Adding upstream version 6.9.7.upstream/6.9.7upstream

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

5 files changed, 65 insertions, 11 deletions

diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
index 0df09bd79..2773f05ad 100644
--- a/drivers/cxl/core/pci.c
+++ b/drivers/cxl/core/pci.c
@@ -1045,3 +1045,32 @@ long cxl_pci_get_latency(struct pci_dev *pdev)
 
 	return cxl_flit_size(pdev) * MEGA / bw;
 }
+
+static int __cxl_endpoint_decoder_reset_detected(struct device *dev, void *data)
+{
+	struct cxl_port *port = data;
+	struct cxl_decoder *cxld;
+	struct cxl_hdm *cxlhdm;
+	void __iomem *hdm;
+	u32 ctrl;
+
+	if (!is_endpoint_decoder(dev))
+		return 0;
+
+	cxld = to_cxl_decoder(dev);
+	if ((cxld->flags & CXL_DECODER_F_ENABLE) == 0)
+		return 0;
+
+	cxlhdm = dev_get_drvdata(&port->dev);
+	hdm = cxlhdm->regs.hdm_decoder;
+	ctrl = readl(hdm + CXL_HDM_DECODER0_CTRL_OFFSET(cxld->id));
+
+	return !FIELD_GET(CXL_HDM_DECODER0_CTRL_COMMITTED, ctrl);
+}
+
+bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port)
+{
+	return device_for_each_child(&port->dev, port,
+				     __cxl_endpoint_decoder_reset_detected);
+}
+EXPORT_SYMBOL_NS_GPL(cxl_endpoint_decoder_reset_detected, CXL);
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 5c186e0a3..18b951496 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -2352,15 +2352,6 @@ static struct cxl_region *devm_cxl_add_region(struct cxl_root_decoder *cxlrd,
 	struct device *dev;
 	int rc;
 
-	switch (mode) {
-	case CXL_DECODER_RAM:
-	case CXL_DECODER_PMEM:
-		break;
-	default:
-		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
-		return ERR_PTR(-EINVAL);
-	}
-
 	cxlr = cxl_region_alloc(cxlrd, id);
 	if (IS_ERR(cxlr))
 		return cxlr;
@@ -2415,6 +2406,15 @@ static struct cxl_region *__create_region(struct cxl_root_decoder *cxlrd,
 {
 	int rc;
 
+	switch (mode) {
+	case CXL_DECODER_RAM:
+	case CXL_DECODER_PMEM:
+		break;
+	default:
+		dev_err(&cxlrd->cxlsd.cxld.dev, "unsupported mode %d\n", mode);
+		return ERR_PTR(-EINVAL);
+	}
+
 	rc = memregion_alloc(GFP_KERNEL);
 	if (rc < 0)
 		return ERR_PTR(rc);
@@ -2719,6 +2719,7 @@ static struct cxl_pmem_region *cxl_pmem_region_alloc(struct cxl_region *cxlr)
 		if (i == 0) {
 			cxl_nvb = cxl_find_nvdimm_bridge(cxlmd);
 			if (!cxl_nvb) {
+				kfree(cxlr_pmem);
 				cxlr_pmem = ERR_PTR(-ENODEV);
 				goto out;
 			}
diff --git a/drivers/cxl/core/trace.h b/drivers/cxl/core/trace.h
index e5f13260f..7c5cd069f 100644
--- a/drivers/cxl/core/trace.h
+++ b/drivers/cxl/core/trace.h
@@ -253,8 +253,8 @@ TRACE_EVENT(cxl_generic_event,
  * DRAM Event Record
  * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
  */
-#define CXL_DPA_FLAGS_MASK			0x3F
-#define CXL_DPA_MASK				(~CXL_DPA_FLAGS_MASK)
+#define CXL_DPA_FLAGS_MASK			GENMASK(1, 0)
+#define CXL_DPA_MASK				GENMASK_ULL(63, 6)
 
 #define CXL_DPA_VOLATILE			BIT(0)
 #define CXL_DPA_NOT_REPAIRABLE			BIT(1)
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 036d17db6..72fa47740 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -891,6 +891,8 @@ void cxl_coordinates_combine(struct access_coordinate *out,
 			     struct access_coordinate *c1,
 			     struct access_coordinate *c2);
 
+bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
+
 /*
  * Unit test builds overrides this to __weak, find the 'strong' version
  * of these symbols in tools/testing/cxl/.
diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c
index 2ff361e75..659f9d46b 100644
--- a/drivers/cxl/pci.c
+++ b/drivers/cxl/pci.c
@@ -957,11 +957,33 @@ static void cxl_error_resume(struct pci_dev *pdev)
 		 dev->driver ? "successful" : "failed");
 }
 
+static void cxl_reset_done(struct pci_dev *pdev)
+{
+	struct cxl_dev_state *cxlds = pci_get_drvdata(pdev);
+	struct cxl_memdev *cxlmd = cxlds->cxlmd;
+	struct device *dev = &pdev->dev;
+
+	/*
+	 * FLR does not expect to touch the HDM decoders and related
+	 * registers.  SBR, however, will wipe all device configurations.
+	 * Issue a warning if there was an active decoder before the reset
+	 * that no longer exists.
+	 */
+	guard(device)(&cxlmd->dev);
+	if (cxlmd->endpoint &&
+	    cxl_endpoint_decoder_reset_detected(cxlmd->endpoint)) {
+		dev_crit(dev, "SBR happened without memory regions removal.\n");
+		dev_crit(dev, "System may be unstable if regions hosted system memory.\n");
+		add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+	}
+}
+
 static const struct pci_error_handlers cxl_error_handlers = {
 	.error_detected	= cxl_error_detected,
 	.slot_reset	= cxl_slot_reset,
 	.resume		= cxl_error_resume,
 	.cor_error_detected	= cxl_cor_error_detected,
+	.reset_done	= cxl_reset_done,
 };
 
 static struct pci_driver cxl_pci_driver = {