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 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'block') 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) { -- cgit v1.3-8-gc7d7 From 7244ad69cc1382fd4dfb18a4fea5613acd67a2e9 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 20 May 2016 17:01:27 -0700 Subject: block/partitions/ldm.c: use generic UUID library Instead of opencoding let's use generic UUID library functions here. Signed-off-by: Andy Shevchenko Cc: "Richard Russon (FlatCap)" Cc: Jens Axboe Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- block/partitions/ldm.c | 60 ++++---------------------------------------------- 1 file changed, 4 insertions(+), 56 deletions(-) (limited to 'block') diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c index e507cfbd044e..edcea70674c9 100644 --- a/block/partitions/ldm.c +++ b/block/partitions/ldm.c @@ -27,6 +27,8 @@ #include #include #include +#include + #include "ldm.h" #include "check.h" #include "msdos.h" @@ -65,60 +67,6 @@ void _ldm_printk(const char *level, const char *function, const char *fmt, ...) va_end(args); } -/** - * ldm_parse_hexbyte - Convert a ASCII hex number to a byte - * @src: Pointer to at least 2 characters to convert. - * - * Convert a two character ASCII hex string to a number. - * - * Return: 0-255 Success, the byte was parsed correctly - * -1 Error, an invalid character was supplied - */ -static int ldm_parse_hexbyte (const u8 *src) -{ - unsigned int x; /* For correct wrapping */ - int h; - - /* high part */ - x = h = hex_to_bin(src[0]); - if (h < 0) - return -1; - - /* low part */ - h = hex_to_bin(src[1]); - if (h < 0) - return -1; - - return (x << 4) + h; -} - -/** - * ldm_parse_guid - Convert GUID from ASCII to binary - * @src: 36 char string of the form fa50ff2b-f2e8-45de-83fa-65417f2f49ba - * @dest: Memory block to hold binary GUID (16 bytes) - * - * N.B. The GUID need not be NULL terminated. - * - * Return: 'true' @dest contains binary GUID - * 'false' @dest contents are undefined - */ -static bool ldm_parse_guid (const u8 *src, u8 *dest) -{ - static const int size[] = { 4, 2, 2, 2, 6 }; - int i, j, v; - - if (src[8] != '-' || src[13] != '-' || - src[18] != '-' || src[23] != '-') - return false; - - for (j = 0; j < 5; j++, src++) - for (i = 0; i < size[j]; i++, src+=2, *dest++ = v) - if ((v = ldm_parse_hexbyte (src)) < 0) - return false; - - return true; -} - /** * ldm_parse_privhead - Read the LDM Database PRIVHEAD structure * @data: Raw database PRIVHEAD structure loaded from the device @@ -167,7 +115,7 @@ static bool ldm_parse_privhead(const u8 *data, struct privhead *ph) ldm_error("PRIVHEAD disk size doesn't match real disk size"); return false; } - if (!ldm_parse_guid(data + 0x0030, ph->disk_id)) { + if (uuid_be_to_bin(data + 0x0030, (uuid_be *)ph->disk_id)) { ldm_error("PRIVHEAD contains an invalid GUID."); return false; } @@ -944,7 +892,7 @@ static bool ldm_parse_dsk3 (const u8 *buffer, int buflen, struct vblk *vb) disk = &vb->vblk.disk; ldm_get_vstr (buffer + 0x18 + r_diskid, disk->alt_name, sizeof (disk->alt_name)); - if (!ldm_parse_guid (buffer + 0x19 + r_name, disk->disk_id)) + if (uuid_be_to_bin(buffer + 0x19 + r_name, (uuid_be *)disk->disk_id)) return false; return true; -- cgit v1.3-8-gc7d7 From acc93d30d7d43f428272c20a047389c4cbca82ba Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sat, 7 May 2016 11:40:28 -0700 Subject: Revert "block: enable dax for raw block devices" This reverts commit 5a023cdba50c5f5f2bc351783b3131699deb3937. The functionality is superseded by the new "Device DAX" facility. Cc: Jeff Moyer Cc: Christoph Hellwig Cc: Dave Chinner Cc: Andrew Morton Cc: Ross Zwisler Cc: Jan Kara Signed-off-by: Dan Williams --- block/ioctl.c | 32 ----------------- fs/block_dev.c | 96 +++++++++++++++---------------------------------- include/linux/fs.h | 8 ----- include/uapi/linux/fs.h | 1 - 4 files changed, 29 insertions(+), 108 deletions(-) (limited to 'block') diff --git a/block/ioctl.c b/block/ioctl.c index 4ff1f92f89ca..698c7933d582 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -407,35 +407,6 @@ 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) { @@ -598,9 +569,6 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); - case BLKDAXGET: - return put_int(arg, !!(bdev->bd_inode->i_flags & S_DAX)); - break; case IOC_PR_REGISTER: return blkdev_pr_register(bdev, argp); case IOC_PR_RESERVE: diff --git a/fs/block_dev.c b/fs/block_dev.c index 20a2c02b77c4..36ee10ca503e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include "internal.h" @@ -1159,6 +1160,33 @@ void bd_set_size(struct block_device *bdev, loff_t size) } EXPORT_SYMBOL(bd_set_size); +static bool blkdev_dax_capable(struct block_device *bdev) +{ + struct gendisk *disk = bdev->bd_disk; + + if (!disk->fops->direct_access || !IS_ENABLED(CONFIG_FS_DAX)) + 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; +} + static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part); /* @@ -1724,79 +1752,13 @@ static const struct address_space_operations def_blk_aops = { .is_dirty_writeback = buffer_check_dirty_writeback, }; -#ifdef CONFIG_FS_DAX -/* - * In the raw block case we do not need to contend with truncation nor - * unwritten file extents. Without those concerns there is no need for - * additional locking beyond the mmap_sem context that these routines - * are already executing under. - * - * Note, there is no protection if the block device is dynamically - * resized (partition grow/shrink) during a fault. A stable block device - * size is already not enforced in the blkdev_direct_IO path. - * - * For DAX, it is the responsibility of the block device driver to - * ensure the whole-disk device size is stable while requests are in - * flight. - * - * Finally, unlike the filemap_page_mkwrite() case there is no - * filesystem superblock to sync against freezing. We still include a - * pfn_mkwrite callback for dax drivers to receive write fault - * notifications. - */ -static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - return __dax_fault(vma, vmf, blkdev_get_block, NULL); -} - -static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma, - struct vm_fault *vmf) -{ - return dax_pfn_mkwrite(vma, vmf); -} - -static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, unsigned int flags) -{ - return __dax_pmd_fault(vma, addr, pmd, flags, blkdev_get_block, NULL); -} - -static const struct vm_operations_struct blkdev_dax_vm_ops = { - .fault = blkdev_dax_fault, - .pmd_fault = blkdev_dax_pmd_fault, - .pfn_mkwrite = blkdev_dax_pfn_mkwrite, -}; - -static const struct vm_operations_struct blkdev_default_vm_ops = { - .fault = filemap_fault, - .map_pages = filemap_map_pages, -}; - -static int blkdev_mmap(struct file *file, struct vm_area_struct *vma) -{ - struct inode *bd_inode = bdev_file_inode(file); - - file_accessed(file); - if (IS_DAX(bd_inode)) { - vma->vm_ops = &blkdev_dax_vm_ops; - vma->vm_flags |= VM_MIXEDMAP | VM_HUGEPAGE; - } else { - vma->vm_ops = &blkdev_default_vm_ops; - } - - return 0; -} -#else -#define blkdev_mmap generic_file_mmap -#endif - const struct file_operations def_blk_fops = { .open = blkdev_open, .release = blkdev_close, .llseek = block_llseek, .read_iter = blkdev_read_iter, .write_iter = blkdev_write_iter, - .mmap = blkdev_mmap, + .mmap = generic_file_mmap, .fsync = blkdev_fsync, .unlocked_ioctl = block_ioctl, #ifdef CONFIG_COMPAT diff --git a/include/linux/fs.h b/include/linux/fs.h index 70e61b58baaf..8363a10660f6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2320,14 +2320,6 @@ 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; diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index a079d50376e1..fbff8b28aa35 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -222,7 +222,6 @@ struct fsxattr { #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BLKZEROOUT _IO(0x12,127) -#define BLKDAXGET _IO(0x12,129) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ -- cgit v1.3-8-gc7d7 From c7de5726307620711a4753b2a13d9e5daecc1081 Mon Sep 17 00:00:00 2001 From: Ming Lin Date: Wed, 25 May 2016 23:23:27 -0700 Subject: blk-mq: clear q->mq_ops if init fail blk_mq_init_queue() calls blk_mq_init_allocated_queue(), but q->mq_ops was not cleared when blk_mq_init_allocated_queue() fails. Then blk_cleanup_queue() calls blk_mq_free_queue() which will crash because: - q->all_q_node is not added to all_q_list yet - q->tag_set is NULL - hctx was not setup yet or already freed Fixed it by clearing q->mq_ops on error path. Signed-off-by: Ming Lin Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 7df9c9263b21..29cbc1b5fbdb 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2020,7 +2020,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, q->queue_ctx = alloc_percpu(struct blk_mq_ctx); if (!q->queue_ctx) - return ERR_PTR(-ENOMEM); + goto err_exit; q->queue_hw_ctx = kzalloc_node(nr_cpu_ids * sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, set->numa_node); @@ -2084,6 +2084,8 @@ err_map: kfree(q->queue_hw_ctx); err_percpu: free_percpu(q->queue_ctx); +err_exit: + q->mq_ops = NULL; return ERR_PTR(-ENOMEM); } EXPORT_SYMBOL(blk_mq_init_allocated_queue); -- cgit v1.3-8-gc7d7 From 87c279e613f848c691111b29d49de8df3f4f56da Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Wed, 1 Jun 2016 22:18:48 -0700 Subject: blk-mq: really fix plug list flushing for nomerge queues Commit 0809e3ac6231 ("block: fix plug list flushing for nomerge queues") updated blk_mq_make_request() to set request_count even when blk_queue_nomerges() returns true. However, blk_mq_make_request() only does limited plugging and doesn't use request_count; blk_sq_make_request() is the one that should have been fixed. Do that and get rid of the unnecessary work in the mq version. Fixes: 0809e3ac6231 ("block: fix plug list flushing for nomerge queues") Signed-off-by: Omar Sandoval Reviewed-by: Ming Lei Reviewed-by: Jeff Moyer Signed-off-by: Jens Axboe --- block/blk-mq.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) (limited to 'block') diff --git a/block/blk-mq.c b/block/blk-mq.c index 29cbc1b5fbdb..f9b9049b1284 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1262,12 +1262,9 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q)) { - if (blk_attempt_plug_merge(q, bio, &request_count, - &same_queue_rq)) - return BLK_QC_T_NONE; - } else - request_count = blk_plug_queued_count(q); + if (!is_flush_fua && !blk_queue_nomerges(q) && + blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) + return BLK_QC_T_NONE; rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) @@ -1358,9 +1355,11 @@ static blk_qc_t blk_sq_make_request(struct request_queue *q, struct bio *bio) blk_queue_split(q, &bio, q->bio_split); - if (!is_flush_fua && !blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, NULL)) - return BLK_QC_T_NONE; + if (!is_flush_fua && !blk_queue_nomerges(q)) { + if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) + return BLK_QC_T_NONE; + } else + request_count = blk_plug_queued_count(q); rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) -- cgit v1.3-8-gc7d7 From 05bd92dddc595d74ea645e793c1f3bd4b1fc251a Mon Sep 17 00:00:00 2001 From: Shaun Tancheff Date: Tue, 7 Jun 2016 11:32:13 -0500 Subject: block: missing bio_put following submit_bio_wait submit_bio_wait() gives the caller an opportunity to examine struct bio and so expects the caller to issue the put_bio() This fixes a memory leak reported by a few people in 4.7-rc2 kmemleak report after 9082e87bfbf8 ("block: remove struct bio_batch") Signed-off-by: Shaun Tancheff Tested-by: Catalin Marinas Tested-by: Larry Finger@lwfinger.net Tested-by: David Drysdale Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-lib.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) (limited to 'block') diff --git a/block/blk-lib.c b/block/blk-lib.c index 23d7f301a196..9e29dc351695 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -113,6 +113,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, ret = submit_bio_wait(type, bio); if (ret == -EOPNOTSUPP) ret = 0; + bio_put(bio); } blk_finish_plug(&plug); @@ -165,8 +166,10 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, } } - if (bio) + if (bio) { ret = submit_bio_wait(REQ_WRITE | REQ_WRITE_SAME, bio); + bio_put(bio); + } return ret != -EOPNOTSUPP ? ret : 0; } EXPORT_SYMBOL(blkdev_issue_write_same); @@ -206,8 +209,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, } } - if (bio) - return submit_bio_wait(WRITE, bio); + if (bio) { + ret = submit_bio_wait(WRITE, bio); + bio_put(bio); + return ret; + } return 0; } -- cgit v1.3-8-gc7d7