diff options
Diffstat (limited to 'drivers/virtio/virtio_mem.c')
| -rw-r--r-- | drivers/virtio/virtio_mem.c | 206 |
1 files changed, 177 insertions, 29 deletions
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 8e3223294442..56d0dbe62163 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -21,6 +21,8 @@ #include <linux/bitmap.h> #include <linux/lockdep.h> #include <linux/log2.h> +#include <linux/vmalloc.h> +#include <linux/suspend.h> #include <acpi/acpi_numa.h> @@ -131,6 +133,8 @@ struct virtio_mem { uint64_t addr; /* Maximum region size in bytes. */ uint64_t region_size; + /* Usable region size in bytes. */ + uint64_t usable_region_size; /* The parent resource for all memory added via this device. */ struct resource *parent_resource; @@ -252,6 +256,9 @@ struct virtio_mem { /* Memory notifier (online/offline events). */ struct notifier_block memory_notifier; + /* Notifier to block hibernation image storing/reloading. */ + struct notifier_block pm_notifier; + #ifdef CONFIG_PROC_VMCORE /* vmcore callback for /proc/vmcore handling in kdump mode */ struct vmcore_cb vmcore_cb; @@ -1111,6 +1118,25 @@ static int virtio_mem_memory_notifier_cb(struct notifier_block *nb, return rc; } +static int virtio_mem_pm_notifier_cb(struct notifier_block *nb, + unsigned long action, void *arg) +{ + struct virtio_mem *vm = container_of(nb, struct virtio_mem, + pm_notifier); + switch (action) { + case PM_HIBERNATION_PREPARE: + case PM_RESTORE_PREPARE: + /* + * When restarting the VM, all memory is unplugged. Don't + * allow to hibernate and restore from an image. + */ + dev_err(&vm->vdev->dev, "hibernation is not supported.\n"); + return NOTIFY_BAD; + default: + return NOTIFY_OK; + } +} + /* * Set a range of pages PG_offline. Remember pages that were never onlined * (via generic_online_page()) using PageDirty(). @@ -1122,12 +1148,16 @@ static void virtio_mem_set_fake_offline(unsigned long pfn, for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); - __SetPageOffline(page); - if (!onlined) { + if (!onlined) + /* + * Pages that have not been onlined yet were initialized + * to PageOffline(). Remember that we have to route them + * through generic_online_page(). + */ SetPageDirty(page); - /* FIXME: remove after cleanups */ - ClearPageReserved(page); - } + else + __SetPageOffline(page); + VM_WARN_ON_ONCE(!PageOffline(page)); } page_offline_end(); } @@ -1142,9 +1172,11 @@ static void virtio_mem_clear_fake_offline(unsigned long pfn, for (; nr_pages--; pfn++) { struct page *page = pfn_to_page(pfn); - __ClearPageOffline(page); if (!onlined) + /* generic_online_page() will clear PageOffline(). */ ClearPageDirty(page); + else + __ClearPageOffline(page); } } @@ -1239,12 +1271,6 @@ static void virtio_mem_fake_offline_going_offline(unsigned long pfn, struct page *page; unsigned long i; - /* - * Drop our reference to the pages so the memory can get offlined - * and add the unplugged pages to the managed page counters (so - * offlining code can correctly subtract them again). - */ - adjust_managed_page_count(pfn_to_page(pfn), nr_pages); /* Drop our reference to the pages so the memory can get offlined. */ for (i = 0; i < nr_pages; i++) { page = pfn_to_page(pfn + i); @@ -1263,10 +1289,9 @@ static void virtio_mem_fake_offline_cancel_offline(unsigned long pfn, unsigned long i; /* - * Get the reference we dropped when going offline and subtract the - * unplugged pages from the managed page counters. + * Get the reference again that we dropped via page_ref_dec_and_test() + * when going offline. */ - adjust_managed_page_count(pfn_to_page(pfn), -nr_pages); for (i = 0; i < nr_pages; i++) page_ref_inc(pfn_to_page(pfn + i)); } @@ -2345,7 +2370,7 @@ static int virtio_mem_cleanup_pending_mb(struct virtio_mem *vm) static void virtio_mem_refresh_config(struct virtio_mem *vm) { const struct range pluggable_range = mhp_get_pluggable_range(true); - uint64_t new_plugged_size, usable_region_size, end_addr; + uint64_t new_plugged_size, end_addr; /* the plugged_size is just a reflection of what _we_ did previously */ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size, @@ -2355,8 +2380,8 @@ static void virtio_mem_refresh_config(struct virtio_mem *vm) /* calculate the last usable memory block id */ virtio_cread_le(vm->vdev, struct virtio_mem_config, - usable_region_size, &usable_region_size); - end_addr = min(vm->addr + usable_region_size - 1, + usable_region_size, &vm->usable_region_size); + end_addr = min(vm->addr + vm->usable_region_size - 1, pluggable_range.end); if (vm->in_sbm) { @@ -2615,11 +2640,20 @@ static int virtio_mem_init_hotplug(struct virtio_mem *vm) rc = register_memory_notifier(&vm->memory_notifier); if (rc) goto out_unreg_group; - rc = register_virtio_mem_device(vm); + /* Block hibernation as early as possible. */ + vm->pm_notifier.priority = INT_MAX; + vm->pm_notifier.notifier_call = virtio_mem_pm_notifier_cb; + rc = register_pm_notifier(&vm->pm_notifier); if (rc) goto out_unreg_mem; + rc = register_virtio_mem_device(vm); + if (rc) + goto out_unreg_pm; + virtio_device_ready(vm->vdev); return 0; +out_unreg_pm: + unregister_pm_notifier(&vm->pm_notifier); out_unreg_mem: unregister_memory_notifier(&vm->memory_notifier); out_unreg_group: @@ -2694,13 +2728,103 @@ static bool virtio_mem_vmcore_pfn_is_ram(struct vmcore_cb *cb, mutex_unlock(&vm->hotplug_mutex); return is_ram; } + +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM +static int virtio_mem_vmcore_add_device_ram(struct virtio_mem *vm, + struct list_head *list, uint64_t start, uint64_t end) +{ + int rc; + + rc = vmcore_alloc_add_range(list, start, end - start); + if (rc) + dev_err(&vm->vdev->dev, + "Error adding device RAM range: %d\n", rc); + return rc; +} + +static int virtio_mem_vmcore_get_device_ram(struct vmcore_cb *cb, + struct list_head *list) +{ + struct virtio_mem *vm = container_of(cb, struct virtio_mem, + vmcore_cb); + const uint64_t device_start = vm->addr; + const uint64_t device_end = vm->addr + vm->usable_region_size; + uint64_t chunk_size, cur_start, cur_end, plugged_range_start = 0; + LIST_HEAD(tmp_list); + int rc; + + if (!vm->plugged_size) + return 0; + + /* Process memory sections, unless the device block size is bigger. */ + chunk_size = max_t(uint64_t, PFN_PHYS(PAGES_PER_SECTION), + vm->device_block_size); + + mutex_lock(&vm->hotplug_mutex); + + /* + * We process larger chunks and indicate the complete chunk if any + * block in there is plugged. This reduces the number of pfn_is_ram() + * callbacks and mimic what is effectively being done when the old + * kernel would add complete memory sections/blocks to the elfcore hdr. + */ + cur_start = device_start; + for (cur_start = device_start; cur_start < device_end; cur_start = cur_end) { + cur_end = ALIGN_DOWN(cur_start + chunk_size, chunk_size); + cur_end = min_t(uint64_t, cur_end, device_end); + + rc = virtio_mem_send_state_request(vm, cur_start, + cur_end - cur_start); + + if (rc < 0) { + dev_err(&vm->vdev->dev, + "Error querying block states: %d\n", rc); + goto out; + } else if (rc != VIRTIO_MEM_STATE_UNPLUGGED) { + /* Merge ranges with plugged memory. */ + if (!plugged_range_start) + plugged_range_start = cur_start; + continue; + } + + /* Flush any plugged range. */ + if (plugged_range_start) { + rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list, + plugged_range_start, + cur_start); + if (rc) + goto out; + plugged_range_start = 0; + } + } + + /* Flush any plugged range. */ + if (plugged_range_start) + rc = virtio_mem_vmcore_add_device_ram(vm, &tmp_list, + plugged_range_start, + cur_start); +out: + mutex_unlock(&vm->hotplug_mutex); + if (rc < 0) { + vmcore_free_ranges(&tmp_list); + return rc; + } + list_splice_tail(&tmp_list, list); + return 0; +} +#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */ #endif /* CONFIG_PROC_VMCORE */ static int virtio_mem_init_kdump(struct virtio_mem *vm) { + /* We must be prepared to receive a callback immediately. */ + virtio_device_ready(vm->vdev); #ifdef CONFIG_PROC_VMCORE dev_info(&vm->vdev->dev, "memory hot(un)plug disabled in kdump kernel\n"); vm->vmcore_cb.pfn_is_ram = virtio_mem_vmcore_pfn_is_ram; +#ifdef CONFIG_PROC_VMCORE_DEVICE_RAM + vm->vmcore_cb.get_device_ram = virtio_mem_vmcore_get_device_ram; +#endif /* CONFIG_PROC_VMCORE_DEVICE_RAM */ register_vmcore_cb(&vm->vmcore_cb); return 0; #else /* CONFIG_PROC_VMCORE */ @@ -2729,6 +2853,8 @@ static int virtio_mem_init(struct virtio_mem *vm) virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr); virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size, &vm->region_size); + virtio_cread_le(vm->vdev, struct virtio_mem_config, usable_region_size, + &vm->usable_region_size); /* Determine the nid for the device based on the lowest address. */ if (vm->nid == NUMA_NO_NODE) @@ -2824,8 +2950,8 @@ static int virtio_mem_probe(struct virtio_device *vdev) mutex_init(&vm->hotplug_mutex); INIT_LIST_HEAD(&vm->next); spin_lock_init(&vm->removal_lock); - hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - vm->retry_timer.function = virtio_mem_timer_expired; + hrtimer_setup(&vm->retry_timer, virtio_mem_timer_expired, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS; vm->in_kdump = is_kdump_kernel(); @@ -2839,8 +2965,6 @@ static int virtio_mem_probe(struct virtio_device *vdev) if (rc) goto out_del_vq; - virtio_device_ready(vdev); - /* trigger a config update to start processing the requested_size */ if (!vm->in_kdump) { atomic_set(&vm->config_changed, 1); @@ -2897,6 +3021,7 @@ static void virtio_mem_deinit_hotplug(struct virtio_mem *vm) /* unregister callbacks */ unregister_virtio_mem_device(vm); + unregister_pm_notifier(&vm->pm_notifier); unregister_memory_notifier(&vm->memory_notifier); /* @@ -2960,17 +3085,40 @@ static void virtio_mem_config_changed(struct virtio_device *vdev) #ifdef CONFIG_PM_SLEEP static int virtio_mem_freeze(struct virtio_device *vdev) { + struct virtio_mem *vm = vdev->priv; + /* - * When restarting the VM, all memory is usually unplugged. Don't - * allow to suspend/hibernate. + * We block hibernation using the PM notifier completely. The workqueue + * is already frozen by the PM core at this point, so we simply + * reset the device and cleanup the queues. */ - dev_err(&vdev->dev, "save/restore not supported.\n"); - return -EPERM; + if (pm_suspend_target_state != PM_SUSPEND_TO_IDLE && + vm->plugged_size && + !virtio_has_feature(vm->vdev, VIRTIO_MEM_F_PERSISTENT_SUSPEND)) { + dev_err(&vm->vdev->dev, + "suspending with plugged memory is not supported\n"); + return -EPERM; + } + + virtio_reset_device(vdev); + vdev->config->del_vqs(vdev); + vm->vq = NULL; + return 0; } static int virtio_mem_restore(struct virtio_device *vdev) { - return -EPERM; + struct virtio_mem *vm = vdev->priv; + int ret; + + ret = virtio_mem_init_vq(vm); + if (ret) + return ret; + virtio_device_ready(vdev); + + /* Let's check if anything changed. */ + virtio_mem_config_changed(vdev); + return 0; } #endif @@ -2979,6 +3127,7 @@ static unsigned int virtio_mem_features[] = { VIRTIO_MEM_F_ACPI_PXM, #endif VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, + VIRTIO_MEM_F_PERSISTENT_SUSPEND, }; static const struct virtio_device_id virtio_mem_id_table[] = { @@ -2990,7 +3139,6 @@ static struct virtio_driver virtio_mem_driver = { .feature_table = virtio_mem_features, .feature_table_size = ARRAY_SIZE(virtio_mem_features), .driver.name = KBUILD_MODNAME, - .driver.owner = THIS_MODULE, .id_table = virtio_mem_id_table, .probe = virtio_mem_probe, .remove = virtio_mem_remove, |