myri10ge: DCA update (resubmit)
This patch contains the following DCA improvements to myri10ge:
1) Finally move myri10ge to use dca3 API
2) Disable PCIe relaxed ordering when enabling DCA on
myri10ge. This provides a performance boost on Nehalem
based Xeons
3) Make sure to properly initialize NIC's DCA state when it is enabled,
rather than giving the NIC a bogus tag (0) and waiting for
the first received packet to trigger an update. Not using a
real tag can cause hardware exceptions on some motherboards
when a CPU socket is empty.
3) Always update the cached CPU when our interrupt affinity changes
so as to avoid excessive calls to dca3_get_tag()
Signed-off-by: Andrew Gallatin <gallatin@myri.com>
Signed-off-by: Loic Prylli <loic@myri.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c
index 3ad1a21..8524cc4 100644
--- a/drivers/net/myri10ge/myri10ge.c
+++ b/drivers/net/myri10ge/myri10ge.c
@@ -225,6 +225,7 @@
struct msix_entry *msix_vectors;
#ifdef CONFIG_MYRI10GE_DCA
int dca_enabled;
+ int relaxed_order;
#endif
u32 link_state;
unsigned int rdma_tags_available;
@@ -1074,10 +1075,28 @@
}
#ifdef CONFIG_MYRI10GE_DCA
+static int myri10ge_toggle_relaxed(struct pci_dev *pdev, int on)
+{
+ int ret, cap, err;
+ u16 ctl;
+
+ cap = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+ if (!cap)
+ return 0;
+
+ err = pci_read_config_word(pdev, cap + PCI_EXP_DEVCTL, &ctl);
+ ret = (ctl & PCI_EXP_DEVCTL_RELAX_EN) >> 4;
+ if (ret != on) {
+ ctl &= ~PCI_EXP_DEVCTL_RELAX_EN;
+ ctl |= (on << 4);
+ pci_write_config_word(pdev, cap + PCI_EXP_DEVCTL, ctl);
+ }
+ return ret;
+}
+
static void
myri10ge_write_dca(struct myri10ge_slice_state *ss, int cpu, int tag)
{
- ss->cpu = cpu;
ss->cached_dca_tag = tag;
put_be32(htonl(tag), ss->dca_tag);
}
@@ -1088,9 +1107,10 @@
int tag;
if (cpu != ss->cpu) {
- tag = dca_get_tag(cpu);
+ tag = dca3_get_tag(&ss->mgp->pdev->dev, cpu);
if (ss->cached_dca_tag != tag)
myri10ge_write_dca(ss, cpu, tag);
+ ss->cpu = cpu;
}
put_cpu();
}
@@ -1113,9 +1133,13 @@
"dca_add_requester() failed, err=%d\n", err);
return;
}
+ mgp->relaxed_order = myri10ge_toggle_relaxed(pdev, 0);
mgp->dca_enabled = 1;
- for (i = 0; i < mgp->num_slices; i++)
- myri10ge_write_dca(&mgp->ss[i], -1, 0);
+ for (i = 0; i < mgp->num_slices; i++) {
+ mgp->ss[i].cpu = -1;
+ mgp->ss[i].cached_dca_tag = -1;
+ myri10ge_update_dca(&mgp->ss[i]);
+ }
}
static void myri10ge_teardown_dca(struct myri10ge_priv *mgp)
@@ -1126,6 +1150,8 @@
if (!mgp->dca_enabled)
return;
mgp->dca_enabled = 0;
+ if (mgp->relaxed_order)
+ myri10ge_toggle_relaxed(pdev, 1);
err = dca_remove_requester(&pdev->dev);
}