PCI: dwc: Work around ECRC configuration issue

DesignWare core has a TLP digest (TD) override bit in one of the control
registers of ATU. This bit also needs to be programmed for proper ECRC
functionality. This is currently identified as an issue with DesignWare
IP version 4.90a.

[bhelgaas: fix typos/grammar errors]
Link: https://lore.kernel.org/r/20201230165723.673-1-vidyas@nvidia.comSigned-off-by: Vidya Sagar <vidyas@nvidia.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>

drivers/pci/controller/dwc/pcie-designware.c

@@ -225,6 +225,47 @@ static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg,
 	dw_pcie_writel_atu(pci, offset + reg, val);
 }
 
+static inline u32 dw_pcie_enable_ecrc(u32 val)
+{
+	/*
+	 * DesignWare core version 4.90A has a design issue where the 'TD'
+	 * bit in the Control register-1 of the ATU outbound region acts
+	 * like an override for the ECRC setting, i.e., the presence of TLP
+	 * Digest (ECRC) in the outgoing TLPs is solely determined by this
+	 * bit. This is contrary to the PCIe spec which says that the
+	 * enablement of the ECRC is solely determined by the AER
+	 * registers.
+	 *
+	 * Because of this, even when the ECRC is enabled through AER
+	 * registers, the transactions going through ATU won't have TLP
+	 * Digest as there is no way the PCI core AER code could program
+	 * the TD bit which is specific to the DesignWare core.
+	 *
+	 * The best way to handle this scenario is to program the TD bit
+	 * always. It affects only the traffic from root port to downstream
+	 * devices.
+	 *
+	 * At this point,
+	 * When ECRC is enabled in AER registers, everything works normally
+	 * When ECRC is NOT enabled in AER registers, then,
+	 * on Root Port:- TLP Digest (DWord size) gets appended to each packet
+	 *                even through it is not required. Since downstream
+	 *                TLPs are mostly for configuration accesses and BAR
+	 *                accesses, they are not in critical path and won't
+	 *                have much negative effect on the performance.
+	 * on End Point:- TLP Digest is received for some/all the packets coming
+	 *                from the root port. TLP Digest is ignored because,
+	 *                as per the PCIe Spec r5.0 v1.0 section 2.2.3
+	 *                "TLP Digest Rules", when an endpoint receives TLP
+	 *                Digest when its ECRC check functionality is disabled
+	 *                in AER registers, received TLP Digest is just ignored.
+	 * Since there is no issue or error reported either side, best way to
+	 * handle the scenario is to program TD bit by default.
+	 */
+
+	return val | PCIE_ATU_TD;
+}
+
 static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, u8 func_no,
 					     int index, int type,
 					     u64 cpu_addr, u64 pci_addr,
@@ -248,6 +289,8 @@ static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, u8 func_no,
 	val = type | PCIE_ATU_FUNC_NUM(func_no);
 	val = upper_32_bits(size - 1) ?
 		val | PCIE_ATU_INCREASE_REGION_SIZE : val;
+	if (pci->version == 0x490A)
+		val = dw_pcie_enable_ecrc(val);
 	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, val);
 	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
 				 PCIE_ATU_ENABLE);
@@ -294,8 +337,10 @@ static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
 			   lower_32_bits(pci_addr));
 	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET,
 			   upper_32_bits(pci_addr));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, type |
-			   PCIE_ATU_FUNC_NUM(func_no));
+	val = type | PCIE_ATU_FUNC_NUM(func_no);
+	if (pci->version == 0x490A)
+		val = dw_pcie_enable_ecrc(val);
+	dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, val);
 	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, PCIE_ATU_ENABLE);
 
 	/*

drivers/pci/controller/dwc/pcie-designware.h

@@ -86,6 +86,7 @@
 #define PCIE_ATU_TYPE_IO		0x2
 #define PCIE_ATU_TYPE_CFG0		0x4
 #define PCIE_ATU_TYPE_CFG1		0x5
+#define PCIE_ATU_TD			BIT(8)
 #define PCIE_ATU_FUNC_NUM(pf)           ((pf) << 20)
 #define PCIE_ATU_CR2			0x908
 #define PCIE_ATU_ENABLE			BIT(31)