/**
* t4_get_mps_bg_map - return the buffer groups associated with a port
* @adap: the adapter
- * @idx: the port index
+ * @pidx: the port index
*
* Returns a bitmap indicating which MPS buffer groups are associated
* with the given port. Bit i is set if buffer group i is used by the
* port.
*/
-unsigned int t4_get_mps_bg_map(struct adapter *adap, int idx)
+unsigned int t4_get_mps_bg_map(struct adapter *adap, unsigned int pidx)
+{
+ unsigned int chip_version = CHELSIO_CHIP_VERSION(adap->params.chip);
+ unsigned int nports = 1 << G_NUMPORTS(t4_read_reg(adap,
+ A_MPS_CMN_CTL));
+
+ if (pidx >= nports) {
+ dev_warn(adap, "MPS Port Index %d >= Nports %d\n",
+ pidx, nports);
+ return 0;
+ }
+
+ switch (chip_version) {
+ case CHELSIO_T4:
+ case CHELSIO_T5:
+ switch (nports) {
+ case 1: return 0xf;
+ case 2: return 3 << (2 * pidx);
+ case 4: return 1 << pidx;
+ }
+ break;
+
+ case CHELSIO_T6:
+ switch (nports) {
+ case 2: return 1 << (2 * pidx);
+ }
+ break;
+ }
+
+ dev_err(adap, "Need MPS Buffer Group Map for Chip %0x, Nports %d\n",
+ chip_version, nports);
+ return 0;
+}
+
+/**
+ * t4_get_tp_ch_map - return TP ingress channels associated with a port
+ * @adapter: the adapter
+ * @pidx: the port index
+ *
+ * Returns a bitmap indicating which TP Ingress Channels are associated with
+ * a given Port. Bit i is set if TP Ingress Channel i is used by the Port.
+ */
+unsigned int t4_get_tp_ch_map(struct adapter *adapter, unsigned int pidx)
{
- u32 n = G_NUMPORTS(t4_read_reg(adap, A_MPS_CMN_CTL));
+ unsigned int chip_version = CHELSIO_CHIP_VERSION(adapter->params.chip);
+ unsigned int nports = 1 << G_NUMPORTS(t4_read_reg(adapter,
+ A_MPS_CMN_CTL));
+
+ if (pidx >= nports) {
+ dev_warn(adap, "TP Port Index %d >= Nports %d\n",
+ pidx, nports);
+ return 0;
+ }
+
+ switch (chip_version) {
+ case CHELSIO_T4:
+ case CHELSIO_T5:
+ /* Note that this happens to be the same values as the MPS
+ * Buffer Group Map for these Chips. But we replicate the code
+ * here because they're really separate concepts.
+ */
+ switch (nports) {
+ case 1: return 0xf;
+ case 2: return 3 << (2 * pidx);
+ case 4: return 1 << pidx;
+ }
+ break;
+
+ case CHELSIO_T6:
+ switch (nports) {
+ case 2: return 1 << pidx;
+ }
+ break;
+ }
- if (n == 0)
- return idx == 0 ? 0xf : 0;
- if (n == 1)
- return idx < 2 ? (3 << (2 * idx)) : 0;
- return 1 << idx;
+ dev_err(adapter, "Need TP Channel Map for Chip %0x, Nports %d\n",
+ chip_version, nports);
+ return 0;
}
/**
void t4_get_port_stats(struct adapter *adap, int idx, struct port_stats *p)
{
u32 bgmap = t4_get_mps_bg_map(adap, idx);
+ u32 stat_ctl = t4_read_reg(adap, A_MPS_STAT_CTL);
#define GET_STAT(name) \
t4_read_reg64(adap, \
p->tx_ppp6 = GET_STAT(TX_PORT_PPP6);
p->tx_ppp7 = GET_STAT(TX_PORT_PPP7);
+ if (CHELSIO_CHIP_VERSION(adap->params.chip) >= CHELSIO_T5) {
+ if (stat_ctl & F_COUNTPAUSESTATTX) {
+ p->tx_frames -= p->tx_pause;
+ p->tx_octets -= p->tx_pause * 64;
+ }
+ if (stat_ctl & F_COUNTPAUSEMCTX)
+ p->tx_mcast_frames -= p->tx_pause;
+ }
+
p->rx_octets = GET_STAT(RX_PORT_BYTES);
p->rx_frames = GET_STAT(RX_PORT_FRAMES);
p->rx_bcast_frames = GET_STAT(RX_PORT_BCAST);
p->rx_ppp5 = GET_STAT(RX_PORT_PPP5);
p->rx_ppp6 = GET_STAT(RX_PORT_PPP6);
p->rx_ppp7 = GET_STAT(RX_PORT_PPP7);
+
+ if (CHELSIO_CHIP_VERSION(adap->params.chip) >= CHELSIO_T5) {
+ if (stat_ctl & F_COUNTPAUSESTATRX) {
+ p->rx_frames -= p->rx_pause;
+ p->rx_octets -= p->rx_pause * 64;
+ }
+ if (stat_ctl & F_COUNTPAUSEMCRX)
+ p->rx_mcast_frames -= p->rx_pause;
+ }
+
p->rx_ovflow0 = (bgmap & 1) ? GET_STAT_COM(RX_BG_0_MAC_DROP_FRAME) : 0;
p->rx_ovflow1 = (bgmap & 2) ? GET_STAT_COM(RX_BG_1_MAC_DROP_FRAME) : 0;
p->rx_ovflow2 = (bgmap & 4) ? GET_STAT_COM(RX_BG_2_MAC_DROP_FRAME) : 0;
return 0;
}
+/**
+ * t4_fl_pkt_align - return the fl packet alignment
+ * @adap: the adapter
+ *
+ * T4 has a single field to specify the packing and padding boundary.
+ * T5 onwards has separate fields for this and hence the alignment for
+ * next packet offset is maximum of these two.
+ */
+int t4_fl_pkt_align(struct adapter *adap)
+{
+ u32 sge_control, sge_control2;
+ unsigned int ingpadboundary, ingpackboundary, fl_align, ingpad_shift;
+
+ sge_control = t4_read_reg(adap, A_SGE_CONTROL);
+
+ /* T4 uses a single control field to specify both the PCIe Padding and
+ * Packing Boundary. T5 introduced the ability to specify these
+ * separately. The actual Ingress Packet Data alignment boundary
+ * within Packed Buffer Mode is the maximum of these two
+ * specifications.
+ */
+ if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5)
+ ingpad_shift = X_INGPADBOUNDARY_SHIFT;
+ else
+ ingpad_shift = X_T6_INGPADBOUNDARY_SHIFT;
+
+ ingpadboundary = 1 << (G_INGPADBOUNDARY(sge_control) + ingpad_shift);
+
+ fl_align = ingpadboundary;
+ if (!is_t4(adap->params.chip)) {
+ sge_control2 = t4_read_reg(adap, A_SGE_CONTROL2);
+ ingpackboundary = G_INGPACKBOUNDARY(sge_control2);
+ if (ingpackboundary == X_INGPACKBOUNDARY_16B)
+ ingpackboundary = 16;
+ else
+ ingpackboundary = 1 << (ingpackboundary +
+ X_INGPACKBOUNDARY_SHIFT);
+
+ fl_align = max(ingpadboundary, ingpackboundary);
+ }
+ return fl_align;
+}
+
/**
* t4_fixup_host_params_compat - fix up host-dependent parameters
* @adap: the adapter
X_INGPADBOUNDARY_SHIFT) |
V_EGRSTATUSPAGESIZE(stat_len != 64));
else {
+ unsigned int pack_align;
+ unsigned int ingpad, ingpack;
+ unsigned int pcie_cap;
+
/*
* T5 introduced the separation of the Free List Padding and
* Packing Boundaries. Thus, we can select a smaller Padding
* Size (the minimum unit of transfer to/from Memory). If we
* have a Padding Boundary which is smaller than the Memory
* Line Size, that'll involve a Read-Modify-Write cycle on the
- * Memory Controller which is never good. For T5 the smallest
- * Padding Boundary which we can select is 32 bytes which is
- * larger than any known Memory Controller Line Size so we'll
- * use that.
+ * Memory Controller which is never good.
*/
+ /* We want the Packing Boundary to be based on the Cache Line
+ * Size in order to help avoid False Sharing performance
+ * issues between CPUs, etc. We also want the Packing
+ * Boundary to incorporate the PCI-E Maximum Payload Size. We
+ * get best performance when the Packing Boundary is a
+ * multiple of the Maximum Payload Size.
+ */
+ pack_align = fl_align;
+ pcie_cap = t4_os_find_pci_capability(adap, PCI_CAP_ID_EXP);
+ if (pcie_cap) {
+ unsigned int mps, mps_log;
+ u16 devctl;
+
+ /* The PCIe Device Control Maximum Payload Size field
+ * [bits 7:5] encodes sizes as powers of 2 starting at
+ * 128 bytes.
+ */
+ t4_os_pci_read_cfg2(adap, pcie_cap + PCI_EXP_DEVCTL,
+ &devctl);
+ mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+ mps = 1 << mps_log;
+ if (mps > pack_align)
+ pack_align = mps;
+ }
+
/*
* N.B. T5 has a different interpretation of the "0" value for
* the Packing Boundary. This corresponds to 16 bytes instead
* on the other hand, if we wanted 32 bytes, the best we can
* really do is 64 bytes ...
*/
- if (fl_align <= 32) {
+ if (pack_align <= 16) {
+ ingpack = X_INGPACKBOUNDARY_16B;
+ fl_align = 16;
+ } else if (pack_align == 32) {
+ ingpack = X_INGPACKBOUNDARY_64B;
fl_align = 64;
- fl_align_log = 6;
+ } else {
+ unsigned int pack_align_log = cxgbe_fls(pack_align) - 1;
+
+ ingpack = pack_align_log - X_INGPACKBOUNDARY_SHIFT;
+ fl_align = pack_align;
}
+
+ /* Use the smallest Ingress Padding which isn't smaller than
+ * the Memory Controller Read/Write Size. We'll take that as
+ * being 8 bytes since we don't know of any system with a
+ * wider Memory Controller Bus Width.
+ */
+ if (is_t5(adap->params.chip))
+ ingpad = X_INGPADBOUNDARY_32B;
+ else
+ ingpad = X_T6_INGPADBOUNDARY_8B;
t4_set_reg_field(adap, A_SGE_CONTROL,
V_INGPADBOUNDARY(M_INGPADBOUNDARY) |
F_EGRSTATUSPAGESIZE,
- V_INGPADBOUNDARY(X_INGPCIEBOUNDARY_32B) |
+ V_INGPADBOUNDARY(ingpad) |
V_EGRSTATUSPAGESIZE(stat_len != 64));
t4_set_reg_field(adap, A_SGE_CONTROL2,
V_INGPACKBOUNDARY(M_INGPACKBOUNDARY),
- V_INGPACKBOUNDARY(fl_align_log -
- X_INGPACKBOUNDARY_SHIFT));
+ V_INGPACKBOUNDARY(ingpack));
}
/*
&adap->params.tp.ingress_config, 1,
A_TP_INGRESS_CONFIG);
+ /* For T6, cache the adapter's compressed error vector
+ * and passing outer header info for encapsulated packets.
+ */
+ if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) {
+ v = t4_read_reg(adap, A_TP_OUT_CONFIG);
+ adap->params.tp.rx_pkt_encap = (v & F_CRXPKTENC) ? 1 : 0;
+ }
+
/*
* Now that we have TP_VLAN_PRI_MAP cached, we can calculate the field
* shift positions of several elements of the Compressed Filter Tuple