diff options
Diffstat (limited to 'drivers/pci/controller/pci-hyperv.c')
| -rw-r--r-- | drivers/pci/controller/pci-hyperv.c | 126 |
1 files changed, 90 insertions, 36 deletions
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index e15022ff63e3..bf40ff09c99d 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -480,6 +480,9 @@ struct hv_pcibus_device { struct workqueue_struct *wq; + /* Highest slot of child device with resources allocated */ + int wslot_res_allocated; + /* hypercall arg, must not cross page boundary */ struct hv_retarget_device_interrupt retarget_msi_interrupt_params; @@ -1356,11 +1359,11 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct irq_cfg *cfg = irqd_cfg(data); struct hv_pcibus_device *hbus; + struct vmbus_channel *channel; struct hv_pci_dev *hpdev; struct pci_bus *pbus; struct pci_dev *pdev; struct cpumask *dest; - unsigned long flags; struct compose_comp_ctxt comp; struct tran_int_desc *int_desc; struct { @@ -1378,6 +1381,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) dest = irq_data_get_effective_affinity_mask(data); pbus = pdev->bus; hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + channel = hbus->hdev->channel; hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); if (!hpdev) goto return_null_message; @@ -1436,42 +1440,51 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) } /* + * Prevents hv_pci_onchannelcallback() from running concurrently + * in the tasklet. + */ + tasklet_disable(&channel->callback_event); + + /* * Since this function is called with IRQ locks held, can't * do normal wait for completion; instead poll. */ while (!try_wait_for_completion(&comp.comp_pkt.host_event)) { + unsigned long flags; + /* 0xFFFF means an invalid PCI VENDOR ID. */ if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) { dev_err_once(&hbus->hdev->device, "the device has gone\n"); - goto free_int_desc; + goto enable_tasklet; } /* - * When the higher level interrupt code calls us with - * interrupt disabled, we must poll the channel by calling - * the channel callback directly when channel->target_cpu is - * the current CPU. When the higher level interrupt code - * calls us with interrupt enabled, let's add the - * local_irq_save()/restore() to avoid race: - * hv_pci_onchannelcallback() can also run in tasklet. + * Make sure that the ring buffer data structure doesn't get + * freed while we dereference the ring buffer pointer. Test + * for the channel's onchannel_callback being NULL within a + * sched_lock critical section. See also the inline comments + * in vmbus_reset_channel_cb(). */ - local_irq_save(flags); - - if (hbus->hdev->channel->target_cpu == smp_processor_id()) - hv_pci_onchannelcallback(hbus); - - local_irq_restore(flags); + spin_lock_irqsave(&channel->sched_lock, flags); + if (unlikely(channel->onchannel_callback == NULL)) { + spin_unlock_irqrestore(&channel->sched_lock, flags); + goto enable_tasklet; + } + hv_pci_onchannelcallback(hbus); + spin_unlock_irqrestore(&channel->sched_lock, flags); if (hpdev->state == hv_pcichild_ejecting) { dev_err_once(&hbus->hdev->device, "the device is being ejected\n"); - goto free_int_desc; + goto enable_tasklet; } udelay(100); } + tasklet_enable(&channel->callback_event); + if (comp.comp_pkt.completion_status < 0) { dev_err(&hbus->hdev->device, "Request for interrupt failed: 0x%x", @@ -1495,6 +1508,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) put_pcichild(hpdev); return; +enable_tasklet: + tasklet_enable(&channel->callback_event); free_int_desc: kfree(int_desc); drop_reference: @@ -2198,10 +2213,8 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus, struct hv_dr_state *dr; int i; - dr = kzalloc(offsetof(struct hv_dr_state, func) + - (sizeof(struct hv_pcidev_description) * - (relations->device_count)), GFP_NOWAIT); - + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); if (!dr) return; @@ -2235,10 +2248,8 @@ static void hv_pci_devices_present2(struct hv_pcibus_device *hbus, struct hv_dr_state *dr; int i; - dr = kzalloc(offsetof(struct hv_dr_state, func) + - (sizeof(struct hv_pcidev_description) * - (relations->device_count)), GFP_NOWAIT); - + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); if (!dr) return; @@ -2432,9 +2443,8 @@ static void hv_pci_onchannelcallback(void *context) bus_rel = (struct pci_bus_relations *)buffer; if (bytes_recvd < - offsetof(struct pci_bus_relations, func) + - (sizeof(struct pci_function_description) * - (bus_rel->device_count))) { + struct_size(bus_rel, func, + bus_rel->device_count)) { dev_err(&hbus->hdev->device, "bus relations too small\n"); break; @@ -2447,9 +2457,8 @@ static void hv_pci_onchannelcallback(void *context) bus_rel2 = (struct pci_bus_relations2 *)buffer; if (bytes_recvd < - offsetof(struct pci_bus_relations2, func) + - (sizeof(struct pci_function_description2) * - (bus_rel2->device_count))) { + struct_size(bus_rel2, func, + bus_rel2->device_count)) { dev_err(&hbus->hdev->device, "bus relations v2 too small\n"); break; @@ -2736,6 +2745,8 @@ static void hv_free_config_window(struct hv_pcibus_device *hbus) vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH); } +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs); + /** * hv_pci_enter_d0() - Bring the "bus" into the D0 power state * @hdev: VMBus's tracking struct for this root PCI bus @@ -2748,8 +2759,10 @@ static int hv_pci_enter_d0(struct hv_device *hdev) struct pci_bus_d0_entry *d0_entry; struct hv_pci_compl comp_pkt; struct pci_packet *pkt; + bool retry = true; int ret; +enter_d0_retry: /* * Tell the host that the bus is ready to use, and moved into the * powered-on state. This includes telling the host which region @@ -2776,6 +2789,38 @@ static int hv_pci_enter_d0(struct hv_device *hdev) if (ret) goto exit; + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + if (comp_pkt.completion_status < 0) { dev_err(&hdev->device, "PCI Pass-through VSP failed D0 Entry with status %x\n", @@ -2847,7 +2892,7 @@ static int hv_send_resources_allocated(struct hv_device *hdev) struct hv_pci_dev *hpdev; struct pci_packet *pkt; size_t size_res; - u32 wslot; + int wslot; int ret; size_res = (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) @@ -2900,6 +2945,8 @@ static int hv_send_resources_allocated(struct hv_device *hdev) comp_pkt.completion_status); break; } + + hbus->wslot_res_allocated = wslot; } kfree(pkt); @@ -2918,10 +2965,10 @@ static int hv_send_resources_released(struct hv_device *hdev) struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); struct pci_child_message pkt; struct hv_pci_dev *hpdev; - u32 wslot; + int wslot; int ret; - for (wslot = 0; wslot < 256; wslot++) { + for (wslot = hbus->wslot_res_allocated; wslot >= 0; wslot--) { hpdev = get_pcichild_wslot(hbus, wslot); if (!hpdev) continue; @@ -2936,8 +2983,12 @@ static int hv_send_resources_released(struct hv_device *hdev) VM_PKT_DATA_INBAND, 0); if (ret) return ret; + + hbus->wslot_res_allocated = wslot - 1; } + hbus->wslot_res_allocated = -1; + return 0; } @@ -3037,6 +3088,7 @@ static int hv_pci_probe(struct hv_device *hdev, if (!hbus) return -ENOMEM; hbus->state = hv_pcibus_init; + hbus->wslot_res_allocated = -1; /* * The PCI bus "domain" is what is called "segment" in ACPI and other @@ -3136,7 +3188,7 @@ static int hv_pci_probe(struct hv_device *hdev, ret = hv_pci_allocate_bridge_windows(hbus); if (ret) - goto free_irq_domain; + goto exit_d0; ret = hv_send_resources_allocated(hdev); if (ret) @@ -3154,6 +3206,8 @@ static int hv_pci_probe(struct hv_device *hdev, free_windows: hv_pci_free_bridge_windows(hbus); +exit_d0: + (void) hv_pci_bus_exit(hdev, true); free_irq_domain: irq_domain_remove(hbus->irq_domain); free_fwnode: @@ -3173,7 +3227,7 @@ free_bus: return ret; } -static int hv_pci_bus_exit(struct hv_device *hdev, bool hibernating) +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) { struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); struct { @@ -3191,7 +3245,7 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool hibernating) if (hdev->channel->rescind) return 0; - if (!hibernating) { + if (!keep_devs) { /* Delete any children which might still exist. */ dr = kzalloc(sizeof(*dr), GFP_KERNEL); if (dr && hv_pci_start_relations_work(hbus, dr)) |