summaryrefslogtreecommitdiffstats
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/Makefile2
-rw-r--r--drivers/block/brd.c8
-rw-r--r--drivers/block/drbd/drbd_bitmap.c4
-rw-r--r--drivers/block/drbd/drbd_int.h2
-rw-r--r--drivers/block/drbd/drbd_receiver.c3
-rw-r--r--drivers/block/drbd/drbd_req.c3
-rw-r--r--drivers/block/loop.c274
-rw-r--r--drivers/block/loop.h13
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c2
-rw-r--r--drivers/block/nbd.c43
-rw-r--r--drivers/block/null_blk.c3
-rw-r--r--drivers/block/nvme-core.c3391
-rw-r--r--drivers/block/nvme-scsi.c2556
-rw-r--r--drivers/block/osdblk.c2
-rw-r--r--drivers/block/paride/pd.c2
-rw-r--r--drivers/block/pktcdvd.c16
-rw-r--r--drivers/block/ps3vram.c6
-rw-r--r--drivers/block/rbd.c191
-rw-r--r--drivers/block/rsxx/dev.c5
-rw-r--r--drivers/block/umem.c4
-rw-r--r--drivers/block/xen-blkback/blkback.c13
-rw-r--r--drivers/block/xen-blkback/common.h17
-rw-r--r--drivers/block/xen-blkback/xenbus.c11
-rw-r--r--drivers/block/xen-blkfront.c563
-rw-r--r--drivers/block/zram/zram_drv.c33
26 files changed, 799 insertions, 6379 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 1b8094d4d7af..29819e719afa 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -310,17 +310,6 @@ config BLK_DEV_NBD
If unsure, say N.
-config BLK_DEV_NVME
- tristate "NVM Express block device"
- depends on PCI
- ---help---
- The NVM Express driver is for solid state drives directly
- connected to the PCI or PCI Express bus. If you know you
- don't have one of these, it is safe to answer N.
-
- To compile this driver as a module, choose M here: the
- module will be called nvme.
-
config BLK_DEV_SKD
tristate "STEC S1120 Block Driver"
depends on PCI
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 02b688d1438d..671329023ec2 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -22,7 +22,6 @@ obj-$(CONFIG_XILINX_SYSACE) += xsysace.o
obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o
obj-$(CONFIG_MG_DISK) += mg_disk.o
obj-$(CONFIG_SUNVDC) += sunvdc.o
-obj-$(CONFIG_BLK_DEV_NVME) += nvme.o
obj-$(CONFIG_BLK_DEV_SKD) += skd.o
obj-$(CONFIG_BLK_DEV_OSD) += osdblk.o
@@ -44,6 +43,5 @@ obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
obj-$(CONFIG_BLK_DEV_NULL_BLK) += null_blk.o
obj-$(CONFIG_ZRAM) += zram/
-nvme-y := nvme-core.o nvme-scsi.o
skd-y := skd_main.o
swim_mod-y := swim.o swim_asm.o
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index b9794aeeb878..a5880f4ab40e 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -323,7 +323,7 @@ out:
return err;
}
-static void brd_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
{
struct block_device *bdev = bio->bi_bdev;
struct brd_device *brd = bdev->bd_disk->private_data;
@@ -337,6 +337,9 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
goto io_error;
if (unlikely(bio->bi_rw & REQ_DISCARD)) {
+ if (sector & ((PAGE_SIZE >> SECTOR_SHIFT) - 1) ||
+ bio->bi_iter.bi_size & PAGE_MASK)
+ goto io_error;
discard_from_brd(brd, sector, bio->bi_iter.bi_size);
goto out;
}
@@ -358,9 +361,10 @@ static void brd_make_request(struct request_queue *q, struct bio *bio)
out:
bio_endio(bio);
- return;
+ return BLK_QC_T_NONE;
io_error:
bio_io_error(bio);
+ return BLK_QC_T_NONE;
}
static int brd_rw_page(struct block_device *bdev, sector_t sector,
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index e5e0f19ceda0..9462d2752850 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -29,7 +29,7 @@
#include <linux/string.h>
#include <linux/drbd.h>
#include <linux/slab.h>
-#include <asm/kmap_types.h>
+#include <linux/highmem.h>
#include "drbd_int.h"
@@ -1007,7 +1007,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
bm_set_page_unchanged(b->bm_pages[page_nr]);
if (ctx->flags & BM_AIO_COPY_PAGES) {
- page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_WAIT);
+ page = mempool_alloc(drbd_md_io_page_pool, __GFP_HIGHMEM|__GFP_RECLAIM);
copy_highpage(page, b->bm_pages[page_nr]);
bm_store_page_idx(page, page_nr);
} else
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 015c6e91b756..e66d453a5f2b 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1448,7 +1448,7 @@ extern int proc_details;
/* drbd_req */
extern void do_submit(struct work_struct *ws);
extern void __drbd_make_request(struct drbd_device *, struct bio *, unsigned long);
-extern void drbd_make_request(struct request_queue *q, struct bio *bio);
+extern blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio);
extern int drbd_read_remote(struct drbd_device *device, struct drbd_request *req);
extern int is_valid_ar_handle(struct drbd_request *, sector_t);
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index c097909c589c..b4b5680ac6ad 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -357,7 +357,8 @@ drbd_alloc_peer_req(struct drbd_peer_device *peer_device, u64 id, sector_t secto
}
if (has_payload && data_size) {
- page = drbd_alloc_pages(peer_device, nr_pages, (gfp_mask & __GFP_WAIT));
+ page = drbd_alloc_pages(peer_device, nr_pages,
+ gfpflags_allow_blocking(gfp_mask));
if (!page)
goto fail;
}
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 211592682169..3ae2c0086563 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -1494,7 +1494,7 @@ void do_submit(struct work_struct *ws)
}
}
-void drbd_make_request(struct request_queue *q, struct bio *bio)
+blk_qc_t drbd_make_request(struct request_queue *q, struct bio *bio)
{
struct drbd_device *device = (struct drbd_device *) q->queuedata;
unsigned long start_jif;
@@ -1510,6 +1510,7 @@ void drbd_make_request(struct request_queue *q, struct bio *bio)
inc_ap_bio(device);
__drbd_make_request(device, bio, start_jif);
+ return BLK_QC_T_NONE;
}
void request_timer_fn(unsigned long data)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 674f800a3b57..423f4ca7d712 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -164,6 +164,62 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file)
return get_size(lo->lo_offset, lo->lo_sizelimit, file);
}
+static void __loop_update_dio(struct loop_device *lo, bool dio)
+{
+ struct file *file = lo->lo_backing_file;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ unsigned short sb_bsize = 0;
+ unsigned dio_align = 0;
+ bool use_dio;
+
+ if (inode->i_sb->s_bdev) {
+ sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
+ dio_align = sb_bsize - 1;
+ }
+
+ /*
+ * We support direct I/O only if lo_offset is aligned with the
+ * logical I/O size of backing device, and the logical block
+ * size of loop is bigger than the backing device's and the loop
+ * needn't transform transfer.
+ *
+ * TODO: the above condition may be loosed in the future, and
+ * direct I/O may be switched runtime at that time because most
+ * of requests in sane appplications should be PAGE_SIZE algined
+ */
+ if (dio) {
+ if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
+ !(lo->lo_offset & dio_align) &&
+ mapping->a_ops->direct_IO &&
+ !lo->transfer)
+ use_dio = true;
+ else
+ use_dio = false;
+ } else {
+ use_dio = false;
+ }
+
+ if (lo->use_dio == use_dio)
+ return;
+
+ /* flush dirty pages before changing direct IO */
+ vfs_fsync(file, 0);
+
+ /*
+ * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
+ * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
+ * will get updated by ioctl(LOOP_GET_STATUS)
+ */
+ blk_mq_freeze_queue(lo->lo_queue);
+ lo->use_dio = use_dio;
+ if (use_dio)
+ lo->lo_flags |= LO_FLAGS_DIRECT_IO;
+ else
+ lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
+ blk_mq_unfreeze_queue(lo->lo_queue);
+}
+
static int
figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
{
@@ -389,6 +445,89 @@ static int lo_req_flush(struct loop_device *lo, struct request *rq)
return ret;
}
+static inline void handle_partial_read(struct loop_cmd *cmd, long bytes)
+{
+ if (bytes < 0 || (cmd->rq->cmd_flags & REQ_WRITE))
+ return;
+
+ if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+ struct bio *bio = cmd->rq->bio;
+
+ bio_advance(bio, bytes);
+ zero_fill_bio(bio);
+ }
+}
+
+static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
+{
+ struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);
+ struct request *rq = cmd->rq;
+
+ handle_partial_read(cmd, ret);
+
+ if (ret > 0)
+ ret = 0;
+ else if (ret < 0)
+ ret = -EIO;
+
+ blk_mq_complete_request(rq, ret);
+}
+
+static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
+ loff_t pos, bool rw)
+{
+ struct iov_iter iter;
+ struct bio_vec *bvec;
+ struct bio *bio = cmd->rq->bio;
+ struct file *file = lo->lo_backing_file;
+ int ret;
+
+ /* nomerge for loop request queue */
+ WARN_ON(cmd->rq->bio != cmd->rq->biotail);
+
+ bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
+ iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
+ bio_segments(bio), blk_rq_bytes(cmd->rq));
+
+ cmd->iocb.ki_pos = pos;
+ cmd->iocb.ki_filp = file;
+ cmd->iocb.ki_complete = lo_rw_aio_complete;
+ cmd->iocb.ki_flags = IOCB_DIRECT;
+
+ if (rw == WRITE)
+ ret = file->f_op->write_iter(&cmd->iocb, &iter);
+ else
+ ret = file->f_op->read_iter(&cmd->iocb, &iter);
+
+ if (ret != -EIOCBQUEUED)
+ cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
+ return 0;
+}
+
+
+static inline int lo_rw_simple(struct loop_device *lo,
+ struct request *rq, loff_t pos, bool rw)
+{
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
+
+ if (cmd->use_aio)
+ return lo_rw_aio(lo, cmd, pos, rw);
+
+ /*
+ * lo_write_simple and lo_read_simple should have been covered
+ * by io submit style function like lo_rw_aio(), one blocker
+ * is that lo_read_simple() need to call flush_dcache_page after
+ * the page is written from kernel, and it isn't easy to handle
+ * this in io submit style function which submits all segments
+ * of the req at one time. And direct read IO doesn't need to
+ * run flush_dcache_page().
+ */
+ if (rw == WRITE)
+ return lo_write_simple(lo, rq, pos);
+ else
+ return lo_read_simple(lo, rq, pos);
+}
+
static int do_req_filebacked(struct loop_device *lo, struct request *rq)
{
loff_t pos;
@@ -404,13 +543,13 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
else if (lo->transfer)
ret = lo_write_transfer(lo, rq, pos);
else
- ret = lo_write_simple(lo, rq, pos);
+ ret = lo_rw_simple(lo, rq, pos, WRITE);
} else {
if (lo->transfer)
ret = lo_read_transfer(lo, rq, pos);
else
- ret = lo_read_simple(lo, rq, pos);
+ ret = lo_rw_simple(lo, rq, pos, READ);
}
return ret;
@@ -421,6 +560,12 @@ struct switch_request {
struct completion wait;
};
+static inline void loop_update_dio(struct loop_device *lo)
+{
+ __loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
+ lo->use_dio);
+}
+
/*
* Do the actual switch; called from the BIO completion routine
*/
@@ -441,6 +586,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
lo->old_gfp_mask = mapping_gfp_mask(mapping);
mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
+ loop_update_dio(lo);
}
/*
@@ -627,11 +773,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
return sprintf(buf, "%s\n", partscan ? "1" : "0");
}
+static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
+{
+ int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);
+
+ return sprintf(buf, "%s\n", dio ? "1" : "0");
+}
+
LOOP_ATTR_RO(backing_file);
LOOP_ATTR_RO(offset);
LOOP_ATTR_RO(sizelimit);
LOOP_ATTR_RO(autoclear);
LOOP_ATTR_RO(partscan);
+LOOP_ATTR_RO(dio);
static struct attribute *loop_attrs[] = {
&loop_attr_backing_file.attr,
@@ -639,6 +793,7 @@ static struct attribute *loop_attrs[] = {
&loop_attr_sizelimit.attr,
&loop_attr_autoclear.attr,
&loop_attr_partscan.attr,
+ &loop_attr_dio.attr,
NULL,
};
@@ -688,6 +843,23 @@ static void loop_config_discard(struct loop_device *lo)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
+static void loop_unprepare_queue(struct loop_device *lo)
+{
+ flush_kthread_worker(&lo->worker);
+ kthread_stop(lo->worker_task);
+}
+
+static int loop_prepare_queue(struct loop_device *lo)
+{
+ init_kthread_worker(&lo->worker);
+ lo->worker_task = kthread_run(kthread_worker_fn,
+ &lo->worker, "loop%d", lo->lo_number);
+ if (IS_ERR(lo->worker_task))
+ return -ENOMEM;
+ set_user_nice(lo->worker_task, MIN_NICE);
+ return 0;
+}
+
static int loop_set_fd(struct loop_device *lo, fmode_t mode,
struct block_device *bdev, unsigned int arg)
{
@@ -745,17 +917,15 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
size = get_loop_size(lo, file);
if ((loff_t)(sector_t)size != size)
goto out_putf;
- error = -ENOMEM;
- lo->wq = alloc_workqueue("kloopd%d",
- WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_UNBOUND, 16,
- lo->lo_number);
- if (!lo->wq)
+ error = loop_prepare_queue(lo);
+ if (error)
goto out_putf;
error = 0;
set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
+ lo->use_dio = false;
lo->lo_blocksize = lo_blocksize;
lo->lo_device = bdev;
lo->lo_flags = lo_flags;
@@ -769,6 +939,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode,
if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
blk_queue_flush(lo->lo_queue, REQ_FLUSH);
+ loop_update_dio(lo);
set_capacity(lo->lo_disk, size);
bd_set_size(bdev, size << 9);
loop_sysfs_init(lo);
@@ -903,8 +1074,7 @@ static int loop_clr_fd(struct loop_device *lo)
lo->lo_flags = 0;
if (!part_shift)
lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
- destroy_workqueue(lo->wq);
- lo->wq = NULL;
+ loop_unprepare_queue(lo);
mutex_unlock(&lo->lo_ctl_mutex);
/*
* Need not hold lo_ctl_mutex to fput backing file.
@@ -988,6 +1158,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
lo->lo_key_owner = uid;
}
+ /* update dio if lo_offset or transfer is changed */
+ __loop_update_dio(lo, lo->use_dio);
+
return 0;
}
@@ -1138,6 +1311,20 @@ static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev)
return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
}
+static int loop_set_dio(struct loop_device *lo, unsigned long arg)
+{
+ int error = -ENXIO;
+ if (lo->lo_state != Lo_bound)
+ goto out;
+
+ __loop_update_dio(lo, !!arg);
+ if (lo->use_dio == !!arg)
+ return 0;
+ error = -EINVAL;
+ out:
+ return error;
+}
+
static int lo_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
@@ -1181,6 +1368,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode,
if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
err = loop_set_capacity(lo, bdev);
break;
+ case LOOP_SET_DIRECT_IO:
+ err = -EPERM;
+ if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
+ err = loop_set_dio(lo, arg);
+ break;
default:
err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
}
@@ -1461,23 +1653,13 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
if (lo->lo_state != Lo_bound)
return -EIO;
- if (cmd->rq->cmd_flags & REQ_WRITE) {
- struct loop_device *lo = cmd->rq->q->queuedata;
- bool need_sched = true;
-
- spin_lock_irq(&lo->lo_lock);
- if (lo->write_started)
- need_sched = false;
- else
- lo->write_started = true;
- list_add_tail(&cmd->list, &lo->write_cmd_head);
- spin_unlock_irq(&lo->lo_lock);
+ if (lo->use_dio && !(cmd->rq->cmd_flags & (REQ_FLUSH |
+ REQ_DISCARD)))
+ cmd->use_aio = true;
+ else
+ cmd->use_aio = false;
- if (need_sched)
- queue_work(lo->wq, &lo->write_work);
- } else {
- queue_work(lo->wq, &cmd->read_work);
- }
+ queue_kthread_work(&lo->worker, &cmd->work);
return BLK_MQ_RQ_QUEUE_OK;
}
@@ -1495,38 +1677,15 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
ret = do_req_filebacked(lo, cmd->rq);
failed:
- blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+ /* complete non-aio request */
+ if (!cmd->use_aio || ret)
+ blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
}
-static void loop_queue_write_work(struct work_struct *work)
-{
- struct loop_device *lo =
- container_of(work, struct loop_device, write_work);
- LIST_HEAD(cmd_list);
-
- spin_lock_irq(&lo->lo_lock);
- repeat:
- list_splice_init(&lo->write_cmd_head, &cmd_list);
- spin_unlock_irq(&lo->lo_lock);
-
- while (!list_empty(&cmd_list)) {
- struct loop_cmd *cmd = list_first_entry(&cmd_list,
- struct loop_cmd, list);
- list_del_init(&cmd->list);
- loop_handle_cmd(cmd);
- }
-
- spin_lock_irq(&lo->lo_lock);
- if (!list_empty(&lo->write_cmd_head))
- goto repeat;
- lo->write_started = false;
- spin_unlock_irq(&lo->lo_lock);
-}
-
-static void loop_queue_read_work(struct work_struct *work)
+static void loop_queue_work(struct kthread_work *work)
{
struct loop_cmd *cmd =
- container_of(work, struct loop_cmd, read_work);
+ container_of(work, struct loop_cmd, work);
loop_handle_cmd(cmd);
}
@@ -1538,7 +1697,7 @@ static int loop_init_request(void *data, struct request *rq,
struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
cmd->rq = rq;
- INIT_WORK(&cmd->read_work, loop_queue_read_work);
+ init_kthread_work(&cmd->work, loop_queue_work);
return 0;
}
@@ -1594,8 +1753,11 @@ static int loop_add(struct loop_device **l, int i)
}
lo->lo_queue->queuedata = lo;
- INIT_LIST_HEAD(&lo->write_cmd_head);
- INIT_WORK(&lo->write_work, loop_queue_write_work);
+ /*
+ * It doesn't make sense to enable merge because the I/O
+ * submitted to backing file is handled page by page.
+ */
+ queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);
disk = lo->lo_disk = alloc_disk(1 << part_shift);
if (!disk)
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index 25e8997ed246..fb2237c73e61 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -14,7 +14,7 @@
#include <linux/blk-mq.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
-#include <linux/workqueue.h>
+#include <linux/kthread.h>
#include <uapi/linux/loop.h>
/* Possible states of device */
@@ -54,12 +54,11 @@ struct loop_device {
gfp_t old_gfp_mask;
spinlock_t lo_lock;
- struct workqueue_struct *wq;
- struct list_head write_cmd_head;
- struct work_struct write_work;
- bool write_started;
int lo_state;
struct mutex lo_ctl_mutex;
+ struct kthread_worker worker;
+ struct task_struct *worker_task;
+ bool use_dio;
struct request_queue *lo_queue;
struct blk_mq_tag_set tag_set;
@@ -67,9 +66,11 @@ struct loop_device {
};
struct loop_cmd {
- struct work_struct read_work;
+ struct kthread_work work;
struct request *rq;
struct list_head list;
+ bool use_aio; /* use AIO interface to handle I/O */
+ struct kiocb iocb;
};
/* Support for loadable transfer modules */
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index f504232c1ee7..a28a562f7b7f 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -173,7 +173,7 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
{
struct request *rq;
- rq = blk_mq_alloc_request(dd->queue, 0, __GFP_WAIT, true);
+ rq = blk_mq_alloc_request(dd->queue, 0, __GFP_RECLAIM, true);
return blk_mq_rq_to_pdu(rq);
}
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 293495a75d3d..93b3f99b6865 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -60,6 +60,7 @@ struct nbd_device {
bool disconnect; /* a disconnect has been requested by user */
struct timer_list timeout_timer;
+ spinlock_t tasks_lock;
struct task_struct *task_recv;
struct task_struct *task_send;
@@ -140,21 +141,23 @@ static void sock_shutdown(struct nbd_device *nbd)
static void nbd_xmit_timeout(unsigned long arg)
{
struct nbd_device *nbd = (struct nbd_device *)arg;
- struct task_struct *task;
+ unsigned long flags;
if (list_empty(&nbd->queue_head))
return;
nbd->disconnect = true;
- task = READ_ONCE(nbd->task_recv);
- if (task)
- force_sig(SIGKILL, task);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
+
+ if (nbd->task_recv)
+ force_sig(SIGKILL, nbd->task_recv);
- task = READ_ONCE(nbd->task_send);
- if (task)
+ if (nbd->task_send)
force_sig(SIGKILL, nbd->task_send);
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
dev_err(nbd_to_dev(nbd), "Connection timed out, killed receiver and sender, shutting down connection\n");
}
@@ -403,17 +406,24 @@ static int nbd_thread_recv(struct nbd_device *nbd)
{
struct request *req;
int ret;
+ unsigned long flags;
BUG_ON(nbd->magic != NBD_MAGIC);
sk_set_memalloc(nbd->sock->sk);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = current;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
ret = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
if (ret) {
dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
+
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
return ret;
}
@@ -429,12 +439,12 @@ static int nbd_thread_recv(struct nbd_device *nbd)
device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_recv = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
if (signal_pending(current)) {
- siginfo_t info;
-
- ret = dequeue_signal_lock(current, &current->blocked, &info);
+ ret = kernel_dequeue_signal(NULL);
dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
task_pid_nr(current), current->comm, ret);
mutex_lock(&nbd->tx_lock);
@@ -534,8 +544,11 @@ static int nbd_thread_send(void *data)
{
struct nbd_device *nbd = data;
struct request *req;
+ unsigned long flags;
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_send = current;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
set_user_nice(current, MIN_NICE);
while (!kthread_should_stop() || !list_empty(&nbd->waiting_queue)) {
@@ -545,11 +558,8 @@ static int nbd_thread_send(void *data)
!list_empty(&nbd->waiting_queue));
if (signal_pending(current)) {
- siginfo_t info;
- int ret;
+ int ret = kernel_dequeue_signal(NULL);
- ret = dequeue_signal_lock(current, &current->blocked,
- &info);
dev_warn(nbd_to_dev(nbd), "pid %d, %s, got signal %d\n",
task_pid_nr(current), current->comm, ret);
mutex_lock(&nbd->tx_lock);
@@ -572,7 +582,13 @@ static int nbd_thread_send(void *data)
nbd_handle_req(nbd, req);
}
+ spin_lock_irqsave(&nbd->tasks_lock, flags);
nbd->task_send = NULL;
+ spin_unlock_irqrestore(&nbd->tasks_lock, flags);
+
+ /* Clear maybe pending signals */
+ if (signal_pending(current))
+ kernel_dequeue_signal(NULL);
return 0;
}
@@ -1052,6 +1068,7 @@ static int __init nbd_init(void)
nbd_dev[i].magic = NBD_MAGIC;
INIT_LIST_HEAD(&nbd_dev[i].waiting_queue);
spin_lock_init(&nbd_dev[i].queue_lock);
+ spin_lock_init(&nbd_dev[i].tasks_lock);
INIT_LIST_HEAD(&nbd_dev[i].queue_head);
mutex_init(&nbd_dev[i].tx_lock);
init_timer(&nbd_dev[i].timeout_timer);
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 1c9e4fe5aa44..6255d1c4bba4 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -321,7 +321,7 @@ static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
return &nullb->queues[index];
}
-static void null_queue_bio(struct request_queue *q, struct bio *bio)
+static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
{
struct nullb *nullb = q->queuedata;
struct nullb_queue *nq = nullb_to_queue(nullb);
@@ -331,6 +331,7 @@ static void null_queue_bio(struct request_queue *q, struct bio *bio)
cmd->bio = bio;
null_handle_cmd(cmd);
+ return BLK_QC_T_NONE;
}
static int null_rq_prep_fn(struct request_queue *q, struct request *req)
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
deleted file mode 100644
index 6f04771f1019..000000000000
--- a/drivers/block/nvme-core.c
+++ /dev/null
@@ -1,3391 +0,0 @@
-/*
- * NVM Express device driver
- * Copyright (c) 2011-2014, Intel Corporation.
- *
- * 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 <linux/nvme.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/blk-mq.h>
-#include <linux/cpu.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/hdreg.h>
-#include <linux/idr.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/kdev_t.h>
-#include <linux/kthread.h>
-#include <linux/kernel.h>
-#include <linux/list_sort.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/pci.h>
-#include <linux/poison.h>
-#include <linux/ptrace.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/t10-pi.h>
-#include <linux/types.h>
-#include <scsi/sg.h>
-#include <asm-generic/io-64-nonatomic-lo-hi.h>
-
-#define NVME_MINORS (1U << MINORBITS)
-#define NVME_Q_DEPTH 1024
-#define NVME_AQ_DEPTH 256
-#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command))
-#define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion))
-#define ADMIN_TIMEOUT (admin_timeout * HZ)
-#define SHUTDOWN_TIMEOUT (shutdown_timeout * HZ)
-
-static unsigned char admin_timeout = 60;
-module_param(admin_timeout, byte, 0644);
-MODULE_PARM_DESC(admin_timeout, "timeout in seconds for admin commands");
-
-unsigned char nvme_io_timeout = 30;
-module_param_named(io_timeout, nvme_io_timeout, byte, 0644);
-MODULE_PARM_DESC(io_timeout, "timeout in seconds for I/O");
-
-static unsigned char shutdown_timeout = 5;
-module_param(shutdown_timeout, byte, 0644);
-MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
-
-static int nvme_major;
-module_param(nvme_major, int, 0);
-
-static int nvme_char_major;
-module_param(nvme_char_major, int, 0);
-
-static int use_threaded_interrupts;
-module_param(use_threaded_interrupts, int, 0);
-
-static bool use_cmb_sqes = true;
-module_param(use_cmb_sqes, bool, 0644);
-MODULE_PARM_DESC(use_cmb_sqes, "use controller's memory buffer for I/O SQes");
-
-static DEFINE_SPINLOCK(dev_list_lock);
-static LIST_HEAD(dev_list);
-static struct task_struct *nvme_thread;
-static struct workqueue_struct *nvme_workq;
-static wait_queue_head_t nvme_kthread_wait;
-
-static struct class *nvme_class;
-
-static void nvme_reset_failed_dev(struct work_struct *ws);
-static int nvme_reset(struct nvme_dev *dev);
-static int nvme_process_cq(struct nvme_queue *nvmeq);
-
-struct async_cmd_info {
- struct kthread_work work;
- struct kthread_worker *worker;
- struct request *req;
- u32 result;
- int status;
- void *ctx;
-};
-
-/*
- * An NVM Express queue. Each device has at least two (one for admin
- * commands and one for I/O commands).
- */
-struct nvme_queue {
- struct device *q_dmadev;
- struct nvme_dev *dev;
- char irqname[24]; /* nvme4294967295-65535\0 */
- spinlock_t q_lock;
- struct nvme_command *sq_cmds;
- struct nvme_command __iomem *sq_cmds_io;
- volatile struct nvme_completion *cqes;
- struct blk_mq_tags **tags;
- dma_addr_t sq_dma_addr;
- dma_addr_t cq_dma_addr;
- u32 __iomem *q_db;
- u16 q_depth;
- s16 cq_vector;
- u16 sq_head;
- u16 sq_tail;
- u16 cq_head;
- u16 qid;
- u8 cq_phase;
- u8 cqe_seen;
- struct async_cmd_info cmdinfo;
-};
-
-/*
- * Check we didin't inadvertently grow the command struct
- */
-static inline void _nvme_check_size(void)
-{
- BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_features) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_command) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_id_ns) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64);
- BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512);
-}
-
-typedef void (*nvme_completion_fn)(struct nvme_queue *, void *,
- struct nvme_completion *);
-
-struct nvme_cmd_info {
- nvme_completion_fn fn;
- void *ctx;
- int aborted;
- struct nvme_queue *nvmeq;
- struct nvme_iod iod[0];
-};
-
-/*
- * Max size of iod being embedded in the request payload
- */
-#define NVME_INT_PAGES 2
-#define NVME_INT_BYTES(dev) (NVME_INT_PAGES * (dev)->page_size)
-#define NVME_INT_MASK 0x01
-
-/*
- * Will slightly overestimate the number of pages needed. This is OK
- * as it only leads to a small amount of wasted memory for the lifetime of
- * the I/O.
- */
-static int nvme_npages(unsigned size, struct nvme_dev *dev)
-{
- unsigned nprps = DIV_ROUND_UP(size + dev->page_size, dev->page_size);
- return DIV_ROUND_UP(8 * nprps, PAGE_SIZE - 8);
-}
-
-static unsigned int nvme_cmd_size(struct nvme_dev *dev)
-{
- unsigned int ret = sizeof(struct nvme_cmd_info);
-
- ret += sizeof(struct nvme_iod);
- ret += sizeof(__le64 *) * nvme_npages(NVME_INT_BYTES(dev), dev);
- ret += sizeof(struct scatterlist) * NVME_INT_PAGES;
-
- return ret;
-}
-
-static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
- unsigned int hctx_idx)
-{
- struct nvme_dev *dev = data;
- struct nvme_queue *nvmeq = dev->queues[0];
-
- WARN_ON(hctx_idx != 0);
- WARN_ON(dev->admin_tagset.tags[0] != hctx->tags);
- WARN_ON(nvmeq->tags);
-
- hctx->driver_data = nvmeq;
- nvmeq->tags = &dev->admin_tagset.tags[0];
- return 0;
-}
-
-static void nvme_admin_exit_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
-{
- struct nvme_queue *nvmeq = hctx->driver_data;
-
- nvmeq->tags = NULL;
-}
-
-static int nvme_admin_init_request(void *data, struct request *req,
- unsigned int hctx_idx, unsigned int rq_idx,
- unsigned int numa_node)
-{
- struct nvme_dev *dev = data;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = dev->queues[0];
-
- BUG_ON(!nvmeq);
- cmd->nvmeq = nvmeq;
- return 0;
-}
-
-static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
- unsigned int hctx_idx)
-{
- struct nvme_dev *dev = data;
- struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
-
- if (!nvmeq->tags)
- nvmeq->tags = &dev->tagset.tags[hctx_idx];
-
- WARN_ON(dev->tagset.tags[hctx_idx] != hctx->tags);
- hctx->driver_data = nvmeq;
- return 0;
-}
-
-static int nvme_init_request(void *data, struct request *req,
- unsigned int hctx_idx, unsigned int rq_idx,
- unsigned int numa_node)
-{
- struct nvme_dev *dev = data;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = dev->queues[hctx_idx + 1];
-
- BUG_ON(!nvmeq);
- cmd->nvmeq = nvmeq;
- return 0;
-}
-
-static void nvme_set_info(struct nvme_cmd_info *cmd, void *ctx,
- nvme_completion_fn handler)
-{
- cmd->fn = handler;
- cmd->ctx = ctx;
- cmd->aborted = 0;
- blk_mq_start_request(blk_mq_rq_from_pdu(cmd));
-}
-
-static void *iod_get_private(struct nvme_iod *iod)
-{
- return (void *) (iod->private & ~0x1UL);
-}
-
-/*
- * If bit 0 is set, the iod is embedded in the request payload.
- */
-static bool iod_should_kfree(struct nvme_iod *iod)
-{
- return (iod->private & NVME_INT_MASK) == 0;
-}
-
-/* Special values must be less than 0x1000 */
-#define CMD_CTX_BASE ((void *)POISON_POINTER_DELTA)
-#define CMD_CTX_CANCELLED (0x30C + CMD_CTX_BASE)
-#define CMD_CTX_COMPLETED (0x310 + CMD_CTX_BASE)
-#define CMD_CTX_INVALID (0x314 + CMD_CTX_BASE)
-
-static void special_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion *cqe)
-{
- if (ctx == CMD_CTX_CANCELLED)
- return;
- if (ctx == CMD_CTX_COMPLETED) {
- dev_warn(nvmeq->q_dmadev,
- "completed id %d twice on queue %d\n",
- cqe->command_id, le16_to_cpup(&cqe->sq_id));
- return;
- }
- if (ctx == CMD_CTX_INVALID) {
- dev_warn(nvmeq->q_dmadev,
- "invalid id %d completed on queue %d\n",
- cqe->command_id, le16_to_cpup(&cqe->sq_id));
- return;
- }
- dev_warn(nvmeq->q_dmadev, "Unknown special completion %p\n", ctx);
-}
-
-static void *cancel_cmd_info(struct nvme_cmd_info *cmd, nvme_completion_fn *fn)
-{
- void *ctx;
-
- if (fn)
- *fn = cmd->fn;
- ctx = cmd->ctx;
- cmd->fn = special_completion;
- cmd->ctx = CMD_CTX_CANCELLED;
- return ctx;
-}
-
-static void async_req_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion *cqe)
-{
- u32 result = le32_to_cpup(&cqe->result);
- u16 status = le16_to_cpup(&cqe->status) >> 1;
-
- if (status == NVME_SC_SUCCESS || status == NVME_SC_ABORT_REQ)
- ++nvmeq->dev->event_limit;
- if (status != NVME_SC_SUCCESS)
- return;
-
- switch (result & 0xff07) {
- case NVME_AER_NOTICE_NS_CHANGED:
- dev_info(nvmeq->q_dmadev, "rescanning\n");
- schedule_work(&nvmeq->dev->scan_work);
- default:
- dev_warn(nvmeq->q_dmadev, "async event result %08x\n", result);
- }
-}
-
-static void abort_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion *cqe)
-{
- struct request *req = ctx;
-
- u16 status = le16_to_cpup(&cqe->status) >> 1;
- u32 result = le32_to_cpup(&cqe->result);
-
- blk_mq_free_request(req);
-
- dev_warn(nvmeq->q_dmadev, "Abort status:%x result:%x", status, result);
- ++nvmeq->dev->abort_limit;
-}
-
-static void async_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion *cqe)
-{
- struct async_cmd_info *cmdinfo = ctx;
- cmdinfo->result = le32_to_cpup(&cqe->result);
- cmdinfo->status = le16_to_cpup(&cqe->status) >> 1;
- queue_kthread_work(cmdinfo->worker, &cmdinfo->work);
- blk_mq_free_request(cmdinfo->req);
-}
-
-static inline struct nvme_cmd_info *get_cmd_from_tag(struct nvme_queue *nvmeq,
- unsigned int tag)
-{
- struct request *req = blk_mq_tag_to_rq(*nvmeq->tags, tag);
-
- return blk_mq_rq_to_pdu(req);
-}
-
-/*
- * Called with local interrupts disabled and the q_lock held. May not sleep.
- */
-static void *nvme_finish_cmd(struct nvme_queue *nvmeq, int tag,
- nvme_completion_fn *fn)
-{
- struct nvme_cmd_info *cmd = get_cmd_from_tag(nvmeq, tag);
- void *ctx;
- if (tag >= nvmeq->q_depth) {
- *fn = special_completion;
- return CMD_CTX_INVALID;
- }
- if (fn)
- *fn = cmd->fn;
- ctx = cmd->ctx;
- cmd->fn = special_completion;
- cmd->ctx = CMD_CTX_COMPLETED;
- return ctx;
-}
-
-/**
- * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell
- * @nvmeq: The queue to use
- * @cmd: The command to send
- *
- * Safe to use from interrupt context
- */
-static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
- struct nvme_command *cmd)
-{
- u16 tail = nvmeq->sq_tail;
-
- if (nvmeq->sq_cmds_io)
- memcpy_toio(&nvmeq->sq_cmds_io[tail], cmd, sizeof(*cmd));
- else
- memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd));
-
- if (++tail == nvmeq->q_depth)
- tail = 0;
- writel(tail, nvmeq->q_db);
- nvmeq->sq_tail = tail;
-}
-
-static void nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd)
-{
- unsigned long flags;
- spin_lock_irqsave(&nvmeq->q_lock, flags);
- __nvme_submit_cmd(nvmeq, cmd);
- spin_unlock_irqrestore(&nvmeq->q_lock, flags);
-}
-
-static __le64 **iod_list(struct nvme_iod *iod)
-{
- return ((void *)iod) + iod->offset;
-}
-
-static inline void iod_init(struct nvme_iod *iod, unsigned nbytes,
- unsigned nseg, unsigned long private)
-{
- iod->private = private;
- iod->offset = offsetof(struct nvme_iod, sg[nseg]);
- iod->npages = -1;
- iod->length = nbytes;
- iod->nents = 0;
-}
-
-static struct nvme_iod *
-__nvme_alloc_iod(unsigned nseg, unsigned bytes, struct nvme_dev *dev,
- unsigned long priv, gfp_t gfp)
-{
- struct nvme_iod *iod = kmalloc(sizeof(struct nvme_iod) +
- sizeof(__le64 *) * nvme_npages(bytes, dev) +
- sizeof(struct scatterlist) * nseg, gfp);
-
- if (iod)
- iod_init(iod, bytes, nseg, priv);
-
- return iod;
-}
-
-static struct nvme_iod *nvme_alloc_iod(struct request *rq, struct nvme_dev *dev,
- gfp_t gfp)
-{
- unsigned size = !(rq->cmd_flags & REQ_DISCARD) ? blk_rq_bytes(rq) :
- sizeof(struct nvme_dsm_range);
- struct nvme_iod *iod;
-
- if (rq->nr_phys_segments <= NVME_INT_PAGES &&
- size <= NVME_INT_BYTES(dev)) {
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(rq);
-
- iod = cmd->iod;
- iod_init(iod, size, rq->nr_phys_segments,
- (unsigned long) rq | NVME_INT_MASK);
- return iod;
- }
-
- return __nvme_alloc_iod(rq->nr_phys_segments, size, dev,
- (unsigned long) rq, gfp);
-}
-
-static void nvme_free_iod(struct nvme_dev *dev, struct nvme_iod *iod)
-{
- const int last_prp = dev->page_size / 8 - 1;
- int i;
- __le64 **list = iod_list(iod);
- dma_addr_t prp_dma = iod->first_dma;
-
- if (iod->npages == 0)
- dma_pool_free(dev->prp_small_pool, list[0], prp_dma);
- for (i = 0; i < iod->npages; i++) {
- __le64 *prp_list = list[i];
- dma_addr_t next_prp_dma = le64_to_cpu(prp_list[last_prp]);
- dma_pool_free(dev->prp_page_pool, prp_list, prp_dma);
- prp_dma = next_prp_dma;
- }
-
- if (iod_should_kfree(iod))
- kfree(iod);
-}
-
-static int nvme_error_status(u16 status)
-{
- switch (status & 0x7ff) {
- case NVME_SC_SUCCESS:
- return 0;
- case NVME_SC_CAP_EXCEEDED:
- return -ENOSPC;
- default:
- return -EIO;
- }
-}
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
- if (be32_to_cpu(pi->ref_tag) == v)
- pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
- if (be32_to_cpu(pi->ref_tag) == p)
- pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted by the
- * block layer. Due to partitioning, MD/DM cloning, etc. the actual physical
- * start sector may be different. Remap protection information to match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
- void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
- struct nvme_ns *ns = req->rq_disk->private_data;
- struct bio_integrity_payload *bip;
- struct t10_pi_tuple *pi;
- void *p, *pmap;
- u32 i, nlb, ts, phys, virt;
-
- if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
- return;
-
- bip = bio_integrity(req->bio);
- if (!bip)
- return;
-
- pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
-
- p = pmap;
- virt = bip_get_seed(bip);
- phys = nvme_block_nr(ns, blk_rq_pos(req));
- nlb = (blk_rq_bytes(req) >> ns->lba_shift);
- ts = ns->disk->integrity->tuple_size;
-
- for (i = 0; i < nlb; i++, virt++, phys++) {
- pi = (struct t10_pi_tuple *)p;
- dif_swap(phys, virt, pi);
- p += ts;
- }
- kunmap_atomic(pmap);
-}
-
-static int nvme_noop_verify(struct blk_integrity_iter *iter)
-{
- return 0;
-}
-
-static int nvme_noop_generate(struct blk_integrity_iter *iter)
-{
- return 0;
-}
-
-struct blk_integrity nvme_meta_noop = {
- .name = "NVME_META_NOOP",
- .generate_fn = nvme_noop_generate,
- .verify_fn = nvme_noop_verify,
-};
-
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
- struct blk_integrity integrity;
-
- switch (ns->pi_type) {
- case NVME_NS_DPS_PI_TYPE3:
- integrity = t10_pi_type3_crc;
- break;
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- integrity = t10_pi_type1_crc;
- break;
- default:
- integrity = nvme_meta_noop;
- break;
- }
- integrity.tuple_size = ns->ms;
- blk_integrity_register(ns->disk, &integrity);
- blk_queue_max_integrity_segments(ns->queue, 1);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
- void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_init_integrity(struct nvme_ns *ns)
-{
-}
-#endif
-
-static void req_completion(struct nvme_queue *nvmeq, void *ctx,
- struct nvme_completion *cqe)
-{
- struct nvme_iod *iod = ctx;
- struct request *req = iod_get_private(iod);
- struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
-
- u16 status = le16_to_cpup(&cqe->status) >> 1;
-
- if (unlikely(status)) {
- if (!(status & NVME_SC_DNR || blk_noretry_request(req))
- && (jiffies - req->start_time) < req->timeout) {
- unsigned long flags;
-
- blk_mq_requeue_request(req);
- spin_lock_irqsave(req->q->queue_lock, flags);
- if (!blk_queue_stopped(req->q))
- blk_mq_kick_requeue_list(req->q);
- spin_unlock_irqrestore(req->q->queue_lock, flags);
- return;
- }
-
- if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
- if (cmd_rq->ctx == CMD_CTX_CANCELLED)
- status = -EINTR;
- } else {
- status = nvme_error_status(status);
- }
- }
-
- if (req->cmd_type == REQ_TYPE_DRV_PRIV) {
- u32 result = le32_to_cpup(&cqe->result);
- req->special = (void *)(uintptr_t)result;
- }
-
- if (cmd_rq->aborted)
- dev_warn(nvmeq->dev->dev,
- "completing aborted command with status:%04x\n",
- status);
-
- if (iod->nents) {
- dma_unmap_sg(nvmeq->dev->dev, iod->sg, iod->nents,
- rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
- if (blk_integrity_rq(req)) {
- if (!rq_data_dir(req))
- nvme_dif_remap(req, nvme_dif_complete);
- dma_unmap_sg(nvmeq->dev->dev, iod->meta_sg, 1,
- rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
- }
- }
- nvme_free_iod(nvmeq->dev, iod);
-
- blk_mq_complete_request(req, status);
-}
-
-/* length is in bytes. gfp flags indicates whether we may sleep. */
-static int nvme_setup_prps(struct nvme_dev *dev, struct nvme_iod *iod,
- int total_len, gfp_t gfp)
-{
- struct dma_pool *pool;
- int length = total_len;
- struct scatterlist *sg = iod->sg;
- int dma_len = sg_dma_len(sg);
- u64 dma_addr = sg_dma_address(sg);
- u32 page_size = dev->page_size;
- int offset = dma_addr & (page_size - 1);
- __le64 *prp_list;
- __le64 **list = iod_list(iod);
- dma_addr_t prp_dma;
- int nprps, i;
-
- length -= (page_size - offset);
- if (length <= 0)
- return total_len;
-
- dma_len -= (page_size - offset);
- if (dma_len) {
- dma_addr += (page_size - offset);
- } else {
- sg = sg_next(sg);
- dma_addr = sg_dma_address(sg);
- dma_len = sg_dma_len(sg);
- }
-
- if (length <= page_size) {
- iod->first_dma = dma_addr;
- return total_len;
- }
-
- nprps = DIV_ROUND_UP(length, page_size);
- if (nprps <= (256 / 8)) {
- pool = dev->prp_small_pool;
- iod->npages = 0;
- } else {
- pool = dev->prp_page_pool;
- iod->npages = 1;
- }
-
- prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
- if (!prp_list) {
- iod->first_dma = dma_addr;
- iod->npages = -1;
- return (total_len - length) + page_size;
- }
- list[0] = prp_list;
- iod->first_dma = prp_dma;
- i = 0;
- for (;;) {
- if (i == page_size >> 3) {
- __le64 *old_prp_list = prp_list;
- prp_list = dma_pool_alloc(pool, gfp, &prp_dma);
- if (!prp_list)
- return total_len - length;
- list[iod->npages++] = prp_list;
- prp_list[0] = old_prp_list[i - 1];
- old_prp_list[i - 1] = cpu_to_le64(prp_dma);
- i = 1;
- }
- prp_list[i++] = cpu_to_le64(dma_addr);
- dma_len -= page_size;
- dma_addr += page_size;
- length -= page_size;
- if (length <= 0)
- break;
- if (dma_len > 0)
- continue;
- BUG_ON(dma_len < 0);
- sg = sg_next(sg);
- dma_addr = sg_dma_address(sg);
- dma_len = sg_dma_len(sg);
- }
-
- return total_len;
-}
-
-static void nvme_submit_priv(struct nvme_queue *nvmeq, struct request *req,
- struct nvme_iod *iod)
-{
- struct nvme_command cmnd;
-
- memcpy(&cmnd, req->cmd, sizeof(cmnd));
- cmnd.rw.command_id = req->tag;
- if (req->nr_phys_segments) {
- cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
- cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
- }
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-/*
- * We reuse the small pool to allocate the 16-byte range here as it is not
- * worth having a special pool for these or additional cases to handle freeing
- * the iod.
- */
-static void nvme_submit_discard(struct nvme_queue *nvmeq, struct nvme_ns *ns,
- struct request *req, struct nvme_iod *iod)
-{
- struct nvme_dsm_range *range =
- (struct nvme_dsm_range *)iod_list(iod)[0];
- struct nvme_command cmnd;
-
- range->cattr = cpu_to_le32(0);
- range->nlb = cpu_to_le32(blk_rq_bytes(req) >> ns->lba_shift);
- range->slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.dsm.opcode = nvme_cmd_dsm;
- cmnd.dsm.command_id = req->tag;
- cmnd.dsm.nsid = cpu_to_le32(ns->ns_id);
- cmnd.dsm.prp1 = cpu_to_le64(iod->first_dma);
- cmnd.dsm.nr = 0;
- cmnd.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-static void nvme_submit_flush(struct nvme_queue *nvmeq, struct nvme_ns *ns,
- int cmdid)
-{
- struct nvme_command cmnd;
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.common.opcode = nvme_cmd_flush;
- cmnd.common.command_id = cmdid;
- cmnd.common.nsid = cpu_to_le32(ns->ns_id);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-}
-
-static int nvme_submit_iod(struct nvme_queue *nvmeq, struct nvme_iod *iod,
- struct nvme_ns *ns)
-{
- struct request *req = iod_get_private(iod);
- struct nvme_command cmnd;
- u16 control = 0;
- u32 dsmgmt = 0;
-
- if (req->cmd_flags & REQ_FUA)
- control |= NVME_RW_FUA;
- if (req->cmd_flags & (REQ_FAILFAST_DEV | REQ_RAHEAD))
- control |= NVME_RW_LR;
-
- if (req->cmd_flags & REQ_RAHEAD)
- dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH;
-
- memset(&cmnd, 0, sizeof(cmnd));
- cmnd.rw.opcode = (rq_data_dir(req) ? nvme_cmd_write : nvme_cmd_read);
- cmnd.rw.command_id = req->tag;
- cmnd.rw.nsid = cpu_to_le32(ns->ns_id);
- cmnd.rw.prp1 = cpu_to_le64(sg_dma_address(iod->sg));
- cmnd.rw.prp2 = cpu_to_le64(iod->first_dma);
- cmnd.rw.slba = cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req)));
- cmnd.rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1);
-
- if (ns->ms) {
- switch (ns->pi_type) {
- case NVME_NS_DPS_PI_TYPE3:
- control |= NVME_RW_PRINFO_PRCHK_GUARD;
- break;
- case NVME_NS_DPS_PI_TYPE1:
- case NVME_NS_DPS_PI_TYPE2:
- control |= NVME_RW_PRINFO_PRCHK_GUARD |
- NVME_RW_PRINFO_PRCHK_REF;
- cmnd.rw.reftag = cpu_to_le32(
- nvme_block_nr(ns, blk_rq_pos(req)));
- break;
- }
- if (blk_integrity_rq(req))
- cmnd.rw.metadata =
- cpu_to_le64(sg_dma_address(iod->meta_sg));
- else
- control |= NVME_RW_PRINFO_PRACT;
- }
-
- cmnd.rw.control = cpu_to_le16(control);
- cmnd.rw.dsmgmt = cpu_to_le32(dsmgmt);
-
- __nvme_submit_cmd(nvmeq, &cmnd);
-
- return 0;
-}
-
-/*
- * NOTE: ns is NULL when called on the admin queue.
- */
-static int nvme_queue_rq(struct blk_mq_hw_ctx *hctx,
- const struct blk_mq_queue_data *bd)
-{
- struct nvme_ns *ns = hctx->queue->queuedata;
- struct nvme_queue *nvmeq = hctx->driver_data;
- struct nvme_dev *dev = nvmeq->dev;
- struct request *req = bd->rq;
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_iod *iod;
- enum dma_data_direction dma_dir;
-
- /*
- * If formated with metadata, require the block layer provide a buffer
- * unless this namespace is formated such that the metadata can be
- * stripped/generated by the controller with PRACT=1.
- */
- if (ns && ns->ms && !blk_integrity_rq(req)) {
- if (!(ns->pi_type && ns->ms == 8) &&
- req->cmd_type != REQ_TYPE_DRV_PRIV) {
- blk_mq_complete_request(req, -EFAULT);
- return BLK_MQ_RQ_QUEUE_OK;
- }
- }
-
- iod = nvme_alloc_iod(req, dev, GFP_ATOMIC);
- if (!iod)
- return BLK_MQ_RQ_QUEUE_BUSY;
-
- if (req->cmd_flags & REQ_DISCARD) {
- void *range;
- /*
- * We reuse the small pool to allocate the 16-byte range here
- * as it is not worth having a special pool for these or
- * additional cases to handle freeing the iod.
- */
- range = dma_pool_alloc(dev->prp_small_pool, GFP_ATOMIC,
- &iod->first_dma);
- if (!range)
- goto retry_cmd;
- iod_list(iod)[0] = (__le64 *)range;
- iod->npages = 0;
- } else if (req->nr_phys_segments) {
- dma_dir = rq_data_dir(req) ? DMA_TO_DEVICE : DMA_FROM_DEVICE;
-
- sg_init_table(iod->sg, req->nr_phys_segments);
- iod->nents = blk_rq_map_sg(req->q, req, iod->sg);
- if (!iod->nents)
- goto error_cmd;
-
- if (!dma_map_sg(nvmeq->q_dmadev, iod->sg, iod->nents, dma_dir))
- goto retry_cmd;
-
- if (blk_rq_bytes(req) !=
- nvme_setup_prps(dev, iod, blk_rq_bytes(req), GFP_ATOMIC)) {
- dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
- goto retry_cmd;
- }
- if (blk_integrity_rq(req)) {
- if (blk_rq_count_integrity_sg(req->q, req->bio) != 1)
- goto error_cmd;
-
- sg_init_table(iod->meta_sg, 1);
- if (blk_rq_map_integrity_sg(
- req->q, req->bio, iod->meta_sg) != 1)
- goto error_cmd;
-
- if (rq_data_dir(req))
- nvme_dif_remap(req, nvme_dif_prep);
-
- if (!dma_map_sg(nvmeq->q_dmadev, iod->meta_sg, 1, dma_dir))
- goto error_cmd;
- }
- }
-
- nvme_set_info(cmd, iod, req_completion);
- spin_lock_irq(&nvmeq->q_lock);
- if (req->cmd_type == REQ_TYPE_DRV_PRIV)
- nvme_submit_priv(nvmeq, req, iod);
- else if (req->cmd_flags & REQ_DISCARD)
- nvme_submit_discard(nvmeq, ns, req, iod);
- else if (req->cmd_flags & REQ_FLUSH)
- nvme_submit_flush(nvmeq, ns, req->tag);
- else
- nvme_submit_iod(nvmeq, iod, ns);
-
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
- return BLK_MQ_RQ_QUEUE_OK;
-
- error_cmd:
- nvme_free_iod(dev, iod);
- return BLK_MQ_RQ_QUEUE_ERROR;
- retry_cmd:
- nvme_free_iod(dev, iod);
- return BLK_MQ_RQ_QUEUE_BUSY;
-}
-
-static int nvme_process_cq(struct nvme_queue *nvmeq)
-{
- u16 head, phase;
-
- head = nvmeq->cq_head;
- phase = nvmeq->cq_phase;
-
- for (;;) {
- void *ctx;
- nvme_completion_fn fn;
- struct nvme_completion cqe = nvmeq->cqes[head];
- if ((le16_to_cpu(cqe.status) & 1) != phase)
- break;
- nvmeq->sq_head = le16_to_cpu(cqe.sq_head);
- if (++head == nvmeq->q_depth) {
- head = 0;
- phase = !phase;
- }
- ctx = nvme_finish_cmd(nvmeq, cqe.command_id, &fn);
- fn(nvmeq, ctx, &cqe);
- }
-
- /* If the controller ignores the cq head doorbell and continuously
- * writes to the queue, it is theoretically possible to wrap around
- * the queue twice and mistakenly return IRQ_NONE. Linux only
- * requires that 0.1% of your interrupts are handled, so this isn't
- * a big problem.
- */
- if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
- return 0;
-
- writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
- nvmeq->cq_head = head;
- nvmeq->cq_phase = phase;
-
- nvmeq->cqe_seen = 1;
- return 1;
-}
-
-static irqreturn_t nvme_irq(int irq, void *data)
-{
- irqreturn_t result;
- struct nvme_queue *nvmeq = data;
- spin_lock(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- result = nvmeq->cqe_seen ? IRQ_HANDLED : IRQ_NONE;
- nvmeq->cqe_seen = 0;
- spin_unlock(&nvmeq->q_lock);
- return result;
-}
-
-static irqreturn_t nvme_irq_check(int irq, void *data)
-{
- struct nvme_queue *nvmeq = data;
- struct nvme_completion cqe = nvmeq->cqes[nvmeq->cq_head];
- if ((le16_to_cpu(cqe.status) & 1) != nvmeq->cq_phase)
- return IRQ_NONE;
- return IRQ_WAKE_THREAD;
-}
-
-/*
- * Returns 0 on success. If the result is negative, it's a Linux error code;
- * if the result is positive, it's an NVM Express status code
- */
-int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
- void *buffer, void __user *ubuffer, unsigned bufflen,
- u32 *result, unsigned timeout)
-{
- bool write = cmd->common.opcode & 1;
- struct bio *bio = NULL;
- struct request *req;
- int ret;
-
- req = blk_mq_alloc_request(q, write, GFP_KERNEL, false);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->cmd_type = REQ_TYPE_DRV_PRIV;
- req->cmd_flags |= REQ_FAILFAST_DRIVER;
- req->__data_len = 0;
- req->__sector = (sector_t) -1;
- req->bio = req->biotail = NULL;
-
- req->timeout = timeout ? timeout : ADMIN_TIMEOUT;
-
- req->cmd = (unsigned char *)cmd;
- req->cmd_len = sizeof(struct nvme_command);
- req->special = (void *)0;
-
- if (buffer && bufflen) {
- ret = blk_rq_map_kern(q, req, buffer, bufflen, __GFP_WAIT);
- if (ret)
- goto out;
- } else if (ubuffer && bufflen) {
- ret = blk_rq_map_user(q, req, NULL, ubuffer, bufflen, __GFP_WAIT);
- if (ret)
- goto out;
- bio = req->bio;
- }
-
- blk_execute_rq(req->q, NULL, req, 0);
- if (bio)
- blk_rq_unmap_user(bio);
- if (result)
- *result = (u32)(uintptr_t)req->special;
- ret = req->errors;
- out:
- blk_mq_free_request(req);
- return ret;
-}
-
-int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
- void *buffer, unsigned bufflen)
-{
- return __nvme_submit_sync_cmd(q, cmd, buffer, NULL, bufflen, NULL, 0);
-}
-
-static int nvme_submit_async_admin_req(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq = dev->queues[0];
- struct nvme_command c;
- struct nvme_cmd_info *cmd_info;
- struct request *req;
-
- req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC, true);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->cmd_flags |= REQ_NO_TIMEOUT;
- cmd_info = blk_mq_rq_to_pdu(req);
- nvme_set_info(cmd_info, NULL, async_req_completion);
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_async_event;
- c.common.command_id = req->tag;
-
- blk_mq_free_request(req);
- __nvme_submit_cmd(nvmeq, &c);
- return 0;
-}
-
-static int nvme_submit_admin_async_cmd(struct nvme_dev *dev,
- struct nvme_command *cmd,
- struct async_cmd_info *cmdinfo, unsigned timeout)
-{
- struct nvme_queue *nvmeq = dev->queues[0];
- struct request *req;
- struct nvme_cmd_info *cmd_rq;
-
- req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_KERNEL, false);
- if (IS_ERR(req))
- return PTR_ERR(req);
-
- req->timeout = timeout;
- cmd_rq = blk_mq_rq_to_pdu(req);
- cmdinfo->req = req;
- nvme_set_info(cmd_rq, cmdinfo, async_completion);
- cmdinfo->status = -EINTR;
-
- cmd->common.command_id = req->tag;
-
- nvme_submit_cmd(nvmeq, cmd);
- return 0;
-}
-
-static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.delete_queue.opcode = opcode;
- c.delete_queue.qid = cpu_to_le16(id);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid,
- struct nvme_queue *nvmeq)
-{
- struct nvme_command c;
- int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED;
-
- /*
- * Note: we (ab)use the fact the the prp fields survive if no data
- * is attached to the request.
- */
- memset(&c, 0, sizeof(c));
- c.create_cq.opcode = nvme_admin_create_cq;
- c.create_cq.prp1 = cpu_to_le64(nvmeq->cq_dma_addr);
- c.create_cq.cqid = cpu_to_le16(qid);
- c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
- c.create_cq.cq_flags = cpu_to_le16(flags);
- c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_alloc_sq(struct nvme_dev *dev, u16 qid,
- struct nvme_queue *nvmeq)
-{
- struct nvme_command c;
- int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM;
-
- /*
- * Note: we (ab)use the fact the the prp fields survive if no data
- * is attached to the request.
- */
- memset(&c, 0, sizeof(c));
- c.create_sq.opcode = nvme_admin_create_sq;
- c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_dma_addr);
- c.create_sq.sqid = cpu_to_le16(qid);
- c.create_sq.qsize = cpu_to_le16(nvmeq->q_depth - 1);
- c.create_sq.sq_flags = cpu_to_le16(flags);
- c.create_sq.cqid = cpu_to_le16(qid);
-
- return nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
-}
-
-static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid)
-{
- return adapter_delete_queue(dev, nvme_admin_delete_cq, cqid);
-}
-
-static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid)
-{
- return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid);
-}
-
-int nvme_identify_ctrl(struct nvme_dev *dev, struct nvme_id_ctrl **id)
-{
- struct nvme_command c = { };
- int error;
-
- /* gcc-4.4.4 (at least) has issues with initializers and anon unions */
- c.identify.opcode = nvme_admin_identify;
- c.identify.cns = cpu_to_le32(1);
-
- *id = kmalloc(sizeof(struct nvme_id_ctrl), GFP_KERNEL);
- if (!*id)
- return -ENOMEM;
-
- error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
- sizeof(struct nvme_id_ctrl));
- if (error)
- kfree(*id);
- return error;
-}
-
-int nvme_identify_ns(struct nvme_dev *dev, unsigned nsid,
- struct nvme_id_ns **id)
-{
- struct nvme_command c = { };
- int error;
-
- /* gcc-4.4.4 (at least) has issues with initializers and anon unions */
- c.identify.opcode = nvme_admin_identify,
- c.identify.nsid = cpu_to_le32(nsid),
-
- *id = kmalloc(sizeof(struct nvme_id_ns), GFP_KERNEL);
- if (!*id)
- return -ENOMEM;
-
- error = nvme_submit_sync_cmd(dev->admin_q, &c, *id,
- sizeof(struct nvme_id_ns));
- if (error)
- kfree(*id);
- return error;
-}
-
-int nvme_get_features(struct nvme_dev *dev, unsigned fid, unsigned nsid,
- dma_addr_t dma_addr, u32 *result)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.features.opcode = nvme_admin_get_features;
- c.features.nsid = cpu_to_le32(nsid);
- c.features.prp1 = cpu_to_le64(dma_addr);
- c.features.fid = cpu_to_le32(fid);
-
- return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, NULL, 0,
- result, 0);
-}
-
-int nvme_set_features(struct nvme_dev *dev, unsigned fid, unsigned dword11,
- dma_addr_t dma_addr, u32 *result)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.features.opcode = nvme_admin_set_features;
- c.features.prp1 = cpu_to_le64(dma_addr);
- c.features.fid = cpu_to_le32(fid);
- c.features.dword11 = cpu_to_le32(dword11);
-
- return __nvme_submit_sync_cmd(dev->admin_q, &c, NULL, NULL, 0,
- result, 0);
-}
-
-int nvme_get_log_page(struct nvme_dev *dev, struct nvme_smart_log **log)
-{
- struct nvme_command c = { };
- int error;
-
- c.common.opcode = nvme_admin_get_log_page,
- c.common.nsid = cpu_to_le32(0xFFFFFFFF),
- c.common.cdw10[0] = cpu_to_le32(
- (((sizeof(struct nvme_smart_log) / 4) - 1) << 16) |
- NVME_LOG_SMART),
-
- *log = kmalloc(sizeof(struct nvme_smart_log), GFP_KERNEL);
- if (!*log)
- return -ENOMEM;
-
- error = nvme_submit_sync_cmd(dev->admin_q, &c, *log,
- sizeof(struct nvme_smart_log));
- if (error)
- kfree(*log);
- return error;
-}
-
-/**
- * nvme_abort_req - Attempt aborting a request
- *
- * Schedule controller reset if the command was already aborted once before and
- * still hasn't been returned to the driver, or if this is the admin queue.
- */
-static void nvme_abort_req(struct request *req)
-{
- struct nvme_cmd_info *cmd_rq = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = cmd_rq->nvmeq;
- struct nvme_dev *dev = nvmeq->dev;
- struct request *abort_req;
- struct nvme_cmd_info *abort_cmd;
- struct nvme_command cmd;
-
- if (!nvmeq->qid || cmd_rq->aborted) {
- unsigned long flags;
-
- spin_lock_irqsave(&dev_list_lock, flags);
- if (work_busy(&dev->reset_work))
- goto out;
- list_del_init(&dev->node);
- dev_warn(dev->dev, "I/O %d QID %d timeout, reset controller\n",
- req->tag, nvmeq->qid);
- dev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev->reset_work);
- out:
- spin_unlock_irqrestore(&dev_list_lock, flags);
- return;
- }
-
- if (!dev->abort_limit)
- return;
-
- abort_req = blk_mq_alloc_request(dev->admin_q, WRITE, GFP_ATOMIC,
- false);
- if (IS_ERR(abort_req))
- return;
-
- abort_cmd = blk_mq_rq_to_pdu(abort_req);
- nvme_set_info(abort_cmd, abort_req, abort_completion);
-
- memset(&cmd, 0, sizeof(cmd));
- cmd.abort.opcode = nvme_admin_abort_cmd;
- cmd.abort.cid = req->tag;
- cmd.abort.sqid = cpu_to_le16(nvmeq->qid);
- cmd.abort.command_id = abort_req->tag;
-
- --dev->abort_limit;
- cmd_rq->aborted = 1;
-
- dev_warn(nvmeq->q_dmadev, "Aborting I/O %d QID %d\n", req->tag,
- nvmeq->qid);
- nvme_submit_cmd(dev->queues[0], &cmd);
-}
-
-static void nvme_cancel_queue_ios(struct request *req, void *data, bool reserved)
-{
- struct nvme_queue *nvmeq = data;
- void *ctx;
- nvme_completion_fn fn;
- struct nvme_cmd_info *cmd;
- struct nvme_completion cqe;
-
- if (!blk_mq_request_started(req))
- return;
-
- cmd = blk_mq_rq_to_pdu(req);
-
- if (cmd->ctx == CMD_CTX_CANCELLED)
- return;
-
- if (blk_queue_dying(req->q))
- cqe.status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
- else
- cqe.status = cpu_to_le16(NVME_SC_ABORT_REQ << 1);
-
-
- dev_warn(nvmeq->q_dmadev, "Cancelling I/O %d QID %d\n",
- req->tag, nvmeq->qid);
- ctx = cancel_cmd_info(cmd, &fn);
- fn(nvmeq, ctx, &cqe);
-}
-
-static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
-{
- struct nvme_cmd_info *cmd = blk_mq_rq_to_pdu(req);
- struct nvme_queue *nvmeq = cmd->nvmeq;
-
- dev_warn(nvmeq->q_dmadev, "Timeout I/O %d QID %d\n", req->tag,
- nvmeq->qid);
- spin_lock_irq(&nvmeq->q_lock);
- nvme_abort_req(req);
- spin_unlock_irq(&nvmeq->q_lock);
-
- /*
- * The aborted req will be completed on receiving the abort req.
- * We enable the timer again. If hit twice, it'll cause a device reset,
- * as the device then is in a faulty state.
- */
- return BLK_EH_RESET_TIMER;
-}
-
-static void nvme_free_queue(struct nvme_queue *nvmeq)
-{
- dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth),
- (void *)nvmeq->cqes, nvmeq->cq_dma_addr);
- if (nvmeq->sq_cmds)
- dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth),
- nvmeq->sq_cmds, nvmeq->sq_dma_addr);
- kfree(nvmeq);
-}
-
-static void nvme_free_queues(struct nvme_dev *dev, int lowest)
-{
- int i;
-
- for (i = dev->queue_count - 1; i >= lowest; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- dev->queue_count--;
- dev->queues[i] = NULL;
- nvme_free_queue(nvmeq);
- }
-}
-
-/**
- * nvme_suspend_queue - put queue into suspended state
- * @nvmeq - queue to suspend
- */
-static int nvme_suspend_queue(struct nvme_queue *nvmeq)
-{
- int vector;
-
- spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->cq_vector == -1) {
- spin_unlock_irq(&nvmeq->q_lock);
- return 1;
- }
- vector = nvmeq->dev->entry[nvmeq->cq_vector].vector;
- nvmeq->dev->online_queues--;
- nvmeq->cq_vector = -1;
- spin_unlock_irq(&nvmeq->q_lock);
-
- if (!nvmeq->qid && nvmeq->dev->admin_q)
- blk_mq_freeze_queue_start(nvmeq->dev->admin_q);
-
- irq_set_affinity_hint(vector, NULL);
- free_irq(vector, nvmeq);
-
- return 0;
-}
-
-static void nvme_clear_queue(struct nvme_queue *nvmeq)
-{
- spin_lock_irq(&nvmeq->q_lock);
- if (nvmeq->tags && *nvmeq->tags)
- blk_mq_all_tag_busy_iter(*nvmeq->tags, nvme_cancel_queue_ios, nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static void nvme_disable_queue(struct nvme_dev *dev, int qid)
-{
- struct nvme_queue *nvmeq = dev->queues[qid];
-
- if (!nvmeq)
- return;
- if (nvme_suspend_queue(nvmeq))
- return;
-
- /* Don't tell the adapter to delete the admin queue.
- * Don't tell a removed adapter to delete IO queues. */
- if (qid && readl(&dev->bar->csts) != -1) {
- adapter_delete_sq(dev, qid);
- adapter_delete_cq(dev, qid);
- }
-
- spin_lock_irq(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static int nvme_cmb_qdepth(struct nvme_dev *dev, int nr_io_queues,
- int entry_size)
-{
- int q_depth = dev->q_depth;
- unsigned q_size_aligned = roundup(q_depth * entry_size, dev->page_size);
-
- if (q_size_aligned * nr_io_queues > dev->cmb_size) {
- u64 mem_per_q = div_u64(dev->cmb_size, nr_io_queues);
- mem_per_q = round_down(mem_per_q, dev->page_size);
- q_depth = div_u64(mem_per_q, entry_size);
-
- /*
- * Ensure the reduced q_depth is above some threshold where it
- * would be better to map queues in system memory with the
- * original depth
- */
- if (q_depth < 64)
- return -ENOMEM;
- }
-
- return q_depth;
-}
-
-static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
- int qid, int depth)
-{
- if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
- unsigned offset = (qid - 1) *
- roundup(SQ_SIZE(depth), dev->page_size);
- nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
- nvmeq->sq_cmds_io = dev->cmb + offset;
- } else {
- nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
- &nvmeq->sq_dma_addr, GFP_KERNEL);
- if (!nvmeq->sq_cmds)
- return -ENOMEM;
- }
-
- return 0;
-}
-
-static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, int qid,
- int depth)
-{
- struct nvme_queue *nvmeq = kzalloc(sizeof(*nvmeq), GFP_KERNEL);
- if (!nvmeq)
- return NULL;
-
- nvmeq->cqes = dma_zalloc_coherent(dev->dev, CQ_SIZE(depth),
- &nvmeq->cq_dma_addr, GFP_KERNEL);
- if (!nvmeq->cqes)
- goto free_nvmeq;
-
- if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth))
- goto free_cqdma;
-
- nvmeq->q_dmadev = dev->dev;
- nvmeq->dev = dev;
- snprintf(nvmeq->irqname, sizeof(nvmeq->irqname), "nvme%dq%d",
- dev->instance, qid);
- spin_lock_init(&nvmeq->q_lock);
- nvmeq->cq_head = 0;
- nvmeq->cq_phase = 1;
- nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- nvmeq->q_depth = depth;
- nvmeq->qid = qid;
- nvmeq->cq_vector = -1;
- dev->queues[qid] = nvmeq;
-
- /* make sure queue descriptor is set before queue count, for kthread */
- mb();
- dev->queue_count++;
-
- return nvmeq;
-
- free_cqdma:
- dma_free_coherent(dev->dev, CQ_SIZE(depth), (void *)nvmeq->cqes,
- nvmeq->cq_dma_addr);
- free_nvmeq:
- kfree(nvmeq);
- return NULL;
-}
-
-static int queue_request_irq(struct nvme_dev *dev, struct nvme_queue *nvmeq,
- const char *name)
-{
- if (use_threaded_interrupts)
- return request_threaded_irq(dev->entry[nvmeq->cq_vector].vector,
- nvme_irq_check, nvme_irq, IRQF_SHARED,
- name, nvmeq);
- return request_irq(dev->entry[nvmeq->cq_vector].vector, nvme_irq,
- IRQF_SHARED, name, nvmeq);
-}
-
-static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
-{
- struct nvme_dev *dev = nvmeq->dev;
-
- spin_lock_irq(&nvmeq->q_lock);
- nvmeq->sq_tail = 0;
- nvmeq->cq_head = 0;
- nvmeq->cq_phase = 1;
- nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
- memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
- dev->online_queues++;
- spin_unlock_irq(&nvmeq->q_lock);
-}
-
-static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
-{
- struct nvme_dev *dev = nvmeq->dev;
- int result;
-
- nvmeq->cq_vector = qid - 1;
- result = adapter_alloc_cq(dev, qid, nvmeq);
- if (result < 0)
- return result;
-
- result = adapter_alloc_sq(dev, qid, nvmeq);
- if (result < 0)
- goto release_cq;
-
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
- if (result < 0)
- goto release_sq;
-
- nvme_init_queue(nvmeq, qid);
- return result;
-
- release_sq:
- adapter_delete_sq(dev, qid);
- release_cq:
- adapter_delete_cq(dev, qid);
- return result;
-}
-
-static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled)
-{
- unsigned long timeout;
- u32 bit = enabled ? NVME_CSTS_RDY : 0;
-
- timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
-
- while ((readl(&dev->bar->csts) & NVME_CSTS_RDY) != bit) {
- msleep(100);
- if (fatal_signal_pending(current))
- return -EINTR;
- if (time_after(jiffies, timeout)) {
- dev_err(dev->dev,
- "Device not ready; aborting %s\n", enabled ?
- "initialisation" : "reset");
- return -ENODEV;
- }
- }
-
- return 0;
-}
-
-/*
- * If the device has been passed off to us in an enabled state, just clear
- * the enabled bit. The spec says we should set the 'shutdown notification
- * bits', but doing so may cause the device to complete commands to the
- * admin queue ... and we don't know what memory that might be pointing at!
- */
-static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap)
-{
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config &= ~NVME_CC_ENABLE;
- writel(dev->ctrl_config, &dev->bar->cc);
-
- return nvme_wait_ready(dev, cap, false);
-}
-
-static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap)
-{
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config |= NVME_CC_ENABLE;
- writel(dev->ctrl_config, &dev->bar->cc);
-
- return nvme_wait_ready(dev, cap, true);
-}
-
-static int nvme_shutdown_ctrl(struct nvme_dev *dev)
-{
- unsigned long timeout;
-
- dev->ctrl_config &= ~NVME_CC_SHN_MASK;
- dev->ctrl_config |= NVME_CC_SHN_NORMAL;
-
- writel(dev->ctrl_config, &dev->bar->cc);
-
- timeout = SHUTDOWN_TIMEOUT + jiffies;
- while ((readl(&dev->bar->csts) & NVME_CSTS_SHST_MASK) !=
- NVME_CSTS_SHST_CMPLT) {
- msleep(100);
- if (fatal_signal_pending(current))
- return -EINTR;
- if (time_after(jiffies, timeout)) {
- dev_err(dev->dev,
- "Device shutdown incomplete; abort shutdown\n");
- return -ENODEV;
- }
- }
-
- return 0;
-}
-
-static struct blk_mq_ops nvme_mq_admin_ops = {
- .queue_rq = nvme_queue_rq,
- .map_queue = blk_mq_map_queue,
- .init_hctx = nvme_admin_init_hctx,
- .exit_hctx = nvme_admin_exit_hctx,
- .init_request = nvme_admin_init_request,
- .timeout = nvme_timeout,
-};
-
-static struct blk_mq_ops nvme_mq_ops = {
- .queue_rq = nvme_queue_rq,
- .map_queue = blk_mq_map_queue,
- .init_hctx = nvme_init_hctx,
- .init_request = nvme_init_request,
- .timeout = nvme_timeout,
-};
-
-static void nvme_dev_remove_admin(struct nvme_dev *dev)
-{
- if (dev->admin_q && !blk_queue_dying(dev->admin_q)) {
- blk_cleanup_queue(dev->admin_q);
- blk_mq_free_tag_set(&dev->admin_tagset);
- }
-}
-
-static int nvme_alloc_admin_tags(struct nvme_dev *dev)
-{
- if (!dev->admin_q) {
- dev->admin_tagset.ops = &nvme_mq_admin_ops;
- dev->admin_tagset.nr_hw_queues = 1;
- dev->admin_tagset.queue_depth = NVME_AQ_DEPTH - 1;
- dev->admin_tagset.reserved_tags = 1;
- dev->admin_tagset.timeout = ADMIN_TIMEOUT;
- dev->admin_tagset.numa_node = dev_to_node(dev->dev);
- dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
- dev->admin_tagset.driver_data = dev;
-
- if (blk_mq_alloc_tag_set(&dev->admin_tagset))
- return -ENOMEM;
-
- dev->admin_q = blk_mq_init_queue(&dev->admin_tagset);
- if (IS_ERR(dev->admin_q)) {
- blk_mq_free_tag_set(&dev->admin_tagset);
- return -ENOMEM;
- }
- if (!blk_get_queue(dev->admin_q)) {
- nvme_dev_remove_admin(dev);
- dev->admin_q = NULL;
- return -ENODEV;
- }
- } else
- blk_mq_unfreeze_queue(dev->admin_q);
-
- return 0;
-}
-
-static int nvme_configure_admin_queue(struct nvme_dev *dev)
-{
- int result;
- u32 aqa;
- u64 cap = readq(&dev->bar->cap);
- struct nvme_queue *nvmeq;
- unsigned page_shift = PAGE_SHIFT;
- unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12;
- unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12;
-
- if (page_shift < dev_page_min) {
- dev_err(dev->dev,
- "Minimum device page size (%u) too large for "
- "host (%u)\n", 1 << dev_page_min,
- 1 << page_shift);
- return -ENODEV;
- }
- if (page_shift > dev_page_max) {
- dev_info(dev->dev,
- "Device maximum page size (%u) smaller than "
- "host (%u); enabling work-around\n",
- 1 << dev_page_max, 1 << page_shift);
- page_shift = dev_page_max;
- }
-
- dev->subsystem = readl(&dev->bar->vs) >= NVME_VS(1, 1) ?
- NVME_CAP_NSSRC(cap) : 0;
-
- if (dev->subsystem && (readl(&dev->bar->csts) & NVME_CSTS_NSSRO))
- writel(NVME_CSTS_NSSRO, &dev->bar->csts);
-
- result = nvme_disable_ctrl(dev, cap);
- if (result < 0)
- return result;
-
- nvmeq = dev->queues[0];
- if (!nvmeq) {
- nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH);
- if (!nvmeq)
- return -ENOMEM;
- }
-
- aqa = nvmeq->q_depth - 1;
- aqa |= aqa << 16;
-
- dev->page_size = 1 << page_shift;
-
- dev->ctrl_config = NVME_CC_CSS_NVM;
- dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT;
- dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE;
- dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES;
-
- writel(aqa, &dev->bar->aqa);
- writeq(nvmeq->sq_dma_addr, &dev->bar->asq);
- writeq(nvmeq->cq_dma_addr, &dev->bar->acq);
-
- result = nvme_enable_ctrl(dev, cap);
- if (result)
- goto free_nvmeq;
-
- nvmeq->cq_vector = 0;
- result = queue_request_irq(dev, nvmeq, nvmeq->irqname);
- if (result) {
- nvmeq->cq_vector = -1;
- goto free_nvmeq;
- }
-
- return result;
-
- free_nvmeq:
- nvme_free_queues(dev, 0);
- return result;
-}
-
-static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
-{
- struct nvme_dev *dev = ns->dev;
- struct nvme_user_io io;
- struct nvme_command c;
- unsigned length, meta_len;
- int status, write;
- dma_addr_t meta_dma = 0;
- void *meta = NULL;
- void __user *metadata;
-
- if (copy_from_user(&io, uio, sizeof(io)))
- return -EFAULT;
-
- switch (io.opcode) {
- case nvme_cmd_write:
- case nvme_cmd_read:
- case nvme_cmd_compare:
- break;
- default:
- return -EINVAL;
- }
-
- length = (io.nblocks + 1) << ns->lba_shift;
- meta_len = (io.nblocks + 1) * ns->ms;
- metadata = (void __user *)(unsigned long)io.metadata;
- write = io.opcode & 1;
-
- if (ns->ext) {
- length += meta_len;
- meta_len = 0;
- }
- if (meta_len) {
- if (((io.metadata & 3) || !io.metadata) && !ns->ext)
- return -EINVAL;
-
- meta = dma_alloc_coherent(dev->dev, meta_len,
- &meta_dma, GFP_KERNEL);
-
- if (!meta) {
- status = -ENOMEM;
- goto unmap;
- }
- if (write) {
- if (copy_from_user(meta, metadata, meta_len)) {
- status = -EFAULT;
- goto unmap;
- }
- }
- }
-
- memset(&c, 0, sizeof(c));
- c.rw.opcode = io.opcode;
- c.rw.flags = io.flags;
- c.rw.nsid = cpu_to_le32(ns->ns_id);
- c.rw.slba = cpu_to_le64(io.slba);
- c.rw.length = cpu_to_le16(io.nblocks);
- c.rw.control = cpu_to_le16(io.control);
- c.rw.dsmgmt = cpu_to_le32(io.dsmgmt);
- c.rw.reftag = cpu_to_le32(io.reftag);
- c.rw.apptag = cpu_to_le16(io.apptag);
- c.rw.appmask = cpu_to_le16(io.appmask);
- c.rw.metadata = cpu_to_le64(meta_dma);
-
- status = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
- (void __user *)io.addr, length, NULL, 0);
- unmap:
- if (meta) {
- if (status == NVME_SC_SUCCESS && !write) {
- if (copy_to_user(metadata, meta, meta_len))
- status = -EFAULT;
- }
- dma_free_coherent(dev->dev, meta_len, meta, meta_dma);
- }
- return status;
-}
-
-static int nvme_user_cmd(struct nvme_dev *dev, struct nvme_ns *ns,
- struct nvme_passthru_cmd __user *ucmd)
-{
- struct nvme_passthru_cmd cmd;
- struct nvme_command c;
- unsigned timeout = 0;
- int status;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
- return -EFAULT;
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = cmd.opcode;
- c.common.flags = cmd.flags;
- c.common.nsid = cpu_to_le32(cmd.nsid);
- c.common.cdw2[0] = cpu_to_le32(cmd.cdw2);
- c.common.cdw2[1] = cpu_to_le32(cmd.cdw3);
- c.common.cdw10[0] = cpu_to_le32(cmd.cdw10);
- c.common.cdw10[1] = cpu_to_le32(cmd.cdw11);
- c.common.cdw10[2] = cpu_to_le32(cmd.cdw12);
- c.common.cdw10[3] = cpu_to_le32(cmd.cdw13);
- c.common.cdw10[4] = cpu_to_le32(cmd.cdw14);
- c.common.cdw10[5] = cpu_to_le32(cmd.cdw15);
-
- if (cmd.timeout_ms)
- timeout = msecs_to_jiffies(cmd.timeout_ms);
-
- status = __nvme_submit_sync_cmd(ns ? ns->queue : dev->admin_q, &c,
- NULL, (void __user *)cmd.addr, cmd.data_len,
- &cmd.result, timeout);
- if (status >= 0) {
- if (put_user(cmd.result, &ucmd->result))
- return -EFAULT;
- }
-
- return status;
-}
-
-static int nvme_subsys_reset(struct nvme_dev *dev)
-{
- if (!dev->subsystem)
- return -ENOTTY;
-
- writel(0x4E564D65, &dev->bar->nssr); /* "NVMe" */
- return 0;
-}
-
-static int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd,
- unsigned long arg)
-{
- struct nvme_ns *ns = bdev->bd_disk->private_data;
-
- switch (cmd) {
- case NVME_IOCTL_ID:
- force_successful_syscall_return();
- return ns->ns_id;
- case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(ns->dev, NULL, (void __user *)arg);
- case NVME_IOCTL_IO_CMD:
- return nvme_user_cmd(ns->dev, ns, (void __user *)arg);
- case NVME_IOCTL_SUBMIT_IO:
- return nvme_submit_io(ns, (void __user *)arg);
- case SG_GET_VERSION_NUM:
- return nvme_sg_get_version_num((void __user *)arg);
- case SG_IO:
- return nvme_sg_io(ns, (void __user *)arg);
- default:
- return -ENOTTY;
- }
-}
-
-#ifdef CONFIG_COMPAT
-static int nvme_compat_ioctl(struct block_device *bdev, fmode_t mode,
- unsigned int cmd, unsigned long arg)
-{
- switch (cmd) {
- case SG_IO:
- return -ENOIOCTLCMD;
- }
- return nvme_ioctl(bdev, mode, cmd, arg);
-}
-#else
-#define nvme_compat_ioctl NULL
-#endif
-
-static int nvme_open(struct block_device *bdev, fmode_t mode)
-{
- int ret = 0;
- struct nvme_ns *ns;
-
- spin_lock(&dev_list_lock);
- ns = bdev->bd_disk->private_data;
- if (!ns)
- ret = -ENXIO;
- else if (!kref_get_unless_zero(&ns->dev->kref))
- ret = -ENXIO;
- spin_unlock(&dev_list_lock);
-
- return ret;
-}
-
-static void nvme_free_dev(struct kref *kref);
-
-static void nvme_release(struct gendisk *disk, fmode_t mode)
-{
- struct nvme_ns *ns = disk->private_data;
- struct nvme_dev *dev = ns->dev;
-
- kref_put(&dev->kref, nvme_free_dev);
-}
-
-static int nvme_getgeo(struct block_device *bd, struct hd_geometry *geo)
-{
- /* some standard values */
- geo->heads = 1 << 6;
- geo->sectors = 1 << 5;
- geo->cylinders = get_capacity(bd->bd_disk) >> 11;
- return 0;
-}
-
-static void nvme_config_discard(struct nvme_ns *ns)
-{
- u32 logical_block_size = queue_logical_block_size(ns->queue);
- ns->queue->limits.discard_zeroes_data = 0;
- ns->queue->limits.discard_alignment = logical_block_size;
- ns->queue->limits.discard_granularity = logical_block_size;
- blk_queue_max_discard_sectors(ns->queue, 0xffffffff);
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
-}
-
-static int nvme_revalidate_disk(struct gendisk *disk)
-{
- struct nvme_ns *ns = disk->private_data;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id;
- u8 lbaf, pi_type;
- u16 old_ms;
- unsigned short bs;
-
- if (nvme_identify_ns(dev, ns->ns_id, &id)) {
- dev_warn(dev->dev, "%s: Identify failure nvme%dn%d\n", __func__,
- dev->instance, ns->ns_id);
- return -ENODEV;
- }
- if (id->ncap == 0) {
- kfree(id);
- return -ENODEV;
- }
-
- old_ms = ns->ms;
- lbaf = id->flbas & NVME_NS_FLBAS_LBA_MASK;
- ns->lba_shift = id->lbaf[lbaf].ds;
- ns->ms = le16_to_cpu(id->lbaf[lbaf].ms);
- ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
-
- /*
- * If identify namespace failed, use default 512 byte block size so
- * block layer can use before failing read/write for 0 capacity.
- */
- if (ns->lba_shift == 0)
- ns->lba_shift = 9;
- bs = 1 << ns->lba_shift;
-
- /* XXX: PI implementation requires metadata equal t10 pi tuple size */
- pi_type = ns->ms == sizeof(struct t10_pi_tuple) ?
- id->dps & NVME_NS_DPS_PI_MASK : 0;
-
- if (blk_get_integrity(disk) && (ns->pi_type != pi_type ||
- ns->ms != old_ms ||
- bs != queue_logical_block_size(disk->queue) ||
- (ns->ms && ns->ext)))
- blk_integrity_unregister(disk);
-
- ns->pi_type = pi_type;
- blk_queue_logical_block_size(ns->queue, bs);
-
- if (ns->ms && !blk_get_integrity(disk) && (disk->flags & GENHD_FL_UP) &&
- !ns->ext)
- nvme_init_integrity(ns);
-
- if (ns->ms && !(ns->ms == 8 && ns->pi_type) && !blk_get_integrity(disk))
- set_capacity(disk, 0);
- else
- set_capacity(disk, le64_to_cpup(&id->nsze) << (ns->lba_shift - 9));
-
- if (dev->oncs & NVME_CTRL_ONCS_DSM)
- nvme_config_discard(ns);
-
- kfree(id);
- return 0;
-}
-
-static const struct block_device_operations nvme_fops = {
- .owner = THIS_MODULE,
- .ioctl = nvme_ioctl,
- .compat_ioctl = nvme_compat_ioctl,
- .open = nvme_open,
- .release = nvme_release,
- .getgeo = nvme_getgeo,
- .revalidate_disk= nvme_revalidate_disk,
-};
-
-static int nvme_kthread(void *data)
-{
- struct nvme_dev *dev, *next;
-
- while (!kthread_should_stop()) {
- set_current_state(TASK_INTERRUPTIBLE);
- spin_lock(&dev_list_lock);
- list_for_each_entry_safe(dev, next, &dev_list, node) {
- int i;
- u32 csts = readl(&dev->bar->csts);
-
- if ((dev->subsystem && (csts & NVME_CSTS_NSSRO)) ||
- csts & NVME_CSTS_CFS) {
- if (work_busy(&dev->reset_work))
- continue;
- list_del_init(&dev->node);
- dev_warn(dev->dev,
- "Failed status: %x, reset controller\n",
- readl(&dev->bar->csts));
- dev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev->reset_work);
- continue;
- }
- for (i = 0; i < dev->queue_count; i++) {
- struct nvme_queue *nvmeq = dev->queues[i];
- if (!nvmeq)
- continue;
- spin_lock_irq(&nvmeq->q_lock);
- nvme_process_cq(nvmeq);
-
- while ((i == 0) && (dev->event_limit > 0)) {
- if (nvme_submit_async_admin_req(dev))
- break;
- dev->event_limit--;
- }
- spin_unlock_irq(&nvmeq->q_lock);
- }
- }
- spin_unlock(&dev_list_lock);
- schedule_timeout(round_jiffies_relative(HZ));
- }
- return 0;
-}
-
-static void nvme_alloc_ns(struct nvme_dev *dev, unsigned nsid)
-{
- struct nvme_ns *ns;
- struct gendisk *disk;
- int node = dev_to_node(dev->dev);
-
- ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node);
- if (!ns)
- return;
-
- ns->queue = blk_mq_init_queue(&dev->tagset);
- if (IS_ERR(ns->queue))
- goto out_free_ns;
- queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, ns->queue);
- queue_flag_set_unlocked(QUEUE_FLAG_NONROT, ns->queue);
- ns->dev = dev;
- ns->queue->queuedata = ns;
-
- disk = alloc_disk_node(0, node);
- if (!disk)
- goto out_free_queue;
-
- ns->ns_id = nsid;
- ns->disk = disk;
- ns->lba_shift = 9; /* set to a default value for 512 until disk is validated */
- list_add_tail(&ns->list, &dev->namespaces);
-
- blk_queue_logical_block_size(ns->queue, 1 << ns->lba_shift);
- if (dev->max_hw_sectors) {
- blk_queue_max_hw_sectors(ns->queue, dev->max_hw_sectors);
- blk_queue_max_segments(ns->queue,
- ((dev->max_hw_sectors << 9) / dev->page_size) + 1);
- }
- if (dev->stripe_size)
- blk_queue_chunk_sectors(ns->queue, dev->stripe_size >> 9);
- if (dev->vwc & NVME_CTRL_VWC_PRESENT)
- blk_queue_flush(ns->queue, REQ_FLUSH | REQ_FUA);
- blk_queue_virt_boundary(ns->queue, dev->page_size - 1);
-
- disk->major = nvme_major;
- disk->first_minor = 0;
- disk->fops = &nvme_fops;
- disk->private_data = ns;
- disk->queue = ns->queue;
- disk->driverfs_dev = dev->device;
- disk->flags = GENHD_FL_EXT_DEVT;
- sprintf(disk->disk_name, "nvme%dn%d", dev->instance, nsid);
-
- /*
- * Initialize capacity to 0 until we establish the namespace format and
- * setup integrity extentions if necessary. The revalidate_disk after
- * add_disk allows the driver to register with integrity if the format
- * requires it.
- */
- set_capacity(disk, 0);
- if (nvme_revalidate_disk(ns->disk))
- goto out_free_disk;
-
- add_disk(ns->disk);
- if (ns->ms) {
- struct block_device *bd = bdget_disk(ns->disk, 0);
- if (!bd)
- return;
- if (blkdev_get(bd, FMODE_READ, NULL)) {
- bdput(bd);
- return;
- }
- blkdev_reread_part(bd);
- blkdev_put(bd, FMODE_READ);
- }
- return;
- out_free_disk:
- kfree(disk);
- list_del(&ns->list);
- out_free_queue:
- blk_cleanup_queue(ns->queue);
- out_free_ns:
- kfree(ns);
-}
-
-static void nvme_create_io_queues(struct nvme_dev *dev)
-{
- unsigned i;
-
- for (i = dev->queue_count; i <= dev->max_qid; i++)
- if (!nvme_alloc_queue(dev, i, dev->q_depth))
- break;
-
- for (i = dev->online_queues; i <= dev->queue_count - 1; i++)
- if (nvme_create_queue(dev->queues[i], i))
- break;
-}
-
-static int set_queue_count(struct nvme_dev *dev, int count)
-{
- int status;
- u32 result;
- u32 q_count = (count - 1) | ((count - 1) << 16);
-
- status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, q_count, 0,
- &result);
- if (status < 0)
- return status;
- if (status > 0) {
- dev_err(dev->dev, "Could not set queue count (%d)\n", status);
- return 0;
- }
- return min(result & 0xffff, result >> 16) + 1;
-}
-
-static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
-{
- u64 szu, size, offset;
- u32 cmbloc;
- resource_size_t bar_size;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- void __iomem *cmb;
- dma_addr_t dma_addr;
-
- if (!use_cmb_sqes)
- return NULL;
-
- dev->cmbsz = readl(&dev->bar->cmbsz);
- if (!(NVME_CMB_SZ(dev->cmbsz)))
- return NULL;
-
- cmbloc = readl(&dev->bar->cmbloc);
-
- szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
- size = szu * NVME_CMB_SZ(dev->cmbsz);
- offset = szu * NVME_CMB_OFST(cmbloc);
- bar_size = pci_resource_len(pdev, NVME_CMB_BIR(cmbloc));
-
- if (offset > bar_size)
- return NULL;
-
- /*
- * Controllers may support a CMB size larger than their BAR,
- * for example, due to being behind a bridge. Reduce the CMB to
- * the reported size of the BAR
- */
- if (size > bar_size - offset)
- size = bar_size - offset;
-
- dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(cmbloc)) + offset;
- cmb = ioremap_wc(dma_addr, size);
- if (!cmb)
- return NULL;
-
- dev->cmb_dma_addr = dma_addr;
- dev->cmb_size = size;
- return cmb;
-}
-
-static inline void nvme_release_cmb(struct nvme_dev *dev)
-{
- if (dev->cmb) {
- iounmap(dev->cmb);
- dev->cmb = NULL;
- }
-}
-
-static size_t db_bar_size(struct nvme_dev *dev, unsigned nr_io_queues)
-{
- return 4096 + ((nr_io_queues + 1) * 8 * dev->db_stride);
-}
-
-static int nvme_setup_io_queues(struct nvme_dev *dev)
-{
- struct nvme_queue *adminq = dev->queues[0];
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- int result, i, vecs, nr_io_queues, size;
-
- nr_io_queues = num_possible_cpus();
- result = set_queue_count(dev, nr_io_queues);
- if (result <= 0)
- return result;
- if (result < nr_io_queues)
- nr_io_queues = result;
-
- if (dev->cmb && NVME_CMB_SQS(dev->cmbsz)) {
- result = nvme_cmb_qdepth(dev, nr_io_queues,
- sizeof(struct nvme_command));
- if (result > 0)
- dev->q_depth = result;
- else
- nvme_release_cmb(dev);
- }
-
- size = db_bar_size(dev, nr_io_queues);
- if (size > 8192) {
- iounmap(dev->bar);
- do {
- dev->bar = ioremap(pci_resource_start(pdev, 0), size);
- if (dev->bar)
- break;
- if (!--nr_io_queues)
- return -ENOMEM;
- size = db_bar_size(dev, nr_io_queues);
- } while (1);
- dev->dbs = ((void __iomem *)dev->bar) + 4096;
- adminq->q_db = dev->dbs;
- }
-
- /* Deregister the admin queue's interrupt */
- free_irq(dev->entry[0].vector, adminq);
-
- /*
- * If we enable msix early due to not intx, disable it again before
- * setting up the full range we need.
- */
- if (!pdev->irq)
- pci_disable_msix(pdev);
-
- for (i = 0; i < nr_io_queues; i++)
- dev->entry[i].entry = i;
- vecs = pci_enable_msix_range(pdev, dev->entry, 1, nr_io_queues);
- if (vecs < 0) {
- vecs = pci_enable_msi_range(pdev, 1, min(nr_io_queues, 32));
- if (vecs < 0) {
- vecs = 1;
- } else {
- for (i = 0; i < vecs; i++)
- dev->entry[i].vector = i + pdev->irq;
- }
- }
-
- /*
- * Should investigate if there's a performance win from allocating
- * more queues than interrupt vectors; it might allow the submission
- * path to scale better, even if the receive path is limited by the
- * number of interrupts.
- */
- nr_io_queues = vecs;
- dev->max_qid = nr_io_queues;
-
- result = queue_request_irq(dev, adminq, adminq->irqname);
- if (result) {
- adminq->cq_vector = -1;
- goto free_queues;
- }
-
- /* Free previously allocated queues that are no longer usable */
- nvme_free_queues(dev, nr_io_queues + 1);
- nvme_create_io_queues(dev);
-
- return 0;
-
- free_queues:
- nvme_free_queues(dev, 1);
- return result;
-}
-
-static void nvme_free_namespace(struct nvme_ns *ns)
-{
- list_del(&ns->list);
-
- spin_lock(&dev_list_lock);
- ns->disk->private_data = NULL;
- spin_unlock(&dev_list_lock);
-
- put_disk(ns->disk);
- kfree(ns);
-}
-
-static int ns_cmp(void *priv, struct list_head *a, struct list_head *b)
-{
- struct nvme_ns *nsa = container_of(a, struct nvme_ns, list);
- struct nvme_ns *nsb = container_of(b, struct nvme_ns, list);
-
- return nsa->ns_id - nsb->ns_id;
-}
-
-static struct nvme_ns *nvme_find_ns(struct nvme_dev *dev, unsigned nsid)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- if (ns->ns_id == nsid)
- return ns;
- if (ns->ns_id > nsid)
- break;
- }
- return NULL;
-}
-
-static inline bool nvme_io_incapable(struct nvme_dev *dev)
-{
- return (!dev->bar || readl(&dev->bar->csts) & NVME_CSTS_CFS ||
- dev->online_queues < 2);
-}
-
-static void nvme_ns_remove(struct nvme_ns *ns)
-{
- bool kill = nvme_io_incapable(ns->dev) && !blk_queue_dying(ns->queue);
-
- if (kill)
- blk_set_queue_dying(ns->queue);
- if (ns->disk->flags & GENHD_FL_UP) {
- if (blk_get_integrity(ns->disk))
- blk_integrity_unregister(ns->disk);
- del_gendisk(ns->disk);
- }
- if (kill || !blk_queue_dying(ns->queue)) {
- blk_mq_abort_requeue_list(ns->queue);
- blk_cleanup_queue(ns->queue);
- }
-}
-
-static void nvme_scan_namespaces(struct nvme_dev *dev, unsigned nn)
-{
- struct nvme_ns *ns, *next;
- unsigned i;
-
- for (i = 1; i <= nn; i++) {
- ns = nvme_find_ns(dev, i);
- if (ns) {
- if (revalidate_disk(ns->disk)) {
- nvme_ns_remove(ns);
- nvme_free_namespace(ns);
- }
- } else
- nvme_alloc_ns(dev, i);
- }
- list_for_each_entry_safe(ns, next, &dev->namespaces, list) {
- if (ns->ns_id > nn) {
- nvme_ns_remove(ns);
- nvme_free_namespace(ns);
- }
- }
- list_sort(NULL, &dev->namespaces, ns_cmp);
-}
-
-static void nvme_set_irq_hints(struct nvme_dev *dev)
-{
- struct nvme_queue *nvmeq;
- int i;
-
- for (i = 0; i < dev->online_queues; i++) {
- nvmeq = dev->queues[i];
-
- if (!nvmeq->tags || !(*nvmeq->tags))
- continue;
-
- irq_set_affinity_hint(dev->entry[nvmeq->cq_vector].vector,
- blk_mq_tags_cpumask(*nvmeq->tags));
- }
-}
-
-static void nvme_dev_scan(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev, scan_work);
- struct nvme_id_ctrl *ctrl;
-
- if (!dev->tagset.tags)
- return;
- if (nvme_identify_ctrl(dev, &ctrl))
- return;
- nvme_scan_namespaces(dev, le32_to_cpup(&ctrl->nn));
- kfree(ctrl);
- nvme_set_irq_hints(dev);
-}
-
-/*
- * Return: error value if an error occurred setting up the queues or calling
- * Identify Device. 0 if these succeeded, even if adding some of the
- * namespaces failed. At the moment, these failures are silent. TBD which
- * failures should be reported.
- */
-static int nvme_dev_add(struct nvme_dev *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev->dev);
- int res;
- struct nvme_id_ctrl *ctrl;
- int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12;
-
- res = nvme_identify_ctrl(dev, &ctrl);
- if (res) {
- dev_err(dev->dev, "Identify Controller failed (%d)\n", res);
- return -EIO;
- }
-
- dev->oncs = le16_to_cpup(&ctrl->oncs);
- dev->abort_limit = ctrl->acl + 1;
- dev->vwc = ctrl->vwc;
- memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn));
- memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn));
- memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr));
- if (ctrl->mdts)
- dev->max_hw_sectors = 1 << (ctrl->mdts + shift - 9);
- if ((pdev->vendor == PCI_VENDOR_ID_INTEL) &&
- (pdev->device == 0x0953) && ctrl->vs[3]) {
- unsigned int max_hw_sectors;
-
- dev->stripe_size = 1 << (ctrl->vs[3] + shift);
- max_hw_sectors = dev->stripe_size >> (shift - 9);
- if (dev->max_hw_sectors) {
- dev->max_hw_sectors = min(max_hw_sectors,
- dev->max_hw_sectors);
- } else
- dev->max_hw_sectors = max_hw_sectors;
- }
- kfree(ctrl);
-
- if (!dev->tagset.tags) {
- dev->tagset.ops = &nvme_mq_ops;
- dev->tagset.nr_hw_queues = dev->online_queues - 1;
- dev->tagset.timeout = NVME_IO_TIMEOUT;
- dev->tagset.numa_node = dev_to_node(dev->dev);
- dev->tagset.queue_depth =
- min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1;
- dev->tagset.cmd_size = nvme_cmd_size(dev);
- dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE;
- dev->tagset.driver_data = dev;
-
- if (blk_mq_alloc_tag_set(&dev->tagset))
- return 0;
- }
- schedule_work(&dev->scan_work);
- return 0;
-}
-
-static int nvme_dev_map(struct nvme_dev *dev)
-{
- u64 cap;
- int bars, result = -ENOMEM;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pci_enable_device_mem(pdev))
- return result;
-
- dev->entry[0].vector = pdev->irq;
- pci_set_master(pdev);
- bars = pci_select_bars(pdev, IORESOURCE_MEM);
- if (!bars)
- goto disable_pci;
-
- if (pci_request_selected_regions(pdev, bars, "nvme"))
- goto disable_pci;
-
- if (dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(64)) &&
- dma_set_mask_and_coherent(dev->dev, DMA_BIT_MASK(32)))
- goto disable;
-
- dev->bar = ioremap(pci_resource_start(pdev, 0), 8192);
- if (!dev->bar)
- goto disable;
-
- if (readl(&dev->bar->csts) == -1) {
- result = -ENODEV;
- goto unmap;
- }
-
- /*
- * Some devices don't advertse INTx interrupts, pre-enable a single
- * MSIX vec for setup. We'll adjust this later.
- */
- if (!pdev->irq) {
- result = pci_enable_msix(pdev, dev->entry, 1);
- if (result < 0)
- goto unmap;
- }
-
- cap = readq(&dev->bar->cap);
- dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH);
- dev->db_stride = 1 << NVME_CAP_STRIDE(cap);
- dev->dbs = ((void __iomem *)dev->bar) + 4096;
- if (readl(&dev->bar->vs) >= NVME_VS(1, 2))
- dev->cmb = nvme_map_cmb(dev);
-
- return 0;
-
- unmap:
- iounmap(dev->bar);
- dev->bar = NULL;
- disable:
- pci_release_regions(pdev);
- disable_pci:
- pci_disable_device(pdev);
- return result;
-}
-
-static void nvme_dev_unmap(struct nvme_dev *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pdev->msi_enabled)
- pci_disable_msi(pdev);
- else if (pdev->msix_enabled)
- pci_disable_msix(pdev);
-
- if (dev->bar) {
- iounmap(dev->bar);
- dev->bar = NULL;
- pci_release_regions(pdev);
- }
-
- if (pci_is_enabled(pdev))
- pci_disable_device(pdev);
-}
-
-struct nvme_delq_ctx {
- struct task_struct *waiter;
- struct kthread_worker *worker;
- atomic_t refcount;
-};
-
-static void nvme_wait_dq(struct nvme_delq_ctx *dq, struct nvme_dev *dev)
-{
- dq->waiter = current;
- mb();
-
- for (;;) {
- set_current_state(TASK_KILLABLE);
- if (!atomic_read(&dq->refcount))
- break;
- if (!schedule_timeout(ADMIN_TIMEOUT) ||
- fatal_signal_pending(current)) {
- /*
- * Disable the controller first since we can't trust it
- * at this point, but leave the admin queue enabled
- * until all queue deletion requests are flushed.
- * FIXME: This may take a while if there are more h/w
- * queues than admin tags.
- */
- set_current_state(TASK_RUNNING);
- nvme_disable_ctrl(dev, readq(&dev->bar->cap));
- nvme_clear_queue(dev->queues[0]);
- flush_kthread_worker(dq->worker);
- nvme_disable_queue(dev, 0);
- return;
- }
- }
- set_current_state(TASK_RUNNING);
-}
-
-static void nvme_put_dq(struct nvme_delq_ctx *dq)
-{
- atomic_dec(&dq->refcount);
- if (dq->waiter)
- wake_up_process(dq->waiter);
-}
-
-static struct nvme_delq_ctx *nvme_get_dq(struct nvme_delq_ctx *dq)
-{
- atomic_inc(&dq->refcount);
- return dq;
-}
-
-static void nvme_del_queue_end(struct nvme_queue *nvmeq)
-{
- struct nvme_delq_ctx *dq = nvmeq->cmdinfo.ctx;
- nvme_put_dq(dq);
-}
-
-static int adapter_async_del_queue(struct nvme_queue *nvmeq, u8 opcode,
- kthread_work_func_t fn)
-{
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.delete_queue.opcode = opcode;
- c.delete_queue.qid = cpu_to_le16(nvmeq->qid);
-
- init_kthread_work(&nvmeq->cmdinfo.work, fn);
- return nvme_submit_admin_async_cmd(nvmeq->dev, &c, &nvmeq->cmdinfo,
- ADMIN_TIMEOUT);
-}
-
-static void nvme_del_cq_work_handler(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
- cmdinfo.work);
- nvme_del_queue_end(nvmeq);
-}
-
-static int nvme_delete_cq(struct nvme_queue *nvmeq)
-{
- return adapter_async_del_queue(nvmeq, nvme_admin_delete_cq,
- nvme_del_cq_work_handler);
-}
-
-static void nvme_del_sq_work_handler(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
- cmdinfo.work);
- int status = nvmeq->cmdinfo.status;
-
- if (!status)
- status = nvme_delete_cq(nvmeq);
- if (status)
- nvme_del_queue_end(nvmeq);
-}
-
-static int nvme_delete_sq(struct nvme_queue *nvmeq)
-{
- return adapter_async_del_queue(nvmeq, nvme_admin_delete_sq,
- nvme_del_sq_work_handler);
-}
-
-static void nvme_del_queue_start(struct kthread_work *work)
-{
- struct nvme_queue *nvmeq = container_of(work, struct nvme_queue,
- cmdinfo.work);
- if (nvme_delete_sq(nvmeq))
- nvme_del_queue_end(nvmeq);
-}
-
-static void nvme_disable_io_queues(struct nvme_dev *dev)
-{
- int i;
- DEFINE_KTHREAD_WORKER_ONSTACK(worker);
- struct nvme_delq_ctx dq;
- struct task_struct *kworker_task = kthread_run(kthread_worker_fn,
- &worker, "nvme%d", dev->instance);
-
- if (IS_ERR(kworker_task)) {
- dev_err(dev->dev,
- "Failed to create queue del task\n");
- for (i = dev->queue_count - 1; i > 0; i--)
- nvme_disable_queue(dev, i);
- return;
- }
-
- dq.waiter = NULL;
- atomic_set(&dq.refcount, 0);
- dq.worker = &worker;
- for (i = dev->queue_count - 1; i > 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
-
- if (nvme_suspend_queue(nvmeq))
- continue;
- nvmeq->cmdinfo.ctx = nvme_get_dq(&dq);
- nvmeq->cmdinfo.worker = dq.worker;
- init_kthread_work(&nvmeq->cmdinfo.work, nvme_del_queue_start);
- queue_kthread_work(dq.worker, &nvmeq->cmdinfo.work);
- }
- nvme_wait_dq(&dq, dev);
- kthread_stop(kworker_task);
-}
-
-/*
-* Remove the node from the device list and check
-* for whether or not we need to stop the nvme_thread.
-*/
-static void nvme_dev_list_remove(struct nvme_dev *dev)
-{
- struct task_struct *tmp = NULL;
-
- spin_lock(&dev_list_lock);
- list_del_init(&dev->node);
- if (list_empty(&dev_list) && !IS_ERR_OR_NULL(nvme_thread)) {
- tmp = nvme_thread;
- nvme_thread = NULL;
- }
- spin_unlock(&dev_list_lock);
-
- if (tmp)
- kthread_stop(tmp);
-}
-
-static void nvme_freeze_queues(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- blk_mq_freeze_queue_start(ns->queue);
-
- spin_lock_irq(ns->queue->queue_lock);
- queue_flag_set(QUEUE_FLAG_STOPPED, ns->queue);
- spin_unlock_irq(ns->queue->queue_lock);
-
- blk_mq_cancel_requeue_work(ns->queue);
- blk_mq_stop_hw_queues(ns->queue);
- }
-}
-
-static void nvme_unfreeze_queues(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list) {
- queue_flag_clear_unlocked(QUEUE_FLAG_STOPPED, ns->queue);
- blk_mq_unfreeze_queue(ns->queue);
- blk_mq_start_stopped_hw_queues(ns->queue, true);
- blk_mq_kick_requeue_list(ns->queue);
- }
-}
-
-static void nvme_dev_shutdown(struct nvme_dev *dev)
-{
- int i;
- u32 csts = -1;
-
- nvme_dev_list_remove(dev);
-
- if (dev->bar) {
- nvme_freeze_queues(dev);
- csts = readl(&dev->bar->csts);
- }
- if (csts & NVME_CSTS_CFS || !(csts & NVME_CSTS_RDY)) {
- for (i = dev->queue_count - 1; i >= 0; i--) {
- struct nvme_queue *nvmeq = dev->queues[i];
- nvme_suspend_queue(nvmeq);
- }
- } else {
- nvme_disable_io_queues(dev);
- nvme_shutdown_ctrl(dev);
- nvme_disable_queue(dev, 0);
- }
- nvme_dev_unmap(dev);
-
- for (i = dev->queue_count - 1; i >= 0; i--)
- nvme_clear_queue(dev->queues[i]);
-}
-
-static void nvme_dev_remove(struct nvme_dev *dev)
-{
- struct nvme_ns *ns;
-
- list_for_each_entry(ns, &dev->namespaces, list)
- nvme_ns_remove(ns);
-}
-
-static int nvme_setup_prp_pools(struct nvme_dev *dev)
-{
- dev->prp_page_pool = dma_pool_create("prp list page", dev->dev,
- PAGE_SIZE, PAGE_SIZE, 0);
- if (!dev->prp_page_pool)
- return -ENOMEM;
-
- /* Optimisation for I/Os between 4k and 128k */
- dev->prp_small_pool = dma_pool_create("prp list 256", dev->dev,
- 256, 256, 0);
- if (!dev->prp_small_pool) {
- dma_pool_destroy(dev->prp_page_pool);
- return -ENOMEM;
- }
- return 0;
-}
-
-static void nvme_release_prp_pools(struct nvme_dev *dev)
-{
- dma_pool_destroy(dev->prp_page_pool);
- dma_pool_destroy(dev->prp_small_pool);
-}
-
-static DEFINE_IDA(nvme_instance_ida);
-
-static int nvme_set_instance(struct nvme_dev *dev)
-{
- int instance, error;
-
- do {
- if (!ida_pre_get(&nvme_instance_ida, GFP_KERNEL))
- return -ENODEV;
-
- spin_lock(&dev_list_lock);
- error = ida_get_new(&nvme_instance_ida, &instance);
- spin_unlock(&dev_list_lock);
- } while (error == -EAGAIN);
-
- if (error)
- return -ENODEV;
-
- dev->instance = instance;
- return 0;
-}
-
-static void nvme_release_instance(struct nvme_dev *dev)
-{
- spin_lock(&dev_list_lock);
- ida_remove(&nvme_instance_ida, dev->instance);
- spin_unlock(&dev_list_lock);
-}
-
-static void nvme_free_namespaces(struct nvme_dev *dev)
-{
- struct nvme_ns *ns, *next;
-
- list_for_each_entry_safe(ns, next, &dev->namespaces, list)
- nvme_free_namespace(ns);
-}
-
-static void nvme_free_dev(struct kref *kref)
-{
- struct nvme_dev *dev = container_of(kref, struct nvme_dev, kref);
-
- put_device(dev->dev);
- put_device(dev->device);
- nvme_free_namespaces(dev);
- nvme_release_instance(dev);
- if (dev->tagset.tags)
- blk_mq_free_tag_set(&dev->tagset);
- if (dev->admin_q)
- blk_put_queue(dev->admin_q);
- kfree(dev->queues);
- kfree(dev->entry);
- kfree(dev);
-}
-
-static int nvme_dev_open(struct inode *inode, struct file *f)
-{
- struct nvme_dev *dev;
- int instance = iminor(inode);
- int ret = -ENODEV;
-
- spin_lock(&dev_list_lock);
- list_for_each_entry(dev, &dev_list, node) {
- if (dev->instance == instance) {
- if (!dev->admin_q) {
- ret = -EWOULDBLOCK;
- break;
- }
- if (!kref_get_unless_zero(&dev->kref))
- break;
- f->private_data = dev;
- ret = 0;
- break;
- }
- }
- spin_unlock(&dev_list_lock);
-
- return ret;
-}
-
-static int nvme_dev_release(struct inode *inode, struct file *f)
-{
- struct nvme_dev *dev = f->private_data;
- kref_put(&dev->kref, nvme_free_dev);
- return 0;
-}
-
-static long nvme_dev_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
-{
- struct nvme_dev *dev = f->private_data;
- struct nvme_ns *ns;
-
- switch (cmd) {
- case NVME_IOCTL_ADMIN_CMD:
- return nvme_user_cmd(dev, NULL, (void __user *)arg);
- case NVME_IOCTL_IO_CMD:
- if (list_empty(&dev->namespaces))
- return -ENOTTY;
- ns = list_first_entry(&dev->namespaces, struct nvme_ns, list);
- return nvme_user_cmd(dev, ns, (void __user *)arg);
- case NVME_IOCTL_RESET:
- dev_warn(dev->dev, "resetting controller\n");
- return nvme_reset(dev);
- case NVME_IOCTL_SUBSYS_RESET:
- return nvme_subsys_reset(dev);
- default:
- return -ENOTTY;
- }
-}
-
-static const struct file_operations nvme_dev_fops = {
- .owner = THIS_MODULE,
- .open = nvme_dev_open,
- .release = nvme_dev_release,
- .unlocked_ioctl = nvme_dev_ioctl,
- .compat_ioctl = nvme_dev_ioctl,
-};
-
-static int nvme_dev_start(struct nvme_dev *dev)
-{
- int result;
- bool start_thread = false;
-
- result = nvme_dev_map(dev);
- if (result)
- return result;
-
- result = nvme_configure_admin_queue(dev);
- if (result)
- goto unmap;
-
- spin_lock(&dev_list_lock);
- if (list_empty(&dev_list) && IS_ERR_OR_NULL(nvme_thread)) {
- start_thread = true;
- nvme_thread = NULL;
- }
- list_add(&dev->node, &dev_list);
- spin_unlock(&dev_list_lock);
-
- if (start_thread) {
- nvme_thread = kthread_run(nvme_kthread, NULL, "nvme");
- wake_up_all(&nvme_kthread_wait);
- } else
- wait_event_killable(nvme_kthread_wait, nvme_thread);
-
- if (IS_ERR_OR_NULL(nvme_thread)) {
- result = nvme_thread ? PTR_ERR(nvme_thread) : -EINTR;
- goto disable;
- }
-
- nvme_init_queue(dev->queues[0], 0);
- result = nvme_alloc_admin_tags(dev);
- if (result)
- goto disable;
-
- result = nvme_setup_io_queues(dev);
- if (result)
- goto free_tags;
-
- dev->event_limit = 1;
- return result;
-
- free_tags:
- nvme_dev_remove_admin(dev);
- blk_put_queue(dev->admin_q);
- dev->admin_q = NULL;
- dev->queues[0]->tags = NULL;
- disable:
- nvme_disable_queue(dev, 0);
- nvme_dev_list_remove(dev);
- unmap:
- nvme_dev_unmap(dev);
- return result;
-}
-
-static int nvme_remove_dead_ctrl(void *arg)
-{
- struct nvme_dev *dev = (struct nvme_dev *)arg;
- struct pci_dev *pdev = to_pci_dev(dev->dev);
-
- if (pci_get_drvdata(pdev))
- pci_stop_and_remove_bus_device_locked(pdev);
- kref_put(&dev->kref, nvme_free_dev);
- return 0;
-}
-
-static void nvme_remove_disks(struct work_struct *ws)
-{
- struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
-
- nvme_free_queues(dev, 1);
- nvme_dev_remove(dev);
-}
-
-static int nvme_dev_resume(struct nvme_dev *dev)
-{
- int ret;
-
- ret = nvme_dev_start(dev);
- if (ret)
- return ret;
- if (dev->online_queues < 2) {
- spin_lock(&dev_list_lock);
- dev->reset_workfn = nvme_remove_disks;
- queue_work(nvme_workq, &dev->reset_work);
- spin_unlock(&dev_list_lock);
- } else {
- nvme_unfreeze_queues(dev);
- nvme_dev_add(dev);
- }
- return 0;
-}
-
-static void nvme_dead_ctrl(struct nvme_dev *dev)
-{
- dev_warn(dev->dev, "Device failed to resume\n");
- kref_get(&dev->kref);
- if (IS_ERR(kthread_run(nvme_remove_dead_ctrl, dev, "nvme%d",
- dev->instance))) {
- dev_err(dev->dev,
- "Failed to start controller remove task\n");
- kref_put(&dev->kref, nvme_free_dev);
- }
-}
-
-static void nvme_dev_reset(struct nvme_dev *dev)
-{
- bool in_probe = work_busy(&dev->probe_work);
-
- nvme_dev_shutdown(dev);
-
- /* Synchronize with device probe so that work will see failure status
- * and exit gracefully without trying to schedule another reset */
- flush_work(&dev->probe_work);
-
- /* Fail this device if reset occured during probe to avoid
- * infinite initialization loops. */
- if (in_probe) {
- nvme_dead_ctrl(dev);
- return;
- }
- /* Schedule device resume asynchronously so the reset work is available
- * to cleanup errors that may occur during reinitialization */
- schedule_work(&dev->probe_work);
-}
-
-static void nvme_reset_failed_dev(struct work_struct *ws)
-{
- struct nvme_dev *dev = container_of(ws, struct nvme_dev, reset_work);
- nvme_dev_reset(dev);
-}
-
-static void nvme_reset_workfn(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
- dev->reset_workfn(work);
-}
-
-static int nvme_reset(struct nvme_dev *dev)
-{
- int ret = -EBUSY;
-
- if (!dev->admin_q || blk_queue_dying(dev->admin_q))
- return -ENODEV;
-
- spin_lock(&dev_list_lock);
- if (!work_pending(&dev->reset_work)) {
- dev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &dev->reset_work);
- ret = 0;
- }
- spin_unlock(&dev_list_lock);
-
- if (!ret) {
- flush_work(&dev->reset_work);
- flush_work(&dev->probe_work);
- return 0;
- }
-
- return ret;
-}
-
-static ssize_t nvme_sysfs_reset(struct device *dev,
- struct device_attribute *attr, const char *buf,
- size_t count)
-{
- struct nvme_dev *ndev = dev_get_drvdata(dev);
- int ret;
-
- ret = nvme_reset(ndev);
- if (ret < 0)
- return ret;
-
- return count;
-}
-static DEVICE_ATTR(reset_controller, S_IWUSR, NULL, nvme_sysfs_reset);
-
-static void nvme_async_probe(struct work_struct *work);
-static int nvme_probe(struct pci_dev *pdev, const struct pci_device_id *id)
-{
- int node, result = -ENOMEM;
- struct nvme_dev *dev;
-
- node = dev_to_node(&pdev->dev);
- if (node == NUMA_NO_NODE)
- set_dev_node(&pdev->dev, 0);
-
- dev = kzalloc_node(sizeof(*dev), GFP_KERNEL, node);
- if (!dev)
- return -ENOMEM;
- dev->entry = kzalloc_node(num_possible_cpus() * sizeof(*dev->entry),
- GFP_KERNEL, node);
- if (!dev->entry)
- goto free;
- dev->queues = kzalloc_node((num_possible_cpus() + 1) * sizeof(void *),
- GFP_KERNEL, node);
- if (!dev->queues)
- goto free;
-
- INIT_LIST_HEAD(&dev->namespaces);
- dev->reset_workfn = nvme_reset_failed_dev;
- INIT_WORK(&dev->reset_work, nvme_reset_workfn);
- dev->dev = get_device(&pdev->dev);
- pci_set_drvdata(pdev, dev);
- result = nvme_set_instance(dev);
- if (result)
- goto put_pci;
-
- result = nvme_setup_prp_pools(dev);
- if (result)
- goto release;
-
- kref_init(&dev->kref);
- dev->device = device_create(nvme_class, &pdev->dev,
- MKDEV(nvme_char_major, dev->instance),
- dev, "nvme%d", dev->instance);
- if (IS_ERR(dev->device)) {
- result = PTR_ERR(dev->device);
- goto release_pools;
- }
- get_device(dev->device);
- dev_set_drvdata(dev->device, dev);
-
- result = device_create_file(dev->device, &dev_attr_reset_controller);
- if (result)
- goto put_dev;
-
- INIT_LIST_HEAD(&dev->node);
- INIT_WORK(&dev->scan_work, nvme_dev_scan);
- INIT_WORK(&dev->probe_work, nvme_async_probe);
- schedule_work(&dev->probe_work);
- return 0;
-
- put_dev:
- device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
- put_device(dev->device);
- release_pools:
- nvme_release_prp_pools(dev);
- release:
- nvme_release_instance(dev);
- put_pci:
- put_device(dev->dev);
- free:
- kfree(dev->queues);
- kfree(dev->entry);
- kfree(dev);
- return result;
-}
-
-static void nvme_async_probe(struct work_struct *work)
-{
- struct nvme_dev *dev = container_of(work, struct nvme_dev, probe_work);
-
- if (nvme_dev_resume(dev) && !work_busy(&dev->reset_work))
- nvme_dead_ctrl(dev);
-}
-
-static void nvme_reset_notify(struct pci_dev *pdev, bool prepare)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
-
- if (prepare)
- nvme_dev_shutdown(dev);
- else
- nvme_dev_resume(dev);
-}
-
-static void nvme_shutdown(struct pci_dev *pdev)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
- nvme_dev_shutdown(dev);
-}
-
-static void nvme_remove(struct pci_dev *pdev)
-{
- struct nvme_dev *dev = pci_get_drvdata(pdev);
-
- spin_lock(&dev_list_lock);
- list_del_init(&dev->node);
- spin_unlock(&dev_list_lock);
-
- pci_set_drvdata(pdev, NULL);
- flush_work(&dev->probe_work);
- flush_work(&dev->reset_work);
- flush_work(&dev->scan_work);
- device_remove_file(dev->device, &dev_attr_reset_controller);
- nvme_dev_remove(dev);
- nvme_dev_shutdown(dev);
- nvme_dev_remove_admin(dev);
- device_destroy(nvme_class, MKDEV(nvme_char_major, dev->instance));
- nvme_free_queues(dev, 0);
- nvme_release_cmb(dev);
- nvme_release_prp_pools(dev);
- kref_put(&dev->kref, nvme_free_dev);
-}
-
-/* These functions are yet to be implemented */
-#define nvme_error_detected NULL
-#define nvme_dump_registers NULL
-#define nvme_link_reset NULL
-#define nvme_slot_reset NULL
-#define nvme_error_resume NULL
-
-#ifdef CONFIG_PM_SLEEP
-static int nvme_suspend(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct nvme_dev *ndev = pci_get_drvdata(pdev);
-
- nvme_dev_shutdown(ndev);
- return 0;
-}
-
-static int nvme_resume(struct device *dev)
-{
- struct pci_dev *pdev = to_pci_dev(dev);
- struct nvme_dev *ndev = pci_get_drvdata(pdev);
-
- if (nvme_dev_resume(ndev) && !work_busy(&ndev->reset_work)) {
- ndev->reset_workfn = nvme_reset_failed_dev;
- queue_work(nvme_workq, &ndev->reset_work);
- }
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(nvme_dev_pm_ops, nvme_suspend, nvme_resume);
-
-static const struct pci_error_handlers nvme_err_handler = {
- .error_detected = nvme_error_detected,
- .mmio_enabled = nvme_dump_registers,
- .link_reset = nvme_link_reset,
- .slot_reset = nvme_slot_reset,
- .resume = nvme_error_resume,
- .reset_notify = nvme_reset_notify,
-};
-
-/* Move to pci_ids.h later */
-#define PCI_CLASS_STORAGE_EXPRESS 0x010802
-
-static const struct pci_device_id nvme_id_table[] = {
- { PCI_DEVICE_CLASS(PCI_CLASS_STORAGE_EXPRESS, 0xffffff) },
- { 0, }
-};
-MODULE_DEVICE_TABLE(pci, nvme_id_table);
-
-static struct pci_driver nvme_driver = {
- .name = "nvme",
- .id_table = nvme_id_table,
- .probe = nvme_probe,
- .remove = nvme_remove,
- .shutdown = nvme_shutdown,
- .driver = {
- .pm = &nvme_dev_pm_ops,
- },
- .err_handler = &nvme_err_handler,
-};
-
-static int __init nvme_init(void)
-{
- int result;
-
- init_waitqueue_head(&nvme_kthread_wait);
-
- nvme_workq = create_singlethread_workqueue("nvme");
- if (!nvme_workq)
- return -ENOMEM;
-
- result = register_blkdev(nvme_major, "nvme");
- if (result < 0)
- goto kill_workq;
- else if (result > 0)
- nvme_major = result;
-
- result = __register_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme",
- &nvme_dev_fops);
- if (result < 0)
- goto unregister_blkdev;
- else if (result > 0)
- nvme_char_major = result;
-
- nvme_class = class_create(THIS_MODULE, "nvme");
- if (IS_ERR(nvme_class)) {
- result = PTR_ERR(nvme_class);
- goto unregister_chrdev;
- }
-
- result = pci_register_driver(&nvme_driver);
- if (result)
- goto destroy_class;
- return 0;
-
- destroy_class:
- class_destroy(nvme_class);
- unregister_chrdev:
- __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
- unregister_blkdev:
- unregister_blkdev(nvme_major, "nvme");
- kill_workq:
- destroy_workqueue(nvme_workq);
- return result;
-}
-
-static void __exit nvme_exit(void)
-{
- pci_unregister_driver(&nvme_driver);
- unregister_blkdev(nvme_major, "nvme");
- destroy_workqueue(nvme_workq);
- class_destroy(nvme_class);
- __unregister_chrdev(nvme_char_major, 0, NVME_MINORS, "nvme");
- BUG_ON(nvme_thread && !IS_ERR(nvme_thread));
- _nvme_check_size();
-}
-
-MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>");
-MODULE_LICENSE("GPL");
-MODULE_VERSION("1.0");
-module_init(nvme_init);
-module_exit(nvme_exit);
diff --git a/drivers/block/nvme-scsi.c b/drivers/block/nvme-scsi.c
deleted file mode 100644
index e5a63f06fb0f..000000000000
--- a/drivers/block/nvme-scsi.c
+++ /dev/null
@@ -1,2556 +0,0 @@
-/*
- * NVM Express device driver
- * Copyright (c) 2011-2014, Intel Corporation.
- *
- * 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.
- */
-
-/*
- * Refer to the SCSI-NVMe Translation spec for details on how
- * each command is translated.
- */
-
-#include <linux/nvme.h>
-#include <linux/bio.h>
-#include <linux/bitops.h>
-#include <linux/blkdev.h>
-#include <linux/compat.h>
-#include <linux/delay.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/genhd.h>
-#include <linux/idr.h>
-#include <linux/init.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/kdev_t.h>
-#include <linux/kthread.h>
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/pci.h>
-#include <linux/poison.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <asm/unaligned.h>
-#include <scsi/sg.h>
-#include <scsi/scsi.h>
-
-
-static int sg_version_num = 30534; /* 2 digits for each component */
-
-/* VPD Page Codes */
-#define VPD_SUPPORTED_PAGES 0x00
-#define VPD_SERIAL_NUMBER 0x80
-#define VPD_DEVICE_IDENTIFIERS 0x83
-#define VPD_EXTENDED_INQUIRY 0x86
-#define VPD_BLOCK_LIMITS 0xB0
-#define VPD_BLOCK_DEV_CHARACTERISTICS 0xB1
-
-/* format unit paramter list offsets */
-#define FORMAT_UNIT_SHORT_PARM_LIST_LEN 4
-#define FORMAT_UNIT_LONG_PARM_LIST_LEN 8
-#define FORMAT_UNIT_PROT_INT_OFFSET 3
-#define FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET 0
-#define FORMAT_UNIT_PROT_FIELD_USAGE_MASK 0x07
-
-/* Misc. defines */
-#define FIXED_SENSE_DATA 0x70
-#define DESC_FORMAT_SENSE_DATA 0x72
-#define FIXED_SENSE_DATA_ADD_LENGTH 10
-#define LUN_ENTRY_SIZE 8
-#define LUN_DATA_HEADER_SIZE 8
-#define ALL_LUNS_RETURNED 0x02
-#define ALL_WELL_KNOWN_LUNS_RETURNED 0x01
-#define RESTRICTED_LUNS_RETURNED 0x00
-#define NVME_POWER_STATE_START_VALID 0x00
-#define NVME_POWER_STATE_ACTIVE 0x01
-#define NVME_POWER_STATE_IDLE 0x02
-#define NVME_POWER_STATE_STANDBY 0x03
-#define NVME_POWER_STATE_LU_CONTROL 0x07
-#define POWER_STATE_0 0
-#define POWER_STATE_1 1
-#define POWER_STATE_2 2
-#define POWER_STATE_3 3
-#define DOWNLOAD_SAVE_ACTIVATE 0x05
-#define DOWNLOAD_SAVE_DEFER_ACTIVATE 0x0E
-#define ACTIVATE_DEFERRED_MICROCODE 0x0F
-#define FORMAT_UNIT_IMMED_MASK 0x2
-#define FORMAT_UNIT_IMMED_OFFSET 1
-#define KELVIN_TEMP_FACTOR 273
-#define FIXED_FMT_SENSE_DATA_SIZE 18
-#define DESC_FMT_SENSE_DATA_SIZE 8
-
-/* SCSI/NVMe defines and bit masks */
-#define INQ_STANDARD_INQUIRY_PAGE 0x00
-#define INQ_SUPPORTED_VPD_PAGES_PAGE 0x00
-#define INQ_UNIT_SERIAL_NUMBER_PAGE 0x80
-#define INQ_DEVICE_IDENTIFICATION_PAGE 0x83
-#define INQ_EXTENDED_INQUIRY_DATA_PAGE 0x86
-#define INQ_BDEV_LIMITS_PAGE 0xB0
-#define INQ_BDEV_CHARACTERISTICS_PAGE 0xB1
-#define INQ_SERIAL_NUMBER_LENGTH 0x14
-#define INQ_NUM_SUPPORTED_VPD_PAGES 6
-#define VERSION_SPC_4 0x06
-#define ACA_UNSUPPORTED 0
-#define STANDARD_INQUIRY_LENGTH 36
-#define ADDITIONAL_STD_INQ_LENGTH 31
-#define EXTENDED_INQUIRY_DATA_PAGE_LENGTH 0x3C
-#define RESERVED_FIELD 0
-
-/* Mode Sense/Select defines */
-#define MODE_PAGE_INFO_EXCEP 0x1C
-#define MODE_PAGE_CACHING 0x08
-#define MODE_PAGE_CONTROL 0x0A
-#define MODE_PAGE_POWER_CONDITION 0x1A
-#define MODE_PAGE_RETURN_ALL 0x3F
-#define MODE_PAGE_BLK_DES_LEN 0x08
-#define MODE_PAGE_LLBAA_BLK_DES_LEN 0x10
-#define MODE_PAGE_CACHING_LEN 0x14
-#define MODE_PAGE_CONTROL_LEN 0x0C
-#define MODE_PAGE_POW_CND_LEN 0x28
-#define MODE_PAGE_INF_EXC_LEN 0x0C
-#define MODE_PAGE_ALL_LEN 0x54
-#define MODE_SENSE6_MPH_SIZE 4
-#define MODE_SENSE_PAGE_CONTROL_MASK 0xC0
-#define MODE_SENSE_PAGE_CODE_OFFSET 2
-#define MODE_SENSE_PAGE_CODE_MASK 0x3F
-#define MODE_SENSE_LLBAA_MASK 0x10
-#define MODE_SENSE_LLBAA_SHIFT 4
-#define MODE_SENSE_DBD_MASK 8
-#define MODE_SENSE_DBD_SHIFT 3
-#define MODE_SENSE10_MPH_SIZE 8
-#define MODE_SELECT_CDB_PAGE_FORMAT_MASK 0x10
-#define MODE_SELECT_CDB_SAVE_PAGES_MASK 0x1
-#define MODE_SELECT_6_BD_OFFSET 3
-#define MODE_SELECT_10_BD_OFFSET 6
-#define MODE_SELECT_10_LLBAA_OFFSET 4
-#define MODE_SELECT_10_LLBAA_MASK 1
-#define MODE_SELECT_6_MPH_SIZE 4
-#define MODE_SELECT_10_MPH_SIZE 8
-#define CACHING_MODE_PAGE_WCE_MASK 0x04
-#define MODE_SENSE_BLK_DESC_ENABLED 0
-#define MODE_SENSE_BLK_DESC_COUNT 1
-#define MODE_SELECT_PAGE_CODE_MASK 0x3F
-#define SHORT_DESC_BLOCK 8
-#define LONG_DESC_BLOCK 16
-#define MODE_PAGE_POW_CND_LEN_FIELD 0x26
-#define MODE_PAGE_INF_EXC_LEN_FIELD 0x0A
-#define MODE_PAGE_CACHING_LEN_FIELD 0x12
-#define MODE_PAGE_CONTROL_LEN_FIELD 0x0A
-#define MODE_SENSE_PC_CURRENT_VALUES 0
-
-/* Log Sense defines */
-#define LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE 0x00
-#define LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH 0x07
-#define LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE 0x2F
-#define LOG_PAGE_TEMPERATURE_PAGE 0x0D
-#define LOG_SENSE_CDB_SP_NOT_ENABLED 0
-#define LOG_SENSE_CDB_PC_MASK 0xC0
-#define LOG_SENSE_CDB_PC_SHIFT 6
-#define LOG_SENSE_CDB_PC_CUMULATIVE_VALUES 1
-#define LOG_SENSE_CDB_PAGE_CODE_MASK 0x3F
-#define REMAINING_INFO_EXCP_PAGE_LENGTH 0x8
-#define LOG_INFO_EXCP_PAGE_LENGTH 0xC
-#define REMAINING_TEMP_PAGE_LENGTH 0xC
-#define LOG_TEMP_PAGE_LENGTH 0x10
-#define LOG_TEMP_UNKNOWN 0xFF
-#define SUPPORTED_LOG_PAGES_PAGE_LENGTH 0x3
-
-/* Read Capacity defines */
-#define READ_CAP_10_RESP_SIZE 8
-#define READ_CAP_16_RESP_SIZE 32
-
-/* NVMe Namespace and Command Defines */
-#define BYTES_TO_DWORDS 4
-#define NVME_MAX_FIRMWARE_SLOT 7
-
-/* Report LUNs defines */
-#define REPORT_LUNS_FIRST_LUN_OFFSET 8
-
-/* SCSI ADDITIONAL SENSE Codes */
-
-#define SCSI_ASC_NO_SENSE 0x00
-#define SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT 0x03
-#define SCSI_ASC_LUN_NOT_READY 0x04
-#define SCSI_ASC_WARNING 0x0B
-#define SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED 0x10
-#define SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED 0x10
-#define SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED 0x10
-#define SCSI_ASC_UNRECOVERED_READ_ERROR 0x11
-#define SCSI_ASC_MISCOMPARE_DURING_VERIFY 0x1D
-#define SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID 0x20
-#define SCSI_ASC_ILLEGAL_COMMAND 0x20
-#define SCSI_ASC_ILLEGAL_BLOCK 0x21
-#define SCSI_ASC_INVALID_CDB 0x24
-#define SCSI_ASC_INVALID_LUN 0x25
-#define SCSI_ASC_INVALID_PARAMETER 0x26
-#define SCSI_ASC_FORMAT_COMMAND_FAILED 0x31
-#define SCSI_ASC_INTERNAL_TARGET_FAILURE 0x44
-
-/* SCSI ADDITIONAL SENSE Code Qualifiers */
-
-#define SCSI_ASCQ_CAUSE_NOT_REPORTABLE 0x00
-#define SCSI_ASCQ_FORMAT_COMMAND_FAILED 0x01
-#define SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED 0x01
-#define SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED 0x02
-#define SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED 0x03
-#define SCSI_ASCQ_FORMAT_IN_PROGRESS 0x04
-#define SCSI_ASCQ_POWER_LOSS_EXPECTED 0x08
-#define SCSI_ASCQ_INVALID_LUN_ID 0x09
-
-/* copied from drivers/usb/gadget/function/storage_common.h */
-static inline u32 get_unaligned_be24(u8 *buf)
-{
- return 0xffffff & (u32) get_unaligned_be32(buf - 1);
-}
-
-/* Struct to gather data that needs to be extracted from a SCSI CDB.
- Not conforming to any particular CDB variant, but compatible with all. */
-
-struct nvme_trans_io_cdb {
- u8 fua;
- u8 prot_info;
- u64 lba;
- u32 xfer_len;
-};
-
-
-/* Internal Helper Functions */
-
-
-/* Copy data to userspace memory */
-
-static int nvme_trans_copy_to_user(struct sg_io_hdr *hdr, void *from,
- unsigned long n)
-{
- int i;
- void *index = from;
- size_t remaining = n;
- size_t xfer_len;
-
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- for (i = 0; i < hdr->iovec_count; i++) {
- if (copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct sg_iovec),
- sizeof(struct sg_iovec)))
- return -EFAULT;
- xfer_len = min(remaining, sgl.iov_len);
- if (copy_to_user(sgl.iov_base, index, xfer_len))
- return -EFAULT;
-
- index += xfer_len;
- remaining -= xfer_len;
- if (remaining == 0)
- break;
- }
- return 0;
- }
-
- if (copy_to_user(hdr->dxferp, from, n))
- return -EFAULT;
- return 0;
-}
-
-/* Copy data from userspace memory */
-
-static int nvme_trans_copy_from_user(struct sg_io_hdr *hdr, void *to,
- unsigned long n)
-{
- int i;
- void *index = to;
- size_t remaining = n;
- size_t xfer_len;
-
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- for (i = 0; i < hdr->iovec_count; i++) {
- if (copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct sg_iovec),
- sizeof(struct sg_iovec)))
- return -EFAULT;
- xfer_len = min(remaining, sgl.iov_len);
- if (copy_from_user(index, sgl.iov_base, xfer_len))
- return -EFAULT;
- index += xfer_len;
- remaining -= xfer_len;
- if (remaining == 0)
- break;
- }
- return 0;
- }
-
- if (copy_from_user(to, hdr->dxferp, n))
- return -EFAULT;
- return 0;
-}
-
-/* Status/Sense Buffer Writeback */
-
-static int nvme_trans_completion(struct sg_io_hdr *hdr, u8 status, u8 sense_key,
- u8 asc, u8 ascq)
-{
- u8 xfer_len;
- u8 resp[DESC_FMT_SENSE_DATA_SIZE];
-
- if (scsi_status_is_good(status)) {
- hdr->status = SAM_STAT_GOOD;
- hdr->masked_status = GOOD;
- hdr->host_status = DID_OK;
- hdr->driver_status = DRIVER_OK;
- hdr->sb_len_wr = 0;
- } else {
- hdr->status = status;
- hdr->masked_status = status >> 1;
- hdr->host_status = DID_OK;
- hdr->driver_status = DRIVER_OK;
-
- memset(resp, 0, DESC_FMT_SENSE_DATA_SIZE);
- resp[0] = DESC_FORMAT_SENSE_DATA;
- resp[1] = sense_key;
- resp[2] = asc;
- resp[3] = ascq;
-
- xfer_len = min_t(u8, hdr->mx_sb_len, DESC_FMT_SENSE_DATA_SIZE);
- hdr->sb_len_wr = xfer_len;
- if (copy_to_user(hdr->sbp, resp, xfer_len) > 0)
- return -EFAULT;
- }
-
- return 0;
-}
-
-/*
- * Take a status code from a lowlevel routine, and if it was a positive NVMe
- * error code update the sense data based on it. In either case the passed
- * in value is returned again, unless an -EFAULT from copy_to_user overrides
- * it.
- */
-static int nvme_trans_status_code(struct sg_io_hdr *hdr, int nvme_sc)
-{
- u8 status, sense_key, asc, ascq;
- int res;
-
- /* For non-nvme (Linux) errors, simply return the error code */
- if (nvme_sc < 0)
- return nvme_sc;
-
- /* Mask DNR, More, and reserved fields */
- switch (nvme_sc & 0x7FF) {
- /* Generic Command Status */
- case NVME_SC_SUCCESS:
- status = SAM_STAT_GOOD;
- sense_key = NO_SENSE;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_OPCODE:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ILLEGAL_COMMAND;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_FIELD:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_INVALID_CDB;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_DATA_XFER_ERROR:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_POWER_LOSS:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_WARNING;
- ascq = SCSI_ASCQ_POWER_LOSS_EXPECTED;
- break;
- case NVME_SC_INTERNAL:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = HARDWARE_ERROR;
- asc = SCSI_ASC_INTERNAL_TARGET_FAILURE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ABORT_REQ:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ABORT_QUEUE:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_FUSED_FAIL:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_FUSED_MISSING:
- status = SAM_STAT_TASK_ABORTED;
- sense_key = ABORTED_COMMAND;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_INVALID_NS:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
- ascq = SCSI_ASCQ_INVALID_LUN_ID;
- break;
- case NVME_SC_LBA_RANGE:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ILLEGAL_BLOCK;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_CAP_EXCEEDED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_NS_NOT_READY:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = NOT_READY;
- asc = SCSI_ASC_LUN_NOT_READY;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
-
- /* Command Specific Status */
- case NVME_SC_INVALID_FORMAT:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_FORMAT_COMMAND_FAILED;
- ascq = SCSI_ASCQ_FORMAT_COMMAND_FAILED;
- break;
- case NVME_SC_BAD_ATTRIBUTES:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_INVALID_CDB;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
-
- /* Media Errors */
- case NVME_SC_WRITE_FAULT:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_PERIPHERAL_DEV_WRITE_FAULT;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_READ_ERROR:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_UNRECOVERED_READ_ERROR;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_GUARD_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_GUARD_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_GUARD_CHECK_FAILED;
- break;
- case NVME_SC_APPTAG_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_APPTAG_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_APPTAG_CHECK_FAILED;
- break;
- case NVME_SC_REFTAG_CHECK:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MEDIUM_ERROR;
- asc = SCSI_ASC_LOG_BLOCK_REFTAG_CHECK_FAILED;
- ascq = SCSI_ASCQ_LOG_BLOCK_REFTAG_CHECK_FAILED;
- break;
- case NVME_SC_COMPARE_FAILED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = MISCOMPARE;
- asc = SCSI_ASC_MISCOMPARE_DURING_VERIFY;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- case NVME_SC_ACCESS_DENIED:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_ACCESS_DENIED_INVALID_LUN_ID;
- ascq = SCSI_ASCQ_INVALID_LUN_ID;
- break;
-
- /* Unspecified/Default */
- case NVME_SC_CMDID_CONFLICT:
- case NVME_SC_CMD_SEQ_ERROR:
- case NVME_SC_CQ_INVALID:
- case NVME_SC_QID_INVALID:
- case NVME_SC_QUEUE_SIZE:
- case NVME_SC_ABORT_LIMIT:
- case NVME_SC_ABORT_MISSING:
- case NVME_SC_ASYNC_LIMIT:
- case NVME_SC_FIRMWARE_SLOT:
- case NVME_SC_FIRMWARE_IMAGE:
- case NVME_SC_INVALID_VECTOR:
- case NVME_SC_INVALID_LOG_PAGE:
- default:
- status = SAM_STAT_CHECK_CONDITION;
- sense_key = ILLEGAL_REQUEST;
- asc = SCSI_ASC_NO_SENSE;
- ascq = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- break;
- }
-
- res = nvme_trans_completion(hdr, status, sense_key, asc, ascq);
- return res ? res : nvme_sc;
-}
-
-/* INQUIRY Helper Functions */
-
-static int nvme_trans_standard_inquiry_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *inq_response,
- int alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- int res;
- int nvme_sc;
- int xfer_len;
- u8 resp_data_format = 0x02;
- u8 protect;
- u8 cmdque = 0x01 << 1;
- u8 fw_offset = sizeof(dev->firmware_rev);
-
- /* nvme ns identify - use DPS value for PROTECT field */
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- if (id_ns->dps)
- protect = 0x01;
- else
- protect = 0;
- kfree(id_ns);
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[2] = VERSION_SPC_4;
- inq_response[3] = resp_data_format; /*normaca=0 | hisup=0 */
- inq_response[4] = ADDITIONAL_STD_INQ_LENGTH;
- inq_response[5] = protect; /* sccs=0 | acc=0 | tpgs=0 | pc3=0 */
- inq_response[7] = cmdque; /* wbus16=0 | sync=0 | vs=0 */
- strncpy(&inq_response[8], "NVMe ", 8);
- strncpy(&inq_response[16], dev->model, 16);
-
- while (dev->firmware_rev[fw_offset - 1] == ' ' && fw_offset > 4)
- fw_offset--;
- fw_offset -= 4;
- strncpy(&inq_response[32], dev->firmware_rev + fw_offset, 4);
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_supported_vpd_pages(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *inq_response,
- int alloc_len)
-{
- int xfer_len;
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = INQ_SUPPORTED_VPD_PAGES_PAGE; /* Page Code */
- inq_response[3] = INQ_NUM_SUPPORTED_VPD_PAGES; /* Page Length */
- inq_response[4] = INQ_SUPPORTED_VPD_PAGES_PAGE;
- inq_response[5] = INQ_UNIT_SERIAL_NUMBER_PAGE;
- inq_response[6] = INQ_DEVICE_IDENTIFICATION_PAGE;
- inq_response[7] = INQ_EXTENDED_INQUIRY_DATA_PAGE;
- inq_response[8] = INQ_BDEV_CHARACTERISTICS_PAGE;
- inq_response[9] = INQ_BDEV_LIMITS_PAGE;
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_unit_serial_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *inq_response,
- int alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- int xfer_len;
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = INQ_UNIT_SERIAL_NUMBER_PAGE; /* Page Code */
- inq_response[3] = INQ_SERIAL_NUMBER_LENGTH; /* Page Length */
- strncpy(&inq_response[4], dev->serial, INQ_SERIAL_NUMBER_LENGTH);
-
- xfer_len = min(alloc_len, STANDARD_INQUIRY_LENGTH);
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_device_id_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *inq_response, int alloc_len)
-{
- struct nvme_dev *dev = ns->dev;
- int res;
- int nvme_sc;
- int xfer_len;
- __be32 tmp_id = cpu_to_be32(ns->ns_id);
-
- memset(inq_response, 0, alloc_len);
- inq_response[1] = INQ_DEVICE_IDENTIFICATION_PAGE; /* Page Code */
- if (readl(&dev->bar->vs) >= NVME_VS(1, 1)) {
- struct nvme_id_ns *id_ns;
- void *eui;
- int len;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- eui = id_ns->eui64;
- len = sizeof(id_ns->eui64);
- if (readl(&dev->bar->vs) >= NVME_VS(1, 2)) {
- if (bitmap_empty(eui, len * 8)) {
- eui = id_ns->nguid;
- len = sizeof(id_ns->nguid);
- }
- }
- if (bitmap_empty(eui, len * 8)) {
- kfree(id_ns);
- goto scsi_string;
- }
-
- inq_response[3] = 4 + len; /* Page Length */
- /* Designation Descriptor start */
- inq_response[4] = 0x01; /* Proto ID=0h | Code set=1h */
- inq_response[5] = 0x02; /* PIV=0b | Asso=00b | Designator Type=2h */
- inq_response[6] = 0x00; /* Rsvd */
- inq_response[7] = len; /* Designator Length */
- memcpy(&inq_response[8], eui, len);
- kfree(id_ns);
- } else {
- scsi_string:
- if (alloc_len < 72) {
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
- inq_response[3] = 0x48; /* Page Length */
- /* Designation Descriptor start */
- inq_response[4] = 0x03; /* Proto ID=0h | Code set=3h */
- inq_response[5] = 0x08; /* PIV=0b | Asso=00b | Designator Type=8h */
- inq_response[6] = 0x00; /* Rsvd */
- inq_response[7] = 0x44; /* Designator Length */
-
- sprintf(&inq_response[8], "%04x", to_pci_dev(dev->dev)->vendor);
- memcpy(&inq_response[12], dev->model, sizeof(dev->model));
- sprintf(&inq_response[52], "%04x", tmp_id);
- memcpy(&inq_response[56], dev->serial, sizeof(dev->serial));
- }
- xfer_len = alloc_len;
- return nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-}
-
-static int nvme_trans_ext_inq_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- int alloc_len)
-{
- u8 *inq_response;
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- struct nvme_id_ns *id_ns;
- int xfer_len;
- u8 microcode = 0x80;
- u8 spt;
- u8 spt_lut[8] = {0, 0, 2, 1, 4, 6, 5, 7};
- u8 grd_chk, app_chk, ref_chk, protect;
- u8 uask_sup = 0x20;
- u8 v_sup;
- u8 luiclr = 0x01;
-
- inq_response = kmalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
- if (inq_response == NULL)
- return -ENOMEM;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- goto out_free_inq;
-
- spt = spt_lut[id_ns->dpc & 0x07] << 3;
- if (id_ns->dps)
- protect = 0x01;
- else
- protect = 0;
- kfree(id_ns);
-
- grd_chk = protect << 2;
- app_chk = protect << 1;
- ref_chk = protect;
-
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- goto out_free_inq;
-
- v_sup = id_ctrl->vwc;
- kfree(id_ctrl);
-
- memset(inq_response, 0, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- inq_response[1] = INQ_EXTENDED_INQUIRY_DATA_PAGE; /* Page Code */
- inq_response[2] = 0x00; /* Page Length MSB */
- inq_response[3] = 0x3C; /* Page Length LSB */
- inq_response[4] = microcode | spt | grd_chk | app_chk | ref_chk;
- inq_response[5] = uask_sup;
- inq_response[6] = v_sup;
- inq_response[7] = luiclr;
- inq_response[8] = 0;
- inq_response[9] = 0;
-
- xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- out_free_inq:
- kfree(inq_response);
- return res;
-}
-
-static int nvme_trans_bdev_limits_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *inq_response, int alloc_len)
-{
- __be32 max_sectors = cpu_to_be32(
- nvme_block_nr(ns, queue_max_hw_sectors(ns->queue)));
- __be32 max_discard = cpu_to_be32(ns->queue->limits.max_discard_sectors);
- __be32 discard_desc_count = cpu_to_be32(0x100);
-
- memset(inq_response, 0, STANDARD_INQUIRY_LENGTH);
- inq_response[1] = VPD_BLOCK_LIMITS;
- inq_response[3] = 0x3c; /* Page Length */
- memcpy(&inq_response[8], &max_sectors, sizeof(u32));
- memcpy(&inq_response[20], &max_discard, sizeof(u32));
-
- if (max_discard)
- memcpy(&inq_response[24], &discard_desc_count, sizeof(u32));
-
- return nvme_trans_copy_to_user(hdr, inq_response, 0x3c);
-}
-
-static int nvme_trans_bdev_char_page(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- int alloc_len)
-{
- u8 *inq_response;
- int res;
- int xfer_len;
-
- inq_response = kzalloc(EXTENDED_INQUIRY_DATA_PAGE_LENGTH, GFP_KERNEL);
- if (inq_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- inq_response[1] = INQ_BDEV_CHARACTERISTICS_PAGE; /* Page Code */
- inq_response[2] = 0x00; /* Page Length MSB */
- inq_response[3] = 0x3C; /* Page Length LSB */
- inq_response[4] = 0x00; /* Medium Rotation Rate MSB */
- inq_response[5] = 0x01; /* Medium Rotation Rate LSB */
- inq_response[6] = 0x00; /* Form Factor */
-
- xfer_len = min(alloc_len, EXTENDED_INQUIRY_DATA_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, inq_response, xfer_len);
-
- kfree(inq_response);
- out_mem:
- return res;
-}
-
-/* LOG SENSE Helper Functions */
-
-static int nvme_trans_log_supp_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- int alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
-
- log_response = kzalloc(LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH, GFP_KERNEL);
- if (log_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- log_response[0] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = SUPPORTED_LOG_PAGES_PAGE_LENGTH;
- log_response[4] = LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE;
- log_response[5] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
- log_response[6] = LOG_PAGE_TEMPERATURE_PAGE;
-
- xfer_len = min(alloc_len, LOG_PAGE_SUPPORTED_LOG_PAGES_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- kfree(log_response);
- out_mem:
- return res;
-}
-
-static int nvme_trans_log_info_exceptions(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, int alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_smart_log *smart_log;
- u8 temp_c;
- u16 temp_k;
-
- log_response = kzalloc(LOG_INFO_EXCP_PAGE_LENGTH, GFP_KERNEL);
- if (log_response == NULL)
- return -ENOMEM;
-
- res = nvme_get_log_page(dev, &smart_log);
- if (res < 0)
- goto out_free_response;
-
- if (res != NVME_SC_SUCCESS) {
- temp_c = LOG_TEMP_UNKNOWN;
- } else {
- temp_k = (smart_log->temperature[1] << 8) +
- (smart_log->temperature[0]);
- temp_c = temp_k - KELVIN_TEMP_FACTOR;
- }
- kfree(smart_log);
-
- log_response[0] = LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = REMAINING_INFO_EXCP_PAGE_LENGTH;
- /* Informational Exceptions Log Parameter 1 Start */
- /* Parameter Code=0x0000 bytes 4,5 */
- log_response[6] = 0x23; /* DU=0, TSD=1, ETC=0, TMC=0, FMT_AND_LNK=11b */
- log_response[7] = 0x04; /* PARAMETER LENGTH */
- /* Add sense Code and qualifier = 0x00 each */
- /* Use Temperature from NVMe Get Log Page, convert to C from K */
- log_response[10] = temp_c;
-
- xfer_len = min(alloc_len, LOG_INFO_EXCP_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- out_free_response:
- kfree(log_response);
- return res;
-}
-
-static int nvme_trans_log_temperature(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- int alloc_len)
-{
- int res;
- int xfer_len;
- u8 *log_response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_smart_log *smart_log;
- u32 feature_resp;
- u8 temp_c_cur, temp_c_thresh;
- u16 temp_k;
-
- log_response = kzalloc(LOG_TEMP_PAGE_LENGTH, GFP_KERNEL);
- if (log_response == NULL)
- return -ENOMEM;
-
- res = nvme_get_log_page(dev, &smart_log);
- if (res < 0)
- goto out_free_response;
-
- if (res != NVME_SC_SUCCESS) {
- temp_c_cur = LOG_TEMP_UNKNOWN;
- } else {
- temp_k = (smart_log->temperature[1] << 8) +
- (smart_log->temperature[0]);
- temp_c_cur = temp_k - KELVIN_TEMP_FACTOR;
- }
- kfree(smart_log);
-
- /* Get Features for Temp Threshold */
- res = nvme_get_features(dev, NVME_FEAT_TEMP_THRESH, 0, 0,
- &feature_resp);
- if (res != NVME_SC_SUCCESS)
- temp_c_thresh = LOG_TEMP_UNKNOWN;
- else
- temp_c_thresh = (feature_resp & 0xFFFF) - KELVIN_TEMP_FACTOR;
-
- log_response[0] = LOG_PAGE_TEMPERATURE_PAGE;
- /* Subpage=0x00, Page Length MSB=0 */
- log_response[3] = REMAINING_TEMP_PAGE_LENGTH;
- /* Temperature Log Parameter 1 (Temperature) Start */
- /* Parameter Code = 0x0000 */
- log_response[6] = 0x01; /* Format and Linking = 01b */
- log_response[7] = 0x02; /* Parameter Length */
- /* Use Temperature from NVMe Get Log Page, convert to C from K */
- log_response[9] = temp_c_cur;
- /* Temperature Log Parameter 2 (Reference Temperature) Start */
- log_response[11] = 0x01; /* Parameter Code = 0x0001 */
- log_response[12] = 0x01; /* Format and Linking = 01b */
- log_response[13] = 0x02; /* Parameter Length */
- /* Use Temperature Thresh from NVMe Get Log Page, convert to C from K */
- log_response[15] = temp_c_thresh;
-
- xfer_len = min(alloc_len, LOG_TEMP_PAGE_LENGTH);
- res = nvme_trans_copy_to_user(hdr, log_response, xfer_len);
-
- out_free_response:
- kfree(log_response);
- return res;
-}
-
-/* MODE SENSE Helper Functions */
-
-static int nvme_trans_fill_mode_parm_hdr(u8 *resp, int len, u8 cdb10, u8 llbaa,
- u16 mode_data_length, u16 blk_desc_len)
-{
- /* Quick check to make sure I don't stomp on my own memory... */
- if ((cdb10 && len < 8) || (!cdb10 && len < 4))
- return -EINVAL;
-
- if (cdb10) {
- resp[0] = (mode_data_length & 0xFF00) >> 8;
- resp[1] = (mode_data_length & 0x00FF);
- resp[3] = 0x10 /* DPOFUA */;
- resp[4] = llbaa;
- resp[5] = RESERVED_FIELD;
- resp[6] = (blk_desc_len & 0xFF00) >> 8;
- resp[7] = (blk_desc_len & 0x00FF);
- } else {
- resp[0] = (mode_data_length & 0x00FF);
- resp[2] = 0x10 /* DPOFUA */;
- resp[3] = (blk_desc_len & 0x00FF);
- }
-
- return 0;
-}
-
-static int nvme_trans_fill_blk_desc(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *resp, int len, u8 llbaa)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 flbas;
- u32 lba_length;
-
- if (llbaa == 0 && len < MODE_PAGE_BLK_DES_LEN)
- return -EINVAL;
- else if (llbaa > 0 && len < MODE_PAGE_LLBAA_BLK_DES_LEN)
- return -EINVAL;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- flbas = (id_ns->flbas) & 0x0F;
- lba_length = (1 << (id_ns->lbaf[flbas].ds));
-
- if (llbaa == 0) {
- __be32 tmp_cap = cpu_to_be32(le64_to_cpu(id_ns->ncap));
- /* Byte 4 is reserved */
- __be32 tmp_len = cpu_to_be32(lba_length & 0x00FFFFFF);
-
- memcpy(resp, &tmp_cap, sizeof(u32));
- memcpy(&resp[4], &tmp_len, sizeof(u32));
- } else {
- __be64 tmp_cap = cpu_to_be64(le64_to_cpu(id_ns->ncap));
- __be32 tmp_len = cpu_to_be32(lba_length);
-
- memcpy(resp, &tmp_cap, sizeof(u64));
- /* Bytes 8, 9, 10, 11 are reserved */
- memcpy(&resp[12], &tmp_len, sizeof(u32));
- }
-
- kfree(id_ns);
- return res;
-}
-
-static int nvme_trans_fill_control_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *resp,
- int len)
-{
- if (len < MODE_PAGE_CONTROL_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_CONTROL;
- resp[1] = MODE_PAGE_CONTROL_LEN_FIELD;
- resp[2] = 0x0E; /* TST=000b, TMF_ONLY=0, DPICZ=1,
- * D_SENSE=1, GLTSD=1, RLEC=0 */
- resp[3] = 0x12; /* Q_ALGO_MODIFIER=1h, NUAR=0, QERR=01b */
- /* Byte 4: VS=0, RAC=0, UA_INT=0, SWP=0 */
- resp[5] = 0x40; /* ATO=0, TAS=1, ATMPE=0, RWWP=0, AUTOLOAD=0 */
- /* resp[6] and [7] are obsolete, thus zero */
- resp[8] = 0xFF; /* Busy timeout period = 0xffff */
- resp[9] = 0xFF;
- /* Bytes 10,11: Extended selftest completion time = 0x0000 */
-
- return 0;
-}
-
-static int nvme_trans_fill_caching_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *resp, int len)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- u32 feature_resp;
- u8 vwc;
-
- if (len < MODE_PAGE_CACHING_LEN)
- return -EINVAL;
-
- nvme_sc = nvme_get_features(dev, NVME_FEAT_VOLATILE_WC, 0, 0,
- &feature_resp);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- vwc = feature_resp & 0x00000001;
-
- resp[0] = MODE_PAGE_CACHING;
- resp[1] = MODE_PAGE_CACHING_LEN_FIELD;
- resp[2] = vwc << 2;
- return 0;
-}
-
-static int nvme_trans_fill_pow_cnd_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *resp,
- int len)
-{
- if (len < MODE_PAGE_POW_CND_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_POWER_CONDITION;
- resp[1] = MODE_PAGE_POW_CND_LEN_FIELD;
- /* All other bytes are zero */
-
- return 0;
-}
-
-static int nvme_trans_fill_inf_exc_page(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *resp,
- int len)
-{
- if (len < MODE_PAGE_INF_EXC_LEN)
- return -EINVAL;
-
- resp[0] = MODE_PAGE_INFO_EXCEP;
- resp[1] = MODE_PAGE_INF_EXC_LEN_FIELD;
- resp[2] = 0x88;
- /* All other bytes are zero */
-
- return 0;
-}
-
-static int nvme_trans_fill_all_pages(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *resp, int len)
-{
- int res;
- u16 mode_pages_offset_1 = 0;
- u16 mode_pages_offset_2, mode_pages_offset_3, mode_pages_offset_4;
-
- mode_pages_offset_2 = mode_pages_offset_1 + MODE_PAGE_CACHING_LEN;
- mode_pages_offset_3 = mode_pages_offset_2 + MODE_PAGE_CONTROL_LEN;
- mode_pages_offset_4 = mode_pages_offset_3 + MODE_PAGE_POW_CND_LEN;
-
- res = nvme_trans_fill_caching_page(ns, hdr, &resp[mode_pages_offset_1],
- MODE_PAGE_CACHING_LEN);
- if (res)
- return res;
- res = nvme_trans_fill_control_page(ns, hdr, &resp[mode_pages_offset_2],
- MODE_PAGE_CONTROL_LEN);
- if (res)
- return res;
- res = nvme_trans_fill_pow_cnd_page(ns, hdr, &resp[mode_pages_offset_3],
- MODE_PAGE_POW_CND_LEN);
- if (res)
- return res;
- return nvme_trans_fill_inf_exc_page(ns, hdr, &resp[mode_pages_offset_4],
- MODE_PAGE_INF_EXC_LEN);
-}
-
-static inline int nvme_trans_get_blk_desc_len(u8 dbd, u8 llbaa)
-{
- if (dbd == MODE_SENSE_BLK_DESC_ENABLED) {
- /* SPC-4: len = 8 x Num_of_descriptors if llbaa = 0, 16x if 1 */
- return 8 * (llbaa + 1) * MODE_SENSE_BLK_DESC_COUNT;
- } else {
- return 0;
- }
-}
-
-static int nvme_trans_mode_page_create(struct nvme_ns *ns,
- struct sg_io_hdr *hdr, u8 *cmd,
- u16 alloc_len, u8 cdb10,
- int (*mode_page_fill_func)
- (struct nvme_ns *,
- struct sg_io_hdr *hdr, u8 *, int),
- u16 mode_pages_tot_len)
-{
- int res;
- int xfer_len;
- u8 *response;
- u8 dbd, llbaa;
- u16 resp_size;
- int mph_size;
- u16 mode_pages_offset_1;
- u16 blk_desc_len, blk_desc_offset, mode_data_length;
-
- dbd = (cmd[1] & MODE_SENSE_DBD_MASK) >> MODE_SENSE_DBD_SHIFT;
- llbaa = (cmd[1] & MODE_SENSE_LLBAA_MASK) >> MODE_SENSE_LLBAA_SHIFT;
- mph_size = cdb10 ? MODE_SENSE10_MPH_SIZE : MODE_SENSE6_MPH_SIZE;
-
- blk_desc_len = nvme_trans_get_blk_desc_len(dbd, llbaa);
-
- resp_size = mph_size + blk_desc_len + mode_pages_tot_len;
- /* Refer spc4r34 Table 440 for calculation of Mode data Length field */
- mode_data_length = 3 + (3 * cdb10) + blk_desc_len + mode_pages_tot_len;
-
- blk_desc_offset = mph_size;
- mode_pages_offset_1 = blk_desc_offset + blk_desc_len;
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- res = nvme_trans_fill_mode_parm_hdr(&response[0], mph_size, cdb10,
- llbaa, mode_data_length, blk_desc_len);
- if (res)
- goto out_free;
- if (blk_desc_len > 0) {
- res = nvme_trans_fill_blk_desc(ns, hdr,
- &response[blk_desc_offset],
- blk_desc_len, llbaa);
- if (res)
- goto out_free;
- }
- res = mode_page_fill_func(ns, hdr, &response[mode_pages_offset_1],
- mode_pages_tot_len);
- if (res)
- goto out_free;
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- out_free:
- kfree(response);
- out_mem:
- return res;
-}
-
-/* Read Capacity Helper Functions */
-
-static void nvme_trans_fill_read_cap(u8 *response, struct nvme_id_ns *id_ns,
- u8 cdb16)
-{
- u8 flbas;
- u32 lba_length;
- u64 rlba;
- u8 prot_en;
- u8 p_type_lut[4] = {0, 0, 1, 2};
- __be64 tmp_rlba;
- __be32 tmp_rlba_32;
- __be32 tmp_len;
-
- flbas = (id_ns->flbas) & 0x0F;
- lba_length = (1 << (id_ns->lbaf[flbas].ds));
- rlba = le64_to_cpup(&id_ns->nsze) - 1;
- (id_ns->dps) ? (prot_en = 0x01) : (prot_en = 0);
-
- if (!cdb16) {
- if (rlba > 0xFFFFFFFF)
- rlba = 0xFFFFFFFF;
- tmp_rlba_32 = cpu_to_be32(rlba);
- tmp_len = cpu_to_be32(lba_length);
- memcpy(response, &tmp_rlba_32, sizeof(u32));
- memcpy(&response[4], &tmp_len, sizeof(u32));
- } else {
- tmp_rlba = cpu_to_be64(rlba);
- tmp_len = cpu_to_be32(lba_length);
- memcpy(response, &tmp_rlba, sizeof(u64));
- memcpy(&response[8], &tmp_len, sizeof(u32));
- response[12] = (p_type_lut[id_ns->dps & 0x3] << 1) | prot_en;
- /* P_I_Exponent = 0x0 | LBPPBE = 0x0 */
- /* LBPME = 0 | LBPRZ = 0 | LALBA = 0x00 */
- /* Bytes 16-31 - Reserved */
- }
-}
-
-/* Start Stop Unit Helper Functions */
-
-static int nvme_trans_power_state(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 pc, u8 pcmod, u8 start)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- int lowest_pow_st; /* max npss = lowest power consumption */
- unsigned ps_desired = 0;
-
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- lowest_pow_st = max(POWER_STATE_0, (int)(id_ctrl->npss - 1));
- kfree(id_ctrl);
-
- switch (pc) {
- case NVME_POWER_STATE_START_VALID:
- /* Action unspecified if POWER CONDITION MODIFIER != 0 */
- if (pcmod == 0 && start == 0x1)
- ps_desired = POWER_STATE_0;
- if (pcmod == 0 && start == 0x0)
- ps_desired = lowest_pow_st;
- break;
- case NVME_POWER_STATE_ACTIVE:
- /* Action unspecified if POWER CONDITION MODIFIER != 0 */
- if (pcmod == 0)
- ps_desired = POWER_STATE_0;
- break;
- case NVME_POWER_STATE_IDLE:
- /* Action unspecified if POWER CONDITION MODIFIER != [0,1,2] */
- if (pcmod == 0x0)
- ps_desired = POWER_STATE_1;
- else if (pcmod == 0x1)
- ps_desired = POWER_STATE_2;
- else if (pcmod == 0x2)
- ps_desired = POWER_STATE_3;
- break;
- case NVME_POWER_STATE_STANDBY:
- /* Action unspecified if POWER CONDITION MODIFIER != [0,1] */
- if (pcmod == 0x0)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 2));
- else if (pcmod == 0x1)
- ps_desired = max(POWER_STATE_0, (lowest_pow_st - 1));
- break;
- case NVME_POWER_STATE_LU_CONTROL:
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- nvme_sc = nvme_set_features(dev, NVME_FEAT_POWER_MGMT, ps_desired, 0,
- NULL);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_send_activate_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 buffer_id)
-{
- struct nvme_command c;
- int nvme_sc;
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_activate_fw;
- c.common.cdw10[0] = cpu_to_le32(buffer_id | NVME_FWACT_REPL_ACTV);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_send_download_fw_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 opcode, u32 tot_len, u32 offset,
- u8 buffer_id)
-{
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_command c;
-
- if (hdr->iovec_count > 0) {
- /* Assuming SGL is not allowed for this command */
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_admin_download_fw;
- c.dlfw.numd = cpu_to_le32((tot_len/BYTES_TO_DWORDS) - 1);
- c.dlfw.offset = cpu_to_le32(offset/BYTES_TO_DWORDS);
-
- nvme_sc = __nvme_submit_sync_cmd(dev->admin_q, &c, NULL,
- hdr->dxferp, tot_len, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-/* Mode Select Helper Functions */
-
-static inline void nvme_trans_modesel_get_bd_len(u8 *parm_list, u8 cdb10,
- u16 *bd_len, u8 *llbaa)
-{
- if (cdb10) {
- /* 10 Byte CDB */
- *bd_len = (parm_list[MODE_SELECT_10_BD_OFFSET] << 8) +
- parm_list[MODE_SELECT_10_BD_OFFSET + 1];
- *llbaa = parm_list[MODE_SELECT_10_LLBAA_OFFSET] &
- MODE_SELECT_10_LLBAA_MASK;
- } else {
- /* 6 Byte CDB */
- *bd_len = parm_list[MODE_SELECT_6_BD_OFFSET];
- }
-}
-
-static void nvme_trans_modesel_save_bd(struct nvme_ns *ns, u8 *parm_list,
- u16 idx, u16 bd_len, u8 llbaa)
-{
- u16 bd_num;
-
- bd_num = bd_len / ((llbaa == 0) ?
- SHORT_DESC_BLOCK : LONG_DESC_BLOCK);
- /* Store block descriptor info if a FORMAT UNIT comes later */
- /* TODO Saving 1st BD info; what to do if multiple BD received? */
- if (llbaa == 0) {
- /* Standard Block Descriptor - spc4r34 7.5.5.1 */
- ns->mode_select_num_blocks =
- (parm_list[idx + 1] << 16) +
- (parm_list[idx + 2] << 8) +
- (parm_list[idx + 3]);
-
- ns->mode_select_block_len =
- (parm_list[idx + 5] << 16) +
- (parm_list[idx + 6] << 8) +
- (parm_list[idx + 7]);
- } else {
- /* Long LBA Block Descriptor - sbc3r27 6.4.2.3 */
- ns->mode_select_num_blocks =
- (((u64)parm_list[idx + 0]) << 56) +
- (((u64)parm_list[idx + 1]) << 48) +
- (((u64)parm_list[idx + 2]) << 40) +
- (((u64)parm_list[idx + 3]) << 32) +
- (((u64)parm_list[idx + 4]) << 24) +
- (((u64)parm_list[idx + 5]) << 16) +
- (((u64)parm_list[idx + 6]) << 8) +
- ((u64)parm_list[idx + 7]);
-
- ns->mode_select_block_len =
- (parm_list[idx + 12] << 24) +
- (parm_list[idx + 13] << 16) +
- (parm_list[idx + 14] << 8) +
- (parm_list[idx + 15]);
- }
-}
-
-static int nvme_trans_modesel_get_mp(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *mode_page, u8 page_code)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- unsigned dword11;
-
- switch (page_code) {
- case MODE_PAGE_CACHING:
- dword11 = ((mode_page[2] & CACHING_MODE_PAGE_WCE_MASK) ? 1 : 0);
- nvme_sc = nvme_set_features(dev, NVME_FEAT_VOLATILE_WC, dword11,
- 0, NULL);
- res = nvme_trans_status_code(hdr, nvme_sc);
- break;
- case MODE_PAGE_CONTROL:
- break;
- case MODE_PAGE_POWER_CONDITION:
- /* Verify the OS is not trying to set timers */
- if ((mode_page[2] & 0x01) != 0 || (mode_page[3] & 0x0F) != 0) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- break;
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
-
- return res;
-}
-
-static int nvme_trans_modesel_data(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd, u16 parm_list_len, u8 pf,
- u8 sp, u8 cdb10)
-{
- int res;
- u8 *parm_list;
- u16 bd_len;
- u8 llbaa = 0;
- u16 index, saved_index;
- u8 page_code;
- u16 mp_size;
-
- /* Get parm list from data-in/out buffer */
- parm_list = kmalloc(parm_list_len, GFP_KERNEL);
- if (parm_list == NULL) {
- res = -ENOMEM;
- goto out;
- }
-
- res = nvme_trans_copy_from_user(hdr, parm_list, parm_list_len);
- if (res)
- goto out_mem;
-
- nvme_trans_modesel_get_bd_len(parm_list, cdb10, &bd_len, &llbaa);
- index = (cdb10) ? (MODE_SELECT_10_MPH_SIZE) : (MODE_SELECT_6_MPH_SIZE);
-
- if (bd_len != 0) {
- /* Block Descriptors present, parse */
- nvme_trans_modesel_save_bd(ns, parm_list, index, bd_len, llbaa);
- index += bd_len;
- }
- saved_index = index;
-
- /* Multiple mode pages may be present; iterate through all */
- /* In 1st Iteration, don't do NVME Command, only check for CDB errors */
- do {
- page_code = parm_list[index] & MODE_SELECT_PAGE_CODE_MASK;
- mp_size = parm_list[index + 1] + 2;
- if ((page_code != MODE_PAGE_CACHING) &&
- (page_code != MODE_PAGE_CONTROL) &&
- (page_code != MODE_PAGE_POWER_CONDITION)) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out_mem;
- }
- index += mp_size;
- } while (index < parm_list_len);
-
- /* In 2nd Iteration, do the NVME Commands */
- index = saved_index;
- do {
- page_code = parm_list[index] & MODE_SELECT_PAGE_CODE_MASK;
- mp_size = parm_list[index + 1] + 2;
- res = nvme_trans_modesel_get_mp(ns, hdr, &parm_list[index],
- page_code);
- if (res)
- break;
- index += mp_size;
- } while (index < parm_list_len);
-
- out_mem:
- kfree(parm_list);
- out:
- return res;
-}
-
-/* Format Unit Helper Functions */
-
-static int nvme_trans_fmt_set_blk_size_count(struct nvme_ns *ns,
- struct sg_io_hdr *hdr)
-{
- int res = 0;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- u8 flbas;
-
- /*
- * SCSI Expects a MODE SELECT would have been issued prior to
- * a FORMAT UNIT, and the block size and number would be used
- * from the block descriptor in it. If a MODE SELECT had not
- * been issued, FORMAT shall use the current values for both.
- */
-
- if (ns->mode_select_num_blocks == 0 || ns->mode_select_block_len == 0) {
- struct nvme_id_ns *id_ns;
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- if (ns->mode_select_num_blocks == 0)
- ns->mode_select_num_blocks = le64_to_cpu(id_ns->ncap);
- if (ns->mode_select_block_len == 0) {
- flbas = (id_ns->flbas) & 0x0F;
- ns->mode_select_block_len =
- (1 << (id_ns->lbaf[flbas].ds));
- }
-
- kfree(id_ns);
- }
-
- return 0;
-}
-
-static int nvme_trans_fmt_get_parm_header(struct sg_io_hdr *hdr, u8 len,
- u8 format_prot_info, u8 *nvme_pf_code)
-{
- int res;
- u8 *parm_list;
- u8 pf_usage, pf_code;
-
- parm_list = kmalloc(len, GFP_KERNEL);
- if (parm_list == NULL) {
- res = -ENOMEM;
- goto out;
- }
- res = nvme_trans_copy_from_user(hdr, parm_list, len);
- if (res)
- goto out_mem;
-
- if ((parm_list[FORMAT_UNIT_IMMED_OFFSET] &
- FORMAT_UNIT_IMMED_MASK) != 0) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out_mem;
- }
-
- if (len == FORMAT_UNIT_LONG_PARM_LIST_LEN &&
- (parm_list[FORMAT_UNIT_PROT_INT_OFFSET] & 0x0F) != 0) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out_mem;
- }
- pf_usage = parm_list[FORMAT_UNIT_PROT_FIELD_USAGE_OFFSET] &
- FORMAT_UNIT_PROT_FIELD_USAGE_MASK;
- pf_code = (pf_usage << 2) | format_prot_info;
- switch (pf_code) {
- case 0:
- *nvme_pf_code = 0;
- break;
- case 2:
- *nvme_pf_code = 1;
- break;
- case 3:
- *nvme_pf_code = 2;
- break;
- case 7:
- *nvme_pf_code = 3;
- break;
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
-
- out_mem:
- kfree(parm_list);
- out:
- return res;
-}
-
-static int nvme_trans_fmt_send_cmd(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 prot_info)
-{
- int res;
- int nvme_sc;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 i;
- u8 flbas, nlbaf;
- u8 selected_lbaf = 0xFF;
- u32 cdw10 = 0;
- struct nvme_command c;
-
- /* Loop thru LBAF's in id_ns to match reqd lbaf, put in cdw10 */
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- flbas = (id_ns->flbas) & 0x0F;
- nlbaf = id_ns->nlbaf;
-
- for (i = 0; i < nlbaf; i++) {
- if (ns->mode_select_block_len == (1 << (id_ns->lbaf[i].ds))) {
- selected_lbaf = i;
- break;
- }
- }
- if (selected_lbaf > 0x0F) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
- if (ns->mode_select_num_blocks != le64_to_cpu(id_ns->ncap)) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
-
- cdw10 |= prot_info << 5;
- cdw10 |= selected_lbaf & 0x0F;
- memset(&c, 0, sizeof(c));
- c.format.opcode = nvme_admin_format_nvm;
- c.format.nsid = cpu_to_le32(ns->ns_id);
- c.format.cdw10 = cpu_to_le32(cdw10);
-
- nvme_sc = nvme_submit_sync_cmd(dev->admin_q, &c, NULL, 0);
- res = nvme_trans_status_code(hdr, nvme_sc);
-
- kfree(id_ns);
- return res;
-}
-
-static inline u32 nvme_trans_io_get_num_cmds(struct sg_io_hdr *hdr,
- struct nvme_trans_io_cdb *cdb_info,
- u32 max_blocks)
-{
- /* If using iovecs, send one nvme command per vector */
- if (hdr->iovec_count > 0)
- return hdr->iovec_count;
- else if (cdb_info->xfer_len > max_blocks)
- return ((cdb_info->xfer_len - 1) / max_blocks) + 1;
- else
- return 1;
-}
-
-static u16 nvme_trans_io_get_control(struct nvme_ns *ns,
- struct nvme_trans_io_cdb *cdb_info)
-{
- u16 control = 0;
-
- /* When Protection information support is added, implement here */
-
- if (cdb_info->fua > 0)
- control |= NVME_RW_FUA;
-
- return control;
-}
-
-static int nvme_trans_do_nvme_io(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- struct nvme_trans_io_cdb *cdb_info, u8 is_write)
-{
- int nvme_sc = NVME_SC_SUCCESS;
- u32 num_cmds;
- u64 unit_len;
- u64 unit_num_blocks; /* Number of blocks to xfer in each nvme cmd */
- u32 retcode;
- u32 i = 0;
- u64 nvme_offset = 0;
- void __user *next_mapping_addr;
- struct nvme_command c;
- u8 opcode = (is_write ? nvme_cmd_write : nvme_cmd_read);
- u16 control;
- u32 max_blocks = queue_max_hw_sectors(ns->queue);
-
- num_cmds = nvme_trans_io_get_num_cmds(hdr, cdb_info, max_blocks);
-
- /*
- * This loop handles two cases.
- * First, when an SGL is used in the form of an iovec list:
- * - Use iov_base as the next mapping address for the nvme command_id
- * - Use iov_len as the data transfer length for the command.
- * Second, when we have a single buffer
- * - If larger than max_blocks, split into chunks, offset
- * each nvme command accordingly.
- */
- for (i = 0; i < num_cmds; i++) {
- memset(&c, 0, sizeof(c));
- if (hdr->iovec_count > 0) {
- struct sg_iovec sgl;
-
- retcode = copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct sg_iovec),
- sizeof(struct sg_iovec));
- if (retcode)
- return -EFAULT;
- unit_len = sgl.iov_len;
- unit_num_blocks = unit_len >> ns->lba_shift;
- next_mapping_addr = sgl.iov_base;
- } else {
- unit_num_blocks = min((u64)max_blocks,
- (cdb_info->xfer_len - nvme_offset));
- unit_len = unit_num_blocks << ns->lba_shift;
- next_mapping_addr = hdr->dxferp +
- ((1 << ns->lba_shift) * nvme_offset);
- }
-
- c.rw.opcode = opcode;
- c.rw.nsid = cpu_to_le32(ns->ns_id);
- c.rw.slba = cpu_to_le64(cdb_info->lba + nvme_offset);
- c.rw.length = cpu_to_le16(unit_num_blocks - 1);
- control = nvme_trans_io_get_control(ns, cdb_info);
- c.rw.control = cpu_to_le16(control);
-
- if (get_capacity(ns->disk) - unit_num_blocks <
- cdb_info->lba + nvme_offset) {
- nvme_sc = NVME_SC_LBA_RANGE;
- break;
- }
- nvme_sc = __nvme_submit_sync_cmd(ns->queue, &c, NULL,
- next_mapping_addr, unit_len, NULL, 0);
- if (nvme_sc)
- break;
-
- nvme_offset += unit_num_blocks;
- }
-
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-
-/* SCSI Command Translation Functions */
-
-static int nvme_trans_io(struct nvme_ns *ns, struct sg_io_hdr *hdr, u8 is_write,
- u8 *cmd)
-{
- int res = 0;
- struct nvme_trans_io_cdb cdb_info = { 0, };
- u8 opcode = cmd[0];
- u64 xfer_bytes;
- u64 sum_iov_len = 0;
- struct sg_iovec sgl;
- int i;
- size_t not_copied;
-
- /*
- * The FUA and WPROTECT fields are not supported in 6-byte CDBs,
- * but always in the same place for all others.
- */
- switch (opcode) {
- case WRITE_6:
- case READ_6:
- break;
- default:
- cdb_info.fua = cmd[1] & 0x8;
- cdb_info.prot_info = (cmd[1] & 0xe0) >> 5;
- if (cdb_info.prot_info && !ns->pi_type) {
- return nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
- }
-
- switch (opcode) {
- case WRITE_6:
- case READ_6:
- cdb_info.lba = get_unaligned_be24(&cmd[1]);
- cdb_info.xfer_len = cmd[4];
- if (cdb_info.xfer_len == 0)
- cdb_info.xfer_len = 256;
- break;
- case WRITE_10:
- case READ_10:
- cdb_info.lba = get_unaligned_be32(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be16(&cmd[7]);
- break;
- case WRITE_12:
- case READ_12:
- cdb_info.lba = get_unaligned_be32(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be32(&cmd[6]);
- break;
- case WRITE_16:
- case READ_16:
- cdb_info.lba = get_unaligned_be64(&cmd[2]);
- cdb_info.xfer_len = get_unaligned_be32(&cmd[10]);
- break;
- default:
- /* Will never really reach here */
- res = -EIO;
- goto out;
- }
-
- /* Calculate total length of transfer (in bytes) */
- if (hdr->iovec_count > 0) {
- for (i = 0; i < hdr->iovec_count; i++) {
- not_copied = copy_from_user(&sgl, hdr->dxferp +
- i * sizeof(struct sg_iovec),
- sizeof(struct sg_iovec));
- if (not_copied)
- return -EFAULT;
- sum_iov_len += sgl.iov_len;
- /* IO vector sizes should be multiples of block size */
- if (sgl.iov_len % (1 << ns->lba_shift) != 0) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_PARAMETER,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
- }
- } else {
- sum_iov_len = hdr->dxfer_len;
- }
-
- /* As Per sg ioctl howto, if the lengths differ, use the lower one */
- xfer_bytes = min(((u64)hdr->dxfer_len), sum_iov_len);
-
- /* If block count and actual data buffer size dont match, error out */
- if (xfer_bytes != (cdb_info.xfer_len << ns->lba_shift)) {
- res = -EINVAL;
- goto out;
- }
-
- /* Check for 0 length transfer - it is not illegal */
- if (cdb_info.xfer_len == 0)
- goto out;
-
- /* Send NVMe IO Command(s) */
- res = nvme_trans_do_nvme_io(ns, hdr, &cdb_info, is_write);
- if (res)
- goto out;
-
- out:
- return res;
-}
-
-static int nvme_trans_inquiry(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res = 0;
- u8 evpd;
- u8 page_code;
- int alloc_len;
- u8 *inq_response;
-
- evpd = cmd[1] & 0x01;
- page_code = cmd[2];
- alloc_len = get_unaligned_be16(&cmd[3]);
-
- inq_response = kmalloc(max(alloc_len, STANDARD_INQUIRY_LENGTH),
- GFP_KERNEL);
- if (inq_response == NULL) {
- res = -ENOMEM;
- goto out_mem;
- }
-
- if (evpd == 0) {
- if (page_code == INQ_STANDARD_INQUIRY_PAGE) {
- res = nvme_trans_standard_inquiry_page(ns, hdr,
- inq_response, alloc_len);
- } else {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- }
- } else {
- switch (page_code) {
- case VPD_SUPPORTED_PAGES:
- res = nvme_trans_supported_vpd_pages(ns, hdr,
- inq_response, alloc_len);
- break;
- case VPD_SERIAL_NUMBER:
- res = nvme_trans_unit_serial_page(ns, hdr, inq_response,
- alloc_len);
- break;
- case VPD_DEVICE_IDENTIFIERS:
- res = nvme_trans_device_id_page(ns, hdr, inq_response,
- alloc_len);
- break;
- case VPD_EXTENDED_INQUIRY:
- res = nvme_trans_ext_inq_page(ns, hdr, alloc_len);
- break;
- case VPD_BLOCK_LIMITS:
- res = nvme_trans_bdev_limits_page(ns, hdr, inq_response,
- alloc_len);
- break;
- case VPD_BLOCK_DEV_CHARACTERISTICS:
- res = nvme_trans_bdev_char_page(ns, hdr, alloc_len);
- break;
- default:
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST,
- SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- }
- kfree(inq_response);
- out_mem:
- return res;
-}
-
-static int nvme_trans_log_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res;
- u16 alloc_len;
- u8 pc;
- u8 page_code;
-
- if (cmd[1] != LOG_SENSE_CDB_SP_NOT_ENABLED) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
-
- page_code = cmd[2] & LOG_SENSE_CDB_PAGE_CODE_MASK;
- pc = (cmd[2] & LOG_SENSE_CDB_PC_MASK) >> LOG_SENSE_CDB_PC_SHIFT;
- if (pc != LOG_SENSE_CDB_PC_CUMULATIVE_VALUES) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
- alloc_len = get_unaligned_be16(&cmd[7]);
- switch (page_code) {
- case LOG_PAGE_SUPPORTED_LOG_PAGES_PAGE:
- res = nvme_trans_log_supp_pages(ns, hdr, alloc_len);
- break;
- case LOG_PAGE_INFORMATIONAL_EXCEPTIONS_PAGE:
- res = nvme_trans_log_info_exceptions(ns, hdr, alloc_len);
- break;
- case LOG_PAGE_TEMPERATURE_PAGE:
- res = nvme_trans_log_temperature(ns, hdr, alloc_len);
- break;
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
-
- out:
- return res;
-}
-
-static int nvme_trans_mode_select(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- u8 cdb10 = 0;
- u16 parm_list_len;
- u8 page_format;
- u8 save_pages;
-
- page_format = cmd[1] & MODE_SELECT_CDB_PAGE_FORMAT_MASK;
- save_pages = cmd[1] & MODE_SELECT_CDB_SAVE_PAGES_MASK;
-
- if (cmd[0] == MODE_SELECT) {
- parm_list_len = cmd[4];
- } else {
- parm_list_len = cmd[7];
- cdb10 = 1;
- }
-
- if (parm_list_len != 0) {
- /*
- * According to SPC-4 r24, a paramter list length field of 0
- * shall not be considered an error
- */
- return nvme_trans_modesel_data(ns, hdr, cmd, parm_list_len,
- page_format, save_pages, cdb10);
- }
-
- return 0;
-}
-
-static int nvme_trans_mode_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res = 0;
- u16 alloc_len;
- u8 cdb10 = 0;
-
- if (cmd[0] == MODE_SENSE) {
- alloc_len = cmd[4];
- } else {
- alloc_len = get_unaligned_be16(&cmd[7]);
- cdb10 = 1;
- }
-
- if ((cmd[2] & MODE_SENSE_PAGE_CONTROL_MASK) !=
- MODE_SENSE_PC_CURRENT_VALUES) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
-
- switch (cmd[2] & MODE_SENSE_PAGE_CODE_MASK) {
- case MODE_PAGE_CACHING:
- res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
- cdb10,
- &nvme_trans_fill_caching_page,
- MODE_PAGE_CACHING_LEN);
- break;
- case MODE_PAGE_CONTROL:
- res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
- cdb10,
- &nvme_trans_fill_control_page,
- MODE_PAGE_CONTROL_LEN);
- break;
- case MODE_PAGE_POWER_CONDITION:
- res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
- cdb10,
- &nvme_trans_fill_pow_cnd_page,
- MODE_PAGE_POW_CND_LEN);
- break;
- case MODE_PAGE_INFO_EXCEP:
- res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
- cdb10,
- &nvme_trans_fill_inf_exc_page,
- MODE_PAGE_INF_EXC_LEN);
- break;
- case MODE_PAGE_RETURN_ALL:
- res = nvme_trans_mode_page_create(ns, hdr, cmd, alloc_len,
- cdb10,
- &nvme_trans_fill_all_pages,
- MODE_PAGE_ALL_LEN);
- break;
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
-
- out:
- return res;
-}
-
-static int nvme_trans_read_capacity(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd, u8 cdb16)
-{
- int res;
- int nvme_sc;
- u32 alloc_len;
- u32 resp_size;
- u32 xfer_len;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ns *id_ns;
- u8 *response;
-
- if (cdb16) {
- alloc_len = get_unaligned_be32(&cmd[10]);
- resp_size = READ_CAP_16_RESP_SIZE;
- } else {
- alloc_len = READ_CAP_10_RESP_SIZE;
- resp_size = READ_CAP_10_RESP_SIZE;
- }
-
- nvme_sc = nvme_identify_ns(dev, ns->ns_id, &id_ns);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_free_id;
- }
- nvme_trans_fill_read_cap(response, id_ns, cdb16);
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out_free_id:
- kfree(id_ns);
- return res;
-}
-
-static int nvme_trans_report_luns(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res;
- int nvme_sc;
- u32 alloc_len, xfer_len, resp_size;
- u8 *response;
- struct nvme_dev *dev = ns->dev;
- struct nvme_id_ctrl *id_ctrl;
- u32 ll_length, lun_id;
- u8 lun_id_offset = REPORT_LUNS_FIRST_LUN_OFFSET;
- __be32 tmp_len;
-
- switch (cmd[2]) {
- default:
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- case ALL_LUNS_RETURNED:
- case ALL_WELL_KNOWN_LUNS_RETURNED:
- case RESTRICTED_LUNS_RETURNED:
- nvme_sc = nvme_identify_ctrl(dev, &id_ctrl);
- res = nvme_trans_status_code(hdr, nvme_sc);
- if (res)
- return res;
-
- ll_length = le32_to_cpu(id_ctrl->nn) * LUN_ENTRY_SIZE;
- resp_size = ll_length + LUN_DATA_HEADER_SIZE;
-
- alloc_len = get_unaligned_be32(&cmd[6]);
- if (alloc_len < resp_size) {
- res = nvme_trans_completion(hdr,
- SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out_free_id;
- }
-
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out_free_id;
- }
-
- /* The first LUN ID will always be 0 per the SAM spec */
- for (lun_id = 0; lun_id < le32_to_cpu(id_ctrl->nn); lun_id++) {
- /*
- * Set the LUN Id and then increment to the next LUN
- * location in the parameter data.
- */
- __be64 tmp_id = cpu_to_be64(lun_id);
- memcpy(&response[lun_id_offset], &tmp_id, sizeof(u64));
- lun_id_offset += LUN_ENTRY_SIZE;
- }
- tmp_len = cpu_to_be32(ll_length);
- memcpy(response, &tmp_len, sizeof(u32));
- }
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out_free_id:
- kfree(id_ctrl);
- return res;
-}
-
-static int nvme_trans_request_sense(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res;
- u8 alloc_len, xfer_len, resp_size;
- u8 desc_format;
- u8 *response;
-
- desc_format = cmd[1] & 0x01;
- alloc_len = cmd[4];
-
- resp_size = ((desc_format) ? (DESC_FMT_SENSE_DATA_SIZE) :
- (FIXED_FMT_SENSE_DATA_SIZE));
- response = kzalloc(resp_size, GFP_KERNEL);
- if (response == NULL) {
- res = -ENOMEM;
- goto out;
- }
-
- if (desc_format) {
- /* Descriptor Format Sense Data */
- response[0] = DESC_FORMAT_SENSE_DATA;
- response[1] = NO_SENSE;
- /* TODO How is LOW POWER CONDITION ON handled? (byte 2) */
- response[2] = SCSI_ASC_NO_SENSE;
- response[3] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- /* SDAT_OVFL = 0 | Additional Sense Length = 0 */
- } else {
- /* Fixed Format Sense Data */
- response[0] = FIXED_SENSE_DATA;
- /* Byte 1 = Obsolete */
- response[2] = NO_SENSE; /* FM, EOM, ILI, SDAT_OVFL = 0 */
- /* Bytes 3-6 - Information - set to zero */
- response[7] = FIXED_SENSE_DATA_ADD_LENGTH;
- /* Bytes 8-11 - Cmd Specific Information - set to zero */
- response[12] = SCSI_ASC_NO_SENSE;
- response[13] = SCSI_ASCQ_CAUSE_NOT_REPORTABLE;
- /* Byte 14 = Field Replaceable Unit Code = 0 */
- /* Bytes 15-17 - SKSV=0; Sense Key Specific = 0 */
- }
-
- xfer_len = min(alloc_len, resp_size);
- res = nvme_trans_copy_to_user(hdr, response, xfer_len);
-
- kfree(response);
- out:
- return res;
-}
-
-static int nvme_trans_security_protocol(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_ILLEGAL_COMMAND,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
-}
-
-static int nvme_trans_synchronize_cache(struct nvme_ns *ns,
- struct sg_io_hdr *hdr)
-{
- int nvme_sc;
- struct nvme_command c;
-
- memset(&c, 0, sizeof(c));
- c.common.opcode = nvme_cmd_flush;
- c.common.nsid = cpu_to_le32(ns->ns_id);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, NULL, 0);
- return nvme_trans_status_code(hdr, nvme_sc);
-}
-
-static int nvme_trans_start_stop(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- u8 immed, pcmod, pc, no_flush, start;
-
- immed = cmd[1] & 0x01;
- pcmod = cmd[3] & 0x0f;
- pc = (cmd[4] & 0xf0) >> 4;
- no_flush = cmd[4] & 0x04;
- start = cmd[4] & 0x01;
-
- if (immed != 0) {
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- } else {
- if (no_flush == 0) {
- /* Issue NVME FLUSH command prior to START STOP UNIT */
- int res = nvme_trans_synchronize_cache(ns, hdr);
- if (res)
- return res;
- }
- /* Setup the expected power state transition */
- return nvme_trans_power_state(ns, hdr, pc, pcmod, start);
- }
-}
-
-static int nvme_trans_format_unit(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res;
- u8 parm_hdr_len = 0;
- u8 nvme_pf_code = 0;
- u8 format_prot_info, long_list, format_data;
-
- format_prot_info = (cmd[1] & 0xc0) >> 6;
- long_list = cmd[1] & 0x20;
- format_data = cmd[1] & 0x10;
-
- if (format_data != 0) {
- if (format_prot_info != 0) {
- if (long_list == 0)
- parm_hdr_len = FORMAT_UNIT_SHORT_PARM_LIST_LEN;
- else
- parm_hdr_len = FORMAT_UNIT_LONG_PARM_LIST_LEN;
- }
- } else if (format_data == 0 && format_prot_info != 0) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
-
- /* Get parm header from data-in/out buffer */
- /*
- * According to the translation spec, the only fields in the parameter
- * list we are concerned with are in the header. So allocate only that.
- */
- if (parm_hdr_len > 0) {
- res = nvme_trans_fmt_get_parm_header(hdr, parm_hdr_len,
- format_prot_info, &nvme_pf_code);
- if (res)
- goto out;
- }
-
- /* Attempt to activate any previously downloaded firmware image */
- res = nvme_trans_send_activate_fw_cmd(ns, hdr, 0);
-
- /* Determine Block size and count and send format command */
- res = nvme_trans_fmt_set_blk_size_count(ns, hdr);
- if (res)
- goto out;
-
- res = nvme_trans_fmt_send_cmd(ns, hdr, nvme_pf_code);
-
- out:
- return res;
-}
-
-static int nvme_trans_test_unit_ready(struct nvme_ns *ns,
- struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- struct nvme_dev *dev = ns->dev;
-
- if (!(readl(&dev->bar->csts) & NVME_CSTS_RDY))
- return nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- NOT_READY, SCSI_ASC_LUN_NOT_READY,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- else
- return nvme_trans_completion(hdr, SAM_STAT_GOOD, NO_SENSE, 0, 0);
-}
-
-static int nvme_trans_write_buffer(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- int res = 0;
- u32 buffer_offset, parm_list_length;
- u8 buffer_id, mode;
-
- parm_list_length = get_unaligned_be24(&cmd[6]);
- if (parm_list_length % BYTES_TO_DWORDS != 0) {
- /* NVMe expects Firmware file to be a whole number of DWORDS */
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
- buffer_id = cmd[2];
- if (buffer_id > NVME_MAX_FIRMWARE_SLOT) {
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- goto out;
- }
- mode = cmd[1] & 0x1f;
- buffer_offset = get_unaligned_be24(&cmd[3]);
-
- switch (mode) {
- case DOWNLOAD_SAVE_ACTIVATE:
- res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw,
- parm_list_length, buffer_offset,
- buffer_id);
- if (res)
- goto out;
- res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id);
- break;
- case DOWNLOAD_SAVE_DEFER_ACTIVATE:
- res = nvme_trans_send_download_fw_cmd(ns, hdr, nvme_admin_download_fw,
- parm_list_length, buffer_offset,
- buffer_id);
- break;
- case ACTIVATE_DEFERRED_MICROCODE:
- res = nvme_trans_send_activate_fw_cmd(ns, hdr, buffer_id);
- break;
- default:
- res = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_INVALID_CDB,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
-
- out:
- return res;
-}
-
-struct scsi_unmap_blk_desc {
- __be64 slba;
- __be32 nlb;
- u32 resv;
-};
-
-struct scsi_unmap_parm_list {
- __be16 unmap_data_len;
- __be16 unmap_blk_desc_data_len;
- u32 resv;
- struct scsi_unmap_blk_desc desc[0];
-};
-
-static int nvme_trans_unmap(struct nvme_ns *ns, struct sg_io_hdr *hdr,
- u8 *cmd)
-{
- struct scsi_unmap_parm_list *plist;
- struct nvme_dsm_range *range;
- struct nvme_command c;
- int i, nvme_sc, res;
- u16 ndesc, list_len;
-
- list_len = get_unaligned_be16(&cmd[7]);
- if (!list_len)
- return -EINVAL;
-
- plist = kmalloc(list_len, GFP_KERNEL);
- if (!plist)
- return -ENOMEM;
-
- res = nvme_trans_copy_from_user(hdr, plist, list_len);
- if (res)
- goto out;
-
- ndesc = be16_to_cpu(plist->unmap_blk_desc_data_len) >> 4;
- if (!ndesc || ndesc > 256) {
- res = -EINVAL;
- goto out;
- }
-
- range = kcalloc(ndesc, sizeof(*range), GFP_KERNEL);
- if (!range) {
- res = -ENOMEM;
- goto out;
- }
-
- for (i = 0; i < ndesc; i++) {
- range[i].nlb = cpu_to_le32(be32_to_cpu(plist->desc[i].nlb));
- range[i].slba = cpu_to_le64(be64_to_cpu(plist->desc[i].slba));
- range[i].cattr = 0;
- }
-
- memset(&c, 0, sizeof(c));
- c.dsm.opcode = nvme_cmd_dsm;
- c.dsm.nsid = cpu_to_le32(ns->ns_id);
- c.dsm.nr = cpu_to_le32(ndesc - 1);
- c.dsm.attributes = cpu_to_le32(NVME_DSMGMT_AD);
-
- nvme_sc = nvme_submit_sync_cmd(ns->queue, &c, range,
- ndesc * sizeof(*range));
- res = nvme_trans_status_code(hdr, nvme_sc);
-
- kfree(range);
- out:
- kfree(plist);
- return res;
-}
-
-static int nvme_scsi_translate(struct nvme_ns *ns, struct sg_io_hdr *hdr)
-{
- u8 cmd[BLK_MAX_CDB];
- int retcode;
- unsigned int opcode;
-
- if (hdr->cmdp == NULL)
- return -EMSGSIZE;
- if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
- return -EFAULT;
-
- /*
- * Prime the hdr with good status for scsi commands that don't require
- * an nvme command for translation.
- */
- retcode = nvme_trans_status_code(hdr, NVME_SC_SUCCESS);
- if (retcode)
- return retcode;
-
- opcode = cmd[0];
-
- switch (opcode) {
- case READ_6:
- case READ_10:
- case READ_12:
- case READ_16:
- retcode = nvme_trans_io(ns, hdr, 0, cmd);
- break;
- case WRITE_6:
- case WRITE_10:
- case WRITE_12:
- case WRITE_16:
- retcode = nvme_trans_io(ns, hdr, 1, cmd);
- break;
- case INQUIRY:
- retcode = nvme_trans_inquiry(ns, hdr, cmd);
- break;
- case LOG_SENSE:
- retcode = nvme_trans_log_sense(ns, hdr, cmd);
- break;
- case MODE_SELECT:
- case MODE_SELECT_10:
- retcode = nvme_trans_mode_select(ns, hdr, cmd);
- break;
- case MODE_SENSE:
- case MODE_SENSE_10:
- retcode = nvme_trans_mode_sense(ns, hdr, cmd);
- break;
- case READ_CAPACITY:
- retcode = nvme_trans_read_capacity(ns, hdr, cmd, 0);
- break;
- case SERVICE_ACTION_IN_16:
- switch (cmd[1]) {
- case SAI_READ_CAPACITY_16:
- retcode = nvme_trans_read_capacity(ns, hdr, cmd, 1);
- break;
- default:
- goto out;
- }
- break;
- case REPORT_LUNS:
- retcode = nvme_trans_report_luns(ns, hdr, cmd);
- break;
- case REQUEST_SENSE:
- retcode = nvme_trans_request_sense(ns, hdr, cmd);
- break;
- case SECURITY_PROTOCOL_IN:
- case SECURITY_PROTOCOL_OUT:
- retcode = nvme_trans_security_protocol(ns, hdr, cmd);
- break;
- case START_STOP:
- retcode = nvme_trans_start_stop(ns, hdr, cmd);
- break;
- case SYNCHRONIZE_CACHE:
- retcode = nvme_trans_synchronize_cache(ns, hdr);
- break;
- case FORMAT_UNIT:
- retcode = nvme_trans_format_unit(ns, hdr, cmd);
- break;
- case TEST_UNIT_READY:
- retcode = nvme_trans_test_unit_ready(ns, hdr, cmd);
- break;
- case WRITE_BUFFER:
- retcode = nvme_trans_write_buffer(ns, hdr, cmd);
- break;
- case UNMAP:
- retcode = nvme_trans_unmap(ns, hdr, cmd);
- break;
- default:
- out:
- retcode = nvme_trans_completion(hdr, SAM_STAT_CHECK_CONDITION,
- ILLEGAL_REQUEST, SCSI_ASC_ILLEGAL_COMMAND,
- SCSI_ASCQ_CAUSE_NOT_REPORTABLE);
- break;
- }
- return retcode;
-}
-
-int nvme_sg_io(struct nvme_ns *ns, struct sg_io_hdr __user *u_hdr)
-{
- struct sg_io_hdr hdr;
- int retcode;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EACCES;
- if (copy_from_user(&hdr, u_hdr, sizeof(hdr)))
- return -EFAULT;
- if (hdr.interface_id != 'S')
- return -EINVAL;
- if (hdr.cmd_len > BLK_MAX_CDB)
- return -EINVAL;
-
- /*
- * A positive return code means a NVMe status, which has been
- * translated to sense data.
- */
- retcode = nvme_scsi_translate(ns, &hdr);
- if (retcode < 0)
- return retcode;
- if (copy_to_user(u_hdr, &hdr, sizeof(sg_io_hdr_t)) > 0)
- return -EFAULT;
- return 0;
-}
-
-int nvme_sg_get_version_num(int __user *ip)
-{
- return put_user(sg_version_num, ip);
-}
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
index e22942596207..1b709a4e3b5e 100644
--- a/drivers/block/osdblk.c
+++ b/drivers/block/osdblk.c
@@ -271,7 +271,7 @@ static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
goto err_out;
tmp->bi_bdev = NULL;
- gfpmask &= ~__GFP_WAIT;
+ gfpmask &= ~__GFP_DIRECT_RECLAIM;
tmp->bi_next = NULL;
if (!new_chain)
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index b9242d78283d..562b5a4ca7b7 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -723,7 +723,7 @@ static int pd_special_command(struct pd_unit *disk,
struct request *rq;
int err = 0;
- rq = blk_get_request(disk->gd->queue, READ, __GFP_WAIT);
+ rq = blk_get_request(disk->gd->queue, READ, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 7be2375db7f2..d06c62eccdf0 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -704,14 +704,14 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
int ret = 0;
rq = blk_get_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
- WRITE : READ, __GFP_WAIT);
+ WRITE : READ, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
blk_rq_set_block_pc(rq);
if (cgc->buflen) {
ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen,
- __GFP_WAIT);
+ __GFP_RECLAIM);
if (ret)
goto out;
}
@@ -2441,7 +2441,7 @@ static void pkt_make_request_write(struct request_queue *q, struct bio *bio)
}
}
-static void pkt_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t pkt_make_request(struct request_queue *q, struct bio *bio)
{
struct pktcdvd_device *pd;
char b[BDEVNAME_SIZE];
@@ -2467,7 +2467,7 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
*/
if (bio_data_dir(bio) == READ) {
pkt_make_request_read(pd, bio);
- return;
+ return BLK_QC_T_NONE;
}
if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
@@ -2499,13 +2499,12 @@ static void pkt_make_request(struct request_queue *q, struct bio *bio)
pkt_make_request_write(q, split);
} while (split != bio);
- return;
+ return BLK_QC_T_NONE;
end_io:
bio_io_error(bio);
+ return BLK_QC_T_NONE;
}
-
-
static void pkt_init_queue(struct pktcdvd_device *pd)
{
struct request_queue *q = pd->disk->queue;
@@ -2803,8 +2802,7 @@ out_new_dev:
out_mem2:
put_disk(disk);
out_mem:
- if (pd->rb_pool)
- mempool_destroy(pd->rb_pool);
+ mempool_destroy(pd->rb_pool);
kfree(pd);
out_mutex:
mutex_unlock(&ctl_mutex);
diff --git a/drivers/block/ps3vram.c b/drivers/block/ps3vram.c
index d89fcac59515..56847fcda086 100644
--- a/drivers/block/ps3vram.c
+++ b/drivers/block/ps3vram.c
@@ -598,7 +598,7 @@ out:
return next;
}
-static void ps3vram_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t ps3vram_make_request(struct request_queue *q, struct bio *bio)
{
struct ps3_system_bus_device *dev = q->queuedata;
struct ps3vram_priv *priv = ps3_system_bus_get_drvdata(dev);
@@ -614,11 +614,13 @@ static void ps3vram_make_request(struct request_queue *q, struct bio *bio)
spin_unlock_irq(&priv->lock);
if (busy)
- return;
+ return BLK_QC_T_NONE;
do {
bio = ps3vram_do_bio(dev, bio);
} while (bio);
+
+ return BLK_QC_T_NONE;
}
static int ps3vram_probe(struct ps3_system_bus_device *dev)
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d93a0372b37b..235708c7c46e 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -96,6 +96,8 @@ static int atomic_dec_return_safe(atomic_t *v)
#define RBD_MINORS_PER_MAJOR 256
#define RBD_SINGLE_MAJOR_PART_SHIFT 4
+#define RBD_MAX_PARENT_CHAIN_LEN 16
+
#define RBD_SNAP_DEV_NAME_PREFIX "snap_"
#define RBD_MAX_SNAP_NAME_LEN \
(NAME_MAX - (sizeof (RBD_SNAP_DEV_NAME_PREFIX) - 1))
@@ -416,8 +418,6 @@ MODULE_PARM_DESC(single_major, "Use a single major number for all rbd devices (d
static int rbd_img_request_submit(struct rbd_img_request *img_request);
-static void rbd_dev_device_release(struct device *dev);
-
static ssize_t rbd_add(struct bus_type *bus, const char *buf,
size_t count);
static ssize_t rbd_remove(struct bus_type *bus, const char *buf,
@@ -426,7 +426,7 @@ static ssize_t rbd_add_single_major(struct bus_type *bus, const char *buf,
size_t count);
static ssize_t rbd_remove_single_major(struct bus_type *bus, const char *buf,
size_t count);
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping);
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth);
static void rbd_spec_put(struct rbd_spec *spec);
static int rbd_dev_id_to_minor(int dev_id)
@@ -1863,9 +1863,11 @@ static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
rbd_osd_read_callback(obj_request);
break;
case CEPH_OSD_OP_SETALLOCHINT:
- rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE);
+ rbd_assert(osd_req->r_ops[1].op == CEPH_OSD_OP_WRITE ||
+ osd_req->r_ops[1].op == CEPH_OSD_OP_WRITEFULL);
/* fall through */
case CEPH_OSD_OP_WRITE:
+ case CEPH_OSD_OP_WRITEFULL:
rbd_osd_write_callback(obj_request);
break;
case CEPH_OSD_OP_STAT:
@@ -2401,7 +2403,10 @@ static void rbd_img_obj_request_fill(struct rbd_obj_request *obj_request,
opcode = CEPH_OSD_OP_ZERO;
}
} else if (op_type == OBJ_OP_WRITE) {
- opcode = CEPH_OSD_OP_WRITE;
+ if (!offset && length == object_size)
+ opcode = CEPH_OSD_OP_WRITEFULL;
+ else
+ opcode = CEPH_OSD_OP_WRITE;
osd_req_op_alloc_hint_init(osd_request, num_ops,
object_size, object_size);
num_ops++;
@@ -3760,6 +3765,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
/* set io sizes to object size */
segment_size = rbd_obj_bytes(&rbd_dev->header);
blk_queue_max_hw_sectors(q, segment_size / SECTOR_SIZE);
+ q->limits.max_sectors = queue_max_hw_sectors(q);
blk_queue_max_segments(q, segment_size / SECTOR_SIZE);
blk_queue_max_segment_size(q, segment_size);
blk_queue_io_min(q, segment_size);
@@ -3772,6 +3778,9 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
blk_queue_max_discard_sectors(q, segment_size / SECTOR_SIZE);
q->limits.discard_zeroes_data = 1;
+ if (!ceph_test_opt(rbd_dev->rbd_client->client, NOCRC))
+ q->backing_dev_info.capabilities |= BDI_CAP_STABLE_WRITES;
+
disk->queue = q;
q->queuedata = rbd_dev;
@@ -3980,14 +3989,12 @@ static const struct attribute_group *rbd_attr_groups[] = {
NULL
};
-static void rbd_sysfs_dev_release(struct device *dev)
-{
-}
+static void rbd_dev_release(struct device *dev);
static struct device_type rbd_device_type = {
.name = "rbd",
.groups = rbd_attr_groups,
- .release = rbd_sysfs_dev_release,
+ .release = rbd_dev_release,
};
static struct rbd_spec *rbd_spec_get(struct rbd_spec *spec)
@@ -4030,6 +4037,25 @@ static void rbd_spec_free(struct kref *kref)
kfree(spec);
}
+static void rbd_dev_release(struct device *dev)
+{
+ struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
+ bool need_put = !!rbd_dev->opts;
+
+ rbd_put_client(rbd_dev->rbd_client);
+ rbd_spec_put(rbd_dev->spec);
+ kfree(rbd_dev->opts);
+ kfree(rbd_dev);
+
+ /*
+ * This is racy, but way better than putting module outside of
+ * the release callback. The race window is pretty small, so
+ * doing something similar to dm (dm-builtin.c) is overkill.
+ */
+ if (need_put)
+ module_put(THIS_MODULE);
+}
+
static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
struct rbd_spec *spec,
struct rbd_options *opts)
@@ -4046,6 +4072,11 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
INIT_LIST_HEAD(&rbd_dev->node);
init_rwsem(&rbd_dev->header_rwsem);
+ rbd_dev->dev.bus = &rbd_bus_type;
+ rbd_dev->dev.type = &rbd_device_type;
+ rbd_dev->dev.parent = &rbd_root_dev;
+ device_initialize(&rbd_dev->dev);
+
rbd_dev->rbd_client = rbdc;
rbd_dev->spec = spec;
rbd_dev->opts = opts;
@@ -4057,15 +4088,21 @@ static struct rbd_device *rbd_dev_create(struct rbd_client *rbdc,
rbd_dev->layout.fl_object_size = cpu_to_le32(1 << RBD_MAX_OBJ_ORDER);
rbd_dev->layout.fl_pg_pool = cpu_to_le32((u32) spec->pool_id);
+ /*
+ * If this is a mapping rbd_dev (as opposed to a parent one),
+ * pin our module. We have a ref from do_rbd_add(), so use
+ * __module_get().
+ */
+ if (rbd_dev->opts)
+ __module_get(THIS_MODULE);
+
return rbd_dev;
}
static void rbd_dev_destroy(struct rbd_device *rbd_dev)
{
- rbd_put_client(rbd_dev->rbd_client);
- rbd_spec_put(rbd_dev->spec);
- kfree(rbd_dev->opts);
- kfree(rbd_dev);
+ if (rbd_dev)
+ put_device(&rbd_dev->dev);
}
/*
@@ -4691,27 +4728,6 @@ static int rbd_dev_header_info(struct rbd_device *rbd_dev)
return rbd_dev_v2_header_info(rbd_dev);
}
-static int rbd_bus_add_dev(struct rbd_device *rbd_dev)
-{
- struct device *dev;
- int ret;
-
- dev = &rbd_dev->dev;
- dev->bus = &rbd_bus_type;
- dev->type = &rbd_device_type;
- dev->parent = &rbd_root_dev;
- dev->release = rbd_dev_device_release;
- dev_set_name(dev, "%d", rbd_dev->dev_id);
- ret = device_register(dev);
-
- return ret;
-}
-
-static void rbd_bus_del_dev(struct rbd_device *rbd_dev)
-{
- device_unregister(&rbd_dev->dev);
-}
-
/*
* Get a unique rbd identifier for the given new rbd_dev, and add
* the rbd_dev to the global list.
@@ -5125,44 +5141,51 @@ out_err:
return ret;
}
-static int rbd_dev_probe_parent(struct rbd_device *rbd_dev)
+/*
+ * @depth is rbd_dev_image_probe() -> rbd_dev_probe_parent() ->
+ * rbd_dev_image_probe() recursion depth, which means it's also the
+ * length of the already discovered part of the parent chain.
+ */
+static int rbd_dev_probe_parent(struct rbd_device *rbd_dev, int depth)
{
struct rbd_device *parent = NULL;
- struct rbd_spec *parent_spec;
- struct rbd_client *rbdc;
int ret;
if (!rbd_dev->parent_spec)
return 0;
- /*
- * We need to pass a reference to the client and the parent
- * spec when creating the parent rbd_dev. Images related by
- * parent/child relationships always share both.
- */
- parent_spec = rbd_spec_get(rbd_dev->parent_spec);
- rbdc = __rbd_get_client(rbd_dev->rbd_client);
- ret = -ENOMEM;
- parent = rbd_dev_create(rbdc, parent_spec, NULL);
- if (!parent)
+ if (++depth > RBD_MAX_PARENT_CHAIN_LEN) {
+ pr_info("parent chain is too long (%d)\n", depth);
+ ret = -EINVAL;
+ goto out_err;
+ }
+
+ parent = rbd_dev_create(rbd_dev->rbd_client, rbd_dev->parent_spec,
+ NULL);
+ if (!parent) {
+ ret = -ENOMEM;
goto out_err;
+ }
+
+ /*
+ * Images related by parent/child relationships always share
+ * rbd_client and spec/parent_spec, so bump their refcounts.
+ */
+ __rbd_get_client(rbd_dev->rbd_client);
+ rbd_spec_get(rbd_dev->parent_spec);
- ret = rbd_dev_image_probe(parent, false);
+ ret = rbd_dev_image_probe(parent, depth);
if (ret < 0)
goto out_err;
+
rbd_dev->parent = parent;
atomic_set(&rbd_dev->parent_ref, 1);
-
return 0;
+
out_err:
- if (parent) {
- rbd_dev_unparent(rbd_dev);
+ rbd_dev_unparent(rbd_dev);
+ if (parent)
rbd_dev_destroy(parent);
- } else {
- rbd_put_client(rbdc);
- rbd_spec_put(parent_spec);
- }
-
return ret;
}
@@ -5207,7 +5230,8 @@ static int rbd_dev_device_setup(struct rbd_device *rbd_dev)
set_capacity(rbd_dev->disk, rbd_dev->mapping.size / SECTOR_SIZE);
set_disk_ro(rbd_dev->disk, rbd_dev->mapping.read_only);
- ret = rbd_bus_add_dev(rbd_dev);
+ dev_set_name(&rbd_dev->dev, "%d", rbd_dev->dev_id);
+ ret = device_add(&rbd_dev->dev);
if (ret)
goto err_out_mapping;
@@ -5230,8 +5254,6 @@ err_out_blkdev:
unregister_blkdev(rbd_dev->major, rbd_dev->name);
err_out_id:
rbd_dev_id_put(rbd_dev);
- rbd_dev_mapping_clear(rbd_dev);
-
return ret;
}
@@ -5280,7 +5302,7 @@ static void rbd_dev_image_release(struct rbd_device *rbd_dev)
* parent), initiate a watch on its header object before using that
* object to get detailed information about the rbd image.
*/
-static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
+static int rbd_dev_image_probe(struct rbd_device *rbd_dev, int depth)
{
int ret;
@@ -5298,7 +5320,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
if (ret)
goto err_out_format;
- if (mapping) {
+ if (!depth) {
ret = rbd_dev_header_watch_sync(rbd_dev);
if (ret) {
if (ret == -ENOENT)
@@ -5319,7 +5341,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
* Otherwise this is a parent image, identified by pool, image
* and snap ids - need to fill in names for those ids.
*/
- if (mapping)
+ if (!depth)
ret = rbd_spec_fill_snap_id(rbd_dev);
else
ret = rbd_spec_fill_names(rbd_dev);
@@ -5341,12 +5363,12 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
* Need to warn users if this image is the one being
* mapped and has a parent.
*/
- if (mapping && rbd_dev->parent_spec)
+ if (!depth && rbd_dev->parent_spec)
rbd_warn(rbd_dev,
"WARNING: kernel layering is EXPERIMENTAL!");
}
- ret = rbd_dev_probe_parent(rbd_dev);
+ ret = rbd_dev_probe_parent(rbd_dev, depth);
if (ret)
goto err_out_probe;
@@ -5357,7 +5379,7 @@ static int rbd_dev_image_probe(struct rbd_device *rbd_dev, bool mapping)
err_out_probe:
rbd_dev_unprobe(rbd_dev);
err_out_watch:
- if (mapping)
+ if (!depth)
rbd_dev_header_unwatch_sync(rbd_dev);
out_header_name:
kfree(rbd_dev->header_name);
@@ -5379,7 +5401,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
struct rbd_spec *spec = NULL;
struct rbd_client *rbdc;
bool read_only;
- int rc = -ENOMEM;
+ int rc;
if (!try_module_get(THIS_MODULE))
return -ENODEV;
@@ -5387,7 +5409,7 @@ static ssize_t do_rbd_add(struct bus_type *bus,
/* parse add command */
rc = rbd_add_parse_args(buf, &ceph_opts, &rbd_opts, &spec);
if (rc < 0)
- goto err_out_module;
+ goto out;
rbdc = rbd_get_client(ceph_opts);
if (IS_ERR(rbdc)) {
@@ -5414,13 +5436,15 @@ static ssize_t do_rbd_add(struct bus_type *bus,
}
rbd_dev = rbd_dev_create(rbdc, spec, rbd_opts);
- if (!rbd_dev)
+ if (!rbd_dev) {
+ rc = -ENOMEM;
goto err_out_client;
+ }
rbdc = NULL; /* rbd_dev now owns this */
spec = NULL; /* rbd_dev now owns this */
rbd_opts = NULL; /* rbd_dev now owns this */
- rc = rbd_dev_image_probe(rbd_dev, true);
+ rc = rbd_dev_image_probe(rbd_dev, 0);
if (rc < 0)
goto err_out_rbd_dev;
@@ -5440,10 +5464,13 @@ static ssize_t do_rbd_add(struct bus_type *bus,
*/
rbd_dev_header_unwatch_sync(rbd_dev);
rbd_dev_image_release(rbd_dev);
- goto err_out_module;
+ goto out;
}
- return count;
+ rc = count;
+out:
+ module_put(THIS_MODULE);
+ return rc;
err_out_rbd_dev:
rbd_dev_destroy(rbd_dev);
@@ -5452,12 +5479,7 @@ err_out_client:
err_out_args:
rbd_spec_put(spec);
kfree(rbd_opts);
-err_out_module:
- module_put(THIS_MODULE);
-
- dout("Error adding device %s\n", buf);
-
- return (ssize_t)rc;
+ goto out;
}
static ssize_t rbd_add(struct bus_type *bus,
@@ -5477,17 +5499,15 @@ static ssize_t rbd_add_single_major(struct bus_type *bus,
return do_rbd_add(bus, buf, count);
}
-static void rbd_dev_device_release(struct device *dev)
+static void rbd_dev_device_release(struct rbd_device *rbd_dev)
{
- struct rbd_device *rbd_dev = dev_to_rbd_dev(dev);
-
rbd_free_disk(rbd_dev);
clear_bit(RBD_DEV_FLAG_EXISTS, &rbd_dev->flags);
+ device_del(&rbd_dev->dev);
rbd_dev_mapping_clear(rbd_dev);
if (!single_major)
unregister_blkdev(rbd_dev->major, rbd_dev->name);
rbd_dev_id_put(rbd_dev);
- rbd_dev_mapping_clear(rbd_dev);
}
static void rbd_dev_remove_parent(struct rbd_device *rbd_dev)
@@ -5572,9 +5592,8 @@ static ssize_t do_rbd_remove(struct bus_type *bus,
* rbd_bus_del_dev() will race with rbd_watch_cb(), resulting
* in a potential use after free of rbd_dev->disk or rbd_dev.
*/
- rbd_bus_del_dev(rbd_dev);
+ rbd_dev_device_release(rbd_dev);
rbd_dev_image_release(rbd_dev);
- module_put(THIS_MODULE);
return count;
}
@@ -5645,10 +5664,8 @@ static int rbd_slab_init(void)
if (rbd_segment_name_cache)
return 0;
out_err:
- if (rbd_obj_request_cache) {
- kmem_cache_destroy(rbd_obj_request_cache);
- rbd_obj_request_cache = NULL;
- }
+ kmem_cache_destroy(rbd_obj_request_cache);
+ rbd_obj_request_cache = NULL;
kmem_cache_destroy(rbd_img_request_cache);
rbd_img_request_cache = NULL;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index 3163e4cdc2cc..e1b8b7061d2f 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -145,7 +145,7 @@ static void bio_dma_done_cb(struct rsxx_cardinfo *card,
}
}
-static void rsxx_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t rsxx_make_request(struct request_queue *q, struct bio *bio)
{
struct rsxx_cardinfo *card = q->queuedata;
struct rsxx_bio_meta *bio_meta;
@@ -199,7 +199,7 @@ static void rsxx_make_request(struct request_queue *q, struct bio *bio)
if (st)
goto queue_err;
- return;
+ return BLK_QC_T_NONE;
queue_err:
kmem_cache_free(bio_meta_pool, bio_meta);
@@ -207,6 +207,7 @@ req_err:
if (st)
bio->bi_error = st;
bio_endio(bio);
+ return BLK_QC_T_NONE;
}
/*----------------- Device Setup -------------------*/
diff --git a/drivers/block/umem.c b/drivers/block/umem.c
index 04d65790a886..7939b9f87441 100644
--- a/drivers/block/umem.c
+++ b/drivers/block/umem.c
@@ -524,7 +524,7 @@ static int mm_check_plugged(struct cardinfo *card)
return !!blk_check_plugged(mm_unplug, card, sizeof(struct blk_plug_cb));
}
-static void mm_make_request(struct request_queue *q, struct bio *bio)
+static blk_qc_t mm_make_request(struct request_queue *q, struct bio *bio)
{
struct cardinfo *card = q->queuedata;
pr_debug("mm_make_request %llu %u\n",
@@ -541,7 +541,7 @@ static void mm_make_request(struct request_queue *q, struct bio *bio)
activate(card);
spin_unlock_irq(&card->lock);
- return;
+ return BLK_QC_T_NONE;
}
static irqreturn_t mm_interrupt(int irq, void *__card)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index 6a685aec6994..f9099940c272 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -87,7 +87,7 @@ MODULE_PARM_DESC(max_persistent_grants,
* Maximum order of pages to be used for the shared ring between front and
* backend, 4KB page granularity is used.
*/
-unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+unsigned int xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
/*
@@ -961,7 +961,7 @@ static int xen_blkbk_parse_indirect(struct blkif_request *req,
seg[n].nsec = segments[i].last_sect -
segments[i].first_sect + 1;
seg[n].offset = (segments[i].first_sect << 9);
- if ((segments[i].last_sect >= (PAGE_SIZE >> 9)) ||
+ if ((segments[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
(segments[i].last_sect < segments[i].first_sect)) {
rc = -EINVAL;
goto unmap;
@@ -1210,6 +1210,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
req_operation = req->operation == BLKIF_OP_INDIRECT ?
req->u.indirect.indirect_op : req->operation;
+
if ((req->operation == BLKIF_OP_INDIRECT) &&
(req_operation != BLKIF_OP_READ) &&
(req_operation != BLKIF_OP_WRITE)) {
@@ -1268,7 +1269,7 @@ static int dispatch_rw_block_io(struct xen_blkif *blkif,
seg[i].nsec = req->u.rw.seg[i].last_sect -
req->u.rw.seg[i].first_sect + 1;
seg[i].offset = (req->u.rw.seg[i].first_sect << 9);
- if ((req->u.rw.seg[i].last_sect >= (PAGE_SIZE >> 9)) ||
+ if ((req->u.rw.seg[i].last_sect >= (XEN_PAGE_SIZE >> 9)) ||
(req->u.rw.seg[i].last_sect <
req->u.rw.seg[i].first_sect))
goto fail_response;
@@ -1445,10 +1446,10 @@ static int __init xen_blkif_init(void)
if (!xen_domain())
return -ENODEV;
- if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+ if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
- xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
- xen_blkif_max_ring_order = XENBUS_MAX_RING_PAGE_ORDER;
+ xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
+ xen_blkif_max_ring_order = XENBUS_MAX_RING_GRANT_ORDER;
}
rc = xen_blkif_interface_init();
diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h
index 45a044a53d1e..68e87a037b99 100644
--- a/drivers/block/xen-blkback/common.h
+++ b/drivers/block/xen-blkback/common.h
@@ -39,6 +39,7 @@
#include <asm/pgalloc.h>
#include <asm/hypervisor.h>
#include <xen/grant_table.h>
+#include <xen/page.h>
#include <xen/xenbus.h>
#include <xen/interface/io/ring.h>
#include <xen/interface/io/blkif.h>
@@ -51,12 +52,20 @@ extern unsigned int xen_blkif_max_ring_order;
*/
#define MAX_INDIRECT_SEGMENTS 256
-#define SEGS_PER_INDIRECT_FRAME \
- (PAGE_SIZE/sizeof(struct blkif_request_segment))
+/*
+ * Xen use 4K pages. The guest may use different page size (4K or 64K)
+ * Number of Xen pages per segment
+ */
+#define XEN_PAGES_PER_SEGMENT (PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define XEN_PAGES_PER_INDIRECT_FRAME \
+ (XEN_PAGE_SIZE/sizeof(struct blkif_request_segment))
+#define SEGS_PER_INDIRECT_FRAME \
+ (XEN_PAGES_PER_INDIRECT_FRAME / XEN_PAGES_PER_SEGMENT)
+
#define MAX_INDIRECT_PAGES \
((MAX_INDIRECT_SEGMENTS + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
-#define INDIRECT_PAGES(_segs) \
- ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+#define INDIRECT_PAGES(_segs) DIV_ROUND_UP(_segs, XEN_PAGES_PER_INDIRECT_FRAME)
/* Not a real protocol. Used to generate ring structs which contain
* the elements common to all protocols only. This way we get a
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 767657565de6..f53cff42f8da 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -176,21 +176,24 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
{
struct blkif_sring *sring;
sring = (struct blkif_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.native, sring, PAGE_SIZE * nr_grefs);
+ BACK_RING_INIT(&blkif->blk_rings.native, sring,
+ XEN_PAGE_SIZE * nr_grefs);
break;
}
case BLKIF_PROTOCOL_X86_32:
{
struct blkif_x86_32_sring *sring_x86_32;
sring_x86_32 = (struct blkif_x86_32_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32, PAGE_SIZE * nr_grefs);
+ BACK_RING_INIT(&blkif->blk_rings.x86_32, sring_x86_32,
+ XEN_PAGE_SIZE * nr_grefs);
break;
}
case BLKIF_PROTOCOL_X86_64:
{
struct blkif_x86_64_sring *sring_x86_64;
sring_x86_64 = (struct blkif_x86_64_sring *)blkif->blk_ring;
- BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64, PAGE_SIZE * nr_grefs);
+ BACK_RING_INIT(&blkif->blk_rings.x86_64, sring_x86_64,
+ XEN_PAGE_SIZE * nr_grefs);
break;
}
default:
@@ -826,7 +829,7 @@ again:
static int connect_ring(struct backend_info *be)
{
struct xenbus_device *dev = be->dev;
- unsigned int ring_ref[XENBUS_MAX_RING_PAGES];
+ unsigned int ring_ref[XENBUS_MAX_RING_GRANTS];
unsigned int evtchn, nr_grefs, ring_page_order;
unsigned int pers_grants;
char protocol[64] = "";
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 611170896b8c..2fee2eef988d 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -68,7 +68,7 @@ enum blkif_state {
struct grant {
grant_ref_t gref;
- unsigned long pfn;
+ struct page *page;
struct list_head node;
};
@@ -78,6 +78,7 @@ struct blk_shadow {
struct grant **grants_used;
struct grant **indirect_grants;
struct scatterlist *sg;
+ unsigned int num_sg;
};
struct split_bio {
@@ -106,8 +107,12 @@ static unsigned int xen_blkif_max_ring_order;
module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
-#define BLK_RING_SIZE(info) __CONST_RING_SIZE(blkif, PAGE_SIZE * (info)->nr_ring_pages)
-#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE * XENBUS_MAX_RING_PAGES)
+#define BLK_RING_SIZE(info) \
+ __CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * (info)->nr_ring_pages)
+
+#define BLK_MAX_RING_SIZE \
+ __CONST_RING_SIZE(blkif, XEN_PAGE_SIZE * XENBUS_MAX_RING_GRANTS)
+
/*
* ring-ref%i i=(-1UL) would take 11 characters + 'ring-ref' is 8, so 19
* characters are enough. Define to 20 to keep consist with backend.
@@ -128,7 +133,7 @@ struct blkfront_info
int vdevice;
blkif_vdev_t handle;
enum blkif_state connected;
- int ring_ref[XENBUS_MAX_RING_PAGES];
+ int ring_ref[XENBUS_MAX_RING_GRANTS];
unsigned int nr_ring_pages;
struct blkif_front_ring ring;
unsigned int evtchn, irq;
@@ -146,6 +151,7 @@ struct blkfront_info
unsigned int discard_granularity;
unsigned int discard_alignment;
unsigned int feature_persistent:1;
+ /* Number of 4KB segments handled */
unsigned int max_indirect_segments;
int is_ready;
struct blk_mq_tag_set tag_set;
@@ -174,10 +180,23 @@ static DEFINE_SPINLOCK(minor_lock);
#define DEV_NAME "xvd" /* name in /dev */
-#define SEGS_PER_INDIRECT_FRAME \
- (PAGE_SIZE/sizeof(struct blkif_request_segment))
-#define INDIRECT_GREFS(_segs) \
- ((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
+/*
+ * Grants are always the same size as a Xen page (i.e 4KB).
+ * A physical segment is always the same size as a Linux page.
+ * Number of grants per physical segment
+ */
+#define GRANTS_PER_PSEG (PAGE_SIZE / XEN_PAGE_SIZE)
+
+#define GRANTS_PER_INDIRECT_FRAME \
+ (XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
+
+#define PSEGS_PER_INDIRECT_FRAME \
+ (GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
+
+#define INDIRECT_GREFS(_grants) \
+ DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
+
+#define GREFS(_psegs) ((_psegs) * GRANTS_PER_PSEG)
static int blkfront_setup_indirect(struct blkfront_info *info);
static int blkfront_gather_backend_features(struct blkfront_info *info);
@@ -221,7 +240,7 @@ static int fill_grant_buffer(struct blkfront_info *info, int num)
kfree(gnt_list_entry);
goto out_of_memory;
}
- gnt_list_entry->pfn = page_to_pfn(granted_page);
+ gnt_list_entry->page = granted_page;
}
gnt_list_entry->gref = GRANT_INVALID_REF;
@@ -236,7 +255,7 @@ out_of_memory:
&info->grants, node) {
list_del(&gnt_list_entry->node);
if (info->feature_persistent)
- __free_page(pfn_to_page(gnt_list_entry->pfn));
+ __free_page(gnt_list_entry->page);
kfree(gnt_list_entry);
i--;
}
@@ -244,34 +263,77 @@ out_of_memory:
return -ENOMEM;
}
-static struct grant *get_grant(grant_ref_t *gref_head,
- unsigned long pfn,
- struct blkfront_info *info)
+static struct grant *get_free_grant(struct blkfront_info *info)
{
struct grant *gnt_list_entry;
- unsigned long buffer_gfn;
BUG_ON(list_empty(&info->grants));
gnt_list_entry = list_first_entry(&info->grants, struct grant,
- node);
+ node);
list_del(&gnt_list_entry->node);
- if (gnt_list_entry->gref != GRANT_INVALID_REF) {
+ if (gnt_list_entry->gref != GRANT_INVALID_REF)
info->persistent_gnts_c--;
+
+ return gnt_list_entry;
+}
+
+static inline void grant_foreign_access(const struct grant *gnt_list_entry,
+ const struct blkfront_info *info)
+{
+ gnttab_page_grant_foreign_access_ref_one(gnt_list_entry->gref,
+ info->xbdev->otherend_id,
+ gnt_list_entry->page,
+ 0);
+}
+
+static struct grant *get_grant(grant_ref_t *gref_head,
+ unsigned long gfn,
+ struct blkfront_info *info)
+{
+ struct grant *gnt_list_entry = get_free_grant(info);
+
+ if (gnt_list_entry->gref != GRANT_INVALID_REF)
return gnt_list_entry;
+
+ /* Assign a gref to this page */
+ gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
+ BUG_ON(gnt_list_entry->gref == -ENOSPC);
+ if (info->feature_persistent)
+ grant_foreign_access(gnt_list_entry, info);
+ else {
+ /* Grant access to the GFN passed by the caller */
+ gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
+ info->xbdev->otherend_id,
+ gfn, 0);
}
+ return gnt_list_entry;
+}
+
+static struct grant *get_indirect_grant(grant_ref_t *gref_head,
+ struct blkfront_info *info)
+{
+ struct grant *gnt_list_entry = get_free_grant(info);
+
+ if (gnt_list_entry->gref != GRANT_INVALID_REF)
+ return gnt_list_entry;
+
/* Assign a gref to this page */
gnt_list_entry->gref = gnttab_claim_grant_reference(gref_head);
BUG_ON(gnt_list_entry->gref == -ENOSPC);
if (!info->feature_persistent) {
- BUG_ON(!pfn);
- gnt_list_entry->pfn = pfn;
+ struct page *indirect_page;
+
+ /* Fetch a pre-allocated page to use for indirect grefs */
+ BUG_ON(list_empty(&info->indirect_pages));
+ indirect_page = list_first_entry(&info->indirect_pages,
+ struct page, lru);
+ list_del(&indirect_page->lru);
+ gnt_list_entry->page = indirect_page;
}
- buffer_gfn = pfn_to_gfn(gnt_list_entry->pfn);
- gnttab_grant_foreign_access_ref(gnt_list_entry->gref,
- info->xbdev->otherend_id,
- buffer_gfn, 0);
+ grant_foreign_access(gnt_list_entry, info);
+
return gnt_list_entry;
}
@@ -394,20 +456,128 @@ static int blkif_ioctl(struct block_device *bdev, fmode_t mode,
return 0;
}
-/*
- * Generate a Xen blkfront IO request from a blk layer request. Reads
- * and writes are handled as expected.
- *
- * @req: a request struct
- */
-static int blkif_queue_request(struct request *req)
+static int blkif_queue_discard_req(struct request *req)
{
struct blkfront_info *info = req->rq_disk->private_data;
struct blkif_request *ring_req;
unsigned long id;
+
+ /* Fill out a communications ring structure. */
+ ring_req = RING_GET_REQUEST(&info->ring, info->ring.req_prod_pvt);
+ id = get_id_from_freelist(info);
+ info->shadow[id].request = req;
+
+ ring_req->operation = BLKIF_OP_DISCARD;
+ ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+ ring_req->u.discard.id = id;
+ ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
+ ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
+ else
+ ring_req->u.discard.flag = 0;
+
+ info->ring.req_prod_pvt++;
+
+ /* Keep a private copy so we can reissue requests when recovering. */
+ info->shadow[id].req = *ring_req;
+
+ return 0;
+}
+
+struct setup_rw_req {
+ unsigned int grant_idx;
+ struct blkif_request_segment *segments;
+ struct blkfront_info *info;
+ struct blkif_request *ring_req;
+ grant_ref_t gref_head;
+ unsigned int id;
+ /* Only used when persistent grant is used and it's a read request */
+ bool need_copy;
+ unsigned int bvec_off;
+ char *bvec_data;
+};
+
+static void blkif_setup_rw_req_grant(unsigned long gfn, unsigned int offset,
+ unsigned int len, void *data)
+{
+ struct setup_rw_req *setup = data;
+ int n, ref;
+ struct grant *gnt_list_entry;
unsigned int fsect, lsect;
- int i, ref, n;
- struct blkif_request_segment *segments = NULL;
+ /* Convenient aliases */
+ unsigned int grant_idx = setup->grant_idx;
+ struct blkif_request *ring_req = setup->ring_req;
+ struct blkfront_info *info = setup->info;
+ struct blk_shadow *shadow = &info->shadow[setup->id];
+
+ if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
+ (grant_idx % GRANTS_PER_INDIRECT_FRAME == 0)) {
+ if (setup->segments)
+ kunmap_atomic(setup->segments);
+
+ n = grant_idx / GRANTS_PER_INDIRECT_FRAME;
+ gnt_list_entry = get_indirect_grant(&setup->gref_head, info);
+ shadow->indirect_grants[n] = gnt_list_entry;
+ setup->segments = kmap_atomic(gnt_list_entry->page);
+ ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
+ }
+
+ gnt_list_entry = get_grant(&setup->gref_head, gfn, info);
+ ref = gnt_list_entry->gref;
+ shadow->grants_used[grant_idx] = gnt_list_entry;
+
+ if (setup->need_copy) {
+ void *shared_data;
+
+ shared_data = kmap_atomic(gnt_list_entry->page);
+ /*
+ * this does not wipe data stored outside the
+ * range sg->offset..sg->offset+sg->length.
+ * Therefore, blkback *could* see data from
+ * previous requests. This is OK as long as
+ * persistent grants are shared with just one
+ * domain. It may need refactoring if this
+ * changes
+ */
+ memcpy(shared_data + offset,
+ setup->bvec_data + setup->bvec_off,
+ len);
+
+ kunmap_atomic(shared_data);
+ setup->bvec_off += len;
+ }
+
+ fsect = offset >> 9;
+ lsect = fsect + (len >> 9) - 1;
+ if (ring_req->operation != BLKIF_OP_INDIRECT) {
+ ring_req->u.rw.seg[grant_idx] =
+ (struct blkif_request_segment) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ } else {
+ setup->segments[grant_idx % GRANTS_PER_INDIRECT_FRAME] =
+ (struct blkif_request_segment) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ }
+
+ (setup->grant_idx)++;
+}
+
+static int blkif_queue_rw_req(struct request *req)
+{
+ struct blkfront_info *info = req->rq_disk->private_data;
+ struct blkif_request *ring_req;
+ unsigned long id;
+ int i;
+ struct setup_rw_req setup = {
+ .grant_idx = 0,
+ .segments = NULL,
+ .info = info,
+ .need_copy = rq_data_dir(req) && info->feature_persistent,
+ };
/*
* Used to store if we are able to queue the request by just using
@@ -415,28 +585,23 @@ static int blkif_queue_request(struct request *req)
* as there are not sufficiently many free.
*/
bool new_persistent_gnts;
- grant_ref_t gref_head;
- struct grant *gnt_list_entry = NULL;
struct scatterlist *sg;
- int nseg, max_grefs;
+ int num_sg, max_grefs, num_grant;
- if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
- return 1;
-
- max_grefs = req->nr_phys_segments;
+ max_grefs = req->nr_phys_segments * GRANTS_PER_PSEG;
if (max_grefs > BLKIF_MAX_SEGMENTS_PER_REQUEST)
/*
* If we are using indirect segments we need to account
* for the indirect grefs used in the request.
*/
- max_grefs += INDIRECT_GREFS(req->nr_phys_segments);
+ max_grefs += INDIRECT_GREFS(max_grefs);
/* Check if we have enough grants to allocate a requests */
if (info->persistent_gnts_c < max_grefs) {
new_persistent_gnts = 1;
if (gnttab_alloc_grant_references(
max_grefs - info->persistent_gnts_c,
- &gref_head) < 0) {
+ &setup.gref_head) < 0) {
gnttab_request_free_callback(
&info->callback,
blkif_restart_queue_callback,
@@ -452,139 +617,82 @@ static int blkif_queue_request(struct request *req)
id = get_id_from_freelist(info);
info->shadow[id].request = req;
- if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE))) {
- ring_req->operation = BLKIF_OP_DISCARD;
- ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
- ring_req->u.discard.id = id;
- ring_req->u.discard.sector_number = (blkif_sector_t)blk_rq_pos(req);
- if ((req->cmd_flags & REQ_SECURE) && info->feature_secdiscard)
- ring_req->u.discard.flag = BLKIF_DISCARD_SECURE;
- else
- ring_req->u.discard.flag = 0;
+ BUG_ON(info->max_indirect_segments == 0 &&
+ GREFS(req->nr_phys_segments) > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ BUG_ON(info->max_indirect_segments &&
+ GREFS(req->nr_phys_segments) > info->max_indirect_segments);
+
+ num_sg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
+ num_grant = 0;
+ /* Calculate the number of grant used */
+ for_each_sg(info->shadow[id].sg, sg, num_sg, i)
+ num_grant += gnttab_count_grant(sg->offset, sg->length);
+
+ ring_req->u.rw.id = id;
+ info->shadow[id].num_sg = num_sg;
+ if (num_grant > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+ /*
+ * The indirect operation can only be a BLKIF_OP_READ or
+ * BLKIF_OP_WRITE
+ */
+ BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
+ ring_req->operation = BLKIF_OP_INDIRECT;
+ ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
+ BLKIF_OP_WRITE : BLKIF_OP_READ;
+ ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.indirect.handle = info->handle;
+ ring_req->u.indirect.nr_segments = num_grant;
} else {
- BUG_ON(info->max_indirect_segments == 0 &&
- req->nr_phys_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
- BUG_ON(info->max_indirect_segments &&
- req->nr_phys_segments > info->max_indirect_segments);
- nseg = blk_rq_map_sg(req->q, req, info->shadow[id].sg);
- ring_req->u.rw.id = id;
- if (nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST) {
+ ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
+ ring_req->u.rw.handle = info->handle;
+ ring_req->operation = rq_data_dir(req) ?
+ BLKIF_OP_WRITE : BLKIF_OP_READ;
+ if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
/*
- * The indirect operation can only be a BLKIF_OP_READ or
- * BLKIF_OP_WRITE
+ * Ideally we can do an unordered flush-to-disk.
+ * In case the backend onlysupports barriers, use that.
+ * A barrier request a superset of FUA, so we can
+ * implement it the same way. (It's also a FLUSH+FUA,
+ * since it is guaranteed ordered WRT previous writes.)
*/
- BUG_ON(req->cmd_flags & (REQ_FLUSH | REQ_FUA));
- ring_req->operation = BLKIF_OP_INDIRECT;
- ring_req->u.indirect.indirect_op = rq_data_dir(req) ?
- BLKIF_OP_WRITE : BLKIF_OP_READ;
- ring_req->u.indirect.sector_number = (blkif_sector_t)blk_rq_pos(req);
- ring_req->u.indirect.handle = info->handle;
- ring_req->u.indirect.nr_segments = nseg;
- } else {
- ring_req->u.rw.sector_number = (blkif_sector_t)blk_rq_pos(req);
- ring_req->u.rw.handle = info->handle;
- ring_req->operation = rq_data_dir(req) ?
- BLKIF_OP_WRITE : BLKIF_OP_READ;
- if (req->cmd_flags & (REQ_FLUSH | REQ_FUA)) {
- /*
- * Ideally we can do an unordered flush-to-disk. In case the
- * backend onlysupports barriers, use that. A barrier request
- * a superset of FUA, so we can implement it the same
- * way. (It's also a FLUSH+FUA, since it is
- * guaranteed ordered WRT previous writes.)
- */
- switch (info->feature_flush &
- ((REQ_FLUSH|REQ_FUA))) {
- case REQ_FLUSH|REQ_FUA:
- ring_req->operation =
- BLKIF_OP_WRITE_BARRIER;
- break;
- case REQ_FLUSH:
- ring_req->operation =
- BLKIF_OP_FLUSH_DISKCACHE;
- break;
- default:
- ring_req->operation = 0;
- }
+ switch (info->feature_flush &
+ ((REQ_FLUSH|REQ_FUA))) {
+ case REQ_FLUSH|REQ_FUA:
+ ring_req->operation =
+ BLKIF_OP_WRITE_BARRIER;
+ break;
+ case REQ_FLUSH:
+ ring_req->operation =
+ BLKIF_OP_FLUSH_DISKCACHE;
+ break;
+ default:
+ ring_req->operation = 0;
}
- ring_req->u.rw.nr_segments = nseg;
}
- for_each_sg(info->shadow[id].sg, sg, nseg, i) {
- fsect = sg->offset >> 9;
- lsect = fsect + (sg->length >> 9) - 1;
-
- if ((ring_req->operation == BLKIF_OP_INDIRECT) &&
- (i % SEGS_PER_INDIRECT_FRAME == 0)) {
- unsigned long uninitialized_var(pfn);
-
- if (segments)
- kunmap_atomic(segments);
-
- n = i / SEGS_PER_INDIRECT_FRAME;
- if (!info->feature_persistent) {
- struct page *indirect_page;
-
- /* Fetch a pre-allocated page to use for indirect grefs */
- BUG_ON(list_empty(&info->indirect_pages));
- indirect_page = list_first_entry(&info->indirect_pages,
- struct page, lru);
- list_del(&indirect_page->lru);
- pfn = page_to_pfn(indirect_page);
- }
- gnt_list_entry = get_grant(&gref_head, pfn, info);
- info->shadow[id].indirect_grants[n] = gnt_list_entry;
- segments = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
- ring_req->u.indirect.indirect_grefs[n] = gnt_list_entry->gref;
- }
-
- gnt_list_entry = get_grant(&gref_head, page_to_pfn(sg_page(sg)), info);
- ref = gnt_list_entry->gref;
-
- info->shadow[id].grants_used[i] = gnt_list_entry;
-
- if (rq_data_dir(req) && info->feature_persistent) {
- char *bvec_data;
- void *shared_data;
+ ring_req->u.rw.nr_segments = num_grant;
+ }
- BUG_ON(sg->offset + sg->length > PAGE_SIZE);
+ setup.ring_req = ring_req;
+ setup.id = id;
+ for_each_sg(info->shadow[id].sg, sg, num_sg, i) {
+ BUG_ON(sg->offset + sg->length > PAGE_SIZE);
- shared_data = kmap_atomic(pfn_to_page(gnt_list_entry->pfn));
- bvec_data = kmap_atomic(sg_page(sg));
+ if (setup.need_copy) {
+ setup.bvec_off = sg->offset;
+ setup.bvec_data = kmap_atomic(sg_page(sg));
+ }
- /*
- * this does not wipe data stored outside the
- * range sg->offset..sg->offset+sg->length.
- * Therefore, blkback *could* see data from
- * previous requests. This is OK as long as
- * persistent grants are shared with just one
- * domain. It may need refactoring if this
- * changes
- */
- memcpy(shared_data + sg->offset,
- bvec_data + sg->offset,
- sg->length);
+ gnttab_foreach_grant_in_range(sg_page(sg),
+ sg->offset,
+ sg->length,
+ blkif_setup_rw_req_grant,
+ &setup);
- kunmap_atomic(bvec_data);
- kunmap_atomic(shared_data);
- }
- if (ring_req->operation != BLKIF_OP_INDIRECT) {
- ring_req->u.rw.seg[i] =
- (struct blkif_request_segment) {
- .gref = ref,
- .first_sect = fsect,
- .last_sect = lsect };
- } else {
- n = i % SEGS_PER_INDIRECT_FRAME;
- segments[n] =
- (struct blkif_request_segment) {
- .gref = ref,
- .first_sect = fsect,
- .last_sect = lsect };
- }
- }
- if (segments)
- kunmap_atomic(segments);
+ if (setup.need_copy)
+ kunmap_atomic(setup.bvec_data);
}
+ if (setup.segments)
+ kunmap_atomic(setup.segments);
info->ring.req_prod_pvt++;
@@ -592,11 +700,29 @@ static int blkif_queue_request(struct request *req)
info->shadow[id].req = *ring_req;
if (new_persistent_gnts)
- gnttab_free_grant_references(gref_head);
+ gnttab_free_grant_references(setup.gref_head);
return 0;
}
+/*
+ * Generate a Xen blkfront IO request from a blk layer request. Reads
+ * and writes are handled as expected.
+ *
+ * @req: a request struct
+ */
+static int blkif_queue_request(struct request *req)
+{
+ struct blkfront_info *info = req->rq_disk->private_data;
+
+ if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
+ return 1;
+
+ if (unlikely(req->cmd_flags & (REQ_DISCARD | REQ_SECURE)))
+ return blkif_queue_discard_req(req);
+ else
+ return blkif_queue_rw_req(req);
+}
static inline void flush_requests(struct blkfront_info *info)
{
@@ -691,14 +817,14 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, sector_size);
blk_queue_physical_block_size(rq, physical_sector_size);
- blk_queue_max_hw_sectors(rq, (segments * PAGE_SIZE) / 512);
+ blk_queue_max_hw_sectors(rq, (segments * XEN_PAGE_SIZE) / 512);
/* Each segment in a request is up to an aligned page in size. */
blk_queue_segment_boundary(rq, PAGE_SIZE - 1);
blk_queue_max_segment_size(rq, PAGE_SIZE);
/* Ensure a merged request will fit in a single I/O ring slot. */
- blk_queue_max_segments(rq, segments);
+ blk_queue_max_segments(rq, segments / GRANTS_PER_PSEG);
/* Make sure buffer addresses are sector-aligned. */
blk_queue_dma_alignment(rq, 511);
@@ -972,7 +1098,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
info->persistent_gnts_c--;
}
if (info->feature_persistent)
- __free_page(pfn_to_page(persistent_gnt->pfn));
+ __free_page(persistent_gnt->page);
kfree(persistent_gnt);
}
}
@@ -1007,7 +1133,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
persistent_gnt = info->shadow[i].grants_used[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
if (info->feature_persistent)
- __free_page(pfn_to_page(persistent_gnt->pfn));
+ __free_page(persistent_gnt->page);
kfree(persistent_gnt);
}
@@ -1021,7 +1147,7 @@ static void blkif_free(struct blkfront_info *info, int suspend)
for (j = 0; j < INDIRECT_GREFS(segs); j++) {
persistent_gnt = info->shadow[i].indirect_grants[j];
gnttab_end_foreign_access(persistent_gnt->gref, 0, 0UL);
- __free_page(pfn_to_page(persistent_gnt->pfn));
+ __free_page(persistent_gnt->page);
kfree(persistent_gnt);
}
@@ -1057,33 +1183,65 @@ free_shadow:
}
+struct copy_from_grant {
+ const struct blk_shadow *s;
+ unsigned int grant_idx;
+ unsigned int bvec_offset;
+ char *bvec_data;
+};
+
+static void blkif_copy_from_grant(unsigned long gfn, unsigned int offset,
+ unsigned int len, void *data)
+{
+ struct copy_from_grant *info = data;
+ char *shared_data;
+ /* Convenient aliases */
+ const struct blk_shadow *s = info->s;
+
+ shared_data = kmap_atomic(s->grants_used[info->grant_idx]->page);
+
+ memcpy(info->bvec_data + info->bvec_offset,
+ shared_data + offset, len);
+
+ info->bvec_offset += len;
+ info->grant_idx++;
+
+ kunmap_atomic(shared_data);
+}
+
static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
struct blkif_response *bret)
{
int i = 0;
struct scatterlist *sg;
- char *bvec_data;
- void *shared_data;
- int nseg;
+ int num_sg, num_grant;
+ struct copy_from_grant data = {
+ .s = s,
+ .grant_idx = 0,
+ };
- nseg = s->req.operation == BLKIF_OP_INDIRECT ?
+ num_grant = s->req.operation == BLKIF_OP_INDIRECT ?
s->req.u.indirect.nr_segments : s->req.u.rw.nr_segments;
+ num_sg = s->num_sg;
if (bret->operation == BLKIF_OP_READ && info->feature_persistent) {
- for_each_sg(s->sg, sg, nseg, i) {
+ for_each_sg(s->sg, sg, num_sg, i) {
BUG_ON(sg->offset + sg->length > PAGE_SIZE);
- shared_data = kmap_atomic(
- pfn_to_page(s->grants_used[i]->pfn));
- bvec_data = kmap_atomic(sg_page(sg));
- memcpy(bvec_data + sg->offset,
- shared_data + sg->offset,
- sg->length);
- kunmap_atomic(bvec_data);
- kunmap_atomic(shared_data);
+
+ data.bvec_offset = sg->offset;
+ data.bvec_data = kmap_atomic(sg_page(sg));
+
+ gnttab_foreach_grant_in_range(sg_page(sg),
+ sg->offset,
+ sg->length,
+ blkif_copy_from_grant,
+ &data);
+
+ kunmap_atomic(data.bvec_data);
}
}
/* Add the persistent grant into the list of free grants */
- for (i = 0; i < nseg; i++) {
+ for (i = 0; i < num_grant; i++) {
if (gnttab_query_foreign_access(s->grants_used[i]->gref)) {
/*
* If the grant is still mapped by the backend (the
@@ -1109,7 +1267,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
}
}
if (s->req.operation == BLKIF_OP_INDIRECT) {
- for (i = 0; i < INDIRECT_GREFS(nseg); i++) {
+ for (i = 0; i < INDIRECT_GREFS(num_grant); i++) {
if (gnttab_query_foreign_access(s->indirect_grants[i]->gref)) {
if (!info->feature_persistent)
pr_alert_ratelimited("backed has not unmapped grant: %u\n",
@@ -1125,7 +1283,7 @@ static void blkif_completion(struct blk_shadow *s, struct blkfront_info *info,
* available pages for indirect grefs.
*/
if (!info->feature_persistent) {
- indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+ indirect_page = s->indirect_grants[i]->page;
list_add(&indirect_page->lru, &info->indirect_pages);
}
s->indirect_grants[i]->gref = GRANT_INVALID_REF;
@@ -1254,8 +1412,8 @@ static int setup_blkring(struct xenbus_device *dev,
{
struct blkif_sring *sring;
int err, i;
- unsigned long ring_size = info->nr_ring_pages * PAGE_SIZE;
- grant_ref_t gref[XENBUS_MAX_RING_PAGES];
+ unsigned long ring_size = info->nr_ring_pages * XEN_PAGE_SIZE;
+ grant_ref_t gref[XENBUS_MAX_RING_GRANTS];
for (i = 0; i < info->nr_ring_pages; i++)
info->ring_ref[i] = GRANT_INVALID_REF;
@@ -1583,8 +1741,8 @@ static int blkif_recover(struct blkfront_info *info)
atomic_set(&split_bio->pending, pending);
split_bio->bio = bio;
for (i = 0; i < pending; i++) {
- offset = (i * segs * PAGE_SIZE) >> 9;
- size = min((unsigned int)(segs * PAGE_SIZE) >> 9,
+ offset = (i * segs * XEN_PAGE_SIZE) >> 9;
+ size = min((unsigned int)(segs * XEN_PAGE_SIZE) >> 9,
(unsigned int)bio_sectors(bio) - offset);
cloned_bio = bio_clone(bio, GFP_NOIO);
BUG_ON(cloned_bio == NULL);
@@ -1695,15 +1853,17 @@ static void blkfront_setup_discard(struct blkfront_info *info)
static int blkfront_setup_indirect(struct blkfront_info *info)
{
- unsigned int segs;
+ unsigned int psegs, grants;
int err, i;
if (info->max_indirect_segments == 0)
- segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
+ grants = BLKIF_MAX_SEGMENTS_PER_REQUEST;
else
- segs = info->max_indirect_segments;
+ grants = info->max_indirect_segments;
+ psegs = grants / GRANTS_PER_PSEG;
- err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
+ err = fill_grant_buffer(info,
+ (grants + INDIRECT_GREFS(grants)) * BLK_RING_SIZE(info));
if (err)
goto out_of_memory;
@@ -1713,7 +1873,7 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
* grants, we need to allocate a set of pages that can be
* used for mapping indirect grefs
*/
- int num = INDIRECT_GREFS(segs) * BLK_RING_SIZE(info);
+ int num = INDIRECT_GREFS(grants) * BLK_RING_SIZE(info);
BUG_ON(!list_empty(&info->indirect_pages));
for (i = 0; i < num; i++) {
@@ -1726,20 +1886,20 @@ static int blkfront_setup_indirect(struct blkfront_info *info)
for (i = 0; i < BLK_RING_SIZE(info); i++) {
info->shadow[i].grants_used = kzalloc(
- sizeof(info->shadow[i].grants_used[0]) * segs,
+ sizeof(info->shadow[i].grants_used[0]) * grants,
GFP_NOIO);
- info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * segs, GFP_NOIO);
+ info->shadow[i].sg = kzalloc(sizeof(info->shadow[i].sg[0]) * psegs, GFP_NOIO);
if (info->max_indirect_segments)
info->shadow[i].indirect_grants = kzalloc(
sizeof(info->shadow[i].indirect_grants[0]) *
- INDIRECT_GREFS(segs),
+ INDIRECT_GREFS(grants),
GFP_NOIO);
if ((info->shadow[i].grants_used == NULL) ||
(info->shadow[i].sg == NULL) ||
(info->max_indirect_segments &&
(info->shadow[i].indirect_grants == NULL)))
goto out_of_memory;
- sg_init_table(info->shadow[i].sg, segs);
+ sg_init_table(info->shadow[i].sg, psegs);
}
@@ -1956,7 +2116,8 @@ static void blkback_changed(struct xenbus_device *dev,
break;
/* Missed the backend's Closing state -- fallthrough */
case XenbusStateClosing:
- blkfront_closing(info);
+ if (info)
+ blkfront_closing(info);
break;
}
}
@@ -2124,9 +2285,9 @@ static int __init xlblk_init(void)
if (!xen_domain())
return -ENODEV;
- if (xen_blkif_max_ring_order > XENBUS_MAX_RING_PAGE_ORDER) {
+ if (xen_blkif_max_ring_order > XENBUS_MAX_RING_GRANT_ORDER) {
pr_info("Invalid max_ring_order (%d), will use default max: %d.\n",
- xen_blkif_max_ring_order, XENBUS_MAX_RING_PAGE_ORDER);
+ xen_blkif_max_ring_order, XENBUS_MAX_RING_GRANT_ORDER);
xen_blkif_max_ring_order = 0;
}
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 9fa15bb9d118..47915d736f8d 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -106,7 +106,7 @@ static void zram_set_obj_size(struct zram_meta *meta,
meta->table[index].value = (flags << ZRAM_FLAG_SHIFT) | size;
}
-static inline int is_partial_io(struct bio_vec *bvec)
+static inline bool is_partial_io(struct bio_vec *bvec)
{
return bvec->bv_len != PAGE_SIZE;
}
@@ -114,25 +114,25 @@ static inline int is_partial_io(struct bio_vec *bvec)
/*
* Check if request is within bounds and aligned on zram logical blocks.
*/
-static inline int valid_io_request(struct zram *zram,
+static inline bool valid_io_request(struct zram *zram,
sector_t start, unsigned int size)
{
u64 end, bound;
/* unaligned request */
if (unlikely(start & (ZRAM_SECTOR_PER_LOGICAL_BLOCK - 1)))
- return 0;
+ return false;
if (unlikely(size & (ZRAM_LOGICAL_BLOCK_SIZE - 1)))
- return 0;
+ return false;
end = start + (size >> SECTOR_SHIFT);
bound = zram->disksize >> SECTOR_SHIFT;
/* out of range range */
if (unlikely(start >= bound || end > bound || start > end))
- return 0;
+ return false;
/* I/O request is valid */
- return 1;
+ return true;
}
static void update_position(u32 *index, int *offset, struct bio_vec *bvec)
@@ -157,7 +157,7 @@ static inline void update_used_max(struct zram *zram,
} while (old_max != cur_max);
}
-static int page_zero_filled(void *ptr)
+static bool page_zero_filled(void *ptr)
{
unsigned int pos;
unsigned long *page;
@@ -166,10 +166,10 @@ static int page_zero_filled(void *ptr)
for (pos = 0; pos != PAGE_SIZE / sizeof(*page); pos++) {
if (page[pos])
- return 0;
+ return false;
}
- return 1;
+ return true;
}
static void handle_zero_page(struct bio_vec *bvec)
@@ -365,6 +365,9 @@ static ssize_t comp_algorithm_store(struct device *dev,
struct zram *zram = dev_to_zram(dev);
size_t sz;
+ if (!zcomp_available_algorithm(buf))
+ return -EINVAL;
+
down_write(&zram->init_lock);
if (init_done(zram)) {
up_write(&zram->init_lock);
@@ -378,9 +381,6 @@ static ssize_t comp_algorithm_store(struct device *dev,
if (sz > 0 && zram->compressor[sz - 1] == '\n')
zram->compressor[sz - 1] = 0x00;
- if (!zcomp_available_algorithm(zram->compressor))
- len = -EINVAL;
-
up_write(&zram->init_lock);
return len;
}
@@ -726,14 +726,14 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
}
alloced_pages = zs_get_total_pages(meta->mem_pool);
+ update_used_max(zram, alloced_pages);
+
if (zram->limit_pages && alloced_pages > zram->limit_pages) {
zs_free(meta->mem_pool, handle);
ret = -ENOMEM;
goto out;
}
- update_used_max(zram, alloced_pages);
-
cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO);
if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) {
@@ -894,7 +894,7 @@ out:
/*
* Handler function for all zram I/O requests.
*/
-static void zram_make_request(struct request_queue *queue, struct bio *bio)
+static blk_qc_t zram_make_request(struct request_queue *queue, struct bio *bio)
{
struct zram *zram = queue->queuedata;
@@ -911,11 +911,12 @@ static void zram_make_request(struct request_queue *queue, struct bio *bio)
__zram_make_request(zram, bio);
zram_meta_put(zram);
- return;
+ return BLK_QC_T_NONE;
put_zram:
zram_meta_put(zram);
error:
bio_io_error(bio);
+ return BLK_QC_T_NONE;
}
static void zram_slot_free_notify(struct block_device *bdev,
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-29 03:18:34 +0100