cxl: add RAS status unmasking for CXL

By default the CXL RAS mask registers bits are defaulted to 1's and
suppress all error reporting. If the kernel has negotiated ownership
of error handling for CXL then unmask the mask registers by writing 0s.

PCI_EXP_DEVCTL capability is checked to see uncorrectable or correctable
errors bits are set before unmasking the respective errors.

Acked-by: Bjorn Helgaas <bhelgaas@google.com>  # pci_regs.h
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Link: https://lore.kernel.org/r/167639402301.778884.12556849214955646539.stgit@djiang5-mobl3.local
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

2 files changed, 66 insertions, 0 deletions

diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index aa3af3bb73b2..197ecffce4d0 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -130,6 +130,7 @@ static inline int ways_to_eiw(unsigned int ways, u8 *eiw)
 #define   CXL_RAS_UNCORRECTABLE_STATUS_MASK (GENMASK(16, 14) | GENMASK(11, 0))
 #define CXL_RAS_UNCORRECTABLE_MASK_OFFSET 0x4
 #define   CXL_RAS_UNCORRECTABLE_MASK_MASK (GENMASK(16, 14) | GENMASK(11, 0))
+#define   CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK BIT(8)
 #define CXL_RAS_UNCORRECTABLE_SEVERITY_OFFSET 0x8
 #define   CXL_RAS_UNCORRECTABLE_SEVERITY_MASK (GENMASK(16, 14) | GENMASK(11, 0))
 #define CXL_RAS_CORRECTABLE_STATUS_OFFSET 0xC
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index cc8b5a766a82..a509640994d7 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -412,6 +412,67 @@ static bool is_cxl_restricted(struct pci_dev *pdev)
 	return pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_END;
 }
 
+/*
+ * CXL v3.0 6.2.3 Table 6-4
+ * The table indicates that if PCIe Flit Mode is set, then CXL is in 256B flits
+ * mode, otherwise it's 68B flits mode.
+ */
+static bool cxl_pci_flit_256(struct pci_dev *pdev)
+{
+	u16 lnksta2;
+
+	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &lnksta2);
+	return lnksta2 & PCI_EXP_LNKSTA2_FLIT;
+}
+
+static int cxl_pci_ras_unmask(struct pci_dev *pdev)
+{
+	struct pci_host_bridge *host_bridge = pci_find_host_bridge(pdev->bus);
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	void __iomem *addr;
+	u32 orig_val, val, mask;
+	u16 cap;
+	int rc;
+
+	if (!cxlds->regs.ras) {
+		dev_dbg(&pdev->dev, "No RAS registers.\n");
+		return 0;
+	}
+
+	/* BIOS has CXL error control */
+	if (!host_bridge->native_cxl_error)
+		return -ENXIO;
+
+	rc = pcie_capability_read_word(pdev, PCI_EXP_DEVCTL, &cap);
+	if (rc)
+		return rc;
+
+	if (cap & PCI_EXP_DEVCTL_URRE) {
+		addr = cxlds->regs.ras + CXL_RAS_UNCORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+
+		mask = CXL_RAS_UNCORRECTABLE_MASK_MASK;
+		if (!cxl_pci_flit_256(pdev))
+			mask &= ~CXL_RAS_UNCORRECTABLE_MASK_F256B_MASK;
+		val = orig_val & ~mask;
+		writel(val, addr);
+		dev_dbg(&pdev->dev,
+			"Uncorrectable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	if (cap & PCI_EXP_DEVCTL_CERE) {
+		addr = cxlds->regs.ras + CXL_RAS_CORRECTABLE_MASK_OFFSET;
+		orig_val = readl(addr);
+		val = orig_val & ~CXL_RAS_CORRECTABLE_MASK_MASK;
+		writel(val, addr);
+		dev_dbg(&pdev->dev, "Correctable RAS Errors Mask: %#x -> %#x\n",
+			orig_val, val);
+	}
+
+	return 0;
+}
+
 static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct cxl_register_map map;
@@ -489,6 +550,10 @@ static int cxl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (IS_ERR(cxlmd))
 		return PTR_ERR(cxlmd);
 
+	rc = cxl_pci_ras_unmask(pdev);
+	if (rc)
+		dev_dbg(&pdev->dev, "No RAS reporting unmasked\n");
+
 	pci_save_state(pdev);
 
 	return rc;