summaryrefslogtreecommitdiffstats
path: root/drivers
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-05-01 10:39:57 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2017-05-01 10:39:57 -0700
commit694752922b12bd318aa80191bd9d8c3dcfb39055 (patch)
tree5afe83fd99100bea546dd5a1c1f778c58f41e5c0 /drivers
parenta351e9b9fc24e982ec2f0e76379a49826036da12 (diff)
parent9438b3e080beccf6022138ea62192d55cc7dc4ed (diff)
downloadlinux-694752922b12bd318aa80191bd9d8c3dcfb39055.tar.bz2
Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe: - Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ was initially a fork of CFQ, but subsequently changed to implement fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant to be used on desktop type single drives, providing good fairness. From Paolo. - Add Kyber IO scheduler. This is a full multiqueue aware scheduler, using a scalable token based algorithm that throttles IO based on live completion IO stats, similary to blk-wbt. From Omar. - A series from Jan, moving users to separately allocated backing devices. This continues the work of separating backing device life times, solving various problems with hot removal. - A series of updates for lightnvm, mostly from Javier. Includes a 'pblk' target that exposes an open channel SSD as a physical block device. - A series of fixes and improvements for nbd from Josef. - A series from Omar, removing queue sharing between devices on mostly legacy drivers. This helps us clean up other bits, if we know that a queue only has a single device backing. This has been overdue for more than a decade. - Fixes for the blk-stats, and improvements to unify the stats and user windows. This both improves blk-wbt, and enables other users to register a need to receive IO stats for a device. From Omar. - blk-throttle improvements from Shaohua. This provides a scalable framework for implementing scalable priotization - particularly for blk-mq, but applicable to any type of block device. The interface is marked experimental for now. - Bucketized IO stats for IO polling from Stephen Bates. This improves efficiency of polled workloads in the presence of mixed block size IO. - A few fixes for opal, from Scott. - A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics. From a variety of folks, mostly Sagi and James Smart. - A series from Bart, improving our exposed info and capabilities from the blk-mq debugfs support. - A series from Christoph, cleaning up how handle WRITE_ZEROES. - A series from Christoph, cleaning up the block layer handling of how we track errors in a request. On top of being a nice cleanup, it also shrinks the size of struct request a bit. - Removal of mg_disk and hd (sorry Linus) by Christoph. The former was never used by platforms, and the latter has outlived it's usefulness. - Various little bug fixes and cleanups from a wide variety of folks. * 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits) block: hide badblocks attribute by default blk-mq: unify hctx delay_work and run_work block: add kblock_mod_delayed_work_on() blk-mq: unify hctx delayed_run_work and run_work nbd: fix use after free on module unload MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler blk-mq-sched: alloate reserved tags out of normal pool mtip32xx: use runtime tag to initialize command header scsi: Implement blk_mq_ops.show_rq() blk-mq: Add blk_mq_ops.show_rq() blk-mq: Show operation, cmd_flags and rq_flags names blk-mq: Make blk_flags_show() callers append a newline character blk-mq: Move the "state" debugfs attribute one level down blk-mq: Unregister debugfs attributes earlier blk-mq: Only unregister hctxs for which registration succeeded blk-mq-debugfs: Rename functions for registering and unregistering the mq directory blk-mq: Let blk_mq_debugfs_register() look up the queue name blk-mq: Register <dev>/queue/mq after having registered <dev>/queue ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset ide-pm: always pass 0 error to __blk_end_request_all ..
Diffstat (limited to 'drivers')
-rw-r--r--drivers/block/Kconfig47
-rw-r--r--drivers/block/Makefile3
-rw-r--r--drivers/block/ataflop.c12
-rw-r--r--drivers/block/brd.c54
-rw-r--r--drivers/block/cciss.c42
-rw-r--r--drivers/block/drbd/drbd_debugfs.c3
-rw-r--r--drivers/block/drbd/drbd_int.h6
-rw-r--r--drivers/block/drbd/drbd_main.c5
-rw-r--r--drivers/block/drbd/drbd_nl.c9
-rw-r--r--drivers/block/drbd/drbd_receiver.c105
-rw-r--r--drivers/block/drbd/drbd_req.c13
-rw-r--r--drivers/block/drbd/drbd_worker.c4
-rw-r--r--drivers/block/floppy.c10
-rw-r--r--drivers/block/hd.c803
-rw-r--r--drivers/block/loop.c38
-rw-r--r--drivers/block/loop.h1
-rw-r--r--drivers/block/mg_disk.c1112
-rw-r--r--drivers/block/mtip32xx/mtip32xx.c58
-rw-r--r--drivers/block/mtip32xx/mtip32xx.h1
-rw-r--r--drivers/block/nbd.c1417
-rw-r--r--drivers/block/null_blk.c22
-rw-r--r--drivers/block/osdblk.c693
-rw-r--r--drivers/block/paride/pcd.c57
-rw-r--r--drivers/block/paride/pd.c57
-rw-r--r--drivers/block/paride/pf.c57
-rw-r--r--drivers/block/pktcdvd.c2
-rw-r--r--drivers/block/rbd.c3
-rw-r--r--drivers/block/rsxx/dev.c1
-rw-r--r--drivers/block/swim.c55
-rw-r--r--drivers/block/swim3.c4
-rw-r--r--drivers/block/virtio_blk.c21
-rw-r--r--drivers/block/xen-blkfront.c41
-rw-r--r--drivers/block/zram/zram_drv.c13
-rw-r--r--drivers/cdrom/cdrom.c3
-rw-r--r--drivers/ide/ide-atapi.c11
-rw-r--r--drivers/ide/ide-cd.c21
-rw-r--r--drivers/ide/ide-cd_ioctl.c3
-rw-r--r--drivers/ide/ide-devsets.c8
-rw-r--r--drivers/ide/ide-disk.c3
-rw-r--r--drivers/ide/ide-dma.c2
-rw-r--r--drivers/ide/ide-eh.c36
-rw-r--r--drivers/ide/ide-floppy.c10
-rw-r--r--drivers/ide/ide-io.c10
-rw-r--r--drivers/ide/ide-ioctls.c7
-rw-r--r--drivers/ide/ide-park.c3
-rw-r--r--drivers/ide/ide-pm.c9
-rw-r--r--drivers/ide/ide-tape.c4
-rw-r--r--drivers/ide/ide-taskfile.c8
-rw-r--r--drivers/lightnvm/Kconfig9
-rw-r--r--drivers/lightnvm/Makefile5
-rw-r--r--drivers/lightnvm/core.c147
-rw-r--r--drivers/lightnvm/pblk-cache.c114
-rw-r--r--drivers/lightnvm/pblk-core.c1667
-rw-r--r--drivers/lightnvm/pblk-gc.c555
-rw-r--r--drivers/lightnvm/pblk-init.c962
-rw-r--r--drivers/lightnvm/pblk-map.c136
-rw-r--r--drivers/lightnvm/pblk-rb.c852
-rw-r--r--drivers/lightnvm/pblk-read.c529
-rw-r--r--drivers/lightnvm/pblk-recovery.c998
-rw-r--r--drivers/lightnvm/pblk-rl.c184
-rw-r--r--drivers/lightnvm/pblk-sysfs.c507
-rw-r--r--drivers/lightnvm/pblk-write.c414
-rw-r--r--drivers/lightnvm/pblk.h1121
-rw-r--r--drivers/lightnvm/rrpc.c25
-rw-r--r--drivers/md/dm-cache-target.c1
-rw-r--r--drivers/md/dm-core.h1
-rw-r--r--drivers/md/dm-crypt.c1
-rw-r--r--drivers/md/dm-io.c18
-rw-r--r--drivers/md/dm-kcopyd.c6
-rw-r--r--drivers/md/dm-linear.c1
-rw-r--r--drivers/md/dm-mpath.c3
-rw-r--r--drivers/md/dm-raid.c6
-rw-r--r--drivers/md/dm-raid1.c1
-rw-r--r--drivers/md/dm-rq.c15
-rw-r--r--drivers/md/dm-stripe.c2
-rw-r--r--drivers/md/dm-table.c49
-rw-r--r--drivers/md/dm-thin.c2
-rw-r--r--drivers/md/dm.c32
-rw-r--r--drivers/md/linear.c1
-rw-r--r--drivers/md/md.h7
-rw-r--r--drivers/md/multipath.c1
-rw-r--r--drivers/md/raid0.c2
-rw-r--r--drivers/md/raid1.c4
-rw-r--r--drivers/md/raid10.c1
-rw-r--r--drivers/md/raid5.c53
-rw-r--r--drivers/mmc/core/queue.c2
-rw-r--r--drivers/mtd/mtdcore.c23
-rw-r--r--drivers/mtd/mtdsuper.c6
-rw-r--r--drivers/mtd/ubi/block.c2
-rw-r--r--drivers/nvme/host/core.c94
-rw-r--r--drivers/nvme/host/fabrics.c28
-rw-r--r--drivers/nvme/host/fabrics.h10
-rw-r--r--drivers/nvme/host/fc.c223
-rw-r--r--drivers/nvme/host/lightnvm.c49
-rw-r--r--drivers/nvme/host/nvme.h48
-rw-r--r--drivers/nvme/host/pci.c223
-rw-r--r--drivers/nvme/host/rdma.c154
-rw-r--r--drivers/nvme/target/admin-cmd.c31
-rw-r--r--drivers/nvme/target/core.c21
-rw-r--r--drivers/nvme/target/discovery.c19
-rw-r--r--drivers/nvme/target/fabrics-cmd.c36
-rw-r--r--drivers/nvme/target/fc.c274
-rw-r--r--drivers/nvme/target/fcloop.c197
-rw-r--r--drivers/nvme/target/io-cmd.c24
-rw-r--r--drivers/nvme/target/loop.c92
-rw-r--r--drivers/nvme/target/nvmet.h11
-rw-r--r--drivers/nvme/target/rdma.c47
-rw-r--r--drivers/sbus/char/jsflash.c50
-rw-r--r--drivers/scsi/Makefile1
-rw-r--r--drivers/scsi/lpfc/lpfc_nvmet.c126
-rw-r--r--drivers/scsi/lpfc/lpfc_nvmet.h7
-rw-r--r--drivers/scsi/osd/osd_initiator.c9
-rw-r--r--drivers/scsi/osst.c4
-rw-r--r--drivers/scsi/qla2xxx/qla_bsg.c6
-rw-r--r--drivers/scsi/scsi_debugfs.c13
-rw-r--r--drivers/scsi/scsi_debugfs.h4
-rw-r--r--drivers/scsi/scsi_error.c2
-rw-r--r--drivers/scsi/scsi_lib.c25
-rw-r--r--drivers/scsi/scsi_transport_sas.c4
-rw-r--r--drivers/scsi/sd.c259
-rw-r--r--drivers/scsi/sd.h8
-rw-r--r--drivers/scsi/sd_zbc.c1
-rw-r--r--drivers/scsi/sg.c4
-rw-r--r--drivers/scsi/st.c8
-rw-r--r--drivers/staging/lustre/lustre/include/lustre_disk.h4
-rw-r--r--drivers/staging/lustre/lustre/llite/llite_lib.c24
-rw-r--r--drivers/target/iscsi/iscsi_target_configfs.c46
-rw-r--r--drivers/target/target_core_device.c2
-rw-r--r--drivers/target/target_core_pscsi.c4
129 files changed, 11309 insertions, 4255 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index f744de7a0f9b..19df4918e37e 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -312,22 +312,6 @@ config BLK_DEV_SKD
Use device /dev/skd$N amd /dev/skd$Np$M.
-config BLK_DEV_OSD
- tristate "OSD object-as-blkdev support"
- depends on SCSI_OSD_ULD
- ---help---
- Saying Y or M here will allow the exporting of a single SCSI
- OSD (object-based storage) object as a Linux block device.
-
- For example, if you create a 2G object on an OSD device,
- you can then use this module to present that 2G object as
- a Linux block device.
-
- To compile this driver as a module, choose M here: the
- module will be called osdblk.
-
- If unsure, say N.
-
config BLK_DEV_SX8
tristate "Promise SATA SX8 support"
depends on PCI
@@ -434,23 +418,6 @@ config ATA_OVER_ETH
This driver provides Support for ATA over Ethernet block
devices like the Coraid EtherDrive (R) Storage Blade.
-config MG_DISK
- tristate "mGine mflash, gflash support"
- depends on ARM && GPIOLIB
- help
- mGine mFlash(gFlash) block device driver
-
-config MG_DISK_RES
- int "Size of reserved area before MBR"
- depends on MG_DISK
- default 0
- help
- Define size of reserved area that usually used for boot. Unit is KB.
- All of the block device operation will be taken this value as start
- offset
- Examples:
- 1024 => 1 MB
-
config SUNVDC
tristate "Sun Virtual Disk Client support"
depends on SUN_LDOMS
@@ -512,19 +479,7 @@ config VIRTIO_BLK_SCSI
Enable support for SCSI passthrough (e.g. the SG_IO ioctl) on
virtio-blk devices. This is only supported for the legacy
virtio protocol and not enabled by default by any hypervisor.
- Your probably want to virtio-scsi instead.
-
-config BLK_DEV_HD
- bool "Very old hard disk (MFM/RLL/IDE) driver"
- depends on HAVE_IDE
- depends on !ARM || ARCH_RPC || BROKEN
- help
- This is a very old hard disk driver that lacks the enhanced
- functionality of the newer ones.
-
- It is required for systems with ancient MFM/RLL/ESDI drives.
-
- If unsure, say N.
+ You probably want to use virtio-scsi instead.
config BLK_DEV_RBD
tristate "Rados block device (RBD)"
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 1e9661e26f29..ec8c36897b75 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -19,10 +19,8 @@ obj-$(CONFIG_BLK_CPQ_CISS_DA) += cciss.o
obj-$(CONFIG_BLK_DEV_DAC960) += DAC960.o
obj-$(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_SKD) += skd.o
-obj-$(CONFIG_BLK_DEV_OSD) += osdblk.o
obj-$(CONFIG_BLK_DEV_UMEM) += umem.o
obj-$(CONFIG_BLK_DEV_NBD) += nbd.o
@@ -30,7 +28,6 @@ obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o
obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
-obj-$(CONFIG_BLK_DEV_HD) += hd.o
obj-$(CONFIG_XEN_BLKDEV_FRONTEND) += xen-blkfront.o
obj-$(CONFIG_XEN_BLKDEV_BACKEND) += xen-blkback/
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 2104b1b4ccda..fa69ecd52cb5 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -617,12 +617,12 @@ static void fd_error( void )
if (!fd_request)
return;
- fd_request->errors++;
- if (fd_request->errors >= MAX_ERRORS) {
+ fd_request->error_count++;
+ if (fd_request->error_count >= MAX_ERRORS) {
printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive );
fd_end_request_cur(-EIO);
}
- else if (fd_request->errors == RECALIBRATE_ERRORS) {
+ else if (fd_request->error_count == RECALIBRATE_ERRORS) {
printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive );
if (SelectedDrive != -1)
SUD.track = -1;
@@ -1386,7 +1386,7 @@ static void setup_req_params( int drive )
ReqData = ReqBuffer + 512 * ReqCnt;
if (UseTrackbuffer)
- read_track = (ReqCmd == READ && fd_request->errors == 0);
+ read_track = (ReqCmd == READ && fd_request->error_count == 0);
else
read_track = 0;
@@ -1409,8 +1409,10 @@ static struct request *set_next_request(void)
fdc_queue = 0;
if (q) {
rq = blk_fetch_request(q);
- if (rq)
+ if (rq) {
+ rq->error_count = 0;
break;
+ }
}
} while (fdc_queue != old_pos);
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 3adc32a3153b..4ec84d504780 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -134,28 +134,6 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector)
return page;
}
-static void brd_free_page(struct brd_device *brd, sector_t sector)
-{
- struct page *page;
- pgoff_t idx;
-
- spin_lock(&brd->brd_lock);
- idx = sector >> PAGE_SECTORS_SHIFT;
- page = radix_tree_delete(&brd->brd_pages, idx);
- spin_unlock(&brd->brd_lock);
- if (page)
- __free_page(page);
-}
-
-static void brd_zero_page(struct brd_device *brd, sector_t sector)
-{
- struct page *page;
-
- page = brd_lookup_page(brd, sector);
- if (page)
- clear_highpage(page);
-}
-
/*
* Free all backing store pages and radix tree. This must only be called when
* there are no other users of the device.
@@ -212,24 +190,6 @@ static int copy_to_brd_setup(struct brd_device *brd, sector_t sector, size_t n)
return 0;
}
-static void discard_from_brd(struct brd_device *brd,
- sector_t sector, size_t n)
-{
- while (n >= PAGE_SIZE) {
- /*
- * Don't want to actually discard pages here because
- * re-allocating the pages can result in writeback
- * deadlocks under heavy load.
- */
- if (0)
- brd_free_page(brd, sector);
- else
- brd_zero_page(brd, sector);
- sector += PAGE_SIZE >> SECTOR_SHIFT;
- n -= PAGE_SIZE;
- }
-}
-
/*
* Copy n bytes from src to the brd starting at sector. Does not sleep.
*/
@@ -338,14 +298,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
if (bio_end_sector(bio) > get_capacity(bdev->bd_disk))
goto io_error;
- if (unlikely(bio_op(bio) == REQ_OP_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;
- }
-
bio_for_each_segment(bvec, bio, iter) {
unsigned int len = bvec.bv_len;
int err;
@@ -357,7 +309,6 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
sector += len >> SECTOR_SHIFT;
}
-out:
bio_endio(bio);
return BLK_QC_T_NONE;
io_error:
@@ -464,11 +415,6 @@ static struct brd_device *brd_alloc(int i)
* is harmless)
*/
blk_queue_physical_block_size(brd->brd_queue, PAGE_SIZE);
-
- brd->brd_queue->limits.discard_granularity = PAGE_SIZE;
- blk_queue_max_discard_sectors(brd->brd_queue, UINT_MAX);
- brd->brd_queue->limits.discard_zeroes_data = 1;
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, brd->brd_queue);
#ifdef CONFIG_BLK_DEV_RAM_DAX
queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue);
#endif
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 8e1a4554951c..cd375503f7b0 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1864,8 +1864,7 @@ static void cciss_softirq_done(struct request *rq)
/* set the residual count for pc requests */
if (blk_rq_is_passthrough(rq))
scsi_req(rq)->resid_len = c->err_info->ResidualCnt;
-
- blk_end_request_all(rq, (rq->errors == 0) ? 0 : -EIO);
+ blk_end_request_all(rq, scsi_req(rq)->result ? -EIO : 0);
spin_lock_irqsave(&h->lock, flags);
cmd_free(h, c);
@@ -3140,18 +3139,19 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
{
int retry_cmd = 0;
struct request *rq = cmd->rq;
+ struct scsi_request *sreq = scsi_req(rq);
- rq->errors = 0;
+ sreq->result = 0;
if (timeout)
- rq->errors = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
+ sreq->result = make_status_bytes(0, 0, 0, DRIVER_TIMEOUT);
if (cmd->err_info->CommandStatus == 0) /* no error has occurred */
goto after_error_processing;
switch (cmd->err_info->CommandStatus) {
case CMD_TARGET_STATUS:
- rq->errors = evaluate_target_status(h, cmd, &retry_cmd);
+ sreq->result = evaluate_target_status(h, cmd, &retry_cmd);
break;
case CMD_DATA_UNDERRUN:
if (!blk_rq_is_passthrough(cmd->rq)) {
@@ -3169,7 +3169,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_INVALID:
dev_warn(&h->pdev->dev, "cciss: cmd %p is "
"reported invalid\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3177,7 +3177,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_PROTOCOL_ERR:
dev_warn(&h->pdev->dev, "cciss: cmd %p has "
"protocol error\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3185,7 +3185,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_HARDWARE_ERR:
dev_warn(&h->pdev->dev, "cciss: cmd %p had "
" hardware error\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3193,7 +3193,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_CONNECTION_LOST:
dev_warn(&h->pdev->dev, "cciss: cmd %p had "
"connection lost\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3201,7 +3201,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_ABORTED:
dev_warn(&h->pdev->dev, "cciss: cmd %p was "
"aborted\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ABORT);
@@ -3209,7 +3209,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
case CMD_ABORT_FAILED:
dev_warn(&h->pdev->dev, "cciss: cmd %p reports "
"abort failed\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3224,21 +3224,21 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
} else
dev_warn(&h->pdev->dev,
"%p retried too many times\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ABORT);
break;
case CMD_TIMEOUT:
dev_warn(&h->pdev->dev, "cmd %p timedout\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
break;
case CMD_UNABORTABLE:
dev_warn(&h->pdev->dev, "cmd %p unabortable\n", cmd);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3247,7 +3247,7 @@ static inline void complete_command(ctlr_info_t *h, CommandList_struct *cmd,
dev_warn(&h->pdev->dev, "cmd %p returned "
"unknown status %x\n", cmd,
cmd->err_info->CommandStatus);
- rq->errors = make_status_bytes(SAM_STAT_GOOD,
+ sreq->result = make_status_bytes(SAM_STAT_GOOD,
cmd->err_info->CommandStatus, DRIVER_OK,
blk_rq_is_passthrough(cmd->rq) ?
DID_PASSTHROUGH : DID_ERROR);
@@ -3380,9 +3380,9 @@ static void do_cciss_request(struct request_queue *q)
if (dma_mapping_error(&h->pdev->dev, temp64.val)) {
dev_warn(&h->pdev->dev,
"%s: error mapping page for DMA\n", __func__);
- creq->errors = make_status_bytes(SAM_STAT_GOOD,
- 0, DRIVER_OK,
- DID_SOFT_ERROR);
+ scsi_req(creq)->result =
+ make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+ DID_SOFT_ERROR);
cmd_free(h, c);
return;
}
@@ -3395,9 +3395,9 @@ static void do_cciss_request(struct request_queue *q)
if (cciss_map_sg_chain_block(h, c, h->cmd_sg_list[c->cmdindex],
(seg - (h->max_cmd_sgentries - 1)) *
sizeof(SGDescriptor_struct))) {
- creq->errors = make_status_bytes(SAM_STAT_GOOD,
- 0, DRIVER_OK,
- DID_SOFT_ERROR);
+ scsi_req(creq)->result =
+ make_status_bytes(SAM_STAT_GOOD, 0, DRIVER_OK,
+ DID_SOFT_ERROR);
cmd_free(h, c);
return;
}
diff --git a/drivers/block/drbd/drbd_debugfs.c b/drivers/block/drbd/drbd_debugfs.c
index de5c3ee8a790..494837e59f23 100644
--- a/drivers/block/drbd/drbd_debugfs.c
+++ b/drivers/block/drbd/drbd_debugfs.c
@@ -236,9 +236,6 @@ static void seq_print_peer_request_flags(struct seq_file *m, struct drbd_peer_re
seq_print_rq_state_bit(m, f & EE_CALL_AL_COMPLETE_IO, &sep, "in-AL");
seq_print_rq_state_bit(m, f & EE_SEND_WRITE_ACK, &sep, "C");
seq_print_rq_state_bit(m, f & EE_MAY_SET_IN_SYNC, &sep, "set-in-sync");
-
- if (f & EE_IS_TRIM)
- __seq_print_rq_state_bit(m, f & EE_IS_TRIM_USE_ZEROOUT, &sep, "zero-out", "trim");
seq_print_rq_state_bit(m, f & EE_WRITE_SAME, &sep, "write-same");
seq_putc(m, '\n');
}
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index 724d1c50fc52..d5da45bb03a6 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -437,9 +437,6 @@ enum {
/* is this a TRIM aka REQ_DISCARD? */
__EE_IS_TRIM,
- /* our lower level cannot handle trim,
- * and we want to fall back to zeroout instead */
- __EE_IS_TRIM_USE_ZEROOUT,
/* In case a barrier failed,
* we need to resubmit without the barrier flag. */
@@ -482,7 +479,6 @@ enum {
#define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
#define EE_MAY_SET_IN_SYNC (1<<__EE_MAY_SET_IN_SYNC)
#define EE_IS_TRIM (1<<__EE_IS_TRIM)
-#define EE_IS_TRIM_USE_ZEROOUT (1<<__EE_IS_TRIM_USE_ZEROOUT)
#define EE_RESUBMITTED (1<<__EE_RESUBMITTED)
#define EE_WAS_ERROR (1<<__EE_WAS_ERROR)
#define EE_HAS_DIGEST (1<<__EE_HAS_DIGEST)
@@ -1561,8 +1557,6 @@ extern void start_resync_timer_fn(unsigned long data);
extern void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req);
/* drbd_receiver.c */
-extern int drbd_issue_discard_or_zero_out(struct drbd_device *device,
- sector_t start, unsigned int nr_sectors, bool discard);
extern int drbd_receiver(struct drbd_thread *thi);
extern int drbd_ack_receiver(struct drbd_thread *thi);
extern void drbd_send_ping_wf(struct work_struct *ws);
diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index 92c60cbd04ee..84455c365f57 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -931,7 +931,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
p->qlim->io_min = cpu_to_be32(queue_io_min(q));
p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
p->qlim->discard_enabled = blk_queue_discard(q);
- p->qlim->discard_zeroes_data = queue_discard_zeroes_data(q);
p->qlim->write_same_capable = !!q->limits.max_write_same_sectors;
} else {
q = device->rq_queue;
@@ -941,7 +940,6 @@ void assign_p_sizes_qlim(struct drbd_device *device, struct p_sizes *p, struct r
p->qlim->io_min = cpu_to_be32(queue_io_min(q));
p->qlim->io_opt = cpu_to_be32(queue_io_opt(q));
p->qlim->discard_enabled = 0;
- p->qlim->discard_zeroes_data = 0;
p->qlim->write_same_capable = 0;
}
}
@@ -1668,7 +1666,8 @@ static u32 bio_flags_to_wire(struct drbd_connection *connection,
(bio->bi_opf & REQ_FUA ? DP_FUA : 0) |
(bio->bi_opf & REQ_PREFLUSH ? DP_FLUSH : 0) |
(bio_op(bio) == REQ_OP_WRITE_SAME ? DP_WSAME : 0) |
- (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0);
+ (bio_op(bio) == REQ_OP_DISCARD ? DP_DISCARD : 0) |
+ (bio_op(bio) == REQ_OP_WRITE_ZEROES ? DP_DISCARD : 0);
else
return bio->bi_opf & REQ_SYNC ? DP_RW_SYNC : 0;
}
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 908c704e20aa..02255a0d68b9 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1199,10 +1199,6 @@ static void decide_on_discard_support(struct drbd_device *device,
struct drbd_connection *connection = first_peer_device(device)->connection;
bool can_do = b ? blk_queue_discard(b) : true;
- if (can_do && b && !b->limits.discard_zeroes_data && !discard_zeroes_if_aligned) {
- can_do = false;
- drbd_info(device, "discard_zeroes_data=0 and discard_zeroes_if_aligned=no: disabling discards\n");
- }
if (can_do && connection->cstate >= C_CONNECTED && !(connection->agreed_features & DRBD_FF_TRIM)) {
can_do = false;
drbd_info(connection, "peer DRBD too old, does not support TRIM: disabling discards\n");
@@ -1217,10 +1213,12 @@ static void decide_on_discard_support(struct drbd_device *device,
blk_queue_discard_granularity(q, 512);
q->limits.max_discard_sectors = drbd_max_discard_sectors(connection);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+ q->limits.max_write_zeroes_sectors = drbd_max_discard_sectors(connection);
} else {
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
blk_queue_discard_granularity(q, 0);
q->limits.max_discard_sectors = 0;
+ q->limits.max_write_zeroes_sectors = 0;
}
}
@@ -1482,8 +1480,7 @@ static void sanitize_disk_conf(struct drbd_device *device, struct disk_conf *dis
if (disk_conf->al_extents > drbd_al_extents_max(nbc))
disk_conf->al_extents = drbd_al_extents_max(nbc);
- if (!blk_queue_discard(q)
- || (!q->limits.discard_zeroes_data && !disk_conf->discard_zeroes_if_aligned)) {
+ if (!blk_queue_discard(q)) {
if (disk_conf->rs_discard_granularity) {
disk_conf->rs_discard_granularity = 0; /* disable feature */
drbd_info(device, "rs_discard_granularity feature disabled\n");
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index aa6bf9692eff..1b0a2be24f39 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -1448,105 +1448,14 @@ void drbd_bump_write_ordering(struct drbd_resource *resource, struct drbd_backin
drbd_info(resource, "Method to ensure write ordering: %s\n", write_ordering_str[resource->write_ordering]);
}
-/*
- * We *may* ignore the discard-zeroes-data setting, if so configured.
- *
- * Assumption is that it "discard_zeroes_data=0" is only because the backend
- * may ignore partial unaligned discards.
- *
- * LVM/DM thin as of at least
- * LVM version: 2.02.115(2)-RHEL7 (2015-01-28)
- * Library version: 1.02.93-RHEL7 (2015-01-28)
- * Driver version: 4.29.0
- * still behaves this way.
- *
- * For unaligned (wrt. alignment and granularity) or too small discards,
- * we zero-out the initial (and/or) trailing unaligned partial chunks,
- * but discard all the aligned full chunks.
- *
- * At least for LVM/DM thin, the result is effectively "discard_zeroes_data=1".
- */
-int drbd_issue_discard_or_zero_out(struct drbd_device *device, sector_t start, unsigned int nr_sectors, bool discard)
-{
- struct block_device *bdev = device->ldev->backing_bdev;
- struct request_queue *q = bdev_get_queue(bdev);
- sector_t tmp, nr;
- unsigned int max_discard_sectors, granularity;
- int alignment;
- int err = 0;
-
- if (!discard)
- goto zero_out;
-
- /* Zero-sector (unknown) and one-sector granularities are the same. */
- granularity = max(q->limits.discard_granularity >> 9, 1U);
- alignment = (bdev_discard_alignment(bdev) >> 9) % granularity;
-
- max_discard_sectors = min(q->limits.max_discard_sectors, (1U << 22));
- max_discard_sectors -= max_discard_sectors % granularity;
- if (unlikely(!max_discard_sectors))
- goto zero_out;
-
- if (nr_sectors < granularity)
- goto zero_out;
-
- tmp = start;
- if (sector_div(tmp, granularity) != alignment) {
- if (nr_sectors < 2*granularity)
- goto zero_out;
- /* start + gran - (start + gran - align) % gran */
- tmp = start + granularity - alignment;
- tmp = start + granularity - sector_div(tmp, granularity);
-
- nr = tmp - start;
- err |= blkdev_issue_zeroout(bdev, start, nr, GFP_NOIO, 0);
- nr_sectors -= nr;
- start = tmp;
- }
- while (nr_sectors >= granularity) {
- nr = min_t(sector_t, nr_sectors, max_discard_sectors);
- err |= blkdev_issue_discard(bdev, start, nr, GFP_NOIO, 0);
- nr_sectors -= nr;
- start += nr;
- }
- zero_out:
- if (nr_sectors) {
- err |= blkdev_issue_zeroout(bdev, start, nr_sectors, GFP_NOIO, 0);
- }
- return err != 0;
-}
-
-static bool can_do_reliable_discards(struct drbd_device *device)
-{
- struct request_queue *q = bdev_get_queue(device->ldev->backing_bdev);
- struct disk_conf *dc;
- bool can_do;
-
- if (!blk_queue_discard(q))
- return false;
-
- if (q->limits.discard_zeroes_data)
- return true;
-
- rcu_read_lock();
- dc = rcu_dereference(device->ldev->disk_conf);
- can_do = dc->discard_zeroes_if_aligned;
- rcu_read_unlock();
- return can_do;
-}
-
static void drbd_issue_peer_discard(struct drbd_device *device, struct drbd_peer_request *peer_req)
{
- /* If the backend cannot discard, or does not guarantee
- * read-back zeroes in discarded ranges, we fall back to
- * zero-out. Unless configuration specifically requested
- * otherwise. */
- if (!can_do_reliable_discards(device))
- peer_req->flags |= EE_IS_TRIM_USE_ZEROOUT;
+ struct block_device *bdev = device->ldev->backing_bdev;
- if (drbd_issue_discard_or_zero_out(device, peer_req->i.sector,
- peer_req->i.size >> 9, !(peer_req->flags & EE_IS_TRIM_USE_ZEROOUT)))
+ if (blkdev_issue_zeroout(bdev, peer_req->i.sector, peer_req->i.size >> 9,
+ GFP_NOIO, 0))
peer_req->flags |= EE_WAS_ERROR;
+
drbd_endio_write_sec_final(peer_req);
}
@@ -2376,7 +2285,7 @@ static unsigned long wire_flags_to_bio_flags(u32 dpf)
static unsigned long wire_flags_to_bio_op(u32 dpf)
{
if (dpf & DP_DISCARD)
- return REQ_OP_DISCARD;
+ return REQ_OP_WRITE_ZEROES;
else
return REQ_OP_WRITE;
}
@@ -2567,7 +2476,7 @@ static int receive_Data(struct drbd_connection *connection, struct packet_info *
op_flags = wire_flags_to_bio_flags(dp_flags);
if (pi->cmd == P_TRIM) {
D_ASSERT(peer_device, peer_req->i.size > 0);
- D_ASSERT(peer_device, op == REQ_OP_DISCARD);
+ D_ASSERT(peer_device, op == REQ_OP_WRITE_ZEROES);
D_ASSERT(peer_device, peer_req->pages == NULL);
} else if (peer_req->pages == NULL) {
D_ASSERT(device, peer_req->i.size == 0);
@@ -4880,7 +4789,7 @@ static int receive_rs_deallocated(struct drbd_connection *connection, struct pac
if (get_ldev(device)) {
struct drbd_peer_request *peer_req;
- const int op = REQ_OP_DISCARD;
+ const int op = REQ_OP_WRITE_ZEROES;
peer_req = drbd_alloc_peer_req(peer_device, ID_SYNCER, sector,
size, 0, GFP_NOIO);
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 652114ae1a8a..b5730e17b455 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -59,6 +59,7 @@ static struct drbd_request *drbd_req_new(struct drbd_device *device, struct bio
drbd_req_make_private_bio(req, bio_src);
req->rq_state = (bio_data_dir(bio_src) == WRITE ? RQ_WRITE : 0)
| (bio_op(bio_src) == REQ_OP_WRITE_SAME ? RQ_WSAME : 0)
+ | (bio_op(bio_src) == REQ_OP_WRITE_ZEROES ? RQ_UNMAP : 0)
| (bio_op(bio_src) == REQ_OP_DISCARD ? RQ_UNMAP : 0);
req->device = device;
req->master_bio = bio_src;
@@ -1148,10 +1149,10 @@ static int drbd_process_write_request(struct drbd_request *req)
static void drbd_process_discard_req(struct drbd_request *req)
{
- int err = drbd_issue_discard_or_zero_out(req->device,
- req->i.sector, req->i.size >> 9, true);
+ struct block_device *bdev = req->device->ldev->backing_bdev;
- if (err)
+ if (blkdev_issue_zeroout(bdev, req->i.sector, req->i.size >> 9,
+ GFP_NOIO, 0))
req->private_bio->bi_error = -EIO;
bio_endio(req->private_bio);
}
@@ -1180,7 +1181,8 @@ drbd_submit_req_private_bio(struct drbd_request *req)
if (get_ldev(device)) {
if (drbd_insert_fault(device, type))
bio_io_error(bio);
- else if (bio_op(bio) == REQ_OP_DISCARD)
+ else if (bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD)
drbd_process_discard_req(req);
else
generic_make_request(bio);
@@ -1234,7 +1236,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
_drbd_start_io_acct(device, req);
/* process discards always from our submitter thread */
- if (bio_op(bio) & REQ_OP_DISCARD)
+ if ((bio_op(bio) & REQ_OP_WRITE_ZEROES) ||
+ (bio_op(bio) & REQ_OP_DISCARD))
goto queue_for_submitter_thread;
if (rw == WRITE && req->private_bio && req->i.size
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 3bff33f21435..1afcb4e02d8d 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -174,7 +174,8 @@ void drbd_peer_request_endio(struct bio *bio)
struct drbd_peer_request *peer_req = bio->bi_private;
struct drbd_device *device = peer_req->peer_device->device;
bool is_write = bio_data_dir(bio) == WRITE;
- bool is_discard = !!(bio_op(bio) == REQ_OP_DISCARD);
+ bool is_discard = bio_op(bio) == REQ_OP_WRITE_ZEROES ||
+ bio_op(bio) == REQ_OP_DISCARD;
if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
drbd_warn(device, "%s: error=%d s=%llus\n",
@@ -249,6 +250,7 @@ void drbd_request_endio(struct bio *bio)
/* to avoid recursion in __req_mod */
if (unlikely(bio->bi_error)) {
switch (bio_op(bio)) {
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_DISCARD:
if (bio->bi_error == -EOPNOTSUPP)
what = DISCARD_COMPLETED_NOTSUPP;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 45b4384f650c..60d4c7653178 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -2805,8 +2805,10 @@ static int set_next_request(void)
fdc_queue = 0;
if (q) {
current_req = blk_fetch_request(q);
- if (current_req)
+ if (current_req) {
+ current_req->error_count = 0;
break;
+ }
}
} while (fdc_queue != old_pos);
@@ -2866,7 +2868,7 @@ do_request:
_floppy = floppy_type + DP->autodetect[DRS->probed_format];
} else
probing = 0;
- errors = &(current_req->errors);
+ errors = &(current_req->error_count);
tmp = make_raw_rw_request();
if (tmp < 2) {
request_done(tmp);
@@ -4207,9 +4209,7 @@ static int __init do_floppy_init(void)
disks[drive]->fops = &floppy_fops;
sprintf(disks[drive]->disk_name, "fd%d", drive);
- init_timer(&motor_off_timer[drive]);
- motor_off_timer[drive].data = drive;
- motor_off_timer[drive].function = motor_off_callback;
+ setup_timer(&motor_off_timer[drive], motor_off_callback, drive);
}
err = register_blkdev(FLOPPY_MAJOR, "fd");
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
deleted file mode 100644
index 6043648da1e8..000000000000
--- a/drivers/block/hd.c
+++ /dev/null
@@ -1,803 +0,0 @@
-/*
- * Copyright (C) 1991, 1992 Linus Torvalds
- *
- * This is the low-level hd interrupt support. It traverses the
- * request-list, using interrupts to jump between functions. As
- * all the functions are called within interrupts, we may not
- * sleep. Special care is recommended.
- *
- * modified by Drew Eckhardt to check nr of hd's from the CMOS.
- *
- * Thanks to Branko Lankester, lankeste@fwi.uva.nl, who found a bug
- * in the early extended-partition checks and added DM partitions
- *
- * IRQ-unmask, drive-id, multiple-mode, support for ">16 heads",
- * and general streamlining by Mark Lord.
- *
- * Removed 99% of above. Use Mark's ide driver for those options.
- * This is now a lightweight ST-506 driver. (Paul Gortmaker)
- *
- * Modified 1995 Russell King for ARM processor.
- *
- * Bugfix: max_sectors must be <= 255 or the wheels tend to come
- * off in a hurry once you queue things up - Paul G. 02/2001
- */
-
-/* Uncomment the following if you want verbose error reports. */
-/* #define VERBOSE_ERRORS */
-
-#include <linux/blkdev.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/interrupt.h>
-#include <linux/timer.h>
-#include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/genhd.h>
-#include <linux/string.h>
-#include <linux/ioport.h>
-#include <linux/init.h>
-#include <linux/blkpg.h>
-#include <linux/ata.h>
-#include <linux/hdreg.h>
-
-#define HD_IRQ 14
-
-#define REALLY_SLOW_IO
-#include <asm/io.h>
-#include <linux/uaccess.h>
-
-#ifdef __arm__
-#undef HD_IRQ
-#endif
-#include <asm/irq.h>
-#ifdef __arm__
-#define HD_IRQ IRQ_HARDDISK
-#endif
-
-/* Hd controller regster ports */
-
-#define HD_DATA 0x1f0 /* _CTL when writing */
-#define HD_ERROR 0x1f1 /* see err-bits */
-#define HD_NSECTOR 0x1f2 /* nr of sectors to read/write */
-#define HD_SECTOR 0x1f3 /* starting sector */
-#define HD_LCYL 0x1f4 /* starting cylinder */
-#define HD_HCYL 0x1f5 /* high byte of starting cyl */
-#define HD_CURRENT 0x1f6 /* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS 0x1f7 /* see status-bits */
-#define HD_FEATURE HD_ERROR /* same io address, read=error, write=feature */
-#define HD_PRECOMP HD_FEATURE /* obsolete use of this port - predates IDE */
-#define HD_COMMAND HD_STATUS /* same io address, read=status, write=cmd */
-
-#define HD_CMD 0x3f6 /* used for resets */
-#define HD_ALTSTATUS 0x3f6 /* same as HD_STATUS but doesn't clear irq */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT 0x01
-#define INDEX_STAT 0x02
-#define ECC_STAT 0x04 /* Corrected error */
-#define DRQ_STAT 0x08
-#define SEEK_STAT 0x10
-#define SERVICE_STAT SEEK_STAT
-#define WRERR_STAT 0x20
-#define READY_STAT 0x40
-#define BUSY_STAT 0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR 0x01 /* Bad address mark */
-#define TRK0_ERR 0x02 /* couldn't find track 0 */
-#define ABRT_ERR 0x04 /* Command aborted */
-#define MCR_ERR 0x08 /* media change request */
-#define ID_ERR 0x10 /* ID field not found */
-#define MC_ERR 0x20 /* media changed */
-#define ECC_ERR 0x40 /* Uncorrectable ECC error */
-#define BBD_ERR 0x80 /* pre-EIDE meaning: block marked bad */
-#define ICRC_ERR 0x80 /* new meaning: CRC error during transfer */
-
-static DEFINE_SPINLOCK(hd_lock);
-static struct request_queue *hd_queue;
-static struct request *hd_req;
-
-#define TIMEOUT_VALUE (6*HZ)
-#define HD_DELAY 0
-
-#define MAX_ERRORS 16 /* Max read/write errors/sector */
-#define RESET_FREQ 8 /* Reset controller every 8th retry */
-#define RECAL_FREQ 4 /* Recalibrate every 4th retry */
-#define MAX_HD 2
-
-#define STAT_OK (READY_STAT|SEEK_STAT)
-#define OK_STATUS(s) (((s)&(STAT_OK|(BUSY_STAT|WRERR_STAT|ERR_STAT)))==STAT_OK)
-
-static void recal_intr(void);
-static void bad_rw_intr(void);
-
-static int reset;
-static int hd_error;
-
-/*
- * This struct defines the HD's and their types.
- */
-struct hd_i_struct {
- unsigned int head, sect, cyl, wpcom, lzone, ctl;
- int unit;
- int recalibrate;
- int special_op;
-};
-
-#ifdef HD_TYPE
-static struct hd_i_struct hd_info[] = { HD_TYPE };
-static int NR_HD = ARRAY_SIZE(hd_info);
-#else
-static struct hd_i_struct hd_info[MAX_HD];
-static int NR_HD;
-#endif
-
-static struct gendisk *hd_gendisk[MAX_HD];
-
-static struct timer_list device_timer;
-
-#define TIMEOUT_VALUE (6*HZ)
-
-#define SET_TIMER \
- do { \
- mod_timer(&device_timer, jiffies + TIMEOUT_VALUE); \
- } while (0)
-
-static void (*do_hd)(void) = NULL;
-#define SET_HANDLER(x) \
-if ((do_hd = (x)) != NULL) \
- SET_TIMER; \
-else \
- del_timer(&device_timer);
-
-
-#if (HD_DELAY > 0)
-
-#include <linux/i8253.h>
-
-unsigned long last_req;
-
-unsigned long read_timer(void)
-{
- unsigned long t, flags;
- int i;
-
- raw_spin_lock_irqsave(&i8253_lock, flags);
- t = jiffies * 11932;
- outb_p(0, 0x43);
- i = inb_p(0x40);
- i |= inb(0x40) << 8;
- raw_spin_unlock_irqrestore(&i8253_lock, flags);
- return(t - i);
-}
-#endif
-
-static void __init hd_setup(char *str, int *ints)
-{
- int hdind = 0;
-
- if (ints[0] != 3)
- return;
- if (hd_info[0].head != 0)
- hdind = 1;
- hd_info[hdind].head = ints[2];
- hd_info[hdind].sect = ints[3];
- hd_info[hdind].cyl = ints[1];
- hd_info[hdind].wpcom = 0;
- hd_info[hdind].lzone = ints[1];
- hd_info[hdind].ctl = (ints[2] > 8 ? 8 : 0);
- NR_HD = hdind+1;
-}
-
-static bool hd_end_request(int err, unsigned int bytes)
-{
- if (__blk_end_request(hd_req, err, bytes))
- return true;
- hd_req = NULL;
- return false;
-}
-
-static bool hd_end_request_cur(int err)
-{
- return hd_end_request(err, blk_rq_cur_bytes(hd_req));
-}
-
-static void dump_status(const char *msg, unsigned int stat)
-{
- char *name = "hd?";
- if (hd_req)
- name = hd_req->rq_disk->disk_name;
-
-#ifdef VERBOSE_ERRORS
- printk("%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
- if (stat & BUSY_STAT) printk("Busy ");
- if (stat & READY_STAT) printk("DriveReady ");
- if (stat & WRERR_STAT) printk("WriteFault ");
- if (stat & SEEK_STAT) printk("SeekComplete ");
- if (stat & DRQ_STAT) printk("DataRequest ");
- if (stat & ECC_STAT) printk("CorrectedError ");
- if (stat & INDEX_STAT) printk("Index ");
- if (stat & ERR_STAT) printk("Error ");
- printk("}\n");
- if ((stat & ERR_STAT) == 0) {
- hd_error = 0;
- } else {
- hd_error = inb(HD_ERROR);
- printk("%s: %s: error=0x%02x { ", name, msg, hd_error & 0xff);
- if (hd_error & BBD_ERR) printk("BadSector ");
- if (hd_error & ECC_ERR) printk("UncorrectableError ");
- if (hd_error & ID_ERR) printk("SectorIdNotFound ");
- if (hd_error & ABRT_ERR) printk("DriveStatusError ");
- if (hd_error & TRK0_ERR) printk("TrackZeroNotFound ");
- if (hd_error & MARK_ERR) printk("AddrMarkNotFound ");
- printk("}");
- if (hd_error & (BBD_ERR|ECC_ERR|ID_ERR|MARK_ERR)) {
- printk(", CHS=%d/%d/%d", (inb(HD_HCYL)<<8) + inb(HD_LCYL),
- inb(HD_CURRENT) & 0xf, inb(HD_SECTOR));
- if (hd_req)
- printk(", sector=%ld", blk_rq_pos(hd_req));
- }
- printk("\n");
- }
-#else
- printk("%s: %s: status=0x%02x.\n", name, msg, stat & 0xff);
- if ((stat & ERR_STAT) == 0) {
- hd_error = 0;
- } else {
- hd_error = inb(HD_ERROR);
- printk("%s: %s: error=0x%02x.\n", name, msg, hd_error & 0xff);
- }
-#endif
-}
-
-static void check_status(void)
-{
- int i = inb_p(HD_STATUS);
-
- if (!OK_STATUS(i)) {
- dump_status("check_status", i);
- bad_rw_intr();
- }
-}
-
-static int controller_busy(void)
-{
- int retries = 100000;
- unsigned char status;
-
- do {
- status = inb_p(HD_STATUS);
- } while ((status & BUSY_STAT) && --retries);
- return status;
-}
-
-static int status_ok(void)
-{
- unsigned char status = inb_p(HD_STATUS);
-
- if (status & BUSY_STAT)
- return 1; /* Ancient, but does it make sense??? */
- if (status & WRERR_STAT)
- return 0;
- if (!(status & READY_STAT))
- return 0;
- if (!(status & SEEK_STAT))
- return 0;
- return 1;
-}
-
-static int controller_ready(unsigned int drive, unsigned int head)
-{
- int retry = 100;
-
- do {
- if (controller_busy() & BUSY_STAT)
- return 0;
- outb_p(0xA0 | (drive<<4) | head, HD_CURRENT);
- if (status_ok())
- return 1;
- } while (--retry);
- return 0;
-}
-
-static void hd_out(struct hd_i_struct *disk,
- unsigned int nsect,
- unsigned int sect,
- unsigned int head,
- unsigned int cyl,
- unsigned int cmd,
- void (*intr_addr)(void))
-{
- unsigned short port;
-
-#if (HD_DELAY > 0)
- while (read_timer() - last_req < HD_DELAY)
- /* nothing */;
-#endif
- if (reset)
- return;
- if (!controller_ready(disk->unit, head)) {
- reset = 1;
- return;
- }
- SET_HANDLER(intr_addr);
- outb_p(disk->ctl, HD_CMD);
- port = HD_DATA;
- outb_p(disk->wpcom >> 2, ++port);
- outb_p(nsect, ++port);
- outb_p(sect, ++port);
- outb_p(cyl, ++port);
- outb_p(cyl >> 8, ++port);
- outb_p(0xA0 | (disk->unit << 4) | head, ++port);
- outb_p(cmd, ++port);
-}
-
-static void hd_request (void);
-
-static int drive_busy(void)
-{
- unsigned int i;
- unsigned char c;
-
- for (i = 0; i < 500000 ; i++) {
- c = inb_p(HD_STATUS);
- if ((c & (BUSY_STAT | READY_STAT | SEEK_STAT)) == STAT_OK)
- return 0;
- }
- dump_status("reset timed out", c);
- return 1;
-}
-
-static void reset_controller(void)
-{
- int i;
-
- outb_p(4, HD_CMD);
- for (i = 0; i < 1000; i++) barrier();
- outb_p(hd_info[0].ctl & 0x0f, HD_CMD);
- for (i = 0; i < 1000; i++) barrier();
- if (drive_busy())
- printk("hd: controller still busy\n");
- else if ((hd_error = inb(HD_ERROR)) != 1)
- printk("hd: controller reset failed: %02x\n", hd_error);
-}
-
-static void reset_hd(void)
-{
- static int i;
-
-repeat:
- if (reset) {
- reset = 0;
- i = -1;
- reset_controller();
- } else {
- check_status();
- if (reset)
- goto repeat;
- }
- if (++i < NR_HD) {
- struct hd_i_struct *disk = &hd_info[i];
- disk->special_op = disk->recalibrate = 1;
- hd_out(disk, disk->sect, disk->sect, disk->head-1,
- disk->cyl, ATA_CMD_INIT_DEV_PARAMS, &reset_hd);
- if (reset)
- goto repeat;
- } else
- hd_request();
-}
-
-/*
- * Ok, don't know what to do with the unexpected interrupts: on some machines
- * doing a reset and a retry seems to result in an eternal loop. Right now I
- * ignore it, and just set the timeout.
- *
- * On laptops (and "green" PCs), an unexpected interrupt occurs whenever the
- * drive enters "idle", "standby", or "sleep" mode, so if the status looks
- * "good", we just ignore the interrupt completely.
- */
-static void unexpected_hd_interrupt(void)
-{
- unsigned int stat = inb_p(HD_STATUS);
-
- if (stat & (BUSY_STAT|DRQ_STAT|ECC_STAT|ERR_STAT)) {
- dump_status("unexpected interrupt", stat);
- SET_TIMER;
- }
-}
-
-/*
- * bad_rw_intr() now tries to be a bit smarter and does things
- * according to the error returned by the controller.
- * -Mika Liljeberg (liljeber@cs.Helsinki.FI)
- */
-static void bad_rw_intr(void)
-{
- struct request *req = hd_req;
-
- if (req != NULL) {
- struct hd_i_struct *disk = req->rq_disk->private_data;
- if (++req->errors >= MAX_ERRORS || (hd_error & BBD_ERR)) {
- hd_end_request_cur(-EIO);
- disk->special_op = disk->recalibrate = 1;
- } else if (req->errors % RESET_FREQ == 0)
- reset = 1;
- else if ((hd_error & TRK0_ERR) || req->errors % RECAL_FREQ == 0)
- disk->special_op = disk->recalibrate = 1;
- /* Otherwise just retry */
- }
-}
-
-static inline int wait_DRQ(void)
-{
- int retries;
- int stat;
-
- for (retries = 0; retries < 100000; retries++) {
- stat = inb_p(HD_STATUS);
- if (stat & DRQ_STAT)
- return 0;
- }
- dump_status("wait_DRQ", stat);
- return -1;
-}
-
-static void read_intr(void)
-{
- struct request *req;
- int i, retries = 100000;
-
- do {
- i = (unsigned) inb_p(HD_STATUS);
- if (i & BUSY_STAT)
- continue;
- if (!OK_STATUS(i))
- break;
- if (i & DRQ_STAT)
- goto ok_to_read;
- } while (--retries > 0);
- dump_status("read_intr", i);
- bad_rw_intr();
- hd_request();
- return;
-
-ok_to_read:
- req = hd_req;
- insw(HD_DATA, bio_data(req->bio), 256);
-#ifdef DEBUG
- printk("%s: read: sector %ld, remaining = %u, buffer=%p\n",
- req->rq_disk->disk_name, blk_rq_pos(req) + 1,
- blk_rq_sectors(req) - 1, bio_data(req->bio)+512);
-#endif
- if (hd_end_request(0, 512)) {
- SET_HANDLER(&read_intr);
- return;
- }
-
- (void) inb_p(HD_STATUS);
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-static void write_intr(void)
-{
- struct request *req = hd_req;
- int i;
- int retries = 100000;
-
- do {
- i = (unsigned) inb_p(HD_STATUS);
- if (i & BUSY_STAT)
- continue;
- if (!OK_STATUS(i))
- break;
- if ((blk_rq_sectors(req) <= 1) || (i & DRQ_STAT))
- goto ok_to_write;
- } while (--retries > 0);
- dump_status("write_intr", i);
- bad_rw_intr();
- hd_request();
- return;
-
-ok_to_write:
- if (hd_end_request(0, 512)) {
- SET_HANDLER(&write_intr);
- outsw(HD_DATA, bio_data(req->bio), 256);
- return;
- }
-
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-static void recal_intr(void)
-{
- check_status();
-#if (HD_DELAY > 0)
- last_req = read_timer();
-#endif
- hd_request();
-}
-
-/*
- * This is another of the error-routines I don't know what to do with. The
- * best idea seems to just set reset, and start all over again.
- */
-static void hd_times_out(unsigned long dummy)
-{
- char *name;
-
- do_hd = NULL;
-
- if (!hd_req)
- return;
-
- spin_lock_irq(hd_queue->queue_lock);
- reset = 1;
- name = hd_req->rq_disk->disk_name;
- printk("%s: timeout\n", name);
- if (++hd_req->errors >= MAX_ERRORS) {
-#ifdef DEBUG
- printk("%s: too many errors\n", name);
-#endif
- hd_end_request_cur(-EIO);
- }
- hd_request();
- spin_unlock_irq(hd_queue->queue_lock);
-}
-
-static int do_special_op(struct hd_i_struct *disk, struct request *req)
-{
- if (disk->recalibrate) {
- disk->recalibrate = 0;
- hd_out(disk, disk->sect, 0, 0, 0, ATA_CMD_RESTORE, &recal_intr);
- return reset;
- }
- if (disk->head > 16) {
- printk("%s: cannot handle device with more than 16 heads - giving up\n", req->rq_disk->disk_name);
- hd_end_request_cur(-EIO);
- }
- disk->special_op = 0;
- return 1;
-}
-
-/*
- * The driver enables interrupts as much as possible. In order to do this,
- * (a) the device-interrupt is disabled before entering hd_request(),
- * and (b) the timeout-interrupt is disabled before the sti().
- *
- * Interrupts are still masked (by default) whenever we are exchanging
- * data/cmds with a drive, because some drives seem to have very poor
- * tolerance for latency during I/O. The IDE driver has support to unmask
- * interrupts for non-broken hardware, so use that driver if required.
- */
-static void hd_request(void)
-{
- unsigned int block, nsect, sec, track, head, cyl;
- struct hd_i_struct *disk;
- struct request *req;
-
- if (do_hd)
- return;
-repeat:
- del_timer(&device_timer);
-
- if (!hd_req) {
- hd_req = blk_fetch_request(hd_queue);
- if (!hd_req) {
- do_hd = NULL;
- return;
- }
- }
- req = hd_req;
-
- if (reset) {
- reset_hd();
- return;
- }
- disk = req->rq_disk->private_data;
- block = blk_rq_pos(req);
- nsect = blk_rq_sectors(req);
- if (block >= get_capacity(req->rq_disk) ||
- ((block+nsect) > get_capacity(req->rq_disk))) {
- printk("%s: bad access: block=%d, count=%d\n",
- req->rq_disk->disk_name, block, nsect);
- hd_end_request_cur(-EIO);
- goto repeat;
- }
-
- if (disk->special_op) {
- if (do_special_op(disk, req))
- goto repeat;
- return;
- }
- sec = block % disk->sect + 1;
- track = block / disk->sect;
- head = track % disk->head;
- cyl = track / disk->head;
-#ifdef DEBUG
- printk("%s: %sing: CHS=%d/%d/%d, sectors=%d, buffer=%p\n",
- req->rq_disk->disk_name,
- req_data_dir(req) == READ ? "read" : "writ",
- cyl, head, sec, nsect, bio_data(req->bio));
-#endif
-
- switch (req_op(req)) {
- case REQ_OP_READ:
- hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_READ,
- &read_intr);
- if (reset)
- goto repeat;
- break;
- case REQ_OP_WRITE:
- hd_out(disk, nsect, sec, head, cyl, ATA_CMD_PIO_WRITE,
- &write_intr);
- if (reset)
- goto repeat;
- if (wait_DRQ()) {
- bad_rw_intr();
- goto repeat;
- }
- outsw(HD_DATA, bio_data(req->bio), 256);
- break;
- default:
- printk("unknown hd-command\n");
- hd_end_request_cur(-EIO);
- break;
- }
-}
-
-static void do_hd_request(struct request_queue *q)
-{
- hd_request();
-}
-
-static int hd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
- struct hd_i_struct *disk = bdev->bd_disk->private_data;
-
- geo->heads = disk->head;
- geo->sectors = disk->sect;
- geo->cylinders = disk->cyl;
- return 0;
-}
-
-/*
- * Releasing a block device means we sync() it, so that it can safely
- * be forgotten about...
- */
-
-static irqreturn_t hd_interrupt(int irq, void *dev_id)
-{
- void (*handler)(void) = do_hd;
-
- spin_lock(hd_queue->queue_lock);
-
- do_hd = NULL;
- del_timer(&device_timer);
- if (!handler)
- handler = unexpected_hd_interrupt;
- handler();
-
- spin_unlock(hd_queue->queue_lock);
-
- return IRQ_HANDLED;
-}
-
-static const struct block_device_operations hd_fops = {
- .getgeo = hd_getgeo,
-};
-
-static int __init hd_init(void)
-{
- int drive;
-
- if (register_blkdev(HD_MAJOR, "hd"))
- return -1;
-
- hd_queue = blk_init_queue(do_hd_request, &hd_lock);
- if (!hd_queue) {
- unregister_blkdev(HD_MAJOR, "hd");
- return -ENOMEM;
- }
-
- blk_queue_max_hw_sectors(hd_queue, 255);
- init_timer(&device_timer);
- device_timer.function = hd_times_out;
- blk_queue_logical_block_size(hd_queue, 512);
-
- if (!NR_HD) {
- /*
- * We don't know anything about the drive. This means
- * that you *MUST* specify the drive parameters to the
- * kernel yourself.
- *
- * If we were on an i386, we used to read this info from
- * the BIOS or CMOS. This doesn't work all that well,
- * since this assumes that this is a primary or secondary
- * drive, and if we're using this legacy driver, it's
- * probably an auxiliary controller added to recover
- * legacy data off an ST-506 drive. Either way, it's
- * definitely safest to have the user explicitly specify
- * the information.
- */
- printk("hd: no drives specified - use hd=cyl,head,sectors"
- " on kernel command line\n");
- goto out;
- }
-
- for (drive = 0 ; drive < NR_HD ; drive++) {
- struct gendisk *disk = alloc_disk(64);
- struct hd_i_struct *p = &hd_info[drive];
- if (!disk)
- goto Enomem;
- disk->major = HD_MAJOR;
- disk->first_minor = drive << 6;
- disk->fops = &hd_fops;
- sprintf(disk->disk_name, "hd%c", 'a'+drive);
- disk->private_data = p;
- set_capacity(disk, p->head * p->sect * p->cyl);
- disk->queue = hd_queue;
- p->unit = drive;
- hd_gendisk[drive] = disk;
- printk("%s: %luMB, CHS=%d/%d/%d\n",
- disk->disk_name, (unsigned long)get_capacity(disk)/2048,
- p->cyl, p->head, p->sect);
- }
-
- if (request_irq(HD_IRQ, hd_interrupt, 0, "hd", NULL)) {
- printk("hd: unable to get IRQ%d for the hard disk driver\n",
- HD_IRQ);
- goto out1;
- }
- if (!request_region(HD_DATA, 8, "hd")) {
- printk(KERN_WARNING "hd: port 0x%x busy\n", HD_DATA);
- goto out2;
- }
- if (!request_region(HD_CMD, 1, "hd(cmd)")) {
- printk(KERN_WARNING "hd: port 0x%x busy\n", HD_CMD);
- goto out3;
- }
-
- /* Let them fly */
- for (drive = 0; drive < NR_HD; drive++)
- add_disk(hd_gendisk[drive]);
-
- return 0;
-
-out3:
- release_region(HD_DATA, 8);
-out2:
- free_irq(HD_IRQ, NULL);
-out1:
- for (drive = 0; drive < NR_HD; drive++)
- put_disk(hd_gendisk[drive]);
- NR_HD = 0;
-out:
- del_timer(&device_timer);
- unregister_blkdev(HD_MAJOR, "hd");
- blk_cleanup_queue(hd_queue);
- return -1;
-Enomem:
- while (drive--)
- put_disk(hd_gendisk[drive]);
- goto out;
-}
-
-static int __init parse_hd_setup(char *line)
-{
- int ints[6];
-
- (void) get_options(line, ARRAY_SIZE(ints), ints);
- hd_setup(NULL, ints);
-
- return 1;
-}
-__setup("hd=", parse_hd_setup);
-
-late_initcall(hd_init);
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 0ecb6461ed81..994403efee19 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -445,32 +445,27 @@ 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)
+static void lo_complete_rq(struct request *rq)
{
- if (bytes < 0 || op_is_write(req_op(cmd->rq)))
- return;
+ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
- if (unlikely(bytes < blk_rq_bytes(cmd->rq))) {
+ if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
+ cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
struct bio *bio = cmd->rq->bio;
- bio_advance(bio, bytes);
+ bio_advance(bio, cmd->ret);
zero_fill_bio(bio);
}
+
+ blk_mq_end_request(rq, cmd->ret < 0 ? -EIO : 0);
}
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);
+ cmd->ret = ret;
+ blk_mq_complete_request(cmd->rq);
}
static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
@@ -528,6 +523,7 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq)
case REQ_OP_FLUSH:
return lo_req_flush(lo, rq);
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
return lo_discard(lo, rq, pos);
case REQ_OP_WRITE:
if (lo->transfer)
@@ -826,7 +822,7 @@ static void loop_config_discard(struct loop_device *lo)
q->limits.discard_granularity = 0;
q->limits.discard_alignment = 0;
blk_queue_max_discard_sectors(q, 0);
- q->limits.discard_zeroes_data = 0;
+ blk_queue_max_write_zeroes_sectors(q, 0);
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
return;
}
@@ -834,7 +830,7 @@ static void loop_config_discard(struct loop_device *lo)
q->limits.discard_granularity = inode->i_sb->s_blocksize;
q->limits.discard_alignment = 0;
blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
- q->limits.discard_zeroes_data = 1;
+ blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
@@ -1660,6 +1656,7 @@ static int loop_queue_rq(struct blk_mq_hw_ctx *hctx,
switch (req_op(cmd->rq)) {
case REQ_OP_FLUSH:
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
cmd->use_aio = false;
break;
default:
@@ -1686,8 +1683,10 @@ static void loop_handle_cmd(struct loop_cmd *cmd)
ret = do_req_filebacked(lo, cmd->rq);
failed:
/* complete non-aio request */
- if (!cmd->use_aio || ret)
- blk_mq_complete_request(cmd->rq, ret ? -EIO : 0);
+ if (!cmd->use_aio || ret) {
+ cmd->ret = ret ? -EIO : 0;
+ blk_mq_complete_request(cmd->rq);
+ }
}
static void loop_queue_work(struct kthread_work *work)
@@ -1710,9 +1709,10 @@ static int loop_init_request(void *data, struct request *rq,
return 0;
}
-static struct blk_mq_ops loop_mq_ops = {
+static const struct blk_mq_ops loop_mq_ops = {
.queue_rq = loop_queue_rq,
.init_request = loop_init_request,
+ .complete = lo_complete_rq,
};
static int loop_add(struct loop_device **l, int i)
diff --git a/drivers/block/loop.h b/drivers/block/loop.h
index fb2237c73e61..fecd3f97ef8c 100644
--- a/drivers/block/loop.h
+++ b/drivers/block/loop.h
@@ -70,6 +70,7 @@ struct loop_cmd {
struct request *rq;
struct list_head list;
bool use_aio; /* use AIO interface to handle I/O */
+ long ret;
struct kiocb iocb;
};
diff --git a/drivers/block/mg_disk.c b/drivers/block/mg_disk.c
deleted file mode 100644
index 286f276f586e..000000000000
--- a/drivers/block/mg_disk.c
+++ /dev/null
@@ -1,1112 +0,0 @@
-/*
- * drivers/block/mg_disk.c
- *
- * Support for the mGine m[g]flash IO mode.
- * Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/blkdev.h>
-#include <linux/hdreg.h>
-#include <linux/ata.h>
-#include <linux/interrupt.h>
-#include <linux/delay.h>
-#include <linux/platform_device.h>
-#include <linux/gpio.h>
-#include <linux/mg_disk.h>
-#include <linux/slab.h>
-
-#define MG_RES_SEC (CONFIG_MG_DISK_RES << 1)
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET 0x8000
-#define MG_REG_OFFSET 0xC000
-#define MG_REG_FEATURE (MG_REG_OFFSET + 2) /* write case */
-#define MG_REG_ERROR (MG_REG_OFFSET + 2) /* read case */
-#define MG_REG_SECT_CNT (MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM (MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW (MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH (MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD (MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND (MG_REG_OFFSET + 0xE) /* write case */
-#define MG_REG_STATUS (MG_REG_OFFSET + 0xE) /* read case */
-#define MG_REG_DRV_CTRL (MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL (MG_REG_OFFSET + 0x12)
-
-/* handy status */
-#define MG_STAT_READY (ATA_DRDY | ATA_DSC)
-#define MG_READY_OK(s) (((s) & (MG_STAT_READY | (ATA_BUSY | ATA_DF | \
- ATA_ERR))) == MG_STAT_READY)
-
-/* error code for others */
-#define MG_ERR_NONE 0
-#define MG_ERR_TIMEOUT 0x100
-#define MG_ERR_INIT_STAT 0x101
-#define MG_ERR_TRANSLATION 0x102
-#define MG_ERR_CTRL_RST 0x103
-#define MG_ERR_INV_STAT 0x104
-#define MG_ERR_RSTOUT 0x105
-
-#define MG_MAX_ERRORS 6 /* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD 1
-#define MG_TMAX_WAIT_RD_DRQ 10
-#define MG_TMAX_WAIT_WR_DRQ 500
-#define MG_TMAX_RST_TO_BUSY 10
-#define MG_TMAX_HDRST_TO_RDY 500
-#define MG_TMAX_SWRST_TO_RDY 500
-#define MG_TMAX_RSTOUT 3000
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* main structure for mflash driver */
-struct mg_host {
- struct device *dev;
-
- struct request_queue *breq;
- struct request *req;
- spinlock_t lock;
- struct gendisk *gd;
-
- struct timer_list timer;
- void (*mg_do_intr) (struct mg_host *);
-
- u16 id[ATA_ID_WORDS];
-
- u16 cyls;
- u16 heads;
- u16 sectors;
- u32 n_sectors;
- u32 nres_sectors;
-
- void __iomem *dev_base;
- unsigned int irq;
- unsigned int rst;
- unsigned int rstout;
-
- u32 major;
- u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-# define MG_DBG(fmt, args...) \
- printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-# define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-static void mg_request(struct request_queue *);
-
-static bool mg_end_request(struct mg_host *host, int err, unsigned int nr_bytes)
-{
- if (__blk_end_request(host->req, err, nr_bytes))
- return true;
-
- host->req = NULL;
- return false;
-}
-
-static bool mg_end_request_cur(struct mg_host *host, int err)
-{
- return mg_end_request(host, err, blk_rq_cur_bytes(host->req));
-}
-
-static void mg_dump_status(const char *msg, unsigned int stat,
- struct mg_host *host)
-{
- char *name = MG_DISK_NAME;
-
- if (host->req)
- name = host->req->rq_disk->disk_name;
-
- printk(KERN_ERR "%s: %s: status=0x%02x { ", name, msg, stat & 0xff);
- if (stat & ATA_BUSY)
- printk("Busy ");
- if (stat & ATA_DRDY)
- printk("DriveReady ");
- if (stat & ATA_DF)
- printk("WriteFault ");
- if (stat & ATA_DSC)
- printk("SeekComplete ");
- if (stat & ATA_DRQ)
- printk("DataRequest ");
- if (stat & ATA_CORR)
- printk("CorrectedError ");
- if (stat & ATA_ERR)
- printk("Error ");
- printk("}\n");
- if ((stat & ATA_ERR) == 0) {
- host->error = 0;
- } else {
- host->error = inb((unsigned long)host->dev_base + MG_REG_ERROR);
- printk(KERN_ERR "%s: %s: error=0x%02x { ", name, msg,
- host->error & 0xff);
- if (host->error & ATA_BBK)
- printk("BadSector ");
- if (host->error & ATA_UNC)
- printk("UncorrectableError ");
- if (host->error & ATA_IDNF)
- printk("SectorIdNotFound ");
- if (host->error & ATA_ABORTED)
- printk("DriveStatusError ");
- if (host->error & ATA_AMNF)
- printk("AddrMarkNotFound ");
- printk("}");
- if (host->error & (ATA_BBK | ATA_UNC | ATA_IDNF | ATA_AMNF)) {
- if (host->req)
- printk(", sector=%u",
- (unsigned int)blk_rq_pos(host->req));
- }
- printk("\n");
- }
-}
-
-static unsigned int mg_wait(struct mg_host *host, u32 expect, u32 msec)
-{
- u8 status;
- unsigned long expire, cur_jiffies;
- struct mg_drv_data *prv_data = host->dev->platform_data;
-
- host->error = MG_ERR_NONE;
- expire = jiffies + msecs_to_jiffies(msec);
-
- /* These 2 times dummy status read prevents reading invalid
- * status. A very little time (3 times of mflash operating clk)
- * is required for busy bit is set. Use dummy read instead of
- * busy wait, because mflash's PLL is machine dependent.
- */
- if (prv_data->use_polling) {
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- }
-
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
- do {
- cur_jiffies = jiffies;
- if (status & ATA_BUSY) {
- if (expect == ATA_BUSY)
- break;
- } else {
- /* Check the error condition! */
- if (status & ATA_ERR) {
- mg_dump_status("mg_wait", status, host);
- break;
- }
-
- if (expect == MG_STAT_READY)
- if (MG_READY_OK(status))
- break;
-
- if (expect == ATA_DRQ)
- if (status & ATA_DRQ)
- break;
- }
- if (!msec) {
- mg_dump_status("not ready", status, host);
- return MG_ERR_INV_STAT;
- }
-
- status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- } while (time_before(cur_jiffies, expire));
-
- if (time_after_eq(cur_jiffies, expire) && msec)
- host->error = MG_ERR_TIMEOUT;
-
- return host->error;
-}
-
-static unsigned int mg_wait_rstout(u32 rstout, u32 msec)
-{
- unsigned long expire;
-
- expire = jiffies + msecs_to_jiffies(msec);
- while (time_before(jiffies, expire)) {
- if (gpio_get_value(rstout) == 1)
- return MG_ERR_NONE;
- msleep(10);
- }
-
- return MG_ERR_RSTOUT;
-}
-
-static void mg_unexpected_intr(struct mg_host *host)
-{
- u32 status = inb((unsigned long)host->dev_base + MG_REG_STATUS);
-
- mg_dump_status("mg_unexpected_intr", status, host);
-}
-
-static irqreturn_t mg_irq(int irq, void *dev_id)
-{
- struct mg_host *host = dev_id;
- void (*handler)(struct mg_host *) = host->mg_do_intr;
-
- spin_lock(&host->lock);
-
- host->mg_do_intr = NULL;
- del_timer(&host->timer);
- if (!handler)
- handler = mg_unexpected_intr;
- handler(host);
-
- spin_unlock(&host->lock);
-
- return IRQ_HANDLED;
-}
-
-/* local copy of ata_id_string() */
-static void mg_id_string(const u16 *id, unsigned char *s,
- unsigned int ofs, unsigned int len)
-{
- unsigned int c;
-
- BUG_ON(len & 1);
-
- while (len > 0) {
- c = id[ofs] >> 8;
- *s = c;
- s++;
-
- c = id[ofs] & 0xff;
- *s = c;
- s++;
-
- ofs++;
- len -= 2;
- }
-}
-
-/* local copy of ata_id_c_string() */
-static void mg_id_c_string(const u16 *id, unsigned char *s,
- unsigned int ofs, unsigned int len)
-{
- unsigned char *p;
-
- mg_id_string(id, s, ofs, len - 1);
-
- p = s + strnlen(s, len - 1);
- while (p > s && p[-1] == ' ')
- p--;
- *p = '\0';
-}
-
-static int mg_get_disk_id(struct mg_host *host)
-{
- u32 i;
- s32 err;
- const u16 *id = host->id;
- struct mg_drv_data *prv_data = host->dev->platform_data;
- char fwrev[ATA_ID_FW_REV_LEN + 1];
- char model[ATA_ID_PROD_LEN + 1];
- char serial[ATA_ID_SERNO_LEN + 1];
-
- if (!prv_data->use_polling)
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- outb(MG_CMD_ID, (unsigned long)host->dev_base + MG_REG_COMMAND);
- err = mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_RD_DRQ);
- if (err)
- return err;
-
- for (i = 0; i < (MG_SECTOR_SIZE >> 1); i++)
- host->id[i] = le16_to_cpu(inw((unsigned long)host->dev_base +
- MG_BUFF_OFFSET + i * 2));
-
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD);
- if (err)
- return err;
-
- if ((id[ATA_ID_FIELD_VALID] & 1) == 0)
- return MG_ERR_TRANSLATION;
-
- host->n_sectors = ata_id_u32(id, ATA_ID_LBA_CAPACITY);
- host->cyls = id[ATA_ID_CYLS];
- host->heads = id[ATA_ID_HEADS];
- host->sectors = id[ATA_ID_SECTORS];
-
- if (MG_RES_SEC && host->heads && host->sectors) {
- /* modify cyls, n_sectors */
- host->cyls = (host->n_sectors - MG_RES_SEC) /
- host->heads / host->sectors;
- host->nres_sectors = host->n_sectors - host->cyls *
- host->heads * host->sectors;
- host->n_sectors -= host->nres_sectors;
- }
-
- mg_id_c_string(id, fwrev, ATA_ID_FW_REV, sizeof(fwrev));
- mg_id_c_string(id, model, ATA_ID_PROD, sizeof(model));
- mg_id_c_string(id, serial, ATA_ID_SERNO, sizeof(serial));
- printk(KERN_INFO "mg_disk: model: %s\n", model);
- printk(KERN_INFO "mg_disk: firm: %.8s\n", fwrev);
- printk(KERN_INFO "mg_disk: serial: %s\n", serial);
- printk(KERN_INFO "mg_disk: %d + reserved %d sectors\n",
- host->n_sectors, host->nres_sectors);
-
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- return err;
-}
-
-
-static int mg_disk_init(struct mg_host *host)
-{
- struct mg_drv_data *prv_data = host->dev->platform_data;
- s32 err;
- u8 init_status;
-
- /* hdd rst low */
- gpio_set_value(host->rst, 0);
- err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
- if (err)
- return err;
-
- /* hdd rst high */
- gpio_set_value(host->rst, 1);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_HDRST_TO_RDY);
- if (err)
- return err;
-
- /* soft reset on */
- outb(ATA_SRST | (prv_data->use_polling ? ATA_NIEN : 0),
- (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- err = mg_wait(host, ATA_BUSY, MG_TMAX_RST_TO_BUSY);
- if (err)
- return err;
-
- /* soft reset off */
- outb(prv_data->use_polling ? ATA_NIEN : 0,
- (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- err = mg_wait(host, MG_STAT_READY, MG_TMAX_SWRST_TO_RDY);
- if (err)
- return err;
-
- init_status = inb((unsigned long)host->dev_base + MG_REG_STATUS) & 0xf;
-
- if (init_status == 0xf)
- return MG_ERR_INIT_STAT;
-
- return err;
-}
-
-static void mg_bad_rw_intr(struct mg_host *host)
-{
- if (host->req)
- if (++host->req->errors >= MG_MAX_ERRORS ||
- host->error == MG_ERR_TIMEOUT)
- mg_end_request_cur(host, -EIO);
-}
-
-static unsigned int mg_out(struct mg_host *host,
- unsigned int sect_num,
- unsigned int sect_cnt,
- unsigned int cmd,
- void (*intr_addr)(struct mg_host *))
-{
- struct mg_drv_data *prv_data = host->dev->platform_data;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return host->error;
-
- if (!prv_data->use_polling) {
- host->mg_do_intr = intr_addr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- }
- if (MG_RES_SEC)
- sect_num += MG_RES_SEC;
- outb((u8)sect_cnt, (unsigned long)host->dev_base + MG_REG_SECT_CNT);
- outb((u8)sect_num, (unsigned long)host->dev_base + MG_REG_SECT_NUM);
- outb((u8)(sect_num >> 8), (unsigned long)host->dev_base +
- MG_REG_CYL_LOW);
- outb((u8)(sect_num >> 16), (unsigned long)host->dev_base +
- MG_REG_CYL_HIGH);
- outb((u8)((sect_num >> 24) | ATA_LBA | ATA_DEVICE_OBS),
- (unsigned long)host->dev_base + MG_REG_DRV_HEAD);
- outb(cmd, (unsigned long)host->dev_base + MG_REG_COMMAND);
- return MG_ERR_NONE;
-}
-
-static void mg_read_one(struct mg_host *host, struct request *req)
-{
- u16 *buff = (u16 *)bio_data(req->bio);
- u32 i;
-
- for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
- *buff++ = inw((unsigned long)host->dev_base + MG_BUFF_OFFSET +
- (i << 1));
-}
-
-static void mg_read(struct request *req)
-{
- struct mg_host *host = req->rq_disk->private_data;
-
- if (mg_out(host, blk_rq_pos(req), blk_rq_sectors(req),
- MG_CMD_RD, NULL) != MG_ERR_NONE)
- mg_bad_rw_intr(host);
-
- MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
- blk_rq_sectors(req), blk_rq_pos(req), bio_data(req->bio));
-
- do {
- if (mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_RD_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- mg_read_one(host, req);
-
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
- } while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_write_one(struct mg_host *host, struct request *req)
-{
- u16 *buff = (u16 *)bio_data(req->bio);
- u32 i;
-
- for (i = 0; i < MG_SECTOR_SIZE >> 1; i++)
- outw(*buff++, (unsigned long)host->dev_base + MG_BUFF_OFFSET +
- (i << 1));
-}
-
-static void mg_write(struct request *req)
-{
- struct mg_host *host = req->rq_disk->private_data;
- unsigned int rem = blk_rq_sectors(req);
-
- if (mg_out(host, blk_rq_pos(req), rem,
- MG_CMD_WR, NULL) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- MG_DBG("requested %d sects (from %ld), buffer=0x%p\n",
- rem, blk_rq_pos(req), bio_data(req->bio));
-
- if (mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
-
- do {
- mg_write_one(host, req);
-
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
-
- rem--;
- if (rem > 1 && mg_wait(host, ATA_DRQ,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- } else if (mg_wait(host, MG_STAT_READY,
- MG_TMAX_WAIT_WR_DRQ) != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return;
- }
- } while (mg_end_request(host, 0, MG_SECTOR_SIZE));
-}
-
-static void mg_read_intr(struct mg_host *host)
-{
- struct request *req = host->req;
- u32 i;
-
- /* check status */
- do {
- i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- if (i & ATA_BUSY)
- break;
- if (!MG_READY_OK(i))
- break;
- if (i & ATA_DRQ)
- goto ok_to_read;
- } while (0);
- mg_dump_status("mg_read_intr", i, host);
- mg_bad_rw_intr(host);
- mg_request(host->breq);
- return;
-
-ok_to_read:
- mg_read_one(host, req);
-
- MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
- blk_rq_pos(req), blk_rq_sectors(req) - 1, bio_data(req->bio));
-
- /* send read confirm */
- outb(MG_CMD_RD_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
- if (mg_end_request(host, 0, MG_SECTOR_SIZE)) {
- /* set handler if read remains */
- host->mg_do_intr = mg_read_intr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- } else /* goto next request */
- mg_request(host->breq);
-}
-
-static void mg_write_intr(struct mg_host *host)
-{
- struct request *req = host->req;
- u32 i;
- bool rem;
-
- /* check status */
- do {
- i = inb((unsigned long)host->dev_base + MG_REG_STATUS);
- if (i & ATA_BUSY)
- break;
- if (!MG_READY_OK(i))
- break;
- if ((blk_rq_sectors(req) <= 1) || (i & ATA_DRQ))
- goto ok_to_write;
- } while (0);
- mg_dump_status("mg_write_intr", i, host);
- mg_bad_rw_intr(host);
- mg_request(host->breq);
- return;
-
-ok_to_write:
- if ((rem = mg_end_request(host, 0, MG_SECTOR_SIZE))) {
- /* write 1 sector and set handler if remains */
- mg_write_one(host, req);
- MG_DBG("sector %ld, remaining=%ld, buffer=0x%p\n",
- blk_rq_pos(req), blk_rq_sectors(req), bio_data(req->bio));
- host->mg_do_intr = mg_write_intr;
- mod_timer(&host->timer, jiffies + 3 * HZ);
- }
-
- /* send write confirm */
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base + MG_REG_COMMAND);
-
- if (!rem)
- mg_request(host->breq);
-}
-
-static void mg_times_out(unsigned long data)
-{
- struct mg_host *host = (struct mg_host *)data;
- char *name;
-
- spin_lock_irq(&host->lock);
-
- if (!host->req)
- goto out_unlock;
-
- host->mg_do_intr = NULL;
-
- name = host->req->rq_disk->disk_name;
- printk(KERN_DEBUG "%s: timeout\n", name);
-
- host->error = MG_ERR_TIMEOUT;
- mg_bad_rw_intr(host);
-
-out_unlock:
- mg_request(host->breq);
- spin_unlock_irq(&host->lock);
-}
-
-static void mg_request_poll(struct request_queue *q)
-{
- struct mg_host *host = q->queuedata;
-
- while (1) {
- if (!host->req) {
- host->req = blk_fetch_request(q);
- if (!host->req)
- break;
- }
-
- switch (req_op(host->req)) {
- case REQ_OP_READ:
- mg_read(host->req);
- break;
- case REQ_OP_WRITE:
- mg_write(host->req);
- break;
- default:
- mg_end_request_cur(host, -EIO);
- break;
- }
- }
-}
-
-static unsigned int mg_issue_req(struct request *req,
- struct mg_host *host,
- unsigned int sect_num,
- unsigned int sect_cnt)
-{
- switch (req_op(host->req)) {
- case REQ_OP_READ:
- if (mg_out(host, sect_num, sect_cnt, MG_CMD_RD, &mg_read_intr)
- != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- break;
- case REQ_OP_WRITE:
- /* TODO : handler */
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- if (mg_out(host, sect_num, sect_cnt, MG_CMD_WR, &mg_write_intr)
- != MG_ERR_NONE) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- del_timer(&host->timer);
- mg_wait(host, ATA_DRQ, MG_TMAX_WAIT_WR_DRQ);
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- if (host->error) {
- mg_bad_rw_intr(host);
- return host->error;
- }
- mg_write_one(host, req);
- mod_timer(&host->timer, jiffies + 3 * HZ);
- outb(MG_CMD_WR_CONF, (unsigned long)host->dev_base +
- MG_REG_COMMAND);
- break;
- default:
- mg_end_request_cur(host, -EIO);
- break;
- }
- return MG_ERR_NONE;
-}
-
-/* This function also called from IRQ context */
-static void mg_request(struct request_queue *q)
-{
- struct mg_host *host = q->queuedata;
- struct request *req;
- u32 sect_num, sect_cnt;
-
- while (1) {
- if (!host->req) {
- host->req = blk_fetch_request(q);
- if (!host->req)
- break;
- }
- req = host->req;
-
- /* check unwanted request call */
- if (host->mg_do_intr)
- return;
-
- del_timer(&host->timer);
-
- sect_num = blk_rq_pos(req);
- /* deal whole segments */
- sect_cnt = blk_rq_sectors(req);
-
- /* sanity check */
- if (sect_num >= get_capacity(req->rq_disk) ||
- ((sect_num + sect_cnt) >
- get_capacity(req->rq_disk))) {
- printk(KERN_WARNING
- "%s: bad access: sector=%d, count=%d\n",
- req->rq_disk->disk_name,
- sect_num, sect_cnt);
- mg_end_request_cur(host, -EIO);
- continue;
- }
-
- if (!mg_issue_req(req, host, sect_num, sect_cnt))
- return;
- }
-}
-
-static int mg_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
- struct mg_host *host = bdev->bd_disk->private_data;
-
- geo->cylinders = (unsigned short)host->cyls;
- geo->heads = (unsigned char)host->heads;
- geo->sectors = (unsigned char)host->sectors;
- return 0;
-}
-
-static const struct block_device_operations mg_disk_ops = {
- .getgeo = mg_getgeo
-};
-
-#ifdef CONFIG_PM_SLEEP
-static int mg_suspend(struct device *dev)
-{
- struct mg_drv_data *prv_data = dev->platform_data;
- struct mg_host *host = prv_data->host;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- if (!prv_data->use_polling)
- outb(ATA_NIEN, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- outb(MG_CMD_SLEEP, (unsigned long)host->dev_base + MG_REG_COMMAND);
- /* wait until mflash deep sleep */
- msleep(1);
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD)) {
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
- return -EIO;
- }
-
- return 0;
-}
-
-static int mg_resume(struct device *dev)
-{
- struct mg_drv_data *prv_data = dev->platform_data;
- struct mg_host *host = prv_data->host;
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- outb(MG_CMD_WAKEUP, (unsigned long)host->dev_base + MG_REG_COMMAND);
- /* wait until mflash wakeup */
- msleep(1);
-
- if (mg_wait(host, MG_STAT_READY, MG_TMAX_CONF_TO_CMD))
- return -EIO;
-
- if (!prv_data->use_polling)
- outb(0, (unsigned long)host->dev_base + MG_REG_DRV_CTRL);
-
- return 0;
-}
-#endif
-
-static SIMPLE_DEV_PM_OPS(mg_pm, mg_suspend, mg_resume);
-
-static int mg_probe(struct platform_device *plat_dev)
-{
- struct mg_host *host;
- struct resource *rsc;
- struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
- int err = 0;
-
- if (!prv_data) {
- printk(KERN_ERR "%s:%d fail (no driver_data)\n",
- __func__, __LINE__);
- err = -EINVAL;
- goto probe_err;
- }
-
- /* alloc mg_host */
- host = kzalloc(sizeof(struct mg_host), GFP_KERNEL);
- if (!host) {
- printk(KERN_ERR "%s:%d fail (no memory for mg_host)\n",
- __func__, __LINE__);
- err = -ENOMEM;
- goto probe_err;
- }
- host->major = MG_DISK_MAJ;
-
- /* link each other */
- prv_data->host = host;
- host->dev = &plat_dev->dev;
-
- /* io remap */
- rsc = platform_get_resource(plat_dev, IORESOURCE_MEM, 0);
- if (!rsc) {
- printk(KERN_ERR "%s:%d platform_get_resource fail\n",
- __func__, __LINE__);
- err = -EINVAL;
- goto probe_err_2;
- }
- host->dev_base = ioremap(rsc->start, resource_size(rsc));
- if (!host->dev_base) {
- printk(KERN_ERR "%s:%d ioremap fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_2;
- }
- MG_DBG("dev_base = 0x%x\n", (u32)host->dev_base);
-
- /* get reset pin */
- rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
- MG_RST_PIN);
- if (!rsc) {
- printk(KERN_ERR "%s:%d get reset pin fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_3;
- }
- host->rst = rsc->start;
-
- /* init rst pin */
- err = gpio_request(host->rst, MG_RST_PIN);
- if (err)
- goto probe_err_3;
- gpio_direction_output(host->rst, 1);
-
- /* reset out pin */
- if (!(prv_data->dev_attr & MG_DEV_MASK)) {
- err = -EINVAL;
- goto probe_err_3a;
- }
-
- if (prv_data->dev_attr != MG_BOOT_DEV) {
- rsc = platform_get_resource_byname(plat_dev, IORESOURCE_IO,
- MG_RSTOUT_PIN);
- if (!rsc) {
- printk(KERN_ERR "%s:%d get reset-out pin fail\n",
- __func__, __LINE__);
- err = -EIO;
- goto probe_err_3a;
- }
- host->rstout = rsc->start;
- err = gpio_request(host->rstout, MG_RSTOUT_PIN);
- if (err)
- goto probe_err_3a;
- gpio_direction_input(host->rstout);
- }
-
- /* disk reset */
- if (prv_data->dev_attr == MG_STORAGE_DEV) {
- /* If POR seq. not yet finished, wait */
- err = mg_wait_rstout(host->rstout, MG_TMAX_RSTOUT);
- if (err)
- goto probe_err_3b;
- err = mg_disk_init(host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (err code : %d)\n",
- __func__, __LINE__, err);
- err = -EIO;
- goto probe_err_3b;
- }
- }
-
- /* get irq resource */
- if (!prv_data->use_polling) {
- host->irq = platform_get_irq(plat_dev, 0);
- if (host->irq == -ENXIO) {
- err = host->irq;
- goto probe_err_3b;
- }
- err = request_irq(host->irq, mg_irq,
- IRQF_TRIGGER_RISING,
- MG_DEV_NAME, host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (request_irq err=%d)\n",
- __func__, __LINE__, err);
- goto probe_err_3b;
- }
-
- }
-
- /* get disk id */
- err = mg_get_disk_id(host);
- if (err) {
- printk(KERN_ERR "%s:%d fail (err code : %d)\n",
- __func__, __LINE__, err);
- err = -EIO;
- goto probe_err_4;
- }
-
- err = register_blkdev(host->major, MG_DISK_NAME);
- if (err < 0) {
- printk(KERN_ERR "%s:%d register_blkdev fail (err code : %d)\n",
- __func__, __LINE__, err);
- goto probe_err_4;
- }
- if (!host->major)
- host->major = err;
-
- spin_lock_init(&host->lock);
-
- if (prv_data->use_polling)
- host->breq = blk_init_queue(mg_request_poll, &host->lock);
- else
- host->breq = blk_init_queue(mg_request, &host->lock);
-
- if (!host->breq) {
- err = -ENOMEM;
- printk(KERN_ERR "%s:%d (blk_init_queue) fail\n",
- __func__, __LINE__);
- goto probe_err_5;
- }
- host->breq->queuedata = host;
-
- /* mflash is random device, thanx for the noop */
- err = elevator_change(host->breq, "noop");
- if (err) {
- printk(KERN_ERR "%s:%d (elevator_init) fail\n",
- __func__, __LINE__);
- goto probe_err_6;
- }
- blk_queue_max_hw_sectors(host->breq, MG_MAX_SECTS);
- blk_queue_logical_block_size(host->breq, MG_SECTOR_SIZE);
-
- init_timer(&host->timer);
- host->timer.function = mg_times_out;
- host->timer.data = (unsigned long)host;
-
- host->gd = alloc_disk(MG_DISK_MAX_PART);
- if (!host->gd) {
- printk(KERN_ERR "%s:%d (alloc_disk) fail\n",
- __func__, __LINE__);
- err = -ENOMEM;
- goto probe_err_7;
- }
- host->gd->major = host->major;
- host->gd->first_minor = 0;
- host->gd->fops = &mg_disk_ops;
- host->gd->queue = host->breq;
- host->gd->private_data = host;
- sprintf(host->gd->disk_name, MG_DISK_NAME"a");
-
- set_capacity(host->gd, host->n_sectors);
-
- add_disk(host->gd);
-
- return err;
-
-probe_err_7:
- del_timer_sync(&host->timer);
-probe_err_6:
- blk_cleanup_queue(host->breq);
-probe_err_5:
- unregister_blkdev(host->major, MG_DISK_NAME);
-probe_err_4:
- if (!prv_data->use_polling)
- free_irq(host->irq, host);
-probe_err_3b:
- gpio_free(host->rstout);
-probe_err_3a:
- gpio_free(host->rst);
-probe_err_3:
- iounmap(host->dev_base);
-probe_err_2:
- kfree(host);
-probe_err:
- return err;
-}
-
-static int mg_remove(struct platform_device *plat_dev)
-{
- struct mg_drv_data *prv_data = plat_dev->dev.platform_data;
- struct mg_host *host = prv_data->host;
- int err = 0;
-
- /* delete timer */
- del_timer_sync(&host->timer);
-
- /* remove disk */
- if (host->gd) {
- del_gendisk(host->gd);
- put_disk(host->gd);
- }
- /* remove queue */
- if (host->breq)
- blk_cleanup_queue(host->breq);
-
- /* unregister blk device */
- unregister_blkdev(host->major, MG_DISK_NAME);
-
- /* free irq */
- if (!prv_data->use_polling)
- free_irq(host->irq, host);
-
- /* free reset-out pin */
- if (prv_data->dev_attr != MG_BOOT_DEV)
- gpio_free(host->rstout);
-
- /* free rst pin */
- if (host->rst)
- gpio_free(host->rst);
-
- /* unmap io */
- if (host->dev_base)
- iounmap(host->dev_base);
-
- /* free mg_host */
- kfree(host);
-
- return err;
-}
-
-static struct platform_driver mg_disk_driver = {
- .probe = mg_probe,
- .remove = mg_remove,
- .driver = {
- .name = MG_DEV_NAME,
- .pm = &mg_pm,
- }
-};
-
-/****************************************************************************
- *
- * Module stuff
- *
- ****************************************************************************/
-
-static int __init mg_init(void)
-{
- printk(KERN_INFO "mGine mflash driver, (c) 2008 mGine Co.\n");
- return platform_driver_register(&mg_disk_driver);
-}
-
-static void __exit mg_exit(void)
-{
- printk(KERN_INFO "mflash driver : bye bye\n");
- platform_driver_unregister(&mg_disk_driver);
-}
-
-module_init(mg_init);
-module_exit(mg_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("unsik Kim <donari75@gmail.com>");
-MODULE_DESCRIPTION("mGine m[g]flash device driver");
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 1d1dc11aa5fa..02804cc79d82 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -169,6 +169,25 @@ static bool mtip_check_surprise_removal(struct pci_dev *pdev)
return false; /* device present */
}
+/* we have to use runtime tag to setup command header */
+static void mtip_init_cmd_header(struct request *rq)
+{
+ struct driver_data *dd = rq->q->queuedata;
+ struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
+ u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
+
+ /* Point the command headers at the command tables. */
+ cmd->command_header = dd->port->command_list +
+ (sizeof(struct mtip_cmd_hdr) * rq->tag);
+ cmd->command_header_dma = dd->port->command_list_dma +
+ (sizeof(struct mtip_cmd_hdr) * rq->tag);
+
+ if (host_cap_64)
+ cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
+
+ cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
+}
+
static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
{
struct request *rq;
@@ -180,6 +199,9 @@ static struct mtip_cmd *mtip_get_int_command(struct driver_data *dd)
if (IS_ERR(rq))
return NULL;
+ /* Internal cmd isn't submitted via .queue_rq */
+ mtip_init_cmd_header(rq);
+
return blk_mq_rq_to_pdu(rq);
}
@@ -241,7 +263,8 @@ static void mtip_async_complete(struct mtip_port *port,
rq = mtip_rq_from_tag(dd, tag);
- blk_mq_complete_request(rq, status);
+ cmd->status = status;
+ blk_mq_complete_request(rq);
}
/*
@@ -2910,18 +2933,19 @@ static void mtip_softirq_done_fn(struct request *rq)
if (unlikely(cmd->unaligned))
up(&dd->port->cmd_slot_unal);
- blk_mq_end_request(rq, rq->errors);
+ blk_mq_end_request(rq, cmd->status);
}
static void mtip_abort_cmd(struct request *req, void *data,
bool reserved)
{
+ struct mtip_cmd *cmd = blk_mq_rq_to_pdu(req);
struct driver_data *dd = data;
dbg_printk(MTIP_DRV_NAME " Aborting request, tag = %d\n", req->tag);
clear_bit(req->tag, dd->port->cmds_to_issue);
- req->errors = -EIO;
+ cmd->status = -EIO;
mtip_softirq_done_fn(req);
}
@@ -3807,6 +3831,8 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
struct request *rq = bd->rq;
int ret;
+ mtip_init_cmd_header(rq);
+
if (unlikely(mtip_check_unal_depth(hctx, rq)))
return BLK_MQ_RQ_QUEUE_BUSY;
@@ -3816,7 +3842,6 @@ static int mtip_queue_rq(struct blk_mq_hw_ctx *hctx,
if (likely(!ret))
return BLK_MQ_RQ_QUEUE_OK;
- rq->errors = ret;
return BLK_MQ_RQ_QUEUE_ERROR;
}
@@ -3838,7 +3863,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
{
struct driver_data *dd = data;
struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq);
- u32 host_cap_64 = readl(dd->mmio + HOST_CAP) & HOST_CAP_64;
/*
* For flush requests, request_idx starts at the end of the
@@ -3855,17 +3879,6 @@ static int mtip_init_cmd(void *data, struct request *rq, unsigned int hctx_idx,
memset(cmd->command, 0, CMD_DMA_ALLOC_SZ);
- /* Point the command headers at the command tables. */
- cmd->command_header = dd->port->command_list +
- (sizeof(struct mtip_cmd_hdr) * request_idx);
- cmd->command_header_dma = dd->port->command_list_dma +
- (sizeof(struct mtip_cmd_hdr) * request_idx);
-
- if (host_cap_64)
- cmd->command_header->ctbau = __force_bit2int cpu_to_le32((cmd->command_dma >> 16) >> 16);
-
- cmd->command_header->ctba = __force_bit2int cpu_to_le32(cmd->command_dma & 0xFFFFFFFF);
-
sg_init_table(cmd->sg, MTIP_MAX_SG);
return 0;
}
@@ -3889,7 +3902,7 @@ exit_handler:
return BLK_EH_RESET_TIMER;
}
-static struct blk_mq_ops mtip_mq_ops = {
+static const struct blk_mq_ops mtip_mq_ops = {
.queue_rq = mtip_queue_rq,
.init_request = mtip_init_cmd,
.exit_request = mtip_free_cmd,
@@ -4025,7 +4038,6 @@ skip_create_disk:
dd->queue->limits.discard_granularity = 4096;
blk_queue_max_discard_sectors(dd->queue,
MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES);
- dd->queue->limits.discard_zeroes_data = 0;
}
/* Set the capacity of the device in 512 byte sectors. */
@@ -4107,9 +4119,11 @@ static void mtip_no_dev_cleanup(struct request *rq, void *data, bool reserv)
struct driver_data *dd = (struct driver_data *)data;
struct mtip_cmd *cmd;
- if (likely(!reserv))
- blk_mq_complete_request(rq, -ENODEV);
- else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
+ if (likely(!reserv)) {
+ cmd = blk_mq_rq_to_pdu(rq);
+ cmd->status = -ENODEV;
+ blk_mq_complete_request(rq);
+ } else if (test_bit(MTIP_PF_IC_ACTIVE_BIT, &dd->port->flags)) {
cmd = mtip_cmd_from_tag(dd, MTIP_TAG_INTERNAL);
if (cmd->comp_func)
@@ -4162,7 +4176,7 @@ static int mtip_block_remove(struct driver_data *dd)
dev_info(&dd->pdev->dev, "device %s surprise removal\n",
dd->disk->disk_name);
- blk_mq_freeze_queue_start(dd->queue);
+ blk_freeze_queue_start(dd->queue);
blk_mq_stop_hw_queues(dd->queue);
blk_mq_tagset_busy_iter(&dd->tags, mtip_no_dev_cleanup, dd);
diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h
index 7617888f7944..57b41528a824 100644
--- a/drivers/block/mtip32xx/mtip32xx.h
+++ b/drivers/block/mtip32xx/mtip32xx.h
@@ -352,6 +352,7 @@ struct mtip_cmd {
int retries; /* The number of retries left for this command. */
int direction; /* Data transfer direction */
+ int status;
};
/* Structure used to describe a port. */
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index d8a23561b4cb..ac376b9b852d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -40,49 +40,82 @@
#include <asm/types.h>
#include <linux/nbd.h>
+#include <linux/nbd-netlink.h>
+#include <net/genetlink.h>
static DEFINE_IDR(nbd_index_idr);
static DEFINE_MUTEX(nbd_index_mutex);
+static int nbd_total_devices = 0;
struct nbd_sock {
struct socket *sock;
struct mutex tx_lock;
struct request *pending;
int sent;
+ bool dead;
+ int fallback_index;
+ int cookie;
+};
+
+struct recv_thread_args {
+ struct work_struct work;
+ struct nbd_device *nbd;
+ int index;
+};
+
+struct link_dead_args {
+ struct work_struct work;
+ int index;
};
#define NBD_TIMEDOUT 0
#define NBD_DISCONNECT_REQUESTED 1
#define NBD_DISCONNECTED 2
-#define NBD_RUNNING 3
+#define NBD_HAS_PID_FILE 3
+#define NBD_HAS_CONFIG_REF 4
+#define NBD_BOUND 5
+#define NBD_DESTROY_ON_DISCONNECT 6
-struct nbd_device {
+struct nbd_config {
u32 flags;
unsigned long runtime_flags;
- struct nbd_sock **socks;
- int magic;
+ u64 dead_conn_timeout;
- struct blk_mq_tag_set tag_set;
-
- struct mutex config_lock;
- struct gendisk *disk;
+ struct nbd_sock **socks;
int num_connections;
+ atomic_t live_connections;
+ wait_queue_head_t conn_wait;
+
atomic_t recv_threads;
wait_queue_head_t recv_wq;
loff_t blksize;
loff_t bytesize;
-
- struct task_struct *task_recv;
- struct task_struct *task_setup;
-
#if IS_ENABLED(CONFIG_DEBUG_FS)
struct dentry *dbg_dir;
#endif
};
+struct nbd_device {
+ struct blk_mq_tag_set tag_set;
+
+ int index;
+ refcount_t config_refs;
+ refcount_t refs;
+ struct nbd_config *config;
+ struct mutex config_lock;
+ struct gendisk *disk;
+
+ struct list_head list;
+ struct task_struct *task_recv;
+ struct task_struct *task_setup;
+};
+
struct nbd_cmd {
struct nbd_device *nbd;
+ int index;
+ int cookie;
struct completion send_complete;
+ int status;
};
#if IS_ENABLED(CONFIG_DEBUG_FS)
@@ -100,18 +133,16 @@ static int part_shift;
static int nbd_dev_dbg_init(struct nbd_device *nbd);
static void nbd_dev_dbg_close(struct nbd_device *nbd);
-
+static void nbd_config_put(struct nbd_device *nbd);
+static void nbd_connect_reply(struct genl_info *info, int index);
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info);
+static void nbd_dead_link_work(struct work_struct *work);
static inline struct device *nbd_to_dev(struct nbd_device *nbd)
{
return disk_to_dev(nbd->disk);
}
-static bool nbd_is_connected(struct nbd_device *nbd)
-{
- return !!nbd->task_recv;
-}
-
static const char *nbdcmd_to_ascii(int cmd)
{
switch (cmd) {
@@ -124,44 +155,104 @@ static const char *nbdcmd_to_ascii(int cmd)
return "invalid";
}
-static int nbd_size_clear(struct nbd_device *nbd, struct block_device *bdev)
+static ssize_t pid_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
{
- if (bdev->bd_openers <= 1)
- bd_set_size(bdev, 0);
- set_capacity(nbd->disk, 0);
- kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+ struct gendisk *disk = dev_to_disk(dev);
+ struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
- return 0;
+ return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
+}
+
+static struct device_attribute pid_attr = {
+ .attr = { .name = "pid", .mode = S_IRUGO},
+ .show = pid_show,
+};
+
+static void nbd_dev_remove(struct nbd_device *nbd)
+{
+ struct gendisk *disk = nbd->disk;
+ if (disk) {
+ del_gendisk(disk);
+ blk_cleanup_queue(disk->queue);
+ blk_mq_free_tag_set(&nbd->tag_set);
+ disk->private_data = NULL;
+ put_disk(disk);
+ }
+ kfree(nbd);
+}
+
+static void nbd_put(struct nbd_device *nbd)
+{
+ if (refcount_dec_and_mutex_lock(&nbd->refs,
+ &nbd_index_mutex)) {
+ idr_remove(&nbd_index_idr, nbd->index);
+ mutex_unlock(&nbd_index_mutex);
+ nbd_dev_remove(nbd);
+ }
+}
+
+static int nbd_disconnected(struct nbd_config *config)
+{
+ return test_bit(NBD_DISCONNECTED, &config->runtime_flags) ||
+ test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags);
+}
+
+static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
+ int notify)
+{
+ if (!nsock->dead && notify && !nbd_disconnected(nbd->config)) {
+ struct link_dead_args *args;
+ args = kmalloc(sizeof(struct link_dead_args), GFP_NOIO);
+ if (args) {
+ INIT_WORK(&args->work, nbd_dead_link_work);
+ args->index = nbd->index;
+ queue_work(system_wq, &args->work);
+ }
+ }
+ if (!nsock->dead) {
+ kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+ atomic_dec(&nbd->config->live_connections);
+ }
+ nsock->dead = true;
+ nsock->pending = NULL;
+ nsock->sent = 0;
+}
+
+static void nbd_size_clear(struct nbd_device *nbd)
+{
+ if (nbd->config->bytesize) {
+ set_capacity(nbd->disk, 0);
+ kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
+ }
}
-static void nbd_size_update(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_size_update(struct nbd_device *nbd)
{
- blk_queue_logical_block_size(nbd->disk->queue, nbd->blksize);
- blk_queue_physical_block_size(nbd->disk->queue, nbd->blksize);
- bd_set_size(bdev, nbd->bytesize);
- set_capacity(nbd->disk, nbd->bytesize >> 9);
+ struct nbd_config *config = nbd->config;
+ blk_queue_logical_block_size(nbd->disk->queue, config->blksize);
+ blk_queue_physical_block_size(nbd->disk->queue, config->blksize);
+ set_capacity(nbd->disk, config->bytesize >> 9);
kobject_uevent(&nbd_to_dev(nbd)->kobj, KOBJ_CHANGE);
}
-static void nbd_size_set(struct nbd_device *nbd, struct block_device *bdev,
- loff_t blocksize, loff_t nr_blocks)
+static void nbd_size_set(struct nbd_device *nbd, loff_t blocksize,
+ loff_t nr_blocks)
{
- nbd->blksize = blocksize;
- nbd->bytesize = blocksize * nr_blocks;
- if (nbd_is_connected(nbd))
- nbd_size_update(nbd, bdev);
+ struct nbd_config *config = nbd->config;
+ config->blksize = blocksize;
+ config->bytesize = blocksize * nr_blocks;
+ nbd_size_update(nbd);
}
-static void nbd_end_request(struct nbd_cmd *cmd)
+static void nbd_complete_rq(struct request *req)
{
- struct nbd_device *nbd = cmd->nbd;
- struct request *req = blk_mq_rq_from_pdu(cmd);
- int error = req->errors ? -EIO : 0;
+ struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
- dev_dbg(nbd_to_dev(nbd), "request %p: %s\n", cmd,
- error ? "failed" : "done");
+ dev_dbg(nbd_to_dev(cmd->nbd), "request %p: %s\n", cmd,
+ cmd->status ? "failed" : "done");
- blk_mq_complete_request(req, error);
+ blk_mq_end_request(req, cmd->status);
}
/*
@@ -169,17 +260,18 @@ static void nbd_end_request(struct nbd_cmd *cmd)
*/
static void sock_shutdown(struct nbd_device *nbd)
{
+ struct nbd_config *config = nbd->config;
int i;
- if (nbd->num_connections == 0)
+ if (config->num_connections == 0)
return;
- if (test_and_set_bit(NBD_DISCONNECTED, &nbd->runtime_flags))
+ if (test_and_set_bit(NBD_DISCONNECTED, &config->runtime_flags))
return;
- for (i = 0; i < nbd->num_connections; i++) {
- struct nbd_sock *nsock = nbd->socks[i];
+ for (i = 0; i < config->num_connections; i++) {
+ struct nbd_sock *nsock = config->socks[i];
mutex_lock(&nsock->tx_lock);
- kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
+ nbd_mark_nsock_dead(nbd, nsock, 0);
mutex_unlock(&nsock->tx_lock);
}
dev_warn(disk_to_dev(nbd->disk), "shutting down sockets\n");
@@ -190,14 +282,58 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
{
struct nbd_cmd *cmd = blk_mq_rq_to_pdu(req);
struct nbd_device *nbd = cmd->nbd;
+ struct nbd_config *config;
- dev_err(nbd_to_dev(nbd), "Connection timed out, shutting down connection\n");
- set_bit(NBD_TIMEDOUT, &nbd->runtime_flags);
- req->errors = -EIO;
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ cmd->status = -EIO;
+ return BLK_EH_HANDLED;
+ }
- mutex_lock(&nbd->config_lock);
+ /* If we are waiting on our dead timer then we could get timeout
+ * callbacks for our request. For this we just want to reset the timer
+ * and let the queue side take care of everything.
+ */
+ if (!completion_done(&cmd->send_complete)) {
+ nbd_config_put(nbd);
+ return BLK_EH_RESET_TIMER;
+ }
+ config = nbd->config;
+
+ if (config->num_connections > 1) {
+ dev_err_ratelimited(nbd_to_dev(nbd),
+ "Connection timed out, retrying\n");
+ /*
+ * Hooray we have more connections, requeue this IO, the submit
+ * path will put it on a real connection.
+ */
+ if (config->socks && config->num_connections > 1) {
+ if (cmd->index < config->num_connections) {
+ struct nbd_sock *nsock =
+ config->socks[cmd->index];
+ mutex_lock(&nsock->tx_lock);
+ /* We can have multiple outstanding requests, so
+ * we don't want to mark the nsock dead if we've
+ * already reconnected with a new socket, so
+ * only mark it dead if its the same socket we
+ * were sent out on.
+ */
+ if (cmd->cookie == nsock->cookie)
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+ }
+ blk_mq_requeue_request(req, true);
+ nbd_config_put(nbd);
+ return BLK_EH_NOT_HANDLED;
+ }
+ } else {
+ dev_err_ratelimited(nbd_to_dev(nbd),
+ "Connection timed out\n");
+ }
+ set_bit(NBD_TIMEDOUT, &config->runtime_flags);
+ cmd->status = -EIO;
sock_shutdown(nbd);
- mutex_unlock(&nbd->config_lock);
+ nbd_config_put(nbd);
+
return BLK_EH_HANDLED;
}
@@ -207,7 +343,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
static int sock_xmit(struct nbd_device *nbd, int index, int send,
struct iov_iter *iter, int msg_flags, int *sent)
{
- struct socket *sock = nbd->socks[index]->sock;
+ struct nbd_config *config = nbd->config;
+ struct socket *sock = config->socks[index]->sock;
int result;
struct msghdr msg;
unsigned long pflags = current->flags;
@@ -253,7 +390,8 @@ static int sock_xmit(struct nbd_device *nbd, int index, int send,
static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
- struct nbd_sock *nsock = nbd->socks[index];
+ struct nbd_config *config = nbd->config;
+ struct nbd_sock *nsock = config->socks[index];
int result;
struct nbd_request request = {.magic = htonl(NBD_REQUEST_MAGIC)};
struct kvec iov = {.iov_base = &request, .iov_len = sizeof(request)};
@@ -284,7 +422,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
if (rq_data_dir(req) == WRITE &&
- (nbd->flags & NBD_FLAG_READ_ONLY)) {
+ (config->flags & NBD_FLAG_READ_ONLY)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Write on read-only\n");
return -EIO;
@@ -301,6 +439,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
iov_iter_advance(&from, sent);
}
+ cmd->index = index;
+ cmd->cookie = nsock->cookie;
request.type = htonl(type);
if (type != NBD_CMD_FLUSH) {
request.from = cpu_to_be64((u64)blk_rq_pos(req) << 9);
@@ -328,7 +468,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
}
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Send control failed (result %d)\n", result);
- return -EIO;
+ return -EAGAIN;
}
send_pages:
if (type != NBD_CMD_WRITE)
@@ -370,7 +510,7 @@ send_pages:
dev_err(disk_to_dev(nbd->disk),
"Send data failed (result %d)\n",
result);
- return -EIO;
+ return -EAGAIN;
}
/*
* The completion might already have come in,
@@ -392,6 +532,7 @@ out:
/* NULL returned = something went wrong, inform userspace */
static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
{
+ struct nbd_config *config = nbd->config;
int result;
struct nbd_reply reply;
struct nbd_cmd *cmd;
@@ -405,8 +546,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply));
result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL);
if (result <= 0) {
- if (!test_bit(NBD_DISCONNECTED, &nbd->runtime_flags) &&
- !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
+ if (!nbd_disconnected(config))
dev_err(disk_to_dev(nbd->disk),
"Receive control failed (result %d)\n", result);
return ERR_PTR(result);
@@ -433,7 +573,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
if (ntohl(reply.error)) {
dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n",
ntohl(reply.error));
- req->errors = -EIO;
+ cmd->status = -EIO;
return cmd;
}
@@ -449,8 +589,19 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
if (result <= 0) {
dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n",
result);
- req->errors = -EIO;
- return cmd;
+ /*
+ * If we've disconnected or we only have 1
+ * connection then we need to make sure we
+ * complete this request, otherwise error out
+ * and let the timeout stuff handle resubmitting
+ * this request onto another connection.
+ */
+ if (nbd_disconnected(config) ||
+ config->num_connections <= 1) {
+ cmd->status = -EIO;
+ return cmd;
+ }
+ return ERR_PTR(-EIO);
}
dev_dbg(nbd_to_dev(nbd), "request %p: got %d bytes data\n",
cmd, bvec.bv_len);
@@ -462,54 +613,34 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index)
return cmd;
}
-static ssize_t pid_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gendisk *disk = dev_to_disk(dev);
- struct nbd_device *nbd = (struct nbd_device *)disk->private_data;
-
- return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv));
-}
-
-static struct device_attribute pid_attr = {
- .attr = { .name = "pid", .mode = S_IRUGO},
- .show = pid_show,
-};
-
-struct recv_thread_args {
- struct work_struct work;
- struct nbd_device *nbd;
- int index;
-};
-
static void recv_work(struct work_struct *work)
{
struct recv_thread_args *args = container_of(work,
struct recv_thread_args,
work);
struct nbd_device *nbd = args->nbd;
+ struct nbd_config *config = nbd->config;
struct nbd_cmd *cmd;
int ret = 0;
- BUG_ON(nbd->magic != NBD_MAGIC);
while (1) {
cmd = nbd_read_stat(nbd, args->index);
if (IS_ERR(cmd)) {
+ struct nbd_sock *nsock = config->socks[args->index];
+
+ mutex_lock(&nsock->tx_lock);
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
ret = PTR_ERR(cmd);
break;
}
- nbd_end_request(cmd);
+ blk_mq_complete_request(blk_mq_rq_from_pdu(cmd));
}
-
- /*
- * We got an error, shut everybody down if this wasn't the result of a
- * disconnect request.
- */
- if (ret && !test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
- sock_shutdown(nbd);
- atomic_dec(&nbd->recv_threads);
- wake_up(&nbd->recv_wq);
+ atomic_dec(&config->recv_threads);
+ wake_up(&config->recv_wq);
+ nbd_config_put(nbd);
+ kfree(args);
}
static void nbd_clear_req(struct request *req, void *data, bool reserved)
@@ -519,47 +650,119 @@ static void nbd_clear_req(struct request *req, void *data, bool reserved)
if (!blk_mq_request_started(req))
return;
cmd = blk_mq_rq_to_pdu(req);
- req->errors = -EIO;
- nbd_end_request(cmd);
+ cmd->status = -EIO;
+ blk_mq_complete_request(req);
}
static void nbd_clear_que(struct nbd_device *nbd)
{
- BUG_ON(nbd->magic != NBD_MAGIC);
-
+ blk_mq_stop_hw_queues(nbd->disk->queue);
blk_mq_tagset_busy_iter(&nbd->tag_set, nbd_clear_req, NULL);
+ blk_mq_start_hw_queues(nbd->disk->queue);
dev_dbg(disk_to_dev(nbd->disk), "queue cleared\n");
}
+static int find_fallback(struct nbd_device *nbd, int index)
+{
+ struct nbd_config *config = nbd->config;
+ int new_index = -1;
+ struct nbd_sock *nsock = config->socks[index];
+ int fallback = nsock->fallback_index;
+
+ if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+ return new_index;
+
+ if (config->num_connections <= 1) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Attempted send on invalid socket\n");
+ return new_index;
+ }
+
+ if (fallback >= 0 && fallback < config->num_connections &&
+ !config->socks[fallback]->dead)
+ return fallback;
+
+ if (nsock->fallback_index < 0 ||
+ nsock->fallback_index >= config->num_connections ||
+ config->socks[nsock->fallback_index]->dead) {
+ int i;
+ for (i = 0; i < config->num_connections; i++) {
+ if (i == index)
+ continue;
+ if (!config->socks[i]->dead) {
+ new_index = i;
+ break;
+ }
+ }
+ nsock->fallback_index = new_index;
+ if (new_index < 0) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Dead connection, failed to find a fallback\n");
+ return new_index;
+ }
+ }
+ new_index = nsock->fallback_index;
+ return new_index;
+}
+
+static int wait_for_reconnect(struct nbd_device *nbd)
+{
+ struct nbd_config *config = nbd->config;
+ if (!config->dead_conn_timeout)
+ return 0;
+ if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
+ return 0;
+ wait_event_interruptible_timeout(config->conn_wait,
+ atomic_read(&config->live_connections),
+ config->dead_conn_timeout);
+ return atomic_read(&config->live_connections);
+}
static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
{
struct request *req = blk_mq_rq_from_pdu(cmd);
struct nbd_device *nbd = cmd->nbd;
+ struct nbd_config *config;
struct nbd_sock *nsock;
int ret;
- if (index >= nbd->num_connections) {
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on invalid socket\n");
+ "Socks array is empty\n");
return -EINVAL;
}
+ config = nbd->config;
- if (test_bit(NBD_DISCONNECTED, &nbd->runtime_flags)) {
+ if (index >= config->num_connections) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on closed socket\n");
+ "Attempted send on invalid socket\n");
+ nbd_config_put(nbd);
return -EINVAL;
}
-
- req->errors = 0;
-
- nsock = nbd->socks[index];
+ cmd->status = 0;
+again:
+ nsock = config->socks[index];
mutex_lock(&nsock->tx_lock);
- if (unlikely(!nsock->sock)) {
+ if (nsock->dead) {
+ int old_index = index;
+ index = find_fallback(nbd, index);
mutex_unlock(&nsock->tx_lock);
- dev_err_ratelimited(disk_to_dev(nbd->disk),
- "Attempted send on closed socket\n");
- return -EINVAL;
+ if (index < 0) {
+ if (wait_for_reconnect(nbd)) {
+ index = old_index;
+ goto again;
+ }
+ /* All the sockets should already be down at this point,
+ * we just want to make sure that DISCONNECTED is set so
+ * any requests that come in that were queue'ed waiting
+ * for the reconnect timer don't trigger the timer again
+ * and instead just error out.
+ */
+ sock_shutdown(nbd);
+ nbd_config_put(nbd);
+ return -EIO;
+ }
+ goto again;
}
/* Handle the case that we have a pending request that was partially
@@ -572,9 +775,21 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
ret = 0;
goto out;
}
+ /*
+ * Some failures are related to the link going down, so anything that
+ * returns EAGAIN can be retried on a different socket.
+ */
ret = nbd_send_cmd(nbd, cmd, index);
+ if (ret == -EAGAIN) {
+ dev_err_ratelimited(disk_to_dev(nbd->disk),
+ "Request send failed trying another connection\n");
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+ goto again;
+ }
out:
mutex_unlock(&nsock->tx_lock);
+ nbd_config_put(nbd);
return ret;
}
@@ -611,9 +826,10 @@ static int nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
return ret;
}
-static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
- unsigned long arg)
+static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
+ bool netlink)
{
+ struct nbd_config *config = nbd->config;
struct socket *sock;
struct nbd_sock **socks;
struct nbd_sock *nsock;
@@ -623,43 +839,107 @@ static int nbd_add_socket(struct nbd_device *nbd, struct block_device *bdev,
if (!sock)
return err;
- if (!nbd->task_setup)
+ if (!netlink && !nbd->task_setup &&
+ !test_bit(NBD_BOUND, &config->runtime_flags))
nbd->task_setup = current;
- if (nbd->task_setup != current) {
+
+ if (!netlink &&
+ (nbd->task_setup != current ||
+ test_bit(NBD_BOUND, &config->runtime_flags))) {
dev_err(disk_to_dev(nbd->disk),
"Device being setup by another task");
- return -EINVAL;
+ sockfd_put(sock);
+ return -EBUSY;
}
- socks = krealloc(nbd->socks, (nbd->num_connections + 1) *
+ socks = krealloc(config->socks, (config->num_connections + 1) *
sizeof(struct nbd_sock *), GFP_KERNEL);
- if (!socks)
+ if (!socks) {
+ sockfd_put(sock);
return -ENOMEM;
+ }
nsock = kzalloc(sizeof(struct nbd_sock), GFP_KERNEL);
- if (!nsock)
+ if (!nsock) {
+ sockfd_put(sock);
return -ENOMEM;
+ }
- nbd->socks = socks;
+ config->socks = socks;
+ nsock->fallback_index = -1;
+ nsock->dead = false;
mutex_init(&nsock->tx_lock);
nsock->sock = sock;
nsock->pending = NULL;
nsock->sent = 0;
- socks[nbd->num_connections++] = nsock;
+ nsock->cookie = 0;
+ socks[config->num_connections++] = nsock;
+ atomic_inc(&config->live_connections);
- if (max_part)
- bdev->bd_invalidated = 1;
return 0;
}
+static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg)
+{
+ struct nbd_config *config = nbd->config;
+ struct socket *sock, *old;
+ struct recv_thread_args *args;
+ int i;
+ int err;
+
+ sock = sockfd_lookup(arg, &err);
+ if (!sock)
+ return err;
+
+ args = kzalloc(sizeof(*args), GFP_KERNEL);
+ if (!args) {
+ sockfd_put(sock);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < config->num_connections; i++) {
+ struct nbd_sock *nsock = config->socks[i];
+
+ if (!nsock->dead)
+ continue;
+
+ mutex_lock(&nsock->tx_lock);
+ if (!nsock->dead) {
+ mutex_unlock(&nsock->tx_lock);
+ continue;
+ }
+ sk_set_memalloc(sock->sk);
+ atomic_inc(&config->recv_threads);
+ refcount_inc(&nbd->config_refs);
+ old = nsock->sock;
+ nsock->fallback_index = -1;
+ nsock->sock = sock;
+ nsock->dead = false;
+ INIT_WORK(&args->work, recv_work);
+ args->index = i;
+ args->nbd = nbd;
+ nsock->cookie++;
+ mutex_unlock(&nsock->tx_lock);
+ sockfd_put(old);
+
+ /* We take the tx_mutex in an error path in the recv_work, so we
+ * need to queue_work outside of the tx_mutex.
+ */
+ queue_work(recv_workqueue, &args->work);
+
+ atomic_inc(&config->live_connections);
+ wake_up(&config->conn_wait);
+ return 0;
+ }
+ sockfd_put(sock);
+ kfree(args);
+ return -ENOSPC;
+}
+
/* Reset all properties of an NBD device */
static void nbd_reset(struct nbd_device *nbd)
{
- nbd->runtime_flags = 0;
- nbd->blksize = 1024;
- nbd->bytesize = 0;
- set_capacity(nbd->disk, 0);
- nbd->flags = 0;
+ nbd->config = NULL;
nbd->tag_set.timeout = 0;
queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
}
@@ -668,21 +948,23 @@ static void nbd_bdev_reset(struct block_device *bdev)
{
if (bdev->bd_openers > 1)
return;
- set_device_ro(bdev, false);
- bdev->bd_inode->i_size = 0;
+ bd_set_size(bdev, 0);
if (max_part > 0) {
blkdev_reread_part(bdev);
bdev->bd_invalidated = 1;
}
}
-static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_parse_flags(struct nbd_device *nbd)
{
- if (nbd->flags & NBD_FLAG_READ_ONLY)
- set_device_ro(bdev, true);
- if (nbd->flags & NBD_FLAG_SEND_TRIM)
+ struct nbd_config *config = nbd->config;
+ if (config->flags & NBD_FLAG_READ_ONLY)
+ set_disk_ro(nbd->disk, true);
+ else
+ set_disk_ro(nbd->disk, false);
+ if (config->flags & NBD_FLAG_SEND_TRIM)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, nbd->disk->queue);
- if (nbd->flags & NBD_FLAG_SEND_FLUSH)
+ if (config->flags & NBD_FLAG_SEND_FLUSH)
blk_queue_write_cache(nbd->disk->queue, true, false);
else
blk_queue_write_cache(nbd->disk->queue, false, false);
@@ -690,6 +972,7 @@ static void nbd_parse_flags(struct nbd_device *nbd, struct block_device *bdev)
static void send_disconnects(struct nbd_device *nbd)
{
+ struct nbd_config *config = nbd->config;
struct nbd_request request = {
.magic = htonl(NBD_REQUEST_MAGIC),
.type = htonl(NBD_CMD_DISC),
@@ -698,7 +981,7 @@ static void send_disconnects(struct nbd_device *nbd)
struct iov_iter from;
int i, ret;
- for (i = 0; i < nbd->num_connections; i++) {
+ for (i = 0; i < config->num_connections; i++) {
iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request));
ret = sock_xmit(nbd, i, 1, &from, 0, NULL);
if (ret <= 0)
@@ -707,145 +990,162 @@ static void send_disconnects(struct nbd_device *nbd)
}
}
-static int nbd_disconnect(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_disconnect(struct nbd_device *nbd)
{
- dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
- if (!nbd->socks)
- return -EINVAL;
-
- mutex_unlock(&nbd->config_lock);
- fsync_bdev(bdev);
- mutex_lock(&nbd->config_lock);
-
- /* Check again after getting mutex back. */
- if (!nbd->socks)
- return -EINVAL;
+ struct nbd_config *config = nbd->config;
+ dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n");
if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED,
- &nbd->runtime_flags))
+ &config->runtime_flags))
send_disconnects(nbd);
return 0;
}
-static int nbd_clear_sock(struct nbd_device *nbd, struct block_device *bdev)
+static void nbd_clear_sock(struct nbd_device *nbd)
{
sock_shutdown(nbd);
nbd_clear_que(nbd);
+ nbd->task_setup = NULL;
+}
- __invalidate_device(bdev, true);
- nbd_bdev_reset(bdev);
- /*
- * We want to give the run thread a chance to wait for everybody
- * to clean up and then do it's own cleanup.
- */
- if (!test_bit(NBD_RUNNING, &nbd->runtime_flags) &&
- nbd->num_connections) {
- int i;
-
- for (i = 0; i < nbd->num_connections; i++) {
- sockfd_put(nbd->socks[i]->sock);
- kfree(nbd->socks[i]);
+static void nbd_config_put(struct nbd_device *nbd)
+{
+ if (refcount_dec_and_mutex_lock(&nbd->config_refs,
+ &nbd->config_lock)) {
+ struct nbd_config *config = nbd->config;
+ nbd_dev_dbg_close(nbd);
+ nbd_size_clear(nbd);
+ if (test_and_clear_bit(NBD_HAS_PID_FILE,
+ &config->runtime_flags))
+ device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
+ nbd->task_recv = NULL;
+ nbd_clear_sock(nbd);
+ if (config->num_connections) {
+ int i;
+ for (i = 0; i < config->num_connections; i++) {
+ sockfd_put(config->socks[i]->sock);
+ kfree(config->socks[i]);
+ }
+ kfree(config->socks);
}
- kfree(nbd->socks);
- nbd->socks = NULL;
- nbd->num_connections = 0;
- }
- nbd->task_setup = NULL;
+ nbd_reset(nbd);
- return 0;
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ module_put(THIS_MODULE);
+ }
}
-static int nbd_start_device(struct nbd_device *nbd, struct block_device *bdev)
+static int nbd_start_device(struct nbd_device *nbd)
{
- struct recv_thread_args *args;
- int num_connections = nbd->num_connections;
+ struct nbd_config *config = nbd->config;
+ int num_connections = config->num_connections;
int error = 0, i;
if (nbd->task_recv)
return -EBUSY;
- if (!nbd->socks)
+ if (!config->socks)
return -EINVAL;
if (num_connections > 1 &&
- !(nbd->flags & NBD_FLAG_CAN_MULTI_CONN)) {
+ !(config->flags & NBD_FLAG_CAN_MULTI_CONN)) {
dev_err(disk_to_dev(nbd->disk), "server does not support multiple connections per device.\n");
- error = -EINVAL;
- goto out_err;
+ return -EINVAL;
}
- set_bit(NBD_RUNNING, &nbd->runtime_flags);
- blk_mq_update_nr_hw_queues(&nbd->tag_set, nbd->num_connections);
- args = kcalloc(num_connections, sizeof(*args), GFP_KERNEL);
- if (!args) {
- error = -ENOMEM;
- goto out_err;
- }
+ blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections);
nbd->task_recv = current;
- mutex_unlock(&nbd->config_lock);
- nbd_parse_flags(nbd, bdev);
+ nbd_parse_flags(nbd);
error = device_create_file(disk_to_dev(nbd->disk), &pid_attr);
if (error) {
dev_err(disk_to_dev(nbd->disk), "device_create_file failed!\n");
- goto out_recv;
+ return error;
}
-
- nbd_size_update(nbd, bdev);
+ set_bit(NBD_HAS_PID_FILE, &config->runtime_flags);
nbd_dev_dbg_init(nbd);
for (i = 0; i < num_connections; i++) {
- sk_set_memalloc(nbd->socks[i]->sock->sk);
- atomic_inc(&nbd->recv_threads);
- INIT_WORK(&args[i].work, recv_work);
- args[i].nbd = nbd;
- args[i].index = i;
- queue_work(recv_workqueue, &args[i].work);
- }
- wait_event_interruptible(nbd->recv_wq,
- atomic_read(&nbd->recv_threads) == 0);
- for (i = 0; i < num_connections; i++)
- flush_work(&args[i].work);
- nbd_dev_dbg_close(nbd);
- nbd_size_clear(nbd, bdev);
- device_remove_file(disk_to_dev(nbd->disk), &pid_attr);
-out_recv:
- mutex_lock(&nbd->config_lock);
- nbd->task_recv = NULL;
-out_err:
- clear_bit(NBD_RUNNING, &nbd->runtime_flags);
- nbd_clear_sock(nbd, bdev);
+ struct recv_thread_args *args;
+ args = kzalloc(sizeof(*args), GFP_KERNEL);
+ if (!args) {
+ sock_shutdown(nbd);
+ return -ENOMEM;
+ }
+ sk_set_memalloc(config->socks[i]->sock->sk);
+ atomic_inc(&config->recv_threads);
+ refcount_inc(&nbd->config_refs);
+ INIT_WORK(&args->work, recv_work);
+ args->nbd = nbd;
+ args->index = i;
+ queue_work(recv_workqueue, &args->work);
+ }
+ return error;
+}
+
+static int nbd_start_device_ioctl(struct nbd_device *nbd, struct block_device *bdev)
+{
+ struct nbd_config *config = nbd->config;
+ int ret;
+
+ ret = nbd_start_device(nbd);
+ if (ret)
+ return ret;
+
+ bd_set_size(bdev, config->bytesize);
+ if (max_part)
+ bdev->bd_invalidated = 1;
+ mutex_unlock(&nbd->config_lock);
+ ret = wait_event_interruptible(config->recv_wq,
+ atomic_read(&config->recv_threads) == 0);
+ if (ret)
+ sock_shutdown(nbd);
+ mutex_lock(&nbd->config_lock);
+ bd_set_size(bdev, 0);
/* user requested, ignore socket errors */
- if (test_bit(NBD_DISCONNECT_REQUESTED, &nbd->runtime_flags))
- error = 0;
- if (test_bit(NBD_TIMEDOUT, &nbd->runtime_flags))
- error = -ETIMEDOUT;
+ if (test_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags))
+ ret = 0;
+ if (test_bit(NBD_TIMEDOUT, &config->runtime_flags))
+ ret = -ETIMEDOUT;
+ return ret;
+}
- nbd_reset(nbd);
- return error;
+static void nbd_clear_sock_ioctl(struct nbd_device *nbd,
+ struct block_device *bdev)
+{
+ sock_shutdown(nbd);
+ kill_bdev(bdev);
+ nbd_bdev_reset(bdev);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
}
/* Must be called with config_lock held */
static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
unsigned int cmd, unsigned long arg)
{
+ struct nbd_config *config = nbd->config;
+
switch (cmd) {
case NBD_DISCONNECT:
- return nbd_disconnect(nbd, bdev);
+ return nbd_disconnect(nbd);
case NBD_CLEAR_SOCK:
- return nbd_clear_sock(nbd, bdev);
+ nbd_clear_sock_ioctl(nbd, bdev);
+ return 0;
case NBD_SET_SOCK:
- return nbd_add_socket(nbd, bdev, arg);
+ return nbd_add_socket(nbd, arg, false);
case NBD_SET_BLKSIZE:
- nbd_size_set(nbd, bdev, arg,
- div_s64(nbd->bytesize, arg));
+ nbd_size_set(nbd, arg,
+ div_s64(config->bytesize, arg));
return 0;
case NBD_SET_SIZE:
- nbd_size_set(nbd, bdev, nbd->blksize,
- div_s64(arg, nbd->blksize));
+ nbd_size_set(nbd, config->blksize,
+ div_s64(arg, config->blksize));
return 0;
case NBD_SET_SIZE_BLOCKS:
- nbd_size_set(nbd, bdev, nbd->blksize, arg);
+ nbd_size_set(nbd, config->blksize, arg);
return 0;
case NBD_SET_TIMEOUT:
if (arg) {
@@ -855,10 +1155,10 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
return 0;
case NBD_SET_FLAGS:
- nbd->flags = arg;
+ config->flags = arg;
return 0;
case NBD_DO_IT:
- return nbd_start_device(nbd, bdev);
+ return nbd_start_device_ioctl(nbd, bdev);
case NBD_CLEAR_QUE:
/*
* This is for compatibility only. The queue is always cleared
@@ -879,23 +1179,92 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
unsigned int cmd, unsigned long arg)
{
struct nbd_device *nbd = bdev->bd_disk->private_data;
- int error;
+ struct nbd_config *config = nbd->config;
+ int error = -EINVAL;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- BUG_ON(nbd->magic != NBD_MAGIC);
-
mutex_lock(&nbd->config_lock);
- error = __nbd_ioctl(bdev, nbd, cmd, arg);
- mutex_unlock(&nbd->config_lock);
+ /* Don't allow ioctl operations on a nbd device that was created with
+ * netlink, unless it's DISCONNECT or CLEAR_SOCK, which are fine.
+ */
+ if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+ (cmd == NBD_DISCONNECT || cmd == NBD_CLEAR_SOCK))
+ error = __nbd_ioctl(bdev, nbd, cmd, arg);
+ else
+ dev_err(nbd_to_dev(nbd), "Cannot use ioctl interface on a netlink controlled device.\n");
+ mutex_unlock(&nbd->config_lock);
return error;
}
+static struct nbd_config *nbd_alloc_config(void)
+{
+ struct nbd_config *config;
+
+ config = kzalloc(sizeof(struct nbd_config), GFP_NOFS);
+ if (!config)
+ return NULL;
+ atomic_set(&config->recv_threads, 0);
+ init_waitqueue_head(&config->recv_wq);
+ init_waitqueue_head(&config->conn_wait);
+ config->blksize = 1024;
+ atomic_set(&config->live_connections, 0);
+ try_module_get(THIS_MODULE);
+ return config;
+}
+
+static int nbd_open(struct block_device *bdev, fmode_t mode)
+{
+ struct nbd_device *nbd;
+ int ret = 0;
+
+ mutex_lock(&nbd_index_mutex);
+ nbd = bdev->bd_disk->private_data;
+ if (!nbd) {
+ ret = -ENXIO;
+ goto out;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ ret = -ENXIO;
+ goto out;
+ }
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ struct nbd_config *config;
+
+ mutex_lock(&nbd->config_lock);
+ if (refcount_inc_not_zero(&nbd->config_refs)) {
+ mutex_unlock(&nbd->config_lock);
+ goto out;
+ }
+ config = nbd->config = nbd_alloc_config();
+ if (!config) {
+ ret = -ENOMEM;
+ mutex_unlock(&nbd->config_lock);
+ goto out;
+ }
+ refcount_set(&nbd->config_refs, 1);
+ refcount_inc(&nbd->refs);
+ mutex_unlock(&nbd->config_lock);
+ }
+out:
+ mutex_unlock(&nbd_index_mutex);
+ return ret;
+}
+
+static void nbd_release(struct gendisk *disk, fmode_t mode)
+{
+ struct nbd_device *nbd = disk->private_data;
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+}
+
static const struct block_device_operations nbd_fops =
{
.owner = THIS_MODULE,
+ .open = nbd_open,
+ .release = nbd_release,
.ioctl = nbd_ioctl,
.compat_ioctl = nbd_ioctl,
};
@@ -927,7 +1296,7 @@ static const struct file_operations nbd_dbg_tasks_ops = {
static int nbd_dbg_flags_show(struct seq_file *s, void *unused)
{
struct nbd_device *nbd = s->private;
- u32 flags = nbd->flags;
+ u32 flags = nbd->config->flags;
seq_printf(s, "Hex: 0x%08x\n\n", flags);
@@ -960,6 +1329,7 @@ static const struct file_operations nbd_dbg_flags_ops = {
static int nbd_dev_dbg_init(struct nbd_device *nbd)
{
struct dentry *dir;
+ struct nbd_config *config = nbd->config;
if (!nbd_dbg_dir)
return -EIO;
@@ -970,12 +1340,12 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
nbd_name(nbd));
return -EIO;
}
- nbd->dbg_dir = dir;
+ config->dbg_dir = dir;
debugfs_create_file("tasks", 0444, dir, nbd, &nbd_dbg_tasks_ops);
- debugfs_create_u64("size_bytes", 0444, dir, &nbd->bytesize);
+ debugfs_create_u64("size_bytes", 0444, dir, &config->bytesize);
debugfs_create_u32("timeout", 0444, dir, &nbd->tag_set.timeout);
- debugfs_create_u64("blocksize", 0444, dir, &nbd->blksize);
+ debugfs_create_u64("blocksize", 0444, dir, &config->blksize);
debugfs_create_file("flags", 0444, dir, nbd, &nbd_dbg_flags_ops);
return 0;
@@ -983,7 +1353,7 @@ static int nbd_dev_dbg_init(struct nbd_device *nbd)
static void nbd_dev_dbg_close(struct nbd_device *nbd)
{
- debugfs_remove_recursive(nbd->dbg_dir);
+ debugfs_remove_recursive(nbd->config->dbg_dir);
}
static int nbd_dbg_init(void)
@@ -1035,25 +1405,13 @@ static int nbd_init_request(void *data, struct request *rq,
return 0;
}
-static struct blk_mq_ops nbd_mq_ops = {
+static const struct blk_mq_ops nbd_mq_ops = {
.queue_rq = nbd_queue_rq,
+ .complete = nbd_complete_rq,
.init_request = nbd_init_request,
.timeout = nbd_xmit_timeout,
};
-static void nbd_dev_remove(struct nbd_device *nbd)
-{
- struct gendisk *disk = nbd->disk;
- nbd->magic = 0;
- if (disk) {
- del_gendisk(disk);
- blk_cleanup_queue(disk->queue);
- blk_mq_free_tag_set(&nbd->tag_set);
- put_disk(disk);
- }
- kfree(nbd);
-}
-
static int nbd_dev_add(int index)
{
struct nbd_device *nbd;
@@ -1082,6 +1440,7 @@ static int nbd_dev_add(int index)
if (err < 0)
goto out_free_disk;
+ nbd->index = index;
nbd->disk = disk;
nbd->tag_set.ops = &nbd_mq_ops;
nbd->tag_set.nr_hw_queues = 1;
@@ -1110,20 +1469,23 @@ static int nbd_dev_add(int index)
queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, disk->queue);
disk->queue->limits.discard_granularity = 512;
blk_queue_max_discard_sectors(disk->queue, UINT_MAX);
- disk->queue->limits.discard_zeroes_data = 0;
+ blk_queue_max_segment_size(disk->queue, UINT_MAX);
+ blk_queue_max_segments(disk->queue, USHRT_MAX);
blk_queue_max_hw_sectors(disk->queue, 65536);
disk->queue->limits.max_sectors = 256;
- nbd->magic = NBD_MAGIC;
mutex_init(&nbd->config_lock);
+ refcount_set(&nbd->config_refs, 0);
+ refcount_set(&nbd->refs, 1);
+ INIT_LIST_HEAD(&nbd->list);
disk->major = NBD_MAJOR;
disk->first_minor = index << part_shift;
disk->fops = &nbd_fops;
disk->private_data = nbd;
sprintf(disk->disk_name, "nbd%d", index);
- init_waitqueue_head(&nbd->recv_wq);
nbd_reset(nbd);
add_disk(disk);
+ nbd_total_devices++;
return index;
out_free_tags:
@@ -1138,10 +1500,535 @@ out:
return err;
}
-/*
- * And here should be modules and kernel interface
- * (Just smiley confuses emacs :-)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+ struct nbd_device *nbd = ptr;
+ struct nbd_device **found = data;
+
+ if (!refcount_read(&nbd->config_refs)) {
+ *found = nbd;
+ return 1;
+ }
+ return 0;
+}
+
+/* Netlink interface. */
+static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+ [NBD_ATTR_INDEX] = { .type = NLA_U32 },
+ [NBD_ATTR_SIZE_BYTES] = { .type = NLA_U64 },
+ [NBD_ATTR_BLOCK_SIZE_BYTES] = { .type = NLA_U64 },
+ [NBD_ATTR_TIMEOUT] = { .type = NLA_U64 },
+ [NBD_ATTR_SERVER_FLAGS] = { .type = NLA_U64 },
+ [NBD_ATTR_CLIENT_FLAGS] = { .type = NLA_U64 },
+ [NBD_ATTR_SOCKETS] = { .type = NLA_NESTED},
+ [NBD_ATTR_DEAD_CONN_TIMEOUT] = { .type = NLA_U64 },
+ [NBD_ATTR_DEVICE_LIST] = { .type = NLA_NESTED},
+};
+
+static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+ [NBD_SOCK_FD] = { .type = NLA_U32 },
+};
+
+/* We don't use this right now since we don't parse the incoming list, but we
+ * still want it here so userspace knows what to expect.
*/
+static struct nla_policy __attribute__((unused))
+nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
+ [NBD_DEVICE_INDEX] = { .type = NLA_U32 },
+ [NBD_DEVICE_CONNECTED] = { .type = NLA_U8 },
+};
+
+static int nbd_genl_connect(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd = NULL;
+ struct nbd_config *config;
+ int index = -1;
+ int ret;
+ bool put_dev = false;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (info->attrs[NBD_ATTR_INDEX])
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ if (!info->attrs[NBD_ATTR_SOCKETS]) {
+ printk(KERN_ERR "nbd: must specify at least one socket\n");
+ return -EINVAL;
+ }
+ if (!info->attrs[NBD_ATTR_SIZE_BYTES]) {
+ printk(KERN_ERR "nbd: must specify a size in bytes for the device\n");
+ return -EINVAL;
+ }
+again:
+ mutex_lock(&nbd_index_mutex);
+ if (index == -1) {
+ ret = idr_for_each(&nbd_index_idr, &find_free_cb, &nbd);
+ if (ret == 0) {
+ int new_index;
+ new_index = nbd_dev_add(-1);
+ if (new_index < 0) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: failed to add new device\n");
+ return ret;
+ }
+ nbd = idr_find(&nbd_index_idr, new_index);
+ }
+ } else {
+ nbd = idr_find(&nbd_index_idr, index);
+ }
+ if (!nbd) {
+ printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+ index);
+ mutex_unlock(&nbd_index_mutex);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ if (index == -1)
+ goto again;
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+
+ mutex_lock(&nbd->config_lock);
+ if (refcount_read(&nbd->config_refs)) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ if (index == -1)
+ goto again;
+ printk(KERN_ERR "nbd: nbd%d already in use\n", index);
+ return -EBUSY;
+ }
+ if (WARN_ON(nbd->config)) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ return -EINVAL;
+ }
+ config = nbd->config = nbd_alloc_config();
+ if (!nbd->config) {
+ mutex_unlock(&nbd->config_lock);
+ nbd_put(nbd);
+ printk(KERN_ERR "nbd: couldn't allocate config\n");
+ return -ENOMEM;
+ }
+ refcount_set(&nbd->config_refs, 1);
+ set_bit(NBD_BOUND, &config->runtime_flags);
+
+ if (info->attrs[NBD_ATTR_SIZE_BYTES]) {
+ u64 bytes = nla_get_u64(info->attrs[NBD_ATTR_SIZE_BYTES]);
+ nbd_size_set(nbd, config->blksize,
+ div64_u64(bytes, config->blksize));
+ }
+ if (info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]) {
+ u64 bsize =
+ nla_get_u64(info->attrs[NBD_ATTR_BLOCK_SIZE_BYTES]);
+ nbd_size_set(nbd, bsize, div64_u64(config->bytesize, bsize));
+ }
+ if (info->attrs[NBD_ATTR_TIMEOUT]) {
+ u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+ nbd->tag_set.timeout = timeout * HZ;
+ blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+ }
+ if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+ config->dead_conn_timeout =
+ nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+ config->dead_conn_timeout *= HZ;
+ }
+ if (info->attrs[NBD_ATTR_SERVER_FLAGS])
+ config->flags =
+ nla_get_u64(info->attrs[NBD_ATTR_SERVER_FLAGS]);
+ if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+ u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+ if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+ set_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags);
+ put_dev = true;
+ }
+ }
+
+ if (info->attrs[NBD_ATTR_SOCKETS]) {
+ struct nlattr *attr;
+ int rem, fd;
+
+ nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+ rem) {
+ struct nlattr *socks[NBD_SOCK_MAX+1];
+
+ if (nla_type(attr) != NBD_SOCK_ITEM) {
+ printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+ nbd_sock_policy);
+ if (ret != 0) {
+ printk(KERN_ERR "nbd: error processing sock list\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!socks[NBD_SOCK_FD])
+ continue;
+ fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+ ret = nbd_add_socket(nbd, fd, true);
+ if (ret)
+ goto out;
+ }
+ }
+ ret = nbd_start_device(nbd);
+out:
+ mutex_unlock(&nbd->config_lock);
+ if (!ret) {
+ set_bit(NBD_HAS_CONFIG_REF, &config->runtime_flags);
+ refcount_inc(&nbd->config_refs);
+ nbd_connect_reply(info, nbd->index);
+ }
+ nbd_config_put(nbd);
+ if (put_dev)
+ nbd_put(nbd);
+ return ret;
+}
+
+static int nbd_genl_disconnect(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd;
+ int index;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!info->attrs[NBD_ATTR_INDEX]) {
+ printk(KERN_ERR "nbd: must specify an index to disconnect\n");
+ return -EINVAL;
+ }
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ mutex_lock(&nbd_index_mutex);
+ nbd = idr_find(&nbd_index_idr, index);
+ if (!nbd) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: couldn't find device at index %d\n",
+ index);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ nbd_put(nbd);
+ return 0;
+ }
+ mutex_lock(&nbd->config_lock);
+ nbd_disconnect(nbd);
+ mutex_unlock(&nbd->config_lock);
+ if (test_and_clear_bit(NBD_HAS_CONFIG_REF,
+ &nbd->config->runtime_flags))
+ nbd_config_put(nbd);
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+ return 0;
+}
+
+static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nbd_device *nbd = NULL;
+ struct nbd_config *config;
+ int index;
+ int ret = -EINVAL;
+ bool put_dev = false;
+
+ if (!netlink_capable(skb, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (!info->attrs[NBD_ATTR_INDEX]) {
+ printk(KERN_ERR "nbd: must specify a device to reconfigure\n");
+ return -EINVAL;
+ }
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+ mutex_lock(&nbd_index_mutex);
+ nbd = idr_find(&nbd_index_idr, index);
+ if (!nbd) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: couldn't find a device at index %d\n",
+ index);
+ return -EINVAL;
+ }
+ if (!refcount_inc_not_zero(&nbd->refs)) {
+ mutex_unlock(&nbd_index_mutex);
+ printk(KERN_ERR "nbd: device at index %d is going down\n",
+ index);
+ return -EINVAL;
+ }
+ mutex_unlock(&nbd_index_mutex);
+
+ if (!refcount_inc_not_zero(&nbd->config_refs)) {
+ dev_err(nbd_to_dev(nbd),
+ "not configured, cannot reconfigure\n");
+ nbd_put(nbd);
+ return -EINVAL;
+ }
+
+ mutex_lock(&nbd->config_lock);
+ config = nbd->config;
+ if (!test_bit(NBD_BOUND, &config->runtime_flags) ||
+ !nbd->task_recv) {
+ dev_err(nbd_to_dev(nbd),
+ "not configured, cannot reconfigure\n");
+ goto out;
+ }
+
+ if (info->attrs[NBD_ATTR_TIMEOUT]) {
+ u64 timeout = nla_get_u64(info->attrs[NBD_ATTR_TIMEOUT]);
+ nbd->tag_set.timeout = timeout * HZ;
+ blk_queue_rq_timeout(nbd->disk->queue, timeout * HZ);
+ }
+ if (info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]) {
+ config->dead_conn_timeout =
+ nla_get_u64(info->attrs[NBD_ATTR_DEAD_CONN_TIMEOUT]);
+ config->dead_conn_timeout *= HZ;
+ }
+ if (info->attrs[NBD_ATTR_CLIENT_FLAGS]) {
+ u64 flags = nla_get_u64(info->attrs[NBD_ATTR_CLIENT_FLAGS]);
+ if (flags & NBD_CFLAG_DESTROY_ON_DISCONNECT) {
+ if (!test_and_set_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags))
+ put_dev = true;
+ } else {
+ if (test_and_clear_bit(NBD_DESTROY_ON_DISCONNECT,
+ &config->runtime_flags))
+ refcount_inc(&nbd->refs);
+ }
+ }
+
+ if (info->attrs[NBD_ATTR_SOCKETS]) {
+ struct nlattr *attr;
+ int rem, fd;
+
+ nla_for_each_nested(attr, info->attrs[NBD_ATTR_SOCKETS],
+ rem) {
+ struct nlattr *socks[NBD_SOCK_MAX+1];
+
+ if (nla_type(attr) != NBD_SOCK_ITEM) {
+ printk(KERN_ERR "nbd: socks must be embedded in a SOCK_ITEM attr\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ ret = nla_parse_nested(socks, NBD_SOCK_MAX, attr,
+ nbd_sock_policy);
+ if (ret != 0) {
+ printk(KERN_ERR "nbd: error processing sock list\n");
+ ret = -EINVAL;
+ goto out;
+ }
+ if (!socks[NBD_SOCK_FD])
+ continue;
+ fd = (int)nla_get_u32(socks[NBD_SOCK_FD]);
+ ret = nbd_reconnect_socket(nbd, fd);
+ if (ret) {
+ if (ret == -ENOSPC)
+ ret = 0;
+ goto out;
+ }
+ dev_info(nbd_to_dev(nbd), "reconnected socket\n");
+ }
+ }
+out:
+ mutex_unlock(&nbd->config_lock);
+ nbd_config_put(nbd);
+ nbd_put(nbd);
+ if (put_dev)
+ nbd_put(nbd);
+ return ret;
+}
+
+static const struct genl_ops nbd_connect_genl_ops[] = {
+ {
+ .cmd = NBD_CMD_CONNECT,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_connect,
+ },
+ {
+ .cmd = NBD_CMD_DISCONNECT,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_disconnect,
+ },
+ {
+ .cmd = NBD_CMD_RECONFIGURE,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_reconfigure,
+ },
+ {
+ .cmd = NBD_CMD_STATUS,
+ .policy = nbd_attr_policy,
+ .doit = nbd_genl_status,
+ },
+};
+
+static const struct genl_multicast_group nbd_mcast_grps[] = {
+ { .name = NBD_GENL_MCAST_GROUP_NAME, },
+};
+
+static struct genl_family nbd_genl_family __ro_after_init = {
+ .hdrsize = 0,
+ .name = NBD_GENL_FAMILY_NAME,
+ .version = NBD_GENL_VERSION,
+ .module = THIS_MODULE,
+ .ops = nbd_connect_genl_ops,
+ .n_ops = ARRAY_SIZE(nbd_connect_genl_ops),
+ .maxattr = NBD_ATTR_MAX,
+ .mcgrps = nbd_mcast_grps,
+ .n_mcgrps = ARRAY_SIZE(nbd_mcast_grps),
+};
+
+static int populate_nbd_status(struct nbd_device *nbd, struct sk_buff *reply)
+{
+ struct nlattr *dev_opt;
+ u8 connected = 0;
+ int ret;
+
+ /* This is a little racey, but for status it's ok. The
+ * reason we don't take a ref here is because we can't
+ * take a ref in the index == -1 case as we would need
+ * to put under the nbd_index_mutex, which could
+ * deadlock if we are configured to remove ourselves
+ * once we're disconnected.
+ */
+ if (refcount_read(&nbd->config_refs))
+ connected = 1;
+ dev_opt = nla_nest_start(reply, NBD_DEVICE_ITEM);
+ if (!dev_opt)
+ return -EMSGSIZE;
+ ret = nla_put_u32(reply, NBD_DEVICE_INDEX, nbd->index);
+ if (ret)
+ return -EMSGSIZE;
+ ret = nla_put_u8(reply, NBD_DEVICE_CONNECTED,
+ connected);
+ if (ret)
+ return -EMSGSIZE;
+ nla_nest_end(reply, dev_opt);
+ return 0;
+}
+
+static int status_cb(int id, void *ptr, void *data)
+{
+ struct nbd_device *nbd = ptr;
+ return populate_nbd_status(nbd, (struct sk_buff *)data);
+}
+
+static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info)
+{
+ struct nlattr *dev_list;
+ struct sk_buff *reply;
+ void *reply_head;
+ size_t msg_size;
+ int index = -1;
+ int ret = -ENOMEM;
+
+ if (info->attrs[NBD_ATTR_INDEX])
+ index = nla_get_u32(info->attrs[NBD_ATTR_INDEX]);
+
+ mutex_lock(&nbd_index_mutex);
+
+ msg_size = nla_total_size(nla_attr_size(sizeof(u32)) +
+ nla_attr_size(sizeof(u8)));
+ msg_size *= (index == -1) ? nbd_total_devices : 1;
+
+ reply = genlmsg_new(msg_size, GFP_KERNEL);
+ if (!reply)
+ goto out;
+ reply_head = genlmsg_put_reply(reply, info, &nbd_genl_family, 0,
+ NBD_CMD_STATUS);
+ if (!reply_head) {
+ nlmsg_free(reply);
+ goto out;
+ }
+
+ dev_list = nla_nest_start(reply, NBD_ATTR_DEVICE_LIST);
+ if (index == -1) {
+ ret = idr_for_each(&nbd_index_idr, &status_cb, reply);
+ if (ret) {
+ nlmsg_free(reply);
+ goto out;
+ }
+ } else {
+ struct nbd_device *nbd;
+ nbd = idr_find(&nbd_index_idr, index);
+ if (nbd) {
+ ret = populate_nbd_status(nbd, reply);
+ if (ret) {
+ nlmsg_free(reply);
+ goto out;
+ }
+ }
+ }
+ nla_nest_end(reply, dev_list);
+ genlmsg_end(reply, reply_head);
+ genlmsg_reply(reply, info);
+ ret = 0;
+out:
+ mutex_unlock(&nbd_index_mutex);
+ return ret;
+}
+
+static void nbd_connect_reply(struct genl_info *info, int index)
+{
+ struct sk_buff *skb;
+ void *msg_head;
+ int ret;
+
+ skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+ if (!skb)
+ return;
+ msg_head = genlmsg_put_reply(skb, info, &nbd_genl_family, 0,
+ NBD_CMD_CONNECT);
+ if (!msg_head) {
+ nlmsg_free(skb);
+ return;
+ }
+ ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+ if (ret) {
+ nlmsg_free(skb);
+ return;
+ }
+ genlmsg_end(skb, msg_head);
+ genlmsg_reply(skb, info);
+}
+
+static void nbd_mcast_index(int index)
+{
+ struct sk_buff *skb;
+ void *msg_head;
+ int ret;
+
+ skb = genlmsg_new(nla_total_size(sizeof(u32)), GFP_KERNEL);
+ if (!skb)
+ return;
+ msg_head = genlmsg_put(skb, 0, 0, &nbd_genl_family, 0,
+ NBD_CMD_LINK_DEAD);
+ if (!msg_head) {
+ nlmsg_free(skb);
+ return;
+ }
+ ret = nla_put_u32(skb, NBD_ATTR_INDEX, index);
+ if (ret) {
+ nlmsg_free(skb);
+ return;
+ }
+ genlmsg_end(skb, msg_head);
+ genlmsg_multicast(&nbd_genl_family, skb, 0, 0, GFP_KERNEL);
+}
+
+static void nbd_dead_link_work(struct work_struct *work)
+{
+ struct link_dead_args *args = container_of(work, struct link_dead_args,
+ work);
+ nbd_mcast_index(args->index);
+ kfree(args);
+}
static int __init nbd_init(void)
{
@@ -1184,6 +2071,11 @@ static int __init nbd_init(void)
return -EIO;
}
+ if (genl_register_family(&nbd_genl_family)) {
+ unregister_blkdev(NBD_MAJOR, "nbd");
+ destroy_workqueue(recv_workqueue);
+ return -EINVAL;
+ }
nbd_dbg_init();
mutex_lock(&nbd_index_mutex);
@@ -1195,17 +2087,34 @@ static int __init nbd_init(void)
static int nbd_exit_cb(int id, void *ptr, void *data)
{
+ struct list_head *list = (struct list_head *)data;
struct nbd_device *nbd = ptr;
- nbd_dev_remove(nbd);
+
+ list_add_tail(&nbd->list, list);
return 0;
}
static void __exit nbd_cleanup(void)
{
+ struct nbd_device *nbd;
+ LIST_HEAD(del_list);
+
nbd_dbg_close();
- idr_for_each(&nbd_index_idr, &nbd_exit_cb, NULL);
+ mutex_lock(&nbd_index_mutex);
+ idr_for_each(&nbd_index_idr, &nbd_exit_cb, &del_list);
+ mutex_unlock(&nbd_index_mutex);
+
+ while (!list_empty(&del_list)) {
+ nbd = list_first_entry(&del_list, struct nbd_device, list);
+ list_del_init(&nbd->list);
+ if (refcount_read(&nbd->refs) != 1)
+ printk(KERN_ERR "nbd: possibly leaking a device\n");
+ nbd_put(nbd);
+ }
+
idr_destroy(&nbd_index_idr);
+ genl_unregister_family(&nbd_genl_family);
destroy_workqueue(recv_workqueue);
unregister_blkdev(NBD_MAJOR, "nbd");
}
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 6f2e565bccc5..d946e1eeac8e 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -117,6 +117,10 @@ static bool use_lightnvm;
module_param(use_lightnvm, bool, S_IRUGO);
MODULE_PARM_DESC(use_lightnvm, "Register as a LightNVM device");
+static bool blocking;
+module_param(blocking, bool, S_IRUGO);
+MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+
static int irqmode = NULL_IRQ_SOFTIRQ;
static int null_set_irqmode(const char *str, const struct kernel_param *kp)
@@ -277,7 +281,7 @@ static inline void null_handle_cmd(struct nullb_cmd *cmd)
case NULL_IRQ_SOFTIRQ:
switch (queue_mode) {
case NULL_Q_MQ:
- blk_mq_complete_request(cmd->rq, cmd->rq->errors);
+ blk_mq_complete_request(cmd->rq);
break;
case NULL_Q_RQ:
blk_complete_request(cmd->rq);
@@ -357,6 +361,8 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx,
{
struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+ might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
if (irqmode == NULL_IRQ_TIMER) {
hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cmd->timer.function = null_cmd_timer_expired;
@@ -392,7 +398,7 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
return 0;
}
-static struct blk_mq_ops null_mq_ops = {
+static const struct blk_mq_ops null_mq_ops = {
.queue_rq = null_queue_rq,
.init_hctx = null_init_hctx,
.complete = null_softirq_done_fn,
@@ -437,14 +443,7 @@ static int null_lnvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
if (IS_ERR(rq))
return -ENOMEM;
- rq->__sector = bio->bi_iter.bi_sector;
- rq->ioprio = bio_prio(bio);
-
- if (bio_has_data(bio))
- rq->nr_phys_segments = bio_phys_segments(q, bio);
-
- rq->__data_len = bio->bi_iter.bi_size;
- rq->bio = rq->biotail = bio;
+ blk_init_request_from_bio(rq, bio);
rq->end_io_data = rqd;
@@ -724,6 +723,9 @@ static int null_add_dev(void)
nullb->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
nullb->tag_set.driver_data = nullb;
+ if (blocking)
+ nullb->tag_set.flags |= BLK_MQ_F_BLOCKING;
+
rv = blk_mq_alloc_tag_set(&nullb->tag_set);
if (rv)
goto out_cleanup_queues;
diff --git a/drivers/block/osdblk.c b/drivers/block/osdblk.c
deleted file mode 100644
index 8127b8201a01..000000000000
--- a/drivers/block/osdblk.c
+++ /dev/null
@@ -1,693 +0,0 @@
-
-/*
- osdblk.c -- Export a single SCSI OSD object as a Linux block device
-
-
- Copyright 2009 Red Hat, Inc.
-
- This program is free software; you can redistribute it and/or modify
- it under the terms of the GNU General Public License as published by
- the Free Software Foundation.
-
- This program is distributed in the hope that 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.
-
- You should have received a copy of the GNU General Public License
- along with this program; see the file COPYING. If not, write to
- the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
-
-
- Instructions for use
- --------------------
-
- 1) Map a Linux block device to an existing OSD object.
-
- In this example, we will use partition id 1234, object id 5678,
- OSD device /dev/osd1.
-
- $ echo "1234 5678 /dev/osd1" > /sys/class/osdblk/add
-
-
- 2) List all active blkdev<->object mappings.
-
- In this example, we have performed step #1 twice, creating two blkdevs,
- mapped to two separate OSD objects.
-
- $ cat /sys/class/osdblk/list
- 0 174 1234 5678 /dev/osd1
- 1 179 1994 897123 /dev/osd0
-
- The columns, in order, are:
- - blkdev unique id
- - blkdev assigned major
- - OSD object partition id
- - OSD object id
- - OSD device
-
-
- 3) Remove an active blkdev<->object mapping.
-
- In this example, we remove the mapping with blkdev unique id 1.
-
- $ echo 1 > /sys/class/osdblk/remove
-
-
- NOTE: The actual creation and deletion of OSD objects is outside the scope
- of this driver.
-
- */
-
-#include <linux/kernel.h>
-#include <linux/device.h>
-#include <linux/module.h>
-#include <linux/fs.h>
-#include <linux/slab.h>
-#include <scsi/osd_initiator.h>
-#include <scsi/osd_attributes.h>
-#include <scsi/osd_sec.h>
-#include <scsi/scsi_device.h>
-
-#define DRV_NAME "osdblk"
-#define PFX DRV_NAME ": "
-
-/* #define _OSDBLK_DEBUG */
-#ifdef _OSDBLK_DEBUG
-#define OSDBLK_DEBUG(fmt, a...) \
- printk(KERN_NOTICE "osdblk @%s:%d: " fmt, __func__, __LINE__, ##a)
-#else
-#define OSDBLK_DEBUG(fmt, a...) \
- do { if (0) printk(fmt, ##a); } while (0)
-#endif
-
-MODULE_AUTHOR("Jeff Garzik <jeff@garzik.org>");
-MODULE_DESCRIPTION("block device inside an OSD object osdblk.ko");
-MODULE_LICENSE("GPL");
-
-struct osdblk_device;
-
-enum {
- OSDBLK_MINORS_PER_MAJOR = 256, /* max minors per blkdev */
- OSDBLK_MAX_REQ = 32, /* max parallel requests */
- OSDBLK_OP_TIMEOUT = 4 * 60, /* sync OSD req timeout */
-};
-
-struct osdblk_request {
- struct request *rq; /* blk layer request */
- struct bio *bio; /* cloned bio */
- struct osdblk_device *osdev; /* associated blkdev */
-};
-
-struct osdblk_device {
- int id; /* blkdev unique id */
-
- int major; /* blkdev assigned major */
- struct gendisk *disk; /* blkdev's gendisk and rq */
- struct request_queue *q;
-
- struct osd_dev *osd; /* associated OSD */
-
- char name[32]; /* blkdev name, e.g. osdblk34 */
-
- spinlock_t lock; /* queue lock */
-
- struct osd_obj_id obj; /* OSD partition, obj id */
- uint8_t obj_cred[OSD_CAP_LEN]; /* OSD cred */
-
- struct osdblk_request req[OSDBLK_MAX_REQ]; /* request table */
-
- struct list_head node;
-
- char osd_path[0]; /* OSD device path */
-};
-
-static struct class *class_osdblk; /* /sys/class/osdblk */
-static DEFINE_MUTEX(ctl_mutex); /* Serialize open/close/setup/teardown */
-static LIST_HEAD(osdblkdev_list);
-
-static const struct block_device_operations osdblk_bd_ops = {
- .owner = THIS_MODULE,
-};
-
-static const struct osd_attr g_attr_logical_length = ATTR_DEF(
- OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
-
-static void osdblk_make_credential(u8 cred_a[OSD_CAP_LEN],
- const struct osd_obj_id *obj)
-{
- osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
-}
-
-/* copied from exofs; move to libosd? */
-/*
- * Perform a synchronous OSD operation. copied from exofs; move to libosd?
- */
-static int osd_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
-{
- int ret;
-
- or->timeout = timeout;
- ret = osd_finalize_request(or, 0, credential, NULL);
- if (ret)
- return ret;
-
- ret = osd_execute_request(or);
-
- /* osd_req_decode_sense(or, ret); */
- return ret;
-}
-
-/*
- * Perform an asynchronous OSD operation. copied from exofs; move to libosd?
- */
-static int osd_async_op(struct osd_request *or, osd_req_done_fn *async_done,
- void *caller_context, u8 *cred)
-{
- int ret;
-
- ret = osd_finalize_request(or, 0, cred, NULL);
- if (ret)
- return ret;
-
- ret = osd_execute_request_async(or, async_done, caller_context);
-
- return ret;
-}
-
-/* copied from exofs; move to libosd? */
-static int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
-{
- struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
- void *iter = NULL;
- int nelem;
-
- do {
- nelem = 1;
- osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
- if ((cur_attr.attr_page == attr->attr_page) &&
- (cur_attr.attr_id == attr->attr_id)) {
- attr->len = cur_attr.len;
- attr->val_ptr = cur_attr.val_ptr;
- return 0;
- }
- } while (iter);
-
- return -EIO;
-}
-
-static int osdblk_get_obj_size(struct osdblk_device *osdev, u64 *size_out)
-{
- struct osd_request *or;
- struct osd_attr attr;
- int ret;
-
- /* start request */
- or = osd_start_request(osdev->osd, GFP_KERNEL);
- if (!or)
- return -ENOMEM;
-
- /* create a get-attributes(length) request */
- osd_req_get_attributes(or, &osdev->obj);
-
- osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
-
- /* execute op synchronously */
- ret = osd_sync_op(or, OSDBLK_OP_TIMEOUT, osdev->obj_cred);
- if (ret)
- goto out;
-
- /* extract length from returned attribute info */
- attr = g_attr_logical_length;
- ret = extract_attr_from_req(or, &attr);
- if (ret)
- goto out;
-
- *size_out = get_unaligned_be64(attr.val_ptr);
-
-out:
- osd_end_request(or);
- return ret;
-
-}
-
-static void osdblk_osd_complete(struct osd_request *or, void *private)
-{
- struct osdblk_request *orq = private;
- struct osd_sense_info osi;
- int ret = osd_req_decode_sense(or, &osi);
-
- if (ret) {
- ret = -EIO;
- OSDBLK_DEBUG("osdblk_osd_complete with err=%d\n", ret);
- }
-
- /* complete OSD request */
- osd_end_request(or);
-
- /* complete request passed to osdblk by block layer */
- __blk_end_request_all(orq->rq, ret);
-}
-
-static void bio_chain_put(struct bio *chain)
-{
- struct bio *tmp;
-
- while (chain) {
- tmp = chain;
- chain = chain->bi_next;
-
- bio_put(tmp);
- }
-}
-
-static struct bio *bio_chain_clone(struct bio *old_chain, gfp_t gfpmask)
-{
- struct bio *tmp, *new_chain = NULL, *tail = NULL;
-
- while (old_chain) {
- tmp = bio_clone_kmalloc(old_chain, gfpmask);
- if (!tmp)
- goto err_out;
-
- tmp->bi_bdev = NULL;
- gfpmask &= ~__GFP_DIRECT_RECLAIM;
- tmp->bi_next = NULL;
-
- if (!new_chain)
- new_chain = tail = tmp;
- else {
- tail->bi_next = tmp;
- tail = tmp;
- }
-
- old_chain = old_chain->bi_next;
- }
-
- return new_chain;
-
-err_out:
- OSDBLK_DEBUG("bio_chain_clone with err\n");
- bio_chain_put(new_chain);
- return NULL;
-}
-
-static void osdblk_rq_fn(struct request_queue *q)
-{
- struct osdblk_device *osdev = q->queuedata;
-
- while (1) {
- struct request *rq;
- struct osdblk_request *orq;
- struct osd_request *or;
- struct bio *bio;
- bool do_write, do_flush;
-
- /* peek at request from block layer */
- rq = blk_fetch_request(q);
- if (!rq)
- break;
-
- /* deduce our operation (read, write, flush) */
- /* I wish the block layer simplified cmd_type/cmd_flags/cmd[]
- * into a clearly defined set of RPC commands:
- * read, write, flush, scsi command, power mgmt req,
- * driver-specific, etc.
- */
-
- do_flush = (req_op(rq) == REQ_OP_FLUSH);
- do_write = (rq_data_dir(rq) == WRITE);
-
- if (!do_flush) { /* osd_flush does not use a bio */
- /* a bio clone to be passed down to OSD request */
- bio = bio_chain_clone(rq->bio, GFP_ATOMIC);
- if (!bio)
- break;
- } else
- bio = NULL;
-
- /* alloc internal OSD request, for OSD command execution */
- or = osd_start_request(osdev->osd, GFP_ATOMIC);
- if (!or) {
- bio_chain_put(bio);
- OSDBLK_DEBUG("osd_start_request with err\n");
- break;
- }
-
- orq = &osdev->req[rq->tag];
- orq->rq = rq;
- orq->bio = bio;
- orq->osdev = osdev;
-
- /* init OSD command: flush, write or read */
- if (do_flush)
- osd_req_flush_object(or, &osdev->obj,
- OSD_CDB_FLUSH_ALL, 0, 0);
- else if (do_write)
- osd_req_write(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
- bio, blk_rq_bytes(rq));
- else
- osd_req_read(or, &osdev->obj, blk_rq_pos(rq) * 512ULL,
- bio, blk_rq_bytes(rq));
-
- OSDBLK_DEBUG("%s 0x%x bytes at 0x%llx\n",
- do_flush ? "flush" : do_write ?
- "write" : "read", blk_rq_bytes(rq),
- blk_rq_pos(rq) * 512ULL);
-
- /* begin OSD command execution */
- if (osd_async_op(or, osdblk_osd_complete, orq,
- osdev->obj_cred)) {
- osd_end_request(or);
- blk_requeue_request(q, rq);
- bio_chain_put(bio);
- OSDBLK_DEBUG("osd_execute_request_async with err\n");
- break;
- }
-
- /* remove the special 'flush' marker, now that the command
- * is executing
- */
- rq->special = NULL;
- }
-}
-
-static void osdblk_free_disk(struct osdblk_device *osdev)
-{
- struct gendisk *disk = osdev->disk;
-
- if (!disk)
- return;
-
- if (disk->flags & GENHD_FL_UP)
- del_gendisk(disk);
- if (disk->queue)
- blk_cleanup_queue(disk->queue);
- put_disk(disk);
-}
-
-static int osdblk_init_disk(struct osdblk_device *osdev)
-{
- struct gendisk *disk;
- struct request_queue *q;
- int rc;
- u64 obj_size = 0;
-
- /* contact OSD, request size info about the object being mapped */
- rc = osdblk_get_obj_size(osdev, &obj_size);
- if (rc)
- return rc;
-
- /* create gendisk info */
- disk = alloc_disk(OSDBLK_MINORS_PER_MAJOR);
- if (!disk)
- return -ENOMEM;
-
- sprintf(disk->disk_name, DRV_NAME "%d", osdev->id);
- disk->major = osdev->major;
- disk->first_minor = 0;
- disk->fops = &osdblk_bd_ops;
- disk->private_data = osdev;
-
- /* init rq */
- q = blk_init_queue(osdblk_rq_fn, &osdev->lock);
- if (!q) {
- put_disk(disk);
- return -ENOMEM;
- }
-
- /* switch queue to TCQ mode; allocate tag map */
- rc = blk_queue_init_tags(q, OSDBLK_MAX_REQ, NULL, BLK_TAG_ALLOC_FIFO);
- if (rc) {
- blk_cleanup_queue(q);
- put_disk(disk);
- return rc;
- }
-
- /* Set our limits to the lower device limits, because osdblk cannot
- * sleep when allocating a lower-request and therefore cannot be
- * bouncing.
- */
- blk_queue_stack_limits(q, osd_request_queue(osdev->osd));
-
- blk_queue_prep_rq(q, blk_queue_start_tag);
- blk_queue_write_cache(q, true, false);
-
- disk->queue = q;
-
- q->queuedata = osdev;
-
- osdev->disk = disk;
- osdev->q = q;
-
- /* finally, announce the disk to the world */
- set_capacity(disk, obj_size / 512ULL);
- add_disk(disk);
-
- printk(KERN_INFO "%s: Added of size 0x%llx\n",
- disk->disk_name, (unsigned long long)obj_size);
-
- return 0;
-}
-
-/********************************************************************
- * /sys/class/osdblk/
- * add map OSD object to blkdev
- * remove unmap OSD object
- * list show mappings
- *******************************************************************/
-
-static void class_osdblk_release(struct class *cls)
-{
- kfree(cls);
-}
-
-static ssize_t class_osdblk_list(struct class *c,
- struct class_attribute *attr,
- char *data)
-{
- int n = 0;
- struct list_head *tmp;
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- struct osdblk_device *osdev;
-
- osdev = list_entry(tmp, struct osdblk_device, node);
-
- n += sprintf(data+n, "%d %d %llu %llu %s\n",
- osdev->id,
- osdev->major,
- osdev->obj.partition,
- osdev->obj.id,
- osdev->osd_path);
- }
-
- mutex_unlock(&ctl_mutex);
- return n;
-}
-
-static ssize_t class_osdblk_add(struct class *c,
- struct class_attribute *attr,
- const char *buf, size_t count)
-{
- struct osdblk_device *osdev;
- ssize_t rc;
- int irc, new_id = 0;
- struct list_head *tmp;
-
- if (!try_module_get(THIS_MODULE))
- return -ENODEV;
-
- /* new osdblk_device object */
- osdev = kzalloc(sizeof(*osdev) + strlen(buf) + 1, GFP_KERNEL);
- if (!osdev) {
- rc = -ENOMEM;
- goto err_out_mod;
- }
-
- /* static osdblk_device initialization */
- spin_lock_init(&osdev->lock);
- INIT_LIST_HEAD(&osdev->node);
-
- /* generate unique id: find highest unique id, add one */
-
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- struct osdblk_device *osdev;
-
- osdev = list_entry(tmp, struct osdblk_device, node);
- if (osdev->id > new_id)
- new_id = osdev->id + 1;
- }
-
- osdev->id = new_id;
-
- /* add to global list */
- list_add_tail(&osdev->node, &osdblkdev_list);
-
- mutex_unlock(&ctl_mutex);
-
- /* parse add command */
- if (sscanf(buf, "%llu %llu %s", &osdev->obj.partition, &osdev->obj.id,
- osdev->osd_path) != 3) {
- rc = -EINVAL;
- goto err_out_slot;
- }
-
- /* initialize rest of new object */
- sprintf(osdev->name, DRV_NAME "%d", osdev->id);
-
- /* contact requested OSD */
- osdev->osd = osduld_path_lookup(osdev->osd_path);
- if (IS_ERR(osdev->osd)) {
- rc = PTR_ERR(osdev->osd);
- goto err_out_slot;
- }
-
- /* build OSD credential */
- osdblk_make_credential(osdev->obj_cred, &osdev->obj);
-
- /* register our block device */
- irc = register_blkdev(0, osdev->name);
- if (irc < 0) {
- rc = irc;
- goto err_out_osd;
- }
-
- osdev->major = irc;
-
- /* set up and announce blkdev mapping */
- rc = osdblk_init_disk(osdev);
- if (rc)
- goto err_out_blkdev;
-
- return count;
-
-err_out_blkdev:
- unregister_blkdev(osdev->major, osdev->name);
-err_out_osd:
- osduld_put_device(osdev->osd);
-err_out_slot:
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
- list_del_init(&osdev->node);
- mutex_unlock(&ctl_mutex);
-
- kfree(osdev);
-err_out_mod:
- OSDBLK_DEBUG("Error adding device %s\n", buf);
- module_put(THIS_MODULE);
- return rc;
-}
-
-static ssize_t class_osdblk_remove(struct class *c,
- struct class_attribute *attr,
- const char *buf,
- size_t count)
-{
- struct osdblk_device *osdev = NULL;
- int target_id, rc;
- unsigned long ul;
- struct list_head *tmp;
-
- rc = kstrtoul(buf, 10, &ul);
- if (rc)
- return rc;
-
- /* convert to int; abort if we lost anything in the conversion */
- target_id = (int) ul;
- if (target_id != ul)
- return -EINVAL;
-
- /* remove object from list immediately */
- mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
- list_for_each(tmp, &osdblkdev_list) {
- osdev = list_entry(tmp, struct osdblk_device, node);
- if (osdev->id == target_id) {
- list_del_init(&osdev->node);
- break;
- }
- osdev = NULL;
- }
-
- mutex_unlock(&ctl_mutex);
-
- if (!osdev)
- return -ENOENT;
-
- /* clean up and free blkdev and associated OSD connection */
- osdblk_free_disk(osdev);
- unregister_blkdev(osdev->major, osdev->name);
- osduld_put_device(osdev->osd);
- kfree(osdev);
-
- /* release module ref */
- module_put(THIS_MODULE);
-
- return count;
-}
-
-static struct class_attribute class_osdblk_attrs[] = {
- __ATTR(add, 0200, NULL, class_osdblk_add),
- __ATTR(remove, 0200, NULL, class_osdblk_remove),
- __ATTR(list, 0444, class_osdblk_list, NULL),
- __ATTR_NULL
-};
-
-static int osdblk_sysfs_init(void)
-{
- int ret = 0;
-
- /*
- * create control files in sysfs
- * /sys/class/osdblk/...
- */
- class_osdblk = kzalloc(sizeof(*class_osdblk), GFP_KERNEL);
- if (!class_osdblk)
- return -ENOMEM;
-
- class_osdblk->name = DRV_NAME;
- class_osdblk->owner = THIS_MODULE;
- class_osdblk->class_release = class_osdblk_release;
- class_osdblk->class_attrs = class_osdblk_attrs;
-
- ret = class_register(class_osdblk);
- if (ret) {
- kfree(class_osdblk);
- class_osdblk = NULL;
- printk(PFX "failed to create class osdblk\n");
- return ret;
- }
-
- return 0;
-}
-
-static void osdblk_sysfs_cleanup(void)
-{
- if (class_osdblk)
- class_destroy(class_osdblk);
- class_osdblk = NULL;
-}
-
-static int __init osdblk_init(void)
-{
- int rc;
-
- rc = osdblk_sysfs_init();
- if (rc)
- return rc;
-
- return 0;
-}
-
-static void __exit osdblk_exit(void)
-{
- osdblk_sysfs_cleanup();
-}
-
-module_init(osdblk_init);
-module_exit(osdblk_exit);
-
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 939641d6e262..b1267ef34d5a 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -300,6 +300,11 @@ static void pcd_init_units(void)
struct gendisk *disk = alloc_disk(1);
if (!disk)
continue;
+ disk->queue = blk_init_queue(do_pcd_request, &pcd_lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ continue;
+ }
cd->disk = disk;
cd->pi = &cd->pia;
cd->present = 0;
@@ -735,18 +740,36 @@ static int pcd_detect(void)
}
/* I/O request processing */
-static struct request_queue *pcd_queue;
+static int pcd_queue;
+
+static int set_next_request(void)
+{
+ struct pcd_unit *cd;
+ struct request_queue *q;
+ int old_pos = pcd_queue;
+
+ do {
+ cd = &pcd[pcd_queue];
+ q = cd->present ? cd->disk->queue : NULL;
+ if (++pcd_queue == PCD_UNITS)
+ pcd_queue = 0;
+ if (q) {
+ pcd_req = blk_fetch_request(q);
+ if (pcd_req)
+ break;
+ }
+ } while (pcd_queue != old_pos);
+
+ return pcd_req != NULL;
+}
-static void do_pcd_request(struct request_queue * q)
+static void pcd_request(void)
{
if (pcd_busy)
return;
while (1) {
- if (!pcd_req) {
- pcd_req = blk_fetch_request(q);
- if (!pcd_req)
- return;
- }
+ if (!pcd_req && !set_next_request())
+ return;
if (rq_data_dir(pcd_req) == READ) {
struct pcd_unit *cd = pcd_req->rq_disk->private_data;
@@ -766,6 +789,11 @@ static void do_pcd_request(struct request_queue * q)
}
}
+static void do_pcd_request(struct request_queue *q)
+{
+ pcd_request();
+}
+
static inline void next_request(int err)
{
unsigned long saved_flags;
@@ -774,7 +802,7 @@ static inline void next_request(int err)
if (!__blk_end_request_cur(pcd_req, err))
pcd_req = NULL;
pcd_busy = 0;
- do_pcd_request(pcd_queue);
+ pcd_request();
spin_unlock_irqrestore(&pcd_lock, saved_flags);
}
@@ -849,7 +877,7 @@ static void do_pcd_read_drq(void)
do_pcd_read();
spin_lock_irqsave(&pcd_lock, saved_flags);
- do_pcd_request(pcd_queue);
+ pcd_request();
spin_unlock_irqrestore(&pcd_lock, saved_flags);
}
@@ -957,19 +985,10 @@ static int __init pcd_init(void)
return -EBUSY;
}
- pcd_queue = blk_init_queue(do_pcd_request, &pcd_lock);
- if (!pcd_queue) {
- unregister_blkdev(major, name);
- for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++)
- put_disk(cd->disk);
- return -ENOMEM;
- }
-
for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) {
if (cd->present) {
register_cdrom(&cd->info);
cd->disk->private_data = cd;
- cd->disk->queue = pcd_queue;
add_disk(cd->disk);
}
}
@@ -988,9 +1007,9 @@ static void __exit pcd_exit(void)
pi_release(cd->pi);
unregister_cdrom(&cd->info);
}
+ blk_cleanup_queue(cd->disk->queue);
put_disk(cd->disk);
}
- blk_cleanup_queue(pcd_queue);
unregister_blkdev(major, name);
pi_unregister_driver(par_drv);
}
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 9cfd2e06a649..7d2402f90978 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -381,12 +381,33 @@ static enum action do_pd_write_start(void);
static enum action do_pd_read_drq(void);
static enum action do_pd_write_done(void);
-static struct request_queue *pd_queue;
+static int pd_queue;
static int pd_claimed;
static struct pd_unit *pd_current; /* current request's drive */
static PIA *pi_current; /* current request's PIA */
+static int set_next_request(void)
+{
+ struct gendisk *disk;
+ struct request_queue *q;
+ int old_pos = pd_queue;
+
+ do {
+ disk = pd[pd_queue].gd;
+ q = disk ? disk->queue : NULL;
+ if (++pd_queue == PD_UNITS)
+ pd_queue = 0;
+ if (q) {
+ pd_req = blk_fetch_request(q);
+ if (pd_req)
+ break;
+ }
+ } while (pd_queue != old_pos);
+
+ return pd_req != NULL;
+}
+
static void run_fsm(void)
{
while (1) {
@@ -418,8 +439,7 @@ static void run_fsm(void)
spin_lock_irqsave(&pd_lock, saved_flags);
if (!__blk_end_request_cur(pd_req,
res == Ok ? 0 : -EIO)) {
- pd_req = blk_fetch_request(pd_queue);
- if (!pd_req)
+ if (!set_next_request())
stop = 1;
}
spin_unlock_irqrestore(&pd_lock, saved_flags);
@@ -719,18 +739,15 @@ static int pd_special_command(struct pd_unit *disk,
enum action (*func)(struct pd_unit *disk))
{
struct request *rq;
- int err = 0;
rq = blk_get_request(disk->gd->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
if (IS_ERR(rq))
return PTR_ERR(rq);
rq->special = func;
-
- err = blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
-
+ blk_execute_rq(disk->gd->queue, disk->gd, rq, 0);
blk_put_request(rq);
- return err;
+ return 0;
}
/* kernel glue structures */
@@ -839,7 +856,13 @@ static void pd_probe_drive(struct pd_unit *disk)
p->first_minor = (disk - pd) << PD_BITS;
disk->gd = p;
p->private_data = disk;
- p->queue = pd_queue;
+ p->queue = blk_init_queue(do_pd_request, &pd_lock);
+ if (!p->queue) {
+ disk->gd = NULL;
+ put_disk(p);
+ return;
+ }
+ blk_queue_max_hw_sectors(p->queue, cluster);
if (disk->drive == -1) {
for (disk->drive = 0; disk->drive <= 1; disk->drive++)
@@ -919,26 +942,18 @@ static int __init pd_init(void)
if (disable)
goto out1;
- pd_queue = blk_init_queue(do_pd_request, &pd_lock);
- if (!pd_queue)
- goto out1;
-
- blk_queue_max_hw_sectors(pd_queue, cluster);
-
if (register_blkdev(major, name))
- goto out2;
+ goto out1;
printk("%s: %s version %s, major %d, cluster %d, nice %d\n",
name, name, PD_VERSION, major, cluster, nice);
if (!pd_detect())
- goto out3;
+ goto out2;
return 0;
-out3:
- unregister_blkdev(major, name);
out2:
- blk_cleanup_queue(pd_queue);
+ unregister_blkdev(major, name);
out1:
return -ENODEV;
}
@@ -953,11 +968,11 @@ static void __exit pd_exit(void)
if (p) {
disk->gd = NULL;
del_gendisk(p);
+ blk_cleanup_queue(p->queue);
put_disk(p);
pi_release(disk->pi);
}
}
- blk_cleanup_queue(pd_queue);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index 14c5d32f5d8b..f24ca7315ddc 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -287,6 +287,12 @@ static void __init pf_init_units(void)
struct gendisk *disk = alloc_disk(1);
if (!disk)
continue;
+ disk->queue = blk_init_queue(do_pf_request, &pf_spin_lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ return;
+ }
+ blk_queue_max_segments(disk->queue, cluster);
pf->disk = disk;
pf->pi = &pf->pia;
pf->media_status = PF_NM;
@@ -772,7 +778,28 @@ static int pf_ready(void)
return (((status_reg(pf_current) & (STAT_BUSY | pf_mask)) == pf_mask));
}
-static struct request_queue *pf_queue;
+static int pf_queue;
+
+static int set_next_request(void)
+{
+ struct pf_unit *pf;
+ struct request_queue *q;
+ int old_pos = pf_queue;
+
+ do {
+ pf = &units[pf_queue];
+ q = pf->present ? pf->disk->queue : NULL;
+ if (++pf_queue == PF_UNITS)
+ pf_queue = 0;
+ if (q) {
+ pf_req = blk_fetch_request(q);
+ if (pf_req)
+ break;
+ }
+ } while (pf_queue != old_pos);
+
+ return pf_req != NULL;
+}
static void pf_end_request(int err)
{
@@ -780,16 +807,13 @@ static void pf_end_request(int err)
pf_req = NULL;
}
-static void do_pf_request(struct request_queue * q)
+static void pf_request(void)
{
if (pf_busy)
return;
repeat:
- if (!pf_req) {
- pf_req = blk_fetch_request(q);
- if (!pf_req)
- return;
- }
+ if (!pf_req && !set_next_request())
+ return;
pf_current = pf_req->rq_disk->private_data;
pf_block = blk_rq_pos(pf_req);
@@ -817,6 +841,11 @@ repeat:
}
}
+static void do_pf_request(struct request_queue *q)
+{
+ pf_request();
+}
+
static int pf_next_buf(void)
{
unsigned long saved_flags;
@@ -846,7 +875,7 @@ static inline void next_request(int err)
spin_lock_irqsave(&pf_spin_lock, saved_flags);
pf_end_request(err);
pf_busy = 0;
- do_pf_request(pf_queue);
+ pf_request();
spin_unlock_irqrestore(&pf_spin_lock, saved_flags);
}
@@ -972,15 +1001,6 @@ static int __init pf_init(void)
put_disk(pf->disk);
return -EBUSY;
}
- pf_queue = blk_init_queue(do_pf_request, &pf_spin_lock);
- if (!pf_queue) {
- unregister_blkdev(major, name);
- for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++)
- put_disk(pf->disk);
- return -ENOMEM;
- }
-
- blk_queue_max_segments(pf_queue, cluster);
for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) {
struct gendisk *disk = pf->disk;
@@ -988,7 +1008,6 @@ static int __init pf_init(void)
if (!pf->present)
continue;
disk->private_data = pf;
- disk->queue = pf_queue;
add_disk(disk);
}
return 0;
@@ -1003,10 +1022,10 @@ static void __exit pf_exit(void)
if (!pf->present)
continue;
del_gendisk(pf->disk);
+ blk_cleanup_queue(pf->disk->queue);
put_disk(pf->disk);
pi_release(pf->pi);
}
- blk_cleanup_queue(pf_queue);
}
MODULE_LICENSE("GPL");
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 66d846ba85a9..205b865ebeb9 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -724,7 +724,7 @@ static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *
rq->rq_flags |= RQF_QUIET;
blk_execute_rq(rq->q, pd->bdev->bd_disk, rq, 0);
- if (rq->errors)
+ if (scsi_req(rq)->result)
ret = -EIO;
out:
blk_put_request(rq);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 517838b65964..089ac4179919 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -4317,7 +4317,7 @@ static int rbd_init_request(void *data, struct request *rq,
return 0;
}
-static struct blk_mq_ops rbd_mq_ops = {
+static const struct blk_mq_ops rbd_mq_ops = {
.queue_rq = rbd_queue_rq,
.init_request = rbd_init_request,
};
@@ -4380,7 +4380,6 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
q->limits.discard_granularity = segment_size;
q->limits.discard_alignment = segment_size;
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;
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index f81d70b39d10..9c566364ac9c 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -300,7 +300,6 @@ int rsxx_setup_dev(struct rsxx_cardinfo *card)
RSXX_HW_BLK_SIZE >> 9);
card->queue->limits.discard_granularity = RSXX_HW_BLK_SIZE;
card->queue->limits.discard_alignment = RSXX_HW_BLK_SIZE;
- card->queue->limits.discard_zeroes_data = 1;
}
card->queue->queuedata = card;
diff --git a/drivers/block/swim.c b/drivers/block/swim.c
index b5afd495d482..3064be6cf375 100644
--- a/drivers/block/swim.c
+++ b/drivers/block/swim.c
@@ -211,7 +211,7 @@ enum head {
struct swim_priv {
struct swim __iomem *base;
spinlock_t lock;
- struct request_queue *queue;
+ int fdc_queue;
int floppy_count;
struct floppy_state unit[FD_MAX_UNIT];
};
@@ -525,12 +525,33 @@ static int floppy_read_sectors(struct floppy_state *fs,
return 0;
}
-static void redo_fd_request(struct request_queue *q)
+static struct request *swim_next_request(struct swim_priv *swd)
{
+ struct request_queue *q;
+ struct request *rq;
+ int old_pos = swd->fdc_queue;
+
+ do {
+ q = swd->unit[swd->fdc_queue].disk->queue;
+ if (++swd->fdc_queue == swd->floppy_count)
+ swd->fdc_queue = 0;
+ if (q) {
+ rq = blk_fetch_request(q);
+ if (rq)
+ return rq;
+ }
+ } while (swd->fdc_queue != old_pos);
+
+ return NULL;
+}
+
+static void do_fd_request(struct request_queue *q)
+{
+ struct swim_priv *swd = q->queuedata;
struct request *req;
struct floppy_state *fs;
- req = blk_fetch_request(q);
+ req = swim_next_request(swd);
while (req) {
int err = -EIO;
@@ -554,15 +575,10 @@ static void redo_fd_request(struct request_queue *q)
}
done:
if (!__blk_end_request_cur(req, err))
- req = blk_fetch_request(q);
+ req = swim_next_request(swd);
}
}
-static void do_fd_request(struct request_queue *q)
-{
- redo_fd_request(q);
-}
-
static struct floppy_struct floppy_type[4] = {
{ 0, 0, 0, 0, 0, 0x00, 0x00, 0x00, 0x00, NULL }, /* no testing */
{ 720, 9, 1, 80, 0, 0x2A, 0x02, 0xDF, 0x50, NULL }, /* 360KB SS 3.5"*/
@@ -833,22 +849,25 @@ static int swim_floppy_init(struct swim_priv *swd)
return -EBUSY;
}
+ spin_lock_init(&swd->lock);
+
for (drive = 0; drive < swd->floppy_count; drive++) {
swd->unit[drive].disk = alloc_disk(1);
if (swd->unit[drive].disk == NULL) {
err = -ENOMEM;
goto exit_put_disks;
}
+ swd->unit[drive].disk->queue = blk_init_queue(do_fd_request,
+ &swd->lock);
+ if (!swd->unit[drive].disk->queue) {
+ err = -ENOMEM;
+ put_disk(swd->unit[drive].disk);
+ goto exit_put_disks;
+ }
+ swd->unit[drive].disk->queue->queuedata = swd;
swd->unit[drive].swd = swd;
}
- spin_lock_init(&swd->lock);
- swd->queue = blk_init_queue(do_fd_request, &swd->lock);
- if (!swd->queue) {
- err = -ENOMEM;
- goto exit_put_disks;
- }
-
for (drive = 0; drive < swd->floppy_count; drive++) {
swd->unit[drive].disk->flags = GENHD_FL_REMOVABLE;
swd->unit[drive].disk->major = FLOPPY_MAJOR;
@@ -856,7 +875,6 @@ static int swim_floppy_init(struct swim_priv *swd)
sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive);
swd->unit[drive].disk->fops = &floppy_fops;
swd->unit[drive].disk->private_data = &swd->unit[drive];
- swd->unit[drive].disk->queue = swd->queue;
set_capacity(swd->unit[drive].disk, 2880);
add_disk(swd->unit[drive].disk);
}
@@ -943,13 +961,12 @@ static int swim_remove(struct platform_device *dev)
for (drive = 0; drive < swd->floppy_count; drive++) {
del_gendisk(swd->unit[drive].disk);
+ blk_cleanup_queue(swd->unit[drive].disk->queue);
put_disk(swd->unit[drive].disk);
}
unregister_blkdev(FLOPPY_MAJOR, "fd");
- blk_cleanup_queue(swd->queue);
-
/* eject floppies */
for (drive = 0; drive < swd->floppy_count; drive++)
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 61b3ffa4f458..ba4809c9bdba 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -343,8 +343,8 @@ static void start_request(struct floppy_state *fs)
req->rq_disk->disk_name, req->cmd,
(long)blk_rq_pos(req), blk_rq_sectors(req),
bio_data(req->bio));
- swim3_dbg(" errors=%d current_nr_sectors=%u\n",
- req->errors, blk_rq_cur_sectors(req));
+ swim3_dbg(" current_nr_sectors=%u\n",
+ blk_rq_cur_sectors(req));
#endif
if (blk_rq_pos(req) >= fs->total_secs) {
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 1d4c9f8bc1e1..f94614257462 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -111,7 +111,7 @@ static int virtblk_add_req_scsi(struct virtqueue *vq, struct virtblk_req *vbr,
return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC);
}
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
struct virtio_blk *vblk = req->q->queuedata;
@@ -119,7 +119,7 @@ static inline void virtblk_scsi_reques_done(struct request *req)
sreq->resid_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.residual);
sreq->sense_len = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.sense_len);
- req->errors = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
+ sreq->result = virtio32_to_cpu(vblk->vdev, vbr->in_hdr.errors);
}
static int virtblk_ioctl(struct block_device *bdev, fmode_t mode,
@@ -144,7 +144,7 @@ static inline int virtblk_add_req_scsi(struct virtqueue *vq,
{
return -EIO;
}
-static inline void virtblk_scsi_reques_done(struct request *req)
+static inline void virtblk_scsi_request_done(struct request *req)
{
}
#define virtblk_ioctl NULL
@@ -175,19 +175,15 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr,
static inline void virtblk_request_done(struct request *req)
{
struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
- int error = virtblk_result(vbr);
switch (req_op(req)) {
case REQ_OP_SCSI_IN:
case REQ_OP_SCSI_OUT:
- virtblk_scsi_reques_done(req);
- break;
- case REQ_OP_DRV_IN:
- req->errors = (error != 0);
+ virtblk_scsi_request_done(req);
break;
}
- blk_mq_end_request(req, error);
+ blk_mq_end_request(req, virtblk_result(vbr));
}
static void virtblk_done(struct virtqueue *vq)
@@ -205,7 +201,7 @@ static void virtblk_done(struct virtqueue *vq)
while ((vbr = virtqueue_get_buf(vblk->vqs[qid].vq, &len)) != NULL) {
struct request *req = blk_mq_rq_from_pdu(vbr);
- blk_mq_complete_request(req, req->errors);
+ blk_mq_complete_request(req);
req_done = true;
}
if (unlikely(virtqueue_is_broken(vq)))
@@ -310,7 +306,8 @@ static int virtblk_get_id(struct gendisk *disk, char *id_str)
if (err)
goto out;
- err = blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+ blk_execute_rq(vblk->disk->queue, vblk->disk, req, false);
+ err = virtblk_result(blk_mq_rq_to_pdu(req));
out:
blk_put_request(req);
return err;
@@ -597,7 +594,7 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set)
return blk_mq_virtio_map_queues(set, vblk->vdev, 0);
}
-static struct blk_mq_ops virtio_mq_ops = {
+static const struct blk_mq_ops virtio_mq_ops = {
.queue_rq = virtio_queue_rq,
.complete = virtblk_request_done,
.init_request = virtblk_init_request,
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 5067a0a952cb..39459631667c 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -115,6 +115,15 @@ struct split_bio {
atomic_t pending;
};
+struct blkif_req {
+ int error;
+};
+
+static inline struct blkif_req *blkif_req(struct request *rq)
+{
+ return blk_mq_rq_to_pdu(rq);
+}
+
static DEFINE_MUTEX(blkfront_mutex);
static const struct block_device_operations xlvbd_block_fops;
@@ -907,8 +916,14 @@ out_busy:
return BLK_MQ_RQ_QUEUE_BUSY;
}
-static struct blk_mq_ops blkfront_mq_ops = {
+static void blkif_complete_rq(struct request *rq)
+{
+ blk_mq_end_request(rq, blkif_req(rq)->error);
+}
+
+static const struct blk_mq_ops blkfront_mq_ops = {
.queue_rq = blkif_queue_rq,
+ .complete = blkif_complete_rq,
};
static void blkif_set_queue_limits(struct blkfront_info *info)
@@ -969,7 +984,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
info->tag_set.queue_depth = BLK_RING_SIZE(info);
info->tag_set.numa_node = NUMA_NO_NODE;
info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
- info->tag_set.cmd_size = 0;
+ info->tag_set.cmd_size = sizeof(struct blkif_req);
info->tag_set.driver_data = info;
if (blk_mq_alloc_tag_set(&info->tag_set))
@@ -1543,7 +1558,6 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
unsigned long flags;
struct blkfront_ring_info *rinfo = (struct blkfront_ring_info *)dev_id;
struct blkfront_info *info = rinfo->dev_info;
- int error;
if (unlikely(info->connected != BLKIF_STATE_CONNECTED))
return IRQ_HANDLED;
@@ -1587,37 +1601,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
continue;
}
- error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
+ blkif_req(req)->error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
case BLKIF_OP_DISCARD:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
struct request_queue *rq = info->rq;
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
info->feature_discard = 0;
info->feature_secdiscard = 0;
queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
queue_flag_clear(QUEUE_FLAG_SECERASE, rq);
}
- blk_mq_complete_request(req, error);
break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
printk(KERN_WARNING "blkfront: %s: %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
}
if (unlikely(bret->status == BLKIF_RSP_ERROR &&
rinfo->shadow[id].req.u.rw.nr_segments == 0)) {
printk(KERN_WARNING "blkfront: %s: empty %s op failed\n",
info->gd->disk_name, op_name(bret->operation));
- error = -EOPNOTSUPP;
+ blkif_req(req)->error = -EOPNOTSUPP;
}
- if (unlikely(error)) {
- if (error == -EOPNOTSUPP)
- error = 0;
+ if (unlikely(blkif_req(req)->error)) {
+ if (blkif_req(req)->error == -EOPNOTSUPP)
+ blkif_req(req)->error = 0;
info->feature_fua = 0;
info->feature_flush = 0;
xlvbd_flush(info);
@@ -1629,11 +1642,12 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id)
dev_dbg(&info->xbdev->dev, "Bad return from blkdev data "
"request: %x\n", bret->status);
- blk_mq_complete_request(req, error);
break;
default:
BUG();
}
+
+ blk_mq_complete_request(req);
}
rinfo->ring.rsp_cons = i;
@@ -2345,6 +2359,7 @@ static void blkfront_connect(struct blkfront_info *info)
unsigned long sector_size;
unsigned int physical_sector_size;
unsigned int binfo;
+ char *envp[] = { "RESIZE=1", NULL };
int err, i;
switch (info->connected) {
@@ -2361,6 +2376,8 @@ static void blkfront_connect(struct blkfront_info *info)
sectors);
set_capacity(info->gd, sectors);
revalidate_disk(info->gd);
+ kobject_uevent_env(&disk_to_dev(info->gd)->kobj,
+ KOBJ_CHANGE, envp);
return;
case BLKIF_STATE_SUSPENDED:
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 0c09d4256108..6fac5fedd610 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -829,10 +829,14 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
offset = (bio->bi_iter.bi_sector &
(SECTORS_PER_PAGE - 1)) << SECTOR_SHIFT;
- if (unlikely(bio_op(bio) == REQ_OP_DISCARD)) {
+ switch (bio_op(bio)) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
zram_bio_discard(zram, index, offset, bio);
bio_endio(bio);
return;
+ default:
+ break;
}
bio_for_each_segment(bvec, bio, iter) {
@@ -1192,6 +1196,8 @@ static int zram_add(void)
zram->disk->queue->limits.max_sectors = SECTORS_PER_PAGE;
zram->disk->queue->limits.chunk_sectors = 0;
blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+
/*
* zram_bio_discard() will clear all logical blocks if logical block
* size is identical with physical block size(PAGE_SIZE). But if it is
@@ -1201,10 +1207,7 @@ static int zram_add(void)
* zeroed.
*/
if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
- zram->disk->queue->limits.discard_zeroes_data = 1;
- else
- zram->disk->queue->limits.discard_zeroes_data = 0;
- queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, zram->disk->queue);
+ blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);
add_disk(zram->disk);
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 87739649eac2..76c952fd9ab9 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2218,7 +2218,8 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
rq->timeout = 60 * HZ;
bio = rq->bio;
- if (blk_execute_rq(q, cdi->disk, rq, 0)) {
+ blk_execute_rq(q, cdi->disk, rq, 0);
+ if (scsi_req(rq)->result) {
struct request_sense *s = req->sense;
ret = -EIO;
cdi->last_sense = s->sense_key;
diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index feb30061123b..5901937284e7 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -107,7 +107,8 @@ int ide_queue_pc_tail(ide_drive_t *drive, struct gendisk *disk,
memcpy(scsi_req(rq)->cmd, pc->c, 12);
if (drive->media == ide_tape)
scsi_req(rq)->cmd[13] = REQ_IDETAPE_PC1;
- error = blk_execute_rq(drive->queue, disk, rq, 0);
+ blk_execute_rq(drive->queue, disk, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
put_req:
blk_put_request(rq);
return error;
@@ -454,7 +455,7 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
debug_log("%s: I/O error\n", drive->name);
if (drive->media != ide_tape)
- pc->rq->errors++;
+ scsi_req(pc->rq)->result++;
if (scsi_req(rq)->cmd[0] == REQUEST_SENSE) {
printk(KERN_ERR PFX "%s: I/O error in request "
@@ -488,13 +489,13 @@ static ide_startstop_t ide_pc_intr(ide_drive_t *drive)
drive->failed_pc = NULL;
if (ata_misc_request(rq)) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
error = 0;
} else {
if (blk_rq_is_passthrough(rq) && uptodate <= 0) {
- if (rq->errors == 0)
- rq->errors = -EIO;
+ if (scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
error = uptodate ? 0 : -EIO;
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 74f1b7dc03f7..07e5ff3a64c3 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -247,10 +247,10 @@ static int ide_cd_breathe(ide_drive_t *drive, struct request *rq)
struct cdrom_info *info = drive->driver_data;
- if (!rq->errors)
+ if (!scsi_req(rq)->result)
info->write_timeout = jiffies + ATAPI_WAIT_WRITE_BUSY;
- rq->errors = 1;
+ scsi_req(rq)->result = 1;
if (time_after(jiffies, info->write_timeout))
return 0;
@@ -294,8 +294,8 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
}
/* if we have an error, pass CHECK_CONDITION as the SCSI status byte */
- if (blk_rq_is_scsi(rq) && !rq->errors)
- rq->errors = SAM_STAT_CHECK_CONDITION;
+ if (blk_rq_is_scsi(rq) && !scsi_req(rq)->result)
+ scsi_req(rq)->result = SAM_STAT_CHECK_CONDITION;
if (blk_noretry_request(rq))
do_end_request = 1;
@@ -325,7 +325,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
* Arrange to retry the request but be sure to give up if we've
* retried too many times.
*/
- if (++rq->errors > ERROR_MAX)
+ if (++scsi_req(rq)->result > ERROR_MAX)
do_end_request = 1;
break;
case ILLEGAL_REQUEST:
@@ -372,7 +372,7 @@ static int cdrom_decode_status(ide_drive_t *drive, u8 stat)
/* go to the default handler for other errors */
ide_error(drive, "cdrom_decode_status", stat);
return 1;
- } else if (++rq->errors > ERROR_MAX)
+ } else if (++scsi_req(rq)->result > ERROR_MAX)
/* we've racked up too many retries, abort */
do_end_request = 1;
}
@@ -452,7 +452,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
}
}
- error = blk_execute_rq(drive->queue, info->disk, rq, 0);
+ blk_execute_rq(drive->queue, info->disk, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
if (buffer)
*bufflen = scsi_req(rq)->resid_len;
@@ -683,8 +684,8 @@ out_end:
if (cmd->nleft == 0)
uptodate = 1;
} else {
- if (uptodate <= 0 && rq->errors == 0)
- rq->errors = -EIO;
+ if (uptodate <= 0 && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
if (uptodate == 0 && rq->bio)
@@ -1379,7 +1380,7 @@ static int ide_cdrom_prep_pc(struct request *rq)
* appropriate action
*/
if (c[0] == MODE_SENSE || c[0] == MODE_SELECT) {
- rq->errors = ILLEGAL_REQUEST;
+ scsi_req(rq)->result = ILLEGAL_REQUEST;
return BLKPREP_KILL;
}
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 9fcefbc8425e..55cd736c39c6 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -307,7 +307,8 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_MISC;
rq->rq_flags = RQF_QUIET;
- ret = blk_execute_rq(drive->queue, cd->disk, rq, 0);
+ blk_execute_rq(drive->queue, cd->disk, rq, 0);
+ ret = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
/*
* A reset will unlock the door. If it was previously locked,
diff --git a/drivers/ide/ide-devsets.c b/drivers/ide/ide-devsets.c
index a45dda5386e4..9b69c32ee560 100644
--- a/drivers/ide/ide-devsets.c
+++ b/drivers/ide/ide-devsets.c
@@ -173,8 +173,8 @@ int ide_devset_execute(ide_drive_t *drive, const struct ide_devset *setting,
*(int *)&scsi_req(rq)->cmd[1] = arg;
rq->special = setting->set;
- if (blk_execute_rq(q, NULL, rq, 0))
- ret = rq->errors;
+ blk_execute_rq(q, NULL, rq, 0);
+ ret = scsi_req(rq)->result;
blk_put_request(rq);
return ret;
@@ -186,7 +186,7 @@ ide_startstop_t ide_do_devset(ide_drive_t *drive, struct request *rq)
err = setfunc(drive, *(int *)&scsi_req(rq)->cmd[1]);
if (err)
- rq->errors = err;
- ide_complete_rq(drive, err, blk_rq_bytes(rq));
+ scsi_req(rq)->result = err;
+ ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
}
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 186159715b71..7c06237f3479 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -470,7 +470,6 @@ ide_devset_get(multcount, mult_count);
static int set_multcount(ide_drive_t *drive, int arg)
{
struct request *rq;
- int error;
if (arg < 0 || arg > (drive->id[ATA_ID_MAX_MULTSECT] & 0xff))
return -EINVAL;
@@ -484,7 +483,7 @@ static int set_multcount(ide_drive_t *drive, int arg)
drive->mult_req = arg;
drive->special_flags |= IDE_SFLAG_SET_MULTMODE;
- error = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
blk_put_request(rq);
return (drive->mult_count == arg) ? 0 : -EIO;
diff --git a/drivers/ide/ide-dma.c b/drivers/ide/ide-dma.c
index 17a65ac56491..51c81223e56d 100644
--- a/drivers/ide/ide-dma.c
+++ b/drivers/ide/ide-dma.c
@@ -490,7 +490,7 @@ ide_startstop_t ide_dma_timeout_retry(ide_drive_t *drive, int error)
* make sure request is sane
*/
if (hwif->rq)
- hwif->rq->errors = 0;
+ scsi_req(hwif->rq)->result = 0;
return ret;
}
diff --git a/drivers/ide/ide-eh.c b/drivers/ide/ide-eh.c
index cf3af6840368..4b7ffd7d158d 100644
--- a/drivers/ide/ide-eh.c
+++ b/drivers/ide/ide-eh.c
@@ -12,7 +12,7 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
if ((stat & ATA_BUSY) ||
((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
/* other bits are useless when BUSY */
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
} else if (stat & ATA_ERR) {
/* err has different meaning on cdrom and tape */
if (err == ATA_ABORTED) {
@@ -25,10 +25,10 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
drive->crc_count++;
} else if (err & (ATA_BBK | ATA_UNC)) {
/* retries won't help these */
- rq->errors = ERROR_MAX;
+ scsi_req(rq)->result = ERROR_MAX;
} else if (err & ATA_TRK0NF) {
/* help it find track zero */
- rq->errors |= ERROR_RECAL;
+ scsi_req(rq)->result |= ERROR_RECAL;
}
}
@@ -39,23 +39,23 @@ static ide_startstop_t ide_ata_error(ide_drive_t *drive, struct request *rq,
ide_pad_transfer(drive, READ, nsect * SECTOR_SIZE);
}
- if (rq->errors >= ERROR_MAX || blk_noretry_request(rq)) {
+ if (scsi_req(rq)->result >= ERROR_MAX || blk_noretry_request(rq)) {
ide_kill_rq(drive, rq);
return ide_stopped;
}
if (hwif->tp_ops->read_status(hwif) & (ATA_BUSY | ATA_DRQ))
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
- if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
- ++rq->errors;
+ if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+ ++scsi_req(rq)->result;
return ide_do_reset(drive);
}
- if ((rq->errors & ERROR_RECAL) == ERROR_RECAL)
+ if ((scsi_req(rq)->result & ERROR_RECAL) == ERROR_RECAL)
drive->special_flags |= IDE_SFLAG_RECALIBRATE;
- ++rq->errors;
+ ++scsi_req(rq)->result;
return ide_stopped;
}
@@ -68,7 +68,7 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
if ((stat & ATA_BUSY) ||
((stat & ATA_DF) && (drive->dev_flags & IDE_DFLAG_NOWERR) == 0)) {
/* other bits are useless when BUSY */
- rq->errors |= ERROR_RESET;
+ scsi_req(rq)->result |= ERROR_RESET;
} else {
/* add decoding error stuff */
}
@@ -77,14 +77,14 @@ static ide_startstop_t ide_atapi_error(ide_drive_t *drive, struct request *rq,
/* force an abort */
hwif->tp_ops->exec_command(hwif, ATA_CMD_IDLEIMMEDIATE);
- if (rq->errors >= ERROR_MAX) {
+ if (scsi_req(rq)->result >= ERROR_MAX) {
ide_kill_rq(drive, rq);
} else {
- if ((rq->errors & ERROR_RESET) == ERROR_RESET) {
- ++rq->errors;
+ if ((scsi_req(rq)->result & ERROR_RESET) == ERROR_RESET) {
+ ++scsi_req(rq)->result;
return ide_do_reset(drive);
}
- ++rq->errors;
+ ++scsi_req(rq)->result;
}
return ide_stopped;
@@ -130,11 +130,11 @@ ide_startstop_t ide_error(ide_drive_t *drive, const char *msg, u8 stat)
if (cmd)
ide_complete_cmd(drive, cmd, stat, err);
} else if (ata_pm_request(rq)) {
- rq->errors = 1;
+ scsi_req(rq)->result = 1;
ide_complete_pm_rq(drive, rq);
return ide_stopped;
}
- rq->errors = err;
+ scsi_req(rq)->result = err;
ide_complete_rq(drive, err ? -EIO : 0, blk_rq_bytes(rq));
return ide_stopped;
}
@@ -149,8 +149,8 @@ static inline void ide_complete_drive_reset(ide_drive_t *drive, int err)
if (rq && ata_misc_request(rq) &&
scsi_req(rq)->cmd[0] == REQ_DRIVE_RESET) {
- if (err <= 0 && rq->errors == 0)
- rq->errors = -EIO;
+ if (err <= 0 && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
ide_complete_rq(drive, err ? err : 0, blk_rq_bytes(rq));
}
}
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index a69e8013f1df..8ac6048cd2df 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -98,7 +98,7 @@ static int ide_floppy_callback(ide_drive_t *drive, int dsc)
}
if (ata_misc_request(rq))
- rq->errors = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
+ scsi_req(rq)->result = uptodate ? 0 : IDE_DRV_ERROR_GENERAL;
return uptodate;
}
@@ -239,7 +239,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
? rq->rq_disk->disk_name
: "dev?"));
- if (rq->errors >= ERROR_MAX) {
+ if (scsi_req(rq)->result >= ERROR_MAX) {
if (drive->failed_pc) {
ide_floppy_report_error(floppy, drive->failed_pc);
drive->failed_pc = NULL;
@@ -247,7 +247,7 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
printk(KERN_ERR PFX "%s: I/O error\n", drive->name);
if (ata_misc_request(rq)) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
} else
@@ -301,8 +301,8 @@ static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
return ide_floppy_issue_pc(drive, &cmd, pc);
out_end:
drive->failed_pc = NULL;
- if (blk_rq_is_passthrough(rq) && rq->errors == 0)
- rq->errors = -EIO;
+ if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
return ide_stopped;
}
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 043b1fb963cb..45b3f41a43d4 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -141,12 +141,12 @@ void ide_kill_rq(ide_drive_t *drive, struct request *rq)
drive->failed_pc = NULL;
if ((media == ide_floppy || media == ide_tape) && drv_req) {
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
} else {
if (media == ide_tape)
- rq->errors = IDE_DRV_ERROR_GENERAL;
- else if (blk_rq_is_passthrough(rq) && rq->errors == 0)
- rq->errors = -EIO;
+ scsi_req(rq)->result = IDE_DRV_ERROR_GENERAL;
+ else if (blk_rq_is_passthrough(rq) && scsi_req(rq)->result == 0)
+ scsi_req(rq)->result = -EIO;
}
ide_complete_rq(drive, -EIO, blk_rq_bytes(rq));
@@ -271,7 +271,7 @@ static ide_startstop_t execute_drive_cmd (ide_drive_t *drive,
#ifdef DEBUG
printk("%s: DRIVE_CMD (null)\n", drive->name);
#endif
- rq->errors = 0;
+ scsi_req(rq)->result = 0;
ide_complete_rq(drive, 0, blk_rq_bytes(rq));
return ide_stopped;
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index 248a3e0ceb46..8c0d17297a7a 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -128,7 +128,8 @@ static int ide_cmd_ioctl(ide_drive_t *drive, unsigned long arg)
rq = blk_get_request(drive->queue, REQ_OP_DRV_IN, __GFP_RECLAIM);
scsi_req_init(rq);
ide_req(rq)->type = ATA_PRIV_TASKFILE;
- err = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ err = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
return err;
@@ -227,8 +228,8 @@ static int generic_drive_reset(ide_drive_t *drive)
ide_req(rq)->type = ATA_PRIV_MISC;
scsi_req(rq)->cmd_len = 1;
scsi_req(rq)->cmd[0] = REQ_DRIVE_RESET;
- if (blk_execute_rq(drive->queue, NULL, rq, 1))
- ret = rq->errors;
+ blk_execute_rq(drive->queue, NULL, rq, 1);
+ ret = scsi_req(rq)->result;
blk_put_request(rq);
return ret;
}
diff --git a/drivers/ide/ide-park.c b/drivers/ide/ide-park.c
index 101aed9a61ca..94e3107f59b9 100644
--- a/drivers/ide/ide-park.c
+++ b/drivers/ide/ide-park.c
@@ -37,7 +37,8 @@ static void issue_park_cmd(ide_drive_t *drive, unsigned long timeout)
scsi_req(rq)->cmd_len = 1;
ide_req(rq)->type = ATA_PRIV_MISC;
rq->special = &timeout;
- rc = blk_execute_rq(q, NULL, rq, 1);
+ blk_execute_rq(q, NULL, rq, 1);
+ rc = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
if (rc)
goto out;
diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c
index ec951be4b0c8..0977fc1f40ce 100644
--- a/drivers/ide/ide-pm.c
+++ b/drivers/ide/ide-pm.c
@@ -27,7 +27,8 @@ int generic_ide_suspend(struct device *dev, pm_message_t mesg)
mesg.event = PM_EVENT_FREEZE;
rqpm.pm_state = mesg.event;
- ret = blk_execute_rq(drive->queue, NULL, rq, 0);
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ ret = scsi_req(rq)->result ? -EIO : 0;
blk_put_request(rq);
if (ret == 0 && ide_port_acpi(hwif)) {
@@ -55,8 +56,8 @@ static int ide_pm_execute_rq(struct request *rq)
spin_lock_irq(q->queue_lock);
if (unlikely(blk_queue_dying(q))) {
rq->rq_flags |= RQF_QUIET;
- rq->errors = -ENXIO;
- __blk_end_request_all(rq, rq->errors);
+ scsi_req(rq)->result = -ENXIO;
+ __blk_end_request_all(rq, 0);
spin_unlock_irq(q->queue_lock);
return -ENXIO;
}
@@ -66,7 +67,7 @@ static int ide_pm_execute_rq(struct request *rq)
wait_for_completion_io(&wait);
- return rq->errors ? -EIO : 0;
+ return scsi_req(rq)->result ? -EIO : 0;
}
int generic_ide_resume(struct device *dev)
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index d8a552b47718..a0651f948b76 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -366,7 +366,7 @@ static int ide_tape_callback(ide_drive_t *drive, int dsc)
err = pc->error;
}
}
- rq->errors = err;
+ scsi_req(rq)->result = err;
return uptodate;
}
@@ -879,7 +879,7 @@ static int idetape_queue_rw_tail(ide_drive_t *drive, int cmd, int size)
tape->valid = 0;
ret = size;
- if (rq->errors == IDE_DRV_ERROR_GENERAL)
+ if (scsi_req(rq)->result == IDE_DRV_ERROR_GENERAL)
ret = -EIO;
out_put:
blk_put_request(rq);
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 4c0007cb74e3..d71199d23c9e 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -287,7 +287,7 @@ static void ide_pio_datablock(ide_drive_t *drive, struct ide_cmd *cmd,
u8 saved_io_32bit = drive->io_32bit;
if (cmd->tf_flags & IDE_TFLAG_FS)
- cmd->rq->errors = 0;
+ scsi_req(cmd->rq)->result = 0;
if (cmd->tf_flags & IDE_TFLAG_IO_16BIT)
drive->io_32bit = 0;
@@ -329,7 +329,7 @@ void ide_finish_cmd(ide_drive_t *drive, struct ide_cmd *cmd, u8 stat)
u8 set_xfer = !!(cmd->tf_flags & IDE_TFLAG_SET_XFER);
ide_complete_cmd(drive, cmd, stat, err);
- rq->errors = err;
+ scsi_req(rq)->result = err;
if (err == 0 && set_xfer) {
ide_set_xfer_rate(drive, nsect);
@@ -452,8 +452,8 @@ int ide_raw_taskfile(ide_drive_t *drive, struct ide_cmd *cmd, u8 *buf,
rq->special = cmd;
cmd->rq = rq;
- error = blk_execute_rq(drive->queue, NULL, rq, 0);
-
+ blk_execute_rq(drive->queue, NULL, rq, 0);
+ error = scsi_req(rq)->result ? -EIO : 0;
put_req:
blk_put_request(rq);
return error;
diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 052714106b7b..ead61a93cb4e 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -33,4 +33,13 @@ config NVM_RRPC
host. The target is implemented using a linear mapping table and
cost-based garbage collection. It is optimized for 4K IO sizes.
+config NVM_PBLK
+ tristate "Physical Block Device Open-Channel SSD target"
+ ---help---
+ Allows an open-channel SSD to be exposed as a block device to the
+ host. The target assumes the device exposes raw flash and must be
+ explicitly managed by the host.
+
+ Please note the disk format is considered EXPERIMENTAL for now.
+
endif # NVM
diff --git a/drivers/lightnvm/Makefile b/drivers/lightnvm/Makefile
index b2a39e2d2895..82d1a117fb27 100644
--- a/drivers/lightnvm/Makefile
+++ b/drivers/lightnvm/Makefile
@@ -4,3 +4,8 @@
obj-$(CONFIG_NVM) := core.o
obj-$(CONFIG_NVM_RRPC) += rrpc.o
+obj-$(CONFIG_NVM_PBLK) += pblk.o
+pblk-y := pblk-init.o pblk-core.o pblk-rb.o \
+ pblk-write.o pblk-cache.o pblk-read.o \
+ pblk-gc.o pblk-recovery.o pblk-map.o \
+ pblk-rl.o pblk-sysfs.o
diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
index 5262ba66a7a7..54a06c3a2b8c 100644
--- a/drivers/lightnvm/core.c
+++ b/drivers/lightnvm/core.c
@@ -89,7 +89,7 @@ static void nvm_release_luns_err(struct nvm_dev *dev, int lun_begin,
WARN_ON(!test_and_clear_bit(i, dev->lun_map));
}
-static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
+static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev, int clear)
{
struct nvm_dev *dev = tgt_dev->parent;
struct nvm_dev_map *dev_map = tgt_dev->map;
@@ -100,11 +100,14 @@ static void nvm_remove_tgt_dev(struct nvm_tgt_dev *tgt_dev)
int *lun_offs = ch_map->lun_offs;
int ch = i + ch_map->ch_off;
- for (j = 0; j < ch_map->nr_luns; j++) {
- int lun = j + lun_offs[j];
- int lunid = (ch * dev->geo.luns_per_chnl) + lun;
+ if (clear) {
+ for (j = 0; j < ch_map->nr_luns; j++) {
+ int lun = j + lun_offs[j];
+ int lunid = (ch * dev->geo.luns_per_chnl) + lun;
- WARN_ON(!test_and_clear_bit(lunid, dev->lun_map));
+ WARN_ON(!test_and_clear_bit(lunid,
+ dev->lun_map));
+ }
}
kfree(ch_map->lun_offs);
@@ -232,6 +235,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
struct nvm_target *t;
struct nvm_tgt_dev *tgt_dev;
void *targetdata;
+ int ret;
tt = nvm_find_target_type(create->tgttype, 1);
if (!tt) {
@@ -252,34 +256,43 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
return -ENOMEM;
t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL);
- if (!t)
+ if (!t) {
+ ret = -ENOMEM;
goto err_reserve;
+ }
tgt_dev = nvm_create_tgt_dev(dev, s->lun_begin, s->lun_end);
if (!tgt_dev) {
pr_err("nvm: could not create target device\n");
+ ret = -ENOMEM;
goto err_t;
}
- tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
- if (!tqueue)
+ tdisk = alloc_disk(0);
+ if (!tdisk) {
+ ret = -ENOMEM;
goto err_dev;
- blk_queue_make_request(tqueue, tt->make_rq);
+ }
- tdisk = alloc_disk(0);
- if (!tdisk)
- goto err_queue;
+ tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node);
+ if (!tqueue) {
+ ret = -ENOMEM;
+ goto err_disk;
+ }
+ blk_queue_make_request(tqueue, tt->make_rq);
- sprintf(tdisk->disk_name, "%s", create->tgtname);
+ strlcpy(tdisk->disk_name, create->tgtname, sizeof(tdisk->disk_name));
tdisk->flags = GENHD_FL_EXT_DEVT;
tdisk->major = 0;
tdisk->first_minor = 0;
tdisk->fops = &nvm_fops;
tdisk->queue = tqueue;
- targetdata = tt->init(tgt_dev, tdisk);
- if (IS_ERR(targetdata))
+ targetdata = tt->init(tgt_dev, tdisk, create->flags);
+ if (IS_ERR(targetdata)) {
+ ret = PTR_ERR(targetdata);
goto err_init;
+ }
tdisk->private_data = targetdata;
tqueue->queuedata = targetdata;
@@ -289,8 +302,10 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create)
set_capacity(tdisk, tt->capacity(targetdata));
add_disk(tdisk);
- if (tt->sysfs_init && tt->sysfs_init(tdisk))
+ if (tt->sysfs_init && tt->sysfs_init(tdisk)) {
+ ret = -ENOMEM;
goto err_sysfs;
+ }
t->type = tt;
t->disk = tdisk;
@@ -305,16 +320,17 @@ err_sysfs:
if (tt->exit)
tt->exit(targetdata);
err_init:
- put_disk(tdisk);
-err_queue:
blk_cleanup_queue(tqueue);
+ tdisk->queue = NULL;
+err_disk:
+ put_disk(tdisk);
err_dev:
- nvm_remove_tgt_dev(tgt_dev);
+ nvm_remove_tgt_dev(tgt_dev, 0);
err_t:
kfree(t);
err_reserve:
nvm_release_luns_err(dev, s->lun_begin, s->lun_end);
- return -ENOMEM;
+ return ret;
}
static void __nvm_remove_target(struct nvm_target *t)
@@ -332,7 +348,7 @@ static void __nvm_remove_target(struct nvm_target *t)
if (tt->exit)
tt->exit(tdisk->private_data);
- nvm_remove_tgt_dev(t->dev);
+ nvm_remove_tgt_dev(t->dev, 1);
put_disk(tdisk);
list_del(&t->list);
@@ -411,6 +427,18 @@ err_rmap:
return -ENOMEM;
}
+static void nvm_unregister_map(struct nvm_dev *dev)
+{
+ struct nvm_dev_map *rmap = dev->rmap;
+ int i;
+
+ for (i = 0; i < dev->geo.nr_chnls; i++)
+ kfree(rmap->chnls[i].lun_offs);
+
+ kfree(rmap->chnls);
+ kfree(rmap);
+}
+
static void nvm_map_to_dev(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *p)
{
struct nvm_dev_map *dev_map = tgt_dev->map;
@@ -486,7 +514,6 @@ void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
int *lun_roffs;
struct ppa_addr gaddr;
u64 pba = le64_to_cpu(entries[i]);
- int off;
u64 diff;
if (!pba)
@@ -496,8 +523,6 @@ void nvm_part_to_tgt(struct nvm_dev *dev, sector_t *entries,
ch_rmap = &dev_rmap->chnls[gaddr.g.ch];
lun_roffs = ch_rmap->lun_offs;
- off = gaddr.g.ch * geo->luns_per_chnl + gaddr.g.lun;
-
diff = ((ch_rmap->ch_off * geo->luns_per_chnl) +
(lun_roffs[gaddr.g.lun])) * geo->sec_per_lun;
@@ -590,11 +615,11 @@ int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
memset(&rqd, 0, sizeof(struct nvm_rq));
- nvm_set_rqd_ppalist(dev, &rqd, ppas, nr_ppas, 1);
+ nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
nvm_rq_tgt_to_dev(tgt_dev, &rqd);
ret = dev->ops->set_bb_tbl(dev, &rqd.ppa_addr, rqd.nr_ppas, type);
- nvm_free_rqd_ppalist(dev, &rqd);
+ nvm_free_rqd_ppalist(tgt_dev, &rqd);
if (ret) {
pr_err("nvm: failed bb mark\n");
return -EINVAL;
@@ -626,34 +651,45 @@ int nvm_submit_io(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
}
EXPORT_SYMBOL(nvm_submit_io);
-int nvm_erase_blk(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas, int flags)
+static void nvm_end_io_sync(struct nvm_rq *rqd)
{
- struct nvm_dev *dev = tgt_dev->parent;
- struct nvm_rq rqd;
- int ret;
+ struct completion *waiting = rqd->private;
- if (!dev->ops->erase_block)
- return 0;
+ complete(waiting);
+}
- nvm_map_to_dev(tgt_dev, ppas);
+int nvm_erase_sync(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
+ int nr_ppas)
+{
+ struct nvm_geo *geo = &tgt_dev->geo;
+ struct nvm_rq rqd;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
memset(&rqd, 0, sizeof(struct nvm_rq));
- ret = nvm_set_rqd_ppalist(dev, &rqd, ppas, 1, 1);
+ rqd.opcode = NVM_OP_ERASE;
+ rqd.end_io = nvm_end_io_sync;
+ rqd.private = &wait;
+ rqd.flags = geo->plane_mode >> 1;
+
+ ret = nvm_set_rqd_ppalist(tgt_dev, &rqd, ppas, nr_ppas, 1);
if (ret)
return ret;
- nvm_rq_tgt_to_dev(tgt_dev, &rqd);
-
- rqd.flags = flags;
-
- ret = dev->ops->erase_block(dev, &rqd);
+ ret = nvm_submit_io(tgt_dev, &rqd);
+ if (ret) {
+ pr_err("rrpr: erase I/O submission failed: %d\n", ret);
+ goto free_ppa_list;
+ }
+ wait_for_completion_io(&wait);
- nvm_free_rqd_ppalist(dev, &rqd);
+free_ppa_list:
+ nvm_free_rqd_ppalist(tgt_dev, &rqd);
return ret;
}
-EXPORT_SYMBOL(nvm_erase_blk);
+EXPORT_SYMBOL(nvm_erase_sync);
int nvm_get_l2p_tbl(struct nvm_tgt_dev *tgt_dev, u64 slba, u32 nlb,
nvm_l2p_update_fn *update_l2p, void *priv)
@@ -732,10 +768,11 @@ void nvm_put_area(struct nvm_tgt_dev *tgt_dev, sector_t begin)
}
EXPORT_SYMBOL(nvm_put_area);
-int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
+int nvm_set_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd,
const struct ppa_addr *ppas, int nr_ppas, int vblk)
{
- struct nvm_geo *geo = &dev->geo;
+ struct nvm_dev *dev = tgt_dev->parent;
+ struct nvm_geo *geo = &tgt_dev->geo;
int i, plane_cnt, pl_idx;
struct ppa_addr ppa;
@@ -773,12 +810,12 @@ int nvm_set_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd,
}
EXPORT_SYMBOL(nvm_set_rqd_ppalist);
-void nvm_free_rqd_ppalist(struct nvm_dev *dev, struct nvm_rq *rqd)
+void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev, struct nvm_rq *rqd)
{
if (!rqd->ppa_list)
return;
- nvm_dev_dma_free(dev, rqd->ppa_list, rqd->dma_ppa_list);
+ nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
}
EXPORT_SYMBOL(nvm_free_rqd_ppalist);
@@ -972,7 +1009,7 @@ err_fmtype:
return ret;
}
-void nvm_free(struct nvm_dev *dev)
+static void nvm_free(struct nvm_dev *dev)
{
if (!dev)
return;
@@ -980,7 +1017,7 @@ void nvm_free(struct nvm_dev *dev)
if (dev->dma_pool)
dev->ops->destroy_dma_pool(dev->dma_pool);
- kfree(dev->rmap);
+ nvm_unregister_map(dev);
kfree(dev->lptbl);
kfree(dev->lun_map);
kfree(dev);
@@ -1174,13 +1211,13 @@ static long nvm_ioctl_get_devices(struct file *file, void __user *arg)
list_for_each_entry(dev, &nvm_devices, devices) {
struct nvm_ioctl_device_info *info = &devices->info[i];
- sprintf(info->devname, "%s", dev->name);
+ strlcpy(info->devname, dev->name, sizeof(info->devname));
/* kept for compatibility */
info->bmversion[0] = 1;
info->bmversion[1] = 0;
info->bmversion[2] = 0;
- sprintf(info->bmname, "%s", "gennvm");
+ strlcpy(info->bmname, "gennvm", sizeof(info->bmname));
i++;
if (i > 31) {
@@ -1217,8 +1254,16 @@ static long nvm_ioctl_dev_create(struct file *file, void __user *arg)
create.tgtname[DISK_NAME_LEN - 1] = '\0';
if (create.flags != 0) {
- pr_err("nvm: no flags supported\n");
- return -EINVAL;
+ __u32 flags = create.flags;
+
+ /* Check for valid flags */
+ if (flags & NVM_TARGET_FACTORY)
+ flags &= ~NVM_TARGET_FACTORY;
+
+ if (flags) {
+ pr_err("nvm: flag not supported\n");
+ return -EINVAL;
+ }
}
return __nvm_configure_create(&create);
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
new file mode 100644
index 000000000000..59bcea88db84
--- /dev/null
+++ b/drivers/lightnvm/pblk-cache.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-cache.c - pblk's write cache
+ */
+
+#include "pblk.h"
+
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
+{
+ struct pblk_w_ctx w_ctx;
+ sector_t lba = pblk_get_lba(bio);
+ unsigned int bpos, pos;
+ int nr_entries = pblk_get_secs(bio);
+ int i, ret;
+
+ /* Update the write buffer head (mem) with the entries that we can
+ * write. The write in itself cannot fail, so there is no need to
+ * rollback from here on.
+ */
+retry:
+ ret = pblk_rb_may_write_user(&pblk->rwb, bio, nr_entries, &bpos);
+ if (ret == NVM_IO_REQUEUE) {
+ io_schedule();
+ goto retry;
+ }
+
+ if (unlikely(!bio_has_data(bio)))
+ goto out;
+
+ w_ctx.flags = flags;
+ pblk_ppa_set_empty(&w_ctx.ppa);
+
+ for (i = 0; i < nr_entries; i++) {
+ void *data = bio_data(bio);
+
+ w_ctx.lba = lba + i;
+
+ pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + i);
+ pblk_rb_write_entry_user(&pblk->rwb, data, w_ctx, pos);
+
+ bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_entries, &pblk->inflight_writes);
+ atomic_long_add(nr_entries, &pblk->req_writes);
+#endif
+
+out:
+ pblk_write_should_kick(pblk);
+ return ret;
+}
+
+/*
+ * On GC the incoming lbas are not necessarily sequential. Also, some of the
+ * lbas might not be valid entries, which are marked as empty by the GC thread
+ */
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+ unsigned int nr_entries, unsigned int nr_rec_entries,
+ struct pblk_line *gc_line, unsigned long flags)
+{
+ struct pblk_w_ctx w_ctx;
+ unsigned int bpos, pos;
+ int i, valid_entries;
+
+ /* Update the write buffer head (mem) with the entries that we can
+ * write. The write in itself cannot fail, so there is no need to
+ * rollback from here on.
+ */
+retry:
+ if (!pblk_rb_may_write_gc(&pblk->rwb, nr_rec_entries, &bpos)) {
+ io_schedule();
+ goto retry;
+ }
+
+ w_ctx.flags = flags;
+ pblk_ppa_set_empty(&w_ctx.ppa);
+
+ for (i = 0, valid_entries = 0; i < nr_entries; i++) {
+ if (lba_list[i] == ADDR_EMPTY)
+ continue;
+
+ w_ctx.lba = lba_list[i];
+
+ pos = pblk_rb_wrap_pos(&pblk->rwb, bpos + valid_entries);
+ pblk_rb_write_entry_gc(&pblk->rwb, data, w_ctx, gc_line, pos);
+
+ data += PBLK_EXPOSED_PAGE_SIZE;
+ valid_entries++;
+ }
+
+ WARN_ONCE(nr_rec_entries != valid_entries,
+ "pblk: inconsistent GC write\n");
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(valid_entries, &pblk->inflight_writes);
+ atomic_long_add(valid_entries, &pblk->recov_gc_writes);
+#endif
+
+ pblk_write_should_kick(pblk);
+ return NVM_IO_OK;
+}
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
new file mode 100644
index 000000000000..5e44768ccffa
--- /dev/null
+++ b/drivers/lightnvm/pblk-core.c
@@ -0,0 +1,1667 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-core.c - pblk's core functionality
+ *
+ */
+
+#include "pblk.h"
+#include <linux/time.h>
+
+static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
+ struct ppa_addr *ppa)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int pos = pblk_dev_ppa_to_pos(geo, *ppa);
+
+ pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+ atomic_long_inc(&pblk->erase_failed);
+
+ atomic_dec(&line->blk_in_line);
+ if (test_and_set_bit(pos, line->blk_bitmap))
+ pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+ line->id, pos);
+
+ pblk_line_run_ws(pblk, NULL, ppa, pblk_line_mark_bb);
+}
+
+static void __pblk_end_io_erase(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct pblk_line *line;
+
+ line = &pblk->lines[pblk_dev_ppa_to_line(rqd->ppa_addr)];
+ atomic_dec(&line->left_seblks);
+
+ if (rqd->error) {
+ struct ppa_addr *ppa;
+
+ ppa = kmalloc(sizeof(struct ppa_addr), GFP_ATOMIC);
+ if (!ppa)
+ return;
+
+ *ppa = rqd->ppa_addr;
+ pblk_mark_bb(pblk, line, ppa);
+ }
+}
+
+/* Erase completion assumes that only one block is erased at the time */
+static void pblk_end_io_erase(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+
+ up(&pblk->erase_sem);
+ __pblk_end_io_erase(pblk, rqd);
+ mempool_free(rqd, pblk->r_rq_pool);
+}
+
+static void __pblk_map_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list = NULL;
+
+ /* Lines being reclaimed (GC'ed) cannot be invalidated. Before the L2P
+ * table is modified with reclaimed sectors, a check is done to endure
+ * that newer updates are not overwritten.
+ */
+ spin_lock(&line->lock);
+ if (line->state == PBLK_LINESTATE_GC ||
+ line->state == PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ return;
+ }
+
+ if (test_and_set_bit(paddr, line->invalid_bitmap)) {
+ WARN_ONCE(1, "pblk: double invalidate\n");
+ spin_unlock(&line->lock);
+ return;
+ }
+ line->vsc--;
+
+ if (line->state == PBLK_LINESTATE_CLOSED)
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ if (move_list) {
+ spin_lock(&l_mg->gc_lock);
+ spin_lock(&line->lock);
+ /* Prevent moving a line that has just been chosen for GC */
+ if (line->state == PBLK_LINESTATE_GC ||
+ line->state == PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ spin_unlock(&l_mg->gc_lock);
+ return;
+ }
+ spin_unlock(&line->lock);
+
+ list_move_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+ }
+}
+
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct pblk_line *line;
+ u64 paddr;
+ int line_id;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a device address */
+ BUG_ON(pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_ppa_empty(ppa));
+#endif
+
+ line_id = pblk_tgt_ppa_to_line(ppa);
+ line = &pblk->lines[line_id];
+ paddr = pblk_dev_ppa_to_line_addr(pblk, ppa);
+
+ __pblk_map_invalidate(pblk, line, paddr);
+}
+
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr)
+{
+ __pblk_map_invalidate(pblk, line, paddr);
+
+ pblk_rb_sync_init(&pblk->rwb, NULL);
+ line->left_ssecs--;
+ if (!line->left_ssecs)
+ pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+ pblk_rb_sync_end(&pblk->rwb, NULL);
+}
+
+static void pblk_invalidate_range(struct pblk *pblk, sector_t slba,
+ unsigned int nr_secs)
+{
+ sector_t lba;
+
+ spin_lock(&pblk->trans_lock);
+ for (lba = slba; lba < slba + nr_secs; lba++) {
+ struct ppa_addr ppa;
+
+ ppa = pblk_trans_map_get(pblk, lba);
+
+ if (!pblk_addr_in_cache(ppa) && !pblk_ppa_empty(ppa))
+ pblk_map_invalidate(pblk, ppa);
+
+ pblk_ppa_set_empty(&ppa);
+ pblk_trans_map_set(pblk, lba, ppa);
+ }
+ spin_unlock(&pblk->trans_lock);
+}
+
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw)
+{
+ mempool_t *pool;
+ struct nvm_rq *rqd;
+ int rq_size;
+
+ if (rw == WRITE) {
+ pool = pblk->w_rq_pool;
+ rq_size = pblk_w_rq_size;
+ } else {
+ pool = pblk->r_rq_pool;
+ rq_size = pblk_r_rq_size;
+ }
+
+ rqd = mempool_alloc(pool, GFP_KERNEL);
+ memset(rqd, 0, rq_size);
+
+ return rqd;
+}
+
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw)
+{
+ mempool_t *pool;
+
+ if (rw == WRITE)
+ pool = pblk->w_rq_pool;
+ else
+ pool = pblk->r_rq_pool;
+
+ mempool_free(rqd, pool);
+}
+
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+ int nr_pages)
+{
+ struct bio_vec bv;
+ int i;
+
+ WARN_ON(off + nr_pages != bio->bi_vcnt);
+
+ bio_advance(bio, off * PBLK_EXPOSED_PAGE_SIZE);
+ for (i = off; i < nr_pages + off; i++) {
+ bv = bio->bi_io_vec[i];
+ mempool_free(bv.bv_page, pblk->page_pool);
+ }
+}
+
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+ int nr_pages)
+{
+ struct request_queue *q = pblk->dev->q;
+ struct page *page;
+ int i, ret;
+
+ for (i = 0; i < nr_pages; i++) {
+ page = mempool_alloc(pblk->page_pool, flags);
+ if (!page)
+ goto err;
+
+ ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
+ if (ret != PBLK_EXPOSED_PAGE_SIZE) {
+ pr_err("pblk: could not add page to bio\n");
+ mempool_free(page, pblk->page_pool);
+ goto err;
+ }
+ }
+
+ return 0;
+err:
+ pblk_bio_free_pages(pblk, bio, 0, i - 1);
+ return -1;
+}
+
+static void pblk_write_kick(struct pblk *pblk)
+{
+ wake_up_process(pblk->writer_ts);
+ mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(1000));
+}
+
+void pblk_write_timer_fn(unsigned long data)
+{
+ struct pblk *pblk = (struct pblk *)data;
+
+ /* kick the write thread every tick to flush outstanding data */
+ pblk_write_kick(pblk);
+}
+
+void pblk_write_should_kick(struct pblk *pblk)
+{
+ unsigned int secs_avail = pblk_rb_read_count(&pblk->rwb);
+
+ if (secs_avail >= pblk->min_write_pgs)
+ pblk_write_kick(pblk);
+}
+
+void pblk_end_bio_sync(struct bio *bio)
+{
+ struct completion *waiting = bio->bi_private;
+
+ complete(waiting);
+}
+
+void pblk_end_io_sync(struct nvm_rq *rqd)
+{
+ struct completion *waiting = rqd->private;
+
+ complete(waiting);
+}
+
+void pblk_flush_writer(struct pblk *pblk)
+{
+ struct bio *bio;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ bio = bio_alloc(GFP_KERNEL, 1);
+ if (!bio)
+ return;
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, REQ_OP_FLUSH);
+ bio->bi_private = &wait;
+ bio->bi_end_io = pblk_end_bio_sync;
+
+ ret = pblk_write_to_cache(pblk, bio, 0);
+ if (ret == NVM_IO_OK) {
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: flush cache timed out\n");
+ }
+ } else if (ret != NVM_IO_DONE) {
+ pr_err("pblk: tear down bio failed\n");
+ }
+
+ if (bio->bi_error)
+ pr_err("pblk: flush sync write failed (%u)\n", bio->bi_error);
+
+ bio_put(bio);
+}
+
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list = NULL;
+
+ if (!line->vsc) {
+ if (line->gc_group != PBLK_LINEGC_FULL) {
+ line->gc_group = PBLK_LINEGC_FULL;
+ move_list = &l_mg->gc_full_list;
+ }
+ } else if (line->vsc < lm->mid_thrs) {
+ if (line->gc_group != PBLK_LINEGC_HIGH) {
+ line->gc_group = PBLK_LINEGC_HIGH;
+ move_list = &l_mg->gc_high_list;
+ }
+ } else if (line->vsc < lm->high_thrs) {
+ if (line->gc_group != PBLK_LINEGC_MID) {
+ line->gc_group = PBLK_LINEGC_MID;
+ move_list = &l_mg->gc_mid_list;
+ }
+ } else if (line->vsc < line->sec_in_line) {
+ if (line->gc_group != PBLK_LINEGC_LOW) {
+ line->gc_group = PBLK_LINEGC_LOW;
+ move_list = &l_mg->gc_low_list;
+ }
+ } else if (line->vsc == line->sec_in_line) {
+ if (line->gc_group != PBLK_LINEGC_EMPTY) {
+ line->gc_group = PBLK_LINEGC_EMPTY;
+ move_list = &l_mg->gc_empty_list;
+ }
+ } else {
+ line->state = PBLK_LINESTATE_CORRUPT;
+ line->gc_group = PBLK_LINEGC_NONE;
+ move_list = &l_mg->corrupt_list;
+ pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+ line->id, line->vsc,
+ line->sec_in_line,
+ lm->high_thrs, lm->mid_thrs);
+ }
+
+ return move_list;
+}
+
+void pblk_discard(struct pblk *pblk, struct bio *bio)
+{
+ sector_t slba = pblk_get_lba(bio);
+ sector_t nr_secs = pblk_get_secs(bio);
+
+ pblk_invalidate_range(pblk, slba, nr_secs);
+}
+
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba)
+{
+ struct ppa_addr ppa;
+
+ spin_lock(&pblk->trans_lock);
+ ppa = pblk_trans_map_get(pblk, lba);
+ spin_unlock(&pblk->trans_lock);
+
+ return ppa;
+}
+
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ atomic_long_inc(&pblk->write_failed);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ /* Empty page read is not necessarily an error (e.g., L2P recovery) */
+ if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+ atomic_long_inc(&pblk->read_empty);
+ return;
+ }
+
+ switch (rqd->error) {
+ case NVM_RSP_WARN_HIGHECC:
+ atomic_long_inc(&pblk->read_high_ecc);
+ break;
+ case NVM_RSP_ERR_FAILECC:
+ case NVM_RSP_ERR_FAILCRC:
+ atomic_long_inc(&pblk->read_failed);
+ break;
+ default:
+ pr_err("pblk: unknown read error:%d\n", rqd->error);
+ }
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+}
+
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+
+#ifdef CONFIG_NVM_DEBUG
+ struct ppa_addr *ppa_list;
+
+ ppa_list = (rqd->nr_ppas > 1) ? rqd->ppa_list : &rqd->ppa_addr;
+ if (pblk_boundary_ppa_checks(dev, ppa_list, rqd->nr_ppas)) {
+ WARN_ON(1);
+ return -EINVAL;
+ }
+
+ if (rqd->opcode == NVM_OP_PWRITE) {
+ struct pblk_line *line;
+ struct ppa_addr ppa;
+ int i;
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ ppa = ppa_list[i];
+ line = &pblk->lines[pblk_dev_ppa_to_line(ppa)];
+
+ spin_lock(&line->lock);
+ if (line->state != PBLK_LINESTATE_OPEN) {
+ pr_err("pblk: bad ppa: line:%d,state:%d\n",
+ line->id, line->state);
+ WARN_ON(1);
+ spin_unlock(&line->lock);
+ return -EINVAL;
+ }
+ spin_unlock(&line->lock);
+ }
+ }
+#endif
+ return nvm_submit_io(dev, rqd);
+}
+
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+ unsigned int nr_secs, unsigned int len,
+ gfp_t gfp_mask)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ void *kaddr = data;
+ struct page *page;
+ struct bio *bio;
+ int i, ret;
+
+ if (l_mg->emeta_alloc_type == PBLK_KMALLOC_META)
+ return bio_map_kern(dev->q, kaddr, len, gfp_mask);
+
+ bio = bio_kmalloc(gfp_mask, nr_secs);
+ if (!bio)
+ return ERR_PTR(-ENOMEM);
+
+ for (i = 0; i < nr_secs; i++) {
+ page = vmalloc_to_page(kaddr);
+ if (!page) {
+ pr_err("pblk: could not map vmalloc bio\n");
+ bio_put(bio);
+ bio = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
+ if (ret != PAGE_SIZE) {
+ pr_err("pblk: could not add page to bio\n");
+ bio_put(bio);
+ bio = ERR_PTR(-ENOMEM);
+ goto out;
+ }
+
+ kaddr += PAGE_SIZE;
+ }
+out:
+ return bio;
+}
+
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+ unsigned long secs_to_flush)
+{
+ int max = pblk->max_write_pgs;
+ int min = pblk->min_write_pgs;
+ int secs_to_sync = 0;
+
+ if (secs_avail >= max)
+ secs_to_sync = max;
+ else if (secs_avail >= min)
+ secs_to_sync = min * (secs_avail / min);
+ else if (secs_to_flush)
+ secs_to_sync = min;
+
+ return secs_to_sync;
+}
+
+static u64 __pblk_alloc_page(struct pblk *pblk, struct pblk_line *line,
+ int nr_secs)
+{
+ u64 addr;
+ int i;
+
+ /* logic error: ppa out-of-bounds. Prevent generating bad address */
+ if (line->cur_sec + nr_secs > pblk->lm.sec_per_line) {
+ WARN(1, "pblk: page allocation out of bounds\n");
+ nr_secs = pblk->lm.sec_per_line - line->cur_sec;
+ }
+
+ line->cur_sec = addr = find_next_zero_bit(line->map_bitmap,
+ pblk->lm.sec_per_line, line->cur_sec);
+ for (i = 0; i < nr_secs; i++, line->cur_sec++)
+ WARN_ON(test_and_set_bit(line->cur_sec, line->map_bitmap));
+
+ return addr;
+}
+
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs)
+{
+ u64 addr;
+
+ /* Lock needed in case a write fails and a recovery needs to remap
+ * failed write buffer entries
+ */
+ spin_lock(&line->lock);
+ addr = __pblk_alloc_page(pblk, line, nr_secs);
+ line->left_msecs -= nr_secs;
+ WARN(line->left_msecs < 0, "pblk: page allocation out of bounds\n");
+ spin_unlock(&line->lock);
+
+ return addr;
+}
+
+/*
+ * Submit emeta to one LUN in the raid line at the time to avoid a deadlock when
+ * taking the per LUN semaphore.
+ */
+static int pblk_line_submit_emeta_io(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr, int dir)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ struct ppa_addr *ppa_list;
+ dma_addr_t dma_ppa_list;
+ void *emeta = line->emeta;
+ int min = pblk->min_write_pgs;
+ int left_ppas = lm->emeta_sec;
+ int id = line->id;
+ int rq_ppas, rq_len;
+ int cmd_op, bio_op;
+ int flags;
+ int i, j;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ if (dir == WRITE) {
+ bio_op = REQ_OP_WRITE;
+ cmd_op = NVM_OP_PWRITE;
+ flags = pblk_set_progr_mode(pblk, WRITE);
+ } else if (dir == READ) {
+ bio_op = REQ_OP_READ;
+ cmd_op = NVM_OP_PREAD;
+ flags = pblk_set_read_mode(pblk);
+ } else
+ return -EINVAL;
+
+ ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_ppa_list);
+ if (!ppa_list)
+ return -ENOMEM;
+
+next_rq:
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = pblk_bio_map_addr(pblk, emeta, rq_ppas, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto free_rqd_dma;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, bio_op, 0);
+
+ rqd.bio = bio;
+ rqd.opcode = cmd_op;
+ rqd.flags = flags;
+ rqd.nr_ppas = rq_ppas;
+ rqd.ppa_list = ppa_list;
+ rqd.dma_ppa_list = dma_ppa_list;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ if (dir == WRITE) {
+ for (i = 0; i < rqd.nr_ppas; ) {
+ spin_lock(&line->lock);
+ paddr = __pblk_alloc_page(pblk, line, min);
+ spin_unlock(&line->lock);
+ for (j = 0; j < min; j++, i++, paddr++)
+ rqd.ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, id);
+ }
+ } else {
+ for (i = 0; i < rqd.nr_ppas; ) {
+ struct ppa_addr ppa = addr_to_gen_ppa(pblk, paddr, id);
+ int pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ paddr += min;
+ if (pblk_boundary_paddr_checks(pblk, paddr)) {
+ pr_err("pblk: corrupt emeta line:%d\n",
+ line->id);
+ bio_put(bio);
+ ret = -EINTR;
+ goto free_rqd_dma;
+ }
+
+ ppa = addr_to_gen_ppa(pblk, paddr, id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
+ pr_err("pblk: corrupt emeta line:%d\n",
+ line->id);
+ bio_put(bio);
+ ret = -EINTR;
+ goto free_rqd_dma;
+ }
+
+ for (j = 0; j < min; j++, i++, paddr++)
+ rqd.ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, line->id);
+ }
+ }
+
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ goto free_rqd_dma;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: emeta I/O timed out\n");
+ }
+ reinit_completion(&wait);
+
+ bio_put(bio);
+
+ if (rqd.error) {
+ if (dir == WRITE)
+ pblk_log_write_err(pblk, &rqd);
+ else
+ pblk_log_read_err(pblk, &rqd);
+ }
+
+ emeta += rq_len;
+ left_ppas -= rq_ppas;
+ if (left_ppas)
+ goto next_rq;
+free_rqd_dma:
+ nvm_dev_dma_free(dev->parent, ppa_list, dma_ppa_list);
+ return ret;
+}
+
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ int bit;
+
+ /* This usually only happens on bad lines */
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ if (bit >= lm->blk_per_line)
+ return -1;
+
+ return bit * geo->sec_per_pl;
+}
+
+static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr, int dir)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ __le64 *lba_list = NULL;
+ int i, ret;
+ int cmd_op, bio_op;
+ int flags;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ if (dir == WRITE) {
+ bio_op = REQ_OP_WRITE;
+ cmd_op = NVM_OP_PWRITE;
+ flags = pblk_set_progr_mode(pblk, WRITE);
+ lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ } else if (dir == READ) {
+ bio_op = REQ_OP_READ;
+ cmd_op = NVM_OP_PREAD;
+ flags = pblk_set_read_mode(pblk);
+ } else
+ return -EINVAL;
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_ppa_list);
+ if (!rqd.ppa_list)
+ return -ENOMEM;
+
+ bio = bio_map_kern(dev->q, line->smeta, lm->smeta_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ ret = PTR_ERR(bio);
+ goto free_ppa_list;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, bio_op, 0);
+
+ rqd.bio = bio;
+ rqd.opcode = cmd_op;
+ rqd.flags = flags;
+ rqd.nr_ppas = lm->smeta_sec;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ for (i = 0; i < lm->smeta_sec; i++, paddr++) {
+ rqd.ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+ if (dir == WRITE)
+ lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+ }
+
+ /*
+ * This I/O is sent by the write thread when a line is replace. Since
+ * the write thread is the only one sending write and erase commands,
+ * there is no need to take the LUN semaphore.
+ */
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ goto free_ppa_list;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: smeta I/O timed out\n");
+ }
+
+ if (rqd.error) {
+ if (dir == WRITE)
+ pblk_log_write_err(pblk, &rqd);
+ else
+ pblk_log_read_err(pblk, &rqd);
+ }
+
+free_ppa_list:
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+
+ return ret;
+}
+
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line)
+{
+ u64 bpaddr = pblk_line_smeta_start(pblk, line);
+
+ return pblk_line_submit_smeta_io(pblk, line, bpaddr, READ);
+}
+
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+ return pblk_line_submit_emeta_io(pblk, line, line->emeta_ssec, READ);
+}
+
+static void pblk_setup_e_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct ppa_addr ppa)
+{
+ rqd->opcode = NVM_OP_ERASE;
+ rqd->ppa_addr = ppa;
+ rqd->nr_ppas = 1;
+ rqd->flags = pblk_set_progr_mode(pblk, ERASE);
+ rqd->bio = NULL;
+}
+
+static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct nvm_rq rqd;
+ int ret;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ pblk_setup_e_rq(pblk, &rqd, ppa);
+
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+
+ /* The write thread schedules erases so that it minimizes disturbances
+ * with writes. Thus, there is no need to take the LUN semaphore.
+ */
+ ret = pblk_submit_io(pblk, &rqd);
+ if (ret) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+ pblk_dev_ppa_to_line(ppa),
+ pblk_dev_ppa_to_pos(geo, ppa));
+
+ rqd.error = ret;
+ goto out;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: sync erase timed out\n");
+ }
+
+out:
+ rqd.private = pblk;
+ __pblk_end_io_erase(pblk, &rqd);
+
+ return 0;
+}
+
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct ppa_addr ppa;
+ int bit = -1;
+
+ /* Erase only good blocks, one at a time */
+ do {
+ spin_lock(&line->lock);
+ bit = find_next_zero_bit(line->erase_bitmap, lm->blk_per_line,
+ bit + 1);
+ if (bit >= lm->blk_per_line) {
+ spin_unlock(&line->lock);
+ break;
+ }
+
+ ppa = pblk->luns[bit].bppa; /* set ch and lun */
+ ppa.g.blk = line->id;
+
+ atomic_dec(&line->left_eblks);
+ WARN_ON(test_and_set_bit(bit, line->erase_bitmap));
+ spin_unlock(&line->lock);
+
+ if (pblk_blk_erase_sync(pblk, ppa)) {
+ pr_err("pblk: failed to erase line %d\n", line->id);
+ return -ENOMEM;
+ }
+ } while (1);
+
+ return 0;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_set_metadata(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_line *cur)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct line_smeta *smeta = line->smeta;
+ struct line_emeta *emeta = line->emeta;
+ int nr_blk_line;
+
+ /* After erasing the line, new bad blocks might appear and we risk
+ * having an invalid line
+ */
+ nr_blk_line = lm->blk_per_line -
+ bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+ if (nr_blk_line < lm->min_blk_line) {
+ spin_lock(&l_mg->free_lock);
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+ spin_unlock(&l_mg->free_lock);
+
+ pr_debug("pblk: line %d is bad\n", line->id);
+
+ return 0;
+ }
+
+ /* Run-time metadata */
+ line->lun_bitmap = ((void *)(smeta)) + sizeof(struct line_smeta);
+
+ /* Mark LUNs allocated in this line (all for now) */
+ bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len);
+
+ smeta->header.identifier = cpu_to_le32(PBLK_MAGIC);
+ memcpy(smeta->header.uuid, pblk->instance_uuid, 16);
+ smeta->header.id = cpu_to_le32(line->id);
+ smeta->header.type = cpu_to_le16(line->type);
+ smeta->header.version = cpu_to_le16(1);
+
+ /* Start metadata */
+ smeta->seq_nr = cpu_to_le64(line->seq_nr);
+ smeta->window_wr_lun = cpu_to_le32(geo->nr_luns);
+
+ /* Fill metadata among lines */
+ if (cur) {
+ memcpy(line->lun_bitmap, cur->lun_bitmap, lm->lun_bitmap_len);
+ smeta->prev_id = cpu_to_le32(cur->id);
+ cur->emeta->next_id = cpu_to_le32(line->id);
+ } else {
+ smeta->prev_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ }
+
+ /* All smeta must be set at this point */
+ smeta->header.crc = cpu_to_le32(pblk_calc_meta_header_crc(pblk, smeta));
+ smeta->crc = cpu_to_le32(pblk_calc_smeta_crc(pblk, smeta));
+
+ /* End metadata */
+ memcpy(&emeta->header, &smeta->header, sizeof(struct line_header));
+ emeta->seq_nr = cpu_to_le64(line->seq_nr);
+ emeta->nr_lbas = cpu_to_le64(line->sec_in_line);
+ emeta->nr_valid_lbas = cpu_to_le64(0);
+ emeta->next_id = cpu_to_le32(PBLK_LINE_EMPTY);
+ emeta->crc = cpu_to_le32(0);
+ emeta->prev_id = smeta->prev_id;
+
+ return 1;
+}
+
+/* For now lines are always assumed full lines. Thus, smeta former and current
+ * lun bitmaps are omitted.
+ */
+static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
+ int init)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int nr_bb = 0;
+ u64 off;
+ int bit = -1;
+
+ line->sec_in_line = lm->sec_per_line;
+
+ /* Capture bad block information on line mapping bitmaps */
+ while ((bit = find_next_bit(line->blk_bitmap, lm->blk_per_line,
+ bit + 1)) < lm->blk_per_line) {
+ off = bit * geo->sec_per_pl;
+ bitmap_shift_left(l_mg->bb_aux, l_mg->bb_template, off,
+ lm->sec_per_line);
+ bitmap_or(line->map_bitmap, line->map_bitmap, l_mg->bb_aux,
+ lm->sec_per_line);
+ line->sec_in_line -= geo->sec_per_blk;
+ if (bit >= lm->emeta_bb)
+ nr_bb++;
+ }
+
+ /* Mark smeta metadata sectors as bad sectors */
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ off = bit * geo->sec_per_pl;
+retry_smeta:
+ bitmap_set(line->map_bitmap, off, lm->smeta_sec);
+ line->sec_in_line -= lm->smeta_sec;
+ line->smeta_ssec = off;
+ line->cur_sec = off + lm->smeta_sec;
+
+ if (init && pblk_line_submit_smeta_io(pblk, line, off, WRITE)) {
+ pr_debug("pblk: line smeta I/O failed. Retry\n");
+ off += geo->sec_per_pl;
+ goto retry_smeta;
+ }
+
+ bitmap_copy(line->invalid_bitmap, line->map_bitmap, lm->sec_per_line);
+
+ /* Mark emeta metadata sectors as bad sectors. We need to consider bad
+ * blocks to make sure that there are enough sectors to store emeta
+ */
+ bit = lm->sec_per_line;
+ off = lm->sec_per_line - lm->emeta_sec;
+ bitmap_set(line->invalid_bitmap, off, lm->emeta_sec);
+ while (nr_bb) {
+ off -= geo->sec_per_pl;
+ if (!test_bit(off, line->invalid_bitmap)) {
+ bitmap_set(line->invalid_bitmap, off, geo->sec_per_pl);
+ nr_bb--;
+ }
+ }
+
+ line->sec_in_line -= lm->emeta_sec;
+ line->emeta_ssec = off;
+ line->vsc = line->left_ssecs = line->left_msecs = line->sec_in_line;
+
+ if (lm->sec_per_line - line->sec_in_line !=
+ bitmap_weight(line->invalid_bitmap, lm->sec_per_line)) {
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+ pr_err("pblk: unexpected line %d is bad\n", line->id);
+
+ return 0;
+ }
+
+ return 1;
+}
+
+static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ int blk_in_line = atomic_read(&line->blk_in_line);
+
+ line->map_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+ if (!line->map_bitmap)
+ return -ENOMEM;
+ memset(line->map_bitmap, 0, lm->sec_bitmap_len);
+
+ /* invalid_bitmap is special since it is used when line is closed. No
+ * need to zeroized; it will be initialized using bb info form
+ * map_bitmap
+ */
+ line->invalid_bitmap = mempool_alloc(pblk->line_meta_pool, GFP_ATOMIC);
+ if (!line->invalid_bitmap) {
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ return -ENOMEM;
+ }
+
+ spin_lock(&line->lock);
+ if (line->state != PBLK_LINESTATE_FREE) {
+ spin_unlock(&line->lock);
+ WARN(1, "pblk: corrupted line state\n");
+ return -EINTR;
+ }
+ line->state = PBLK_LINESTATE_OPEN;
+
+ atomic_set(&line->left_eblks, blk_in_line);
+ atomic_set(&line->left_seblks, blk_in_line);
+ spin_unlock(&line->lock);
+
+ /* Bad blocks do not need to be erased */
+ bitmap_copy(line->erase_bitmap, line->blk_bitmap, lm->blk_per_line);
+
+ kref_init(&line->ref);
+
+ return 0;
+}
+
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int ret;
+
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_line = line;
+ list_del(&line->list);
+
+ ret = pblk_line_prepare(pblk, line);
+ if (ret) {
+ list_add(&line->list, &l_mg->free_list);
+ spin_unlock(&l_mg->free_lock);
+ return ret;
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_dec(&pblk->rl, line);
+
+ if (!pblk_line_init_bb(pblk, line, 0)) {
+ list_add(&line->list, &l_mg->free_list);
+ return -EINTR;
+ }
+
+ return 0;
+}
+
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line)
+{
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+}
+
+struct pblk_line *pblk_line_get(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line = NULL;
+ int bit;
+
+ lockdep_assert_held(&l_mg->free_lock);
+
+retry_get:
+ if (list_empty(&l_mg->free_list)) {
+ pr_err("pblk: no free lines\n");
+ goto out;
+ }
+
+ line = list_first_entry(&l_mg->free_list, struct pblk_line, list);
+ list_del(&line->list);
+ l_mg->nr_free_lines--;
+
+ bit = find_first_zero_bit(line->blk_bitmap, lm->blk_per_line);
+ if (unlikely(bit >= lm->blk_per_line)) {
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_BAD;
+ spin_unlock(&line->lock);
+
+ list_add_tail(&line->list, &l_mg->bad_list);
+
+ pr_debug("pblk: line %d is bad\n", line->id);
+ goto retry_get;
+ }
+
+ if (pblk_line_prepare(pblk, line)) {
+ pr_err("pblk: failed to prepare line %d\n", line->id);
+ list_add(&line->list, &l_mg->free_list);
+ return NULL;
+ }
+
+out:
+ return line;
+}
+
+static struct pblk_line *pblk_line_retry(struct pblk *pblk,
+ struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *retry_line;
+
+ spin_lock(&l_mg->free_lock);
+ retry_line = pblk_line_get(pblk);
+ if (!retry_line) {
+ l_mg->data_line = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ retry_line->smeta = line->smeta;
+ retry_line->emeta = line->emeta;
+ retry_line->meta_line = line->meta_line;
+
+ pblk_line_free(pblk, line);
+ l_mg->data_line = retry_line;
+ spin_unlock(&l_mg->free_lock);
+
+ if (pblk_line_erase(pblk, retry_line)) {
+ spin_lock(&l_mg->free_lock);
+ l_mg->data_line = NULL;
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ pblk_rl_free_lines_dec(&pblk->rl, retry_line);
+
+ return retry_line;
+}
+
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ int meta_line;
+ int is_next = 0;
+
+ spin_lock(&l_mg->free_lock);
+ line = pblk_line_get(pblk);
+ if (!line) {
+ spin_unlock(&l_mg->free_lock);
+ return NULL;
+ }
+
+ line->seq_nr = l_mg->d_seq_nr++;
+ line->type = PBLK_LINETYPE_DATA;
+ l_mg->data_line = line;
+
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ line->smeta = l_mg->sline_meta[meta_line].meta;
+ line->emeta = l_mg->eline_meta[meta_line].meta;
+ line->meta_line = meta_line;
+
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_dec(&pblk->rl, line);
+ if (is_next)
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+ if (pblk_line_erase(pblk, line))
+ return NULL;
+
+retry_setup:
+ if (!pblk_line_set_metadata(pblk, line, NULL)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ if (!pblk_line_init_bb(pblk, line, 1)) {
+ line = pblk_line_retry(pblk, line);
+ if (!line)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ return line;
+}
+
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *cur, *new;
+ unsigned int left_seblks;
+ int meta_line;
+ int is_next = 0;
+
+ cur = l_mg->data_line;
+ new = l_mg->data_next;
+ if (!new)
+ return NULL;
+ l_mg->data_line = new;
+
+retry_line:
+ left_seblks = atomic_read(&new->left_seblks);
+ if (left_seblks) {
+ /* If line is not fully erased, erase it */
+ if (atomic_read(&new->left_eblks)) {
+ if (pblk_line_erase(pblk, new))
+ return NULL;
+ } else {
+ io_schedule();
+ }
+ goto retry_line;
+ }
+
+ spin_lock(&l_mg->free_lock);
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+
+retry_meta:
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ if (meta_line == PBLK_DATA_LINES) {
+ spin_unlock(&l_mg->free_lock);
+ io_schedule();
+ spin_lock(&l_mg->free_lock);
+ goto retry_meta;
+ }
+
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ new->smeta = l_mg->sline_meta[meta_line].meta;
+ new->emeta = l_mg->eline_meta[meta_line].meta;
+ new->meta_line = meta_line;
+
+ memset(new->smeta, 0, lm->smeta_len);
+ memset(new->emeta, 0, lm->emeta_len);
+ spin_unlock(&l_mg->free_lock);
+
+ if (is_next)
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+
+retry_setup:
+ if (!pblk_line_set_metadata(pblk, new, cur)) {
+ new = pblk_line_retry(pblk, new);
+ if (!new)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ if (!pblk_line_init_bb(pblk, new, 1)) {
+ new = pblk_line_retry(pblk, new);
+ if (!new)
+ return NULL;
+
+ goto retry_setup;
+ }
+
+ return new;
+}
+
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line)
+{
+ if (line->map_bitmap)
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ if (line->invalid_bitmap)
+ mempool_free(line->invalid_bitmap, pblk->line_meta_pool);
+
+ line->map_bitmap = NULL;
+ line->invalid_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+}
+
+void pblk_line_put(struct kref *ref)
+{
+ struct pblk_line *line = container_of(ref, struct pblk_line, ref);
+ struct pblk *pblk = line->pblk;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_GC);
+ line->state = PBLK_LINESTATE_FREE;
+ line->gc_group = PBLK_LINEGC_NONE;
+ pblk_line_free(pblk, line);
+ spin_unlock(&line->lock);
+
+ spin_lock(&l_mg->free_lock);
+ list_add_tail(&line->list, &l_mg->free_list);
+ l_mg->nr_free_lines++;
+ spin_unlock(&l_mg->free_lock);
+
+ pblk_rl_free_lines_inc(&pblk->rl, line);
+}
+
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
+{
+ struct nvm_rq *rqd;
+ int err;
+
+ rqd = mempool_alloc(pblk->r_rq_pool, GFP_KERNEL);
+ memset(rqd, 0, pblk_r_rq_size);
+
+ pblk_setup_e_rq(pblk, rqd, ppa);
+
+ rqd->end_io = pblk_end_io_erase;
+ rqd->private = pblk;
+
+ /* The write thread schedules erases so that it minimizes disturbances
+ * with writes. Thus, there is no need to take the LUN semaphore.
+ */
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ pr_err("pblk: could not async erase line:%d,blk:%d\n",
+ pblk_dev_ppa_to_line(ppa),
+ pblk_dev_ppa_to_pos(geo, ppa));
+ }
+
+ return err;
+}
+
+struct pblk_line *pblk_line_get_data(struct pblk *pblk)
+{
+ return pblk->l_mg.data_line;
+}
+
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk)
+{
+ return pblk->l_mg.data_next;
+}
+
+int pblk_line_is_full(struct pblk_line *line)
+{
+ return (line->left_msecs == 0);
+}
+
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list;
+
+ line->emeta->crc = cpu_to_le32(pblk_calc_emeta_crc(pblk, line->emeta));
+
+ if (pblk_line_submit_emeta_io(pblk, line, line->cur_sec, WRITE))
+ pr_err("pblk: line %d close I/O failed\n", line->id);
+
+ WARN(!bitmap_full(line->map_bitmap, line->sec_in_line),
+ "pblk: corrupt closed line %d\n", line->id);
+
+ spin_lock(&l_mg->free_lock);
+ WARN_ON(!test_and_clear_bit(line->meta_line, &l_mg->meta_bitmap));
+ spin_unlock(&l_mg->free_lock);
+
+ spin_lock(&l_mg->gc_lock);
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_OPEN);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+
+ list_add_tail(&line->list, move_list);
+
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+
+ spin_unlock(&line->lock);
+ spin_unlock(&l_mg->gc_lock);
+}
+
+void pblk_line_close_ws(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct pblk_line *line = line_ws->line;
+
+ pblk_line_close(pblk, line);
+ mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_mark_bb(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct ppa_addr *ppa = line_ws->priv;
+ int ret;
+
+ ret = nvm_set_tgt_bb_tbl(dev, ppa, 1, NVM_BLK_T_GRWN_BAD);
+ if (ret) {
+ struct pblk_line *line;
+ int pos;
+
+ line = &pblk->lines[pblk_dev_ppa_to_line(*ppa)];
+ pos = pblk_dev_ppa_to_pos(&dev->geo, *ppa);
+
+ pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+ line->id, pos);
+ }
+
+ kfree(ppa);
+ mempool_free(line_ws, pblk->line_ws_pool);
+}
+
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+ void (*work)(struct work_struct *))
+{
+ struct pblk_line_ws *line_ws;
+
+ line_ws = mempool_alloc(pblk->line_ws_pool, GFP_ATOMIC);
+ if (!line_ws)
+ return;
+
+ line_ws->pblk = pblk;
+ line_ws->line = line;
+ line_ws->priv = priv;
+
+ INIT_WORK(&line_ws->ws, work);
+ queue_work(pblk->kw_wq, &line_ws->ws);
+}
+
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int lun_id = ppa_list[0].g.ch * geo->luns_per_chnl + ppa_list[0].g.lun;
+ int ret;
+
+ /*
+ * Only send one inflight I/O per LUN. Since we map at a page
+ * granurality, all ppas in the I/O will map to the same LUN
+ */
+#ifdef CONFIG_NVM_DEBUG
+ int i;
+
+ for (i = 1; i < nr_ppas; i++)
+ WARN_ON(ppa_list[0].g.lun != ppa_list[i].g.lun ||
+ ppa_list[0].g.ch != ppa_list[i].g.ch);
+#endif
+ /* If the LUN has been locked for this same request, do no attempt to
+ * lock it again
+ */
+ if (test_and_set_bit(lun_id, lun_bitmap))
+ return;
+
+ rlun = &pblk->luns[lun_id];
+ ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(5000));
+ if (ret) {
+ switch (ret) {
+ case -ETIME:
+ pr_err("pblk: lun semaphore timed out\n");
+ break;
+ case -EINTR:
+ pr_err("pblk: lun semaphore timed out\n");
+ break;
+ }
+ }
+}
+
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int nr_luns = geo->nr_luns;
+ int bit = -1;
+
+ while ((bit = find_next_bit(lun_bitmap, nr_luns, bit + 1)) < nr_luns) {
+ rlun = &pblk->luns[bit];
+ up(&rlun->wr_sem);
+ }
+
+ kfree(lun_bitmap);
+}
+
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+ struct ppa_addr l2p_ppa;
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+ if (!pblk_addr_in_cache(l2p_ppa) && !pblk_ppa_empty(l2p_ppa))
+ pblk_map_invalidate(pblk, l2p_ppa);
+
+ pblk_trans_map_set(pblk, lba, ppa);
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
+{
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(!pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+ pblk_update_map(pblk, lba, ppa);
+}
+
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct pblk_line *gc_line)
+{
+ struct ppa_addr l2p_ppa;
+ int ret = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(!pblk_addr_in_cache(ppa));
+ BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
+#endif
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return 0;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_ppa = pblk_trans_map_get(pblk, lba);
+
+ /* Prevent updated entries to be overwritten by GC */
+ if (pblk_addr_in_cache(l2p_ppa) || pblk_ppa_empty(l2p_ppa) ||
+ pblk_tgt_ppa_to_line(l2p_ppa) != gc_line->id) {
+ ret = 0;
+ goto out;
+ }
+
+ pblk_trans_map_set(pblk, lba, ppa);
+out:
+ spin_unlock(&pblk->trans_lock);
+ return ret;
+}
+
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct ppa_addr entry_line)
+{
+ struct ppa_addr l2p_line;
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a device address */
+ BUG_ON(pblk_addr_in_cache(ppa));
+#endif
+ /* Invalidate and discard padded entries */
+ if (lba == ADDR_EMPTY) {
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->padded_wb);
+#endif
+ pblk_map_invalidate(pblk, ppa);
+ return;
+ }
+
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ return;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ l2p_line = pblk_trans_map_get(pblk, lba);
+
+ /* Do not update L2P if the cacheline has been updated. In this case,
+ * the mapped ppa must be invalidated
+ */
+ if (l2p_line.ppa != entry_line.ppa) {
+ if (!pblk_ppa_empty(ppa))
+ pblk_map_invalidate(pblk, ppa);
+ goto out;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ WARN_ON(!pblk_addr_in_cache(l2p_line) && !pblk_ppa_empty(l2p_line));
+#endif
+
+ pblk_trans_map_set(pblk, lba, ppa);
+out:
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+ sector_t blba, int nr_secs)
+{
+ int i;
+
+ spin_lock(&pblk->trans_lock);
+ for (i = 0; i < nr_secs; i++)
+ ppas[i] = pblk_trans_map_get(pblk, blba + i);
+ spin_unlock(&pblk->trans_lock);
+}
+
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+ u64 *lba_list, int nr_secs)
+{
+ sector_t lba;
+ int i;
+
+ spin_lock(&pblk->trans_lock);
+ for (i = 0; i < nr_secs; i++) {
+ lba = lba_list[i];
+ if (lba == ADDR_EMPTY) {
+ ppas[i].ppa = ADDR_EMPTY;
+ } else {
+ /* logic error: lba out-of-bounds. Ignore update */
+ if (!(lba < pblk->rl.nr_secs)) {
+ WARN(1, "pblk: corrupted L2P map request\n");
+ continue;
+ }
+ ppas[i] = pblk_trans_map_get(pblk, lba);
+ }
+ }
+ spin_unlock(&pblk->trans_lock);
+}
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
new file mode 100644
index 000000000000..eaf479c6b63c
--- /dev/null
+++ b/drivers/lightnvm/pblk-gc.c
@@ -0,0 +1,555 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-gc.c - pblk's garbage collector
+ */
+
+#include "pblk.h"
+#include <linux/delay.h>
+
+static void pblk_gc_free_gc_rq(struct pblk_gc_rq *gc_rq)
+{
+ kfree(gc_rq->data);
+ kfree(gc_rq->lba_list);
+ kfree(gc_rq);
+}
+
+static int pblk_gc_write(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_gc_rq *gc_rq, *tgc_rq;
+ LIST_HEAD(w_list);
+
+ spin_lock(&gc->w_lock);
+ if (list_empty(&gc->w_list)) {
+ spin_unlock(&gc->w_lock);
+ return 1;
+ }
+
+ list_for_each_entry_safe(gc_rq, tgc_rq, &gc->w_list, list) {
+ list_move_tail(&gc_rq->list, &w_list);
+ gc->w_entries--;
+ }
+ spin_unlock(&gc->w_lock);
+
+ list_for_each_entry_safe(gc_rq, tgc_rq, &w_list, list) {
+ pblk_write_gc_to_cache(pblk, gc_rq->data, gc_rq->lba_list,
+ gc_rq->nr_secs, gc_rq->secs_to_gc,
+ gc_rq->line, PBLK_IOTYPE_GC);
+
+ kref_put(&gc_rq->line->ref, pblk_line_put);
+
+ list_del(&gc_rq->list);
+ pblk_gc_free_gc_rq(gc_rq);
+ }
+
+ return 0;
+}
+
+static void pblk_gc_writer_kick(struct pblk_gc *gc)
+{
+ wake_up_process(gc->gc_writer_ts);
+}
+
+/*
+ * Responsible for managing all memory related to a gc request. Also in case of
+ * failure
+ */
+static int pblk_gc_move_valid_secs(struct pblk *pblk, struct pblk_line *line,
+ u64 *lba_list, unsigned int nr_secs)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_gc_rq *gc_rq;
+ void *data;
+ unsigned int secs_to_gc;
+ int ret = NVM_IO_OK;
+
+ data = kmalloc(nr_secs * geo->sec_size, GFP_KERNEL);
+ if (!data) {
+ ret = NVM_IO_ERR;
+ goto free_lba_list;
+ }
+
+ /* Read from GC victim block */
+ if (pblk_submit_read_gc(pblk, lba_list, data, nr_secs,
+ &secs_to_gc, line)) {
+ ret = NVM_IO_ERR;
+ goto free_data;
+ }
+
+ if (!secs_to_gc)
+ goto free_data;
+
+ gc_rq = kmalloc(sizeof(struct pblk_gc_rq), GFP_KERNEL);
+ if (!gc_rq) {
+ ret = NVM_IO_ERR;
+ goto free_data;
+ }
+
+ gc_rq->line = line;
+ gc_rq->data = data;
+ gc_rq->lba_list = lba_list;
+ gc_rq->nr_secs = nr_secs;
+ gc_rq->secs_to_gc = secs_to_gc;
+
+ kref_get(&line->ref);
+
+retry:
+ spin_lock(&gc->w_lock);
+ if (gc->w_entries > 256) {
+ spin_unlock(&gc->w_lock);
+ usleep_range(256, 1024);
+ goto retry;
+ }
+ gc->w_entries++;
+ list_add_tail(&gc_rq->list, &gc->w_list);
+ spin_unlock(&gc->w_lock);
+
+ pblk_gc_writer_kick(&pblk->gc);
+
+ return NVM_IO_OK;
+
+free_data:
+ kfree(data);
+free_lba_list:
+ kfree(lba_list);
+
+ return ret;
+}
+
+static void pblk_put_line_back(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct list_head *move_list;
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_GC);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ if (move_list) {
+ spin_lock(&l_mg->gc_lock);
+ list_add_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+ }
+}
+
+static void pblk_gc_line_ws(struct work_struct *work)
+{
+ struct pblk_line_ws *line_ws = container_of(work, struct pblk_line_ws,
+ ws);
+ struct pblk *pblk = line_ws->pblk;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line = line_ws->line;
+ struct pblk_line_meta *lm = &pblk->lm;
+ __le64 *lba_list = line_ws->priv;
+ u64 *gc_list;
+ int sec_left;
+ int nr_ppas, bit;
+ int put_line = 1;
+
+ pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+
+ spin_lock(&line->lock);
+ sec_left = line->vsc;
+ if (!sec_left) {
+ /* Lines are erased before being used (l_mg->data_/log_next) */
+ spin_unlock(&line->lock);
+ goto out;
+ }
+ spin_unlock(&line->lock);
+
+ if (sec_left < 0) {
+ pr_err("pblk: corrupted GC line (%d)\n", line->id);
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ bit = -1;
+next_rq:
+ gc_list = kmalloc_array(pblk->max_write_pgs, sizeof(u64), GFP_KERNEL);
+ if (!gc_list) {
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ nr_ppas = 0;
+ do {
+ bit = find_next_zero_bit(line->invalid_bitmap, lm->sec_per_line,
+ bit + 1);
+ if (bit > line->emeta_ssec)
+ break;
+
+ gc_list[nr_ppas++] = le64_to_cpu(lba_list[bit]);
+ } while (nr_ppas < pblk->max_write_pgs);
+
+ if (unlikely(!nr_ppas)) {
+ kfree(gc_list);
+ goto out;
+ }
+
+ if (pblk_gc_move_valid_secs(pblk, line, gc_list, nr_ppas)) {
+ pr_err("pblk: could not GC all sectors: line:%d (%d/%d/%d)\n",
+ line->id, line->vsc,
+ nr_ppas, nr_ppas);
+ put_line = 0;
+ pblk_put_line_back(pblk, line);
+ goto out;
+ }
+
+ sec_left -= nr_ppas;
+ if (sec_left > 0)
+ goto next_rq;
+
+out:
+ pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+ mempool_free(line_ws, pblk->line_ws_pool);
+ atomic_dec(&pblk->gc.inflight_gc);
+ if (put_line)
+ kref_put(&line->ref, pblk_line_put);
+}
+
+static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_ws *line_ws;
+ __le64 *lba_list;
+ int ret;
+
+ line_ws = mempool_alloc(pblk->line_ws_pool, GFP_KERNEL);
+ line->emeta = pblk_malloc(lm->emeta_len, l_mg->emeta_alloc_type,
+ GFP_KERNEL);
+ if (!line->emeta) {
+ pr_err("pblk: cannot use GC emeta\n");
+ goto fail_free_ws;
+ }
+
+ ret = pblk_line_read_emeta(pblk, line);
+ if (ret) {
+ pr_err("pblk: line %d read emeta failed (%d)\n", line->id, ret);
+ goto fail_free_emeta;
+ }
+
+ /* If this read fails, it means that emeta is corrupted. For now, leave
+ * the line untouched. TODO: Implement a recovery routine that scans and
+ * moves all sectors on the line.
+ */
+ lba_list = pblk_recov_get_lba_list(pblk, line->emeta);
+ if (!lba_list) {
+ pr_err("pblk: could not interpret emeta (line %d)\n", line->id);
+ goto fail_free_emeta;
+ }
+
+ line_ws->pblk = pblk;
+ line_ws->line = line;
+ line_ws->priv = lba_list;
+
+ INIT_WORK(&line_ws->ws, pblk_gc_line_ws);
+ queue_work(pblk->gc.gc_reader_wq, &line_ws->ws);
+
+ return 0;
+
+fail_free_emeta:
+ pblk_mfree(line->emeta, l_mg->emeta_alloc_type);
+fail_free_ws:
+ mempool_free(line_ws, pblk->line_ws_pool);
+ pblk_put_line_back(pblk, line);
+
+ return 1;
+}
+
+static void pblk_gc_lines(struct pblk *pblk, struct list_head *gc_list)
+{
+ struct pblk_line *line, *tline;
+
+ list_for_each_entry_safe(line, tline, gc_list, list) {
+ if (pblk_gc_line(pblk, line))
+ pr_err("pblk: failed to GC line %d\n", line->id);
+ list_del(&line->list);
+ }
+}
+
+/*
+ * Lines with no valid sectors will be returned to the free list immediately. If
+ * GC is activated - either because the free block count is under the determined
+ * threshold, or because it is being forced from user space - only lines with a
+ * high count of invalid sectors will be recycled.
+ */
+static void pblk_gc_run(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_gc *gc = &pblk->gc;
+ struct pblk_line *line, *tline;
+ unsigned int nr_blocks_free, nr_blocks_need;
+ struct list_head *group_list;
+ int run_gc, gc_group = 0;
+ int prev_gc = 0;
+ int inflight_gc = atomic_read(&gc->inflight_gc);
+ LIST_HEAD(gc_list);
+
+ spin_lock(&l_mg->gc_lock);
+ list_for_each_entry_safe(line, tline, &l_mg->gc_full_list, list) {
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+ line->state = PBLK_LINESTATE_GC;
+ spin_unlock(&line->lock);
+
+ list_del(&line->list);
+ kref_put(&line->ref, pblk_line_put);
+ }
+ spin_unlock(&l_mg->gc_lock);
+
+ nr_blocks_need = pblk_rl_gc_thrs(&pblk->rl);
+ nr_blocks_free = pblk_rl_nr_free_blks(&pblk->rl);
+ run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+
+next_gc_group:
+ group_list = l_mg->gc_lists[gc_group++];
+ spin_lock(&l_mg->gc_lock);
+ while (run_gc && !list_empty(group_list)) {
+ /* No need to queue up more GC lines than we can handle */
+ if (!run_gc || inflight_gc > gc->gc_jobs_active) {
+ spin_unlock(&l_mg->gc_lock);
+ pblk_gc_lines(pblk, &gc_list);
+ return;
+ }
+
+ line = list_first_entry(group_list, struct pblk_line, list);
+ nr_blocks_free += atomic_read(&line->blk_in_line);
+
+ spin_lock(&line->lock);
+ WARN_ON(line->state != PBLK_LINESTATE_CLOSED);
+ line->state = PBLK_LINESTATE_GC;
+ list_move_tail(&line->list, &gc_list);
+ atomic_inc(&gc->inflight_gc);
+ inflight_gc++;
+ spin_unlock(&line->lock);
+
+ prev_gc = 1;
+ run_gc = (nr_blocks_need > nr_blocks_free || gc->gc_forced);
+ }
+ spin_unlock(&l_mg->gc_lock);
+
+ pblk_gc_lines(pblk, &gc_list);
+
+ if (!prev_gc && pblk->rl.rb_state > gc_group &&
+ gc_group < PBLK_NR_GC_LISTS)
+ goto next_gc_group;
+}
+
+
+static void pblk_gc_kick(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ wake_up_process(gc->gc_ts);
+ pblk_gc_writer_kick(gc);
+ mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+}
+
+static void pblk_gc_timer(unsigned long data)
+{
+ struct pblk *pblk = (struct pblk *)data;
+
+ pblk_gc_kick(pblk);
+}
+
+static int pblk_gc_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ pblk_gc_run(pblk);
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
+
+static int pblk_gc_writer_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ if (!pblk_gc_write(pblk))
+ continue;
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
+
+static void pblk_gc_start(struct pblk *pblk)
+{
+ pblk->gc.gc_active = 1;
+
+ pr_debug("pblk: gc start\n");
+}
+
+int pblk_gc_status(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int ret;
+
+ spin_lock(&gc->lock);
+ ret = gc->gc_active;
+ spin_unlock(&gc->lock);
+
+ return ret;
+}
+
+static void __pblk_gc_should_start(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ lockdep_assert_held(&gc->lock);
+
+ if (gc->gc_enabled && !gc->gc_active)
+ pblk_gc_start(pblk);
+}
+
+void pblk_gc_should_start(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ spin_lock(&gc->lock);
+ __pblk_gc_should_start(pblk);
+ spin_unlock(&gc->lock);
+}
+
+/*
+ * If flush_wq == 1 then no lock should be held by the caller since
+ * flush_workqueue can sleep
+ */
+static void pblk_gc_stop(struct pblk *pblk, int flush_wq)
+{
+ spin_lock(&pblk->gc.lock);
+ pblk->gc.gc_active = 0;
+ spin_unlock(&pblk->gc.lock);
+
+ pr_debug("pblk: gc stop\n");
+}
+
+void pblk_gc_should_stop(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ if (gc->gc_active && !gc->gc_forced)
+ pblk_gc_stop(pblk, 0);
+}
+
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+ int *gc_active)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ spin_lock(&gc->lock);
+ *gc_enabled = gc->gc_enabled;
+ *gc_active = gc->gc_active;
+ spin_unlock(&gc->lock);
+}
+
+void pblk_gc_sysfs_force(struct pblk *pblk, int force)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int rsv = 0;
+
+ spin_lock(&gc->lock);
+ if (force) {
+ gc->gc_enabled = 1;
+ rsv = 64;
+ }
+ pblk_rl_set_gc_rsc(&pblk->rl, rsv);
+ gc->gc_forced = force;
+ __pblk_gc_should_start(pblk);
+ spin_unlock(&gc->lock);
+}
+
+int pblk_gc_init(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ int ret;
+
+ gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
+ if (IS_ERR(gc->gc_ts)) {
+ pr_err("pblk: could not allocate GC main kthread\n");
+ return PTR_ERR(gc->gc_ts);
+ }
+
+ gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
+ "pblk-gc-writer-ts");
+ if (IS_ERR(gc->gc_writer_ts)) {
+ pr_err("pblk: could not allocate GC writer kthread\n");
+ ret = PTR_ERR(gc->gc_writer_ts);
+ goto fail_free_main_kthread;
+ }
+
+ setup_timer(&gc->gc_timer, pblk_gc_timer, (unsigned long)pblk);
+ mod_timer(&gc->gc_timer, jiffies + msecs_to_jiffies(GC_TIME_MSECS));
+
+ gc->gc_active = 0;
+ gc->gc_forced = 0;
+ gc->gc_enabled = 1;
+ gc->gc_jobs_active = 8;
+ gc->w_entries = 0;
+ atomic_set(&gc->inflight_gc, 0);
+
+ gc->gc_reader_wq = alloc_workqueue("pblk-gc-reader-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, gc->gc_jobs_active);
+ if (!gc->gc_reader_wq) {
+ pr_err("pblk: could not allocate GC reader workqueue\n");
+ ret = -ENOMEM;
+ goto fail_free_writer_kthread;
+ }
+
+ spin_lock_init(&gc->lock);
+ spin_lock_init(&gc->w_lock);
+ INIT_LIST_HEAD(&gc->w_list);
+
+ return 0;
+
+fail_free_writer_kthread:
+ kthread_stop(gc->gc_writer_ts);
+fail_free_main_kthread:
+ kthread_stop(gc->gc_ts);
+
+ return ret;
+}
+
+void pblk_gc_exit(struct pblk *pblk)
+{
+ struct pblk_gc *gc = &pblk->gc;
+
+ flush_workqueue(gc->gc_reader_wq);
+
+ del_timer(&gc->gc_timer);
+ pblk_gc_stop(pblk, 1);
+
+ if (gc->gc_ts)
+ kthread_stop(gc->gc_ts);
+
+ if (pblk->gc.gc_reader_wq)
+ destroy_workqueue(pblk->gc.gc_reader_wq);
+
+ if (gc->gc_writer_ts)
+ kthread_stop(gc->gc_writer_ts);
+}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
new file mode 100644
index 000000000000..ae8cd6d5af8b
--- /dev/null
+++ b/drivers/lightnvm/pblk-init.c
@@ -0,0 +1,962 @@
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.c)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-init.c - pblk's initialization.
+ */
+
+#include "pblk.h"
+
+static struct kmem_cache *pblk_blk_ws_cache, *pblk_rec_cache, *pblk_r_rq_cache,
+ *pblk_w_rq_cache, *pblk_line_meta_cache;
+static DECLARE_RWSEM(pblk_lock);
+
+static int pblk_rw_io(struct request_queue *q, struct pblk *pblk,
+ struct bio *bio)
+{
+ int ret;
+
+ /* Read requests must be <= 256kb due to NVMe's 64 bit completion bitmap
+ * constraint. Writes can be of arbitrary size.
+ */
+ if (bio_data_dir(bio) == READ) {
+ blk_queue_split(q, &bio, q->bio_split);
+ ret = pblk_submit_read(pblk, bio);
+ if (ret == NVM_IO_DONE && bio_flagged(bio, BIO_CLONED))
+ bio_put(bio);
+
+ return ret;
+ }
+
+ /* Prevent deadlock in the case of a modest LUN configuration and large
+ * user I/Os. Unless stalled, the rate limiter leaves at least 256KB
+ * available for user I/O.
+ */
+ if (unlikely(pblk_get_secs(bio) >= pblk_rl_sysfs_rate_show(&pblk->rl)))
+ blk_queue_split(q, &bio, q->bio_split);
+
+ return pblk_write_to_cache(pblk, bio, PBLK_IOTYPE_USER);
+}
+
+static blk_qc_t pblk_make_rq(struct request_queue *q, struct bio *bio)
+{
+ struct pblk *pblk = q->queuedata;
+
+ if (bio_op(bio) == REQ_OP_DISCARD) {
+ pblk_discard(pblk, bio);
+ if (!(bio->bi_opf & REQ_PREFLUSH)) {
+ bio_endio(bio);
+ return BLK_QC_T_NONE;
+ }
+ }
+
+ switch (pblk_rw_io(q, pblk, bio)) {
+ case NVM_IO_ERR:
+ bio_io_error(bio);
+ break;
+ case NVM_IO_DONE:
+ bio_endio(bio);
+ break;
+ }
+
+ return BLK_QC_T_NONE;
+}
+
+static void pblk_l2p_free(struct pblk *pblk)
+{
+ vfree(pblk->trans_map);
+}
+
+static int pblk_l2p_init(struct pblk *pblk)
+{
+ sector_t i;
+ struct ppa_addr ppa;
+ int entry_size = 8;
+
+ if (pblk->ppaf_bitsize < 32)
+ entry_size = 4;
+
+ pblk->trans_map = vmalloc(entry_size * pblk->rl.nr_secs);
+ if (!pblk->trans_map)
+ return -ENOMEM;
+
+ pblk_ppa_set_empty(&ppa);
+
+ for (i = 0; i < pblk->rl.nr_secs; i++)
+ pblk_trans_map_set(pblk, i, ppa);
+
+ return 0;
+}
+
+static void pblk_rwb_free(struct pblk *pblk)
+{
+ if (pblk_rb_tear_down_check(&pblk->rwb))
+ pr_err("pblk: write buffer error on tear down\n");
+
+ pblk_rb_data_free(&pblk->rwb);
+ vfree(pblk_rb_entries_ref(&pblk->rwb));
+}
+
+static int pblk_rwb_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_rb_entry *entries;
+ unsigned long nr_entries;
+ unsigned int power_size, power_seg_sz;
+
+ nr_entries = pblk_rb_calculate_size(pblk->pgs_in_buffer);
+
+ entries = vzalloc(nr_entries * sizeof(struct pblk_rb_entry));
+ if (!entries)
+ return -ENOMEM;
+
+ power_size = get_count_order(nr_entries);
+ power_seg_sz = get_count_order(geo->sec_size);
+
+ return pblk_rb_init(&pblk->rwb, entries, power_size, power_seg_sz);
+}
+
+/* Minimum pages needed within a lun */
+#define PAGE_POOL_SIZE 16
+#define ADDR_POOL_SIZE 64
+
+static int pblk_set_ppaf(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct nvm_addr_format ppaf = geo->ppaf;
+ int power_len;
+
+ /* Re-calculate channel and lun format to adapt to configuration */
+ power_len = get_count_order(geo->nr_chnls);
+ if (1 << power_len != geo->nr_chnls) {
+ pr_err("pblk: supports only power-of-two channel config.\n");
+ return -EINVAL;
+ }
+ ppaf.ch_len = power_len;
+
+ power_len = get_count_order(geo->luns_per_chnl);
+ if (1 << power_len != geo->luns_per_chnl) {
+ pr_err("pblk: supports only power-of-two LUN config.\n");
+ return -EINVAL;
+ }
+ ppaf.lun_len = power_len;
+
+ pblk->ppaf.sec_offset = 0;
+ pblk->ppaf.pln_offset = ppaf.sect_len;
+ pblk->ppaf.ch_offset = pblk->ppaf.pln_offset + ppaf.pln_len;
+ pblk->ppaf.lun_offset = pblk->ppaf.ch_offset + ppaf.ch_len;
+ pblk->ppaf.pg_offset = pblk->ppaf.lun_offset + ppaf.lun_len;
+ pblk->ppaf.blk_offset = pblk->ppaf.pg_offset + ppaf.pg_len;
+ pblk->ppaf.sec_mask = (1ULL << ppaf.sect_len) - 1;
+ pblk->ppaf.pln_mask = ((1ULL << ppaf.pln_len) - 1) <<
+ pblk->ppaf.pln_offset;
+ pblk->ppaf.ch_mask = ((1ULL << ppaf.ch_len) - 1) <<
+ pblk->ppaf.ch_offset;
+ pblk->ppaf.lun_mask = ((1ULL << ppaf.lun_len) - 1) <<
+ pblk->ppaf.lun_offset;
+ pblk->ppaf.pg_mask = ((1ULL << ppaf.pg_len) - 1) <<
+ pblk->ppaf.pg_offset;
+ pblk->ppaf.blk_mask = ((1ULL << ppaf.blk_len) - 1) <<
+ pblk->ppaf.blk_offset;
+
+ pblk->ppaf_bitsize = pblk->ppaf.blk_offset + ppaf.blk_len;
+
+ return 0;
+}
+
+static int pblk_init_global_caches(struct pblk *pblk)
+{
+ char cache_name[PBLK_CACHE_NAME_LEN];
+
+ down_write(&pblk_lock);
+ pblk_blk_ws_cache = kmem_cache_create("pblk_blk_ws",
+ sizeof(struct pblk_line_ws), 0, 0, NULL);
+ if (!pblk_blk_ws_cache) {
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_rec_cache = kmem_cache_create("pblk_rec",
+ sizeof(struct pblk_rec_ctx), 0, 0, NULL);
+ if (!pblk_rec_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_r_rq_cache = kmem_cache_create("pblk_r_rq", pblk_r_rq_size,
+ 0, 0, NULL);
+ if (!pblk_r_rq_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ pblk_w_rq_cache = kmem_cache_create("pblk_w_rq", pblk_w_rq_size,
+ 0, 0, NULL);
+ if (!pblk_w_rq_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+
+ snprintf(cache_name, sizeof(cache_name), "pblk_line_m_%s",
+ pblk->disk->disk_name);
+ pblk_line_meta_cache = kmem_cache_create(cache_name,
+ pblk->lm.sec_bitmap_len, 0, 0, NULL);
+ if (!pblk_line_meta_cache) {
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ kmem_cache_destroy(pblk_w_rq_cache);
+ up_write(&pblk_lock);
+ return -ENOMEM;
+ }
+ up_write(&pblk_lock);
+
+ return 0;
+}
+
+static int pblk_core_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int max_write_ppas;
+ int mod;
+
+ pblk->min_write_pgs = geo->sec_per_pl * (geo->sec_size / PAGE_SIZE);
+ max_write_ppas = pblk->min_write_pgs * geo->nr_luns;
+ pblk->max_write_pgs = (max_write_ppas < nvm_max_phys_sects(dev)) ?
+ max_write_ppas : nvm_max_phys_sects(dev);
+ pblk->pgs_in_buffer = NVM_MEM_PAGE_WRITE * geo->sec_per_pg *
+ geo->nr_planes * geo->nr_luns;
+
+ if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
+ pr_err("pblk: cannot support device max_phys_sect\n");
+ return -EINVAL;
+ }
+
+ div_u64_rem(geo->sec_per_blk, pblk->min_write_pgs, &mod);
+ if (mod) {
+ pr_err("pblk: bad configuration of sectors/pages\n");
+ return -EINVAL;
+ }
+
+ if (pblk_init_global_caches(pblk))
+ return -ENOMEM;
+
+ pblk->page_pool = mempool_create_page_pool(PAGE_POOL_SIZE, 0);
+ if (!pblk->page_pool)
+ return -ENOMEM;
+
+ pblk->line_ws_pool = mempool_create_slab_pool(geo->nr_luns,
+ pblk_blk_ws_cache);
+ if (!pblk->line_ws_pool)
+ goto free_page_pool;
+
+ pblk->rec_pool = mempool_create_slab_pool(geo->nr_luns, pblk_rec_cache);
+ if (!pblk->rec_pool)
+ goto free_blk_ws_pool;
+
+ pblk->r_rq_pool = mempool_create_slab_pool(64, pblk_r_rq_cache);
+ if (!pblk->r_rq_pool)
+ goto free_rec_pool;
+
+ pblk->w_rq_pool = mempool_create_slab_pool(64, pblk_w_rq_cache);
+ if (!pblk->w_rq_pool)
+ goto free_r_rq_pool;
+
+ pblk->line_meta_pool =
+ mempool_create_slab_pool(16, pblk_line_meta_cache);
+ if (!pblk->line_meta_pool)
+ goto free_w_rq_pool;
+
+ pblk->kw_wq = alloc_workqueue("pblk-aux-wq",
+ WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+ if (!pblk->kw_wq)
+ goto free_line_meta_pool;
+
+ if (pblk_set_ppaf(pblk))
+ goto free_kw_wq;
+
+ if (pblk_rwb_init(pblk))
+ goto free_kw_wq;
+
+ INIT_LIST_HEAD(&pblk->compl_list);
+ return 0;
+
+free_kw_wq:
+ destroy_workqueue(pblk->kw_wq);
+free_line_meta_pool:
+ mempool_destroy(pblk->line_meta_pool);
+free_w_rq_pool:
+ mempool_destroy(pblk->w_rq_pool);
+free_r_rq_pool:
+ mempool_destroy(pblk->r_rq_pool);
+free_rec_pool:
+ mempool_destroy(pblk->rec_pool);
+free_blk_ws_pool:
+ mempool_destroy(pblk->line_ws_pool);
+free_page_pool:
+ mempool_destroy(pblk->page_pool);
+ return -ENOMEM;
+}
+
+static void pblk_core_free(struct pblk *pblk)
+{
+ if (pblk->kw_wq)
+ destroy_workqueue(pblk->kw_wq);
+
+ mempool_destroy(pblk->page_pool);
+ mempool_destroy(pblk->line_ws_pool);
+ mempool_destroy(pblk->rec_pool);
+ mempool_destroy(pblk->r_rq_pool);
+ mempool_destroy(pblk->w_rq_pool);
+ mempool_destroy(pblk->line_meta_pool);
+
+ kmem_cache_destroy(pblk_blk_ws_cache);
+ kmem_cache_destroy(pblk_rec_cache);
+ kmem_cache_destroy(pblk_r_rq_cache);
+ kmem_cache_destroy(pblk_w_rq_cache);
+ kmem_cache_destroy(pblk_line_meta_cache);
+}
+
+static void pblk_luns_free(struct pblk *pblk)
+{
+ kfree(pblk->luns);
+}
+
+static void pblk_lines_free(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ int i;
+
+ spin_lock(&l_mg->free_lock);
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ line = &pblk->lines[i];
+
+ pblk_line_free(pblk, line);
+ kfree(line->blk_bitmap);
+ kfree(line->erase_bitmap);
+ }
+ spin_unlock(&l_mg->free_lock);
+}
+
+static void pblk_line_meta_free(struct pblk *pblk)
+{
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ int i;
+
+ kfree(l_mg->bb_template);
+ kfree(l_mg->bb_aux);
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+ pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+ }
+
+ kfree(pblk->lines);
+}
+
+static int pblk_bb_discovery(struct nvm_tgt_dev *dev, struct pblk_lun *rlun)
+{
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr ppa;
+ u8 *blks;
+ int nr_blks, ret;
+
+ nr_blks = geo->blks_per_lun * geo->plane_mode;
+ blks = kmalloc(nr_blks, GFP_KERNEL);
+ if (!blks)
+ return -ENOMEM;
+
+ ppa.ppa = 0;
+ ppa.g.ch = rlun->bppa.g.ch;
+ ppa.g.lun = rlun->bppa.g.lun;
+
+ ret = nvm_get_tgt_bb_tbl(dev, ppa, blks);
+ if (ret)
+ goto out;
+
+ nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
+ if (nr_blks < 0) {
+ ret = nr_blks;
+ goto out;
+ }
+
+ rlun->bb_list = blks;
+
+ return 0;
+out:
+ kfree(blks);
+ return ret;
+}
+
+static int pblk_bb_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_lun *rlun;
+ int bb_cnt = 0;
+ int i;
+
+ line->blk_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+ if (!line->blk_bitmap)
+ return -ENOMEM;
+
+ line->erase_bitmap = kzalloc(lm->blk_bitmap_len, GFP_KERNEL);
+ if (!line->erase_bitmap) {
+ kfree(line->blk_bitmap);
+ return -ENOMEM;
+ }
+
+ for (i = 0; i < lm->blk_per_line; i++) {
+ rlun = &pblk->luns[i];
+ if (rlun->bb_list[line->id] == NVM_BLK_T_FREE)
+ continue;
+
+ set_bit(i, line->blk_bitmap);
+ bb_cnt++;
+ }
+
+ return bb_cnt;
+}
+
+static int pblk_luns_init(struct pblk *pblk, struct ppa_addr *luns)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ int i, ret;
+
+ /* TODO: Implement unbalanced LUN support */
+ if (geo->luns_per_chnl < 0) {
+ pr_err("pblk: unbalanced LUN config.\n");
+ return -EINVAL;
+ }
+
+ pblk->luns = kcalloc(geo->nr_luns, sizeof(struct pblk_lun), GFP_KERNEL);
+ if (!pblk->luns)
+ return -ENOMEM;
+
+ for (i = 0; i < geo->nr_luns; i++) {
+ /* Stripe across channels */
+ int ch = i % geo->nr_chnls;
+ int lun_raw = i / geo->nr_chnls;
+ int lunid = lun_raw + ch * geo->luns_per_chnl;
+
+ rlun = &pblk->luns[i];
+ rlun->bppa = luns[lunid];
+
+ sema_init(&rlun->wr_sem, 1);
+
+ ret = pblk_bb_discovery(dev, rlun);
+ if (ret) {
+ while (--i >= 0)
+ kfree(pblk->luns[i].bb_list);
+ return ret;
+ }
+ }
+
+ return 0;
+}
+
+static int pblk_lines_configure(struct pblk *pblk, int flags)
+{
+ struct pblk_line *line = NULL;
+ int ret = 0;
+
+ if (!(flags & NVM_TARGET_FACTORY)) {
+ line = pblk_recov_l2p(pblk);
+ if (IS_ERR(line)) {
+ pr_err("pblk: could not recover l2p table\n");
+ ret = -EFAULT;
+ }
+ }
+
+ if (!line) {
+ /* Configure next line for user data */
+ line = pblk_line_get_first_data(pblk);
+ if (!line) {
+ pr_err("pblk: line list corrupted\n");
+ ret = -EFAULT;
+ }
+ }
+
+ return ret;
+}
+
+/* See comment over struct line_emeta definition */
+static unsigned int calc_emeta_len(struct pblk *pblk, struct pblk_line_meta *lm)
+{
+ return (sizeof(struct line_emeta) +
+ ((lm->sec_per_line - lm->emeta_sec) * sizeof(u64)) +
+ (pblk->l_mg.nr_lines * sizeof(u32)) +
+ lm->blk_bitmap_len);
+}
+
+static void pblk_set_provision(struct pblk *pblk, long nr_free_blks)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ sector_t provisioned;
+
+ pblk->over_pct = 20;
+
+ provisioned = nr_free_blks;
+ provisioned *= (100 - pblk->over_pct);
+ sector_div(provisioned, 100);
+
+ /* Internally pblk manages all free blocks, but all calculations based
+ * on user capacity consider only provisioned blocks
+ */
+ pblk->rl.total_blocks = nr_free_blks;
+ pblk->rl.nr_secs = nr_free_blks * geo->sec_per_blk;
+ pblk->capacity = provisioned * geo->sec_per_blk;
+ atomic_set(&pblk->rl.free_blocks, nr_free_blks);
+}
+
+static int pblk_lines_init(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *line;
+ unsigned int smeta_len, emeta_len;
+ long nr_bad_blks, nr_meta_blks, nr_free_blks;
+ int bb_distance;
+ int i;
+ int ret;
+
+ lm->sec_per_line = geo->sec_per_blk * geo->nr_luns;
+ lm->blk_per_line = geo->nr_luns;
+ lm->blk_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+ lm->sec_bitmap_len = BITS_TO_LONGS(lm->sec_per_line) * sizeof(long);
+ lm->lun_bitmap_len = BITS_TO_LONGS(geo->nr_luns) * sizeof(long);
+ lm->high_thrs = lm->sec_per_line / 2;
+ lm->mid_thrs = lm->sec_per_line / 4;
+
+ /* Calculate necessary pages for smeta. See comment over struct
+ * line_smeta definition
+ */
+ lm->smeta_len = sizeof(struct line_smeta) +
+ PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+
+ i = 1;
+add_smeta_page:
+ lm->smeta_sec = i * geo->sec_per_pl;
+ lm->smeta_len = lm->smeta_sec * geo->sec_size;
+
+ smeta_len = sizeof(struct line_smeta) +
+ PBLK_LINE_NR_LUN_BITMAP * lm->lun_bitmap_len;
+ if (smeta_len > lm->smeta_len) {
+ i++;
+ goto add_smeta_page;
+ }
+
+ /* Calculate necessary pages for emeta. See comment over struct
+ * line_emeta definition
+ */
+ i = 1;
+add_emeta_page:
+ lm->emeta_sec = i * geo->sec_per_pl;
+ lm->emeta_len = lm->emeta_sec * geo->sec_size;
+
+ emeta_len = calc_emeta_len(pblk, lm);
+ if (emeta_len > lm->emeta_len) {
+ i++;
+ goto add_emeta_page;
+ }
+ lm->emeta_bb = geo->nr_luns - i;
+
+ nr_meta_blks = (lm->smeta_sec + lm->emeta_sec +
+ (geo->sec_per_blk / 2)) / geo->sec_per_blk;
+ lm->min_blk_line = nr_meta_blks + 1;
+
+ l_mg->nr_lines = geo->blks_per_lun;
+ l_mg->log_line = l_mg->data_line = NULL;
+ l_mg->l_seq_nr = l_mg->d_seq_nr = 0;
+ l_mg->nr_free_lines = 0;
+ bitmap_zero(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+
+ /* smeta is always small enough to fit on a kmalloc memory allocation,
+ * emeta depends on the number of LUNs allocated to the pblk instance
+ */
+ l_mg->smeta_alloc_type = PBLK_KMALLOC_META;
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->sline_meta[i].meta = kmalloc(lm->smeta_len, GFP_KERNEL);
+ if (!l_mg->sline_meta[i].meta)
+ while (--i >= 0) {
+ kfree(l_mg->sline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+
+ if (lm->emeta_len > KMALLOC_MAX_CACHE_SIZE) {
+ l_mg->emeta_alloc_type = PBLK_VMALLOC_META;
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->eline_meta[i].meta = vmalloc(lm->emeta_len);
+ if (!l_mg->eline_meta[i].meta)
+ while (--i >= 0) {
+ vfree(l_mg->eline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+ } else {
+ l_mg->emeta_alloc_type = PBLK_KMALLOC_META;
+
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ l_mg->eline_meta[i].meta =
+ kmalloc(lm->emeta_len, GFP_KERNEL);
+ if (!l_mg->eline_meta[i].meta)
+ while (--i >= 0) {
+ kfree(l_mg->eline_meta[i].meta);
+ ret = -ENOMEM;
+ goto fail;
+ }
+ }
+ }
+
+ l_mg->bb_template = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!l_mg->bb_template) {
+ ret = -ENOMEM;
+ goto fail_free_meta;
+ }
+
+ l_mg->bb_aux = kzalloc(lm->sec_bitmap_len, GFP_KERNEL);
+ if (!l_mg->bb_aux) {
+ ret = -ENOMEM;
+ goto fail_free_bb_template;
+ }
+
+ bb_distance = (geo->nr_luns) * geo->sec_per_pl;
+ for (i = 0; i < lm->sec_per_line; i += bb_distance)
+ bitmap_set(l_mg->bb_template, i, geo->sec_per_pl);
+
+ INIT_LIST_HEAD(&l_mg->free_list);
+ INIT_LIST_HEAD(&l_mg->corrupt_list);
+ INIT_LIST_HEAD(&l_mg->bad_list);
+ INIT_LIST_HEAD(&l_mg->gc_full_list);
+ INIT_LIST_HEAD(&l_mg->gc_high_list);
+ INIT_LIST_HEAD(&l_mg->gc_mid_list);
+ INIT_LIST_HEAD(&l_mg->gc_low_list);
+ INIT_LIST_HEAD(&l_mg->gc_empty_list);
+
+ l_mg->gc_lists[0] = &l_mg->gc_high_list;
+ l_mg->gc_lists[1] = &l_mg->gc_mid_list;
+ l_mg->gc_lists[2] = &l_mg->gc_low_list;
+
+ spin_lock_init(&l_mg->free_lock);
+ spin_lock_init(&l_mg->gc_lock);
+
+ pblk->lines = kcalloc(l_mg->nr_lines, sizeof(struct pblk_line),
+ GFP_KERNEL);
+ if (!pblk->lines) {
+ ret = -ENOMEM;
+ goto fail_free_bb_aux;
+ }
+
+ nr_free_blks = 0;
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ int blk_in_line;
+
+ line = &pblk->lines[i];
+
+ line->pblk = pblk;
+ line->id = i;
+ line->type = PBLK_LINETYPE_FREE;
+ line->state = PBLK_LINESTATE_FREE;
+ line->gc_group = PBLK_LINEGC_NONE;
+ spin_lock_init(&line->lock);
+
+ nr_bad_blks = pblk_bb_line(pblk, line);
+ if (nr_bad_blks < 0 || nr_bad_blks > lm->blk_per_line) {
+ ret = -EINVAL;
+ goto fail_free_lines;
+ }
+
+ blk_in_line = lm->blk_per_line - nr_bad_blks;
+ if (blk_in_line < lm->min_blk_line) {
+ line->state = PBLK_LINESTATE_BAD;
+ list_add_tail(&line->list, &l_mg->bad_list);
+ continue;
+ }
+
+ nr_free_blks += blk_in_line;
+ atomic_set(&line->blk_in_line, blk_in_line);
+
+ l_mg->nr_free_lines++;
+ list_add_tail(&line->list, &l_mg->free_list);
+ }
+
+ pblk_set_provision(pblk, nr_free_blks);
+
+ sema_init(&pblk->erase_sem, 1);
+
+ /* Cleanup per-LUN bad block lists - managed within lines on run-time */
+ for (i = 0; i < geo->nr_luns; i++)
+ kfree(pblk->luns[i].bb_list);
+
+ return 0;
+fail_free_lines:
+ kfree(pblk->lines);
+fail_free_bb_aux:
+ kfree(l_mg->bb_aux);
+fail_free_bb_template:
+ kfree(l_mg->bb_template);
+fail_free_meta:
+ for (i = 0; i < PBLK_DATA_LINES; i++) {
+ pblk_mfree(l_mg->sline_meta[i].meta, l_mg->smeta_alloc_type);
+ pblk_mfree(l_mg->eline_meta[i].meta, l_mg->emeta_alloc_type);
+ }
+fail:
+ for (i = 0; i < geo->nr_luns; i++)
+ kfree(pblk->luns[i].bb_list);
+
+ return ret;
+}
+
+static int pblk_writer_init(struct pblk *pblk)
+{
+ setup_timer(&pblk->wtimer, pblk_write_timer_fn, (unsigned long)pblk);
+ mod_timer(&pblk->wtimer, jiffies + msecs_to_jiffies(100));
+
+ pblk->writer_ts = kthread_create(pblk_write_ts, pblk, "pblk-writer-t");
+ if (IS_ERR(pblk->writer_ts)) {
+ pr_err("pblk: could not allocate writer kthread\n");
+ return PTR_ERR(pblk->writer_ts);
+ }
+
+ return 0;
+}
+
+static void pblk_writer_stop(struct pblk *pblk)
+{
+ if (pblk->writer_ts)
+ kthread_stop(pblk->writer_ts);
+ del_timer(&pblk->wtimer);
+}
+
+static void pblk_free(struct pblk *pblk)
+{
+ pblk_luns_free(pblk);
+ pblk_lines_free(pblk);
+ pblk_line_meta_free(pblk);
+ pblk_core_free(pblk);
+ pblk_l2p_free(pblk);
+
+ kfree(pblk);
+}
+
+static void pblk_tear_down(struct pblk *pblk)
+{
+ pblk_flush_writer(pblk);
+ pblk_writer_stop(pblk);
+ pblk_rb_sync_l2p(&pblk->rwb);
+ pblk_recov_pad(pblk);
+ pblk_rwb_free(pblk);
+ pblk_rl_free(&pblk->rl);
+
+ pr_debug("pblk: consistent tear down\n");
+}
+
+static void pblk_exit(void *private)
+{
+ struct pblk *pblk = private;
+
+ down_write(&pblk_lock);
+ pblk_gc_exit(pblk);
+ pblk_tear_down(pblk);
+ pblk_free(pblk);
+ up_write(&pblk_lock);
+}
+
+static sector_t pblk_capacity(void *private)
+{
+ struct pblk *pblk = private;
+
+ return pblk->capacity * NR_PHY_IN_LOG;
+}
+
+static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+ int flags)
+{
+ struct nvm_geo *geo = &dev->geo;
+ struct request_queue *bqueue = dev->q;
+ struct request_queue *tqueue = tdisk->queue;
+ struct pblk *pblk;
+ int ret;
+
+ if (dev->identity.dom & NVM_RSP_L2P) {
+ pr_err("pblk: device-side L2P table not supported. (%x)\n",
+ dev->identity.dom);
+ return ERR_PTR(-EINVAL);
+ }
+
+ pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+ if (!pblk)
+ return ERR_PTR(-ENOMEM);
+
+ pblk->dev = dev;
+ pblk->disk = tdisk;
+
+ spin_lock_init(&pblk->trans_lock);
+ spin_lock_init(&pblk->lock);
+
+ if (flags & NVM_TARGET_FACTORY)
+ pblk_setup_uuid(pblk);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_set(&pblk->inflight_writes, 0);
+ atomic_long_set(&pblk->padded_writes, 0);
+ atomic_long_set(&pblk->padded_wb, 0);
+ atomic_long_set(&pblk->nr_flush, 0);
+ atomic_long_set(&pblk->req_writes, 0);
+ atomic_long_set(&pblk->sub_writes, 0);
+ atomic_long_set(&pblk->sync_writes, 0);
+ atomic_long_set(&pblk->compl_writes, 0);
+ atomic_long_set(&pblk->inflight_reads, 0);
+ atomic_long_set(&pblk->sync_reads, 0);
+ atomic_long_set(&pblk->recov_writes, 0);
+ atomic_long_set(&pblk->recov_writes, 0);
+ atomic_long_set(&pblk->recov_gc_writes, 0);
+#endif
+
+ atomic_long_set(&pblk->read_failed, 0);
+ atomic_long_set(&pblk->read_empty, 0);
+ atomic_long_set(&pblk->read_high_ecc, 0);
+ atomic_long_set(&pblk->read_failed_gc, 0);
+ atomic_long_set(&pblk->write_failed, 0);
+ atomic_long_set(&pblk->erase_failed, 0);
+
+ ret = pblk_luns_init(pblk, dev->luns);
+ if (ret) {
+ pr_err("pblk: could not initialize luns\n");
+ goto fail;
+ }
+
+ ret = pblk_lines_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize lines\n");
+ goto fail_free_luns;
+ }
+
+ ret = pblk_core_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize core\n");
+ goto fail_free_line_meta;
+ }
+
+ ret = pblk_l2p_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize maps\n");
+ goto fail_free_core;
+ }
+
+ ret = pblk_lines_configure(pblk, flags);
+ if (ret) {
+ pr_err("pblk: could not configure lines\n");
+ goto fail_free_l2p;
+ }
+
+ ret = pblk_writer_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize write thread\n");
+ goto fail_free_lines;
+ }
+
+ ret = pblk_gc_init(pblk);
+ if (ret) {
+ pr_err("pblk: could not initialize gc\n");
+ goto fail_stop_writer;
+ }
+
+ /* inherit the size from the underlying device */
+ blk_queue_logical_block_size(tqueue, queue_physical_block_size(bqueue));
+ blk_queue_max_hw_sectors(tqueue, queue_max_hw_sectors(bqueue));
+
+ blk_queue_write_cache(tqueue, true, false);
+
+ tqueue->limits.discard_granularity = geo->pgs_per_blk * geo->pfpg_size;
+ tqueue->limits.discard_alignment = 0;
+ blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, tqueue);
+
+ pr_info("pblk init: luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
+ geo->nr_luns, pblk->l_mg.nr_lines,
+ (unsigned long long)pblk->rl.nr_secs,
+ pblk->rwb.nr_entries);
+
+ wake_up_process(pblk->writer_ts);
+ return pblk;
+
+fail_stop_writer:
+ pblk_writer_stop(pblk);
+fail_free_lines:
+ pblk_lines_free(pblk);
+fail_free_l2p:
+ pblk_l2p_free(pblk);
+fail_free_core:
+ pblk_core_free(pblk);
+fail_free_line_meta:
+ pblk_line_meta_free(pblk);
+fail_free_luns:
+ pblk_luns_free(pblk);
+fail:
+ kfree(pblk);
+ return ERR_PTR(ret);
+}
+
+/* physical block device target */
+static struct nvm_tgt_type tt_pblk = {
+ .name = "pblk",
+ .version = {1, 0, 0},
+
+ .make_rq = pblk_make_rq,
+ .capacity = pblk_capacity,
+
+ .init = pblk_init,
+ .exit = pblk_exit,
+
+ .sysfs_init = pblk_sysfs_init,
+ .sysfs_exit = pblk_sysfs_exit,
+};
+
+static int __init pblk_module_init(void)
+{
+ return nvm_register_tgt_type(&tt_pblk);
+}
+
+static void pblk_module_exit(void)
+{
+ nvm_unregister_tgt_type(&tt_pblk);
+}
+
+module_init(pblk_module_init);
+module_exit(pblk_module_exit);
+MODULE_AUTHOR("Javier Gonzalez <javier@cnexlabs.com>");
+MODULE_AUTHOR("Matias Bjorling <matias@cnexlabs.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Physical Block-Device for Open-Channel SSDs");
diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c
new file mode 100644
index 000000000000..17c16955284d
--- /dev/null
+++ b/drivers/lightnvm/pblk-map.c
@@ -0,0 +1,136 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-map.c - pblk's lba-ppa mapping strategy
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_map_page_data(struct pblk *pblk, unsigned int sentry,
+ struct ppa_addr *ppa_list,
+ unsigned long *lun_bitmap,
+ struct pblk_sec_meta *meta_list,
+ unsigned int valid_secs)
+{
+ struct pblk_line *line = pblk_line_get_data(pblk);
+ struct line_emeta *emeta = line->emeta;
+ struct pblk_w_ctx *w_ctx;
+ __le64 *lba_list = pblk_line_emeta_to_lbas(emeta);
+ u64 paddr;
+ int nr_secs = pblk->min_write_pgs;
+ int i;
+
+ paddr = pblk_alloc_page(pblk, line, nr_secs);
+
+ for (i = 0; i < nr_secs; i++, paddr++) {
+ /* ppa to be sent to the device */
+ ppa_list[i] = addr_to_gen_ppa(pblk, paddr, line->id);
+
+ /* Write context for target bio completion on write buffer. Note
+ * that the write buffer is protected by the sync backpointer,
+ * and a single writer thread have access to each specific entry
+ * at a time. Thus, it is safe to modify the context for the
+ * entry we are setting up for submission without taking any
+ * lock or memory barrier.
+ */
+ if (i < valid_secs) {
+ kref_get(&line->ref);
+ w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i);
+ w_ctx->ppa = ppa_list[i];
+ meta_list[i].lba = cpu_to_le64(w_ctx->lba);
+ lba_list[paddr] = cpu_to_le64(w_ctx->lba);
+ le64_add_cpu(&line->emeta->nr_valid_lbas, 1);
+ } else {
+ meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+ lba_list[paddr] = cpu_to_le64(ADDR_EMPTY);
+ pblk_map_pad_invalidate(pblk, line, paddr);
+ }
+ }
+
+ if (pblk_line_is_full(line)) {
+ line = pblk_line_replace_data(pblk);
+ if (!line)
+ return;
+ }
+
+ pblk_down_rq(pblk, ppa_list, nr_secs, lun_bitmap);
+}
+
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+ unsigned long *lun_bitmap, unsigned int valid_secs,
+ unsigned int off)
+{
+ struct pblk_sec_meta *meta_list = rqd->meta_list;
+ unsigned int map_secs;
+ int min = pblk->min_write_pgs;
+ int i;
+
+ for (i = off; i < rqd->nr_ppas; i += min) {
+ map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+ pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs);
+ }
+}
+
+/* only if erase_ppa is set, acquire erase semaphore */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int sentry, unsigned long *lun_bitmap,
+ unsigned int valid_secs, struct ppa_addr *erase_ppa)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+ struct pblk_sec_meta *meta_list = rqd->meta_list;
+ unsigned int map_secs;
+ int min = pblk->min_write_pgs;
+ int i, erase_lun;
+
+ for (i = 0; i < rqd->nr_ppas; i += min) {
+ map_secs = (i + min > valid_secs) ? (valid_secs % min) : min;
+ pblk_map_page_data(pblk, sentry + i, &rqd->ppa_list[i],
+ lun_bitmap, &meta_list[i], map_secs);
+
+ erase_lun = rqd->ppa_list[i].g.lun * geo->nr_chnls +
+ rqd->ppa_list[i].g.ch;
+
+ if (!test_bit(erase_lun, e_line->erase_bitmap)) {
+ if (down_trylock(&pblk->erase_sem))
+ continue;
+
+ set_bit(erase_lun, e_line->erase_bitmap);
+ atomic_dec(&e_line->left_eblks);
+ *erase_ppa = rqd->ppa_list[i];
+ erase_ppa->g.blk = e_line->id;
+
+ /* Avoid evaluating e_line->left_eblks */
+ return pblk_map_rq(pblk, rqd, sentry, lun_bitmap,
+ valid_secs, i + min);
+ }
+ }
+
+ /* Erase blocks that are bad in this line but might not be in next */
+ if (unlikely(ppa_empty(*erase_ppa))) {
+ struct pblk_line_meta *lm = &pblk->lm;
+
+ i = find_first_zero_bit(e_line->erase_bitmap, lm->blk_per_line);
+ if (i == lm->blk_per_line)
+ return;
+
+ set_bit(i, e_line->erase_bitmap);
+ atomic_dec(&e_line->left_eblks);
+ *erase_ppa = pblk->luns[i].bppa; /* set ch and lun */
+ erase_ppa->g.blk = e_line->id;
+ }
+}
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
new file mode 100644
index 000000000000..045384ddc1f9
--- /dev/null
+++ b/drivers/lightnvm/pblk-rb.c
@@ -0,0 +1,852 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * Based upon the circular ringbuffer.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-rb.c - pblk's write buffer
+ */
+
+#include <linux/circ_buf.h>
+
+#include "pblk.h"
+
+static DECLARE_RWSEM(pblk_rb_lock);
+
+void pblk_rb_data_free(struct pblk_rb *rb)
+{
+ struct pblk_rb_pages *p, *t;
+
+ down_write(&pblk_rb_lock);
+ list_for_each_entry_safe(p, t, &rb->pages, list) {
+ free_pages((unsigned long)page_address(p->pages), p->order);
+ list_del(&p->list);
+ kfree(p);
+ }
+ up_write(&pblk_rb_lock);
+}
+
+/*
+ * Initialize ring buffer. The data and metadata buffers must be previously
+ * allocated and their size must be a power of two
+ * (Documentation/circular-buffers.txt)
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+ unsigned int power_size, unsigned int power_seg_sz)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ unsigned int init_entry = 0;
+ unsigned int alloc_order = power_size;
+ unsigned int max_order = MAX_ORDER - 1;
+ unsigned int order, iter;
+
+ down_write(&pblk_rb_lock);
+ rb->entries = rb_entry_base;
+ rb->seg_size = (1 << power_seg_sz);
+ rb->nr_entries = (1 << power_size);
+ rb->mem = rb->subm = rb->sync = rb->l2p_update = 0;
+ rb->sync_point = EMPTY_ENTRY;
+
+ spin_lock_init(&rb->w_lock);
+ spin_lock_init(&rb->s_lock);
+
+ INIT_LIST_HEAD(&rb->pages);
+
+ if (alloc_order >= max_order) {
+ order = max_order;
+ iter = (1 << (alloc_order - max_order));
+ } else {
+ order = alloc_order;
+ iter = 1;
+ }
+
+ do {
+ struct pblk_rb_entry *entry;
+ struct pblk_rb_pages *page_set;
+ void *kaddr;
+ unsigned long set_size;
+ int i;
+
+ page_set = kmalloc(sizeof(struct pblk_rb_pages), GFP_KERNEL);
+ if (!page_set) {
+ up_write(&pblk_rb_lock);
+ return -ENOMEM;
+ }
+
+ page_set->order = order;
+ page_set->pages = alloc_pages(GFP_KERNEL, order);
+ if (!page_set->pages) {
+ kfree(page_set);
+ pblk_rb_data_free(rb);
+ up_write(&pblk_rb_lock);
+ return -ENOMEM;
+ }
+ kaddr = page_address(page_set->pages);
+
+ entry = &rb->entries[init_entry];
+ entry->data = kaddr;
+ entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+ entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+
+ set_size = (1 << order);
+ for (i = 1; i < set_size; i++) {
+ entry = &rb->entries[init_entry];
+ entry->cacheline = pblk_cacheline_to_addr(init_entry++);
+ entry->data = kaddr + (i * rb->seg_size);
+ entry->w_ctx.flags = PBLK_WRITABLE_ENTRY;
+ bio_list_init(&entry->w_ctx.bios);
+ }
+
+ list_add_tail(&page_set->list, &rb->pages);
+ iter--;
+ } while (iter > 0);
+ up_write(&pblk_rb_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_set(&rb->inflight_sync_point, 0);
+#endif
+
+ /*
+ * Initialize rate-limiter, which controls access to the write buffer
+ * but user and GC I/O
+ */
+ pblk_rl_init(&pblk->rl, rb->nr_entries);
+
+ return 0;
+}
+
+/*
+ * pblk_rb_calculate_size -- calculate the size of the write buffer
+ */
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries)
+{
+ /* Alloc a write buffer that can at least fit 128 entries */
+ return (1 << max(get_count_order(nr_entries), 7));
+}
+
+void *pblk_rb_entries_ref(struct pblk_rb *rb)
+{
+ return rb->entries;
+}
+
+static void clean_wctx(struct pblk_w_ctx *w_ctx)
+{
+ int flags;
+
+try:
+ flags = READ_ONCE(w_ctx->flags);
+ if (!(flags & PBLK_SUBMITTED_ENTRY))
+ goto try;
+
+ /* Release flags on context. Protect from writes and reads */
+ smp_store_release(&w_ctx->flags, PBLK_WRITABLE_ENTRY);
+ pblk_ppa_set_empty(&w_ctx->ppa);
+}
+
+#define pblk_rb_ring_count(head, tail, size) CIRC_CNT(head, tail, size)
+#define pblk_rb_ring_space(rb, head, tail, size) \
+ (CIRC_SPACE(head, tail, size))
+
+/*
+ * Buffer space is calculated with respect to the back pointer signaling
+ * synchronized entries to the media.
+ */
+static unsigned int pblk_rb_space(struct pblk_rb *rb)
+{
+ unsigned int mem = READ_ONCE(rb->mem);
+ unsigned int sync = READ_ONCE(rb->sync);
+
+ return pblk_rb_ring_space(rb, mem, sync, rb->nr_entries);
+}
+
+/*
+ * Buffer count is calculated with respect to the submission entry signaling the
+ * entries that are available to send to the media
+ */
+unsigned int pblk_rb_read_count(struct pblk_rb *rb)
+{
+ unsigned int mem = READ_ONCE(rb->mem);
+ unsigned int subm = READ_ONCE(rb->subm);
+
+ return pblk_rb_ring_count(mem, subm, rb->nr_entries);
+}
+
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int nr_entries)
+{
+ unsigned int subm;
+
+ subm = READ_ONCE(rb->subm);
+ /* Commit read means updating submission pointer */
+ smp_store_release(&rb->subm,
+ (subm + nr_entries) & (rb->nr_entries - 1));
+
+ return subm;
+}
+
+static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int *l2p_upd,
+ unsigned int to_update)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_line *line;
+ struct pblk_rb_entry *entry;
+ struct pblk_w_ctx *w_ctx;
+ unsigned int i;
+
+ for (i = 0; i < to_update; i++) {
+ entry = &rb->entries[*l2p_upd];
+ w_ctx = &entry->w_ctx;
+
+ pblk_update_map_dev(pblk, w_ctx->lba, w_ctx->ppa,
+ entry->cacheline);
+
+ line = &pblk->lines[pblk_tgt_ppa_to_line(w_ctx->ppa)];
+ kref_put(&line->ref, pblk_line_put);
+ clean_wctx(w_ctx);
+ *l2p_upd = (*l2p_upd + 1) & (rb->nr_entries - 1);
+ }
+
+ return 0;
+}
+
+/*
+ * When we move the l2p_update pointer, we update the l2p table - lookups will
+ * point to the physical address instead of to the cacheline in the write buffer
+ * from this moment on.
+ */
+static int pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int mem, unsigned int sync)
+{
+ unsigned int space, count;
+ int ret = 0;
+
+ lockdep_assert_held(&rb->w_lock);
+
+ /* Update l2p only as buffer entries are being overwritten */
+ space = pblk_rb_ring_space(rb, mem, rb->l2p_update, rb->nr_entries);
+ if (space > nr_entries)
+ goto out;
+
+ count = nr_entries - space;
+ /* l2p_update used exclusively under rb->w_lock */
+ ret = __pblk_rb_update_l2p(rb, &rb->l2p_update, count);
+
+out:
+ return ret;
+}
+
+/*
+ * Update the l2p entry for all sectors stored on the write buffer. This means
+ * that all future lookups to the l2p table will point to a device address, not
+ * to the cacheline in the write buffer.
+ */
+void pblk_rb_sync_l2p(struct pblk_rb *rb)
+{
+ unsigned int sync;
+ unsigned int to_update;
+
+ spin_lock(&rb->w_lock);
+
+ /* Protect from reads and writes */
+ sync = smp_load_acquire(&rb->sync);
+
+ to_update = pblk_rb_ring_count(sync, rb->l2p_update, rb->nr_entries);
+ __pblk_rb_update_l2p(rb, &rb->l2p_update, to_update);
+
+ spin_unlock(&rb->w_lock);
+}
+
+/*
+ * Write @nr_entries to ring buffer from @data buffer if there is enough space.
+ * Typically, 4KB data chunks coming from a bio will be copied to the ring
+ * buffer, thus the write will fail if not all incoming data can be copied.
+ *
+ */
+static void __pblk_rb_write_entry(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx,
+ struct pblk_rb_entry *entry)
+{
+ memcpy(entry->data, data, rb->seg_size);
+
+ entry->w_ctx.lba = w_ctx.lba;
+ entry->w_ctx.ppa = w_ctx.ppa;
+}
+
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, unsigned int ring_pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ int flags;
+
+ entry = &rb->entries[ring_pos];
+ flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must guarantee that the entry is free */
+ BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+ __pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+ pblk_update_map_cache(pblk, w_ctx.lba, entry->cacheline);
+ flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+ /* Release flags on write context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+ unsigned int ring_pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ int flags;
+
+ entry = &rb->entries[ring_pos];
+ flags = READ_ONCE(entry->w_ctx.flags);
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must guarantee that the entry is free */
+ BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
+#endif
+
+ __pblk_rb_write_entry(rb, data, w_ctx, entry);
+
+ if (!pblk_update_map_gc(pblk, w_ctx.lba, entry->cacheline, gc_line))
+ entry->w_ctx.lba = ADDR_EMPTY;
+
+ flags = w_ctx.flags | PBLK_WRITTEN_DATA;
+
+ /* Release flags on write context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+}
+
+static int pblk_rb_sync_point_set(struct pblk_rb *rb, struct bio *bio,
+ unsigned int pos)
+{
+ struct pblk_rb_entry *entry;
+ unsigned int subm, sync_point;
+ int flags;
+
+ subm = READ_ONCE(rb->subm);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_inc(&rb->inflight_sync_point);
+#endif
+
+ if (pos == subm)
+ return 0;
+
+ sync_point = (pos == 0) ? (rb->nr_entries - 1) : (pos - 1);
+ entry = &rb->entries[sync_point];
+
+ flags = READ_ONCE(entry->w_ctx.flags);
+ flags |= PBLK_FLUSH_ENTRY;
+
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+
+ /* Protect syncs */
+ smp_store_release(&rb->sync_point, sync_point);
+
+ spin_lock_irq(&rb->s_lock);
+ bio_list_add(&entry->w_ctx.bios, bio);
+ spin_unlock_irq(&rb->s_lock);
+
+ return 1;
+}
+
+static int __pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ unsigned int mem;
+ unsigned int sync;
+
+ sync = READ_ONCE(rb->sync);
+ mem = READ_ONCE(rb->mem);
+
+ if (pblk_rb_ring_space(rb, mem, sync, rb->nr_entries) < nr_entries)
+ return 0;
+
+ if (pblk_rb_update_l2p(rb, nr_entries, mem, sync))
+ return 0;
+
+ *pos = mem;
+
+ return 1;
+}
+
+static int pblk_rb_may_write(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ if (!__pblk_rb_may_write(rb, nr_entries, pos))
+ return 0;
+
+ /* Protect from read count */
+ smp_store_release(&rb->mem, (*pos + nr_entries) & (rb->nr_entries - 1));
+ return 1;
+}
+
+static int pblk_rb_may_write_flush(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos, struct bio *bio,
+ int *io_ret)
+{
+ unsigned int mem;
+
+ if (!__pblk_rb_may_write(rb, nr_entries, pos))
+ return 0;
+
+ mem = (*pos + nr_entries) & (rb->nr_entries - 1);
+ *io_ret = NVM_IO_DONE;
+
+ if (bio->bi_opf & REQ_PREFLUSH) {
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->nr_flush);
+#endif
+ if (pblk_rb_sync_point_set(&pblk->rwb, bio, mem))
+ *io_ret = NVM_IO_OK;
+ }
+
+ /* Protect from read count */
+ smp_store_release(&rb->mem, mem);
+ return 1;
+}
+
+/*
+ * Atomically check that (i) there is space on the write buffer for the
+ * incoming I/O, and (ii) the current I/O type has enough budget in the write
+ * buffer (rate-limiter).
+ */
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+ unsigned int nr_entries, unsigned int *pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ int flush_done;
+
+ spin_lock(&rb->w_lock);
+ if (!pblk_rl_user_may_insert(&pblk->rl, nr_entries)) {
+ spin_unlock(&rb->w_lock);
+ return NVM_IO_REQUEUE;
+ }
+
+ if (!pblk_rb_may_write_flush(rb, nr_entries, pos, bio, &flush_done)) {
+ spin_unlock(&rb->w_lock);
+ return NVM_IO_REQUEUE;
+ }
+
+ pblk_rl_user_in(&pblk->rl, nr_entries);
+ spin_unlock(&rb->w_lock);
+
+ return flush_done;
+}
+
+/*
+ * Look at pblk_rb_may_write_user comment
+ */
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+
+ spin_lock(&rb->w_lock);
+ if (!pblk_rl_gc_may_insert(&pblk->rl, nr_entries)) {
+ spin_unlock(&rb->w_lock);
+ return 0;
+ }
+
+ if (!pblk_rb_may_write(rb, nr_entries, pos)) {
+ spin_unlock(&rb->w_lock);
+ return 0;
+ }
+
+ pblk_rl_gc_in(&pblk->rl, nr_entries);
+ spin_unlock(&rb->w_lock);
+
+ return 1;
+}
+
+/*
+ * The caller of this function must ensure that the backpointer will not
+ * overwrite the entries passed on the list.
+ */
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+ struct list_head *list,
+ unsigned int max)
+{
+ struct pblk_rb_entry *entry, *tentry;
+ struct page *page;
+ unsigned int read = 0;
+ int ret;
+
+ list_for_each_entry_safe(entry, tentry, list, index) {
+ if (read > max) {
+ pr_err("pblk: too many entries on list\n");
+ goto out;
+ }
+
+ page = virt_to_page(entry->data);
+ if (!page) {
+ pr_err("pblk: could not allocate write bio page\n");
+ goto out;
+ }
+
+ ret = bio_add_page(bio, page, rb->seg_size, 0);
+ if (ret != rb->seg_size) {
+ pr_err("pblk: could not add page to write bio\n");
+ goto out;
+ }
+
+ list_del(&entry->index);
+ read++;
+ }
+
+out:
+ return read;
+}
+
+/*
+ * Read available entries on rb and add them to the given bio. To avoid a memory
+ * copy, a page reference to the write buffer is used to be added to the bio.
+ *
+ * This function is used by the write thread to form the write bio that will
+ * persist data on the write buffer to the media.
+ */
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+ struct pblk_c_ctx *c_ctx,
+ unsigned int pos,
+ unsigned int nr_entries,
+ unsigned int count)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_rb_entry *entry;
+ struct page *page;
+ unsigned int pad = 0, read = 0, to_read = nr_entries;
+ unsigned int user_io = 0, gc_io = 0;
+ unsigned int i;
+ int flags;
+ int ret;
+
+ if (count < nr_entries) {
+ pad = nr_entries - count;
+ to_read = count;
+ }
+
+ c_ctx->sentry = pos;
+ c_ctx->nr_valid = to_read;
+ c_ctx->nr_padded = pad;
+
+ for (i = 0; i < to_read; i++) {
+ entry = &rb->entries[pos];
+
+ /* A write has been allowed into the buffer, but data is still
+ * being copied to it. It is ok to busy wait.
+ */
+try:
+ flags = READ_ONCE(entry->w_ctx.flags);
+ if (!(flags & PBLK_WRITTEN_DATA))
+ goto try;
+
+ if (flags & PBLK_IOTYPE_USER)
+ user_io++;
+ else if (flags & PBLK_IOTYPE_GC)
+ gc_io++;
+ else
+ WARN(1, "pblk: unknown IO type\n");
+
+ page = virt_to_page(entry->data);
+ if (!page) {
+ pr_err("pblk: could not allocate write bio page\n");
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+ goto out;
+ }
+
+ ret = bio_add_page(bio, page, rb->seg_size, 0);
+ if (ret != rb->seg_size) {
+ pr_err("pblk: could not add page to write bio\n");
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+ goto out;
+ }
+
+ if (flags & PBLK_FLUSH_ENTRY) {
+ unsigned int sync_point;
+
+ sync_point = READ_ONCE(rb->sync_point);
+ if (sync_point == pos) {
+ /* Protect syncs */
+ smp_store_release(&rb->sync_point, EMPTY_ENTRY);
+ }
+
+ flags &= ~PBLK_FLUSH_ENTRY;
+#ifdef CONFIG_NVM_DEBUG
+ atomic_dec(&rb->inflight_sync_point);
+#endif
+ }
+
+ flags &= ~PBLK_WRITTEN_DATA;
+ flags |= PBLK_SUBMITTED_ENTRY;
+
+ /* Release flags on context. Protect from writes */
+ smp_store_release(&entry->w_ctx.flags, flags);
+
+ pos = (pos + 1) & (rb->nr_entries - 1);
+ }
+
+ read = to_read;
+ pblk_rl_out(&pblk->rl, user_io, gc_io);
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(pad, &((struct pblk *)
+ (container_of(rb, struct pblk, rwb)))->padded_writes);
+#endif
+out:
+ return read;
+}
+
+/*
+ * Copy to bio only if the lba matches the one on the given cache entry.
+ * Otherwise, it means that the entry has been overwritten, and the bio should
+ * be directed to disk.
+ */
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+ u64 pos, int bio_iter)
+{
+ struct pblk_rb_entry *entry;
+ struct pblk_w_ctx *w_ctx;
+ void *data;
+ int flags;
+ int ret = 1;
+
+ spin_lock(&rb->w_lock);
+
+#ifdef CONFIG_NVM_DEBUG
+ /* Caller must ensure that the access will not cause an overflow */
+ BUG_ON(pos >= rb->nr_entries);
+#endif
+ entry = &rb->entries[pos];
+ w_ctx = &entry->w_ctx;
+ flags = READ_ONCE(w_ctx->flags);
+
+ /* Check if the entry has been overwritten or is scheduled to be */
+ if (w_ctx->lba != lba || flags & PBLK_WRITABLE_ENTRY) {
+ ret = 0;
+ goto out;
+ }
+
+ /* Only advance the bio if it hasn't been advanced already. If advanced,
+ * this bio is at least a partial bio (i.e., it has partially been
+ * filled with data from the cache). If part of the data resides on the
+ * media, we will read later on
+ */
+ if (unlikely(!bio->bi_iter.bi_idx))
+ bio_advance(bio, bio_iter * PBLK_EXPOSED_PAGE_SIZE);
+
+ data = bio_data(bio);
+ memcpy(data, entry->data, rb->seg_size);
+
+out:
+ spin_unlock(&rb->w_lock);
+ return ret;
+}
+
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos)
+{
+ unsigned int entry = pos & (rb->nr_entries - 1);
+
+ return &rb->entries[entry].w_ctx;
+}
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags)
+ __acquires(&rb->s_lock)
+{
+ if (flags)
+ spin_lock_irqsave(&rb->s_lock, *flags);
+ else
+ spin_lock_irq(&rb->s_lock);
+
+ return rb->sync;
+}
+
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags)
+ __releases(&rb->s_lock)
+{
+ lockdep_assert_held(&rb->s_lock);
+
+ if (flags)
+ spin_unlock_irqrestore(&rb->s_lock, *flags);
+ else
+ spin_unlock_irq(&rb->s_lock);
+}
+
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries)
+{
+ unsigned int sync;
+ unsigned int i;
+
+ lockdep_assert_held(&rb->s_lock);
+
+ sync = READ_ONCE(rb->sync);
+
+ for (i = 0; i < nr_entries; i++)
+ sync = (sync + 1) & (rb->nr_entries - 1);
+
+ /* Protect from counts */
+ smp_store_release(&rb->sync, sync);
+
+ return sync;
+}
+
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb)
+{
+ unsigned int subm, sync_point;
+ unsigned int count;
+
+ /* Protect syncs */
+ sync_point = smp_load_acquire(&rb->sync_point);
+ if (sync_point == EMPTY_ENTRY)
+ return 0;
+
+ subm = READ_ONCE(rb->subm);
+
+ /* The sync point itself counts as a sector to sync */
+ count = pblk_rb_ring_count(sync_point, subm, rb->nr_entries) + 1;
+
+ return count;
+}
+
+/*
+ * Scan from the current position of the sync pointer to find the entry that
+ * corresponds to the given ppa. This is necessary since write requests can be
+ * completed out of order. The assumption is that the ppa is close to the sync
+ * pointer thus the search will not take long.
+ *
+ * The caller of this function must guarantee that the sync pointer will no
+ * reach the entry while it is using the metadata associated with it. With this
+ * assumption in mind, there is no need to take the sync lock.
+ */
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+ struct ppa_addr *ppa)
+{
+ unsigned int sync, subm, count;
+ unsigned int i;
+
+ sync = READ_ONCE(rb->sync);
+ subm = READ_ONCE(rb->subm);
+ count = pblk_rb_ring_count(subm, sync, rb->nr_entries);
+
+ for (i = 0; i < count; i++)
+ sync = (sync + 1) & (rb->nr_entries - 1);
+
+ return NULL;
+}
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb)
+{
+ struct pblk_rb_entry *entry;
+ int i;
+ int ret = 0;
+
+ spin_lock(&rb->w_lock);
+ spin_lock_irq(&rb->s_lock);
+
+ if ((rb->mem == rb->subm) && (rb->subm == rb->sync) &&
+ (rb->sync == rb->l2p_update) &&
+ (rb->sync_point == EMPTY_ENTRY)) {
+ goto out;
+ }
+
+ if (!rb->entries) {
+ ret = 1;
+ goto out;
+ }
+
+ for (i = 0; i < rb->nr_entries; i++) {
+ entry = &rb->entries[i];
+
+ if (!entry->data) {
+ ret = 1;
+ goto out;
+ }
+ }
+
+out:
+ spin_unlock(&rb->w_lock);
+ spin_unlock_irq(&rb->s_lock);
+
+ return ret;
+}
+
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos)
+{
+ return (pos & (rb->nr_entries - 1));
+}
+
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos)
+{
+ return (pos >= rb->nr_entries);
+}
+
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
+{
+ struct pblk *pblk = container_of(rb, struct pblk, rwb);
+ struct pblk_c_ctx *c;
+ ssize_t offset;
+ int queued_entries = 0;
+
+ spin_lock_irq(&rb->s_lock);
+ list_for_each_entry(c, &pblk->compl_list, list)
+ queued_entries++;
+ spin_unlock_irq(&rb->s_lock);
+
+ if (rb->sync_point != EMPTY_ENTRY)
+ offset = scnprintf(buf, PAGE_SIZE,
+ "%u\t%u\t%u\t%u\t%u\t%u\t%u - %u/%u/%u - %d\n",
+ rb->nr_entries,
+ rb->mem,
+ rb->subm,
+ rb->sync,
+ rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+ atomic_read(&rb->inflight_sync_point),
+#else
+ 0,
+#endif
+ rb->sync_point,
+ pblk_rb_read_count(rb),
+ pblk_rb_space(rb),
+ pblk_rb_sync_point_count(rb),
+ queued_entries);
+ else
+ offset = scnprintf(buf, PAGE_SIZE,
+ "%u\t%u\t%u\t%u\t%u\t%u\tNULL - %u/%u/%u - %d\n",
+ rb->nr_entries,
+ rb->mem,
+ rb->subm,
+ rb->sync,
+ rb->l2p_update,
+#ifdef CONFIG_NVM_DEBUG
+ atomic_read(&rb->inflight_sync_point),
+#else
+ 0,
+#endif
+ pblk_rb_read_count(rb),
+ pblk_rb_space(rb),
+ pblk_rb_sync_point_count(rb),
+ queued_entries);
+
+ return offset;
+}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
new file mode 100644
index 000000000000..4a12f14d78c6
--- /dev/null
+++ b/drivers/lightnvm/pblk-read.c
@@ -0,0 +1,529 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-read.c - pblk's read path
+ */
+
+#include "pblk.h"
+
+/*
+ * There is no guarantee that the value read from cache has not been updated and
+ * resides at another location in the cache. We guarantee though that if the
+ * value is read from the cache, it belongs to the mapped lba. In order to
+ * guarantee and order between writes and reads are ordered, a flush must be
+ * issued.
+ */
+static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
+ sector_t lba, struct ppa_addr ppa,
+ int bio_iter)
+{
+#ifdef CONFIG_NVM_DEBUG
+ /* Callers must ensure that the ppa points to a cache address */
+ BUG_ON(pblk_ppa_empty(ppa));
+ BUG_ON(!pblk_addr_in_cache(ppa));
+#endif
+
+ return pblk_rb_copy_to_bio(&pblk->rwb, bio, lba,
+ pblk_addr_to_cacheline(ppa), bio_iter);
+}
+
+static void pblk_read_ppalist_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned long *read_bitmap)
+{
+ struct bio *bio = rqd->bio;
+ struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+ sector_t blba = pblk_get_lba(bio);
+ int nr_secs = rqd->nr_ppas;
+ int advanced_bio = 0;
+ int i, j = 0;
+
+ /* logic error: lba out-of-bounds. Ignore read request */
+ if (blba + nr_secs >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lbas out of bounds\n");
+ return;
+ }
+
+ pblk_lookup_l2p_seq(pblk, ppas, blba, nr_secs);
+
+ for (i = 0; i < nr_secs; i++) {
+ struct ppa_addr p = ppas[i];
+ sector_t lba = blba + i;
+
+retry:
+ if (pblk_ppa_empty(p)) {
+ WARN_ON(test_and_set_bit(i, read_bitmap));
+ continue;
+ }
+
+ /* Try to read from write buffer. The address is later checked
+ * on the write buffer to prevent retrieving overwritten data.
+ */
+ if (pblk_addr_in_cache(p)) {
+ if (!pblk_read_from_cache(pblk, bio, lba, p, i)) {
+ pblk_lookup_l2p_seq(pblk, &p, lba, 1);
+ goto retry;
+ }
+ WARN_ON(test_and_set_bit(i, read_bitmap));
+ advanced_bio = 1;
+ } else {
+ /* Read from media non-cached sectors */
+ rqd->ppa_list[j++] = p;
+ }
+
+ if (advanced_bio)
+ bio_advance(bio, PBLK_EXPOSED_PAGE_SIZE);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_secs, &pblk->inflight_reads);
+#endif
+}
+
+static int pblk_submit_read_io(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ int err;
+
+ rqd->flags = pblk_set_read_mode(pblk);
+
+ err = pblk_submit_io(pblk, rqd);
+ if (err)
+ return NVM_IO_ERR;
+
+ return NVM_IO_OK;
+}
+
+static void pblk_end_io_read(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+ struct bio *bio = rqd->bio;
+
+ if (rqd->error)
+ pblk_log_read_err(pblk, rqd);
+#ifdef CONFIG_NVM_DEBUG
+ else
+ WARN_ONCE(bio->bi_error, "pblk: corrupted read error\n");
+#endif
+
+ if (rqd->nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
+
+ bio_put(bio);
+ if (r_ctx->orig_bio) {
+#ifdef CONFIG_NVM_DEBUG
+ WARN_ONCE(r_ctx->orig_bio->bi_error,
+ "pblk: corrupted read bio\n");
+#endif
+ bio_endio(r_ctx->orig_bio);
+ bio_put(r_ctx->orig_bio);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
+ atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
+#endif
+
+ pblk_free_rqd(pblk, rqd, READ);
+}
+
+static int pblk_fill_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int bio_init_idx,
+ unsigned long *read_bitmap)
+{
+ struct bio *new_bio, *bio = rqd->bio;
+ struct bio_vec src_bv, dst_bv;
+ void *ppa_ptr = NULL;
+ void *src_p, *dst_p;
+ dma_addr_t dma_ppa_list = 0;
+ int nr_secs = rqd->nr_ppas;
+ int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+ int i, ret, hole;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+ if (!new_bio) {
+ pr_err("pblk: could not alloc read bio\n");
+ return NVM_IO_ERR;
+ }
+
+ if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+ goto err;
+
+ if (nr_holes != new_bio->bi_vcnt) {
+ pr_err("pblk: malformed bio\n");
+ goto err;
+ }
+
+ new_bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+ new_bio->bi_private = &wait;
+ new_bio->bi_end_io = pblk_end_bio_sync;
+
+ rqd->bio = new_bio;
+ rqd->nr_ppas = nr_holes;
+ rqd->end_io = NULL;
+
+ if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+ ppa_ptr = rqd->ppa_list;
+ dma_ppa_list = rqd->dma_ppa_list;
+ rqd->ppa_addr = rqd->ppa_list[0];
+ }
+
+ ret = pblk_submit_read_io(pblk, rqd);
+ if (ret) {
+ bio_put(rqd->bio);
+ pr_err("pblk: read IO submission failed\n");
+ goto err;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: partial read I/O timed out\n");
+ }
+
+ if (rqd->error) {
+ atomic_long_inc(&pblk->read_failed);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, rqd, rqd->error);
+#endif
+ }
+
+ if (unlikely(nr_secs > 1 && nr_holes == 1)) {
+ rqd->ppa_list = ppa_ptr;
+ rqd->dma_ppa_list = dma_ppa_list;
+ }
+
+ /* Fill the holes in the original bio */
+ i = 0;
+ hole = find_first_zero_bit(read_bitmap, nr_secs);
+ do {
+ src_bv = new_bio->bi_io_vec[i++];
+ dst_bv = bio->bi_io_vec[bio_init_idx + hole];
+
+ src_p = kmap_atomic(src_bv.bv_page);
+ dst_p = kmap_atomic(dst_bv.bv_page);
+
+ memcpy(dst_p + dst_bv.bv_offset,
+ src_p + src_bv.bv_offset,
+ PBLK_EXPOSED_PAGE_SIZE);
+
+ kunmap_atomic(src_p);
+ kunmap_atomic(dst_p);
+
+ mempool_free(src_bv.bv_page, pblk->page_pool);
+
+ hole = find_next_zero_bit(read_bitmap, nr_secs, hole + 1);
+ } while (hole < nr_secs);
+
+ bio_put(new_bio);
+
+ /* Complete the original bio and associated request */
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_secs;
+ rqd->private = pblk;
+
+ bio_endio(bio);
+ pblk_end_io_read(rqd);
+ return NVM_IO_OK;
+
+err:
+ /* Free allocated pages in new bio */
+ pblk_bio_free_pages(pblk, bio, 0, new_bio->bi_vcnt);
+ rqd->private = pblk;
+ pblk_end_io_read(rqd);
+ return NVM_IO_ERR;
+}
+
+static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned long *read_bitmap)
+{
+ struct bio *bio = rqd->bio;
+ struct ppa_addr ppa;
+ sector_t lba = pblk_get_lba(bio);
+
+ /* logic error: lba out-of-bounds. Ignore read request */
+ if (lba >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lba out of bounds\n");
+ return;
+ }
+
+ pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+retry:
+ if (pblk_ppa_empty(ppa)) {
+ WARN_ON(test_and_set_bit(0, read_bitmap));
+ return;
+ }
+
+ /* Try to read from write buffer. The address is later checked on the
+ * write buffer to prevent retrieving overwritten data.
+ */
+ if (pblk_addr_in_cache(ppa)) {
+ if (!pblk_read_from_cache(pblk, bio, lba, ppa, 0)) {
+ pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
+ goto retry;
+ }
+ WARN_ON(test_and_set_bit(0, read_bitmap));
+ } else {
+ rqd->ppa_addr = ppa;
+ }
+}
+
+int pblk_submit_read(struct pblk *pblk, struct bio *bio)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ unsigned int nr_secs = pblk_get_secs(bio);
+ struct nvm_rq *rqd;
+ unsigned long read_bitmap; /* Max 64 ppas per request */
+ unsigned int bio_init_idx;
+ int ret = NVM_IO_ERR;
+
+ if (nr_secs > PBLK_MAX_REQ_ADDRS)
+ return NVM_IO_ERR;
+
+ bitmap_zero(&read_bitmap, nr_secs);
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd)) {
+ pr_err_ratelimited("pblk: not able to alloc rqd");
+ return NVM_IO_ERR;
+ }
+
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_secs;
+ rqd->private = pblk;
+ rqd->end_io = pblk_end_io_read;
+
+ /* Save the index for this bio's start. This is needed in case
+ * we need to fill a partial read.
+ */
+ bio_init_idx = pblk_get_bi_idx(bio);
+
+ if (nr_secs > 1) {
+ rqd->ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd->dma_ppa_list);
+ if (!rqd->ppa_list) {
+ pr_err("pblk: not able to allocate ppa list\n");
+ goto fail_rqd_free;
+ }
+
+ pblk_read_ppalist_rq(pblk, rqd, &read_bitmap);
+ } else {
+ pblk_read_rq(pblk, rqd, &read_bitmap);
+ }
+
+ bio_get(bio);
+ if (bitmap_full(&read_bitmap, nr_secs)) {
+ bio_endio(bio);
+ pblk_end_io_read(rqd);
+ return NVM_IO_OK;
+ }
+
+ /* All sectors are to be read from the device */
+ if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+ struct bio *int_bio = NULL;
+ struct pblk_r_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+
+ /* Clone read bio to deal with read errors internally */
+ int_bio = bio_clone_bioset(bio, GFP_KERNEL, fs_bio_set);
+ if (!int_bio) {
+ pr_err("pblk: could not clone read bio\n");
+ return NVM_IO_ERR;
+ }
+
+ rqd->bio = int_bio;
+ r_ctx->orig_bio = bio;
+
+ ret = pblk_submit_read_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: read IO submission failed\n");
+ if (int_bio)
+ bio_put(int_bio);
+ return ret;
+ }
+
+ return NVM_IO_OK;
+ }
+
+ /* The read bio request could be partially filled by the write buffer,
+ * but there are some holes that need to be read from the drive.
+ */
+ ret = pblk_fill_partial_read_bio(pblk, rqd, bio_init_idx, &read_bitmap);
+ if (ret) {
+ pr_err("pblk: failed to perform partial read\n");
+ return ret;
+ }
+
+ return NVM_IO_OK;
+
+fail_rqd_free:
+ pblk_free_rqd(pblk, rqd, READ);
+ return ret;
+}
+
+static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_line *line, u64 *lba_list,
+ unsigned int nr_secs)
+{
+ struct ppa_addr ppas[PBLK_MAX_REQ_ADDRS];
+ int valid_secs = 0;
+ int i;
+
+ pblk_lookup_l2p_rand(pblk, ppas, lba_list, nr_secs);
+
+ for (i = 0; i < nr_secs; i++) {
+ if (pblk_addr_in_cache(ppas[i]) || ppas[i].g.blk != line->id ||
+ pblk_ppa_empty(ppas[i])) {
+ lba_list[i] = ADDR_EMPTY;
+ continue;
+ }
+
+ rqd->ppa_list[valid_secs++] = ppas[i];
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(valid_secs, &pblk->inflight_reads);
+#endif
+ return valid_secs;
+}
+
+static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_line *line, sector_t lba)
+{
+ struct ppa_addr ppa;
+ int valid_secs = 0;
+
+ if (lba == ADDR_EMPTY)
+ goto out;
+
+ /* logic error: lba out-of-bounds */
+ if (lba >= pblk->rl.nr_secs) {
+ WARN(1, "pblk: read lba out of bounds\n");
+ goto out;
+ }
+
+ spin_lock(&pblk->trans_lock);
+ ppa = pblk_trans_map_get(pblk, lba);
+ spin_unlock(&pblk->trans_lock);
+
+ /* Ignore updated values until the moment */
+ if (pblk_addr_in_cache(ppa) || ppa.g.blk != line->id ||
+ pblk_ppa_empty(ppa))
+ goto out;
+
+ rqd->ppa_addr = ppa;
+ valid_secs = 1;
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->inflight_reads);
+#endif
+
+out:
+ return valid_secs;
+}
+
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+ unsigned int nr_secs, unsigned int *secs_to_gc,
+ struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct request_queue *q = dev->q;
+ struct bio *bio;
+ struct nvm_rq rqd;
+ int ret, data_len;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ memset(&rqd, 0, sizeof(struct nvm_rq));
+
+ if (nr_secs > 1) {
+ rqd.ppa_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd.dma_ppa_list);
+ if (!rqd.ppa_list)
+ return NVM_IO_ERR;
+
+ *secs_to_gc = read_ppalist_rq_gc(pblk, &rqd, line, lba_list,
+ nr_secs);
+ if (*secs_to_gc == 1) {
+ struct ppa_addr ppa;
+
+ ppa = rqd.ppa_list[0];
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list,
+ rqd.dma_ppa_list);
+ rqd.ppa_addr = ppa;
+ }
+ } else {
+ *secs_to_gc = read_rq_gc(pblk, &rqd, line, lba_list[0]);
+ }
+
+ if (!(*secs_to_gc))
+ goto out;
+
+ data_len = (*secs_to_gc) * geo->sec_size;
+ bio = bio_map_kern(q, data, data_len, GFP_KERNEL);
+ if (IS_ERR(bio)) {
+ pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+ goto err_free_dma;
+ }
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd.opcode = NVM_OP_PREAD;
+ rqd.end_io = pblk_end_io_sync;
+ rqd.private = &wait;
+ rqd.nr_ppas = *secs_to_gc;
+ rqd.bio = bio;
+
+ ret = pblk_submit_read_io(pblk, &rqd);
+ if (ret) {
+ bio_endio(bio);
+ pr_err("pblk: GC read request failed\n");
+ goto err_free_dma;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: GC read I/O timed out\n");
+ }
+
+ if (rqd.error) {
+ atomic_long_inc(&pblk->read_failed_gc);
+#ifdef CONFIG_NVM_DEBUG
+ pblk_print_failed_rqd(pblk, &rqd, rqd.error);
+#endif
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(*secs_to_gc, &pblk->sync_reads);
+ atomic_long_add(*secs_to_gc, &pblk->recov_gc_reads);
+ atomic_long_sub(*secs_to_gc, &pblk->inflight_reads);
+#endif
+
+out:
+ if (rqd.nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ return NVM_IO_OK;
+
+err_free_dma:
+ if (rqd.nr_ppas > 1)
+ nvm_dev_dma_free(dev->parent, rqd.ppa_list, rqd.dma_ppa_list);
+ return NVM_IO_ERR;
+}
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
new file mode 100644
index 000000000000..f8f85087cd3c
--- /dev/null
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -0,0 +1,998 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-recovery.c - pblk's recovery path
+ */
+
+#include "pblk.h"
+
+void pblk_submit_rec(struct work_struct *work)
+{
+ struct pblk_rec_ctx *recovery =
+ container_of(work, struct pblk_rec_ctx, ws_rec);
+ struct pblk *pblk = recovery->pblk;
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_rq *rqd = recovery->rqd;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ int max_secs = nvm_max_phys_sects(dev);
+ struct bio *bio;
+ unsigned int nr_rec_secs;
+ unsigned int pgs_read;
+ int ret;
+
+ nr_rec_secs = bitmap_weight((unsigned long int *)&rqd->ppa_status,
+ max_secs);
+
+ bio = bio_alloc(GFP_KERNEL, nr_rec_secs);
+ if (!bio) {
+ pr_err("pblk: not able to create recovery bio\n");
+ return;
+ }
+
+ bio->bi_iter.bi_sector = 0;
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ rqd->bio = bio;
+ rqd->nr_ppas = nr_rec_secs;
+
+ pgs_read = pblk_rb_read_to_bio_list(&pblk->rwb, bio, &recovery->failed,
+ nr_rec_secs);
+ if (pgs_read != nr_rec_secs) {
+ pr_err("pblk: could not read recovery entries\n");
+ goto err;
+ }
+
+ if (pblk_setup_w_rec_rq(pblk, rqd, c_ctx)) {
+ pr_err("pblk: could not setup recovery request\n");
+ goto err;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(nr_rec_secs, &pblk->recov_writes);
+#endif
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ goto err;
+ }
+
+ mempool_free(recovery, pblk->rec_pool);
+ return;
+
+err:
+ bio_put(bio);
+ pblk_free_rqd(pblk, rqd, WRITE);
+}
+
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+ struct pblk_rec_ctx *recovery, u64 *comp_bits,
+ unsigned int comp)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ int max_secs = nvm_max_phys_sects(dev);
+ struct nvm_rq *rec_rqd;
+ struct pblk_c_ctx *rec_ctx;
+ int nr_entries = c_ctx->nr_valid + c_ctx->nr_padded;
+
+ rec_rqd = pblk_alloc_rqd(pblk, WRITE);
+ if (IS_ERR(rec_rqd)) {
+ pr_err("pblk: could not create recovery req.\n");
+ return -ENOMEM;
+ }
+
+ rec_ctx = nvm_rq_to_pdu(rec_rqd);
+
+ /* Copy completion bitmap, but exclude the first X completed entries */
+ bitmap_shift_right((unsigned long int *)&rec_rqd->ppa_status,
+ (unsigned long int *)comp_bits,
+ comp, max_secs);
+
+ /* Save the context for the entries that need to be re-written and
+ * update current context with the completed entries.
+ */
+ rec_ctx->sentry = pblk_rb_wrap_pos(&pblk->rwb, c_ctx->sentry + comp);
+ if (comp >= c_ctx->nr_valid) {
+ rec_ctx->nr_valid = 0;
+ rec_ctx->nr_padded = nr_entries - comp;
+
+ c_ctx->nr_padded = comp - c_ctx->nr_valid;
+ } else {
+ rec_ctx->nr_valid = c_ctx->nr_valid - comp;
+ rec_ctx->nr_padded = c_ctx->nr_padded;
+
+ c_ctx->nr_valid = comp;
+ c_ctx->nr_padded = 0;
+ }
+
+ recovery->rqd = rec_rqd;
+ recovery->pblk = pblk;
+
+ return 0;
+}
+
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta)
+{
+ u32 crc;
+
+ crc = pblk_calc_emeta_crc(pblk, emeta);
+ if (le32_to_cpu(emeta->crc) != crc)
+ return NULL;
+
+ if (le32_to_cpu(emeta->header.identifier) != PBLK_MAGIC)
+ return NULL;
+
+ return pblk_line_emeta_to_lbas(emeta);
+}
+
+static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct line_emeta *emeta = line->emeta;
+ __le64 *lba_list;
+ int data_start;
+ int nr_data_lbas, nr_valid_lbas, nr_lbas = 0;
+ int i;
+
+ lba_list = pblk_recov_get_lba_list(pblk, emeta);
+ if (!lba_list)
+ return 1;
+
+ data_start = pblk_line_smeta_start(pblk, line) + lm->smeta_sec;
+ nr_data_lbas = lm->sec_per_line - lm->emeta_sec;
+ nr_valid_lbas = le64_to_cpu(emeta->nr_valid_lbas);
+
+ for (i = data_start; i < nr_data_lbas && nr_lbas < nr_valid_lbas; i++) {
+ struct ppa_addr ppa;
+ int pos;
+
+ ppa = addr_to_pblk_ppa(pblk, i, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+
+ /* Do not update bad blocks */
+ if (test_bit(pos, line->blk_bitmap))
+ continue;
+
+ if (le64_to_cpu(lba_list[i]) == ADDR_EMPTY) {
+ spin_lock(&line->lock);
+ if (test_and_set_bit(i, line->invalid_bitmap))
+ WARN_ONCE(1, "pblk: rec. double invalidate:\n");
+ else
+ line->vsc--;
+ spin_unlock(&line->lock);
+
+ continue;
+ }
+
+ pblk_update_map(pblk, le64_to_cpu(lba_list[i]), ppa);
+ nr_lbas++;
+ }
+
+ if (nr_valid_lbas != nr_lbas)
+ pr_err("pblk: line %d - inconsistent lba list(%llu/%d)\n",
+ line->id, line->emeta->nr_valid_lbas, nr_lbas);
+
+ line->left_msecs = 0;
+
+ return 0;
+}
+
+static int pblk_calc_sec_in_line(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ int nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+
+ return lm->sec_per_line - lm->smeta_sec - lm->emeta_sec -
+ nr_bb * geo->sec_per_blk;
+}
+
+struct pblk_recov_alloc {
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ void *data;
+ dma_addr_t dma_ppa_list;
+ dma_addr_t dma_meta_list;
+};
+
+static int pblk_recov_read_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, u64 r_ptr)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 r_ptr_int;
+ int left_ppas;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ left_ppas = line->cur_sec - r_ptr;
+ if (!left_ppas)
+ return 0;
+
+ r_ptr_int = r_ptr;
+
+next_read_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ r_ptr_int += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, r_ptr_int++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, r_ptr_int, line->id);
+ }
+
+ /* If read fails, more padding is needed */
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ return -EINTR;
+ }
+
+ reinit_completion(&wait);
+
+ /* At this point, the read should not fail. If it does, it is a problem
+ * we cannot recover from here. Need FTL log.
+ */
+ if (rqd->error) {
+ pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+ return -EINTR;
+ }
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_read_rq;
+
+ return 0;
+}
+
+static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, int left_ppas)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ __le64 *lba_list = pblk_line_emeta_to_lbas(line->emeta);
+ u64 w_ptr = line->cur_sec;
+ int left_line_ppas = line->left_msecs;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+next_pad_rq:
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PWRITE;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ w_ptr += pblk->min_write_pgs;
+ ppa = addr_to_pblk_ppa(pblk, w_ptr, line->id);
+ pos = pblk_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++) {
+ struct ppa_addr dev_ppa;
+
+ dev_ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+
+ pblk_map_invalidate(pblk, dev_ppa);
+ meta_list[i].lba = cpu_to_le64(ADDR_EMPTY);
+ lba_list[w_ptr] = cpu_to_le64(ADDR_EMPTY);
+ rqd->ppa_list[i] = dev_ppa;
+ }
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery write timed out\n");
+ }
+ reinit_completion(&wait);
+
+ left_line_ppas -= rq_ppas;
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0 && left_line_ppas)
+ goto next_pad_rq;
+
+ return 0;
+}
+
+/* When this function is called, it means that not all upper pages have been
+ * written in a page that contains valid data. In order to recover this data, we
+ * first find the write pointer on the device, then we pad all necessary
+ * sectors, and finally attempt to read the valid data
+ */
+static int pblk_recov_scan_all_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 w_ptr = 0, r_ptr;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ int rec_round;
+ int left_ppas = pblk_calc_sec_in_line(pblk, line) - line->cur_sec;
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ /* we could recover up until the line write pointer */
+ r_ptr = line->cur_sec;
+ rec_round = 0;
+
+next_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ w_ptr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ w_ptr += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, w_ptr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, w_ptr++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, w_ptr, line->id);
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ }
+ reinit_completion(&wait);
+
+ /* This should not happen since the read failed during normal recovery,
+ * but the media works funny sometimes...
+ */
+ if (!rec_round++ && !rqd->error) {
+ rec_round = 0;
+ for (i = 0; i < rqd->nr_ppas; i++, r_ptr++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+ }
+
+ /* Reached the end of the written line */
+ if (rqd->error == NVM_RSP_ERR_EMPTYPAGE) {
+ int pad_secs, nr_error_bits, bit;
+ int ret;
+
+ bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+ nr_error_bits = rqd->nr_ppas - bit;
+
+ /* Roll back failed sectors */
+ line->cur_sec -= nr_error_bits;
+ line->left_msecs += nr_error_bits;
+ bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+ pad_secs = pblk_pad_distance(pblk);
+ if (pad_secs > line->left_msecs)
+ pad_secs = line->left_msecs;
+
+ ret = pblk_recov_pad_oob(pblk, line, p, pad_secs);
+ if (ret)
+ pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+
+ ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
+ if (ret)
+ pr_err("pblk: OOB read failed (err:%d)\n", ret);
+
+ line->left_ssecs = line->left_msecs;
+ left_ppas = 0;
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_rq;
+
+ return ret;
+}
+
+static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line,
+ struct pblk_recov_alloc p, int *done)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct nvm_rq *rqd;
+ struct bio *bio;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ u64 paddr;
+ int rq_ppas, rq_len;
+ int i, j;
+ int ret = 0;
+ int left_ppas = pblk_calc_sec_in_line(pblk, line);
+ DECLARE_COMPLETION_ONSTACK(wait);
+
+ ppa_list = p.ppa_list;
+ meta_list = p.meta_list;
+ rqd = p.rqd;
+ data = p.data;
+ dma_ppa_list = p.dma_ppa_list;
+ dma_meta_list = p.dma_meta_list;
+
+ *done = 1;
+
+next_rq:
+ memset(rqd, 0, pblk_r_rq_size);
+
+ rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
+ if (!rq_ppas)
+ rq_ppas = pblk->min_write_pgs;
+ rq_len = rq_ppas * geo->sec_size;
+
+ bio = bio_map_kern(dev->q, data, rq_len, GFP_KERNEL);
+ if (IS_ERR(bio))
+ return PTR_ERR(bio);
+
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_READ, 0);
+
+ rqd->bio = bio;
+ rqd->opcode = NVM_OP_PREAD;
+ rqd->flags = pblk_set_read_mode(pblk);
+ rqd->meta_list = meta_list;
+ rqd->nr_ppas = rq_ppas;
+ rqd->ppa_list = ppa_list;
+ rqd->dma_ppa_list = dma_ppa_list;
+ rqd->dma_meta_list = dma_meta_list;
+ rqd->end_io = pblk_end_io_sync;
+ rqd->private = &wait;
+
+ for (i = 0; i < rqd->nr_ppas; ) {
+ struct ppa_addr ppa;
+ int pos;
+
+ paddr = pblk_alloc_page(pblk, line, pblk->min_write_pgs);
+ ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+
+ while (test_bit(pos, line->blk_bitmap)) {
+ paddr += pblk->min_write_pgs;
+ ppa = addr_to_gen_ppa(pblk, paddr, line->id);
+ pos = pblk_dev_ppa_to_pos(geo, ppa);
+ }
+
+ for (j = 0; j < pblk->min_write_pgs; j++, i++, paddr++)
+ rqd->ppa_list[i] =
+ addr_to_gen_ppa(pblk, paddr, line->id);
+ }
+
+ ret = pblk_submit_io(pblk, rqd);
+ if (ret) {
+ pr_err("pblk: I/O submission failed: %d\n", ret);
+ bio_put(bio);
+ return ret;
+ }
+
+ if (!wait_for_completion_io_timeout(&wait,
+ msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
+ pr_err("pblk: L2P recovery read timed out\n");
+ }
+ reinit_completion(&wait);
+
+ /* Reached the end of the written line */
+ if (rqd->error) {
+ int nr_error_bits, bit;
+
+ bit = find_first_bit((void *)&rqd->ppa_status, rqd->nr_ppas);
+ nr_error_bits = rqd->nr_ppas - bit;
+
+ /* Roll back failed sectors */
+ line->cur_sec -= nr_error_bits;
+ line->left_msecs += nr_error_bits;
+ line->left_ssecs = line->left_msecs;
+ bitmap_clear(line->map_bitmap, line->cur_sec, nr_error_bits);
+
+ left_ppas = 0;
+ rqd->nr_ppas = bit;
+
+ if (rqd->error != NVM_RSP_ERR_EMPTYPAGE)
+ *done = 0;
+ }
+
+ for (i = 0; i < rqd->nr_ppas; i++) {
+ u64 lba = le64_to_cpu(meta_list[i].lba);
+
+ if (lba == ADDR_EMPTY || lba > pblk->rl.nr_secs)
+ continue;
+
+ pblk_update_map(pblk, lba, rqd->ppa_list[i]);
+ }
+
+ left_ppas -= rq_ppas;
+ if (left_ppas > 0)
+ goto next_rq;
+
+ return ret;
+}
+
+/* Scan line for lbas on out of bound area */
+static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct nvm_rq *rqd;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ struct pblk_recov_alloc p;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+ int done, ret = 0;
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd))
+ return PTR_ERR(rqd);
+
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+ if (!meta_list) {
+ ret = -ENOMEM;
+ goto free_rqd;
+ }
+
+ ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+ data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+ if (!data) {
+ ret = -ENOMEM;
+ goto free_meta_list;
+ }
+
+ p.ppa_list = ppa_list;
+ p.meta_list = meta_list;
+ p.rqd = rqd;
+ p.data = data;
+ p.dma_ppa_list = dma_ppa_list;
+ p.dma_meta_list = dma_meta_list;
+
+ ret = pblk_recov_scan_oob(pblk, line, p, &done);
+ if (ret) {
+ pr_err("pblk: could not recover L2P from OOB\n");
+ goto out;
+ }
+
+ if (!done) {
+ ret = pblk_recov_scan_all_oob(pblk, line, p);
+ if (ret) {
+ pr_err("pblk: could not recover L2P from OOB\n");
+ goto out;
+ }
+ }
+
+ if (pblk_line_is_full(line))
+ pblk_line_recov_close(pblk, line);
+
+out:
+ kfree(data);
+free_meta_list:
+ nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+ pblk_free_rqd(pblk, rqd, READ);
+
+ return ret;
+}
+
+/* Insert lines ordered by sequence number (seq_num) on list */
+static void pblk_recov_line_add_ordered(struct list_head *head,
+ struct pblk_line *line)
+{
+ struct pblk_line *t = NULL;
+
+ list_for_each_entry(t, head, list)
+ if (t->seq_nr > line->seq_nr)
+ break;
+
+ __list_add(&line->list, t->list.prev, &t->list);
+}
+
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line, *tline, *data_line = NULL;
+ struct line_smeta *smeta;
+ struct line_emeta *emeta;
+ int found_lines = 0, recovered_lines = 0, open_lines = 0;
+ int is_next = 0;
+ int meta_line;
+ int i, valid_uuid = 0;
+ LIST_HEAD(recov_list);
+
+ /* TODO: Implement FTL snapshot */
+
+ /* Scan recovery - takes place when FTL snapshot fails */
+ spin_lock(&l_mg->free_lock);
+ meta_line = find_first_zero_bit(&l_mg->meta_bitmap, PBLK_DATA_LINES);
+ set_bit(meta_line, &l_mg->meta_bitmap);
+ smeta = l_mg->sline_meta[meta_line].meta;
+ emeta = l_mg->eline_meta[meta_line].meta;
+ spin_unlock(&l_mg->free_lock);
+
+ /* Order data lines using their sequence number */
+ for (i = 0; i < l_mg->nr_lines; i++) {
+ u32 crc;
+
+ line = &pblk->lines[i];
+
+ memset(smeta, 0, lm->smeta_len);
+ line->smeta = smeta;
+ line->lun_bitmap = ((void *)(smeta)) +
+ sizeof(struct line_smeta);
+
+ /* Lines that cannot be read are assumed as not written here */
+ if (pblk_line_read_smeta(pblk, line))
+ continue;
+
+ crc = pblk_calc_smeta_crc(pblk, smeta);
+ if (le32_to_cpu(smeta->crc) != crc)
+ continue;
+
+ if (le32_to_cpu(smeta->header.identifier) != PBLK_MAGIC)
+ continue;
+
+ if (le16_to_cpu(smeta->header.version) != 1) {
+ pr_err("pblk: found incompatible line version %u\n",
+ smeta->header.version);
+ return ERR_PTR(-EINVAL);
+ }
+
+ /* The first valid instance uuid is used for initialization */
+ if (!valid_uuid) {
+ memcpy(pblk->instance_uuid, smeta->header.uuid, 16);
+ valid_uuid = 1;
+ }
+
+ if (memcmp(pblk->instance_uuid, smeta->header.uuid, 16)) {
+ pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+ i);
+ continue;
+ }
+
+ /* Update line metadata */
+ spin_lock(&line->lock);
+ line->id = le32_to_cpu(line->smeta->header.id);
+ line->type = le16_to_cpu(line->smeta->header.type);
+ line->seq_nr = le64_to_cpu(line->smeta->seq_nr);
+ spin_unlock(&line->lock);
+
+ /* Update general metadata */
+ spin_lock(&l_mg->free_lock);
+ if (line->seq_nr >= l_mg->d_seq_nr)
+ l_mg->d_seq_nr = line->seq_nr + 1;
+ l_mg->nr_free_lines--;
+ spin_unlock(&l_mg->free_lock);
+
+ if (pblk_line_recov_alloc(pblk, line))
+ goto out;
+
+ pblk_recov_line_add_ordered(&recov_list, line);
+ found_lines++;
+ pr_debug("pblk: recovering data line %d, seq:%llu\n",
+ line->id, smeta->seq_nr);
+ }
+
+ if (!found_lines) {
+ pblk_setup_uuid(pblk);
+
+ spin_lock(&l_mg->free_lock);
+ WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+ &l_mg->meta_bitmap));
+ spin_unlock(&l_mg->free_lock);
+
+ goto out;
+ }
+
+ /* Verify closed blocks and recover this portion of L2P table*/
+ list_for_each_entry_safe(line, tline, &recov_list, list) {
+ int off, nr_bb;
+
+ recovered_lines++;
+ /* Calculate where emeta starts based on the line bb */
+ off = lm->sec_per_line - lm->emeta_sec;
+ nr_bb = bitmap_weight(line->blk_bitmap, lm->blk_per_line);
+ off -= nr_bb * geo->sec_per_pl;
+
+ memset(emeta, 0, lm->emeta_len);
+ line->emeta = emeta;
+ line->emeta_ssec = off;
+
+ if (pblk_line_read_emeta(pblk, line)) {
+ pblk_recov_l2p_from_oob(pblk, line);
+ goto next;
+ }
+
+ if (pblk_recov_l2p_from_emeta(pblk, line))
+ pblk_recov_l2p_from_oob(pblk, line);
+
+next:
+ if (pblk_line_is_full(line)) {
+ struct list_head *move_list;
+
+ spin_lock(&line->lock);
+ line->state = PBLK_LINESTATE_CLOSED;
+ move_list = pblk_line_gc_list(pblk, line);
+ spin_unlock(&line->lock);
+
+ spin_lock(&l_mg->gc_lock);
+ list_move_tail(&line->list, move_list);
+ spin_unlock(&l_mg->gc_lock);
+
+ mempool_free(line->map_bitmap, pblk->line_meta_pool);
+ line->map_bitmap = NULL;
+ line->smeta = NULL;
+ line->emeta = NULL;
+ } else {
+ if (open_lines > 1)
+ pr_err("pblk: failed to recover L2P\n");
+
+ open_lines++;
+ line->meta_line = meta_line;
+ data_line = line;
+ }
+ }
+
+ spin_lock(&l_mg->free_lock);
+ if (!open_lines) {
+ WARN_ON_ONCE(!test_and_clear_bit(meta_line,
+ &l_mg->meta_bitmap));
+ pblk_line_replace_data(pblk);
+ } else {
+ /* Allocate next line for preparation */
+ l_mg->data_next = pblk_line_get(pblk);
+ if (l_mg->data_next) {
+ l_mg->data_next->seq_nr = l_mg->d_seq_nr++;
+ l_mg->data_next->type = PBLK_LINETYPE_DATA;
+ is_next = 1;
+ }
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ if (is_next) {
+ pblk_line_erase(pblk, l_mg->data_next);
+ pblk_rl_free_lines_dec(&pblk->rl, l_mg->data_next);
+ }
+
+out:
+ if (found_lines != recovered_lines)
+ pr_err("pblk: failed to recover all found lines %d/%d\n",
+ found_lines, recovered_lines);
+
+ return data_line;
+}
+
+/*
+ * Pad until smeta can be read on current data line
+ */
+void pblk_recov_pad(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line *line;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct nvm_rq *rqd;
+ struct pblk_recov_alloc p;
+ struct ppa_addr *ppa_list;
+ struct pblk_sec_meta *meta_list;
+ void *data;
+ dma_addr_t dma_ppa_list, dma_meta_list;
+
+ spin_lock(&l_mg->free_lock);
+ line = l_mg->data_line;
+ spin_unlock(&l_mg->free_lock);
+
+ rqd = pblk_alloc_rqd(pblk, READ);
+ if (IS_ERR(rqd))
+ return;
+
+ meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL, &dma_meta_list);
+ if (!meta_list)
+ goto free_rqd;
+
+ ppa_list = (void *)(meta_list) + pblk_dma_meta_size;
+ dma_ppa_list = dma_meta_list + pblk_dma_meta_size;
+
+ data = kcalloc(pblk->max_write_pgs, geo->sec_size, GFP_KERNEL);
+ if (!data)
+ goto free_meta_list;
+
+ p.ppa_list = ppa_list;
+ p.meta_list = meta_list;
+ p.rqd = rqd;
+ p.data = data;
+ p.dma_ppa_list = dma_ppa_list;
+ p.dma_meta_list = dma_meta_list;
+
+ if (pblk_recov_pad_oob(pblk, line, p, line->left_msecs)) {
+ pr_err("pblk: Tear down padding failed\n");
+ goto free_data;
+ }
+
+ pblk_line_close(pblk, line);
+
+free_data:
+ kfree(data);
+free_meta_list:
+ nvm_dev_dma_free(dev->parent, meta_list, dma_meta_list);
+free_rqd:
+ pblk_free_rqd(pblk, rqd, READ);
+}
diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c
new file mode 100644
index 000000000000..ab7cbb144f3f
--- /dev/null
+++ b/drivers/lightnvm/pblk-rl.c
@@ -0,0 +1,184 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-rl.c - pblk's rate limiter for user I/O
+ *
+ */
+
+#include "pblk.h"
+
+static void pblk_rl_kick_u_timer(struct pblk_rl *rl)
+{
+ mod_timer(&rl->u_timer, jiffies + msecs_to_jiffies(5000));
+}
+
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+ int rb_user_cnt = atomic_read(&rl->rb_user_cnt);
+
+ return (!(rb_user_cnt + nr_entries > rl->rb_user_max));
+}
+
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries)
+{
+ int rb_gc_cnt = atomic_read(&rl->rb_gc_cnt);
+ int rb_user_active;
+
+ /* If there is no user I/O let GC take over space on the write buffer */
+ rb_user_active = READ_ONCE(rl->rb_user_active);
+ return (!(rb_gc_cnt + nr_entries > rl->rb_gc_max && rb_user_active));
+}
+
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries)
+{
+ atomic_add(nr_entries, &rl->rb_user_cnt);
+
+ /* Release user I/O state. Protect from GC */
+ smp_store_release(&rl->rb_user_active, 1);
+ pblk_rl_kick_u_timer(rl);
+}
+
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries)
+{
+ atomic_add(nr_entries, &rl->rb_gc_cnt);
+}
+
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc)
+{
+ atomic_sub(nr_user, &rl->rb_user_cnt);
+ atomic_sub(nr_gc, &rl->rb_gc_cnt);
+}
+
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl)
+{
+ return atomic_read(&rl->free_blocks);
+}
+
+/*
+ * We check for (i) the number of free blocks in the current LUN and (ii) the
+ * total number of free blocks in the pblk instance. This is to even out the
+ * number of free blocks on each LUN when GC kicks in.
+ *
+ * Only the total number of free blocks is used to configure the rate limiter.
+ */
+static int pblk_rl_update_rates(struct pblk_rl *rl, unsigned long max)
+{
+ unsigned long free_blocks = pblk_rl_nr_free_blks(rl);
+
+ if (free_blocks >= rl->high) {
+ rl->rb_user_max = max - rl->rb_gc_rsv;
+ rl->rb_gc_max = rl->rb_gc_rsv;
+ rl->rb_state = PBLK_RL_HIGH;
+ } else if (free_blocks < rl->high) {
+ int shift = rl->high_pw - rl->rb_windows_pw;
+ int user_windows = free_blocks >> shift;
+ int user_max = user_windows << PBLK_MAX_REQ_ADDRS_PW;
+ int gc_max;
+
+ rl->rb_user_max = user_max;
+ gc_max = max - rl->rb_user_max;
+ rl->rb_gc_max = max(gc_max, rl->rb_gc_rsv);
+
+ if (free_blocks > rl->low)
+ rl->rb_state = PBLK_RL_MID;
+ else
+ rl->rb_state = PBLK_RL_LOW;
+ }
+
+ return rl->rb_state;
+}
+
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv)
+{
+ rl->rb_gc_rsv = rl->rb_gc_max = rsv;
+}
+
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line)
+{
+ struct pblk *pblk = container_of(rl, struct pblk, rl);
+ int blk_in_line = atomic_read(&line->blk_in_line);
+ int ret;
+
+ atomic_add(blk_in_line, &rl->free_blocks);
+ /* Rates will not change that often - no need to lock update */
+ ret = pblk_rl_update_rates(rl, rl->rb_budget);
+
+ if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+ pblk_gc_should_start(pblk);
+ else
+ pblk_gc_should_stop(pblk);
+}
+
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line)
+{
+ struct pblk *pblk = container_of(rl, struct pblk, rl);
+ int blk_in_line = atomic_read(&line->blk_in_line);
+ int ret;
+
+ atomic_sub(blk_in_line, &rl->free_blocks);
+
+ /* Rates will not change that often - no need to lock update */
+ ret = pblk_rl_update_rates(rl, rl->rb_budget);
+ if (ret == (PBLK_RL_MID | PBLK_RL_LOW))
+ pblk_gc_should_start(pblk);
+ else
+ pblk_gc_should_stop(pblk);
+}
+
+int pblk_rl_gc_thrs(struct pblk_rl *rl)
+{
+ return rl->high;
+}
+
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl)
+{
+ return rl->rb_user_max;
+}
+
+static void pblk_rl_u_timer(unsigned long data)
+{
+ struct pblk_rl *rl = (struct pblk_rl *)data;
+
+ /* Release user I/O state. Protect from GC */
+ smp_store_release(&rl->rb_user_active, 0);
+}
+
+void pblk_rl_free(struct pblk_rl *rl)
+{
+ del_timer(&rl->u_timer);
+}
+
+void pblk_rl_init(struct pblk_rl *rl, int budget)
+{
+ unsigned int rb_windows;
+
+ rl->high = rl->total_blocks / PBLK_USER_HIGH_THRS;
+ rl->low = rl->total_blocks / PBLK_USER_LOW_THRS;
+ rl->high_pw = get_count_order(rl->high);
+
+ /* This will always be a power-of-2 */
+ rb_windows = budget / PBLK_MAX_REQ_ADDRS;
+ rl->rb_windows_pw = get_count_order(rb_windows) + 1;
+
+ /* To start with, all buffer is available to user I/O writers */
+ rl->rb_budget = budget;
+ rl->rb_user_max = budget;
+ atomic_set(&rl->rb_user_cnt, 0);
+ rl->rb_gc_max = 0;
+ rl->rb_state = PBLK_RL_HIGH;
+ atomic_set(&rl->rb_gc_cnt, 0);
+
+ setup_timer(&rl->u_timer, pblk_rl_u_timer, (unsigned long)rl);
+ rl->rb_user_active = 0;
+}
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
new file mode 100644
index 000000000000..f0af1d1ceeff
--- /dev/null
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -0,0 +1,507 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * Implementation of a physical block-device target for Open-channel SSDs.
+ *
+ * pblk-sysfs.c - pblk's sysfs
+ *
+ */
+
+#include "pblk.h"
+
+static ssize_t pblk_sysfs_luns_show(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_lun *rlun;
+ ssize_t sz = 0;
+ int i;
+
+ for (i = 0; i < geo->nr_luns; i++) {
+ int active = 1;
+
+ rlun = &pblk->luns[i];
+ if (!down_trylock(&rlun->wr_sem)) {
+ active = 0;
+ up(&rlun->wr_sem);
+ }
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "pblk: pos:%d, ch:%d, lun:%d - %d\n",
+ i,
+ rlun->bppa.g.ch,
+ rlun->bppa.g.lun,
+ active);
+ }
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_rate_limiter(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int free_blocks, total_blocks;
+ int rb_user_max, rb_user_cnt;
+ int rb_gc_max, rb_gc_rsv, rb_gc_cnt, rb_budget, rb_state;
+
+ free_blocks = atomic_read(&pblk->rl.free_blocks);
+ rb_user_max = pblk->rl.rb_user_max;
+ rb_user_cnt = atomic_read(&pblk->rl.rb_user_cnt);
+ rb_gc_max = pblk->rl.rb_gc_max;
+ rb_gc_rsv = pblk->rl.rb_gc_rsv;
+ rb_gc_cnt = atomic_read(&pblk->rl.rb_gc_cnt);
+ rb_budget = pblk->rl.rb_budget;
+ rb_state = pblk->rl.rb_state;
+
+ total_blocks = geo->blks_per_lun * geo->nr_luns;
+
+ return snprintf(page, PAGE_SIZE,
+ "u:%u/%u,gc:%u/%u/%u(%u/%u)(stop:<%u,full:>%u,free:%d/%d)-%d\n",
+ rb_user_cnt,
+ rb_user_max,
+ rb_gc_cnt,
+ rb_gc_max,
+ rb_gc_rsv,
+ rb_state,
+ rb_budget,
+ pblk->rl.low,
+ pblk->rl.high,
+ free_blocks,
+ total_blocks,
+ READ_ONCE(pblk->rl.rb_user_active));
+}
+
+static ssize_t pblk_sysfs_gc_state_show(struct pblk *pblk, char *page)
+{
+ int gc_enabled, gc_active;
+
+ pblk_gc_sysfs_state_show(pblk, &gc_enabled, &gc_active);
+ return snprintf(page, PAGE_SIZE, "gc_enabled=%d, gc_active=%d\n",
+ gc_enabled, gc_active);
+}
+
+static ssize_t pblk_sysfs_stats(struct pblk *pblk, char *page)
+{
+ ssize_t sz;
+
+ sz = snprintf(page, PAGE_SIZE,
+ "read_failed=%lu, read_high_ecc=%lu, read_empty=%lu, read_failed_gc=%lu, write_failed=%lu, erase_failed=%lu\n",
+ atomic_long_read(&pblk->read_failed),
+ atomic_long_read(&pblk->read_high_ecc),
+ atomic_long_read(&pblk->read_empty),
+ atomic_long_read(&pblk->read_failed_gc),
+ atomic_long_read(&pblk->write_failed),
+ atomic_long_read(&pblk->erase_failed));
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_write_buffer(struct pblk *pblk, char *page)
+{
+ return pblk_rb_sysfs(&pblk->rwb, page);
+}
+
+static ssize_t pblk_sysfs_ppaf(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ ssize_t sz = 0;
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "g:(b:%d)blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+ pblk->ppaf_bitsize,
+ pblk->ppaf.blk_offset, geo->ppaf.blk_len,
+ pblk->ppaf.pg_offset, geo->ppaf.pg_len,
+ pblk->ppaf.lun_offset, geo->ppaf.lun_len,
+ pblk->ppaf.ch_offset, geo->ppaf.ch_len,
+ pblk->ppaf.pln_offset, geo->ppaf.pln_len,
+ pblk->ppaf.sec_offset, geo->ppaf.sect_len);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "d:blk:%d/%d,pg:%d/%d,lun:%d/%d,ch:%d/%d,pl:%d/%d,sec:%d/%d\n",
+ geo->ppaf.blk_offset, geo->ppaf.blk_len,
+ geo->ppaf.pg_offset, geo->ppaf.pg_len,
+ geo->ppaf.lun_offset, geo->ppaf.lun_len,
+ geo->ppaf.ch_offset, geo->ppaf.ch_len,
+ geo->ppaf.pln_offset, geo->ppaf.pln_len,
+ geo->ppaf.sect_offset, geo->ppaf.sect_len);
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line_mgmt *l_mg = &pblk->l_mg;
+ struct pblk_line *line;
+ ssize_t sz = 0;
+ int nr_free_lines;
+ int cur_data, cur_log;
+ int free_line_cnt = 0, closed_line_cnt = 0;
+ int d_line_cnt = 0, l_line_cnt = 0;
+ int gc_full = 0, gc_high = 0, gc_mid = 0, gc_low = 0, gc_empty = 0;
+ int free = 0, bad = 0, cor = 0;
+ int msecs = 0, ssecs = 0, cur_sec = 0, vsc = 0, sec_in_line = 0;
+ int map_weight = 0, meta_weight = 0;
+
+ spin_lock(&l_mg->free_lock);
+ cur_data = (l_mg->data_line) ? l_mg->data_line->id : -1;
+ cur_log = (l_mg->log_line) ? l_mg->log_line->id : -1;
+ nr_free_lines = l_mg->nr_free_lines;
+
+ list_for_each_entry(line, &l_mg->free_list, list)
+ free_line_cnt++;
+ spin_unlock(&l_mg->free_lock);
+
+ spin_lock(&l_mg->gc_lock);
+ list_for_each_entry(line, &l_mg->gc_full_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_full++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_high_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_high++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_mid_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_mid++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_low_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_low++;
+ }
+
+ list_for_each_entry(line, &l_mg->gc_empty_list, list) {
+ if (line->type == PBLK_LINETYPE_DATA)
+ d_line_cnt++;
+ else if (line->type == PBLK_LINETYPE_LOG)
+ l_line_cnt++;
+ closed_line_cnt++;
+ gc_empty++;
+ }
+
+ list_for_each_entry(line, &l_mg->free_list, list)
+ free++;
+ list_for_each_entry(line, &l_mg->bad_list, list)
+ bad++;
+ list_for_each_entry(line, &l_mg->corrupt_list, list)
+ cor++;
+ spin_unlock(&l_mg->gc_lock);
+
+ spin_lock(&l_mg->free_lock);
+ if (l_mg->data_line) {
+ cur_sec = l_mg->data_line->cur_sec;
+ msecs = l_mg->data_line->left_msecs;
+ ssecs = l_mg->data_line->left_ssecs;
+ vsc = l_mg->data_line->vsc;
+ sec_in_line = l_mg->data_line->sec_in_line;
+ meta_weight = bitmap_weight(&l_mg->meta_bitmap,
+ PBLK_DATA_LINES);
+ map_weight = bitmap_weight(l_mg->data_line->map_bitmap,
+ lm->sec_per_line);
+ }
+ spin_unlock(&l_mg->free_lock);
+
+ if (nr_free_lines != free_line_cnt)
+ pr_err("pblk: corrupted free line list\n");
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "line: nluns:%d, nblks:%d, nsecs:%d\n",
+ geo->nr_luns, lm->blk_per_line, lm->sec_per_line);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "lines:d:%d,l:%d-f:%d(%d),b:%d,co:%d,c:%d(d:%d,l:%d)t:%d\n",
+ cur_data, cur_log,
+ free, nr_free_lines, bad, cor,
+ closed_line_cnt,
+ d_line_cnt, l_line_cnt,
+ l_mg->nr_lines);
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "GC: full:%d, high:%d, mid:%d, low:%d, empty:%d, queue:%d\n",
+ gc_full, gc_high, gc_mid, gc_low, gc_empty,
+ atomic_read(&pblk->gc.inflight_gc));
+
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "data (%d) cur:%d, left:%d/%d, vsc:%d, s:%d, map:%d/%d (%d)\n",
+ cur_data, cur_sec, msecs, ssecs, vsc, sec_in_line,
+ map_weight, lm->sec_per_line, meta_weight);
+
+ return sz;
+}
+
+static ssize_t pblk_sysfs_lines_info(struct pblk *pblk, char *page)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ struct pblk_line_meta *lm = &pblk->lm;
+ ssize_t sz = 0;
+
+ sz = snprintf(page, PAGE_SIZE - sz,
+ "smeta - len:%d, secs:%d\n",
+ lm->smeta_len, lm->smeta_sec);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "emeta - len:%d, sec:%d, bb_start:%d\n",
+ lm->emeta_len, lm->emeta_sec,
+ lm->emeta_bb);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "bitmap lengths: sec:%d, blk:%d, lun:%d\n",
+ lm->sec_bitmap_len,
+ lm->blk_bitmap_len,
+ lm->lun_bitmap_len);
+ sz += snprintf(page + sz, PAGE_SIZE - sz,
+ "blk_line:%d, sec_line:%d, sec_blk:%d\n",
+ lm->blk_per_line,
+ lm->sec_per_line,
+ geo->sec_per_blk);
+
+ return sz;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
+{
+ return snprintf(page, PAGE_SIZE,
+ "%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\t%lu\n",
+ atomic_long_read(&pblk->inflight_writes),
+ atomic_long_read(&pblk->inflight_reads),
+ atomic_long_read(&pblk->req_writes),
+ atomic_long_read(&pblk->nr_flush),
+ atomic_long_read(&pblk->padded_writes),
+ atomic_long_read(&pblk->padded_wb),
+ atomic_long_read(&pblk->sub_writes),
+ atomic_long_read(&pblk->sync_writes),
+ atomic_long_read(&pblk->compl_writes),
+ atomic_long_read(&pblk->recov_writes),
+ atomic_long_read(&pblk->recov_gc_writes),
+ atomic_long_read(&pblk->recov_gc_reads),
+ atomic_long_read(&pblk->sync_reads));
+}
+#endif
+
+static ssize_t pblk_sysfs_rate_store(struct pblk *pblk, const char *page,
+ size_t len)
+{
+ struct pblk_gc *gc = &pblk->gc;
+ size_t c_len;
+ int value;
+
+ c_len = strcspn(page, "\n");
+ if (c_len >= len)
+ return -EINVAL;
+
+ if (kstrtouint(page, 0, &value))
+ return -EINVAL;
+
+ spin_lock(&gc->lock);
+ pblk_rl_set_gc_rsc(&pblk->rl, value);
+ spin_unlock(&gc->lock);
+
+ return len;
+}
+
+static ssize_t pblk_sysfs_gc_force(struct pblk *pblk, const char *page,
+ size_t len)
+{
+ size_t c_len;
+ int force;
+
+ c_len = strcspn(page, "\n");
+ if (c_len >= len)
+ return -EINVAL;
+
+ if (kstrtouint(page, 0, &force))
+ return -EINVAL;
+
+ if (force < 0 || force > 1)
+ return -EINVAL;
+
+ pblk_gc_sysfs_force(pblk, force);
+
+ return len;
+}
+
+static struct attribute sys_write_luns = {
+ .name = "write_luns",
+ .mode = 0444,
+};
+
+static struct attribute sys_rate_limiter_attr = {
+ .name = "rate_limiter",
+ .mode = 0444,
+};
+
+static struct attribute sys_gc_state = {
+ .name = "gc_state",
+ .mode = 0444,
+};
+
+static struct attribute sys_errors_attr = {
+ .name = "errors",
+ .mode = 0444,
+};
+
+static struct attribute sys_rb_attr = {
+ .name = "write_buffer",
+ .mode = 0444,
+};
+
+static struct attribute sys_stats_ppaf_attr = {
+ .name = "ppa_format",
+ .mode = 0444,
+};
+
+static struct attribute sys_lines_attr = {
+ .name = "lines",
+ .mode = 0444,
+};
+
+static struct attribute sys_lines_info_attr = {
+ .name = "lines_info",
+ .mode = 0444,
+};
+
+static struct attribute sys_gc_force = {
+ .name = "gc_force",
+ .mode = 0200,
+};
+
+static struct attribute sys_gc_rl_max = {
+ .name = "gc_rl_max",
+ .mode = 0200,
+};
+
+#ifdef CONFIG_NVM_DEBUG
+static struct attribute sys_stats_debug_attr = {
+ .name = "stats",
+ .mode = 0444,
+};
+#endif
+
+static struct attribute *pblk_attrs[] = {
+ &sys_write_luns,
+ &sys_rate_limiter_attr,
+ &sys_errors_attr,
+ &sys_gc_state,
+ &sys_gc_force,
+ &sys_gc_rl_max,
+ &sys_rb_attr,
+ &sys_stats_ppaf_attr,
+ &sys_lines_attr,
+ &sys_lines_info_attr,
+#ifdef CONFIG_NVM_DEBUG
+ &sys_stats_debug_attr,
+#endif
+ NULL,
+};
+
+static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
+ char *buf)
+{
+ struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+ if (strcmp(attr->name, "rate_limiter") == 0)
+ return pblk_sysfs_rate_limiter(pblk, buf);
+ else if (strcmp(attr->name, "write_luns") == 0)
+ return pblk_sysfs_luns_show(pblk, buf);
+ else if (strcmp(attr->name, "gc_state") == 0)
+ return pblk_sysfs_gc_state_show(pblk, buf);
+ else if (strcmp(attr->name, "errors") == 0)
+ return pblk_sysfs_stats(pblk, buf);
+ else if (strcmp(attr->name, "write_buffer") == 0)
+ return pblk_sysfs_write_buffer(pblk, buf);
+ else if (strcmp(attr->name, "ppa_format") == 0)
+ return pblk_sysfs_ppaf(pblk, buf);
+ else if (strcmp(attr->name, "lines") == 0)
+ return pblk_sysfs_lines(pblk, buf);
+ else if (strcmp(attr->name, "lines_info") == 0)
+ return pblk_sysfs_lines_info(pblk, buf);
+#ifdef CONFIG_NVM_DEBUG
+ else if (strcmp(attr->name, "stats") == 0)
+ return pblk_sysfs_stats_debug(pblk, buf);
+#endif
+ return 0;
+}
+
+static ssize_t pblk_sysfs_store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t len)
+{
+ struct pblk *pblk = container_of(kobj, struct pblk, kobj);
+
+ if (strcmp(attr->name, "gc_rl_max") == 0)
+ return pblk_sysfs_rate_store(pblk, buf, len);
+ else if (strcmp(attr->name, "gc_force") == 0)
+ return pblk_sysfs_gc_force(pblk, buf, len);
+
+ return 0;
+}
+
+static const struct sysfs_ops pblk_sysfs_ops = {
+ .show = pblk_sysfs_show,
+ .store = pblk_sysfs_store,
+};
+
+static struct kobj_type pblk_ktype = {
+ .sysfs_ops = &pblk_sysfs_ops,
+ .default_attrs = pblk_attrs,
+};
+
+int pblk_sysfs_init(struct gendisk *tdisk)
+{
+ struct pblk *pblk = tdisk->private_data;
+ struct device *parent_dev = disk_to_dev(pblk->disk);
+ int ret;
+
+ ret = kobject_init_and_add(&pblk->kobj, &pblk_ktype,
+ kobject_get(&parent_dev->kobj),
+ "%s", "pblk");
+ if (ret) {
+ pr_err("pblk: could not register %s/pblk\n",
+ tdisk->disk_name);
+ return ret;
+ }
+
+ kobject_uevent(&pblk->kobj, KOBJ_ADD);
+ return 0;
+}
+
+void pblk_sysfs_exit(struct gendisk *tdisk)
+{
+ struct pblk *pblk = tdisk->private_data;
+
+ kobject_uevent(&pblk->kobj, KOBJ_REMOVE);
+ kobject_del(&pblk->kobj);
+ kobject_put(&pblk->kobj);
+}
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
new file mode 100644
index 000000000000..aef6fd7c4a0c
--- /dev/null
+++ b/drivers/lightnvm/pblk-write.c
@@ -0,0 +1,414 @@
+/*
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Javier Gonzalez <javier@cnexlabs.com>
+ * Matias Bjorling <matias@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * pblk-write.c - pblk's write path from write buffer to media
+ */
+
+#include "pblk.h"
+
+static void pblk_sync_line(struct pblk *pblk, struct pblk_line *line)
+{
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_inc(&pblk->sync_writes);
+#endif
+
+ /* Counter protected by rb sync lock */
+ line->left_ssecs--;
+ if (!line->left_ssecs)
+ pblk_line_run_ws(pblk, line, NULL, pblk_line_close_ws);
+}
+
+static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct bio *original_bio;
+ unsigned long ret;
+ int i;
+
+ for (i = 0; i < c_ctx->nr_valid; i++) {
+ struct pblk_w_ctx *w_ctx;
+ struct ppa_addr p;
+ struct pblk_line *line;
+
+ w_ctx = pblk_rb_w_ctx(&pblk->rwb, c_ctx->sentry + i);
+
+ p = rqd->ppa_list[i];
+ line = &pblk->lines[pblk_dev_ppa_to_line(p)];
+ pblk_sync_line(pblk, line);
+
+ while ((original_bio = bio_list_pop(&w_ctx->bios)))
+ bio_endio(original_bio);
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(c_ctx->nr_valid, &pblk->compl_writes);
+#endif
+
+ ret = pblk_rb_sync_advance(&pblk->rwb, c_ctx->nr_valid);
+
+ if (rqd->meta_list)
+ nvm_dev_dma_free(dev->parent, rqd->meta_list,
+ rqd->dma_meta_list);
+
+ bio_put(rqd->bio);
+ pblk_free_rqd(pblk, rqd, WRITE);
+
+ return ret;
+}
+
+static unsigned long pblk_end_queued_w_bio(struct pblk *pblk,
+ struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ list_del(&c_ctx->list);
+ return pblk_end_w_bio(pblk, rqd, c_ctx);
+}
+
+static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_c_ctx *c, *r;
+ unsigned long flags;
+ unsigned long pos;
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
+#endif
+
+ pblk_up_rq(pblk, rqd->ppa_list, rqd->nr_ppas, c_ctx->lun_bitmap);
+
+ pos = pblk_rb_sync_init(&pblk->rwb, &flags);
+ if (pos == c_ctx->sentry) {
+ pos = pblk_end_w_bio(pblk, rqd, c_ctx);
+
+retry:
+ list_for_each_entry_safe(c, r, &pblk->compl_list, list) {
+ rqd = nvm_rq_from_c_ctx(c);
+ if (c->sentry == pos) {
+ pos = pblk_end_queued_w_bio(pblk, rqd, c);
+ goto retry;
+ }
+ }
+ } else {
+ WARN_ON(nvm_rq_from_c_ctx(c_ctx) != rqd);
+ list_add_tail(&c_ctx->list, &pblk->compl_list);
+ }
+ pblk_rb_sync_end(&pblk->rwb, &flags);
+}
+
+/* When a write fails, we are not sure whether the block has grown bad or a page
+ * range is more susceptible to write errors. If a high number of pages fail, we
+ * assume that the block is bad and we mark it accordingly. In all cases, we
+ * remap and resubmit the failed entries as fast as possible; if a flush is
+ * waiting on a completion, the whole stack would stall otherwise.
+ */
+static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
+{
+ void *comp_bits = &rqd->ppa_status;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+ struct pblk_rec_ctx *recovery;
+ struct ppa_addr *ppa_list = rqd->ppa_list;
+ int nr_ppas = rqd->nr_ppas;
+ unsigned int c_entries;
+ int bit, ret;
+
+ if (unlikely(nr_ppas == 1))
+ ppa_list = &rqd->ppa_addr;
+
+ recovery = mempool_alloc(pblk->rec_pool, GFP_ATOMIC);
+ if (!recovery) {
+ pr_err("pblk: could not allocate recovery context\n");
+ return;
+ }
+ INIT_LIST_HEAD(&recovery->failed);
+
+ bit = -1;
+ while ((bit = find_next_bit(comp_bits, nr_ppas, bit + 1)) < nr_ppas) {
+ struct pblk_rb_entry *entry;
+ struct ppa_addr ppa;
+
+ /* Logic error */
+ if (bit > c_ctx->nr_valid) {
+ WARN_ONCE(1, "pblk: corrupted write request\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ ppa = ppa_list[bit];
+ entry = pblk_rb_sync_scan_entry(&pblk->rwb, &ppa);
+ if (!entry) {
+ pr_err("pblk: could not scan entry on write failure\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ /* The list is filled first and emptied afterwards. No need for
+ * protecting it with a lock
+ */
+ list_add_tail(&entry->index, &recovery->failed);
+ }
+
+ c_entries = find_first_bit(comp_bits, nr_ppas);
+ ret = pblk_recov_setup_rq(pblk, c_ctx, recovery, comp_bits, c_entries);
+ if (ret) {
+ pr_err("pblk: could not recover from write failure\n");
+ mempool_free(recovery, pblk->rec_pool);
+ goto out;
+ }
+
+ INIT_WORK(&recovery->ws_rec, pblk_submit_rec);
+ queue_work(pblk->kw_wq, &recovery->ws_rec);
+
+out:
+ pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static void pblk_end_io_write(struct nvm_rq *rqd)
+{
+ struct pblk *pblk = rqd->private;
+ struct pblk_c_ctx *c_ctx = nvm_rq_to_pdu(rqd);
+
+ if (rqd->error) {
+ pblk_log_write_err(pblk, rqd);
+ return pblk_end_w_fail(pblk, rqd);
+ }
+#ifdef CONFIG_NVM_DEBUG
+ else
+ WARN_ONCE(rqd->bio->bi_error, "pblk: corrupted write error\n");
+#endif
+
+ pblk_complete_write(pblk, rqd, c_ctx);
+}
+
+static int pblk_alloc_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int nr_secs)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+
+ /* Setup write request */
+ rqd->opcode = NVM_OP_PWRITE;
+ rqd->nr_ppas = nr_secs;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+ rqd->private = pblk;
+ rqd->end_io = pblk_end_io_write;
+
+ rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
+ &rqd->dma_meta_list);
+ if (!rqd->meta_list)
+ return -ENOMEM;
+
+ if (unlikely(nr_secs == 1))
+ return 0;
+
+ rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
+ rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
+
+ return 0;
+}
+
+static int pblk_setup_w_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ struct pblk_line *e_line = pblk_line_get_data_next(pblk);
+ struct ppa_addr erase_ppa;
+ unsigned int valid = c_ctx->nr_valid;
+ unsigned int padded = c_ctx->nr_padded;
+ unsigned int nr_secs = valid + padded;
+ unsigned long *lun_bitmap;
+ int ret = 0;
+
+ lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+ if (!lun_bitmap) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ c_ctx->lun_bitmap = lun_bitmap;
+
+ ret = pblk_alloc_w_rq(pblk, rqd, nr_secs);
+ if (ret) {
+ kfree(lun_bitmap);
+ goto out;
+ }
+
+ ppa_set_empty(&erase_ppa);
+ if (likely(!e_line || !atomic_read(&e_line->left_eblks)))
+ pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, valid, 0);
+ else
+ pblk_map_erase_rq(pblk, rqd, c_ctx->sentry, lun_bitmap,
+ valid, &erase_ppa);
+
+out:
+ if (unlikely(e_line && !ppa_empty(erase_ppa))) {
+ if (pblk_blk_erase_async(pblk, erase_ppa)) {
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int bit;
+
+ atomic_inc(&e_line->left_eblks);
+ bit = erase_ppa.g.lun * geo->nr_chnls + erase_ppa.g.ch;
+ WARN_ON(!test_and_clear_bit(bit, e_line->erase_bitmap));
+ up(&pblk->erase_sem);
+ }
+ }
+
+ return ret;
+}
+
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ unsigned long *lun_bitmap;
+ int ret;
+
+ lun_bitmap = kzalloc(lm->lun_bitmap_len, GFP_KERNEL);
+ if (!lun_bitmap)
+ return -ENOMEM;
+
+ c_ctx->lun_bitmap = lun_bitmap;
+
+ ret = pblk_alloc_w_rq(pblk, rqd, rqd->nr_ppas);
+ if (ret)
+ return ret;
+
+ pblk_map_rq(pblk, rqd, c_ctx->sentry, lun_bitmap, c_ctx->nr_valid, 0);
+
+ rqd->ppa_status = (u64)0;
+ rqd->flags = pblk_set_progr_mode(pblk, WRITE);
+
+ return ret;
+}
+
+static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
+ unsigned int secs_to_flush)
+{
+ int secs_to_sync;
+
+ secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
+
+#ifdef CONFIG_NVM_DEBUG
+ if ((!secs_to_sync && secs_to_flush)
+ || (secs_to_sync < 0)
+ || (secs_to_sync > secs_avail && !secs_to_flush)) {
+ pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+ secs_avail, secs_to_sync, secs_to_flush);
+ }
+#endif
+
+ return secs_to_sync;
+}
+
+static int pblk_submit_write(struct pblk *pblk)
+{
+ struct bio *bio;
+ struct nvm_rq *rqd;
+ struct pblk_c_ctx *c_ctx;
+ unsigned int pgs_read;
+ unsigned int secs_avail, secs_to_sync, secs_to_com;
+ unsigned int secs_to_flush;
+ unsigned long pos;
+ int err;
+
+ /* If there are no sectors in the cache, flushes (bios without data)
+ * will be cleared on the cache threads
+ */
+ secs_avail = pblk_rb_read_count(&pblk->rwb);
+ if (!secs_avail)
+ return 1;
+
+ secs_to_flush = pblk_rb_sync_point_count(&pblk->rwb);
+ if (!secs_to_flush && secs_avail < pblk->min_write_pgs)
+ return 1;
+
+ rqd = pblk_alloc_rqd(pblk, WRITE);
+ if (IS_ERR(rqd)) {
+ pr_err("pblk: cannot allocate write req.\n");
+ return 1;
+ }
+ c_ctx = nvm_rq_to_pdu(rqd);
+
+ bio = bio_alloc(GFP_KERNEL, pblk->max_write_pgs);
+ if (!bio) {
+ pr_err("pblk: cannot allocate write bio\n");
+ goto fail_free_rqd;
+ }
+ bio->bi_iter.bi_sector = 0; /* internal bio */
+ bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+ rqd->bio = bio;
+
+ secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail, secs_to_flush);
+ if (secs_to_sync > pblk->max_write_pgs) {
+ pr_err("pblk: bad buffer sync calculation\n");
+ goto fail_put_bio;
+ }
+
+ secs_to_com = (secs_to_sync > secs_avail) ? secs_avail : secs_to_sync;
+ pos = pblk_rb_read_commit(&pblk->rwb, secs_to_com);
+
+ pgs_read = pblk_rb_read_to_bio(&pblk->rwb, bio, c_ctx, pos,
+ secs_to_sync, secs_avail);
+ if (!pgs_read) {
+ pr_err("pblk: corrupted write bio\n");
+ goto fail_put_bio;
+ }
+
+ if (c_ctx->nr_padded)
+ if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, c_ctx->nr_padded))
+ goto fail_put_bio;
+
+ /* Assign lbas to ppas and populate request structure */
+ err = pblk_setup_w_rq(pblk, rqd, c_ctx);
+ if (err) {
+ pr_err("pblk: could not setup write request\n");
+ goto fail_free_bio;
+ }
+
+ err = pblk_submit_io(pblk, rqd);
+ if (err) {
+ pr_err("pblk: I/O submission failed: %d\n", err);
+ goto fail_free_bio;
+ }
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_long_add(secs_to_sync, &pblk->sub_writes);
+#endif
+
+ return 0;
+
+fail_free_bio:
+ if (c_ctx->nr_padded)
+ pblk_bio_free_pages(pblk, bio, secs_to_sync, c_ctx->nr_padded);
+fail_put_bio:
+ bio_put(bio);
+fail_free_rqd:
+ pblk_free_rqd(pblk, rqd, WRITE);
+
+ return 1;
+}
+
+int pblk_write_ts(void *data)
+{
+ struct pblk *pblk = data;
+
+ while (!kthread_should_stop()) {
+ if (!pblk_submit_write(pblk))
+ continue;
+ set_current_state(TASK_INTERRUPTIBLE);
+ io_schedule();
+ }
+
+ return 0;
+}
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
new file mode 100644
index 000000000000..99f3186b5288
--- /dev/null
+++ b/drivers/lightnvm/pblk.h
@@ -0,0 +1,1121 @@
+/*
+ * Copyright (C) 2015 IT University of Copenhagen (rrpc.h)
+ * Copyright (C) 2016 CNEX Labs
+ * Initial release: Matias Bjorling <matias@cnexlabs.com>
+ * Write buffering: Javier Gonzalez <javier@cnexlabs.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that 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.
+ *
+ * Implementation of a Physical Block-device target for Open-channel SSDs.
+ *
+ */
+
+#ifndef PBLK_H_
+#define PBLK_H_
+
+#include <linux/blkdev.h>
+#include <linux/blk-mq.h>
+#include <linux/bio.h>
+#include <linux/module.h>
+#include <linux/kthread.h>
+#include <linux/vmalloc.h>
+#include <linux/crc32.h>
+#include <linux/uuid.h>
+
+#include <linux/lightnvm.h>
+
+/* Run only GC if less than 1/X blocks are free */
+#define GC_LIMIT_INVERSE 5
+#define GC_TIME_MSECS 1000
+
+#define PBLK_SECTOR (512)
+#define PBLK_EXPOSED_PAGE_SIZE (4096)
+#define PBLK_MAX_REQ_ADDRS (64)
+#define PBLK_MAX_REQ_ADDRS_PW (6)
+
+#define PBLK_CACHE_NAME_LEN (DISK_NAME_LEN + 16)
+
+#define PBLK_COMMAND_TIMEOUT_MS 30000
+
+/* Max 512 LUNs per device */
+#define PBLK_MAX_LUNS_BITMAP (4)
+
+#define NR_PHY_IN_LOG (PBLK_EXPOSED_PAGE_SIZE / PBLK_SECTOR)
+
+#define pblk_for_each_lun(pblk, rlun, i) \
+ for ((i) = 0, rlun = &(pblk)->luns[0]; \
+ (i) < (pblk)->nr_luns; (i)++, rlun = &(pblk)->luns[(i)])
+
+#define ERASE 2 /* READ = 0, WRITE = 1 */
+
+enum {
+ /* IO Types */
+ PBLK_IOTYPE_USER = 1 << 0,
+ PBLK_IOTYPE_GC = 1 << 1,
+
+ /* Write buffer flags */
+ PBLK_FLUSH_ENTRY = 1 << 2,
+ PBLK_WRITTEN_DATA = 1 << 3,
+ PBLK_SUBMITTED_ENTRY = 1 << 4,
+ PBLK_WRITABLE_ENTRY = 1 << 5,
+};
+
+enum {
+ PBLK_BLK_ST_OPEN = 0x1,
+ PBLK_BLK_ST_CLOSED = 0x2,
+};
+
+/* The number of GC lists and the rate-limiter states go together. This way the
+ * rate-limiter can dictate how much GC is needed based on resource utilization.
+ */
+#define PBLK_NR_GC_LISTS 3
+#define PBLK_MAX_GC_JOBS 32
+
+enum {
+ PBLK_RL_HIGH = 1,
+ PBLK_RL_MID = 2,
+ PBLK_RL_LOW = 3,
+};
+
+struct pblk_sec_meta {
+ u64 reserved;
+ __le64 lba;
+};
+
+#define pblk_dma_meta_size (sizeof(struct pblk_sec_meta) * PBLK_MAX_REQ_ADDRS)
+
+/* write completion context */
+struct pblk_c_ctx {
+ struct list_head list; /* Head for out-of-order completion */
+
+ unsigned long *lun_bitmap; /* Luns used on current request */
+ unsigned int sentry;
+ unsigned int nr_valid;
+ unsigned int nr_padded;
+};
+
+/* Read context */
+struct pblk_r_ctx {
+ struct bio *orig_bio;
+};
+
+/* Recovery context */
+struct pblk_rec_ctx {
+ struct pblk *pblk;
+ struct nvm_rq *rqd;
+ struct list_head failed;
+ struct work_struct ws_rec;
+};
+
+/* Write context */
+struct pblk_w_ctx {
+ struct bio_list bios; /* Original bios - used for completion
+ * in REQ_FUA, REQ_FLUSH case
+ */
+ u64 lba; /* Logic addr. associated with entry */
+ struct ppa_addr ppa; /* Physic addr. associated with entry */
+ int flags; /* Write context flags */
+};
+
+struct pblk_rb_entry {
+ struct ppa_addr cacheline; /* Cacheline for this entry */
+ void *data; /* Pointer to data on this entry */
+ struct pblk_w_ctx w_ctx; /* Context for this entry */
+ struct list_head index; /* List head to enable indexes */
+};
+
+#define EMPTY_ENTRY (~0U)
+
+struct pblk_rb_pages {
+ struct page *pages;
+ int order;
+ struct list_head list;
+};
+
+struct pblk_rb {
+ struct pblk_rb_entry *entries; /* Ring buffer entries */
+ unsigned int mem; /* Write offset - points to next
+ * writable entry in memory
+ */
+ unsigned int subm; /* Read offset - points to last entry
+ * that has been submitted to the media
+ * to be persisted
+ */
+ unsigned int sync; /* Synced - backpointer that signals
+ * the last submitted entry that has
+ * been successfully persisted to media
+ */
+ unsigned int sync_point; /* Sync point - last entry that must be
+ * flushed to the media. Used with
+ * REQ_FLUSH and REQ_FUA
+ */
+ unsigned int l2p_update; /* l2p update point - next entry for
+ * which l2p mapping will be updated to
+ * contain a device ppa address (instead
+ * of a cacheline
+ */
+ unsigned int nr_entries; /* Number of entries in write buffer -
+ * must be a power of two
+ */
+ unsigned int seg_size; /* Size of the data segments being
+ * stored on each entry. Typically this
+ * will be 4KB
+ */
+
+ struct list_head pages; /* List of data pages */
+
+ spinlock_t w_lock; /* Write lock */
+ spinlock_t s_lock; /* Sync lock */
+
+#ifdef CONFIG_NVM_DEBUG
+ atomic_t inflight_sync_point; /* Not served REQ_FLUSH | REQ_FUA */
+#endif
+};
+
+#define PBLK_RECOVERY_SECTORS 16
+
+struct pblk_lun {
+ struct ppa_addr bppa;
+
+ u8 *bb_list; /* Bad block list for LUN. Only used on
+ * bring up. Bad blocks are managed
+ * within lines on run-time.
+ */
+
+ struct semaphore wr_sem;
+};
+
+struct pblk_gc_rq {
+ struct pblk_line *line;
+ void *data;
+ u64 *lba_list;
+ int nr_secs;
+ int secs_to_gc;
+ struct list_head list;
+};
+
+struct pblk_gc {
+ int gc_active;
+ int gc_enabled;
+ int gc_forced;
+ int gc_jobs_active;
+ atomic_t inflight_gc;
+
+ struct task_struct *gc_ts;
+ struct task_struct *gc_writer_ts;
+ struct workqueue_struct *gc_reader_wq;
+ struct timer_list gc_timer;
+
+ int w_entries;
+ struct list_head w_list;
+
+ spinlock_t lock;
+ spinlock_t w_lock;
+};
+
+struct pblk_rl {
+ unsigned int high; /* Upper threshold for rate limiter (free run -
+ * user I/O rate limiter
+ */
+ unsigned int low; /* Lower threshold for rate limiter (user I/O
+ * rate limiter - stall)
+ */
+ unsigned int high_pw; /* High rounded up as a power of 2 */
+
+#define PBLK_USER_HIGH_THRS 2 /* Begin write limit at 50 percent
+ * available blks
+ */
+#define PBLK_USER_LOW_THRS 20 /* Aggressive GC at 5% available blocks */
+
+ int rb_windows_pw; /* Number of rate windows in the write buffer
+ * given as a power-of-2. This guarantees that
+ * when user I/O is being rate limited, there
+ * will be reserved enough space for the GC to
+ * place its payload. A window is of
+ * pblk->max_write_pgs size, which in NVMe is
+ * 64, i.e., 256kb.
+ */
+ int rb_budget; /* Total number of entries available for I/O */
+ int rb_user_max; /* Max buffer entries available for user I/O */
+ atomic_t rb_user_cnt; /* User I/O buffer counter */
+ int rb_gc_max; /* Max buffer entries available for GC I/O */
+ int rb_gc_rsv; /* Reserved buffer entries for GC I/O */
+ int rb_state; /* Rate-limiter current state */
+ atomic_t rb_gc_cnt; /* GC I/O buffer counter */
+
+ int rb_user_active;
+ struct timer_list u_timer;
+
+ unsigned long long nr_secs;
+ unsigned long total_blocks;
+ atomic_t free_blocks;
+};
+
+#define PBLK_LINE_NR_LUN_BITMAP 2
+#define PBLK_LINE_NR_SEC_BITMAP 2
+#define PBLK_LINE_EMPTY (~0U)
+
+enum {
+ /* Line Types */
+ PBLK_LINETYPE_FREE = 0,
+ PBLK_LINETYPE_LOG = 1,
+ PBLK_LINETYPE_DATA = 2,
+
+ /* Line state */
+ PBLK_LINESTATE_FREE = 10,
+ PBLK_LINESTATE_OPEN = 11,
+ PBLK_LINESTATE_CLOSED = 12,
+ PBLK_LINESTATE_GC = 13,
+ PBLK_LINESTATE_BAD = 14,
+ PBLK_LINESTATE_CORRUPT = 15,
+
+ /* GC group */
+ PBLK_LINEGC_NONE = 20,
+ PBLK_LINEGC_EMPTY = 21,
+ PBLK_LINEGC_LOW = 22,
+ PBLK_LINEGC_MID = 23,
+ PBLK_LINEGC_HIGH = 24,
+ PBLK_LINEGC_FULL = 25,
+};
+
+#define PBLK_MAGIC 0x70626c6b /*pblk*/
+
+struct line_header {
+ __le32 crc;
+ __le32 identifier; /* pblk identifier */
+ __u8 uuid[16]; /* instance uuid */
+ __le16 type; /* line type */
+ __le16 version; /* type version */
+ __le32 id; /* line id for current line */
+};
+
+struct line_smeta {
+ struct line_header header;
+
+ __le32 crc; /* Full structure including struct crc */
+ /* Previous line metadata */
+ __le32 prev_id; /* Line id for previous line */
+
+ /* Current line metadata */
+ __le64 seq_nr; /* Sequence number for current line */
+
+ /* Active writers */
+ __le32 window_wr_lun; /* Number of parallel LUNs to write */
+
+ __le32 rsvd[2];
+};
+
+/*
+ * Metadata Layout:
+ * 1. struct pblk_emeta
+ * 2. nr_lbas u64 forming lba list
+ * 3. nr_lines (all) u32 valid sector count (vsc) (~0U: non-alloc line)
+ * 4. nr_luns bits (u64 format) forming line bad block bitmap
+ *
+ * 3. and 4. will be part of FTL log
+ */
+struct line_emeta {
+ struct line_header header;
+
+ __le32 crc; /* Full structure including struct crc */
+
+ /* Previous line metadata */
+ __le32 prev_id; /* Line id for prev line */
+
+ /* Current line metadata */
+ __le64 seq_nr; /* Sequence number for current line */
+
+ /* Active writers */
+ __le32 window_wr_lun; /* Number of parallel LUNs to write */
+
+ /* Bookkeeping for recovery */
+ __le32 next_id; /* Line id for next line */
+ __le64 nr_lbas; /* Number of lbas mapped in line */
+ __le64 nr_valid_lbas; /* Number of valid lbas mapped in line */
+};
+
+struct pblk_line {
+ struct pblk *pblk;
+ unsigned int id; /* Line number corresponds to the
+ * block line
+ */
+ unsigned int seq_nr; /* Unique line sequence number */
+
+ int state; /* PBLK_LINESTATE_X */
+ int type; /* PBLK_LINETYPE_X */
+ int gc_group; /* PBLK_LINEGC_X */
+ struct list_head list; /* Free, GC lists */
+
+ unsigned long *lun_bitmap; /* Bitmap for LUNs mapped in line */
+
+ struct line_smeta *smeta; /* Start metadata */
+ struct line_emeta *emeta; /* End metadata */
+ int meta_line; /* Metadata line id */
+ u64 smeta_ssec; /* Sector where smeta starts */
+ u64 emeta_ssec; /* Sector where emeta starts */
+
+ unsigned int sec_in_line; /* Number of usable secs in line */
+
+ atomic_t blk_in_line; /* Number of good blocks in line */
+ unsigned long *blk_bitmap; /* Bitmap for valid/invalid blocks */
+ unsigned long *erase_bitmap; /* Bitmap for erased blocks */
+
+ unsigned long *map_bitmap; /* Bitmap for mapped sectors in line */
+ unsigned long *invalid_bitmap; /* Bitmap for invalid sectors in line */
+
+ atomic_t left_eblks; /* Blocks left for erasing */
+ atomic_t left_seblks; /* Blocks left for sync erasing */
+
+ int left_msecs; /* Sectors left for mapping */
+ int left_ssecs; /* Sectors left to sync */
+ unsigned int cur_sec; /* Sector map pointer */
+ unsigned int vsc; /* Valid sector count in line */
+
+ struct kref ref; /* Write buffer L2P references */
+
+ spinlock_t lock; /* Necessary for invalid_bitmap only */
+};
+
+#define PBLK_DATA_LINES 4
+
+enum{
+ PBLK_KMALLOC_META = 1,
+ PBLK_VMALLOC_META = 2,
+};
+
+struct pblk_line_metadata {
+ void *meta;
+};
+
+struct pblk_line_mgmt {
+ int nr_lines; /* Total number of full lines */
+ int nr_free_lines; /* Number of full lines in free list */
+
+ /* Free lists - use free_lock */
+ struct list_head free_list; /* Full lines ready to use */
+ struct list_head corrupt_list; /* Full lines corrupted */
+ struct list_head bad_list; /* Full lines bad */
+
+ /* GC lists - use gc_lock */
+ struct list_head *gc_lists[PBLK_NR_GC_LISTS];
+ struct list_head gc_high_list; /* Full lines ready to GC, high isc */
+ struct list_head gc_mid_list; /* Full lines ready to GC, mid isc */
+ struct list_head gc_low_list; /* Full lines ready to GC, low isc */
+
+ struct list_head gc_full_list; /* Full lines ready to GC, no valid */
+ struct list_head gc_empty_list; /* Full lines close, all valid */
+
+ struct pblk_line *log_line; /* Current FTL log line */
+ struct pblk_line *data_line; /* Current data line */
+ struct pblk_line *log_next; /* Next FTL log line */
+ struct pblk_line *data_next; /* Next data line */
+
+ /* Metadata allocation type: VMALLOC | KMALLOC */
+ int smeta_alloc_type;
+ int emeta_alloc_type;
+
+ /* Pre-allocated metadata for data lines */
+ struct pblk_line_metadata sline_meta[PBLK_DATA_LINES];
+ struct pblk_line_metadata eline_meta[PBLK_DATA_LINES];
+ unsigned long meta_bitmap;
+
+ /* Helpers for fast bitmap calculations */
+ unsigned long *bb_template;
+ unsigned long *bb_aux;
+
+ unsigned long d_seq_nr; /* Data line unique sequence number */
+ unsigned long l_seq_nr; /* Log line unique sequence number */
+
+ spinlock_t free_lock;
+ spinlock_t gc_lock;
+};
+
+struct pblk_line_meta {
+ unsigned int smeta_len; /* Total length for smeta */
+ unsigned int smeta_sec; /* Sectors needed for smeta*/
+ unsigned int emeta_len; /* Total length for emeta */
+ unsigned int emeta_sec; /* Sectors needed for emeta*/
+ unsigned int emeta_bb; /* Boundary for bb that affects emeta */
+ unsigned int sec_bitmap_len; /* Length for sector bitmap in line */
+ unsigned int blk_bitmap_len; /* Length for block bitmap in line */
+ unsigned int lun_bitmap_len; /* Length for lun bitmap in line */
+
+ unsigned int blk_per_line; /* Number of blocks in a full line */
+ unsigned int sec_per_line; /* Number of sectors in a line */
+ unsigned int min_blk_line; /* Min. number of good blocks in line */
+
+ unsigned int mid_thrs; /* Threshold for GC mid list */
+ unsigned int high_thrs; /* Threshold for GC high list */
+};
+
+struct pblk_addr_format {
+ u64 ch_mask;
+ u64 lun_mask;
+ u64 pln_mask;
+ u64 blk_mask;
+ u64 pg_mask;
+ u64 sec_mask;
+ u8 ch_offset;
+ u8 lun_offset;
+ u8 pln_offset;
+ u8 blk_offset;
+ u8 pg_offset;
+ u8 sec_offset;
+};
+
+struct pblk {
+ struct nvm_tgt_dev *dev;
+ struct gendisk *disk;
+
+ struct kobject kobj;
+
+ struct pblk_lun *luns;
+
+ struct pblk_line *lines; /* Line array */
+ struct pblk_line_mgmt l_mg; /* Line management */
+ struct pblk_line_meta lm; /* Line metadata */
+
+ int ppaf_bitsize;
+ struct pblk_addr_format ppaf;
+
+ struct pblk_rb rwb;
+
+ int min_write_pgs; /* Minimum amount of pages required by controller */
+ int max_write_pgs; /* Maximum amount of pages supported by controller */
+ int pgs_in_buffer; /* Number of pages that need to be held in buffer to
+ * guarantee successful reads.
+ */
+
+ sector_t capacity; /* Device capacity when bad blocks are subtracted */
+ int over_pct; /* Percentage of device used for over-provisioning */
+
+ /* pblk provisioning values. Used by rate limiter */
+ struct pblk_rl rl;
+
+ struct semaphore erase_sem;
+
+ unsigned char instance_uuid[16];
+#ifdef CONFIG_NVM_DEBUG
+ /* All debug counters apply to 4kb sector I/Os */
+ atomic_long_t inflight_writes; /* Inflight writes (user and gc) */
+ atomic_long_t padded_writes; /* Sectors padded due to flush/fua */
+ atomic_long_t padded_wb; /* Sectors padded in write buffer */
+ atomic_long_t nr_flush; /* Number of flush/fua I/O */
+ atomic_long_t req_writes; /* Sectors stored on write buffer */
+ atomic_long_t sub_writes; /* Sectors submitted from buffer */
+ atomic_long_t sync_writes; /* Sectors synced to media */
+ atomic_long_t compl_writes; /* Sectors completed in write bio */
+ atomic_long_t inflight_reads; /* Inflight sector read requests */
+ atomic_long_t sync_reads; /* Completed sector read requests */
+ atomic_long_t recov_writes; /* Sectors submitted from recovery */
+ atomic_long_t recov_gc_writes; /* Sectors submitted from write GC */
+ atomic_long_t recov_gc_reads; /* Sectors submitted from read GC */
+#endif
+
+ spinlock_t lock;
+
+ atomic_long_t read_failed;
+ atomic_long_t read_empty;
+ atomic_long_t read_high_ecc;
+ atomic_long_t read_failed_gc;
+ atomic_long_t write_failed;
+ atomic_long_t erase_failed;
+
+ struct task_struct *writer_ts;
+
+ /* Simple translation map of logical addresses to physical addresses.
+ * The logical addresses is known by the host system, while the physical
+ * addresses are used when writing to the disk block device.
+ */
+ unsigned char *trans_map;
+ spinlock_t trans_lock;
+
+ struct list_head compl_list;
+
+ mempool_t *page_pool;
+ mempool_t *line_ws_pool;
+ mempool_t *rec_pool;
+ mempool_t *r_rq_pool;
+ mempool_t *w_rq_pool;
+ mempool_t *line_meta_pool;
+
+ struct workqueue_struct *kw_wq;
+ struct timer_list wtimer;
+
+ struct pblk_gc gc;
+};
+
+struct pblk_line_ws {
+ struct pblk *pblk;
+ struct pblk_line *line;
+ void *priv;
+ struct work_struct ws;
+};
+
+#define pblk_r_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_r_ctx))
+#define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
+
+/*
+ * pblk ring buffer operations
+ */
+int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
+ unsigned int power_size, unsigned int power_seg_sz);
+unsigned int pblk_rb_calculate_size(unsigned int nr_entries);
+void *pblk_rb_entries_ref(struct pblk_rb *rb);
+int pblk_rb_may_write_user(struct pblk_rb *rb, struct bio *bio,
+ unsigned int nr_entries, unsigned int *pos);
+int pblk_rb_may_write_gc(struct pblk_rb *rb, unsigned int nr_entries,
+ unsigned int *pos);
+void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, unsigned int pos);
+void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
+ struct pblk_w_ctx w_ctx, struct pblk_line *gc_line,
+ unsigned int pos);
+struct pblk_w_ctx *pblk_rb_w_ctx(struct pblk_rb *rb, unsigned int pos);
+
+void pblk_rb_sync_l2p(struct pblk_rb *rb);
+unsigned int pblk_rb_read_to_bio(struct pblk_rb *rb, struct bio *bio,
+ struct pblk_c_ctx *c_ctx,
+ unsigned int pos,
+ unsigned int nr_entries,
+ unsigned int count);
+unsigned int pblk_rb_read_to_bio_list(struct pblk_rb *rb, struct bio *bio,
+ struct list_head *list,
+ unsigned int max);
+int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
+ u64 pos, int bio_iter);
+unsigned int pblk_rb_read_commit(struct pblk_rb *rb, unsigned int entries);
+
+unsigned int pblk_rb_sync_init(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_advance(struct pblk_rb *rb, unsigned int nr_entries);
+struct pblk_rb_entry *pblk_rb_sync_scan_entry(struct pblk_rb *rb,
+ struct ppa_addr *ppa);
+void pblk_rb_sync_end(struct pblk_rb *rb, unsigned long *flags);
+unsigned int pblk_rb_sync_point_count(struct pblk_rb *rb);
+
+unsigned int pblk_rb_read_count(struct pblk_rb *rb);
+unsigned int pblk_rb_wrap_pos(struct pblk_rb *rb, unsigned int pos);
+
+int pblk_rb_tear_down_check(struct pblk_rb *rb);
+int pblk_rb_pos_oob(struct pblk_rb *rb, u64 pos);
+void pblk_rb_data_free(struct pblk_rb *rb);
+ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf);
+
+/*
+ * pblk core
+ */
+struct nvm_rq *pblk_alloc_rqd(struct pblk *pblk, int rw);
+int pblk_setup_w_rec_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ struct pblk_c_ctx *c_ctx);
+void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int rw);
+void pblk_flush_writer(struct pblk *pblk);
+struct ppa_addr pblk_get_lba_map(struct pblk *pblk, sector_t lba);
+void pblk_discard(struct pblk *pblk, struct bio *bio);
+void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd);
+void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd);
+int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd);
+struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
+ unsigned int nr_secs, unsigned int len,
+ gfp_t gfp_mask);
+struct pblk_line *pblk_line_get(struct pblk *pblk);
+struct pblk_line *pblk_line_get_first_data(struct pblk *pblk);
+struct pblk_line *pblk_line_replace_data(struct pblk *pblk);
+int pblk_line_recov_alloc(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_recov_close(struct pblk *pblk, struct pblk_line *line);
+struct pblk_line *pblk_line_get_data(struct pblk *pblk);
+struct pblk_line *pblk_line_get_data_next(struct pblk *pblk);
+int pblk_line_erase(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_is_full(struct pblk_line *line);
+void pblk_line_free(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_close_ws(struct work_struct *work);
+void pblk_line_close(struct pblk *pblk, struct pblk_line *line);
+void pblk_line_mark_bb(struct work_struct *work);
+void pblk_line_run_ws(struct pblk *pblk, struct pblk_line *line, void *priv,
+ void (*work)(struct work_struct *));
+u64 pblk_line_smeta_start(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_smeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_line_read_emeta(struct pblk *pblk, struct pblk_line *line);
+int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr erase_ppa);
+void pblk_line_put(struct kref *ref);
+struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line);
+u64 pblk_alloc_page(struct pblk *pblk, struct pblk_line *line, int nr_secs);
+int pblk_calc_secs(struct pblk *pblk, unsigned long secs_avail,
+ unsigned long secs_to_flush);
+void pblk_down_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap);
+void pblk_up_rq(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas,
+ unsigned long *lun_bitmap);
+void pblk_end_bio_sync(struct bio *bio);
+void pblk_end_io_sync(struct nvm_rq *rqd);
+int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
+ int nr_pages);
+void pblk_map_pad_invalidate(struct pblk *pblk, struct pblk_line *line,
+ u64 paddr);
+void pblk_bio_free_pages(struct pblk *pblk, struct bio *bio, int off,
+ int nr_pages);
+void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa);
+void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa);
+void pblk_update_map_cache(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa);
+void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa, struct ppa_addr entry_line);
+int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa,
+ struct pblk_line *gc_line);
+void pblk_lookup_l2p_rand(struct pblk *pblk, struct ppa_addr *ppas,
+ u64 *lba_list, int nr_secs);
+void pblk_lookup_l2p_seq(struct pblk *pblk, struct ppa_addr *ppas,
+ sector_t blba, int nr_secs);
+
+/*
+ * pblk user I/O write path
+ */
+int pblk_write_to_cache(struct pblk *pblk, struct bio *bio,
+ unsigned long flags);
+int pblk_write_gc_to_cache(struct pblk *pblk, void *data, u64 *lba_list,
+ unsigned int nr_entries, unsigned int nr_rec_entries,
+ struct pblk_line *gc_line, unsigned long flags);
+
+/*
+ * pblk map
+ */
+void pblk_map_erase_rq(struct pblk *pblk, struct nvm_rq *rqd,
+ unsigned int sentry, unsigned long *lun_bitmap,
+ unsigned int valid_secs, struct ppa_addr *erase_ppa);
+void pblk_map_rq(struct pblk *pblk, struct nvm_rq *rqd, unsigned int sentry,
+ unsigned long *lun_bitmap, unsigned int valid_secs,
+ unsigned int off);
+
+/*
+ * pblk write thread
+ */
+int pblk_write_ts(void *data);
+void pblk_write_timer_fn(unsigned long data);
+void pblk_write_should_kick(struct pblk *pblk);
+
+/*
+ * pblk read path
+ */
+int pblk_submit_read(struct pblk *pblk, struct bio *bio);
+int pblk_submit_read_gc(struct pblk *pblk, u64 *lba_list, void *data,
+ unsigned int nr_secs, unsigned int *secs_to_gc,
+ struct pblk_line *line);
+/*
+ * pblk recovery
+ */
+void pblk_submit_rec(struct work_struct *work);
+struct pblk_line *pblk_recov_l2p(struct pblk *pblk);
+void pblk_recov_pad(struct pblk *pblk);
+__le64 *pblk_recov_get_lba_list(struct pblk *pblk, struct line_emeta *emeta);
+int pblk_recov_setup_rq(struct pblk *pblk, struct pblk_c_ctx *c_ctx,
+ struct pblk_rec_ctx *recovery, u64 *comp_bits,
+ unsigned int comp);
+
+/*
+ * pblk gc
+ */
+#define PBLK_GC_TRIES 3
+
+int pblk_gc_init(struct pblk *pblk);
+void pblk_gc_exit(struct pblk *pblk);
+void pblk_gc_should_start(struct pblk *pblk);
+void pblk_gc_should_stop(struct pblk *pblk);
+int pblk_gc_status(struct pblk *pblk);
+void pblk_gc_sysfs_state_show(struct pblk *pblk, int *gc_enabled,
+ int *gc_active);
+void pblk_gc_sysfs_force(struct pblk *pblk, int force);
+
+/*
+ * pblk rate limiter
+ */
+void pblk_rl_init(struct pblk_rl *rl, int budget);
+void pblk_rl_free(struct pblk_rl *rl);
+int pblk_rl_gc_thrs(struct pblk_rl *rl);
+unsigned long pblk_rl_nr_free_blks(struct pblk_rl *rl);
+int pblk_rl_user_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_user_in(struct pblk_rl *rl, int nr_entries);
+int pblk_rl_gc_may_insert(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_gc_in(struct pblk_rl *rl, int nr_entries);
+void pblk_rl_out(struct pblk_rl *rl, int nr_user, int nr_gc);
+void pblk_rl_set_gc_rsc(struct pblk_rl *rl, int rsv);
+int pblk_rl_sysfs_rate_show(struct pblk_rl *rl);
+void pblk_rl_free_lines_inc(struct pblk_rl *rl, struct pblk_line *line);
+void pblk_rl_free_lines_dec(struct pblk_rl *rl, struct pblk_line *line);
+
+/*
+ * pblk sysfs
+ */
+int pblk_sysfs_init(struct gendisk *tdisk);
+void pblk_sysfs_exit(struct gendisk *tdisk);
+
+static inline void *pblk_malloc(size_t size, int type, gfp_t flags)
+{
+ if (type == PBLK_KMALLOC_META)
+ return kmalloc(size, flags);
+ return vmalloc(size);
+}
+
+static inline void pblk_mfree(void *ptr, int type)
+{
+ if (type == PBLK_KMALLOC_META)
+ kfree(ptr);
+ else
+ vfree(ptr);
+}
+
+static inline struct nvm_rq *nvm_rq_from_c_ctx(void *c_ctx)
+{
+ return c_ctx - sizeof(struct nvm_rq);
+}
+
+static inline void *pblk_line_emeta_to_lbas(struct line_emeta *emeta)
+{
+ return (emeta) + 1;
+}
+
+#define NVM_MEM_PAGE_WRITE (8)
+
+static inline int pblk_pad_distance(struct pblk *pblk)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+
+ return NVM_MEM_PAGE_WRITE * geo->nr_luns * geo->sec_per_pl;
+}
+
+static inline int pblk_dev_ppa_to_line(struct ppa_addr p)
+{
+ return p.g.blk;
+}
+
+static inline int pblk_tgt_ppa_to_line(struct ppa_addr p)
+{
+ return p.g.blk;
+}
+
+static inline int pblk_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+ return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+/* A block within a line corresponds to the lun */
+static inline int pblk_dev_ppa_to_pos(struct nvm_geo *geo, struct ppa_addr p)
+{
+ return p.g.lun * geo->nr_chnls + p.g.ch;
+}
+
+static inline struct ppa_addr pblk_ppa32_to_ppa64(struct pblk *pblk, u32 ppa32)
+{
+ struct ppa_addr ppa64;
+
+ ppa64.ppa = 0;
+
+ if (ppa32 == -1) {
+ ppa64.ppa = ADDR_EMPTY;
+ } else if (ppa32 & (1U << 31)) {
+ ppa64.c.line = ppa32 & ((~0U) >> 1);
+ ppa64.c.is_cached = 1;
+ } else {
+ ppa64.g.blk = (ppa32 & pblk->ppaf.blk_mask) >>
+ pblk->ppaf.blk_offset;
+ ppa64.g.pg = (ppa32 & pblk->ppaf.pg_mask) >>
+ pblk->ppaf.pg_offset;
+ ppa64.g.lun = (ppa32 & pblk->ppaf.lun_mask) >>
+ pblk->ppaf.lun_offset;
+ ppa64.g.ch = (ppa32 & pblk->ppaf.ch_mask) >>
+ pblk->ppaf.ch_offset;
+ ppa64.g.pl = (ppa32 & pblk->ppaf.pln_mask) >>
+ pblk->ppaf.pln_offset;
+ ppa64.g.sec = (ppa32 & pblk->ppaf.sec_mask) >>
+ pblk->ppaf.sec_offset;
+ }
+
+ return ppa64;
+}
+
+static inline struct ppa_addr pblk_trans_map_get(struct pblk *pblk,
+ sector_t lba)
+{
+ struct ppa_addr ppa;
+
+ if (pblk->ppaf_bitsize < 32) {
+ u32 *map = (u32 *)pblk->trans_map;
+
+ ppa = pblk_ppa32_to_ppa64(pblk, map[lba]);
+ } else {
+ struct ppa_addr *map = (struct ppa_addr *)pblk->trans_map;
+
+ ppa = map[lba];
+ }
+
+ return ppa;
+}
+
+static inline u32 pblk_ppa64_to_ppa32(struct pblk *pblk, struct ppa_addr ppa64)
+{
+ u32 ppa32 = 0;
+
+ if (ppa64.ppa == ADDR_EMPTY) {
+ ppa32 = ~0U;
+ } else if (ppa64.c.is_cached) {
+ ppa32 |= ppa64.c.line;
+ ppa32 |= 1U << 31;
+ } else {
+ ppa32 |= ppa64.g.blk << pblk->ppaf.blk_offset;
+ ppa32 |= ppa64.g.pg << pblk->ppaf.pg_offset;
+ ppa32 |= ppa64.g.lun << pblk->ppaf.lun_offset;
+ ppa32 |= ppa64.g.ch << pblk->ppaf.ch_offset;
+ ppa32 |= ppa64.g.pl << pblk->ppaf.pln_offset;
+ ppa32 |= ppa64.g.sec << pblk->ppaf.sec_offset;
+ }
+
+ return ppa32;
+}
+
+static inline void pblk_trans_map_set(struct pblk *pblk, sector_t lba,
+ struct ppa_addr ppa)
+{
+ if (pblk->ppaf_bitsize < 32) {
+ u32 *map = (u32 *)pblk->trans_map;
+
+ map[lba] = pblk_ppa64_to_ppa32(pblk, ppa);
+ } else {
+ u64 *map = (u64 *)pblk->trans_map;
+
+ map[lba] = ppa.ppa;
+ }
+}
+
+static inline u64 pblk_dev_ppa_to_line_addr(struct pblk *pblk,
+ struct ppa_addr p)
+{
+ u64 paddr;
+
+ paddr = 0;
+ paddr |= (u64)p.g.pg << pblk->ppaf.pg_offset;
+ paddr |= (u64)p.g.lun << pblk->ppaf.lun_offset;
+ paddr |= (u64)p.g.ch << pblk->ppaf.ch_offset;
+ paddr |= (u64)p.g.pl << pblk->ppaf.pln_offset;
+ paddr |= (u64)p.g.sec << pblk->ppaf.sec_offset;
+
+ return paddr;
+}
+
+static inline int pblk_ppa_empty(struct ppa_addr ppa_addr)
+{
+ return (ppa_addr.ppa == ADDR_EMPTY);
+}
+
+static inline void pblk_ppa_set_empty(struct ppa_addr *ppa_addr)
+{
+ ppa_addr->ppa = ADDR_EMPTY;
+}
+
+static inline int pblk_addr_in_cache(struct ppa_addr ppa)
+{
+ return (ppa.ppa != ADDR_EMPTY && ppa.c.is_cached);
+}
+
+static inline int pblk_addr_to_cacheline(struct ppa_addr ppa)
+{
+ return ppa.c.line;
+}
+
+static inline struct ppa_addr pblk_cacheline_to_addr(int addr)
+{
+ struct ppa_addr p;
+
+ p.c.line = addr;
+ p.c.is_cached = 1;
+
+ return p;
+}
+
+static inline struct ppa_addr addr_to_gen_ppa(struct pblk *pblk, u64 paddr,
+ u64 line_id)
+{
+ struct ppa_addr ppa;
+
+ ppa.ppa = 0;
+ ppa.g.blk = line_id;
+ ppa.g.pg = (paddr & pblk->ppaf.pg_mask) >> pblk->ppaf.pg_offset;
+ ppa.g.lun = (paddr & pblk->ppaf.lun_mask) >> pblk->ppaf.lun_offset;
+ ppa.g.ch = (paddr & pblk->ppaf.ch_mask) >> pblk->ppaf.ch_offset;
+ ppa.g.pl = (paddr & pblk->ppaf.pln_mask) >> pblk->ppaf.pln_offset;
+ ppa.g.sec = (paddr & pblk->ppaf.sec_mask) >> pblk->ppaf.sec_offset;
+
+ return ppa;
+}
+
+static inline struct ppa_addr addr_to_pblk_ppa(struct pblk *pblk, u64 paddr,
+ u64 line_id)
+{
+ struct ppa_addr ppa;
+
+ ppa = addr_to_gen_ppa(pblk, paddr, line_id);
+
+ return ppa;
+}
+
+static inline u32 pblk_calc_meta_header_crc(struct pblk *pblk,
+ struct line_smeta *smeta)
+{
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)smeta + sizeof(crc),
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline u32 pblk_calc_smeta_crc(struct pblk *pblk,
+ struct line_smeta *smeta)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)smeta +
+ sizeof(struct line_header) + sizeof(crc),
+ lm->smeta_len -
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline u32 pblk_calc_emeta_crc(struct pblk *pblk,
+ struct line_emeta *emeta)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+ u32 crc = ~(u32)0;
+
+ crc = crc32_le(crc, (unsigned char *)emeta +
+ sizeof(struct line_header) + sizeof(crc),
+ lm->emeta_len -
+ sizeof(struct line_header) - sizeof(crc));
+
+ return crc;
+}
+
+static inline int pblk_set_progr_mode(struct pblk *pblk, int type)
+{
+ struct nvm_tgt_dev *dev = pblk->dev;
+ struct nvm_geo *geo = &dev->geo;
+ int flags;
+
+ flags = geo->plane_mode >> 1;
+
+ if (type == WRITE)
+ flags |= NVM_IO_SCRAMBLE_ENABLE;
+
+ return flags;
+}
+
+static inline int pblk_set_read_mode(struct pblk *pblk)
+{
+ return NVM_IO_SNGL_ACCESS | NVM_IO_SUSPEND | NVM_IO_SCRAMBLE_ENABLE;
+}
+
+#ifdef CONFIG_NVM_DEBUG
+static inline void print_ppa(struct ppa_addr *p, char *msg, int error)
+{
+ if (p->c.is_cached) {
+ pr_err("ppa: (%s: %x) cache line: %llu\n",
+ msg, error, (u64)p->c.line);
+ } else {
+ pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+ msg, error,
+ p->g.ch, p->g.lun, p->g.blk,
+ p->g.pg, p->g.pl, p->g.sec);
+ }
+}
+
+static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
+ int error)
+{
+ int bit = -1;
+
+ if (rqd->nr_ppas == 1) {
+ print_ppa(&rqd->ppa_addr, "rqd", error);
+ return;
+ }
+
+ while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
+ bit + 1)) < rqd->nr_ppas) {
+ print_ppa(&rqd->ppa_list[bit], "rqd", error);
+ }
+
+ pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+}
+#endif
+
+static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
+ struct ppa_addr *ppas, int nr_ppas)
+{
+ struct nvm_geo *geo = &tgt_dev->geo;
+ struct ppa_addr *ppa;
+ int i;
+
+ for (i = 0; i < nr_ppas; i++) {
+ ppa = &ppas[i];
+
+ if (!ppa->c.is_cached &&
+ ppa->g.ch < geo->nr_chnls &&
+ ppa->g.lun < geo->luns_per_chnl &&
+ ppa->g.pl < geo->nr_planes &&
+ ppa->g.blk < geo->blks_per_lun &&
+ ppa->g.pg < geo->pgs_per_blk &&
+ ppa->g.sec < geo->sec_per_pg)
+ continue;
+
+#ifdef CONFIG_NVM_DEBUG
+ print_ppa(ppa, "boundary", i);
+#endif
+ return 1;
+ }
+ return 0;
+}
+
+static inline int pblk_boundary_paddr_checks(struct pblk *pblk, u64 paddr)
+{
+ struct pblk_line_meta *lm = &pblk->lm;
+
+ if (paddr > lm->sec_per_line)
+ return 1;
+
+ return 0;
+}
+
+static inline unsigned int pblk_get_bi_idx(struct bio *bio)
+{
+ return bio->bi_iter.bi_idx;
+}
+
+static inline sector_t pblk_get_lba(struct bio *bio)
+{
+ return bio->bi_iter.bi_sector / NR_PHY_IN_LOG;
+}
+
+static inline unsigned int pblk_get_secs(struct bio *bio)
+{
+ return bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE;
+}
+
+static inline sector_t pblk_get_sector(sector_t lba)
+{
+ return lba * NR_PHY_IN_LOG;
+}
+
+static inline void pblk_setup_uuid(struct pblk *pblk)
+{
+ uuid_le uuid;
+
+ uuid_le_gen(&uuid);
+ memcpy(pblk->instance_uuid, uuid.b, 16);
+}
+#endif /* PBLK_H_ */
diff --git a/drivers/lightnvm/rrpc.c b/drivers/lightnvm/rrpc.c
index e00b1d7b976f..cf0e28a0ff61 100644
--- a/drivers/lightnvm/rrpc.c
+++ b/drivers/lightnvm/rrpc.c
@@ -318,10 +318,6 @@ static int rrpc_move_valid_pages(struct rrpc *rrpc, struct rrpc_block *rblk)
}
page = mempool_alloc(rrpc->page_pool, GFP_NOIO);
- if (!page) {
- bio_put(bio);
- return -ENOMEM;
- }
while ((slot = find_first_zero_bit(rblk->invalid_pages,
nr_sec_per_blk)) < nr_sec_per_blk) {
@@ -414,7 +410,6 @@ static void rrpc_block_gc(struct work_struct *work)
struct rrpc *rrpc = gcb->rrpc;
struct rrpc_block *rblk = gcb->rblk;
struct rrpc_lun *rlun = rblk->rlun;
- struct nvm_tgt_dev *dev = rrpc->dev;
struct ppa_addr ppa;
mempool_free(gcb, rrpc->gcb_pool);
@@ -430,7 +425,7 @@ static void rrpc_block_gc(struct work_struct *work)
ppa.g.lun = rlun->bppa.g.lun;
ppa.g.blk = rblk->id;
- if (nvm_erase_blk(dev, &ppa, 0))
+ if (nvm_erase_sync(rrpc->dev, &ppa, 1))
goto put_back;
rrpc_put_blk(rrpc, rblk);
@@ -822,7 +817,7 @@ static int rrpc_read_ppalist_rq(struct rrpc *rrpc, struct bio *bio,
for (i = 0; i < npages; i++) {
/* We assume that mapping occurs at 4KB granularity */
- BUG_ON(!(laddr + i >= 0 && laddr + i < rrpc->nr_sects));
+ BUG_ON(!(laddr + i < rrpc->nr_sects));
gp = &rrpc->trans_map[laddr + i];
if (gp->rblk) {
@@ -851,7 +846,7 @@ static int rrpc_read_rq(struct rrpc *rrpc, struct bio *bio, struct nvm_rq *rqd,
if (!is_gc && rrpc_lock_rq(rrpc, bio, rqd))
return NVM_IO_REQUEUE;
- BUG_ON(!(laddr >= 0 && laddr < rrpc->nr_sects));
+ BUG_ON(!(laddr < rrpc->nr_sects));
gp = &rrpc->trans_map[laddr];
if (gp->rblk) {
@@ -1007,11 +1002,6 @@ static blk_qc_t rrpc_make_rq(struct request_queue *q, struct bio *bio)
}
rqd = mempool_alloc(rrpc->rq_pool, GFP_KERNEL);
- if (!rqd) {
- pr_err_ratelimited("rrpc: not able to queue bio.");
- bio_io_error(bio);
- return BLK_QC_T_NONE;
- }
memset(rqd, 0, sizeof(struct nvm_rq));
err = rrpc_submit_io(rrpc, bio, rqd, NVM_IOTYPE_NONE);
@@ -1275,8 +1265,10 @@ static int rrpc_bb_discovery(struct nvm_tgt_dev *dev, struct rrpc_lun *rlun)
}
nr_blks = nvm_bb_tbl_fold(dev->parent, blks, nr_blks);
- if (nr_blks < 0)
- return nr_blks;
+ if (nr_blks < 0) {
+ ret = nr_blks;
+ goto out;
+ }
for (i = 0; i < nr_blks; i++) {
if (blks[i] == NVM_BLK_T_FREE)
@@ -1514,7 +1506,8 @@ err:
static struct nvm_tgt_type tt_rrpc;
-static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk)
+static void *rrpc_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
+ int flags)
{
struct request_queue *bqueue = dev->q;
struct request_queue *tqueue = tdisk->queue;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 9c689b34e6e7..975922c8f231 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2773,7 +2773,6 @@ static int cache_create(struct cache_args *ca, struct cache **result)
ti->num_discard_bios = 1;
ti->discards_supported = true;
- ti->discard_zeroes_data_unsupported = true;
ti->split_discard_bios = false;
cache->features = ca->features;
diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h
index 136fda3ff9e5..fea5bd52ada8 100644
--- a/drivers/md/dm-core.h
+++ b/drivers/md/dm-core.h
@@ -132,6 +132,7 @@ void dm_init_md_queue(struct mapped_device *md);
void dm_init_normal_md_queue(struct mapped_device *md);
int md_in_flight(struct mapped_device *md);
void disable_write_same(struct mapped_device *md);
+void disable_write_zeroes(struct mapped_device *md);
static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
{
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 389a3637ffcc..ef1d836bd81b 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -2030,7 +2030,6 @@ static int crypt_ctr(struct dm_target *ti, unsigned int argc, char **argv)
wake_up_process(cc->write_thread);
ti->num_flush_bios = 1;
- ti->discard_zeroes_data_unsupported = true;
return 0;
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 03940bf36f6c..3702e502466d 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -312,9 +312,12 @@ static void do_region(int op, int op_flags, unsigned region,
*/
if (op == REQ_OP_DISCARD)
special_cmd_max_sectors = q->limits.max_discard_sectors;
+ else if (op == REQ_OP_WRITE_ZEROES)
+ special_cmd_max_sectors = q->limits.max_write_zeroes_sectors;
else if (op == REQ_OP_WRITE_SAME)
special_cmd_max_sectors = q->limits.max_write_same_sectors;
- if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_SAME) &&
+ if ((op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES ||
+ op == REQ_OP_WRITE_SAME) &&
special_cmd_max_sectors == 0) {
dec_count(io, region, -EOPNOTSUPP);
return;
@@ -328,11 +331,18 @@ static void do_region(int op, int op_flags, unsigned region,
/*
* Allocate a suitably sized-bio.
*/
- if ((op == REQ_OP_DISCARD) || (op == REQ_OP_WRITE_SAME))
+ switch (op) {
+ case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
+ num_bvecs = 0;
+ break;
+ case REQ_OP_WRITE_SAME:
num_bvecs = 1;
- else
+ break;
+ default:
num_bvecs = min_t(int, BIO_MAX_PAGES,
dm_sector_div_up(remaining, (PAGE_SIZE >> SECTOR_SHIFT)));
+ }
bio = bio_alloc_bioset(GFP_NOIO, num_bvecs, io->client->bios);
bio->bi_iter.bi_sector = where->sector + (where->count - remaining);
@@ -341,7 +351,7 @@ static void do_region(int op, int op_flags, unsigned region,
bio_set_op_attrs(bio, op, op_flags);
store_io_and_region_in_bio(bio, io, region);
- if (op == REQ_OP_DISCARD) {
+ if (op == REQ_OP_DISCARD || op == REQ_OP_WRITE_ZEROES) {
num_sectors = min_t(sector_t, special_cmd_max_sectors, remaining);
bio->bi_iter.bi_size = num_sectors << SECTOR_SHIFT;
remaining -= num_sectors;
diff --git a/drivers/md/dm-kcopyd.c b/drivers/md/dm-kcopyd.c
index 9e9d04cb7d51..f85846741d50 100644
--- a/drivers/md/dm-kcopyd.c
+++ b/drivers/md/dm-kcopyd.c
@@ -733,11 +733,11 @@ int dm_kcopyd_copy(struct dm_kcopyd_client *kc, struct dm_io_region *from,
job->pages = &zero_page_list;
/*
- * Use WRITE SAME to optimize zeroing if all dests support it.
+ * Use WRITE ZEROES to optimize zeroing if all dests support it.
*/
- job->rw = REQ_OP_WRITE_SAME;
+ job->rw = REQ_OP_WRITE_ZEROES;
for (i = 0; i < job->num_dests; i++)
- if (!bdev_write_same(job->dests[i].bdev)) {
+ if (!bdev_write_zeroes_sectors(job->dests[i].bdev)) {
job->rw = WRITE;
break;
}
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 4788b0b989a9..e17fd44ceef5 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -59,6 +59,7 @@ static int linear_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_same_bios = 1;
+ ti->num_write_zeroes_bios = 1;
ti->private = lc;
return 0;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 7f223dbed49f..2950b145443d 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1103,6 +1103,7 @@ static int multipath_ctr(struct dm_target *ti, unsigned argc, char **argv)
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->num_write_same_bios = 1;
+ ti->num_write_zeroes_bios = 1;
if (m->queue_mode == DM_TYPE_BIO_BASED)
ti->per_io_data_size = multipath_per_bio_data_size();
else
@@ -1491,7 +1492,7 @@ static int do_end_io(struct multipath *m, struct request *clone,
*/
int r = DM_ENDIO_REQUEUE;
- if (!error && !clone->errors)
+ if (!error)
return 0; /* I/O complete */
if (noretry_error(error))
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 1e217ba84d09..2dae3e5b851c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -2813,7 +2813,9 @@ static void configure_discard_support(struct raid_set *rs)
/* Assume discards not supported until after checks below. */
ti->discards_supported = false;
- /* RAID level 4,5,6 require discard_zeroes_data for data integrity! */
+ /*
+ * XXX: RAID level 4,5,6 require zeroing for safety.
+ */
raid456 = (rs->md.level == 4 || rs->md.level == 5 || rs->md.level == 6);
for (i = 0; i < rs->raid_disks; i++) {
@@ -2827,8 +2829,6 @@ static void configure_discard_support(struct raid_set *rs)
return;
if (raid456) {
- if (!q->limits.discard_zeroes_data)
- return;
if (!devices_handle_discard_safely) {
DMERR("raid456 discard support disabled due to discard_zeroes_data uncertainty.");
DMERR("Set dm-raid.devices_handle_discard_safely=Y to override.");
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 2ddc2d20e62d..a95cbb80fb34 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1124,7 +1124,6 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->num_flush_bios = 1;
ti->num_discard_bios = 1;
ti->per_io_data_size = sizeof(struct dm_raid1_bio_record);
- ti->discard_zeroes_data_unsupported = true;
ms->kmirrord_wq = alloc_workqueue("kmirrord", WQ_MEM_RECLAIM, 0);
if (!ms->kmirrord_wq) {
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index 0b081d170087..bff7e3bdb4ed 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -298,9 +298,14 @@ static void dm_done(struct request *clone, int error, bool mapped)
r = rq_end_io(tio->ti, clone, error, &tio->info);
}
- if (unlikely(r == -EREMOTEIO && (req_op(clone) == REQ_OP_WRITE_SAME) &&
- !clone->q->limits.max_write_same_sectors))
- disable_write_same(tio->md);
+ if (unlikely(r == -EREMOTEIO)) {
+ if (req_op(clone) == REQ_OP_WRITE_SAME &&
+ !clone->q->limits.max_write_same_sectors)
+ disable_write_same(tio->md);
+ if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
+ !clone->q->limits.max_write_zeroes_sectors)
+ disable_write_zeroes(tio->md);
+ }
if (r <= 0)
/* The target wants to complete the I/O */
@@ -358,7 +363,7 @@ static void dm_complete_request(struct request *rq, int error)
if (!rq->q->mq_ops)
blk_complete_request(rq);
else
- blk_mq_complete_request(rq, error);
+ blk_mq_complete_request(rq);
}
/*
@@ -762,7 +767,7 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
return BLK_MQ_RQ_QUEUE_OK;
}
-static struct blk_mq_ops dm_mq_ops = {
+static const struct blk_mq_ops dm_mq_ops = {
.queue_rq = dm_mq_queue_rq,
.complete = dm_softirq_done,
.init_request = dm_mq_init_request,
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index 28193a57bf47..5ef49c121d99 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -169,6 +169,7 @@ static int stripe_ctr(struct dm_target *ti, unsigned int argc, char **argv)
ti->num_flush_bios = stripes;
ti->num_discard_bios = stripes;
ti->num_write_same_bios = stripes;
+ ti->num_write_zeroes_bios = stripes;
sc->chunk_size = chunk_size;
if (chunk_size & (chunk_size - 1))
@@ -293,6 +294,7 @@ static int stripe_map(struct dm_target *ti, struct bio *bio)
return DM_MAPIO_REMAPPED;
}
if (unlikely(bio_op(bio) == REQ_OP_DISCARD) ||
+ unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES) ||
unlikely(bio_op(bio) == REQ_OP_WRITE_SAME)) {
target_bio_nr = dm_bio_get_target_bio_nr(bio);
BUG_ON(target_bio_nr >= sc->stripes);
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 3ad16d9c9d5a..958275aca008 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -1449,22 +1449,6 @@ static bool dm_table_supports_flush(struct dm_table *t, unsigned long flush)
return false;
}
-static bool dm_table_discard_zeroes_data(struct dm_table *t)
-{
- struct dm_target *ti;
- unsigned i = 0;
-
- /* Ensure that all targets supports discard_zeroes_data. */
- while (i < dm_table_get_num_targets(t)) {
- ti = dm_table_get_target(t, i++);
-
- if (ti->discard_zeroes_data_unsupported)
- return false;
- }
-
- return true;
-}
-
static int device_is_nonrot(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
@@ -1533,6 +1517,34 @@ static bool dm_table_supports_write_same(struct dm_table *t)
return true;
}
+static int device_not_write_zeroes_capable(struct dm_target *ti, struct dm_dev *dev,
+ sector_t start, sector_t len, void *data)
+{
+ struct request_queue *q = bdev_get_queue(dev->bdev);
+
+ return q && !q->limits.max_write_zeroes_sectors;
+}
+
+static bool dm_table_supports_write_zeroes(struct dm_table *t)
+{
+ struct dm_target *ti;
+ unsigned i = 0;
+
+ while (i < dm_table_get_num_targets(t)) {
+ ti = dm_table_get_target(t, i++);
+
+ if (!ti->num_write_zeroes_bios)
+ return false;
+
+ if (!ti->type->iterate_devices ||
+ ti->type->iterate_devices(ti, device_not_write_zeroes_capable, NULL))
+ return false;
+ }
+
+ return true;
+}
+
+
static int device_discard_capable(struct dm_target *ti, struct dm_dev *dev,
sector_t start, sector_t len, void *data)
{
@@ -1592,9 +1604,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
}
blk_queue_write_cache(q, wc, fua);
- if (!dm_table_discard_zeroes_data(t))
- q->limits.discard_zeroes_data = 0;
-
/* Ensure that all underlying devices are non-rotational. */
if (dm_table_all_devices_attribute(t, device_is_nonrot))
queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q);
@@ -1603,6 +1612,8 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
if (!dm_table_supports_write_same(t))
q->limits.max_write_same_sectors = 0;
+ if (!dm_table_supports_write_zeroes(t))
+ q->limits.max_write_zeroes_sectors = 0;
if (dm_table_all_devices_attribute(t, queue_supports_sg_merge))
queue_flag_clear_unlocked(QUEUE_FLAG_NO_SG_MERGE, q);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 2b266a2b5035..a5f1916f621a 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -3263,7 +3263,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv)
* them down to the data device. The thin device's discard
* processing will cause mappings to be removed from the btree.
*/
- ti->discard_zeroes_data_unsupported = true;
if (pf.discard_enabled && pf.discard_passdown) {
ti->num_discard_bios = 1;
@@ -4119,7 +4118,6 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
ti->per_io_data_size = sizeof(struct dm_thin_endio_hook);
/* In case the pool supports discards, pass them on. */
- ti->discard_zeroes_data_unsupported = true;
if (tc->pool->pf.discard_enabled) {
ti->discards_supported = true;
ti->num_discard_bios = 1;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index dfb75979e455..8bf397729bbd 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -810,7 +810,6 @@ static void dec_pending(struct dm_io *io, int error)
queue_io(md, bio);
} else {
/* done with normal IO or empty flush */
- trace_block_bio_complete(md->queue, bio, io_error);
bio->bi_error = io_error;
bio_endio(bio);
}
@@ -825,6 +824,14 @@ void disable_write_same(struct mapped_device *md)
limits->max_write_same_sectors = 0;
}
+void disable_write_zeroes(struct mapped_device *md)
+{
+ struct queue_limits *limits = dm_get_queue_limits(md);
+
+ /* device doesn't really support WRITE ZEROES, disable it */
+ limits->max_write_zeroes_sectors = 0;
+}
+
static void clone_endio(struct bio *bio)
{
int error = bio->bi_error;
@@ -851,9 +858,14 @@ static void clone_endio(struct bio *bio)
}
}
- if (unlikely(r == -EREMOTEIO && (bio_op(bio) == REQ_OP_WRITE_SAME) &&
- !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors))
- disable_write_same(md);
+ if (unlikely(r == -EREMOTEIO)) {
+ if (bio_op(bio) == REQ_OP_WRITE_SAME &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
+ disable_write_same(md);
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+ disable_write_zeroes(md);
+ }
free_tio(tio);
dec_pending(io, error);
@@ -1202,6 +1214,11 @@ static unsigned get_num_write_same_bios(struct dm_target *ti)
return ti->num_write_same_bios;
}
+static unsigned get_num_write_zeroes_bios(struct dm_target *ti)
+{
+ return ti->num_write_zeroes_bios;
+}
+
typedef bool (*is_split_required_fn)(struct dm_target *ti);
static bool is_split_required_for_discard(struct dm_target *ti)
@@ -1256,6 +1273,11 @@ static int __send_write_same(struct clone_info *ci)
return __send_changing_extent_only(ci, get_num_write_same_bios, NULL);
}
+static int __send_write_zeroes(struct clone_info *ci)
+{
+ return __send_changing_extent_only(ci, get_num_write_zeroes_bios, NULL);
+}
+
/*
* Select the correct strategy for processing a non-flush bio.
*/
@@ -1270,6 +1292,8 @@ static int __split_and_process_non_flush(struct clone_info *ci)
return __send_discard(ci);
else if (unlikely(bio_op(bio) == REQ_OP_WRITE_SAME))
return __send_write_same(ci);
+ else if (unlikely(bio_op(bio) == REQ_OP_WRITE_ZEROES))
+ return __send_write_zeroes(ci);
ti = dm_table_find_target(ci->map, ci->sector);
if (!dm_target_is_valid(ti))
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 3e38e0207a3e..377a8a3672e3 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -293,6 +293,7 @@ static void linear_make_request(struct mddev *mddev, struct bio *bio)
split, disk_devt(mddev->gendisk),
bio_sector);
mddev_check_writesame(mddev, split);
+ mddev_check_write_zeroes(mddev, split);
generic_make_request(split);
}
} while (split != bio);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index dde8ecb760c8..1e76d64ce180 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -709,4 +709,11 @@ static inline void mddev_check_writesame(struct mddev *mddev, struct bio *bio)
!bdev_get_queue(bio->bi_bdev)->limits.max_write_same_sectors)
mddev->queue->limits.max_write_same_sectors = 0;
}
+
+static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio)
+{
+ if (bio_op(bio) == REQ_OP_WRITE_ZEROES &&
+ !bdev_get_queue(bio->bi_bdev)->limits.max_write_zeroes_sectors)
+ mddev->queue->limits.max_write_zeroes_sectors = 0;
+}
#endif /* _MD_MD_H */
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 79a12b59250b..e95d521d93e9 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -139,6 +139,7 @@ static void multipath_make_request(struct mddev *mddev, struct bio * bio)
mp_bh->bio.bi_end_io = multipath_end_request;
mp_bh->bio.bi_private = mp_bh;
mddev_check_writesame(mddev, &mp_bh->bio);
+ mddev_check_write_zeroes(mddev, &mp_bh->bio);
generic_make_request(&mp_bh->bio);
return;
}
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 93347ca7c7a6..ce7a6a56cf73 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -383,6 +383,7 @@ static int raid0_run(struct mddev *mddev)
blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
@@ -504,6 +505,7 @@ static void raid0_make_request(struct mddev *mddev, struct bio *bio)
split, disk_devt(mddev->gendisk),
bio_sector);
mddev_check_writesame(mddev, split);
+ mddev_check_write_zeroes(mddev, split);
generic_make_request(split);
}
} while (split != bio);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index a34f58772022..b59cc100320a 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3177,8 +3177,10 @@ static int raid1_run(struct mddev *mddev)
if (IS_ERR(conf))
return PTR_ERR(conf);
- if (mddev->queue)
+ if (mddev->queue) {
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
+ }
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index e89a8d78a9ed..28ec3a93acee 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3749,6 +3749,7 @@ static int raid10_run(struct mddev *mddev)
blk_queue_max_discard_sectors(mddev->queue,
mddev->chunk_sectors);
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ed5cd705b985..2efdb0d67460 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -5031,8 +5031,6 @@ static void raid5_align_endio(struct bio *bi)
rdev_dec_pending(rdev, conf->mddev);
if (!error) {
- trace_block_bio_complete(bdev_get_queue(raid_bi->bi_bdev),
- raid_bi, 0);
bio_endio(raid_bi);
if (atomic_dec_and_test(&conf->active_aligned_reads))
wake_up(&conf->wait_for_quiescent);
@@ -7229,7 +7227,6 @@ static int raid5_run(struct mddev *mddev)
if (mddev->queue) {
int chunk_size;
- bool discard_supported = true;
/* read-ahead size must cover two whole stripes, which
* is 2 * (datadisks) * chunksize where 'n' is the
* number of raid devices
@@ -7265,48 +7262,32 @@ static int raid5_run(struct mddev *mddev)
blk_queue_max_discard_sectors(mddev->queue,
0xfffe * STRIPE_SECTORS);
- /*
- * unaligned part of discard request will be ignored, so can't
- * guarantee discard_zeroes_data
- */
- mddev->queue->limits.discard_zeroes_data = 0;
-
blk_queue_max_write_same_sectors(mddev->queue, 0);
+ blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
rdev_for_each(rdev, mddev) {
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->new_data_offset << 9);
- /*
- * discard_zeroes_data is required, otherwise data
- * could be lost. Consider a scenario: discard a stripe
- * (the stripe could be inconsistent if
- * discard_zeroes_data is 0); write one disk of the
- * stripe (the stripe could be inconsistent again
- * depending on which disks are used to calculate
- * parity); the disk is broken; The stripe data of this
- * disk is lost.
- */
- if (!blk_queue_discard(bdev_get_queue(rdev->bdev)) ||
- !bdev_get_queue(rdev->bdev)->
- limits.discard_zeroes_data)
- discard_supported = false;
- /* Unfortunately, discard_zeroes_data is not currently
- * a guarantee - just a hint. So we only allow DISCARD
- * if the sysadmin has confirmed that only safe devices
- * are in use by setting a module parameter.
- */
- if (!devices_handle_discard_safely) {
- if (discard_supported) {
- pr_info("md/raid456: discard support disabled due to uncertainty.\n");
- pr_info("Set raid456.devices_handle_discard_safely=Y to override.\n");
- }
- discard_supported = false;
- }
}
- if (discard_supported &&
+ /*
+ * zeroing is required, otherwise data
+ * could be lost. Consider a scenario: discard a stripe
+ * (the stripe could be inconsistent if
+ * discard_zeroes_data is 0); write one disk of the
+ * stripe (the stripe could be inconsistent again
+ * depending on which disks are used to calculate
+ * parity); the disk is broken; The stripe data of this
+ * disk is lost.
+ *
+ * We only allow DISCARD if the sysadmin has confirmed that
+ * only safe devices are in use by setting a module parameter.
+ * A better idea might be to turn DISCARD into WRITE_ZEROES
+ * requests, as that is required to be safe.
+ */
+ if (devices_handle_discard_safely &&
mddev->queue->limits.max_discard_sectors >= (stripe >> 9) &&
mddev->queue->limits.discard_granularity >= stripe)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD,
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 493eb10ce580..4c54ad34e17a 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -167,8 +167,6 @@ static void mmc_queue_setup_discard(struct request_queue *q,
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
blk_queue_max_discard_sectors(q, max_discard);
- if (card->erased_byte == 0 && !mmc_can_discard(card))
- q->limits.discard_zeroes_data = 1;
q->limits.discard_granularity = card->pref_erase << 9;
/* granularity must not be greater than max. discard */
if (card->pref_erase > max_discard)
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 66a9dedd1062..1517da3ddd7d 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -46,7 +46,7 @@
#include "mtdcore.h"
-static struct backing_dev_info *mtd_bdi;
+struct backing_dev_info *mtd_bdi;
#ifdef CONFIG_PM_SLEEP
@@ -496,11 +496,9 @@ int add_mtd_device(struct mtd_info *mtd)
* mtd_device_parse_register() multiple times on the same master MTD,
* especially with CONFIG_MTD_PARTITIONED_MASTER=y.
*/
- if (WARN_ONCE(mtd->backing_dev_info, "MTD already registered\n"))
+ if (WARN_ONCE(mtd->dev.type, "MTD already registered\n"))
return -EEXIST;
- mtd->backing_dev_info = mtd_bdi;
-
BUG_ON(mtd->writesize == 0);
mutex_lock(&mtd_table_mutex);
@@ -1775,13 +1773,18 @@ static struct backing_dev_info * __init mtd_bdi_init(char *name)
struct backing_dev_info *bdi;
int ret;
- bdi = kzalloc(sizeof(*bdi), GFP_KERNEL);
+ bdi = bdi_alloc(GFP_KERNEL);
if (!bdi)
return ERR_PTR(-ENOMEM);
- ret = bdi_setup_and_register(bdi, name);
+ bdi->name = name;
+ /*
+ * We put '-0' suffix to the name to get the same name format as we
+ * used to get. Since this is called only once, we get a unique name.
+ */
+ ret = bdi_register(bdi, "%.28s-0", name);
if (ret)
- kfree(bdi);
+ bdi_put(bdi);
return ret ? ERR_PTR(ret) : bdi;
}
@@ -1813,8 +1816,7 @@ static int __init init_mtd(void)
out_procfs:
if (proc_mtd)
remove_proc_entry("mtd", NULL);
- bdi_destroy(mtd_bdi);
- kfree(mtd_bdi);
+ bdi_put(mtd_bdi);
err_bdi:
class_unregister(&mtd_class);
err_reg:
@@ -1828,8 +1830,7 @@ static void __exit cleanup_mtd(void)
if (proc_mtd)
remove_proc_entry("mtd", NULL);
class_unregister(&mtd_class);
- bdi_destroy(mtd_bdi);
- kfree(mtd_bdi);
+ bdi_put(mtd_bdi);
idr_destroy(&mtd_idr);
}
diff --git a/drivers/mtd/mtdsuper.c b/drivers/mtd/mtdsuper.c
index 20c02a3b7417..e43fea896d1e 100644
--- a/drivers/mtd/mtdsuper.c
+++ b/drivers/mtd/mtdsuper.c
@@ -18,6 +18,7 @@
#include <linux/ctype.h>
#include <linux/slab.h>
#include <linux/major.h>
+#include <linux/backing-dev.h>
/*
* compare superblocks to see if they're equivalent
@@ -38,6 +39,8 @@ static int get_sb_mtd_compare(struct super_block *sb, void *_mtd)
return 0;
}
+extern struct backing_dev_info *mtd_bdi;
+
/*
* mark the superblock by the MTD device it is using
* - set the device number to be the correct MTD block device for pesuperstence
@@ -49,7 +52,8 @@ static int get_sb_mtd_set(struct super_block *sb, void *_mtd)
sb->s_mtd = mtd;
sb->s_dev = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
- sb->s_bdi = mtd->backing_dev_info;
+ sb->s_bdi = bdi_get(mtd_bdi);
+
return 0;
}
diff --git a/drivers/mtd/ubi/block.c b/drivers/mtd/ubi/block.c
index c80869e60909..51f2be8889b5 100644
--- a/drivers/mtd/ubi/block.c
+++ b/drivers/mtd/ubi/block.c
@@ -347,7 +347,7 @@ static int ubiblock_init_request(void *data, struct request *req,
return 0;
}
-static struct blk_mq_ops ubiblock_mq_ops = {
+static const struct blk_mq_ops ubiblock_mq_ops = {
.queue_rq = ubiblock_queue_rq,
.init_request = ubiblock_init_request,
};
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eeb409c287b8..bf6729b1d8bf 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -49,10 +49,9 @@ unsigned char shutdown_timeout = 5;
module_param(shutdown_timeout, byte, 0644);
MODULE_PARM_DESC(shutdown_timeout, "timeout in seconds for controller shutdown");
-unsigned int nvme_max_retries = 5;
-module_param_named(max_retries, nvme_max_retries, uint, 0644);
+static u8 nvme_max_retries = 5;
+module_param_named(max_retries, nvme_max_retries, byte, 0644);
MODULE_PARM_DESC(max_retries, "max number of retries a command may have");
-EXPORT_SYMBOL_GPL(nvme_max_retries);
static int nvme_char_major;
module_param(nvme_char_major, int, 0);
@@ -67,6 +66,57 @@ static DEFINE_SPINLOCK(dev_list_lock);
static struct class *nvme_class;
+static int nvme_error_status(struct request *req)
+{
+ switch (nvme_req(req)->status & 0x7ff) {
+ case NVME_SC_SUCCESS:
+ return 0;
+ case NVME_SC_CAP_EXCEEDED:
+ return -ENOSPC;
+ default:
+ return -EIO;
+
+ /*
+ * XXX: these errors are a nasty side-band protocol to
+ * drivers/md/dm-mpath.c:noretry_error() that aren't documented
+ * anywhere..
+ */
+ case NVME_SC_CMD_SEQ_ERROR:
+ return -EILSEQ;
+ case NVME_SC_ONCS_NOT_SUPPORTED:
+ return -EOPNOTSUPP;
+ case NVME_SC_WRITE_FAULT:
+ case NVME_SC_READ_ERROR:
+ case NVME_SC_UNWRITTEN_BLOCK:
+ return -ENODATA;
+ }
+}
+
+static inline bool nvme_req_needs_retry(struct request *req)
+{
+ if (blk_noretry_request(req))
+ return false;
+ if (nvme_req(req)->status & NVME_SC_DNR)
+ return false;
+ if (jiffies - req->start_time >= req->timeout)
+ return false;
+ if (nvme_req(req)->retries >= nvme_max_retries)
+ return false;
+ return true;
+}
+
+void nvme_complete_rq(struct request *req)
+{
+ if (unlikely(nvme_req(req)->status && nvme_req_needs_retry(req))) {
+ nvme_req(req)->retries++;
+ blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
+ return;
+ }
+
+ blk_mq_end_request(req, nvme_error_status(req));
+}
+EXPORT_SYMBOL_GPL(nvme_complete_rq);
+
void nvme_cancel_request(struct request *req, void *data, bool reserved)
{
int status;
@@ -80,7 +130,9 @@ void nvme_cancel_request(struct request *req, void *data, bool reserved)
status = NVME_SC_ABORT_REQ;
if (blk_queue_dying(req->q))
status |= NVME_SC_DNR;
- blk_mq_complete_request(req, status);
+ nvme_req(req)->status = status;
+ blk_mq_complete_request(req);
+
}
EXPORT_SYMBOL_GPL(nvme_cancel_request);
@@ -205,12 +257,6 @@ fail:
return NULL;
}
-void nvme_requeue_req(struct request *req)
-{
- blk_mq_requeue_request(req, !blk_mq_queue_stopped(req->q));
-}
-EXPORT_SYMBOL_GPL(nvme_requeue_req);
-
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid)
{
@@ -327,6 +373,12 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
{
int ret = BLK_MQ_RQ_QUEUE_OK;
+ if (!(req->rq_flags & RQF_DONTPREP)) {
+ nvme_req(req)->retries = 0;
+ nvme_req(req)->flags = 0;
+ req->rq_flags |= RQF_DONTPREP;
+ }
+
switch (req_op(req)) {
case REQ_OP_DRV_IN:
case REQ_OP_DRV_OUT:
@@ -335,6 +387,8 @@ int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
case REQ_OP_FLUSH:
nvme_setup_flush(ns, cmd);
break;
+ case REQ_OP_WRITE_ZEROES:
+ /* currently only aliased to deallocate for a few ctrls: */
case REQ_OP_DISCARD:
ret = nvme_setup_discard(ns, req, cmd);
break;
@@ -378,7 +432,10 @@ int __nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
blk_execute_rq(req->q, NULL, req, at_head);
if (result)
*result = nvme_req(req)->result;
- ret = req->errors;
+ if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else
+ ret = nvme_req(req)->status;
out:
blk_mq_free_request(req);
return ret;
@@ -463,7 +520,10 @@ int __nvme_submit_user_cmd(struct request_queue *q, struct nvme_command *cmd,
}
submit:
blk_execute_rq(req->q, disk, req, 0);
- ret = req->errors;
+ if (nvme_req(req)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else
+ ret = nvme_req(req)->status;
if (result)
*result = le32_to_cpu(nvme_req(req)->result.u32);
if (meta && !ret && !write) {
@@ -900,16 +960,14 @@ static void nvme_config_discard(struct nvme_ns *ns)
BUILD_BUG_ON(PAGE_SIZE / sizeof(struct nvme_dsm_range) <
NVME_DSM_MAX_RANGES);
- if (ctrl->quirks & NVME_QUIRK_DISCARD_ZEROES)
- ns->queue->limits.discard_zeroes_data = 1;
- else
- 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, UINT_MAX);
blk_queue_max_discard_segments(ns->queue, NVME_DSM_MAX_RANGES);
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, ns->queue);
+
+ if (ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES)
+ blk_queue_max_write_zeroes_sectors(ns->queue, UINT_MAX);
}
static int nvme_revalidate_ns(struct nvme_ns *ns, struct nvme_id_ns **id)
@@ -2393,7 +2451,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl)
mutex_lock(&ctrl->namespaces_mutex);
list_for_each_entry(ns, &ctrl->namespaces, list)
- blk_mq_freeze_queue_start(ns->queue);
+ blk_freeze_queue_start(ns->queue);
mutex_unlock(&ctrl->namespaces_mutex);
}
EXPORT_SYMBOL_GPL(nvme_start_freeze);
diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 5b7386f69f4d..990e6fb32a63 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -471,6 +471,16 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid)
}
EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
+{
+ if (ctrl->opts->max_reconnects != -1 &&
+ ctrl->opts->nr_reconnects < ctrl->opts->max_reconnects)
+ return true;
+
+ return false;
+}
+EXPORT_SYMBOL_GPL(nvmf_should_reconnect);
+
/**
* nvmf_register_transport() - NVMe Fabrics Library registration function.
* @ops: Transport ops instance to be registered to the
@@ -533,6 +543,7 @@ static const match_table_t opt_tokens = {
{ NVMF_OPT_QUEUE_SIZE, "queue_size=%d" },
{ NVMF_OPT_NR_IO_QUEUES, "nr_io_queues=%d" },
{ NVMF_OPT_RECONNECT_DELAY, "reconnect_delay=%d" },
+ { NVMF_OPT_CTRL_LOSS_TMO, "ctrl_loss_tmo=%d" },
{ NVMF_OPT_KATO, "keep_alive_tmo=%d" },
{ NVMF_OPT_HOSTNQN, "hostnqn=%s" },
{ NVMF_OPT_HOST_TRADDR, "host_traddr=%s" },
@@ -546,6 +557,7 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
char *options, *o, *p;
int token, ret = 0;
size_t nqnlen = 0;
+ int ctrl_loss_tmo = NVMF_DEF_CTRL_LOSS_TMO;
/* Set defaults */
opts->queue_size = NVMF_DEF_QUEUE_SIZE;
@@ -655,6 +667,16 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
opts->kato = token;
break;
+ case NVMF_OPT_CTRL_LOSS_TMO:
+ if (match_int(args, &token)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (token < 0)
+ pr_warn("ctrl_loss_tmo < 0 will reconnect forever\n");
+ ctrl_loss_tmo = token;
+ break;
case NVMF_OPT_HOSTNQN:
if (opts->host) {
pr_err("hostnqn already user-assigned: %s\n",
@@ -710,6 +732,12 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts,
}
}
+ if (ctrl_loss_tmo < 0)
+ opts->max_reconnects = -1;
+ else
+ opts->max_reconnects = DIV_ROUND_UP(ctrl_loss_tmo,
+ opts->reconnect_delay);
+
if (!opts->host) {
kref_get(&nvmf_default_host->ref);
opts->host = nvmf_default_host;
diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h
index 156018182ce4..f5a9c1fb186f 100644
--- a/drivers/nvme/host/fabrics.h
+++ b/drivers/nvme/host/fabrics.h
@@ -21,6 +21,8 @@
#define NVMF_MAX_QUEUE_SIZE 1024
#define NVMF_DEF_QUEUE_SIZE 128
#define NVMF_DEF_RECONNECT_DELAY 10
+/* default to 600 seconds of reconnect attempts before giving up */
+#define NVMF_DEF_CTRL_LOSS_TMO 600
/*
* Define a host as seen by the target. We allocate one at boot, but also
@@ -53,6 +55,7 @@ enum {
NVMF_OPT_HOSTNQN = 1 << 8,
NVMF_OPT_RECONNECT_DELAY = 1 << 9,
NVMF_OPT_HOST_TRADDR = 1 << 10,
+ NVMF_OPT_CTRL_LOSS_TMO = 1 << 11,
};
/**
@@ -77,6 +80,10 @@ enum {
* @discovery_nqn: indicates if the subsysnqn is the well-known discovery NQN.
* @kato: Keep-alive timeout.
* @host: Virtual NVMe host, contains the NQN and Host ID.
+ * @nr_reconnects: number of reconnect attempted since the last ctrl failure
+ * @max_reconnects: maximum number of allowed reconnect attempts before removing
+ * the controller, (-1) means reconnect forever, zero means remove
+ * immediately;
*/
struct nvmf_ctrl_options {
unsigned mask;
@@ -91,6 +98,8 @@ struct nvmf_ctrl_options {
bool discovery_nqn;
unsigned int kato;
struct nvmf_host *host;
+ int nr_reconnects;
+ int max_reconnects;
};
/*
@@ -133,5 +142,6 @@ void nvmf_unregister_transport(struct nvmf_transport_ops *ops);
void nvmf_free_options(struct nvmf_ctrl_options *opts);
const char *nvmf_get_subsysnqn(struct nvme_ctrl *ctrl);
int nvmf_get_address(struct nvme_ctrl *ctrl, char *buf, int size);
+bool nvmf_should_reconnect(struct nvme_ctrl *ctrl);
#endif /* _NVME_FABRICS_H */
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index d996ca73d3be..ecc1048de837 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -61,16 +61,23 @@ struct nvme_fc_queue {
unsigned long flags;
} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */
+enum nvme_fcop_flags {
+ FCOP_FLAGS_TERMIO = (1 << 0),
+ FCOP_FLAGS_RELEASED = (1 << 1),
+ FCOP_FLAGS_COMPLETE = (1 << 2),
+};
+
struct nvmefc_ls_req_op {
struct nvmefc_ls_req ls_req;
- struct nvme_fc_ctrl *ctrl;
+ struct nvme_fc_rport *rport;
struct nvme_fc_queue *queue;
struct request *rq;
+ u32 flags;
int ls_error;
struct completion ls_done;
- struct list_head lsreq_list; /* ctrl->ls_req_list */
+ struct list_head lsreq_list; /* rport->ls_req_list */
bool req_queued;
};
@@ -120,6 +127,9 @@ struct nvme_fc_rport {
struct list_head endp_list; /* for lport->endp_list */
struct list_head ctrl_list;
+ struct list_head ls_req_list;
+ struct device *dev; /* physical device for dma */
+ struct nvme_fc_lport *lport;
spinlock_t lock;
struct kref ref;
} __aligned(sizeof(u64)); /* alignment for other things alloc'd with */
@@ -144,7 +154,6 @@ struct nvme_fc_ctrl {
u64 cap;
struct list_head ctrl_list; /* rport->ctrl_list */
- struct list_head ls_req_list;
struct blk_mq_tag_set admin_tag_set;
struct blk_mq_tag_set tag_set;
@@ -419,9 +428,12 @@ nvme_fc_register_remoteport(struct nvme_fc_local_port *localport,
INIT_LIST_HEAD(&newrec->endp_list);
INIT_LIST_HEAD(&newrec->ctrl_list);
+ INIT_LIST_HEAD(&newrec->ls_req_list);
kref_init(&newrec->ref);
spin_lock_init(&newrec->lock);
newrec->remoteport.localport = &lport->localport;
+ newrec->dev = lport->dev;
+ newrec->lport = lport;
newrec->remoteport.private = &newrec[1];
newrec->remoteport.port_role = pinfo->port_role;
newrec->remoteport.node_name = pinfo->node_name;
@@ -444,7 +456,6 @@ out_kfree_rport:
out_reghost_failed:
*portptr = NULL;
return ret;
-
}
EXPORT_SYMBOL_GPL(nvme_fc_register_remoteport);
@@ -487,6 +498,30 @@ nvme_fc_rport_get(struct nvme_fc_rport *rport)
return kref_get_unless_zero(&rport->ref);
}
+static int
+nvme_fc_abort_lsops(struct nvme_fc_rport *rport)
+{
+ struct nvmefc_ls_req_op *lsop;
+ unsigned long flags;
+
+restart:
+ spin_lock_irqsave(&rport->lock, flags);
+
+ list_for_each_entry(lsop, &rport->ls_req_list, lsreq_list) {
+ if (!(lsop->flags & FCOP_FLAGS_TERMIO)) {
+ lsop->flags |= FCOP_FLAGS_TERMIO;
+ spin_unlock_irqrestore(&rport->lock, flags);
+ rport->lport->ops->ls_abort(&rport->lport->localport,
+ &rport->remoteport,
+ &lsop->ls_req);
+ goto restart;
+ }
+ }
+ spin_unlock_irqrestore(&rport->lock, flags);
+
+ return 0;
+}
+
/**
* nvme_fc_unregister_remoteport - transport entry point called by an
* LLDD to deregister/remove a previously
@@ -522,6 +557,8 @@ nvme_fc_unregister_remoteport(struct nvme_fc_remote_port *portptr)
spin_unlock_irqrestore(&rport->lock, flags);
+ nvme_fc_abort_lsops(rport);
+
nvme_fc_rport_put(rport);
return 0;
}
@@ -624,16 +661,16 @@ static int nvme_fc_ctrl_get(struct nvme_fc_ctrl *);
static void
-__nvme_fc_finish_ls_req(struct nvme_fc_ctrl *ctrl,
- struct nvmefc_ls_req_op *lsop)
+__nvme_fc_finish_ls_req(struct nvmefc_ls_req_op *lsop)
{
+ struct nvme_fc_rport *rport = lsop->rport;
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
unsigned long flags;
- spin_lock_irqsave(&ctrl->lock, flags);
+ spin_lock_irqsave(&rport->lock, flags);
if (!lsop->req_queued) {
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
return;
}
@@ -641,56 +678,71 @@ __nvme_fc_finish_ls_req(struct nvme_fc_ctrl *ctrl,
lsop->req_queued = false;
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
- fc_dma_unmap_single(ctrl->dev, lsreq->rqstdma,
+ fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
(lsreq->rqstlen + lsreq->rsplen),
DMA_BIDIRECTIONAL);
- nvme_fc_ctrl_put(ctrl);
+ nvme_fc_rport_put(rport);
}
static int
-__nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl,
+__nvme_fc_send_ls_req(struct nvme_fc_rport *rport,
struct nvmefc_ls_req_op *lsop,
void (*done)(struct nvmefc_ls_req *req, int status))
{
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
unsigned long flags;
- int ret;
+ int ret = 0;
- if (!nvme_fc_ctrl_get(ctrl))
+ if (rport->remoteport.port_state != FC_OBJSTATE_ONLINE)
+ return -ECONNREFUSED;
+
+ if (!nvme_fc_rport_get(rport))
return -ESHUTDOWN;
lsreq->done = done;
- lsop->ctrl = ctrl;
+ lsop->rport = rport;
lsop->req_queued = false;
INIT_LIST_HEAD(&lsop->lsreq_list);
init_completion(&lsop->ls_done);
- lsreq->rqstdma = fc_dma_map_single(ctrl->dev, lsreq->rqstaddr,
+ lsreq->rqstdma = fc_dma_map_single(rport->dev, lsreq->rqstaddr,
lsreq->rqstlen + lsreq->rsplen,
DMA_BIDIRECTIONAL);
- if (fc_dma_mapping_error(ctrl->dev, lsreq->rqstdma)) {
- nvme_fc_ctrl_put(ctrl);
- dev_err(ctrl->dev,
- "els request command failed EFAULT.\n");
- return -EFAULT;
+ if (fc_dma_mapping_error(rport->dev, lsreq->rqstdma)) {
+ ret = -EFAULT;
+ goto out_putrport;
}
lsreq->rspdma = lsreq->rqstdma + lsreq->rqstlen;
- spin_lock_irqsave(&ctrl->lock, flags);
+ spin_lock_irqsave(&rport->lock, flags);
- list_add_tail(&lsop->lsreq_list, &ctrl->ls_req_list);
+ list_add_tail(&lsop->lsreq_list, &rport->ls_req_list);
lsop->req_queued = true;
- spin_unlock_irqrestore(&ctrl->lock, flags);
+ spin_unlock_irqrestore(&rport->lock, flags);
- ret = ctrl->lport->ops->ls_req(&ctrl->lport->localport,
- &ctrl->rport->remoteport, lsreq);
+ ret = rport->lport->ops->ls_req(&rport->lport->localport,
+ &rport->remoteport, lsreq);
if (ret)
- lsop->ls_error = ret;
+ goto out_unlink;
+
+ return 0;
+
+out_unlink:
+ lsop->ls_error = ret;
+ spin_lock_irqsave(&rport->lock, flags);
+ lsop->req_queued = false;
+ list_del(&lsop->lsreq_list);
+ spin_unlock_irqrestore(&rport->lock, flags);
+ fc_dma_unmap_single(rport->dev, lsreq->rqstdma,
+ (lsreq->rqstlen + lsreq->rsplen),
+ DMA_BIDIRECTIONAL);
+out_putrport:
+ nvme_fc_rport_put(rport);
return ret;
}
@@ -705,15 +757,15 @@ nvme_fc_send_ls_req_done(struct nvmefc_ls_req *lsreq, int status)
}
static int
-nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
+nvme_fc_send_ls_req(struct nvme_fc_rport *rport, struct nvmefc_ls_req_op *lsop)
{
struct nvmefc_ls_req *lsreq = &lsop->ls_req;
struct fcnvme_ls_rjt *rjt = lsreq->rspaddr;
int ret;
- ret = __nvme_fc_send_ls_req(ctrl, lsop, nvme_fc_send_ls_req_done);
+ ret = __nvme_fc_send_ls_req(rport, lsop, nvme_fc_send_ls_req_done);
- if (!ret)
+ if (!ret) {
/*
* No timeout/not interruptible as we need the struct
* to exist until the lldd calls us back. Thus mandate
@@ -722,14 +774,14 @@ nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
*/
wait_for_completion(&lsop->ls_done);
- __nvme_fc_finish_ls_req(ctrl, lsop);
+ __nvme_fc_finish_ls_req(lsop);
- if (ret) {
- dev_err(ctrl->dev,
- "ls request command failed (%d).\n", ret);
- return ret;
+ ret = lsop->ls_error;
}
+ if (ret)
+ return ret;
+
/* ACC or RJT payload ? */
if (rjt->w0.ls_cmd == FCNVME_LS_RJT)
return -ENXIO;
@@ -737,19 +789,14 @@ nvme_fc_send_ls_req(struct nvme_fc_ctrl *ctrl, struct nvmefc_ls_req_op *lsop)
return 0;
}
-static void
-nvme_fc_send_ls_req_async(struct nvme_fc_ctrl *ctrl,
+static int
+nvme_fc_send_ls_req_async(struct nvme_fc_rport *rport,
struct nvmefc_ls_req_op *lsop,
void (*done)(struct nvmefc_ls_req *req, int status))
{
- int ret;
-
- ret = __nvme_fc_send_ls_req(ctrl, lsop, done);
-
/* don't wait for completion */
- if (ret)
- done(&lsop->ls_req, ret);
+ return __nvme_fc_send_ls_req(rport, lsop, done);
}
/* Validation Error indexes into the string table below */
@@ -839,7 +886,7 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
lsreq->rsplen = sizeof(*assoc_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- ret = nvme_fc_send_ls_req(ctrl, lsop);
+ ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
if (ret)
goto out_free_buffer;
@@ -848,11 +895,12 @@ nvme_fc_connect_admin_queue(struct nvme_fc_ctrl *ctrl,
/* validate the ACC response */
if (assoc_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
fcret = VERR_LSACC;
- if (assoc_acc->hdr.desc_list_len !=
+ else if (assoc_acc->hdr.desc_list_len !=
fcnvme_lsdesc_len(
sizeof(struct fcnvme_ls_cr_assoc_acc)))
fcret = VERR_CR_ASSOC_ACC_LEN;
- if (assoc_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+ else if (assoc_acc->hdr.rqst.desc_tag !=
+ cpu_to_be32(FCNVME_LSDESC_RQST))
fcret = VERR_LSDESC_RQST;
else if (assoc_acc->hdr.rqst.desc_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
@@ -946,7 +994,7 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
lsreq->rsplen = sizeof(*conn_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- ret = nvme_fc_send_ls_req(ctrl, lsop);
+ ret = nvme_fc_send_ls_req(ctrl->rport, lsop);
if (ret)
goto out_free_buffer;
@@ -955,10 +1003,10 @@ nvme_fc_connect_queue(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
/* validate the ACC response */
if (conn_acc->hdr.w0.ls_cmd != FCNVME_LS_ACC)
fcret = VERR_LSACC;
- if (conn_acc->hdr.desc_list_len !=
+ else if (conn_acc->hdr.desc_list_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_ls_cr_conn_acc)))
fcret = VERR_CR_CONN_ACC_LEN;
- if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
+ else if (conn_acc->hdr.rqst.desc_tag != cpu_to_be32(FCNVME_LSDESC_RQST))
fcret = VERR_LSDESC_RQST;
else if (conn_acc->hdr.rqst.desc_len !=
fcnvme_lsdesc_len(sizeof(struct fcnvme_lsdesc_rqst)))
@@ -997,14 +1045,8 @@ static void
nvme_fc_disconnect_assoc_done(struct nvmefc_ls_req *lsreq, int status)
{
struct nvmefc_ls_req_op *lsop = ls_req_to_lsop(lsreq);
- struct nvme_fc_ctrl *ctrl = lsop->ctrl;
- __nvme_fc_finish_ls_req(ctrl, lsop);
-
- if (status)
- dev_err(ctrl->dev,
- "disconnect assoc ls request command failed (%d).\n",
- status);
+ __nvme_fc_finish_ls_req(lsop);
/* fc-nvme iniator doesn't care about success or failure of cmd */
@@ -1035,6 +1077,7 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
struct fcnvme_ls_disconnect_acc *discon_acc;
struct nvmefc_ls_req_op *lsop;
struct nvmefc_ls_req *lsreq;
+ int ret;
lsop = kzalloc((sizeof(*lsop) +
ctrl->lport->ops->lsrqst_priv_sz +
@@ -1077,7 +1120,10 @@ nvme_fc_xmt_disconnect_assoc(struct nvme_fc_ctrl *ctrl)
lsreq->rsplen = sizeof(*discon_acc);
lsreq->timeout = NVME_FC_CONNECT_TIMEOUT_SEC;
- nvme_fc_send_ls_req_async(ctrl, lsop, nvme_fc_disconnect_assoc_done);
+ ret = nvme_fc_send_ls_req_async(ctrl->rport, lsop,
+ nvme_fc_disconnect_assoc_done);
+ if (ret)
+ kfree(lsop);
/* only meaningful part to terminating the association */
ctrl->association_id = 0;
@@ -1146,7 +1192,8 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
struct nvme_fc_ctrl *ctrl = op->ctrl;
struct nvme_fc_queue *queue = op->queue;
struct nvme_completion *cqe = &op->rsp_iu.cqe;
- u16 status;
+ __le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
+ union nvme_result result;
/*
* WARNING:
@@ -1181,9 +1228,9 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
sizeof(op->rsp_iu), DMA_FROM_DEVICE);
if (atomic_read(&op->state) == FCPOP_STATE_ABORTED)
- status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
- else
- status = freq->status;
+ status = cpu_to_le16((NVME_SC_ABORT_REQ | NVME_SC_DNR) << 1);
+ else if (freq->status)
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
/*
* For the linux implementation, if we have an unsuccesful
@@ -1211,10 +1258,10 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
*/
if (freq->transferred_length !=
be32_to_cpu(op->cmd_iu.data_len)) {
- status = -EIO;
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
- op->nreq.result.u64 = 0;
+ result.u64 = 0;
break;
case sizeof(struct nvme_fc_ersp_iu):
@@ -1226,28 +1273,28 @@ nvme_fc_fcpio_done(struct nvmefc_fcp_req *req)
(freq->rcv_rsplen / 4) ||
be32_to_cpu(op->rsp_iu.xfrd_len) !=
freq->transferred_length ||
+ op->rsp_iu.status_code ||
op->rqno != le16_to_cpu(cqe->command_id))) {
- status = -EIO;
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
- op->nreq.result = cqe->result;
- status = le16_to_cpu(cqe->status) >> 1;
+ result = cqe->result;
+ status = cqe->status;
break;
default:
- status = -EIO;
+ status = cpu_to_le16(NVME_SC_FC_TRANSPORT_ERROR << 1);
goto done;
}
done:
if (!queue->qnum && op->rqno >= AEN_CMDID_BASE) {
- nvme_complete_async_event(&queue->ctrl->ctrl, status,
- &op->nreq.result);
+ nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
nvme_fc_ctrl_put(ctrl);
return;
}
- blk_mq_complete_request(rq, status);
+ nvme_end_request(rq, status, result);
}
static int
@@ -1761,7 +1808,7 @@ nvme_fc_start_fcp_op(struct nvme_fc_ctrl *ctrl, struct nvme_fc_queue *queue,
op->fcp_req.io_dir = io_dir;
op->fcp_req.transferred_length = 0;
op->fcp_req.rcv_rsplen = 0;
- op->fcp_req.status = 0;
+ op->fcp_req.status = NVME_SC_SUCCESS;
op->fcp_req.sqid = cpu_to_le16(queue->qnum);
/*
@@ -1923,32 +1970,18 @@ nvme_fc_complete_rq(struct request *rq)
{
struct nvme_fc_fcp_op *op = blk_mq_rq_to_pdu(rq);
struct nvme_fc_ctrl *ctrl = op->ctrl;
- int error = 0, state;
+ int state;
state = atomic_xchg(&op->state, FCPOP_STATE_IDLE);
nvme_cleanup_cmd(rq);
-
nvme_fc_unmap_data(ctrl, rq, op);
-
- if (unlikely(rq->errors)) {
- if (nvme_req_needs_retry(rq, rq->errors)) {
- nvme_requeue_req(rq);
- return;
- }
-
- if (blk_rq_is_passthrough(rq))
- error = rq->errors;
- else
- error = nvme_error_status(rq->errors);
- }
-
+ nvme_complete_rq(rq);
nvme_fc_ctrl_put(ctrl);
- blk_mq_end_request(rq, error);
}
-static struct blk_mq_ops nvme_fc_mq_ops = {
+static const struct blk_mq_ops nvme_fc_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
.complete = nvme_fc_complete_rq,
.init_request = nvme_fc_init_request,
@@ -1959,7 +1992,7 @@ static struct blk_mq_ops nvme_fc_mq_ops = {
.timeout = nvme_fc_timeout,
};
-static struct blk_mq_ops nvme_fc_admin_mq_ops = {
+static const struct blk_mq_ops nvme_fc_admin_mq_ops = {
.queue_rq = nvme_fc_queue_rq,
.complete = nvme_fc_complete_rq,
.init_request = nvme_fc_init_admin_request,
@@ -2314,7 +2347,6 @@ __nvme_fc_create_ctrl(struct device *dev, struct nvmf_ctrl_options *opts,
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->ctrl_list);
- INIT_LIST_HEAD(&ctrl->ls_req_list);
ctrl->lport = lport;
ctrl->rport = rport;
ctrl->dev = lport->dev;
@@ -2546,11 +2578,20 @@ static struct nvmf_transport_ops nvme_fc_transport = {
static int __init nvme_fc_init_module(void)
{
+ int ret;
+
nvme_fc_wq = create_workqueue("nvme_fc_wq");
if (!nvme_fc_wq)
return -ENOMEM;
- return nvmf_register_transport(&nvme_fc_transport);
+ ret = nvmf_register_transport(&nvme_fc_transport);
+ if (ret)
+ goto err;
+
+ return 0;
+err:
+ destroy_workqueue(nvme_fc_wq);
+ return ret;
}
static void __exit nvme_fc_exit_module(void)
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 21cac8523bd8..de61a4a03d78 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -241,9 +241,9 @@ static inline void _nvme_nvm_check_size(void)
BUILD_BUG_ON(sizeof(struct nvme_nvm_l2ptbl) != 64);
BUILD_BUG_ON(sizeof(struct nvme_nvm_erase_blk) != 64);
BUILD_BUG_ON(sizeof(struct nvme_nvm_id_group) != 960);
- BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 128);
+ BUILD_BUG_ON(sizeof(struct nvme_nvm_addr_format) != 16);
BUILD_BUG_ON(sizeof(struct nvme_nvm_id) != 4096);
- BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 512);
+ BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64);
}
static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
@@ -324,7 +324,7 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
- sizeof(struct nvme_nvm_addr_format));
+ sizeof(struct nvm_addr_format));
ret = init_grps(nvm_id, nvme_nvm_id);
out:
@@ -484,7 +484,7 @@ static void nvme_nvm_end_io(struct request *rq, int error)
struct nvm_rq *rqd = rq->end_io_data;
rqd->ppa_status = nvme_req(rq)->result.u64;
- rqd->error = error;
+ rqd->error = nvme_req(rq)->status;
nvm_end_io(rqd);
kfree(nvme_req(rq)->cmd);
@@ -510,12 +510,12 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
}
rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
- rq->ioprio = bio_prio(bio);
- if (bio_has_data(bio))
- rq->nr_phys_segments = bio_phys_segments(q, bio);
-
- rq->__data_len = bio->bi_iter.bi_size;
- rq->bio = rq->biotail = bio;
+ if (bio) {
+ blk_init_request_from_bio(rq, bio);
+ } else {
+ rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
+ rq->__data_len = 0;
+ }
nvme_nvm_rqtocmd(rq, rqd, ns, cmd);
@@ -526,21 +526,6 @@ static int nvme_nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd)
return 0;
}
-static int nvme_nvm_erase_block(struct nvm_dev *dev, struct nvm_rq *rqd)
-{
- struct request_queue *q = dev->q;
- struct nvme_ns *ns = q->queuedata;
- struct nvme_nvm_command c = {};
-
- c.erase.opcode = NVM_OP_ERASE;
- c.erase.nsid = cpu_to_le32(ns->ns_id);
- c.erase.spba = cpu_to_le64(rqd->ppa_addr.ppa);
- c.erase.length = cpu_to_le16(rqd->nr_ppas - 1);
- c.erase.control = cpu_to_le16(rqd->flags);
-
- return nvme_submit_sync_cmd(q, (struct nvme_command *)&c, NULL, 0);
-}
-
static void *nvme_nvm_create_dma_pool(struct nvm_dev *nvmdev, char *name)
{
struct nvme_ns *ns = nvmdev->q->queuedata;
@@ -576,7 +561,6 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
.set_bb_tbl = nvme_nvm_set_bb_tbl,
.submit_io = nvme_nvm_submit_io,
- .erase_block = nvme_nvm_erase_block,
.create_dma_pool = nvme_nvm_create_dma_pool,
.destroy_dma_pool = nvme_nvm_destroy_dma_pool,
@@ -611,7 +595,7 @@ static int nvme_nvm_submit_user_cmd(struct request_queue *q,
__le64 *metadata = NULL;
dma_addr_t metadata_dma;
DECLARE_COMPLETION_ONSTACK(wait);
- int ret;
+ int ret = 0;
rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
NVME_QID_ANY);
@@ -681,9 +665,12 @@ submit:
wait_for_completion_io(&wait);
- ret = nvme_error_status(rq->errors);
+ if (nvme_req(rq)->flags & NVME_REQ_CANCELLED)
+ ret = -EINTR;
+ else if (nvme_req(rq)->status & 0x7ff)
+ ret = -EIO;
if (result)
- *result = rq->errors & 0x7ff;
+ *result = nvme_req(rq)->status & 0x7ff;
if (status)
*status = le64_to_cpu(nvme_req(rq)->result.u64);
@@ -766,7 +753,7 @@ static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
/* cdw11-12 */
c.ph_rw.length = cpu_to_le16(vcmd.nppas);
- c.ph_rw.control = cpu_to_le32(vcmd.control);
+ c.ph_rw.control = cpu_to_le16(vcmd.control);
c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
@@ -809,6 +796,8 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
struct request_queue *q = ns->queue;
struct nvm_dev *dev;
+ _nvme_nvm_check_size();
+
dev = nvm_alloc_dev(node);
if (!dev)
return -ENOMEM;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index ab2d6ec7eb5c..29c708ca9621 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -21,16 +21,6 @@
#include <linux/lightnvm.h>
#include <linux/sed-opal.h>
-enum {
- /*
- * Driver internal status code for commands that were cancelled due
- * to timeouts or controller shutdown. The value is negative so
- * that it a) doesn't overlap with the unsigned hardware error codes,
- * and b) can easily be tested for.
- */
- NVME_SC_CANCELLED = -EINTR,
-};
-
extern unsigned char nvme_io_timeout;
#define NVME_IO_TIMEOUT (nvme_io_timeout * HZ)
@@ -43,8 +33,6 @@ extern unsigned char shutdown_timeout;
#define NVME_DEFAULT_KATO 5
#define NVME_KATO_GRACE 10
-extern unsigned int nvme_max_retries;
-
enum {
NVME_NS_LBA = 0,
NVME_NS_LIGHTNVM = 1,
@@ -68,10 +56,10 @@ enum nvme_quirks {
NVME_QUIRK_IDENTIFY_CNS = (1 << 1),
/*
- * The controller deterministically returns O's on reads to discarded
- * logical blocks.
+ * The controller deterministically returns O's on reads to
+ * logical blocks that deallocate was called on.
*/
- NVME_QUIRK_DISCARD_ZEROES = (1 << 2),
+ NVME_QUIRK_DEALLOCATE_ZEROES = (1 << 2),
/*
* The controller needs a delay before starts checking the device
@@ -97,6 +85,13 @@ enum nvme_quirks {
struct nvme_request {
struct nvme_command *cmd;
union nvme_result result;
+ u8 retries;
+ u8 flags;
+ u16 status;
+};
+
+enum {
+ NVME_REQ_CANCELLED = (1 << 0),
};
static inline struct nvme_request *nvme_req(struct request *req)
@@ -254,25 +249,17 @@ static inline void nvme_cleanup_cmd(struct request *req)
}
}
-static inline int nvme_error_status(u16 status)
+static inline void nvme_end_request(struct request *req, __le16 status,
+ union nvme_result result)
{
- switch (status & 0x7ff) {
- case NVME_SC_SUCCESS:
- return 0;
- case NVME_SC_CAP_EXCEEDED:
- return -ENOSPC;
- default:
- return -EIO;
- }
-}
+ struct nvme_request *rq = nvme_req(req);
-static inline bool nvme_req_needs_retry(struct request *req, u16 status)
-{
- return !(status & NVME_SC_DNR || blk_noretry_request(req)) &&
- (jiffies - req->start_time) < req->timeout &&
- req->retries < nvme_max_retries;
+ rq->status = le16_to_cpu(status) >> 1;
+ rq->result = result;
+ blk_mq_complete_request(req);
}
+void nvme_complete_rq(struct request *req);
void nvme_cancel_request(struct request *req, void *data, bool reserved);
bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
enum nvme_ctrl_state new_state);
@@ -307,7 +294,6 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
#define NVME_QID_ANY -1
struct request *nvme_alloc_request(struct request_queue *q,
struct nvme_command *cmd, unsigned int flags, int qid);
-void nvme_requeue_req(struct request *req);
int nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
struct nvme_command *cmd);
int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 5d309535abbd..c8541c3dcd19 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -104,8 +104,22 @@ struct nvme_dev {
u32 cmbloc;
struct nvme_ctrl ctrl;
struct completion ioq_wait;
+ u32 *dbbuf_dbs;
+ dma_addr_t dbbuf_dbs_dma_addr;
+ u32 *dbbuf_eis;
+ dma_addr_t dbbuf_eis_dma_addr;
};
+static inline unsigned int sq_idx(unsigned int qid, u32 stride)
+{
+ return qid * 2 * stride;
+}
+
+static inline unsigned int cq_idx(unsigned int qid, u32 stride)
+{
+ return (qid * 2 + 1) * stride;
+}
+
static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl)
{
return container_of(ctrl, struct nvme_dev, ctrl);
@@ -134,6 +148,10 @@ struct nvme_queue {
u16 qid;
u8 cq_phase;
u8 cqe_seen;
+ u32 *dbbuf_sq_db;
+ u32 *dbbuf_cq_db;
+ u32 *dbbuf_sq_ei;
+ u32 *dbbuf_cq_ei;
};
/*
@@ -172,6 +190,112 @@ static inline void _nvme_check_size(void)
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);
+ BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64);
+}
+
+static inline unsigned int nvme_dbbuf_size(u32 stride)
+{
+ return ((num_possible_cpus() + 1) * 8 * stride);
+}
+
+static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev)
+{
+ unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+ if (dev->dbbuf_dbs)
+ return 0;
+
+ dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size,
+ &dev->dbbuf_dbs_dma_addr,
+ GFP_KERNEL);
+ if (!dev->dbbuf_dbs)
+ return -ENOMEM;
+ dev->dbbuf_eis = dma_alloc_coherent(dev->dev, mem_size,
+ &dev->dbbuf_eis_dma_addr,
+ GFP_KERNEL);
+ if (!dev->dbbuf_eis) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+ dev->dbbuf_dbs = NULL;
+ return -ENOMEM;
+ }
+
+ return 0;
+}
+
+static void nvme_dbbuf_dma_free(struct nvme_dev *dev)
+{
+ unsigned int mem_size = nvme_dbbuf_size(dev->db_stride);
+
+ if (dev->dbbuf_dbs) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_dbs, dev->dbbuf_dbs_dma_addr);
+ dev->dbbuf_dbs = NULL;
+ }
+ if (dev->dbbuf_eis) {
+ dma_free_coherent(dev->dev, mem_size,
+ dev->dbbuf_eis, dev->dbbuf_eis_dma_addr);
+ dev->dbbuf_eis = NULL;
+ }
+}
+
+static void nvme_dbbuf_init(struct nvme_dev *dev,
+ struct nvme_queue *nvmeq, int qid)
+{
+ if (!dev->dbbuf_dbs || !qid)
+ return;
+
+ nvmeq->dbbuf_sq_db = &dev->dbbuf_dbs[sq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_cq_db = &dev->dbbuf_dbs[cq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_sq_ei = &dev->dbbuf_eis[sq_idx(qid, dev->db_stride)];
+ nvmeq->dbbuf_cq_ei = &dev->dbbuf_eis[cq_idx(qid, dev->db_stride)];
+}
+
+static void nvme_dbbuf_set(struct nvme_dev *dev)
+{
+ struct nvme_command c;
+
+ if (!dev->dbbuf_dbs)
+ return;
+
+ memset(&c, 0, sizeof(c));
+ c.dbbuf.opcode = nvme_admin_dbbuf;
+ c.dbbuf.prp1 = cpu_to_le64(dev->dbbuf_dbs_dma_addr);
+ c.dbbuf.prp2 = cpu_to_le64(dev->dbbuf_eis_dma_addr);
+
+ if (nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0)) {
+ dev_warn(dev->dev, "unable to set dbbuf\n");
+ /* Free memory and continue on */
+ nvme_dbbuf_dma_free(dev);
+ }
+}
+
+static inline int nvme_dbbuf_need_event(u16 event_idx, u16 new_idx, u16 old)
+{
+ return (u16)(new_idx - event_idx - 1) < (u16)(new_idx - old);
+}
+
+/* Update dbbuf and return true if an MMIO is required */
+static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db,
+ volatile u32 *dbbuf_ei)
+{
+ if (dbbuf_db) {
+ u16 old_value;
+
+ /*
+ * Ensure that the queue is written before updating
+ * the doorbell in memory
+ */
+ wmb();
+
+ old_value = *dbbuf_db;
+ *dbbuf_db = value;
+
+ if (!nvme_dbbuf_need_event(*dbbuf_ei, value, old_value))
+ return false;
+ }
+
+ return true;
}
/*
@@ -298,7 +422,9 @@ static void __nvme_submit_cmd(struct nvme_queue *nvmeq,
if (++tail == nvmeq->q_depth)
tail = 0;
- writel(tail, nvmeq->q_db);
+ if (nvme_dbbuf_update_and_check_event(tail, nvmeq->dbbuf_sq_db,
+ nvmeq->dbbuf_sq_ei))
+ writel(tail, nvmeq->q_db);
nvmeq->sq_tail = tail;
}
@@ -327,10 +453,6 @@ static int nvme_init_iod(struct request *rq, struct nvme_dev *dev)
iod->nents = 0;
iod->length = size;
- if (!(rq->rq_flags & RQF_DONTPREP)) {
- rq->retries = 0;
- rq->rq_flags |= RQF_DONTPREP;
- }
return BLK_MQ_RQ_QUEUE_OK;
}
@@ -629,34 +751,12 @@ out_free_cmd:
return ret;
}
-static void nvme_complete_rq(struct request *req)
+static void nvme_pci_complete_rq(struct request *req)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
- struct nvme_dev *dev = iod->nvmeq->dev;
- int error = 0;
-
- nvme_unmap_data(dev, req);
-
- if (unlikely(req->errors)) {
- if (nvme_req_needs_retry(req, req->errors)) {
- req->retries++;
- nvme_requeue_req(req);
- return;
- }
-
- if (blk_rq_is_passthrough(req))
- error = req->errors;
- else
- error = nvme_error_status(req->errors);
- }
-
- if (unlikely(iod->aborted)) {
- dev_warn(dev->ctrl.device,
- "completing aborted command with status: %04x\n",
- req->errors);
- }
- blk_mq_end_request(req, error);
+ nvme_unmap_data(iod->nvmeq->dev, req);
+ nvme_complete_rq(req);
}
/* We read the CQE phase first to check if the rest of the entry is valid */
@@ -706,15 +806,16 @@ static void __nvme_process_cq(struct nvme_queue *nvmeq, unsigned int *tag)
}
req = blk_mq_tag_to_rq(*nvmeq->tags, cqe.command_id);
- nvme_req(req)->result = cqe.result;
- blk_mq_complete_request(req, le16_to_cpu(cqe.status) >> 1);
+ nvme_end_request(req, cqe.status, cqe.result);
}
if (head == nvmeq->cq_head && phase == nvmeq->cq_phase)
return;
if (likely(nvmeq->cq_vector >= 0))
- writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
+ if (nvme_dbbuf_update_and_check_event(head, nvmeq->dbbuf_cq_db,
+ nvmeq->dbbuf_cq_ei))
+ writel(head, nvmeq->q_db + nvmeq->dev->db_stride);
nvmeq->cq_head = head;
nvmeq->cq_phase = phase;
@@ -746,10 +847,8 @@ static irqreturn_t nvme_irq_check(int irq, void *data)
return IRQ_NONE;
}
-static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag)
{
- struct nvme_queue *nvmeq = hctx->driver_data;
-
if (nvme_cqe_valid(nvmeq, nvmeq->cq_head, nvmeq->cq_phase)) {
spin_lock_irq(&nvmeq->q_lock);
__nvme_process_cq(nvmeq, &tag);
@@ -762,6 +861,13 @@ static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
return 0;
}
+static int nvme_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
+{
+ struct nvme_queue *nvmeq = hctx->driver_data;
+
+ return __nvme_poll(nvmeq, tag);
+}
+
static void nvme_pci_submit_async_event(struct nvme_ctrl *ctrl, int aer_idx)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
@@ -813,7 +919,7 @@ 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;
+ int flags = NVME_QUEUE_PHYS_CONTIG;
/*
* Note: we (ab)use the fact the the prp fields survive if no data
@@ -844,9 +950,9 @@ static void abort_endio(struct request *req, int error)
{
struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
struct nvme_queue *nvmeq = iod->nvmeq;
- u16 status = req->errors;
- dev_warn(nvmeq->dev->ctrl.device, "Abort status: 0x%x", status);
+ dev_warn(nvmeq->dev->ctrl.device,
+ "Abort status: 0x%x", nvme_req(req)->status);
atomic_inc(&nvmeq->dev->ctrl.abort_limit);
blk_mq_free_request(req);
}
@@ -860,6 +966,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
struct nvme_command cmd;
/*
+ * Did we miss an interrupt?
+ */
+ if (__nvme_poll(nvmeq, req->tag)) {
+ dev_warn(dev->ctrl.device,
+ "I/O %d QID %d timeout, completion polled\n",
+ req->tag, nvmeq->qid);
+ return BLK_EH_HANDLED;
+ }
+
+ /*
* Shutdown immediately if controller times out while starting. The
* reset work will see the pci device disabled when it gets the forced
* cancellation error. All outstanding requests are completed on
@@ -870,7 +986,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
"I/O %d QID %d timeout, disable controller\n",
req->tag, nvmeq->qid);
nvme_dev_disable(dev, false);
- req->errors = NVME_SC_CANCELLED;
+ nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_HANDLED;
}
@@ -890,7 +1006,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
* Mark the request as handled, since the inline shutdown
* forces all outstanding requests to complete.
*/
- req->errors = NVME_SC_CANCELLED;
+ nvme_req(req)->flags |= NVME_REQ_CANCELLED;
return BLK_EH_HANDLED;
}
@@ -1098,6 +1214,7 @@ static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid)
nvmeq->cq_phase = 1;
nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride];
memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth));
+ nvme_dbbuf_init(dev, nvmeq, qid);
dev->online_queues++;
spin_unlock_irq(&nvmeq->q_lock);
}
@@ -1130,18 +1247,18 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid)
return result;
}
-static struct blk_mq_ops nvme_mq_admin_ops = {
+static const struct blk_mq_ops nvme_mq_admin_ops = {
.queue_rq = nvme_queue_rq,
- .complete = nvme_complete_rq,
+ .complete = nvme_pci_complete_rq,
.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 = {
+static const struct blk_mq_ops nvme_mq_ops = {
.queue_rq = nvme_queue_rq,
- .complete = nvme_complete_rq,
+ .complete = nvme_pci_complete_rq,
.init_hctx = nvme_init_hctx,
.init_request = nvme_init_request,
.map_queues = nvme_pci_map_queues,
@@ -1570,6 +1687,8 @@ static int nvme_dev_add(struct nvme_dev *dev)
if (blk_mq_alloc_tag_set(&dev->tagset))
return 0;
dev->ctrl.tagset = &dev->tagset;
+
+ nvme_dbbuf_set(dev);
} else {
blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
@@ -1756,6 +1875,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
{
struct nvme_dev *dev = to_nvme_dev(ctrl);
+ nvme_dbbuf_dma_free(dev);
put_device(dev->dev);
if (dev->tagset.tags)
blk_mq_free_tag_set(&dev->tagset);
@@ -1823,6 +1943,13 @@ static void nvme_reset_work(struct work_struct *work)
dev->ctrl.opal_dev = NULL;
}
+ if (dev->ctrl.oacs & NVME_CTRL_OACS_DBBUF_SUPP) {
+ result = nvme_dbbuf_dma_alloc(dev);
+ if (result)
+ dev_warn(dev->dev,
+ "unable to allocate dma for dbbuf\n");
+ }
+
result = nvme_setup_io_queues(dev);
if (result)
goto out;
@@ -2159,13 +2286,13 @@ static const struct pci_error_handlers nvme_err_handler = {
static const struct pci_device_id nvme_id_table[] = {
{ PCI_VDEVICE(INTEL, 0x0953),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a53),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x0a54),
.driver_data = NVME_QUIRK_STRIPE_SIZE |
- NVME_QUIRK_DISCARD_ZEROES, },
+ NVME_QUIRK_DEALLOCATE_ZEROES, },
{ PCI_VDEVICE(INTEL, 0x5845), /* Qemu emulated controller */
.driver_data = NVME_QUIRK_IDENTIFY_CNS, },
{ PCI_DEVICE(0x1c58, 0x0003), /* HGST adapter */
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 16f84eb0b95e..29cf88ac3f61 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -34,7 +34,7 @@
#include "fabrics.h"
-#define NVME_RDMA_CONNECT_TIMEOUT_MS 1000 /* 1 second */
+#define NVME_RDMA_CONNECT_TIMEOUT_MS 3000 /* 3 second */
#define NVME_RDMA_MAX_SEGMENT_SIZE 0xffffff /* 24-bit SGL field */
@@ -118,7 +118,6 @@ struct nvme_rdma_ctrl {
struct nvme_rdma_qe async_event_sqe;
- int reconnect_delay;
struct delayed_work reconnect_work;
struct list_head list;
@@ -129,14 +128,8 @@ struct nvme_rdma_ctrl {
u64 cap;
u32 max_fr_pages;
- union {
- struct sockaddr addr;
- struct sockaddr_in addr_in;
- };
- union {
- struct sockaddr src_addr;
- struct sockaddr_in src_addr_in;
- };
+ struct sockaddr_storage addr;
+ struct sockaddr_storage src_addr;
struct nvme_ctrl ctrl;
};
@@ -569,11 +562,12 @@ static int nvme_rdma_init_queue(struct nvme_rdma_ctrl *ctrl,
return PTR_ERR(queue->cm_id);
}
- queue->cm_error = -ETIMEDOUT;
if (ctrl->ctrl.opts->mask & NVMF_OPT_HOST_TRADDR)
- src_addr = &ctrl->src_addr;
+ src_addr = (struct sockaddr *)&ctrl->src_addr;
- ret = rdma_resolve_addr(queue->cm_id, src_addr, &ctrl->addr,
+ queue->cm_error = -ETIMEDOUT;
+ ret = rdma_resolve_addr(queue->cm_id, src_addr,
+ (struct sockaddr *)&ctrl->addr,
NVME_RDMA_CONNECT_TIMEOUT_MS);
if (ret) {
dev_info(ctrl->ctrl.device,
@@ -712,6 +706,26 @@ free_ctrl:
kfree(ctrl);
}
+static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
+{
+ /* If we are resetting/deleting then do nothing */
+ if (ctrl->ctrl.state != NVME_CTRL_RECONNECTING) {
+ WARN_ON_ONCE(ctrl->ctrl.state == NVME_CTRL_NEW ||
+ ctrl->ctrl.state == NVME_CTRL_LIVE);
+ return;
+ }
+
+ if (nvmf_should_reconnect(&ctrl->ctrl)) {
+ dev_info(ctrl->ctrl.device, "Reconnecting in %d seconds...\n",
+ ctrl->ctrl.opts->reconnect_delay);
+ queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
+ ctrl->ctrl.opts->reconnect_delay * HZ);
+ } else {
+ dev_info(ctrl->ctrl.device, "Removing controller...\n");
+ queue_work(nvme_rdma_wq, &ctrl->delete_work);
+ }
+}
+
static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
{
struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
@@ -719,6 +733,8 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
bool changed;
int ret;
+ ++ctrl->ctrl.opts->nr_reconnects;
+
if (ctrl->queue_count > 1) {
nvme_rdma_free_io_queues(ctrl);
@@ -763,6 +779,7 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
+ ctrl->ctrl.opts->nr_reconnects = 0;
if (ctrl->queue_count > 1) {
nvme_start_queues(&ctrl->ctrl);
@@ -777,13 +794,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
stop_admin_q:
blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
requeue:
- /* Make sure we are not resetting/deleting */
- if (ctrl->ctrl.state == NVME_CTRL_RECONNECTING) {
- dev_info(ctrl->ctrl.device,
- "Failed reconnect attempt, requeueing...\n");
- queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
- ctrl->reconnect_delay * HZ);
- }
+ dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
+ ctrl->ctrl.opts->nr_reconnects);
+ nvme_rdma_reconnect_or_remove(ctrl);
}
static void nvme_rdma_error_recovery_work(struct work_struct *work)
@@ -810,11 +823,7 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
nvme_cancel_request, &ctrl->ctrl);
- dev_info(ctrl->ctrl.device, "reconnecting in %d seconds\n",
- ctrl->reconnect_delay);
-
- queue_delayed_work(nvme_rdma_wq, &ctrl->reconnect_work,
- ctrl->reconnect_delay * HZ);
+ nvme_rdma_reconnect_or_remove(ctrl);
}
static void nvme_rdma_error_recovery(struct nvme_rdma_ctrl *ctrl)
@@ -1169,8 +1178,7 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue,
wc->ex.invalidate_rkey == req->mr->rkey)
req->mr->need_inval = false;
- req->req.result = cqe->result;
- blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+ nvme_end_request(rq, cqe->status, cqe->result);
return ret;
}
@@ -1407,7 +1415,7 @@ nvme_rdma_timeout(struct request *rq, bool reserved)
nvme_rdma_error_recovery(req->queue->ctrl);
/* fail with DNR on cmd timeout */
- rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
return BLK_EH_HANDLED;
}
@@ -1509,27 +1517,12 @@ static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag)
static void nvme_rdma_complete_rq(struct request *rq)
{
struct nvme_rdma_request *req = blk_mq_rq_to_pdu(rq);
- struct nvme_rdma_queue *queue = req->queue;
- int error = 0;
-
- nvme_rdma_unmap_data(queue, rq);
- if (unlikely(rq->errors)) {
- if (nvme_req_needs_retry(rq, rq->errors)) {
- nvme_requeue_req(rq);
- return;
- }
-
- if (blk_rq_is_passthrough(rq))
- error = rq->errors;
- else
- error = nvme_error_status(rq->errors);
- }
-
- blk_mq_end_request(rq, error);
+ nvme_rdma_unmap_data(req->queue, rq);
+ nvme_complete_rq(rq);
}
-static struct blk_mq_ops nvme_rdma_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
.init_request = nvme_rdma_init_request,
@@ -1540,7 +1533,7 @@ static struct blk_mq_ops nvme_rdma_mq_ops = {
.timeout = nvme_rdma_timeout,
};
-static struct blk_mq_ops nvme_rdma_admin_mq_ops = {
+static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
.queue_rq = nvme_rdma_queue_rq,
.complete = nvme_rdma_complete_rq,
.init_request = nvme_rdma_init_admin_request,
@@ -1857,27 +1850,13 @@ out_free_io_queues:
return ret;
}
-static int nvme_rdma_parse_ipaddr(struct sockaddr_in *in_addr, char *p)
-{
- u8 *addr = (u8 *)&in_addr->sin_addr.s_addr;
- size_t buflen = strlen(p);
-
- /* XXX: handle IPv6 addresses */
-
- if (buflen > INET_ADDRSTRLEN)
- return -EINVAL;
- if (in4_pton(p, buflen, addr, '\0', NULL) == 0)
- return -EINVAL;
- in_addr->sin_family = AF_INET;
- return 0;
-}
-
static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
struct nvmf_ctrl_options *opts)
{
struct nvme_rdma_ctrl *ctrl;
int ret;
bool changed;
+ char *port;
ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
if (!ctrl)
@@ -1885,40 +1864,33 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
ctrl->ctrl.opts = opts;
INIT_LIST_HEAD(&ctrl->list);
- ret = nvme_rdma_parse_ipaddr(&ctrl->addr_in, opts->traddr);
+ if (opts->mask & NVMF_OPT_TRSVCID)
+ port = opts->trsvcid;
+ else
+ port = __stringify(NVME_RDMA_IP_PORT);
+
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+ opts->traddr, port, &ctrl->addr);
if (ret) {
- pr_err("malformed IP address passed: %s\n", opts->traddr);
+ pr_err("malformed address passed: %s:%s\n", opts->traddr, port);
goto out_free_ctrl;
}
if (opts->mask & NVMF_OPT_HOST_TRADDR) {
- ret = nvme_rdma_parse_ipaddr(&ctrl->src_addr_in,
- opts->host_traddr);
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC,
+ opts->host_traddr, NULL, &ctrl->src_addr);
if (ret) {
- pr_err("malformed src IP address passed: %s\n",
+ pr_err("malformed src address passed: %s\n",
opts->host_traddr);
goto out_free_ctrl;
}
}
- if (opts->mask & NVMF_OPT_TRSVCID) {
- u16 port;
-
- ret = kstrtou16(opts->trsvcid, 0, &port);
- if (ret)
- goto out_free_ctrl;
-
- ctrl->addr_in.sin_port = cpu_to_be16(port);
- } else {
- ctrl->addr_in.sin_port = cpu_to_be16(NVME_RDMA_IP_PORT);
- }
-
ret = nvme_init_ctrl(&ctrl->ctrl, dev, &nvme_rdma_ctrl_ops,
0 /* no quirks, we're perfect! */);
if (ret)
goto out_free_ctrl;
- ctrl->reconnect_delay = opts->reconnect_delay;
INIT_DELAYED_WORK(&ctrl->reconnect_work,
nvme_rdma_reconnect_ctrl_work);
INIT_WORK(&ctrl->err_work, nvme_rdma_error_recovery_work);
@@ -1977,7 +1949,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
- dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n",
+ dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
kref_get(&ctrl->ctrl.kref);
@@ -2013,7 +1985,7 @@ static struct nvmf_transport_ops nvme_rdma_transport = {
.name = "rdma",
.required_opts = NVMF_OPT_TRADDR,
.allowed_opts = NVMF_OPT_TRSVCID | NVMF_OPT_RECONNECT_DELAY |
- NVMF_OPT_HOST_TRADDR,
+ NVMF_OPT_HOST_TRADDR | NVMF_OPT_CTRL_LOSS_TMO,
.create_ctrl = nvme_rdma_create_ctrl,
};
@@ -2055,12 +2027,20 @@ static int __init nvme_rdma_init_module(void)
return -ENOMEM;
ret = ib_register_client(&nvme_rdma_ib_client);
- if (ret) {
- destroy_workqueue(nvme_rdma_wq);
- return ret;
- }
+ if (ret)
+ goto err_destroy_wq;
+
+ ret = nvmf_register_transport(&nvme_rdma_transport);
+ if (ret)
+ goto err_unreg_client;
+
+ return 0;
- return nvmf_register_transport(&nvme_rdma_transport);
+err_unreg_client:
+ ib_unregister_client(&nvme_rdma_ib_client);
+err_destroy_wq:
+ destroy_workqueue(nvme_rdma_wq);
+ return ret;
}
static void __exit nvme_rdma_cleanup_module(void)
diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 76450b0c55f1..ff1f97006322 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -121,7 +121,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
}
switch (req->cmd->get_log_page.lid) {
- case 0x01:
+ case NVME_LOG_ERROR:
/*
* We currently never set the More bit in the status field,
* so all error log entries are invalid and can be zeroed out.
@@ -129,7 +129,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
* mandatory log page.
*/
break;
- case 0x02:
+ case NVME_LOG_SMART:
/*
* XXX: fill out actual smart log
*
@@ -149,7 +149,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
goto err;
}
break;
- case 0x03:
+ case NVME_LOG_FW_SLOT:
/*
* We only support a single firmware slot which always is
* active, so we can zero out the whole firmware slot log and
@@ -480,31 +480,25 @@ static void nvmet_execute_keep_alive(struct nvmet_req *req)
nvmet_req_complete(req, 0);
}
-int nvmet_parse_admin_cmd(struct nvmet_req *req)
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
+ u16 ret;
req->ns = NULL;
- if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
- pr_err("nvmet: got admin cmd %d while CC.EN == 0\n",
- cmd->common.opcode);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
- if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got admin cmd %d while CSTS.RDY == 0\n",
- cmd->common.opcode);
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
+ ret = nvmet_check_ctrl_status(req, cmd);
+ if (unlikely(ret))
+ return ret;
switch (cmd->common.opcode) {
case nvme_admin_get_log_page:
req->data_len = nvmet_get_log_page_len(cmd);
switch (cmd->get_log_page.lid) {
- case 0x01:
- case 0x02:
- case 0x03:
+ case NVME_LOG_ERROR:
+ case NVME_LOG_SMART:
+ case NVME_LOG_FW_SLOT:
req->execute = nvmet_execute_get_log_page;
return 0;
}
@@ -545,6 +539,7 @@ int nvmet_parse_admin_cmd(struct nvmet_req *req)
return 0;
}
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+ req->sq->qid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 798653b329b2..cf90713043da 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -273,8 +273,8 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
ns->bdev = blkdev_get_by_path(ns->device_path, FMODE_READ | FMODE_WRITE,
NULL);
if (IS_ERR(ns->bdev)) {
- pr_err("nvmet: failed to open block device %s: (%ld)\n",
- ns->device_path, PTR_ERR(ns->bdev));
+ pr_err("failed to open block device %s: (%ld)\n",
+ ns->device_path, PTR_ERR(ns->bdev));
ret = PTR_ERR(ns->bdev);
ns->bdev = NULL;
goto out_unlock;
@@ -661,6 +661,23 @@ out:
return status;
}
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd)
+{
+ if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+ pr_err("got io cmd %d while CC.EN == 0 on qid = %d\n",
+ cmd->common.opcode, req->sq->qid);
+ return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ }
+
+ if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+ pr_err("got io cmd %d while CSTS.RDY == 0 on qid = %d\n",
+ cmd->common.opcode, req->sq->qid);
+ req->ns = NULL;
+ return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ }
+ return 0;
+}
+
static bool __nvmet_host_allowed(struct nvmet_subsys *subsys,
const char *hostnqn)
{
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index af8aabf05335..1aaf597e81fc 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -159,15 +159,15 @@ out:
nvmet_req_complete(req, status);
}
-int nvmet_parse_discovery_cmd(struct nvmet_req *req)
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
req->ns = NULL;
if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got cmd %d while not ready\n",
- cmd->common.opcode);
+ pr_err("got cmd %d while not ready\n",
+ cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
@@ -180,8 +180,8 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
req->execute = nvmet_execute_get_disc_log_page;
return 0;
default:
- pr_err("nvmet: unsupported get_log_page lid %d\n",
- cmd->get_log_page.lid);
+ pr_err("unsupported get_log_page lid %d\n",
+ cmd->get_log_page.lid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
case nvme_admin_identify:
@@ -192,17 +192,16 @@ int nvmet_parse_discovery_cmd(struct nvmet_req *req)
nvmet_execute_identify_disc_ctrl;
return 0;
default:
- pr_err("nvmet: unsupported identify cns %d\n",
- cmd->identify.cns);
+ pr_err("unsupported identify cns %d\n",
+ cmd->identify.cns);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
default:
- pr_err("nvmet: unsupported cmd %d\n",
- cmd->common.opcode);
+ pr_err("unsupported cmd %d\n", cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d\n", cmd->common.opcode);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
index 8bd022af3df6..3cc17269504b 100644
--- a/drivers/nvme/target/fabrics-cmd.c
+++ b/drivers/nvme/target/fabrics-cmd.c
@@ -73,7 +73,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
nvmet_req_complete(req, status);
}
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req)
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
@@ -122,7 +122,15 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
struct nvmet_ctrl *ctrl = NULL;
u16 status = 0;
- d = kmap(sg_page(req->sg)) + req->sg->offset;
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto complete;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto out;
/* zero out initial completion result, assign values as needed */
req->rsp->result.u32 = 0;
@@ -143,7 +151,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
}
status = nvmet_alloc_ctrl(d->subsysnqn, d->hostnqn, req,
- le32_to_cpu(c->kato), &ctrl);
+ le32_to_cpu(c->kato), &ctrl);
if (status)
goto out;
@@ -158,7 +166,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid);
out:
- kunmap(sg_page(req->sg));
+ kfree(d);
+complete:
nvmet_req_complete(req, status);
}
@@ -170,7 +179,15 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
u16 qid = le16_to_cpu(c->qid);
u16 status = 0;
- d = kmap(sg_page(req->sg)) + req->sg->offset;
+ d = kmalloc(sizeof(*d), GFP_KERNEL);
+ if (!d) {
+ status = NVME_SC_INTERNAL;
+ goto complete;
+ }
+
+ status = nvmet_copy_from_sgl(req, 0, d, sizeof(*d));
+ if (status)
+ goto out;
/* zero out initial completion result, assign values as needed */
req->rsp->result.u32 = 0;
@@ -183,8 +200,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
}
status = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
- le16_to_cpu(d->cntlid),
- req, &ctrl);
+ le16_to_cpu(d->cntlid),
+ req, &ctrl);
if (status)
goto out;
@@ -205,7 +222,8 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
pr_info("adding queue %d to ctrl %d.\n", qid, ctrl->cntlid);
out:
- kunmap(sg_page(req->sg));
+ kfree(d);
+complete:
nvmet_req_complete(req, status);
return;
@@ -214,7 +232,7 @@ out_ctrl_put:
goto out;
}
-int nvmet_parse_connect_cmd(struct nvmet_req *req)
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c
index 8f483ee7868c..074bd3743b5f 100644
--- a/drivers/nvme/target/fc.c
+++ b/drivers/nvme/target/fc.c
@@ -82,10 +82,13 @@ struct nvmet_fc_fcp_iod {
enum nvmet_fcp_datadir io_dir;
bool active;
bool abort;
+ bool aborted;
+ bool writedataactive;
spinlock_t flock;
struct nvmet_req req;
struct work_struct work;
+ struct work_struct done_work;
struct nvmet_fc_tgtport *tgtport;
struct nvmet_fc_tgt_queue *queue;
@@ -213,6 +216,7 @@ static DEFINE_IDA(nvmet_fc_tgtport_cnt);
static void nvmet_fc_handle_ls_rqst_work(struct work_struct *work);
static void nvmet_fc_handle_fcp_rqst_work(struct work_struct *work);
+static void nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work);
static void nvmet_fc_tgt_a_put(struct nvmet_fc_tgt_assoc *assoc);
static int nvmet_fc_tgt_a_get(struct nvmet_fc_tgt_assoc *assoc);
static void nvmet_fc_tgt_q_put(struct nvmet_fc_tgt_queue *queue);
@@ -414,9 +418,13 @@ nvmet_fc_prep_fcp_iodlist(struct nvmet_fc_tgtport *tgtport,
for (i = 0; i < queue->sqsize; fod++, i++) {
INIT_WORK(&fod->work, nvmet_fc_handle_fcp_rqst_work);
+ INIT_WORK(&fod->done_work, nvmet_fc_fcp_rqst_op_done_work);
fod->tgtport = tgtport;
fod->queue = queue;
fod->active = false;
+ fod->abort = false;
+ fod->aborted = false;
+ fod->fcpreq = NULL;
list_add_tail(&fod->fcp_list, &queue->fod_list);
spin_lock_init(&fod->flock);
@@ -463,7 +471,6 @@ nvmet_fc_alloc_fcp_iod(struct nvmet_fc_tgt_queue *queue)
if (fod) {
list_del(&fod->fcp_list);
fod->active = true;
- fod->abort = false;
/*
* no queue reference is taken, as it was taken by the
* queue lookup just prior to the allocation. The iod
@@ -479,17 +486,30 @@ static void
nvmet_fc_free_fcp_iod(struct nvmet_fc_tgt_queue *queue,
struct nvmet_fc_fcp_iod *fod)
{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+ struct nvmet_fc_tgtport *tgtport = fod->tgtport;
unsigned long flags;
+ fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
+ sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+
+ fcpreq->nvmet_fc_private = NULL;
+
spin_lock_irqsave(&queue->qlock, flags);
list_add_tail(&fod->fcp_list, &fod->queue->fod_list);
fod->active = false;
+ fod->abort = false;
+ fod->aborted = false;
+ fod->writedataactive = false;
+ fod->fcpreq = NULL;
spin_unlock_irqrestore(&queue->qlock, flags);
/*
* release the reference taken at queue lookup and fod allocation
*/
nvmet_fc_tgt_q_put(queue);
+
+ tgtport->ops->fcp_req_release(&tgtport->fc_target_port, fcpreq);
}
static int
@@ -616,32 +636,12 @@ nvmet_fc_tgt_q_get(struct nvmet_fc_tgt_queue *queue)
static void
-nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
- struct nvmefc_tgt_fcp_req *fcpreq)
-{
- int ret;
-
- fcpreq->op = NVMET_FCOP_ABORT;
- fcpreq->offset = 0;
- fcpreq->timeout = 0;
- fcpreq->transfer_length = 0;
- fcpreq->transferred_length = 0;
- fcpreq->fcp_error = 0;
- fcpreq->sg_cnt = 0;
-
- ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fcpreq);
- if (ret)
- /* should never reach here !! */
- WARN_ON(1);
-}
-
-
-static void
nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
{
+ struct nvmet_fc_tgtport *tgtport = queue->assoc->tgtport;
struct nvmet_fc_fcp_iod *fod = queue->fod;
unsigned long flags;
- int i;
+ int i, writedataactive;
bool disconnect;
disconnect = atomic_xchg(&queue->connected, 0);
@@ -652,7 +652,20 @@ nvmet_fc_delete_target_queue(struct nvmet_fc_tgt_queue *queue)
if (fod->active) {
spin_lock(&fod->flock);
fod->abort = true;
+ writedataactive = fod->writedataactive;
spin_unlock(&fod->flock);
+ /*
+ * only call lldd abort routine if waiting for
+ * writedata. other outstanding ops should finish
+ * on their own.
+ */
+ if (writedataactive) {
+ spin_lock(&fod->flock);
+ fod->aborted = true;
+ spin_unlock(&fod->flock);
+ tgtport->ops->fcp_abort(
+ &tgtport->fc_target_port, fod->fcpreq);
+ }
}
}
spin_unlock_irqrestore(&queue->qlock, flags);
@@ -846,7 +859,8 @@ nvmet_fc_register_targetport(struct nvmet_fc_port_info *pinfo,
int ret, idx;
if (!template->xmt_ls_rsp || !template->fcp_op ||
- !template->targetport_delete ||
+ !template->fcp_abort ||
+ !template->fcp_req_release || !template->targetport_delete ||
!template->max_hw_queues || !template->max_sgl_segments ||
!template->max_dif_sgl_segments || !template->dma_boundary) {
ret = -EINVAL;
@@ -1189,8 +1203,8 @@ nvmet_fc_ls_create_association(struct nvmet_fc_tgtport *tgtport,
validation_errors[ret]);
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
- ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
@@ -1281,8 +1295,9 @@ nvmet_fc_ls_create_connection(struct nvmet_fc_tgtport *tgtport,
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
(ret == VERR_NO_ASSOC) ?
- ELS_RJT_PROT : ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_INV_ASSOC :
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
@@ -1369,8 +1384,12 @@ nvmet_fc_ls_disconnect(struct nvmet_fc_tgtport *tgtport,
validation_errors[ret]);
iod->lsreq->rsplen = nvmet_fc_format_rjt(acc,
NVME_FC_MAX_LS_BUFFER_SIZE, rqst->w0.ls_cmd,
- (ret == 8) ? ELS_RJT_PROT : ELS_RJT_LOGIC,
- ELS_EXPL_NONE, 0);
+ (ret == VERR_NO_ASSOC) ?
+ FCNVME_RJT_RC_INV_ASSOC :
+ (ret == VERR_NO_CONN) ?
+ FCNVME_RJT_RC_INV_CONN :
+ FCNVME_RJT_RC_LOGIC,
+ FCNVME_RJT_EXP_NONE, 0);
return;
}
@@ -1479,7 +1498,7 @@ nvmet_fc_handle_ls_rqst(struct nvmet_fc_tgtport *tgtport,
default:
iod->lsreq->rsplen = nvmet_fc_format_rjt(iod->rspbuf,
NVME_FC_MAX_LS_BUFFER_SIZE, w0->ls_cmd,
- ELS_RJT_INVAL, ELS_EXPL_NONE, 0);
+ FCNVME_RJT_RC_INVAL, FCNVME_RJT_EXP_NONE, 0);
}
nvmet_fc_xmt_ls_rsp(tgtport, iod);
@@ -1619,6 +1638,8 @@ nvmet_fc_free_tgt_pgs(struct nvmet_fc_fcp_iod *fod)
for_each_sg(fod->data_sg, sg, fod->data_sg_cnt, count)
__free_page(sg_page(sg));
kfree(fod->data_sg);
+ fod->data_sg = NULL;
+ fod->data_sg_cnt = 0;
}
@@ -1704,6 +1725,26 @@ nvmet_fc_prep_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
static void nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq);
static void
+nvmet_fc_abort_op(struct nvmet_fc_tgtport *tgtport,
+ struct nvmet_fc_fcp_iod *fod)
+{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+
+ /* data no longer needed */
+ nvmet_fc_free_tgt_pgs(fod);
+
+ /*
+ * if an ABTS was received or we issued the fcp_abort early
+ * don't call abort routine again.
+ */
+ /* no need to take lock - lock was taken earlier to get here */
+ if (!fod->aborted)
+ tgtport->ops->fcp_abort(&tgtport->fc_target_port, fcpreq);
+
+ nvmet_fc_free_fcp_iod(fod->queue, fod);
+}
+
+static void
nvmet_fc_xmt_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
struct nvmet_fc_fcp_iod *fod)
{
@@ -1716,7 +1757,7 @@ nvmet_fc_xmt_fcp_rsp(struct nvmet_fc_tgtport *tgtport,
ret = tgtport->ops->fcp_op(&tgtport->fc_target_port, fod->fcpreq);
if (ret)
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
}
static void
@@ -1725,6 +1766,7 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
{
struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
struct scatterlist *sg, *datasg;
+ unsigned long flags;
u32 tlen, sg_off;
int ret;
@@ -1789,10 +1831,13 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
*/
fod->abort = true;
- if (op == NVMET_FCOP_WRITEDATA)
+ if (op == NVMET_FCOP_WRITEDATA) {
+ spin_lock_irqsave(&fod->flock, flags);
+ fod->writedataactive = false;
+ spin_unlock_irqrestore(&fod->flock, flags);
nvmet_req_complete(&fod->req,
NVME_SC_FC_TRANSPORT_ERROR);
- else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
+ } else /* NVMET_FCOP_READDATA or NVMET_FCOP_READDATA_RSP */ {
fcpreq->fcp_error = ret;
fcpreq->transferred_length = 0;
nvmet_fc_xmt_fcp_op_done(fod->fcpreq);
@@ -1800,32 +1845,54 @@ nvmet_fc_transfer_fcp_data(struct nvmet_fc_tgtport *tgtport,
}
}
+static inline bool
+__nvmet_fc_fod_op_abort(struct nvmet_fc_fcp_iod *fod, bool abort)
+{
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
+ struct nvmet_fc_tgtport *tgtport = fod->tgtport;
+
+ /* if in the middle of an io and we need to tear down */
+ if (abort) {
+ if (fcpreq->op == NVMET_FCOP_WRITEDATA) {
+ nvmet_req_complete(&fod->req,
+ NVME_SC_FC_TRANSPORT_ERROR);
+ return true;
+ }
+
+ nvmet_fc_abort_op(tgtport, fod);
+ return true;
+ }
+
+ return false;
+}
+
+/*
+ * actual done handler for FCP operations when completed by the lldd
+ */
static void
-nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+nvmet_fc_fod_op_done(struct nvmet_fc_fcp_iod *fod)
{
- struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmefc_tgt_fcp_req *fcpreq = fod->fcpreq;
struct nvmet_fc_tgtport *tgtport = fod->tgtport;
unsigned long flags;
bool abort;
spin_lock_irqsave(&fod->flock, flags);
abort = fod->abort;
+ fod->writedataactive = false;
spin_unlock_irqrestore(&fod->flock, flags);
- /* if in the middle of an io and we need to tear down */
- if (abort && fcpreq->op != NVMET_FCOP_ABORT) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_req_complete(&fod->req, fcpreq->fcp_error);
- return;
- }
-
switch (fcpreq->op) {
case NVMET_FCOP_WRITEDATA:
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
if (fcpreq->fcp_error ||
fcpreq->transferred_length != fcpreq->transfer_length) {
+ spin_lock(&fod->flock);
+ fod->abort = true;
+ spin_unlock(&fod->flock);
+
nvmet_req_complete(&fod->req,
NVME_SC_FC_TRANSPORT_ERROR);
return;
@@ -1833,6 +1900,10 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
fod->offset += fcpreq->transferred_length;
if (fod->offset != fod->total_length) {
+ spin_lock_irqsave(&fod->flock, flags);
+ fod->writedataactive = true;
+ spin_unlock_irqrestore(&fod->flock, flags);
+
/* transfer the next chunk */
nvmet_fc_transfer_fcp_data(tgtport, fod,
NVMET_FCOP_WRITEDATA);
@@ -1847,12 +1918,11 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
case NVMET_FCOP_READDATA:
case NVMET_FCOP_READDATA_RSP:
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
if (fcpreq->fcp_error ||
fcpreq->transferred_length != fcpreq->transfer_length) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
@@ -1861,8 +1931,6 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
if (fcpreq->op == NVMET_FCOP_READDATA_RSP) {
/* data no longer needed */
nvmet_fc_free_tgt_pgs(fod);
- fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
- sizeof(fod->rspiubuf), DMA_TO_DEVICE);
nvmet_fc_free_fcp_iod(fod->queue, fod);
return;
}
@@ -1885,19 +1953,38 @@ nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
break;
case NVMET_FCOP_RSP:
- case NVMET_FCOP_ABORT:
- fc_dma_sync_single_for_cpu(tgtport->dev, fod->rspdma,
- sizeof(fod->rspiubuf), DMA_TO_DEVICE);
+ if (__nvmet_fc_fod_op_abort(fod, abort))
+ return;
nvmet_fc_free_fcp_iod(fod->queue, fod);
break;
default:
- nvmet_fc_free_tgt_pgs(fod);
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
break;
}
}
+static void
+nvmet_fc_fcp_rqst_op_done_work(struct work_struct *work)
+{
+ struct nvmet_fc_fcp_iod *fod =
+ container_of(work, struct nvmet_fc_fcp_iod, done_work);
+
+ nvmet_fc_fod_op_done(fod);
+}
+
+static void
+nvmet_fc_xmt_fcp_op_done(struct nvmefc_tgt_fcp_req *fcpreq)
+{
+ struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmet_fc_tgt_queue *queue = fod->queue;
+
+ if (fod->tgtport->ops->target_features & NVMET_FCTGTFEAT_OPDONE_IN_ISR)
+ /* context switch so completion is not in ISR context */
+ queue_work_on(queue->cpu, queue->work_q, &fod->done_work);
+ else
+ nvmet_fc_fod_op_done(fod);
+}
+
/*
* actual completion handler after execution by the nvmet layer
*/
@@ -1919,10 +2006,7 @@ __nvmet_fc_fcp_nvme_cmd_done(struct nvmet_fc_tgtport *tgtport,
fod->queue->sqhd = cqe->sq_head;
if (abort) {
- /* data no longer needed */
- nvmet_fc_free_tgt_pgs(fod);
-
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
@@ -2018,8 +2102,8 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
&fod->queue->nvme_cq,
&fod->queue->nvme_sq,
&nvmet_fc_tgt_fcp_ops);
- if (!ret) { /* bad SQE content */
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ if (!ret) { /* bad SQE content or invalid ctrl state */
+ nvmet_fc_abort_op(tgtport, fod);
return;
}
@@ -2059,7 +2143,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport,
return;
transport_error:
- nvmet_fc_abort_op(tgtport, fod->fcpreq);
+ nvmet_fc_abort_op(tgtport, fod);
}
/*
@@ -2089,7 +2173,7 @@ nvmet_fc_handle_fcp_rqst_work(struct work_struct *work)
* If this routine returns error, the lldd should abort the exchange.
*
* @target_port: pointer to the (registered) target port the FCP CMD IU
- * was receive on.
+ * was received on.
* @fcpreq: pointer to a fcpreq request structure to be used to reference
* the exchange corresponding to the FCP Exchange.
* @cmdiubuf: pointer to the buffer containing the FCP CMD IU
@@ -2112,7 +2196,6 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port,
(be16_to_cpu(cmdiu->iu_len) != (sizeof(*cmdiu)/4)))
return -EIO;
-
queue = nvmet_fc_find_target_queue(tgtport,
be64_to_cpu(cmdiu->connection_id));
if (!queue)
@@ -2142,12 +2225,68 @@ nvmet_fc_rcv_fcp_req(struct nvmet_fc_target_port *target_port,
((queue->qid - 1) % tgtport->ops->max_hw_queues) : 0;
memcpy(&fod->cmdiubuf, cmdiubuf, cmdiubuf_len);
- queue_work_on(queue->cpu, queue->work_q, &fod->work);
+ if (tgtport->ops->target_features & NVMET_FCTGTFEAT_CMD_IN_ISR)
+ queue_work_on(queue->cpu, queue->work_q, &fod->work);
+ else
+ nvmet_fc_handle_fcp_rqst(tgtport, fod);
return 0;
}
EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_req);
+/**
+ * nvmet_fc_rcv_fcp_abort - transport entry point called by an LLDD
+ * upon the reception of an ABTS for a FCP command
+ *
+ * Notify the transport that an ABTS has been received for a FCP command
+ * that had been given to the transport via nvmet_fc_rcv_fcp_req(). The
+ * LLDD believes the command is still being worked on
+ * (template_ops->fcp_req_release() has not been called).
+ *
+ * The transport will wait for any outstanding work (an op to the LLDD,
+ * which the lldd should complete with error due to the ABTS; or the
+ * completion from the nvmet layer of the nvme command), then will
+ * stop processing and call the nvmet_fc_rcv_fcp_req() callback to
+ * return the i/o context to the LLDD. The LLDD may send the BA_ACC
+ * to the ABTS either after return from this function (assuming any
+ * outstanding op work has been terminated) or upon the callback being
+ * called.
+ *
+ * @target_port: pointer to the (registered) target port the FCP CMD IU
+ * was received on.
+ * @fcpreq: pointer to the fcpreq request structure that corresponds
+ * to the exchange that received the ABTS.
+ */
+void
+nvmet_fc_rcv_fcp_abort(struct nvmet_fc_target_port *target_port,
+ struct nvmefc_tgt_fcp_req *fcpreq)
+{
+ struct nvmet_fc_fcp_iod *fod = fcpreq->nvmet_fc_private;
+ struct nvmet_fc_tgt_queue *queue;
+ unsigned long flags;
+
+ if (!fod || fod->fcpreq != fcpreq)
+ /* job appears to have already completed, ignore abort */
+ return;
+
+ queue = fod->queue;
+
+ spin_lock_irqsave(&queue->qlock, flags);
+ if (fod->active) {
+ /*
+ * mark as abort. The abort handler, invoked upon completion
+ * of any work, will detect the aborted status and do the
+ * callback.
+ */
+ spin_lock(&fod->flock);
+ fod->abort = true;
+ fod->aborted = true;
+ spin_unlock(&fod->flock);
+ }
+ spin_unlock_irqrestore(&queue->qlock, flags);
+}
+EXPORT_SYMBOL_GPL(nvmet_fc_rcv_fcp_abort);
+
enum {
FCT_TRADDR_ERR = 0,
FCT_TRADDR_WWNN = 1 << 0,
@@ -2177,7 +2316,7 @@ nvmet_fc_parse_traddr(struct nvmet_fc_traddr *traddr, char *buf)
if (!options)
return -ENOMEM;
- while ((p = strsep(&o, ",\n")) != NULL) {
+ while ((p = strsep(&o, ":\n")) != NULL) {
if (!*p)
continue;
@@ -2238,6 +2377,7 @@ nvmet_fc_add_port(struct nvmet_port *port)
if (!tgtport->port) {
tgtport->port = port;
port->priv = tgtport;
+ nvmet_fc_tgtport_get(tgtport);
ret = 0;
} else
ret = -EALREADY;
diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c
index 4e8e6a22bce1..aaa3dbe22bd5 100644
--- a/drivers/nvme/target/fcloop.c
+++ b/drivers/nvme/target/fcloop.c
@@ -246,11 +246,19 @@ struct fcloop_lsreq {
struct fcloop_fcpreq {
struct fcloop_tport *tport;
struct nvmefc_fcp_req *fcpreq;
+ spinlock_t reqlock;
u16 status;
+ bool active;
+ bool aborted;
struct work_struct work;
struct nvmefc_tgt_fcp_req tgt_fcp_req;
};
+struct fcloop_ini_fcpreq {
+ struct nvmefc_fcp_req *fcpreq;
+ struct fcloop_fcpreq *tfcp_req;
+ struct work_struct iniwork;
+};
static inline struct fcloop_lsreq *
tgt_ls_req_to_lsreq(struct nvmefc_tgt_ls_req *tgt_lsreq)
@@ -341,7 +349,21 @@ fcloop_xmt_ls_rsp(struct nvmet_fc_target_port *tport,
}
/*
- * FCP IO operation done. call back up initiator "done" flows.
+ * FCP IO operation done by initiator abort.
+ * call back up initiator "done" flows.
+ */
+static void
+fcloop_tgt_fcprqst_ini_done_work(struct work_struct *work)
+{
+ struct fcloop_ini_fcpreq *inireq =
+ container_of(work, struct fcloop_ini_fcpreq, iniwork);
+
+ inireq->fcpreq->done(inireq->fcpreq);
+}
+
+/*
+ * FCP IO operation done by target completion.
+ * call back up initiator "done" flows.
*/
static void
fcloop_tgt_fcprqst_done_work(struct work_struct *work)
@@ -349,12 +371,18 @@ fcloop_tgt_fcprqst_done_work(struct work_struct *work)
struct fcloop_fcpreq *tfcp_req =
container_of(work, struct fcloop_fcpreq, work);
struct fcloop_tport *tport = tfcp_req->tport;
- struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+ struct nvmefc_fcp_req *fcpreq;
- if (tport->remoteport) {
+ spin_lock(&tfcp_req->reqlock);
+ fcpreq = tfcp_req->fcpreq;
+ spin_unlock(&tfcp_req->reqlock);
+
+ if (tport->remoteport && fcpreq) {
fcpreq->status = tfcp_req->status;
fcpreq->done(fcpreq);
}
+
+ kfree(tfcp_req);
}
@@ -364,20 +392,25 @@ fcloop_fcp_req(struct nvme_fc_local_port *localport,
void *hw_queue_handle,
struct nvmefc_fcp_req *fcpreq)
{
- struct fcloop_fcpreq *tfcp_req = fcpreq->private;
struct fcloop_rport *rport = remoteport->private;
+ struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+ struct fcloop_fcpreq *tfcp_req;
int ret = 0;
- INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
+ if (!rport->targetport)
+ return -ECONNREFUSED;
- if (!rport->targetport) {
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ERROR;
- schedule_work(&tfcp_req->work);
- return ret;
- }
+ tfcp_req = kzalloc(sizeof(*tfcp_req), GFP_KERNEL);
+ if (!tfcp_req)
+ return -ENOMEM;
+ inireq->fcpreq = fcpreq;
+ inireq->tfcp_req = tfcp_req;
+ INIT_WORK(&inireq->iniwork, fcloop_tgt_fcprqst_ini_done_work);
tfcp_req->fcpreq = fcpreq;
tfcp_req->tport = rport->targetport->private;
+ spin_lock_init(&tfcp_req->reqlock);
+ INIT_WORK(&tfcp_req->work, fcloop_tgt_fcprqst_done_work);
ret = nvmet_fc_rcv_fcp_req(rport->targetport, &tfcp_req->tgt_fcp_req,
fcpreq->cmdaddr, fcpreq->cmdlen);
@@ -444,63 +477,129 @@ fcloop_fcp_op(struct nvmet_fc_target_port *tgtport,
struct nvmefc_tgt_fcp_req *tgt_fcpreq)
{
struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
- struct nvmefc_fcp_req *fcpreq = tfcp_req->fcpreq;
+ struct nvmefc_fcp_req *fcpreq;
u32 rsplen = 0, xfrlen = 0;
- int fcp_err = 0;
+ int fcp_err = 0, active, aborted;
u8 op = tgt_fcpreq->op;
+ spin_lock(&tfcp_req->reqlock);
+ fcpreq = tfcp_req->fcpreq;
+ active = tfcp_req->active;
+ aborted = tfcp_req->aborted;
+ tfcp_req->active = true;
+ spin_unlock(&tfcp_req->reqlock);
+
+ if (unlikely(active))
+ /* illegal - call while i/o active */
+ return -EALREADY;
+
+ if (unlikely(aborted)) {
+ /* target transport has aborted i/o prior */
+ spin_lock(&tfcp_req->reqlock);
+ tfcp_req->active = false;
+ spin_unlock(&tfcp_req->reqlock);
+ tgt_fcpreq->transferred_length = 0;
+ tgt_fcpreq->fcp_error = -ECANCELED;
+ tgt_fcpreq->done(tgt_fcpreq);
+ return 0;
+ }
+
+ /*
+ * if fcpreq is NULL, the I/O has been aborted (from
+ * initiator side). For the target side, act as if all is well
+ * but don't actually move data.
+ */
+
switch (op) {
case NVMET_FCOP_WRITEDATA:
xfrlen = tgt_fcpreq->transfer_length;
- fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
- tgt_fcpreq->offset, xfrlen);
- fcpreq->transferred_length += xfrlen;
+ if (fcpreq) {
+ fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+ fcpreq->first_sgl, tgt_fcpreq->offset,
+ xfrlen);
+ fcpreq->transferred_length += xfrlen;
+ }
break;
case NVMET_FCOP_READDATA:
case NVMET_FCOP_READDATA_RSP:
xfrlen = tgt_fcpreq->transfer_length;
- fcloop_fcp_copy_data(op, tgt_fcpreq->sg, fcpreq->first_sgl,
- tgt_fcpreq->offset, xfrlen);
- fcpreq->transferred_length += xfrlen;
+ if (fcpreq) {
+ fcloop_fcp_copy_data(op, tgt_fcpreq->sg,
+ fcpreq->first_sgl, tgt_fcpreq->offset,
+ xfrlen);
+ fcpreq->transferred_length += xfrlen;
+ }
if (op == NVMET_FCOP_READDATA)
break;
/* Fall-Thru to RSP handling */
case NVMET_FCOP_RSP:
- rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
- fcpreq->rsplen : tgt_fcpreq->rsplen);
- memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
- if (rsplen < tgt_fcpreq->rsplen)
- fcp_err = -E2BIG;
- fcpreq->rcv_rsplen = rsplen;
- fcpreq->status = 0;
+ if (fcpreq) {
+ rsplen = ((fcpreq->rsplen < tgt_fcpreq->rsplen) ?
+ fcpreq->rsplen : tgt_fcpreq->rsplen);
+ memcpy(fcpreq->rspaddr, tgt_fcpreq->rspaddr, rsplen);
+ if (rsplen < tgt_fcpreq->rsplen)
+ fcp_err = -E2BIG;
+ fcpreq->rcv_rsplen = rsplen;
+ fcpreq->status = 0;
+ }
tfcp_req->status = 0;
break;
- case NVMET_FCOP_ABORT:
- tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
- break;
-
default:
fcp_err = -EINVAL;
break;
}
+ spin_lock(&tfcp_req->reqlock);
+ tfcp_req->active = false;
+ spin_unlock(&tfcp_req->reqlock);
+
tgt_fcpreq->transferred_length = xfrlen;
tgt_fcpreq->fcp_error = fcp_err;
tgt_fcpreq->done(tgt_fcpreq);
- if ((!fcp_err) && (op == NVMET_FCOP_RSP ||
- op == NVMET_FCOP_READDATA_RSP ||
- op == NVMET_FCOP_ABORT))
- schedule_work(&tfcp_req->work);
-
return 0;
}
static void
+fcloop_tgt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+ struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+ int active;
+
+ /*
+ * mark aborted only in case there were 2 threads in transport
+ * (one doing io, other doing abort) and only kills ops posted
+ * after the abort request
+ */
+ spin_lock(&tfcp_req->reqlock);
+ active = tfcp_req->active;
+ tfcp_req->aborted = true;
+ spin_unlock(&tfcp_req->reqlock);
+
+ tfcp_req->status = NVME_SC_FC_TRANSPORT_ABORTED;
+
+ /*
+ * nothing more to do. If io wasn't active, the transport should
+ * immediately call the req_release. If it was active, the op
+ * will complete, and the lldd should call req_release.
+ */
+}
+
+static void
+fcloop_fcp_req_release(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *tgt_fcpreq)
+{
+ struct fcloop_fcpreq *tfcp_req = tgt_fcp_req_to_fcpreq(tgt_fcpreq);
+
+ schedule_work(&tfcp_req->work);
+}
+
+static void
fcloop_ls_abort(struct nvme_fc_local_port *localport,
struct nvme_fc_remote_port *remoteport,
struct nvmefc_ls_req *lsreq)
@@ -513,6 +612,27 @@ fcloop_fcp_abort(struct nvme_fc_local_port *localport,
void *hw_queue_handle,
struct nvmefc_fcp_req *fcpreq)
{
+ struct fcloop_rport *rport = remoteport->private;
+ struct fcloop_ini_fcpreq *inireq = fcpreq->private;
+ struct fcloop_fcpreq *tfcp_req = inireq->tfcp_req;
+
+ if (!tfcp_req)
+ /* abort has already been called */
+ return;
+
+ if (rport->targetport)
+ nvmet_fc_rcv_fcp_abort(rport->targetport,
+ &tfcp_req->tgt_fcp_req);
+
+ /* break initiator/target relationship for io */
+ spin_lock(&tfcp_req->reqlock);
+ inireq->tfcp_req = NULL;
+ tfcp_req->fcpreq = NULL;
+ spin_unlock(&tfcp_req->reqlock);
+
+ /* post the aborted io completion */
+ fcpreq->status = -ECANCELED;
+ schedule_work(&inireq->iniwork);
}
static void
@@ -563,20 +683,23 @@ struct nvme_fc_port_template fctemplate = {
.local_priv_sz = sizeof(struct fcloop_lport),
.remote_priv_sz = sizeof(struct fcloop_rport),
.lsrqst_priv_sz = sizeof(struct fcloop_lsreq),
- .fcprqst_priv_sz = sizeof(struct fcloop_fcpreq),
+ .fcprqst_priv_sz = sizeof(struct fcloop_ini_fcpreq),
};
struct nvmet_fc_target_template tgttemplate = {
.targetport_delete = fcloop_targetport_delete,
.xmt_ls_rsp = fcloop_xmt_ls_rsp,
.fcp_op = fcloop_fcp_op,
+ .fcp_abort = fcloop_tgt_fcp_abort,
+ .fcp_req_release = fcloop_fcp_req_release,
.max_hw_queues = FCLOOP_HW_QUEUES,
.max_sgl_segments = FCLOOP_SGL_SEGS,
.max_dif_sgl_segments = FCLOOP_SGL_SEGS,
.dma_boundary = FCLOOP_DMABOUND_4G,
/* optional features */
- .target_features = NVMET_FCTGTFEAT_READDATA_RSP |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED,
+ .target_features = NVMET_FCTGTFEAT_CMD_IN_ISR |
+ NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR,
/* sizes of additional private data for data structures */
.target_priv_sz = sizeof(struct fcloop_tport),
};
diff --git a/drivers/nvme/target/io-cmd.c b/drivers/nvme/target/io-cmd.c
index 6b0baa9caab9..c77940d80fc8 100644
--- a/drivers/nvme/target/io-cmd.c
+++ b/drivers/nvme/target/io-cmd.c
@@ -184,7 +184,7 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
(req->ns->blksize_shift - 9)) + 1;
if (__blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector,
- GFP_KERNEL, &bio, true))
+ GFP_KERNEL, &bio, 0))
status = NVME_SC_INTERNAL | NVME_SC_DNR;
if (bio) {
@@ -196,26 +196,19 @@ static void nvmet_execute_write_zeroes(struct nvmet_req *req)
}
}
-int nvmet_parse_io_cmd(struct nvmet_req *req)
+u16 nvmet_parse_io_cmd(struct nvmet_req *req)
{
struct nvme_command *cmd = req->cmd;
+ u16 ret;
- if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
- pr_err("nvmet: got io cmd %d while CC.EN == 0\n",
- cmd->common.opcode);
+ ret = nvmet_check_ctrl_status(req, cmd);
+ if (unlikely(ret)) {
req->ns = NULL;
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
- }
-
- if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
- pr_err("nvmet: got io cmd %d while CSTS.RDY == 0\n",
- cmd->common.opcode);
- req->ns = NULL;
- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
+ return ret;
}
req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
- if (!req->ns)
+ if (unlikely(!req->ns))
return NVME_SC_INVALID_NS | NVME_SC_DNR;
switch (cmd->common.opcode) {
@@ -237,7 +230,8 @@ int nvmet_parse_io_cmd(struct nvmet_req *req)
req->execute = nvmet_execute_write_zeroes;
return 0;
default:
- pr_err("nvmet: unhandled cmd %d\n", cmd->common.opcode);
+ pr_err("unhandled cmd %d on qid %d\n", cmd->common.opcode,
+ req->sq->qid);
return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
}
}
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index c7b0b6a52708..304f1c87c160 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -13,12 +13,10 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/scatterlist.h>
-#include <linux/delay.h>
#include <linux/blk-mq.h>
#include <linux/nvme.h>
#include <linux/module.h>
#include <linux/parser.h>
-#include <linux/t10-pi.h>
#include "nvmet.h"
#include "../host/nvme.h"
#include "../host/fabrics.h"
@@ -93,31 +91,26 @@ static inline int nvme_loop_queue_idx(struct nvme_loop_queue *queue)
static void nvme_loop_complete_rq(struct request *req)
{
struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(req);
- int error = 0;
nvme_cleanup_cmd(req);
sg_free_table_chained(&iod->sg_table, true);
+ nvme_complete_rq(req);
+}
- if (unlikely(req->errors)) {
- if (nvme_req_needs_retry(req, req->errors)) {
- nvme_requeue_req(req);
- return;
- }
-
- if (blk_rq_is_passthrough(req))
- error = req->errors;
- else
- error = nvme_error_status(req->errors);
- }
+static struct blk_mq_tags *nvme_loop_tagset(struct nvme_loop_queue *queue)
+{
+ u32 queue_idx = nvme_loop_queue_idx(queue);
- blk_mq_end_request(req, error);
+ if (queue_idx == 0)
+ return queue->ctrl->admin_tag_set.tags[queue_idx];
+ return queue->ctrl->tag_set.tags[queue_idx - 1];
}
static void nvme_loop_queue_response(struct nvmet_req *req)
{
- struct nvme_loop_iod *iod =
- container_of(req, struct nvme_loop_iod, req);
- struct nvme_completion *cqe = &iod->rsp;
+ struct nvme_loop_queue *queue =
+ container_of(req->sq, struct nvme_loop_queue, nvme_sq);
+ struct nvme_completion *cqe = req->rsp;
/*
* AEN requests are special as they don't time out and can
@@ -125,15 +118,22 @@ static void nvme_loop_queue_response(struct nvmet_req *req)
* aborts. We don't even bother to allocate a struct request
* for them but rather special case them here.
*/
- if (unlikely(nvme_loop_queue_idx(iod->queue) == 0 &&
+ if (unlikely(nvme_loop_queue_idx(queue) == 0 &&
cqe->command_id >= NVME_LOOP_AQ_BLKMQ_DEPTH)) {
- nvme_complete_async_event(&iod->queue->ctrl->ctrl, cqe->status,
+ nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status,
&cqe->result);
} else {
- struct request *rq = blk_mq_rq_from_pdu(iod);
+ struct request *rq;
+
+ rq = blk_mq_tag_to_rq(nvme_loop_tagset(queue), cqe->command_id);
+ if (!rq) {
+ dev_err(queue->ctrl->ctrl.device,
+ "tag 0x%x on queue %d not found\n",
+ cqe->command_id, nvme_loop_queue_idx(queue));
+ return;
+ }
- iod->nvme_req.result = cqe->result;
- blk_mq_complete_request(rq, le16_to_cpu(cqe->status) >> 1);
+ nvme_end_request(rq, cqe->status, cqe->result);
}
}
@@ -154,7 +154,7 @@ nvme_loop_timeout(struct request *rq, bool reserved)
schedule_work(&iod->queue->ctrl->reset_work);
/* fail with DNR on admin cmd timeout */
- rq->errors = NVME_SC_ABORT_REQ | NVME_SC_DNR;
+ nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR;
return BLK_EH_HANDLED;
}
@@ -268,7 +268,7 @@ static int nvme_loop_init_admin_hctx(struct blk_mq_hw_ctx *hctx, void *data,
return 0;
}
-static struct blk_mq_ops nvme_loop_mq_ops = {
+static const struct blk_mq_ops nvme_loop_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
.init_request = nvme_loop_init_request,
@@ -276,7 +276,7 @@ static struct blk_mq_ops nvme_loop_mq_ops = {
.timeout = nvme_loop_timeout,
};
-static struct blk_mq_ops nvme_loop_admin_mq_ops = {
+static const struct blk_mq_ops nvme_loop_admin_mq_ops = {
.queue_rq = nvme_loop_queue_rq,
.complete = nvme_loop_complete_rq,
.init_request = nvme_loop_init_admin_request,
@@ -349,6 +349,19 @@ out_destroy_queues:
return ret;
}
+static int nvme_loop_connect_io_queues(struct nvme_loop_ctrl *ctrl)
+{
+ int i, ret;
+
+ for (i = 1; i < ctrl->queue_count; i++) {
+ ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl)
{
int error;
@@ -490,7 +503,7 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
struct nvme_loop_ctrl *ctrl = container_of(work,
struct nvme_loop_ctrl, reset_work);
bool changed;
- int i, ret;
+ int ret;
nvme_loop_shutdown_ctrl(ctrl);
@@ -502,11 +515,9 @@ static void nvme_loop_reset_ctrl_work(struct work_struct *work)
if (ret)
goto out_destroy_admin;
- for (i = 1; i < ctrl->queue_count; i++) {
- ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
- if (ret)
- goto out_destroy_io;
- }
+ ret = nvme_loop_connect_io_queues(ctrl);
+ if (ret)
+ goto out_destroy_io;
changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
WARN_ON_ONCE(!changed);
@@ -559,7 +570,7 @@ static const struct nvme_ctrl_ops nvme_loop_ctrl_ops = {
static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
{
- int ret, i;
+ int ret;
ret = nvme_loop_init_io_queues(ctrl);
if (ret)
@@ -588,11 +599,9 @@ static int nvme_loop_create_io_queues(struct nvme_loop_ctrl *ctrl)
goto out_free_tagset;
}
- for (i = 1; i < ctrl->queue_count; i++) {
- ret = nvmf_connect_io_queue(&ctrl->ctrl, i);
- if (ret)
- goto out_cleanup_connect_q;
- }
+ ret = nvme_loop_connect_io_queues(ctrl);
+ if (ret)
+ goto out_cleanup_connect_q;
return 0;
@@ -736,7 +745,12 @@ static int __init nvme_loop_init_module(void)
ret = nvmet_register_transport(&nvme_loop_ops);
if (ret)
return ret;
- return nvmf_register_transport(&nvme_loop_transport);
+
+ ret = nvmf_register_transport(&nvme_loop_transport);
+ if (ret)
+ nvmet_unregister_transport(&nvme_loop_ops);
+
+ return ret;
}
static void __exit nvme_loop_cleanup_module(void)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index f7ff15f17ca9..7cb77ba5993b 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -253,11 +253,11 @@ struct nvmet_async_event {
u8 log_page;
};
-int nvmet_parse_connect_cmd(struct nvmet_req *req);
-int nvmet_parse_io_cmd(struct nvmet_req *req);
-int nvmet_parse_admin_cmd(struct nvmet_req *req);
-int nvmet_parse_discovery_cmd(struct nvmet_req *req);
-int nvmet_parse_fabrics_cmd(struct nvmet_req *req);
+u16 nvmet_parse_connect_cmd(struct nvmet_req *req);
+u16 nvmet_parse_io_cmd(struct nvmet_req *req);
+u16 nvmet_parse_admin_cmd(struct nvmet_req *req);
+u16 nvmet_parse_discovery_cmd(struct nvmet_req *req);
+u16 nvmet_parse_fabrics_cmd(struct nvmet_req *req);
bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
struct nvmet_sq *sq, struct nvmet_fabrics_ops *ops);
@@ -278,6 +278,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid,
struct nvmet_req *req, struct nvmet_ctrl **ret);
void nvmet_ctrl_put(struct nvmet_ctrl *ctrl);
+u16 nvmet_check_ctrl_status(struct nvmet_req *req, struct nvme_command *cmd);
struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn,
enum nvme_subsys_type type);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index ecc4fe862561..99c69018a35f 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -1199,6 +1199,11 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,
}
queue->port = cm_id->context;
+ if (queue->host_qid == 0) {
+ /* Let inflight controller teardown complete */
+ flush_scheduled_work();
+ }
+
ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn);
if (ret)
goto release_queue;
@@ -1427,12 +1432,16 @@ restart:
static int nvmet_rdma_add_port(struct nvmet_port *port)
{
struct rdma_cm_id *cm_id;
- struct sockaddr_in addr_in;
- u16 port_in;
+ struct sockaddr_storage addr = { };
+ __kernel_sa_family_t af;
int ret;
switch (port->disc_addr.adrfam) {
case NVMF_ADDR_FAMILY_IP4:
+ af = AF_INET;
+ break;
+ case NVMF_ADDR_FAMILY_IP6:
+ af = AF_INET6;
break;
default:
pr_err("address family %d not supported\n",
@@ -1440,13 +1449,13 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
return -EINVAL;
}
- ret = kstrtou16(port->disc_addr.trsvcid, 0, &port_in);
- if (ret)
+ ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
+ port->disc_addr.trsvcid, &addr);
+ if (ret) {
+ pr_err("malformed ip/port passed: %s:%s\n",
+ port->disc_addr.traddr, port->disc_addr.trsvcid);
return ret;
-
- addr_in.sin_family = AF_INET;
- addr_in.sin_addr.s_addr = in_aton(port->disc_addr.traddr);
- addr_in.sin_port = htons(port_in);
+ }
cm_id = rdma_create_id(&init_net, nvmet_rdma_cm_handler, port,
RDMA_PS_TCP, IB_QPT_RC);
@@ -1455,20 +1464,32 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
return PTR_ERR(cm_id);
}
- ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr_in);
+ /*
+ * Allow both IPv4 and IPv6 sockets to bind a single port
+ * at the same time.
+ */
+ ret = rdma_set_afonly(cm_id, 1);
+ if (ret) {
+ pr_err("rdma_set_afonly failed (%d)\n", ret);
+ goto out_destroy_id;
+ }
+
+ ret = rdma_bind_addr(cm_id, (struct sockaddr *)&addr);
if (ret) {
- pr_err("binding CM ID to %pISpc failed (%d)\n", &addr_in, ret);
+ pr_err("binding CM ID to %pISpcs failed (%d)\n",
+ (struct sockaddr *)&addr, ret);
goto out_destroy_id;
}
ret = rdma_listen(cm_id, 128);
if (ret) {
- pr_err("listening to %pISpc failed (%d)\n", &addr_in, ret);
+ pr_err("listening to %pISpcs failed (%d)\n",
+ (struct sockaddr *)&addr, ret);
goto out_destroy_id;
}
- pr_info("enabling port %d (%pISpc)\n",
- le16_to_cpu(port->disc_addr.portid), &addr_in);
+ pr_info("enabling port %d (%pISpcs)\n",
+ le16_to_cpu(port->disc_addr.portid), (struct sockaddr *)&addr);
port->priv = cm_id;
return 0;
diff --git a/drivers/sbus/char/jsflash.c b/drivers/sbus/char/jsflash.c
index 6ff61dad5e21..62fed9dc893e 100644
--- a/drivers/sbus/char/jsflash.c
+++ b/drivers/sbus/char/jsflash.c
@@ -183,11 +183,33 @@ static void jsfd_read(char *buf, unsigned long p, size_t togo) {
}
}
-static void jsfd_do_request(struct request_queue *q)
+static int jsfd_queue;
+
+static struct request *jsfd_next_request(void)
+{
+ struct request_queue *q;
+ struct request *rq;
+ int old_pos = jsfd_queue;
+
+ do {
+ q = jsfd_disk[jsfd_queue]->queue;
+ if (++jsfd_queue == JSF_MAX)
+ jsfd_queue = 0;
+ if (q) {
+ rq = blk_fetch_request(q);
+ if (rq)
+ return rq;
+ }
+ } while (jsfd_queue != old_pos);
+
+ return NULL;
+}
+
+static void jsfd_request(void)
{
struct request *req;
- req = blk_fetch_request(q);
+ req = jsfd_next_request();
while (req) {
struct jsfd_part *jdp = req->rq_disk->private_data;
unsigned long offset = blk_rq_pos(req) << 9;
@@ -211,10 +233,15 @@ static void jsfd_do_request(struct request_queue *q)
err = 0;
end:
if (!__blk_end_request_cur(req, err))
- req = blk_fetch_request(q);
+ req = jsfd_next_request();
}
}
+static void jsfd_do_request(struct request_queue *q)
+{
+ jsfd_request();
+}
+
/*
* The memory devices use the full 32/64 bits of the offset, and so we cannot
* check against negative addresses: they are ok. The return value is weird,
@@ -544,8 +571,6 @@ static int jsflash_init(void)
return 0;
}
-static struct request_queue *jsf_queue;
-
static int jsfd_init(void)
{
static DEFINE_SPINLOCK(lock);
@@ -562,6 +587,11 @@ static int jsfd_init(void)
struct gendisk *disk = alloc_disk(1);
if (!disk)
goto out;
+ disk->queue = blk_init_queue(jsfd_do_request, &lock);
+ if (!disk->queue) {
+ put_disk(disk);
+ goto out;
+ }
jsfd_disk[i] = disk;
}
@@ -570,13 +600,6 @@ static int jsfd_init(void)
goto out;
}
- jsf_queue = blk_init_queue(jsfd_do_request, &lock);
- if (!jsf_queue) {
- err = -ENOMEM;
- unregister_blkdev(JSFD_MAJOR, "jsfd");
- goto out;
- }
-
for (i = 0; i < JSF_MAX; i++) {
struct gendisk *disk = jsfd_disk[i];
if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
@@ -589,7 +612,6 @@ static int jsfd_init(void)
disk->fops = &jsfd_fops;
set_capacity(disk, jdp->dsize >> 9);
disk->private_data = jdp;
- disk->queue = jsf_queue;
add_disk(disk);
set_disk_ro(disk, 1);
}
@@ -619,6 +641,7 @@ static void __exit jsflash_cleanup_module(void)
for (i = 0; i < JSF_MAX; i++) {
if ((i & JSF_PART_MASK) >= JSF_NPART) continue;
del_gendisk(jsfd_disk[i]);
+ blk_cleanup_queue(jsfd_disk[i]->queue);
put_disk(jsfd_disk[i]);
}
if (jsf0.busy)
@@ -628,7 +651,6 @@ static void __exit jsflash_cleanup_module(void)
misc_deregister(&jsf_dev);
unregister_blkdev(JSFD_MAJOR, "jsfd");
- blk_cleanup_queue(jsf_queue);
}
module_init(jsflash_init_module);
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index fc2855565a51..93dbe58c47c8 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -166,6 +166,7 @@ scsi_mod-y += scsi_scan.o scsi_sysfs.o scsi_devinfo.o
scsi_mod-$(CONFIG_SCSI_NETLINK) += scsi_netlink.o
scsi_mod-$(CONFIG_SYSCTL) += scsi_sysctl.o
scsi_mod-$(CONFIG_SCSI_PROC_FS) += scsi_proc.o
+scsi_mod-$(CONFIG_BLK_DEBUG_FS) += scsi_debugfs.o
scsi_mod-y += scsi_trace.o scsi_logging.o
scsi_mod-$(CONFIG_PM) += scsi_pm.o
scsi_mod-$(CONFIG_SCSI_DH) += scsi_dh.o
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index acba1b67e505..b2333b3889c7 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -408,9 +408,7 @@ out:
if (phba->ktime_on)
lpfc_nvmet_ktime(phba, ctxp);
#endif
- /* Let Abort cmpl repost the context */
- if (!(ctxp->flag & LPFC_NVMET_ABORT_OP))
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ /* lpfc_nvmet_xmt_fcp_release() will recycle the context */
} else {
ctxp->entry_cnt++;
start_clean = offsetof(struct lpfc_iocbq, wqe);
@@ -544,27 +542,6 @@ lpfc_nvmet_xmt_fcp_op(struct nvmet_fc_target_port *tgtport,
}
#endif
- if (rsp->op == NVMET_FCOP_ABORT) {
- lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
- "6103 Abort op: oxri x%x %d cnt %d\n",
- ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
- lpfc_nvmeio_data(phba, "NVMET FCP ABRT: "
- "xri x%x state x%x cnt x%x\n",
- ctxp->oxid, ctxp->state, ctxp->entry_cnt);
-
- atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
- ctxp->entry_cnt++;
- ctxp->flag |= LPFC_NVMET_ABORT_OP;
- if (ctxp->flag & LPFC_NVMET_IO_INP)
- lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
- ctxp->oxid);
- else
- lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
- ctxp->oxid);
- return 0;
- }
-
/* Sanity check */
if (ctxp->state == LPFC_NVMET_STE_ABORT) {
atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
@@ -634,10 +611,75 @@ lpfc_nvmet_targetport_delete(struct nvmet_fc_target_port *targetport)
complete(&tport->tport_unreg_done);
}
+static void
+lpfc_nvmet_xmt_fcp_abort(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *req)
+{
+ struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
+ struct lpfc_nvmet_rcv_ctx *ctxp =
+ container_of(req, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+ struct lpfc_hba *phba = ctxp->phba;
+
+ lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
+ "6103 Abort op: oxri x%x %d cnt %d\n",
+ ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+
+ lpfc_nvmeio_data(phba, "NVMET FCP ABRT: xri x%x state x%x cnt x%x\n",
+ ctxp->oxid, ctxp->state, ctxp->entry_cnt);
+
+ atomic_inc(&lpfc_nvmep->xmt_fcp_abort);
+ ctxp->entry_cnt++;
+ ctxp->flag |= LPFC_NVMET_ABORT_OP;
+ if (ctxp->flag & LPFC_NVMET_IO_INP)
+ lpfc_nvmet_sol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+ ctxp->oxid);
+ else
+ lpfc_nvmet_unsol_fcp_issue_abort(phba, ctxp, ctxp->sid,
+ ctxp->oxid);
+}
+
+static void
+lpfc_nvmet_xmt_fcp_release(struct nvmet_fc_target_port *tgtport,
+ struct nvmefc_tgt_fcp_req *rsp)
+{
+ struct lpfc_nvmet_tgtport *lpfc_nvmep = tgtport->private;
+ struct lpfc_nvmet_rcv_ctx *ctxp =
+ container_of(rsp, struct lpfc_nvmet_rcv_ctx, ctx.fcp_req);
+ struct lpfc_hba *phba = ctxp->phba;
+ unsigned long flags;
+ bool aborting = false;
+
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if (ctxp->flag & LPFC_NVMET_ABORT_OP) {
+ aborting = true;
+ ctxp->flag |= LPFC_NVMET_CTX_RLS;
+ }
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
+ if (aborting)
+ /* let the abort path do the real release */
+ return;
+
+ /* Sanity check */
+ if (ctxp->state != LPFC_NVMET_STE_DONE) {
+ atomic_inc(&lpfc_nvmep->xmt_fcp_drop);
+ lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
+ "6117 Bad state IO x%x aborted\n",
+ ctxp->oxid);
+ }
+
+ lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
+ ctxp->state, 0);
+
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+}
+
static struct nvmet_fc_target_template lpfc_tgttemplate = {
.targetport_delete = lpfc_nvmet_targetport_delete,
.xmt_ls_rsp = lpfc_nvmet_xmt_ls_rsp,
.fcp_op = lpfc_nvmet_xmt_fcp_op,
+ .fcp_abort = lpfc_nvmet_xmt_fcp_abort,
+ .fcp_req_release = lpfc_nvmet_xmt_fcp_release,
.max_hw_queues = 1,
.max_sgl_segments = LPFC_NVMET_DEFAULT_SEGS,
@@ -669,7 +711,9 @@ lpfc_nvmet_create_targetport(struct lpfc_hba *phba)
lpfc_tgttemplate.max_hw_queues = phba->cfg_nvme_io_channel;
lpfc_tgttemplate.max_sgl_segments = phba->cfg_sg_seg_cnt;
lpfc_tgttemplate.target_features = NVMET_FCTGTFEAT_READDATA_RSP |
- NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED;
+ NVMET_FCTGTFEAT_NEEDS_CMD_CPUSCHED |
+ NVMET_FCTGTFEAT_CMD_IN_ISR |
+ NVMET_FCTGTFEAT_OPDONE_IN_ISR;
#if (IS_ENABLED(CONFIG_NVME_TARGET_FC))
error = nvmet_fc_register_targetport(&pinfo, &lpfc_tgttemplate,
@@ -832,6 +876,7 @@ dropit:
ctxp->wqeq = NULL;
ctxp->state = LPFC_NVMET_STE_RCV;
ctxp->rqb_buffer = (void *)nvmebuf;
+ spin_lock_init(&ctxp->ctxlock);
lpfc_nvmeio_data(phba, "NVMET LS RCV: xri x%x sz %d from %06x\n",
oxid, size, sid);
@@ -1593,6 +1638,8 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
uint32_t status, result;
+ unsigned long flags;
+ bool released = false;
ctxp = cmdwqe->context2;
status = bf_get(lpfc_wcqe_c_status, wcqe);
@@ -1607,7 +1654,18 @@ lpfc_nvmet_sol_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
result, wcqe->word3);
ctxp->state = LPFC_NVMET_STE_DONE;
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if (ctxp->flag & LPFC_NVMET_CTX_RLS)
+ released = true;
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
+ /*
+ * if transport has released ctx, then can reuse it. Otherwise,
+ * will be recycled by transport release call.
+ */
+ if (released)
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
cmdwqe->context2 = NULL;
cmdwqe->context3 = NULL;
@@ -1630,7 +1688,9 @@ lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
{
struct lpfc_nvmet_rcv_ctx *ctxp;
struct lpfc_nvmet_tgtport *tgtp;
+ unsigned long flags;
uint32_t status, result;
+ bool released = false;
ctxp = cmdwqe->context2;
status = bf_get(lpfc_wcqe_c_status, wcqe);
@@ -1652,7 +1712,19 @@ lpfc_nvmet_xmt_fcp_abort_cmp(struct lpfc_hba *phba, struct lpfc_iocbq *cmdwqe,
ctxp->state, ctxp->oxid);
}
ctxp->state = LPFC_NVMET_STE_DONE;
- lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+ spin_lock_irqsave(&ctxp->ctxlock, flags);
+ if (ctxp->flag & LPFC_NVMET_CTX_RLS)
+ released = true;
+ ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+ spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
+ /*
+ * if transport has released ctx, then can reuse it. Otherwise,
+ * will be recycled by transport release call.
+ */
+ if (released)
+ lpfc_nvmet_rq_post(phba, ctxp, &ctxp->rqb_buffer->hbuf);
+
cmdwqe->context2 = NULL;
cmdwqe->context3 = NULL;
}
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index ca96f05c1604..02735fc6fd41 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -81,6 +81,7 @@ struct lpfc_nvmet_rcv_ctx {
struct lpfc_iocbq *wqeq;
struct lpfc_iocbq *abort_wqeq;
dma_addr_t txrdy_phys;
+ spinlock_t ctxlock; /* protect flag access */
uint32_t *txrdy;
uint32_t sid;
uint32_t offset;
@@ -97,8 +98,10 @@ struct lpfc_nvmet_rcv_ctx {
#define LPFC_NVMET_STE_RSP 4
#define LPFC_NVMET_STE_DONE 5
uint16_t flag;
-#define LPFC_NVMET_IO_INP 1
-#define LPFC_NVMET_ABORT_OP 2
+#define LPFC_NVMET_IO_INP 0x1
+#define LPFC_NVMET_ABORT_OP 0x2
+#define LPFC_NVMET_CTX_RLS 0x4
+
struct rqb_dmabuf *rqb_buffer;
#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c
index 6903f03c88af..8a1b94816419 100644
--- a/drivers/scsi/osd/osd_initiator.c
+++ b/drivers/scsi/osd/osd_initiator.c
@@ -477,7 +477,7 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
int error)
{
or->async_error = error;
- or->req_errors = req->errors ? : error;
+ or->req_errors = scsi_req(req)->result ? : error;
or->sense_len = scsi_req(req)->sense_len;
if (or->sense_len)
memcpy(or->sense, scsi_req(req)->sense, or->sense_len);
@@ -489,7 +489,10 @@ static void _set_error_resid(struct osd_request *or, struct request *req,
int osd_execute_request(struct osd_request *or)
{
- int error = blk_execute_rq(or->request->q, NULL, or->request, 0);
+ int error;
+
+ blk_execute_rq(or->request->q, NULL, or->request, 0);
+ error = scsi_req(or->request)->result ? -EIO : 0;
_set_error_resid(or, or->request, error);
return error;
@@ -1602,7 +1605,7 @@ static int _init_blk_request(struct osd_request *or,
req->rq_flags |= RQF_QUIET;
req->timeout = or->timeout;
- req->retries = or->retries;
+ scsi_req(req)->retries = or->retries;
if (has_out) {
or->out.req = req;
diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c
index c47f4b349bac..67cbed92f07d 100644
--- a/drivers/scsi/osst.c
+++ b/drivers/scsi/osst.c
@@ -327,7 +327,7 @@ static void osst_end_async(struct request *req, int update)
struct osst_tape *STp = SRpnt->stp;
struct rq_map_data *mdata = &SRpnt->stp->buffer->map_data;
- STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+ STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
#if DEBUG
STp->write_pending = 0;
#endif
@@ -414,7 +414,7 @@ static int osst_execute(struct osst_request *SRpnt, const unsigned char *cmd,
memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
- req->retries = retries;
+ rq->retries = retries;
req->end_io_data = SRpnt;
blk_execute_rq_nowait(req->q, NULL, req, 1, osst_end_async);
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 84c9098cc089..b6e40fd4c3c1 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -2553,13 +2553,13 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
ql_log(ql_log_warn, vha, 0x7089,
"mbx abort_command "
"failed.\n");
- bsg_job->req->errors =
+ scsi_req(bsg_job->req)->result =
bsg_reply->result = -EIO;
} else {
ql_dbg(ql_dbg_user, vha, 0x708a,
"mbx abort_command "
"success.\n");
- bsg_job->req->errors =
+ scsi_req(bsg_job->req)->result =
bsg_reply->result = 0;
}
spin_lock_irqsave(&ha->hardware_lock, flags);
@@ -2570,7 +2570,7 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
}
spin_unlock_irqrestore(&ha->hardware_lock, flags);
ql_log(ql_log_info, vha, 0x708b, "SRB not found to abort.\n");
- bsg_job->req->errors = bsg_reply->result = -ENXIO;
+ scsi_req(bsg_job->req)->result = bsg_reply->result = -ENXIO;
return 0;
done:
diff --git a/drivers/scsi/scsi_debugfs.c b/drivers/scsi/scsi_debugfs.c
new file mode 100644
index 000000000000..a97c9507103d
--- /dev/null
+++ b/drivers/scsi/scsi_debugfs.c
@@ -0,0 +1,13 @@
+#include <linux/seq_file.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_dbg.h>
+#include "scsi_debugfs.h"
+
+void scsi_show_rq(struct seq_file *m, struct request *rq)
+{
+ struct scsi_cmnd *cmd = container_of(scsi_req(rq), typeof(*cmd), req);
+ char buf[80];
+
+ __scsi_format_command(buf, sizeof(buf), cmd->cmnd, cmd->cmd_len);
+ seq_printf(m, ", .cmd=%s", buf);
+}
diff --git a/drivers/scsi/scsi_debugfs.h b/drivers/scsi/scsi_debugfs.h
new file mode 100644
index 000000000000..951b043e82d0
--- /dev/null
+++ b/drivers/scsi/scsi_debugfs.h
@@ -0,0 +1,4 @@
+struct request;
+struct seq_file;
+
+void scsi_show_rq(struct seq_file *m, struct request *rq);
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index f2cafae150bc..2db412dd4b44 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1988,7 +1988,7 @@ static void scsi_eh_lock_door(struct scsi_device *sdev)
req->rq_flags |= RQF_QUIET;
req->timeout = 10 * HZ;
- req->retries = 5;
+ rq->retries = 5;
blk_execute_rq_nowait(req->q, NULL, req, 1, eh_lock_door_done);
}
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 15c9fe766071..1c3e87d6c48f 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -34,6 +34,7 @@
#include <trace/events/scsi.h>
+#include "scsi_debugfs.h"
#include "scsi_priv.h"
#include "scsi_logging.h"
@@ -229,8 +230,8 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
* @rq_flags: flags for ->rq_flags
* @resid: optional residual length
*
- * returns the req->errors value which is the scsi_cmnd result
- * field.
+ * Returns the scsi_cmnd result field if a command was executed, or a negative
+ * Linux error code if we didn't get that far.
*/
int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
int data_direction, void *buffer, unsigned bufflen,
@@ -256,7 +257,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
rq->cmd_len = COMMAND_SIZE(cmd[0]);
memcpy(rq->cmd, cmd, rq->cmd_len);
- req->retries = retries;
+ rq->retries = retries;
req->timeout = timeout;
req->cmd_flags |= flags;
req->rq_flags |= rq_flags | RQF_QUIET | RQF_PREEMPT;
@@ -281,7 +282,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
memcpy(sense, rq->sense, SCSI_SENSE_BUFFERSIZE);
if (sshdr)
scsi_normalize_sense(rq->sense, rq->sense_len, sshdr);
- ret = req->errors;
+ ret = rq->result;
out:
blk_put_request(req);
@@ -797,8 +798,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
/*
* __scsi_error_from_host_byte may have reset the host_byte
*/
- req->errors = cmd->result;
-
+ scsi_req(req)->result = cmd->result;
scsi_req(req)->resid_len = scsi_get_resid(cmd);
if (scsi_bidi_cmnd(cmd)) {
@@ -835,7 +835,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
/*
* Recovered errors need reporting, but they're always treated as
* success, so fiddle the result code here. For passthrough requests
- * we already took a copy of the original into rq->errors which
+ * we already took a copy of the original into sreq->result which
* is what gets returned to the user
*/
if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
@@ -1177,7 +1177,7 @@ static int scsi_setup_scsi_cmnd(struct scsi_device *sdev, struct request *req)
cmd->cmd_len = scsi_req(req)->cmd_len;
cmd->cmnd = scsi_req(req)->cmd;
cmd->transfersize = blk_rq_bytes(req);
- cmd->allowed = req->retries;
+ cmd->allowed = scsi_req(req)->retries;
return BLKPREP_OK;
}
@@ -1281,7 +1281,7 @@ scsi_prep_return(struct request_queue *q, struct request *req, int ret)
switch (ret) {
case BLKPREP_KILL:
case BLKPREP_INVALID:
- req->errors = DID_NO_CONNECT << 16;
+ scsi_req(req)->result = DID_NO_CONNECT << 16;
/* release the command and kill it */
if (req->special) {
struct scsi_cmnd *cmd = req->special;
@@ -1905,7 +1905,7 @@ static int scsi_mq_prep_fn(struct request *req)
static void scsi_mq_done(struct scsi_cmnd *cmd)
{
trace_scsi_dispatch_cmd_done(cmd);
- blk_mq_complete_request(cmd->request, cmd->request->errors);
+ blk_mq_complete_request(cmd->request);
}
static int scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -2154,10 +2154,13 @@ struct request_queue *scsi_alloc_queue(struct scsi_device *sdev)
return q;
}
-static struct blk_mq_ops scsi_mq_ops = {
+static const struct blk_mq_ops scsi_mq_ops = {
.queue_rq = scsi_queue_rq,
.complete = scsi_softirq_done,
.timeout = scsi_timeout,
+#ifdef CONFIG_BLK_DEBUG_FS
+ .show_rq = scsi_show_rq,
+#endif
.init_request = scsi_init_request,
.exit_request = scsi_exit_request,
.map_queues = scsi_map_queues,
diff --git a/drivers/scsi/scsi_transport_sas.c b/drivers/scsi/scsi_transport_sas.c
index cdbb293aca08..9fdbd50c31b4 100644
--- a/drivers/scsi/scsi_transport_sas.c
+++ b/drivers/scsi/scsi_transport_sas.c
@@ -184,9 +184,9 @@ static void sas_smp_request(struct request_queue *q, struct Scsi_Host *shost,
blk_rq_bytes(req->next_rq);
handler = to_sas_internal(shost->transportt)->f->smp_handler;
ret = handler(shost, rphy, req);
- req->errors = ret;
+ scsi_req(req)->result = ret;
- blk_end_request_all(req, ret);
+ blk_end_request_all(req, 0);
spin_lock_irq(q->queue_lock);
}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 35ad5e8a31ab..0dc95e102e69 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -418,6 +418,46 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr,
}
static DEVICE_ATTR_RW(provisioning_mode);
+static const char *zeroing_mode[] = {
+ [SD_ZERO_WRITE] = "write",
+ [SD_ZERO_WS] = "writesame",
+ [SD_ZERO_WS16_UNMAP] = "writesame_16_unmap",
+ [SD_ZERO_WS10_UNMAP] = "writesame_10_unmap",
+};
+
+static ssize_t
+zeroing_mode_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+ return snprintf(buf, 20, "%s\n", zeroing_mode[sdkp->zeroing_mode]);
+}
+
+static ssize_t
+zeroing_mode_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct scsi_disk *sdkp = to_scsi_disk(dev);
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ if (!strncmp(buf, zeroing_mode[SD_ZERO_WRITE], 20))
+ sdkp->zeroing_mode = SD_ZERO_WRITE;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS16_UNMAP], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+ else if (!strncmp(buf, zeroing_mode[SD_ZERO_WS10_UNMAP], 20))
+ sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+ else
+ return -EINVAL;
+
+ return count;
+}
+static DEVICE_ATTR_RW(zeroing_mode);
+
static ssize_t
max_medium_access_timeouts_show(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -496,6 +536,7 @@ static struct attribute *sd_disk_attrs[] = {
&dev_attr_app_tag_own.attr,
&dev_attr_thin_provisioning.attr,
&dev_attr_provisioning_mode.attr,
+ &dev_attr_zeroing_mode.attr,
&dev_attr_max_write_same_blocks.attr,
&dev_attr_max_medium_access_timeouts.attr,
NULL,
@@ -644,26 +685,11 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
unsigned int logical_block_size = sdkp->device->sector_size;
unsigned int max_blocks = 0;
- q->limits.discard_zeroes_data = 0;
-
- /*
- * When LBPRZ is reported, discard alignment and granularity
- * must be fixed to the logical block size. Otherwise the block
- * layer will drop misaligned portions of the request which can
- * lead to data corruption. If LBPRZ is not set, we honor the
- * device preference.
- */
- if (sdkp->lbprz) {
- q->limits.discard_alignment = 0;
- q->limits.discard_granularity = logical_block_size;
- } else {
- q->limits.discard_alignment = sdkp->unmap_alignment *
- logical_block_size;
- q->limits.discard_granularity =
- max(sdkp->physical_block_size,
- sdkp->unmap_granularity * logical_block_size);
- }
-
+ q->limits.discard_alignment =
+ sdkp->unmap_alignment * logical_block_size;
+ q->limits.discard_granularity =
+ max(sdkp->physical_block_size,
+ sdkp->unmap_granularity * logical_block_size);
sdkp->provisioning_mode = mode;
switch (mode) {
@@ -681,19 +707,16 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
case SD_LBP_WS16:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS16_BLOCKS);
- q->limits.discard_zeroes_data = sdkp->lbprz;
break;
case SD_LBP_WS10:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
- q->limits.discard_zeroes_data = sdkp->lbprz;
break;
case SD_LBP_ZERO:
max_blocks = min_not_zero(sdkp->max_ws_blocks,
(u32)SD_MAX_WS10_BLOCKS);
- q->limits.discard_zeroes_data = 1;
break;
}
@@ -701,93 +724,122 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}
-/**
- * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device
- * @sdp: scsi device to operate on
- * @rq: Request to prepare
- *
- * Will issue either UNMAP or WRITE SAME(16) depending on preference
- * indicated by target device.
- **/
-static int sd_setup_discard_cmnd(struct scsi_cmnd *cmd)
+static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd)
{
- struct request *rq = cmd->request;
struct scsi_device *sdp = cmd->device;
- struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
- sector_t sector = blk_rq_pos(rq);
- unsigned int nr_sectors = blk_rq_sectors(rq);
- unsigned int len;
- int ret;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ unsigned int data_len = 24;
char *buf;
- struct page *page;
-
- sector >>= ilog2(sdp->sector_size) - 9;
- nr_sectors >>= ilog2(sdp->sector_size) - 9;
- page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
- if (!page)
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- switch (sdkp->provisioning_mode) {
- case SD_LBP_UNMAP:
- buf = page_address(page);
+ cmd->cmd_len = 10;
+ cmd->cmnd[0] = UNMAP;
+ cmd->cmnd[8] = 24;
- cmd->cmd_len = 10;
- cmd->cmnd[0] = UNMAP;
- cmd->cmnd[8] = 24;
+ buf = page_address(rq->special_vec.bv_page);
+ put_unaligned_be16(6 + 16, &buf[0]);
+ put_unaligned_be16(16, &buf[2]);
+ put_unaligned_be64(sector, &buf[8]);
+ put_unaligned_be32(nr_sectors, &buf[16]);
- put_unaligned_be16(6 + 16, &buf[0]);
- put_unaligned_be16(16, &buf[2]);
- put_unaligned_be64(sector, &buf[8]);
- put_unaligned_be32(nr_sectors, &buf[16]);
+ cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = SD_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- len = 24;
- break;
+ return scsi_init_io(cmd);
+}
- case SD_LBP_WS16:
- cmd->cmd_len = 16;
- cmd->cmnd[0] = WRITE_SAME_16;
+static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+ struct scsi_device *sdp = cmd->device;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 data_len = sdp->sector_size;
+
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
+ return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
+
+ cmd->cmd_len = 16;
+ cmd->cmnd[0] = WRITE_SAME_16;
+ if (unmap)
cmd->cmnd[1] = 0x8; /* UNMAP */
- put_unaligned_be64(sector, &cmd->cmnd[2]);
- put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
+ put_unaligned_be64(sector, &cmd->cmnd[2]);
+ put_unaligned_be32(nr_sectors, &cmd->cmnd[10]);
- len = sdkp->device->sector_size;
- break;
+ cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- case SD_LBP_WS10:
- case SD_LBP_ZERO:
- cmd->cmd_len = 10;
- cmd->cmnd[0] = WRITE_SAME;
- if (sdkp->provisioning_mode == SD_LBP_WS10)
- cmd->cmnd[1] = 0x8; /* UNMAP */
- put_unaligned_be32(sector, &cmd->cmnd[2]);
- put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
+ return scsi_init_io(cmd);
+}
- len = sdkp->device->sector_size;
- break;
+static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap)
+{
+ struct scsi_device *sdp = cmd->device;
+ struct request *rq = cmd->request;
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 data_len = sdp->sector_size;
- default:
- ret = BLKPREP_INVALID;
- goto out;
- }
+ rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!rq->special_vec.bv_page)
+ return BLKPREP_DEFER;
+ rq->special_vec.bv_offset = 0;
+ rq->special_vec.bv_len = data_len;
+ rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- rq->timeout = SD_TIMEOUT;
+ cmd->cmd_len = 10;
+ cmd->cmnd[0] = WRITE_SAME;
+ if (unmap)
+ cmd->cmnd[1] = 0x8; /* UNMAP */
+ put_unaligned_be32(sector, &cmd->cmnd[2]);
+ put_unaligned_be16(nr_sectors, &cmd->cmnd[7]);
- cmd->transfersize = len;
cmd->allowed = SD_MAX_RETRIES;
+ cmd->transfersize = data_len;
+ rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT;
+ scsi_req(rq)->resid_len = data_len;
- rq->special_vec.bv_page = page;
- rq->special_vec.bv_offset = 0;
- rq->special_vec.bv_len = len;
+ return scsi_init_io(cmd);
+}
- rq->rq_flags |= RQF_SPECIAL_PAYLOAD;
- scsi_req(rq)->resid_len = len;
+static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd)
+{
+ struct request *rq = cmd->request;
+ struct scsi_device *sdp = cmd->device;
+ struct scsi_disk *sdkp = scsi_disk(rq->rq_disk);
+ u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9);
+ u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9);
+
+ if (!(rq->cmd_flags & REQ_NOUNMAP)) {
+ switch (sdkp->zeroing_mode) {
+ case SD_ZERO_WS16_UNMAP:
+ return sd_setup_write_same16_cmnd(cmd, true);
+ case SD_ZERO_WS10_UNMAP:
+ return sd_setup_write_same10_cmnd(cmd, true);
+ }
+ }
- ret = scsi_init_io(cmd);
-out:
- if (ret != BLKPREP_OK)
- __free_page(page);
- return ret;
+ if (sdp->no_write_same)
+ return BLKPREP_INVALID;
+ if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff)
+ return sd_setup_write_same16_cmnd(cmd, false);
+ return sd_setup_write_same10_cmnd(cmd, false);
}
static void sd_config_write_same(struct scsi_disk *sdkp)
@@ -816,9 +868,20 @@ static void sd_config_write_same(struct scsi_disk *sdkp)
sdkp->max_ws_blocks = 0;
}
+ if (sdkp->lbprz && sdkp->lbpws)
+ sdkp->zeroing_mode = SD_ZERO_WS16_UNMAP;
+ else if (sdkp->lbprz && sdkp->lbpws10)
+ sdkp->zeroing_mode = SD_ZERO_WS10_UNMAP;
+ else if (sdkp->max_ws_blocks)
+ sdkp->zeroing_mode = SD_ZERO_WS;
+ else
+ sdkp->zeroing_mode = SD_ZERO_WRITE;
+
out:
blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks *
(logical_block_size >> 9));
+ blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks *
+ (logical_block_size >> 9));
}
/**
@@ -1155,7 +1218,20 @@ static int sd_init_command(struct scsi_cmnd *cmd)
switch (req_op(rq)) {
case REQ_OP_DISCARD:
- return sd_setup_discard_cmnd(cmd);
+ switch (scsi_disk(rq->rq_disk)->provisioning_mode) {
+ case SD_LBP_UNMAP:
+ return sd_setup_unmap_cmnd(cmd);
+ case SD_LBP_WS16:
+ return sd_setup_write_same16_cmnd(cmd, true);
+ case SD_LBP_WS10:
+ return sd_setup_write_same10_cmnd(cmd, true);
+ case SD_LBP_ZERO:
+ return sd_setup_write_same10_cmnd(cmd, false);
+ default:
+ return BLKPREP_INVALID;
+ }
+ case REQ_OP_WRITE_ZEROES:
+ return sd_setup_write_zeroes_cmnd(cmd);
case REQ_OP_WRITE_SAME:
return sd_setup_write_same_cmnd(cmd);
case REQ_OP_FLUSH:
@@ -1795,6 +1871,7 @@ static int sd_done(struct scsi_cmnd *SCpnt)
switch (req_op(req)) {
case REQ_OP_DISCARD:
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
if (!result) {
@@ -2768,7 +2845,7 @@ static void sd_read_block_limits(struct scsi_disk *sdkp)
sd_config_discard(sdkp, SD_LBP_WS16);
} else { /* LBP VPD page tells us what to use */
- if (sdkp->lbpu && sdkp->max_unmap_blocks && !sdkp->lbprz)
+ if (sdkp->lbpu && sdkp->max_unmap_blocks)
sd_config_discard(sdkp, SD_LBP_UNMAP);
else if (sdkp->lbpws)
sd_config_discard(sdkp, SD_LBP_WS16);
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 4dac35e96a75..a2c4b5c35379 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -59,6 +59,13 @@ enum {
SD_LBP_DISABLE, /* Discard disabled due to failed cmd */
};
+enum {
+ SD_ZERO_WRITE = 0, /* Use WRITE(10/16) command */
+ SD_ZERO_WS, /* Use WRITE SAME(10/16) command */
+ SD_ZERO_WS16_UNMAP, /* Use WRITE SAME(16) with UNMAP */
+ SD_ZERO_WS10_UNMAP, /* Use WRITE SAME(10) with UNMAP */
+};
+
struct scsi_disk {
struct scsi_driver *driver; /* always &sd_template */
struct scsi_device *device;
@@ -89,6 +96,7 @@ struct scsi_disk {
u8 write_prot;
u8 protection_type;/* Data Integrity Field */
u8 provisioning_mode;
+ u8 zeroing_mode;
unsigned ATO : 1; /* state of disk ATO bit */
unsigned cache_override : 1; /* temp override of WCE,RCD */
unsigned WCE : 1; /* state of disk WCE bit */
diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index 92620c8ea8ad..1994f7799fce 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -329,6 +329,7 @@ void sd_zbc_complete(struct scsi_cmnd *cmd,
switch (req_op(rq)) {
case REQ_OP_WRITE:
+ case REQ_OP_WRITE_ZEROES:
case REQ_OP_WRITE_SAME:
case REQ_OP_ZONE_RESET:
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 225abaad4d1c..504504beaa5e 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1300,7 +1300,7 @@ sg_rq_end_io(struct request *rq, int uptodate)
pr_info("%s: device detaching\n", __func__);
sense = req->sense;
- result = rq->errors;
+ result = req->result;
resid = req->resid_len;
SCSI_LOG_TIMEOUT(4, sg_printk(KERN_INFO, sdp,
@@ -1718,7 +1718,7 @@ sg_start_req(Sg_request *srp, unsigned char *cmd)
srp->rq = rq;
rq->end_io_data = srp;
- rq->retries = SG_DEFAULT_RETRIES;
+ req->retries = SG_DEFAULT_RETRIES;
if ((dxfer_len <= 0) || (dxfer_dir == SG_DXFER_NONE))
return 0;
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index e5ef78a6848e..1ea34d6f5437 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -480,7 +480,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
atomic64_add(ktime_to_ns(now), &STp->stats->tot_write_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
atomic64_inc(&STp->stats->write_cnt);
- if (req->errors) {
+ if (scsi_req(req)->result) {
atomic64_add(atomic_read(&STp->stats->last_write_size)
- STp->buffer->cmdstat.residual,
&STp->stats->write_byte_cnt);
@@ -494,7 +494,7 @@ static void st_do_stats(struct scsi_tape *STp, struct request *req)
atomic64_add(ktime_to_ns(now), &STp->stats->tot_read_time);
atomic64_add(ktime_to_ns(now), &STp->stats->tot_io_time);
atomic64_inc(&STp->stats->read_cnt);
- if (req->errors) {
+ if (scsi_req(req)->result) {
atomic64_add(atomic_read(&STp->stats->last_read_size)
- STp->buffer->cmdstat.residual,
&STp->stats->read_byte_cnt);
@@ -518,7 +518,7 @@ static void st_scsi_execute_end(struct request *req, int uptodate)
struct scsi_tape *STp = SRpnt->stp;
struct bio *tmp;
- STp->buffer->cmdstat.midlevel_result = SRpnt->result = req->errors;
+ STp->buffer->cmdstat.midlevel_result = SRpnt->result = rq->result;
STp->buffer->cmdstat.residual = rq->resid_len;
st_do_stats(STp, req);
@@ -579,7 +579,7 @@ static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd,
memset(rq->cmd, 0, BLK_MAX_CDB);
memcpy(rq->cmd, cmd, rq->cmd_len);
req->timeout = timeout;
- req->retries = retries;
+ rq->retries = retries;
req->end_io_data = SRpnt;
blk_execute_rq_nowait(req->q, NULL, req, 1, st_scsi_execute_end);
diff --git a/drivers/staging/lustre/lustre/include/lustre_disk.h b/drivers/staging/lustre/lustre/include/lustre_disk.h
index 8886458748c1..a676bccabd43 100644
--- a/drivers/staging/lustre/lustre/include/lustre_disk.h
+++ b/drivers/staging/lustre/lustre/include/lustre_disk.h
@@ -133,13 +133,9 @@ struct lustre_sb_info {
struct obd_export *lsi_osd_exp;
char lsi_osd_type[16];
char lsi_fstype[16];
- struct backing_dev_info lsi_bdi; /* each client mountpoint needs
- * own backing_dev_info
- */
};
#define LSI_UMOUNT_FAILOVER 0x00200000
-#define LSI_BDI_INITIALIZED 0x00400000
#define s2lsi(sb) ((struct lustre_sb_info *)((sb)->s_fs_info))
#define s2lsi_nocast(sb) ((sb)->s_fs_info)
diff --git a/drivers/staging/lustre/lustre/llite/llite_lib.c b/drivers/staging/lustre/lustre/llite/llite_lib.c
index b229cbc7bb33..d483c44aafe5 100644
--- a/drivers/staging/lustre/lustre/llite/llite_lib.c
+++ b/drivers/staging/lustre/lustre/llite/llite_lib.c
@@ -863,15 +863,6 @@ void ll_lli_init(struct ll_inode_info *lli)
mutex_init(&lli->lli_layout_mutex);
}
-static inline int ll_bdi_register(struct backing_dev_info *bdi)
-{
- static atomic_t ll_bdi_num = ATOMIC_INIT(0);
-
- bdi->name = "lustre";
- return bdi_register(bdi, NULL, "lustre-%d",
- atomic_inc_return(&ll_bdi_num));
-}
-
int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
{
struct lustre_profile *lprof = NULL;
@@ -881,6 +872,7 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
char *profilenm = get_profile_name(sb);
struct config_llog_instance *cfg;
int err;
+ static atomic_t ll_bdi_num = ATOMIC_INIT(0);
CDEBUG(D_VFSTRACE, "VFS Op: sb %p\n", sb);
@@ -903,16 +895,11 @@ int ll_fill_super(struct super_block *sb, struct vfsmount *mnt)
if (err)
goto out_free;
- err = bdi_init(&lsi->lsi_bdi);
- if (err)
- goto out_free;
- lsi->lsi_flags |= LSI_BDI_INITIALIZED;
- lsi->lsi_bdi.capabilities = 0;
- err = ll_bdi_register(&lsi->lsi_bdi);
+ err = super_setup_bdi_name(sb, "lustre-%d",
+ atomic_inc_return(&ll_bdi_num));
if (err)
goto out_free;
- sb->s_bdi = &lsi->lsi_bdi;
/* kernel >= 2.6.38 store dentry operations in sb->s_d_op. */
sb->s_d_op = &ll_d_ops;
@@ -1033,11 +1020,6 @@ void ll_put_super(struct super_block *sb)
if (profilenm)
class_del_profile(profilenm);
- if (lsi->lsi_flags & LSI_BDI_INITIALIZED) {
- bdi_destroy(&lsi->lsi_bdi);
- lsi->lsi_flags &= ~LSI_BDI_INITIALIZED;
- }
-
ll_free_sbi(sb);
lsi->lsi_llsbi = NULL;
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 344e8448869c..5798810197ec 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -167,10 +167,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
struct iscsi_portal_group *tpg;
struct iscsi_tpg_np *tpg_np;
char *str, *str2, *ip_str, *port_str;
- struct sockaddr_storage sockaddr;
- struct sockaddr_in *sock_in;
- struct sockaddr_in6 *sock_in6;
- unsigned long port;
+ struct sockaddr_storage sockaddr = { };
int ret;
char buf[MAX_PORTAL_LEN + 1];
@@ -182,21 +179,19 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
memset(buf, 0, MAX_PORTAL_LEN + 1);
snprintf(buf, MAX_PORTAL_LEN + 1, "%s", name);
- memset(&sockaddr, 0, sizeof(struct sockaddr_storage));
-
str = strstr(buf, "[");
if (str) {
- const char *end;
-
str2 = strstr(str, "]");
if (!str2) {
pr_err("Unable to locate trailing \"]\""
" in IPv6 iSCSI network portal address\n");
return ERR_PTR(-EINVAL);
}
- str++; /* Skip over leading "[" */
+
+ ip_str = str + 1; /* Skip over leading "[" */
*str2 = '\0'; /* Terminate the unbracketed IPv6 address */
str2++; /* Skip over the \0 */
+
port_str = strstr(str2, ":");
if (!port_str) {
pr_err("Unable to locate \":port\""
@@ -205,23 +200,8 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
}
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
-
- ret = kstrtoul(port_str, 0, &port);
- if (ret < 0) {
- pr_err("kstrtoul() failed for port_str: %d\n", ret);
- return ERR_PTR(ret);
- }
- sock_in6 = (struct sockaddr_in6 *)&sockaddr;
- sock_in6->sin6_family = AF_INET6;
- sock_in6->sin6_port = htons((unsigned short)port);
- ret = in6_pton(str, -1,
- (void *)&sock_in6->sin6_addr.in6_u, -1, &end);
- if (ret <= 0) {
- pr_err("in6_pton returned: %d\n", ret);
- return ERR_PTR(-EINVAL);
- }
} else {
- str = ip_str = &buf[0];
+ ip_str = &buf[0];
port_str = strstr(ip_str, ":");
if (!port_str) {
pr_err("Unable to locate \":port\""
@@ -230,17 +210,15 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
}
*port_str = '\0'; /* Terminate string for IP */
port_str++; /* Skip over ":" */
+ }
- ret = kstrtoul(port_str, 0, &port);
- if (ret < 0) {
- pr_err("kstrtoul() failed for port_str: %d\n", ret);
- return ERR_PTR(ret);
- }
- sock_in = (struct sockaddr_in *)&sockaddr;
- sock_in->sin_family = AF_INET;
- sock_in->sin_port = htons((unsigned short)port);
- sock_in->sin_addr.s_addr = in_aton(ip_str);
+ ret = inet_pton_with_scope(&init_net, AF_UNSPEC, ip_str,
+ port_str, &sockaddr);
+ if (ret) {
+ pr_err("malformed ip/port passed: %s\n", name);
+ return ERR_PTR(ret);
}
+
tpg = container_of(se_tpg, struct iscsi_portal_group, tpg_se_tpg);
ret = iscsit_get_tpg(tpg);
if (ret < 0)
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index c754ae33bf7b..d2f089cfa9ae 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -851,7 +851,7 @@ bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
attrib->unmap_granularity = q->limits.discard_granularity / block_size;
attrib->unmap_granularity_alignment = q->limits.discard_alignment /
block_size;
- attrib->unmap_zeroes_data = q->limits.discard_zeroes_data;
+ attrib->unmap_zeroes_data = 0;
return true;
}
EXPORT_SYMBOL(target_configure_unmap_from_queue);
diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c
index 94cda7991e80..a93d94e68ab5 100644
--- a/drivers/target/target_core_pscsi.c
+++ b/drivers/target/target_core_pscsi.c
@@ -1008,7 +1008,7 @@ pscsi_execute_cmd(struct se_cmd *cmd)
req->timeout = PS_TIMEOUT_DISK;
else
req->timeout = PS_TIMEOUT_OTHER;
- req->retries = PS_RETRY;
+ scsi_req(req)->retries = PS_RETRY;
blk_execute_rq_nowait(pdv->pdv_sd->request_queue, NULL, req,
(cmd->sam_task_attr == TCM_HEAD_TAG),
@@ -1050,7 +1050,7 @@ static void pscsi_req_done(struct request *req, int uptodate)
struct se_cmd *cmd = req->end_io_data;
struct pscsi_plugin_task *pt = cmd->priv;
- pt->pscsi_result = req->errors;
+ pt->pscsi_result = scsi_req(req)->result;
pt->pscsi_resid = scsi_req(req)->resid_len;
cmd->scsi_status = status_byte(pt->pscsi_result) << 1;