staging/hfi1: set Gen3 half-swing for integrated devices

Correctly set half-swing for integrated devices.  A0 needs all fields set for
CcePcieCtrl.  B0 and later only need a few fields set.

Reviewed-by: Stuart Summers <john.s.summers@intel.com>
Signed-off-by: Dean Luick <dean.luick@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
diff --git a/drivers/staging/rdma/hfi1/chip_registers.h b/drivers/staging/rdma/hfi1/chip_registers.h
index 701e9e1..014d7a6 100644
--- a/drivers/staging/rdma/hfi1/chip_registers.h
+++ b/drivers/staging/rdma/hfi1/chip_registers.h
@@ -551,6 +551,17 @@
 #define CCE_MSIX_TABLE_UPPER (CCE + 0x000000100008)
 #define CCE_MSIX_TABLE_UPPER_RESETCSR 0x0000000100000000ull
 #define CCE_MSIX_VEC_CLR_WITHOUT_INT (CCE + 0x000000110400)
+#define CCE_PCIE_CTRL (CCE + 0x0000000000C0)
+#define CCE_PCIE_CTRL_PCIE_LANE_BUNDLE_MASK 0x3ull
+#define CCE_PCIE_CTRL_PCIE_LANE_BUNDLE_SHIFT 0
+#define CCE_PCIE_CTRL_PCIE_LANE_DELAY_MASK 0xFull
+#define CCE_PCIE_CTRL_PCIE_LANE_DELAY_SHIFT 2
+#define CCE_PCIE_CTRL_XMT_MARGIN_OVERWRITE_ENABLE_SHIFT 8
+#define CCE_PCIE_CTRL_XMT_MARGIN_SHIFT 9
+#define CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_OVERWRITE_ENABLE_MASK 0x1ull
+#define CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_OVERWRITE_ENABLE_SHIFT 12
+#define CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_MASK 0x7ull
+#define CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_SHIFT 13
 #define CCE_REVISION (CCE + 0x000000000000)
 #define CCE_REVISION2 (CCE + 0x000000000008)
 #define CCE_REVISION2_HFI_ID_MASK 0x1ull
diff --git a/drivers/staging/rdma/hfi1/pcie.c b/drivers/staging/rdma/hfi1/pcie.c
index 8317b07..9917faf 100644
--- a/drivers/staging/rdma/hfi1/pcie.c
+++ b/drivers/staging/rdma/hfi1/pcie.c
@@ -867,6 +867,83 @@
 }
 
 /*
+ * CCE_PCIE_CTRL long name helpers
+ * We redefine these shorter macros to use in the code while leaving
+ * chip_registers.h to be autogenerated from the hardware spec.
+ */
+#define LANE_BUNDLE_MASK              CCE_PCIE_CTRL_PCIE_LANE_BUNDLE_MASK
+#define LANE_BUNDLE_SHIFT             CCE_PCIE_CTRL_PCIE_LANE_BUNDLE_SHIFT
+#define LANE_DELAY_MASK               CCE_PCIE_CTRL_PCIE_LANE_DELAY_MASK
+#define LANE_DELAY_SHIFT              CCE_PCIE_CTRL_PCIE_LANE_DELAY_SHIFT
+#define MARGIN_OVERWRITE_ENABLE_SHIFT CCE_PCIE_CTRL_XMT_MARGIN_OVERWRITE_ENABLE_SHIFT
+#define MARGIN_SHIFT                  CCE_PCIE_CTRL_XMT_MARGIN_SHIFT
+#define MARGIN_G1_G2_OVERWRITE_MASK   CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_OVERWRITE_ENABLE_MASK
+#define MARGIN_G1_G2_OVERWRITE_SHIFT  CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_OVERWRITE_ENABLE_SHIFT
+#define MARGIN_GEN1_GEN2_MASK         CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_MASK
+#define MARGIN_GEN1_GEN2_SHIFT        CCE_PCIE_CTRL_XMT_MARGIN_GEN1_GEN2_SHIFT
+
+ /*
+  * Write xmt_margin for full-swing (WFR-B) or half-swing (WFR-C).
+  */
+static void write_xmt_margin(struct hfi1_devdata *dd, const char *fname)
+{
+	u64 pcie_ctrl;
+	u64 xmt_margin;
+	u64 xmt_margin_oe;
+	u64 lane_delay;
+	u64 lane_bundle;
+
+	pcie_ctrl = read_csr(dd, CCE_PCIE_CTRL);
+
+	/*
+	 * For Discrete, use full-swing.
+	 *  - PCIe TX defaults to full-swing.
+	 *    Leave this register as default.
+	 * For Integrated, use half-swing
+	 *  - Copy xmt_margin and xmt_margin_oe
+	 *    from Gen1/Gen2 to Gen3.
+	 */
+	if (dd->pcidev->device == PCI_DEVICE_ID_INTEL1) { /* integrated */
+		/* extract initial fields */
+		xmt_margin = (pcie_ctrl >> MARGIN_GEN1_GEN2_SHIFT)
+			      & MARGIN_GEN1_GEN2_MASK;
+		xmt_margin_oe = (pcie_ctrl >> MARGIN_G1_G2_OVERWRITE_SHIFT)
+				 & MARGIN_G1_G2_OVERWRITE_MASK;
+		lane_delay = (pcie_ctrl >> LANE_DELAY_SHIFT) & LANE_DELAY_MASK;
+		lane_bundle = (pcie_ctrl >> LANE_BUNDLE_SHIFT)
+			       & LANE_BUNDLE_MASK;
+
+		/*
+		 * For A0, EFUSE values are not set.  Override with the
+		 * correct values.
+		 */
+		if (is_ax(dd)) {
+			/*
+			 * xmt_margin and OverwiteEnabel should be the
+			 * same for Gen1/Gen2 and Gen3
+			 */
+			xmt_margin = 0x5;
+			xmt_margin_oe = 0x1;
+			lane_delay = 0xF; /* Delay 240ns. */
+			lane_bundle = 0x0; /* Set to 1 lane. */
+		}
+
+		/* overwrite existing values */
+		pcie_ctrl = (xmt_margin << MARGIN_GEN1_GEN2_SHIFT)
+			| (xmt_margin_oe << MARGIN_G1_G2_OVERWRITE_SHIFT)
+			| (xmt_margin << MARGIN_SHIFT)
+			| (xmt_margin_oe << MARGIN_OVERWRITE_ENABLE_SHIFT)
+			| (lane_delay << LANE_DELAY_SHIFT)
+			| (lane_bundle << LANE_BUNDLE_SHIFT);
+
+		write_csr(dd, CCE_PCIE_CTRL, pcie_ctrl);
+	}
+
+	dd_dev_dbg(dd, "%s: program XMT margin, CcePcieCtrl 0x%llx\n",
+		   fname, pcie_ctrl);
+}
+
+/*
  * Do all the steps needed to transition the PCIe link to Gen3 speed.
  */
 int do_pcie_gen3_transition(struct hfi1_devdata *dd)
@@ -1064,11 +1141,8 @@
 
 	/*
 	 * step 5d: program XMT margin
-	 * Right now, leave the default alone.  To change, do a
-	 * read-modify-write of:
-	 *	CcePcieCtrl.XmtMargin
-	 *	CcePcieCtrl.XmitMarginOverwriteEnable
 	 */
+	write_xmt_margin(dd, __func__);
 
 	/* step 5e: disable active state power management (ASPM) */
 	dd_dev_info(dd, "%s: clearing ASPM\n", __func__);