From 09cbfeaf1a5a67bfb3201e0c83c810cecb2efa5a Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 1 Apr 2016 15:29:47 +0300 Subject: mm, fs: get rid of PAGE_CACHE_* and page_cache_{get,release} macros PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time ago with promise that one day it will be possible to implement page cache with bigger chunks than PAGE_SIZE. This promise never materialized. And unlikely will. We have many places where PAGE_CACHE_SIZE assumed to be equal to PAGE_SIZE. And it's constant source of confusion on whether PAGE_CACHE_* or PAGE_* constant should be used in a particular case, especially on the border between fs and mm. Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much breakage to be doable. Let's stop pretending that pages in page cache are special. They are not. The changes are pretty straight-forward: - << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> ; - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN}; - page_cache_get() -> get_page(); - page_cache_release() -> put_page(); This patch contains automated changes generated with coccinelle using script below. For some reason, coccinelle doesn't patch header files. I've called spatch for them manually. The only adjustment after coccinelle is revert of changes to PAGE_CAHCE_ALIGN definition: we are going to drop it later. There are few places in the code where coccinelle didn't reach. I'll fix them manually in a separate patch. Comments and documentation also will be addressed with the separate patch. virtual patch @@ expression E; @@ - E << (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ expression E; @@ - E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) + E @@ @@ - PAGE_CACHE_SHIFT + PAGE_SHIFT @@ @@ - PAGE_CACHE_SIZE + PAGE_SIZE @@ @@ - PAGE_CACHE_MASK + PAGE_MASK @@ expression E; @@ - PAGE_CACHE_ALIGN(E) + PAGE_ALIGN(E) @@ expression E; @@ - page_cache_get(E) + get_page(E) @@ expression E; @@ - page_cache_release(E) + put_page(E) Signed-off-by: Kirill A. Shutemov Acked-by: Michal Hocko Signed-off-by: Linus Torvalds --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 7e5d7e018bea..669e419d6234 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1372,7 +1372,7 @@ unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); static inline void put_dev_sector(Sector p) { - page_cache_release(p.v); + put_page(p.v); } static inline bool __bvec_gap_to_prev(struct request_queue *q, -- cgit v1.2.3 From 37e58237a16b94fcd2c2d1b7e9c6e1ca661c231b Mon Sep 17 00:00:00 2001 From: Ming Lin Date: Tue, 22 Mar 2016 00:24:44 -0700 Subject: block: add offset in blk_add_request_payload() We could kmalloc() the payload, so need the offset in page. Signed-off-by: Ming Lin Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 5 +++-- drivers/block/skd_main.c | 2 +- drivers/scsi/sd.c | 2 +- include/linux/blkdev.h | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index b60537b2c35b..c50227796a26 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1523,6 +1523,7 @@ EXPORT_SYMBOL(blk_put_request); * blk_add_request_payload - add a payload to a request * @rq: request to update * @page: page backing the payload + * @offset: offset in page * @len: length of the payload. * * This allows to later add a payload to an already submitted request by @@ -1533,12 +1534,12 @@ EXPORT_SYMBOL(blk_put_request); * discard requests should ever use it. */ void blk_add_request_payload(struct request *rq, struct page *page, - unsigned int len) + int offset, unsigned int len) { struct bio *bio = rq->bio; bio->bi_io_vec->bv_page = page; - bio->bi_io_vec->bv_offset = 0; + bio->bi_io_vec->bv_offset = offset; bio->bi_io_vec->bv_len = len; bio->bi_iter.bi_size = len; diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 586f9168ffa4..9a9ec212fab8 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -562,7 +562,7 @@ skd_prep_discard_cdb(struct skd_scsi_request *scsi_req, put_unaligned_be32(count, &buf[16]); req = skreq->req; - blk_add_request_payload(req, page, len); + blk_add_request_payload(req, page, 0, len); } static void skd_request_fn_not_online(struct request_queue *q); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index f52b74cf8d1e..69b0a4a7a15f 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -779,7 +779,7 @@ static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd) * discarded on disk. This allows us to report completion on the full * amount of blocks described by the request. */ - blk_add_request_payload(rq, page, len); + blk_add_request_payload(rq, page, 0, len); ret = scsi_init_io(cmd); rq->__data_len = nr_bytes; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 669e419d6234..bbaa76757018 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -779,7 +779,7 @@ extern struct request *blk_make_request(struct request_queue *, struct bio *, extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, - unsigned int len); + int offset, unsigned int len); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, -- cgit v1.2.3 From 93e9d8e836cb1a9a58b33eb6643bf061c6119ef2 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 12 Apr 2016 12:32:46 -0600 Subject: block: add ability to flag write back caching on a device Add an internal helper and flag for setting whether a queue has write back caching, or write through (or none). Add a sysfs file to show this as well, and make it changeable from user space. This will replace the (awkward) blk_queue_flush() interface that drivers currently use to inform the block layer of write cache state and capabilities. Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig --- Documentation/block/queue-sysfs.txt | 9 +++++++++ block/blk-settings.c | 26 +++++++++++++++++++++++++ block/blk-sysfs.c | 39 +++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 3 +++ 4 files changed, 77 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/Documentation/block/queue-sysfs.txt b/Documentation/block/queue-sysfs.txt index e5d914845be6..dce25d848d92 100644 --- a/Documentation/block/queue-sysfs.txt +++ b/Documentation/block/queue-sysfs.txt @@ -141,6 +141,15 @@ control of this block device to that new IO scheduler. Note that writing an IO scheduler name to this file will attempt to load that IO scheduler module, if it isn't already present in the system. +write_cache (RW) +---------------- +When read, this file will display whether the device has write back +caching enabled or not. It will return "write back" for the former +case, and "write through" for the latter. Writing to this file can +change the kernels view of the device, but it doesn't alter the +device state. This means that it might not be safe to toggle the +setting from "write back" to "write through", since that will also +eliminate cache flushes issued by the kernel. Jens Axboe , February 2009 diff --git a/block/blk-settings.c b/block/blk-settings.c index 331e4eee0dda..c903bee43cf8 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -846,6 +846,32 @@ void blk_queue_flush_queueable(struct request_queue *q, bool queueable) } EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); +/** + * blk_queue_write_cache - configure queue's write cache + * @q: the request queue for the device + * @wc: write back cache on or off + * @fua: device supports FUA writes, if true + * + * Tell the block layer about the write cache of @q. + */ +void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) +{ + spin_lock_irq(q->queue_lock); + if (wc) { + queue_flag_set(QUEUE_FLAG_WC, q); + q->flush_flags = REQ_FLUSH; + } else + queue_flag_clear(QUEUE_FLAG_WC, q); + if (fua) { + if (wc) + q->flush_flags |= REQ_FUA; + queue_flag_set(QUEUE_FLAG_FUA, q); + } else + queue_flag_clear(QUEUE_FLAG_FUA, q); + spin_unlock_irq(q->queue_lock); +} +EXPORT_SYMBOL_GPL(blk_queue_write_cache); + static int __init blk_settings_init(void) { blk_max_low_pfn = max_low_pfn - 1; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 995b58d46ed1..99205965f559 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -347,6 +347,38 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page, return ret; } +static ssize_t queue_wc_show(struct request_queue *q, char *page) +{ + if (test_bit(QUEUE_FLAG_WC, &q->queue_flags)) + return sprintf(page, "write back\n"); + + return sprintf(page, "write through\n"); +} + +static ssize_t queue_wc_store(struct request_queue *q, const char *page, + size_t count) +{ + int set = -1; + + if (!strncmp(page, "write back", 10)) + set = 1; + else if (!strncmp(page, "write through", 13) || + !strncmp(page, "none", 4)) + set = 0; + + if (set == -1) + return -EINVAL; + + spin_lock_irq(q->queue_lock); + if (set) + queue_flag_set(QUEUE_FLAG_WC, q); + else + queue_flag_clear(QUEUE_FLAG_WC, q); + spin_unlock_irq(q->queue_lock); + + return count; +} + static struct queue_sysfs_entry queue_requests_entry = { .attr = {.name = "nr_requests", .mode = S_IRUGO | S_IWUSR }, .show = queue_requests_show, @@ -478,6 +510,12 @@ static struct queue_sysfs_entry queue_poll_entry = { .store = queue_poll_store, }; +static struct queue_sysfs_entry queue_wc_entry = { + .attr = {.name = "write_cache", .mode = S_IRUGO | S_IWUSR }, + .show = queue_wc_show, + .store = queue_wc_store, +}; + static struct attribute *default_attrs[] = { &queue_requests_entry.attr, &queue_ra_entry.attr, @@ -503,6 +541,7 @@ static struct attribute *default_attrs[] = { &queue_iostats_entry.attr, &queue_random_entry.attr, &queue_poll_entry.attr, + &queue_wc_entry.attr, NULL, }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index bbaa76757018..ba72687c5654 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -491,6 +491,8 @@ struct request_queue { #define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ #define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ #define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */ +#define QUEUE_FLAG_WC 23 /* Write back caching */ +#define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -1009,6 +1011,7 @@ extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush(struct request_queue *q, unsigned int flush); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); +extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); -- cgit v1.2.3 From 2245f6de6c68b225986229a2de78c240536f7f38 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 30 Mar 2016 10:19:30 -0600 Subject: block: kill blk_queue_flush() We don't have any drivers left using it, so kill it off. Update documentation to use the newer blk_queue_write_cache(). Signed-off-by: Jens Axboe Reviewed-by: Christoph Hellwig --- Documentation/block/writeback_cache_control.txt | 4 ++-- block/blk-settings.c | 20 -------------------- include/linux/blkdev.h | 1 - 3 files changed, 2 insertions(+), 23 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/Documentation/block/writeback_cache_control.txt b/Documentation/block/writeback_cache_control.txt index 83407d36630a..59e0516cbf6b 100644 --- a/Documentation/block/writeback_cache_control.txt +++ b/Documentation/block/writeback_cache_control.txt @@ -71,7 +71,7 @@ requests that have a payload. For devices with volatile write caches the driver needs to tell the block layer that it supports flushing caches by doing: - blk_queue_flush(sdkp->disk->queue, REQ_FLUSH); + blk_queue_write_cache(sdkp->disk->queue, true, false); and handle empty REQ_FLUSH requests in its prep_fn/request_fn. Note that REQ_FLUSH requests with a payload are automatically turned into a sequence @@ -79,7 +79,7 @@ of an empty REQ_FLUSH request followed by the actual write by the block layer. For devices that also support the FUA bit the block layer needs to be told to pass through the REQ_FUA bit using: - blk_queue_flush(sdkp->disk->queue, REQ_FLUSH | REQ_FUA); + blk_queue_write_cache(sdkp->disk->queue, true, true); and the driver must handle write requests that have the REQ_FUA bit set in prep_fn/request_fn. If the FUA bit is not natively supported the block diff --git a/block/blk-settings.c b/block/blk-settings.c index c903bee43cf8..80d9327a214b 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -820,26 +820,6 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask) } EXPORT_SYMBOL(blk_queue_update_dma_alignment); -/** - * blk_queue_flush - configure queue's cache flush capability - * @q: the request queue for the device - * @flush: 0, REQ_FLUSH or REQ_FLUSH | REQ_FUA - * - * Tell block layer cache flush capability of @q. If it supports - * flushing, REQ_FLUSH should be set. If it supports bypassing - * write cache for individual writes, REQ_FUA should be set. - */ -void blk_queue_flush(struct request_queue *q, unsigned int flush) -{ - WARN_ON_ONCE(flush & ~(REQ_FLUSH | REQ_FUA)); - - if (WARN_ON_ONCE(!(flush & REQ_FLUSH) && (flush & REQ_FUA))) - flush &= ~REQ_FUA; - - q->flush_flags = flush & (REQ_FLUSH | REQ_FUA); -} -EXPORT_SYMBOL_GPL(blk_queue_flush); - void blk_queue_flush_queueable(struct request_queue *q, bool queueable) { q->flush_not_queueable = !queueable; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba72687c5654..f3f232fa505d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1009,7 +1009,6 @@ extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); -extern void blk_queue_flush(struct request_queue *q, unsigned int flush); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); -- cgit v1.2.3 From c888a8f95ae5b1067855235b3b71c1ebccf504f5 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 13 Apr 2016 13:33:19 -0600 Subject: block: kill off q->flush_flags Now that we converted everything to the newer block write cache interface, kill off the queue flush_flags and queueable flush entries. Signed-off-by: Jens Axboe --- block/blk-core.c | 3 ++- block/blk-flush.c | 11 ++++++----- block/blk-settings.c | 18 ++++++++++-------- drivers/block/xen-blkback/xenbus.c | 2 +- drivers/md/dm-table.c | 12 ++++++------ drivers/md/raid5-cache.c | 3 ++- drivers/target/target_core_iblock.c | 6 +++--- include/linux/blkdev.h | 5 ++--- 8 files changed, 32 insertions(+), 28 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index c50227796a26..2475b1c72773 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1964,7 +1964,8 @@ generic_make_request_checks(struct bio *bio) * drivers without flush support don't have to worry * about them. */ - if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && !q->flush_flags) { + if ((bio->bi_rw & (REQ_FLUSH | REQ_FUA)) && + !test_bit(QUEUE_FLAG_WC, &q->queue_flags)) { bio->bi_rw &= ~(REQ_FLUSH | REQ_FUA); if (!nr_sectors) { err = 0; diff --git a/block/blk-flush.c b/block/blk-flush.c index 9c423e53324a..b1c91d229e5e 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -95,17 +95,18 @@ enum { static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq); -static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq) +static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq) { unsigned int policy = 0; if (blk_rq_sectors(rq)) policy |= REQ_FSEQ_DATA; - if (fflags & REQ_FLUSH) { + if (fflags & (1UL << QUEUE_FLAG_WC)) { if (rq->cmd_flags & REQ_FLUSH) policy |= REQ_FSEQ_PREFLUSH; - if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA)) + if (!(fflags & (1UL << QUEUE_FLAG_FUA)) && + (rq->cmd_flags & REQ_FUA)) policy |= REQ_FSEQ_POSTFLUSH; } return policy; @@ -384,7 +385,7 @@ static void mq_flush_data_end_io(struct request *rq, int error) void blk_insert_flush(struct request *rq) { struct request_queue *q = rq->q; - unsigned int fflags = q->flush_flags; /* may change, cache */ + unsigned long fflags = q->queue_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx); @@ -393,7 +394,7 @@ void blk_insert_flush(struct request *rq) * REQ_FLUSH and FUA for the driver. */ rq->cmd_flags &= ~REQ_FLUSH; - if (!(fflags & REQ_FUA)) + if (!(fflags & (1UL << QUEUE_FLAG_FUA))) rq->cmd_flags &= ~REQ_FUA; /* diff --git a/block/blk-settings.c b/block/blk-settings.c index 80d9327a214b..f679ae122843 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -822,7 +822,12 @@ EXPORT_SYMBOL(blk_queue_update_dma_alignment); void blk_queue_flush_queueable(struct request_queue *q, bool queueable) { - q->flush_not_queueable = !queueable; + spin_lock_irq(q->queue_lock); + if (queueable) + clear_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags); + else + set_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags); + spin_unlock_irq(q->queue_lock); } EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); @@ -837,16 +842,13 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) { spin_lock_irq(q->queue_lock); - if (wc) { + if (wc) queue_flag_set(QUEUE_FLAG_WC, q); - q->flush_flags = REQ_FLUSH; - } else + else queue_flag_clear(QUEUE_FLAG_WC, q); - if (fua) { - if (wc) - q->flush_flags |= REQ_FUA; + if (fua) queue_flag_set(QUEUE_FLAG_FUA, q); - } else + else queue_flag_clear(QUEUE_FLAG_FUA, q); spin_unlock_irq(q->queue_lock); } diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 26aa080e243c..3355f1cdd4e5 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -477,7 +477,7 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle, vbd->type |= VDISK_REMOVABLE; q = bdev_get_queue(bdev); - if (q && q->flush_flags) + if (q && test_bit(QUEUE_FLAG_WC, &q->queue_flags)) vbd->flush_support = true; if (q && blk_queue_secdiscard(q)) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 4b1ffc0abe11..626a5ec04466 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1348,13 +1348,13 @@ static void dm_table_verify_integrity(struct dm_table *t) static int device_flush_capable(struct dm_target *ti, struct dm_dev *dev, sector_t start, sector_t len, void *data) { - unsigned flush = (*(unsigned *)data); + unsigned long flush = (unsigned long) data; struct request_queue *q = bdev_get_queue(dev->bdev); - return q && (q->flush_flags & flush); + return q && (q->queue_flags & flush); } -static bool dm_table_supports_flush(struct dm_table *t, unsigned flush) +static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush) { struct dm_target *ti; unsigned i = 0; @@ -1375,7 +1375,7 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned flush) return true; if (ti->type->iterate_devices && - ti->type->iterate_devices(ti, device_flush_capable, &flush)) + ti->type->iterate_devices(ti, device_flush_capable, (void *) flush)) return true; } @@ -1518,9 +1518,9 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, else queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); - if (dm_table_supports_flush(t, REQ_FLUSH)) { + if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_WC))) { wc = true; - if (dm_table_supports_flush(t, REQ_FUA)) + if (dm_table_supports_flush(t, (1UL << QUEUE_FLAG_FUA))) fua = true; } blk_queue_write_cache(q, wc, fua); diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c index 9531f5f05b93..26f14970a858 100644 --- a/drivers/md/raid5-cache.c +++ b/drivers/md/raid5-cache.c @@ -1188,6 +1188,7 @@ ioerr: int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) { + struct request_queue *q = bdev_get_queue(rdev->bdev); struct r5l_log *log; if (PAGE_SIZE != 4096) @@ -1197,7 +1198,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) return -ENOMEM; log->rdev = rdev; - log->need_cache_flush = (rdev->bdev->bd_disk->queue->flush_flags != 0); + log->need_cache_flush = test_bit(QUEUE_FLAG_WC, &q->queue_flags) != 0; log->uuid_checksum = crc32c_le(~0, rdev->mddev->uuid, sizeof(rdev->mddev->uuid)); diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 026a758e5778..7c4efb4417b0 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -687,10 +687,10 @@ iblock_execute_rw(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, * Force writethrough using WRITE_FUA if a volatile write cache * is not enabled, or if initiator set the Force Unit Access bit. */ - if (q->flush_flags & REQ_FUA) { + if (test_bit(QUEUE_FLAG_FUA, &q->queue_flags)) { if (cmd->se_cmd_flags & SCF_FUA) rw = WRITE_FUA; - else if (!(q->flush_flags & REQ_FLUSH)) + else if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) rw = WRITE_FUA; else rw = WRITE; @@ -836,7 +836,7 @@ static bool iblock_get_write_cache(struct se_device *dev) struct block_device *bd = ib_dev->ibd_bd; struct request_queue *q = bdev_get_queue(bd); - return q->flush_flags & REQ_FLUSH; + return test_bit(QUEUE_FLAG_WC, &q->queue_flags); } static const struct target_backend_ops iblock_ops = { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3f232fa505d..57c085917da6 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -433,8 +433,6 @@ struct request_queue { /* * for flush operations */ - unsigned int flush_flags; - unsigned int flush_not_queueable:1; struct blk_flush_queue *fq; struct list_head requeue_list; @@ -493,6 +491,7 @@ struct request_queue { #define QUEUE_FLAG_POLL 22 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 23 /* Write back caching */ #define QUEUE_FLAG_FUA 24 /* device supports FUA writes */ +#define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -1365,7 +1364,7 @@ static inline unsigned int block_size(struct block_device *bdev) static inline bool queue_flush_queueable(struct request_queue *q) { - return !q->flush_not_queueable; + return !test_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags); } typedef struct {struct page *v;} Sector; -- cgit v1.2.3 From 38f252553300ee1d3346a5273e95fe1dd60ca50a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 16 Apr 2016 14:55:28 -0400 Subject: block: add __blkdev_issue_discard This is a version of blkdev_issue_discard which doesn't wait for the I/O to complete, but instead allows the caller to submit the final bio and/or chain it to others. Signed-off-by: Christoph Hellwig Signed-off-by: Ming Lin Signed-off-by: Sagi Grimberg Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 63 +++++++++++++++++++++++++++++--------------------- include/linux/blkdev.h | 2 ++ 2 files changed, 39 insertions(+), 26 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-lib.c b/block/blk-lib.c index 700d248cbde5..ccbce2b2ea05 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -22,45 +22,25 @@ static struct bio *next_bio(struct bio *bio, int rw, unsigned int nr_pages, return new; } -/** - * blkdev_issue_discard - queue a discard - * @bdev: blockdev to issue discard for - * @sector: start sector - * @nr_sects: number of sectors to discard - * @gfp_mask: memory allocation flags (for bio_alloc) - * @flags: BLKDEV_IFL_* flags to control behaviour - * - * Description: - * Issue a discard request for the sectors in question. - */ -int blkdev_issue_discard(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) +int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop) { struct request_queue *q = bdev_get_queue(bdev); - int type = REQ_WRITE | REQ_DISCARD; + struct bio *bio = *biop; unsigned int granularity; int alignment; - struct bio *bio = NULL; - int ret = 0; - struct blk_plug plug; if (!q) return -ENXIO; - if (!blk_queue_discard(q)) return -EOPNOTSUPP; + if ((type & REQ_SECURE) && !blk_queue_secdiscard(q)) + return -EOPNOTSUPP; /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); alignment = (bdev_discard_alignment(bdev) >> 9) % granularity; - if (flags & BLKDEV_DISCARD_SECURE) { - if (!blk_queue_secdiscard(q)) - return -EOPNOTSUPP; - type |= REQ_SECURE; - } - - blk_start_plug(&plug); while (nr_sects) { unsigned int req_sects; sector_t end_sect, tmp; @@ -98,7 +78,38 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, */ cond_resched(); } - if (bio) + + *biop = bio; + return 0; +} +EXPORT_SYMBOL(__blkdev_issue_discard); + +/** + * blkdev_issue_discard - queue a discard + * @bdev: blockdev to issue discard for + * @sector: start sector + * @nr_sects: number of sectors to discard + * @gfp_mask: memory allocation flags (for bio_alloc) + * @flags: BLKDEV_IFL_* flags to control behaviour + * + * Description: + * Issue a discard request for the sectors in question. + */ +int blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, unsigned long flags) +{ + int type = REQ_WRITE | REQ_DISCARD; + struct bio *bio = NULL; + struct blk_plug plug; + int ret; + + if (flags & BLKDEV_DISCARD_SECURE) + type |= REQ_SECURE; + + blk_start_plug(&plug); + ret = __blkdev_issue_discard(bdev, sector, nr_sects, gfp_mask, type, + &bio); + if (!ret && bio) ret = submit_bio_wait(type, bio); blk_finish_plug(&plug); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba72687c5654..b79131acf6c0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1131,6 +1131,8 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); +extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, int type, struct bio **biop); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, -- cgit v1.2.3 From 2af3a8159cd204fc8437ed2f75863f0fb930f0d0 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 10 May 2016 10:23:52 -0600 Subject: block: Add vfs_msg() interface In preparation of moving DAX capability checks to the block layer from filesystem code, add a VFS message interface that aligns with filesystem's message format. For instance, a vfs_msg() message followed by XFS messages in case of a dax mount error may look like: VFS (pmem0p1): error: unaligned partition for dax XFS (pmem0p1): DAX unsupported by block device. Turning off DAX. XFS (pmem0p1): Mounting V5 Filesystem : vfs_msg() is largely based on ext4_msg(). Signed-off-by: Toshi Kani Reviewed-by: Christoph Hellwig Cc: Alexander Viro Cc: Jens Axboe Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: Jan Kara Cc: Dave Chinner Cc: Dan Williams Cc: Ross Zwisler Cc: Christoph Hellwig Cc: Boaz Harrosh Signed-off-by: Vishal Verma --- fs/block_dev.c | 12 ++++++++++++ include/linux/blkdev.h | 11 +++++++++++ 2 files changed, 23 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/fs/block_dev.c b/fs/block_dev.c index b25bb230b28a..91e0ec0233c0 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -50,6 +50,18 @@ struct block_device *I_BDEV(struct inode *inode) } EXPORT_SYMBOL(I_BDEV); +void __vfs_msg(struct super_block *sb, const char *prefix, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk_ratelimited("%sVFS (%s): %pV\n", prefix, sb->s_id, &vaf); + va_end(args); +} + static void bdev_write_inode(struct block_device *bdev) { struct inode *inode = bdev->bd_inode; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 669e419d6234..78c48ab22f46 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -767,6 +767,17 @@ static inline void rq_flush_dcache_pages(struct request *rq) } #endif +#ifdef CONFIG_PRINTK +#define vfs_msg(sb, level, fmt, ...) \ + __vfs_msg(sb, level, fmt, ##__VA_ARGS__) +#else +#define vfs_msg(sb, level, fmt, ...) \ +do { \ + no_printk(fmt, ##__VA_ARGS__); \ + __vfs_msg(sb, "", " "); \ +} while (0) +#endif + extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); -- cgit v1.2.3 From 2d96afc8f70ef86c66a0b5d80c24a27d6dd13df3 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 10 May 2016 10:23:53 -0600 Subject: block: Add bdev_dax_supported() for dax mount checks DAX imposes additional requirements to a device. Add bdev_dax_supported() which performs all the precondition checks necessary for filesystem to mount the device with dax option. Also add a new check to verify if a partition is aligned by 4KB. When a partition is unaligned, any dax read/write access fails, except for metadata update. Signed-off-by: Toshi Kani Reviewed-by: Christoph Hellwig Cc: Alexander Viro Cc: Jens Axboe Cc: "Theodore Ts'o" Cc: Andreas Dilger Cc: Jan Kara Cc: Dave Chinner Cc: Dan Williams Cc: Ross Zwisler Cc: Christoph Hellwig Cc: Boaz Harrosh Signed-off-by: Vishal Verma --- fs/block_dev.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 1 + 2 files changed, 46 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/fs/block_dev.c b/fs/block_dev.c index 91e0ec0233c0..518cde62c01c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -509,6 +509,51 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) } EXPORT_SYMBOL_GPL(bdev_direct_access); +/** + * bdev_dax_supported() - Check if the device supports dax for filesystem + * @sb: The superblock of the device + * @blocksize: The block size of the device + * + * This is a library function for filesystems to check if the block device + * can be mounted with dax option. + * + * Return: negative errno if unsupported, 0 if supported. + */ +int bdev_dax_supported(struct super_block *sb, int blocksize) +{ + struct blk_dax_ctl dax = { + .sector = 0, + .size = PAGE_SIZE, + }; + int err; + + if (blocksize != PAGE_SIZE) { + vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax"); + return -EINVAL; + } + + err = bdev_direct_access(sb->s_bdev, &dax); + if (err < 0) { + switch (err) { + case -EOPNOTSUPP: + vfs_msg(sb, KERN_ERR, + "error: device does not support dax"); + break; + case -EINVAL: + vfs_msg(sb, KERN_ERR, + "error: unaligned partition for dax"); + break; + default: + vfs_msg(sb, KERN_ERR, + "error: dax access failed (%d)", err); + } + return err; + } + + return 0; +} +EXPORT_SYMBOL_GPL(bdev_dax_supported); + /* * pseudo-fs */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 78c48ab22f46..71231a55debd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1688,6 +1688,7 @@ extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *); +extern int bdev_dax_supported(struct super_block *, int); #else /* CONFIG_BLOCK */ struct block_device; -- cgit v1.2.3 From a8078b1fc616da6112eb95f0063cd34531d4ccf0 Mon Sep 17 00:00:00 2001 From: Toshi Kani Date: Tue, 10 May 2016 10:23:57 -0600 Subject: block: Update blkdev_dax_capable() for consistency blkdev_dax_capable() is similar to bdev_dax_supported(), but needs to remain as a separate interface for checking dax capability of a raw block device. Rename and relocate blkdev_dax_capable() to keep them maintained consistently, and call bdev_direct_access() for the dax capability check. There is no change in the behavior. Link: https://lkml.org/lkml/2016/5/9/950 Signed-off-by: Toshi Kani Reviewed-by: Jan Kara Cc: Alexander Viro Cc: Jens Axboe Cc: Andreas Dilger Cc: Jan Kara Cc: Dave Chinner Cc: Dan Williams Cc: Ross Zwisler Cc: Christoph Hellwig Cc: Boaz Harrosh Signed-off-by: Vishal Verma --- block/ioctl.c | 30 ------------------------------ fs/block_dev.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/blkdev.h | 1 + include/linux/fs.h | 8 -------- 4 files changed, 38 insertions(+), 40 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/ioctl.c b/block/ioctl.c index 4ff1f92f89ca..7eeda072dc70 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include #include @@ -407,35 +406,6 @@ static inline int is_unrecognized_ioctl(int ret) ret == -ENOIOCTLCMD; } -#ifdef CONFIG_FS_DAX -bool blkdev_dax_capable(struct block_device *bdev) -{ - struct gendisk *disk = bdev->bd_disk; - - if (!disk->fops->direct_access) - return false; - - /* - * If the partition is not aligned on a page boundary, we can't - * do dax I/O to it. - */ - if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) - || (bdev->bd_part->nr_sects % (PAGE_SIZE / 512))) - return false; - - /* - * If the device has known bad blocks, force all I/O through the - * driver / page cache. - * - * TODO: support finer grained dax error handling - */ - if (disk->bb && disk->bb->count) - return false; - - return true; -} -#endif - static int blkdev_flushbuf(struct block_device *bdev, fmode_t mode, unsigned cmd, unsigned long arg) { diff --git a/fs/block_dev.c b/fs/block_dev.c index 518cde62c01c..8477d4501b1e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "internal.h" @@ -554,6 +555,40 @@ int bdev_dax_supported(struct super_block *sb, int blocksize) } EXPORT_SYMBOL_GPL(bdev_dax_supported); +/** + * bdev_dax_capable() - Return if the raw device is capable for dax + * @bdev: The device for raw block device access + */ +bool bdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + struct blk_dax_ctl dax = { + .size = PAGE_SIZE, + }; + + if (!IS_ENABLED(CONFIG_FS_DAX)) + return false; + + dax.sector = 0; + if (bdev_direct_access(bdev, &dax) < 0) + return false; + + dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512); + if (bdev_direct_access(bdev, &dax) < 0) + return false; + + /* + * If the device has known bad blocks, force all I/O through the + * driver / page cache. + * + * TODO: support finer grained dax error handling + */ + if (disk->bb && disk->bb->count) + return false; + + return true; +} + /* * pseudo-fs */ @@ -1295,7 +1330,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!ret) { bd_set_size(bdev,(loff_t)get_capacity(disk)<<9); - if (!blkdev_dax_capable(bdev)) + if (!bdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } @@ -1332,7 +1367,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) goto out_clear; } bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9); - if (!blkdev_dax_capable(bdev)) + if (!bdev_dax_capable(bdev)) bdev->bd_inode->i_flags &= ~S_DAX; } } else { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 71231a55debd..27cbefe8c985 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1689,6 +1689,7 @@ extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); extern long bdev_direct_access(struct block_device *, struct blk_dax_ctl *); extern int bdev_dax_supported(struct super_block *, int); +extern bool bdev_dax_capable(struct block_device *); #else /* CONFIG_BLOCK */ struct block_device; diff --git a/include/linux/fs.h b/include/linux/fs.h index 9f2813090d1b..17f934fcf564 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2319,14 +2319,6 @@ extern struct super_block *freeze_bdev(struct block_device *); extern void emergency_thaw_all(void); extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); extern int fsync_bdev(struct block_device *); -#ifdef CONFIG_FS_DAX -extern bool blkdev_dax_capable(struct block_device *bdev); -#else -static inline bool blkdev_dax_capable(struct block_device *bdev) -{ - return false; -} -#endif extern struct super_block *blockdev_superblock; -- cgit v1.2.3 From 0a70bd43053331d99881211e1d09f32de531432f Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Wed, 24 Feb 2016 14:02:11 -0800 Subject: dax: enable dax in the presence of known media errors (badblocks) 1/ If a mapping overlaps a bad sector fail the request. 2/ Do not opportunistically report more dax-capable capacity than is requested when errors present. Reviewed-by: Jeff Moyer Reviewed-by: Christoph Hellwig Signed-off-by: Dan Williams [vishal: fix a conflict with system RAM collision patches] [vishal: add a 'size' parameter to ->direct_access] [vishal: fix a conflict with DAX alignment check patches] Signed-off-by: Vishal Verma --- arch/powerpc/sysdev/axonram.c | 2 +- drivers/block/brd.c | 2 +- drivers/nvdimm/pmem.c | 10 +++++++++- drivers/s390/block/dcssblk.c | 4 ++-- fs/block_dev.c | 13 +------------ include/linux/blkdev.h | 2 +- 6 files changed, 15 insertions(+), 18 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/arch/powerpc/sysdev/axonram.c b/arch/powerpc/sysdev/axonram.c index 0d112b94d91d..ff75d70f7285 100644 --- a/arch/powerpc/sysdev/axonram.c +++ b/arch/powerpc/sysdev/axonram.c @@ -143,7 +143,7 @@ axon_ram_make_request(struct request_queue *queue, struct bio *bio) */ static long axon_ram_direct_access(struct block_device *device, sector_t sector, - void __pmem **kaddr, pfn_t *pfn) + void __pmem **kaddr, pfn_t *pfn, long size) { struct axon_ram_bank *bank = device->bd_disk->private_data; loff_t offset = (loff_t)sector << AXON_RAM_SECTOR_SHIFT; diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 51a071e32221..c04bd9bc39fd 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -381,7 +381,7 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, #ifdef CONFIG_BLK_DEV_RAM_DAX static long brd_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, pfn_t *pfn) + void __pmem **kaddr, pfn_t *pfn, long size) { struct brd_device *brd = bdev->bd_disk->private_data; struct page *page; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index f798899338ed..c447579bd853 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -182,14 +182,22 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector, } static long pmem_direct_access(struct block_device *bdev, sector_t sector, - void __pmem **kaddr, pfn_t *pfn) + void __pmem **kaddr, pfn_t *pfn, long size) { struct pmem_device *pmem = bdev->bd_disk->private_data; resource_size_t offset = sector * 512 + pmem->data_offset; + if (unlikely(is_bad_pmem(&pmem->bb, sector, size))) + return -EIO; *kaddr = pmem->virt_addr + offset; *pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags); + /* + * If badblocks are present, limit known good range to the + * requested range. + */ + if (unlikely(pmem->bb.count)) + return size; return pmem->size - pmem->pfn_pad - offset; } diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c index 1bce9cf51b1e..6ac33984bc0f 100644 --- a/drivers/s390/block/dcssblk.c +++ b/drivers/s390/block/dcssblk.c @@ -31,7 +31,7 @@ static void dcssblk_release(struct gendisk *disk, fmode_t mode); static blk_qc_t dcssblk_make_request(struct request_queue *q, struct bio *bio); static long dcssblk_direct_access(struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, pfn_t *pfn); + void __pmem **kaddr, pfn_t *pfn, long size); static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0"; @@ -883,7 +883,7 @@ fail: static long dcssblk_direct_access (struct block_device *bdev, sector_t secnum, - void __pmem **kaddr, pfn_t *pfn) + void __pmem **kaddr, pfn_t *pfn, long size) { struct dcssblk_dev_info *dev_info; unsigned long offset, dev_sz; diff --git a/fs/block_dev.c b/fs/block_dev.c index 8477d4501b1e..45839b27972c 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include "internal.h" @@ -501,7 +500,7 @@ long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax) sector += get_start_sect(bdev); if (sector % (PAGE_SIZE / 512)) return -EINVAL; - avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn); + avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size); if (!avail) return -ERANGE; if (avail > 0 && avail & ~PAGE_MASK) @@ -561,7 +560,6 @@ EXPORT_SYMBOL_GPL(bdev_dax_supported); */ bool bdev_dax_capable(struct block_device *bdev) { - struct gendisk *disk = bdev->bd_disk; struct blk_dax_ctl dax = { .size = PAGE_SIZE, }; @@ -577,15 +575,6 @@ bool bdev_dax_capable(struct block_device *bdev) if (bdev_direct_access(bdev, &dax) < 0) return false; - /* - * If the device has known bad blocks, force all I/O through the - * driver / page cache. - * - * TODO: support finer grained dax error handling - */ - if (disk->bb && disk->bb->count) - return false; - return true; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 27cbefe8c985..cf7c13c2c38d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1668,7 +1668,7 @@ struct block_device_operations { int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); long (*direct_access)(struct block_device *, sector_t, void __pmem **, - pfn_t *); + pfn_t *, long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ -- cgit v1.2.3