diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 0df09bd7940884..2773f05adb7d26 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/cxl.h b/drivers/cxl/cxl.h index 036d17db68e006..72fa477407689c 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 2ff361e756d661..659f9d46b154c9 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 = {