sfc: Implement hardware acceleration of RFS
Use the existing filter management functions to insert TCP/IPv4 and
UDP/IPv4 4-tuple filters for Receive Flow Steering.
For each channel, track how many RFS filters are being added during
processing of received packets and scan the corresponding number of
table entries for filters that may be reclaimed. Do this in batches
to reduce lock overhead.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index d4e0425..35b7bc5 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -21,6 +21,7 @@
#include <linux/ethtool.h>
#include <linux/topology.h>
#include <linux/gfp.h>
+#include <linux/cpu_rmap.h>
#include "net_driver.h"
#include "efx.h"
#include "nic.h"
@@ -307,6 +308,8 @@
channel->irq_mod_score = 0;
}
+ efx_filter_rfs_expire(channel);
+
/* 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
@@ -1175,10 +1178,32 @@
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 void efx_probe_interrupts(struct efx_nic *efx)
+static int efx_probe_interrupts(struct efx_nic *efx)
{
int max_channels =
min_t(int, efx->type->phys_addr_channels, EFX_MAX_CHANNELS);
@@ -1220,6 +1245,11 @@
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;
+ }
for (i = 0; i < n_channels; i++)
efx_get_channel(efx, i)->irq =
xentries[i].vector;
@@ -1253,6 +1283,8 @@
efx->n_tx_channels = 1;
efx->legacy_irq = efx->pci_dev->irq;
}
+
+ return 0;
}
static void efx_remove_interrupts(struct efx_nic *efx)
@@ -1289,7 +1321,9 @@
/* Determine the number of channels and queues by trying to hook
* in MSI-X interrupts. */
- efx_probe_interrupts(efx);
+ rc = efx_probe_interrupts(efx);
+ if (rc)
+ goto fail;
if (efx->n_channels > 1)
get_random_bytes(&efx->rx_hash_key, sizeof(efx->rx_hash_key));
@@ -1304,6 +1338,10 @@
efx_init_irq_moderation(efx, tx_irq_mod_usec, rx_irq_mod_usec, true);
return 0;
+
+fail:
+ efx->type->remove(efx);
+ return rc;
}
static void efx_remove_nic(struct efx_nic *efx)
@@ -1837,6 +1875,9 @@
.ndo_poll_controller = efx_netpoll,
#endif
.ndo_setup_tc = efx_setup_tc,
+#ifdef CONFIG_RFS_ACCEL
+ .ndo_rx_flow_steer = efx_filter_rfs,
+#endif
};
static void efx_update_name(struct efx_nic *efx)
@@ -2274,6 +2315,10 @@
*/
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
efx_nic_fini_interrupt(efx);
efx_fini_channels(efx);
efx_fini_port(efx);