summaryrefslogtreecommitdiff
path: root/drivers/block
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/block')
-rw-r--r--drivers/block/Kconfig11
-rw-r--r--drivers/block/Makefile1
-rw-r--r--drivers/block/drbd/drbd_debugfs.c8
-rw-r--r--drivers/block/pmem.c262
-rw-r--r--drivers/block/rbd.c31
-rw-r--r--drivers/block/xen-blkback/blkback.c35
-rw-r--r--drivers/block/zram/zram_drv.c23
7 files changed, 337 insertions, 34 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1b8094d4d7af..eb1fed5bd516 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -404,6 +404,17 @@ config BLK_DEV_RAM_DAX
and will prevent RAM block device backing store memory from being
allocated from highmem (only a problem for highmem systems).
+config BLK_DEV_PMEM
+ tristate "Persistent memory block device support"
+ help
+ Saying Y here will allow you to use a contiguous range of reserved
+ memory as one or more persistent block devices.
+
+ To compile this driver as a module, choose M here: the module will be
+ called 'pmem'.
+
+ If unsure, say N.
+
config CDROM_PKTCDVD
tristate "Packet writing on CD/DVD media"
depends on !UML
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d1438d..9cc6c18a1c7e 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -14,6 +14,7 @@ obj-$(CONFIG_PS3_VRAM) += ps3vram.o
obj-$(CONFIG_ATARI_FLOPPY) += ataflop.o
obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o
obj-$(CONFIG_BLK_DEV_RAM) += brd.o
+obj-$(CONFIG_BLK_DEV_PMEM) += pmem.o
obj-$(CONFIG_BLK_DEV_LOOP) += loop.o
obj-$(CONFIG_BLK_CPQ_DA) += cpqarray.o
obj-$(CONFIG_BLK_CPQ_CISS_DA) += cciss.o
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index 9a950022ff88..a6ee3d750c30 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -424,7 +424,7 @@ static int in_flight_summary_show(struct seq_file *m, void *pos)
* So we have our own inline version of it above. :-( */
static inline int debugfs_positive(struct dentry *dentry)
{
- return dentry->d_inode && !d_unhashed(dentry);
+ return d_really_is_positive(dentry) && !d_unhashed(dentry);
}
/* make sure at *open* time that the respective object won't go away. */
@@ -439,15 +439,15 @@ static int drbd_single_open(struct file *file, int (*show)(struct seq_file *, vo
* or has debugfs_remove() already been called? */
parent = file->f_path.dentry->d_parent;
/* not sure if this can happen: */
- if (!parent || !parent->d_inode)
+ if (!parent || d_really_is_negative(parent))
goto out;
/* serialize with d_delete() */
- mutex_lock(&parent->d_inode->i_mutex);
+ mutex_lock(&d_inode(parent)->i_mutex);
/* Make sure the object is still alive */
if (debugfs_positive(file->f_path.dentry)
&& kref_get_unless_zero(kref))
ret = 0;
- mutex_unlock(&parent->d_inode->i_mutex);
+ mutex_unlock(&d_inode(parent)->i_mutex);
if (!ret) {
ret = single_open(file, show, data);
if (ret)
diff --git a/drivers/block/pmem.c b/drivers/block/pmem.c
new file mode 100644
index 000000000000..eabf4a8d0085
--- /dev/null
+++ b/drivers/block/pmem.c
@@ -0,0 +1,262 @@
+/*
+ * Persistent Memory Driver
+ *
+ * Copyright (c) 2014, Intel Corporation.
+ * Copyright (c) 2015, Christoph Hellwig <hch@lst.de>.
+ * Copyright (c) 2015, Boaz Harrosh <boaz@plexistor.com>.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ */
+
+#include <asm/cacheflush.h>
+#include <linux/blkdev.h>
+#include <linux/hdreg.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/slab.h>
+
+#define PMEM_MINORS 16
+
+struct pmem_device {
+ struct request_queue *pmem_queue;
+ struct gendisk *pmem_disk;
+
+ /* One contiguous memory region per device */
+ phys_addr_t phys_addr;
+ void *virt_addr;
+ size_t size;
+};
+
+static int pmem_major;
+static atomic_t pmem_index;
+
+static void pmem_do_bvec(struct pmem_device *pmem, struct page *page,
+ unsigned int len, unsigned int off, int rw,
+ sector_t sector)
+{
+ void *mem = kmap_atomic(page);
+ size_t pmem_off = sector << 9;
+
+ if (rw == READ) {
+ memcpy(mem + off, pmem->virt_addr + pmem_off, len);
+ flush_dcache_page(page);
+ } else {
+ flush_dcache_page(page);
+ memcpy(pmem->virt_addr + pmem_off, mem + off, len);
+ }
+
+ kunmap_atomic(mem);
+}
+
+static void pmem_make_request(struct request_queue *q, struct bio *bio)
+{
+ struct block_device *bdev = bio->bi_bdev;
+ struct pmem_device *pmem = bdev->bd_disk->private_data;
+ int rw;
+ struct bio_vec bvec;
+ sector_t sector;
+ struct bvec_iter iter;
+ int err = 0;
+
+ if (bio_end_sector(bio) > get_capacity(bdev->bd_disk)) {
+ err = -EIO;
+ goto out;
+ }
+
+ BUG_ON(bio->bi_rw & REQ_DISCARD);
+
+ rw = bio_data_dir(bio);
+ sector = bio->bi_iter.bi_sector;
+ bio_for_each_segment(bvec, bio, iter) {
+ pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len, bvec.bv_offset,
+ rw, sector);
+ sector += bvec.bv_len >> 9;
+ }
+
+out:
+ bio_endio(bio, err);
+}
+
+static int pmem_rw_page(struct block_device *bdev, sector_t sector,
+ struct page *page, int rw)
+{
+ struct pmem_device *pmem = bdev->bd_disk->private_data;
+
+ pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
+ page_endio(page, rw & WRITE, 0);
+
+ return 0;
+}
+
+static long pmem_direct_access(struct block_device *bdev, sector_t sector,
+ void **kaddr, unsigned long *pfn, long size)
+{
+ struct pmem_device *pmem = bdev->bd_disk->private_data;
+ size_t offset = sector << 9;
+
+ if (!pmem)
+ return -ENODEV;
+
+ *kaddr = pmem->virt_addr + offset;
+ *pfn = (pmem->phys_addr + offset) >> PAGE_SHIFT;
+
+ return pmem->size - offset;
+}
+
+static const struct block_device_operations pmem_fops = {
+ .owner = THIS_MODULE,
+ .rw_page = pmem_rw_page,
+ .direct_access = pmem_direct_access,
+};
+
+static struct pmem_device *pmem_alloc(struct device *dev, struct resource *res)
+{
+ struct pmem_device *pmem;
+ struct gendisk *disk;
+ int idx, err;
+
+ err = -ENOMEM;
+ pmem = kzalloc(sizeof(*pmem), GFP_KERNEL);
+ if (!pmem)
+ goto out;
+
+ pmem->phys_addr = res->start;
+ pmem->size = resource_size(res);
+
+ err = -EINVAL;
+ if (!request_mem_region(pmem->phys_addr, pmem->size, "pmem")) {
+ dev_warn(dev, "could not reserve region [0x%pa:0x%zx]\n", &pmem->phys_addr, pmem->size);
+ goto out_free_dev;
+ }
+
+ /*
+ * Map the memory as non-cachable, as we can't write back the contents
+ * of the CPU caches in case of a crash.
+ */
+ err = -ENOMEM;
+ pmem->virt_addr = ioremap_nocache(pmem->phys_addr, pmem->size);
+ if (!pmem->virt_addr)
+ goto out_release_region;
+
+ pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
+ if (!pmem->pmem_queue)
+ goto out_unmap;
+
+ blk_queue_make_request(pmem->pmem_queue, pmem_make_request);
+ blk_queue_max_hw_sectors(pmem->pmem_queue, 1024);
+ blk_queue_bounce_limit(pmem->pmem_queue, BLK_BOUNCE_ANY);
+
+ disk = alloc_disk(PMEM_MINORS);
+ if (!disk)
+ goto out_free_queue;
+
+ idx = atomic_inc_return(&pmem_index) - 1;
+
+ disk->major = pmem_major;
+ disk->first_minor = PMEM_MINORS * idx;
+ disk->fops = &pmem_fops;
+ disk->private_data = pmem;
+ disk->queue = pmem->pmem_queue;
+ disk->flags = GENHD_FL_EXT_DEVT;
+ sprintf(disk->disk_name, "pmem%d", idx);
+ disk->driverfs_dev = dev;
+ set_capacity(disk, pmem->size >> 9);
+ pmem->pmem_disk = disk;
+
+ add_disk(disk);
+
+ return pmem;
+
+out_free_queue:
+ blk_cleanup_queue(pmem->pmem_queue);
+out_unmap:
+ iounmap(pmem->virt_addr);
+out_release_region:
+ release_mem_region(pmem->phys_addr, pmem->size);
+out_free_dev:
+ kfree(pmem);
+out:
+ return ERR_PTR(err);
+}
+
+static void pmem_free(struct pmem_device *pmem)
+{
+ del_gendisk(pmem->pmem_disk);
+ put_disk(pmem->pmem_disk);
+ blk_cleanup_queue(pmem->pmem_queue);
+ iounmap(pmem->virt_addr);
+ release_mem_region(pmem->phys_addr, pmem->size);
+ kfree(pmem);
+}
+
+static int pmem_probe(struct platform_device *pdev)
+{
+ struct pmem_device *pmem;
+ struct resource *res;
+
+ if (WARN_ON(pdev->num_resources > 1))
+ return -ENXIO;
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res)
+ return -ENXIO;
+
+ pmem = pmem_alloc(&pdev->dev, res);
+ if (IS_ERR(pmem))
+ return PTR_ERR(pmem);
+
+ platform_set_drvdata(pdev, pmem);
+
+ return 0;
+}
+
+static int pmem_remove(struct platform_device *pdev)
+{
+ struct pmem_device *pmem = platform_get_drvdata(pdev);
+
+ pmem_free(pmem);
+ return 0;
+}
+
+static struct platform_driver pmem_driver = {
+ .probe = pmem_probe,
+ .remove = pmem_remove,
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "pmem",
+ },
+};
+
+static int __init pmem_init(void)
+{
+ int error;
+
+ pmem_major = register_blkdev(0, "pmem");
+ if (pmem_major < 0)
+ return pmem_major;
+
+ error = platform_driver_register(&pmem_driver);
+ if (error)
+ unregister_blkdev(pmem_major, "pmem");
+ return error;
+}
+module_init(pmem_init);
+
+static void pmem_exit(void)
+{
+ platform_driver_unregister(&pmem_driver);
+ unregister_blkdev(pmem_major, "pmem");
+}
+module_exit(pmem_exit);
+
+MODULE_AUTHOR("Ross Zwisler <ross.zwisler@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index b40af3203089..ec6c5c6e1ac9 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -2264,6 +2264,11 @@ static bool rbd_img_obj_end_request(struct rbd_obj_request *obj_request)
result, xferred);
if (!img_request->result)
img_request->result = result;
+ /*
+ * Need to end I/O on the entire obj_request worth of
+ * bytes in case of error.
+ */
+ xferred = obj_request->length;
}
/* Image object requests don't own their page array */
@@ -3762,8 +3767,8 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
goto out_tag_set;
}
- /* We use the default size, but let's be explicit about it. */
- blk_queue_physical_block_size(q, SECTOR_SIZE);
+ queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
+ /* QUEUE_FLAG_ADD_RANDOM is off by default for blk-mq */
/* set io sizes to object size */
segment_size = rbd_obj_bytes(&rbd_dev->header);
@@ -5301,8 +5306,13 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
if (mapping) {
ret = rbd_dev_header_watch_sync(rbd_dev);
- if (ret)
+ if (ret) {
+ if (ret == -ENOENT)
+ pr_info("image %s/%s does not exist\n",
+ rbd_dev->spec->pool_name,
+ rbd_dev->spec->image_name);
goto out_header_name;
+ }
}
ret = rbd_dev_header_info(rbd_dev);
@@ -5319,8 +5329,14 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
ret = rbd_spec_fill_snap_id(rbd_dev);
else
ret = rbd_spec_fill_names(rbd_dev);
- if (ret)
+ if (ret) {
+ if (ret == -ENOENT)
+ pr_info("snap %s/%s@%s does not exist\n",
+ rbd_dev->spec->pool_name,
+ rbd_dev->spec->image_name,
+ rbd_dev->spec->snap_name);
goto err_out_probe;
+ }
if (rbd_dev->header.features & RBD_FEATURE_LAYERING) {
ret = rbd_dev_v2_parent_info(rbd_dev);
@@ -5390,8 +5406,11 @@ static ssize_t do_rbd_add(struct bus_type *bus,
/* pick the pool */
rc = rbd_add_get_pool_id(rbdc, spec->pool_name);
- if (rc < 0)
+ if (rc < 0) {
+ if (rc == -ENOENT)
+ pr_info("pool %s does not exist\n", spec->pool_name);
goto err_out_client;
+ }
spec->pool_id = (u64)rc;
/* The ceph file layout needs to fit pool id in 32 bits */
@@ -5673,7 +5692,7 @@ static int __init rbd_init(void)
/*
* The number of active work items is limited by the number of
- * rbd devices, so leave @max_active at default.
+ * rbd devices * queue depth, so leave @max_active at default.
*/
rbd_wq = alloc_workqueue(RBD_DRV_NAME, WQ_MEM_RECLAIM, 0);
if (!rbd_wq) {
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index bd2b3bbbb22c..713fc9ff1149 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -265,17 +265,6 @@ static void put_persistent_gnt(struct xen_blkif *blkif,
atomic_dec(&blkif->persistent_gnt_in_use);
}
-static void free_persistent_gnts_unmap_callback(int result,
- struct gntab_unmap_queue_data *data)
-{
- struct completion *c = data->data;
-
- /* BUG_ON used to reproduce existing behaviour,
- but is this the best way to deal with this? */
- BUG_ON(result);
- complete(c);
-}
-
static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
unsigned int num)
{
@@ -285,12 +274,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
struct rb_node *n;
int segs_to_unmap = 0;
struct gntab_unmap_queue_data unmap_data;
- struct completion unmap_completion;
- init_completion(&unmap_completion);
-
- unmap_data.data = &unmap_completion;
- unmap_data.done = &free_persistent_gnts_unmap_callback;
unmap_data.pages = pages;
unmap_data.unmap_ops = unmap;
unmap_data.kunmap_ops = NULL;
@@ -310,8 +294,7 @@ static void free_persistent_gnts(struct xen_blkif *blkif, struct rb_root *root,
!rb_next(&persistent_gnt->node)) {
unmap_data.count = segs_to_unmap;
- gnttab_unmap_refs_async(&unmap_data);
- wait_for_completion(&unmap_completion);
+ BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
put_free_pages(blkif, pages, segs_to_unmap);
segs_to_unmap = 0;
@@ -329,8 +312,13 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
struct gnttab_unmap_grant_ref unmap[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct page *pages[BLKIF_MAX_SEGMENTS_PER_REQUEST];
struct persistent_gnt *persistent_gnt;
- int ret, segs_to_unmap = 0;
+ int segs_to_unmap = 0;
struct xen_blkif *blkif = container_of(work, typeof(*blkif), persistent_purge_work);
+ struct gntab_unmap_queue_data unmap_data;
+
+ unmap_data.pages = pages;
+ unmap_data.unmap_ops = unmap;
+ unmap_data.kunmap_ops = NULL;
while(!list_empty(&blkif->persistent_purge_list)) {
persistent_gnt = list_first_entry(&blkif->persistent_purge_list,
@@ -346,17 +334,16 @@ void xen_blkbk_unmap_purged_grants(struct work_struct *work)
pages[segs_to_unmap] = persistent_gnt->page;
if (++segs_to_unmap == BLKIF_MAX_SEGMENTS_PER_REQUEST) {
- ret = gnttab_unmap_refs(unmap, NULL, pages,
- segs_to_unmap);
- BUG_ON(ret);
+ unmap_data.count = segs_to_unmap;
+ BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
put_free_pages(blkif, pages, segs_to_unmap);
segs_to_unmap = 0;
}
kfree(persistent_gnt);
}
if (segs_to_unmap > 0) {
- ret = gnttab_unmap_refs(unmap, NULL, pages, segs_to_unmap);
- BUG_ON(ret);
+ unmap_data.count = segs_to_unmap;
+ BUG_ON(gnttab_unmap_refs_sync(&unmap_data));
put_free_pages(blkif, pages, segs_to_unmap);
}
}
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index c94386aa563d..8dcbced0eafd 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -74,6 +74,27 @@ static inline struct zram *dev_to_zram(struct device *dev)
return (struct zram *)dev_to_disk(dev)->private_data;
}
+static ssize_t compact_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t len)
+{
+ unsigned long nr_migrated;
+ struct zram *zram = dev_to_zram(dev);
+ struct zram_meta *meta;
+
+ down_read(&zram->init_lock);
+ if (!init_done(zram)) {
+ up_read(&zram->init_lock);
+ return -EINVAL;
+ }
+
+ meta = zram->meta;
+ nr_migrated = zs_compact(meta->mem_pool);
+ atomic64_add(nr_migrated, &zram->stats.num_migrated);
+ up_read(&zram->init_lock);
+
+ return len;
+}
+
static ssize_t disksize_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
@@ -1038,6 +1059,7 @@ static const struct block_device_operations zram_devops = {
.owner = THIS_MODULE
};
+static DEVICE_ATTR_WO(compact);
static DEVICE_ATTR_RW(disksize);
static DEVICE_ATTR_RO(initstate);
static DEVICE_ATTR_WO(reset);
@@ -1114,6 +1136,7 @@ static struct attribute *zram_disk_attrs[] = {
&dev_attr_num_writes.attr,
&dev_attr_failed_reads.attr,
&dev_attr_failed_writes.attr,
+ &dev_attr_compact.attr,
&dev_attr_invalid_io.attr,
&dev_attr_notify_free.attr,
&dev_attr_zero_pages.attr,
View Lorry Controller Status