| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 16 Feb 2012 00:52:30 +0000
From: Ben Hutchings <bhutchings@...arflare.com>
To: David Miller <davem@...emloft.net>
CC: <netdev@...r.kernel.org>, <linux-net-drivers@...arflare.com>,
Shradha Shah <sshah@...arflare.com>
Subject: [PATCH net-next 19/19] sfc: Add SR-IOV back-end support for SFC9000
family
On the SFC9000 family, each port has 1024 Virtual Interfaces (VIs),
each with an RX queue, a TX queue, an event queue and a mailbox
register. These may be assigned to up to 127 SR-IOV virtual functions
per port, with up to 64 VIs per VF.
We allocate an extra channel (IRQ and event queue only) to receive
requests from VF drivers.
There is a per-port limit of 4 concurrent RX queue flushes, and queue
flushes may be initiated by the MC in response to a Function Level
Reset (FLR) of a VF. Therefore, when SR-IOV is in use, we submit all
flush requests via the MC.
The RSS indirection table is shared with VFs, so the number of RX
queues used in the PF is limited to the number of VIs per VF.
This is almost entirely the work of Steve Hodgson, formerly
shodgson@...arflare.com.
Signed-off-by: Ben Hutchings <bhutchings@...arflare.com>
---
drivers/net/ethernet/sfc/Kconfig | 8 +
drivers/net/ethernet/sfc/Makefile | 1 +
drivers/net/ethernet/sfc/efx.c | 70 ++-
drivers/net/ethernet/sfc/ethtool.c | 3 +-
drivers/net/ethernet/sfc/mcdi.c | 34 +
drivers/net/ethernet/sfc/mcdi.h | 2 +
drivers/net/ethernet/sfc/mcdi_mac.c | 2 +-
drivers/net/ethernet/sfc/net_driver.h | 32 +-
drivers/net/ethernet/sfc/nic.c | 79 ++-
drivers/net/ethernet/sfc/nic.h | 89 ++
drivers/net/ethernet/sfc/siena.c | 2 +
drivers/net/ethernet/sfc/siena_sriov.c | 1642 ++++++++++++++++++++++++++++++++
drivers/net/ethernet/sfc/vfdi.h | 254 +++++
13 files changed, 2192 insertions(+), 26 deletions(-)
create mode 100644 drivers/net/ethernet/sfc/siena_sriov.c
create mode 100644 drivers/net/ethernet/sfc/vfdi.h
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 8d42354..fb3cbc2 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -26,3 +26,11 @@ config SFC_MCDI_MON
----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 3fa2e25..ea1f8db 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -4,5 +4,6 @@ sfc-y += efx.o nic.o falcon.o siena.o tx.o rx.o filter.o \
tenxpress.o txc43128_phy.o falcon_boards.o \
mcdi.o mcdi_phy.o mcdi_mon.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/efx.c b/drivers/net/ethernet/sfc/efx.c
index c9c306a..ac571cf 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -1175,25 +1175,40 @@ static unsigned int efx_wanted_parallelism(struct efx_nic *efx)
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(&thread_mask, GFP_KERNEL))) {
- netif_warn(efx, probe, efx->net_dev,
- "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, thread_mask)) {
- ++count;
- cpumask_or(thread_mask, thread_mask,
- topology_thread_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(thread_mask);
return count;
}
@@ -1327,6 +1342,10 @@ static int efx_probe_interrupts(struct efx_nic *efx)
}
}
+ /* RSS might be usable on VFs even if it is disabled on the PF */
+ efx->rss_spread = (efx->n_rx_channels > 1 ?
+ efx->n_rx_channels : efx_vf_size(efx));
+
return 0;
}
@@ -1426,7 +1445,7 @@ static int efx_probe_nic(struct efx_nic *efx)
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);
@@ -1915,6 +1934,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data)
}
memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len);
+ efx_sriov_mac_address_changed(efx);
/* Reconfigure the MAC */
mutex_lock(&efx->mac_lock);
@@ -1981,6 +2001,12 @@ static const struct net_device_ops efx_netdev_ops = {
.ndo_set_mac_address = efx_set_mac_address,
.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
@@ -2150,6 +2176,7 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok)
efx_start_interrupts(efx, false);
efx_restore_filters(efx);
+ efx_sriov_reset(efx);
mutex_unlock(&efx->mac_lock);
@@ -2440,6 +2467,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev)
rtnl_unlock();
efx_stop_interrupts(efx, false);
+ efx_sriov_fini(efx);
efx_unregister_netdev(efx);
efx_mtd_remove(efx);
@@ -2581,6 +2609,11 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev,
if (rc)
goto fail4;
+ rc = efx_sriov_init(efx);
+ if (rc)
+ 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 */
@@ -2732,6 +2765,10 @@ 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;
@@ -2747,6 +2784,8 @@ 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;
@@ -2758,6 +2797,7 @@ 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);
}
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 8319115..f22f45f 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -1085,7 +1085,8 @@ 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));
}
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index 619f63a..17b6463 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -560,6 +560,9 @@ void efx_mcdi_process_event(struct efx_channel *channel,
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;
default:
netif_err(efx, hw, efx->net_dev, "Unknown MCDI event 0x%x\n",
@@ -1154,6 +1157,37 @@ fail:
return rc;
}
+int efx_mcdi_flush_rxqs(struct efx_nic *efx)
+{
+ struct efx_channel *channel;
+ struct efx_rx_queue *rx_queue;
+ __le32 *qid;
+ int rc, count;
+
+ qid = kmalloc(EFX_MAX_CHANNELS * sizeof(*qid), GFP_KERNEL);
+ if (qid == NULL)
+ return -ENOMEM;
+
+ 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);
+ qid[count++] = cpu_to_le32(
+ efx_rx_queue_index(rx_queue));
+ }
+ }
+ }
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_FLUSH_RX_QUEUES, (u8 *)qid,
+ count * sizeof(*qid), NULL, 0, NULL);
+ WARN_ON(rc > 0);
+
+ kfree(qid);
+
+ return rc;
+}
int efx_mcdi_wol_filter_reset(struct efx_nic *efx)
{
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index fbaa6ef..0bdf3e3 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -146,6 +146,8 @@ extern int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx,
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);
+extern int efx_mcdi_flush_rxqs(struct efx_nic *efx);
+extern int efx_mcdi_set_mac(struct efx_nic *efx);
extern int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr,
u32 dma_len, int enable, int clear);
extern int efx_mcdi_mac_reconfigure(struct efx_nic *efx);
diff --git a/drivers/net/ethernet/sfc/mcdi_mac.c b/drivers/net/ethernet/sfc/mcdi_mac.c
index 98afe1c..1003f30 100644
--- a/drivers/net/ethernet/sfc/mcdi_mac.c
+++ b/drivers/net/ethernet/sfc/mcdi_mac.c
@@ -12,7 +12,7 @@
#include "mcdi.h"
#include "mcdi_pcol.h"
-static int efx_mcdi_set_mac(struct efx_nic *efx)
+int efx_mcdi_set_mac(struct efx_nic *efx)
{
u32 reject, fcntl;
u8 cmdbytes[MC_CMD_SET_MAC_IN_LEN];
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 7870cef..3fbec45 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -24,6 +24,7 @@
#include <linux/device.h>
#include <linux/highmem.h>
#include <linux/workqueue.h>
+#include <linux/mutex.h>
#include <linux/vmalloc.h>
#include <linux/i2c.h>
@@ -54,7 +55,8 @@
#define EFX_MAX_CHANNELS 32U
#define EFX_MAX_RX_QUEUES EFX_MAX_CHANNELS
-#define EFX_MAX_EXTRA_CHANNELS 0U
+#define EFX_EXTRA_CHANNEL_IOV 0
+#define EFX_MAX_EXTRA_CHANNELS 1U
/* Checksum generation is a per-queue option in hardware, so each
* queue visible to the networking core is backed by two hardware TX
@@ -629,6 +631,8 @@ union efx_multicast_hash {
};
struct efx_filter_state;
+struct efx_vf;
+struct vfdi_status;
/**
* struct efx_nic - an Efx NIC
@@ -712,6 +716,17 @@ struct efx_filter_state;
* 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.
* @monitor_work: Hardware monitor workitem
* @biu_lock: BIU (bus interface unit) lock
* @last_irq_cpu: Last CPU to handle a possible test interrupt. This
@@ -762,6 +777,7 @@ struct efx_nic {
unsigned next_buffer_table;
unsigned n_channels;
unsigned n_rx_channels;
+ unsigned rss_spread;
unsigned tx_channel_offset;
unsigned n_tx_channels;
unsigned int rx_buffer_len;
@@ -820,6 +836,20 @@ struct efx_nic {
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
+
/* The following fields may be written more often */
struct delayed_work monitor_work ____cacheline_aligned_in_smp;
diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c
index 747cf94..2bf4283 100644
--- a/drivers/net/ethernet/sfc/nic.c
+++ b/drivers/net/ethernet/sfc/nic.c
@@ -264,6 +264,10 @@ static int efx_alloc_special_buffer(struct efx_nic *efx,
/* 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 "
@@ -693,6 +697,16 @@ int efx_nic_flush_queues(struct efx_nic *efx)
}
while (timeout && atomic_read(&efx->drain_pending) > 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
@@ -712,6 +726,7 @@ int efx_nic_flush_queues(struct efx_nic *efx)
}
}
+ wait:
timeout = wait_event_timeout(efx->flush_wq, efx_flush_wake(efx),
timeout);
}
@@ -1102,11 +1117,13 @@ efx_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
netif_vdbg(efx, hw, efx->net_dev, "channel %d TXQ %d flushed\n",
channel->channel, ev_sub_data);
efx_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_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,
@@ -1138,16 +1155,24 @@ efx_handle_driver_event(struct efx_channel *channel, efx_qword_t *event)
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);
+ 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_RX_DESC_FETCH);
+ } else
+ efx_sriov_desc_fetch_err(efx, ev_sub_data);
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);
+ 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_TX_DESC_FETCH);
+ } else
+ efx_sriov_desc_fetch_err(efx, ev_sub_data);
break;
default:
netif_vdbg(efx, hw, efx->net_dev,
@@ -1207,6 +1232,9 @@ int efx_nic_process_eventq(struct efx_channel *channel, int budget)
case FSE_AZ_EV_CODE_DRIVER_EV:
efx_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;
@@ -1609,6 +1637,15 @@ void efx_nic_fini_interrupt(struct efx_nic *efx)
free_irq(efx->legacy_irq, efx);
}
+/* 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_nic_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
{
unsigned vi_count, buftbl_min;
@@ -1622,6 +1659,32 @@ void efx_nic_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw)
* 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;
}
diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h
index 5df7da8..246c414 100644
--- a/drivers/net/ethernet/sfc/nic.h
+++ b/drivers/net/ethernet/sfc/nic.h
@@ -169,6 +169,95 @@ static inline struct efx_mcdi_mon *efx_mcdi_mon(struct efx_nic *efx)
}
#endif
+/*
+ * 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;
+}
+
+extern int efx_init_sriov(void);
+extern void efx_sriov_probe(struct efx_nic *efx);
+extern int efx_sriov_init(struct efx_nic *efx);
+extern void efx_sriov_mac_address_changed(struct efx_nic *efx);
+extern void efx_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+extern void efx_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event);
+extern void efx_sriov_event(struct efx_channel *channel, efx_qword_t *event);
+extern void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq);
+extern void efx_sriov_flr(struct efx_nic *efx, unsigned flr);
+extern void efx_sriov_reset(struct efx_nic *efx);
+extern void efx_sriov_fini(struct efx_nic *efx);
+extern 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
+
+extern int efx_sriov_set_vf_mac(struct net_device *dev, int vf, u8 *mac);
+extern int efx_sriov_set_vf_vlan(struct net_device *dev, int vf,
+ u16 vlan, u8 qos);
+extern int efx_sriov_get_vf_config(struct net_device *dev, int vf,
+ struct ifla_vf_info *ivf);
+extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf,
+ bool spoofchk);
+
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;
diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c
index 657f3fa..7bea790 100644
--- a/drivers/net/ethernet/sfc/siena.c
+++ b/drivers/net/ethernet/sfc/siena.c
@@ -313,6 +313,8 @@ static int siena_probe_nic(struct efx_nic *efx)
if (rc)
goto fail5;
+ efx_sriov_probe(efx);
+
return 0;
fail5:
diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c
new file mode 100644
index 0000000..5c6839e
--- /dev/null
+++ b/drivers/net/ethernet/sfc/siena_sriov.c
@@ -0,0 +1,1642 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm network controllers and boards
+ * Copyright 2010-2011 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 "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)
+
+/**
+ * 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)
+{
+ u8 inbuf[MC_CMD_SRIOV_IN_LEN];
+ u8 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, ®, FR_CZ_USR_EV_CFG);
+}
+
+static int efx_sriov_memcpy(struct efx_nic *efx, struct efx_memcpy_req *req,
+ unsigned int count)
+{
+ u8 *inbuf, *record;
+ unsigned int used;
+ u32 from_rid, from_hi, from_lo;
+ int rc;
+
+ mb(); /* Finish writing source/reading dest before DMA starts */
+
+ used = MC_CMD_MEMCPY_IN_LEN(count);
+ if (WARN_ON(used > MCDI_CTL_SDU_LEN_MAX))
+ return -ENOBUFS;
+
+ /* Allocate room for the largest request */
+ inbuf = kzalloc(MCDI_CTL_SDU_LEN_MAX, GFP_KERNEL);
+ if (inbuf == NULL)
+ return -ENOMEM;
+
+ record = inbuf;
+ MCDI_SET_DWORD(record, MEMCPY_IN_RECORD, count);
+ while (count-- > 0) {
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_TO_RID,
+ req->to_rid);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO,
+ (u32)req->to_addr);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI,
+ (u32)(req->to_addr >> 32));
+ if (req->from_buf == NULL) {
+ from_rid = req->from_rid;
+ from_lo = (u32)req->from_addr;
+ from_hi = (u32)(req->from_addr >> 32);
+ } else {
+ if (WARN_ON(used + req->length > MCDI_CTL_SDU_LEN_MAX)) {
+ rc = -ENOBUFS;
+ goto out;
+ }
+
+ from_rid = MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE;
+ from_lo = used;
+ from_hi = 0;
+ memcpy(inbuf + used, req->from_buf, req->length);
+ used += req->length;
+ }
+
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_RID, from_rid);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO,
+ from_lo);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI,
+ from_hi);
+ MCDI_SET_DWORD(record, MEMCPY_RECORD_TYPEDEF_LENGTH,
+ req->length);
+
+ ++req;
+ record += MC_CMD_MEMCPY_IN_RECORD_LEN;
+ }
+
+ rc = efx_mcdi_rpc(efx, MC_CMD_MEMCPY, inbuf, used, NULL, 0, NULL);
+out:
+ kfree(inbuf);
+
+ 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_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, ®, 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, ®, 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) ||
+ 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, ®, 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, ®, 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;
+ __le32 *rxqs;
+ int rc;
+
+ rxqs = kmalloc(count * sizeof(*rxqs), GFP_KERNEL);
+ if (rxqs == NULL)
+ return VFDI_RC_ENOMEM;
+
+ rtnl_lock();
+ if (efx->fc_disable++ == 0)
+ efx_mcdi_set_mac(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, ®, FR_AZ_TX_FLUSH_DESCQ);
+ }
+ if (test_bit(index, vf->rxq_mask))
+ rxqs[rxqs_count++] = cpu_to_le32(vf_offset + index);
+ }
+
+ 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, (u8 *)rxqs,
+ rxqs_count * sizeof(*rxqs), 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);
+ rxqs[rxqs_count++] =
+ cpu_to_le32(vf_offset + index);
+ }
+ }
+ }
+
+ rtnl_lock();
+ if (--efx->fc_disable == 0)
+ efx_mcdi_set_mac(efx);
+ rtnl_unlock();
+
+ /* Irrespective of success/failure, fini the queues */
+ EFX_ZERO_OWORD(reg);
+ for (index = 0; index < count; ++index) {
+ efx_writeo_table(efx, ®, FR_BZ_RX_DESC_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, ®, FR_BZ_TX_DESC_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, ®, FR_BZ_EVQ_PTR_TBL,
+ vf_offset + index);
+ efx_writeo_table(efx, ®, FR_BZ_TIMER_TBL,
+ vf_offset + index);
+ }
+ efx_sriov_bufs(efx, vf->buftbl_base, NULL,
+ EFX_VF_BUFTBL_PER_VI * efx_vf_size(efx));
+ kfree(rxqs);
+ 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;
+ unsigned int page_count;
+
+ page_count = req->u.set_status_page.peer_page_count;
+ if (!req->u.set_status_page.dma_addr || EFX_PAGE_SIZE <
+ offsetof(struct vfdi_req,
+ u.set_status_page.peer_page_addr[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, ®, 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, ®, FR_BZ_EVQ_PTR_TBL, abs_evq);
+ EFX_POPULATE_DWORD_1(ptr, FRF_AZ_EVQ_RPTR, 0);
+ efx_writed_table(efx, &ptr, FR_BZ_EVQ_RPTR, 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)) {
+ 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,
+ .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) {
+ memcpy(peer->mac_addr, local_addr->addr, ETH_ALEN);
+ 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);
+ 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));
+ 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();
+ memcpy(vfdi_status->peers[0].mac_addr,
+ net_dev->dev_addr, ETH_ALEN);
+ 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;
+ memcpy(vfdi_status->peers[0].mac_addr,
+ efx->net_dev->dev_addr, ETH_ALEN);
+ 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))
+ 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);
+ memcpy(vf->addr.mac_addr, mac, ETH_ALEN);
+ __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;
+ memcpy(ivi->mac, vf->addr.mac_addr, ETH_ALEN);
+ ivi->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/vfdi.h b/drivers/net/ethernet/sfc/vfdi.h
new file mode 100644
index 0000000..656fa70
--- /dev/null
+++ b/drivers/net/ethernet/sfc/vfdi.h
@@ -0,0 +1,254 @@
+/****************************************************************************
+ * Driver for Solarflare Solarstorm 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 such that the structure fits within a page.
+ * @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
--
1.7.7.6
--
Ben Hutchings, Staff Engineer, Solarflare
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists