diff options
Diffstat (limited to 'drivers/block')
38 files changed, 761 insertions, 529 deletions
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c index f781eff7d23e..f6518067aa7d 100644 --- a/drivers/block/DAC960.c +++ b/drivers/block/DAC960.c @@ -1179,7 +1179,6 @@ static bool DAC960_V1_EnableMemoryMailboxInterface(DAC960_Controller_T if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32))) return DAC960_Failure(Controller, "DMA mask out of range"); - Controller->BounceBufferLimit = DMA_BIT_MASK(32); if ((hw_type == DAC960_PD_Controller) || (hw_type == DAC960_P_Controller)) { CommandMailboxesSize = 0; @@ -1380,11 +1379,8 @@ static bool DAC960_V2_EnableMemoryMailboxInterface(DAC960_Controller_T dma_addr_t CommandMailboxDMA; DAC960_V2_CommandStatus_T CommandStatus; - if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64))) - Controller->BounceBufferLimit = DMA_BIT_MASK(64); - else if (!pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32))) - Controller->BounceBufferLimit = DMA_BIT_MASK(32); - else + if (pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(64)) && + pci_set_dma_mask(Controller->PCIDevice, DMA_BIT_MASK(32))) return DAC960_Failure(Controller, "DMA mask out of range"); /* This is a temporary dma mapping, used only in the scope of this function */ @@ -2540,7 +2536,6 @@ static bool DAC960_RegisterBlockDevice(DAC960_Controller_T *Controller) continue; } Controller->RequestQueue[n] = RequestQueue; - blk_queue_bounce_limit(RequestQueue, Controller->BounceBufferLimit); RequestQueue->queuedata = Controller; blk_queue_max_segments(RequestQueue, Controller->DriverScatterGatherLimit); blk_queue_max_hw_sectors(RequestQueue, Controller->MaxBlocksPerCommand); @@ -5724,8 +5719,8 @@ static bool DAC960_CheckStatusBuffer(DAC960_Controller_T *Controller, Controller->CombinedStatusBufferLength = NewStatusBufferLength; return true; } - NewStatusBuffer = kmalloc(2 * Controller->CombinedStatusBufferLength, - GFP_ATOMIC); + NewStatusBuffer = kmalloc_array(2, Controller->CombinedStatusBufferLength, + GFP_ATOMIC); if (NewStatusBuffer == NULL) { DAC960_Warning("Unable to expand Combined Status Buffer - Truncating\n", @@ -6451,19 +6446,6 @@ static int dac960_proc_show(struct seq_file *m, void *v) return 0; } -static int dac960_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, dac960_proc_show, NULL); -} - -static const struct file_operations dac960_proc_fops = { - .owner = THIS_MODULE, - .open = dac960_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int dac960_initial_status_proc_show(struct seq_file *m, void *v) { DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private; @@ -6471,19 +6453,6 @@ static int dac960_initial_status_proc_show(struct seq_file *m, void *v) return 0; } -static int dac960_initial_status_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, dac960_initial_status_proc_show, PDE_DATA(inode)); -} - -static const struct file_operations dac960_initial_status_proc_fops = { - .owner = THIS_MODULE, - .open = dac960_initial_status_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int dac960_current_status_proc_show(struct seq_file *m, void *v) { DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private; @@ -6517,19 +6486,6 @@ static int dac960_current_status_proc_show(struct seq_file *m, void *v) return 0; } -static int dac960_current_status_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, dac960_current_status_proc_show, PDE_DATA(inode)); -} - -static const struct file_operations dac960_current_status_proc_fops = { - .owner = THIS_MODULE, - .open = dac960_current_status_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static int dac960_user_command_proc_show(struct seq_file *m, void *v) { DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private; @@ -6584,17 +6540,19 @@ static void DAC960_CreateProcEntries(DAC960_Controller_T *Controller) if (DAC960_ProcDirectoryEntry == NULL) { DAC960_ProcDirectoryEntry = proc_mkdir("rd", NULL); - proc_create("status", 0, DAC960_ProcDirectoryEntry, - &dac960_proc_fops); + proc_create_single("status", 0, DAC960_ProcDirectoryEntry, + dac960_proc_show); } snprintf(Controller->ControllerName, sizeof(Controller->ControllerName), "c%d", Controller->ControllerNumber); ControllerProcEntry = proc_mkdir(Controller->ControllerName, DAC960_ProcDirectoryEntry); - proc_create_data("initial_status", 0, ControllerProcEntry, &dac960_initial_status_proc_fops, Controller); - proc_create_data("current_status", 0, ControllerProcEntry, &dac960_current_status_proc_fops, Controller); - proc_create_data("user_command", S_IWUSR | S_IRUSR, ControllerProcEntry, &dac960_user_command_proc_fops, Controller); + proc_create_single_data("initial_status", 0, ControllerProcEntry, + dac960_initial_status_proc_show, Controller); + proc_create_single_data("current_status", 0, ControllerProcEntry, + dac960_current_status_proc_show, Controller); + proc_create_data("user_command", 0600, ControllerProcEntry, &dac960_user_command_proc_fops, Controller); Controller->ControllerProcEntry = ControllerProcEntry; } diff --git a/drivers/block/DAC960.h b/drivers/block/DAC960.h index 21aff470d268..1439e651928b 100644 --- a/drivers/block/DAC960.h +++ b/drivers/block/DAC960.h @@ -2295,7 +2295,6 @@ typedef struct DAC960_Controller unsigned short MaxBlocksPerCommand; unsigned short ControllerScatterGatherLimit; unsigned short DriverScatterGatherLimit; - u64 BounceBufferLimit; unsigned int CombinedStatusBufferLength; unsigned int InitialStatusLength; unsigned int CurrentStatusLength; diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 6797e6c23c8a..429ebb84b592 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -159,14 +159,14 @@ static int aoe_debugfs_open(struct inode *inode, struct file *file) return single_open(file, aoedisk_debugfs_show, inode->i_private); } -static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL); -static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL); -static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL); +static DEVICE_ATTR(state, 0444, aoedisk_show_state, NULL); +static DEVICE_ATTR(mac, 0444, aoedisk_show_mac, NULL); +static DEVICE_ATTR(netif, 0444, aoedisk_show_netif, NULL); static struct device_attribute dev_attr_firmware_version = { - .attr = { .name = "firmware-version", .mode = S_IRUGO }, + .attr = { .name = "firmware-version", .mode = 0444 }, .show = aoedisk_show_fwver, }; -static DEVICE_ATTR(payload, S_IRUGO, aoedisk_show_payload, NULL); +static DEVICE_ATTR(payload, 0444, aoedisk_show_payload, NULL); static struct attribute *aoe_attrs[] = { &dev_attr_state.attr, @@ -388,7 +388,6 @@ aoeblk_gdalloc(void *vp) d->aoemajor, d->aoeminor); goto err_mempool; } - blk_queue_bounce_limit(q, BLK_BOUNCE_HIGH); spin_lock_irqsave(&d->lock, flags); WARN_ON(!(d->flags & DEVFL_GD_NOW)); diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index 540bb60cd071..096882e54095 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -1032,8 +1032,9 @@ bvcpy(struct sk_buff *skb, struct bio *bio, struct bvec_iter iter, long cnt) iter.bi_size = cnt; __bio_for_each_segment(bv, bio, iter, iter) { - char *p = page_address(bv.bv_page) + bv.bv_offset; + char *p = kmap_atomic(bv.bv_page) + bv.bv_offset; skb_copy_bits(skb, soff, p, bv.bv_len); + kunmap_atomic(p); soff += bv.bv_len; } } diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 66cb0f857f64..bb976598ee43 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -331,15 +331,15 @@ static const struct block_device_operations brd_fops = { * And now the modules code and kernel interface. */ static int rd_nr = CONFIG_BLK_DEV_RAM_COUNT; -module_param(rd_nr, int, S_IRUGO); +module_param(rd_nr, int, 0444); MODULE_PARM_DESC(rd_nr, "Maximum number of brd devices"); unsigned long rd_size = CONFIG_BLK_DEV_RAM_SIZE; -module_param(rd_size, ulong, S_IRUGO); +module_param(rd_size, ulong, 0444); MODULE_PARM_DESC(rd_size, "Size of each RAM disk in kbytes."); static int max_part = 1; -module_param(max_part, int, S_IRUGO); +module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Num Minors to reserve between devices"); MODULE_LICENSE("GPL"); @@ -402,6 +402,10 @@ static struct brd_device *brd_alloc(int i) set_capacity(disk, rd_size * 2); disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; + /* Tell the block layer that this is not a rotational device */ + blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); + blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); + return brd; out_free_queue: diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index 9f4e6f502b84..11a85b740327 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -977,7 +977,7 @@ static void drbd_bm_endio(struct bio *bio) bm_page_unlock_io(device, idx); if (ctx->flags & BM_AIO_COPY_PAGES) - mempool_free(bio->bi_io_vec[0].bv_page, drbd_md_io_page_pool); + mempool_free(bio->bi_io_vec[0].bv_page, &drbd_md_io_page_pool); bio_put(bio); @@ -1014,7 +1014,8 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho bm_set_page_unchanged(b->bm_pages[page_nr]); if (ctx->flags & BM_AIO_COPY_PAGES) { - page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM); + page = mempool_alloc(&drbd_md_io_page_pool, + GFP_NOIO | __GFP_HIGHMEM); copy_highpage(page, b->bm_pages[page_nr]); bm_store_page_idx(page, page_nr); } else diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c index ab21976a87b2..5d5e8d6a8a56 100644 --- a/drivers/block/drbd/drbd_debugfs.c +++ b/drivers/block/drbd/drbd_debugfs.c @@ -481,9 +481,9 @@ void drbd_debugfs_resource_add(struct drbd_resource *resource) goto fail; resource->debugfs_res_connections = dentry; - dentry = debugfs_create_file("in_flight_summary", S_IRUSR|S_IRGRP, - resource->debugfs_res, resource, - &in_flight_summary_fops); + dentry = debugfs_create_file("in_flight_summary", 0440, + resource->debugfs_res, resource, + &in_flight_summary_fops); if (IS_ERR_OR_NULL(dentry)) goto fail; resource->debugfs_res_in_flight_summary = dentry; @@ -645,16 +645,16 @@ void drbd_debugfs_connection_add(struct drbd_connection *connection) goto fail; connection->debugfs_conn = dentry; - dentry = debugfs_create_file("callback_history", S_IRUSR|S_IRGRP, - connection->debugfs_conn, connection, - &connection_callback_history_fops); + dentry = debugfs_create_file("callback_history", 0440, + connection->debugfs_conn, connection, + &connection_callback_history_fops); if (IS_ERR_OR_NULL(dentry)) goto fail; connection->debugfs_conn_callback_history = dentry; - dentry = debugfs_create_file("oldest_requests", S_IRUSR|S_IRGRP, - connection->debugfs_conn, connection, - &connection_oldest_requests_fops); + dentry = debugfs_create_file("oldest_requests", 0440, + connection->debugfs_conn, connection, + &connection_oldest_requests_fops); if (IS_ERR_OR_NULL(dentry)) goto fail; connection->debugfs_conn_oldest_requests = dentry; @@ -824,7 +824,7 @@ void drbd_debugfs_device_add(struct drbd_device *device) device->debugfs_minor = dentry; #define DCF(name) do { \ - dentry = debugfs_create_file(#name, S_IRUSR|S_IRGRP, \ + dentry = debugfs_create_file(#name, 0440, \ device->debugfs_vol, device, \ &device_ ## name ## _fops); \ if (IS_ERR_OR_NULL(dentry)) \ diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 06ecee1b528e..bc4ed2ed40a2 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1405,8 +1405,8 @@ extern struct kmem_cache *drbd_request_cache; extern struct kmem_cache *drbd_ee_cache; /* peer requests */ extern struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */ extern struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ -extern mempool_t *drbd_request_mempool; -extern mempool_t *drbd_ee_mempool; +extern mempool_t drbd_request_mempool; +extern mempool_t drbd_ee_mempool; /* drbd's page pool, used to buffer data received from the peer, * or data requested by the peer. @@ -1432,16 +1432,16 @@ extern wait_queue_head_t drbd_pp_wait; * 128 should be plenty, currently we probably can get away with as few as 1. */ #define DRBD_MIN_POOL_PAGES 128 -extern mempool_t *drbd_md_io_page_pool; +extern mempool_t drbd_md_io_page_pool; /* We also need to make sure we get a bio * when we need it for housekeeping purposes */ -extern struct bio_set *drbd_md_io_bio_set; +extern struct bio_set drbd_md_io_bio_set; /* to allocate from that set */ extern struct bio *bio_alloc_drbd(gfp_t gfp_mask); /* And a bio_set for cloning */ -extern struct bio_set *drbd_io_bio_set; +extern struct bio_set drbd_io_bio_set; extern struct mutex resources_mutex; @@ -1643,7 +1643,7 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin /* drbd_proc.c */ extern struct proc_dir_entry *drbd_proc; -extern const struct file_operations drbd_proc_fops; +int drbd_seq_show(struct seq_file *seq, void *v); /* drbd_actlog.c */ extern bool drbd_al_begin_io_prepare(struct drbd_device *device, struct drbd_interval *i); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 185f1ef00a7c..a80809bd3057 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -124,11 +124,11 @@ struct kmem_cache *drbd_request_cache; struct kmem_cache *drbd_ee_cache; /* peer requests */ struct kmem_cache *drbd_bm_ext_cache; /* bitmap extents */ struct kmem_cache *drbd_al_ext_cache; /* activity log extents */ -mempool_t *drbd_request_mempool; -mempool_t *drbd_ee_mempool; -mempool_t *drbd_md_io_page_pool; -struct bio_set *drbd_md_io_bio_set; -struct bio_set *drbd_io_bio_set; +mempool_t drbd_request_mempool; +mempool_t drbd_ee_mempool; +mempool_t drbd_md_io_page_pool; +struct bio_set drbd_md_io_bio_set; +struct bio_set drbd_io_bio_set; /* I do not use a standard mempool, because: 1) I want to hand out the pre-allocated objects first. @@ -153,10 +153,10 @@ struct bio *bio_alloc_drbd(gfp_t gfp_mask) { struct bio *bio; - if (!drbd_md_io_bio_set) + if (!bioset_initialized(&drbd_md_io_bio_set)) return bio_alloc(gfp_mask, 1); - bio = bio_alloc_bioset(gfp_mask, 1, drbd_md_io_bio_set); + bio = bio_alloc_bioset(gfp_mask, 1, &drbd_md_io_bio_set); if (!bio) return NULL; return bio; @@ -511,7 +511,8 @@ static void drbd_calc_cpu_mask(cpumask_var_t *cpu_mask) { unsigned int *resources_per_cpu, min_index = ~0; - resources_per_cpu = kzalloc(nr_cpu_ids * sizeof(*resources_per_cpu), GFP_KERNEL); + resources_per_cpu = kcalloc(nr_cpu_ids, sizeof(*resources_per_cpu), + GFP_KERNEL); if (resources_per_cpu) { struct drbd_resource *resource; unsigned int cpu, min = ~0; @@ -2097,16 +2098,11 @@ static void drbd_destroy_mempools(void) /* D_ASSERT(device, atomic_read(&drbd_pp_vacant)==0); */ - if (drbd_io_bio_set) - bioset_free(drbd_io_bio_set); - if (drbd_md_io_bio_set) - bioset_free(drbd_md_io_bio_set); - if (drbd_md_io_page_pool) - mempool_destroy(drbd_md_io_page_pool); - if (drbd_ee_mempool) - mempool_destroy(drbd_ee_mempool); - if (drbd_request_mempool) - mempool_destroy(drbd_request_mempool); + bioset_exit(&drbd_io_bio_set); + bioset_exit(&drbd_md_io_bio_set); + mempool_exit(&drbd_md_io_page_pool); + mempool_exit(&drbd_ee_mempool); + mempool_exit(&drbd_request_mempool); if (drbd_ee_cache) kmem_cache_destroy(drbd_ee_cache); if (drbd_request_cache) @@ -2116,11 +2112,6 @@ static void drbd_destroy_mempools(void) if (drbd_al_ext_cache) kmem_cache_destroy(drbd_al_ext_cache); - drbd_io_bio_set = NULL; - drbd_md_io_bio_set = NULL; - drbd_md_io_page_pool = NULL; - drbd_ee_mempool = NULL; - drbd_request_mempool = NULL; drbd_ee_cache = NULL; drbd_request_cache = NULL; drbd_bm_ext_cache = NULL; @@ -2133,18 +2124,7 @@ static int drbd_create_mempools(void) { struct page *page; const int number = (DRBD_MAX_BIO_SIZE/PAGE_SIZE) * drbd_minor_count; - int i; - - /* prepare our caches and mempools */ - drbd_request_mempool = NULL; - drbd_ee_cache = NULL; - drbd_request_cache = NULL; - drbd_bm_ext_cache = NULL; - drbd_al_ext_cache = NULL; - drbd_pp_pool = NULL; - drbd_md_io_page_pool = NULL; - drbd_md_io_bio_set = NULL; - drbd_io_bio_set = NULL; + int i, ret; /* caches */ drbd_request_cache = kmem_cache_create( @@ -2168,26 +2148,26 @@ static int drbd_create_mempools(void) goto Enomem; /* mempools */ - drbd_io_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0); - if (drbd_io_bio_set == NULL) + ret = bioset_init(&drbd_io_bio_set, BIO_POOL_SIZE, 0, 0); + if (ret) goto Enomem; - drbd_md_io_bio_set = bioset_create(DRBD_MIN_POOL_PAGES, 0, - BIOSET_NEED_BVECS); - if (drbd_md_io_bio_set == NULL) + ret = bioset_init(&drbd_md_io_bio_set, DRBD_MIN_POOL_PAGES, 0, + BIOSET_NEED_BVECS); + if (ret) goto Enomem; - drbd_md_io_page_pool = mempool_create_page_pool(DRBD_MIN_POOL_PAGES, 0); - if (drbd_md_io_page_pool == NULL) + ret = mempool_init_page_pool(&drbd_md_io_page_pool, DRBD_MIN_POOL_PAGES, 0); + if (ret) goto Enomem; - drbd_request_mempool = mempool_create_slab_pool(number, - drbd_request_cache); - if (drbd_request_mempool == NULL) + ret = mempool_init_slab_pool(&drbd_request_mempool, number, + drbd_request_cache); + if (ret) goto Enomem; - drbd_ee_mempool = mempool_create_slab_pool(number, drbd_ee_cache); - if (drbd_ee_mempool == NULL) + ret = mempool_init_slab_pool(&drbd_ee_mempool, number, drbd_ee_cache); + if (ret) goto Enomem; /* drbd's page pool */ @@ -3010,7 +2990,7 @@ static int __init drbd_init(void) goto fail; err = -ENOMEM; - drbd_proc = proc_create_data("drbd", S_IFREG | S_IRUGO , NULL, &drbd_proc_fops, NULL); + drbd_proc = proc_create_single("drbd", S_IFREG | 0444 , NULL, drbd_seq_show); if (!drbd_proc) { pr_err("unable to register proc file\n"); goto fail; diff --git a/drivers/block/drbd/drbd_proc.c b/drivers/block/drbd/drbd_proc.c index 582caeb0de86..74ef29247bb5 100644 --- a/drivers/block/drbd/drbd_proc.c +++ b/drivers/block/drbd/drbd_proc.c @@ -33,18 +33,7 @@ #include <linux/drbd.h> #include "drbd_int.h" -static int drbd_proc_open(struct inode *inode, struct file *file); -static int drbd_proc_release(struct inode *inode, struct file *file); - - struct proc_dir_entry *drbd_proc; -const struct file_operations drbd_proc_fops = { - .owner = THIS_MODULE, - .open = drbd_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = drbd_proc_release, -}; static void seq_printf_with_thousands_grouping(struct seq_file *seq, long v) { @@ -235,7 +224,7 @@ static void drbd_syncer_progress(struct drbd_device *device, struct seq_file *se } } -static int drbd_seq_show(struct seq_file *seq, void *v) +int drbd_seq_show(struct seq_file *seq, void *v) { int i, prev_i = -1; const char *sn; @@ -345,24 +334,3 @@ static int drbd_seq_show(struct seq_file *seq, void *v) return 0; } - -static int drbd_proc_open(struct inode *inode, struct file *file) -{ - int err; - - if (try_module_get(THIS_MODULE)) { - err = single_open(file, drbd_seq_show, NULL); - if (err) - module_put(THIS_MODULE); - return err; - } - return -ENODEV; -} - -static int drbd_proc_release(struct inode *inode, struct file *file) -{ - module_put(THIS_MODULE); - return single_release(inode, file); -} - -/* PROC FS stuff end */ diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c72dee0ef083..be9450f5ad1c 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -378,7 +378,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto if (drbd_insert_fault(device, DRBD_FAULT_AL_EE)) return NULL; - peer_req = mempool_alloc(drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM); + peer_req = mempool_alloc(&drbd_ee_mempool, gfp_mask & ~__GFP_HIGHMEM); if (!peer_req) { if (!(gfp_mask & __GFP_NOWARN)) drbd_err(device, "%s: allocation failed\n", __func__); @@ -409,7 +409,7 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto return peer_req; fail: - mempool_free(peer_req, drbd_ee_mempool); + mempool_free(peer_req, &drbd_ee_mempool); return NULL; } @@ -426,7 +426,7 @@ void __drbd_free_peer_req(struct drbd_device *device, struct drbd_peer_request * peer_req->flags &= ~EE_CALL_AL_COMPLETE_IO; drbd_al_complete_io(device, &peer_req->i); } - mempool_free(peer_req, drbd_ee_mempool); + mempool_free(peer_req, &drbd_ee_mempool); } int drbd_free_peer_reqs(struct drbd_device *device, struct list_head *list) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index a500e738d929..d146fedc38bb 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -55,7 +55,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio { struct drbd_request *req; - req = mempool_alloc(drbd_request_mempool, GFP_NOIO); + req = mempool_alloc(&drbd_request_mempool, GFP_NOIO); if (!req) return NULL; memset(req, 0, sizeof(*req)); @@ -184,7 +184,7 @@ void drbd_req_destroy(struct kref *kref) } } - mempool_free(req, drbd_request_mempool); + mempool_free(req, &drbd_request_mempool); } static void wake_all_senders(struct drbd_connection *connection) @@ -1244,8 +1244,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long _drbd_start_io_acct(device, req); /* process discards always from our submitter thread */ - if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) || - (bio_op(bio) & REQ_OP_DISCARD)) + if (bio_op(bio) == REQ_OP_WRITE_ZEROES || + bio_op(bio) == REQ_OP_DISCARD) goto queue_for_submitter_thread; if (rw == WRITE && req->private_bio && req->i.size diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h index cb97b3b30962..94c654020f0f 100644 --- a/drivers/block/drbd/drbd_req.h +++ b/drivers/block/drbd/drbd_req.h @@ -269,7 +269,7 @@ enum drbd_req_state_bits { static inline void drbd_req_make_private_bio(struct drbd_request *req, struct bio *bio_src) { struct bio *bio; - bio = bio_clone_fast(bio_src, GFP_NOIO, drbd_io_bio_set); + bio = bio_clone_fast(bio_src, GFP_NOIO, &drbd_io_bio_set); req->private_bio = bio; diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c index 1476cb3439f4..5e793dd7adfb 100644 --- a/drivers/block/drbd/drbd_worker.c +++ b/drivers/block/drbd/drbd_worker.c @@ -282,8 +282,8 @@ void drbd_request_endio(struct bio *bio) what = COMPLETED_OK; } - bio_put(req->private_bio); req->private_bio = ERR_PTR(blk_status_to_errno(bio->bi_status)); + bio_put(bio); /* not req_mod(), we need irqsave here! */ spin_lock_irqsave(&device->resource->req_lock, flags); diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 8ec7235fc93b..8871b5044d9e 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4450,7 +4450,7 @@ static ssize_t floppy_cmos_show(struct device *dev, return sprintf(buf, "%X\n", UDP->cmos); } -static DEVICE_ATTR(cmos, S_IRUGO, floppy_cmos_show, NULL); +static DEVICE_ATTR(cmos, 0444, floppy_cmos_show, NULL); static struct attribute *floppy_dev_attrs[] = { &dev_attr_cmos.attr, diff --git a/drivers/block/loop.c b/drivers/block/loop.c index c9d04497a415..4cb1d1be3cfb 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -76,6 +76,8 @@ #include <linux/miscdevice.h> #include <linux/falloc.h> #include <linux/uio.h> +#include <linux/ioprio.h> + #include "loop.h" #include <linux/uaccess.h> @@ -451,25 +453,47 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq) static void lo_complete_rq(struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); + blk_status_t ret = BLK_STS_OK; - if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio && - cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) { - struct bio *bio = cmd->rq->bio; - - bio_advance(bio, cmd->ret); - zero_fill_bio(bio); + if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || + req_op(rq) != REQ_OP_READ) { + if (cmd->ret < 0) + ret = BLK_STS_IOERR; + goto end_io; } - blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK); + /* + * Short READ - if we got some data, advance our request and + * retry it. If we got no data, end the rest with EIO. + */ + if (cmd->ret) { + blk_update_request(rq, BLK_STS_OK, cmd->ret); + cmd->ret = 0; + blk_mq_requeue_request(rq, true); + } else { + if (cmd->use_aio) { + struct bio *bio = rq->bio; + + while (bio) { + zero_fill_bio(bio); + bio = bio->bi_next; + } + } + ret = BLK_STS_IOERR; +end_io: + blk_mq_end_request(rq, ret); + } } static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { + struct request *rq = blk_mq_rq_from_pdu(cmd); + if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2) @@ -487,7 +511,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, { struct iov_iter iter; struct bio_vec *bvec; - struct request *rq = cmd->rq; + struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; unsigned int offset; @@ -500,7 +524,8 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, __rq_for_each_bio(bio, rq) segments += bio_segments(bio); - bvec = kmalloc(sizeof(struct bio_vec) * segments, GFP_NOIO); + bvec = kmalloc_array(segments, sizeof(struct bio_vec), + GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; @@ -537,6 +562,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, cmd->iocb.ki_filp = file; cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; + cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0); if (cmd->css) kthread_associate_blkcg(cmd->css); @@ -622,6 +648,36 @@ static void loop_reread_partitions(struct loop_device *lo, __func__, lo->lo_number, lo->lo_file_name, rc); } +static inline int is_loop_device(struct file *file) +{ + struct inode *i = file->f_mapping->host; + + return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; +} + +static int loop_validate_file(struct file *file, struct block_device *bdev) +{ + struct inode *inode = file->f_mapping->host; + struct file *f = file; + + /* Avoid recursion */ + while (is_loop_device(f)) { + struct loop_device *l; + + if (f->f_mapping->host->i_bdev == bdev) + return -EBADF; + + l = f->f_mapping->host->i_bdev->bd_disk->private_data; + if (l->lo_state == Lo_unbound) { + return -EINVAL; + } + f = l->lo_backing_file; + } + if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) + return -EINVAL; + return 0; +} + /* * loop_change_fd switched the backing store of a loopback device to * a new file. This is useful for operating system installers to free up @@ -651,14 +707,15 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, if (!file) goto out; + error = loop_validate_file(file, bdev); + if (error) + goto out_putf; + inode = file->f_mapping->host; old_file = lo->lo_backing_file; error = -EINVAL; - if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) - goto out_putf; - /* size of the new backing store needs to be the same */ if (get_loop_size(lo, file) != get_loop_size(lo, old_file)) goto out_putf; @@ -684,13 +741,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev, return error; } -static inline int is_loop_device(struct file *file) -{ - struct inode *i = file->f_mapping->host; - - return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR; -} - /* loop sysfs attributes */ static ssize_t loop_attr_show(struct device *dev, char *page, @@ -710,7 +760,7 @@ static ssize_t loop_attr_do_show_##_name(struct device *d, \ return loop_attr_show(d, b, loop_attr_##_name##_show); \ } \ static struct device_attribute loop_attr_##_name = \ - __ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL); + __ATTR(_name, 0444, loop_attr_do_show_##_name, NULL); static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) { @@ -787,16 +837,17 @@ static struct attribute_group loop_attribute_group = { .attrs= loop_attrs, }; -static int loop_sysfs_init(struct loop_device *lo) +static void loop_sysfs_init(struct loop_device *lo) { - return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, - &loop_attribute_group); + lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj, + &loop_attribute_group); } static void loop_sysfs_exit(struct loop_device *lo) { - sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, - &loop_attribute_group); + if (lo->sysfs_inited) + sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj, + &loop_attribute_group); } static void loop_config_discard(struct loop_device *lo) @@ -855,7 +906,7 @@ static int loop_prepare_queue(struct loop_device *lo) static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct block_device *bdev, unsigned int arg) { - struct file *file, *f; + struct file *file; struct inode *inode; struct address_space *mapping; int lo_flags = 0; @@ -874,29 +925,13 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (lo->lo_state != Lo_unbound) goto out_putf; - /* Avoid recursion */ - f = file; - while (is_loop_device(f)) { - struct loop_device *l; - - if (f->f_mapping->host->i_bdev == bdev) - goto out_putf; - - l = f->f_mapping->host->i_bdev->bd_disk->private_data; - if (l->lo_state == Lo_unbound) { - error = -EINVAL; - goto out_putf; - } - f = l->lo_backing_file; - } + error = loop_validate_file(file, bdev); + if (error) + goto out_putf; mapping = file->f_mapping; inode = mapping->host; - error = -EINVAL; - if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode)) - goto out_putf; - if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) || !file->f_op->write_iter) lo_flags |= LO_FLAGS_READ_ONLY; @@ -1046,6 +1081,7 @@ static int loop_clr_fd(struct loop_device *lo) if (bdev) { bdput(bdev); invalidate_bdev(bdev); + bdev->bd_inode->i_mapping->wb_err = 0; } set_capacity(lo->lo_disk, 0); loop_sysfs_exit(lo); @@ -1577,6 +1613,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, arg = (unsigned long) compat_ptr(arg); case LOOP_SET_FD: case LOOP_CHANGE_FD: + case LOOP_SET_BLOCK_SIZE: err = lo_ioctl(bdev, mode, cmd, arg); break; default: @@ -1654,9 +1691,9 @@ static const struct block_device_operations lo_fops = { * And now the modules code and kernel interface. */ static int max_loop; -module_param(max_loop, int, S_IRUGO); +module_param(max_loop, int, 0444); MODULE_PARM_DESC(max_loop, "Maximum number of loop devices"); -module_param(max_part, int, S_IRUGO); +module_param(max_part, int, 0444); MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); @@ -1702,15 +1739,16 @@ EXPORT_SYMBOL(loop_unregister_transfer); static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { - struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq); - struct loop_device *lo = cmd->rq->q->queuedata; + struct request *rq = bd->rq; + struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); + struct loop_device *lo = rq->q->queuedata; - blk_mq_start_request(bd->rq); + blk_mq_start_request(rq); if (lo->lo_state != Lo_bound) return BLK_STS_IOERR; - switch (req_op(cmd->rq)) { + switch (req_op(rq)) { case REQ_OP_FLUSH: case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: @@ -1723,8 +1761,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP - if (cmd->use_aio && cmd->rq->bio && cmd->rq->bio->bi_css) { - cmd->css = cmd->rq->bio->bi_css; + if (cmd->use_aio && rq->bio && rq->bio->bi_css) { + cmd->css = rq->bio->bi_css; css_get(cmd->css); } else #endif @@ -1736,8 +1774,9 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, static void loop_handle_cmd(struct loop_cmd *cmd) { - const bool write = op_is_write(req_op(cmd->rq)); - struct loop_device *lo = cmd->rq->q->queuedata; + struct request *rq = blk_mq_rq_from_pdu(cmd); + const bool write = op_is_write(req_op(rq)); + struct loop_device *lo = rq->q->queuedata; int ret = 0; if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) { @@ -1745,12 +1784,12 @@ static void loop_handle_cmd(struct loop_cmd *cmd) goto failed; } - ret = do_req_filebacked(lo, cmd->rq); + ret = do_req_filebacked(lo, rq); failed: /* complete non-aio request */ if (!cmd->use_aio || ret) { cmd->ret = ret ? -EIO : 0; - blk_mq_complete_request(cmd->rq); + blk_mq_complete_request(rq); } } @@ -1767,9 +1806,7 @@ static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); - cmd->rq = rq; kthread_init_work(&cmd->work, loop_queue_work); - return 0; } diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 0f45416e4fcf..4d42c7af7de7 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -58,6 +58,7 @@ struct loop_device { struct kthread_worker worker; struct task_struct *worker_task; bool use_dio; + bool sysfs_inited; struct request_queue *lo_queue; struct blk_mq_tag_set tag_set; @@ -66,7 +67,6 @@ struct loop_device { struct loop_cmd { struct kthread_work work; - struct request *rq; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret; diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 769c551e3d71..c73626decb46 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2285,7 +2285,7 @@ static ssize_t mtip_hw_show_status(struct device *dev, return size; } -static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); +static DEVICE_ATTR(status, 0444, mtip_hw_show_status, NULL); /* debugsfs entries */ @@ -2566,10 +2566,9 @@ static int mtip_hw_debugfs_init(struct driver_data *dd) return -1; } - debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd, - &mtip_flags_fops); - debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd, - &mtip_regs_fops); + debugfs_create_file("flags", 0444, dd->dfs_node, dd, &mtip_flags_fops); + debugfs_create_file("registers", 0444, dd->dfs_node, dd, + &mtip_regs_fops); return 0; } @@ -2726,15 +2725,11 @@ static void mtip_softirq_done_fn(struct request *rq) blk_mq_end_request(rq, cmd->status); } -static void mtip_abort_cmd(struct request *req, void *data, - bool reserved) +static void mtip_abort_cmd(struct request *req, void *data, bool reserved) { struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req); struct driver_data *dd = data; - if (!blk_mq_request_started(req)) - return; - dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag); clear_bit(req->tag, dd->port->cmds_to_issue); @@ -2742,14 +2737,10 @@ static void mtip_abort_cmd(struct request *req, void *data, mtip_softirq_done_fn(req); } -static void mtip_queue_cmd(struct request *req, void *data, - bool reserved) +static void mtip_queue_cmd(struct request *req, void *data, bool reserved) { struct driver_data *dd = data; - if (!blk_mq_request_started(req)) - return; - set_bit(req->tag, dd->port->cmds_to_issue); blk_abort_request(req); } @@ -3720,7 +3711,8 @@ static enum blk_eh_timer_return mtip_cmd_timeout(struct request *req, struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req); cmd->status = BLK_STS_TIMEOUT; - return BLK_EH_HANDLED; + blk_mq_complete_request(req); + return BLK_EH_DONE; } if (test_bit(req->tag, dd->port->cmds_to_issue)) @@ -3862,7 +3854,6 @@ skip_create_disk: blk_queue_max_hw_sectors(dd->queue, 0xffff); blk_queue_max_segment_size(dd->queue, 0x400000); blk_queue_io_min(dd->queue, 4096); - blk_queue_bounce_limit(dd->queue, dd->pdev->dma_mask); /* Signal trim support */ if (dd->trim_supp == true) { @@ -4273,7 +4264,7 @@ static int mtip_pci_probe(struct pci_dev *pdev, if (!dd->isr_workq) { dev_warn(&pdev->dev, "Can't create wq %d\n", dd->instance); rv = -ENOMEM; - goto block_initialize_err; + goto setmask_err; } memset(cpu_list, 0, sizeof(cpu_list)); @@ -4614,7 +4605,7 @@ static int __init mtip_init(void) } if (dfs_parent) { dfs_device_status = debugfs_create_file("device_status", - S_IRUGO, dfs_parent, NULL, + 0444, dfs_parent, NULL, &mtip_device_status_fops); if (IS_ERR_OR_NULL(dfs_device_status)) { pr_err("Error creating device_status node\n"); diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index afbc202ca6fd..3fb95c8d9fd8 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -76,6 +76,7 @@ struct link_dead_args { #define NBD_HAS_CONFIG_REF 4 #define NBD_BOUND 5 #define NBD_DESTROY_ON_DISCONNECT 6 +#define NBD_DISCONNECT_ON_CLOSE 7 struct nbd_config { u32 flags; @@ -111,12 +112,16 @@ struct nbd_device { struct task_struct *task_setup; }; +#define NBD_CMD_REQUEUED 1 + struct nbd_cmd { struct nbd_device *nbd; + struct mutex lock; int index; int cookie; - struct completion send_complete; blk_status_t status; + unsigned long flags; + u32 cmd_cookie; }; #if IS_ENABLED(CONFIG_DEBUG_FS) @@ -138,12 +143,42 @@ static void nbd_config_put(struct nbd_device *nbd); static void nbd_connect_reply(struct genl_info *info, int index); static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info); static void nbd_dead_link_work(struct work_struct *work); +static void nbd_disconnect_and_put(struct nbd_device *nbd); static inline struct device *nbd_to_dev(struct nbd_device *nbd) { return disk_to_dev(nbd->disk); } +static void nbd_requeue_cmd(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) + blk_mq_requeue_request(req, true); +} + +#define NBD_COOKIE_BITS 32 + +static u64 nbd_cmd_handle(struct nbd_cmd *cmd) +{ + struct request *req = blk_mq_rq_from_pdu(cmd); + u32 tag = blk_mq_unique_tag(req); + u64 cookie = cmd->cmd_cookie; + + return (cookie << NBD_COOKIE_BITS) | tag; +} + +static u32 nbd_handle_to_tag(u64 handle) +{ + return (u32)handle; +} + +static u32 nbd_handle_to_cookie(u64 handle) +{ + return (u32)(handle >> NBD_COOKIE_BITS); +} + static const char *nbdcmd_to_ascii(int cmd) { switch (cmd) { @@ -166,16 +201,19 @@ static ssize_t pid_show(struct device *dev, } static const struct device_attribute pid_attr = { - .attr = { .name = "pid", .mode = S_IRUGO}, + .attr = { .name = "pid", .mode = 0444}, .show = pid_show, }; static void nbd_dev_remove(struct nbd_device *nbd) { struct gendisk *disk = nbd->disk; + struct request_queue *q; + if (disk) { + q = disk->queue; del_gendisk(disk); - blk_cleanup_queue(disk->queue); + blk_cleanup_queue(q); blk_mq_free_tag_set(&nbd->tag_set); disk->private_data = NULL; put_disk(disk); @@ -213,7 +251,15 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock, } if (!nsock->dead) { kernel_sock_shutdown(nsock->sock, SHUT_RDWR); - atomic_dec(&nbd->config->live_connections); + if (atomic_dec_return(&nbd->config->live_connections) == 0) { + if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED, + &nbd->config->runtime_flags)) { + set_bit(NBD_DISCONNECTED, + &nbd->config->runtime_flags); + dev_info(nbd_to_dev(nbd), + "Disconnected due to user request.\n"); + } + } } nsock->dead = true; nsock->pending = NULL; @@ -231,9 +277,23 @@ static void nbd_size_clear(struct nbd_device *nbd) static void nbd_size_update(struct nbd_device *nbd) { struct nbd_config *config = nbd->config; + struct block_device *bdev = bdget_disk(nbd->disk, 0); + + if (config->flags & NBD_FLAG_SEND_TRIM) { + nbd->disk->queue->limits.discard_granularity = config->blksize; + nbd->disk->queue->limits.discard_alignment = config->blksize; + blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); + } blk_queue_logical_block_size(nbd->disk->queue, config->blksize); blk_queue_physical_block_size(nbd->disk->queue, config->blksize); set_capacity(nbd->disk, config->bytesize >> 9); + if (bdev) { + if (bdev->bd_disk) + bd_set_size(bdev, config->bytesize); + else + bdev->bd_invalidated = 1; + bdput(bdev); + } kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE); } @@ -243,13 +303,15 @@ static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize, struct nbd_config *config = nbd->config; config->blksize = blocksize; config->bytesize = blocksize * nr_blocks; + if (nbd->task_recv != NULL) + nbd_size_update(nbd); } static void nbd_complete_rq(struct request *req) { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); - dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd, + dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", req, cmd->status ? "failed" : "done"); blk_mq_end_request(req, cmd->status); @@ -286,13 +348,18 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, if (!refcount_inc_not_zero(&nbd->config_refs)) { cmd->status = BLK_STS_TIMEOUT; - return BLK_EH_HANDLED; + goto done; } config = nbd->config; + if (!mutex_trylock(&cmd->lock)) + return BLK_EH_RESET_TIMER; + if (config->num_connections > 1) { dev_err_ratelimited(nbd_to_dev(nbd), - "Connection timed out, retrying\n"); + "Connection timed out, retrying (%d/%d alive)\n", + atomic_read(&config->live_connections), + config->num_connections); /* * Hooray we have more connections, requeue this IO, the submit * path will put it on a real connection. @@ -312,9 +379,10 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - blk_mq_requeue_request(req, true); + mutex_unlock(&cmd->lock); + nbd_requeue_cmd(cmd); nbd_config_put(nbd); - return BLK_EH_NOT_HANDLED; + return BLK_EH_DONE; } } else { dev_err_ratelimited(nbd_to_dev(nbd), @@ -322,10 +390,12 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, } set_bit(NBD_TIMEDOUT, &config->runtime_flags); cmd->status = BLK_STS_IOERR; + mutex_unlock(&cmd->lock); sock_shutdown(nbd); nbd_config_put(nbd); - - return BLK_EH_HANDLED; +done: + blk_mq_complete_request(req); + return BLK_EH_DONE; } /* @@ -398,9 +468,9 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) struct iov_iter from; unsigned long size = blk_rq_bytes(req); struct bio *bio; + u64 handle; u32 type; u32 nbd_cmd_flags = 0; - u32 tag = blk_mq_unique_tag(req); int sent = nsock->sent, skip = 0; iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); @@ -442,6 +512,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) goto send_pages; } iov_iter_advance(&from, sent); + } else { + cmd->cmd_cookie++; } cmd->index = index; cmd->cookie = nsock->cookie; @@ -450,10 +522,11 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9); request.len = htonl(size); } - memcpy(request.handle, &tag, sizeof(tag)); + handle = nbd_cmd_handle(cmd); + memcpy(request.handle, &handle, sizeof(handle)); dev_dbg(nbd_to_dev(nbd), "request %p: sending control (%s@%llu,%uB)\n", - cmd, nbdcmd_to_ascii(type), + req, nbdcmd_to_ascii(type), (unsigned long long)blk_rq_pos(req) << 9, blk_rq_bytes(req)); result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); @@ -468,6 +541,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) nsock->pending = req; nsock->sent = sent; } + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err_ratelimited(disk_to_dev(nbd->disk), @@ -489,7 +563,7 @@ send_pages: int flags = is_last ? 0 : MSG_MORE; dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", - cmd, bvec.bv_len); + req, bvec.bv_len); iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, bvec.bv_len); if (skip) { @@ -509,6 +583,7 @@ send_pages: */ nsock->pending = req; nsock->sent = sent; + set_bit(NBD_CMD_REQUEUED, &cmd->flags); return BLK_STS_RESOURCE; } dev_err(disk_to_dev(nbd->disk), @@ -541,10 +616,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; + u64 handle; u16 hwq; u32 tag; struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; struct iov_iter to; + int ret = 0; reply.magic = 0; iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); @@ -562,8 +639,8 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-EPROTO); } - memcpy(&tag, reply.handle, sizeof(u32)); - + memcpy(&handle, reply.handle, sizeof(handle)); + tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) req = blk_mq_tag_to_rq(nbd->tag_set.tags[hwq], @@ -574,14 +651,28 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) return ERR_PTR(-ENOENT); } cmd = blk_mq_rq_to_pdu(req); + + mutex_lock(&cmd->lock); + if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { + dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", + req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); + ret = -ENOENT; + goto out; + } + if (test_bit(NBD_CMD_REQUEUED, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Raced with timeout on req %p\n", + req); + ret = -ENOENT; + goto out; + } if (ntohl(reply.error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", ntohl(reply.error)); cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", cmd); + dev_dbg(nbd_to_dev(nbd), "request %p: got reply\n", req); if (rq_data_dir(req) != WRITE) { struct req_iterator iter; struct bio_vec bvec; @@ -603,18 +694,18 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (nbd_disconnected(config) || config->num_connections <= 1) { cmd->status = BLK_STS_IOERR; - return cmd; + goto out; } - return ERR_PTR(-EIO); + ret = -EIO; + goto out; } dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n", - cmd, bvec.bv_len); + req, bvec.bv_len); } - } else { - /* See the comment in nbd_queue_rq. */ - wait_for_completion(&cmd->send_complete); } - return cmd; +out: + mutex_unlock(&cmd->lock); + return ret ? ERR_PTR(ret) : cmd; } static void recv_work(struct work_struct *work) @@ -647,11 +738,8 @@ static void recv_work(struct work_struct *work) static void nbd_clear_req(struct request *req, void *data, bool reserved) { - struct nbd_cmd *cmd; + struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req); - if (!blk_mq_request_started(req)) - return; - cmd = blk_mq_rq_to_pdu(req); cmd->status = BLK_STS_IOERR; blk_mq_complete_request(req); } @@ -714,10 +802,9 @@ static int wait_for_reconnect(struct nbd_device *nbd) return 0; if (test_bit(NBD_DISCONNECTED, &config->runtime_flags)) return 0; - wait_event_timeout(config->conn_wait, - atomic_read(&config->live_connections), - config->dead_conn_timeout); - return atomic_read(&config->live_connections); + return wait_event_timeout(config->conn_wait, + atomic_read(&config->live_connections) > 0, + config->dead_conn_timeout) > 0; } static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) @@ -777,7 +864,7 @@ again: */ blk_mq_start_request(req); if (unlikely(nsock->pending && nsock->pending != req)) { - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; goto out; } @@ -790,7 +877,7 @@ again: dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); - blk_mq_requeue_request(req, true); + nbd_requeue_cmd(cmd); ret = 0; } out: @@ -814,7 +901,8 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, * that the server is misbehaving (or there was an error) before we're * done sending everything over the wire. */ - init_completion(&cmd->send_complete); + mutex_lock(&cmd->lock); + clear_bit(NBD_CMD_REQUEUED, &cmd->flags); /* We can be called directly from the user space process, which means we * could possibly have signals pending so our sendmsg will fail. In @@ -826,7 +914,7 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx, ret = BLK_STS_IOERR; else if (!ret) ret = BLK_STS_OK; - complete(&cmd->send_complete); + mutex_unlock(&cmd->lock); return ret; } @@ -950,10 +1038,6 @@ static void nbd_bdev_reset(struct block_device *bdev) if (bdev->bd_openers > 1) return; bd_set_size(bdev, 0); - if (max_part > 0) { - blkdev_reread_part(bdev); - bdev->bd_invalidated = 1; - } } static void nbd_parse_flags(struct nbd_device *nbd) @@ -1040,6 +1124,9 @@ static void nbd_config_put(struct nbd_device *nbd) nbd->config = NULL; nbd->tag_set.timeout = 0; + nbd->disk->queue->limits.discard_granularity = 0; + nbd->disk->queue->limits.discard_alignment = 0; + blk_queue_max_discard_sectors(nbd->disk->queue, UINT_MAX); blk_queue_flag_clear(QUEUE_FLAG_DISCARD, nbd->disk->queue); mutex_unlock(&nbd->config_lock); @@ -1109,7 +1196,6 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b if (ret) return ret; - bd_set_size(bdev, config->bytesize); if (max_part) bdev->bd_invalidated = 1; mutex_unlock(&nbd->config_lock); @@ -1118,7 +1204,7 @@ static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *b if (ret) sock_shutdown(nbd); mutex_lock(&nbd->config_lock); - bd_set_size(bdev, 0); + nbd_bdev_reset(bdev); /* user requested, ignore socket errors */ if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags)) ret = 0; @@ -1269,6 +1355,9 @@ static int nbd_open(struct block_device *bdev, fmode_t mode) refcount_set(&nbd->config_refs, 1); refcount_inc(&nbd->refs); mutex_unlock(&nbd->config_lock); + bdev->bd_invalidated = 1; + } else if (nbd_disconnected(nbd->config)) { + bdev->bd_invalidated = 1; } out: mutex_unlock(&nbd_index_mutex); @@ -1278,6 +1367,12 @@ out: static void nbd_release(struct gendisk *disk, fmode_t mode) { struct nbd_device *nbd = disk->private_data; + struct block_device *bdev = bdget_disk(disk, 0); + + if (test_bit(NBD_DISCONNECT_ON_CLOSE, &nbd->config->runtime_flags) && + bdev->bd_openers == 0) + nbd_disconnect_and_put(nbd); + nbd_config_put(nbd); nbd_put(nbd); } @@ -1425,6 +1520,8 @@ static int nbd_init_request(struct blk_mq_tag_set *set, struct request *rq, { struct nbd_cmd *cmd = blk_mq_rq_to_pdu(rq); cmd->nbd = set->driver_data; + cmd->flags = 0; + mutex_init(&cmd->lock); return 0; } @@ -1490,8 +1587,9 @@ static int nbd_dev_add(int index) */ blk_queue_flag_set(QUEUE_FLAG_NONROT, disk->queue); blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, disk->queue); - disk->queue->limits.discard_granularity = 512; - blk_queue_max_discard_sectors(disk->queue, UINT_MAX); + disk->queue->limits.discard_granularity = 0; + disk->queue->limits.discard_alignment = 0; + blk_queue_max_discard_sectors(disk->queue, 0); blk_queue_max_segment_size(disk->queue, UINT_MAX); blk_queue_max_segments(disk->queue, USHRT_MAX); blk_queue_max_hw_sectors(disk->queue, 65536); @@ -1677,6 +1775,10 @@ again: &config->runtime_flags); put_dev = true; } + if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { + set_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } } if (info->attrs[NBD_ATTR_SOCKETS]) { @@ -1721,6 +1823,17 @@ out: return ret; } +static void nbd_disconnect_and_put(struct nbd_device *nbd) +{ + mutex_lock(&nbd->config_lock); + nbd_disconnect(nbd); + nbd_clear_sock(nbd); + mutex_unlock(&nbd->config_lock); + if (test_and_clear_bit(NBD_HAS_CONFIG_REF, + &nbd->config->runtime_flags)) + nbd_config_put(nbd); +} + static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) { struct nbd_device *nbd; @@ -1753,12 +1866,7 @@ static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info) nbd_put(nbd); return 0; } - mutex_lock(&nbd->config_lock); - nbd_disconnect(nbd); - mutex_unlock(&nbd->config_lock); - if (test_and_clear_bit(NBD_HAS_CONFIG_REF, - &nbd->config->runtime_flags)) - nbd_config_put(nbd); + nbd_disconnect_and_put(nbd); nbd_config_put(nbd); nbd_put(nbd); return 0; @@ -1769,7 +1877,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) struct nbd_device *nbd = NULL; struct nbd_config *config; int index; - int ret = -EINVAL; + int ret = 0; bool put_dev = false; if (!netlink_capable(skb, CAP_SYS_ADMIN)) @@ -1809,6 +1917,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) !nbd->task_recv) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); + ret = -EINVAL; goto out; } @@ -1833,6 +1942,14 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) &config->runtime_flags)) refcount_inc(&nbd->refs); } + + if (flags & NBD_CFLAG_DISCONNECT_ON_CLOSE) { + set_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } else { + clear_bit(NBD_DISCONNECT_ON_CLOSE, + &config->runtime_flags); + } } if (info->attrs[NBD_ATTR_SOCKETS]) { @@ -2093,7 +2210,8 @@ static int __init nbd_init(void) if (nbds_max > 1UL << (MINORBITS - part_shift)) return -EINVAL; recv_workqueue = alloc_workqueue("knbd-recv", - WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + WQ_MEM_RECLAIM | WQ_HIGHPRI | + WQ_UNBOUND, 0); if (!recv_workqueue) return -ENOMEM; diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index a76553293a31..042c778e5a4e 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -157,23 +157,23 @@ enum { }; static int g_no_sched; -module_param_named(no_sched, g_no_sched, int, S_IRUGO); +module_param_named(no_sched, g_no_sched, int, 0444); MODULE_PARM_DESC(no_sched, "No io scheduler"); static int g_submit_queues = 1; -module_param_named(submit_queues, g_submit_queues, int, S_IRUGO); +module_param_named(submit_queues, g_submit_queues, int, 0444); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); static int g_home_node = NUMA_NO_NODE; -module_param_named(home_node, g_home_node, int, S_IRUGO); +module_param_named(home_node, g_home_node, int, 0444); MODULE_PARM_DESC(home_node, "Home node for the device"); #ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION static char g_timeout_str[80]; -module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), S_IRUGO); +module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444); static char g_requeue_str[80]; -module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), S_IRUGO); +module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444); #endif static int g_queue_mode = NULL_Q_MQ; @@ -203,27 +203,27 @@ static const struct kernel_param_ops null_queue_mode_param_ops = { .get = param_get_int, }; -device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, S_IRUGO); +device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444); MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)"); static int g_gb = 250; -module_param_named(gb, g_gb, int, S_IRUGO); +module_param_named(gb, g_gb, int, 0444); MODULE_PARM_DESC(gb, "Size in GB"); static int g_bs = 512; -module_param_named(bs, g_bs, int, S_IRUGO); +module_param_named(bs, g_bs, int, 0444); MODULE_PARM_DESC(bs, "Block size (in bytes)"); static int nr_devices = 1; -module_param(nr_devices, int, S_IRUGO); +module_param(nr_devices, int, 0444); MODULE_PARM_DESC(nr_devices, "Number of devices to register"); static bool g_blocking; -module_param_named(blocking, g_blocking, bool, S_IRUGO); +module_param_named(blocking, g_blocking, bool, 0444); MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device"); static bool shared_tags; -module_param(shared_tags, bool, S_IRUGO); +module_param(shared_tags, bool, 0444); MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq"); static int g_irqmode = NULL_IRQ_SOFTIRQ; @@ -239,19 +239,19 @@ static const struct kernel_param_ops null_irqmode_param_ops = { .get = param_get_int, }; -device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, S_IRUGO); +device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444); MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer"); static unsigned long g_completion_nsec = 10000; -module_param_named(completion_nsec, g_completion_nsec, ulong, S_IRUGO); +module_param_named(completion_nsec, g_completion_nsec, ulong, 0444); MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns"); static int g_hw_queue_depth = 64; -module_param_named(hw_queue_depth, g_hw_queue_depth, int, S_IRUGO); +module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64"); static bool g_use_per_node_hctx; -module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, S_IRUGO); +module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444); MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); static struct nullb_device *null_alloc_dev(void); @@ -1365,7 +1365,8 @@ static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio) static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq) { pr_info("null: rq %p timed out\n", rq); - return BLK_EH_HANDLED; + __blk_complete_request(rq); + return BLK_EH_DONE; } static int null_rq_prep_fn(struct request_queue *q, struct request *req) @@ -1427,7 +1428,8 @@ static void null_request_fn(struct request_queue *q) static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) { pr_info("null: rq %p timed out\n", rq); - return BLK_EH_HANDLED; + blk_mq_complete_request(rq); + return BLK_EH_DONE; } static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, @@ -1573,12 +1575,12 @@ static int setup_commands(struct nullb_queue *nq) struct nullb_cmd *cmd; int i, tag_size; - nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL); + nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL); if (!nq->cmds) return -ENOMEM; tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG; - nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL); + nq->tag_map = kcalloc(tag_size, sizeof(unsigned long), GFP_KERNEL); if (!nq->tag_map) { kfree(nq->cmds); return -ENOMEM; @@ -1596,8 +1598,9 @@ static int setup_commands(struct nullb_queue *nq) static int setup_queues(struct nullb *nullb) { - nullb->queues = kzalloc(nullb->dev->submit_queues * - sizeof(struct nullb_queue), GFP_KERNEL); + nullb->queues = kcalloc(nullb->dev->submit_queues, + sizeof(struct nullb_queue), + GFP_KERNEL); if (!nullb->queues) return -ENOMEM; diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 27a44b97393a..8961b190e256 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -740,7 +740,7 @@ static int pd_special_command(struct pd_unit *disk, { struct request *rq; - rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM); + rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index c61d20c9f3f8..b3f83cd96f33 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -97,8 +97,8 @@ static int pktdev_major; static int write_congestion_on = PKT_WRITE_CONGESTION_ON; static int write_congestion_off = PKT_WRITE_CONGESTION_OFF; static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */ -static mempool_t *psd_pool; -static struct bio_set *pkt_bio_set; +static mempool_t psd_pool; +static struct bio_set pkt_bio_set; static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */ static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ @@ -478,8 +478,8 @@ static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) if (!pd->dfs_d_root) return; - pd->dfs_f_info = debugfs_create_file("info", S_IRUGO, - pd->dfs_d_root, pd, &debug_fops); + pd->dfs_f_info = debugfs_create_file("info", 0444, + pd->dfs_d_root, pd, &debug_fops); } static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd) @@ -631,7 +631,7 @@ static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node) static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node) { rb_erase(&node->rb_node, &pd->bio_queue); - mempool_free(node, pd->rb_pool); + mempool_free(node, &pd->rb_pool); pd->bio_queue_size--; BUG_ON(pd->bio_queue_size < 0); } @@ -704,13 +704,13 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command * int ret = 0; rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? - REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, __GFP_RECLAIM); + REQ_OP_SCSI_OUT : REQ_OP_SCSI_IN, 0); if (IS_ERR(rq)) return PTR_ERR(rq); if (cgc->buflen) { ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, - __GFP_RECLAIM); + GFP_NOIO); if (ret) goto out; } @@ -1285,7 +1285,7 @@ static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) * Fill-in bvec with data from orig_bios. */ spin_lock(&pkt->lock); - bio_copy_data(pkt->w_bio, pkt->orig_bios.head); + bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); spin_unlock(&pkt->lock); @@ -2303,14 +2303,14 @@ static void pkt_end_io_read_cloned(struct bio *bio) psd->bio->bi_status = bio->bi_status; bio_put(bio); bio_endio(psd->bio); - mempool_free(psd, psd_pool); + mempool_free(psd, &psd_pool); pkt_bio_finished(pd); } static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) { - struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, pkt_bio_set); - struct packet_stacked_data *psd = mempool_alloc(psd_pool, GFP_NOIO); + struct bio *cloned_bio = bio_clone_fast(bio, GFP_NOIO, &pkt_bio_set); + struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO); psd->pd = pd; psd->bio = bio; @@ -2381,7 +2381,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio) /* * No matching packet found. Store the bio in the work queue. */ - node = mempool_alloc(pd->rb_pool, GFP_NOIO); + node = mempool_alloc(&pd->rb_pool, GFP_NOIO); node->bio = bio; spin_lock(&pd->lock); BUG_ON(pd->bio_queue_size < 0); @@ -2451,7 +2451,7 @@ static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio) split = bio_split(bio, last_zone - bio->bi_iter.bi_sector, - GFP_NOIO, pkt_bio_set); + GFP_NOIO, &pkt_bio_set); bio_chain(split, bio); } else { split = bio; @@ -2538,18 +2538,6 @@ static int pkt_seq_show(struct seq_file *m, void *p) return 0; } -static int pkt_seq_open(struct inode *inode, struct file *file) -{ - return single_open(file, pkt_seq_show, PDE_DATA(inode)); -} - -static const struct file_operations pkt_proc_fops = { - .open = pkt_seq_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release -}; - static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) { int i; @@ -2604,7 +2592,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) goto out_mem; } - proc_create_data(pd->name, 0, pkt_proc, &pkt_proc_fops, pd); + proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); pkt_dbg(1, pd, "writer mapped to %s\n", bdevname(bdev, b)); return 0; @@ -2707,9 +2695,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) if (!pd) goto out_mutex; - pd->rb_pool = mempool_create_kmalloc_pool(PKT_RB_POOL_SIZE, - sizeof(struct pkt_rb_node)); - if (!pd->rb_pool) + ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE, + sizeof(struct pkt_rb_node)); + if (ret) goto out_mem; INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); @@ -2766,7 +2754,7 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) out_mem2: put_disk(disk); out_mem: - mempool_destroy(pd->rb_pool); + mempool_exit(&pd->rb_pool); kfree(pd); out_mutex: mutex_unlock(&ctl_mutex); @@ -2817,7 +2805,7 @@ static int pkt_remove_dev(dev_t pkt_dev) blk_cleanup_queue(pd->disk->queue); put_disk(pd->disk); - mempool_destroy(pd->rb_pool); + mempool_exit(&pd->rb_pool); kfree(pd); /* This is safe: open() is still holding a reference. */ @@ -2914,14 +2902,14 @@ static int __init pkt_init(void) mutex_init(&ctl_mutex); - psd_pool = mempool_create_kmalloc_pool(PSD_POOL_SIZE, - sizeof(struct packet_stacked_data)); - if (!psd_pool) - return -ENOMEM; - pkt_bio_set = bioset_create(BIO_POOL_SIZE, 0, 0); - if (!pkt_bio_set) { - mempool_destroy(psd_pool); - return -ENOMEM; + ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE, + sizeof(struct packet_stacked_data)); + if (ret) + return ret; + ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0); + if (ret) { + mempool_exit(&psd_pool); + return ret; } ret = register_blkdev(pktdev_major, DRIVER_NAME); @@ -2954,8 +2942,8 @@ out_misc: out: unregister_blkdev(pktdev_major, DRIVER_NAME); out2: - mempool_destroy(psd_pool); - bioset_free(pkt_bio_set); + mempool_exit(&psd_pool); + bioset_exit(&pkt_bio_set); return ret; } @@ -2968,8 +2956,8 @@ static void __exit pkt_exit(void) pkt_sysfs_cleanup(); unregister_blkdev(pktdev_major, DRIVER_NAME); - mempool_destroy(psd_pool); - bioset_free(pkt_bio_set); + mempool_exit(&psd_pool); + bioset_exit(&pkt_bio_set); } MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives"); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 075662f2cf46..afe1508d82c6 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -465,8 +465,6 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) priv->queue = queue; queue->queuedata = dev; - blk_queue_bounce_limit(queue, BLK_BOUNCE_HIGH); - blk_queue_max_hw_sectors(queue, dev->bounce_size >> 9); blk_queue_segment_boundary(queue, -1UL); blk_queue_dma_alignment(queue, dev->blk_size-1); diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c index 6a55959cbf78..1e3d5de9d838 100644 --- a/drivers/block/ps3vram.c +++ b/drivers/block/ps3vram.c @@ -407,8 +407,9 @@ static int ps3vram_cache_init(struct ps3_system_bus_device *dev) priv->cache.page_count = CACHE_PAGE_COUNT; priv->cache.page_size = CACHE_PAGE_SIZE; - priv->cache.tags = kzalloc(sizeof(struct ps3vram_tag) * - CACHE_PAGE_COUNT, GFP_KERNEL); + priv->cache.tags = kcalloc(CACHE_PAGE_COUNT, + sizeof(struct ps3vram_tag), + GFP_KERNEL); if (!priv->cache.tags) return -ENOMEM; @@ -521,26 +522,13 @@ static int ps3vram_proc_show(struct seq_file *m, void *v) return 0; } -static int ps3vram_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, ps3vram_proc_show, PDE_DATA(inode)); -} - -static const struct file_operations ps3vram_proc_fops = { - .owner = THIS_MODULE, - .open = ps3vram_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - static void ps3vram_proc_init(struct ps3_system_bus_device *dev) { struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev); struct proc_dir_entry *pde; - pde = proc_create_data(DEVICE_NAME, 0444, NULL, &ps3vram_proc_fops, - priv); + pde = proc_create_single_data(DEVICE_NAME, 0444, NULL, + ps3vram_proc_show, priv); if (!pde) dev_warn(&dev->core, "failed to create /proc entry\n"); } diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 07dc5419bd63..fa0729c1e776 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -424,7 +424,7 @@ static struct workqueue_struct *rbd_wq; * single-major requires >= 0.75 version of userspace rbd utility. */ static bool single_major = true; -module_param(single_major, bool, S_IRUGO); +module_param(single_major, bool, 0444); MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (default: true)"); static ssize_t rbd_add(struct bus_type *bus, const char *buf, @@ -468,11 +468,11 @@ static ssize_t rbd_supported_features_show(struct bus_type *bus, char *buf) return sprintf(buf, "0x%llx\n", RBD_FEATURES_SUPPORTED); } -static BUS_ATTR(add, S_IWUSR, NULL, rbd_add); -static BUS_ATTR(remove, S_IWUSR, NULL, rbd_remove); -static BUS_ATTR(add_single_major, S_IWUSR, NULL, rbd_add_single_major); -static BUS_ATTR(remove_single_major, S_IWUSR, NULL, rbd_remove_single_major); -static BUS_ATTR(supported_features, S_IRUGO, rbd_supported_features_show, NULL); +static BUS_ATTR(add, 0200, NULL, rbd_add); +static BUS_ATTR(remove, 0200, NULL, rbd_remove); +static BUS_ATTR(add_single_major, 0200, NULL, rbd_add_single_major); +static BUS_ATTR(remove_single_major, 0200, NULL, rbd_remove_single_major); +static BUS_ATTR(supported_features, 0444, rbd_supported_features_show, NULL); static struct attribute *rbd_bus_attrs[] = { &bus_attr_add.attr, @@ -732,6 +732,7 @@ static struct rbd_client *rbd_client_find(struct ceph_options *ceph_opts) */ enum { Opt_queue_depth, + Opt_lock_timeout, Opt_last_int, /* int args above */ Opt_last_string, @@ -740,11 +741,13 @@ enum { Opt_read_write, Opt_lock_on_read, Opt_exclusive, + Opt_notrim, Opt_err }; static match_table_t rbd_opts_tokens = { {Opt_queue_depth, "queue_depth=%d"}, + {Opt_lock_timeout, "lock_timeout=%d"}, /* int args above */ /* string args above */ {Opt_read_only, "read_only"}, @@ -753,20 +756,25 @@ static match_table_t rbd_opts_tokens = { {Opt_read_write, "rw"}, /* Alternate spelling */ {Opt_lock_on_read, "lock_on_read"}, {Opt_exclusive, "exclusive"}, + {Opt_notrim, "notrim"}, {Opt_err, NULL} }; struct rbd_options { int queue_depth; + unsigned long lock_timeout; bool read_only; bool lock_on_read; bool exclusive; + bool trim; }; #define RBD_QUEUE_DEPTH_DEFAULT BLKDEV_MAX_RQ +#define RBD_LOCK_TIMEOUT_DEFAULT 0 /* no timeout */ #define RBD_READ_ONLY_DEFAULT false #define RBD_LOCK_ON_READ_DEFAULT false #define RBD_EXCLUSIVE_DEFAULT false +#define RBD_TRIM_DEFAULT true static int parse_rbd_opts_token(char *c, void *private) { @@ -796,6 +804,14 @@ static int parse_rbd_opts_token(char *c, void *private) } rbd_opts->queue_depth = intval; break; + case Opt_lock_timeout: + /* 0 is "wait forever" (i.e. infinite timeout) */ + if (intval < 0 || intval > INT_MAX / 1000) { + pr_err("lock_timeout out of range\n"); + return -EINVAL; + } + rbd_opts->lock_timeout = msecs_to_jiffies(intval * 1000); + break; case Opt_read_only: rbd_opts->read_only = true; break; @@ -808,6 +824,9 @@ static int parse_rbd_opts_token(char *c, void *private) case Opt_exclusive: rbd_opts->exclusive = true; break; + case Opt_notrim: + rbd_opts->trim = false; + break; default: /* libceph prints "bad option" msg */ return -EINVAL; @@ -1392,7 +1411,7 @@ static bool rbd_img_is_write(struct rbd_img_request *img_req) case OBJ_OP_DISCARD: return true; default: - rbd_assert(0); + BUG(); } } @@ -2320,6 +2339,7 @@ static bool is_zero_bvecs(struct bio_vec *bvecs, u32 bytes) static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes) { unsigned int num_osd_ops = obj_req->osd_req->r_num_ops; + int ret; dout("%s obj_req %p bytes %u\n", __func__, obj_req, bytes); rbd_assert(obj_req->osd_req->r_ops[0].op == CEPH_OSD_OP_STAT); @@ -2334,6 +2354,11 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes) if (!obj_req->osd_req) return -ENOMEM; + ret = osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd", + "copyup"); + if (ret) + return ret; + /* * Only send non-zero copyup data to save some I/O and network * bandwidth -- zero copyup data is equivalent to the object not @@ -2343,11 +2368,10 @@ static int rbd_obj_issue_copyup(struct rbd_obj_request *obj_req, u32 bytes) dout("%s obj_req %p detected zeroes\n", __func__, obj_req); bytes = 0; } - - osd_req_op_cls_init(obj_req->osd_req, 0, CEPH_OSD_OP_CALL, "rbd", - "copyup"); osd_req_op_cls_request_data_bvecs(obj_req->osd_req, 0, - obj_req->copyup_bvecs, bytes); + obj_req->copyup_bvecs, + obj_req->copyup_bvec_count, + bytes); switch (obj_req->img_request->op_type) { case OBJ_OP_WRITE: @@ -2466,7 +2490,7 @@ again: } return false; default: - rbd_assert(0); + BUG(); } } @@ -2494,7 +2518,7 @@ static bool __rbd_obj_handle_request(struct rbd_obj_request *obj_req) } return false; default: - rbd_assert(0); + BUG(); } } @@ -3376,7 +3400,6 @@ static void cancel_tasks_sync(struct rbd_device *rbd_dev) { dout("%s rbd_dev %p\n", __func__, rbd_dev); - cancel_delayed_work_sync(&rbd_dev->watch_dwork); cancel_work_sync(&rbd_dev->acquired_lock_work); cancel_work_sync(&rbd_dev->released_lock_work); cancel_delayed_work_sync(&rbd_dev->lock_dwork); @@ -3394,6 +3417,7 @@ static void rbd_unregister_watch(struct rbd_device *rbd_dev) rbd_dev->watch_state = RBD_WATCH_STATE_UNREGISTERED; mutex_unlock(&rbd_dev->watch_mutex); + cancel_delayed_work_sync(&rbd_dev->watch_dwork); ceph_osdc_flush_notifies(&rbd_dev->rbd_client->client->osdc); } @@ -3533,9 +3557,22 @@ static int rbd_obj_method_sync(struct rbd_device *rbd_dev, /* * lock_rwsem must be held for read */ -static void rbd_wait_state_locked(struct rbd_device *rbd_dev) +static int rbd_wait_state_locked(struct rbd_device *rbd_dev, bool may_acquire) { DEFINE_WAIT(wait); + unsigned long timeout; + int ret = 0; + + if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) + return -EBLACKLISTED; + + if (rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED) + return 0; + + if (!may_acquire) { + rbd_warn(rbd_dev, "exclusive lock required"); + return -EROFS; + } do { /* @@ -3547,12 +3584,22 @@ static void rbd_wait_state_locked(struct rbd_device *rbd_dev) prepare_to_wait_exclusive(&rbd_dev->lock_waitq, &wait, TASK_UNINTERRUPTIBLE); up_read(&rbd_dev->lock_rwsem); - schedule(); + timeout = schedule_timeout(ceph_timeout_jiffies( + rbd_dev->opts->lock_timeout)); down_read(&rbd_dev->lock_rwsem); - } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED && - !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)); + if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) { + ret = -EBLACKLISTED; + break; + } + if (!timeout) { + rbd_warn(rbd_dev, "timed out waiting for lock"); + ret = -ETIMEDOUT; + break; + } + } while (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED); finish_wait(&rbd_dev->lock_waitq, &wait); + return ret; } static void rbd_queue_workfn(struct work_struct *work) @@ -3638,19 +3685,10 @@ static void rbd_queue_workfn(struct work_struct *work) (op_type != OBJ_OP_READ || rbd_dev->opts->lock_on_read); if (must_be_locked) { down_read(&rbd_dev->lock_rwsem); - if (rbd_dev->lock_state != RBD_LOCK_STATE_LOCKED && - !test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) { - if (rbd_dev->opts->exclusive) { - rbd_warn(rbd_dev, "exclusive lock required"); - result = -EROFS; - goto err_unlock; - } - rbd_wait_state_locked(rbd_dev); - } - if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) { - result = -EBLACKLISTED; + result = rbd_wait_state_locked(rbd_dev, + !rbd_dev->opts->exclusive); + if (result) goto err_unlock; - } } img_request = rbd_img_request_create(rbd_dev, op_type, snapc); @@ -3902,7 +3940,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) { struct gendisk *disk; struct request_queue *q; - u64 segment_size; + unsigned int objset_bytes = + rbd_dev->layout.object_size * rbd_dev->layout.stripe_count; int err; /* create gendisk info */ @@ -3942,20 +3981,19 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) blk_queue_flag_set(QUEUE_FLAG_NONROT, q); /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */ - /* set io sizes to object size */ - segment_size = rbd_obj_bytes(&rbd_dev->header); - blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE); + blk_queue_max_hw_sectors(q, objset_bytes >> SECTOR_SHIFT); q->limits.max_sectors = queue_max_hw_sectors(q); blk_queue_max_segments(q, USHRT_MAX); blk_queue_max_segment_size(q, UINT_MAX); - blk_queue_io_min(q, segment_size); - blk_queue_io_opt(q, segment_size); + blk_queue_io_min(q, objset_bytes); + blk_queue_io_opt(q, objset_bytes); - /* enable the discard support */ - blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); - q->limits.discard_granularity = segment_size; - blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE); - blk_queue_max_write_zeroes_sectors(q, segment_size / SECTOR_SIZE); + if (rbd_dev->opts->trim) { + blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); + q->limits.discard_granularity = objset_bytes; + blk_queue_max_discard_sectors(q, objset_bytes >> SECTOR_SHIFT); + blk_queue_max_write_zeroes_sectors(q, objset_bytes >> SECTOR_SHIFT); + } if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC)) q->backing_dev_info->capabilities |= BDI_CAP_STABLE_WRITES; @@ -4169,22 +4207,22 @@ static ssize_t rbd_image_refresh(struct device *dev, return size; } -static DEVICE_ATTR(size, S_IRUGO, rbd_size_show, NULL); -static DEVICE_ATTR(features, S_IRUGO, rbd_features_show, NULL); -static DEVICE_ATTR(major, S_IRUGO, rbd_major_show, NULL); -static DEVICE_ATTR(minor, S_IRUGO, rbd_minor_show, NULL); -static DEVICE_ATTR(client_addr, S_IRUGO, rbd_client_addr_show, NULL); -static DEVICE_ATTR(client_id, S_IRUGO, rbd_client_id_show, NULL); -static DEVICE_ATTR(cluster_fsid, S_IRUGO, rbd_cluster_fsid_show, NULL); -static DEVICE_ATTR(config_info, S_IRUSR, rbd_config_info_show, NULL); -static DEVICE_ATTR(pool, S_IRUGO, rbd_pool_show, NULL); -static DEVICE_ATTR(pool_id, S_IRUGO, rbd_pool_id_show, NULL); -static DEVICE_ATTR(name, S_IRUGO, rbd_name_show, NULL); -static DEVICE_ATTR(image_id, S_IRUGO, rbd_image_id_show, NULL); -static DEVICE_ATTR(refresh, S_IWUSR, NULL, rbd_image_refresh); -static DEVICE_ATTR(current_snap, S_IRUGO, rbd_snap_show, NULL); -static DEVICE_ATTR(snap_id, S_IRUGO, rbd_snap_id_show, NULL); -static DEVICE_ATTR(parent, S_IRUGO, rbd_parent_show, NULL); +static DEVICE_ATTR(size, 0444, rbd_size_show, NULL); +static DEVICE_ATTR(features, 0444, rbd_features_show, NULL); +static DEVICE_ATTR(major, 0444, rbd_major_show, NULL); +static DEVICE_ATTR(minor, 0444, rbd_minor_show, NULL); +static DEVICE_ATTR(client_addr, 0444, rbd_client_addr_show, NULL); +static DEVICE_ATTR(client_id, 0444, rbd_client_id_show, NULL); +static DEVICE_ATTR(cluster_fsid, 0444, rbd_cluster_fsid_show, NULL); +static DEVICE_ATTR(config_info, 0400, rbd_config_info_show, NULL); +static DEVICE_ATTR(pool, 0444, rbd_pool_show, NULL); +static DEVICE_ATTR(pool_id, 0444, rbd_pool_id_show, NULL); +static DEVICE_ATTR(name, 0444, rbd_name_show, NULL); +static DEVICE_ATTR(image_id, 0444, rbd_image_id_show, NULL); +static DEVICE_ATTR(refresh, 0200, NULL, rbd_image_refresh); +static DEVICE_ATTR(current_snap, 0444, rbd_snap_show, NULL); +static DEVICE_ATTR(snap_id, 0444, rbd_snap_id_show, NULL); +static DEVICE_ATTR(parent, 0444, rbd_parent_show, NULL); static struct attribute *rbd_attrs[] = { &dev_attr_size.attr, @@ -5179,8 +5217,10 @@ static int rbd_add_parse_args(const char *buf, rbd_opts->read_only = RBD_READ_ONLY_DEFAULT; rbd_opts->queue_depth = RBD_QUEUE_DEPTH_DEFAULT; + rbd_opts->lock_timeout = RBD_LOCK_TIMEOUT_DEFAULT; rbd_opts->lock_on_read = RBD_LOCK_ON_READ_DEFAULT; rbd_opts->exclusive = RBD_EXCLUSIVE_DEFAULT; + rbd_opts->trim = RBD_TRIM_DEFAULT; copts = ceph_parse_options(options, mon_addrs, mon_addrs + mon_addrs_size - 1, @@ -5216,6 +5256,8 @@ static void rbd_dev_image_unlock(struct rbd_device *rbd_dev) static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) { + int ret; + if (!(rbd_dev->header.features & RBD_FEATURE_EXCLUSIVE_LOCK)) { rbd_warn(rbd_dev, "exclusive-lock feature is not enabled"); return -EINVAL; @@ -5223,9 +5265,9 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) /* FIXME: "rbd map --exclusive" should be in interruptible */ down_read(&rbd_dev->lock_rwsem); - rbd_wait_state_locked(rbd_dev); + ret = rbd_wait_state_locked(rbd_dev, true); up_read(&rbd_dev->lock_rwsem); - if (test_bit(RBD_DEV_FLAG_BLACKLISTED, &rbd_dev->flags)) { + if (ret) { rbd_warn(rbd_dev, "failed to acquire exclusive lock"); return -EROFS; } diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 34997df132e2..b7d71914a32a 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -247,19 +247,19 @@ static void rsxx_debugfs_dev_new(struct rsxx_cardinfo *card) if (IS_ERR_OR_NULL(card->debugfs_dir)) goto failed_debugfs_dir; - debugfs_stats = debugfs_create_file("stats", S_IRUGO, + debugfs_stats = debugfs_create_file("stats", 0444, card->debugfs_dir, card, &debugfs_stats_fops); if (IS_ERR_OR_NULL(debugfs_stats)) goto failed_debugfs_stats; - debugfs_pci_regs = debugfs_create_file("pci_regs", S_IRUGO, + debugfs_pci_regs = debugfs_create_file("pci_regs", 0444, card->debugfs_dir, card, &debugfs_pci_regs_fops); if (IS_ERR_OR_NULL(debugfs_pci_regs)) goto failed_debugfs_pci_regs; - debugfs_cram = debugfs_create_file("cram", S_IRUGO | S_IWUSR, + debugfs_cram = debugfs_create_file("cram", 0644, card->debugfs_dir, card, &debugfs_cram_fops); if (IS_ERR_OR_NULL(debugfs_cram)) @@ -873,7 +873,8 @@ static int rsxx_pci_probe(struct pci_dev *dev, dev_info(CARD_TO_DEV(card), "Failed reading the number of DMA targets\n"); - card->ctrl = kzalloc(card->n_targets * sizeof(*card->ctrl), GFP_KERNEL); + card->ctrl = kcalloc(card->n_targets, sizeof(*card->ctrl), + GFP_KERNEL); if (!card->ctrl) { st = -ENOMEM; goto failed_dma_setup; diff --git a/drivers/block/rsxx/dma.c b/drivers/block/rsxx/dma.c index beaccf197a5a..8fbc1bf6db3d 100644 --- a/drivers/block/rsxx/dma.c +++ b/drivers/block/rsxx/dma.c @@ -1038,7 +1038,7 @@ int rsxx_eeh_save_issued_dmas(struct rsxx_cardinfo *card) struct rsxx_dma *dma; struct list_head *issued_dmas; - issued_dmas = kzalloc(sizeof(*issued_dmas) * card->n_targets, + issued_dmas = kcalloc(card->n_targets, sizeof(*issued_dmas), GFP_KERNEL); if (!issued_dmas) return -ENOMEM; diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 64e066eba72e..0e31884a9519 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -110,7 +110,7 @@ struct iwm { /* Select values for swim_select and swim_readbit */ #define READ_DATA_0 0x074 -#define TWOMEG_DRIVE 0x075 +#define ONEMEG_DRIVE 0x075 #define SINGLE_SIDED 0x076 #define DRIVE_PRESENT 0x077 #define DISK_IN 0x170 @@ -118,9 +118,9 @@ struct iwm { #define TRACK_ZERO 0x172 #define TACHO 0x173 #define READ_DATA_1 0x174 -#define MFM_MODE 0x175 +#define GCR_MODE 0x175 #define SEEK_COMPLETE 0x176 -#define ONEMEG_MEDIA 0x177 +#define TWOMEG_MEDIA 0x177 /* Bits in handshake register */ @@ -612,7 +612,6 @@ static void setup_medium(struct floppy_state *fs) struct floppy_struct *g; fs->disk_in = 1; fs->write_protected = swim_readbit(base, WRITE_PROT); - fs->type = swim_readbit(base, ONEMEG_MEDIA); if (swim_track00(base)) printk(KERN_ERR @@ -620,6 +619,9 @@ static void setup_medium(struct floppy_state *fs) swim_track00(base); + fs->type = swim_readbit(base, TWOMEG_MEDIA) ? + HD_MEDIA : DD_MEDIA; + fs->head_number = swim_readbit(base, SINGLE_SIDED) ? 1 : 2; get_floppy_geometry(fs, 0, &g); fs->total_secs = g->size; fs->secpercyl = g->head * g->sect; @@ -646,7 +648,7 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) swim_write(base, setup, S_IBM_DRIVE | S_FCLK_DIV2); udelay(10); - swim_drive(base, INTERNAL_DRIVE); + swim_drive(base, fs->location); swim_motor(base, ON); swim_action(base, SETMFM); if (fs->ejected) @@ -656,6 +658,8 @@ static int floppy_open(struct block_device *bdev, fmode_t mode) goto out; } + set_capacity(fs->disk, fs->total_secs); + if (mode & FMODE_NDELAY) return 0; @@ -727,14 +731,9 @@ static int floppy_ioctl(struct block_device *bdev, fmode_t mode, if (copy_to_user((void __user *) param, (void *) &floppy_type, sizeof(struct floppy_struct))) return -EFAULT; - break; - - default: - printk(KERN_DEBUG "SWIM floppy_ioctl: unknown cmd %d\n", - cmd); - return -ENOSYS; + return 0; } - return 0; + return -ENOTTY; } static int floppy_getgeo(struct block_device *bdev, struct hd_geometry *geo) @@ -795,7 +794,7 @@ static struct kobject *floppy_find(dev_t dev, int *part, void *data) struct swim_priv *swd = data; int drive = (*part & 3); - if (drive > swd->floppy_count) + if (drive >= swd->floppy_count) return NULL; *part = 0; @@ -813,10 +812,9 @@ static int swim_add_floppy(struct swim_priv *swd, enum drive_location location) swim_motor(base, OFF); - if (swim_readbit(base, SINGLE_SIDED)) - fs->head_number = 1; - else - fs->head_number = 2; + fs->type = HD_MEDIA; + fs->head_number = 2; + fs->ref_count = 0; fs->ejected = 1; @@ -834,10 +832,12 @@ static int swim_floppy_init(struct swim_priv *swd) /* scan floppy drives */ swim_drive(base, INTERNAL_DRIVE); - if (swim_readbit(base, DRIVE_PRESENT)) + if (swim_readbit(base, DRIVE_PRESENT) && + !swim_readbit(base, ONEMEG_DRIVE)) swim_add_floppy(swd, INTERNAL_DRIVE); swim_drive(base, EXTERNAL_DRIVE); - if (swim_readbit(base, DRIVE_PRESENT)) + if (swim_readbit(base, DRIVE_PRESENT) && + !swim_readbit(base, ONEMEG_DRIVE)) swim_add_floppy(swd, EXTERNAL_DRIVE); /* register floppy drives */ @@ -861,7 +861,6 @@ static int swim_floppy_init(struct swim_priv *swd) &swd->lock); if (!swd->unit[drive].disk->queue) { err = -ENOMEM; - put_disk(swd->unit[drive].disk); goto exit_put_disks; } blk_queue_bounce_limit(swd->unit[drive].disk->queue, @@ -911,7 +910,7 @@ static int swim_probe(struct platform_device *dev) goto out; } - swim_base = ioremap(res->start, resource_size(res)); + swim_base = (struct swim __iomem *)res->start; if (!swim_base) { ret = -ENOMEM; goto out_release_io; @@ -923,7 +922,7 @@ static int swim_probe(struct platform_device *dev) if (!get_swim_mode(swim_base)) { printk(KERN_INFO "SWIM device not found !\n"); ret = -ENODEV; - goto out_iounmap; + goto out_release_io; } /* set platform driver data */ @@ -931,7 +930,7 @@ static int swim_probe(struct platform_device *dev) swd = kzalloc(sizeof(struct swim_priv), GFP_KERNEL); if (!swd) { ret = -ENOMEM; - goto out_iounmap; + goto out_release_io; } platform_set_drvdata(dev, swd); @@ -945,8 +944,6 @@ static int swim_probe(struct platform_device *dev) out_kfree: kfree(swd); -out_iounmap: - iounmap(swim_base); out_release_io: release_mem_region(res->start, resource_size(res)); out: @@ -974,8 +971,6 @@ static int swim_remove(struct platform_device *dev) for (drive = 0; drive < swd->floppy_count; drive++) floppy_eject(&swd->unit[drive]); - iounmap(swd->base); - res = platform_get_resource(dev, IORESOURCE_MEM, 0); if (res) release_mem_region(res->start, resource_size(res)); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index af51015d056e..469541c1e51e 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -148,7 +148,7 @@ struct swim3 { #define MOTOR_ON 2 #define RELAX 3 /* also eject in progress */ #define READ_DATA_0 4 -#define TWOMEG_DRIVE 5 +#define ONEMEG_DRIVE 5 #define SINGLE_SIDED 6 /* drive or diskette is 4MB type? */ #define DRIVE_PRESENT 7 #define DISK_IN 8 @@ -156,9 +156,9 @@ struct swim3 { #define TRACK_ZERO 10 #define TACHO 11 #define READ_DATA_1 12 -#define MFM_MODE 13 +#define GCR_MODE 13 #define SEEK_COMPLETE 14 -#define ONEMEG_MEDIA 15 +#define TWOMEG_MEDIA 15 /* Definitions of values used in writing and formatting */ #define DATA_ESCAPE 0x99 diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 08586dc14e85..4d90e5eba2f5 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -567,7 +567,7 @@ static struct carm_request *carm_get_special(struct carm_host *host) if (!crq) return NULL; - rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, GFP_KERNEL); + rq = blk_get_request(host->oob_q, REQ_OP_DRV_OUT, 0); if (IS_ERR(rq)) { spin_lock_irqsave(&host->lock, flags); carm_put_request(host, crq); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 4a07593c2efd..23752dc99b00 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -298,7 +298,7 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str) struct request *req; int err; - req = blk_get_request(q, REQ_OP_DRV_IN, GFP_KERNEL); + req = blk_get_request(q, REQ_OP_DRV_IN, 0); if (IS_ERR(req)) return PTR_ERR(req); @@ -371,7 +371,7 @@ static ssize_t virtblk_serial_show(struct device *dev, return err; } -static DEVICE_ATTR(serial, S_IRUGO, virtblk_serial_show, NULL); +static DEVICE_ATTR(serial, 0444, virtblk_serial_show, NULL); /* The queue's logical block size must be set before calling this */ static void virtblk_update_capacity(struct virtio_blk *vblk, bool resize) @@ -576,10 +576,10 @@ virtblk_cache_type_show(struct device *dev, struct device_attribute *attr, } static const struct device_attribute dev_attr_cache_type_ro = - __ATTR(cache_type, S_IRUGO, + __ATTR(cache_type, 0444, virtblk_cache_type_show, NULL); static const struct device_attribute dev_attr_cache_type_rw = - __ATTR(cache_type, S_IRUGO|S_IWUSR, + __ATTR(cache_type, 0644, virtblk_cache_type_show, virtblk_cache_type_store); static int virtblk_init_request(struct blk_mq_tag_set *set, struct request *rq, diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c index 987d665e82de..b55b245e8052 100644 --- a/drivers/block/xen-blkback/blkback.c +++ b/drivers/block/xen-blkback/blkback.c @@ -98,7 +98,7 @@ MODULE_PARM_DESC(max_queues, * backend, 4KB page granularity is used. */ unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER; -module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO); +module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444); MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring"); /* * The LRU mechanism to clean the lists of persistent grants needs to diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 21c1be1eb226..a4bc74e72c39 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -139,7 +139,8 @@ static int xen_blkif_alloc_rings(struct xen_blkif *blkif) { unsigned int r; - blkif->rings = kzalloc(blkif->nr_rings * sizeof(struct xen_blkif_ring), GFP_KERNEL); + blkif->rings = kcalloc(blkif->nr_rings, sizeof(struct xen_blkif_ring), + GFP_KERNEL); if (!blkif->rings) return -ENOMEM; @@ -367,7 +368,7 @@ int __init xen_blkif_interface_init(void) out: \ return sprintf(buf, format, result); \ } \ - static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) + static DEVICE_ATTR(name, 0444, show_##name, NULL) VBD_SHOW_ALLRING(oo_req, "%llu\n"); VBD_SHOW_ALLRING(rd_req, "%llu\n"); @@ -403,7 +404,7 @@ static const struct attribute_group xen_vbdstat_group = { \ return sprintf(buf, format, ##args); \ } \ - static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) + static DEVICE_ATTR(name, 0444, show_##name, NULL) VBD_SHOW(physical_device, "%x:%x\n", be->major, be->minor); VBD_SHOW(mode, "%s\n", be->mode); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 2a8e7813bd1a..b5cedccb5d7d 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -129,13 +129,12 @@ static const struct block_device_operations xlvbd_block_fops; */ static unsigned int xen_blkif_max_segments = 32; -module_param_named(max_indirect_segments, xen_blkif_max_segments, uint, - S_IRUGO); +module_param_named(max_indirect_segments, xen_blkif_max_segments, uint, 0444); MODULE_PARM_DESC(max_indirect_segments, "Maximum amount of segments in indirect requests (default is 32)"); static unsigned int xen_blkif_max_queues = 4; -module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO); +module_param_named(max_queues, xen_blkif_max_queues, uint, 0444); MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per virtual disk"); /* @@ -143,7 +142,7 @@ MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings used per v * backend, 4KB page granularity is used. */ static unsigned int xen_blkif_max_ring_order; -module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO); +module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, 0444); MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring"); #define BLK_RING_SIZE(info) \ @@ -1907,7 +1906,9 @@ static int negotiate_mq(struct blkfront_info *info) if (!info->nr_rings) info->nr_rings = 1; - info->rinfo = kzalloc(sizeof(struct blkfront_ring_info) * info->nr_rings, GFP_KERNEL); + info->rinfo = kcalloc(info->nr_rings, + sizeof(struct blkfront_ring_info), + GFP_KERNEL); if (!info->rinfo) { xenbus_dev_fatal(info->xbdev, -ENOMEM, "allocating ring_info structure"); return -ENOMEM; @@ -2217,15 +2218,18 @@ static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo) } for (i = 0; i < BLK_RING_SIZE(info); i++) { - rinfo->shadow[i].grants_used = kzalloc( - sizeof(rinfo->shadow[i].grants_used[0]) * grants, - GFP_NOIO); - rinfo->shadow[i].sg = kzalloc(sizeof(rinfo->shadow[i].sg[0]) * psegs, GFP_NOIO); - if (info->max_indirect_segments) - rinfo->shadow[i].indirect_grants = kzalloc( - sizeof(rinfo->shadow[i].indirect_grants[0]) * - INDIRECT_GREFS(grants), + rinfo->shadow[i].grants_used = + kcalloc(grants, + sizeof(rinfo->shadow[i].grants_used[0]), GFP_NOIO); + rinfo->shadow[i].sg = kcalloc(psegs, + sizeof(rinfo->shadow[i].sg[0]), + GFP_NOIO); + if (info->max_indirect_segments) + rinfo->shadow[i].indirect_grants = + kcalloc(INDIRECT_GREFS(grants), + sizeof(rinfo->shadow[i].indirect_grants[0]), + GFP_NOIO); if ((rinfo->shadow[i].grants_used == NULL) || (rinfo->shadow[i].sg == NULL) || (info->max_indirect_segments && diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c index 8f9130ab5887..d0c5bc4e0703 100644 --- a/drivers/block/z2ram.c +++ b/drivers/block/z2ram.c @@ -197,8 +197,9 @@ static int z2_open(struct block_device *bdev, fmode_t mode) vaddr = (unsigned long)z_remap_nocache_nonser(paddr, size); #endif z2ram_map = - kmalloc((size/Z2RAM_CHUNKSIZE)*sizeof(z2ram_map[0]), - GFP_KERNEL); + kmalloc_array(size / Z2RAM_CHUNKSIZE, + sizeof(z2ram_map[0]), + GFP_KERNEL); if ( z2ram_map == NULL ) { printk( KERN_ERR DEVICE_NAME diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index ac3a31d433b2..635235759a0a 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,7 +13,7 @@ config ZRAM It has several use cases, for example: /tmp storage, use as swap disks and maybe many more. - See zram.txt for more information. + See Documentation/blockdev/zram.txt for more information. config ZRAM_WRITEBACK bool "Write back incompressible page to backing device" @@ -25,4 +25,14 @@ config ZRAM_WRITEBACK For this feature, admin should set up backing device via /sys/block/zramX/backing_dev. - See zram.txt for more infomration. + See Documentation/blockdev/zram.txt for more information. + +config ZRAM_MEMORY_TRACKING + bool "Track zRam block status" + depends on ZRAM && DEBUG_FS + help + With this feature, admin can track the state of allocated blocks + of zRAM. Admin could see the information via + /sys/kernel/debug/zram/zramX/block_state. + + See Documentation/blockdev/zram.txt for more information. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 0f3fadd71230..7436b2d27fa3 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -31,6 +31,7 @@ #include <linux/err.h> #include <linux/idr.h> #include <linux/sysfs.h> +#include <linux/debugfs.h> #include <linux/cpuhotplug.h> #include "zram_drv.h" @@ -52,11 +53,28 @@ static size_t huge_class_size; static void zram_free_page(struct zram *zram, size_t index); +static void zram_slot_lock(struct zram *zram, u32 index) +{ + bit_spin_lock(ZRAM_LOCK, &zram->table[index].value); +} + +static void zram_slot_unlock(struct zram *zram, u32 index) +{ + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value); +} + static inline bool init_done(struct zram *zram) { return zram->disksize; } +static inline bool zram_allocated(struct zram *zram, u32 index) +{ + + return (zram->table[index].value >> (ZRAM_FLAG_SHIFT + 1)) || + zram->table[index].handle; +} + static inline struct zram *dev_to_zram(struct device *dev) { return (struct zram *)dev_to_disk(dev)->private_data; @@ -73,7 +91,7 @@ static void zram_set_handle(struct zram *zram, u32 index, unsigned long handle) } /* flag operations require table entry bit_spin_lock() being held */ -static int zram_test_flag(struct zram *zram, u32 index, +static bool zram_test_flag(struct zram *zram, u32 index, enum zram_pageflags flag) { return zram->table[index].value & BIT(flag); @@ -600,6 +618,114 @@ static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, static void zram_wb_clear(struct zram *zram, u32 index) {} #endif +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + +static struct dentry *zram_debugfs_root; + +static void zram_debugfs_create(void) +{ + zram_debugfs_root = debugfs_create_dir("zram", NULL); +} + +static void zram_debugfs_destroy(void) +{ + debugfs_remove_recursive(zram_debugfs_root); +} + +static void zram_accessed(struct zram *zram, u32 index) +{ + zram->table[index].ac_time = ktime_get_boottime(); +} + +static void zram_reset_access(struct zram *zram, u32 index) +{ + zram->table[index].ac_time = 0; +} + +static ssize_t read_block_state(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + char *kbuf; + ssize_t index, written = 0; + struct zram *zram = file->private_data; + unsigned long nr_pages = zram->disksize >> PAGE_SHIFT; + struct timespec64 ts; + + kbuf = kvmalloc(count, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + down_read(&zram->init_lock); + if (!init_done(zram)) { + up_read(&zram->init_lock); + kvfree(kbuf); + return -EINVAL; + } + + for (index = *ppos; index < nr_pages; index++) { + int copied; + + zram_slot_lock(zram, index); + if (!zram_allocated(zram, index)) + goto next; + + ts = ktime_to_timespec64(zram->table[index].ac_time); + copied = snprintf(kbuf + written, count, + "%12zd %12lld.%06lu %c%c%c\n", + index, (s64)ts.tv_sec, + ts.tv_nsec / NSEC_PER_USEC, + zram_test_flag(zram, index, ZRAM_SAME) ? 's' : '.', + zram_test_flag(zram, index, ZRAM_WB) ? 'w' : '.', + zram_test_flag(zram, index, ZRAM_HUGE) ? 'h' : '.'); + + if (count < copied) { + zram_slot_unlock(zram, index); + break; + } + written += copied; + count -= copied; +next: + zram_slot_unlock(zram, index); + *ppos += 1; + } + + up_read(&zram->init_lock); + if (copy_to_user(buf, kbuf, written)) + written = -EFAULT; + kvfree(kbuf); + + return written; +} + +static const struct file_operations proc_zram_block_state_op = { + .open = simple_open, + .read = read_block_state, + .llseek = default_llseek, +}; + +static void zram_debugfs_register(struct zram *zram) +{ + if (!zram_debugfs_root) + return; + + zram->debugfs_dir = debugfs_create_dir(zram->disk->disk_name, + zram_debugfs_root); + debugfs_create_file("block_state", 0400, zram->debugfs_dir, + zram, &proc_zram_block_state_op); +} + +static void zram_debugfs_unregister(struct zram *zram) +{ + debugfs_remove_recursive(zram->debugfs_dir); +} +#else +static void zram_debugfs_create(void) {}; +static void zram_debugfs_destroy(void) {}; +static void zram_accessed(struct zram *zram, u32 index) {}; +static void zram_reset_access(struct zram *zram, u32 index) {}; +static void zram_debugfs_register(struct zram *zram) {}; +static void zram_debugfs_unregister(struct zram *zram) {}; +#endif /* * We switched to per-cpu streams and this attr is not needed anymore. @@ -719,14 +845,15 @@ static ssize_t mm_stat_show(struct device *dev, max_used = atomic_long_read(&zram->stats.max_used_pages); ret = scnprintf(buf, PAGE_SIZE, - "%8llu %8llu %8llu %8lu %8ld %8llu %8lu\n", + "%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n", orig_size << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.compr_data_size), mem_used << PAGE_SHIFT, zram->limit_pages << PAGE_SHIFT, max_used << PAGE_SHIFT, (u64)atomic64_read(&zram->stats.same_pages), - pool_stats.pages_compacted); + pool_stats.pages_compacted, + (u64)atomic64_read(&zram->stats.huge_pages)); up_read(&zram->init_lock); return ret; @@ -753,16 +880,6 @@ static DEVICE_ATTR_RO(io_stat); static DEVICE_ATTR_RO(mm_stat); static DEVICE_ATTR_RO(debug_stat); -static void zram_slot_lock(struct zram *zram, u32 index) -{ - bit_spin_lock(ZRAM_ACCESS, &zram->table[index].value); -} - -static void zram_slot_unlock(struct zram *zram, u32 index) -{ - bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value); -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -781,7 +898,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) size_t num_pages; num_pages = disksize >> PAGE_SHIFT; - zram->table = vzalloc(num_pages * sizeof(*zram->table)); + zram->table = vzalloc(array_size(num_pages, sizeof(*zram->table))); if (!zram->table) return false; @@ -805,6 +922,13 @@ static void zram_free_page(struct zram *zram, size_t index) { unsigned long handle; + zram_reset_access(zram, index); + + if (zram_test_flag(zram, index, ZRAM_HUGE)) { + zram_clear_flag(zram, index, ZRAM_HUGE); + atomic64_dec(&zram->stats.huge_pages); + } + if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { zram_wb_clear(zram, index); atomic64_dec(&zram->stats.pages_stored); @@ -973,6 +1097,7 @@ compress_again: } if (unlikely(comp_len >= huge_class_size)) { + comp_len = PAGE_SIZE; if (zram_wb_enabled(zram) && allow_wb) { zcomp_stream_put(zram->comp); ret = write_to_bdev(zram, bvec, index, bio, &element); @@ -984,7 +1109,6 @@ compress_again: allow_wb = false; goto compress_again; } - comp_len = PAGE_SIZE; } /* @@ -1046,6 +1170,11 @@ out: zram_slot_lock(zram, index); zram_free_page(zram, index); + if (comp_len == PAGE_SIZE) { + zram_set_flag(zram, index, ZRAM_HUGE); + atomic64_inc(&zram->stats.huge_pages); + } + if (flags) { zram_set_flag(zram, index, flags); zram_set_element(zram, index, element); @@ -1166,6 +1295,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index, generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time); + zram_slot_lock(zram, index); + zram_accessed(zram, index); + zram_slot_unlock(zram, index); + if (unlikely(ret < 0)) { if (!is_write) atomic64_inc(&zram->stats.failed_reads); @@ -1577,6 +1710,7 @@ static int zram_add(void) } strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor)); + zram_debugfs_register(zram); pr_info("Added device: %s\n", zram->disk->disk_name); return device_id; @@ -1610,6 +1744,7 @@ static int zram_remove(struct zram *zram) zram->claim = true; mutex_unlock(&bdev->bd_mutex); + zram_debugfs_unregister(zram); /* * Remove sysfs first, so no one will perform a disksize * store while we destroy the devices. This also helps during @@ -1712,6 +1847,7 @@ static void destroy_devices(void) { class_unregister(&zram_control_class); idr_for_each(&zram_index_idr, &zram_remove_cb, NULL); + zram_debugfs_destroy(); idr_destroy(&zram_index_idr); unregister_blkdev(zram_major, "zram"); cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE); @@ -1733,6 +1869,7 @@ static int __init zram_init(void) return ret; } + zram_debugfs_create(); zram_major = register_blkdev(0, "zram"); if (zram_major <= 0) { pr_err("Unable to get major number\n"); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 008861220723..72c8584b6dff 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -43,10 +43,11 @@ /* Flags for zram pages (table[page_no].value) */ enum zram_pageflags { - /* Page consists the same element */ - ZRAM_SAME = ZRAM_FLAG_SHIFT, - ZRAM_ACCESS, /* page is now accessed */ + /* zram slot is locked */ + ZRAM_LOCK = ZRAM_FLAG_SHIFT, + ZRAM_SAME, /* Page consists the same element */ ZRAM_WB, /* page is stored on backing_device */ + ZRAM_HUGE, /* Incompressible page */ __NR_ZRAM_PAGEFLAGS, }; @@ -60,6 +61,9 @@ struct zram_table_entry { unsigned long element; }; unsigned long value; +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + ktime_t ac_time; +#endif }; struct zram_stats { @@ -71,6 +75,7 @@ struct zram_stats { atomic64_t invalid_io; /* non-page-aligned I/O requests */ atomic64_t notify_free; /* no. of swap slot free notifications */ atomic64_t same_pages; /* no. of same element filled pages */ + atomic64_t huge_pages; /* no. of huge pages */ atomic64_t pages_stored; /* no. of pages currently stored */ atomic_long_t max_used_pages; /* no. of maximum pages stored */ atomic64_t writestall; /* no. of write slow paths */ @@ -107,5 +112,8 @@ struct zram { unsigned long nr_pages; spinlock_t bitmap_lock; #endif +#ifdef CONFIG_ZRAM_MEMORY_TRACKING + struct dentry *debugfs_dir; +#endif }; #endif |
