diff --git a/drivers/misc/cxl/guest.c b/drivers/misc/cxl/guest.c index 3bc0c15d4d85b7f16e8ad10fa00847c17ee5dc7e..b83a373e3a8dd3ce3682aa5249236d9b234565c4 100644 --- a/drivers/misc/cxl/guest.c +++ b/drivers/misc/cxl/guest.c @@ -267,6 +267,7 @@ static int guest_reset(struct cxl *adapter) int i, rc; pr_devel("Adapter reset request\n"); + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { if ((afu = adapter->afu[i])) { pci_error_handlers(afu, CXL_ERROR_DETECTED_EVENT, @@ -283,6 +284,7 @@ static int guest_reset(struct cxl *adapter) pci_error_handlers(afu, CXL_RESUME_EVENT, 0); } } + spin_unlock(&adapter->afu_list_lock); return rc; } diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c index b66d832d3233b65369a10c843843600d7563529c..787a69a2a726fabc3f9ec83614660723c28057a7 100644 --- a/drivers/misc/cxl/pci.c +++ b/drivers/misc/cxl/pci.c @@ -1807,7 +1807,7 @@ static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu, /* There should only be one entry, but go through the list * anyway */ - if (afu->phb == NULL) + if (afu == NULL || afu->phb == NULL) return result; list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) { @@ -1834,7 +1834,8 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, { struct cxl *adapter = pci_get_drvdata(pdev); struct cxl_afu *afu; - pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET, afu_result; + pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET; + pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET; int i; /* At this point, we could still have an interrupt pending. @@ -1845,6 +1846,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, /* If we're permanently dead, give up. */ if (state == pci_channel_io_perm_failure) { + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; /* @@ -1853,6 +1855,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, */ cxl_vphb_error_detected(afu, state); } + spin_unlock(&adapter->afu_list_lock); return PCI_ERS_RESULT_DISCONNECT; } @@ -1934,11 +1937,17 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, * * In slot_reset, free the old resources and allocate new ones. * * In resume, clear the flag to allow things to start. */ + + /* Make sure no one else changes the afu list */ + spin_lock(&adapter->afu_list_lock); + for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; - afu_result = cxl_vphb_error_detected(afu, state); + if (afu == NULL) + continue; + afu_result = cxl_vphb_error_detected(afu, state); cxl_context_detach_all(afu); cxl_ops->afu_deactivate_mode(afu, afu->current_mode); pci_deconfigure_afu(afu); @@ -1950,6 +1959,7 @@ static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev, (result == PCI_ERS_RESULT_NEED_RESET)) result = PCI_ERS_RESULT_NONE; } + spin_unlock(&adapter->afu_list_lock); /* should take the context lock here */ if (cxl_adapter_context_lock(adapter) != 0) @@ -1982,14 +1992,18 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) */ cxl_adapter_context_unlock(adapter); + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; + if (afu == NULL) + continue; + if (pci_configure_afu(afu, adapter, pdev)) - goto err; + goto err_unlock; if (cxl_afu_select_best_mode(afu)) - goto err; + goto err_unlock; if (afu->phb == NULL) continue; @@ -2001,16 +2015,16 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) ctx = cxl_get_context(afu_dev); if (ctx && cxl_release_context(ctx)) - goto err; + goto err_unlock; ctx = cxl_dev_context_init(afu_dev); if (IS_ERR(ctx)) - goto err; + goto err_unlock; afu_dev->dev.archdata.cxl_ctx = ctx; if (cxl_ops->afu_check_and_enable(afu)) - goto err; + goto err_unlock; afu_dev->error_state = pci_channel_io_normal; @@ -2031,8 +2045,13 @@ static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev) result = PCI_ERS_RESULT_DISCONNECT; } } + + spin_unlock(&adapter->afu_list_lock); return result; +err_unlock: + spin_unlock(&adapter->afu_list_lock); + err: /* All the bits that happen in both error_detected and cxl_remove * should be idempotent, so we don't need to worry about leaving a mix @@ -2053,10 +2072,11 @@ static void cxl_pci_resume(struct pci_dev *pdev) * This is not the place to be checking if everything came back up * properly, because there's no return value: do that in slot_reset. */ + spin_lock(&adapter->afu_list_lock); for (i = 0; i < adapter->slices; i++) { afu = adapter->afu[i]; - if (afu->phb == NULL) + if (afu == NULL || afu->phb == NULL) continue; list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) { @@ -2065,6 +2085,7 @@ static void cxl_pci_resume(struct pci_dev *pdev) afu_dev->driver->err_handler->resume(afu_dev); } } + spin_unlock(&adapter->afu_list_lock); } static const struct pci_error_handlers cxl_err_handler = {