILTER_OP_IN_MATCH_UNKNOWN_UCAST_DST_WIDTH 1
+/* receive destination */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_OFST 20
+/* enum: drop packets */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_DROP 0x0
+/* enum: receive to host */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_HOST 0x1
+/* enum: receive to MC */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_MC 0x2
+/* enum: loop back to port 0 TX MAC */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_TX0 0x3
+/* enum: loop back to port 1 TX MAC */
+#define MC_CMD_FILTER_OP_IN_RX_DEST_TX1 0x4
+/* receive queue handle (for multiple queue modes, this is the base queue) */
+#define MC_CMD_FILTER_OP_IN_RX_QUEUE_OFST 24
+/* receive mode */
+#define MC_CMD_FILTER_OP_IN_RX_MODE_OFST 28
+/* enum: receive to just the specified queue */
+#define MC_CMD_FILTER_OP_IN_RX_MODE_SIMPLE 0x0
+/* enum: receive to multiple queues using RSS context */
+#define MC_CMD_FILTER_OP_IN_RX_MODE_RSS 0x1
+/* enum: receive to multiple queues using .1p mapping */
+#define MC_CMD_FILTER_OP_IN_RX_MODE_DOT1P_MAPPING 0x2
+/* enum: install a filter entry that will never match; for test purposes only
+ */
+#define MC_CMD_FILTER_OP_IN_RX_MODE_TEST_NEVER_MATCH 0x80000000
+/* RSS context (for RX_MODE_RSS) or .1p mapping handle (for
+ * RX_MODE_DOT1P_MAPPING), as returned by MC_CMD_RSS_CONTEXT_ALLOC or
+ * MC_CMD_DOT1P_MAPPING_ALLOC. Note that these handles should be considered
+ * opaque to the host, although a value of 0xFFFFFFFF is guaranteed never to be
+ * a valid handle.
+ */
+#define MC_CMD_FILTER_OP_IN_RX_CONTEXT_OFST 32
+/* transmit domain (reserved; set to 0) */
+#define MC_CMD_FILTER_OP_IN_TX_DOMAIN_OFST 36
+/* transmit destination (either set the MAC and/or PM bits for explicit
+ * control, or set this field to TX_DEST_DEFAULT for sensible default
+ * behaviour)
+ */
+#define MC_CMD_FILTER_OP_IN_TX_DEST_OFST 40
+/* enum: request default behaviour (based on filter type) */
+#define MC_CMD_FILTER_OP_IN_TX_DEST_DEFAULT 0xffffffff
+#define MC_CMD_FILTER_OP_IN_TX_DEST_MAC_LBN 0
+#define MC_CMD_FILTER_OP_IN_TX_DEST_MAC_WIDTH 1
+#define MC_CMD_FILTER_OP_IN_TX_DEST_PM_LBN 1
+#define MC_CMD_FILTER_OP_IN_TX_DEST_PM_WIDTH 1
+/* source MAC address to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_SRC_MAC_OFST 44
+#define MC_CMD_FILTER_OP_IN_SRC_MAC_LEN 6
+/* source port to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_SRC_PORT_OFST 50
+#define MC_CMD_FILTER_OP_IN_SRC_PORT_LEN 2
+/* destination MAC address to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_DST_MAC_OFST 52
+#define MC_CMD_FILTER_OP_IN_DST_MAC_LEN 6
+/* destination port to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_DST_PORT_OFST 58
+#define MC_CMD_FILTER_OP_IN_DST_PORT_LEN 2
+/* Ethernet type to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_ETHER_TYPE_OFST 60
+#define MC_CMD_FILTER_OP_IN_ETHER_TYPE_LEN 2
+/* Inner VLAN tag to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_INNER_VLAN_OFST 62
+#define MC_CMD_FILTER_OP_IN_INNER_VLAN_LEN 2
+/* Outer VLAN tag to match (as bytes in network order) */
+#define MC_CMD_FILTER_OP_IN_OUTER_VLAN_OFST 64
+#define MC_CMD_FILTER_OP_IN_OUTER_VLAN_LEN 2
+/* IP protocol to match (in low byte; set high byte to 0) */
+#define MC_CMD_FILTER_OP_IN_IP_PROTO_OFST 66
+#define MC_CMD_FILTER_OP_IN_IP_PROTO_LEN 2
+/* Firmware defined register 0 to match (reserved; set to 0) */
+#define MC_CMD_FILTER_OP_IN_FWDEF0_OFST 68
+/* Firmware defined register 1 to match (reserved; set to 0) */
+#define MC_CMD_FILTER_OP_IN_FWDEF1_OFST 72
+/* source IP address to match (as bytes in network order; set last 12 bytes to
+ * 0 for IPv4 address)
+ */
+#define MC_CMD_FILTER_OP_IN_SRC_IP_OFST 76
+#define MC_CMD_FILTER_OP_IN_SRC_IP_LEN 16
+/* destination IP address to match (as bytes in network order; set last 12
+ * bytes to 0 for IPv4 address)
+ */
+#define MC_CMD_FILTER_OP_IN_DST_IP_OFST 92
+#define MC_CMD_FILTER_OP_IN_DST_IP_LEN 16
+
+/* MC_CMD_FILTER_OP_OUT msgresponse */
+#define MC_CMD_FILTER_OP_OUT_LEN 12
+/* identifies the type of operation requested */
+#define MC_CMD_FILTER_OP_OUT_OP_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_FILTER_OP_IN/OP */
+/* Returned filter handle (for insert / subscribe operations). Note that these
+ * handles should be considered opaque to the host, although a value of
+ * 0xFFFFFFFF_FFFFFFFF is guaranteed never to be a valid handle.
+ */
+#define MC_CMD_FILTER_OP_OUT_HANDLE_OFST 4
+#define MC_CMD_FILTER_OP_OUT_HANDLE_LEN 8
+#define MC_CMD_FILTER_OP_OUT_HANDLE_LO_OFST 4
+#define MC_CMD_FILTER_OP_OUT_HANDLE_HI_OFST 8
+
+
+/***********************************/
+/* MC_CMD_GET_PARSER_DISP_INFO
+ * Get information related to the parser-dispatcher subsystem
+ */
+#define MC_CMD_GET_PARSER_DISP_INFO 0xe4
+
+/* MC_CMD_GET_PARSER_DISP_INFO_IN msgrequest */
+#define MC_CMD_GET_PARSER_DISP_INFO_IN_LEN 4
+/* identifies the type of operation requested */
+#define MC_CMD_GET_PARSER_DISP_INFO_IN_OP_OFST 0
+/* enum: read the list of supported RX filter matches */
+#define MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_RX_MATCHES 0x1
+
+/* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMAX 252
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_LEN(num) (8+4*(num))
+/* identifies the type of operation requested */
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_OP_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_GET_PARSER_DISP_INFO_IN/OP */
+/* number of supported match types */
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_NUM_SUPPORTED_MATCHES_OFST 4
+/* array of supported match types (valid MATCH_FIELDS values for
+ * MC_CMD_FILTER_OP) sorted in decreasing priority order
+ */
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_OFST 8
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_LEN 4
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MINNUM 0
+#define MC_CMD_GET_PARSER_DISP_INFO_OUT_SUPPORTED_MATCHES_MAXNUM 61
+
+
+/***********************************/
+/* MC_CMD_PARSER_DISP_RW
+ * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging
+ */
+#define MC_CMD_PARSER_DISP_RW 0xe5
+
+/* MC_CMD_PARSER_DISP_RW_IN msgrequest */
+#define MC_CMD_PARSER_DISP_RW_IN_LEN 32
+/* identifies the target of the operation */
+#define MC_CMD_PARSER_DISP_RW_IN_TARGET_OFST 0
+/* enum: RX dispatcher CPU */
+#define MC_CMD_PARSER_DISP_RW_IN_RX_DICPU 0x0
+/* enum: TX dispatcher CPU */
+#define MC_CMD_PARSER_DISP_RW_IN_TX_DICPU 0x1
+/* enum: Lookup engine */
+#define MC_CMD_PARSER_DISP_RW_IN_LUE 0x2
+/* identifies the type of operation requested */
+#define MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4
+/* enum: read a word of DICPU DMEM or a LUE entry */
+#define MC_CMD_PARSER_DISP_RW_IN_READ 0x0
+/* enum: write a word of DICPU DMEM or a LUE entry */
+#define MC_CMD_PARSER_DISP_RW_IN_WRITE 0x1
+/* enum: read-modify-write a word of DICPU DMEM (not valid for LUE) */
+#define MC_CMD_PARSER_DISP_RW_IN_RMW 0x2
+/* data memory address or LUE index */
+#define MC_CMD_PARSER_DISP_RW_IN_ADDRESS_OFST 8
+/* value to write (for DMEM writes) */
+#define MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_OFST 12
+/* XOR value (for DMEM read-modify-writes: new = (old & mask) ^ value) */
+#define MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_OFST 12
+/* AND mask (for DMEM read-modify-writes: new = (old & mask) ^ value) */
+#define MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_OFST 16
+/* value to write (for LUE writes) */
+#define MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_OFST 12
+#define MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_LEN 20
+
+/* MC_CMD_PARSER_DISP_RW_OUT msgresponse */
+#define MC_CMD_PARSER_DISP_RW_OUT_LEN 52
+/* value read (for DMEM reads) */
+#define MC_CMD_PARSER_DISP_RW_OUT_DMEM_READ_VALUE_OFST 0
+/* value read (for LUE reads) */
+#define MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_OFST 0
+#define MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_LEN 20
+/* up to 8 32-bit words of additional soft state from the LUE manager (the
+ * exact content is firmware-dependent and intended only for debug use)
+ */
+#define MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_OFST 20
+#define MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_LEN 32
+
+
+/***********************************/
+/* MC_CMD_GET_PF_COUNT
+ * Get number of PFs on the device.
+ */
+#define MC_CMD_GET_PF_COUNT 0xb6
+
+/* MC_CMD_GET_PF_COUNT_IN msgrequest */
+#define MC_CMD_GET_PF_COUNT_IN_LEN 0
+
+/* MC_CMD_GET_PF_COUNT_OUT msgresponse */
+#define MC_CMD_GET_PF_COUNT_OUT_LEN 1
+/* Identifies the number of PFs on the device. */
+#define MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_OFST 0
+#define MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_LEN 1
+
+
+/***********************************/
+/* MC_CMD_SET_PF_COUNT
+ * Set number of PFs on the device.
+ */
+#define MC_CMD_SET_PF_COUNT 0xb7
+
+/* MC_CMD_SET_PF_COUNT_IN msgrequest */
+#define MC_CMD_SET_PF_COUNT_IN_LEN 4
+/* New number of PFs on the device. */
+#define MC_CMD_SET_PF_COUNT_IN_PF_COUNT_OFST 0
+
+/* MC_CMD_SET_PF_COUNT_OUT msgresponse */
+#define MC_CMD_SET_PF_COUNT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_PORT_ASSIGNMENT
+ * Get port assignment for current PCI function.
+ */
+#define MC_CMD_GET_PORT_ASSIGNMENT 0xb8
+
+/* MC_CMD_GET_PORT_ASSIGNMENT_IN msgrequest */
+#define MC_CMD_GET_PORT_ASSIGNMENT_IN_LEN 0
+
+/* MC_CMD_GET_PORT_ASSIGNMENT_OUT msgresponse */
+#define MC_CMD_GET_PORT_ASSIGNMENT_OUT_LEN 4
+/* Identifies the port assignment for this function. */
+#define MC_CMD_GET_PORT_ASSIGNMENT_OUT_PORT_OFST 0
+
+
+/***********************************/
+/* MC_CMD_SET_PORT_ASSIGNMENT
+ * Set port assignment for current PCI function.
+ */
+#define MC_CMD_SET_PORT_ASSIGNMENT 0xb9
+
+/* MC_CMD_SET_PORT_ASSIGNMENT_IN msgrequest */
+#define MC_CMD_SET_PORT_ASSIGNMENT_IN_LEN 4
+/* Identifies the port assignment for this function. */
+#define MC_CMD_SET_PORT_ASSIGNMENT_IN_PORT_OFST 0
+
+/* MC_CMD_SET_PORT_ASSIGNMENT_OUT msgresponse */
+#define MC_CMD_SET_PORT_ASSIGNMENT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_ALLOC_VIS
+ * Allocate VIs for current PCI function.
+ */
+#define MC_CMD_ALLOC_VIS 0x8b
+
+/* MC_CMD_ALLOC_VIS_IN msgrequest */
+#define MC_CMD_ALLOC_VIS_IN_LEN 8
+/* The minimum number of VIs that is acceptable */
+#define MC_CMD_ALLOC_VIS_IN_MIN_VI_COUNT_OFST 0
+/* The maximum number of VIs that would be useful */
+#define MC_CMD_ALLOC_VIS_IN_MAX_VI_COUNT_OFST 4
+
+/* MC_CMD_ALLOC_VIS_OUT msgresponse */
+#define MC_CMD_ALLOC_VIS_OUT_LEN 8
+/* The number of VIs allocated on this function */
+#define MC_CMD_ALLOC_VIS_OUT_VI_COUNT_OFST 0
+/* The base absolute VI number allocated to this function. Required to
+ * correctly interpret wakeup events.
+ */
+#define MC_CMD_ALLOC_VIS_OUT_VI_BASE_OFST 4
+
+
+/***********************************/
+/* MC_CMD_FREE_VIS
+ * Free VIs for current PCI function. Any linked PIO buffers will be unlinked,
+ * but not freed.
+ */
+#define MC_CMD_FREE_VIS 0x8c
+
+/* MC_CMD_FREE_VIS_IN msgrequest */
+#define MC_CMD_FREE_VIS_IN_LEN 0
+
+/* MC_CMD_FREE_VIS_OUT msgresponse */
+#define MC_CMD_FREE_VIS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_SRIOV_CFG
+ * Get SRIOV config for this PF.
+ */
+#define MC_CMD_GET_SRIOV_CFG 0xba
+
+/* MC_CMD_GET_SRIOV_CFG_IN msgrequest */
+#define MC_CMD_GET_SRIOV_CFG_IN_LEN 0
+
+/* MC_CMD_GET_SRIOV_CFG_OUT msgresponse */
+#define MC_CMD_GET_SRIOV_CFG_OUT_LEN 20
+/* Number of VFs currently enabled. */
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_CURRENT_OFST 0
+/* Max number of VFs before sriov stride and offset may need to be changed. */
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_MAX_OFST 4
+#define MC_CMD_GET_SRIOV_CFG_OUT_FLAGS_OFST 8
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_ENABLED_LBN 0
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_ENABLED_WIDTH 1
+/* RID offset of first VF from PF. */
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_OFFSET_OFST 12
+/* RID offset of each subsequent VF from the previous. */
+#define MC_CMD_GET_SRIOV_CFG_OUT_VF_STRIDE_OFST 16
+
+
+/***********************************/
+/* MC_CMD_SET_SRIOV_CFG
+ * Set SRIOV config for this PF.
+ */
+#define MC_CMD_SET_SRIOV_CFG 0xbb
+
+/* MC_CMD_SET_SRIOV_CFG_IN msgrequest */
+#define MC_CMD_SET_SRIOV_CFG_IN_LEN 20
+/* Number of VFs currently enabled. */
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_CURRENT_OFST 0
+/* Max number of VFs before sriov stride and offset may need to be changed. */
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_MAX_OFST 4
+#define MC_CMD_SET_SRIOV_CFG_IN_FLAGS_OFST 8
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_LBN 0
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_WIDTH 1
+/* RID offset of first VF from PF, or 0 for no change, or
+ * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate an offset.
+ */
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_OFFSET_OFST 12
+/* RID offset of each subsequent VF from the previous, 0 for no change, or
+ * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate a stride.
+ */
+#define MC_CMD_SET_SRIOV_CFG_IN_VF_STRIDE_OFST 16
+
+/* MC_CMD_SET_SRIOV_CFG_OUT msgresponse */
+#define MC_CMD_SET_SRIOV_CFG_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_VI_ALLOC_INFO
+ * Get information about number of VI's and base VI number allocated to this
+ * function.
+ */
+#define MC_CMD_GET_VI_ALLOC_INFO 0x8d
+
+/* MC_CMD_GET_VI_ALLOC_INFO_IN msgrequest */
+#define MC_CMD_GET_VI_ALLOC_INFO_IN_LEN 0
+
+/* MC_CMD_GET_VI_ALLOC_INFO_OUT msgresponse */
+#define MC_CMD_GET_VI_ALLOC_INFO_OUT_LEN 8
+/* The number of VIs allocated on this function */
+#define MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_OFST 0
+/* The base absolute VI number allocated to this function. Required to
+ * correctly interpret wakeup events.
+ */
+#define MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_OFST 4
+
+
+/***********************************/
+/* MC_CMD_DUMP_VI_STATE
+ * For CmdClient use. Dump pertinent information on a specific absolute VI.
+ */
+#define MC_CMD_DUMP_VI_STATE 0x8e
+
+/* MC_CMD_DUMP_VI_STATE_IN msgrequest */
+#define MC_CMD_DUMP_VI_STATE_IN_LEN 4
+/* The VI number to query. */
+#define MC_CMD_DUMP_VI_STATE_IN_VI_NUMBER_OFST 0
+
+/* MC_CMD_DUMP_VI_STATE_OUT msgresponse */
+#define MC_CMD_DUMP_VI_STATE_OUT_LEN 96
+/* The PF part of the function owning this VI. */
+#define MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_OFST 0
+#define MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_LEN 2
+/* The VF part of the function owning this VI. */
+#define MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_OFST 2
+#define MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_LEN 2
+/* Base of VIs allocated to this function. */
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_OFST 4
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_LEN 2
+/* Count of VIs allocated to the owner function. */
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_OFST 6
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_LEN 2
+/* Base interrupt vector allocated to this function. */
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_OFST 8
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_LEN 2
+/* Number of interrupt vectors allocated to this function. */
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_OFST 10
+#define MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_LEN 2
+/* Raw evq ptr table data. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_OFST 12
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_OFST 12
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_OFST 16
+/* Raw evq timer table data. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_OFST 20
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_OFST 20
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_OFST 24
+/* Combined metadata field. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_OFST 28
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_LBN 0
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_WIDTH 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_LBN 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_LBN 24
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_WIDTH 8
+/* TXDPCPU raw table data for queue. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_OFST 32
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_OFST 32
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_OFST 36
+/* TXDPCPU raw table data for queue. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_OFST 40
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_OFST 40
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_OFST 44
+/* TXDPCPU raw table data for queue. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_OFST 48
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_OFST 48
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_OFST 52
+/* Combined metadata field. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_OFST 56
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_OFST 56
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_OFST 60
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_LBN 0
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_WIDTH 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_LBN 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_LBN 24
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_LBN 32
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_LBN 40
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_WIDTH 24
+/* RXDPCPU raw table data for queue. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_OFST 64
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_OFST 64
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_OFST 68
+/* RXDPCPU raw table data for queue. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_OFST 72
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_OFST 72
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_OFST 76
+/* Reserved, currently 0. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_OFST 80
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_OFST 80
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_OFST 84
+/* Combined metadata field. */
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_OFST 88
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LEN 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_OFST 88
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_OFST 92
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_LBN 0
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_WIDTH 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_LBN 16
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_LBN 24
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_WIDTH 8
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_LBN 32
+#define MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_WIDTH 8
+
+
+/***********************************/
+/* MC_CMD_ALLOC_PIOBUF
+ * Allocate a push I/O buffer for later use with a tx queue.
+ */
+#define MC_CMD_ALLOC_PIOBUF 0x8f
+
+/* MC_CMD_ALLOC_PIOBUF_IN msgrequest */
+#define MC_CMD_ALLOC_PIOBUF_IN_LEN 0
+
+/* MC_CMD_ALLOC_PIOBUF_OUT msgresponse */
+#define MC_CMD_ALLOC_PIOBUF_OUT_LEN 4
+/* Handle for allocated push I/O buffer. */
+#define MC_CMD_ALLOC_PIOBUF_OUT_PIOBUF_HANDLE_OFST 0
+
+
+/***********************************/
+/* MC_CMD_FREE_PIOBUF
+ * Free a push I/O buffer.
+ */
+#define MC_CMD_FREE_PIOBUF 0x90
+
+/* MC_CMD_FREE_PIOBUF_IN msgrequest */
+#define MC_CMD_FREE_PIOBUF_IN_LEN 4
+/* Handle for allocated push I/O buffer. */
+#define MC_CMD_FREE_PIOBUF_IN_PIOBUF_HANDLE_OFST 0
+
+/* MC_CMD_FREE_PIOBUF_OUT msgresponse */
+#define MC_CMD_FREE_PIOBUF_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_VI_TLP_PROCESSING
+ * Get TLP steering and ordering information for a VI.
+ */
+#define MC_CMD_GET_VI_TLP_PROCESSING 0xb0
+
+/* MC_CMD_GET_VI_TLP_PROCESSING_IN msgrequest */
+#define MC_CMD_GET_VI_TLP_PROCESSING_IN_LEN 4
+/* VI number to get information for. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
+
+/* MC_CMD_GET_VI_TLP_PROCESSING_OUT msgresponse */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_LEN 4
+/* Transaction processing steering hint 1 for use with the Rx Queue. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_OFST 0
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_LEN 1
+/* Transaction processing steering hint 2 for use with the Ev Queue. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_OFST 1
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_LEN 1
+/* Use Relaxed ordering model for TLPs on this VI. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_LBN 16
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_WIDTH 1
+/* Use ID based ordering for TLPs on this VI. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_LBN 17
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_WIDTH 1
+/* Set no snoop bit for TLPs on this VI. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_LBN 18
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_WIDTH 1
+/* Enable TPH for TLPs on this VI. */
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_LBN 19
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_WIDTH 1
+#define MC_CMD_GET_VI_TLP_PROCESSING_OUT_DATA_OFST 0
+
+
+/***********************************/
+/* MC_CMD_SET_VI_TLP_PROCESSING
+ * Set TLP steering and ordering information for a VI.
+ */
+#define MC_CMD_SET_VI_TLP_PROCESSING 0xb1
+
+/* MC_CMD_SET_VI_TLP_PROCESSING_IN msgrequest */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_LEN 8
+/* VI number to set information for. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
+/* Transaction processing steering hint 1 for use with the Rx Queue. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_OFST 4
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_LEN 1
+/* Transaction processing steering hint 2 for use with the Ev Queue. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_OFST 5
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_LEN 1
+/* Use Relaxed ordering model for TLPs on this VI. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_LBN 48
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_WIDTH 1
+/* Use ID based ordering for TLPs on this VI. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_LBN 49
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_WIDTH 1
+/* Set the no snoop bit for TLPs on this VI. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_LBN 50
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_WIDTH 1
+/* Enable TPH for TLPs on this VI. */
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_LBN 51
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_WIDTH 1
+#define MC_CMD_SET_VI_TLP_PROCESSING_IN_DATA_OFST 4
+
+/* MC_CMD_SET_VI_TLP_PROCESSING_OUT msgresponse */
+#define MC_CMD_SET_VI_TLP_PROCESSING_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_TLP_PROCESSING_GLOBALS
+ * Get global PCIe steering and transaction processing configuration.
+ */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS 0xbc
+
+/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN msgrequest */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_LEN 4
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
+/* enum: MISC. */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_MISC 0x0
+/* enum: IDO. */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_IDO 0x1
+/* enum: RO. */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_RO 0x2
+/* enum: TPH Type. */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_TPH_TYPE 0x3
+
+/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_LEN 8
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_GLOBAL_CATEGORY_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
+/* Amalgamated TLP info word. */
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_WORD_OFST 4
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_LBN 0
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_LBN 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_WIDTH 31
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_LBN 0
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_LBN 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_LBN 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_LBN 3
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_LBN 4
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_WIDTH 28
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_LBN 0
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_LBN 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_LBN 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_WIDTH 1
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_LBN 3
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_WIDTH 29
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_LBN 0
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_LBN 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_WIDTH 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_LBN 4
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_WIDTH 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_LBN 6
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_WIDTH 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_LBN 8
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_WIDTH 2
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_LBN 9
+#define MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_WIDTH 23
+
+
+/***********************************/
+/* MC_CMD_SET_TLP_PROCESSING_GLOBALS
+ * Set global PCIe steering and transaction processing configuration.
+ */
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS 0xbd
+
+/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN msgrequest */
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_LEN 8
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
+/* Enum values, see field(s): */
+/* MC_CMD_GET_TLP_PROCESSING_GLOBALS/MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
+/* Amalgamated TLP info word. */
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_WORD_OFST 4
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_LBN 0
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_LBN 0
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_LBN 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_LBN 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_LBN 3
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_LBN 0
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_LBN 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_LBN 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_WIDTH 1
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_LBN 0
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_LBN 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_WIDTH 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_LBN 4
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_WIDTH 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_LBN 6
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_WIDTH 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_LBN 8
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_WIDTH 2
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_LBN 10
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_WIDTH 22
+
+/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
+#define MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_SATELLITE_DOWNLOAD
+ * Download a new set of images to the satellite CPUs from the host.
+ */
+#define MC_CMD_SATELLITE_DOWNLOAD 0x91
+
+/* MC_CMD_SATELLITE_DOWNLOAD_IN msgrequest: The reset requirements for the CPUs
+ * are subtle, and so downloads must proceed in a number of phases.
+ *
+ * 1) PHASE_RESET with a target of TARGET_ALL and chunk ID/length of 0.
+ *
+ * 2) PHASE_IMEMS for each of the IMEM targets (target IDs 0-11). Each download
+ * may consist of multiple chunks. The final chunk (with CHUNK_ID_LAST) should
+ * be a checksum (a simple 32-bit sum) of the transferred data. An individual
+ * download may be aborted using CHUNK_ID_ABORT.
*
- * OUT: nothing
+ * 3) PHASE_VECTORS for each of the vector table targets (target IDs 12-15),
+ * similar to PHASE_IMEMS.
*
- * Returns: ENOENT if the sensor specified does not exist, EINVAL if the limits are
- * out of range.
+ * 4) PHASE_READY with a target of TARGET_ALL and chunk ID/length of 0.
+ *
+ * After any error (a requested abort is not considered to be an error) the
+ * sequence must be restarted from PHASE_RESET.
*/
-#define MC_CMD_SENSOR_SET_LIMS 0x4e
-#define MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
-#define MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
-#define MC_CMD_SENSOR_SET_LIMS_IN_LOW0_OFST 4
-#define MC_CMD_SENSOR_SET_LIMS_IN_HI0_OFST 8
-#define MC_CMD_SENSOR_SET_LIMS_IN_LOW1_OFST 12
-#define MC_CMD_SENSOR_SET_LIMS_IN_HI1_OFST 16
-
-/* Do NOT add new commands beyond 0x4f as part of 3.0 : 0x50 - 0x7f will be
- * used for post-3.0 extensions. If you run out of space, look for gaps or
- * commands that are unused in the existing range. */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_LENMIN 20
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_LENMAX 252
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_LEN(num) (16+4*(num))
+/* Download phase. (Note: the IDLE phase is used internally and is never valid
+ * in a command from the host.)
+ */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_OFST 0
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IDLE 0x0 /* enum */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_RESET 0x1 /* enum */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IMEMS 0x2 /* enum */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_VECTORS 0x3 /* enum */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_READY 0x4 /* enum */
+/* Target for download. (These match the blob numbers defined in
+ * mc_flash_layout.h.)
+ */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_OFST 4
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_TEXT 0x0
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_TEXT 0x1
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDP_TEXT 0x2
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDP_TEXT 0x3
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT 0x4
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT_CFG 0x5
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT 0x6
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT_CFG 0x7
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_PGM 0x8
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_SL_PGM 0x9
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_PGM 0xa
+/* enum: Valid in phase 2 (PHASE_IMEMS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_SL_PGM 0xb
+/* enum: Valid in phase 3 (PHASE_VECTORS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL0 0xc
+/* enum: Valid in phase 3 (PHASE_VECTORS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL0 0xd
+/* enum: Valid in phase 3 (PHASE_VECTORS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL1 0xe
+/* enum: Valid in phase 3 (PHASE_VECTORS) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL1 0xf
+/* enum: Valid in phases 1 (PHASE_RESET) and 4 (PHASE_READY) only */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_ALL 0xffffffff
+/* Chunk ID, or CHUNK_ID_LAST or CHUNK_ID_ABORT */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_OFST 8
+/* enum: Last chunk, containing checksum rather than data */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_LAST 0xffffffff
+/* enum: Abort download of this item */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_ABORT 0xfffffffe
+/* Length of this chunk in bytes */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_LEN_OFST 12
+/* Data for this chunk */
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_OFST 16
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_LEN 4
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MINNUM 1
+#define MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MAXNUM 59
+
+/* MC_CMD_SATELLITE_DOWNLOAD_OUT msgresponse */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_LEN 8
+/* Same as MC_CMD_ERR field, but included as 0 in success cases */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_RESULT_OFST 0
+/* Extra status information */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_INFO_OFST 4
+/* enum: Code download OK, completed. */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_COMPLETE 0x0
+/* enum: Code download aborted as requested. */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_ABORTED 0x1
+/* enum: Code download OK so far, send next chunk. */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_NEXT_CHUNK 0x2
+/* enum: Download phases out of sequence */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_PHASE 0x100
+/* enum: Bad target for this phase */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_TARGET 0x101
+/* enum: Chunk ID out of sequence */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_ID 0x200
+/* enum: Chunk length zero or too large */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_LEN 0x201
+/* enum: Checksum was incorrect */
+#define MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHECKSUM 0x300
+
+
+/***********************************/
+/* MC_CMD_GET_CAPABILITIES
+ * Get device capabilities.
+ *
+ * This is supplementary to the MC_CMD_GET_BOARD_CFG command, and intended to
+ * reference inherent device capabilities as opposed to current NVRAM config.
+ */
+#define MC_CMD_GET_CAPABILITIES 0xbe
+
+/* MC_CMD_GET_CAPABILITIES_IN msgrequest */
+#define MC_CMD_GET_CAPABILITIES_IN_LEN 0
+
+/* MC_CMD_GET_CAPABILITIES_OUT msgresponse */
+#define MC_CMD_GET_CAPABILITIES_OUT_LEN 20
+/* First word of flags. */
+#define MC_CMD_GET_CAPABILITIES_OUT_FLAGS1_OFST 0
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_VLAN_INSERTION_LBN 19
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_VLAN_STRIPPING_LBN 20
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN 21
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_0_LBN 22
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_LBN 23
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_TIMESTAMP_LBN 24
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_TIMESTAMP_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN 25
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+/* RxDPCPU firmware id. */
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4
+#define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP 0x0
+/* enum: Low latency RXDP firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_LOW_LATENCY 0x1
+/* enum: RXDP Test firmware image 1 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+/* enum: RXDP Test firmware image 2 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+/* enum: RXDP Test firmware image 3 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+/* enum: RXDP Test firmware image 4 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+/* enum: RXDP Test firmware image 5 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_BACKPRESSURE 0x105
+/* enum: RXDP Test firmware image 6 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+/* enum: RXDP Test firmware image 7 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+/* enum: RXDP Test firmware image 8 */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+/* TxDPCPU firmware id. */
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_OFST 6
+#define MC_CMD_GET_CAPABILITIES_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXDP 0x0
+/* enum: Low latency TXDP firmware */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXDP_LOW_LATENCY 0x1
+/* enum: TXDP Test firmware image 1 */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+/* enum: TXDP Test firmware image 2 */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_OFST 8
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_LEN 2
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_VSWITCH 0x3 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_OFST 10
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_LEN 2
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_VSWITCH 0x3 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4 /* enum */
+#define MC_CMD_GET_CAPABILITIES_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* Hardware capabilities of NIC */
+#define MC_CMD_GET_CAPABILITIES_OUT_HW_CAPABILITIES_OFST 12
+/* Licensed capabilities */
+#define MC_CMD_GET_CAPABILITIES_OUT_LICENSE_CAPABILITIES_OFST 16
+
+
+/***********************************/
+/* MC_CMD_V2_EXTN
+ * Encapsulation for a v2 extended command
+ */
+#define MC_CMD_V2_EXTN 0x7f
+
+/* MC_CMD_V2_EXTN_IN msgrequest */
+#define MC_CMD_V2_EXTN_IN_LEN 4
+/* the extended command number */
+#define MC_CMD_V2_EXTN_IN_EXTENDED_CMD_LBN 0
+#define MC_CMD_V2_EXTN_IN_EXTENDED_CMD_WIDTH 15
+#define MC_CMD_V2_EXTN_IN_UNUSED_LBN 15
+#define MC_CMD_V2_EXTN_IN_UNUSED_WIDTH 1
+/* the actual length of the encapsulated command (which is not in the v1
+ * header)
+ */
+#define MC_CMD_V2_EXTN_IN_ACTUAL_LEN_LBN 16
+#define MC_CMD_V2_EXTN_IN_ACTUAL_LEN_WIDTH 10
+#define MC_CMD_V2_EXTN_IN_UNUSED2_LBN 26
+#define MC_CMD_V2_EXTN_IN_UNUSED2_WIDTH 6
+
+
+/***********************************/
+/* MC_CMD_TCM_BUCKET_ALLOC
+ * Allocate a pacer bucket (for qau rp or a snapper test)
+ */
+#define MC_CMD_TCM_BUCKET_ALLOC 0xb2
+
+/* MC_CMD_TCM_BUCKET_ALLOC_IN msgrequest */
+#define MC_CMD_TCM_BUCKET_ALLOC_IN_LEN 0
+
+/* MC_CMD_TCM_BUCKET_ALLOC_OUT msgresponse */
+#define MC_CMD_TCM_BUCKET_ALLOC_OUT_LEN 4
+/* the bucket id */
+#define MC_CMD_TCM_BUCKET_ALLOC_OUT_BUCKET_OFST 0
+
+
+/***********************************/
+/* MC_CMD_TCM_BUCKET_FREE
+ * Free a pacer bucket
+ */
+#define MC_CMD_TCM_BUCKET_FREE 0xb3
+
+/* MC_CMD_TCM_BUCKET_FREE_IN msgrequest */
+#define MC_CMD_TCM_BUCKET_FREE_IN_LEN 4
+/* the bucket id */
+#define MC_CMD_TCM_BUCKET_FREE_IN_BUCKET_OFST 0
+
+/* MC_CMD_TCM_BUCKET_FREE_OUT msgresponse */
+#define MC_CMD_TCM_BUCKET_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_TCM_BUCKET_INIT
+ * Initialise pacer bucket with a given rate
+ */
+#define MC_CMD_TCM_BUCKET_INIT 0xb4
+
+/* MC_CMD_TCM_BUCKET_INIT_IN msgrequest */
+#define MC_CMD_TCM_BUCKET_INIT_IN_LEN 8
+/* the bucket id */
+#define MC_CMD_TCM_BUCKET_INIT_IN_BUCKET_OFST 0
+/* the rate in mbps */
+#define MC_CMD_TCM_BUCKET_INIT_IN_RATE_OFST 4
+
+/* MC_CMD_TCM_BUCKET_INIT_OUT msgresponse */
+#define MC_CMD_TCM_BUCKET_INIT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_TCM_TXQ_INIT
+ * Initialise txq in pacer with given options or set options
+ */
+#define MC_CMD_TCM_TXQ_INIT 0xb5
+
+/* MC_CMD_TCM_TXQ_INIT_IN msgrequest */
+#define MC_CMD_TCM_TXQ_INIT_IN_LEN 28
+/* the txq id */
+#define MC_CMD_TCM_TXQ_INIT_IN_QID_OFST 0
+/* the static priority associated with the txq */
+#define MC_CMD_TCM_TXQ_INIT_IN_LABEL_OFST 4
+/* bitmask of the priority queues this txq is inserted into */
+#define MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_OFST 8
+/* the reaction point (RP) bucket */
+#define MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_OFST 12
+/* an already reserved bucket (typically set to bucket associated with outer
+ * vswitch)
+ */
+#define MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT1_OFST 16
+/* an already reserved bucket (typically set to bucket associated with inner
+ * vswitch)
+ */
+#define MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT2_OFST 20
+/* the min bucket (typically for ETS/minimum bandwidth) */
+#define MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_OFST 24
+
+/* MC_CMD_TCM_TXQ_INIT_OUT msgresponse */
+#define MC_CMD_TCM_TXQ_INIT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_LINK_PIOBUF
+ * Link a push I/O buffer to a TxQ
+ */
+#define MC_CMD_LINK_PIOBUF 0x92
+
+/* MC_CMD_LINK_PIOBUF_IN msgrequest */
+#define MC_CMD_LINK_PIOBUF_IN_LEN 8
+/* Handle for allocated push I/O buffer. */
+#define MC_CMD_LINK_PIOBUF_IN_PIOBUF_HANDLE_OFST 0
+/* Function Local Instance (VI) number. */
+#define MC_CMD_LINK_PIOBUF_IN_TXQ_INSTANCE_OFST 4
+
+/* MC_CMD_LINK_PIOBUF_OUT msgresponse */
+#define MC_CMD_LINK_PIOBUF_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_UNLINK_PIOBUF
+ * Unlink a push I/O buffer from a TxQ
+ */
+#define MC_CMD_UNLINK_PIOBUF 0x93
+
+/* MC_CMD_UNLINK_PIOBUF_IN msgrequest */
+#define MC_CMD_UNLINK_PIOBUF_IN_LEN 4
+/* Function Local Instance (VI) number. */
+#define MC_CMD_UNLINK_PIOBUF_IN_TXQ_INSTANCE_OFST 0
+
+/* MC_CMD_UNLINK_PIOBUF_OUT msgresponse */
+#define MC_CMD_UNLINK_PIOBUF_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VSWITCH_ALLOC
+ * allocate and initialise a v-switch.
+ */
+#define MC_CMD_VSWITCH_ALLOC 0x94
+
+/* MC_CMD_VSWITCH_ALLOC_IN msgrequest */
+#define MC_CMD_VSWITCH_ALLOC_IN_LEN 16
+/* The port to connect to the v-switch's upstream port. */
+#define MC_CMD_VSWITCH_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+/* The type of v-switch to create. */
+#define MC_CMD_VSWITCH_ALLOC_IN_TYPE_OFST 4
+/* enum: VLAN */
+#define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VLAN 0x1
+/* enum: VEB */
+#define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VEB 0x2
+/* enum: VEPA */
+#define MC_CMD_VSWITCH_ALLOC_IN_VSWITCH_TYPE_VEPA 0x3
+/* Flags controlling v-port creation */
+#define MC_CMD_VSWITCH_ALLOC_IN_FLAGS_OFST 8
+#define MC_CMD_VSWITCH_ALLOC_IN_FLAG_AUTO_PORT_LBN 0
+#define MC_CMD_VSWITCH_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1
+/* The number of VLAN tags to support. */
+#define MC_CMD_VSWITCH_ALLOC_IN_NUM_VLAN_TAGS_OFST 12
+
+/* MC_CMD_VSWITCH_ALLOC_OUT msgresponse */
+#define MC_CMD_VSWITCH_ALLOC_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VSWITCH_FREE
+ * de-allocate a v-switch.
+ */
+#define MC_CMD_VSWITCH_FREE 0x95
+
+/* MC_CMD_VSWITCH_FREE_IN msgrequest */
+#define MC_CMD_VSWITCH_FREE_IN_LEN 4
+/* The port to which the v-switch is connected. */
+#define MC_CMD_VSWITCH_FREE_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VSWITCH_FREE_OUT msgresponse */
+#define MC_CMD_VSWITCH_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VPORT_ALLOC
+ * allocate a v-port.
+ */
+#define MC_CMD_VPORT_ALLOC 0x96
+
+/* MC_CMD_VPORT_ALLOC_IN msgrequest */
+#define MC_CMD_VPORT_ALLOC_IN_LEN 20
+/* The port to which the v-switch is connected. */
+#define MC_CMD_VPORT_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+/* The type of the new v-port. */
+#define MC_CMD_VPORT_ALLOC_IN_TYPE_OFST 4
+/* enum: VLAN (obsolete) */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_VLAN 0x1
+/* enum: VEB (obsolete) */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_VEB 0x2
+/* enum: VEPA (obsolete) */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_VEPA 0x3
+/* enum: A normal v-port receives packets which match a specified MAC and/or
+ * VLAN.
+ */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL 0x4
+/* enum: An expansion v-port packets traffic which don't match any other
+ * v-port.
+ */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_EXPANSION 0x5
+/* enum: An test v-port receives packets which match any filters installed by
+ * its downstream components.
+ */
+#define MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_TEST 0x6
+/* Flags controlling v-port creation */
+#define MC_CMD_VPORT_ALLOC_IN_FLAGS_OFST 8
+#define MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_LBN 0
+#define MC_CMD_VPORT_ALLOC_IN_FLAG_AUTO_PORT_WIDTH 1
+/* The number of VLAN tags to insert/remove. */
+#define MC_CMD_VPORT_ALLOC_IN_NUM_VLAN_TAGS_OFST 12
+/* The actual VLAN tags to insert/remove */
+#define MC_CMD_VPORT_ALLOC_IN_VLAN_TAGS_OFST 16
+#define MC_CMD_VPORT_ALLOC_IN_VLAN_TAG_0_LBN 0
+#define MC_CMD_VPORT_ALLOC_IN_VLAN_TAG_0_WIDTH 16
+#define MC_CMD_VPORT_ALLOC_IN_VLAN_TAG_1_LBN 16
+#define MC_CMD_VPORT_ALLOC_IN_VLAN_TAG_1_WIDTH 16
+
+/* MC_CMD_VPORT_ALLOC_OUT msgresponse */
+#define MC_CMD_VPORT_ALLOC_OUT_LEN 4
+/* The handle of the new v-port */
+#define MC_CMD_VPORT_ALLOC_OUT_VPORT_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_VPORT_FREE
+ * de-allocate a v-port.
+ */
+#define MC_CMD_VPORT_FREE 0x97
+
+/* MC_CMD_VPORT_FREE_IN msgrequest */
+#define MC_CMD_VPORT_FREE_IN_LEN 4
+/* The handle of the v-port */
+#define MC_CMD_VPORT_FREE_IN_VPORT_ID_OFST 0
+
+/* MC_CMD_VPORT_FREE_OUT msgresponse */
+#define MC_CMD_VPORT_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VADAPTOR_ALLOC
+ * allocate a v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_ALLOC 0x98
+
+/* MC_CMD_VADAPTOR_ALLOC_IN msgrequest */
+#define MC_CMD_VADAPTOR_ALLOC_IN_LEN 16
+/* The port to connect to the v-adaptor's port. */
+#define MC_CMD_VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+/* Flags controlling v-adaptor creation */
+#define MC_CMD_VADAPTOR_ALLOC_IN_FLAGS_OFST 8
+#define MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_LBN 0
+#define MC_CMD_VADAPTOR_ALLOC_IN_FLAG_AUTO_VADAPTOR_WIDTH 1
+/* The number of VLAN tags to strip on receive */
+#define MC_CMD_VADAPTOR_ALLOC_IN_NUM_VLANS_OFST 12
+
+/* MC_CMD_VADAPTOR_ALLOC_OUT msgresponse */
+#define MC_CMD_VADAPTOR_ALLOC_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VADAPTOR_FREE
+ * de-allocate a v-adaptor.
+ */
+#define MC_CMD_VADAPTOR_FREE 0x99
+
+/* MC_CMD_VADAPTOR_FREE_IN msgrequest */
+#define MC_CMD_VADAPTOR_FREE_IN_LEN 4
+/* The port to which the v-adaptor is connected. */
+#define MC_CMD_VADAPTOR_FREE_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_VADAPTOR_FREE_OUT msgresponse */
+#define MC_CMD_VADAPTOR_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_EVB_PORT_ASSIGN
+ * assign a port to a PCI function.
+ */
+#define MC_CMD_EVB_PORT_ASSIGN 0x9a
+
+/* MC_CMD_EVB_PORT_ASSIGN_IN msgrequest */
+#define MC_CMD_EVB_PORT_ASSIGN_IN_LEN 8
+/* The port to assign. */
+#define MC_CMD_EVB_PORT_ASSIGN_IN_PORT_ID_OFST 0
+/* The target function to modify. */
+#define MC_CMD_EVB_PORT_ASSIGN_IN_FUNCTION_OFST 4
+#define MC_CMD_EVB_PORT_ASSIGN_IN_PF_LBN 0
+#define MC_CMD_EVB_PORT_ASSIGN_IN_PF_WIDTH 16
+#define MC_CMD_EVB_PORT_ASSIGN_IN_VF_LBN 16
+#define MC_CMD_EVB_PORT_ASSIGN_IN_VF_WIDTH 16
+
+/* MC_CMD_EVB_PORT_ASSIGN_OUT msgresponse */
+#define MC_CMD_EVB_PORT_ASSIGN_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RDWR_A64_REGIONS
+ * Assign the 64 bit region addresses.
+ */
+#define MC_CMD_RDWR_A64_REGIONS 0x9b
+
+/* MC_CMD_RDWR_A64_REGIONS_IN msgrequest */
+#define MC_CMD_RDWR_A64_REGIONS_IN_LEN 17
+#define MC_CMD_RDWR_A64_REGIONS_IN_REGION0_OFST 0
+#define MC_CMD_RDWR_A64_REGIONS_IN_REGION1_OFST 4
+#define MC_CMD_RDWR_A64_REGIONS_IN_REGION2_OFST 8
+#define MC_CMD_RDWR_A64_REGIONS_IN_REGION3_OFST 12
+/* Write enable bits 0-3, set to write, clear to read. */
+#define MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_LBN 128
+#define MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_WIDTH 4
+#define MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_OFST 16
+#define MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_LEN 1
+
+/* MC_CMD_RDWR_A64_REGIONS_OUT msgresponse: This data always included
+ * regardless of state of write bits in the request.
+ */
+#define MC_CMD_RDWR_A64_REGIONS_OUT_LEN 16
+#define MC_CMD_RDWR_A64_REGIONS_OUT_REGION0_OFST 0
+#define MC_CMD_RDWR_A64_REGIONS_OUT_REGION1_OFST 4
+#define MC_CMD_RDWR_A64_REGIONS_OUT_REGION2_OFST 8
+#define MC_CMD_RDWR_A64_REGIONS_OUT_REGION3_OFST 12
+
+
+/***********************************/
+/* MC_CMD_ONLOAD_STACK_ALLOC
+ * Allocate an Onload stack ID.
+ */
+#define MC_CMD_ONLOAD_STACK_ALLOC 0x9c
+
+/* MC_CMD_ONLOAD_STACK_ALLOC_IN msgrequest */
+#define MC_CMD_ONLOAD_STACK_ALLOC_IN_LEN 4
+/* The handle of the owning upstream port */
+#define MC_CMD_ONLOAD_STACK_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+
+/* MC_CMD_ONLOAD_STACK_ALLOC_OUT msgresponse */
+#define MC_CMD_ONLOAD_STACK_ALLOC_OUT_LEN 4
+/* The handle of the new Onload stack */
+#define MC_CMD_ONLOAD_STACK_ALLOC_OUT_ONLOAD_STACK_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_ONLOAD_STACK_FREE
+ * Free an Onload stack ID.
+ */
+#define MC_CMD_ONLOAD_STACK_FREE 0x9d
+
+/* MC_CMD_ONLOAD_STACK_FREE_IN msgrequest */
+#define MC_CMD_ONLOAD_STACK_FREE_IN_LEN 4
+/* The handle of the Onload stack */
+#define MC_CMD_ONLOAD_STACK_FREE_IN_ONLOAD_STACK_ID_OFST 0
+
+/* MC_CMD_ONLOAD_STACK_FREE_OUT msgresponse */
+#define MC_CMD_ONLOAD_STACK_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_ALLOC
+ * Allocate an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_ALLOC 0x9e
+
+/* MC_CMD_RSS_CONTEXT_ALLOC_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_LEN 12
+/* The handle of the owning upstream port */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+/* The type of context to allocate */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_OFST 4
+/* enum: Allocate a context for exclusive use. The key and indirection table
+ * must be explicitly configured.
+ */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_EXCLUSIVE 0x0
+/* enum: Allocate a context for shared use; this will spread across a range of
+ * queues, but the key and indirection table are pre-configured and may not be
+ * changed. For this mode, NUM_QUEUES must 2, 4, 8, 16, 32 or 64.
+ */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_TYPE_SHARED 0x1
+/* Number of queues spanned by this context, in the range 1-64; valid offsets
+ * in the indirection table will be in the range 0 to NUM_QUEUES-1.
+ */
+#define MC_CMD_RSS_CONTEXT_ALLOC_IN_NUM_QUEUES_OFST 8
+
+/* MC_CMD_RSS_CONTEXT_ALLOC_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_ALLOC_OUT_LEN 4
+/* The handle of the new RSS context */
+#define MC_CMD_RSS_CONTEXT_ALLOC_OUT_RSS_CONTEXT_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_FREE
+ * Free an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_FREE 0x9f
+
+/* MC_CMD_RSS_CONTEXT_FREE_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_FREE_IN_LEN 4
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_FREE_IN_RSS_CONTEXT_ID_OFST 0
+
+/* MC_CMD_RSS_CONTEXT_FREE_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_SET_KEY
+ * Set the Toeplitz hash key for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_SET_KEY 0xa0
+
+/* MC_CMD_RSS_CONTEXT_SET_KEY_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_SET_KEY_IN_LEN 44
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_SET_KEY_IN_RSS_CONTEXT_ID_OFST 0
+/* The 40-byte Toeplitz hash key (TBD endianness issues?) */
+#define MC_CMD_RSS_CONTEXT_SET_KEY_IN_TOEPLITZ_KEY_OFST 4
+#define MC_CMD_RSS_CONTEXT_SET_KEY_IN_TOEPLITZ_KEY_LEN 40
+
+/* MC_CMD_RSS_CONTEXT_SET_KEY_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_SET_KEY_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_GET_KEY
+ * Get the Toeplitz hash key for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_GET_KEY 0xa1
+
+/* MC_CMD_RSS_CONTEXT_GET_KEY_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_GET_KEY_IN_LEN 4
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_GET_KEY_IN_RSS_CONTEXT_ID_OFST 0
+
+/* MC_CMD_RSS_CONTEXT_GET_KEY_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_GET_KEY_OUT_LEN 44
+/* The 40-byte Toeplitz hash key (TBD endianness issues?) */
+#define MC_CMD_RSS_CONTEXT_GET_KEY_OUT_TOEPLITZ_KEY_OFST 4
+#define MC_CMD_RSS_CONTEXT_GET_KEY_OUT_TOEPLITZ_KEY_LEN 40
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_SET_TABLE
+ * Set the indirection table for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_SET_TABLE 0xa2
+
+/* MC_CMD_RSS_CONTEXT_SET_TABLE_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_SET_TABLE_IN_LEN 132
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_SET_TABLE_IN_RSS_CONTEXT_ID_OFST 0
+/* The 128-byte indirection table (1 byte per entry) */
+#define MC_CMD_RSS_CONTEXT_SET_TABLE_IN_INDIRECTION_TABLE_OFST 4
+#define MC_CMD_RSS_CONTEXT_SET_TABLE_IN_INDIRECTION_TABLE_LEN 128
+
+/* MC_CMD_RSS_CONTEXT_SET_TABLE_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_SET_TABLE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_GET_TABLE
+ * Get the indirection table for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_GET_TABLE 0xa3
+
+/* MC_CMD_RSS_CONTEXT_GET_TABLE_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_GET_TABLE_IN_LEN 4
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_GET_TABLE_IN_RSS_CONTEXT_ID_OFST 0
+
+/* MC_CMD_RSS_CONTEXT_GET_TABLE_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_GET_TABLE_OUT_LEN 132
+/* The 128-byte indirection table (1 byte per entry) */
+#define MC_CMD_RSS_CONTEXT_GET_TABLE_OUT_INDIRECTION_TABLE_OFST 4
+#define MC_CMD_RSS_CONTEXT_GET_TABLE_OUT_INDIRECTION_TABLE_LEN 128
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_SET_FLAGS
+ * Set various control flags for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS 0xe1
+
+/* MC_CMD_RSS_CONTEXT_SET_FLAGS_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_LEN 8
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_RSS_CONTEXT_ID_OFST 0
+/* Hash control flags */
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_FLAGS_OFST 4
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_LBN 0
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV4_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV4_EN_LBN 1
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV4_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV6_EN_LBN 2
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_IPV6_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV6_EN_LBN 3
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_IN_TOEPLITZ_TCPV6_EN_WIDTH 1
+
+/* MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_SET_FLAGS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RSS_CONTEXT_GET_FLAGS
+ * Get various control flags for an RSS context.
+ */
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS 0xe2
+
+/* MC_CMD_RSS_CONTEXT_GET_FLAGS_IN msgrequest */
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_IN_LEN 4
+/* The handle of the RSS context */
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_IN_RSS_CONTEXT_ID_OFST 0
+
+/* MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT msgresponse */
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_LEN 8
+/* Hash control flags */
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_FLAGS_OFST 4
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_LBN 0
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV4_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV4_EN_LBN 1
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV4_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV6_EN_LBN 2
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_IPV6_EN_WIDTH 1
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_LBN 3
+#define MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_TOEPLITZ_TCPV6_EN_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_DOT1P_MAPPING_ALLOC
+ * Allocate a .1p mapping.
+ */
+#define MC_CMD_DOT1P_MAPPING_ALLOC 0xa4
+
+/* MC_CMD_DOT1P_MAPPING_ALLOC_IN msgrequest */
+#define MC_CMD_DOT1P_MAPPING_ALLOC_IN_LEN 8
+/* The handle of the owning upstream port */
+#define MC_CMD_DOT1P_MAPPING_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
+/* Number of queues spanned by this mapping, in the range 1-64; valid fixed
+ * offsets in the mapping table will be in the range 0 to NUM_QUEUES-1, and
+ * referenced RSS contexts must span no more than this number.
+ */
+#define MC_CMD_DOT1P_MAPPING_ALLOC_IN_NUM_QUEUES_OFST 4
+
+/* MC_CMD_DOT1P_MAPPING_ALLOC_OUT msgresponse */
+#define MC_CMD_DOT1P_MAPPING_ALLOC_OUT_LEN 4
+/* The handle of the new .1p mapping */
+#define MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_OFST 0
+
+
+/***********************************/
+/* MC_CMD_DOT1P_MAPPING_FREE
+ * Free a .1p mapping.
+ */
+#define MC_CMD_DOT1P_MAPPING_FREE 0xa5
+
+/* MC_CMD_DOT1P_MAPPING_FREE_IN msgrequest */
+#define MC_CMD_DOT1P_MAPPING_FREE_IN_LEN 4
+/* The handle of the .1p mapping */
+#define MC_CMD_DOT1P_MAPPING_FREE_IN_DOT1P_MAPPING_ID_OFST 0
+
+/* MC_CMD_DOT1P_MAPPING_FREE_OUT msgresponse */
+#define MC_CMD_DOT1P_MAPPING_FREE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_DOT1P_MAPPING_SET_TABLE
+ * Set the mapping table for a .1p mapping.
+ */
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE 0xa6
+
+/* MC_CMD_DOT1P_MAPPING_SET_TABLE_IN msgrequest */
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_LEN 36
+/* The handle of the .1p mapping */
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
+/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
+ * handle)
+ */
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_OFST 4
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_LEN 32
+
+/* MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT msgresponse */
+#define MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_DOT1P_MAPPING_GET_TABLE
+ * Get the mapping table for a .1p mapping.
+ */
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE 0xa7
+
+/* MC_CMD_DOT1P_MAPPING_GET_TABLE_IN msgrequest */
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_LEN 4
+/* The handle of the .1p mapping */
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
+
+/* MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT msgresponse */
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_LEN 36
+/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
+ * handle)
+ */
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_OFST 4
+#define MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_LEN 32
+
+
+/***********************************/
+/* MC_CMD_GET_VECTOR_CFG
+ * Get Interrupt Vector config for this PF.
+ */
+#define MC_CMD_GET_VECTOR_CFG 0xbf
+
+/* MC_CMD_GET_VECTOR_CFG_IN msgrequest */
+#define MC_CMD_GET_VECTOR_CFG_IN_LEN 0
+
+/* MC_CMD_GET_VECTOR_CFG_OUT msgresponse */
+#define MC_CMD_GET_VECTOR_CFG_OUT_LEN 12
+/* Base absolute interrupt vector number. */
+#define MC_CMD_GET_VECTOR_CFG_OUT_VEC_BASE_OFST 0
+/* Number of interrupt vectors allocate to this PF. */
+#define MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_PF_OFST 4
+/* Number of interrupt vectors to allocate per VF. */
+#define MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_VF_OFST 8
+
+
+/***********************************/
+/* MC_CMD_SET_VECTOR_CFG
+ * Set Interrupt Vector config for this PF.
+ */
+#define MC_CMD_SET_VECTOR_CFG 0xc0
+
+/* MC_CMD_SET_VECTOR_CFG_IN msgrequest */
+#define MC_CMD_SET_VECTOR_CFG_IN_LEN 12
+/* Base absolute interrupt vector number, or MC_CMD_RESOURCE_INSTANCE_ANY to
+ * let the system find a suitable base.
+ */
+#define MC_CMD_SET_VECTOR_CFG_IN_VEC_BASE_OFST 0
+/* Number of interrupt vectors allocate to this PF. */
+#define MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_PF_OFST 4
+/* Number of interrupt vectors to allocate per VF. */
+#define MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_VF_OFST 8
+
+/* MC_CMD_SET_VECTOR_CFG_OUT msgresponse */
+#define MC_CMD_SET_VECTOR_CFG_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_CLASS_STATS
+ * Retrieve rmon rx class statistics
+ */
+#define MC_CMD_RMON_RX_CLASS_STATS 0xc3
+
+/* MC_CMD_RMON_RX_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_RX_CLASS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_CLASS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_CLASS_STATS
+ * Retrieve rmon tx class statistics
+ */
+#define MC_CMD_RMON_TX_CLASS_STATS 0xc4
+
+/* MC_CMD_RMON_TX_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_TX_CLASS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_CLASS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_SUPER_CLASS_STATS
+ * Retrieve rmon rx super_class statistics
+ */
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS 0xc5
+
+/* MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_RST_LBN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_SUPER_CLASS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_SUPER_CLASS_STATS
+ * Retrieve rmon tx super_class statistics
+ */
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS 0xc6
+
+/* MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_RST_LBN 4
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_SUPER_CLASS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS
+ * Add qid to class for statistics collection
+ */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS 0xc7
+
+/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN msgrequest */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_LEN 12
+/* class */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_CLASS_OFST 0
+/* qid */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_QID_OFST 4
+/* flags */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_MTU_LBN 8
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14
+
+/* MC_CMD_RMON_RX_ADD_QID_TO_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_RX_ADD_QID_TO_CLASS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS
+ * Add qid to class for statistics collection
+ */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS 0xc8
+
+/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN msgrequest */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_LEN 12
+/* class */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_CLASS_OFST 0
+/* qid */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_QID_OFST 4
+/* flags */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_MTU_LBN 8
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14
+
+/* MC_CMD_RMON_TX_ADD_QID_TO_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_TX_ADD_QID_TO_CLASS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS
+ * Add qid to class for statistics collection
+ */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS 0xc9
+
+/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN msgrequest */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_LEN 12
+/* class */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_CLASS_OFST 0
+/* qid */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_QID_OFST 4
+/* flags */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_FLAGS_OFST 8
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_PE_DELTA_LBN 4
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_PE_DELTA_WIDTH 4
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_MTU_LBN 8
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_IN_MTU_WIDTH 14
+
+/* MC_CMD_RMON_MC_ADD_QID_TO_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_MC_ADD_QID_TO_CLASS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_ALLOC_CLASS
+ * Allocate an rmon class
+ */
+#define MC_CMD_RMON_ALLOC_CLASS 0xca
+
+/* MC_CMD_RMON_ALLOC_CLASS_IN msgrequest */
+#define MC_CMD_RMON_ALLOC_CLASS_IN_LEN 0
+
+/* MC_CMD_RMON_ALLOC_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_ALLOC_CLASS_OUT_LEN 4
+/* class */
+#define MC_CMD_RMON_ALLOC_CLASS_OUT_CLASS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_RMON_DEALLOC_CLASS
+ * Deallocate an rmon class
+ */
+#define MC_CMD_RMON_DEALLOC_CLASS 0xcb
+
+/* MC_CMD_RMON_DEALLOC_CLASS_IN msgrequest */
+#define MC_CMD_RMON_DEALLOC_CLASS_IN_LEN 4
+/* class */
+#define MC_CMD_RMON_DEALLOC_CLASS_IN_CLASS_OFST 0
+
+/* MC_CMD_RMON_DEALLOC_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_DEALLOC_CLASS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_ALLOC_SUPER_CLASS
+ * Allocate an rmon super_class
+ */
+#define MC_CMD_RMON_ALLOC_SUPER_CLASS 0xcc
+
+/* MC_CMD_RMON_ALLOC_SUPER_CLASS_IN msgrequest */
+#define MC_CMD_RMON_ALLOC_SUPER_CLASS_IN_LEN 0
+
+/* MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT_LEN 4
+/* super_class */
+#define MC_CMD_RMON_ALLOC_SUPER_CLASS_OUT_SUPER_CLASS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_RMON_DEALLOC_SUPER_CLASS
+ * Deallocate an rmon tx super_class
+ */
+#define MC_CMD_RMON_DEALLOC_SUPER_CLASS 0xcd
+
+/* MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN msgrequest */
+#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN_LEN 4
+/* super_class */
+#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_IN_SUPER_CLASS_OFST 0
+
+/* MC_CMD_RMON_DEALLOC_SUPER_CLASS_OUT msgresponse */
+#define MC_CMD_RMON_DEALLOC_SUPER_CLASS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_UP_CONV_STATS
+ * Retrieve up converter statistics
+ */
+#define MC_CMD_RMON_RX_UP_CONV_STATS 0xce
+
+/* MC_CMD_RMON_RX_UP_CONV_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_PORT_LBN 0
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_PORT_WIDTH 2
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_RST_LBN 2
+#define MC_CMD_RMON_RX_UP_CONV_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_UP_CONV_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_UP_CONV_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_IPI_STATS
+ * Retrieve rx ipi stats
+ */
+#define MC_CMD_RMON_RX_IPI_STATS 0xcf
+
+/* MC_CMD_RMON_RX_IPI_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_IPI_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_IPI_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_IPI_STATS_IN_VFIFO_LBN 0
+#define MC_CMD_RMON_RX_IPI_STATS_IN_VFIFO_WIDTH 5
+#define MC_CMD_RMON_RX_IPI_STATS_IN_RST_LBN 5
+#define MC_CMD_RMON_RX_IPI_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_IPI_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_IPI_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS
+ * Retrieve rx ipsec cntxt_ptr indexed stats
+ */
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS 0xd0
+
+/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_LBN 0
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_WIDTH 9
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_RST_LBN 9
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_IPSEC_PORT_STATS
+ * Retrieve rx ipsec port indexed stats
+ */
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS 0xd1
+
+/* MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_PORT_LBN 0
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_PORT_WIDTH 2
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_RST_LBN 2
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_IPSEC_PORT_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS
+ * Retrieve tx ipsec overflow
+ */
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS 0xd2
+
+/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_PORT_LBN 0
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_PORT_WIDTH 2
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_RST_LBN 2
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_IPSEC_OFLOW_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_VPORT_ADD_MAC_ADDRESS
+ * Add a MAC address to a v-port
+ */
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS 0xa8
+
+/* MC_CMD_VPORT_ADD_MAC_ADDRESS_IN msgrequest */
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN 10
+/* The handle of the v-port */
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_VPORT_ID_OFST 0
+/* MAC address to add */
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_MACADDR_OFST 4
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_MACADDR_LEN 6
+
+/* MC_CMD_VPORT_ADD_MAC_ADDRESS_OUT msgresponse */
+#define MC_CMD_VPORT_ADD_MAC_ADDRESS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VPORT_DEL_MAC_ADDRESS
+ * Delete a MAC address from a v-port
+ */
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS 0xa9
+
+/* MC_CMD_VPORT_DEL_MAC_ADDRESS_IN msgrequest */
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN 10
+/* The handle of the v-port */
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID_OFST 0
+/* MAC address to add */
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_MACADDR_OFST 4
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_MACADDR_LEN 6
+
+/* MC_CMD_VPORT_DEL_MAC_ADDRESS_OUT msgresponse */
+#define MC_CMD_VPORT_DEL_MAC_ADDRESS_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_VPORT_GET_MAC_ADDRESSES
+ * Delete a MAC address from a v-port
+ */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES 0xaa
+
+/* MC_CMD_VPORT_GET_MAC_ADDRESSES_IN msgrequest */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_LEN 4
+/* The handle of the v-port */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_IN_VPORT_ID_OFST 0
+
+/* MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT msgresponse */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMIN 4
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LENMAX 250
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_LEN(num) (4+6*(num))
+/* The number of MAC addresses returned */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_COUNT_OFST 0
+/* Array of MAC addresses */
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_OFST 4
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_LEN 6
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_MINNUM 0
+#define MC_CMD_VPORT_GET_MAC_ADDRESSES_OUT_MACADDR_MAXNUM 41
+
+
+/***********************************/
+/* MC_CMD_DUMP_BUFTBL_ENTRIES
+ * Dump buffer table entries, mainly for command client debug use. Dumps
+ * absolute entries, and does not use chunk handles. All entries must be in
+ * range, and used for q page mapping, Although the latter restriction may be
+ * lifted in future.
+ */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES 0xab
+
+/* MC_CMD_DUMP_BUFTBL_ENTRIES_IN msgrequest */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_IN_LEN 8
+/* Index of the first buffer table entry. */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_IN_FIRSTID_OFST 0
+/* Number of buffer table entries to dump. */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 4
+
+/* MC_CMD_DUMP_BUFTBL_ENTRIES_OUT msgresponse */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMIN 12
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX 252
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LEN(num) (0+12*(num))
+/* Raw buffer table entries, layed out as BUFTBL_ENTRY. */
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_OFST 0
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_LEN 12
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MINNUM 1
+#define MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MAXNUM 21
+
+
+/***********************************/
+/* MC_CMD_SET_RXDP_CONFIG
+ * Set global RXDP configuration settings
+ */
+#define MC_CMD_SET_RXDP_CONFIG 0xc1
+
+/* MC_CMD_SET_RXDP_CONFIG_IN msgrequest */
+#define MC_CMD_SET_RXDP_CONFIG_IN_LEN 4
+#define MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
+#define MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_LBN 0
+#define MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_WIDTH 1
+
+/* MC_CMD_SET_RXDP_CONFIG_OUT msgresponse */
+#define MC_CMD_SET_RXDP_CONFIG_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_RXDP_CONFIG
+ * Get global RXDP configuration settings
+ */
+#define MC_CMD_GET_RXDP_CONFIG 0xc2
+
+/* MC_CMD_GET_RXDP_CONFIG_IN msgrequest */
+#define MC_CMD_GET_RXDP_CONFIG_IN_LEN 0
+
+/* MC_CMD_GET_RXDP_CONFIG_OUT msgresponse */
+#define MC_CMD_GET_RXDP_CONFIG_OUT_LEN 4
+#define MC_CMD_GET_RXDP_CONFIG_OUT_DATA_OFST 0
+#define MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_LBN 0
+#define MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_CLASS_DROPS_STATS
+ * Retrieve rx class drop stats
+ */
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS 0xd3
+
+/* MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_CLASS_DROPS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS
+ * Retrieve rx super class drop stats
+ */
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS 0xd4
+
+/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_SUPER_CLASS_LBN 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_SUPER_CLASS_WIDTH 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_RST_LBN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_SUPER_CLASS_DROPS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_ERRORS_STATS
+ * Retrieve rxdp errors
+ */
+#define MC_CMD_RMON_RX_ERRORS_STATS 0xd5
+
+/* MC_CMD_RMON_RX_ERRORS_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_QID_LBN 0
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_QID_WIDTH 11
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_RST_LBN 11
+#define MC_CMD_RMON_RX_ERRORS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_ERRORS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_ERRORS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_RX_OVERFLOW_STATS
+ * Retrieve rxdp overflow
+ */
+#define MC_CMD_RMON_RX_OVERFLOW_STATS 0xd6
+
+/* MC_CMD_RMON_RX_OVERFLOW_STATS_IN msgrequest */
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_RX_OVERFLOW_STATS_OUT msgresponse */
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_RX_OVERFLOW_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_IPI_STATS
+ * Retrieve tx ipi stats
+ */
+#define MC_CMD_RMON_TX_IPI_STATS 0xd7
+
+/* MC_CMD_RMON_TX_IPI_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_IPI_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_IPI_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_IPI_STATS_IN_VFIFO_LBN 0
+#define MC_CMD_RMON_TX_IPI_STATS_IN_VFIFO_WIDTH 5
+#define MC_CMD_RMON_TX_IPI_STATS_IN_RST_LBN 5
+#define MC_CMD_RMON_TX_IPI_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_IPI_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_IPI_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS
+ * Retrieve tx ipsec counters by cntxt_ptr
+ */
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS 0xd8
+
+/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_LBN 0
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_CNTXT_PTR_WIDTH 9
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_RST_LBN 9
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_IPSEC_CNTXT_PTR_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_IPSEC_PORT_STATS
+ * Retrieve tx ipsec counters by port
+ */
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS 0xd9
+
+/* MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_PORT_LBN 0
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_PORT_WIDTH 2
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_RST_LBN 2
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_IPSEC_PORT_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS
+ * Retrieve tx ipsec overflow
+ */
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS 0xda
+
+/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_PORT_LBN 0
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_PORT_WIDTH 2
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_RST_LBN 2
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_IPSEC_OFLOW_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_NOWHERE_STATS
+ * Retrieve tx nowhere stats
+ */
+#define MC_CMD_RMON_TX_NOWHERE_STATS 0xdb
+
+/* MC_CMD_RMON_TX_NOWHERE_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_TX_NOWHERE_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_NOWHERE_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_NOWHERE_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS
+ * Retrieve tx nowhere qbb stats
+ */
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS 0xdc
+
+/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_PRIORITY_LBN 0
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_PRIORITY_WIDTH 3
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_RST_LBN 3
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_NOWHERE_QBB_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_ERRORS_STATS
+ * Retrieve rxdp errors
+ */
+#define MC_CMD_RMON_TX_ERRORS_STATS 0xdd
+
+/* MC_CMD_RMON_TX_ERRORS_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_QID_LBN 0
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_QID_WIDTH 11
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_RST_LBN 11
+#define MC_CMD_RMON_TX_ERRORS_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_ERRORS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_ERRORS_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_TX_OVERFLOW_STATS
+ * Retrieve rxdp overflow
+ */
+#define MC_CMD_RMON_TX_OVERFLOW_STATS 0xde
+
+/* MC_CMD_RMON_TX_OVERFLOW_STATS_IN msgrequest */
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_LEN 4
+/* flags */
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_FLAGS_OFST 0
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_CLASS_LBN 0
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_CLASS_WIDTH 8
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_RST_LBN 8
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_IN_RST_WIDTH 1
+
+/* MC_CMD_RMON_TX_OVERFLOW_STATS_OUT msgresponse */
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LENMIN 4
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LENMAX 252
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_LEN(num) (0+4*(num))
+/* Array of stats */
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_OFST 0
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_LEN 4
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_MINNUM 1
+#define MC_CMD_RMON_TX_OVERFLOW_STATS_OUT_BUFFER_MAXNUM 63
+
+
+/***********************************/
+/* MC_CMD_RMON_COLLECT_CLASS_STATS
+ * Explicitly collect class stats at the specified evb port
+ */
+#define MC_CMD_RMON_COLLECT_CLASS_STATS 0xdf
+
+/* MC_CMD_RMON_COLLECT_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_COLLECT_CLASS_STATS_IN_LEN 4
+/* The port id associated with the vport/pport at which to collect class stats
+ */
+#define MC_CMD_RMON_COLLECT_CLASS_STATS_IN_PORT_ID_OFST 0
+
+/* MC_CMD_RMON_COLLECT_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_COLLECT_CLASS_STATS_OUT_LEN 4
+/* class */
+#define MC_CMD_RMON_COLLECT_CLASS_STATS_OUT_CLASS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS
+ * Explicitly collect class stats at the specified evb port
+ */
+#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS 0xe0
+
+/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN msgrequest */
+#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN_LEN 4
+/* The port id associated with the vport/pport at which to collect class stats
+ */
+#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_IN_PORT_ID_OFST 0
+
+/* MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT msgresponse */
+#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT_LEN 4
+/* super_class */
+#define MC_CMD_RMON_COLLECT_SUPER_CLASS_STATS_OUT_SUPER_CLASS_OFST 0
+
+
+/***********************************/
+/* MC_CMD_GET_CLOCK
+ * Return the system and PDCPU clock frequencies.
+ */
+#define MC_CMD_GET_CLOCK 0xac
+
+/* MC_CMD_GET_CLOCK_IN msgrequest */
+#define MC_CMD_GET_CLOCK_IN_LEN 0
+
+/* MC_CMD_GET_CLOCK_OUT msgresponse */
+#define MC_CMD_GET_CLOCK_OUT_LEN 8
+/* System frequency, MHz */
+#define MC_CMD_GET_CLOCK_OUT_SYS_FREQ_OFST 0
+/* DPCPU frequency, MHz */
+#define MC_CMD_GET_CLOCK_OUT_DPCPU_FREQ_OFST 4
+
+
+/***********************************/
+/* MC_CMD_SET_CLOCK
+ * Control the system and DPCPU clock frequencies. Changes are lost reboot.
+ */
+#define MC_CMD_SET_CLOCK 0xad
+
+/* MC_CMD_SET_CLOCK_IN msgrequest */
+#define MC_CMD_SET_CLOCK_IN_LEN 12
+/* Requested system frequency in MHz; 0 leaves unchanged. */
+#define MC_CMD_SET_CLOCK_IN_SYS_FREQ_OFST 0
+/* Requested inter-core frequency in MHz; 0 leaves unchanged. */
+#define MC_CMD_SET_CLOCK_IN_ICORE_FREQ_OFST 4
+/* Request DPCPU frequency in MHz; 0 leaves unchanged. */
+#define MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_OFST 8
+
+/* MC_CMD_SET_CLOCK_OUT msgresponse */
+#define MC_CMD_SET_CLOCK_OUT_LEN 12
+/* Resulting system frequency in MHz */
+#define MC_CMD_SET_CLOCK_OUT_SYS_FREQ_OFST 0
+/* Resulting inter-core frequency in MHz */
+#define MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_OFST 4
+/* Resulting DPCPU frequency in MHz */
+#define MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_OFST 8
+
+
+/***********************************/
+/* MC_CMD_DPCPU_RPC
+ * Send an arbitrary DPCPU message.
+ */
+#define MC_CMD_DPCPU_RPC 0xae
+
+/* MC_CMD_DPCPU_RPC_IN msgrequest */
+#define MC_CMD_DPCPU_RPC_IN_LEN 36
+#define MC_CMD_DPCPU_RPC_IN_CPU_OFST 0
+/* enum: RxDPCPU */
+#define MC_CMD_DPCPU_RPC_IN_DPCPU_RX 0x0
+/* enum: TxDPCPU0 */
+#define MC_CMD_DPCPU_RPC_IN_DPCPU_TX0 0x1
+/* enum: TxDPCPU1 */
+#define MC_CMD_DPCPU_RPC_IN_DPCPU_TX1 0x2
+/* First 8 bits [39:32] of DATA are consumed by MC-DPCPU protocol and must be
+ * initialised to zero
+ */
+#define MC_CMD_DPCPU_RPC_IN_DATA_OFST 4
+#define MC_CMD_DPCPU_RPC_IN_DATA_LEN 32
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_LBN 8
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_WIDTH 8
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_READ 0x6 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_WRITE 0x7 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_SELF_TEST 0xc /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_CSR_ACCESS 0xe /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_READ 0x46 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_WRITE 0x47 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SELF_TEST 0x4a /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_CSR_ACCESS 0x4c /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SET_MC_REPLAY_CNTXT 0x4d /* enum */
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_LBN 16
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_LBN 16
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_LBN 48
+#define MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_LBN 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_WIDTH 240
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_LBN 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_STOP_RETURN_RESULT 0x0 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_READ 0x1 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE 0x2 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE_READ 0x3 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_PIPELINED_READ 0x4 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_LBN 48
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_LBN 64
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_LBN 80
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_LBN 16
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_CUT_THROUGH 0x1 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD 0x2 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD_FIRST 0x3 /* enum */
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_LBN 64
+#define MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_WIDTH 16
+#define MC_CMD_DPCPU_RPC_IN_WDATA_OFST 12
+#define MC_CMD_DPCPU_RPC_IN_WDATA_LEN 24
+/* Register data to write. Only valid in write/write-read. */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_DATA_OFST 16
+/* Register address. */
+#define MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_ADDRESS_OFST 20
+
+/* MC_CMD_DPCPU_RPC_OUT msgresponse */
+#define MC_CMD_DPCPU_RPC_OUT_LEN 36
+#define MC_CMD_DPCPU_RPC_OUT_RC_OFST 0
+/* DATA */
+#define MC_CMD_DPCPU_RPC_OUT_DATA_OFST 4
+#define MC_CMD_DPCPU_RPC_OUT_DATA_LEN 32
+#define MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_LBN 32
+#define MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_WIDTH 16
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_LBN 48
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_WIDTH 16
+#define MC_CMD_DPCPU_RPC_OUT_RDATA_OFST 12
+#define MC_CMD_DPCPU_RPC_OUT_RDATA_LEN 24
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_1_OFST 12
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_2_OFST 16
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_3_OFST 20
+#define MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_4_OFST 24
+
+
+/***********************************/
+/* MC_CMD_TRIGGER_INTERRUPT
+ * Trigger an interrupt by prodding the BIU.
+ */
+#define MC_CMD_TRIGGER_INTERRUPT 0xe3
+
+/* MC_CMD_TRIGGER_INTERRUPT_IN msgrequest */
+#define MC_CMD_TRIGGER_INTERRUPT_IN_LEN 4
+/* Interrupt level relative to base for function. */
+#define MC_CMD_TRIGGER_INTERRUPT_IN_INTR_LEVEL_OFST 0
+
+/* MC_CMD_TRIGGER_INTERRUPT_OUT msgresponse */
+#define MC_CMD_TRIGGER_INTERRUPT_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_CAP_BLK_READ
+ * Read multiple 64bit words from capture block memory
+ */
+#define MC_CMD_CAP_BLK_READ 0xe7
+
+/* MC_CMD_CAP_BLK_READ_IN msgrequest */
+#define MC_CMD_CAP_BLK_READ_IN_LEN 12
+#define MC_CMD_CAP_BLK_READ_IN_CAP_REG_OFST 0
+#define MC_CMD_CAP_BLK_READ_IN_ADDR_OFST 4
+#define MC_CMD_CAP_BLK_READ_IN_COUNT_OFST 8
+
+/* MC_CMD_CAP_BLK_READ_OUT msgresponse */
+#define MC_CMD_CAP_BLK_READ_OUT_LENMIN 8
+#define MC_CMD_CAP_BLK_READ_OUT_LENMAX 248
+#define MC_CMD_CAP_BLK_READ_OUT_LEN(num) (0+8*(num))
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_OFST 0
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_LEN 8
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_OFST 0
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_OFST 4
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_MINNUM 1
+#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM 31
+
+
+/***********************************/
+/* MC_CMD_DUMP_DO
+ * Take a dump of the DUT state
+ */
+#define MC_CMD_DUMP_DO 0xe8
+
+/* MC_CMD_DUMP_DO_IN msgrequest */
+#define MC_CMD_DUMP_DO_IN_LEN 52
+#define MC_CMD_DUMP_DO_IN_PADDING_OFST 0
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_OFST 4
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM 0x0 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_DEFAULT 0x1 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_TYPE_OFST 8
+#define MC_CMD_DUMP_DO_IN_DUMP_LOCATION_NVRAM 0x1 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMP_LOCATION_HOST_MEMORY 0x2 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMP_LOCATION_HOST_MEMORY_MLI 0x3 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMP_LOCATION_UART 0x4 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_NVRAM_PARTITION_TYPE_ID_OFST 12
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_NVRAM_OFFSET_OFST 16
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_ADDR_LO_OFST 12
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_ADDR_HI_OFST 16
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_LO_OFST 12
+#define MC_CMD_DUMP_DO_IN_HOST_MEMORY_MLI_PAGE_SIZE 0x1000 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_HI_OFST 16
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_DEPTH_OFST 20
+#define MC_CMD_DUMP_DO_IN_HOST_MEMORY_MLI_MAX_DEPTH 0x2 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_UART_PORT_OFST 12
+/* enum: The uart port this command was received over (if using a uart
+ * transport)
+ */
+#define MC_CMD_DUMP_DO_IN_UART_PORT_SRC 0xff
+#define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_SIZE_OFST 24
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_OFST 28
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM 0x0 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_NVRAM_DUMP_PARTITION 0x1 /* enum */
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_TYPE_OFST 32
+/* Enum values, see field(s): */
+/* MC_CMD_DUMP_DO_IN/DUMPSPEC_SRC_CUSTOM_TYPE */
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_NVRAM_PARTITION_TYPE_ID_OFST 36
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_NVRAM_OFFSET_OFST 40
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_ADDR_LO_OFST 36
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_ADDR_HI_OFST 40
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_LO_OFST 36
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_HI_OFST 40
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_DEPTH_OFST 44
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_UART_PORT_OFST 36
+#define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM_SIZE_OFST 48
+
+/* MC_CMD_DUMP_DO_OUT msgresponse */
+#define MC_CMD_DUMP_DO_OUT_LEN 4
+#define MC_CMD_DUMP_DO_OUT_DUMPFILE_SIZE_OFST 0
+
+
+/***********************************/
+/* MC_CMD_DUMP_CONFIGURE_UNSOLICITED
+ * Configure unsolicited dumps
+ */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED 0xe9
+
+/* MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN msgrequest */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_LEN 52
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_ENABLE_OFST 0
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_OFST 4
+/* Enum values, see field(s): */
+/* MC_CMD_DUMP_DO/MC_CMD_DUMP_DO_IN/DUMPSPEC_SRC */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_TYPE_OFST 8
+/* Enum values, see field(s): */
+/* MC_CMD_DUMP_DO/MC_CMD_DUMP_DO_IN/DUMPSPEC_SRC_CUSTOM_TYPE */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_NVRAM_PARTITION_TYPE_ID_OFST 12
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_NVRAM_OFFSET_OFST 16
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_ADDR_LO_OFST 12
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_ADDR_HI_OFST 16
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_LO_OFST 12
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_HI_OFST 16
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_DEPTH_OFST 20
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_UART_PORT_OFST 12
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPSPEC_SRC_CUSTOM_SIZE_OFST 24
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_OFST 28
+/* Enum values, see field(s): */
+/* MC_CMD_DUMP_DO/MC_CMD_DUMP_DO_IN/DUMPFILE_DST */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_TYPE_OFST 32
+/* Enum values, see field(s): */
+/* MC_CMD_DUMP_DO/MC_CMD_DUMP_DO_IN/DUMPSPEC_SRC_CUSTOM_TYPE */
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_NVRAM_PARTITION_TYPE_ID_OFST 36
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_NVRAM_OFFSET_OFST 40
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_ADDR_LO_OFST 36
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_ADDR_HI_OFST 40
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_LO_OFST 36
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_ROOT_ADDR_HI_OFST 40
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_HOST_MEMORY_MLI_DEPTH_OFST 44
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_UART_PORT_OFST 36
+#define MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_SIZE_OFST 48
+
+
+/***********************************/
+/* MC_CMD_SET_PSU
+ * Adjusts power supply parameters. This is a warranty-voiding operation.
+ * Returns: ENOENT if the parameter or rail specified does not exist, EINVAL if
+ * the parameter is out of range.
+ */
+#define MC_CMD_SET_PSU 0xea
+
+/* MC_CMD_SET_PSU_IN msgrequest */
+#define MC_CMD_SET_PSU_IN_LEN 12
+#define MC_CMD_SET_PSU_IN_PARAM_OFST 0
+#define MC_CMD_SET_PSU_IN_PARAM_SUPPLY_VOLTAGE 0x0 /* enum */
+#define MC_CMD_SET_PSU_IN_RAIL_OFST 4
+#define MC_CMD_SET_PSU_IN_RAIL_0V9 0x0 /* enum */
+#define MC_CMD_SET_PSU_IN_RAIL_1V2 0x1 /* enum */
+/* desired value, eg voltage in mV */
+#define MC_CMD_SET_PSU_IN_VALUE_OFST 8
+
+/* MC_CMD_SET_PSU_OUT msgresponse */
+#define MC_CMD_SET_PSU_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_FUNCTION_INFO
+ * Get function information. PF and VF number.
+ */
+#define MC_CMD_GET_FUNCTION_INFO 0xec
+
+/* MC_CMD_GET_FUNCTION_INFO_IN msgrequest */
+#define MC_CMD_GET_FUNCTION_INFO_IN_LEN 0
+
+/* MC_CMD_GET_FUNCTION_INFO_OUT msgresponse */
+#define MC_CMD_GET_FUNCTION_INFO_OUT_LEN 8
+#define MC_CMD_GET_FUNCTION_INFO_OUT_PF_OFST 0
+#define MC_CMD_GET_FUNCTION_INFO_OUT_VF_OFST 4
+
+
+/***********************************/
+/* MC_CMD_ENABLE_OFFLINE_BIST
+ * Enters offline BIST mode. All queues are torn down, chip enters quiescent
+ * mode, calling function gets exclusive MCDI ownership. The only way out is
+ * reboot.
+ */
+#define MC_CMD_ENABLE_OFFLINE_BIST 0xed
+
+/* MC_CMD_ENABLE_OFFLINE_BIST_IN msgrequest */
+#define MC_CMD_ENABLE_OFFLINE_BIST_IN_LEN 0
+
+/* MC_CMD_ENABLE_OFFLINE_BIST_OUT msgresponse */
+#define MC_CMD_ENABLE_OFFLINE_BIST_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_UART_SEND_DATA
+ * Send checksummed[sic] block of data over the uart. Response is a placeholder
+ * should we wish to make this reliable; currently requests are fire-and-
+ * forget.
+ */
+#define MC_CMD_UART_SEND_DATA 0xee
+
+/* MC_CMD_UART_SEND_DATA_OUT msgrequest */
+#define MC_CMD_UART_SEND_DATA_OUT_LENMIN 16
+#define MC_CMD_UART_SEND_DATA_OUT_LENMAX 252
+#define MC_CMD_UART_SEND_DATA_OUT_LEN(num) (16+1*(num))
+/* CRC32 over OFFSET, LENGTH, RESERVED, DATA */
+#define MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_OFST 0
+/* Offset at which to write the data */
+#define MC_CMD_UART_SEND_DATA_OUT_OFFSET_OFST 4
+/* Length of data */
+#define MC_CMD_UART_SEND_DATA_OUT_LENGTH_OFST 8
+/* Reserved for future use */
+#define MC_CMD_UART_SEND_DATA_OUT_RESERVED_OFST 12
+#define MC_CMD_UART_SEND_DATA_OUT_DATA_OFST 16
+#define MC_CMD_UART_SEND_DATA_OUT_DATA_LEN 1
+#define MC_CMD_UART_SEND_DATA_OUT_DATA_MINNUM 0
+#define MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM 236
+
+/* MC_CMD_UART_SEND_DATA_IN msgresponse */
+#define MC_CMD_UART_SEND_DATA_IN_LEN 0
+
+
+/***********************************/
+/* MC_CMD_UART_RECV_DATA
+ * Request checksummed[sic] block of data over the uart. Only a placeholder,
+ * subject to change and not currently implemented.
+ */
+#define MC_CMD_UART_RECV_DATA 0xef
+
+/* MC_CMD_UART_RECV_DATA_OUT msgrequest */
+#define MC_CMD_UART_RECV_DATA_OUT_LEN 16
+/* CRC32 over OFFSET, LENGTH, RESERVED */
+#define MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_OFST 0
+/* Offset from which to read the data */
+#define MC_CMD_UART_RECV_DATA_OUT_OFFSET_OFST 4
+/* Length of data */
+#define MC_CMD_UART_RECV_DATA_OUT_LENGTH_OFST 8
+/* Reserved for future use */
+#define MC_CMD_UART_RECV_DATA_OUT_RESERVED_OFST 12
+
+/* MC_CMD_UART_RECV_DATA_IN msgresponse */
+#define MC_CMD_UART_RECV_DATA_IN_LENMIN 16
+#define MC_CMD_UART_RECV_DATA_IN_LENMAX 252
+#define MC_CMD_UART_RECV_DATA_IN_LEN(num) (16+1*(num))
+/* CRC32 over RESERVED1, RESERVED2, RESERVED3, DATA */
+#define MC_CMD_UART_RECV_DATA_IN_CHECKSUM_OFST 0
+/* Offset at which to write the data */
+#define MC_CMD_UART_RECV_DATA_IN_RESERVED1_OFST 4
+/* Length of data */
+#define MC_CMD_UART_RECV_DATA_IN_RESERVED2_OFST 8
+/* Reserved for future use */
+#define MC_CMD_UART_RECV_DATA_IN_RESERVED3_OFST 12
+#define MC_CMD_UART_RECV_DATA_IN_DATA_OFST 16
+#define MC_CMD_UART_RECV_DATA_IN_DATA_LEN 1
+#define MC_CMD_UART_RECV_DATA_IN_DATA_MINNUM 0
+#define MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM 236
+
+
+/***********************************/
+/* MC_CMD_READ_FUSES
+ * Read data programmed into the device One-Time-Programmable (OTP) Fuses
+ */
+#define MC_CMD_READ_FUSES 0xf0
+
+/* MC_CMD_READ_FUSES_IN msgrequest */
+#define MC_CMD_READ_FUSES_IN_LEN 8
+/* Offset in OTP to read */
+#define MC_CMD_READ_FUSES_IN_OFFSET_OFST 0
+/* Length of data to read in bytes */
+#define MC_CMD_READ_FUSES_IN_LENGTH_OFST 4
+
+/* MC_CMD_READ_FUSES_OUT msgresponse */
+#define MC_CMD_READ_FUSES_OUT_LENMIN 4
+#define MC_CMD_READ_FUSES_OUT_LENMAX 252
+#define MC_CMD_READ_FUSES_OUT_LEN(num) (4+1*(num))
+/* Length of returned OTP data in bytes */
+#define MC_CMD_READ_FUSES_OUT_LENGTH_OFST 0
+/* Returned data */
+#define MC_CMD_READ_FUSES_OUT_DATA_OFST 4
+#define MC_CMD_READ_FUSES_OUT_DATA_LEN 1
+#define MC_CMD_READ_FUSES_OUT_DATA_MINNUM 0
+#define MC_CMD_READ_FUSES_OUT_DATA_MAXNUM 248
+
+
+/***********************************/
+/* MC_CMD_KR_TUNE
+ * Get or set KR Serdes RXEQ and TX Driver settings
+ */
+#define MC_CMD_KR_TUNE 0xf1
+
+/* MC_CMD_KR_TUNE_IN msgrequest */
+#define MC_CMD_KR_TUNE_IN_LENMIN 4
+#define MC_CMD_KR_TUNE_IN_LENMAX 252
+#define MC_CMD_KR_TUNE_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_OP_LEN 1
+/* enum: Get current RXEQ settings */
+#define MC_CMD_KR_TUNE_IN_RXEQ_GET 0x0
+/* enum: Override RXEQ settings */
+#define MC_CMD_KR_TUNE_IN_RXEQ_SET 0x1
+/* enum: Get current TX Driver settings */
+#define MC_CMD_KR_TUNE_IN_TXEQ_GET 0x2
+/* enum: Override TX Driver settings */
+#define MC_CMD_KR_TUNE_IN_TXEQ_SET 0x3
+/* enum: Force KR Serdes reset / recalibration */
+#define MC_CMD_KR_TUNE_IN_RECAL 0x4
+/* enum: Start KR Serdes Eye diagram plot on a given lane. Lane must have valid
+ * signal.
+ */
+#define MC_CMD_KR_TUNE_IN_START_EYE_PLOT 0x5
+/* enum: Poll KR Serdes Eye diagram plot. Returns one row of BER data. The
+ * caller should call this command repeatedly after starting eye plot, until no
+ * more data is returned.
+ */
+#define MC_CMD_KR_TUNE_IN_POLL_EYE_PLOT 0x6
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_LEN 3
+/* Arguments specific to the operation */
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_ARGS_OFST 4
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_ARGS_LEN 4
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_ARGS_MINNUM 0
+#define MC_CMD_KR_TUNE_IN_KR_TUNE_ARGS_MAXNUM 62
+
+/* MC_CMD_KR_TUNE_OUT msgresponse */
+#define MC_CMD_KR_TUNE_OUT_LEN 0
+
+/* MC_CMD_KR_TUNE_RXEQ_GET_IN msgrequest */
+#define MC_CMD_KR_TUNE_RXEQ_GET_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_KR_TUNE_RXEQ_GET_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_RXEQ_GET_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_RXEQ_GET_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_RXEQ_GET_IN_KR_TUNE_RSVD_LEN 3
+
+/* MC_CMD_KR_TUNE_RXEQ_GET_OUT msgresponse */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LENMIN 4
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LENMAX 252
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LEN(num) (0+4*(num))
+/* RXEQ Parameter */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_OFST 0
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LEN 4
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_MINNUM 1
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
+/* enum: Attenuation (0-15) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_ATT 0x0
+/* enum: CTLE Boost (0-15) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_BOOST 0x1
+/* enum: Edge DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP1 0x2
+/* enum: Edge DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP2 0x3
+/* enum: Edge DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP3 0x4
+/* enum: Edge DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP4 0x5
+/* enum: Edge DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_EDFE_TAP5 0x6
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 3
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_0 0x0 /* enum */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_1 0x1 /* enum */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_2 0x2 /* enum */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_3 0x3 /* enum */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_LANE_ALL 0x4 /* enum */
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_LBN 11
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_WIDTH 1
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_RESERVED_LBN 12
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 4
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_INITIAL_LBN 16
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_INITIAL_WIDTH 8
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
+#define MC_CMD_KR_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
+
+/* MC_CMD_KR_TUNE_RXEQ_SET_IN msgrequest */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_LENMIN 8
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_LENMAX 252
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_KR_TUNE_RSVD_LEN 3
+/* RXEQ Parameter */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_OFST 4
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_LEN 4
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_MINNUM 1
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_MAXNUM 62
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_ID_LBN 0
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_ID_WIDTH 8
+/* Enum values, see field(s): */
+/* MC_CMD_KR_TUNE_RXEQ_GET_OUT/PARAM_ID */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_LANE_LBN 8
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_LANE_WIDTH 3
+/* Enum values, see field(s): */
+/* MC_CMD_KR_TUNE_RXEQ_GET_OUT/PARAM_LANE */
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_LBN 11
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_WIDTH 1
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_RESERVED_LBN 12
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_RESERVED_WIDTH 4
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_INITIAL_LBN 16
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_RESERVED2_LBN 24
+#define MC_CMD_KR_TUNE_RXEQ_SET_IN_RESERVED2_WIDTH 8
+
+/* MC_CMD_KR_TUNE_RXEQ_SET_OUT msgresponse */
+#define MC_CMD_KR_TUNE_RXEQ_SET_OUT_LEN 0
+
+/* MC_CMD_KR_TUNE_TXEQ_GET_IN msgrequest */
+#define MC_CMD_KR_TUNE_TXEQ_GET_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_RSVD_LEN 3
+
+/* MC_CMD_KR_TUNE_TXEQ_GET_OUT msgresponse */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LENMIN 4
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LENMAX 252
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LEN(num) (0+4*(num))
+/* TXEQ Parameter */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_OFST 0
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LEN 4
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MINNUM 1
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
+/* enum: TX Amplitude */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV 0x0
+/* enum: De-Emphasis Tap1 Magnitude (0-7) */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_MODE 0x1
+/* enum: De-Emphasis Tap1 Fine */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_DTLEV 0x2
+/* enum: De-Emphasis Tap2 Magnitude (0-6) */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2 0x3
+/* enum: De-Emphasis Tap2 Fine */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2TLEV 0x4
+/* enum: Pre-Emphasis Magnitude */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_E 0x5
+/* enum: Pre-Emphasis Fine */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_ETLEV 0x6
+/* enum: TX Slew Rate Coarse control */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_PREDRV_DLY 0x7
+/* enum: TX Slew Rate Fine control */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_SR_SET 0x8
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 3
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_0 0x0 /* enum */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_1 0x1 /* enum */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_2 0x2 /* enum */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_3 0x3 /* enum */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_ALL 0x4 /* enum */
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED_LBN 11
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED_WIDTH 5
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_INITIAL_LBN 16
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_INITIAL_WIDTH 8
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED2_LBN 24
+#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED2_WIDTH 8
+
+/* MC_CMD_KR_TUNE_TXEQ_SET_IN msgrequest */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LENMIN 8
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LENMAX 252
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_RSVD_LEN 3
+/* TXEQ Parameter */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_OFST 4
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LEN 4
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_MINNUM 1
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_MAXNUM 62
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_ID_LBN 0
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_ID_WIDTH 8
+/* Enum values, see field(s): */
+/* MC_CMD_KR_TUNE_TXEQ_GET_OUT/PARAM_ID */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LANE_LBN 8
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LANE_WIDTH 3
+/* Enum values, see field(s): */
+/* MC_CMD_KR_TUNE_TXEQ_GET_OUT/PARAM_LANE */
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED_LBN 11
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED_WIDTH 5
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_INITIAL_LBN 16
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED2_LBN 24
+#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED2_WIDTH 8
+
+/* MC_CMD_KR_TUNE_TXEQ_SET_OUT msgresponse */
+#define MC_CMD_KR_TUNE_TXEQ_SET_OUT_LEN 0
+
+/* MC_CMD_KR_TUNE_RECAL_IN msgrequest */
+#define MC_CMD_KR_TUNE_RECAL_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_KR_TUNE_RECAL_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_RECAL_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_RECAL_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_RECAL_IN_KR_TUNE_RSVD_LEN 3
+
+/* MC_CMD_KR_TUNE_RECAL_OUT msgresponse */
+#define MC_CMD_KR_TUNE_RECAL_OUT_LEN 0
+
+/* MC_CMD_KR_TUNE_START_EYE_PLOT_IN msgrequest */
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_LEN 8
+/* Requested operation */
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_RSVD_LEN 3
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_LANE_OFST 4
+
+/* MC_CMD_KR_TUNE_START_EYE_PLOT_OUT msgresponse */
+#define MC_CMD_KR_TUNE_START_EYE_PLOT_OUT_LEN 0
+
+/* MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN msgrequest */
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_OP_OFST 0
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_RSVD_OFST 1
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_RSVD_LEN 3
+
+/* MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT msgresponse */
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num))
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0
+#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126
+
+
+/***********************************/
+/* MC_CMD_PCIE_TUNE
+ * Get or set PCIE Serdes RXEQ and TX Driver settings
+ */
+#define MC_CMD_PCIE_TUNE 0xf2
+
+/* MC_CMD_PCIE_TUNE_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_IN_LENMIN 4
+#define MC_CMD_PCIE_TUNE_IN_LENMAX 252
+#define MC_CMD_PCIE_TUNE_IN_LEN(num) (4+4*(num))
+/* Requested operation */
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_OFST 0
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_LEN 1
+/* enum: Get current RXEQ settings */
+#define MC_CMD_PCIE_TUNE_IN_RXEQ_GET 0x0
+/* enum: Override RXEQ settings */
+#define MC_CMD_PCIE_TUNE_IN_RXEQ_SET 0x1
+/* enum: Get current TX Driver settings */
+#define MC_CMD_PCIE_TUNE_IN_TXEQ_GET 0x2
+/* enum: Override TX Driver settings */
+#define MC_CMD_PCIE_TUNE_IN_TXEQ_SET 0x3
+/* enum: Start PCIe Serdes Eye diagram plot on a given lane. */
+#define MC_CMD_PCIE_TUNE_IN_START_EYE_PLOT 0x5
+/* enum: Poll PCIe Serdes Eye diagram plot. Returns one row of BER data. The
+ * caller should call this command repeatedly after starting eye plot, until no
+ * more data is returned.
+ */
+#define MC_CMD_PCIE_TUNE_IN_POLL_EYE_PLOT 0x6
+/* Align the arguments to 32 bits */
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_OFST 1
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_LEN 3
+/* Arguments specific to the operation */
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_OFST 4
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_LEN 4
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MINNUM 0
+#define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MAXNUM 62
+
+/* MC_CMD_PCIE_TUNE_OUT msgresponse */
+#define MC_CMD_PCIE_TUNE_OUT_LEN 0
+
+/* MC_CMD_PCIE_TUNE_RXEQ_GET_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
+
+/* MC_CMD_PCIE_TUNE_RXEQ_GET_OUT msgresponse */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMIN 4
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMAX 252
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LEN(num) (0+4*(num))
+/* RXEQ Parameter */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_OFST 0
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LEN 4
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MINNUM 1
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
+/* enum: Attenuation (0-15) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_ATT 0x0
+/* enum: CTLE Boost (0-15) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_BOOST 0x1
+/* enum: DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP1 0x2
+/* enum: DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP2 0x3
+/* enum: DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP3 0x4
+/* enum: DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP4 0x5
+/* enum: DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP5 0x6
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 4
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_0 0x0 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_1 0x1 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_2 0x2 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_3 0x3 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_4 0x4 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_5 0x5 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_6 0x6 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_7 0x7 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL 0x8 /* enum */
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 12
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 12
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
+#define MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
+
+/* MC_CMD_PCIE_TUNE_TXEQ_GET_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
+
+/* MC_CMD_PCIE_TUNE_TXEQ_GET_OUT msgresponse */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMIN 4
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMAX 252
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LEN(num) (0+4*(num))
+/* RXEQ Parameter */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_OFST 0
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LEN 4
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MINNUM 1
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
+/* enum: TxMargin (PIPE) */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXMARGIN 0x0
+/* enum: TxSwing (PIPE) */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXSWING 0x1
+/* enum: De-emphasis coefficient C(-1) (PIPE) */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CM1 0x2
+/* enum: De-emphasis coefficient C(0) (PIPE) */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_C0 0x3
+/* enum: De-emphasis coefficient C(+1) (PIPE) */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CP1 0x4
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 4
+/* Enum values, see field(s): */
+/* MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_LBN 12
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_WIDTH 12
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_LBN 24
+#define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
+
+/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LEN 8
+/* Requested operation */
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_OFST 4
+
+/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT msgresponse */
+#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT_LEN 0
+
+/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN msgrequest */
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_LEN 4
+/* Requested operation */
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
+/* Align the arguments to 32 bits */
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
+
+/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT msgresponse */
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num))
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0
+#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126
+
+
+/***********************************/
+/* MC_CMD_LICENSING
+ * Operations on the NVRAM_PARTITION_TYPE_LICENSE application license partition
+ */
+#define MC_CMD_LICENSING 0xf3
+
+/* MC_CMD_LICENSING_IN msgrequest */
+#define MC_CMD_LICENSING_IN_LEN 4
+/* identifies the type of operation requested */
+#define MC_CMD_LICENSING_IN_OP_OFST 0
+/* enum: re-read and apply licenses after a license key partition update; note
+ * that this operation returns a zero-length response
+ */
+#define MC_CMD_LICENSING_IN_OP_UPDATE_LICENSE 0x0
+/* enum: report counts of installed licenses */
+#define MC_CMD_LICENSING_IN_OP_GET_KEY_STATS 0x1
+
+/* MC_CMD_LICENSING_OUT msgresponse */
+#define MC_CMD_LICENSING_OUT_LEN 28
+/* count of application keys which are valid */
+#define MC_CMD_LICENSING_OUT_VALID_APP_KEYS_OFST 0
+/* sum of UNVERIFIABLE_APP_KEYS + WRONG_NODE_APP_KEYS (for compatibility with
+ * MC_CMD_FC_OP_LICENSE)
+ */
+#define MC_CMD_LICENSING_OUT_INVALID_APP_KEYS_OFST 4
+/* count of application keys which are invalid due to being blacklisted */
+#define MC_CMD_LICENSING_OUT_BLACKLISTED_APP_KEYS_OFST 8
+/* count of application keys which are invalid due to being unverifiable */
+#define MC_CMD_LICENSING_OUT_UNVERIFIABLE_APP_KEYS_OFST 12
+/* count of application keys which are invalid due to being for the wrong node
+ */
+#define MC_CMD_LICENSING_OUT_WRONG_NODE_APP_KEYS_OFST 16
+/* licensing state (for diagnostics; the exact meaning of the bits in this
+ * field are private to the firmware)
+ */
+#define MC_CMD_LICENSING_OUT_LICENSING_STATE_OFST 20
+/* licensing subsystem self-test report (for manftest) */
+#define MC_CMD_LICENSING_OUT_LICENSING_SELF_TEST_OFST 24
+/* enum: licensing subsystem self-test failed */
+#define MC_CMD_LICENSING_OUT_SELF_TEST_FAIL 0x0
+/* enum: licensing subsystem self-test passed */
+#define MC_CMD_LICENSING_OUT_SELF_TEST_PASS 0x1
+
+
+/***********************************/
+/* MC_CMD_MC2MC_PROXY
+ * Execute an arbitrary MCDI command on the slave MC of a dual-core device.
+ * This will fail on a single-core system.
+ */
+#define MC_CMD_MC2MC_PROXY 0xf4
+
+/* MC_CMD_MC2MC_PROXY_IN msgrequest */
+#define MC_CMD_MC2MC_PROXY_IN_LEN 0
+
+/* MC_CMD_MC2MC_PROXY_OUT msgresponse */
+#define MC_CMD_MC2MC_PROXY_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_LICENSED_APP_STATE
+ * Query the state of an individual licensed application. (Note that the actual
+ * state may be invalidated by the MC_CMD_LICENSING OP_UPDATE_LICENSE operation
+ * or a reboot of the MC.)
+ */
+#define MC_CMD_GET_LICENSED_APP_STATE 0xf5
+
+/* MC_CMD_GET_LICENSED_APP_STATE_IN msgrequest */
+#define MC_CMD_GET_LICENSED_APP_STATE_IN_LEN 4
+/* application ID to query (LICENSED_APP_ID_xxx) */
+#define MC_CMD_GET_LICENSED_APP_STATE_IN_APP_ID_OFST 0
+
+/* MC_CMD_GET_LICENSED_APP_STATE_OUT msgresponse */
+#define MC_CMD_GET_LICENSED_APP_STATE_OUT_LEN 4
+/* state of this application */
+#define MC_CMD_GET_LICENSED_APP_STATE_OUT_STATE_OFST 0
+/* enum: no (or invalid) license is present for the application */
+#define MC_CMD_GET_LICENSED_APP_STATE_OUT_NOT_LICENSED 0x0
+/* enum: a valid license is present for the application */
+#define MC_CMD_GET_LICENSED_APP_STATE_OUT_LICENSED 0x1
+
+
+/***********************************/
+/* MC_CMD_LICENSED_APP_OP
+ * Perform an action for an individual licensed application.
+ */
+#define MC_CMD_LICENSED_APP_OP 0xf6
+
+/* MC_CMD_LICENSED_APP_OP_IN msgrequest */
+#define MC_CMD_LICENSED_APP_OP_IN_LENMIN 8
+#define MC_CMD_LICENSED_APP_OP_IN_LENMAX 252
+#define MC_CMD_LICENSED_APP_OP_IN_LEN(num) (8+4*(num))
+/* application ID */
+#define MC_CMD_LICENSED_APP_OP_IN_APP_ID_OFST 0
+/* the type of operation requested */
+#define MC_CMD_LICENSED_APP_OP_IN_OP_OFST 4
+/* enum: validate application */
+#define MC_CMD_LICENSED_APP_OP_IN_OP_VALIDATE 0x0
+/* arguments specific to this particular operation */
+#define MC_CMD_LICENSED_APP_OP_IN_ARGS_OFST 8
+#define MC_CMD_LICENSED_APP_OP_IN_ARGS_LEN 4
+#define MC_CMD_LICENSED_APP_OP_IN_ARGS_MINNUM 0
+#define MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM 61
+
+/* MC_CMD_LICENSED_APP_OP_OUT msgresponse */
+#define MC_CMD_LICENSED_APP_OP_OUT_LENMIN 0
+#define MC_CMD_LICENSED_APP_OP_OUT_LENMAX 252
+#define MC_CMD_LICENSED_APP_OP_OUT_LEN(num) (0+4*(num))
+/* result specific to this particular operation */
+#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_OFST 0
+#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_LEN 4
+#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_MINNUM 0
+#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM 63
+
+/* MC_CMD_LICENSED_APP_OP_VALIDATE_IN msgrequest */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_LEN 72
+/* application ID */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_OFST 0
+/* the type of operation requested */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_OFST 4
+/* validation challenge */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_OFST 8
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_LEN 64
+
+/* MC_CMD_LICENSED_APP_OP_VALIDATE_OUT msgresponse */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_LEN 68
+/* feature expiry (time_t) */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_OFST 0
+/* validation response */
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_OFST 4
+#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_LEN 64
+
+
+/***********************************/
+/* MC_CMD_SET_PORT_SNIFF_CONFIG
+ * Configure port sniffing for the physical port associated with the calling
+ * function. Only a privileged function may change the port sniffing
+ * configuration. A copy of all traffic delivered to the host (non-promiscuous
+ * mode) or all traffic arriving at the port (promiscuous mode) may be
+ * delivered to a specific queue, or a set of queues with RSS.
+ */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG 0xf7
+
+/* MC_CMD_SET_PORT_SNIFF_CONFIG_IN msgrequest */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_LEN 16
+/* configuration flags */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_LBN 1
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_WIDTH 1
+/* receive queue handle (for RSS mode, this is the base queue) */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4
+/* receive mode */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8
+/* enum: receive to just the specified queue */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0
+/* enum: receive to multiple queues using RSS context */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1
+/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note
+ * that these handles should be considered opaque to the host, although a value
+ * of 0xFFFFFFFF is guaranteed never to be a valid handle.
+ */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12
+
+/* MC_CMD_SET_PORT_SNIFF_CONFIG_OUT msgresponse */
+#define MC_CMD_SET_PORT_SNIFF_CONFIG_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_PORT_SNIFF_CONFIG
+ * Obtain the current port sniffing configuration for the physical port
+ * associated with the calling function. Only a privileged function may read
+ * the configuration.
+ */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG 0xf8
+
+/* MC_CMD_GET_PORT_SNIFF_CONFIG_IN msgrequest */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_IN_LEN 0
+
+/* MC_CMD_GET_PORT_SNIFF_CONFIG_OUT msgresponse */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_LEN 16
+/* configuration flags */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_LBN 1
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_WIDTH 1
+/* receiving queue handle (for RSS mode, this is the base queue) */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4
+/* receive mode */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8
+/* enum: receiving to just the specified queue */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0
+/* enum: receiving to multiple queues using RSS context */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1
+/* RSS context (for RX_MODE_RSS) */
+#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12
+
#endif /* MCDI_PCOL_H */
diff --git a/drivers/net/ethernet/sfc/mcdi_phy.c b/drivers/net/ethernet/sfc/mcdi_port.c
index 6c63ab0710a..e5fc4e1574b 100644
--- a/drivers/net/ethernet/sfc/mcdi_phy.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2009-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2009-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -36,7 +36,7 @@ struct efx_mcdi_phy_data {
static int
efx_mcdi_get_phy_cfg(struct efx_nic *efx, struct efx_mcdi_phy_data *cfg)
{
- u8 outbuf[MC_CMD_GET_PHY_CFG_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_CFG_OUT_LEN);
size_t outlen;
int rc;
@@ -78,7 +78,7 @@ static int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities,
u32 flags, u32 loopback_mode,
u32 loopback_speed)
{
- u8 inbuf[MC_CMD_SET_LINK_IN_LEN];
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_LINK_IN_LEN);
int rc;
BUILD_BUG_ON(MC_CMD_SET_LINK_OUT_LEN != 0);
@@ -90,19 +90,12 @@ static int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities,
rc = efx_mcdi_rpc(efx, MC_CMD_SET_LINK, inbuf, sizeof(inbuf),
NULL, 0, NULL);
- if (rc)
- goto fail;
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
return rc;
}
static int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes)
{
- u8 outbuf[MC_CMD_GET_LOOPBACK_MODES_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LOOPBACK_MODES_OUT_LEN);
size_t outlen;
int rc;
@@ -111,12 +104,13 @@ static int efx_mcdi_loopback_modes(struct efx_nic *efx, u64 *loopback_modes)
if (rc)
goto fail;
- if (outlen < MC_CMD_GET_LOOPBACK_MODES_OUT_LEN) {
+ if (outlen < (MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_OFST +
+ MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_LEN)) {
rc = -EIO;
goto fail;
}
- *loopback_modes = MCDI_QWORD(outbuf, GET_LOOPBACK_MODES_SUGGESTED);
+ *loopback_modes = MCDI_QWORD(outbuf, GET_LOOPBACK_MODES_OUT_SUGGESTED);
return 0;
@@ -125,16 +119,16 @@ fail:
return rc;
}
-int efx_mcdi_mdio_read(struct efx_nic *efx, unsigned int bus,
- unsigned int prtad, unsigned int devad, u16 addr,
- u16 *value_out, u32 *status_out)
+static int efx_mcdi_mdio_read(struct net_device *net_dev,
+ int prtad, int devad, u16 addr)
{
- u8 inbuf[MC_CMD_MDIO_READ_IN_LEN];
- u8 outbuf[MC_CMD_MDIO_READ_OUT_LEN];
+ struct efx_nic *efx = netdev_priv(net_dev);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_READ_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_READ_OUT_LEN);
size_t outlen;
int rc;
- MCDI_SET_DWORD(inbuf, MDIO_READ_IN_BUS, bus);
+ MCDI_SET_DWORD(inbuf, MDIO_READ_IN_BUS, efx->mdio_bus);
MCDI_SET_DWORD(inbuf, MDIO_READ_IN_PRTAD, prtad);
MCDI_SET_DWORD(inbuf, MDIO_READ_IN_DEVAD, devad);
MCDI_SET_DWORD(inbuf, MDIO_READ_IN_ADDR, addr);
@@ -142,27 +136,25 @@ int efx_mcdi_mdio_read(struct efx_nic *efx, unsigned int bus,
rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_READ, inbuf, sizeof(inbuf),
outbuf, sizeof(outbuf), &outlen);
if (rc)
- goto fail;
+ return rc;
- *value_out = (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE);
- *status_out = MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS);
- return 0;
+ if (MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS) !=
+ MC_CMD_MDIO_STATUS_GOOD)
+ return -EIO;
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
+ return (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE);
}
-int efx_mcdi_mdio_write(struct efx_nic *efx, unsigned int bus,
- unsigned int prtad, unsigned int devad, u16 addr,
- u16 value, u32 *status_out)
+static int efx_mcdi_mdio_write(struct net_device *net_dev,
+ int prtad, int devad, u16 addr, u16 value)
{
- u8 inbuf[MC_CMD_MDIO_WRITE_IN_LEN];
- u8 outbuf[MC_CMD_MDIO_WRITE_OUT_LEN];
+ struct efx_nic *efx = netdev_priv(net_dev);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_WRITE_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_WRITE_OUT_LEN);
size_t outlen;
int rc;
- MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_BUS, bus);
+ MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_BUS, efx->mdio_bus);
MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_PRTAD, prtad);
MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_DEVAD, devad);
MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_ADDR, addr);
@@ -171,14 +163,13 @@ int efx_mcdi_mdio_write(struct efx_nic *efx, unsigned int bus,
rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_WRITE, inbuf, sizeof(inbuf),
outbuf, sizeof(outbuf), &outlen);
if (rc)
- goto fail;
+ return rc;
- *status_out = MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS);
- return 0;
+ if (MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS) !=
+ MC_CMD_MDIO_STATUS_GOOD)
+ return -EIO;
-fail:
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc);
- return rc;
+ return 0;
}
static u32 mcdi_to_ethtool_cap(u32 media, u32 cap)
@@ -264,22 +255,22 @@ static u32 efx_get_mcdi_phy_flags(struct efx_nic *efx)
/* TODO: Advertise the capabilities supported by this PHY */
supported = 0;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_TXDIS_LBN))
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_TXDIS_LBN))
supported |= PHY_MODE_TX_DISABLED;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_LOWPOWER_LBN))
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_LOWPOWER_LBN))
supported |= PHY_MODE_LOW_POWER;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_POWEROFF_LBN))
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_POWEROFF_LBN))
supported |= PHY_MODE_OFF;
mode = efx->phy_mode & supported;
flags = 0;
if (mode & PHY_MODE_TX_DISABLED)
- flags |= (1 << MC_CMD_SET_LINK_TXDIS_LBN);
+ flags |= (1 << MC_CMD_SET_LINK_IN_TXDIS_LBN);
if (mode & PHY_MODE_LOW_POWER)
- flags |= (1 << MC_CMD_SET_LINK_LOWPOWER_LBN);
+ flags |= (1 << MC_CMD_SET_LINK_IN_LOWPOWER_LBN);
if (mode & PHY_MODE_OFF)
- flags |= (1 << MC_CMD_SET_LINK_POWEROFF_LBN);
+ flags |= (1 << MC_CMD_SET_LINK_IN_POWEROFF_LBN);
return flags;
}
@@ -304,10 +295,37 @@ static u32 mcdi_to_ethtool_media(u32 media)
}
}
+static void efx_mcdi_phy_decode_link(struct efx_nic *efx,
+ struct efx_link_state *link_state,
+ u32 speed, u32 flags, u32 fcntl)
+{
+ switch (fcntl) {
+ case MC_CMD_FCNTL_AUTO:
+ WARN_ON(1); /* This is not a link mode */
+ link_state->fc = EFX_FC_AUTO | EFX_FC_TX | EFX_FC_RX;
+ break;
+ case MC_CMD_FCNTL_BIDIR:
+ link_state->fc = EFX_FC_TX | EFX_FC_RX;
+ break;
+ case MC_CMD_FCNTL_RESPOND:
+ link_state->fc = EFX_FC_RX;
+ break;
+ default:
+ WARN_ON(1);
+ case MC_CMD_FCNTL_OFF:
+ link_state->fc = 0;
+ break;
+ }
+
+ link_state->up = !!(flags & (1 << MC_CMD_GET_LINK_OUT_LINK_UP_LBN));
+ link_state->fd = !!(flags & (1 << MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN));
+ link_state->speed = speed;
+}
+
static int efx_mcdi_phy_probe(struct efx_nic *efx)
{
struct efx_mcdi_phy_data *phy_data;
- u8 outbuf[MC_CMD_GET_LINK_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
u32 caps;
int rc;
@@ -403,7 +421,7 @@ fail:
return rc;
}
-int efx_mcdi_phy_reconfigure(struct efx_nic *efx)
+int efx_mcdi_port_reconfigure(struct efx_nic *efx)
{
struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
u32 caps = (efx->link_advertising ?
@@ -414,37 +432,10 @@ int efx_mcdi_phy_reconfigure(struct efx_nic *efx)
efx->loopback_mode, 0);
}
-void efx_mcdi_phy_decode_link(struct efx_nic *efx,
- struct efx_link_state *link_state,
- u32 speed, u32 flags, u32 fcntl)
-{
- switch (fcntl) {
- case MC_CMD_FCNTL_AUTO:
- WARN_ON(1); /* This is not a link mode */
- link_state->fc = EFX_FC_AUTO | EFX_FC_TX | EFX_FC_RX;
- break;
- case MC_CMD_FCNTL_BIDIR:
- link_state->fc = EFX_FC_TX | EFX_FC_RX;
- break;
- case MC_CMD_FCNTL_RESPOND:
- link_state->fc = EFX_FC_RX;
- break;
- default:
- WARN_ON(1);
- case MC_CMD_FCNTL_OFF:
- link_state->fc = 0;
- break;
- }
-
- link_state->up = !!(flags & (1 << MC_CMD_GET_LINK_LINK_UP_LBN));
- link_state->fd = !!(flags & (1 << MC_CMD_GET_LINK_FULL_DUPLEX_LBN));
- link_state->speed = speed;
-}
-
/* Verify that the forced flow control settings (!EFX_FC_AUTO) are
* supported by the link partner. Warn the user if this isn't the case
*/
-void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa)
+static void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa)
{
struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
u32 rmtadv;
@@ -472,7 +463,7 @@ void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa)
static bool efx_mcdi_phy_poll(struct efx_nic *efx)
{
struct efx_link_state old_state = efx->link_state;
- u8 outbuf[MC_CMD_GET_LINK_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
int rc;
WARN_ON(!mutex_is_locked(&efx->mac_lock));
@@ -481,17 +472,14 @@ static bool efx_mcdi_phy_poll(struct efx_nic *efx)
rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
outbuf, sizeof(outbuf), NULL);
- if (rc) {
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n",
- __func__, rc);
+ if (rc)
efx->link_state.up = false;
- } else {
+ else
efx_mcdi_phy_decode_link(
efx, &efx->link_state,
MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED),
MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS),
MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL));
- }
return !efx_link_state_equal(&efx->link_state, &old_state);
}
@@ -507,7 +495,7 @@ static void efx_mcdi_phy_remove(struct efx_nic *efx)
static void efx_mcdi_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
{
struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
- u8 outbuf[MC_CMD_GET_LINK_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
int rc;
ecmd->supported =
@@ -525,11 +513,8 @@ static void efx_mcdi_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *e
BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
outbuf, sizeof(outbuf), NULL);
- if (rc) {
- netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n",
- __func__, rc);
+ if (rc)
return;
- }
ecmd->lp_advertising =
mcdi_to_ethtool_cap(phy_cfg->media,
MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP));
@@ -550,6 +535,7 @@ static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ec
case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break;
case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break;
case 10000: caps = 1 << MC_CMD_PHY_CAP_10000FDX_LBN; break;
+ case 40000: caps = 1 << MC_CMD_PHY_CAP_40000FDX_LBN; break;
default: return -EINVAL;
}
} else {
@@ -579,7 +565,7 @@ static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ec
static int efx_mcdi_phy_test_alive(struct efx_nic *efx)
{
- u8 outbuf[MC_CMD_GET_PHY_STATE_OUT_LEN];
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_STATE_OUT_LEN);
size_t outlen;
int rc;
@@ -592,7 +578,7 @@ static int efx_mcdi_phy_test_alive(struct efx_nic *efx)
if (outlen < MC_CMD_GET_PHY_STATE_OUT_LEN)
return -EIO;
- if (MCDI_DWORD(outbuf, GET_PHY_STATE_STATE) != MC_CMD_PHY_STATE_OK)
+ if (MCDI_DWORD(outbuf, GET_PHY_STATE_OUT_STATE) != MC_CMD_PHY_STATE_OK)
return -EINVAL;
return 0;
@@ -615,17 +601,15 @@ static int efx_mcdi_bist(struct efx_nic *efx, unsigned int bist_mode,
unsigned int retry, i, count = 0;
size_t outlen;
u32 status;
- u8 *buf, *ptr;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_SFT9001_LEN);
+ u8 *ptr;
int rc;
- buf = kzalloc(0x100, GFP_KERNEL);
- if (buf == NULL)
- return -ENOMEM;
-
BUILD_BUG_ON(MC_CMD_START_BIST_OUT_LEN != 0);
- MCDI_SET_DWORD(buf, START_BIST_IN_TYPE, bist_mode);
- rc = efx_mcdi_rpc(efx, MC_CMD_START_BIST, buf, MC_CMD_START_BIST_IN_LEN,
- NULL, 0, NULL);
+ MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_mode);
+ rc = efx_mcdi_rpc(efx, MC_CMD_START_BIST,
+ inbuf, MC_CMD_START_BIST_IN_LEN, NULL, 0, NULL);
if (rc)
goto out;
@@ -633,11 +617,11 @@ static int efx_mcdi_bist(struct efx_nic *efx, unsigned int bist_mode,
for (retry = 0; retry < 100; ++retry) {
BUILD_BUG_ON(MC_CMD_POLL_BIST_IN_LEN != 0);
rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0,
- buf, 0x100, &outlen);
+ outbuf, sizeof(outbuf), &outlen);
if (rc)
goto out;
- status = MCDI_DWORD(buf, POLL_BIST_OUT_RESULT);
+ status = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT);
if (status != MC_CMD_POLL_BIST_RUNNING)
goto finished;
@@ -654,7 +638,7 @@ finished:
if (efx->phy_type == PHY_TYPE_SFT9001B &&
(bist_mode == MC_CMD_PHY_BIST_CABLE_SHORT ||
bist_mode == MC_CMD_PHY_BIST_CABLE_LONG)) {
- ptr = MCDI_PTR(buf, POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A);
+ ptr = MCDI_PTR(outbuf, POLL_BIST_OUT_SFT9001_CABLE_LENGTH_A);
if (status == MC_CMD_POLL_BIST_PASSED &&
outlen >= MC_CMD_POLL_BIST_OUT_SFT9001_LEN) {
for (i = 0; i < 8; i++) {
@@ -668,8 +652,6 @@ finished:
rc = count;
out:
- kfree(buf);
-
return rc;
}
@@ -680,7 +662,7 @@ static int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results,
u32 mode;
int rc;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_LBN)) {
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) {
rc = efx_mcdi_bist(efx, MC_CMD_PHY_BIST, results);
if (rc < 0)
return rc;
@@ -691,15 +673,15 @@ static int efx_mcdi_phy_run_tests(struct efx_nic *efx, int *results,
/* If we support both LONG and SHORT, then run each in response to
* break or not. Otherwise, run the one we support */
mode = 0;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_LBN)) {
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN)) {
if ((flags & ETH_TEST_FL_OFFLINE) &&
(phy_cfg->flags &
- (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN)))
+ (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN)))
mode = MC_CMD_PHY_BIST_CABLE_LONG;
else
mode = MC_CMD_PHY_BIST_CABLE_SHORT;
} else if (phy_cfg->flags &
- (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN))
+ (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))
mode = MC_CMD_PHY_BIST_CABLE_LONG;
if (mode != 0) {
@@ -717,14 +699,14 @@ static const char *efx_mcdi_phy_test_name(struct efx_nic *efx,
{
struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
- if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_BIST_LBN)) {
+ if (phy_cfg->flags & (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_LBN)) {
if (index == 0)
return "bist";
--index;
}
- if (phy_cfg->flags & ((1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_SHORT_LBN) |
- (1 << MC_CMD_GET_PHY_CFG_BIST_CABLE_LONG_LBN))) {
+ if (phy_cfg->flags & ((1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_SHORT_LBN) |
+ (1 << MC_CMD_GET_PHY_CFG_OUT_BIST_CABLE_LONG_LBN))) {
if (index == 0)
return "cable";
--index;
@@ -739,10 +721,83 @@ static const char *efx_mcdi_phy_test_name(struct efx_nic *efx,
return NULL;
}
-const struct efx_phy_operations efx_mcdi_phy_ops = {
+#define SFP_PAGE_SIZE 128
+#define SFP_NUM_PAGES 2
+static int efx_mcdi_phy_get_module_eeprom(struct efx_nic *efx,
+ struct ethtool_eeprom *ee, u8 *data)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX);
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_PHY_MEDIA_INFO_IN_LEN);
+ size_t outlen;
+ int rc;
+ unsigned int payload_len;
+ unsigned int space_remaining = ee->len;
+ unsigned int page;
+ unsigned int page_off;
+ unsigned int to_copy;
+ u8 *user_data = data;
+
+ BUILD_BUG_ON(SFP_PAGE_SIZE * SFP_NUM_PAGES != ETH_MODULE_SFF_8079_LEN);
+
+ page_off = ee->offset % SFP_PAGE_SIZE;
+ page = ee->offset / SFP_PAGE_SIZE;
+
+ while (space_remaining && (page < SFP_NUM_PAGES)) {
+ MCDI_SET_DWORD(inbuf, GET_PHY_MEDIA_INFO_IN_PAGE, page);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PHY_MEDIA_INFO,
+ inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf),
+ &outlen);
+ if (rc)
+ return rc;
+
+ if (outlen < (MC_CMD_GET_PHY_MEDIA_INFO_OUT_DATA_OFST +
+ SFP_PAGE_SIZE))
+ return -EIO;
+
+ payload_len = MCDI_DWORD(outbuf,
+ GET_PHY_MEDIA_INFO_OUT_DATALEN);
+ if (payload_len != SFP_PAGE_SIZE)
+ return -EIO;
+
+ /* Copy as much as we can into data */
+ payload_len -= page_off;
+ to_copy = (space_remaining < payload_len) ?
+ space_remaining : payload_len;
+
+ memcpy(user_data,
+ MCDI_PTR(outbuf, GET_PHY_MEDIA_INFO_OUT_DATA) + page_off,
+ to_copy);
+
+ space_remaining -= to_copy;
+ user_data += to_copy;
+ page_off = 0;
+ page++;
+ }
+
+ return 0;
+}
+
+static int efx_mcdi_phy_get_module_info(struct efx_nic *efx,
+ struct ethtool_modinfo *modinfo)
+{
+ struct efx_mcdi_phy_data *phy_cfg = efx->phy_data;
+
+ switch (phy_cfg->media) {
+ case MC_CMD_MEDIA_SFP_PLUS:
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static const struct efx_phy_operations efx_mcdi_phy_ops = {
.probe = efx_mcdi_phy_probe,
- .init = efx_port_dummy_op_int,
- .reconfigure = efx_mcdi_phy_reconfigure,
+ .init = efx_port_dummy_op_int,
+ .reconfigure = efx_mcdi_port_reconfigure,
.poll = efx_mcdi_phy_poll,
.fini = efx_port_dummy_op_void,
.remove = efx_mcdi_phy_remove,
@@ -751,4 +806,219 @@ const struct efx_phy_operations efx_mcdi_phy_ops = {
.test_alive = efx_mcdi_phy_test_alive,
.run_tests = efx_mcdi_phy_run_tests,
.test_name = efx_mcdi_phy_test_name,
+ .get_module_eeprom = efx_mcdi_phy_get_module_eeprom,
+ .get_module_info = efx_mcdi_phy_get_module_info,
+};
+
+u32 efx_mcdi_phy_get_caps(struct efx_nic *efx)
+{
+ struct efx_mcdi_phy_data *phy_data = efx->phy_data;
+
+ return phy_data->supported_cap;
+}
+
+static unsigned int efx_mcdi_event_link_speed[] = {
+ [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100,
+ [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000,
+ [MCDI_EVENT_LINKCHANGE_SPEED_40G] = 40000,
+};
+
+void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev)
+{
+ u32 flags, fcntl, speed, lpa;
+
+ speed = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_SPEED);
+ EFX_BUG_ON_PARANOID(speed >= ARRAY_SIZE(efx_mcdi_event_link_speed));
+ speed = efx_mcdi_event_link_speed[speed];
+
+ flags = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LINK_FLAGS);
+ fcntl = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_FCNTL);
+ lpa = EFX_QWORD_FIELD(*ev, MCDI_EVENT_LINKCHANGE_LP_CAP);
+
+ /* efx->link_state is only modified by efx_mcdi_phy_get_link(),
+ * which is only run after flushing the event queues. Therefore, it
+ * is safe to modify the link state outside of the mac_lock here.
+ */
+ efx_mcdi_phy_decode_link(efx, &efx->link_state, speed, flags, fcntl);
+
+ efx_mcdi_phy_check_fcntl(efx, lpa);
+
+ efx_link_status_changed(efx);
+}
+
+int efx_mcdi_set_mac(struct efx_nic *efx)
+{
+ u32 fcntl;
+ MCDI_DECLARE_BUF(cmdbytes, MC_CMD_SET_MAC_IN_LEN);
+
+ BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0);
+
+ ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR),
+ efx->net_dev->dev_addr);
+
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU,
+ EFX_MAX_FRAME_LEN(efx->net_dev->mtu));
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_DRAIN, 0);
+
+ /* Set simple MAC filter for Siena */
+ MCDI_POPULATE_DWORD_1(cmdbytes, SET_MAC_IN_REJECT,
+ SET_MAC_IN_REJECT_UNCST, efx->unicast_filter);
+
+ switch (efx->wanted_fc) {
+ case EFX_FC_RX | EFX_FC_TX:
+ fcntl = MC_CMD_FCNTL_BIDIR;
+ break;
+ case EFX_FC_RX:
+ fcntl = MC_CMD_FCNTL_RESPOND;
+ break;
+ default:
+ fcntl = MC_CMD_FCNTL_OFF;
+ break;
+ }
+ if (efx->wanted_fc & EFX_FC_AUTO)
+ fcntl = MC_CMD_FCNTL_AUTO;
+ if (efx->fc_disable)
+ fcntl = MC_CMD_FCNTL_OFF;
+
+ MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_FCNTL, fcntl);
+
+ return efx_mcdi_rpc(efx, MC_CMD_SET_MAC, cmdbytes, sizeof(cmdbytes),
+ NULL, 0, NULL);
+}
+
+bool efx_mcdi_mac_check_fault(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_LINK_OUT_LEN);
+ size_t outlength;
+ int rc;
+
+ BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0,
+ outbuf, sizeof(outbuf), &outlength);
+ if (rc)
+ return true;
+
+ return MCDI_DWORD(outbuf, GET_LINK_OUT_MAC_FAULT) != 0;
+}
+
+enum efx_stats_action {
+ EFX_STATS_ENABLE,
+ EFX_STATS_DISABLE,
+ EFX_STATS_PULL,
};
+
+static int efx_mcdi_mac_stats(struct efx_nic *efx,
+ enum efx_stats_action action, int clear)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN);
+ int rc;
+ int change = action == EFX_STATS_PULL ? 0 : 1;
+ int enable = action == EFX_STATS_ENABLE ? 1 : 0;
+ int period = action == EFX_STATS_ENABLE ? 1000 : 0;
+ dma_addr_t dma_addr = efx->stats_buffer.dma_addr;
+ u32 dma_len = action != EFX_STATS_DISABLE ?
+ MC_CMD_MAC_NSTATS * sizeof(u64) : 0;
+
+ BUILD_BUG_ON(MC_CMD_MAC_STATS_OUT_DMA_LEN != 0);
+
+ MCDI_SET_QWORD(inbuf, MAC_STATS_IN_DMA_ADDR, dma_addr);
+ MCDI_POPULATE_DWORD_7(inbuf, MAC_STATS_IN_CMD,
+ MAC_STATS_IN_DMA, !!enable,
+ MAC_STATS_IN_CLEAR, clear,
+ MAC_STATS_IN_PERIODIC_CHANGE, change,
+ MAC_STATS_IN_PERIODIC_ENABLE, enable,
+ MAC_STATS_IN_PERIODIC_CLEAR, 0,
+ MAC_STATS_IN_PERIODIC_NOEVENT, 1,
+ MAC_STATS_IN_PERIOD_MS, period);
+ MCDI_SET_DWORD(inbuf, MAC_STATS_IN_DMA_LEN, dma_len);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+ return rc;
+}
+
+void efx_mcdi_mac_start_stats(struct efx_nic *efx)
+{
+ __le64 *dma_stats = efx->stats_buffer.addr;
+
+ dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID;
+
+ efx_mcdi_mac_stats(efx, EFX_STATS_ENABLE, 0);
+}
+
+void efx_mcdi_mac_stop_stats(struct efx_nic *efx)
+{
+ efx_mcdi_mac_stats(efx, EFX_STATS_DISABLE, 0);
+}
+
+#define EFX_MAC_STATS_WAIT_US 100
+#define EFX_MAC_STATS_WAIT_ATTEMPTS 10
+
+void efx_mcdi_mac_pull_stats(struct efx_nic *efx)
+{
+ __le64 *dma_stats = efx->stats_buffer.addr;
+ int attempts = EFX_MAC_STATS_WAIT_ATTEMPTS;
+
+ dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID;
+ efx_mcdi_mac_stats(efx, EFX_STATS_PULL, 0);
+
+ while (dma_stats[MC_CMD_MAC_GENERATION_END] ==
+ EFX_MC_STATS_GENERATION_INVALID &&
+ attempts-- != 0)
+ udelay(EFX_MAC_STATS_WAIT_US);
+}
+
+int efx_mcdi_port_probe(struct efx_nic *efx)
+{
+ int rc;
+
+ /* Hook in PHY operations table */
+ efx->phy_op = &efx_mcdi_phy_ops;
+
+ /* Set up MDIO structure for PHY */
+ efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
+ efx->mdio.mdio_read = efx_mcdi_mdio_read;
+ efx->mdio.mdio_write = efx_mcdi_mdio_write;
+
+ /* Fill out MDIO structure, loopback modes, and initial link state */
+ rc = efx->phy_op->probe(efx);
+ if (rc != 0)
+ return rc;
+
+ /* Allocate buffer for stats */
+ rc = efx_nic_alloc_buffer(efx, &efx->stats_buffer,
+ MC_CMD_MAC_NSTATS * sizeof(u64), GFP_KERNEL);
+ if (rc)
+ return rc;
+ netif_dbg(efx, probe, efx->net_dev,
+ "stats buffer at %llx (virt %p phys %llx)\n",
+ (u64)efx->stats_buffer.dma_addr,
+ efx->stats_buffer.addr,
+ (u64)virt_to_phys(efx->stats_buffer.addr));
+
+ efx_mcdi_mac_stats(efx, EFX_STATS_DISABLE, 1);
+
+ return 0;
+}
+
+void efx_mcdi_port_remove(struct efx_nic *efx)
+{
+ efx->phy_op->remove(efx);
+ efx_nic_free_buffer(efx, &efx->stats_buffer);
+}
+
+/* Get physical port number (EF10 only; on Siena it is same as PF number) */
+int efx_mcdi_port_get_number(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_PORT_ASSIGNMENT_OUT_LEN);
+ int rc;
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_GET_PORT_ASSIGNMENT, NULL, 0,
+ outbuf, sizeof(outbuf), NULL);
+ if (rc)
+ return rc;
+
+ return MCDI_DWORD(outbuf, GET_PORT_ASSIGNMENT_OUT_PORT);
+}
diff --git a/drivers/net/ethernet/sfc/mdio_10g.c b/drivers/net/ethernet/sfc/mdio_10g.c
index 7ab385c8136..8ff954c59ef 100644
--- a/drivers/net/ethernet/sfc/mdio_10g.c
+++ b/drivers/net/ethernet/sfc/mdio_10g.c
@@ -1,5 +1,5 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2006-2011 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -228,7 +228,7 @@ void efx_mdio_set_mmds_lpower(struct efx_nic *efx,
/**
* efx_mdio_set_settings - Set (some of) the PHY settings over MDIO.
* @efx: Efx NIC
- * @ecmd: New settings
+ * @ecmd: New settings
*/
int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd)
{
diff --git a/drivers/net/ethernet/sfc/mdio_10g.h b/drivers/net/ethernet/sfc/mdio_10g.h
index a97dbbd2de9..4a2dc4c281b 100644
--- a/drivers/net/ethernet/sfc/mdio_10g.h
+++ b/drivers/net/ethernet/sfc/mdio_10g.h
@@ -1,5 +1,5 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2006-2011 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -20,7 +20,7 @@
static inline unsigned efx_mdio_id_rev(u32 id) { return id & 0xf; }
static inline unsigned efx_mdio_id_model(u32 id) { return (id >> 4) & 0x3f; }
-extern unsigned efx_mdio_id_oui(u32 id);
+unsigned efx_mdio_id_oui(u32 id);
static inline int efx_mdio_read(struct efx_nic *efx, int devad, int addr)
{
@@ -56,7 +56,7 @@ static inline bool efx_mdio_phyxgxs_lane_sync(struct efx_nic *efx)
return sync;
}
-extern const char *efx_mdio_mmd_name(int mmd);
+const char *efx_mdio_mmd_name(int mmd);
/*
* Reset a specific MMD and wait for reset to clear.
@@ -64,30 +64,29 @@ extern const char *efx_mdio_mmd_name(int mmd);
*
* This function will sleep
*/
-extern int efx_mdio_reset_mmd(struct efx_nic *efx, int mmd,
- int spins, int spintime);
+int efx_mdio_reset_mmd(struct efx_nic *efx, int mmd, int spins, int spintime);
/* As efx_mdio_check_mmd but for multiple MMDs */
int efx_mdio_check_mmds(struct efx_nic *efx, unsigned int mmd_mask);
/* Check the link status of specified mmds in bit mask */
-extern bool efx_mdio_links_ok(struct efx_nic *efx, unsigned int mmd_mask);
+bool efx_mdio_links_ok(struct efx_nic *efx, unsigned int mmd_mask);
/* Generic transmit disable support though PMAPMD */
-extern void efx_mdio_transmit_disable(struct efx_nic *efx);
+void efx_mdio_transmit_disable(struct efx_nic *efx);
/* Generic part of reconfigure: set/clear loopback bits */
-extern void efx_mdio_phy_reconfigure(struct efx_nic *efx);
+void efx_mdio_phy_reconfigure(struct efx_nic *efx);
/* Set the power state of the specified MMDs */
-extern void efx_mdio_set_mmds_lpower(struct efx_nic *efx,
- int low_power, unsigned int mmd_mask);
+void efx_mdio_set_mmds_lpower(struct efx_nic *efx, int low_power,
+ unsigned int mmd_mask);
/* Set (some of) the PHY settings over MDIO */
-extern int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd);
+int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd);
/* Push advertising flags and restart autonegotiation */
-extern void efx_mdio_an_reconfigure(struct efx_nic *efx);
+void efx_mdio_an_reconfigure(struct efx_nic *efx);
/* Get pause parameters from AN if available (otherwise return
* requested pause parameters)
@@ -95,8 +94,7 @@ extern void efx_mdio_an_reconfigure(struct efx_nic *efx);
u8 efx_mdio_get_pause(struct efx_nic *efx);
/* Wait for specified MMDs to exit reset within a timeout */
-extern int efx_mdio_wait_reset_mmds(struct efx_nic *efx,
- unsigned int mmd_mask);
+int efx_mdio_wait_reset_mmds(struct efx_nic *efx, unsigned int mmd_mask);
/* Set or clear flag, debouncing */
static inline void
@@ -107,6 +105,6 @@ efx_mdio_set_flag(struct efx_nic *efx, int devad, int addr,
}
/* Liveness self-test for MDIO PHYs */
-extern int efx_mdio_test_alive(struct efx_nic *efx);
+int efx_mdio_test_alive(struct efx_nic *efx);
#endif /* EFX_MDIO_10G_H */
diff --git a/drivers/net/ethernet/sfc/mtd.c b/drivers/net/ethernet/sfc/mtd.c
index bc9dcd6b30d..a77a8bd2dd7 100644
--- a/drivers/net/ethernet/sfc/mtd.c
+++ b/drivers/net/ethernet/sfc/mtd.c
@@ -1,199 +1,37 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
* by the Free Software Foundation, incorporated herein by reference.
*/
-#include <linux/bitops.h>
#include <linux/module.h>
#include <linux/mtd/mtd.h>
-#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/rtnetlink.h>
#include "net_driver.h"
-#include "spi.h"
#include "efx.h"
-#include "nic.h"
-#include "mcdi.h"
-#include "mcdi_pcol.h"
-
-#define EFX_SPI_VERIFY_BUF_LEN 16
-
-struct efx_mtd_partition {
- struct mtd_info mtd;
- union {
- struct {
- bool updating;
- u8 nvram_type;
- u16 fw_subtype;
- } mcdi;
- size_t offset;
- };
- const char *type_name;
- char name[IFNAMSIZ + 20];
-};
-
-struct efx_mtd_ops {
- int (*read)(struct mtd_info *mtd, loff_t start, size_t len,
- size_t *retlen, u8 *buffer);
- int (*erase)(struct mtd_info *mtd, loff_t start, size_t len);
- int (*write)(struct mtd_info *mtd, loff_t start, size_t len,
- size_t *retlen, const u8 *buffer);
- int (*sync)(struct mtd_info *mtd);
-};
-
-struct efx_mtd {
- struct list_head node;
- struct efx_nic *efx;
- const struct efx_spi_device *spi;
- const char *name;
- const struct efx_mtd_ops *ops;
- size_t n_parts;
- struct efx_mtd_partition part[0];
-};
-
-#define efx_for_each_partition(part, efx_mtd) \
- for ((part) = &(efx_mtd)->part[0]; \
- (part) != &(efx_mtd)->part[(efx_mtd)->n_parts]; \
- (part)++)
#define to_efx_mtd_partition(mtd) \
container_of(mtd, struct efx_mtd_partition, mtd)
-static int falcon_mtd_probe(struct efx_nic *efx);
-static int siena_mtd_probe(struct efx_nic *efx);
-
-/* SPI utilities */
-
-static int
-efx_spi_slow_wait(struct efx_mtd_partition *part, bool uninterruptible)
-{
- struct efx_mtd *efx_mtd = part->mtd.priv;
- const struct efx_spi_device *spi = efx_mtd->spi;
- struct efx_nic *efx = efx_mtd->efx;
- u8 status;
- int rc, i;
-
- /* Wait up to 4s for flash/EEPROM to finish a slow operation. */
- for (i = 0; i < 40; i++) {
- __set_current_state(uninterruptible ?
- TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE);
- schedule_timeout(HZ / 10);
- rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
- &status, sizeof(status));
- if (rc)
- return rc;
- if (!(status & SPI_STATUS_NRDY))
- return 0;
- if (signal_pending(current))
- return -EINTR;
- }
- pr_err("%s: timed out waiting for %s\n", part->name, efx_mtd->name);
- return -ETIMEDOUT;
-}
-
-static int
-efx_spi_unlock(struct efx_nic *efx, const struct efx_spi_device *spi)
-{
- const u8 unlock_mask = (SPI_STATUS_BP2 | SPI_STATUS_BP1 |
- SPI_STATUS_BP0);
- u8 status;
- int rc;
-
- rc = falcon_spi_cmd(efx, spi, SPI_RDSR, -1, NULL,
- &status, sizeof(status));
- if (rc)
- return rc;
-
- if (!(status & unlock_mask))
- return 0; /* already unlocked */
-
- rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0);
- if (rc)
- return rc;
- rc = falcon_spi_cmd(efx, spi, SPI_SST_EWSR, -1, NULL, NULL, 0);
- if (rc)
- return rc;
-
- status &= ~unlock_mask;
- rc = falcon_spi_cmd(efx, spi, SPI_WRSR, -1, &status,
- NULL, sizeof(status));
- if (rc)
- return rc;
- rc = falcon_spi_wait_write(efx, spi);
- if (rc)
- return rc;
-
- return 0;
-}
-
-static int
-efx_spi_erase(struct efx_mtd_partition *part, loff_t start, size_t len)
-{
- struct efx_mtd *efx_mtd = part->mtd.priv;
- const struct efx_spi_device *spi = efx_mtd->spi;
- struct efx_nic *efx = efx_mtd->efx;
- unsigned pos, block_len;
- u8 empty[EFX_SPI_VERIFY_BUF_LEN];
- u8 buffer[EFX_SPI_VERIFY_BUF_LEN];
- int rc;
-
- if (len != spi->erase_size)
- return -EINVAL;
-
- if (spi->erase_command == 0)
- return -EOPNOTSUPP;
-
- rc = efx_spi_unlock(efx, spi);
- if (rc)
- return rc;
- rc = falcon_spi_cmd(efx, spi, SPI_WREN, -1, NULL, NULL, 0);
- if (rc)
- return rc;
- rc = falcon_spi_cmd(efx, spi, spi->erase_command, start, NULL,
- NULL, 0);
- if (rc)
- return rc;
- rc = efx_spi_slow_wait(part, false);
-
- /* Verify the entire region has been wiped */
- memset(empty, 0xff, sizeof(empty));
- for (pos = 0; pos < len; pos += block_len) {
- block_len = min(len - pos, sizeof(buffer));
- rc = falcon_spi_read(efx, spi, start + pos, block_len,
- NULL, buffer);
- if (rc)
- return rc;
- if (memcmp(empty, buffer, block_len))
- return -EIO;
-
- /* Avoid locking up the system */
- cond_resched();
- if (signal_pending(current))
- return -EINTR;
- }
-
- return rc;
-}
-
/* MTD interface */
static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase)
{
- struct efx_mtd *efx_mtd = mtd->priv;
+ struct efx_nic *efx = mtd->priv;
int rc;
- rc = efx_mtd->ops->erase(mtd, erase->addr, erase->len);
+ rc = efx->type->mtd_erase(mtd, erase->addr, erase->len);
if (rc == 0) {
erase->state = MTD_ERASE_DONE;
} else {
erase->state = MTD_ERASE_FAILED;
- erase->fail_addr = 0xffffffff;
+ erase->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
}
mtd_erase_callback(erase);
return rc;
@@ -202,13 +40,13 @@ static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase)
static void efx_mtd_sync(struct mtd_info *mtd)
{
struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
+ struct efx_nic *efx = mtd->priv;
int rc;
- rc = efx_mtd->ops->sync(mtd);
+ rc = efx->type->mtd_sync(mtd);
if (rc)
pr_err("%s: %s sync failed (%d)\n",
- part->name, efx_mtd->name, rc);
+ part->name, part->dev_type_name, rc);
}
static void efx_mtd_remove_partition(struct efx_mtd_partition *part)
@@ -222,472 +60,74 @@ static void efx_mtd_remove_partition(struct efx_mtd_partition *part)
ssleep(1);
}
WARN_ON(rc);
+ list_del(&part->node);
}
-static void efx_mtd_remove_device(struct efx_mtd *efx_mtd)
-{
- struct efx_mtd_partition *part;
-
- efx_for_each_partition(part, efx_mtd)
- efx_mtd_remove_partition(part);
- list_del(&efx_mtd->node);
- kfree(efx_mtd);
-}
-
-static void efx_mtd_rename_device(struct efx_mtd *efx_mtd)
-{
- struct efx_mtd_partition *part;
-
- efx_for_each_partition(part, efx_mtd)
- if (efx_nic_rev(efx_mtd->efx) >= EFX_REV_SIENA_A0)
- snprintf(part->name, sizeof(part->name),
- "%s %s:%02x", efx_mtd->efx->name,
- part->type_name, part->mcdi.fw_subtype);
- else
- snprintf(part->name, sizeof(part->name),
- "%s %s", efx_mtd->efx->name,
- part->type_name);
-}
-
-static int efx_mtd_probe_device(struct efx_nic *efx, struct efx_mtd *efx_mtd)
+int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts,
+ size_t n_parts, size_t sizeof_part)
{
struct efx_mtd_partition *part;
+ size_t i;
- efx_mtd->efx = efx;
+ for (i = 0; i < n_parts; i++) {
+ part = (struct efx_mtd_partition *)((char *)parts +
+ i * sizeof_part);
- efx_mtd_rename_device(efx_mtd);
-
- efx_for_each_partition(part, efx_mtd) {
part->mtd.writesize = 1;
part->mtd.owner = THIS_MODULE;
- part->mtd.priv = efx_mtd;
+ part->mtd.priv = efx;
part->mtd.name = part->name;
- part->mtd.erase = efx_mtd_erase;
- part->mtd.read = efx_mtd->ops->read;
- part->mtd.write = efx_mtd->ops->write;
- part->mtd.sync = efx_mtd_sync;
+ part->mtd._erase = efx_mtd_erase;
+ part->mtd._read = efx->type->mtd_read;
+ part->mtd._write = efx->type->mtd_write;
+ part->mtd._sync = efx_mtd_sync;
+
+ efx->type->mtd_rename(part);
if (mtd_device_register(&part->mtd, NULL, 0))
goto fail;
+
+ /* Add to list in order - efx_mtd_remove() depends on this */
+ list_add_tail(&part->node, &efx->mtd_list);
}
- list_add(&efx_mtd->node, &efx->mtd_list);
return 0;
fail:
- while (part != &efx_mtd->part[0]) {
- --part;
+ while (i--) {
+ part = (struct efx_mtd_partition *)((char *)parts +
+ i * sizeof_part);
efx_mtd_remove_partition(part);
}
- /* mtd_device_register() returns 1 if the MTD table is full */
+ /* Failure is unlikely here, but probably means we're out of memory */
return -ENOMEM;
}
void efx_mtd_remove(struct efx_nic *efx)
{
- struct efx_mtd *efx_mtd, *next;
+ struct efx_mtd_partition *parts, *part, *next;
WARN_ON(efx_dev_registered(efx));
- list_for_each_entry_safe(efx_mtd, next, &efx->mtd_list, node)
- efx_mtd_remove_device(efx_mtd);
-}
-
-void efx_mtd_rename(struct efx_nic *efx)
-{
- struct efx_mtd *efx_mtd;
-
- ASSERT_RTNL();
-
- list_for_each_entry(efx_mtd, &efx->mtd_list, node)
- efx_mtd_rename_device(efx_mtd);
-}
-
-int efx_mtd_probe(struct efx_nic *efx)
-{
- if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
- return siena_mtd_probe(efx);
- else
- return falcon_mtd_probe(efx);
-}
-
-/* Implementation of MTD operations for Falcon */
-
-static int falcon_mtd_read(struct mtd_info *mtd, loff_t start,
- size_t len, size_t *retlen, u8 *buffer)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- const struct efx_spi_device *spi = efx_mtd->spi;
- struct efx_nic *efx = efx_mtd->efx;
- struct falcon_nic_data *nic_data = efx->nic_data;
- int rc;
-
- rc = mutex_lock_interruptible(&nic_data->spi_lock);
- if (rc)
- return rc;
- rc = falcon_spi_read(efx, spi, part->offset + start, len,
- retlen, buffer);
- mutex_unlock(&nic_data->spi_lock);
- return rc;
-}
-
-static int falcon_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- struct falcon_nic_data *nic_data = efx->nic_data;
- int rc;
-
- rc = mutex_lock_interruptible(&nic_data->spi_lock);
- if (rc)
- return rc;
- rc = efx_spi_erase(part, part->offset + start, len);
- mutex_unlock(&nic_data->spi_lock);
- return rc;
-}
-
-static int falcon_mtd_write(struct mtd_info *mtd, loff_t start,
- size_t len, size_t *retlen, const u8 *buffer)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- const struct efx_spi_device *spi = efx_mtd->spi;
- struct efx_nic *efx = efx_mtd->efx;
- struct falcon_nic_data *nic_data = efx->nic_data;
- int rc;
-
- rc = mutex_lock_interruptible(&nic_data->spi_lock);
- if (rc)
- return rc;
- rc = falcon_spi_write(efx, spi, part->offset + start, len,
- retlen, buffer);
- mutex_unlock(&nic_data->spi_lock);
- return rc;
-}
-
-static int falcon_mtd_sync(struct mtd_info *mtd)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- struct falcon_nic_data *nic_data = efx->nic_data;
- int rc;
-
- mutex_lock(&nic_data->spi_lock);
- rc = efx_spi_slow_wait(part, true);
- mutex_unlock(&nic_data->spi_lock);
- return rc;
-}
-
-static struct efx_mtd_ops falcon_mtd_ops = {
- .read = falcon_mtd_read,
- .erase = falcon_mtd_erase,
- .write = falcon_mtd_write,
- .sync = falcon_mtd_sync,
-};
-
-static int falcon_mtd_probe(struct efx_nic *efx)
-{
- struct falcon_nic_data *nic_data = efx->nic_data;
- struct efx_spi_device *spi;
- struct efx_mtd *efx_mtd;
- int rc = -ENODEV;
-
- ASSERT_RTNL();
-
- spi = &nic_data->spi_flash;
- if (efx_spi_present(spi) && spi->size > FALCON_FLASH_BOOTCODE_START) {
- efx_mtd = kzalloc(sizeof(*efx_mtd) + sizeof(efx_mtd->part[0]),
- GFP_KERNEL);
- if (!efx_mtd)
- return -ENOMEM;
-
- efx_mtd->spi = spi;
- efx_mtd->name = "flash";
- efx_mtd->ops = &falcon_mtd_ops;
-
- efx_mtd->n_parts = 1;
- efx_mtd->part[0].mtd.type = MTD_NORFLASH;
- efx_mtd->part[0].mtd.flags = MTD_CAP_NORFLASH;
- efx_mtd->part[0].mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START;
- efx_mtd->part[0].mtd.erasesize = spi->erase_size;
- efx_mtd->part[0].offset = FALCON_FLASH_BOOTCODE_START;
- efx_mtd->part[0].type_name = "sfc_flash_bootrom";
-
- rc = efx_mtd_probe_device(efx, efx_mtd);
- if (rc) {
- kfree(efx_mtd);
- return rc;
- }
- }
-
- spi = &nic_data->spi_eeprom;
- if (efx_spi_present(spi) && spi->size > EFX_EEPROM_BOOTCONFIG_START) {
- efx_mtd = kzalloc(sizeof(*efx_mtd) + sizeof(efx_mtd->part[0]),
- GFP_KERNEL);
- if (!efx_mtd)
- return -ENOMEM;
-
- efx_mtd->spi = spi;
- efx_mtd->name = "EEPROM";
- efx_mtd->ops = &falcon_mtd_ops;
-
- efx_mtd->n_parts = 1;
- efx_mtd->part[0].mtd.type = MTD_RAM;
- efx_mtd->part[0].mtd.flags = MTD_CAP_RAM;
- efx_mtd->part[0].mtd.size =
- min(spi->size, EFX_EEPROM_BOOTCONFIG_END) -
- EFX_EEPROM_BOOTCONFIG_START;
- efx_mtd->part[0].mtd.erasesize = spi->erase_size;
- efx_mtd->part[0].offset = EFX_EEPROM_BOOTCONFIG_START;
- efx_mtd->part[0].type_name = "sfc_bootconfig";
-
- rc = efx_mtd_probe_device(efx, efx_mtd);
- if (rc) {
- kfree(efx_mtd);
- return rc;
- }
- }
-
- return rc;
-}
-
-/* Implementation of MTD operations for Siena */
-
-static int siena_mtd_read(struct mtd_info *mtd, loff_t start,
- size_t len, size_t *retlen, u8 *buffer)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- loff_t offset = start;
- loff_t end = min_t(loff_t, start + len, mtd->size);
- size_t chunk;
- int rc = 0;
-
- while (offset < end) {
- chunk = min_t(size_t, end - offset, EFX_MCDI_NVRAM_LEN_MAX);
- rc = efx_mcdi_nvram_read(efx, part->mcdi.nvram_type, offset,
- buffer, chunk);
- if (rc)
- goto out;
- offset += chunk;
- buffer += chunk;
- }
-out:
- *retlen = offset - start;
- return rc;
-}
-
-static int siena_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- loff_t offset = start & ~((loff_t)(mtd->erasesize - 1));
- loff_t end = min_t(loff_t, start + len, mtd->size);
- size_t chunk = part->mtd.erasesize;
- int rc = 0;
-
- if (!part->mcdi.updating) {
- rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type);
- if (rc)
- goto out;
- part->mcdi.updating = true;
- }
-
- /* The MCDI interface can in fact do multiple erase blocks at once;
- * but erasing may be slow, so we make multiple calls here to avoid
- * tripping the MCDI RPC timeout. */
- while (offset < end) {
- rc = efx_mcdi_nvram_erase(efx, part->mcdi.nvram_type, offset,
- chunk);
- if (rc)
- goto out;
- offset += chunk;
- }
-out:
- return rc;
-}
-
-static int siena_mtd_write(struct mtd_info *mtd, loff_t start,
- size_t len, size_t *retlen, const u8 *buffer)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- loff_t offset = start;
- loff_t end = min_t(loff_t, start + len, mtd->size);
- size_t chunk;
- int rc = 0;
-
- if (!part->mcdi.updating) {
- rc = efx_mcdi_nvram_update_start(efx, part->mcdi.nvram_type);
- if (rc)
- goto out;
- part->mcdi.updating = true;
- }
-
- while (offset < end) {
- chunk = min_t(size_t, end - offset, EFX_MCDI_NVRAM_LEN_MAX);
- rc = efx_mcdi_nvram_write(efx, part->mcdi.nvram_type, offset,
- buffer, chunk);
- if (rc)
- goto out;
- offset += chunk;
- buffer += chunk;
- }
-out:
- *retlen = offset - start;
- return rc;
-}
-
-static int siena_mtd_sync(struct mtd_info *mtd)
-{
- struct efx_mtd_partition *part = to_efx_mtd_partition(mtd);
- struct efx_mtd *efx_mtd = mtd->priv;
- struct efx_nic *efx = efx_mtd->efx;
- int rc = 0;
-
- if (part->mcdi.updating) {
- part->mcdi.updating = false;
- rc = efx_mcdi_nvram_update_finish(efx, part->mcdi.nvram_type);
- }
-
- return rc;
-}
-
-static struct efx_mtd_ops siena_mtd_ops = {
- .read = siena_mtd_read,
- .erase = siena_mtd_erase,
- .write = siena_mtd_write,
- .sync = siena_mtd_sync,
-};
-
-struct siena_nvram_type_info {
- int port;
- const char *name;
-};
+ if (list_empty(&efx->mtd_list))
+ return;
-static struct siena_nvram_type_info siena_nvram_types[] = {
- [MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO] = { 0, "sfc_dummy_phy" },
- [MC_CMD_NVRAM_TYPE_MC_FW] = { 0, "sfc_mcfw" },
- [MC_CMD_NVRAM_TYPE_MC_FW_BACKUP] = { 0, "sfc_mcfw_backup" },
- [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0] = { 0, "sfc_static_cfg" },
- [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1] = { 1, "sfc_static_cfg" },
- [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0] = { 0, "sfc_dynamic_cfg" },
- [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1] = { 1, "sfc_dynamic_cfg" },
- [MC_CMD_NVRAM_TYPE_EXP_ROM] = { 0, "sfc_exp_rom" },
- [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0] = { 0, "sfc_exp_rom_cfg" },
- [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1] = { 1, "sfc_exp_rom_cfg" },
- [MC_CMD_NVRAM_TYPE_PHY_PORT0] = { 0, "sfc_phy_fw" },
- [MC_CMD_NVRAM_TYPE_PHY_PORT1] = { 1, "sfc_phy_fw" },
-};
+ parts = list_first_entry(&efx->mtd_list, struct efx_mtd_partition,
+ node);
-static int siena_mtd_probe_partition(struct efx_nic *efx,
- struct efx_mtd *efx_mtd,
- unsigned int part_id,
- unsigned int type)
-{
- struct efx_mtd_partition *part = &efx_mtd->part[part_id];
- struct siena_nvram_type_info *info;
- size_t size, erase_size;
- bool protected;
- int rc;
-
- if (type >= ARRAY_SIZE(siena_nvram_types))
- return -ENODEV;
-
- info = &siena_nvram_types[type];
-
- if (info->port != efx_port_num(efx))
- return -ENODEV;
-
- rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
- if (rc)
- return rc;
- if (protected)
- return -ENODEV; /* hide it */
-
- part->mcdi.nvram_type = type;
- part->type_name = info->name;
-
- part->mtd.type = MTD_NORFLASH;
- part->mtd.flags = MTD_CAP_NORFLASH;
- part->mtd.size = size;
- part->mtd.erasesize = erase_size;
+ list_for_each_entry_safe(part, next, &efx->mtd_list, node)
+ efx_mtd_remove_partition(part);
- return 0;
+ kfree(parts);
}
-static int siena_mtd_get_fw_subtypes(struct efx_nic *efx,
- struct efx_mtd *efx_mtd)
+void efx_mtd_rename(struct efx_nic *efx)
{
struct efx_mtd_partition *part;
- uint16_t fw_subtype_list[MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_LEN /
- sizeof(uint16_t)];
- int rc;
-
- rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list);
- if (rc)
- return rc;
-
- efx_for_each_partition(part, efx_mtd)
- part->mcdi.fw_subtype = fw_subtype_list[part->mcdi.nvram_type];
-
- return 0;
-}
-
-static int siena_mtd_probe(struct efx_nic *efx)
-{
- struct efx_mtd *efx_mtd;
- int rc = -ENODEV;
- u32 nvram_types;
- unsigned int type;
ASSERT_RTNL();
- rc = efx_mcdi_nvram_types(efx, &nvram_types);
- if (rc)
- return rc;
-
- efx_mtd = kzalloc(sizeof(*efx_mtd) +
- hweight32(nvram_types) * sizeof(efx_mtd->part[0]),
- GFP_KERNEL);
- if (!efx_mtd)
- return -ENOMEM;
-
- efx_mtd->name = "Siena NVRAM manager";
-
- efx_mtd->ops = &siena_mtd_ops;
-
- type = 0;
- efx_mtd->n_parts = 0;
-
- while (nvram_types != 0) {
- if (nvram_types & 1) {
- rc = siena_mtd_probe_partition(efx, efx_mtd,
- efx_mtd->n_parts, type);
- if (rc == 0)
- efx_mtd->n_parts++;
- else if (rc != -ENODEV)
- goto fail;
- }
- type++;
- nvram_types >>= 1;
- }
-
- rc = siena_mtd_get_fw_subtypes(efx, efx_mtd);
- if (rc)
- goto fail;
-
- rc = efx_mtd_probe_device(efx, efx_mtd);
-fail:
- if (rc)
- kfree(efx_mtd);
- return rc;
+ list_for_each_entry(part, &efx->mtd_list, node)
+ efx->type->mtd_rename(part);
}
-
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index c49502bab6a..5bdae8ed7c5 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2005-2011 Solarflare Communications Inc.
+ * Copyright 2005-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -13,10 +13,6 @@
#ifndef EFX_NET_DRIVER_H
#define EFX_NET_DRIVER_H
-#if defined(EFX_ENABLE_DEBUG) && !defined(DEBUG)
-#define DEBUG
-#endif
-
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ethtool.h>
@@ -28,11 +24,14 @@
#include <linux/device.h>
#include <linux/highmem.h>
#include <linux/workqueue.h>
+#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/i2c.h>
+#include <linux/mtd/mtd.h>
#include "enum.h"
#include "bitfield.h"
+#include "filter.h"
/**************************************************************************
*
@@ -40,9 +39,9 @@
*
**************************************************************************/
-#define EFX_DRIVER_VERSION "3.1"
+#define EFX_DRIVER_VERSION "4.0"
-#ifdef EFX_ENABLE_DEBUG
+#ifdef DEBUG
#define EFX_BUG_ON_PARANOID(x) BUG_ON(x)
#define EFX_WARN_ON_PARANOID(x) WARN_ON(x)
#else
@@ -56,8 +55,11 @@
*
**************************************************************************/
-#define EFX_MAX_CHANNELS 32
+#define EFX_MAX_CHANNELS 32U
#define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
+#define EFX_EXTRA_CHANNEL_IOV 0
+#define EFX_EXTRA_CHANNEL_PTP 1
+#define EFX_MAX_EXTRA_CHANNELS 2U
/* Checksum generation is a per-queue option in hardware, so each
* queue visible to the networking core is backed by two hardware TX
@@ -69,57 +71,99 @@
#define EFX_TXQ_TYPES 4
#define EFX_MAX_TX_QUEUES (EFX_TXQ_TYPES * EFX_MAX_CHANNELS)
+/* Maximum possible MTU the driver supports */
+#define EFX_MAX_MTU (9 * 1024)
+
+/* Size of an RX scatter buffer. Small enough to pack 2 into a 4K page,
+ * and should be a multiple of the cache line size.
+ */
+#define EFX_RX_USR_BUF_SIZE (2048 - 256)
+
+/* If possible, we should ensure cache line alignment at start and end
+ * of every buffer. Otherwise, we just need to ensure 4-byte
+ * alignment of the network header.
+ */
+#if NET_IP_ALIGN == 0
+#define EFX_RX_BUF_ALIGNMENT L1_CACHE_BYTES
+#else
+#define EFX_RX_BUF_ALIGNMENT 4
+#endif
+
+/* Forward declare Precision Time Protocol (PTP) support structure. */
+struct efx_ptp_data;
+struct hwtstamp_config;
+
+struct efx_self_tests;
+
/**
- * struct efx_special_buffer - An Efx special buffer
- * @addr: CPU base address of the buffer
+ * struct efx_buffer - A general-purpose DMA buffer
+ * @addr: host base address of the buffer
* @dma_addr: DMA base address of the buffer
* @len: Buffer length, in bytes
- * @index: Buffer index within controller;s buffer table
- * @entries: Number of buffer table entries
*
- * Special buffers are used for the event queues and the TX and RX
- * descriptor queues for each channel. They are *not* used for the
- * actual transmit and receive buffers.
+ * The NIC uses these buffers for its interrupt status registers and
+ * MAC stats dumps.
*/
-struct efx_special_buffer {
+struct efx_buffer {
void *addr;
dma_addr_t dma_addr;
unsigned int len;
- int index;
- int entries;
};
-enum efx_flush_state {
- FLUSH_NONE,
- FLUSH_PENDING,
- FLUSH_FAILED,
- FLUSH_DONE,
+/**
+ * struct efx_special_buffer - DMA buffer entered into buffer table
+ * @buf: Standard &struct efx_buffer
+ * @index: Buffer index within controller;s buffer table
+ * @entries: Number of buffer table entries
+ *
+ * The NIC has a buffer table that maps buffers of size %EFX_BUF_SIZE.
+ * Event and descriptor rings are addressed via one or more buffer
+ * table entries (and so can be physically non-contiguous, although we
+ * currently do not take advantage of that). On Falcon and Siena we
+ * have to take care of allocating and initialising the entries
+ * ourselves. On later hardware this is managed by the firmware and
+ * @index and @entries are left as 0.
+ */
+struct efx_special_buffer {
+ struct efx_buffer buf;
+ unsigned int index;
+ unsigned int entries;
};
/**
- * struct efx_tx_buffer - An Efx TX buffer
- * @skb: The associated socket buffer.
- * Set only on the final fragment of a packet; %NULL for all other
- * fragments. When this fragment completes, then we can free this
- * skb.
- * @tsoh: The associated TSO header structure, or %NULL if this
- * buffer is not a TSO header.
+ * struct efx_tx_buffer - buffer state for a TX descriptor
+ * @skb: When @flags & %EFX_TX_BUF_SKB, the associated socket buffer to be
+ * freed when descriptor completes
+ * @heap_buf: When @flags & %EFX_TX_BUF_HEAP, the associated heap buffer to be
+ * freed when descriptor completes.
+ * @option: When @flags & %EFX_TX_BUF_OPTION, a NIC-specific option descriptor.
* @dma_addr: DMA address of the fragment.
+ * @flags: Flags for allocation and DMA mapping type
* @len: Length of this fragment.
* This field is zero when the queue slot is empty.
- * @continuation: True if this fragment is not the end of a packet.
- * @unmap_single: True if pci_unmap_single should be used.
* @unmap_len: Length of this fragment to unmap
+ * @dma_offset: Offset of @dma_addr from the address of the backing DMA mapping.
+ * Only valid if @unmap_len != 0.
*/
struct efx_tx_buffer {
- const struct sk_buff *skb;
- struct efx_tso_header *tsoh;
- dma_addr_t dma_addr;
+ union {
+ const struct sk_buff *skb;
+ void *heap_buf;
+ };
+ union {
+ efx_qword_t option;
+ dma_addr_t dma_addr;
+ };
+ unsigned short flags;
unsigned short len;
- bool continuation;
- bool unmap_single;
unsigned short unmap_len;
+ unsigned short dma_offset;
};
+#define EFX_TX_BUF_CONT 1 /* not last descriptor of packet */
+#define EFX_TX_BUF_SKB 2 /* buffer is last part of skb */
+#define EFX_TX_BUF_HEAP 4 /* buffer was allocated with kmalloc() */
+#define EFX_TX_BUF_MAP_SINGLE 8 /* buffer was mapped with dma_map_single() */
+#define EFX_TX_BUF_OPTION 0x10 /* empty buffer for option descriptor */
/**
* struct efx_tx_queue - An Efx TX queue
@@ -139,10 +183,13 @@ struct efx_tx_buffer {
* @channel: The associated channel
* @core_txq: The networking core TX queue structure
* @buffer: The software buffer ring
+ * @tsoh_page: Array of pages of TSO header buffers
* @txd: The hardware descriptor ring
* @ptr_mask: The size of the ring minus 1.
+ * @piobuf: PIO buffer region for this TX queue (shared with its partner).
+ * Size of the region is efx_piobuf_size.
+ * @piobuf_offset: Buffer offset to be specified in PIO descriptors
* @initialised: Has hardware queue been initialised?
- * @flushed: Used when handling queue flushing
* @read_count: Current read pointer.
* This is the number of buffers that have been removed from both rings.
* @old_write_count: The value of @write_count when last checked.
@@ -151,6 +198,7 @@ struct efx_tx_buffer {
* variable indicates that the queue is empty. This is to
* avoid cache-line ping-pong between the xmit path and the
* completion path.
+ * @merge_events: Number of TX merged completion events
* @insert_count: Current insert pointer
* This is the number of buffers that have been added to the
* software ring.
@@ -163,14 +211,12 @@ struct efx_tx_buffer {
* variable indicates that the queue is full. This is to
* avoid cache-line ping-pong between the xmit path and the
* completion path.
- * @tso_headers_free: A list of TSO headers allocated for this TX queue
- * that are not in use, and so available for new TSO sends. The list
- * is protected by the TX queue lock.
* @tso_bursts: Number of times TSO xmit invoked by kernel
* @tso_long_headers: Number of packets with headers too long for standard
* blocks
* @tso_packets: Number of packets via the TSO xmit path
* @pushes: Number of times the TX push feature has been used
+ * @pio_packets: Number of times the TX PIO feature has been used
* @empty_read_count: If the completion path has seen the queue as empty
* and the transmission path has not yet checked this, the value of
* @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0.
@@ -182,49 +228,58 @@ struct efx_tx_queue {
struct efx_channel *channel;
struct netdev_queue *core_txq;
struct efx_tx_buffer *buffer;
+ struct efx_buffer *tsoh_page;
struct efx_special_buffer txd;
unsigned int ptr_mask;
+ void __iomem *piobuf;
+ unsigned int piobuf_offset;
bool initialised;
- enum efx_flush_state flushed;
/* Members used mainly on the completion path */
unsigned int read_count ____cacheline_aligned_in_smp;
unsigned int old_write_count;
+ unsigned int merge_events;
/* Members used only on the xmit path */
unsigned int insert_count ____cacheline_aligned_in_smp;
unsigned int write_count;
unsigned int old_read_count;
- struct efx_tso_header *tso_headers_free;
unsigned int tso_bursts;
unsigned int tso_long_headers;
unsigned int tso_packets;
unsigned int pushes;
+ unsigned int pio_packets;
/* Members shared between paths and sometimes updated */
unsigned int empty_read_count ____cacheline_aligned_in_smp;
#define EFX_EMPTY_COUNT_VALID 0x80000000
+ atomic_t flush_outstanding;
};
/**
* struct efx_rx_buffer - An Efx RX data buffer
* @dma_addr: DMA base address of the buffer
- * @skb: The associated socket buffer, if any.
- * If both this and page are %NULL, the buffer slot is currently free.
- * @page: The associated page buffer, if any.
- * If both this and skb are %NULL, the buffer slot is currently free.
- * @len: Buffer length, in bytes.
- * @is_page: Indicates if @page is valid. If false, @skb is valid.
+ * @page: The associated page buffer.
+ * Will be %NULL if the buffer slot is currently free.
+ * @page_offset: If pending: offset in @page of DMA base address.
+ * If completed: offset in @page of Ethernet header.
+ * @len: If pending: length for DMA descriptor.
+ * If completed: received length, excluding hash prefix.
+ * @flags: Flags for buffer and packet state. These are only set on the
+ * first buffer of a scattered packet.
*/
struct efx_rx_buffer {
dma_addr_t dma_addr;
- union {
- struct sk_buff *skb;
- struct page *page;
- } u;
- unsigned int len;
- bool is_page;
+ struct page *page;
+ u16 page_offset;
+ u16 len;
+ u16 flags;
};
+#define EFX_RX_BUF_LAST_IN_PAGE 0x0001
+#define EFX_RX_PKT_CSUMMED 0x0002
+#define EFX_RX_PKT_DISCARD 0x0004
+#define EFX_RX_PKT_TCP 0x0040
+#define EFX_RX_PKT_PREFIX_LEN 0x0080 /* length is in prefix only */
/**
* struct efx_rx_page_state - Page-based rx buffer state
@@ -233,12 +288,9 @@ struct efx_rx_buffer {
* Used to facilitate sharing dma mappings between recycled rx buffers
* and those passed up to the kernel.
*
- * @refcnt: Number of struct efx_rx_buffer's referencing this page.
- * When refcnt falls to zero, the page is unmapped for dma
* @dma_addr: The dma address of this page.
*/
struct efx_rx_page_state {
- unsigned refcnt;
dma_addr_t dma_addr;
unsigned int __pad[0] ____cacheline_aligned;
@@ -247,67 +299,72 @@ struct efx_rx_page_state {
/**
* struct efx_rx_queue - An Efx RX queue
* @efx: The associated Efx NIC
+ * @core_index: Index of network core RX queue. Will be >= 0 iff this
+ * is associated with a real RX queue.
* @buffer: The software buffer ring
* @rxd: The hardware descriptor ring
* @ptr_mask: The size of the ring minus 1.
+ * @refill_enabled: Enable refill whenever fill level is low
+ * @flush_pending: Set when a RX flush is pending. Has the same lifetime as
+ * @rxq_flush_pending.
* @added_count: Number of buffers added to the receive queue.
* @notified_count: Number of buffers given to NIC (<= @added_count).
* @removed_count: Number of buffers removed from the receive queue.
+ * @scatter_n: Used by NIC specific receive code.
+ * @scatter_len: Used by NIC specific receive code.
+ * @page_ring: The ring to store DMA mapped pages for reuse.
+ * @page_add: Counter to calculate the write pointer for the recycle ring.
+ * @page_remove: Counter to calculate the read pointer for the recycle ring.
+ * @page_recycle_count: The number of pages that have been recycled.
+ * @page_recycle_failed: The number of pages that couldn't be recycled because
+ * the kernel still held a reference to them.
+ * @page_recycle_full: The number of pages that were released because the
+ * recycle ring was full.
+ * @page_ptr_mask: The number of pages in the RX recycle ring minus 1.
* @max_fill: RX descriptor maximum fill level (<= ring size)
* @fast_fill_trigger: RX descriptor fill level that will trigger a fast fill
* (<= @max_fill)
- * @fast_fill_limit: The level to which a fast fill will fill
- * (@fast_fill_trigger <= @fast_fill_limit <= @max_fill)
* @min_fill: RX descriptor minimum non-zero fill level.
* This records the minimum fill level observed when a ring
* refill was triggered.
- * @alloc_page_count: RX allocation strategy counter.
- * @alloc_skb_count: RX allocation strategy counter.
+ * @recycle_count: RX buffer recycle counter.
* @slow_fill: Timer used to defer efx_nic_generate_fill_event().
- * @flushed: Use when handling queue flushing
*/
struct efx_rx_queue {
struct efx_nic *efx;
+ int core_index;
struct efx_rx_buffer *buffer;
struct efx_special_buffer rxd;
unsigned int ptr_mask;
-
- int added_count;
- int notified_count;
- int removed_count;
+ bool refill_enabled;
+ bool flush_pending;
+
+ unsigned int added_count;
+ unsigned int notified_count;
+ unsigned int removed_count;
+ unsigned int scatter_n;
+ unsigned int scatter_len;
+ struct page **page_ring;
+ unsigned int page_add;
+ unsigned int page_remove;
+ unsigned int page_recycle_count;
+ unsigned int page_recycle_failed;
+ unsigned int page_recycle_full;
+ unsigned int page_ptr_mask;
unsigned int max_fill;
unsigned int fast_fill_trigger;
- unsigned int fast_fill_limit;
unsigned int min_fill;
unsigned int min_overfill;
- unsigned int alloc_page_count;
- unsigned int alloc_skb_count;
+ unsigned int recycle_count;
struct timer_list slow_fill;
unsigned int slow_fill_count;
-
- enum efx_flush_state flushed;
-};
-
-/**
- * struct efx_buffer - An Efx general-purpose buffer
- * @addr: host base address of the buffer
- * @dma_addr: DMA base address of the buffer
- * @len: Buffer length, in bytes
- *
- * The NIC uses these buffers for its interrupt status registers and
- * MAC stats dumps.
- */
-struct efx_buffer {
- void *addr;
- dma_addr_t dma_addr;
- unsigned int len;
};
-
-enum efx_rx_alloc_method {
- RX_ALLOC_METHOD_AUTO = 0,
- RX_ALLOC_METHOD_SKB = 1,
- RX_ALLOC_METHOD_PAGE = 2,
+enum efx_sync_events_state {
+ SYNC_EVENTS_DISABLED = 0,
+ SYNC_EVENTS_QUIESCENT,
+ SYNC_EVENTS_REQUESTED,
+ SYNC_EVENTS_VALID,
};
/**
@@ -319,22 +376,19 @@ enum efx_rx_alloc_method {
*
* @efx: Associated Efx NIC
* @channel: Channel instance number
+ * @type: Channel type definition
+ * @eventq_init: Event queue initialised flag
* @enabled: Channel enabled indicator
* @irq: IRQ number (MSI and MSI-X only)
* @irq_moderation: IRQ moderation value (in hardware ticks)
* @napi_dev: Net device used with NAPI
* @napi_str: NAPI control structure
- * @work_pending: Is work pending via NAPI?
* @eventq: Event queue buffer
* @eventq_mask: Event queue pointer mask
* @eventq_read_ptr: Event queue read pointer
- * @last_eventq_read_ptr: Last event queue read pointer value.
+ * @event_test_cpu: Last CPU to handle interrupt or test event for this channel
* @irq_count: Number of IRQs since last adaptive moderation decision
* @irq_mod_score: IRQ moderation score
- * @rx_alloc_level: Watermark based heuristic counter for pushing descriptors
- * and diagnostic counters
- * @rx_alloc_push_pages: RX allocation method currently in use for pushing
- * descriptors
* @n_rx_tobe_disc: Count of RX_TOBE_DISC errors
* @n_rx_ip_hdr_chksum_err: Count of RX IP header checksum errors
* @n_rx_tcp_udp_chksum_err: Count of RX TCP and UDP checksum errors
@@ -342,22 +396,34 @@ enum efx_rx_alloc_method {
* @n_rx_frm_trunc: Count of RX_FRM_TRUNC errors
* @n_rx_overlength: Count of RX_OVERLENGTH errors
* @n_skbuff_leaks: Count of skbuffs leaked due to RX overrun
+ * @n_rx_nodesc_trunc: Number of RX packets truncated and then dropped due to
+ * lack of descriptors
+ * @n_rx_merge_events: Number of RX merged completion events
+ * @n_rx_merge_packets: Number of RX packets completed by merged events
+ * @rx_pkt_n_frags: Number of fragments in next packet to be delivered by
+ * __efx_rx_packet(), or zero if there is none
+ * @rx_pkt_index: Ring index of first buffer for next packet to be delivered
+ * by __efx_rx_packet(), if @rx_pkt_n_frags != 0
* @rx_queue: RX queue for this channel
* @tx_queue: TX queues for this channel
+ * @sync_events_state: Current state of sync events on this channel
+ * @sync_timestamp_major: Major part of the last ptp sync event
+ * @sync_timestamp_minor: Minor part of the last ptp sync event
*/
struct efx_channel {
struct efx_nic *efx;
int channel;
+ const struct efx_channel_type *type;
+ bool eventq_init;
bool enabled;
int irq;
unsigned int irq_moderation;
struct net_device *napi_dev;
struct napi_struct napi_str;
- bool work_pending;
struct efx_special_buffer eventq;
unsigned int eventq_mask;
unsigned int eventq_read_ptr;
- unsigned int last_eventq_read_ptr;
+ int event_test_cpu;
unsigned int irq_count;
unsigned int irq_mod_score;
@@ -365,9 +431,6 @@ struct efx_channel {
unsigned int rfs_filters_added;
#endif
- int rx_alloc_level;
- int rx_alloc_push_pages;
-
unsigned n_rx_tobe_disc;
unsigned n_rx_ip_hdr_chksum_err;
unsigned n_rx_tcp_udp_chksum_err;
@@ -375,15 +438,57 @@ struct efx_channel {
unsigned n_rx_frm_trunc;
unsigned n_rx_overlength;
unsigned n_skbuff_leaks;
+ unsigned int n_rx_nodesc_trunc;
+ unsigned int n_rx_merge_events;
+ unsigned int n_rx_merge_packets;
- /* Used to pipeline received packets in order to optimise memory
- * access with prefetches.
- */
- struct efx_rx_buffer *rx_pkt;
- bool rx_pkt_csummed;
+ unsigned int rx_pkt_n_frags;
+ unsigned int rx_pkt_index;
struct efx_rx_queue rx_queue;
struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
+
+ enum efx_sync_events_state sync_events_state;
+ u32 sync_timestamp_major;
+ u32 sync_timestamp_minor;
+};
+
+/**
+ * struct efx_msi_context - Context for each MSI
+ * @efx: The associated NIC
+ * @index: Index of the channel/IRQ
+ * @name: Name of the channel/IRQ
+ *
+ * Unlike &struct efx_channel, this is never reallocated and is always
+ * safe for the IRQ handler to access.
+ */
+struct efx_msi_context {
+ struct efx_nic *efx;
+ unsigned int index;
+ char name[IFNAMSIZ + 6];
+};
+
+/**
+ * struct efx_channel_type - distinguishes traffic and extra channels
+ * @handle_no_channel: Handle failure to allocate an extra channel
+ * @pre_probe: Set up extra state prior to initialisation
+ * @post_remove: Tear down extra state after finalisation, if allocated.
+ * May be called on channels that have not been probed.
+ * @get_name: Generate the channel's name (used for its IRQ handler)
+ * @copy: Copy the channel state prior to reallocation. May be %NULL if
+ * reallocation is not supported.
+ * @receive_skb: Handle an skb ready to be passed to netif_receive_skb()
+ * @keep_eventq: Flag for whether event queue should be kept initialised
+ * while the device is stopped
+ */
+struct efx_channel_type {
+ void (*handle_no_channel)(struct efx_nic *);
+ int (*pre_probe)(struct efx_channel *);
+ void (*post_remove)(struct efx_channel *);
+ void (*get_name)(struct efx_channel *, char *buf, size_t len);
+ struct efx_channel *(*copy)(const struct efx_channel *);
+ bool (*receive_skb)(struct efx_channel *, struct sk_buff *);
+ bool keep_eventq;
};
enum efx_led_mode {
@@ -395,12 +500,12 @@ enum efx_led_mode {
#define STRING_TABLE_LOOKUP(val, member) \
((val) < member ## _max) ? member ## _names[val] : "(invalid)"
-extern const char *efx_loopback_mode_names[];
+extern const char *const efx_loopback_mode_names[];
extern const unsigned int efx_loopback_mode_max;
#define LOOPBACK_MODE(efx) \
STRING_TABLE_LOOKUP((efx)->loopback_mode, efx_loopback_mode)
-extern const char *efx_reset_type_names[];
+extern const char *const efx_reset_type_names[];
extern const unsigned int efx_reset_type_max;
#define RESET_TYPE(type) \
STRING_TABLE_LOOKUP(type, efx_reset_type)
@@ -415,35 +520,12 @@ enum efx_int_mode {
#define EFX_INT_MODE_USE_MSI(x) (((x)->interrupt_mode) <= EFX_INT_MODE_MSI)
enum nic_state {
- STATE_INIT = 0,
- STATE_RUNNING = 1,
- STATE_FINI = 2,
- STATE_DISABLED = 3,
- STATE_MAX,
+ STATE_UNINIT = 0, /* device being probed/removed or is frozen */
+ STATE_READY = 1, /* hardware ready and netdev registered */
+ STATE_DISABLED = 2, /* device disabled due to hardware errors */
+ STATE_RECOVERY = 3, /* device recovering from PCI error */
};
-/*
- * Alignment of page-allocated RX buffers
- *
- * Controls the number of bytes inserted at the start of an RX buffer.
- * This is the equivalent of NET_IP_ALIGN [which controls the alignment
- * of the skb->head for hardware DMA].
- */
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#define EFX_PAGE_IP_ALIGN 0
-#else
-#define EFX_PAGE_IP_ALIGN NET_IP_ALIGN
-#endif
-
-/*
- * Alignment of the skb->head which wraps a page-allocated RX buffer
- *
- * The skb allocated to wrap an rx_buffer can have this alignment. Since
- * the data is memcpy'd from the rx_buf, it does not need to be equal to
- * EFX_PAGE_IP_ALIGN.
- */
-#define EFX_PAGE_SKB_ALIGN 2
-
/* Forward declaration */
struct efx_nic;
@@ -474,18 +556,6 @@ static inline bool efx_link_state_equal(const struct efx_link_state *left,
}
/**
- * struct efx_mac_operations - Efx MAC operations table
- * @reconfigure: Reconfigure MAC. Serialised by the mac_lock
- * @update_stats: Update statistics
- * @check_fault: Check fault state. True if fault present.
- */
-struct efx_mac_operations {
- int (*reconfigure) (struct efx_nic *efx);
- void (*update_stats) (struct efx_nic *efx);
- bool (*check_fault)(struct efx_nic *efx);
-};
-
-/**
* struct efx_phy_operations - Efx PHY operations table
* @probe: Probe PHY and initialise efx->mdio.mode_support, efx->mdio.mmds,
* efx->loopback_modes.
@@ -518,10 +588,15 @@ struct efx_phy_operations {
int (*test_alive) (struct efx_nic *efx);
const char *(*test_name) (struct efx_nic *efx, unsigned int index);
int (*run_tests) (struct efx_nic *efx, int *results, unsigned flags);
+ int (*get_module_eeprom) (struct efx_nic *efx,
+ struct ethtool_eeprom *ee,
+ u8 *data);
+ int (*get_module_info) (struct efx_nic *efx,
+ struct ethtool_modinfo *modinfo);
};
/**
- * @enum efx_phy_mode - PHY operating mode flags
+ * enum efx_phy_mode - PHY operating mode flags
* @PHY_MODE_NORMAL: on and should pass traffic
* @PHY_MODE_TX_DISABLED: on with TX disabled
* @PHY_MODE_LOW_POWER: set to low power through MDIO
@@ -541,75 +616,17 @@ static inline bool efx_phy_mode_disabled(enum efx_phy_mode mode)
return !!(mode & ~PHY_MODE_TX_DISABLED);
}
-/*
- * Efx extended statistics
- *
- * Not all statistics are provided by all supported MACs. The purpose
- * is this structure is to contain the raw statistics provided by each
- * MAC.
+/**
+ * struct efx_hw_stat_desc - Description of a hardware statistic
+ * @name: Name of the statistic as visible through ethtool, or %NULL if
+ * it should not be exposed
+ * @dma_width: Width in bits (0 for non-DMA statistics)
+ * @offset: Offset within stats (ignored for non-DMA statistics)
*/
-struct efx_mac_stats {
- u64 tx_bytes;
- u64 tx_good_bytes;
- u64 tx_bad_bytes;
- unsigned long tx_packets;
- unsigned long tx_bad;
- unsigned long tx_pause;
- unsigned long tx_control;
- unsigned long tx_unicast;
- unsigned long tx_multicast;
- unsigned long tx_broadcast;
- unsigned long tx_lt64;
- unsigned long tx_64;
- unsigned long tx_65_to_127;
- unsigned long tx_128_to_255;
- unsigned long tx_256_to_511;
- unsigned long tx_512_to_1023;
- unsigned long tx_1024_to_15xx;
- unsigned long tx_15xx_to_jumbo;
- unsigned long tx_gtjumbo;
- unsigned long tx_collision;
- unsigned long tx_single_collision;
- unsigned long tx_multiple_collision;
- unsigned long tx_excessive_collision;
- unsigned long tx_deferred;
- unsigned long tx_late_collision;
- unsigned long tx_excessive_deferred;
- unsigned long tx_non_tcpudp;
- unsigned long tx_mac_src_error;
- unsigned long tx_ip_src_error;
- u64 rx_bytes;
- u64 rx_good_bytes;
- u64 rx_bad_bytes;
- unsigned long rx_packets;
- unsigned long rx_good;
- unsigned long rx_bad;
- unsigned long rx_pause;
- unsigned long rx_control;
- unsigned long rx_unicast;
- unsigned long rx_multicast;
- unsigned long rx_broadcast;
- unsigned long rx_lt64;
- unsigned long rx_64;
- unsigned long rx_65_to_127;
- unsigned long rx_128_to_255;
- unsigned long rx_256_to_511;
- unsigned long rx_512_to_1023;
- unsigned long rx_1024_to_15xx;
- unsigned long rx_15xx_to_jumbo;
- unsigned long rx_gtjumbo;
- unsigned long rx_bad_lt64;
- unsigned long rx_bad_64_to_15xx;
- unsigned long rx_bad_15xx_to_jumbo;
- unsigned long rx_bad_gtjumbo;
- unsigned long rx_overflow;
- unsigned long rx_missed;
- unsigned long rx_false_carrier;
- unsigned long rx_symbol_error;
- unsigned long rx_align_error;
- unsigned long rx_length_error;
- unsigned long rx_internal_error;
- unsigned long rx_good_lt64;
+struct efx_hw_stat_desc {
+ const char *name;
+ u16 dma_width;
+ u16 offset;
};
/* Number of bits used in a multicast filter hash address */
@@ -624,15 +641,22 @@ union efx_multicast_hash {
efx_oword_t oword[EFX_MCAST_HASH_ENTRIES / sizeof(efx_oword_t) / 8];
};
-struct efx_filter_state;
+struct efx_vf;
+struct vfdi_status;
/**
* struct efx_nic - an Efx NIC
* @name: Device name (net device name or bus id before net device registered)
* @pci_dev: The PCI device
+ * @node: List node for maintaning primary/secondary function lists
+ * @primary: &struct efx_nic instance for the primary function of this
+ * controller. May be the same structure, and may be %NULL if no
+ * primary function is bound. Serialised by rtnl_lock.
+ * @secondary_list: List of &struct efx_nic instances for the secondary PCI
+ * functions of the controller, if this is for the primary function.
+ * Serialised by rtnl_lock.
* @type: Controller type attributes
* @legacy_irq: IRQ number
- * @legacy_irq_enabled: Are IRQs enabled on NIC (INT_EN_KER register)?
* @workqueue: Workqueue for port reconfigures and the HW monitor.
* Work items do not hold and must not acquire RTNL.
* @workqueue_name: Name of workqueue
@@ -640,32 +664,56 @@ struct efx_filter_state;
* @membase_phys: Memory BAR value as physical address
* @membase: Memory BAR value
* @interrupt_mode: Interrupt mode
+ * @timer_quantum_ns: Interrupt timer quantum, in nanoseconds
* @irq_rx_adaptive: Adaptive IRQ moderation enabled for RX event queues
* @irq_rx_moderation: IRQ moderation time for RX event queues
* @msg_enable: Log message enable flags
- * @state: Device state flag. Serialised by the rtnl_lock.
+ * @state: Device state number (%STATE_*). Serialised by the rtnl_lock.
* @reset_pending: Bitmask for pending resets
* @tx_queue: TX DMA queues
* @rx_queue: RX DMA queues
* @channel: Channels
- * @channel_name: Names for channels and their IRQs
+ * @msi_context: Context for each MSI
+ * @extra_channel_types: Types of extra (non-traffic) channels that
+ * should be allocated for this NIC
* @rxq_entries: Size of receive queues requested by user.
* @txq_entries: Size of transmit queues requested by user.
+ * @txq_stop_thresh: TX queue fill level at or above which we stop it.
+ * @txq_wake_thresh: TX queue fill level at or below which we wake it.
+ * @tx_dc_base: Base qword address in SRAM of TX queue descriptor caches
+ * @rx_dc_base: Base qword address in SRAM of RX queue descriptor caches
+ * @sram_lim_qw: Qword address limit of SRAM
* @next_buffer_table: First available buffer table id
* @n_channels: Number of channels in use
* @n_rx_channels: Number of channels used for RX (= number of RX queues)
* @n_tx_channels: Number of channels used for TX
- * @rx_buffer_len: RX buffer length
+ * @rx_ip_align: RX DMA address offset to have IP header aligned in
+ * in accordance with NET_IP_ALIGN
+ * @rx_dma_len: Current maximum RX DMA length
* @rx_buffer_order: Order (log2) of number of pages for each RX buffer
+ * @rx_buffer_truesize: Amortised allocation size of an RX buffer,
+ * for use in sk_buff::truesize
+ * @rx_prefix_size: Size of RX prefix before packet data
+ * @rx_packet_hash_offset: Offset of RX flow hash from start of packet data
+ * (valid only if @rx_prefix_size != 0; always negative)
+ * @rx_packet_len_offset: Offset of RX packet length from start of packet data
+ * (valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative)
+ * @rx_packet_ts_offset: Offset of timestamp from start of packet data
+ * (valid only if channel->sync_timestamps_enabled; always negative)
* @rx_hash_key: Toeplitz hash key for RSS
* @rx_indir_table: Indirection table for RSS
+ * @rx_scatter: Scatter mode enabled for receives
* @int_error_count: Number of internal errors seen recently
* @int_error_expire: Time at which error count will be expired
+ * @irq_soft_enabled: Are IRQs soft-enabled? If not, IRQ handler will
+ * acknowledge but do nothing else.
* @irq_status: Interrupt status buffer
* @irq_zero_count: Number of legacy IRQs seen with queue flags == 0
- * @fatal_irq_level: IRQ level (bit number) used for serious errors
+ * @irq_level: IRQ level/index for IRQs not triggered by an event queue
+ * @selftest_work: Work item for asynchronous self-test
* @mtd_list: List of MTDs attached to the NIC
* @nic_data: Hardware dependent state
+ * @mcdi: Management-Controller-to-Driver Interface state
* @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode,
* efx_monitor() and efx_reconfigure_port()
* @port_enabled: Port enabled indicator.
@@ -676,7 +724,6 @@ struct efx_filter_state;
* @port_initialized: Port initialized?
* @net_dev: Operating system network device. Consider holding the rtnl lock
* @stats_buffer: DMA buffer for statistics
- * @mac_op: MAC interface
* @phy_type: PHY type
* @phy_op: PHY interface
* @phy_data: PHY private data (including PHY-specific stats)
@@ -686,24 +733,50 @@ struct efx_filter_state;
* @link_advertising: Autonegotiation advertising flags
* @link_state: Current state of the link
* @n_link_state_changes: Number of times the link has changed state
- * @promiscuous: Promiscuous flag. Protected by netif_tx_lock.
- * @multicast_hash: Multicast hash table
+ * @unicast_filter: Flag for Falcon-arch simple unicast filter.
+ * Protected by @mac_lock.
+ * @multicast_hash: Multicast hash table for Falcon-arch.
+ * Protected by @mac_lock.
* @wanted_fc: Wanted flow control flags
+ * @fc_disable: When non-zero flow control is disabled. Typically used to
+ * ensure that network back pressure doesn't delay dma queue flushes.
+ * Serialised by the rtnl lock.
* @mac_work: Work item for changing MAC promiscuity and multicast hash
* @loopback_mode: Loopback status
* @loopback_modes: Supported loopback mode bitmask
* @loopback_selftest: Offline self-test private state
+ * @filter_lock: Filter table lock
+ * @filter_state: Architecture-dependent filter table state
+ * @rps_flow_id: Flow IDs of filters allocated for accelerated RFS,
+ * indexed by filter ID
+ * @rps_expire_index: Next index to check for expiry in @rps_flow_id
+ * @active_queues: Count of RX and TX queues that haven't been flushed and drained.
+ * @rxq_flush_pending: Count of number of receive queues that need to be flushed.
+ * Decremented when the efx_flush_rx_queue() is called.
+ * @rxq_flush_outstanding: Count of number of RX flushes started but not yet
+ * completed (either success or failure). Not used when MCDI is used to
+ * flush receive queues.
+ * @flush_wq: wait queue used by efx_nic_flush_queues() to wait for flush completions.
+ * @vf: Array of &struct efx_vf objects.
+ * @vf_count: Number of VFs intended to be enabled.
+ * @vf_init_count: Number of VFs that have been fully initialised.
+ * @vi_scale: log2 number of vnics per VF.
+ * @vf_buftbl_base: The zeroth buffer table index used to back VF queues.
+ * @vfdi_status: Common VFDI status page to be dmad to VF address space.
+ * @local_addr_list: List of local addresses. Protected by %local_lock.
+ * @local_page_list: List of DMA addressable pages used to broadcast
+ * %local_addr_list. Protected by %local_lock.
+ * @local_lock: Mutex protecting %local_addr_list and %local_page_list.
+ * @peer_work: Work item to broadcast peer addresses to VMs.
+ * @ptp_data: PTP state data
+ * @vpd_sn: Serial number read from VPD
* @monitor_work: Hardware monitor workitem
* @biu_lock: BIU (bus interface unit) lock
- * @last_irq_cpu: Last CPU to handle interrupt.
- * This register is written with the SMP processor ID whenever an
- * interrupt is handled. It is used by efx_nic_test_interrupt()
- * to verify that an interrupt has occurred.
- * @n_rx_nodesc_drop_cnt: RX no descriptor drop count
- * @mac_stats: MAC statistics. These include all statistics the MACs
- * can provide. Generic code converts these into a standard
- * &struct net_device_stats.
- * @stats_lock: Statistics update lock. Serialises statistics fetches
+ * @last_irq_cpu: Last CPU to handle a possible test interrupt. This
+ * field is used by efx_test_interrupts() to verify that an
+ * interrupt has occurred.
+ * @stats_lock: Statistics update lock. Must be held when calling
+ * efx_nic_type::{update,start,stop}_stats.
*
* This is stored in the private area of the &struct net_device.
*/
@@ -711,10 +784,14 @@ struct efx_nic {
/* The following fields should be written very rarely */
char name[IFNAMSIZ];
+ struct list_head node;
+ struct efx_nic *primary;
+ struct list_head secondary_list;
struct pci_dev *pci_dev;
+ unsigned int port_num;
const struct efx_nic_type *type;
int legacy_irq;
- bool legacy_irq_enabled;
+ bool eeh_disabled_legacy_irq;
struct workqueue_struct *workqueue;
char workqueue_name[16];
struct work_struct reset_work;
@@ -722,6 +799,7 @@ struct efx_nic {
void __iomem *membase;
enum efx_int_mode interrupt_mode;
+ unsigned int timer_quantum_ns;
bool irq_rx_adaptive;
unsigned int irq_rx_moderation;
u32 msg_enable;
@@ -730,43 +808,69 @@ struct efx_nic {
unsigned long reset_pending;
struct efx_channel *channel[EFX_MAX_CHANNELS];
- char channel_name[EFX_MAX_CHANNELS][IFNAMSIZ + 6];
+ struct efx_msi_context msi_context[EFX_MAX_CHANNELS];
+ const struct efx_channel_type *
+ extra_channel_type[EFX_MAX_EXTRA_CHANNELS];
unsigned rxq_entries;
unsigned txq_entries;
+ unsigned int txq_stop_thresh;
+ unsigned int txq_wake_thresh;
+
+ unsigned tx_dc_base;
+ unsigned rx_dc_base;
+ unsigned sram_lim_qw;
unsigned next_buffer_table;
+
+ unsigned int max_channels;
unsigned n_channels;
unsigned n_rx_channels;
+ unsigned rss_spread;
unsigned tx_channel_offset;
unsigned n_tx_channels;
- unsigned int rx_buffer_len;
+ unsigned int rx_ip_align;
+ unsigned int rx_dma_len;
unsigned int rx_buffer_order;
+ unsigned int rx_buffer_truesize;
+ unsigned int rx_page_buf_step;
+ unsigned int rx_bufs_per_page;
+ unsigned int rx_pages_per_batch;
+ unsigned int rx_prefix_size;
+ int rx_packet_hash_offset;
+ int rx_packet_len_offset;
+ int rx_packet_ts_offset;
u8 rx_hash_key[40];
u32 rx_indir_table[128];
+ bool rx_scatter;
unsigned int_error_count;
unsigned long int_error_expire;
+ bool irq_soft_enabled;
struct efx_buffer irq_status;
unsigned irq_zero_count;
- unsigned fatal_irq_level;
+ unsigned irq_level;
+ struct delayed_work selftest_work;
#ifdef CONFIG_SFC_MTD
struct list_head mtd_list;
#endif
void *nic_data;
+ struct efx_mcdi_data *mcdi;
struct mutex mac_lock;
struct work_struct mac_work;
bool port_enabled;
+ bool mc_bist_for_other_fn;
bool port_initialized;
struct net_device *net_dev;
struct efx_buffer stats_buffer;
-
- const struct efx_mac_operations *mac_op;
+ u64 rx_nodesc_drops_total;
+ u64 rx_nodesc_drops_while_down;
+ bool rx_nodesc_drops_prev_state;
unsigned int phy_type;
const struct efx_phy_operations *phy_op;
@@ -779,9 +883,10 @@ struct efx_nic {
struct efx_link_state link_state;
unsigned int n_link_state_changes;
- bool promiscuous;
+ bool unicast_filter;
union efx_multicast_hash multicast_hash;
u8 wanted_fc;
+ unsigned fc_disable;
atomic_t rx_reset;
enum efx_loopback_mode loopback_mode;
@@ -789,15 +894,41 @@ struct efx_nic {
void *loopback_selftest;
- struct efx_filter_state *filter_state;
+ spinlock_t filter_lock;
+ void *filter_state;
+#ifdef CONFIG_RFS_ACCEL
+ u32 *rps_flow_id;
+ unsigned int rps_expire_index;
+#endif
+
+ atomic_t active_queues;
+ atomic_t rxq_flush_pending;
+ atomic_t rxq_flush_outstanding;
+ wait_queue_head_t flush_wq;
+
+#ifdef CONFIG_SFC_SRIOV
+ struct efx_channel *vfdi_channel;
+ struct efx_vf *vf;
+ unsigned vf_count;
+ unsigned vf_init_count;
+ unsigned vi_scale;
+ unsigned vf_buftbl_base;
+ struct efx_buffer vfdi_status;
+ struct list_head local_addr_list;
+ struct list_head local_page_list;
+ struct mutex local_lock;
+ struct work_struct peer_work;
+#endif
+
+ struct efx_ptp_data *ptp_data;
+
+ char *vpd_sn;
/* The following fields may be written more often */
struct delayed_work monitor_work ____cacheline_aligned_in_smp;
spinlock_t biu_lock;
- volatile signed int last_irq_cpu;
- unsigned n_rx_nodesc_drop_cnt;
- struct efx_mac_stats mac_stats;
+ int last_irq_cpu;
spinlock_t stats_lock;
};
@@ -806,25 +937,27 @@ static inline int efx_dev_registered(struct efx_nic *efx)
return efx->net_dev->reg_state == NETREG_REGISTERED;
}
-/* Net device name, for inclusion in log messages if it has been registered.
- * Use efx->name not efx->net_dev->name so that races with (un)registration
- * are harmless.
- */
-static inline const char *efx_dev_name(struct efx_nic *efx)
-{
- return efx_dev_registered(efx) ? efx->name : "";
-}
-
static inline unsigned int efx_port_num(struct efx_nic *efx)
{
- return efx->net_dev->dev_id;
+ return efx->port_num;
}
+struct efx_mtd_partition {
+ struct list_head node;
+ struct mtd_info mtd;
+ const char *dev_type_name;
+ const char *type_name;
+ char name[IFNAMSIZ + 20];
+};
+
/**
* struct efx_nic_type - Efx device type definition
+ * @mem_map_size: Get memory BAR mapped size
* @probe: Probe the controller
* @remove: Free resources allocated by probe()
* @init: Initialise the controller
+ * @dimension_resources: Dimension controller resources (buffer table,
+ * and VIs once the available interrupt resources are clear)
* @fini: Shut down the controller
* @monitor: Periodic function for polling link state and hardware monitor
* @map_reset_reason: Map ethtool reset reason to a reset method
@@ -834,43 +967,130 @@ static inline unsigned int efx_port_num(struct efx_nic *efx)
* @probe_port: Probe the MAC and PHY
* @remove_port: Free resources allocated by probe_port()
* @handle_global_event: Handle a "global" event (may be %NULL)
+ * @fini_dmaq: Flush and finalise DMA queues (RX and TX queues)
* @prepare_flush: Prepare the hardware for flushing the DMA queues
- * @update_stats: Update statistics not provided by event handling
+ * (for Falcon architecture)
+ * @finish_flush: Clean up after flushing the DMA queues (for Falcon
+ * architecture)
+ * @prepare_flr: Prepare for an FLR
+ * @finish_flr: Clean up after an FLR
+ * @describe_stats: Describe statistics for ethtool
+ * @update_stats: Update statistics not provided by event handling.
+ * Either argument may be %NULL.
* @start_stats: Start the regular fetching of statistics
+ * @pull_stats: Pull stats from the NIC and wait until they arrive.
* @stop_stats: Stop the regular fetching of statistics
* @set_id_led: Set state of identifying LED or revert to automatic function
* @push_irq_moderation: Apply interrupt moderation value
- * @push_multicast_hash: Apply multicast hash table
* @reconfigure_port: Push loopback/power/txdis changes to the MAC and PHY
+ * @prepare_enable_fc_tx: Prepare MAC to enable pause frame TX (may be %NULL)
+ * @reconfigure_mac: Push MAC address, MTU, flow control and filter settings
+ * to the hardware. Serialised by the mac_lock.
+ * @check_mac_fault: Check MAC fault state. True if fault present.
* @get_wol: Get WoL configuration from driver state
* @set_wol: Push WoL configuration to the NIC
* @resume_wol: Synchronise WoL state between driver and MC (e.g. after resume)
- * @test_registers: Test read/write functionality of control registers
+ * @test_chip: Test registers. May use efx_farch_test_registers(), and is
+ * expected to reset the NIC.
* @test_nvram: Test validity of NVRAM contents
- * @default_mac_ops: efx_mac_operations to set at startup
+ * @mcdi_request: Send an MCDI request with the given header and SDU.
+ * The SDU length may be any value from 0 up to the protocol-
+ * defined maximum, but its buffer will be padded to a multiple
+ * of 4 bytes.
+ * @mcdi_poll_response: Test whether an MCDI response is available.
+ * @mcdi_read_response: Read the MCDI response PDU. The offset will
+ * be a multiple of 4. The length may not be, but the buffer
+ * will be padded so it is safe to round up.
+ * @mcdi_poll_reboot: Test whether the MCDI has rebooted. If so,
+ * return an appropriate error code for aborting any current
+ * request; otherwise return 0.
+ * @irq_enable_master: Enable IRQs on the NIC. Each event queue must
+ * be separately enabled after this.
+ * @irq_test_generate: Generate a test IRQ
+ * @irq_disable_non_ev: Disable non-event IRQs on the NIC. Each event
+ * queue must be separately disabled before this.
+ * @irq_handle_msi: Handle MSI for a channel. The @dev_id argument is
+ * a pointer to the &struct efx_msi_context for the channel.
+ * @irq_handle_legacy: Handle legacy interrupt. The @dev_id argument
+ * is a pointer to the &struct efx_nic.
+ * @tx_probe: Allocate resources for TX queue
+ * @tx_init: Initialise TX queue on the NIC
+ * @tx_remove: Free resources for TX queue
+ * @tx_write: Write TX descriptors and doorbell
+ * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC
+ * @rx_probe: Allocate resources for RX queue
+ * @rx_init: Initialise RX queue on the NIC
+ * @rx_remove: Free resources for RX queue
+ * @rx_write: Write RX descriptors and doorbell
+ * @rx_defer_refill: Generate a refill reminder event
+ * @ev_probe: Allocate resources for event queue
+ * @ev_init: Initialise event queue on the NIC
+ * @ev_fini: Deinitialise event queue on the NIC
+ * @ev_remove: Free resources for event queue
+ * @ev_process: Process events for a queue, up to the given NAPI quota
+ * @ev_read_ack: Acknowledge read events on a queue, rearming its IRQ
+ * @ev_test_generate: Generate a test event
+ * @filter_table_probe: Probe filter capabilities and set up filter software state
+ * @filter_table_restore: Restore filters removed from hardware
+ * @filter_table_remove: Remove filters from hardware and tear down software state
+ * @filter_update_rx_scatter: Update filters after change to rx scatter setting
+ * @filter_insert: add or replace a filter
+ * @filter_remove_safe: remove a filter by ID, carefully
+ * @filter_get_safe: retrieve a filter by ID, carefully
+ * @filter_clear_rx: Remove all RX filters whose priority is less than or
+ * equal to the given priority and is not %EFX_FILTER_PRI_AUTO
+ * @filter_count_rx_used: Get the number of filters in use at a given priority
+ * @filter_get_rx_id_limit: Get maximum value of a filter id, plus 1
+ * @filter_get_rx_ids: Get list of RX filters at a given priority
+ * @filter_rfs_insert: Add or replace a filter for RFS. This must be
+ * atomic. The hardware change may be asynchronous but should
+ * not be delayed for long. It may fail if this can't be done
+ * atomically.
+ * @filter_rfs_expire_one: Consider expiring a filter inserted for RFS.
+ * This must check whether the specified table entry is used by RFS
+ * and that rps_may_expire_flow() returns true for it.
+ * @mtd_probe: Probe and add MTD partitions associated with this net device,
+ * using efx_mtd_add()
+ * @mtd_rename: Set an MTD partition name using the net device name
+ * @mtd_read: Read from an MTD partition
+ * @mtd_erase: Erase part of an MTD partition
+ * @mtd_write: Write to an MTD partition
+ * @mtd_sync: Wait for write-back to complete on MTD partition. This
+ * also notifies the driver that a writer has finished using this
+ * partition.
+ * @ptp_write_host_time: Send host time to MC as part of sync protocol
+ * @ptp_set_ts_sync_events: Enable or disable sync events for inline RX
+ * timestamping, possibly only temporarily for the purposes of a reset.
+ * @ptp_set_ts_config: Set hardware timestamp configuration. The flags
+ * and tx_type will already have been validated but this operation
+ * must validate and update rx_filter.
* @revision: Hardware architecture revision
- * @mem_map_size: Memory BAR mapped size
* @txd_ptr_tbl_base: TX descriptor ring base address
* @rxd_ptr_tbl_base: RX descriptor ring base address
* @buf_tbl_base: Buffer table base address
* @evq_ptr_tbl_base: Event queue pointer table base address
* @evq_rptr_tbl_base: Event queue read-pointer table base address
* @max_dma_mask: Maximum possible DMA mask
- * @rx_buffer_hash_size: Size of hash at start of RX buffer
- * @rx_buffer_padding: Size of padding at end of RX buffer
+ * @rx_prefix_size: Size of RX prefix before packet data
+ * @rx_hash_offset: Offset of RX flow hash within prefix
+ * @rx_ts_offset: Offset of timestamp within prefix
+ * @rx_buffer_padding: Size of padding at end of RX packet
+ * @can_rx_scatter: NIC is able to scatter packets to multiple buffers
+ * @always_rx_scatter: NIC will always scatter packets to multiple buffers
* @max_interrupt_mode: Highest capability interrupt mode supported
* from &enum efx_init_mode.
- * @phys_addr_channels: Number of channels with physically addressed
- * descriptors
- * @tx_dc_base: Base address in SRAM of TX queue descriptor caches
- * @rx_dc_base: Base address in SRAM of RX queue descriptor caches
+ * @timer_period_max: Maximum period of interrupt timer (in ticks)
* @offload_features: net_device feature flags for protocol offload
* features implemented in hardware
+ * @mcdi_max_ver: Maximum MCDI version supported
+ * @hwtstamp_filters: Mask of hardware timestamp filter types supported
*/
struct efx_nic_type {
+ unsigned int (*mem_map_size)(struct efx_nic *efx);
int (*probe)(struct efx_nic *efx);
void (*remove)(struct efx_nic *efx);
int (*init)(struct efx_nic *efx);
+ int (*dimension_resources)(struct efx_nic *efx);
void (*fini)(struct efx_nic *efx);
void (*monitor)(struct efx_nic *efx);
enum reset_type (*map_reset_reason)(enum reset_type reason);
@@ -879,36 +1099,117 @@ struct efx_nic_type {
int (*probe_port)(struct efx_nic *efx);
void (*remove_port)(struct efx_nic *efx);
bool (*handle_global_event)(struct efx_channel *channel, efx_qword_t *);
+ int (*fini_dmaq)(struct efx_nic *efx);
void (*prepare_flush)(struct efx_nic *efx);
- void (*update_stats)(struct efx_nic *efx);
+ void (*finish_flush)(struct efx_nic *efx);
+ void (*prepare_flr)(struct efx_nic *efx);
+ void (*finish_flr)(struct efx_nic *efx);
+ size_t (*describe_stats)(struct efx_nic *efx, u8 *names);
+ size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats,
+ struct rtnl_link_stats64 *core_stats);
void (*start_stats)(struct efx_nic *efx);
+ void (*pull_stats)(struct efx_nic *efx);
void (*stop_stats)(struct efx_nic *efx);
void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode);
void (*push_irq_moderation)(struct efx_channel *channel);
- void (*push_multicast_hash)(struct efx_nic *efx);
int (*reconfigure_port)(struct efx_nic *efx);
+ void (*prepare_enable_fc_tx)(struct efx_nic *efx);
+ int (*reconfigure_mac)(struct efx_nic *efx);
+ bool (*check_mac_fault)(struct efx_nic *efx);
void (*get_wol)(struct efx_nic *efx, struct ethtool_wolinfo *wol);
int (*set_wol)(struct efx_nic *efx, u32 type);
void (*resume_wol)(struct efx_nic *efx);
- int (*test_registers)(struct efx_nic *efx);
+ int (*test_chip)(struct efx_nic *efx, struct efx_self_tests *tests);
int (*test_nvram)(struct efx_nic *efx);
- const struct efx_mac_operations *default_mac_ops;
+ void (*mcdi_request)(struct efx_nic *efx,
+ const efx_dword_t *hdr, size_t hdr_len,
+ const efx_dword_t *sdu, size_t sdu_len);
+ bool (*mcdi_poll_response)(struct efx_nic *efx);
+ void (*mcdi_read_response)(struct efx_nic *efx, efx_dword_t *pdu,
+ size_t pdu_offset, size_t pdu_len);
+ int (*mcdi_poll_reboot)(struct efx_nic *efx);
+ void (*irq_enable_master)(struct efx_nic *efx);
+ void (*irq_test_generate)(struct efx_nic *efx);
+ void (*irq_disable_non_ev)(struct efx_nic *efx);
+ irqreturn_t (*irq_handle_msi)(int irq, void *dev_id);
+ irqreturn_t (*irq_handle_legacy)(int irq, void *dev_id);
+ int (*tx_probe)(struct efx_tx_queue *tx_queue);
+ void (*tx_init)(struct efx_tx_queue *tx_queue);
+ void (*tx_remove)(struct efx_tx_queue *tx_queue);
+ void (*tx_write)(struct efx_tx_queue *tx_queue);
+ void (*rx_push_rss_config)(struct efx_nic *efx);
+ int (*rx_probe)(struct efx_rx_queue *rx_queue);
+ void (*rx_init)(struct efx_rx_queue *rx_queue);
+ void (*rx_remove)(struct efx_rx_queue *rx_queue);
+ void (*rx_write)(struct efx_rx_queue *rx_queue);
+ void (*rx_defer_refill)(struct efx_rx_queue *rx_queue);
+ int (*ev_probe)(struct efx_channel *channel);
+ int (*ev_init)(struct efx_channel *channel);
+ void (*ev_fini)(struct efx_channel *channel);
+ void (*ev_remove)(struct efx_channel *channel);
+ int (*ev_process)(struct efx_channel *channel, int quota);
+ void (*ev_read_ack)(struct efx_channel *channel);
+ void (*ev_test_generate)(struct efx_channel *channel);
+ int (*filter_table_probe)(struct efx_nic *efx);
+ void (*filter_table_restore)(struct efx_nic *efx);
+ void (*filter_table_remove)(struct efx_nic *efx);
+ void (*filter_update_rx_scatter)(struct efx_nic *efx);
+ s32 (*filter_insert)(struct efx_nic *efx,
+ struct efx_filter_spec *spec, bool replace);
+ int (*filter_remove_safe)(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id);
+ int (*filter_get_safe)(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id, struct efx_filter_spec *);
+ int (*filter_clear_rx)(struct efx_nic *efx,
+ enum efx_filter_priority priority);
+ u32 (*filter_count_rx_used)(struct efx_nic *efx,
+ enum efx_filter_priority priority);
+ u32 (*filter_get_rx_id_limit)(struct efx_nic *efx);
+ s32 (*filter_get_rx_ids)(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 *buf, u32 size);
+#ifdef CONFIG_RFS_ACCEL
+ s32 (*filter_rfs_insert)(struct efx_nic *efx,
+ struct efx_filter_spec *spec);
+ bool (*filter_rfs_expire_one)(struct efx_nic *efx, u32 flow_id,
+ unsigned int index);
+#endif
+#ifdef CONFIG_SFC_MTD
+ int (*mtd_probe)(struct efx_nic *efx);
+ void (*mtd_rename)(struct efx_mtd_partition *part);
+ int (*mtd_read)(struct mtd_info *mtd, loff_t start, size_t len,
+ size_t *retlen, u8 *buffer);
+ int (*mtd_erase)(struct mtd_info *mtd, loff_t start, size_t len);
+ int (*mtd_write)(struct mtd_info *mtd, loff_t start, size_t len,
+ size_t *retlen, const u8 *buffer);
+ int (*mtd_sync)(struct mtd_info *mtd);
+#endif
+ void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time);
+ int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp);
+ int (*ptp_set_ts_config)(struct efx_nic *efx,
+ struct hwtstamp_config *init);
int revision;
- unsigned int mem_map_size;
unsigned int txd_ptr_tbl_base;
unsigned int rxd_ptr_tbl_base;
unsigned int buf_tbl_base;
unsigned int evq_ptr_tbl_base;
unsigned int evq_rptr_tbl_base;
u64 max_dma_mask;
- unsigned int rx_buffer_hash_size;
+ unsigned int rx_prefix_size;
+ unsigned int rx_hash_offset;
+ unsigned int rx_ts_offset;
unsigned int rx_buffer_padding;
+ bool can_rx_scatter;
+ bool always_rx_scatter;
unsigned int max_interrupt_mode;
- unsigned int phys_addr_channels;
- unsigned int tx_dc_base;
- unsigned int rx_dc_base;
+ unsigned int timer_period_max;
netdev_features_t offload_features;
+ int mcdi_max_ver;
+ unsigned int max_rx_ip_filters;
+ u32 hwtstamp_filters;
};
/**************************************************************************
@@ -931,6 +1232,13 @@ efx_get_channel(struct efx_nic *efx, unsigned index)
_channel = (_channel->channel + 1 < (_efx)->n_channels) ? \
(_efx)->channel[_channel->channel + 1] : NULL)
+/* Iterate over all used channels in reverse */
+#define efx_for_each_channel_rev(_channel, _efx) \
+ for (_channel = (_efx)->channel[(_efx)->n_channels - 1]; \
+ _channel; \
+ _channel = _channel->channel ? \
+ (_efx)->channel[_channel->channel - 1] : NULL)
+
static inline struct efx_tx_queue *
efx_get_tx_queue(struct efx_nic *efx, unsigned index, unsigned type)
{
@@ -971,20 +1279,16 @@ static inline bool efx_tx_queue_used(struct efx_tx_queue *tx_queue)
/* Iterate over all possible TX queues belonging to a channel */
#define efx_for_each_possible_channel_tx_queue(_tx_queue, _channel) \
- for (_tx_queue = (_channel)->tx_queue; \
- _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES; \
- _tx_queue++)
-
-static inline struct efx_rx_queue *
-efx_get_rx_queue(struct efx_nic *efx, unsigned index)
-{
- EFX_BUG_ON_PARANOID(index >= efx->n_rx_channels);
- return &efx->channel[index]->rx_queue;
-}
+ if (!efx_channel_has_tx_queues(_channel)) \
+ ; \
+ else \
+ for (_tx_queue = (_channel)->tx_queue; \
+ _tx_queue < (_channel)->tx_queue + EFX_TXQ_TYPES; \
+ _tx_queue++)
static inline bool efx_channel_has_rx_queue(struct efx_channel *channel)
{
- return channel->channel < channel->efx->n_rx_channels;
+ return channel->rx_queue.core_index >= 0;
}
static inline struct efx_rx_queue *
@@ -1023,19 +1327,6 @@ static inline struct efx_rx_buffer *efx_rx_buffer(struct efx_rx_queue *rx_queue,
return &rx_queue->buffer[index];
}
-/* Set bit in a little-endian bitfield */
-static inline void set_bit_le(unsigned nr, unsigned char *addr)
-{
- addr[nr / 8] |= (1 << (nr % 8));
-}
-
-/* Clear bit in a little-endian bitfield */
-static inline void clear_bit_le(unsigned nr, unsigned char *addr)
-{
- addr[nr / 8] &= ~(1 << (nr % 8));
-}
-
-
/**
* EFX_MAX_FRAME_LEN - calculate maximum frame length
*
@@ -1056,5 +1347,13 @@ static inline void clear_bit_le(unsigned nr, unsigned char *addr)
#define EFX_MAX_FRAME_LEN(mtu) \
((((mtu) + ETH_HLEN + VLAN_HLEN + 4/* FCS */ + 7) & ~7) + 16)
+static inline bool efx_xmit_with_hwtstamp(struct sk_buff *skb)
+{
+ return skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP;
+}
+static inline void efx_xmit_hwtstamp_pending(struct sk_buff *skb)
+{
+ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+}
#endif /* EFX_NET_DRIVER_H */
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 3edfbaf5f02..89b83e59e1d 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2011 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -14,1052 +14,43 @@
#include <linux/pci.h>
#include <linux/module.h>
#include <linux/seq_file.h>
+#include <linux/cpu_rmap.h>
#include "net_driver.h"
#include "bitfield.h"
#include "efx.h"
#include "nic.h"
-#include "regs.h"
+#include "ef10_regs.h"
+#include "farch_regs.h"
#include "io.h"
#include "workarounds.h"
/**************************************************************************
*
- * Configurable values
- *
- **************************************************************************
- */
-
-/* This is set to 16 for a good reason. In summary, if larger than
- * 16, the descriptor cache holds more than a default socket
- * buffer's worth of packets (for UDP we can only have at most one
- * socket buffer's worth outstanding). This combined with the fact
- * that we only get 1 TX event per descriptor cache means the NIC
- * goes idle.
- */
-#define TX_DC_ENTRIES 16
-#define TX_DC_ENTRIES_ORDER 1
-
-#define RX_DC_ENTRIES 64
-#define RX_DC_ENTRIES_ORDER 3
-
-/* If EFX_MAX_INT_ERRORS internal errors occur within
- * EFX_INT_ERROR_EXPIRE seconds, we consider the NIC broken and
- * disable it.
- */
-#define EFX_INT_ERROR_EXPIRE 3600
-#define EFX_MAX_INT_ERRORS 5
-
-/* We poll for events every FLUSH_INTERVAL ms, and check FLUSH_POLL_COUNT times
- */
-#define EFX_FLUSH_INTERVAL 10
-#define EFX_FLUSH_POLL_COUNT 100
-
-/* Size and alignment of special buffers (4KB) */
-#define EFX_BUF_SIZE 4096
-
-/* Depth of RX flush request fifo */
-#define EFX_RX_FLUSH_COUNT 4
-
-/* Generated event code for efx_generate_test_event() */
-#define EFX_CHANNEL_MAGIC_TEST(_channel) \
- (0x00010100 + (_channel)->channel)
-
-/* Generated event code for efx_generate_fill_event() */
-#define EFX_CHANNEL_MAGIC_FILL(_channel) \
- (0x00010200 + (_channel)->channel)
-
-/**************************************************************************
- *
- * Solarstorm hardware access
- *
- **************************************************************************/
-
-static inline void efx_write_buf_tbl(struct efx_nic *efx, efx_qword_t *value,
- unsigned int index)
-{
- efx_sram_writeq(efx, efx->membase + efx->type->buf_tbl_base,
- value, index);
-}
-
-/* Read the current event from the event queue */
-static inline efx_qword_t *efx_event(struct efx_channel *channel,
- unsigned int index)
-{
- return ((efx_qword_t *) (channel->eventq.addr)) +
- (index & channel->eventq_mask);
-}
-
-/* See if an event is present
- *
- * We check both the high and low dword of the event for all ones. We
- * wrote all ones when we cleared the event, and no valid event can
- * have all ones in either its high or low dwords. This approach is
- * robust against reordering.
- *
- * Note that using a single 64-bit comparison is incorrect; even
- * though the CPU read will be atomic, the DMA write may not be.
- */
-static inline int efx_event_present(efx_qword_t *event)
-{
- return !(EFX_DWORD_IS_ALL_ONES(event->dword[0]) |
- EFX_DWORD_IS_ALL_ONES(event->dword[1]));
-}
-
-static bool efx_masked_compare_oword(const efx_oword_t *a, const efx_oword_t *b,
- const efx_oword_t *mask)
-{
- return ((a->u64[0] ^ b->u64[0]) & mask->u64[0]) ||
- ((a->u64[1] ^ b->u64[1]) & mask->u64[1]);
-}
-
-int efx_nic_test_registers(struct efx_nic *efx,
- const struct efx_nic_register_test *regs,
- size_t n_regs)
-{
- unsigned address = 0, i, j;
- efx_oword_t mask, imask, original, reg, buf;
-
- /* Falcon should be in loopback to isolate the XMAC from the PHY */
- WARN_ON(!LOOPBACK_INTERNAL(efx));
-
- for (i = 0; i < n_regs; ++i) {
- address = regs[i].address;
- mask = imask = regs[i].mask;
- EFX_INVERT_OWORD(imask);
-
- efx_reado(efx, &original, address);
-
- /* bit sweep on and off */
- for (j = 0; j < 128; j++) {
- if (!EFX_EXTRACT_OWORD32(mask, j, j))
- continue;
-
- /* Test this testable bit can be set in isolation */
- EFX_AND_OWORD(reg, original, mask);
- EFX_SET_OWORD32(reg, j, j, 1);
-
- efx_writeo(efx, &reg, address);
- efx_reado(efx, &buf, address);
-
- if (efx_masked_compare_oword(&reg, &buf, &mask))
- goto fail;
-
- /* Test this testable bit can be cleared in isolation */
- EFX_OR_OWORD(reg, original, mask);
- EFX_SET_OWORD32(reg, j, j, 0);
-
- efx_writeo(efx, &reg, address);
- efx_reado(efx, &buf, address);
-
- if (efx_masked_compare_oword(&reg, &buf, &mask))
- goto fail;
- }
-
- efx_writeo(efx, &original, address);
- }
-
- return 0;
-
-fail:
- netif_err(efx, hw, efx->net_dev,
- "wrote "EFX_OWORD_FMT" read "EFX_OWORD_FMT
- " at address 0x%x mask "EFX_OWORD_FMT"\n", EFX_OWORD_VAL(reg),
- EFX_OWORD_VAL(buf), address, EFX_OWORD_VAL(mask));
- return -EIO;
-}
-
-/**************************************************************************
- *
- * Special buffer handling
- * Special buffers are used for event queues and the TX and RX
- * descriptor rings.
- *
- *************************************************************************/
-
-/*
- * Initialise a special buffer
- *
- * This will define a buffer (previously allocated via
- * efx_alloc_special_buffer()) in the buffer table, allowing
- * it to be used for event queues, descriptor rings etc.
- */
-static void
-efx_init_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
-{
- efx_qword_t buf_desc;
- int index;
- dma_addr_t dma_addr;
- int i;
-
- EFX_BUG_ON_PARANOID(!buffer->addr);
-
- /* Write buffer descriptors to NIC */
- for (i = 0; i < buffer->entries; i++) {
- index = buffer->index + i;
- dma_addr = buffer->dma_addr + (i * 4096);
- netif_dbg(efx, probe, efx->net_dev,
- "mapping special buffer %d at %llx\n",
- index, (unsigned long long)dma_addr);
- EFX_POPULATE_QWORD_3(buf_desc,
- FRF_AZ_BUF_ADR_REGION, 0,
- FRF_AZ_BUF_ADR_FBUF, dma_addr >> 12,
- FRF_AZ_BUF_OWNER_ID_FBUF, 0);
- efx_write_buf_tbl(efx, &buf_desc, index);
- }
-}
-
-/* Unmaps a buffer and clears the buffer table entries */
-static void
-efx_fini_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
-{
- efx_oword_t buf_tbl_upd;
- unsigned int start = buffer->index;
- unsigned int end = (buffer->index + buffer->entries - 1);
-
- if (!buffer->entries)
- return;
-
- netif_dbg(efx, hw, efx->net_dev, "unmapping special buffers %d-%d\n",
- buffer->index, buffer->index + buffer->entries - 1);
-
- EFX_POPULATE_OWORD_4(buf_tbl_upd,
- FRF_AZ_BUF_UPD_CMD, 0,
- FRF_AZ_BUF_CLR_CMD, 1,
- FRF_AZ_BUF_CLR_END_ID, end,
- FRF_AZ_BUF_CLR_START_ID, start);
- efx_writeo(efx, &buf_tbl_upd, FR_AZ_BUF_TBL_UPD);
-}
-
-/*
- * Allocate a new special buffer
- *
- * This allocates memory for a new buffer, clears it and allocates a
- * new buffer ID range. It does not write into the buffer table.
- *
- * This call will allocate 4KB buffers, since 8KB buffers can't be
- * used for event queues and descriptor rings.
- */
-static int efx_alloc_special_buffer(struct efx_nic *efx,
- struct efx_special_buffer *buffer,
- unsigned int len)
-{
- len = ALIGN(len, EFX_BUF_SIZE);
-
- buffer->addr = dma_alloc_coherent(&efx->pci_dev->dev, len,
- &buffer->dma_addr, GFP_KERNEL);
- if (!buffer->addr)
- return -ENOMEM;
- buffer->len = len;
- buffer->entries = len / EFX_BUF_SIZE;
- BUG_ON(buffer->dma_addr & (EFX_BUF_SIZE - 1));
-
- /* All zeros is a potentially valid event so memset to 0xff */
- memset(buffer->addr, 0xff, len);
-
- /* Select new buffer ID */
- buffer->index = efx->next_buffer_table;
- efx->next_buffer_table += buffer->entries;
-
- netif_dbg(efx, probe, efx->net_dev,
- "allocating special buffers %d-%d at %llx+%x "
- "(virt %p phys %llx)\n", buffer->index,
- buffer->index + buffer->entries - 1,
- (u64)buffer->dma_addr, len,
- buffer->addr, (u64)virt_to_phys(buffer->addr));
-
- return 0;
-}
-
-static void
-efx_free_special_buffer(struct efx_nic *efx, struct efx_special_buffer *buffer)
-{
- if (!buffer->addr)
- return;
-
- netif_dbg(efx, hw, efx->net_dev,
- "deallocating special buffers %d-%d at %llx+%x "
- "(virt %p phys %llx)\n", buffer->index,
- buffer->index + buffer->entries - 1,
- (u64)buffer->dma_addr, buffer->len,
- buffer->addr, (u64)virt_to_phys(buffer->addr));
-
- dma_free_coherent(&efx->pci_dev->dev, buffer->len, buffer->addr,
- buffer->dma_addr);
- buffer->addr = NULL;
- buffer->entries = 0;
-}
-
-/**************************************************************************
- *
* Generic buffer handling
- * These buffers are used for interrupt status and MAC stats
+ * These buffers are used for interrupt status, MAC stats, etc.
*
**************************************************************************/
int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer,
- unsigned int len)
+ unsigned int len, gfp_t gfp_flags)
{
- buffer->addr = pci_alloc_consistent(efx->pci_dev, len,
- &buffer->dma_addr);
+ buffer->addr = dma_zalloc_coherent(&efx->pci_dev->dev, len,
+ &buffer->dma_addr, gfp_flags);
if (!buffer->addr)
return -ENOMEM;
buffer->len = len;
- memset(buffer->addr, 0, len);
return 0;
}
void efx_nic_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer)
{
if (buffer->addr) {
- pci_free_consistent(efx->pci_dev, buffer->len,
- buffer->addr, buffer->dma_addr);
+ dma_free_coherent(&efx->pci_dev->dev, buffer->len,
+ buffer->addr, buffer->dma_addr);
buffer->addr = NULL;
}
}
-/**************************************************************************
- *
- * TX path
- *
- **************************************************************************/
-
-/* Returns a pointer to the specified transmit descriptor in the TX
- * descriptor queue belonging to the specified channel.
- */
-static inline efx_qword_t *
-efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
-{
- return ((efx_qword_t *) (tx_queue->txd.addr)) + index;
-}
-
-/* This writes to the TX_DESC_WPTR; write pointer for TX descriptor ring */
-static inline void efx_notify_tx_desc(struct efx_tx_queue *tx_queue)
-{
- unsigned write_ptr;
- efx_dword_t reg;
-
- write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
- EFX_POPULATE_DWORD_1(reg, FRF_AZ_TX_DESC_WPTR_DWORD, write_ptr);
- efx_writed_page(tx_queue->efx, &reg,
- FR_AZ_TX_DESC_UPD_DWORD_P0, tx_queue->queue);
-}
-
-/* Write pointer and first descriptor for TX descriptor ring */
-static inline void efx_push_tx_desc(struct efx_tx_queue *tx_queue,
- const efx_qword_t *txd)
-{
- unsigned write_ptr;
- efx_oword_t reg;
-
- BUILD_BUG_ON(FRF_AZ_TX_DESC_LBN != 0);
- BUILD_BUG_ON(FR_AA_TX_DESC_UPD_KER != FR_BZ_TX_DESC_UPD_P0);
-
- write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
- EFX_POPULATE_OWORD_2(reg, FRF_AZ_TX_DESC_PUSH_CMD, true,
- FRF_AZ_TX_DESC_WPTR, write_ptr);
- reg.qword[0] = *txd;
- efx_writeo_page(tx_queue->efx, &reg,
- FR_BZ_TX_DESC_UPD_P0, tx_queue->queue);
-}
-
-static inline bool
-efx_may_push_tx_desc(struct efx_tx_queue *tx_queue, unsigned int write_count)
-{
- unsigned empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count);
-
- if (empty_read_count == 0)
- return false;
-
- tx_queue->empty_read_count = 0;
- return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0;
-}
-
-/* For each entry inserted into the software descriptor ring, create a
- * descriptor in the hardware TX descriptor ring (in host memory), and
- * write a doorbell.
- */
-void efx_nic_push_buffers(struct efx_tx_queue *tx_queue)
-{
-
- struct efx_tx_buffer *buffer;
- efx_qword_t *txd;
- unsigned write_ptr;
- unsigned old_write_count = tx_queue->write_count;
-
- BUG_ON(tx_queue->write_count == tx_queue->insert_count);
-
- do {
- write_ptr = tx_queue->write_count & tx_queue->ptr_mask;
- buffer = &tx_queue->buffer[write_ptr];
- txd = efx_tx_desc(tx_queue, write_ptr);
- ++tx_queue->write_count;
-
- /* Create TX descriptor ring entry */
- EFX_POPULATE_QWORD_4(*txd,
- FSF_AZ_TX_KER_CONT, buffer->continuation,
- FSF_AZ_TX_KER_BYTE_COUNT, buffer->len,
- FSF_AZ_TX_KER_BUF_REGION, 0,
- FSF_AZ_TX_KER_BUF_ADDR, buffer->dma_addr);
- } while (tx_queue->write_count != tx_queue->insert_count);
-
- wmb(); /* Ensure descriptors are written before they are fetched */
-
- if (efx_may_push_tx_desc(tx_queue, old_write_count)) {
- txd = efx_tx_desc(tx_queue,
- old_write_count & tx_queue->ptr_mask);
- efx_push_tx_desc(tx_queue, txd);
- ++tx_queue->pushes;
- } else {
- efx_notify_tx_desc(tx_queue);
- }
-}
-
-/* Allocate hardware resources for a TX queue */
-int efx_nic_probe_tx(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
- unsigned entries;
-
- entries = tx_queue->ptr_mask + 1;
- return efx_alloc_special_buffer(efx, &tx_queue->txd,
- entries * sizeof(efx_qword_t));
-}
-
-void efx_nic_init_tx(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
- efx_oword_t reg;
-
- tx_queue->flushed = FLUSH_NONE;
-
- /* Pin TX descriptor ring */
- efx_init_special_buffer(efx, &tx_queue->txd);
-
- /* Push TX descriptor ring to card */
- EFX_POPULATE_OWORD_10(reg,
- FRF_AZ_TX_DESCQ_EN, 1,
- FRF_AZ_TX_ISCSI_DDIG_EN, 0,
- FRF_AZ_TX_ISCSI_HDIG_EN, 0,
- FRF_AZ_TX_DESCQ_BUF_BASE_ID, tx_queue->txd.index,
- FRF_AZ_TX_DESCQ_EVQ_ID,
- tx_queue->channel->channel,
- FRF_AZ_TX_DESCQ_OWNER_ID, 0,
- FRF_AZ_TX_DESCQ_LABEL, tx_queue->queue,
- FRF_AZ_TX_DESCQ_SIZE,
- __ffs(tx_queue->txd.entries),
- FRF_AZ_TX_DESCQ_TYPE, 0,
- FRF_BZ_TX_NON_IP_DROP_DIS, 1);
-
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
- int csum = tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD;
- EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_IP_CHKSM_DIS, !csum);
- EFX_SET_OWORD_FIELD(reg, FRF_BZ_TX_TCP_CHKSM_DIS,
- !csum);
- }
-
- efx_writeo_table(efx, &reg, efx->type->txd_ptr_tbl_base,
- tx_queue->queue);
-
- if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) {
- /* Only 128 bits in this register */
- BUILD_BUG_ON(EFX_MAX_TX_QUEUES > 128);
-
- efx_reado(efx, &reg, FR_AA_TX_CHKSM_CFG);
- if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
- clear_bit_le(tx_queue->queue, (void *)&reg);
- else
- set_bit_le(tx_queue->queue, (void *)&reg);
- efx_writeo(efx, &reg, FR_AA_TX_CHKSM_CFG);
- }
-
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
- EFX_POPULATE_OWORD_1(reg,
- FRF_BZ_TX_PACE,
- (tx_queue->queue & EFX_TXQ_TYPE_HIGHPRI) ?
- FFE_BZ_TX_PACE_OFF :
- FFE_BZ_TX_PACE_RESERVED);
- efx_writeo_table(efx, &reg, FR_BZ_TX_PACE_TBL,
- tx_queue->queue);
- }
-}
-
-static void efx_flush_tx_queue(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
- efx_oword_t tx_flush_descq;
-
- tx_queue->flushed = FLUSH_PENDING;
-
- /* Post a flush command */
- EFX_POPULATE_OWORD_2(tx_flush_descq,
- FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
- FRF_AZ_TX_FLUSH_DESCQ, tx_queue->queue);
- efx_writeo(efx, &tx_flush_descq, FR_AZ_TX_FLUSH_DESCQ);
-}
-
-void efx_nic_fini_tx(struct efx_tx_queue *tx_queue)
-{
- struct efx_nic *efx = tx_queue->efx;
- efx_oword_t tx_desc_ptr;
-
- /* The queue should have been flushed */
- WARN_ON(tx_queue->flushed != FLUSH_DONE);
-
- /* Remove TX descriptor ring from card */
- EFX_ZERO_OWORD(tx_desc_ptr);
- efx_writeo_table(efx, &tx_desc_ptr, efx->type->txd_ptr_tbl_base,
- tx_queue->queue);
-
- /* Unpin TX descriptor ring */
- efx_fini_special_buffer(efx, &tx_queue->txd);
-}
-
-/* Free buffers backing TX queue */
-void efx_nic_remove_tx(struct efx_tx_queue *tx_queue)
-{
- efx_free_special_buffer(tx_queue->efx, &tx_queue->txd);
-}
-
-/**************************************************************************
- *
- * RX path
- *
- **************************************************************************/
-
-/* Returns a pointer to the specified descriptor in the RX descriptor queue */
-static inline efx_qword_t *
-efx_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
-{
- return ((efx_qword_t *) (rx_queue->rxd.addr)) + index;
-}
-
-/* This creates an entry in the RX descriptor queue */
-static inline void
-efx_build_rx_desc(struct efx_rx_queue *rx_queue, unsigned index)
-{
- struct efx_rx_buffer *rx_buf;
- efx_qword_t *rxd;
-
- rxd = efx_rx_desc(rx_queue, index);
- rx_buf = efx_rx_buffer(rx_queue, index);
- EFX_POPULATE_QWORD_3(*rxd,
- FSF_AZ_RX_KER_BUF_SIZE,
- rx_buf->len -
- rx_queue->efx->type->rx_buffer_padding,
- FSF_AZ_RX_KER_BUF_REGION, 0,
- FSF_AZ_RX_KER_BUF_ADDR, rx_buf->dma_addr);
-}
-
-/* This writes to the RX_DESC_WPTR register for the specified receive
- * descriptor ring.
- */
-void efx_nic_notify_rx_desc(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- efx_dword_t reg;
- unsigned write_ptr;
-
- while (rx_queue->notified_count != rx_queue->added_count) {
- efx_build_rx_desc(
- rx_queue,
- rx_queue->notified_count & rx_queue->ptr_mask);
- ++rx_queue->notified_count;
- }
-
- wmb();
- write_ptr = rx_queue->added_count & rx_queue->ptr_mask;
- EFX_POPULATE_DWORD_1(reg, FRF_AZ_RX_DESC_WPTR_DWORD, write_ptr);
- efx_writed_page(efx, &reg, FR_AZ_RX_DESC_UPD_DWORD_P0,
- efx_rx_queue_index(rx_queue));
-}
-
-int efx_nic_probe_rx(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- unsigned entries;
-
- entries = rx_queue->ptr_mask + 1;
- return efx_alloc_special_buffer(efx, &rx_queue->rxd,
- entries * sizeof(efx_qword_t));
-}
-
-void efx_nic_init_rx(struct efx_rx_queue *rx_queue)
-{
- efx_oword_t rx_desc_ptr;
- struct efx_nic *efx = rx_queue->efx;
- bool is_b0 = efx_nic_rev(efx) >= EFX_REV_FALCON_B0;
- bool iscsi_digest_en = is_b0;
-
- netif_dbg(efx, hw, efx->net_dev,
- "RX queue %d ring in special buffers %d-%d\n",
- efx_rx_queue_index(rx_queue), rx_queue->rxd.index,
- rx_queue->rxd.index + rx_queue->rxd.entries - 1);
-
- rx_queue->flushed = FLUSH_NONE;
-
- /* Pin RX descriptor ring */
- efx_init_special_buffer(efx, &rx_queue->rxd);
-
- /* Push RX descriptor ring to card */
- EFX_POPULATE_OWORD_10(rx_desc_ptr,
- FRF_AZ_RX_ISCSI_DDIG_EN, iscsi_digest_en,
- FRF_AZ_RX_ISCSI_HDIG_EN, iscsi_digest_en,
- FRF_AZ_RX_DESCQ_BUF_BASE_ID, rx_queue->rxd.index,
- FRF_AZ_RX_DESCQ_EVQ_ID,
- efx_rx_queue_channel(rx_queue)->channel,
- FRF_AZ_RX_DESCQ_OWNER_ID, 0,
- FRF_AZ_RX_DESCQ_LABEL,
- efx_rx_queue_index(rx_queue),
- FRF_AZ_RX_DESCQ_SIZE,
- __ffs(rx_queue->rxd.entries),
- FRF_AZ_RX_DESCQ_TYPE, 0 /* kernel queue */ ,
- /* For >=B0 this is scatter so disable */
- FRF_AZ_RX_DESCQ_JUMBO, !is_b0,
- FRF_AZ_RX_DESCQ_EN, 1);
- efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
- efx_rx_queue_index(rx_queue));
-}
-
-static void efx_flush_rx_queue(struct efx_rx_queue *rx_queue)
-{
- struct efx_nic *efx = rx_queue->efx;
- efx_oword_t rx_flush_descq;
-
- rx_queue->flushed = FLUSH_PENDING;
-
- /* Post a flush command */
- EFX_POPULATE_OWORD_2(rx_flush_descq,
- FRF_AZ_RX_FLUSH_DESCQ_CMD, 1,
- FRF_AZ_RX_FLUSH_DESCQ,
- efx_rx_queue_index(rx_queue));
- efx_writeo(efx, &rx_flush_descq, FR_AZ_RX_FLUSH_DESCQ);
-}
-
-void efx_nic_fini_rx(struct efx_rx_queue *rx_queue)
-{
- efx_oword_t rx_desc_ptr;
- struct efx_nic *efx = rx_queue->efx;
-
- /* The queue should already have been flushed */
- WARN_ON(rx_queue->flushed != FLUSH_DONE);
-
- /* Remove RX descriptor ring from card */
- EFX_ZERO_OWORD(rx_desc_ptr);
- efx_writeo_table(efx, &rx_desc_ptr, efx->type->rxd_ptr_tbl_base,
- efx_rx_queue_index(rx_queue));
-
- /* Unpin RX descriptor ring */
- efx_fini_special_buffer(efx, &rx_queue->rxd);
-}
-
-/* Free buffers backing RX queue */
-void efx_nic_remove_rx(struct efx_rx_queue *rx_queue)
-{
- efx_free_special_buffer(rx_queue->efx, &rx_queue->rxd);
-}
-
-/**************************************************************************
- *
- * Event queue processing
- * Event queues are processed by per-channel tasklets.
- *
- **************************************************************************/
-
-/* Update a channel's event queue's read pointer (RPTR) register
- *
- * This writes the EVQ_RPTR_REG register for the specified channel's
- * event queue.
- */
-void efx_nic_eventq_read_ack(struct efx_channel *channel)
-{
- efx_dword_t reg;
- struct efx_nic *efx = channel->efx;
-
- EFX_POPULATE_DWORD_1(reg, FRF_AZ_EVQ_RPTR,
- channel->eventq_read_ptr & channel->eventq_mask);
- efx_writed_table(efx, &reg, efx->type->evq_rptr_tbl_base,
- channel->channel);
-}
-
-/* Use HW to insert a SW defined event */
-static void efx_generate_event(struct efx_channel *channel, efx_qword_t *event)
-{
- efx_oword_t drv_ev_reg;
-
- BUILD_BUG_ON(FRF_AZ_DRV_EV_DATA_LBN != 0 ||
- FRF_AZ_DRV_EV_DATA_WIDTH != 64);
- drv_ev_reg.u32[0] = event->u32[0];
- drv_ev_reg.u32[1] = event->u32[1];
- drv_ev_reg.u32[2] = 0;
- drv_ev_reg.u32[3] = 0;
- EFX_SET_OWORD_FIELD(drv_ev_reg, FRF_AZ_DRV_EV_QID, channel->channel);
- efx_writeo(channel->efx, &drv_ev_reg, FR_AZ_DRV_EV);
-}
-
-/* Handle a transmit completion event
- *
- * The NIC batches TX completion events; the message we receive is of
- * the form "complete all TX events up to this index".
- */
-static int
-efx_handle_tx_event(struct efx_channel *channel, efx_qword_t *event)
-{
- unsigned int tx_ev_desc_ptr;
- unsigned int tx_ev_q_label;
- struct efx_tx_queue *tx_queue;
- struct efx_nic *efx = channel->efx;
- int tx_packets = 0;
-
- if (likely(EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_COMP))) {
- /* Transmit completion */
- tx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_DESC_PTR);
- tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
- tx_queue = efx_channel_get_tx_queue(
- channel, tx_ev_q_label % EFX_TXQ_TYPES);
- tx_packets = ((tx_ev_desc_ptr - tx_queue->read_count) &
- tx_queue->ptr_mask);
- channel->irq_mod_score += tx_packets;
- efx_xmit_done(tx_queue, tx_ev_desc_ptr);
- } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_WQ_FF_FULL)) {
- /* Rewrite the FIFO write pointer */
- tx_ev_q_label = EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_Q_LABEL);
- tx_queue = efx_channel_get_tx_queue(
- channel, tx_ev_q_label % EFX_TXQ_TYPES);
-
- if (efx_dev_registered(efx))
- netif_tx_lock(efx->net_dev);
- efx_notify_tx_desc(tx_queue);
- if (efx_dev_registered(efx))
- netif_tx_unlock(efx->net_dev);
- } else if (EFX_QWORD_FIELD(*event, FSF_AZ_TX_EV_PKT_ERR) &&
- EFX_WORKAROUND_10727(efx)) {
- efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH);
- } else {
- netif_err(efx, tx_err, efx->net_dev,
- "channel %d unexpected TX event "
- EFX_QWORD_FMT"\n", channel->channel,
- EFX_QWORD_VAL(*event));
- }
-
- return tx_packets;
-}
-
-/* Detect errors included in the rx_evt_pkt_ok bit. */
-static void efx_handle_rx_not_ok(struct efx_rx_queue *rx_queue,
- const efx_qword_t *event,
- bool *rx_ev_pkt_ok,
- bool *discard)
-{
- struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
- struct efx_nic *efx = rx_queue->efx;
- bool rx_ev_buf_owner_id_err, rx_ev_ip_hdr_chksum_err;
- bool rx_ev_tcp_udp_chksum_err, rx_ev_eth_crc_err;
- bool rx_ev_frm_trunc, rx_ev_drib_nib, rx_ev_tobe_disc;
- bool rx_ev_other_err, rx_ev_pause_frm;
- bool rx_ev_hdr_type, rx_ev_mcast_pkt;
- unsigned rx_ev_pkt_type;
-
- rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
- rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
- rx_ev_tobe_disc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_TOBE_DISC);
- rx_ev_pkt_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_TYPE);
- rx_ev_buf_owner_id_err = EFX_QWORD_FIELD(*event,
- FSF_AZ_RX_EV_BUF_OWNER_ID_ERR);
- rx_ev_ip_hdr_chksum_err = EFX_QWORD_FIELD(*event,
- FSF_AZ_RX_EV_IP_HDR_CHKSUM_ERR);
- rx_ev_tcp_udp_chksum_err = EFX_QWORD_FIELD(*event,
- FSF_AZ_RX_EV_TCP_UDP_CHKSUM_ERR);
- rx_ev_eth_crc_err = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_ETH_CRC_ERR);
- rx_ev_frm_trunc = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_FRM_TRUNC);
- rx_ev_drib_nib = ((efx_nic_rev(efx) >= EFX_REV_FALCON_B0) ?
- 0 : EFX_QWORD_FIELD(*event, FSF_AA_RX_EV_DRIB_NIB));
- rx_ev_pause_frm = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PAUSE_FRM_ERR);
-
- /* Every error apart from tobe_disc and pause_frm */
- rx_ev_other_err = (rx_ev_drib_nib | rx_ev_tcp_udp_chksum_err |
- rx_ev_buf_owner_id_err | rx_ev_eth_crc_err |
- rx_ev_frm_trunc | rx_ev_ip_hdr_chksum_err);
-
- /* Count errors that are not in MAC stats. Ignore expected
- * checksum errors during self-test. */
- if (rx_ev_frm_trunc)
- ++channel->n_rx_frm_trunc;
- else if (rx_ev_tobe_disc)
- ++channel->n_rx_tobe_disc;
- else if (!efx->loopback_selftest) {
- if (rx_ev_ip_hdr_chksum_err)
- ++channel->n_rx_ip_hdr_chksum_err;
- else if (rx_ev_tcp_udp_chksum_err)
- ++channel->n_rx_tcp_udp_chksum_err;
- }
-
- /* The frame must be discarded if any of these are true. */
- *discard = (rx_ev_eth_crc_err | rx_ev_frm_trunc | rx_ev_drib_nib |
- rx_ev_tobe_disc | rx_ev_pause_frm);
-
- /* TOBE_DISC is expected on unicast mismatches; don't print out an
- * error message. FRM_TRUNC indicates RXDP dropped the packet due
- * to a FIFO overflow.
- */
-#ifdef EFX_ENABLE_DEBUG
- if (rx_ev_other_err && net_ratelimit()) {
- netif_dbg(efx, rx_err, efx->net_dev,
- " RX queue %d unexpected RX event "
- EFX_QWORD_FMT "%s%s%s%s%s%s%s%s\n",
- efx_rx_queue_index(rx_queue), EFX_QWORD_VAL(*event),
- rx_ev_buf_owner_id_err ? " [OWNER_ID_ERR]" : "",
- rx_ev_ip_hdr_chksum_err ?
- " [IP_HDR_CHKSUM_ERR]" : "",
- rx_ev_tcp_udp_chksum_err ?
- " [TCP_UDP_CHKSUM_ERR]" : "",
- rx_ev_eth_crc_err ? " [ETH_CRC_ERR]" : "",
- rx_ev_frm_trunc ? " [FRM_TRUNC]" : "",
- rx_ev_drib_nib ? " [DRIB_NIB]" : "",
- rx_ev_tobe_disc ? " [TOBE_DISC]" : "",
- rx_ev_pause_frm ? " [PAUSE]" : "");
- }
-#endif
-}
-
-/* Handle receive events that are not in-order. */
-static void
-efx_handle_rx_bad_index(struct efx_rx_queue *rx_queue, unsigned index)
-{
- struct efx_nic *efx = rx_queue->efx;
- unsigned expected, dropped;
-
- expected = rx_queue->removed_count & rx_queue->ptr_mask;
- dropped = (index - expected) & rx_queue->ptr_mask;
- netif_info(efx, rx_err, efx->net_dev,
- "dropped %d events (index=%d expected=%d)\n",
- dropped, index, expected);
-
- efx_schedule_reset(efx, EFX_WORKAROUND_5676(efx) ?
- RESET_TYPE_RX_RECOVERY : RESET_TYPE_DISABLE);
-}
-
-/* Handle a packet received event
- *
- * The NIC gives a "discard" flag if it's a unicast packet with the
- * wrong destination address
- * Also "is multicast" and "matches multicast filter" flags can be used to
- * discard non-matching multicast packets.
- */
-static void
-efx_handle_rx_event(struct efx_channel *channel, const efx_qword_t *event)
-{
- unsigned int rx_ev_desc_ptr, rx_ev_byte_cnt;
- unsigned int rx_ev_hdr_type, rx_ev_mcast_pkt;
- unsigned expected_ptr;
- bool rx_ev_pkt_ok, discard = false, checksummed;
- struct efx_rx_queue *rx_queue;
-
- /* Basic packet information */
- rx_ev_byte_cnt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_BYTE_CNT);
- rx_ev_pkt_ok = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_PKT_OK);
- rx_ev_hdr_type = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_HDR_TYPE);
- WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_JUMBO_CONT));
- WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_SOP) != 1);
- WARN_ON(EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_Q_LABEL) !=
- channel->channel);
-
- rx_queue = efx_channel_get_rx_queue(channel);
-
- rx_ev_desc_ptr = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_DESC_PTR);
- expected_ptr = rx_queue->removed_count & rx_queue->ptr_mask;
- if (unlikely(rx_ev_desc_ptr != expected_ptr))
- efx_handle_rx_bad_index(rx_queue, rx_ev_desc_ptr);
-
- if (likely(rx_ev_pkt_ok)) {
- /* If packet is marked as OK and packet type is TCP/IP or
- * UDP/IP, then we can rely on the hardware checksum.
- */
- checksummed =
- rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_TCP ||
- rx_ev_hdr_type == FSE_CZ_RX_EV_HDR_TYPE_IPV4V6_UDP;
- } else {
- efx_handle_rx_not_ok(rx_queue, event, &rx_ev_pkt_ok, &discard);
- checksummed = false;
- }
-
- /* Detect multicast packets that didn't match the filter */
- rx_ev_mcast_pkt = EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_PKT);
- if (rx_ev_mcast_pkt) {
- unsigned int rx_ev_mcast_hash_match =
- EFX_QWORD_FIELD(*event, FSF_AZ_RX_EV_MCAST_HASH_MATCH);
-
- if (unlikely(!rx_ev_mcast_hash_match)) {
- ++channel->n_rx_mcast_mismatch;
- discard = true;
- }
- }
-
- channel->irq_mod_score += 2;
-
- /* Handle received packet */
- efx_rx_packet(rx_queue, rx_ev_desc_ptr, rx_ev_byte_cnt,
- checksummed, discard);
-}
-
-static void
-efx_handle_generated_event(struct efx_channel *channel, efx_qword_t *event)
-{
- struct efx_nic *efx = channel->efx;
- unsigned code;
-
- code = EFX_QWORD_FIELD(*event, FSF_AZ_DRV_GEN_EV_MAGIC);
- if (code == EFX_CHANNEL_MAGIC_TEST(channel))
- ; /* ignore */
- else if (code == EFX_CHANNEL_MAGIC_FILL(channel))
- /* The queue must be empty, so we won't receive any rx
- * events, so efx_process_channel() won't refill the
- * queue. Refill it here */
- efx_fast_push_rx_descriptors(efx_channel_get_rx_queue(channel));
- else
- netif_dbg(efx, hw, efx->net_dev, "channel %d received "
- "generated event "EFX_QWORD_FMT"\n",
- channel->channel, EFX_QWORD_VAL(*event));
-}
-
-static void
-efx_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
-{
- struct efx_nic *efx = channel->efx;
- unsigned int ev_sub_code;
- unsigned int ev_sub_data;
-
- ev_sub_code = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBCODE);
- ev_sub_data = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);
-
- switch (ev_sub_code) {
- case FSE_AZ_TX_DESCQ_FLS_DONE_EV:
- netif_vdbg(efx, hw, efx->net_dev, "channel %d TXQ %d flushed\n",
- channel->channel, ev_sub_data);
- break;
- case FSE_AZ_RX_DESCQ_FLS_DONE_EV:
- netif_vdbg(efx, hw, efx->net_dev, "channel %d RXQ %d flushed\n",
- channel->channel, ev_sub_data);
- break;
- case FSE_AZ_EVQ_INIT_DONE_EV:
- netif_dbg(efx, hw, efx->net_dev,
- "channel %d EVQ %d initialised\n",
- channel->channel, ev_sub_data);
- break;
- case FSE_AZ_SRM_UPD_DONE_EV:
- netif_vdbg(efx, hw, efx->net_dev,
- "channel %d SRAM update done\n", channel->channel);
- break;
- case FSE_AZ_WAKE_UP_EV:
- netif_vdbg(efx, hw, efx->net_dev,
- "channel %d RXQ %d wakeup event\n",
- channel->channel, ev_sub_data);
- break;
- case FSE_AZ_TIMER_EV:
- netif_vdbg(efx, hw, efx->net_dev,
- "channel %d RX queue %d timer expired\n",
- channel->channel, ev_sub_data);
- break;
- case FSE_AA_RX_RECOVER_EV:
- netif_err(efx, rx_err, efx->net_dev,
- "channel %d seen DRIVER RX_RESET event. "
- "Resetting.\n", channel->channel);
- atomic_inc(&efx->rx_reset);
- efx_schedule_reset(efx,
- EFX_WORKAROUND_6555(efx) ?
- RESET_TYPE_RX_RECOVERY :
- RESET_TYPE_DISABLE);
- break;
- case FSE_BZ_RX_DSC_ERROR_EV:
- netif_err(efx, rx_err, efx->net_dev,
- "RX DMA Q %d reports descriptor fetch error."
- " RX Q %d is disabled.\n", ev_sub_data, ev_sub_data);
- efx_schedule_reset(efx, RESET_TYPE_RX_DESC_FETCH);
- break;
- case FSE_BZ_TX_DSC_ERROR_EV:
- netif_err(efx, tx_err, efx->net_dev,
- "TX DMA Q %d reports descriptor fetch error."
- " TX Q %d is disabled.\n", ev_sub_data, ev_sub_data);
- efx_schedule_reset(efx, RESET_TYPE_TX_DESC_FETCH);
- break;
- default:
- netif_vdbg(efx, hw, efx->net_dev,
- "channel %d unknown driver event code %d "
- "data %04x\n", channel->channel, ev_sub_code,
- ev_sub_data);
- break;
- }
-}
-
-int efx_nic_process_eventq(struct efx_channel *channel, int budget)
-{
- struct efx_nic *efx = channel->efx;
- unsigned int read_ptr;
- efx_qword_t event, *p_event;
- int ev_code;
- int tx_packets = 0;
- int spent = 0;
-
- read_ptr = channel->eventq_read_ptr;
-
- for (;;) {
- p_event = efx_event(channel, read_ptr);
- event = *p_event;
-
- if (!efx_event_present(&event))
- /* End of events */
- break;
-
- netif_vdbg(channel->efx, intr, channel->efx->net_dev,
- "channel %d event is "EFX_QWORD_FMT"\n",
- channel->channel, EFX_QWORD_VAL(event));
-
- /* Clear this event by marking it all ones */
- EFX_SET_QWORD(*p_event);
-
- ++read_ptr;
-
- ev_code = EFX_QWORD_FIELD(event, FSF_AZ_EV_CODE);
-
- switch (ev_code) {
- case FSE_AZ_EV_CODE_RX_EV:
- efx_handle_rx_event(channel, &event);
- if (++spent == budget)
- goto out;
- break;
- case FSE_AZ_EV_CODE_TX_EV:
- tx_packets += efx_handle_tx_event(channel, &event);
- if (tx_packets > efx->txq_entries) {
- spent = budget;
- goto out;
- }
- break;
- case FSE_AZ_EV_CODE_DRV_GEN_EV:
- efx_handle_generated_event(channel, &event);
- break;
- case FSE_AZ_EV_CODE_DRIVER_EV:
- efx_handle_driver_event(channel, &event);
- break;
- case FSE_CZ_EV_CODE_MCDI_EV:
- efx_mcdi_process_event(channel, &event);
- break;
- case FSE_AZ_EV_CODE_GLOBAL_EV:
- if (efx->type->handle_global_event &&
- efx->type->handle_global_event(channel, &event))
- break;
- /* else fall through */
- default:
- netif_err(channel->efx, hw, channel->efx->net_dev,
- "channel %d unknown event type %d (data "
- EFX_QWORD_FMT ")\n", channel->channel,
- ev_code, EFX_QWORD_VAL(event));
- }
- }
-
-out:
- channel->eventq_read_ptr = read_ptr;
- return spent;
-}
-
/* Check whether an event is present in the eventq at the current
* read pointer. Only useful for self-test.
*/
@@ -1068,464 +59,18 @@ bool efx_nic_event_present(struct efx_channel *channel)
return efx_event_present(efx_event(channel, channel->eventq_read_ptr));
}
-/* Allocate buffer table entries for event queue */
-int efx_nic_probe_eventq(struct efx_channel *channel)
-{
- struct efx_nic *efx = channel->efx;
- unsigned entries;
-
- entries = channel->eventq_mask + 1;
- return efx_alloc_special_buffer(efx, &channel->eventq,
- entries * sizeof(efx_qword_t));
-}
-
-void efx_nic_init_eventq(struct efx_channel *channel)
-{
- efx_oword_t reg;
- struct efx_nic *efx = channel->efx;
-
- netif_dbg(efx, hw, efx->net_dev,
- "channel %d event queue in special buffers %d-%d\n",
- channel->channel, channel->eventq.index,
- channel->eventq.index + channel->eventq.entries - 1);
-
- if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0) {
- EFX_POPULATE_OWORD_3(reg,
- FRF_CZ_TIMER_Q_EN, 1,
- FRF_CZ_HOST_NOTIFY_MODE, 0,
- FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
- efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);
- }
-
- /* Pin event queue buffer */
- efx_init_special_buffer(efx, &channel->eventq);
-
- /* Fill event queue with all ones (i.e. empty events) */
- memset(channel->eventq.addr, 0xff, channel->eventq.len);
-
- /* Push event queue to card */
- EFX_POPULATE_OWORD_3(reg,
- FRF_AZ_EVQ_EN, 1,
- FRF_AZ_EVQ_SIZE, __ffs(channel->eventq.entries),
- FRF_AZ_EVQ_BUF_BASE_ID, channel->eventq.index);
- efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
- channel->channel);
-
- efx->type->push_irq_moderation(channel);
-}
-
-void efx_nic_fini_eventq(struct efx_channel *channel)
-{
- efx_oword_t reg;
- struct efx_nic *efx = channel->efx;
-
- /* Remove event queue from card */
- EFX_ZERO_OWORD(reg);
- efx_writeo_table(efx, &reg, efx->type->evq_ptr_tbl_base,
- channel->channel);
- if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
- efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, channel->channel);
-
- /* Unpin event queue */
- efx_fini_special_buffer(efx, &channel->eventq);
-}
-
-/* Free buffers backing event queue */
-void efx_nic_remove_eventq(struct efx_channel *channel)
-{
- efx_free_special_buffer(channel->efx, &channel->eventq);
-}
-
-
-void efx_nic_generate_test_event(struct efx_channel *channel)
-{
- unsigned int magic = EFX_CHANNEL_MAGIC_TEST(channel);
- efx_qword_t test_event;
-
- EFX_POPULATE_QWORD_2(test_event, FSF_AZ_EV_CODE,
- FSE_AZ_EV_CODE_DRV_GEN_EV,
- FSF_AZ_DRV_GEN_EV_MAGIC, magic);
- efx_generate_event(channel, &test_event);
-}
-
-void efx_nic_generate_fill_event(struct efx_channel *channel)
-{
- unsigned int magic = EFX_CHANNEL_MAGIC_FILL(channel);
- efx_qword_t test_event;
-
- EFX_POPULATE_QWORD_2(test_event, FSF_AZ_EV_CODE,
- FSE_AZ_EV_CODE_DRV_GEN_EV,
- FSF_AZ_DRV_GEN_EV_MAGIC, magic);
- efx_generate_event(channel, &test_event);
-}
-
-/**************************************************************************
- *
- * Flush handling
- *
- **************************************************************************/
-
-
-static void efx_poll_flush_events(struct efx_nic *efx)
-{
- struct efx_channel *channel = efx_get_channel(efx, 0);
- struct efx_tx_queue *tx_queue;
- struct efx_rx_queue *rx_queue;
- unsigned int read_ptr = channel->eventq_read_ptr;
- unsigned int end_ptr = read_ptr + channel->eventq_mask - 1;
-
- do {
- efx_qword_t *event = efx_event(channel, read_ptr);
- int ev_code, ev_sub_code, ev_queue;
- bool ev_failed;
-
- if (!efx_event_present(event))
- break;
-
- ev_code = EFX_QWORD_FIELD(*event, FSF_AZ_EV_CODE);
- ev_sub_code = EFX_QWORD_FIELD(*event,
- FSF_AZ_DRIVER_EV_SUBCODE);
- if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV &&
- ev_sub_code == FSE_AZ_TX_DESCQ_FLS_DONE_EV) {
- ev_queue = EFX_QWORD_FIELD(*event,
- FSF_AZ_DRIVER_EV_SUBDATA);
- if (ev_queue < EFX_TXQ_TYPES * efx->n_tx_channels) {
- tx_queue = efx_get_tx_queue(
- efx, ev_queue / EFX_TXQ_TYPES,
- ev_queue % EFX_TXQ_TYPES);
- tx_queue->flushed = FLUSH_DONE;
- }
- } else if (ev_code == FSE_AZ_EV_CODE_DRIVER_EV &&
- ev_sub_code == FSE_AZ_RX_DESCQ_FLS_DONE_EV) {
- ev_queue = EFX_QWORD_FIELD(
- *event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
- ev_failed = EFX_QWORD_FIELD(
- *event, FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
- if (ev_queue < efx->n_rx_channels) {
- rx_queue = efx_get_rx_queue(efx, ev_queue);
- rx_queue->flushed =
- ev_failed ? FLUSH_FAILED : FLUSH_DONE;
- }
- }
-
- /* We're about to destroy the queue anyway, so
- * it's ok to throw away every non-flush event */
- EFX_SET_QWORD(*event);
-
- ++read_ptr;
- } while (read_ptr != end_ptr);
-
- channel->eventq_read_ptr = read_ptr;
-}
-
-/* Handle tx and rx flushes at the same time, since they run in
- * parallel in the hardware and there's no reason for us to
- * serialise them */
-int efx_nic_flush_queues(struct efx_nic *efx)
-{
- struct efx_channel *channel;
- struct efx_rx_queue *rx_queue;
- struct efx_tx_queue *tx_queue;
- int i, tx_pending, rx_pending;
-
- /* If necessary prepare the hardware for flushing */
- efx->type->prepare_flush(efx);
-
- /* Flush all tx queues in parallel */
- efx_for_each_channel(channel, efx) {
- efx_for_each_possible_channel_tx_queue(tx_queue, channel) {
- if (tx_queue->initialised)
- efx_flush_tx_queue(tx_queue);
- }
- }
-
- /* The hardware supports four concurrent rx flushes, each of which may
- * need to be retried if there is an outstanding descriptor fetch */
- for (i = 0; i < EFX_FLUSH_POLL_COUNT; ++i) {
- rx_pending = tx_pending = 0;
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- if (rx_queue->flushed == FLUSH_PENDING)
- ++rx_pending;
- }
- }
- efx_for_each_channel(channel, efx) {
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- if (rx_pending == EFX_RX_FLUSH_COUNT)
- break;
- if (rx_queue->flushed == FLUSH_FAILED ||
- rx_queue->flushed == FLUSH_NONE) {
- efx_flush_rx_queue(rx_queue);
- ++rx_pending;
- }
- }
- efx_for_each_possible_channel_tx_queue(tx_queue, channel) {
- if (tx_queue->initialised &&
- tx_queue->flushed != FLUSH_DONE)
- ++tx_pending;
- }
- }
-
- if (rx_pending == 0 && tx_pending == 0)
- return 0;
-
- msleep(EFX_FLUSH_INTERVAL);
- efx_poll_flush_events(efx);
- }
-
- /* Mark the queues as all flushed. We're going to return failure
- * leading to a reset, or fake up success anyway */
- efx_for_each_channel(channel, efx) {
- efx_for_each_possible_channel_tx_queue(tx_queue, channel) {
- if (tx_queue->initialised &&
- tx_queue->flushed != FLUSH_DONE)
- netif_err(efx, hw, efx->net_dev,
- "tx queue %d flush command timed out\n",
- tx_queue->queue);
- tx_queue->flushed = FLUSH_DONE;
- }
- efx_for_each_channel_rx_queue(rx_queue, channel) {
- if (rx_queue->flushed != FLUSH_DONE)
- netif_err(efx, hw, efx->net_dev,
- "rx queue %d flush command timed out\n",
- efx_rx_queue_index(rx_queue));
- rx_queue->flushed = FLUSH_DONE;
- }
- }
-
- return -ETIMEDOUT;
-}
-
-/**************************************************************************
- *
- * Hardware interrupts
- * The hardware interrupt handler does very little work; all the event
- * queue processing is carried out by per-channel tasklets.
- *
- **************************************************************************/
-
-/* Enable/disable/generate interrupts */
-static inline void efx_nic_interrupts(struct efx_nic *efx,
- bool enabled, bool force)
-{
- efx_oword_t int_en_reg_ker;
-
- EFX_POPULATE_OWORD_3(int_en_reg_ker,
- FRF_AZ_KER_INT_LEVE_SEL, efx->fatal_irq_level,
- FRF_AZ_KER_INT_KER, force,
- FRF_AZ_DRV_INT_EN_KER, enabled);
- efx_writeo(efx, &int_en_reg_ker, FR_AZ_INT_EN_KER);
-}
-
-void efx_nic_enable_interrupts(struct efx_nic *efx)
-{
- struct efx_channel *channel;
-
- EFX_ZERO_OWORD(*((efx_oword_t *) efx->irq_status.addr));
- wmb(); /* Ensure interrupt vector is clear before interrupts enabled */
-
- /* Enable interrupts */
- efx_nic_interrupts(efx, true, false);
-
- /* Force processing of all the channels to get the EVQ RPTRs up to
- date */
- efx_for_each_channel(channel, efx)
- efx_schedule_channel(channel);
-}
-
-void efx_nic_disable_interrupts(struct efx_nic *efx)
-{
- /* Disable interrupts */
- efx_nic_interrupts(efx, false, false);
-}
-
-/* Generate a test interrupt
- * Interrupt must already have been enabled, otherwise nasty things
- * may happen.
- */
-void efx_nic_generate_interrupt(struct efx_nic *efx)
+void efx_nic_event_test_start(struct efx_channel *channel)
{
- efx_nic_interrupts(efx, true, true);
+ channel->event_test_cpu = -1;
+ smp_wmb();
+ channel->efx->type->ev_test_generate(channel);
}
-/* Process a fatal interrupt
- * Disable bus mastering ASAP and schedule a reset
- */
-irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx)
+void efx_nic_irq_test_start(struct efx_nic *efx)
{
- struct falcon_nic_data *nic_data = efx->nic_data;
- efx_oword_t *int_ker = efx->irq_status.addr;
- efx_oword_t fatal_intr;
- int error, mem_perr;
-
- efx_reado(efx, &fatal_intr, FR_AZ_FATAL_INTR_KER);
- error = EFX_OWORD_FIELD(fatal_intr, FRF_AZ_FATAL_INTR);
-
- netif_err(efx, hw, efx->net_dev, "SYSTEM ERROR "EFX_OWORD_FMT" status "
- EFX_OWORD_FMT ": %s\n", EFX_OWORD_VAL(*int_ker),
- EFX_OWORD_VAL(fatal_intr),
- error ? "disabling bus mastering" : "no recognised error");
-
- /* If this is a memory parity error dump which blocks are offending */
- mem_perr = (EFX_OWORD_FIELD(fatal_intr, FRF_AZ_MEM_PERR_INT_KER) ||
- EFX_OWORD_FIELD(fatal_intr, FRF_AZ_SRM_PERR_INT_KER));
- if (mem_perr) {
- efx_oword_t reg;
- efx_reado(efx, &reg, FR_AZ_MEM_STAT);
- netif_err(efx, hw, efx->net_dev,
- "SYSTEM ERROR: memory parity error "EFX_OWORD_FMT"\n",
- EFX_OWORD_VAL(reg));
- }
-
- /* Disable both devices */
- pci_clear_master(efx->pci_dev);
- if (efx_nic_is_dual_func(efx))
- pci_clear_master(nic_data->pci_dev2);
- efx_nic_disable_interrupts(efx);
-
- /* Count errors and reset or disable the NIC accordingly */
- if (efx->int_error_count == 0 ||
- time_after(jiffies, efx->int_error_expire)) {
- efx->int_error_count = 0;
- efx->int_error_expire =
- jiffies + EFX_INT_ERROR_EXPIRE * HZ;
- }
- if (++efx->int_error_count < EFX_MAX_INT_ERRORS) {
- netif_err(efx, hw, efx->net_dev,
- "SYSTEM ERROR - reset scheduled\n");
- efx_schedule_reset(efx, RESET_TYPE_INT_ERROR);
- } else {
- netif_err(efx, hw, efx->net_dev,
- "SYSTEM ERROR - max number of errors seen."
- "NIC will be disabled\n");
- efx_schedule_reset(efx, RESET_TYPE_DISABLE);
- }
-
- return IRQ_HANDLED;
-}
-
-/* Handle a legacy interrupt
- * Acknowledges the interrupt and schedule event queue processing.
- */
-static irqreturn_t efx_legacy_interrupt(int irq, void *dev_id)
-{
- struct efx_nic *efx = dev_id;
- efx_oword_t *int_ker = efx->irq_status.addr;
- irqreturn_t result = IRQ_NONE;
- struct efx_channel *channel;
- efx_dword_t reg;
- u32 queues;
- int syserr;
-
- /* Could this be ours? If interrupts are disabled then the
- * channel state may not be valid.
- */
- if (!efx->legacy_irq_enabled)
- return result;
-
- /* Read the ISR which also ACKs the interrupts */
- efx_readd(efx, &reg, FR_BZ_INT_ISR0);
- queues = EFX_EXTRACT_DWORD(reg, 0, 31);
-
- /* Check to see if we have a serious error condition */
- if (queues & (1U << efx->fatal_irq_level)) {
- syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
- if (unlikely(syserr))
- return efx_nic_fatal_interrupt(efx);
- }
-
- if (queues != 0) {
- if (EFX_WORKAROUND_15783(efx))
- efx->irq_zero_count = 0;
-
- /* Schedule processing of any interrupting queues */
- efx_for_each_channel(channel, efx) {
- if (queues & 1)
- efx_schedule_channel(channel);
- queues >>= 1;
- }
- result = IRQ_HANDLED;
-
- } else if (EFX_WORKAROUND_15783(efx)) {
- efx_qword_t *event;
-
- /* We can't return IRQ_HANDLED more than once on seeing ISR=0
- * because this might be a shared interrupt. */
- if (efx->irq_zero_count++ == 0)
- result = IRQ_HANDLED;
-
- /* Ensure we schedule or rearm all event queues */
- efx_for_each_channel(channel, efx) {
- event = efx_event(channel, channel->eventq_read_ptr);
- if (efx_event_present(event))
- efx_schedule_channel(channel);
- else
- efx_nic_eventq_read_ack(channel);
- }
- }
-
- if (result == IRQ_HANDLED) {
- efx->last_irq_cpu = raw_smp_processor_id();
- netif_vdbg(efx, intr, efx->net_dev,
- "IRQ %d on CPU %d status " EFX_DWORD_FMT "\n",
- irq, raw_smp_processor_id(), EFX_DWORD_VAL(reg));
- }
-
- return result;
-}
-
-/* Handle an MSI interrupt
- *
- * Handle an MSI hardware interrupt. This routine schedules event
- * queue processing. No interrupt acknowledgement cycle is necessary.
- * Also, we never need to check that the interrupt is for us, since
- * MSI interrupts cannot be shared.
- */
-static irqreturn_t efx_msi_interrupt(int irq, void *dev_id)
-{
- struct efx_channel *channel = *(struct efx_channel **)dev_id;
- struct efx_nic *efx = channel->efx;
- efx_oword_t *int_ker = efx->irq_status.addr;
- int syserr;
-
- efx->last_irq_cpu = raw_smp_processor_id();
- netif_vdbg(efx, intr, efx->net_dev,
- "IRQ %d on CPU %d status " EFX_OWORD_FMT "\n",
- irq, raw_smp_processor_id(), EFX_OWORD_VAL(*int_ker));
-
- /* Check to see if we have a serious error condition */
- if (channel->channel == efx->fatal_irq_level) {
- syserr = EFX_OWORD_FIELD(*int_ker, FSF_AZ_NET_IVEC_FATAL_INT);
- if (unlikely(syserr))
- return efx_nic_fatal_interrupt(efx);
- }
-
- /* Schedule processing of the channel */
- efx_schedule_channel(channel);
-
- return IRQ_HANDLED;
-}
-
-
-/* Setup RSS indirection table.
- * This maps from the hash value of the packet to RXQ
- */
-void efx_nic_push_rx_indir_table(struct efx_nic *efx)
-{
- size_t i = 0;
- efx_dword_t dword;
-
- if (efx_nic_rev(efx) < EFX_REV_FALCON_B0)
- return;
-
- BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) !=
- FR_BZ_RX_INDIRECTION_TBL_ROWS);
-
- for (i = 0; i < FR_BZ_RX_INDIRECTION_TBL_ROWS; i++) {
- EFX_POPULATE_DWORD_1(dword, FRF_BZ_IT_QUEUE,
- efx->rx_indir_table[i]);
- efx_writed_table(efx, &dword, FR_BZ_RX_INDIRECTION_TBL, i);
- }
+ efx->last_irq_cpu = -1;
+ smp_wmb();
+ efx->type->irq_test_generate(efx);
}
/* Hook interrupt handler(s)
@@ -1534,16 +79,12 @@ void efx_nic_push_rx_indir_table(struct efx_nic *efx)
int efx_nic_init_interrupt(struct efx_nic *efx)
{
struct efx_channel *channel;
+ unsigned int n_irqs;
int rc;
if (!EFX_INT_MODE_USE_MSI(efx)) {
- irq_handler_t handler;
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)
- handler = efx_legacy_interrupt;
- else
- handler = falcon_legacy_interrupt_a1;
-
- rc = request_irq(efx->legacy_irq, handler, IRQF_SHARED,
+ rc = request_irq(efx->legacy_irq,
+ efx->type->irq_handle_legacy, IRQF_SHARED,
efx->name, efx);
if (rc) {
netif_err(efx, drv, efx->net_dev,
@@ -1554,24 +95,54 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
return 0;
}
+#ifdef CONFIG_RFS_ACCEL
+ if (efx->interrupt_mode == EFX_INT_MODE_MSIX) {
+ efx->net_dev->rx_cpu_rmap =
+ alloc_irq_cpu_rmap(efx->n_rx_channels);
+ if (!efx->net_dev->rx_cpu_rmap) {
+ rc = -ENOMEM;
+ goto fail1;
+ }
+ }
+#endif
+
/* Hook MSI or MSI-X interrupt */
+ n_irqs = 0;
efx_for_each_channel(channel, efx) {
- rc = request_irq(channel->irq, efx_msi_interrupt,
+ rc = request_irq(channel->irq, efx->type->irq_handle_msi,
IRQF_PROBE_SHARED, /* Not shared */
- efx->channel_name[channel->channel],
- &efx->channel[channel->channel]);
+ efx->msi_context[channel->channel].name,
+ &efx->msi_context[channel->channel]);
if (rc) {
netif_err(efx, drv, efx->net_dev,
"failed to hook IRQ %d\n", channel->irq);
goto fail2;
}
+ ++n_irqs;
+
+#ifdef CONFIG_RFS_ACCEL
+ if (efx->interrupt_mode == EFX_INT_MODE_MSIX &&
+ channel->channel < efx->n_rx_channels) {
+ rc = irq_cpu_rmap_add(efx->net_dev->rx_cpu_rmap,
+ channel->irq);
+ if (rc)
+ goto fail2;
+ }
+#endif
}
return 0;
fail2:
- efx_for_each_channel(channel, efx)
- free_irq(channel->irq, &efx->channel[channel->channel]);
+#ifdef CONFIG_RFS_ACCEL
+ free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
+ efx->net_dev->rx_cpu_rmap = NULL;
+#endif
+ efx_for_each_channel(channel, efx) {
+ if (n_irqs-- == 0)
+ break;
+ free_irq(channel->irq, &efx->msi_context[channel->channel]);
+ }
fail1:
return rc;
}
@@ -1579,145 +150,49 @@ int efx_nic_init_interrupt(struct efx_nic *efx)
void efx_nic_fini_interrupt(struct efx_nic *efx)
{
struct efx_channel *channel;
- efx_oword_t reg;
- /* Disable MSI/MSI-X interrupts */
- efx_for_each_channel(channel, efx) {
- if (channel->irq)
- free_irq(channel->irq, &efx->channel[channel->channel]);
- }
-
- /* ACK legacy interrupt */
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)
- efx_reado(efx, &reg, FR_BZ_INT_ISR0);
- else
- falcon_irq_ack_a1(efx);
+#ifdef CONFIG_RFS_ACCEL
+ free_irq_cpu_rmap(efx->net_dev->rx_cpu_rmap);
+ efx->net_dev->rx_cpu_rmap = NULL;
+#endif
- /* Disable legacy interrupt */
- if (efx->legacy_irq)
+ if (EFX_INT_MODE_USE_MSI(efx)) {
+ /* Disable MSI/MSI-X interrupts */
+ efx_for_each_channel(channel, efx)
+ free_irq(channel->irq,
+ &efx->msi_context[channel->channel]);
+ } else {
+ /* Disable legacy interrupt */
free_irq(efx->legacy_irq, efx);
-}
-
-u32 efx_nic_fpga_ver(struct efx_nic *efx)
-{
- efx_oword_t altera_build;
- efx_reado(efx, &altera_build, FR_AZ_ALTERA_BUILD);
- return EFX_OWORD_FIELD(altera_build, FRF_AZ_ALTERA_BUILD_VER);
-}
-
-void efx_nic_init_common(struct efx_nic *efx)
-{
- efx_oword_t temp;
-
- /* Set positions of descriptor caches in SRAM. */
- EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_TX_DC_BASE_ADR,
- efx->type->tx_dc_base / 8);
- efx_writeo(efx, &temp, FR_AZ_SRM_TX_DC_CFG);
- EFX_POPULATE_OWORD_1(temp, FRF_AZ_SRM_RX_DC_BASE_ADR,
- efx->type->rx_dc_base / 8);
- efx_writeo(efx, &temp, FR_AZ_SRM_RX_DC_CFG);
-
- /* Set TX descriptor cache size. */
- BUILD_BUG_ON(TX_DC_ENTRIES != (8 << TX_DC_ENTRIES_ORDER));
- EFX_POPULATE_OWORD_1(temp, FRF_AZ_TX_DC_SIZE, TX_DC_ENTRIES_ORDER);
- efx_writeo(efx, &temp, FR_AZ_TX_DC_CFG);
-
- /* Set RX descriptor cache size. Set low watermark to size-8, as
- * this allows most efficient prefetching.
- */
- BUILD_BUG_ON(RX_DC_ENTRIES != (8 << RX_DC_ENTRIES_ORDER));
- EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_SIZE, RX_DC_ENTRIES_ORDER);
- efx_writeo(efx, &temp, FR_AZ_RX_DC_CFG);
- EFX_POPULATE_OWORD_1(temp, FRF_AZ_RX_DC_PF_LWM, RX_DC_ENTRIES - 8);
- efx_writeo(efx, &temp, FR_AZ_RX_DC_PF_WM);
-
- /* Program INT_KER address */
- EFX_POPULATE_OWORD_2(temp,
- FRF_AZ_NORM_INT_VEC_DIS_KER,
- EFX_INT_MODE_USE_MSI(efx),
- FRF_AZ_INT_ADR_KER, efx->irq_status.dma_addr);
- efx_writeo(efx, &temp, FR_AZ_INT_ADR_KER);
-
- if (EFX_WORKAROUND_17213(efx) && !EFX_INT_MODE_USE_MSI(efx))
- /* Use an interrupt level unused by event queues */
- efx->fatal_irq_level = 0x1f;
- else
- /* Use a valid MSI-X vector */
- efx->fatal_irq_level = 0;
-
- /* Enable all the genuinely fatal interrupts. (They are still
- * masked by the overall interrupt mask, controlled by
- * falcon_interrupts()).
- *
- * Note: All other fatal interrupts are enabled
- */
- EFX_POPULATE_OWORD_3(temp,
- FRF_AZ_ILL_ADR_INT_KER_EN, 1,
- FRF_AZ_RBUF_OWN_INT_KER_EN, 1,
- FRF_AZ_TBUF_OWN_INT_KER_EN, 1);
- if (efx_nic_rev(efx) >= EFX_REV_SIENA_A0)
- EFX_SET_OWORD_FIELD(temp, FRF_CZ_SRAM_PERR_INT_P_KER_EN, 1);
- EFX_INVERT_OWORD(temp);
- efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER);
-
- efx_nic_push_rx_indir_table(efx);
-
- /* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be
- * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q.
- */
- efx_reado(efx, &temp, FR_AZ_TX_RESERVED);
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER, 0xfe);
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_RX_SPACER_EN, 1);
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_ONE_PKT_PER_Q, 1);
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PUSH_EN, 1);
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_DIS_NON_IP_EV, 1);
- /* Enable SW_EV to inherit in char driver - assume harmless here */
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_SOFT_EVT_EN, 1);
- /* Prefetch threshold 2 => fetch when descriptor cache half empty */
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_THRESHOLD, 2);
- /* Disable hardware watchdog which can misfire */
- EFX_SET_OWORD_FIELD(temp, FRF_AZ_TX_PREF_WD_TMR, 0x3fffff);
- /* Squash TX of packets of 16 bytes or less */
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0)
- EFX_SET_OWORD_FIELD(temp, FRF_BZ_TX_FLUSH_MIN_LEN_EN, 1);
- efx_writeo(efx, &temp, FR_AZ_TX_RESERVED);
-
- if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) {
- EFX_POPULATE_OWORD_4(temp,
- /* Default values */
- FRF_BZ_TX_PACE_SB_NOT_AF, 0x15,
- FRF_BZ_TX_PACE_SB_AF, 0xb,
- FRF_BZ_TX_PACE_FB_BASE, 0,
- /* Allow large pace values in the
- * fast bin. */
- FRF_BZ_TX_PACE_BIN_TH,
- FFE_BZ_TX_PACE_RESERVED);
- efx_writeo(efx, &temp, FR_BZ_TX_PACE);
}
}
/* Register dump */
-#define REGISTER_REVISION_A 1
-#define REGISTER_REVISION_B 2
-#define REGISTER_REVISION_C 3
-#define REGISTER_REVISION_Z 3 /* latest revision */
+#define REGISTER_REVISION_FA 1
+#define REGISTER_REVISION_FB 2
+#define REGISTER_REVISION_FC 3
+#define REGISTER_REVISION_FZ 3 /* last Falcon arch revision */
+#define REGISTER_REVISION_ED 4
+#define REGISTER_REVISION_EZ 4 /* latest EF10 revision */
struct efx_nic_reg {
u32 offset:24;
- u32 min_revision:2, max_revision:2;
+ u32 min_revision:3, max_revision:3;
};
-#define REGISTER(name, min_rev, max_rev) { \
- FR_ ## min_rev ## max_rev ## _ ## name, \
- REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev \
+#define REGISTER(name, arch, min_rev, max_rev) { \
+ arch ## R_ ## min_rev ## max_rev ## _ ## name, \
+ REGISTER_REVISION_ ## arch ## min_rev, \
+ REGISTER_REVISION_ ## arch ## max_rev \
}
-#define REGISTER_AA(name) REGISTER(name, A, A)
-#define REGISTER_AB(name) REGISTER(name, A, B)
-#define REGISTER_AZ(name) REGISTER(name, A, Z)
-#define REGISTER_BB(name) REGISTER(name, B, B)
-#define REGISTER_BZ(name) REGISTER(name, B, Z)
-#define REGISTER_CZ(name) REGISTER(name, C, Z)
+#define REGISTER_AA(name) REGISTER(name, F, A, A)
+#define REGISTER_AB(name) REGISTER(name, F, A, B)
+#define REGISTER_AZ(name) REGISTER(name, F, A, Z)
+#define REGISTER_BB(name) REGISTER(name, F, B, B)
+#define REGISTER_BZ(name) REGISTER(name, F, B, Z)
+#define REGISTER_CZ(name) REGISTER(name, F, C, Z)
+#define REGISTER_DZ(name) REGISTER(name, E, D, Z)
static const struct efx_nic_reg efx_nic_regs[] = {
REGISTER_AZ(ADR_REGION),
@@ -1824,37 +299,42 @@ static const struct efx_nic_reg efx_nic_regs[] = {
REGISTER_AB(XX_TXDRV_CTL),
/* XX_PRBS_CTL, XX_PRBS_CHK and XX_PRBS_ERR are not used */
/* XX_CORE_STAT is partly RC */
+ REGISTER_DZ(BIU_HW_REV_ID),
+ REGISTER_DZ(MC_DB_LWRD),
+ REGISTER_DZ(MC_DB_HWRD),
};
struct efx_nic_reg_table {
u32 offset:24;
- u32 min_revision:2, max_revision:2;
+ u32 min_revision:3, max_revision:3;
u32 step:6, rows:21;
};
-#define REGISTER_TABLE_DIMENSIONS(_, offset, min_rev, max_rev, step, rows) { \
+#define REGISTER_TABLE_DIMENSIONS(_, offset, arch, min_rev, max_rev, step, rows) { \
offset, \
- REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev, \
+ REGISTER_REVISION_ ## arch ## min_rev, \
+ REGISTER_REVISION_ ## arch ## max_rev, \
step, rows \
}
-#define REGISTER_TABLE(name, min_rev, max_rev) \
+#define REGISTER_TABLE(name, arch, min_rev, max_rev) \
REGISTER_TABLE_DIMENSIONS( \
- name, FR_ ## min_rev ## max_rev ## _ ## name, \
- min_rev, max_rev, \
- FR_ ## min_rev ## max_rev ## _ ## name ## _STEP, \
- FR_ ## min_rev ## max_rev ## _ ## name ## _ROWS)
-#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, A, A)
-#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, A, Z)
-#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, B, B)
-#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, B, Z)
+ name, arch ## R_ ## min_rev ## max_rev ## _ ## name, \
+ arch, min_rev, max_rev, \
+ arch ## R_ ## min_rev ## max_rev ## _ ## name ## _STEP, \
+ arch ## R_ ## min_rev ## max_rev ## _ ## name ## _ROWS)
+#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, F, A, A)
+#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, F, A, Z)
+#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, F, B, B)
+#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, F, B, Z)
#define REGISTER_TABLE_BB_CZ(name) \
- REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, B, B, \
+ REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, B, B, \
FR_BZ_ ## name ## _STEP, \
FR_BB_ ## name ## _ROWS), \
- REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, C, Z, \
+ REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, C, Z, \
FR_BZ_ ## name ## _STEP, \
FR_CZ_ ## name ## _ROWS)
-#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, C, Z)
+#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, F, C, Z)
+#define REGISTER_TABLE_DZ(name) REGISTER_TABLE(name, E, D, Z)
static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
/* DRIVER is not used */
@@ -1872,9 +352,9 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
* 1K entries allows for some expansion of queue count and
* size before we need to change the version. */
REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL_KER, FR_AA_BUF_FULL_TBL_KER,
- A, A, 8, 1024),
+ F, A, A, 8, 1024),
REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL, FR_BZ_BUF_FULL_TBL,
- B, Z, 8, 1024),
+ F, B, Z, 8, 1024),
REGISTER_TABLE_CZ(RX_MAC_FILTER_TBL0),
REGISTER_TABLE_BB_CZ(TIMER_TBL),
REGISTER_TABLE_BB_CZ(TX_PACE_TBL),
@@ -1885,6 +365,7 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = {
/* MSIX_PBA_TABLE is not mapped */
/* SRM_DBG is not mapped (and is redundant with BUF_FLL_TBL) */
REGISTER_TABLE_BZ(RX_FILTER_TBL0),
+ REGISTER_TABLE_DZ(BIU_MC_SFT_STATUS),
};
size_t efx_nic_get_regs_len(struct efx_nic *efx)
@@ -1938,15 +419,15 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf)
for (i = 0; i < table->rows; i++) {
switch (table->step) {
- case 4: /* 32-bit register or SRAM */
- efx_readd_table(efx, buf, table->offset, i);
+ case 4: /* 32-bit SRAM */
+ efx_readd(efx, buf, table->offset + 4 * i);
break;
case 8: /* 64-bit SRAM */
efx_sram_readq(efx,
efx->membase + table->offset,
buf, i);
break;
- case 16: /* 128-bit register */
+ case 16: /* 128-bit-readable register */
efx_reado_table(efx, buf, table->offset, i);
break;
case 32: /* 128-bit register, interleaved */
@@ -1960,3 +441,94 @@ void efx_nic_get_regs(struct efx_nic *efx, void *buf)
}
}
}
+
+/**
+ * efx_nic_describe_stats - Describe supported statistics for ethtool
+ * @desc: Array of &struct efx_hw_stat_desc describing the statistics
+ * @count: Length of the @desc array
+ * @mask: Bitmask of which elements of @desc are enabled
+ * @names: Buffer to copy names to, or %NULL. The names are copied
+ * starting at intervals of %ETH_GSTRING_LEN bytes.
+ *
+ * Returns the number of visible statistics, i.e. the number of set
+ * bits in the first @count bits of @mask for which a name is defined.
+ */
+size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count,
+ const unsigned long *mask, u8 *names)
+{
+ size_t visible = 0;
+ size_t index;
+
+ for_each_set_bit(index, mask, count) {
+ if (desc[index].name) {
+ if (names) {
+ strlcpy(names, desc[index].name,
+ ETH_GSTRING_LEN);
+ names += ETH_GSTRING_LEN;
+ }
+ ++visible;
+ }
+ }
+
+ return visible;
+}
+
+/**
+ * efx_nic_update_stats - Convert statistics DMA buffer to array of u64
+ * @desc: Array of &struct efx_hw_stat_desc describing the DMA buffer
+ * layout. DMA widths of 0, 16, 32 and 64 are supported; where
+ * the width is specified as 0 the corresponding element of
+ * @stats is not updated.
+ * @count: Length of the @desc array
+ * @mask: Bitmask of which elements of @desc are enabled
+ * @stats: Buffer to update with the converted statistics. The length
+ * of this array must be at least @count.
+ * @dma_buf: DMA buffer containing hardware statistics
+ * @accumulate: If set, the converted values will be added rather than
+ * directly stored to the corresponding elements of @stats
+ */
+void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count,
+ const unsigned long *mask,
+ u64 *stats, const void *dma_buf, bool accumulate)
+{
+ size_t index;
+
+ for_each_set_bit(index, mask, count) {
+ if (desc[index].dma_width) {
+ const void *addr = dma_buf + desc[index].offset;
+ u64 val;
+
+ switch (desc[index].dma_width) {
+ case 16:
+ val = le16_to_cpup((__le16 *)addr);
+ break;
+ case 32:
+ val = le32_to_cpup((__le32 *)addr);
+ break;
+ case 64:
+ val = le64_to_cpup((__le64 *)addr);
+ break;
+ default:
+ WARN_ON(1);
+ val = 0;
+ break;
+ }
+
+ if (accumulate)
+ stats[index] += val;
+ else
+ stats[index] = val;
+ }
+ }
+}
+
+void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *rx_nodesc_drops)
+{
+ /* if down, or this is the first update after coming up */
+ if (!(efx->net_dev->flags & IFF_UP) || !efx->rx_nodesc_drops_prev_state)
+ efx->rx_nodesc_drops_while_down +=
+ *rx_nodesc_drops - efx->rx_nodesc_drops_total;
+ efx->rx_nodesc_drops_total = *rx_nodesc_drops;
+ efx->rx_nodesc_drops_prev_state = !!(efx->net_dev->flags & IFF_UP);
+ *rx_nodesc_drops -= efx->rx_nodesc_drops_while_down;
+}
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 5fb24d3aa3c..d3ad8ed8d90 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2011 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -11,21 +11,18 @@
#ifndef EFX_NIC_H
#define EFX_NIC_H
+#include <linux/net_tstamp.h>
#include <linux/i2c-algo-bit.h>
#include "net_driver.h"
#include "efx.h"
#include "mcdi.h"
-#include "spi.h"
-
-/*
- * Falcon hardware control
- */
enum {
EFX_REV_FALCON_A0 = 0,
EFX_REV_FALCON_A1 = 1,
EFX_REV_FALCON_B0 = 2,
EFX_REV_SIENA_A0 = 3,
+ EFX_REV_HUNT_A0 = 4,
};
static inline int efx_nic_rev(struct efx_nic *efx)
@@ -33,18 +30,89 @@ static inline int efx_nic_rev(struct efx_nic *efx)
return efx->type->revision;
}
-extern u32 efx_nic_fpga_ver(struct efx_nic *efx);
+u32 efx_farch_fpga_ver(struct efx_nic *efx);
-static inline bool efx_nic_has_mc(struct efx_nic *efx)
-{
- return efx_nic_rev(efx) >= EFX_REV_SIENA_A0;
-}
/* NIC has two interlinked PCI functions for the same port. */
static inline bool efx_nic_is_dual_func(struct efx_nic *efx)
{
return efx_nic_rev(efx) < EFX_REV_FALCON_B0;
}
+/* Read the current event from the event queue */
+static inline efx_qword_t *efx_event(struct efx_channel *channel,
+ unsigned int index)
+{
+ return ((efx_qword_t *) (channel->eventq.buf.addr)) +
+ (index & channel->eventq_mask);
+}
+
+/* See if an event is present
+ *
+ * We check both the high and low dword of the event for all ones. We
+ * wrote all ones when we cleared the event, and no valid event can
+ * have all ones in either its high or low dwords. This approach is
+ * robust against reordering.
+ *
+ * Note that using a single 64-bit comparison is incorrect; even
+ * though the CPU read will be atomic, the DMA write may not be.
+ */
+static inline int efx_event_present(efx_qword_t *event)
+{
+ return !(EFX_DWORD_IS_ALL_ONES(event->dword[0]) |
+ EFX_DWORD_IS_ALL_ONES(event->dword[1]));
+}
+
+/* Returns a pointer to the specified transmit descriptor in the TX
+ * descriptor queue belonging to the specified channel.
+ */
+static inline efx_qword_t *
+efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index)
+{
+ return ((efx_qword_t *) (tx_queue->txd.buf.addr)) + index;
+}
+
+/* Report whether the NIC considers this TX queue empty, given the
+ * write_count used for the last doorbell push. May return false
+ * negative.
+ */
+static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue,
+ unsigned int write_count)
+{
+ unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count);
+
+ if (empty_read_count == 0)
+ return false;
+
+ return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0;
+}
+
+static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue)
+{
+ return __efx_nic_tx_is_empty(tx_queue, tx_queue->write_count);
+}
+
+/* Decide whether to push a TX descriptor to the NIC vs merely writing
+ * the doorbell. This can reduce latency when we are adding a single
+ * descriptor to an empty queue, but is otherwise pointless. Further,
+ * Falcon and Siena have hardware bugs (SF bug 33851) that may be
+ * triggered if we don't check this.
+ */
+static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue,
+ unsigned int write_count)
+{
+ bool was_empty = __efx_nic_tx_is_empty(tx_queue, write_count);
+
+ tx_queue->empty_read_count = 0;
+ return was_empty && tx_queue->write_count - write_count == 1;
+}
+
+/* Returns a pointer to the specified descriptor in the RX descriptor queue */
+static inline efx_qword_t *
+efx_rx_desc(struct efx_rx_queue *rx_queue, unsigned int index)
+{
+ return ((efx_qword_t *) (rx_queue->rxd.buf.addr)) + index;
+}
+
enum {
PHY_TYPE_NONE = 0,
PHY_TYPE_TXC43128 = 1,
@@ -62,14 +130,14 @@ enum {
(1 << LOOPBACK_XGXS) | \
(1 << LOOPBACK_XAUI))
-#define FALCON_GMAC_LOOPBACKS \
- (1 << LOOPBACK_GMAC)
+/* Alignment of PCIe DMA boundaries (4KB) */
+#define EFX_PAGE_SIZE 4096
+/* Size and alignment of buffer table entries (same) */
+#define EFX_BUF_SIZE EFX_PAGE_SIZE
/**
* struct falcon_board_type - board operations and type information
* @id: Board type id, as found in NVRAM
- * @ref_model: Model number of Solarflare reference design
- * @gen_type: Generic board type description
* @init: Allocate resources and initialise peripheral hardware
* @init_phy: Do board-specific PHY initialisation
* @fini: Shut down hardware and free resources
@@ -78,8 +146,6 @@ enum {
*/
struct falcon_board_type {
u8 id;
- const char *ref_model;
- const char *gen_type;
int (*init) (struct efx_nic *nic);
void (*init_phy) (struct efx_nic *efx);
void (*fini) (struct efx_nic *nic);
@@ -107,13 +173,96 @@ struct falcon_board {
};
/**
+ * struct falcon_spi_device - a Falcon SPI (Serial Peripheral Interface) device
+ * @device_id: Controller's id for the device
+ * @size: Size (in bytes)
+ * @addr_len: Number of address bytes in read/write commands
+ * @munge_address: Flag whether addresses should be munged.
+ * Some devices with 9-bit addresses (e.g. AT25040A EEPROM)
+ * use bit 3 of the command byte as address bit A8, rather
+ * than having a two-byte address. If this flag is set, then
+ * commands should be munged in this way.
+ * @erase_command: Erase command (or 0 if sector erase not needed).
+ * @erase_size: Erase sector size (in bytes)
+ * Erase commands affect sectors with this size and alignment.
+ * This must be a power of two.
+ * @block_size: Write block size (in bytes).
+ * Write commands are limited to blocks with this size and alignment.
+ */
+struct falcon_spi_device {
+ int device_id;
+ unsigned int size;
+ unsigned int addr_len;
+ unsigned int munge_address:1;
+ u8 erase_command;
+ unsigned int erase_size;
+ unsigned int block_size;
+};
+
+static inline bool falcon_spi_present(const struct falcon_spi_device *spi)
+{
+ return spi->size != 0;
+}
+
+enum {
+ FALCON_STAT_tx_bytes,
+ FALCON_STAT_tx_packets,
+ FALCON_STAT_tx_pause,
+ FALCON_STAT_tx_control,
+ FALCON_STAT_tx_unicast,
+ FALCON_STAT_tx_multicast,
+ FALCON_STAT_tx_broadcast,
+ FALCON_STAT_tx_lt64,
+ FALCON_STAT_tx_64,
+ FALCON_STAT_tx_65_to_127,
+ FALCON_STAT_tx_128_to_255,
+ FALCON_STAT_tx_256_to_511,
+ FALCON_STAT_tx_512_to_1023,
+ FALCON_STAT_tx_1024_to_15xx,
+ FALCON_STAT_tx_15xx_to_jumbo,
+ FALCON_STAT_tx_gtjumbo,
+ FALCON_STAT_tx_non_tcpudp,
+ FALCON_STAT_tx_mac_src_error,
+ FALCON_STAT_tx_ip_src_error,
+ FALCON_STAT_rx_bytes,
+ FALCON_STAT_rx_good_bytes,
+ FALCON_STAT_rx_bad_bytes,
+ FALCON_STAT_rx_packets,
+ FALCON_STAT_rx_good,
+ FALCON_STAT_rx_bad,
+ FALCON_STAT_rx_pause,
+ FALCON_STAT_rx_control,
+ FALCON_STAT_rx_unicast,
+ FALCON_STAT_rx_multicast,
+ FALCON_STAT_rx_broadcast,
+ FALCON_STAT_rx_lt64,
+ FALCON_STAT_rx_64,
+ FALCON_STAT_rx_65_to_127,
+ FALCON_STAT_rx_128_to_255,
+ FALCON_STAT_rx_256_to_511,
+ FALCON_STAT_rx_512_to_1023,
+ FALCON_STAT_rx_1024_to_15xx,
+ FALCON_STAT_rx_15xx_to_jumbo,
+ FALCON_STAT_rx_gtjumbo,
+ FALCON_STAT_rx_bad_lt64,
+ FALCON_STAT_rx_bad_gtjumbo,
+ FALCON_STAT_rx_overflow,
+ FALCON_STAT_rx_symbol_error,
+ FALCON_STAT_rx_align_error,
+ FALCON_STAT_rx_length_error,
+ FALCON_STAT_rx_internal_error,
+ FALCON_STAT_rx_nodesc_drop_cnt,
+ FALCON_STAT_COUNT
+};
+
+/**
* struct falcon_nic_data - Falcon NIC state
* @pci_dev2: Secondary function of Falcon A
* @board: Board state and functions
+ * @stats: Hardware statistics
* @stats_disable_count: Nest count for disabling statistics fetches
* @stats_pending: Is there a pending DMA of MAC statistics.
* @stats_timer: A timer for regularly fetching MAC statistics.
- * @stats_dma_done: Pointer to the flag which indicates DMA completion.
* @spi_flash: SPI flash device
* @spi_eeprom: SPI EEPROM device
* @spi_lock: SPI bus lock
@@ -123,12 +272,12 @@ struct falcon_board {
struct falcon_nic_data {
struct pci_dev *pci_dev2;
struct falcon_board board;
+ u64 stats[FALCON_STAT_COUNT];
unsigned int stats_disable_count;
bool stats_pending;
struct timer_list stats_timer;
- u32 *stats_dma_done;
- struct efx_spi_device spi_flash;
- struct efx_spi_device spi_eeprom;
+ struct falcon_spi_device spi_flash;
+ struct falcon_spi_device spi_eeprom;
struct mutex spi_lock;
struct mutex mdio_lock;
bool xmac_poll_required;
@@ -140,19 +289,301 @@ static inline struct falcon_board *falcon_board(struct efx_nic *efx)
return &data->board;
}
+enum {
+ SIENA_STAT_tx_bytes,
+ SIENA_STAT_tx_good_bytes,
+ SIENA_STAT_tx_bad_bytes,
+ SIENA_STAT_tx_packets,
+ SIENA_STAT_tx_bad,
+ SIENA_STAT_tx_pause,
+ SIENA_STAT_tx_control,
+ SIENA_STAT_tx_unicast,
+ SIENA_STAT_tx_multicast,
+ SIENA_STAT_tx_broadcast,
+ SIENA_STAT_tx_lt64,
+ SIENA_STAT_tx_64,
+ SIENA_STAT_tx_65_to_127,
+ SIENA_STAT_tx_128_to_255,
+ SIENA_STAT_tx_256_to_511,
+ SIENA_STAT_tx_512_to_1023,
+ SIENA_STAT_tx_1024_to_15xx,
+ SIENA_STAT_tx_15xx_to_jumbo,
+ SIENA_STAT_tx_gtjumbo,
+ SIENA_STAT_tx_collision,
+ SIENA_STAT_tx_single_collision,
+ SIENA_STAT_tx_multiple_collision,
+ SIENA_STAT_tx_excessive_collision,
+ SIENA_STAT_tx_deferred,
+ SIENA_STAT_tx_late_collision,
+ SIENA_STAT_tx_excessive_deferred,
+ SIENA_STAT_tx_non_tcpudp,
+ SIENA_STAT_tx_mac_src_error,
+ SIENA_STAT_tx_ip_src_error,
+ SIENA_STAT_rx_bytes,
+ SIENA_STAT_rx_good_bytes,
+ SIENA_STAT_rx_bad_bytes,
+ SIENA_STAT_rx_packets,
+ SIENA_STAT_rx_good,
+ SIENA_STAT_rx_bad,
+ SIENA_STAT_rx_pause,
+ SIENA_STAT_rx_control,
+ SIENA_STAT_rx_unicast,
+ SIENA_STAT_rx_multicast,
+ SIENA_STAT_rx_broadcast,
+ SIENA_STAT_rx_lt64,
+ SIENA_STAT_rx_64,
+ SIENA_STAT_rx_65_to_127,
+ SIENA_STAT_rx_128_to_255,
+ SIENA_STAT_rx_256_to_511,
+ SIENA_STAT_rx_512_to_1023,
+ SIENA_STAT_rx_1024_to_15xx,
+ SIENA_STAT_rx_15xx_to_jumbo,
+ SIENA_STAT_rx_gtjumbo,
+ SIENA_STAT_rx_bad_gtjumbo,
+ SIENA_STAT_rx_overflow,
+ SIENA_STAT_rx_false_carrier,
+ SIENA_STAT_rx_symbol_error,
+ SIENA_STAT_rx_align_error,
+ SIENA_STAT_rx_length_error,
+ SIENA_STAT_rx_internal_error,
+ SIENA_STAT_rx_nodesc_drop_cnt,
+ SIENA_STAT_COUNT
+};
+
/**
* struct siena_nic_data - Siena NIC state
- * @mcdi: Management-Controller-to-Driver Interface
* @wol_filter_id: Wake-on-LAN packet filter id
+ * @stats: Hardware statistics
*/
struct siena_nic_data {
- struct efx_mcdi_iface mcdi;
int wol_filter_id;
+ u64 stats[SIENA_STAT_COUNT];
+};
+
+enum {
+ EF10_STAT_tx_bytes,
+ EF10_STAT_tx_packets,
+ EF10_STAT_tx_pause,
+ EF10_STAT_tx_control,
+ EF10_STAT_tx_unicast,
+ EF10_STAT_tx_multicast,
+ EF10_STAT_tx_broadcast,
+ EF10_STAT_tx_lt64,
+ EF10_STAT_tx_64,
+ EF10_STAT_tx_65_to_127,
+ EF10_STAT_tx_128_to_255,
+ EF10_STAT_tx_256_to_511,
+ EF10_STAT_tx_512_to_1023,
+ EF10_STAT_tx_1024_to_15xx,
+ EF10_STAT_tx_15xx_to_jumbo,
+ EF10_STAT_rx_bytes,
+ EF10_STAT_rx_bytes_minus_good_bytes,
+ EF10_STAT_rx_good_bytes,
+ EF10_STAT_rx_bad_bytes,
+ EF10_STAT_rx_packets,
+ EF10_STAT_rx_good,
+ EF10_STAT_rx_bad,
+ EF10_STAT_rx_pause,
+ EF10_STAT_rx_control,
+ EF10_STAT_rx_unicast,
+ EF10_STAT_rx_multicast,
+ EF10_STAT_rx_broadcast,
+ EF10_STAT_rx_lt64,
+ EF10_STAT_rx_64,
+ EF10_STAT_rx_65_to_127,
+ EF10_STAT_rx_128_to_255,
+ EF10_STAT_rx_256_to_511,
+ EF10_STAT_rx_512_to_1023,
+ EF10_STAT_rx_1024_to_15xx,
+ EF10_STAT_rx_15xx_to_jumbo,
+ EF10_STAT_rx_gtjumbo,
+ EF10_STAT_rx_bad_gtjumbo,
+ EF10_STAT_rx_overflow,
+ EF10_STAT_rx_align_error,
+ EF10_STAT_rx_length_error,
+ EF10_STAT_rx_nodesc_drops,
+ EF10_STAT_rx_pm_trunc_bb_overflow,
+ EF10_STAT_rx_pm_discard_bb_overflow,
+ EF10_STAT_rx_pm_trunc_vfifo_full,
+ EF10_STAT_rx_pm_discard_vfifo_full,
+ EF10_STAT_rx_pm_trunc_qbb,
+ EF10_STAT_rx_pm_discard_qbb,
+ EF10_STAT_rx_pm_discard_mapping,
+ EF10_STAT_rx_dp_q_disabled_packets,
+ EF10_STAT_rx_dp_di_dropped_packets,
+ EF10_STAT_rx_dp_streaming_packets,
+ EF10_STAT_rx_dp_hlb_fetch,
+ EF10_STAT_rx_dp_hlb_wait,
+ EF10_STAT_COUNT
+};
+
+/* Maximum number of TX PIO buffers we may allocate to a function.
+ * This matches the total number of buffers on each SFC9100-family
+ * controller.
+ */
+#define EF10_TX_PIOBUF_COUNT 16
+
+/**
+ * struct efx_ef10_nic_data - EF10 architecture NIC state
+ * @mcdi_buf: DMA buffer for MCDI
+ * @warm_boot_count: Last seen MC warm boot count
+ * @vi_base: Absolute index of first VI in this function
+ * @n_allocated_vis: Number of VIs allocated to this function
+ * @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot
+ * @must_restore_filters: Flag: filters have yet to be restored after MC reboot
+ * @n_piobufs: Number of PIO buffers allocated to this function
+ * @wc_membase: Base address of write-combining mapping of the memory BAR
+ * @pio_write_base: Base address for writing PIO buffers
+ * @pio_write_vi_base: Relative VI number for @pio_write_base
+ * @piobuf_handle: Handle of each PIO buffer allocated
+ * @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC
+ * reboot
+ * @rx_rss_context: Firmware handle for our RSS context
+ * @stats: Hardware statistics
+ * @workaround_35388: Flag: firmware supports workaround for bug 35388
+ * @must_check_datapath_caps: Flag: @datapath_caps needs to be revalidated
+ * after MC reboot
+ * @datapath_caps: Capabilities of datapath firmware (FLAGS1 field of
+ * %MC_CMD_GET_CAPABILITIES response)
+ */
+struct efx_ef10_nic_data {
+ struct efx_buffer mcdi_buf;
+ u16 warm_boot_count;
+ unsigned int vi_base;
+ unsigned int n_allocated_vis;
+ bool must_realloc_vis;
+ bool must_restore_filters;
+ unsigned int n_piobufs;
+ void __iomem *wc_membase, *pio_write_base;
+ unsigned int pio_write_vi_base;
+ unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT];
+ bool must_restore_piobufs;
+ u32 rx_rss_context;
+ u64 stats[EF10_STAT_COUNT];
+ bool workaround_35388;
+ bool must_check_datapath_caps;
+ u32 datapath_caps;
};
+/*
+ * On the SFC9000 family each port is associated with 1 PCI physical
+ * function (PF) handled by sfc and a configurable number of virtual
+ * functions (VFs) that may be handled by some other driver, often in
+ * a VM guest. The queue pointer registers are mapped in both PF and
+ * VF BARs such that an 8K region provides access to a single RX, TX
+ * and event queue (collectively a Virtual Interface, VI or VNIC).
+ *
+ * The PF has access to all 1024 VIs while VFs are mapped to VIs
+ * according to VI_BASE and VI_SCALE: VF i has access to VIs numbered
+ * in range [VI_BASE + i << VI_SCALE, VI_BASE + i + 1 << VI_SCALE).
+ * The number of VIs and the VI_SCALE value are configurable but must
+ * be established at boot time by firmware.
+ */
+
+/* Maximum VI_SCALE parameter supported by Siena */
+#define EFX_VI_SCALE_MAX 6
+/* Base VI to use for SR-IOV. Must be aligned to (1 << EFX_VI_SCALE_MAX),
+ * so this is the smallest allowed value. */
+#define EFX_VI_BASE 128U
+/* Maximum number of VFs allowed */
+#define EFX_VF_COUNT_MAX 127
+/* Limit EVQs on VFs to be only 8k to reduce buffer table reservation */
+#define EFX_MAX_VF_EVQ_SIZE 8192UL
+/* The number of buffer table entries reserved for each VI on a VF */
+#define EFX_VF_BUFTBL_PER_VI \
+ ((EFX_MAX_VF_EVQ_SIZE + 2 * EFX_MAX_DMAQ_SIZE) * \
+ sizeof(efx_qword_t) / EFX_BUF_SIZE)
+
+#ifdef CONFIG_SFC_SRIOV
+
+static inline bool efx_sriov_wanted(struct efx_nic *efx)
+{
+ return efx->vf_count != 0;
+}
+static inline bool efx_sriov_enabled(struct efx_nic *efx)
+{
+ return efx->vf_init_count != 0;
+}
+static inline unsigned int efx_vf_size(struct efx_nic *efx)
+{
+ return 1 << efx->vi_scale;
+}
+
+int efx_init_sriov(void);
+void efx_sriov_probe(struct efx_nic *efx);
+int efx_sriov_init(struct efx_nic *efx);
+void efx_sriov_mac_address_changed(struct efx_nic *efx);
+void efx_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+void efx_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+void efx_sriov_event(struct efx_channel *channel, efx_qword_t *event);
+void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq);
+void efx_sriov_flr(struct efx_nic *efx, unsigned flr);
+void efx_sriov_reset(struct efx_nic *efx);
+void efx_sriov_fini(struct efx_nic *efx);
+void efx_fini_sriov(void);
+
+#else
+
+static inline bool efx_sriov_wanted(struct efx_nic *efx) { return false; }
+static inline bool efx_sriov_enabled(struct efx_nic *efx) { return false; }
+static inline unsigned int efx_vf_size(struct efx_nic *efx) { return 0; }
+
+static inline int efx_init_sriov(void) { return 0; }
+static inline void efx_sriov_probe(struct efx_nic *efx) {}
+static inline int efx_sriov_init(struct efx_nic *efx) { return -EOPNOTSUPP; }
+static inline void efx_sriov_mac_address_changed(struct efx_nic *efx) {}
+static inline void efx_sriov_tx_flush_done(struct efx_nic *efx,
+ efx_qword_t *event) {}
+static inline void efx_sriov_rx_flush_done(struct efx_nic *efx,
+ efx_qword_t *event) {}
+static inline void efx_sriov_event(struct efx_channel *channel,
+ efx_qword_t *event) {}
+static inline void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq) {}
+static inline void efx_sriov_flr(struct efx_nic *efx, unsigned flr) {}
+static inline void efx_sriov_reset(struct efx_nic *efx) {}
+static inline void efx_sriov_fini(struct efx_nic *efx) {}
+static inline void efx_fini_sriov(void) {}
+
+#endif
+
+int efx_sriov_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
+int efx_sriov_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos);
+int efx_sriov_get_vf_config(struct net_device *dev, int vf,
+ struct ifla_vf_info *ivf);
+int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
+ bool spoofchk);
+
+struct ethtool_ts_info;
+int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel);
+void efx_ptp_defer_probe_with_channel(struct efx_nic *efx);
+void efx_ptp_remove(struct efx_nic *efx);
+int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr);
+int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr);
+void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info);
+bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+int efx_ptp_get_mode(struct efx_nic *efx);
+int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
+ unsigned int new_mode);
+int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb);
+void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev);
+size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings);
+size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats);
+void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev);
+void __efx_rx_skb_attach_timestamp(struct efx_channel *channel,
+ struct sk_buff *skb);
+static inline void efx_rx_skb_attach_timestamp(struct efx_channel *channel,
+ struct sk_buff *skb)
+{
+ if (channel->sync_events_state == SYNC_EVENTS_VALID)
+ __efx_rx_skb_attach_timestamp(channel, skb);
+}
+void efx_ptp_start_datapath(struct efx_nic *efx);
+void efx_ptp_stop_datapath(struct efx_nic *efx);
+
extern const struct efx_nic_type falcon_a1_nic_type;
extern const struct efx_nic_type falcon_b0_nic_type;
extern const struct efx_nic_type siena_a0_nic_type;
+extern const struct efx_nic_type efx_hunt_a0_nic_type;
/**************************************************************************
*
@@ -161,112 +592,207 @@ extern const struct efx_nic_type siena_a0_nic_type;
**************************************************************************
*/
-extern int falcon_probe_board(struct efx_nic *efx, u16 revision_info);
+int falcon_probe_board(struct efx_nic *efx, u16 revision_info);
/* TX data path */
-extern int efx_nic_probe_tx(struct efx_tx_queue *tx_queue);
-extern void efx_nic_init_tx(struct efx_tx_queue *tx_queue);
-extern void efx_nic_fini_tx(struct efx_tx_queue *tx_queue);
-extern void efx_nic_remove_tx(struct efx_tx_queue *tx_queue);
-extern void efx_nic_push_buffers(struct efx_tx_queue *tx_queue);
+static inline int efx_nic_probe_tx(struct efx_tx_queue *tx_queue)
+{
+ return tx_queue->efx->type->tx_probe(tx_queue);
+}
+static inline void efx_nic_init_tx(struct efx_tx_queue *tx_queue)
+{
+ tx_queue->efx->type->tx_init(tx_queue);
+}
+static inline void efx_nic_remove_tx(struct efx_tx_queue *tx_queue)
+{
+ tx_queue->efx->type->tx_remove(tx_queue);
+}
+static inline void efx_nic_push_buffers(struct efx_tx_queue *tx_queue)
+{
+ tx_queue->efx->type->tx_write(tx_queue);
+}
/* RX data path */
-extern int efx_nic_probe_rx(struct efx_rx_queue *rx_queue);
-extern void efx_nic_init_rx(struct efx_rx_queue *rx_queue);
-extern void efx_nic_fini_rx(struct efx_rx_queue *rx_queue);
-extern void efx_nic_remove_rx(struct efx_rx_queue *rx_queue);
-extern void efx_nic_notify_rx_desc(struct efx_rx_queue *rx_queue);
+static inline int efx_nic_probe_rx(struct efx_rx_queue *rx_queue)
+{
+ return rx_queue->efx->type->rx_probe(rx_queue);
+}
+static inline void efx_nic_init_rx(struct efx_rx_queue *rx_queue)
+{
+ rx_queue->efx->type->rx_init(rx_queue);
+}
+static inline void efx_nic_remove_rx(struct efx_rx_queue *rx_queue)
+{
+ rx_queue->efx->type->rx_remove(rx_queue);
+}
+static inline void efx_nic_notify_rx_desc(struct efx_rx_queue *rx_queue)
+{
+ rx_queue->efx->type->rx_write(rx_queue);
+}
+static inline void efx_nic_generate_fill_event(struct efx_rx_queue *rx_queue)
+{
+ rx_queue->efx->type->rx_defer_refill(rx_queue);
+}
/* Event data path */
-extern int efx_nic_probe_eventq(struct efx_channel *channel);
-extern void efx_nic_init_eventq(struct efx_channel *channel);
-extern void efx_nic_fini_eventq(struct efx_channel *channel);
-extern void efx_nic_remove_eventq(struct efx_channel *channel);
-extern int efx_nic_process_eventq(struct efx_channel *channel, int rx_quota);
-extern void efx_nic_eventq_read_ack(struct efx_channel *channel);
-extern bool efx_nic_event_present(struct efx_channel *channel);
-
-/* MAC/PHY */
-extern void falcon_drain_tx_fifo(struct efx_nic *efx);
-extern void falcon_reconfigure_mac_wrapper(struct efx_nic *efx);
-
-/* Interrupts and test events */
-extern int efx_nic_init_interrupt(struct efx_nic *efx);
-extern void efx_nic_enable_interrupts(struct efx_nic *efx);
-extern void efx_nic_generate_test_event(struct efx_channel *channel);
-extern void efx_nic_generate_fill_event(struct efx_channel *channel);
-extern void efx_nic_generate_interrupt(struct efx_nic *efx);
-extern void efx_nic_disable_interrupts(struct efx_nic *efx);
-extern void efx_nic_fini_interrupt(struct efx_nic *efx);
-extern irqreturn_t efx_nic_fatal_interrupt(struct efx_nic *efx);
-extern irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id);
-extern void falcon_irq_ack_a1(struct efx_nic *efx);
-
-#define EFX_IRQ_MOD_RESOLUTION 5
-#define EFX_IRQ_MOD_MAX 0x1000
+static inline int efx_nic_probe_eventq(struct efx_channel *channel)
+{
+ return channel->efx->type->ev_probe(channel);
+}
+static inline int efx_nic_init_eventq(struct efx_channel *channel)
+{
+ return channel->efx->type->ev_init(channel);
+}
+static inline void efx_nic_fini_eventq(struct efx_channel *channel)
+{
+ channel->efx->type->ev_fini(channel);
+}
+static inline void efx_nic_remove_eventq(struct efx_channel *channel)
+{
+ channel->efx->type->ev_remove(channel);
+}
+static inline int
+efx_nic_process_eventq(struct efx_channel *channel, int quota)
+{
+ return channel->efx->type->ev_process(channel, quota);
+}
+static inline void efx_nic_eventq_read_ack(struct efx_channel *channel)
+{
+ channel->efx->type->ev_read_ack(channel);
+}
+void efx_nic_event_test_start(struct efx_channel *channel);
+
+/* Falcon/Siena queue operations */
+int efx_farch_tx_probe(struct efx_tx_queue *tx_queue);
+void efx_farch_tx_init(struct efx_tx_queue *tx_queue);
+void efx_farch_tx_fini(struct efx_tx_queue *tx_queue);
+void efx_farch_tx_remove(struct efx_tx_queue *tx_queue);
+void efx_farch_tx_write(struct efx_tx_queue *tx_queue);
+int efx_farch_rx_probe(struct efx_rx_queue *rx_queue);
+void efx_farch_rx_init(struct efx_rx_queue *rx_queue);
+void efx_farch_rx_fini(struct efx_rx_queue *rx_queue);
+void efx_farch_rx_remove(struct efx_rx_queue *rx_queue);
+void efx_farch_rx_write(struct efx_rx_queue *rx_queue);
+void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue);
+int efx_farch_ev_probe(struct efx_channel *channel);
+int efx_farch_ev_init(struct efx_channel *channel);
+void efx_farch_ev_fini(struct efx_channel *channel);
+void efx_farch_ev_remove(struct efx_channel *channel);
+int efx_farch_ev_process(struct efx_channel *channel, int quota);
+void efx_farch_ev_read_ack(struct efx_channel *channel);
+void efx_farch_ev_test_generate(struct efx_channel *channel);
+
+/* Falcon/Siena filter operations */
+int efx_farch_filter_table_probe(struct efx_nic *efx);
+void efx_farch_filter_table_restore(struct efx_nic *efx);
+void efx_farch_filter_table_remove(struct efx_nic *efx);
+void efx_farch_filter_update_rx_scatter(struct efx_nic *efx);
+s32 efx_farch_filter_insert(struct efx_nic *efx, struct efx_filter_spec *spec,
+ bool replace);
+int efx_farch_filter_remove_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority,
+ u32 filter_id);
+int efx_farch_filter_get_safe(struct efx_nic *efx,
+ enum efx_filter_priority priority, u32 filter_id,
+ struct efx_filter_spec *);
+int efx_farch_filter_clear_rx(struct efx_nic *efx,
+ enum efx_filter_priority priority);
+u32 efx_farch_filter_count_rx_used(struct efx_nic *efx,
+ enum efx_filter_priority priority);
+u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx);
+s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx,
+ enum efx_filter_priority priority, u32 *buf,
+ u32 size);
+#ifdef CONFIG_RFS_ACCEL
+s32 efx_farch_filter_rfs_insert(struct efx_nic *efx,
+ struct efx_filter_spec *spec);
+bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id,
+ unsigned int index);
+#endif
+void efx_farch_filter_sync_rx_mode(struct efx_nic *efx);
+
+bool efx_nic_event_present(struct efx_channel *channel);
+
+/* Some statistics are computed as A - B where A and B each increase
+ * linearly with some hardware counter(s) and the counters are read
+ * asynchronously. If the counters contributing to B are always read
+ * after those contributing to A, the computed value may be lower than
+ * the true value by some variable amount, and may decrease between
+ * subsequent computations.
+ *
+ * We should never allow statistics to decrease or to exceed the true
+ * value. Since the computed value will never be greater than the
+ * true value, we can achieve this by only storing the computed value
+ * when it increases.
+ */
+static inline void efx_update_diff_stat(u64 *stat, u64 diff)
+{
+ if ((s64)(diff - *stat) > 0)
+ *stat = diff;
+}
+
+/* Interrupts */
+int efx_nic_init_interrupt(struct efx_nic *efx);
+void efx_nic_irq_test_start(struct efx_nic *efx);
+void efx_nic_fini_interrupt(struct efx_nic *efx);
+
+/* Falcon/Siena interrupts */
+void efx_farch_irq_enable_master(struct efx_nic *efx);
+void efx_farch_irq_test_generate(struct efx_nic *efx);
+void efx_farch_irq_disable_master(struct efx_nic *efx);
+irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id);
+irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id);
+irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx);
+
+static inline int efx_nic_event_test_irq_cpu(struct efx_channel *channel)
+{
+ return ACCESS_ONCE(channel->event_test_cpu);
+}
+static inline int efx_nic_irq_test_irq_cpu(struct efx_nic *efx)
+{
+ return ACCESS_ONCE(efx->last_irq_cpu);
+}
/* Global Resources */
-extern int efx_nic_flush_queues(struct efx_nic *efx);
-extern void falcon_start_nic_stats(struct efx_nic *efx);
-extern void falcon_stop_nic_stats(struct efx_nic *efx);
-extern void falcon_setup_xaui(struct efx_nic *efx);
-extern int falcon_reset_xaui(struct efx_nic *efx);
-extern void efx_nic_init_common(struct efx_nic *efx);
-extern void efx_nic_push_rx_indir_table(struct efx_nic *efx);
+int efx_nic_flush_queues(struct efx_nic *efx);
+void siena_prepare_flush(struct efx_nic *efx);
+int efx_farch_fini_dmaq(struct efx_nic *efx);
+void efx_farch_finish_flr(struct efx_nic *efx);
+void siena_finish_flush(struct efx_nic *efx);
+void falcon_start_nic_stats(struct efx_nic *efx);
+void falcon_stop_nic_stats(struct efx_nic *efx);
+int falcon_reset_xaui(struct efx_nic *efx);
+void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw);
+void efx_farch_init_common(struct efx_nic *efx);
+void efx_ef10_handle_drain_event(struct efx_nic *efx);
+void efx_farch_rx_push_indir_table(struct efx_nic *efx);
int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer,
- unsigned int len);
+ unsigned int len, gfp_t gfp_flags);
void efx_nic_free_buffer(struct efx_nic *efx, struct efx_buffer *buffer);
/* Tests */
-struct efx_nic_register_test {
+struct efx_farch_register_test {
unsigned address;
efx_oword_t mask;
};
-extern int efx_nic_test_registers(struct efx_nic *efx,
- const struct efx_nic_register_test *regs,
- size_t n_regs);
+int efx_farch_test_registers(struct efx_nic *efx,
+ const struct efx_farch_register_test *regs,
+ size_t n_regs);
-extern size_t efx_nic_get_regs_len(struct efx_nic *efx);
-extern void efx_nic_get_regs(struct efx_nic *efx, void *buf);
+size_t efx_nic_get_regs_len(struct efx_nic *efx);
+void efx_nic_get_regs(struct efx_nic *efx, void *buf);
-/**************************************************************************
- *
- * Falcon MAC stats
- *
- **************************************************************************
- */
+size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count,
+ const unsigned long *mask, u8 *names);
+void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count,
+ const unsigned long *mask, u64 *stats,
+ const void *dma_buf, bool accumulate);
+void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *stat);
+
+#define EFX_MAX_FLUSH_TIME 5000
-#define FALCON_STAT_OFFSET(falcon_stat) EFX_VAL(falcon_stat, offset)
-#define FALCON_STAT_WIDTH(falcon_stat) EFX_VAL(falcon_stat, WIDTH)
-
-/* Retrieve statistic from statistics block */
-#define FALCON_STAT(efx, falcon_stat, efx_stat) do { \
- if (FALCON_STAT_WIDTH(falcon_stat) == 16) \
- (efx)->mac_stats.efx_stat += le16_to_cpu( \
- *((__force __le16 *) \
- (efx->stats_buffer.addr + \
- FALCON_STAT_OFFSET(falcon_stat)))); \
- else if (FALCON_STAT_WIDTH(falcon_stat) == 32) \
- (efx)->mac_stats.efx_stat += le32_to_cpu( \
- *((__force __le32 *) \
- (efx->stats_buffer.addr + \
- FALCON_STAT_OFFSET(falcon_stat)))); \
- else \
- (efx)->mac_stats.efx_stat += le64_to_cpu( \
- *((__force __le64 *) \
- (efx->stats_buffer.addr + \
- FALCON_STAT_OFFSET(falcon_stat)))); \
- } while (0)
-
-#define FALCON_MAC_STATS_SIZE 0x100
-
-#define MAC_DATA_LBN 0
-#define MAC_DATA_WIDTH 32
-
-extern void efx_nic_generate_event(struct efx_channel *channel,
- efx_qword_t *event);
-
-extern void falcon_poll_xmac(struct efx_nic *efx);
+void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq,
+ efx_qword_t *event);
#endif /* EFX_NIC_H */
diff --git a/drivers/net/ethernet/sfc/phy.h b/drivers/net/ethernet/sfc/phy.h
index 11d148cd844..803bf445c08 100644
--- a/drivers/net/ethernet/sfc/phy.h
+++ b/drivers/net/ethernet/sfc/phy.h
@@ -1,5 +1,5 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2007-2010 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -15,7 +15,7 @@
*/
extern const struct efx_phy_operations falcon_sfx7101_phy_ops;
-extern void tenxpress_set_id_led(struct efx_nic *efx, enum efx_led_mode mode);
+void tenxpress_set_id_led(struct efx_nic *efx, enum efx_led_mode mode);
/****************************************************************************
* AMCC/Quake QT202x PHYs
@@ -34,7 +34,7 @@ extern const struct efx_phy_operations falcon_qt202x_phy_ops;
#define QUAKE_LED_TXLINK (0)
#define QUAKE_LED_RXLINK (8)
-extern void falcon_qt202x_set_led(struct efx_nic *p, int led, int state);
+void falcon_qt202x_set_led(struct efx_nic *p, int led, int state);
/****************************************************************************
* Transwitch CX4 retimer
@@ -44,24 +44,7 @@ extern const struct efx_phy_operations falcon_txc_phy_ops;
#define TXC_GPIO_DIR_INPUT 0
#define TXC_GPIO_DIR_OUTPUT 1
-extern void falcon_txc_set_gpio_dir(struct efx_nic *efx, int pin, int dir);
-extern void falcon_txc_set_gpio_val(struct efx_nic *efx, int pin, int val);
-
-/****************************************************************************
- * Siena managed PHYs
- */
-extern const struct efx_phy_operations efx_mcdi_phy_ops;
-
-extern int efx_mcdi_mdio_read(struct efx_nic *efx, unsigned int bus,
- unsigned int prtad, unsigned int devad,
- u16 addr, u16 *value_out, u32 *status_out);
-extern int efx_mcdi_mdio_write(struct efx_nic *efx, unsigned int bus,
- unsigned int prtad, unsigned int devad,
- u16 addr, u16 value, u32 *status_out);
-extern void efx_mcdi_phy_decode_link(struct efx_nic *efx,
- struct efx_link_state *link_state,
- u32 speed, u32 flags, u32 fcntl);
-extern int efx_mcdi_phy_reconfigure(struct efx_nic *efx);
-extern void efx_mcdi_phy_check_fcntl(struct efx_nic *efx, u32 lpa);
+void falcon_txc_set_gpio_dir(struct efx_nic *efx, int pin, int dir);
+void falcon_txc_set_gpio_val(struct efx_nic *efx, int pin, int val);
#endif
diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c
new file mode 100644
index 00000000000..6b861e3de4b
--- /dev/null
+++ b/drivers/net/ethernet/sfc/ptp.c
@@ -0,0 +1,1939 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2011-2013 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+/* Theory of operation:
+ *
+ * PTP support is assisted by firmware running on the MC, which provides
+ * the hardware timestamping capabilities. Both transmitted and received
+ * PTP event packets are queued onto internal queues for subsequent processing;
+ * this is because the MC operations are relatively long and would block
+ * block NAPI/interrupt operation.
+ *
+ * Receive event processing:
+ * The event contains the packet's UUID and sequence number, together
+ * with the hardware timestamp. The PTP receive packet queue is searched
+ * for this UUID/sequence number and, if found, put on a pending queue.
+ * Packets not matching are delivered without timestamps (MCDI events will
+ * always arrive after the actual packet).
+ * It is important for the operation of the PTP protocol that the ordering
+ * of packets between the event and general port is maintained.
+ *
+ * Work queue processing:
+ * If work waiting, synchronise host/hardware time
+ *
+ * Transmit: send packet through MC, which returns the transmission time
+ * that is converted to an appropriate timestamp.
+ *
+ * Receive: the packet's reception time is converted to an appropriate
+ * timestamp.
+ */
+#include <linux/ip.h>
+#include <linux/udp.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/module.h>
+#include <linux/net_tstamp.h>
+#include <linux/pps_kernel.h>
+#include <linux/ptp_clock_kernel.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "mcdi.h"
+#include "mcdi_pcol.h"
+#include "io.h"
+#include "farch_regs.h"
+#include "nic.h"
+
+/* Maximum number of events expected to make up a PTP event */
+#define MAX_EVENT_FRAGS 3
+
+/* Maximum delay, ms, to begin synchronisation */
+#define MAX_SYNCHRONISE_WAIT_MS 2
+
+/* How long, at most, to spend synchronising */
+#define SYNCHRONISE_PERIOD_NS 250000
+
+/* How often to update the shared memory time */
+#define SYNCHRONISATION_GRANULARITY_NS 200
+
+/* Minimum permitted length of a (corrected) synchronisation time */
+#define DEFAULT_MIN_SYNCHRONISATION_NS 120
+
+/* Maximum permitted length of a (corrected) synchronisation time */
+#define MAX_SYNCHRONISATION_NS 1000
+
+/* How many (MC) receive events that can be queued */
+#define MAX_RECEIVE_EVENTS 8
+
+/* Length of (modified) moving average. */
+#define AVERAGE_LENGTH 16
+
+/* How long an unmatched event or packet can be held */
+#define PKT_EVENT_LIFETIME_MS 10
+
+/* Offsets into PTP packet for identification. These offsets are from the
+ * start of the IP header, not the MAC header. Note that neither PTP V1 nor
+ * PTP V2 permit the use of IPV4 options.
+ */
+#define PTP_DPORT_OFFSET 22
+
+#define PTP_V1_VERSION_LENGTH 2
+#define PTP_V1_VERSION_OFFSET 28
+
+#define PTP_V1_UUID_LENGTH 6
+#define PTP_V1_UUID_OFFSET 50
+
+#define PTP_V1_SEQUENCE_LENGTH 2
+#define PTP_V1_SEQUENCE_OFFSET 58
+
+/* The minimum length of a PTP V1 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define PTP_V1_MIN_LENGTH 64
+
+#define PTP_V2_VERSION_LENGTH 1
+#define PTP_V2_VERSION_OFFSET 29
+
+#define PTP_V2_UUID_LENGTH 8
+#define PTP_V2_UUID_OFFSET 48
+
+/* Although PTP V2 UUIDs are comprised a ClockIdentity (8) and PortNumber (2),
+ * the MC only captures the last six bytes of the clock identity. These values
+ * reflect those, not the ones used in the standard. The standard permits
+ * mapping of V1 UUIDs to V2 UUIDs with these same values.
+ */
+#define PTP_V2_MC_UUID_LENGTH 6
+#define PTP_V2_MC_UUID_OFFSET 50
+
+#define PTP_V2_SEQUENCE_LENGTH 2
+#define PTP_V2_SEQUENCE_OFFSET 58
+
+/* The minimum length of a PTP V2 packet for offsets, etc. to be valid:
+ * includes IP header.
+ */
+#define PTP_V2_MIN_LENGTH 63
+
+#define PTP_MIN_LENGTH 63
+
+#define PTP_ADDRESS 0xe0000181 /* 224.0.1.129 */
+#define PTP_EVENT_PORT 319
+#define PTP_GENERAL_PORT 320
+
+/* Annoyingly the format of the version numbers are different between
+ * versions 1 and 2 so it isn't possible to simply look for 1 or 2.
+ */
+#define PTP_VERSION_V1 1
+
+#define PTP_VERSION_V2 2
+#define PTP_VERSION_V2_MASK 0x0f
+
+enum ptp_packet_state {
+ PTP_PACKET_STATE_UNMATCHED = 0,
+ PTP_PACKET_STATE_MATCHED,
+ PTP_PACKET_STATE_TIMED_OUT,
+ PTP_PACKET_STATE_MATCH_UNWANTED
+};
+
+/* NIC synchronised with single word of time only comprising
+ * partial seconds and full nanoseconds: 10^9 ~ 2^30 so 2 bits for seconds.
+ */
+#define MC_NANOSECOND_BITS 30
+#define MC_NANOSECOND_MASK ((1 << MC_NANOSECOND_BITS) - 1)
+#define MC_SECOND_MASK ((1 << (32 - MC_NANOSECOND_BITS)) - 1)
+
+/* Maximum parts-per-billion adjustment that is acceptable */
+#define MAX_PPB 1000000
+
+/* Number of bits required to hold the above */
+#define MAX_PPB_BITS 20
+
+/* Number of extra bits allowed when calculating fractional ns.
+ * EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS + MAX_PPB_BITS should
+ * be less than 63.
+ */
+#define PPB_EXTRA_BITS 2
+
+/* Precalculate scale word to avoid long long division at runtime */
+#define PPB_SCALE_WORD ((1LL << (PPB_EXTRA_BITS + MC_CMD_PTP_IN_ADJUST_BITS +\
+ MAX_PPB_BITS)) / 1000000000LL)
+
+#define PTP_SYNC_ATTEMPTS 4
+
+/**
+ * struct efx_ptp_match - Matching structure, stored in sk_buff's cb area.
+ * @words: UUID and (partial) sequence number
+ * @expiry: Time after which the packet should be delivered irrespective of
+ * event arrival.
+ * @state: The state of the packet - whether it is ready for processing or
+ * whether that is of no interest.
+ */
+struct efx_ptp_match {
+ u32 words[DIV_ROUND_UP(PTP_V1_UUID_LENGTH, 4)];
+ unsigned long expiry;
+ enum ptp_packet_state state;
+};
+
+/**
+ * struct efx_ptp_event_rx - A PTP receive event (from MC)
+ * @seq0: First part of (PTP) UUID
+ * @seq1: Second part of (PTP) UUID and sequence number
+ * @hwtimestamp: Event timestamp
+ */
+struct efx_ptp_event_rx {
+ struct list_head link;
+ u32 seq0;
+ u32 seq1;
+ ktime_t hwtimestamp;
+ unsigned long expiry;
+};
+
+/**
+ * struct efx_ptp_timeset - Synchronisation between host and MC
+ * @host_start: Host time immediately before hardware timestamp taken
+ * @major: Hardware timestamp, major
+ * @minor: Hardware timestamp, minor
+ * @host_end: Host time immediately after hardware timestamp taken
+ * @wait: Number of NIC clock ticks between hardware timestamp being read and
+ * host end time being seen
+ * @window: Difference of host_end and host_start
+ * @valid: Whether this timeset is valid
+ */
+struct efx_ptp_timeset {
+ u32 host_start;
+ u32 major;
+ u32 minor;
+ u32 host_end;
+ u32 wait;
+ u32 window; /* Derived: end - start, allowing for wrap */
+};
+
+/**
+ * struct efx_ptp_data - Precision Time Protocol (PTP) state
+ * @efx: The NIC context
+ * @channel: The PTP channel (Siena only)
+ * @rx_ts_inline: Flag for whether RX timestamps are inline (else they are
+ * separate events)
+ * @rxq: Receive queue (awaiting timestamps)
+ * @txq: Transmit queue
+ * @evt_list: List of MC receive events awaiting packets
+ * @evt_free_list: List of free events
+ * @evt_lock: Lock for manipulating evt_list and evt_free_list
+ * @rx_evts: Instantiated events (on evt_list and evt_free_list)
+ * @workwq: Work queue for processing pending PTP operations
+ * @work: Work task
+ * @reset_required: A serious error has occurred and the PTP task needs to be
+ * reset (disable, enable).
+ * @rxfilter_event: Receive filter when operating
+ * @rxfilter_general: Receive filter when operating
+ * @config: Current timestamp configuration
+ * @enabled: PTP operation enabled
+ * @mode: Mode in which PTP operating (PTP version)
+ * @time_format: Time format supported by this NIC
+ * @ns_to_nic_time: Function to convert from scalar nanoseconds to NIC time
+ * @nic_to_kernel_time: Function to convert from NIC to kernel time
+ * @min_synchronisation_ns: Minimum acceptable corrected sync window
+ * @ts_corrections.tx: Required driver correction of transmit timestamps
+ * @ts_corrections.rx: Required driver correction of receive timestamps
+ * @ts_corrections.pps_out: PPS output error (information only)
+ * @ts_corrections.pps_in: Required driver correction of PPS input timestamps
+ * @evt_frags: Partly assembled PTP events
+ * @evt_frag_idx: Current fragment number
+ * @evt_code: Last event code
+ * @start: Address at which MC indicates ready for synchronisation
+ * @host_time_pps: Host time at last PPS
+ * @current_adjfreq: Current ppb adjustment.
+ * @phc_clock: Pointer to registered phc device (if primary function)
+ * @phc_clock_info: Registration structure for phc device
+ * @pps_work: pps work task for handling pps events
+ * @pps_workwq: pps work queue
+ * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled
+ * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids
+ * allocations in main data path).
+ * @good_syncs: Number of successful synchronisations.
+ * @fast_syncs: Number of synchronisations requiring short delay
+ * @bad_syncs: Number of failed synchronisations.
+ * @sync_timeouts: Number of synchronisation timeouts
+ * @no_time_syncs: Number of synchronisations with no good times.
+ * @invalid_sync_windows: Number of sync windows with bad durations.
+ * @undersize_sync_windows: Number of corrected sync windows that are too small
+ * @oversize_sync_windows: Number of corrected sync windows that are too large
+ * @rx_no_timestamp: Number of packets received without a timestamp.
+ * @timeset: Last set of synchronisation statistics.
+ */
+struct efx_ptp_data {
+ struct efx_nic *efx;
+ struct efx_channel *channel;
+ bool rx_ts_inline;
+ struct sk_buff_head rxq;
+ struct sk_buff_head txq;
+ struct list_head evt_list;
+ struct list_head evt_free_list;
+ spinlock_t evt_lock;
+ struct efx_ptp_event_rx rx_evts[MAX_RECEIVE_EVENTS];
+ struct workqueue_struct *workwq;
+ struct work_struct work;
+ bool reset_required;
+ u32 rxfilter_event;
+ u32 rxfilter_general;
+ bool rxfilter_installed;
+ struct hwtstamp_config config;
+ bool enabled;
+ unsigned int mode;
+ unsigned int time_format;
+ void (*ns_to_nic_time)(s64 ns, u32 *nic_major, u32 *nic_minor);
+ ktime_t (*nic_to_kernel_time)(u32 nic_major, u32 nic_minor,
+ s32 correction);
+ unsigned int min_synchronisation_ns;
+ struct {
+ s32 tx;
+ s32 rx;
+ s32 pps_out;
+ s32 pps_in;
+ } ts_corrections;
+ efx_qword_t evt_frags[MAX_EVENT_FRAGS];
+ int evt_frag_idx;
+ int evt_code;
+ struct efx_buffer start;
+ struct pps_event_time host_time_pps;
+ s64 current_adjfreq;
+ struct ptp_clock *phc_clock;
+ struct ptp_clock_info phc_clock_info;
+ struct work_struct pps_work;
+ struct workqueue_struct *pps_workwq;
+ bool nic_ts_enabled;
+ MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX);
+
+ unsigned int good_syncs;
+ unsigned int fast_syncs;
+ unsigned int bad_syncs;
+ unsigned int sync_timeouts;
+ unsigned int no_time_syncs;
+ unsigned int invalid_sync_windows;
+ unsigned int undersize_sync_windows;
+ unsigned int oversize_sync_windows;
+ unsigned int rx_no_timestamp;
+ struct efx_ptp_timeset
+ timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM];
+};
+
+static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta);
+static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta);
+static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts);
+static int efx_phc_settime(struct ptp_clock_info *ptp,
+ const struct timespec *e_ts);
+static int efx_phc_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *request, int on);
+
+#define PTP_SW_STAT(ext_name, field_name) \
+ { #ext_name, 0, offsetof(struct efx_ptp_data, field_name) }
+#define PTP_MC_STAT(ext_name, mcdi_name) \
+ { #ext_name, 32, MC_CMD_PTP_OUT_STATUS_STATS_ ## mcdi_name ## _OFST }
+static const struct efx_hw_stat_desc efx_ptp_stat_desc[] = {
+ PTP_SW_STAT(ptp_good_syncs, good_syncs),
+ PTP_SW_STAT(ptp_fast_syncs, fast_syncs),
+ PTP_SW_STAT(ptp_bad_syncs, bad_syncs),
+ PTP_SW_STAT(ptp_sync_timeouts, sync_timeouts),
+ PTP_SW_STAT(ptp_no_time_syncs, no_time_syncs),
+ PTP_SW_STAT(ptp_invalid_sync_windows, invalid_sync_windows),
+ PTP_SW_STAT(ptp_undersize_sync_windows, undersize_sync_windows),
+ PTP_SW_STAT(ptp_oversize_sync_windows, oversize_sync_windows),
+ PTP_SW_STAT(ptp_rx_no_timestamp, rx_no_timestamp),
+ PTP_MC_STAT(ptp_tx_timestamp_packets, TX),
+ PTP_MC_STAT(ptp_rx_timestamp_packets, RX),
+ PTP_MC_STAT(ptp_timestamp_packets, TS),
+ PTP_MC_STAT(ptp_filter_matches, FM),
+ PTP_MC_STAT(ptp_non_filter_matches, NFM),
+};
+#define PTP_STAT_COUNT ARRAY_SIZE(efx_ptp_stat_desc)
+static const unsigned long efx_ptp_stat_mask[] = {
+ [0 ... BITS_TO_LONGS(PTP_STAT_COUNT) - 1] = ~0UL,
+};
+
+size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings)
+{
+ if (!efx->ptp_data)
+ return 0;
+
+ return efx_nic_describe_stats(efx_ptp_stat_desc, PTP_STAT_COUNT,
+ efx_ptp_stat_mask, strings);
+}
+
+size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_STATUS_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_STATUS_LEN);
+ size_t i;
+ int rc;
+
+ if (!efx->ptp_data)
+ return 0;
+
+ /* Copy software statistics */
+ for (i = 0; i < PTP_STAT_COUNT; i++) {
+ if (efx_ptp_stat_desc[i].dma_width)
+ continue;
+ stats[i] = *(unsigned int *)((char *)efx->ptp_data +
+ efx_ptp_stat_desc[i].offset);
+ }
+
+ /* Fetch MC statistics. We *must* fill in all statistics or
+ * risk leaking kernel memory to userland, so if the MCDI
+ * request fails we pretend we got zeroes.
+ */
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_STATUS);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ if (rc) {
+ netif_err(efx, hw, efx->net_dev,
+ "MC_CMD_PTP_OP_STATUS failed (%d)\n", rc);
+ memset(outbuf, 0, sizeof(outbuf));
+ }
+ efx_nic_update_stats(efx_ptp_stat_desc, PTP_STAT_COUNT,
+ efx_ptp_stat_mask,
+ stats, _MCDI_PTR(outbuf, 0), false);
+
+ return PTP_STAT_COUNT;
+}
+
+/* For Siena platforms NIC time is s and ns */
+static void efx_ptp_ns_to_s_ns(s64 ns, u32 *nic_major, u32 *nic_minor)
+{
+ struct timespec ts = ns_to_timespec(ns);
+ *nic_major = ts.tv_sec;
+ *nic_minor = ts.tv_nsec;
+}
+
+static ktime_t efx_ptp_s_ns_to_ktime_correction(u32 nic_major, u32 nic_minor,
+ s32 correction)
+{
+ ktime_t kt = ktime_set(nic_major, nic_minor);
+ if (correction >= 0)
+ kt = ktime_add_ns(kt, (u64)correction);
+ else
+ kt = ktime_sub_ns(kt, (u64)-correction);
+ return kt;
+}
+
+/* To convert from s27 format to ns we multiply then divide by a power of 2.
+ * For the conversion from ns to s27, the operation is also converted to a
+ * multiply and shift.
+ */
+#define S27_TO_NS_SHIFT (27)
+#define NS_TO_S27_MULT (((1ULL << 63) + NSEC_PER_SEC / 2) / NSEC_PER_SEC)
+#define NS_TO_S27_SHIFT (63 - S27_TO_NS_SHIFT)
+#define S27_MINOR_MAX (1 << S27_TO_NS_SHIFT)
+
+/* For Huntington platforms NIC time is in seconds and fractions of a second
+ * where the minor register only uses 27 bits in units of 2^-27s.
+ */
+static void efx_ptp_ns_to_s27(s64 ns, u32 *nic_major, u32 *nic_minor)
+{
+ struct timespec ts = ns_to_timespec(ns);
+ u32 maj = ts.tv_sec;
+ u32 min = (u32)(((u64)ts.tv_nsec * NS_TO_S27_MULT +
+ (1ULL << (NS_TO_S27_SHIFT - 1))) >> NS_TO_S27_SHIFT);
+
+ /* The conversion can result in the minor value exceeding the maximum.
+ * In this case, round up to the next second.
+ */
+ if (min >= S27_MINOR_MAX) {
+ min -= S27_MINOR_MAX;
+ maj++;
+ }
+
+ *nic_major = maj;
+ *nic_minor = min;
+}
+
+static inline ktime_t efx_ptp_s27_to_ktime(u32 nic_major, u32 nic_minor)
+{
+ u32 ns = (u32)(((u64)nic_minor * NSEC_PER_SEC +
+ (1ULL << (S27_TO_NS_SHIFT - 1))) >> S27_TO_NS_SHIFT);
+ return ktime_set(nic_major, ns);
+}
+
+static ktime_t efx_ptp_s27_to_ktime_correction(u32 nic_major, u32 nic_minor,
+ s32 correction)
+{
+ /* Apply the correction and deal with carry */
+ nic_minor += correction;
+ if ((s32)nic_minor < 0) {
+ nic_minor += S27_MINOR_MAX;
+ nic_major--;
+ } else if (nic_minor >= S27_MINOR_MAX) {
+ nic_minor -= S27_MINOR_MAX;
+ nic_major++;
+ }
+
+ return efx_ptp_s27_to_ktime(nic_major, nic_minor);
+}
+
+/* Get PTP attributes and set up time conversions */
+static int efx_ptp_get_attributes(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_GET_ATTRIBUTES_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN);
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ int rc;
+ u32 fmt;
+ size_t out_len;
+
+ /* Get the PTP attributes. If the NIC doesn't support the operation we
+ * use the default format for compatibility with older NICs i.e.
+ * seconds and nanoseconds.
+ */
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_GET_ATTRIBUTES);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), &out_len);
+ if (rc == 0)
+ fmt = MCDI_DWORD(outbuf, PTP_OUT_GET_ATTRIBUTES_TIME_FORMAT);
+ else if (rc == -EINVAL)
+ fmt = MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS;
+ else
+ return rc;
+
+ if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION) {
+ ptp->ns_to_nic_time = efx_ptp_ns_to_s27;
+ ptp->nic_to_kernel_time = efx_ptp_s27_to_ktime_correction;
+ } else if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS) {
+ ptp->ns_to_nic_time = efx_ptp_ns_to_s_ns;
+ ptp->nic_to_kernel_time = efx_ptp_s_ns_to_ktime_correction;
+ } else {
+ return -ERANGE;
+ }
+
+ ptp->time_format = fmt;
+
+ /* MC_CMD_PTP_OP_GET_ATTRIBUTES is an extended version of an older
+ * operation MC_CMD_PTP_OP_GET_TIME_FORMAT that also returns a value
+ * to use for the minimum acceptable corrected synchronization window.
+ * If we have the extra information store it. For older firmware that
+ * does not implement the extended command use the default value.
+ */
+ if (rc == 0 && out_len >= MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN)
+ ptp->min_synchronisation_ns =
+ MCDI_DWORD(outbuf,
+ PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN);
+ else
+ ptp->min_synchronisation_ns = DEFAULT_MIN_SYNCHRONISATION_NS;
+
+ return 0;
+}
+
+/* Get PTP timestamp corrections */
+static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN);
+ int rc;
+
+ /* Get the timestamp corrections from the NIC. If this operation is
+ * not supported (older NICs) then no correction is required.
+ */
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP,
+ MC_CMD_PTP_OP_GET_TIMESTAMP_CORRECTIONS);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ if (rc == 0) {
+ efx->ptp_data->ts_corrections.tx = MCDI_DWORD(outbuf,
+ PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT);
+ efx->ptp_data->ts_corrections.rx = MCDI_DWORD(outbuf,
+ PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE);
+ efx->ptp_data->ts_corrections.pps_out = MCDI_DWORD(outbuf,
+ PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT);
+ efx->ptp_data->ts_corrections.pps_in = MCDI_DWORD(outbuf,
+ PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN);
+ } else if (rc == -EINVAL) {
+ efx->ptp_data->ts_corrections.tx = 0;
+ efx->ptp_data->ts_corrections.rx = 0;
+ efx->ptp_data->ts_corrections.pps_out = 0;
+ efx->ptp_data->ts_corrections.pps_in = 0;
+ } else {
+ return rc;
+ }
+
+ return 0;
+}
+
+/* Enable MCDI PTP support. */
+static int efx_ptp_enable(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ENABLE_LEN);
+ MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE,
+ efx->ptp_data->channel ?
+ efx->ptp_data->channel->channel : 0);
+ MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode);
+
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ rc = (rc == -EALREADY) ? 0 : rc;
+ if (rc)
+ efx_mcdi_display_error(efx, MC_CMD_PTP,
+ MC_CMD_PTP_IN_ENABLE_LEN,
+ outbuf, sizeof(outbuf), rc);
+ return rc;
+}
+
+/* Disable MCDI PTP support.
+ *
+ * Note that this function should never rely on the presence of ptp_data -
+ * may be called before that exists.
+ */
+static int efx_ptp_disable(struct efx_nic *efx)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_DISABLE_LEN);
+ MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0);
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ rc = (rc == -EALREADY) ? 0 : rc;
+ if (rc)
+ efx_mcdi_display_error(efx, MC_CMD_PTP,
+ MC_CMD_PTP_IN_DISABLE_LEN,
+ outbuf, sizeof(outbuf), rc);
+ return rc;
+}
+
+static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q)
+{
+ struct sk_buff *skb;
+
+ while ((skb = skb_dequeue(q))) {
+ local_bh_disable();
+ netif_receive_skb(skb);
+ local_bh_enable();
+ }
+}
+
+static void efx_ptp_handle_no_channel(struct efx_nic *efx)
+{
+ netif_err(efx, drv, efx->net_dev,
+ "ERROR: PTP requires MSI-X and 1 additional interrupt"
+ "vector. PTP disabled\n");
+}
+
+/* Repeatedly send the host time to the MC which will capture the hardware
+ * time.
+ */
+static void efx_ptp_send_times(struct efx_nic *efx,
+ struct pps_event_time *last_time)
+{
+ struct pps_event_time now;
+ struct timespec limit;
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct timespec start;
+ int *mc_running = ptp->start.addr;
+
+ pps_get_ts(&now);
+ start = now.ts_real;
+ limit = now.ts_real;
+ timespec_add_ns(&limit, SYNCHRONISE_PERIOD_NS);
+
+ /* Write host time for specified period or until MC is done */
+ while ((timespec_compare(&now.ts_real, &limit) < 0) &&
+ ACCESS_ONCE(*mc_running)) {
+ struct timespec update_time;
+ unsigned int host_time;
+
+ /* Don't update continuously to avoid saturating the PCIe bus */
+ update_time = now.ts_real;
+ timespec_add_ns(&update_time, SYNCHRONISATION_GRANULARITY_NS);
+ do {
+ pps_get_ts(&now);
+ } while ((timespec_compare(&now.ts_real, &update_time) < 0) &&
+ ACCESS_ONCE(*mc_running));
+
+ /* Synchronise NIC with single word of time only */
+ host_time = (now.ts_real.tv_sec << MC_NANOSECOND_BITS |
+ now.ts_real.tv_nsec);
+ /* Update host time in NIC memory */
+ efx->type->ptp_write_host_time(efx, host_time);
+ }
+ *last_time = now;
+}
+
+/* Read a timeset from the MC's results and partial process. */
+static void efx_ptp_read_timeset(MCDI_DECLARE_STRUCT_PTR(data),
+ struct efx_ptp_timeset *timeset)
+{
+ unsigned start_ns, end_ns;
+
+ timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART);
+ timeset->major = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MAJOR);
+ timeset->minor = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MINOR);
+ timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND),
+ timeset->wait = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS);
+
+ /* Ignore seconds */
+ start_ns = timeset->host_start & MC_NANOSECOND_MASK;
+ end_ns = timeset->host_end & MC_NANOSECOND_MASK;
+ /* Allow for rollover */
+ if (end_ns < start_ns)
+ end_ns += NSEC_PER_SEC;
+ /* Determine duration of operation */
+ timeset->window = end_ns - start_ns;
+}
+
+/* Process times received from MC.
+ *
+ * Extract times from returned results, and establish the minimum value
+ * seen. The minimum value represents the "best" possible time and events
+ * too much greater than this are rejected - the machine is, perhaps, too
+ * busy. A number of readings are taken so that, hopefully, at least one good
+ * synchronisation will be seen in the results.
+ */
+static int
+efx_ptp_process_times(struct efx_nic *efx, MCDI_DECLARE_STRUCT_PTR(synch_buf),
+ size_t response_length,
+ const struct pps_event_time *last_time)
+{
+ unsigned number_readings =
+ MCDI_VAR_ARRAY_LEN(response_length,
+ PTP_OUT_SYNCHRONIZE_TIMESET);
+ unsigned i;
+ unsigned ngood = 0;
+ unsigned last_good = 0;
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ u32 last_sec;
+ u32 start_sec;
+ struct timespec delta;
+ ktime_t mc_time;
+
+ if (number_readings == 0)
+ return -EAGAIN;
+
+ /* Read the set of results and find the last good host-MC
+ * synchronization result. The MC times when it finishes reading the
+ * host time so the corrected window time should be fairly constant
+ * for a given platform. Increment stats for any results that appear
+ * to be erroneous.
+ */
+ for (i = 0; i < number_readings; i++) {
+ s32 window, corrected;
+ struct timespec wait;
+
+ efx_ptp_read_timeset(
+ MCDI_ARRAY_STRUCT_PTR(synch_buf,
+ PTP_OUT_SYNCHRONIZE_TIMESET, i),
+ &ptp->timeset[i]);
+
+ wait = ktime_to_timespec(
+ ptp->nic_to_kernel_time(0, ptp->timeset[i].wait, 0));
+ window = ptp->timeset[i].window;
+ corrected = window - wait.tv_nsec;
+
+ /* We expect the uncorrected synchronization window to be at
+ * least as large as the interval between host start and end
+ * times. If it is smaller than this then this is mostly likely
+ * to be a consequence of the host's time being adjusted.
+ * Check that the corrected sync window is in a reasonable
+ * range. If it is out of range it is likely to be because an
+ * interrupt or other delay occurred between reading the system
+ * time and writing it to MC memory.
+ */
+ if (window < SYNCHRONISATION_GRANULARITY_NS) {
+ ++ptp->invalid_sync_windows;
+ } else if (corrected >= MAX_SYNCHRONISATION_NS) {
+ ++ptp->oversize_sync_windows;
+ } else if (corrected < ptp->min_synchronisation_ns) {
+ ++ptp->undersize_sync_windows;
+ } else {
+ ngood++;
+ last_good = i;
+ }
+ }
+
+ if (ngood == 0) {
+ netif_warn(efx, drv, efx->net_dev,
+ "PTP no suitable synchronisations\n");
+ return -EAGAIN;
+ }
+
+ /* Calculate delay from last good sync (host time) to last_time.
+ * It is possible that the seconds rolled over between taking
+ * the start reading and the last value written by the host. The
+ * timescales are such that a gap of more than one second is never
+ * expected. delta is *not* normalised.
+ */
+ start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS;
+ last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK;
+ if (start_sec != last_sec &&
+ ((start_sec + 1) & MC_SECOND_MASK) != last_sec) {
+ netif_warn(efx, hw, efx->net_dev,
+ "PTP bad synchronisation seconds\n");
+ return -EAGAIN;
+ }
+ delta.tv_sec = (last_sec - start_sec) & 1;
+ delta.tv_nsec =
+ last_time->ts_real.tv_nsec -
+ (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK);
+
+ /* Convert the NIC time at last good sync into kernel time.
+ * No correction is required - this time is the output of a
+ * firmware process.
+ */
+ mc_time = ptp->nic_to_kernel_time(ptp->timeset[last_good].major,
+ ptp->timeset[last_good].minor, 0);
+
+ /* Calculate delay from NIC top of second to last_time */
+ delta.tv_nsec += ktime_to_timespec(mc_time).tv_nsec;
+
+ /* Set PPS timestamp to match NIC top of second */
+ ptp->host_time_pps = *last_time;
+ pps_sub_ts(&ptp->host_time_pps, delta);
+
+ return 0;
+}
+
+/* Synchronize times between the host and the MC */
+static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ MCDI_DECLARE_BUF(synch_buf, MC_CMD_PTP_OUT_SYNCHRONIZE_LENMAX);
+ size_t response_length;
+ int rc;
+ unsigned long timeout;
+ struct pps_event_time last_time = {};
+ unsigned int loops = 0;
+ int *start = ptp->start.addr;
+
+ MCDI_SET_DWORD(synch_buf, PTP_IN_OP, MC_CMD_PTP_OP_SYNCHRONIZE);
+ MCDI_SET_DWORD(synch_buf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_DWORD(synch_buf, PTP_IN_SYNCHRONIZE_NUMTIMESETS,
+ num_readings);
+ MCDI_SET_QWORD(synch_buf, PTP_IN_SYNCHRONIZE_START_ADDR,
+ ptp->start.dma_addr);
+
+ /* Clear flag that signals MC ready */
+ ACCESS_ONCE(*start) = 0;
+ rc = efx_mcdi_rpc_start(efx, MC_CMD_PTP, synch_buf,
+ MC_CMD_PTP_IN_SYNCHRONIZE_LEN);
+ EFX_BUG_ON_PARANOID(rc);
+
+ /* Wait for start from MCDI (or timeout) */
+ timeout = jiffies + msecs_to_jiffies(MAX_SYNCHRONISE_WAIT_MS);
+ while (!ACCESS_ONCE(*start) && (time_before(jiffies, timeout))) {
+ udelay(20); /* Usually start MCDI execution quickly */
+ loops++;
+ }
+
+ if (loops <= 1)
+ ++ptp->fast_syncs;
+ if (!time_before(jiffies, timeout))
+ ++ptp->sync_timeouts;
+
+ if (ACCESS_ONCE(*start))
+ efx_ptp_send_times(efx, &last_time);
+
+ /* Collect results */
+ rc = efx_mcdi_rpc_finish(efx, MC_CMD_PTP,
+ MC_CMD_PTP_IN_SYNCHRONIZE_LEN,
+ synch_buf, sizeof(synch_buf),
+ &response_length);
+ if (rc == 0) {
+ rc = efx_ptp_process_times(efx, synch_buf, response_length,
+ &last_time);
+ if (rc == 0)
+ ++ptp->good_syncs;
+ else
+ ++ptp->no_time_syncs;
+ }
+
+ /* Increment the bad syncs counter if the synchronize fails, whatever
+ * the reason.
+ */
+ if (rc != 0)
+ ++ptp->bad_syncs;
+
+ return rc;
+}
+
+/* Transmit a PTP packet, via the MCDI interface, to the wire. */
+static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb)
+{
+ struct efx_ptp_data *ptp_data = efx->ptp_data;
+ struct skb_shared_hwtstamps timestamps;
+ int rc = -EIO;
+ MCDI_DECLARE_BUF(txtime, MC_CMD_PTP_OUT_TRANSMIT_LEN);
+ size_t len;
+
+ MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_OP, MC_CMD_PTP_OP_TRANSMIT);
+ MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_DWORD(ptp_data->txbuf, PTP_IN_TRANSMIT_LENGTH, skb->len);
+ if (skb_shinfo(skb)->nr_frags != 0) {
+ rc = skb_linearize(skb);
+ if (rc != 0)
+ goto fail;
+ }
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ rc = skb_checksum_help(skb);
+ if (rc != 0)
+ goto fail;
+ }
+ skb_copy_from_linear_data(skb,
+ MCDI_PTR(ptp_data->txbuf,
+ PTP_IN_TRANSMIT_PACKET),
+ skb->len);
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP,
+ ptp_data->txbuf, MC_CMD_PTP_IN_TRANSMIT_LEN(skb->len),
+ txtime, sizeof(txtime), &len);
+ if (rc != 0)
+ goto fail;
+
+ memset(&timestamps, 0, sizeof(timestamps));
+ timestamps.hwtstamp = ptp_data->nic_to_kernel_time(
+ MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MAJOR),
+ MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MINOR),
+ ptp_data->ts_corrections.tx);
+
+ skb_tstamp_tx(skb, &timestamps);
+
+ rc = 0;
+
+fail:
+ dev_kfree_skb(skb);
+
+ return rc;
+}
+
+static void efx_ptp_drop_time_expired_events(struct efx_nic *efx)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct list_head *cursor;
+ struct list_head *next;
+
+ if (ptp->rx_ts_inline)
+ return;
+
+ /* Drop time-expired events */
+ spin_lock_bh(&ptp->evt_lock);
+ if (!list_empty(&ptp->evt_list)) {
+ list_for_each_safe(cursor, next, &ptp->evt_list) {
+ struct efx_ptp_event_rx *evt;
+
+ evt = list_entry(cursor, struct efx_ptp_event_rx,
+ link);
+ if (time_after(jiffies, evt->expiry)) {
+ list_move(&evt->link, &ptp->evt_free_list);
+ netif_warn(efx, hw, efx->net_dev,
+ "PTP rx event dropped\n");
+ }
+ }
+ }
+ spin_unlock_bh(&ptp->evt_lock);
+}
+
+static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx,
+ struct sk_buff *skb)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ bool evts_waiting;
+ struct list_head *cursor;
+ struct list_head *next;
+ struct efx_ptp_match *match;
+ enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED;
+
+ WARN_ON_ONCE(ptp->rx_ts_inline);
+
+ spin_lock_bh(&ptp->evt_lock);
+ evts_waiting = !list_empty(&ptp->evt_list);
+ spin_unlock_bh(&ptp->evt_lock);
+
+ if (!evts_waiting)
+ return PTP_PACKET_STATE_UNMATCHED;
+
+ match = (struct efx_ptp_match *)skb->cb;
+ /* Look for a matching timestamp in the event queue */
+ spin_lock_bh(&ptp->evt_lock);
+ list_for_each_safe(cursor, next, &ptp->evt_list) {
+ struct efx_ptp_event_rx *evt;
+
+ evt = list_entry(cursor, struct efx_ptp_event_rx, link);
+ if ((evt->seq0 == match->words[0]) &&
+ (evt->seq1 == match->words[1])) {
+ struct skb_shared_hwtstamps *timestamps;
+
+ /* Match - add in hardware timestamp */
+ timestamps = skb_hwtstamps(skb);
+ timestamps->hwtstamp = evt->hwtimestamp;
+
+ match->state = PTP_PACKET_STATE_MATCHED;
+ rc = PTP_PACKET_STATE_MATCHED;
+ list_move(&evt->link, &ptp->evt_free_list);
+ break;
+ }
+ }
+ spin_unlock_bh(&ptp->evt_lock);
+
+ return rc;
+}
+
+/* Process any queued receive events and corresponding packets
+ *
+ * q is returned with all the packets that are ready for delivery.
+ */
+static void efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct sk_buff *skb;
+
+ while ((skb = skb_dequeue(&ptp->rxq))) {
+ struct efx_ptp_match *match;
+
+ match = (struct efx_ptp_match *)skb->cb;
+ if (match->state == PTP_PACKET_STATE_MATCH_UNWANTED) {
+ __skb_queue_tail(q, skb);
+ } else if (efx_ptp_match_rx(efx, skb) ==
+ PTP_PACKET_STATE_MATCHED) {
+ __skb_queue_tail(q, skb);
+ } else if (time_after(jiffies, match->expiry)) {
+ match->state = PTP_PACKET_STATE_TIMED_OUT;
+ ++ptp->rx_no_timestamp;
+ __skb_queue_tail(q, skb);
+ } else {
+ /* Replace unprocessed entry and stop */
+ skb_queue_head(&ptp->rxq, skb);
+ break;
+ }
+ }
+}
+
+/* Complete processing of a received packet */
+static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb)
+{
+ local_bh_disable();
+ netif_receive_skb(skb);
+ local_bh_enable();
+}
+
+static void efx_ptp_remove_multicast_filters(struct efx_nic *efx)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+
+ if (ptp->rxfilter_installed) {
+ efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+ ptp->rxfilter_general);
+ efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+ ptp->rxfilter_event);
+ ptp->rxfilter_installed = false;
+ }
+}
+
+static int efx_ptp_insert_multicast_filters(struct efx_nic *efx)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct efx_filter_spec rxfilter;
+ int rc;
+
+ if (!ptp->channel || ptp->rxfilter_installed)
+ return 0;
+
+ /* Must filter on both event and general ports to ensure
+ * that there is no packet re-ordering.
+ */
+ efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
+ efx_rx_queue_index(
+ efx_channel_get_rx_queue(ptp->channel)));
+ rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
+ htonl(PTP_ADDRESS),
+ htons(PTP_EVENT_PORT));
+ if (rc != 0)
+ return rc;
+
+ rc = efx_filter_insert_filter(efx, &rxfilter, true);
+ if (rc < 0)
+ return rc;
+ ptp->rxfilter_event = rc;
+
+ efx_filter_init_rx(&rxfilter, EFX_FILTER_PRI_REQUIRED, 0,
+ efx_rx_queue_index(
+ efx_channel_get_rx_queue(ptp->channel)));
+ rc = efx_filter_set_ipv4_local(&rxfilter, IPPROTO_UDP,
+ htonl(PTP_ADDRESS),
+ htons(PTP_GENERAL_PORT));
+ if (rc != 0)
+ goto fail;
+
+ rc = efx_filter_insert_filter(efx, &rxfilter, true);
+ if (rc < 0)
+ goto fail;
+ ptp->rxfilter_general = rc;
+
+ ptp->rxfilter_installed = true;
+ return 0;
+
+fail:
+ efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+ ptp->rxfilter_event);
+ return rc;
+}
+
+static int efx_ptp_start(struct efx_nic *efx)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ int rc;
+
+ ptp->reset_required = false;
+
+ rc = efx_ptp_insert_multicast_filters(efx);
+ if (rc)
+ return rc;
+
+ rc = efx_ptp_enable(efx);
+ if (rc != 0)
+ goto fail;
+
+ ptp->evt_frag_idx = 0;
+ ptp->current_adjfreq = 0;
+
+ return 0;
+
+fail:
+ efx_ptp_remove_multicast_filters(efx);
+ return rc;
+}
+
+static int efx_ptp_stop(struct efx_nic *efx)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct list_head *cursor;
+ struct list_head *next;
+ int rc;
+
+ if (ptp == NULL)
+ return 0;
+
+ rc = efx_ptp_disable(efx);
+
+ efx_ptp_remove_multicast_filters(efx);
+
+ /* Make sure RX packets are really delivered */
+ efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq);
+ skb_queue_purge(&efx->ptp_data->txq);
+
+ /* Drop any pending receive events */
+ spin_lock_bh(&efx->ptp_data->evt_lock);
+ list_for_each_safe(cursor, next, &efx->ptp_data->evt_list) {
+ list_move(cursor, &efx->ptp_data->evt_free_list);
+ }
+ spin_unlock_bh(&efx->ptp_data->evt_lock);
+
+ return rc;
+}
+
+static int efx_ptp_restart(struct efx_nic *efx)
+{
+ if (efx->ptp_data && efx->ptp_data->enabled)
+ return efx_ptp_start(efx);
+ return 0;
+}
+
+static void efx_ptp_pps_worker(struct work_struct *work)
+{
+ struct efx_ptp_data *ptp =
+ container_of(work, struct efx_ptp_data, pps_work);
+ struct efx_nic *efx = ptp->efx;
+ struct ptp_clock_event ptp_evt;
+
+ if (efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS))
+ return;
+
+ ptp_evt.type = PTP_CLOCK_PPSUSR;
+ ptp_evt.pps_times = ptp->host_time_pps;
+ ptp_clock_event(ptp->phc_clock, &ptp_evt);
+}
+
+static void efx_ptp_worker(struct work_struct *work)
+{
+ struct efx_ptp_data *ptp_data =
+ container_of(work, struct efx_ptp_data, work);
+ struct efx_nic *efx = ptp_data->efx;
+ struct sk_buff *skb;
+ struct sk_buff_head tempq;
+
+ if (ptp_data->reset_required) {
+ efx_ptp_stop(efx);
+ efx_ptp_start(efx);
+ return;
+ }
+
+ efx_ptp_drop_time_expired_events(efx);
+
+ __skb_queue_head_init(&tempq);
+ efx_ptp_process_events(efx, &tempq);
+
+ while ((skb = skb_dequeue(&ptp_data->txq)))
+ efx_ptp_xmit_skb(efx, skb);
+
+ while ((skb = __skb_dequeue(&tempq)))
+ efx_ptp_process_rx(efx, skb);
+}
+
+static const struct ptp_clock_info efx_phc_clock_info = {
+ .owner = THIS_MODULE,
+ .name = "sfc",
+ .max_adj = MAX_PPB,
+ .n_alarm = 0,
+ .n_ext_ts = 0,
+ .n_per_out = 0,
+ .n_pins = 0,
+ .pps = 1,
+ .adjfreq = efx_phc_adjfreq,
+ .adjtime = efx_phc_adjtime,
+ .gettime = efx_phc_gettime,
+ .settime = efx_phc_settime,
+ .enable = efx_phc_enable,
+};
+
+/* Initialise PTP state. */
+int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel)
+{
+ struct efx_ptp_data *ptp;
+ int rc = 0;
+ unsigned int pos;
+
+ ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL);
+ efx->ptp_data = ptp;
+ if (!efx->ptp_data)
+ return -ENOMEM;
+
+ ptp->efx = efx;
+ ptp->channel = channel;
+ ptp->rx_ts_inline = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
+
+ rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int), GFP_KERNEL);
+ if (rc != 0)
+ goto fail1;
+
+ skb_queue_head_init(&ptp->rxq);
+ skb_queue_head_init(&ptp->txq);
+ ptp->workwq = create_singlethread_workqueue("sfc_ptp");
+ if (!ptp->workwq) {
+ rc = -ENOMEM;
+ goto fail2;
+ }
+
+ INIT_WORK(&ptp->work, efx_ptp_worker);
+ ptp->config.flags = 0;
+ ptp->config.tx_type = HWTSTAMP_TX_OFF;
+ ptp->config.rx_filter = HWTSTAMP_FILTER_NONE;
+ INIT_LIST_HEAD(&ptp->evt_list);
+ INIT_LIST_HEAD(&ptp->evt_free_list);
+ spin_lock_init(&ptp->evt_lock);
+ for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++)
+ list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list);
+
+ /* Get the NIC PTP attributes and set up time conversions */
+ rc = efx_ptp_get_attributes(efx);
+ if (rc < 0)
+ goto fail3;
+
+ /* Get the timestamp corrections */
+ rc = efx_ptp_get_timestamp_corrections(efx);
+ if (rc < 0)
+ goto fail3;
+
+ if (efx->mcdi->fn_flags &
+ (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY)) {
+ ptp->phc_clock_info = efx_phc_clock_info;
+ ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info,
+ &efx->pci_dev->dev);
+ if (IS_ERR(ptp->phc_clock)) {
+ rc = PTR_ERR(ptp->phc_clock);
+ goto fail3;
+ }
+
+ INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker);
+ ptp->pps_workwq = create_singlethread_workqueue("sfc_pps");
+ if (!ptp->pps_workwq) {
+ rc = -ENOMEM;
+ goto fail4;
+ }
+ }
+ ptp->nic_ts_enabled = false;
+
+ return 0;
+fail4:
+ ptp_clock_unregister(efx->ptp_data->phc_clock);
+
+fail3:
+ destroy_workqueue(efx->ptp_data->workwq);
+
+fail2:
+ efx_nic_free_buffer(efx, &ptp->start);
+
+fail1:
+ kfree(efx->ptp_data);
+ efx->ptp_data = NULL;
+
+ return rc;
+}
+
+/* Initialise PTP channel.
+ *
+ * Setting core_index to zero causes the queue to be initialised and doesn't
+ * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue.
+ */
+static int efx_ptp_probe_channel(struct efx_channel *channel)
+{
+ struct efx_nic *efx = channel->efx;
+
+ channel->irq_moderation = 0;
+ channel->rx_queue.core_index = 0;
+
+ return efx_ptp_probe(efx, channel);
+}
+
+void efx_ptp_remove(struct efx_nic *efx)
+{
+ if (!efx->ptp_data)
+ return;
+
+ (void)efx_ptp_disable(efx);
+
+ cancel_work_sync(&efx->ptp_data->work);
+ cancel_work_sync(&efx->ptp_data->pps_work);
+
+ skb_queue_purge(&efx->ptp_data->rxq);
+ skb_queue_purge(&efx->ptp_data->txq);
+
+ if (efx->ptp_data->phc_clock) {
+ destroy_workqueue(efx->ptp_data->pps_workwq);
+ ptp_clock_unregister(efx->ptp_data->phc_clock);
+ }
+
+ destroy_workqueue(efx->ptp_data->workwq);
+
+ efx_nic_free_buffer(efx, &efx->ptp_data->start);
+ kfree(efx->ptp_data);
+}
+
+static void efx_ptp_remove_channel(struct efx_channel *channel)
+{
+ efx_ptp_remove(channel->efx);
+}
+
+static void efx_ptp_get_channel_name(struct efx_channel *channel,
+ char *buf, size_t len)
+{
+ snprintf(buf, len, "%s-ptp", channel->efx->name);
+}
+
+/* Determine whether this packet should be processed by the PTP module
+ * or transmitted conventionally.
+ */
+bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+ return efx->ptp_data &&
+ efx->ptp_data->enabled &&
+ skb->len >= PTP_MIN_LENGTH &&
+ skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM &&
+ likely(skb->protocol == htons(ETH_P_IP)) &&
+ skb_transport_header_was_set(skb) &&
+ skb_network_header_len(skb) >= sizeof(struct iphdr) &&
+ ip_hdr(skb)->protocol == IPPROTO_UDP &&
+ skb_headlen(skb) >=
+ skb_transport_offset(skb) + sizeof(struct udphdr) &&
+ udp_hdr(skb)->dest == htons(PTP_EVENT_PORT);
+}
+
+/* Receive a PTP packet. Packets are queued until the arrival of
+ * the receive timestamp from the MC - this will probably occur after the
+ * packet arrival because of the processing in the MC.
+ */
+static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb)
+{
+ struct efx_nic *efx = channel->efx;
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb;
+ u8 *match_data_012, *match_data_345;
+ unsigned int version;
+ u8 *data;
+
+ match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
+
+ /* Correct version? */
+ if (ptp->mode == MC_CMD_PTP_MODE_V1) {
+ if (!pskb_may_pull(skb, PTP_V1_MIN_LENGTH)) {
+ return false;
+ }
+ data = skb->data;
+ version = ntohs(*(__be16 *)&data[PTP_V1_VERSION_OFFSET]);
+ if (version != PTP_VERSION_V1) {
+ return false;
+ }
+
+ /* PTP V1 uses all six bytes of the UUID to match the packet
+ * to the timestamp
+ */
+ match_data_012 = data + PTP_V1_UUID_OFFSET;
+ match_data_345 = data + PTP_V1_UUID_OFFSET + 3;
+ } else {
+ if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) {
+ return false;
+ }
+ data = skb->data;
+ version = data[PTP_V2_VERSION_OFFSET];
+ if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) {
+ return false;
+ }
+
+ /* The original V2 implementation uses bytes 2-7 of
+ * the UUID to match the packet to the timestamp. This
+ * discards two of the bytes of the MAC address used
+ * to create the UUID (SF bug 33070). The PTP V2
+ * enhanced mode fixes this issue and uses bytes 0-2
+ * and byte 5-7 of the UUID.
+ */
+ match_data_345 = data + PTP_V2_UUID_OFFSET + 5;
+ if (ptp->mode == MC_CMD_PTP_MODE_V2) {
+ match_data_012 = data + PTP_V2_UUID_OFFSET + 2;
+ } else {
+ match_data_012 = data + PTP_V2_UUID_OFFSET + 0;
+ BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED);
+ }
+ }
+
+ /* Does this packet require timestamping? */
+ if (ntohs(*(__be16 *)&data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) {
+ match->state = PTP_PACKET_STATE_UNMATCHED;
+
+ /* We expect the sequence number to be in the same position in
+ * the packet for PTP V1 and V2
+ */
+ BUILD_BUG_ON(PTP_V1_SEQUENCE_OFFSET != PTP_V2_SEQUENCE_OFFSET);
+ BUILD_BUG_ON(PTP_V1_SEQUENCE_LENGTH != PTP_V2_SEQUENCE_LENGTH);
+
+ /* Extract UUID/Sequence information */
+ match->words[0] = (match_data_012[0] |
+ (match_data_012[1] << 8) |
+ (match_data_012[2] << 16) |
+ (match_data_345[0] << 24));
+ match->words[1] = (match_data_345[1] |
+ (match_data_345[2] << 8) |
+ (data[PTP_V1_SEQUENCE_OFFSET +
+ PTP_V1_SEQUENCE_LENGTH - 1] <<
+ 16));
+ } else {
+ match->state = PTP_PACKET_STATE_MATCH_UNWANTED;
+ }
+
+ skb_queue_tail(&ptp->rxq, skb);
+ queue_work(ptp->workwq, &ptp->work);
+
+ return true;
+}
+
+/* Transmit a PTP packet. This has to be transmitted by the MC
+ * itself, through an MCDI call. MCDI calls aren't permitted
+ * in the transmit path so defer the actual transmission to a suitable worker.
+ */
+int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+
+ skb_queue_tail(&ptp->txq, skb);
+
+ if ((udp_hdr(skb)->dest == htons(PTP_EVENT_PORT)) &&
+ (skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM))
+ efx_xmit_hwtstamp_pending(skb);
+ queue_work(ptp->workwq, &ptp->work);
+
+ return NETDEV_TX_OK;
+}
+
+int efx_ptp_get_mode(struct efx_nic *efx)
+{
+ return efx->ptp_data->mode;
+}
+
+int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted,
+ unsigned int new_mode)
+{
+ if ((enable_wanted != efx->ptp_data->enabled) ||
+ (enable_wanted && (efx->ptp_data->mode != new_mode))) {
+ int rc = 0;
+
+ if (enable_wanted) {
+ /* Change of mode requires disable */
+ if (efx->ptp_data->enabled &&
+ (efx->ptp_data->mode != new_mode)) {
+ efx->ptp_data->enabled = false;
+ rc = efx_ptp_stop(efx);
+ if (rc != 0)
+ return rc;
+ }
+
+ /* Set new operating mode and establish
+ * baseline synchronisation, which must
+ * succeed.
+ */
+ efx->ptp_data->mode = new_mode;
+ if (netif_running(efx->net_dev))
+ rc = efx_ptp_start(efx);
+ if (rc == 0) {
+ rc = efx_ptp_synchronize(efx,
+ PTP_SYNC_ATTEMPTS * 2);
+ if (rc != 0)
+ efx_ptp_stop(efx);
+ }
+ } else {
+ rc = efx_ptp_stop(efx);
+ }
+
+ if (rc != 0)
+ return rc;
+
+ efx->ptp_data->enabled = enable_wanted;
+ }
+
+ return 0;
+}
+
+static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init)
+{
+ int rc;
+
+ if (init->flags)
+ return -EINVAL;
+
+ if ((init->tx_type != HWTSTAMP_TX_OFF) &&
+ (init->tx_type != HWTSTAMP_TX_ON))
+ return -ERANGE;
+
+ rc = efx->type->ptp_set_ts_config(efx, init);
+ if (rc)
+ return rc;
+
+ efx->ptp_data->config = *init;
+ return 0;
+}
+
+void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ struct efx_nic *primary = efx->primary;
+
+ ASSERT_RTNL();
+
+ if (!ptp)
+ return;
+
+ ts_info->so_timestamping |= (SOF_TIMESTAMPING_TX_HARDWARE |
+ SOF_TIMESTAMPING_RX_HARDWARE |
+ SOF_TIMESTAMPING_RAW_HARDWARE);
+ if (primary && primary->ptp_data && primary->ptp_data->phc_clock)
+ ts_info->phc_index =
+ ptp_clock_index(primary->ptp_data->phc_clock);
+ ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON;
+ ts_info->rx_filters = ptp->efx->type->hwtstamp_filters;
+}
+
+int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+{
+ struct hwtstamp_config config;
+ int rc;
+
+ /* Not a PTP enabled port */
+ if (!efx->ptp_data)
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+ return -EFAULT;
+
+ rc = efx_ptp_ts_init(efx, &config);
+ if (rc != 0)
+ return rc;
+
+ return copy_to_user(ifr->ifr_data, &config, sizeof(config))
+ ? -EFAULT : 0;
+}
+
+int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr)
+{
+ if (!efx->ptp_data)
+ return -EOPNOTSUPP;
+
+ return copy_to_user(ifr->ifr_data, &efx->ptp_data->config,
+ sizeof(efx->ptp_data->config)) ? -EFAULT : 0;
+}
+
+static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+
+ netif_err(efx, hw, efx->net_dev,
+ "PTP unexpected event length: got %d expected %d\n",
+ ptp->evt_frag_idx, expected_frag_len);
+ ptp->reset_required = true;
+ queue_work(ptp->workwq, &ptp->work);
+}
+
+/* Process a completed receive event. Put it on the event queue and
+ * start worker thread. This is required because event and their
+ * correspoding packets may come in either order.
+ */
+static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+ struct efx_ptp_event_rx *evt = NULL;
+
+ if (WARN_ON_ONCE(ptp->rx_ts_inline))
+ return;
+
+ if (ptp->evt_frag_idx != 3) {
+ ptp_event_failure(efx, 3);
+ return;
+ }
+
+ spin_lock_bh(&ptp->evt_lock);
+ if (!list_empty(&ptp->evt_free_list)) {
+ evt = list_first_entry(&ptp->evt_free_list,
+ struct efx_ptp_event_rx, link);
+ list_del(&evt->link);
+
+ evt->seq0 = EFX_QWORD_FIELD(ptp->evt_frags[2], MCDI_EVENT_DATA);
+ evt->seq1 = (EFX_QWORD_FIELD(ptp->evt_frags[2],
+ MCDI_EVENT_SRC) |
+ (EFX_QWORD_FIELD(ptp->evt_frags[1],
+ MCDI_EVENT_SRC) << 8) |
+ (EFX_QWORD_FIELD(ptp->evt_frags[0],
+ MCDI_EVENT_SRC) << 16));
+ evt->hwtimestamp = efx->ptp_data->nic_to_kernel_time(
+ EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA),
+ EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA),
+ ptp->ts_corrections.rx);
+ evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS);
+ list_add_tail(&evt->link, &ptp->evt_list);
+
+ queue_work(ptp->workwq, &ptp->work);
+ } else if (net_ratelimit()) {
+ /* Log a rate-limited warning message. */
+ netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n");
+ }
+ spin_unlock_bh(&ptp->evt_lock);
+}
+
+static void ptp_event_fault(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+ int code = EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA);
+ if (ptp->evt_frag_idx != 1) {
+ ptp_event_failure(efx, 1);
+ return;
+ }
+
+ netif_err(efx, hw, efx->net_dev, "PTP error %d\n", code);
+}
+
+static void ptp_event_pps(struct efx_nic *efx, struct efx_ptp_data *ptp)
+{
+ if (ptp->nic_ts_enabled)
+ queue_work(ptp->pps_workwq, &ptp->pps_work);
+}
+
+void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev)
+{
+ struct efx_ptp_data *ptp = efx->ptp_data;
+ int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE);
+
+ if (!ptp) {
+ if (net_ratelimit())
+ netif_warn(efx, drv, efx->net_dev,
+ "Received PTP event but PTP not set up\n");
+ return;
+ }
+
+ if (!ptp->enabled)
+ return;
+
+ if (ptp->evt_frag_idx == 0) {
+ ptp->evt_code = code;
+ } else if (ptp->evt_code != code) {
+ netif_err(efx, hw, efx->net_dev,
+ "PTP out of sequence event %d\n", code);
+ ptp->evt_frag_idx = 0;
+ }
+
+ ptp->evt_frags[ptp->evt_frag_idx++] = *ev;
+ if (!MCDI_EVENT_FIELD(*ev, CONT)) {
+ /* Process resulting event */
+ switch (code) {
+ case MCDI_EVENT_CODE_PTP_RX:
+ ptp_event_rx(efx, ptp);
+ break;
+ case MCDI_EVENT_CODE_PTP_FAULT:
+ ptp_event_fault(efx, ptp);
+ break;
+ case MCDI_EVENT_CODE_PTP_PPS:
+ ptp_event_pps(efx, ptp);
+ break;
+ default:
+ netif_err(efx, hw, efx->net_dev,
+ "PTP unknown event %d\n", code);
+ break;
+ }
+ ptp->evt_frag_idx = 0;
+ } else if (MAX_EVENT_FRAGS == ptp->evt_frag_idx) {
+ netif_err(efx, hw, efx->net_dev,
+ "PTP too many event fragments\n");
+ ptp->evt_frag_idx = 0;
+ }
+}
+
+void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev)
+{
+ channel->sync_timestamp_major = MCDI_EVENT_FIELD(*ev, PTP_TIME_MAJOR);
+ channel->sync_timestamp_minor =
+ MCDI_EVENT_FIELD(*ev, PTP_TIME_MINOR_26_19) << 19;
+ /* if sync events have been disabled then we want to silently ignore
+ * this event, so throw away result.
+ */
+ (void) cmpxchg(&channel->sync_events_state, SYNC_EVENTS_REQUESTED,
+ SYNC_EVENTS_VALID);
+}
+
+/* make some assumptions about the time representation rather than abstract it,
+ * since we currently only support one type of inline timestamping and only on
+ * EF10.
+ */
+#define MINOR_TICKS_PER_SECOND 0x8000000
+/* Fuzz factor for sync events to be out of order with RX events */
+#define FUZZ (MINOR_TICKS_PER_SECOND / 10)
+#define EXPECTED_SYNC_EVENTS_PER_SECOND 4
+
+static inline u32 efx_rx_buf_timestamp_minor(struct efx_nic *efx, const u8 *eh)
+{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+ return __le32_to_cpup((const __le32 *)(eh + efx->rx_packet_ts_offset));
+#else
+ const u8 *data = eh + efx->rx_packet_ts_offset;
+ return (u32)data[0] |
+ (u32)data[1] << 8 |
+ (u32)data[2] << 16 |
+ (u32)data[3] << 24;
+#endif
+}
+
+void __efx_rx_skb_attach_timestamp(struct efx_channel *channel,
+ struct sk_buff *skb)
+{
+ struct efx_nic *efx = channel->efx;
+ u32 pkt_timestamp_major, pkt_timestamp_minor;
+ u32 diff, carry;
+ struct skb_shared_hwtstamps *timestamps;
+
+ pkt_timestamp_minor = (efx_rx_buf_timestamp_minor(efx,
+ skb_mac_header(skb)) +
+ (u32) efx->ptp_data->ts_corrections.rx) &
+ (MINOR_TICKS_PER_SECOND - 1);
+
+ /* get the difference between the packet and sync timestamps,
+ * modulo one second
+ */
+ diff = (pkt_timestamp_minor - channel->sync_timestamp_minor) &
+ (MINOR_TICKS_PER_SECOND - 1);
+ /* do we roll over a second boundary and need to carry the one? */
+ carry = channel->sync_timestamp_minor + diff > MINOR_TICKS_PER_SECOND ?
+ 1 : 0;
+
+ if (diff <= MINOR_TICKS_PER_SECOND / EXPECTED_SYNC_EVENTS_PER_SECOND +
+ FUZZ) {
+ /* packet is ahead of the sync event by a quarter of a second or
+ * less (allowing for fuzz)
+ */
+ pkt_timestamp_major = channel->sync_timestamp_major + carry;
+ } else if (diff >= MINOR_TICKS_PER_SECOND - FUZZ) {
+ /* packet is behind the sync event but within the fuzz factor.
+ * This means the RX packet and sync event crossed as they were
+ * placed on the event queue, which can sometimes happen.
+ */
+ pkt_timestamp_major = channel->sync_timestamp_major - 1 + carry;
+ } else {
+ /* it's outside tolerance in both directions. this might be
+ * indicative of us missing sync events for some reason, so
+ * we'll call it an error rather than risk giving a bogus
+ * timestamp.
+ */
+ netif_vdbg(efx, drv, efx->net_dev,
+ "packet timestamp %x too far from sync event %x:%x\n",
+ pkt_timestamp_minor, channel->sync_timestamp_major,
+ channel->sync_timestamp_minor);
+ return;
+ }
+
+ /* attach the timestamps to the skb */
+ timestamps = skb_hwtstamps(skb);
+ timestamps->hwtstamp =
+ efx_ptp_s27_to_ktime(pkt_timestamp_major, pkt_timestamp_minor);
+}
+
+static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta)
+{
+ struct efx_ptp_data *ptp_data = container_of(ptp,
+ struct efx_ptp_data,
+ phc_clock_info);
+ struct efx_nic *efx = ptp_data->efx;
+ MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN);
+ s64 adjustment_ns;
+ int rc;
+
+ if (delta > MAX_PPB)
+ delta = MAX_PPB;
+ else if (delta < -MAX_PPB)
+ delta = -MAX_PPB;
+
+ /* Convert ppb to fixed point ns. */
+ adjustment_ns = (((s64)delta * PPB_SCALE_WORD) >>
+ (PPB_EXTRA_BITS + MAX_PPB_BITS));
+
+ MCDI_SET_DWORD(inadj, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
+ MCDI_SET_DWORD(inadj, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_QWORD(inadj, PTP_IN_ADJUST_FREQ, adjustment_ns);
+ MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_SECONDS, 0);
+ MCDI_SET_DWORD(inadj, PTP_IN_ADJUST_NANOSECONDS, 0);
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inadj, sizeof(inadj),
+ NULL, 0, NULL);
+ if (rc != 0)
+ return rc;
+
+ ptp_data->current_adjfreq = adjustment_ns;
+ return 0;
+}
+
+static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+ u32 nic_major, nic_minor;
+ struct efx_ptp_data *ptp_data = container_of(ptp,
+ struct efx_ptp_data,
+ phc_clock_info);
+ struct efx_nic *efx = ptp_data->efx;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ADJUST_LEN);
+
+ efx->ptp_data->ns_to_nic_time(delta, &nic_major, &nic_minor);
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+ MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, ptp_data->current_adjfreq);
+ MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_MAJOR, nic_major);
+ MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_MINOR, nic_minor);
+ return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ NULL, 0, NULL);
+}
+
+static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts)
+{
+ struct efx_ptp_data *ptp_data = container_of(ptp,
+ struct efx_ptp_data,
+ phc_clock_info);
+ struct efx_nic *efx = ptp_data->efx;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_READ_NIC_TIME_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_READ_NIC_TIME_LEN);
+ int rc;
+ ktime_t kt;
+
+ MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_READ_NIC_TIME);
+ MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf),
+ outbuf, sizeof(outbuf), NULL);
+ if (rc != 0)
+ return rc;
+
+ kt = ptp_data->nic_to_kernel_time(
+ MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MAJOR),
+ MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MINOR), 0);
+ *ts = ktime_to_timespec(kt);
+ return 0;
+}
+
+static int efx_phc_settime(struct ptp_clock_info *ptp,
+ const struct timespec *e_ts)
+{
+ /* Get the current NIC time, efx_phc_gettime.
+ * Subtract from the desired time to get the offset
+ * call efx_phc_adjtime with the offset
+ */
+ int rc;
+ struct timespec time_now;
+ struct timespec delta;
+
+ rc = efx_phc_gettime(ptp, &time_now);
+ if (rc != 0)
+ return rc;
+
+ delta = timespec_sub(*e_ts, time_now);
+
+ rc = efx_phc_adjtime(ptp, timespec_to_ns(&delta));
+ if (rc != 0)
+ return rc;
+
+ return 0;
+}
+
+static int efx_phc_enable(struct ptp_clock_info *ptp,
+ struct ptp_clock_request *request,
+ int enable)
+{
+ struct efx_ptp_data *ptp_data = container_of(ptp,
+ struct efx_ptp_data,
+ phc_clock_info);
+ if (request->type != PTP_CLK_REQ_PPS)
+ return -EOPNOTSUPP;
+
+ ptp_data->nic_ts_enabled = !!enable;
+ return 0;
+}
+
+static const struct efx_channel_type efx_ptp_channel_type = {
+ .handle_no_channel = efx_ptp_handle_no_channel,
+ .pre_probe = efx_ptp_probe_channel,
+ .post_remove = efx_ptp_remove_channel,
+ .get_name = efx_ptp_get_channel_name,
+ /* no copy operation; there is no need to reallocate this channel */
+ .receive_skb = efx_ptp_rx,
+ .keep_eventq = false,
+};
+
+void efx_ptp_defer_probe_with_channel(struct efx_nic *efx)
+{
+ /* Check whether PTP is implemented on this NIC. The DISABLE
+ * operation will succeed if and only if it is implemented.
+ */
+ if (efx_ptp_disable(efx) == 0)
+ efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] =
+ &efx_ptp_channel_type;
+}
+
+void efx_ptp_start_datapath(struct efx_nic *efx)
+{
+ if (efx_ptp_restart(efx))
+ netif_err(efx, drv, efx->net_dev, "Failed to restart PTP.\n");
+ /* re-enable timestamping if it was previously enabled */
+ if (efx->type->ptp_set_ts_sync_events)
+ efx->type->ptp_set_ts_sync_events(efx, true, true);
+}
+
+void efx_ptp_stop_datapath(struct efx_nic *efx)
+{
+ /* temporarily disable timestamping */
+ if (efx->type->ptp_set_ts_sync_events)
+ efx->type->ptp_set_ts_sync_events(efx, false, true);
+ efx_ptp_stop(efx);
+}
diff --git a/drivers/net/ethernet/sfc/qt202x_phy.c b/drivers/net/ethernet/sfc/qt202x_phy.c
index 7ad97e39740..efa3612affc 100644
--- a/drivers/net/ethernet/sfc/qt202x_phy.c
+++ b/drivers/net/ethernet/sfc/qt202x_phy.c
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2006-2012 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -47,7 +47,7 @@
#define PMA_PMD_FTX_STATIC_LBN 13
#define PMA_PMD_VEND1_REG 0xc001
#define PMA_PMD_VEND1_LBTXD_LBN 15
-#define PCS_VEND1_REG 0xc000
+#define PCS_VEND1_REG 0xc000
#define PCS_VEND1_LBTXD_LBN 5
void falcon_qt202x_set_led(struct efx_nic *p, int led, int mode)
@@ -449,14 +449,47 @@ static void qt202x_phy_remove(struct efx_nic *efx)
efx->phy_data = NULL;
}
+static int qt202x_phy_get_module_info(struct efx_nic *efx,
+ struct ethtool_modinfo *modinfo)
+{
+ modinfo->type = ETH_MODULE_SFF_8079;
+ modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN;
+ return 0;
+}
+
+static int qt202x_phy_get_module_eeprom(struct efx_nic *efx,
+ struct ethtool_eeprom *ee, u8 *data)
+{
+ int mmd, reg_base, rc, i;
+
+ if (efx->phy_type == PHY_TYPE_QT2025C) {
+ mmd = MDIO_MMD_PCS;
+ reg_base = 0xd000;
+ } else {
+ mmd = MDIO_MMD_PMAPMD;
+ reg_base = 0x8007;
+ }
+
+ for (i = 0; i < ee->len; i++) {
+ rc = efx_mdio_read(efx, mmd, reg_base + ee->offset + i);
+ if (rc < 0)
+ return rc;
+ data[i] = rc;
+ }
+
+ return 0;
+}
+
const struct efx_phy_operations falcon_qt202x_phy_ops = {
.probe = qt202x_phy_probe,
.init = qt202x_phy_init,
.reconfigure = qt202x_phy_reconfigure,
- .poll = qt202x_phy_poll,
+ .poll = qt202x_phy_poll,
.fini = efx_port_dummy_op_void,
- .remove = qt202x_phy_remove,
+ .remove = qt202x_phy_remove,
.get_settings = qt202x_phy_get_settings,
.set_settings = efx_mdio_set_settings,
.test_alive = efx_mdio_test_alive,
+ .get_module_eeprom = qt202x_phy_get_module_eeprom,
+ .get_module_info = qt202x_phy_get_module_info,
};
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index aca34986176..48588ddf81b 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2005-2011 Solarflare Communications Inc.
+ * Copyright 2005-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -12,348 +12,325 @@
#include <linux/in.h>
#include <linux/slab.h>
#include <linux/ip.h>
+#include <linux/ipv6.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/prefetch.h>
#include <linux/moduleparam.h>
+#include <linux/iommu.h>
#include <net/ip.h>
#include <net/checksum.h>
#include "net_driver.h"
#include "efx.h"
+#include "filter.h"
#include "nic.h"
#include "selftest.h"
#include "workarounds.h"
-/* Number of RX descriptors pushed at once. */
-#define EFX_RX_BATCH 8
+/* Preferred number of descriptors to fill at once */
+#define EFX_RX_PREFERRED_BATCH 8U
-/* Maximum size of a buffer sharing a page */
-#define EFX_RX_HALF_PAGE ((PAGE_SIZE >> 1) - sizeof(struct efx_rx_page_state))
-
-/* Size of buffer allocated for skb header area. */
-#define EFX_SKB_HEADERS 64u
-
-/*
- * rx_alloc_method - RX buffer allocation method
- *
- * This driver supports two methods for allocating and using RX buffers:
- * each RX buffer may be backed by an skb or by an order-n page.
- *
- * When GRO is in use then the second method has a lower overhead,
- * since we don't have to allocate then free skbs on reassembled frames.
- *
- * Values:
- * - RX_ALLOC_METHOD_AUTO = 0
- * - RX_ALLOC_METHOD_SKB = 1
- * - RX_ALLOC_METHOD_PAGE = 2
- *
- * The heuristic for %RX_ALLOC_METHOD_AUTO is a simple hysteresis count
- * controlled by the parameters below.
- *
- * - Since pushing and popping descriptors are separated by the rx_queue
- * size, so the watermarks should be ~rxd_size.
- * - The performance win by using page-based allocation for GRO is less
- * than the performance hit of using page-based allocation of non-GRO,
- * so the watermarks should reflect this.
- *
- * Per channel we maintain a single variable, updated by each channel:
- *
- * rx_alloc_level += (gro_performed ? RX_ALLOC_FACTOR_GRO :
- * RX_ALLOC_FACTOR_SKB)
- * Per NAPI poll interval, we constrain rx_alloc_level to 0..MAX (which
- * limits the hysteresis), and update the allocation strategy:
- *
- * rx_alloc_method = (rx_alloc_level > RX_ALLOC_LEVEL_GRO ?
- * RX_ALLOC_METHOD_PAGE : RX_ALLOC_METHOD_SKB)
+/* Number of RX buffers to recycle pages for. When creating the RX page recycle
+ * ring, this number is divided by the number of buffers per page to calculate
+ * the number of pages to store in the RX page recycle ring.
*/
-static int rx_alloc_method = RX_ALLOC_METHOD_AUTO;
+#define EFX_RECYCLE_RING_SIZE_IOMMU 4096
+#define EFX_RECYCLE_RING_SIZE_NOIOMMU (2 * EFX_RX_PREFERRED_BATCH)
-#define RX_ALLOC_LEVEL_GRO 0x2000
-#define RX_ALLOC_LEVEL_MAX 0x3000
-#define RX_ALLOC_FACTOR_GRO 1
-#define RX_ALLOC_FACTOR_SKB (-2)
+/* Size of buffer allocated for skb header area. */
+#define EFX_SKB_HEADERS 128u
/* This is the percentage fill level below which new RX descriptors
* will be added to the RX descriptor ring.
*/
-static unsigned int rx_refill_threshold = 90;
+static unsigned int rx_refill_threshold;
-/* This is the percentage fill level to which an RX queue will be refilled
- * when the "RX refill threshold" is reached.
- */
-static unsigned int rx_refill_limit = 95;
+/* Each packet can consume up to ceil(max_frame_len / buffer_size) buffers */
+#define EFX_RX_MAX_FRAGS DIV_ROUND_UP(EFX_MAX_FRAME_LEN(EFX_MAX_MTU), \
+ EFX_RX_USR_BUF_SIZE)
/*
* RX maximum head room required.
*
- * This must be at least 1 to prevent overflow and at least 2 to allow
- * pipelined receives.
+ * This must be at least 1 to prevent overflow, plus one packet-worth
+ * to allow pipelined receives.
*/
-#define EFX_RXD_HEAD_ROOM 2
+#define EFX_RXD_HEAD_ROOM (1 + EFX_RX_MAX_FRAGS)
-/* Offset of ethernet header within page */
-static inline unsigned int efx_rx_buf_offset(struct efx_nic *efx,
- struct efx_rx_buffer *buf)
+static inline u8 *efx_rx_buf_va(struct efx_rx_buffer *buf)
{
- /* Offset is always within one page, so we don't need to consider
- * the page order.
- */
- return (((__force unsigned long) buf->dma_addr & (PAGE_SIZE - 1)) +
- efx->type->rx_buffer_hash_size);
+ return page_address(buf->page) + buf->page_offset;
}
-static inline unsigned int efx_rx_buf_size(struct efx_nic *efx)
+
+static inline u32 efx_rx_buf_hash(struct efx_nic *efx, const u8 *eh)
{
- return PAGE_SIZE << efx->rx_buffer_order;
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
+ return __le32_to_cpup((const __le32 *)(eh + efx->rx_packet_hash_offset));
+#else
+ const u8 *data = eh + efx->rx_packet_hash_offset;
+ return (u32)data[0] |
+ (u32)data[1] << 8 |
+ (u32)data[2] << 16 |
+ (u32)data[3] << 24;
+#endif
}
-static u8 *efx_rx_buf_eh(struct efx_nic *efx, struct efx_rx_buffer *buf)
+static inline struct efx_rx_buffer *
+efx_rx_buf_next(struct efx_rx_queue *rx_queue, struct efx_rx_buffer *rx_buf)
{
- if (buf->is_page)
- return page_address(buf->u.page) + efx_rx_buf_offset(efx, buf);
+ if (unlikely(rx_buf == efx_rx_buffer(rx_queue, rx_queue->ptr_mask)))
+ return efx_rx_buffer(rx_queue, 0);
else
- return ((u8 *)buf->u.skb->data +
- efx->type->rx_buffer_hash_size);
+ return rx_buf + 1;
}
-static inline u32 efx_rx_buf_hash(const u8 *eh)
+static inline void efx_sync_rx_buffer(struct efx_nic *efx,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int len)
{
- /* The ethernet header is always directly after any hash. */
-#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || NET_IP_ALIGN % 4 == 0
- return __le32_to_cpup((const __le32 *)(eh - 4));
-#else
- const u8 *data = eh - 4;
- return ((u32)data[0] |
- (u32)data[1] << 8 |
- (u32)data[2] << 16 |
- (u32)data[3] << 24);
-#endif
+ dma_sync_single_for_cpu(&efx->pci_dev->dev, rx_buf->dma_addr, len,
+ DMA_FROM_DEVICE);
}
-/**
- * efx_init_rx_buffers_skb - create EFX_RX_BATCH skb-based RX buffers
- *
- * @rx_queue: Efx RX queue
- *
- * This allocates EFX_RX_BATCH skbs, maps them for DMA, and populates a
- * struct efx_rx_buffer for each one. Return a negative error code or 0
- * on success. May fail having only inserted fewer than EFX_RX_BATCH
- * buffers.
- */
-static int efx_init_rx_buffers_skb(struct efx_rx_queue *rx_queue)
+void efx_rx_config_page_split(struct efx_nic *efx)
{
- struct efx_nic *efx = rx_queue->efx;
- struct net_device *net_dev = efx->net_dev;
- struct efx_rx_buffer *rx_buf;
- struct sk_buff *skb;
- int skb_len = efx->rx_buffer_len;
- unsigned index, count;
-
- for (count = 0; count < EFX_RX_BATCH; ++count) {
- index = rx_queue->added_count & rx_queue->ptr_mask;
- rx_buf = efx_rx_buffer(rx_queue, index);
+ efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align,
+ EFX_RX_BUF_ALIGNMENT);
+ efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 :
+ ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) /
+ efx->rx_page_buf_step);
+ efx->rx_buffer_truesize = (PAGE_SIZE << efx->rx_buffer_order) /
+ efx->rx_bufs_per_page;
+ efx->rx_pages_per_batch = DIV_ROUND_UP(EFX_RX_PREFERRED_BATCH,
+ efx->rx_bufs_per_page);
+}
- rx_buf->u.skb = skb = netdev_alloc_skb(net_dev, skb_len);
- if (unlikely(!skb))
- return -ENOMEM;
+/* Check the RX page recycle ring for a page that can be reused. */
+static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue)
+{
+ struct efx_nic *efx = rx_queue->efx;
+ struct page *page;
+ struct efx_rx_page_state *state;
+ unsigned index;
- /* Adjust the SKB for padding and checksum */
- skb_reserve(skb, NET_IP_ALIGN);
- rx_buf->len = skb_len - NET_IP_ALIGN;
- rx_buf->is_page = false;
- skb->ip_summed = CHECKSUM_UNNECESSARY;
+ index = rx_queue->page_remove & rx_queue->page_ptr_mask;
+ page = rx_queue->page_ring[index];
+ if (page == NULL)
+ return NULL;
- rx_buf->dma_addr = pci_map_single(efx->pci_dev,
- skb->data, rx_buf->len,
- PCI_DMA_FROMDEVICE);
- if (unlikely(pci_dma_mapping_error(efx->pci_dev,
- rx_buf->dma_addr))) {
- dev_kfree_skb_any(skb);
- rx_buf->u.skb = NULL;
- return -EIO;
- }
+ rx_queue->page_ring[index] = NULL;
+ /* page_remove cannot exceed page_add. */
+ if (rx_queue->page_remove != rx_queue->page_add)
+ ++rx_queue->page_remove;
- ++rx_queue->added_count;
- ++rx_queue->alloc_skb_count;
+ /* If page_count is 1 then we hold the only reference to this page. */
+ if (page_count(page) == 1) {
+ ++rx_queue->page_recycle_count;
+ return page;
+ } else {
+ state = page_address(page);
+ dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ put_page(page);
+ ++rx_queue->page_recycle_failed;
}
- return 0;
+ return NULL;
}
/**
- * efx_init_rx_buffers_page - create EFX_RX_BATCH page-based RX buffers
+ * efx_init_rx_buffers - create EFX_RX_BATCH page-based RX buffers
*
* @rx_queue: Efx RX queue
*
- * This allocates memory for EFX_RX_BATCH receive buffers, maps them for DMA,
- * and populates struct efx_rx_buffers for each one. Return a negative error
- * code or 0 on success. If a single page can be split between two buffers,
- * then the page will either be inserted fully, or not at at all.
+ * This allocates a batch of pages, maps them for DMA, and populates
+ * struct efx_rx_buffers for each one. Return a negative error code or
+ * 0 on success. If a single page can be used for multiple buffers,
+ * then the page will either be inserted fully, or not at all.
*/
-static int efx_init_rx_buffers_page(struct efx_rx_queue *rx_queue)
+static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic)
{
struct efx_nic *efx = rx_queue->efx;
struct efx_rx_buffer *rx_buf;
struct page *page;
- void *page_addr;
+ unsigned int page_offset;
struct efx_rx_page_state *state;
dma_addr_t dma_addr;
unsigned index, count;
- /* We can split a page between two buffers */
- BUILD_BUG_ON(EFX_RX_BATCH & 1);
-
- for (count = 0; count < EFX_RX_BATCH; ++count) {
- page = alloc_pages(__GFP_COLD | __GFP_COMP | GFP_ATOMIC,
- efx->rx_buffer_order);
- if (unlikely(page == NULL))
- return -ENOMEM;
- dma_addr = pci_map_page(efx->pci_dev, page, 0,
- efx_rx_buf_size(efx),
- PCI_DMA_FROMDEVICE);
- if (unlikely(pci_dma_mapping_error(efx->pci_dev, dma_addr))) {
- __free_pages(page, efx->rx_buffer_order);
- return -EIO;
+ count = 0;
+ do {
+ page = efx_reuse_page(rx_queue);
+ if (page == NULL) {
+ page = alloc_pages(__GFP_COLD | __GFP_COMP |
+ (atomic ? GFP_ATOMIC : GFP_KERNEL),
+ efx->rx_buffer_order);
+ if (unlikely(page == NULL))
+ return -ENOMEM;
+ dma_addr =
+ dma_map_page(&efx->pci_dev->dev, page, 0,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ if (unlikely(dma_mapping_error(&efx->pci_dev->dev,
+ dma_addr))) {
+ __free_pages(page, efx->rx_buffer_order);
+ return -EIO;
+ }
+ state = page_address(page);
+ state->dma_addr = dma_addr;
+ } else {
+ state = page_address(page);
+ dma_addr = state->dma_addr;
}
- page_addr = page_address(page);
- state = page_addr;
- state->refcnt = 0;
- state->dma_addr = dma_addr;
- page_addr += sizeof(struct efx_rx_page_state);
dma_addr += sizeof(struct efx_rx_page_state);
-
- split:
- index = rx_queue->added_count & rx_queue->ptr_mask;
- rx_buf = efx_rx_buffer(rx_queue, index);
- rx_buf->dma_addr = dma_addr + EFX_PAGE_IP_ALIGN;
- rx_buf->u.page = page;
- rx_buf->len = efx->rx_buffer_len - EFX_PAGE_IP_ALIGN;
- rx_buf->is_page = true;
- ++rx_queue->added_count;
- ++rx_queue->alloc_page_count;
- ++state->refcnt;
-
- if ((~count & 1) && (efx->rx_buffer_len <= EFX_RX_HALF_PAGE)) {
- /* Use the second half of the page */
+ page_offset = sizeof(struct efx_rx_page_state);
+
+ do {
+ index = rx_queue->added_count & rx_queue->ptr_mask;
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ rx_buf->dma_addr = dma_addr + efx->rx_ip_align;
+ rx_buf->page = page;
+ rx_buf->page_offset = page_offset + efx->rx_ip_align;
+ rx_buf->len = efx->rx_dma_len;
+ rx_buf->flags = 0;
+ ++rx_queue->added_count;
get_page(page);
- dma_addr += (PAGE_SIZE >> 1);
- page_addr += (PAGE_SIZE >> 1);
- ++count;
- goto split;
- }
- }
+ dma_addr += efx->rx_page_buf_step;
+ page_offset += efx->rx_page_buf_step;
+ } while (page_offset + efx->rx_page_buf_step <= PAGE_SIZE);
+
+ rx_buf->flags = EFX_RX_BUF_LAST_IN_PAGE;
+ } while (++count < efx->rx_pages_per_batch);
return 0;
}
+/* Unmap a DMA-mapped page. This function is only called for the final RX
+ * buffer in a page.
+ */
static void efx_unmap_rx_buffer(struct efx_nic *efx,
struct efx_rx_buffer *rx_buf)
{
- if (rx_buf->is_page && rx_buf->u.page) {
- struct efx_rx_page_state *state;
+ struct page *page = rx_buf->page;
+
+ if (page) {
+ struct efx_rx_page_state *state = page_address(page);
+ dma_unmap_page(&efx->pci_dev->dev,
+ state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ }
+}
- state = page_address(rx_buf->u.page);
- if (--state->refcnt == 0) {
- pci_unmap_page(efx->pci_dev,
- state->dma_addr,
- efx_rx_buf_size(efx),
- PCI_DMA_FROMDEVICE);
- }
- } else if (!rx_buf->is_page && rx_buf->u.skb) {
- pci_unmap_single(efx->pci_dev, rx_buf->dma_addr,
- rx_buf->len, PCI_DMA_FROMDEVICE);
+static void efx_free_rx_buffer(struct efx_rx_buffer *rx_buf)
+{
+ if (rx_buf->page) {
+ put_page(rx_buf->page);
+ rx_buf->page = NULL;
}
}
-static void efx_free_rx_buffer(struct efx_nic *efx,
- struct efx_rx_buffer *rx_buf)
+/* Attempt to recycle the page if there is an RX recycle ring; the page can
+ * only be added if this is the final RX buffer, to prevent pages being used in
+ * the descriptor ring and appearing in the recycle ring simultaneously.
+ */
+static void efx_recycle_rx_page(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf)
{
- if (rx_buf->is_page && rx_buf->u.page) {
- __free_pages(rx_buf->u.page, efx->rx_buffer_order);
- rx_buf->u.page = NULL;
- } else if (!rx_buf->is_page && rx_buf->u.skb) {
- dev_kfree_skb_any(rx_buf->u.skb);
- rx_buf->u.skb = NULL;
+ struct page *page = rx_buf->page;
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned index;
+
+ /* Only recycle the page after processing the final buffer. */
+ if (!(rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE))
+ return;
+
+ index = rx_queue->page_add & rx_queue->page_ptr_mask;
+ if (rx_queue->page_ring[index] == NULL) {
+ unsigned read_index = rx_queue->page_remove &
+ rx_queue->page_ptr_mask;
+
+ /* The next slot in the recycle ring is available, but
+ * increment page_remove if the read pointer currently
+ * points here.
+ */
+ if (read_index == index)
+ ++rx_queue->page_remove;
+ rx_queue->page_ring[index] = page;
+ ++rx_queue->page_add;
+ return;
}
+ ++rx_queue->page_recycle_full;
+ efx_unmap_rx_buffer(efx, rx_buf);
+ put_page(rx_buf->page);
}
static void efx_fini_rx_buffer(struct efx_rx_queue *rx_queue,
struct efx_rx_buffer *rx_buf)
{
- efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
- efx_free_rx_buffer(rx_queue->efx, rx_buf);
+ /* Release the page reference we hold for the buffer. */
+ if (rx_buf->page)
+ put_page(rx_buf->page);
+
+ /* If this is the last buffer in a page, unmap and free it. */
+ if (rx_buf->flags & EFX_RX_BUF_LAST_IN_PAGE) {
+ efx_unmap_rx_buffer(rx_queue->efx, rx_buf);
+ efx_free_rx_buffer(rx_buf);
+ }
+ rx_buf->page = NULL;
}
-/* Attempt to resurrect the other receive buffer that used to share this page,
- * which had previously been passed up to the kernel and freed. */
-static void efx_resurrect_rx_buffer(struct efx_rx_queue *rx_queue,
- struct efx_rx_buffer *rx_buf)
+/* Recycle the pages that are used by buffers that have just been received. */
+static void efx_recycle_rx_pages(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
{
- struct efx_rx_page_state *state = page_address(rx_buf->u.page);
- struct efx_rx_buffer *new_buf;
- unsigned fill_level, index;
-
- /* +1 because efx_rx_packet() incremented removed_count. +1 because
- * we'd like to insert an additional descriptor whilst leaving
- * EFX_RXD_HEAD_ROOM for the non-recycle path */
- fill_level = (rx_queue->added_count - rx_queue->removed_count + 2);
- if (unlikely(fill_level > rx_queue->max_fill)) {
- /* We could place "state" on a list, and drain the list in
- * efx_fast_push_rx_descriptors(). For now, this will do. */
- return;
- }
-
- ++state->refcnt;
- get_page(rx_buf->u.page);
+ struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
- index = rx_queue->added_count & rx_queue->ptr_mask;
- new_buf = efx_rx_buffer(rx_queue, index);
- new_buf->dma_addr = rx_buf->dma_addr ^ (PAGE_SIZE >> 1);
- new_buf->u.page = rx_buf->u.page;
- new_buf->len = rx_buf->len;
- new_buf->is_page = true;
- ++rx_queue->added_count;
+ do {
+ efx_recycle_rx_page(channel, rx_buf);
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--n_frags);
}
-/* Recycle the given rx buffer directly back into the rx_queue. There is
- * always room to add this buffer, because we've just popped a buffer. */
-static void efx_recycle_rx_buffer(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf)
+static void efx_discard_rx_packet(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
{
- struct efx_nic *efx = channel->efx;
struct efx_rx_queue *rx_queue = efx_channel_get_rx_queue(channel);
- struct efx_rx_buffer *new_buf;
- unsigned index;
- if (rx_buf->is_page && efx->rx_buffer_len <= EFX_RX_HALF_PAGE &&
- page_count(rx_buf->u.page) == 1)
- efx_resurrect_rx_buffer(rx_queue, rx_buf);
+ efx_recycle_rx_pages(channel, rx_buf, n_frags);
- index = rx_queue->added_count & rx_queue->ptr_mask;
- new_buf = efx_rx_buffer(rx_queue, index);
-
- memcpy(new_buf, rx_buf, sizeof(*new_buf));
- rx_buf->u.page = NULL;
- ++rx_queue->added_count;
+ do {
+ efx_free_rx_buffer(rx_buf);
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ } while (--n_frags);
}
/**
* efx_fast_push_rx_descriptors - push new RX descriptors quickly
* @rx_queue: RX descriptor queue
+ *
* This will aim to fill the RX descriptor queue up to
- * @rx_queue->@fast_fill_limit. If there is insufficient atomic
+ * @rx_queue->@max_fill. If there is insufficient atomic
* memory to do so, a slow fill will be scheduled.
*
* The caller must provide serialisation (none is used here). In practise,
* this means this function must run from the NAPI handler, or be called
* when NAPI is disabled.
*/
-void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue)
+void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic)
{
- struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
- unsigned fill_level;
+ struct efx_nic *efx = rx_queue->efx;
+ unsigned int fill_level, batch_size;
int space, rc = 0;
+ if (!rx_queue->refill_enabled)
+ return;
+
/* Calculate current fill level, and exit if we don't need to fill */
fill_level = (rx_queue->added_count - rx_queue->removed_count);
EFX_BUG_ON_PARANOID(fill_level > rx_queue->efx->rxq_entries);
@@ -366,29 +343,26 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue)
rx_queue->min_fill = fill_level;
}
- space = rx_queue->fast_fill_limit - fill_level;
- if (space < EFX_RX_BATCH)
- goto out;
+ batch_size = efx->rx_pages_per_batch * efx->rx_bufs_per_page;
+ space = rx_queue->max_fill - fill_level;
+ EFX_BUG_ON_PARANOID(space < batch_size);
netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
"RX queue %d fast-filling descriptor ring from"
- " level %d to level %d using %s allocation\n",
+ " level %d to level %d\n",
efx_rx_queue_index(rx_queue), fill_level,
- rx_queue->fast_fill_limit,
- channel->rx_alloc_push_pages ? "page" : "skb");
+ rx_queue->max_fill);
+
do {
- if (channel->rx_alloc_push_pages)
- rc = efx_init_rx_buffers_page(rx_queue);
- else
- rc = efx_init_rx_buffers_skb(rx_queue);
+ rc = efx_init_rx_buffers(rx_queue, atomic);
if (unlikely(rc)) {
/* Ensure that we don't leave the rx queue empty */
if (rx_queue->added_count == rx_queue->removed_count)
efx_schedule_slow_fill(rx_queue);
goto out;
}
- } while ((space -= EFX_RX_BATCH) >= EFX_RX_BATCH);
+ } while ((space -= batch_size) >= batch_size);
netif_vdbg(rx_queue->efx, rx_status, rx_queue->efx->net_dev,
"RX queue %d fast-filled descriptor ring "
@@ -403,17 +377,15 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue)
void efx_rx_slow_fill(unsigned long context)
{
struct efx_rx_queue *rx_queue = (struct efx_rx_queue *)context;
- struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
/* Post an event to cause NAPI to run and refill the queue */
- efx_nic_generate_fill_event(channel);
+ efx_nic_generate_fill_event(rx_queue);
++rx_queue->slow_fill_count;
}
static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
struct efx_rx_buffer *rx_buf,
- int len, bool *discard,
- bool *leak_packet)
+ int len)
{
struct efx_nic *efx = rx_queue->efx;
unsigned max_len = rx_buf->len - efx->type->rx_buffer_padding;
@@ -424,7 +396,7 @@ static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
/* The packet must be discarded, but this is only a fatal error
* if the caller indicated it was
*/
- *discard = true;
+ rx_buf->flags |= EFX_RX_PKT_DISCARD;
if ((len > rx_buf->len) && EFX_WORKAROUND_8071(efx)) {
if (net_ratelimit())
@@ -433,11 +405,6 @@ static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
"RX event (0x%x > 0x%x+0x%x). Leaking\n",
efx_rx_queue_index(rx_queue), len, max_len,
efx->type->rx_buffer_padding);
- /* If this buffer was skb-allocated, then the meta
- * data at the end of the skb will be trashed. So
- * we have no choice but to leak the fragment.
- */
- *leak_packet = !rx_buf->is_page;
efx_schedule_reset(efx, RESET_TYPE_RX_RECOVERY);
} else {
if (net_ratelimit())
@@ -450,203 +417,257 @@ static void efx_rx_packet__check_len(struct efx_rx_queue *rx_queue,
efx_rx_queue_channel(rx_queue)->n_rx_overlength++;
}
-/* Pass a received packet up through the generic GRO stack
- *
- * Handles driverlink veto, and passes the fragment up via
- * the appropriate GRO method
+/* Pass a received packet up through GRO. GRO can handle pages
+ * regardless of checksum state and skbs with a good checksum.
*/
-static void efx_rx_packet_gro(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf,
- const u8 *eh, bool checksummed)
+static void
+efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags, u8 *eh)
{
struct napi_struct *napi = &channel->napi_str;
gro_result_t gro_result;
+ struct efx_nic *efx = channel->efx;
+ struct sk_buff *skb;
- /* Pass the skb/page into the GRO engine */
- if (rx_buf->is_page) {
- struct efx_nic *efx = channel->efx;
- struct page *page = rx_buf->u.page;
- struct sk_buff *skb;
-
- rx_buf->u.page = NULL;
-
- skb = napi_get_frags(napi);
- if (!skb) {
- put_page(page);
- return;
+ skb = napi_get_frags(napi);
+ if (unlikely(!skb)) {
+ while (n_frags--) {
+ put_page(rx_buf->page);
+ rx_buf->page = NULL;
+ rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
}
+ return;
+ }
- if (efx->net_dev->features & NETIF_F_RXHASH)
- skb->rxhash = efx_rx_buf_hash(eh);
+ if (efx->net_dev->features & NETIF_F_RXHASH)
+ skb_set_hash(skb, efx_rx_buf_hash(efx, eh),
+ PKT_HASH_TYPE_L3);
+ skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ?
+ CHECKSUM_UNNECESSARY : CHECKSUM_NONE);
+
+ for (;;) {
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ rx_buf->page, rx_buf->page_offset,
+ rx_buf->len);
+ rx_buf->page = NULL;
+ skb->len += rx_buf->len;
+ if (skb_shinfo(skb)->nr_frags == n_frags)
+ break;
+
+ rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
+ }
- skb_fill_page_desc(skb, 0, page,
- efx_rx_buf_offset(efx, rx_buf), rx_buf->len);
+ skb->data_len = skb->len;
+ skb->truesize += n_frags * efx->rx_buffer_truesize;
- skb->len = rx_buf->len;
- skb->data_len = rx_buf->len;
- skb->truesize += rx_buf->len;
- skb->ip_summed =
- checksummed ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
+ skb_record_rx_queue(skb, channel->rx_queue.core_index);
- skb_record_rx_queue(skb, channel->channel);
+ gro_result = napi_gro_frags(napi);
+ if (gro_result != GRO_DROP)
+ channel->irq_mod_score += 2;
+}
- gro_result = napi_gro_frags(napi);
+/* Allocate and construct an SKB around page fragments */
+static struct sk_buff *efx_rx_mk_skb(struct efx_channel *channel,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags,
+ u8 *eh, int hdr_len)
+{
+ struct efx_nic *efx = channel->efx;
+ struct sk_buff *skb;
+
+ /* Allocate an SKB to store the headers */
+ skb = netdev_alloc_skb(efx->net_dev,
+ efx->rx_ip_align + efx->rx_prefix_size +
+ hdr_len);
+ if (unlikely(skb == NULL))
+ return NULL;
+
+ EFX_BUG_ON_PARANOID(rx_buf->len < hdr_len);
+
+ memcpy(skb->data + efx->rx_ip_align, eh - efx->rx_prefix_size,
+ efx->rx_prefix_size + hdr_len);
+ skb_reserve(skb, efx->rx_ip_align + efx->rx_prefix_size);
+ __skb_put(skb, hdr_len);
+
+ /* Append the remaining page(s) onto the frag list */
+ if (rx_buf->len > hdr_len) {
+ rx_buf->page_offset += hdr_len;
+ rx_buf->len -= hdr_len;
+
+ for (;;) {
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ rx_buf->page, rx_buf->page_offset,
+ rx_buf->len);
+ rx_buf->page = NULL;
+ skb->len += rx_buf->len;
+ skb->data_len += rx_buf->len;
+ if (skb_shinfo(skb)->nr_frags == n_frags)
+ break;
+
+ rx_buf = efx_rx_buf_next(&channel->rx_queue, rx_buf);
+ }
} else {
- struct sk_buff *skb = rx_buf->u.skb;
+ __free_pages(rx_buf->page, efx->rx_buffer_order);
+ rx_buf->page = NULL;
+ n_frags = 0;
+ }
- EFX_BUG_ON_PARANOID(!checksummed);
- rx_buf->u.skb = NULL;
+ skb->truesize += n_frags * efx->rx_buffer_truesize;
- gro_result = napi_gro_receive(napi, skb);
- }
+ /* Move past the ethernet header */
+ skb->protocol = eth_type_trans(skb, efx->net_dev);
- if (gro_result == GRO_NORMAL) {
- channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
- } else if (gro_result != GRO_DROP) {
- channel->rx_alloc_level += RX_ALLOC_FACTOR_GRO;
- channel->irq_mod_score += 2;
- }
+ return skb;
}
void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
- unsigned int len, bool checksummed, bool discard)
+ unsigned int n_frags, unsigned int len, u16 flags)
{
struct efx_nic *efx = rx_queue->efx;
struct efx_channel *channel = efx_rx_queue_channel(rx_queue);
struct efx_rx_buffer *rx_buf;
- bool leak_packet = false;
rx_buf = efx_rx_buffer(rx_queue, index);
-
- /* This allows the refill path to post another buffer.
- * EFX_RXD_HEAD_ROOM ensures that the slot we are using
- * isn't overwritten yet.
- */
- rx_queue->removed_count++;
-
- /* Validate the length encoded in the event vs the descriptor pushed */
- efx_rx_packet__check_len(rx_queue, rx_buf, len,
- &discard, &leak_packet);
+ rx_buf->flags |= flags;
+
+ /* Validate the number of fragments and completed length */
+ if (n_frags == 1) {
+ if (!(flags & EFX_RX_PKT_PREFIX_LEN))
+ efx_rx_packet__check_len(rx_queue, rx_buf, len);
+ } else if (unlikely(n_frags > EFX_RX_MAX_FRAGS) ||
+ unlikely(len <= (n_frags - 1) * efx->rx_dma_len) ||
+ unlikely(len > n_frags * efx->rx_dma_len) ||
+ unlikely(!efx->rx_scatter)) {
+ /* If this isn't an explicit discard request, either
+ * the hardware or the driver is broken.
+ */
+ WARN_ON(!(len == 0 && rx_buf->flags & EFX_RX_PKT_DISCARD));
+ rx_buf->flags |= EFX_RX_PKT_DISCARD;
+ }
netif_vdbg(efx, rx_status, efx->net_dev,
- "RX queue %d received id %x at %llx+%x %s%s\n",
+ "RX queue %d received ids %x-%x len %d %s%s\n",
efx_rx_queue_index(rx_queue), index,
- (unsigned long long)rx_buf->dma_addr, len,
- (checksummed ? " [SUMMED]" : ""),
- (discard ? " [DISCARD]" : ""));
-
- /* Discard packet, if instructed to do so */
- if (unlikely(discard)) {
- if (unlikely(leak_packet))
- channel->n_skbuff_leaks++;
- else
- efx_recycle_rx_buffer(channel, rx_buf);
-
- /* Don't hold off the previous receive */
- rx_buf = NULL;
- goto out;
+ (index + n_frags - 1) & rx_queue->ptr_mask, len,
+ (rx_buf->flags & EFX_RX_PKT_CSUMMED) ? " [SUMMED]" : "",
+ (rx_buf->flags & EFX_RX_PKT_DISCARD) ? " [DISCARD]" : "");
+
+ /* Discard packet, if instructed to do so. Process the
+ * previous receive first.
+ */
+ if (unlikely(rx_buf->flags & EFX_RX_PKT_DISCARD)) {
+ efx_rx_flush_packet(channel);
+ efx_discard_rx_packet(channel, rx_buf, n_frags);
+ return;
}
- /* Release card resources - assumes all RX buffers consumed in-order
- * per RX queue
+ if (n_frags == 1 && !(flags & EFX_RX_PKT_PREFIX_LEN))
+ rx_buf->len = len;
+
+ /* Release and/or sync the DMA mapping - assumes all RX buffers
+ * consumed in-order per RX queue.
*/
- efx_unmap_rx_buffer(efx, rx_buf);
+ efx_sync_rx_buffer(efx, rx_buf, rx_buf->len);
/* Prefetch nice and early so data will (hopefully) be in cache by
* the time we look at it.
*/
- prefetch(efx_rx_buf_eh(efx, rx_buf));
+ prefetch(efx_rx_buf_va(rx_buf));
+
+ rx_buf->page_offset += efx->rx_prefix_size;
+ rx_buf->len -= efx->rx_prefix_size;
+
+ if (n_frags > 1) {
+ /* Release/sync DMA mapping for additional fragments.
+ * Fix length for last fragment.
+ */
+ unsigned int tail_frags = n_frags - 1;
+
+ for (;;) {
+ rx_buf = efx_rx_buf_next(rx_queue, rx_buf);
+ if (--tail_frags == 0)
+ break;
+ efx_sync_rx_buffer(efx, rx_buf, efx->rx_dma_len);
+ }
+ rx_buf->len = len - (n_frags - 1) * efx->rx_dma_len;
+ efx_sync_rx_buffer(efx, rx_buf, rx_buf->len);
+ }
+
+ /* All fragments have been DMA-synced, so recycle pages. */
+ rx_buf = efx_rx_buffer(rx_queue, index);
+ efx_recycle_rx_pages(channel, rx_buf, n_frags);
/* Pipeline receives so that we give time for packet headers to be
* prefetched into cache.
*/
- rx_buf->len = len - efx->type->rx_buffer_hash_size;
-out:
- if (channel->rx_pkt)
- __efx_rx_packet(channel,
- channel->rx_pkt, channel->rx_pkt_csummed);
- channel->rx_pkt = rx_buf;
- channel->rx_pkt_csummed = checksummed;
+ efx_rx_flush_packet(channel);
+ channel->rx_pkt_n_frags = n_frags;
+ channel->rx_pkt_index = index;
}
-/* Handle a received packet. Second half: Touches packet payload. */
-void __efx_rx_packet(struct efx_channel *channel,
- struct efx_rx_buffer *rx_buf, bool checksummed)
+static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
+ struct efx_rx_buffer *rx_buf,
+ unsigned int n_frags)
{
- struct efx_nic *efx = channel->efx;
struct sk_buff *skb;
- u8 *eh = efx_rx_buf_eh(efx, rx_buf);
-
- /* If we're in loopback test, then pass the packet directly to the
- * loopback layer, and free the rx_buf here
- */
- if (unlikely(efx->loopback_selftest)) {
- efx_loopback_rx_packet(efx, eh, rx_buf->len);
- efx_free_rx_buffer(efx, rx_buf);
- return;
- }
-
- if (!rx_buf->is_page) {
- skb = rx_buf->u.skb;
+ u16 hdr_len = min_t(u16, rx_buf->len, EFX_SKB_HEADERS);
- prefetch(skb_shinfo(skb));
-
- skb_reserve(skb, efx->type->rx_buffer_hash_size);
- skb_put(skb, rx_buf->len);
-
- if (efx->net_dev->features & NETIF_F_RXHASH)
- skb->rxhash = efx_rx_buf_hash(eh);
-
- /* Move past the ethernet header. rx_buf->data still points
- * at the ethernet header */
- skb->protocol = eth_type_trans(skb, efx->net_dev);
-
- skb_record_rx_queue(skb, channel->channel);
- }
-
- if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM)))
- checksummed = false;
-
- if (likely(checksummed || rx_buf->is_page)) {
- efx_rx_packet_gro(channel, rx_buf, eh, checksummed);
+ skb = efx_rx_mk_skb(channel, rx_buf, n_frags, eh, hdr_len);
+ if (unlikely(skb == NULL)) {
+ efx_free_rx_buffer(rx_buf);
return;
}
-
- /* We now own the SKB */
- skb = rx_buf->u.skb;
- rx_buf->u.skb = NULL;
+ skb_record_rx_queue(skb, channel->rx_queue.core_index);
/* Set the SKB flags */
skb_checksum_none_assert(skb);
+ if (likely(rx_buf->flags & EFX_RX_PKT_CSUMMED))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ efx_rx_skb_attach_timestamp(channel, skb);
+
+ if (channel->type->receive_skb)
+ if (channel->type->receive_skb(channel, skb))
+ return;
/* Pass the packet up */
netif_receive_skb(skb);
-
- /* Update allocation strategy method */
- channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
}
-void efx_rx_strategy(struct efx_channel *channel)
+/* Handle a received packet. Second half: Touches packet payload. */
+void __efx_rx_packet(struct efx_channel *channel)
{
- enum efx_rx_alloc_method method = rx_alloc_method;
-
- /* Only makes sense to use page based allocation if GRO is enabled */
- if (!(channel->efx->net_dev->features & NETIF_F_GRO)) {
- method = RX_ALLOC_METHOD_SKB;
- } else if (method == RX_ALLOC_METHOD_AUTO) {
- /* Constrain the rx_alloc_level */
- if (channel->rx_alloc_level < 0)
- channel->rx_alloc_level = 0;
- else if (channel->rx_alloc_level > RX_ALLOC_LEVEL_MAX)
- channel->rx_alloc_level = RX_ALLOC_LEVEL_MAX;
-
- /* Decide on the allocation method */
- method = ((channel->rx_alloc_level > RX_ALLOC_LEVEL_GRO) ?
- RX_ALLOC_METHOD_PAGE : RX_ALLOC_METHOD_SKB);
+ struct efx_nic *efx = channel->efx;
+ struct efx_rx_buffer *rx_buf =
+ efx_rx_buffer(&channel->rx_queue, channel->rx_pkt_index);
+ u8 *eh = efx_rx_buf_va(rx_buf);
+
+ /* Read length from the prefix if necessary. This already
+ * excludes the length of the prefix itself.
+ */
+ if (rx_buf->flags & EFX_RX_PKT_PREFIX_LEN)
+ rx_buf->len = le16_to_cpup((__le16 *)
+ (eh + efx->rx_packet_len_offset));
+
+ /* If we're in loopback test, then pass the packet directly to the
+ * loopback layer, and free the rx_buf here
+ */
+ if (unlikely(efx->loopback_selftest)) {
+ efx_loopback_rx_packet(efx, eh, rx_buf->len);
+ efx_free_rx_buffer(rx_buf);
+ goto out;
}
- /* Push the option */
- channel->rx_alloc_push_pages = (method == RX_ALLOC_METHOD_PAGE);
+ if (unlikely(!(efx->net_dev->features & NETIF_F_RXCSUM)))
+ rx_buf->flags &= ~EFX_RX_PKT_CSUMMED;
+
+ if ((rx_buf->flags & EFX_RX_PKT_TCP) && !channel->type->receive_skb)
+ efx_rx_packet_gro(channel, rx_buf, channel->rx_pkt_n_frags, eh);
+ else
+ efx_rx_deliver(channel, eh, rx_buf, channel->rx_pkt_n_frags);
+out:
+ channel->rx_pkt_n_frags = 0;
}
int efx_probe_rx_queue(struct efx_rx_queue *rx_queue)
@@ -676,13 +697,36 @@ int efx_probe_rx_queue(struct efx_rx_queue *rx_queue)
kfree(rx_queue->buffer);
rx_queue->buffer = NULL;
}
+
return rc;
}
+static void efx_init_rx_recycle_ring(struct efx_nic *efx,
+ struct efx_rx_queue *rx_queue)
+{
+ unsigned int bufs_in_recycle_ring, page_ring_size;
+
+ /* Set the RX recycle ring size */
+#ifdef CONFIG_PPC64
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
+#else
+ if (iommu_present(&pci_bus_type))
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_IOMMU;
+ else
+ bufs_in_recycle_ring = EFX_RECYCLE_RING_SIZE_NOIOMMU;
+#endif /* CONFIG_PPC64 */
+
+ page_ring_size = roundup_pow_of_two(bufs_in_recycle_ring /
+ efx->rx_bufs_per_page);
+ rx_queue->page_ring = kcalloc(page_ring_size,
+ sizeof(*rx_queue->page_ring), GFP_KERNEL);
+ rx_queue->page_ptr_mask = page_ring_size - 1;
+}
+
void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
{
struct efx_nic *efx = rx_queue->efx;
- unsigned int max_fill, trigger, limit;
+ unsigned int max_fill, trigger, max_trigger;
netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
"initialising RX queue %d\n", efx_rx_queue_index(rx_queue));
@@ -692,15 +736,29 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
rx_queue->notified_count = 0;
rx_queue->removed_count = 0;
rx_queue->min_fill = -1U;
+ efx_init_rx_recycle_ring(efx, rx_queue);
+
+ rx_queue->page_remove = 0;
+ rx_queue->page_add = rx_queue->page_ptr_mask + 1;
+ rx_queue->page_recycle_count = 0;
+ rx_queue->page_recycle_failed = 0;
+ rx_queue->page_recycle_full = 0;
/* Initialise limit fields */
max_fill = efx->rxq_entries - EFX_RXD_HEAD_ROOM;
- trigger = max_fill * min(rx_refill_threshold, 100U) / 100U;
- limit = max_fill * min(rx_refill_limit, 100U) / 100U;
+ max_trigger =
+ max_fill - efx->rx_pages_per_batch * efx->rx_bufs_per_page;
+ if (rx_refill_threshold != 0) {
+ trigger = max_fill * min(rx_refill_threshold, 100U) / 100U;
+ if (trigger > max_trigger)
+ trigger = max_trigger;
+ } else {
+ trigger = max_trigger;
+ }
rx_queue->max_fill = max_fill;
rx_queue->fast_fill_trigger = trigger;
- rx_queue->fast_fill_limit = limit;
+ rx_queue->refill_enabled = true;
/* Set up RX descriptor ring */
efx_nic_init_rx(rx_queue);
@@ -709,21 +767,40 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue)
void efx_fini_rx_queue(struct efx_rx_queue *rx_queue)
{
int i;
+ struct efx_nic *efx = rx_queue->efx;
struct efx_rx_buffer *rx_buf;
netif_dbg(rx_queue->efx, drv, rx_queue->efx->net_dev,
"shutting down RX queue %d\n", efx_rx_queue_index(rx_queue));
del_timer_sync(&rx_queue->slow_fill);
- efx_nic_fini_rx(rx_queue);
- /* Release RX buffers NB start at index 0 not current HW ptr */
+ /* Release RX buffers from the current read ptr to the write ptr */
if (rx_queue->buffer) {
- for (i = 0; i <= rx_queue->ptr_mask; i++) {
- rx_buf = efx_rx_buffer(rx_queue, i);
+ for (i = rx_queue->removed_count; i < rx_queue->added_count;
+ i++) {
+ unsigned index = i & rx_queue->ptr_mask;
+ rx_buf = efx_rx_buffer(rx_queue, index);
efx_fini_rx_buffer(rx_queue, rx_buf);
}
}
+
+ /* Unmap and release the pages in the recycle ring. Remove the ring. */
+ for (i = 0; i <= rx_queue->page_ptr_mask; i++) {
+ struct page *page = rx_queue->page_ring[i];
+ struct efx_rx_page_state *state;
+
+ if (page == NULL)
+ continue;
+
+ state = page_address(page);
+ dma_unmap_page(&efx->pci_dev->dev, state->dma_addr,
+ PAGE_SIZE << efx->rx_buffer_order,
+ DMA_FROM_DEVICE);
+ put_page(page);
+ }
+ kfree(rx_queue->page_ring);
+ rx_queue->page_ring = NULL;
}
void efx_remove_rx_queue(struct efx_rx_queue *rx_queue)
@@ -738,10 +815,167 @@ void efx_remove_rx_queue(struct efx_rx_queue *rx_queue)
}
-module_param(rx_alloc_method, int, 0644);
-MODULE_PARM_DESC(rx_alloc_method, "Allocation method used for RX buffers");
-
module_param(rx_refill_threshold, uint, 0444);
MODULE_PARM_DESC(rx_refill_threshold,
- "RX descriptor ring fast/slow fill threshold (%)");
+ "RX descriptor ring refill threshold (%)");
+
+#ifdef CONFIG_RFS_ACCEL
+
+int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb,
+ u16 rxq_index, u32 flow_id)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ struct efx_channel *channel;
+ struct efx_filter_spec spec;
+ const __be16 *ports;
+ __be16 ether_type;
+ int nhoff;
+ int rc;
+
+ /* The core RPS/RFS code has already parsed and validated
+ * VLAN, IP and transport headers. We assume they are in the
+ * header area.
+ */
+
+ if (skb->protocol == htons(ETH_P_8021Q)) {
+ const struct vlan_hdr *vh =
+ (const struct vlan_hdr *)skb->data;
+
+ /* We can't filter on the IP 5-tuple and the vlan
+ * together, so just strip the vlan header and filter
+ * on the IP part.
+ */
+ EFX_BUG_ON_PARANOID(skb_headlen(skb) < sizeof(*vh));
+ ether_type = vh->h_vlan_encapsulated_proto;
+ nhoff = sizeof(struct vlan_hdr);
+ } else {
+ ether_type = skb->protocol;
+ nhoff = 0;
+ }
+
+ if (ether_type != htons(ETH_P_IP) && ether_type != htons(ETH_P_IPV6))
+ return -EPROTONOSUPPORT;
+
+ efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT,
+ efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0,
+ rxq_index);
+ spec.match_flags =
+ EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO |
+ EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT |
+ EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT;
+ spec.ether_type = ether_type;
+
+ if (ether_type == htons(ETH_P_IP)) {
+ const struct iphdr *ip =
+ (const struct iphdr *)(skb->data + nhoff);
+
+ EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip));
+ if (ip_is_fragment(ip))
+ return -EPROTONOSUPPORT;
+ spec.ip_proto = ip->protocol;
+ spec.rem_host[0] = ip->saddr;
+ spec.loc_host[0] = ip->daddr;
+ EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4);
+ ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl);
+ } else {
+ const struct ipv6hdr *ip6 =
+ (const struct ipv6hdr *)(skb->data + nhoff);
+
+ EFX_BUG_ON_PARANOID(skb_headlen(skb) <
+ nhoff + sizeof(*ip6) + 4);
+ spec.ip_proto = ip6->nexthdr;
+ memcpy(spec.rem_host, &ip6->saddr, sizeof(ip6->saddr));
+ memcpy(spec.loc_host, &ip6->daddr, sizeof(ip6->daddr));
+ ports = (const __be16 *)(ip6 + 1);
+ }
+
+ spec.rem_port = ports[0];
+ spec.loc_port = ports[1];
+
+ rc = efx->type->filter_rfs_insert(efx, &spec);
+ if (rc < 0)
+ return rc;
+
+ /* Remember this so we can check whether to expire the filter later */
+ efx->rps_flow_id[rc] = flow_id;
+ channel = efx_get_channel(efx, skb_get_rx_queue(skb));
+ ++channel->rfs_filters_added;
+
+ if (ether_type == htons(ETH_P_IP))
+ netif_info(efx, rx_status, efx->net_dev,
+ "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n",
+ (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
+ spec.rem_host, ntohs(ports[0]), spec.loc_host,
+ ntohs(ports[1]), rxq_index, flow_id, rc);
+ else
+ netif_info(efx, rx_status, efx->net_dev,
+ "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n",
+ (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP",
+ spec.rem_host, ntohs(ports[0]), spec.loc_host,
+ ntohs(ports[1]), rxq_index, flow_id, rc);
+
+ return rc;
+}
+bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned int quota)
+{
+ bool (*expire_one)(struct efx_nic *efx, u32 flow_id, unsigned int index);
+ unsigned int index, size;
+ u32 flow_id;
+
+ if (!spin_trylock_bh(&efx->filter_lock))
+ return false;
+
+ expire_one = efx->type->filter_rfs_expire_one;
+ index = efx->rps_expire_index;
+ size = efx->type->max_rx_ip_filters;
+ while (quota--) {
+ flow_id = efx->rps_flow_id[index];
+ if (expire_one(efx, flow_id, index))
+ netif_info(efx, rx_status, efx->net_dev,
+ "expired filter %d [flow %u]\n",
+ index, flow_id);
+ if (++index == size)
+ index = 0;
+ }
+ efx->rps_expire_index = index;
+
+ spin_unlock_bh(&efx->filter_lock);
+ return true;
+}
+
+#endif /* CONFIG_RFS_ACCEL */
+
+/**
+ * efx_filter_is_mc_recipient - test whether spec is a multicast recipient
+ * @spec: Specification to test
+ *
+ * Return: %true if the specification is a non-drop RX filter that
+ * matches a local MAC address I/G bit value of 1 or matches a local
+ * IPv4 or IPv6 address value in the respective multicast address
+ * range. Otherwise %false.
+ */
+bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec)
+{
+ if (!(spec->flags & EFX_FILTER_FLAG_RX) ||
+ spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP)
+ return false;
+
+ if (spec->match_flags &
+ (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG) &&
+ is_multicast_ether_addr(spec->loc_mac))
+ return true;
+
+ if ((spec->match_flags &
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) ==
+ (EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_LOC_HOST)) {
+ if (spec->ether_type == htons(ETH_P_IP) &&
+ ipv4_is_multicast(spec->loc_host[0]))
+ return true;
+ if (spec->ether_type == htons(ETH_P_IPV6) &&
+ ((const u8 *)spec->loc_host)[0] == 0xff)
+ return true;
+ }
+
+ return false;
+}
diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c
index 52edd24fcde..0fc5baef45b 100644
--- a/drivers/net/ethernet/sfc/selftest.c
+++ b/drivers/net/ethernet/sfc/selftest.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2012 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -19,13 +19,22 @@
#include <linux/udp.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
-#include <asm/io.h>
#include "net_driver.h"
#include "efx.h"
#include "nic.h"
#include "selftest.h"
#include "workarounds.h"
+/* IRQ latency can be enormous because:
+ * - All IRQs may be disabled on a CPU for a *long* time by e.g. a
+ * slow serial console or an old IDE driver doing error recovery
+ * - The PREEMPT_RT patches mostly deal with this, but also allow a
+ * tasklet or normal task to be given higher priority than our IRQ
+ * threads
+ * Try to avoid blaming the hardware for this.
+ */
+#define IRQ_TIMEOUT HZ
+
/*
* Loopback test packet structure
*
@@ -41,7 +50,7 @@ struct efx_loopback_payload {
} __packed;
/* Loopback test source MAC address */
-static const unsigned char payload_source[ETH_ALEN] = {
+static const u8 payload_source[ETH_ALEN] __aligned(2) = {
0x00, 0x0f, 0x53, 0x1b, 0x1b, 0x1b,
};
@@ -50,7 +59,7 @@ static const char payload_msg[] =
/* Interrupt mode names */
static const unsigned int efx_interrupt_mode_max = EFX_INT_MODE_MAX;
-static const char *efx_interrupt_mode_names[] = {
+static const char *const efx_interrupt_mode_names[] = {
[EFX_INT_MODE_MSIX] = "MSI-X",
[EFX_INT_MODE_MSI] = "MSI",
[EFX_INT_MODE_LEGACY] = "legacy",
@@ -78,6 +87,9 @@ struct efx_loopback_state {
struct efx_loopback_payload payload;
};
+/* How long to wait for all the packets to arrive (in ms) */
+#define LOOPBACK_TIMEOUT_MS 1000
+
/**************************************************************************
*
* MII, NVRAM and register tests
@@ -108,19 +120,6 @@ static int efx_test_nvram(struct efx_nic *efx, struct efx_self_tests *tests)
return rc;
}
-static int efx_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
-{
- int rc = 0;
-
- /* Test register access */
- if (efx->type->test_registers) {
- rc = efx->type->test_registers(efx);
- tests->registers = rc ? -1 : 1;
- }
-
- return rc;
-}
-
/**************************************************************************
*
* Interrupt and event queue testing
@@ -131,87 +130,117 @@ static int efx_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
static int efx_test_interrupts(struct efx_nic *efx,
struct efx_self_tests *tests)
{
+ unsigned long timeout, wait;
+ int cpu;
+
netif_dbg(efx, drv, efx->net_dev, "testing interrupts\n");
tests->interrupt = -1;
- /* Reset interrupt flag */
- efx->last_irq_cpu = -1;
- smp_wmb();
-
- efx_nic_generate_interrupt(efx);
+ efx_nic_irq_test_start(efx);
+ timeout = jiffies + IRQ_TIMEOUT;
+ wait = 1;
/* Wait for arrival of test interrupt. */
netif_dbg(efx, drv, efx->net_dev, "waiting for test interrupt\n");
- schedule_timeout_uninterruptible(HZ / 10);
- if (efx->last_irq_cpu >= 0)
- goto success;
+ do {
+ schedule_timeout_uninterruptible(wait);
+ cpu = efx_nic_irq_test_irq_cpu(efx);
+ if (cpu >= 0)
+ goto success;
+ wait *= 2;
+ } while (time_before(jiffies, timeout));
netif_err(efx, drv, efx->net_dev, "timed out waiting for interrupt\n");
return -ETIMEDOUT;
success:
netif_dbg(efx, drv, efx->net_dev, "%s test interrupt seen on CPU%d\n",
- INT_MODE(efx),
- efx->last_irq_cpu);
+ INT_MODE(efx), cpu);
tests->interrupt = 1;
return 0;
}
/* Test generation and receipt of interrupting events */
-static int efx_test_eventq_irq(struct efx_channel *channel,
+static int efx_test_eventq_irq(struct efx_nic *efx,
struct efx_self_tests *tests)
{
- struct efx_nic *efx = channel->efx;
- unsigned int read_ptr, count;
+ struct efx_channel *channel;
+ unsigned int read_ptr[EFX_MAX_CHANNELS];
+ unsigned long napi_ran = 0, dma_pend = 0, int_pend = 0;
+ unsigned long timeout, wait;
- tests->eventq_dma[channel->channel] = -1;
- tests->eventq_int[channel->channel] = -1;
- tests->eventq_poll[channel->channel] = -1;
+ BUILD_BUG_ON(EFX_MAX_CHANNELS > BITS_PER_LONG);
- read_ptr = channel->eventq_read_ptr;
- channel->efx->last_irq_cpu = -1;
- smp_wmb();
+ efx_for_each_channel(channel, efx) {
+ read_ptr[channel->channel] = channel->eventq_read_ptr;
+ set_bit(channel->channel, &dma_pend);
+ set_bit(channel->channel, &int_pend);
+ efx_nic_event_test_start(channel);
+ }
- efx_nic_generate_test_event(channel);
+ timeout = jiffies + IRQ_TIMEOUT;
+ wait = 1;
- /* Wait for arrival of interrupt */
- count = 0;
+ /* Wait for arrival of interrupts. NAPI processing may or may
+ * not complete in time, but we can cope in any case.
+ */
do {
- schedule_timeout_uninterruptible(HZ / 100);
-
- if (ACCESS_ONCE(channel->eventq_read_ptr) != read_ptr)
- goto eventq_ok;
- } while (++count < 2);
-
- netif_err(efx, drv, efx->net_dev,
- "channel %d timed out waiting for event queue\n",
- channel->channel);
+ schedule_timeout_uninterruptible(wait);
+
+ efx_for_each_channel(channel, efx) {
+ napi_disable(&channel->napi_str);
+ if (channel->eventq_read_ptr !=
+ read_ptr[channel->channel]) {
+ set_bit(channel->channel, &napi_ran);
+ clear_bit(channel->channel, &dma_pend);
+ clear_bit(channel->channel, &int_pend);
+ } else {
+ if (efx_nic_event_present(channel))
+ clear_bit(channel->channel, &dma_pend);
+ if (efx_nic_event_test_irq_cpu(channel) >= 0)
+ clear_bit(channel->channel, &int_pend);
+ }
+ napi_enable(&channel->napi_str);
+ efx_nic_eventq_read_ack(channel);
+ }
- /* See if interrupt arrived */
- if (channel->efx->last_irq_cpu >= 0) {
- netif_err(efx, drv, efx->net_dev,
- "channel %d saw interrupt on CPU%d "
- "during event queue test\n", channel->channel,
- raw_smp_processor_id());
- tests->eventq_int[channel->channel] = 1;
- }
+ wait *= 2;
+ } while ((dma_pend || int_pend) && time_before(jiffies, timeout));
- /* Check to see if event was received even if interrupt wasn't */
- if (efx_nic_event_present(channel)) {
- netif_err(efx, drv, efx->net_dev,
- "channel %d event was generated, but "
- "failed to trigger an interrupt\n", channel->channel);
- tests->eventq_dma[channel->channel] = 1;
+ efx_for_each_channel(channel, efx) {
+ bool dma_seen = !test_bit(channel->channel, &dma_pend);
+ bool int_seen = !test_bit(channel->channel, &int_pend);
+
+ tests->eventq_dma[channel->channel] = dma_seen ? 1 : -1;
+ tests->eventq_int[channel->channel] = int_seen ? 1 : -1;
+
+ if (dma_seen && int_seen) {
+ netif_dbg(efx, drv, efx->net_dev,
+ "channel %d event queue passed (with%s NAPI)\n",
+ channel->channel,
+ test_bit(channel->channel, &napi_ran) ?
+ "" : "out");
+ } else {
+ /* Report failure and whether either interrupt or DMA
+ * worked
+ */
+ netif_err(efx, drv, efx->net_dev,
+ "channel %d timed out waiting for event queue\n",
+ channel->channel);
+ if (int_seen)
+ netif_err(efx, drv, efx->net_dev,
+ "channel %d saw interrupt "
+ "during event queue test\n",
+ channel->channel);
+ if (dma_seen)
+ netif_err(efx, drv, efx->net_dev,
+ "channel %d event was generated, but "
+ "failed to trigger an interrupt\n",
+ channel->channel);
+ }
}
- return -ETIMEDOUT;
- eventq_ok:
- netif_dbg(efx, drv, efx->net_dev, "channel %d event queue passed\n",
- channel->channel);
- tests->eventq_dma[channel->channel] = 1;
- tests->eventq_int[channel->channel] = 1;
- tests->eventq_poll[channel->channel] = 1;
- return 0;
+ return (dma_pend || int_pend) ? -ETIMEDOUT : 0;
}
static int efx_test_phy(struct efx_nic *efx, struct efx_self_tests *tests,
@@ -316,7 +345,7 @@ void efx_loopback_rx_packet(struct efx_nic *efx,
return;
err:
-#ifdef EFX_ENABLE_DEBUG
+#ifdef DEBUG
if (atomic_read(&state->rx_bad) == 0) {
netif_err(efx, drv, efx->net_dev, "received packet:\n");
print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 0x10, 1,
@@ -337,14 +366,14 @@ static void efx_iterate_state(struct efx_nic *efx)
struct efx_loopback_payload *payload = &state->payload;
/* Initialise the layerII header */
- memcpy(&payload->header.h_dest, net_dev->dev_addr, ETH_ALEN);
- memcpy(&payload->header.h_source, &payload_source, ETH_ALEN);
+ ether_addr_copy((u8 *)&payload->header.h_dest, net_dev->dev_addr);
+ ether_addr_copy((u8 *)&payload->header.h_source, payload_source);
payload->header.h_proto = htons(ETH_P_IP);
/* saddr set later and used as incrementing count */
payload->ip.daddr = htonl(INADDR_LOOPBACK);
payload->ip.ihl = 5;
- payload->ip.check = htons(0xdead);
+ payload->ip.check = (__force __sum16) htons(0xdead);
payload->ip.tot_len = htons(sizeof(*payload) - sizeof(struct ethhdr));
payload->ip.version = IPVERSION;
payload->ip.protocol = IPPROTO_UDP;
@@ -395,11 +424,9 @@ static int efx_begin_loopback(struct efx_tx_queue *tx_queue)
* interrupt handler. */
smp_wmb();
- if (efx_dev_registered(efx))
- netif_tx_lock_bh(efx->net_dev);
+ netif_tx_lock_bh(efx->net_dev);
rc = efx_enqueue_skb(tx_queue, skb);
- if (efx_dev_registered(efx))
- netif_tx_unlock_bh(efx->net_dev);
+ netif_tx_unlock_bh(efx->net_dev);
if (rc != NETDEV_TX_OK) {
netif_err(efx, drv, efx->net_dev,
@@ -420,14 +447,7 @@ static int efx_begin_loopback(struct efx_tx_queue *tx_queue)
static int efx_poll_loopback(struct efx_nic *efx)
{
struct efx_loopback_state *state = efx->loopback_selftest;
- struct efx_channel *channel;
- /* NAPI polling is not enabled, so process channels
- * synchronously */
- efx_for_each_channel(channel, efx) {
- if (channel->work_pending)
- efx_process_channel_now(channel);
- }
return atomic_read(&state->rx_good) == state->packet_count;
}
@@ -440,20 +460,18 @@ static int efx_end_loopback(struct efx_tx_queue *tx_queue,
int tx_done = 0, rx_good, rx_bad;
int i, rc = 0;
- if (efx_dev_registered(efx))
- netif_tx_lock_bh(efx->net_dev);
+ netif_tx_lock_bh(efx->net_dev);
/* Count the number of tx completions, and decrement the refcnt. Any
* skbs not already completed will be free'd when the queue is flushed */
- for (i=0; i < state->packet_count; i++) {
+ for (i = 0; i < state->packet_count; i++) {
skb = state->skbs[i];
if (skb && !skb_shared(skb))
++tx_done;
- dev_kfree_skb_any(skb);
+ dev_kfree_skb(skb);
}
- if (efx_dev_registered(efx))
- netif_tx_unlock_bh(efx->net_dev);
+ netif_tx_unlock_bh(efx->net_dev);
/* Check TX completion and received packet counts */
rx_good = atomic_read(&state->rx_good);
@@ -518,10 +536,10 @@ efx_test_loopback(struct efx_tx_queue *tx_queue,
begin_rc = efx_begin_loopback(tx_queue);
/* This will normally complete very quickly, but be
- * prepared to wait up to 100 ms. */
+ * prepared to wait much longer. */
msleep(1);
if (!efx_poll_loopback(efx)) {
- msleep(100);
+ msleep(LOOPBACK_TIMEOUT_MS);
efx_poll_loopback(efx);
}
@@ -561,16 +579,12 @@ static int efx_wait_for_link(struct efx_nic *efx)
mutex_lock(&efx->mac_lock);
efx->type->monitor(efx);
mutex_unlock(&efx->mac_lock);
- } else {
- struct efx_channel *channel = efx_get_channel(efx, 0);
- if (channel->work_pending)
- efx_process_channel_now(channel);
}
mutex_lock(&efx->mac_lock);
link_up = link_state->up;
if (link_up)
- link_up = !efx->mac_op->check_fault(efx);
+ link_up = !efx->type->check_mac_fault(efx);
mutex_unlock(&efx->mac_lock);
if (link_up) {
@@ -589,7 +603,8 @@ static int efx_test_loopbacks(struct efx_nic *efx, struct efx_self_tests *tests,
{
enum efx_loopback_mode mode;
struct efx_loopback_state *state;
- struct efx_channel *channel = efx_get_channel(efx, 0);
+ struct efx_channel *channel =
+ efx_get_channel(efx, efx->tx_channel_offset);
struct efx_tx_queue *tx_queue;
int rc = 0;
@@ -661,9 +676,9 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
{
enum efx_loopback_mode loopback_mode = efx->loopback_mode;
int phy_mode = efx->phy_mode;
- enum reset_type reset_method = RESET_TYPE_INVISIBLE;
- struct efx_channel *channel;
- int rc_test = 0, rc_reset = 0, rc;
+ int rc_test = 0, rc_reset, rc;
+
+ efx_selftest_async_cancel(efx);
/* Online (i.e. non-disruptive) testing
* This checks interrupt generation, event delivery and PHY presence. */
@@ -680,11 +695,9 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
if (rc && !rc_test)
rc_test = rc;
- efx_for_each_channel(channel, efx) {
- rc = efx_test_eventq_irq(channel, tests);
- if (rc && !rc_test)
- rc_test = rc;
- }
+ rc = efx_test_eventq_irq(efx, tests);
+ if (rc && !rc_test)
+ rc_test = rc;
if (rc_test)
return rc_test;
@@ -698,46 +711,28 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
/* Detach the device so the kernel doesn't transmit during the
* loopback test and the watchdog timeout doesn't fire.
*/
- netif_device_detach(efx->net_dev);
+ efx_device_detach_sync(efx);
+
+ if (efx->type->test_chip) {
+ rc_reset = efx->type->test_chip(efx, tests);
+ if (rc_reset) {
+ netif_err(efx, hw, efx->net_dev,
+ "Unable to recover from chip test\n");
+ efx_schedule_reset(efx, RESET_TYPE_DISABLE);
+ return rc_reset;
+ }
- mutex_lock(&efx->mac_lock);
- if (efx->loopback_modes) {
- /* We need the 312 clock from the PHY to test the XMAC
- * registers, so move into XGMII loopback if available */
- if (efx->loopback_modes & (1 << LOOPBACK_XGMII))
- efx->loopback_mode = LOOPBACK_XGMII;
- else
- efx->loopback_mode = __ffs(efx->loopback_modes);
+ if ((tests->memory < 0 || tests->registers < 0) && !rc_test)
+ rc_test = -EIO;
}
- __efx_reconfigure_port(efx);
- mutex_unlock(&efx->mac_lock);
-
- /* free up all consumers of SRAM (including all the queues) */
- efx_reset_down(efx, reset_method);
-
- rc = efx_test_chip(efx, tests);
- if (rc && !rc_test)
- rc_test = rc;
-
- /* reset the chip to recover from the register test */
- rc_reset = efx->type->reset(efx, reset_method);
-
/* Ensure that the phy is powered and out of loopback
* for the bist and loopback tests */
+ mutex_lock(&efx->mac_lock);
efx->phy_mode &= ~PHY_MODE_LOW_POWER;
efx->loopback_mode = LOOPBACK_NONE;
-
- rc = efx_reset_up(efx, reset_method, rc_reset == 0);
- if (rc && !rc_reset)
- rc_reset = rc;
-
- if (rc_reset) {
- netif_err(efx, drv, efx->net_dev,
- "Unable to recover from chip test\n");
- efx_schedule_reset(efx, RESET_TYPE_DISABLE);
- return rc_reset;
- }
+ __efx_reconfigure_port(efx);
+ mutex_unlock(&efx->mac_lock);
rc = efx_test_phy(efx, tests, flags);
if (rc && !rc_test)
@@ -759,3 +754,36 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
return rc_test;
}
+void efx_selftest_async_start(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+
+ efx_for_each_channel(channel, efx)
+ efx_nic_event_test_start(channel);
+ schedule_delayed_work(&efx->selftest_work, IRQ_TIMEOUT);
+}
+
+void efx_selftest_async_cancel(struct efx_nic *efx)
+{
+ cancel_delayed_work_sync(&efx->selftest_work);
+}
+
+void efx_selftest_async_work(struct work_struct *data)
+{
+ struct efx_nic *efx = container_of(data, struct efx_nic,
+ selftest_work.work);
+ struct efx_channel *channel;
+ int cpu;
+
+ efx_for_each_channel(channel, efx) {
+ cpu = efx_nic_event_test_irq_cpu(channel);
+ if (cpu < 0)
+ netif_err(efx, ifup, efx->net_dev,
+ "channel %d failed to trigger an interrupt\n",
+ channel->channel);
+ else
+ netif_dbg(efx, ifup, efx->net_dev,
+ "channel %d triggered interrupt on CPU %d\n",
+ channel->channel, cpu);
+ }
+}
diff --git a/drivers/net/ethernet/sfc/selftest.h b/drivers/net/ethernet/sfc/selftest.h
index dba5456e70f..009dbe88f3b 100644
--- a/drivers/net/ethernet/sfc/selftest.h
+++ b/drivers/net/ethernet/sfc/selftest.h
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2012 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -37,17 +37,19 @@ struct efx_self_tests {
int interrupt;
int eventq_dma[EFX_MAX_CHANNELS];
int eventq_int[EFX_MAX_CHANNELS];
- int eventq_poll[EFX_MAX_CHANNELS];
/* offline tests */
+ int memory;
int registers;
int phy_ext[EFX_MAX_PHY_TESTS];
struct efx_loopback_self_tests loopback[LOOPBACK_TEST_MAX + 1];
};
-extern void efx_loopback_rx_packet(struct efx_nic *efx,
- const char *buf_ptr, int pkt_len);
-extern int efx_selftest(struct efx_nic *efx,
- struct efx_self_tests *tests,
- unsigned flags);
+void efx_loopback_rx_packet(struct efx_nic *efx, const char *buf_ptr,
+ int pkt_len);
+int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests,
+ unsigned flags);
+void efx_selftest_async_start(struct efx_nic *efx);
+void efx_selftest_async_cancel(struct efx_nic *efx);
+void efx_selftest_async_work(struct work_struct *data);
#endif /* EFX_SELFTEST_H */
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 4d5d619feaa..50ffefed492 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -18,14 +18,13 @@
#include "bitfield.h"
#include "efx.h"
#include "nic.h"
-#include "mac.h"
-#include "spi.h"
-#include "regs.h"
+#include "farch_regs.h"
#include "io.h"
#include "phy.h"
#include "workarounds.h"
#include "mcdi.h"
#include "mcdi_pcol.h"
+#include "selftest.h"
/* Hardware control for SFC9000 family including SFL9021 (aka Siena). */
@@ -36,8 +35,6 @@ static void siena_push_irq_moderation(struct efx_channel *channel)
{
efx_dword_t timer_cmd;
- BUILD_BUG_ON(EFX_IRQ_MOD_MAX > (1 << FRF_CZ_TC_TIMER_VAL_WIDTH));
-
if (channel->irq_moderation)
EFX_POPULATE_DWORD_2(timer_cmd,
FRF_CZ_TC_TIMER_MODE,
@@ -53,91 +50,19 @@ static void siena_push_irq_moderation(struct efx_channel *channel)
channel->channel);
}
-static void siena_push_multicast_hash(struct efx_nic *efx)
-{
- WARN_ON(!mutex_is_locked(&efx->mac_lock));
-
- efx_mcdi_rpc(efx, MC_CMD_SET_MCAST_HASH,
- efx->multicast_hash.byte, sizeof(efx->multicast_hash),
- NULL, 0, NULL);
-}
-
-static int siena_mdio_write(struct net_device *net_dev,
- int prtad, int devad, u16 addr, u16 value)
-{
- struct efx_nic *efx = netdev_priv(net_dev);
- uint32_t status;
- int rc;
-
- rc = efx_mcdi_mdio_write(efx, efx->mdio_bus, prtad, devad,
- addr, value, &status);
- if (rc)
- return rc;
- if (status != MC_CMD_MDIO_STATUS_GOOD)
- return -EIO;
-
- return 0;
-}
-
-static int siena_mdio_read(struct net_device *net_dev,
- int prtad, int devad, u16 addr)
+void siena_prepare_flush(struct efx_nic *efx)
{
- struct efx_nic *efx = netdev_priv(net_dev);
- uint16_t value;
- uint32_t status;
- int rc;
-
- rc = efx_mcdi_mdio_read(efx, efx->mdio_bus, prtad, devad,
- addr, &value, &status);
- if (rc)
- return rc;
- if (status != MC_CMD_MDIO_STATUS_GOOD)
- return -EIO;
-
- return (int)value;
-}
-
-/* This call is responsible for hooking in the MAC and PHY operations */
-static int siena_probe_port(struct efx_nic *efx)
-{
- int rc;
-
- /* Hook in PHY operations table */
- efx->phy_op = &efx_mcdi_phy_ops;
-
- /* Set up MDIO structure for PHY */
- efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
- efx->mdio.mdio_read = siena_mdio_read;
- efx->mdio.mdio_write = siena_mdio_write;
-
- /* Fill out MDIO structure, loopback modes, and initial link state */
- rc = efx->phy_op->probe(efx);
- if (rc != 0)
- return rc;
-
- /* Allocate buffer for stats */
- rc = efx_nic_alloc_buffer(efx, &efx->stats_buffer,
- MC_CMD_MAC_NSTATS * sizeof(u64));
- if (rc)
- return rc;
- netif_dbg(efx, probe, efx->net_dev,
- "stats buffer at %llx (virt %p phys %llx)\n",
- (u64)efx->stats_buffer.dma_addr,
- efx->stats_buffer.addr,
- (u64)virt_to_phys(efx->stats_buffer.addr));
-
- efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 1);
-
- return 0;
+ if (efx->fc_disable++ == 0)
+ efx_mcdi_set_mac(efx);
}
-static void siena_remove_port(struct efx_nic *efx)
+void siena_finish_flush(struct efx_nic *efx)
{
- efx->phy_op->remove(efx);
- efx_nic_free_buffer(efx, &efx->stats_buffer);
+ if (--efx->fc_disable == 0)
+ efx_mcdi_set_mac(efx);
}
-static const struct efx_nic_register_test siena_register_tests[] = {
+static const struct efx_farch_register_test siena_register_tests[] = {
{ FR_AZ_ADR_REGION,
EFX_OWORD32(0x0003FFFF, 0x0003FFFF, 0x0003FFFF, 0x0003FFFF) },
{ FR_CZ_USR_EV_CFG,
@@ -166,24 +91,86 @@ static const struct efx_nic_register_test siena_register_tests[] = {
EFX_OWORD32(0xFFFFFFFF, 0xFFFFFFFF, 0x00000007, 0x00000000) },
};
-static int siena_test_registers(struct efx_nic *efx)
+static int siena_test_chip(struct efx_nic *efx, struct efx_self_tests *tests)
{
- return efx_nic_test_registers(efx, siena_register_tests,
- ARRAY_SIZE(siena_register_tests));
+ enum reset_type reset_method = RESET_TYPE_ALL;
+ int rc, rc2;
+
+ efx_reset_down(efx, reset_method);
+
+ /* Reset the chip immediately so that it is completely
+ * quiescent regardless of what any VF driver does.
+ */
+ rc = efx_mcdi_reset(efx, reset_method);
+ if (rc)
+ goto out;
+
+ tests->registers =
+ efx_farch_test_registers(efx, siena_register_tests,
+ ARRAY_SIZE(siena_register_tests))
+ ? -1 : 1;
+
+ rc = efx_mcdi_reset(efx, reset_method);
+out:
+ rc2 = efx_reset_up(efx, reset_method, rc == 0);
+ return rc ? rc : rc2;
}
/**************************************************************************
*
- * Device reset
+ * PTP
*
**************************************************************************
*/
-static enum reset_type siena_map_reset_reason(enum reset_type reason)
+static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time)
{
- return RESET_TYPE_ALL;
+ _efx_writed(efx, cpu_to_le32(host_time),
+ FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST);
}
+static int siena_ptp_set_ts_config(struct efx_nic *efx,
+ struct hwtstamp_config *init)
+{
+ int rc;
+
+ switch (init->rx_filter) {
+ case HWTSTAMP_FILTER_NONE:
+ /* if TX timestamping is still requested then leave PTP on */
+ return efx_ptp_change_mode(efx,
+ init->tx_type != HWTSTAMP_TX_OFF,
+ efx_ptp_get_mode(efx));
+ case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+ init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
+ return efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V1);
+ case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+ case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+ case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+ init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
+ rc = efx_ptp_change_mode(efx, true,
+ MC_CMD_PTP_MODE_V2_ENHANCED);
+ /* bug 33070 - old versions of the firmware do not support the
+ * improved UUID filtering option. Similarly old versions of the
+ * application do not expect it to be enabled. If the firmware
+ * does not accept the enhanced mode, fall back to the standard
+ * PTP v2 UUID filtering. */
+ if (rc != 0)
+ rc = efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V2);
+ return rc;
+ default:
+ return -ERANGE;
+ }
+}
+
+/**************************************************************************
+ *
+ * Device reset
+ *
+ **************************************************************************
+ */
+
static int siena_map_reset_flags(u32 *flags)
{
enum {
@@ -209,30 +196,54 @@ static int siena_map_reset_flags(u32 *flags)
return -EINVAL;
}
-static int siena_reset_hw(struct efx_nic *efx, enum reset_type method)
+#ifdef CONFIG_EEH
+/* When a PCI device is isolated from the bus, a subsequent MMIO read is
+ * required for the kernel EEH mechanisms to notice. As the Solarflare driver
+ * was written to minimise MMIO read (for latency) then a periodic call to check
+ * the EEH status of the device is required so that device recovery can happen
+ * in a timely fashion.
+ */
+static void siena_monitor(struct efx_nic *efx)
{
+ struct eeh_dev *eehdev =
+ of_node_to_eeh_dev(pci_device_to_OF_node(efx->pci_dev));
+
+ eeh_dev_check_failure(eehdev);
+}
+#endif
+
+static int siena_probe_nvconfig(struct efx_nic *efx)
+{
+ u32 caps = 0;
int rc;
- /* Recover from a failed assertion pre-reset */
- rc = efx_mcdi_handle_assertion(efx);
- if (rc)
- return rc;
+ rc = efx_mcdi_get_board_cfg(efx, efx->net_dev->perm_addr, NULL, &caps);
- if (method == RESET_TYPE_WORLD)
- return efx_mcdi_reset_mc(efx);
- else
- return efx_mcdi_reset_port(efx);
+ efx->timer_quantum_ns =
+ (caps & (1 << MC_CMD_CAPABILITIES_TURBO_ACTIVE_LBN)) ?
+ 3072 : 6144; /* 768 cycles */
+ return rc;
}
-static int siena_probe_nvconfig(struct efx_nic *efx)
+static int siena_dimension_resources(struct efx_nic *efx)
+{
+ /* Each port has a small block of internal SRAM dedicated to
+ * the buffer table and descriptor caches. In theory we can
+ * map both blocks to one port, but we don't.
+ */
+ efx_farch_dimension_resources(efx, FR_CZ_BUF_FULL_TBL_ROWS / 2);
+ return 0;
+}
+
+static unsigned int siena_mem_map_size(struct efx_nic *efx)
{
- return efx_mcdi_get_board_cfg(efx, efx->net_dev->perm_addr, NULL);
+ return FR_CZ_MC_TREG_SMEM +
+ FR_CZ_MC_TREG_SMEM_STEP * FR_CZ_MC_TREG_SMEM_ROWS;
}
static int siena_probe_nic(struct efx_nic *efx)
{
struct siena_nic_data *nic_data;
- bool already_attached = false;
efx_oword_t reg;
int rc;
@@ -242,38 +253,24 @@ static int siena_probe_nic(struct efx_nic *efx)
return -ENOMEM;
efx->nic_data = nic_data;
- if (efx_nic_fpga_ver(efx) != 0) {
+ if (efx_farch_fpga_ver(efx) != 0) {
netif_err(efx, probe, efx->net_dev,
"Siena FPGA not supported\n");
rc = -ENODEV;
goto fail1;
}
- efx_reado(efx, &reg, FR_AZ_CS_DEBUG);
- efx->net_dev->dev_id = EFX_OWORD_FIELD(reg, FRF_CZ_CS_PORT_NUM) - 1;
+ efx->max_channels = EFX_MAX_CHANNELS;
- efx_mcdi_init(efx);
+ efx_reado(efx, &reg, FR_AZ_CS_DEBUG);
+ efx->port_num = EFX_OWORD_FIELD(reg, FRF_CZ_CS_PORT_NUM) - 1;
- /* Recover from a failed assertion before probing */
- rc = efx_mcdi_handle_assertion(efx);
+ rc = efx_mcdi_init(efx);
if (rc)
goto fail1;
- /* Let the BMC know that the driver is now in charge of link and
- * filter settings. We must do this before we reset the NIC */
- rc = efx_mcdi_drv_attach(efx, true, &already_attached);
- if (rc) {
- netif_err(efx, probe, efx->net_dev,
- "Unable to register driver with MCPU\n");
- goto fail2;
- }
- if (already_attached)
- /* Not a fatal error */
- netif_err(efx, probe, efx->net_dev,
- "Host already registered with MCPU\n");
-
/* Now we can reset the NIC */
- rc = siena_reset_hw(efx, RESET_TYPE_ALL);
+ rc = efx_mcdi_reset(efx, RESET_TYPE_ALL);
if (rc) {
netif_err(efx, probe, efx->net_dev, "failed to reset NIC\n");
goto fail3;
@@ -282,7 +279,8 @@ static int siena_probe_nic(struct efx_nic *efx)
siena_init_wol(efx);
/* Allocate memory for INT_KER */
- rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t));
+ rc = efx_nic_alloc_buffer(efx, &efx->irq_status, sizeof(efx_oword_t),
+ GFP_KERNEL);
if (rc)
goto fail4;
BUG_ON(efx->irq_status.dma_addr & 0x0f);
@@ -304,19 +302,50 @@ static int siena_probe_nic(struct efx_nic *efx)
goto fail5;
}
+ rc = efx_mcdi_mon_probe(efx);
+ if (rc)
+ goto fail5;
+
+ efx_sriov_probe(efx);
+ efx_ptp_defer_probe_with_channel(efx);
+
return 0;
fail5:
efx_nic_free_buffer(efx, &efx->irq_status);
fail4:
fail3:
- efx_mcdi_drv_attach(efx, false, NULL);
-fail2:
+ efx_mcdi_fini(efx);
fail1:
kfree(efx->nic_data);
return rc;
}
+static void siena_rx_push_rss_config(struct efx_nic *efx)
+{
+ efx_oword_t temp;
+
+ /* Set hash key for IPv4 */
+ memcpy(&temp, efx->rx_hash_key, sizeof(temp));
+ efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
+
+ /* Enable IPv6 RSS */
+ BUILD_BUG_ON(sizeof(efx->rx_hash_key) <
+ 2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 ||
+ FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0);
+ memcpy(&temp, efx->rx_hash_key, sizeof(temp));
+ efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1);
+ memcpy(&temp, efx->rx_hash_key + sizeof(temp), sizeof(temp));
+ efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2);
+ EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1,
+ FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1);
+ memcpy(&temp, efx->rx_hash_key + 2 * sizeof(temp),
+ FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
+ efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
+
+ efx_farch_rx_push_indir_table(efx);
+}
+
/* This call performs hardware-specific global initialisation, such as
* defining the descriptor cache sizes and number of RSS channels.
* It does not set up any buffers, descriptor rings or event queues.
@@ -353,25 +382,11 @@ static int siena_init_nic(struct efx_nic *efx)
EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_HASH_INSRT_HDR, 1);
EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_HASH_ALG, 1);
EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_IP_HASH, 1);
+ EFX_SET_OWORD_FIELD(temp, FRF_BZ_RX_USR_BUF_SIZE,
+ EFX_RX_USR_BUF_SIZE >> 5);
efx_writeo(efx, &temp, FR_AZ_RX_CFG);
- /* Set hash key for IPv4 */
- memcpy(&temp, efx->rx_hash_key, sizeof(temp));
- efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY);
-
- /* Enable IPv6 RSS */
- BUILD_BUG_ON(sizeof(efx->rx_hash_key) <
- 2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 ||
- FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0);
- memcpy(&temp, efx->rx_hash_key, sizeof(temp));
- efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1);
- memcpy(&temp, efx->rx_hash_key + sizeof(temp), sizeof(temp));
- efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2);
- EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1,
- FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1);
- memcpy(&temp, efx->rx_hash_key + 2 * sizeof(temp),
- FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8);
- efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3);
+ siena_rx_push_rss_config(efx);
/* Enable event logging */
rc = efx_mcdi_log_ctrl(efx, true, false, 0);
@@ -385,153 +400,204 @@ static int siena_init_nic(struct efx_nic *efx)
EFX_POPULATE_OWORD_1(temp, FRF_CZ_USREV_DIS, 1);
efx_writeo(efx, &temp, FR_CZ_USR_EV_CFG);
- efx_nic_init_common(efx);
+ efx_farch_init_common(efx);
return 0;
}
static void siena_remove_nic(struct efx_nic *efx)
{
+ efx_mcdi_mon_remove(efx);
+
efx_nic_free_buffer(efx, &efx->irq_status);
- siena_reset_hw(efx, RESET_TYPE_ALL);
+ efx_mcdi_reset(efx, RESET_TYPE_ALL);
- /* Relinquish the device back to the BMC */
- if (efx_nic_has_mc(efx))
- efx_mcdi_drv_attach(efx, false, NULL);
+ efx_mcdi_fini(efx);
/* Tear down the private nic state */
kfree(efx->nic_data);
efx->nic_data = NULL;
}
-#define STATS_GENERATION_INVALID ((__force __le64)(-1))
+#define SIENA_DMA_STAT(ext_name, mcdi_name) \
+ [SIENA_STAT_ ## ext_name] = \
+ { #ext_name, 64, 8 * MC_CMD_MAC_ ## mcdi_name }
+#define SIENA_OTHER_STAT(ext_name) \
+ [SIENA_STAT_ ## ext_name] = { #ext_name, 0, 0 }
+
+static const struct efx_hw_stat_desc siena_stat_desc[SIENA_STAT_COUNT] = {
+ SIENA_DMA_STAT(tx_bytes, TX_BYTES),
+ SIENA_OTHER_STAT(tx_good_bytes),
+ SIENA_DMA_STAT(tx_bad_bytes, TX_BAD_BYTES),
+ SIENA_DMA_STAT(tx_packets, TX_PKTS),
+ SIENA_DMA_STAT(tx_bad, TX_BAD_FCS_PKTS),
+ SIENA_DMA_STAT(tx_pause, TX_PAUSE_PKTS),
+ SIENA_DMA_STAT(tx_control, TX_CONTROL_PKTS),
+ SIENA_DMA_STAT(tx_unicast, TX_UNICAST_PKTS),
+ SIENA_DMA_STAT(tx_multicast, TX_MULTICAST_PKTS),
+ SIENA_DMA_STAT(tx_broadcast, TX_BROADCAST_PKTS),
+ SIENA_DMA_STAT(tx_lt64, TX_LT64_PKTS),
+ SIENA_DMA_STAT(tx_64, TX_64_PKTS),
+ SIENA_DMA_STAT(tx_65_to_127, TX_65_TO_127_PKTS),
+ SIENA_DMA_STAT(tx_128_to_255, TX_128_TO_255_PKTS),
+ SIENA_DMA_STAT(tx_256_to_511, TX_256_TO_511_PKTS),
+ SIENA_DMA_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS),
+ SIENA_DMA_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS),
+ SIENA_DMA_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS),
+ SIENA_DMA_STAT(tx_gtjumbo, TX_GTJUMBO_PKTS),
+ SIENA_OTHER_STAT(tx_collision),
+ SIENA_DMA_STAT(tx_single_collision, TX_SINGLE_COLLISION_PKTS),
+ SIENA_DMA_STAT(tx_multiple_collision, TX_MULTIPLE_COLLISION_PKTS),
+ SIENA_DMA_STAT(tx_excessive_collision, TX_EXCESSIVE_COLLISION_PKTS),
+ SIENA_DMA_STAT(tx_deferred, TX_DEFERRED_PKTS),
+ SIENA_DMA_STAT(tx_late_collision, TX_LATE_COLLISION_PKTS),
+ SIENA_DMA_STAT(tx_excessive_deferred, TX_EXCESSIVE_DEFERRED_PKTS),
+ SIENA_DMA_STAT(tx_non_tcpudp, TX_NON_TCPUDP_PKTS),
+ SIENA_DMA_STAT(tx_mac_src_error, TX_MAC_SRC_ERR_PKTS),
+ SIENA_DMA_STAT(tx_ip_src_error, TX_IP_SRC_ERR_PKTS),
+ SIENA_DMA_STAT(rx_bytes, RX_BYTES),
+ SIENA_OTHER_STAT(rx_good_bytes),
+ SIENA_DMA_STAT(rx_bad_bytes, RX_BAD_BYTES),
+ SIENA_DMA_STAT(rx_packets, RX_PKTS),
+ SIENA_DMA_STAT(rx_good, RX_GOOD_PKTS),
+ SIENA_DMA_STAT(rx_bad, RX_BAD_FCS_PKTS),
+ SIENA_DMA_STAT(rx_pause, RX_PAUSE_PKTS),
+ SIENA_DMA_STAT(rx_control, RX_CONTROL_PKTS),
+ SIENA_DMA_STAT(rx_unicast, RX_UNICAST_PKTS),
+ SIENA_DMA_STAT(rx_multicast, RX_MULTICAST_PKTS),
+ SIENA_DMA_STAT(rx_broadcast, RX_BROADCAST_PKTS),
+ SIENA_DMA_STAT(rx_lt64, RX_UNDERSIZE_PKTS),
+ SIENA_DMA_STAT(rx_64, RX_64_PKTS),
+ SIENA_DMA_STAT(rx_65_to_127, RX_65_TO_127_PKTS),
+ SIENA_DMA_STAT(rx_128_to_255, RX_128_TO_255_PKTS),
+ SIENA_DMA_STAT(rx_256_to_511, RX_256_TO_511_PKTS),
+ SIENA_DMA_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS),
+ SIENA_DMA_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS),
+ SIENA_DMA_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS),
+ SIENA_DMA_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS),
+ SIENA_DMA_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS),
+ SIENA_DMA_STAT(rx_overflow, RX_OVERFLOW_PKTS),
+ SIENA_DMA_STAT(rx_false_carrier, RX_FALSE_CARRIER_PKTS),
+ SIENA_DMA_STAT(rx_symbol_error, RX_SYMBOL_ERROR_PKTS),
+ SIENA_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS),
+ SIENA_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS),
+ SIENA_DMA_STAT(rx_internal_error, RX_INTERNAL_ERROR_PKTS),
+ SIENA_DMA_STAT(rx_nodesc_drop_cnt, RX_NODESC_DROPS),
+};
+static const unsigned long siena_stat_mask[] = {
+ [0 ... BITS_TO_LONGS(SIENA_STAT_COUNT) - 1] = ~0UL,
+};
+
+static size_t siena_describe_nic_stats(struct efx_nic *efx, u8 *names)
+{
+ return efx_nic_describe_stats(siena_stat_desc, SIENA_STAT_COUNT,
+ siena_stat_mask, names);
+}
static int siena_try_update_nic_stats(struct efx_nic *efx)
{
+ struct siena_nic_data *nic_data = efx->nic_data;
+ u64 *stats = nic_data->stats;
__le64 *dma_stats;
- struct efx_mac_stats *mac_stats;
__le64 generation_start, generation_end;
- mac_stats = &efx->mac_stats;
dma_stats = efx->stats_buffer.addr;
generation_end = dma_stats[MC_CMD_MAC_GENERATION_END];
- if (generation_end == STATS_GENERATION_INVALID)
+ if (generation_end == EFX_MC_STATS_GENERATION_INVALID)
return 0;
rmb();
-
-#define MAC_STAT(M, D) \
- mac_stats->M = le64_to_cpu(dma_stats[MC_CMD_MAC_ ## D])
-
- MAC_STAT(tx_bytes, TX_BYTES);
- MAC_STAT(tx_bad_bytes, TX_BAD_BYTES);
- mac_stats->tx_good_bytes = (mac_stats->tx_bytes -
- mac_stats->tx_bad_bytes);
- MAC_STAT(tx_packets, TX_PKTS);
- MAC_STAT(tx_bad, TX_BAD_FCS_PKTS);
- MAC_STAT(tx_pause, TX_PAUSE_PKTS);
- MAC_STAT(tx_control, TX_CONTROL_PKTS);
- MAC_STAT(tx_unicast, TX_UNICAST_PKTS);
- MAC_STAT(tx_multicast, TX_MULTICAST_PKTS);
- MAC_STAT(tx_broadcast, TX_BROADCAST_PKTS);
- MAC_STAT(tx_lt64, TX_LT64_PKTS);
- MAC_STAT(tx_64, TX_64_PKTS);
- MAC_STAT(tx_65_to_127, TX_65_TO_127_PKTS);
- MAC_STAT(tx_128_to_255, TX_128_TO_255_PKTS);
- MAC_STAT(tx_256_to_511, TX_256_TO_511_PKTS);
- MAC_STAT(tx_512_to_1023, TX_512_TO_1023_PKTS);
- MAC_STAT(tx_1024_to_15xx, TX_1024_TO_15XX_PKTS);
- MAC_STAT(tx_15xx_to_jumbo, TX_15XX_TO_JUMBO_PKTS);
- MAC_STAT(tx_gtjumbo, TX_GTJUMBO_PKTS);
- mac_stats->tx_collision = 0;
- MAC_STAT(tx_single_collision, TX_SINGLE_COLLISION_PKTS);
- MAC_STAT(tx_multiple_collision, TX_MULTIPLE_COLLISION_PKTS);
- MAC_STAT(tx_excessive_collision, TX_EXCESSIVE_COLLISION_PKTS);
- MAC_STAT(tx_deferred, TX_DEFERRED_PKTS);
- MAC_STAT(tx_late_collision, TX_LATE_COLLISION_PKTS);
- mac_stats->tx_collision = (mac_stats->tx_single_collision +
- mac_stats->tx_multiple_collision +
- mac_stats->tx_excessive_collision +
- mac_stats->tx_late_collision);
- MAC_STAT(tx_excessive_deferred, TX_EXCESSIVE_DEFERRED_PKTS);
- MAC_STAT(tx_non_tcpudp, TX_NON_TCPUDP_PKTS);
- MAC_STAT(tx_mac_src_error, TX_MAC_SRC_ERR_PKTS);
- MAC_STAT(tx_ip_src_error, TX_IP_SRC_ERR_PKTS);
- MAC_STAT(rx_bytes, RX_BYTES);
- MAC_STAT(rx_bad_bytes, RX_BAD_BYTES);
- mac_stats->rx_good_bytes = (mac_stats->rx_bytes -
- mac_stats->rx_bad_bytes);
- MAC_STAT(rx_packets, RX_PKTS);
- MAC_STAT(rx_good, RX_GOOD_PKTS);
- MAC_STAT(rx_bad, RX_BAD_FCS_PKTS);
- MAC_STAT(rx_pause, RX_PAUSE_PKTS);
- MAC_STAT(rx_control, RX_CONTROL_PKTS);
- MAC_STAT(rx_unicast, RX_UNICAST_PKTS);
- MAC_STAT(rx_multicast, RX_MULTICAST_PKTS);
- MAC_STAT(rx_broadcast, RX_BROADCAST_PKTS);
- MAC_STAT(rx_lt64, RX_UNDERSIZE_PKTS);
- MAC_STAT(rx_64, RX_64_PKTS);
- MAC_STAT(rx_65_to_127, RX_65_TO_127_PKTS);
- MAC_STAT(rx_128_to_255, RX_128_TO_255_PKTS);
- MAC_STAT(rx_256_to_511, RX_256_TO_511_PKTS);
- MAC_STAT(rx_512_to_1023, RX_512_TO_1023_PKTS);
- MAC_STAT(rx_1024_to_15xx, RX_1024_TO_15XX_PKTS);
- MAC_STAT(rx_15xx_to_jumbo, RX_15XX_TO_JUMBO_PKTS);
- MAC_STAT(rx_gtjumbo, RX_GTJUMBO_PKTS);
- mac_stats->rx_bad_lt64 = 0;
- mac_stats->rx_bad_64_to_15xx = 0;
- mac_stats->rx_bad_15xx_to_jumbo = 0;
- MAC_STAT(rx_bad_gtjumbo, RX_JABBER_PKTS);
- MAC_STAT(rx_overflow, RX_OVERFLOW_PKTS);
- mac_stats->rx_missed = 0;
- MAC_STAT(rx_false_carrier, RX_FALSE_CARRIER_PKTS);
- MAC_STAT(rx_symbol_error, RX_SYMBOL_ERROR_PKTS);
- MAC_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS);
- MAC_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS);
- MAC_STAT(rx_internal_error, RX_INTERNAL_ERROR_PKTS);
- mac_stats->rx_good_lt64 = 0;
-
- efx->n_rx_nodesc_drop_cnt =
- le64_to_cpu(dma_stats[MC_CMD_MAC_RX_NODESC_DROPS]);
-
-#undef MAC_STAT
-
+ efx_nic_update_stats(siena_stat_desc, SIENA_STAT_COUNT, siena_stat_mask,
+ stats, efx->stats_buffer.addr, false);
rmb();
generation_start = dma_stats[MC_CMD_MAC_GENERATION_START];
if (generation_end != generation_start)
return -EAGAIN;
+ /* Update derived statistics */
+ efx_nic_fix_nodesc_drop_stat(efx,
+ &stats[SIENA_STAT_rx_nodesc_drop_cnt]);
+ efx_update_diff_stat(&stats[SIENA_STAT_tx_good_bytes],
+ stats[SIENA_STAT_tx_bytes] -
+ stats[SIENA_STAT_tx_bad_bytes]);
+ stats[SIENA_STAT_tx_collision] =
+ stats[SIENA_STAT_tx_single_collision] +
+ stats[SIENA_STAT_tx_multiple_collision] +
+ stats[SIENA_STAT_tx_excessive_collision] +
+ stats[SIENA_STAT_tx_late_collision];
+ efx_update_diff_stat(&stats[SIENA_STAT_rx_good_bytes],
+ stats[SIENA_STAT_rx_bytes] -
+ stats[SIENA_STAT_rx_bad_bytes]);
return 0;
}
-static void siena_update_nic_stats(struct efx_nic *efx)
+static size_t siena_update_nic_stats(struct efx_nic *efx, u64 *full_stats,
+ struct rtnl_link_stats64 *core_stats)
{
+ struct siena_nic_data *nic_data = efx->nic_data;
+ u64 *stats = nic_data->stats;
int retry;
/* If we're unlucky enough to read statistics wduring the DMA, wait
* up to 10ms for it to finish (typically takes <500us) */
for (retry = 0; retry < 100; ++retry) {
if (siena_try_update_nic_stats(efx) == 0)
- return;
+ break;
udelay(100);
}
- /* Use the old values instead */
+ if (full_stats)
+ memcpy(full_stats, stats, sizeof(u64) * SIENA_STAT_COUNT);
+
+ if (core_stats) {
+ core_stats->rx_packets = stats[SIENA_STAT_rx_packets];
+ core_stats->tx_packets = stats[SIENA_STAT_tx_packets];
+ core_stats->rx_bytes = stats[SIENA_STAT_rx_bytes];
+ core_stats->tx_bytes = stats[SIENA_STAT_tx_bytes];
+ core_stats->rx_dropped = stats[SIENA_STAT_rx_nodesc_drop_cnt];
+ core_stats->multicast = stats[SIENA_STAT_rx_multicast];
+ core_stats->collisions = stats[SIENA_STAT_tx_collision];
+ core_stats->rx_length_errors =
+ stats[SIENA_STAT_rx_gtjumbo] +
+ stats[SIENA_STAT_rx_length_error];
+ core_stats->rx_crc_errors = stats[SIENA_STAT_rx_bad];
+ core_stats->rx_frame_errors = stats[SIENA_STAT_rx_align_error];
+ core_stats->rx_fifo_errors = stats[SIENA_STAT_rx_overflow];
+ core_stats->tx_window_errors =
+ stats[SIENA_STAT_tx_late_collision];
+
+ core_stats->rx_errors = (core_stats->rx_length_errors +
+ core_stats->rx_crc_errors +
+ core_stats->rx_frame_errors +
+ stats[SIENA_STAT_rx_symbol_error]);
+ core_stats->tx_errors = (core_stats->tx_window_errors +
+ stats[SIENA_STAT_tx_bad]);
+ }
+
+ return SIENA_STAT_COUNT;
}
-static void siena_start_nic_stats(struct efx_nic *efx)
+static int siena_mac_reconfigure(struct efx_nic *efx)
{
- __le64 *dma_stats = efx->stats_buffer.addr;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SET_MCAST_HASH_IN_LEN);
+ int rc;
- dma_stats[MC_CMD_MAC_GENERATION_END] = STATS_GENERATION_INVALID;
+ BUILD_BUG_ON(MC_CMD_SET_MCAST_HASH_IN_LEN !=
+ MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST +
+ sizeof(efx->multicast_hash));
- efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr,
- MC_CMD_MAC_NSTATS * sizeof(u64), 1, 0);
-}
+ efx_farch_filter_sync_rx_mode(efx);
-static void siena_stop_nic_stats(struct efx_nic *efx)
-{
- efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 0);
+ WARN_ON(!mutex_is_locked(&efx->mac_lock));
+
+ rc = efx_mcdi_set_mac(efx);
+ if (rc != 0)
+ return rc;
+
+ memcpy(MCDI_PTR(inbuf, SET_MCAST_HASH_IN_HASH0),
+ efx->multicast_hash.byte, sizeof(efx->multicast_hash));
+ return efx_mcdi_rpc(efx, MC_CMD_SET_MCAST_HASH,
+ inbuf, sizeof(inbuf), NULL, 0, NULL);
}
/**************************************************************************
@@ -605,6 +671,228 @@ static void siena_init_wol(struct efx_nic *efx)
}
}
+/**************************************************************************
+ *
+ * MCDI
+ *
+ **************************************************************************
+ */
+
+#define MCDI_PDU(efx) \
+ (efx_port_num(efx) ? MC_SMEM_P1_PDU_OFST : MC_SMEM_P0_PDU_OFST)
+#define MCDI_DOORBELL(efx) \
+ (efx_port_num(efx) ? MC_SMEM_P1_DOORBELL_OFST : MC_SMEM_P0_DOORBELL_OFST)
+#define MCDI_STATUS(efx) \
+ (efx_port_num(efx) ? MC_SMEM_P1_STATUS_OFST : MC_SMEM_P0_STATUS_OFST)
+
+static void siena_mcdi_request(struct efx_nic *efx,
+ const efx_dword_t *hdr, size_t hdr_len,
+ const efx_dword_t *sdu, size_t sdu_len)
+{
+ unsigned pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+ unsigned doorbell = FR_CZ_MC_TREG_SMEM + MCDI_DOORBELL(efx);
+ unsigned int i;
+ unsigned int inlen_dw = DIV_ROUND_UP(sdu_len, 4);
+
+ EFX_BUG_ON_PARANOID(hdr_len != 4);
+
+ efx_writed(efx, hdr, pdu);
+
+ for (i = 0; i < inlen_dw; i++)
+ efx_writed(efx, &sdu[i], pdu + hdr_len + 4 * i);
+
+ /* Ensure the request is written out before the doorbell */
+ wmb();
+
+ /* ring the doorbell with a distinctive value */
+ _efx_writed(efx, (__force __le32) 0x45789abc, doorbell);
+}
+
+static bool siena_mcdi_poll_response(struct efx_nic *efx)
+{
+ unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+ efx_dword_t hdr;
+
+ efx_readd(efx, &hdr, pdu);
+
+ /* All 1's indicates that shared memory is in reset (and is
+ * not a valid hdr). Wait for it to come out reset before
+ * completing the command
+ */
+ return EFX_DWORD_FIELD(hdr, EFX_DWORD_0) != 0xffffffff &&
+ EFX_DWORD_FIELD(hdr, MCDI_HEADER_RESPONSE);
+}
+
+static void siena_mcdi_read_response(struct efx_nic *efx, efx_dword_t *outbuf,
+ size_t offset, size_t outlen)
+{
+ unsigned int pdu = FR_CZ_MC_TREG_SMEM + MCDI_PDU(efx);
+ unsigned int outlen_dw = DIV_ROUND_UP(outlen, 4);
+ int i;
+
+ for (i = 0; i < outlen_dw; i++)
+ efx_readd(efx, &outbuf[i], pdu + offset + 4 * i);
+}
+
+static int siena_mcdi_poll_reboot(struct efx_nic *efx)
+{
+ struct siena_nic_data *nic_data = efx->nic_data;
+ unsigned int addr = FR_CZ_MC_TREG_SMEM + MCDI_STATUS(efx);
+ efx_dword_t reg;
+ u32 value;
+
+ efx_readd(efx, &reg, addr);
+ value = EFX_DWORD_FIELD(reg, EFX_DWORD_0);
+
+ if (value == 0)
+ return 0;
+
+ EFX_ZERO_DWORD(reg);
+ efx_writed(efx, &reg, addr);
+
+ /* MAC statistics have been cleared on the NIC; clear the local
+ * copies that we update with efx_update_diff_stat().
+ */
+ nic_data->stats[SIENA_STAT_tx_good_bytes] = 0;
+ nic_data->stats[SIENA_STAT_rx_good_bytes] = 0;
+
+ if (value == MC_STATUS_DWORD_ASSERT)
+ return -EINTR;
+ else
+ return -EIO;
+}
+
+/**************************************************************************
+ *
+ * MTD
+ *
+ **************************************************************************
+ */
+
+#ifdef CONFIG_SFC_MTD
+
+struct siena_nvram_type_info {
+ int port;
+ const char *name;
+};
+
+static const struct siena_nvram_type_info siena_nvram_types[] = {
+ [MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO] = { 0, "sfc_dummy_phy" },
+ [MC_CMD_NVRAM_TYPE_MC_FW] = { 0, "sfc_mcfw" },
+ [MC_CMD_NVRAM_TYPE_MC_FW_BACKUP] = { 0, "sfc_mcfw_backup" },
+ [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT0] = { 0, "sfc_static_cfg" },
+ [MC_CMD_NVRAM_TYPE_STATIC_CFG_PORT1] = { 1, "sfc_static_cfg" },
+ [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT0] = { 0, "sfc_dynamic_cfg" },
+ [MC_CMD_NVRAM_TYPE_DYNAMIC_CFG_PORT1] = { 1, "sfc_dynamic_cfg" },
+ [MC_CMD_NVRAM_TYPE_EXP_ROM] = { 0, "sfc_exp_rom" },
+ [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT0] = { 0, "sfc_exp_rom_cfg" },
+ [MC_CMD_NVRAM_TYPE_EXP_ROM_CFG_PORT1] = { 1, "sfc_exp_rom_cfg" },
+ [MC_CMD_NVRAM_TYPE_PHY_PORT0] = { 0, "sfc_phy_fw" },
+ [MC_CMD_NVRAM_TYPE_PHY_PORT1] = { 1, "sfc_phy_fw" },
+ [MC_CMD_NVRAM_TYPE_FPGA] = { 0, "sfc_fpga" },
+};
+
+static int siena_mtd_probe_partition(struct efx_nic *efx,
+ struct efx_mcdi_mtd_partition *part,
+ unsigned int type)
+{
+ const struct siena_nvram_type_info *info;
+ size_t size, erase_size;
+ bool protected;
+ int rc;
+
+ if (type >= ARRAY_SIZE(siena_nvram_types) ||
+ siena_nvram_types[type].name == NULL)
+ return -ENODEV;
+
+ info = &siena_nvram_types[type];
+
+ if (info->port != efx_port_num(efx))
+ return -ENODEV;
+
+ rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
+ if (rc)
+ return rc;
+ if (protected)
+ return -ENODEV; /* hide it */
+
+ part->nvram_type = type;
+ part->common.dev_type_name = "Siena NVRAM manager";
+ part->common.type_name = info->name;
+
+ part->common.mtd.type = MTD_NORFLASH;
+ part->common.mtd.flags = MTD_CAP_NORFLASH;
+ part->common.mtd.size = size;
+ part->common.mtd.erasesize = erase_size;
+
+ return 0;
+}
+
+static int siena_mtd_get_fw_subtypes(struct efx_nic *efx,
+ struct efx_mcdi_mtd_partition *parts,
+ size_t n_parts)
+{
+ uint16_t fw_subtype_list[
+ MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM];
+ size_t i;
+ int rc;
+
+ rc = efx_mcdi_get_board_cfg(efx, NULL, fw_subtype_list, NULL);
+ if (rc)
+ return rc;
+
+ for (i = 0; i < n_parts; i++)
+ parts[i].fw_subtype = fw_subtype_list[parts[i].nvram_type];
+
+ return 0;
+}
+
+static int siena_mtd_probe(struct efx_nic *efx)
+{
+ struct efx_mcdi_mtd_partition *parts;
+ u32 nvram_types;
+ unsigned int type;
+ size_t n_parts;
+ int rc;
+
+ ASSERT_RTNL();
+
+ rc = efx_mcdi_nvram_types(efx, &nvram_types);
+ if (rc)
+ return rc;
+
+ parts = kcalloc(hweight32(nvram_types), sizeof(*parts), GFP_KERNEL);
+ if (!parts)
+ return -ENOMEM;
+
+ type = 0;
+ n_parts = 0;
+
+ while (nvram_types != 0) {
+ if (nvram_types & 1) {
+ rc = siena_mtd_probe_partition(efx, &parts[n_parts],
+ type);
+ if (rc == 0)
+ n_parts++;
+ else if (rc != -ENODEV)
+ goto fail;
+ }
+ type++;
+ nvram_types >>= 1;
+ }
+
+ rc = siena_mtd_get_fw_subtypes(efx, parts, n_parts);
+ if (rc)
+ goto fail;
+
+ rc = efx_mtd_add(efx, &parts[0].common, n_parts, sizeof(*parts));
+fail:
+ if (rc)
+ kfree(parts);
+ return rc;
+}
+
+#endif /* CONFIG_SFC_MTD */
/**************************************************************************
*
@@ -614,48 +902,116 @@ static void siena_init_wol(struct efx_nic *efx)
*/
const struct efx_nic_type siena_a0_nic_type = {
+ .mem_map_size = siena_mem_map_size,
.probe = siena_probe_nic,
.remove = siena_remove_nic,
.init = siena_init_nic,
+ .dimension_resources = siena_dimension_resources,
.fini = efx_port_dummy_op_void,
+#ifdef CONFIG_EEH
+ .monitor = siena_monitor,
+#else
.monitor = NULL,
- .map_reset_reason = siena_map_reset_reason,
+#endif
+ .map_reset_reason = efx_mcdi_map_reset_reason,
.map_reset_flags = siena_map_reset_flags,
- .reset = siena_reset_hw,
- .probe_port = siena_probe_port,
- .remove_port = siena_remove_port,
- .prepare_flush = efx_port_dummy_op_void,
+ .reset = efx_mcdi_reset,
+ .probe_port = efx_mcdi_port_probe,
+ .remove_port = efx_mcdi_port_remove,
+ .fini_dmaq = efx_farch_fini_dmaq,
+ .prepare_flush = siena_prepare_flush,
+ .finish_flush = siena_finish_flush,
+ .prepare_flr = efx_port_dummy_op_void,
+ .finish_flr = efx_farch_finish_flr,
+ .describe_stats = siena_describe_nic_stats,
.update_stats = siena_update_nic_stats,
- .start_stats = siena_start_nic_stats,
- .stop_stats = siena_stop_nic_stats,
+ .start_stats = efx_mcdi_mac_start_stats,
+ .pull_stats = efx_mcdi_mac_pull_stats,
+ .stop_stats = efx_mcdi_mac_stop_stats,
.set_id_led = efx_mcdi_set_id_led,
.push_irq_moderation = siena_push_irq_moderation,
- .push_multicast_hash = siena_push_multicast_hash,
- .reconfigure_port = efx_mcdi_phy_reconfigure,
+ .reconfigure_mac = siena_mac_reconfigure,
+ .check_mac_fault = efx_mcdi_mac_check_fault,
+ .reconfigure_port = efx_mcdi_port_reconfigure,
.get_wol = siena_get_wol,
.set_wol = siena_set_wol,
.resume_wol = siena_init_wol,
- .test_registers = siena_test_registers,
+ .test_chip = siena_test_chip,
.test_nvram = efx_mcdi_nvram_test_all,
- .default_mac_ops = &efx_mcdi_mac_operations,
+ .mcdi_request = siena_mcdi_request,
+ .mcdi_poll_response = siena_mcdi_poll_response,
+ .mcdi_read_response = siena_mcdi_read_response,
+ .mcdi_poll_reboot = siena_mcdi_poll_reboot,
+ .irq_enable_master = efx_farch_irq_enable_master,
+ .irq_test_generate = efx_farch_irq_test_generate,
+ .irq_disable_non_ev = efx_farch_irq_disable_master,
+ .irq_handle_msi = efx_farch_msi_interrupt,
+ .irq_handle_legacy = efx_farch_legacy_interrupt,
+ .tx_probe = efx_farch_tx_probe,
+ .tx_init = efx_farch_tx_init,
+ .tx_remove = efx_farch_tx_remove,
+ .tx_write = efx_farch_tx_write,
+ .rx_push_rss_config = siena_rx_push_rss_config,
+ .rx_probe = efx_farch_rx_probe,
+ .rx_init = efx_farch_rx_init,
+ .rx_remove = efx_farch_rx_remove,
+ .rx_write = efx_farch_rx_write,
+ .rx_defer_refill = efx_farch_rx_defer_refill,
+ .ev_probe = efx_farch_ev_probe,
+ .ev_init = efx_farch_ev_init,
+ .ev_fini = efx_farch_ev_fini,
+ .ev_remove = efx_farch_ev_remove,
+ .ev_process = efx_farch_ev_process,
+ .ev_read_ack = efx_farch_ev_read_ack,
+ .ev_test_generate = efx_farch_ev_test_generate,
+ .filter_table_probe = efx_farch_filter_table_probe,
+ .filter_table_restore = efx_farch_filter_table_restore,
+ .filter_table_remove = efx_farch_filter_table_remove,
+ .filter_update_rx_scatter = efx_farch_filter_update_rx_scatter,
+ .filter_insert = efx_farch_filter_insert,
+ .filter_remove_safe = efx_farch_filter_remove_safe,
+ .filter_get_safe = efx_farch_filter_get_safe,
+ .filter_clear_rx = efx_farch_filter_clear_rx,
+ .filter_count_rx_used = efx_farch_filter_count_rx_used,
+ .filter_get_rx_id_limit = efx_farch_filter_get_rx_id_limit,
+ .filter_get_rx_ids = efx_farch_filter_get_rx_ids,
+#ifdef CONFIG_RFS_ACCEL
+ .filter_rfs_insert = efx_farch_filter_rfs_insert,
+ .filter_rfs_expire_one = efx_farch_filter_rfs_expire_one,
+#endif
+#ifdef CONFIG_SFC_MTD
+ .mtd_probe = siena_mtd_probe,
+ .mtd_rename = efx_mcdi_mtd_rename,
+ .mtd_read = efx_mcdi_mtd_read,
+ .mtd_erase = efx_mcdi_mtd_erase,
+ .mtd_write = efx_mcdi_mtd_write,
+ .mtd_sync = efx_mcdi_mtd_sync,
+#endif
+ .ptp_write_host_time = siena_ptp_write_host_time,
+ .ptp_set_ts_config = siena_ptp_set_ts_config,
.revision = EFX_REV_SIENA_A0,
- .mem_map_size = (FR_CZ_MC_TREG_SMEM +
- FR_CZ_MC_TREG_SMEM_STEP * FR_CZ_MC_TREG_SMEM_ROWS),
.txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL,
.rxd_ptr_tbl_base = FR_BZ_RX_DESC_PTR_TBL,
.buf_tbl_base = FR_BZ_BUF_FULL_TBL,
.evq_ptr_tbl_base = FR_BZ_EVQ_PTR_TBL,
.evq_rptr_tbl_base = FR_BZ_EVQ_RPTR,
.max_dma_mask = DMA_BIT_MASK(FSF_AZ_TX_KER_BUF_ADDR_WIDTH),
- .rx_buffer_hash_size = 0x10,
+ .rx_prefix_size = FS_BZ_RX_PREFIX_SIZE,
+ .rx_hash_offset = FS_BZ_RX_PREFIX_HASH_OFST,
.rx_buffer_padding = 0,
+ .can_rx_scatter = true,
.max_interrupt_mode = EFX_INT_MODE_MSIX,
- .phys_addr_channels = 32, /* Hardware limit is 64, but the legacy
- * interrupt handler only supports 32
- * channels */
- .tx_dc_base = 0x88000,
- .rx_dc_base = 0x68000,
+ .timer_period_max = 1 << FRF_CZ_TC_TIMER_VAL_WIDTH,
.offload_features = (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
NETIF_F_RXHASH | NETIF_F_NTUPLE),
+ .mcdi_max_ver = 1,
+ .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS,
+ .hwtstamp_filters = (1 << HWTSTAMP_FILTER_NONE |
+ 1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT |
+ 1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC |
+ 1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ |
+ 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT |
+ 1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC |
+ 1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ),
};
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
new file mode 100644
index 00000000000..43d2e64546e
--- /dev/null
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -0,0 +1,1645 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2010-2012 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#include <linux/pci.h>
+#include <linux/module.h>
+#include "net_driver.h"
+#include "efx.h"
+#include "nic.h"
+#include "io.h"
+#include "mcdi.h"
+#include "filter.h"
+#include "mcdi_pcol.h"
+#include "farch_regs.h"
+#include "vfdi.h"
+
+/* Number of longs required to track all the VIs in a VF */
+#define VI_MASK_LENGTH BITS_TO_LONGS(1 << EFX_VI_SCALE_MAX)
+
+/* Maximum number of RX queues supported */
+#define VF_MAX_RX_QUEUES 63
+
+/**
+ * enum efx_vf_tx_filter_mode - TX MAC filtering behaviour
+ * @VF_TX_FILTER_OFF: Disabled
+ * @VF_TX_FILTER_AUTO: Enabled if MAC address assigned to VF and only
+ * 2 TX queues allowed per VF.
+ * @VF_TX_FILTER_ON: Enabled
+ */
+enum efx_vf_tx_filter_mode {
+ VF_TX_FILTER_OFF,
+ VF_TX_FILTER_AUTO,
+ VF_TX_FILTER_ON,
+};
+
+/**
+ * struct efx_vf - Back-end resource and protocol state for a PCI VF
+ * @efx: The Efx NIC owning this VF
+ * @pci_rid: The PCI requester ID for this VF
+ * @pci_name: The PCI name (formatted address) of this VF
+ * @index: Index of VF within its port and PF.
+ * @req: VFDI incoming request work item. Incoming USR_EV events are received
+ * by the NAPI handler, but must be handled by executing MCDI requests
+ * inside a work item.
+ * @req_addr: VFDI incoming request DMA address (in VF's PCI address space).
+ * @req_type: Expected next incoming (from VF) %VFDI_EV_TYPE member.
+ * @req_seqno: Expected next incoming (from VF) %VFDI_EV_SEQ member.
+ * @msg_seqno: Next %VFDI_EV_SEQ member to reply to VF. Protected by
+ * @status_lock
+ * @busy: VFDI request queued to be processed or being processed. Receiving
+ * a VFDI request when @busy is set is an error condition.
+ * @buf: Incoming VFDI requests are DMA from the VF into this buffer.
+ * @buftbl_base: Buffer table entries for this VF start at this index.
+ * @rx_filtering: Receive filtering has been requested by the VF driver.
+ * @rx_filter_flags: The flags sent in the %VFDI_OP_INSERT_FILTER request.
+ * @rx_filter_qid: VF relative qid for RX filter requested by VF.
+ * @rx_filter_id: Receive MAC filter ID. Only one filter per VF is supported.
+ * @tx_filter_mode: Transmit MAC filtering mode.
+ * @tx_filter_id: Transmit MAC filter ID.
+ * @addr: The MAC address and outer vlan tag of the VF.
+ * @status_addr: VF DMA address of page for &struct vfdi_status updates.
+ * @status_lock: Mutex protecting @msg_seqno, @status_addr, @addr,
+ * @peer_page_addrs and @peer_page_count from simultaneous
+ * updates by the VM and consumption by
+ * efx_sriov_update_vf_addr()
+ * @peer_page_addrs: Pointer to an array of guest pages for local addresses.
+ * @peer_page_count: Number of entries in @peer_page_count.
+ * @evq0_addrs: Array of guest pages backing evq0.
+ * @evq0_count: Number of entries in @evq0_addrs.
+ * @flush_waitq: wait queue used by %VFDI_OP_FINI_ALL_QUEUES handler
+ * to wait for flush completions.
+ * @txq_lock: Mutex for TX queue allocation.
+ * @txq_mask: Mask of initialized transmit queues.
+ * @txq_count: Number of initialized transmit queues.
+ * @rxq_mask: Mask of initialized receive queues.
+ * @rxq_count: Number of initialized receive queues.
+ * @rxq_retry_mask: Mask or receive queues that need to be flushed again
+ * due to flush failure.
+ * @rxq_retry_count: Number of receive queues in @rxq_retry_mask.
+ * @reset_work: Work item to schedule a VF reset.
+ */
+struct efx_vf {
+ struct efx_nic *efx;
+ unsigned int pci_rid;
+ char pci_name[13]; /* dddd:bb:dd.f */
+ unsigned int index;
+ struct work_struct req;
+ u64 req_addr;
+ int req_type;
+ unsigned req_seqno;
+ unsigned msg_seqno;
+ bool busy;
+ struct efx_buffer buf;
+ unsigned buftbl_base;
+ bool rx_filtering;
+ enum efx_filter_flags rx_filter_flags;
+ unsigned rx_filter_qid;
+ int rx_filter_id;
+ enum efx_vf_tx_filter_mode tx_filter_mode;
+ int tx_filter_id;
+ struct vfdi_endpoint addr;
+ u64 status_addr;
+ struct mutex status_lock;
+ u64 *peer_page_addrs;
+ unsigned peer_page_count;
+ u64 evq0_addrs[EFX_MAX_VF_EVQ_SIZE * sizeof(efx_qword_t) /
+ EFX_BUF_SIZE];
+ unsigned evq0_count;
+ wait_queue_head_t flush_waitq;
+ struct mutex txq_lock;
+ unsigned long txq_mask[VI_MASK_LENGTH];
+ unsigned txq_count;
+ unsigned long rxq_mask[VI_MASK_LENGTH];
+ unsigned rxq_count;
+ unsigned long rxq_retry_mask[VI_MASK_LENGTH];
+ atomic_t rxq_retry_count;
+ struct work_struct reset_work;
+};
+
+struct efx_memcpy_req {
+ unsigned int from_rid;
+ void *from_buf;
+ u64 from_addr;
+ unsigned int to_rid;
+ u64 to_addr;
+ unsigned length;
+};
+
+/**
+ * struct efx_local_addr - A MAC address on the vswitch without a VF.
+ *
+ * Siena does not have a switch, so VFs can't transmit data to each
+ * other. Instead the VFs must be made aware of the local addresses
+ * on the vswitch, so that they can arrange for an alternative
+ * software datapath to be used.
+ *
+ * @link: List head for insertion into efx->local_addr_list.
+ * @addr: Ethernet address
+ */
+struct efx_local_addr {
+ struct list_head link;
+ u8 addr[ETH_ALEN];
+};
+
+/**
+ * struct efx_endpoint_page - Page of vfdi_endpoint structures
+ *
+ * @link: List head for insertion into efx->local_page_list.
+ * @ptr: Pointer to page.
+ * @addr: DMA address of page.
+ */
+struct efx_endpoint_page {
+ struct list_head link;
+ void *ptr;
+ dma_addr_t addr;
+};
+
+/* Buffer table entries are reserved txq0,rxq0,evq0,txq1,rxq1,evq1 */
+#define EFX_BUFTBL_TXQ_BASE(_vf, _qid) \
+ ((_vf)->buftbl_base + EFX_VF_BUFTBL_PER_VI * (_qid))
+#define EFX_BUFTBL_RXQ_BASE(_vf, _qid) \
+ (EFX_BUFTBL_TXQ_BASE(_vf, _qid) + \
+ (EFX_MAX_DMAQ_SIZE * sizeof(efx_qword_t) / EFX_BUF_SIZE))
+#define EFX_BUFTBL_EVQ_BASE(_vf, _qid) \
+ (EFX_BUFTBL_TXQ_BASE(_vf, _qid) + \
+ (2 * EFX_MAX_DMAQ_SIZE * sizeof(efx_qword_t) / EFX_BUF_SIZE))
+
+#define EFX_FIELD_MASK(_field) \
+ ((1 << _field ## _WIDTH) - 1)
+
+/* VFs can only use this many transmit channels */
+static unsigned int vf_max_tx_channels = 2;
+module_param(vf_max_tx_channels, uint, 0444);
+MODULE_PARM_DESC(vf_max_tx_channels,
+ "Limit the number of TX channels VFs can use");
+
+static int max_vfs = -1;
+module_param(max_vfs, int, 0444);
+MODULE_PARM_DESC(max_vfs,
+ "Reduce the number of VFs initialized by the driver");
+
+/* Workqueue used by VFDI communication. We can't use the global
+ * workqueue because it may be running the VF driver's probe()
+ * routine, which will be blocked there waiting for a VFDI response.
+ */
+static struct workqueue_struct *vfdi_workqueue;
+
+static unsigned abs_index(struct efx_vf *vf, unsigned index)
+{
+ return EFX_VI_BASE + vf->index * efx_vf_size(vf->efx) + index;
+}
+
+static int efx_sriov_cmd(struct efx_nic *efx, bool enable,
+ unsigned *vi_scale_out, unsigned *vf_total_out)
+{
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_SRIOV_IN_LEN);
+ MCDI_DECLARE_BUF(outbuf, MC_CMD_SRIOV_OUT_LEN);
+ unsigned vi_scale, vf_total;
+ size_t outlen;
+ int rc;
+
+ MCDI_SET_DWORD(inbuf, SRIOV_IN_ENABLE, enable ? 1 : 0);
+ MCDI_SET_DWORD(inbuf, SRIOV_IN_VI_BASE, EFX_VI_BASE);
+ MCDI_SET_DWORD(inbuf, SRIOV_IN_VF_COUNT, efx->vf_count);
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_SRIOV, inbuf, MC_CMD_SRIOV_IN_LEN,
+ outbuf, MC_CMD_SRIOV_OUT_LEN, &outlen);
+ if (rc)
+ return rc;
+ if (outlen < MC_CMD_SRIOV_OUT_LEN)
+ return -EIO;
+
+ vf_total = MCDI_DWORD(outbuf, SRIOV_OUT_VF_TOTAL);
+ vi_scale = MCDI_DWORD(outbuf, SRIOV_OUT_VI_SCALE);
+ if (vi_scale > EFX_VI_SCALE_MAX)
+ return -EOPNOTSUPP;
+
+ if (vi_scale_out)
+ *vi_scale_out = vi_scale;
+ if (vf_total_out)
+ *vf_total_out = vf_total;
+
+ return 0;
+}
+
+static void efx_sriov_usrev(struct efx_nic *efx, bool enabled)
+{
+ efx_oword_t reg;
+
+ EFX_POPULATE_OWORD_2(reg,
+ FRF_CZ_USREV_DIS, enabled ? 0 : 1,
+ FRF_CZ_DFLT_EVQ, efx->vfdi_channel->channel);
+ efx_writeo(efx, &reg, FR_CZ_USR_EV_CFG);
+}
+
+static int efx_sriov_memcpy(struct efx_nic *efx, struct efx_memcpy_req *req,
+ unsigned int count)
+{
+ MCDI_DECLARE_BUF(inbuf, MCDI_CTL_SDU_LEN_MAX_V1);
+ MCDI_DECLARE_STRUCT_PTR(record);
+ unsigned int index, used;
+ u64 from_addr;
+ u32 from_rid;
+ int rc;
+
+ mb(); /* Finish writing source/reading dest before DMA starts */
+
+ if (WARN_ON(count > MC_CMD_MEMCPY_IN_RECORD_MAXNUM))
+ return -ENOBUFS;
+ used = MC_CMD_MEMCPY_IN_LEN(count);
+
+ for (index = 0; index < count; index++) {
+ record = MCDI_ARRAY_STRUCT_PTR(inbuf, MEMCPY_IN_RECORD, index);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_NUM_RECORDS,
+ count);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_TO_RID,
+ req->to_rid);
+ MCDI_SET_QWORD(record, MEMCPY_RECORD_TYPEDEF_TO_ADDR,
+ req->to_addr);
+ if (req->from_buf == NULL) {
+ from_rid = req->from_rid;
+ from_addr = req->from_addr;
+ } else {
+ if (WARN_ON(used + req->length >
+ MCDI_CTL_SDU_LEN_MAX_V1)) {
+ rc = -ENOBUFS;
+ goto out;
+ }
+
+ from_rid = MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE;
+ from_addr = used;
+ memcpy(_MCDI_PTR(inbuf, used), req->from_buf,
+ req->length);
+ used += req->length;
+ }
+
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_RID, from_rid);
+ MCDI_SET_QWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_ADDR,
+ from_addr);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_LENGTH,
+ req->length);
+
+ ++req;
+ }
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_MEMCPY, inbuf, used, NULL, 0, NULL);
+out:
+ mb(); /* Don't write source/read dest before DMA is complete */
+
+ return rc;
+}
+
+/* The TX filter is entirely controlled by this driver, and is modified
+ * underneath the feet of the VF
+ */
+static void efx_sriov_reset_tx_filter(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct efx_filter_spec filter;
+ u16 vlan;
+ int rc;
+
+ if (vf->tx_filter_id != -1) {
+ efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+ vf->tx_filter_id);
+ netif_dbg(efx, hw, efx->net_dev, "Removed vf %s tx filter %d\n",
+ vf->pci_name, vf->tx_filter_id);
+ vf->tx_filter_id = -1;
+ }
+
+ if (is_zero_ether_addr(vf->addr.mac_addr))
+ return;
+
+ /* Turn on TX filtering automatically if not explicitly
+ * enabled or disabled.
+ */
+ if (vf->tx_filter_mode == VF_TX_FILTER_AUTO && vf_max_tx_channels <= 2)
+ vf->tx_filter_mode = VF_TX_FILTER_ON;
+
+ vlan = ntohs(vf->addr.tci) & VLAN_VID_MASK;
+ efx_filter_init_tx(&filter, abs_index(vf, 0));
+ rc = efx_filter_set_eth_local(&filter,
+ vlan ? vlan : EFX_FILTER_VID_UNSPEC,
+ vf->addr.mac_addr);
+ BUG_ON(rc);
+
+ rc = efx_filter_insert_filter(efx, &filter, true);
+ if (rc < 0) {
+ netif_warn(efx, hw, efx->net_dev,
+ "Unable to migrate tx filter for vf %s\n",
+ vf->pci_name);
+ } else {
+ netif_dbg(efx, hw, efx->net_dev, "Inserted vf %s tx filter %d\n",
+ vf->pci_name, rc);
+ vf->tx_filter_id = rc;
+ }
+}
+
+/* The RX filter is managed here on behalf of the VF driver */
+static void efx_sriov_reset_rx_filter(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct efx_filter_spec filter;
+ u16 vlan;
+ int rc;
+
+ if (vf->rx_filter_id != -1) {
+ efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED,
+ vf->rx_filter_id);
+ netif_dbg(efx, hw, efx->net_dev, "Removed vf %s rx filter %d\n",
+ vf->pci_name, vf->rx_filter_id);
+ vf->rx_filter_id = -1;
+ }
+
+ if (!vf->rx_filtering || is_zero_ether_addr(vf->addr.mac_addr))
+ return;
+
+ vlan = ntohs(vf->addr.tci) & VLAN_VID_MASK;
+ efx_filter_init_rx(&filter, EFX_FILTER_PRI_REQUIRED,
+ vf->rx_filter_flags,
+ abs_index(vf, vf->rx_filter_qid));
+ rc = efx_filter_set_eth_local(&filter,
+ vlan ? vlan : EFX_FILTER_VID_UNSPEC,
+ vf->addr.mac_addr);
+ BUG_ON(rc);
+
+ rc = efx_filter_insert_filter(efx, &filter, true);
+ if (rc < 0) {
+ netif_warn(efx, hw, efx->net_dev,
+ "Unable to insert rx filter for vf %s\n",
+ vf->pci_name);
+ } else {
+ netif_dbg(efx, hw, efx->net_dev, "Inserted vf %s rx filter %d\n",
+ vf->pci_name, rc);
+ vf->rx_filter_id = rc;
+ }
+}
+
+static void __efx_sriov_update_vf_addr(struct efx_vf *vf)
+{
+ efx_sriov_reset_tx_filter(vf);
+ efx_sriov_reset_rx_filter(vf);
+ queue_work(vfdi_workqueue, &vf->efx->peer_work);
+}
+
+/* Push the peer list to this VF. The caller must hold status_lock to interlock
+ * with VFDI requests, and they must be serialised against manipulation of
+ * local_page_list, either by acquiring local_lock or by running from
+ * efx_sriov_peer_work()
+ */
+static void __efx_sriov_push_vf_status(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_status *status = efx->vfdi_status.addr;
+ struct efx_memcpy_req copy[4];
+ struct efx_endpoint_page *epp;
+ unsigned int pos, count;
+ unsigned data_offset;
+ efx_qword_t event;
+
+ WARN_ON(!mutex_is_locked(&vf->status_lock));
+ WARN_ON(!vf->status_addr);
+
+ status->local = vf->addr;
+ status->generation_end = ++status->generation_start;
+
+ memset(copy, '\0', sizeof(copy));
+ /* Write generation_start */
+ copy[0].from_buf = &status->generation_start;
+ copy[0].to_rid = vf->pci_rid;
+ copy[0].to_addr = vf->status_addr + offsetof(struct vfdi_status,
+ generation_start);
+ copy[0].length = sizeof(status->generation_start);
+ /* DMA the rest of the structure (excluding the generations). This
+ * assumes that the non-generation portion of vfdi_status is in
+ * one chunk starting at the version member.
+ */
+ data_offset = offsetof(struct vfdi_status, version);
+ copy[1].from_rid = efx->pci_dev->devfn;
+ copy[1].from_addr = efx->vfdi_status.dma_addr + data_offset;
+ copy[1].to_rid = vf->pci_rid;
+ copy[1].to_addr = vf->status_addr + data_offset;
+ copy[1].length = status->length - data_offset;
+
+ /* Copy the peer pages */
+ pos = 2;
+ count = 0;
+ list_for_each_entry(epp, &efx->local_page_list, link) {
+ if (count == vf->peer_page_count) {
+ /* The VF driver will know they need to provide more
+ * pages because peer_addr_count is too large.
+ */
+ break;
+ }
+ copy[pos].from_buf = NULL;
+ copy[pos].from_rid = efx->pci_dev->devfn;
+ copy[pos].from_addr = epp->addr;
+ copy[pos].to_rid = vf->pci_rid;
+ copy[pos].to_addr = vf->peer_page_addrs[count];
+ copy[pos].length = EFX_PAGE_SIZE;
+
+ if (++pos == ARRAY_SIZE(copy)) {
+ efx_sriov_memcpy(efx, copy, ARRAY_SIZE(copy));
+ pos = 0;
+ }
+ ++count;
+ }
+
+ /* Write generation_end */
+ copy[pos].from_buf = &status->generation_end;
+ copy[pos].to_rid = vf->pci_rid;
+ copy[pos].to_addr = vf->status_addr + offsetof(struct vfdi_status,
+ generation_end);
+ copy[pos].length = sizeof(status->generation_end);
+ efx_sriov_memcpy(efx, copy, pos + 1);
+
+ /* Notify the guest */
+ EFX_POPULATE_QWORD_3(event,
+ FSF_AZ_EV_CODE, FSE_CZ_EV_CODE_USER_EV,
+ VFDI_EV_SEQ, (vf->msg_seqno & 0xff),
+ VFDI_EV_TYPE, VFDI_EV_TYPE_STATUS);
+ ++vf->msg_seqno;
+ efx_farch_generate_event(efx,
+ EFX_VI_BASE + vf->index * efx_vf_size(efx),
+ &event);
+}
+
+static void efx_sriov_bufs(struct efx_nic *efx, unsigned offset,
+ u64 *addr, unsigned count)
+{
+ efx_qword_t buf;
+ unsigned pos;
+
+ for (pos = 0; pos < count; ++pos) {
+ EFX_POPULATE_QWORD_3(buf,
+ FRF_AZ_BUF_ADR_REGION, 0,
+ FRF_AZ_BUF_ADR_FBUF,
+ addr ? addr[pos] >> 12 : 0,
+ FRF_AZ_BUF_OWNER_ID_FBUF, 0);
+ efx_sram_writeq(efx, efx->membase + FR_BZ_BUF_FULL_TBL,
+ &buf, offset + pos);
+ }
+}
+
+static bool bad_vf_index(struct efx_nic *efx, unsigned index)
+{
+ return index >= efx_vf_size(efx);
+}
+
+static bool bad_buf_count(unsigned buf_count, unsigned max_entry_count)
+{
+ unsigned max_buf_count = max_entry_count *
+ sizeof(efx_qword_t) / EFX_BUF_SIZE;
+
+ return ((buf_count & (buf_count - 1)) || buf_count > max_buf_count);
+}
+
+/* Check that VI specified by per-port index belongs to a VF.
+ * Optionally set VF index and VI index within the VF.
+ */
+static bool map_vi_index(struct efx_nic *efx, unsigned abs_index,
+ struct efx_vf **vf_out, unsigned *rel_index_out)
+{
+ unsigned vf_i;
+
+ if (abs_index < EFX_VI_BASE)
+ return true;
+ vf_i = (abs_index - EFX_VI_BASE) / efx_vf_size(efx);
+ if (vf_i >= efx->vf_init_count)
+ return true;
+
+ if (vf_out)
+ *vf_out = efx->vf + vf_i;
+ if (rel_index_out)
+ *rel_index_out = abs_index % efx_vf_size(efx);
+ return false;
+}
+
+static int efx_vfdi_init_evq(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ unsigned vf_evq = req->u.init_evq.index;
+ unsigned buf_count = req->u.init_evq.buf_count;
+ unsigned abs_evq = abs_index(vf, vf_evq);
+ unsigned buftbl = EFX_BUFTBL_EVQ_BASE(vf, vf_evq);
+ efx_oword_t reg;
+
+ if (bad_vf_index(efx, vf_evq) ||
+ bad_buf_count(buf_count, EFX_MAX_VF_EVQ_SIZE)) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Invalid INIT_EVQ from %s: evq %d bufs %d\n",
+ vf->pci_name, vf_evq, buf_count);
+ return VFDI_RC_EINVAL;
+ }
+
+ efx_sriov_bufs(efx, buftbl, req->u.init_evq.addr, buf_count);
+
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_CZ_TIMER_Q_EN, 1,
+ FRF_CZ_HOST_NOTIFY_MODE, 0,
+ FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
+ efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, abs_evq);
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_AZ_EVQ_EN, 1,
+ FRF_AZ_EVQ_SIZE, __ffs(buf_count),
+ FRF_AZ_EVQ_BUF_BASE_ID, buftbl);
+ efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL, abs_evq);
+
+ if (vf_evq == 0) {
+ memcpy(vf->evq0_addrs, req->u.init_evq.addr,
+ buf_count * sizeof(u64));
+ vf->evq0_count = buf_count;
+ }
+
+ return VFDI_RC_SUCCESS;
+}
+
+static int efx_vfdi_init_rxq(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ unsigned vf_rxq = req->u.init_rxq.index;
+ unsigned vf_evq = req->u.init_rxq.evq;
+ unsigned buf_count = req->u.init_rxq.buf_count;
+ unsigned buftbl = EFX_BUFTBL_RXQ_BASE(vf, vf_rxq);
+ unsigned label;
+ efx_oword_t reg;
+
+ if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_rxq) ||
+ vf_rxq >= VF_MAX_RX_QUEUES ||
+ bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Invalid INIT_RXQ from %s: rxq %d evq %d "
+ "buf_count %d\n", vf->pci_name, vf_rxq,
+ vf_evq, buf_count);
+ return VFDI_RC_EINVAL;
+ }
+ if (__test_and_set_bit(req->u.init_rxq.index, vf->rxq_mask))
+ ++vf->rxq_count;
+ efx_sriov_bufs(efx, buftbl, req->u.init_rxq.addr, buf_count);
+
+ label = req->u.init_rxq.label & EFX_FIELD_MASK(FRF_AZ_RX_DESCQ_LABEL);
+ EFX_POPULATE_OWORD_6(reg,
+ FRF_AZ_RX_DESCQ_BUF_BASE_ID, buftbl,
+ FRF_AZ_RX_DESCQ_EVQ_ID, abs_index(vf, vf_evq),
+ FRF_AZ_RX_DESCQ_LABEL, label,
+ FRF_AZ_RX_DESCQ_SIZE, __ffs(buf_count),
+ FRF_AZ_RX_DESCQ_JUMBO,
+ !!(req->u.init_rxq.flags &
+ VFDI_RXQ_FLAG_SCATTER_EN),
+ FRF_AZ_RX_DESCQ_EN, 1);
+ efx_writeo_table(efx, &reg, FR_BZ_RX_DESC_PTR_TBL,
+ abs_index(vf, vf_rxq));
+
+ return VFDI_RC_SUCCESS;
+}
+
+static int efx_vfdi_init_txq(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ unsigned vf_txq = req->u.init_txq.index;
+ unsigned vf_evq = req->u.init_txq.evq;
+ unsigned buf_count = req->u.init_txq.buf_count;
+ unsigned buftbl = EFX_BUFTBL_TXQ_BASE(vf, vf_txq);
+ unsigned label, eth_filt_en;
+ efx_oword_t reg;
+
+ if (bad_vf_index(efx, vf_evq) || bad_vf_index(efx, vf_txq) ||
+ vf_txq >= vf_max_tx_channels ||
+ bad_buf_count(buf_count, EFX_MAX_DMAQ_SIZE)) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Invalid INIT_TXQ from %s: txq %d evq %d "
+ "buf_count %d\n", vf->pci_name, vf_txq,
+ vf_evq, buf_count);
+ return VFDI_RC_EINVAL;
+ }
+
+ mutex_lock(&vf->txq_lock);
+ if (__test_and_set_bit(req->u.init_txq.index, vf->txq_mask))
+ ++vf->txq_count;
+ mutex_unlock(&vf->txq_lock);
+ efx_sriov_bufs(efx, buftbl, req->u.init_txq.addr, buf_count);
+
+ eth_filt_en = vf->tx_filter_mode == VF_TX_FILTER_ON;
+
+ label = req->u.init_txq.label & EFX_FIELD_MASK(FRF_AZ_TX_DESCQ_LABEL);
+ EFX_POPULATE_OWORD_8(reg,
+ FRF_CZ_TX_DPT_Q_MASK_WIDTH, min(efx->vi_scale, 1U),
+ FRF_CZ_TX_DPT_ETH_FILT_EN, eth_filt_en,
+ FRF_AZ_TX_DESCQ_EN, 1,
+ FRF_AZ_TX_DESCQ_BUF_BASE_ID, buftbl,
+ FRF_AZ_TX_DESCQ_EVQ_ID, abs_index(vf, vf_evq),
+ FRF_AZ_TX_DESCQ_LABEL, label,
+ FRF_AZ_TX_DESCQ_SIZE, __ffs(buf_count),
+ FRF_BZ_TX_NON_IP_DROP_DIS, 1);
+ efx_writeo_table(efx, &reg, FR_BZ_TX_DESC_PTR_TBL,
+ abs_index(vf, vf_txq));
+
+ return VFDI_RC_SUCCESS;
+}
+
+/* Returns true when efx_vfdi_fini_all_queues should wake */
+static bool efx_vfdi_flush_wake(struct efx_vf *vf)
+{
+ /* Ensure that all updates are visible to efx_vfdi_fini_all_queues() */
+ smp_mb();
+
+ return (!vf->txq_count && !vf->rxq_count) ||
+ atomic_read(&vf->rxq_retry_count);
+}
+
+static void efx_vfdi_flush_clear(struct efx_vf *vf)
+{
+ memset(vf->txq_mask, 0, sizeof(vf->txq_mask));
+ vf->txq_count = 0;
+ memset(vf->rxq_mask, 0, sizeof(vf->rxq_mask));
+ vf->rxq_count = 0;
+ memset(vf->rxq_retry_mask, 0, sizeof(vf->rxq_retry_mask));
+ atomic_set(&vf->rxq_retry_count, 0);
+}
+
+static int efx_vfdi_fini_all_queues(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ efx_oword_t reg;
+ unsigned count = efx_vf_size(efx);
+ unsigned vf_offset = EFX_VI_BASE + vf->index * efx_vf_size(efx);
+ unsigned timeout = HZ;
+ unsigned index, rxqs_count;
+ MCDI_DECLARE_BUF(inbuf, MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX);
+ int rc;
+
+ BUILD_BUG_ON(VF_MAX_RX_QUEUES >
+ MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM);
+
+ rtnl_lock();
+ siena_prepare_flush(efx);
+ rtnl_unlock();
+
+ /* Flush all the initialized queues */
+ rxqs_count = 0;
+ for (index = 0; index < count; ++index) {
+ if (test_bit(index, vf->txq_mask)) {
+ EFX_POPULATE_OWORD_2(reg,
+ FRF_AZ_TX_FLUSH_DESCQ_CMD, 1,
+ FRF_AZ_TX_FLUSH_DESCQ,
+ vf_offset + index);
+ efx_writeo(efx, &reg, FR_AZ_TX_FLUSH_DESCQ);
+ }
+ if (test_bit(index, vf->rxq_mask)) {
+ MCDI_SET_ARRAY_DWORD(
+ inbuf, FLUSH_RX_QUEUES_IN_QID_OFST,
+ rxqs_count, vf_offset + index);
+ rxqs_count++;
+ }
+ }
+
+ atomic_set(&vf->rxq_retry_count, 0);
+ while (timeout && (vf->rxq_count || vf->txq_count)) {
+ rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, inbuf,
+ MC_CMD_FLUSH_RX_QUEUES_IN_LEN(rxqs_count),
+ NULL, 0, NULL);
+ WARN_ON(rc < 0);
+
+ timeout = wait_event_timeout(vf->flush_waitq,
+ efx_vfdi_flush_wake(vf),
+ timeout);
+ rxqs_count = 0;
+ for (index = 0; index < count; ++index) {
+ if (test_and_clear_bit(index, vf->rxq_retry_mask)) {
+ atomic_dec(&vf->rxq_retry_count);
+ MCDI_SET_ARRAY_DWORD(
+ inbuf, FLUSH_RX_QUEUES_IN_QID_OFST,
+ rxqs_count, vf_offset + index);
+ rxqs_count++;
+ }
+ }
+ }
+
+ rtnl_lock();
+ siena_finish_flush(efx);
+ rtnl_unlock();
+
+ /* Irrespective of success/failure, fini the queues */
+ EFX_ZERO_OWORD(reg);
+ for (index = 0; index < count; ++index) {
+ efx_writeo_table(efx, &reg, FR_BZ_RX_DESC_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, &reg, FR_BZ_TX_DESC_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL,
+ vf_offset + index);
+ }
+ efx_sriov_bufs(efx, vf->buftbl_base, NULL,
+ EFX_VF_BUFTBL_PER_VI * efx_vf_size(efx));
+ efx_vfdi_flush_clear(vf);
+
+ vf->evq0_count = 0;
+
+ return timeout ? 0 : VFDI_RC_ETIMEDOUT;
+}
+
+static int efx_vfdi_insert_filter(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ unsigned vf_rxq = req->u.mac_filter.rxq;
+ unsigned flags;
+
+ if (bad_vf_index(efx, vf_rxq) || vf->rx_filtering) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Invalid INSERT_FILTER from %s: rxq %d "
+ "flags 0x%x\n", vf->pci_name, vf_rxq,
+ req->u.mac_filter.flags);
+ return VFDI_RC_EINVAL;
+ }
+
+ flags = 0;
+ if (req->u.mac_filter.flags & VFDI_MAC_FILTER_FLAG_RSS)
+ flags |= EFX_FILTER_FLAG_RX_RSS;
+ if (req->u.mac_filter.flags & VFDI_MAC_FILTER_FLAG_SCATTER)
+ flags |= EFX_FILTER_FLAG_RX_SCATTER;
+ vf->rx_filter_flags = flags;
+ vf->rx_filter_qid = vf_rxq;
+ vf->rx_filtering = true;
+
+ efx_sriov_reset_rx_filter(vf);
+ queue_work(vfdi_workqueue, &efx->peer_work);
+
+ return VFDI_RC_SUCCESS;
+}
+
+static int efx_vfdi_remove_all_filters(struct efx_vf *vf)
+{
+ vf->rx_filtering = false;
+ efx_sriov_reset_rx_filter(vf);
+ queue_work(vfdi_workqueue, &vf->efx->peer_work);
+
+ return VFDI_RC_SUCCESS;
+}
+
+static int efx_vfdi_set_status_page(struct efx_vf *vf)
+{
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ u64 page_count = req->u.set_status_page.peer_page_count;
+ u64 max_page_count =
+ (EFX_PAGE_SIZE -
+ offsetof(struct vfdi_req, u.set_status_page.peer_page_addr[0]))
+ / sizeof(req->u.set_status_page.peer_page_addr[0]);
+
+ if (!req->u.set_status_page.dma_addr || page_count > max_page_count) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Invalid SET_STATUS_PAGE from %s\n",
+ vf->pci_name);
+ return VFDI_RC_EINVAL;
+ }
+
+ mutex_lock(&efx->local_lock);
+ mutex_lock(&vf->status_lock);
+ vf->status_addr = req->u.set_status_page.dma_addr;
+
+ kfree(vf->peer_page_addrs);
+ vf->peer_page_addrs = NULL;
+ vf->peer_page_count = 0;
+
+ if (page_count) {
+ vf->peer_page_addrs = kcalloc(page_count, sizeof(u64),
+ GFP_KERNEL);
+ if (vf->peer_page_addrs) {
+ memcpy(vf->peer_page_addrs,
+ req->u.set_status_page.peer_page_addr,
+ page_count * sizeof(u64));
+ vf->peer_page_count = page_count;
+ }
+ }
+
+ __efx_sriov_push_vf_status(vf);
+ mutex_unlock(&vf->status_lock);
+ mutex_unlock(&efx->local_lock);
+
+ return VFDI_RC_SUCCESS;
+}
+
+static int efx_vfdi_clear_status_page(struct efx_vf *vf)
+{
+ mutex_lock(&vf->status_lock);
+ vf->status_addr = 0;
+ mutex_unlock(&vf->status_lock);
+
+ return VFDI_RC_SUCCESS;
+}
+
+typedef int (*efx_vfdi_op_t)(struct efx_vf *vf);
+
+static const efx_vfdi_op_t vfdi_ops[VFDI_OP_LIMIT] = {
+ [VFDI_OP_INIT_EVQ] = efx_vfdi_init_evq,
+ [VFDI_OP_INIT_TXQ] = efx_vfdi_init_txq,
+ [VFDI_OP_INIT_RXQ] = efx_vfdi_init_rxq,
+ [VFDI_OP_FINI_ALL_QUEUES] = efx_vfdi_fini_all_queues,
+ [VFDI_OP_INSERT_FILTER] = efx_vfdi_insert_filter,
+ [VFDI_OP_REMOVE_ALL_FILTERS] = efx_vfdi_remove_all_filters,
+ [VFDI_OP_SET_STATUS_PAGE] = efx_vfdi_set_status_page,
+ [VFDI_OP_CLEAR_STATUS_PAGE] = efx_vfdi_clear_status_page,
+};
+
+static void efx_sriov_vfdi(struct work_struct *work)
+{
+ struct efx_vf *vf = container_of(work, struct efx_vf, req);
+ struct efx_nic *efx = vf->efx;
+ struct vfdi_req *req = vf->buf.addr;
+ struct efx_memcpy_req copy[2];
+ int rc;
+
+ /* Copy this page into the local address space */
+ memset(copy, '\0', sizeof(copy));
+ copy[0].from_rid = vf->pci_rid;
+ copy[0].from_addr = vf->req_addr;
+ copy[0].to_rid = efx->pci_dev->devfn;
+ copy[0].to_addr = vf->buf.dma_addr;
+ copy[0].length = EFX_PAGE_SIZE;
+ rc = efx_sriov_memcpy(efx, copy, 1);
+ if (rc) {
+ /* If we can't get the request, we can't reply to the caller */
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Unable to fetch VFDI request from %s rc %d\n",
+ vf->pci_name, -rc);
+ vf->busy = false;
+ return;
+ }
+
+ if (req->op < VFDI_OP_LIMIT && vfdi_ops[req->op] != NULL) {
+ rc = vfdi_ops[req->op](vf);
+ if (rc == 0) {
+ netif_dbg(efx, hw, efx->net_dev,
+ "vfdi request %d from %s ok\n",
+ req->op, vf->pci_name);
+ }
+ } else {
+ netif_dbg(efx, hw, efx->net_dev,
+ "ERROR: Unrecognised request %d from VF %s addr "
+ "%llx\n", req->op, vf->pci_name,
+ (unsigned long long)vf->req_addr);
+ rc = VFDI_RC_EOPNOTSUPP;
+ }
+
+ /* Allow subsequent VF requests */
+ vf->busy = false;
+ smp_wmb();
+
+ /* Respond to the request */
+ req->rc = rc;
+ req->op = VFDI_OP_RESPONSE;
+
+ memset(copy, '\0', sizeof(copy));
+ copy[0].from_buf = &req->rc;
+ copy[0].to_rid = vf->pci_rid;
+ copy[0].to_addr = vf->req_addr + offsetof(struct vfdi_req, rc);
+ copy[0].length = sizeof(req->rc);
+ copy[1].from_buf = &req->op;
+ copy[1].to_rid = vf->pci_rid;
+ copy[1].to_addr = vf->req_addr + offsetof(struct vfdi_req, op);
+ copy[1].length = sizeof(req->op);
+
+ (void) efx_sriov_memcpy(efx, copy, ARRAY_SIZE(copy));
+}
+
+
+
+/* After a reset the event queues inside the guests no longer exist. Fill the
+ * event ring in guest memory with VFDI reset events, then (re-initialise) the
+ * event queue to raise an interrupt. The guest driver will then recover.
+ */
+static void efx_sriov_reset_vf(struct efx_vf *vf, struct efx_buffer *buffer)
+{
+ struct efx_nic *efx = vf->efx;
+ struct efx_memcpy_req copy_req[4];
+ efx_qword_t event;
+ unsigned int pos, count, k, buftbl, abs_evq;
+ efx_oword_t reg;
+ efx_dword_t ptr;
+ int rc;
+
+ BUG_ON(buffer->len != EFX_PAGE_SIZE);
+
+ if (!vf->evq0_count)
+ return;
+ BUG_ON(vf->evq0_count & (vf->evq0_count - 1));
+
+ mutex_lock(&vf->status_lock);
+ EFX_POPULATE_QWORD_3(event,
+ FSF_AZ_EV_CODE, FSE_CZ_EV_CODE_USER_EV,
+ VFDI_EV_SEQ, vf->msg_seqno,
+ VFDI_EV_TYPE, VFDI_EV_TYPE_RESET);
+ vf->msg_seqno++;
+ for (pos = 0; pos < EFX_PAGE_SIZE; pos += sizeof(event))
+ memcpy(buffer->addr + pos, &event, sizeof(event));
+
+ for (pos = 0; pos < vf->evq0_count; pos += count) {
+ count = min_t(unsigned, vf->evq0_count - pos,
+ ARRAY_SIZE(copy_req));
+ for (k = 0; k < count; k++) {
+ copy_req[k].from_buf = NULL;
+ copy_req[k].from_rid = efx->pci_dev->devfn;
+ copy_req[k].from_addr = buffer->dma_addr;
+ copy_req[k].to_rid = vf->pci_rid;
+ copy_req[k].to_addr = vf->evq0_addrs[pos + k];
+ copy_req[k].length = EFX_PAGE_SIZE;
+ }
+ rc = efx_sriov_memcpy(efx, copy_req, count);
+ if (rc) {
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Unable to notify %s of reset"
+ ": %d\n", vf->pci_name, -rc);
+ break;
+ }
+ }
+
+ /* Reinitialise, arm and trigger evq0 */
+ abs_evq = abs_index(vf, 0);
+ buftbl = EFX_BUFTBL_EVQ_BASE(vf, 0);
+ efx_sriov_bufs(efx, buftbl, vf->evq0_addrs, vf->evq0_count);
+
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_CZ_TIMER_Q_EN, 1,
+ FRF_CZ_HOST_NOTIFY_MODE, 0,
+ FRF_CZ_TIMER_MODE, FFE_CZ_TIMER_MODE_DIS);
+ efx_writeo_table(efx, &reg, FR_BZ_TIMER_TBL, abs_evq);
+ EFX_POPULATE_OWORD_3(reg,
+ FRF_AZ_EVQ_EN, 1,
+ FRF_AZ_EVQ_SIZE, __ffs(vf->evq0_count),
+ FRF_AZ_EVQ_BUF_BASE_ID, buftbl);
+ efx_writeo_table(efx, &reg, FR_BZ_EVQ_PTR_TBL, abs_evq);
+ EFX_POPULATE_DWORD_1(ptr, FRF_AZ_EVQ_RPTR, 0);
+ efx_writed(efx, &ptr, FR_BZ_EVQ_RPTR + FR_BZ_EVQ_RPTR_STEP * abs_evq);
+
+ mutex_unlock(&vf->status_lock);
+}
+
+static void efx_sriov_reset_vf_work(struct work_struct *work)
+{
+ struct efx_vf *vf = container_of(work, struct efx_vf, req);
+ struct efx_nic *efx = vf->efx;
+ struct efx_buffer buf;
+
+ if (!efx_nic_alloc_buffer(efx, &buf, EFX_PAGE_SIZE, GFP_NOIO)) {
+ efx_sriov_reset_vf(vf, &buf);
+ efx_nic_free_buffer(efx, &buf);
+ }
+}
+
+static void efx_sriov_handle_no_channel(struct efx_nic *efx)
+{
+ netif_err(efx, drv, efx->net_dev,
+ "ERROR: IOV requires MSI-X and 1 additional interrupt"
+ "vector. IOV disabled\n");
+ efx->vf_count = 0;
+}
+
+static int efx_sriov_probe_channel(struct efx_channel *channel)
+{
+ channel->efx->vfdi_channel = channel;
+ return 0;
+}
+
+static void
+efx_sriov_get_channel_name(struct efx_channel *channel, char *buf, size_t len)
+{
+ snprintf(buf, len, "%s-iov", channel->efx->name);
+}
+
+static const struct efx_channel_type efx_sriov_channel_type = {
+ .handle_no_channel = efx_sriov_handle_no_channel,
+ .pre_probe = efx_sriov_probe_channel,
+ .post_remove = efx_channel_dummy_op_void,
+ .get_name = efx_sriov_get_channel_name,
+ /* no copy operation; channel must not be reallocated */
+ .keep_eventq = true,
+};
+
+void efx_sriov_probe(struct efx_nic *efx)
+{
+ unsigned count;
+
+ if (!max_vfs)
+ return;
+
+ if (efx_sriov_cmd(efx, false, &efx->vi_scale, &count))
+ return;
+ if (count > 0 && count > max_vfs)
+ count = max_vfs;
+
+ /* efx_nic_dimension_resources() will reduce vf_count as appopriate */
+ efx->vf_count = count;
+
+ efx->extra_channel_type[EFX_EXTRA_CHANNEL_IOV] = &efx_sriov_channel_type;
+}
+
+/* Copy the list of individual addresses into the vfdi_status.peers
+ * array and auxillary pages, protected by %local_lock. Drop that lock
+ * and then broadcast the address list to every VF.
+ */
+static void efx_sriov_peer_work(struct work_struct *data)
+{
+ struct efx_nic *efx = container_of(data, struct efx_nic, peer_work);
+ struct vfdi_status *vfdi_status = efx->vfdi_status.addr;
+ struct efx_vf *vf;
+ struct efx_local_addr *local_addr;
+ struct vfdi_endpoint *peer;
+ struct efx_endpoint_page *epp;
+ struct list_head pages;
+ unsigned int peer_space;
+ unsigned int peer_count;
+ unsigned int pos;
+
+ mutex_lock(&efx->local_lock);
+
+ /* Move the existing peer pages off %local_page_list */
+ INIT_LIST_HEAD(&pages);
+ list_splice_tail_init(&efx->local_page_list, &pages);
+
+ /* Populate the VF addresses starting from entry 1 (entry 0 is
+ * the PF address)
+ */
+ peer = vfdi_status->peers + 1;
+ peer_space = ARRAY_SIZE(vfdi_status->peers) - 1;
+ peer_count = 1;
+ for (pos = 0; pos < efx->vf_count; ++pos) {
+ vf = efx->vf + pos;
+
+ mutex_lock(&vf->status_lock);
+ if (vf->rx_filtering && !is_zero_ether_addr(vf->addr.mac_addr)) {
+ *peer++ = vf->addr;
+ ++peer_count;
+ --peer_space;
+ BUG_ON(peer_space == 0);
+ }
+ mutex_unlock(&vf->status_lock);
+ }
+
+ /* Fill the remaining addresses */
+ list_for_each_entry(local_addr, &efx->local_addr_list, link) {
+ ether_addr_copy(peer->mac_addr, local_addr->addr);
+ peer->tci = 0;
+ ++peer;
+ ++peer_count;
+ if (--peer_space == 0) {
+ if (list_empty(&pages)) {
+ epp = kmalloc(sizeof(*epp), GFP_KERNEL);
+ if (!epp)
+ break;
+ epp->ptr = dma_alloc_coherent(
+ &efx->pci_dev->dev, EFX_PAGE_SIZE,
+ &epp->addr, GFP_KERNEL);
+ if (!epp->ptr) {
+ kfree(epp);
+ break;
+ }
+ } else {
+ epp = list_first_entry(
+ &pages, struct efx_endpoint_page, link);
+ list_del(&epp->link);
+ }
+
+ list_add_tail(&epp->link, &efx->local_page_list);
+ peer = (struct vfdi_endpoint *)epp->ptr;
+ peer_space = EFX_PAGE_SIZE / sizeof(struct vfdi_endpoint);
+ }
+ }
+ vfdi_status->peer_count = peer_count;
+ mutex_unlock(&efx->local_lock);
+
+ /* Free any now unused endpoint pages */
+ while (!list_empty(&pages)) {
+ epp = list_first_entry(
+ &pages, struct efx_endpoint_page, link);
+ list_del(&epp->link);
+ dma_free_coherent(&efx->pci_dev->dev, EFX_PAGE_SIZE,
+ epp->ptr, epp->addr);
+ kfree(epp);
+ }
+
+ /* Finally, push the pages */
+ for (pos = 0; pos < efx->vf_count; ++pos) {
+ vf = efx->vf + pos;
+
+ mutex_lock(&vf->status_lock);
+ if (vf->status_addr)
+ __efx_sriov_push_vf_status(vf);
+ mutex_unlock(&vf->status_lock);
+ }
+}
+
+static void efx_sriov_free_local(struct efx_nic *efx)
+{
+ struct efx_local_addr *local_addr;
+ struct efx_endpoint_page *epp;
+
+ while (!list_empty(&efx->local_addr_list)) {
+ local_addr = list_first_entry(&efx->local_addr_list,
+ struct efx_local_addr, link);
+ list_del(&local_addr->link);
+ kfree(local_addr);
+ }
+
+ while (!list_empty(&efx->local_page_list)) {
+ epp = list_first_entry(&efx->local_page_list,
+ struct efx_endpoint_page, link);
+ list_del(&epp->link);
+ dma_free_coherent(&efx->pci_dev->dev, EFX_PAGE_SIZE,
+ epp->ptr, epp->addr);
+ kfree(epp);
+ }
+}
+
+static int efx_sriov_vf_alloc(struct efx_nic *efx)
+{
+ unsigned index;
+ struct efx_vf *vf;
+
+ efx->vf = kzalloc(sizeof(struct efx_vf) * efx->vf_count, GFP_KERNEL);
+ if (!efx->vf)
+ return -ENOMEM;
+
+ for (index = 0; index < efx->vf_count; ++index) {
+ vf = efx->vf + index;
+
+ vf->efx = efx;
+ vf->index = index;
+ vf->rx_filter_id = -1;
+ vf->tx_filter_mode = VF_TX_FILTER_AUTO;
+ vf->tx_filter_id = -1;
+ INIT_WORK(&vf->req, efx_sriov_vfdi);
+ INIT_WORK(&vf->reset_work, efx_sriov_reset_vf_work);
+ init_waitqueue_head(&vf->flush_waitq);
+ mutex_init(&vf->status_lock);
+ mutex_init(&vf->txq_lock);
+ }
+
+ return 0;
+}
+
+static void efx_sriov_vfs_fini(struct efx_nic *efx)
+{
+ struct efx_vf *vf;
+ unsigned int pos;
+
+ for (pos = 0; pos < efx->vf_count; ++pos) {
+ vf = efx->vf + pos;
+
+ efx_nic_free_buffer(efx, &vf->buf);
+ kfree(vf->peer_page_addrs);
+ vf->peer_page_addrs = NULL;
+ vf->peer_page_count = 0;
+
+ vf->evq0_count = 0;
+ }
+}
+
+static int efx_sriov_vfs_init(struct efx_nic *efx)
+{
+ struct pci_dev *pci_dev = efx->pci_dev;
+ unsigned index, devfn, sriov, buftbl_base;
+ u16 offset, stride;
+ struct efx_vf *vf;
+ int rc;
+
+ sriov = pci_find_ext_capability(pci_dev, PCI_EXT_CAP_ID_SRIOV);
+ if (!sriov)
+ return -ENOENT;
+
+ pci_read_config_word(pci_dev, sriov + PCI_SRIOV_VF_OFFSET, &offset);
+ pci_read_config_word(pci_dev, sriov + PCI_SRIOV_VF_STRIDE, &stride);
+
+ buftbl_base = efx->vf_buftbl_base;
+ devfn = pci_dev->devfn + offset;
+ for (index = 0; index < efx->vf_count; ++index) {
+ vf = efx->vf + index;
+
+ /* Reserve buffer entries */
+ vf->buftbl_base = buftbl_base;
+ buftbl_base += EFX_VF_BUFTBL_PER_VI * efx_vf_size(efx);
+
+ vf->pci_rid = devfn;
+ snprintf(vf->pci_name, sizeof(vf->pci_name),
+ "%04x:%02x:%02x.%d",
+ pci_domain_nr(pci_dev->bus), pci_dev->bus->number,
+ PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+ rc = efx_nic_alloc_buffer(efx, &vf->buf, EFX_PAGE_SIZE,
+ GFP_KERNEL);
+ if (rc)
+ goto fail;
+
+ devfn += stride;
+ }
+
+ return 0;
+
+fail:
+ efx_sriov_vfs_fini(efx);
+ return rc;
+}
+
+int efx_sriov_init(struct efx_nic *efx)
+{
+ struct net_device *net_dev = efx->net_dev;
+ struct vfdi_status *vfdi_status;
+ int rc;
+
+ /* Ensure there's room for vf_channel */
+ BUILD_BUG_ON(EFX_MAX_CHANNELS + 1 >= EFX_VI_BASE);
+ /* Ensure that VI_BASE is aligned on VI_SCALE */
+ BUILD_BUG_ON(EFX_VI_BASE & ((1 << EFX_VI_SCALE_MAX) - 1));
+
+ if (efx->vf_count == 0)
+ return 0;
+
+ rc = efx_sriov_cmd(efx, true, NULL, NULL);
+ if (rc)
+ goto fail_cmd;
+
+ rc = efx_nic_alloc_buffer(efx, &efx->vfdi_status, sizeof(*vfdi_status),
+ GFP_KERNEL);
+ if (rc)
+ goto fail_status;
+ vfdi_status = efx->vfdi_status.addr;
+ memset(vfdi_status, 0, sizeof(*vfdi_status));
+ vfdi_status->version = 1;
+ vfdi_status->length = sizeof(*vfdi_status);
+ vfdi_status->max_tx_channels = vf_max_tx_channels;
+ vfdi_status->vi_scale = efx->vi_scale;
+ vfdi_status->rss_rxq_count = efx->rss_spread;
+ vfdi_status->peer_count = 1 + efx->vf_count;
+ vfdi_status->timer_quantum_ns = efx->timer_quantum_ns;
+
+ rc = efx_sriov_vf_alloc(efx);
+ if (rc)
+ goto fail_alloc;
+
+ mutex_init(&efx->local_lock);
+ INIT_WORK(&efx->peer_work, efx_sriov_peer_work);
+ INIT_LIST_HEAD(&efx->local_addr_list);
+ INIT_LIST_HEAD(&efx->local_page_list);
+
+ rc = efx_sriov_vfs_init(efx);
+ if (rc)
+ goto fail_vfs;
+
+ rtnl_lock();
+ ether_addr_copy(vfdi_status->peers[0].mac_addr, net_dev->dev_addr);
+ efx->vf_init_count = efx->vf_count;
+ rtnl_unlock();
+
+ efx_sriov_usrev(efx, true);
+
+ /* At this point we must be ready to accept VFDI requests */
+
+ rc = pci_enable_sriov(efx->pci_dev, efx->vf_count);
+ if (rc)
+ goto fail_pci;
+
+ netif_info(efx, probe, net_dev,
+ "enabled SR-IOV for %d VFs, %d VI per VF\n",
+ efx->vf_count, efx_vf_size(efx));
+ return 0;
+
+fail_pci:
+ efx_sriov_usrev(efx, false);
+ rtnl_lock();
+ efx->vf_init_count = 0;
+ rtnl_unlock();
+ efx_sriov_vfs_fini(efx);
+fail_vfs:
+ cancel_work_sync(&efx->peer_work);
+ efx_sriov_free_local(efx);
+ kfree(efx->vf);
+fail_alloc:
+ efx_nic_free_buffer(efx, &efx->vfdi_status);
+fail_status:
+ efx_sriov_cmd(efx, false, NULL, NULL);
+fail_cmd:
+ return rc;
+}
+
+void efx_sriov_fini(struct efx_nic *efx)
+{
+ struct efx_vf *vf;
+ unsigned int pos;
+
+ if (efx->vf_init_count == 0)
+ return;
+
+ /* Disable all interfaces to reconfiguration */
+ BUG_ON(efx->vfdi_channel->enabled);
+ efx_sriov_usrev(efx, false);
+ rtnl_lock();
+ efx->vf_init_count = 0;
+ rtnl_unlock();
+
+ /* Flush all reconfiguration work */
+ for (pos = 0; pos < efx->vf_count; ++pos) {
+ vf = efx->vf + pos;
+ cancel_work_sync(&vf->req);
+ cancel_work_sync(&vf->reset_work);
+ }
+ cancel_work_sync(&efx->peer_work);
+
+ pci_disable_sriov(efx->pci_dev);
+
+ /* Tear down back-end state */
+ efx_sriov_vfs_fini(efx);
+ efx_sriov_free_local(efx);
+ kfree(efx->vf);
+ efx_nic_free_buffer(efx, &efx->vfdi_status);
+ efx_sriov_cmd(efx, false, NULL, NULL);
+}
+
+void efx_sriov_event(struct efx_channel *channel, efx_qword_t *event)
+{
+ struct efx_nic *efx = channel->efx;
+ struct efx_vf *vf;
+ unsigned qid, seq, type, data;
+
+ qid = EFX_QWORD_FIELD(*event, FSF_CZ_USER_QID);
+
+ /* USR_EV_REG_VALUE is dword0, so access the VFDI_EV fields directly */
+ BUILD_BUG_ON(FSF_CZ_USER_EV_REG_VALUE_LBN != 0);
+ seq = EFX_QWORD_FIELD(*event, VFDI_EV_SEQ);
+ type = EFX_QWORD_FIELD(*event, VFDI_EV_TYPE);
+ data = EFX_QWORD_FIELD(*event, VFDI_EV_DATA);
+
+ netif_vdbg(efx, hw, efx->net_dev,
+ "USR_EV event from qid %d seq 0x%x type %d data 0x%x\n",
+ qid, seq, type, data);
+
+ if (map_vi_index(efx, qid, &vf, NULL))
+ return;
+ if (vf->busy)
+ goto error;
+
+ if (type == VFDI_EV_TYPE_REQ_WORD0) {
+ /* Resynchronise */
+ vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
+ vf->req_seqno = seq + 1;
+ vf->req_addr = 0;
+ } else if (seq != (vf->req_seqno++ & 0xff) || type != vf->req_type)
+ goto error;
+
+ switch (vf->req_type) {
+ case VFDI_EV_TYPE_REQ_WORD0:
+ case VFDI_EV_TYPE_REQ_WORD1:
+ case VFDI_EV_TYPE_REQ_WORD2:
+ vf->req_addr |= (u64)data << (vf->req_type << 4);
+ ++vf->req_type;
+ return;
+
+ case VFDI_EV_TYPE_REQ_WORD3:
+ vf->req_addr |= (u64)data << 48;
+ vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
+ vf->busy = true;
+ queue_work(vfdi_workqueue, &vf->req);
+ return;
+ }
+
+error:
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "ERROR: Screaming VFDI request from %s\n",
+ vf->pci_name);
+ /* Reset the request and sequence number */
+ vf->req_type = VFDI_EV_TYPE_REQ_WORD0;
+ vf->req_seqno = seq + 1;
+}
+
+void efx_sriov_flr(struct efx_nic *efx, unsigned vf_i)
+{
+ struct efx_vf *vf;
+
+ if (vf_i > efx->vf_init_count)
+ return;
+ vf = efx->vf + vf_i;
+ netif_info(efx, hw, efx->net_dev,
+ "FLR on VF %s\n", vf->pci_name);
+
+ vf->status_addr = 0;
+ efx_vfdi_remove_all_filters(vf);
+ efx_vfdi_flush_clear(vf);
+
+ vf->evq0_count = 0;
+}
+
+void efx_sriov_mac_address_changed(struct efx_nic *efx)
+{
+ struct vfdi_status *vfdi_status = efx->vfdi_status.addr;
+
+ if (!efx->vf_init_count)
+ return;
+ ether_addr_copy(vfdi_status->peers[0].mac_addr,
+ efx->net_dev->dev_addr);
+ queue_work(vfdi_workqueue, &efx->peer_work);
+}
+
+void efx_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event)
+{
+ struct efx_vf *vf;
+ unsigned queue, qid;
+
+ queue = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_SUBDATA);
+ if (map_vi_index(efx, queue, &vf, &qid))
+ return;
+ /* Ignore flush completions triggered by an FLR */
+ if (!test_bit(qid, vf->txq_mask))
+ return;
+
+ __clear_bit(qid, vf->txq_mask);
+ --vf->txq_count;
+
+ if (efx_vfdi_flush_wake(vf))
+ wake_up(&vf->flush_waitq);
+}
+
+void efx_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event)
+{
+ struct efx_vf *vf;
+ unsigned ev_failed, queue, qid;
+
+ queue = EFX_QWORD_FIELD(*event, FSF_AZ_DRIVER_EV_RX_DESCQ_ID);
+ ev_failed = EFX_QWORD_FIELD(*event,
+ FSF_AZ_DRIVER_EV_RX_FLUSH_FAIL);
+ if (map_vi_index(efx, queue, &vf, &qid))
+ return;
+ if (!test_bit(qid, vf->rxq_mask))
+ return;
+
+ if (ev_failed) {
+ set_bit(qid, vf->rxq_retry_mask);
+ atomic_inc(&vf->rxq_retry_count);
+ } else {
+ __clear_bit(qid, vf->rxq_mask);
+ --vf->rxq_count;
+ }
+ if (efx_vfdi_flush_wake(vf))
+ wake_up(&vf->flush_waitq);
+}
+
+/* Called from napi. Schedule the reset work item */
+void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq)
+{
+ struct efx_vf *vf;
+ unsigned int rel;
+
+ if (map_vi_index(efx, dmaq, &vf, &rel))
+ return;
+
+ if (net_ratelimit())
+ netif_err(efx, hw, efx->net_dev,
+ "VF %d DMA Q %d reports descriptor fetch error.\n",
+ vf->index, rel);
+ queue_work(vfdi_workqueue, &vf->reset_work);
+}
+
+/* Reset all VFs */
+void efx_sriov_reset(struct efx_nic *efx)
+{
+ unsigned int vf_i;
+ struct efx_buffer buf;
+ struct efx_vf *vf;
+
+ ASSERT_RTNL();
+
+ if (efx->vf_init_count == 0)
+ return;
+
+ efx_sriov_usrev(efx, true);
+ (void)efx_sriov_cmd(efx, true, NULL, NULL);
+
+ if (efx_nic_alloc_buffer(efx, &buf, EFX_PAGE_SIZE, GFP_NOIO))
+ return;
+
+ for (vf_i = 0; vf_i < efx->vf_init_count; ++vf_i) {
+ vf = efx->vf + vf_i;
+ efx_sriov_reset_vf(vf, &buf);
+ }
+
+ efx_nic_free_buffer(efx, &buf);
+}
+
+int efx_init_sriov(void)
+{
+ /* A single threaded workqueue is sufficient. efx_sriov_vfdi() and
+ * efx_sriov_peer_work() spend almost all their time sleeping for
+ * MCDI to complete anyway
+ */
+ vfdi_workqueue = create_singlethread_workqueue("sfc_vfdi");
+ if (!vfdi_workqueue)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void efx_fini_sriov(void)
+{
+ destroy_workqueue(vfdi_workqueue);
+}
+
+int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ struct efx_vf *vf;
+
+ if (vf_i >= efx->vf_init_count)
+ return -EINVAL;
+ vf = efx->vf + vf_i;
+
+ mutex_lock(&vf->status_lock);
+ ether_addr_copy(vf->addr.mac_addr, mac);
+ __efx_sriov_update_vf_addr(vf);
+ mutex_unlock(&vf->status_lock);
+
+ return 0;
+}
+
+int efx_sriov_set_vf_vlan(struct net_device *net_dev, int vf_i,
+ u16 vlan, u8 qos)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ struct efx_vf *vf;
+ u16 tci;
+
+ if (vf_i >= efx->vf_init_count)
+ return -EINVAL;
+ vf = efx->vf + vf_i;
+
+ mutex_lock(&vf->status_lock);
+ tci = (vlan & VLAN_VID_MASK) | ((qos & 0x7) << VLAN_PRIO_SHIFT);
+ vf->addr.tci = htons(tci);
+ __efx_sriov_update_vf_addr(vf);
+ mutex_unlock(&vf->status_lock);
+
+ return 0;
+}
+
+int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf_i,
+ bool spoofchk)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ struct efx_vf *vf;
+ int rc;
+
+ if (vf_i >= efx->vf_init_count)
+ return -EINVAL;
+ vf = efx->vf + vf_i;
+
+ mutex_lock(&vf->txq_lock);
+ if (vf->txq_count == 0) {
+ vf->tx_filter_mode =
+ spoofchk ? VF_TX_FILTER_ON : VF_TX_FILTER_OFF;
+ rc = 0;
+ } else {
+ /* This cannot be changed while TX queues are running */
+ rc = -EBUSY;
+ }
+ mutex_unlock(&vf->txq_lock);
+ return rc;
+}
+
+int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i,
+ struct ifla_vf_info *ivi)
+{
+ struct efx_nic *efx = netdev_priv(net_dev);
+ struct efx_vf *vf;
+ u16 tci;
+
+ if (vf_i >= efx->vf_init_count)
+ return -EINVAL;
+ vf = efx->vf + vf_i;
+
+ ivi->vf = vf_i;
+ ether_addr_copy(ivi->mac, vf->addr.mac_addr);
+ ivi->max_tx_rate = 0;
+ ivi->min_tx_rate = 0;
+ tci = ntohs(vf->addr.tci);
+ ivi->vlan = tci & VLAN_VID_MASK;
+ ivi->qos = (tci >> VLAN_PRIO_SHIFT) & 0x7;
+ ivi->spoofchk = vf->tx_filter_mode == VF_TX_FILTER_ON;
+
+ return 0;
+}
+
diff --git a/drivers/net/ethernet/sfc/spi.h b/drivers/net/ethernet/sfc/spi.h
deleted file mode 100644
index 71f2e3ebe1c..00000000000
--- a/drivers/net/ethernet/sfc/spi.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2005 Fen Systems Ltd.
- * Copyright 2006-2010 Solarflare Communications Inc.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation, incorporated herein by reference.
- */
-
-#ifndef EFX_SPI_H
-#define EFX_SPI_H
-
-#include "net_driver.h"
-
-/**************************************************************************
- *
- * Basic SPI command set and bit definitions
- *
- *************************************************************************/
-
-#define SPI_WRSR 0x01 /* Write status register */
-#define SPI_WRITE 0x02 /* Write data to memory array */
-#define SPI_READ 0x03 /* Read data from memory array */
-#define SPI_WRDI 0x04 /* Reset write enable latch */
-#define SPI_RDSR 0x05 /* Read status register */
-#define SPI_WREN 0x06 /* Set write enable latch */
-#define SPI_SST_EWSR 0x50 /* SST: Enable write to status register */
-
-#define SPI_STATUS_WPEN 0x80 /* Write-protect pin enabled */
-#define SPI_STATUS_BP2 0x10 /* Block protection bit 2 */
-#define SPI_STATUS_BP1 0x08 /* Block protection bit 1 */
-#define SPI_STATUS_BP0 0x04 /* Block protection bit 0 */
-#define SPI_STATUS_WEN 0x02 /* State of the write enable latch */
-#define SPI_STATUS_NRDY 0x01 /* Device busy flag */
-
-/**
- * struct efx_spi_device - an Efx SPI (Serial Peripheral Interface) device
- * @device_id: Controller's id for the device
- * @size: Size (in bytes)
- * @addr_len: Number of address bytes in read/write commands
- * @munge_address: Flag whether addresses should be munged.
- * Some devices with 9-bit addresses (e.g. AT25040A EEPROM)
- * use bit 3 of the command byte as address bit A8, rather
- * than having a two-byte address. If this flag is set, then
- * commands should be munged in this way.
- * @erase_command: Erase command (or 0 if sector erase not needed).
- * @erase_size: Erase sector size (in bytes)
- * Erase commands affect sectors with this size and alignment.
- * This must be a power of two.
- * @block_size: Write block size (in bytes).
- * Write commands are limited to blocks with this size and alignment.
- */
-struct efx_spi_device {
- int device_id;
- unsigned int size;
- unsigned int addr_len;
- unsigned int munge_address:1;
- u8 erase_command;
- unsigned int erase_size;
- unsigned int block_size;
-};
-
-static inline bool efx_spi_present(const struct efx_spi_device *spi)
-{
- return spi->size != 0;
-}
-
-int falcon_spi_cmd(struct efx_nic *efx,
- const struct efx_spi_device *spi, unsigned int command,
- int address, const void* in, void *out, size_t len);
-int falcon_spi_wait_write(struct efx_nic *efx,
- const struct efx_spi_device *spi);
-int falcon_spi_read(struct efx_nic *efx,
- const struct efx_spi_device *spi, loff_t start,
- size_t len, size_t *retlen, u8 *buffer);
-int falcon_spi_write(struct efx_nic *efx,
- const struct efx_spi_device *spi, loff_t start,
- size_t len, size_t *retlen, const u8 *buffer);
-
-/*
- * SFC4000 flash is partitioned into:
- * 0-0x400 chip and board config (see falcon_hwdefs.h)
- * 0x400-0x8000 unused (or may contain VPD if EEPROM not present)
- * 0x8000-end boot code (mapped to PCI expansion ROM)
- * SFC4000 small EEPROM (size < 0x400) is used for VPD only.
- * SFC4000 large EEPROM (size >= 0x400) is partitioned into:
- * 0-0x400 chip and board config
- * configurable VPD
- * 0x800-0x1800 boot config
- * Aside from the chip and board config, all of these are optional and may
- * be absent or truncated depending on the devices used.
- */
-#define FALCON_NVCONFIG_END 0x400U
-#define FALCON_FLASH_BOOTCODE_START 0x8000U
-#define EFX_EEPROM_BOOTCONFIG_START 0x800U
-#define EFX_EEPROM_BOOTCONFIG_END 0x1800U
-
-#endif /* EFX_SPI_H */
diff --git a/drivers/net/ethernet/sfc/tenxpress.c b/drivers/net/ethernet/sfc/tenxpress.c
index 7b0fd89e7b8..2c90e6b3157 100644
--- a/drivers/net/ethernet/sfc/tenxpress.c
+++ b/drivers/net/ethernet/sfc/tenxpress.c
@@ -1,5 +1,5 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2007-2011 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -121,7 +121,7 @@
#define GPHY_XCONTROL_REG 49152
#define GPHY_ISOLATE_LBN 10
#define GPHY_ISOLATE_WIDTH 1
-#define GPHY_DUPLEX_LBN 8
+#define GPHY_DUPLEX_LBN 8
#define GPHY_DUPLEX_WIDTH 1
#define GPHY_LOOPBACK_NEAR_LBN 14
#define GPHY_LOOPBACK_NEAR_WIDTH 1
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index 72f0fbc73b1..ede8dcca0ff 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -1,7 +1,7 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2005-2006 Fen Systems Ltd.
- * Copyright 2005-2010 Solarflare Communications Inc.
+ * Copyright 2005-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -17,18 +17,46 @@
#include <net/ipv6.h>
#include <linux/if_ether.h>
#include <linux/highmem.h>
+#include <linux/cache.h>
#include "net_driver.h"
#include "efx.h"
+#include "io.h"
#include "nic.h"
#include "workarounds.h"
+#include "ef10_regs.h"
-/*
- * TX descriptor ring full threshold
- *
- * The tx_queue descriptor ring fill-level must fall below this value
- * before we restart the netif queue
- */
-#define EFX_TXQ_THRESHOLD(_efx) ((_efx)->txq_entries / 2u)
+#ifdef EFX_USE_PIO
+
+#define EFX_PIOBUF_SIZE_MAX ER_DZ_TX_PIOBUF_SIZE
+#define EFX_PIOBUF_SIZE_DEF ALIGN(256, L1_CACHE_BYTES)
+unsigned int efx_piobuf_size __read_mostly = EFX_PIOBUF_SIZE_DEF;
+
+#endif /* EFX_USE_PIO */
+
+static inline unsigned int
+efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue)
+{
+ return tx_queue->insert_count & tx_queue->ptr_mask;
+}
+
+static inline struct efx_tx_buffer *
+__efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
+{
+ return &tx_queue->buffer[efx_tx_queue_get_insert_index(tx_queue)];
+}
+
+static inline struct efx_tx_buffer *
+efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue)
+{
+ struct efx_tx_buffer *buffer =
+ __efx_tx_queue_get_insert_buffer(tx_queue);
+
+ EFX_BUG_ON_PARANOID(buffer->len);
+ EFX_BUG_ON_PARANOID(buffer->flags);
+ EFX_BUG_ON_PARANOID(buffer->unmap_len);
+
+ return buffer;
+}
static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
struct efx_tx_buffer *buffer,
@@ -36,70 +64,34 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue,
unsigned int *bytes_compl)
{
if (buffer->unmap_len) {
- struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
- dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len -
- buffer->unmap_len);
- if (buffer->unmap_single)
- pci_unmap_single(pci_dev, unmap_addr, buffer->unmap_len,
- PCI_DMA_TODEVICE);
+ struct device *dma_dev = &tx_queue->efx->pci_dev->dev;
+ dma_addr_t unmap_addr = buffer->dma_addr - buffer->dma_offset;
+ if (buffer->flags & EFX_TX_BUF_MAP_SINGLE)
+ dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len,
+ DMA_TO_DEVICE);
else
- pci_unmap_page(pci_dev, unmap_addr, buffer->unmap_len,
- PCI_DMA_TODEVICE);
+ dma_unmap_page(dma_dev, unmap_addr, buffer->unmap_len,
+ DMA_TO_DEVICE);
buffer->unmap_len = 0;
- buffer->unmap_single = false;
}
- if (buffer->skb) {
+ if (buffer->flags & EFX_TX_BUF_SKB) {
(*pkts_compl)++;
(*bytes_compl) += buffer->skb->len;
dev_kfree_skb_any((struct sk_buff *) buffer->skb);
- buffer->skb = NULL;
netif_vdbg(tx_queue->efx, tx_done, tx_queue->efx->net_dev,
"TX queue %d transmission id %x complete\n",
tx_queue->queue, tx_queue->read_count);
+ } else if (buffer->flags & EFX_TX_BUF_HEAP) {
+ kfree(buffer->heap_buf);
}
-}
-/**
- * struct efx_tso_header - a DMA mapped buffer for packet headers
- * @next: Linked list of free ones.
- * The list is protected by the TX queue lock.
- * @dma_unmap_len: Length to unmap for an oversize buffer, or 0.
- * @dma_addr: The DMA address of the header below.
- *
- * This controls the memory used for a TSO header. Use TSOH_DATA()
- * to find the packet header data. Use TSOH_SIZE() to calculate the
- * total size required for a given packet header length. TSO headers
- * in the free list are exactly %TSOH_STD_SIZE bytes in size.
- */
-struct efx_tso_header {
- union {
- struct efx_tso_header *next;
- size_t unmap_len;
- };
- dma_addr_t dma_addr;
-};
+ buffer->len = 0;
+ buffer->flags = 0;
+}
static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
struct sk_buff *skb);
-static void efx_fini_tso(struct efx_tx_queue *tx_queue);
-static void efx_tsoh_heap_free(struct efx_tx_queue *tx_queue,
- struct efx_tso_header *tsoh);
-
-static void efx_tsoh_free(struct efx_tx_queue *tx_queue,
- struct efx_tx_buffer *buffer)
-{
- if (buffer->tsoh) {
- if (likely(!buffer->tsoh->unmap_len)) {
- buffer->tsoh->next = tx_queue->tso_headers_free;
- tx_queue->tso_headers_free = buffer->tsoh;
- } else {
- efx_tsoh_heap_free(tx_queue, buffer->tsoh);
- }
- buffer->tsoh = NULL;
- }
-}
-
static inline unsigned
efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
@@ -110,7 +102,7 @@ efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
* little benefit from using descriptors that cross those
* boundaries and we keep things simple by not doing so.
*/
- unsigned len = (~dma_addr & 0xfff) + 1;
+ unsigned len = (~dma_addr & (EFX_PAGE_SIZE - 1)) + 1;
/* Work around hardware bug for unaligned buffers. */
if (EFX_WORKAROUND_5391(efx) && (dma_addr & 0xf))
@@ -119,6 +111,228 @@ efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
return len;
}
+unsigned int efx_tx_max_skb_descs(struct efx_nic *efx)
+{
+ /* Header and payload descriptor for each output segment, plus
+ * one for every input fragment boundary within a segment
+ */
+ unsigned int max_descs = EFX_TSO_MAX_SEGS * 2 + MAX_SKB_FRAGS;
+
+ /* Possibly one more per segment for the alignment workaround,
+ * or for option descriptors
+ */
+ if (EFX_WORKAROUND_5391(efx) || efx_nic_rev(efx) >= EFX_REV_HUNT_A0)
+ max_descs += EFX_TSO_MAX_SEGS;
+
+ /* Possibly more for PCIe page boundaries within input fragments */
+ if (PAGE_SIZE > EFX_PAGE_SIZE)
+ max_descs += max_t(unsigned int, MAX_SKB_FRAGS,
+ DIV_ROUND_UP(GSO_MAX_SIZE, EFX_PAGE_SIZE));
+
+ return max_descs;
+}
+
+/* Get partner of a TX queue, seen as part of the same net core queue */
+static struct efx_tx_queue *efx_tx_queue_partner(struct efx_tx_queue *tx_queue)
+{
+ if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD)
+ return tx_queue - EFX_TXQ_TYPE_OFFLOAD;
+ else
+ return tx_queue + EFX_TXQ_TYPE_OFFLOAD;
+}
+
+static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1)
+{
+ /* We need to consider both queues that the net core sees as one */
+ struct efx_tx_queue *txq2 = efx_tx_queue_partner(txq1);
+ struct efx_nic *efx = txq1->efx;
+ unsigned int fill_level;
+
+ fill_level = max(txq1->insert_count - txq1->old_read_count,
+ txq2->insert_count - txq2->old_read_count);
+ if (likely(fill_level < efx->txq_stop_thresh))
+ return;
+
+ /* We used the stale old_read_count above, which gives us a
+ * pessimistic estimate of the fill level (which may even
+ * validly be >= efx->txq_entries). Now try again using
+ * read_count (more likely to be a cache miss).
+ *
+ * If we read read_count and then conditionally stop the
+ * queue, it is possible for the completion path to race with
+ * us and complete all outstanding descriptors in the middle,
+ * after which there will be no more completions to wake it.
+ * Therefore we stop the queue first, then read read_count
+ * (with a memory barrier to ensure the ordering), then
+ * restart the queue if the fill level turns out to be low
+ * enough.
+ */
+ netif_tx_stop_queue(txq1->core_txq);
+ smp_mb();
+ txq1->old_read_count = ACCESS_ONCE(txq1->read_count);
+ txq2->old_read_count = ACCESS_ONCE(txq2->read_count);
+
+ fill_level = max(txq1->insert_count - txq1->old_read_count,
+ txq2->insert_count - txq2->old_read_count);
+ EFX_BUG_ON_PARANOID(fill_level >= efx->txq_entries);
+ if (likely(fill_level < efx->txq_stop_thresh)) {
+ smp_mb();
+ if (likely(!efx->loopback_selftest))
+ netif_tx_start_queue(txq1->core_txq);
+ }
+}
+
+#ifdef EFX_USE_PIO
+
+struct efx_short_copy_buffer {
+ int used;
+ u8 buf[L1_CACHE_BYTES];
+};
+
+/* Copy in explicit 64-bit writes. */
+static void efx_memcpy_64(void __iomem *dest, void *src, size_t len)
+{
+ u64 *src64 = src;
+ u64 __iomem *dest64 = dest;
+ size_t l64 = len / 8;
+ size_t i;
+
+ for (i = 0; i < l64; i++)
+ writeq(src64[i], &dest64[i]);
+}
+
+/* Copy to PIO, respecting that writes to PIO buffers must be dword aligned.
+ * Advances piobuf pointer. Leaves additional data in the copy buffer.
+ */
+static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf,
+ u8 *data, int len,
+ struct efx_short_copy_buffer *copy_buf)
+{
+ int block_len = len & ~(sizeof(copy_buf->buf) - 1);
+
+ efx_memcpy_64(*piobuf, data, block_len);
+ *piobuf += block_len;
+ len -= block_len;
+
+ if (len) {
+ data += block_len;
+ BUG_ON(copy_buf->used);
+ BUG_ON(len > sizeof(copy_buf->buf));
+ memcpy(copy_buf->buf, data, len);
+ copy_buf->used = len;
+ }
+}
+
+/* Copy to PIO, respecting dword alignment, popping data from copy buffer first.
+ * Advances piobuf pointer. Leaves additional data in the copy buffer.
+ */
+static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf,
+ u8 *data, int len,
+ struct efx_short_copy_buffer *copy_buf)
+{
+ if (copy_buf->used) {
+ /* if the copy buffer is partially full, fill it up and write */
+ int copy_to_buf =
+ min_t(int, sizeof(copy_buf->buf) - copy_buf->used, len);
+
+ memcpy(copy_buf->buf + copy_buf->used, data, copy_to_buf);
+ copy_buf->used += copy_to_buf;
+
+ /* if we didn't fill it up then we're done for now */
+ if (copy_buf->used < sizeof(copy_buf->buf))
+ return;
+
+ efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+ *piobuf += sizeof(copy_buf->buf);
+ data += copy_to_buf;
+ len -= copy_to_buf;
+ copy_buf->used = 0;
+ }
+
+ efx_memcpy_toio_aligned(efx, piobuf, data, len, copy_buf);
+}
+
+static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf,
+ struct efx_short_copy_buffer *copy_buf)
+{
+ /* if there's anything in it, write the whole buffer, including junk */
+ if (copy_buf->used)
+ efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf));
+}
+
+/* Traverse skb structure and copy fragments in to PIO buffer.
+ * Advances piobuf pointer.
+ */
+static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb,
+ u8 __iomem **piobuf,
+ struct efx_short_copy_buffer *copy_buf)
+{
+ int i;
+
+ efx_memcpy_toio_aligned(efx, piobuf, skb->data, skb_headlen(skb),
+ copy_buf);
+
+ for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
+ skb_frag_t *f = &skb_shinfo(skb)->frags[i];
+ u8 *vaddr;
+
+ vaddr = kmap_atomic(skb_frag_page(f));
+
+ efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + f->page_offset,
+ skb_frag_size(f), copy_buf);
+ kunmap_atomic(vaddr);
+ }
+
+ EFX_BUG_ON_PARANOID(skb_shinfo(skb)->frag_list);
+}
+
+static struct efx_tx_buffer *
+efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
+{
+ struct efx_tx_buffer *buffer =
+ efx_tx_queue_get_insert_buffer(tx_queue);
+ u8 __iomem *piobuf = tx_queue->piobuf;
+
+ /* Copy to PIO buffer. Ensure the writes are padded to the end
+ * of a cache line, as this is required for write-combining to be
+ * effective on at least x86.
+ */
+
+ if (skb_shinfo(skb)->nr_frags) {
+ /* The size of the copy buffer will ensure all writes
+ * are the size of a cache line.
+ */
+ struct efx_short_copy_buffer copy_buf;
+
+ copy_buf.used = 0;
+
+ efx_skb_copy_bits_to_pio(tx_queue->efx, skb,
+ &piobuf, &copy_buf);
+ efx_flush_copy_buffer(tx_queue->efx, piobuf, &copy_buf);
+ } else {
+ /* Pad the write to the size of a cache line.
+ * We can do this because we know the skb_shared_info sruct is
+ * after the source, and the destination buffer is big enough.
+ */
+ BUILD_BUG_ON(L1_CACHE_BYTES >
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
+ efx_memcpy_64(tx_queue->piobuf, skb->data,
+ ALIGN(skb->len, L1_CACHE_BYTES));
+ }
+
+ EFX_POPULATE_QWORD_5(buffer->option,
+ ESF_DZ_TX_DESC_IS_OPT, 1,
+ ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_PIO,
+ ESF_DZ_TX_PIO_CONT, 0,
+ ESF_DZ_TX_PIO_BYTE_CNT, skb->len,
+ ESF_DZ_TX_PIO_BUF_ADDR,
+ tx_queue->piobuf_offset);
+ ++tx_queue->pio_packets;
+ ++tx_queue->insert_count;
+ return buffer;
+}
+#endif /* EFX_USE_PIO */
+
/*
* Add a socket buffer to a TX queue
*
@@ -132,21 +346,20 @@ efx_max_tx_len(struct efx_nic *efx, dma_addr_t dma_addr)
* This function is split out from efx_hard_start_xmit to allow the
* loopback test to direct packets via specific TX queues.
*
- * Returns NETDEV_TX_OK or NETDEV_TX_BUSY
+ * Returns NETDEV_TX_OK.
* You must hold netif_tx_lock() to call this function.
*/
netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
{
struct efx_nic *efx = tx_queue->efx;
- struct pci_dev *pci_dev = efx->pci_dev;
+ struct device *dma_dev = &efx->pci_dev->dev;
struct efx_tx_buffer *buffer;
skb_frag_t *fragment;
- unsigned int len, unmap_len = 0, fill_level, insert_ptr;
+ unsigned int len, unmap_len = 0;
dma_addr_t dma_addr, unmap_addr = 0;
unsigned int dma_len;
- bool unmap_single;
- int q_space, i = 0;
- netdev_tx_t rc = NETDEV_TX_OK;
+ unsigned short dma_flags;
+ int i = 0;
EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
@@ -164,20 +377,28 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
return NETDEV_TX_OK;
}
- fill_level = tx_queue->insert_count - tx_queue->old_read_count;
- q_space = efx->txq_entries - 1 - fill_level;
+ /* Consider using PIO for short packets */
+#ifdef EFX_USE_PIO
+ if (skb->len <= efx_piobuf_size && tx_queue->piobuf &&
+ efx_nic_tx_is_empty(tx_queue) &&
+ efx_nic_tx_is_empty(efx_tx_queue_partner(tx_queue))) {
+ buffer = efx_enqueue_skb_pio(tx_queue, skb);
+ dma_flags = EFX_TX_BUF_OPTION;
+ goto finish_packet;
+ }
+#endif
- /* Map for DMA. Use pci_map_single rather than pci_map_page
+ /* Map for DMA. Use dma_map_single rather than dma_map_page
* since this is more efficient on machines with sparse
* memory.
*/
- unmap_single = true;
- dma_addr = pci_map_single(pci_dev, skb->data, len, PCI_DMA_TODEVICE);
+ dma_flags = EFX_TX_BUF_MAP_SINGLE;
+ dma_addr = dma_map_single(dma_dev, skb->data, len, PCI_DMA_TODEVICE);
/* Process all fragments */
while (1) {
- if (unlikely(pci_dma_mapping_error(pci_dev, dma_addr)))
- goto pci_err;
+ if (unlikely(dma_mapping_error(dma_dev, dma_addr)))
+ goto dma_err;
/* Store fields for marking in the per-fragment final
* descriptor */
@@ -186,40 +407,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
/* Add to TX queue, splitting across DMA boundaries */
do {
- if (unlikely(q_space-- <= 0)) {
- /* It might be that completions have
- * happened since the xmit path last
- * checked. Update the xmit path's
- * copy of read_count.
- */
- netif_tx_stop_queue(tx_queue->core_txq);
- /* This memory barrier protects the
- * change of queue state from the access
- * of read_count. */
- smp_mb();
- tx_queue->old_read_count =
- ACCESS_ONCE(tx_queue->read_count);
- fill_level = (tx_queue->insert_count
- - tx_queue->old_read_count);
- q_space = efx->txq_entries - 1 - fill_level;
- if (unlikely(q_space-- <= 0)) {
- rc = NETDEV_TX_BUSY;
- goto unwind;
- }
- smp_mb();
- if (likely(!efx->loopback_selftest))
- netif_tx_start_queue(
- tx_queue->core_txq);
- }
-
- insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
- buffer = &tx_queue->buffer[insert_ptr];
- efx_tsoh_free(tx_queue, buffer);
- EFX_BUG_ON_PARANOID(buffer->tsoh);
- EFX_BUG_ON_PARANOID(buffer->skb);
- EFX_BUG_ON_PARANOID(buffer->len);
- EFX_BUG_ON_PARANOID(!buffer->continuation);
- EFX_BUG_ON_PARANOID(buffer->unmap_len);
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
dma_len = efx_max_tx_len(efx, dma_addr);
if (likely(dma_len >= len))
@@ -228,14 +416,16 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
/* Fill out per descriptor fields */
buffer->len = dma_len;
buffer->dma_addr = dma_addr;
+ buffer->flags = EFX_TX_BUF_CONT;
len -= dma_len;
dma_addr += dma_len;
++tx_queue->insert_count;
} while (len);
/* Transfer ownership of the unmapping to the final buffer */
- buffer->unmap_single = unmap_single;
+ buffer->flags = EFX_TX_BUF_CONT | dma_flags;
buffer->unmap_len = unmap_len;
+ buffer->dma_offset = buffer->dma_addr - unmap_addr;
unmap_len = 0;
/* Get address and size of next fragment */
@@ -245,23 +435,28 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
len = skb_frag_size(fragment);
i++;
/* Map for DMA */
- unmap_single = false;
- dma_addr = skb_frag_dma_map(&pci_dev->dev, fragment, 0, len,
+ dma_flags = 0;
+ dma_addr = skb_frag_dma_map(dma_dev, fragment, 0, len,
DMA_TO_DEVICE);
}
/* Transfer ownership of the skb to the final buffer */
+#ifdef EFX_USE_PIO
+finish_packet:
+#endif
buffer->skb = skb;
- buffer->continuation = false;
+ buffer->flags = EFX_TX_BUF_SKB | dma_flags;
netdev_tx_sent_queue(tx_queue->core_txq, skb->len);
/* Pass off to hardware */
efx_nic_push_buffers(tx_queue);
+ efx_tx_maybe_stop_queue(tx_queue);
+
return NETDEV_TX_OK;
- pci_err:
+ dma_err:
netif_err(efx, tx_err, efx->net_dev,
" TX queue %d could not map skb with %d bytes %d "
"fragments for DMA\n", tx_queue->queue, skb->len,
@@ -270,28 +465,25 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb)
/* Mark the packet as transmitted, and free the SKB ourselves */
dev_kfree_skb_any(skb);
- unwind:
/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
unsigned int pkts_compl = 0, bytes_compl = 0;
--tx_queue->insert_count;
- insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
- buffer = &tx_queue->buffer[insert_ptr];
+ buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
- buffer->len = 0;
}
/* Free the fragment we were mid-way through pushing */
if (unmap_len) {
- if (unmap_single)
- pci_unmap_single(pci_dev, unmap_addr, unmap_len,
- PCI_DMA_TODEVICE);
+ if (dma_flags & EFX_TX_BUF_MAP_SINGLE)
+ dma_unmap_single(dma_dev, unmap_addr, unmap_len,
+ DMA_TO_DEVICE);
else
- pci_unmap_page(pci_dev, unmap_addr, unmap_len,
- PCI_DMA_TODEVICE);
+ dma_unmap_page(dma_dev, unmap_addr, unmap_len,
+ DMA_TO_DEVICE);
}
- return rc;
+ return NETDEV_TX_OK;
}
/* Remove packets from the TX queue
@@ -312,7 +504,9 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
while (read_ptr != stop_index) {
struct efx_tx_buffer *buffer = &tx_queue->buffer[read_ptr];
- if (unlikely(buffer->len == 0)) {
+
+ if (!(buffer->flags & EFX_TX_BUF_OPTION) &&
+ unlikely(buffer->len == 0)) {
netif_err(efx, tx_err, efx->net_dev,
"TX queue %d spurious TX completion id %x\n",
tx_queue->queue, read_ptr);
@@ -321,8 +515,6 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
}
efx_dequeue_buffer(tx_queue, buffer, pkts_compl, bytes_compl);
- buffer->continuation = true;
- buffer->len = 0;
++tx_queue->read_count;
read_ptr = tx_queue->read_count & tx_queue->ptr_mask;
@@ -339,7 +531,7 @@ static void efx_dequeue_buffers(struct efx_tx_queue *tx_queue,
* OS to free the skb.
*/
netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
- struct net_device *net_dev)
+ struct net_device *net_dev)
{
struct efx_nic *efx = netdev_priv(net_dev);
struct efx_tx_queue *tx_queue;
@@ -347,6 +539,12 @@ netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb,
EFX_WARN_ON_PARANOID(!netif_device_present(net_dev));
+ /* PTP "event" packet */
+ if (unlikely(efx_xmit_with_hwtstamp(skb)) &&
+ unlikely(efx_ptp_is_ptp_tx(efx, skb))) {
+ return efx_ptp_tx(efx, skb);
+ }
+
index = skb_get_queue_mapping(skb);
type = skb->ip_summed == CHECKSUM_PARTIAL ? EFX_TXQ_TYPE_OFFLOAD : 0;
if (index >= efx->n_tx_channels) {
@@ -431,6 +629,7 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
{
unsigned fill_level;
struct efx_nic *efx = tx_queue->efx;
+ struct efx_tx_queue *txq2;
unsigned int pkts_compl = 0, bytes_compl = 0;
EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask);
@@ -438,18 +637,22 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
- /* See if we need to restart the netif queue. This barrier
- * separates the update of read_count from the test of the
- * queue state. */
+ if (pkts_compl > 1)
+ ++tx_queue->merge_events;
+
+ /* See if we need to restart the netif queue. This memory
+ * barrier ensures that we write read_count (inside
+ * efx_dequeue_buffers()) before reading the queue status.
+ */
smp_mb();
if (unlikely(netif_tx_queue_stopped(tx_queue->core_txq)) &&
likely(efx->port_enabled) &&
likely(netif_device_present(efx->net_dev))) {
- fill_level = tx_queue->insert_count - tx_queue->read_count;
- if (fill_level < EFX_TXQ_THRESHOLD(efx)) {
- EFX_BUG_ON_PARANOID(!efx_dev_registered(efx));
+ txq2 = efx_tx_queue_partner(tx_queue);
+ fill_level = max(tx_queue->insert_count - tx_queue->read_count,
+ txq2->insert_count - txq2->read_count);
+ if (fill_level <= efx->txq_wake_thresh)
netif_tx_wake_queue(tx_queue->core_txq);
- }
}
/* Check whether the hardware queue is now empty */
@@ -463,11 +666,26 @@ void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index)
}
}
+/* Size of page-based TSO header buffers. Larger blocks must be
+ * allocated from the heap.
+ */
+#define TSOH_STD_SIZE 128
+#define TSOH_PER_PAGE (PAGE_SIZE / TSOH_STD_SIZE)
+
+/* At most half the descriptors in the queue at any time will refer to
+ * a TSO header buffer, since they must always be followed by a
+ * payload descriptor referring to an skb.
+ */
+static unsigned int efx_tsoh_page_count(struct efx_tx_queue *tx_queue)
+{
+ return DIV_ROUND_UP(tx_queue->ptr_mask + 1, 2 * TSOH_PER_PAGE);
+}
+
int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
{
struct efx_nic *efx = tx_queue->efx;
unsigned int entries;
- int i, rc;
+ int rc;
/* Create the smallest power-of-two aligned ring */
entries = max(roundup_pow_of_two(efx->txq_entries), EFX_MIN_DMAQ_SIZE);
@@ -483,17 +701,28 @@ int efx_probe_tx_queue(struct efx_tx_queue *tx_queue)
GFP_KERNEL);
if (!tx_queue->buffer)
return -ENOMEM;
- for (i = 0; i <= tx_queue->ptr_mask; ++i)
- tx_queue->buffer[i].continuation = true;
+
+ if (tx_queue->queue & EFX_TXQ_TYPE_OFFLOAD) {
+ tx_queue->tsoh_page =
+ kcalloc(efx_tsoh_page_count(tx_queue),
+ sizeof(tx_queue->tsoh_page[0]), GFP_KERNEL);
+ if (!tx_queue->tsoh_page) {
+ rc = -ENOMEM;
+ goto fail1;
+ }
+ }
/* Allocate hardware ring */
rc = efx_nic_probe_tx(tx_queue);
if (rc)
- goto fail;
+ goto fail2;
return 0;
- fail:
+fail2:
+ kfree(tx_queue->tsoh_page);
+ tx_queue->tsoh_page = NULL;
+fail1:
kfree(tx_queue->buffer);
tx_queue->buffer = NULL;
return rc;
@@ -517,10 +746,13 @@ void efx_init_tx_queue(struct efx_tx_queue *tx_queue)
tx_queue->initialised = true;
}
-void efx_release_tx_buffers(struct efx_tx_queue *tx_queue)
+void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
{
struct efx_tx_buffer *buffer;
+ netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
+ "shutting down TX queue %d\n", tx_queue->queue);
+
if (!tx_queue->buffer)
return;
@@ -529,35 +761,16 @@ void efx_release_tx_buffers(struct efx_tx_queue *tx_queue)
unsigned int pkts_compl = 0, bytes_compl = 0;
buffer = &tx_queue->buffer[tx_queue->read_count & tx_queue->ptr_mask];
efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl);
- buffer->continuation = true;
- buffer->len = 0;
++tx_queue->read_count;
}
netdev_tx_reset_queue(tx_queue->core_txq);
}
-void efx_fini_tx_queue(struct efx_tx_queue *tx_queue)
-{
- if (!tx_queue->initialised)
- return;
-
- netif_dbg(tx_queue->efx, drv, tx_queue->efx->net_dev,
- "shutting down TX queue %d\n", tx_queue->queue);
-
- tx_queue->initialised = false;
-
- /* Flush TX queue, remove descriptor ring */
- efx_nic_fini_tx(tx_queue);
-
- efx_release_tx_buffers(tx_queue);
-
- /* Free up TSO header cache */
- efx_fini_tso(tx_queue);
-}
-
void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
{
+ int i;
+
if (!tx_queue->buffer)
return;
@@ -565,6 +778,14 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
"destroying TX queue %d\n", tx_queue->queue);
efx_nic_remove_tx(tx_queue);
+ if (tx_queue->tsoh_page) {
+ for (i = 0; i < efx_tsoh_page_count(tx_queue); i++)
+ efx_nic_free_buffer(tx_queue->efx,
+ &tx_queue->tsoh_page[i]);
+ kfree(tx_queue->tsoh_page);
+ tx_queue->tsoh_page = NULL;
+ }
+
kfree(tx_queue->buffer);
tx_queue->buffer = NULL;
}
@@ -578,31 +799,7 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
* Requires TX checksum offload support.
*/
-/* Number of bytes inserted at the start of a TSO header buffer,
- * similar to NET_IP_ALIGN.
- */
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#define TSOH_OFFSET 0
-#else
-#define TSOH_OFFSET NET_IP_ALIGN
-#endif
-
-#define TSOH_BUFFER(tsoh) ((u8 *)(tsoh + 1) + TSOH_OFFSET)
-
-/* Total size of struct efx_tso_header, buffer and padding */
-#define TSOH_SIZE(hdr_len) \
- (sizeof(struct efx_tso_header) + TSOH_OFFSET + hdr_len)
-
-/* Size of blocks on free list. Larger blocks must be allocated from
- * the heap.
- */
-#define TSOH_STD_SIZE 128
-
#define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2))
-#define ETH_HDR_LEN(skb) (skb_network_header(skb) - (skb)->data)
-#define SKB_TCP_OFF(skb) PTR_DIFF(tcp_hdr(skb), (skb)->data)
-#define SKB_IPV4_OFF(skb) PTR_DIFF(ip_hdr(skb), (skb)->data)
-#define SKB_IPV6_OFF(skb) PTR_DIFF(ipv6_hdr(skb), (skb)->data)
/**
* struct tso_state - TSO state for an SKB
@@ -614,10 +811,15 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue)
* @in_len: Remaining length in current SKB fragment
* @unmap_len: Length of SKB fragment
* @unmap_addr: DMA address of SKB fragment
- * @unmap_single: DMA single vs page mapping flag
+ * @dma_flags: TX buffer flags for DMA mapping - %EFX_TX_BUF_MAP_SINGLE or 0
* @protocol: Network protocol (after any VLAN header)
+ * @ip_off: Offset of IP header
+ * @tcp_off: Offset of TCP header
* @header_len: Number of bytes of header
- * @full_packet_size: Number of bytes to put in each outgoing segment
+ * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload
+ * @header_dma_addr: Header DMA address, when using option descriptors
+ * @header_unmap_len: Header DMA mapped length, or 0 if not using option
+ * descriptors
*
* The state used during segmentation. It is put into this data structure
* just to make it easy to pass into inline functions.
@@ -626,7 +828,7 @@ struct tso_state {
/* Output position */
unsigned out_len;
unsigned seqnum;
- unsigned ipv4_id;
+ u16 ipv4_id;
unsigned packet_space;
/* Input position */
@@ -634,11 +836,15 @@ struct tso_state {
unsigned in_len;
unsigned unmap_len;
dma_addr_t unmap_addr;
- bool unmap_single;
+ unsigned short dma_flags;
__be16 protocol;
+ unsigned int ip_off;
+ unsigned int tcp_off;
unsigned header_len;
- int full_packet_size;
+ unsigned int ip_base_len;
+ dma_addr_t header_dma_addr;
+ unsigned int header_unmap_len;
};
@@ -653,17 +859,8 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
EFX_BUG_ON_PARANOID(((struct ethhdr *)skb->data)->h_proto !=
protocol);
if (protocol == htons(ETH_P_8021Q)) {
- /* Find the encapsulated protocol; reset network header
- * and transport header based on that. */
struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data;
protocol = veh->h_vlan_encapsulated_proto;
- skb_set_network_header(skb, sizeof(*veh));
- if (protocol == htons(ETH_P_IP))
- skb_set_transport_header(skb, sizeof(*veh) +
- 4 * ip_hdr(skb)->ihl);
- else if (protocol == htons(ETH_P_IPV6))
- skb_set_transport_header(skb, sizeof(*veh) +
- sizeof(struct ipv6hdr));
}
if (protocol == htons(ETH_P_IP)) {
@@ -679,92 +876,44 @@ static __be16 efx_tso_check_protocol(struct sk_buff *skb)
return protocol;
}
-
-/*
- * Allocate a page worth of efx_tso_header structures, and string them
- * into the tx_queue->tso_headers_free linked list. Return 0 or -ENOMEM.
- */
-static int efx_tsoh_block_alloc(struct efx_tx_queue *tx_queue)
+static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer, unsigned int len)
{
+ u8 *result;
- struct pci_dev *pci_dev = tx_queue->efx->pci_dev;
- struct efx_tso_header *tsoh;
- dma_addr_t dma_addr;
- u8 *base_kva, *kva;
-
- base_kva = pci_alloc_consistent(pci_dev, PAGE_SIZE, &dma_addr);
- if (base_kva == NULL) {
- netif_err(tx_queue->efx, tx_err, tx_queue->efx->net_dev,
- "Unable to allocate page for TSO headers\n");
- return -ENOMEM;
- }
-
- /* pci_alloc_consistent() allocates pages. */
- EFX_BUG_ON_PARANOID(dma_addr & (PAGE_SIZE - 1u));
-
- for (kva = base_kva; kva < base_kva + PAGE_SIZE; kva += TSOH_STD_SIZE) {
- tsoh = (struct efx_tso_header *)kva;
- tsoh->dma_addr = dma_addr + (TSOH_BUFFER(tsoh) - base_kva);
- tsoh->next = tx_queue->tso_headers_free;
- tx_queue->tso_headers_free = tsoh;
- }
-
- return 0;
-}
-
-
-/* Free up a TSO header, and all others in the same page. */
-static void efx_tsoh_block_free(struct efx_tx_queue *tx_queue,
- struct efx_tso_header *tsoh,
- struct pci_dev *pci_dev)
-{
- struct efx_tso_header **p;
- unsigned long base_kva;
- dma_addr_t base_dma;
-
- base_kva = (unsigned long)tsoh & PAGE_MASK;
- base_dma = tsoh->dma_addr & PAGE_MASK;
-
- p = &tx_queue->tso_headers_free;
- while (*p != NULL) {
- if (((unsigned long)*p & PAGE_MASK) == base_kva)
- *p = (*p)->next;
- else
- p = &(*p)->next;
- }
+ EFX_BUG_ON_PARANOID(buffer->len);
+ EFX_BUG_ON_PARANOID(buffer->flags);
+ EFX_BUG_ON_PARANOID(buffer->unmap_len);
- pci_free_consistent(pci_dev, PAGE_SIZE, (void *)base_kva, base_dma);
-}
+ if (likely(len <= TSOH_STD_SIZE - NET_IP_ALIGN)) {
+ unsigned index =
+ (tx_queue->insert_count & tx_queue->ptr_mask) / 2;
+ struct efx_buffer *page_buf =
+ &tx_queue->tsoh_page[index / TSOH_PER_PAGE];
+ unsigned offset =
+ TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + NET_IP_ALIGN;
+
+ if (unlikely(!page_buf->addr) &&
+ efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE,
+ GFP_ATOMIC))
+ return NULL;
+
+ result = (u8 *)page_buf->addr + offset;
+ buffer->dma_addr = page_buf->dma_addr + offset;
+ buffer->flags = EFX_TX_BUF_CONT;
+ } else {
+ tx_queue->tso_long_headers++;
-static struct efx_tso_header *
-efx_tsoh_heap_alloc(struct efx_tx_queue *tx_queue, size_t header_len)
-{
- struct efx_tso_header *tsoh;
-
- tsoh = kmalloc(TSOH_SIZE(header_len), GFP_ATOMIC | GFP_DMA);
- if (unlikely(!tsoh))
- return NULL;
-
- tsoh->dma_addr = pci_map_single(tx_queue->efx->pci_dev,
- TSOH_BUFFER(tsoh), header_len,
- PCI_DMA_TODEVICE);
- if (unlikely(pci_dma_mapping_error(tx_queue->efx->pci_dev,
- tsoh->dma_addr))) {
- kfree(tsoh);
- return NULL;
+ buffer->heap_buf = kmalloc(NET_IP_ALIGN + len, GFP_ATOMIC);
+ if (unlikely(!buffer->heap_buf))
+ return NULL;
+ result = (u8 *)buffer->heap_buf + NET_IP_ALIGN;
+ buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP;
}
- tsoh->unmap_len = header_len;
- return tsoh;
-}
+ buffer->len = len;
-static void
-efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
-{
- pci_unmap_single(tx_queue->efx->pci_dev,
- tsoh->dma_addr, tsoh->unmap_len,
- PCI_DMA_TODEVICE);
- kfree(tsoh);
+ return result;
}
/**
@@ -774,62 +923,26 @@ efx_tsoh_heap_free(struct efx_tx_queue *tx_queue, struct efx_tso_header *tsoh)
* @len: Length of fragment
* @final_buffer: The final buffer inserted into the queue
*
- * Push descriptors onto the TX queue. Return 0 on success or 1 if
- * @tx_queue full.
+ * Push descriptors onto the TX queue.
*/
-static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
- dma_addr_t dma_addr, unsigned len,
- struct efx_tx_buffer **final_buffer)
+static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
+ dma_addr_t dma_addr, unsigned len,
+ struct efx_tx_buffer **final_buffer)
{
struct efx_tx_buffer *buffer;
struct efx_nic *efx = tx_queue->efx;
- unsigned dma_len, fill_level, insert_ptr;
- int q_space;
+ unsigned dma_len;
EFX_BUG_ON_PARANOID(len <= 0);
- fill_level = tx_queue->insert_count - tx_queue->old_read_count;
- /* -1 as there is no way to represent all descriptors used */
- q_space = efx->txq_entries - 1 - fill_level;
-
while (1) {
- if (unlikely(q_space-- <= 0)) {
- /* It might be that completions have happened
- * since the xmit path last checked. Update
- * the xmit path's copy of read_count.
- */
- netif_tx_stop_queue(tx_queue->core_txq);
- /* This memory barrier protects the change of
- * queue state from the access of read_count. */
- smp_mb();
- tx_queue->old_read_count =
- ACCESS_ONCE(tx_queue->read_count);
- fill_level = (tx_queue->insert_count
- - tx_queue->old_read_count);
- q_space = efx->txq_entries - 1 - fill_level;
- if (unlikely(q_space-- <= 0)) {
- *final_buffer = NULL;
- return 1;
- }
- smp_mb();
- netif_tx_start_queue(tx_queue->core_txq);
- }
-
- insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask;
- buffer = &tx_queue->buffer[insert_ptr];
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
++tx_queue->insert_count;
EFX_BUG_ON_PARANOID(tx_queue->insert_count -
tx_queue->read_count >=
efx->txq_entries);
- efx_tsoh_free(tx_queue, buffer);
- EFX_BUG_ON_PARANOID(buffer->len);
- EFX_BUG_ON_PARANOID(buffer->unmap_len);
- EFX_BUG_ON_PARANOID(buffer->skb);
- EFX_BUG_ON_PARANOID(!buffer->continuation);
- EFX_BUG_ON_PARANOID(buffer->tsoh);
-
buffer->dma_addr = dma_addr;
dma_len = efx_max_tx_len(efx, dma_addr);
@@ -838,7 +951,8 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
if (dma_len >= len)
break;
- buffer->len = dma_len; /* Don't set the other members */
+ buffer->len = dma_len;
+ buffer->flags = EFX_TX_BUF_CONT;
dma_addr += dma_len;
len -= dma_len;
}
@@ -846,7 +960,6 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
EFX_BUG_ON_PARANOID(!len);
buffer->len = len;
*final_buffer = buffer;
- return 0;
}
@@ -857,82 +970,102 @@ static int efx_tx_queue_insert(struct efx_tx_queue *tx_queue,
* a single fragment, and we know it doesn't cross a page boundary. It
* also allows us to not worry about end-of-packet etc.
*/
-static void efx_tso_put_header(struct efx_tx_queue *tx_queue,
- struct efx_tso_header *tsoh, unsigned len)
+static int efx_tso_put_header(struct efx_tx_queue *tx_queue,
+ struct efx_tx_buffer *buffer, u8 *header)
{
- struct efx_tx_buffer *buffer;
-
- buffer = &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask];
- efx_tsoh_free(tx_queue, buffer);
- EFX_BUG_ON_PARANOID(buffer->len);
- EFX_BUG_ON_PARANOID(buffer->unmap_len);
- EFX_BUG_ON_PARANOID(buffer->skb);
- EFX_BUG_ON_PARANOID(!buffer->continuation);
- EFX_BUG_ON_PARANOID(buffer->tsoh);
- buffer->len = len;
- buffer->dma_addr = tsoh->dma_addr;
- buffer->tsoh = tsoh;
+ if (unlikely(buffer->flags & EFX_TX_BUF_HEAP)) {
+ buffer->dma_addr = dma_map_single(&tx_queue->efx->pci_dev->dev,
+ header, buffer->len,
+ DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(&tx_queue->efx->pci_dev->dev,
+ buffer->dma_addr))) {
+ kfree(buffer->heap_buf);
+ buffer->len = 0;
+ buffer->flags = 0;
+ return -ENOMEM;
+ }
+ buffer->unmap_len = buffer->len;
+ buffer->dma_offset = 0;
+ buffer->flags |= EFX_TX_BUF_MAP_SINGLE;
+ }
++tx_queue->insert_count;
+ return 0;
}
-/* Remove descriptors put into a tx_queue. */
+/* Remove buffers put into a tx_queue. None of the buffers must have
+ * an skb attached.
+ */
static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue)
{
struct efx_tx_buffer *buffer;
- dma_addr_t unmap_addr;
/* Work backwards until we hit the original insert pointer value */
while (tx_queue->insert_count != tx_queue->write_count) {
--tx_queue->insert_count;
- buffer = &tx_queue->buffer[tx_queue->insert_count &
- tx_queue->ptr_mask];
- efx_tsoh_free(tx_queue, buffer);
- EFX_BUG_ON_PARANOID(buffer->skb);
- if (buffer->unmap_len) {
- unmap_addr = (buffer->dma_addr + buffer->len -
- buffer->unmap_len);
- if (buffer->unmap_single)
- pci_unmap_single(tx_queue->efx->pci_dev,
- unmap_addr, buffer->unmap_len,
- PCI_DMA_TODEVICE);
- else
- pci_unmap_page(tx_queue->efx->pci_dev,
- unmap_addr, buffer->unmap_len,
- PCI_DMA_TODEVICE);
- buffer->unmap_len = 0;
- }
- buffer->len = 0;
- buffer->continuation = true;
+ buffer = __efx_tx_queue_get_insert_buffer(tx_queue);
+ efx_dequeue_buffer(tx_queue, buffer, NULL, NULL);
}
}
/* Parse the SKB header and initialise state. */
-static void tso_start(struct tso_state *st, const struct sk_buff *skb)
+static int tso_start(struct tso_state *st, struct efx_nic *efx,
+ const struct sk_buff *skb)
{
- /* All ethernet/IP/TCP headers combined size is TCP header size
- * plus offset of TCP header relative to start of packet.
- */
- st->header_len = ((tcp_hdr(skb)->doff << 2u)
- + PTR_DIFF(tcp_hdr(skb), skb->data));
- st->full_packet_size = st->header_len + skb_shinfo(skb)->gso_size;
+ bool use_opt_desc = efx_nic_rev(efx) >= EFX_REV_HUNT_A0;
+ struct device *dma_dev = &efx->pci_dev->dev;
+ unsigned int header_len, in_len;
+ dma_addr_t dma_addr;
- if (st->protocol == htons(ETH_P_IP))
+ st->ip_off = skb_network_header(skb) - skb->data;
+ st->tcp_off = skb_transport_header(skb) - skb->data;
+ header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u);
+ in_len = skb_headlen(skb) - header_len;
+ st->header_len = header_len;
+ st->in_len = in_len;
+ if (st->protocol == htons(ETH_P_IP)) {
+ st->ip_base_len = st->header_len - st->ip_off;
st->ipv4_id = ntohs(ip_hdr(skb)->id);
- else
+ } else {
+ st->ip_base_len = st->header_len - st->tcp_off;
st->ipv4_id = 0;
+ }
st->seqnum = ntohl(tcp_hdr(skb)->seq);
EFX_BUG_ON_PARANOID(tcp_hdr(skb)->urg);
EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn);
EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst);
- st->packet_space = st->full_packet_size;
- st->out_len = skb->len - st->header_len;
- st->unmap_len = 0;
- st->unmap_single = false;
+ st->out_len = skb->len - header_len;
+
+ if (!use_opt_desc) {
+ st->header_unmap_len = 0;
+
+ if (likely(in_len == 0)) {
+ st->dma_flags = 0;
+ st->unmap_len = 0;
+ return 0;
+ }
+
+ dma_addr = dma_map_single(dma_dev, skb->data + header_len,
+ in_len, DMA_TO_DEVICE);
+ st->dma_flags = EFX_TX_BUF_MAP_SINGLE;
+ st->dma_addr = dma_addr;
+ st->unmap_addr = dma_addr;
+ st->unmap_len = in_len;
+ } else {
+ dma_addr = dma_map_single(dma_dev, skb->data,
+ skb_headlen(skb), DMA_TO_DEVICE);
+ st->header_dma_addr = dma_addr;
+ st->header_unmap_len = skb_headlen(skb);
+ st->dma_flags = 0;
+ st->dma_addr = dma_addr + header_len;
+ st->unmap_len = 0;
+ }
+
+ return unlikely(dma_mapping_error(dma_dev, dma_addr)) ? -ENOMEM : 0;
}
static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
@@ -941,7 +1074,7 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
st->unmap_addr = skb_frag_dma_map(&efx->pci_dev->dev, frag, 0,
skb_frag_size(frag), DMA_TO_DEVICE);
if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) {
- st->unmap_single = false;
+ st->dma_flags = 0;
st->unmap_len = skb_frag_size(frag);
st->in_len = skb_frag_size(frag);
st->dma_addr = st->unmap_addr;
@@ -950,24 +1083,6 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx,
return -ENOMEM;
}
-static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
- const struct sk_buff *skb)
-{
- int hl = st->header_len;
- int len = skb_headlen(skb) - hl;
-
- st->unmap_addr = pci_map_single(efx->pci_dev, skb->data + hl,
- len, PCI_DMA_TODEVICE);
- if (likely(!pci_dma_mapping_error(efx->pci_dev, st->unmap_addr))) {
- st->unmap_single = true;
- st->unmap_len = len;
- st->in_len = len;
- st->dma_addr = st->unmap_addr;
- return 0;
- }
- return -ENOMEM;
-}
-
/**
* tso_fill_packet_with_fragment - form descriptors for the current fragment
@@ -976,20 +1091,19 @@ static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx,
* @st: TSO state
*
* Form descriptors for the current fragment, until we reach the end
- * of fragment or end-of-packet. Return 0 on success, 1 if not enough
- * space in @tx_queue.
+ * of fragment or end-of-packet.
*/
-static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
- const struct sk_buff *skb,
- struct tso_state *st)
+static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
+ const struct sk_buff *skb,
+ struct tso_state *st)
{
struct efx_tx_buffer *buffer;
- int n, end_of_packet, rc;
+ int n;
if (st->in_len == 0)
- return 0;
+ return;
if (st->packet_space == 0)
- return 0;
+ return;
EFX_BUG_ON_PARANOID(st->in_len <= 0);
EFX_BUG_ON_PARANOID(st->packet_space <= 0);
@@ -1000,25 +1114,25 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
st->out_len -= n;
st->in_len -= n;
- rc = efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
- if (likely(rc == 0)) {
- if (st->out_len == 0)
- /* Transfer ownership of the skb */
- buffer->skb = skb;
+ efx_tx_queue_insert(tx_queue, st->dma_addr, n, &buffer);
- end_of_packet = st->out_len == 0 || st->packet_space == 0;
- buffer->continuation = !end_of_packet;
+ if (st->out_len == 0) {
+ /* Transfer ownership of the skb */
+ buffer->skb = skb;
+ buffer->flags = EFX_TX_BUF_SKB;
+ } else if (st->packet_space != 0) {
+ buffer->flags = EFX_TX_BUF_CONT;
+ }
- if (st->in_len == 0) {
- /* Transfer ownership of the pci mapping */
- buffer->unmap_len = st->unmap_len;
- buffer->unmap_single = st->unmap_single;
- st->unmap_len = 0;
- }
+ if (st->in_len == 0) {
+ /* Transfer ownership of the DMA mapping */
+ buffer->unmap_len = st->unmap_len;
+ buffer->dma_offset = buffer->unmap_len - buffer->len;
+ buffer->flags |= st->dma_flags;
+ st->unmap_len = 0;
}
st->dma_addr += n;
- return rc;
}
@@ -1029,75 +1143,107 @@ static int tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue,
* @st: TSO state
*
* Generate a new header and prepare for the new packet. Return 0 on
- * success, or -1 if failed to alloc header.
+ * success, or -%ENOMEM if failed to alloc header.
*/
static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
const struct sk_buff *skb,
struct tso_state *st)
{
- struct efx_tso_header *tsoh;
- struct tcphdr *tsoh_th;
- unsigned ip_length;
- u8 *header;
-
- /* Allocate a DMA-mapped header buffer. */
- if (likely(TSOH_SIZE(st->header_len) <= TSOH_STD_SIZE)) {
- if (tx_queue->tso_headers_free == NULL) {
- if (efx_tsoh_block_alloc(tx_queue))
- return -1;
- }
- EFX_BUG_ON_PARANOID(!tx_queue->tso_headers_free);
- tsoh = tx_queue->tso_headers_free;
- tx_queue->tso_headers_free = tsoh->next;
- tsoh->unmap_len = 0;
+ struct efx_tx_buffer *buffer =
+ efx_tx_queue_get_insert_buffer(tx_queue);
+ bool is_last = st->out_len <= skb_shinfo(skb)->gso_size;
+ u8 tcp_flags_clear;
+
+ if (!is_last) {
+ st->packet_space = skb_shinfo(skb)->gso_size;
+ tcp_flags_clear = 0x09; /* mask out FIN and PSH */
} else {
- tx_queue->tso_long_headers++;
- tsoh = efx_tsoh_heap_alloc(tx_queue, st->header_len);
- if (unlikely(!tsoh))
- return -1;
+ st->packet_space = st->out_len;
+ tcp_flags_clear = 0x00;
}
- header = TSOH_BUFFER(tsoh);
- tsoh_th = (struct tcphdr *)(header + SKB_TCP_OFF(skb));
+ if (!st->header_unmap_len) {
+ /* Allocate and insert a DMA-mapped header buffer. */
+ struct tcphdr *tsoh_th;
+ unsigned ip_length;
+ u8 *header;
+ int rc;
- /* Copy and update the headers. */
- memcpy(header, skb->data, st->header_len);
+ header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len);
+ if (!header)
+ return -ENOMEM;
- tsoh_th->seq = htonl(st->seqnum);
- st->seqnum += skb_shinfo(skb)->gso_size;
- if (st->out_len > skb_shinfo(skb)->gso_size) {
- /* This packet will not finish the TSO burst. */
- ip_length = st->full_packet_size - ETH_HDR_LEN(skb);
- tsoh_th->fin = 0;
- tsoh_th->psh = 0;
- } else {
- /* This packet will be the last in the TSO burst. */
- ip_length = st->header_len - ETH_HDR_LEN(skb) + st->out_len;
- tsoh_th->fin = tcp_hdr(skb)->fin;
- tsoh_th->psh = tcp_hdr(skb)->psh;
- }
+ tsoh_th = (struct tcphdr *)(header + st->tcp_off);
- if (st->protocol == htons(ETH_P_IP)) {
- struct iphdr *tsoh_iph =
- (struct iphdr *)(header + SKB_IPV4_OFF(skb));
+ /* Copy and update the headers. */
+ memcpy(header, skb->data, st->header_len);
+
+ tsoh_th->seq = htonl(st->seqnum);
+ ((u8 *)tsoh_th)[13] &= ~tcp_flags_clear;
- tsoh_iph->tot_len = htons(ip_length);
+ ip_length = st->ip_base_len + st->packet_space;
- /* Linux leaves suitable gaps in the IP ID space for us to fill. */
- tsoh_iph->id = htons(st->ipv4_id);
- st->ipv4_id++;
+ if (st->protocol == htons(ETH_P_IP)) {
+ struct iphdr *tsoh_iph =
+ (struct iphdr *)(header + st->ip_off);
+
+ tsoh_iph->tot_len = htons(ip_length);
+ tsoh_iph->id = htons(st->ipv4_id);
+ } else {
+ struct ipv6hdr *tsoh_iph =
+ (struct ipv6hdr *)(header + st->ip_off);
+
+ tsoh_iph->payload_len = htons(ip_length);
+ }
+
+ rc = efx_tso_put_header(tx_queue, buffer, header);
+ if (unlikely(rc))
+ return rc;
} else {
- struct ipv6hdr *tsoh_iph =
- (struct ipv6hdr *)(header + SKB_IPV6_OFF(skb));
+ /* Send the original headers with a TSO option descriptor
+ * in front
+ */
+ u8 tcp_flags = ((u8 *)tcp_hdr(skb))[13] & ~tcp_flags_clear;
- tsoh_iph->payload_len = htons(ip_length - sizeof(*tsoh_iph));
+ buffer->flags = EFX_TX_BUF_OPTION;
+ buffer->len = 0;
+ buffer->unmap_len = 0;
+ EFX_POPULATE_QWORD_5(buffer->option,
+ ESF_DZ_TX_DESC_IS_OPT, 1,
+ ESF_DZ_TX_OPTION_TYPE,
+ ESE_DZ_TX_OPTION_DESC_TSO,
+ ESF_DZ_TX_TSO_TCP_FLAGS, tcp_flags,
+ ESF_DZ_TX_TSO_IP_ID, st->ipv4_id,
+ ESF_DZ_TX_TSO_TCP_SEQNO, st->seqnum);
+ ++tx_queue->insert_count;
+
+ /* We mapped the headers in tso_start(). Unmap them
+ * when the last segment is completed.
+ */
+ buffer = efx_tx_queue_get_insert_buffer(tx_queue);
+ buffer->dma_addr = st->header_dma_addr;
+ buffer->len = st->header_len;
+ if (is_last) {
+ buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_MAP_SINGLE;
+ buffer->unmap_len = st->header_unmap_len;
+ buffer->dma_offset = 0;
+ /* Ensure we only unmap them once in case of a
+ * later DMA mapping error and rollback
+ */
+ st->header_unmap_len = 0;
+ } else {
+ buffer->flags = EFX_TX_BUF_CONT;
+ buffer->unmap_len = 0;
+ }
+ ++tx_queue->insert_count;
}
- st->packet_space = skb_shinfo(skb)->gso_size;
- ++tx_queue->tso_packets;
+ st->seqnum += skb_shinfo(skb)->gso_size;
+
+ /* Linux leaves suitable gaps in the IP ID space for us to fill. */
+ ++st->ipv4_id;
- /* Form a descriptor for this header. */
- efx_tso_put_header(tx_queue, tsoh, st->header_len);
+ ++tx_queue->tso_packets;
return 0;
}
@@ -1112,13 +1258,13 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue,
*
* Add socket buffer @skb to @tx_queue, doing TSO or return != 0 if
* @skb was not enqueued. In all cases @skb is consumed. Return
- * %NETDEV_TX_OK or %NETDEV_TX_BUSY.
+ * %NETDEV_TX_OK.
*/
static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
struct sk_buff *skb)
{
struct efx_nic *efx = tx_queue->efx;
- int frag_i, rc, rc2 = NETDEV_TX_OK;
+ int frag_i, rc;
struct tso_state state;
/* Find the packet protocol and sanity-check it */
@@ -1126,12 +1272,11 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count);
- tso_start(&state, skb);
+ rc = tso_start(&state, efx, skb);
+ if (rc)
+ goto mem_err;
- /* Assume that skb header area contains exactly the headers, and
- * all payload is in the frag list.
- */
- if (skb_headlen(skb) == state.header_len) {
+ if (likely(state.in_len == 0)) {
/* Grab the first payload fragment. */
EFX_BUG_ON_PARANOID(skb_shinfo(skb)->nr_frags < 1);
frag_i = 0;
@@ -1140,9 +1285,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
if (rc)
goto mem_err;
} else {
- rc = tso_get_head_fragment(&state, efx, skb);
- if (rc)
- goto mem_err;
+ /* Payload starts in the header area. */
frag_i = -1;
}
@@ -1150,11 +1293,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
goto mem_err;
while (1) {
- rc = tso_fill_packet_with_fragment(tx_queue, skb, &state);
- if (unlikely(rc)) {
- rc2 = NETDEV_TX_BUSY;
- goto unwind;
- }
+ tso_fill_packet_with_fragment(tx_queue, skb, &state);
/* Move onto the next fragment? */
if (state.in_len == 0) {
@@ -1178,45 +1317,31 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue,
/* Pass off to hardware */
efx_nic_push_buffers(tx_queue);
+ efx_tx_maybe_stop_queue(tx_queue);
+
tx_queue->tso_bursts++;
return NETDEV_TX_OK;
mem_err:
netif_err(efx, tx_err, efx->net_dev,
- "Out of memory for TSO headers, or PCI mapping error\n");
+ "Out of memory for TSO headers, or DMA mapping error\n");
dev_kfree_skb_any(skb);
- unwind:
/* Free the DMA mapping we were in the process of writing out */
if (state.unmap_len) {
- if (state.unmap_single)
- pci_unmap_single(efx->pci_dev, state.unmap_addr,
- state.unmap_len, PCI_DMA_TODEVICE);
+ if (state.dma_flags & EFX_TX_BUF_MAP_SINGLE)
+ dma_unmap_single(&efx->pci_dev->dev, state.unmap_addr,
+ state.unmap_len, DMA_TO_DEVICE);
else
- pci_unmap_page(efx->pci_dev, state.unmap_addr,
- state.unmap_len, PCI_DMA_TODEVICE);
+ dma_unmap_page(&efx->pci_dev->dev, state.unmap_addr,
+ state.unmap_len, DMA_TO_DEVICE);
}
- efx_enqueue_unwind(tx_queue);
- return rc2;
-}
-
+ /* Free the header DMA mapping, if using option descriptors */
+ if (state.header_unmap_len)
+ dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr,
+ state.header_unmap_len, DMA_TO_DEVICE);
-/*
- * Free up all TSO datastructures associated with tx_queue. This
- * routine should be called only once the tx_queue is both empty and
- * will no longer be used.
- */
-static void efx_fini_tso(struct efx_tx_queue *tx_queue)
-{
- unsigned i;
-
- if (tx_queue->buffer) {
- for (i = 0; i <= tx_queue->ptr_mask; ++i)
- efx_tsoh_free(tx_queue, &tx_queue->buffer[i]);
- }
-
- while (tx_queue->tso_headers_free != NULL)
- efx_tsoh_block_free(tx_queue, tx_queue->tso_headers_free,
- tx_queue->efx->pci_dev);
+ efx_enqueue_unwind(tx_queue);
+ return NETDEV_TX_OK;
}
diff --git a/drivers/net/ethernet/sfc/txc43128_phy.c b/drivers/net/ethernet/sfc/txc43128_phy.c
index 7c21b334a75..3d5ee325988 100644
--- a/drivers/net/ethernet/sfc/txc43128_phy.c
+++ b/drivers/net/ethernet/sfc/txc43128_phy.c
@@ -1,5 +1,5 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
+ * Driver for Solarflare network controllers and boards
* Copyright 2006-2011 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
@@ -512,7 +512,7 @@ static bool txc43128_phy_poll(struct efx_nic *efx)
return efx->link_state.up != was_up;
}
-static const char *txc43128_test_names[] = {
+static const char *const txc43128_test_names[] = {
"bist"
};
diff --git a/drivers/net/ethernet/sfc/vfdi.h b/drivers/net/ethernet/sfc/vfdi.h
new file mode 100644
index 00000000000..ae044f44936
--- /dev/null
+++ b/drivers/net/ethernet/sfc/vfdi.h
@@ -0,0 +1,255 @@
+/****************************************************************************
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2010-2012 Solarflare Communications Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+#ifndef _VFDI_H
+#define _VFDI_H
+
+/**
+ * DOC: Virtual Function Driver Interface
+ *
+ * This file contains software structures used to form a two way
+ * communication channel between the VF driver and the PF driver,
+ * named Virtual Function Driver Interface (VFDI).
+ *
+ * For the purposes of VFDI, a page is a memory region with size and
+ * alignment of 4K. All addresses are DMA addresses to be used within
+ * the domain of the relevant VF.
+ *
+ * The only hardware-defined channels for a VF driver to communicate
+ * with the PF driver are the event mailboxes (%FR_CZ_USR_EV
+ * registers). Writing to these registers generates an event with
+ * EV_CODE = EV_CODE_USR_EV, USER_QID set to the index of the mailbox
+ * and USER_EV_REG_VALUE set to the value written. The PF driver may
+ * direct or disable delivery of these events by setting
+ * %FR_CZ_USR_EV_CFG.
+ *
+ * The PF driver can send arbitrary events to arbitrary event queues.
+ * However, for consistency, VFDI events from the PF are defined to
+ * follow the same form and be sent to the first event queue assigned
+ * to the VF while that queue is enabled by the VF driver.
+ *
+ * The general form of the variable bits of VFDI events is:
+ *
+ * 0 16 24 31
+ * | DATA | TYPE | SEQ |
+ *
+ * SEQ is a sequence number which should be incremented by 1 (modulo
+ * 256) for each event. The sequence numbers used in each direction
+ * are independent.
+ *
+ * The VF submits requests of type &struct vfdi_req by sending the
+ * address of the request (ADDR) in a series of 4 events:
+ *
+ * 0 16 24 31
+ * | ADDR[0:15] | VFDI_EV_TYPE_REQ_WORD0 | SEQ |
+ * | ADDR[16:31] | VFDI_EV_TYPE_REQ_WORD1 | SEQ+1 |
+ * | ADDR[32:47] | VFDI_EV_TYPE_REQ_WORD2 | SEQ+2 |
+ * | ADDR[48:63] | VFDI_EV_TYPE_REQ_WORD3 | SEQ+3 |
+ *
+ * The address must be page-aligned. After receiving such a valid
+ * series of events, the PF driver will attempt to read the request
+ * and write a response to the same address. In case of an invalid
+ * sequence of events or a DMA error, there will be no response.
+ *
+ * The VF driver may request that the PF driver writes status
+ * information into its domain asynchronously. After writing the
+ * status, the PF driver will send an event of the form:
+ *
+ * 0 16 24 31
+ * | reserved | VFDI_EV_TYPE_STATUS | SEQ |
+ *
+ * In case the VF must be reset for any reason, the PF driver will
+ * send an event of the form:
+ *
+ * 0 16 24 31
+ * | reserved | VFDI_EV_TYPE_RESET | SEQ |
+ *
+ * It is then the responsibility of the VF driver to request
+ * reinitialisation of its queues.
+ */
+#define VFDI_EV_SEQ_LBN 24
+#define VFDI_EV_SEQ_WIDTH 8
+#define VFDI_EV_TYPE_LBN 16
+#define VFDI_EV_TYPE_WIDTH 8
+#define VFDI_EV_TYPE_REQ_WORD0 0
+#define VFDI_EV_TYPE_REQ_WORD1 1
+#define VFDI_EV_TYPE_REQ_WORD2 2
+#define VFDI_EV_TYPE_REQ_WORD3 3
+#define VFDI_EV_TYPE_STATUS 4
+#define VFDI_EV_TYPE_RESET 5
+#define VFDI_EV_DATA_LBN 0
+#define VFDI_EV_DATA_WIDTH 16
+
+struct vfdi_endpoint {
+ u8 mac_addr[ETH_ALEN];
+ __be16 tci;
+};
+
+/**
+ * enum vfdi_op - VFDI operation enumeration
+ * @VFDI_OP_RESPONSE: Indicates a response to the request.
+ * @VFDI_OP_INIT_EVQ: Initialize SRAM entries and initialize an EVQ.
+ * @VFDI_OP_INIT_RXQ: Initialize SRAM entries and initialize an RXQ.
+ * @VFDI_OP_INIT_TXQ: Initialize SRAM entries and initialize a TXQ.
+ * @VFDI_OP_FINI_ALL_QUEUES: Flush all queues, finalize all queues, then
+ * finalize the SRAM entries.
+ * @VFDI_OP_INSERT_FILTER: Insert a MAC filter targetting the given RXQ.
+ * @VFDI_OP_REMOVE_ALL_FILTERS: Remove all filters.
+ * @VFDI_OP_SET_STATUS_PAGE: Set the DMA page(s) used for status updates
+ * from PF and write the initial status.
+ * @VFDI_OP_CLEAR_STATUS_PAGE: Clear the DMA page(s) used for status
+ * updates from PF.
+ */
+enum vfdi_op {
+ VFDI_OP_RESPONSE = 0,
+ VFDI_OP_INIT_EVQ = 1,
+ VFDI_OP_INIT_RXQ = 2,
+ VFDI_OP_INIT_TXQ = 3,
+ VFDI_OP_FINI_ALL_QUEUES = 4,
+ VFDI_OP_INSERT_FILTER = 5,
+ VFDI_OP_REMOVE_ALL_FILTERS = 6,
+ VFDI_OP_SET_STATUS_PAGE = 7,
+ VFDI_OP_CLEAR_STATUS_PAGE = 8,
+ VFDI_OP_LIMIT,
+};
+
+/* Response codes for VFDI operations. Other values may be used in future. */
+#define VFDI_RC_SUCCESS 0
+#define VFDI_RC_ENOMEM (-12)
+#define VFDI_RC_EINVAL (-22)
+#define VFDI_RC_EOPNOTSUPP (-95)
+#define VFDI_RC_ETIMEDOUT (-110)
+
+/**
+ * struct vfdi_req - Request from VF driver to PF driver
+ * @op: Operation code or response indicator, taken from &enum vfdi_op.
+ * @rc: Response code. Set to 0 on success or a negative error code on failure.
+ * @u.init_evq.index: Index of event queue to create.
+ * @u.init_evq.buf_count: Number of 4k buffers backing event queue.
+ * @u.init_evq.addr: Array of length %u.init_evq.buf_count containing DMA
+ * address of each page backing the event queue.
+ * @u.init_rxq.index: Index of receive queue to create.
+ * @u.init_rxq.buf_count: Number of 4k buffers backing receive queue.
+ * @u.init_rxq.evq: Instance of event queue to target receive events at.
+ * @u.init_rxq.label: Label used in receive events.
+ * @u.init_rxq.flags: Unused.
+ * @u.init_rxq.addr: Array of length %u.init_rxq.buf_count containing DMA
+ * address of each page backing the receive queue.
+ * @u.init_txq.index: Index of transmit queue to create.
+ * @u.init_txq.buf_count: Number of 4k buffers backing transmit queue.
+ * @u.init_txq.evq: Instance of event queue to target transmit completion
+ * events at.
+ * @u.init_txq.label: Label used in transmit completion events.
+ * @u.init_txq.flags: Checksum offload flags.
+ * @u.init_txq.addr: Array of length %u.init_txq.buf_count containing DMA
+ * address of each page backing the transmit queue.
+ * @u.mac_filter.rxq: Insert MAC filter at VF local address/VLAN targetting
+ * all traffic at this receive queue.
+ * @u.mac_filter.flags: MAC filter flags.
+ * @u.set_status_page.dma_addr: Base address for the &struct vfdi_status.
+ * This address must be page-aligned and the PF may write up to a
+ * whole page (allowing for extension of the structure).
+ * @u.set_status_page.peer_page_count: Number of additional pages the VF
+ * has provided into which peer addresses may be DMAd.
+ * @u.set_status_page.peer_page_addr: Array of DMA addresses of pages.
+ * If the number of peers exceeds 256, then the VF must provide
+ * additional pages in this array. The PF will then DMA up to
+ * 512 vfdi_endpoint structures into each page. These addresses
+ * must be page-aligned.
+ */
+struct vfdi_req {
+ u32 op;
+ u32 reserved1;
+ s32 rc;
+ u32 reserved2;
+ union {
+ struct {
+ u32 index;
+ u32 buf_count;
+ u64 addr[];
+ } init_evq;
+ struct {
+ u32 index;
+ u32 buf_count;
+ u32 evq;
+ u32 label;
+ u32 flags;
+#define VFDI_RXQ_FLAG_SCATTER_EN 1
+ u32 reserved;
+ u64 addr[];
+ } init_rxq;
+ struct {
+ u32 index;
+ u32 buf_count;
+ u32 evq;
+ u32 label;
+ u32 flags;
+#define VFDI_TXQ_FLAG_IP_CSUM_DIS 1
+#define VFDI_TXQ_FLAG_TCPUDP_CSUM_DIS 2
+ u32 reserved;
+ u64 addr[];
+ } init_txq;
+ struct {
+ u32 rxq;
+ u32 flags;
+#define VFDI_MAC_FILTER_FLAG_RSS 1
+#define VFDI_MAC_FILTER_FLAG_SCATTER 2
+ } mac_filter;
+ struct {
+ u64 dma_addr;
+ u64 peer_page_count;
+ u64 peer_page_addr[];
+ } set_status_page;
+ } u;
+};
+
+/**
+ * struct vfdi_status - Status provided by PF driver to VF driver
+ * @generation_start: A generation count DMA'd to VF *before* the
+ * rest of the structure.
+ * @generation_end: A generation count DMA'd to VF *after* the
+ * rest of the structure.
+ * @version: Version of this structure; currently set to 1. Later
+ * versions must either be layout-compatible or only be sent to VFs
+ * that specifically request them.
+ * @length: Total length of this structure including embedded tables
+ * @vi_scale: log2 the number of VIs available on this VF. This quantity
+ * is used by the hardware for register decoding.
+ * @max_tx_channels: The maximum number of transmit queues the VF can use.
+ * @rss_rxq_count: The number of receive queues present in the shared RSS
+ * indirection table.
+ * @peer_count: Total number of peers in the complete peer list. If larger
+ * than ARRAY_SIZE(%peers), then the VF must provide sufficient
+ * additional pages each of which is filled with vfdi_endpoint structures.
+ * @local: The MAC address and outer VLAN tag of *this* VF
+ * @peers: Table of peer addresses. The @tci fields in these structures
+ * are currently unused and must be ignored. Additional peers are
+ * written into any additional pages provided by the VF.
+ * @timer_quantum_ns: Timer quantum (nominal period between timer ticks)
+ * for interrupt moderation timers, in nanoseconds. This member is only
+ * present if @length is sufficiently large.
+ */
+struct vfdi_status {
+ u32 generation_start;
+ u32 generation_end;
+ u32 version;
+ u32 length;
+ u8 vi_scale;
+ u8 max_tx_channels;
+ u8 rss_rxq_count;
+ u8 reserved1;
+ u16 peer_count;
+ u16 reserved2;
+ struct vfdi_endpoint local;
+ struct vfdi_endpoint peers[256];
+
+ /* Members below here extend version 1 of this structure */
+ u32 timer_quantum_ns;
+};
+
+#endif
diff --git a/drivers/net/ethernet/sfc/workarounds.h b/drivers/net/ethernet/sfc/workarounds.h
index e4dd3a7f304..2310b75d4ec 100644
--- a/drivers/net/ethernet/sfc/workarounds.h
+++ b/drivers/net/ethernet/sfc/workarounds.h
@@ -1,6 +1,6 @@
/****************************************************************************
- * Driver for Solarflare Solarstorm network controllers and boards
- * Copyright 2006-2010 Solarflare Communications Inc.
+ * Driver for Solarflare network controllers and boards
+ * Copyright 2006-2013 Solarflare Communications Inc.
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 as published
@@ -15,27 +15,15 @@
* Bug numbers are from Solarflare's Bugzilla.
*/
-#define EFX_WORKAROUND_ALWAYS(efx) 1
#define EFX_WORKAROUND_FALCON_A(efx) (efx_nic_rev(efx) <= EFX_REV_FALCON_A1)
#define EFX_WORKAROUND_FALCON_AB(efx) (efx_nic_rev(efx) <= EFX_REV_FALCON_B0)
#define EFX_WORKAROUND_SIENA(efx) (efx_nic_rev(efx) == EFX_REV_SIENA_A0)
#define EFX_WORKAROUND_10G(efx) 1
-/* XAUI resets if link not detected */
-#define EFX_WORKAROUND_5147 EFX_WORKAROUND_ALWAYS
-/* RX PCIe double split performance issue */
-#define EFX_WORKAROUND_7575 EFX_WORKAROUND_ALWAYS
/* Bit-bashed I2C reads cause performance drop */
#define EFX_WORKAROUND_7884 EFX_WORKAROUND_10G
-/* TX_EV_PKT_ERR can be caused by a dangling TX descriptor
- * or a PCIe error (bug 11028) */
-#define EFX_WORKAROUND_10727 EFX_WORKAROUND_ALWAYS
-/* Transmit flow control may get disabled */
-#define EFX_WORKAROUND_11482 EFX_WORKAROUND_FALCON_AB
/* Truncated IPv4 packets can confuse the TX packet parser */
#define EFX_WORKAROUND_15592 EFX_WORKAROUND_FALCON_AB
-/* Legacy ISR read can return zero once */
-#define EFX_WORKAROUND_15783 EFX_WORKAROUND_ALWAYS
/* Legacy interrupt storm when interrupt fifo fills */
#define EFX_WORKAROUND_17213 EFX_WORKAROUND_SIENA
@@ -56,4 +44,10 @@
/* Leak overlength packets rather than free */
#define EFX_WORKAROUND_8071 EFX_WORKAROUND_FALCON_A
+/* Lockup when writing event block registers at gen2/gen3 */
+#define EFX_EF10_WORKAROUND_35388(efx) \
+ (((struct efx_ef10_nic_data *)efx->nic_data)->workaround_35388)
+#define EFX_WORKAROUND_35388(efx) \
+ (efx_nic_rev(efx) == EFX_REV_HUNT_A0 && EFX_EF10_WORKAROUND_35388(efx))
+
#endif /* EFX_WORKAROUNDS_H */