From b8179958327a1f513efca095ba782a1986c7c4fb Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 12 Feb 2015 15:00:31 -0800 Subject: zram: clean up zram_meta_alloc() A trivial cleanup of zram_meta_alloc() error handling. Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index bd8bda386e02..369fe5642799 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -318,31 +318,29 @@ static struct zram_meta *zram_meta_alloc(u64 disksize) { size_t num_pages; struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL); + if (!meta) - goto out; + return NULL; num_pages = disksize >> PAGE_SHIFT; meta->table = vzalloc(num_pages * sizeof(*meta->table)); if (!meta->table) { pr_err("Error allocating zram address table\n"); - goto free_meta; + goto out_error; } meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM); if (!meta->mem_pool) { pr_err("Error creating memory pool\n"); - goto free_table; + goto out_error; } return meta; -free_table: +out_error: vfree(meta->table); -free_meta: kfree(meta); - meta = NULL; -out: - return meta; + return NULL; } static void update_position(u32 *index, int *offset, struct bio_vec *bvec) -- cgit v1.2.3 From 1fec117281d9f5349c35279c9521f4096fa33357 Mon Sep 17 00:00:00 2001 From: Ganesh Mahendran Date: Thu, 12 Feb 2015 15:00:33 -0800 Subject: zram: free meta table in zram_meta_free zram_meta_alloc() and zram_meta_free() are a pair. In zram_meta_alloc(), meta table is allocated. So it it better to free it in zram_meta_free(). Signed-off-by: Ganesh Mahendran Acked-by: Minchan Kim Acked-by: Sergey Senozhatsky Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 369fe5642799..0e07652cf7c1 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -307,8 +307,21 @@ static inline int valid_io_request(struct zram *zram, return 1; } -static void zram_meta_free(struct zram_meta *meta) +static void zram_meta_free(struct zram_meta *meta, u64 disksize) { + size_t num_pages = disksize >> PAGE_SHIFT; + size_t index; + + /* Free all pages that are still in this zram device */ + for (index = 0; index < num_pages; index++) { + unsigned long handle = meta->table[index].handle; + + if (!handle) + continue; + + zs_free(meta->mem_pool, handle); + } + zs_destroy_pool(meta->mem_pool); vfree(meta->table); kfree(meta); @@ -704,9 +717,6 @@ static void zram_bio_discard(struct zram *zram, u32 index, static void zram_reset_device(struct zram *zram, bool reset_capacity) { - size_t index; - struct zram_meta *meta; - down_write(&zram->init_lock); zram->limit_pages = 0; @@ -716,20 +726,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) return; } - meta = zram->meta; - /* Free all pages that are still in this zram device */ - for (index = 0; index < zram->disksize >> PAGE_SHIFT; index++) { - unsigned long handle = meta->table[index].handle; - if (!handle) - continue; - - zs_free(meta->mem_pool, handle); - } - zcomp_destroy(zram->comp); zram->max_comp_streams = 1; - - zram_meta_free(zram->meta); + zram_meta_free(zram->meta, zram->disksize); zram->meta = NULL; /* Reset stats */ memset(&zram->stats, 0, sizeof(zram->stats)); @@ -801,7 +800,7 @@ out_destroy_comp: up_write(&zram->init_lock); zcomp_destroy(comp); out_free_meta: - zram_meta_free(meta); + zram_meta_free(meta, disksize); return err; } -- cgit v1.2.3 From ba6b17d68c8e3aa8d55d0474299cb931965c5ea5 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 12 Feb 2015 15:00:36 -0800 Subject: zram: fix umount-reset_store-mount race condition Ganesh Mahendran was the first one who proposed to use bdev->bd_mutex to avoid ->bd_holders race condition: CPU0 CPU1 umount /* zram->init_done is true */ reset_store() bdev->bd_holders == 0 mount ... zram_make_request() zram_reset_device() However, his solution required some considerable amount of code movement, which we can avoid. Apart from using bdev->bd_mutex in reset_store(), this patch also simplifies zram_reset_device(). zram_reset_device() has a bool parameter reset_capacity which tells it whether disk capacity and itself disk should be reset. There are two zram_reset_device() callers: -- zram_exit() passes reset_capacity=false -- reset_store() passes reset_capacity=true So we can move reset_capacity-sensitive work out of zram_reset_device() and perform it unconditionally in reset_store(). This also lets us drop reset_capacity parameter from zram_reset_device() and pass zram pointer only. Signed-off-by: Sergey Senozhatsky Reported-by: Ganesh Mahendran Cc: Minchan Kim Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 23 +++++++++-------------- 1 file changed, 9 insertions(+), 14 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 0e07652cf7c1..2607bd9f4955 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -715,7 +715,7 @@ static void zram_bio_discard(struct zram *zram, u32 index, } } -static void zram_reset_device(struct zram *zram, bool reset_capacity) +static void zram_reset_device(struct zram *zram) { down_write(&zram->init_lock); @@ -734,18 +734,7 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) memset(&zram->stats, 0, sizeof(zram->stats)); zram->disksize = 0; - if (reset_capacity) - set_capacity(zram->disk, 0); - up_write(&zram->init_lock); - - /* - * Revalidate disk out of the init_lock to avoid lockdep splat. - * It's okay because disk's capacity is protected by init_lock - * so that revalidate_disk always sees up-to-date capacity. - */ - if (reset_capacity) - revalidate_disk(zram->disk); } static ssize_t disksize_store(struct device *dev, @@ -818,6 +807,7 @@ static ssize_t reset_store(struct device *dev, if (!bdev) return -ENOMEM; + mutex_lock(&bdev->bd_mutex); /* Do not reset an active device! */ if (bdev->bd_holders) { ret = -EBUSY; @@ -835,12 +825,17 @@ static ssize_t reset_store(struct device *dev, /* Make sure all pending I/O is finished */ fsync_bdev(bdev); + zram_reset_device(zram); + set_capacity(zram->disk, 0); + + mutex_unlock(&bdev->bd_mutex); + revalidate_disk(zram->disk); bdput(bdev); - zram_reset_device(zram, true); return len; out: + mutex_unlock(&bdev->bd_mutex); bdput(bdev); return ret; } @@ -1186,7 +1181,7 @@ static void __exit zram_exit(void) * Shouldn't access zram->disk after destroy_device * because destroy_device already released zram->disk. */ - zram_reset_device(zram, false); + zram_reset_device(zram); } unregister_blkdev(zram_major, "zram"); -- cgit v1.2.3 From a096cafc31862c54da0b56c8441dc14023437008 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 12 Feb 2015 15:00:39 -0800 Subject: zram: rework reset and destroy path We need to return set_capacity(disk, 0) from reset_store() back to zram_reset_device(), a catch by Ganesh Mahendran. Potentially, we can race set_capacity() calls from init and reset paths. The problem is that zram_reset_device() is also getting called from zram_exit(), which performs operations in misleading reversed order -- we first create_device() and then init it, while zram_exit() perform destroy_device() first and then does zram_reset_device(). This is done to remove sysfs group before we reset device, so we can continue with device reset/destruction not being raced by sysfs attr write (f.e. disksize). Apart from that, destroy_device() releases zram->disk (but we still have ->disk pointer), so we cannot acces zram->disk in later zram_reset_device() call, which may cause additional errors in the future. So, this patch rework and cleanup destroy path. 1) remove several unneeded goto labels in zram_init() 2) factor out zram_init() error path and zram_exit() into destroy_devices() function, which takes the number of devices to destroy as its argument. 3) remove sysfs group in destroy_devices() first, so we can reorder operations -- reset device (as expected) goes before disk destroy and queue cleanup. So we can always access ->disk in zram_reset_device(). 4) and, finally, return set_capacity() back under ->init_lock. [akpm@linux-foundation.org: tweak comment] Signed-off-by: Sergey Senozhatsky Reported-by: Ganesh Mahendran Cc: Minchan Kim Cc: Jerome Marchand Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 75 +++++++++++++++++++------------------------ 1 file changed, 33 insertions(+), 42 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2607bd9f4955..81ac8fd53340 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -732,8 +732,9 @@ static void zram_reset_device(struct zram *zram) zram->meta = NULL; /* Reset stats */ memset(&zram->stats, 0, sizeof(zram->stats)); - zram->disksize = 0; + set_capacity(zram->disk, 0); + up_write(&zram->init_lock); } @@ -826,7 +827,6 @@ static ssize_t reset_store(struct device *dev, /* Make sure all pending I/O is finished */ fsync_bdev(bdev); zram_reset_device(zram); - set_capacity(zram->disk, 0); mutex_unlock(&bdev->bd_mutex); revalidate_disk(zram->disk); @@ -1112,15 +1112,31 @@ out: return ret; } -static void destroy_device(struct zram *zram) +static void destroy_devices(unsigned int nr) { - sysfs_remove_group(&disk_to_dev(zram->disk)->kobj, - &zram_disk_attr_group); + struct zram *zram; + unsigned int i; - del_gendisk(zram->disk); - put_disk(zram->disk); + for (i = 0; i < nr; i++) { + zram = &zram_devices[i]; + /* + * Remove sysfs first, so no one will perform a disksize + * store while we destroy the devices + */ + sysfs_remove_group(&disk_to_dev(zram->disk)->kobj, + &zram_disk_attr_group); - blk_cleanup_queue(zram->queue); + zram_reset_device(zram); + + del_gendisk(zram->disk); + put_disk(zram->disk); + + blk_cleanup_queue(zram->queue); + } + + kfree(zram_devices); + unregister_blkdev(zram_major, "zram"); + pr_info("Destroyed %u device(s)\n", nr); } static int __init zram_init(void) @@ -1130,64 +1146,39 @@ static int __init zram_init(void) if (num_devices > max_num_devices) { pr_warn("Invalid value for num_devices: %u\n", num_devices); - ret = -EINVAL; - goto out; + return -EINVAL; } zram_major = register_blkdev(0, "zram"); if (zram_major <= 0) { pr_warn("Unable to get major number\n"); - ret = -EBUSY; - goto out; + return -EBUSY; } /* Allocate the device array and initialize each one */ zram_devices = kzalloc(num_devices * sizeof(struct zram), GFP_KERNEL); if (!zram_devices) { - ret = -ENOMEM; - goto unregister; + unregister_blkdev(zram_major, "zram"); + return -ENOMEM; } for (dev_id = 0; dev_id < num_devices; dev_id++) { ret = create_device(&zram_devices[dev_id], dev_id); if (ret) - goto free_devices; + goto out_error; } - pr_info("Created %u device(s) ...\n", num_devices); - + pr_info("Created %u device(s)\n", num_devices); return 0; -free_devices: - while (dev_id) - destroy_device(&zram_devices[--dev_id]); - kfree(zram_devices); -unregister: - unregister_blkdev(zram_major, "zram"); -out: +out_error: + destroy_devices(dev_id); return ret; } static void __exit zram_exit(void) { - int i; - struct zram *zram; - - for (i = 0; i < num_devices; i++) { - zram = &zram_devices[i]; - - destroy_device(zram); - /* - * Shouldn't access zram->disk after destroy_device - * because destroy_device already released zram->disk. - */ - zram_reset_device(zram); - } - - unregister_blkdev(zram_major, "zram"); - - kfree(zram_devices); - pr_debug("Cleanup done!\n"); + destroy_devices(num_devices); } module_init(zram_init); -- cgit v1.2.3 From 2b269ce6fcbfafc6cae37254cab4bf2309bfed0e Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 12 Feb 2015 15:00:42 -0800 Subject: zram: check bd_openers instead of bd_holders bd_holders is increased only when user open the device file as FMODE_EXCL so if something opens zram0 as !FMODE_EXCL and request I/O while another user reset zram0, we can see following warning. zram0: detected capacity change from 0 to 64424509440 Buffer I/O error on dev zram0, logical block 180823, lost async page write Buffer I/O error on dev zram0, logical block 180824, lost async page write Buffer I/O error on dev zram0, logical block 180825, lost async page write Buffer I/O error on dev zram0, logical block 180826, lost async page write Buffer I/O error on dev zram0, logical block 180827, lost async page write Buffer I/O error on dev zram0, logical block 180828, lost async page write Buffer I/O error on dev zram0, logical block 180829, lost async page write Buffer I/O error on dev zram0, logical block 180830, lost async page write Buffer I/O error on dev zram0, logical block 180831, lost async page write Buffer I/O error on dev zram0, logical block 180832, lost async page write ------------[ cut here ]------------ WARNING: CPU: 11 PID: 1996 at fs/block_dev.c:57 __blkdev_put+0x1d7/0x210() Modules linked in: CPU: 11 PID: 1996 Comm: dd Not tainted 3.19.0-rc6-next-20150202+ #1125 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: dump_stack+0x45/0x57 warn_slowpath_common+0x8a/0xc0 warn_slowpath_null+0x1a/0x20 __blkdev_put+0x1d7/0x210 blkdev_put+0x50/0x130 blkdev_close+0x25/0x30 __fput+0xdf/0x1e0 ____fput+0xe/0x10 task_work_run+0xa7/0xe0 do_notify_resume+0x49/0x60 int_signal+0x12/0x17 ---[ end trace 274fbbc5664827d2 ]--- The warning comes from bdev_write_node in blkdev_put path. static void bdev_write_inode(struct inode *inode) { spin_lock(&inode->i_lock); while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); WARN_ON_ONCE(write_inode_now(inode, true)); <========= here. spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); } The reason is dd process encounters I/O fails due to sudden block device disappear so in filemap_check_errors in __writeback_single_inode returns -EIO. If we check bd_openers instead of bd_holders, we could address the problem. When I see the brd, it already have used it rather than bd_holders so although I'm not a expert of block layer, it seems to be better. I can make following warning with below simple script. In addition, I added msleep(2000) below set_capacity(zram->disk, 0) after applying your patch to make window huge(Kudos to Ganesh!) script: echo $((60<<30)) > /sys/block/zram0/disksize setsid dd if=/dev/zero of=/dev/zram0 & sleep 1 setsid echo 1 > /sys/block/zram0/reset Signed-off-by: Minchan Kim Acked-by: Sergey Senozhatsky Cc: Nitin Gupta Cc: Jerome Marchand Cc: Ganesh Mahendran Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 81ac8fd53340..0abcf4a31c78 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -810,7 +810,7 @@ static ssize_t reset_store(struct device *dev, mutex_lock(&bdev->bd_mutex); /* Do not reset an active device! */ - if (bdev->bd_holders) { + if (bdev->bd_openers) { ret = -EBUSY; goto out; } -- cgit v1.2.3 From 08eee69fcf6baea543a2b4d2a2fcba0e61aa3160 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 12 Feb 2015 15:00:45 -0800 Subject: zram: remove init_lock in zram_make_request Admin could reset zram during I/O operation going on so we have used zram->init_lock as read-side lock in I/O path to prevent sudden zram meta freeing. However, the init_lock is really troublesome. We can't do call zram_meta_alloc under init_lock due to lockdep splat because zram_rw_page is one of the function under reclaim path and hold it as read_lock while other places in process context hold it as write_lock. So, we have used allocation out of the lock to avoid lockdep warn but it's not good for readability and fainally, I met another lockdep splat between init_lock and cpu_hotplug from kmem_cache_destroy during working zsmalloc compaction. :( Yes, the ideal is to remove horrible init_lock of zram in rw path. This patch removes it in rw path and instead, add atomic refcount for meta lifetime management and completion to free meta in process context. It's important to free meta in process context because some of resource destruction needs mutex lock, which could be held if we releases the resource in reclaim context so it's deadlock, again. As a bonus, we could remove init_done check in rw path because zram_meta_get will do a role for it, instead. Signed-off-by: Sergey Senozhatsky Signed-off-by: Minchan Kim Cc: Nitin Gupta Cc: Jerome Marchand Cc: Ganesh Mahendran Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 76 ++++++++++++++++++++++++++++++------------- drivers/block/zram/zram_drv.h | 20 +++++++----- 2 files changed, 64 insertions(+), 32 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 0abcf4a31c78..db94572b35c4 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -53,9 +53,9 @@ static ssize_t name##_show(struct device *d, \ } \ static DEVICE_ATTR_RO(name); -static inline int init_done(struct zram *zram) +static inline bool init_done(struct zram *zram) { - return zram->meta != NULL; + return zram->disksize; } static inline struct zram *dev_to_zram(struct device *dev) @@ -356,6 +356,18 @@ out_error: return NULL; } +static inline bool zram_meta_get(struct zram *zram) +{ + if (atomic_inc_not_zero(&zram->refcount)) + return true; + return false; +} + +static inline void zram_meta_put(struct zram *zram) +{ + atomic_dec(&zram->refcount); +} + static void update_position(u32 *index, int *offset, struct bio_vec *bvec) { if (*offset + bvec->bv_len >= PAGE_SIZE) @@ -717,6 +729,10 @@ static void zram_bio_discard(struct zram *zram, u32 index, static void zram_reset_device(struct zram *zram) { + struct zram_meta *meta; + struct zcomp *comp; + u64 disksize; + down_write(&zram->init_lock); zram->limit_pages = 0; @@ -726,16 +742,31 @@ static void zram_reset_device(struct zram *zram) return; } - zcomp_destroy(zram->comp); - zram->max_comp_streams = 1; - zram_meta_free(zram->meta, zram->disksize); - zram->meta = NULL; + meta = zram->meta; + comp = zram->comp; + disksize = zram->disksize; + /* + * Refcount will go down to 0 eventually and r/w handler + * cannot handle further I/O so it will bail out by + * check zram_meta_get. + */ + zram_meta_put(zram); + /* + * We want to free zram_meta in process context to avoid + * deadlock between reclaim path and any other locks. + */ + wait_event(zram->io_done, atomic_read(&zram->refcount) == 0); + /* Reset stats */ memset(&zram->stats, 0, sizeof(zram->stats)); zram->disksize = 0; + zram->max_comp_streams = 1; set_capacity(zram->disk, 0); up_write(&zram->init_lock); + /* I/O operation under all of CPU are done so let's free */ + zram_meta_free(meta, disksize); + zcomp_destroy(comp); } static ssize_t disksize_store(struct device *dev, @@ -771,6 +802,8 @@ static ssize_t disksize_store(struct device *dev, goto out_destroy_comp; } + init_waitqueue_head(&zram->io_done); + atomic_set(&zram->refcount, 1); zram->meta = meta; zram->comp = comp; zram->disksize = disksize; @@ -901,23 +934,21 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio) { struct zram *zram = queue->queuedata; - down_read(&zram->init_lock); - if (unlikely(!init_done(zram))) + if (unlikely(!zram_meta_get(zram))) goto error; if (!valid_io_request(zram, bio->bi_iter.bi_sector, bio->bi_iter.bi_size)) { atomic64_inc(&zram->stats.invalid_io); - goto error; + goto put_zram; } __zram_make_request(zram, bio); - up_read(&zram->init_lock); - + zram_meta_put(zram); return; - +put_zram: + zram_meta_put(zram); error: - up_read(&zram->init_lock); bio_io_error(bio); } @@ -939,21 +970,19 @@ static void zram_slot_free_notify(struct block_device *bdev, static int zram_rw_page(struct block_device *bdev, sector_t sector, struct page *page, int rw) { - int offset, err; + int offset, err = -EIO; u32 index; struct zram *zram; struct bio_vec bv; zram = bdev->bd_disk->private_data; + if (unlikely(!zram_meta_get(zram))) + goto out; + if (!valid_io_request(zram, sector, PAGE_SIZE)) { atomic64_inc(&zram->stats.invalid_io); - return -EINVAL; - } - - down_read(&zram->init_lock); - if (unlikely(!init_done(zram))) { - err = -EIO; - goto out_unlock; + err = -EINVAL; + goto put_zram; } index = sector >> SECTORS_PER_PAGE_SHIFT; @@ -964,8 +993,9 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector, bv.bv_offset = 0; err = zram_bvec_rw(zram, &bv, index, offset, rw); -out_unlock: - up_read(&zram->init_lock); +put_zram: + zram_meta_put(zram); +out: /* * If I/O fails, just return error(ie, non-zero) without * calling page_endio. diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index b05a816b09ac..5249f51ccdb3 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -100,24 +100,26 @@ struct zram_meta { struct zram { struct zram_meta *meta; + struct zcomp *comp; struct request_queue *queue; struct gendisk *disk; - struct zcomp *comp; - - /* Prevent concurrent execution of device init, reset and R/W request */ + /* Prevent concurrent execution of device init */ struct rw_semaphore init_lock; /* - * This is the limit on amount of *uncompressed* worth of data - * we can store in a disk. + * the number of pages zram can consume for storing compressed data */ - u64 disksize; /* bytes */ + unsigned long limit_pages; int max_comp_streams; + struct zram_stats stats; + atomic_t refcount; /* refcount for zram_meta */ + /* wait all IO under all of cpu are done */ + wait_queue_head_t io_done; /* - * the number of pages zram can consume for storing compressed data + * This is the limit on amount of *uncompressed* worth of data + * we can store in a disk. */ - unsigned long limit_pages; - + u64 disksize; /* bytes */ char compressor[10]; }; #endif -- cgit v1.2.3 From ee98016010ae036a5b27300d83bd99ef3fd5776e Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 12 Feb 2015 15:00:48 -0800 Subject: zram: remove request_queue from struct zram `struct zram' contains both `struct gendisk' and `struct request_queue'. the latter can be deleted, because zram->disk carries ->queue pointer, and ->queue carries zram pointer: create_device() zram->queue->queuedata = zram zram->disk->queue = zram->queue zram->disk->private_data = zram so zram->queue is not needed, we can access all necessary data anyway. Signed-off-by: Sergey Senozhatsky Cc: Minchan Kim Cc: Jerome Marchand Cc: Nitin Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 16 ++++++++-------- drivers/block/zram/zram_drv.h | 1 - 2 files changed, 8 insertions(+), 9 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index db94572b35c4..eca4b67274c1 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -1061,19 +1061,19 @@ static struct attribute_group zram_disk_attr_group = { static int create_device(struct zram *zram, int device_id) { + struct request_queue *queue; int ret = -ENOMEM; init_rwsem(&zram->init_lock); - zram->queue = blk_alloc_queue(GFP_KERNEL); - if (!zram->queue) { + queue = blk_alloc_queue(GFP_KERNEL); + if (!queue) { pr_err("Error allocating disk queue for device %d\n", device_id); goto out; } - blk_queue_make_request(zram->queue, zram_make_request); - zram->queue->queuedata = zram; + blk_queue_make_request(queue, zram_make_request); /* gendisk structure */ zram->disk = alloc_disk(1); @@ -1086,7 +1086,8 @@ static int create_device(struct zram *zram, int device_id) zram->disk->major = zram_major; zram->disk->first_minor = device_id; zram->disk->fops = &zram_devops; - zram->disk->queue = zram->queue; + zram->disk->queue = queue; + zram->disk->queue->queuedata = zram; zram->disk->private_data = zram; snprintf(zram->disk->disk_name, 16, "zram%d", device_id); @@ -1137,7 +1138,7 @@ out_free_disk: del_gendisk(zram->disk); put_disk(zram->disk); out_free_queue: - blk_cleanup_queue(zram->queue); + blk_cleanup_queue(queue); out: return ret; } @@ -1158,10 +1159,9 @@ static void destroy_devices(unsigned int nr) zram_reset_device(zram); + blk_cleanup_queue(zram->disk->queue); del_gendisk(zram->disk); put_disk(zram->disk); - - blk_cleanup_queue(zram->queue); } kfree(zram_devices); diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 5249f51ccdb3..17056e589146 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -101,7 +101,6 @@ struct zram_meta { struct zram { struct zram_meta *meta; struct zcomp *comp; - struct request_queue *queue; struct gendisk *disk; /* Prevent concurrent execution of device init */ struct rw_semaphore init_lock; -- cgit v1.2.3 From 3eba0c6a56c04f2b017b43641a821f1ebfb7fb4c Mon Sep 17 00:00:00 2001 From: Ganesh Mahendran Date: Thu, 12 Feb 2015 15:00:51 -0800 Subject: mm/zpool: add name argument to create zpool Currently the underlay of zpool: zsmalloc/zbud, do not know who creates them. There is not a method to let zsmalloc/zbud find which caller they belong to. Now we want to add statistics collection in zsmalloc. We need to name the debugfs dir for each pool created. The way suggested by Minchan Kim is to use a name passed by caller(such as zram) to create the zsmalloc pool. /sys/kernel/debug/zsmalloc/zram0 This patch adds an argument `name' to zs_create_pool() and other related functions. Signed-off-by: Ganesh Mahendran Acked-by: Minchan Kim Cc: Seth Jennings Cc: Nitin Gupta Cc: Dan Streetman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 8 +++++--- include/linux/zpool.h | 5 +++-- include/linux/zsmalloc.h | 2 +- mm/zbud.c | 3 ++- mm/zpool.c | 6 ++++-- mm/zsmalloc.c | 6 +++--- mm/zswap.c | 5 +++-- 7 files changed, 21 insertions(+), 14 deletions(-) (limited to 'drivers/block') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index eca4b67274c1..8e233edd7a09 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -327,9 +327,10 @@ static void zram_meta_free(struct zram_meta *meta, u64 disksize) kfree(meta); } -static struct zram_meta *zram_meta_alloc(u64 disksize) +static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize) { size_t num_pages; + char pool_name[8]; struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL); if (!meta) @@ -342,7 +343,8 @@ static struct zram_meta *zram_meta_alloc(u64 disksize) goto out_error; } - meta->mem_pool = zs_create_pool(GFP_NOIO | __GFP_HIGHMEM); + snprintf(pool_name, sizeof(pool_name), "zram%d", device_id); + meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM); if (!meta->mem_pool) { pr_err("Error creating memory pool\n"); goto out_error; @@ -783,7 +785,7 @@ static ssize_t disksize_store(struct device *dev, return -EINVAL; disksize = PAGE_ALIGN(disksize); - meta = zram_meta_alloc(disksize); + meta = zram_meta_alloc(zram->disk->first_minor, disksize); if (!meta) return -ENOMEM; diff --git a/include/linux/zpool.h b/include/linux/zpool.h index f14bd75f08b3..56529b34dc63 100644 --- a/include/linux/zpool.h +++ b/include/linux/zpool.h @@ -36,7 +36,8 @@ enum zpool_mapmode { ZPOOL_MM_DEFAULT = ZPOOL_MM_RW }; -struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops); +struct zpool *zpool_create_pool(char *type, char *name, + gfp_t gfp, struct zpool_ops *ops); char *zpool_get_type(struct zpool *pool); @@ -80,7 +81,7 @@ struct zpool_driver { atomic_t refcount; struct list_head list; - void *(*create)(gfp_t gfp, struct zpool_ops *ops); + void *(*create)(char *name, gfp_t gfp, struct zpool_ops *ops); void (*destroy)(void *pool); int (*malloc)(void *pool, size_t size, gfp_t gfp, diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h index 05c214760977..3283c6a55425 100644 --- a/include/linux/zsmalloc.h +++ b/include/linux/zsmalloc.h @@ -36,7 +36,7 @@ enum zs_mapmode { struct zs_pool; -struct zs_pool *zs_create_pool(gfp_t flags); +struct zs_pool *zs_create_pool(char *name, gfp_t flags); void zs_destroy_pool(struct zs_pool *pool); unsigned long zs_malloc(struct zs_pool *pool, size_t size); diff --git a/mm/zbud.c b/mm/zbud.c index 4e387bea702e..2ee4e4520493 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -130,7 +130,8 @@ static struct zbud_ops zbud_zpool_ops = { .evict = zbud_zpool_evict }; -static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zbud_zpool_create(char *name, gfp_t gfp, + struct zpool_ops *zpool_ops) { return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); } diff --git a/mm/zpool.c b/mm/zpool.c index 739cdf0d183a..bacdab6e47de 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -129,6 +129,7 @@ static void zpool_put_driver(struct zpool_driver *driver) /** * zpool_create_pool() - Create a new zpool * @type The type of the zpool to create (e.g. zbud, zsmalloc) + * @name The name of the zpool (e.g. zram0, zswap) * @gfp The GFP flags to use when allocating the pool. * @ops The optional ops callback. * @@ -140,7 +141,8 @@ static void zpool_put_driver(struct zpool_driver *driver) * * Returns: New zpool on success, NULL on failure. */ -struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops) +struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, + struct zpool_ops *ops) { struct zpool_driver *driver; struct zpool *zpool; @@ -168,7 +170,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops) zpool->type = driver->type; zpool->driver = driver; - zpool->pool = driver->create(gfp, ops); + zpool->pool = driver->create(name, gfp, ops); zpool->ops = ops; if (!zpool->pool) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b72403927aa4..2359e61b02bf 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -246,9 +246,9 @@ struct mapping_area { #ifdef CONFIG_ZPOOL -static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops) { - return zs_create_pool(gfp); + return zs_create_pool(name, gfp); } static void zs_zpool_destroy(void *pool) @@ -1148,7 +1148,7 @@ EXPORT_SYMBOL_GPL(zs_free); * On success, a pointer to the newly created pool is returned, * otherwise NULL. */ -struct zs_pool *zs_create_pool(gfp_t flags) +struct zs_pool *zs_create_pool(char *name, gfp_t flags) { int i; struct zs_pool *pool; diff --git a/mm/zswap.c b/mm/zswap.c index 0cfce9bc51e4..4249e82ff934 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -906,11 +906,12 @@ static int __init init_zswap(void) pr_info("loading zswap\n"); - zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, &zswap_zpool_ops); + zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, + &zswap_zpool_ops); if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) { pr_info("%s zpool not available\n", zswap_zpool_type); zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT; - zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, + zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, &zswap_zpool_ops); } if (!zswap_pool) { -- cgit v1.2.3 From 02f1f2170d2831b3233e91091c60a66622f29e82 Mon Sep 17 00:00:00 2001 From: Rasmus Villemoes Date: Thu, 12 Feb 2015 15:01:31 -0800 Subject: kernel.h: remove ancient __FUNCTION__ hack __FUNCTION__ hasn't been treated as a string literal since gcc 3.4, so this only helps people who only test-compile using 3.3 (compiler-gcc3.h barks at anything older than that). Besides, there are almost no occurrences of __FUNCTION__ left in the tree. [akpm@linux-foundation.org: convert remaining __FUNCTION__ references] Signed-off-by: Rasmus Villemoes Cc: Michal Nazarewicz Cc: Joe Perches Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/kernel/hpet.c | 2 +- arch/x86/kernel/rtc.c | 4 ++-- arch/x86/platform/intel-mid/intel_mid_vrtc.c | 2 +- drivers/acpi/acpica/utdebug.c | 4 ++-- drivers/block/xen-blkfront.c | 2 +- include/acpi/acoutput.h | 6 +++--- include/linux/kernel.h | 3 --- 7 files changed, 10 insertions(+), 13 deletions(-) (limited to 'drivers/block') diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 319bcb9372fe..3acbff4716b0 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -168,7 +168,7 @@ static void _hpet_print_config(const char *function, int line) #define hpet_print_config() \ do { \ if (hpet_verbose) \ - _hpet_print_config(__FUNCTION__, __LINE__); \ + _hpet_print_config(__func__, __LINE__); \ } while (0) /* diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index fe3dbfe0c4a5..cd9685235df9 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -49,11 +49,11 @@ int mach_set_rtc_mmss(const struct timespec *now) retval = set_rtc_time(&tm); if (retval) printk(KERN_ERR "%s: RTC write failed with error %d\n", - __FUNCTION__, retval); + __func__, retval); } else { printk(KERN_ERR "%s: Invalid RTC value: write of %lx to RTC failed\n", - __FUNCTION__, nowtime); + __func__, nowtime); retval = -EINVAL; } return retval; diff --git a/arch/x86/platform/intel-mid/intel_mid_vrtc.c b/arch/x86/platform/intel-mid/intel_mid_vrtc.c index 4762cff7facd..32947ba0f62d 100644 --- a/arch/x86/platform/intel-mid/intel_mid_vrtc.c +++ b/arch/x86/platform/intel-mid/intel_mid_vrtc.c @@ -110,7 +110,7 @@ int vrtc_set_mmss(const struct timespec *now) spin_unlock_irqrestore(&rtc_lock, flags); } else { pr_err("%s: Invalid vRTC value: write of %lx to vRTC failed\n", - __FUNCTION__, now->tv_sec); + __func__, now->tv_sec); retval = -EINVAL; } return retval; diff --git a/drivers/acpi/acpica/utdebug.c b/drivers/acpi/acpica/utdebug.c index 57078e3ea9b7..4f3f888d33bb 100644 --- a/drivers/acpi/acpica/utdebug.c +++ b/drivers/acpi/acpica/utdebug.c @@ -111,8 +111,8 @@ void acpi_ut_track_stack_ptr(void) * RETURN: Updated pointer to the function name * * DESCRIPTION: Remove the "Acpi" prefix from the function name, if present. - * This allows compiler macros such as __FUNCTION__ to be used - * with no change to the debug output. + * This allows compiler macros such as __func__ to be used with no + * change to the debug output. * ******************************************************************************/ diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 2236c6f31608..d2cae5fc211a 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -1391,7 +1391,7 @@ static int blkfront_probe(struct xenbus_device *dev, if (major != XENVBD_MAJOR) { printk(KERN_INFO "%s: HVM does not support vbd %d as xen block device\n", - __FUNCTION__, vdevice); + __func__, vdevice); return -ENODEV; } } diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h index 9318a87ee39a..a8f344363e77 100644 --- a/include/acpi/acoutput.h +++ b/include/acpi/acoutput.h @@ -240,7 +240,7 @@ /* * If ACPI_GET_FUNCTION_NAME was not defined in the compiler-dependent header, * define it now. This is the case where there the compiler does not support - * a __FUNCTION__ macro or equivalent. + * a __func__ macro or equivalent. */ #ifndef ACPI_GET_FUNCTION_NAME #define ACPI_GET_FUNCTION_NAME _acpi_function_name @@ -249,12 +249,12 @@ * The Name parameter should be the procedure name as a quoted string. * The function name is also used by the function exit macros below. * Note: (const char) is used to be compatible with the debug interfaces - * and macros such as __FUNCTION__. + * and macros such as __func__. */ #define ACPI_FUNCTION_NAME(name) static const char _acpi_function_name[] = #name; #else -/* Compiler supports __FUNCTION__ (or equivalent) -- Ignore this macro */ +/* Compiler supports __func__ (or equivalent) -- Ignore this macro */ #define ACPI_FUNCTION_NAME(name) #endif /* ACPI_GET_FUNCTION_NAME */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index e42e7dc34c68..d6d630d31ef3 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -800,9 +800,6 @@ static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { } const typeof( ((type *)0)->member ) *__mptr = (ptr); \ (type *)( (char *)__mptr - offsetof(type,member) );}) -/* Trap pasters of __FUNCTION__ at compile-time */ -#define __FUNCTION__ (__func__) - /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */ #ifdef CONFIG_FTRACE_MCOUNT_RECORD # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD -- cgit v1.2.3